337 files changed, 10531 insertions, 5847 deletions

diff --git a/arch/arm/mach-davinci/time.c b/arch/arm/mach-davinci/time.c
index 4d8425de6922..e96a3dcdc1a7 100644
--- a/arch/arm/mach-davinci/time.c
+++ b/arch/arm/mach-davinci/time.c
@@ -285,6 +285,8 @@ static void davinci_set_mode(enum clock_event_mode mode,
         case CLOCK_EVT_MODE_SHUTDOWN:
                 t->opts = TIMER_OPTS_DISABLED;
                 break;
+        case CLOCK_EVT_MODE_RESUME:
+                break;
         }
 }
 
diff --git a/arch/arm/mach-imx/time.c b/arch/arm/mach-imx/time.c
index 010f6fa984a6..d86d124aea22 100644
--- a/arch/arm/mach-imx/time.c
+++ b/arch/arm/mach-imx/time.c
@@ -159,6 +159,7 @@ static void imx_set_mode(enum clock_event_mode mode, struct clock_event_device *
                 break;
         case CLOCK_EVT_MODE_SHUTDOWN:
         case CLOCK_EVT_MODE_UNUSED:
+        case CLOCK_EVT_MODE_RESUME:
                 /* Left event sources disabled, no more interrupts appears */
                 break;
         }
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index 4c54a86eda3a..c1271c449246 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -459,6 +459,8 @@ static void ixp4xx_set_mode(enum clock_event_mode mode,
         default:
                 osrt = opts = 0;
                 break;
+        case CLOCK_EVT_MODE_RESUME:
+                break;
         }
 
         *IXP4XX_OSRT1 = osrt | opts;
diff --git a/arch/arm/mach-omap1/time.c b/arch/arm/mach-omap1/time.c
index 3705d20c4e5c..237651ebae5d 100644
--- a/arch/arm/mach-omap1/time.c
+++ b/arch/arm/mach-omap1/time.c
@@ -156,6 +156,7 @@ static void omap_mpu_set_mode(enum clock_event_mode mode,
                 break;
         case CLOCK_EVT_MODE_UNUSED:
         case CLOCK_EVT_MODE_SHUTDOWN:
+        case CLOCK_EVT_MODE_RESUME:
                 break;
         }
 }
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index c04124a095cf..846cce48e2b7 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -145,8 +145,8 @@ void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
                 __do_kernel_fault(mm, addr, fsr, regs);
 }
 
-#define VM_FAULT_BADMAP         (-20)
-#define VM_FAULT_BADACCESS      (-21)
+#define VM_FAULT_BADMAP         0x010000
+#define VM_FAULT_BADACCESS      0x020000
 
 static int
 __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
@@ -249,7 +249,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
         /*
          * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
          */
-        if (likely(!(fault & VM_FAULT_ERROR)))
+        if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
                 return 0;
 
         /*
diff --git a/arch/arm/plat-omap/timer32k.c b/arch/arm/plat-omap/timer32k.c
index 2feceec8eccd..b0af014b0e2c 100644
--- a/arch/arm/plat-omap/timer32k.c
+++ b/arch/arm/plat-omap/timer32k.c
@@ -156,6 +156,8 @@ static void omap_32k_timer_set_mode(enum clock_event_mode mode,
         case CLOCK_EVT_MODE_SHUTDOWN:
                 omap_32k_timer_stop();
                 break;
+        case CLOCK_EVT_MODE_RESUME:
+                break;
         }
 }
 
diff --git a/arch/avr32/boards/atngw100/setup.c b/arch/avr32/boards/atngw100/setup.c
index 6c4dc0a00e9f..2edcecdea8bd 100644
--- a/arch/avr32/boards/atngw100/setup.c
+++ b/arch/avr32/boards/atngw100/setup.c
@@ -13,6 +13,7 @@
 #include <linux/linkage.h>
 #include <linux/platform_device.h>
 #include <linux/types.h>
+#include <linux/leds.h>
 #include <linux/spi/spi.h>
 
 #include <asm/io.h>
@@ -21,6 +22,7 @@
 #include <asm/arch/at32ap7000.h>
 #include <asm/arch/board.h>
 #include <asm/arch/init.h>
+#include <asm/arch/portmux.h>
 
 /* Initialized by bootloader-specific startup code. */
 struct tag *bootloader_tags __initdata;
@@ -100,8 +102,31 @@ void __init setup_board(void)
         at32_setup_serial_console(0);
 }
 
+static const struct gpio_led ngw_leds[] = {
+        { .name = "sys", .gpio = GPIO_PIN_PA(16), .active_low = 1,
+                .default_trigger = "heartbeat",
+        },
+        { .name = "a", .gpio = GPIO_PIN_PA(19), .active_low = 1, },
+        { .name = "b", .gpio = GPIO_PIN_PE(19), .active_low = 1, },
+};
+
+static const struct gpio_led_platform_data ngw_led_data = {
+        .num_leds =     ARRAY_SIZE(ngw_leds),
+        .leds =         (void *) ngw_leds,
+};
+
+static struct platform_device ngw_gpio_leds = {
+        .name =         "leds-gpio",
+        .id =           -1,
+        .dev = {
+                .platform_data = (void *) &ngw_led_data,
+        }
+};
+
 static int __init atngw100_init(void)
 {
+        unsigned        i;
+
         /*
          * ATNGW100 uses 16-bit SDRAM interface, so we don't need to
          * reserve any pins for it.
@@ -116,6 +141,12 @@ static int __init atngw100_init(void)
 
         at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
 
+        for (i = 0; i < ARRAY_SIZE(ngw_leds); i++) {
+                at32_select_gpio(ngw_leds[i].gpio,
+                                AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
+        }
+        platform_device_register(&ngw_gpio_leds);
+
         return 0;
 }
 postcore_initcall(atngw100_init);
diff --git a/arch/avr32/configs/atngw100_defconfig b/arch/avr32/configs/atngw100_defconfig
index 49493ad3b5a9..b799a68ffd97 100644
--- a/arch/avr32/configs/atngw100_defconfig
+++ b/arch/avr32/configs/atngw100_defconfig
@@ -712,7 +712,21 @@ CONFIG_SPI_ATMEL=y
 #
 # LED devices
 #
-# CONFIG_NEW_LEDS is not set
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+
+#
+# LED drivers
+#
+CONFIG_LEDS_GPIO=y
+
+#
+# LED Triggers
+#
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_TIMER=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+
 
 #
 # LED drivers
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index 7a11b905ef49..abb582bc218f 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -18,6 +18,10 @@ config GENERIC_TIME
         bool
         default y
 
+config GENERIC_CMOS_UPDATE
+        bool
+        default y
+
 config CLOCKSOURCE_WATCHDOG
         bool
         default y
@@ -544,6 +548,7 @@ config HIGHMEM4G
 config HIGHMEM64G
         bool "64GB"
         depends on !M386 && !M486
+        select X86_PAE
         help
           Select this if you have a 32-bit processor and more than 4
           gigabytes of physical RAM.
@@ -573,12 +578,12 @@ choice
         config VMSPLIT_3G
                 bool "3G/1G user/kernel split"
         config VMSPLIT_3G_OPT
-                depends on !HIGHMEM
+                depends on !X86_PAE
                 bool "3G/1G user/kernel split (for full 1G low memory)"
         config VMSPLIT_2G
                 bool "2G/2G user/kernel split"
         config VMSPLIT_2G_OPT
-                depends on !HIGHMEM
+                depends on !X86_PAE
                 bool "2G/2G user/kernel split (for full 2G low memory)"
         config VMSPLIT_1G
                 bool "1G/3G user/kernel split"
@@ -598,10 +603,15 @@ config HIGHMEM
         default y
 
 config X86_PAE
-        bool
-        depends on HIGHMEM64G
-        default y
+        bool "PAE (Physical Address Extension) Support"
+        default n
+        depends on !HIGHMEM4G
         select RESOURCES_64BIT
+        help
+          PAE is required for NX support, and furthermore enables
+          larger swapspace support for non-overcommit purposes. It
+          has the cost of more pagetable lookup overhead, and also
+          consumes more pagetable space per process.
 
 # Common NUMA Features
 config NUMA
@@ -817,6 +827,7 @@ config CRASH_DUMP
 
 config PHYSICAL_START
         hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP)
+        default "0x1000000" if X86_NUMAQ
         default "0x100000"
         help
           This gives the physical address where the kernel is loaded.
diff --git a/arch/i386/boot/compressed/relocs.c b/arch/i386/boot/compressed/relocs.c
index b0e21c3cee5c..2d77ee728f92 100644
--- a/arch/i386/boot/compressed/relocs.c
+++ b/arch/i386/boot/compressed/relocs.c
@@ -31,6 +31,7 @@ static const char* safe_abs_relocs[] = {
                 "__kernel_rt_sigreturn",
                 "__kernel_sigreturn",
                 "SYSENTER_RETURN",
+                "VDSO_NOTE_MASK",
                 "xen_irq_disable_direct_reloc",
                 "xen_save_fl_direct_reloc",
 };
diff --git a/arch/i386/defconfig b/arch/i386/defconfig
index 0ac62cdcd3b7..54ee1764fdae 100644
--- a/arch/i386/defconfig
+++ b/arch/i386/defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.22-rc2
-# Mon May 21 13:23:44 2007
+# Linux kernel version: 2.6.22-git14
+# Fri Jul 20 09:53:15 2007
 #
 CONFIG_X86_32=y
 CONFIG_GENERIC_TIME=y
@@ -37,19 +37,18 @@ CONFIG_LOCALVERSION=""
 CONFIG_LOCALVERSION_AUTO=y
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
-# CONFIG_IPC_NS is not set
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
-# CONFIG_UTS_NS is not set
+# CONFIG_USER_NS is not set
 # CONFIG_AUDIT is not set
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=18
 # CONFIG_CPUSETS is not set
 CONFIG_SYSFS_DEPRECATED=y
-# CONFIG_RELAY is not set
+CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE=""
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
@@ -73,16 +72,13 @@ CONFIG_TIMERFD=y
 CONFIG_EVENTFD=y
 CONFIG_SHMEM=y
 CONFIG_VM_EVENT_COUNTERS=y
-CONFIG_SLAB=y
-# CONFIG_SLUB is not set
+CONFIG_SLUB_DEBUG=y
+# CONFIG_SLAB is not set
+CONFIG_SLUB=y
 # CONFIG_SLOB is not set
 CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
-
-#
-# Loadable module support
-#
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
@@ -90,14 +86,11 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 # CONFIG_KMOD is not set
 CONFIG_STOP_MACHINE=y
-
-#
-# Block layer
-#
 CONFIG_BLOCK=y
 CONFIG_LBD=y
 # CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_LSF is not set
+# CONFIG_BLK_DEV_BSG is not set
 
 #
 # IO Schedulers
@@ -201,6 +194,7 @@ CONFIG_X86_CPUID=y
 # CONFIG_EDD is not set
 # CONFIG_DELL_RBU is not set
 # CONFIG_DCDBAS is not set
+CONFIG_DMIID=y
 # CONFIG_NOHIGHMEM is not set
 CONFIG_HIGHMEM4G=y
 # CONFIG_HIGHMEM64G is not set
@@ -217,7 +211,9 @@ CONFIG_FLAT_NODE_MEM_MAP=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
 CONFIG_RESOURCES_64BIT=y
 CONFIG_ZONE_DMA_FLAG=1
+CONFIG_BOUNCE=y
 CONFIG_NR_QUICK=1
+CONFIG_VIRT_TO_BUS=y
 # CONFIG_HIGHPTE is not set
 # CONFIG_MATH_EMULATION is not set
 CONFIG_MTRR=y
@@ -244,7 +240,6 @@ CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
 CONFIG_PM=y
 CONFIG_PM_LEGACY=y
 # CONFIG_PM_DEBUG is not set
-# CONFIG_PM_SYSFS_DEPRECATED is not set
 
 #
 # ACPI (Advanced Configuration and Power Interface) Support
@@ -284,7 +279,7 @@ CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 # CONFIG_CPU_FREQ_GOV_POWERSAVE is not set
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
-# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set
+CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
 
 #
 # CPUFreq processor drivers
@@ -325,7 +320,7 @@ CONFIG_PCI_MMCONFIG=y
 CONFIG_ARCH_SUPPORTS_MSI=y
 CONFIG_PCI_MSI=y
 # CONFIG_PCI_DEBUG is not set
-CONFIG_HT_IRQ=y
+# CONFIG_HT_IRQ is not set
 CONFIG_ISA_DMA_API=y
 # CONFIG_ISA is not set
 # CONFIG_MCA is not set
@@ -381,7 +376,7 @@ CONFIG_IP_PNP_DHCP=y
 CONFIG_INET_TUNNEL=y
 CONFIG_INET_XFRM_MODE_TRANSPORT=y
 CONFIG_INET_XFRM_MODE_TUNNEL=y
-CONFIG_INET_XFRM_MODE_BEET=y
+# CONFIG_INET_XFRM_MODE_BEET is not set
 CONFIG_INET_DIAG=y
 CONFIG_INET_TCP_DIAG=y
 # CONFIG_TCP_CONG_ADVANCED is not set
@@ -400,27 +395,15 @@ CONFIG_IPV6=y
 # CONFIG_INET6_TUNNEL is not set
 CONFIG_INET6_XFRM_MODE_TRANSPORT=y
 CONFIG_INET6_XFRM_MODE_TUNNEL=y
-CONFIG_INET6_XFRM_MODE_BEET=y
+# CONFIG_INET6_XFRM_MODE_BEET is not set
 # CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set
 CONFIG_IPV6_SIT=y
 # CONFIG_IPV6_TUNNEL is not set
 # CONFIG_IPV6_MULTIPLE_TABLES is not set
 # CONFIG_NETWORK_SECMARK is not set
 # CONFIG_NETFILTER is not set
-
-#
-# DCCP Configuration (EXPERIMENTAL)
-#
 # CONFIG_IP_DCCP is not set
-
-#
-# SCTP Configuration (EXPERIMENTAL)
-#
 # CONFIG_IP_SCTP is not set
-
-#
-# TIPC Configuration (EXPERIMENTAL)
-#
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
 # CONFIG_BRIDGE is not set
@@ -457,6 +440,7 @@ CONFIG_IPV6_SIT=y
 # CONFIG_MAC80211 is not set
 # CONFIG_IEEE80211 is not set
 # CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
 
 #
 # Device Drivers
@@ -471,21 +455,9 @@ CONFIG_FW_LOADER=y
 # CONFIG_DEBUG_DRIVER is not set
 # CONFIG_DEBUG_DEVRES is not set
 # CONFIG_SYS_HYPERVISOR is not set
-
-#
-# Connector - unified userspace <-> kernelspace linker
-#
 # CONFIG_CONNECTOR is not set
 # CONFIG_MTD is not set
-
-#
-# Parallel port support
-#
 # CONFIG_PARPORT is not set
-
-#
-# Plug and Play support
-#
 CONFIG_PNP=y
 # CONFIG_PNP_DEBUG is not set
 
@@ -493,10 +465,7 @@ CONFIG_PNP=y
 # Protocols
 #
 CONFIG_PNPACPI=y
-
-#
-# Block devices
-#
+CONFIG_BLK_DEV=y
 CONFIG_BLK_DEV_FD=y
 # CONFIG_BLK_CPQ_DA is not set
 # CONFIG_BLK_CPQ_CISS_DA is not set
@@ -514,17 +483,14 @@ CONFIG_BLK_DEV_RAM_SIZE=4096
 CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
 # CONFIG_CDROM_PKTCDVD is not set
 # CONFIG_ATA_OVER_ETH is not set
-
-#
-# Misc devices
-#
+CONFIG_MISC_DEVICES=y
 # CONFIG_IBM_ASM is not set
 # CONFIG_PHANTOM is not set
+# CONFIG_EEPROM_93CX6 is not set
 # CONFIG_SGI_IOC4 is not set
 # CONFIG_TIFM_CORE is not set
 # CONFIG_SONY_LAPTOP is not set
 # CONFIG_THINKPAD_ACPI is not set
-# CONFIG_BLINK is not set
 CONFIG_IDE=y
 CONFIG_BLK_DEV_IDE=y
 
@@ -596,6 +562,7 @@ CONFIG_BLK_DEV_IDEDMA=y
 #
 # CONFIG_RAID_ATTRS is not set
 CONFIG_SCSI=y
+CONFIG_SCSI_DMA=y
 # CONFIG_SCSI_TGT is not set
 CONFIG_SCSI_NETLINK=y
 # CONFIG_SCSI_PROC_FS is not set
@@ -606,8 +573,9 @@ CONFIG_SCSI_NETLINK=y
 CONFIG_BLK_DEV_SD=y
 # CONFIG_CHR_DEV_ST is not set
 # CONFIG_CHR_DEV_OSST is not set
-# CONFIG_BLK_DEV_SR is not set
-# CONFIG_CHR_DEV_SG is not set
+CONFIG_BLK_DEV_SR=y
+# CONFIG_BLK_DEV_SR_VENDOR is not set
+CONFIG_CHR_DEV_SG=y
 # CONFIG_CHR_DEV_SCH is not set
 
 #
@@ -667,6 +635,7 @@ CONFIG_AIC79XX_DEBUG_MASK=0
 # CONFIG_SCSI_INIA100 is not set
 # CONFIG_SCSI_STEX is not set
 # CONFIG_SCSI_SYM53C8XX_2 is not set
+# CONFIG_SCSI_IPR is not set
 # CONFIG_SCSI_QLOGIC_1280 is not set
 # CONFIG_SCSI_QLA_FC is not set
 # CONFIG_SCSI_QLA_ISCSI is not set
@@ -675,14 +644,73 @@ CONFIG_AIC79XX_DEBUG_MASK=0
 # CONFIG_SCSI_DC390T is not set
 # CONFIG_SCSI_NSP32 is not set
 # CONFIG_SCSI_DEBUG is not set
-# CONFIG_SCSI_ESP_CORE is not set
 # CONFIG_SCSI_SRP is not set
-# CONFIG_ATA is not set
-
-#
-# Multi-device support (RAID and LVM)
-#
-# CONFIG_MD is not set
+CONFIG_ATA=y
+# CONFIG_ATA_NONSTANDARD is not set
+CONFIG_ATA_ACPI=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_SVW=y
+CONFIG_ATA_PIIX=y
+# CONFIG_SATA_MV is not set
+CONFIG_SATA_NV=y
+# CONFIG_PDC_ADMA is not set
+# CONFIG_SATA_QSTOR is not set
+# CONFIG_SATA_PROMISE is not set
+# CONFIG_SATA_SX4 is not set
+CONFIG_SATA_SIL=y
+# CONFIG_SATA_SIL24 is not set
+# CONFIG_SATA_SIS is not set
+# CONFIG_SATA_ULI is not set
+CONFIG_SATA_VIA=y
+# CONFIG_SATA_VITESSE is not set
+# CONFIG_SATA_INIC162X is not set
+# CONFIG_PATA_ALI is not set
+# CONFIG_PATA_AMD is not set
+# CONFIG_PATA_ARTOP is not set
+# CONFIG_PATA_ATIIXP is not set
+# CONFIG_PATA_CMD640_PCI is not set
+# CONFIG_PATA_CMD64X is not set
+# CONFIG_PATA_CS5520 is not set
+# CONFIG_PATA_CS5530 is not set
+# CONFIG_PATA_CS5535 is not set
+# CONFIG_PATA_CYPRESS is not set
+# CONFIG_PATA_EFAR is not set
+# CONFIG_ATA_GENERIC is not set
+# CONFIG_PATA_HPT366 is not set
+# CONFIG_PATA_HPT37X is not set
+# CONFIG_PATA_HPT3X2N is not set
+# CONFIG_PATA_HPT3X3 is not set
+# CONFIG_PATA_IT821X is not set
+# CONFIG_PATA_IT8213 is not set
+# CONFIG_PATA_JMICRON is not set
+# CONFIG_PATA_TRIFLEX is not set
+# CONFIG_PATA_MARVELL is not set
+# CONFIG_PATA_MPIIX is not set
+# CONFIG_PATA_OLDPIIX is not set
+# CONFIG_PATA_NETCELL is not set
+# CONFIG_PATA_NS87410 is not set
+# CONFIG_PATA_OPTI is not set
+# CONFIG_PATA_OPTIDMA is not set
+# CONFIG_PATA_PDC_OLD is not set
+# CONFIG_PATA_RADISYS is not set
+# CONFIG_PATA_RZ1000 is not set
+# CONFIG_PATA_SC1200 is not set
+# CONFIG_PATA_SERVERWORKS is not set
+# CONFIG_PATA_PDC2027X is not set
+# CONFIG_PATA_SIL680 is not set
+# CONFIG_PATA_SIS is not set
+# CONFIG_PATA_VIA is not set
+# CONFIG_PATA_WINBOND is not set
+CONFIG_MD=y
+# CONFIG_BLK_DEV_MD is not set
+CONFIG_BLK_DEV_DM=y
+# CONFIG_DM_DEBUG is not set
+# CONFIG_DM_CRYPT is not set
+# CONFIG_DM_SNAPSHOT is not set
+# CONFIG_DM_MIRROR is not set
+# CONFIG_DM_ZERO is not set
+# CONFIG_DM_MULTIPATH is not set
+# CONFIG_DM_DELAY is not set
 
 #
 # Fusion MPT device support
@@ -723,42 +751,27 @@ CONFIG_IEEE1394_OHCI1394=y
 # CONFIG_IEEE1394_ETH1394 is not set
 # CONFIG_IEEE1394_DV1394 is not set
 CONFIG_IEEE1394_RAWIO=y
-
-#
-# I2O device support
-#
 # CONFIG_I2O is not set
-# CONFIG_MACINTOSH_DRIVERS is not set
-
-#
-# Network device support
-#
+CONFIG_MACINTOSH_DRIVERS=y
+# CONFIG_MAC_EMUMOUSEBTN is not set
 CONFIG_NETDEVICES=y
+CONFIG_NETDEVICES_MULTIQUEUE=y
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
+# CONFIG_MACVLAN is not set
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
 # CONFIG_NET_SB1000 is not set
-
-#
-# ARCnet devices
-#
 # CONFIG_ARCNET is not set
 # CONFIG_PHYLIB is not set
-
-#
-# Ethernet (10 or 100Mbit)
-#
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
 # CONFIG_HAPPYMEAL is not set
 # CONFIG_SUNGEM is not set
 # CONFIG_CASSINI is not set
-# CONFIG_NET_VENDOR_3COM is not set
-
-#
-# Tulip family network device support
-#
+CONFIG_NET_VENDOR_3COM=y
+CONFIG_VORTEX=y
+# CONFIG_TYPHOON is not set
 CONFIG_NET_TULIP=y
 # CONFIG_DE2104X is not set
 CONFIG_TULIP=y
@@ -809,7 +822,6 @@ CONFIG_R8169=y
 # CONFIG_SIS190 is not set
 # CONFIG_SKGE is not set
 CONFIG_SKY2=y
-# CONFIG_SK98LIN is not set
 # CONFIG_VIA_VELOCITY is not set
 CONFIG_TIGON3=y
 CONFIG_BNX2=y
@@ -823,10 +835,6 @@ CONFIG_NETDEV_10000=y
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_MLX4_CORE is not set
-
-#
-# Token Ring devices
-#
 # CONFIG_TR is not set
 
 #
@@ -855,15 +863,7 @@ CONFIG_NETCONSOLE=y
 CONFIG_NETPOLL=y
 # CONFIG_NETPOLL_TRAP is not set
 CONFIG_NET_POLL_CONTROLLER=y
-
-#
-# ISDN subsystem
-#
 # CONFIG_ISDN is not set
-
-#
-# Telephony Support
-#
 # CONFIG_PHONE is not set
 
 #
@@ -871,6 +871,7 @@ CONFIG_NET_POLL_CONTROLLER=y
 #
 CONFIG_INPUT=y
 # CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
 
 #
 # Userland interfaces
@@ -936,6 +937,7 @@ CONFIG_HW_CONSOLE=y
 #
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_FIX_EARLYCON_MEM=y
 CONFIG_SERIAL_8250_PCI=y
 CONFIG_SERIAL_8250_PNP=y
 CONFIG_SERIAL_8250_NR_UARTS=4
@@ -951,10 +953,6 @@ CONFIG_SERIAL_CORE_CONSOLE=y
 CONFIG_UNIX98_PTYS=y
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=256
-
-#
-# IPMI
-#
 # CONFIG_IPMI_HANDLER is not set
 # CONFIG_WATCHDOG is not set
 CONFIG_HW_RANDOM=y
@@ -988,11 +986,7 @@ CONFIG_MAX_RAW_DEVS=256
 CONFIG_HPET=y
 # CONFIG_HPET_RTC_IRQ is not set
 CONFIG_HPET_MMAP=y
-CONFIG_HANGCHECK_TIMER=y
-
-#
-# TPM devices
-#
+# CONFIG_HANGCHECK_TIMER is not set
 # CONFIG_TCG_TPM is not set
 # CONFIG_TELCLOCK is not set
 CONFIG_DEVPORT=y
@@ -1003,11 +997,8 @@ CONFIG_DEVPORT=y
 #
 # CONFIG_SPI is not set
 # CONFIG_SPI_MASTER is not set
-
-#
-# Dallas's 1-wire bus
-#
 # CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
 # CONFIG_HWMON is not set
 
 #
@@ -1041,7 +1032,7 @@ CONFIG_DAB=y
 CONFIG_VGA_CONSOLE=y
 CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=128
-# CONFIG_VIDEO_SELECT is not set
+CONFIG_VIDEO_SELECT=y
 CONFIG_DUMMY_CONSOLE=y
 
 #
@@ -1058,15 +1049,11 @@ CONFIG_SOUND=y
 # Open Sound System
 #
 CONFIG_SOUND_PRIME=y
-# CONFIG_OSS_OBSOLETE is not set
 # CONFIG_SOUND_TRIDENT is not set
 # CONFIG_SOUND_MSNDCLAS is not set
 # CONFIG_SOUND_MSNDPIN is not set
 # CONFIG_SOUND_OSS is not set
-
-#
-# HID Devices
-#
+CONFIG_HID_SUPPORT=y
 CONFIG_HID=y
 # CONFIG_HID_DEBUG is not set
 
@@ -1077,10 +1064,7 @@ CONFIG_USB_HID=y
 # CONFIG_USB_HIDINPUT_POWERBOOK is not set
 # CONFIG_HID_FF is not set
 # CONFIG_USB_HIDDEV is not set
-
-#
-# USB support
-#
+CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
 CONFIG_USB_ARCH_HAS_EHCI=y
@@ -1094,6 +1078,7 @@ CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_DEVICE_CLASS is not set
 # CONFIG_USB_DYNAMIC_MINORS is not set
 # CONFIG_USB_SUSPEND is not set
+# CONFIG_USB_PERSIST is not set
 # CONFIG_USB_OTG is not set
 
 #
@@ -1103,7 +1088,6 @@ CONFIG_USB_EHCI_HCD=y
 # CONFIG_USB_EHCI_SPLIT_ISO is not set
 # CONFIG_USB_EHCI_ROOT_HUB_TT is not set
 # CONFIG_USB_EHCI_TT_NEWSCHED is not set
-# CONFIG_USB_EHCI_BIG_ENDIAN_MMIO is not set
 # CONFIG_USB_ISP116X_HCD is not set
 CONFIG_USB_OHCI_HCD=y
 # CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set
@@ -1111,6 +1095,7 @@ CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_OHCI_LITTLE_ENDIAN=y
 CONFIG_USB_UHCI_HCD=y
 # CONFIG_USB_SL811_HCD is not set
+# CONFIG_USB_R8A66597_HCD is not set
 
 #
 # USB Device Class drivers
@@ -1201,15 +1186,7 @@ CONFIG_USB_MON=y
 #
 # LED Triggers
 #
-
-#
-# InfiniBand support
-#
 # CONFIG_INFINIBAND is not set
-
-#
-# EDAC - error detection and reporting (RAS) (EXPERIMENTAL)
-#
 # CONFIG_EDAC is not set
 
 #
@@ -1229,11 +1206,13 @@ CONFIG_USB_MON=y
 #
 # DMA Devices
 #
+CONFIG_VIRTUALIZATION=y
+# CONFIG_KVM is not set
 
 #
-# Virtualization
+# Userspace I/O
 #
-# CONFIG_KVM is not set
+# CONFIG_UIO is not set
 
 #
 # File systems
@@ -1271,6 +1250,7 @@ CONFIG_DNOTIFY=y
 # CONFIG_AUTOFS_FS is not set
 CONFIG_AUTOFS4_FS=y
 # CONFIG_FUSE_FS is not set
+CONFIG_GENERIC_ACL=y
 
 #
 # CD-ROM/DVD Filesystems
@@ -1298,7 +1278,7 @@ CONFIG_PROC_KCORE=y
 CONFIG_PROC_SYSCTL=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
-# CONFIG_TMPFS_POSIX_ACL is not set
+CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 CONFIG_HUGETLB_PAGE=y
 CONFIG_RAMFS=y
@@ -1348,7 +1328,6 @@ CONFIG_SUNRPC=y
 # CONFIG_NCP_FS is not set
 # CONFIG_CODA_FS is not set
 # CONFIG_AFS_FS is not set
-# CONFIG_9P_FS is not set
 
 #
 # Partition Types
@@ -1404,10 +1383,7 @@ CONFIG_NLS_UTF8=y
 # Distributed Lock Manager
 #
 # CONFIG_DLM is not set
-
-#
-# Instrumentation Support
-#
+CONFIG_INSTRUMENTATION=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
 CONFIG_KPROBES=y
@@ -1417,7 +1393,7 @@ CONFIG_KPROBES=y
 #
 CONFIG_TRACE_IRQFLAGS_SUPPORT=y
 # CONFIG_PRINTK_TIME is not set
-CONFIG_ENABLE_MUST_CHECK=y
+# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_UNUSED_SYMBOLS=y
 # CONFIG_DEBUG_FS is not set
@@ -1425,15 +1401,17 @@ CONFIG_UNUSED_SYMBOLS=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
 CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_SCHED_DEBUG is not set
 # CONFIG_SCHEDSTATS is not set
-# CONFIG_TIMER_STATS is not set
-# CONFIG_DEBUG_SLAB is not set
+CONFIG_TIMER_STATS=y
+# CONFIG_SLUB_DEBUG_ON is not set
 # CONFIG_DEBUG_RT_MUTEXES is not set
 # CONFIG_RT_MUTEX_TESTER is not set
 # CONFIG_DEBUG_SPINLOCK is not set
 # CONFIG_DEBUG_MUTEXES is not set
 # CONFIG_DEBUG_LOCK_ALLOC is not set
 # CONFIG_PROVE_LOCKING is not set
+# CONFIG_LOCK_STAT is not set
 # CONFIG_DEBUG_SPINLOCK_SLEEP is not set
 # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
 # CONFIG_DEBUG_KOBJECT is not set
@@ -1443,7 +1421,6 @@ CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_DEBUG_VM is not set
 # CONFIG_DEBUG_LIST is not set
 # CONFIG_FRAME_POINTER is not set
-# CONFIG_UNWIND_INFO is not set
 # CONFIG_FORCED_INLINING is not set
 # CONFIG_RCU_TORTURE_TEST is not set
 # CONFIG_LKDTM is not set
@@ -1462,10 +1439,6 @@ CONFIG_DOUBLEFAULT=y
 #
 # CONFIG_KEYS is not set
 # CONFIG_SECURITY is not set
-
-#
-# Cryptographic options
-#
 # CONFIG_CRYPTO is not set
 
 #
@@ -1476,6 +1449,7 @@ CONFIG_BITREVERSE=y
 # CONFIG_CRC16 is not set
 # CONFIG_CRC_ITU_T is not set
 CONFIG_CRC32=y
+# CONFIG_CRC7 is not set
 # CONFIG_LIBCRC32C is not set
 CONFIG_ZLIB_INFLATE=y
 CONFIG_PLIST=y
diff --git a/arch/i386/kernel/Makefile b/arch/i386/kernel/Makefile
index 06da59f6f837..dbe5e87e0d66 100644
--- a/arch/i386/kernel/Makefile
+++ b/arch/i386/kernel/Makefile
@@ -40,6 +40,7 @@ obj-$(CONFIG_VM86)		+= vm86.o
 obj-$(CONFIG_EARLY_PRINTK)      += early_printk.o
 obj-$(CONFIG_HPET_TIMER)        += hpet.o
 obj-$(CONFIG_K8_NB)             += k8.o
+obj-$(CONFIG_MGEODE_LX)         += geode.o
 
 obj-$(CONFIG_VMI)               += vmi.o vmiclock.o
 obj-$(CONFIG_PARAVIRT)          += paravirt.o
diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c
index a574cd2c8b61..cacdd883bf2b 100644
--- a/arch/i386/kernel/acpi/boot.c
+++ b/arch/i386/kernel/acpi/boot.c
@@ -618,6 +618,8 @@ static int __init acpi_parse_sbf(struct acpi_table_header *table)
 #ifdef CONFIG_HPET_TIMER
 #include <asm/hpet.h>
 
+static struct __initdata resource *hpet_res;
+
 static int __init acpi_parse_hpet(struct acpi_table_header *table)
 {
         struct acpi_table_hpet *hpet_tbl;
@@ -638,8 +640,42 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table)
         printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n",
                hpet_tbl->id, hpet_address);
 
+        /*
+         * Allocate and initialize the HPET firmware resource for adding into
+         * the resource tree during the lateinit timeframe.
+         */
+#define HPET_RESOURCE_NAME_SIZE 9
+        hpet_res = alloc_bootmem(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE);
+
+        if (!hpet_res)
+                return 0;
+
+        memset(hpet_res, 0, sizeof(*hpet_res));
+        hpet_res->name = (void *)&hpet_res[1];
+        hpet_res->flags = IORESOURCE_MEM;
+        snprintf((char *)hpet_res->name, HPET_RESOURCE_NAME_SIZE, "HPET %u",
+                 hpet_tbl->sequence);
+
+        hpet_res->start = hpet_address;
+        hpet_res->end = hpet_address + (1 * 1024) - 1;
+
         return 0;
 }
+
+/*
+ * hpet_insert_resource inserts the HPET resources used into the resource
+ * tree.
+ */
+static __init int hpet_insert_resource(void)
+{
+        if (!hpet_res)
+                return 1;
+
+        return insert_resource(&iomem_resource, hpet_res);
+}
+
+late_initcall(hpet_insert_resource);
+
 #else
 #define acpi_parse_hpet NULL
 #endif
@@ -950,14 +986,6 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = {
          },
         {
          .callback = force_acpi_ht,
-         .ident = "DELL GX240",
-         .matches = {
-                     DMI_MATCH(DMI_BOARD_VENDOR, "Dell Computer Corporation"),
-                     DMI_MATCH(DMI_BOARD_NAME, "OptiPlex GX240"),
-                     },
-         },
-        {
-         .callback = force_acpi_ht,
          .ident = "HP VISUALIZE NT Workstation",
          .matches = {
                      DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"),
diff --git a/arch/i386/kernel/alternative.c b/arch/i386/kernel/alternative.c
index d8cda14fff8b..c3750c2c4113 100644
--- a/arch/i386/kernel/alternative.c
+++ b/arch/i386/kernel/alternative.c
@@ -2,12 +2,17 @@
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <linux/kprobes.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
+#include <asm/pgtable.h>
+#include <asm/mce.h>
+#include <asm/nmi.h>
 
-static int noreplace_smp     = 0;
-static int smp_alt_once      = 0;
-static int debug_alternative = 0;
+#ifdef CONFIG_HOTPLUG_CPU
+static int smp_alt_once;
 
 static int __init bootonly(char *str)
 {
@@ -15,6 +20,11 @@ static int __init bootonly(char *str)
         return 1;
 }
 __setup("smp-alt-boot", bootonly);
+#else
+#define smp_alt_once 1
+#endif
+
+static int debug_alternative;
 
 static int __init debug_alt(char *str)
 {
@@ -23,6 +33,8 @@ static int __init debug_alt(char *str)
 }
 __setup("debug-alternative", debug_alt);
 
+static int noreplace_smp;
+
 static int __init setup_noreplace_smp(char *str)
 {
         noreplace_smp = 1;
@@ -144,7 +156,7 @@ static void nop_out(void *insns, unsigned int len)
                 unsigned int noplen = len;
                 if (noplen > ASM_NOP_MAX)
                         noplen = ASM_NOP_MAX;
-                memcpy(insns, noptable[noplen], noplen);
+                text_poke(insns, noptable[noplen], noplen);
                 insns += noplen;
                 len -= noplen;
         }
@@ -196,7 +208,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
                         continue;
                 if (*ptr > text_end)
                         continue;
-                **ptr = 0xf0; /* lock prefix */
+                text_poke(*ptr, ((unsigned char []){0xf0}), 1); /* add lock prefix */
         };
 }
 
@@ -354,10 +366,6 @@ void apply_paravirt(struct paravirt_patch_site *start,
                 /* Pad the rest with nops */
                 nop_out(p->instr + used, p->len - used);
         }
-
-        /* Sync to be conservative, in case we patched following
-         * instructions */
-        sync_core();
 }
 extern struct paravirt_patch_site __start_parainstructions[],
         __stop_parainstructions[];
@@ -367,6 +375,14 @@ void __init alternative_instructions(void)
 {
         unsigned long flags;
 
+        /* The patching is not fully atomic, so try to avoid local interruptions
+           that might execute the to be patched code.
+           Other CPUs are not running. */
+        stop_nmi();
+#ifdef CONFIG_MCE
+        stop_mce();
+#endif
+
         local_irq_save(flags);
         apply_alternatives(__alt_instructions, __alt_instructions_end);
 
@@ -376,8 +392,6 @@ void __init alternative_instructions(void)
 #ifdef CONFIG_HOTPLUG_CPU
         if (num_possible_cpus() < 2)
                 smp_alt_once = 1;
-#else
-        smp_alt_once = 1;
 #endif
 
 #ifdef CONFIG_SMP
@@ -401,4 +415,37 @@ void __init alternative_instructions(void)
 #endif
         apply_paravirt(__parainstructions, __parainstructions_end);
         local_irq_restore(flags);
+
+        restart_nmi();
+#ifdef CONFIG_MCE
+        restart_mce();
+#endif
+}
+
+/*
+ * Warning:
+ * When you use this code to patch more than one byte of an instruction
+ * you need to make sure that other CPUs cannot execute this code in parallel.
+ * Also no thread must be currently preempted in the middle of these instructions.
+ * And on the local CPU you need to be protected again NMI or MCE handlers
+ * seeing an inconsistent instruction while you patch.
+ */
+void __kprobes text_poke(void *oaddr, unsigned char *opcode, int len)
+{
+        u8 *addr = oaddr;
+        if (!pte_write(*lookup_address((unsigned long)addr))) {
+                struct page *p[2] = { virt_to_page(addr), virt_to_page(addr+PAGE_SIZE) };
+                addr = vmap(p, 2, VM_MAP, PAGE_KERNEL);
+                if (!addr)
+                        return;
+                addr += ((unsigned long)oaddr) % PAGE_SIZE;
+        }
+        memcpy(addr, opcode, len);
+        sync_core();
+        /* Not strictly needed, but can speed CPU recovery up. Ignore cross cacheline
+           case. */
+        if (cpu_has_clflush)
+                asm("clflush (%0) " :: "r" (oaddr) : "memory");
+        if (addr != oaddr)
+                vunmap(addr);
 }
diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c
index 67824f3bb974..bfc6cb7df7e7 100644
--- a/arch/i386/kernel/apic.c
+++ b/arch/i386/kernel/apic.c
@@ -263,6 +263,9 @@ static void lapic_timer_setup(enum clock_event_mode mode,
                 v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
                 apic_write_around(APIC_LVTT, v);
                 break;
+        case CLOCK_EVT_MODE_RESUME:
+                /* Nothing to do here */
+                break;
         }
 
         local_irq_restore(flags);
@@ -315,7 +318,7 @@ static void __devinit setup_APIC_timer(void)
 
 #define LAPIC_CAL_LOOPS         (HZ/10)
 
-static __initdata volatile int lapic_cal_loops = -1;
+static __initdata int lapic_cal_loops = -1;
 static __initdata long lapic_cal_t1, lapic_cal_t2;
 static __initdata unsigned long long lapic_cal_tsc1, lapic_cal_tsc2;
 static __initdata unsigned long lapic_cal_pm1, lapic_cal_pm2;
@@ -485,7 +488,7 @@ void __init setup_boot_APIC_clock(void)
                 /* Let the interrupts run */
                 local_irq_enable();
 
-                while(lapic_cal_loops <= LAPIC_CAL_LOOPS)
+                while (lapic_cal_loops <= LAPIC_CAL_LOOPS)
                         cpu_relax();
 
                 local_irq_disable();
@@ -521,6 +524,9 @@ void __init setup_boot_APIC_clock(void)
                  */
                 if (nmi_watchdog != NMI_IO_APIC)
                         lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
+                else
+                        printk(KERN_WARNING "APIC timer registered as dummy,"
+                               " due to nmi_watchdog=1!\n");
         }
 
         /* Setup the lapic or request the broadcast */
diff --git a/arch/i386/kernel/cpu/Makefile b/arch/i386/kernel/cpu/Makefile
index 0b6a8551e9e2..778396c78d65 100644
--- a/arch/i386/kernel/cpu/Makefile
+++ b/arch/i386/kernel/cpu/Makefile
@@ -9,7 +9,6 @@ obj-y	+=	cyrix.o
 obj-y   +=      centaur.o
 obj-y   +=      transmeta.o
 obj-y   +=      intel.o intel_cacheinfo.o addon_cpuid_features.o
-obj-y   +=      rise.o
 obj-y   +=      nexgen.o
 obj-y   +=      umc.o
 
diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c
index 6f47eeeb93ea..c7ba455d5ac7 100644
--- a/arch/i386/kernel/cpu/amd.c
+++ b/arch/i386/kernel/cpu/amd.c
@@ -231,6 +231,9 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 
         switch (c->x86) {
         case 15:
+        /* Use K8 tuning for Fam10h and Fam11h */
+        case 0x10:
+        case 0x11:
                 set_bit(X86_FEATURE_K8, c->x86_capability);
                 break;
         case 6:
@@ -272,8 +275,12 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
         }
 #endif
 
-        if (cpuid_eax(0x80000000) >= 0x80000006)
-                num_cache_leaves = 3;
+        if (cpuid_eax(0x80000000) >= 0x80000006) {
+                if ((c->x86 == 0x10) && (cpuid_edx(0x80000006) & 0xf000))
+                        num_cache_leaves = 4;
+                else
+                        num_cache_leaves = 3;
+        }
 
         if (amd_apic_timer_broken())
                 set_bit(X86_FEATURE_LAPIC_TIMER_BROKEN, c->x86_capability);
diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index e5419a9dec88..d506201d397c 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -606,7 +606,6 @@ extern int nsc_init_cpu(void);
 extern int amd_init_cpu(void);
 extern int centaur_init_cpu(void);
 extern int transmeta_init_cpu(void);
-extern int rise_init_cpu(void);
 extern int nexgen_init_cpu(void);
 extern int umc_init_cpu(void);
 
@@ -618,7 +617,6 @@ void __init early_cpu_init(void)
         amd_init_cpu();
         centaur_init_cpu();
         transmeta_init_cpu();
-        rise_init_cpu();
         nexgen_init_cpu();
         umc_init_cpu();
         early_cpu_detect();
diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
index 18c8b67ea3a7..6f846bee2103 100644
--- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -665,8 +665,8 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
         data->max_freq = perf->states[0].core_frequency * 1000;
         /* table init */
         for (i=0; i<perf->state_count; i++) {
-                if (i>0 && perf->states[i].core_frequency ==
-                    perf->states[i-1].core_frequency)
+                if (i>0 && perf->states[i].core_frequency >=
+                    data->freq_table[valid_states-1].frequency / 1000)
                         continue;
 
                 data->freq_table[valid_states].index = i;
diff --git a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c
index 194144539a6f..461dabc4e495 100644
--- a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c
+++ b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c
@@ -79,7 +79,7 @@
 #include <linux/smp.h>
 #include <linux/cpufreq.h>
 #include <linux/pci.h>
-#include <asm/processor.h>
+#include <asm/processor-cyrix.h>
 #include <asm/errno.h>
 
 /* PCI config registers, all at F0 */
diff --git a/arch/i386/kernel/cpu/cyrix.c b/arch/i386/kernel/cpu/cyrix.c
index e88d2fba156b..122d2d75aa9f 100644
--- a/arch/i386/kernel/cpu/cyrix.c
+++ b/arch/i386/kernel/cpu/cyrix.c
@@ -4,7 +4,7 @@
 #include <linux/pci.h>
 #include <asm/dma.h>
 #include <asm/io.h>
-#include <asm/processor.h>
+#include <asm/processor-cyrix.h>
 #include <asm/timer.h>
 #include <asm/pci-direct.h>
 #include <asm/tsc.h>
diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c
index e5be819492ef..d5a456d27d82 100644
--- a/arch/i386/kernel/cpu/intel_cacheinfo.c
+++ b/arch/i386/kernel/cpu/intel_cacheinfo.c
@@ -4,7 +4,7 @@
  *      Changes:
  *      Venkatesh Pallipadi     : Adding cache identification through cpuid(4)
  *              Ashok Raj <ashok.raj@intel.com>: Work with CPU hotplug infrastructure.
- *      Andi Kleen              : CPUID4 emulation on AMD.
+ *      Andi Kleen / Andreas Herrmann   : CPUID4 emulation on AMD.
  */
 
 #include <linux/init.h>
@@ -135,7 +135,7 @@ unsigned short			num_cache_leaves;
 
 /* AMD doesn't have CPUID4. Emulate it here to report the same
    information to the user.  This makes some assumptions about the machine:
-   No L3, L2 not shared, no SMT etc. that is currently true on AMD CPUs.
+   L2 not shared, no SMT etc. that is currently true on AMD CPUs.
 
    In theory the TLBs could be reported as fake type (they are in "dummy").
    Maybe later */
@@ -159,13 +159,26 @@ union l2_cache {
         unsigned val;
 };
 
+union l3_cache {
+        struct {
+                unsigned line_size : 8;
+                unsigned lines_per_tag : 4;
+                unsigned assoc : 4;
+                unsigned res : 2;
+                unsigned size_encoded : 14;
+        };
+        unsigned val;
+};
+
 static const unsigned short assocs[] = {
         [1] = 1, [2] = 2, [4] = 4, [6] = 8,
-        [8] = 16,
+        [8] = 16, [0xa] = 32, [0xb] = 48,
+        [0xc] = 64,
         [0xf] = 0xffff // ??
-        };
-static const unsigned char levels[] = { 1, 1, 2 };
-static const unsigned char types[] = { 1, 2, 3 };
+};
+
+static const unsigned char levels[] = { 1, 1, 2, 3 };
+static const unsigned char types[] = { 1, 2, 3, 3 };
 
 static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
                        union _cpuid4_leaf_ebx *ebx,
@@ -175,37 +188,58 @@ static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
         unsigned line_size, lines_per_tag, assoc, size_in_kb;
         union l1_cache l1i, l1d;
         union l2_cache l2;
+        union l3_cache l3;
+        union l1_cache *l1 = &l1d;
 
         eax->full = 0;
         ebx->full = 0;
         ecx->full = 0;
 
         cpuid(0x80000005, &dummy, &dummy, &l1d.val, &l1i.val);
-        cpuid(0x80000006, &dummy, &dummy, &l2.val, &dummy);
-
-        if (leaf > 2 || !l1d.val || !l1i.val || !l2.val)
-                return;
-
-        eax->split.is_self_initializing = 1;
-        eax->split.type = types[leaf];
-        eax->split.level = levels[leaf];
-        eax->split.num_threads_sharing = 0;
-        eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
-
-        if (leaf <= 1) {
-                union l1_cache *l1 = leaf == 0 ? &l1d : &l1i;
+        cpuid(0x80000006, &dummy, &dummy, &l2.val, &l3.val);
+
+        switch (leaf) {
+        case 1:
+                l1 = &l1i;
+        case 0:
+                if (!l1->val)
+                        return;
                 assoc = l1->assoc;
                 line_size = l1->line_size;
                 lines_per_tag = l1->lines_per_tag;
                 size_in_kb = l1->size_in_kb;
-        } else {
+                break;
+        case 2:
+                if (!l2.val)
+                        return;
                 assoc = l2.assoc;
                 line_size = l2.line_size;
                 lines_per_tag = l2.lines_per_tag;
                 /* cpu_data has errata corrections for K7 applied */
                 size_in_kb = current_cpu_data.x86_cache_size;
+                break;
+        case 3:
+                if (!l3.val)
+                        return;
+                assoc = l3.assoc;
+                line_size = l3.line_size;
+                lines_per_tag = l3.lines_per_tag;
+                size_in_kb = l3.size_encoded * 512;
+                break;
+        default:
+                return;
         }
 
+        eax->split.is_self_initializing = 1;
+        eax->split.type = types[leaf];
+        eax->split.level = levels[leaf];
+        if (leaf == 3)
+                eax->split.num_threads_sharing = current_cpu_data.x86_max_cores - 1;
+        else
+                eax->split.num_threads_sharing = 0;
+        eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
+
+
         if (assoc == 0xf)
                 eax->split.is_fully_associative = 1;
         ebx->split.coherency_line_size = line_size - 1;
@@ -239,8 +273,7 @@ static int __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_le
         return 0;
 }
 
-/* will only be called once; __init is safe here */
-static int __init find_num_cache_leaves(void)
+static int __cpuinit find_num_cache_leaves(void)
 {
         unsigned int            eax, ebx, ecx, edx;
         union _cpuid4_leaf_eax  cache_eax;
@@ -710,7 +743,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
         return retval;
 }
 
-static void __cpuexit cache_remove_dev(struct sys_device * sys_dev)
+static void __cpuinit cache_remove_dev(struct sys_device * sys_dev)
 {
         unsigned int cpu = sys_dev->id;
         unsigned long i;
diff --git a/arch/i386/kernel/cpu/mcheck/mce.c b/arch/i386/kernel/cpu/mcheck/mce.c
index 56cd485b127c..34c781eddee4 100644
--- a/arch/i386/kernel/cpu/mcheck/mce.c
+++ b/arch/i386/kernel/cpu/mcheck/mce.c
@@ -60,6 +60,20 @@ void mcheck_init(struct cpuinfo_x86 *c)
         }
 }
 
+static unsigned long old_cr4 __initdata;
+
+void __init stop_mce(void)
+{
+        old_cr4 = read_cr4();
+        clear_in_cr4(X86_CR4_MCE);
+}
+
+void __init restart_mce(void)
+{
+        if (old_cr4 & X86_CR4_MCE)
+                set_in_cr4(X86_CR4_MCE);
+}
+
 static int __init mcheck_disable(char *str)
 {
         mce_disabled = 1;
diff --git a/arch/i386/kernel/cpu/mcheck/non-fatal.c b/arch/i386/kernel/cpu/mcheck/non-fatal.c
index 6b5d3518a1c0..bf39409b3838 100644
--- a/arch/i386/kernel/cpu/mcheck/non-fatal.c
+++ b/arch/i386/kernel/cpu/mcheck/non-fatal.c
@@ -57,7 +57,7 @@ static DECLARE_DELAYED_WORK(mce_work, mce_work_fn);
 static void mce_work_fn(struct work_struct *work)
 { 
         on_each_cpu(mce_checkregs, NULL, 1, 1);
-        schedule_delayed_work(&mce_work, MCE_RATE);
+        schedule_delayed_work(&mce_work, round_jiffies_relative(MCE_RATE));
 } 
 
 static int __init init_nonfatal_mce_checker(void)
@@ -82,7 +82,7 @@ static int __init init_nonfatal_mce_checker(void)
         /*
          * Check for non-fatal errors every MCE_RATE s
          */
-        schedule_delayed_work(&mce_work, MCE_RATE);
+        schedule_delayed_work(&mce_work, round_jiffies_relative(MCE_RATE));
         printk(KERN_INFO "Machine check exception polling timer started.\n");
         return 0;
 }
diff --git a/arch/i386/kernel/cpu/mtrr/cyrix.c b/arch/i386/kernel/cpu/mtrr/cyrix.c
index 1001f1e0fe6d..2287d4863a8a 100644
--- a/arch/i386/kernel/cpu/mtrr/cyrix.c
+++ b/arch/i386/kernel/cpu/mtrr/cyrix.c
@@ -3,6 +3,7 @@
 #include <asm/mtrr.h>
 #include <asm/msr.h>
 #include <asm/io.h>
+#include <asm/processor-cyrix.h>
 #include "mtrr.h"
 
 int arr3_protected;
diff --git a/arch/i386/kernel/cpu/mtrr/generic.c b/arch/i386/kernel/cpu/mtrr/generic.c
index f6e46943e6ef..56f64e34829f 100644
--- a/arch/i386/kernel/cpu/mtrr/generic.c
+++ b/arch/i386/kernel/cpu/mtrr/generic.c
@@ -79,7 +79,7 @@ static void print_fixed(unsigned base, unsigned step, const mtrr_type*types)
 }
 
 /*  Grab all of the MTRR state for this CPU into *state  */
-void get_mtrr_state(void)
+void __init get_mtrr_state(void)
 {
         unsigned int i;
         struct mtrr_var_range *vrs;
diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c
index 75dc6d5214bc..c48b6fea5ab4 100644
--- a/arch/i386/kernel/cpu/mtrr/main.c
+++ b/arch/i386/kernel/cpu/mtrr/main.c
@@ -643,7 +643,7 @@ static struct sysdev_driver mtrr_sysdev_driver = {
  * initialized (i.e. before smp_init()).
  * 
  */
-__init void mtrr_bp_init(void)
+void __init mtrr_bp_init(void)
 {
         init_ifs();
 
diff --git a/arch/i386/kernel/cpu/mtrr/state.c b/arch/i386/kernel/cpu/mtrr/state.c
index 7b39a2f954d9..c9014ca4a575 100644
--- a/arch/i386/kernel/cpu/mtrr/state.c
+++ b/arch/i386/kernel/cpu/mtrr/state.c
@@ -3,6 +3,7 @@
 #include <asm/io.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
+#include <asm-i386/processor-cyrix.h>
 #include "mtrr.h"
 
 
diff --git a/arch/i386/kernel/cpu/perfctr-watchdog.c b/arch/i386/kernel/cpu/perfctr-watchdog.c
index 4d26d514c56f..4be488e73bee 100644
--- a/arch/i386/kernel/cpu/perfctr-watchdog.c
+++ b/arch/i386/kernel/cpu/perfctr-watchdog.c
@@ -325,7 +325,7 @@ static struct wd_ops k7_wd_ops = {
         .stop = single_msr_stop_watchdog,
         .perfctr = MSR_K7_PERFCTR0,
         .evntsel = MSR_K7_EVNTSEL0,
-        .checkbit = 1ULL<<63,
+        .checkbit = 1ULL<<47,
 };
 
 /* Intel Model 6 (PPro+,P2,P3,P-M,Core1) */
@@ -346,7 +346,9 @@ static int setup_p6_watchdog(unsigned nmi_hz)
         perfctr_msr = MSR_P6_PERFCTR0;
         evntsel_msr = MSR_P6_EVNTSEL0;
 
-        wrmsrl(perfctr_msr, 0UL);
+        /* KVM doesn't implement this MSR */
+        if (wrmsr_safe(perfctr_msr, 0, 0) < 0)
+                return 0;
 
         evntsel = P6_EVNTSEL_INT
                 | P6_EVNTSEL_OS
@@ -599,8 +601,8 @@ static struct wd_ops intel_arch_wd_ops = {
         .setup = setup_intel_arch_watchdog,
         .rearm = p6_rearm,
         .stop = single_msr_stop_watchdog,
-        .perfctr = MSR_ARCH_PERFMON_PERFCTR0,
-        .evntsel = MSR_ARCH_PERFMON_EVENTSEL0,
+        .perfctr = MSR_ARCH_PERFMON_PERFCTR1,
+        .evntsel = MSR_ARCH_PERFMON_EVENTSEL1,
 };
 
 static void probe_nmi_watchdog(void)
diff --git a/arch/i386/kernel/cpu/rise.c b/arch/i386/kernel/cpu/rise.c
deleted file mode 100644
index 50076f22e90f..000000000000
--- a/arch/i386/kernel/cpu/rise.c
+++ /dev/null
@@ -1,52 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/bitops.h>
-#include <asm/processor.h>
-
-#include "cpu.h"
-
-static void __cpuinit init_rise(struct cpuinfo_x86 *c)
-{
-        printk("CPU: Rise iDragon");
-        if (c->x86_model > 2)
-                printk(" II");
-        printk("\n");
-
-        /* Unhide possibly hidden capability flags
-           The mp6 iDragon family don't have MSRs.
-           We switch on extra features with this cpuid weirdness: */
-        __asm__ (
-                "movl $0x6363452a, %%eax\n\t"
-                "movl $0x3231206c, %%ecx\n\t"
-                "movl $0x2a32313a, %%edx\n\t"
-                "cpuid\n\t"
-                "movl $0x63634523, %%eax\n\t"
-                "movl $0x32315f6c, %%ecx\n\t"
-                "movl $0x2333313a, %%edx\n\t"
-                "cpuid\n\t" : : : "eax", "ebx", "ecx", "edx"
-        );
-        set_bit(X86_FEATURE_CX8, c->x86_capability);
-}
-
-static struct cpu_dev rise_cpu_dev __cpuinitdata = {
-        .c_vendor       = "Rise",
-        .c_ident        = { "RiseRiseRise" },
-        .c_models = {
-                { .vendor = X86_VENDOR_RISE, .family = 5, .model_names = 
-                  { 
-                          [0] = "iDragon", 
-                          [2] = "iDragon", 
-                          [8] = "iDragon II", 
-                          [9] = "iDragon II"
-                  }
-                },
-        },
-        .c_init         = init_rise,
-};
-
-int __init rise_init_cpu(void)
-{
-        cpu_devs[X86_VENDOR_RISE] = &rise_cpu_dev;
-        return 0;
-}
-
diff --git a/arch/i386/kernel/e820.c b/arch/i386/kernel/e820.c
index fc822a46897a..e60cddbc4cfb 100644
--- a/arch/i386/kernel/e820.c
+++ b/arch/i386/kernel/e820.c
@@ -10,6 +10,7 @@
 #include <linux/efi.h>
 #include <linux/pfn.h>
 #include <linux/uaccess.h>
+#include <linux/suspend.h>
 
 #include <asm/pgtable.h>
 #include <asm/page.h>
@@ -320,6 +321,37 @@ static int __init request_standard_resources(void)
 
 subsys_initcall(request_standard_resources);
 
+#if defined(CONFIG_PM) && defined(CONFIG_SOFTWARE_SUSPEND)
+/**
+ * e820_mark_nosave_regions - Find the ranges of physical addresses that do not
+ * correspond to e820 RAM areas and mark the corresponding pages as nosave for
+ * hibernation.
+ *
+ * This function requires the e820 map to be sorted and without any
+ * overlapping entries and assumes the first e820 area to be RAM.
+ */
+void __init e820_mark_nosave_regions(void)
+{
+        int i;
+        unsigned long pfn;
+
+        pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size);
+        for (i = 1; i < e820.nr_map; i++) {
+                struct e820entry *ei = &e820.map[i];
+
+                if (pfn < PFN_UP(ei->addr))
+                        register_nosave_region(pfn, PFN_UP(ei->addr));
+
+                pfn = PFN_DOWN(ei->addr + ei->size);
+                if (ei->type != E820_RAM)
+                        register_nosave_region(PFN_UP(ei->addr), pfn);
+
+                if (pfn >= max_low_pfn)
+                        break;
+        }
+}
+#endif
+
 void __init add_memory_region(unsigned long long start,
                               unsigned long long size, int type)
 {
diff --git a/arch/i386/kernel/geode.c b/arch/i386/kernel/geode.c
new file mode 100644
index 000000000000..41e8aec4c61d
--- /dev/null
+++ b/arch/i386/kernel/geode.c
@@ -0,0 +1,155 @@
+/*
+ * AMD Geode southbridge support code
+ * Copyright (C) 2006, Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/ioport.h>
+#include <linux/io.h>
+#include <asm/msr.h>
+#include <asm/geode.h>
+
+static struct {
+        char *name;
+        u32 msr;
+        int size;
+        u32 base;
+} lbars[] = {
+        { "geode-pms",   MSR_LBAR_PMS, LBAR_PMS_SIZE, 0 },
+        { "geode-acpi",  MSR_LBAR_ACPI, LBAR_ACPI_SIZE, 0 },
+        { "geode-gpio",  MSR_LBAR_GPIO, LBAR_GPIO_SIZE, 0 },
+        { "geode-mfgpt", MSR_LBAR_MFGPT, LBAR_MFGPT_SIZE, 0 }
+};
+
+static void __init init_lbars(void)
+{
+        u32 lo, hi;
+        int i;
+
+        for (i = 0; i < ARRAY_SIZE(lbars); i++) {
+                rdmsr(lbars[i].msr, lo, hi);
+                if (hi & 0x01)
+                        lbars[i].base = lo & 0x0000ffff;
+
+                if (lbars[i].base == 0)
+                        printk(KERN_ERR "geode:  Couldn't initialize '%s'\n",
+                                        lbars[i].name);
+        }
+}
+
+int geode_get_dev_base(unsigned int dev)
+{
+        BUG_ON(dev >= ARRAY_SIZE(lbars));
+        return lbars[dev].base;
+}
+EXPORT_SYMBOL_GPL(geode_get_dev_base);
+
+/* === GPIO API === */
+
+void geode_gpio_set(unsigned int gpio, unsigned int reg)
+{
+        u32 base = geode_get_dev_base(GEODE_DEV_GPIO);
+
+        if (!base)
+                return;
+
+        if (gpio < 16)
+                outl(1 << gpio, base + reg);
+        else
+                outl(1 << (gpio - 16), base + 0x80 + reg);
+}
+EXPORT_SYMBOL_GPL(geode_gpio_set);
+
+void geode_gpio_clear(unsigned int gpio, unsigned int reg)
+{
+        u32 base = geode_get_dev_base(GEODE_DEV_GPIO);
+
+        if (!base)
+                return;
+
+        if (gpio < 16)
+                outl(1 << (gpio + 16), base + reg);
+        else
+                outl(1 << gpio, base + 0x80 + reg);
+}
+EXPORT_SYMBOL_GPL(geode_gpio_clear);
+
+int geode_gpio_isset(unsigned int gpio, unsigned int reg)
+{
+        u32 base = geode_get_dev_base(GEODE_DEV_GPIO);
+
+        if (!base)
+                return 0;
+
+        if (gpio < 16)
+                return (inl(base + reg) & (1 << gpio)) ? 1 : 0;
+        else
+                return (inl(base + 0x80 + reg) & (1 << (gpio - 16))) ? 1 : 0;
+}
+EXPORT_SYMBOL_GPL(geode_gpio_isset);
+
+void geode_gpio_set_irq(unsigned int group, unsigned int irq)
+{
+        u32 lo, hi;
+
+        if (group > 7 || irq > 15)
+                return;
+
+        rdmsr(MSR_PIC_ZSEL_HIGH, lo, hi);
+
+        lo &= ~(0xF << (group * 4));
+        lo |= (irq & 0xF) << (group * 4);
+
+        wrmsr(MSR_PIC_ZSEL_HIGH, lo, hi);
+}
+EXPORT_SYMBOL_GPL(geode_gpio_set_irq);
+
+void geode_gpio_setup_event(unsigned int gpio, int pair, int pme)
+{
+        u32 base = geode_get_dev_base(GEODE_DEV_GPIO);
+        u32 offset, shift, val;
+
+        if (gpio >= 24)
+                offset = GPIO_MAP_W;
+        else if (gpio >= 16)
+                offset = GPIO_MAP_Z;
+        else if (gpio >= 8)
+                offset = GPIO_MAP_Y;
+        else
+                offset = GPIO_MAP_X;
+
+        shift = (gpio % 8) * 4;
+
+        val = inl(base + offset);
+
+        /* Clear whatever was there before */
+        val &= ~(0xF << shift);
+
+        /* And set the new value */
+
+        val |= ((pair & 7) << shift);
+
+        /* Set the PME bit if this is a PME event */
+
+        if (pme)
+                val |= (1 << (shift + 3));
+
+        outl(val, base + offset);
+}
+EXPORT_SYMBOL_GPL(geode_gpio_setup_event);
+
+static int __init geode_southbridge_init(void)
+{
+        if (!is_geode())
+                return -ENODEV;
+
+        init_lbars();
+        return 0;
+}
+
+postcore_initcall(geode_southbridge_init);
diff --git a/arch/i386/kernel/hpet.c b/arch/i386/kernel/hpet.c
index 17d73459fc5f..533d4932bc79 100644
--- a/arch/i386/kernel/hpet.c
+++ b/arch/i386/kernel/hpet.c
@@ -5,6 +5,7 @@
 #include <linux/init.h>
 #include <linux/sysdev.h>
 #include <linux/pm.h>
+#include <linux/delay.h>
 
 #include <asm/hpet.h>
 #include <asm/io.h>
@@ -187,6 +188,10 @@ static void hpet_set_mode(enum clock_event_mode mode,
                 cfg &= ~HPET_TN_ENABLE;
                 hpet_writel(cfg, HPET_T0_CFG);
                 break;
+
+        case CLOCK_EVT_MODE_RESUME:
+                hpet_enable_int();
+                break;
         }
 }
 
@@ -217,6 +222,7 @@ static struct clocksource clocksource_hpet = {
         .mask           = HPET_MASK,
         .shift          = HPET_SHIFT,
         .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
+        .resume         = hpet_start_counter,
 };
 
 /*
@@ -226,7 +232,8 @@ int __init hpet_enable(void)
 {
         unsigned long id;
         uint64_t hpet_freq;
-        u64 tmp;
+        u64 tmp, start, now;
+        cycle_t t1;
 
         if (!is_hpet_capable())
                 return 0;
@@ -273,6 +280,27 @@ int __init hpet_enable(void)
         /* Start the counter */
         hpet_start_counter();
 
+        /* Verify whether hpet counter works */
+        t1 = read_hpet();
+        rdtscll(start);
+
+        /*
+         * We don't know the TSC frequency yet, but waiting for
+         * 200000 TSC cycles is safe:
+         * 4 GHz == 50us
+         * 1 GHz == 200us
+         */
+        do {
+                rep_nop();
+                rdtscll(now);
+        } while ((now - start) < 200000UL);
+
+        if (t1 == read_hpet()) {
+                printk(KERN_WARNING
+                       "HPET counter not counting. HPET disabled\n");
+                goto out_nohpet;
+        }
+
         /* Initialize and register HPET clocksource
          *
          * hpet period is in femto seconds per cycle
@@ -291,7 +319,6 @@ int __init hpet_enable(void)
 
         clocksource_register(&clocksource_hpet);
 
-
         if (id & HPET_ID_LEGSUP) {
                 hpet_enable_int();
                 hpet_reserve_platform_timers(id);
@@ -299,7 +326,7 @@ int __init hpet_enable(void)
                  * Start hpet with the boot cpu mask and make it
                  * global after the IO_APIC has been initialized.
                  */
-                hpet_clockevent.cpumask =cpumask_of_cpu(0);
+                hpet_clockevent.cpumask = cpumask_of_cpu(smp_processor_id());
                 clockevents_register_device(&hpet_clockevent);
                 global_clock_event = &hpet_clockevent;
                 return 1;
@@ -524,68 +551,3 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
         return IRQ_HANDLED;
 }
 #endif
-
-
-/*
- * Suspend/resume part
- */
-
-#ifdef CONFIG_PM
-
-static int hpet_suspend(struct sys_device *sys_device, pm_message_t state)
-{
-        unsigned long cfg = hpet_readl(HPET_CFG);
-
-        cfg &= ~(HPET_CFG_ENABLE|HPET_CFG_LEGACY);
-        hpet_writel(cfg, HPET_CFG);
-
-        return 0;
-}
-
-static int hpet_resume(struct sys_device *sys_device)
-{
-        unsigned int id;
-
-        hpet_start_counter();
-
-        id = hpet_readl(HPET_ID);
-
-        if (id & HPET_ID_LEGSUP)
-                hpet_enable_int();
-
-        return 0;
-}
-
-static struct sysdev_class hpet_class = {
-        set_kset_name("hpet"),
-        .suspend        = hpet_suspend,
-        .resume         = hpet_resume,
-};
-
-static struct sys_device hpet_device = {
-        .id             = 0,
-        .cls            = &hpet_class,
-};
-
-
-static __init int hpet_register_sysfs(void)
-{
-        int err;
-
-        if (!is_hpet_capable())
-                return 0;
-
-        err = sysdev_class_register(&hpet_class);
-
-        if (!err) {
-                err = sysdev_register(&hpet_device);
-                if (err)
-                        sysdev_class_unregister(&hpet_class);
-        }
-
-        return err;
-}
-
-device_initcall(hpet_register_sysfs);
-
-#endif
diff --git a/arch/i386/kernel/i8253.c b/arch/i386/kernel/i8253.c
index f8a3c4054c70..6d839f2f1b1a 100644
--- a/arch/i386/kernel/i8253.c
+++ b/arch/i386/kernel/i8253.c
@@ -3,18 +3,17 @@
  *
  */
 #include <linux/clockchips.h>
-#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
 #include <linux/jiffies.h>
-#include <linux/sysdev.h>
 #include <linux/module.h>
-#include <linux/init.h>
+#include <linux/spinlock.h>
 
 #include <asm/smp.h>
 #include <asm/delay.h>
 #include <asm/i8253.h>
 #include <asm/io.h>
-
-#include "io_ports.h"
+#include <asm/timer.h>
 
 DEFINE_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
@@ -41,26 +40,27 @@ static void init_pit_timer(enum clock_event_mode mode,
         case CLOCK_EVT_MODE_PERIODIC:
                 /* binary, mode 2, LSB/MSB, ch 0 */
                 outb_p(0x34, PIT_MODE);
-                udelay(10);
                 outb_p(LATCH & 0xff , PIT_CH0); /* LSB */
-                udelay(10);
                 outb(LATCH >> 8 , PIT_CH0);     /* MSB */
                 break;
 
-        /*
-         * Avoid unnecessary state transitions, as it confuses
-         * Geode / Cyrix based boxen.
-         */
         case CLOCK_EVT_MODE_SHUTDOWN:
-                if (evt->mode == CLOCK_EVT_MODE_UNUSED)
-                        break;
         case CLOCK_EVT_MODE_UNUSED:
-                if (evt->mode == CLOCK_EVT_MODE_SHUTDOWN)
-                        break;
+                if (evt->mode == CLOCK_EVT_MODE_PERIODIC ||
+                    evt->mode == CLOCK_EVT_MODE_ONESHOT) {
+                        outb_p(0x30, PIT_MODE);
+                        outb_p(0, PIT_CH0);
+                        outb_p(0, PIT_CH0);
+                }
+                break;
+
         case CLOCK_EVT_MODE_ONESHOT:
                 /* One shot setup */
                 outb_p(0x38, PIT_MODE);
-                udelay(10);
+                break;
+
+        case CLOCK_EVT_MODE_RESUME:
+                /* Nothing to do here */
                 break;
         }
         spin_unlock_irqrestore(&i8253_lock, flags);
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index 21db8f56c9a1..893df8280756 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -353,14 +353,6 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
 # include <linux/slab.h>                /* kmalloc() */
 # include <linux/timer.h>       /* time_after() */
  
-#ifdef CONFIG_BALANCED_IRQ_DEBUG
-#  define TDprintk(x...) do { printk("<%ld:%s:%d>: ", jiffies, __FILE__, __LINE__); printk(x); } while (0)
-#  define Dprintk(x...) do { TDprintk(x); } while (0)
-# else
-#  define TDprintk(x...) 
-#  define Dprintk(x...) 
-# endif
-
 #define IRQBALANCE_CHECK_ARCH -999
 #define MAX_BALANCED_IRQ_INTERVAL       (5*HZ)
 #define MIN_BALANCED_IRQ_INTERVAL       (HZ/2)
@@ -443,7 +435,7 @@ static inline void balance_irq(int cpu, int irq)
 static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
 {
         int i, j;
-        Dprintk("Rotating IRQs among CPUs.\n");
+
         for_each_online_cpu(i) {
                 for (j = 0; j < NR_IRQS; j++) {
                         if (!irq_desc[j].action)
@@ -560,19 +552,11 @@ tryanothercpu:
         max_loaded = tmp_loaded;        /* processor */
         imbalance = (max_cpu_irq - min_cpu_irq) / 2;
         
-        Dprintk("max_loaded cpu = %d\n", max_loaded);
-        Dprintk("min_loaded cpu = %d\n", min_loaded);
-        Dprintk("max_cpu_irq load = %ld\n", max_cpu_irq);
-        Dprintk("min_cpu_irq load = %ld\n", min_cpu_irq);
-        Dprintk("load imbalance = %lu\n", imbalance);
-
         /* if imbalance is less than approx 10% of max load, then
          * observe diminishing returns action. - quit
          */
-        if (imbalance < (max_cpu_irq >> 3)) {
-                Dprintk("Imbalance too trivial\n");
+        if (imbalance < (max_cpu_irq >> 3))
                 goto not_worth_the_effort;
-        }
 
 tryanotherirq:
         /* if we select an IRQ to move that can't go where we want, then
@@ -629,9 +613,6 @@ tryanotherirq:
         cpus_and(tmp, target_cpu_mask, allowed_mask);
 
         if (!cpus_empty(tmp)) {
-
-                Dprintk("irq = %d moved to cpu = %d\n",
-                                selected_irq, min_loaded);
                 /* mark for change destination */
                 set_pending_irq(selected_irq, cpumask_of_cpu(min_loaded));
 
@@ -651,7 +632,6 @@ not_worth_the_effort:
          */
         balanced_irq_interval = min((long)MAX_BALANCED_IRQ_INTERVAL,
                 balanced_irq_interval + BALANCED_IRQ_MORE_DELTA);       
-        Dprintk("IRQ worth rotating not found\n");
         return;
 }
 
@@ -1902,7 +1882,7 @@ __setup("no_timer_check", notimercheck);
  *      - if this function detects that timer IRQs are defunct, then we fall
  *        back to ISA timer IRQs
  */
-int __init timer_irq_works(void)
+static int __init timer_irq_works(void)
 {
         unsigned long t1 = jiffies;
 
diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c
index ba44d40b066d..dd2b97fc00b2 100644
--- a/arch/i386/kernel/irq.c
+++ b/arch/i386/kernel/irq.c
@@ -149,15 +149,11 @@ fastcall unsigned int do_IRQ(struct pt_regs *regs)
 
 #ifdef CONFIG_4KSTACKS
 
-/*
- * These should really be __section__(".bss.page_aligned") as well, but
- * gcc's 3.0 and earlier don't handle that correctly.
- */
 static char softirq_stack[NR_CPUS * THREAD_SIZE]
-                __attribute__((__aligned__(THREAD_SIZE)));
+                __attribute__((__section__(".bss.page_aligned")));
 
 static char hardirq_stack[NR_CPUS * THREAD_SIZE]
-                __attribute__((__aligned__(THREAD_SIZE)));
+                __attribute__((__section__(".bss.page_aligned")));
 
 /*
  * allocate per-cpu stacks for hardirq and for softirq processing
diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index dde828a333c3..448a50b1324c 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -35,6 +35,7 @@
 #include <asm/cacheflush.h>
 #include <asm/desc.h>
 #include <asm/uaccess.h>
+#include <asm/alternative.h>
 
 void jprobe_return_end(void);
 
@@ -169,16 +170,12 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 
 void __kprobes arch_arm_kprobe(struct kprobe *p)
 {
-        *p->addr = BREAKPOINT_INSTRUCTION;
-        flush_icache_range((unsigned long) p->addr,
-                           (unsigned long) p->addr + sizeof(kprobe_opcode_t));
+        text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1);
 }
 
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
-        *p->addr = p->opcode;
-        flush_icache_range((unsigned long) p->addr,
-                           (unsigned long) p->addr + sizeof(kprobe_opcode_t));
+        text_poke(p->addr, &p->opcode, 1);
 }
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index 03b7f5584d71..99beac7f96ce 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -353,7 +353,7 @@ __kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
          * Take the local apic timer and PIT/HPET into account. We don't
          * know which one is active, when we have highres/dyntick on
          */
-        sum = per_cpu(irq_stat, cpu).apic_timer_irqs + kstat_irqs(0);
+        sum = per_cpu(irq_stat, cpu).apic_timer_irqs + kstat_cpu(cpu).irqs[0];
 
         /* if the none of the timers isn't firing, this cpu isn't doing much */
         if (!touched && last_irq_sums[cpu] == sum) {
diff --git a/arch/i386/kernel/paravirt.c b/arch/i386/kernel/paravirt.c
index 53f07a8275e3..ea962c0667d5 100644
--- a/arch/i386/kernel/paravirt.c
+++ b/arch/i386/kernel/paravirt.c
@@ -124,20 +124,28 @@ unsigned paravirt_patch_ignore(unsigned len)
         return len;
 }
 
+struct branch {
+        unsigned char opcode;
+        u32 delta;
+} __attribute__((packed));
+
 unsigned paravirt_patch_call(void *target, u16 tgt_clobbers,
                              void *site, u16 site_clobbers,
                              unsigned len)
 {
         unsigned char *call = site;
         unsigned long delta = (unsigned long)target - (unsigned long)(call+5);
+        struct branch b;
 
         if (tgt_clobbers & ~site_clobbers)
                 return len;     /* target would clobber too much for this site */
         if (len < 5)
                 return len;     /* call too long for patch site */
 
-        *call++ = 0xe8;         /* call */
-        *(unsigned long *)call = delta;
+        b.opcode = 0xe8; /* call */
+        b.delta = delta;
+        BUILD_BUG_ON(sizeof(b) != 5);
+        text_poke(call, (unsigned char *)&b, 5);
 
         return 5;
 }
@@ -146,12 +154,14 @@ unsigned paravirt_patch_jmp(void *target, void *site, unsigned len)
 {
         unsigned char *jmp = site;
         unsigned long delta = (unsigned long)target - (unsigned long)(jmp+5);
+        struct branch b;
 
         if (len < 5)
                 return len;     /* call too long for patch site */
 
-        *jmp++ = 0xe9;          /* jmp */
-        *(unsigned long *)jmp = delta;
+        b.opcode = 0xe9;        /* jmp */
+        b.delta = delta;
+        text_poke(jmp, (unsigned char *)&b, 5);
 
         return 5;
 }
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 6c49acb96982..84664710b784 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -300,6 +300,7 @@ early_param("idle", idle_setup);
 void show_regs(struct pt_regs * regs)
 {
         unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
+        unsigned long d0, d1, d2, d3, d6, d7;
 
         printk("\n");
         printk("Pid: %d, comm: %20s\n", current->pid, current->comm);
@@ -324,6 +325,17 @@ void show_regs(struct pt_regs * regs)
         cr3 = read_cr3();
         cr4 = read_cr4_safe();
         printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4);
+
+        get_debugreg(d0, 0);
+        get_debugreg(d1, 1);
+        get_debugreg(d2, 2);
+        get_debugreg(d3, 3);
+        printk("DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
+                        d0, d1, d2, d3);
+        get_debugreg(d6, 6);
+        get_debugreg(d7, 7);
+        printk("DR6: %08lx DR7: %08lx\n", d6, d7);
+
         show_trace(NULL, regs, &regs->esp);
 }
 
diff --git a/arch/i386/kernel/reboot.c b/arch/i386/kernel/reboot.c
index 5513f8d5b5be..0d796248866c 100644
--- a/arch/i386/kernel/reboot.c
+++ b/arch/i386/kernel/reboot.c
@@ -113,6 +113,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
                         DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 300/"),
                 },
         },
+        {       /* Handle problems with rebooting on Dell Optiplex 745's SFF*/
+                .callback = set_bios_reboot,
+                .ident = "Dell OptiPlex 745",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"),
+                        DMI_MATCH(DMI_BOARD_NAME, "0WF810"),
+                },
+        },
         {       /* Handle problems with rebooting on Dell 2400's */
                 .callback = set_bios_reboot,
                 .ident = "Dell PowerEdge 2400",
diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c
index 74871d066c2b..d474cd639bcb 100644
--- a/arch/i386/kernel/setup.c
+++ b/arch/i386/kernel/setup.c
@@ -273,18 +273,18 @@ unsigned long __init find_max_low_pfn(void)
                 printk(KERN_WARNING "Warning only %ldMB will be used.\n",
                                         MAXMEM>>20);
                 if (max_pfn > MAX_NONPAE_PFN)
-                        printk(KERN_WARNING "Use a PAE enabled kernel.\n");
+                        printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n");
                 else
                         printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
                 max_pfn = MAXMEM_PFN;
 #else /* !CONFIG_HIGHMEM */
-#ifndef CONFIG_X86_PAE
+#ifndef CONFIG_HIGHMEM64G
                 if (max_pfn > MAX_NONPAE_PFN) {
                         max_pfn = MAX_NONPAE_PFN;
                         printk(KERN_WARNING "Warning only 4GB will be used.\n");
-                        printk(KERN_WARNING "Use a PAE enabled kernel.\n");
+                        printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n");
                 }
-#endif /* !CONFIG_X86_PAE */
+#endif /* !CONFIG_HIGHMEM64G */
 #endif /* !CONFIG_HIGHMEM */
         } else {
                 if (highmem_pages == -1)
@@ -466,7 +466,7 @@ void __init setup_bootmem_allocator(void)
  *
  * This should all compile down to nothing when NUMA is off.
  */
-void __init remapped_pgdat_init(void)
+static void __init remapped_pgdat_init(void)
 {
         int nid;
 
@@ -640,6 +640,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
         e820_register_memory();
+        e820_mark_nosave_regions();
 
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
diff --git a/arch/i386/kernel/signal.c b/arch/i386/kernel/signal.c
index d574e38f0f77..f5dd85656c18 100644
--- a/arch/i386/kernel/signal.c
+++ b/arch/i386/kernel/signal.c
@@ -199,6 +199,13 @@ asmlinkage int sys_sigreturn(unsigned long __unused)
         return eax;
 
 badframe:
+        if (show_unhandled_signals && printk_ratelimit())
+                printk("%s%s[%d] bad frame in sigreturn frame:%p eip:%lx"
+                       " esp:%lx oeax:%lx\n",
+                    current->pid > 1 ? KERN_INFO : KERN_EMERG,
+                    current->comm, current->pid, frame, regs->eip,
+                    regs->esp, regs->orig_eax);
+
         force_sig(SIGSEGV, current);
         return 0;
 }       
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index 5910d3fac561..e4f61d1c6248 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -308,7 +308,7 @@ cpumask_t cpu_coregroup_map(int cpu)
 /* representing cpus for which sibling maps can be computed */
 static cpumask_t cpu_sibling_setup_map;
 
-void set_cpu_sibling_map(int cpu)
+void __cpuinit set_cpu_sibling_map(int cpu)
 {
         int i;
         struct cpuinfo_x86 *c = cpu_data;
diff --git a/arch/i386/kernel/sysenter.c b/arch/i386/kernel/sysenter.c
index ff4ee6f3326b..6deb159d08e0 100644
--- a/arch/i386/kernel/sysenter.c
+++ b/arch/i386/kernel/sysenter.c
@@ -336,7 +336,9 @@ struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
 
 int in_gate_area(struct task_struct *task, unsigned long addr)
 {
-        return 0;
+        const struct vm_area_struct *vma = get_gate_vma(task);
+
+        return vma && addr >= vma->vm_start && addr < vma->vm_end;
 }
 
 int in_gate_area_no_task(unsigned long addr)
diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c
index a665df61f08c..19a6c678d02e 100644
--- a/arch/i386/kernel/time.c
+++ b/arch/i386/kernel/time.c
@@ -207,55 +207,9 @@ unsigned long read_persistent_clock(void)
         return retval;
 }
 
-static void sync_cmos_clock(unsigned long dummy);
-
-static DEFINE_TIMER(sync_cmos_timer, sync_cmos_clock, 0, 0);
-int no_sync_cmos_clock;
-
-static void sync_cmos_clock(unsigned long dummy)
-{
-        struct timeval now, next;
-        int fail = 1;
-
-        /*
-         * If we have an externally synchronized Linux clock, then update
-         * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
-         * called as close as possible to 500 ms before the new second starts.
-         * This code is run on a timer.  If the clock is set, that timer
-         * may not expire at the correct time.  Thus, we adjust...
-         */
-        if (!ntp_synced())
-                /*
-                 * Not synced, exit, do not restart a timer (if one is
-                 * running, let it run out).
-                 */
-                return;
-
-        do_gettimeofday(&now);
-        if (now.tv_usec >= USEC_AFTER - ((unsigned) TICK_SIZE) / 2 &&
-            now.tv_usec <= USEC_BEFORE + ((unsigned) TICK_SIZE) / 2)
-                fail = set_rtc_mmss(now.tv_sec);
-
-        next.tv_usec = USEC_AFTER - now.tv_usec;
-        if (next.tv_usec <= 0)
-                next.tv_usec += USEC_PER_SEC;
-
-        if (!fail)
-                next.tv_sec = 659;
-        else
-                next.tv_sec = 0;
-
-        if (next.tv_usec >= USEC_PER_SEC) {
-                next.tv_sec++;
-                next.tv_usec -= USEC_PER_SEC;
-        }
-        mod_timer(&sync_cmos_timer, jiffies + timeval_to_jiffies(&next));
-}
-
-void notify_arch_cmos_timer(void)
+int update_persistent_clock(struct timespec now)
 {
-        if (!no_sync_cmos_clock)
-                mod_timer(&sync_cmos_timer, jiffies + 1);
+        return set_rtc_mmss(now.tv_sec);
 }
 
 extern void (*late_time_init)(void);
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index 3e7753c78b9b..cfffe3dd9e83 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -152,7 +152,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
         if (!stack) {
                 unsigned long dummy;
                 stack = &dummy;
-                if (task && task != current)
+                if (task != current)
                         stack = (unsigned long *)task->thread.esp;
         }
 
@@ -211,6 +211,7 @@ static void print_trace_address(void *data, unsigned long addr)
 {
         printk("%s [<%08lx>] ", (char *)data, addr);
         print_symbol("%s\n", addr);
+        touch_nmi_watchdog();
 }
 
 static struct stacktrace_ops print_trace_ops = {
@@ -617,6 +618,13 @@ fastcall void __kprobes do_general_protection(struct pt_regs * regs,
 
         current->thread.error_code = error_code;
         current->thread.trap_no = 13;
+        if (show_unhandled_signals && unhandled_signal(current, SIGSEGV) &&
+            printk_ratelimit())
+                printk(KERN_INFO
+                    "%s[%d] general protection eip:%lx esp:%lx error:%lx\n",
+                    current->comm, current->pid,
+                    regs->eip, regs->esp, error_code);
+
         force_sig(SIGSEGV, current);
         return;
 
@@ -767,6 +775,8 @@ static __kprobes void default_do_nmi(struct pt_regs * regs)
         reassert_nmi();
 }
 
+static int ignore_nmis;
+
 fastcall __kprobes void do_nmi(struct pt_regs * regs, long error_code)
 {
         int cpu;
@@ -777,11 +787,24 @@ fastcall __kprobes void do_nmi(struct pt_regs * regs, long error_code)
 
         ++nmi_count(cpu);
 
-        default_do_nmi(regs);
+        if (!ignore_nmis)
+                default_do_nmi(regs);
 
         nmi_exit();
 }
 
+void stop_nmi(void)
+{
+        acpi_nmi_disable();
+        ignore_nmis++;
+}
+
+void restart_nmi(void)
+{
+        ignore_nmis--;
+        acpi_nmi_enable();
+}
+
 #ifdef CONFIG_KPROBES
 fastcall void __kprobes do_int3(struct pt_regs *regs, long error_code)
 {
diff --git a/arch/i386/kernel/vmiclock.c b/arch/i386/kernel/vmiclock.c
index f9b845f4e692..b1b5ab08b26e 100644
--- a/arch/i386/kernel/vmiclock.c
+++ b/arch/i386/kernel/vmiclock.c
@@ -32,6 +32,7 @@
 #include <asm/apicdef.h>
 #include <asm/apic.h>
 #include <asm/timer.h>
+#include <asm/i8253.h>
 
 #include <irq_vectors.h>
 #include "io_ports.h"
@@ -142,6 +143,7 @@ static void vmi_timer_set_mode(enum clock_event_mode mode,
 
         switch (mode) {
         case CLOCK_EVT_MODE_ONESHOT:
+        case CLOCK_EVT_MODE_RESUME:
                 break;
         case CLOCK_EVT_MODE_PERIODIC:
                 cycles_per_hz = vmi_timer_ops.get_cycle_frequency();
diff --git a/arch/i386/kernel/vsyscall-note.S b/arch/i386/kernel/vsyscall-note.S
index 271f16a8ca01..07c0daf78237 100644
--- a/arch/i386/kernel/vsyscall-note.S
+++ b/arch/i386/kernel/vsyscall-note.S
@@ -14,7 +14,6 @@ ELFNOTE_START(Linux, 0, "a")
 ELFNOTE_END
 
 #ifdef CONFIG_XEN
-
 /*
  * Add a special note telling glibc's dynamic linker a fake hardware
  * flavor that it will use to choose the search path for libraries in the
@@ -28,15 +27,19 @@ ELFNOTE_END
  * It should contain:
  *      hwcap 1 nosegneg
  * to match the mapping of bit to name that we give here.
+ *
+ * At runtime, the fake hardware feature will be considered to be present
+ * if its bit is set in the mask word.  So, we start with the mask 0, and
+ * at boot time we set VDSO_NOTE_NONEGSEG_BIT if running under Xen.
  */
 
-/* Bit used for the pseudo-hwcap for non-negative segments.  We use
-   bit 1 to avoid bugs in some versions of glibc when bit 0 is
-   used; the choice is otherwise arbitrary. */
-#define VDSO_NOTE_NONEGSEG_BIT  1
+#include "../xen/vdso.h"        /* Defines VDSO_NOTE_NONEGSEG_BIT.  */
 
+        .globl VDSO_NOTE_MASK
 ELFNOTE_START(GNU, 2, "a")
-        .long 1, 1<<VDSO_NOTE_NONEGSEG_BIT              /* ncaps, mask */
+        .long 1                 /* ncaps */
+VDSO_NOTE_MASK:
+        .long 0                 /* mask */
         .byte VDSO_NOTE_NONEGSEG_BIT; .asciz "nosegneg" /* bit, name */
 ELFNOTE_END
 #endif
diff --git a/arch/i386/lib/Makefile b/arch/i386/lib/Makefile
index 22d8ac5815f0..4d105fdfe817 100644
--- a/arch/i386/lib/Makefile
+++ b/arch/i386/lib/Makefile
@@ -4,7 +4,7 @@
 
 
 lib-y = checksum.o delay.o usercopy.o getuser.o putuser.o memcpy.o strstr.o \
-        bitops.o semaphore.o
+        bitops.o semaphore.o string.o
 
 lib-$(CONFIG_X86_USE_3DNOW) += mmx.o
 
diff --git a/arch/i386/lib/string.c b/arch/i386/lib/string.c
new file mode 100644
index 000000000000..2c773fefa3dd
--- /dev/null
+++ b/arch/i386/lib/string.c
@@ -0,0 +1,257 @@
+/*
+ * Most of the string-functions are rather heavily hand-optimized,
+ * see especially strsep,strstr,str[c]spn. They should work, but are not
+ * very easy to understand. Everything is done entirely within the register
+ * set, making the functions fast and clean. String instructions have been
+ * used through-out, making for "slightly" unclear code :-)
+ *
+ * AK: On P4 and K7 using non string instruction implementations might be faster
+ * for large memory blocks. But most of them are unlikely to be used on large
+ * strings.
+ */
+
+#include <linux/string.h>
+#include <linux/module.h>
+
+#ifdef __HAVE_ARCH_STRCPY
+char *strcpy(char * dest,const char *src)
+{
+        int d0, d1, d2;
+        asm volatile( "1:\tlodsb\n\t"
+                "stosb\n\t"
+                "testb %%al,%%al\n\t"
+                "jne 1b"
+                : "=&S" (d0), "=&D" (d1), "=&a" (d2)
+                :"0" (src),"1" (dest) : "memory");
+        return dest;
+}
+EXPORT_SYMBOL(strcpy);
+#endif
+
+#ifdef __HAVE_ARCH_STRNCPY
+char *strncpy(char * dest,const char *src,size_t count)
+{
+        int d0, d1, d2, d3;
+        asm volatile( "1:\tdecl %2\n\t"
+                "js 2f\n\t"
+                "lodsb\n\t"
+                "stosb\n\t"
+                "testb %%al,%%al\n\t"
+                "jne 1b\n\t"
+                "rep\n\t"
+                "stosb\n"
+                "2:"
+                : "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3)
+                :"0" (src),"1" (dest),"2" (count) : "memory");
+        return dest;
+}
+EXPORT_SYMBOL(strncpy);
+#endif
+
+#ifdef __HAVE_ARCH_STRCAT
+char *strcat(char * dest,const char * src)
+{
+        int d0, d1, d2, d3;
+        asm volatile( "repne\n\t"
+                "scasb\n\t"
+                "decl %1\n"
+                "1:\tlodsb\n\t"
+                "stosb\n\t"
+                "testb %%al,%%al\n\t"
+                "jne 1b"
+                : "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
+                : "0" (src), "1" (dest), "2" (0), "3" (0xffffffffu): "memory");
+        return dest;
+}
+EXPORT_SYMBOL(strcat);
+#endif
+
+#ifdef __HAVE_ARCH_STRNCAT
+char *strncat(char * dest,const char * src,size_t count)
+{
+        int d0, d1, d2, d3;
+        asm volatile( "repne\n\t"
+                "scasb\n\t"
+                "decl %1\n\t"
+                "movl %8,%3\n"
+                "1:\tdecl %3\n\t"
+                "js 2f\n\t"
+                "lodsb\n\t"
+                "stosb\n\t"
+                "testb %%al,%%al\n\t"
+                "jne 1b\n"
+                "2:\txorl %2,%2\n\t"
+                "stosb"
+                : "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
+                : "0" (src),"1" (dest),"2" (0),"3" (0xffffffffu), "g" (count)
+                : "memory");
+        return dest;
+}
+EXPORT_SYMBOL(strncat);
+#endif
+
+#ifdef __HAVE_ARCH_STRCMP
+int strcmp(const char * cs,const char * ct)
+{
+        int d0, d1;
+        int res;
+        asm volatile( "1:\tlodsb\n\t"
+                "scasb\n\t"
+                "jne 2f\n\t"
+                "testb %%al,%%al\n\t"
+                "jne 1b\n\t"
+                "xorl %%eax,%%eax\n\t"
+                "jmp 3f\n"
+                "2:\tsbbl %%eax,%%eax\n\t"
+                "orb $1,%%al\n"
+                "3:"
+                :"=a" (res), "=&S" (d0), "=&D" (d1)
+                :"1" (cs),"2" (ct)
+                :"memory");
+        return res;
+}
+EXPORT_SYMBOL(strcmp);
+#endif
+
+#ifdef __HAVE_ARCH_STRNCMP
+int strncmp(const char * cs,const char * ct,size_t count)
+{
+        int res;
+        int d0, d1, d2;
+        asm volatile( "1:\tdecl %3\n\t"
+                "js 2f\n\t"
+                "lodsb\n\t"
+                "scasb\n\t"
+                "jne 3f\n\t"
+                "testb %%al,%%al\n\t"
+                "jne 1b\n"
+                "2:\txorl %%eax,%%eax\n\t"
+                "jmp 4f\n"
+                "3:\tsbbl %%eax,%%eax\n\t"
+                "orb $1,%%al\n"
+                "4:"
+                :"=a" (res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
+                :"1" (cs),"2" (ct),"3" (count)
+                :"memory");
+        return res;
+}
+EXPORT_SYMBOL(strncmp);
+#endif
+
+#ifdef __HAVE_ARCH_STRCHR
+char *strchr(const char * s, int c)
+{
+        int d0;
+        char * res;
+        asm volatile( "movb %%al,%%ah\n"
+                "1:\tlodsb\n\t"
+                "cmpb %%ah,%%al\n\t"
+                "je 2f\n\t"
+                "testb %%al,%%al\n\t"
+                "jne 1b\n\t"
+                "movl $1,%1\n"
+                "2:\tmovl %1,%0\n\t"
+                "decl %0"
+                :"=a" (res), "=&S" (d0)
+                :"1" (s),"0" (c)
+                :"memory");
+        return res;
+}
+EXPORT_SYMBOL(strchr);
+#endif
+
+#ifdef __HAVE_ARCH_STRRCHR
+char *strrchr(const char * s, int c)
+{
+        int d0, d1;
+        char * res;
+        asm volatile( "movb %%al,%%ah\n"
+                "1:\tlodsb\n\t"
+                "cmpb %%ah,%%al\n\t"
+                "jne 2f\n\t"
+                "leal -1(%%esi),%0\n"
+                "2:\ttestb %%al,%%al\n\t"
+                "jne 1b"
+                :"=g" (res), "=&S" (d0), "=&a" (d1)
+                :"0" (0),"1" (s),"2" (c)
+                :"memory");
+        return res;
+}
+EXPORT_SYMBOL(strrchr);
+#endif
+
+#ifdef __HAVE_ARCH_STRLEN
+size_t strlen(const char * s)
+{
+        int d0;
+        int res;
+        asm volatile( "repne\n\t"
+                "scasb\n\t"
+                "notl %0\n\t"
+                "decl %0"
+                :"=c" (res), "=&D" (d0)
+                :"1" (s),"a" (0), "0" (0xffffffffu)
+                :"memory");
+        return res;
+}
+EXPORT_SYMBOL(strlen);
+#endif
+
+#ifdef __HAVE_ARCH_MEMCHR
+void *memchr(const void *cs,int c,size_t count)
+{
+        int d0;
+        void *res;
+        if (!count)
+                return NULL;
+        asm volatile( "repne\n\t"
+                "scasb\n\t"
+                "je 1f\n\t"
+                "movl $1,%0\n"
+                "1:\tdecl %0"
+                :"=D" (res), "=&c" (d0)
+                :"a" (c),"0" (cs),"1" (count)
+                :"memory");
+        return res;
+}
+EXPORT_SYMBOL(memchr);
+#endif
+
+#ifdef __HAVE_ARCH_MEMSCAN
+void *memscan(void * addr, int c, size_t size)
+{
+        if (!size)
+                return addr;
+        asm volatile("repnz; scasb\n\t"
+            "jnz 1f\n\t"
+            "dec %%edi\n"
+            "1:"
+            : "=D" (addr), "=c" (size)
+            : "0" (addr), "1" (size), "a" (c)
+            : "memory");
+        return addr;
+}
+EXPORT_SYMBOL(memscan);
+#endif
+
+#ifdef __HAVE_ARCH_STRNLEN
+size_t strnlen(const char *s, size_t count)
+{
+        int d0;
+        int res;
+        asm volatile( "movl %2,%0\n\t"
+                "jmp 2f\n"
+                "1:\tcmpb $0,(%0)\n\t"
+                "je 3f\n\t"
+                "incl %0\n"
+                "2:\tdecl %1\n\t"
+                "cmpl $-1,%1\n\t"
+                "jne 1b\n"
+                "3:\tsubl %2,%0"
+                :"=a" (res), "=&d" (d0)
+                :"c" (s),"1" (count)
+                :"memory");
+        return res;
+}
+EXPORT_SYMBOL(strnlen);
+#endif
diff --git a/arch/i386/mm/fault.c b/arch/i386/mm/fault.c
index e92a10124935..01ffdd4964f0 100644
--- a/arch/i386/mm/fault.c
+++ b/arch/i386/mm/fault.c
@@ -283,6 +283,8 @@ static inline int vmalloc_fault(unsigned long address)
         return 0;
 }
 
+int show_unhandled_signals = 1;
+
 /*
  * This routine handles page faults.  It determines the address,
  * and the problem, and then passes it off to one of the appropriate
@@ -469,6 +471,14 @@ bad_area_nosemaphore:
                 if (is_prefetch(regs, address, error_code))
                         return;
 
+                if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
+                    printk_ratelimit()) {
+                        printk("%s%s[%d]: segfault at %08lx eip %08lx "
+                            "esp %08lx error %lx\n",
+                            tsk->pid > 1 ? KERN_INFO : KERN_EMERG,
+                            tsk->comm, tsk->pid, address, regs->eip,
+                            regs->esp, error_code);
+                }
                 tsk->thread.cr2 = address;
                 /* Kernel addresses are always protection faults */
                 tsk->thread.error_code = error_code | (address >= TASK_SIZE);
diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c
index 6e72f22e6bbd..c3b9905af2d5 100644
--- a/arch/i386/mm/init.c
+++ b/arch/i386/mm/init.c
@@ -471,6 +471,10 @@ void zap_low_mappings (void)
         flush_tlb_all();
 }
 
+int nx_enabled = 0;
+
+#ifdef CONFIG_X86_PAE
+
 static int disable_nx __initdata = 0;
 u64 __supported_pte_mask __read_mostly = ~_PAGE_NX;
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
@@ -500,9 +504,6 @@ static int __init noexec_setup(char *str)
 }
 early_param("noexec", noexec_setup);
 
-int nx_enabled = 0;
-#ifdef CONFIG_X86_PAE
-
 static void __init set_nx(void)
 {
         unsigned int v[4], l, h;
@@ -799,17 +800,9 @@ void mark_rodata_ro(void)
         unsigned long start = PFN_ALIGN(_text);
         unsigned long size = PFN_ALIGN(_etext) - start;
 
-#ifndef CONFIG_KPROBES
-#ifdef CONFIG_HOTPLUG_CPU
-        /* It must still be possible to apply SMP alternatives. */
-        if (num_possible_cpus() <= 1)
-#endif
-        {
-                change_page_attr(virt_to_page(start),
-                                 size >> PAGE_SHIFT, PAGE_KERNEL_RX);
-                printk("Write protecting the kernel text: %luk\n", size >> 10);
-        }
-#endif
+        change_page_attr(virt_to_page(start),
+                         size >> PAGE_SHIFT, PAGE_KERNEL_RX);
+        printk("Write protecting the kernel text: %luk\n", size >> 10);
         start += size;
         size = (unsigned long)__end_rodata - start;
         change_page_attr(virt_to_page(start),
diff --git a/arch/i386/mm/ioremap.c b/arch/i386/mm/ioremap.c
index fff08ae7b5ed..0b278315d737 100644
--- a/arch/i386/mm/ioremap.c
+++ b/arch/i386/mm/ioremap.c
@@ -196,7 +196,7 @@ void iounmap(volatile void __iomem *addr)
         /* Reset the direct mapping. Can block */
         if ((p->flags >> 20) && p->phys_addr < virt_to_phys(high_memory) - 1) {
                 change_page_attr(virt_to_page(__va(p->phys_addr)),
-                                 p->size >> PAGE_SHIFT,
+                                 get_vm_area_size(p) >> PAGE_SHIFT,
                                  PAGE_KERNEL);
                 global_flush_tlb();
         } 
diff --git a/arch/i386/mm/pageattr.c b/arch/i386/mm/pageattr.c
index 37992ffb1633..8927222b3ab2 100644
--- a/arch/i386/mm/pageattr.c
+++ b/arch/i386/mm/pageattr.c
@@ -82,7 +82,7 @@ static void flush_kernel_map(void *arg)
         struct page *p;
 
         /* High level code is not ready for clflush yet */
-        if (0 && cpu_has_clflush) {
+        if (cpu_has_clflush) {
                 list_for_each_entry (p, lh, lru)
                         cache_flush_page(p);
         } else if (boot_cpu_data.x86_model >= 4)
@@ -136,6 +136,12 @@ static inline void revert_page(struct page *kpte_page, unsigned long address)
                             ref_prot));
 }
 
+static inline void save_page(struct page *kpte_page)
+{
+        if (!test_and_set_bit(PG_arch_1, &kpte_page->flags))
+                list_add(&kpte_page->lru, &df_list);
+}
+
 static int
 __change_page_attr(struct page *page, pgprot_t prot)
 { 
@@ -150,6 +156,9 @@ __change_page_attr(struct page *page, pgprot_t prot)
         if (!kpte)
                 return -EINVAL;
         kpte_page = virt_to_page(kpte);
+        BUG_ON(PageLRU(kpte_page));
+        BUG_ON(PageCompound(kpte_page));
+
         if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) { 
                 if (!pte_huge(*kpte)) {
                         set_pte_atomic(kpte, mk_pte(page, prot)); 
@@ -179,11 +188,11 @@ __change_page_attr(struct page *page, pgprot_t prot)
          * time (not via split_large_page) and in turn we must not
          * replace it with a largepage.
          */
+
+        save_page(kpte_page);
         if (!PageReserved(kpte_page)) {
                 if (cpu_has_pse && (page_private(kpte_page) == 0)) {
-                        ClearPagePrivate(kpte_page);
                         paravirt_release_pt(page_to_pfn(kpte_page));
-                        list_add(&kpte_page->lru, &df_list);
                         revert_page(kpte_page, address);
                 }
         }
@@ -236,6 +245,11 @@ void global_flush_tlb(void)
         spin_unlock_irq(&cpa_lock);
         flush_map(&l);
         list_for_each_entry_safe(pg, next, &l, lru) {
+                list_del(&pg->lru);
+                clear_bit(PG_arch_1, &pg->flags);
+                if (PageReserved(pg) || !cpu_has_pse || page_private(pg) != 0)
+                        continue;
+                ClearPagePrivate(pg);
                 __free_page(pg);
         }
 }
diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c
index 8d7c0864cc04..01437c46baae 100644
--- a/arch/i386/mm/pgtable.c
+++ b/arch/i386/mm/pgtable.c
@@ -235,7 +235,7 @@ static inline void pgd_list_del(pgd_t *pgd)
 
 #if (PTRS_PER_PMD == 1)
 /* Non-PAE pgd constructor */
-void pgd_ctor(void *pgd)
+static void pgd_ctor(void *pgd)
 {
         unsigned long flags;
 
@@ -257,7 +257,7 @@ void pgd_ctor(void *pgd)
 }
 #else  /* PTRS_PER_PMD > 1 */
 /* PAE pgd constructor */
-void pgd_ctor(void *pgd)
+static void pgd_ctor(void *pgd)
 {
         /* PAE, kernel PMD may be shared */
 
@@ -276,7 +276,7 @@ void pgd_ctor(void *pgd)
 }
 #endif  /* PTRS_PER_PMD */
 
-void pgd_dtor(void *pgd)
+static void pgd_dtor(void *pgd)
 {
         unsigned long flags; /* can be called from interrupt context */
 
diff --git a/arch/i386/pci/acpi.c b/arch/i386/pci/acpi.c
index b33aea845f58..bc8a44bddaa7 100644
--- a/arch/i386/pci/acpi.c
+++ b/arch/i386/pci/acpi.c
@@ -8,20 +8,42 @@
 struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int domain, int busnum)
 {
         struct pci_bus *bus;
+        struct pci_sysdata *sd;
+        int pxm;
+
+        /* Allocate per-root-bus (not per bus) arch-specific data.
+         * TODO: leak; this memory is never freed.
+         * It's arguable whether it's worth the trouble to care.
+         */
+        sd = kzalloc(sizeof(*sd), GFP_KERNEL);
+        if (!sd) {
+                printk(KERN_ERR "PCI: OOM, not probing PCI bus %02x\n", busnum);
+                return NULL;
+        }
 
         if (domain != 0) {
                 printk(KERN_WARNING "PCI: Multiple domains not supported\n");
+                kfree(sd);
                 return NULL;
         }
 
-        bus = pcibios_scan_root(busnum);
+        sd->node = -1;
+
+        pxm = acpi_get_pxm(device->handle);
+#ifdef CONFIG_ACPI_NUMA
+        if (pxm >= 0)
+                sd->node = pxm_to_node(pxm);
+#endif
+
+        bus = pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd);
+        if (!bus)
+                kfree(sd);
+
 #ifdef CONFIG_ACPI_NUMA
         if (bus != NULL) {
-                int pxm = acpi_get_pxm(device->handle);
                 if (pxm >= 0) {
-                        bus->sysdata = (void *)(unsigned long)pxm_to_node(pxm);
-                        printk("bus %d -> pxm %d -> node %ld\n",
-                                busnum, pxm, (long)(bus->sysdata));
+                        printk("bus %d -> pxm %d -> node %d\n",
+                                busnum, pxm, sd->node);
                 }
         }
 #endif
diff --git a/arch/i386/pci/common.c b/arch/i386/pci/common.c
index 3f78d4d8ecf3..85503deeda46 100644
--- a/arch/i386/pci/common.c
+++ b/arch/i386/pci/common.c
@@ -293,6 +293,7 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = {
 struct pci_bus * __devinit pcibios_scan_root(int busnum)
 {
         struct pci_bus *bus = NULL;
+        struct pci_sysdata *sd;
 
         dmi_check_system(pciprobe_dmi_table);
 
@@ -303,9 +304,19 @@ struct pci_bus * __devinit pcibios_scan_root(int busnum)
                 }
         }
 
+        /* Allocate per-root-bus (not per bus) arch-specific data.
+         * TODO: leak; this memory is never freed.
+         * It's arguable whether it's worth the trouble to care.
+         */
+        sd = kzalloc(sizeof(*sd), GFP_KERNEL);
+        if (!sd) {
+                printk(KERN_ERR "PCI: OOM, not probing PCI bus %02x\n", busnum);
+                return NULL;
+        }
+
         printk(KERN_DEBUG "PCI: Probing PCI hardware (bus %02x)\n", busnum);
 
-        return pci_scan_bus_parented(NULL, busnum, &pci_root_ops, NULL);
+        return pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd);
 }
 
 extern u8 pci_cache_line_size;
diff --git a/arch/i386/pci/mmconfig-shared.c b/arch/i386/pci/mmconfig-shared.c
index c7cabeed4d7b..4df637e34f81 100644
--- a/arch/i386/pci/mmconfig-shared.c
+++ b/arch/i386/pci/mmconfig-shared.c
@@ -24,6 +24,9 @@
 
 DECLARE_BITMAP(pci_mmcfg_fallback_slots, 32*PCI_MMCFG_MAX_CHECK_BUS);
 
+/* Indicate if the mmcfg resources have been placed into the resource table. */
+static int __initdata pci_mmcfg_resources_inserted;
+
 /* K8 systems have some devices (typically in the builtin northbridge)
    that are only accessible using type1
    Normally this can be expressed in the MCFG by not listing them
@@ -170,7 +173,7 @@ static int __init pci_mmcfg_check_hostbridge(void)
         return name != NULL;
 }
 
-static void __init pci_mmcfg_insert_resources(void)
+static void __init pci_mmcfg_insert_resources(unsigned long resource_flags)
 {
 #define PCI_MMCFG_RESOURCE_NAME_LEN 19
         int i;
@@ -194,10 +197,13 @@ static void __init pci_mmcfg_insert_resources(void)
                          cfg->pci_segment);
                 res->start = cfg->address;
                 res->end = res->start + (num_buses << 20) - 1;
-                res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+                res->flags = IORESOURCE_MEM | resource_flags;
                 insert_resource(&iomem_resource, res);
                 names += PCI_MMCFG_RESOURCE_NAME_LEN;
         }
+
+        /* Mark that the resources have been inserted. */
+        pci_mmcfg_resources_inserted = 1;
 }
 
 static void __init pci_mmcfg_reject_broken(int type)
@@ -267,7 +273,43 @@ void __init pci_mmcfg_init(int type)
                 if (type == 1)
                         unreachable_devices();
                 if (known_bridge)
-                        pci_mmcfg_insert_resources();
+                        pci_mmcfg_insert_resources(IORESOURCE_BUSY);
                 pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;
+        } else {
+                /*
+                 * Signal not to attempt to insert mmcfg resources because
+                 * the architecture mmcfg setup could not initialize.
+                 */
+                pci_mmcfg_resources_inserted = 1;
         }
 }
+
+static int __init pci_mmcfg_late_insert_resources(void)
+{
+        /*
+         * If resources are already inserted or we are not using MMCONFIG,
+         * don't insert the resources.
+         */
+        if ((pci_mmcfg_resources_inserted == 1) ||
+            (pci_probe & PCI_PROBE_MMCONF) == 0 ||
+            (pci_mmcfg_config_num == 0) ||
+            (pci_mmcfg_config == NULL) ||
+            (pci_mmcfg_config[0].address == 0))
+                return 1;
+
+        /*
+         * Attempt to insert the mmcfg resources but not with the busy flag
+         * marked so it won't cause request errors when __request_region is
+         * called.
+         */
+        pci_mmcfg_insert_resources(0);
+
+        return 0;
+}
+
+/*
+ * Perform MMCONFIG resource insertion after PCI initialization to allow for
+ * misprogrammed MCFG tables that state larger sizes but actually conflict
+ * with other system resources.
+ */
+late_initcall(pci_mmcfg_late_insert_resources);
diff --git a/arch/i386/xen/events.c b/arch/i386/xen/events.c
index 8904acc20f8c..da1b173547a1 100644
--- a/arch/i386/xen/events.c
+++ b/arch/i386/xen/events.c
@@ -31,6 +31,7 @@
 #include <asm/irq.h>
 #include <asm/sync_bitops.h>
 #include <asm/xen/hypercall.h>
+#include <asm/xen/hypervisor.h>
 
 #include <xen/events.h>
 #include <xen/interface/xen.h>
diff --git a/arch/i386/xen/setup.c b/arch/i386/xen/setup.c
index 2fe6eac510f0..f84e77226646 100644
--- a/arch/i386/xen/setup.c
+++ b/arch/i386/xen/setup.c
@@ -19,6 +19,7 @@
 #include <xen/features.h>
 
 #include "xen-ops.h"
+#include "vdso.h"
 
 /* These are code, but not functions.  Defined in entry.S */
 extern const char xen_hypervisor_callback[];
@@ -55,6 +56,18 @@ static void xen_idle(void)
         }
 }
 
+/*
+ * Set the bit indicating "nosegneg" library variants should be used.
+ */
+static void fiddle_vdso(void)
+{
+        extern u32 VDSO_NOTE_MASK; /* See ../kernel/vsyscall-note.S.  */
+        extern char vsyscall_int80_start;
+        u32 *mask = (u32 *) ((unsigned long) &VDSO_NOTE_MASK - VDSO_PRELINK +
+                             &vsyscall_int80_start);
+        *mask |= 1 << VDSO_NOTE_NONEGSEG_BIT;
+}
+
 void __init xen_arch_setup(void)
 {
         struct physdev_set_iopl set_iopl;
@@ -93,4 +106,6 @@ void __init xen_arch_setup(void)
 #endif
 
         paravirt_disable_iospace();
+
+        fiddle_vdso();
 }
diff --git a/arch/i386/xen/time.c b/arch/i386/xen/time.c
index 51fdabf1fd4d..dfd6db69ead5 100644
--- a/arch/i386/xen/time.c
+++ b/arch/i386/xen/time.c
@@ -412,6 +412,7 @@ static void xen_timerop_set_mode(enum clock_event_mode mode,
                 break;
 
         case CLOCK_EVT_MODE_ONESHOT:
+        case CLOCK_EVT_MODE_RESUME:
                 break;
 
         case CLOCK_EVT_MODE_UNUSED:
@@ -474,6 +475,8 @@ static void xen_vcpuop_set_mode(enum clock_event_mode mode,
                     HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL))
                         BUG();
                 break;
+        case CLOCK_EVT_MODE_RESUME:
+                break;
         }
 }
 
diff --git a/arch/i386/xen/vdso.h b/arch/i386/xen/vdso.h
new file mode 100644
index 000000000000..861fedfe5230
--- /dev/null
+++ b/arch/i386/xen/vdso.h
@@ -0,0 +1,4 @@
+/* Bit used for the pseudo-hwcap for non-negative segments.  We use
+   bit 1 to avoid bugs in some versions of glibc when bit 0 is
+   used; the choice is otherwise arbitrary. */
+#define VDSO_NOTE_NONEGSEG_BIT  1
diff --git a/arch/i386/xen/xen-head.S b/arch/i386/xen/xen-head.S
index 2998d55a0017..bc71f3bc4014 100644
--- a/arch/i386/xen/xen-head.S
+++ b/arch/i386/xen/xen-head.S
@@ -7,6 +7,7 @@
 #include <asm/boot.h>
 #include <xen/interface/elfnote.h>
 
+        .section .init.text
 ENTRY(startup_xen)
         movl %esi,xen_start_info
         cld
@@ -19,6 +20,7 @@ ENTRY(hypercall_page)
         .skip 0x1000
 .popsection
 
+        .section .text
         ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS,       .asciz "linux")
         ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION,  .asciz "2.6")
         ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION,    .asciz "xen-3.0")
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 616c96e73483..36c7b9682aa6 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -62,7 +62,11 @@ config GENERIC_CALIBRATE_DELAY
         bool
         default y
 
-config TIME_INTERPOLATION
+config GENERIC_TIME
+        bool
+        default y
+
+config GENERIC_TIME_VSYSCALL
         bool
         default y
 
diff --git a/arch/ia64/configs/bigsur_defconfig b/arch/ia64/configs/bigsur_defconfig
index 90e9c2e61bf4..9eb48c0927b0 100644
--- a/arch/ia64/configs/bigsur_defconfig
+++ b/arch/ia64/configs/bigsur_defconfig
@@ -85,7 +85,7 @@ CONFIG_MMU=y
 CONFIG_SWIOTLB=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_TIME_INTERPOLATION=y
+CONFIG_GENERIC_TIME=y
 CONFIG_EFI=y
 CONFIG_GENERIC_IOMAP=y
 CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
diff --git a/arch/ia64/configs/gensparse_defconfig b/arch/ia64/configs/gensparse_defconfig
index 0d29aa2066b3..3a9ed951db08 100644
--- a/arch/ia64/configs/gensparse_defconfig
+++ b/arch/ia64/configs/gensparse_defconfig
@@ -86,7 +86,7 @@ CONFIG_MMU=y
 CONFIG_SWIOTLB=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_TIME_INTERPOLATION=y
+CONFIG_GENERIC_TIME=y
 CONFIG_EFI=y
 CONFIG_GENERIC_IOMAP=y
 CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
diff --git a/arch/ia64/configs/sim_defconfig b/arch/ia64/configs/sim_defconfig
index d9146c31ea13..c420d9f3df98 100644
--- a/arch/ia64/configs/sim_defconfig
+++ b/arch/ia64/configs/sim_defconfig
@@ -86,7 +86,7 @@ CONFIG_MMU=y
 CONFIG_SWIOTLB=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_TIME_INTERPOLATION=y
+CONFIG_GENERIC_TIME=y
 CONFIG_EFI=y
 CONFIG_GENERIC_IOMAP=y
 CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
diff --git a/arch/ia64/configs/sn2_defconfig b/arch/ia64/configs/sn2_defconfig
index 64e951de4e57..4c9ffc47bc7a 100644
--- a/arch/ia64/configs/sn2_defconfig
+++ b/arch/ia64/configs/sn2_defconfig
@@ -93,7 +93,7 @@ CONFIG_SWIOTLB=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_TIME_INTERPOLATION=y
+CONFIG_GENERIC_TIME=y
 CONFIG_DMI=y
 CONFIG_EFI=y
 CONFIG_GENERIC_IOMAP=y
diff --git a/arch/ia64/configs/tiger_defconfig b/arch/ia64/configs/tiger_defconfig
index a1446931b401..3dbb3987df27 100644
--- a/arch/ia64/configs/tiger_defconfig
+++ b/arch/ia64/configs/tiger_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.21-rc3
-# Thu Mar  8 11:07:09 2007
+# Linux kernel version: 2.6.22
+# Thu Jul 19 13:54:47 2007
 #
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
 
@@ -19,15 +19,15 @@ CONFIG_LOCALVERSION=""
 CONFIG_LOCALVERSION_AUTO=y
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
-# CONFIG_IPC_NS is not set
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
-# CONFIG_UTS_NS is not set
+# CONFIG_USER_NS is not set
 # CONFIG_AUDIT is not set
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=20
 # CONFIG_CPUSETS is not set
 CONFIG_SYSFS_DEPRECATED=y
 # CONFIG_RELAY is not set
@@ -46,18 +46,19 @@ CONFIG_BUG=y
 CONFIG_ELF_CORE=y
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
+CONFIG_ANON_INODES=y
 CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
 CONFIG_SHMEM=y
-CONFIG_SLAB=y
 CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_SLAB=y
+# CONFIG_SLUB is not set
+# CONFIG_SLOB is not set
 CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
-# CONFIG_SLOB is not set
-
-#
-# Loadable module support
-#
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_FORCE_UNLOAD is not set
@@ -65,12 +66,9 @@ CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
 CONFIG_KMOD=y
 CONFIG_STOP_MACHINE=y
-
-#
-# Block layer
-#
 CONFIG_BLOCK=y
 # CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_BLK_DEV_BSG is not set
 
 #
 # IO Schedulers
@@ -91,6 +89,7 @@ CONFIG_DEFAULT_IOSCHED="anticipatory"
 CONFIG_IA64=y
 CONFIG_64BIT=y
 CONFIG_ZONE_DMA=y
+CONFIG_QUICKLIST=y
 CONFIG_MMU=y
 CONFIG_SWIOTLB=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
@@ -98,7 +97,7 @@ CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
 CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_TIME_INTERPOLATION=y
+CONFIG_GENERIC_TIME=y
 CONFIG_DMI=y
 CONFIG_EFI=y
 CONFIG_GENERIC_IOMAP=y
@@ -114,8 +113,8 @@ CONFIG_IA64_DIG=y
 CONFIG_MCKINLEY=y
 # CONFIG_IA64_PAGE_SIZE_4KB is not set
 # CONFIG_IA64_PAGE_SIZE_8KB is not set
-CONFIG_IA64_PAGE_SIZE_16KB=y
-# CONFIG_IA64_PAGE_SIZE_64KB is not set
+# CONFIG_IA64_PAGE_SIZE_16KB is not set
+CONFIG_IA64_PAGE_SIZE_64KB=y
 CONFIG_PGTABLE_3=y
 # CONFIG_PGTABLE_4 is not set
 # CONFIG_HZ_100 is not set
@@ -145,6 +144,9 @@ CONFIG_FLAT_NODE_MEM_MAP=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
 CONFIG_RESOURCES_64BIT=y
 CONFIG_ZONE_DMA_FLAG=1
+CONFIG_BOUNCE=y
+CONFIG_NR_QUICK=1
+CONFIG_VIRT_TO_BUS=y
 CONFIG_ARCH_SELECT_MEMORY_MODEL=y
 CONFIG_ARCH_DISCONTIGMEM_ENABLE=y
 CONFIG_ARCH_FLATMEM_ENABLE=y
@@ -152,11 +154,11 @@ CONFIG_ARCH_SPARSEMEM_ENABLE=y
 CONFIG_ARCH_POPULATES_NODE_MAP=y
 CONFIG_VIRTUAL_MEM_MAP=y
 CONFIG_HOLES_IN_ZONE=y
-CONFIG_IA32_SUPPORT=y
-CONFIG_COMPAT=y
+# CONFIG_IA32_SUPPORT is not set
 CONFIG_IA64_MCA_RECOVERY=y
 CONFIG_PERFMON=y
 CONFIG_IA64_PALINFO=y
+# CONFIG_IA64_MC_ERR_INJECT is not set
 # CONFIG_IA64_ESI is not set
 CONFIG_KEXEC=y
 # CONFIG_CRASH_DUMP is not set
@@ -166,6 +168,7 @@ CONFIG_KEXEC=y
 #
 CONFIG_EFI_VARS=y
 CONFIG_EFI_PCDP=y
+CONFIG_DMIID=y
 CONFIG_BINFMT_ELF=y
 CONFIG_BINFMT_MISC=m
 
@@ -175,7 +178,6 @@ CONFIG_BINFMT_MISC=m
 CONFIG_PM=y
 CONFIG_PM_LEGACY=y
 # CONFIG_PM_DEBUG is not set
-# CONFIG_PM_SYSFS_DEPRECATED is not set
 
 #
 # ACPI (Advanced Configuration and Power Interface) Support
@@ -205,13 +207,11 @@ CONFIG_ACPI_CONTAINER=m
 #
 CONFIG_PCI=y
 CONFIG_PCI_DOMAINS=y
+CONFIG_PCI_SYSCALL=y
 # CONFIG_PCIEPORTBUS is not set
+CONFIG_ARCH_SUPPORTS_MSI=y
 # CONFIG_PCI_MSI is not set
 # CONFIG_PCI_DEBUG is not set
-
-#
-# PCI Hotplug Support
-#
 CONFIG_HOTPLUG_PCI=m
 # CONFIG_HOTPLUG_PCI_FAKE is not set
 CONFIG_HOTPLUG_PCI_ACPI=m
@@ -232,7 +232,6 @@ CONFIG_NET=y
 #
 # Networking options
 #
-# CONFIG_NETDEBUG is not set
 CONFIG_PACKET=y
 # CONFIG_PACKET_MMAP is not set
 CONFIG_UNIX=y
@@ -270,20 +269,8 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 # CONFIG_INET6_TUNNEL is not set
 # CONFIG_NETWORK_SECMARK is not set
 # CONFIG_NETFILTER is not set
-
-#
-# DCCP Configuration (EXPERIMENTAL)
-#
 # CONFIG_IP_DCCP is not set
-
-#
-# SCTP Configuration (EXPERIMENTAL)
-#
 # CONFIG_IP_SCTP is not set
-
-#
-# TIPC Configuration (EXPERIMENTAL)
-#
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
 # CONFIG_BRIDGE is not set
@@ -309,7 +296,17 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 # CONFIG_HAMRADIO is not set
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
+# CONFIG_AF_RXRPC is not set
+
+#
+# Wireless
+#
+# CONFIG_CFG80211 is not set
+# CONFIG_WIRELESS_EXT is not set
+# CONFIG_MAC80211 is not set
 # CONFIG_IEEE80211 is not set
+# CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
 
 #
 # Device Drivers
@@ -324,25 +321,9 @@ CONFIG_FW_LOADER=m
 # CONFIG_DEBUG_DRIVER is not set
 # CONFIG_DEBUG_DEVRES is not set
 # CONFIG_SYS_HYPERVISOR is not set
-
-#
-# Connector - unified userspace <-> kernelspace linker
-#
 # CONFIG_CONNECTOR is not set
-
-#
-# Memory Technology Devices (MTD)
-#
 # CONFIG_MTD is not set
-
-#
-# Parallel port support
-#
 # CONFIG_PARPORT is not set
-
-#
-# Plug and Play support
-#
 CONFIG_PNP=y
 # CONFIG_PNP_DEBUG is not set
 
@@ -350,10 +331,7 @@ CONFIG_PNP=y
 # Protocols
 #
 CONFIG_PNPACPI=y
-
-#
-# Block devices
-#
+CONFIG_BLK_DEV=y
 # CONFIG_BLK_CPQ_DA is not set
 # CONFIG_BLK_CPQ_CISS_DA is not set
 # CONFIG_BLK_DEV_DAC960 is not set
@@ -370,16 +348,11 @@ CONFIG_BLK_DEV_RAM_SIZE=4096
 CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
 # CONFIG_CDROM_PKTCDVD is not set
 # CONFIG_ATA_OVER_ETH is not set
-
-#
-# Misc devices
-#
+CONFIG_MISC_DEVICES=y
+# CONFIG_PHANTOM is not set
+# CONFIG_EEPROM_93CX6 is not set
 # CONFIG_SGI_IOC4 is not set
 # CONFIG_TIFM_CORE is not set
-
-#
-# ATA/ATAPI/MFM/RLL support
-#
 CONFIG_IDE=y
 CONFIG_IDE_MAX_HWIFS=4
 CONFIG_BLK_DEV_IDE=y
@@ -396,6 +369,7 @@ CONFIG_BLK_DEV_IDEFLOPPY=y
 CONFIG_BLK_DEV_IDESCSI=m
 # CONFIG_BLK_DEV_IDEACPI is not set
 # CONFIG_IDE_TASK_IOCTL is not set
+CONFIG_IDE_PROC_FS=y
 
 #
 # IDE chipset support/bugfixes
@@ -404,12 +378,12 @@ CONFIG_BLK_DEV_IDESCSI=m
 # CONFIG_BLK_DEV_IDEPNP is not set
 CONFIG_BLK_DEV_IDEPCI=y
 # CONFIG_IDEPCI_SHARE_IRQ is not set
+CONFIG_IDEPCI_PCIBUS_ORDER=y
 # CONFIG_BLK_DEV_OFFBOARD is not set
 CONFIG_BLK_DEV_GENERIC=y
 # CONFIG_BLK_DEV_OPTI621 is not set
 CONFIG_BLK_DEV_IDEDMA_PCI=y
 # CONFIG_BLK_DEV_IDEDMA_FORCED is not set
-CONFIG_IDEDMA_PCI_AUTO=y
 # CONFIG_IDEDMA_ONLYDISK is not set
 # CONFIG_BLK_DEV_AEC62XX is not set
 # CONFIG_BLK_DEV_ALI15X3 is not set
@@ -438,7 +412,6 @@ CONFIG_BLK_DEV_PIIX=y
 # CONFIG_IDE_ARM is not set
 CONFIG_BLK_DEV_IDEDMA=y
 # CONFIG_IDEDMA_IVB is not set
-CONFIG_IDEDMA_AUTO=y
 # CONFIG_BLK_DEV_HD is not set
 
 #
@@ -446,6 +419,7 @@ CONFIG_IDEDMA_AUTO=y
 #
 # CONFIG_RAID_ATTRS is not set
 CONFIG_SCSI=y
+CONFIG_SCSI_DMA=y
 # CONFIG_SCSI_TGT is not set
 CONFIG_SCSI_NETLINK=y
 CONFIG_SCSI_PROC_FS=y
@@ -468,6 +442,7 @@ CONFIG_CHR_DEV_SG=m
 # CONFIG_SCSI_CONSTANTS is not set
 # CONFIG_SCSI_LOGGING is not set
 # CONFIG_SCSI_SCAN_ASYNC is not set
+CONFIG_SCSI_WAIT_SCAN=m
 
