Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc: (144 commits)
  powerpc/44x: Support 16K/64K base page sizes on 44x
  powerpc: Force memory size to be a multiple of PAGE_SIZE
  powerpc/32: Wire up the trampoline code for kdump
  powerpc/32: Add the ability for a classic ppc kernel to be loaded at 32M
  powerpc/32: Allow __ioremap on RAM addresses for kdump kernel
  powerpc/32: Setup OF properties for kdump
  powerpc/32/kdump: Implement crash_setup_regs() using ppc_save_regs()
  powerpc: Prepare xmon_save_regs for use with kdump
  powerpc: Remove default kexec/crash_kernel ops assignments
  powerpc: Make default kexec/crash_kernel ops implicit
  powerpc: Setup OF properties for ppc32 kexec
  powerpc/pseries: Fix cpu hotplug
  powerpc: Fix KVM build on ppc440
  powerpc/cell: add QPACE as a separate Cell platform
  powerpc/cell: fix build breakage with CONFIG_SPUFS disabled
  powerpc/mpc5200: fix error paths in PSC UART probe function
  powerpc/mpc5200: add rts/cts handling in PSC UART driver
  powerpc/mpc5200: Make PSC UART driver update serial errors counters
  powerpc/mpc5200: Remove obsolete code from mpc5200 MDIO driver
  powerpc/mpc5200: Add MDMA/UDMA support to MPC5200 ATA driver
  ...

Fix trivial conflict in drivers/char/Makefile as per Paul's directions

222 files changed, 6151 insertions, 2489 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index adb23ea1c1ef..79f25cef32df 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -285,6 +285,10 @@ config IOMMU_VMERGE
 config IOMMU_HELPER
         def_bool PPC64
 
+config PPC_NEED_DMA_SYNC_OPS
+        def_bool y
+        depends on NOT_COHERENT_CACHE
+
 config HOTPLUG_CPU
         bool "Support for enabling/disabling CPUs"
         depends on SMP && HOTPLUG && EXPERIMENTAL && (PPC_PSERIES || PPC_PMAC)
@@ -322,7 +326,7 @@ config KEXEC
 
 config CRASH_DUMP
         bool "Build a kdump crash kernel"
-        depends on PPC_MULTIPLATFORM && PPC64 && RELOCATABLE
+        depends on (PPC64 && RELOCATABLE) || 6xx
         help
           Build a kernel suitable for use as a kdump capture kernel.
           The same kernel binary can be used as production kernel and dump
@@ -401,23 +405,53 @@ config PPC_HAS_HASH_64K
         depends on PPC64
         default n
 
-config PPC_64K_PAGES
-        bool "64k page size"
-        depends on PPC64
-        select PPC_HAS_HASH_64K
+choice
+        prompt "Page size"
+        default PPC_4K_PAGES
         help
-          This option changes the kernel logical page size to 64k. On machines
-          without processor support for 64k pages, the kernel will simulate
-          them by loading each individual 4k page on demand transparently,
-          while on hardware with such support, it will be used to map
-          normal application pages.
+          Select the kernel logical page size. Increasing the page size
+          will reduce software overhead at each page boundary, allow
+          hardware prefetch mechanisms to be more effective, and allow
+          larger dma transfers increasing IO efficiency and reducing
+          overhead. However the utilization of memory will increase.
+          For example, each cached file will using a multiple of the
+          page size to hold its contents and the difference between the
+          end of file and the end of page is wasted.
+
+          Some dedicated systems, such as software raid serving with
+          accelerated calculations, have shown significant increases.
+
+          If you configure a 64 bit kernel for 64k pages but the
+          processor does not support them, then the kernel will simulate
+          them with 4k pages, loading them on demand, but with the
+          reduced software overhead and larger internal fragmentation.
+          For the 32 bit kernel, a large page option will not be offered
+          unless it is supported by the configured processor.
+
+          If unsure, choose 4K_PAGES.
+
+config PPC_4K_PAGES
+        bool "4k page size"
+
+config PPC_16K_PAGES
+        bool "16k page size" if 44x
+
+config PPC_64K_PAGES
+        bool "64k page size" if 44x || PPC_STD_MMU_64
+        select PPC_HAS_HASH_64K if PPC_STD_MMU_64
+
+endchoice
 