 #
 # SCSI Transports
@@ -514,15 +489,7 @@ CONFIG_SCSI_QLOGIC_1280=y
 # CONFIG_SCSI_DC390T is not set
 # CONFIG_SCSI_DEBUG is not set
 # CONFIG_SCSI_SRP is not set
-
-#
-# Serial ATA (prod) and Parallel ATA (experimental) drivers
-#
 # CONFIG_ATA is not set
-
-#
-# Multi-device support (RAID and LVM)
-#
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=m
 CONFIG_MD_LINEAR=m
@@ -539,6 +506,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_ZERO=m
 # CONFIG_DM_MULTIPATH is not set
+# CONFIG_DM_DELAY is not set
 
 #
 # Fusion MPT device support
@@ -553,46 +521,25 @@ CONFIG_FUSION_CTL=y
 #
 # IEEE 1394 (FireWire) support
 #
+# CONFIG_FIREWIRE is not set
 # CONFIG_IEEE1394 is not set
-
-#
-# I2O device support
-#
 # CONFIG_I2O is not set
-
-#
-# Network device support
-#
 CONFIG_NETDEVICES=y
+# CONFIG_NETDEVICES_MULTIQUEUE is not set
 CONFIG_DUMMY=m
 # CONFIG_BONDING is not set
+# CONFIG_MACVLAN is not set
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
 # CONFIG_NET_SB1000 is not set
-
-#
-# ARCnet devices
-#
 # CONFIG_ARCNET is not set
-
-#
-# PHY device support
-#
 # CONFIG_PHYLIB is not set
-
-#
-# Ethernet (10 or 100Mbit)
-#
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=m
 # CONFIG_HAPPYMEAL is not set
 # CONFIG_SUNGEM is not set
 # CONFIG_CASSINI is not set
 # CONFIG_NET_VENDOR_3COM is not set
-
-#
-# Tulip family network device support
-#
 CONFIG_NET_TULIP=y
 # CONFIG_DE2104X is not set
 CONFIG_TULIP=m
@@ -623,10 +570,7 @@ CONFIG_E100=m
 # CONFIG_SUNDANCE is not set
 # CONFIG_VIA_RHINE is not set
 # CONFIG_SC92031 is not set
-
-#
-# Ethernet (1000 Mbit)
-#
+CONFIG_NETDEV_1000=y
 # CONFIG_ACENIC is not set
 # CONFIG_DL2K is not set
 CONFIG_E1000=y
@@ -639,36 +583,36 @@ CONFIG_E1000=y
 # CONFIG_SIS190 is not set
 # CONFIG_SKGE is not set
 # CONFIG_SKY2 is not set
-# CONFIG_SK98LIN is not set
 # CONFIG_VIA_VELOCITY is not set
 CONFIG_TIGON3=y
 # CONFIG_BNX2 is not set
 # CONFIG_QLA3XXX is not set
 # CONFIG_ATL1 is not set
-
-#
-# Ethernet (10000 Mbit)
-#
+CONFIG_NETDEV_10000=y
 # CONFIG_CHELSIO_T1 is not set
 # CONFIG_CHELSIO_T3 is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
-
-#
-# Token Ring devices
-#
+# CONFIG_MLX4_CORE is not set
 # CONFIG_TR is not set
 
 #
-# Wireless LAN (non-hamradio)
+# Wireless LAN
 #
-# CONFIG_NET_RADIO is not set
+# CONFIG_WLAN_PRE80211 is not set
+# CONFIG_WLAN_80211 is not set
 
 #
-# Wan interfaces
+# USB Network Adapters
 #
+# CONFIG_USB_CATC is not set
+# CONFIG_USB_KAWETH is not set
+# CONFIG_USB_PEGASUS is not set
+# CONFIG_USB_RTL8150 is not set
+# CONFIG_USB_USBNET_MII is not set
+# CONFIG_USB_USBNET is not set
 # CONFIG_WAN is not set
 # CONFIG_FDDI is not set
 # CONFIG_HIPPI is not set
@@ -678,18 +622,9 @@ CONFIG_TIGON3=y
 # CONFIG_SHAPER is not set
 CONFIG_NETCONSOLE=y
 CONFIG_NETPOLL=y
-# CONFIG_NETPOLL_RX is not set
 # CONFIG_NETPOLL_TRAP is not set
 CONFIG_NET_POLL_CONTROLLER=y
-
-#
-# ISDN subsystem
-#
 # CONFIG_ISDN is not set
-
-#
-# Telephony Support
-#
 # CONFIG_PHONE is not set
 
 #
@@ -697,6 +632,7 @@ CONFIG_NET_POLL_CONTROLLER=y
 #
 CONFIG_INPUT=y
 # CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
 
 #
 # Userland interfaces
@@ -722,9 +658,17 @@ CONFIG_KEYBOARD_ATKBD=y
 # CONFIG_KEYBOARD_STOWAWAY is not set
 CONFIG_INPUT_MOUSE=y
 CONFIG_MOUSE_PS2=y
+CONFIG_MOUSE_PS2_ALPS=y
+CONFIG_MOUSE_PS2_LOGIPS2PP=y
+CONFIG_MOUSE_PS2_SYNAPTICS=y
+CONFIG_MOUSE_PS2_LIFEBOOK=y
+CONFIG_MOUSE_PS2_TRACKPOINT=y
+# CONFIG_MOUSE_PS2_TOUCHKIT is not set
 # CONFIG_MOUSE_SERIAL is not set
+# CONFIG_MOUSE_APPLETOUCH is not set
 # CONFIG_MOUSE_VSXXXAA is not set
 # CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TABLET is not set
 # CONFIG_INPUT_TOUCHSCREEN is not set
 # CONFIG_INPUT_MISC is not set
 
@@ -790,19 +734,10 @@ CONFIG_SERIAL_CORE_CONSOLE=y
 CONFIG_UNIX98_PTYS=y
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=256
-
-#
-# IPMI
-#
 # CONFIG_IPMI_HANDLER is not set
-
-#
-# Watchdog Cards
-#
 # CONFIG_WATCHDOG is not set
 # CONFIG_HW_RANDOM is not set
 CONFIG_EFI_RTC=y
-# CONFIG_DTLK is not set
 # CONFIG_R3964 is not set
 # CONFIG_APPLICOM is not set
 CONFIG_AGP=m
@@ -821,15 +756,8 @@ CONFIG_HPET=y
 # CONFIG_HPET_RTC_IRQ is not set
 CONFIG_HPET_MMAP=y
 # CONFIG_HANGCHECK_TIMER is not set
-
-#
-# TPM devices
-#
 # CONFIG_TCG_TPM is not set
-
-#
-# I2C support
-#
+CONFIG_DEVPORT=y
 # CONFIG_I2C is not set
 
 #
@@ -837,21 +765,17 @@ CONFIG_HPET_MMAP=y
 #
 # CONFIG_SPI is not set
 # CONFIG_SPI_MASTER is not set
-
-#
-# Dallas's 1-wire bus
-#
 # CONFIG_W1 is not set
-
-#
-# Hardware Monitoring support
-#
+# CONFIG_POWER_SUPPLY is not set
 CONFIG_HWMON=y
 # CONFIG_HWMON_VID is not set
 # CONFIG_SENSORS_ABITUGURU is not set
 # CONFIG_SENSORS_F71805F is not set
 # CONFIG_SENSORS_PC87427 is not set
+# CONFIG_SENSORS_SMSC47M1 is not set
+# CONFIG_SENSORS_SMSC47B397 is not set
 # CONFIG_SENSORS_VT1211 is not set
+# CONFIG_SENSORS_W83627HF is not set
 # CONFIG_HWMON_DEBUG_CHIP is not set
 
 #
@@ -863,17 +787,20 @@ CONFIG_HWMON=y
 # Multimedia devices
 #
 # CONFIG_VIDEO_DEV is not set
-
-#
-# Digital Video Broadcasting Devices
-#
-# CONFIG_DVB is not set
+# CONFIG_DVB_CORE is not set
+CONFIG_DAB=y
 # CONFIG_USB_DABUSB is not set
 
 #
 # Graphics support
 #
 # CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
+# CONFIG_VGASTATE is not set
 # CONFIG_FB is not set
 
 #
@@ -887,16 +814,18 @@ CONFIG_DUMMY_CONSOLE=y
 # Sound
 #
 # CONFIG_SOUND is not set
-
-#
-# HID Devices
-#
+CONFIG_HID_SUPPORT=y
 CONFIG_HID=y
 # CONFIG_HID_DEBUG is not set
 
 #
-# USB support
+# USB Input Devices
 #
+CONFIG_USB_HID=y
+# CONFIG_USB_HIDINPUT_POWERBOOK is not set
+# CONFIG_HID_FF is not set
+# CONFIG_USB_HIDDEV is not set
+CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
 CONFIG_USB_ARCH_HAS_EHCI=y
@@ -907,8 +836,10 @@ CONFIG_USB=y
 # Miscellaneous USB options
 #
 CONFIG_USB_DEVICEFS=y
+CONFIG_USB_DEVICE_CLASS=y
 # CONFIG_USB_DYNAMIC_MINORS is not set
 # CONFIG_USB_SUSPEND is not set
+# CONFIG_USB_PERSIST is not set
 # CONFIG_USB_OTG is not set
 
 #
@@ -918,7 +849,6 @@ CONFIG_USB_EHCI_HCD=m
 # CONFIG_USB_EHCI_SPLIT_ISO is not set
 # CONFIG_USB_EHCI_ROOT_HUB_TT is not set
 # CONFIG_USB_EHCI_TT_NEWSCHED is not set
-# CONFIG_USB_EHCI_BIG_ENDIAN_MMIO is not set
 # CONFIG_USB_ISP116X_HCD is not set
 CONFIG_USB_OHCI_HCD=m
 # CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set
@@ -926,6 +856,7 @@ CONFIG_USB_OHCI_HCD=m
 CONFIG_USB_OHCI_LITTLE_ENDIAN=y
 CONFIG_USB_UHCI_HCD=y
 # CONFIG_USB_SL811_HCD is not set
+# CONFIG_USB_R8A66597_HCD is not set
 
 #
 # USB Device Class drivers
@@ -955,41 +886,10 @@ CONFIG_USB_STORAGE=m
 # CONFIG_USB_LIBUSUAL is not set
 
 #
-# USB Input Devices
-#
-CONFIG_USB_HID=y
-# CONFIG_USB_HIDINPUT_POWERBOOK is not set
-# CONFIG_HID_FF is not set
-# CONFIG_USB_HIDDEV is not set
-# CONFIG_USB_AIPTEK is not set
-# CONFIG_USB_WACOM is not set
-# CONFIG_USB_ACECAD is not set
-# CONFIG_USB_KBTAB is not set
-# CONFIG_USB_POWERMATE is not set
-# CONFIG_USB_TOUCHSCREEN is not set
-# CONFIG_USB_YEALINK is not set
-# CONFIG_USB_XPAD is not set
-# CONFIG_USB_ATI_REMOTE is not set
-# CONFIG_USB_ATI_REMOTE2 is not set
-# CONFIG_USB_KEYSPAN_REMOTE is not set
-# CONFIG_USB_APPLETOUCH is not set
-# CONFIG_USB_GTCO is not set
-
-#
 # USB Imaging devices
 #
 # CONFIG_USB_MDC800 is not set
 # CONFIG_USB_MICROTEK is not set
-
-#
-# USB Network Adapters
-#
-# CONFIG_USB_CATC is not set
-# CONFIG_USB_KAWETH is not set
-# CONFIG_USB_PEGASUS is not set
-# CONFIG_USB_RTL8150 is not set
-# CONFIG_USB_USBNET_MII is not set
-# CONFIG_USB_USBNET is not set
 # CONFIG_USB_MON is not set
 
 #
@@ -1033,10 +933,6 @@ CONFIG_USB_HID=y
 # USB Gadget Support
 #
 # CONFIG_USB_GADGET is not set
-
-#
-# MMC/SD Card support
-#
 # CONFIG_MMC is not set
 
 #
@@ -1051,17 +947,9 @@ CONFIG_USB_HID=y
 #
 # LED Triggers
 #
-
-#
-# InfiniBand support
-#
 # CONFIG_INFINIBAND is not set
 
 #
-# EDAC - error detection and reporting (RAS) (EXPERIMENTAL)
-#
-
-#
 # Real Time Clock
 #
 # CONFIG_RTC_CLASS is not set
@@ -1080,12 +968,9 @@ CONFIG_USB_HID=y
 #
 
 #
-# Auxiliary Display support
-#
-
-#
-# Virtualization
+# Userspace I/O
 #
+# CONFIG_UIO is not set
 # CONFIG_MSPEC is not set
 
 #
@@ -1200,7 +1085,8 @@ CONFIG_EXPORTFS=m
 CONFIG_NFS_COMMON=y
 CONFIG_SUNRPC=m
 CONFIG_SUNRPC_GSS=m
-CONFIG_RPCSEC_GSS_KRB5=m
+# CONFIG_SUNRPC_BIND34 is not set
+CONFIG_RPCSEC_GSS_KRB5=y
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 CONFIG_SMB_FS=m
 CONFIG_SMB_NLS_DEFAULT=y
@@ -1214,7 +1100,6 @@ CONFIG_CIFS=m
 # CONFIG_NCP_FS is not set
 # CONFIG_CODA_FS is not set
 # CONFIG_AFS_FS is not set
-# CONFIG_9P_FS is not set
 
 #
 # Partition Types
@@ -1236,6 +1121,7 @@ CONFIG_SGI_PARTITION=y
 # CONFIG_SUN_PARTITION is not set
 # CONFIG_KARMA_PARTITION is not set
 CONFIG_EFI_PARTITION=y
+# CONFIG_SYSV68_PARTITION is not set
 
 #
 # Native Language Support
@@ -1292,11 +1178,14 @@ CONFIG_NLS_UTF8=m
 CONFIG_BITREVERSE=y
 # CONFIG_CRC_CCITT is not set
 # CONFIG_CRC16 is not set
+# CONFIG_CRC_ITU_T is not set
 CONFIG_CRC32=y
+# CONFIG_CRC7 is not set
 # CONFIG_LIBCRC32C is not set
 CONFIG_PLIST=y
 CONFIG_HAS_IOMEM=y
 CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
 CONFIG_GENERIC_HARDIRQS=y
 CONFIG_GENERIC_IRQ_PROBE=y
 CONFIG_GENERIC_PENDING_IRQ=y
@@ -1319,8 +1208,8 @@ CONFIG_MAGIC_SYSRQ=y
 # CONFIG_HEADERS_CHECK is not set
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
-CONFIG_LOG_BUF_SHIFT=20
 CONFIG_DETECT_SOFTLOCKUP=y
+CONFIG_SCHED_DEBUG=y
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
 # CONFIG_DEBUG_SLAB is not set
@@ -1343,17 +1232,12 @@ CONFIG_IA64_GRANULE_16MB=y
 # CONFIG_DISABLE_VHPT is not set
 # CONFIG_IA64_DEBUG_CMPXCHG is not set
 # CONFIG_IA64_DEBUG_IRQ is not set
-CONFIG_SYSVIPC_COMPAT=y
 
 #
 # Security options
 #
 # CONFIG_KEYS is not set
 # CONFIG_SECURITY is not set
-
-#
-# Cryptographic options
-#
 CONFIG_CRYPTO=y
 CONFIG_CRYPTO_ALGAPI=y
 CONFIG_CRYPTO_BLKCIPHER=m
@@ -1373,6 +1257,7 @@ CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_CBC=m
 CONFIG_CRYPTO_PCBC=m
 # CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_CRYPTD is not set
 CONFIG_CRYPTO_DES=m
 # CONFIG_CRYPTO_FCRYPT is not set
 # CONFIG_CRYPTO_BLOWFISH is not set
@@ -1390,7 +1275,4 @@ CONFIG_CRYPTO_DES=m
 # CONFIG_CRYPTO_CRC32C is not set
 # CONFIG_CRYPTO_CAMELLIA is not set
 # CONFIG_CRYPTO_TEST is not set
-
-#
-# Hardware crypto devices
-#
+CONFIG_CRYPTO_HW=y
diff --git a/arch/ia64/configs/zx1_defconfig b/arch/ia64/configs/zx1_defconfig
index 1c7955c16358..4a060fc39934 100644
--- a/arch/ia64/configs/zx1_defconfig
+++ b/arch/ia64/configs/zx1_defconfig
@@ -96,7 +96,7 @@ CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
 CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_TIME_INTERPOLATION=y
+CONFIG_GENERIC_TIME=y
 CONFIG_DMI=y
 CONFIG_EFI=y
 CONFIG_GENERIC_IOMAP=y
diff --git a/arch/ia64/defconfig b/arch/ia64/defconfig
index 90bd9601cdde..03172dc8c403 100644
--- a/arch/ia64/defconfig
+++ b/arch/ia64/defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.21-rc3
-# Thu Mar  8 11:01:03 2007
+# Linux kernel version: 2.6.22
+# Thu Jul 19 13:55:32 2007
 #
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
 
@@ -19,15 +19,15 @@ CONFIG_LOCALVERSION=""
 CONFIG_LOCALVERSION_AUTO=y
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
-# CONFIG_IPC_NS is not set
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
-# CONFIG_UTS_NS is not set
+# CONFIG_USER_NS is not set
 # CONFIG_AUDIT is not set
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=20
 # CONFIG_CPUSETS is not set
 CONFIG_SYSFS_DEPRECATED=y
 # CONFIG_RELAY is not set
@@ -46,18 +46,19 @@ CONFIG_BUG=y
 CONFIG_ELF_CORE=y
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
+CONFIG_ANON_INODES=y
 CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
 CONFIG_SHMEM=y
-CONFIG_SLAB=y
 CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_SLAB=y
+# CONFIG_SLUB is not set
+# CONFIG_SLOB is not set
 CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
-# CONFIG_SLOB is not set
-
-#
-# Loadable module support
-#
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_FORCE_UNLOAD is not set
@@ -65,12 +66,9 @@ CONFIG_MODVERSIONS=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_KMOD=y
 CONFIG_STOP_MACHINE=y
-
-#
-# Block layer
-#
 CONFIG_BLOCK=y
 # CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_BLK_DEV_BSG is not set
 
 #
 # IO Schedulers
@@ -91,6 +89,7 @@ CONFIG_DEFAULT_IOSCHED="anticipatory"
 CONFIG_IA64=y
 CONFIG_64BIT=y
 CONFIG_ZONE_DMA=y
+CONFIG_QUICKLIST=y
 CONFIG_MMU=y
 CONFIG_SWIOTLB=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
@@ -98,7 +97,7 @@ CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
 CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_TIME_INTERPOLATION=y
+CONFIG_GENERIC_TIME=y
 CONFIG_DMI=y
 CONFIG_EFI=y
 CONFIG_GENERIC_IOMAP=y
@@ -114,8 +113,8 @@ CONFIG_IA64_GENERIC=y
 CONFIG_MCKINLEY=y
 # CONFIG_IA64_PAGE_SIZE_4KB is not set
 # CONFIG_IA64_PAGE_SIZE_8KB is not set
-CONFIG_IA64_PAGE_SIZE_16KB=y
-# CONFIG_IA64_PAGE_SIZE_64KB is not set
+# CONFIG_IA64_PAGE_SIZE_16KB is not set
+CONFIG_IA64_PAGE_SIZE_64KB=y
 CONFIG_PGTABLE_3=y
 # CONFIG_PGTABLE_4 is not set
 # CONFIG_HZ_100 is not set
@@ -147,6 +146,9 @@ CONFIG_SPLIT_PTLOCK_CPUS=4
 CONFIG_MIGRATION=y
 CONFIG_RESOURCES_64BIT=y
 CONFIG_ZONE_DMA_FLAG=1
+CONFIG_BOUNCE=y
+CONFIG_NR_QUICK=1
+CONFIG_VIRT_TO_BUS=y
 CONFIG_ARCH_SELECT_MEMORY_MODEL=y
 CONFIG_ARCH_DISCONTIGMEM_ENABLE=y
 CONFIG_ARCH_FLATMEM_ENABLE=y
@@ -164,7 +166,7 @@ CONFIG_COMPAT=y
 CONFIG_IA64_MCA_RECOVERY=y
 CONFIG_PERFMON=y
 CONFIG_IA64_PALINFO=y
-# CONFIG_MC_ERR_INJECT is not set
+# CONFIG_IA64_MC_ERR_INJECT is not set
 CONFIG_SGI_SN=y
 # CONFIG_IA64_ESI is not set
 
@@ -180,6 +182,7 @@ CONFIG_CRASH_DUMP=y
 #
 CONFIG_EFI_VARS=y
 CONFIG_EFI_PCDP=y
+CONFIG_DMIID=y
 CONFIG_BINFMT_ELF=y
 CONFIG_BINFMT_MISC=m
 
@@ -189,7 +192,6 @@ CONFIG_BINFMT_MISC=m
 CONFIG_PM=y
 CONFIG_PM_LEGACY=y
 # CONFIG_PM_DEBUG is not set
-# CONFIG_PM_SYSFS_DEPRECATED is not set
 
 #
 # ACPI (Advanced Configuration and Power Interface) Support
@@ -220,13 +222,11 @@ CONFIG_ACPI_CONTAINER=m
 #
 CONFIG_PCI=y
 CONFIG_PCI_DOMAINS=y
+CONFIG_PCI_SYSCALL=y
 # CONFIG_PCIEPORTBUS is not set
+CONFIG_ARCH_SUPPORTS_MSI=y
 # CONFIG_PCI_MSI is not set
 # CONFIG_PCI_DEBUG is not set
-
-#
-# PCI Hotplug Support
-#
 CONFIG_HOTPLUG_PCI=m
 # CONFIG_HOTPLUG_PCI_FAKE is not set
 CONFIG_HOTPLUG_PCI_ACPI=m
@@ -248,7 +248,6 @@ CONFIG_NET=y
 #
 # Networking options
 #
-# CONFIG_NETDEBUG is not set
 CONFIG_PACKET=y
 # CONFIG_PACKET_MMAP is not set
 CONFIG_UNIX=y
@@ -286,20 +285,8 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 # CONFIG_INET6_TUNNEL is not set
 # CONFIG_NETWORK_SECMARK is not set
 # CONFIG_NETFILTER is not set
-
-#
-# DCCP Configuration (EXPERIMENTAL)
-#
 # CONFIG_IP_DCCP is not set
-
-#
-# SCTP Configuration (EXPERIMENTAL)
-#
 # CONFIG_IP_SCTP is not set
-
-#
-# TIPC Configuration (EXPERIMENTAL)
-#
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
 # CONFIG_BRIDGE is not set
@@ -325,7 +312,17 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 # CONFIG_HAMRADIO is not set
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
+# CONFIG_AF_RXRPC is not set
+
+#
+# Wireless
+#
+# CONFIG_CFG80211 is not set
+# CONFIG_WIRELESS_EXT is not set
+# CONFIG_MAC80211 is not set
 # CONFIG_IEEE80211 is not set
+# CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
 
 #
 # Device Drivers
@@ -340,25 +337,9 @@ CONFIG_FW_LOADER=m
 # CONFIG_DEBUG_DRIVER is not set
 # CONFIG_DEBUG_DEVRES is not set
 # CONFIG_SYS_HYPERVISOR is not set
-
-#
-# Connector - unified userspace <-> kernelspace linker
-#
 # CONFIG_CONNECTOR is not set
-
-#
-# Memory Technology Devices (MTD)
-#
 # CONFIG_MTD is not set
-
-#
-# Parallel port support
-#
 # CONFIG_PARPORT is not set
-
-#
-# Plug and Play support
-#
 CONFIG_PNP=y
 # CONFIG_PNP_DEBUG is not set
 
@@ -366,10 +347,7 @@ CONFIG_PNP=y
 # Protocols
 #
 CONFIG_PNPACPI=y
-
-#
-# Block devices
-#
+CONFIG_BLK_DEV=y
 # CONFIG_BLK_CPQ_DA is not set
 # CONFIG_BLK_CPQ_CISS_DA is not set
 # CONFIG_BLK_DEV_DAC960 is not set
@@ -386,16 +364,11 @@ CONFIG_BLK_DEV_RAM_SIZE=4096
 CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
 # CONFIG_CDROM_PKTCDVD is not set
 # CONFIG_ATA_OVER_ETH is not set
-
-#
-# Misc devices
-#
+CONFIG_MISC_DEVICES=y
+# CONFIG_PHANTOM is not set
+# CONFIG_EEPROM_93CX6 is not set
 CONFIG_SGI_IOC4=y
 # CONFIG_TIFM_CORE is not set
-
-#
-# ATA/ATAPI/MFM/RLL support
-#
 CONFIG_IDE=y
 CONFIG_IDE_MAX_HWIFS=4
 CONFIG_BLK_DEV_IDE=y
@@ -412,6 +385,7 @@ CONFIG_BLK_DEV_IDEFLOPPY=y
 CONFIG_BLK_DEV_IDESCSI=m
 # CONFIG_BLK_DEV_IDEACPI is not set
 # CONFIG_IDE_TASK_IOCTL is not set
+CONFIG_IDE_PROC_FS=y
 
 #
 # IDE chipset support/bugfixes
@@ -420,12 +394,12 @@ CONFIG_BLK_DEV_IDESCSI=m
 # CONFIG_BLK_DEV_IDEPNP is not set
 CONFIG_BLK_DEV_IDEPCI=y
 CONFIG_IDEPCI_SHARE_IRQ=y
+CONFIG_IDEPCI_PCIBUS_ORDER=y
 # CONFIG_BLK_DEV_OFFBOARD is not set
 CONFIG_BLK_DEV_GENERIC=y
 # CONFIG_BLK_DEV_OPTI621 is not set
 CONFIG_BLK_DEV_IDEDMA_PCI=y
 # CONFIG_BLK_DEV_IDEDMA_FORCED is not set
-CONFIG_IDEDMA_PCI_AUTO=y
 # CONFIG_IDEDMA_ONLYDISK is not set
 # CONFIG_BLK_DEV_AEC62XX is not set
 # CONFIG_BLK_DEV_ALI15X3 is not set
@@ -455,7 +429,6 @@ CONFIG_BLK_DEV_SGIIOC4=y
 # CONFIG_IDE_ARM is not set
 CONFIG_BLK_DEV_IDEDMA=y
 # CONFIG_IDEDMA_IVB is not set
-CONFIG_IDEDMA_AUTO=y
 # CONFIG_BLK_DEV_HD is not set
 
 #
@@ -463,6 +436,7 @@ CONFIG_IDEDMA_AUTO=y
 #
 # CONFIG_RAID_ATTRS is not set
 CONFIG_SCSI=y
+CONFIG_SCSI_DMA=y
 # CONFIG_SCSI_TGT is not set
 CONFIG_SCSI_NETLINK=y
 CONFIG_SCSI_PROC_FS=y
@@ -485,6 +459,7 @@ CONFIG_CHR_DEV_SG=m
 # CONFIG_SCSI_CONSTANTS is not set
 # CONFIG_SCSI_LOGGING is not set
 # CONFIG_SCSI_SCAN_ASYNC is not set
+CONFIG_SCSI_WAIT_SCAN=m
 
 #
 # SCSI Transports
@@ -492,7 +467,7 @@ CONFIG_CHR_DEV_SG=m
 CONFIG_SCSI_SPI_ATTRS=y
 CONFIG_SCSI_FC_ATTRS=y
 # CONFIG_SCSI_ISCSI_ATTRS is not set
-# CONFIG_SCSI_SAS_ATTRS is not set
+CONFIG_SCSI_SAS_ATTRS=y
 # CONFIG_SCSI_SAS_LIBSAS is not set
 
 #
@@ -531,15 +506,7 @@ CONFIG_SCSI_QLOGIC_1280=y
 # CONFIG_SCSI_DC390T is not set
 # CONFIG_SCSI_DEBUG is not set
 # CONFIG_SCSI_SRP is not set
-
-#
-# Serial ATA (prod) and Parallel ATA (experimental) drivers
-#
 # CONFIG_ATA is not set
-
-#
-# Multi-device support (RAID and LVM)
-#
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=m
 CONFIG_MD_LINEAR=m
@@ -557,6 +524,8 @@ CONFIG_DM_MIRROR=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 # CONFIG_DM_MULTIPATH_EMC is not set
+# CONFIG_DM_MULTIPATH_RDAC is not set
+# CONFIG_DM_DELAY is not set
 
 #
 # Fusion MPT device support
@@ -564,53 +533,32 @@ CONFIG_DM_MULTIPATH=m
 CONFIG_FUSION=y
 CONFIG_FUSION_SPI=y
 CONFIG_FUSION_FC=m
-# CONFIG_FUSION_SAS is not set
+CONFIG_FUSION_SAS=y
 CONFIG_FUSION_MAX_SGE=128
 # CONFIG_FUSION_CTL is not set
 
 #
 # IEEE 1394 (FireWire) support
 #
+# CONFIG_FIREWIRE is not set
 # CONFIG_IEEE1394 is not set
-
-#
-# I2O device support
-#
 # CONFIG_I2O is not set
-
-#
-# Network device support
-#
 CONFIG_NETDEVICES=y
+# CONFIG_NETDEVICES_MULTIQUEUE is not set
 CONFIG_DUMMY=m
 # CONFIG_BONDING is not set
+# CONFIG_MACVLAN is not set
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
 # CONFIG_NET_SB1000 is not set
-
-#
-# ARCnet devices
-#
 # CONFIG_ARCNET is not set
-
-#
-# PHY device support
-#
 # CONFIG_PHYLIB is not set
-
-#
-# Ethernet (10 or 100Mbit)
-#
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=m
 # CONFIG_HAPPYMEAL is not set
 # CONFIG_SUNGEM is not set
 # CONFIG_CASSINI is not set
 # CONFIG_NET_VENDOR_3COM is not set
-
-#
-# Tulip family network device support
-#
 CONFIG_NET_TULIP=y
 # CONFIG_DE2104X is not set
 CONFIG_TULIP=m
@@ -641,10 +589,7 @@ CONFIG_E100=m
 # CONFIG_SUNDANCE is not set
 # CONFIG_VIA_RHINE is not set
 # CONFIG_SC92031 is not set
-
-#
-# Ethernet (1000 Mbit)
-#
+CONFIG_NETDEV_1000=y
 # CONFIG_ACENIC is not set
 # CONFIG_DL2K is not set
 CONFIG_E1000=y
@@ -657,36 +602,36 @@ CONFIG_E1000=y
 # CONFIG_SIS190 is not set
 # CONFIG_SKGE is not set
 # CONFIG_SKY2 is not set
-# CONFIG_SK98LIN is not set
 # CONFIG_VIA_VELOCITY is not set
 CONFIG_TIGON3=y
 # CONFIG_BNX2 is not set
 # CONFIG_QLA3XXX is not set
 # CONFIG_ATL1 is not set
-
-#
-# Ethernet (10000 Mbit)
-#
+CONFIG_NETDEV_10000=y
 # CONFIG_CHELSIO_T1 is not set
 # CONFIG_CHELSIO_T3 is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
-
-#
-# Token Ring devices
-#
+# CONFIG_MLX4_CORE is not set
 # CONFIG_TR is not set
 
 #
-# Wireless LAN (non-hamradio)
+# Wireless LAN
 #
-# CONFIG_NET_RADIO is not set
+# CONFIG_WLAN_PRE80211 is not set
+# CONFIG_WLAN_80211 is not set
 
 #
-# Wan interfaces
+# USB Network Adapters
 #
+# CONFIG_USB_CATC is not set
+# CONFIG_USB_KAWETH is not set
+# CONFIG_USB_PEGASUS is not set
+# CONFIG_USB_RTL8150 is not set
+# CONFIG_USB_USBNET_MII is not set
+# CONFIG_USB_USBNET is not set
 # CONFIG_WAN is not set
 # CONFIG_FDDI is not set
 # CONFIG_HIPPI is not set
@@ -696,18 +641,9 @@ CONFIG_TIGON3=y
 # CONFIG_SHAPER is not set
 CONFIG_NETCONSOLE=y
 CONFIG_NETPOLL=y
-# CONFIG_NETPOLL_RX is not set
 # CONFIG_NETPOLL_TRAP is not set
 CONFIG_NET_POLL_CONTROLLER=y
-
-#
-# ISDN subsystem
-#
 # CONFIG_ISDN is not set
-
-#
-# Telephony Support
-#
 # CONFIG_PHONE is not set
 
 #
@@ -715,6 +651,7 @@ CONFIG_NET_POLL_CONTROLLER=y
 #
 CONFIG_INPUT=y
 # CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
 
 #
 # Userland interfaces
@@ -740,9 +677,17 @@ CONFIG_KEYBOARD_ATKBD=y
 # CONFIG_KEYBOARD_STOWAWAY is not set
 CONFIG_INPUT_MOUSE=y
 CONFIG_MOUSE_PS2=y
+CONFIG_MOUSE_PS2_ALPS=y
+CONFIG_MOUSE_PS2_LOGIPS2PP=y
+CONFIG_MOUSE_PS2_SYNAPTICS=y
+CONFIG_MOUSE_PS2_LIFEBOOK=y
+CONFIG_MOUSE_PS2_TRACKPOINT=y
+# CONFIG_MOUSE_PS2_TOUCHKIT is not set
 # CONFIG_MOUSE_SERIAL is not set
+# CONFIG_MOUSE_APPLETOUCH is not set
 # CONFIG_MOUSE_VSXXXAA is not set
 # CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TABLET is not set
 # CONFIG_INPUT_TOUCHSCREEN is not set
 # CONFIG_INPUT_MISC is not set
 
@@ -814,19 +759,10 @@ CONFIG_SERIAL_SGI_IOC4=y
 CONFIG_UNIX98_PTYS=y
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=256
-
-#
-# IPMI
-#
 # CONFIG_IPMI_HANDLER is not set
-
-#
-# Watchdog Cards
-#
 # CONFIG_WATCHDOG is not set
 # CONFIG_HW_RANDOM is not set
 CONFIG_EFI_RTC=y
-# CONFIG_DTLK is not set
 # CONFIG_R3964 is not set
 # CONFIG_APPLICOM is not set
 CONFIG_AGP=m
@@ -848,15 +784,8 @@ CONFIG_HPET=y
 CONFIG_HPET_MMAP=y
 # CONFIG_HANGCHECK_TIMER is not set
 CONFIG_MMTIMER=y
-
-#
-# TPM devices
-#
 # CONFIG_TCG_TPM is not set
-
-#
-# I2C support
-#
+CONFIG_DEVPORT=y
 # CONFIG_I2C is not set
 
 #
@@ -864,21 +793,17 @@ CONFIG_MMTIMER=y
 #
 # CONFIG_SPI is not set
 # CONFIG_SPI_MASTER is not set
-
-#
-# Dallas's 1-wire bus
-#
 # CONFIG_W1 is not set
-
-#
-# Hardware Monitoring support
-#
+# CONFIG_POWER_SUPPLY is not set
 CONFIG_HWMON=y
 # CONFIG_HWMON_VID is not set
 # CONFIG_SENSORS_ABITUGURU is not set
 # CONFIG_SENSORS_F71805F is not set
 # CONFIG_SENSORS_PC87427 is not set
+# CONFIG_SENSORS_SMSC47M1 is not set
+# CONFIG_SENSORS_SMSC47B397 is not set
 # CONFIG_SENSORS_VT1211 is not set
+# CONFIG_SENSORS_W83627HF is not set
 # CONFIG_HWMON_DEBUG_CHIP is not set
 
 #
@@ -890,17 +815,20 @@ CONFIG_HWMON=y
 # Multimedia devices
 #
 # CONFIG_VIDEO_DEV is not set
-
-#
-# Digital Video Broadcasting Devices
-#
-# CONFIG_DVB is not set
+# CONFIG_DVB_CORE is not set
+CONFIG_DAB=y
 # CONFIG_USB_DABUSB is not set
 
 #
 # Graphics support
 #
 # CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
+# CONFIG_VGASTATE is not set
 # CONFIG_FB is not set
 
 #
@@ -1014,9 +942,10 @@ CONFIG_SND_FM801=m
 # USB devices
 #
 # CONFIG_SND_USB_AUDIO is not set
+# CONFIG_SND_USB_CAIAQ is not set
 
 #
-# SoC audio support
+# System on Chip audio support
 #
 # CONFIG_SND_SOC is not set
 
@@ -1025,16 +954,24 @@ CONFIG_SND_FM801=m
 #
 # CONFIG_SOUND_PRIME is not set
 CONFIG_AC97_BUS=m
+CONFIG_HID_SUPPORT=y
+CONFIG_HID=y
+# CONFIG_HID_DEBUG is not set
 
 #
-# HID Devices
+# USB Input Devices
 #
-CONFIG_HID=y
-# CONFIG_HID_DEBUG is not set
+CONFIG_USB_HID=m
+# CONFIG_USB_HIDINPUT_POWERBOOK is not set
+# CONFIG_HID_FF is not set
+# CONFIG_USB_HIDDEV is not set
 
 #
-# USB support
+# USB HID Boot Protocol drivers
 #
+# CONFIG_USB_KBD is not set
+# CONFIG_USB_MOUSE is not set
+CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
 CONFIG_USB_ARCH_HAS_EHCI=y
@@ -1045,8 +982,10 @@ CONFIG_USB=m
 # Miscellaneous USB options
 #
 CONFIG_USB_DEVICEFS=y
+CONFIG_USB_DEVICE_CLASS=y
 # CONFIG_USB_DYNAMIC_MINORS is not set
 # CONFIG_USB_SUSPEND is not set
+# CONFIG_USB_PERSIST is not set
 # CONFIG_USB_OTG is not set
 
 #
@@ -1056,7 +995,6 @@ CONFIG_USB_EHCI_HCD=m
 # CONFIG_USB_EHCI_SPLIT_ISO is not set
 # CONFIG_USB_EHCI_ROOT_HUB_TT is not set
 # CONFIG_USB_EHCI_TT_NEWSCHED is not set
-# CONFIG_USB_EHCI_BIG_ENDIAN_MMIO is not set
 # CONFIG_USB_ISP116X_HCD is not set
 CONFIG_USB_OHCI_HCD=m
 # CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set
@@ -1064,6 +1002,7 @@ CONFIG_USB_OHCI_HCD=m
 CONFIG_USB_OHCI_LITTLE_ENDIAN=y
 CONFIG_USB_UHCI_HCD=m
 # CONFIG_USB_SL811_HCD is not set
+# CONFIG_USB_R8A66597_HCD is not set
 
 #
 # USB Device Class drivers
@@ -1093,47 +1032,10 @@ CONFIG_USB_STORAGE=m
 # CONFIG_USB_LIBUSUAL is not set
 
 #
-# USB Input Devices
-#
-CONFIG_USB_HID=m
-# CONFIG_USB_HIDINPUT_POWERBOOK is not set
-# CONFIG_HID_FF is not set
-# CONFIG_USB_HIDDEV is not set
-
-#
-# USB HID Boot Protocol drivers
-#
-# CONFIG_USB_KBD is not set
-# CONFIG_USB_MOUSE is not set
-# CONFIG_USB_AIPTEK is not set
-# CONFIG_USB_WACOM is not set
-# CONFIG_USB_ACECAD is not set
-# CONFIG_USB_KBTAB is not set
-# CONFIG_USB_POWERMATE is not set
-# CONFIG_USB_TOUCHSCREEN is not set
-# CONFIG_USB_YEALINK is not set
-# CONFIG_USB_XPAD is not set
-# CONFIG_USB_ATI_REMOTE is not set
-# CONFIG_USB_ATI_REMOTE2 is not set
-# CONFIG_USB_KEYSPAN_REMOTE is not set
-# CONFIG_USB_APPLETOUCH is not set
-# CONFIG_USB_GTCO is not set
-
-#
 # USB Imaging devices
 #
 # CONFIG_USB_MDC800 is not set
 # CONFIG_USB_MICROTEK is not set
-
-#
-# USB Network Adapters
-#
-# CONFIG_USB_CATC is not set
-# CONFIG_USB_KAWETH is not set
-# CONFIG_USB_PEGASUS is not set
-# CONFIG_USB_RTL8150 is not set
-# CONFIG_USB_USBNET_MII is not set
-# CONFIG_USB_USBNET is not set
 CONFIG_USB_MON=y
 
 #
@@ -1177,10 +1079,6 @@ CONFIG_USB_MON=y
 # USB Gadget Support
 #
 # CONFIG_USB_GADGET is not set
-
-#
-# MMC/SD Card support
-#
 # CONFIG_MMC is not set
 
 #
@@ -1195,10 +1093,6 @@ CONFIG_USB_MON=y
 #
 # LED Triggers
 #
-
-#
-# InfiniBand support
-#
 CONFIG_INFINIBAND=m
 # CONFIG_INFINIBAND_USER_MAD is not set
 # CONFIG_INFINIBAND_USER_ACCESS is not set
@@ -1206,6 +1100,7 @@ CONFIG_INFINIBAND_ADDR_TRANS=y
 CONFIG_INFINIBAND_MTHCA=m
 CONFIG_INFINIBAND_MTHCA_DEBUG=y
 # CONFIG_INFINIBAND_AMSO1100 is not set
+# CONFIG_MLX4_INFINIBAND is not set
 CONFIG_INFINIBAND_IPOIB=m
 # CONFIG_INFINIBAND_IPOIB_CM is not set
 CONFIG_INFINIBAND_IPOIB_DEBUG=y
@@ -1214,10 +1109,6 @@ CONFIG_INFINIBAND_IPOIB_DEBUG=y
 # CONFIG_INFINIBAND_ISER is not set
 
 #
-# EDAC - error detection and reporting (RAS) (EXPERIMENTAL)
-#
-
-#
 # Real Time Clock
 #
 # CONFIG_RTC_CLASS is not set
@@ -1236,12 +1127,9 @@ CONFIG_INFINIBAND_IPOIB_DEBUG=y
 #
 
 #
-# Auxiliary Display support
-#
-
-#
-# Virtualization
+# Userspace I/O
 #
+# CONFIG_UIO is not set
 # CONFIG_MSPEC is not set
 
 #
@@ -1357,7 +1245,8 @@ CONFIG_EXPORTFS=m
 CONFIG_NFS_COMMON=y
 CONFIG_SUNRPC=m
 CONFIG_SUNRPC_GSS=m
-CONFIG_RPCSEC_GSS_KRB5=m
+# CONFIG_SUNRPC_BIND34 is not set
+CONFIG_RPCSEC_GSS_KRB5=y
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 CONFIG_SMB_FS=m
 CONFIG_SMB_NLS_DEFAULT=y
@@ -1371,7 +1260,6 @@ CONFIG_CIFS=m
 # CONFIG_NCP_FS is not set
 # CONFIG_CODA_FS is not set
 # CONFIG_AFS_FS is not set
-# CONFIG_9P_FS is not set
 
 #
 # Partition Types
@@ -1393,6 +1281,7 @@ CONFIG_SGI_PARTITION=y
 # CONFIG_SUN_PARTITION is not set
 # CONFIG_KARMA_PARTITION is not set
 CONFIG_EFI_PARTITION=y
+# CONFIG_SYSV68_PARTITION is not set
 
 #
 # Native Language Support
@@ -1449,11 +1338,14 @@ CONFIG_NLS_UTF8=m
 CONFIG_BITREVERSE=y
 # CONFIG_CRC_CCITT is not set
 # CONFIG_CRC16 is not set
+# CONFIG_CRC_ITU_T is not set
 CONFIG_CRC32=y
+# CONFIG_CRC7 is not set
 # CONFIG_LIBCRC32C is not set
 CONFIG_PLIST=y
 CONFIG_HAS_IOMEM=y
 CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
 CONFIG_GENERIC_HARDIRQS=y
 CONFIG_GENERIC_IRQ_PROBE=y
 CONFIG_GENERIC_PENDING_IRQ=y
@@ -1483,8 +1375,8 @@ CONFIG_MAGIC_SYSRQ=y
 # CONFIG_HEADERS_CHECK is not set
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
-CONFIG_LOG_BUF_SHIFT=20
 CONFIG_DETECT_SOFTLOCKUP=y
+CONFIG_SCHED_DEBUG=y
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
 # CONFIG_DEBUG_SLAB is not set
@@ -1514,10 +1406,6 @@ CONFIG_SYSVIPC_COMPAT=y
 #
 # CONFIG_KEYS is not set
 # CONFIG_SECURITY is not set
-
-#
-# Cryptographic options
-#
 CONFIG_CRYPTO=y
 CONFIG_CRYPTO_ALGAPI=y
 CONFIG_CRYPTO_BLKCIPHER=m
@@ -1537,6 +1425,7 @@ CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_CBC=m
 CONFIG_CRYPTO_PCBC=m
 # CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_CRYPTD is not set
 CONFIG_CRYPTO_DES=m
 # CONFIG_CRYPTO_FCRYPT is not set
 # CONFIG_CRYPTO_BLOWFISH is not set
@@ -1554,7 +1443,4 @@ CONFIG_CRYPTO_DES=m
 # CONFIG_CRYPTO_CRC32C is not set
 # CONFIG_CRYPTO_CAMELLIA is not set
 # CONFIG_CRYPTO_TEST is not set
-
-#
-# Hardware crypto devices
-#
+CONFIG_CRYPTO_HW=y
diff --git a/arch/ia64/ia32/binfmt_elf32.c b/arch/ia64/ia32/binfmt_elf32.c
index e1189ba1ca5e..1cfab326fb7e 100644
--- a/arch/ia64/ia32/binfmt_elf32.c
+++ b/arch/ia64/ia32/binfmt_elf32.c
@@ -226,7 +226,7 @@ elf32_set_personality (void)
 }
 
 static unsigned long
-elf32_map (struct file *filep, unsigned long addr, struct elf_phdr *eppnt, int prot, int type, unsigned long unused)
+elf32_map (struct file *filep, unsigned long addr, struct elf_phdr *eppnt, int prot, int type)
 {
         unsigned long pgoff = (eppnt->p_vaddr) & ~IA32_PAGE_MASK;
 
diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c
index 2236fabbb3c6..0aebc6f79e95 100644
--- a/arch/ia64/kernel/asm-offsets.c
+++ b/arch/ia64/kernel/asm-offsets.c
@@ -7,6 +7,7 @@
 #define ASM_OFFSETS_C 1
 
 #include <linux/sched.h>
+#include <linux/clocksource.h>
 
 #include <asm-ia64/processor.h>
 #include <asm-ia64/ptrace.h>
@@ -15,6 +16,7 @@
 #include <asm-ia64/mca.h>
 
 #include "../kernel/sigframe.h"
+#include "../kernel/fsyscall_gtod_data.h"
 
 #define DEFINE(sym, val) \
         asm volatile("\n->" #sym " %0 " #val : : "i" (val))
@@ -256,17 +258,24 @@ void foo(void)
         BLANK();
 
         /* used by fsys_gettimeofday in arch/ia64/kernel/fsys.S */
-        DEFINE(IA64_TIME_INTERPOLATOR_ADDRESS_OFFSET, offsetof (struct time_interpolator, addr));
-        DEFINE(IA64_TIME_INTERPOLATOR_SOURCE_OFFSET, offsetof (struct time_interpolator, source));
-        DEFINE(IA64_TIME_INTERPOLATOR_SHIFT_OFFSET, offsetof (struct time_interpolator, shift));
-        DEFINE(IA64_TIME_INTERPOLATOR_NSEC_OFFSET, offsetof (struct time_interpolator, nsec_per_cyc));
-        DEFINE(IA64_TIME_INTERPOLATOR_OFFSET_OFFSET, offsetof (struct time_interpolator, offset));
-        DEFINE(IA64_TIME_INTERPOLATOR_LAST_CYCLE_OFFSET, offsetof (struct time_interpolator, last_cycle));
-        DEFINE(IA64_TIME_INTERPOLATOR_LAST_COUNTER_OFFSET, offsetof (struct time_interpolator, last_counter));
-        DEFINE(IA64_TIME_INTERPOLATOR_JITTER_OFFSET, offsetof (struct time_interpolator, jitter));
-        DEFINE(IA64_TIME_INTERPOLATOR_MASK_OFFSET, offsetof (struct time_interpolator, mask));
-        DEFINE(IA64_TIME_SOURCE_CPU, TIME_SOURCE_CPU);
-        DEFINE(IA64_TIME_SOURCE_MMIO64, TIME_SOURCE_MMIO64);
-        DEFINE(IA64_TIME_SOURCE_MMIO32, TIME_SOURCE_MMIO32);
-        DEFINE(IA64_TIMESPEC_TV_NSEC_OFFSET, offsetof (struct timespec, tv_nsec));
+        DEFINE(IA64_GTOD_LOCK_OFFSET,
+                offsetof (struct fsyscall_gtod_data_t, lock));
+        DEFINE(IA64_GTOD_WALL_TIME_OFFSET,
+                offsetof (struct fsyscall_gtod_data_t, wall_time));
+        DEFINE(IA64_GTOD_MONO_TIME_OFFSET,
+                offsetof (struct fsyscall_gtod_data_t, monotonic_time));
+        DEFINE(IA64_CLKSRC_MASK_OFFSET,
+                offsetof (struct fsyscall_gtod_data_t, clk_mask));
+        DEFINE(IA64_CLKSRC_MULT_OFFSET,
+                offsetof (struct fsyscall_gtod_data_t, clk_mult));
+        DEFINE(IA64_CLKSRC_SHIFT_OFFSET,
+                offsetof (struct fsyscall_gtod_data_t, clk_shift));
+        DEFINE(IA64_CLKSRC_MMIO_OFFSET,
+                offsetof (struct fsyscall_gtod_data_t, clk_fsys_mmio));
+        DEFINE(IA64_CLKSRC_CYCLE_LAST_OFFSET,
+                offsetof (struct fsyscall_gtod_data_t, clk_cycle_last));
+        DEFINE(IA64_ITC_JITTER_OFFSET,
+                offsetof (struct itc_jitter_data_t, itc_jitter));
+        DEFINE(IA64_ITC_LASTCYCLE_OFFSET,
+                offsetof (struct itc_jitter_data_t, itc_lastcycle));
 }
diff --git a/arch/ia64/kernel/cyclone.c b/arch/ia64/kernel/cyclone.c
index e00b21514f7c..2fd96d9062a1 100644
--- a/arch/ia64/kernel/cyclone.c
+++ b/arch/ia64/kernel/cyclone.c
@@ -3,6 +3,7 @@
 #include <linux/time.h>
 #include <linux/errno.h>
 #include <linux/timex.h>
+#include <linux/clocksource.h>
 #include <asm/io.h>
 
 /* IBM Summit (EXA) Cyclone counter code*/
@@ -18,13 +19,21 @@ void __init cyclone_setup(void)
         use_cyclone = 1;
 }
 
+static void __iomem *cyclone_mc;
 
-struct time_interpolator cyclone_interpolator = {
-        .source =       TIME_SOURCE_MMIO64,
-        .shift =        16,
-        .frequency =    CYCLONE_TIMER_FREQ,
-        .drift =        -100,
-        .mask =         (1LL << 40) - 1
+static cycle_t read_cyclone(void)
+{
+        return (cycle_t)readq((void __iomem *)cyclone_mc);
+}
+
+static struct clocksource clocksource_cyclone = {
+        .name           = "cyclone",
+        .rating         = 300,
+        .read           = read_cyclone,
+        .mask           = (1LL << 40) - 1,
+        .mult           = 0, /*to be caluclated*/
+        .shift          = 16,
+        .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 int __init init_cyclone_clock(void)
@@ -44,13 +53,15 @@ int __init init_cyclone_clock(void)
         offset = (CYCLONE_CBAR_ADDR);
         reg = (u64*)ioremap_nocache(offset, sizeof(u64));
         if(!reg){
-                printk(KERN_ERR "Summit chipset: Could not find valid CBAR register.\n");
+                printk(KERN_ERR "Summit chipset: Could not find valid CBAR"
+                                " register.\n");
                 use_cyclone = 0;
                 return -ENODEV;
         }
         base = readq(reg);
         if(!base){
-                printk(KERN_ERR "Summit chipset: Could not find valid CBAR value.\n");
+                printk(KERN_ERR "Summit chipset: Could not find valid CBAR"
+                                " value.\n");
                 use_cyclone = 0;
                 return -ENODEV;
         }
@@ -60,7 +71,8 @@ int __init init_cyclone_clock(void)
         offset = (base + CYCLONE_PMCC_OFFSET);
         reg = (u64*)ioremap_nocache(offset, sizeof(u64));
         if(!reg){
-                printk(KERN_ERR "Summit chipset: Could not find valid PMCC register.\n");
+                printk(KERN_ERR "Summit chipset: Could not find valid PMCC"
+                                " register.\n");
                 use_cyclone = 0;
                 return -ENODEV;
         }
@@ -71,7 +83,8 @@ int __init init_cyclone_clock(void)
         offset = (base + CYCLONE_MPCS_OFFSET);
         reg = (u64*)ioremap_nocache(offset, sizeof(u64));
         if(!reg){
-                printk(KERN_ERR "Summit chipset: Could not find valid MPCS register.\n");
+                printk(KERN_ERR "Summit chipset: Could not find valid MPCS"
+                                " register.\n");
                 use_cyclone = 0;
                 return -ENODEV;
         }
@@ -82,7 +95,8 @@ int __init init_cyclone_clock(void)
         offset = (base + CYCLONE_MPMC_OFFSET);
         cyclone_timer = (u32*)ioremap_nocache(offset, sizeof(u32));
         if(!cyclone_timer){
-                printk(KERN_ERR "Summit chipset: Could not find valid MPMC register.\n");
+                printk(KERN_ERR "Summit chipset: Could not find valid MPMC"
+                                " register.\n");
                 use_cyclone = 0;
                 return -ENODEV;
         }
@@ -93,7 +107,8 @@ int __init init_cyclone_clock(void)
                 int stall = 100;
                 while(stall--) barrier();
                 if(readl(cyclone_timer) == old){
-                        printk(KERN_ERR "Summit chipset: Counter not counting! DISABLED\n");
+                        printk(KERN_ERR "Summit chipset: Counter not counting!"
+                                        " DISABLED\n");
                         iounmap(cyclone_timer);
                         cyclone_timer = 0;
                         use_cyclone = 0;
@@ -101,8 +116,11 @@ int __init init_cyclone_clock(void)
                 }
         }
         /* initialize last tick */
-        cyclone_interpolator.addr = cyclone_timer;
-        register_time_interpolator(&cyclone_interpolator);
+        cyclone_mc = cyclone_timer;
+        clocksource_cyclone.fsys_mmio = cyclone_timer;
+        clocksource_cyclone.mult = clocksource_hz2mult(CYCLONE_TIMER_FREQ,
+                                                clocksource_cyclone.shift);
+        clocksource_register(&clocksource_cyclone);
 
         return 0;
 }
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 95f517515235..c36f43c94600 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1581,7 +1581,7 @@ sys_call_table:
         data8 sys_sync_file_range               // 1300
         data8 sys_tee
         data8 sys_vmsplice
-        data8 sys_ni_syscall                    // reserved for move_pages
+        data8 sys_fallocate
         data8 sys_getcpu
         data8 sys_epoll_pwait                   // 1305
         data8 sys_utimensat
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index 3f926c2dc708..44841971f077 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -147,12 +147,11 @@ ENTRY(fsys_set_tid_address)
         FSYS_RETURN
 END(fsys_set_tid_address)
 
-/*
- * Ensure that the time interpolator structure is compatible with the asm code
- */
-#if IA64_TIME_INTERPOLATOR_SOURCE_OFFSET !=0 || IA64_TIME_INTERPOLATOR_SHIFT_OFFSET != 2 \
-        || IA64_TIME_INTERPOLATOR_JITTER_OFFSET != 3 || IA64_TIME_INTERPOLATOR_NSEC_OFFSET != 4
-#error fsys_gettimeofday incompatible with changes to struct time_interpolator
+#if IA64_GTOD_LOCK_OFFSET !=0
+#error fsys_gettimeofday incompatible with changes to struct fsyscall_gtod_data_t
+#endif
+#if IA64_ITC_JITTER_OFFSET !=0
+#error fsys_gettimeofday incompatible with changes to struct itc_jitter_data_t
 #endif
 #define CLOCK_REALTIME 0
 #define CLOCK_MONOTONIC 1
@@ -179,126 +178,124 @@ ENTRY(fsys_gettimeofday)
         // r11 = preserved: saved ar.pfs
         // r12 = preserved: memory stack
         // r13 = preserved: thread pointer
-        // r14 = address of mask / mask
+        // r14 = address of mask / mask value
         // r15 = preserved: system call number
         // r16 = preserved: current task pointer
-        // r17 = wall to monotonic use
-        // r18 = time_interpolator->offset
-        // r19 = address of wall_to_monotonic
-        // r20 = pointer to struct time_interpolator / pointer to time_interpolator->address
-        // r21 = shift factor
-        // r22 = address of time interpolator->last_counter
-        // r23 = address of time_interpolator->last_cycle
-        // r24 = adress of time_interpolator->offset
-        // r25 = last_cycle value
-        // r26 = last_counter value
-        // r27 = pointer to xtime
+        // r17 = (not used)
+        // r18 = (not used)
+        // r19 = address of itc_lastcycle
+        // r20 = struct fsyscall_gtod_data (= address of gtod_lock.sequence)
+        // r21 = address of mmio_ptr
+        // r22 = address of wall_time or monotonic_time
+        // r23 = address of shift / value
+        // r24 = address mult factor / cycle_last value
+        // r25 = itc_lastcycle value
+        // r26 = address clocksource cycle_last
+        // r27 = (not used)
         // r28 = sequence number at the beginning of critcal section
-        // r29 = address of seqlock
+        // r29 = address of itc_jitter
         // r30 = time processing flags / memory address
         // r31 = pointer to result
         // Predicates
         // p6,p7 short term use
         // p8 = timesource ar.itc
         // p9 = timesource mmio64
-        // p10 = timesource mmio32
+        // p10 = timesource mmio32 - not used
         // p11 = timesource not to be handled by asm code
-        // p12 = memory time source ( = p9 | p10)
-        // p13 = do cmpxchg with time_interpolator_last_cycle
+        // p12 = memory time source ( = p9 | p10) - not used
+        // p13 = do cmpxchg with itc_lastcycle
         // p14 = Divide by 1000
         // p15 = Add monotonic
         //
-        // Note that instructions are optimized for McKinley. McKinley can process two
-        // bundles simultaneously and therefore we continuously try to feed the CPU
-        // two bundles and then a stop.
-        tnat.nz p6,p0 = r31     // branch deferred since it does not fit into bundle structure
+        // Note that instructions are optimized for McKinley. McKinley can
+        // process two bundles simultaneously and therefore we continuously
+        // try to feed the CPU two bundles and then a stop.
+        //
+        // Additional note that code has changed a lot. Optimization is TBD.
+        // Comments begin with "?" are maybe outdated.
+        tnat.nz p6,p0 = r31     // ? branch deferred to fit later bundle
         mov pr = r30,0xc000     // Set predicates according to function
         add r2 = TI_FLAGS+IA64_TASK_SIZE,r16
-        movl r20 = time_interpolator
+        movl r20 = fsyscall_gtod_data // load fsyscall gettimeofday data address
         ;;
-        ld8 r20 = [r20]         // get pointer to time_interpolator structure
-        movl r29 = xtime_lock
+        movl r29 = itc_jitter_data      // itc_jitter
+        add r22 = IA64_GTOD_WALL_TIME_OFFSET,r20        // wall_time
         ld4 r2 = [r2]           // process work pending flags
-        movl r27 = xtime
-        ;;      // only one bundle here
-        ld8 r21 = [r20]         // first quad with control information
+        ;;
+(p15)   add r22 = IA64_GTOD_MONO_TIME_OFFSET,r20        // monotonic_time
+        add r21 = IA64_CLKSRC_MMIO_OFFSET,r20
+        add r19 = IA64_ITC_LASTCYCLE_OFFSET,r29
         and r2 = TIF_ALLWORK_MASK,r2
-(p6)    br.cond.spnt.few .fail_einval   // deferred branch
+(p6)    br.cond.spnt.few .fail_einval   // ? deferred branch
         ;;
-        add r10 = IA64_TIME_INTERPOLATOR_ADDRESS_OFFSET,r20
-        extr r3 = r21,32,32     // time_interpolator->nsec_per_cyc
-        extr r8 = r21,0,16      // time_interpolator->source
+        add r26 = IA64_CLKSRC_CYCLE_LAST_OFFSET,r20 // clksrc_cycle_last
         cmp.ne p6, p0 = 0, r2   // Fallback if work is scheduled
 (p6)    br.cond.spnt.many fsys_fallback_syscall
         ;;
-        cmp.eq p8,p12 = 0,r8    // Check for cpu timer
-        cmp.eq p9,p0 = 1,r8     // MMIO64 ?
-        extr r2 = r21,24,8      // time_interpolator->jitter
-        cmp.eq p10,p0 = 2,r8    // MMIO32 ?
-        cmp.ltu p11,p0 = 2,r8   // function or other clock
-(p11)   br.cond.spnt.many fsys_fallback_syscall
+        // Begin critical section
+.time_redo:
+        ld4.acq r28 = [r20]     // gtod_lock.sequence, Must take first
+        ;;
+        and r28 = ~1,r28        // And make sequence even to force retry if odd
         ;;
-        setf.sig f7 = r3        // Setup for scaling of counter
-(p15)   movl r19 = wall_to_monotonic
-(p12)   ld8 r30 = [r10]
-        cmp.ne p13,p0 = r2,r0   // need jitter compensation?
-        extr r21 = r21,16,8     // shift factor
+        ld8 r30 = [r21]         // clocksource->mmio_ptr
+        add r24 = IA64_CLKSRC_MULT_OFFSET,r20
+        ld4 r2 = [r29]          // itc_jitter value
+        add r23 = IA64_CLKSRC_SHIFT_OFFSET,r20
+        add r14 = IA64_CLKSRC_MASK_OFFSET,r20
         ;;
-.time_redo:
-        .pred.rel.mutex p8,p9,p10
-        ld4.acq r28 = [r29]     // xtime_lock.sequence. Must come first for locking purposes
+        ld4 r3 = [r24]          // clocksource mult value
+        ld8 r14 = [r14]         // clocksource mask value
+        cmp.eq p8,p9 = 0,r30    // use cpu timer if no mmio_ptr
         ;;
-        and r28 = ~1,r28        // Make sequence even to force retry if odd
+        setf.sig f7 = r3        // Setup for mult scaling of counter
+(p8)    cmp.ne p13,p0 = r2,r0   // need itc_jitter compensation, set p13
+        ld4 r23 = [r23]         // clocksource shift value
+        ld8 r24 = [r26]         // get clksrc_cycle_last value
+(p9)    cmp.eq p13,p0 = 0,r30   // if mmio_ptr, clear p13 jitter control
         ;;
+        .pred.rel.mutex p8,p9
 (p8)    mov r2 = ar.itc         // CPU_TIMER. 36 clocks latency!!!
-        add r22 = IA64_TIME_INTERPOLATOR_LAST_COUNTER_OFFSET,r20
-(p9)    ld8 r2 = [r30]          // readq(ti->address). Could also have latency issues..
-(p10)   ld4 r2 = [r30]          // readw(ti->address)
-(p13)   add r23 = IA64_TIME_INTERPOLATOR_LAST_CYCLE_OFFSET,r20
-        ;;                      // could be removed by moving the last add upward
-        ld8 r26 = [r22]         // time_interpolator->last_counter
-(p13)   ld8 r25 = [r23]         // time interpolator->last_cycle
-        add r24 = IA64_TIME_INTERPOLATOR_OFFSET_OFFSET,r20
-(p15)   ld8 r17 = [r19],IA64_TIMESPEC_TV_NSEC_OFFSET
-        ld8 r9 = [r27],IA64_TIMESPEC_TV_NSEC_OFFSET
-        add r14 = IA64_TIME_INTERPOLATOR_MASK_OFFSET, r20
-        ;;
-        ld8 r18 = [r24]         // time_interpolator->offset
-        ld8 r8 = [r27],-IA64_TIMESPEC_TV_NSEC_OFFSET    // xtime.tv_nsec
-(p13)   sub r3 = r25,r2 // Diff needed before comparison (thanks davidm)
-        ;;
-        ld8 r14 = [r14]         // time_interpolator->mask
-(p13)   cmp.gt.unc p6,p7 = r3,r0        // check if it is less than last. p6,p7 cleared
-        sub r10 = r2,r26        // current_counter - last_counter
-        ;;
-(p6)    sub r10 = r25,r26       // time we got was less than last_cycle
+(p9)    ld8 r2 = [r30]          // MMIO_TIMER. Could also have latency issues..
+(p13)   ld8 r25 = [r19]         // get itc_lastcycle value
+        ;;              // ? could be removed by moving the last add upward
+        ld8 r9 = [r22],IA64_TIMESPEC_TV_NSEC_OFFSET     // tv_sec
+        ;;
+        ld8 r8 = [r22],-IA64_TIMESPEC_TV_NSEC_OFFSET    // tv_nsec
+(p13)   sub r3 = r25,r2         // Diff needed before comparison (thanks davidm)
+        ;;
+(p13)   cmp.gt.unc p6,p7 = r3,r0 // check if it is less than last. p6,p7 cleared
+        sub r10 = r2,r24        // current_cycle - last_cycle
+        ;;
+(p6)    sub r10 = r25,r24       // time we got was less than last_cycle
 (p7)    mov ar.ccv = r25        // more than last_cycle. Prep for cmpxchg
         ;;
+(p7)    cmpxchg8.rel r3 = [r19],r2,ar.ccv
+        ;;
+(p7)    cmp.ne p7,p0 = r25,r3   // if cmpxchg not successful
+        ;;
+(p7)    sub r10 = r3,r24        // then use new last_cycle instead
+        ;;
         and r10 = r10,r14       // Apply mask
         ;;
         setf.sig f8 = r10
         nop.i 123
         ;;
-(p7)    cmpxchg8.rel r3 = [r23],r2,ar.ccv
-EX(.fail_efault, probe.w.fault r31, 3)  // This takes 5 cycles and we have spare time
+        // fault check takes 5 cycles and we have spare time
+EX(.fail_efault, probe.w.fault r31, 3)
         xmpy.l f8 = f8,f7       // nsec_per_cyc*(counter-last_counter)
-(p15)   add r9 = r9,r17         // Add wall to monotonic.secs to result secs
         ;;
-(p15)   ld8 r17 = [r19],-IA64_TIMESPEC_TV_NSEC_OFFSET
-(p7)    cmp.ne p7,p0 = r25,r3   // if cmpxchg not successful redo
-        // simulate tbit.nz.or p7,p0 = r28,0
+        // ? simulate tbit.nz.or p7,p0 = r28,0
         getf.sig r2 = f8
         mf
-        add r8 = r8,r18         // Add time interpolator offset
         ;;
-        ld4 r10 = [r29]         // xtime_lock.sequence
-(p15)   add r8 = r8, r17        // Add monotonic.nsecs to nsecs
-        shr.u r2 = r2,r21
-        ;;              // overloaded 3 bundles!
-        // End critical section.
+        ld4 r10 = [r20]         // gtod_lock.sequence
+        shr.u r2 = r2,r23       // shift by factor
+        ;;              // ? overloaded 3 bundles!
         add r8 = r8,r2          // Add xtime.nsecs
-        cmp4.ne.or p7,p0 = r28,r10
-(p7)    br.cond.dpnt.few .time_redo     // sequence number changed ?
+        cmp4.ne p7,p0 = r28,r10
+(p7)    br.cond.dpnt.few .time_redo     // sequence number changed, redo
+        // End critical section.
         // Now r8=tv->tv_nsec and r9=tv->tv_sec
         mov r10 = r0
         movl r2 = 1000000000
@@ -308,19 +305,19 @@ EX(.fail_efault, probe.w.fault r31, 3)	// This takes 5 cycles and we have spare
 .time_normalize:
         mov r21 = r8
         cmp.ge p6,p0 = r8,r2
-(p14)   shr.u r20 = r8, 3               // We can repeat this if necessary just wasting some time
+(p14)   shr.u r20 = r8, 3 // We can repeat this if necessary just wasting time
         ;;
 (p14)   setf.sig f8 = r20
 (p6)    sub r8 = r8,r2
-(p6)    add r9 = 1,r9                   // two nops before the branch.
-(p14)   setf.sig f7 = r3                // Chances for repeats are 1 in 10000 for gettod
+(p6)    add r9 = 1,r9           // two nops before the branch.
+(p14)   setf.sig f7 = r3        // Chances for repeats are 1 in 10000 for gettod
 (p6)    br.cond.dpnt.few .time_normalize
         ;;
         // Divided by 8 though shift. Now divide by 125
         // The compiler was able to do that with a multiply
         // and a shift and we do the same
-EX(.fail_efault, probe.w.fault r23, 3)          // This also costs 5 cycles
-(p14)   xmpy.hu f8 = f8, f7                     // xmpy has 5 cycles latency so use it...
+EX(.fail_efault, probe.w.fault r23, 3)  // This also costs 5 cycles
+(p14)   xmpy.hu f8 = f8, f7             // xmpy has 5 cycles latency so use it
         ;;
         mov r8 = r0
 (p14)   getf.sig r2 = f8
diff --git a/arch/ia64/kernel/fsyscall_gtod_data.h b/arch/ia64/kernel/fsyscall_gtod_data.h
new file mode 100644
index 000000000000..490dab55fba3
--- /dev/null
+++ b/arch/ia64/kernel/fsyscall_gtod_data.h
@@ -0,0 +1,23 @@
+/*
+ * (c) Copyright 2007 Hewlett-Packard Development Company, L.P.
+ *        Contributed by Peter Keilty <peter.keilty@hp.com>
+ *
+ * fsyscall gettimeofday data
+ */
+
+struct fsyscall_gtod_data_t {
+        seqlock_t       lock;
+        struct timespec wall_time;
+        struct timespec monotonic_time;
+        cycle_t         clk_mask;
+        u32             clk_mult;
+        u32             clk_shift;
+        void            *clk_fsys_mmio;
+        cycle_t         clk_cycle_last;
+} __attribute__ ((aligned (L1_CACHE_BYTES)));
+
+struct itc_jitter_data_t {
+        int             itc_jitter;
+        cycle_t         itc_lastcycle;
+} __attribute__ ((aligned (L1_CACHE_BYTES)));
+
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index 37f46527d233..91e6dc1e7baf 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -118,15 +118,25 @@ static DEFINE_SPINLOCK(iosapic_lock);
  * vector.
  */
 
-struct iosapic_rte_info {
-        struct list_head rte_list;      /* node in list of RTEs sharing the
-                                         * same vector */
+#define NO_REF_RTE      0
+
+static struct iosapic {
         char __iomem    *addr;          /* base address of IOSAPIC */
-        unsigned int    gsi_base;       /* first GSI assigned to this
-                                         * IOSAPIC */
+        unsigned int    gsi_base;       /* GSI base */
+        unsigned short  num_rte;        /* # of RTEs on this IOSAPIC */
+        int             rtes_inuse;     /* # of RTEs in use on this IOSAPIC */
+#ifdef CONFIG_NUMA
+        unsigned short  node;           /* numa node association via pxm */
+#endif
+        spinlock_t      lock;           /* lock for indirect reg access */
+} iosapic_lists[NR_IOSAPICS];
+
+struct iosapic_rte_info {
+        struct list_head rte_list;      /* RTEs sharing the same vector */
         char            rte_index;      /* IOSAPIC RTE index */
         int             refcnt;         /* reference counter */
         unsigned int    flags;          /* flags */
+        struct iosapic  *iosapic;
 } ____cacheline_aligned;
 
 static struct iosapic_intr_info {
@@ -140,24 +150,23 @@ static struct iosapic_intr_info {
         unsigned char   polarity: 1;    /* interrupt polarity
                                          * (see iosapic.h) */
         unsigned char   trigger : 1;    /* trigger mode (see iosapic.h) */
-} iosapic_intr_info[IA64_NUM_VECTORS];
-
-static struct iosapic {
-        char __iomem    *addr;          /* base address of IOSAPIC */
-        unsigned int    gsi_base;       /* first GSI assigned to this
-                                         * IOSAPIC */
-        unsigned short  num_rte;        /* # of RTEs on this IOSAPIC */
-        int             rtes_inuse;     /* # of RTEs in use on this IOSAPIC */
-#ifdef CONFIG_NUMA
-        unsigned short  node;           /* numa node association via pxm */
-#endif
-} iosapic_lists[NR_IOSAPICS];
+} iosapic_intr_info[NR_IRQS];
 
 static unsigned char pcat_compat __devinitdata; /* 8259 compatibility flag */
 
 static int iosapic_kmalloc_ok;
 static LIST_HEAD(free_rte_list);
 
+static inline void
+iosapic_write(struct iosapic *iosapic, unsigned int reg, u32 val)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&iosapic->lock, flags);
+        __iosapic_write(iosapic->addr, reg, val);
+        spin_unlock_irqrestore(&iosapic->lock, flags);
+}
+
 /*
  * Find an IOSAPIC associated with a GSI
  */
@@ -175,17 +184,18 @@ find_iosapic (unsigned int gsi)
         return -1;
 }
 
-static inline int
-_gsi_to_vector (unsigned int gsi)
+static inline int __gsi_to_irq(unsigned int gsi)
 {
+        int irq;
         struct iosapic_intr_info *info;
         struct iosapic_rte_info *rte;
 
-        for (info = iosapic_intr_info; info <
-                     iosapic_intr_info + IA64_NUM_VECTORS; ++info)
+        for (irq = 0; irq < NR_IRQS; irq++) {
+                info = &iosapic_intr_info[irq];
                 list_for_each_entry(rte, &info->rtes, rte_list)
-                        if (rte->gsi_base + rte->rte_index == gsi)
-                                return info - iosapic_intr_info;
+                        if (rte->iosapic->gsi_base + rte->rte_index == gsi)
+                                return irq;
+        }
         return -1;
 }
 
@@ -196,7 +206,10 @@ _gsi_to_vector (unsigned int gsi)
 inline int
 gsi_to_vector (unsigned int gsi)
 {
-        return _gsi_to_vector(gsi);
+        int irq = __gsi_to_irq(gsi);
+        if (check_irq_used(irq) < 0)
+                return -1;
+        return irq_to_vector(irq);
 }
 
 int
@@ -204,66 +217,48 @@ gsi_to_irq (unsigned int gsi)
 {
         unsigned long flags;
         int irq;
-        /*
-         * XXX fix me: this assumes an identity mapping between IA-64 vector
-         * and Linux irq numbers...
-         */
+
         spin_lock_irqsave(&iosapic_lock, flags);
-        {
-                irq = _gsi_to_vector(gsi);
-        }
+        irq = __gsi_to_irq(gsi);
         spin_unlock_irqrestore(&iosapic_lock, flags);
-
         return irq;
 }
 
-static struct iosapic_rte_info *gsi_vector_to_rte(unsigned int gsi,
-                                                  unsigned int vec)
+static struct iosapic_rte_info *find_rte(unsigned int irq, unsigned int gsi)
 {
         struct iosapic_rte_info *rte;
 
-        list_for_each_entry(rte, &iosapic_intr_info[vec].rtes, rte_list)
-                if (rte->gsi_base + rte->rte_index == gsi)
+        list_for_each_entry(rte, &iosapic_intr_info[irq].rtes, rte_list)
+                if (rte->iosapic->gsi_base + rte->rte_index == gsi)
                         return rte;
         return NULL;
 }
 
 static void
-set_rte (unsigned int gsi, unsigned int vector, unsigned int dest, int mask)
+set_rte (unsigned int gsi, unsigned int irq, unsigned int dest, int mask)
 {
         unsigned long pol, trigger, dmode;
         u32 low32, high32;
-        char __iomem *addr;
         int rte_index;
         char redir;
         struct iosapic_rte_info *rte;
+        ia64_vector vector = irq_to_vector(irq);
 
         DBG(KERN_DEBUG"IOSAPIC: routing vector %d to 0x%x\n", vector, dest);
 
-        rte = gsi_vector_to_rte(gsi, vector);
+        rte = find_rte(irq, gsi);
         if (!rte)
                 return;         /* not an IOSAPIC interrupt */
 
         rte_index = rte->rte_index;
-        addr    = rte->addr;
-        pol     = iosapic_intr_info[vector].polarity;
-        trigger = iosapic_intr_info[vector].trigger;
-        dmode   = iosapic_intr_info[vector].dmode;
+        pol     = iosapic_intr_info[irq].polarity;
+        trigger = iosapic_intr_info[irq].trigger;
+        dmode   = iosapic_intr_info[irq].dmode;
 
         redir = (dmode == IOSAPIC_LOWEST_PRIORITY) ? 1 : 0;
 
 #ifdef CONFIG_SMP
-        {
-                unsigned int irq;
-
-                for (irq = 0; irq < NR_IRQS; ++irq)
-                        if (irq_to_vector(irq) == vector) {
-                                set_irq_affinity_info(irq,
-                                                      (int)(dest & 0xffff),
-                                                      redir);
-                                break;
-                        }
-        }
+        set_irq_affinity_info(irq, (int)(dest & 0xffff), redir);
 #endif
 
         low32 = ((pol << IOSAPIC_POLARITY_SHIFT) |
@@ -275,10 +270,10 @@ set_rte (unsigned int gsi, unsigned int vector, unsigned int dest, int mask)
         /* dest contains both id and eid */
         high32 = (dest << IOSAPIC_DEST_SHIFT);
 
-        iosapic_write(addr, IOSAPIC_RTE_HIGH(rte_index), high32);
-        iosapic_write(addr, IOSAPIC_RTE_LOW(rte_index), low32);
-        iosapic_intr_info[vector].low32 = low32;
-        iosapic_intr_info[vector].dest = dest;
+        iosapic_write(rte->iosapic, IOSAPIC_RTE_HIGH(rte_index), high32);
+        iosapic_write(rte->iosapic, IOSAPIC_RTE_LOW(rte_index), low32);
+        iosapic_intr_info[irq].low32 = low32;
+        iosapic_intr_info[irq].dest = dest;
 }
 
 static void
@@ -294,15 +289,18 @@ kexec_disable_iosapic(void)
 {
         struct iosapic_intr_info *info;
         struct iosapic_rte_info *rte;
-        u8 vec = 0;
-        for (info = iosapic_intr_info; info <
-                        iosapic_intr_info + IA64_NUM_VECTORS; ++info, ++vec) {
+        ia64_vector vec;
+        int irq;
+
+        for (irq = 0; irq < NR_IRQS; irq++) {
+                info = &iosapic_intr_info[irq];
+                vec = irq_to_vector(irq);
                 list_for_each_entry(rte, &info->rtes,
                                 rte_list) {
-                        iosapic_write(rte->addr,
+                        iosapic_write(rte->iosapic,
                                         IOSAPIC_RTE_LOW(rte->rte_index),
                                         IOSAPIC_MASK|vec);
-                        iosapic_eoi(rte->addr, vec);
+                        iosapic_eoi(rte->iosapic->addr, vec);
                 }
         }
 }
@@ -311,54 +309,36 @@ kexec_disable_iosapic(void)
 static void
 mask_irq (unsigned int irq)
 {
-        unsigned long flags;
-        char __iomem *addr;
         u32 low32;
         int rte_index;
-        ia64_vector vec = irq_to_vector(irq);
         struct iosapic_rte_info *rte;
 
-        if (list_empty(&iosapic_intr_info[vec].rtes))
+        if (list_empty(&iosapic_intr_info[irq].rtes))
                 return;                 /* not an IOSAPIC interrupt! */
 
-        spin_lock_irqsave(&iosapic_lock, flags);
-        {
-                /* set only the mask bit */
-                low32 = iosapic_intr_info[vec].low32 |= IOSAPIC_MASK;
-                list_for_each_entry(rte, &iosapic_intr_info[vec].rtes,
-                                    rte_list) {
-                        addr = rte->addr;
-                        rte_index = rte->rte_index;
-                        iosapic_write(addr, IOSAPIC_RTE_LOW(rte_index), low32);
-                }
+        /* set only the mask bit */
+        low32 = iosapic_intr_info[irq].low32 |= IOSAPIC_MASK;
+        list_for_each_entry(rte, &iosapic_intr_info[irq].rtes, rte_list) {
+                rte_index = rte->rte_index;
+                iosapic_write(rte->iosapic, IOSAPIC_RTE_LOW(rte_index), low32);
         }
-        spin_unlock_irqrestore(&iosapic_lock, flags);
 }
 
 static void
 unmask_irq (unsigned int irq)
 {
-        unsigned long flags;
-        char __iomem *addr;
         u32 low32;
         int rte_index;
-        ia64_vector vec = irq_to_vector(irq);
         struct iosapic_rte_info *rte;
 
-        if (list_empty(&iosapic_intr_info[vec].rtes))
+        if (list_empty(&iosapic_intr_info[irq].rtes))
                 return;                 /* not an IOSAPIC interrupt! */
 
-        spin_lock_irqsave(&iosapic_lock, flags);
-        {
-                low32 = iosapic_intr_info[vec].low32 &= ~IOSAPIC_MASK;
-                list_for_each_entry(rte, &iosapic_intr_info[vec].rtes,
-                                    rte_list) {
-                        addr = rte->addr;
-                        rte_index = rte->rte_index;
-                        iosapic_write(addr, IOSAPIC_RTE_LOW(rte_index), low32);
-                }
+        low32 = iosapic_intr_info[irq].low32 &= ~IOSAPIC_MASK;
+        list_for_each_entry(rte, &iosapic_intr_info[irq].rtes, rte_list) {
+                rte_index = rte->rte_index;
+                iosapic_write(rte->iosapic, IOSAPIC_RTE_LOW(rte_index), low32);
         }
-        spin_unlock_irqrestore(&iosapic_lock, flags);
 }
 
 
@@ -366,23 +346,24 @@ static void
 iosapic_set_affinity (unsigned int irq, cpumask_t mask)
 {
 #ifdef CONFIG_SMP
-        unsigned long flags;
         u32 high32, low32;
         int dest, rte_index;
-        char __iomem *addr;
         int redir = (irq & IA64_IRQ_REDIRECTED) ? 1 : 0;
-        ia64_vector vec;
         struct iosapic_rte_info *rte;
+        struct iosapic *iosapic;
 
         irq &= (~IA64_IRQ_REDIRECTED);
-        vec = irq_to_vector(irq);
 
+        cpus_and(mask, mask, cpu_online_map);
         if (cpus_empty(mask))
                 return;
 
+        if (reassign_irq_vector(irq, first_cpu(mask)))
+                return;
+
         dest = cpu_physical_id(first_cpu(mask));
 
-        if (list_empty(&iosapic_intr_info[vec].rtes))
+        if (list_empty(&iosapic_intr_info[irq].rtes))
                 return;                 /* not an IOSAPIC interrupt */
 
         set_irq_affinity_info(irq, dest, redir);
@@ -390,31 +371,24 @@ iosapic_set_affinity (unsigned int irq, cpumask_t mask)
         /* dest contains both id and eid */
         high32 = dest << IOSAPIC_DEST_SHIFT;
 
-        spin_lock_irqsave(&iosapic_lock, flags);
-        {
-                low32 = iosapic_intr_info[vec].low32 &
-                        ~(7 << IOSAPIC_DELIVERY_SHIFT);
-
-                if (redir)
-                        /* change delivery mode to lowest priority */
-                        low32 |= (IOSAPIC_LOWEST_PRIORITY <<
-                                  IOSAPIC_DELIVERY_SHIFT);
-                else
-                        /* change delivery mode to fixed */
-                        low32 |= (IOSAPIC_FIXED << IOSAPIC_DELIVERY_SHIFT);
-
-                iosapic_intr_info[vec].low32 = low32;
-                iosapic_intr_info[vec].dest = dest;
-                list_for_each_entry(rte, &iosapic_intr_info[vec].rtes,
-                                    rte_list) {
-                        addr = rte->addr;
-                        rte_index = rte->rte_index;
-                        iosapic_write(addr, IOSAPIC_RTE_HIGH(rte_index),
-                                      high32);
-                        iosapic_write(addr, IOSAPIC_RTE_LOW(rte_index), low32);
-                }
+        low32 = iosapic_intr_info[irq].low32 & ~(7 << IOSAPIC_DELIVERY_SHIFT);
+        if (redir)
+                /* change delivery mode to lowest priority */
+                low32 |= (IOSAPIC_LOWEST_PRIORITY << IOSAPIC_DELIVERY_SHIFT);
+        else
+                /* change delivery mode to fixed */
+                low32 |= (IOSAPIC_FIXED << IOSAPIC_DELIVERY_SHIFT);
+        low32 &= IOSAPIC_VECTOR_MASK;
+        low32 |= irq_to_vector(irq);
+
+        iosapic_intr_info[irq].low32 = low32;
+        iosapic_intr_info[irq].dest = dest;
+        list_for_each_entry(rte, &iosapic_intr_info[irq].rtes, rte_list) {
+                iosapic = rte->iosapic;
+                rte_index = rte->rte_index;
+                iosapic_write(iosapic, IOSAPIC_RTE_HIGH(rte_index), high32);
+                iosapic_write(iosapic, IOSAPIC_RTE_LOW(rte_index), low32);
         }
-        spin_unlock_irqrestore(&iosapic_lock, flags);
 #endif
 }
 
@@ -434,10 +408,20 @@ iosapic_end_level_irq (unsigned int irq)
 {
         ia64_vector vec = irq_to_vector(irq);
         struct iosapic_rte_info *rte;
+        int do_unmask_irq = 0;
 
-        move_native_irq(irq);
-        list_for_each_entry(rte, &iosapic_intr_info[vec].rtes, rte_list)
-                iosapic_eoi(rte->addr, vec);
+        if (unlikely(irq_desc[irq].status & IRQ_MOVE_PENDING)) {
+                do_unmask_irq = 1;
+                mask_irq(irq);
+        }
+
+        list_for_each_entry(rte, &iosapic_intr_info[irq].rtes, rte_list)
+                iosapic_eoi(rte->iosapic->addr, vec);
+
+        if (unlikely(do_unmask_irq)) {
+                move_masked_irq(irq);
+                unmask_irq(irq);
+        }
 }
 
 #define iosapic_shutdown_level_irq      mask_irq
@@ -519,13 +503,12 @@ iosapic_version (char __iomem *addr)
          *      unsigned int reserved2 : 8;
          * }
          */
-        return iosapic_read(addr, IOSAPIC_VERSION);
+        return __iosapic_read(addr, IOSAPIC_VERSION);
 }
 
-static int iosapic_find_sharable_vector (unsigned long trigger,
-                                         unsigned long pol)
+static int iosapic_find_sharable_irq(unsigned long trigger, unsigned long pol)
 {
-        int i, vector = -1, min_count = -1;
+        int i, irq = -ENOSPC, min_count = -1;
         struct iosapic_intr_info *info;
 
         /*
@@ -533,21 +516,21 @@ static int iosapic_find_sharable_vector (unsigned long trigger,
          * supported yet
          */
         if (trigger == IOSAPIC_EDGE)
-                return -1;
+                return -EINVAL;
 
-        for (i = IA64_FIRST_DEVICE_VECTOR; i <= IA64_LAST_DEVICE_VECTOR; i++) {
+        for (i = 0; i <= NR_IRQS; i++) {
                 info = &iosapic_intr_info[i];
                 if (info->trigger == trigger && info->polarity == pol &&
-                    (info->dmode == IOSAPIC_FIXED || info->dmode ==
-                     IOSAPIC_LOWEST_PRIORITY)) {
+                    (info->dmode == IOSAPIC_FIXED ||
+                     info->dmode == IOSAPIC_LOWEST_PRIORITY) &&
+                    can_request_irq(i, IRQF_SHARED)) {
                         if (min_count == -1 || info->count < min_count) {
-                                vector = i;
+                                irq = i;
                                 min_count = info->count;
                         }
                 }
         }
-
-        return vector;
+        return irq;
 }
 
 /*
@@ -555,25 +538,25 @@ static int iosapic_find_sharable_vector (unsigned long trigger,
  *  assign a new vector for the other and make the vector available
  */
 static void __init
-iosapic_reassign_vector (int vector)
+iosapic_reassign_vector (int irq)
 {
-        int new_vector;
+        int new_irq;
 
-        if (!list_empty(&iosapic_intr_info[vector].rtes)) {
-                new_vector = assign_irq_vector(AUTO_ASSIGN);
-                if (new_vector < 0)
+        if (!list_empty(&iosapic_intr_info[irq].rtes)) {
+                new_irq = create_irq();
+                if (new_irq < 0)
                         panic("%s: out of interrupt vectors!\n", __FUNCTION__);
                 printk(KERN_INFO "Reassigning vector %d to %d\n",
-                       vector, new_vector);
-                memcpy(&iosapic_intr_info[new_vector], &iosapic_intr_info[vector],
+                       irq_to_vector(irq), irq_to_vector(new_irq));
+                memcpy(&iosapic_intr_info[new_irq], &iosapic_intr_info[irq],
                        sizeof(struct iosapic_intr_info));
-                INIT_LIST_HEAD(&iosapic_intr_info[new_vector].rtes);
-                list_move(iosapic_intr_info[vector].rtes.next,
-                          &iosapic_intr_info[new_vector].rtes);
-                memset(&iosapic_intr_info[vector], 0,
+                INIT_LIST_HEAD(&iosapic_intr_info[new_irq].rtes);
+                list_move(iosapic_intr_info[irq].rtes.next,
+                          &iosapic_intr_info[new_irq].rtes);
+                memset(&iosapic_intr_info[irq], 0,
                        sizeof(struct iosapic_intr_info));
-                iosapic_intr_info[vector].low32 = IOSAPIC_MASK;
-                INIT_LIST_HEAD(&iosapic_intr_info[vector].rtes);
+                iosapic_intr_info[irq].low32 = IOSAPIC_MASK;
+                INIT_LIST_HEAD(&iosapic_intr_info[irq].rtes);
         }
 }
 
@@ -610,29 +593,18 @@ static struct iosapic_rte_info *iosapic_alloc_rte (void)
         return rte;
 }
 
-static void iosapic_free_rte (struct iosapic_rte_info *rte)
+static inline int irq_is_shared (int irq)
 {
-        if (rte->flags & RTE_PREALLOCATED)
-                list_add_tail(&rte->rte_list, &free_rte_list);
-        else
-                kfree(rte);
-}
-
-static inline int vector_is_shared (int vector)
-{
-        return (iosapic_intr_info[vector].count > 1);
+        return (iosapic_intr_info[irq].count > 1);
 }
 
 static int
-register_intr (unsigned int gsi, int vector, unsigned char delivery,
+register_intr (unsigned int gsi, int irq, unsigned char delivery,
                unsigned long polarity, unsigned long trigger)
 {
         irq_desc_t *idesc;
         struct hw_interrupt_type *irq_type;
-        int rte_index;
         int index;
-        unsigned long gsi_base;
-        void __iomem *iosapic_address;
         struct iosapic_rte_info *rte;
 
         index = find_iosapic(gsi);
@@ -642,10 +614,7 @@ register_intr (unsigned int gsi, int vector, unsigned char delivery,
                 return -ENODEV;
         }
 
-        iosapic_address = iosapic_lists[index].addr;
-        gsi_base = iosapic_lists[index].gsi_base;
-
-        rte = gsi_vector_to_rte(gsi, vector);
+        rte = find_rte(irq, gsi);
         if (!rte) {
                 rte = iosapic_alloc_rte();
                 if (!rte) {
@@ -654,40 +623,42 @@ register_intr (unsigned int gsi, int vector, unsigned char delivery,
                         return -ENOMEM;
                 }
 
-                rte_index = gsi - gsi_base;
-                rte->rte_index  = rte_index;
-                rte->addr       = iosapic_address;
-                rte->gsi_base   = gsi_base;
+                rte->iosapic    = &iosapic_lists[index];
+                rte->rte_index  = gsi - rte->iosapic->gsi_base;
                 rte->refcnt++;
-                list_add_tail(&rte->rte_list, &iosapic_intr_info[vector].rtes);
-                iosapic_intr_info[vector].count++;
+                list_add_tail(&rte->rte_list, &iosapic_intr_info[irq].rtes);
+                iosapic_intr_info[irq].count++;
                 iosapic_lists[index].rtes_inuse++;
         }
-        else if (vector_is_shared(vector)) {
-                struct iosapic_intr_info *info = &iosapic_intr_info[vector];
-                if (info->trigger != trigger || info->polarity != polarity) {
+        else if (rte->refcnt == NO_REF_RTE) {
+                struct iosapic_intr_info *info = &iosapic_intr_info[irq];
+                if (info->count > 0 &&
+                    (info->trigger != trigger || info->polarity != polarity)){
                         printk (KERN_WARNING
                                 "%s: cannot override the interrupt\n",
                                 __FUNCTION__);
                         return -EINVAL;
                 }
+                rte->refcnt++;
+                iosapic_intr_info[irq].count++;
+                iosapic_lists[index].rtes_inuse++;
         }
 
-        iosapic_intr_info[vector].polarity = polarity;
-        iosapic_intr_info[vector].dmode    = delivery;
-        iosapic_intr_info[vector].trigger  = trigger;
+        iosapic_intr_info[irq].polarity = polarity;
+        iosapic_intr_info[irq].dmode    = delivery;
+        iosapic_intr_info[irq].trigger  = trigger;
 
         if (trigger == IOSAPIC_EDGE)
                 irq_type = &irq_type_iosapic_edge;
         else
                 irq_type = &irq_type_iosapic_level;
 
-        idesc = irq_desc + vector;
+        idesc = irq_desc + irq;
         if (idesc->chip != irq_type) {
                 if (idesc->chip != &no_irq_type)
                         printk(KERN_WARNING
                                "%s: changing vector %d from %s to %s\n",
-                               __FUNCTION__, vector,
+                               __FUNCTION__, irq_to_vector(irq),
                                idesc->chip->name, irq_type->name);
                 idesc->chip = irq_type;
         }
@@ -695,18 +666,19 @@ register_intr (unsigned int gsi, int vector, unsigned char delivery,
 }
 
 static unsigned int
-get_target_cpu (unsigned int gsi, int vector)
+get_target_cpu (unsigned int gsi, int irq)
 {
 #ifdef CONFIG_SMP
         static int cpu = -1;
         extern int cpe_vector;
+        cpumask_t domain = irq_to_domain(irq);
 
         /*
          * In case of vector shared by multiple RTEs, all RTEs that
          * share the vector need to use the same destination CPU.
          */
-        if (!list_empty(&iosapic_intr_info[vector].rtes))
-                return iosapic_intr_info[vector].dest;
+        if (!list_empty(&iosapic_intr_info[irq].rtes))
+                return iosapic_intr_info[irq].dest;
 
         /*
          * If the platform supports redirection via XTP, let it
@@ -723,7 +695,7 @@ get_target_cpu (unsigned int gsi, int vector)
                 return cpu_physical_id(smp_processor_id());
 
 #ifdef CONFIG_ACPI
-        if (cpe_vector > 0 && vector == IA64_CPEP_VECTOR)
+        if (cpe_vector > 0 && irq_to_vector(irq) == IA64_CPEP_VECTOR)
                 return get_cpei_target_cpu();
 #endif
 
@@ -738,7 +710,7 @@ get_target_cpu (unsigned int gsi, int vector)
                         goto skip_numa_setup;
 
                 cpu_mask = node_to_cpumask(iosapic_lists[iosapic_index].node);
-
+                cpus_and(cpu_mask, cpu_mask, domain);
                 for_each_cpu_mask(numa_cpu, cpu_mask) {
                         if (!cpu_online(numa_cpu))
                                 cpu_clear(numa_cpu, cpu_mask);
@@ -749,8 +721,8 @@ get_target_cpu (unsigned int gsi, int vector)
                 if (!num_cpus)
                         goto skip_numa_setup;
 
-                /* Use vector assignment to distribute across cpus in node */
-                cpu_index = vector % num_cpus;
+                /* Use irq assignment to distribute across cpus in node */
+                cpu_index = irq % num_cpus;
 
                 for (numa_cpu = first_cpu(cpu_mask) ; i < cpu_index ; i++)
                         numa_cpu = next_cpu(numa_cpu, cpu_mask);
@@ -768,7 +740,7 @@ skip_numa_setup:
         do {
                 if (++cpu >= NR_CPUS)
                         cpu = 0;
-        } while (!cpu_online(cpu));
+        } while (!cpu_online(cpu) || !cpu_isset(cpu, domain));
 
         return cpu_physical_id(cpu);
 #else  /* CONFIG_SMP */
@@ -785,84 +757,72 @@ int
 iosapic_register_intr (unsigned int gsi,
                        unsigned long polarity, unsigned long trigger)
 {
-        int vector, mask = 1, err;
+        int irq, mask = 1, err;
         unsigned int dest;
         unsigned long flags;
         struct iosapic_rte_info *rte;
         u32 low32;
-again:
+
         /*
          * If this GSI has already been registered (i.e., it's a
          * shared interrupt, or we lost a race to register it),
          * don't touch the RTE.
          */
         spin_lock_irqsave(&iosapic_lock, flags);
-        {
-                vector = gsi_to_vector(gsi);
-                if (vector > 0) {
-                        rte = gsi_vector_to_rte(gsi, vector);
+        irq = __gsi_to_irq(gsi);
+        if (irq > 0) {
+                rte = find_rte(irq, gsi);
+                if(iosapic_intr_info[irq].count == 0) {
+                        assign_irq_vector(irq);
+                        dynamic_irq_init(irq);
+                } else if (rte->refcnt != NO_REF_RTE) {
                         rte->refcnt++;
-                        spin_unlock_irqrestore(&iosapic_lock, flags);
-                        return vector;
+                        goto unlock_iosapic_lock;
                 }
-        }
-        spin_unlock_irqrestore(&iosapic_lock, flags);
+        } else
+                irq = create_irq();
 
         /* If vector is running out, we try to find a sharable vector */
-        vector = assign_irq_vector(AUTO_ASSIGN);
-        if (vector < 0) {
-                vector = iosapic_find_sharable_vector(trigger, polarity);
-                if (vector < 0)
-                        return -ENOSPC;
+        if (irq < 0) {
+                irq = iosapic_find_sharable_irq(trigger, polarity);
+                if (irq < 0)
+                        goto unlock_iosapic_lock;
         }
 
-        spin_lock_irqsave(&irq_desc[vector].lock, flags);
-        spin_lock(&iosapic_lock);
-        {
-                if (gsi_to_vector(gsi) > 0) {
-                        if (list_empty(&iosapic_intr_info[vector].rtes))
-                                free_irq_vector(vector);
-                        spin_unlock(&iosapic_lock);
-                        spin_unlock_irqrestore(&irq_desc[vector].lock,
-                                               flags);
-                        goto again;
-                }
-
-                dest = get_target_cpu(gsi, vector);
-                err = register_intr(gsi, vector, IOSAPIC_LOWEST_PRIORITY,
-                              polarity, trigger);
-                if (err < 0) {
-                        spin_unlock(&iosapic_lock);
-                        spin_unlock_irqrestore(&irq_desc[vector].lock,
-                                               flags);
-                        return err;
-                }
-
-                /*
-                 * If the vector is shared and already unmasked for
-                 * other interrupt sources, don't mask it.
-                 */
-                low32 = iosapic_intr_info[vector].low32;
-                if (vector_is_shared(vector) && !(low32 & IOSAPIC_MASK))
-                        mask = 0;
-                set_rte(gsi, vector, dest, mask);
+        spin_lock(&irq_desc[irq].lock);
+        dest = get_target_cpu(gsi, irq);
+        err = register_intr(gsi, irq, IOSAPIC_LOWEST_PRIORITY,
+                            polarity, trigger);
+        if (err < 0) {
+                irq = err;
+                goto unlock_all;
         }
-        spin_unlock(&iosapic_lock);
-        spin_unlock_irqrestore(&irq_desc[vector].lock, flags);
+
+        /*
+         * If the vector is shared and already unmasked for other
+         * interrupt sources, don't mask it.
+         */
+        low32 = iosapic_intr_info[irq].low32;
+        if (irq_is_shared(irq) && !(low32 & IOSAPIC_MASK))
+                mask = 0;
+        set_rte(gsi, irq, dest, mask);
 
         printk(KERN_INFO "GSI %u (%s, %s) -> CPU %d (0x%04x) vector %d\n",
                gsi, (trigger == IOSAPIC_EDGE ? "edge" : "level"),
                (polarity == IOSAPIC_POL_HIGH ? "high" : "low"),
-               cpu_logical_id(dest), dest, vector);
-
-        return vector;
+               cpu_logical_id(dest), dest, irq_to_vector(irq));
+ unlock_all:
+        spin_unlock(&irq_desc[irq].lock);
+ unlock_iosapic_lock:
+        spin_unlock_irqrestore(&iosapic_lock, flags);
+        return irq;
 }
 
 void
 iosapic_unregister_intr (unsigned int gsi)
 {
         unsigned long flags;
-        int irq, vector, index;
+        int irq, index;
         irq_desc_t *idesc;
         u32 low32;
         unsigned long trigger, polarity;
@@ -881,78 +841,56 @@ iosapic_unregister_intr (unsigned int gsi)
                 WARN_ON(1);
                 return;
         }
-        vector = irq_to_vector(irq);
 
-        idesc = irq_desc + irq;
-        spin_lock_irqsave(&idesc->lock, flags);
-        spin_lock(&iosapic_lock);
-        {
-                if ((rte = gsi_vector_to_rte(gsi, vector)) == NULL) {
-                        printk(KERN_ERR
-                               "iosapic_unregister_intr(%u) unbalanced\n",
-                               gsi);
-                        WARN_ON(1);
-                        goto out;
-                }
+        spin_lock_irqsave(&iosapic_lock, flags);
+        if ((rte = find_rte(irq, gsi)) == NULL) {
+                printk(KERN_ERR "iosapic_unregister_intr(%u) unbalanced\n",
+                       gsi);
+                WARN_ON(1);
+                goto out;
+        }
 
-                if (--rte->refcnt > 0)
-                        goto out;
+        if (--rte->refcnt > 0)
+                goto out;
 
-                /* Mask the interrupt */
-                low32 = iosapic_intr_info[vector].low32 | IOSAPIC_MASK;
-                iosapic_write(rte->addr, IOSAPIC_RTE_LOW(rte->rte_index),
-                              low32);
+        idesc = irq_desc + irq;
+        rte->refcnt = NO_REF_RTE;
 
-                /* Remove the rte entry from the list */
-                list_del(&rte->rte_list);
-                iosapic_intr_info[vector].count--;
-                iosapic_free_rte(rte);
-                index = find_iosapic(gsi);
-                iosapic_lists[index].rtes_inuse--;
-                WARN_ON(iosapic_lists[index].rtes_inuse < 0);
-
-                trigger  = iosapic_intr_info[vector].trigger;
-                polarity = iosapic_intr_info[vector].polarity;
-                dest     = iosapic_intr_info[vector].dest;
-                printk(KERN_INFO
-                       "GSI %u (%s, %s) -> CPU %d (0x%04x)"
-                       " vector %d unregistered\n",
-                       gsi, (trigger == IOSAPIC_EDGE ? "edge" : "level"),
-                       (polarity == IOSAPIC_POL_HIGH ? "high" : "low"),
-                       cpu_logical_id(dest), dest, vector);
+        /* Mask the interrupt */
+        low32 = iosapic_intr_info[irq].low32 | IOSAPIC_MASK;
+        iosapic_write(rte->iosapic, IOSAPIC_RTE_LOW(rte->rte_index), low32);
 
-                if (list_empty(&iosapic_intr_info[vector].rtes)) {
-                        /* Sanity check */
-                        BUG_ON(iosapic_intr_info[vector].count);
+        iosapic_intr_info[irq].count--;
+        index = find_iosapic(gsi);
+        iosapic_lists[index].rtes_inuse--;
+        WARN_ON(iosapic_lists[index].rtes_inuse < 0);
 
-                        /* Clear the interrupt controller descriptor */
-                        idesc->chip = &no_irq_type;
+        trigger  = iosapic_intr_info[irq].trigger;
+        polarity = iosapic_intr_info[irq].polarity;
+        dest     = iosapic_intr_info[irq].dest;
+        printk(KERN_INFO
+               "GSI %u (%s, %s) -> CPU %d (0x%04x) vector %d unregistered\n",
+               gsi, (trigger == IOSAPIC_EDGE ? "edge" : "level"),
+               (polarity == IOSAPIC_POL_HIGH ? "high" : "low"),
+               cpu_logical_id(dest), dest, irq_to_vector(irq));
 
+        if (iosapic_intr_info[irq].count == 0) {
 #ifdef CONFIG_SMP
-                        /* Clear affinity */
-                        cpus_setall(idesc->affinity);
+                /* Clear affinity */
+                cpus_setall(idesc->affinity);
 #endif
-
-                        /* Clear the interrupt information */
-                        memset(&iosapic_intr_info[vector], 0,
-                               sizeof(struct iosapic_intr_info));
-                        iosapic_intr_info[vector].low32 |= IOSAPIC_MASK;
-                        INIT_LIST_HEAD(&iosapic_intr_info[vector].rtes);
-
-                        if (idesc->action) {
-                                printk(KERN_ERR
-                                       "interrupt handlers still exist on"
-                                       "IRQ %u\n", irq);
-                                WARN_ON(1);
-                        }
-
-                        /* Free the interrupt vector */
-                        free_irq_vector(vector);
-                }
+                /* Clear the interrupt information */
+                iosapic_intr_info[irq].dest = 0;
+                iosapic_intr_info[irq].dmode = 0;
+                iosapic_intr_info[irq].polarity = 0;
+                iosapic_intr_info[irq].trigger = 0;
+                iosapic_intr_info[irq].low32 |= IOSAPIC_MASK;
+
+                /* Destroy and reserve IRQ */
+                destroy_and_reserve_irq(irq);
         }
  out:
-        spin_unlock(&iosapic_lock);
-        spin_unlock_irqrestore(&idesc->lock, flags);
+        spin_unlock_irqrestore(&iosapic_lock, flags);
 }
 
 /*
@@ -965,27 +903,30 @@ iosapic_register_platform_intr (u32 int_type, unsigned int gsi,
 {
         static const char * const name[] = {"unknown", "PMI", "INIT", "CPEI"};
         unsigned char delivery;
-        int vector, mask = 0;
+        int irq, vector, mask = 0;
         unsigned int dest = ((id << 8) | eid) & 0xffff;
 
         switch (int_type) {
               case ACPI_INTERRUPT_PMI:
-                vector = iosapic_vector;
+                irq = vector = iosapic_vector;
+                bind_irq_vector(irq, vector, CPU_MASK_ALL);
                 /*
                  * since PMI vector is alloc'd by FW(ACPI) not by kernel,
                  * we need to make sure the vector is available
                  */
-                iosapic_reassign_vector(vector);
+                iosapic_reassign_vector(irq);
                 delivery = IOSAPIC_PMI;
                 break;
               case ACPI_INTERRUPT_INIT:
-                vector = assign_irq_vector(AUTO_ASSIGN);
-                if (vector < 0)
+                irq = create_irq();
+                if (irq < 0)
                         panic("%s: out of interrupt vectors!\n", __FUNCTION__);
+                vector = irq_to_vector(irq);
                 delivery = IOSAPIC_INIT;
                 break;
               case ACPI_INTERRUPT_CPEI:
-                vector = IA64_CPE_VECTOR;
+                irq = vector = IA64_CPE_VECTOR;
+                BUG_ON(bind_irq_vector(irq, vector, CPU_MASK_ALL));
                 delivery = IOSAPIC_LOWEST_PRIORITY;
                 mask = 1;
                 break;
@@ -995,7 +936,7 @@ iosapic_register_platform_intr (u32 int_type, unsigned int gsi,
                 return -1;
         }
 
-        register_intr(gsi, vector, delivery, polarity, trigger);
+        register_intr(gsi, irq, delivery, polarity, trigger);
 
         printk(KERN_INFO
                "PLATFORM int %s (0x%x): GSI %u (%s, %s) -> CPU %d (0x%04x)"
@@ -1005,7 +946,7 @@ iosapic_register_platform_intr (u32 int_type, unsigned int gsi,
                (polarity == IOSAPIC_POL_HIGH ? "high" : "low"),
                cpu_logical_id(dest), dest, vector);
 
-        set_rte(gsi, vector, dest, mask);
+        set_rte(gsi, irq, dest, mask);
         return vector;
 }
 
@@ -1017,30 +958,32 @@ iosapic_override_isa_irq (unsigned int isa_irq, unsigned int gsi,
                           unsigned long polarity,
                           unsigned long trigger)
 {
-        int vector;
+        int vector, irq;
         unsigned int dest = cpu_physical_id(smp_processor_id());
 
-        vector = isa_irq_to_vector(isa_irq);
-
-        register_intr(gsi, vector, IOSAPIC_LOWEST_PRIORITY, polarity, trigger);
+        irq = vector = isa_irq_to_vector(isa_irq);
+        BUG_ON(bind_irq_vector(irq, vector, CPU_MASK_ALL));
+        register_intr(gsi, irq, IOSAPIC_LOWEST_PRIORITY, polarity, trigger);
 
         DBG("ISA: IRQ %u -> GSI %u (%s,%s) -> CPU %d (0x%04x) vector %d\n",
             isa_irq, gsi, trigger == IOSAPIC_EDGE ? "edge" : "level",
             polarity == IOSAPIC_POL_HIGH ? "high" : "low",
             cpu_logical_id(dest), dest, vector);
 
-        set_rte(gsi, vector, dest, 1);
+        set_rte(gsi, irq, dest, 1);
 }
 
 void __init
 iosapic_system_init (int system_pcat_compat)
 {
-        int vector;
+        int irq;
 
-        for (vector = 0; vector < IA64_NUM_VECTORS; ++vector) {
-                iosapic_intr_info[vector].low32 = IOSAPIC_MASK;
+        for (irq = 0; irq < NR_IRQS; ++irq) {
+                iosapic_intr_info[irq].low32 = IOSAPIC_MASK;
                 /* mark as unused */
-                INIT_LIST_HEAD(&iosapic_intr_info[vector].rtes);
+                INIT_LIST_HEAD(&iosapic_intr_info[irq].rtes);
+
+                iosapic_intr_info[irq].count = 0;
         }
 
         pcat_compat = system_pcat_compat;
@@ -1108,31 +1051,35 @@ iosapic_init (unsigned long phys_addr, unsigned int gsi_base)
         unsigned long flags;
 
         spin_lock_irqsave(&iosapic_lock, flags);
-        {
-                addr = ioremap(phys_addr, 0);
-                ver = iosapic_version(addr);
+        index = find_iosapic(gsi_base);
+        if (index >= 0) {
+                spin_unlock_irqrestore(&iosapic_lock, flags);
+                return -EBUSY;
+        }
 
-                if ((err = iosapic_check_gsi_range(gsi_base, ver))) {
-                        iounmap(addr);
-                        spin_unlock_irqrestore(&iosapic_lock, flags);
-                        return err;
-                }
+        addr = ioremap(phys_addr, 0);
+        ver = iosapic_version(addr);
+        if ((err = iosapic_check_gsi_range(gsi_base, ver))) {
+                iounmap(addr);
+                spin_unlock_irqrestore(&iosapic_lock, flags);
+                return err;
+        }
 
-                /*
-                 * The MAX_REDIR register holds the highest input pin
-                 * number (starting from 0).
-                 * We add 1 so that we can use it for number of pins (= RTEs)
-                 */
-                num_rte = ((ver >> 16) & 0xff) + 1;
+        /*
+         * The MAX_REDIR register holds the highest input pin number
+         * (starting from 0).  We add 1 so that we can use it for
+         * number of pins (= RTEs)
+         */
+        num_rte = ((ver >> 16) & 0xff) + 1;
 
-                index = iosapic_alloc();
-                iosapic_lists[index].addr = addr;
-                iosapic_lists[index].gsi_base = gsi_base;
-                iosapic_lists[index].num_rte = num_rte;
+        index = iosapic_alloc();
+        iosapic_lists[index].addr = addr;
+        iosapic_lists[index].gsi_base = gsi_base;
+        iosapic_lists[index].num_rte = num_rte;
 #ifdef CONFIG_NUMA
-                iosapic_lists[index].node = MAX_NUMNODES;
+        iosapic_lists[index].node = MAX_NUMNODES;
 #endif
-        }
+        spin_lock_init(&iosapic_lists[index].lock);
         spin_unlock_irqrestore(&iosapic_lock, flags);
 
         if ((gsi_base == 0) && pcat_compat) {
@@ -1157,25 +1104,22 @@ iosapic_remove (unsigned int gsi_base)
         unsigned long flags;
 
         spin_lock_irqsave(&iosapic_lock, flags);
-        {
-                index = find_iosapic(gsi_base);
-                if (index < 0) {
-                        printk(KERN_WARNING "%s: No IOSAPIC for GSI base %u\n",
-                               __FUNCTION__, gsi_base);
-                        goto out;
-                }
-
-                if (iosapic_lists[index].rtes_inuse) {
-                        err = -EBUSY;
-                        printk(KERN_WARNING
-                               "%s: IOSAPIC for GSI base %u is busy\n",
-                               __FUNCTION__, gsi_base);
-                        goto out;
-                }
+        index = find_iosapic(gsi_base);
+        if (index < 0) {
+                printk(KERN_WARNING "%s: No IOSAPIC for GSI base %u\n",
+                       __FUNCTION__, gsi_base);
+                goto out;
+        }
 
-                iounmap(iosapic_lists[index].addr);
-                iosapic_free(index);
+        if (iosapic_lists[index].rtes_inuse) {
+                err = -EBUSY;
+                printk(KERN_WARNING "%s: IOSAPIC for GSI base %u is busy\n",
+                       __FUNCTION__, gsi_base);
+                goto out;
         }
+
+        iounmap(iosapic_lists[index].addr);
+        iosapic_free(index);
  out:
         spin_unlock_irqrestore(&iosapic_lock, flags);
         return err;
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index 407b45870489..cc3ee4ef37af 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -35,7 +35,7 @@ void ack_bad_irq(unsigned int irq)
 #ifdef CONFIG_IA64_GENERIC
 unsigned int __ia64_local_vector_to_irq (ia64_vector vec)
 {
-        return (unsigned int) vec;
+        return __get_cpu_var(vector_irq)[vec];
 }
 #endif
 
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index bc47049f060f..91797c111162 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -46,6 +46,12 @@
 
 #define IRQ_DEBUG       0
 
+#define IRQ_VECTOR_UNASSIGNED   (0)
+
+#define IRQ_UNUSED              (0)
+#define IRQ_USED                (1)
+#define IRQ_RSVD                (2)
+
 /* These can be overridden in platform_irq_init */
 int ia64_first_device_vector = IA64_DEF_FIRST_DEVICE_VECTOR;
 int ia64_last_device_vector = IA64_DEF_LAST_DEVICE_VECTOR;
@@ -54,6 +60,8 @@ int ia64_last_device_vector = IA64_DEF_LAST_DEVICE_VECTOR;
 void __iomem *ipi_base_addr = ((void __iomem *)
                                (__IA64_UNCACHED_OFFSET | IA64_IPI_DEFAULT_BASE_ADDR));
 
+static cpumask_t vector_allocation_domain(int cpu);
+
 /*
  * Legacy IRQ to IA-64 vector translation table.
  */
@@ -64,46 +72,269 @@ __u8 isa_irq_to_vector_map[16] = {
 };
 EXPORT_SYMBOL(isa_irq_to_vector_map);
 
-static unsigned long ia64_vector_mask[BITS_TO_LONGS(IA64_MAX_DEVICE_VECTORS)];
+DEFINE_SPINLOCK(vector_lock);
+
+struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
+        [0 ... NR_IRQS - 1] = {
+                .vector = IRQ_VECTOR_UNASSIGNED,
+                .domain = CPU_MASK_NONE
+        }
+};
+
+DEFINE_PER_CPU(int[IA64_NUM_VECTORS], vector_irq) = {
+        [0 ... IA64_NUM_VECTORS - 1] = IA64_SPURIOUS_INT_VECTOR
+};
+
+static cpumask_t vector_table[IA64_MAX_DEVICE_VECTORS] = {
+        [0 ... IA64_MAX_DEVICE_VECTORS - 1] = CPU_MASK_NONE
+};
+
+static int irq_status[NR_IRQS] = {
+        [0 ... NR_IRQS -1] = IRQ_UNUSED
+};
+
+int check_irq_used(int irq)
+{
+        if (irq_status[irq] == IRQ_USED)
+                return 1;
+
+        return -1;
+}
+
+static void reserve_irq(unsigned int irq)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&vector_lock, flags);
+        irq_status[irq] = IRQ_RSVD;
+        spin_unlock_irqrestore(&vector_lock, flags);
+}
+
+static inline int find_unassigned_irq(void)
+{
+        int irq;
+
+        for (irq = IA64_FIRST_DEVICE_VECTOR; irq < NR_IRQS; irq++)
+                if (irq_status[irq] == IRQ_UNUSED)
+                        return irq;
+        return -ENOSPC;
+}
+
+static inline int find_unassigned_vector(cpumask_t domain)
+{
+        cpumask_t mask;
+        int pos;
+
+        cpus_and(mask, domain, cpu_online_map);
+        if (cpus_empty(mask))
+                return -EINVAL;
+
+        for (pos = 0; pos < IA64_NUM_DEVICE_VECTORS; pos++) {
+                cpus_and(mask, domain, vector_table[pos]);
+                if (!cpus_empty(mask))
+                        continue;
+                return IA64_FIRST_DEVICE_VECTOR + pos;
+        }
+        return -ENOSPC;
+}
+
+static int __bind_irq_vector(int irq, int vector, cpumask_t domain)
+{
+        cpumask_t mask;
+        int cpu, pos;
+        struct irq_cfg *cfg = &irq_cfg[irq];
+
+        cpus_and(mask, domain, cpu_online_map);
+        if (cpus_empty(mask))
+                return -EINVAL;
+        if ((cfg->vector == vector) && cpus_equal(cfg->domain, domain))
+                return 0;
+        if (cfg->vector != IRQ_VECTOR_UNASSIGNED)
+                return -EBUSY;
+        for_each_cpu_mask(cpu, mask)
+                per_cpu(vector_irq, cpu)[vector] = irq;
+        cfg->vector = vector;
+        cfg->domain = domain;
+        irq_status[irq] = IRQ_USED;
+        pos = vector - IA64_FIRST_DEVICE_VECTOR;
+        cpus_or(vector_table[pos], vector_table[pos], domain);
+        return 0;
+}
+
+int bind_irq_vector(int irq, int vector, cpumask_t domain)
+{
+        unsigned long flags;
+        int ret;
+
+        spin_lock_irqsave(&vector_lock, flags);
+        ret = __bind_irq_vector(irq, vector, domain);
+        spin_unlock_irqrestore(&vector_lock, flags);
+        return ret;
+}
+
+static void __clear_irq_vector(int irq)
+{
+        int vector, cpu, pos;
+        cpumask_t mask;
+        cpumask_t domain;
+        struct irq_cfg *cfg = &irq_cfg[irq];
+
+        BUG_ON((unsigned)irq >= NR_IRQS);
+        BUG_ON(cfg->vector == IRQ_VECTOR_UNASSIGNED);
+        vector = cfg->vector;
+        domain = cfg->domain;
+        cpus_and(mask, cfg->domain, cpu_online_map);
+        for_each_cpu_mask(cpu, mask)
+                per_cpu(vector_irq, cpu)[vector] = IA64_SPURIOUS_INT_VECTOR;
+        cfg->vector = IRQ_VECTOR_UNASSIGNED;
+        cfg->domain = CPU_MASK_NONE;
+        irq_status[irq] = IRQ_UNUSED;
+        pos = vector - IA64_FIRST_DEVICE_VECTOR;
+        cpus_andnot(vector_table[pos], vector_table[pos], domain);
+}
+
+static void clear_irq_vector(int irq)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&vector_lock, flags);
+        __clear_irq_vector(irq);
+        spin_unlock_irqrestore(&vector_lock, flags);
+}
 
 int
 assign_irq_vector (int irq)
 {
-        int pos, vector;
- again:
-        pos = find_first_zero_bit(ia64_vector_mask, IA64_NUM_DEVICE_VECTORS);
-        vector = IA64_FIRST_DEVICE_VECTOR + pos;
-        if (vector > IA64_LAST_DEVICE_VECTOR)
-                return -ENOSPC;
-        if (test_and_set_bit(pos, ia64_vector_mask))
-                goto again;
+        unsigned long flags;
+        int vector, cpu;
+        cpumask_t domain;
+
+        vector = -ENOSPC;
+
+        spin_lock_irqsave(&vector_lock, flags);
+        if (irq < 0) {
+                goto out;
+        }
+        for_each_online_cpu(cpu) {
+                domain = vector_allocation_domain(cpu);
+                vector = find_unassigned_vector(domain);
+                if (vector >= 0)
+                        break;
+        }
+        if (vector < 0)
+                goto out;
+        BUG_ON(__bind_irq_vector(irq, vector, domain));
+ out:
+        spin_unlock_irqrestore(&vector_lock, flags);
         return vector;
 }
 
 void
 free_irq_vector (int vector)
 {
-        int pos;
-
-        if (vector < IA64_FIRST_DEVICE_VECTOR || vector > IA64_LAST_DEVICE_VECTOR)
+        if (vector < IA64_FIRST_DEVICE_VECTOR ||
+            vector > IA64_LAST_DEVICE_VECTOR)
                 return;
-
-        pos = vector - IA64_FIRST_DEVICE_VECTOR;
-        if (!test_and_clear_bit(pos, ia64_vector_mask))
-                printk(KERN_WARNING "%s: double free!\n", __FUNCTION__);
+        clear_irq_vector(vector);
 }
 
 int
 reserve_irq_vector (int vector)
 {
-        int pos;
-
         if (vector < IA64_FIRST_DEVICE_VECTOR ||
             vector > IA64_LAST_DEVICE_VECTOR)
                 return -EINVAL;
+        return !!bind_irq_vector(vector, vector, CPU_MASK_ALL);
+}
 
-        pos = vector - IA64_FIRST_DEVICE_VECTOR;
-        return test_and_set_bit(pos, ia64_vector_mask);
+/*
+ * Initialize vector_irq on a new cpu. This function must be called
+ * with vector_lock held.
+ */
+void __setup_vector_irq(int cpu)
+{
+        int irq, vector;
+
+        /* Clear vector_irq */
+        for (vector = 0; vector < IA64_NUM_VECTORS; ++vector)
+                per_cpu(vector_irq, cpu)[vector] = IA64_SPURIOUS_INT_VECTOR;
+        /* Mark the inuse vectors */
+        for (irq = 0; irq < NR_IRQS; ++irq) {
+                if (!cpu_isset(cpu, irq_cfg[irq].domain))
+                        continue;
+                vector = irq_to_vector(irq);
+                per_cpu(vector_irq, cpu)[vector] = irq;
+        }
+}
+
+#if defined(CONFIG_SMP) && (defined(CONFIG_IA64_GENERIC) || defined(CONFIG_IA64_DIG))
+static enum vector_domain_type {
+        VECTOR_DOMAIN_NONE,
+        VECTOR_DOMAIN_PERCPU
+} vector_domain_type = VECTOR_DOMAIN_NONE;
+
+static cpumask_t vector_allocation_domain(int cpu)
+{
+        if (vector_domain_type == VECTOR_DOMAIN_PERCPU)
+                return cpumask_of_cpu(cpu);
+        return CPU_MASK_ALL;
+}
+
+static int __init parse_vector_domain(char *arg)
+{
+        if (!arg)
+                return -EINVAL;
+        if (!strcmp(arg, "percpu")) {
+                vector_domain_type = VECTOR_DOMAIN_PERCPU;
+                no_int_routing = 1;
+        }
+        return 1;
+}
+early_param("vector", parse_vector_domain);
+#else
+static cpumask_t vector_allocation_domain(int cpu)
+{
+        return CPU_MASK_ALL;
+}
+#endif
+
+
+void destroy_and_reserve_irq(unsigned int irq)
+{
+        dynamic_irq_cleanup(irq);
+
+        clear_irq_vector(irq);
+        reserve_irq(irq);
+}
+
+static int __reassign_irq_vector(int irq, int cpu)
+{
+        struct irq_cfg *cfg = &irq_cfg[irq];
+        int vector;
+        cpumask_t domain;
+
+        if (cfg->vector == IRQ_VECTOR_UNASSIGNED || !cpu_online(cpu))
+                return -EINVAL;
+        if (cpu_isset(cpu, cfg->domain))
+                return 0;
+        domain = vector_allocation_domain(cpu);
+        vector = find_unassigned_vector(domain);
+        if (vector < 0)
+                return -ENOSPC;
+        __clear_irq_vector(irq);
+        BUG_ON(__bind_irq_vector(irq, vector, domain));
+        return 0;
+}
+
+int reassign_irq_vector(int irq, int cpu)
+{
+        unsigned long flags;
+        int ret;
+
+        spin_lock_irqsave(&vector_lock, flags);
+        ret = __reassign_irq_vector(irq, cpu);
+        spin_unlock_irqrestore(&vector_lock, flags);
+        return ret;
 }
 
 /*
@@ -111,18 +342,35 @@ reserve_irq_vector (int vector)
  */
 int create_irq(void)
 {
-        int vector = assign_irq_vector(AUTO_ASSIGN);
-
-        if (vector >= 0)
-                dynamic_irq_init(vector);
-
-        return vector;
+        unsigned long flags;
+        int irq, vector, cpu;
+        cpumask_t domain;
+
+        irq = vector = -ENOSPC;
+        spin_lock_irqsave(&vector_lock, flags);
+        for_each_online_cpu(cpu) {
+                domain = vector_allocation_domain(cpu);
+                vector = find_unassigned_vector(domain);
+                if (vector >= 0)
+                        break;
+        }
+        if (vector < 0)
+                goto out;
+        irq = find_unassigned_irq();
+        if (irq < 0)
+                goto out;
+        BUG_ON(__bind_irq_vector(irq, vector, domain));
+ out:
+        spin_unlock_irqrestore(&vector_lock, flags);
+        if (irq >= 0)
+                dynamic_irq_init(irq);
+        return irq;
 }
 
 void destroy_irq(unsigned int irq)
 {
         dynamic_irq_cleanup(irq);
-        free_irq_vector(irq);
+        clear_irq_vector(irq);
 }
 
 #ifdef CONFIG_SMP
@@ -301,14 +549,13 @@ register_percpu_irq (ia64_vector vec, struct irqaction *action)
         irq_desc_t *desc;
         unsigned int irq;
 
-        for (irq = 0; irq < NR_IRQS; ++irq)
-                if (irq_to_vector(irq) == vec) {
-                        desc = irq_desc + irq;
-                        desc->status |= IRQ_PER_CPU;
-                        desc->chip = &irq_type_ia64_lsapic;
-                        if (action)
-                                setup_irq(irq, action);
-                }
+        irq = vec;
+        BUG_ON(bind_irq_vector(irq, vec, CPU_MASK_ALL));
+        desc = irq_desc + irq;
+        desc->status |= IRQ_PER_CPU;
+        desc->chip = &irq_type_ia64_lsapic;
+        if (action)
+                setup_irq(irq, action);
 }
 
 void __init
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index c81080df70df..2fdbd5c3f213 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -13,6 +13,7 @@
 
 #define MSI_DATA_VECTOR_SHIFT           0
 #define     MSI_DATA_VECTOR(v)          (((u8)v) << MSI_DATA_VECTOR_SHIFT)
+#define MSI_DATA_VECTOR_MASK            0xffffff00
 
 #define MSI_DATA_DELIVERY_SHIFT         8
 #define     MSI_DATA_DELIVERY_FIXED     (0 << MSI_DATA_DELIVERY_SHIFT)
@@ -50,17 +51,29 @@ static struct irq_chip	ia64_msi_chip;
 static void ia64_set_msi_irq_affinity(unsigned int irq, cpumask_t cpu_mask)
 {
         struct msi_msg msg;
-        u32 addr;
+        u32 addr, data;
+        int cpu = first_cpu(cpu_mask);
+
+        if (!cpu_online(cpu))
+                return;
+
+        if (reassign_irq_vector(irq, cpu))
+                return;
 
         read_msi_msg(irq, &msg);
 
         addr = msg.address_lo;
         addr &= MSI_ADDR_DESTID_MASK;
-        addr |= MSI_ADDR_DESTID_CPU(cpu_physical_id(first_cpu(cpu_mask)));
+        addr |= MSI_ADDR_DESTID_CPU(cpu_physical_id(cpu));
         msg.address_lo = addr;
 
+        data = msg.data;
+        data &= MSI_DATA_VECTOR_MASK;
+        data |= MSI_DATA_VECTOR(irq_to_vector(irq));
+        msg.data = data;
+
         write_msi_msg(irq, &msg);
-        irq_desc[irq].affinity = cpu_mask;
+        irq_desc[irq].affinity = cpumask_of_cpu(cpu);
 }
 #endif /* CONFIG_SMP */
 
@@ -69,13 +82,15 @@ int ia64_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)
         struct msi_msg  msg;
         unsigned long   dest_phys_id;
         int     irq, vector;
+        cpumask_t mask;
 
         irq = create_irq();
         if (irq < 0)
                 return irq;
 
         set_irq_msi(irq, desc);
-        dest_phys_id = cpu_physical_id(first_cpu(cpu_online_map));
+        cpus_and(mask, irq_to_domain(irq), cpu_online_map);
+        dest_phys_id = cpu_physical_id(first_cpu(mask));
         vector = irq_to_vector(irq);
 
         msg.address_hi = 0;
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 3c9d8e6089cf..9f5c90b594b9 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -395,9 +395,13 @@ smp_callin (void)
         fix_b0_for_bsp();
 
         lock_ipi_calllock();
+        spin_lock(&vector_lock);
+        /* Setup the per cpu irq handling data structures */
+        __setup_vector_irq(cpuid);
         cpu_set(cpuid, cpu_online_map);
         unlock_ipi_calllock();
         per_cpu(cpu_state, cpuid) = CPU_ONLINE;
+        spin_unlock(&vector_lock);
 
         smp_setup_percpu_timer();
 