 config FORCE_MAX_ZONEORDER
         int "Maximum zone order"
-        range 9 64 if PPC_64K_PAGES
-        default "9" if PPC_64K_PAGES
-        range 13 64 if PPC64 && !PPC_64K_PAGES
-        default "13" if PPC64 && !PPC_64K_PAGES
+        range 9 64 if PPC_STD_MMU_64 && PPC_64K_PAGES
+        default "9" if PPC_STD_MMU_64 && PPC_64K_PAGES
+        range 13 64 if PPC_STD_MMU_64 && !PPC_64K_PAGES
+        default "13" if PPC_STD_MMU_64 && !PPC_64K_PAGES
+        range 9 64 if PPC_STD_MMU_32 && PPC_16K_PAGES
+        default "9" if PPC_STD_MMU_32 && PPC_16K_PAGES
+        range 7 64 if PPC_STD_MMU_32 && PPC_64K_PAGES
+        default "7" if PPC_STD_MMU_32 && PPC_64K_PAGES
         range 11 64
         default "11"
         help
@@ -437,7 +471,7 @@ config FORCE_MAX_ZONEORDER
 
 config PPC_SUBPAGE_PROT
         bool "Support setting protections for 4k subpages"
-        depends on PPC_64K_PAGES
+        depends on PPC_STD_MMU_64 && PPC_64K_PAGES
         help
           This option adds support for a system call to allow user programs
           to set access permissions (read/write, readonly, or no access)
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 15eb27861fc7..08f7cc0a1953 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -2,6 +2,15 @@ menu "Kernel hacking"
 
 source "lib/Kconfig.debug"
 
+config PRINT_STACK_DEPTH
+        int "Stack depth to print" if DEBUG_KERNEL
+        default 64
+        help
+          This option allows you to set the stack depth that the kernel
+          prints in stack traces. This can be useful if your display is
+          too small and stack traces cause important information to
+          scroll off the screen.
+
 config DEBUG_STACKOVERFLOW
         bool "Check for stack overflows"
         depends on DEBUG_KERNEL
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 1f0667069940..72d17f50e54f 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -107,7 +107,6 @@ KBUILD_CFLAGS += $(call cc-option,-mno-altivec)
 # (We use all available options to help semi-broken compilers)
 KBUILD_CFLAGS += $(call cc-option,-mno-spe)
 KBUILD_CFLAGS += $(call cc-option,-mspe=no)
-KBUILD_CFLAGS += $(call cc-option,-mabi=no-spe)
 
 # Enable unit-at-a-time mode when possible. It shrinks the
 # kernel considerably.
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 3d3daa674299..f32829937aad 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -194,6 +194,7 @@ image-$(CONFIG_PPC_MAPLE)		+= zImage.pseries
 image-$(CONFIG_PPC_IBM_CELL_BLADE)      += zImage.pseries
 image-$(CONFIG_PPC_PS3)                 += dtbImage.ps3
 image-$(CONFIG_PPC_CELLEB)              += zImage.pseries
+image-$(CONFIG_PPC_CELL_QPACE)          += zImage.pseries
 image-$(CONFIG_PPC_CHRP)                += zImage.chrp
 image-$(CONFIG_PPC_EFIKA)               += zImage.chrp
 image-$(CONFIG_PPC_PMAC)                += zImage.pmac
diff --git a/arch/powerpc/boot/devtree.c b/arch/powerpc/boot/devtree.c
index 5d12336dc360..a7e21a35c03a 100644
--- a/arch/powerpc/boot/devtree.c
+++ b/arch/powerpc/boot/devtree.c
@@ -213,7 +213,7 @@ static int find_range(u32 *reg, u32 *ranges, int nregaddr,
                 u32 range_addr[MAX_ADDR_CELLS];
                 u32 range_size[MAX_ADDR_CELLS];
 
-                copy_val(range_addr, ranges + i, naddr);
+                copy_val(range_addr, ranges + i, nregaddr);
                 copy_val(range_size, ranges + i + nregaddr + naddr, nsize);
 
                 if (compare_reg(reg, range_addr, range_size))
diff --git a/arch/powerpc/boot/dts/bamboo.dts b/arch/powerpc/boot/dts/bamboo.dts
index 6ce0cc2c0208..aa68911f6560 100644
--- a/arch/powerpc/boot/dts/bamboo.dts
+++ b/arch/powerpc/boot/dts/bamboo.dts
@@ -269,7 +269,8 @@
                          * later cannot be changed. Chip supports a second
                          * IO range but we don't use it for now
                          */
-                        ranges = <0x02000000 0x00000000 0xa0000000 0x00000000 0xa0000000 0x00000000 0x20000000
+                        ranges = <0x02000000 0x00000000 0xa0000000 0x00000000 0xa0000000 0x00000000 0x40000000
+                                  0x02000000 0x00000000 0x00000000 0x00000000 0xe0000000 0x00000000 0x00100000
                                   0x01000000 0x00000000 0x00000000 0x00000000 0xe8000000 0x00000000 0x00010000>;
 