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 3486fe7d6e65..627785c48ea9 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -19,6 +19,7 @@
 #include <linux/interrupt.h>
 #include <linux/efi.h>
 #include <linux/timex.h>
+#include <linux/clocksource.h>
 
 #include <asm/machvec.h>
 #include <asm/delay.h>
@@ -28,6 +29,16 @@
 #include <asm/sections.h>
 #include <asm/system.h>
 
+#include "fsyscall_gtod_data.h"
+
+static cycle_t itc_get_cycles(void);
+
+struct fsyscall_gtod_data_t fsyscall_gtod_data = {
+        .lock = SEQLOCK_UNLOCKED,
+};
+
+struct itc_jitter_data_t itc_jitter_data;
+
 volatile int time_keeper_id = 0; /* smp_processor_id() of time-keeper */
 
 #ifdef CONFIG_IA64_DEBUG_IRQ
@@ -37,11 +48,16 @@ EXPORT_SYMBOL(last_cli_ip);
 
 #endif
 
-static struct time_interpolator itc_interpolator = {
-        .shift = 16,
-        .mask = 0xffffffffffffffffLL,
-        .source = TIME_SOURCE_CPU
+static struct clocksource clocksource_itc = {
+        .name           = "itc",
+        .rating         = 350,
+        .read           = itc_get_cycles,
+        .mask           = 0xffffffffffffffff,
+        .mult           = 0, /*to be caluclated*/
+        .shift          = 16,
+        .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 };
+static struct clocksource *itc_clocksource;
 
 static irqreturn_t
 timer_interrupt (int irq, void *dev_id)
@@ -210,8 +226,6 @@ ia64_init_itm (void)
                                         + itc_freq/2)/itc_freq;
 
         if (!(sal_platform_features & IA64_SAL_PLATFORM_FEATURE_ITC_DRIFT)) {
-                itc_interpolator.frequency = local_cpu_data->itc_freq;
-                itc_interpolator.drift = itc_drift;
 #ifdef CONFIG_SMP
                 /* On IA64 in an SMP configuration ITCs are never accurately synchronized.
                  * Jitter compensation requires a cmpxchg which may limit
@@ -223,15 +237,50 @@ ia64_init_itm (void)
                  * even going backward) if the ITC offsets between the individual CPUs
                  * are too large.
                  */
-                if (!nojitter) itc_interpolator.jitter = 1;
+                if (!nojitter)
+                        itc_jitter_data.itc_jitter = 1;
 #endif
-                register_time_interpolator(&itc_interpolator);
         }
 
         /* Setup the CPU local timer tick */
         ia64_cpu_local_tick();
+
+        if (!itc_clocksource) {
+                /* Sort out mult/shift values: */
+                clocksource_itc.mult =
+                        clocksource_hz2mult(local_cpu_data->itc_freq,
+                                                clocksource_itc.shift);
+                clocksource_register(&clocksource_itc);
+                itc_clocksource = &clocksource_itc;
+        }
 }
 
+static cycle_t itc_get_cycles()
+{
+        u64 lcycle, now, ret;
+
+        if (!itc_jitter_data.itc_jitter)
+                return get_cycles();
+
+        lcycle = itc_jitter_data.itc_lastcycle;
+        now = get_cycles();
+        if (lcycle && time_after(lcycle, now))
+                return lcycle;
+
+        /*
+         * Keep track of the last timer value returned.
+         * In an SMP environment, you could lose out in contention of
+         * cmpxchg. If so, your cmpxchg returns new value which the
+         * winner of contention updated to. Use the new value instead.
+         */
+        ret = cmpxchg(&itc_jitter_data.itc_lastcycle, lcycle, now);
+        if (unlikely(ret != lcycle))
+                return ret;
+
+        return now;
+}
+
+
 static struct irqaction timer_irqaction = {
         .handler =      timer_interrupt,
         .flags =        IRQF_DISABLED | IRQF_IRQPOLL,
@@ -307,3 +356,34 @@ ia64_setup_printk_clock(void)
         if (!(sal_platform_features & IA64_SAL_PLATFORM_FEATURE_ITC_DRIFT))
                 ia64_printk_clock = ia64_itc_printk_clock;
 }
+
+void update_vsyscall(struct timespec *wall, struct clocksource *c)
+{
+        unsigned long flags;
+
+        write_seqlock_irqsave(&fsyscall_gtod_data.lock, flags);
+
+        /* copy fsyscall clock data */
+        fsyscall_gtod_data.clk_mask = c->mask;
+        fsyscall_gtod_data.clk_mult = c->mult;
+        fsyscall_gtod_data.clk_shift = c->shift;
+        fsyscall_gtod_data.clk_fsys_mmio = c->fsys_mmio;
+        fsyscall_gtod_data.clk_cycle_last = c->cycle_last;
+
+        /* copy kernel time structures */
+        fsyscall_gtod_data.wall_time.tv_sec = wall->tv_sec;
+        fsyscall_gtod_data.wall_time.tv_nsec = wall->tv_nsec;
+        fsyscall_gtod_data.monotonic_time.tv_sec = wall_to_monotonic.tv_sec
+                                                        + wall->tv_sec;
+        fsyscall_gtod_data.monotonic_time.tv_nsec = wall_to_monotonic.tv_nsec
+                                                        + wall->tv_nsec;
+
+        /* normalize */
+        while (fsyscall_gtod_data.monotonic_time.tv_nsec >= NSEC_PER_SEC) {
+                fsyscall_gtod_data.monotonic_time.tv_nsec -= NSEC_PER_SEC;
+                fsyscall_gtod_data.monotonic_time.tv_sec++;
+        }
+
+        write_sequnlock_irqrestore(&fsyscall_gtod_data.lock, flags);
+}
+
diff --git a/arch/ia64/sn/kernel/sn2/timer.c b/arch/ia64/sn/kernel/sn2/timer.c
index 56a88b6df4b4..19e25d2b64fc 100644
--- a/arch/ia64/sn/kernel/sn2/timer.c
+++ b/arch/ia64/sn/kernel/sn2/timer.c
@@ -11,6 +11,7 @@
 #include <linux/sched.h>
 #include <linux/time.h>
 #include <linux/interrupt.h>
+#include <linux/clocksource.h>
 
 #include <asm/hw_irq.h>
 #include <asm/system.h>
@@ -22,11 +23,21 @@
 
 extern unsigned long sn_rtc_cycles_per_second;
 
-static struct time_interpolator sn2_interpolator = {
-        .drift = -1,
-        .shift = 10,
-        .mask = (1LL << 55) - 1,
-        .source = TIME_SOURCE_MMIO64
+static void __iomem *sn2_mc;
+
+static cycle_t read_sn2(void)
+{
+        return (cycle_t)readq(sn2_mc);
+}
+
+static struct clocksource clocksource_sn2 = {
+        .name           = "sn2_rtc",
+        .rating         = 300,
+        .read           = read_sn2,
+        .mask           = (1LL << 55) - 1,
+        .mult           = 0,
+        .shift          = 10,
+        .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 /*
@@ -47,9 +58,11 @@ ia64_sn_udelay (unsigned long usecs)
 
 void __init sn_timer_init(void)
 {
-        sn2_interpolator.frequency = sn_rtc_cycles_per_second;
-        sn2_interpolator.addr = RTC_COUNTER_ADDR;
-        register_time_interpolator(&sn2_interpolator);
+        sn2_mc = RTC_COUNTER_ADDR;
+        clocksource_sn2.fsys_mmio = RTC_COUNTER_ADDR;
+        clocksource_sn2.mult = clocksource_hz2mult(sn_rtc_cycles_per_second,
+                                                        clocksource_sn2.shift);
+        clocksource_register(&clocksource_sn2);
 
         ia64_udelay = &ia64_sn_udelay;
 }
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index a86e2e9a639f..20a9c08e59c3 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -37,6 +37,10 @@ config TIME_LOW_RES
         bool
         default y
 
+config GENERIC_IOMAP
+        bool
+        default y
+
 config ARCH_MAY_HAVE_PC_FDC
         bool
         depends on Q40 || (BROKEN && SUN3X)
@@ -45,6 +49,9 @@ config ARCH_MAY_HAVE_PC_FDC
 config NO_IOPORT
         def_bool y
 
+config NO_DMA
+        def_bool SUN3
+
 mainmenu "Linux/68k Kernel Configuration"
 
 source "init/Kconfig"
diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c
index cb8e7609df4c..78df98f2029a 100644
--- a/arch/m68k/apollo/config.c
+++ b/arch/m68k/apollo/config.c
@@ -148,8 +148,8 @@ void dn_serial_print (const char *str)
     }
 }
 
-void config_apollo(void) {
-
+void __init config_apollo(void)
+{
         int i;
 
         dn_setup_model();
diff --git a/arch/m68k/apollo/dn_ints.c b/arch/m68k/apollo/dn_ints.c
index 13bd41bed28e..5d47f3aa3810 100644
--- a/arch/m68k/apollo/dn_ints.c
+++ b/arch/m68k/apollo/dn_ints.c
@@ -37,7 +37,7 @@ static struct irq_controller apollo_irq_controller = {
 };
 
 
-void dn_init_IRQ(void)
+void __init dn_init_IRQ(void)
 {
         m68k_setup_user_interrupt(VEC_USER + 96, 16, dn_process_int);
         m68k_setup_irq_controller(&apollo_irq_controller, IRQ_APOLLO, 16);
diff --git a/arch/m68k/atari/atakeyb.c b/arch/m68k/atari/atakeyb.c
index 1c29603b16b3..2b5f64726a2e 100644
--- a/arch/m68k/atari/atakeyb.c
+++ b/arch/m68k/atari/atakeyb.c
@@ -13,6 +13,7 @@
  * enhanced by Bjoern Brauel and Roman Hodek
  */
 
+#include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
@@ -42,6 +43,9 @@ void (*atari_mouse_interrupt_hook) (char *);
 void (*atari_input_keyboard_interrupt_hook) (unsigned char, char);
 /* Hook for mouse inputdev  driver */
 void (*atari_input_mouse_interrupt_hook) (char *);
+EXPORT_SYMBOL(atari_mouse_interrupt_hook);
+EXPORT_SYMBOL(atari_input_keyboard_interrupt_hook);
+EXPORT_SYMBOL(atari_input_mouse_interrupt_hook);
 
 /* variables for IKBD self test: */
 
@@ -429,6 +433,7 @@ void ikbd_mouse_rel_pos(void)
 
         ikbd_write(cmd, 1);
 }
+EXPORT_SYMBOL(ikbd_mouse_rel_pos);
 
 /* Set absolute mouse position reporting */
 void ikbd_mouse_abs_pos(int xmax, int ymax)
@@ -453,6 +458,7 @@ void ikbd_mouse_thresh(int x, int y)
 
         ikbd_write(cmd, 3);
 }
+EXPORT_SYMBOL(ikbd_mouse_thresh);
 
 /* Set mouse scale */
 void ikbd_mouse_scale(int x, int y)
@@ -495,6 +501,7 @@ void ikbd_mouse_y0_top(void)
 
         ikbd_write(cmd, 1);
 }
+EXPORT_SYMBOL(ikbd_mouse_y0_top);
 
 /* Resume */
 void ikbd_resume(void)
@@ -511,6 +518,7 @@ void ikbd_mouse_disable(void)
 
         ikbd_write(cmd, 1);
 }
+EXPORT_SYMBOL(ikbd_mouse_disable);
 
 /* Pause output */
 void ikbd_pause(void)
@@ -696,7 +704,6 @@ int __init atari_keyb_init(void)
         return 0;
 }
 
-
 int atari_kbdrate(struct kbd_repeat *k)
 {
         if (k->delay > 0) {
diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
index 896ae3d3d919..9433a88a33c4 100644
--- a/arch/m68k/bvme6000/config.c
+++ b/arch/m68k/bvme6000/config.c
@@ -97,7 +97,7 @@ static int bvme6000_get_hardware_list(char *buffer)
  * This function is called during kernel startup to initialize
  * the bvme6000 IRQ handling routines.
  */
-static void bvme6000_init_IRQ(void)
+static void __init bvme6000_init_IRQ(void)
 {
         m68k_setup_user_interrupt(VEC_USER, 192, NULL);
 }
diff --git a/arch/m68k/kernel/head.S b/arch/m68k/kernel/head.S
index 05741f233567..faa6764f1d13 100644
--- a/arch/m68k/kernel/head.S
+++ b/arch/m68k/kernel/head.S
@@ -577,7 +577,7 @@ func_define	putn,1
 #endif
 .endm
 
-.text
+.section ".text.head","ax"
 ENTRY(_stext)
 /*
  * Version numbers of the bootinfo interface
diff --git a/arch/m68k/kernel/setup.c b/arch/m68k/kernel/setup.c
index 215c7bd43924..7e6d5fb75390 100644
--- a/arch/m68k/kernel/setup.c
+++ b/arch/m68k/kernel/setup.c
@@ -58,6 +58,7 @@ extern int end;
 extern unsigned long availmem;
 
 int m68k_num_memory;
+EXPORT_SYMBOL(m68k_num_memory);
 int m68k_realnum_memory;
 EXPORT_SYMBOL(m68k_realnum_memory);
 unsigned long m68k_memoffset;
diff --git a/arch/m68k/kernel/sun3-head.S b/arch/m68k/kernel/sun3-head.S
index 4b5f050204e8..aad01592dbbc 100644
--- a/arch/m68k/kernel/sun3-head.S
+++ b/arch/m68k/kernel/sun3-head.S
@@ -29,7 +29,7 @@ kernel_pmd_table:              .skip 0x2000
 .globl kernel_pg_dir
 .equ    kernel_pg_dir,kernel_pmd_table
 
-        .section .head
+        .section .text.head
 ENTRY(_stext)
 ENTRY(_start)
 
diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c
index 4c065f9ceffc..7db41594d7b6 100644
--- a/arch/m68k/kernel/time.c
+++ b/arch/m68k/kernel/time.c
@@ -72,7 +72,7 @@ static irqreturn_t timer_interrupt(int irq, void *dummy)
         return IRQ_HANDLED;
 }
 
-void time_init(void)
+void __init time_init(void)
 {
         struct rtc_time time;
 
diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds
index 40f02b128f22..c42245775a4d 100644
--- a/arch/m68k/kernel/vmlinux-std.lds
+++ b/arch/m68k/kernel/vmlinux-std.lds
@@ -11,6 +11,7 @@ SECTIONS
   . = 0x1000;
   _text = .;                    /* Text and read-only data */
   .text : {
+        *(.text.head)
         TEXT_TEXT
         SCHED_TEXT
         LOCK_TEXT
diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds
index f06425b6d206..4adffefb5c48 100644
--- a/arch/m68k/kernel/vmlinux-sun3.lds
+++ b/arch/m68k/kernel/vmlinux-sun3.lds
@@ -11,7 +11,7 @@ SECTIONS
   . = 0xE002000;
   _text = .;                    /* Text and read-only data */
   .text : {
-        *(.head)
+        *(.text.head)
         TEXT_TEXT
         SCHED_TEXT
         LOCK_TEXT
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 5fd413246f89..8547dbc5e8d7 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -49,6 +49,7 @@ struct mac_booter_data mac_bi_data;
 int mac_bisize = sizeof mac_bi_data;
 
 struct mac_hw_present mac_hw_present;
+EXPORT_SYMBOL(mac_hw_present);
 
 /* New m68k bootinfo stuff and videobase */
 
@@ -84,7 +85,7 @@ extern void nubus_sweep_video(void);
 
 static void mac_get_model(char *str);
 
-static void mac_sched_init(irq_handler_t vector)
+static void __init mac_sched_init(irq_handler_t vector)
 {
         via_init_clock(vector);
 }
@@ -769,7 +770,7 @@ static struct mac_model mac_data_table[] = {
         }
 };
 
-void mac_identify(void)
+void __init mac_identify(void)
 {
         struct mac_model *m;
 
@@ -846,7 +847,7 @@ void mac_identify(void)
         baboon_init();
 }
 
-void mac_report_hardware(void)
+void __init mac_report_hardware(void)
 {
         printk(KERN_INFO "Apple Macintosh %s\n", macintosh_config->name);
 }
diff --git a/arch/m68k/mac/macints.c b/arch/m68k/mac/macints.c
index 0fc72d8f786e..ecddac4a02b9 100644
--- a/arch/m68k/mac/macints.c
+++ b/arch/m68k/mac/macints.c
@@ -114,6 +114,7 @@
  *
  */
 
+#include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
@@ -224,7 +225,7 @@ static struct irq_controller mac_irq_controller = {
         .disable        = mac_disable_irq,
 };
 
-void mac_init_IRQ(void)
+void __init mac_init_IRQ(void)
 {
 #ifdef DEBUG_MACINTS
         printk("mac_init_IRQ(): Setting things up...\n");
@@ -391,6 +392,7 @@ int mac_irq_pending(unsigned int irq)
         }
         return 0;
 }
+EXPORT_SYMBOL(mac_irq_pending);
 
 static int num_debug[8];
 
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index f1de19e1dde6..f42caa79e4e8 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -44,7 +44,7 @@ pg_data_t *pg_data_table[65];
 EXPORT_SYMBOL(pg_data_table);
 #endif
 
-void m68k_setup_node(int node)
+void __init m68k_setup_node(int node)
 {
 #ifndef CONFIG_SINGLE_MEMORY_CHUNK
         struct mem_info *info = m68k_memory + node;
diff --git a/arch/m68k/mm/sun3kmap.c b/arch/m68k/mm/sun3kmap.c
index 1af24cb5bfe1..3dc41158c05e 100644
--- a/arch/m68k/mm/sun3kmap.c
+++ b/arch/m68k/mm/sun3kmap.c
@@ -105,6 +105,7 @@ void __iomem *sun3_ioremap(unsigned long phys, unsigned long size,
         return (void __iomem *)ret;
 
 }
+EXPORT_SYMBOL(sun3_ioremap);
 
 
 void __iomem *__ioremap(unsigned long phys, unsigned long size, int cache)
@@ -157,3 +158,4 @@ int sun3_map_test(unsigned long addr, char *val)
 
         return ret;
 }
+EXPORT_SYMBOL(sun3_map_test);
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index 4a7df9c3f85a..92fe50714112 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -89,7 +89,7 @@ static int mvme147_get_hardware_list(char *buffer)
  * the mvme147 IRQ handling routines.
  */
 
-void mvme147_init_IRQ(void)
+void __init mvme147_init_IRQ(void)
 {
         m68k_setup_user_interrupt(VEC_USER, 192, NULL);
 }
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index c829ebb6b1af..daa785161401 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -119,7 +119,7 @@ static int mvme16x_get_hardware_list(char *buffer)
  * that the base vectors for the VMEChip2 and PCCChip2 are valid.
  */
 
-static void mvme16x_init_IRQ (void)
+static void __init mvme16x_init_IRQ (void)
 {
         m68k_setup_user_interrupt(VEC_USER, 192, NULL);
 }
diff --git a/arch/m68k/q40/q40ints.c b/arch/m68k/q40/q40ints.c
index 2fb25ae46a8a..ad3ed1fb8879 100644
--- a/arch/m68k/q40/q40ints.c
+++ b/arch/m68k/q40/q40ints.c
@@ -79,7 +79,7 @@ static struct irq_controller q40_irq_controller = {
 
 static int disabled;
 
-void q40_init_IRQ(void)
+void __init q40_init_IRQ(void)
 {
         m68k_setup_irq_controller(&q40_irq_controller, 1, Q40_IRQ_MAX);
 
diff --git a/arch/m68k/sun3/sun3ints.c b/arch/m68k/sun3/sun3ints.c
index 50df34bf80e3..cf93481adb1d 100644
--- a/arch/m68k/sun3/sun3ints.c
+++ b/arch/m68k/sun3/sun3ints.c
@@ -97,7 +97,7 @@ static struct irq_controller sun3_irq_controller = {
         .disable        = sun3_disable_irq,
 };
 
-void sun3_init_IRQ(void)
+void __init sun3_init_IRQ(void)
 {
         *sun3_intreg = 1;
 
diff --git a/arch/m68k/sun3x/prom.c b/arch/m68k/sun3x/prom.c
index 48f8eb7b1565..a7b7e818d627 100644
--- a/arch/m68k/sun3x/prom.c
+++ b/arch/m68k/sun3x/prom.c
@@ -92,7 +92,7 @@ static struct console sun3x_debug = {
         .index  = -1,
 };
 
-void sun3x_prom_init(void)
+void __init sun3x_prom_init(void)
 {
         /* Read the vector table */
 
diff --git a/arch/m68knommu/kernel/setup.c b/arch/m68knommu/kernel/setup.c
index 80f4e9d74ac1..2203f694f26b 100644
--- a/arch/m68knommu/kernel/setup.c
+++ b/arch/m68knommu/kernel/setup.c
@@ -231,32 +231,33 @@ void setup_arch(char **cmdline_p)
 /*
  *      Get CPU information for use by the procfs.
  */
-
 static int show_cpuinfo(struct seq_file *m, void *v)
 {
-    char *cpu, *mmu, *fpu;
-    u_long clockfreq;
+        char *cpu, *mmu, *fpu;
+        u_long clockfreq;
 
-    cpu = CPU;
-    mmu = "none";
-    fpu = "none";
+        cpu = CPU;
+        mmu = "none";
+        fpu = "none";
 
 #ifdef CONFIG_COLDFIRE
-    clockfreq = (loops_per_jiffy*HZ)*3;
+        clockfreq = (loops_per_jiffy * HZ) * 3;
 #else
-    clockfreq = (loops_per_jiffy*HZ)*16;
-#endif
-
-    seq_printf(m, "CPU:\t\t%s\n"
-                   "MMU:\t\t%s\n"
-                   "FPU:\t\t%s\n"
-                   "Clocking:\t%lu.%1luMHz\n"
-                   "BogoMips:\t%lu.%02lu\n"
-                   "Calibration:\t%lu loops\n",
-                   cpu, mmu, fpu,
-                   clockfreq/1000000,(clockfreq/100000)%10,
-                   (loops_per_jiffy*HZ)/500000,((loops_per_jiffy*HZ)/5000)%100,
-                   (loops_per_jiffy*HZ));
+        clockfreq = (loops_per_jiffy * HZ) * 16;
+#endif
+
+        seq_printf(m, "CPU:\t\t%s\n"
+                      "MMU:\t\t%s\n"
+                      "FPU:\t\t%s\n"
+                      "Clocking:\t%lu.%1luMHz\n"
+                      "BogoMips:\t%lu.%02lu\n"
+                      "Calibration:\t%lu loops\n",
+                      cpu, mmu, fpu,
+                      clockfreq / 1000000,
+                      (clockfreq / 100000) % 10,
+                      (loops_per_jiffy * HZ) / 500000,
+                      ((loops_per_jiffy * HZ) / 5000) % 100,
+                      (loops_per_jiffy * HZ));
 
         return 0;
 }
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 5c863bcd5614..1e3aeccd7322 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1190,8 +1190,19 @@ config SYS_HAS_CPU_RM9000
 config SYS_HAS_CPU_SB1
         bool
 
+#
+# CPU may reorder R->R, R->W, W->R, W->W
+# Reordering beyond LL and SC is handled in WEAK_REORDERING_BEYOND_LLSC
+#
 config WEAK_ORDERING
         bool
+
+#
+# CPU may reorder reads and writes beyond LL/SC
+# CPU may reorder R->LL, R->LL, W->LL, W->LL, R->SC, R->SC, W->SC, W->SC
+#
+config WEAK_REORDERING_BEYOND_LLSC
+        bool
 endmenu
 
 #
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index c6b8b074a81a..06448a9656dc 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -75,6 +75,27 @@ static void r4k_wait_irqoff(void)
         local_irq_enable();
 }
 
+/*
+ * The RM7000 variant has to handle erratum 38.  The workaround is to not
+ * have any pending stores when the WAIT instruction is executed.
+ */
+static void rm7k_wait_irqoff(void)
+{
+        local_irq_disable();
+        if (!need_resched())
+                __asm__(
+                "       .set    push                                    \n"
+                "       .set    mips3                                   \n"
+                "       .set    noat                                    \n"
+                "       mfc0    $1, $12                                 \n"
+                "       sync                                            \n"
+                "       mtc0    $1, $12         # stalls until W stage  \n"
+                "       wait                                            \n"
+                "       mtc0    $1, $12         # stalls until W stage  \n"
+                "       .set    pop                                     \n");
+        local_irq_enable();
+}
+
 /* The Au1xxx wait is available only if using 32khz counter or
  * external timer source, but specifically not CP0 Counter. */
 int allow_au1k_wait;
@@ -132,7 +153,6 @@ static inline void check_wait(void)
         case CPU_R4700:
         case CPU_R5000:
         case CPU_NEVADA:
-        case CPU_RM7000:
         case CPU_4KC:
         case CPU_4KEC:
         case CPU_4KSC:
@@ -142,6 +162,10 @@ static inline void check_wait(void)
                 cpu_wait = r4k_wait;
                 break;
 
+        case CPU_RM7000:
+                cpu_wait = rm7k_wait_irqoff;
+                break;
+
         case CPU_24K:
         case CPU_34K:
                 cpu_wait = r4k_wait;
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 8f4cf27c7157..bd05f5a927ea 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -25,7 +25,9 @@
 #include <linux/init.h>
 #include <linux/completion.h>
 #include <linux/kallsyms.h>
+#include <linux/random.h>
 
+#include <asm/asm.h>
 #include <asm/bootinfo.h>
 #include <asm/cpu.h>
 #include <asm/dsp.h>
@@ -460,3 +462,15 @@ unsigned long get_wchan(struct task_struct *task)
 out:
         return pc;
 }
+
+/*
+ * Don't forget that the stack pointer must be aligned on a 8 bytes
+ * boundary for 32-bits ABI and 16 bytes for 64-bits ABI.
+ */
+unsigned long arch_align_stack(unsigned long sp)
+{
+        if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
+                sp -= get_random_int() & ~PAGE_MASK;
+
+        return sp & ALMASK;
+}
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d860b640a140..853c282da22e 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -92,6 +92,9 @@ config ARCH_MAY_HAVE_PC_FDC
 config PPC_OF
         def_bool y
 
+config OF
+        def_bool y
+
 config PPC_UDBG_16550
         bool
         default n
diff --git a/arch/powerpc/boot/ps3-head.S b/arch/powerpc/boot/ps3-head.S
index 1a6d64a68df5..a55c2735f759 100644
--- a/arch/powerpc/boot/ps3-head.S
+++ b/arch/powerpc/boot/ps3-head.S
@@ -20,6 +20,8 @@
 
 #include "ppc_asm.h"
 
+        .machine "ppc64"
+
         .text
 
 /*
diff --git a/arch/powerpc/boot/ps3-hvcall.S b/arch/powerpc/boot/ps3-hvcall.S
index c8b7df3210d1..585965f7e6a8 100644
--- a/arch/powerpc/boot/ps3-hvcall.S
+++ b/arch/powerpc/boot/ps3-hvcall.S
@@ -20,6 +20,8 @@
 
 #include "ppc_asm.h"
 
+        .machine "ppc64"
+
 /*
  * The PS3 hypervisor uses a 64 bit "C" language calling convention.
  * The routines here marshal arguments between the 32 bit wrapper
diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig
index 74f83f4a4e5e..d9ac24e8de16 100644
--- a/arch/powerpc/configs/cell_defconfig
+++ b/arch/powerpc/configs/cell_defconfig
@@ -1455,7 +1455,8 @@ CONFIG_HAS_DMA=y
 # Instrumentation Support
 #
 CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
+CONFIG_OPROFILE=m
+CONFIG_OPROFILE_CELL=y
 # CONFIG_KPROBES is not set
 
 #
diff --git a/arch/powerpc/configs/prpmc2800_defconfig b/arch/powerpc/configs/prpmc2800_defconfig
index fb504a714625..858f865f2d59 100644
--- a/arch/powerpc/configs/prpmc2800_defconfig
+++ b/arch/powerpc/configs/prpmc2800_defconfig
@@ -48,7 +48,7 @@ CONFIG_PPC_STD_MMU_32=y
 # CONFIG_PPC_MM_SLICES is not set
 # CONFIG_SMP is not set
 CONFIG_NOT_COHERENT_CACHE=y
-CONFIG_CONFIG_CHECK_CACHE_COHERENCY=y
+CONFIG_CHECK_CACHE_COHERENCY=y
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
 
 #
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index d3f2080d2eee..37658ea417fa 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -219,6 +219,72 @@ void crash_kexec_secondary(struct pt_regs *regs)
         cpus_in_sr = CPU_MASK_NONE;
 }
 #endif
+#ifdef CONFIG_SPU_BASE
+
+#include <asm/spu.h>
+#include <asm/spu_priv1.h>
+
+struct crash_spu_info {
+        struct spu *spu;
+        u32 saved_spu_runcntl_RW;
+        u32 saved_spu_status_R;
+        u32 saved_spu_npc_RW;
+        u64 saved_mfc_sr1_RW;
+        u64 saved_mfc_dar;
+        u64 saved_mfc_dsisr;
+};
+
+#define CRASH_NUM_SPUS  16      /* Enough for current hardware */
+static struct crash_spu_info crash_spu_info[CRASH_NUM_SPUS];
+
+static void crash_kexec_stop_spus(void)
+{
+        struct spu *spu;
+        int i;
+        u64 tmp;
+
+        for (i = 0; i < CRASH_NUM_SPUS; i++) {
+                if (!crash_spu_info[i].spu)
+                        continue;
+
+                spu = crash_spu_info[i].spu;
+
+                crash_spu_info[i].saved_spu_runcntl_RW =
+                        in_be32(&spu->problem->spu_runcntl_RW);
+                crash_spu_info[i].saved_spu_status_R =
+                        in_be32(&spu->problem->spu_status_R);
+                crash_spu_info[i].saved_spu_npc_RW =
+                        in_be32(&spu->problem->spu_npc_RW);
+
+                crash_spu_info[i].saved_mfc_dar    = spu_mfc_dar_get(spu);
+                crash_spu_info[i].saved_mfc_dsisr  = spu_mfc_dsisr_get(spu);
+                tmp = spu_mfc_sr1_get(spu);
+                crash_spu_info[i].saved_mfc_sr1_RW = tmp;
+
+                tmp &= ~MFC_STATE1_MASTER_RUN_CONTROL_MASK;
+                spu_mfc_sr1_set(spu, tmp);
+
+                __delay(200);
+        }
+}
+
+void crash_register_spus(struct list_head *list)
+{
+        struct spu *spu;
+
+        list_for_each_entry(spu, list, full_list) {
+                if (WARN_ON(spu->number >= CRASH_NUM_SPUS))
+                        continue;
+
+                crash_spu_info[spu->number].spu = spu;
+        }
+}
+
+#else
+static inline void crash_kexec_stop_spus(void)
+{
+}
+#endif /* CONFIG_SPU_BASE */
 
 void default_machine_crash_shutdown(struct pt_regs *regs)
 {
@@ -254,6 +320,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
         crash_save_cpu(regs, crashing_cpu);
         crash_kexec_prepare_cpus(crashing_cpu);
         cpu_set(crashing_cpu, cpus_in_crash);
+        crash_kexec_stop_spus();
         if (ppc_md.kexec_cpu_down)
                 ppc_md.kexec_cpu_down(1, 0);
 }
diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c
index a464d67248df..89b911e83c04 100644
--- a/arch/powerpc/kernel/of_device.c
+++ b/arch/powerpc/kernel/of_device.c
@@ -1,5 +1,6 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
+#include <linux/of.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -8,118 +9,6 @@
 #include <asm/errno.h>
 #include <asm/of_device.h>
 
-/**
- * of_match_node - Tell if an device_node has a matching of_match structure
- * @ids: array of of device match structures to search in
- * @node: the of device structure to match against
- *
- * Low level utility function used by device matching.
- */
-const struct of_device_id *of_match_node(const struct of_device_id *matches,
-                                         const struct device_node *node)
-{
-        while (matches->name[0] || matches->type[0] || matches->compatible[0]) {
-                int match = 1;
-                if (matches->name[0])
-                        match &= node->name
-                                && !strcmp(matches->name, node->name);
-                if (matches->type[0])
-                        match &= node->type
-                                && !strcmp(matches->type, node->type);
-                if (matches->compatible[0])
-                        match &= of_device_is_compatible(node,
-                                                      matches->compatible);
-                if (match)
-                        return matches;
-                matches++;
-        }
-        return NULL;
-}
-
-/**
- * of_match_device - Tell if an of_device structure has a matching
- * of_match structure
- * @ids: array of of device match structures to search in
- * @dev: the of device structure to match against
- *
- * Used by a driver to check whether an of_device present in the
- * system is in its list of supported devices.
- */
-const struct of_device_id *of_match_device(const struct of_device_id *matches,
-                                        const struct of_device *dev)
-{
-        if (!dev->node)
-                return NULL;
-        return of_match_node(matches, dev->node);
-}
-
-struct of_device *of_dev_get(struct of_device *dev)
-{
-        struct device *tmp;
-
-        if (!dev)
-                return NULL;
-        tmp = get_device(&dev->dev);
-        if (tmp)
-                return to_of_device(tmp);
-        else
-                return NULL;
-}
-
-void of_dev_put(struct of_device *dev)
-{
-        if (dev)
-                put_device(&dev->dev);
-}
-
-static ssize_t dev_show_devspec(struct device *dev,
-                                struct device_attribute *attr, char *buf)
-{
-        struct of_device *ofdev;
-
-        ofdev = to_of_device(dev);
-        return sprintf(buf, "%s", ofdev->node->full_name);
-}
-
-static DEVICE_ATTR(devspec, S_IRUGO, dev_show_devspec, NULL);
-
-/**
- * of_release_dev - free an of device structure when all users of it are finished.
- * @dev: device that's been disconnected
- *
- * Will be called only by the device core when all users of this of device are
- * done.
- */
-void of_release_dev(struct device *dev)
-{
-        struct of_device *ofdev;
-
-        ofdev = to_of_device(dev);
-        of_node_put(ofdev->node);
-        kfree(ofdev);
-}
-
-int of_device_register(struct of_device *ofdev)
-{
-        int rc;
-
-        BUG_ON(ofdev->node == NULL);
-
-        rc = device_register(&ofdev->dev);
-        if (rc)
-                return rc;
-
-        return device_create_file(&ofdev->dev, &dev_attr_devspec);
-}
-
-void of_device_unregister(struct of_device *ofdev)
-{
-        device_remove_file(&ofdev->dev, &dev_attr_devspec);
-
-        device_unregister(&ofdev->dev);
-}
-
-
 ssize_t of_device_get_modalias(struct of_device *ofdev,
                                 char *str, ssize_t len)
 {
@@ -229,14 +118,5 @@ int of_device_uevent(struct device *dev,
 
         return 0;
 }
-
-
-EXPORT_SYMBOL(of_match_node);
-EXPORT_SYMBOL(of_match_device);
-EXPORT_SYMBOL(of_device_register);
-EXPORT_SYMBOL(of_device_unregister);
-EXPORT_SYMBOL(of_dev_get);
-EXPORT_SYMBOL(of_dev_put);
-EXPORT_SYMBOL(of_release_dev);
 EXPORT_SYMBOL(of_device_uevent);
 EXPORT_SYMBOL(of_device_get_modalias);
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index 8ded4e7dc87e..f70e787d556f 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -55,94 +55,14 @@ static struct of_device_id of_default_bus_ids[] = {
 
 static atomic_t bus_no_reg_magic;
 
-/*
- *
- * OF platform device type definition & base infrastructure
- *
- */
-
-static int of_platform_bus_match(struct device *dev, struct device_driver *drv)
-{
-        struct of_device * of_dev = to_of_device(dev);
-        struct of_platform_driver * of_drv = to_of_platform_driver(drv);
-        const struct of_device_id * matches = of_drv->match_table;
-
-        if (!matches)
-                return 0;
-
-        return of_match_device(matches, of_dev) != NULL;
-}
-
-static int of_platform_device_probe(struct device *dev)
-{
-        int error = -ENODEV;
-        struct of_platform_driver *drv;
-        struct of_device *of_dev;
-        const struct of_device_id *match;
-
-        drv = to_of_platform_driver(dev->driver);
-        of_dev = to_of_device(dev);
-
-        if (!drv->probe)
-                return error;
-
-        of_dev_get(of_dev);
-
-        match = of_match_device(drv->match_table, of_dev);
-        if (match)
-                error = drv->probe(of_dev, match);
-        if (error)
-                of_dev_put(of_dev);
-
-        return error;
-}
-
-static int of_platform_device_remove(struct device *dev)
-{
-        struct of_device * of_dev = to_of_device(dev);
-        struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
-
-        if (dev->driver && drv->remove)
-                drv->remove(of_dev);
-        return 0;
-}
-
-static int of_platform_device_suspend(struct device *dev, pm_message_t state)
-{
-        struct of_device * of_dev = to_of_device(dev);
-        struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
-        int error = 0;
-
-        if (dev->driver && drv->suspend)
-                error = drv->suspend(of_dev, state);
-        return error;
-}
-
-static int of_platform_device_resume(struct device * dev)
-{
-        struct of_device * of_dev = to_of_device(dev);
-        struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
-        int error = 0;
-
-        if (dev->driver && drv->resume)
-                error = drv->resume(of_dev);
-        return error;
-}
-
 struct bus_type of_platform_bus_type = {
-       .name    = "of_platform",
-       .match   = of_platform_bus_match,
        .uevent  = of_device_uevent,
-       .probe   = of_platform_device_probe,
-       .remove  = of_platform_device_remove,
-       .suspend = of_platform_device_suspend,
-       .resume  = of_platform_device_resume,
 };
 EXPORT_SYMBOL(of_platform_bus_type);
 
 static int __init of_bus_driver_init(void)
 {
-        return bus_register(&of_platform_bus_type);
+        return of_bus_type_init(&of_platform_bus_type, "of_platform");
 }
 
 postcore_initcall(of_bus_driver_init);
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 94b4a028232a..fe7d1255e11e 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -166,7 +166,7 @@ int pcibios_add_platform_entries(struct pci_dev *pdev)
 
 }
 
-char __init *pcibios_setup(char *str)
+char __devinit *pcibios_setup(char *str)
 {
         return str;
 }
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 37ff99bd98b4..a38197b12d3e 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -78,12 +78,9 @@ static struct boot_param_header *initial_boot_params __initdata;
 struct boot_param_header *initial_boot_params;
 #endif
 
-static struct device_node *allnodes = NULL;
+extern struct device_node *allnodes;    /* temporary while merging */
 
-/* use when traversing tree through the allnext, child, sibling,
- * or parent members of struct device_node.
- */
-static DEFINE_RWLOCK(devtree_lock);
+extern rwlock_t devtree_lock;   /* temporary while merging */
 
 /* export that to outside world */
 struct device_node *of_chosen;
@@ -1056,60 +1053,6 @@ void __init early_init_devtree(void *params)
         DBG(" <- early_init_devtree()\n");
 }
 
-int of_n_addr_cells(struct device_node* np)
-{
-        const 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 1 */
-        return 1;
-}
-EXPORT_SYMBOL(of_n_addr_cells);
-
-int of_n_size_cells(struct device_node* np)
-{
-        const 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);
-
-/** Checks if the given "compat" string matches one of the strings in
- * the device's "compatible" property
- */
-int of_device_is_compatible(const struct device_node *device,
-                const char *compat)
-{
-        const char* cp;
-        int cplen, l;
-
-        cp = of_get_property(device, "compatible", &cplen);
-        if (cp == NULL)
-                return 0;
-        while (cplen > 0) {
-                if (strncasecmp(cp, compat, strlen(compat)) == 0)
-                        return 1;
-                l = strlen(cp) + 1;
-                cp += l;
-                cplen -= l;
-        }
-
-        return 0;
-}
-EXPORT_SYMBOL(of_device_is_compatible);
-
 
 /**
  * Indicates whether the root node has a given value in its
@@ -1141,119 +1084,6 @@ EXPORT_SYMBOL(machine_is_compatible);
  *******/
 
 /**
- *      of_find_node_by_name - Find a node by its "name" property
- *      @from:  The node to start searching from or NULL, the node
- *              you pass will not be searched, only the next one
- *              will; typically, you pass what the previous call
- *              returned. of_node_put() will be called on it
- *      @name:  The name string to match against
- *
- *      Returns a node pointer with refcount incremented, use
- *      of_node_put() on it when done.
- */
-struct device_node *of_find_node_by_name(struct device_node *from,
-        const char *name)
-{
-        struct device_node *np;
-
-        read_lock(&devtree_lock);
-        np = from ? from->allnext : allnodes;
-        for (; np != NULL; np = np->allnext)
-                if (np->name != NULL && strcasecmp(np->name, name) == 0
-                    && of_node_get(np))
-                        break;
-        of_node_put(from);
-        read_unlock(&devtree_lock);
-        return np;
-}
-EXPORT_SYMBOL(of_find_node_by_name);
-
-/**
- *      of_find_node_by_type - Find a node by its "device_type" property
- *      @from:  The node to start searching from, or NULL to start searching
- *              the entire device tree. The node you pass will not be
- *              searched, only the next one will; typically, you pass
- *              what the previous call returned. of_node_put() will be
- *              called on from for you.
- *      @type:  The type string to match against
- *
- *      Returns a node pointer with refcount incremented, use
- *      of_node_put() on it when done.
- */
-struct device_node *of_find_node_by_type(struct device_node *from,
-        const char *type)
-{
-        struct device_node *np;
-
-        read_lock(&devtree_lock);
-        np = from ? from->allnext : allnodes;
-        for (; np != 0; np = np->allnext)
-                if (np->type != 0 && strcasecmp(np->type, type) == 0
-                    && of_node_get(np))
-                        break;
-        of_node_put(from);
-        read_unlock(&devtree_lock);
-        return np;
-}
-EXPORT_SYMBOL(of_find_node_by_type);
-
-/**
- *      of_find_compatible_node - Find a node based on type and one of the
- *                                tokens in its "compatible" property
- *      @from:          The node to start searching from or NULL, the node
- *                      you pass will not be searched, only the next one
- *                      will; typically, you pass what the previous call
- *                      returned. of_node_put() will be called on it
- *      @type:          The type string to match "device_type" or NULL to ignore
- *      @compatible:    The string to match to one of the tokens in the device
- *                      "compatible" list.
- *
- *      Returns a node pointer with refcount incremented, use
- *      of_node_put() on it when done.
- */
-struct device_node *of_find_compatible_node(struct device_node *from,
-        const char *type, const char *compatible)
-{
-        struct device_node *np;
-
-        read_lock(&devtree_lock);
-        np = from ? from->allnext : allnodes;
-        for (; np != 0; np = np->allnext) {
-                if (type != NULL
-                    && !(np->type != 0 && strcasecmp(np->type, type) == 0))
-                        continue;
-                if (of_device_is_compatible(np, compatible) && of_node_get(np))
-                        break;
-        }
-        of_node_put(from);
-        read_unlock(&devtree_lock);
-        return np;
-}
-EXPORT_SYMBOL(of_find_compatible_node);
-
-/**
- *      of_find_node_by_path - Find a node matching a full OF path
- *      @path:  The full path to match
- *
- *      Returns a node pointer with refcount incremented, use
- *      of_node_put() on it when done.
- */
-struct device_node *of_find_node_by_path(const char *path)
-{
-        struct device_node *np = allnodes;
-
-        read_lock(&devtree_lock);
-        for (; np != 0; np = np->allnext) {
-                if (np->full_name != 0 && strcasecmp(np->full_name, path) == 0
-                    && of_node_get(np))
-                        break;
-        }
-        read_unlock(&devtree_lock);
-        return np;
-}
-EXPORT_SYMBOL(of_find_node_by_path);
-
-/**
  *      of_find_node_by_phandle - Find a node given a phandle
  *      @handle:        phandle of the node to find
  *
@@ -1298,51 +1128,6 @@ struct device_node *of_find_all_nodes(struct device_node *prev)
 EXPORT_SYMBOL(of_find_all_nodes);
 
 /**
- *      of_get_parent - Get a node's parent if any
- *      @node:  Node to get parent
- *
- *      Returns a node pointer with refcount incremented, use
- *      of_node_put() on it when done.
- */
-struct device_node *of_get_parent(const struct device_node *node)
-{
-        struct device_node *np;
-
-        if (!node)
-                return NULL;
-
-        read_lock(&devtree_lock);
-        np = of_node_get(node->parent);
-        read_unlock(&devtree_lock);
-        return np;
-}
-EXPORT_SYMBOL(of_get_parent);
-
-/**
- *      of_get_next_child - Iterate a node childs
- *      @node:  parent node
- *      @prev:  previous child of the parent node, or NULL to get first
- *
- *      Returns a node pointer with refcount incremented, use
- *      of_node_put() on it when done.
- */
-struct device_node *of_get_next_child(const struct device_node *node,
-        struct device_node *prev)
-{
-        struct device_node *next;
-
-        read_lock(&devtree_lock);
-        next = prev ? prev->sibling : node->child;
-        for (; next != 0; next = next->sibling)
-                if (of_node_get(next))
-                        break;
-        of_node_put(prev);
-        read_unlock(&devtree_lock);
-        return next;
-}
-EXPORT_SYMBOL(of_get_next_child);
-
-/**
  *      of_node_get - Increment refcount of a node
  *      @node:  Node to inc refcount, NULL is supported to
  *              simplify writing of callers
@@ -1433,7 +1218,7 @@ void of_attach_node(struct device_node *np)
  * a reference to the node.  The memory associated with the node
  * is not freed until its refcount goes to zero.
  */
-void of_detach_node(const struct device_node *np)
+void of_detach_node(struct device_node *np)
 {
         struct device_node *parent;
 
@@ -1543,37 +1328,6 @@ static int __init prom_reconfig_setup(void)
 __initcall(prom_reconfig_setup);
 #endif
 
-struct property *of_find_property(const struct device_node *np,
-                                  const char *name,
-                                  int *lenp)
-{
-        struct property *pp;
-
-        read_lock(&devtree_lock);
-        for (pp = np->properties; pp != 0; pp = pp->next)
-                if (strcmp(pp->name, name) == 0) {
-                        if (lenp != 0)
-                                *lenp = pp->length;
-                        break;
-                }
-        read_unlock(&devtree_lock);
-
-        return pp;
-}
-EXPORT_SYMBOL(of_find_property);
-
-/*
- * Find a property with a given name for a given node
- * and return the value.
- */
-const void *of_get_property(const struct device_node *np, const char *name,
-                         int *lenp)
-{
-        struct property *pp = of_find_property(np,name,lenp);
-        return pp ? pp->value : NULL;
-}
-EXPORT_SYMBOL(of_get_property);
-
 /*
  * Add a property to a node
  */
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index d577b71db375..087c92f2a3eb 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -284,7 +284,7 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, int
                         int wait)
 {
         cpumask_t map = CPU_MASK_NONE;
-        int ret = -EBUSY;
+        int ret = 0;
 
         if (!cpu_online(cpu))
                 return -EINVAL;
@@ -292,6 +292,11 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, int
         cpu_set(cpu, map);
         if (cpu != get_cpu())
                 ret = smp_call_function_map(func,info,nonatomic,wait,map);
+        else {
+                local_irq_disable();
+                func(info);
+                local_irq_enable();
+        }
         put_cpu();
         return ret;
 }
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index e5df167f7824..727a6699f2f4 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -122,6 +122,7 @@ extern struct timezone sys_tz;
 static long timezone_offset;
 
 unsigned long ppc_proc_freq;
+EXPORT_SYMBOL(ppc_proc_freq);
 unsigned long ppc_tb_freq;
 
 static u64 tb_last_jiffy __cacheline_aligned_in_smp;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 3767211b3d0f..ab3546c5ac3a 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -283,7 +283,13 @@ good_area:
                 /* protection fault */
                 if (error_code & DSISR_PROTFAULT)
                         goto bad_area;
-                if (!(vma->vm_flags & VM_EXEC))
+                /*
+                 * Allow execution from readable areas if the MMU does not
+                 * provide separate controls over reading and executing.
+                 */
+                if (!(vma->vm_flags & VM_EXEC) &&
+                    (cpu_has_feature(CPU_FTR_NOEXECUTE) ||
+                     !(vma->vm_flags & (VM_READ | VM_WRITE))))
                         goto bad_area;
 #else
                 pte_t *ptep;
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 2ce9491b48d4..bc7b0cedae5e 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -609,7 +609,7 @@ static void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
         mm->context.sllp = SLB_VSID_USER | mmu_psize_defs[MMU_PAGE_4K].sllp;
 #endif /* CONFIG_PPC_MM_SLICES */
 
-#ifdef CONFIG_SPE_BASE
+#ifdef CONFIG_SPU_BASE
         spu_flush_all_slbs(mm);
 #endif
 }
@@ -744,7 +744,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
                                "to 4kB pages because of "
                                "non-cacheable mapping\n");
                         psize = mmu_vmalloc_psize = MMU_PAGE_4K;
-#ifdef CONFIG_SPE_BASE
+#ifdef CONFIG_SPU_BASE
                         spu_flush_all_slbs(mm);
 #endif
                 }
diff --git a/arch/powerpc/mm/tlb_32.c b/arch/powerpc/mm/tlb_32.c
index 06c7e77e097a..eb4b512d65fa 100644
--- a/arch/powerpc/mm/tlb_32.c
+++ b/arch/powerpc/mm/tlb_32.c
@@ -26,6 +26,8 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/highmem.h>
+#include <linux/pagemap.h>
+
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 
diff --git a/arch/powerpc/oprofile/Kconfig b/arch/powerpc/oprofile/Kconfig
index eb2dece76a54..7089e79689b9 100644
--- a/arch/powerpc/oprofile/Kconfig
+++ b/arch/powerpc/oprofile/Kconfig
@@ -15,3 +15,10 @@ config OPROFILE
 
           If unsure, say N.
 
+config OPROFILE_CELL
+        bool "OProfile for Cell Broadband Engine"
+        depends on (SPU_FS = y && OPROFILE = m) || (SPU_FS = y && OPROFILE = y) || (SPU_FS = m && OPROFILE = m)
+        default y
+        help
+          Profiling of Cell BE SPUs requires special support enabled
+          by this option.
diff --git a/arch/powerpc/oprofile/Makefile b/arch/powerpc/oprofile/Makefile
index 4b5f9528218c..c5f64c3bd668 100644
--- a/arch/powerpc/oprofile/Makefile
+++ b/arch/powerpc/oprofile/Makefile
@@ -11,7 +11,9 @@ DRIVER_OBJS := $(addprefix ../../../drivers/oprofile/, \
                 timer_int.o )
 
 oprofile-y := $(DRIVER_OBJS) common.o backtrace.o
-oprofile-$(CONFIG_PPC_CELL_NATIVE) += op_model_cell.o
+oprofile-$(CONFIG_OPROFILE_CELL) += op_model_cell.o \
+                cell/spu_profiler.o cell/vma_map.o \
+                cell/spu_task_sync.o
 oprofile-$(CONFIG_PPC64) += op_model_rs64.o op_model_power4.o op_model_pa6t.o
 oprofile-$(CONFIG_FSL_BOOKE) += op_model_fsl_booke.o
 oprofile-$(CONFIG_6xx) += op_model_7450.o
diff --git a/arch/powerpc/oprofile/cell/pr_util.h b/arch/powerpc/oprofile/cell/pr_util.h
new file mode 100644
index 000000000000..e5704f00c8b4
--- /dev/null
+++ b/arch/powerpc/oprofile/cell/pr_util.h
@@ -0,0 +1,97 @@
+ /*
+ * Cell Broadband Engine OProfile Support
+ *
+ * (C) Copyright IBM Corporation 2006
+ *
+ * Author: Maynard Johnson <maynardj@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef PR_UTIL_H
+#define PR_UTIL_H
+
+#include <linux/cpumask.h>
+#include <linux/oprofile.h>
+#include <asm/cell-pmu.h>
+#include <asm/spu.h>
+
+#include "../../platforms/cell/cbe_regs.h"
+
+/* Defines used for sync_start */
+#define SKIP_GENERIC_SYNC 0
+#define SYNC_START_ERROR -1
+#define DO_GENERIC_SYNC 1
+
+struct spu_overlay_info {       /* map of sections within an SPU overlay */
+        unsigned int vma;       /* SPU virtual memory address from elf */
+        unsigned int size;      /* size of section from elf */
+        unsigned int offset;    /* offset of section into elf file */
+        unsigned int buf;
+};
+
+struct vma_to_fileoffset_map {  /* map of sections within an SPU program */
+        struct vma_to_fileoffset_map *next;     /* list pointer */
+        unsigned int vma;       /* SPU virtual memory address from elf */
+        unsigned int size;      /* size of section from elf */
+        unsigned int offset;    /* offset of section into elf file */
+        unsigned int guard_ptr;
+        unsigned int guard_val;
+        /*
+         * The guard pointer is an entry in the _ovly_buf_table,
+         * computed using ovly.buf as the index into the table.  Since
+         * ovly.buf values begin at '1' to reference the first (or 0th)
+         * entry in the _ovly_buf_table, the computation subtracts 1
+         * from ovly.buf.
+         * The guard value is stored in the _ovly_buf_table entry and
+         * is an index (starting at 1) back to the _ovly_table entry
+         * that is pointing at this _ovly_buf_table entry.  So, for
+         * example, for an overlay scenario with one overlay segment
+         * and two overlay sections:
+         *      - Section 1 points to the first entry of the
+         *        _ovly_buf_table, which contains a guard value
+         *        of '1', referencing the first (index=0) entry of
+         *        _ovly_table.
+         *      - Section 2 points to the second entry of the
+         *        _ovly_buf_table, which contains a guard value
+         *        of '2', referencing the second (index=1) entry of
+         *        _ovly_table.
+         */
+
+};
+
+/* The three functions below are for maintaining and accessing
+ * the vma-to-fileoffset map.
+ */
+struct vma_to_fileoffset_map *create_vma_map(const struct spu *spu,
+                                             u64 objectid);
+unsigned int vma_map_lookup(struct vma_to_fileoffset_map *map,
+                            unsigned int vma, const struct spu *aSpu,
+                            int *grd_val);
+void vma_map_free(struct vma_to_fileoffset_map *map);
+
+/*
+ * Entry point for SPU profiling.
+ * cycles_reset is the SPU_CYCLES count value specified by the user.
+ */
+int start_spu_profiling(unsigned int cycles_reset);
+
+void stop_spu_profiling(void);
+
+
+/* add the necessary profiling hooks */
+int spu_sync_start(void);
+
+/* remove the hooks */
+int spu_sync_stop(void);
+
+/* Record SPU program counter samples to the oprofile event buffer. */
+void spu_sync_buffer(int spu_num, unsigned int *samples,
+                     int num_samples);
+
+void set_spu_profiling_frequency(unsigned int freq_khz, unsigned int cycles_reset);
+
+#endif    /* PR_UTIL_H */
diff --git a/arch/powerpc/oprofile/cell/spu_profiler.c b/arch/powerpc/oprofile/cell/spu_profiler.c
new file mode 100644
index 000000000000..380d7e217531
--- /dev/null
+++ b/arch/powerpc/oprofile/cell/spu_profiler.c
@@ -0,0 +1,221 @@
+/*
+ * Cell Broadband Engine OProfile Support
+ *
+ * (C) Copyright IBM Corporation 2006
+ *
+ * Authors: Maynard Johnson <maynardj@us.ibm.com>
+ *          Carl Love <carll@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/hrtimer.h>
+#include <linux/smp.h>
+#include <linux/slab.h>
+#include <asm/cell-pmu.h>
+#include "pr_util.h"
+
+#define TRACE_ARRAY_SIZE 1024
+#define SCALE_SHIFT 14
+
+static u32 *samples;
+
+static int spu_prof_running;
+static unsigned int profiling_interval;
+
+#define NUM_SPU_BITS_TRBUF 16
+#define SPUS_PER_TB_ENTRY   4
+#define SPUS_PER_NODE        8
+
+#define SPU_PC_MASK          0xFFFF
+
+static DEFINE_SPINLOCK(sample_array_lock);
+unsigned long sample_array_lock_flags;
+
+void set_spu_profiling_frequency(unsigned int freq_khz, unsigned int cycles_reset)
+{
+        unsigned long ns_per_cyc;
+
+        if (!freq_khz)
+                freq_khz = ppc_proc_freq/1000;
+
+        /* To calculate a timeout in nanoseconds, the basic
+         * formula is ns = cycles_reset * (NSEC_PER_SEC / cpu frequency).
+         * To avoid floating point math, we use the scale math
+         * technique as described in linux/jiffies.h.  We use
+         * a scale factor of SCALE_SHIFT, which provides 4 decimal places
+         * of precision.  This is close enough for the purpose at hand.
+         *
+         * The value of the timeout should be small enough that the hw
+         * trace buffer will not get more then about 1/3 full for the
+         * maximum user specified (the LFSR value) hw sampling frequency.
+         * This is to ensure the trace buffer will never fill even if the
+         * kernel thread scheduling varies under a heavy system load.
+         */
+
+        ns_per_cyc = (USEC_PER_SEC << SCALE_SHIFT)/freq_khz;
+        profiling_interval = (ns_per_cyc * cycles_reset) >> SCALE_SHIFT;
+
+}
+
+/*
+ * Extract SPU PC from trace buffer entry
+ */
+static void spu_pc_extract(int cpu, int entry)
+{
+        /* the trace buffer is 128 bits */
+        u64 trace_buffer[2];
+        u64 spu_mask;
+        int spu;
+
+        spu_mask = SPU_PC_MASK;
+
+        /* Each SPU PC is 16 bits; hence, four spus in each of
+         * the two 64-bit buffer entries that make up the
+         * 128-bit trace_buffer entry.  Process two 64-bit values
+         * simultaneously.
+         * trace[0] SPU PC contents are: 0 1 2 3
+         * trace[1] SPU PC contents are: 4 5 6 7
+         */
+
+        cbe_read_trace_buffer(cpu, trace_buffer);
+
+        for (spu = SPUS_PER_TB_ENTRY-1; spu >= 0; spu--) {
+                /* spu PC trace entry is upper 16 bits of the
+                 * 18 bit SPU program counter
+                 */
+                samples[spu * TRACE_ARRAY_SIZE + entry]
+                        = (spu_mask & trace_buffer[0]) << 2;
+                samples[(spu + SPUS_PER_TB_ENTRY) * TRACE_ARRAY_SIZE + entry]
+                        = (spu_mask & trace_buffer[1]) << 2;
+
+                trace_buffer[0] = trace_buffer[0] >> NUM_SPU_BITS_TRBUF;
+                trace_buffer[1] = trace_buffer[1] >> NUM_SPU_BITS_TRBUF;
+        }
+}
+
+static int cell_spu_pc_collection(int cpu)
+{
+        u32 trace_addr;
+        int entry;
+
+        /* process the collected SPU PC for the node */
+
+        entry = 0;
+
+        trace_addr = cbe_read_pm(cpu, trace_address);
+        while (!(trace_addr & CBE_PM_TRACE_BUF_EMPTY)) {
+                /* there is data in the trace buffer to process */
+                spu_pc_extract(cpu, entry);
+
+                entry++;
+
+                if (entry >= TRACE_ARRAY_SIZE)
+                        /* spu_samples is full */
+                        break;
+
+                trace_addr = cbe_read_pm(cpu, trace_address);
+        }
+
+        return entry;
+}
+
+
+static enum hrtimer_restart profile_spus(struct hrtimer *timer)
+{
+        ktime_t kt;
+        int cpu, node, k, num_samples, spu_num;
+
+        if (!spu_prof_running)
+                goto stop;
+
+        for_each_online_cpu(cpu) {
+                if (cbe_get_hw_thread_id(cpu))
+                        continue;
+
+                node = cbe_cpu_to_node(cpu);
+
+                /* There should only be one kernel thread at a time processing
+                 * the samples.  In the very unlikely case that the processing
+                 * is taking a very long time and multiple kernel threads are
+                 * started to process the samples.  Make sure only one kernel
+                 * thread is working on the samples array at a time.  The
+                 * sample array must be loaded and then processed for a given
+                 * cpu.  The sample array is not per cpu.
+                 */
+                spin_lock_irqsave(&sample_array_lock,
+                                  sample_array_lock_flags);
+                num_samples = cell_spu_pc_collection(cpu);
+
+                if (num_samples == 0) {
+                        spin_unlock_irqrestore(&sample_array_lock,
+                                               sample_array_lock_flags);
+                        continue;
+                }
+
+                for (k = 0; k < SPUS_PER_NODE; k++) {
+                        spu_num = k + (node * SPUS_PER_NODE);
+                        spu_sync_buffer(spu_num,
+                                        samples + (k * TRACE_ARRAY_SIZE),
+                                        num_samples);
+                }
+
+                spin_unlock_irqrestore(&sample_array_lock,
+                                       sample_array_lock_flags);
+
+        }
+        smp_wmb();      /* insure spu event buffer updates are written */
+                        /* don't want events intermingled... */
+
+        kt = ktime_set(0, profiling_interval);
+        if (!spu_prof_running)
+                goto stop;
+        hrtimer_forward(timer, timer->base->get_time(), kt);
+        return HRTIMER_RESTART;
+
+ stop:
+        printk(KERN_INFO "SPU_PROF: spu-prof timer ending\n");
+        return HRTIMER_NORESTART;
+}
+
+static struct hrtimer timer;
+/*
+ * Entry point for SPU profiling.
+ * NOTE:  SPU profiling is done system-wide, not per-CPU.
+ *
+ * cycles_reset is the count value specified by the user when
+ * setting up OProfile to count SPU_CYCLES.
+ */
+int start_spu_profiling(unsigned int cycles_reset)
+{
+        ktime_t kt;
+
+        pr_debug("timer resolution: %lu\n", TICK_NSEC);
+        kt = ktime_set(0, profiling_interval);
+        hrtimer_init(&timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+        timer.expires = kt;
+        timer.function = profile_spus;
+
+        /* Allocate arrays for collecting SPU PC samples */
+        samples = kzalloc(SPUS_PER_NODE *
+                          TRACE_ARRAY_SIZE * sizeof(u32), GFP_KERNEL);
+
+        if (!samples)
+                return -ENOMEM;
+
+        spu_prof_running = 1;
+        hrtimer_start(&timer, kt, HRTIMER_MODE_REL);
+
+        return 0;
+}
+
+void stop_spu_profiling(void)
+{
+        spu_prof_running = 0;
+        hrtimer_cancel(&timer);
+        kfree(samples);
+        pr_debug("SPU_PROF: stop_spu_profiling issued\n");
+}
diff --git a/arch/powerpc/oprofile/cell/spu_task_sync.c b/arch/powerpc/oprofile/cell/spu_task_sync.c
new file mode 100644
index 000000000000..133665754a75
--- /dev/null
+++ b/arch/powerpc/oprofile/cell/spu_task_sync.c
@@ -0,0 +1,484 @@
+/*
+ * Cell Broadband Engine OProfile Support
+ *
+ * (C) Copyright IBM Corporation 2006
+ *
+ * Author: Maynard Johnson <maynardj@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+/* The purpose of this file is to handle SPU event task switching
+ * and to record SPU context information into the OProfile
+ * event buffer.
+ *
+ * Additionally, the spu_sync_buffer function is provided as a helper
+ * for recoding actual SPU program counter samples to the event buffer.
+ */
+#include <linux/dcookies.h>
+#include <linux/kref.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/numa.h>
+#include <linux/oprofile.h>
+#include <linux/spinlock.h>
+#include "pr_util.h"
+
+#define RELEASE_ALL 9999
+
+static DEFINE_SPINLOCK(buffer_lock);
+static DEFINE_SPINLOCK(cache_lock);
+static int num_spu_nodes;
+int spu_prof_num_nodes;
+int last_guard_val[MAX_NUMNODES * 8];
+
+/* Container for caching information about an active SPU task. */
+struct cached_info {
+        struct vma_to_fileoffset_map *map;
+        struct spu *the_spu;    /* needed to access pointer to local_store */
+        struct kref cache_ref;
+};
+
+static struct cached_info *spu_info[MAX_NUMNODES * 8];
+
+static void destroy_cached_info(struct kref *kref)
+{
+        struct cached_info *info;
+
+        info = container_of(kref, struct cached_info, cache_ref);
+        vma_map_free(info->map);
+        kfree(info);
+        module_put(THIS_MODULE);
+}
+
+/* Return the cached_info for the passed SPU number.
+ * ATTENTION:  Callers are responsible for obtaining the
+ *             cache_lock if needed prior to invoking this function.
+ */
+static struct cached_info *get_cached_info(struct spu *the_spu, int spu_num)
+{
+        struct kref *ref;
+        struct cached_info *ret_info;
+
+        if (spu_num >= num_spu_nodes) {
+                printk(KERN_ERR "SPU_PROF: "
+                       "%s, line %d: Invalid index %d into spu info cache\n",
+                       __FUNCTION__, __LINE__, spu_num);
+                ret_info = NULL;
+                goto out;
+        }
+        if (!spu_info[spu_num] && the_spu) {
+                ref = spu_get_profile_private_kref(the_spu->ctx);
+                if (ref) {
+                        spu_info[spu_num] = container_of(ref, struct cached_info, cache_ref);
+                        kref_get(&spu_info[spu_num]->cache_ref);
+                }
+        }
+
+        ret_info = spu_info[spu_num];
+ out:
+        return ret_info;
+}
+
+
+/* Looks for cached info for the passed spu.  If not found, the
+ * cached info is created for the passed spu.
+ * Returns 0 for success; otherwise, -1 for error.
+ */
+static int
+prepare_cached_spu_info(struct spu *spu, unsigned long objectId)
+{
+        unsigned long flags;
+        struct vma_to_fileoffset_map *new_map;
+        int retval = 0;
+        struct cached_info *info;
+
+        /* We won't bother getting cache_lock here since
+         * don't do anything with the cached_info that's returned.
+         */
+        info = get_cached_info(spu, spu->number);
+
+        if (info) {
+                pr_debug("Found cached SPU info.\n");
+                goto out;
+        }
+
+        /* Create cached_info and set spu_info[spu->number] to point to it.
+         * spu->number is a system-wide value, not a per-node value.
+         */
+        info = kzalloc(sizeof(struct cached_info), GFP_KERNEL);
+        if (!info) {
+                printk(KERN_ERR "SPU_PROF: "
+                       "%s, line %d: create vma_map failed\n",
+                       __FUNCTION__, __LINE__);
+                retval = -ENOMEM;
+                goto err_alloc;
+        }
+        new_map = create_vma_map(spu, objectId);
+        if (!new_map) {
+                printk(KERN_ERR "SPU_PROF: "
+                       "%s, line %d: create vma_map failed\n",
+                       __FUNCTION__, __LINE__);
+                retval = -ENOMEM;
+                goto err_alloc;
+        }
+
+        pr_debug("Created vma_map\n");
+        info->map = new_map;
+        info->the_spu = spu;
+        kref_init(&info->cache_ref);
+        spin_lock_irqsave(&cache_lock, flags);
+        spu_info[spu->number] = info;
+        /* Increment count before passing off ref to SPUFS. */
+        kref_get(&info->cache_ref);
+
+        /* We increment the module refcount here since SPUFS is
+         * responsible for the final destruction of the cached_info,
+         * and it must be able to access the destroy_cached_info()
+         * function defined in the OProfile module.  We decrement
+         * the module refcount in destroy_cached_info.
+         */
+        try_module_get(THIS_MODULE);
+        spu_set_profile_private_kref(spu->ctx, &info->cache_ref,
+                                destroy_cached_info);
+        spin_unlock_irqrestore(&cache_lock, flags);
+        goto out;
+
+err_alloc:
+        kfree(info);
+out:
+        return retval;
+}
+
+/*
+ * NOTE:  The caller is responsible for locking the
+ *        cache_lock prior to calling this function.
+ */
+static int release_cached_info(int spu_index)
+{
+        int index, end;
+
+        if (spu_index == RELEASE_ALL) {
+                end = num_spu_nodes;
+                index = 0;
+        } else {
+                if (spu_index >= num_spu_nodes) {
+                        printk(KERN_ERR "SPU_PROF: "
+                                "%s, line %d: "
+                                "Invalid index %d into spu info cache\n",
+                                __FUNCTION__, __LINE__, spu_index);
+                        goto out;
+                }
+                end = spu_index + 1;
+                index = spu_index;
+        }
+        for (; index < end; index++) {
+                if (spu_info[index]) {
+                        kref_put(&spu_info[index]->cache_ref,
+                                 destroy_cached_info);
+                        spu_info[index] = NULL;
+                }
+        }
+
+out:
+        return 0;
+}
+
+/* The source code for fast_get_dcookie was "borrowed"
+ * from drivers/oprofile/buffer_sync.c.
+ */
+
+/* Optimisation. We can manage without taking the dcookie sem
+ * because we cannot reach this code without at least one
+ * dcookie user still being registered (namely, the reader
+ * of the event buffer).
+ */
+static inline unsigned long fast_get_dcookie(struct dentry *dentry,
+                                             struct vfsmount *vfsmnt)
+{
+        unsigned long cookie;
+
+        if (dentry->d_cookie)
+                return (unsigned long)dentry;
+        get_dcookie(dentry, vfsmnt, &cookie);
+        return cookie;
+}
+
+/* Look up the dcookie for the task's first VM_EXECUTABLE mapping,
+ * which corresponds loosely to "application name". Also, determine
+ * the offset for the SPU ELF object.  If computed offset is
+ * non-zero, it implies an embedded SPU object; otherwise, it's a
+ * separate SPU binary, in which case we retrieve it's dcookie.
+ * For the embedded case, we must determine if SPU ELF is embedded
+ * in the executable application or another file (i.e., shared lib).
+ * If embedded in a shared lib, we must get the dcookie and return
+ * that to the caller.
+ */
+static unsigned long
+get_exec_dcookie_and_offset(struct spu *spu, unsigned int *offsetp,
+                            unsigned long *spu_bin_dcookie,
+                            unsigned long spu_ref)
+{
+        unsigned long app_cookie = 0;
+        unsigned int my_offset = 0;
+        struct file *app = NULL;
+        struct vm_area_struct *vma;
+        struct mm_struct *mm = spu->mm;
+
+        if (!mm)
+                goto out;
+
+        down_read(&mm->mmap_sem);
+
+        for (vma = mm->mmap; vma; vma = vma->vm_next) {
+                if (!vma->vm_file)
+                        continue;
+                if (!(vma->vm_flags & VM_EXECUTABLE))
+                        continue;
+                app_cookie = fast_get_dcookie(vma->vm_file->f_dentry,
+                                          vma->vm_file->f_vfsmnt);
+                pr_debug("got dcookie for %s\n",
+                         vma->vm_file->f_dentry->d_name.name);
+                app = vma->vm_file;
+                break;
+        }
+
+        for (vma = mm->mmap; vma; vma = vma->vm_next) {
+                if (vma->vm_start > spu_ref || vma->vm_end <= spu_ref)
+                        continue;
+                my_offset = spu_ref - vma->vm_start;
+                if (!vma->vm_file)
+                        goto fail_no_image_cookie;
+
+                pr_debug("Found spu ELF at %X(object-id:%lx) for file %s\n",
+                         my_offset, spu_ref,
+                         vma->vm_file->f_dentry->d_name.name);
+                *offsetp = my_offset;
+                break;
+        }
+
+        *spu_bin_dcookie = fast_get_dcookie(vma->vm_file->f_dentry,
+                                                 vma->vm_file->f_vfsmnt);
+        pr_debug("got dcookie for %s\n", vma->vm_file->f_dentry->d_name.name);
+
+        up_read(&mm->mmap_sem);
+
+out:
+        return app_cookie;
+
+fail_no_image_cookie:
+        up_read(&mm->mmap_sem);
+
+        printk(KERN_ERR "SPU_PROF: "
+                "%s, line %d: Cannot find dcookie for SPU binary\n",
+                __FUNCTION__, __LINE__);
+        goto out;
+}
+
+
+
+/* This function finds or creates cached context information for the
+ * passed SPU and records SPU context information into the OProfile
+ * event buffer.
+ */
+static int process_context_switch(struct spu *spu, unsigned long objectId)
+{
+        unsigned long flags;
+        int retval;
+        unsigned int offset = 0;
+        unsigned long spu_cookie = 0, app_dcookie;
+
+        retval = prepare_cached_spu_info(spu, objectId);
+        if (retval)
+                goto out;
+
+        /* Get dcookie first because a mutex_lock is taken in that
+         * code path, so interrupts must not be disabled.
+         */
+        app_dcookie = get_exec_dcookie_and_offset(spu, &offset, &spu_cookie, objectId);
+        if (!app_dcookie || !spu_cookie) {
+                retval  = -ENOENT;
+                goto out;
+        }
+
+        /* Record context info in event buffer */
+        spin_lock_irqsave(&buffer_lock, flags);
+        add_event_entry(ESCAPE_CODE);
+        add_event_entry(SPU_CTX_SWITCH_CODE);
+        add_event_entry(spu->number);
+        add_event_entry(spu->pid);
+        add_event_entry(spu->tgid);
+        add_event_entry(app_dcookie);
+        add_event_entry(spu_cookie);
+        add_event_entry(offset);
+        spin_unlock_irqrestore(&buffer_lock, flags);
+        smp_wmb();      /* insure spu event buffer updates are written */
+                        /* don't want entries intermingled... */
+out:
+        return retval;
+}
+
+/*
+ * This function is invoked on either a bind_context or unbind_context.
+ * If called for an unbind_context, the val arg is 0; otherwise,
+ * it is the object-id value for the spu context.
+ * The data arg is of type 'struct spu *'.
+ */
+static int spu_active_notify(struct notifier_block *self, unsigned long val,
+                                void *data)
+{
+        int retval;
+        unsigned long flags;
+        struct spu *the_spu = data;
+
+        pr_debug("SPU event notification arrived\n");
+        if (!val) {
+                spin_lock_irqsave(&cache_lock, flags);
+                retval = release_cached_info(the_spu->number);
+                spin_unlock_irqrestore(&cache_lock, flags);
+        } else {
+                retval = process_context_switch(the_spu, val);
+        }
+        return retval;
+}
+
+static struct notifier_block spu_active = {
+        .notifier_call = spu_active_notify,
+};
+
+static int number_of_online_nodes(void)
+{
+        u32 cpu; u32 tmp;
+        int nodes = 0;
+        for_each_online_cpu(cpu) {
+                tmp = cbe_cpu_to_node(cpu) + 1;
+                if (tmp > nodes)
+                        nodes++;
+        }
+        return nodes;
+}
+
+/* The main purpose of this function is to synchronize
+ * OProfile with SPUFS by registering to be notified of
+ * SPU task switches.
+ *
+ * NOTE: When profiling SPUs, we must ensure that only
+ * spu_sync_start is invoked and not the generic sync_start
+ * in drivers/oprofile/oprof.c.  A return value of
+ * SKIP_GENERIC_SYNC or SYNC_START_ERROR will
+ * accomplish this.
+ */
+int spu_sync_start(void)
+{
+        int k;
+        int ret = SKIP_GENERIC_SYNC;
+        int register_ret;
+        unsigned long flags = 0;
+
+        spu_prof_num_nodes = number_of_online_nodes();
+        num_spu_nodes = spu_prof_num_nodes * 8;
+
+        spin_lock_irqsave(&buffer_lock, flags);
+        add_event_entry(ESCAPE_CODE);
+        add_event_entry(SPU_PROFILING_CODE);
+        add_event_entry(num_spu_nodes);
+        spin_unlock_irqrestore(&buffer_lock, flags);
+
+        /* Register for SPU events  */
+        register_ret = spu_switch_event_register(&spu_active);
+        if (register_ret) {
+                ret = SYNC_START_ERROR;
+                goto out;
+        }
+
+        for (k = 0; k < (MAX_NUMNODES * 8); k++)
+                last_guard_val[k] = 0;
+        pr_debug("spu_sync_start -- running.\n");
+out:
+        return ret;
+}
+
+/* Record SPU program counter samples to the oprofile event buffer. */
+void spu_sync_buffer(int spu_num, unsigned int *samples,
+                     int num_samples)
+{
+        unsigned long long file_offset;
+        unsigned long flags;
+        int i;
+        struct vma_to_fileoffset_map *map;
+        struct spu *the_spu;
+        unsigned long long spu_num_ll = spu_num;
+        unsigned long long spu_num_shifted = spu_num_ll << 32;
+        struct cached_info *c_info;
+
+        /* We need to obtain the cache_lock here because it's
+         * possible that after getting the cached_info, the SPU job
+         * corresponding to this cached_info may end, thus resulting
+         * in the destruction of the cached_info.
+         */
+        spin_lock_irqsave(&cache_lock, flags);
+        c_info = get_cached_info(NULL, spu_num);
+        if (!c_info) {
+                /* This legitimately happens when the SPU task ends before all
+                 * samples are recorded.
+                 * No big deal -- so we just drop a few samples.
+                 */
+                pr_debug("SPU_PROF: No cached SPU contex "
+                          "for SPU #%d. Dropping samples.\n", spu_num);
+                goto out;
+        }
+
+        map = c_info->map;
+        the_spu = c_info->the_spu;
+        spin_lock(&buffer_lock);
+        for (i = 0; i < num_samples; i++) {
+                unsigned int sample = *(samples+i);
+                int grd_val = 0;
+                file_offset = 0;
+                if (sample == 0)
+                        continue;
+                file_offset = vma_map_lookup( map, sample, the_spu, &grd_val);
+
+                /* If overlays are used by this SPU application, the guard
+                 * value is non-zero, indicating which overlay section is in
+                 * use.  We need to discard samples taken during the time
+                 * period which an overlay occurs (i.e., guard value changes).
+                 */
+                if (grd_val && grd_val != last_guard_val[spu_num]) {
+                        last_guard_val[spu_num] = grd_val;
+                        /* Drop the rest of the samples. */
+                        break;
+                }
+
+                add_event_entry(file_offset | spu_num_shifted);
+        }
+        spin_unlock(&buffer_lock);
+out:
+        spin_unlock_irqrestore(&cache_lock, flags);
+}
+
+
+int spu_sync_stop(void)
+{
+        unsigned long flags = 0;
+        int ret = spu_switch_event_unregister(&spu_active);
+        if (ret) {
+                printk(KERN_ERR "SPU_PROF: "
+                        "%s, line %d: spu_switch_event_unregister returned %d\n",
+                        __FUNCTION__, __LINE__, ret);
+                goto out;
+        }
+
+        spin_lock_irqsave(&cache_lock, flags);
+        ret = release_cached_info(RELEASE_ALL);
+        spin_unlock_irqrestore(&cache_lock, flags);
+out:
+        pr_debug("spu_sync_stop -- done.\n");
+        return ret;
+}
+
+
diff --git a/arch/powerpc/oprofile/cell/vma_map.c b/arch/powerpc/oprofile/cell/vma_map.c
new file mode 100644
index 000000000000..76ec1d16aef7
--- /dev/null
+++ b/arch/powerpc/oprofile/cell/vma_map.c
@@ -0,0 +1,287 @@
+/*
+ * Cell Broadband Engine OProfile Support
+ *
+ * (C) Copyright IBM Corporation 2006
+ *
+ * Author: Maynard Johnson <maynardj@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+/* The code in this source file is responsible for generating
+ * vma-to-fileOffset maps for both overlay and non-overlay SPU
+ * applications.
+ */
+
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/elf.h>
+#include "pr_util.h"
+
+
+void vma_map_free(struct vma_to_fileoffset_map *map)
+{
+        while (map) {
+                struct vma_to_fileoffset_map *next = map->next;
+                kfree(map);
+                map = next;
+        }
+}
+
+unsigned int
+vma_map_lookup(struct vma_to_fileoffset_map *map, unsigned int vma,
+               const struct spu *aSpu, int *grd_val)
+{
+        /*
+         * Default the offset to the physical address + a flag value.
+         * Addresses of dynamically generated code can't be found in the vma
+         * map.  For those addresses the flagged value will be sent on to
+         * the user space tools so they can be reported rather than just
+         * thrown away.
+         */
+        u32 offset = 0x10000000 + vma;
+        u32 ovly_grd;
+
+        for (; map; map = map->next) {
+                if (vma < map->vma || vma >= map->vma + map->size)
+                        continue;
+
+                if (map->guard_ptr) {
+                        ovly_grd = *(u32 *)(aSpu->local_store + map->guard_ptr);
+                        if (ovly_grd != map->guard_val)
+                                continue;
+                        *grd_val = ovly_grd;
+                }
+                offset = vma - map->vma + map->offset;
+                break;
+        }
+
+        return offset;
+}
+
+static struct vma_to_fileoffset_map *
+vma_map_add(struct vma_to_fileoffset_map *map, unsigned int vma,
+            unsigned int size, unsigned int offset, unsigned int guard_ptr,
+            unsigned int guard_val)
+{
+        struct vma_to_fileoffset_map *new =
+                kzalloc(sizeof(struct vma_to_fileoffset_map), GFP_KERNEL);
+        if (!new) {
+                printk(KERN_ERR "SPU_PROF: %s, line %d: malloc failed\n",
+                       __FUNCTION__, __LINE__);
+                vma_map_free(map);
+                return NULL;
+        }
+
+        new->next = map;
+        new->vma = vma;
+        new->size = size;
+        new->offset = offset;
+        new->guard_ptr = guard_ptr;
+        new->guard_val = guard_val;
+
+        return new;
+}
+
+
+/* Parse SPE ELF header and generate a list of vma_maps.
+ * A pointer to the first vma_map in the generated list
+ * of vma_maps is returned.  */
+struct vma_to_fileoffset_map *create_vma_map(const struct spu *aSpu,
+                                             unsigned long spu_elf_start)
+{
+        static const unsigned char expected[EI_PAD] = {
+                [EI_MAG0] = ELFMAG0,
+                [EI_MAG1] = ELFMAG1,
+                [EI_MAG2] = ELFMAG2,
+                [EI_MAG3] = ELFMAG3,
+                [EI_CLASS] = ELFCLASS32,
+                [EI_DATA] = ELFDATA2MSB,
+                [EI_VERSION] = EV_CURRENT,
+                [EI_OSABI] = ELFOSABI_NONE
+        };
+
+        int grd_val;
+        struct vma_to_fileoffset_map *map = NULL;
+        struct spu_overlay_info ovly;
+        unsigned int overlay_tbl_offset = -1;
+        unsigned long phdr_start, shdr_start;
+        Elf32_Ehdr ehdr;
+        Elf32_Phdr phdr;
+        Elf32_Shdr shdr, shdr_str;
+        Elf32_Sym sym;
+        int i, j;
+        char name[32];
+
+        unsigned int ovly_table_sym = 0;
+        unsigned int ovly_buf_table_sym = 0;
+        unsigned int ovly_table_end_sym = 0;
+        unsigned int ovly_buf_table_end_sym = 0;
+        unsigned long ovly_table;
+        unsigned int n_ovlys;
+
+        /* Get and validate ELF header.  */
+
+        if (copy_from_user(&ehdr, (void *) spu_elf_start, sizeof (ehdr)))
+                goto fail;
+
+        if (memcmp(ehdr.e_ident, expected, EI_PAD) != 0) {
+                printk(KERN_ERR "SPU_PROF: "
+                       "%s, line %d: Unexpected e_ident parsing SPU ELF\n",
+                       __FUNCTION__, __LINE__);
+                goto fail;
+        }
+        if (ehdr.e_machine != EM_SPU) {
+                printk(KERN_ERR "SPU_PROF: "
+                       "%s, line %d: Unexpected e_machine parsing SPU ELF\n",
+                       __FUNCTION__,  __LINE__);
+                goto fail;
+        }
+        if (ehdr.e_type != ET_EXEC) {
+                printk(KERN_ERR "SPU_PROF: "
+                       "%s, line %d: Unexpected e_type parsing SPU ELF\n",
+                       __FUNCTION__, __LINE__);
+                goto fail;
+        }
+        phdr_start = spu_elf_start + ehdr.e_phoff;
+        shdr_start = spu_elf_start + ehdr.e_shoff;
+
+        /* Traverse program headers.  */
+        for (i = 0; i < ehdr.e_phnum; i++) {
+                if (copy_from_user(&phdr,
+                                   (void *) (phdr_start + i * sizeof(phdr)),
+                                   sizeof(phdr)))
+                        goto fail;
+
+                if (phdr.p_type != PT_LOAD)
+                        continue;
+                if (phdr.p_flags & (1 << 27))
+                        continue;
+
+                map = vma_map_add(map, phdr.p_vaddr, phdr.p_memsz,
+                                  phdr.p_offset, 0, 0);
+                if (!map)
+                        goto fail;
+        }
+
+        pr_debug("SPU_PROF: Created non-overlay maps\n");
+        /* Traverse section table and search for overlay-related symbols.  */
+        for (i = 0; i < ehdr.e_shnum; i++) {
+                if (copy_from_user(&shdr,
+                                   (void *) (shdr_start + i * sizeof(shdr)),
+                                   sizeof(shdr)))
+                        goto fail;
+
+                if (shdr.sh_type != SHT_SYMTAB)
+                        continue;
+                if (shdr.sh_entsize != sizeof (sym))
+                        continue;
+
+                if (copy_from_user(&shdr_str,
+                                   (void *) (shdr_start + shdr.sh_link *
+                                             sizeof(shdr)),
+                                   sizeof(shdr)))
+                        goto fail;
+
+                if (shdr_str.sh_type != SHT_STRTAB)
+                        goto fail;;
+
+                for (j = 0; j < shdr.sh_size / sizeof (sym); j++) {
+                        if (copy_from_user(&sym, (void *) (spu_elf_start +
+                                                       shdr.sh_offset + j *
+                                                           sizeof (sym)),
+                                           sizeof (sym)))
+                                goto fail;
+
+                        if (copy_from_user(name, (void *)
+                                           (spu_elf_start + shdr_str.sh_offset +
+                                            sym.st_name),
+                                           20))
+                                goto fail;
+
+                        if (memcmp(name, "_ovly_table", 12) == 0)
+                                ovly_table_sym = sym.st_value;
+                        if (memcmp(name, "_ovly_buf_table", 16) == 0)
+                                ovly_buf_table_sym = sym.st_value;
+                        if (memcmp(name, "_ovly_table_end", 16) == 0)
+                                ovly_table_end_sym = sym.st_value;
+                        if (memcmp(name, "_ovly_buf_table_end", 20) == 0)
+                                ovly_buf_table_end_sym = sym.st_value;
+                }
+        }
+
+        /* If we don't have overlays, we're done.  */
+        if (ovly_table_sym == 0 || ovly_buf_table_sym == 0
+            || ovly_table_end_sym == 0 || ovly_buf_table_end_sym == 0) {
+                pr_debug("SPU_PROF: No overlay table found\n");
+                goto out;
+        } else {
+                pr_debug("SPU_PROF: Overlay table found\n");
+        }
+
+        /* The _ovly_table symbol represents a table with one entry
+         * per overlay section.  The _ovly_buf_table symbol represents
+         * a table with one entry per overlay region.
+         * The struct spu_overlay_info gives the structure of the _ovly_table
+         * entries.  The structure of _ovly_table_buf is simply one
+         * u32 word per entry.
+         */
+        overlay_tbl_offset = vma_map_lookup(map, ovly_table_sym,
+                                            aSpu, &grd_val);
+        if (overlay_tbl_offset < 0) {
+                printk(KERN_ERR "SPU_PROF: "
+                       "%s, line %d: Error finding SPU overlay table\n",
+                       __FUNCTION__, __LINE__);
+                goto fail;
+        }
+        ovly_table = spu_elf_start + overlay_tbl_offset;
+
+        n_ovlys = (ovly_table_end_sym -
+                   ovly_table_sym) / sizeof (ovly);
+
+        /* Traverse overlay table.  */
+        for (i = 0; i < n_ovlys; i++) {
+                if (copy_from_user(&ovly, (void *)
+                                   (ovly_table + i * sizeof (ovly)),
+                                   sizeof (ovly)))
+                        goto fail;
+
+                /* The ovly.vma/size/offset arguments are analogous to the same
+                 * arguments used above for non-overlay maps.  The final two
+                 * args are referred to as the guard pointer and the guard
+                 * value.
+                 * The guard pointer is an entry in the _ovly_buf_table,
+                 * computed using ovly.buf as the index into the table.  Since
+                 * ovly.buf values begin at '1' to reference the first (or 0th)
+                 * entry in the _ovly_buf_table, the computation subtracts 1
+                 * from ovly.buf.
+                 * The guard value is stored in the _ovly_buf_table entry and
+                 * is an index (starting at 1) back to the _ovly_table entry
+                 * that is pointing at this _ovly_buf_table entry.  So, for
+                 * example, for an overlay scenario with one overlay segment
+                 * and two overlay sections:
+                 *      - Section 1 points to the first entry of the
+                 *        _ovly_buf_table, which contains a guard value
+                 *        of '1', referencing the first (index=0) entry of
+                 *        _ovly_table.
+                 *      - Section 2 points to the second entry of the
+                 *        _ovly_buf_table, which contains a guard value
+                 *        of '2', referencing the second (index=1) entry of
+                 *        _ovly_table.
+                 */
+                map = vma_map_add(map, ovly.vma, ovly.size, ovly.offset,
+                                  ovly_buf_table_sym + (ovly.buf-1) * 4, i+1);
+                if (!map)
+                        goto fail;
+        }
+        goto out;
+
+ fail:
+        map = NULL;
+ out:
+        return map;
+}
diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c
index 1a7ef7e246d2..a28cce1d6c24 100644
--- a/arch/powerpc/oprofile/common.c
+++ b/arch/powerpc/oprofile/common.c
@@ -29,6 +29,8 @@ static struct op_powerpc_model *model;
 static struct op_counter_config ctr[OP_MAX_COUNTER];
 static struct op_system_config sys;
 
+static int op_per_cpu_rc;
+
 static void op_handle_interrupt(struct pt_regs *regs)
 {
         model->handle_interrupt(regs, ctr);
@@ -36,25 +38,41 @@ static void op_handle_interrupt(struct pt_regs *regs)
 
 static void op_powerpc_cpu_setup(void *dummy)
 {
-        model->cpu_setup(ctr);
+        int ret;
+
+        ret = model->cpu_setup(ctr);
+
+        if (ret != 0)
+                op_per_cpu_rc = ret;
 }
 
 static int op_powerpc_setup(void)
 {
         int err;
 
+        op_per_cpu_rc = 0;
+
         /* Grab the hardware */
         err = reserve_pmc_hardware(op_handle_interrupt);
         if (err)
                 return err;
 
         /* Pre-compute the values to stuff in the hardware registers.  */
-        model->reg_setup(ctr, &sys, model->num_counters);
+        op_per_cpu_rc = model->reg_setup(ctr, &sys, model->num_counters);
 
-        /* Configure the registers on all cpus.  */
+        if (op_per_cpu_rc)
+                goto out;
+
+        /* Configure the registers on all cpus.  If an error occurs on one
+         * of the cpus, op_per_cpu_rc will be set to the error */
         on_each_cpu(op_powerpc_cpu_setup, NULL, 0, 1);
 
-        return 0;
+out:    if (op_per_cpu_rc) {
+                /* error on setup release the performance counter hardware */
+                release_pmc_hardware();
+        }
+
+        return op_per_cpu_rc;
 }
 
 static void op_powerpc_shutdown(void)
@@ -64,16 +82,29 @@ static void op_powerpc_shutdown(void)
 
 static void op_powerpc_cpu_start(void *dummy)
 {
-        model->start(ctr);
+        /* If any of the cpus have return an error, set the
+         * global flag to the error so it can be returned
+         * to the generic OProfile caller.
+         */
+        int ret;
+
+        ret = model->start(ctr);
+        if (ret != 0)
+                op_per_cpu_rc = ret;
 }
 
 static int op_powerpc_start(void)
 {
+        op_per_cpu_rc = 0;
+
         if (model->global_start)
-                model->global_start(ctr);
-        if (model->start)
+                return model->global_start(ctr);
+        if (model->start) {
                 on_each_cpu(op_powerpc_cpu_start, NULL, 0, 1);
-        return 0;
+                return op_per_cpu_rc;
+        }
+        return -EIO; /* No start function is defined for this
+                        power architecture */
 }
 
 static inline void op_powerpc_cpu_stop(void *dummy)
@@ -147,11 +178,13 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 
         switch (cur_cpu_spec->oprofile_type) {
 #ifdef CONFIG_PPC64
-#ifdef CONFIG_PPC_CELL_NATIVE
+#ifdef CONFIG_OPROFILE_CELL
                 case PPC_OPROFILE_CELL:
                         if (firmware_has_feature(FW_FEATURE_LPAR))
                                 return -ENODEV;
                         model = &op_model_cell;
+                        ops->sync_start = model->sync_start;
+                        ops->sync_stop = model->sync_stop;
                         break;
 #endif
                 case PPC_OPROFILE_RS64:
diff --git a/arch/powerpc/oprofile/op_model_7450.c b/arch/powerpc/oprofile/op_model_7450.c
index 5d1bbaf35ccb..cc599eb8768b 100644
--- a/arch/powerpc/oprofile/op_model_7450.c
+++ b/arch/powerpc/oprofile/op_model_7450.c
@@ -81,7 +81,7 @@ static void pmc_stop_ctrs(void)
 
 /* Configures the counters on this CPU based on the global
  * settings */
-static void fsl7450_cpu_setup(struct op_counter_config *ctr)
+static int fsl7450_cpu_setup(struct op_counter_config *ctr)
 {
         /* freeze all counters */
         pmc_stop_ctrs();
@@ -89,12 +89,14 @@ static void fsl7450_cpu_setup(struct op_counter_config *ctr)
         mtspr(SPRN_MMCR0, mmcr0_val);
         mtspr(SPRN_MMCR1, mmcr1_val);
         mtspr(SPRN_MMCR2, mmcr2_val);
+
+        return 0;
 }
 
 #define NUM_CTRS 6
 
 /* Configures the global settings for the countes on all CPUs. */
-static void fsl7450_reg_setup(struct op_counter_config *ctr,
+static int fsl7450_reg_setup(struct op_counter_config *ctr,
                              struct op_system_config *sys,
                              int num_ctrs)
 {
@@ -126,10 +128,12 @@ static void fsl7450_reg_setup(struct op_counter_config *ctr,
                 | mmcr1_event6(ctr[5].event);
 
         mmcr2_val = 0;
+
+        return 0;
 }
 
 /* Sets the counters on this CPU to the chosen values, and starts them */
-static void fsl7450_start(struct op_counter_config *ctr)
+static int fsl7450_start(struct op_counter_config *ctr)
 {
         int i;
 
@@ -148,6 +152,8 @@ static void fsl7450_start(struct op_counter_config *ctr)
         pmc_start_ctrs();
 
         oprofile_running = 1;
+
+        return 0;
 }
 
 /* Stop the counters on this CPU */
@@ -193,7 +199,7 @@ static void fsl7450_handle_interrupt(struct pt_regs *regs,
         /* The freeze bit was set by the interrupt. */
         /* Clear the freeze bit, and reenable the interrupt.
          * The counters won't actually start until the rfi clears
-         * the PMM bit */
+         * the PM/M bit */
         pmc_start_ctrs();
 }
 
diff --git a/arch/powerpc/oprofile/op_model_cell.c b/arch/powerpc/oprofile/op_model_cell.c
index c29293befba9..d928b54f3a0f 100644
--- a/arch/powerpc/oprofile/op_model_cell.c
+++ b/arch/powerpc/oprofile/op_model_cell.c
@@ -5,8 +5,8 @@
  *
  * Author: David Erb (djerb@us.ibm.com)
  * Modifications:
- *         Carl Love <carll@us.ibm.com>
- *         Maynard Johnson <maynardj@us.ibm.com>
+ *         Carl Love <carll@us.ibm.com>
+ *         Maynard Johnson <maynardj@us.ibm.com>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -38,12 +38,25 @@
 
 #include "../platforms/cell/interrupt.h"
 #include "../platforms/cell/cbe_regs.h"
+#include "cell/pr_util.h"
+
+static void cell_global_stop_spu(void);
+
+/*
+ * spu_cycle_reset is the number of cycles between samples.
+ * This variable is used for SPU profiling and should ONLY be set
+ * at the beginning of cell_reg_setup; otherwise, it's read-only.
+ */
+static unsigned int spu_cycle_reset;
+
+#define NUM_SPUS_PER_NODE    8
+#define SPU_CYCLES_EVENT_NUM 2  /*  event number for SPU_CYCLES */
 
 #define PPU_CYCLES_EVENT_NUM 1  /*  event number for CYCLES */
-#define PPU_CYCLES_GRP_NUM   1  /* special group number for identifying
-                                 * PPU_CYCLES event
-                                 */
-#define CBE_COUNT_ALL_CYCLES 0x42800000 /* PPU cycle event specifier */
+#define PPU_CYCLES_GRP_NUM   1  /* special group number for identifying
+                                 * PPU_CYCLES event
+                                 */
+#define CBE_COUNT_ALL_CYCLES 0x42800000 /* PPU cycle event specifier */
 
 #define NUM_THREADS 2         /* number of physical threads in
                                * physical processor
@@ -51,6 +64,7 @@
 #define NUM_TRACE_BUS_WORDS 4
 #define NUM_INPUT_BUS_WORDS 2
 
+#define MAX_SPU_COUNT 0xFFFFFF  /* maximum 24 bit LFSR value */
 
 struct pmc_cntrl_data {
         unsigned long vcntr;
@@ -62,11 +76,10 @@ struct pmc_cntrl_data {
 /*
  * ibm,cbe-perftools rtas parameters
  */
-
 struct pm_signal {
         u16 cpu;                /* Processor to modify */
-        u16 sub_unit;           /* hw subunit this applies to (if applicable) */
-        short int signal_group; /* Signal Group to Enable/Disable */
+        u16 sub_unit;           /* hw subunit this applies to (if applicable)*/
+        short int signal_group; /* Signal Group to Enable/Disable */
         u8 bus_word;            /* Enable/Disable on this Trace/Trigger/Event
                                  * Bus Word(s) (bitmask)
                                  */
@@ -112,21 +125,42 @@ static DEFINE_PER_CPU(unsigned long[NR_PHYS_CTRS], pmc_values);
 
 static struct pmc_cntrl_data pmc_cntrl[NUM_THREADS][NR_PHYS_CTRS];
 
-/* Interpetation of hdw_thread:
+/*
+ * The CELL profiling code makes rtas calls to setup the debug bus to
+ * route the performance signals.  Additionally, SPU profiling requires
+ * a second rtas call to setup the hardware to capture the SPU PCs.
+ * The EIO error value is returned if the token lookups or the rtas
+ * call fail.  The EIO error number is the best choice of the existing
+ * error numbers.  The probability of rtas related error is very low.  But
+ * by returning EIO and printing additional information to dmsg the user
+ * will know that OProfile did not start and dmesg will tell them why.
+ * OProfile does not support returning errors on Stop.  Not a huge issue
+ * since failure to reset the debug bus or stop the SPU PC collection is
+ * not a fatel issue.  Chances are if the Stop failed, Start doesn't work
+ * either.
+ */
+
+/*
+ * Interpetation of hdw_thread:
  * 0 - even virtual cpus 0, 2, 4,...
  * 1 - odd virtual cpus 1, 3, 5, ...
+ *
+ * FIXME: this is strictly wrong, we need to clean this up in a number
+ * of places. It works for now. -arnd
  */
 static u32 hdw_thread;
 
 static u32 virt_cntr_inter_mask;
 static struct timer_list timer_virt_cntr;
 
-/* pm_signal needs to be global since it is initialized in
+/*
+ * pm_signal needs to be global since it is initialized in
  * cell_reg_setup at the time when the necessary information
  * is available.
  */
 static struct pm_signal pm_signal[NR_PHYS_CTRS];
-static int pm_rtas_token;
+static int pm_rtas_token;    /* token for debug bus setup call */
+static int spu_rtas_token;   /* token for SPU cycle profiling */
 
 static u32 reset_value[NR_PHYS_CTRS];
 static int num_counters;
@@ -147,8 +181,8 @@ rtas_ibm_cbe_perftools(int subfunc, int passthru,
 {
         u64 paddr = __pa(address);
 
-        return rtas_call(pm_rtas_token, 5, 1, NULL, subfunc, passthru,
-                         paddr >> 32, paddr & 0xffffffff, length);
+        return rtas_call(pm_rtas_token, 5, 1, NULL, subfunc,
+                         passthru, paddr >> 32, paddr & 0xffffffff, length);
 }
 
 static void pm_rtas_reset_signals(u32 node)
@@ -156,12 +190,13 @@ static void pm_rtas_reset_signals(u32 node)
         int ret;
         struct pm_signal pm_signal_local;
 
-        /*  The debug bus is being set to the passthru disable state.
-         *  However, the FW still expects atleast one legal signal routing
-         *  entry or it will return an error on the arguments.  If we don't
-         *  supply a valid entry, we must ignore all return values.  Ignoring
-         *  all return values means we might miss an error we should be
-         *  concerned about.
+        /*
+         * The debug bus is being set to the passthru disable state.
+         * However, the FW still expects atleast one legal signal routing
+         * entry or it will return an error on the arguments.   If we don't
+         * supply a valid entry, we must ignore all return values.  Ignoring
+         * all return values means we might miss an error we should be
+         * concerned about.
          */
 
         /*  fw expects physical cpu #. */
@@ -175,18 +210,24 @@ static void pm_rtas_reset_signals(u32 node)
                                      &pm_signal_local,
                                      sizeof(struct pm_signal));
 
-        if (ret)
+        if (unlikely(ret))
+                /*
+                 * Not a fatal error. For Oprofile stop, the oprofile
+                 * functions do not support returning an error for
+                 * failure to stop OProfile.
+                 */
                 printk(KERN_WARNING "%s: rtas returned: %d\n",
                        __FUNCTION__, ret);
 }
 
-static void pm_rtas_activate_signals(u32 node, u32 count)
+static int pm_rtas_activate_signals(u32 node, u32 count)
 {
         int ret;
         int i, j;
         struct pm_signal pm_signal_local[NR_PHYS_CTRS];
 
-        /* There is no debug setup required for the cycles event.
+        /*
+         * There is no debug setup required for the cycles event.
          * Note that only events in the same group can be used.
          * Otherwise, there will be conflicts in correctly routing
          * the signals on the debug bus.  It is the responsiblity
@@ -213,10 +254,14 @@ static void pm_rtas_activate_signals(u32 node, u32 count)
                                              pm_signal_local,
                                              i * sizeof(struct pm_signal));
 
-                if (ret)
+                if (unlikely(ret)) {
                         printk(KERN_WARNING "%s: rtas returned: %d\n",
                                __FUNCTION__, ret);
+                        return -EIO;
+                }
         }
+
+        return 0;
 }
 
 /*
@@ -260,11 +305,12 @@ static void set_pm_event(u32 ctr, int event, u32 unit_mask)
         pm_regs.pm07_cntrl[ctr] |= PM07_CTR_POLARITY(polarity);
         pm_regs.pm07_cntrl[ctr] |= PM07_CTR_INPUT_CONTROL(input_control);
 
-        /* Some of the islands signal selection is based on 64 bit words.
+        /*
+         * Some of the islands signal selection is based on 64 bit words.
          * The debug bus words are 32 bits, the input words to the performance
          * counters are defined as 32 bits.  Need to convert the 64 bit island
          * specification to the appropriate 32 input bit and bus word for the
-         * performance counter event selection.  See the CELL Performance
+         * performance counter event selection.  See the CELL Performance
          * monitoring signals manual and the Perf cntr hardware descriptions
          * for the details.
          */
@@ -298,6 +344,7 @@ static void set_pm_event(u32 ctr, int event, u32 unit_mask)
                                         input_bus[j] = i;
                                         pm_regs.group_control |=
                                             (i << (31 - i));
+
                                         break;
                                 }
                         }
@@ -309,7 +356,8 @@ out:
 
 static void write_pm_cntrl(int cpu)
 {
-        /* Oprofile will use 32 bit counters, set bits 7:10 to 0
+        /*
+         * Oprofile will use 32 bit counters, set bits 7:10 to 0
          * pmregs.pm_cntrl is a global
          */
 
@@ -326,7 +374,8 @@ static void write_pm_cntrl(int cpu)
         if (pm_regs.pm_cntrl.freeze == 1)
                 val |= CBE_PM_FREEZE_ALL_CTRS;
 
-        /* Routine set_count_mode must be called previously to set
+        /*
+         * Routine set_count_mode must be called previously to set
          * the count mode based on the user selection of user and kernel.
          */
         val |= CBE_PM_COUNT_MODE_SET(pm_regs.pm_cntrl.count_mode);
@@ -336,7 +385,8 @@ static void write_pm_cntrl(int cpu)
 static inline void
 set_count_mode(u32 kernel, u32 user)
 {
-        /* The user must specify user and kernel if they want them. If
+        /*
+         * The user must specify user and kernel if they want them. If
          *  neither is specified, OProfile will count in hypervisor mode.
          *  pm_regs.pm_cntrl is a global
          */
@@ -364,7 +414,7 @@ static inline void enable_ctr(u32 cpu, u32 ctr, u32 * pm07_cntrl)
 
 /*
  * Oprofile is expected to collect data on all CPUs simultaneously.
- * However, there is one set of performance counters per node.  There are
+ * However, there is one set of performance counters per node.  There are
  * two hardware threads or virtual CPUs on each node.  Hence, OProfile must
  * multiplex in time the performance counter collection on the two virtual
  * CPUs.  The multiplexing of the performance counters is done by this
@@ -377,19 +427,19 @@ static inline void enable_ctr(u32 cpu, u32 ctr, u32 * pm07_cntrl)
  * pair of per-cpu arrays is used for storing the previous and next
  * pmc values for a given node.
  * NOTE: We use the per-cpu variable to improve cache performance.
+ *
+ * This routine will alternate loading the virtual counters for
+ * virtual CPUs
  */
 static void cell_virtual_cntr(unsigned long data)
 {
-        /* This routine will alternate loading the virtual counters for
-         * virtual CPUs
-         */
         int i, prev_hdw_thread, next_hdw_thread;
         u32 cpu;
         unsigned long flags;
 
-        /* Make sure that the interrupt_hander and
-         * the virt counter are not both playing with
-         * the counters on the same node.
+        /*
+         * Make sure that the interrupt_hander and the virt counter are
+         * not both playing with the counters on the same node.
          */
 
         spin_lock_irqsave(&virt_cntr_lock, flags);
@@ -400,22 +450,25 @@ static void cell_virtual_cntr(unsigned long data)
         hdw_thread = 1 ^ hdw_thread;
         next_hdw_thread = hdw_thread;
 
-        for (i = 0; i < num_counters; i++)
-        /* There are some per thread events.  Must do the
+        /*
+         * There are some per thread events.  Must do the
          * set event, for the thread that is being started
          */
+        for (i = 0; i < num_counters; i++)
                 set_pm_event(i,
                         pmc_cntrl[next_hdw_thread][i].evnts,
                         pmc_cntrl[next_hdw_thread][i].masks);
 
-        /* The following is done only once per each node, but
+        /*
+         * The following is done only once per each node, but
          * we need cpu #, not node #, to pass to the cbe_xxx functions.
          */
         for_each_online_cpu(cpu) {
                 if (cbe_get_hw_thread_id(cpu))
                         continue;
 
-                /* stop counters, save counter values, restore counts
+                /*
+                 * stop counters, save counter values, restore counts
                  * for previous thread
                  */
                 cbe_disable_pm(cpu);
@@ -428,7 +481,7 @@ static void cell_virtual_cntr(unsigned long data)
                             == 0xFFFFFFFF)
                                 /* If the cntr value is 0xffffffff, we must
                                  * reset that to 0xfffffff0 when the current
-                                 * thread is restarted.  This will generate a
+                                 * thread is restarted.  This will generate a
                                  * new interrupt and make sure that we never
                                  * restore the counters to the max value.  If
                                  * the counters were restored to the max value,
@@ -444,13 +497,15 @@ static void cell_virtual_cntr(unsigned long data)
                                                       next_hdw_thread)[i]);
                 }
 
-                /* Switch to the other thread. Change the interrupt
+                /*
+                 * Switch to the other thread. Change the interrupt
                  * and control regs to be scheduled on the CPU
                  * corresponding to the thread to execute.
                  */
                 for (i = 0; i < num_counters; i++) {
                         if (pmc_cntrl[next_hdw_thread][i].enabled) {
-                                /* There are some per thread events.
+                                /*
+                                 * There are some per thread events.
                                  * Must do the set event, enable_cntr
                                  * for each cpu.
                                  */
@@ -482,17 +537,42 @@ static void start_virt_cntrs(void)
 }
 
 /* This function is called once for all cpus combined */
-static void
-cell_reg_setup(struct op_counter_config *ctr,
-               struct op_system_config *sys, int num_ctrs)
+static int cell_reg_setup(struct op_counter_config *ctr,
+                        struct op_system_config *sys, int num_ctrs)
 {
         int i, j, cpu;
+        spu_cycle_reset = 0;
+
+        if (ctr[0].event == SPU_CYCLES_EVENT_NUM) {
+                spu_cycle_reset = ctr[0].count;
+
+                /*
+                 * Each node will need to make the rtas call to start
+                 * and stop SPU profiling.  Get the token once and store it.
+                 */
+                spu_rtas_token = rtas_token("ibm,cbe-spu-perftools");
+
+                if (unlikely(spu_rtas_token == RTAS_UNKNOWN_SERVICE)) {
+                        printk(KERN_ERR
+                               "%s: rtas token ibm,cbe-spu-perftools unknown\n",
+                               __FUNCTION__);
+                        return -EIO;
+                }
+        }
 
         pm_rtas_token = rtas_token("ibm,cbe-perftools");
-        if (pm_rtas_token == RTAS_UNKNOWN_SERVICE) {
-                printk(KERN_WARNING "%s: RTAS_UNKNOWN_SERVICE\n",
+
+        /*
+         * For all events excetp PPU CYCLEs, each node will need to make
+         * the rtas cbe-perftools call to setup and reset the debug bus.
+         * Make the token lookup call once and store it in the global
+         * variable pm_rtas_token.
+         */
+        if (unlikely(pm_rtas_token == RTAS_UNKNOWN_SERVICE)) {
+                printk(KERN_ERR
+                       "%s: rtas token ibm,cbe-perftools unknown\n",
                        __FUNCTION__);
-                goto out;
+                return -EIO;
         }
 
         num_counters = num_ctrs;
@@ -520,7 +600,8 @@ cell_reg_setup(struct op_counter_config *ctr,
                         per_cpu(pmc_values, j)[i] = 0;
         }
 
-        /* Setup the thread 1 events, map the thread 0 event to the
+        /*
+         * Setup the thread 1 events, map the thread 0 event to the
          * equivalent thread 1 event.
          */
         for (i = 0; i < num_ctrs; ++i) {
@@ -544,9 +625,10 @@ cell_reg_setup(struct op_counter_config *ctr,
         for (i = 0; i < NUM_INPUT_BUS_WORDS; i++)
                 input_bus[i] = 0xff;
 
-        /* Our counters count up, and "count" refers to
+        /*
+         * Our counters count up, and "count" refers to
          * how much before the next interrupt, and we interrupt
-         * on overflow.  So we calculate the starting value
+         * on overflow.  So we calculate the starting value
          * which will give us "count" until overflow.
          * Then we set the events on the enabled counters.
          */
@@ -569,28 +651,27 @@ cell_reg_setup(struct op_counter_config *ctr,
                 for (i = 0; i < num_counters; ++i) {
                         per_cpu(pmc_values, cpu)[i] = reset_value[i];
                 }
-out:
-        ;
+
+        return 0;
 }
 
+
+
 /* This function is called once for each cpu */
-static void cell_cpu_setup(struct op_counter_config *cntr)
+static int cell_cpu_setup(struct op_counter_config *cntr)
 {
         u32 cpu = smp_processor_id();
         u32 num_enabled = 0;
         int i;
 
+        if (spu_cycle_reset)
+                return 0;
+
         /* There is one performance monitor per processor chip (i.e. node),
          * so we only need to perform this function once per node.
          */
         if (cbe_get_hw_thread_id(cpu))
-                goto out;
-
-        if (pm_rtas_token == RTAS_UNKNOWN_SERVICE) {
-                printk(KERN_WARNING "%s: RTAS_UNKNOWN_SERVICE\n",
-                       __FUNCTION__);
-                goto out;
-        }
+                return 0;
 
         /* Stop all counters */
         cbe_disable_pm(cpu);
@@ -609,16 +690,286 @@ static void cell_cpu_setup(struct op_counter_config *cntr)
                 }
         }
 
-        pm_rtas_activate_signals(cbe_cpu_to_node(cpu), num_enabled);
+        /*
+         * The pm_rtas_activate_signals will return -EIO if the FW
+         * call failed.
+         */
+        return pm_rtas_activate_signals(cbe_cpu_to_node(cpu), num_enabled);
+}
+
+#define ENTRIES  303
+#define MAXLFSR  0xFFFFFF
+
+/* precomputed table of 24 bit LFSR values */
+static int initial_lfsr[] = {
+ 8221349, 12579195, 5379618, 10097839, 7512963, 7519310, 3955098, 10753424,
+ 15507573, 7458917, 285419, 2641121, 9780088, 3915503, 6668768, 1548716,
+ 4885000, 8774424, 9650099, 2044357, 2304411, 9326253, 10332526, 4421547,
+ 3440748, 10179459, 13332843, 10375561, 1313462, 8375100, 5198480, 6071392,
+ 9341783, 1526887, 3985002, 1439429, 13923762, 7010104, 11969769, 4547026,
+ 2040072, 4025602, 3437678, 7939992, 11444177, 4496094, 9803157, 10745556,
+ 3671780, 4257846, 5662259, 13196905, 3237343, 12077182, 16222879, 7587769,
+ 14706824, 2184640, 12591135, 10420257, 7406075, 3648978, 11042541, 15906893,
+ 11914928, 4732944, 10695697, 12928164, 11980531, 4430912, 11939291, 2917017,
+ 6119256, 4172004, 9373765, 8410071, 14788383, 5047459, 5474428, 1737756,
+ 15967514, 13351758, 6691285, 8034329, 2856544, 14394753, 11310160, 12149558,
+ 7487528, 7542781, 15668898, 12525138, 12790975, 3707933, 9106617, 1965401,
+ 16219109, 12801644, 2443203, 4909502, 8762329, 3120803, 6360315, 9309720,
+ 15164599, 10844842, 4456529, 6667610, 14924259, 884312, 6234963, 3326042,
+ 15973422, 13919464, 5272099, 6414643, 3909029, 2764324, 5237926, 4774955,
+ 10445906, 4955302, 5203726, 10798229, 11443419, 2303395, 333836, 9646934,
+ 3464726, 4159182, 568492, 995747, 10318756, 13299332, 4836017, 8237783,
+ 3878992, 2581665, 11394667, 5672745, 14412947, 3159169, 9094251, 16467278,
+ 8671392, 15230076, 4843545, 7009238, 15504095, 1494895, 9627886, 14485051,
+ 8304291, 252817, 12421642, 16085736, 4774072, 2456177, 4160695, 15409741,
+ 4902868, 5793091, 13162925, 16039714, 782255, 11347835, 14884586, 366972,
+ 16308990, 11913488, 13390465, 2958444, 10340278, 1177858, 1319431, 10426302,
+ 2868597, 126119, 5784857, 5245324, 10903900, 16436004, 3389013, 1742384,
+ 14674502, 10279218, 8536112, 10364279, 6877778, 14051163, 1025130, 6072469,
+ 1988305, 8354440, 8216060, 16342977, 13112639, 3976679, 5913576, 8816697,
+ 6879995, 14043764, 3339515, 9364420, 15808858, 12261651, 2141560, 5636398,
+ 10345425, 10414756, 781725, 6155650, 4746914, 5078683, 7469001, 6799140,
+ 10156444, 9667150, 10116470, 4133858, 2121972, 1124204, 1003577, 1611214,
+ 14304602, 16221850, 13878465, 13577744, 3629235, 8772583, 10881308, 2410386,
+ 7300044, 5378855, 9301235, 12755149, 4977682, 8083074, 10327581, 6395087,
+ 9155434, 15501696, 7514362, 14520507, 15808945, 3244584, 4741962, 9658130,
+ 14336147, 8654727, 7969093, 15759799, 14029445, 5038459, 9894848, 8659300,
+ 13699287, 8834306, 10712885, 14753895, 10410465, 3373251, 309501, 9561475,
+ 5526688, 14647426, 14209836, 5339224, 207299, 14069911, 8722990, 2290950,
+ 3258216, 12505185, 6007317, 9218111, 14661019, 10537428, 11731949, 9027003,
+ 6641507, 9490160, 200241, 9720425, 16277895, 10816638, 1554761, 10431375,
+ 7467528, 6790302, 3429078, 14633753, 14428997, 11463204, 3576212, 2003426,
+ 6123687, 820520, 9992513, 15784513, 5778891, 6428165, 8388607
+};
+
+/*
+ * The hardware uses an LFSR counting sequence to determine when to capture
+ * the SPU PCs.  An LFSR sequence is like a puesdo random number sequence
+ * where each number occurs once in the sequence but the sequence is not in
+ * numerical order. The SPU PC capture is done when the LFSR sequence reaches
+ * the last value in the sequence.  Hence the user specified value N
+ * corresponds to the LFSR number that is N from the end of the sequence.
+ *
+ * To avoid the time to compute the LFSR, a lookup table is used.  The 24 bit
+ * LFSR sequence is broken into four ranges.  The spacing of the precomputed
+ * values is adjusted in each range so the error between the user specifed
+ * number (N) of events between samples and the actual number of events based
+ * on the precomputed value will be les then about 6.2%.  Note, if the user
+ * specifies N < 2^16, the LFSR value that is 2^16 from the end will be used.
+ * This is to prevent the loss of samples because the trace buffer is full.
+ *
+ *         User specified N                  Step between          Index in
+ *                                       precomputed values      precomputed
+ *                                                                  table
+ * 0                to  2^16-1                  ----                  0
+ * 2^16     to  2^16+2^19-1             2^12                1 to 128
+ * 2^16+2^19        to  2^16+2^19+2^22-1        2^15              129 to 256
+ * 2^16+2^19+2^22  to   2^24-1                  2^18              257 to 302
+ *
+ *
+ * For example, the LFSR values in the second range are computed for 2^16,
+ * 2^16+2^12, ... , 2^19-2^16, 2^19 and stored in the table at indicies
+ * 1, 2,..., 127, 128.
+ *
+ * The 24 bit LFSR value for the nth number in the sequence can be
+ * calculated using the following code:
+ *
+ * #define size 24
+ * int calculate_lfsr(int n)
+ * {
+ *      int i;
+ *      unsigned int newlfsr0;
+ *      unsigned int lfsr = 0xFFFFFF;
+ *      unsigned int howmany = n;
+ *
+ *      for (i = 2; i < howmany + 2; i++) {
+ *              newlfsr0 = (((lfsr >> (size - 1 - 0)) & 1) ^
+ *              ((lfsr >> (size - 1 - 1)) & 1) ^
+ *              (((lfsr >> (size - 1 - 6)) & 1) ^
+ *              ((lfsr >> (size - 1 - 23)) & 1)));
+ *
+ *              lfsr >>= 1;
+ *              lfsr = lfsr | (newlfsr0 << (size - 1));
+ *      }
+ *      return lfsr;
+ * }
+ */
+
+#define V2_16  (0x1 << 16)
+#define V2_19  (0x1 << 19)
+#define V2_22  (0x1 << 22)
+
+static int calculate_lfsr(int n)
+{
+        /*
+         * The ranges and steps are in powers of 2 so the calculations
+         * can be done using shifts rather then divide.
+         */
+        int index;
+
+        if ((n >> 16) == 0)
+                index = 0;
+        else if (((n - V2_16) >> 19) == 0)
+                index = ((n - V2_16) >> 12) + 1;
+        else if (((n - V2_16 - V2_19) >> 22) == 0)
+                index = ((n - V2_16 - V2_19) >> 15 ) + 1 + 128;
+        else if (((n - V2_16 - V2_19 - V2_22) >> 24) == 0)
+                index = ((n - V2_16 - V2_19 - V2_22) >> 18 ) + 1 + 256;
+        else
+                index = ENTRIES-1;
+
+        /* make sure index is valid */
+        if ((index > ENTRIES) || (index < 0))
+                index = ENTRIES-1;
+
+        return initial_lfsr[index];
+}
+
+static int pm_rtas_activate_spu_profiling(u32 node)
+{
+        int ret, i;
+        struct pm_signal pm_signal_local[NR_PHYS_CTRS];
+
+        /*
+         * Set up the rtas call to configure the debug bus to
+         * route the SPU PCs.  Setup the pm_signal for each SPU
+         */
+        for (i = 0; i < NUM_SPUS_PER_NODE; i++) {
+                pm_signal_local[i].cpu = node;
+                pm_signal_local[i].signal_group = 41;
+                /* spu i on word (i/2) */
+                pm_signal_local[i].bus_word = 1 << i / 2;
+                /* spu i */
+                pm_signal_local[i].sub_unit = i;
+                pm_signal_local[i].bit = 63;
+        }
+
+        ret = rtas_ibm_cbe_perftools(SUBFUNC_ACTIVATE,
+                                     PASSTHRU_ENABLE, pm_signal_local,
+                                     (NUM_SPUS_PER_NODE
+                                      * sizeof(struct pm_signal)));
+
+        if (unlikely(ret)) {
+                printk(KERN_WARNING "%s: rtas returned: %d\n",
+                       __FUNCTION__, ret);
+                return -EIO;
+        }
+
+        return 0;
+}
+
+#ifdef CONFIG_CPU_FREQ
+static int
+oprof_cpufreq_notify(struct notifier_block *nb, unsigned long val, void *data)
+{
+        int ret = 0;
+        struct cpufreq_freqs *frq = data;
+        if ((val == CPUFREQ_PRECHANGE && frq->old < frq->new) ||
+            (val == CPUFREQ_POSTCHANGE && frq->old > frq->new) ||
+            (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE))
+                set_spu_profiling_frequency(frq->new, spu_cycle_reset);
+        return ret;
+}
+
+static struct notifier_block cpu_freq_notifier_block = {
+        .notifier_call  = oprof_cpufreq_notify
+};
+#endif
+
+static int cell_global_start_spu(struct op_counter_config *ctr)
+{
+        int subfunc;
+        unsigned int lfsr_value;
+        int cpu;
+        int ret;
+        int rtas_error;
+        unsigned int cpu_khzfreq = 0;
+
+        /* The SPU profiling uses time-based profiling based on
+         * cpu frequency, so if configured with the CPU_FREQ
+         * option, we should detect frequency changes and react
+         * accordingly.
+         */
+#ifdef CONFIG_CPU_FREQ
+        ret = cpufreq_register_notifier(&cpu_freq_notifier_block,
+                                        CPUFREQ_TRANSITION_NOTIFIER);
+        if (ret < 0)
+                /* this is not a fatal error */
+                printk(KERN_ERR "CPU freq change registration failed: %d\n",
+                       ret);
+
+        else
+                cpu_khzfreq = cpufreq_quick_get(smp_processor_id());
+#endif
+
+        set_spu_profiling_frequency(cpu_khzfreq, spu_cycle_reset);
+
+        for_each_online_cpu(cpu) {
+                if (cbe_get_hw_thread_id(cpu))
+                        continue;
+
+                /*
+                 * Setup SPU cycle-based profiling.
+                 * Set perf_mon_control bit 0 to a zero before
+                 * enabling spu collection hardware.
+                 */
+                cbe_write_pm(cpu, pm_control, 0);
+
+                if (spu_cycle_reset > MAX_SPU_COUNT)
+                        /* use largest possible value */
+                        lfsr_value = calculate_lfsr(MAX_SPU_COUNT-1);
+                else
+                        lfsr_value = calculate_lfsr(spu_cycle_reset);
+
+                /* must use a non zero value. Zero disables data collection. */
+                if (lfsr_value == 0)
+                        lfsr_value = calculate_lfsr(1);
+
+                lfsr_value = lfsr_value << 8; /* shift lfsr to correct
+                                                * register location
+                                                */
+
+                /* debug bus setup */
+                ret = pm_rtas_activate_spu_profiling(cbe_cpu_to_node(cpu));
+
+                if (unlikely(ret)) {
+                        rtas_error = ret;
+                        goto out;
+                }
+
+
+                subfunc = 2;    /* 2 - activate SPU tracing, 3 - deactivate */
+
+                /* start profiling */
+                ret = rtas_call(spu_rtas_token, 3, 1, NULL, subfunc,
+                  cbe_cpu_to_node(cpu), lfsr_value);
+
+                if (unlikely(ret != 0)) {
+                        printk(KERN_ERR
+                               "%s: rtas call ibm,cbe-spu-perftools failed, return = %d\n",
+                               __FUNCTION__, ret);
+                        rtas_error = -EIO;
+                        goto out;
+                }
+        }
+
+        rtas_error = start_spu_profiling(spu_cycle_reset);
+        if (rtas_error)
+                goto out_stop;
+
+        oprofile_running = 1;
+        return 0;
+
+out_stop:
+        cell_global_stop_spu();         /* clean up the PMU/debug bus */
 out:
-        ;
+        return rtas_error;
 }
 
-static void cell_global_start(struct op_counter_config *ctr)
+static int cell_global_start_ppu(struct op_counter_config *ctr)
 {
-        u32 cpu;
+        u32 cpu, i;
         u32 interrupt_mask = 0;
-        u32 i;
 
         /* This routine gets called once for the system.
          * There is one performance monitor per node, so we
@@ -651,19 +1002,79 @@ static void cell_global_start(struct op_counter_config *ctr)
         oprofile_running = 1;
         smp_wmb();
 
-        /* NOTE: start_virt_cntrs will result in cell_virtual_cntr() being
-         * executed which manipulates the PMU.  We start the "virtual counter"
+        /*
+         * NOTE: start_virt_cntrs will result in cell_virtual_cntr() being
+         * executed which manipulates the PMU.  We start the "virtual counter"
          * here so that we do not need to synchronize access to the PMU in
          * the above for-loop.
          */
         start_virt_cntrs();
+
+        return 0;
 }
 
-static void cell_global_stop(void)
+static int cell_global_start(struct op_counter_config *ctr)
+{
+        if (spu_cycle_reset)
+                return cell_global_start_spu(ctr);
+        else
+                return cell_global_start_ppu(ctr);
+}
+
+/*
+ * Note the generic OProfile stop calls do not support returning
+ * an error on stop.  Hence, will not return an error if the FW
+ * calls fail on stop.  Failure to reset the debug bus is not an issue.
+ * Failure to disable the SPU profiling is not an issue.  The FW calls
+ * to enable the performance counters and debug bus will work even if
+ * the hardware was not cleanly reset.
+ */
+static void cell_global_stop_spu(void)
+{
+        int subfunc, rtn_value;
+        unsigned int lfsr_value;
+        int cpu;
+
+        oprofile_running = 0;
+
+#ifdef CONFIG_CPU_FREQ
+        cpufreq_unregister_notifier(&cpu_freq_notifier_block,
+                                    CPUFREQ_TRANSITION_NOTIFIER);
+#endif
+
+        for_each_online_cpu(cpu) {
+                if (cbe_get_hw_thread_id(cpu))
+                        continue;
+
+                subfunc = 3;    /*
+                                 * 2 - activate SPU tracing,
+                                 * 3 - deactivate
+                                 */
+                lfsr_value = 0x8f100000;
+
+                rtn_value = rtas_call(spu_rtas_token, 3, 1, NULL,
+                                      subfunc, cbe_cpu_to_node(cpu),
+                                      lfsr_value);
+
+                if (unlikely(rtn_value != 0)) {
+                        printk(KERN_ERR
+                               "%s: rtas call ibm,cbe-spu-perftools failed, return = %d\n",
+                               __FUNCTION__, rtn_value);
+                }
+
+                /* Deactivate the signals */
+                pm_rtas_reset_signals(cbe_cpu_to_node(cpu));
+        }
+
+        stop_spu_profiling();
+}
+
+static void cell_global_stop_ppu(void)
 {
         int cpu;
 
-        /* This routine will be called once for the system.
+        /*
+         * This routine will be called once for the system.
          * There is one performance monitor per node, so we
          * only need to perform this function once per node.
          */
@@ -687,8 +1098,16 @@ static void cell_global_stop(void)
         }
 }
 
-static void
-cell_handle_interrupt(struct pt_regs *regs, struct op_counter_config *ctr)
+static void cell_global_stop(void)
+{
+        if (spu_cycle_reset)
+                cell_global_stop_spu();
+        else
+                cell_global_stop_ppu();
+}
+
+static void cell_handle_interrupt(struct pt_regs *regs,
+                                struct op_counter_config *ctr)
 {
         u32 cpu;
         u64 pc;
@@ -699,13 +1118,15 @@ cell_handle_interrupt(struct pt_regs *regs, struct op_counter_config *ctr)
 
         cpu = smp_processor_id();
 
-        /* Need to make sure the interrupt handler and the virt counter
+        /*
+         * Need to make sure the interrupt handler and the virt counter
          * routine are not running at the same time. See the
          * cell_virtual_cntr() routine for additional comments.
          */
         spin_lock_irqsave(&virt_cntr_lock, flags);
 
-        /* Need to disable and reenable the performance counters
+        /*
+         * Need to disable and reenable the performance counters
          * to get the desired behavior from the hardware.  This
          * is hardware specific.
          */
@@ -714,7 +1135,8 @@ cell_handle_interrupt(struct pt_regs *regs, struct op_counter_config *ctr)
 
         interrupt_mask = cbe_get_and_clear_pm_interrupts(cpu);
 
-        /* If the interrupt mask has been cleared, then the virt cntr
+        /*
+         * If the interrupt mask has been cleared, then the virt cntr
          * has cleared the interrupt.  When the thread that generated
          * the interrupt is restored, the data count will be restored to
          * 0xffffff0 to cause the interrupt to be regenerated.
@@ -732,18 +1154,20 @@ cell_handle_interrupt(struct pt_regs *regs, struct op_counter_config *ctr)
                         }
                 }
 
-                /* The counters were frozen by the interrupt.
+                /*
+                 * The counters were frozen by the interrupt.
                  * Reenable the interrupt and restart the counters.
                  * If there was a race between the interrupt handler and
-                 * the virtual counter routine.  The virutal counter
+                 * the virtual counter routine.  The virutal counter
                  * routine may have cleared the interrupts.  Hence must
                  * use the virt_cntr_inter_mask to re-enable the interrupts.
                  */
                 cbe_enable_pm_interrupts(cpu, hdw_thread,
                                          virt_cntr_inter_mask);
 
-                /* The writes to the various performance counters only writes
-                 * to a latch.  The new values (interrupt setting bits, reset
+                /*
+                 * The writes to the various performance counters only writes
+                 * to a latch.  The new values (interrupt setting bits, reset
                  * counter value etc.) are not copied to the actual registers
                  * until the performance monitor is enabled.  In order to get
                  * this to work as desired, the permormance monitor needs to
@@ -755,10 +1179,33 @@ cell_handle_interrupt(struct pt_regs *regs, struct op_counter_config *ctr)
         spin_unlock_irqrestore(&virt_cntr_lock, flags);
 }
 
+/*
+ * This function is called from the generic OProfile
+ * driver.  When profiling PPUs, we need to do the
+ * generic sync start; otherwise, do spu_sync_start.
+ */
+static int cell_sync_start(void)
+{
+        if (spu_cycle_reset)
+                return spu_sync_start();
+        else
+                return DO_GENERIC_SYNC;
+}
+
+static int cell_sync_stop(void)
+{
+        if (spu_cycle_reset)
+                return spu_sync_stop();
+        else
+                return 1;
+}
+
 struct op_powerpc_model op_model_cell = {
         .reg_setup = cell_reg_setup,
         .cpu_setup = cell_cpu_setup,
         .global_start = cell_global_start,
         .global_stop = cell_global_stop,
+        .sync_start = cell_sync_start,
+        .sync_stop = cell_sync_stop,
         .handle_interrupt = cell_handle_interrupt,
 };
diff --git a/arch/powerpc/oprofile/op_model_fsl_booke.c b/arch/powerpc/oprofile/op_model_fsl_booke.c
index 2267eb8c661b..183a28bb1812 100644
--- a/arch/powerpc/oprofile/op_model_fsl_booke.c
+++ b/arch/powerpc/oprofile/op_model_fsl_booke.c
@@ -244,7 +244,7 @@ static void dump_pmcs(void)
                         mfpmr(PMRN_PMLCA3), mfpmr(PMRN_PMLCB3));
 }
 
-static void fsl_booke_cpu_setup(struct op_counter_config *ctr)
+static int fsl_booke_cpu_setup(struct op_counter_config *ctr)
 {
         int i;
 
@@ -258,9 +258,11 @@ static void fsl_booke_cpu_setup(struct op_counter_config *ctr)
 
                 set_pmc_user_kernel(i, ctr[i].user, ctr[i].kernel);
         }
+
+        return 0;
 }
 
-static void fsl_booke_reg_setup(struct op_counter_config *ctr,
+static int fsl_booke_reg_setup(struct op_counter_config *ctr,
                              struct op_system_config *sys,
                              int num_ctrs)
 {
@@ -276,9 +278,10 @@ static void fsl_booke_reg_setup(struct op_counter_config *ctr,
         for (i = 0; i < num_counters; ++i)
                 reset_value[i] = 0x80000000UL - ctr[i].count;
 
+        return 0;
 }
 
-static void fsl_booke_start(struct op_counter_config *ctr)
+static int fsl_booke_start(struct op_counter_config *ctr)
 {
         int i;
 
@@ -308,6 +311,8 @@ static void fsl_booke_start(struct op_counter_config *ctr)
 
         pr_debug("start on cpu %d, pmgc0 %x\n", smp_processor_id(),
                         mfpmr(PMRN_PMGC0));
+
+        return 0;
 }
 
 static void fsl_booke_stop(void)
diff --git a/arch/powerpc/oprofile/op_model_pa6t.c b/arch/powerpc/oprofile/op_model_pa6t.c
index e8a56b0adadc..c40de461fd4e 100644
--- a/arch/powerpc/oprofile/op_model_pa6t.c
+++ b/arch/powerpc/oprofile/op_model_pa6t.c
@@ -89,7 +89,7 @@ static inline void ctr_write(unsigned int i, u64 val)
 
 
 /* precompute the values to stuff in the hardware registers */
-static void pa6t_reg_setup(struct op_counter_config *ctr,
+static int pa6t_reg_setup(struct op_counter_config *ctr,
                            struct op_system_config *sys,
                            int num_ctrs)
 {
@@ -135,10 +135,12 @@ static void pa6t_reg_setup(struct op_counter_config *ctr,
                 pr_debug("reset_value for pmc%u inited to 0x%lx\n",
                                  pmc, reset_value[pmc]);
         }
+
+        return 0;
 }
 
 /* configure registers on this cpu */
-static void pa6t_cpu_setup(struct op_counter_config *ctr)
+static int pa6t_cpu_setup(struct op_counter_config *ctr)
 {
         u64 mmcr0 = mmcr0_val;
         u64 mmcr1 = mmcr1_val;
@@ -154,9 +156,11 @@ static void pa6t_cpu_setup(struct op_counter_config *ctr)
                 mfspr(SPRN_PA6T_MMCR0));
         pr_debug("setup on cpu %d, mmcr1 %016lx\n", smp_processor_id(),
                 mfspr(SPRN_PA6T_MMCR1));
+
+        return 0;
 }
 
-static void pa6t_start(struct op_counter_config *ctr)
+static int pa6t_start(struct op_counter_config *ctr)
 {
         int i;
 
@@ -174,6 +178,8 @@ static void pa6t_start(struct op_counter_config *ctr)
         oprofile_running = 1;
 
         pr_debug("start on cpu %d, mmcr0 %lx\n", smp_processor_id(), mmcr0);
+
+        return 0;
 }
 
 static void pa6t_stop(void)
diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c
index a7c206b665af..cddc250a6a5c 100644
--- a/arch/powerpc/oprofile/op_model_power4.c
+++ b/arch/powerpc/oprofile/op_model_power4.c
@@ -32,7 +32,7 @@ static u32 mmcr0_val;
 static u64 mmcr1_val;
 static u64 mmcra_val;
 
-static void power4_reg_setup(struct op_counter_config *ctr,
+static int power4_reg_setup(struct op_counter_config *ctr,
                              struct op_system_config *sys,
                              int num_ctrs)
 {
@@ -60,6 +60,8 @@ static void power4_reg_setup(struct op_counter_config *ctr,
                 mmcr0_val &= ~MMCR0_PROBLEM_DISABLE;
         else
                 mmcr0_val |= MMCR0_PROBLEM_DISABLE;
+
+        return 0;
 }
 
 extern void ppc64_enable_pmcs(void);
@@ -84,7 +86,7 @@ static inline int mmcra_must_set_sample(void)
         return 0;
 }
 
-static void power4_cpu_setup(struct op_counter_config *ctr)
+static int power4_cpu_setup(struct op_counter_config *ctr)
 {
         unsigned int mmcr0 = mmcr0_val;
         unsigned long mmcra = mmcra_val;
@@ -111,9 +113,11 @@ static void power4_cpu_setup(struct op_counter_config *ctr)
             mfspr(SPRN_MMCR1));
         dbg("setup on cpu %d, mmcra %lx\n", smp_processor_id(),
             mfspr(SPRN_MMCRA));
+
+        return 0;
 }
 
-static void power4_start(struct op_counter_config *ctr)
+static int power4_start(struct op_counter_config *ctr)
 {
         int i;
         unsigned int mmcr0;
@@ -148,6 +152,7 @@ static void power4_start(struct op_counter_config *ctr)
         oprofile_running = 1;
 
         dbg("start on cpu %d, mmcr0 %x\n", smp_processor_id(), mmcr0);
+        return 0;
 }
 
 static void power4_stop(void)
diff --git a/arch/powerpc/oprofile/op_model_rs64.c b/arch/powerpc/oprofile/op_model_rs64.c
index c731acbfb2a5..a20afe45d936 100644
--- a/arch/powerpc/oprofile/op_model_rs64.c
+++ b/arch/powerpc/oprofile/op_model_rs64.c
@@ -88,7 +88,7 @@ static unsigned long reset_value[OP_MAX_COUNTER];
 
 static int num_counters;
 
-static void rs64_reg_setup(struct op_counter_config *ctr,
+static int rs64_reg_setup(struct op_counter_config *ctr,
                            struct op_system_config *sys,
                            int num_ctrs)
 {
@@ -100,9 +100,10 @@ static void rs64_reg_setup(struct op_counter_config *ctr,
                 reset_value[i] = 0x80000000UL - ctr[i].count;
 
         /* XXX setup user and kernel profiling */
+        return 0;
 }
 
-static void rs64_cpu_setup(struct op_counter_config *ctr)
+static int rs64_cpu_setup(struct op_counter_config *ctr)
 {
         unsigned int mmcr0;
 
@@ -125,9 +126,11 @@ static void rs64_cpu_setup(struct op_counter_config *ctr)
             mfspr(SPRN_MMCR0));
         dbg("setup on cpu %d, mmcr1 %lx\n", smp_processor_id(),
             mfspr(SPRN_MMCR1));
+
+        return 0;
 }
 
-static void rs64_start(struct op_counter_config *ctr)
+static int rs64_start(struct op_counter_config *ctr)
 {
         int i;
         unsigned int mmcr0;
@@ -155,6 +158,7 @@ static void rs64_start(struct op_counter_config *ctr)
         mtspr(SPRN_MMCR0, mmcr0);
 
         dbg("start on cpu %d, mmcr0 %x\n", smp_processor_id(), mmcr0);
+        return 0;
 }
 
 static void rs64_stop(void)
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 33545d352e92..932538a93c2b 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -272,4 +272,14 @@ config CPM2
           you wish to build a kernel for a machine with a CPM2 coprocessor
           on it (826x, 827x, 8560).
 
+config AXON_RAM
+        tristate "Axon DDR2 memory device driver"
+        depends on PPC_IBM_CELL_BLADE
+        default m
+        help
+          It registers one block device per Axon's DDR2 memory bank found
+          on a system. Block devices are called axonram?, their major and
+          minor numbers are available in /proc/devices, /proc/partitions or
+          in /sys/block/axonram?/dev.
+
 endmenu
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index b8b5fde94668..e4b2aee53a73 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -215,7 +215,7 @@ config NOT_COHERENT_CACHE
         depends on 4xx || 8xx || E200
         default y
 
-config CONFIG_CHECK_CACHE_COHERENCY
+config CHECK_CACHE_COHERENCY
         bool
 
 endmenu
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 9b2b386ccf48..ac8032034fb8 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -73,4 +73,14 @@ config CBE_CPUFREQ
           For details, take a look at <file:Documentation/cpu-freq/>.
           If you don't have such processor, say N
 
+config CBE_CPUFREQ_PMI
+        tristate "CBE frequency scaling using PMI interface"
+        depends on CBE_CPUFREQ && PPC_PMI && EXPERIMENTAL
+        default n
+        help
+          Select this, if you want to use the PMI interface
+          to switch frequencies. Using PMI, the
+          processor will not only be able to run at lower speed,
+          but also at lower core voltage.
+
 endmenu
diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile
index 869af89df6ff..f88a7c76f296 100644
--- a/arch/powerpc/platforms/cell/Makefile
+++ b/arch/powerpc/platforms/cell/Makefile
@@ -4,7 +4,9 @@ obj-$(CONFIG_PPC_CELL_NATIVE)		+= interrupt.o iommu.o setup.o \
 obj-$(CONFIG_CBE_RAS)                   += ras.o
 
 obj-$(CONFIG_CBE_THERM)                 += cbe_thermal.o
-obj-$(CONFIG_CBE_CPUFREQ)               += cbe_cpufreq.o
+obj-$(CONFIG_CBE_CPUFREQ_PMI)           += cbe_cpufreq_pmi.o
+obj-$(CONFIG_CBE_CPUFREQ)               += cbe-cpufreq.o
+cbe-cpufreq-y                           += cbe_cpufreq_pervasive.o cbe_cpufreq.o
 
 ifeq ($(CONFIG_SMP),y)
 obj-$(CONFIG_PPC_CELL_NATIVE)           += smp.o
@@ -23,3 +25,5 @@ obj-$(CONFIG_SPU_BASE)			+= spu_callbacks.o spu_base.o \
                                            $(spu-priv1-y) \
                                            $(spu-manage-y) \
                                            spufs/
+
+obj-$(CONFIG_PCI_MSI)                   += axon_msi.o
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
new file mode 100644
index 000000000000..4c9ab5b70bae
--- /dev/null
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -0,0 +1,445 @@
+/*
+ * Copyright 2007, Michael Ellerman, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <linux/reboot.h>
+
+#include <asm/dcr.h>
+#include <asm/machdep.h>
+#include <asm/prom.h>
+
+
+/*
+ * MSIC registers, specified as offsets from dcr_base
+ */
+#define MSIC_CTRL_REG   0x0
+
+/* Base Address registers specify FIFO location in BE memory */
+#define MSIC_BASE_ADDR_HI_REG   0x3
+#define MSIC_BASE_ADDR_LO_REG   0x4
+
+/* Hold the read/write offsets into the FIFO */
+#define MSIC_READ_OFFSET_REG    0x5
+#define MSIC_WRITE_OFFSET_REG   0x6
+
+
+/* MSIC control register flags */
+#define MSIC_CTRL_ENABLE                0x0001
+#define MSIC_CTRL_FIFO_FULL_ENABLE      0x0002
+#define MSIC_CTRL_IRQ_ENABLE            0x0008
+#define MSIC_CTRL_FULL_STOP_ENABLE      0x0010
+
+/*
+ * The MSIC can be configured to use a FIFO of 32KB, 64KB, 128KB or 256KB.
+ * Currently we're using a 64KB FIFO size.
+ */
+#define MSIC_FIFO_SIZE_SHIFT    16
+#define MSIC_FIFO_SIZE_BYTES    (1 << MSIC_FIFO_SIZE_SHIFT)
+
+/*
+ * To configure the FIFO size as (1 << n) bytes, we write (n - 15) into bits
+ * 8-9 of the MSIC control reg.
+ */
+#define MSIC_CTRL_FIFO_SIZE     (((MSIC_FIFO_SIZE_SHIFT - 15) << 8) & 0x300)
+
+/*
+ * We need to mask the read/write offsets to make sure they stay within
+ * the bounds of the FIFO. Also they should always be 16-byte aligned.
+ */
+#define MSIC_FIFO_SIZE_MASK     ((MSIC_FIFO_SIZE_BYTES - 1) & ~0xFu)
+
+/* Each entry in the FIFO is 16 bytes, the first 4 bytes hold the irq # */
+#define MSIC_FIFO_ENTRY_SIZE    0x10
+
+
+struct axon_msic {
+        struct device_node *dn;
+        struct irq_host *irq_host;
+        __le32 *fifo;
+        dcr_host_t dcr_host;
+        struct list_head list;
+        u32 read_offset;
+        u32 dcr_base;
+};
+
+static LIST_HEAD(axon_msic_list);
+
+static void msic_dcr_write(struct axon_msic *msic, unsigned int dcr_n, u32 val)
+{
+        pr_debug("axon_msi: dcr_write(0x%x, 0x%x)\n", val, dcr_n);
+
+        dcr_write(msic->dcr_host, msic->dcr_base + dcr_n, val);
+}
+
+static u32 msic_dcr_read(struct axon_msic *msic, unsigned int dcr_n)
+{
+        return dcr_read(msic->dcr_host, msic->dcr_base + dcr_n);
+}
+
+static void axon_msi_cascade(unsigned int irq, struct irq_desc *desc)
+{
+        struct axon_msic *msic = get_irq_data(irq);
+        u32 write_offset, msi;
+        int idx;
+
+        write_offset = msic_dcr_read(msic, MSIC_WRITE_OFFSET_REG);
+        pr_debug("axon_msi: original write_offset 0x%x\n", write_offset);
+
+        /* write_offset doesn't wrap properly, so we have to mask it */
+        write_offset &= MSIC_FIFO_SIZE_MASK;
+
+        while (msic->read_offset != write_offset) {
+                idx  = msic->read_offset / sizeof(__le32);
+                msi  = le32_to_cpu(msic->fifo[idx]);
+                msi &= 0xFFFF;
+
+                pr_debug("axon_msi: woff %x roff %x msi %x\n",
+                          write_offset, msic->read_offset, msi);
+
+                msic->read_offset += MSIC_FIFO_ENTRY_SIZE;
+                msic->read_offset &= MSIC_FIFO_SIZE_MASK;
+
+                if (msi < NR_IRQS && irq_map[msi].host == msic->irq_host)
+                        generic_handle_irq(msi);
+                else
+                        pr_debug("axon_msi: invalid irq 0x%x!\n", msi);
+        }
+
+        desc->chip->eoi(irq);
+}
+
+static struct axon_msic *find_msi_translator(struct pci_dev *dev)
+{
+        struct irq_host *irq_host;
+        struct device_node *dn, *tmp;
+        const phandle *ph;
+        struct axon_msic *msic = NULL;
+
+        dn = pci_device_to_OF_node(dev);
+        if (!dn) {
+                dev_dbg(&dev->dev, "axon_msi: no pci_dn found\n");
+                return NULL;
+        }
+
+        for (; dn; tmp = of_get_parent(dn), of_node_put(dn), dn = tmp) {
+                ph = of_get_property(dn, "msi-translator", NULL);
+                if (ph)
+                        break;
+        }
+
+        if (!ph) {
+                dev_dbg(&dev->dev,
+                        "axon_msi: no msi-translator property found\n");
+                goto out_error;
+        }
+
+        tmp = dn;
+        dn = of_find_node_by_phandle(*ph);
+        if (!dn) {
+                dev_dbg(&dev->dev,
+                        "axon_msi: msi-translator doesn't point to a node\n");
+                goto out_error;
+        }
+
+        irq_host = irq_find_host(dn);
+        if (!irq_host) {
+                dev_dbg(&dev->dev, "axon_msi: no irq_host found for node %s\n",
+                        dn->full_name);
+                goto out_error;
+        }
+
+        msic = irq_host->host_data;
+
+out_error:
+        of_node_put(dn);
+        of_node_put(tmp);
+
+        return msic;
+}
+
+static int axon_msi_check_device(struct pci_dev *dev, int nvec, int type)
+{
+        if (!find_msi_translator(dev))
+                return -ENODEV;
+
+        return 0;
+}
+
+static int setup_msi_msg_address(struct pci_dev *dev, struct msi_msg *msg)
+{
+        struct device_node *dn, *tmp;
+        struct msi_desc *entry;
+        int len;
+        const u32 *prop;
+
+        dn = pci_device_to_OF_node(dev);
+        if (!dn) {
+                dev_dbg(&dev->dev, "axon_msi: no pci_dn found\n");
+                return -ENODEV;
+        }
+
+        entry = list_first_entry(&dev->msi_list, struct msi_desc, list);
+
+        for (; dn; tmp = of_get_parent(dn), of_node_put(dn), dn = tmp) {
+                if (entry->msi_attrib.is_64) {
+                        prop = of_get_property(dn, "msi-address-64", &len);
+                        if (prop)
+                                break;
+                }
+
+                prop = of_get_property(dn, "msi-address-32", &len);
+                if (prop)
+                        break;
+        }
+
+        if (!prop) {
+                dev_dbg(&dev->dev,
+                        "axon_msi: no msi-address-(32|64) properties found\n");
+                return -ENOENT;
+        }
+
+        switch (len) {
+        case 8:
+                msg->address_hi = prop[0];
+                msg->address_lo = prop[1];
+                break;
+        case 4:
+                msg->address_hi = 0;
+                msg->address_lo = prop[0];
+                break;
+        default:
+                dev_dbg(&dev->dev,
+                        "axon_msi: malformed msi-address-(32|64) property\n");
+                of_node_put(dn);
+                return -EINVAL;
+        }
+
+        of_node_put(dn);
+
+        return 0;
+}
+
+static int axon_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+        unsigned int virq, rc;
+        struct msi_desc *entry;
+        struct msi_msg msg;
+        struct axon_msic *msic;
+
+        msic = find_msi_translator(dev);
+        if (!msic)
+                return -ENODEV;
+
+        rc = setup_msi_msg_address(dev, &msg);
+        if (rc)
+                return rc;
+
+        /* We rely on being able to stash a virq in a u16 */
+        BUILD_BUG_ON(NR_IRQS > 65536);
+
+        list_for_each_entry(entry, &dev->msi_list, list) {
+                virq = irq_create_direct_mapping(msic->irq_host);
+                if (virq == NO_IRQ) {
+                        dev_warn(&dev->dev,
+                                 "axon_msi: virq allocation failed!\n");
+                        return -1;
+                }
+                dev_dbg(&dev->dev, "axon_msi: allocated virq 0x%x\n", virq);
+
+                set_irq_msi(virq, entry);
+                msg.data = virq;
+                write_msi_msg(virq, &msg);
+        }
+
+        return 0;
+}
+
+static void axon_msi_teardown_msi_irqs(struct pci_dev *dev)
+{
+        struct msi_desc *entry;
+
+        dev_dbg(&dev->dev, "axon_msi: tearing down msi irqs\n");
+
+        list_for_each_entry(entry, &dev->msi_list, list) {
+                if (entry->irq == NO_IRQ)
+                        continue;
+
+                set_irq_msi(entry->irq, NULL);
+                irq_dispose_mapping(entry->irq);
+        }
+}
+
+static struct irq_chip msic_irq_chip = {
+        .mask           = mask_msi_irq,
+        .unmask         = unmask_msi_irq,
+        .shutdown       = unmask_msi_irq,
+        .typename       = "AXON-MSI",
+};
+
+static int msic_host_map(struct irq_host *h, unsigned int virq,
+                         irq_hw_number_t hw)
+{
+        set_irq_chip_and_handler(virq, &msic_irq_chip, handle_simple_irq);
+
+        return 0;
+}
+
+static int msic_host_match(struct irq_host *host, struct device_node *dn)
+{
+        struct axon_msic *msic = host->host_data;
+
+        return msic->dn == dn;
+}
+
+static struct irq_host_ops msic_host_ops = {
+        .match  = msic_host_match,
+        .map    = msic_host_map,
+};
+
+static int axon_msi_notify_reboot(struct notifier_block *nb,
+                                  unsigned long code, void *data)
+{
+        struct axon_msic *msic;
+        u32 tmp;
+
+        list_for_each_entry(msic, &axon_msic_list, list) {
+                pr_debug("axon_msi: disabling %s\n", msic->dn->full_name);
+                tmp  = msic_dcr_read(msic, MSIC_CTRL_REG);
+                tmp &= ~MSIC_CTRL_ENABLE & ~MSIC_CTRL_IRQ_ENABLE;
+                msic_dcr_write(msic, MSIC_CTRL_REG, tmp);
+        }
+
+        return 0;
+}
+
+static struct notifier_block axon_msi_reboot_notifier = {
+        .notifier_call = axon_msi_notify_reboot
+};
+
+static int axon_msi_setup_one(struct device_node *dn)
+{
+        struct page *page;
+        struct axon_msic *msic;
+        unsigned int virq;
+        int dcr_len;
+
+        pr_debug("axon_msi: setting up dn %s\n", dn->full_name);
+
+        msic = kzalloc(sizeof(struct axon_msic), GFP_KERNEL);
+        if (!msic) {
+                printk(KERN_ERR "axon_msi: couldn't allocate msic for %s\n",
+                       dn->full_name);
+                goto out;
+        }
+
+        msic->dcr_base = dcr_resource_start(dn, 0);
+        dcr_len = dcr_resource_len(dn, 0);
+
+        if (msic->dcr_base == 0 || dcr_len == 0) {
+                printk(KERN_ERR
+                       "axon_msi: couldn't parse dcr properties on %s\n",
+                        dn->full_name);
+                goto out;
+        }
+
+        msic->dcr_host = dcr_map(dn, msic->dcr_base, dcr_len);
+        if (!DCR_MAP_OK(msic->dcr_host)) {
+                printk(KERN_ERR "axon_msi: dcr_map failed for %s\n",
+                       dn->full_name);
+                goto out_free_msic;
+        }
+
+        page = alloc_pages_node(of_node_to_nid(dn), GFP_KERNEL,
+                                get_order(MSIC_FIFO_SIZE_BYTES));
+        if (!page) {
+                printk(KERN_ERR "axon_msi: couldn't allocate fifo for %s\n",
+                       dn->full_name);
+                goto out_free_msic;
+        }
+
+        msic->fifo = page_address(page);
+
+        msic->irq_host = irq_alloc_host(IRQ_HOST_MAP_NOMAP, NR_IRQS,
+                                        &msic_host_ops, 0);
+        if (!msic->irq_host) {
+                printk(KERN_ERR "axon_msi: couldn't allocate irq_host for %s\n",
+                       dn->full_name);
+                goto out_free_fifo;
+        }
+
+        msic->irq_host->host_data = msic;
+
+        virq = irq_of_parse_and_map(dn, 0);
+        if (virq == NO_IRQ) {
+                printk(KERN_ERR "axon_msi: irq parse and map failed for %s\n",
+                       dn->full_name);
+                goto out_free_host;
+        }
+
+        msic->dn = of_node_get(dn);
+
+        set_irq_data(virq, msic);
+        set_irq_chained_handler(virq, axon_msi_cascade);
+        pr_debug("axon_msi: irq 0x%x setup for axon_msi\n", virq);
+
+        /* Enable the MSIC hardware */
+        msic_dcr_write(msic, MSIC_BASE_ADDR_HI_REG, (u64)msic->fifo >> 32);
+        msic_dcr_write(msic, MSIC_BASE_ADDR_LO_REG,
+                                  (u64)msic->fifo & 0xFFFFFFFF);
+        msic_dcr_write(msic, MSIC_CTRL_REG,
+                        MSIC_CTRL_IRQ_ENABLE | MSIC_CTRL_ENABLE |
+                        MSIC_CTRL_FIFO_SIZE);
+
+        list_add(&msic->list, &axon_msic_list);
+
+        printk(KERN_DEBUG "axon_msi: setup MSIC on %s\n", dn->full_name);
+
+        return 0;
+
+out_free_host:
+        kfree(msic->irq_host);
+out_free_fifo:
+        __free_pages(virt_to_page(msic->fifo), get_order(MSIC_FIFO_SIZE_BYTES));
+out_free_msic:
+        kfree(msic);
+out:
+
+        return -1;
+}
+
+static int axon_msi_init(void)
+{
+        struct device_node *dn;
+        int found = 0;
+
+        pr_debug("axon_msi: initialising ...\n");
+
+        for_each_compatible_node(dn, NULL, "ibm,axon-msic") {
+                if (axon_msi_setup_one(dn) == 0)
+                        found++;
+        }
+
+        if (found) {
+                ppc_md.setup_msi_irqs = axon_msi_setup_msi_irqs;
+                ppc_md.teardown_msi_irqs = axon_msi_teardown_msi_irqs;
+                ppc_md.msi_check_device = axon_msi_check_device;
+
+                register_reboot_notifier(&axon_msi_reboot_notifier);
+
+                pr_debug("axon_msi: registered callbacks!\n");
+        }
+
+        return 0;
+}
+arch_initcall(axon_msi_init);
diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq.c b/arch/powerpc/platforms/cell/cbe_cpufreq.c
index ab511d5b65a4..0b6e8ee85ab1 100644
--- a/arch/powerpc/platforms/cell/cbe_cpufreq.c
+++ b/arch/powerpc/platforms/cell/cbe_cpufreq.c
@@ -1,7 +1,7 @@
 /*
  * cpufreq driver for the cell processor
  *
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
+ * (C) Copyright IBM Deutschland Entwicklung GmbH 2005-2007
  *
  * Author: Christian Krafft <krafft@de.ibm.com>
  *
@@ -21,18 +21,11 @@
  */
 
 #include <linux/cpufreq.h>
-#include <linux/timer.h>
-
-#include <asm/hw_irq.h>
-#include <asm/io.h>
 #include <asm/machdep.h>
-#include <asm/processor.h>
-#include <asm/prom.h>
-#include <asm/time.h>
-#include <asm/pmi.h>
 #include <asm/of_platform.h>
-
+#include <asm/prom.h>
 #include "cbe_regs.h"
+#include "cbe_cpufreq.h"
 
 static DEFINE_MUTEX(cbe_switch_mutex);
 
@@ -50,159 +43,24 @@ static struct cpufreq_frequency_table cbe_freqs[] = {
         {0,     CPUFREQ_TABLE_END},
 };
 
-/* to write to MIC register */
-static u64 MIC_Slow_Fast_Timer_table[] = {
-        [0 ... 7] = 0x007fc00000000000ull,
-};
-
-/* more values for the MIC */
-static u64 MIC_Slow_Next_Timer_table[] = {
-        0x0000240000000000ull,
-        0x0000268000000000ull,
-        0x000029C000000000ull,
-        0x00002D0000000000ull,
-        0x0000300000000000ull,
-        0x0000334000000000ull,
-        0x000039C000000000ull,
-        0x00003FC000000000ull,
-};
-
-static unsigned int pmi_frequency_limit = 0;
 /*
  * hardware specific functions
  */
 
-static struct of_device *pmi_dev;
-
-#ifdef CONFIG_PPC_PMI
-static int set_pmode_pmi(int cpu, unsigned int pmode)
-{
-        int ret;
-        pmi_message_t pmi_msg;
-#ifdef DEBUG
-        u64 time;
-#endif
-
-        pmi_msg.type = PMI_TYPE_FREQ_CHANGE;
-        pmi_msg.data1 = cbe_cpu_to_node(cpu);
-        pmi_msg.data2 = pmode;
-
-#ifdef DEBUG
-        time = (u64) get_cycles();
-#endif
-
-        pmi_send_message(pmi_dev, pmi_msg);
-        ret = pmi_msg.data2;
-
-        pr_debug("PMI returned slow mode %d\n", ret);
-
-#ifdef DEBUG
-        time = (u64) get_cycles() - time; /* actual cycles (not cpu cycles!) */
-        time = 1000000000 * time / CLOCK_TICK_RATE; /* time in ns (10^-9) */
-        pr_debug("had to wait %lu ns for a transition\n", time);
-#endif
-        return ret;
-}
-#endif
-
-static int get_pmode(int cpu)
+static int set_pmode(unsigned int cpu, unsigned int slow_mode)
 {
-        int ret;
-        struct cbe_pmd_regs __iomem *pmd_regs;
-
-        pmd_regs = cbe_get_cpu_pmd_regs(cpu);
-        ret = in_be64(&pmd_regs->pmsr) & 0x07;
-
-        return ret;
-}
-
-static int set_pmode_reg(int cpu, unsigned int pmode)
-{
-        struct cbe_pmd_regs __iomem *pmd_regs;
-        struct cbe_mic_tm_regs __iomem *mic_tm_regs;
-        u64 flags;
-        u64 value;
-
-        local_irq_save(flags);
-
-        mic_tm_regs = cbe_get_cpu_mic_tm_regs(cpu);
-        pmd_regs = cbe_get_cpu_pmd_regs(cpu);
-
-        pr_debug("pm register is mapped at %p\n", &pmd_regs->pmcr);
-        pr_debug("mic register is mapped at %p\n", &mic_tm_regs->slow_fast_timer_0);
-
-        out_be64(&mic_tm_regs->slow_fast_timer_0, MIC_Slow_Fast_Timer_table[pmode]);
-        out_be64(&mic_tm_regs->slow_fast_timer_1, MIC_Slow_Fast_Timer_table[pmode]);
-
-        out_be64(&mic_tm_regs->slow_next_timer_0, MIC_Slow_Next_Timer_table[pmode]);
-        out_be64(&mic_tm_regs->slow_next_timer_1, MIC_Slow_Next_Timer_table[pmode]);
-
-        value = in_be64(&pmd_regs->pmcr);
-        /* set bits to zero */
-        value &= 0xFFFFFFFFFFFFFFF8ull;
-        /* set bits to next pmode */
-        value |= pmode;
-
-        out_be64(&pmd_regs->pmcr, value);
-
-        /* wait until new pmode appears in status register */
-        value = in_be64(&pmd_regs->pmsr) & 0x07;
-        while(value != pmode) {
-                cpu_relax();
-                value = in_be64(&pmd_regs->pmsr) & 0x07;
-        }
-
-        local_irq_restore(flags);
-
-        return 0;
-}
+        int rc;
 
-static int set_pmode(int cpu, unsigned int slow_mode) {
-#ifdef CONFIG_PPC_PMI
-        if (pmi_dev)
-                return set_pmode_pmi(cpu, slow_mode);
+        if (cbe_cpufreq_has_pmi)
+                rc = cbe_cpufreq_set_pmode_pmi(cpu, slow_mode);
         else
-#endif
-                return set_pmode_reg(cpu, slow_mode);
-}
-
-static void cbe_cpufreq_handle_pmi(struct of_device *dev, pmi_message_t pmi_msg)
-{
-        u8 cpu;
-        u8 cbe_pmode_new;
-
-        BUG_ON(pmi_msg.type != PMI_TYPE_FREQ_CHANGE);
+                rc = cbe_cpufreq_set_pmode(cpu, slow_mode);
 
-        cpu = cbe_node_to_cpu(pmi_msg.data1);
-        cbe_pmode_new = pmi_msg.data2;
+        pr_debug("register contains slow mode %d\n", cbe_cpufreq_get_pmode(cpu));
 
-        pmi_frequency_limit = cbe_freqs[cbe_pmode_new].frequency;
-
-        pr_debug("cbe_handle_pmi: max freq=%d\n", pmi_frequency_limit);
-}
-
-static int pmi_notifier(struct notifier_block *nb,
-                                       unsigned long event, void *data)
-{
-        struct cpufreq_policy *policy = data;
-
-        if (event != CPUFREQ_INCOMPATIBLE)
-                return 0;
-
-        cpufreq_verify_within_limits(policy, 0, pmi_frequency_limit);
-        return 0;
+        return rc;
 }
 
-static struct notifier_block pmi_notifier_block = {
-        .notifier_call = pmi_notifier,
-};
-
-static struct pmi_handler cbe_pmi_handler = {
-        .type                   = PMI_TYPE_FREQ_CHANGE,
-        .handle_pmi_message     = cbe_cpufreq_handle_pmi,
-};
-
-
 /*
  * cpufreq functions
  */
@@ -221,8 +79,19 @@ static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
         pr_debug("init cpufreq on CPU %d\n", policy->cpu);
 
+        /*
+         * Let's check we can actually get to the CELL regs
+         */
+        if (!cbe_get_cpu_pmd_regs(policy->cpu) ||
+            !cbe_get_cpu_mic_tm_regs(policy->cpu)) {
+                pr_info("invalid CBE regs pointers for cpufreq\n");
+                return -EINVAL;
+        }
+
         max_freqp = of_get_property(cpu, "clock-frequency", NULL);
 
+        of_node_put(cpu);
+
         if (!max_freqp)
                 return -EINVAL;
 
@@ -239,10 +108,12 @@ static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy)
         }
 
         policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
-        /* if DEBUG is enabled set_pmode() measures the correct latency of a transition */
+
+        /* if DEBUG is enabled set_pmode() measures the latency
+         * of a transition */
         policy->cpuinfo.transition_latency = 25000;
 
-        cur_pmode = get_pmode(policy->cpu);
+        cur_pmode = cbe_cpufreq_get_pmode(policy->cpu);
         pr_debug("current pmode is at %d\n",cur_pmode);
 
         policy->cur = cbe_freqs[cur_pmode].frequency;
@@ -253,21 +124,13 @@ static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
         cpufreq_frequency_table_get_attr(cbe_freqs, policy->cpu);
 
-        if (pmi_dev) {
-                /* frequency might get limited later, initialize limit with max_freq */
-                pmi_frequency_limit = max_freq;
-                cpufreq_register_notifier(&pmi_notifier_block, CPUFREQ_POLICY_NOTIFIER);
-        }
-
-        /* this ensures that policy->cpuinfo_min and policy->cpuinfo_max are set correctly */
+        /* this ensures that policy->cpuinfo_min
+         * and policy->cpuinfo_max are set correctly */
         return cpufreq_frequency_table_cpuinfo(policy, cbe_freqs);
 }
 
 static int cbe_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
-        if (pmi_dev)
-                cpufreq_unregister_notifier(&pmi_notifier_block, CPUFREQ_POLICY_NOTIFIER);
-
         cpufreq_frequency_table_put_attr(policy->cpu);
         return 0;
 }
@@ -277,13 +140,13 @@ static int cbe_cpufreq_verify(struct cpufreq_policy *policy)
         return cpufreq_frequency_table_verify(policy, cbe_freqs);
 }
 
-
-static int cbe_cpufreq_target(struct cpufreq_policy *policy, unsigned int target_freq,
-                            unsigned int relation)
+static int cbe_cpufreq_target(struct cpufreq_policy *policy,
+                              unsigned int target_freq,
+                              unsigned int relation)
 {
         int rc;
         struct cpufreq_freqs freqs;
-        int cbe_pmode_new;
+        unsigned int cbe_pmode_new;
 
         cpufreq_frequency_table_target(policy,
                                        cbe_freqs,
@@ -298,12 +161,14 @@ static int cbe_cpufreq_target(struct cpufreq_policy *policy, unsigned int target
         mutex_lock(&cbe_switch_mutex);
         cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 
-        pr_debug("setting frequency for cpu %d to %d kHz, 1/%d of max frequency\n",
+        pr_debug("setting frequency for cpu %d to %d kHz, " \
+                 "1/%d of max frequency\n",
                  policy->cpu,
                  cbe_freqs[cbe_pmode_new].frequency,
                  cbe_freqs[cbe_pmode_new].index);
 
         rc = set_pmode(policy->cpu, cbe_pmode_new);
+
         cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
         mutex_unlock(&cbe_switch_mutex);
 
@@ -326,28 +191,14 @@ static struct cpufreq_driver cbe_cpufreq_driver = {
 
 static int __init cbe_cpufreq_init(void)
 {
-#ifdef CONFIG_PPC_PMI
-        struct device_node *np;
-#endif
         if (!machine_is(cell))
                 return -ENODEV;
-#ifdef CONFIG_PPC_PMI
-        np = of_find_node_by_type(NULL, "ibm,pmi");
-
-        pmi_dev = of_find_device_by_node(np);
 
-        if (pmi_dev)
-                pmi_register_handler(pmi_dev, &cbe_pmi_handler);
-#endif
         return cpufreq_register_driver(&cbe_cpufreq_driver);
 }
 
 static void __exit cbe_cpufreq_exit(void)
 {
-#ifdef CONFIG_PPC_PMI
-        if (pmi_dev)
-                pmi_unregister_handler(pmi_dev, &cbe_pmi_handler);
-#endif
         cpufreq_unregister_driver(&cbe_cpufreq_driver);
 }
 
diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq.h b/arch/powerpc/platforms/cell/cbe_cpufreq.h
new file mode 100644
index 000000000000..c1d86bfa92ff
--- /dev/null
+++ b/arch/powerpc/platforms/cell/cbe_cpufreq.h
@@ -0,0 +1,24 @@
+/*
+ * cbe_cpufreq.h
+ *
+ * This file contains the definitions used by the cbe_cpufreq driver.
+ *
+ * (C) Copyright IBM Deutschland Entwicklung GmbH 2005-2007
+ *
+ * Author: Christian Krafft <krafft@de.ibm.com>
+ *
+ */
+
+#include <linux/cpufreq.h>
+#include <linux/types.h>
+
+int cbe_cpufreq_set_pmode(int cpu, unsigned int pmode);
+int cbe_cpufreq_get_pmode(int cpu);
+
+int cbe_cpufreq_set_pmode_pmi(int cpu, unsigned int pmode);
+
+#if defined(CONFIG_CBE_CPUFREQ_PMI) || defined(CONFIG_CBE_CPUFREQ_PMI_MODULE)
+extern bool cbe_cpufreq_has_pmi;
+#else
+#define cbe_cpufreq_has_pmi (0)
+#endif
diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq_pervasive.c b/arch/powerpc/platforms/cell/cbe_cpufreq_pervasive.c
new file mode 100644
index 000000000000..163263b3e1cd
--- /dev/null
+++ b/arch/powerpc/platforms/cell/cbe_cpufreq_pervasive.c
@@ -0,0 +1,115 @@
+/*
+ * pervasive backend for the cbe_cpufreq driver
+ *
+ * This driver makes use of the pervasive unit to
+ * engage the desired frequency.
+ *
+ * (C) Copyright IBM Deutschland Entwicklung GmbH 2005-2007
+ *
+ * Author: Christian Krafft <krafft@de.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/time.h>
+#include <asm/machdep.h>
+#include <asm/hw_irq.h>
+
+#include "cbe_regs.h"
+#include "cbe_cpufreq.h"
+
+/* to write to MIC register */
+static u64 MIC_Slow_Fast_Timer_table[] = {
+        [0 ... 7] = 0x007fc00000000000ull,
+};
+
+/* more values for the MIC */
+static u64 MIC_Slow_Next_Timer_table[] = {
+        0x0000240000000000ull,
+        0x0000268000000000ull,
+        0x000029C000000000ull,
+        0x00002D0000000000ull,
+        0x0000300000000000ull,
+        0x0000334000000000ull,
+        0x000039C000000000ull,
+        0x00003FC000000000ull,
+};
+
+
+int cbe_cpufreq_set_pmode(int cpu, unsigned int pmode)
+{
+        struct cbe_pmd_regs __iomem *pmd_regs;
+        struct cbe_mic_tm_regs __iomem *mic_tm_regs;
+        u64 flags;
+        u64 value;
+#ifdef DEBUG
+        long time;
+#endif
+
+        local_irq_save(flags);
+
+        mic_tm_regs = cbe_get_cpu_mic_tm_regs(cpu);
+        pmd_regs = cbe_get_cpu_pmd_regs(cpu);
+
+#ifdef DEBUG
+        time = jiffies;
+#endif
+
+        out_be64(&mic_tm_regs->slow_fast_timer_0, MIC_Slow_Fast_Timer_table[pmode]);
+        out_be64(&mic_tm_regs->slow_fast_timer_1, MIC_Slow_Fast_Timer_table[pmode]);
+
+        out_be64(&mic_tm_regs->slow_next_timer_0, MIC_Slow_Next_Timer_table[pmode]);
+        out_be64(&mic_tm_regs->slow_next_timer_1, MIC_Slow_Next_Timer_table[pmode]);
+
+        value = in_be64(&pmd_regs->pmcr);
+        /* set bits to zero */
+        value &= 0xFFFFFFFFFFFFFFF8ull;
+        /* set bits to next pmode */
+        value |= pmode;
+
+        out_be64(&pmd_regs->pmcr, value);
+
+#ifdef DEBUG
+        /* wait until new pmode appears in status register */
+        value = in_be64(&pmd_regs->pmsr) & 0x07;
+        while (value != pmode) {
+                cpu_relax();
+                value = in_be64(&pmd_regs->pmsr) & 0x07;
+        }
+
+        time = jiffies  - time;
+        time = jiffies_to_msecs(time);
+        pr_debug("had to wait %lu ms for a transition using " \
+                 "pervasive unit\n", time);
+#endif
+        local_irq_restore(flags);
+
+        return 0;
+}
+
+
+int cbe_cpufreq_get_pmode(int cpu)
+{
+        int ret;
+        struct cbe_pmd_regs __iomem *pmd_regs;
+
+        pmd_regs = cbe_get_cpu_pmd_regs(cpu);
+        ret = in_be64(&pmd_regs->pmsr) & 0x07;
+
+        return ret;
+}
+
diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c b/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c
new file mode 100644
index 000000000000..fc6f38982ff4
--- /dev/null
+++ b/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c
@@ -0,0 +1,148 @@
+/*
+ * pmi backend for the cbe_cpufreq driver
+ *
+ * (C) Copyright IBM Deutschland Entwicklung GmbH 2005-2007
+ *
+ * Author: Christian Krafft <krafft@de.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/timer.h>
+#include <asm/of_platform.h>
+#include <asm/processor.h>
+#include <asm/prom.h>
+#include <asm/pmi.h>
+
+#ifdef DEBUG
+#include <asm/time.h>
+#endif
+
+#include "cbe_regs.h"
+#include "cbe_cpufreq.h"
+
+static u8 pmi_slow_mode_limit[MAX_CBE];
+
+bool cbe_cpufreq_has_pmi = false;
+EXPORT_SYMBOL_GPL(cbe_cpufreq_has_pmi);
+
+/*
+ * hardware specific functions
+ */
+
+int cbe_cpufreq_set_pmode_pmi(int cpu, unsigned int pmode)
+{
+        int ret;
+        pmi_message_t pmi_msg;
+#ifdef DEBUG
+        long time;
+#endif
+        pmi_msg.type = PMI_TYPE_FREQ_CHANGE;
+        pmi_msg.data1 = cbe_cpu_to_node(cpu);
+        pmi_msg.data2 = pmode;
+
+#ifdef DEBUG
+        time = jiffies;
+#endif
+        pmi_send_message(pmi_msg);
+
+#ifdef DEBUG
+        time = jiffies  - time;
+        time = jiffies_to_msecs(time);
+        pr_debug("had to wait %lu ms for a transition using " \
+                 "PMI\n", time);
+#endif
+        ret = pmi_msg.data2;
+        pr_debug("PMI returned slow mode %d\n", ret);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(cbe_cpufreq_set_pmode_pmi);
+
+
+static void cbe_cpufreq_handle_pmi(pmi_message_t pmi_msg)
+{
+        u8 node, slow_mode;
+
+        BUG_ON(pmi_msg.type != PMI_TYPE_FREQ_CHANGE);
+
+        node = pmi_msg.data1;
+        slow_mode = pmi_msg.data2;
+
+        pmi_slow_mode_limit[node] = slow_mode;
+
+        pr_debug("cbe_handle_pmi: node: %d max_freq: %d\n", node, slow_mode);
+}
+
+static int pmi_notifier(struct notifier_block *nb,
+                                       unsigned long event, void *data)
+{
+        struct cpufreq_policy *policy = data;
+        struct cpufreq_frequency_table *cbe_freqs;
+        u8 node;
+
+        cbe_freqs = cpufreq_frequency_get_table(policy->cpu);
+        node = cbe_cpu_to_node(policy->cpu);
+
+        pr_debug("got notified, event=%lu, node=%u\n", event, node);
+
+        if (pmi_slow_mode_limit[node] != 0) {
+                pr_debug("limiting node %d to slow mode %d\n",
+                         node, pmi_slow_mode_limit[node]);
+
+                cpufreq_verify_within_limits(policy, 0,
+
+                        cbe_freqs[pmi_slow_mode_limit[node]].frequency);
+        }
+
+        return 0;
+}
+
+static struct notifier_block pmi_notifier_block = {
+        .notifier_call = pmi_notifier,
+};
+
+static struct pmi_handler cbe_pmi_handler = {
+        .type                   = PMI_TYPE_FREQ_CHANGE,
+        .handle_pmi_message     = cbe_cpufreq_handle_pmi,
+};
+
+
+
+static int __init cbe_cpufreq_pmi_init(void)
+{
+        cbe_cpufreq_has_pmi = pmi_register_handler(&cbe_pmi_handler) == 0;
+
+        if (!cbe_cpufreq_has_pmi)
+                return -ENODEV;
+
+        cpufreq_register_notifier(&pmi_notifier_block, CPUFREQ_POLICY_NOTIFIER);
+
+        return 0;
+}
+
+static void __exit cbe_cpufreq_pmi_exit(void)
+{
+        cpufreq_unregister_notifier(&pmi_notifier_block, CPUFREQ_POLICY_NOTIFIER);
+        pmi_unregister_handler(&cbe_pmi_handler);
+}
+
+module_init(cbe_cpufreq_pmi_init);
+module_exit(cbe_cpufreq_pmi_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c
index 12c9674b4b1f..c8f7f0007422 100644
--- a/arch/powerpc/platforms/cell/cbe_regs.c
+++ b/arch/powerpc/platforms/cell/cbe_regs.c
@@ -174,6 +174,13 @@ static struct device_node *cbe_get_be_node(int cpu_id)
 
                 cpu_handle = of_get_property(np, "cpus", &len);
 
+                /*
+                 * the CAB SLOF tree is non compliant, so we just assume
+                 * there is only one node
+                 */
+                if (WARN_ON_ONCE(!cpu_handle))
+                        return np;
+
                 for (i=0; i<len; i++)
                         if (of_find_node_by_phandle(cpu_handle[i]) == of_get_cpu_node(cpu_id, NULL))
                                 return np;
diff --git a/arch/powerpc/platforms/cell/cbe_thermal.c b/arch/powerpc/platforms/cell/cbe_thermal.c
index f370f0fa6f4c..e4132f8f51b3 100644
--- a/arch/powerpc/platforms/cell/cbe_thermal.c
+++ b/arch/powerpc/platforms/cell/cbe_thermal.c
@@ -292,7 +292,7 @@ static struct attribute_group ppe_attribute_group = {
 /*
  * initialize throttling with default values
  */
-static void __init init_default_values(void)
+static int __init init_default_values(void)
 {
         int cpu;
         struct cbe_pmd_regs __iomem *pmd_regs;
@@ -339,25 +339,40 @@ static void __init init_default_values(void)
         for_each_possible_cpu (cpu) {
                 pr_debug("processing cpu %d\n", cpu);
                 sysdev = get_cpu_sysdev(cpu);
+
+                if (!sysdev) {
+                        pr_info("invalid sysdev pointer for cbe_thermal\n");
+                        return -EINVAL;
+                }
+
                 pmd_regs = cbe_get_cpu_pmd_regs(sysdev->id);
 
+                if (!pmd_regs) {
+                        pr_info("invalid CBE regs pointer for cbe_thermal\n");
+                        return -EINVAL;
+                }
+
                 out_be64(&pmd_regs->tm_str2, str2);
                 out_be64(&pmd_regs->tm_str1.val, str1.val);
                 out_be64(&pmd_regs->tm_tpr.val, tpr.val);
                 out_be64(&pmd_regs->tm_cr1.val, cr1.val);
                 out_be64(&pmd_regs->tm_cr2, cr2);
         }
+
+        return 0;
 }
 
 
 static int __init thermal_init(void)
 {
-        init_default_values();
+        int rc = init_default_values();
 
-        spu_add_sysdev_attr_group(&spu_attribute_group);
-        cpu_add_sysdev_attr_group(&ppe_attribute_group);
+        if (rc == 0) {
+                spu_add_sysdev_attr_group(&spu_attribute_group);
+                cpu_add_sysdev_attr_group(&ppe_attribute_group);
+        }
 
-        return 0;
+        return rc;
 }
 module_init(thermal_init);
 
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index 96a8f609690c..90124228b8f4 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -35,18 +35,37 @@
 #include <asm/spu.h>
 #include <asm/spu_priv1.h>
 #include <asm/xmon.h>
+#include <asm/prom.h>
+#include "spu_priv1_mmio.h"
 
 const struct spu_management_ops *spu_management_ops;
 EXPORT_SYMBOL_GPL(spu_management_ops);
 
 const struct spu_priv1_ops *spu_priv1_ops;
+EXPORT_SYMBOL_GPL(spu_priv1_ops);
 
-static struct list_head spu_list[MAX_NUMNODES];
-static LIST_HEAD(spu_full_list);
-static DEFINE_MUTEX(spu_mutex);
-static DEFINE_SPINLOCK(spu_list_lock);
+struct cbe_spu_info cbe_spu_info[MAX_NUMNODES];
+EXPORT_SYMBOL_GPL(cbe_spu_info);
 
-EXPORT_SYMBOL_GPL(spu_priv1_ops);
+/*
+ * Protects cbe_spu_info and spu->number.
+ */
+static DEFINE_SPINLOCK(spu_lock);
+
+/*
+ * List of all spus in the system.
+ *
+ * This list is iterated by callers from irq context and callers that
+ * want to sleep.  Thus modifications need to be done with both
+ * spu_full_list_lock and spu_full_list_mutex held, while iterating
+ * through it requires either of these locks.
+ *
+ * In addition spu_full_list_lock protects all assignmens to
+ * spu->mm.
+ */
+static LIST_HEAD(spu_full_list);
+static DEFINE_SPINLOCK(spu_full_list_lock);
+static DEFINE_MUTEX(spu_full_list_mutex);
 
 void spu_invalidate_slbs(struct spu *spu)
 {
@@ -65,12 +84,12 @@ void spu_flush_all_slbs(struct mm_struct *mm)
         struct spu *spu;
         unsigned long flags;
 
-        spin_lock_irqsave(&spu_list_lock, flags);
+        spin_lock_irqsave(&spu_full_list_lock, flags);
         list_for_each_entry(spu, &spu_full_list, full_list) {
                 if (spu->mm == mm)
                         spu_invalidate_slbs(spu);
         }
-        spin_unlock_irqrestore(&spu_list_lock, flags);
+        spin_unlock_irqrestore(&spu_full_list_lock, flags);
 }
 
 /* The hack below stinks... try to do something better one of
@@ -88,9 +107,9 @@ void spu_associate_mm(struct spu *spu, struct mm_struct *mm)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&spu_list_lock, flags);
+        spin_lock_irqsave(&spu_full_list_lock, flags);
         spu->mm = mm;
-        spin_unlock_irqrestore(&spu_list_lock, flags);
+        spin_unlock_irqrestore(&spu_full_list_lock, flags);
         if (mm)
                 mm_needs_global_tlbie(mm);
 }
@@ -390,7 +409,7 @@ static void spu_free_irqs(struct spu *spu)
                 free_irq(spu->irqs[2], spu);
 }
 
-static void spu_init_channels(struct spu *spu)
+void spu_init_channels(struct spu *spu)
 {
         static const struct {
                  unsigned channel;
@@ -423,46 +442,7 @@ static void spu_init_channels(struct spu *spu)
                 out_be64(&priv2->spu_chnlcnt_RW, count_list[i].count);
         }
 }
-
-struct spu *spu_alloc_node(int node)
-{
-        struct spu *spu = NULL;
-
-        mutex_lock(&spu_mutex);
-        if (!list_empty(&spu_list[node])) {
-                spu = list_entry(spu_list[node].next, struct spu, list);
-                list_del_init(&spu->list);
-                pr_debug("Got SPU %d %d\n", spu->number, spu->node);
-        }
-        mutex_unlock(&spu_mutex);
-
-        if (spu)
-                spu_init_channels(spu);
-        return spu;
-}
-EXPORT_SYMBOL_GPL(spu_alloc_node);
-
-struct spu *spu_alloc(void)
-{
-        struct spu *spu = NULL;
-        int node;
-
-        for (node = 0; node < MAX_NUMNODES; node++) {
-                spu = spu_alloc_node(node);
-                if (spu)
-                        break;
-        }
-
-        return spu;
-}
-
-void spu_free(struct spu *spu)
-{
-        mutex_lock(&spu_mutex);
-        list_add_tail(&spu->list, &spu_list[spu->node]);
-        mutex_unlock(&spu_mutex);
-}
-EXPORT_SYMBOL_GPL(spu_free);
+EXPORT_SYMBOL_GPL(spu_init_channels);
 
 static int spu_shutdown(struct sys_device *sysdev)
 {
@@ -481,12 +461,12 @@ struct sysdev_class spu_sysdev_class = {
 int spu_add_sysdev_attr(struct sysdev_attribute *attr)
 {
         struct spu *spu;
-        mutex_lock(&spu_mutex);
 
+        mutex_lock(&spu_full_list_mutex);
         list_for_each_entry(spu, &spu_full_list, full_list)
                 sysdev_create_file(&spu->sysdev, attr);
+        mutex_unlock(&spu_full_list_mutex);
 
-        mutex_unlock(&spu_mutex);
         return 0;
 }
 EXPORT_SYMBOL_GPL(spu_add_sysdev_attr);
@@ -494,12 +474,12 @@ EXPORT_SYMBOL_GPL(spu_add_sysdev_attr);
 int spu_add_sysdev_attr_group(struct attribute_group *attrs)
 {
         struct spu *spu;
-        mutex_lock(&spu_mutex);
 
+        mutex_lock(&spu_full_list_mutex);
         list_for_each_entry(spu, &spu_full_list, full_list)
                 sysfs_create_group(&spu->sysdev.kobj, attrs);
+        mutex_unlock(&spu_full_list_mutex);
 
-        mutex_unlock(&spu_mutex);
         return 0;
 }
 EXPORT_SYMBOL_GPL(spu_add_sysdev_attr_group);
@@ -508,24 +488,22 @@ EXPORT_SYMBOL_GPL(spu_add_sysdev_attr_group);
 void spu_remove_sysdev_attr(struct sysdev_attribute *attr)
 {
         struct spu *spu;
-        mutex_lock(&spu_mutex);
 
+        mutex_lock(&spu_full_list_mutex);
         list_for_each_entry(spu, &spu_full_list, full_list)
                 sysdev_remove_file(&spu->sysdev, attr);
-
-        mutex_unlock(&spu_mutex);
+        mutex_unlock(&spu_full_list_mutex);
 }
 EXPORT_SYMBOL_GPL(spu_remove_sysdev_attr);
 
 void spu_remove_sysdev_attr_group(struct attribute_group *attrs)
 {
         struct spu *spu;
-        mutex_lock(&spu_mutex);
 
+        mutex_lock(&spu_full_list_mutex);
         list_for_each_entry(spu, &spu_full_list, full_list)
                 sysfs_remove_group(&spu->sysdev.kobj, attrs);
-
-        mutex_unlock(&spu_mutex);
+        mutex_unlock(&spu_full_list_mutex);
 }
 EXPORT_SYMBOL_GPL(spu_remove_sysdev_attr_group);
 
@@ -553,16 +531,19 @@ static int __init create_spu(void *data)
         int ret;
         static int number;
         unsigned long flags;
+        struct timespec ts;
 
         ret = -ENOMEM;
         spu = kzalloc(sizeof (*spu), GFP_KERNEL);
         if (!spu)
                 goto out;
 
+        spu->alloc_state = SPU_FREE;
+
         spin_lock_init(&spu->register_lock);
-        mutex_lock(&spu_mutex);
+        spin_lock(&spu_lock);
         spu->number = number++;
-        mutex_unlock(&spu_mutex);
+        spin_unlock(&spu_lock);
 
         ret = spu_create_spu(spu, data);
 
@@ -579,15 +560,22 @@ static int __init create_spu(void *data)
         if (ret)
                 goto out_free_irqs;
 
-        mutex_lock(&spu_mutex);
-        spin_lock_irqsave(&spu_list_lock, flags);
-        list_add(&spu->list, &spu_list[spu->node]);
+        mutex_lock(&cbe_spu_info[spu->node].list_mutex);
+        list_add(&spu->cbe_list, &cbe_spu_info[spu->node].spus);
+        cbe_spu_info[spu->node].n_spus++;
+        mutex_unlock(&cbe_spu_info[spu->node].list_mutex);
+
+        mutex_lock(&spu_full_list_mutex);
+        spin_lock_irqsave(&spu_full_list_lock, flags);
         list_add(&spu->full_list, &spu_full_list);
-        spin_unlock_irqrestore(&spu_list_lock, flags);
-        mutex_unlock(&spu_mutex);
+        spin_unlock_irqrestore(&spu_full_list_lock, flags);
+        mutex_unlock(&spu_full_list_mutex);
+
+        spu->stats.util_state = SPU_UTIL_IDLE_LOADED;
+        ktime_get_ts(&ts);
+        spu->stats.tstamp = timespec_to_ns(&ts);
 
-        spu->stats.utilization_state = SPU_UTIL_IDLE;
-        spu->stats.tstamp = jiffies;
+        INIT_LIST_HEAD(&spu->aff_list);
 
         goto out;
 
@@ -608,12 +596,20 @@ static const char *spu_state_names[] = {
 static unsigned long long spu_acct_time(struct spu *spu,
                 enum spu_utilization_state state)
 {
+        struct timespec ts;
         unsigned long long time = spu->stats.times[state];
 
-        if (spu->stats.utilization_state == state)
-                time += jiffies - spu->stats.tstamp;
+        /*
+         * If the spu is idle or the context is stopped, utilization
+         * statistics are not updated.  Apply the time delta from the
+         * last recorded state of the spu.
+         */
+        if (spu->stats.util_state == state) {
+                ktime_get_ts(&ts);
+                time += timespec_to_ns(&ts) - spu->stats.tstamp;
+        }
 
-        return jiffies_to_msecs(time);
+        return time / NSEC_PER_MSEC;
 }
 
 
@@ -623,11 +619,11 @@ static ssize_t spu_stat_show(struct sys_device *sysdev, char *buf)
 
         return sprintf(buf, "%s %llu %llu %llu %llu "
                       "%llu %llu %llu %llu %llu %llu %llu %llu\n",
-                spu_state_names[spu->stats.utilization_state],
+                spu_state_names[spu->stats.util_state],
                 spu_acct_time(spu, SPU_UTIL_USER),
                 spu_acct_time(spu, SPU_UTIL_SYSTEM),
                 spu_acct_time(spu, SPU_UTIL_IOWAIT),
-                spu_acct_time(spu, SPU_UTIL_IDLE),
+                spu_acct_time(spu, SPU_UTIL_IDLE_LOADED),
                 spu->stats.vol_ctx_switch,
                 spu->stats.invol_ctx_switch,
                 spu->stats.slb_flt,
@@ -640,12 +636,146 @@ static ssize_t spu_stat_show(struct sys_device *sysdev, char *buf)
 
 static SYSDEV_ATTR(stat, 0644, spu_stat_show, NULL);
 
+/* Hardcoded affinity idxs for QS20 */
+#define SPES_PER_BE 8
+static int QS20_reg_idxs[SPES_PER_BE] =   { 0, 2, 4, 6, 7, 5, 3, 1 };
+static int QS20_reg_memory[SPES_PER_BE] = { 1, 1, 0, 0, 0, 0, 0, 0 };
+
+static struct spu *spu_lookup_reg(int node, u32 reg)
+{
+        struct spu *spu;
+
+        list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) {
+                if (*(u32 *)get_property(spu_devnode(spu), "reg", NULL) == reg)
+                        return spu;
+        }
+        return NULL;
+}
+
+static void init_aff_QS20_harcoded(void)
+{
+        int node, i;
+        struct spu *last_spu, *spu;
+        u32 reg;
+
+        for (node = 0; node < MAX_NUMNODES; node++) {
+                last_spu = NULL;
+                for (i = 0; i < SPES_PER_BE; i++) {
+                        reg = QS20_reg_idxs[i];
+                        spu = spu_lookup_reg(node, reg);
+                        if (!spu)
+                                continue;
+                        spu->has_mem_affinity = QS20_reg_memory[reg];
+                        if (last_spu)
+                                list_add_tail(&spu->aff_list,
+                                                &last_spu->aff_list);
+                        last_spu = spu;
+                }
+        }
+}
+
+static int of_has_vicinity(void)
+{
+        struct spu* spu;
+
+        spu = list_entry(cbe_spu_info[0].spus.next, struct spu, cbe_list);
+        return of_find_property(spu_devnode(spu), "vicinity", NULL) != NULL;
+}
+
+static struct spu *aff_devnode_spu(int cbe, struct device_node *dn)
+{
+        struct spu *spu;
+
+        list_for_each_entry(spu, &cbe_spu_info[cbe].spus, cbe_list)
+                if (spu_devnode(spu) == dn)
+                        return spu;
+        return NULL;
+}
+
+static struct spu *
+aff_node_next_to(int cbe, struct device_node *target, struct device_node *avoid)
+{
+        struct spu *spu;
+        const phandle *vic_handles;
+        int lenp, i;
+
+        list_for_each_entry(spu, &cbe_spu_info[cbe].spus, cbe_list) {
+                if (spu_devnode(spu) == avoid)
+                        continue;
+                vic_handles = get_property(spu_devnode(spu), "vicinity", &lenp);
+                for (i=0; i < (lenp / sizeof(phandle)); i++) {
+                        if (vic_handles[i] == target->linux_phandle)
+                                return spu;
+                }
+        }
+        return NULL;
+}
+
+static void init_aff_fw_vicinity_node(int cbe)
+{
+        struct spu *spu, *last_spu;
+        struct device_node *vic_dn, *last_spu_dn;
+        phandle avoid_ph;
+        const phandle *vic_handles;
+        const char *name;
+        int lenp, i, added, mem_aff;
+
+        last_spu = list_entry(cbe_spu_info[cbe].spus.next, struct spu, cbe_list);
+        avoid_ph = 0;
+        for (added = 1; added < cbe_spu_info[cbe].n_spus; added++) {
+                last_spu_dn = spu_devnode(last_spu);
+                vic_handles = get_property(last_spu_dn, "vicinity", &lenp);
+
+                for (i = 0; i < (lenp / sizeof(phandle)); i++) {
+                        if (vic_handles[i] == avoid_ph)
+                                continue;
+
+                        vic_dn = of_find_node_by_phandle(vic_handles[i]);
+                        if (!vic_dn)
+                                continue;
+
+                        name = get_property(vic_dn, "name", NULL);
+                        if (strcmp(name, "spe") == 0) {
+                                spu = aff_devnode_spu(cbe, vic_dn);
+                                avoid_ph = last_spu_dn->linux_phandle;
+                        }
+                        else {
+                                mem_aff = strcmp(name, "mic-tm") == 0;
+                                spu = aff_node_next_to(cbe, vic_dn, last_spu_dn);
+                                if (!spu)
+                                        continue;
+                                if (mem_aff) {
+                                        last_spu->has_mem_affinity = 1;
+                                        spu->has_mem_affinity = 1;
+                                }
+                                avoid_ph = vic_dn->linux_phandle;
+                        }
+                        list_add_tail(&spu->aff_list, &last_spu->aff_list);
+                        last_spu = spu;
+                        break;
+                }
+        }
+}
+
+static void init_aff_fw_vicinity(void)
+{
+        int cbe;
+
+        /* sets has_mem_affinity for each spu, as long as the
+         * spu->aff_list list, linking each spu to its neighbors
+         */
+        for (cbe = 0; cbe < MAX_NUMNODES; cbe++)
+                init_aff_fw_vicinity_node(cbe);
+}
+
 static int __init init_spu_base(void)
 {
         int i, ret = 0;
 
-        for (i = 0; i < MAX_NUMNODES; i++)
-                INIT_LIST_HEAD(&spu_list[i]);
+        for (i = 0; i < MAX_NUMNODES; i++) {
+                mutex_init(&cbe_spu_info[i].list_mutex);
+                INIT_LIST_HEAD(&cbe_spu_info[i].spus);
+        }
 
         if (!spu_management_ops)
                 goto out;
@@ -675,16 +805,25 @@ static int __init init_spu_base(void)
                 fb_append_extra_logo(&logo_spe_clut224, ret);
         }
 
+        mutex_lock(&spu_full_list_mutex);
         xmon_register_spus(&spu_full_list);
-
+        crash_register_spus(&spu_full_list);
+        mutex_unlock(&spu_full_list_mutex);
         spu_add_sysdev_attr(&attr_stat);
 
+        if (of_has_vicinity()) {
+                init_aff_fw_vicinity();
+        } else {
+                long root = of_get_flat_dt_root();
+                if (of_flat_dt_is_compatible(root, "IBM,CPBW-1.0"))
+                        init_aff_QS20_harcoded();
+        }
+
         return 0;
 
  out_unregister_sysdev_class:
         sysdev_class_unregister(&spu_sysdev_class);
  out:
-
         return ret;
 }
 module_init(init_spu_base);
diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c
index 261b507a901a..dd2c6688c8aa 100644
--- a/arch/powerpc/platforms/cell/spu_syscalls.c
+++ b/arch/powerpc/platforms/cell/spu_syscalls.c
@@ -34,14 +34,27 @@ struct spufs_calls spufs_calls = {
  * this file is not used and the syscalls directly enter the fs code */
 
 asmlinkage long sys_spu_create(const char __user *name,
-                unsigned int flags, mode_t mode)
+                unsigned int flags, mode_t mode, int neighbor_fd)
 {
         long ret;
         struct module *owner = spufs_calls.owner;
+        struct file *neighbor;
+        int fput_needed;
 
         ret = -ENOSYS;
         if (owner && try_module_get(owner)) {
-                ret = spufs_calls.create_thread(name, flags, mode);
+                if (flags & SPU_CREATE_AFFINITY_SPU) {
+                        neighbor = fget_light(neighbor_fd, &fput_needed);
+                        if (neighbor) {
+                                ret = spufs_calls.create_thread(name, flags,
+                                                                mode, neighbor);
+                                fput_light(neighbor, fput_needed);
+                        }
+                }
+                else {
+                        ret = spufs_calls.create_thread(name, flags,
+                                                        mode, NULL);
+                }
                 module_put(owner);
         }
         return ret;
diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c
index 6d7bd60f5380..6694f86d7000 100644
--- a/arch/powerpc/platforms/cell/spufs/context.c
+++ b/arch/powerpc/platforms/cell/spufs/context.c
@@ -22,6 +22,7 @@
 
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/module.h>
 #include <linux/slab.h>
 #include <asm/atomic.h>
 #include <asm/spu.h>
@@ -55,12 +56,12 @@ struct spu_context *alloc_spu_context(struct spu_gang *gang)
         ctx->ops = &spu_backing_ops;
         ctx->owner = get_task_mm(current);
         INIT_LIST_HEAD(&ctx->rq);
+        INIT_LIST_HEAD(&ctx->aff_list);
         if (gang)
                 spu_gang_add_ctx(gang, ctx);
         ctx->cpus_allowed = current->cpus_allowed;
         spu_set_timeslice(ctx);
-        ctx->stats.execution_state = SPUCTX_UTIL_USER;
-        ctx->stats.tstamp = jiffies;
+        ctx->stats.util_state = SPU_UTIL_IDLE_LOADED;
 
         atomic_inc(&nr_spu_contexts);
         goto out;
@@ -81,6 +82,8 @@ void destroy_spu_context(struct kref *kref)
         spu_fini_csa(&ctx->csa);
         if (ctx->gang)
                 spu_gang_remove_ctx(ctx->gang, ctx);
+        if (ctx->prof_priv_kref)
+                kref_put(ctx->prof_priv_kref, ctx->prof_priv_release);
         BUG_ON(!list_empty(&ctx->rq));
         atomic_dec(&nr_spu_contexts);
         kfree(ctx);
@@ -166,6 +169,39 @@ int spu_acquire_runnable(struct spu_context *ctx, unsigned long flags)
 void spu_acquire_saved(struct spu_context *ctx)
 {
         spu_acquire(ctx);
-        if (ctx->state != SPU_STATE_SAVED)
+        if (ctx->state != SPU_STATE_SAVED) {
+                set_bit(SPU_SCHED_WAS_ACTIVE, &ctx->sched_flags);
                 spu_deactivate(ctx);
+        }
+}
+
+/**
+ * spu_release_saved - unlock spu context and return it to the runqueue
+ * @ctx:        context to unlock
+ */
+void spu_release_saved(struct spu_context *ctx)
+{
+        BUG_ON(ctx->state != SPU_STATE_SAVED);
+
+        if (test_and_clear_bit(SPU_SCHED_WAS_ACTIVE, &ctx->sched_flags))
+                spu_activate(ctx, 0);
+
+        spu_release(ctx);
 }
+
+void spu_set_profile_private_kref(struct spu_context *ctx,
+                                  struct kref *prof_info_kref,
+                                  void ( * prof_info_release) (struct kref *kref))
+{
+        ctx->prof_priv_kref = prof_info_kref;
+        ctx->prof_priv_release = prof_info_release;
+}
+EXPORT_SYMBOL_GPL(spu_set_profile_private_kref);
+
+void *spu_get_profile_private_kref(struct spu_context *ctx)
+{
+        return ctx->prof_priv_kref;
+}
+EXPORT_SYMBOL_GPL(spu_get_profile_private_kref);
+
+
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 5d9ad5a0307b..5e31799b1e3f 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -226,7 +226,7 @@ static void spufs_arch_write_notes(struct file *file)
                 spu_acquire_saved(ctx_info->ctx);
                 for (j = 0; j < spufs_coredump_num_notes; j++)
                         spufs_arch_write_note(ctx_info, j, file);
-                spu_release(ctx_info->ctx);
+                spu_release_saved(ctx_info->ctx);
                 list_del(&ctx_info->list);
                 kfree(ctx_info);
         }
diff --git a/arch/powerpc/platforms/cell/spufs/fault.c b/arch/powerpc/platforms/cell/spufs/fault.c
index f53a07437472..917eab4be486 100644
--- a/arch/powerpc/platforms/cell/spufs/fault.c
+++ b/arch/powerpc/platforms/cell/spufs/fault.c
@@ -179,16 +179,14 @@ int spufs_handle_class1(struct spu_context *ctx)
         if (!(dsisr & (MFC_DSISR_PTE_NOT_FOUND | MFC_DSISR_ACCESS_DENIED)))
                 return 0;
 
-        spuctx_switch_state(ctx, SPUCTX_UTIL_IOWAIT);
+        spuctx_switch_state(ctx, SPU_UTIL_IOWAIT);
 
         pr_debug("ctx %p: ea %016lx, dsisr %016lx state %d\n", ctx, ea,
                 dsisr, ctx->state);
 
         ctx->stats.hash_flt++;
-        if (ctx->state == SPU_STATE_RUNNABLE) {
+        if (ctx->state == SPU_STATE_RUNNABLE)
                 ctx->spu->stats.hash_flt++;
-                spu_switch_state(ctx->spu, SPU_UTIL_IOWAIT);
-        }
 
         /* we must not hold the lock when entering spu_handle_mm_fault */
         spu_release(ctx);
@@ -226,7 +224,7 @@ int spufs_handle_class1(struct spu_context *ctx)
         } else
                 spufs_handle_dma_error(ctx, ea, SPE_EVENT_SPE_DATA_STORAGE);
 
-        spuctx_switch_state(ctx, SPUCTX_UTIL_SYSTEM);
+        spuctx_switch_state(ctx, SPU_UTIL_SYSTEM);
         return ret;
 }
 EXPORT_SYMBOL_GPL(spufs_handle_class1);
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index c2814ea96af2..4100ddc52f02 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -370,7 +370,7 @@ spufs_regs_read(struct file *file, char __user *buffer,
 
         spu_acquire_saved(ctx);
         ret = __spufs_regs_read(ctx, buffer, size, pos);
-        spu_release(ctx);
+        spu_release_saved(ctx);
         return ret;
 }
 
@@ -392,7 +392,7 @@ spufs_regs_write(struct file *file, const char __user *buffer,
         ret = copy_from_user(lscsa->gprs + *pos - size,
                              buffer, size) ? -EFAULT : size;
 
-        spu_release(ctx);
+        spu_release_saved(ctx);
         return ret;
 }
 
@@ -421,7 +421,7 @@ spufs_fpcr_read(struct file *file, char __user * buffer,
 
         spu_acquire_saved(ctx);
         ret = __spufs_fpcr_read(ctx, buffer, size, pos);
-        spu_release(ctx);
+        spu_release_saved(ctx);
         return ret;
 }
 
@@ -443,7 +443,7 @@ spufs_fpcr_write(struct file *file, const char __user * buffer,
         ret = copy_from_user((char *)&lscsa->fpcr + *pos - size,
                              buffer, size) ? -EFAULT : size;
 
-        spu_release(ctx);
+        spu_release_saved(ctx);
         return ret;
 }
 
@@ -868,7 +868,7 @@ static ssize_t spufs_signal1_read(struct file *file, char __user *buf,
 
         spu_acquire_saved(ctx);
         ret = __spufs_signal1_read(ctx, buf, len, pos);
-        spu_release(ctx);
+        spu_release_saved(ctx);
 
         return ret;
 }
@@ -934,6 +934,13 @@ static const struct file_operations spufs_signal1_fops = {
         .mmap = spufs_signal1_mmap,
 };
 
+static const struct file_operations spufs_signal1_nosched_fops = {
+        .open = spufs_signal1_open,
+        .release = spufs_signal1_release,
+        .write = spufs_signal1_write,
+        .mmap = spufs_signal1_mmap,
+};
+
 static int spufs_signal2_open(struct inode *inode, struct file *file)
 {
         struct spufs_inode_info *i = SPUFS_I(inode);
@@ -992,7 +999,7 @@ static ssize_t spufs_signal2_read(struct file *file, char __user *buf,
 
         spu_acquire_saved(ctx);
         ret = __spufs_signal2_read(ctx, buf, len, pos);
-        spu_release(ctx);
+        spu_release_saved(ctx);
 
         return ret;
 }
@@ -1062,6 +1069,13 @@ static const struct file_operations spufs_signal2_fops = {
         .mmap = spufs_signal2_mmap,
 };
 
+static const struct file_operations spufs_signal2_nosched_fops = {
+        .open = spufs_signal2_open,
+        .release = spufs_signal2_release,
+        .write = spufs_signal2_write,
+        .mmap = spufs_signal2_mmap,
+};
+
 static void spufs_signal1_type_set(void *data, u64 val)
 {
         struct spu_context *ctx = data;
@@ -1612,7 +1626,7 @@ static void spufs_decr_set(void *data, u64 val)
         struct spu_lscsa *lscsa = ctx->csa.lscsa;
         spu_acquire_saved(ctx);
         lscsa->decr.slot[0] = (u32) val;
-        spu_release(ctx);
+        spu_release_saved(ctx);
 }
 
 static u64 __spufs_decr_get(void *data)
@@ -1628,7 +1642,7 @@ static u64 spufs_decr_get(void *data)
         u64 ret;
         spu_acquire_saved(ctx);
         ret = __spufs_decr_get(data);
-        spu_release(ctx);
+        spu_release_saved(ctx);
         return ret;
 }
 DEFINE_SIMPLE_ATTRIBUTE(spufs_decr_ops, spufs_decr_get, spufs_decr_set,
@@ -1637,17 +1651,21 @@ DEFINE_SIMPLE_ATTRIBUTE(spufs_decr_ops, spufs_decr_get, spufs_decr_set,
 static void spufs_decr_status_set(void *data, u64 val)
 {
         struct spu_context *ctx = data;
-        struct spu_lscsa *lscsa = ctx->csa.lscsa;
         spu_acquire_saved(ctx);
-        lscsa->decr_status.slot[0] = (u32) val;
-        spu_release(ctx);
+        if (val)
+                ctx->csa.priv2.mfc_control_RW |= MFC_CNTL_DECREMENTER_RUNNING;
+        else
+                ctx->csa.priv2.mfc_control_RW &= ~MFC_CNTL_DECREMENTER_RUNNING;
+        spu_release_saved(ctx);
 }
 
 static u64 __spufs_decr_status_get(void *data)
 {
         struct spu_context *ctx = data;
-        struct spu_lscsa *lscsa = ctx->csa.lscsa;
-        return lscsa->decr_status.slot[0];
+        if (ctx->csa.priv2.mfc_control_RW & MFC_CNTL_DECREMENTER_RUNNING)
+                return SPU_DECR_STATUS_RUNNING;
+        else
+                return 0;
 }
 
 static u64 spufs_decr_status_get(void *data)
@@ -1656,7 +1674,7 @@ static u64 spufs_decr_status_get(void *data)
         u64 ret;
         spu_acquire_saved(ctx);
         ret = __spufs_decr_status_get(data);
-        spu_release(ctx);
+        spu_release_saved(ctx);
         return ret;
 }
 DEFINE_SIMPLE_ATTRIBUTE(spufs_decr_status_ops, spufs_decr_status_get,
@@ -1668,7 +1686,7 @@ static void spufs_event_mask_set(void *data, u64 val)
         struct spu_lscsa *lscsa = ctx->csa.lscsa;
         spu_acquire_saved(ctx);
         lscsa->event_mask.slot[0] = (u32) val;
-        spu_release(ctx);
+        spu_release_saved(ctx);
 }
 
 static u64 __spufs_event_mask_get(void *data)
@@ -1684,7 +1702,7 @@ static u64 spufs_event_mask_get(void *data)
         u64 ret;
         spu_acquire_saved(ctx);
         ret = __spufs_event_mask_get(data);
-        spu_release(ctx);
+        spu_release_saved(ctx);
         return ret;
 }
 DEFINE_SIMPLE_ATTRIBUTE(spufs_event_mask_ops, spufs_event_mask_get,
@@ -1708,7 +1726,7 @@ static u64 spufs_event_status_get(void *data)
 
         spu_acquire_saved(ctx);
         ret = __spufs_event_status_get(data);
-        spu_release(ctx);
+        spu_release_saved(ctx);
         return ret;
 }
 DEFINE_SIMPLE_ATTRIBUTE(spufs_event_status_ops, spufs_event_status_get,
@@ -1720,7 +1738,7 @@ static void spufs_srr0_set(void *data, u64 val)
         struct spu_lscsa *lscsa = ctx->csa.lscsa;
         spu_acquire_saved(ctx);
         lscsa->srr0.slot[0] = (u32) val;
-        spu_release(ctx);
+        spu_release_saved(ctx);
 }
 
 static u64 spufs_srr0_get(void *data)
@@ -1730,7 +1748,7 @@ static u64 spufs_srr0_get(void *data)
         u64 ret;
         spu_acquire_saved(ctx);
         ret = lscsa->srr0.slot[0];
-        spu_release(ctx);
+        spu_release_saved(ctx);
         return ret;
 }
 DEFINE_SIMPLE_ATTRIBUTE(spufs_srr0_ops, spufs_srr0_get, spufs_srr0_set,
@@ -1786,7 +1804,7 @@ static u64 spufs_lslr_get(void *data)
 
         spu_acquire_saved(ctx);
         ret = __spufs_lslr_get(data);
-        spu_release(ctx);
+        spu_release_saved(ctx);
 
         return ret;
 }
@@ -1850,7 +1868,7 @@ static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf,
         spin_lock(&ctx->csa.register_lock);
         ret = __spufs_mbox_info_read(ctx, buf, len, pos);
         spin_unlock(&ctx->csa.register_lock);
-        spu_release(ctx);
+        spu_release_saved(ctx);
 
         return ret;
 }
@@ -1888,7 +1906,7 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf,
         spin_lock(&ctx->csa.register_lock);
         ret = __spufs_ibox_info_read(ctx, buf, len, pos);
         spin_unlock(&ctx->csa.register_lock);
-        spu_release(ctx);
+        spu_release_saved(ctx);
 
         return ret;
 }
@@ -1929,7 +1947,7 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf,
         spin_lock(&ctx->csa.register_lock);
         ret = __spufs_wbox_info_read(ctx, buf, len, pos);
         spin_unlock(&ctx->csa.register_lock);
-        spu_release(ctx);
+        spu_release_saved(ctx);
 
         return ret;
 }
@@ -1979,7 +1997,7 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf,
         spin_lock(&ctx->csa.register_lock);
         ret = __spufs_dma_info_read(ctx, buf, len, pos);
         spin_unlock(&ctx->csa.register_lock);
-        spu_release(ctx);
+        spu_release_saved(ctx);
 
         return ret;
 }
@@ -2030,7 +2048,7 @@ static ssize_t spufs_proxydma_info_read(struct file *file, char __user *buf,
         spin_lock(&ctx->csa.register_lock);
         ret = __spufs_proxydma_info_read(ctx, buf, len, pos);
         spin_unlock(&ctx->csa.register_lock);
-        spu_release(ctx);
+        spu_release_saved(ctx);
 
         return ret;
 }
@@ -2065,14 +2083,26 @@ static const char *ctx_state_names[] = {
 };
 
 static unsigned long long spufs_acct_time(struct spu_context *ctx,
-                enum spuctx_execution_state state)
+                enum spu_utilization_state state)
 {
-        unsigned long time = ctx->stats.times[state];
+        struct timespec ts;
+        unsigned long long time = ctx->stats.times[state];
 
-        if (ctx->stats.execution_state == state)
-                time += jiffies - ctx->stats.tstamp;
+        /*
+         * In general, utilization statistics are updated by the controlling
+         * thread as the spu context moves through various well defined
+         * state transitions, but if the context is lazily loaded its
+         * utilization statistics are not updated as the controlling thread
+         * is not tightly coupled with the execution of the spu context.  We
+         * calculate and apply the time delta from the last recorded state
+         * of the spu context.
+         */
+        if (ctx->spu && ctx->stats.util_state == state) {
+                ktime_get_ts(&ts);
+                time += timespec_to_ns(&ts) - ctx->stats.tstamp;
+        }
 
-        return jiffies_to_msecs(time);
+        return time / NSEC_PER_MSEC;
 }
 
 static unsigned long long spufs_slb_flts(struct spu_context *ctx)
@@ -2107,11 +2137,11 @@ static int spufs_show_stat(struct seq_file *s, void *private)
         spu_acquire(ctx);
         seq_printf(s, "%s %llu %llu %llu %llu "
                       "%llu %llu %llu %llu %llu %llu %llu %llu\n",
-                ctx_state_names[ctx->stats.execution_state],
-                spufs_acct_time(ctx, SPUCTX_UTIL_USER),
-                spufs_acct_time(ctx, SPUCTX_UTIL_SYSTEM),
-                spufs_acct_time(ctx, SPUCTX_UTIL_IOWAIT),
-                spufs_acct_time(ctx, SPUCTX_UTIL_LOADED),
+                ctx_state_names[ctx->stats.util_state],
+                spufs_acct_time(ctx, SPU_UTIL_USER),
+                spufs_acct_time(ctx, SPU_UTIL_SYSTEM),
+                spufs_acct_time(ctx, SPU_UTIL_IOWAIT),
+                spufs_acct_time(ctx, SPU_UTIL_IDLE_LOADED),
                 ctx->stats.vol_ctx_switch,
                 ctx->stats.invol_ctx_switch,
                 spufs_slb_flts(ctx),
@@ -2147,8 +2177,8 @@ struct tree_descr spufs_dir_contents[] = {
         { "mbox_stat", &spufs_mbox_stat_fops, 0444, },
         { "ibox_stat", &spufs_ibox_stat_fops, 0444, },
         { "wbox_stat", &spufs_wbox_stat_fops, 0444, },
-        { "signal1", &spufs_signal1_fops, 0666, },
-        { "signal2", &spufs_signal2_fops, 0666, },
+        { "signal1", &spufs_signal1_nosched_fops, 0222, },
+        { "signal2", &spufs_signal2_nosched_fops, 0222, },
         { "signal1_type", &spufs_signal1_type, 0666, },
         { "signal2_type", &spufs_signal2_type, 0666, },
         { "cntl", &spufs_cntl_fops,  0666, },
@@ -2184,8 +2214,8 @@ struct tree_descr spufs_dir_nosched_contents[] = {
         { "mbox_stat", &spufs_mbox_stat_fops, 0444, },
         { "ibox_stat", &spufs_ibox_stat_fops, 0444, },
         { "wbox_stat", &spufs_wbox_stat_fops, 0444, },
-        { "signal1", &spufs_signal1_fops, 0666, },
-        { "signal2", &spufs_signal2_fops, 0666, },
+        { "signal1", &spufs_signal1_nosched_fops, 0222, },
+        { "signal2", &spufs_signal2_nosched_fops, 0222, },
         { "signal1_type", &spufs_signal1_type, 0666, },
         { "signal2_type", &spufs_signal2_type, 0666, },
         { "mss", &spufs_mss_fops, 0666, },
diff --git a/arch/powerpc/platforms/cell/spufs/gang.c b/arch/powerpc/platforms/cell/spufs/gang.c
index 212ea78f9051..71a443253021 100644
--- a/arch/powerpc/platforms/cell/spufs/gang.c
+++ b/arch/powerpc/platforms/cell/spufs/gang.c
@@ -35,7 +35,9 @@ struct spu_gang *alloc_spu_gang(void)
 
         kref_init(&gang->kref);
         mutex_init(&gang->mutex);
+        mutex_init(&gang->aff_mutex);
         INIT_LIST_HEAD(&gang->list);
+        INIT_LIST_HEAD(&gang->aff_list_head);
 
 out:
         return gang;
@@ -73,6 +75,10 @@ void spu_gang_remove_ctx(struct spu_gang *gang, struct spu_context *ctx)
 {
         mutex_lock(&gang->mutex);
         WARN_ON(ctx->gang != gang);
+        if (!list_empty(&ctx->aff_list)) {
+                list_del_init(&ctx->aff_list);
+                gang->aff_flags &= ~AFF_OFFSETS_SET;
+        }
         list_del_init(&ctx->gang_list);
         gang->contexts--;
         mutex_unlock(&gang->mutex);
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 7eb4d6cbcb74..b3d0dd118dd0 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -316,11 +316,107 @@ out:
         return ret;
 }
 
-static int spufs_create_context(struct inode *inode,
-                        struct dentry *dentry,
-                        struct vfsmount *mnt, int flags, int mode)
+static struct spu_context *
+spufs_assert_affinity(unsigned int flags, struct spu_gang *gang,
+                                                struct file *filp)
+{
+        struct spu_context *tmp, *neighbor;
+        int count, node;
+        int aff_supp;
+
+        aff_supp = !list_empty(&(list_entry(cbe_spu_info[0].spus.next,
+                                        struct spu, cbe_list))->aff_list);
+
+        if (!aff_supp)
+                return ERR_PTR(-EINVAL);
+
+        if (flags & SPU_CREATE_GANG)
+                return ERR_PTR(-EINVAL);
+
+        if (flags & SPU_CREATE_AFFINITY_MEM &&
+            gang->aff_ref_ctx &&
+            gang->aff_ref_ctx->flags & SPU_CREATE_AFFINITY_MEM)
+                return ERR_PTR(-EEXIST);
+
+        if (gang->aff_flags & AFF_MERGED)
+                return ERR_PTR(-EBUSY);
+
+        neighbor = NULL;
+        if (flags & SPU_CREATE_AFFINITY_SPU) {
+                if (!filp || filp->f_op != &spufs_context_fops)
+                        return ERR_PTR(-EINVAL);
+
+                neighbor = get_spu_context(
+                                SPUFS_I(filp->f_dentry->d_inode)->i_ctx);
+
+                if (!list_empty(&neighbor->aff_list) && !(neighbor->aff_head) &&
+                    !list_is_last(&neighbor->aff_list, &gang->aff_list_head) &&
+                    !list_entry(neighbor->aff_list.next, struct spu_context,
+                    aff_list)->aff_head)
+                        return ERR_PTR(-EEXIST);
+
+                if (gang != neighbor->gang)
+                        return ERR_PTR(-EINVAL);
+
+                count = 1;
+                list_for_each_entry(tmp, &gang->aff_list_head, aff_list)
+                        count++;
+                if (list_empty(&neighbor->aff_list))
+                        count++;
+
+                for (node = 0; node < MAX_NUMNODES; node++) {
+                        if ((cbe_spu_info[node].n_spus - atomic_read(
+                                &cbe_spu_info[node].reserved_spus)) >= count)
+                                break;
+                }
+
+                if (node == MAX_NUMNODES)
+                        return ERR_PTR(-EEXIST);
+        }
+
+        return neighbor;
+}
+
+static void
+spufs_set_affinity(unsigned int flags, struct spu_context *ctx,
+                                        struct spu_context *neighbor)
+{
+        if (flags & SPU_CREATE_AFFINITY_MEM)
+                ctx->gang->aff_ref_ctx = ctx;
+
+        if (flags & SPU_CREATE_AFFINITY_SPU) {
+                if (list_empty(&neighbor->aff_list)) {
+                        list_add_tail(&neighbor->aff_list,
+                                &ctx->gang->aff_list_head);
+                        neighbor->aff_head = 1;
+                }
+
+                if (list_is_last(&neighbor->aff_list, &ctx->gang->aff_list_head)
+                    || list_entry(neighbor->aff_list.next, struct spu_context,
+                                                        aff_list)->aff_head) {
+                        list_add(&ctx->aff_list, &neighbor->aff_list);
+                } else  {
+                        list_add_tail(&ctx->aff_list, &neighbor->aff_list);
+                        if (neighbor->aff_head) {
+                                neighbor->aff_head = 0;
+                                ctx->aff_head = 1;
+                        }
+                }
+
+                if (!ctx->gang->aff_ref_ctx)
+                        ctx->gang->aff_ref_ctx = ctx;
+        }
+}
+
+static int
+spufs_create_context(struct inode *inode, struct dentry *dentry,
+                        struct vfsmount *mnt, int flags, int mode,
+                        struct file *aff_filp)
 {
         int ret;
+        int affinity;
+        struct spu_gang *gang;
+        struct spu_context *neighbor;
 
         ret = -EPERM;
         if ((flags & SPU_CREATE_NOSCHED) &&
@@ -336,9 +432,29 @@ static int spufs_create_context(struct inode *inode,
         if ((flags & SPU_CREATE_ISOLATE) && !isolated_loader)
                 goto out_unlock;
 
+        gang = NULL;
+        neighbor = NULL;
+        affinity = flags & (SPU_CREATE_AFFINITY_MEM | SPU_CREATE_AFFINITY_SPU);
+        if (affinity) {
+                gang = SPUFS_I(inode)->i_gang;
+                ret = -EINVAL;
+                if (!gang)
+                        goto out_unlock;
+                mutex_lock(&gang->aff_mutex);
+                neighbor = spufs_assert_affinity(flags, gang, aff_filp);
+                if (IS_ERR(neighbor)) {
+                        ret = PTR_ERR(neighbor);
+                        goto out_aff_unlock;
+                }
+        }
+
         ret = spufs_mkdir(inode, dentry, flags, mode & S_IRWXUGO);
         if (ret)
-                goto out_unlock;
+                goto out_aff_unlock;
+
+        if (affinity)
+                spufs_set_affinity(flags, SPUFS_I(dentry->d_inode)->i_ctx,
+                                                                neighbor);
 
         /*
          * get references for dget and mntget, will be released
@@ -352,6 +468,9 @@ static int spufs_create_context(struct inode *inode,
                 goto out;
         }
 
+out_aff_unlock:
+        if (affinity)
+                mutex_unlock(&gang->aff_mutex);
 out_unlock:
         mutex_unlock(&inode->i_mutex);
 out:
@@ -450,7 +569,8 @@ out:
 
 static struct file_system_type spufs_type;
 
-long spufs_create(struct nameidata *nd, unsigned int flags, mode_t mode)
+long spufs_create(struct nameidata *nd, unsigned int flags, mode_t mode,
+                                                        struct file *filp)
 {
         struct dentry *dentry;
         int ret;
@@ -487,7 +607,7 @@ long spufs_create(struct nameidata *nd, unsigned int flags, mode_t mode)
                                         dentry, nd->mnt, mode);
         else
                 return spufs_create_context(nd->dentry->d_inode,
-                                        dentry, nd->mnt, flags, mode);
+                                        dentry, nd->mnt, flags, mode, filp);
 
 out_dput:
         dput(dentry);
diff --git a/arch/powerpc/platforms/cell/spufs/run.c b/arch/powerpc/platforms/cell/spufs/run.c
index 58ae13b7de84..0b50fa5cb39d 100644
--- a/arch/powerpc/platforms/cell/spufs/run.c
+++ b/arch/powerpc/platforms/cell/spufs/run.c
@@ -18,15 +18,17 @@ void spufs_stop_callback(struct spu *spu)
         wake_up_all(&ctx->stop_wq);
 }
 
-static inline int spu_stopped(struct spu_context *ctx, u32 * stat)
+static inline int spu_stopped(struct spu_context *ctx, u32 *stat)
 {
         struct spu *spu;
         u64 pte_fault;
 
         *stat = ctx->ops->status_read(ctx);
-        if (ctx->state != SPU_STATE_RUNNABLE)
-                return 1;
+
         spu = ctx->spu;
+        if (ctx->state != SPU_STATE_RUNNABLE ||
+            test_bit(SPU_SCHED_NOTIFY_ACTIVE, &ctx->sched_flags))
+                return 1;
         pte_fault = spu->dsisr &
             (MFC_DSISR_PTE_NOT_FOUND | MFC_DSISR_ACCESS_DENIED);
         return (!(*stat & SPU_STATUS_RUNNING) || pte_fault || spu->class_0_pending) ?
@@ -124,8 +126,10 @@ out:
         return ret;
 }
 
-static int spu_run_init(struct spu_context *ctx, u32 * npc)
+static int spu_run_init(struct spu_context *ctx, u32 *npc)
 {
+        spuctx_switch_state(ctx, SPU_UTIL_SYSTEM);
+
         if (ctx->flags & SPU_CREATE_ISOLATE) {
                 unsigned long runcntl;
 
@@ -151,16 +155,20 @@ static int spu_run_init(struct spu_context *ctx, u32 * npc)
                 ctx->ops->runcntl_write(ctx, SPU_RUNCNTL_RUNNABLE);
         }
 
+        spuctx_switch_state(ctx, SPU_UTIL_USER);
+
         return 0;
 }
 
-static int spu_run_fini(struct spu_context *ctx, u32 * npc,
-                               u32 * status)
+static int spu_run_fini(struct spu_context *ctx, u32 *npc,
+                               u32 *status)
 {
         int ret = 0;
 
         *status = ctx->ops->status_read(ctx);
         *npc = ctx->ops->npc_read(ctx);
+
+        spuctx_switch_state(ctx, SPU_UTIL_IDLE_LOADED);
         spu_release(ctx);
 
         if (signal_pending(current))
@@ -289,10 +297,10 @@ static inline int spu_process_events(struct spu_context *ctx)
         return ret;
 }
 
-long spufs_run_spu(struct file *file, struct spu_context *ctx,
-                   u32 *npc, u32 *event)
+long spufs_run_spu(struct spu_context *ctx, u32 *npc, u32 *event)
 {
         int ret;
+        struct spu *spu;
         u32 status;
 
         if (mutex_lock_interruptible(&ctx->run_mutex))
@@ -328,6 +336,17 @@ long spufs_run_spu(struct file *file, struct spu_context *ctx,
                 ret = spufs_wait(ctx->stop_wq, spu_stopped(ctx, &status));
                 if (unlikely(ret))
                         break;
+                spu = ctx->spu;
+                if (unlikely(test_and_clear_bit(SPU_SCHED_NOTIFY_ACTIVE,
+                                                &ctx->sched_flags))) {
+                        if (!(status & SPU_STATUS_STOPPED_BY_STOP)) {
+                                spu_switch_notify(spu, ctx);
+                                continue;
+                        }
+                }
+
+                spuctx_switch_state(ctx, SPU_UTIL_SYSTEM);
+
                 if ((status & SPU_STATUS_STOPPED_BY_STOP) &&
                     (status >> SPU_STOP_STATUS_SHIFT == 0x2104)) {
                         ret = spu_process_callback(ctx);
@@ -356,6 +375,7 @@ long spufs_run_spu(struct file *file, struct spu_context *ctx,
             (ctx->state == SPU_STATE_RUNNABLE))
                 ctx->stats.libassist++;
 
+
         ctx->ops->master_stop(ctx);
         ret = spu_run_fini(ctx, npc, &status);
         spu_yield(ctx);
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index e5b4dd1db286..227968b4779d 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -51,9 +51,6 @@ struct spu_prio_array {
         DECLARE_BITMAP(bitmap, MAX_PRIO);
         struct list_head runq[MAX_PRIO];
         spinlock_t runq_lock;
-        struct list_head active_list[MAX_NUMNODES];
-        struct mutex active_mutex[MAX_NUMNODES];
-        int nr_active[MAX_NUMNODES];
         int nr_waiting;
 };
 
@@ -127,7 +124,7 @@ void __spu_update_sched_info(struct spu_context *ctx)
         ctx->policy = current->policy;
 
         /*
-         * A lot of places that don't hold active_mutex poke into
+         * A lot of places that don't hold list_mutex poke into
          * cpus_allowed, including grab_runnable_context which
          * already holds the runq_lock.  So abuse runq_lock
          * to protect this field aswell.
@@ -141,9 +138,9 @@ void spu_update_sched_info(struct spu_context *ctx)
 {
         int node = ctx->spu->node;
 
-        mutex_lock(&spu_prio->active_mutex[node]);
+        mutex_lock(&cbe_spu_info[node].list_mutex);
         __spu_update_sched_info(ctx);
-        mutex_unlock(&spu_prio->active_mutex[node]);
+        mutex_unlock(&cbe_spu_info[node].list_mutex);
 }
 
 static int __node_allowed(struct spu_context *ctx, int node)
@@ -169,56 +166,56 @@ static int node_allowed(struct spu_context *ctx, int node)
         return rval;
 }
 
-/**
- * spu_add_to_active_list - add spu to active list
- * @spu:        spu to add to the active list
- */
-static void spu_add_to_active_list(struct spu *spu)
-{
-        int node = spu->node;
-
-        mutex_lock(&spu_prio->active_mutex[node]);
-        spu_prio->nr_active[node]++;
-        list_add_tail(&spu->list, &spu_prio->active_list[node]);
-        mutex_unlock(&spu_prio->active_mutex[node]);
-}
+static BLOCKING_NOTIFIER_HEAD(spu_switch_notifier);
 
-static void __spu_remove_from_active_list(struct spu *spu)
+void spu_switch_notify(struct spu *spu, struct spu_context *ctx)
 {
-        list_del_init(&spu->list);
-        spu_prio->nr_active[spu->node]--;
+        blocking_notifier_call_chain(&spu_switch_notifier,
+                            ctx ? ctx->object_id : 0, spu);
 }
 
-/**
- * spu_remove_from_active_list - remove spu from active list
- * @spu:       spu to remove from the active list
- */
-static void spu_remove_from_active_list(struct spu *spu)
+static void notify_spus_active(void)
 {
-        int node = spu->node;
-
-        mutex_lock(&spu_prio->active_mutex[node]);
-        __spu_remove_from_active_list(spu);
-        mutex_unlock(&spu_prio->active_mutex[node]);
-}
+        int node;
 
-static BLOCKING_NOTIFIER_HEAD(spu_switch_notifier);
+        /*
+         * Wake up the active spu_contexts.
+         *
+         * When the awakened processes see their "notify_active" flag is set,
+         * they will call spu_switch_notify();
+         */
+        for_each_online_node(node) {
+                struct spu *spu;
 
-static void spu_switch_notify(struct spu *spu, struct spu_context *ctx)
-{
-        blocking_notifier_call_chain(&spu_switch_notifier,
-                            ctx ? ctx->object_id : 0, spu);
+                mutex_lock(&cbe_spu_info[node].list_mutex);
+                list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) {
+                        if (spu->alloc_state != SPU_FREE) {
+                                struct spu_context *ctx = spu->ctx;
+                                set_bit(SPU_SCHED_NOTIFY_ACTIVE,
+                                        &ctx->sched_flags);
+                                mb();
+                                wake_up_all(&ctx->stop_wq);
+                        }
+                }
+                mutex_unlock(&cbe_spu_info[node].list_mutex);
+        }
 }
 
 int spu_switch_event_register(struct notifier_block * n)
 {
-        return blocking_notifier_chain_register(&spu_switch_notifier, n);
+        int ret;
+        ret = blocking_notifier_chain_register(&spu_switch_notifier, n);
+        if (!ret)
+                notify_spus_active();
+        return ret;
 }
+EXPORT_SYMBOL_GPL(spu_switch_event_register);
 
 int spu_switch_event_unregister(struct notifier_block * n)
 {
         return blocking_notifier_chain_unregister(&spu_switch_notifier, n);
 }
+EXPORT_SYMBOL_GPL(spu_switch_event_unregister);
 
 /**
  * spu_bind_context - bind spu context to physical spu
@@ -229,6 +226,12 @@ static void spu_bind_context(struct spu *spu, struct spu_context *ctx)
 {
         pr_debug("%s: pid=%d SPU=%d NODE=%d\n", __FUNCTION__, current->pid,
                  spu->number, spu->node);
+        spuctx_switch_state(ctx, SPU_UTIL_SYSTEM);
+
+        if (ctx->flags & SPU_CREATE_NOSCHED)
+                atomic_inc(&cbe_spu_info[spu->node].reserved_spus);
+        if (!list_empty(&ctx->aff_list))
+                atomic_inc(&ctx->gang->aff_sched_count);
 
         ctx->stats.slb_flt_base = spu->stats.slb_flt;
         ctx->stats.class2_intr_base = spu->stats.class2_intr;
@@ -238,6 +241,7 @@ static void spu_bind_context(struct spu *spu, struct spu_context *ctx)
         ctx->spu = spu;
         ctx->ops = &spu_hw_ops;
         spu->pid = current->pid;
+        spu->tgid = current->tgid;
         spu_associate_mm(spu, ctx->owner);
         spu->ibox_callback = spufs_ibox_callback;
         spu->wbox_callback = spufs_wbox_callback;
@@ -251,7 +255,153 @@ static void spu_bind_context(struct spu *spu, struct spu_context *ctx)
         spu_cpu_affinity_set(spu, raw_smp_processor_id());
         spu_switch_notify(spu, ctx);
         ctx->state = SPU_STATE_RUNNABLE;
-        spu_switch_state(spu, SPU_UTIL_SYSTEM);
+
+        spuctx_switch_state(ctx, SPU_UTIL_IDLE_LOADED);
+}
+
+/*
+ * Must be used with the list_mutex held.
+ */
+static inline int sched_spu(struct spu *spu)
+{
+        BUG_ON(!mutex_is_locked(&cbe_spu_info[spu->node].list_mutex));
+
+        return (!spu->ctx || !(spu->ctx->flags & SPU_CREATE_NOSCHED));
+}
+
+static void aff_merge_remaining_ctxs(struct spu_gang *gang)
+{
+        struct spu_context *ctx;
+
+        list_for_each_entry(ctx, &gang->aff_list_head, aff_list) {
+                if (list_empty(&ctx->aff_list))
+                        list_add(&ctx->aff_list, &gang->aff_list_head);
+        }
+        gang->aff_flags |= AFF_MERGED;
+}
+
+static void aff_set_offsets(struct spu_gang *gang)
+{
+        struct spu_context *ctx;
+        int offset;
+
+        offset = -1;
+        list_for_each_entry_reverse(ctx, &gang->aff_ref_ctx->aff_list,
+                                                                aff_list) {
+                if (&ctx->aff_list == &gang->aff_list_head)
+                        break;
+                ctx->aff_offset = offset--;
+        }
+
+        offset = 0;
+        list_for_each_entry(ctx, gang->aff_ref_ctx->aff_list.prev, aff_list) {
+                if (&ctx->aff_list == &gang->aff_list_head)
+                        break;
+                ctx->aff_offset = offset++;
+        }
+
+        gang->aff_flags |= AFF_OFFSETS_SET;
+}
+
+static struct spu *aff_ref_location(struct spu_context *ctx, int mem_aff,
+                 int group_size, int lowest_offset)
+{
+        struct spu *spu;
+        int node, n;
+
+        /*
+         * TODO: A better algorithm could be used to find a good spu to be
+         *       used as reference location for the ctxs chain.
+         */
+        node = cpu_to_node(raw_smp_processor_id());
+        for (n = 0; n < MAX_NUMNODES; n++, node++) {
+                node = (node < MAX_NUMNODES) ? node : 0;
+                if (!node_allowed(ctx, node))
+                        continue;
+                mutex_lock(&cbe_spu_info[node].list_mutex);
+                list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) {
+                        if ((!mem_aff || spu->has_mem_affinity) &&
+                                                        sched_spu(spu)) {
+                                mutex_unlock(&cbe_spu_info[node].list_mutex);
+                                return spu;
+                        }
+                }
+                mutex_unlock(&cbe_spu_info[node].list_mutex);
+        }
+        return NULL;
+}
+
+static void aff_set_ref_point_location(struct spu_gang *gang)
+{
+        int mem_aff, gs, lowest_offset;
+        struct spu_context *ctx;
+        struct spu *tmp;
+
+        mem_aff = gang->aff_ref_ctx->flags & SPU_CREATE_AFFINITY_MEM;
+        lowest_offset = 0;
+        gs = 0;
+
+        list_for_each_entry(tmp, &gang->aff_list_head, aff_list)
+                gs++;
+
+        list_for_each_entry_reverse(ctx, &gang->aff_ref_ctx->aff_list,
+                                                                aff_list) {
+                if (&ctx->aff_list == &gang->aff_list_head)
+                        break;
+                lowest_offset = ctx->aff_offset;
+        }
+
+        gang->aff_ref_spu = aff_ref_location(ctx, mem_aff, gs, lowest_offset);
+}
+
+static struct spu *ctx_location(struct spu *ref, int offset, int node)
+{
+        struct spu *spu;
+
+        spu = NULL;
+        if (offset >= 0) {
+                list_for_each_entry(spu, ref->aff_list.prev, aff_list) {
+                        BUG_ON(spu->node != node);
+                        if (offset == 0)
+                                break;
+                        if (sched_spu(spu))
+                                offset--;
+                }
+        } else {
+                list_for_each_entry_reverse(spu, ref->aff_list.next, aff_list) {
+                        BUG_ON(spu->node != node);
+                        if (offset == 0)
+                                break;
+                        if (sched_spu(spu))
+                                offset++;
+                }
+        }
+
+        return spu;
+}
+
+/*
+ * affinity_check is called each time a context is going to be scheduled.
+ * It returns the spu ptr on which the context must run.
+ */
+static int has_affinity(struct spu_context *ctx)
+{
+        struct spu_gang *gang = ctx->gang;
+
+        if (list_empty(&ctx->aff_list))
+                return 0;
+
+        mutex_lock(&gang->aff_mutex);
+        if (!gang->aff_ref_spu) {
+                if (!(gang->aff_flags & AFF_MERGED))
+                        aff_merge_remaining_ctxs(gang);
+                if (!(gang->aff_flags & AFF_OFFSETS_SET))
+                        aff_set_offsets(gang);
+                aff_set_ref_point_location(gang);
+        }
+        mutex_unlock(&gang->aff_mutex);
+
+        return gang->aff_ref_spu != NULL;
 }
 
 /**
@@ -263,9 +413,13 @@ static void spu_unbind_context(struct spu *spu, struct spu_context *ctx)
 {
         pr_debug("%s: unbind pid=%d SPU=%d NODE=%d\n", __FUNCTION__,
                  spu->pid, spu->number, spu->node);
+        spuctx_switch_state(ctx, SPU_UTIL_SYSTEM);
 
-        spu_switch_state(spu, SPU_UTIL_IDLE);
-
+        if (spu->ctx->flags & SPU_CREATE_NOSCHED)
+                atomic_dec(&cbe_spu_info[spu->node].reserved_spus);
+        if (!list_empty(&ctx->aff_list))
+                if (atomic_dec_and_test(&ctx->gang->aff_sched_count))
+                        ctx->gang->aff_ref_spu = NULL;
         spu_switch_notify(spu, NULL);
         spu_unmap_mappings(ctx);
         spu_save(&ctx->csa, spu);
@@ -278,8 +432,8 @@ static void spu_unbind_context(struct spu *spu, struct spu_context *ctx)
         spu->dma_callback = NULL;
         spu_associate_mm(spu, NULL);
         spu->pid = 0;
+        spu->tgid = 0;
         ctx->ops = &spu_backing_ops;
-        ctx->spu = NULL;
         spu->flags = 0;
         spu->ctx = NULL;
 
@@ -287,6 +441,10 @@ static void spu_unbind_context(struct spu *spu, struct spu_context *ctx)
                 (spu->stats.slb_flt - ctx->stats.slb_flt_base);
         ctx->stats.class2_intr +=
                 (spu->stats.class2_intr - ctx->stats.class2_intr_base);
+
+        /* This maps the underlying spu state to idle */
+        spuctx_switch_state(ctx, SPU_UTIL_IDLE_LOADED);
+        ctx->spu = NULL;
 }
 
 /**
@@ -352,18 +510,41 @@ static void spu_prio_wait(struct spu_context *ctx)
 
 static struct spu *spu_get_idle(struct spu_context *ctx)
 {
-        struct spu *spu = NULL;
-        int node = cpu_to_node(raw_smp_processor_id());
-        int n;
+        struct spu *spu;
+        int node, n;
+
+        if (has_affinity(ctx)) {
+                node = ctx->gang->aff_ref_spu->node;
 
+                mutex_lock(&cbe_spu_info[node].list_mutex);
+                spu = ctx_location(ctx->gang->aff_ref_spu, ctx->aff_offset, node);
+                if (spu && spu->alloc_state == SPU_FREE)
+                        goto found;
+                mutex_unlock(&cbe_spu_info[node].list_mutex);
+                return NULL;
+        }
+
+        node = cpu_to_node(raw_smp_processor_id());
         for (n = 0; n < MAX_NUMNODES; n++, node++) {
                 node = (node < MAX_NUMNODES) ? node : 0;
                 if (!node_allowed(ctx, node))
                         continue;
-                spu = spu_alloc_node(node);
-                if (spu)
-                        break;
+
+                mutex_lock(&cbe_spu_info[node].list_mutex);
+                list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) {
+                        if (spu->alloc_state == SPU_FREE)
+                                goto found;
+                }
+                mutex_unlock(&cbe_spu_info[node].list_mutex);
         }
+
+        return NULL;
+
+ found:
+        spu->alloc_state = SPU_USED;
+        mutex_unlock(&cbe_spu_info[node].list_mutex);
+        pr_debug("Got SPU %d %d\n", spu->number, spu->node);
+        spu_init_channels(spu);
         return spu;
 }
 
@@ -393,15 +574,15 @@ static struct spu *find_victim(struct spu_context *ctx)
                 if (!node_allowed(ctx, node))
                         continue;
 
-                mutex_lock(&spu_prio->active_mutex[node]);
-                list_for_each_entry(spu, &spu_prio->active_list[node], list) {
+                mutex_lock(&cbe_spu_info[node].list_mutex);
+                list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) {
                         struct spu_context *tmp = spu->ctx;
 
                         if (tmp->prio > ctx->prio &&
                             (!victim || tmp->prio > victim->prio))
                                 victim = spu->ctx;
                 }
-                mutex_unlock(&spu_prio->active_mutex[node]);
+                mutex_unlock(&cbe_spu_info[node].list_mutex);
 
                 if (victim) {
                         /*
@@ -426,7 +607,11 @@ static struct spu *find_victim(struct spu_context *ctx)
                                 victim = NULL;
                                 goto restart;
                         }
-                        spu_remove_from_active_list(spu);
+
+                        mutex_lock(&cbe_spu_info[node].list_mutex);
+                        cbe_spu_info[node].nr_active--;
+                        mutex_unlock(&cbe_spu_info[node].list_mutex);
+
                         spu_unbind_context(spu, victim);
                         victim->stats.invol_ctx_switch++;
                         spu->stats.invol_ctx_switch++;
@@ -455,8 +640,6 @@ static struct spu *find_victim(struct spu_context *ctx)
  */
 int spu_activate(struct spu_context *ctx, unsigned long flags)
 {
-        spuctx_switch_state(ctx, SPUCTX_UTIL_SYSTEM);
-
         do {
                 struct spu *spu;
 
@@ -477,8 +660,12 @@ int spu_activate(struct spu_context *ctx, unsigned long flags)
                 if (!spu && rt_prio(ctx->prio))
                         spu = find_victim(ctx);
                 if (spu) {
+                        int node = spu->node;
+
+                        mutex_lock(&cbe_spu_info[node].list_mutex);
                         spu_bind_context(spu, ctx);
-                        spu_add_to_active_list(spu);
+                        cbe_spu_info[node].nr_active++;
+                        mutex_unlock(&cbe_spu_info[node].list_mutex);
                         return 0;
                 }
 
@@ -500,7 +687,7 @@ static struct spu_context *grab_runnable_context(int prio, int node)
         int best;
 
         spin_lock(&spu_prio->runq_lock);
-        best = sched_find_first_bit(spu_prio->bitmap);
+        best = find_first_bit(spu_prio->bitmap, prio);
         while (best < prio) {
                 struct list_head *rq = &spu_prio->runq[best];
 
@@ -527,11 +714,17 @@ static int __spu_deactivate(struct spu_context *ctx, int force, int max_prio)
         if (spu) {
                 new = grab_runnable_context(max_prio, spu->node);
                 if (new || force) {
-                        spu_remove_from_active_list(spu);
+                        int node = spu->node;
+
+                        mutex_lock(&cbe_spu_info[node].list_mutex);
                         spu_unbind_context(spu, ctx);
+                        spu->alloc_state = SPU_FREE;
+                        cbe_spu_info[node].nr_active--;
+                        mutex_unlock(&cbe_spu_info[node].list_mutex);
+
                         ctx->stats.vol_ctx_switch++;
                         spu->stats.vol_ctx_switch++;
-                        spu_free(spu);
+
                         if (new)
                                 wake_up(&new->stop_wq);
                 }
@@ -550,21 +743,11 @@ static int __spu_deactivate(struct spu_context *ctx, int force, int max_prio)
  */
 void spu_deactivate(struct spu_context *ctx)
 {
-        /*
-         * We must never reach this for a nosched context,
-         * but handle the case gracefull instead of panicing.
-         */
-        if (ctx->flags & SPU_CREATE_NOSCHED) {
-                WARN_ON(1);
-                return;
-        }
-
         __spu_deactivate(ctx, 1, MAX_PRIO);
-        spuctx_switch_state(ctx, SPUCTX_UTIL_USER);
 }
 
 /**
- * spu_yield -  yield a physical spu if others are waiting
+ * spu_yield -  yield a physical spu if others are waiting
  * @ctx:        spu context to yield
  *
  * Check if there is a higher priority context waiting and if yes
@@ -575,17 +758,12 @@ void spu_yield(struct spu_context *ctx)
 {
         if (!(ctx->flags & SPU_CREATE_NOSCHED)) {
                 mutex_lock(&ctx->state_mutex);
-                if (__spu_deactivate(ctx, 0, MAX_PRIO))
-                        spuctx_switch_state(ctx, SPUCTX_UTIL_USER);
-                else {
-                        spuctx_switch_state(ctx, SPUCTX_UTIL_LOADED);
-                        spu_switch_state(ctx->spu, SPU_UTIL_USER);
-                }
+                __spu_deactivate(ctx, 0, MAX_PRIO);
                 mutex_unlock(&ctx->state_mutex);
         }
 }
 
-static void spusched_tick(struct spu_context *ctx)
+static noinline void spusched_tick(struct spu_context *ctx)
 {
         if (ctx->flags & SPU_CREATE_NOSCHED)
                 return;
@@ -596,7 +774,7 @@ static void spusched_tick(struct spu_context *ctx)
                 return;
 
         /*
-         * Unfortunately active_mutex ranks outside of state_mutex, so
+         * Unfortunately list_mutex ranks outside of state_mutex, so
          * we have to trylock here.  If we fail give the context another
          * tick and try again.
          */
@@ -606,12 +784,11 @@ static void spusched_tick(struct spu_context *ctx)
 
                 new = grab_runnable_context(ctx->prio + 1, spu->node);
                 if (new) {
-
-                        __spu_remove_from_active_list(spu);
                         spu_unbind_context(spu, ctx);
                         ctx->stats.invol_ctx_switch++;
                         spu->stats.invol_ctx_switch++;
-                        spu_free(spu);
+                        spu->alloc_state = SPU_FREE;
+                        cbe_spu_info[spu->node].nr_active--;
                         wake_up(&new->stop_wq);
                         /*
                          * We need to break out of the wait loop in
@@ -632,7 +809,7 @@ static void spusched_tick(struct spu_context *ctx)
  *
  * Return the number of tasks currently running or waiting to run.
  *
- * Note that we don't take runq_lock / active_mutex here.  Reading
+ * Note that we don't take runq_lock / list_mutex here.  Reading
  * a single 32bit value is atomic on powerpc, and we don't care
  * about memory ordering issues here.
  */
@@ -641,7 +818,7 @@ static unsigned long count_active_contexts(void)
         int nr_active = 0, node;
 
         for (node = 0; node < MAX_NUMNODES; node++)
-                nr_active += spu_prio->nr_active[node];
+                nr_active += cbe_spu_info[node].nr_active;
         nr_active += spu_prio->nr_waiting;
 
         return nr_active;
@@ -681,19 +858,18 @@ static void spusched_wake(unsigned long data)
 
 static int spusched_thread(void *unused)
 {
-        struct spu *spu, *next;
+        struct spu *spu;
         int node;
 
         while (!kthread_should_stop()) {
                 set_current_state(TASK_INTERRUPTIBLE);
                 schedule();
                 for (node = 0; node < MAX_NUMNODES; node++) {
-                        mutex_lock(&spu_prio->active_mutex[node]);
-                        list_for_each_entry_safe(spu, next,
-                                                 &spu_prio->active_list[node],
-                                                 list)
-                                spusched_tick(spu->ctx);
-                        mutex_unlock(&spu_prio->active_mutex[node]);
+                        mutex_lock(&cbe_spu_info[node].list_mutex);
+                        list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list)
+                                if (spu->ctx)
+                                        spusched_tick(spu->ctx);
+                        mutex_unlock(&cbe_spu_info[node].list_mutex);
                 }
         }
 
@@ -751,10 +927,9 @@ int __init spu_sched_init(void)
                 INIT_LIST_HEAD(&spu_prio->runq[i]);
                 __clear_bit(i, spu_prio->bitmap);
         }
-        __set_bit(MAX_PRIO, spu_prio->bitmap);
         for (i = 0; i < MAX_NUMNODES; i++) {
-                mutex_init(&spu_prio->active_mutex[i]);
-                INIT_LIST_HEAD(&spu_prio->active_list[i]);
+                mutex_init(&cbe_spu_info[i].list_mutex);
+                INIT_LIST_HEAD(&cbe_spu_info[i].spus);
         }
         spin_lock_init(&spu_prio->runq_lock);
 
@@ -783,9 +958,9 @@ int __init spu_sched_init(void)
         return err;
 }
 
-void __exit spu_sched_exit(void)
+void spu_sched_exit(void)
 {
-        struct spu *spu, *tmp;
+        struct spu *spu;
         int node;
 
         remove_proc_entry("spu_loadavg", NULL);
@@ -794,13 +969,11 @@ void __exit spu_sched_exit(void)
         kthread_stop(spusched_task);
 
         for (node = 0; node < MAX_NUMNODES; node++) {
-                mutex_lock(&spu_prio->active_mutex[node]);
-                list_for_each_entry_safe(spu, tmp, &spu_prio->active_list[node],
-                                         list) {
-                        list_del_init(&spu->list);
-                        spu_free(spu);
-                }
-                mutex_unlock(&spu_prio->active_mutex[node]);
+                mutex_lock(&cbe_spu_info[node].list_mutex);
+                list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list)
+                        if (spu->alloc_state != SPU_FREE)
+                                spu->alloc_state = SPU_FREE;
+                mutex_unlock(&cbe_spu_info[node].list_mutex);
         }
         kfree(spu_prio);
 }
diff --git a/arch/powerpc/platforms/cell/spufs/spu_restore.c b/arch/powerpc/platforms/cell/spufs/spu_restore.c
index 4e19ed7a0756..21a9c952d88b 100644
--- a/arch/powerpc/platforms/cell/spufs/spu_restore.c
+++ b/arch/powerpc/platforms/cell/spufs/spu_restore.c
@@ -84,13 +84,13 @@ static inline void restore_decr(void)
         unsigned int decr_running;
         unsigned int decr;
 
-        /* Restore, Step 6:
+        /* Restore, Step 6(moved):
          *    If the LSCSA "decrementer running" flag is set
          *    then write the SPU_WrDec channel with the
          *    decrementer value from LSCSA.
          */
         offset = LSCSA_QW_OFFSET(decr_status);
-        decr_running = regs_spill[offset].slot[0];
+        decr_running = regs_spill[offset].slot[0] & SPU_DECR_STATUS_RUNNING;
         if (decr_running) {
                 offset = LSCSA_QW_OFFSET(decr);
                 decr = regs_spill[offset].slot[0];
@@ -318,10 +318,10 @@ int main()
         build_dma_list(lscsa_ea);       /* Step 3.  */
         restore_upper_240kb(lscsa_ea);  /* Step 4.  */
                                         /* Step 5: done by 'exit'. */
-        restore_decr();                 /* Step 6. */
         enqueue_putllc(lscsa_ea);       /* Step 7. */
         set_tag_update();               /* Step 8. */
         read_tag_status();              /* Step 9. */
+        restore_decr();                 /* moved Step 6. */
         read_llar_status();             /* Step 10. */
         write_ppu_mb();                 /* Step 11. */
         write_ppuint_mb();              /* Step 12. */
diff --git a/arch/powerpc/platforms/cell/spufs/spu_restore_dump.h_shipped b/arch/powerpc/platforms/cell/spufs/spu_restore_dump.h_shipped
index 15183d209b58..f383b027e8bf 100644
--- a/arch/powerpc/platforms/cell/spufs/spu_restore_dump.h_shipped
+++ b/arch/powerpc/platforms/cell/spufs/spu_restore_dump.h_shipped
@@ -10,7 +10,7 @@ static unsigned int spu_restore_code[]  __attribute__((__aligned__(128))) = {
 0x24fd8081,
 0x1cd80081,
 0x33001180,
-0x42030003,
+0x42034003,
 0x33800284,
 0x1c010204,
 0x40200000,
@@ -24,22 +24,22 @@ static unsigned int spu_restore_code[]  __attribute__((__aligned__(128))) = {
 0x23fffd84,
 0x1c100183,
 0x217ffa85,
-0x3080a000,
-0x3080a201,
-0x3080a402,
-0x3080a603,
-0x3080a804,
-0x3080aa05,
-0x3080ac06,
-0x3080ae07,
-0x3080b008,
-0x3080b209,
-0x3080b40a,
-0x3080b60b,
-0x3080b80c,
-0x3080ba0d,
-0x3080bc0e,
-0x3080be0f,
+0x3080b000,
+0x3080b201,
+0x3080b402,
+0x3080b603,
+0x3080b804,
+0x3080ba05,
+0x3080bc06,
+0x3080be07,
+0x3080c008,
+0x3080c209,
+0x3080c40a,
+0x3080c60b,
+0x3080c80c,
+0x3080ca0d,
+0x3080cc0e,
+0x3080ce0f,
 0x00003ffc,
 0x00000000,
 0x00000000,
@@ -48,19 +48,18 @@ static unsigned int spu_restore_code[]  __attribute__((__aligned__(128))) = {
 0x3ec00083,
 0xb0a14103,
 0x01a00204,
-0x3ec10082,
-0x4202800e,
-0x04000703,
-0xb0a14202,
-0x21a00803,
-0x3fbf028d,
-0x3f20068d,
-0x3fbe0682,
+0x3ec10083,
+0x4202c002,
+0xb0a14203,
+0x21a00802,
+0x3fbf028a,
+0x3f20050a,
+0x3fbe0502,
 0x3fe30102,
 0x21a00882,
-0x3f82028f,
-0x3fe3078f,
-0x3fbf0784,
+0x3f82028b,
+0x3fe3058b,
+0x3fbf0584,
 0x3f200204,
 0x3fbe0204,
 0x3fe30204,
@@ -75,252 +74,285 @@ static unsigned int spu_restore_code[]  __attribute__((__aligned__(128))) = {
 0x21a00083,
 0x40800082,
 0x21a00b02,
-0x10002818,
-0x42a00002,
-0x32800007,
-0x4207000c,
-0x18008208,
-0x40a0000b,
-0x4080020a,
-0x40800709,
-0x00200000,
-0x42070002,
-0x3ac30384,
+0x10002612,
+0x42a00003,
+0x42074006,
+0x1800c204,
+0x40a00008,
+0x40800789,
+0x1c010305,
+0x34000302,
 0x1cffc489,
-0x00200000,
-0x18008383,
-0x38830382,
-0x4cffc486,
-0x3ac28185,
-0xb0408584,
-0x28830382,
-0x1c020387,
-0x38828182,
-0xb0408405,
-0x1802c408,
-0x28828182,
-0x217ff886,
-0x04000583,
-0x21a00803,
-0x3fbe0682,
-0x3fe30102,
-0x04000106,
-0x21a00886,
-0x04000603,
-0x21a00903,
-0x40803c02,
-0x21a00982,
-0x40800003,
-0x04000184,
-0x21a00a04,
+0x3ec00303,
+0x3ec00287,
+0xb0408403,
+0x24000302,
+0x34000282,
+0x1c020306,
+0xb0408207,
+0x18020204,
+0x24000282,
+0x217ffa09,
+0x04000402,
+0x21a00802,
+0x3fbe0504,
+0x3fe30204,
+0x21a00884,
+0x42074002,
+0x21a00902,
+0x40803c03,
+0x21a00983,
+0x04000485,
+0x21a00a05,
 0x40802202,
 0x21a00a82,
-0x42028005,
-0x34208702,
-0x21002282,
-0x21a00804,
-0x21a00886,
-0x3fbf0782,
+0x21a00805,
+0x21a00884,
+0x3fbf0582,
 0x3f200102,
 0x3fbe0102,
 0x3fe30102,
 0x21a00902,
 0x40804003,
 0x21a00983,
-0x21a00a04,
+0x21a00a05,
 0x40805a02,
 0x21a00a82,
 0x40800083,
 0x21a00b83,
 0x01a00c02,
-0x01a00d83,
-0x3420c282,
+0x30809c03,
+0x34000182,
+0x14004102,
+0x21002082,
+0x01a00d82,
+0x3080a003,
+0x34000182,
 0x21a00e02,
-0x34210283,
-0x21a00f03,
-0x34200284,
-0x77400200,
-0x3421c282,
+0x3080a203,
+0x34000182,
+0x21a00f02,
+0x3080a403,
+0x34000182,
+0x77400100,
+0x3080a603,
+0x34000182,
 0x21a00702,
-0x34218283,
-0x21a00083,
-0x34214282,
+0x3080a803,
+0x34000182,
+0x21a00082,
+0x3080aa03,
+0x34000182,
 0x21a00b02,
-0x4200480c,
-0x00200000,
-0x1c010286,
-0x34220284,
-0x34220302,
-0x0f608203,
-0x5c024204,
-0x3b81810b,
-0x42013c02,
-0x00200000,
-0x18008185,
-0x38808183,
-0x3b814182,
-0x21004e84,
+0x4020007f,
+0x3080ae02,
+0x42004805,
+0x3080ac04,
+0x34000103,
+0x34000202,
+0x1cffc183,
+0x3b810106,
+0x0f608184,
+0x42013802,
+0x5c020183,
+0x38810102,
+0x3b810102,
+0x21000e83,
 0x4020007f,
 0x35000100,
-0x000004e0,
-0x000002a0,
-0x000002e8,
-0x00000428,
+0x00000470,
+0x000002f8,
+0x00000430,
 0x00000360,
-0x000002e8,
-0x000004a0,
-0x00000468,
+0x000002f8,
 0x000003c8,
+0x000004a8,
+0x00000298,
 0x00000360,
+0x00200000,
 0x409ffe02,
 0x30801203,
-0x40800204,
-0x3ec40085,
-0x10009c09,
-0x3ac10606,
-0xb060c105,
-0x4020007f,
-0x4020007f,
+0x40800208,
+0x3ec40084,
+0x40800407,
+0x3ac20289,
+0xb060c104,
+0x3ac1c284,
 0x20801203,
-0x38810602,
-0xb0408586,
-0x28810602,
-0x32004180,
-0x34204702,
+0x38820282,
+0x41004003,
+0xb0408189,
+0x28820282,
+0x3881c282,
+0xb0408304,
+0x2881c282,
+0x00400000,
+0x40800003,
+0x35000000,
+0x30809e03,
+0x34000182,
 0x21a00382,
 0x4020007f,
-0x327fdc80,
+0x327fde00,
 0x409ffe02,
 0x30801203,
-0x40800204,
-0x3ec40087,
-0x40800405,
-0x00200000,
-0x40800606,
-0x3ac10608,
-0x3ac14609,
-0x3ac1860a,
-0xb060c107,
+0x40800206,
+0x3ec40084,
+0x40800407,
+0x40800608,
+0x3ac1828a,
+0x3ac20289,
+0xb060c104,
+0x3ac1c284,
 0x20801203,
+0x38818282,
 0x41004003,
-0x38810602,
-0x4020007f,
-0xb0408188,
-0x4020007f,
-0x28810602,
-0x41201002,
-0x38814603,
-0x10009c09,
-0xb060c109,
-0x4020007f,
-0x28814603,
+0xb040818a,
+0x10005b0b,
+0x41201003,
+0x28818282,
+0x3881c282,
+0xb0408184,
 0x41193f83,
-0x38818602,
 0x60ffc003,
-0xb040818a,
-0x28818602,
-0x32003080,
+0x2881c282,
+0x38820282,
+0xb0408189,
+0x28820282,
+0x327fef80,
 0x409ffe02,
 0x30801203,
-0x40800204,
-0x3ec40087,
-0x41201008,
-0x10009c14,
-0x40800405,
-0x3ac10609,
-0x40800606,
-0x3ac1460a,
-0xb060c107,
-0x3ac1860b,
+0x40800207,
+0x3ec40086,
+0x4120100b,
+0x10005b14,
+0x40800404,
+0x3ac1c289,
+0x40800608,
+0xb060c106,
+0x3ac10286,
+0x3ac2028a,
 0x20801203,
-0x38810602,
-0xb0408409,
-0x28810602,
-0x38814603,
-0xb060c40a,
-0x4020007f,
-0x28814603,
+0x3881c282,
 0x41193f83,
-0x38818602,
 0x60ffc003,
-0xb040818b,
-0x28818602,
-0x32002380,
-0x409ffe02,
-0x30801204,
-0x40800205,
-0x3ec40083,
-0x40800406,
-0x3ac14607,
-0x3ac18608,
-0xb0810103,
-0x41004002,
-0x20801204,
-0x4020007f,
-0x38814603,
-0x10009c0b,
-0xb060c107,
-0x4020007f,
-0x4020007f,
-0x28814603,
-0x38818602,
-0x4020007f,
+0xb0408589,
+0x2881c282,
+0x38810282,
+0xb0408586,
+0x28810282,
+0x38820282,
+0xb040818a,
+0x28820282,
 0x4020007f,
-0xb0408588,
-0x28818602,
+0x327fe280,
+0x409ffe02,
+0x30801203,
+0x40800207,
+0x3ec40084,
+0x40800408,
+0x10005b14,
+0x40800609,
+0x3ac1c28a,
+0x3ac2028b,
+0xb060c104,
+0x3ac24284,
+0x20801203,
+0x41201003,
+0x3881c282,
+0xb040830a,
+0x2881c282,
+0x38820282,
+0xb040818b,
+0x41193f83,
+0x60ffc003,
+0x28820282,
+0x38824282,
+0xb0408184,
+0x28824282,
 0x4020007f,
-0x32001780,
+0x327fd580,
 0x409ffe02,
-0x1000640e,
-0x40800204,
+0x1000658e,
+0x40800206,
 0x30801203,
-0x40800405,
-0x3ec40087,
-0x40800606,
-0x3ac10608,
-0x3ac14609,
-0x3ac1860a,
-0xb060c107,
+0x40800407,
+0x3ec40084,
+0x40800608,
+0x3ac1828a,
+0x3ac20289,
+0xb060c104,
+0x3ac1c284,
 0x20801203,
 0x413d8003,
-0x38810602,
+0x38818282,
 0x4020007f,
-0x327fd780,
-0x409ffe02,
-0x10007f0c,
-0x40800205,
-0x30801204,
-0x40800406,
-0x3ec40083,
-0x3ac14607,
-0x3ac18608,
-0xb0810103,
-0x413d8002,
-0x20801204,
-0x38814603,
+0x327fd800,
+0x409ffe03,
+0x30801202,
+0x40800207,
+0x3ec40084,
+0x10005b09,
+0x3ac1c288,
+0xb0408184,
 0x4020007f,
-0x327feb80,
+0x4020007f,
+0x20801202,
+0x3881c282,
+0xb0408308,
+0x2881c282,
+0x327fc680,
 0x409ffe02,
+0x1000588b,
+0x40800208,
 0x30801203,
-0x40800204,
-0x3ec40087,
-0x40800405,
-0x1000650a,
-0x40800606,
-0x3ac10608,
-0x3ac14609,
-0x3ac1860a,
-0xb060c107,
+0x40800407,
+0x3ec40084,
+0x3ac20289,
+0xb060c104,
+0x3ac1c284,
 0x20801203,
-0x38810602,
-0xb0408588,
-0x4020007f,
-0x327fc980,
-0x00400000,
-0x40800003,
-0x4020007f,
-0x35000000,
+0x413d8003,
+0x38820282,
+0x327fbd80,
+0x00200000,
+0x00000da0,
+0x00000000,
+0x00000000,
+0x00000000,
+0x00000d90,
+0x00000000,
+0x00000000,
+0x00000000,
+0x00000db0,
+0x00000000,
+0x00000000,
+0x00000000,
+0x00000dc0,
+0x00000000,
+0x00000000,
+0x00000000,
+0x00000d80,
+0x00000000,
+0x00000000,
+0x00000000,
+0x00000df0,
+0x00000000,
+0x00000000,
+0x00000000,
+0x00000de0,
+0x00000000,
+0x00000000,
+0x00000000,
+0x00000dd0,
+0x00000000,
+0x00000000,
+0x00000000,
+0x00000e04,
+0x00000000,
+0x00000000,
 0x00000000,
+0x00000e00,
 0x00000000,
 0x00000000,
 0x00000000,
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index 08b3530288ac..8b20c0c1556f 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -40,17 +40,13 @@ enum {
 struct spu_context_ops;
 struct spu_gang;
 