                         /* Inbound 2GB range starting at 0 */
diff --git a/arch/powerpc/boot/dts/canyonlands.dts b/arch/powerpc/boot/dts/canyonlands.dts
index 79fe412c11c9..8b5ba8261a36 100644
--- a/arch/powerpc/boot/dts/canyonlands.dts
+++ b/arch/powerpc/boot/dts/canyonlands.dts
@@ -40,6 +40,7 @@
                         d-cache-size = <32768>;
                         dcr-controller;
                         dcr-access-method = "native";
+                        next-level-cache = <&L2C0>;
                 };
         };
 
@@ -104,6 +105,16 @@
                 dcr-reg = <0x00c 0x002>;
         };
 
+        L2C0: l2c {
+                compatible = "ibm,l2-cache-460ex", "ibm,l2-cache";
+                dcr-reg = <0x020 0x008          /* Internal SRAM DCR's */
+                           0x030 0x008>;        /* L2 cache DCR's */
+                cache-line-size = <32>;         /* 32 bytes */
+                cache-size = <262144>;          /* L2, 256K */
+                interrupt-parent = <&UIC1>;
+                interrupts = <11 1>;
+        };
+
         plb {
                 compatible = "ibm,plb-460ex", "ibm,plb4";
                 #address-cells = <2>;
@@ -343,6 +354,7 @@
                          * later cannot be changed
                          */
                         ranges = <0x02000000 0x00000000 0x80000000 0x0000000d 0x80000000 0x00000000 0x80000000
+                                  0x02000000 0x00000000 0x00000000 0x0000000c 0x0ee00000 0x00000000 0x00100000
                                   0x01000000 0x00000000 0x00000000 0x0000000c 0x08000000 0x00000000 0x00010000>;
 
                         /* Inbound 2GB range starting at 0 */
@@ -373,6 +385,7 @@
                          * later cannot be changed
                          */
                         ranges = <0x02000000 0x00000000 0x80000000 0x0000000e 0x00000000 0x00000000 0x80000000
+                                  0x02000000 0x00000000 0x00000000 0x0000000f 0x00000000 0x00000000 0x00100000
                                   0x01000000 0x00000000 0x00000000 0x0000000f 0x80000000 0x00000000 0x00010000>;
 
                         /* Inbound 2GB range starting at 0 */
@@ -414,6 +427,7 @@
                          * later cannot be changed
                          */
                         ranges = <0x02000000 0x00000000 0x80000000 0x0000000e 0x80000000 0x00000000 0x80000000
+                                  0x02000000 0x00000000 0x00000000 0x0000000f 0x00100000 0x00000000 0x00100000
                                   0x01000000 0x00000000 0x00000000 0x0000000f 0x80010000 0x00000000 0x00010000>;
 
                         /* Inbound 2GB range starting at 0 */
diff --git a/arch/powerpc/boot/dts/gef_sbc610.dts b/arch/powerpc/boot/dts/gef_sbc610.dts
index e48cfa740c8a..9708b3423bbd 100644
--- a/arch/powerpc/boot/dts/gef_sbc610.dts
+++ b/arch/powerpc/boot/dts/gef_sbc610.dts
@@ -98,6 +98,12 @@
                         interrupt-parent = <&mpic>;
 
                 };
+                gef_gpio: gpio@7,14000 {
+                        #gpio-cells = <2>;
+                        compatible = "gef,sbc610-gpio";
+                        reg = <0x7 0x14000 0x24>;
+                        gpio-controller;
+                };
         };
 
         soc@fef00000 {
@@ -119,6 +125,11 @@
                         interrupt-parent = <&mpic>;
                         dfsrr;
 
+                        rtc@51 {
+                                compatible = "epson,rx8581";
+                                reg = <0x00000051>;
+                        };
+
                         eti@6b {
                                 compatible = "dallas,ds1682";
                                 reg = <0x6b>;
diff --git a/arch/powerpc/boot/dts/kuroboxHD.dts b/arch/powerpc/boot/dts/kuroboxHD.dts
index 2e5a1a1812b6..8d725d10882f 100644
--- a/arch/powerpc/boot/dts/kuroboxHD.dts
+++ b/arch/powerpc/boot/dts/kuroboxHD.dts
@@ -76,7 +76,6 @@ XXXX add flash parts, rtc, ??
                         interrupt-parent = <&mpic>;
 