-/*
- * This is the state for spu utilization reporting to userspace.
- * Because this state is visible to userspace it must never change and needs
- * to be kept strictly separate from any internal state kept by the kernel.
- */
-enum spuctx_execution_state {
-        SPUCTX_UTIL_USER = 0,
-        SPUCTX_UTIL_SYSTEM,
-        SPUCTX_UTIL_IOWAIT,
-        SPUCTX_UTIL_LOADED,
-        SPUCTX_UTIL_MAX
+enum {
+        SPU_SCHED_WAS_ACTIVE,   /* was active upon spu_acquire_saved()  */
+};
+
+/* ctx->sched_flags */
+enum {
+        SPU_SCHED_NOTIFY_ACTIVE,
 };
 
 struct spu_context {
@@ -89,6 +85,8 @@ struct spu_context {
 
         struct list_head gang_list;
         struct spu_gang *gang;
+        struct kref *prof_priv_kref;
+        void ( * prof_priv_release) (struct kref *kref);
 
         /* owner thread */
         pid_t tid;
@@ -104,9 +102,9 @@ struct spu_context {
         /* statistics */
         struct {
                 /* updates protected by ctx->state_mutex */
-                enum spuctx_execution_state execution_state;
-                unsigned long tstamp;           /* time of last ctx switch */
-                unsigned long times[SPUCTX_UTIL_MAX];
+                enum spu_utilization_state util_state;
+                unsigned long long tstamp;      /* time of last state switch */
+                unsigned long long times[SPU_UTIL_MAX];
                 unsigned long long vol_ctx_switch;
                 unsigned long long invol_ctx_switch;
                 unsigned long long min_flt;
@@ -118,6 +116,10 @@ struct spu_context {
                 unsigned long long class2_intr_base; /* # at last ctx switch */
                 unsigned long long libassist;
         } stats;
+
+        struct list_head aff_list;
+        int aff_head;
+        int aff_offset;
 };
 
 struct spu_gang {
@@ -125,8 +127,19 @@ struct spu_gang {
         struct mutex mutex;
         struct kref kref;
         int contexts;
+
+        struct spu_context *aff_ref_ctx;
+        struct list_head aff_list_head;
+        struct mutex aff_mutex;
+        int aff_flags;
+        struct spu *aff_ref_spu;
+        atomic_t aff_sched_count;
 };
 
+/* Flag bits for spu_gang aff_flags */
+#define AFF_OFFSETS_SET         1
+#define AFF_MERGED              2
+
 struct mfc_dma_command {
         int32_t pad;    /* reserved */
         uint32_t lsa;   /* local storage address */
@@ -190,10 +203,9 @@ extern struct tree_descr spufs_dir_contents[];
 extern struct tree_descr spufs_dir_nosched_contents[];
 
 /* system call implementation */
-long spufs_run_spu(struct file *file,
-                   struct spu_context *ctx, u32 *npc, u32 *status);
-long spufs_create(struct nameidata *nd,
-                         unsigned int flags, mode_t mode);
+long spufs_run_spu(struct spu_context *ctx, u32 *npc, u32 *status);
+long spufs_create(struct nameidata *nd, unsigned int flags,
+                        mode_t mode, struct file *filp);
 extern const struct file_operations spufs_context_fops;
 
 /* gang management */
@@ -206,6 +218,9 @@ void spu_gang_add_ctx(struct spu_gang *gang, struct spu_context *ctx);
 /* fault handling */
 int spufs_handle_class1(struct spu_context *ctx);
 
+/* affinity */
+struct spu *affinity_check(struct spu_context *ctx);
+
 /* context management */
 extern atomic_t nr_spu_contexts;
 static inline void spu_acquire(struct spu_context *ctx)
@@ -227,15 +242,17 @@ void spu_unmap_mappings(struct spu_context *ctx);
 void spu_forget(struct spu_context *ctx);
 int spu_acquire_runnable(struct spu_context *ctx, unsigned long flags);
 void spu_acquire_saved(struct spu_context *ctx);
+void spu_release_saved(struct spu_context *ctx);
 
 int spu_activate(struct spu_context *ctx, unsigned long flags);
 void spu_deactivate(struct spu_context *ctx);
 void spu_yield(struct spu_context *ctx);
+void spu_switch_notify(struct spu *spu, struct spu_context *ctx);
 void spu_set_timeslice(struct spu_context *ctx);
 void spu_update_sched_info(struct spu_context *ctx);
 void __spu_update_sched_info(struct spu_context *ctx);
 int __init spu_sched_init(void);
-void __exit spu_sched_exit(void);
+void spu_sched_exit(void);
 
 extern char *isolated_loader;
 
@@ -293,30 +310,34 @@ extern int spufs_coredump_num_notes;
  * line.
  */
 static inline void spuctx_switch_state(struct spu_context *ctx,
-                enum spuctx_execution_state new_state)
+                enum spu_utilization_state new_state)
 {
-        WARN_ON(!mutex_is_locked(&ctx->state_mutex));
-
-        if (ctx->stats.execution_state != new_state) {
-                unsigned long curtime = jiffies;
-
-                ctx->stats.times[ctx->stats.execution_state] +=
-                                 curtime - ctx->stats.tstamp;
-                ctx->stats.tstamp = curtime;
-                ctx->stats.execution_state = new_state;
-        }
-}
+        unsigned long long curtime;
+        signed long long delta;
+        struct timespec ts;
+        struct spu *spu;
+        enum spu_utilization_state old_state;
 
-static inline void spu_switch_state(struct spu *spu,
-                enum spuctx_execution_state new_state)
-{
-        if (spu->stats.utilization_state != new_state) {
-                unsigned long curtime = jiffies;
+        ktime_get_ts(&ts);
+        curtime = timespec_to_ns(&ts);
+        delta = curtime - ctx->stats.tstamp;
 
-                spu->stats.times[spu->stats.utilization_state] +=
-                                 curtime - spu->stats.tstamp;
+        WARN_ON(!mutex_is_locked(&ctx->state_mutex));
+        WARN_ON(delta < 0);
+
+        spu = ctx->spu;
+        old_state = ctx->stats.util_state;
+        ctx->stats.util_state = new_state;
+        ctx->stats.tstamp = curtime;
+
+        /*
+         * Update the physical SPU utilization statistics.
+         */
+        if (spu) {
+                ctx->stats.times[old_state] += delta;
+                spu->stats.times[old_state] += delta;
+                spu->stats.util_state = new_state;
                 spu->stats.tstamp = curtime;
-                spu->stats.utilization_state = new_state;
         }
 }
 
diff --git a/arch/powerpc/platforms/cell/spufs/switch.c b/arch/powerpc/platforms/cell/spufs/switch.c
index 9c506ba08cdc..27ffdae98e5a 100644
--- a/arch/powerpc/platforms/cell/spufs/switch.c
+++ b/arch/powerpc/platforms/cell/spufs/switch.c
@@ -180,7 +180,7 @@ static inline void save_mfc_cntl(struct spu_state *csa, struct spu *spu)
         case MFC_CNTL_SUSPEND_COMPLETE:
                 if (csa) {
                         csa->priv2.mfc_control_RW =
-                                in_be64(&priv2->mfc_control_RW) |
+                                MFC_CNTL_SUSPEND_MASK |
                                 MFC_CNTL_SUSPEND_DMA_QUEUE;
                 }
                 break;
@@ -190,9 +190,7 @@ static inline void save_mfc_cntl(struct spu_state *csa, struct spu *spu)
                                   MFC_CNTL_SUSPEND_DMA_STATUS_MASK) ==
                                  MFC_CNTL_SUSPEND_COMPLETE);
                 if (csa) {
-                        csa->priv2.mfc_control_RW =
-                                in_be64(&priv2->mfc_control_RW) &
-                                ~MFC_CNTL_SUSPEND_DMA_QUEUE;
+                        csa->priv2.mfc_control_RW = 0;
                 }
                 break;
         }
@@ -251,16 +249,8 @@ static inline void save_mfc_decr(struct spu_state *csa, struct spu *spu)
          *     Read MFC_CNTL[Ds].  Update saved copy of
          *     CSA.MFC_CNTL[Ds].
          */
-        if (in_be64(&priv2->mfc_control_RW) & MFC_CNTL_DECREMENTER_RUNNING) {
-                csa->priv2.mfc_control_RW |= MFC_CNTL_DECREMENTER_RUNNING;
-                csa->suspend_time = get_cycles();
-                out_be64(&priv2->spu_chnlcntptr_RW, 7ULL);
-                eieio();
-                csa->spu_chnldata_RW[7] = in_be64(&priv2->spu_chnldata_RW);
-                eieio();
-        } else {
-                csa->priv2.mfc_control_RW &= ~MFC_CNTL_DECREMENTER_RUNNING;
-        }
+        csa->priv2.mfc_control_RW |=
+                in_be64(&priv2->mfc_control_RW) & MFC_CNTL_DECREMENTER_RUNNING;
 }
 
 static inline void halt_mfc_decr(struct spu_state *csa, struct spu *spu)
@@ -271,7 +261,8 @@ static inline void halt_mfc_decr(struct spu_state *csa, struct spu *spu)
          *     Write MFC_CNTL[Dh] set to a '1' to halt
          *     the decrementer.
          */
-        out_be64(&priv2->mfc_control_RW, MFC_CNTL_DECREMENTER_HALTED);
+        out_be64(&priv2->mfc_control_RW,
+                 MFC_CNTL_DECREMENTER_HALTED | MFC_CNTL_SUSPEND_MASK);
         eieio();
 }
 
@@ -615,7 +606,7 @@ static inline void save_ppuint_mb(struct spu_state *csa, struct spu *spu)
 static inline void save_ch_part1(struct spu_state *csa, struct spu *spu)
 {
         struct spu_priv2 __iomem *priv2 = spu->priv2;
-        u64 idx, ch_indices[7] = { 0UL, 3UL, 4UL, 24UL, 25UL, 27UL };
+        u64 idx, ch_indices[] = { 0UL, 3UL, 4UL, 24UL, 25UL, 27UL };
         int i;
 
         /* Save, Step 42:
@@ -626,7 +617,7 @@ static inline void save_ch_part1(struct spu_state *csa, struct spu *spu)
         csa->spu_chnldata_RW[1] = in_be64(&priv2->spu_chnldata_RW);
 
         /* Save the following CH: [0,3,4,24,25,27] */
-        for (i = 0; i < 7; i++) {
+        for (i = 0; i < ARRAY_SIZE(ch_indices); i++) {
                 idx = ch_indices[i];
                 out_be64(&priv2->spu_chnlcntptr_RW, idx);
                 eieio();
@@ -983,13 +974,13 @@ static inline void terminate_spu_app(struct spu_state *csa, struct spu *spu)
          */
 }
 
-static inline void suspend_mfc(struct spu_state *csa, struct spu *spu)
+static inline void suspend_mfc_and_halt_decr(struct spu_state *csa,
+                struct spu *spu)
 {
         struct spu_priv2 __iomem *priv2 = spu->priv2;
 
         /* Restore, Step 7:
-         * Restore, Step 47.
-         *     Write MFC_Cntl[Dh,Sc]='1','1' to suspend
+         *     Write MFC_Cntl[Dh,Sc,Sm]='1','1','0' to suspend
          *     the queue and halt the decrementer.
          */
         out_be64(&priv2->mfc_control_RW, MFC_CNTL_SUSPEND_DMA_QUEUE |
@@ -1090,7 +1081,7 @@ static inline void clear_spu_status(struct spu_state *csa, struct spu *spu)
 static inline void reset_ch_part1(struct spu_state *csa, struct spu *spu)
 {
         struct spu_priv2 __iomem *priv2 = spu->priv2;
-        u64 ch_indices[7] = { 0UL, 3UL, 4UL, 24UL, 25UL, 27UL };
+        u64 ch_indices[] = { 0UL, 3UL, 4UL, 24UL, 25UL, 27UL };
         u64 idx;
         int i;
 
@@ -1102,7 +1093,7 @@ static inline void reset_ch_part1(struct spu_state *csa, struct spu *spu)
         out_be64(&priv2->spu_chnldata_RW, 0UL);
 
         /* Reset the following CH: [0,3,4,24,25,27] */
-        for (i = 0; i < 7; i++) {
+        for (i = 0; i < ARRAY_SIZE(ch_indices); i++) {
                 idx = ch_indices[i];
                 out_be64(&priv2->spu_chnlcntptr_RW, idx);
                 eieio();
@@ -1289,7 +1280,15 @@ static inline void setup_decr(struct spu_state *csa, struct spu *spu)
                 cycles_t resume_time = get_cycles();
                 cycles_t delta_time = resume_time - csa->suspend_time;
 
+                csa->lscsa->decr_status.slot[0] = SPU_DECR_STATUS_RUNNING;
+                if (csa->lscsa->decr.slot[0] < delta_time) {
+                        csa->lscsa->decr_status.slot[0] |=
+                                 SPU_DECR_STATUS_WRAPPED;
+                }
+
                 csa->lscsa->decr.slot[0] -= delta_time;
+        } else {
+                csa->lscsa->decr_status.slot[0] = 0;
         }
 }
 
@@ -1398,6 +1397,18 @@ static inline void restore_ls_16kb(struct spu_state *csa, struct spu *spu)
         send_mfc_dma(spu, addr, ls_offset, size, tag, rclass, cmd);
 }
 
+static inline void suspend_mfc(struct spu_state *csa, struct spu *spu)
+{
+        struct spu_priv2 __iomem *priv2 = spu->priv2;
+
+        /* Restore, Step 47.
+         *     Write MFC_Cntl[Sc,Sm]='1','0' to suspend
+         *     the queue.
+         */
+        out_be64(&priv2->mfc_control_RW, MFC_CNTL_SUSPEND_DMA_QUEUE);
+        eieio();
+}
+
 static inline void clear_interrupts(struct spu_state *csa, struct spu *spu)
 {
         /* Restore, Step 49:
@@ -1548,10 +1559,10 @@ static inline void restore_decr_wrapped(struct spu_state *csa, struct spu *spu)
          *     "wrapped" flag is set, OR in a '1' to
          *     CSA.SPU_Event_Status[Tm].
          */
-        if (csa->lscsa->decr_status.slot[0] == 1) {
+        if (csa->lscsa->decr_status.slot[0] & SPU_DECR_STATUS_WRAPPED) {
                 csa->spu_chnldata_RW[0] |= 0x20;
         }
-        if ((csa->lscsa->decr_status.slot[0] == 1) &&
+        if ((csa->lscsa->decr_status.slot[0] & SPU_DECR_STATUS_WRAPPED) &&
             (csa->spu_chnlcnt_RW[0] == 0 &&
              ((csa->spu_chnldata_RW[2] & 0x20) == 0x0) &&
              ((csa->spu_chnldata_RW[0] & 0x20) != 0x1))) {
@@ -1562,18 +1573,13 @@ static inline void restore_decr_wrapped(struct spu_state *csa, struct spu *spu)
 static inline void restore_ch_part1(struct spu_state *csa, struct spu *spu)
 {
         struct spu_priv2 __iomem *priv2 = spu->priv2;
-        u64 idx, ch_indices[7] = { 0UL, 3UL, 4UL, 24UL, 25UL, 27UL };
+        u64 idx, ch_indices[] = { 0UL, 3UL, 4UL, 24UL, 25UL, 27UL };
         int i;
 
         /* Restore, Step 59:
+         *      Restore the following CH: [0,3,4,24,25,27]
          */
-
-        /* Restore CH 1 without count */
-        out_be64(&priv2->spu_chnlcntptr_RW, 1);
-        out_be64(&priv2->spu_chnldata_RW, csa->spu_chnldata_RW[1]);
-
-        /* Restore the following CH: [0,3,4,24,25,27] */
-        for (i = 0; i < 7; i++) {
+        for (i = 0; i < ARRAY_SIZE(ch_indices); i++) {
                 idx = ch_indices[i];
                 out_be64(&priv2->spu_chnlcntptr_RW, idx);
                 eieio();
@@ -1932,7 +1938,7 @@ static void harvest(struct spu_state *prev, struct spu *spu)
         set_switch_pending(prev, spu);          /* Step 5.  */
         stop_spu_isolate(spu);                  /* NEW.     */
         remove_other_spu_access(prev, spu);     /* Step 6.  */
-        suspend_mfc(prev, spu);                 /* Step 7.  */
+        suspend_mfc_and_halt_decr(prev, spu);   /* Step 7.  */
         wait_suspend_mfc_complete(prev, spu);   /* Step 8.  */
         if (!suspend_spe(prev, spu))            /* Step 9.  */
                 clear_spu_status(prev, spu);    /* Step 10. */
diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c
index 8e37bdf4dfda..43f0fb88abbc 100644
--- a/arch/powerpc/platforms/cell/spufs/syscalls.c
+++ b/arch/powerpc/platforms/cell/spufs/syscalls.c
@@ -47,7 +47,7 @@ static long do_spu_run(struct file *filp,
                 goto out;
 
         i = SPUFS_I(filp->f_path.dentry->d_inode);
-        ret = spufs_run_spu(filp, i->i_ctx, &npc, &status);
+        ret = spufs_run_spu(i->i_ctx, &npc, &status);
 
         if (put_user(npc, unpc))
                 ret = -EFAULT;
@@ -76,8 +76,8 @@ asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, __u32 __user *ustatus)
 }
 #endif
 
-asmlinkage long sys_spu_create(const char __user *pathname,
-                                        unsigned int flags, mode_t mode)
+asmlinkage long do_spu_create(const char __user *pathname, unsigned int flags,
+                                mode_t mode, struct file *neighbor)
 {
         char *tmp;
         int ret;
@@ -90,7 +90,7 @@ asmlinkage long sys_spu_create(const char __user *pathname,
                 ret = path_lookup(tmp, LOOKUP_PARENT|
                                 LOOKUP_OPEN|LOOKUP_CREATE, &nd);
                 if (!ret) {
-                        ret = spufs_create(&nd, flags, mode);
+                        ret = spufs_create(&nd, flags, mode, neighbor);
                         path_release(&nd);
                 }
                 putname(tmp);
@@ -99,8 +99,32 @@ asmlinkage long sys_spu_create(const char __user *pathname,
         return ret;
 }
 
+#ifndef MODULE
+asmlinkage long sys_spu_create(const char __user *pathname, unsigned int flags,
+                                mode_t mode, int neighbor_fd)
+{
+        int fput_needed;
+        struct file *neighbor;
+        long ret;
+
+        if (flags & SPU_CREATE_AFFINITY_SPU) {
+                ret = -EBADF;
+                neighbor = fget_light(neighbor_fd, &fput_needed);
+                if (neighbor) {
+                        ret = do_spu_create(pathname, flags, mode, neighbor);
+                        fput_light(neighbor, fput_needed);
+                }
+        }
+        else {
+                ret = do_spu_create(pathname, flags, mode, NULL);
+        }
+
+        return ret;
+}
+#endif
+
 struct spufs_calls spufs_calls = {
-        .create_thread = sys_spu_create,
+        .create_thread = do_spu_create,
         .spu_run = do_spu_run,
         .owner = THIS_MODULE,
 };
diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig
index bec772674e40..2d12f77e46bc 100644
--- a/arch/powerpc/platforms/embedded6xx/Kconfig
+++ b/arch/powerpc/platforms/embedded6xx/Kconfig
@@ -59,7 +59,7 @@ config MPC10X_BRIDGE
 config MV64X60
         bool
         select PPC_INDIRECT_PCI
-        select CONFIG_CHECK_CACHE_COHERENCY
+        select CHECK_CACHE_COHERENCY
 
 config MPC10X_OPENPIC
         bool
diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig
index a05079b07696..d4fc74f7bb15 100644
--- a/arch/powerpc/platforms/ps3/Kconfig
+++ b/arch/powerpc/platforms/ps3/Kconfig
@@ -102,4 +102,40 @@ config PS3_STORAGE
         depends on PPC_PS3
         tristate
 
+config PS3_DISK
+        tristate "PS3 Disk Storage Driver"
+        depends on PPC_PS3 && BLOCK
+        select PS3_STORAGE
+        help
+          Include support for the PS3 Disk Storage.
+
+          This support is required to access the PS3 hard disk.
+          In general, all users will say Y or M.
+
+config PS3_ROM
+        tristate "PS3 BD/DVD/CD-ROM Storage Driver"
+        depends on PPC_PS3 && SCSI
+        select PS3_STORAGE
+        help
+          Include support for the PS3 ROM Storage.
+
+          This support is required to access the PS3 BD/DVD/CD-ROM drive.
+          In general, all users will say Y or M.
+          Also make sure to say Y or M to "SCSI CDROM support" later.
+
+config PS3_FLASH
+        tristate "PS3 FLASH ROM Storage Driver"
+        depends on PPC_PS3
+        select PS3_STORAGE
+        help
+          Include support for the PS3 FLASH ROM Storage.
+
+          This support is required to access the PS3 FLASH ROM, which
+          contains the boot loader and some boot options.
+          In general, all users will say Y or M.
+
+          As this driver needs a fixed buffer of 256 KiB of memory, it can
+          be disabled on the kernel command line using "ps3flash=off", to
+          not allocate this fixed buffer.
+
 endmenu
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index 29bf83bfb1f0..8b18a1c40092 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -66,24 +66,13 @@ firmware_features_table[FIRMWARE_MAX_FEATURES] = {
  * device-tree/ibm,hypertas-functions.  Ultimately this functionality may
  * be moved into prom.c prom_init().
  */
-void __init fw_feature_init(void)
+void __init fw_feature_init(const char *hypertas, unsigned long len)
 {
-        struct device_node *dn;
-        const char *hypertas, *s;
-        int len, i;
+        const char *s;
+        int i;
 
         DBG(" -> fw_feature_init()\n");
 
-        dn = of_find_node_by_path("/rtas");
-        if (dn == NULL) {
-                printk(KERN_ERR "WARNING! Cannot find RTAS in device-tree!\n");
-                goto out;
-        }
-
-        hypertas = of_get_property(dn, "ibm,hypertas-functions", &len);
-        if (hypertas == NULL)
-                goto out;
-
         for (s = hypertas; s < hypertas + len; s += strlen(s) + 1) {
                 for (i = 0; i < FIRMWARE_MAX_FEATURES; i++) {
                         /* check value against table of strings */
@@ -98,7 +87,5 @@ void __init fw_feature_init(void)
                 }
         }
 
-out:
-        of_node_put(dn);
         DBG(" <- fw_feature_init()\n");
 }
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 61e19f78b923..61136d019554 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -10,7 +10,7 @@
 #ifndef _PSERIES_PSERIES_H
 #define _PSERIES_PSERIES_H
 
-extern void __init fw_feature_init(void);
+extern void __init fw_feature_init(const char *hypertas, unsigned long len);
 
 struct pt_regs;
 
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 59e69f085cb4..f0b7146a110f 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -320,8 +320,6 @@ static void __init pSeries_init_early(void)
 {
         DBG(" -> pSeries_init_early()\n");
 
-        fw_feature_init();
-
         if (firmware_has_feature(FW_FEATURE_LPAR))
                 find_udbg_vterm();
 
@@ -343,14 +341,21 @@ static int __init pSeries_probe_hypertas(unsigned long node,
                                          const char *uname, int depth,
                                          void *data)
 {
+        const char *hypertas;
+        unsigned long len;
+
         if (depth != 1 ||
             (strcmp(uname, "rtas") != 0 && strcmp(uname, "rtas@0") != 0))
-                return 0;
+                return 0;
+
+        hypertas = of_get_flat_dt_prop(node, "ibm,hypertas-functions", &len);
+        if (!hypertas)
+                return 1;
 
-        if (of_get_flat_dt_prop(node, "ibm,hypertas-functions", NULL) != NULL)
-                powerpc_firmware_features |= FW_FEATURE_LPAR;
+        powerpc_firmware_features |= FW_FEATURE_LPAR;
+        fw_feature_init(hypertas, len);
 
-        return 1;
+        return 1;
 }
 
 static int __init pSeries_probe(void)
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index f65078c3d3b3..484eb4e0e9db 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_QUICC_ENGINE)	+= qe_lib/
 mv64x60-$(CONFIG_PCI)           += mv64x60_pci.o
 obj-$(CONFIG_MV64X60)           += $(mv64x60-y) mv64x60_pic.o mv64x60_dev.o
 obj-$(CONFIG_RTC_DRV_CMOS)      += rtc_cmos_setup.o
+obj-$(CONFIG_AXON_RAM)          += axonram.o
 
 # contains only the suspend handler for time
 ifeq ($(CONFIG_RTC_CLASS),)
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
new file mode 100644
index 000000000000..2326d5dc5752
--- /dev/null
+++ b/arch/powerpc/sysdev/axonram.c
@@ -0,0 +1,381 @@
+/*
+ * (C) Copyright IBM Deutschland Entwicklung GmbH 2006
+ *
+ * Author: Maxim Shchetynin <maxim@de.ibm.com>
+ *
+ * Axon DDR2 device driver.
+ * It registers one block device per Axon's DDR2 memory bank found on a system.
+ * Block devices are called axonram?, their major and minor numbers are
+ * available in /proc/devices, /proc/partitions or in /sys/block/axonram?/dev.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/genhd.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/irq.h>
+#include <linux/irqreturn.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <asm/of_device.h>
+#include <asm/of_platform.h>
+#include <asm/page.h>
+#include <asm/prom.h>
+
+#define AXON_RAM_MODULE_NAME            "axonram"
+#define AXON_RAM_DEVICE_NAME            "axonram"
+#define AXON_RAM_MINORS_PER_DISK        16
+#define AXON_RAM_BLOCK_SHIFT            PAGE_SHIFT
+#define AXON_RAM_BLOCK_SIZE             1 << AXON_RAM_BLOCK_SHIFT
+#define AXON_RAM_SECTOR_SHIFT           9
+#define AXON_RAM_SECTOR_SIZE            1 << AXON_RAM_SECTOR_SHIFT
+#define AXON_RAM_IRQ_FLAGS              IRQF_SHARED | IRQF_TRIGGER_RISING
+
+struct axon_ram_bank {
+        struct of_device        *device;
+        struct gendisk          *disk;
+        unsigned int            irq_correctable;
+        unsigned int            irq_uncorrectable;
+        unsigned long           ph_addr;
+        unsigned long           io_addr;
+        unsigned long           size;
+        unsigned long           ecc_counter;
+};
+
+static ssize_t
+axon_ram_sysfs_ecc(struct device *dev, struct device_attribute *attr, char *buf)
+{
+        struct of_device *device = to_of_device(dev);
+        struct axon_ram_bank *bank = device->dev.platform_data;
+
+        BUG_ON(!bank);
+
+        return sprintf(buf, "%ld\n", bank->ecc_counter);
+}
+
+static DEVICE_ATTR(ecc, S_IRUGO, axon_ram_sysfs_ecc, NULL);
+
+/**
+ * axon_ram_irq_handler - interrupt handler for Axon RAM ECC
+ * @irq: interrupt ID
+ * @dev: pointer to of_device
+ */
+static irqreturn_t
+axon_ram_irq_handler(int irq, void *dev)
+{
+        struct of_device *device = dev;
+        struct axon_ram_bank *bank = device->dev.platform_data;
+
+        BUG_ON(!bank);
+
+        if (irq == bank->irq_correctable) {
+                dev_err(&device->dev, "Correctable memory error occured\n");
+                bank->ecc_counter++;
+                return IRQ_HANDLED;
+        } else if (irq == bank->irq_uncorrectable) {
+                dev_err(&device->dev, "Uncorrectable memory error occured\n");
+                panic("Critical ECC error on %s", device->node->full_name);
+        }
+
+        return IRQ_NONE;
+}
+
+/**
+ * axon_ram_make_request - make_request() method for block device
+ * @queue, @bio: see blk_queue_make_request()
+ */
+static int
+axon_ram_make_request(struct request_queue *queue, struct bio *bio)
+{
+        struct axon_ram_bank *bank = bio->bi_bdev->bd_disk->private_data;
+        unsigned long phys_mem, phys_end;
+        void *user_mem;
+        struct bio_vec *vec;
+        unsigned int transfered;
+        unsigned short idx;
+        int rc = 0;
+
+        phys_mem = bank->io_addr + (bio->bi_sector << AXON_RAM_SECTOR_SHIFT);
+        phys_end = bank->io_addr + bank->size;
+        transfered = 0;
+        bio_for_each_segment(vec, bio, idx) {
+                if (unlikely(phys_mem + vec->bv_len > phys_end)) {
+                        bio_io_error(bio, bio->bi_size);
+                        rc = -ERANGE;
+                        break;
+                }
+
+                user_mem = page_address(vec->bv_page) + vec->bv_offset;
+                if (bio_data_dir(bio) == READ)
+                        memcpy(user_mem, (void *) phys_mem, vec->bv_len);
+                else
+                        memcpy((void *) phys_mem, user_mem, vec->bv_len);
+
+                phys_mem += vec->bv_len;
+                transfered += vec->bv_len;
+        }
+        bio_endio(bio, transfered, 0);
+
+        return rc;
+}
+
+/**
+ * axon_ram_direct_access - direct_access() method for block device
+ * @device, @sector, @data: see block_device_operations method
+ */
+static int
+axon_ram_direct_access(struct block_device *device, sector_t sector,
+                       unsigned long *data)
+{
+        struct axon_ram_bank *bank = device->bd_disk->private_data;
+        loff_t offset;
+
+        offset = sector << AXON_RAM_SECTOR_SHIFT;
+        if (offset >= bank->size) {
+                dev_err(&bank->device->dev, "Access outside of address space\n");
+                return -ERANGE;
+        }
+
+        *data = bank->ph_addr + offset;
+
+        return 0;
+}
+
+static struct block_device_operations axon_ram_devops = {
+        .owner          = THIS_MODULE,
+        .direct_access  = axon_ram_direct_access
+};
+
+/**
+ * axon_ram_probe - probe() method for platform driver
+ * @device, @device_id: see of_platform_driver method
+ */
+static int
+axon_ram_probe(struct of_device *device, const struct of_device_id *device_id)
+{
+        static int axon_ram_bank_id = -1;
+        struct axon_ram_bank *bank;
+        struct resource resource;
+        int rc = 0;
+
+        axon_ram_bank_id++;
+
+        dev_info(&device->dev, "Found memory controller on %s\n",
+                        device->node->full_name);
+
+        bank = kzalloc(sizeof(struct axon_ram_bank), GFP_KERNEL);
+        if (bank == NULL) {
+                dev_err(&device->dev, "Out of memory\n");
+                rc = -ENOMEM;
+                goto failed;
+        }
+
+        device->dev.platform_data = bank;
+
+        bank->device = device;
+
+        if (of_address_to_resource(device->node, 0, &resource) != 0) {
+                dev_err(&device->dev, "Cannot access device tree\n");
+                rc = -EFAULT;
+                goto failed;
+        }
+
+        bank->size = resource.end - resource.start + 1;
+
+        if (bank->size == 0) {
+                dev_err(&device->dev, "No DDR2 memory found for %s%d\n",
+                                AXON_RAM_DEVICE_NAME, axon_ram_bank_id);
+                rc = -ENODEV;
+                goto failed;
+        }
+
+        dev_info(&device->dev, "Register DDR2 memory device %s%d with %luMB\n",
+                        AXON_RAM_DEVICE_NAME, axon_ram_bank_id, bank->size >> 20);
+
+        bank->ph_addr = resource.start;
+        bank->io_addr = (unsigned long) ioremap_flags(
+                        bank->ph_addr, bank->size, _PAGE_NO_CACHE);
+        if (bank->io_addr == 0) {
+                dev_err(&device->dev, "ioremap() failed\n");
+                rc = -EFAULT;
+                goto failed;
+        }
+
+        bank->disk = alloc_disk(AXON_RAM_MINORS_PER_DISK);
+        if (bank->disk == NULL) {
+                dev_err(&device->dev, "Cannot register disk\n");
+                rc = -EFAULT;
+                goto failed;
+        }
+
+        bank->disk->first_minor = 0;
+        bank->disk->fops = &axon_ram_devops;
+        bank->disk->private_data = bank;
+        bank->disk->driverfs_dev = &device->dev;
+
+        sprintf(bank->disk->disk_name, "%s%d",
+                        AXON_RAM_DEVICE_NAME, axon_ram_bank_id);
+        bank->disk->major = register_blkdev(0, bank->disk->disk_name);
+        if (bank->disk->major < 0) {
+                dev_err(&device->dev, "Cannot register block device\n");
+                rc = -EFAULT;
+                goto failed;
+        }
+
+        bank->disk->queue = blk_alloc_queue(GFP_KERNEL);
+        if (bank->disk->queue == NULL) {
+                dev_err(&device->dev, "Cannot register disk queue\n");
+                rc = -EFAULT;
+                goto failed;
+        }
+
+        set_capacity(bank->disk, bank->size >> AXON_RAM_SECTOR_SHIFT);
+        blk_queue_make_request(bank->disk->queue, axon_ram_make_request);
+        blk_queue_hardsect_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE);
+        add_disk(bank->disk);
+
+        bank->irq_correctable = irq_of_parse_and_map(device->node, 0);
+        bank->irq_uncorrectable = irq_of_parse_and_map(device->node, 1);
+        if ((bank->irq_correctable <= 0) || (bank->irq_uncorrectable <= 0)) {
+                dev_err(&device->dev, "Cannot access ECC interrupt ID\n");
+                rc = -EFAULT;
+                goto failed;
+        }
+
+        rc = request_irq(bank->irq_correctable, axon_ram_irq_handler,
+                        AXON_RAM_IRQ_FLAGS, bank->disk->disk_name, device);
+        if (rc != 0) {
+                dev_err(&device->dev, "Cannot register ECC interrupt handler\n");
+                bank->irq_correctable = bank->irq_uncorrectable = 0;
+                rc = -EFAULT;
+                goto failed;
+        }
+
+        rc = request_irq(bank->irq_uncorrectable, axon_ram_irq_handler,
+                        AXON_RAM_IRQ_FLAGS, bank->disk->disk_name, device);
+        if (rc != 0) {
+                dev_err(&device->dev, "Cannot register ECC interrupt handler\n");
+                bank->irq_uncorrectable = 0;
+                rc = -EFAULT;
+                goto failed;
+        }
+
+        rc = device_create_file(&device->dev, &dev_attr_ecc);
+        if (rc != 0) {
+                dev_err(&device->dev, "Cannot create sysfs file\n");
+                rc = -EFAULT;
+                goto failed;
+        }
+
+        return 0;
+
+failed:
+        if (bank != NULL) {
+                if (bank->irq_uncorrectable > 0)
+                        free_irq(bank->irq_uncorrectable, device);
+                if (bank->irq_correctable > 0)
+                        free_irq(bank->irq_correctable, device);
+                if (bank->disk != NULL) {
+                        if (bank->disk->queue != NULL)
+                                blk_cleanup_queue(bank->disk->queue);
+                        if (bank->disk->major > 0)
+                                unregister_blkdev(bank->disk->major,
+                                                bank->disk->disk_name);
+                        del_gendisk(bank->disk);
+                }
+                device->dev.platform_data = NULL;
+                if (bank->io_addr != 0)
+                        iounmap((void __iomem *) bank->io_addr);
+                kfree(bank);
+        }
+
+        return rc;
+}
+
+/**
+ * axon_ram_remove - remove() method for platform driver
+ * @device: see of_platform_driver method
+ */
+static int
+axon_ram_remove(struct of_device *device)
+{
+        struct axon_ram_bank *bank = device->dev.platform_data;
+
+        BUG_ON(!bank || !bank->disk);
+
+        device_remove_file(&device->dev, &dev_attr_ecc);
+        free_irq(bank->irq_uncorrectable, device);
+        free_irq(bank->irq_correctable, device);
+        blk_cleanup_queue(bank->disk->queue);
+        unregister_blkdev(bank->disk->major, bank->disk->disk_name);
+        del_gendisk(bank->disk);
+        iounmap((void __iomem *) bank->io_addr);
+        kfree(bank);
+
+        return 0;
+}
+
+static struct of_device_id axon_ram_device_id[] = {
+        {
+                .type   = "dma-memory"
+        },
+        {}
+};
+
+static struct of_platform_driver axon_ram_driver = {
+        .owner          = THIS_MODULE,
+        .name           = AXON_RAM_MODULE_NAME,
+        .match_table    = axon_ram_device_id,
+        .probe          = axon_ram_probe,
+        .remove         = axon_ram_remove
+};
+
+/**
+ * axon_ram_init
+ */
+static int __init
+axon_ram_init(void)
+{
+        return of_register_platform_driver(&axon_ram_driver);
+}
+
+/**
+ * axon_ram_exit
+ */
+static void __exit
+axon_ram_exit(void)
+{
+        of_unregister_platform_driver(&axon_ram_driver);
+}
+
+module_init(axon_ram_init);
+module_exit(axon_ram_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Maxim Shchetynin <maxim@de.ibm.com>");
+MODULE_DESCRIPTION("Axon DDR2 RAM device driver for IBM Cell BE");
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 75aad38179f0..74c64c0d3b71 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -877,6 +877,8 @@ static int mpic_host_map(struct irq_host *h, unsigned int virq,
 
         if (hw == mpic->spurious_vec)
                 return -EINVAL;
+        if (mpic->protected && test_bit(hw, mpic->protected))
+                return -EINVAL;
 
 #ifdef CONFIG_SMP
         else if (hw >= mpic->ipi_vecs[0]) {
@@ -1034,6 +1036,25 @@ struct mpic * __init mpic_alloc(struct device_node *node,
         if (node && of_get_property(node, "big-endian", NULL) != NULL)
                 mpic->flags |= MPIC_BIG_ENDIAN;
 
+        /* Look for protected sources */
+        if (node) {
+                unsigned int psize, bits, mapsize;
+                const u32 *psrc =
+                        of_get_property(node, "protected-sources", &psize);
+                if (psrc) {
+                        psize /= 4;
+                        bits = intvec_top + 1;
+                        mapsize = BITS_TO_LONGS(bits) * sizeof(unsigned long);
+                        mpic->protected = alloc_bootmem(mapsize);
+                        BUG_ON(mpic->protected == NULL);
+                        memset(mpic->protected, 0, mapsize);
+                        for (i = 0; i < psize; i++) {
+                                if (psrc[i] > intvec_top)
+                                        continue;
+                                __set_bit(psrc[i], mpic->protected);
+                        }
+                }
+        }
 
 #ifdef CONFIG_MPIC_WEIRD
         mpic->hw_set = mpic_infos[MPIC_GET_REGSET(flags)];
@@ -1213,6 +1234,9 @@ void __init mpic_init(struct mpic *mpic)
                 u32 vecpri = MPIC_VECPRI_MASK | i |
                         (8 << MPIC_VECPRI_PRIORITY_SHIFT);
                 
+                /* check if protected */
+                if (mpic->protected && test_bit(i, mpic->protected))
+                        continue;
                 /* init hw */
                 mpic_irq_write(i, MPIC_INFO(IRQ_VECTOR_PRI), vecpri);
                 mpic_irq_write(i, MPIC_INFO(IRQ_DESTINATION),
@@ -1407,6 +1431,14 @@ unsigned int mpic_get_one_irq(struct mpic *mpic)
                         mpic_eoi(mpic);
                 return NO_IRQ;
         }
+        if (unlikely(mpic->protected && test_bit(src, mpic->protected))) {
+                if (printk_ratelimit())
+                        printk(KERN_WARNING "%s: Got protected source %d !\n",
+                               mpic->name, (int)src);
+                mpic_eoi(mpic);
+                return NO_IRQ;
+        }
+
         return irq_linear_revmap(mpic->irqhost, src);
 }
 
diff --git a/arch/powerpc/sysdev/pmi.c b/arch/powerpc/sysdev/pmi.c
index 85a7c99c1003..2f91b55b7754 100644
--- a/arch/powerpc/sysdev/pmi.c
+++ b/arch/powerpc/sysdev/pmi.c
@@ -48,15 +48,13 @@ struct pmi_data {
         struct work_struct      work;
 };
 
+static struct pmi_data *data;
 
 static int pmi_irq_handler(int irq, void *dev_id)
 {
-        struct pmi_data *data;
         u8 type;
         int rc;
 
-        data = dev_id;
-
         spin_lock(&data->pmi_spinlock);
 
         type = ioread8(data->pmi_reg + PMI_READ_TYPE);
@@ -111,16 +109,13 @@ MODULE_DEVICE_TABLE(of, pmi_match);
 
 static void pmi_notify_handlers(struct work_struct *work)
 {
-        struct pmi_data *data;
         struct pmi_handler *handler;
 
-        data = container_of(work, struct pmi_data, work);
-
         spin_lock(&data->handler_spinlock);
         list_for_each_entry(handler, &data->handler, node) {
                 pr_debug(KERN_INFO "pmi: notifying handler %p\n", handler);
                 if (handler->type == data->msg.type)
-                        handler->handle_pmi_message(data->dev, data->msg);
+                        handler->handle_pmi_message(data->msg);
         }
         spin_unlock(&data->handler_spinlock);
 }
@@ -129,9 +124,14 @@ static int pmi_of_probe(struct of_device *dev,
                         const struct of_device_id *match)
 {
         struct device_node *np = dev->node;
-        struct pmi_data *data;
         int rc;
 
+        if (data) {
+                printk(KERN_ERR "pmi: driver has already been initialized.\n");
+                rc = -EBUSY;
+                goto out;
+        }
+
         data = kzalloc(sizeof(struct pmi_data), GFP_KERNEL);
         if (!data) {
                 printk(KERN_ERR "pmi: could not allocate memory.\n");
@@ -154,7 +154,6 @@ static int pmi_of_probe(struct of_device *dev,
 
         INIT_WORK(&data->work, pmi_notify_handlers);
 
-        dev->dev.driver_data = data;
         data->dev = dev;
 
         data->irq = irq_of_parse_and_map(np, 0);
@@ -164,7 +163,7 @@ static int pmi_of_probe(struct of_device *dev,
                 goto error_cleanup_iomap;
         }
 
-        rc = request_irq(data->irq, pmi_irq_handler, 0, "pmi", data);
+        rc = request_irq(data->irq, pmi_irq_handler, 0, "pmi", NULL);
         if (rc) {
                 printk(KERN_ERR "pmi: can't request IRQ %d: returned %d\n",
                                 data->irq, rc);
@@ -187,12 +186,9 @@ out:
 
 static int pmi_of_remove(struct of_device *dev)
 {
-        struct pmi_data *data;
         struct pmi_handler *handler, *tmp;
 
-        data = dev->dev.driver_data;
-
-        free_irq(data->irq, data);
+        free_irq(data->irq, NULL);
         iounmap(data->pmi_reg);
 
         spin_lock(&data->handler_spinlock);
@@ -202,7 +198,8 @@ static int pmi_of_remove(struct of_device *dev)
 
         spin_unlock(&data->handler_spinlock);
 
-        kfree(dev->dev.driver_data);
+        kfree(data);
+        data = NULL;
 
         return 0;
 }
@@ -226,13 +223,13 @@ static void __exit pmi_module_exit(void)
 }
 module_exit(pmi_module_exit);
 
-void pmi_send_message(struct of_device *device, pmi_message_t msg)
+int pmi_send_message(pmi_message_t msg)
 {
-        struct pmi_data *data;
         unsigned long flags;
         DECLARE_COMPLETION_ONSTACK(completion);
 
-        data = device->dev.driver_data;
+        if (!data)
+                return -ENODEV;
 
         mutex_lock(&data->msg_mutex);
 
@@ -256,30 +253,26 @@ void pmi_send_message(struct of_device *device, pmi_message_t msg)
         data->completion = NULL;
 
         mutex_unlock(&data->msg_mutex);
+
+        return 0;
 }
 EXPORT_SYMBOL_GPL(pmi_send_message);
 
-void pmi_register_handler(struct of_device *device,
-                          struct pmi_handler *handler)
+int pmi_register_handler(struct pmi_handler *handler)
 {
-        struct pmi_data *data;
-        data = device->dev.driver_data;
-
         if (!data)
-                return;
+                return -ENODEV;
 
         spin_lock(&data->handler_spinlock);
         list_add_tail(&handler->node, &data->handler);
         spin_unlock(&data->handler_spinlock);
+
+        return 0;
 }
 EXPORT_SYMBOL_GPL(pmi_register_handler);
 
-void pmi_unregister_handler(struct of_device *device,
-                            struct pmi_handler *handler)
+void pmi_unregister_handler(struct pmi_handler *handler)
 {
-        struct pmi_data *data;
-        data = device->dev.driver_data;
-
         if (!data)
                 return;
 
diff --git a/arch/powerpc/xmon/nonstdio.c b/arch/powerpc/xmon/nonstdio.c
index 78765833f4c0..bfac84fbe780 100644
--- a/arch/powerpc/xmon/nonstdio.c
+++ b/arch/powerpc/xmon/nonstdio.c
@@ -132,3 +132,8 @@ void xmon_printf(const char *format, ...)
         va_end(args);
         xmon_write(xmon_outbuf, n);
 }
+
+void xmon_puts(const char *str)
+{
+        xmon_write(str, strlen(str));
+}
diff --git a/arch/powerpc/xmon/nonstdio.h b/arch/powerpc/xmon/nonstdio.h
index 47cebbd2b1b1..23dd95f4599c 100644
--- a/arch/powerpc/xmon/nonstdio.h
+++ b/arch/powerpc/xmon/nonstdio.h
@@ -5,10 +5,11 @@
 
 extern int xmon_putchar(int c);
 extern int xmon_getchar(void);
+extern void xmon_puts(const char *);
 extern char *xmon_gets(char *, int);
 extern void xmon_printf(const char *, ...);
 extern void xmon_map_scc(void);
 extern int xmon_expect(const char *str, unsigned long timeout);
-extern int xmon_write(void *ptr, int nb);
+extern int xmon_write(const void *ptr, int nb);
 extern int xmon_readchar(void);
 extern int xmon_read_poll(void);
diff --git a/arch/powerpc/xmon/start.c b/arch/powerpc/xmon/start.c
index 712552c4f242..8864de2af382 100644
--- a/arch/powerpc/xmon/start.c
+++ b/arch/powerpc/xmon/start.c
@@ -14,7 +14,7 @@ void xmon_map_scc(void)
 {
 }
 
-int xmon_write(void *ptr, int nb)
+int xmon_write(const void *ptr, int nb)
 {
         return udbg_write(ptr, nb);
 }
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 669e6566ad70..121b04d165d1 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -833,7 +833,7 @@ cmds(struct pt_regs *excp)
                         mdelay(2000);
                         return cmd;
                 case '?':
-                        printf(help_string);
+                        xmon_puts(help_string);
                         break;
                 case 'b':
                         bpt_cmds();
diff --git a/arch/ppc/syslib/mv64x60.c b/arch/ppc/syslib/mv64x60.c
index 032f4b7f4225..d212b1c418a9 100644
--- a/arch/ppc/syslib/mv64x60.c
+++ b/arch/ppc/syslib/mv64x60.c
@@ -14,6 +14,7 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/mv643xx.h>
@@ -2359,7 +2360,7 @@ mv64460_chip_specific_init(struct mv64x60_handle *bh,
 /* Export the hotswap register via sysfs for enum event monitoring */
 #define VAL_LEN_MAX     11 /* 32-bit hex or dec stringified number + '\n' */
 
-DECLARE_MUTEX(mv64xxx_hs_lock);
+static DEFINE_MUTEX(mv64xxx_hs_lock);
 
 static ssize_t
 mv64xxx_hs_reg_read(struct kobject *kobj, char *buf, loff_t off, size_t count)
@@ -2372,14 +2373,14 @@ mv64xxx_hs_reg_read(struct kobject *kobj, char *buf, loff_t off, size_t count)
         if (count < VAL_LEN_MAX)
                 return -EINVAL;
 
-        if (down_interruptible(&mv64xxx_hs_lock))
+        if (mutex_lock_interruptible(&mv64xxx_hs_lock))
                 return -ERESTARTSYS;
         save_exclude = mv64x60_pci_exclude_bridge;
         mv64x60_pci_exclude_bridge = 0;
         early_read_config_dword(&sysfs_hose_a, 0, PCI_DEVFN(0, 0),
                         MV64360_PCICFG_CPCI_HOTSWAP, &v);
         mv64x60_pci_exclude_bridge = save_exclude;
-        up(&mv64xxx_hs_lock);
+        mutex_unlock(&mv64xxx_hs_lock);
 
         return sprintf(buf, "0x%08x\n", v);
 }
@@ -2396,14 +2397,14 @@ mv64xxx_hs_reg_write(struct kobject *kobj, char *buf, loff_t off, size_t count)
                 return -EINVAL;
 
         if (sscanf(buf, "%i", &v) == 1) {
-                if (down_interruptible(&mv64xxx_hs_lock))
+                if (mutex_lock_interruptible(&mv64xxx_hs_lock))
                         return -ERESTARTSYS;
                 save_exclude = mv64x60_pci_exclude_bridge;
                 mv64x60_pci_exclude_bridge = 0;
                 early_write_config_dword(&sysfs_hose_a, 0, PCI_DEVFN(0, 0),
                                 MV64360_PCICFG_CPCI_HOTSWAP, v);
                 mv64x60_pci_exclude_bridge = save_exclude;
-                up(&mv64xxx_hs_lock);
+                mutex_unlock(&mv64xxx_hs_lock);
         }
         else
                 count = -EINVAL;
@@ -2433,10 +2434,10 @@ mv64xxx_hs_reg_valid_show(struct device *dev, struct device_attribute *attr,
         pdev = container_of(dev, struct platform_device, dev);
         pdp = (struct mv64xxx_pdata *)pdev->dev.platform_data;
 
-        if (down_interruptible(&mv64xxx_hs_lock))
+        if (mutex_lock_interruptible(&mv64xxx_hs_lock))
                 return -ERESTARTSYS;
         v = pdp->hs_reg_valid;
-        up(&mv64xxx_hs_lock);
+        mutex_unlock(&mv64xxx_hs_lock);
 
         return sprintf(buf, "%i\n", v);
 }
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index d8ed6676ae86..f87f429e0b24 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -178,6 +178,9 @@ config CPU_HAS_PINT_IRQ
 config CPU_HAS_MASKREG_IRQ
         bool
 
+config CPU_HAS_INTC_IRQ
+        bool
+
 config CPU_HAS_INTC2_IRQ
         bool
 
@@ -209,6 +212,7 @@ config SOLUTION_ENGINE
 config SH_SOLUTION_ENGINE
         bool "SolutionEngine"
         select SOLUTION_ENGINE
+        select CPU_HAS_IPR_IRQ
         depends on CPU_SUBTYPE_SH7709 || CPU_SUBTYPE_SH7750
         help
           Select SolutionEngine if configuring for a Hitachi SH7709
@@ -241,6 +245,7 @@ config SH_7722_SOLUTION_ENGINE
 config SH_7751_SOLUTION_ENGINE
         bool "SolutionEngine7751"
         select SOLUTION_ENGINE
+        select CPU_HAS_IPR_IRQ
         depends on CPU_SUBTYPE_SH7751
         help
           Select 7751 SolutionEngine if configuring for a Hitachi SH7751
@@ -250,6 +255,7 @@ config SH_7780_SOLUTION_ENGINE
         bool "SolutionEngine7780"
         select SOLUTION_ENGINE
         select SYS_SUPPORTS_PCI
+        select CPU_HAS_INTC2_IRQ
         depends on CPU_SUBTYPE_SH7780
         help
           Select 7780 SolutionEngine if configuring for a Renesas SH7780
@@ -317,6 +323,7 @@ config SH_MPC1211
 config SH_SH03
         bool "Interface CTP/PCI-SH03"
         depends on CPU_SUBTYPE_SH7751 && BROKEN
+        select CPU_HAS_IPR_IRQ
         select SYS_SUPPORTS_PCI
         help
           CTP/PCI-SH03 is a CPU module computer that is produced
@@ -326,6 +333,7 @@ config SH_SH03
 config SH_SECUREEDGE5410
         bool "SecureEdge5410"
         depends on CPU_SUBTYPE_SH7751R
+        select CPU_HAS_IPR_IRQ
         select SYS_SUPPORTS_PCI
         help
           Select SecureEdge5410 if configuring for a SnapGear SH board.
@@ -380,6 +388,7 @@ config SH_LANDISK
 config SH_TITAN
         bool "TITAN"
         depends on CPU_SUBTYPE_SH7751R
+        select CPU_HAS_IPR_IRQ
         select SYS_SUPPORTS_PCI
         help
           Select Titan if you are configuring for a Nimble Microsystems
@@ -388,6 +397,7 @@ config SH_TITAN
 config SH_SHMIN
         bool "SHMIN"
         depends on CPU_SUBTYPE_SH7706
+        select CPU_HAS_IPR_IRQ
         help
           Select SHMIN if configuring for the SHMIN board.
 
diff --git a/arch/sh/Makefile b/arch/sh/Makefile
index 77fecc62a056..0016609d1eba 100644
--- a/arch/sh/Makefile
+++ b/arch/sh/Makefile
@@ -121,8 +121,7 @@ core-y	+= $(addprefix arch/sh/boards/, \
 endif
 
 # Companion chips
-core-$(CONFIG_HD64461)          += arch/sh/cchips/hd6446x/hd64461/
-core-$(CONFIG_HD64465)          += arch/sh/cchips/hd6446x/hd64465/
+core-$(CONFIG_HD6446X_SERIES)   += arch/sh/cchips/hd6446x/
 core-$(CONFIG_VOYAGERGX)        += arch/sh/cchips/voyagergx/
 
 cpuincdir-$(CONFIG_CPU_SH2)     := cpu-sh2
diff --git a/arch/sh/boards/mpc1211/pci.c b/arch/sh/boards/mpc1211/pci.c
index 4ed1a95c6d56..23849f70f133 100644
--- a/arch/sh/boards/mpc1211/pci.c
+++ b/arch/sh/boards/mpc1211/pci.c
@@ -187,7 +187,7 @@ char * __devinit pcibios_setup(char *str)
  *  are examined.
  */
 
-void __init pcibios_fixup_bus(struct pci_bus *b)
+void __devinit pcibios_fixup_bus(struct pci_bus *b)
 {
         pci_read_bridge_bases(b);
 }
diff --git a/arch/sh/boards/renesas/r7780rp/setup.c b/arch/sh/boards/renesas/r7780rp/setup.c
index 5afb864a1ec5..adb529d01bae 100644
--- a/arch/sh/boards/renesas/r7780rp/setup.c
+++ b/arch/sh/boards/renesas/r7780rp/setup.c
@@ -21,6 +21,58 @@
 #include <asm/clock.h>
 #include <asm/io.h>
 
+static struct resource r8a66597_usb_host_resources[] = {
+        [0] = {
+                .name   = "r8a66597_hcd",
+                .start  = 0xA4200000,
+                .end    = 0xA42000FF,
+                .flags  = IORESOURCE_MEM,
+        },
+        [1] = {
+                .name   = "r8a66597_hcd",
+                .start  = 11,           /* irq number */
+                .end    = 11,
+                .flags  = IORESOURCE_IRQ,
+        },
+};
+
+static struct platform_device r8a66597_usb_host_device = {
+        .name           = "r8a66597_hcd",
+        .id             = -1,
+        .dev = {
+                .dma_mask               = NULL,         /* don't use dma */
+                .coherent_dma_mask      = 0xffffffff,
+        },
+        .num_resources  = ARRAY_SIZE(r8a66597_usb_host_resources),
+        .resource       = r8a66597_usb_host_resources,
+};
+
+static struct resource m66592_usb_peripheral_resources[] = {
+        [0] = {
+                .name   = "m66592_udc",
+                .start  = 0xb0000000,
+                .end    = 0xb00000FF,
+                .flags  = IORESOURCE_MEM,
+        },
+        [1] = {
+                .name   = "m66592_udc",
+                .start  = 9,            /* irq number */
+                .end    = 9,
+                .flags  = IORESOURCE_IRQ,
+        },
+};
+
+static struct platform_device m66592_usb_peripheral_device = {
+        .name           = "m66592_udc",
+        .id             = -1,
+        .dev = {
+                .dma_mask               = NULL,         /* don't use dma */
+                .coherent_dma_mask      = 0xffffffff,
+        },
+        .num_resources  = ARRAY_SIZE(m66592_usb_peripheral_resources),
+        .resource       = m66592_usb_peripheral_resources,
+};
+
 static struct resource cf_ide_resources[] = {
         [0] = {
                 .start  = PA_AREA5_IO + 0x1000,
@@ -81,6 +133,8 @@ static struct platform_device heartbeat_device = {
 };
 
 static struct platform_device *r7780rp_devices[] __initdata = {
+        &r8a66597_usb_host_device,
+        &m66592_usb_peripheral_device,
         &cf_ide_device,
         &heartbeat_device,
 };
diff --git a/arch/sh/boards/renesas/rts7751r2d/setup.c b/arch/sh/boards/renesas/rts7751r2d/setup.c
index 656fda30ef70..e165d85c03b5 100644
--- a/arch/sh/boards/renesas/rts7751r2d/setup.c
+++ b/arch/sh/boards/renesas/rts7751r2d/setup.c
@@ -86,7 +86,8 @@ static struct plat_serial8250_port uart_platform_data[] = {
                 .flags          = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST,
                 .regshift       = 2,
                 .uartclk        = (9600 * 16),
-        }
+        },
+        { 0 },
 };
 
 static struct platform_device uart_device = {
diff --git a/arch/sh/boards/se/7722/irq.c b/arch/sh/boards/se/7722/irq.c
index 26cff0efda40..0b03f3f610b8 100644
--- a/arch/sh/boards/se/7722/irq.c
+++ b/arch/sh/boards/se/7722/irq.c
@@ -16,95 +16,61 @@
 #include <asm/io.h>
 #include <asm/se7722.h>
 
-#define INTC_INTMSK0             0xFFD00044
-#define INTC_INTMSKCLR0          0xFFD00064
-
-struct se7722_data {
-        unsigned char irq;
-        unsigned char ipr_idx;
-        unsigned char shift;
-        unsigned short priority;
-        unsigned long addr;
-};
-
-
 static void disable_se7722_irq(unsigned int irq)
 {
-        struct se7722_data *p = get_irq_chip_data(irq);
-        ctrl_outw( ctrl_inw( p->addr ) | p->priority , p->addr );
+        unsigned int bit = irq - SE7722_FPGA_IRQ_BASE;
+        ctrl_outw(ctrl_inw(IRQ01_MASK) | 1 << bit, IRQ01_MASK);
 }
 
 static void enable_se7722_irq(unsigned int irq)
 {
-        struct se7722_data *p = get_irq_chip_data(irq);
-        ctrl_outw( ctrl_inw( p->addr ) & ~p->priority , p->addr );
+        unsigned int bit = irq - SE7722_FPGA_IRQ_BASE;
+        ctrl_outw(ctrl_inw(IRQ01_MASK) & ~(1 << bit), IRQ01_MASK);
 }
 
 static struct irq_chip se7722_irq_chip __read_mostly = {
-        .name           = "SE7722",
+        .name           = "SE7722-FPGA",
         .mask           = disable_se7722_irq,
         .unmask         = enable_se7722_irq,
         .mask_ack       = disable_se7722_irq,
 };
 
-static struct se7722_data ipr_irq_table[] = {
-        /* irq        ,idx,sft, priority     , addr   */
-        { MRSHPC_IRQ0 , 0 , 0 , MRSHPC_BIT0 , IRQ01_MASK } ,
-        { MRSHPC_IRQ1 , 0 , 0 , MRSHPC_BIT1 , IRQ01_MASK } ,
-        { MRSHPC_IRQ2 , 0 , 0 , MRSHPC_BIT2 , IRQ01_MASK } ,
-        { MRSHPC_IRQ3 , 0 , 0 , MRSHPC_BIT3 , IRQ01_MASK } ,
-        { SMC_IRQ     , 0 , 0 , SMC_BIT     , IRQ01_MASK } ,
-        { EXT_IRQ     , 0 , 0 , EXT_BIT     , IRQ01_MASK } ,
-};
-
-int se7722_irq_demux(int irq)
+static void se7722_irq_demux(unsigned int irq, struct irq_desc *desc)
 {
+        unsigned short intv = ctrl_inw(IRQ01_STS);
+        struct irq_desc *ext_desc;
+        unsigned int ext_irq = SE7722_FPGA_IRQ_BASE;
+
+        intv &= (1 << SE7722_FPGA_IRQ_NR) - 1;
 
-        if ((irq == IRQ0_IRQ)||(irq == IRQ1_IRQ)) {
-                volatile unsigned short intv =
-                        *(volatile unsigned short *)IRQ01_STS;
-                if (irq == IRQ0_IRQ){
-                        if(intv & SMC_BIT ) {
-                                return SMC_IRQ;
-                        } else if(intv & USB_BIT) {
-                                return USB_IRQ;
-                        } else {
-                                printk("intv =%04x\n", intv);
-                                return SMC_IRQ;
-                        }
-                } else if(irq == IRQ1_IRQ){
-                        if(intv & MRSHPC_BIT0) {
-                                return MRSHPC_IRQ0;
-                        } else if(intv & MRSHPC_BIT1) {
-                                return MRSHPC_IRQ1;
-                        } else if(intv & MRSHPC_BIT2) {
-                                return MRSHPC_IRQ2;
-                        } else if(intv & MRSHPC_BIT3) {
-                                return MRSHPC_IRQ3;
-                        } else {
-                                printk("BIT_EXTENTION =%04x\n", intv);
-                                return EXT_IRQ;
-                        }
+        while (intv) {
+                if (intv & 1) {
+                        ext_desc = irq_desc + ext_irq;
+                        handle_level_irq(ext_irq, ext_desc);
                 }
+                intv >>= 1;
+                ext_irq++;
         }
-        return irq;
-
 }
+
 /*
  * Initialize IRQ setting
  */
 void __init init_se7722_IRQ(void)
 {
-        int i = 0;
+        int i;
+
+        ctrl_outw(0, IRQ01_MASK);       /* disable all irqs */
         ctrl_outw(0x2000, 0xb03fffec);  /* mrshpc irq enable */
-        ctrl_outl((3 << ((7 - 0) * 4))|(3 << ((7 - 1) * 4)), INTC_INTPRI0);     /* irq0 pri=3,irq1,pri=3 */
-        ctrl_outw((2 << ((7 - 0) * 2))|(2 << ((7 - 1) * 2)), INTC_ICR1);        /* irq0,1 low-level irq */
 
-        for (i = 0; i < ARRAY_SIZE(ipr_irq_table); i++) {
-                disable_irq_nosync(ipr_irq_table[i].irq);
-                set_irq_chip_and_handler_name( ipr_irq_table[i].irq, &se7722_irq_chip,
-                        handle_level_irq, "level");
-                set_irq_chip_data( ipr_irq_table[i].irq, &ipr_irq_table[i] );
-                disable_se7722_irq(ipr_irq_table[i].irq);
-        }
+        for (i = 0; i < SE7722_FPGA_IRQ_NR; i++)
+                set_irq_chip_and_handler_name(SE7722_FPGA_IRQ_BASE + i,
+                                              &se7722_irq_chip,
+                                              handle_level_irq, "level");
+
+        set_irq_chained_handler(IRQ0_IRQ, se7722_irq_demux);
+        set_irq_type(IRQ0_IRQ, IRQ_TYPE_LEVEL_LOW);
+
+        set_irq_chained_handler(IRQ1_IRQ, se7722_irq_demux);
+        set_irq_type(IRQ1_IRQ, IRQ_TYPE_LEVEL_LOW);
 }
diff --git a/arch/sh/boards/se/7722/setup.c b/arch/sh/boards/se/7722/setup.c
index 6cca6cbc8069..495fc7e2b60f 100644
--- a/arch/sh/boards/se/7722/setup.c
+++ b/arch/sh/boards/se/7722/setup.c
@@ -77,6 +77,7 @@ static struct resource cf_ide_resources[] = {
         },
         [2] = {
                 .start  = MRSHPC_IRQ0,
+                .end    = MRSHPC_IRQ0,
                 .flags  = IORESOURCE_IRQ,
         },
 };
@@ -140,8 +141,6 @@ static void __init se7722_setup(char **cmdline_p)
 static struct sh_machine_vector mv_se7722 __initmv = {
         .mv_name                = "Solution Engine 7722" ,
         .mv_setup               = se7722_setup ,
-        .mv_nr_irqs             = 109 ,
+        .mv_nr_irqs             = SE7722_FPGA_IRQ_BASE + SE7722_FPGA_IRQ_NR,
         .mv_init_irq            = init_se7722_IRQ,
-        .mv_irq_demux           = se7722_irq_demux,
-
 };
diff --git a/arch/sh/cchips/hd6446x/Makefile b/arch/sh/cchips/hd6446x/Makefile
new file mode 100644
index 000000000000..a106dd9db986
--- /dev/null
+++ b/arch/sh/cchips/hd6446x/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_HD64461)   += hd64461.o
+obj-$(CONFIG_HD64465)   += hd64465/
diff --git a/arch/sh/cchips/hd6446x/hd64461/setup.c b/arch/sh/cchips/hd6446x/hd64461.c
index 4d49b5cbcc13..97f6512aa1b7 100644
--- a/arch/sh/cchips/hd6446x/hd64461/setup.c
+++ b/arch/sh/cchips/hd6446x/hd64461.c
@@ -1,5 +1,4 @@
 /*
- *      $Id: setup.c,v 1.5 2004/03/16 00:07:50 lethal Exp $
  *      Copyright (C) 2000 YAEGASHI Takeshi
  *      Hitachi HD64461 companion chip support
  */
diff --git a/arch/sh/cchips/hd6446x/hd64461/Makefile b/arch/sh/cchips/hd6446x/hd64461/Makefile
deleted file mode 100644
index bff4b92e388c..000000000000
--- a/arch/sh/cchips/hd6446x/hd64461/Makefile
+++ /dev/null
@@ -1,6 +0,0 @@
-#
-# Makefile for the HD64461 
-#
-
-obj-y    := setup.o io.o
-
diff --git a/arch/sh/cchips/hd6446x/hd64461/io.c b/arch/sh/cchips/hd6446x/hd64461/io.c
deleted file mode 100644
index 7909a1b7b512..000000000000
--- a/arch/sh/cchips/hd6446x/hd64461/io.c
+++ /dev/null
@@ -1,150 +0,0 @@
-/*
- *      Copyright (C) 2000 YAEGASHI Takeshi
- *      Typical I/O routines for HD64461 system.
- */
-
-#include <asm/io.h>
-#include <asm/hd64461.h>
-
-#define MEM_BASE (CONFIG_HD64461_IOBASE - HD64461_STBCR)
-
-static __inline__ unsigned long PORT2ADDR(unsigned long port)
-{
-        /* 16550A: HD64461 internal */
-        if (0x3f8<=port && port<=0x3ff)
-                return CONFIG_HD64461_IOBASE + 0x8000 + ((port-0x3f8)<<1);
-        if (0x2f8<=port && port<=0x2ff)
-                return CONFIG_HD64461_IOBASE + 0x7000 + ((port-0x2f8)<<1);
-
-#ifdef CONFIG_HD64461_ENABLER
-        /* NE2000: HD64461 PCMCIA channel 0 (I/O) */
-        if (0x300<=port && port<=0x31f)
-                return 0xba000000 + port;
-
-        /* ide0: HD64461 PCMCIA channel 1 (memory) */
-        /* On HP690, CF in slot 1 is configured as a memory card
-           device.  See CF+ and CompactFlash Specification for the
-           detail of CF's memory mapped addressing. */
-        if (0x1f0<=port && port<=0x1f7) return 0xb5000000 + port;
-        if (port == 0x3f6) return 0xb50001fe;
-        if (port == 0x3f7) return 0xb50001ff;
-
-        /* ide1 */
-        if (0x170<=port && port<=0x177) return 0xba000000 + port;
-        if (port == 0x376) return 0xba000376;
-        if (port == 0x377) return 0xba000377;
-#endif
-
-        /* ??? */
-        if (port < 0xf000) return 0xa0000000 + port;
-        /* PCMCIA channel 0, I/O (0xba000000) */
-        if (port < 0x10000) return 0xba000000 + port - 0xf000;
-
-        /* HD64461 internal devices (0xb0000000) */
-        if (port < 0x20000) return CONFIG_HD64461_IOBASE + port - 0x10000;
-
-        /* PCMCIA channel 0, I/O (0xba000000) */
-        if (port < 0x30000) return 0xba000000 + port - 0x20000;
-
-        /* PCMCIA channel 1, memory (0xb5000000) */
-        if (port < 0x40000) return 0xb5000000 + port - 0x30000;
-
-        /* Whole physical address space (0xa0000000) */
-        return 0xa0000000 + (port & 0x1fffffff);
-}
-
-unsigned char hd64461_inb(unsigned long port)
-{
-        return *(volatile unsigned char*)PORT2ADDR(port);
-}
-
-unsigned char hd64461_inb_p(unsigned long port)
-{
-        unsigned long v = *(volatile unsigned char*)PORT2ADDR(port);
-        ctrl_delay();
-        return v;
-}
-
-unsigned short hd64461_inw(unsigned long port)
-{
-        return *(volatile unsigned short*)PORT2ADDR(port);
-}
-
-unsigned int hd64461_inl(unsigned long port)
-{
-        return *(volatile unsigned long*)PORT2ADDR(port);
-}
-
-void hd64461_outb(unsigned char b, unsigned long port)
-{
-        *(volatile unsigned char*)PORT2ADDR(port) = b;
-}
-
-void hd64461_outb_p(unsigned char b, unsigned long port)
-{
-        *(volatile unsigned char*)PORT2ADDR(port) = b;
-        ctrl_delay();
-}
-
-void hd64461_outw(unsigned short b, unsigned long port)
-{
-        *(volatile unsigned short*)PORT2ADDR(port) = b;
-}
-
-void hd64461_outl(unsigned int b, unsigned long port)
-{
-        *(volatile unsigned long*)PORT2ADDR(port) = b;
-}
-
-void hd64461_insb(unsigned long port, void *buffer, unsigned long count)
-{
-        volatile unsigned char* addr=(volatile unsigned char*)PORT2ADDR(port);
-        unsigned char *buf=buffer;
-        while(count--) *buf++=*addr;
-}
-
-void hd64461_insw(unsigned long port, void *buffer, unsigned long count)
-{
-        volatile unsigned short* addr=(volatile unsigned short*)PORT2ADDR(port);
-        unsigned short *buf=buffer;
-        while(count--) *buf++=*addr;
-}
-
-void hd64461_insl(unsigned long port, void *buffer, unsigned long count)
-{
-        volatile unsigned long* addr=(volatile unsigned long*)PORT2ADDR(port);
-        unsigned long *buf=buffer;
-        while(count--) *buf++=*addr;
-}
-
-void hd64461_outsb(unsigned long port, const void *buffer, unsigned long count)
-{
-        volatile unsigned char* addr=(volatile unsigned char*)PORT2ADDR(port);
-        const unsigned char *buf=buffer;
-        while(count--) *addr=*buf++;
-}
-
-void hd64461_outsw(unsigned long port, const void *buffer, unsigned long count)
-{
-        volatile unsigned short* addr=(volatile unsigned short*)PORT2ADDR(port);
-        const unsigned short *buf=buffer;
-        while(count--) *addr=*buf++;
-}
-
-void hd64461_outsl(unsigned long port, const void *buffer, unsigned long count)
-{
-        volatile unsigned long* addr=(volatile unsigned long*)PORT2ADDR(port);
-        const unsigned long *buf=buffer;
-        while(count--) *addr=*buf++;
-}
-
-unsigned short hd64461_readw(void __iomem *addr)
-{
-        return ctrl_inw(MEM_BASE+(unsigned long __force)addr);
-}
-
-void hd64461_writew(unsigned short b, void __iomem *addr)
-{
-        ctrl_outw(b, MEM_BASE+(unsigned long __force)addr);
-}
-
diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig
index e7f8ddb0ada4..07310fa03250 100644
--- a/arch/sh/configs/landisk_defconfig
+++ b/arch/sh/configs/landisk_defconfig
@@ -217,7 +217,7 @@ CONFIG_SH_FPU=y
 # CONFIG_SH_DSP is not set
 # CONFIG_SH_STORE_QUEUES is not set
 CONFIG_CPU_HAS_INTEVT=y
-CONFIG_CPU_HAS_IPR_IRQ=y
+CONFIG_CPU_HAS_INTC_IRQ=y
 CONFIG_CPU_HAS_SR_RB=y
 CONFIG_CPU_HAS_PTEA=y
 
diff --git a/arch/sh/configs/lboxre2_defconfig b/arch/sh/configs/lboxre2_defconfig
index be86414dcc87..fa09d68d057a 100644
--- a/arch/sh/configs/lboxre2_defconfig
+++ b/arch/sh/configs/lboxre2_defconfig
@@ -222,7 +222,7 @@ CONFIG_SH_FPU=y
 # CONFIG_SH_DSP is not set
 # CONFIG_SH_STORE_QUEUES is not set
 CONFIG_CPU_HAS_INTEVT=y
-CONFIG_CPU_HAS_IPR_IRQ=y
+CONFIG_CPU_HAS_INTC_IRQ=y
 CONFIG_CPU_HAS_SR_RB=y
 CONFIG_CPU_HAS_PTEA=y
 
diff --git a/arch/sh/configs/r7780mp_defconfig b/arch/sh/configs/r7780mp_defconfig
index 17f7402b31d8..ac4de4973b60 100644
--- a/arch/sh/configs/r7780mp_defconfig
+++ b/arch/sh/configs/r7780mp_defconfig
@@ -191,7 +191,7 @@ CONFIG_SH_FPU=y
 CONFIG_SH_STORE_QUEUES=y
 CONFIG_SPECULATIVE_EXECUTION=y
 CONFIG_CPU_HAS_INTEVT=y
-CONFIG_CPU_HAS_INTC2_IRQ=y
+CONFIG_CPU_HAS_INTC_IRQ=y
 CONFIG_CPU_HAS_SR_RB=y
 
 #
diff --git a/arch/sh/configs/r7780rp_defconfig b/arch/sh/configs/r7780rp_defconfig
index 48c6a2194c98..12cc01910cf8 100644
--- a/arch/sh/configs/r7780rp_defconfig
+++ b/arch/sh/configs/r7780rp_defconfig
@@ -241,7 +241,7 @@ CONFIG_SH_FPU=y
 CONFIG_SH_STORE_QUEUES=y
 CONFIG_SPECULATIVE_EXECUTION=y
 CONFIG_CPU_HAS_INTEVT=y
-CONFIG_CPU_HAS_INTC2_IRQ=y
+CONFIG_CPU_HAS_INTC_IRQ=y
 CONFIG_CPU_HAS_SR_RB=y
 
 #
diff --git a/arch/sh/configs/rts7751r2d_defconfig b/arch/sh/configs/rts7751r2d_defconfig
index a59bb78bd071..f1e979b1e495 100644
--- a/arch/sh/configs/rts7751r2d_defconfig
+++ b/arch/sh/configs/rts7751r2d_defconfig
@@ -155,7 +155,7 @@ CONFIG_CPU_SH4=y
 # CONFIG_CPU_SUBTYPE_SH7091 is not set
 # CONFIG_CPU_SUBTYPE_SH7750R is not set
 # CONFIG_CPU_SUBTYPE_SH7750S is not set
-CONFIG_CPU_SUBTYPE_SH7751=y
+# CONFIG_CPU_SUBTYPE_SH7751 is not set
 CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
@@ -218,7 +218,7 @@ CONFIG_SH_FPU=y
 # CONFIG_SH_DSP is not set
 # CONFIG_SH_STORE_QUEUES is not set
 CONFIG_CPU_HAS_INTEVT=y
-CONFIG_CPU_HAS_IPR_IRQ=y
+CONFIG_CPU_HAS_INTC_IRQ=y
 CONFIG_CPU_HAS_SR_RB=y
 CONFIG_CPU_HAS_PTEA=y
 
@@ -280,7 +280,7 @@ CONFIG_ZERO_PAGE_OFFSET=0x00010000
 CONFIG_BOOT_LINK_OFFSET=0x00800000
 # CONFIG_UBC_WAKEUP is not set
 CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=tty0 console=ttySC0,115200 root=/dev/sda1"
+CONFIG_CMDLINE="console=tty0 console=ttySC0,115200 root=/dev/sda1 earlyprintk=bios"
 
 #
 # Bus options
@@ -1323,7 +1323,7 @@ CONFIG_ENABLE_MUST_CHECK=y
 # CONFIG_DEBUG_KERNEL is not set
 CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_DEBUG_BUGVERBOSE is not set
-# CONFIG_SH_STANDARD_BIOS is not set
+CONFIG_SH_STANDARD_BIOS=y
 CONFIG_EARLY_SCIF_CONSOLE=y
 CONFIG_EARLY_SCIF_CONSOLE_PORT=0xffe80000
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/sh/configs/se7722_defconfig b/arch/sh/configs/se7722_defconfig
index 764b813c4051..8e6a6baf5d27 100644
--- a/arch/sh/configs/se7722_defconfig
+++ b/arch/sh/configs/se7722_defconfig
@@ -200,7 +200,7 @@ CONFIG_CPU_LITTLE_ENDIAN=y
 CONFIG_SH_DSP=y
 CONFIG_SH_STORE_QUEUES=y
 CONFIG_CPU_HAS_INTEVT=y
-CONFIG_CPU_HAS_IPR_IRQ=y
+CONFIG_CPU_HAS_INTC_IRQ=y
 CONFIG_CPU_HAS_SR_RB=y
 CONFIG_CPU_HAS_PTEA=y
 
@@ -565,7 +565,7 @@ CONFIG_SERIO_LIBPS2=y
 # Non-8250 serial port support
 #
 CONFIG_SERIAL_SH_SCI=y
-CONFIG_SERIAL_SH_SCI_NR_UARTS=2
+CONFIG_SERIAL_SH_SCI_NR_UARTS=3
 CONFIG_SERIAL_SH_SCI_CONSOLE=y
 CONFIG_SERIAL_CORE=y
 CONFIG_SERIAL_CORE_CONSOLE=y
diff --git a/arch/sh/configs/se7750_defconfig b/arch/sh/configs/se7750_defconfig
index 4e6e77fa4ce7..c60b6fd4fc42 100644
--- a/arch/sh/configs/se7750_defconfig
+++ b/arch/sh/configs/se7750_defconfig
@@ -226,7 +226,7 @@ CONFIG_SH_FPU=y
 # CONFIG_SH_DSP is not set
 # CONFIG_SH_STORE_QUEUES is not set
 CONFIG_CPU_HAS_INTEVT=y
-CONFIG_CPU_HAS_IPR_IRQ=y
+CONFIG_CPU_HAS_INTC_IRQ=y
 CONFIG_CPU_HAS_SR_RB=y
 CONFIG_CPU_HAS_PTEA=y
 
diff --git a/arch/sh/configs/se7780_defconfig b/arch/sh/configs/se7780_defconfig
index 538661e98793..f68743dc3931 100644
--- a/arch/sh/configs/se7780_defconfig
+++ b/arch/sh/configs/se7780_defconfig
@@ -218,6 +218,7 @@ CONFIG_SH_FPU=y
 # CONFIG_SH_STORE_QUEUES is not set
 CONFIG_CPU_HAS_INTEVT=y
 CONFIG_CPU_HAS_INTC2_IRQ=y
+CONFIG_CPU_HAS_INTC_IRQ=y
 CONFIG_CPU_HAS_SR_RB=y
 
 #
diff --git a/arch/sh/drivers/dma/Kconfig b/arch/sh/drivers/dma/Kconfig
index 333898077c7c..ee711431e504 100644
--- a/arch/sh/drivers/dma/Kconfig
+++ b/arch/sh/drivers/dma/Kconfig
@@ -5,12 +5,13 @@ config SH_DMA_API
 
 config SH_DMA
         bool "SuperH on-chip DMA controller (DMAC) support"
+        depends on CPU_SH3 || CPU_SH4
         select SH_DMA_API
         default n
 
 config NR_ONCHIP_DMA_CHANNELS
+        int
         depends on SH_DMA
-        int "Number of on-chip DMAC channels"
         default "8" if CPU_SUBTYPE_SH7750R || CPU_SUBTYPE_SH7751R
         default "12" if CPU_SUBTYPE_SH7780
         default "4"
diff --git a/arch/sh/drivers/heartbeat.c b/arch/sh/drivers/heartbeat.c
index 23dd6080422f..10c1828c9ff5 100644
--- a/arch/sh/drivers/heartbeat.c
+++ b/arch/sh/drivers/heartbeat.c
@@ -78,7 +78,7 @@ static int heartbeat_drv_probe(struct platform_device *pdev)
                         hd->bit_pos[i] = i;
         }
 
-        hd->base = (void __iomem *)res->start;
+        hd->base = (void __iomem *)(unsigned long)res->start;
 
         setup_timer(&hd->timer, heartbeat_timer, (unsigned long)hd);
         platform_set_drvdata(pdev, hd);
diff --git a/arch/sh/drivers/pci/Makefile b/arch/sh/drivers/pci/Makefile
index 0e9b532b9fbc..2f65ac72f48a 100644
--- a/arch/sh/drivers/pci/Makefile
+++ b/arch/sh/drivers/pci/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_PCI_AUTO)			+= pci-auto.o
 
 obj-$(CONFIG_CPU_SUBTYPE_ST40STB1)      += pci-st40.o
 obj-$(CONFIG_CPU_SUBTYPE_SH7751)        += pci-sh7751.o ops-sh4.o
+obj-$(CONFIG_CPU_SUBTYPE_SH7751R)       += pci-sh7751.o ops-sh4.o
 obj-$(CONFIG_CPU_SUBTYPE_SH7780)        += pci-sh7780.o ops-sh4.o
 obj-$(CONFIG_CPU_SUBTYPE_SH7785)        += pci-sh7780.o ops-sh4.o
 
diff --git a/arch/sh/drivers/pci/ops-sh4.c b/arch/sh/drivers/pci/ops-sh4.c
index 54232f13e406..710a3b0306e5 100644
--- a/arch/sh/drivers/pci/ops-sh4.c
+++ b/arch/sh/drivers/pci/ops-sh4.c
@@ -153,7 +153,7 @@ static void __init pci_fixup_ide_bases(struct pci_dev *d)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_ide_bases);
 
-char * __init pcibios_setup(char *str)
+char * __devinit pcibios_setup(char *str)
 {
         if (!strcmp(str, "off")) {
                 pci_probe = 0;
diff --git a/arch/sh/drivers/pci/pci-st40.c b/arch/sh/drivers/pci/pci-st40.c
index 543417ff8314..1502a14386b6 100644
--- a/arch/sh/drivers/pci/pci-st40.c
+++ b/arch/sh/drivers/pci/pci-st40.c
@@ -328,7 +328,7 @@ int __init st40pci_init(unsigned memStart, unsigned memSize)
         return 1;
 }
 
-char * __init pcibios_setup(char *str)
+char * __devinit pcibios_setup(char *str)
 {
         return str;
 }
diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c
index d439336d2e18..ccaba368ac9b 100644
--- a/arch/sh/drivers/pci/pci.c
+++ b/arch/sh/drivers/pci/pci.c
@@ -71,7 +71,7 @@ subsys_initcall(pcibios_init);
  *  Called after each bus is probed, but before its children
  *  are examined.
  */
-void __init pcibios_fixup_bus(struct pci_bus *bus)
+void __devinit pcibios_fixup_bus(struct pci_bus *bus)
 {
         pci_read_bridge_bases(bus);
 }
diff --git a/arch/sh/drivers/push-switch.c b/arch/sh/drivers/push-switch.c
index b3d20c0e021f..725be6de589b 100644
--- a/arch/sh/drivers/push-switch.c
+++ b/arch/sh/drivers/push-switch.c
@@ -138,4 +138,4 @@ module_exit(switch_exit);
 
 MODULE_VERSION(DRV_VERSION);
 MODULE_AUTHOR("Paul Mundt");
-MODULE_LICENSE("GPLv2");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/sh/kernel/cpu/clock.c b/arch/sh/kernel/cpu/clock.c
index 63251549e9a8..92807ffa8e20 100644
--- a/arch/sh/kernel/cpu/clock.c
+++ b/arch/sh/kernel/cpu/clock.c
@@ -229,6 +229,22 @@ void clk_recalc_rate(struct clk *clk)
 }
 EXPORT_SYMBOL_GPL(clk_recalc_rate);
 
+long clk_round_rate(struct clk *clk, unsigned long rate)
+{
+        if (likely(clk->ops && clk->ops->round_rate)) {
+                unsigned long flags, rounded;
+
+                spin_lock_irqsave(&clock_lock, flags);
+                rounded = clk->ops->round_rate(clk, rate);
+                spin_unlock_irqrestore(&clock_lock, flags);
+
+                return rounded;
+        }
+
+        return clk_get_rate(clk);
+}
+EXPORT_SYMBOL_GPL(clk_round_rate);
+
 /*
  * Returns a clock. Note that we first try to use device id on the bus
  * and clock name. If this fails, we try to use clock name only.
diff --git a/arch/sh/kernel/cpu/irq/Makefile b/arch/sh/kernel/cpu/irq/Makefile
index 1c23308cfc25..9ddb446ac930 100644
--- a/arch/sh/kernel/cpu/irq/Makefile
+++ b/arch/sh/kernel/cpu/irq/Makefile
@@ -6,4 +6,5 @@ obj-y	+= imask.o
 obj-$(CONFIG_CPU_HAS_IPR_IRQ)           += ipr.o
 obj-$(CONFIG_CPU_HAS_PINT_IRQ)          += pint.o 
 obj-$(CONFIG_CPU_HAS_MASKREG_IRQ)       += maskreg.o
+obj-$(CONFIG_CPU_HAS_INTC_IRQ)          += intc.o
 obj-$(CONFIG_CPU_HAS_INTC2_IRQ)         += intc2.o
diff --git a/arch/sh/kernel/cpu/irq/intc.c b/arch/sh/kernel/cpu/irq/intc.c
new file mode 100644
index 000000000000..9345a7130e9e
--- /dev/null
+++ b/arch/sh/kernel/cpu/irq/intc.c
@@ -0,0 +1,405 @@
+/*
+ * Shared interrupt handling code for IPR and INTC2 types of IRQs.
+ *
+ * Copyright (C) 2007 Magnus Damm
+ *
+ * Based on intc2.c and ipr.c
+ *
+ * Copyright (C) 1999  Niibe Yutaka & Takeshi Yaegashi
+ * Copyright (C) 2000  Kazumoto Kojima
+ * Copyright (C) 2001  David J. Mckay (david.mckay@st.com)
+ * Copyright (C) 2003  Takashi Kusuda <kusuda-takashi@hitachi-ul.co.jp>
+ * Copyright (C) 2005, 2006  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+
+#define _INTC_MK(fn, idx, bit, value) \
+        ((fn) << 24 | ((value) << 16) | ((idx) << 8) | (bit))
+#define _INTC_FN(h) (h >> 24)
+#define _INTC_VALUE(h) ((h >> 16) & 0xff)
+#define _INTC_IDX(h) ((h >> 8) & 0xff)
+#define _INTC_BIT(h) (h & 0xff)
+
+#define _INTC_PTR(desc, member, data) \
+        (desc->member + _INTC_IDX(data))
+
+static inline struct intc_desc *get_intc_desc(unsigned int irq)
+{
+        struct irq_chip *chip = get_irq_chip(irq);
+        return (void *)((char *)chip - offsetof(struct intc_desc, chip));
+}
+
+static inline unsigned int set_field(unsigned int value,
+                                     unsigned int field_value,
+                                     unsigned int width,
+                                     unsigned int shift)
+{
+        value &= ~(((1 << width) - 1) << shift);
+        value |= field_value << shift;
+        return value;
+}
+
+static inline unsigned int set_prio_field(struct intc_desc *desc,
+                                          unsigned int value,
+                                          unsigned int priority,
+                                          unsigned int data)
+{
+        unsigned int width = _INTC_PTR(desc, prio_regs, data)->field_width;
+
+        return set_field(value, priority, width, _INTC_BIT(data));
+}
+
+static void disable_prio_16(struct intc_desc *desc, unsigned int data)
+{
+        unsigned long addr = _INTC_PTR(desc, prio_regs, data)->reg;
+
+        ctrl_outw(set_prio_field(desc, ctrl_inw(addr), 0, data), addr);
+}
+
+static void enable_prio_16(struct intc_desc *desc, unsigned int data)
+{
+        unsigned long addr = _INTC_PTR(desc, prio_regs, data)->reg;
+        unsigned int prio = _INTC_VALUE(data);
+
+        ctrl_outw(set_prio_field(desc, ctrl_inw(addr), prio, data), addr);
+}
+
+static void disable_prio_32(struct intc_desc *desc, unsigned int data)
+{
+        unsigned long addr = _INTC_PTR(desc, prio_regs, data)->reg;
+
+        ctrl_outl(set_prio_field(desc, ctrl_inl(addr), 0, data), addr);
+}
+
+static void enable_prio_32(struct intc_desc *desc, unsigned int data)
+{
+        unsigned long addr = _INTC_PTR(desc, prio_regs, data)->reg;
+        unsigned int prio = _INTC_VALUE(data);
+
+        ctrl_outl(set_prio_field(desc, ctrl_inl(addr), prio, data), addr);
+}
+
+static void disable_mask_8(struct intc_desc *desc, unsigned int data)
+{
+        ctrl_outb(1 << _INTC_BIT(data),
+                  _INTC_PTR(desc, mask_regs, data)->set_reg);
+}
+
+static void enable_mask_8(struct intc_desc *desc, unsigned int data)
+{
+        ctrl_outb(1 << _INTC_BIT(data),
+                  _INTC_PTR(desc, mask_regs, data)->clr_reg);
+}
+
+static void disable_mask_32(struct intc_desc *desc, unsigned int data)
+{
+        ctrl_outl(1 << _INTC_BIT(data),
+                  _INTC_PTR(desc, mask_regs, data)->set_reg);
+}
+
+static void enable_mask_32(struct intc_desc *desc, unsigned int data)
+{
+        ctrl_outl(1 << _INTC_BIT(data),
+                  _INTC_PTR(desc, mask_regs, data)->clr_reg);
+}
+
+enum {  REG_FN_ERROR=0,
+        REG_FN_MASK_8, REG_FN_MASK_32,
+        REG_FN_PRIO_16, REG_FN_PRIO_32 };
+
+static struct {
+        void (*enable)(struct intc_desc *, unsigned int);
+        void (*disable)(struct intc_desc *, unsigned int);
+} intc_reg_fns[] = {
+        [REG_FN_MASK_8] = { enable_mask_8, disable_mask_8 },
+        [REG_FN_MASK_32] = { enable_mask_32, disable_mask_32 },
+        [REG_FN_PRIO_16] = { enable_prio_16, disable_prio_16 },
+        [REG_FN_PRIO_32] = { enable_prio_32, disable_prio_32 },
+};
+
+static void intc_enable(unsigned int irq)
+{
+        struct intc_desc *desc = get_intc_desc(irq);
+        unsigned int data = (unsigned int) get_irq_chip_data(irq);
+
+        intc_reg_fns[_INTC_FN(data)].enable(desc, data);
+}
+
+static void intc_disable(unsigned int irq)
+{
+        struct intc_desc *desc = get_intc_desc(irq);
+        unsigned int data = (unsigned int) get_irq_chip_data(irq);
+
+        intc_reg_fns[_INTC_FN(data)].disable(desc, data);
+}
+
+static void set_sense_16(struct intc_desc *desc, unsigned int data)
+{
+        unsigned long addr = _INTC_PTR(desc, sense_regs, data)->reg;
+        unsigned int width = _INTC_PTR(desc, sense_regs, data)->field_width;
+        unsigned int bit = _INTC_BIT(data);
+        unsigned int value = _INTC_VALUE(data);
+
+        ctrl_outw(set_field(ctrl_inw(addr), value, width, bit), addr);
+}
+
+static void set_sense_32(struct intc_desc *desc, unsigned int data)
+{
+        unsigned long addr = _INTC_PTR(desc, sense_regs, data)->reg;
+        unsigned int width = _INTC_PTR(desc, sense_regs, data)->field_width;
+        unsigned int bit = _INTC_BIT(data);
+        unsigned int value = _INTC_VALUE(data);
+
+        ctrl_outl(set_field(ctrl_inl(addr), value, width, bit), addr);
+}
+
+#define VALID(x) (x | 0x80)
+
+static unsigned char intc_irq_sense_table[IRQ_TYPE_SENSE_MASK + 1] = {
+        [IRQ_TYPE_EDGE_FALLING] = VALID(0),
+        [IRQ_TYPE_EDGE_RISING] = VALID(1),
+        [IRQ_TYPE_LEVEL_LOW] = VALID(2),
+        [IRQ_TYPE_LEVEL_HIGH] = VALID(3),
+};
+
+static int intc_set_sense(unsigned int irq, unsigned int type)
+{
+        struct intc_desc *desc = get_intc_desc(irq);
+        unsigned char value = intc_irq_sense_table[type & IRQ_TYPE_SENSE_MASK];
+        unsigned int i, j, data, bit;
+        intc_enum enum_id = 0;
+
+        for (i = 0; i < desc->nr_vectors; i++) {
+                struct intc_vect *vect = desc->vectors + i;
+
+                if (evt2irq(vect->vect) != irq)
+                        continue;
+
+                enum_id = vect->enum_id;
+                break;
+        }
+
+        if (!enum_id || !value)
+                return -EINVAL;
+
+        value ^= VALID(0);
+
+        for (i = 0; i < desc->nr_sense_regs; i++) {
+                struct intc_sense_reg *sr = desc->sense_regs + i;
+
+                for (j = 0; j < ARRAY_SIZE(sr->enum_ids); j++) {
+                        if (sr->enum_ids[j] != enum_id)
+                                continue;
+
+                        bit = sr->reg_width - ((j + 1) * sr->field_width);
+                        data = _INTC_MK(0, i, bit, value);
+
+                        switch(sr->reg_width) {
+                        case 16:
+                                set_sense_16(desc, data);
+                                break;
+                        case 32:
+                                set_sense_32(desc, data);
+                                break;
+                        }
+
+                        return 0;
+                }
+        }
+
+        return -EINVAL;
+}
+
+static unsigned int __init intc_find_mask_handler(unsigned int width)
+{
+        switch (width) {
+        case 8:
+                return REG_FN_MASK_8;
+        case 32:
+                return REG_FN_MASK_32;
+        }
+
+        BUG();
+        return REG_FN_ERROR;
+}
+
+static unsigned int __init intc_find_prio_handler(unsigned int width)
+{
+        switch (width) {
+        case 16:
+                return REG_FN_PRIO_16;
+        case 32:
+                return REG_FN_PRIO_32;
+        }
+
+        BUG();
+        return REG_FN_ERROR;
+}
+
+static intc_enum __init intc_grp_id(struct intc_desc *desc, intc_enum enum_id)
+{
+        struct intc_group *g = desc->groups;
+        unsigned int i, j;
+
+        for (i = 0; g && enum_id && i < desc->nr_groups; i++) {
+                g = desc->groups + i;
+
+                for (j = 0; g->enum_ids[j]; j++) {
+                        if (g->enum_ids[j] != enum_id)
+                                continue;
+
+                        return g->enum_id;
+                }
+        }
+
+        return 0;
+}
+
+static unsigned int __init intc_prio_value(struct intc_desc *desc,
+                                           intc_enum enum_id, int do_grps)
+{
+        struct intc_prio *p = desc->priorities;
+        unsigned int i;
+
+        for (i = 0; p && enum_id && i < desc->nr_priorities; i++) {
+                p = desc->priorities + i;
+
+                if (p->enum_id != enum_id)
+                        continue;
+
+                return p->priority;
+        }
+
+        if (do_grps)
+                return intc_prio_value(desc, intc_grp_id(desc, enum_id), 0);
+
+        /* default to the lowest priority possible if no priority is set
+         * - this needs to be at least 2 for 5-bit priorities on 7780
+         */
+
+        return 2;
+}
+
+static unsigned int __init intc_mask_data(struct intc_desc *desc,
+                                          intc_enum enum_id, int do_grps)
+{
+        struct intc_mask_reg *mr = desc->mask_regs;
+        unsigned int i, j, fn;
+
+        for (i = 0; mr && enum_id && i < desc->nr_mask_regs; i++) {
+                mr = desc->mask_regs + i;
+
+                for (j = 0; j < ARRAY_SIZE(mr->enum_ids); j++) {
+                        if (mr->enum_ids[j] != enum_id)
+                                continue;
+
+                        fn = intc_find_mask_handler(mr->reg_width);
+                        if (fn == REG_FN_ERROR)
+                                return 0;
+
+                        return _INTC_MK(fn, i, (mr->reg_width - 1) - j, 0);
+                }
+        }
+
+        if (do_grps)
+                return intc_mask_data(desc, intc_grp_id(desc, enum_id), 0);
+
+        return 0;
+}
+
+static unsigned int __init intc_prio_data(struct intc_desc *desc,
+                                          intc_enum enum_id, int do_grps)
+{
+        struct intc_prio_reg *pr = desc->prio_regs;
+        unsigned int i, j, fn, bit, prio;
+
+        for (i = 0; pr && enum_id && i < desc->nr_prio_regs; i++) {
+                pr = desc->prio_regs + i;
+
+                for (j = 0; j < ARRAY_SIZE(pr->enum_ids); j++) {
+                        if (pr->enum_ids[j] != enum_id)
+                                continue;
+
+                        fn = intc_find_prio_handler(pr->reg_width);
+                        if (fn == REG_FN_ERROR)
+                                return 0;
+
+                        prio = intc_prio_value(desc, enum_id, 1);
+                        bit = pr->reg_width - ((j + 1) * pr->field_width);
+
+                        BUG_ON(bit < 0);
+
+                        return _INTC_MK(fn, i, bit, prio);
+                }
+        }
+
+        if (do_grps)
+                return intc_prio_data(desc, intc_grp_id(desc, enum_id), 0);
+
+        return 0;
+}
+
+static void __init intc_register_irq(struct intc_desc *desc, intc_enum enum_id,
+                                     unsigned int irq)
+{
+        unsigned int data[2], primary;
+
+        /* Prefer single interrupt source bitmap over other combinations:
+         * 1. bitmap, single interrupt source
+         * 2. priority, single interrupt source
+         * 3. bitmap, multiple interrupt sources (groups)
+         * 4. priority, multiple interrupt sources (groups)
+         */
+
+        data[0] = intc_mask_data(desc, enum_id, 0);
+        data[1] = intc_prio_data(desc, enum_id, 0);
+
+        primary = 0;
+        if (!data[0] && data[1])
+                primary = 1;
+
+        data[0] = data[0] ? data[0] : intc_mask_data(desc, enum_id, 1);
+        data[1] = data[1] ? data[1] : intc_prio_data(desc, enum_id, 1);
+
+        if (!data[primary])
+                primary ^= 1;
+
+        BUG_ON(!data[primary]); /* must have primary masking method */
+
+        disable_irq_nosync(irq);
+        set_irq_chip_and_handler_name(irq, &desc->chip,
+                                      handle_level_irq, "level");
+        set_irq_chip_data(irq, (void *)data[primary]);
+
+        /* enable secondary masking method if present */
+        if (data[!primary])
+                intc_reg_fns[_INTC_FN(data[!primary])].enable(desc,
+                                                              data[!primary]);
+
+        /* irq should be disabled by default */
+        desc->chip.mask(irq);
+}
+
+void __init register_intc_controller(struct intc_desc *desc)
+{
+        unsigned int i;
+
+        desc->chip.mask = intc_disable;
+        desc->chip.unmask = intc_enable;
+        desc->chip.mask_ack = intc_disable;
+        desc->chip.set_type = intc_set_sense;
+
+        for (i = 0; i < desc->nr_vectors; i++) {
+                struct intc_vect *vect = desc->vectors + i;
+
+                intc_register_irq(desc, vect->enum_id, evt2irq(vect->vect));
+        }
+}
diff --git a/arch/sh/kernel/cpu/sh2/setup-sh7619.c b/arch/sh/kernel/cpu/sh2/setup-sh7619.c
index 1a107fe22dde..a979b981e6a3 100644
--- a/arch/sh/kernel/cpu/sh2/setup-sh7619.c
+++ b/arch/sh/kernel/cpu/sh2/setup-sh7619.c
@@ -88,7 +88,7 @@ static struct ipr_desc ipr_irq_desc = {
         },
 };
 
-void __init init_IRQ_ipr(void)
+void __init plat_irq_setup(void)
 {
         register_ipr_controller(&ipr_irq_desc);
 }
diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7206.c b/arch/sh/kernel/cpu/sh2a/setup-sh7206.c
index b6e3a6351fa6..deab16500167 100644
--- a/arch/sh/kernel/cpu/sh2a/setup-sh7206.c
+++ b/arch/sh/kernel/cpu/sh2a/setup-sh7206.c
@@ -107,7 +107,7 @@ static struct ipr_desc ipr_irq_desc = {
         },
 };
 
-void __init init_IRQ_ipr(void)
+void __init plat_irq_setup(void)
 {
         register_ipr_controller(&ipr_irq_desc);
 }
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7705.c b/arch/sh/kernel/cpu/sh3/setup-sh7705.c
index a55b8ce2c54c..ebd9d06d8bdd 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh7705.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh7705.c
@@ -92,7 +92,7 @@ static struct ipr_desc ipr_irq_desc = {
         },
 };
 
-void __init init_IRQ_ipr(void)
+void __init plat_irq_setup(void)
 {
         register_ipr_controller(&ipr_irq_desc);
 }
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7709.c b/arch/sh/kernel/cpu/sh3/setup-sh7709.c
index d79ec0c0522f..086f8e2545af 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh7709.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh7709.c
@@ -139,7 +139,7 @@ static struct ipr_desc ipr_irq_desc = {
         },
 };
 
-void __init init_IRQ_ipr(void)
+void __init plat_irq_setup(void)
 {
         register_ipr_controller(&ipr_irq_desc);
 }
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7710.c b/arch/sh/kernel/cpu/sh3/setup-sh7710.c
index f40e6dac337d..132284893373 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh7710.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh7710.c
@@ -101,7 +101,7 @@ static struct ipr_desc ipr_irq_desc = {
         },
 };
 
-void __init init_IRQ_ipr(void)
+void __init plat_irq_setup(void)
 {
         register_ipr_controller(&ipr_irq_desc);
 }
diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7750.c b/arch/sh/kernel/cpu/sh4/setup-sh7750.c
index da153bcdfeb2..f2286de22bd5 100644
--- a/arch/sh/kernel/cpu/sh4/setup-sh7750.c
+++ b/arch/sh/kernel/cpu/sh4/setup-sh7750.c
@@ -82,88 +82,213 @@ static int __init sh7750_devices_setup(void)
 }
 __initcall(sh7750_devices_setup);
 
-static struct ipr_data ipr_irq_table[] = {
-        /* IRQ, IPR-idx, shift, priority */
-        { 16, 0, 12, 2 }, /* TMU0 TUNI*/
-        { 17, 0, 12, 2 }, /* TMU1 TUNI */
-        { 18, 0,  4, 2 }, /* TMU2 TUNI */
-        { 19, 0,  4, 2 }, /* TMU2 TIPCI */
-        { 27, 1, 12, 2 }, /* WDT ITI */
-        { 20, 0,  0, 2 }, /* RTC ATI (alarm) */
-        { 21, 0,  0, 2 }, /* RTC PRI (period) */
-        { 22, 0,  0, 2 }, /* RTC CUI (carry) */
-        { 23, 1,  4, 3 }, /* SCI ERI */
-        { 24, 1,  4, 3 }, /* SCI RXI */
-        { 25, 1,  4, 3 }, /* SCI TXI */
-        { 40, 2,  4, 3 }, /* SCIF ERI */
-        { 41, 2,  4, 3 }, /* SCIF RXI */
-        { 42, 2,  4, 3 }, /* SCIF BRI */
-        { 43, 2,  4, 3 }, /* SCIF TXI */
-        { 34, 2,  8, 7 }, /* DMAC DMTE0 */
-        { 35, 2,  8, 7 }, /* DMAC DMTE1 */
-        { 36, 2,  8, 7 }, /* DMAC DMTE2 */
-        { 37, 2,  8, 7 }, /* DMAC DMTE3 */
-        { 38, 2,  8, 7 }, /* DMAC DMAE */
-};
-
-static unsigned long ipr_offsets[] = {
-        0xffd00004UL,   /* 0: IPRA */
-        0xffd00008UL,   /* 1: IPRB */
-        0xffd0000cUL,   /* 2: IPRC */
-        0xffd00010UL,   /* 3: IPRD */
-};
-
-static struct ipr_desc ipr_irq_desc = {
-        .ipr_offsets    = ipr_offsets,
-        .nr_offsets     = ARRAY_SIZE(ipr_offsets),
-
-        .ipr_data       = ipr_irq_table,
-        .nr_irqs        = ARRAY_SIZE(ipr_irq_table),
-
-        .chip = {
-                .name   = "IPR-sh7750",
-        },
+enum {
+        UNUSED = 0,
+
+        /* interrupt sources */
+        IRL0, IRL1, IRL2, IRL3, /* only IRLM mode supported */
+        HUDI, GPIOI,
+        DMAC_DMTE0, DMAC_DMTE1, DMAC_DMTE2, DMAC_DMTE3,
+        DMAC_DMTE4, DMAC_DMTE5, DMAC_DMTE6, DMAC_DMTE7,
+        DMAC_DMAE,
+        PCIC0_PCISERR, PCIC1_PCIERR, PCIC1_PCIPWDWN, PCIC1_PCIPWON,
+        PCIC1_PCIDMA0, PCIC1_PCIDMA1, PCIC1_PCIDMA2, PCIC1_PCIDMA3,
+        TMU3, TMU4, TMU0, TMU1, TMU2_TUNI, TMU2_TICPI,
+        RTC_ATI, RTC_PRI, RTC_CUI,
+        SCI1_ERI, SCI1_RXI, SCI1_TXI, SCI1_TEI,
+        SCIF_ERI, SCIF_RXI, SCIF_BRI, SCIF_TXI,
+        WDT,
+        REF_RCMI, REF_ROVI,
+
+        /* interrupt groups */
+        DMAC, PCIC1, TMU2, RTC, SCI1, SCIF, REF,
 };
 
-#ifdef CONFIG_CPU_SUBTYPE_SH7751
-static struct ipr_data ipr_irq_table_sh7751[] = {
-        { 44, 2,  8, 7 }, /* DMAC DMTE4 */
-        { 45, 2,  8, 7 }, /* DMAC DMTE5 */
-        { 46, 2,  8, 7 }, /* DMAC DMTE6 */
-        { 47, 2,  8, 7 }, /* DMAC DMTE7 */
-        /* The following use INTC_INPRI00 for masking, which is a 32-bit
-           register, not a 16-bit register like the IPRx registers, so it
-           would need special support */
-        /*{ 72, INTPRI00,  8, ? },*/ /* TMU3 TUNI */
-        /*{ 76, INTPRI00, 12, ? },*/ /* TMU4 TUNI */
+static struct intc_vect vectors[] = {
+        INTC_VECT(HUDI, 0x600), INTC_VECT(GPIOI, 0x620),
+        INTC_VECT(TMU0, 0x400), INTC_VECT(TMU1, 0x420),
+        INTC_VECT(TMU2_TUNI, 0x440), INTC_VECT(TMU2_TICPI, 0x460),
+        INTC_VECT(RTC_ATI, 0x480), INTC_VECT(RTC_PRI, 0x4a0),
+        INTC_VECT(RTC_CUI, 0x4c0),
+        INTC_VECT(SCI1_ERI, 0x4e0), INTC_VECT(SCI1_RXI, 0x500),
+        INTC_VECT(SCI1_TXI, 0x520), INTC_VECT(SCI1_TEI, 0x540),
+        INTC_VECT(SCIF_ERI, 0x700), INTC_VECT(SCIF_RXI, 0x720),
+        INTC_VECT(SCIF_BRI, 0x740), INTC_VECT(SCIF_TXI, 0x760),
+        INTC_VECT(WDT, 0x560),
+        INTC_VECT(REF_RCMI, 0x580), INTC_VECT(REF_ROVI, 0x5a0),
 };
 
-static struct ipr_desc ipr_irq_desc_sh7751 = {
-        .ipr_offsets    = ipr_offsets,
-        .nr_offsets     = ARRAY_SIZE(ipr_offsets),
+static struct intc_group groups[] = {
+        INTC_GROUP(TMU2, TMU2_TUNI, TMU2_TICPI),
+        INTC_GROUP(RTC, RTC_ATI, RTC_PRI, RTC_CUI),
+        INTC_GROUP(SCI1, SCI1_ERI, SCI1_RXI, SCI1_TXI, SCI1_TEI),
+        INTC_GROUP(SCIF, SCIF_ERI, SCIF_RXI, SCIF_BRI, SCIF_TXI),
+        INTC_GROUP(REF, REF_RCMI, REF_ROVI),
+};
 
-        .ipr_data       = ipr_irq_table_sh7751,
-        .nr_irqs        = ARRAY_SIZE(ipr_irq_table_sh7751),
+static struct intc_prio priorities[] = {
+        INTC_PRIO(SCIF, 3),
+        INTC_PRIO(SCI1, 3),
+        INTC_PRIO(DMAC, 7),
+};
 
-        .chip = {
-                .name   = "IPR-sh7751",
-        },
+static struct intc_prio_reg prio_registers[] = {
+        { 0xffd00004, 16, 4, /* IPRA */ { TMU0, TMU1, TMU2, RTC } },
+        { 0xffd00008, 16, 4, /* IPRB */ { WDT, REF, SCI1, 0 } },
+        { 0xffd0000c, 16, 4, /* IPRC */ { GPIOI, DMAC, SCIF, HUDI } },
+        { 0xffd00010, 16, 4, /* IPRD */ { IRL0, IRL1, IRL2, IRL3 } },
+        { 0xfe080000, 32, 4, /* INTPRI00 */ { 0, 0, 0, 0,
+                                              TMU4, TMU3,
+                                              PCIC1, PCIC0_PCISERR } },
+};
+
+static DECLARE_INTC_DESC(intc_desc, "sh7750", vectors, groups,
+                         priorities, NULL, prio_registers, NULL);
+
+/* SH7750, SH7750S, SH7751 and SH7091 all have 4-channel DMA controllers */
+#if defined(CONFIG_CPU_SUBTYPE_SH7750) || \
+        defined(CONFIG_CPU_SUBTYPE_SH7750S) || \
+        defined(CONFIG_CPU_SUBTYPE_SH7751) || \
+        defined(CONFIG_CPU_SUBTYPE_SH7091)
+static struct intc_vect vectors_dma4[] = {
+        INTC_VECT(DMAC_DMTE0, 0x640), INTC_VECT(DMAC_DMTE1, 0x660),
+        INTC_VECT(DMAC_DMTE2, 0x680), INTC_VECT(DMAC_DMTE3, 0x6a0),
+        INTC_VECT(DMAC_DMAE, 0x6c0),
+};
+
+static struct intc_group groups_dma4[] = {
+        INTC_GROUP(DMAC, DMAC_DMTE0, DMAC_DMTE1, DMAC_DMTE2,
+                   DMAC_DMTE3, DMAC_DMAE),
+};
+
+static DECLARE_INTC_DESC(intc_desc_dma4, "sh7750_dma4",
+                         vectors_dma4, groups_dma4,
+                         priorities, NULL, prio_registers, NULL);
+#endif
+
+/* SH7750R and SH7751R both have 8-channel DMA controllers */
+#if defined(CONFIG_CPU_SUBTYPE_SH7750R) || defined(CONFIG_CPU_SUBTYPE_SH7751R)
+static struct intc_vect vectors_dma8[] = {
+        INTC_VECT(DMAC_DMTE0, 0x640), INTC_VECT(DMAC_DMTE1, 0x660),
+        INTC_VECT(DMAC_DMTE2, 0x680), INTC_VECT(DMAC_DMTE3, 0x6a0),
+        INTC_VECT(DMAC_DMTE4, 0x780), INTC_VECT(DMAC_DMTE5, 0x7a0),
+        INTC_VECT(DMAC_DMTE6, 0x7c0), INTC_VECT(DMAC_DMTE7, 0x7e0),
+        INTC_VECT(DMAC_DMAE, 0x6c0),
+};
+
+static struct intc_group groups_dma8[] = {
+        INTC_GROUP(DMAC, DMAC_DMTE0, DMAC_DMTE1, DMAC_DMTE2,
+                   DMAC_DMTE3, DMAC_DMTE4, DMAC_DMTE5,
+                   DMAC_DMTE6, DMAC_DMTE7, DMAC_DMAE),
+};
+
+static DECLARE_INTC_DESC(intc_desc_dma8, "sh7750_dma8",
+                         vectors_dma8, groups_dma8,
+                         priorities, NULL, prio_registers, NULL);
+#endif
+
+/* SH7750R, SH7751 and SH7751R all have two extra timer channels */
+#if defined(CONFIG_CPU_SUBTYPE_SH7750R) || \
+        defined(CONFIG_CPU_SUBTYPE_SH7751) || \
+        defined(CONFIG_CPU_SUBTYPE_SH7751R)
+static struct intc_vect vectors_tmu34[] = {
+        INTC_VECT(TMU3, 0xb00), INTC_VECT(TMU4, 0xb80),
 };
+
+static struct intc_mask_reg mask_registers[] = {
+        { 0xfe080040, 0xfe080060, 32, /* INTMSK00 / INTMSKCLR00 */
+          { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+            0, 0, 0, 0, 0, 0, TMU4, TMU3,
+            PCIC1_PCIERR, PCIC1_PCIPWDWN, PCIC1_PCIPWON,
+            PCIC1_PCIDMA0, PCIC1_PCIDMA1, PCIC1_PCIDMA2,
+            PCIC1_PCIDMA3, PCIC0_PCISERR } },
+};
+
+static DECLARE_INTC_DESC(intc_desc_tmu34, "sh7750_tmu34",
+                         vectors_tmu34, NULL, priorities,
+                         mask_registers, prio_registers, NULL);
 #endif
 
-void __init init_IRQ_ipr(void)
+/* SH7750S, SH7750R, SH7751 and SH7751R all have IRLM priority registers */
+static struct intc_vect vectors_irlm[] = {
+        INTC_VECT(IRL0, 0x240), INTC_VECT(IRL1, 0x2a0),
+        INTC_VECT(IRL2, 0x300), INTC_VECT(IRL3, 0x360),
+};
+
+static DECLARE_INTC_DESC(intc_desc_irlm, "sh7750_irlm", vectors_irlm, NULL,
+                         priorities, NULL, prio_registers, NULL);
+
+/* SH7751 and SH7751R both have PCI */
+#if defined(CONFIG_CPU_SUBTYPE_SH7751) || defined(CONFIG_CPU_SUBTYPE_SH7751R)
+static struct intc_vect vectors_pci[] = {
+        INTC_VECT(PCIC0_PCISERR, 0xa00), INTC_VECT(PCIC1_PCIERR, 0xae0),
+        INTC_VECT(PCIC1_PCIPWDWN, 0xac0), INTC_VECT(PCIC1_PCIPWON, 0xaa0),
+        INTC_VECT(PCIC1_PCIDMA0, 0xa80), INTC_VECT(PCIC1_PCIDMA1, 0xa60),
+        INTC_VECT(PCIC1_PCIDMA2, 0xa40), INTC_VECT(PCIC1_PCIDMA3, 0xa20),
+};
+
+static struct intc_group groups_pci[] = {
+        INTC_GROUP(PCIC1, PCIC1_PCIERR, PCIC1_PCIPWDWN, PCIC1_PCIPWON,
+                   PCIC1_PCIDMA0, PCIC1_PCIDMA1, PCIC1_PCIDMA2, PCIC1_PCIDMA3),
+};
+
+static DECLARE_INTC_DESC(intc_desc_pci, "sh7750_pci", vectors_pci, groups_pci,
+                         priorities, mask_registers, prio_registers, NULL);
+#endif
+
+#if defined(CONFIG_CPU_SUBTYPE_SH7750) || \
+        defined(CONFIG_CPU_SUBTYPE_SH7750S) || \
+        defined(CONFIG_CPU_SUBTYPE_SH7091)
+void __init plat_irq_setup(void)
 {
-        register_ipr_controller(&ipr_irq_desc);
-#ifdef CONFIG_CPU_SUBTYPE_SH7751
-        register_ipr_controller(&ipr_irq_desc_sh7751);
+        /*
+         * same vectors for SH7750, SH7750S and SH7091 except for IRLM,
+         * see below..
+         */
+        register_intc_controller(&intc_desc);
+        register_intc_controller(&intc_desc_dma4);
+}
 #endif
+
+#if defined(CONFIG_CPU_SUBTYPE_SH7750R)
+void __init plat_irq_setup(void)
+{
+        register_intc_controller(&intc_desc);
+        register_intc_controller(&intc_desc_dma8);
+        register_intc_controller(&intc_desc_tmu34);
 }
+#endif
+
+#if defined(CONFIG_CPU_SUBTYPE_SH7751)
+void __init plat_irq_setup(void)
+{
+        register_intc_controller(&intc_desc);
+        register_intc_controller(&intc_desc_dma4);
+        register_intc_controller(&intc_desc_tmu34);
+        register_intc_controller(&intc_desc_pci);
+}
+#endif
+
+#if defined(CONFIG_CPU_SUBTYPE_SH7751R)
+void __init plat_irq_setup(void)
+{
+        register_intc_controller(&intc_desc);
+        register_intc_controller(&intc_desc_dma8);
+        register_intc_controller(&intc_desc_tmu34);
+        register_intc_controller(&intc_desc_pci);
+}
+#endif
 
 #define INTC_ICR        0xffd00000UL
 #define INTC_ICR_IRLM   (1<<7)
 
 /* enable individual interrupt mode for external interupts */
-void ipr_irq_enable_irlm(void)
+void __init ipr_irq_enable_irlm(void)
 {
+#if defined(CONFIG_CPU_SUBTYPE_SH7750) || defined(CONFIG_CPU_SUBTYPE_SH7091)
+        BUG(); /* impossible to mask interrupts on SH7750 and SH7091 */
+#endif
+        register_intc_controller(&intc_desc_irlm);
+
         ctrl_outw(ctrl_inw(INTC_ICR) | INTC_ICR_IRLM, INTC_ICR);
 }
diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7760.c b/arch/sh/kernel/cpu/sh4/setup-sh7760.c
index 3df169755673..47fa27056253 100644
--- a/arch/sh/kernel/cpu/sh4/setup-sh7760.c
+++ b/arch/sh/kernel/cpu/sh4/setup-sh7760.c
@@ -109,11 +109,6 @@ static struct intc2_desc intc2_irq_desc __read_mostly = {
         },
 };
 
-void __init init_IRQ_intc2(void)
-{
-        register_intc2_controller(&intc2_irq_desc);
-}
-
 static struct ipr_data ipr_irq_table[] = {
         /* IRQ, IPR-idx, shift, priority */
         { 16, 0, 12, 2 }, /* TMU0 TUNI*/
@@ -163,7 +158,8 @@ static struct ipr_desc ipr_irq_desc = {
         },
 };
 
-void __init init_IRQ_ipr(void)
+void __init plat_irq_setup(void)
 {
+        register_intc2_controller(&intc2_irq_desc);
         register_ipr_controller(&ipr_irq_desc);
 }
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7722.c b/arch/sh/kernel/cpu/sh4a/clock-sh7722.c
index 51b386d454de..a0fd8bb21f7c 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7722.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7722.c
@@ -387,9 +387,24 @@ out_err:
         return err;
 }
 
+static long sh7722_frqcr_round_rate(struct clk *clk, unsigned long rate)
+{
+        unsigned long parent_rate = clk->parent->rate;
+        int div;
+
+        /* look for multiplier/divisor pair */
+        div = sh7722_find_divisors(parent_rate, rate);
+        if (div < 0)
+                return clk->rate;
+
+        /* calculate new value of clock rate */
+        return parent_rate * 2 / div;
+}
+
 static struct clk_ops sh7722_frqcr_clk_ops = {
         .recalc = sh7722_frqcr_recalc,
         .set_rate = sh7722_frqcr_set_rate,
+        .round_rate = sh7722_frqcr_round_rate,
 };
 
 /*
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c
index a3e159ef6dfe..25b913e07e2c 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c
@@ -19,8 +19,21 @@ static struct plat_sci_port sci_platform_data[] = {
                 .mapbase        = 0xffe00000,
                 .flags          = UPF_BOOT_AUTOCONF,
                 .type           = PORT_SCIF,
-                .irqs           = { 80, 81, 83, 82 },
-        }, {
+                .irqs           = { 80, 80, 80, 80 },
+        },
+        {
+                .mapbase        = 0xffe10000,
+                .flags          = UPF_BOOT_AUTOCONF,
+                .type           = PORT_SCIF,
+                .irqs           = { 81, 81, 81, 81 },
+        },
+        {
+                .mapbase        = 0xffe20000,
+                .flags          = UPF_BOOT_AUTOCONF,
+                .type           = PORT_SCIF,
+                .irqs           = { 82, 82, 82, 82 },
+        },
+        {
                 .flags = 0,
         }
 };
@@ -44,46 +57,145 @@ static int __init sh7722_devices_setup(void)
 }
 __initcall(sh7722_devices_setup);
 
-static struct ipr_data ipr_irq_table[] = {
-        /* IRQ, IPR-idx, shift, prio */
-        { 16, 0, 12, 2 }, /* TMU0 */
-        { 17, 0,  8, 2 }, /* TMU1 */
-        { 80, 6, 12, 3 }, /* SCIF ERI */
-        { 81, 6, 12, 3 }, /* SCIF RXI */
-        { 82, 6, 12, 3 }, /* SCIF BRI */
-        { 83, 6, 12, 3 }, /* SCIF TXI */
+enum {
+        UNUSED=0,
+
+        /* interrupt sources */
+        IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5, IRQ6, IRQ7,
+        HUDI,
+        SIM_ERI, SIM_RXI, SIM_TXI, SIM_TEI,
+        RTC_ATI, RTC_PRI, RTC_CUI,
+        DMAC0, DMAC1, DMAC2, DMAC3,
+        VIO_CEUI, VIO_BEUI, VIO_VEUI, VOU,
+        VPU, TPU,
+        USB_USBI0, USB_USBI1,
+        DMAC4, DMAC5, DMAC_DADERR,
+        KEYSC,
+        SCIF0, SCIF1, SCIF2, SIOF0, SIOF1, SIO,
+        FLCTL_FLSTEI, FLCTL_FLENDI, FLCTL_FLTREQ0I, FLCTL_FLTREQ1I,
+        I2C_ALI, I2C_TACKI, I2C_WAITI, I2C_DTEI,
+        SDHI0, SDHI1, SDHI2, SDHI3,
+        CMT, TSIF, SIU, TWODG,
+        TMU0, TMU1, TMU2,
+        IRDA, JPU, LCDC,
+
+        /* interrupt groups */
+
+        SIM, RTC, DMAC0123, VIOVOU, USB, DMAC45, FLCTL, I2C, SDHI,
 };
 
-static unsigned long ipr_offsets[] = {
-        0xa4080000, /*  0: IPRA */
-        0xa4080004, /*  1: IPRB */
-        0xa4080008, /*  2: IPRC */
-        0xa408000c, /*  3: IPRD */
-        0xa4080010, /*  4: IPRE */
-        0xa4080014, /*  5: IPRF */
-        0xa4080018, /*  6: IPRG */
-        0xa408001c, /*  7: IPRH */
-        0xa4080020, /*  8: IPRI */
-        0xa4080024, /*  9: IPRJ */
-        0xa4080028, /* 10: IPRK */
-        0xa408002c, /* 11: IPRL */
+static struct intc_vect vectors[] = {
+        INTC_VECT(IRQ0, 0x600), INTC_VECT(IRQ1, 0x620),
+        INTC_VECT(IRQ2, 0x640), INTC_VECT(IRQ3, 0x660),
+        INTC_VECT(IRQ4, 0x680), INTC_VECT(IRQ5, 0x6a0),
+        INTC_VECT(IRQ6, 0x6c0), INTC_VECT(IRQ7, 0x6e0),
+        INTC_VECT(SIM_ERI, 0x700), INTC_VECT(SIM_RXI, 0x720),
+        INTC_VECT(SIM_TXI, 0x740), INTC_VECT(SIM_TEI, 0x760),
+        INTC_VECT(RTC_ATI, 0x780), INTC_VECT(RTC_PRI, 0x7a0),
+        INTC_VECT(RTC_CUI, 0x7c0),
+        INTC_VECT(DMAC0, 0x800), INTC_VECT(DMAC1, 0x820),
+        INTC_VECT(DMAC2, 0x840), INTC_VECT(DMAC3, 0x860),
+        INTC_VECT(VIO_CEUI, 0x880), INTC_VECT(VIO_BEUI, 0x8a0),
+        INTC_VECT(VIO_VEUI, 0x8c0), INTC_VECT(VOU, 0x8e0),
+        INTC_VECT(VPU, 0x980), INTC_VECT(TPU, 0x9a0),
+        INTC_VECT(USB_USBI0, 0xa20), INTC_VECT(USB_USBI1, 0xa40),
+        INTC_VECT(DMAC4, 0xb80), INTC_VECT(DMAC5, 0xba0),
+        INTC_VECT(DMAC_DADERR, 0xbc0), INTC_VECT(KEYSC, 0xbe0),
+        INTC_VECT(SCIF0, 0xc00), INTC_VECT(SCIF1, 0xc20),
+        INTC_VECT(SCIF2, 0xc40), INTC_VECT(SIOF0, 0xc80),
+        INTC_VECT(SIOF1, 0xca0), INTC_VECT(SIO, 0xd00),
+        INTC_VECT(FLCTL_FLSTEI, 0xd80), INTC_VECT(FLCTL_FLENDI, 0xda0),
+        INTC_VECT(FLCTL_FLTREQ0I, 0xdc0), INTC_VECT(FLCTL_FLTREQ1I, 0xde0),
+        INTC_VECT(I2C_ALI, 0xe00), INTC_VECT(I2C_TACKI, 0xe20),
+        INTC_VECT(I2C_WAITI, 0xe40), INTC_VECT(I2C_DTEI, 0xe60),
+        INTC_VECT(SDHI0, 0xe80), INTC_VECT(SDHI1, 0xea0),
+        INTC_VECT(SDHI2, 0xec0), INTC_VECT(SDHI3, 0xee0),
+        INTC_VECT(CMT, 0xf00), INTC_VECT(TSIF, 0xf20),
+        INTC_VECT(SIU, 0xf80), INTC_VECT(TWODG, 0xfa0),
+        INTC_VECT(TMU0, 0x400), INTC_VECT(TMU1, 0x420),
+        INTC_VECT(TMU2, 0x440), INTC_VECT(IRDA, 0x480),
+        INTC_VECT(JPU, 0x560), INTC_VECT(LCDC, 0x580),
 };
 
-static struct ipr_desc ipr_irq_desc = {
-        .ipr_offsets    = ipr_offsets,
-        .nr_offsets     = ARRAY_SIZE(ipr_offsets),
+static struct intc_group groups[] = {
+        INTC_GROUP(SIM, SIM_ERI, SIM_RXI, SIM_TXI, SIM_TEI),
+        INTC_GROUP(RTC, RTC_ATI, RTC_PRI, RTC_CUI),
+        INTC_GROUP(DMAC0123, DMAC0, DMAC1, DMAC2, DMAC3),
+        INTC_GROUP(VIOVOU, VIO_CEUI, VIO_BEUI, VIO_VEUI, VOU),
+        INTC_GROUP(USB, USB_USBI0, USB_USBI1),
+        INTC_GROUP(DMAC45, DMAC4, DMAC5, DMAC_DADERR),
+        INTC_GROUP(FLCTL, FLCTL_FLSTEI, FLCTL_FLENDI,
+                   FLCTL_FLTREQ0I, FLCTL_FLTREQ1I),
+        INTC_GROUP(I2C, I2C_ALI, I2C_TACKI, I2C_WAITI, I2C_DTEI),
+        INTC_GROUP(SDHI, SDHI0, SDHI1, SDHI2, SDHI3),
+};
 
-        .ipr_data       = ipr_irq_table,
-        .nr_irqs        = ARRAY_SIZE(ipr_irq_table),
+static struct intc_prio priorities[] = {
+        INTC_PRIO(SCIF0, 3),
+        INTC_PRIO(SCIF1, 3),
+        INTC_PRIO(SCIF2, 3),
+        INTC_PRIO(TMU0, 2),
+        INTC_PRIO(TMU1, 2),
+};
 
-        .chip = {
-                .name   = "IPR-sh7722",
-        },
+static struct intc_mask_reg mask_registers[] = {
+        { 0xa4080080, 0xa40800c0, 8, /* IMR0 / IMCR0 */
+          { } },
+        { 0xa4080084, 0xa40800c4, 8, /* IMR1 / IMCR1 */
+          { VOU, VIO_VEUI, VIO_BEUI, VIO_CEUI, DMAC3, DMAC2, DMAC1, DMAC0 } },
+        { 0xa4080088, 0xa40800c8, 8, /* IMR2 / IMCR2 */
+          { 0, 0, 0, VPU, } },
+        { 0xa408008c, 0xa40800cc, 8, /* IMR3 / IMCR3 */
+          { SIM_TEI, SIM_TXI, SIM_RXI, SIM_ERI, 0, 0, 0, IRDA } },
+        { 0xa4080090, 0xa40800d0, 8, /* IMR4 / IMCR4 */
+          { 0, TMU2, TMU1, TMU0, JPU, 0, 0, LCDC } },
+        { 0xa4080094, 0xa40800d4, 8, /* IMR5 / IMCR5 */
+          { KEYSC, DMAC_DADERR, DMAC5, DMAC4, 0, SCIF2, SCIF1, SCIF0 } },
+        { 0xa4080098, 0xa40800d8, 8, /* IMR6 / IMCR6 */
+          { 0, 0, 0, SIO, 0, 0, SIOF1, SIOF0 } },
+        { 0xa408009c, 0xa40800dc, 8, /* IMR7 / IMCR7 */
+          { I2C_DTEI, I2C_WAITI, I2C_TACKI, I2C_ALI,
+            FLCTL_FLTREQ1I, FLCTL_FLTREQ0I, FLCTL_FLENDI, FLCTL_FLSTEI } },
+        { 0xa40800a0, 0xa40800e0, 8, /* IMR8 / IMCR8 */
+          { SDHI3, SDHI2, SDHI1, SDHI0, 0, 0, TWODG, SIU } },
+        { 0xa40800a4, 0xa40800e4, 8, /* IMR9 / IMCR9 */
+          { 0, 0, 0, CMT, 0, USB_USBI1, USB_USBI0, } },
+        { 0xa40800a8, 0xa40800e8, 8, /* IMR10 / IMCR10 */
+          { } },
+        { 0xa40800ac, 0xa40800ec, 8, /* IMR11 / IMCR11 */
+          { 0, RTC_CUI, RTC_PRI, RTC_ATI, 0, TPU, 0, TSIF } },
+        { 0xa4140044, 0xa4140064, 8, /* INTMSK00 / INTMSKCLR00 */
+          { IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5, IRQ6, IRQ7 } },
 };
 
-void __init init_IRQ_ipr(void)
+static struct intc_prio_reg prio_registers[] = {
+        { 0xa4080000, 16, 4, /* IPRA */ { TMU0, TMU1, TMU2, IRDA } },
+        { 0xa4080004, 16, 4, /* IPRB */ { JPU, LCDC, SIM } },
+        { 0xa4080008, 16, 4, /* IPRC */ { } },
+        { 0xa408000c, 16, 4, /* IPRD */ { } },
+        { 0xa4080010, 16, 4, /* IPRE */ { DMAC0123, VIOVOU, 0, VPU } },
+        { 0xa4080014, 16, 4, /* IPRF */ { KEYSC, DMAC45, USB, CMT } },
+        { 0xa4080018, 16, 4, /* IPRG */ { SCIF0, SCIF1, SCIF2 } },
+        { 0xa408001c, 16, 4, /* IPRH */ { SIOF0, SIOF1, FLCTL, I2C } },
+        { 0xa4080020, 16, 4, /* IPRI */ { SIO, 0, TSIF, RTC } },
+        { 0xa4080024, 16, 4, /* IPRJ */ { 0, 0, SIU } },
+        { 0xa4080028, 16, 4, /* IPRK */ { 0, 0, 0, SDHI } },
+        { 0xa408002c, 16, 4, /* IPRL */ { TWODG, 0, TPU } },
+        { 0xa4140010, 32, 4, /* INTPRI00 */
+          { IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5, IRQ6, IRQ7 } },
+};
+
+static struct intc_sense_reg sense_registers[] = {
+        { 0xa414001c, 16, 2, /* ICR1 */
+          { IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5, IRQ6, IRQ7 } },
+};
+
+static DECLARE_INTC_DESC(intc_desc, "sh7722", vectors, groups, priorities,
+                         mask_registers, prio_registers, sense_registers);
+
+void __init plat_irq_setup(void)
 {
-        register_ipr_controller(&ipr_irq_desc);
+        register_intc_controller(&intc_desc);
 }
 
 void __init plat_mem_setup(void)
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c
index b57c760bffde..a4127ec15203 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c
@@ -30,7 +30,7 @@ static struct resource rtc_resources[] = {
         },
         [3] = {
                 /* Alarm IRQ */
-                .start  = 23,
+                .start  = 20,
                 .flags  = IORESOURCE_IRQ,
         },
 };
@@ -78,44 +78,205 @@ static int __init sh7780_devices_setup(void)
 }
 __initcall(sh7780_devices_setup);
 
-static struct intc2_data intc2_irq_table[] = {
-        { 28, 0, 24, 0, 0, 2 },         /* TMU0 */
+enum {
+        UNUSED = 0,
 
-        { 21, 1,  0, 0, 2, 2 },
-        { 22, 1,  1, 0, 2, 2 },
-        { 23, 1,  2, 0, 2, 2 },
+        /* interrupt sources */
 
-        { 40, 8, 24, 0, 3, 3 },         /* SCIF0 ERI */
-        { 41, 8, 24, 0, 3, 3 },         /* SCIF0 RXI */
-        { 42, 8, 24, 0, 3, 3 },         /* SCIF0 BRI */
-        { 43, 8, 24, 0, 3, 3 },         /* SCIF0 TXI */
+        IRL_LLLL, IRL_LLLH, IRL_LLHL, IRL_LLHH,
+        IRL_LHLL, IRL_LHLH, IRL_LHHL, IRL_LHHH,
+        IRL_HLLL, IRL_HLLH, IRL_HLHL, IRL_HLHH,
+        IRL_HHLL, IRL_HHLH, IRL_HHHL,
 
-        { 76, 8, 16, 0, 4, 3 },         /* SCIF1 ERI */
-        { 77, 8, 16, 0, 4, 3 },         /* SCIF1 RXI */
-        { 78, 8, 16, 0, 4, 3 },         /* SCIF1 BRI */
-        { 79, 8, 16, 0, 4, 3 },         /* SCIF1 TXI */
+        IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5, IRQ6, IRQ7,
+        RTC_ATI, RTC_PRI, RTC_CUI,
+        WDT,
+        TMU0, TMU1, TMU2, TMU2_TICPI,
+        HUDI,
+        DMAC0_DMINT0, DMAC0_DMINT1, DMAC0_DMINT2, DMAC0_DMINT3, DMAC0_DMAE,
+        SCIF0_ERI, SCIF0_RXI, SCIF0_BRI, SCIF0_TXI,
+        DMAC0_DMINT4, DMAC0_DMINT5, DMAC1_DMINT6, DMAC1_DMINT7,
+        CMT, HAC,
+        PCISERR, PCIINTA, PCIINTB, PCIINTC, PCIINTD,
+        PCIERR, PCIPWD3, PCIPWD2, PCIPWD1, PCIPWD0,
+        SCIF1_ERI, SCIF1_RXI, SCIF1_BRI, SCIF1_TXI,
+        SIOF, HSPI,
+        MMCIF_FSTAT, MMCIF_TRAN, MMCIF_ERR, MMCIF_FRDY,
+        DMAC1_DMINT8, DMAC1_DMINT9, DMAC1_DMINT10, DMAC1_DMINT11,
+        TMU3, TMU4, TMU5,
+        SSI,
+        FLCTL_FLSTE, FLCTL_FLEND, FLCTL_FLTRQ0, FLCTL_FLTRQ1,
+        GPIOI0, GPIOI1, GPIOI2, GPIOI3,
 
-        { 64, 0x10,  8, 0, 14, 2 },     /* PCIC0 */
-        { 65, 0x10,  0, 0, 15, 2 },     /* PCIC1 */
-        { 66, 0x14, 24, 0, 16, 2 },     /* PCIC2 */
-        { 67, 0x14, 16, 0, 17, 2 },     /* PCIC3 */
-        { 68, 0x14,  8, 0, 18, 2 },     /* PCIC4 */
+        /* interrupt groups */
+
+        RTC, TMU012, DMAC0, SCIF0, DMAC45, DMAC1,
+        PCIC5, SCIF1, MMCIF, TMU345, FLCTL, GPIO,
 };
 
-static struct intc2_desc intc2_irq_desc __read_mostly = {
-        .prio_base      = 0xffd40000,
-        .msk_base       = 0xffd40038,
-        .mskclr_base    = 0xffd4003c,
+static struct intc_vect vectors[] = {
+        INTC_VECT(RTC_ATI, 0x480), INTC_VECT(RTC_PRI, 0x4a0),
+        INTC_VECT(RTC_CUI, 0x4c0),
+        INTC_VECT(WDT, 0x560),
+        INTC_VECT(TMU0, 0x580), INTC_VECT(TMU1, 0x5a0),
+        INTC_VECT(TMU2, 0x5c0), INTC_VECT(TMU2_TICPI, 0x5e0),
+        INTC_VECT(HUDI, 0x600),
+        INTC_VECT(DMAC0_DMINT0, 0x640), INTC_VECT(DMAC0_DMINT1, 0x660),
+        INTC_VECT(DMAC0_DMINT2, 0x680), INTC_VECT(DMAC0_DMINT3, 0x6a0),
+        INTC_VECT(DMAC0_DMAE, 0x6c0),
+        INTC_VECT(SCIF0_ERI, 0x700), INTC_VECT(SCIF0_RXI, 0x720),
+        INTC_VECT(SCIF0_BRI, 0x740), INTC_VECT(SCIF0_TXI, 0x760),
+        INTC_VECT(DMAC0_DMINT4, 0x780), INTC_VECT(DMAC0_DMINT5, 0x7a0),
+        INTC_VECT(DMAC1_DMINT6, 0x7c0), INTC_VECT(DMAC1_DMINT7, 0x7e0),
+        INTC_VECT(CMT, 0x900), INTC_VECT(HAC, 0x980),
+        INTC_VECT(PCISERR, 0xa00), INTC_VECT(PCIINTA, 0xa20),
+        INTC_VECT(PCIINTB, 0xa40), INTC_VECT(PCIINTC, 0xa60),
+        INTC_VECT(PCIINTD, 0xa80), INTC_VECT(PCIERR, 0xaa0),
+        INTC_VECT(PCIPWD3, 0xac0), INTC_VECT(PCIPWD2, 0xae0),
+        INTC_VECT(PCIPWD1, 0xb00), INTC_VECT(PCIPWD0, 0xb20),
+        INTC_VECT(SCIF1_ERI, 0xb80), INTC_VECT(SCIF1_RXI, 0xba0),
+        INTC_VECT(SCIF1_BRI, 0xbc0), INTC_VECT(SCIF1_TXI, 0xbe0),
+        INTC_VECT(SIOF, 0xc00), INTC_VECT(HSPI, 0xc80),
+        INTC_VECT(MMCIF_FSTAT, 0xd00), INTC_VECT(MMCIF_TRAN, 0xd20),
+        INTC_VECT(MMCIF_ERR, 0xd40), INTC_VECT(MMCIF_FRDY, 0xd60),
+        INTC_VECT(DMAC1_DMINT8, 0xd80), INTC_VECT(DMAC1_DMINT9, 0xda0),
+        INTC_VECT(DMAC1_DMINT10, 0xdc0), INTC_VECT(DMAC1_DMINT11, 0xde0),
+        INTC_VECT(TMU3, 0xe00), INTC_VECT(TMU4, 0xe20),
+        INTC_VECT(TMU5, 0xe40),
+        INTC_VECT(SSI, 0xe80),
+        INTC_VECT(FLCTL_FLSTE, 0xf00), INTC_VECT(FLCTL_FLEND, 0xf20),
+        INTC_VECT(FLCTL_FLTRQ0, 0xf40), INTC_VECT(FLCTL_FLTRQ1, 0xf60),
+        INTC_VECT(GPIOI0, 0xf80), INTC_VECT(GPIOI1, 0xfa0),
+        INTC_VECT(GPIOI2, 0xfc0), INTC_VECT(GPIOI3, 0xfe0),
+};
 
-        .intc2_data     = intc2_irq_table,
-        .nr_irqs        = ARRAY_SIZE(intc2_irq_table),
+static struct intc_group groups[] = {
+        INTC_GROUP(RTC, RTC_ATI, RTC_PRI, RTC_CUI),
+        INTC_GROUP(TMU012, TMU0, TMU1, TMU2, TMU2_TICPI),
+        INTC_GROUP(DMAC0, DMAC0_DMINT0, DMAC0_DMINT1, DMAC0_DMINT2,
+                   DMAC0_DMINT3, DMAC0_DMINT4, DMAC0_DMINT5, DMAC0_DMAE),
+        INTC_GROUP(SCIF0, SCIF0_ERI, SCIF0_RXI, SCIF0_BRI, SCIF0_TXI),
+        INTC_GROUP(DMAC1, DMAC1_DMINT6, DMAC1_DMINT7, DMAC1_DMINT8,
+                   DMAC1_DMINT9, DMAC1_DMINT10, DMAC1_DMINT11),
+        INTC_GROUP(PCIC5, PCIERR, PCIPWD3, PCIPWD2, PCIPWD1, PCIPWD0),
+        INTC_GROUP(SCIF1, SCIF1_ERI, SCIF1_RXI, SCIF1_BRI, SCIF1_TXI),
+        INTC_GROUP(MMCIF, MMCIF_FSTAT, MMCIF_TRAN, MMCIF_ERR, MMCIF_FRDY),
+        INTC_GROUP(TMU345, TMU3, TMU4, TMU5),
+        INTC_GROUP(FLCTL, FLCTL_FLSTE, FLCTL_FLEND,
+                   FLCTL_FLTRQ0, FLCTL_FLTRQ1),
+        INTC_GROUP(GPIO, GPIOI0, GPIOI1, GPIOI2, GPIOI3),
+};
 
-        .chip = {
-                .name   = "INTC2-sh7780",
-        },
+static struct intc_prio priorities[] = {
+        INTC_PRIO(SCIF0, 3),
+        INTC_PRIO(SCIF1, 3),
+};
+
+static struct intc_mask_reg mask_registers[] = {
+        { 0xffd40038, 0xffd4003c, 32, /* INT2MSKR / INT2MSKCR */
+          { 0, 0, 0, 0, 0, 0, GPIO, FLCTL,
+            SSI, MMCIF, HSPI, SIOF, PCIC5, PCIINTD, PCIINTC, PCIINTB,
+            PCIINTA, PCISERR, HAC, CMT, 0, 0, DMAC1, DMAC0,
+            HUDI, 0, WDT, SCIF1, SCIF0, RTC, TMU345, TMU012 } },
+};
+
+static struct intc_prio_reg prio_registers[] = {
+        { 0xffd40000, 32, 8, /* INT2PRI0 */ { TMU0, TMU1, TMU2, TMU2_TICPI } },
+        { 0xffd40004, 32, 8, /* INT2PRI1 */ { TMU3, TMU4, TMU5, RTC } },
+        { 0xffd40008, 32, 8, /* INT2PRI2 */ { SCIF0, SCIF1, WDT } },
+        { 0xffd4000c, 32, 8, /* INT2PRI3 */ { HUDI, DMAC0, DMAC1 } },
+        { 0xffd40010, 32, 8, /* INT2PRI4 */ { CMT, HAC, PCISERR, PCIINTA, } },
+        { 0xffd40014, 32, 8, /* INT2PRI5 */ { PCIINTB, PCIINTC,
+                                              PCIINTD, PCIC5 } },
+        { 0xffd40018, 32, 8, /* INT2PRI6 */ { SIOF, HSPI, MMCIF, SSI } },
+        { 0xffd4001c, 32, 8, /* INT2PRI7 */ { FLCTL, GPIO } },
+};
+
+static DECLARE_INTC_DESC(intc_desc, "sh7780", vectors, groups, priorities,
+                         mask_registers, prio_registers, NULL);
+
+/* Support for external interrupt pins in IRQ mode */
+
+static struct intc_vect irq_vectors[] = {
+        INTC_VECT(IRQ0, 0x240), INTC_VECT(IRQ1, 0x280),
+        INTC_VECT(IRQ2, 0x2c0), INTC_VECT(IRQ3, 0x300),
+        INTC_VECT(IRQ4, 0x340), INTC_VECT(IRQ5, 0x380),
+        INTC_VECT(IRQ6, 0x3c0), INTC_VECT(IRQ7, 0x200),
+};
+
+static struct intc_mask_reg irq_mask_registers[] = {
+        { 0xffd00044, 0xffd00064, 32, /* INTMSK0 / INTMSKCLR0 */
+          { IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5, IRQ6, IRQ7 } },
+};
+
+static struct intc_prio_reg irq_prio_registers[] = {
+        { 0xffd00010, 32, 4, /* INTPRI */ { IRQ0, IRQ1, IRQ2, IRQ3,
+                                            IRQ4, IRQ5, IRQ6, IRQ7 } },
 };
 
-void __init init_IRQ_intc2(void)
+static struct intc_sense_reg irq_sense_registers[] = {
+        { 0xffd0001c, 32, 2, /* ICR1 */   { IRQ0, IRQ1, IRQ2, IRQ3,
+                                            IRQ4, IRQ5, IRQ6, IRQ7 } },
+};
+
+static DECLARE_INTC_DESC(intc_irq_desc, "sh7780-irq", irq_vectors,
+                         NULL, NULL, irq_mask_registers, irq_prio_registers,
+                         irq_sense_registers);
+
+/* External interrupt pins in IRL mode */
+
+static struct intc_vect irl_vectors[] = {
+        INTC_VECT(IRL_LLLL, 0x200), INTC_VECT(IRL_LLLH, 0x220),
+        INTC_VECT(IRL_LLHL, 0x240), INTC_VECT(IRL_LLHH, 0x260),
+        INTC_VECT(IRL_LHLL, 0x280), INTC_VECT(IRL_LHLH, 0x2a0),
+        INTC_VECT(IRL_LHHL, 0x2c0), INTC_VECT(IRL_LHHH, 0x2e0),
+        INTC_VECT(IRL_HLLL, 0x300), INTC_VECT(IRL_HLLH, 0x320),
+        INTC_VECT(IRL_HLHL, 0x340), INTC_VECT(IRL_HLHH, 0x360),
+        INTC_VECT(IRL_HHLL, 0x380), INTC_VECT(IRL_HHLH, 0x3a0),
+        INTC_VECT(IRL_HHHL, 0x3c0),
+};
+
+static struct intc_mask_reg irl3210_mask_registers[] = {
+        { 0xffd00080, 0xffd00084, 32, /* INTMSK2 / INTMSKCLR2 */
+          { IRL_LLLL, IRL_LLLH, IRL_LLHL, IRL_LLHH,
+            IRL_LHLL, IRL_LHLH, IRL_LHHL, IRL_LHHH,
+            IRL_HLLL, IRL_HLLH, IRL_HLHL, IRL_HLHH,
+            IRL_HHLL, IRL_HHLH, IRL_HHHL, } },
+};
+
+static struct intc_mask_reg irl7654_mask_registers[] = {
+        { 0xffd00080, 0xffd00084, 32, /* INTMSK2 / INTMSKCLR2 */
+          { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+            IRL_LLLL, IRL_LLLH, IRL_LLHL, IRL_LLHH,
+            IRL_LHLL, IRL_LHLH, IRL_LHHL, IRL_LHHH,
+            IRL_HLLL, IRL_HLLH, IRL_HLHL, IRL_HLHH,
+            IRL_HHLL, IRL_HHLH, IRL_HHHL, } },
+};
+
+static DECLARE_INTC_DESC(intc_irl7654_desc, "sh7780-irl7654", irl_vectors,
+                         NULL, NULL, irl7654_mask_registers, NULL, NULL);
+
+static DECLARE_INTC_DESC(intc_irl3210_desc, "sh7780-irl3210", irl_vectors,
+                         NULL, NULL, irl3210_mask_registers, NULL, NULL);
+
+void __init plat_irq_setup(void)
 {
-        register_intc2_controller(&intc2_irq_desc);
+        register_intc_controller(&intc_desc);
+}
+
+void __init plat_irq_setup_pins(int mode)
+{
+        switch (mode) {
+        case IRQ_MODE_IRQ:
+                register_intc_controller(&intc_irq_desc);
+                break;
+        case IRQ_MODE_IRL7654:
+                register_intc_controller(&intc_irl7654_desc);
+                break;
+        case IRQ_MODE_IRL3210:
+                register_intc_controller(&intc_irl3210_desc);
+                break;
+        default:
+                BUG();
+        }
 }
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c
index ce10ec5d6914..cf047562e43f 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c
@@ -110,7 +110,7 @@ static struct intc2_desc intc2_irq_desc __read_mostly = {
         },
 };
 
-void __init init_IRQ_intc2(void)
+void __init plat_irq_setup(void)
 {
         register_intc2_controller(&intc2_irq_desc);
 }
diff --git a/arch/sh/kernel/cpu/sh4a/setup-shx3.c b/arch/sh/kernel/cpu/sh4a/setup-shx3.c
index 70683ea12b83..704c064f70dc 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-shx3.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-shx3.c
@@ -79,7 +79,7 @@ static struct intc2_desc intc2_irq_desc __read_mostly = {
         },
 };
 
-void __init init_IRQ_intc2(void)
+void __init plat_irq_setup(void)
 {
         register_intc2_controller(&intc2_irq_desc);
 }
diff --git a/arch/sh/kernel/cpufreq.c b/arch/sh/kernel/cpufreq.c
index 47abf6e49dfb..e61890217c50 100644
--- a/arch/sh/kernel/cpufreq.c
+++ b/arch/sh/kernel/cpufreq.c
@@ -3,89 +3,46 @@
  *
  * cpufreq driver for the SuperH processors.
  *
- * Copyright (C) 2002, 2003, 2004, 2005 Paul Mundt
+ * Copyright (C) 2002 - 2007 Paul Mundt
  * Copyright (C) 2002 M. R. Brown
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
+ * Clock framework bits from arch/avr32/mach-at32ap/cpufreq.c
+ *
+ *   Copyright (C) 2004-2007 Atmel Corporation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
  */
 #include <linux/types.h>
 #include <linux/cpufreq.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/slab.h>
 #include <linux/init.h>
-#include <linux/delay.h>
+#include <linux/err.h>
 #include <linux/cpumask.h>
 #include <linux/smp.h>
 #include <linux/sched.h>        /* set_cpus_allowed() */
+#include <linux/clk.h>
 
-#include <asm/processor.h>
-#include <asm/watchdog.h>
-#include <asm/freq.h>
-#include <asm/io.h>
-
-/*
- * For SuperH, each policy change requires that we change the IFC, BFC, and
- * PFC at the same time.  Here we define sane values that won't trash the
- * system.
- *
- * Note the max set is computed at runtime, we use the divisors that we booted
- * with to setup our maximum operating frequencies.
- */
-struct clock_set {
-        unsigned int ifc;
-        unsigned int bfc;
-        unsigned int pfc;
-} clock_sets[] = {
-#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH2)
-        { 0, 0, 0 },    /* not implemented yet */
-#elif defined(CONFIG_CPU_SH4)
-        { 4, 8, 8 },    /* min - IFC: 1/4, BFC: 1/8, PFC: 1/8 */
-        { 1, 2, 2 },    /* max - IFC: 1, BFC: 1/2, PFC: 1/2 */
-#endif
-};
-
-#define MIN_CLOCK_SET   0
-#define MAX_CLOCK_SET   (ARRAY_SIZE(clock_sets) - 1)
-
-/*
- * For the time being, we only support two frequencies, which in turn are
- * aimed at the POWERSAVE and PERFORMANCE policies, which in turn are derived
- * directly from the respective min/max clock sets. Technically we could
- * support a wider range of frequencies, but these vary far too much for each
- * CPU subtype (and we'd have to construct a frequency table for each subtype).
- *
- * Maybe something to implement in the future..
- */
-#define SH_FREQ_MAX     0
-#define SH_FREQ_MIN     1
-
-static struct cpufreq_frequency_table sh_freqs[] = {
-        { SH_FREQ_MAX,  0 },
-        { SH_FREQ_MIN,  0 },
-        { 0,            CPUFREQ_TABLE_END },
-};
+static struct clk *cpuclk;
 
-static void sh_cpufreq_update_clocks(unsigned int set)
+static unsigned int sh_cpufreq_get(unsigned int cpu)
 {
-        current_cpu_data.cpu_clock = current_cpu_data.master_clock / clock_sets[set].ifc;
-        current_cpu_data.bus_clock = current_cpu_data.master_clock / clock_sets[set].bfc;
-        current_cpu_data.module_clock = current_cpu_data.master_clock / clock_sets[set].pfc;
-        current_cpu_data.loops_per_jiffy = loops_per_jiffy;
+        return (clk_get_rate(cpuclk) + 500) / 1000;
 }
 
-/* XXX: This needs to be split out per CPU and CPU subtype. */
 /*
  * Here we notify other drivers of the proposed change and the final change.
  */
-static int sh_cpufreq_setstate(unsigned int cpu, unsigned int set)
+static int sh_cpufreq_target(struct cpufreq_policy *policy,
+                             unsigned int target_freq,
+                             unsigned int relation)
 {
-        unsigned short frqcr = ctrl_inw(FRQCR);
+        unsigned int cpu = policy->cpu;
         cpumask_t cpus_allowed;
         struct cpufreq_freqs freqs;
+        long freq;
 
         if (!cpu_online(cpu))
                 return -ENODEV;
@@ -95,125 +52,109 @@ static int sh_cpufreq_setstate(unsigned int cpu, unsigned int set)
 
         BUG_ON(smp_processor_id() != cpu);
 
-        freqs.cpu = cpu;
-        freqs.old = current_cpu_data.cpu_clock / 1000;
-        freqs.new = (current_cpu_data.master_clock / clock_sets[set].ifc) / 1000;
+        /* Convert target_freq from kHz to Hz */
+        freq = clk_round_rate(cpuclk, target_freq * 1000);
 
-        cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
-#if defined(CONFIG_CPU_SH3)
-        frqcr |= (newstate & 0x4000) << 14;
-        frqcr |= (newstate & 0x000c) <<  2;
-#elif defined(CONFIG_CPU_SH4)
-        /*
-         * FRQCR.PLL2EN is 1, we need to allow the PLL to stabilize by
-         * initializing the WDT.
-         */
-        if (frqcr & (1 << 9)) {
-                __u8 csr;
-
-                /*
-                 * Set the overflow period to the highest available,
-                 * in this case a 1/4096 division ratio yields a 5.25ms
-                 * overflow period. See asm-sh/watchdog.h for more
-                 * information and a range of other divisors.
-                 */
-                csr = sh_wdt_read_csr();
-                csr |= WTCSR_CKS_4096;
-                sh_wdt_write_csr(csr);
-
-                sh_wdt_write_cnt(0);
-        }
-        frqcr &= 0x0e00;        /* Clear ifc, bfc, pfc */
-        frqcr |= get_ifc_value(clock_sets[set].ifc) << 6;
-        frqcr |= get_bfc_value(clock_sets[set].bfc) << 3;
-        frqcr |= get_pfc_value(clock_sets[set].pfc);
-#endif
-        ctrl_outw(frqcr, FRQCR);
-        sh_cpufreq_update_clocks(set);
+        if (freq < (policy->min * 1000) || freq > (policy->max * 1000))
+                return -EINVAL;
+
+        pr_debug("cpufreq: requested frequency %u Hz\n", target_freq * 1000);
 
+        freqs.cpu       = cpu;
+        freqs.old       = sh_cpufreq_get(cpu);
+        freqs.new       = (freq + 500) / 1000;
+        freqs.flags     = 0;
+
+        cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
         set_cpus_allowed(current, cpus_allowed);
+        clk_set_rate(cpuclk, freq);
         cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 
+        pr_debug("cpufreq: set frequency %lu Hz\n", freq);
+
         return 0;
 }
 
 static int sh_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-        unsigned int min_freq, max_freq;
-        unsigned int ifc, bfc, pfc;
+        printk(KERN_INFO "cpufreq: SuperH CPU frequency driver.\n");
 
         if (!cpu_online(policy->cpu))
                 return -ENODEV;
 
-        /* Update our maximum clock set */
-        get_current_frequency_divisors(&ifc, &bfc, &pfc);
-        clock_sets[MAX_CLOCK_SET].ifc = ifc;
-        clock_sets[MAX_CLOCK_SET].bfc = bfc;
-        clock_sets[MAX_CLOCK_SET].pfc = pfc;
-
-        /* Convert from Hz to kHz */
-        max_freq = current_cpu_data.cpu_clock / 1000;
-        min_freq = (current_cpu_data.master_clock / clock_sets[MIN_CLOCK_SET].ifc) / 1000;
-        
-        sh_freqs[SH_FREQ_MAX].frequency = max_freq;
-        sh_freqs[SH_FREQ_MIN].frequency = min_freq;
+        cpuclk = clk_get(NULL, "cpu_clk");
+        if (IS_ERR(cpuclk)) {
+                printk(KERN_ERR "cpufreq: couldn't get CPU clk\n");
+                return PTR_ERR(cpuclk);
+        }
 
         /* cpuinfo and default policy values */
-        policy->governor                   = CPUFREQ_DEFAULT_GOVERNOR;
+        policy->cpuinfo.min_freq = (clk_round_rate(cpuclk, 1) + 500) / 1000;
+        policy->cpuinfo.max_freq = (clk_round_rate(cpuclk, ~0UL) + 500) / 1000;
         policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
-        policy->cur                        = max_freq;
 
-        return cpufreq_frequency_table_cpuinfo(policy, &sh_freqs[0]);
-}
+        policy->governor        = CPUFREQ_DEFAULT_GOVERNOR;
+        policy->cur             = sh_cpufreq_get(policy->cpu);
+        policy->min             = policy->cpuinfo.min_freq;
+        policy->max             = policy->cpuinfo.max_freq;
 
-static int sh_cpufreq_verify(struct cpufreq_policy *policy)
-{
-        return cpufreq_frequency_table_verify(policy, &sh_freqs[0]);
-}
 
-static int sh_cpufreq_target(struct cpufreq_policy *policy,
-                             unsigned int target_freq,
-                             unsigned int relation)
-{
-        unsigned int set, idx = 0;
+        /*
+         * Catch the cases where the clock framework hasn't been wired up
+         * properly to support scaling.
+         */
+        if (unlikely(policy->min == policy->max)) {
+                printk(KERN_ERR "cpufreq: clock framework rate rounding "
+                       "not supported on this CPU.\n");
 
-        if (cpufreq_frequency_table_target(policy, &sh_freqs[0], target_freq, relation, &idx))
+                clk_put(cpuclk);
                 return -EINVAL;
+        }
 
-        set = (idx == SH_FREQ_MIN) ? MIN_CLOCK_SET : MAX_CLOCK_SET;
+        printk(KERN_INFO "cpufreq: Frequencies - Minimum %u.%03u MHz, "
+               "Maximum %u.%03u MHz.\n",
+               policy->min / 1000, policy->min % 1000,
+               policy->max / 1000, policy->max % 1000);
 
-        sh_cpufreq_setstate(policy->cpu, set);
+        return 0;
+}
 
+static int sh_cpufreq_verify(struct cpufreq_policy *policy)
+{
+        cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
+                                     policy->cpuinfo.max_freq);
+        return 0;
+}
+
+static int sh_cpufreq_exit(struct cpufreq_policy *policy)
+{
+        clk_put(cpuclk);
         return 0;
 }
 
 static struct cpufreq_driver sh_cpufreq_driver = {
         .owner          = THIS_MODULE,
-        .name           = "SH cpufreq",
+        .name           = "sh",
         .init           = sh_cpufreq_cpu_init,
         .verify         = sh_cpufreq_verify,
         .target         = sh_cpufreq_target,
+        .get            = sh_cpufreq_get,
+        .exit           = sh_cpufreq_exit,
 };
 
-static int __init sh_cpufreq_init(void)
+static int __init sh_cpufreq_module_init(void)
 {
-        if (!current_cpu_data.cpu_clock)
-                return -EINVAL;
-        if (cpufreq_register_driver(&sh_cpufreq_driver))
-                return -EINVAL;
-
-        return 0;
+        return cpufreq_register_driver(&sh_cpufreq_driver);
 }
 
-static void __exit sh_cpufreq_exit(void)
+static void __exit sh_cpufreq_module_exit(void)
 {
         cpufreq_unregister_driver(&sh_cpufreq_driver);
 }
 
-module_init(sh_cpufreq_init);
-module_exit(sh_cpufreq_exit);
+module_init(sh_cpufreq_module_init);
+module_exit(sh_cpufreq_module_exit);
 
 MODULE_AUTHOR("Paul Mundt <lethal@linux-sh.org>");
 MODULE_DESCRIPTION("cpufreq driver for SuperH");
 MODULE_LICENSE("GPL");
-
diff --git a/arch/sh/kernel/head.S b/arch/sh/kernel/head.S
index 71a3ad7d283e..0bccc0ca5a0f 100644
--- a/arch/sh/kernel/head.S
+++ b/arch/sh/kernel/head.S
@@ -36,7 +36,8 @@ ENTRY(empty_zero_page)
 1:
         .skip   PAGE_SIZE - empty_zero_page - 1b
 
-        .text   
+        .section        .text.head, "ax"
+
 /*
  * Condition at the entry of _stext:
  *
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 27897798867a..03404987528d 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -253,14 +253,7 @@ void __init init_IRQ(void)
 #ifdef CONFIG_CPU_HAS_PINT_IRQ
         init_IRQ_pint();
 #endif
-
-#ifdef CONFIG_CPU_HAS_INTC2_IRQ
-        init_IRQ_intc2();
-#endif
-
-#ifdef CONFIG_CPU_HAS_IPR_IRQ
-        init_IRQ_ipr();
-#endif
+        plat_irq_setup();
 
         /* Perform the machine specific initialisation */
         if (sh_mv.mv_init_irq)
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index de8e6e2f2c87..c14a3e95d0b1 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -21,6 +21,7 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/kexec.h>
+#include <linux/module.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/page.h>
@@ -78,7 +79,11 @@ static char __initdata command_line[COMMAND_LINE_SIZE] = { 0, };
 static struct resource code_resource = { .name = "Kernel code", };
 static struct resource data_resource = { .name = "Kernel data", };
 
-unsigned long memory_start, memory_end;
+unsigned long memory_start;
+EXPORT_SYMBOL(memory_start);
+
+unsigned long memory_end;
+EXPORT_SYMBOL(memory_end);
 
 static int __init early_parse_mem(char *p)
 {
diff --git a/arch/sh/kernel/sh_bios.c b/arch/sh/kernel/sh_bios.c
index 5b53e10bb9cd..d1bcac4fa269 100644
--- a/arch/sh/kernel/sh_bios.c
+++ b/arch/sh/kernel/sh_bios.c
@@ -5,7 +5,7 @@
  *  Copyright (C) 2000 Greg Banks, Mitch Davis
  *
  */
-
+#include <linux/module.h>
 #include <asm/sh_bios.h>
 
 #define BIOS_CALL_CONSOLE_WRITE         0
@@ -63,6 +63,7 @@ void sh_bios_gdb_detach(void)
 {
     sh_bios_call(BIOS_CALL_GDB_DETACH, 0, 0, 0, 0);
 }
+EXPORT_SYMBOL(sh_bios_gdb_detach);
 
 void sh_bios_get_node_addr (unsigned char *node_addr)
 {
diff --git a/arch/sh/kernel/sh_ksyms.c b/arch/sh/kernel/sh_ksyms.c
index c968dcf09eee..37aef0a85197 100644
--- a/arch/sh/kernel/sh_ksyms.c
+++ b/arch/sh/kernel/sh_ksyms.c
@@ -63,10 +63,43 @@ EXPORT_SYMBOL(__const_udelay);
 /* These symbols are generated by the compiler itself */
 DECLARE_EXPORT(__udivsi3);
 DECLARE_EXPORT(__sdivsi3);
+DECLARE_EXPORT(__ashrsi3);
+DECLARE_EXPORT(__ashlsi3);
 DECLARE_EXPORT(__ashrdi3);
 DECLARE_EXPORT(__ashldi3);
+DECLARE_EXPORT(__ashiftrt_r4_6);
+DECLARE_EXPORT(__ashiftrt_r4_7);
+DECLARE_EXPORT(__ashiftrt_r4_8);
+DECLARE_EXPORT(__ashiftrt_r4_9);
+DECLARE_EXPORT(__ashiftrt_r4_10);
+DECLARE_EXPORT(__ashiftrt_r4_11);
+DECLARE_EXPORT(__ashiftrt_r4_12);
+DECLARE_EXPORT(__ashiftrt_r4_13);
+DECLARE_EXPORT(__ashiftrt_r4_14);
+DECLARE_EXPORT(__ashiftrt_r4_15);
+DECLARE_EXPORT(__ashiftrt_r4_20);
+DECLARE_EXPORT(__ashiftrt_r4_21);
+DECLARE_EXPORT(__ashiftrt_r4_22);
+DECLARE_EXPORT(__ashiftrt_r4_23);
+DECLARE_EXPORT(__ashiftrt_r4_24);
+DECLARE_EXPORT(__ashiftrt_r4_27);
+DECLARE_EXPORT(__ashiftrt_r4_30);
+DECLARE_EXPORT(__lshrsi3);
 DECLARE_EXPORT(__lshrdi3);
+DECLARE_EXPORT(__movstrSI8);
+DECLARE_EXPORT(__movstrSI12);
 DECLARE_EXPORT(__movstrSI16);
+DECLARE_EXPORT(__movstrSI20);
+DECLARE_EXPORT(__movstrSI24);
+DECLARE_EXPORT(__movstrSI28);
+DECLARE_EXPORT(__movstrSI32);
+DECLARE_EXPORT(__movstrSI36);
+DECLARE_EXPORT(__movstrSI40);
+DECLARE_EXPORT(__movstrSI44);
+DECLARE_EXPORT(__movstrSI48);
+DECLARE_EXPORT(__movstrSI52);
+DECLARE_EXPORT(__movstrSI56);
+DECLARE_EXPORT(__movstrSI60);
 #if __GNUC__ == 4
 DECLARE_EXPORT(__movmem);
 #else
@@ -115,7 +148,9 @@ EXPORT_SYMBOL(synchronize_irq);
 #endif
 
 EXPORT_SYMBOL(csum_partial);
+EXPORT_SYMBOL(csum_partial_copy_generic);
 #ifdef CONFIG_IPV6
 EXPORT_SYMBOL(csum_ipv6_magic);
 #endif
 EXPORT_SYMBOL(clear_page);
+EXPORT_SYMBOL(__clear_user);
diff --git a/arch/sh/kernel/syscalls.S b/arch/sh/kernel/syscalls.S
index ff5656e60c05..91fb7024e06f 100644
--- a/arch/sh/kernel/syscalls.S
+++ b/arch/sh/kernel/syscalls.S
@@ -358,3 +358,4 @@ ENTRY(sys_call_table)
         .long sys_signalfd
         .long sys_timerfd
         .long sys_eventfd
+        .long sys_fallocate
diff --git a/arch/sh/kernel/timers/timer-tmu.c b/arch/sh/kernel/timers/timer-tmu.c
index 097ebd49f1bf..7aca37d79766 100644
--- a/arch/sh/kernel/timers/timer-tmu.c
+++ b/arch/sh/kernel/timers/timer-tmu.c
@@ -80,6 +80,7 @@ static void tmu_set_mode(enum clock_event_mode mode,
                 break;
         case CLOCK_EVT_MODE_UNUSED:
         case CLOCK_EVT_MODE_SHUTDOWN:
+        case CLOCK_EVT_MODE_RESUME:
                 break;
         }
 }
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index 5ba216180b30..9cb95af7b090 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -22,6 +22,7 @@ SECTIONS
         *(.empty_zero_page)
         } = 0
   .text : {
+        *(.text.head)
         TEXT_TEXT
         SCHED_TEXT
         LOCK_TEXT
diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig
index 28d79a474cde..70da1c8d407e 100644
--- a/arch/sh/mm/Kconfig
+++ b/arch/sh/mm/Kconfig
@@ -120,14 +120,14 @@ config CPU_SUBTYPE_SH7712
 config CPU_SUBTYPE_SH7750
         bool "Support SH7750 processor"
         select CPU_SH4
-        select CPU_HAS_IPR_IRQ
+        select CPU_HAS_INTC_IRQ
         help
           Select SH7750 if you have a 200 Mhz SH-4 HD6417750 CPU.
 
 config CPU_SUBTYPE_SH7091
         bool "Support SH7091 processor"
         select CPU_SH4
-        select CPU_HAS_IPR_IRQ
+        select CPU_HAS_INTC_IRQ
         help
           Select SH7091 if you have an SH-4 based Sega device (such as
           the Dreamcast, Naomi, and Naomi 2).
@@ -135,17 +135,17 @@ config CPU_SUBTYPE_SH7091
 config CPU_SUBTYPE_SH7750R
         bool "Support SH7750R processor"
         select CPU_SH4
-        select CPU_HAS_IPR_IRQ
+        select CPU_HAS_INTC_IRQ
 
 config CPU_SUBTYPE_SH7750S
         bool "Support SH7750S processor"
         select CPU_SH4
-        select CPU_HAS_IPR_IRQ
+        select CPU_HAS_INTC_IRQ
 
 config CPU_SUBTYPE_SH7751
         bool "Support SH7751 processor"
         select CPU_SH4
-        select CPU_HAS_IPR_IRQ
+        select CPU_HAS_INTC_IRQ
         help
           Select SH7751 if you have a 166 Mhz SH-4 HD6417751 CPU,
           or if you have a HD6417751R CPU.
@@ -153,7 +153,7 @@ config CPU_SUBTYPE_SH7751
 config CPU_SUBTYPE_SH7751R
         bool "Support SH7751R processor"
         select CPU_SH4
-        select CPU_HAS_IPR_IRQ
+        select CPU_HAS_INTC_IRQ
 
 config CPU_SUBTYPE_SH7760
         bool "Support SH7760 processor"
@@ -189,7 +189,7 @@ config CPU_SUBTYPE_SH7770
 config CPU_SUBTYPE_SH7780
         bool "Support SH7780 processor"
         select CPU_SH4A
-        select CPU_HAS_INTC2_IRQ
+        select CPU_HAS_INTC_IRQ
 
 config CPU_SUBTYPE_SH7785
         bool "Support SH7785 processor"
@@ -217,7 +217,7 @@ config CPU_SUBTYPE_SH7722
         bool "Support SH7722 processor"
         select CPU_SH4AL_DSP
         select CPU_SHX2
-        select CPU_HAS_IPR_IRQ
+        select CPU_HAS_INTC_IRQ
         select ARCH_SPARSEMEM_ENABLE
         select SYS_SUPPORTS_NUMA
 
diff --git a/arch/sh64/configs/cayman_defconfig b/arch/sh64/configs/cayman_defconfig
index ed035084b053..784434143343 100644
--- a/arch/sh64/configs/cayman_defconfig
+++ b/arch/sh64/configs/cayman_defconfig
@@ -1,11 +1,12 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.22-rc1
-# Mon May 14 08:43:31 2007
+# Linux kernel version: 2.6.22
+# Fri Jul 20 12:28:34 2007
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH64=y
 CONFIG_MMU=y
+CONFIG_QUICKLIST=y
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_HWEIGHT=y
@@ -32,7 +33,7 @@ CONFIG_SWAP=y
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
-# CONFIG_UTS_NS is not set
+# CONFIG_USER_NS is not set
 # CONFIG_AUDIT is not set
 # CONFIG_IKCONFIG is not set
 CONFIG_LOG_BUF_SHIFT=14
@@ -66,19 +67,12 @@ CONFIG_SLAB=y
 CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
-
-#
-# Loadable module support
-#
 # CONFIG_MODULES is not set
-
-#
-# Block layer
-#
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
 # CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_LSF is not set
+# CONFIG_BLK_DEV_BSG is not set
 
 #
 # IO Schedulers
@@ -156,6 +150,8 @@ CONFIG_FLAT_NODE_MEM_MAP=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
 # CONFIG_RESOURCES_64BIT is not set
 CONFIG_ZONE_DMA_FLAG=0
+CONFIG_NR_QUICK=1
+CONFIG_VIRT_TO_BUS=y
 
 #
 # Bus options (PCI, PCMCIA, EISA, MCA, ISA)
@@ -175,7 +171,6 @@ CONFIG_SH_PCIDMA_NONCOHERENT=y
 # Executable file formats
 #
 CONFIG_BINFMT_ELF=y
-# CONFIG_BINFMT_FLAT is not set
 # CONFIG_BINFMT_MISC is not set
 
 #
@@ -225,20 +220,8 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 # CONFIG_INET6_TUNNEL is not set
 # CONFIG_NETWORK_SECMARK is not set
 # CONFIG_NETFILTER is not set
-
-#
-# DCCP Configuration (EXPERIMENTAL)
-#
 # CONFIG_IP_DCCP is not set
-
-#
-# SCTP Configuration (EXPERIMENTAL)
-#
 # CONFIG_IP_SCTP is not set
-
-#
-# TIPC Configuration (EXPERIMENTAL)
-#
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
 # CONFIG_BRIDGE is not set
@@ -274,6 +257,7 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 # CONFIG_MAC80211 is not set
 # CONFIG_IEEE80211 is not set
 # CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
 
 #
 # Device Drivers
@@ -288,26 +272,10 @@ CONFIG_PREVENT_FIRMWARE_BUILD=y
 # CONFIG_DEBUG_DRIVER is not set
 # CONFIG_DEBUG_DEVRES is not set
 # CONFIG_SYS_HYPERVISOR is not set
-
-#
-# Connector - unified userspace <-> kernelspace linker
-#
 # CONFIG_CONNECTOR is not set
 # CONFIG_MTD is not set
-
-#
-# Parallel port support
-#
 # CONFIG_PARPORT is not set
-
-#
-# Plug and Play support
-#
-# CONFIG_PNPACPI is not set
-
-#
-# Block devices
-#
+CONFIG_BLK_DEV=y
 # CONFIG_BLK_CPQ_DA is not set
 # CONFIG_BLK_CPQ_CISS_DA is not set
 # CONFIG_BLK_DEV_DAC960 is not set
@@ -323,18 +291,11 @@ CONFIG_BLK_DEV_RAM_SIZE=4096
 CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
 # CONFIG_CDROM_PKTCDVD is not set
 # CONFIG_ATA_OVER_ETH is not set
-
-#
-# Misc devices
-#
+CONFIG_MISC_DEVICES=y
 # CONFIG_PHANTOM is not set
+# CONFIG_EEPROM_93CX6 is not set
 # CONFIG_SGI_IOC4 is not set
 # CONFIG_TIFM_CORE is not set
-# CONFIG_BLINK is not set
-
-#
-# ATA/ATAPI/MFM/RLL support
-#
 # CONFIG_IDE is not set
 
 #
@@ -342,6 +303,7 @@ CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
 #
 # CONFIG_RAID_ATTRS is not set
 CONFIG_SCSI=y
+CONFIG_SCSI_DMA=y
 # CONFIG_SCSI_TGT is not set
 # CONFIG_SCSI_NETLINK is not set
 CONFIG_SCSI_PROC_FS=y
@@ -410,13 +372,8 @@ CONFIG_SCSI_SYM53C8XX_MMIO=y
 # CONFIG_SCSI_DC390T is not set
 # CONFIG_SCSI_NSP32 is not set
 # CONFIG_SCSI_DEBUG is not set
-# CONFIG_SCSI_ESP_CORE is not set
 # CONFIG_SCSI_SRP is not set
 # CONFIG_ATA is not set
-
-#
-# Multi-device support (RAID and LVM)
-#
 # CONFIG_MD is not set
 
 #
@@ -432,30 +389,16 @@ CONFIG_SCSI_SYM53C8XX_MMIO=y
 #
 # CONFIG_FIREWIRE is not set
 # CONFIG_IEEE1394 is not set
-
-#
-# I2O device support
-#
 # CONFIG_I2O is not set
-
-#
-# Network device support
-#
 CONFIG_NETDEVICES=y
+# CONFIG_NETDEVICES_MULTIQUEUE is not set
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
+# CONFIG_MACVLAN is not set
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
-
-#
-# ARCnet devices
-#
 # CONFIG_ARCNET is not set
 # CONFIG_PHYLIB is not set
-
-#
-# Ethernet (10 or 100Mbit)
-#
 CONFIG_NET_ETHERNET=y
 # CONFIG_MII is not set
 # CONFIG_STNIC is not set
@@ -464,10 +407,6 @@ CONFIG_NET_ETHERNET=y
 # CONFIG_CASSINI is not set
 # CONFIG_NET_VENDOR_3COM is not set
 # CONFIG_SMC91X is not set
-
-#
-# Tulip family network device support
-#
 CONFIG_NET_TULIP=y
 # CONFIG_DE2104X is not set
 CONFIG_TULIP=y
@@ -510,7 +449,6 @@ CONFIG_NETDEV_1000=y
 # CONFIG_SIS190 is not set
 # CONFIG_SKGE is not set
 # CONFIG_SKY2 is not set
-# CONFIG_SK98LIN is not set
 # CONFIG_VIA_VELOCITY is not set
 # CONFIG_TIGON3 is not set
 # CONFIG_BNX2 is not set
@@ -524,11 +462,6 @@ CONFIG_NETDEV_10000=y
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_MLX4_CORE is not set
-CONFIG_MLX4_DEBUG=y
-
-#
-# Token Ring devices
-#
 # CONFIG_TR is not set
 
 #
@@ -546,15 +479,7 @@ CONFIG_MLX4_DEBUG=y
 # CONFIG_NETCONSOLE is not set
 # CONFIG_NETPOLL is not set
 # CONFIG_NET_POLL_CONTROLLER is not set
-
-#
-# ISDN subsystem
-#
 # CONFIG_ISDN is not set
-
-#
-# Telephony Support
-#
 # CONFIG_PHONE is not set
 
 #
@@ -562,6 +487,7 @@ CONFIG_MLX4_DEBUG=y
 #
 CONFIG_INPUT=y
 # CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
 
 #
 # Userland interfaces
@@ -638,10 +564,6 @@ CONFIG_SERIAL_CORE_CONSOLE=y
 CONFIG_UNIX98_PTYS=y
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=256
-
-#
-# IPMI
-#
 # CONFIG_IPMI_HANDLER is not set
 CONFIG_WATCHDOG=y
 # CONFIG_WATCHDOG_NOWAYOUT is not set
@@ -658,15 +580,10 @@ CONFIG_WATCHDOG=y
 # CONFIG_PCIPCWATCHDOG is not set
 # CONFIG_WDTPCI is not set
 CONFIG_HW_RANDOM=y
-# CONFIG_GEN_RTC is not set
 # CONFIG_R3964 is not set
 # CONFIG_APPLICOM is not set
 # CONFIG_DRM is not set
 # CONFIG_RAW_DRIVER is not set
-
-#
-# TPM devices
-#
 # CONFIG_TCG_TPM is not set
 CONFIG_DEVPORT=y
 # CONFIG_I2C is not set
@@ -676,20 +593,24 @@ CONFIG_DEVPORT=y
 #
 # CONFIG_SPI is not set
 # CONFIG_SPI_MASTER is not set
-
-#
-# Dallas's 1-wire bus
-#
 # CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
 CONFIG_HWMON=y
 # CONFIG_HWMON_VID is not set
 # CONFIG_SENSORS_ABITUGURU is not set
+# CONFIG_SENSORS_ABITUGURU3 is not set
 # CONFIG_SENSORS_F71805F is not set
+# CONFIG_SENSORS_IT87 is not set
+# CONFIG_SENSORS_PC87360 is not set
 # CONFIG_SENSORS_PC87427 is not set
+# CONFIG_SENSORS_SIS5595 is not set
 # CONFIG_SENSORS_SMSC47M1 is not set
 # CONFIG_SENSORS_SMSC47B397 is not set
+# CONFIG_SENSORS_VIA686A is not set
 # CONFIG_SENSORS_VT1211 is not set
+# CONFIG_SENSORS_VT8231 is not set
 # CONFIG_SENSORS_W83627HF is not set
+# CONFIG_SENSORS_W83627EHF is not set
 # CONFIG_HWMON_DEBUG_CHIP is not set
 
 #
@@ -739,7 +660,6 @@ CONFIG_FB_MODE_HELPERS=y
 # CONFIG_FB_CYBER2000 is not set
 # CONFIG_FB_ASILIANT is not set
 # CONFIG_FB_IMSTT is not set
-# CONFIG_FB_EPSON1355 is not set
 # CONFIG_FB_S1D13XXX is not set
 # CONFIG_FB_NVIDIA is not set
 # CONFIG_FB_RIVA is not set
@@ -765,6 +685,7 @@ CONFIG_FB_KYRO=y
 #
 CONFIG_DUMMY_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
+# CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY is not set
 # CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
 CONFIG_FONTS=y
 # CONFIG_FONT_8x8 is not set
@@ -789,16 +710,10 @@ CONFIG_LOGO_SUPERH_CLUT224=y
 # Sound
 #
 # CONFIG_SOUND is not set
-
-#
-# HID Devices
-#
+CONFIG_HID_SUPPORT=y
 CONFIG_HID=y
 # CONFIG_HID_DEBUG is not set
-
-#
-# USB support
-#
+CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
 CONFIG_USB_ARCH_HAS_EHCI=y
@@ -826,17 +741,9 @@ CONFIG_USB_ARCH_HAS_EHCI=y
 #
 # LED Triggers
 #
-
-#
-# InfiniBand support
-#
 # CONFIG_INFINIBAND is not set
 
 #
-# EDAC - error detection and reporting (RAS) (EXPERIMENTAL)
-#
-
-#
 # Real Time Clock
 #
 # CONFIG_RTC_CLASS is not set
@@ -855,6 +762,11 @@ CONFIG_USB_ARCH_HAS_EHCI=y
 #
 
 #
+# Userspace I/O
+#
+# CONFIG_UIO is not set
+
+#
 # File systems
 #
 CONFIG_EXT2_FS=y
@@ -950,7 +862,6 @@ CONFIG_SUNRPC=y
 # CONFIG_NCP_FS is not set
 # CONFIG_CODA_FS is not set
 # CONFIG_AFS_FS is not set
-# CONFIG_9P_FS is not set
 
 #
 # Partition Types
@@ -1001,6 +912,7 @@ CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
 CONFIG_DETECT_SOFTLOCKUP=y
+CONFIG_SCHED_DEBUG=y
 CONFIG_SCHEDSTATS=y
 # CONFIG_TIMER_STATS is not set
 # CONFIG_DEBUG_SLAB is not set
@@ -1017,7 +929,6 @@ CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_DEBUG_LIST is not set
 CONFIG_FRAME_POINTER=y
 CONFIG_FORCED_INLINING=y
-# CONFIG_RCU_TORTURE_TEST is not set
 # CONFIG_FAULT_INJECTION is not set
 # CONFIG_EARLY_PRINTK is not set
 # CONFIG_DEBUG_KERNEL_WITH_GDB_STUB is not set
@@ -1033,10 +944,6 @@ CONFIG_SH64_SR_WATCH=y
 #
 # CONFIG_KEYS is not set
 # CONFIG_SECURITY is not set
-
-#
-# Cryptographic options
-#
 # CONFIG_CRYPTO is not set
 
 #
@@ -1047,6 +954,7 @@ CONFIG_BITREVERSE=y
 # CONFIG_CRC16 is not set
 # CONFIG_CRC_ITU_T is not set
 CONFIG_CRC32=y
+# CONFIG_CRC7 is not set
 # CONFIG_LIBCRC32C is not set
 CONFIG_PLIST=y
 CONFIG_HAS_IOMEM=y
diff --git a/arch/sh64/kernel/head.S b/arch/sh64/kernel/head.S
index f3740ddbc471..186406d3ad9c 100644
--- a/arch/sh64/kernel/head.S
+++ b/arch/sh64/kernel/head.S
@@ -124,7 +124,7 @@ empty_bad_pte_table:
 fpu_in_use:     .quad   0
 
 
-        .section        .text, "ax"
+        .section        .text.head, "ax"
         .balign L1_CACHE_BYTES
 /*
  * Condition at the entry of __stext:
diff --git a/arch/sh64/kernel/pci_sh5.c b/arch/sh64/kernel/pci_sh5.c
index 3334f99b5835..388bb711f1b0 100644
--- a/arch/sh64/kernel/pci_sh5.c
+++ b/arch/sh64/kernel/pci_sh5.c
@@ -48,7 +48,7 @@ static void __init pci_fixup_ide_bases(struct pci_dev *d)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_ide_bases);
 
-char * __init pcibios_setup(char *str)
+char * __devinit pcibios_setup(char *str)
 {
         return str;
 }
@@ -497,7 +497,7 @@ static int __init pcibios_init(void)
 
 subsys_initcall(pcibios_init);
 
-void __init pcibios_fixup_bus(struct pci_bus *bus)
+void __devinit pcibios_fixup_bus(struct pci_bus *bus)
 {
         struct pci_dev *dev = bus->self;
         int i;
diff --git a/arch/sh64/kernel/syscalls.S b/arch/sh64/kernel/syscalls.S
index a5c680d29384..abb94c05d07a 100644
--- a/arch/sh64/kernel/syscalls.S
+++ b/arch/sh64/kernel/syscalls.S
@@ -378,3 +378,4 @@ sys_call_table:
         .long sys_signalfd
         .long sys_timerfd               /* 350 */
         .long sys_eventfd
+        .long sys_fallocate
diff --git a/arch/sh64/kernel/vmlinux.lds.S b/arch/sh64/kernel/vmlinux.lds.S
index 8ac9c7c5f848..267b4f9af2e1 100644
--- a/arch/sh64/kernel/vmlinux.lds.S
+++ b/arch/sh64/kernel/vmlinux.lds.S
@@ -54,6 +54,7 @@ SECTIONS
         } = 0
 
   .text : C_PHYS(.text) {
+        *(.text.head)
         TEXT_TEXT
         *(.text64)
         *(.text..SHmedia32)
diff --git a/arch/sh64/mm/ioremap.c b/arch/sh64/mm/ioremap.c
index ff26c02511aa..990857756d44 100644
--- a/arch/sh64/mm/ioremap.c
+++ b/arch/sh64/mm/ioremap.c
@@ -242,7 +242,7 @@ static void shmedia_free_io(struct resource *res)
         release_resource(res);
 }
 
-static void *sh64_get_page(void)
+static __init_refok void *sh64_get_page(void)
 {
         extern int after_bootmem;
         void *page;
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 603d83ad65c8..9d327ec59759 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -24,6 +24,9 @@ config GENERIC_ISA_DMA
 config ARCH_NO_VIRT_TO_BUS
         def_bool y
 
+config OF
+        def_bool y
+
 source "init/Kconfig"
 
 menu "General machine setup"
diff --git a/arch/sparc/kernel/ebus.c b/arch/sparc/kernel/ebus.c
index 7bb86b9cdaa3..ac352eb6dff3 100644
--- a/arch/sparc/kernel/ebus.c
+++ b/arch/sparc/kernel/ebus.c
@@ -148,6 +148,7 @@ void __init fill_ebus_device(struct device_node *dp, struct linux_ebus_device *d
 {
         const struct linux_prom_registers *regs;
         struct linux_ebus_child *child;
+        struct dev_archdata *sd;
         const int *irqs;
         int i, n, len;
         unsigned long baseaddr;
@@ -234,6 +235,10 @@ void __init fill_ebus_device(struct device_node *dp, struct linux_ebus_device *d
                 }
         }
 
+        sd = &dev->ofdev.dev.archdata;
+        sd->prom_node = dp;
+        sd->op = &dev->ofdev;
+
         dev->ofdev.node = dp;
         dev->ofdev.dev.parent = &dev->bus->ofdev.dev;
         dev->ofdev.dev.bus = &ebus_bus_type;
diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index 831f540251f8..eac38388f5fd 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -1749,8 +1749,8 @@ fpload:
 __ndelay:
         save    %sp, -STACKFRAME_SZ, %sp
         mov     %i0, %o0
-        call    .umul
-         mov    0x1ad, %o1              ! 2**32 / (1 000 000 000 / HZ)
+        call    .umul                   ! round multiplier up so large ns ok
+         mov    0x1ae, %o1              ! 2**32 / (1 000 000 000 / HZ)
         call    .umul
          mov    %i1, %o1                ! udelay_val
         ba      delay_continue
@@ -1760,11 +1760,17 @@ __ndelay:
 __udelay:
         save    %sp, -STACKFRAME_SZ, %sp
         mov     %i0, %o0
-        sethi   %hi(0x10c6), %o1
+        sethi   %hi(0x10c7), %o1        ! round multiplier up so large us ok
         call    .umul
-         or     %o1, %lo(0x10c6), %o1   ! 2**32 / 1 000 000
+         or     %o1, %lo(0x10c7), %o1   ! 2**32 / 1 000 000
         call    .umul
          mov    %i1, %o1                ! udelay_val
+        sethi   %hi(0x028f4b62), %l0    ! Add in rounding constant * 2**32,
+        or      %g0, %lo(0x028f4b62), %l0
+        addcc   %o0, %l0, %o0           ! 2**32 * 0.009 999
+        bcs,a   3f
+         add    %o1, 0x01, %o1
+3:
         call    .umul
          mov    HZ, %o0                 ! >>32 earlier for wider range
 
diff --git a/arch/sparc/kernel/irq.c b/arch/sparc/kernel/irq.c
index f257a67bcf93..75b2240ad0f9 100644
--- a/arch/sparc/kernel/irq.c
+++ b/arch/sparc/kernel/irq.c
@@ -47,6 +47,8 @@
 #include <asm/cacheflush.h>
 #include <asm/irq_regs.h>
 
+#include "irq.h"
+
 #ifdef CONFIG_SMP
 #define SMP_NOP2 "nop; nop;\n\t"
 #define SMP_NOP3 "nop; nop; nop;\n\t"
@@ -268,7 +270,7 @@ void free_irq(unsigned int irq, void *dev_id)
         kfree(action);
 
         if (!sparc_irq[cpu_irq].action)
-                disable_irq(irq);
+                __disable_irq(irq);
 
 out_unlock:
         spin_unlock_irqrestore(&irq_action_lock, flags);
@@ -464,7 +466,7 @@ int request_fast_irq(unsigned int irq,
 
         sparc_irq[cpu_irq].action = action;
 
-        enable_irq(irq);
+        __enable_irq(irq);
 
         ret = 0;
 out_unlock:
@@ -544,7 +546,7 @@ int request_irq(unsigned int irq,
 
         *actionp = action;
 
-        enable_irq(irq);
+        __enable_irq(irq);
 
         ret = 0;
 out_unlock:
@@ -555,6 +557,25 @@ out:
 
 EXPORT_SYMBOL(request_irq);
 
+void disable_irq_nosync(unsigned int irq)
+{
+        return __disable_irq(irq);
+}
+EXPORT_SYMBOL(disable_irq_nosync);
+
+void disable_irq(unsigned int irq)
+{
+        return __disable_irq(irq);
+}
+EXPORT_SYMBOL(disable_irq);
+
+void enable_irq(unsigned int irq)
+{
+        return __enable_irq(irq);
+}
+
+EXPORT_SYMBOL(enable_irq);
+
 /* We really don't need these at all on the Sparc.  We only have
  * stubs here because they are exported to modules.
  */
diff --git a/arch/sparc/kernel/irq.h b/arch/sparc/kernel/irq.h
new file mode 100644
index 000000000000..32ef3ebd0a88
--- /dev/null
+++ b/arch/sparc/kernel/irq.h
@@ -0,0 +1,68 @@
+#include <asm/btfixup.h>
+
+/* Dave Redman (djhr@tadpole.co.uk)
+ * changed these to function pointers.. it saves cycles and will allow
+ * the irq dependencies to be split into different files at a later date
+ * sun4c_irq.c, sun4m_irq.c etc so we could reduce the kernel size.
+ * Jakub Jelinek (jj@sunsite.mff.cuni.cz)
+ * Changed these to btfixup entities... It saves cycles :)
+ */
+
+BTFIXUPDEF_CALL(void, disable_irq, unsigned int)
+BTFIXUPDEF_CALL(void, enable_irq, unsigned int)
+BTFIXUPDEF_CALL(void, disable_pil_irq, unsigned int)
+BTFIXUPDEF_CALL(void, enable_pil_irq, unsigned int)
+BTFIXUPDEF_CALL(void, clear_clock_irq, void)
+BTFIXUPDEF_CALL(void, clear_profile_irq, int)
+BTFIXUPDEF_CALL(void, load_profile_irq, int, unsigned int)
+
+static inline void __disable_irq(unsigned int irq)
+{
+        BTFIXUP_CALL(disable_irq)(irq);
+}
+
+static inline void __enable_irq(unsigned int irq)
+{
+        BTFIXUP_CALL(enable_irq)(irq);
+}
+
+static inline void disable_pil_irq(unsigned int irq)
+{
+        BTFIXUP_CALL(disable_pil_irq)(irq);
+}
+
+static inline void enable_pil_irq(unsigned int irq)
+{
+        BTFIXUP_CALL(enable_pil_irq)(irq);
+}
+
+static inline void clear_clock_irq(void)
+{
+        BTFIXUP_CALL(clear_clock_irq)();
+}
+
+static inline void clear_profile_irq(int irq)
+{
+        BTFIXUP_CALL(clear_profile_irq)(irq);
+}
+
+static inline void load_profile_irq(int cpu, int limit)
+{
+        BTFIXUP_CALL(load_profile_irq)(cpu, limit);
+}
+
+extern void (*sparc_init_timers)(irq_handler_t lvl10_irq);
+
+extern void claim_ticker14(irq_handler_t irq_handler,
+                           int irq,
+                           unsigned int timeout);
+
+#ifdef CONFIG_SMP
+BTFIXUPDEF_CALL(void, set_cpu_int, int, int)
+BTFIXUPDEF_CALL(void, clear_cpu_int, int, int)
+BTFIXUPDEF_CALL(void, set_irq_udt, int)
+
+#define set_cpu_int(cpu,level) BTFIXUP_CALL(set_cpu_int)(cpu,level)
+#define clear_cpu_int(cpu,level) BTFIXUP_CALL(clear_cpu_int)(cpu,level)
+#define set_irq_udt(cpu) BTFIXUP_CALL(set_irq_udt)(cpu)
+#endif
diff --git a/arch/sparc/kernel/of_device.c b/arch/sparc/kernel/of_device.c
index fd7f8cb668a3..36383f73d685 100644
--- a/arch/sparc/kernel/of_device.c
+++ b/arch/sparc/kernel/of_device.c
@@ -1,132 +1,13 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
+#include <linux/of.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
 #include <linux/slab.h>
-
-#include <asm/errno.h>
-#include <asm/of_device.h>
-
-/**
- * of_match_device - Tell if an of_device structure has a matching
- * of_match structure
- * @ids: array of of device match structures to search in
- * @dev: the of device structure to match against
- *
- * Used by a driver to check whether an of_device present in the
- * system is in its list of supported devices.
- */
-const struct of_device_id *of_match_device(const struct of_device_id *matches,
-                                        const struct of_device *dev)
-{
-        if (!dev->node)
-                return NULL;
-        while (matches->name[0] || matches->type[0] || matches->compatible[0]) {
-                int match = 1;
-                if (matches->name[0])
-                        match &= dev->node->name
-                                && !strcmp(matches->name, dev->node->name);
-                if (matches->type[0])
-                        match &= dev->node->type
-                                && !strcmp(matches->type, dev->node->type);
-                if (matches->compatible[0])
-                        match &= of_device_is_compatible(dev->node,
-                                                         matches->compatible);
-                if (match)
-                        return matches;
-                matches++;
-        }
-        return NULL;
-}
-
-static int of_platform_bus_match(struct device *dev, struct device_driver *drv)
-{
-        struct of_device * of_dev = to_of_device(dev);
-        struct of_platform_driver * of_drv = to_of_platform_driver(drv);
-        const struct of_device_id * matches = of_drv->match_table;
-
-        if (!matches)
-                return 0;
-
-        return of_match_device(matches, of_dev) != NULL;
-}
-
-struct of_device *of_dev_get(struct of_device *dev)
-{
-        struct device *tmp;
-
-        if (!dev)
-                return NULL;
-        tmp = get_device(&dev->dev);
-        if (tmp)
-                return to_of_device(tmp);
-        else
-                return NULL;
-}
-
-void of_dev_put(struct of_device *dev)
-{
-        if (dev)
-                put_device(&dev->dev);
-}
-
-
-static int of_device_probe(struct device *dev)
-{
-        int error = -ENODEV;
-        struct of_platform_driver *drv;
-        struct of_device *of_dev;
-        const struct of_device_id *match;
-
-        drv = to_of_platform_driver(dev->driver);
-        of_dev = to_of_device(dev);
-
-        if (!drv->probe)
-                return error;
-
-        of_dev_get(of_dev);
-
-        match = of_match_device(drv->match_table, of_dev);
-        if (match)
-                error = drv->probe(of_dev, match);
-        if (error)
-                of_dev_put(of_dev);
-
-        return error;
-}
-
-static int of_device_remove(struct device *dev)
-{
-        struct of_device * of_dev = to_of_device(dev);
-        struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
-
-        if (dev->driver && drv->remove)
-                drv->remove(of_dev);
-        return 0;
-}
-
-static int of_device_suspend(struct device *dev, pm_message_t state)
-{
-        struct of_device * of_dev = to_of_device(dev);
-        struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
-        int error = 0;
-
-        if (dev->driver && drv->suspend)
-                error = drv->suspend(of_dev, state);
-        return error;
-}
-
-static int of_device_resume(struct device * dev)
-{
-        struct of_device * of_dev = to_of_device(dev);
-        struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
-        int error = 0;
-
-        if (dev->driver && drv->resume)
-                error = drv->resume(of_dev);
-        return error;
-}
+#include <linux/errno.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
 
 static int node_match(struct device *dev, void *data)
 {
@@ -138,7 +19,7 @@ static int node_match(struct device *dev, void *data)
 
 struct of_device *of_find_device_by_node(struct device_node *dp)
 {
-        struct device *dev = bus_find_device(&of_bus_type, NULL,
+        struct device *dev = bus_find_device(&of_platform_bus_type, NULL,
                                              dp, node_match);
 
         if (dev)
@@ -149,38 +30,17 @@ struct of_device *of_find_device_by_node(struct device_node *dp)
 EXPORT_SYMBOL(of_find_device_by_node);
 
 #ifdef CONFIG_PCI
-struct bus_type ebus_bus_type = {
-       .name    = "ebus",
-       .match   = of_platform_bus_match,
-       .probe   = of_device_probe,
-       .remove  = of_device_remove,
-       .suspend = of_device_suspend,
-       .resume  = of_device_resume,
-};
+struct bus_type ebus_bus_type;
 EXPORT_SYMBOL(ebus_bus_type);
 #endif
 
 #ifdef CONFIG_SBUS
-struct bus_type sbus_bus_type = {
-       .name    = "sbus",
-       .match   = of_platform_bus_match,
-       .probe   = of_device_probe,
-       .remove  = of_device_remove,
-       .suspend = of_device_suspend,
-       .resume  = of_device_resume,
-};
+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);
+struct bus_type of_platform_bus_type;
+EXPORT_SYMBOL(of_platform_bus_type);
 
 static inline u64 of_read_addr(const u32 *cell, int size)
 {
@@ -560,11 +420,16 @@ static struct of_device * __init scan_one_device(struct device_node *dp,
 {
         struct of_device *op = kzalloc(sizeof(*op), GFP_KERNEL);
         const struct linux_prom_irqs *intr;
+        struct dev_archdata *sd;
         int len, i;
 
         if (!op)
                 return NULL;
 
+        sd = &op->dev.archdata;
+        sd->prom_node = dp;
+        sd->op = op;
+
         op->node = dp;
 
         op->clock_freq = of_getintprop_default(dp, "clock-frequency",
@@ -646,7 +511,7 @@ build_resources:
         build_device_resources(op, parent);
 
         op->dev.parent = parent;
-        op->dev.bus = &of_bus_type;
+        op->dev.bus = &of_platform_bus_type;
         if (!parent)
                 strcpy(op->dev.bus_id, "root");
         else
@@ -690,14 +555,14 @@ static int __init of_bus_driver_init(void)
 {
         int err;
 
-        err = bus_register(&of_bus_type);
+        err = of_bus_type_init(&of_platform_bus_type, "of");
 #ifdef CONFIG_PCI
         if (!err)
-                err = bus_register(&ebus_bus_type);
+                err = of_bus_type_init(&ebus_bus_type, "ebus");
 #endif
 #ifdef CONFIG_SBUS
         if (!err)
-                err = bus_register(&sbus_bus_type);
+                err = of_bus_type_init(&sbus_bus_type, "sbus");
 #endif
 
         if (!err)
@@ -735,56 +600,6 @@ void of_unregister_driver(struct of_platform_driver *drv)
         driver_unregister(&drv->driver);
 }
 
-
-static ssize_t dev_show_devspec(struct device *dev, struct device_attribute *attr, char *buf)
-{
-        struct of_device *ofdev;
-
-        ofdev = to_of_device(dev);
-        return sprintf(buf, "%s", ofdev->node->full_name);
-}
-
-static DEVICE_ATTR(devspec, S_IRUGO, dev_show_devspec, NULL);
-
-/**
- * of_release_dev - free an of device structure when all users of it are finished.
- * @dev: device that's been disconnected
- *
- * Will be called only by the device core when all users of this of device are
- * done.
- */
-void of_release_dev(struct device *dev)
-{
-        struct of_device *ofdev;
-
-        ofdev = to_of_device(dev);
-
-        kfree(ofdev);
-}
-
-int of_device_register(struct of_device *ofdev)
-{
-        int rc;
-
-        BUG_ON(ofdev->node == NULL);
-
-        rc = device_register(&ofdev->dev);
-        if (rc)
-                return rc;
-
-        rc = device_create_file(&ofdev->dev, &dev_attr_devspec);
-        if (rc)
-                device_unregister(&ofdev->dev);
-
-        return rc;
-}
-
-void of_device_unregister(struct of_device *ofdev)
-{
-        device_remove_file(&ofdev->dev, &dev_attr_devspec);
-        device_unregister(&ofdev->dev);
-}
-
 struct of_device* of_platform_device_create(struct device_node *np,
                                             const char *bus_id,
                                             struct device *parent,
@@ -810,12 +625,6 @@ struct of_device* of_platform_device_create(struct device_node *np,
         return dev;
 }
 
-EXPORT_SYMBOL(of_match_device);
 EXPORT_SYMBOL(of_register_driver);
 EXPORT_SYMBOL(of_unregister_driver);
-EXPORT_SYMBOL(of_device_register);
-EXPORT_SYMBOL(of_device_unregister);
-EXPORT_SYMBOL(of_dev_get);
-EXPORT_SYMBOL(of_dev_put);
 EXPORT_SYMBOL(of_platform_device_create);
-EXPORT_SYMBOL(of_release_dev);
diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c
index 791771196905..f2eae457fc9a 100644
--- a/arch/sparc/kernel/pcic.c
+++ b/arch/sparc/kernel/pcic.c
@@ -36,6 +36,7 @@
 #include <asm/uaccess.h>
 #include <asm/irq_regs.h>
 
+#include "irq.h"
 
 /*
  * I studied different documents and many live PROMs both from 2.30
diff --git a/arch/sparc/kernel/process.c b/arch/sparc/kernel/process.c
index 8c37f8f5adb7..33f7a3ddb104 100644
--- a/arch/sparc/kernel/process.c
+++ b/arch/sparc/kernel/process.c
@@ -39,6 +39,7 @@
 #include <asm/processor.h>
 #include <asm/psr.h>
 #include <asm/elf.h>
+#include <asm/prom.h>
 #include <asm/unistd.h>
 
 /* 
@@ -150,7 +151,7 @@ void machine_halt(void)
         local_irq_enable();
         mdelay(8);
         local_irq_disable();
-        if (!serial_console && prom_palette)
+        if (prom_palette)
                 prom_palette (1);
         prom_halt();
         panic("Halt failed!");
@@ -166,7 +167,7 @@ void machine_restart(char * cmd)
 
         p = strchr (reboot_command, '\n');
         if (p) *p = 0;
-        if (!serial_console && prom_palette)
+        if (prom_palette)
                 prom_palette (1);
         if (cmd)
                 prom_reboot(cmd);
@@ -179,7 +180,8 @@ void machine_restart(char * cmd)
 void machine_power_off(void)
 {
 #ifdef CONFIG_SUN_AUXIO
-        if (auxio_power_register && (!serial_console || scons_pwroff))
+        if (auxio_power_register &&
+            (strcmp(of_console_device->type, "serial") || scons_pwroff))
                 *auxio_power_register |= AUXIO_POWER_OFF;
 #endif
         machine_halt();
diff --git a/arch/sparc/kernel/prom.c b/arch/sparc/kernel/prom.c
index eed140b3c739..e3a537650db1 100644
--- a/arch/sparc/kernel/prom.c
+++ b/arch/sparc/kernel/prom.c
@@ -25,73 +25,9 @@
 #include <asm/prom.h>
 #include <asm/oplib.h>
 
-static struct device_node *allnodes;
+extern struct device_node *allnodes;    /* temporary while merging */
 
-/* use when traversing tree through the allnext, child, sibling,
- * or parent members of struct device_node.
- */
-static DEFINE_RWLOCK(devtree_lock);
-
-int of_device_is_compatible(const struct device_node *device,
-                            const char *compat)
-{
-        const char* cp;
-        int cplen, l;
-
-        cp = of_get_property(device, "compatible", &cplen);
-        if (cp == NULL)
-                return 0;
-        while (cplen > 0) {
-                if (strncmp(cp, compat, strlen(compat)) == 0)
-                        return 1;
-                l = strlen(cp) + 1;
-                cp += l;
-                cplen -= l;
-        }
-
-        return 0;
-}
-EXPORT_SYMBOL(of_device_is_compatible);
-
-struct device_node *of_get_parent(const struct device_node *node)
-{
-        struct device_node *np;
-
-        if (!node)
-                return NULL;
-
-        np = node->parent;
-
-        return np;
-}
-EXPORT_SYMBOL(of_get_parent);
-
-struct device_node *of_get_next_child(const struct device_node *node,
-        struct device_node *prev)
-{
-        struct device_node *next;
-
-        next = prev ? prev->sibling : node->child;
-        for (; next != 0; next = next->sibling) {
-                break;
-        }
-
-        return next;
-}
-EXPORT_SYMBOL(of_get_next_child);
-
-struct device_node *of_find_node_by_path(const char *path)
-{
-        struct device_node *np = allnodes;
-
-        for (; np != 0; np = np->allnext) {
-                if (np->full_name != 0 && strcmp(np->full_name, path) == 0)
-                        break;
-        }
-
-        return np;
-}
-EXPORT_SYMBOL(of_find_node_by_path);
+extern rwlock_t devtree_lock;   /* temporary while merging */
 
 struct device_node *of_find_node_by_phandle(phandle handle)
 {
@@ -105,81 +41,6 @@ struct device_node *of_find_node_by_phandle(phandle handle)
 }
 EXPORT_SYMBOL(of_find_node_by_phandle);
 
-struct device_node *of_find_node_by_name(struct device_node *from,
-        const char *name)
-{
-        struct device_node *np;
-
-        np = from ? from->allnext : allnodes;
-        for (; np != NULL; np = np->allnext)
-                if (np->name != NULL && strcmp(np->name, name) == 0)
-                        break;
-
-        return np;
-}
-EXPORT_SYMBOL(of_find_node_by_name);
-
-struct device_node *of_find_node_by_type(struct device_node *from,
-        const char *type)
-{
-        struct device_node *np;
-
-        np = from ? from->allnext : allnodes;
-        for (; np != 0; np = np->allnext)
-                if (np->type != 0 && strcmp(np->type, type) == 0)
-                        break;
-
-        return np;
-}
-EXPORT_SYMBOL(of_find_node_by_type);
-
-struct device_node *of_find_compatible_node(struct device_node *from,
-        const char *type, const char *compatible)
-{
-        struct device_node *np;
-
-        np = from ? from->allnext : allnodes;
-        for (; np != 0; np = np->allnext) {
-                if (type != NULL
-                    && !(np->type != 0 && strcmp(np->type, type) == 0))
-                        continue;
-                if (of_device_is_compatible(np, compatible))
-                        break;
-        }
-
-        return np;
-}
-EXPORT_SYMBOL(of_find_compatible_node);
-
-struct property *of_find_property(const struct device_node *np,
-                                  const char *name,
-                                  int *lenp)
-{
-        struct property *pp;
-
-        for (pp = np->properties; pp != 0; pp = pp->next) {
-                if (strcasecmp(pp->name, name) == 0) {
-                        if (lenp != 0)
-                                *lenp = pp->length;
-                        break;
-                }
-        }
-        return pp;
-}
-EXPORT_SYMBOL(of_find_property);
-
-/*
- * Find a property with a given name for a given node
- * and return the value.
- */
-const void *of_get_property(const struct device_node *np, const char *name,
-                            int *lenp)
-{
-        struct property *pp = of_find_property(np,name,lenp);
-        return pp ? pp->value : NULL;
-}
-EXPORT_SYMBOL(of_get_property);
-
 int of_getintprop_default(struct device_node *np, const char *name, int def)
 {
         struct property *prop;
@@ -193,36 +54,6 @@ 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)
-{
-        const 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)
-{
-        const 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;
@@ -566,6 +397,135 @@ static struct device_node * __init build_tree(struct device_node *parent, phandl
         return dp;
 }
 
+struct device_node *of_console_device;
+EXPORT_SYMBOL(of_console_device);
+
+char *of_console_path;
+EXPORT_SYMBOL(of_console_path);
+
+char *of_console_options;
+EXPORT_SYMBOL(of_console_options);
+
+extern void restore_current(void);
+
+static void __init of_console_init(void)
+{
+        char *msg = "OF stdout device is: %s\n";
+        struct device_node *dp;
+        unsigned long flags;
+        const char *type;
+        phandle node;
+        int skip, fd;
+
+        of_console_path = prom_early_alloc(256);
+
+        switch (prom_vers) {
+        case PROM_V0:
+        case PROM_SUN4:
+                skip = 0;
+                switch (*romvec->pv_stdout) {
+                case PROMDEV_SCREEN:
+                        type = "display";
+                        break;
+
+                case PROMDEV_TTYB:
+                        skip = 1;
+                        /* FALLTHRU */
+
+                case PROMDEV_TTYA:
+                        type = "serial";
+                        break;
+
+                default:
+                        prom_printf("Invalid PROM_V0 stdout value %u\n",
+                                    *romvec->pv_stdout);
+                        prom_halt();
+                }
+
+                for_each_node_by_type(dp, type) {
+                        if (!skip--)
+                                break;
+                }
+                if (!dp) {
+                        prom_printf("Cannot find PROM_V0 console node.\n");
+                        prom_halt();
+                }
+                of_console_device = dp;
+
+                strcpy(of_console_path, dp->full_name);
+                if (!strcmp(type, "serial")) {
+                        strcat(of_console_path,
+                               (skip ? ":b" : ":a"));
+                }
+                break;
+
+        default:
+        case PROM_V2:
+        case PROM_V3:
+                fd = *romvec->pv_v2bootargs.fd_stdout;
+
+                spin_lock_irqsave(&prom_lock, flags);
+                node = (*romvec->pv_v2devops.v2_inst2pkg)(fd);
+                restore_current();
+                spin_unlock_irqrestore(&prom_lock, flags);
+
+                if (!node) {
+                        prom_printf("Cannot resolve stdout node from "
+                                    "instance %08x.\n", fd);
+                        prom_halt();
+                }
+                dp = of_find_node_by_phandle(node);
+                type = of_get_property(dp, "device_type", NULL);
+
+                if (!type) {
+                        prom_printf("Console stdout lacks "
+                                    "device_type property.\n");
+                        prom_halt();
+                }
+
+                if (strcmp(type, "display") && strcmp(type, "serial")) {
+                        prom_printf("Console device_type is neither display "
+                                    "nor serial.\n");
+                        prom_halt();
+                }
+
+                of_console_device = dp;
+
+                if (prom_vers == PROM_V2) {
+                        strcpy(of_console_path, dp->full_name);
+                        switch (*romvec->pv_stdout) {
+                        case PROMDEV_TTYA:
+                                strcat(of_console_path, ":a");
+                                break;
+                        case PROMDEV_TTYB:
+                                strcat(of_console_path, ":b");
+                                break;
+                        }
+                } else {
+                        const char *path;
+
+                        dp = of_find_node_by_path("/");
+                        path = of_get_property(dp, "stdout-path", NULL);
+                        if (!path) {
+                                prom_printf("No stdout-path in root node.\n");
+                                prom_halt();
+                        }
+                        strcpy(of_console_path, path);
+                }
+                break;
+        }
+
+        of_console_options = strrchr(of_console_path, ':');
+        if (of_console_options) {
+                of_console_options++;
+                if (*of_console_options == '\0')
+                        of_console_options = NULL;
+        }
+
+        prom_printf(msg, of_console_path);
+        printk(msg, of_console_path);
+}
+
 void __init prom_build_devicetree(void)
 {
         struct device_node **nextp;
@@ -578,6 +538,8 @@ void __init prom_build_devicetree(void)
         allnodes->child = build_tree(allnodes,
                                      prom_getchild(allnodes->node),
                                      &nextp);
+        of_console_init();
+
         printk("PROM: Built device tree with %u bytes of memory.\n",
                prom_early_allocated);
 }
diff --git a/arch/sparc/kernel/setup.c b/arch/sparc/kernel/setup.c
index 64c0ed98820a..f8228383895a 100644
--- a/arch/sparc/kernel/setup.c
+++ b/arch/sparc/kernel/setup.c
@@ -146,31 +146,6 @@ static void __init process_switch(char c)
         }
 }
 
-static void __init process_console(char *commands)
-{
-        serial_console = 0;
-        commands += 8;
-        /* Linux-style serial */
-        if (!strncmp(commands, "ttyS", 4))
-                serial_console = simple_strtoul(commands + 4, NULL, 10) + 1;
-        else if (!strncmp(commands, "tty", 3)) {
-                char c = *(commands + 3);
-                /* Solaris-style serial */
-                if (c == 'a' || c == 'b')
-                        serial_console = c - 'a' + 1;
-                /* else Linux-style fbcon, not serial */
-        }
-#if defined(CONFIG_PROM_CONSOLE)
-        if (!strncmp(commands, "prom", 4)) {
-                char *p;
-
-                for (p = commands - 8; *p && *p != ' '; p++)
-                        *p = ' ';
-                conswitchp = &prom_con;
-        }
-#endif
-}
-
 static void __init boot_flags_init(char *commands)
 {
         while (*commands) {
@@ -187,9 +162,7 @@ static void __init boot_flags_init(char *commands)
                                 process_switch(*commands++);
                         continue;
                 }
-                if (!strncmp(commands, "console=", 8)) {
-                        process_console(commands);
-                } else if (!strncmp(commands, "mem=", 4)) {
+                if (!strncmp(commands, "mem=", 4)) {
                         /*
                          * "mem=XXX[kKmM] overrides the PROM-reported
                          * memory size.
@@ -341,41 +314,6 @@ void __init setup_arch(char **cmdline_p)
         smp_setup_cpu_possible_map();
 }
 
-static int __init set_preferred_console(void)
-{
-        int idev, odev;
-
-        /* The user has requested a console so this is already set up. */
-        if (serial_console >= 0)
-                return -EBUSY;
-
-        idev = prom_query_input_device();
-        odev = prom_query_output_device();
-        if (idev == PROMDEV_IKBD && odev == PROMDEV_OSCREEN) {
-                serial_console = 0;
-        } else if (idev == PROMDEV_ITTYA && odev == PROMDEV_OTTYA) {
-                serial_console = 1;
-        } else if (idev == PROMDEV_ITTYB && odev == PROMDEV_OTTYB) {
-                serial_console = 2;
-        } else if (idev == PROMDEV_I_UNK && odev == PROMDEV_OTTYA) {
-                prom_printf("MrCoffee ttya\n");
-                serial_console = 1;
-        } else if (idev == PROMDEV_I_UNK && odev == PROMDEV_OSCREEN) {
-                serial_console = 0;
-                prom_printf("MrCoffee keyboard\n");
-        } else {
-                prom_printf("Confusing console (idev %d, odev %d)\n",
-                    idev, odev);
-                serial_console = 1;
-        }
-
-        if (serial_console)
-                return add_preferred_console("ttyS", serial_console - 1, NULL);
-
-        return -ENODEV;
-}
-console_initcall(set_preferred_console);
-
 extern char *sparc_cpu_type;
 extern char *sparc_fpu_type;
 
@@ -461,7 +399,6 @@ void sun_do_break(void)
         prom_cmdline();
 }
 
-int serial_console = -1;
 int stop_a_enabled = 1;
 
 static int __init topology_init(void)
diff --git a/arch/sparc/kernel/smp.c b/arch/sparc/kernel/smp.c
index 4fea3ac7bff0..6724ab90f82b 100644
--- a/arch/sparc/kernel/smp.c
+++ b/arch/sparc/kernel/smp.c
@@ -33,6 +33,8 @@
 #include <asm/tlbflush.h>
 #include <asm/cpudata.h>
 
+#include "irq.h"
+
 int smp_num_cpus = 1;
 volatile unsigned long cpu_callin_map[NR_CPUS] __initdata = {0,};
 unsigned char boot_cpu_id = 0;
diff --git a/arch/sparc/kernel/sparc_ksyms.c b/arch/sparc/kernel/sparc_ksyms.c
index d8e008a04e2b..55bac516dfe2 100644
--- a/arch/sparc/kernel/sparc_ksyms.c
+++ b/arch/sparc/kernel/sparc_ksyms.c
@@ -154,8 +154,6 @@ EXPORT_SYMBOL(BTFIXUP_CALL(___xchg32));
 #else
 EXPORT_SYMBOL(BTFIXUP_CALL(__hard_smp_processor_id));
 #endif
-EXPORT_SYMBOL(BTFIXUP_CALL(enable_irq));
-EXPORT_SYMBOL(BTFIXUP_CALL(disable_irq));
 EXPORT_SYMBOL(BTFIXUP_CALL(mmu_unlockarea));
 EXPORT_SYMBOL(BTFIXUP_CALL(mmu_lockarea));
 EXPORT_SYMBOL(BTFIXUP_CALL(mmu_get_scsi_sgl));
diff --git a/arch/sparc/kernel/sun4c_irq.c b/arch/sparc/kernel/sun4c_irq.c
index 009e891a4329..c6ac9fc52563 100644
--- a/arch/sparc/kernel/sun4c_irq.c
+++ b/arch/sparc/kernel/sun4c_irq.c
@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/slab.h>
 #include <linux/init.h>
+#include "irq.h"
 
 #include <asm/ptrace.h>
 #include <asm/processor.h>
@@ -40,6 +41,20 @@ static struct resource sun4c_timer_eb = { "sun4c_timer" };
 static struct resource sun4c_intr_eb = { "sun4c_intr" };
 #endif
 
+/*
+ * Bit field defines for the interrupt registers on various
+ * Sparc machines.
+ */
+
+/* The sun4c interrupt register. */
+#define SUN4C_INT_ENABLE  0x01     /* Allow interrupts. */
+#define SUN4C_INT_E14     0x80     /* Enable level 14 IRQ. */
+#define SUN4C_INT_E10     0x20     /* Enable level 10 IRQ. */
+#define SUN4C_INT_E8      0x10     /* Enable level 8 IRQ. */
+#define SUN4C_INT_E6      0x08     /* Enable level 6 IRQ. */
+#define SUN4C_INT_E4      0x04     /* Enable level 4 IRQ. */
+#define SUN4C_INT_E1      0x02     /* Enable level 1 IRQ. */
+
 /* Pointer to the interrupt enable byte
  *
  * Dave Redman (djhr@tadpole.co.uk)
diff --git a/arch/sparc/kernel/sun4d_irq.c b/arch/sparc/kernel/sun4d_irq.c
index 396797e20c39..e0efab2a6bef 100644
--- a/arch/sparc/kernel/sun4d_irq.c
+++ b/arch/sparc/kernel/sun4d_irq.c
@@ -39,6 +39,8 @@
 #include <asm/cacheflush.h>
 #include <asm/irq_regs.h>
 
+#include "irq.h"
+
 /* If you trust current SCSI layer to handle different SCSI IRQs, enable this. I don't trust it... -jj */
 /* #define DISTRIBUTE_IRQS */
 
@@ -188,7 +190,7 @@ void sun4d_free_irq(unsigned int irq, void *dev_id)
         kfree(action);
 
         if (!(*actionp))
-                disable_irq(irq);
+                __disable_irq(irq);
 
 out_unlock:
         spin_unlock_irqrestore(&irq_action_lock, flags);
@@ -346,7 +348,7 @@ int sun4d_request_irq(unsigned int irq,
         else
                 *actionp = action;
                 
-        enable_irq(irq);
+        __enable_irq(irq);
 
         ret = 0;
 out_unlock:
diff --git a/arch/sparc/kernel/sun4d_smp.c b/arch/sparc/kernel/sun4d_smp.c
index 098c94f1a322..89a6de95070c 100644
--- a/arch/sparc/kernel/sun4d_smp.c
+++ b/arch/sparc/kernel/sun4d_smp.c
@@ -36,6 +36,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cpudata.h>
 
+#include "irq.h"
 #define IRQ_CROSS_CALL          15
 
 extern ctxd_t *srmmu_ctx_table_phys;
diff --git a/arch/sparc/kernel/sun4m_irq.c b/arch/sparc/kernel/sun4m_irq.c
index 91a803ea88be..b92d6d2d5b04 100644
--- a/arch/sparc/kernel/sun4m_irq.c
+++ b/arch/sparc/kernel/sun4m_irq.c
@@ -38,11 +38,85 @@
 #include <asm/sbus.h>
 #include <asm/cacheflush.h>
 
+#include "irq.h"
+
+/* On the sun4m, just like the timers, we have both per-cpu and master
+ * interrupt registers.
+ */
+
+/* These registers are used for sending/receiving irqs from/to
+ * different cpu's.
+ */
+struct sun4m_intreg_percpu {
+        unsigned int tbt;        /* Interrupts still pending for this cpu. */
+
+        /* These next two registers are WRITE-ONLY and are only
+         * "on bit" sensitive, "off bits" written have NO affect.
+         */
+        unsigned int clear;  /* Clear this cpus irqs here. */
+        unsigned int set;    /* Set this cpus irqs here. */
+        unsigned char space[PAGE_SIZE - 12];
+};
+
+/*
+ * djhr
+ * Actually the clear and set fields in this struct are misleading..
+ * according to the SLAVIO manual (and the same applies for the SEC)
+ * the clear field clears bits in the mask which will ENABLE that IRQ
+ * the set field sets bits in the mask to DISABLE the IRQ.
+ *
+ * Also the undirected_xx address in the SLAVIO is defined as
+ * RESERVED and write only..
+ *
+ * DAVEM_NOTE: The SLAVIO only specifies behavior on uniprocessor
+ *             sun4m machines, for MP the layout makes more sense.
+ */
+struct sun4m_intregs {
+        struct sun4m_intreg_percpu cpu_intregs[SUN4M_NCPUS];
+        unsigned int tbt;                /* IRQ's that are still pending. */
+        unsigned int irqs;               /* Master IRQ bits. */
+
+        /* Again, like the above, two these registers are WRITE-ONLY. */
+        unsigned int clear;              /* Clear master IRQ's by setting bits here. */
+        unsigned int set;                /* Set master IRQ's by setting bits here. */
+
+        /* This register is both READ and WRITE. */
+        unsigned int undirected_target;  /* Which cpu gets undirected irqs. */
+};
+
 static unsigned long dummy;
 
 struct sun4m_intregs *sun4m_interrupts;
 unsigned long *irq_rcvreg = &dummy;
 
+/* Dave Redman (djhr@tadpole.co.uk)
+ * The sun4m interrupt registers.
+ */
+#define SUN4M_INT_ENABLE        0x80000000
+#define SUN4M_INT_E14           0x00000080
+#define SUN4M_INT_E10           0x00080000
+
+#define SUN4M_HARD_INT(x)       (0x000000001 << (x))
+#define SUN4M_SOFT_INT(x)       (0x000010000 << (x))
+
+#define SUN4M_INT_MASKALL       0x80000000        /* mask all interrupts */
+#define SUN4M_INT_MODULE_ERR    0x40000000        /* module error */
+#define SUN4M_INT_M2S_WRITE     0x20000000        /* write buffer error */
+#define SUN4M_INT_ECC           0x10000000        /* ecc memory error */
+#define SUN4M_INT_FLOPPY        0x00400000        /* floppy disk */
+#define SUN4M_INT_MODULE        0x00200000        /* module interrupt */
+#define SUN4M_INT_VIDEO         0x00100000        /* onboard video */
+#define SUN4M_INT_REALTIME      0x00080000        /* system timer */
+#define SUN4M_INT_SCSI          0x00040000        /* onboard scsi */
+#define SUN4M_INT_AUDIO         0x00020000        /* audio/isdn */
+#define SUN4M_INT_ETHERNET      0x00010000        /* onboard ethernet */
+#define SUN4M_INT_SERIAL        0x00008000        /* serial ports */
+#define SUN4M_INT_KBDMS         0x00004000        /* keyboard/mouse */
+#define SUN4M_INT_SBUSBITS      0x00003F80        /* sbus int bits */
+
+#define SUN4M_INT_SBUS(x)       (1 << (x+7))
+#define SUN4M_INT_VME(x)        (1 << (x))
+
 /* These tables only apply for interrupts greater than 15..
  * 
  * any intr value below 0x10 is considered to be a soft-int
diff --git a/arch/sparc/kernel/sun4m_smp.c b/arch/sparc/kernel/sun4m_smp.c
index 63ed19bfd028..730eb5796f8e 100644
--- a/arch/sparc/kernel/sun4m_smp.c
+++ b/arch/sparc/kernel/sun4m_smp.c
@@ -31,6 +31,8 @@
 #include <asm/oplib.h>
 #include <asm/cpudata.h>
 
+#include "irq.h"
+
 #define IRQ_RESCHEDULE          13
 #define IRQ_STOP_CPU            14
 #define IRQ_CROSS_CALL          15
diff --git a/arch/sparc/kernel/systbls.S b/arch/sparc/kernel/systbls.S
index 90b52d4dab9a..55722840859c 100644
--- a/arch/sparc/kernel/systbls.S
+++ b/arch/sparc/kernel/systbls.S
@@ -1,8 +1,7 @@
-/* $Id: systbls.S,v 1.103 2002/02/08 03:57:14 davem Exp $
- * systbls.S: System call entry point tables for OS compatibility.
+/* systbls.S: System call entry point tables for OS compatibility.
  *            The native Linux system call table lives here also.
  *
- * Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu)
+ * Copyright (C) 1995, 2007 David S. Miller (davem@davemloft.net)
  *
  * Based upon preliminary work which is:
  *
@@ -80,7 +79,7 @@ sys_call_table:
 /*295*/ .long sys_fchmodat, sys_faccessat, sys_pselect6, sys_ppoll, sys_unshare
 /*300*/ .long sys_set_robust_list, sys_get_robust_list, sys_migrate_pages, sys_mbind, sys_get_mempolicy
 /*305*/ .long sys_set_mempolicy, sys_kexec_load, sys_move_pages, sys_getcpu, sys_epoll_pwait
-/*310*/ .long sys_utimensat, sys_signalfd, sys_timerfd, sys_eventfd
+/*310*/ .long sys_utimensat, sys_signalfd, sys_timerfd, sys_eventfd, sys_fallocate
 
 #ifdef CONFIG_SUNOS_EMUL
         /* Now the SunOS syscall table. */
@@ -198,6 +197,6 @@ sunos_sys_table:
         .long sunos_nosys, sunos_nosys, sunos_nosys
         .long sunos_nosys
 /*310*/ .long sunos_nosys, sunos_nosys, sunos_nosys
-        .long sunos_nosys
+        .long sunos_nosys, sunos_nosys
 
 #endif
diff --git a/arch/sparc/kernel/tick14.c b/arch/sparc/kernel/tick14.c
index f1a7bd19e04f..707bfda86570 100644
--- a/arch/sparc/kernel/tick14.c
+++ b/arch/sparc/kernel/tick14.c
@@ -25,6 +25,8 @@
 #include <asm/irq.h>
 #include <asm/io.h>
 
+#include "irq.h"
+
 extern unsigned long lvl14_save[5];
 static unsigned long *linux_lvl14 = NULL;
 static unsigned long obp_lvl14[4];
@@ -62,7 +64,7 @@ void claim_ticker14(irq_handler_t handler,
 
         /* first we copy the obp handler instructions
          */
-        disable_irq(irq_nr);
+        __disable_irq(irq_nr);
         if (!handler)
                 return;
     
@@ -79,6 +81,6 @@ void claim_ticker14(irq_handler_t handler,
                          NULL)) {
                 install_linux_ticker();
                 load_profile_irq(cpu, timeout);
-                enable_irq(irq_nr);
+                __enable_irq(irq_nr);
         }
 }
diff --git a/arch/sparc/kernel/time.c b/arch/sparc/kernel/time.c
index 7b4612da74a6..6a2513321620 100644
--- a/arch/sparc/kernel/time.c
+++ b/arch/sparc/kernel/time.c
@@ -44,6 +44,8 @@
 #include <asm/of_device.h>
 #include <asm/irq_regs.h>
 
+#include "irq.h"
+
 DEFINE_SPINLOCK(rtc_lock);
 enum sparc_clock_type sp_clock_typ;
 DEFINE_SPINLOCK(mostek_lock);
@@ -354,7 +356,7 @@ static struct of_platform_driver clock_driver = {
 /* Probe for the mostek real time clock chip. */
 static int __init clock_init(void)
 {
-        return of_register_driver(&clock_driver, &of_bus_type);
+        return of_register_driver(&clock_driver, &of_platform_bus_type);
 }
 
 /* Must be after subsys_initcall() so that busses are probed.  Must
diff --git a/arch/sparc/mm/init.c b/arch/sparc/mm/init.c
index a532922e2e35..a1bef07755a9 100644
--- a/arch/sparc/mm/init.c
+++ b/arch/sparc/mm/init.c
@@ -308,6 +308,9 @@ extern void sun4c_paging_init(void);
 extern void srmmu_paging_init(void);
 extern void device_scan(void);
 
+pgprot_t PAGE_SHARED __read_mostly;
+EXPORT_SYMBOL(PAGE_SHARED);
+
 void __init paging_init(void)
 {
         switch(sparc_cpu_model) {
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index ca26232da7ab..17b485f2825c 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -2154,7 +2154,7 @@ void __init ld_mmu_srmmu(void)
         BTFIXUPSET_SIMM13(ptrs_per_pgd, SRMMU_PTRS_PER_PGD);
 
         BTFIXUPSET_INT(page_none, pgprot_val(SRMMU_PAGE_NONE));
-        BTFIXUPSET_INT(page_shared, pgprot_val(SRMMU_PAGE_SHARED));
+        PAGE_SHARED = pgprot_val(SRMMU_PAGE_SHARED);
         BTFIXUPSET_INT(page_copy, pgprot_val(SRMMU_PAGE_COPY));
         BTFIXUPSET_INT(page_readonly, pgprot_val(SRMMU_PAGE_RDONLY));
         BTFIXUPSET_INT(page_kernel, pgprot_val(SRMMU_PAGE_KERNEL));
diff --git a/arch/sparc/mm/sun4c.c b/arch/sparc/mm/sun4c.c
index bdd835fba02e..a57a366e339a 100644
--- a/arch/sparc/mm/sun4c.c
+++ b/arch/sparc/mm/sun4c.c
@@ -2155,7 +2155,7 @@ void __init ld_mmu_sun4c(void)
         BTFIXUPSET_SIMM13(user_ptrs_per_pgd, KERNBASE / SUN4C_PGDIR_SIZE);
 
         BTFIXUPSET_INT(page_none, pgprot_val(SUN4C_PAGE_NONE));
-        BTFIXUPSET_INT(page_shared, pgprot_val(SUN4C_PAGE_SHARED));
+        PAGE_SHARED = pgprot_val(SUN4C_PAGE_SHARED);
         BTFIXUPSET_INT(page_copy, pgprot_val(SUN4C_PAGE_COPY));
         BTFIXUPSET_INT(page_readonly, pgprot_val(SUN4C_PAGE_READONLY));
         BTFIXUPSET_INT(page_kernel, pgprot_val(SUN4C_PAGE_KERNEL));
diff --git a/arch/sparc/prom/console.c b/arch/sparc/prom/console.c
index 4e6e41d3291d..8d1cfb0d5068 100644
--- a/arch/sparc/prom/console.c
+++ b/arch/sparc/prom/console.c
@@ -102,119 +102,3 @@ prom_putchar(char c)
         while(prom_nbputchar(c) == -1) ;
         return;
 }
-
-/* Query for input device type */
-enum prom_input_device
-prom_query_input_device(void)
-{
-        unsigned long flags;
-        int st_p;
-        char propb[64];
-        char *p;
-        int propl;
-
-        switch(prom_vers) {
-        case PROM_V0:
-        case PROM_V2:
-        case PROM_SUN4:
-        default:
-                switch(*romvec->pv_stdin) {
-                case PROMDEV_KBD:       return PROMDEV_IKBD;
-                case PROMDEV_TTYA:      return PROMDEV_ITTYA;
-                case PROMDEV_TTYB:      return PROMDEV_ITTYB;
-                default:
-                        return PROMDEV_I_UNK;
-                };
-        case PROM_V3:
-                spin_lock_irqsave(&prom_lock, flags);
-                st_p = (*romvec->pv_v2devops.v2_inst2pkg)(*romvec->pv_v2bootargs.fd_stdin);
-                restore_current();
-                spin_unlock_irqrestore(&prom_lock, flags);
-                if(prom_node_has_property(st_p, "keyboard"))
-                        return PROMDEV_IKBD;
-                if (prom_getproperty(st_p, "name", propb, sizeof(propb)) != -1) {
-                        if(strncmp(propb, "keyboard", sizeof("serial")) == 0)
-                                return PROMDEV_IKBD;
-                }
-                if (prom_getproperty(st_p, "device_type", propb, sizeof(propb)) != -1) {
-                if(strncmp(propb, "serial", sizeof("serial")))
-                        return PROMDEV_I_UNK;
-                }
-                propl = prom_getproperty(prom_root_node, "stdin-path", propb, sizeof(propb));
-                if(propl > 2) {
-                        p = propb;
-                        while(*p) p++; p -= 2;
-                        if(p[0] == ':') {
-                                if(p[1] == 'a')
-                                        return PROMDEV_ITTYA;
-                                else if(p[1] == 'b')
-                                        return PROMDEV_ITTYB;
-                        }
-                }
-                return PROMDEV_I_UNK;
-        }
-}
-
-/* Query for output device type */
-
-enum prom_output_device
-prom_query_output_device(void)
-{
-        unsigned long flags;
-        int st_p;
-        char propb[64];
-        char *p;
-        int propl;
-
-        switch(prom_vers) {
-        case PROM_V0:
-        case PROM_SUN4:
-                switch(*romvec->pv_stdin) {
-                case PROMDEV_SCREEN:    return PROMDEV_OSCREEN;
-                case PROMDEV_TTYA:      return PROMDEV_OTTYA;
-                case PROMDEV_TTYB:      return PROMDEV_OTTYB;
-                };
-                break;
-        case PROM_V2:
-        case PROM_V3:
-                spin_lock_irqsave(&prom_lock, flags);
-                st_p = (*romvec->pv_v2devops.v2_inst2pkg)(*romvec->pv_v2bootargs.fd_stdout);
-                restore_current();
-                spin_unlock_irqrestore(&prom_lock, flags);
-                propl = prom_getproperty(st_p, "device_type", propb, sizeof(propb));
-                if (propl == sizeof("display") &&
-                        strncmp("display", propb, sizeof("display")) == 0)
-                {
-                        return PROMDEV_OSCREEN;
-                }
-                if(prom_vers == PROM_V3) {
-                        if(propl >= 0 &&
-                            strncmp("serial", propb, sizeof("serial")) != 0)
-                                return PROMDEV_O_UNK;
-                        propl = prom_getproperty(prom_root_node, "stdout-path",
-                                                 propb, sizeof(propb));
-                        if(propl == CON_SIZE_JMC &&
-                            strncmp(propb, con_name_jmc, CON_SIZE_JMC) == 0)
-                                return PROMDEV_OTTYA;
-                        if(propl > 2) {
-                                p = propb;
-                                while(*p) p++; p-= 2;
-                                if(p[0]==':') {
-                                        if(p[1] == 'a')
-                                                return PROMDEV_OTTYA;
-                                        else if(p[1] == 'b')
-                                                return PROMDEV_OTTYB;
-                                }
-                        }
-                } else {
-                        switch(*romvec->pv_stdin) {
-                        case PROMDEV_TTYA:      return PROMDEV_OTTYA;
-                        case PROMDEV_TTYB:      return PROMDEV_OTTYB;
-                        };
-                }
-                break;
-        default:
-                ;
-        };
-        return PROMDEV_O_UNK;
-}
diff --git a/arch/sparc/prom/misc.c b/arch/sparc/prom/misc.c
index 1942c7c05cb1..37cff5f54704 100644
--- a/arch/sparc/prom/misc.c
+++ b/arch/sparc/prom/misc.c
@@ -58,7 +58,7 @@ prom_cmdline(void)
         extern void install_linux_ticker(void);
         unsigned long flags;
 
-        if(!serial_console && prom_palette)
+        if (prom_palette)
                 prom_palette (1);
         spin_lock_irqsave(&prom_lock, flags);
         install_obp_ticker();
@@ -69,7 +69,7 @@ prom_cmdline(void)
 #ifdef CONFIG_SUN_AUXIO
         set_auxio(AUXIO_LED, 0);
 #endif
-        if(!serial_console && prom_palette)
+        if (prom_palette)
                 prom_palette (0);
 }
 
diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig
index df6ee71894d1..33dabf588bdd 100644
--- a/arch/sparc64/Kconfig
+++ b/arch/sparc64/Kconfig
@@ -23,6 +23,10 @@ config GENERIC_TIME
         bool
         default y
 
+config GENERIC_CMOS_UPDATE
+        bool
+        default y
+
 config GENERIC_CLOCKEVENTS
         bool
         default y
@@ -65,6 +69,9 @@ config AUDIT_ARCH
 config ARCH_NO_VIRT_TO_BUS
         def_bool y
 
+config OF
+        def_bool y
+
 choice
         prompt "Kernel page size"
         default SPARC64_PAGE_SIZE_8KB
diff --git a/arch/sparc64/defconfig b/arch/sparc64/defconfig
index 45ebf91a280c..10e301970a44 100644
--- a/arch/sparc64/defconfig
+++ b/arch/sparc64/defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
 # Linux kernel version: 2.6.22
-# Tue Jul 17 01:19:52 2007
+# Thu Jul 19 21:30:37 2007
 #
 CONFIG_SPARC=y
 CONFIG_SPARC64=y
@@ -16,6 +16,7 @@ CONFIG_ARCH_MAY_HAVE_PC_FDC=y
 # CONFIG_ARCH_HAS_ILOG2_U32 is not set
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
 CONFIG_AUDIT_ARCH=y
+CONFIG_ARCH_NO_VIRT_TO_BUS=y
 CONFIG_SPARC64_PAGE_SIZE_8KB=y
 # CONFIG_SPARC64_PAGE_SIZE_64KB is not set
 # CONFIG_SPARC64_PAGE_SIZE_512KB is not set
@@ -148,7 +149,6 @@ CONFIG_SPLIT_PTLOCK_CPUS=4
 CONFIG_RESOURCES_64BIT=y
 CONFIG_ZONE_DMA_FLAG=0
 CONFIG_NR_QUICK=1
-CONFIG_VIRT_TO_BUS=y
 CONFIG_SBUS=y
 CONFIG_SBUSCHAR=y
 CONFIG_SUN_AUXIO=y
@@ -317,7 +317,6 @@ CONFIG_CONNECTOR=m
 # CONFIG_PARPORT is not set
 CONFIG_BLK_DEV=y
 # CONFIG_BLK_DEV_FD is not set
-# CONFIG_BLK_CPQ_DA is not set
 # CONFIG_BLK_CPQ_CISS_DA is not set
 # CONFIG_BLK_DEV_DAC960 is not set
 # CONFIG_BLK_DEV_UMEM is not set
@@ -470,10 +469,6 @@ CONFIG_ISCSI_TCP=m
 # CONFIG_SCSI_SUNESP is not set
 # CONFIG_SCSI_SRP is not set
 # CONFIG_ATA is not set
-
-#
-# Multi-device support (RAID and LVM)
-#
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=m
 CONFIG_MD_LINEAR=m
@@ -610,10 +605,6 @@ CONFIG_SLHC=m
 # CONFIG_NETCONSOLE is not set
 # CONFIG_NETPOLL is not set
 # CONFIG_NET_POLL_CONTROLLER is not set
-
-#
-# ISDN subsystem
-#
 # CONFIG_ISDN is not set
 # CONFIG_PHONE is not set
 
@@ -782,6 +773,7 @@ CONFIG_I2C_ALGOBIT=y
 CONFIG_HWMON=y
 # CONFIG_HWMON_VID is not set
 # CONFIG_SENSORS_ABITUGURU is not set
+# CONFIG_SENSORS_ABITUGURU3 is not set
 # CONFIG_SENSORS_AD7418 is not set
 # CONFIG_SENSORS_ADM1021 is not set
 # CONFIG_SENSORS_ADM1025 is not set
@@ -808,11 +800,13 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_LM87 is not set
 # CONFIG_SENSORS_LM90 is not set
 # CONFIG_SENSORS_LM92 is not set
+# CONFIG_SENSORS_LM93 is not set
 # CONFIG_SENSORS_MAX1619 is not set
 # CONFIG_SENSORS_MAX6650 is not set
 # CONFIG_SENSORS_PC87360 is not set
 # CONFIG_SENSORS_PC87427 is not set
 # CONFIG_SENSORS_SIS5595 is not set
+# CONFIG_SENSORS_DME1737 is not set
 # CONFIG_SENSORS_SMSC47M1 is not set
 # CONFIG_SENSORS_SMSC47M192 is not set
 # CONFIG_SENSORS_SMSC47B397 is not set
@@ -906,6 +900,7 @@ CONFIG_FB_RADEON_I2C=y
 # CONFIG_PROM_CONSOLE is not set
 CONFIG_DUMMY_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 # CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
 CONFIG_FONTS=y
 # CONFIG_FONT_8x8 is not set
@@ -1196,6 +1191,11 @@ CONFIG_USB_STORAGE=m
 #
 
 #
+# Userspace I/O
+#
+# CONFIG_UIO is not set
+
+#
 # Misc Linux/SPARC drivers
 #
 CONFIG_SUN_OPENPROMIO=m
@@ -1385,6 +1385,7 @@ CONFIG_SCHEDSTATS=y
 # CONFIG_DEBUG_MUTEXES is not set
 # CONFIG_DEBUG_LOCK_ALLOC is not set
 # CONFIG_PROVE_LOCKING is not set
+# CONFIG_LOCK_STAT is not set
 # CONFIG_DEBUG_SPINLOCK_SLEEP is not set
 # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
 # CONFIG_DEBUG_KOBJECT is not set
@@ -1461,6 +1462,7 @@ CONFIG_CRC_CCITT=m
 CONFIG_CRC16=m
 # CONFIG_CRC_ITU_T is not set
 CONFIG_CRC32=y
+# CONFIG_CRC7 is not set
 CONFIG_LIBCRC32C=m
 CONFIG_ZLIB_INFLATE=y
 CONFIG_ZLIB_DEFLATE=y
diff --git a/arch/sparc64/kernel/auxio.c b/arch/sparc64/kernel/auxio.c
index 826118ee53d5..7b379761e9f8 100644
--- a/arch/sparc64/kernel/auxio.c
+++ b/arch/sparc64/kernel/auxio.c
@@ -155,7 +155,7 @@ static struct of_platform_driver auxio_driver = {
 
 static int __init auxio_init(void)
 {
-        return of_register_driver(&auxio_driver, &of_bus_type);
+        return of_register_driver(&auxio_driver, &of_platform_bus_type);
 }
 
 /* Must be after subsys_initcall() so that busses are probed.  Must
diff --git a/arch/sparc64/kernel/ds.c b/arch/sparc64/kernel/ds.c
index fa1f04d756a2..9f472a79d37e 100644
--- a/arch/sparc64/kernel/ds.c
+++ b/arch/sparc64/kernel/ds.c
@@ -13,11 +13,11 @@
 #include <linux/delay.h>
 #include <linux/mutex.h>
 #include <linux/kthread.h>
+#include <linux/reboot.h>
 #include <linux/cpu.h>
 
 #include <asm/ldc.h>
 #include <asm/vio.h>
-#include <asm/power.h>
 #include <asm/mdesc.h>
 #include <asm/head.h>
 #include <asm/irq.h>
@@ -124,10 +124,11 @@ struct ds_data_nack {
         __u64                   result;
 };
 
+struct ds_info;
 struct ds_cap_state {
         __u64                   handle;
 
-        void                    (*data)(struct ldc_channel *lp,
+        void                    (*data)(struct ds_info *dp,
                                         struct ds_cap_state *cp,
                                         void *buf, int len);
 
@@ -139,27 +140,27 @@ struct ds_cap_state {
 #define CAP_STATE_REGISTERED    0x02
 };
 
-static void md_update_data(struct ldc_channel *lp, struct ds_cap_state *cp,
+static void md_update_data(struct ds_info *dp, struct ds_cap_state *cp,
                            void *buf, int len);
-static void domain_shutdown_data(struct ldc_channel *lp,
+static void domain_shutdown_data(struct ds_info *dp,
                                  struct ds_cap_state *cp,
                                  void *buf, int len);
-static void domain_panic_data(struct ldc_channel *lp,
+static void domain_panic_data(struct ds_info *dp,
                               struct ds_cap_state *cp,
                               void *buf, int len);
 #ifdef CONFIG_HOTPLUG_CPU
-static void dr_cpu_data(struct ldc_channel *lp,
+static void dr_cpu_data(struct ds_info *dp,
                         struct ds_cap_state *cp,
                         void *buf, int len);
 #endif
-static void ds_pri_data(struct ldc_channel *lp,
+static void ds_pri_data(struct ds_info *dp,
                         struct ds_cap_state *cp,
                         void *buf, int len);
-static void ds_var_data(struct ldc_channel *lp,
+static void ds_var_data(struct ds_info *dp,
                         struct ds_cap_state *cp,
                         void *buf, int len);
 
-struct ds_cap_state ds_states[] = {
+struct ds_cap_state ds_states_template[] = {
         {
                 .service_id     = "md-update",
                 .data           = md_update_data,
@@ -200,30 +201,38 @@ struct ds_info {
 #define DS_HS_START             0x01
 #define DS_HS_DONE              0x02
 
+        u64                     id;
+
         void                    *rcv_buf;
         int                     rcv_buf_len;
+
+        struct ds_cap_state     *ds_states;
+        int                     num_ds_states;
+
+        struct ds_info          *next;
 };
 
-static struct ds_info *ds_info;
+static struct ds_info *ds_info_list;
 
-static struct ds_cap_state *find_cap(u64 handle)
+static struct ds_cap_state *find_cap(struct ds_info *dp, u64 handle)
 {
         unsigned int index = handle >> 32;
 
-        if (index >= ARRAY_SIZE(ds_states))
+        if (index >= dp->num_ds_states)
                 return NULL;
-        return &ds_states[index];
+        return &dp->ds_states[index];
 }
 
-static struct ds_cap_state *find_cap_by_string(const char *name)
+static struct ds_cap_state *find_cap_by_string(struct ds_info *dp,
+                                               const char *name)
 {
         int i;
 
-        for (i = 0; i < ARRAY_SIZE(ds_states); i++) {
-                if (strcmp(ds_states[i].service_id, name))
+        for (i = 0; i < dp->num_ds_states; i++) {
+                if (strcmp(dp->ds_states[i].service_id, name))
                         continue;
 
-                return &ds_states[i];
+                return &dp->ds_states[i];
         }
         return NULL;
 }
@@ -264,10 +273,11 @@ struct ds_md_update_res {
         __u32                           result;
 };
 
-static void md_update_data(struct ldc_channel *lp,
-                           struct ds_cap_state *dp,
+static void md_update_data(struct ds_info *dp,
+                           struct ds_cap_state *cp,
                            void *buf, int len)
 {
+        struct ldc_channel *lp = dp->lp;
         struct ds_data *dpkt = buf;
         struct ds_md_update_req *rp;
         struct {
@@ -277,14 +287,14 @@ static void md_update_data(struct ldc_channel *lp,
 
         rp = (struct ds_md_update_req *) (dpkt + 1);
 
-        printk(KERN_INFO PFX "Machine description update.\n");
+        printk(KERN_INFO "ds-%lu: Machine description update.\n", dp->id);
 
         mdesc_update();
 
         memset(&pkt, 0, sizeof(pkt));
         pkt.data.tag.type = DS_DATA;
         pkt.data.tag.len = sizeof(pkt) - sizeof(struct ds_msg_tag);
-        pkt.data.handle = dp->handle;
+        pkt.data.handle = cp->handle;
         pkt.res.req_num = rp->req_num;
         pkt.res.result = DS_OK;
 
@@ -302,10 +312,11 @@ struct ds_shutdown_res {
         char                            reason[1];
 };
 
-static void domain_shutdown_data(struct ldc_channel *lp,
-                                 struct ds_cap_state *dp,
+static void domain_shutdown_data(struct ds_info *dp,
+                                 struct ds_cap_state *cp,
                                  void *buf, int len)
 {
+        struct ldc_channel *lp = dp->lp;
         struct ds_data *dpkt = buf;
         struct ds_shutdown_req *rp;
         struct {
@@ -315,20 +326,20 @@ static void domain_shutdown_data(struct ldc_channel *lp,
 
         rp = (struct ds_shutdown_req *) (dpkt + 1);
 
-        printk(KERN_ALERT PFX "Shutdown request from "
-               "LDOM manager received.\n");
+        printk(KERN_ALERT "ds-%lu: Shutdown request from "
+               "LDOM manager received.\n", dp->id);
 
         memset(&pkt, 0, sizeof(pkt));
         pkt.data.tag.type = DS_DATA;
         pkt.data.tag.len = sizeof(pkt) - sizeof(struct ds_msg_tag);
-        pkt.data.handle = dp->handle;
+        pkt.data.handle = cp->handle;
         pkt.res.req_num = rp->req_num;
         pkt.res.result = DS_OK;
         pkt.res.reason[0] = 0;
 
         ds_send(lp, &pkt, sizeof(pkt));
 
-        wake_up_powerd();
+        orderly_poweroff(true);
 }
 
 struct ds_panic_req {
@@ -341,10 +352,11 @@ struct ds_panic_res {
         char                            reason[1];
 };
 
-static void domain_panic_data(struct ldc_channel *lp,
-                              struct ds_cap_state *dp,
+static void domain_panic_data(struct ds_info *dp,
+                              struct ds_cap_state *cp,
                               void *buf, int len)
 {
+        struct ldc_channel *lp = dp->lp;
         struct ds_data *dpkt = buf;
         struct ds_panic_req *rp;
         struct {
@@ -354,13 +366,13 @@ static void domain_panic_data(struct ldc_channel *lp,
 
         rp = (struct ds_panic_req *) (dpkt + 1);
 
-        printk(KERN_ALERT PFX "Panic request from "
-               "LDOM manager received.\n");
+        printk(KERN_ALERT "ds-%lu: Panic request from "
+               "LDOM manager received.\n", dp->id);
 
         memset(&pkt, 0, sizeof(pkt));
         pkt.data.tag.type = DS_DATA;
         pkt.data.tag.len = sizeof(pkt) - sizeof(struct ds_msg_tag);
-        pkt.data.handle = dp->handle;
+        pkt.data.handle = cp->handle;
         pkt.res.req_num = rp->req_num;
         pkt.res.result = DS_OK;
         pkt.res.reason[0] = 0;
@@ -403,10 +415,11 @@ struct dr_cpu_resp_entry {
         __u32                           str_off;
 };
 
-static void __dr_cpu_send_error(struct ds_cap_state *cp, struct ds_data *data)
+static void __dr_cpu_send_error(struct ds_info *dp,
+                                struct ds_cap_state *cp,
+                                struct ds_data *data)
 {
         struct dr_cpu_tag *tag = (struct dr_cpu_tag *) (data + 1);
-        struct ds_info *dp = ds_info;
         struct {
                 struct ds_data          data;
                 struct dr_cpu_tag       tag;
@@ -428,12 +441,14 @@ static void __dr_cpu_send_error(struct ds_cap_state *cp, struct ds_data *data)
         __ds_send(dp->lp, &pkt, msg_len);
 }
 
-static void dr_cpu_send_error(struct ds_cap_state *cp, struct ds_data *data)
+static void dr_cpu_send_error(struct ds_info *dp,
+                              struct ds_cap_state *cp,
+                              struct ds_data *data)
 {
         unsigned long flags;
 
         spin_lock_irqsave(&ds_lock, flags);
-        __dr_cpu_send_error(cp, data);
+        __dr_cpu_send_error(dp, cp, data);
         spin_unlock_irqrestore(&ds_lock, flags);
 }
 
@@ -511,7 +526,9 @@ static void dr_cpu_mark(struct ds_data *resp, int cpu, int ncpus,
         }
 }
 
-static int dr_cpu_configure(struct ds_cap_state *cp, u64 req_num,
+static int dr_cpu_configure(struct ds_info *dp,
+                            struct ds_cap_state *cp,
+                            u64 req_num,
                             cpumask_t *mask)
 {
         struct ds_data *resp;
@@ -533,7 +550,8 @@ static int dr_cpu_configure(struct ds_cap_state *cp, u64 req_num,
         for_each_cpu_mask(cpu, *mask) {
                 int err;
 
-                printk(KERN_INFO PFX "Starting cpu %d...\n", cpu);
+                printk(KERN_INFO "ds-%lu: Starting cpu %d...\n",
+                       dp->id, cpu);
                 err = cpu_up(cpu);
                 if (err) {
                         __u32 res = DR_CPU_RES_FAILURE;
@@ -548,14 +566,14 @@ static int dr_cpu_configure(struct ds_cap_state *cp, u64 req_num,
                                 res = DR_CPU_RES_CPU_NOT_RESPONDING;
                         }
 
-                        printk(KERN_INFO PFX "CPU startup failed err=%d\n",
-                               err);
+                        printk(KERN_INFO "ds-%lu: CPU startup failed err=%d\n",
+                               dp->id, err);
                         dr_cpu_mark(resp, cpu, ncpus, res, stat);
                 }
         }
 
         spin_lock_irqsave(&ds_lock, flags);
-        __ds_send(ds_info->lp, resp, resp_len);
+        __ds_send(dp->lp, resp, resp_len);
         spin_unlock_irqrestore(&ds_lock, flags);
 
         kfree(resp);
@@ -566,7 +584,9 @@ static int dr_cpu_configure(struct ds_cap_state *cp, u64 req_num,
         return 0;
 }
 
-static int dr_cpu_unconfigure(struct ds_cap_state *cp, u64 req_num,
+static int dr_cpu_unconfigure(struct ds_info *dp,
+                              struct ds_cap_state *cp,
+                              u64 req_num,
                               cpumask_t *mask)
 {
         struct ds_data *resp;
@@ -586,8 +606,8 @@ static int dr_cpu_unconfigure(struct ds_cap_state *cp, u64 req_num,
         for_each_cpu_mask(cpu, *mask) {
                 int err;
 
-                printk(KERN_INFO PFX "CPU[%d]: Shutting down cpu %d...\n",
-                       smp_processor_id(), cpu);
+                printk(KERN_INFO "ds-%lu: Shutting down cpu %d...\n",
+                       dp->id, cpu);
                 err = cpu_down(cpu);
                 if (err)
                         dr_cpu_mark(resp, cpu, ncpus,
@@ -596,7 +616,7 @@ static int dr_cpu_unconfigure(struct ds_cap_state *cp, u64 req_num,
         }
 
         spin_lock_irqsave(&ds_lock, flags);
-        __ds_send(ds_info->lp, resp, resp_len);
+        __ds_send(dp->lp, resp, resp_len);
         spin_unlock_irqrestore(&ds_lock, flags);
 
         kfree(resp);
@@ -604,7 +624,7 @@ static int dr_cpu_unconfigure(struct ds_cap_state *cp, u64 req_num,
         return 0;
 }
 
-static void dr_cpu_data(struct ldc_channel *lp,
+static void dr_cpu_data(struct ds_info *dp,
                         struct ds_cap_state *cp,
                         void *buf, int len)
 {
@@ -623,7 +643,7 @@ static void dr_cpu_data(struct ldc_channel *lp,
                 break;
 
         default:
-                dr_cpu_send_error(cp, data);
+                dr_cpu_send_error(dp, cp, data);
                 return;
         }
 
@@ -639,12 +659,12 @@ static void dr_cpu_data(struct ldc_channel *lp,
         }
 
         if (tag->type == DR_CPU_CONFIGURE)
-                err = dr_cpu_configure(cp, req_num, &mask);
+                err = dr_cpu_configure(dp, cp, req_num, &mask);
         else
-                err = dr_cpu_unconfigure(cp, req_num, &mask);
+                err = dr_cpu_unconfigure(dp, cp, req_num, &mask);
 
         if (err)
-                dr_cpu_send_error(cp, data);
+                dr_cpu_send_error(dp, cp, data);
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
@@ -656,8 +676,8 @@ struct ds_pri_msg {
 #define DS_PRI_UPDATE                   0x02
 };
 
-static void ds_pri_data(struct ldc_channel *lp,
-                        struct ds_cap_state *dp,
+static void ds_pri_data(struct ds_info *dp,
+                        struct ds_cap_state *cp,
                         void *buf, int len)
 {
         struct ds_data *dpkt = buf;
@@ -665,8 +685,8 @@ static void ds_pri_data(struct ldc_channel *lp,
 
         rp = (struct ds_pri_msg *) (dpkt + 1);
 
-        printk(KERN_INFO PFX "PRI REQ [%lx:%lx], len=%d\n",
-               rp->req_num, rp->type, len);
+        printk(KERN_INFO "ds-%lu: PRI REQ [%lx:%lx], len=%d\n",
+               dp->id, rp->req_num, rp->type, len);
 }
 
 struct ds_var_hdr {
@@ -701,8 +721,8 @@ static DEFINE_MUTEX(ds_var_mutex);
 static int ds_var_doorbell;
 static int ds_var_response;
 
-static void ds_var_data(struct ldc_channel *lp,
-                        struct ds_cap_state *dp,
+static void ds_var_data(struct ds_info *dp,
+                        struct ds_cap_state *cp,
                         void *buf, int len)
 {
         struct ds_data *dpkt = buf;
@@ -721,14 +741,35 @@ static void ds_var_data(struct ldc_channel *lp,
 
 void ldom_set_var(const char *var, const char *value)
 {
-        struct ds_info *dp = ds_info;
         struct ds_cap_state *cp;
+        struct ds_info *dp;
+        unsigned long flags;
 
-        cp = find_cap_by_string("var-config");
-        if (cp->state != CAP_STATE_REGISTERED)
-                cp = find_cap_by_string("var-config-backup");
+        spin_lock_irqsave(&ds_lock, flags);
+        cp = NULL;
+        for (dp = ds_info_list; dp; dp = dp->next) {
+                struct ds_cap_state *tmp;
 
-        if (cp->state == CAP_STATE_REGISTERED) {
+                tmp = find_cap_by_string(dp, "var-config");
+                if (tmp && tmp->state == CAP_STATE_REGISTERED) {
+                        cp = tmp;
+                        break;
+                }
+        }
+        if (!cp) {
+                for (dp = ds_info_list; dp; dp = dp->next) {
+                        struct ds_cap_state *tmp;
+
+                        tmp = find_cap_by_string(dp, "var-config-backup");
+                        if (tmp && tmp->state == CAP_STATE_REGISTERED) {
+                                cp = tmp;
+                                break;
+                        }
+                }
+        }
+        spin_unlock_irqrestore(&ds_lock, flags);
+
+        if (cp) {
                 union {
                         struct {
                                 struct ds_data          data;
@@ -736,7 +777,6 @@ void ldom_set_var(const char *var, const char *value)
                         } header;
                         char                    all[512];
                 } pkt;
-                unsigned long flags;
                 char  *base, *p;
                 int msg_len, loops;
 
@@ -777,9 +817,9 @@ void ldom_set_var(const char *var, const char *value)
 
                 if (ds_var_doorbell == 0 ||
                     ds_var_response != DS_VAR_SUCCESS)
-                        printk(KERN_ERR PFX "var-config [%s:%s] "
+                        printk(KERN_ERR "ds-%lu: var-config [%s:%s] "
                                "failed, response(%d).\n",
-                               var, value,
+                               dp->id, var, value,
                                ds_var_response);
         } else {
                 printk(KERN_ERR PFX "var-config not registered so "
@@ -811,8 +851,8 @@ void ldom_power_off(void)
 
 static void ds_conn_reset(struct ds_info *dp)
 {
-        printk(KERN_ERR PFX "ds_conn_reset() from %p\n",
-               __builtin_return_address(0));
+        printk(KERN_ERR "ds-%lu: ds_conn_reset() from %p\n",
+               dp->id, __builtin_return_address(0));
 }
 
 static int register_services(struct ds_info *dp)
@@ -820,12 +860,12 @@ static int register_services(struct ds_info *dp)
         struct ldc_channel *lp = dp->lp;
         int i;
 
-        for (i = 0; i < ARRAY_SIZE(ds_states); i++) {
+        for (i = 0; i < dp->num_ds_states; i++) {
                 struct {
                         struct ds_reg_req req;
                         u8 id_buf[256];
                 } pbuf;
-                struct ds_cap_state *cp = &ds_states[i];
+                struct ds_cap_state *cp = &dp->ds_states[i];
                 int err, msg_len;
                 u64 new_count;
 
@@ -870,28 +910,26 @@ static int ds_handshake(struct ds_info *dp, struct ds_msg_tag *pkt)
 
         if (pkt->type == DS_REG_ACK) {
                 struct ds_reg_ack *ap = (struct ds_reg_ack *) pkt;
-                struct ds_cap_state *cp = find_cap(ap->handle);
+                struct ds_cap_state *cp = find_cap(dp, ap->handle);
 
                 if (!cp) {
-                        printk(KERN_ERR PFX "REG ACK for unknown handle %lx\n",
-                               ap->handle);
+                        printk(KERN_ERR "ds-%lu: REG ACK for unknown "
+                               "handle %lx\n", dp->id, ap->handle);
                         return 0;
                 }
-                printk(KERN_INFO PFX "Registered %s service.\n",
-                       cp->service_id);
+                printk(KERN_INFO "ds-%lu: Registered %s service.\n",
+                       dp->id, cp->service_id);
                 cp->state = CAP_STATE_REGISTERED;
         } else if (pkt->type == DS_REG_NACK) {
                 struct ds_reg_nack *np = (struct ds_reg_nack *) pkt;
-                struct ds_cap_state *cp = find_cap(np->handle);
+                struct ds_cap_state *cp = find_cap(dp, np->handle);
 
                 if (!cp) {
-                        printk(KERN_ERR PFX "REG NACK for "
+                        printk(KERN_ERR "ds-%lu: REG NACK for "
                                "unknown handle %lx\n",
-                               np->handle);
+                               dp->id, np->handle);
                         return 0;
                 }
-                printk(KERN_INFO PFX "Could not register %s service\n",
-                       cp->service_id);
                 cp->state = CAP_STATE_UNKNOWN;
         }
 
@@ -922,6 +960,7 @@ static DECLARE_WAIT_QUEUE_HEAD(ds_wait);
 
 struct ds_queue_entry {
         struct list_head                list;
+        struct ds_info                  *dp;
         int                             req_len;
         int                             __pad;
         u64                             req[0];
@@ -930,7 +969,6 @@ struct ds_queue_entry {
 static void process_ds_work(void)
 {
         struct ds_queue_entry *qp, *tmp;
-        static struct ds_info *dp;
         unsigned long flags;
         LIST_HEAD(todo);
 
@@ -939,22 +977,22 @@ static void process_ds_work(void)
         INIT_LIST_HEAD(&ds_work_list);
         spin_unlock_irqrestore(&ds_lock, flags);
 
-        dp = ds_info;
-
         list_for_each_entry_safe(qp, tmp, &todo, list) {
                 struct ds_data *dpkt = (struct ds_data *) qp->req;
-                struct ds_cap_state *cp = find_cap(dpkt->handle);
+                struct ds_info *dp = qp->dp;
+                struct ds_cap_state *cp = find_cap(dp, dpkt->handle);
                 int req_len = qp->req_len;
 
                 if (!cp) {
-                        printk(KERN_ERR PFX "Data for unknown handle %lu\n",
-                               dpkt->handle);
+                        printk(KERN_ERR "ds-%lu: Data for unknown "
+                               "handle %lu\n",
+                               dp->id, dpkt->handle);
 
                         spin_lock_irqsave(&ds_lock, flags);
                         __send_ds_nack(dp, dpkt->handle);
                         spin_unlock_irqrestore(&ds_lock, flags);
                 } else {
-                        cp->data(dp->lp, cp, dpkt, req_len);
+                        cp->data(dp, cp, dpkt, req_len);
                 }
 
                 list_del(&qp->list);
@@ -990,6 +1028,7 @@ static int ds_data(struct ds_info *dp, struct ds_msg_tag *pkt, int len)
         if (!qp) {
                 __send_ds_nack(dp, dpkt->handle);
         } else {
+                qp->dp = dp;
                 memcpy(&qp->req, pkt, len);
                 list_add_tail(&qp->list, &ds_work_list);
                 wake_up(&ds_wait);
@@ -1019,8 +1058,8 @@ static void ds_reset(struct ds_info *dp)
 
         dp->hs_state = 0;
 
-        for (i = 0; i < ARRAY_SIZE(ds_states); i++) {
-                struct ds_cap_state *cp = &ds_states[i];
+        for (i = 0; i < dp->num_ds_states; i++) {
+                struct ds_cap_state *cp = &dp->ds_states[i];
 
                 cp->state = CAP_STATE_UNKNOWN;
         }
@@ -1048,7 +1087,8 @@ static void ds_event(void *arg, int event)
         }
 
         if (event != LDC_EVENT_DATA_READY) {
-                printk(KERN_WARNING PFX "Unexpected LDC event %d\n", event);
+                printk(KERN_WARNING "ds-%lu: Unexpected LDC event %d\n",
+                       dp->id, event);
                 spin_unlock_irqrestore(&ds_lock, flags);
                 return;
         }
@@ -1099,9 +1139,11 @@ static int __devinit ds_probe(struct vio_dev *vdev,
                 .mtu            = 4096,
                 .mode           = LDC_MODE_STREAM,
         };
+        struct mdesc_handle *hp;
         struct ldc_channel *lp;
         struct ds_info *dp;
-        int err;
+        const u64 *val;
+        int err, i;
 
         if (ds_version_printed++ == 0)
                 printk(KERN_INFO "%s", version);
@@ -1111,19 +1153,37 @@ static int __devinit ds_probe(struct vio_dev *vdev,
         if (!dp)
                 goto out_err;
 
+        hp = mdesc_grab();
+        val = mdesc_get_property(hp, vdev->mp, "id", NULL);
+        if (val)
+                dp->id = *val;
+        mdesc_release(hp);
+
         dp->rcv_buf = kzalloc(4096, GFP_KERNEL);
         if (!dp->rcv_buf)
                 goto out_free_dp;
 
         dp->rcv_buf_len = 4096;
 
+        dp->ds_states = kzalloc(sizeof(ds_states_template),
+                                GFP_KERNEL);
+        if (!dp->ds_states)
+                goto out_free_rcv_buf;
+
+        memcpy(dp->ds_states, ds_states_template,
+               sizeof(ds_states_template));
+        dp->num_ds_states = ARRAY_SIZE(ds_states_template);
+
+        for (i = 0; i < dp->num_ds_states; i++)
+                dp->ds_states[i].handle = ((u64)i << 32);
+
         ds_cfg.tx_irq = vdev->tx_irq;
         ds_cfg.rx_irq = vdev->rx_irq;
 
         lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp);
         if (IS_ERR(lp)) {
                 err = PTR_ERR(lp);
-                goto out_free_rcv_buf;
+                goto out_free_ds_states;
         }
         dp->lp = lp;
 
@@ -1131,15 +1191,19 @@ static int __devinit ds_probe(struct vio_dev *vdev,
         if (err)
                 goto out_free_ldc;
 
-        ds_info = dp;
-
-        start_powerd();
+        spin_lock_irq(&ds_lock);
+        dp->next = ds_info_list;
+        ds_info_list = dp;
+        spin_unlock_irq(&ds_lock);
 
         return err;
 
 out_free_ldc:
         ldc_free(dp->lp);
 
+out_free_ds_states:
+        kfree(dp->ds_states);
+
 out_free_rcv_buf:
         kfree(dp->rcv_buf);
 
@@ -1174,11 +1238,6 @@ static struct vio_driver ds_driver = {
 
 static int __init ds_init(void)
 {
-        int i;
-
-        for (i = 0; i < ARRAY_SIZE(ds_states); i++)
-                ds_states[i].handle = ((u64)i << 32);
-
         kthread_run(ds_thread, NULL, "kldomd");
 
         return vio_register_driver(&ds_driver);
diff --git a/arch/sparc64/kernel/ebus.c b/arch/sparc64/kernel/ebus.c
index ad55a9bb50dd..6d2956179cde 100644
--- a/arch/sparc64/kernel/ebus.c
+++ b/arch/sparc64/kernel/ebus.c
@@ -362,6 +362,7 @@ static int __init child_regs_nonstandard(struct linux_ebus_device *dev)
 static void __init fill_ebus_device(struct device_node *dp, struct linux_ebus_device *dev)
 {
         struct linux_ebus_child *child;
+        struct dev_archdata *sd;
         struct of_device *op;
         int i, len;
 
@@ -387,6 +388,10 @@ static void __init fill_ebus_device(struct device_node *dp, struct linux_ebus_de
                         dev->irqs[i] = op->irqs[i];
         }
 
+        sd = &dev->ofdev.dev.archdata;
+        sd->prom_node = dp;
+        sd->op = &dev->ofdev;
+
         dev->ofdev.node = dp;
         dev->ofdev.dev.parent = &dev->bus->ofdev.dev;
         dev->ofdev.dev.bus = &ebus_bus_type;
diff --git a/arch/sparc64/kernel/head.S b/arch/sparc64/kernel/head.S
index 77259526cb15..35feacb6b8ec 100644
--- a/arch/sparc64/kernel/head.S
+++ b/arch/sparc64/kernel/head.S
@@ -458,7 +458,6 @@ tlb_fixup_done:
         or      %g6, %lo(init_thread_union), %g6
         ldx     [%g6 + TI_TASK], %g4
         mov     %sp, %l6
-        mov     %o4, %l7
 
         wr      %g0, ASI_P, %asi
         mov     1, %g1
diff --git a/arch/sparc64/kernel/irq.c b/arch/sparc64/kernel/irq.c
index 8cb3358674f5..db31bf6b42db 100644
--- a/arch/sparc64/kernel/irq.c
+++ b/arch/sparc64/kernel/irq.c
@@ -87,7 +87,11 @@ struct ino_bucket ivector_table[NUM_IVECS] __attribute__ ((aligned (SMP_CACHE_BY
  */
 #define irq_work(__cpu) &(trap_block[(__cpu)].irq_worklist)
 
-static unsigned int virt_to_real_irq_table[NR_IRQS];
+static struct {
+        unsigned int irq;
+        unsigned int dev_handle;
+        unsigned int dev_ino;
+} virt_to_real_irq_table[NR_IRQS];
 
 static unsigned char virt_irq_alloc(unsigned int real_irq)
 {
@@ -96,7 +100,7 @@ static unsigned char virt_irq_alloc(unsigned int real_irq)
         BUILD_BUG_ON(NR_IRQS >= 256);
 
         for (ent = 1; ent < NR_IRQS; ent++) {
-                if (!virt_to_real_irq_table[ent])
+                if (!virt_to_real_irq_table[ent].irq)
                         break;
         }
         if (ent >= NR_IRQS) {
@@ -104,7 +108,7 @@ static unsigned char virt_irq_alloc(unsigned int real_irq)
                 return 0;
         }
 
-        virt_to_real_irq_table[ent] = real_irq;
+        virt_to_real_irq_table[ent].irq = real_irq;
 
         return ent;
 }
@@ -117,8 +121,8 @@ static void virt_irq_free(unsigned int virt_irq)
         if (virt_irq >= NR_IRQS)
                 return;
 
-        real_irq = virt_to_real_irq_table[virt_irq];
-        virt_to_real_irq_table[virt_irq] = 0;
+        real_irq = virt_to_real_irq_table[virt_irq].irq;
+        virt_to_real_irq_table[virt_irq].irq = 0;
 
         __bucket(real_irq)->virt_irq = 0;
 }
@@ -126,7 +130,7 @@ static void virt_irq_free(unsigned int virt_irq)
 
 static unsigned int virt_to_real_irq(unsigned char virt_irq)
 {
-        return virt_to_real_irq_table[virt_irq];
+        return virt_to_real_irq_table[virt_irq].irq;
 }
 
 /*
@@ -336,15 +340,15 @@ static void sun4v_irq_enable(unsigned int virt_irq)
 
                 err = sun4v_intr_settarget(ino, cpuid);
                 if (err != HV_EOK)
-                        printk("sun4v_intr_settarget(%x,%lu): err(%d)\n",
-                               ino, cpuid, err);
+                        printk(KERN_ERR "sun4v_intr_settarget(%x,%lu): "
+                               "err(%d)\n", ino, cpuid, err);
                 err = sun4v_intr_setstate(ino, HV_INTR_STATE_IDLE);
                 if (err != HV_EOK)
-                        printk("sun4v_intr_setstate(%x): "
+                        printk(KERN_ERR "sun4v_intr_setstate(%x): "
                                "err(%d)\n", ino, err);
                 err = sun4v_intr_setenabled(ino, HV_INTR_ENABLED);
                 if (err != HV_EOK)
-                        printk("sun4v_intr_setenabled(%x): err(%d)\n",
+                        printk(KERN_ERR "sun4v_intr_setenabled(%x): err(%d)\n",
                                ino, err);
         }
 }
@@ -362,8 +366,8 @@ static void sun4v_set_affinity(unsigned int virt_irq, cpumask_t mask)
 
                 err = sun4v_intr_settarget(ino, cpuid);
                 if (err != HV_EOK)
-                        printk("sun4v_intr_settarget(%x,%lu): err(%d)\n",
-                               ino, cpuid, err);
+                        printk(KERN_ERR "sun4v_intr_settarget(%x,%lu): "
+                               "err(%d)\n", ino, cpuid, err);
         }
 }
 
@@ -377,7 +381,7 @@ static void sun4v_irq_disable(unsigned int virt_irq)
 
                 err = sun4v_intr_setenabled(ino, HV_INTR_DISABLED);
                 if (err != HV_EOK)
-                        printk("sun4v_intr_setenabled(%x): "
+                        printk(KERN_ERR "sun4v_intr_setenabled(%x): "
                                "err(%d)\n", ino, err);
         }
 }
@@ -410,7 +414,7 @@ static void sun4v_irq_end(unsigned int virt_irq)
 
                 err = sun4v_intr_setstate(ino, HV_INTR_STATE_IDLE);
                 if (err != HV_EOK)
-                        printk("sun4v_intr_setstate(%x): "
+                        printk(KERN_ERR "sun4v_intr_setstate(%x): "
                                "err(%d)\n", ino, err);
         }
 }
@@ -418,7 +422,6 @@ static void sun4v_irq_end(unsigned int virt_irq)
 static void sun4v_virq_enable(unsigned int virt_irq)
 {
         struct ino_bucket *bucket = virt_irq_to_bucket(virt_irq);
-        unsigned int ino = bucket - &ivector_table[0];
 
         if (likely(bucket)) {
                 unsigned long cpuid, dev_handle, dev_ino;
@@ -426,24 +429,24 @@ static void sun4v_virq_enable(unsigned int virt_irq)
 
                 cpuid = irq_choose_cpu(virt_irq);
 
-                dev_handle = ino & IMAP_IGN;
-                dev_ino = ino & IMAP_INO;
+                dev_handle = virt_to_real_irq_table[virt_irq].dev_handle;
+                dev_ino = virt_to_real_irq_table[virt_irq].dev_ino;
 
                 err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid);
                 if (err != HV_EOK)
-                        printk("sun4v_vintr_set_target(%lx,%lx,%lu): "
+                        printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): "
                                "err(%d)\n",
                                dev_handle, dev_ino, cpuid, err);
                 err = sun4v_vintr_set_state(dev_handle, dev_ino,
                                             HV_INTR_STATE_IDLE);
                 if (err != HV_EOK)
-                        printk("sun4v_vintr_set_state(%lx,%lx,"
+                        printk(KERN_ERR "sun4v_vintr_set_state(%lx,%lx,"
                                 "HV_INTR_STATE_IDLE): err(%d)\n",
                                dev_handle, dev_ino, err);
                 err = sun4v_vintr_set_valid(dev_handle, dev_ino,
                                             HV_INTR_ENABLED);
                 if (err != HV_EOK)
-                        printk("sun4v_vintr_set_state(%lx,%lx,"
+                        printk(KERN_ERR "sun4v_vintr_set_state(%lx,%lx,"
                                "HV_INTR_ENABLED): err(%d)\n",
                                dev_handle, dev_ino, err);
         }
@@ -452,7 +455,6 @@ static void sun4v_virq_enable(unsigned int virt_irq)
 static void sun4v_virt_set_affinity(unsigned int virt_irq, cpumask_t mask)
 {
         struct ino_bucket *bucket = virt_irq_to_bucket(virt_irq);
-        unsigned int ino = bucket - &ivector_table[0];
 
         if (likely(bucket)) {
                 unsigned long cpuid, dev_handle, dev_ino;
@@ -460,12 +462,12 @@ static void sun4v_virt_set_affinity(unsigned int virt_irq, cpumask_t mask)
 
                 cpuid = irq_choose_cpu(virt_irq);
 
-                dev_handle = ino & IMAP_IGN;
-                dev_ino = ino & IMAP_INO;
+                dev_handle = virt_to_real_irq_table[virt_irq].dev_handle;
+                dev_ino = virt_to_real_irq_table[virt_irq].dev_ino;
 
                 err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid);
                 if (err != HV_EOK)
-                        printk("sun4v_vintr_set_target(%lx,%lx,%lu): "
+                        printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): "
                                "err(%d)\n",
                                dev_handle, dev_ino, cpuid, err);
         }
@@ -474,19 +476,18 @@ static void sun4v_virt_set_affinity(unsigned int virt_irq, cpumask_t mask)
 static void sun4v_virq_disable(unsigned int virt_irq)
 {
         struct ino_bucket *bucket = virt_irq_to_bucket(virt_irq);
-        unsigned int ino = bucket - &ivector_table[0];
 
         if (likely(bucket)) {
                 unsigned long dev_handle, dev_ino;
                 int err;
 
-                dev_handle = ino & IMAP_IGN;
-                dev_ino = ino & IMAP_INO;
+                dev_handle = virt_to_real_irq_table[virt_irq].dev_handle;
+                dev_ino = virt_to_real_irq_table[virt_irq].dev_ino;
 
                 err = sun4v_vintr_set_valid(dev_handle, dev_ino,
                                             HV_INTR_DISABLED);
                 if (err != HV_EOK)
-                        printk("sun4v_vintr_set_state(%lx,%lx,"
+                        printk(KERN_ERR "sun4v_vintr_set_state(%lx,%lx,"
                                "HV_INTR_DISABLED): err(%d)\n",
                                dev_handle, dev_ino, err);
         }
@@ -495,7 +496,6 @@ static void sun4v_virq_disable(unsigned int virt_irq)
 static void sun4v_virq_end(unsigned int virt_irq)
 {
         struct ino_bucket *bucket = virt_irq_to_bucket(virt_irq);
-        unsigned int ino = bucket - &ivector_table[0];
         struct irq_desc *desc = irq_desc + virt_irq;
 
         if (unlikely(desc->status & (IRQ_DISABLED|IRQ_INPROGRESS)))
@@ -505,13 +505,13 @@ static void sun4v_virq_end(unsigned int virt_irq)
                 unsigned long dev_handle, dev_ino;
                 int err;
 
-                dev_handle = ino & IMAP_IGN;
-                dev_ino = ino & IMAP_INO;
+                dev_handle = virt_to_real_irq_table[virt_irq].dev_handle;
+                dev_ino = virt_to_real_irq_table[virt_irq].dev_ino;
 
                 err = sun4v_vintr_set_state(dev_handle, dev_ino,
                                             HV_INTR_STATE_IDLE);
                 if (err != HV_EOK)
-                        printk("sun4v_vintr_set_state(%lx,%lx,"
+                        printk(KERN_ERR "sun4v_vintr_set_state(%lx,%lx,"
                                 "HV_INTR_STATE_IDLE): err(%d)\n",
                                dev_handle, dev_ino, err);
         }
@@ -700,11 +700,12 @@ unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino)
 unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino)
 {
         unsigned long sysino, hv_err;
+        unsigned int virq;
 
-        BUG_ON(devhandle & ~IMAP_IGN);
-        BUG_ON(devino & ~IMAP_INO);
+        BUG_ON(devhandle & devino);
 
         sysino = devhandle | devino;
+        BUG_ON(sysino & ~(IMAP_IGN | IMAP_INO));
 
         hv_err = sun4v_vintr_set_cookie(devhandle, devino, sysino);
         if (hv_err) {
@@ -713,7 +714,12 @@ unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino)
                 prom_halt();
         }
 
-        return sun4v_build_common(sysino, &sun4v_virq);
+        virq = sun4v_build_common(sysino, &sun4v_virq);
+
+        virt_to_real_irq_table[virq].dev_handle = devhandle;
+        virt_to_real_irq_table[virq].dev_ino = devino;
+
+        return virq;
 }
 
 #ifdef CONFIG_PCI_MSI
diff --git a/arch/sparc64/kernel/isa.c b/arch/sparc64/kernel/isa.c
index 6a6882e57ff2..1a1043fcf97d 100644
--- a/arch/sparc64/kernel/isa.c
+++ b/arch/sparc64/kernel/isa.c
@@ -79,6 +79,7 @@ static void __init isa_fill_devices(struct sparc_isa_bridge *isa_br)
 
         while (dp) {
                 struct sparc_isa_device *isa_dev;
+                struct dev_archdata *sd;
 
                 isa_dev = kzalloc(sizeof(*isa_dev), GFP_KERNEL);
                 if (!isa_dev) {
@@ -86,6 +87,10 @@ static void __init isa_fill_devices(struct sparc_isa_bridge *isa_br)
                         return;
                 }
 
+                sd = &isa_dev->ofdev.dev.archdata;
+                sd->prom_node = dp;
+                sd->op = &isa_dev->ofdev;
+
                 isa_dev->ofdev.node = dp;
                 isa_dev->ofdev.dev.parent = &isa_br->ofdev.dev;
                 isa_dev->ofdev.dev.bus = &isa_bus_type;
diff --git a/arch/sparc64/kernel/mdesc.c b/arch/sparc64/kernel/mdesc.c
index 302ba5e5a0bb..cce4d0ddf5d5 100644
--- a/arch/sparc64/kernel/mdesc.c
+++ b/arch/sparc64/kernel/mdesc.c
@@ -83,7 +83,7 @@ static void mdesc_handle_init(struct mdesc_handle *hp,
         hp->handle_size = handle_size;
 }
 
-static struct mdesc_handle *mdesc_bootmem_alloc(unsigned int mdesc_size)
+static struct mdesc_handle * __init mdesc_bootmem_alloc(unsigned int mdesc_size)
 {
         struct mdesc_handle *hp;
         unsigned int handle_size, alloc_size;
@@ -123,7 +123,7 @@ static void mdesc_bootmem_free(struct mdesc_handle *hp)
         }
 }
 
-static struct mdesc_mem_ops bootmem_mdesc_memops = {
+static struct mdesc_mem_ops bootmem_mdesc_ops = {
         .alloc = mdesc_bootmem_alloc,
         .free  = mdesc_bootmem_free,
 };
@@ -231,6 +231,25 @@ void mdesc_register_notifier(struct mdesc_notifier_client *client)
         mutex_unlock(&mdesc_mutex);
 }
 
+static const u64 *parent_cfg_handle(struct mdesc_handle *hp, u64 node)
+{
+        const u64 *id;
+        u64 a;
+
+        id = NULL;
+        mdesc_for_each_arc(a, hp, node, MDESC_ARC_TYPE_BACK) {
+                u64 target;
+
+                target = mdesc_arc_target(hp, a);
+                id = mdesc_get_property(hp, target,
+                                        "cfg-handle", NULL);
+                if (id)
+                        break;
+        }
+
+        return id;
+}
+
 /* Run 'func' on nodes which are in A but not in B.  */
 static void invoke_on_missing(const char *name,
                               struct mdesc_handle *a,
@@ -240,13 +259,42 @@ static void invoke_on_missing(const char *name,
         u64 node;
 
         mdesc_for_each_node_by_name(a, node, name) {
-                const u64 *id = mdesc_get_property(a, node, "id", NULL);
-                int found = 0;
+                int found = 0, is_vdc_port = 0;
+                const char *name_prop;
+                const u64 *id;
                 u64 fnode;
 
+                name_prop = mdesc_get_property(a, node, "name", NULL);
+                if (name_prop && !strcmp(name_prop, "vdc-port")) {
+                        is_vdc_port = 1;
+                        id = parent_cfg_handle(a, node);
+                } else
+                        id = mdesc_get_property(a, node, "id", NULL);
+
+                if (!id) {
+                        printk(KERN_ERR "MD: Cannot find ID for %s node.\n",
+                               (name_prop ? name_prop : name));
+                        continue;
+                }
+
                 mdesc_for_each_node_by_name(b, fnode, name) {
-                        const u64 *fid = mdesc_get_property(b, fnode,
-                                                            "id", NULL);
+                        const u64 *fid;
+
+                        if (is_vdc_port) {
+                                name_prop = mdesc_get_property(b, fnode,
+                                                               "name", NULL);
+                                if (!name_prop ||
+                                    strcmp(name_prop, "vdc-port"))
+                                        continue;
+                                fid = parent_cfg_handle(b, fnode);
+                                if (!fid) {
+                                        printk(KERN_ERR "MD: Cannot find ID "
+                                               "for vdc-port node.\n");
+                                        continue;
+                                }
+                        } else
+                                fid = mdesc_get_property(b, fnode,
+                                                         "id", NULL);
 
                         if (*id == *fid) {
                                 found = 1;
@@ -812,7 +860,7 @@ void __init sun4v_mdesc_init(void)
 
         printk("MDESC: Size is %lu bytes.\n", len);
 
-        hp = mdesc_alloc(len, &bootmem_mdesc_memops);
+        hp = mdesc_alloc(len, &bootmem_mdesc_ops);
         if (hp == NULL) {
                 prom_printf("MDESC: alloc of %lu bytes failed.\n", len);
                 prom_halt();
diff --git a/arch/sparc64/kernel/of_device.c b/arch/sparc64/kernel/of_device.c
index 6676b93219dc..4cc77485f536 100644
--- a/arch/sparc64/kernel/of_device.c
+++ b/arch/sparc64/kernel/of_device.c
@@ -1,132 +1,13 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
+#include <linux/of.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
 #include <linux/slab.h>
-
-#include <asm/errno.h>
-#include <asm/of_device.h>
-
-/**
- * of_match_device - Tell if an of_device structure has a matching
- * of_match structure
- * @ids: array of of device match structures to search in
- * @dev: the of device structure to match against
- *
- * Used by a driver to check whether an of_device present in the
- * system is in its list of supported devices.
- */
-const struct of_device_id *of_match_device(const struct of_device_id *matches,
-                                        const struct of_device *dev)
-{
-        if (!dev->node)
-                return NULL;
-        while (matches->name[0] || matches->type[0] || matches->compatible[0]) {
-                int match = 1;
-                if (matches->name[0])
-                        match &= dev->node->name
-                                && !strcmp(matches->name, dev->node->name);
-                if (matches->type[0])
-                        match &= dev->node->type
-                                && !strcmp(matches->type, dev->node->type);
-                if (matches->compatible[0])
-                        match &= of_device_is_compatible(dev->node,
-                                                         matches->compatible);
-                if (match)
-                        return matches;
-                matches++;
-        }
-        return NULL;
-}
-
-static int of_platform_bus_match(struct device *dev, struct device_driver *drv)
-{
-        struct of_device * of_dev = to_of_device(dev);
-        struct of_platform_driver * of_drv = to_of_platform_driver(drv);
-        const struct of_device_id * matches = of_drv->match_table;
-
-        if (!matches)
-                return 0;
-
-        return of_match_device(matches, of_dev) != NULL;
-}
-
-struct of_device *of_dev_get(struct of_device *dev)
-{
-        struct device *tmp;
-
-        if (!dev)
-                return NULL;
-        tmp = get_device(&dev->dev);
-        if (tmp)
-                return to_of_device(tmp);
-        else
-                return NULL;
-}
-
-void of_dev_put(struct of_device *dev)
-{
-        if (dev)
-                put_device(&dev->dev);
-}
-
-
-static int of_device_probe(struct device *dev)
-{
-        int error = -ENODEV;
-        struct of_platform_driver *drv;
-        struct of_device *of_dev;
-        const struct of_device_id *match;
-
-        drv = to_of_platform_driver(dev->driver);
-        of_dev = to_of_device(dev);
-
-        if (!drv->probe)
-                return error;
-
-        of_dev_get(of_dev);
-
-        match = of_match_device(drv->match_table, of_dev);
-        if (match)
-                error = drv->probe(of_dev, match);
-        if (error)
-                of_dev_put(of_dev);
-
-        return error;
-}
-
-static int of_device_remove(struct device *dev)
-{
-        struct of_device * of_dev = to_of_device(dev);
-        struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
-
-        if (dev->driver && drv->remove)
-                drv->remove(of_dev);
-        return 0;
-}
-
-static int of_device_suspend(struct device *dev, pm_message_t state)
-{
-        struct of_device * of_dev = to_of_device(dev);
-        struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
-        int error = 0;
-
-        if (dev->driver && drv->suspend)
-                error = drv->suspend(of_dev, state);
-        return error;
-}
-
-static int of_device_resume(struct device * dev)
-{
-        struct of_device * of_dev = to_of_device(dev);
-        struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
-        int error = 0;
-
-        if (dev->driver && drv->resume)
-                error = drv->resume(of_dev);
-        return error;
-}
+#include <linux/errno.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
 
 void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name)
 {
@@ -163,7 +44,7 @@ static int node_match(struct device *dev, void *data)
 
 struct of_device *of_find_device_by_node(struct device_node *dp)
 {
-        struct device *dev = bus_find_device(&of_bus_type, NULL,
+        struct device *dev = bus_find_device(&of_platform_bus_type, NULL,
                                              dp, node_match);
 
         if (dev)
@@ -174,48 +55,20 @@ struct of_device *of_find_device_by_node(struct device_node *dp)
 EXPORT_SYMBOL(of_find_device_by_node);
 
 #ifdef CONFIG_PCI
-struct bus_type isa_bus_type = {
-       .name    = "isa",
-       .match   = of_platform_bus_match,
-       .probe   = of_device_probe,
-       .remove  = of_device_remove,
-       .suspend = of_device_suspend,
-       .resume  = of_device_resume,
-};
+struct bus_type isa_bus_type;
 EXPORT_SYMBOL(isa_bus_type);
 
-struct bus_type ebus_bus_type = {
-       .name    = "ebus",
-       .match   = of_platform_bus_match,
-       .probe   = of_device_probe,
-       .remove  = of_device_remove,
-       .suspend = of_device_suspend,
-       .resume  = of_device_resume,
-};
+struct bus_type ebus_bus_type;
 EXPORT_SYMBOL(ebus_bus_type);
 #endif
 
 #ifdef CONFIG_SBUS
-struct bus_type sbus_bus_type = {
-       .name    = "sbus",
-       .match   = of_platform_bus_match,
-       .probe   = of_device_probe,
-       .remove  = of_device_remove,
-       .suspend = of_device_suspend,
-       .resume  = of_device_resume,
-};
+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);
+struct bus_type of_platform_bus_type;
+EXPORT_SYMBOL(of_platform_bus_type);
 
 static inline u64 of_read_addr(const u32 *cell, int size)
 {
@@ -899,11 +752,16 @@ static struct of_device * __init scan_one_device(struct device_node *dp,
 {
         struct of_device *op = kzalloc(sizeof(*op), GFP_KERNEL);
         const unsigned int *irq;
+        struct dev_archdata *sd;
         int len, i;
 
         if (!op)
                 return NULL;
 
+        sd = &op->dev.archdata;
+        sd->prom_node = dp;
+        sd->op = op;
+
         op->node = dp;
 
         op->clock_freq = of_getintprop_default(dp, "clock-frequency",
@@ -933,7 +791,7 @@ static struct of_device * __init scan_one_device(struct device_node *dp,
                 op->irqs[i] = build_one_device_irq(op, parent, op->irqs[i]);
 
         op->dev.parent = parent;
-        op->dev.bus = &of_bus_type;
+        op->dev.bus = &of_platform_bus_type;
         if (!parent)
                 strcpy(op->dev.bus_id, "root");
         else
@@ -977,16 +835,16 @@ static int __init of_bus_driver_init(void)
 {
         int err;
 
-        err = bus_register(&of_bus_type);
+        err = of_bus_type_init(&of_platform_bus_type, "of");
 #ifdef CONFIG_PCI
         if (!err)
-                err = bus_register(&isa_bus_type);
+                err = of_bus_type_init(&isa_bus_type, "isa");
         if (!err)
-                err = bus_register(&ebus_bus_type);
+                err = of_bus_type_init(&ebus_bus_type, "ebus");
 #endif
 #ifdef CONFIG_SBUS
         if (!err)
-                err = bus_register(&sbus_bus_type);
+                err = of_bus_type_init(&sbus_bus_type, "sbus");
 #endif
 
         if (!err)
@@ -1020,61 +878,13 @@ int of_register_driver(struct of_platform_driver *drv, struct bus_type *bus)
         /* register with core */
         return driver_register(&drv->driver);
 }
+EXPORT_SYMBOL(of_register_driver);
 
 void of_unregister_driver(struct of_platform_driver *drv)
 {
         driver_unregister(&drv->driver);
 }
-
-
-static ssize_t dev_show_devspec(struct device *dev, struct device_attribute *attr, char *buf)
-{
-        struct of_device *ofdev;
-
-        ofdev = to_of_device(dev);
-        return sprintf(buf, "%s", ofdev->node->full_name);
-}
-
-static DEVICE_ATTR(devspec, S_IRUGO, dev_show_devspec, NULL);
-
-/**
- * of_release_dev - free an of device structure when all users of it are finished.
- * @dev: device that's been disconnected
- *
- * Will be called only by the device core when all users of this of device are
- * done.
- */
-void of_release_dev(struct device *dev)
-{
-        struct of_device *ofdev;
-
-        ofdev = to_of_device(dev);
-
-        kfree(ofdev);
-}
-
-int of_device_register(struct of_device *ofdev)
-{
-        int rc;
-
-        BUG_ON(ofdev->node == NULL);
-
-        rc = device_register(&ofdev->dev);
-        if (rc)
-                return rc;
-
-        rc = device_create_file(&ofdev->dev, &dev_attr_devspec);
-        if (rc)
-                device_unregister(&ofdev->dev);
-
-        return rc;
-}
-
-void of_device_unregister(struct of_device *ofdev)
-{
-        device_remove_file(&ofdev->dev, &dev_attr_devspec);
-        device_unregister(&ofdev->dev);
-}
+EXPORT_SYMBOL(of_unregister_driver);
 
 struct of_device* of_platform_device_create(struct device_node *np,
                                             const char *bus_id,
@@ -1100,13 +910,4 @@ struct of_device* of_platform_device_create(struct device_node *np,
 
         return dev;
 }
-
-EXPORT_SYMBOL(of_match_device);
-EXPORT_SYMBOL(of_register_driver);
-EXPORT_SYMBOL(of_unregister_driver);
-EXPORT_SYMBOL(of_device_register);
-EXPORT_SYMBOL(of_device_unregister);
-EXPORT_SYMBOL(of_dev_get);
-EXPORT_SYMBOL(of_dev_put);
 EXPORT_SYMBOL(of_platform_device_create);
-EXPORT_SYMBOL(of_release_dev);
diff --git a/arch/sparc64/kernel/pci_sun4v.c b/arch/sparc64/kernel/pci_sun4v.c
index 6b3fe2c1d65e..639cf06ca372 100644
--- a/arch/sparc64/kernel/pci_sun4v.c
+++ b/arch/sparc64/kernel/pci_sun4v.c
@@ -1129,7 +1129,7 @@ static void pci_sun4v_msi_init(struct pci_pbm_info *pbm)
 }
 #endif /* !(CONFIG_PCI_MSI) */
 
-static void pci_sun4v_pbm_init(struct pci_controller_info *p, struct device_node *dp, u32 devhandle)
+static void __init pci_sun4v_pbm_init(struct pci_controller_info *p, struct device_node *dp, u32 devhandle)
 {
         struct pci_pbm_info *pbm;
 
@@ -1163,7 +1163,7 @@ static void pci_sun4v_pbm_init(struct pci_controller_info *p, struct device_node
         pci_sun4v_msi_init(pbm);
 }
 
-void sun4v_pci_init(struct device_node *dp, char *model_name)
+void __init sun4v_pci_init(struct device_node *dp, char *model_name)
 {
         static int hvapi_negotiated = 0;
         struct pci_controller_info *p;
diff --git a/arch/sparc64/kernel/power.c b/arch/sparc64/kernel/power.c
index 8dd4294ad21e..881a09ee4c4c 100644
--- a/arch/sparc64/kernel/power.c
+++ b/arch/sparc64/kernel/power.c
@@ -12,13 +12,13 @@
 #include <linux/interrupt.h>
 #include <linux/pm.h>
 #include <linux/syscalls.h>
+#include <linux/reboot.h>
 
 #include <asm/system.h>
 #include <asm/auxio.h>
 #include <asm/prom.h>
 #include <asm/of_device.h>
 #include <asm/io.h>
-#include <asm/power.h>
 #include <asm/sstate.h>
 
 #include <linux/unistd.h>
@@ -31,20 +31,9 @@ int scons_pwroff = 1;
 
 static void __iomem *power_reg;
 
-static DECLARE_WAIT_QUEUE_HEAD(powerd_wait);
-static int button_pressed;
-
-void wake_up_powerd(void)
-{
-        if (button_pressed == 0) {
-                button_pressed = 1;
-                wake_up(&powerd_wait);
-        }
-}
-
 static irqreturn_t power_handler(int irq, void *dev_id)
 {
-        wake_up_powerd();
+        orderly_poweroff(true);
 
         /* FIXME: Check registers for status... */
         return IRQ_HANDLED;
@@ -57,7 +46,7 @@ static void (*poweroff_method)(void) = machine_alt_power_off;
 void machine_power_off(void)
 {
         sstate_poweroff();
-        if (!serial_console || scons_pwroff) {
+        if (strcmp(of_console_device->type, "serial") || scons_pwroff) {
                 if (power_reg) {
                         /* Both register bits seem to have the
                          * same effect, so until I figure out
@@ -77,48 +66,6 @@ void machine_power_off(void)
 void (*pm_power_off)(void) = machine_power_off;
 EXPORT_SYMBOL(pm_power_off);
 
-static int powerd(void *__unused)
-{
-        static char *envp[] = { "HOME=/", "TERM=linux", "PATH=/sbin:/usr/sbin:/bin:/usr/bin", NULL };
-        char *argv[] = { "/sbin/shutdown", "-h", "now", NULL };
-        DECLARE_WAITQUEUE(wait, current);
-
-        daemonize("powerd");
-
-        add_wait_queue(&powerd_wait, &wait);
-
-        for (;;) {
-                set_task_state(current, TASK_INTERRUPTIBLE);
-                if (button_pressed)
-                        break;
-                flush_signals(current);
-                schedule();
-        }
-        __set_current_state(TASK_RUNNING);
-        remove_wait_queue(&powerd_wait, &wait);
-
-        /* Ok, down we go... */
-        button_pressed = 0;
-        if (kernel_execve("/sbin/shutdown", argv, envp) < 0) {
-                printk(KERN_ERR "powerd: shutdown execution failed\n");
-                machine_power_off();
-        }
-        return 0;
-}
-
-int start_powerd(void)
-{
-        int err;
-
-        err = kernel_thread(powerd, NULL, CLONE_FS);
-        if (err < 0)
-                printk(KERN_ERR "power: Failed to start power daemon.\n");
-        else
-                printk(KERN_INFO "power: powerd running.\n");
-
-        return err;
-}
-
 static int __init has_button_interrupt(unsigned int irq, struct device_node *dp)
 {
         if (irq == 0xffffffff)
@@ -136,20 +83,15 @@ static int __devinit power_probe(struct of_device *op, const struct of_device_id
 
         power_reg = of_ioremap(res, 0, 0x4, "power");
 
-        printk("%s: Control reg at %lx ... ",
+        printk(KERN_INFO "%s: Control reg at %lx\n",
                op->node->name, res->start);
 
         poweroff_method = machine_halt;  /* able to use the standard halt */
 
         if (has_button_interrupt(irq, op->node)) {
-                if (start_powerd() < 0)
-                        return 0;
-
                 if (request_irq(irq,
                                 power_handler, 0, "power", NULL) < 0)
                         printk(KERN_ERR "power: Cannot setup IRQ handler.\n");
-        } else {
-                printk(KERN_INFO "power: Not using powerd.\n");
         }
 
         return 0;
@@ -170,6 +112,6 @@ static struct of_platform_driver power_driver = {
 
 void __init power_init(void)
 {
-        of_register_driver(&power_driver, &of_bus_type);
+        of_register_driver(&power_driver, &of_platform_bus_type);
         return;
 }
diff --git a/arch/sparc64/kernel/process.c b/arch/sparc64/kernel/process.c
index 93557507ec9f..fd7899ba1d70 100644
--- a/arch/sparc64/kernel/process.c
+++ b/arch/sparc64/kernel/process.c
@@ -119,7 +119,7 @@ extern void (*prom_keyboard)(void);
 void machine_halt(void)
 {
         sstate_halt();
-        if (!serial_console && prom_palette)
+        if (prom_palette)
                 prom_palette (1);
         if (prom_keyboard)
                 prom_keyboard();
@@ -130,7 +130,7 @@ void machine_halt(void)
 void machine_alt_power_off(void)
 {
         sstate_poweroff();
-        if (!serial_console && prom_palette)
+        if (prom_palette)
                 prom_palette(1);
         if (prom_keyboard)
                 prom_keyboard();
@@ -145,7 +145,7 @@ void machine_restart(char * cmd)
         sstate_reboot();
         p = strchr (reboot_command, '\n');
         if (p) *p = 0;
-        if (!serial_console && prom_palette)
+        if (prom_palette)
                 prom_palette (1);
         if (prom_keyboard)
                 prom_keyboard();
diff --git a/arch/sparc64/kernel/prom.c b/arch/sparc64/kernel/prom.c
index 5d220302cd50..f4e0a9ad9be3 100644
--- a/arch/sparc64/kernel/prom.c
+++ b/arch/sparc64/kernel/prom.c
@@ -30,73 +30,9 @@
 #include <asm/upa.h>
 #include <asm/smp.h>
 
-static struct device_node *allnodes;
+extern struct device_node *allnodes;    /* temporary while merging */
 
-/* use when traversing tree through the allnext, child, sibling,
- * or parent members of struct device_node.
- */
-static DEFINE_RWLOCK(devtree_lock);
-
-int of_device_is_compatible(const struct device_node *device,
-                            const char *compat)
-{
-        const char* cp;
-        int cplen, l;
-
-        cp = of_get_property(device, "compatible", &cplen);
-        if (cp == NULL)
-                return 0;
-        while (cplen > 0) {
-                if (strncmp(cp, compat, strlen(compat)) == 0)
-                        return 1;
-                l = strlen(cp) + 1;
-                cp += l;
-                cplen -= l;
-        }
-
-        return 0;
-}
-EXPORT_SYMBOL(of_device_is_compatible);
-
-struct device_node *of_get_parent(const struct device_node *node)
-{
-        struct device_node *np;
-
-        if (!node)
-                return NULL;
-
-        np = node->parent;
-
-        return np;
-}
-EXPORT_SYMBOL(of_get_parent);
-
-struct device_node *of_get_next_child(const struct device_node *node,
-        struct device_node *prev)
-{
-        struct device_node *next;
-
-        next = prev ? prev->sibling : node->child;
-        for (; next != 0; next = next->sibling) {
-                break;
-        }
-
-        return next;
-}
-EXPORT_SYMBOL(of_get_next_child);
-
-struct device_node *of_find_node_by_path(const char *path)
-{
-        struct device_node *np = allnodes;
-
-        for (; np != 0; np = np->allnext) {
-                if (np->full_name != 0 && strcmp(np->full_name, path) == 0)
-                        break;
-        }
-
-        return np;
-}
-EXPORT_SYMBOL(of_find_node_by_path);
+extern rwlock_t devtree_lock;   /* temporary while merging */
 
 struct device_node *of_find_node_by_phandle(phandle handle)
 {
@@ -110,81 +46,6 @@ struct device_node *of_find_node_by_phandle(phandle handle)
 }
 EXPORT_SYMBOL(of_find_node_by_phandle);
 
-struct device_node *of_find_node_by_name(struct device_node *from,
-        const char *name)
-{
-        struct device_node *np;
-
-        np = from ? from->allnext : allnodes;
-        for (; np != NULL; np = np->allnext)
-                if (np->name != NULL && strcmp(np->name, name) == 0)
-                        break;
-
-        return np;
-}
-EXPORT_SYMBOL(of_find_node_by_name);
-
-struct device_node *of_find_node_by_type(struct device_node *from,
-        const char *type)
-{
-        struct device_node *np;
-
-        np = from ? from->allnext : allnodes;
-        for (; np != 0; np = np->allnext)
-                if (np->type != 0 && strcmp(np->type, type) == 0)
-                        break;
-
-        return np;
-}
-EXPORT_SYMBOL(of_find_node_by_type);
-
-struct device_node *of_find_compatible_node(struct device_node *from,
-        const char *type, const char *compatible)
-{
-        struct device_node *np;
-
-        np = from ? from->allnext : allnodes;
-        for (; np != 0; np = np->allnext) {
-                if (type != NULL
-                    && !(np->type != 0 && strcmp(np->type, type) == 0))
-                        continue;
-                if (of_device_is_compatible(np, compatible))
-                        break;
-        }
-
-        return np;
-}
-EXPORT_SYMBOL(of_find_compatible_node);
-
-struct property *of_find_property(const struct device_node *np,
-                                  const char *name,
-                                  int *lenp)
-{
-        struct property *pp;
-
-        for (pp = np->properties; pp != 0; pp = pp->next) {
-                if (strcasecmp(pp->name, name) == 0) {
-                        if (lenp != 0)
-                                *lenp = pp->length;
-                        break;
-                }
-        }
-        return pp;
-}
-EXPORT_SYMBOL(of_find_property);
-
-/*
- * Find a property with a given name for a given node
- * and return the value.
- */
-const void *of_get_property(const struct device_node *np, const char *name,
-                      int *lenp)
-{
-        struct property *pp = of_find_property(np,name,lenp);
-        return pp ? pp->value : NULL;
-}
-EXPORT_SYMBOL(of_get_property);
-
 int of_getintprop_default(struct device_node *np, const char *name, int def)
 {
         struct property *prop;
@@ -198,36 +59,6 @@ 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)
-{
-        const 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)
-{
-        const 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;
@@ -1815,6 +1646,60 @@ static void __init of_fill_in_cpu_data(void)
         smp_fill_in_sib_core_maps();
 }
 
+struct device_node *of_console_device;
+EXPORT_SYMBOL(of_console_device);
+
+char *of_console_path;
+EXPORT_SYMBOL(of_console_path);
+
+char *of_console_options;
+EXPORT_SYMBOL(of_console_options);
+
+static void __init of_console_init(void)
+{
+        char *msg = "OF stdout device is: %s\n";
+        struct device_node *dp;
+        const char *type;
+        phandle node;
+
+        of_console_path = prom_early_alloc(256);
+        if (prom_ihandle2path(prom_stdout, of_console_path, 256) < 0) {
+                prom_printf("Cannot obtain path of stdout.\n");
+                prom_halt();
+        }
+        of_console_options = strrchr(of_console_path, ':');
+        if (of_console_options) {
+                of_console_options++;
+                if (*of_console_options == '\0')
+                        of_console_options = NULL;
+        }
+
+        node = prom_inst2pkg(prom_stdout);
+        if (!node) {
+                prom_printf("Cannot resolve stdout node from "
+                            "instance %08x.\n", prom_stdout);
+                prom_halt();
+        }
+
+        dp = of_find_node_by_phandle(node);
+        type = of_get_property(dp, "device_type", NULL);
+        if (!type) {
+                prom_printf("Console stdout lacks device_type property.\n");
+                prom_halt();
+        }
+
+        if (strcmp(type, "display") && strcmp(type, "serial")) {
+                prom_printf("Console device_type is neither display "
+                            "nor serial.\n");
+                prom_halt();
+        }
+
+        of_console_device = dp;
+
+        prom_printf(msg, of_console_path);
+        printk(msg, of_console_path);
+}
+
 void __init prom_build_devicetree(void)
 {
         struct device_node **nextp;
@@ -1827,6 +1712,8 @@ void __init prom_build_devicetree(void)
         allnodes->child = build_tree(allnodes,
                                      prom_getchild(allnodes->node),
                                      &nextp);
+        of_console_init();
+
         printk("PROM: Built device tree with %u bytes of memory.\n",
                prom_early_allocated);
 
diff --git a/arch/sparc64/kernel/setup.c b/arch/sparc64/kernel/setup.c
index aafde3dd9fd4..0f5be828ee92 100644
--- a/arch/sparc64/kernel/setup.c
+++ b/arch/sparc64/kernel/setup.c
@@ -133,33 +133,6 @@ static void __init process_switch(char c)
         }
 }
 
-static void __init process_console(char *commands)
-{
-        serial_console = 0;
-        commands += 8;
-        /* Linux-style serial */
-        if (!strncmp(commands, "ttyS", 4))
-                serial_console = simple_strtoul(commands + 4, NULL, 10) + 1;
-        else if (!strncmp(commands, "tty", 3)) {
-                char c = *(commands + 3);
-                /* Solaris-style serial */
-                if (c == 'a' || c == 'b') {
-                        serial_console = c - 'a' + 1;
-                        prom_printf ("Using /dev/tty%c as console.\n", c);
-                }
-                /* else Linux-style fbcon, not serial */
-        }
-#if defined(CONFIG_PROM_CONSOLE)
-        if (!strncmp(commands, "prom", 4)) {
-                char *p;
-
-                for (p = commands - 8; *p && *p != ' '; p++)
-                        *p = ' ';
-                conswitchp = &prom_con;
-        }
-#endif
-}
-
 static void __init boot_flags_init(char *commands)
 {
         while (*commands) {
@@ -176,9 +149,7 @@ static void __init boot_flags_init(char *commands)
                                 process_switch(*commands++);
                         continue;
                 }
-                if (!strncmp(commands, "console=", 8)) {
-                        process_console(commands);
-                } else if (!strncmp(commands, "mem=", 4)) {
+                if (!strncmp(commands, "mem=", 4)) {
                         /*
                          * "mem=XXX[kKmM]" overrides the PROM-reported
                          * memory size.
@@ -378,44 +349,6 @@ void __init setup_arch(char **cmdline_p)
         paging_init();
 }
 
-static int __init set_preferred_console(void)
-{
-        int idev, odev;
-
-        /* The user has requested a console so this is already set up. */
-        if (serial_console >= 0)
-                return -EBUSY;
-
-        idev = prom_query_input_device();
-        odev = prom_query_output_device();
-        if (idev == PROMDEV_IKBD && odev == PROMDEV_OSCREEN) {
-                serial_console = 0;
-        } else if (idev == PROMDEV_ITTYA && odev == PROMDEV_OTTYA) {
-                serial_console = 1;
-        } else if (idev == PROMDEV_ITTYB && odev == PROMDEV_OTTYB) {
-                serial_console = 2;
-        } else if (idev == PROMDEV_IRSC && odev == PROMDEV_ORSC) {
-                serial_console = 3;
-        } else if (idev == PROMDEV_IVCONS && odev == PROMDEV_OVCONS) {
-                /* sunhv_console_init() doesn't check the serial_console
-                 * value anyways...
-                 */
-                serial_console = 4;
-                return add_preferred_console("ttyHV", 0, NULL);
-        } else {
-                prom_printf("Inconsistent console: "
-                            "input %d, output %d\n",
-                            idev, odev);
-                prom_halt();
-        }
-
-        if (serial_console)
-                return add_preferred_console("ttyS", serial_console - 1, NULL);
-
-        return -ENODEV;
-}
-console_initcall(set_preferred_console);
-
 /* BUFFER is PAGE_SIZE bytes long. */
 
 extern char *sparc_cpu_type;
@@ -508,5 +441,4 @@ void sun_do_break(void)
         prom_cmdline();
 }
 
-int serial_console = -1;
 int stop_a_enabled = 1;
diff --git a/arch/sparc64/kernel/sparc64_ksyms.c b/arch/sparc64/kernel/sparc64_ksyms.c
index 719d676c2ddc..d270c2f0be0f 100644
--- a/arch/sparc64/kernel/sparc64_ksyms.c
+++ b/arch/sparc64/kernel/sparc64_ksyms.c
@@ -280,6 +280,7 @@ EXPORT_SYMBOL(sys_getgid);
 EXPORT_SYMBOL(svr4_getcontext);
 EXPORT_SYMBOL(svr4_setcontext);
 EXPORT_SYMBOL(compat_sys_ioctl);
+EXPORT_SYMBOL(sys_ioctl);
 EXPORT_SYMBOL(sparc32_open);
 #endif
 
@@ -330,7 +331,6 @@ EXPORT_SYMBOL(VISenter);
 
 /* for input/keybdev */
 EXPORT_SYMBOL(sun_do_break);
-EXPORT_SYMBOL(serial_console);
 EXPORT_SYMBOL(stop_a_enabled);
 
 #ifdef CONFIG_DEBUG_BUGVERBOSE
diff --git a/arch/sparc64/kernel/sys_sparc32.c b/arch/sparc64/kernel/sys_sparc32.c
index abd83129b2e7..e8dce90d05d4 100644
--- a/arch/sparc64/kernel/sys_sparc32.c
+++ b/arch/sparc64/kernel/sys_sparc32.c
@@ -1,8 +1,7 @@
-/* $Id: sys_sparc32.c,v 1.184 2002/02/09 19:49:31 davem Exp $
- * sys_sparc32.c: Conversion between 32bit and 64bit native syscalls.
+/* sys_sparc32.c: Conversion between 32bit and 64bit native syscalls.
  *
  * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
- * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
+ * Copyright (C) 1997, 2007 David S. Miller (davem@davemloft.net)
  *
  * These routines maintain argument size conversion between 32bit and 64bit
  * environment.
@@ -1028,3 +1027,10 @@ long compat_sync_file_range(int fd, unsigned long off_high, unsigned long off_lo
                                    (nb_high << 32) | nb_low,
                                    flags);
 }
+
+asmlinkage long compat_sys_fallocate(int fd, int mode, u32 offhi, u32 offlo,
+                                     u32 lenhi, u32 lenlo)
+{
+        return sys_fallocate(fd, mode, ((loff_t)offhi << 32) | offlo,
+                             ((loff_t)lenhi << 32) | lenlo);
+}
diff --git a/arch/sparc64/kernel/systbls.S b/arch/sparc64/kernel/systbls.S
index 8765e32155a0..06d10907d8ce 100644
--- a/arch/sparc64/kernel/systbls.S
+++ b/arch/sparc64/kernel/systbls.S
@@ -1,8 +1,7 @@
-/* $Id: systbls.S,v 1.81 2002/02/08 03:57:14 davem Exp $
- * systbls.S: System call entry point tables for OS compatibility.
+/* systbls.S: System call entry point tables for OS compatibility.
  *            The native Linux system call table lives here also.
  *
- * Copyright (C) 1995, 1996 David S. Miller (davem@caip.rutgers.edu)
+ * Copyright (C) 1995, 1996, 2007 David S. Miller (davem@davemloft.net)
  * Copyright (C) 1997 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
  *
  * Based upon preliminary work which is:
@@ -81,7 +80,7 @@ sys_call_table32:
         .word sys_fchmodat, sys_faccessat, compat_sys_pselect6, compat_sys_ppoll, sys_unshare
 /*300*/ .word compat_sys_set_robust_list, compat_sys_get_robust_list, compat_sys_migrate_pages, compat_sys_mbind, compat_sys_get_mempolicy
         .word compat_sys_set_mempolicy, compat_sys_kexec_load, compat_sys_move_pages, sys_getcpu, compat_sys_epoll_pwait
-/*310*/ .word compat_sys_utimensat, compat_sys_signalfd, compat_sys_timerfd, sys_eventfd
+/*310*/ .word compat_sys_utimensat, compat_sys_signalfd, compat_sys_timerfd, sys_eventfd, compat_sys_fallocate
 
 #endif /* CONFIG_COMPAT */
 
@@ -153,7 +152,7 @@ sys_call_table:
         .word sys_fchmodat, sys_faccessat, sys_pselect6, sys_ppoll, sys_unshare
 /*300*/ .word sys_set_robust_list, sys_get_robust_list, sys_migrate_pages, sys_mbind, sys_get_mempolicy
         .word sys_set_mempolicy, sys_kexec_load, sys_move_pages, sys_getcpu, sys_epoll_pwait
-/*310*/ .word sys_utimensat, sys_signalfd, sys_timerfd, sys_eventfd
+/*310*/ .word sys_utimensat, sys_signalfd, sys_timerfd, sys_eventfd, sys_fallocate
 
 #if defined(CONFIG_SUNOS_EMUL) || defined(CONFIG_SOLARIS_EMUL) || \
     defined(CONFIG_SOLARIS_EMUL_MODULE)
@@ -272,6 +271,6 @@ sunos_sys_table:
         .word sunos_nosys, sunos_nosys, sunos_nosys
         .word sunos_nosys
 /*310*/ .word sunos_nosys, sunos_nosys, sunos_nosys
-        .word sunos_nosys
+        .word sunos_nosys, sunos_nosys
 
 #endif
diff --git a/arch/sparc64/kernel/time.c b/arch/sparc64/kernel/time.c
index 62e316ab1339..49063ca2efcd 100644
--- a/arch/sparc64/kernel/time.c
+++ b/arch/sparc64/kernel/time.c
@@ -403,58 +403,9 @@ static struct sparc64_tick_ops hbtick_operations __read_mostly = {
 
 static unsigned long timer_ticks_per_nsec_quotient __read_mostly;
 
-#define TICK_SIZE (tick_nsec / 1000)
-
-#define USEC_AFTER      500000
-#define USEC_BEFORE     500000
-
-static void sync_cmos_clock(unsigned long dummy);
-
-static DEFINE_TIMER(sync_cmos_timer, sync_cmos_clock, 0, 0);
-
-static void sync_cmos_clock(unsigned long dummy)
-{
-        struct timeval now, next;
-        int fail = 1;
-
-        /*
-         * If we have an externally synchronized Linux clock, then update
-         * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
-         * called as close as possible to 500 ms before the new second starts.
-         * This code is run on a timer.  If the clock is set, that timer
-         * may not expire at the correct time.  Thus, we adjust...
-         */
-        if (!ntp_synced())
-                /*
-                 * Not synced, exit, do not restart a timer (if one is
-                 * running, let it run out).
-                 */
-                return;
-
-        do_gettimeofday(&now);
-        if (now.tv_usec >= USEC_AFTER - ((unsigned) TICK_SIZE) / 2 &&
-            now.tv_usec <= USEC_BEFORE + ((unsigned) TICK_SIZE) / 2)
-                fail = set_rtc_mmss(now.tv_sec);
-
-        next.tv_usec = USEC_AFTER - now.tv_usec;
-        if (next.tv_usec <= 0)
-                next.tv_usec += USEC_PER_SEC;
-
-        if (!fail)
-                next.tv_sec = 659;
-        else
-                next.tv_sec = 0;
-
-        if (next.tv_usec >= USEC_PER_SEC) {
-                next.tv_sec++;
-                next.tv_usec -= USEC_PER_SEC;
-        }
-        mod_timer(&sync_cmos_timer, jiffies + timeval_to_jiffies(&next));
-}
-
-void notify_arch_cmos_timer(void)
+int update_persistent_clock(struct timespec now)
 {
-        mod_timer(&sync_cmos_timer, jiffies + 1);
+        return set_rtc_mmss(now.tv_sec);
 }
 
 /* Kick start a stopped clock (procedure from the Sun NVRAM/hostid FAQ). */
@@ -835,7 +786,7 @@ static int __init clock_init(void)
                 return 0;
         }
 
-        return of_register_driver(&clock_driver, &of_bus_type);
+        return of_register_driver(&clock_driver, &of_platform_bus_type);
 }
 
 /* Must be after subsys_initcall() so that busses are probed.  Must
@@ -931,6 +882,7 @@ static void sparc64_timer_setup(enum clock_event_mode mode,
 {
         switch (mode) {
         case CLOCK_EVT_MODE_ONESHOT:
+        case CLOCK_EVT_MODE_RESUME:
                 break;
 
         case CLOCK_EVT_MODE_SHUTDOWN:
@@ -1434,6 +1386,78 @@ static int bq4802_set_rtc_time(struct rtc_time *time)
 
         return 0;
 }
+
+static void cmos_get_rtc_time(struct rtc_time *rtc_tm)
+{
+        unsigned char ctrl;
+
+        rtc_tm->tm_sec = CMOS_READ(RTC_SECONDS);
+        rtc_tm->tm_min = CMOS_READ(RTC_MINUTES);
+        rtc_tm->tm_hour = CMOS_READ(RTC_HOURS);
+        rtc_tm->tm_mday = CMOS_READ(RTC_DAY_OF_MONTH);
+        rtc_tm->tm_mon = CMOS_READ(RTC_MONTH);
+        rtc_tm->tm_year = CMOS_READ(RTC_YEAR);
+        rtc_tm->tm_wday = CMOS_READ(RTC_DAY_OF_WEEK);
+
+        ctrl = CMOS_READ(RTC_CONTROL);
+        if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
+                BCD_TO_BIN(rtc_tm->tm_sec);
+                BCD_TO_BIN(rtc_tm->tm_min);
+                BCD_TO_BIN(rtc_tm->tm_hour);
+                BCD_TO_BIN(rtc_tm->tm_mday);
+                BCD_TO_BIN(rtc_tm->tm_mon);
+                BCD_TO_BIN(rtc_tm->tm_year);
+                BCD_TO_BIN(rtc_tm->tm_wday);
+        }
+
+        if (rtc_tm->tm_year <= 69)
+                rtc_tm->tm_year += 100;
+
+        rtc_tm->tm_mon--;
+}
+
+static int cmos_set_rtc_time(struct rtc_time *rtc_tm)
+{
+        unsigned char mon, day, hrs, min, sec;
+        unsigned char save_control, save_freq_select;
+        unsigned int yrs;
+
+        yrs = rtc_tm->tm_year;
+        mon = rtc_tm->tm_mon + 1;
+        day = rtc_tm->tm_mday;
+        hrs = rtc_tm->tm_hour;
+        min = rtc_tm->tm_min;
+        sec = rtc_tm->tm_sec;
+
+        if (yrs >= 100)
+                yrs -= 100;
+
+        if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
+                BIN_TO_BCD(sec);
+                BIN_TO_BCD(min);
+                BIN_TO_BCD(hrs);
+                BIN_TO_BCD(day);
+                BIN_TO_BCD(mon);
+                BIN_TO_BCD(yrs);
+        }
+
+        save_control = CMOS_READ(RTC_CONTROL);
+        CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
+        save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
+        CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT);
+
+        CMOS_WRITE(yrs, RTC_YEAR);
+        CMOS_WRITE(mon, RTC_MONTH);
+        CMOS_WRITE(day, RTC_DAY_OF_MONTH);
+        CMOS_WRITE(hrs, RTC_HOURS);
+        CMOS_WRITE(min, RTC_MINUTES);
+        CMOS_WRITE(sec, RTC_SECONDS);
+
+        CMOS_WRITE(save_control, RTC_CONTROL);
+        CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
+
+        return 0;
+}
 #endif /* CONFIG_PCI */
 
 struct mini_rtc_ops {
@@ -1456,6 +1480,11 @@ static struct mini_rtc_ops bq4802_rtc_ops = {
         .get_rtc_time = bq4802_get_rtc_time,
         .set_rtc_time = bq4802_set_rtc_time,
 };
+
+static struct mini_rtc_ops cmos_rtc_ops = {
+        .get_rtc_time = cmos_get_rtc_time,
+        .set_rtc_time = cmos_set_rtc_time,
+};
 #endif /* CONFIG_PCI */
 
 static struct mini_rtc_ops *mini_rtc_ops;
@@ -1583,6 +1612,8 @@ static int __init rtc_mini_init(void)
 #ifdef CONFIG_PCI
         else if (bq4802_regs)
                 mini_rtc_ops = &bq4802_rtc_ops;
+        else if (ds1287_regs)
+                mini_rtc_ops = &cmos_rtc_ops;
 #endif /* CONFIG_PCI */
         else
                 return -ENODEV;
diff --git a/arch/sparc64/kernel/vio.c b/arch/sparc64/kernel/vio.c
index 8d3cc4fdb557..3685daf5157f 100644
--- a/arch/sparc64/kernel/vio.c
+++ b/arch/sparc64/kernel/vio.c
@@ -103,9 +103,9 @@ static ssize_t devspec_show(struct device *dev,
         struct vio_dev *vdev = to_vio_dev(dev);
         const char *str = "none";
 
-        if (!strcmp(vdev->type, "network"))
+        if (!strcmp(vdev->type, "vnet-port"))
                 str = "vnet";
-        else if (!strcmp(vdev->type, "block"))
+        else if (!strcmp(vdev->type, "vdc-port"))
                 str = "vdisk";
 
         return sprintf(buf, "%s\n", str);
@@ -205,7 +205,8 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
         struct device_node *dp;
         struct vio_dev *vdev;
         int err, tlen, clen;
-        const u64 *id;
+        const u64 *id, *cfg_handle;
+        u64 a;
 
         type = mdesc_get_property(hp, mp, "device-type", &tlen);
         if (!type) {
@@ -221,6 +222,19 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
                 return NULL;
         }
 
+        id = mdesc_get_property(hp, mp, "id", NULL);
+
+        cfg_handle = NULL;
+        mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_BACK) {
+                u64 target;
+
+                target = mdesc_arc_target(hp, a);
+                cfg_handle = mdesc_get_property(hp, target,
+                                                "cfg-handle", NULL);
+                if (cfg_handle)
+                        break;
+        }
+
         bus_id_name = type;
         if (!strcmp(type, "domain-services-port"))
                 bus_id_name = "ds";
@@ -260,13 +274,19 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
 
         vio_fill_channel_info(hp, mp, vdev);
 
-        id = mdesc_get_property(hp, mp, "id", NULL);
-        if (!id)
+        if (!id) {
                 snprintf(vdev->dev.bus_id, BUS_ID_SIZE, "%s",
                          bus_id_name);
-        else
+                vdev->dev_no = ~(u64)0;
+        } else if (!cfg_handle) {
                 snprintf(vdev->dev.bus_id, BUS_ID_SIZE, "%s-%lu",
                          bus_id_name, *id);
+                vdev->dev_no = *id;
+        } else {
+                snprintf(vdev->dev.bus_id, BUS_ID_SIZE, "%s-%lu-%lu",
+                         bus_id_name, *cfg_handle, *id);
+                vdev->dev_no = *cfg_handle;
+        }
 
         vdev->dev.parent = parent;
         vdev->dev.bus = &vio_bus_type;
diff --git a/arch/sparc64/prom/console.c b/arch/sparc64/prom/console.c
index 7c25c54cefdc..3fafa9a8b50b 100644
--- a/arch/sparc64/prom/console.c
+++ b/arch/sparc64/prom/console.c
@@ -73,88 +73,3 @@ prom_puts(const char *s, int len)
                            P1275_INOUT(3,1),
                            prom_stdout, s, P1275_SIZE(len));
 }
-
-/* Query for input device type */
-enum prom_input_device
-prom_query_input_device(void)
-{
-        int st_p;
-        char propb[64];
-
-        st_p = prom_inst2pkg(prom_stdin);
-        if(prom_node_has_property(st_p, "keyboard"))
-                return PROMDEV_IKBD;
-        prom_getproperty(st_p, "device_type", propb, sizeof(propb));
-        if(strncmp(propb, "serial", 6))
-                return PROMDEV_I_UNK;
-        /* FIXME: Is there any better way how to find out? */   
-        memset(propb, 0, sizeof(propb));
-        st_p = prom_finddevice ("/options");
-        prom_getproperty(st_p, "input-device", propb, sizeof(propb));
-
-        /*
-         * If we get here with propb == 'keyboard', we are on ttya, as
-         * the PROM defaulted to this due to 'no input device'.
-         */
-        if (!strncmp(propb, "keyboard", 8))
-                return PROMDEV_ITTYA;
-
-        if (!strncmp (propb, "rsc", 3))
-                return PROMDEV_IRSC;
-
-        if (!strncmp (propb, "virtual-console", 3))
-                return PROMDEV_IVCONS;
-
-        if (strncmp (propb, "tty", 3) || !propb[3])
-                return PROMDEV_I_UNK;
-
-        switch (propb[3]) {
-                case 'a': return PROMDEV_ITTYA;
-                case 'b': return PROMDEV_ITTYB;
-                default: return PROMDEV_I_UNK;
-        }
-}
-
-/* Query for output device type */
-
-enum prom_output_device
-prom_query_output_device(void)
-{
-        int st_p;
-        char propb[64];
-        int propl;
-
-        st_p = prom_inst2pkg(prom_stdout);
-        propl = prom_getproperty(st_p, "device_type", propb, sizeof(propb));
-        if (propl >= 0 && propl == sizeof("display") &&
-            strncmp("display", propb, sizeof("display")) == 0)
-                return PROMDEV_OSCREEN;
-        if(strncmp("serial", propb, 6))
-                return PROMDEV_O_UNK;
-        /* FIXME: Is there any better way how to find out? */   
-        memset(propb, 0, sizeof(propb));
-        st_p = prom_finddevice ("/options");
-        prom_getproperty(st_p, "output-device", propb, sizeof(propb));
-
-        /*
-         * If we get here with propb == 'screen', we are on ttya, as
-         * the PROM defaulted to this due to 'no input device'.
-         */
-        if (!strncmp(propb, "screen", 6))
-                return PROMDEV_OTTYA;
-
-        if (!strncmp (propb, "rsc", 3))
-                return PROMDEV_ORSC;
-
-        if (!strncmp (propb, "virtual-console", 3))
-                return PROMDEV_OVCONS;
-
-        if (strncmp (propb, "tty", 3) || !propb[3])
-                return PROMDEV_O_UNK;
-
-        switch (propb[3]) {
-                case 'a': return PROMDEV_OTTYA;
-                case 'b': return PROMDEV_OTTYB;
-                default: return PROMDEV_O_UNK;
-        }
-}
diff --git a/arch/sparc64/prom/misc.c b/arch/sparc64/prom/misc.c
index 33c5b7da31e5..68c83ad04ad9 100644
--- a/arch/sparc64/prom/misc.c
+++ b/arch/sparc64/prom/misc.c
@@ -72,7 +72,7 @@ void prom_cmdline(void)
 
         local_irq_save(flags);
 
-        if (!serial_console && prom_palette)
+        if (prom_palette)
                 prom_palette(1);
 
 #ifdef CONFIG_SMP
@@ -85,7 +85,7 @@ void prom_cmdline(void)
         smp_release();
 #endif
 
-        if (!serial_console && prom_palette)
+        if (prom_palette)
                 prom_palette(0);
 
         local_irq_restore(flags);
diff --git a/arch/sparc64/prom/tree.c b/arch/sparc64/prom/tree.c
index 17b7ecfe7ca9..b2c5b12c9818 100644
--- a/arch/sparc64/prom/tree.c
+++ b/arch/sparc64/prom/tree.c
@@ -304,3 +304,11 @@ prom_pathtoinode(const char *path)
         if (node == -1) return 0;
         return node;
 }
+
+int prom_ihandle2path(int handle, char *buffer, int bufsize)
+{
+        return p1275_cmd("instance-to-path",
+                         P1275_ARG(1,P1275_ARG_OUT_BUF)|
+                         P1275_INOUT(3, 1),
+                         handle, buffer, P1275_SIZE(bufsize));
+}
diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig
index 14bf8ce3ea23..45f82ae6d389 100644
--- a/arch/x86_64/Kconfig
+++ b/arch/x86_64/Kconfig
@@ -32,6 +32,10 @@ config GENERIC_TIME_VSYSCALL
         bool
         default y
 
+config GENERIC_CMOS_UPDATE
+        bool
+        default y
+
 config ZONE_DMA32
         bool
         default y
@@ -56,6 +60,14 @@ config ZONE_DMA
         bool
         default y
 
+config QUICKLIST
+        bool
+        default y
+
+config NR_QUICK
+        int
+        default 2
+
 config ISA
         bool
 
diff --git a/arch/x86_64/Makefile b/arch/x86_64/Makefile
index 29617ae3926d..128561d3e876 100644
--- a/arch/x86_64/Makefile
+++ b/arch/x86_64/Makefile
@@ -76,7 +76,8 @@ head-y := arch/x86_64/kernel/head.o arch/x86_64/kernel/head64.o arch/x86_64/kern
 libs-y                                  += arch/x86_64/lib/
 core-y                                  += arch/x86_64/kernel/ \
                                            arch/x86_64/mm/ \
-                                           arch/x86_64/crypto/
+                                           arch/x86_64/crypto/ \
+                                           arch/x86_64/vdso/
 core-$(CONFIG_IA32_EMULATION)           += arch/x86_64/ia32/
 drivers-$(CONFIG_PCI)                   += arch/x86_64/pci/
 drivers-$(CONFIG_OPROFILE)              += arch/x86_64/oprofile/
diff --git a/arch/x86_64/boot/compressed/Makefile b/arch/x86_64/boot/compressed/Makefile
index c9f2da7496c1..877c0bdbbc67 100644
--- a/arch/x86_64/boot/compressed/Makefile
+++ b/arch/x86_64/boot/compressed/Makefile
@@ -3,8 +3,6 @@
 #
 # create a compressed vmlinux image from the original vmlinux
 #
-# Note all the files here are compiled/linked as 32bit executables.
-#
 
 targets         := vmlinux vmlinux.bin vmlinux.bin.gz head.o misc.o piggy.o
 
diff --git a/arch/x86_64/defconfig b/arch/x86_64/defconfig
index 40178e5c3104..b7c4cd04bfc3 100644
--- a/arch/x86_64/defconfig
+++ b/arch/x86_64/defconfig
@@ -1,19 +1,22 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.22-rc2
-# Mon May 21 13:23:40 2007
+# Linux kernel version: 2.6.22-git14
+# Fri Jul 20 09:53:15 2007
 #
 CONFIG_X86_64=y
 CONFIG_64BIT=y
 CONFIG_X86=y
 CONFIG_GENERIC_TIME=y
 CONFIG_GENERIC_TIME_VSYSCALL=y
+CONFIG_GENERIC_CMOS_UPDATE=y
 CONFIG_ZONE_DMA32=y
 CONFIG_LOCKDEP_SUPPORT=y
 CONFIG_STACKTRACE_SUPPORT=y
 CONFIG_SEMAPHORE_SLEEPERS=y
 CONFIG_MMU=y
 CONFIG_ZONE_DMA=y
+CONFIG_QUICKLIST=y
+CONFIG_NR_QUICK=2
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_HWEIGHT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
@@ -44,19 +47,18 @@ CONFIG_LOCALVERSION=""
 CONFIG_LOCALVERSION_AUTO=y
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
-# CONFIG_IPC_NS is not set
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
-# CONFIG_UTS_NS is not set
+# CONFIG_USER_NS is not set
 # CONFIG_AUDIT is not set
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=18
 # CONFIG_CPUSETS is not set
 CONFIG_SYSFS_DEPRECATED=y
-# CONFIG_RELAY is not set
+CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE=""
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
@@ -86,10 +88,6 @@ CONFIG_SLAB=y
 CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
-
-#
-# Loadable module support
-#
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
@@ -97,12 +95,9 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 # CONFIG_KMOD is not set
 CONFIG_STOP_MACHINE=y
-
-#
-# Block layer
-#
 CONFIG_BLOCK=y
 # CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_BLK_DEV_BSG is not set
 
 #
 # IO Schedulers
@@ -165,9 +160,12 @@ CONFIG_SPLIT_PTLOCK_CPUS=4
 CONFIG_MIGRATION=y
 CONFIG_RESOURCES_64BIT=y
 CONFIG_ZONE_DMA_FLAG=1
+CONFIG_BOUNCE=y
+CONFIG_VIRT_TO_BUS=y
 CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y
 CONFIG_OUT_OF_LINE_PFN_TO_PAGE=y
 CONFIG_NR_CPUS=32
+CONFIG_PHYSICAL_ALIGN=0x200000
 CONFIG_HOTPLUG_CPU=y
 CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
 CONFIG_HPET_TIMER=y
@@ -180,7 +178,7 @@ CONFIG_X86_MCE_INTEL=y
 CONFIG_X86_MCE_AMD=y
 # CONFIG_KEXEC is not set
 # CONFIG_CRASH_DUMP is not set
-CONFIG_RELOCATABLE=y
+# CONFIG_RELOCATABLE is not set
 CONFIG_PHYSICAL_START=0x200000
 CONFIG_SECCOMP=y
 # CONFIG_CC_STACKPROTECTOR is not set
@@ -201,7 +199,6 @@ CONFIG_GENERIC_PENDING_IRQ=y
 CONFIG_PM=y
 # CONFIG_PM_LEGACY is not set
 # CONFIG_PM_DEBUG is not set
-# CONFIG_PM_SYSFS_DEPRECATED is not set
 CONFIG_SOFTWARE_SUSPEND=y
 CONFIG_PM_STD_PARTITION=""
 CONFIG_SUSPEND_SMP=y
@@ -248,7 +245,7 @@ CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 # CONFIG_CPU_FREQ_GOV_POWERSAVE is not set
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
-# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set
+CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
 
 #
 # CPUFreq processor drivers
@@ -351,20 +348,8 @@ CONFIG_IPV6_SIT=y
 # CONFIG_IPV6_MULTIPLE_TABLES is not set
 # CONFIG_NETWORK_SECMARK is not set
 # CONFIG_NETFILTER is not set
-
-#
-# DCCP Configuration (EXPERIMENTAL)
-#
 # CONFIG_IP_DCCP is not set
-
-#
-# SCTP Configuration (EXPERIMENTAL)
-#
 # CONFIG_IP_SCTP is not set
-
-#
-# TIPC Configuration (EXPERIMENTAL)
-#
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
 # CONFIG_BRIDGE is not set
@@ -401,6 +386,7 @@ CONFIG_IPV6_SIT=y
 # CONFIG_MAC80211 is not set
 # CONFIG_IEEE80211 is not set
 # CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
 
 #
 # Device Drivers
@@ -415,21 +401,9 @@ CONFIG_FW_LOADER=y
 # CONFIG_DEBUG_DRIVER is not set
 # CONFIG_DEBUG_DEVRES is not set
 # CONFIG_SYS_HYPERVISOR is not set
-
-#
-# Connector - unified userspace <-> kernelspace linker
-#
 # CONFIG_CONNECTOR is not set
 # CONFIG_MTD is not set
-
-#
-# Parallel port support
-#
 # CONFIG_PARPORT is not set
-
-#
-# Plug and Play support
-#
 CONFIG_PNP=y
 # CONFIG_PNP_DEBUG is not set
 
@@ -437,10 +411,7 @@ CONFIG_PNP=y
 # Protocols
 #
 CONFIG_PNPACPI=y
-
-#
-# Block devices
-#
+CONFIG_BLK_DEV=y
 CONFIG_BLK_DEV_FD=y
 # CONFIG_BLK_CPQ_DA is not set
 # CONFIG_BLK_CPQ_CISS_DA is not set
@@ -458,17 +429,14 @@ CONFIG_BLK_DEV_RAM_SIZE=4096
 CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
 # CONFIG_CDROM_PKTCDVD is not set
 # CONFIG_ATA_OVER_ETH is not set
-
-#
-# Misc devices
-#
+CONFIG_MISC_DEVICES=y
 # CONFIG_IBM_ASM is not set
 # CONFIG_PHANTOM is not set
+# CONFIG_EEPROM_93CX6 is not set
 # CONFIG_SGI_IOC4 is not set
 # CONFIG_TIFM_CORE is not set
 # CONFIG_SONY_LAPTOP is not set
 # CONFIG_THINKPAD_ACPI is not set
-# CONFIG_BLINK is not set
 CONFIG_IDE=y
 CONFIG_BLK_DEV_IDE=y
 
@@ -539,6 +507,7 @@ CONFIG_BLK_DEV_IDEDMA=y
 #
 # CONFIG_RAID_ATTRS is not set
 CONFIG_SCSI=y
+CONFIG_SCSI_DMA=y
 # CONFIG_SCSI_TGT is not set
 CONFIG_SCSI_NETLINK=y
 # CONFIG_SCSI_PROC_FS is not set
@@ -590,11 +559,9 @@ CONFIG_AIC79XX_DEBUG_MASK=0
 # CONFIG_AIC79XX_REG_PRETTY_PRINT is not set
 # CONFIG_SCSI_AIC94XX is not set
 # CONFIG_SCSI_ARCMSR is not set
-CONFIG_MEGARAID_NEWGEN=y
-CONFIG_MEGARAID_MM=y
-CONFIG_MEGARAID_MAILBOX=y
+# CONFIG_MEGARAID_NEWGEN is not set
 # CONFIG_MEGARAID_LEGACY is not set
-CONFIG_MEGARAID_SAS=y
+# CONFIG_MEGARAID_SAS is not set
 # CONFIG_SCSI_HPTIOP is not set
 # CONFIG_SCSI_BUSLOGIC is not set
 # CONFIG_SCSI_DMX3191D is not set
@@ -614,7 +581,6 @@ CONFIG_MEGARAID_SAS=y
 # CONFIG_SCSI_DC395x is not set
 # CONFIG_SCSI_DC390T is not set
 # CONFIG_SCSI_DEBUG is not set
-# CONFIG_SCSI_ESP_CORE is not set
 # CONFIG_SCSI_SRP is not set
 CONFIG_ATA=y
 # CONFIG_ATA_NONSTANDARD is not set
@@ -671,10 +637,6 @@ CONFIG_SATA_VIA=y
 # CONFIG_PATA_SIS is not set
 # CONFIG_PATA_VIA is not set
 # CONFIG_PATA_WINBOND is not set
-
-#
-# Multi-device support (RAID and LVM)
-#
 CONFIG_MD=y
 # CONFIG_BLK_DEV_MD is not set
 CONFIG_BLK_DEV_DM=y
@@ -692,7 +654,7 @@ CONFIG_BLK_DEV_DM=y
 CONFIG_FUSION=y
 CONFIG_FUSION_SPI=y
 # CONFIG_FUSION_FC is not set
-CONFIG_FUSION_SAS=y
+# CONFIG_FUSION_SAS is not set
 CONFIG_FUSION_MAX_SGE=128
 # CONFIG_FUSION_CTL is not set
 
@@ -710,7 +672,10 @@ CONFIG_IEEE1394=y
 #
 # Controllers
 #
-# CONFIG_IEEE1394_PCILYNX is not set
+
+#
+# Texas Instruments PCILynx requires I2C
+#
 CONFIG_IEEE1394_OHCI1394=y
 
 #
@@ -722,32 +687,19 @@ CONFIG_IEEE1394_OHCI1394=y
 # CONFIG_IEEE1394_ETH1394 is not set
 # CONFIG_IEEE1394_DV1394 is not set
 CONFIG_IEEE1394_RAWIO=y
-
-#
-# I2O device support
-#
 # CONFIG_I2O is not set
-# CONFIG_MACINTOSH_DRIVERS is not set
-
-#
-# Network device support
-#
+CONFIG_MACINTOSH_DRIVERS=y
+# CONFIG_MAC_EMUMOUSEBTN is not set
 CONFIG_NETDEVICES=y
+CONFIG_NETDEVICES_MULTIQUEUE=y
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
+# CONFIG_MACVLAN is not set
 # CONFIG_EQUALIZER is not set
 CONFIG_TUN=y
 # CONFIG_NET_SB1000 is not set
-
-#
-# ARCnet devices
-#
 # CONFIG_ARCNET is not set
 # CONFIG_PHYLIB is not set
-
-#
-# Ethernet (10 or 100Mbit)
-#
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
 # CONFIG_HAPPYMEAL is not set
@@ -756,10 +708,6 @@ CONFIG_MII=y
 CONFIG_NET_VENDOR_3COM=y
 CONFIG_VORTEX=y
 # CONFIG_TYPHOON is not set
-
-#
-# Tulip family network device support
-#
 CONFIG_NET_TULIP=y
 # CONFIG_DE2104X is not set
 CONFIG_TULIP=y
@@ -773,7 +721,8 @@ CONFIG_TULIP=y
 # CONFIG_HP100 is not set
 CONFIG_NET_PCI=y
 # CONFIG_PCNET32 is not set
-# CONFIG_AMD8111_ETH is not set
+CONFIG_AMD8111_ETH=y
+# CONFIG_AMD8111E_NAPI is not set
 # CONFIG_ADAPTEC_STARFIRE is not set
 CONFIG_B44=y
 CONFIG_FORCEDETH=y
@@ -808,7 +757,6 @@ CONFIG_E1000=y
 # CONFIG_SIS190 is not set
 # CONFIG_SKGE is not set
 # CONFIG_SKY2 is not set
-# CONFIG_SK98LIN is not set
 # CONFIG_VIA_VELOCITY is not set
 CONFIG_TIGON3=y
 CONFIG_BNX2=y
@@ -823,10 +771,6 @@ CONFIG_S2IO=m
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_MLX4_CORE is not set
-
-#
-# Token Ring devices
-#
 # CONFIG_TR is not set
 
 #
@@ -855,15 +799,7 @@ CONFIG_NETCONSOLE=y
 CONFIG_NETPOLL=y
 # CONFIG_NETPOLL_TRAP is not set
 CONFIG_NET_POLL_CONTROLLER=y
-
-#
-# ISDN subsystem
-#
 # CONFIG_ISDN is not set
-
-#
-# Telephony Support
-#
 # CONFIG_PHONE is not set
 
 #
@@ -871,6 +807,7 @@ CONFIG_NET_POLL_CONTROLLER=y
 #
 CONFIG_INPUT=y
 # CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
 
 #
 # Userland interfaces
@@ -936,6 +873,7 @@ CONFIG_HW_CONSOLE=y
 #
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_FIX_EARLYCON_MEM=y
 CONFIG_SERIAL_8250_PCI=y
 CONFIG_SERIAL_8250_PNP=y
 CONFIG_SERIAL_8250_NR_UARTS=4
@@ -951,16 +889,11 @@ CONFIG_SERIAL_CORE_CONSOLE=y
 CONFIG_UNIX98_PTYS=y
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=256
-
-#
-# IPMI
-#
 # CONFIG_IPMI_HANDLER is not set
 # CONFIG_WATCHDOG is not set
 CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_INTEL=y
 CONFIG_HW_RANDOM_AMD=y
-# CONFIG_HW_RANDOM_GEODE is not set
 # CONFIG_NVRAM is not set
 CONFIG_RTC=y
 # CONFIG_R3964 is not set
@@ -979,127 +912,19 @@ CONFIG_HPET=y
 # CONFIG_HPET_RTC_IRQ is not set
 CONFIG_HPET_MMAP=y
 # CONFIG_HANGCHECK_TIMER is not set
-
-#
-# TPM devices
-#
 # CONFIG_TCG_TPM is not set
 # CONFIG_TELCLOCK is not set
 CONFIG_DEVPORT=y
-CONFIG_I2C=m
-CONFIG_I2C_BOARDINFO=y
-CONFIG_I2C_CHARDEV=m
-
-#
-# I2C Algorithms
-#
-# CONFIG_I2C_ALGOBIT is not set
-# CONFIG_I2C_ALGOPCF is not set
-# CONFIG_I2C_ALGOPCA is not set
-
-#
-# I2C Hardware Bus support
-#
-# CONFIG_I2C_ALI1535 is not set
-# CONFIG_I2C_ALI1563 is not set
-# CONFIG_I2C_ALI15X3 is not set
-# CONFIG_I2C_AMD756 is not set
-# CONFIG_I2C_AMD8111 is not set
-# CONFIG_I2C_I801 is not set
-# CONFIG_I2C_I810 is not set
-# CONFIG_I2C_PIIX4 is not set
-# CONFIG_I2C_NFORCE2 is not set
-# CONFIG_I2C_OCORES is not set
-# CONFIG_I2C_PARPORT_LIGHT is not set
-# CONFIG_I2C_PROSAVAGE is not set
-# CONFIG_I2C_SAVAGE4 is not set
-# CONFIG_I2C_SIMTEC is not set
-# CONFIG_I2C_SIS5595 is not set
-# CONFIG_I2C_SIS630 is not set
-# CONFIG_I2C_SIS96X is not set
-# CONFIG_I2C_STUB is not set
-# CONFIG_I2C_TINY_USB is not set
-# CONFIG_I2C_VIA is not set
-# CONFIG_I2C_VIAPRO is not set
-# CONFIG_I2C_VOODOO3 is not set
-
-#
-# Miscellaneous I2C Chip support
-#
-# CONFIG_SENSORS_DS1337 is not set
-# CONFIG_SENSORS_DS1374 is not set
-# CONFIG_SENSORS_EEPROM is not set
-# CONFIG_SENSORS_PCF8574 is not set
-# CONFIG_SENSORS_PCA9539 is not set
-# CONFIG_SENSORS_PCF8591 is not set
-# CONFIG_SENSORS_MAX6875 is not set
-# CONFIG_I2C_DEBUG_CORE is not set
-# CONFIG_I2C_DEBUG_ALGO is not set
-# CONFIG_I2C_DEBUG_BUS is not set
-# CONFIG_I2C_DEBUG_CHIP is not set
+# CONFIG_I2C is not set
 
 #
 # SPI support
 #
 # CONFIG_SPI is not set
 # CONFIG_SPI_MASTER is not set
-
-#
-# Dallas's 1-wire bus
-#
 # CONFIG_W1 is not set
-CONFIG_HWMON=y
-# CONFIG_HWMON_VID is not set
-# CONFIG_SENSORS_ABITUGURU is not set
-# CONFIG_SENSORS_AD7418 is not set
-# CONFIG_SENSORS_ADM1021 is not set
-# CONFIG_SENSORS_ADM1025 is not set
-# CONFIG_SENSORS_ADM1026 is not set
-# CONFIG_SENSORS_ADM1029 is not set
-# CONFIG_SENSORS_ADM1031 is not set
-# CONFIG_SENSORS_ADM9240 is not set
-# CONFIG_SENSORS_K8TEMP is not set
-# CONFIG_SENSORS_ASB100 is not set
-# CONFIG_SENSORS_ATXP1 is not set
-# CONFIG_SENSORS_DS1621 is not set
-# CONFIG_SENSORS_F71805F is not set
-# CONFIG_SENSORS_FSCHER is not set
-# CONFIG_SENSORS_FSCPOS is not set
-# CONFIG_SENSORS_GL518SM is not set
-# CONFIG_SENSORS_GL520SM is not set
-CONFIG_SENSORS_CORETEMP=y
-# CONFIG_SENSORS_IT87 is not set
-# CONFIG_SENSORS_LM63 is not set
-# CONFIG_SENSORS_LM75 is not set
-# CONFIG_SENSORS_LM77 is not set
-# CONFIG_SENSORS_LM78 is not set
-# CONFIG_SENSORS_LM80 is not set
-# CONFIG_SENSORS_LM83 is not set
-# CONFIG_SENSORS_LM85 is not set
-# CONFIG_SENSORS_LM87 is not set
-# CONFIG_SENSORS_LM90 is not set
-# CONFIG_SENSORS_LM92 is not set
-# CONFIG_SENSORS_MAX1619 is not set
-# CONFIG_SENSORS_MAX6650 is not set
-# CONFIG_SENSORS_PC87360 is not set
-# CONFIG_SENSORS_PC87427 is not set
-# CONFIG_SENSORS_SIS5595 is not set
-# CONFIG_SENSORS_SMSC47M1 is not set
-# CONFIG_SENSORS_SMSC47M192 is not set
-CONFIG_SENSORS_SMSC47B397=m
-# CONFIG_SENSORS_VIA686A is not set
-# CONFIG_SENSORS_VT1211 is not set
-# CONFIG_SENSORS_VT8231 is not set
-# CONFIG_SENSORS_W83781D is not set
-# CONFIG_SENSORS_W83791D is not set
-# CONFIG_SENSORS_W83792D is not set
-# CONFIG_SENSORS_W83793 is not set
-# CONFIG_SENSORS_W83L785TS is not set
-# CONFIG_SENSORS_W83627HF is not set
-# CONFIG_SENSORS_W83627EHF is not set
-# CONFIG_SENSORS_HDAPS is not set
-# CONFIG_SENSORS_APPLESMC is not set
-# CONFIG_HWMON_DEBUG_CHIP is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_HWMON is not set
 
 #
 # Multifunction device drivers
@@ -1149,15 +974,11 @@ CONFIG_SOUND=y
 # Open Sound System
 #
 CONFIG_SOUND_PRIME=y
-# CONFIG_OSS_OBSOLETE is not set
 # CONFIG_SOUND_TRIDENT is not set
 # CONFIG_SOUND_MSNDCLAS is not set
 # CONFIG_SOUND_MSNDPIN is not set
 # CONFIG_SOUND_OSS is not set
-
-#
-# HID Devices
-#
+CONFIG_HID_SUPPORT=y
 CONFIG_HID=y
 # CONFIG_HID_DEBUG is not set
 
@@ -1168,10 +989,7 @@ CONFIG_USB_HID=y
 # CONFIG_USB_HIDINPUT_POWERBOOK is not set
 # CONFIG_HID_FF is not set
 # CONFIG_USB_HIDDEV is not set
-
-#
-# USB support
-#
+CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
 CONFIG_USB_ARCH_HAS_EHCI=y
@@ -1185,6 +1003,7 @@ CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_DEVICE_CLASS is not set
 # CONFIG_USB_DYNAMIC_MINORS is not set
 # CONFIG_USB_SUSPEND is not set
+# CONFIG_USB_PERSIST is not set
 # CONFIG_USB_OTG is not set
 
 #
@@ -1194,7 +1013,6 @@ CONFIG_USB_EHCI_HCD=y
 # CONFIG_USB_EHCI_SPLIT_ISO is not set
 # CONFIG_USB_EHCI_ROOT_HUB_TT is not set
 # CONFIG_USB_EHCI_TT_NEWSCHED is not set
-# CONFIG_USB_EHCI_BIG_ENDIAN_MMIO is not set
 # CONFIG_USB_ISP116X_HCD is not set
 CONFIG_USB_OHCI_HCD=y
 # CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set
@@ -1202,6 +1020,7 @@ CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_OHCI_LITTLE_ENDIAN=y
 CONFIG_USB_UHCI_HCD=y
 # CONFIG_USB_SL811_HCD is not set
+# CONFIG_USB_R8A66597_HCD is not set
 
 #
 # USB Device Class drivers
@@ -1292,15 +1111,7 @@ CONFIG_USB_MON=y
 #
 # LED Triggers
 #
-
-#
-# InfiniBand support
-#
 # CONFIG_INFINIBAND is not set
-
-#
-# EDAC - error detection and reporting (RAS) (EXPERIMENTAL)
-#
 # CONFIG_EDAC is not set
 
 #
@@ -1320,11 +1131,13 @@ CONFIG_USB_MON=y
 #
 # DMA Devices
 #
+CONFIG_VIRTUALIZATION=y
+# CONFIG_KVM is not set
 
 #
-# Virtualization
+# Userspace I/O
 #
-# CONFIG_KVM is not set
+# CONFIG_UIO is not set
 
 #
 # Firmware Drivers
@@ -1332,6 +1145,7 @@ CONFIG_USB_MON=y
 # CONFIG_EDD is not set
 # CONFIG_DELL_RBU is not set
 # CONFIG_DCDBAS is not set
+CONFIG_DMIID=y
 
 #
 # File systems
@@ -1447,7 +1261,6 @@ CONFIG_SUNRPC=y
 # CONFIG_NCP_FS is not set
 # CONFIG_CODA_FS is not set
 # CONFIG_AFS_FS is not set
-# CONFIG_9P_FS is not set
 
 #
 # Partition Types
@@ -1524,8 +1337,9 @@ CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
 CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_SCHED_DEBUG is not set
 # CONFIG_SCHEDSTATS is not set
-# CONFIG_TIMER_STATS is not set
+CONFIG_TIMER_STATS=y
 # CONFIG_DEBUG_SLAB is not set
 # CONFIG_DEBUG_RT_MUTEXES is not set
 # CONFIG_RT_MUTEX_TESTER is not set
@@ -1533,6 +1347,7 @@ CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_DEBUG_MUTEXES is not set
 # CONFIG_DEBUG_LOCK_ALLOC is not set
 # CONFIG_PROVE_LOCKING is not set
+# CONFIG_LOCK_STAT is not set
 # CONFIG_DEBUG_SPINLOCK_SLEEP is not set
 # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
 # CONFIG_DEBUG_KOBJECT is not set
@@ -1541,8 +1356,6 @@ CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_DEBUG_VM is not set
 # CONFIG_DEBUG_LIST is not set
 # CONFIG_FRAME_POINTER is not set
-CONFIG_UNWIND_INFO=y
-CONFIG_STACK_UNWIND=y
 # CONFIG_FORCED_INLINING is not set
 # CONFIG_RCU_TORTURE_TEST is not set
 # CONFIG_LKDTM is not set
@@ -1557,10 +1370,6 @@ CONFIG_DEBUG_STACKOVERFLOW=y
 #
 # CONFIG_KEYS is not set
 # CONFIG_SECURITY is not set
-
-#
-# Cryptographic options
-#
 # CONFIG_CRYPTO is not set
 
 #
@@ -1571,6 +1380,7 @@ CONFIG_BITREVERSE=y
 # CONFIG_CRC16 is not set
 # CONFIG_CRC_ITU_T is not set
 CONFIG_CRC32=y
+# CONFIG_CRC7 is not set
 # CONFIG_LIBCRC32C is not set
 CONFIG_ZLIB_INFLATE=y
 CONFIG_PLIST=y
diff --git a/arch/x86_64/ia32/ia32_binfmt.c b/arch/x86_64/ia32/ia32_binfmt.c
index ed56a8806eab..b70f3e7cf06c 100644
--- a/arch/x86_64/ia32/ia32_binfmt.c
+++ b/arch/x86_64/ia32/ia32_binfmt.c
@@ -38,6 +38,7 @@
 
 int sysctl_vsyscall32 = 1;
 
+#undef ARCH_DLINFO
 #define ARCH_DLINFO do {  \
         if (sysctl_vsyscall32) { \
         NEW_AUX_ENT(AT_SYSINFO, (u32)(u64)VSYSCALL32_VSYSCALL); \
diff --git a/arch/x86_64/ia32/ia32entry.S b/arch/x86_64/ia32/ia32entry.S
index 3f66e970d86f..938278697e20 100644
--- a/arch/x86_64/ia32/ia32entry.S
+++ b/arch/x86_64/ia32/ia32entry.S
@@ -104,7 +104,7 @@ ENTRY(ia32_sysenter_target)
         pushq   %rax
         CFI_ADJUST_CFA_OFFSET 8
         cld
-        SAVE_ARGS 0,0,0
+        SAVE_ARGS 0,0,1
         /* no need to do an access_ok check here because rbp has been
            32bit zero extended */ 
 1:      movl    (%rbp),%r9d
@@ -294,7 +294,7 @@ ia32_badarg:
  */                             
 
 ENTRY(ia32_syscall)
-        CFI_STARTPROC   simple
+        CFI_STARTPROC32 simple
         CFI_SIGNAL_FRAME
         CFI_DEF_CFA     rsp,SS+8-RIP
         /*CFI_REL_OFFSET        ss,SS-RIP*/
@@ -330,6 +330,7 @@ ia32_sysret:
 
 ia32_tracesys:                   
         SAVE_REST
+        CLEAR_RREGS
         movq $-ENOSYS,RAX(%rsp) /* really needed? */
         movq %rsp,%rdi        /* &pt_regs -> arg1 */
         call syscall_trace_enter
diff --git a/arch/x86_64/kernel/aperture.c b/arch/x86_64/kernel/aperture.c
index a3d450d6c15b..8f681cae7bf7 100644
--- a/arch/x86_64/kernel/aperture.c
+++ b/arch/x86_64/kernel/aperture.c
@@ -20,7 +20,7 @@
 #include <linux/ioport.h>
 #include <asm/e820.h>
 #include <asm/io.h>
-#include <asm/proto.h>
+#include <asm/iommu.h>
 #include <asm/pci-direct.h>
 #include <asm/dma.h>
 #include <asm/k8.h>
@@ -214,7 +214,7 @@ void __init iommu_hole_init(void)
         if (iommu_aperture_disabled || !fix_aperture || !early_pci_allowed())
                 return;
 
-        printk("Checking aperture...\n"); 
+        printk(KERN_INFO  "Checking aperture...\n");
 
         fix = 0;
         for (num = 24; num < 32; num++) {               
diff --git a/arch/x86_64/kernel/apic.c b/arch/x86_64/kernel/apic.c
index 1b0e07bb8728..900ff38d68de 100644
--- a/arch/x86_64/kernel/apic.c
+++ b/arch/x86_64/kernel/apic.c
@@ -92,8 +92,9 @@ unsigned int safe_apic_wait_icr_idle(void)
 void enable_NMI_through_LVT0 (void * dummy)
 {
         unsigned int v;
-        
-        v = APIC_DM_NMI;                        /* unmask and set to NMI */
+
+        /* unmask and set to NMI */
+        v = APIC_DM_NMI;
         apic_write(APIC_LVT0, v);
 }
 
@@ -120,7 +121,7 @@ void ack_bad_irq(unsigned int irq)
          * holds up an irq slot - in excessive cases (when multiple
          * unexpected vectors occur) that might lock up the APIC
          * completely.
-         * But don't ack when the APIC is disabled. -AK
+         * But don't ack when the APIC is disabled. -AK
          */
         if (!disable_apic)
                 ack_APIC_irq();
@@ -616,7 +617,7 @@ early_param("apic", apic_set_verbosity);
  * Detect and enable local APICs on non-SMP boards.
  * Original code written by Keir Fraser.
  * On AMD64 we trust the BIOS - if it says no APIC it is likely
- * not correctly set up (usually the APIC timer won't work etc.) 
+ * not correctly set up (usually the APIC timer won't work etc.)
  */
 
 static int __init detect_init_APIC (void)
@@ -789,13 +790,13 @@ static void setup_APIC_timer(unsigned int clocks)
         local_irq_save(flags);
 
         /* wait for irq slice */
-        if (hpet_address && hpet_use_timer) {
-                int trigger = hpet_readl(HPET_T0_CMP);
-                while (hpet_readl(HPET_COUNTER) >= trigger)
-                        /* do nothing */ ;
-                while (hpet_readl(HPET_COUNTER) <  trigger)
-                        /* do nothing */ ;
-        } else {
+        if (hpet_address && hpet_use_timer) {
+                int trigger = hpet_readl(HPET_T0_CMP);
+                while (hpet_readl(HPET_COUNTER) >= trigger)
+                        /* do nothing */ ;
+                while (hpet_readl(HPET_COUNTER) <  trigger)
+                        /* do nothing */ ;
+        } else {
                 int c1, c2;
                 outb_p(0x00, 0x43);
                 c2 = inb_p(0x40);
@@ -881,10 +882,10 @@ static unsigned int calibration_result;
 
 void __init setup_boot_APIC_clock (void)
 {
-        if (disable_apic_timer) { 
-                printk(KERN_INFO "Disabling APIC timer\n"); 
-                return; 
-        } 
+        if (disable_apic_timer) {
+                printk(KERN_INFO "Disabling APIC timer\n");
+                return;
+        }
 
         printk(KERN_INFO "Using local APIC timer interrupts.\n");
         using_apic_timer = 1;
@@ -990,8 +991,8 @@ int setup_profiling_timer(unsigned int multiplier)
         return -EINVAL;
 }
 
-void setup_APIC_extened_lvt(unsigned char lvt_off, unsigned char vector,
-                            unsigned char msg_type, unsigned char mask)
+void setup_APIC_extended_lvt(unsigned char lvt_off, unsigned char vector,
+                             unsigned char msg_type, unsigned char mask)
 {
         unsigned long reg = (lvt_off << 4) + K8_APIC_EXT_LVT_BASE;
         unsigned int  v   = (mask << 16) | (msg_type << 8) | vector;
@@ -1128,20 +1129,6 @@ asmlinkage void smp_spurious_interrupt(void)
         if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
                 ack_APIC_irq();
 
-#if 0
-        static unsigned long last_warning; 
-        static unsigned long skipped; 
-
-        /* see sw-dev-man vol 3, chapter 7.4.13.5 */
-        if (time_before(last_warning+30*HZ,jiffies)) { 
-                printk(KERN_INFO "spurious APIC interrupt on CPU#%d, %ld skipped.\n",
-                       smp_processor_id(), skipped);
-                last_warning = jiffies; 
-                skipped = 0;
-        } else { 
-                skipped++; 
-        } 
-#endif 
         irq_exit();
 }
 
@@ -1173,11 +1160,11 @@ asmlinkage void smp_error_interrupt(void)
            7: Illegal register address
         */
         printk (KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n",
-                smp_processor_id(), v , v1);
+                smp_processor_id(), v , v1);
         irq_exit();
 }
 
-int disable_apic; 
+int disable_apic;
 
 /*
  * This initializes the IO-APIC and APIC hardware if this is
@@ -1185,11 +1172,11 @@ int disable_apic;
  */
 int __init APIC_init_uniprocessor (void)
 {
-        if (disable_apic) { 
+        if (disable_apic) {
                 printk(KERN_INFO "Apic disabled\n");
-                return -1; 
+                return -1;
         }
-        if (!cpu_has_apic) { 
+        if (!cpu_has_apic) {
                 disable_apic = 1;
                 printk(KERN_INFO "Apic disabled by BIOS\n");
                 return -1;
@@ -1211,8 +1198,8 @@ int __init APIC_init_uniprocessor (void)
         return 0;
 }
 
-static __init int setup_disableapic(char *str) 
-{ 
+static __init int setup_disableapic(char *str)
+{
         disable_apic = 1;
         clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
         return 0;
@@ -1220,10 +1207,10 @@ static __init int setup_disableapic(char *str)
 early_param("disableapic", setup_disableapic);
 
 /* same as disableapic, for compatibility */
-static __init int setup_nolapic(char *str) 
-{ 
+static __init int setup_nolapic(char *str)
+{
         return setup_disableapic(str);
-} 
+}
 early_param("nolapic", setup_nolapic);
 
 static int __init parse_lapic_timer_c2_ok(char *arg)
@@ -1233,13 +1220,13 @@ static int __init parse_lapic_timer_c2_ok(char *arg)
 }
 early_param("lapic_timer_c2_ok", parse_lapic_timer_c2_ok);
 
-static __init int setup_noapictimer(char *str) 
-{ 
+static __init int setup_noapictimer(char *str)
+{
         if (str[0] != ' ' && str[0] != 0)
                 return 0;
         disable_apic_timer = 1;
         return 1;
-} 
+}
 
 static __init int setup_apicmaintimer(char *str)
 {
@@ -1264,5 +1251,5 @@ static __init int setup_apicpmtimer(char *s)
 }
 __setup("apicpmtimer", setup_apicpmtimer);
 
-__setup("noapictimer", setup_noapictimer); 
+__setup("noapictimer", setup_noapictimer);
 
diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c
index 13c6c37610e0..0f4d5e209e9b 100644
--- a/arch/x86_64/kernel/e820.c
+++ b/arch/x86_64/kernel/e820.c
@@ -194,37 +194,6 @@ unsigned long __init e820_end_of_ram(void)
 }
 
 /*
- * Find the hole size in the range.
- */
-unsigned long __init e820_hole_size(unsigned long start, unsigned long end)
-{
-        unsigned long ram = 0;
-        int i;
-
-        for (i = 0; i < e820.nr_map; i++) {
-                struct e820entry *ei = &e820.map[i];
-                unsigned long last, addr;
-
-                if (ei->type != E820_RAM ||
-                    ei->addr+ei->size <= start ||
-                    ei->addr >= end)
-                        continue;
-
-                addr = round_up(ei->addr, PAGE_SIZE);
-                if (addr < start)
-                        addr = start;
-
-                last = round_down(ei->addr + ei->size, PAGE_SIZE);
-                if (last >= end)
-                        last = end;
-
-                if (last > addr)
-                        ram += last - addr;
-        }
-        return ((end - start) - ram);
-}
-
-/*
  * Mark e820 reserved areas as busy for the resource manager.
  */
 void __init e820_reserve_resources(void)
@@ -289,47 +258,61 @@ void __init e820_mark_nosave_regions(void)
         }
 }
 
-/* Walk the e820 map and register active regions within a node */
-void __init
-e820_register_active_regions(int nid, unsigned long start_pfn,
-                                                        unsigned long end_pfn)
+/*
+ * Finds an active region in the address range from start_pfn to end_pfn and
+ * returns its range in ei_startpfn and ei_endpfn for the e820 entry.
+ */
+static int __init e820_find_active_region(const struct e820entry *ei,
+                                          unsigned long start_pfn,
+                                          unsigned long end_pfn,
+                                          unsigned long *ei_startpfn,
+                                          unsigned long *ei_endpfn)
 {
-        int i;
-        unsigned long ei_startpfn, ei_endpfn;
-        for (i = 0; i < e820.nr_map; i++) {
-                struct e820entry *ei = &e820.map[i];
-                ei_startpfn = round_up(ei->addr, PAGE_SIZE) >> PAGE_SHIFT;
-                ei_endpfn = round_down(ei->addr + ei->size, PAGE_SIZE)
-                                                                >> PAGE_SHIFT;
+        *ei_startpfn = round_up(ei->addr, PAGE_SIZE) >> PAGE_SHIFT;
+        *ei_endpfn = round_down(ei->addr + ei->size, PAGE_SIZE) >> PAGE_SHIFT;
 
-                /* Skip map entries smaller than a page */
-                if (ei_startpfn >= ei_endpfn)
-                        continue;
+        /* Skip map entries smaller than a page */
+        if (*ei_startpfn >= *ei_endpfn)
+                return 0;
 
-                /* Check if end_pfn_map should be updated */
-                if (ei->type != E820_RAM && ei_endpfn > end_pfn_map)
-                        end_pfn_map = ei_endpfn;
+        /* Check if end_pfn_map should be updated */
+        if (ei->type != E820_RAM && *ei_endpfn > end_pfn_map)
+                end_pfn_map = *ei_endpfn;
 
-                /* Skip if map is outside the node */
-                if (ei->type != E820_RAM ||
-                                ei_endpfn <= start_pfn ||
-                                ei_startpfn >= end_pfn)
-                        continue;
+        /* Skip if map is outside the node */
+        if (ei->type != E820_RAM || *ei_endpfn <= start_pfn ||
+                                    *ei_startpfn >= end_pfn)
+                return 0;
 
-                /* Check for overlaps */
-                if (ei_startpfn < start_pfn)
-                        ei_startpfn = start_pfn;
-                if (ei_endpfn > end_pfn)
-                        ei_endpfn = end_pfn;
+        /* Check for overlaps */
+        if (*ei_startpfn < start_pfn)
+                *ei_startpfn = start_pfn;
+        if (*ei_endpfn > end_pfn)
+                *ei_endpfn = end_pfn;
 
-                /* Obey end_user_pfn to save on memmap */
-                if (ei_startpfn >= end_user_pfn)
-                        continue;
-                if (ei_endpfn > end_user_pfn)
-                        ei_endpfn = end_user_pfn;
+        /* Obey end_user_pfn to save on memmap */
+        if (*ei_startpfn >= end_user_pfn)
+                return 0;
+        if (*ei_endpfn > end_user_pfn)
+                *ei_endpfn = end_user_pfn;
 
-                add_active_range(nid, ei_startpfn, ei_endpfn);
-        }
+        return 1;
+}
+
+/* Walk the e820 map and register active regions within a node */
+void __init
+e820_register_active_regions(int nid, unsigned long start_pfn,
+                                                        unsigned long end_pfn)
+{
+        unsigned long ei_startpfn;
+        unsigned long ei_endpfn;
+        int i;
+
+        for (i = 0; i < e820.nr_map; i++)
+                if (e820_find_active_region(&e820.map[i],
+                                            start_pfn, end_pfn,
+                                            &ei_startpfn, &ei_endpfn))
+                        add_active_range(nid, ei_startpfn, ei_endpfn);
 }
 
 /* 
@@ -350,12 +333,35 @@ void __init add_memory_region(unsigned long start, unsigned long size, int type)
         e820.nr_map++;
 }
 
+/*
+ * Find the hole size (in bytes) in the memory range.
+ * @start: starting address of the memory range to scan
+ * @end: ending address of the memory range to scan
+ */
+unsigned long __init e820_hole_size(unsigned long start, unsigned long end)
+{
+        unsigned long start_pfn = start >> PAGE_SHIFT;
+        unsigned long end_pfn = end >> PAGE_SHIFT;
+        unsigned long ei_startpfn;
+        unsigned long ei_endpfn;
+        unsigned long ram = 0;
+        int i;
+
+        for (i = 0; i < e820.nr_map; i++) {
+                if (e820_find_active_region(&e820.map[i],
+                                            start_pfn, end_pfn,
+                                            &ei_startpfn, &ei_endpfn))
+                        ram += ei_endpfn - ei_startpfn;
+        }
+        return end - start - (ram << PAGE_SHIFT);
+}
+
 void __init e820_print_map(char *who)
 {
         int i;
 
         for (i = 0; i < e820.nr_map; i++) {
-                printk(" %s: %016Lx - %016Lx ", who,
+                printk(KERN_INFO " %s: %016Lx - %016Lx ", who,
                         (unsigned long long) e820.map[i].addr,
                         (unsigned long long) (e820.map[i].addr + e820.map[i].size));
                 switch (e820.map[i].type) {
diff --git a/arch/x86_64/kernel/early-quirks.c b/arch/x86_64/kernel/early-quirks.c
index 990d9c218a5d..13aa4fd728f3 100644
--- a/arch/x86_64/kernel/early-quirks.c
+++ b/arch/x86_64/kernel/early-quirks.c
@@ -14,6 +14,7 @@
 #include <linux/pci_ids.h>
 #include <asm/pci-direct.h>
 #include <asm/proto.h>
+#include <asm/iommu.h>
 #include <asm/dma.h>
 
 static void __init via_bugs(void)
diff --git a/arch/x86_64/kernel/entry.S b/arch/x86_64/kernel/entry.S
index a67f87bf4015..830cfc6ee8cb 100644
--- a/arch/x86_64/kernel/entry.S
+++ b/arch/x86_64/kernel/entry.S
@@ -282,7 +282,7 @@ sysret_careful:
 sysret_signal:
         TRACE_IRQS_ON
         sti
-        testl $(_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SINGLESTEP),%edx
+        testl $(_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY),%edx
         jz    1f
 
         /* Really a signal */
@@ -375,7 +375,7 @@ int_very_careful:
         jmp int_restore_rest
         
 int_signal:
-        testl $(_TIF_NOTIFY_RESUME|_TIF_SIGPENDING|_TIF_SINGLESTEP),%edx
+        testl $(_TIF_NOTIFY_RESUME|_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY),%edx
         jz 1f
         movq %rsp,%rdi          # &ptregs -> arg1
         xorl %esi,%esi          # oldset -> arg2
@@ -599,7 +599,7 @@ retint_careful:
         jmp retint_check
         
 retint_signal:
-        testl $(_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SINGLESTEP),%edx
+        testl $(_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY),%edx
         jz    retint_swapgs
         TRACE_IRQS_ON
         sti
diff --git a/arch/x86_64/kernel/head.S b/arch/x86_64/kernel/head.S
index 941c84baecc8..e89abcdbdde8 100644
--- a/arch/x86_64/kernel/head.S
+++ b/arch/x86_64/kernel/head.S
@@ -25,7 +25,7 @@
  */
 
         .text
-        .section .bootstrap.text
+        .section .text.head
         .code64
         .globl startup_64
 startup_64:
@@ -243,10 +243,16 @@ ENTRY(secondary_startup_64)
         lretq
 
         /* SMP bootup changes these two */
+#ifndef CONFIG_HOTPLUG_CPU
+        .pushsection .init.data
+#endif
         .align  8
         .globl  initial_code
 initial_code:
         .quad   x86_64_start_kernel
+#ifndef CONFIG_HOTPLUG_CPU
+        .popsection
+#endif
         .globl init_rsp
 init_rsp:
         .quad  init_thread_union+THREAD_SIZE-8
diff --git a/arch/x86_64/kernel/hpet.c b/arch/x86_64/kernel/hpet.c
index b8286968662d..e2d1b912e154 100644
--- a/arch/x86_64/kernel/hpet.c
+++ b/arch/x86_64/kernel/hpet.c
@@ -133,7 +133,7 @@ struct clocksource clocksource_hpet = {
         .vread          = vread_hpet,
 };
 
-int hpet_arch_init(void)
+int __init hpet_arch_init(void)
 {
         unsigned int id;
         u64 tmp;
@@ -190,7 +190,7 @@ int hpet_reenable(void)
  */
 
 #define TICK_COUNT 100000000
-#define TICK_MIN   5000
+#define SMI_THRESHOLD 50000
 #define MAX_TRIES  5
 
 /*
@@ -205,7 +205,7 @@ static void __init read_hpet_tsc(int *hpet, int *tsc)
                 tsc1 = get_cycles_sync();
                 hpet1 = hpet_readl(HPET_COUNTER);
                 tsc2 = get_cycles_sync();
-                if (tsc2 - tsc1 > TICK_MIN)
+                if ((tsc2 - tsc1) < SMI_THRESHOLD)
                         break;
         }
         *hpet = hpet1;
@@ -439,7 +439,7 @@ int hpet_rtc_dropped_irq(void)
         return 1;
 }
 
-irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
 {
         struct rtc_time curr_time;
         unsigned long rtc_int_flag = 0;
diff --git a/arch/x86_64/kernel/i8259.c b/arch/x86_64/kernel/i8259.c
index 4b326655b208..948cae646099 100644
--- a/arch/x86_64/kernel/i8259.c
+++ b/arch/x86_64/kernel/i8259.c
@@ -444,24 +444,6 @@ void __init init_ISA_irqs (void)
         }
 }
 
-void apic_timer_interrupt(void);
-void spurious_interrupt(void);
-void error_interrupt(void);
-void reschedule_interrupt(void);
-void call_function_interrupt(void);
-void irq_move_cleanup_interrupt(void);
-void invalidate_interrupt0(void);
-void invalidate_interrupt1(void);
-void invalidate_interrupt2(void);
-void invalidate_interrupt3(void);
-void invalidate_interrupt4(void);
-void invalidate_interrupt5(void);
-void invalidate_interrupt6(void);
-void invalidate_interrupt7(void);
-void thermal_interrupt(void);
-void threshold_interrupt(void);
-void i8254_timer_resume(void);
-
 static void setup_timer_hardware(void)
 {
         outb_p(0x34,0x43);              /* binary, mode 2, LSB/MSB, ch 0 */
diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c
index 1c6c6f724573..050141c0602b 100644
--- a/arch/x86_64/kernel/io_apic.c
+++ b/arch/x86_64/kernel/io_apic.c
@@ -152,6 +152,32 @@ static inline void io_apic_modify(unsigned int apic, unsigned int value)
         writel(value, &io_apic->data);
 }
 
+static int io_apic_level_ack_pending(unsigned int irq)
+{
+        struct irq_pin_list *entry;
+        unsigned long flags;
+        int pending = 0;
+
+        spin_lock_irqsave(&ioapic_lock, flags);
+        entry = irq_2_pin + irq;
+        for (;;) {
+                unsigned int reg;
+                int pin;
+
+                pin = entry->pin;
+                if (pin == -1)
+                        break;
+                reg = io_apic_read(entry->apic, 0x10 + pin*2);
+                /* Is the remote IRR bit set? */
+                pending |= (reg >> 14) & 1;
+                if (!entry->next)
+                        break;
+                entry = irq_2_pin + entry->next;
+        }
+        spin_unlock_irqrestore(&ioapic_lock, flags);
+        return pending;
+}
+
 /*
  * Synchronize the IO-APIC and the CPU by doing
  * a dummy read from the IO-APIC
@@ -1418,9 +1444,37 @@ static void ack_apic_level(unsigned int irq)
         ack_APIC_irq();
 
         /* Now we can move and renable the irq */
-        move_masked_irq(irq);
-        if (unlikely(do_unmask_irq))
+        if (unlikely(do_unmask_irq)) {
+                /* Only migrate the irq if the ack has been received.
+                 *
+                 * On rare occasions the broadcast level triggered ack gets
+                 * delayed going to ioapics, and if we reprogram the
+                 * vector while Remote IRR is still set the irq will never
+                 * fire again.
+                 *
+                 * To prevent this scenario we read the Remote IRR bit
+                 * of the ioapic.  This has two effects.
+                 * - On any sane system the read of the ioapic will
+                 *   flush writes (and acks) going to the ioapic from
+                 *   this cpu.
+                 * - We get to see if the ACK has actually been delivered.
+                 *
+                 * Based on failed experiments of reprogramming the
+                 * ioapic entry from outside of irq context starting
+                 * with masking the ioapic entry and then polling until
+                 * Remote IRR was clear before reprogramming the
+                 * ioapic I don't trust the Remote IRR bit to be
+                 * completey accurate.
+                 *
+                 * However there appears to be no other way to plug
+                 * this race, so if the Remote IRR bit is not
+                 * accurate and is causing problems then it is a hardware bug
+                 * and you can go talk to the chipset vendor about it.
+                 */
+                if (!io_apic_level_ack_pending(irq))
+                        move_masked_irq(irq);
                 unmask_IO_APIC_irq(irq);
+        }
 }
 
 static struct irq_chip ioapic_chip __read_mostly = {
diff --git a/arch/x86_64/kernel/kprobes.c b/arch/x86_64/kernel/kprobes.c
index d4a0d0ac9935..a30e004682e2 100644
--- a/arch/x86_64/kernel/kprobes.c
+++ b/arch/x86_64/kernel/kprobes.c
@@ -39,9 +39,9 @@
 #include <linux/module.h>
 #include <linux/kdebug.h>
 
-#include <asm/cacheflush.h>
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
+#include <asm/alternative.h>
 
 void jprobe_return_end(void);
 static void __kprobes arch_copy_kprobe(struct kprobe *p);
@@ -209,16 +209,12 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p)
 
 void __kprobes arch_arm_kprobe(struct kprobe *p)
 {
-        *p->addr = BREAKPOINT_INSTRUCTION;
-        flush_icache_range((unsigned long) p->addr,
-                           (unsigned long) p->addr + sizeof(kprobe_opcode_t));
+        text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1);
 }
 
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
-        *p->addr = p->opcode;
-        flush_icache_range((unsigned long) p->addr,
-                           (unsigned long) p->addr + sizeof(kprobe_opcode_t));
+        text_poke(p->addr, &p->opcode, 1);
 }
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c
index f3fb8174559e..a66d607f5b92 100644
--- a/arch/x86_64/kernel/mce.c
+++ b/arch/x86_64/kernel/mce.c
@@ -18,6 +18,8 @@
 #include <linux/capability.h>
 #include <linux/cpu.h>
 #include <linux/percpu.h>
+#include <linux/poll.h>
+#include <linux/thread_info.h>
 #include <linux/ctype.h>
 #include <linux/kmod.h>
 #include <linux/kdebug.h>
@@ -26,6 +28,7 @@
 #include <asm/mce.h>
 #include <asm/uaccess.h>
 #include <asm/smp.h>
+#include <asm/idle.h>
 
 #define MISC_MCELOG_MINOR 227
 #define NR_BANKS 6
@@ -34,13 +37,17 @@ atomic_t mce_entry;
 
 static int mce_dont_init;
 
-/* 0: always panic, 1: panic if deadlock possible, 2: try to avoid panic,
-   3: never panic or exit (for testing only) */
+/*
+ * Tolerant levels:
+ *   0: always panic on uncorrected errors, log corrected errors
+ *   1: panic or SIGBUS on uncorrected errors, log corrected errors
+ *   2: SIGBUS or log uncorrected errors (if possible), log corrected errors
+ *   3: never panic or SIGBUS, log all errors (for testing only)
+ */
 static int tolerant = 1;
 static int banks;
 static unsigned long bank[NR_BANKS] = { [0 ... NR_BANKS-1] = ~0UL };
-static unsigned long console_logged;
-static int notify_user;
+static unsigned long notify_user;
 static int rip_msr;
 static int mce_bootlog = 1;
 static atomic_t mce_events;
@@ -48,6 +55,8 @@ static atomic_t mce_events;
 static char trigger[128];
 static char *trigger_argv[2] = { trigger, NULL };
 
+static DECLARE_WAIT_QUEUE_HEAD(mce_wait);
+
 /*
  * Lockless MCE logging infrastructure.
  * This avoids deadlocks on printk locks without having to break locks. Also
@@ -94,8 +103,7 @@ void mce_log(struct mce *mce)
         mcelog.entry[entry].finished = 1;
         wmb();
 
-        if (!test_and_set_bit(0, &console_logged))
-                notify_user = 1;
+        set_bit(0, &notify_user);
 }
 
 static void print_mce(struct mce *m)
@@ -128,6 +136,7 @@ static void print_mce(struct mce *m)
 static void mce_panic(char *msg, struct mce *backup, unsigned long start)
 { 
         int i;
+
         oops_begin();
         for (i = 0; i < MCE_LOG_LEN; i++) {
                 unsigned long tsc = mcelog.entry[i].tsc;
@@ -139,10 +148,7 @@ static void mce_panic(char *msg, struct mce *backup, unsigned long start)
         }
         if (backup)
                 print_mce(backup);
-        if (tolerant >= 3)
-                printk("Fake panic: %s\n", msg);
-        else
-                panic(msg);
+        panic(msg);
 } 
 
 static int mce_available(struct cpuinfo_x86 *c)
@@ -167,17 +173,6 @@ static inline void mce_get_rip(struct mce *m, struct pt_regs *regs)
         }
 }
 
-static void do_mce_trigger(void)
-{
-        static atomic_t mce_logged;
-        int events = atomic_read(&mce_events);
-        if (events != atomic_read(&mce_logged) && trigger[0]) {
-                /* Small race window, but should be harmless.  */
-                atomic_set(&mce_logged, events);
-                call_usermodehelper(trigger, trigger_argv, NULL, UMH_NO_WAIT);
-        }
-}
-
 /* 
  * The actual machine check handler
  */
@@ -185,11 +180,19 @@ static void do_mce_trigger(void)
 void do_machine_check(struct pt_regs * regs, long error_code)
 {
         struct mce m, panicm;
-        int nowayout = (tolerant < 1); 
-        int kill_it = 0;
         u64 mcestart = 0;
         int i;
         int panicm_found = 0;
+        /*
+         * If no_way_out gets set, there is no safe way to recover from this
+         * MCE.  If tolerant is cranked up, we'll try anyway.
+         */
+        int no_way_out = 0;
+        /*
+         * If kill_it gets set, there might be a way to recover from this
+         * error.
+         */
+        int kill_it = 0;
 
         atomic_inc(&mce_entry);
 
@@ -201,8 +204,9 @@ void do_machine_check(struct pt_regs * regs, long error_code)
         memset(&m, 0, sizeof(struct mce));
         m.cpu = smp_processor_id();
         rdmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus);
+        /* if the restart IP is not valid, we're done for */
         if (!(m.mcgstatus & MCG_STATUS_RIPV))
-                kill_it = 1;
+                no_way_out = 1;
         
         rdtscll(mcestart);
         barrier();
@@ -221,10 +225,18 @@ void do_machine_check(struct pt_regs * regs, long error_code)
                         continue;
 
                 if (m.status & MCI_STATUS_EN) {
-                        /* In theory _OVER could be a nowayout too, but
-                           assume any overflowed errors were no fatal. */
-                        nowayout |= !!(m.status & MCI_STATUS_PCC);
-                        kill_it |= !!(m.status & MCI_STATUS_UC);
+                        /* if PCC was set, there's no way out */
+                        no_way_out |= !!(m.status & MCI_STATUS_PCC);
+                        /*
+                         * If this error was uncorrectable and there was
+                         * an overflow, we're in trouble.  If no overflow,
+                         * we might get away with just killing a task.
+                         */
+                        if (m.status & MCI_STATUS_UC) {
+                                if (tolerant < 1 || m.status & MCI_STATUS_OVER)
+                                        no_way_out = 1;
+                                kill_it = 1;
+                        }
                 }
 
                 if (m.status & MCI_STATUS_MISCV)
@@ -235,7 +247,6 @@ void do_machine_check(struct pt_regs * regs, long error_code)
                 mce_get_rip(&m, regs);
                 if (error_code >= 0)
                         rdtscll(m.tsc);
-                wrmsrl(MSR_IA32_MC0_STATUS + i*4, 0);
                 if (error_code != -2)
                         mce_log(&m);
 
@@ -251,45 +262,59 @@ void do_machine_check(struct pt_regs * regs, long error_code)
         }
 
         /* Never do anything final in the polling timer */
-        if (!regs) {
-                /* Normal interrupt context here. Call trigger for any new
-                   events. */
-                do_mce_trigger();
+        if (!regs)
                 goto out;
-        }
 
         /* If we didn't find an uncorrectable error, pick
            the last one (shouldn't happen, just being safe). */
         if (!panicm_found)
                 panicm = m;
-        if (nowayout)
+
+        /*
+         * If we have decided that we just CAN'T continue, and the user
+         *  has not set tolerant to an insane level, give up and die.
+         */
+        if (no_way_out && tolerant < 3)
                 mce_panic("Machine check", &panicm, mcestart);
-        if (kill_it) {
+
+        /*
+         * If the error seems to be unrecoverable, something should be
+         * done.  Try to kill as little as possible.  If we can kill just
+         * one task, do that.  If the user has set the tolerance very
+         * high, don't try to do anything at all.
+         */
+        if (kill_it && tolerant < 3) {
                 int user_space = 0;
 
-                if (m.mcgstatus & MCG_STATUS_RIPV)
+                /*
+                 * If the EIPV bit is set, it means the saved IP is the
+                 * instruction which caused the MCE.
+                 */
+                if (m.mcgstatus & MCG_STATUS_EIPV)
                         user_space = panicm.rip && (panicm.cs & 3);
-                
-                /* When the machine was in user space and the CPU didn't get
-                   confused it's normally not necessary to panic, unless you 
-                   are paranoid (tolerant == 0)
-
-                   RED-PEN could be more tolerant for MCEs in idle,
-                   but most likely they occur at boot anyways, where
-                   it is best to just halt the machine. */
-                if ((!user_space && (panic_on_oops || tolerant < 2)) ||
-                    (unsigned)current->pid <= 1)
-                        mce_panic("Uncorrected machine check", &panicm, mcestart);
-
-                /* do_exit takes an awful lot of locks and has as
-                   slight risk of deadlocking. If you don't want that
-                   don't set tolerant >= 2 */
-                if (tolerant < 3)
+
+                /*
+                 * If we know that the error was in user space, send a
+                 * SIGBUS.  Otherwise, panic if tolerance is low.
+                 *
+                 * do_exit() takes an awful lot of locks and has a slight
+                 * risk of deadlocking.
+                 */
+                if (user_space) {
                         do_exit(SIGBUS);
+                } else if (panic_on_oops || tolerant < 2) {
+                        mce_panic("Uncorrected machine check",
+                                &panicm, mcestart);
+                }
         }
 
+        /* notify userspace ASAP */
+        set_thread_flag(TIF_MCE_NOTIFY);
+
  out:
-        /* Last thing done in the machine check exception to clear state. */
+        /* the last thing we do is clear state */
+        for (i = 0; i < banks; i++)
+                wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0);
         wrmsrl(MSR_IA32_MCG_STATUS, 0);
  out2:
         atomic_dec(&mce_entry);
@@ -344,37 +369,69 @@ static void mcheck_timer(struct work_struct *work)
         on_each_cpu(mcheck_check_cpu, NULL, 1, 1);
 
         /*
-         * It's ok to read stale data here for notify_user and
-         * console_logged as we'll simply get the updated versions
-         * on the next mcheck_timer execution and atomic operations
-         * on console_logged act as synchronization for notify_user
-         * writes.
+         * Alert userspace if needed.  If we logged an MCE, reduce the
+         * polling interval, otherwise increase the polling interval.
          */
-        if (notify_user && console_logged) {
+        if (mce_notify_user()) {
+                next_interval = max(next_interval/2, HZ/100);
+        } else {
+                next_interval = min(next_interval*2,
+                                (int)round_jiffies_relative(check_interval*HZ));
+        }
+
+        schedule_delayed_work(&mcheck_work, next_interval);
+}
+
+/*
+ * This is only called from process context.  This is where we do
+ * anything we need to alert userspace about new MCEs.  This is called
+ * directly from the poller and also from entry.S and idle, thanks to
+ * TIF_MCE_NOTIFY.
+ */
+int mce_notify_user(void)
+{
+        clear_thread_flag(TIF_MCE_NOTIFY);
+        if (test_and_clear_bit(0, &notify_user)) {
                 static unsigned long last_print;
                 unsigned long now = jiffies;
 
-                /* if we logged an MCE, reduce the polling interval */
-                next_interval = max(next_interval/2, HZ/100);
-                notify_user = 0;
-                clear_bit(0, &console_logged);
+                wake_up_interruptible(&mce_wait);
+                if (trigger[0])
+                        call_usermodehelper(trigger, trigger_argv, NULL,
+                                                UMH_NO_WAIT);
+
                 if (time_after_eq(now, last_print + (check_interval*HZ))) {
                         last_print = now;
                         printk(KERN_INFO "Machine check events logged\n");
                 }
-        } else {
-                next_interval = min(next_interval*2, check_interval*HZ);
+
+                return 1;
         }
+        return 0;
+}
 
-        schedule_delayed_work(&mcheck_work, next_interval);
+/* see if the idle task needs to notify userspace */
+static int
+mce_idle_callback(struct notifier_block *nfb, unsigned long action, void *junk)
+{
+        /* IDLE_END should be safe - interrupts are back on */
+        if (action == IDLE_END && test_thread_flag(TIF_MCE_NOTIFY))
+                mce_notify_user();
+
+        return NOTIFY_OK;
 }
 
+static struct notifier_block mce_idle_notifier = {
+        .notifier_call = mce_idle_callback,
+};
 
 static __init int periodic_mcheck_init(void)
 { 
         next_interval = check_interval * HZ;
         if (next_interval)
-                schedule_delayed_work(&mcheck_work, next_interval);
+                schedule_delayed_work(&mcheck_work,
+                                      round_jiffies_relative(next_interval));
+        idle_notifier_register(&mce_idle_notifier);
         return 0;
 } 
 __initcall(periodic_mcheck_init);
@@ -465,6 +522,40 @@ void __cpuinit mcheck_init(struct cpuinfo_x86 *c)
  * Character device to read and clear the MCE log.
  */
 
+static DEFINE_SPINLOCK(mce_state_lock);
+static int open_count;  /* #times opened */
+static int open_exclu;  /* already open exclusive? */
+
+static int mce_open(struct inode *inode, struct file *file)
+{
+        spin_lock(&mce_state_lock);
+
+        if (open_exclu || (open_count && (file->f_flags & O_EXCL))) {
+                spin_unlock(&mce_state_lock);
+                return -EBUSY;
+        }
+
+        if (file->f_flags & O_EXCL)
+                open_exclu = 1;
+        open_count++;
+
+        spin_unlock(&mce_state_lock);
+
+        return nonseekable_open(inode, file);
+}
+
+static int mce_release(struct inode *inode, struct file *file)
+{
+        spin_lock(&mce_state_lock);
+
+        open_count--;
+        open_exclu = 0;
+
+        spin_unlock(&mce_state_lock);
+
+        return 0;
+}
+
 static void collect_tscs(void *data) 
 { 
         unsigned long *cpu_tsc = (unsigned long *)data;
@@ -532,6 +623,14 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, loff
         return err ? -EFAULT : buf - ubuf; 
 }
 
+static unsigned int mce_poll(struct file *file, poll_table *wait)
+{
+        poll_wait(file, &mce_wait, wait);
+        if (rcu_dereference(mcelog.next))
+                return POLLIN | POLLRDNORM;
+        return 0;
+}
+
 static int mce_ioctl(struct inode *i, struct file *f,unsigned int cmd, unsigned long arg)
 {
         int __user *p = (int __user *)arg;
@@ -555,7 +654,10 @@ static int mce_ioctl(struct inode *i, struct file *f,unsigned int cmd, unsigned
 }
 
 static const struct file_operations mce_chrdev_ops = {
+        .open = mce_open,
+        .release = mce_release,
         .read = mce_read,
+        .poll = mce_poll,
         .ioctl = mce_ioctl,
 };
 
@@ -565,6 +667,20 @@ static struct miscdevice mce_log_device = {
         &mce_chrdev_ops,
 };
 
+static unsigned long old_cr4 __initdata;
+
+void __init stop_mce(void)
+{
+        old_cr4 = read_cr4();
+        clear_in_cr4(X86_CR4_MCE);
+}
+
+void __init restart_mce(void)
+{
+        if (old_cr4 & X86_CR4_MCE)
+                set_in_cr4(X86_CR4_MCE);
+}
+
 /* 
  * Old style boot options parsing. Only for compatibility. 
  */
@@ -620,7 +736,8 @@ static void mce_restart(void)
         on_each_cpu(mce_init, NULL, 1, 1);       
         next_interval = check_interval * HZ;
         if (next_interval)
-                schedule_delayed_work(&mcheck_work, next_interval);
+                schedule_delayed_work(&mcheck_work,
+                                      round_jiffies_relative(next_interval));
 }
 
 static struct sysdev_class mce_sysclass = {
diff --git a/arch/x86_64/kernel/mce_amd.c b/arch/x86_64/kernel/mce_amd.c
index 03356e64f9c8..2f8a7f18b0fe 100644
--- a/arch/x86_64/kernel/mce_amd.c
+++ b/arch/x86_64/kernel/mce_amd.c
@@ -157,9 +157,9 @@ void __cpuinit mce_amd_feature_init(struct cpuinfo_x86 *c)
                         high |= K8_APIC_EXT_LVT_ENTRY_THRESHOLD << 20;
                         wrmsr(address, low, high);
 
-                        setup_APIC_extened_lvt(K8_APIC_EXT_LVT_ENTRY_THRESHOLD,
-                                               THRESHOLD_APIC_VECTOR,
-                                               K8_APIC_EXT_INT_MSG_FIX, 0);
+                        setup_APIC_extended_lvt(K8_APIC_EXT_LVT_ENTRY_THRESHOLD,
+                                                THRESHOLD_APIC_VECTOR,
+                                                K8_APIC_EXT_INT_MSG_FIX, 0);
 
                         threshold_defaults.address = address;
                         threshold_restart_bank(&threshold_defaults, 0, 0);
diff --git a/arch/x86_64/kernel/mpparse.c b/arch/x86_64/kernel/mpparse.c
index 61ae57eb9e4c..8bf0ca03ac8e 100644
--- a/arch/x86_64/kernel/mpparse.c
+++ b/arch/x86_64/kernel/mpparse.c
@@ -32,7 +32,6 @@
 
 /* Have we found an MP table */
 int smp_found_config;
-unsigned int __initdata maxcpus = NR_CPUS;
 
 /*
  * Various Linux-internal data structures created from the
@@ -649,6 +648,20 @@ static int mp_find_ioapic(int gsi)
         return -1;
 }
 
+static u8 uniq_ioapic_id(u8 id)
+{
+        int i;
+        DECLARE_BITMAP(used, 256);
+        bitmap_zero(used, 256);
+        for (i = 0; i < nr_ioapics; i++) {
+                struct mpc_config_ioapic *ia = &mp_ioapics[i];
+                __set_bit(ia->mpc_apicid, used);
+        }
+        if (!test_bit(id, used))
+                return id;
+        return find_first_zero_bit(used, 256);
+}
+
 void __init mp_register_ioapic(u8 id, u32 address, u32 gsi_base)
 {
         int idx = 0;
@@ -656,14 +669,14 @@ void __init mp_register_ioapic(u8 id, u32 address, u32 gsi_base)
         if (bad_ioapic(address))
                 return;
 
-        idx = nr_ioapics++;
+        idx = nr_ioapics;
 
         mp_ioapics[idx].mpc_type = MP_IOAPIC;
         mp_ioapics[idx].mpc_flags = MPC_APIC_USABLE;
         mp_ioapics[idx].mpc_apicaddr = address;
 
         set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
-        mp_ioapics[idx].mpc_apicid = id;
+        mp_ioapics[idx].mpc_apicid = uniq_ioapic_id(id);
         mp_ioapics[idx].mpc_apicver = 0;
         
         /* 
@@ -680,6 +693,8 @@ void __init mp_register_ioapic(u8 id, u32 address, u32 gsi_base)
                 mp_ioapics[idx].mpc_apicaddr,
                 mp_ioapic_routing[idx].gsi_start,
                 mp_ioapic_routing[idx].gsi_end);
+
+        nr_ioapics++;
 }
 
 void __init
diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index edbbc59b7523..cb8ee9d02f86 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -384,11 +384,14 @@ int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
         return rc;
 }
 
+static unsigned ignore_nmis;
+
 asmlinkage __kprobes void do_nmi(struct pt_regs * regs, long error_code)
 {
         nmi_enter();
         add_pda(__nmi_count,1);
-        default_do_nmi(regs);
+        if (!ignore_nmis)
+                default_do_nmi(regs);
         nmi_exit();
 }
 
@@ -401,6 +404,18 @@ int do_nmi_callback(struct pt_regs * regs, int cpu)
         return 0;
 }
 
+void stop_nmi(void)
+{
+        acpi_nmi_disable();
+        ignore_nmis++;
+}
+
+void restart_nmi(void)
+{
+        ignore_nmis--;
+        acpi_nmi_enable();
+}
+
 #ifdef CONFIG_SYSCTL
 
 static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
diff --git a/arch/x86_64/kernel/pci-calgary.c b/arch/x86_64/kernel/pci-calgary.c
index 5bd20b542c1e..ba16c968ca3f 100644
--- a/arch/x86_64/kernel/pci-calgary.c
+++ b/arch/x86_64/kernel/pci-calgary.c
@@ -1,7 +1,7 @@
 /*
  * Derived from arch/powerpc/kernel/iommu.c
  *
- * Copyright (C) IBM Corporation, 2006
+ * Copyright IBM Corporation, 2006-2007
  * Copyright (C) 2006  Jon Mason <jdmason@kudzu.us>
  *
  * Author: Jon Mason <jdmason@kudzu.us>
@@ -35,7 +35,7 @@
 #include <linux/pci_ids.h>
 #include <linux/pci.h>
 #include <linux/delay.h>
-#include <asm/proto.h>
+#include <asm/iommu.h>
 #include <asm/calgary.h>
 #include <asm/tce.h>
 #include <asm/pci-direct.h>
@@ -50,13 +50,7 @@ int use_calgary __read_mostly = 0;
 #endif /* CONFIG_CALGARY_DEFAULT_ENABLED */
 
 #define PCI_DEVICE_ID_IBM_CALGARY 0x02a1
-#define PCI_VENDOR_DEVICE_ID_CALGARY \
-        (PCI_VENDOR_ID_IBM | PCI_DEVICE_ID_IBM_CALGARY << 16)
-
-/* we need these for register space address calculation */
-#define START_ADDRESS           0xfe000000
-#define CHASSIS_BASE            0
-#define ONE_BASED_CHASSIS_NUM   1
+#define PCI_DEVICE_ID_IBM_CALIOC2 0x0308
 
 /* register offsets inside the host bridge space */
 #define CALGARY_CONFIG_REG      0x0108
@@ -80,6 +74,12 @@ int use_calgary __read_mostly = 0;
 #define PHB_MEM_2_SIZE_LOW      0x02E0
 #define PHB_DOSHOLE_OFFSET      0x08E0
 
+/* CalIOC2 specific */
+#define PHB_SAVIOR_L2           0x0DB0
+#define PHB_PAGE_MIG_CTRL       0x0DA8
+#define PHB_PAGE_MIG_DEBUG      0x0DA0
+#define PHB_ROOT_COMPLEX_STATUS 0x0CB0
+
 /* PHB_CONFIG_RW */
 #define PHB_TCE_ENABLE          0x20000000
 #define PHB_SLOT_DISABLE        0x1C000000
@@ -92,7 +92,11 @@ int use_calgary __read_mostly = 0;
 /* CSR (Channel/DMA Status Register) */
 #define CSR_AGENT_MASK          0xffe0ffff
 /* CCR (Calgary Configuration Register) */
-#define CCR_2SEC_TIMEOUT        0x000000000000000EUL
+#define CCR_2SEC_TIMEOUT        0x000000000000000EUL
+/* PMCR/PMDR (Page Migration Control/Debug Registers */
+#define PMR_SOFTSTOP            0x80000000
+#define PMR_SOFTSTOPFAULT       0x40000000
+#define PMR_HARDSTOP            0x20000000
 
 #define MAX_NUM_OF_PHBS         8 /* how many PHBs in total? */
 #define MAX_NUM_CHASSIS         8 /* max number of chassis */
@@ -155,9 +159,26 @@ struct calgary_bus_info {
         void __iomem *bbar;
 };
 
-static struct calgary_bus_info bus_info[MAX_PHB_BUS_NUM] = { { NULL, 0, 0 }, };
+static void calgary_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev);
+static void calgary_tce_cache_blast(struct iommu_table *tbl);
+static void calgary_dump_error_regs(struct iommu_table *tbl);
+static void calioc2_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev);
+static void calioc2_tce_cache_blast(struct iommu_table *tbl);
+static void calioc2_dump_error_regs(struct iommu_table *tbl);
+
+static struct cal_chipset_ops calgary_chip_ops = {
+        .handle_quirks = calgary_handle_quirks,
+        .tce_cache_blast = calgary_tce_cache_blast,
+        .dump_error_regs = calgary_dump_error_regs
+};
 
-static void tce_cache_blast(struct iommu_table *tbl);
+static struct cal_chipset_ops calioc2_chip_ops = {
+        .handle_quirks = calioc2_handle_quirks,
+        .tce_cache_blast = calioc2_tce_cache_blast,
+        .dump_error_regs = calioc2_dump_error_regs
+};
+
+static struct calgary_bus_info bus_info[MAX_PHB_BUS_NUM] = { { NULL, 0, 0 }, };
 
 /* enable this to stress test the chip's TCE cache */
 #ifdef CONFIG_IOMMU_DEBUG
@@ -187,6 +208,7 @@ static inline unsigned long verify_bit_range(unsigned long* bitmap,
 {
         return ~0UL;
 }
+
 #endif /* CONFIG_IOMMU_DEBUG */
 
 static inline unsigned int num_dma_pages(unsigned long dma, unsigned int dmalen)
@@ -206,11 +228,12 @@ static inline int translate_phb(struct pci_dev* dev)
 }
 
 static void iommu_range_reserve(struct iommu_table *tbl,
-        unsigned long start_addr, unsigned int npages)
+        unsigned long start_addr, unsigned int npages)
 {
         unsigned long index;
         unsigned long end;
         unsigned long badbit;
+        unsigned long flags;
 
         index = start_addr >> PAGE_SHIFT;
 
@@ -222,6 +245,8 @@ static void iommu_range_reserve(struct iommu_table *tbl,
         if (end > tbl->it_size) /* don't go off the table */
                 end = tbl->it_size;
 
+        spin_lock_irqsave(&tbl->it_lock, flags);
+
         badbit = verify_bit_range(tbl->it_map, 0, index, end);
         if (badbit != ~0UL) {
                 if (printk_ratelimit())
@@ -231,23 +256,29 @@ static void iommu_range_reserve(struct iommu_table *tbl,
         }
 
         set_bit_string(tbl->it_map, index, npages);
+
+        spin_unlock_irqrestore(&tbl->it_lock, flags);
 }
 
 static unsigned long iommu_range_alloc(struct iommu_table *tbl,
         unsigned int npages)
 {
+        unsigned long flags;
         unsigned long offset;
 
         BUG_ON(npages == 0);
 
+        spin_lock_irqsave(&tbl->it_lock, flags);
+
         offset = find_next_zero_string(tbl->it_map, tbl->it_hint,
                                        tbl->it_size, npages);
         if (offset == ~0UL) {
-                tce_cache_blast(tbl);
+                tbl->chip_ops->tce_cache_blast(tbl);
                 offset = find_next_zero_string(tbl->it_map, 0,
                                                tbl->it_size, npages);
                 if (offset == ~0UL) {
                         printk(KERN_WARNING "Calgary: IOMMU full.\n");
+                        spin_unlock_irqrestore(&tbl->it_lock, flags);
                         if (panic_on_overflow)
                                 panic("Calgary: fix the allocator.\n");
                         else
@@ -259,17 +290,17 @@ static unsigned long iommu_range_alloc(struct iommu_table *tbl,
         tbl->it_hint = offset + npages;
         BUG_ON(tbl->it_hint > tbl->it_size);
 
+        spin_unlock_irqrestore(&tbl->it_lock, flags);
+
         return offset;
 }
 
 static dma_addr_t iommu_alloc(struct iommu_table *tbl, void *vaddr,
         unsigned int npages, int direction)
 {
-        unsigned long entry, flags;
+        unsigned long entry;
         dma_addr_t ret = bad_dma_address;
 
-        spin_lock_irqsave(&tbl->it_lock, flags);
-
         entry = iommu_range_alloc(tbl, npages);
 
         if (unlikely(entry == bad_dma_address))
@@ -282,23 +313,21 @@ static dma_addr_t iommu_alloc(struct iommu_table *tbl, void *vaddr,
         tce_build(tbl, entry, npages, (unsigned long)vaddr & PAGE_MASK,
                   direction);
 
-        spin_unlock_irqrestore(&tbl->it_lock, flags);
-
         return ret;
 
 error:
-        spin_unlock_irqrestore(&tbl->it_lock, flags);
         printk(KERN_WARNING "Calgary: failed to allocate %u pages in "
                "iommu %p\n", npages, tbl);
         return bad_dma_address;
 }
 
-static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
+static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
         unsigned int npages)
 {
         unsigned long entry;
         unsigned long badbit;
         unsigned long badend;
+        unsigned long flags;
 
         /* were we called with bad_dma_address? */
         badend = bad_dma_address + (EMERGENCY_PAGES * PAGE_SIZE);
@@ -315,6 +344,8 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 
         tce_free(tbl, entry, npages);
 
+        spin_lock_irqsave(&tbl->it_lock, flags);
+
         badbit = verify_bit_range(tbl->it_map, 1, entry, entry + npages);
         if (badbit != ~0UL) {
                 if (printk_ratelimit())
@@ -324,23 +355,40 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
         }
 
         __clear_bit_string(tbl->it_map, entry, npages);
+
+        spin_unlock_irqrestore(&tbl->it_lock, flags);
 }
 
-static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
-        unsigned int npages)
+static inline struct iommu_table *find_iommu_table(struct device *dev)
 {
-        unsigned long flags;
+        struct pci_dev *pdev;
+        struct pci_bus *pbus;
+        struct iommu_table *tbl;
 
-        spin_lock_irqsave(&tbl->it_lock, flags);
+        pdev = to_pci_dev(dev);
 
-        __iommu_free(tbl, dma_addr, npages);
+        /* is the device behind a bridge? */
+        if (unlikely(pdev->bus->parent))
+                pbus = pdev->bus->parent;
+        else
+                pbus = pdev->bus;
 
-        spin_unlock_irqrestore(&tbl->it_lock, flags);
+        tbl = pci_iommu(pbus);
+
+        BUG_ON(pdev->bus->parent &&
+               (tbl->it_busno != pdev->bus->parent->number));
+
+        return tbl;
 }
 
-static void __calgary_unmap_sg(struct iommu_table *tbl,
+static void calgary_unmap_sg(struct device *dev,
         struct scatterlist *sglist, int nelems, int direction)
 {
+        struct iommu_table *tbl = find_iommu_table(dev);
+
+        if (!translate_phb(to_pci_dev(dev)))
+                return;
+
         while (nelems--) {
                 unsigned int npages;
                 dma_addr_t dma = sglist->dma_address;
@@ -350,33 +398,17 @@ static void __calgary_unmap_sg(struct iommu_table *tbl,
                         break;
 
                 npages = num_dma_pages(dma, dmalen);
-                __iommu_free(tbl, dma, npages);
+                iommu_free(tbl, dma, npages);
                 sglist++;
         }
 }
 
-void calgary_unmap_sg(struct device *dev, struct scatterlist *sglist,
-                      int nelems, int direction)
-{
-        unsigned long flags;
-        struct iommu_table *tbl = to_pci_dev(dev)->bus->self->sysdata;
-
-        if (!translate_phb(to_pci_dev(dev)))
-                return;
-
-        spin_lock_irqsave(&tbl->it_lock, flags);
-
-        __calgary_unmap_sg(tbl, sglist, nelems, direction);
-
-        spin_unlock_irqrestore(&tbl->it_lock, flags);
-}
-
 static int calgary_nontranslate_map_sg(struct device* dev,
         struct scatterlist *sg, int nelems, int direction)
 {
         int i;
 
-        for (i = 0; i < nelems; i++ ) {
+        for (i = 0; i < nelems; i++ ) {
                 struct scatterlist *s = &sg[i];
                 BUG_ON(!s->page);
                 s->dma_address = virt_to_bus(page_address(s->page) +s->offset);
@@ -385,11 +417,10 @@ static int calgary_nontranslate_map_sg(struct device* dev,
         return nelems;
 }
 
-int calgary_map_sg(struct device *dev, struct scatterlist *sg,
+static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
         int nelems, int direction)
 {
-        struct iommu_table *tbl = to_pci_dev(dev)->bus->self->sysdata;
-        unsigned long flags;
+        struct iommu_table *tbl = find_iommu_table(dev);
         unsigned long vaddr;
         unsigned int npages;
         unsigned long entry;
@@ -398,8 +429,6 @@ int calgary_map_sg(struct device *dev, struct scatterlist *sg,
         if (!translate_phb(to_pci_dev(dev)))
                 return calgary_nontranslate_map_sg(dev, sg, nelems, direction);
 
-        spin_lock_irqsave(&tbl->it_lock, flags);
-
         for (i = 0; i < nelems; i++ ) {
                 struct scatterlist *s = &sg[i];
                 BUG_ON(!s->page);
@@ -423,26 +452,23 @@ int calgary_map_sg(struct device *dev, struct scatterlist *sg,
                 s->dma_length = s->length;
         }
 
-        spin_unlock_irqrestore(&tbl->it_lock, flags);
-
         return nelems;
 error:
-        __calgary_unmap_sg(tbl, sg, nelems, direction);
+        calgary_unmap_sg(dev, sg, nelems, direction);
         for (i = 0; i < nelems; i++) {
                 sg[i].dma_address = bad_dma_address;
                 sg[i].dma_length = 0;
         }
-        spin_unlock_irqrestore(&tbl->it_lock, flags);
         return 0;
 }
 
-dma_addr_t calgary_map_single(struct device *dev, void *vaddr,
+static dma_addr_t calgary_map_single(struct device *dev, void *vaddr,
         size_t size, int direction)
 {
         dma_addr_t dma_handle = bad_dma_address;
         unsigned long uaddr;
         unsigned int npages;
-        struct iommu_table *tbl = to_pci_dev(dev)->bus->self->sysdata;
+        struct iommu_table *tbl = find_iommu_table(dev);
 
         uaddr = (unsigned long)vaddr;
         npages = num_dma_pages(uaddr, size);
@@ -455,10 +481,10 @@ dma_addr_t calgary_map_single(struct device *dev, void *vaddr,
         return dma_handle;
 }
 
-void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle,
+static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle,
         size_t size, int direction)
 {
-        struct iommu_table *tbl = to_pci_dev(dev)->bus->self->sysdata;
+        struct iommu_table *tbl = find_iommu_table(dev);
         unsigned int npages;
 
         if (!translate_phb(to_pci_dev(dev)))
@@ -468,15 +494,13 @@ void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle,
         iommu_free(tbl, dma_handle, npages);
 }
 
-void* calgary_alloc_coherent(struct device *dev, size_t size,
+static void* calgary_alloc_coherent(struct device *dev, size_t size,
         dma_addr_t *dma_handle, gfp_t flag)
 {
         void *ret = NULL;
         dma_addr_t mapping;
         unsigned int npages, order;
-        struct iommu_table *tbl;
-
-        tbl = to_pci_dev(dev)->bus->self->sysdata;
+        struct iommu_table *tbl = find_iommu_table(dev);
 
         size = PAGE_ALIGN(size); /* size rounded up to full pages */
         npages = size >> PAGE_SHIFT;
@@ -552,7 +576,22 @@ static inline void __iomem* calgary_reg(void __iomem *bar, unsigned long offset)
         return (void __iomem*)target;
 }
 
-static void tce_cache_blast(struct iommu_table *tbl)
+static inline int is_calioc2(unsigned short device)
+{
+        return (device == PCI_DEVICE_ID_IBM_CALIOC2);
+}
+
+static inline int is_calgary(unsigned short device)
+{
+        return (device == PCI_DEVICE_ID_IBM_CALGARY);
+}
+
+static inline int is_cal_pci_dev(unsigned short device)
+{
+        return (is_calgary(device) || is_calioc2(device));
+}
+
+static void calgary_tce_cache_blast(struct iommu_table *tbl)
 {
         u64 val;
         u32 aer;
@@ -589,6 +628,85 @@ static void tce_cache_blast(struct iommu_table *tbl)
         (void)readl(target); /* flush */
 }
 
+static void calioc2_tce_cache_blast(struct iommu_table *tbl)
+{
+        void __iomem *bbar = tbl->bbar;
+        void __iomem *target;
+        u64 val64;
+        u32 val;
+        int i = 0;
+        int count = 1;
+        unsigned char bus = tbl->it_busno;
+
+begin:
+        printk(KERN_DEBUG "Calgary: CalIOC2 bus 0x%x entering tce cache blast "
+               "sequence - count %d\n", bus, count);
+
+        /* 1. using the Page Migration Control reg set SoftStop */
+        target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_CTRL);
+        val = be32_to_cpu(readl(target));
+        printk(KERN_DEBUG "1a. read 0x%x [LE] from %p\n", val, target);
+        val |= PMR_SOFTSTOP;
+        printk(KERN_DEBUG "1b. writing 0x%x [LE] to %p\n", val, target);
+        writel(cpu_to_be32(val), target);
+
+        /* 2. poll split queues until all DMA activity is done */
+        printk(KERN_DEBUG "2a. starting to poll split queues\n");
+        target = calgary_reg(bbar, split_queue_offset(bus));
+        do {
+                val64 = readq(target);
+                i++;
+        } while ((val64 & 0xff) != 0xff && i < 100);
+        if (i == 100)
+                printk(KERN_WARNING "CalIOC2: PCI bus not quiesced, "
+                       "continuing anyway\n");
+
+        /* 3. poll Page Migration DEBUG for SoftStopFault */
+        target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_DEBUG);
+        val = be32_to_cpu(readl(target));
+        printk(KERN_DEBUG "3. read 0x%x [LE] from %p\n", val, target);
+
+        /* 4. if SoftStopFault - goto (1) */
+        if (val & PMR_SOFTSTOPFAULT) {
+                if (++count < 100)
+                        goto begin;
+                else {
+                        printk(KERN_WARNING "CalIOC2: too many SoftStopFaults, "
+                               "aborting TCE cache flush sequence!\n");
+                        return; /* pray for the best */
+                }
+        }
+
+        /* 5. Slam into HardStop by reading PHB_PAGE_MIG_CTRL */
+        target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_CTRL);
+        printk(KERN_DEBUG "5a. slamming into HardStop by reading %p\n", target);
+        val = be32_to_cpu(readl(target));
+        printk(KERN_DEBUG "5b. read 0x%x [LE] from %p\n", val, target);
+        target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_DEBUG);
+        val = be32_to_cpu(readl(target));
+        printk(KERN_DEBUG "5c. read 0x%x [LE] from %p (debug)\n", val, target);
+
+        /* 6. invalidate TCE cache */
+        printk(KERN_DEBUG "6. invalidating TCE cache\n");
+        target = calgary_reg(bbar, tar_offset(bus));
+        writeq(tbl->tar_val, target);
+
+        /* 7. Re-read PMCR */
+        printk(KERN_DEBUG "7a. Re-reading PMCR\n");
+        target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_CTRL);
+        val = be32_to_cpu(readl(target));
+        printk(KERN_DEBUG "7b. read 0x%x [LE] from %p\n", val, target);
+
+        /* 8. Remove HardStop */
+        printk(KERN_DEBUG "8a. removing HardStop from PMCR\n");
+        target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_CTRL);
+        val = 0;
+        printk(KERN_DEBUG "8b. writing 0x%x [LE] to %p\n", val, target);
+        writel(cpu_to_be32(val), target);
+        val = be32_to_cpu(readl(target));
+        printk(KERN_DEBUG "8c. read 0x%x [LE] from %p\n", val, target);
+}
+
 static void __init calgary_reserve_mem_region(struct pci_dev *dev, u64 start,
         u64 limit)
 {
@@ -598,7 +716,7 @@ static void __init calgary_reserve_mem_region(struct pci_dev *dev, u64 start,
         limit++;
 
         numpages = ((limit - start) >> PAGE_SHIFT);
-        iommu_range_reserve(dev->sysdata, start, numpages);
+        iommu_range_reserve(pci_iommu(dev->bus), start, numpages);
 }
 
 static void __init calgary_reserve_peripheral_mem_1(struct pci_dev *dev)
@@ -606,7 +724,7 @@ static void __init calgary_reserve_peripheral_mem_1(struct pci_dev *dev)
         void __iomem *target;
         u64 low, high, sizelow;
         u64 start, limit;
-        struct iommu_table *tbl = dev->sysdata;
+        struct iommu_table *tbl = pci_iommu(dev->bus);
         unsigned char busnum = dev->bus->number;
         void __iomem *bbar = tbl->bbar;
 
@@ -630,7 +748,7 @@ static void __init calgary_reserve_peripheral_mem_2(struct pci_dev *dev)
         u32 val32;
         u64 low, high, sizelow, sizehigh;
         u64 start, limit;
-        struct iommu_table *tbl = dev->sysdata;
+        struct iommu_table *tbl = pci_iommu(dev->bus);
         unsigned char busnum = dev->bus->number;
         void __iomem *bbar = tbl->bbar;
 
@@ -666,14 +784,20 @@ static void __init calgary_reserve_regions(struct pci_dev *dev)
 {
         unsigned int npages;
         u64 start;
-        struct iommu_table *tbl = dev->sysdata;
+        struct iommu_table *tbl = pci_iommu(dev->bus);
 
         /* reserve EMERGENCY_PAGES from bad_dma_address and up */
         iommu_range_reserve(tbl, bad_dma_address, EMERGENCY_PAGES);
 
         /* avoid the BIOS/VGA first 640KB-1MB region */
-        start = (640 * 1024);
-        npages = ((1024 - 640) * 1024) >> PAGE_SHIFT;
+        /* for CalIOC2 - avoid the entire first MB */
+        if (is_calgary(dev->device)) {
+                start = (640 * 1024);
+                npages = ((1024 - 640) * 1024) >> PAGE_SHIFT;
+        } else { /* calioc2 */
+                start = 0;
+                npages = (1 * 1024 * 1024) >> PAGE_SHIFT;
+        }
         iommu_range_reserve(tbl, start, npages);
 
         /* reserve the two PCI peripheral memory regions in IO space */
@@ -694,10 +818,17 @@ static int __init calgary_setup_tar(struct pci_dev *dev, void __iomem *bbar)
         if (ret)
                 return ret;
 
-        tbl = dev->sysdata;
+        tbl = pci_iommu(dev->bus);
         tbl->it_base = (unsigned long)bus_info[dev->bus->number].tce_space;
         tce_free(tbl, 0, tbl->it_size);
 
+        if (is_calgary(dev->device))
+                tbl->chip_ops = &calgary_chip_ops;
+        else if (is_calioc2(dev->device))
+                tbl->chip_ops = &calioc2_chip_ops;
+        else
+                BUG();
+
         calgary_reserve_regions(dev);
 
         /* set TARs for each PHB */
@@ -706,15 +837,15 @@ static int __init calgary_setup_tar(struct pci_dev *dev, void __iomem *bbar)
 
         /* zero out all TAR bits under sw control */
         val64 &= ~TAR_SW_BITS;
-
-        tbl = dev->sysdata;
         table_phys = (u64)__pa(tbl->it_base);
+
         val64 |= table_phys;
 
         BUG_ON(specified_table_size > TCE_TABLE_SIZE_8M);
         val64 |= (u64) specified_table_size;
 
         tbl->tar_val = cpu_to_be64(val64);
+
         writeq(tbl->tar_val, target);
         readq(target); /* flush */
 
@@ -724,7 +855,7 @@ static int __init calgary_setup_tar(struct pci_dev *dev, void __iomem *bbar)
 static void __init calgary_free_bus(struct pci_dev *dev)
 {
         u64 val64;
-        struct iommu_table *tbl = dev->sysdata;
+        struct iommu_table *tbl = pci_iommu(dev->bus);
         void __iomem *target;
         unsigned int bitmapsz;
 
@@ -739,16 +870,81 @@ static void __init calgary_free_bus(struct pci_dev *dev)
         tbl->it_map = NULL;
 
         kfree(tbl);
-        dev->sysdata = NULL;
+        
+        set_pci_iommu(dev->bus, NULL);
 
         /* Can't free bootmem allocated memory after system is up :-( */
         bus_info[dev->bus->number].tce_space = NULL;
 }
 
+static void calgary_dump_error_regs(struct iommu_table *tbl)
+{
+        void __iomem *bbar = tbl->bbar;
+        void __iomem *target;
+        u32 csr, plssr;
+
+        target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_CSR_OFFSET);
+        csr = be32_to_cpu(readl(target));
+
+        target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_PLSSR_OFFSET);
+        plssr = be32_to_cpu(readl(target));
+
+        /* If no error, the agent ID in the CSR is not valid */
+        printk(KERN_EMERG "Calgary: DMA error on Calgary PHB 0x%x, "
+               "0x%08x@CSR 0x%08x@PLSSR\n", tbl->it_busno, csr, plssr);
+}
+
+static void calioc2_dump_error_regs(struct iommu_table *tbl)
+{
+        void __iomem *bbar = tbl->bbar;
+        u32 csr, csmr, plssr, mck, rcstat;
+        void __iomem *target;
+        unsigned long phboff = phb_offset(tbl->it_busno);
+        unsigned long erroff;
+        u32 errregs[7];
+        int i;
+
+        /* dump CSR */
+        target = calgary_reg(bbar, phboff | PHB_CSR_OFFSET);
+        csr = be32_to_cpu(readl(target));
+        /* dump PLSSR */
+        target = calgary_reg(bbar, phboff | PHB_PLSSR_OFFSET);
+        plssr = be32_to_cpu(readl(target));
+        /* dump CSMR */
+        target = calgary_reg(bbar, phboff | 0x290);
+        csmr = be32_to_cpu(readl(target));
+        /* dump mck */
+        target = calgary_reg(bbar, phboff | 0x800);
+        mck = be32_to_cpu(readl(target));
+
+        printk(KERN_EMERG "Calgary: DMA error on CalIOC2 PHB 0x%x\n",
+               tbl->it_busno);
+
+        printk(KERN_EMERG "Calgary: 0x%08x@CSR 0x%08x@PLSSR 0x%08x@CSMR 0x%08x@MCK\n",
+               csr, plssr, csmr, mck);
+
+        /* dump rest of error regs */
+        printk(KERN_EMERG "Calgary: ");
+        for (i = 0; i < ARRAY_SIZE(errregs); i++) {
+                /* err regs are at 0x810 - 0x870 */
+                erroff = (0x810 + (i * 0x10));
+                target = calgary_reg(bbar, phboff | erroff);
+                errregs[i] = be32_to_cpu(readl(target));
+                printk("0x%08x@0x%lx ", errregs[i], erroff);
+        }
+        printk("\n");
+
+        /* root complex status */
+        target = calgary_reg(bbar, phboff | PHB_ROOT_COMPLEX_STATUS);
+        rcstat = be32_to_cpu(readl(target));
+        printk(KERN_EMERG "Calgary: 0x%08x@0x%x\n", rcstat,
+               PHB_ROOT_COMPLEX_STATUS);
+}
+
 static void calgary_watchdog(unsigned long data)
 {
         struct pci_dev *dev = (struct pci_dev *)data;
-        struct iommu_table *tbl = dev->sysdata;
+        struct iommu_table *tbl = pci_iommu(dev->bus);
         void __iomem *bbar = tbl->bbar;
         u32 val32;
         void __iomem *target;
@@ -758,13 +954,14 @@ static void calgary_watchdog(unsigned long data)
 
         /* If no error, the agent ID in the CSR is not valid */
         if (val32 & CSR_AGENT_MASK) {
-                printk(KERN_EMERG "calgary_watchdog: DMA error on PHB %#x, "
-                                  "CSR = %#x\n", dev->bus->number, val32);
+                tbl->chip_ops->dump_error_regs(tbl);
+
+                /* reset error */
                 writel(0, target);
 
                 /* Disable bus that caused the error */
                 target = calgary_reg(bbar, phb_offset(tbl->it_busno) |
-                                           PHB_CONFIG_RW_OFFSET);
+                                     PHB_CONFIG_RW_OFFSET);
                 val32 = be32_to_cpu(readl(target));
                 val32 |= PHB_SLOT_DISABLE;
                 writel(cpu_to_be32(val32), target);
@@ -775,8 +972,8 @@ static void calgary_watchdog(unsigned long data)
         }
 }
 
-static void __init calgary_increase_split_completion_timeout(void __iomem *bbar,
-        unsigned char busnum)
+static void __init calgary_set_split_completion_timeout(void __iomem *bbar,
+        unsigned char busnum, unsigned long timeout)
 {
         u64 val64;
         void __iomem *target;
@@ -802,11 +999,40 @@ static void __init calgary_increase_split_completion_timeout(void __iomem *bbar,
         /* zero out this PHB's timer bits */
         mask = ~(0xFUL << phb_shift);
         val64 &= mask;
-        val64 |= (CCR_2SEC_TIMEOUT << phb_shift);
+        val64 |= (timeout << phb_shift);
         writeq(cpu_to_be64(val64), target);
         readq(target); /* flush */
 }
 
+static void calioc2_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev)
+{
+        unsigned char busnum = dev->bus->number;
+        void __iomem *bbar = tbl->bbar;
+        void __iomem *target;
+        u32 val;
+
+        /*
+         * CalIOC2 designers recommend setting bit 8 in 0xnDB0 to 1
+         */
+        target = calgary_reg(bbar, phb_offset(busnum) | PHB_SAVIOR_L2);
+        val = cpu_to_be32(readl(target));
+        val |= 0x00800000;
+        writel(cpu_to_be32(val), target);
+}
+
+static void calgary_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev)
+{
+        unsigned char busnum = dev->bus->number;
+
+        /*
+         * Give split completion a longer timeout on bus 1 for aic94xx
+         * http://bugzilla.kernel.org/show_bug.cgi?id=7180
+         */
+        if (is_calgary(dev->device) && (busnum == 1))
+                calgary_set_split_completion_timeout(tbl->bbar, busnum,
+                                                     CCR_2SEC_TIMEOUT);
+}
+
 static void __init calgary_enable_translation(struct pci_dev *dev)
 {
         u32 val32;
@@ -816,7 +1042,7 @@ static void __init calgary_enable_translation(struct pci_dev *dev)
         struct iommu_table *tbl;
 
         busnum = dev->bus->number;
-        tbl = dev->sysdata;
+        tbl = pci_iommu(dev->bus);
         bbar = tbl->bbar;
 
         /* enable TCE in PHB Config Register */
@@ -824,20 +1050,15 @@ static void __init calgary_enable_translation(struct pci_dev *dev)
         val32 = be32_to_cpu(readl(target));
         val32 |= PHB_TCE_ENABLE | PHB_DAC_DISABLE | PHB_MCSR_ENABLE;
 
-        printk(KERN_INFO "Calgary: enabling translation on PHB %#x\n", busnum);
+        printk(KERN_INFO "Calgary: enabling translation on %s PHB %#x\n",
+               (dev->device == PCI_DEVICE_ID_IBM_CALGARY) ?
+               "Calgary" : "CalIOC2", busnum);
         printk(KERN_INFO "Calgary: errant DMAs will now be prevented on this "
                "bus.\n");
 
         writel(cpu_to_be32(val32), target);
         readl(target); /* flush */
 
-        /*
-         * Give split completion a longer timeout on bus 1 for aic94xx
-         * http://bugzilla.kernel.org/show_bug.cgi?id=7180
-         */
-        if (busnum == 1)
-                calgary_increase_split_completion_timeout(bbar, busnum);
-
         init_timer(&tbl->watchdog_timer);
         tbl->watchdog_timer.function = &calgary_watchdog;
         tbl->watchdog_timer.data = (unsigned long)dev;
@@ -853,7 +1074,7 @@ static void __init calgary_disable_translation(struct pci_dev *dev)
         struct iommu_table *tbl;
 
         busnum = dev->bus->number;
-        tbl = dev->sysdata;
+        tbl = pci_iommu(dev->bus);
         bbar = tbl->bbar;
 
         /* disable TCE in PHB Config Register */
@@ -871,13 +1092,19 @@ static void __init calgary_disable_translation(struct pci_dev *dev)
 static void __init calgary_init_one_nontraslated(struct pci_dev *dev)
 {
         pci_dev_get(dev);
-        dev->sysdata = NULL;
-        dev->bus->self = dev;
+        set_pci_iommu(dev->bus, NULL);
+
+        /* is the device behind a bridge? */
+        if (dev->bus->parent)
+                dev->bus->parent->self = dev;
+        else
+                dev->bus->self = dev;
 }
 
 static int __init calgary_init_one(struct pci_dev *dev)
 {
         void __iomem *bbar;
+        struct iommu_table *tbl;
         int ret;
 
         BUG_ON(dev->bus->number >= MAX_PHB_BUS_NUM);
@@ -888,7 +1115,18 @@ static int __init calgary_init_one(struct pci_dev *dev)
                 goto done;
 
         pci_dev_get(dev);
-        dev->bus->self = dev;
+
+        if (dev->bus->parent) {
+                if (dev->bus->parent->self)
+                        printk(KERN_WARNING "Calgary: IEEEE, dev %p has "
+                               "bus->parent->self!\n", dev);
+                dev->bus->parent->self = dev;
+        } else
+                dev->bus->self = dev;
+
+        tbl = pci_iommu(dev->bus);
+        tbl->chip_ops->handle_quirks(tbl, dev);
+
         calgary_enable_translation(dev);
 
         return 0;
@@ -924,11 +1162,18 @@ static int __init calgary_locate_bbars(void)
                         target = calgary_reg(bbar, offset);
 
                         val = be32_to_cpu(readl(target));
+
                         start_bus = (u8)((val & 0x00FF0000) >> 16);
                         end_bus = (u8)((val & 0x0000FF00) >> 8);
-                        for (bus = start_bus; bus <= end_bus; bus++) {
-                                bus_info[bus].bbar = bbar;
-                                bus_info[bus].phbid = phb;
+
+                        if (end_bus) {
+                                for (bus = start_bus; bus <= end_bus; bus++) {
+                                        bus_info[bus].bbar = bbar;
+                                        bus_info[bus].phbid = phb;
+                                }
+                        } else {
+                                bus_info[start_bus].bbar = bbar;
+                                bus_info[start_bus].phbid = phb;
                         }
                 }
         }
@@ -948,22 +1193,24 @@ static int __init calgary_init(void)
 {
         int ret;
         struct pci_dev *dev = NULL;
+        void *tce_space;
 
         ret = calgary_locate_bbars();
         if (ret)
                 return ret;
 
         do {
-                dev = pci_get_device(PCI_VENDOR_ID_IBM,
-                                     PCI_DEVICE_ID_IBM_CALGARY,
-                                     dev);
+                dev = pci_get_device(PCI_VENDOR_ID_IBM, PCI_ANY_ID, dev);
                 if (!dev)
                         break;
+                if (!is_cal_pci_dev(dev->device))
+                        continue;
                 if (!translate_phb(dev)) {
                         calgary_init_one_nontraslated(dev);
                         continue;
                 }
-                if (!bus_info[dev->bus->number].tce_space && !translate_empty_slots)
+                tce_space = bus_info[dev->bus->number].tce_space;
+                if (!tce_space && !translate_empty_slots)
                         continue;
 
                 ret = calgary_init_one(dev);
@@ -976,10 +1223,11 @@ static int __init calgary_init(void)
 error:
         do {
                 dev = pci_get_device_reverse(PCI_VENDOR_ID_IBM,
-                                              PCI_DEVICE_ID_IBM_CALGARY,
-                                              dev);
+                                             PCI_ANY_ID, dev);
                 if (!dev)
                         break;
+                if (!is_cal_pci_dev(dev->device))
+                        continue;
                 if (!translate_phb(dev)) {
                         pci_dev_put(dev);
                         continue;
@@ -1057,9 +1305,29 @@ static int __init build_detail_arrays(void)
         return 0;
 }
 
-void __init detect_calgary(void)
+static int __init calgary_bus_has_devices(int bus, unsigned short pci_dev)
 {
+        int dev;
         u32 val;
+
+        if (pci_dev == PCI_DEVICE_ID_IBM_CALIOC2) {
+                /*
+                 * FIXME: properly scan for devices accross the
+                 * PCI-to-PCI bridge on every CalIOC2 port.
+                 */
+                return 1;
+        }
+
+        for (dev = 1; dev < 8; dev++) {
+                val = read_pci_config(bus, dev, 0, 0);
+                if (val != 0xffffffff)
+                        break;
+        }
+        return (val != 0xffffffff);
+}
+
+void __init detect_calgary(void)
+{
         int bus;
         void *tbl;
         int calgary_found = 0;
@@ -1116,29 +1384,26 @@ void __init detect_calgary(void)
         specified_table_size = determine_tce_table_size(end_pfn * PAGE_SIZE);
 
         for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) {
-                int dev;
                 struct calgary_bus_info *info = &bus_info[bus];
+                unsigned short pci_device;
+                u32 val;
+
+                val = read_pci_config(bus, 0, 0, 0);
+                pci_device = (val & 0xFFFF0000) >> 16;
 
-                if (read_pci_config(bus, 0, 0, 0) != PCI_VENDOR_DEVICE_ID_CALGARY)
+                if (!is_cal_pci_dev(pci_device))
                         continue;
 
                 if (info->translation_disabled)
                         continue;
 
-                /*
-                 * Scan the slots of the PCI bus to see if there is a device present.
-                 * The parent bus will be the zero-ith device, so start at 1.
-                 */
-                for (dev = 1; dev < 8; dev++) {
-                        val = read_pci_config(bus, dev, 0, 0);
-                        if (val != 0xffffffff || translate_empty_slots) {
-                                tbl = alloc_tce_table();
-                                if (!tbl)
-                                        goto cleanup;
-                                info->tce_space = tbl;
-                                calgary_found = 1;
-                                break;
-                        }
+                if (calgary_bus_has_devices(bus, pci_device) ||
+                    translate_empty_slots) {
+                        tbl = alloc_tce_table();
+                        if (!tbl)
+                                goto cleanup;
+                        info->tce_space = tbl;
+                        calgary_found = 1;
                 }
         }
 
@@ -1249,3 +1514,66 @@ static int __init calgary_parse_options(char *p)
         return 1;
 }
 __setup("calgary=", calgary_parse_options);
+
+static void __init calgary_fixup_one_tce_space(struct pci_dev *dev)
+{
+        struct iommu_table *tbl;
+        unsigned int npages;
+        int i;
+
+        tbl = pci_iommu(dev->bus);
+
+        for (i = 0; i < 4; i++) {
+                struct resource *r = &dev->resource[PCI_BRIDGE_RESOURCES + i];
+
+                /* Don't give out TCEs that map MEM resources */
+                if (!(r->flags & IORESOURCE_MEM))
+                        continue;
+
+                /* 0-based? we reserve the whole 1st MB anyway */
+                if (!r->start)
+                        continue;
+
+                /* cover the whole region */
+                npages = (r->end - r->start) >> PAGE_SHIFT;
+                npages++;
+
+                iommu_range_reserve(tbl, r->start, npages);
+        }
+}
+
+static int __init calgary_fixup_tce_spaces(void)
+{
+        struct pci_dev *dev = NULL;
+        void *tce_space;
+
+        if (no_iommu || swiotlb || !calgary_detected)
+                return -ENODEV;
+
+        printk(KERN_DEBUG "Calgary: fixing up tce spaces\n");
+
+        do {
+                dev = pci_get_device(PCI_VENDOR_ID_IBM, PCI_ANY_ID, dev);
+                if (!dev)
+                        break;
+                if (!is_cal_pci_dev(dev->device))
+                        continue;
+                if (!translate_phb(dev))
+                        continue;
+
+                tce_space = bus_info[dev->bus->number].tce_space;
+                if (!tce_space)
+                        continue;
+
+                calgary_fixup_one_tce_space(dev);
+
+        } while (1);
+
+        return 0;
+}
+
+/*
+ * We need to be call after pcibios_assign_resources (fs_initcall level)
+ * and before device_initcall.
+ */
+rootfs_initcall(calgary_fixup_tce_spaces);
diff --git a/arch/x86_64/kernel/pci-dma.c b/arch/x86_64/kernel/pci-dma.c
index 90f6315d02d4..05d745ede561 100644
--- a/arch/x86_64/kernel/pci-dma.c
+++ b/arch/x86_64/kernel/pci-dma.c
@@ -8,7 +8,7 @@
 #include <linux/pci.h>
 #include <linux/module.h>
 #include <asm/io.h>
-#include <asm/proto.h>
+#include <asm/iommu.h>
 #include <asm/calgary.h>
 
 int iommu_merge __read_mostly = 0;
@@ -321,6 +321,11 @@ static int __init pci_iommu_init(void)
         return 0;
 }
 
+void pci_iommu_shutdown(void)
+{
+        gart_iommu_shutdown();
+}
+
 #ifdef CONFIG_PCI
 /* Many VIA bridges seem to corrupt data for DAC. Disable it here */
 
diff --git a/arch/x86_64/kernel/pci-gart.c b/arch/x86_64/kernel/pci-gart.c
index ae091cdc1a4d..4918c575d582 100644
--- a/arch/x86_64/kernel/pci-gart.c
+++ b/arch/x86_64/kernel/pci-gart.c
@@ -28,6 +28,7 @@
 #include <asm/mtrr.h>
 #include <asm/pgtable.h>
 #include <asm/proto.h>
+#include <asm/iommu.h>
 #include <asm/cacheflush.h>
 #include <asm/swiotlb.h>
 #include <asm/dma.h>
@@ -235,7 +236,7 @@ static dma_addr_t gart_map_simple(struct device *dev, char *buf,
 }
 
 /* Map a single area into the IOMMU */
-dma_addr_t gart_map_single(struct device *dev, void *addr, size_t size, int dir)
+static dma_addr_t gart_map_single(struct device *dev, void *addr, size_t size, int dir)
 {
         unsigned long phys_mem, bus;
 
@@ -253,7 +254,7 @@ dma_addr_t gart_map_single(struct device *dev, void *addr, size_t size, int dir)
 /*
  * Free a DMA mapping.
  */
-void gart_unmap_single(struct device *dev, dma_addr_t dma_addr,
+static void gart_unmap_single(struct device *dev, dma_addr_t dma_addr,
                       size_t size, int direction)
 {
         unsigned long iommu_page;
@@ -275,7 +276,7 @@ void gart_unmap_single(struct device *dev, dma_addr_t dma_addr,
 /*
  * Wrapper for pci_unmap_single working with scatterlists.
  */
-void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
+static void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
 {
         int i;
 
@@ -571,6 +572,26 @@ static const struct dma_mapping_ops gart_dma_ops = {
         .unmap_sg = gart_unmap_sg,
 };
 
+void gart_iommu_shutdown(void)
+{
+        struct pci_dev *dev;
+        int i;
+
+        if (no_agp && (dma_ops != &gart_dma_ops))
+                return;
+
+        for (i = 0; i < num_k8_northbridges; i++) {
+                u32 ctl;
+
+                dev = k8_northbridges[i];
+                pci_read_config_dword(dev, 0x90, &ctl);
+
+                ctl &= ~1;
+
+                pci_write_config_dword(dev, 0x90, ctl);
+        }
+}
+
 void __init gart_iommu_init(void)
 { 
         struct agp_kern_info info;
diff --git a/arch/x86_64/kernel/pci-nommu.c b/arch/x86_64/kernel/pci-nommu.c
index 6dade0c867cc..2a34c6c025a9 100644
--- a/arch/x86_64/kernel/pci-nommu.c
+++ b/arch/x86_64/kernel/pci-nommu.c
@@ -6,7 +6,7 @@
 #include <linux/string.h>
 #include <linux/dma-mapping.h>
 
-#include <asm/proto.h>
+#include <asm/iommu.h>
 #include <asm/processor.h>
 #include <asm/dma.h>
 
@@ -34,7 +34,7 @@ nommu_map_single(struct device *hwdev, void *ptr, size_t size,
         return bus;
 }
 
-void nommu_unmap_single(struct device *dev, dma_addr_t addr,size_t size,
+static void nommu_unmap_single(struct device *dev, dma_addr_t addr,size_t size,
                         int direction)
 {
 }
@@ -54,7 +54,7 @@ void nommu_unmap_single(struct device *dev, dma_addr_t addr,size_t size,
  * Device ownership issues as mentioned above for pci_map_single are
  * the same here.
  */
-int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
+static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
                int nents, int direction)
 {
         int i;
@@ -74,7 +74,7 @@ int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
  * Again, cpu read rules concerning calls here are the same as for
  * pci_unmap_single() above.
  */
-void nommu_unmap_sg(struct device *dev, struct scatterlist *sg,
+static void nommu_unmap_sg(struct device *dev, struct scatterlist *sg,
                   int nents, int dir)
 {
 }
diff --git a/arch/x86_64/kernel/pci-swiotlb.c b/arch/x86_64/kernel/pci-swiotlb.c
index 4b4569abc60c..b2f405ea7c85 100644
--- a/arch/x86_64/kernel/pci-swiotlb.c
+++ b/arch/x86_64/kernel/pci-swiotlb.c
@@ -5,7 +5,7 @@
 #include <linux/module.h>
 #include <linux/dma-mapping.h>
 
-#include <asm/proto.h>
+#include <asm/iommu.h>
 #include <asm/swiotlb.h>
 #include <asm/dma.h>
 
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 5909039f37aa..e7ac629d4c46 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -207,6 +207,7 @@ void cpu_idle (void)
                         if (__get_cpu_var(cpu_idle_state))
                                 __get_cpu_var(cpu_idle_state) = 0;
 
+                        check_pgt_cache();
                         rmb();
                         idle = pm_idle;
                         if (!idle)
@@ -278,7 +279,7 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
                  */
                 if (!pm_idle) {
                         if (!printed) {
-                                printk("using mwait in idle threads.\n");
+                                printk(KERN_INFO "using mwait in idle threads.\n");
                                 printed = 1;
                         }
                         pm_idle = mwait_idle;
@@ -305,6 +306,7 @@ early_param("idle", idle_setup);
 void __show_regs(struct pt_regs * regs)
 {
         unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
+        unsigned long d0, d1, d2, d3, d6, d7;
         unsigned int fsindex,gsindex;
         unsigned int ds,cs,es; 
 
@@ -340,15 +342,24 @@ void __show_regs(struct pt_regs * regs)
         rdmsrl(MSR_GS_BASE, gs); 
         rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); 
 
-        asm("movq %%cr0, %0": "=r" (cr0));
-        asm("movq %%cr2, %0": "=r" (cr2));
-        asm("movq %%cr3, %0": "=r" (cr3));
-        asm("movq %%cr4, %0": "=r" (cr4));
+        cr0 = read_cr0();
+        cr2 = read_cr2();
+        cr3 = read_cr3();
+        cr4 = read_cr4();
 
         printk("FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", 
                fs,fsindex,gs,gsindex,shadowgs); 
         printk("CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, es, cr0); 
         printk("CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, cr4);
+
+        get_debugreg(d0, 0);
+        get_debugreg(d1, 1);
+        get_debugreg(d2, 2);
+        printk("DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
+        get_debugreg(d3, 3);
+        get_debugreg(d6, 6);
+        get_debugreg(d7, 7);
+        printk("DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
 }
 
 void show_regs(struct pt_regs *regs)
diff --git a/arch/x86_64/kernel/reboot.c b/arch/x86_64/kernel/reboot.c
index 7503068e788d..368db2b9c5ac 100644
--- a/arch/x86_64/kernel/reboot.c
+++ b/arch/x86_64/kernel/reboot.c
@@ -16,6 +16,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/apic.h>
+#include <asm/iommu.h>
 
 /*
  * Power off function, if any
@@ -81,6 +82,7 @@ static inline void kb_wait(void)
 void machine_shutdown(void)
 {
         unsigned long flags;
+
         /* Stop the cpus and apics */
 #ifdef CONFIG_SMP
         int reboot_cpu_id;
@@ -111,6 +113,8 @@ void machine_shutdown(void)
         disable_IO_APIC();
 
         local_irq_restore(flags);
+
+        pci_iommu_shutdown();
 }
 
 void machine_emergency_restart(void)
diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c
index 33ef718f8cb5..af838f6b0b7f 100644
--- a/arch/x86_64/kernel/setup.c
+++ b/arch/x86_64/kernel/setup.c
@@ -575,6 +575,8 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
         level = cpuid_eax(1);
         if (c->x86 == 15 && ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58))
                 set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability);
+        if (c->x86 == 0x10)
+                set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability);
 
         /* Enable workaround for FXSAVE leak */
         if (c->x86 >= 6)
@@ -600,8 +602,14 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
         if (c->extended_cpuid_level >= 0x80000008)
                 amd_detect_cmp(c);
 
-        /* Fix cpuid4 emulation for more */
-        num_cache_leaves = 3;
+        if (c->extended_cpuid_level >= 0x80000006 &&
+                (cpuid_edx(0x80000006) & 0xf000))
+                num_cache_leaves = 4;
+        else
+                num_cache_leaves = 3;
+
+        if (c->x86 == 0xf || c->x86 == 0x10 || c->x86 == 0x11)
+                set_bit(X86_FEATURE_K8, &c->x86_capability);
 
         /* RDTSC can be speculated around */
         clear_bit(X86_FEATURE_SYNC_RDTSC, &c->x86_capability);
diff --git a/arch/x86_64/kernel/signal.c b/arch/x86_64/kernel/signal.c
index 290f5d8037cd..739175b01e06 100644
--- a/arch/x86_64/kernel/signal.c
+++ b/arch/x86_64/kernel/signal.c
@@ -26,6 +26,7 @@
 #include <asm/i387.h>
 #include <asm/proto.h>
 #include <asm/ia32_unistd.h>
+#include <asm/mce.h>
 
 /* #define DEBUG_SIG 1 */
 
@@ -472,6 +473,12 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
                 clear_thread_flag(TIF_SINGLESTEP);
         }
 
+#ifdef CONFIG_X86_MCE
+        /* notify userspace of pending MCEs */
+        if (thread_info_flags & _TIF_MCE_NOTIFY)
+                mce_notify_user();
+#endif /* CONFIG_X86_MCE */
+
         /* deal with pending signal delivery */
         if (thread_info_flags & (_TIF_SIGPENDING|_TIF_RESTORE_SIGMASK))
                 do_signal(regs);
@@ -480,7 +487,7 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
 { 
         struct task_struct *me = current; 
-        if (exception_trace)
+        if (show_unhandled_signals && printk_ratelimit())
                 printk("%s[%d] bad frame in %s frame:%p rip:%lx rsp:%lx orax:%lx\n",
                me->comm,me->pid,where,frame,regs->rip,regs->rsp,regs->orig_rax); 
 
diff --git a/arch/x86_64/kernel/smp.c b/arch/x86_64/kernel/smp.c
index 0694940b2e73..673a300b5944 100644
--- a/arch/x86_64/kernel/smp.c
+++ b/arch/x86_64/kernel/smp.c
@@ -241,7 +241,7 @@ void flush_tlb_mm (struct mm_struct * mm)
         }
         if (!cpus_empty(cpu_mask))
                 flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
-
+        check_pgt_cache();
         preempt_enable();
 }
 EXPORT_SYMBOL(flush_tlb_mm);
@@ -386,9 +386,9 @@ int smp_call_function_single (int cpu, void (*func) (void *info), void *info,
                 return 0;
         }
 
-        spin_lock_bh(&call_lock);
+        spin_lock(&call_lock);
         __smp_call_function_single(cpu, func, info, nonatomic, wait);
-        spin_unlock_bh(&call_lock);
+        spin_unlock(&call_lock);
         put_cpu();
         return 0;
 }
diff --git a/arch/x86_64/kernel/suspend.c b/arch/x86_64/kernel/suspend.c
index 6a5a98f2a75c..ea83a9f91965 100644
--- a/arch/x86_64/kernel/suspend.c
+++ b/arch/x86_64/kernel/suspend.c
@@ -55,11 +55,11 @@ void __save_processor_state(struct saved_context *ctxt)
          * control registers 
          */
         rdmsrl(MSR_EFER, ctxt->efer);
-        asm volatile ("movq %%cr0, %0" : "=r" (ctxt->cr0));
-        asm volatile ("movq %%cr2, %0" : "=r" (ctxt->cr2));
-        asm volatile ("movq %%cr3, %0" : "=r" (ctxt->cr3));
-        asm volatile ("movq %%cr4, %0" : "=r" (ctxt->cr4));
-        asm volatile ("movq %%cr8, %0" : "=r" (ctxt->cr8));
+        ctxt->cr0 = read_cr0();
+        ctxt->cr2 = read_cr2();
+        ctxt->cr3 = read_cr3();
+        ctxt->cr4 = read_cr4();
+        ctxt->cr8 = read_cr8();
 }
 
 void save_processor_state(void)
@@ -81,11 +81,11 @@ void __restore_processor_state(struct saved_context *ctxt)
          * control registers
          */
         wrmsrl(MSR_EFER, ctxt->efer);
-        asm volatile ("movq %0, %%cr8" :: "r" (ctxt->cr8));
-        asm volatile ("movq %0, %%cr4" :: "r" (ctxt->cr4));
-        asm volatile ("movq %0, %%cr3" :: "r" (ctxt->cr3));
-        asm volatile ("movq %0, %%cr2" :: "r" (ctxt->cr2));
-        asm volatile ("movq %0, %%cr0" :: "r" (ctxt->cr0));
+        write_cr8(ctxt->cr8);
+        write_cr4(ctxt->cr4);
+        write_cr3(ctxt->cr3);
+        write_cr2(ctxt->cr2);
+        write_cr0(ctxt->cr0);
 
         /*
          * now restore the descriptor tables to their proper values
diff --git a/arch/x86_64/kernel/tce.c b/arch/x86_64/kernel/tce.c
index f61fb8e4f129..3aeae2fa2e24 100644
--- a/arch/x86_64/kernel/tce.c
+++ b/arch/x86_64/kernel/tce.c
@@ -136,9 +136,9 @@ int build_tce_table(struct pci_dev *dev, void __iomem *bbar)
         struct iommu_table *tbl;
         int ret;
 
-        if (dev->sysdata) {
-                printk(KERN_ERR "Calgary: dev %p has sysdata %p\n",
-                       dev, dev->sysdata);
+        if (pci_iommu(dev->bus)) {
+                printk(KERN_ERR "Calgary: dev %p has sysdata->iommu %p\n",
+                       dev, pci_iommu(dev->bus));
                 BUG();
         }
 
@@ -155,11 +155,7 @@ int build_tce_table(struct pci_dev *dev, void __iomem *bbar)
 
         tbl->bbar = bbar;
 
-        /*
-         * NUMA is already using the bus's sysdata pointer, so we use
-         * the bus's pci_dev's sysdata instead.
-         */
-        dev->sysdata = tbl;
+        set_pci_iommu(dev->bus, tbl);
 
         return 0;
 
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index 4a0895bacf51..6d48a4e826d9 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -33,6 +33,7 @@
 #include <acpi/acpi_bus.h>
 #endif
 #include <asm/8253pit.h>
+#include <asm/i8253.h>
 #include <asm/pgtable.h>
 #include <asm/vsyscall.h>
 #include <asm/timex.h>
@@ -44,12 +45,14 @@
 #include <asm/hpet.h>
 #include <asm/mpspec.h>
 #include <asm/nmi.h>
+#include <asm/vgtod.h>
 
 static char *timename = NULL;
 
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL(rtc_lock);
 DEFINE_SPINLOCK(i8253_lock);
+EXPORT_SYMBOL(i8253_lock);
 
 volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
 
@@ -79,8 +82,9 @@ EXPORT_SYMBOL(profile_pc);
  * sheet for details.
  */
 
-static void set_rtc_mmss(unsigned long nowtime)
+static int set_rtc_mmss(unsigned long nowtime)
 {
+        int retval = 0;
         int real_seconds, real_minutes, cmos_minutes;
         unsigned char control, freq_select;
 
@@ -120,6 +124,7 @@ static void set_rtc_mmss(unsigned long nowtime)
         if (abs(real_minutes - cmos_minutes) >= 30) {
                 printk(KERN_WARNING "time.c: can't update CMOS clock "
                        "from %d to %d\n", cmos_minutes, real_minutes);
+                retval = -1;
         } else {
                 BIN_TO_BCD(real_seconds);
                 BIN_TO_BCD(real_minutes);
@@ -139,12 +144,17 @@ static void set_rtc_mmss(unsigned long nowtime)
         CMOS_WRITE(freq_select, RTC_FREQ_SELECT);
 
         spin_unlock(&rtc_lock);
+
+        return retval;
 }
 
+int update_persistent_clock(struct timespec now)
+{
+        return set_rtc_mmss(now.tv_sec);
+}
 
 void main_timer_handler(void)
 {
-        static unsigned long rtc_update = 0;
 /*
  * Here we are in the timer irq handler. We have irqs locally disabled (so we
  * don't need spin_lock_irqsave()) but we don't know if the timer_bh is running
@@ -172,20 +182,6 @@ void main_timer_handler(void)
         if (!using_apic_timer)
                 smp_local_timer_interrupt();
 
-/*
- * If we have an externally synchronized Linux clock, then update CMOS clock
- * accordingly every ~11 minutes. set_rtc_mmss() will be called in the jiffy
- * closest to exactly 500 ms before the next second. If the update fails, we
- * don't care, as it'll be updated on the next turn, and the problem (time way
- * off) isn't likely to go away much sooner anyway.
- */
-
-        if (ntp_synced() && xtime.tv_sec > rtc_update &&
-                abs(xtime.tv_nsec - 500000000) <= tick_nsec / 2) {
-                set_rtc_mmss(xtime.tv_sec);
-                rtc_update = xtime.tv_sec + 660;
-        }
- 
         write_sequnlock(&xtime_lock);
 }
 
@@ -199,7 +195,7 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
         return IRQ_HANDLED;
 }
 
-static unsigned long get_cmos_time(void)
+unsigned long read_persistent_clock(void)
 {
         unsigned int year, mon, day, hour, min, sec;
         unsigned long flags;
@@ -226,7 +222,7 @@ static unsigned long get_cmos_time(void)
         /*
          * We know that x86-64 always uses BCD format, no need to check the
          * config register.
-         */
+         */
 
         BCD_TO_BIN(sec);
         BCD_TO_BIN(min);
@@ -239,11 +235,11 @@ static unsigned long get_cmos_time(void)
                 BCD_TO_BIN(century);
                 year += century * 100;
                 printk(KERN_INFO "Extended CMOS year: %d\n", century * 100);
-        } else { 
+        } else {
                 /*
                  * x86-64 systems only exists since 2002.
                  * This will work up to Dec 31, 2100
-                 */
+                 */
                 year += 2000;
         }
 
@@ -255,45 +251,45 @@ static unsigned long get_cmos_time(void)
 #define TICK_COUNT 100000000
 static unsigned int __init tsc_calibrate_cpu_khz(void)
 {
-       int tsc_start, tsc_now;
-       int i, no_ctr_free;
-       unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0;
-       unsigned long flags;
-
-       for (i = 0; i < 4; i++)
-               if (avail_to_resrv_perfctr_nmi_bit(i))
-                       break;
-       no_ctr_free = (i == 4);
-       if (no_ctr_free) {
-               i = 3;
-               rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
-               wrmsrl(MSR_K7_EVNTSEL3, 0);
-               rdmsrl(MSR_K7_PERFCTR3, pmc3);
-       } else {
-               reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i);
-               reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
-       }
-       local_irq_save(flags);
-       /* start meauring cycles, incrementing from 0 */
-       wrmsrl(MSR_K7_PERFCTR0 + i, 0);
-       wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76);
-       rdtscl(tsc_start);
-       do {
-               rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now);
-               tsc_now = get_cycles_sync();
-       } while ((tsc_now - tsc_start) < TICK_COUNT);
-
-       local_irq_restore(flags);
-       if (no_ctr_free) {
-               wrmsrl(MSR_K7_EVNTSEL3, 0);
-               wrmsrl(MSR_K7_PERFCTR3, pmc3);
-               wrmsrl(MSR_K7_EVNTSEL3, evntsel3);
-       } else {
-               release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
-               release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
-       }
-
-       return pmc_now * tsc_khz / (tsc_now - tsc_start);
+        int tsc_start, tsc_now;
+        int i, no_ctr_free;
+        unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0;
+        unsigned long flags;
+
+        for (i = 0; i < 4; i++)
+                if (avail_to_resrv_perfctr_nmi_bit(i))
+                        break;
+        no_ctr_free = (i == 4);
+        if (no_ctr_free) {
+                i = 3;
+                rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
+                wrmsrl(MSR_K7_EVNTSEL3, 0);
+                rdmsrl(MSR_K7_PERFCTR3, pmc3);
+        } else {
+                reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+                reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+        }
+        local_irq_save(flags);
+        /* start meauring cycles, incrementing from 0 */
+        wrmsrl(MSR_K7_PERFCTR0 + i, 0);
+        wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76);
+        rdtscl(tsc_start);
+        do {
+                rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now);
+                tsc_now = get_cycles_sync();
+        } while ((tsc_now - tsc_start) < TICK_COUNT);
+
+        local_irq_restore(flags);
+        if (no_ctr_free) {
+                wrmsrl(MSR_K7_EVNTSEL3, 0);
+                wrmsrl(MSR_K7_PERFCTR3, pmc3);
+                wrmsrl(MSR_K7_EVNTSEL3, evntsel3);
+        } else {
+                release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+                release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+        }
+
+        return pmc_now * tsc_khz / (tsc_now - tsc_start);
 }
 
 /*
@@ -321,7 +317,7 @@ static unsigned int __init pit_calibrate_tsc(void)
         end = get_cycles_sync();
 
         spin_unlock_irqrestore(&i8253_lock, flags);
-        
+
         return (end - start) / 50;
 }
 
@@ -366,25 +362,20 @@ static struct irqaction irq0 = {
         .handler        = timer_interrupt,
         .flags          = IRQF_DISABLED | IRQF_IRQPOLL,
         .mask           = CPU_MASK_NONE,
-        .name           = "timer"
+        .name           = "timer"
 };
 
 void __init time_init(void)
 {
         if (nohpet)
                 hpet_address = 0;
-        xtime.tv_sec = get_cmos_time();
-        xtime.tv_nsec = 0;
-
-        set_normalized_timespec(&wall_to_monotonic,
-                                -xtime.tv_sec, -xtime.tv_nsec);
 
         if (hpet_arch_init())
                 hpet_address = 0;
 
         if (hpet_use_timer) {
                 /* set tick_nsec to use the proper rate for HPET */
-                tick_nsec = TICK_NSEC_HPET;
+                tick_nsec = TICK_NSEC_HPET;
                 tsc_khz = hpet_calibrate_tsc();
                 timename = "HPET";
         } else {
@@ -415,54 +406,21 @@ void __init time_init(void)
         setup_irq(0, &irq0);
 }
 
-
-static long clock_cmos_diff;
-static unsigned long sleep_start;
-
 /*
  * sysfs support for the timer.
  */
 
 static int timer_suspend(struct sys_device *dev, pm_message_t state)
 {
-        /*
-         * Estimate time zone so that set_time can update the clock
-         */
-        long cmos_time =  get_cmos_time();
-
-        clock_cmos_diff = -cmos_time;
-        clock_cmos_diff += get_seconds();
-        sleep_start = cmos_time;
         return 0;
 }
 
 static int timer_resume(struct sys_device *dev)
 {
-        unsigned long flags;
-        unsigned long sec;
-        unsigned long ctime = get_cmos_time();
-        long sleep_length = (ctime - sleep_start) * HZ;
-
-        if (sleep_length < 0) {
-                printk(KERN_WARNING "Time skew detected in timer resume!\n");
-                /* The time after the resume must not be earlier than the time
-                 * before the suspend or some nasty things will happen
-                 */
-                sleep_length = 0;
-                ctime = sleep_start;
-        }
         if (hpet_address)
                 hpet_reenable();
         else
                 i8254_timer_resume();
-
-        sec = ctime + clock_cmos_diff;
-        write_seqlock_irqsave(&xtime_lock,flags);
-        xtime.tv_sec = sec;
-        xtime.tv_nsec = 0;
-        jiffies += sleep_length;
-        write_sequnlock_irqrestore(&xtime_lock,flags);
-        touch_softlockup_watchdog();
         return 0;
 }
 
diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c
index 8713ad4a4db1..03888420775d 100644
--- a/arch/x86_64/kernel/traps.c
+++ b/arch/x86_64/kernel/traps.c
@@ -584,7 +584,8 @@ static void __kprobes do_trap(int trapnr, int signr, char *str,
                 tsk->thread.error_code = error_code;
                 tsk->thread.trap_no = trapnr;
 
-                if (exception_trace && unhandled_signal(tsk, signr))
+                if (show_unhandled_signals && unhandled_signal(tsk, signr) &&
+                    printk_ratelimit())
                         printk(KERN_INFO
                                "%s[%d] trap %s rip:%lx rsp:%lx error:%lx\n",
                                tsk->comm, tsk->pid, str,
@@ -688,7 +689,8 @@ asmlinkage void __kprobes do_general_protection(struct pt_regs * regs,
                 tsk->thread.error_code = error_code;
                 tsk->thread.trap_no = 13;
 
-                if (exception_trace && unhandled_signal(tsk, SIGSEGV))
+                if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
+                    printk_ratelimit())
                         printk(KERN_INFO
                        "%s[%d] general protection rip:%lx rsp:%lx error:%lx\n",
                                tsk->comm, tsk->pid,
diff --git a/arch/x86_64/kernel/tsc.c b/arch/x86_64/kernel/tsc.c
index e850aa01e1b3..9b76b03d0600 100644
--- a/arch/x86_64/kernel/tsc.c
+++ b/arch/x86_64/kernel/tsc.c
@@ -61,25 +61,9 @@ inline int check_tsc_unstable(void)
  * first tick after the change will be slightly wrong.
  */
 
-#include <linux/workqueue.h>
-
-static unsigned int cpufreq_delayed_issched = 0;
-static unsigned int cpufreq_init = 0;
-static struct work_struct cpufreq_delayed_get_work;
-
-static void handle_cpufreq_delayed_get(struct work_struct *v)
-{
-        unsigned int cpu;
-        for_each_online_cpu(cpu) {
-                cpufreq_get(cpu);
-        }
-        cpufreq_delayed_issched = 0;
-}
-
-static unsigned int  ref_freq = 0;
-static unsigned long loops_per_jiffy_ref = 0;
-
-static unsigned long tsc_khz_ref = 0;
+static unsigned int  ref_freq;
+static unsigned long loops_per_jiffy_ref;
+static unsigned long tsc_khz_ref;
 
 static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
                                  void *data)
@@ -125,10 +109,8 @@ static struct notifier_block time_cpufreq_notifier_block = {
 
 static int __init cpufreq_tsc(void)
 {
-        INIT_WORK(&cpufreq_delayed_get_work, handle_cpufreq_delayed_get);
-        if (!cpufreq_register_notifier(&time_cpufreq_notifier_block,
-                                       CPUFREQ_TRANSITION_NOTIFIER))
-                cpufreq_init = 1;
+        cpufreq_register_notifier(&time_cpufreq_notifier_block,
+                                  CPUFREQ_TRANSITION_NOTIFIER);
         return 0;
 }
 
@@ -153,17 +135,18 @@ __cpuinit int unsynchronized_tsc(void)
 #endif
         /* Most intel systems have synchronized TSCs except for
            multi node systems */
-        if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
+        if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
 #ifdef CONFIG_ACPI
                 /* But TSC doesn't tick in C3 so don't use it there */
-                if (acpi_gbl_FADT.header.length > 0 && acpi_gbl_FADT.C3latency < 1000)
+                if (acpi_gbl_FADT.header.length > 0 &&
+                    acpi_gbl_FADT.C3latency < 1000)
                         return 1;
 #endif
-                return 0;
+                return 0;
         }
 
-        /* Assume multi socket systems are not synchronized */
-        return num_present_cpus() > 1;
+        /* Assume multi socket systems are not synchronized */
+        return num_present_cpus() > 1;
 }
 
 int __init notsc_setup(char *s)
diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S
index 5c57ea4591c1..ba8ea97abd21 100644
--- a/arch/x86_64/kernel/vmlinux.lds.S
+++ b/arch/x86_64/kernel/vmlinux.lds.S
@@ -28,7 +28,7 @@ SECTIONS
   _text = .;                    /* Text and read-only data */
   .text :  AT(ADDR(.text) - LOAD_OFFSET) {
         /* First the code that has to be first for bootstrapping */
-        *(.bootstrap.text)
+        *(.text.head)
         _stext = .;
         /* Then the rest */
         TEXT_TEXT
@@ -54,6 +54,13 @@ SECTIONS
 
   RODATA
 
+  . = ALIGN(4);
+  .tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) {
+        __tracedata_start = .;
+        *(.tracedata)
+        __tracedata_end = .;
+  }
+
   . = ALIGN(PAGE_SIZE);        /* Align data segment to page size boundary */
                                 /* Data */
   .data : AT(ADDR(.data) - LOAD_OFFSET) {
@@ -93,6 +100,9 @@ SECTIONS
   .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data))
                 { *(.vsyscall_gtod_data) }
   vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
+  .vsyscall_clock : AT(VLOAD(.vsyscall_clock))
+                { *(.vsyscall_clock) }
+  vsyscall_clock = VVIRT(.vsyscall_clock);
 
 
   .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1))
@@ -133,20 +143,11 @@ SECTIONS
   /* might get freed after init */
   . = ALIGN(4096);
   __smp_alt_begin = .;
-  __smp_alt_instructions = .;
-  .smp_altinstructions : AT(ADDR(.smp_altinstructions) - LOAD_OFFSET) {
-        *(.smp_altinstructions)
-  }
-  __smp_alt_instructions_end = .;
-  . = ALIGN(8);
   __smp_locks = .;
   .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
         *(.smp_locks)
   }
   __smp_locks_end = .;
-  .smp_altinstr_replacement : AT(ADDR(.smp_altinstr_replacement) - LOAD_OFFSET) {
-        *(.smp_altinstr_replacement)
-  }
   . = ALIGN(4096);
   __smp_alt_end = .;
 
@@ -189,6 +190,12 @@ SECTIONS
   .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) { *(.exit.text) }
   .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) { *(.exit.data) }
 
+/* vdso blob that is mapped into user space */
+  vdso_start = . ;
+  .vdso  : AT(ADDR(.vdso) - LOAD_OFFSET) { *(.vdso) }
+  . = ALIGN(4096);
+  vdso_end = .;
+
 #ifdef CONFIG_BLK_DEV_INITRD
   . = ALIGN(4096);
   __initramfs_start = .;
diff --git a/arch/x86_64/kernel/vsyscall.c b/arch/x86_64/kernel/vsyscall.c
index 57660d58d500..06c34949bfdc 100644
--- a/arch/x86_64/kernel/vsyscall.c
+++ b/arch/x86_64/kernel/vsyscall.c
@@ -42,6 +42,7 @@
 #include <asm/segment.h>
 #include <asm/desc.h>
 #include <asm/topology.h>
+#include <asm/vgtod.h>
 
 #define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr)))
 #define __syscall_clobber "r11","rcx","memory"
@@ -57,26 +58,9 @@
  * - writen by timer interrupt or systcl (/proc/sys/kernel/vsyscall64)
  * Try to keep this structure as small as possible to avoid cache line ping pongs
  */
-struct vsyscall_gtod_data_t {
-        seqlock_t       lock;
-
-        /* open coded 'struct timespec' */
-        time_t          wall_time_sec;
-        u32             wall_time_nsec;
-
-        int             sysctl_enabled;
-        struct timezone sys_tz;
-        struct { /* extract of a clocksource struct */
-                cycle_t (*vread)(void);
-                cycle_t cycle_last;
-                cycle_t mask;
-                u32     mult;
-                u32     shift;
-        } clock;
-};
 int __vgetcpu_mode __section_vgetcpu_mode;
 
-struct vsyscall_gtod_data_t __vsyscall_gtod_data __section_vsyscall_gtod_data =
+struct vsyscall_gtod_data __vsyscall_gtod_data __section_vsyscall_gtod_data =
 {
         .lock = SEQLOCK_UNLOCKED,
         .sysctl_enabled = 1,
@@ -96,6 +80,8 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
         vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec;
         vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
         vsyscall_gtod_data.sys_tz = sys_tz;
+        vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
+        vsyscall_gtod_data.wall_to_monotonic = wall_to_monotonic;
         write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
 }
 
diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
index 84f11728fc76..327c9f2fa626 100644
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -159,7 +159,7 @@ void dump_pagetable(unsigned long address)
         pmd_t *pmd;
         pte_t *pte;
 
-        asm("movq %%cr3,%0" : "=r" (pgd));
+        pgd = (pgd_t *)read_cr3();
 
         pgd = __va((unsigned long)pgd & PHYSICAL_PAGE_MASK); 
         pgd += pgd_index(address);
@@ -221,16 +221,6 @@ static int is_errata93(struct pt_regs *regs, unsigned long address)
         return 0;
 } 
 
-int unhandled_signal(struct task_struct *tsk, int sig)
-{
-        if (is_init(tsk))
-                return 1;
-        if (tsk->ptrace & PT_PTRACED)
-                return 0;
-        return (tsk->sighand->action[sig-1].sa.sa_handler == SIG_IGN) ||
-                (tsk->sighand->action[sig-1].sa.sa_handler == SIG_DFL);
-}
-
 static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
                                  unsigned long error_code)
 {
@@ -301,8 +291,8 @@ static int vmalloc_fault(unsigned long address)
         return 0;
 }
 
-int page_fault_trace = 0;
-int exception_trace = 1;
+static int page_fault_trace;
+int show_unhandled_signals = 1;
 
 /*
  * This routine handles page faults.  It determines the address,
@@ -326,7 +316,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
         prefetchw(&mm->mmap_sem);
 
         /* get the address */
-        __asm__("movq %%cr2,%0":"=r" (address));
+        address = read_cr2();
 
         info.si_code = SEGV_MAPERR;
 
@@ -494,7 +484,8 @@ bad_area_nosemaphore:
                     (address >> 32))
                         return;
 
-                if (exception_trace && unhandled_signal(tsk, SIGSEGV)) {
+                if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
+                    printk_ratelimit()) {
                         printk(
                        "%s%s[%d]: segfault at %016lx rip %016lx rsp %016lx error %lx\n",
                                         tsk->pid > 1 ? KERN_INFO : KERN_EMERG,
@@ -568,7 +559,7 @@ out_of_memory:
         }
         printk("VM: killing process %s\n", tsk->comm);
         if (error_code & 4)
-                do_exit(SIGKILL);
+                do_group_exit(SIGKILL);
         goto no_context;
 
 do_sigbus:
diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index 9a0e98accf04..38f5d6368006 100644
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -383,7 +383,7 @@ void __meminit init_memory_mapping(unsigned long start, unsigned long end)
         } 
 
         if (!after_bootmem)
-                asm volatile("movq %%cr4,%0" : "=r" (mmu_cr4_features));
+                mmu_cr4_features = read_cr4();
         __flush_tlb_all();
 }
 
@@ -600,16 +600,6 @@ void mark_rodata_ro(void)
 {
         unsigned long start = (unsigned long)_stext, end;
 
-#ifdef CONFIG_HOTPLUG_CPU
-        /* It must still be possible to apply SMP alternatives. */
-        if (num_possible_cpus() > 1)
-                start = (unsigned long)_etext;
-#endif
-
-#ifdef CONFIG_KPROBES
-        start = (unsigned long)__start_rodata;
-#endif
-        
         end = (unsigned long)__end_rodata;
         start = (start + PAGE_SIZE - 1) & PAGE_MASK;
         end &= PAGE_MASK;
@@ -697,41 +687,6 @@ int kern_addr_valid(unsigned long addr)
         return pfn_valid(pte_pfn(*pte));
 }
 
-#ifdef CONFIG_SYSCTL
-#include <linux/sysctl.h>
-
-extern int exception_trace, page_fault_trace;
-
-static ctl_table debug_table2[] = {
-        {
-                .ctl_name       = 99,
-                .procname       = "exception-trace",
-                .data           = &exception_trace,
-                .maxlen         = sizeof(int),
-                .mode           = 0644,
-                .proc_handler   = proc_dointvec
-        },
-        {}
-}; 
-
-static ctl_table debug_root_table2[] = { 
-        {
-                .ctl_name = CTL_DEBUG,
-                .procname = "debug",
-                .mode = 0555,
-                .child = debug_table2
-        },
-        {}
-}; 
-
-static __init int x8664_sysctl_init(void)
-{ 
-        register_sysctl_table(debug_root_table2);
-        return 0;
-}
-__initcall(x8664_sysctl_init);
-#endif
-
 /* A pseudo VMA to allow ptrace access for the vsyscall page.  This only
    covers the 64bit vsyscall page now. 32bit has a real VMA now and does
    not need special handling anymore. */
@@ -769,8 +724,17 @@ int in_gate_area_no_task(unsigned long addr)
         return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END);
 }
 
-void *alloc_bootmem_high_node(pg_data_t *pgdat, unsigned long size)
+void * __init alloc_bootmem_high_node(pg_data_t *pgdat, unsigned long size)
 {
         return __alloc_bootmem_core(pgdat->bdata, size,
                         SMP_CACHE_BYTES, (4UL*1024*1024*1024), 0);
 }
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+        if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
+                return "[vdso]";
+        if (vma == &gate_vma)
+                return "[vsyscall]";
+        return NULL;
+}
diff --git a/arch/x86_64/mm/k8topology.c b/arch/x86_64/mm/k8topology.c
index f983c75825d0..a96006f7ae0c 100644
--- a/arch/x86_64/mm/k8topology.c
+++ b/arch/x86_64/mm/k8topology.c
@@ -44,12 +44,12 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
 { 
         unsigned long prevbase;
         struct bootnode nodes[8];
-        int nodeid, i, nb; 
+        int nodeid, i, j, nb;
         unsigned char nodeids[8];
         int found = 0;
         u32 reg;
         unsigned numnodes;
-        unsigned dualcore = 0;
+        unsigned num_cores;
 
         if (!early_pci_allowed())
                 return -1;
@@ -60,6 +60,9 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
 
         printk(KERN_INFO "Scanning NUMA topology in Northbridge %d\n", nb); 
 
+        num_cores = (cpuid_ecx(0x80000008) & 0xff) + 1;
+        printk(KERN_INFO "CPU has %d num_cores\n", num_cores);
+
         reg = read_pci_config(0, nb, 0, 0x60); 
         numnodes = ((reg >> 4) & 0xF) + 1;
         if (numnodes <= 1)
@@ -73,8 +76,6 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
                 unsigned long base,limit; 
                 u32 nodeid;
                 
-                /* Undefined before E stepping, but hopefully 0 */
-                dualcore |= ((read_pci_config(0, nb, 3, 0xe8) >> 12) & 3) == 1;
                 base = read_pci_config(0, nb, 1, 0x40 + i*8);
                 limit = read_pci_config(0, nb, 1, 0x44 + i*8);
 
@@ -170,8 +171,8 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
         for (i = 0; i < 8; i++) {
                 if (nodes[i].start != nodes[i].end) { 
                         nodeid = nodeids[i];
-                        apicid_to_node[nodeid << dualcore] = i;
-                        apicid_to_node[(nodeid << dualcore) + dualcore] = i;
+                        for (j = 0; j < num_cores; j++)
+                                apicid_to_node[(nodeid * num_cores) + j] = i;
                         setup_node_bootmem(i, nodes[i].start, nodes[i].end); 
                 } 
         }
diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index 51548947ad3b..6da235522269 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -273,9 +273,6 @@ void __init numa_init_array(void)
 
 #ifdef CONFIG_NUMA_EMU
 /* Numa emulation */
-#define E820_ADDR_HOLE_SIZE(start, end)                                 \
-        (e820_hole_size((start) >> PAGE_SHIFT, (end) >> PAGE_SHIFT) <<  \
-        PAGE_SHIFT)
 char *cmdline __initdata;
 
 /*
@@ -319,7 +316,7 @@ static int __init split_nodes_equally(struct bootnode *nodes, u64 *addr,
                 return -1;
         if (num_nodes > MAX_NUMNODES)
                 num_nodes = MAX_NUMNODES;
-        size = (max_addr - *addr - E820_ADDR_HOLE_SIZE(*addr, max_addr)) /
+        size = (max_addr - *addr - e820_hole_size(*addr, max_addr)) /
                num_nodes;
         /*
          * Calculate the number of big nodes that can be allocated as a result
@@ -347,7 +344,7 @@ static int __init split_nodes_equally(struct bootnode *nodes, u64 *addr,
                 if (i == num_nodes + node_start - 1)
                         end = max_addr;
                 else
-                        while (end - *addr - E820_ADDR_HOLE_SIZE(*addr, end) <
+                        while (end - *addr - e820_hole_size(*addr, end) <
                                size) {
                                 end += FAKE_NODE_MIN_SIZE;
                                 if (end > max_addr) {
@@ -476,18 +473,22 @@ out:
 
         /*
          * We need to vacate all active ranges that may have been registered by
-         * SRAT.
+         * SRAT and set acpi_numa to -1 so that srat_disabled() always returns
+         * true.  NUMA emulation has succeeded so we will not scan ACPI nodes.
          */
         remove_all_active_ranges();
+#ifdef CONFIG_ACPI_NUMA
+        acpi_numa = -1;
+#endif
         for_each_node_mask(i, node_possible_map) {
                 e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
                                                 nodes[i].end >> PAGE_SHIFT);
                 setup_node_bootmem(i, nodes[i].start, nodes[i].end);
         }
+        acpi_fake_nodes(nodes, num_nodes);
         numa_init_array();
         return 0;
 }
-#undef E820_ADDR_HOLE_SIZE
 #endif /* CONFIG_NUMA_EMU */
 
 void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
diff --git a/arch/x86_64/mm/pageattr.c b/arch/x86_64/mm/pageattr.c
index 9148f4a4cec6..7e161c698af4 100644
--- a/arch/x86_64/mm/pageattr.c
+++ b/arch/x86_64/mm/pageattr.c
@@ -13,7 +13,7 @@
 #include <asm/tlbflush.h>
 #include <asm/io.h>
 
-static inline pte_t *lookup_address(unsigned long address) 
+pte_t *lookup_address(unsigned long address)
 { 
         pgd_t *pgd = pgd_offset_k(address);
         pud_t *pud;
@@ -74,14 +74,12 @@ static void flush_kernel_map(void *arg)
         struct page *pg;
 
         /* When clflush is available always use it because it is
-           much cheaper than WBINVD. Disable clflush for now because
-           the high level code is not ready yet */
-        if (1 || !cpu_has_clflush)
+           much cheaper than WBINVD. */
+        if (!cpu_has_clflush)
                 asm volatile("wbinvd" ::: "memory");
         else list_for_each_entry(pg, l, lru) {
                 void *adr = page_address(pg);
-                if (cpu_has_clflush)
-                        cache_flush_page(adr);
+                cache_flush_page(adr);
         }
         __flush_tlb_all();
 }
@@ -95,7 +93,8 @@ static LIST_HEAD(deferred_pages); /* protected by init_mm.mmap_sem */
 
 static inline void save_page(struct page *fpage)
 {
-        list_add(&fpage->lru, &deferred_pages);
+        if (!test_and_set_bit(PG_arch_1, &fpage->flags))
+                list_add(&fpage->lru, &deferred_pages);
 }
 
 /* 
@@ -129,9 +128,12 @@ __change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot,
         pte_t *kpte; 
         struct page *kpte_page;
         pgprot_t ref_prot2;
+
         kpte = lookup_address(address);
         if (!kpte) return 0;
         kpte_page = virt_to_page(((unsigned long)kpte) & PAGE_MASK);
+        BUG_ON(PageLRU(kpte_page));
+        BUG_ON(PageCompound(kpte_page));
         if (pgprot_val(prot) != pgprot_val(ref_prot)) { 
                 if (!pte_huge(*kpte)) {
                         set_pte(kpte, pfn_pte(pfn, prot));
@@ -159,10 +161,9 @@ __change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot,
         /* on x86-64 the direct mapping set at boot is not using 4k pages */
         BUG_ON(PageReserved(kpte_page));
 
-        if (page_private(kpte_page) == 0) {
-                save_page(kpte_page);
+        save_page(kpte_page);
+        if (page_private(kpte_page) == 0)
                 revert_page(address, ref_prot);
-        }
         return 0;
 } 
 
@@ -234,6 +235,10 @@ void global_flush_tlb(void)
         flush_map(&l);
 
         list_for_each_entry_safe(pg, next, &l, lru) {
+                list_del(&pg->lru);
+                clear_bit(PG_arch_1, &pg->flags);
+                if (page_private(pg) != 0)
+                        continue;
                 ClearPagePrivate(pg);
                 __free_page(pg);
         } 
diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c
index 1e76bb0a7277..acdf03e19146 100644
--- a/arch/x86_64/mm/srat.c
+++ b/arch/x86_64/mm/srat.c
@@ -106,9 +106,9 @@ static __init int slit_valid(struct acpi_table_slit *slit)
                 for (j = 0; j < d; j++)  {
                         u8 val = slit->entry[d*i + j];
                         if (i == j) {
-                                if (val != 10)
+                                if (val != LOCAL_DISTANCE)
                                         return 0;
-                        } else if (val <= 10)
+                        } else if (val <= LOCAL_DISTANCE)
                                 return 0;
                 }
         }
@@ -350,7 +350,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 
 /* Sanity check to catch more bad SRATs (they are amazingly common).
    Make sure the PXMs cover all memory. */
-static int nodes_cover_memory(void)
+static int __init nodes_cover_memory(const struct bootnode *nodes)
 {
         int i;
         unsigned long pxmram, e820ram;
@@ -394,6 +394,9 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 {
         int i;
 
+        if (acpi_numa <= 0)
+                return -1;
+
         /* First clean up the node list */
         for (i = 0; i < MAX_NUMNODES; i++) {
                 cutoff_node(i, start, end);
@@ -403,10 +406,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
                 }
         }
 
-        if (acpi_numa <= 0)
-                return -1;
-
-        if (!nodes_cover_memory()) {
+        if (!nodes_cover_memory(nodes)) {
                 bad_srat();
                 return -1;
         }
@@ -440,6 +440,86 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
         return 0;
 }
 
+#ifdef CONFIG_NUMA_EMU
+static int __init find_node_by_addr(unsigned long addr)
+{
+        int ret = NUMA_NO_NODE;
+        int i;
+
+        for_each_node_mask(i, nodes_parsed) {
+                /*
+                 * Find the real node that this emulated node appears on.  For
+                 * the sake of simplicity, we only use a real node's starting
+                 * address to determine which emulated node it appears on.
+                 */
+                if (addr >= nodes[i].start && addr < nodes[i].end) {
+                        ret = i;
+                        break;
+                }
+        }
+        return i;
+}
+
+/*
+ * In NUMA emulation, we need to setup proximity domain (_PXM) to node ID
+ * mappings that respect the real ACPI topology but reflect our emulated
+ * environment.  For each emulated node, we find which real node it appears on
+ * and create PXM to NID mappings for those fake nodes which mirror that
+ * locality.  SLIT will now represent the correct distances between emulated
+ * nodes as a result of the real topology.
+ */
+void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
+{
+        int i, j;
+        int fake_node_to_pxm_map[MAX_NUMNODES] = {
+                [0 ... MAX_NUMNODES-1] = PXM_INVAL
+        };
+        unsigned char fake_apicid_to_node[MAX_LOCAL_APIC] = {
+                [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
+        };
+
+        printk(KERN_INFO "Faking PXM affinity for fake nodes on real "
+                         "topology.\n");
+        for (i = 0; i < num_nodes; i++) {
+                int nid, pxm;
+
+                nid = find_node_by_addr(fake_nodes[i].start);
+                if (nid == NUMA_NO_NODE)
+                        continue;
+                pxm = node_to_pxm(nid);
+                if (pxm == PXM_INVAL)
+                        continue;
+                fake_node_to_pxm_map[i] = pxm;
+                /*
+                 * For each apicid_to_node mapping that exists for this real
+                 * node, it must now point to the fake node ID.
+                 */
+                for (j = 0; j < MAX_LOCAL_APIC; j++)
+                        if (apicid_to_node[j] == nid)
+                                fake_apicid_to_node[j] = i;
+        }
+        for (i = 0; i < num_nodes; i++)
+                __acpi_map_pxm_to_node(fake_node_to_pxm_map[i], i);
+        memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
+
+        nodes_clear(nodes_parsed);
+        for (i = 0; i < num_nodes; i++)
+                if (fake_nodes[i].start != fake_nodes[i].end)
+                        node_set(i, nodes_parsed);
+        WARN_ON(!nodes_cover_memory(fake_nodes));
+}
+
+static int null_slit_node_compare(int a, int b)
+{
+        return node_to_pxm(a) == node_to_pxm(b);
+}
+#else
+static int null_slit_node_compare(int a, int b)
+{
+        return a == b;
+}
+#endif /* CONFIG_NUMA_EMU */
+
 void __init srat_reserve_add_area(int nodeid)
 {
         if (found_add_area && nodes_add[nodeid].end) {
@@ -464,7 +544,8 @@ int __node_distance(int a, int b)
         int index;
 
         if (!acpi_slit)
-                return a == b ? 10 : 20;
+                return null_slit_node_compare(a, b) ? LOCAL_DISTANCE :
+                                                      REMOTE_DISTANCE;
         index = acpi_slit->locality_count * node_to_pxm(a);
         return acpi_slit->entry[index + node_to_pxm(b)];
 }
diff --git a/arch/x86_64/pci/k8-bus.c b/arch/x86_64/pci/k8-bus.c
index 3acf60ded2a0..9cc813e29706 100644
--- a/arch/x86_64/pci/k8-bus.c
+++ b/arch/x86_64/pci/k8-bus.c
@@ -59,6 +59,8 @@ fill_mp_bus_to_cpumask(void)
                                      j <= SUBORDINATE_LDT_BUS_NUMBER(ldtbus);
                                      j++) { 
                                         struct pci_bus *bus;
+                                        struct pci_sysdata *sd;
+
                                         long node = NODE_ID(nid);
                                         /* Algorithm a bit dumb, but
                                            it shouldn't matter here */
@@ -67,7 +69,9 @@ fill_mp_bus_to_cpumask(void)
                                                 continue;
                                         if (!node_online(node))
                                                 node = 0;
-                                        bus->sysdata = (void *)node;
+
+                                        sd = bus->sysdata;
+                                        sd->node = node;
                                 }               
                         }
                 }
diff --git a/arch/x86_64/vdso/Makefile b/arch/x86_64/vdso/Makefile
new file mode 100644
index 000000000000..faaa72fb250c
--- /dev/null
+++ b/arch/x86_64/vdso/Makefile
@@ -0,0 +1,49 @@
+#
+# x86-64 vDSO.
+#
+
+# files to link into the vdso
+# vdso-start.o has to be first
+vobjs-y := vdso-start.o vdso-note.o vclock_gettime.o vgetcpu.o vvar.o
+
+# files to link into kernel
+obj-y := vma.o vdso.o vdso-syms.o
+
+vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
+
+$(obj)/vdso.o: $(obj)/vdso.so
+
+targets += vdso.so vdso.lds $(vobjs-y) vdso-syms.o
+
+# The DSO images are built using a special linker script.
+quiet_cmd_syscall = SYSCALL $@
+      cmd_syscall = $(CC) -m elf_x86_64 -nostdlib $(SYSCFLAGS_$(@F)) \
+                          -Wl,-T,$(filter-out FORCE,$^) -o $@
+
+export CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
+
+vdso-flags = -fPIC -shared -Wl,-soname=linux-vdso.so.1 \
+                 $(call ld-option, -Wl$(comma)--hash-style=sysv) \
+                -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
+SYSCFLAGS_vdso.so = $(vdso-flags)
+
+$(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
+
+$(obj)/vdso.so: $(src)/vdso.lds $(vobjs) FORCE
+        $(call if_changed,syscall)
+
+CF := $(PROFILING) -mcmodel=small -fPIC -g0 -O2 -fasynchronous-unwind-tables -m64
+
+$(obj)/vclock_gettime.o: CFLAGS = $(CF)
+$(obj)/vgetcpu.o: CFLAGS = $(CF)
+
+# We also create a special relocatable object that should mirror the symbol
+# table and layout of the linked DSO.  With ld -R we can then refer to
+# these symbols in the kernel code rather than hand-coded addresses.
+extra-y += vdso-syms.o
+$(obj)/built-in.o: $(obj)/vdso-syms.o
+$(obj)/built-in.o: ld_flags += -R $(obj)/vdso-syms.o
+
+SYSCFLAGS_vdso-syms.o = -r -d
+$(obj)/vdso-syms.o: $(src)/vdso.lds $(vobjs) FORCE
+        $(call if_changed,syscall)
diff --git a/arch/x86_64/vdso/vclock_gettime.c b/arch/x86_64/vdso/vclock_gettime.c
new file mode 100644
index 000000000000..17f6a00de712
--- /dev/null
+++ b/arch/x86_64/vdso/vclock_gettime.c
@@ -0,0 +1,120 @@
+/*
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * Subject to the GNU Public License, v.2
+ *
+ * Fast user context implementation of clock_gettime and gettimeofday.
+ *
+ * The code should have no internal unresolved relocations.
+ * Check with readelf after changing.
+ * Also alternative() doesn't work.
+ */
+
+#include <linux/kernel.h>
+#include <linux/posix-timers.h>
+#include <linux/time.h>
+#include <linux/string.h>
+#include <asm/vsyscall.h>
+#include <asm/vgtod.h>
+#include <asm/timex.h>
+#include <asm/hpet.h>
+#include <asm/unistd.h>
+#include <asm/io.h>
+#include <asm/vgtod.h>
+#include "vextern.h"
+
+#define gtod vdso_vsyscall_gtod_data
+
+static long vdso_fallback_gettime(long clock, struct timespec *ts)
+{
+        long ret;
+        asm("syscall" : "=a" (ret) :
+            "0" (__NR_clock_gettime),"D" (clock), "S" (ts) : "memory");
+        return ret;
+}
+
+static inline long vgetns(void)
+{
+        cycles_t (*vread)(void);
+        vread = gtod->clock.vread;
+        return ((vread() - gtod->clock.cycle_last) * gtod->clock.mult) >>
+                gtod->clock.shift;
+}
+
+static noinline int do_realtime(struct timespec *ts)
+{
+        unsigned long seq, ns;
+        do {
+                seq = read_seqbegin(&gtod->lock);
+                ts->tv_sec = gtod->wall_time_sec;
+                ts->tv_nsec = gtod->wall_time_nsec;
+                ns = vgetns();
+        } while (unlikely(read_seqretry(&gtod->lock, seq)));
+        timespec_add_ns(ts, ns);
+        return 0;
+}
+
+/* Copy of the version in kernel/time.c which we cannot directly access */
+static void vset_normalized_timespec(struct timespec *ts, long sec, long nsec)
+{
+        while (nsec >= NSEC_PER_SEC) {
+                nsec -= NSEC_PER_SEC;
+                ++sec;
+        }
+        while (nsec < 0) {
+                nsec += NSEC_PER_SEC;
+                --sec;
+        }
+        ts->tv_sec = sec;
+        ts->tv_nsec = nsec;
+}
+
+static noinline int do_monotonic(struct timespec *ts)
+{
+        unsigned long seq, ns, secs;
+        do {
+                seq = read_seqbegin(&gtod->lock);
+                secs = gtod->wall_time_sec;
+                ns = gtod->wall_time_nsec + vgetns();
+                secs += gtod->wall_to_monotonic.tv_sec;
+                ns += gtod->wall_to_monotonic.tv_nsec;
+        } while (unlikely(read_seqretry(&gtod->lock, seq)));
+        vset_normalized_timespec(ts, secs, ns);
+        return 0;
+}
+
+int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
+{
+        if (likely(gtod->sysctl_enabled && gtod->clock.vread))
+                switch (clock) {
+                case CLOCK_REALTIME:
+                        return do_realtime(ts);
+                case CLOCK_MONOTONIC:
+                        return do_monotonic(ts);
+                }
+        return vdso_fallback_gettime(clock, ts);
+}
+int clock_gettime(clockid_t, struct timespec *)
+        __attribute__((weak, alias("__vdso_clock_gettime")));
+
+int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+        long ret;
+        if (likely(gtod->sysctl_enabled && gtod->clock.vread)) {
+                BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
+                             offsetof(struct timespec, tv_nsec) ||
+                             sizeof(*tv) != sizeof(struct timespec));
+                do_realtime((struct timespec *)tv);
+                tv->tv_usec /= 1000;
+                if (unlikely(tz != NULL)) {
+                        /* This relies on gcc inlining the memcpy. We'll notice
+                           if it ever fails to do so. */
+                        memcpy(tz, &gtod->sys_tz, sizeof(struct timezone));
+                }
+                return 0;
+        }
+        asm("syscall" : "=a" (ret) :
+            "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+        return ret;
+}
+int gettimeofday(struct timeval *, struct timezone *)
+        __attribute__((weak, alias("__vdso_gettimeofday")));
diff --git a/arch/x86_64/vdso/vdso-note.S b/arch/x86_64/vdso/vdso-note.S
new file mode 100644
index 000000000000..79a071e4357e
--- /dev/null
+++ b/arch/x86_64/vdso/vdso-note.S
@@ -0,0 +1,12 @@
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/uts.h>
+#include <linux/version.h>
+#include <linux/elfnote.h>
+
+ELFNOTE_START(Linux, 0, "a")
+        .long LINUX_VERSION_CODE
+ELFNOTE_END
diff --git a/arch/x86_64/vdso/vdso-start.S b/arch/x86_64/vdso/vdso-start.S
new file mode 100644
index 000000000000..2dc2cdb84d67
--- /dev/null
+++ b/arch/x86_64/vdso/vdso-start.S
@@ -0,0 +1,2 @@
+        .globl vdso_kernel_start
+vdso_kernel_start:
diff --git a/arch/x86_64/vdso/vdso.S b/arch/x86_64/vdso/vdso.S
new file mode 100644
index 000000000000..92e80c1972a7
--- /dev/null
+++ b/arch/x86_64/vdso/vdso.S
@@ -0,0 +1,2 @@
+        .section ".vdso","a"
+        .incbin "arch/x86_64/vdso/vdso.so"
diff --git a/arch/x86_64/vdso/vdso.lds.S b/arch/x86_64/vdso/vdso.lds.S
new file mode 100644
index 000000000000..b9a60e665d08
--- /dev/null
+++ b/arch/x86_64/vdso/vdso.lds.S
@@ -0,0 +1,77 @@
+/*
+ * Linker script for vsyscall DSO.  The vsyscall page is an ELF shared
+ * object prelinked to its virtual address, and with only one read-only
+ * segment (that fits in one page).  This script controls its layout.
+ */
+#include <asm/asm-offsets.h>
+#include "voffset.h"
+
+#define VDSO_PRELINK 0xffffffffff700000
+
+SECTIONS
+{
+  . = VDSO_PRELINK + SIZEOF_HEADERS;
+
+  .hash           : { *(.hash) }                :text
+  .gnu.hash       : { *(.gnu.hash) }
+  .dynsym         : { *(.dynsym) }
+  .dynstr         : { *(.dynstr) }
+  .gnu.version    : { *(.gnu.version) }
+  .gnu.version_d  : { *(.gnu.version_d) }
+  .gnu.version_r  : { *(.gnu.version_r) }
+
+  /* This linker script is used both with -r and with -shared.
+     For the layouts to match, we need to skip more than enough
+     space for the dynamic symbol table et al.  If this amount
+     is insufficient, ld -shared will barf.  Just increase it here.  */
+  . = VDSO_PRELINK + VDSO_TEXT_OFFSET;
+
+  .text           : { *(.text) }                :text
+  .text.ptr       : { *(.text.ptr) }            :text
+  . = VDSO_PRELINK + 0x900;
+  .data           : { *(.data) }                :text
+  .bss            : { *(.bss) }                 :text
+
+  .altinstructions : { *(.altinstructions) }                    :text
+  .altinstr_replacement  : { *(.altinstr_replacement) } :text
+
+  .note           : { *(.note.*) }              :text :note
+  .eh_frame_hdr   : { *(.eh_frame_hdr) }        :text :eh_frame_hdr
+  .eh_frame       : { KEEP (*(.eh_frame)) }     :text
+  .dynamic        : { *(.dynamic) }             :text :dynamic
+  .useless        : {
+        *(.got.plt) *(.got)
+        *(.gnu.linkonce.d.*)
+        *(.dynbss)
+        *(.gnu.linkonce.b.*)
+  }                                             :text
+}
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+  text PT_LOAD FILEHDR PHDRS FLAGS(5); /* PF_R|PF_X */
+  dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
+  note PT_NOTE FLAGS(4); /* PF_R */
+  eh_frame_hdr 0x6474e550; /* PT_GNU_EH_FRAME, but ld doesn't match the name */
+}
+
+/*
+ * This controls what symbols we export from the DSO.
+ */
+VERSION
+{
+  LINUX_2.6 {
+    global:
+        clock_gettime;
+        __vdso_clock_gettime;
+        gettimeofday;
+        __vdso_gettimeofday;
+        getcpu;
+        __vdso_getcpu;
+    local: *;
+  };
+}
diff --git a/arch/x86_64/vdso/vextern.h b/arch/x86_64/vdso/vextern.h
new file mode 100644
index 000000000000..1683ba2ae3e8
--- /dev/null
+++ b/arch/x86_64/vdso/vextern.h
@@ -0,0 +1,16 @@
+#ifndef VEXTERN
+#include <asm/vsyscall.h>
+#define VEXTERN(x) \
+        extern typeof(x) *vdso_ ## x __attribute__((visibility("hidden")));
+#endif
+
+#define VMAGIC 0xfeedbabeabcdefabUL
+
+/* Any kernel variables used in the vDSO must be exported in the main
+   kernel's vmlinux.lds.S/vsyscall.h/proper __section and
+   put into vextern.h and be referenced as a pointer with vdso prefix.
+   The main kernel later fills in the values.   */
+
+VEXTERN(jiffies)
+VEXTERN(vgetcpu_mode)
+VEXTERN(vsyscall_gtod_data)
diff --git a/arch/x86_64/vdso/vgetcpu.c b/arch/x86_64/vdso/vgetcpu.c
new file mode 100644
index 000000000000..91f6e85d0fc2
--- /dev/null
+++ b/arch/x86_64/vdso/vgetcpu.c
@@ -0,0 +1,50 @@
+/*
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * Subject to the GNU Public License, v.2
+ *
+ * Fast user context implementation of getcpu()
+ */
+
+#include <linux/kernel.h>
+#include <linux/getcpu.h>
+#include <linux/jiffies.h>
+#include <linux/time.h>
+#include <asm/vsyscall.h>
+#include <asm/vgtod.h>
+#include "vextern.h"
+
+long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
+{
+        unsigned int dummy, p;
+        unsigned long j = 0;
+
+        /* Fast cache - only recompute value once per jiffies and avoid
+           relatively costly rdtscp/cpuid otherwise.
+           This works because the scheduler usually keeps the process
+           on the same CPU and this syscall doesn't guarantee its
+           results anyways.
+           We do this here because otherwise user space would do it on
+           its own in a likely inferior way (no access to jiffies).
+           If you don't like it pass NULL. */
+        if (tcache && tcache->blob[0] == (j = *vdso_jiffies)) {
+                p = tcache->blob[1];
+        } else if (*vdso_vgetcpu_mode == VGETCPU_RDTSCP) {
+                /* Load per CPU data from RDTSCP */
+                rdtscp(dummy, dummy, p);
+        } else {
+                /* Load per CPU data from GDT */
+                asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+        }
+        if (tcache) {
+                tcache->blob[0] = j;
+                tcache->blob[1] = p;
+        }
+        if (cpu)
+                *cpu = p & 0xfff;
+        if (node)
+                *node = p >> 12;
+        return 0;
+}
+
+long getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
+        __attribute__((weak, alias("__vdso_getcpu")));
diff --git a/arch/x86_64/vdso/vma.c b/arch/x86_64/vdso/vma.c
new file mode 100644
index 000000000000..d4cb83a6c066
--- /dev/null
+++ b/arch/x86_64/vdso/vma.c
@@ -0,0 +1,139 @@
+/*
+ * Set up the VMAs to tell the VM about the vDSO.
+ * Copyright 2007 Andi Kleen, SUSE Labs.
+ * Subject to the GPL, v.2
+ */
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/random.h>
+#include <asm/vsyscall.h>
+#include <asm/vgtod.h>
+#include <asm/proto.h>
+#include "voffset.h"
+
+int vdso_enabled = 1;
+
+#define VEXTERN(x) extern typeof(__ ## x) *vdso_ ## x;
+#include "vextern.h"
+#undef VEXTERN
+
+extern char vdso_kernel_start[], vdso_start[], vdso_end[];
+extern unsigned short vdso_sync_cpuid;
+
+struct page **vdso_pages;
+
+static inline void *var_ref(void *vbase, char *var, char *name)
+{
+        unsigned offset = var - &vdso_kernel_start[0] + VDSO_TEXT_OFFSET;
+        void *p = vbase + offset;
+        if (*(void **)p != (void *)VMAGIC) {
+                printk("VDSO: variable %s broken\n", name);
+                vdso_enabled = 0;
+        }
+        return p;
+}
+
+static int __init init_vdso_vars(void)
+{
+        int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE;
+        int i;
+        char *vbase;
+
+        vdso_pages = kmalloc(sizeof(struct page *) * npages, GFP_KERNEL);
+        if (!vdso_pages)
+                goto oom;
+        for (i = 0; i < npages; i++) {
+                struct page *p;
+                p = alloc_page(GFP_KERNEL);
+                if (!p)
+                        goto oom;
+                vdso_pages[i] = p;
+                copy_page(page_address(p), vdso_start + i*PAGE_SIZE);
+        }
+
+        vbase = vmap(vdso_pages, npages, 0, PAGE_KERNEL);
+        if (!vbase)
+                goto oom;
+
+        if (memcmp(vbase, "\177ELF", 4)) {
+                printk("VDSO: I'm broken; not ELF\n");
+                vdso_enabled = 0;
+        }
+
+#define V(x) *(typeof(x) *) var_ref(vbase, (char *)RELOC_HIDE(&x, 0), #x)
+#define VEXTERN(x) \
+        V(vdso_ ## x) = &__ ## x;
+#include "vextern.h"
+#undef VEXTERN
+        return 0;
+
+ oom:
+        printk("Cannot allocate vdso\n");
+        vdso_enabled = 0;
+        return -ENOMEM;
+}
+__initcall(init_vdso_vars);
+
+struct linux_binprm;
+
+/* Put the vdso above the (randomized) stack with another randomized offset.
+   This way there is no hole in the middle of address space.
+   To save memory make sure it is still in the same PTE as the stack top.
+   This doesn't give that many random bits */
+static unsigned long vdso_addr(unsigned long start, unsigned len)
+{
+        unsigned long addr, end;
+        unsigned offset;
+        end = (start + PMD_SIZE - 1) & PMD_MASK;
+        if (end >= TASK_SIZE64)
+                end = TASK_SIZE64;
+        end -= len;
+        /* This loses some more bits than a modulo, but is cheaper */
+        offset = get_random_int() & (PTRS_PER_PTE - 1);
+        addr = start + (offset << PAGE_SHIFT);
+        if (addr >= end)
+                addr = end;
+        return addr;
+}
+
+/* Setup a VMA at program startup for the vsyscall page.
+   Not called for compat tasks */
+int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack)
+{
+        struct mm_struct *mm = current->mm;
+        unsigned long addr;
+        int ret;
+        unsigned len = round_up(vdso_end - vdso_start, PAGE_SIZE);
+
+        if (!vdso_enabled)
+                return 0;
+
+        down_write(&mm->mmap_sem);
+        addr = vdso_addr(mm->start_stack, len);
+        addr = get_unmapped_area(NULL, addr, len, 0, 0);
+        if (IS_ERR_VALUE(addr)) {
+                ret = addr;
+                goto up_fail;
+        }
+
+        ret = install_special_mapping(mm, addr, len,
+                                      VM_READ|VM_EXEC|
+                                      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+                                      VM_ALWAYSDUMP,
+                                      vdso_pages);
+        if (ret)
+                goto up_fail;
+
+        current->mm->context.vdso = (void *)addr;
+up_fail:
+        up_write(&mm->mmap_sem);
+        return ret;
+}
+
+static __init int vdso_setup(char *s)
+{
+        vdso_enabled = simple_strtoul(s, NULL, 0);
+        return 0;
+}
+__setup("vdso=", vdso_setup);
diff --git a/arch/x86_64/vdso/voffset.h b/arch/x86_64/vdso/voffset.h
new file mode 100644
index 000000000000..5304204911f2
--- /dev/null
+++ b/arch/x86_64/vdso/voffset.h
@@ -0,0 +1 @@
+#define VDSO_TEXT_OFFSET 0x500
diff --git a/arch/x86_64/vdso/vvar.c b/arch/x86_64/vdso/vvar.c
new file mode 100644
index 000000000000..6fc22219a472
--- /dev/null
+++ b/arch/x86_64/vdso/vvar.c
@@ -0,0 +1,12 @@
+/* Define pointer to external vDSO variables.
+   These are part of the vDSO. The kernel fills in the real addresses
+   at boot time. This is done because when the vdso is linked the
+   kernel isn't yet and we don't know the final addresses. */
+#include <linux/kernel.h>
+#include <linux/time.h>
+#include <asm/vsyscall.h>
+#include <asm/timex.h>
+#include <asm/vgtod.h>
+
+#define VEXTERN(x) typeof (__ ## x) *vdso_ ## x = (void *)VMAGIC;
+#include "vextern.h"