                         rtc@32 {
-                                device_type = "rtc";
                                 compatible = "ricoh,rs5c372a";
                                 reg = <0x32>;
                         };
diff --git a/arch/powerpc/boot/dts/kuroboxHG.dts b/arch/powerpc/boot/dts/kuroboxHG.dts
index e4916e69ad31..b13a11eb81b0 100644
--- a/arch/powerpc/boot/dts/kuroboxHG.dts
+++ b/arch/powerpc/boot/dts/kuroboxHG.dts
@@ -76,7 +76,6 @@ XXXX add flash parts, rtc, ??
                         interrupt-parent = <&mpic>;
 
                         rtc@32 {
-                                device_type = "rtc";
                                 compatible = "ricoh,rs5c372a";
                                 reg = <0x32>;
                         };
diff --git a/arch/powerpc/boot/dts/lite5200.dts b/arch/powerpc/boot/dts/lite5200.dts
index 2cf9a8768f44..3f7a5dce8de0 100644
--- a/arch/powerpc/boot/dts/lite5200.dts
+++ b/arch/powerpc/boot/dts/lite5200.dts
@@ -130,7 +130,6 @@
 
                 rtc@800 {       // Real time clock
                         compatible = "fsl,mpc5200-rtc";
-                        device_type = "rtc";
                         reg = <0x800 0x100>;
                         interrupts = <1 5 0 1 6 0>;
                         interrupt-parent = <&mpc5200_pic>;
diff --git a/arch/powerpc/boot/dts/lite5200b.dts b/arch/powerpc/boot/dts/lite5200b.dts
index 7bd5b9c399b8..63e3bb48e843 100644
--- a/arch/powerpc/boot/dts/lite5200b.dts
+++ b/arch/powerpc/boot/dts/lite5200b.dts
@@ -130,7 +130,6 @@
 
                 rtc@800 {       // Real time clock
                         compatible = "fsl,mpc5200b-rtc","fsl,mpc5200-rtc";
-                        device_type = "rtc";
                         reg = <0x800 0x100>;
                         interrupts = <1 5 0 1 6 0>;
                         interrupt-parent = <&mpc5200_pic>;
diff --git a/arch/powerpc/boot/dts/motionpro.dts b/arch/powerpc/boot/dts/motionpro.dts
index 9e3c921be164..52ba6f98b273 100644
--- a/arch/powerpc/boot/dts/motionpro.dts
+++ b/arch/powerpc/boot/dts/motionpro.dts
@@ -248,7 +248,6 @@
                         fsl5200-clocking;
 
                         rtc@68 {
-                                device_type = "rtc";
                                 compatible = "dallas,ds1339";
                                 reg = <0x68>;
                         };
diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index d2cdd47a246d..072c9b0f8c8e 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -117,7 +117,6 @@
                         interrupt-parent = <&ipic>;
                         dfsrr;
                         rtc@68 {
-                                device_type = "rtc";
                                 compatible = "dallas,ds1339";
                                 reg = <0x68>;
                         };
diff --git a/arch/powerpc/boot/dts/mpc8349emitx.dts b/arch/powerpc/boot/dts/mpc8349emitx.dts
index 712783d0707e..b5eda94a8e2a 100644
--- a/arch/powerpc/boot/dts/mpc8349emitx.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitx.dts
@@ -85,7 +85,6 @@
                         dfsrr;
 
                         rtc@68 {
-                                device_type = "rtc";
                                 compatible = "dallas,ds1339";
                                 reg = <0x68>;
                                 interrupts = <18 0x8>;
diff --git a/arch/powerpc/boot/dts/mpc8349emitxgp.dts b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
index 3e918af41fb1..c87a6015e165 100644
--- a/arch/powerpc/boot/dts/mpc8349emitxgp.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
@@ -83,7 +83,6 @@
                         dfsrr;
 
                         rtc@68 {
-                                device_type = "rtc";
                                 compatible = "dallas,ds1339";
                                 reg = <0x68>;
                                 interrupts = <18 0x8>;
diff --git a/arch/powerpc/boot/dts/mpc8377_rdb.dts b/arch/powerpc/boot/dts/mpc8377_rdb.dts
index 31f348fdfe14..9413af3b9925 100644
--- a/arch/powerpc/boot/dts/mpc8377_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8377_rdb.dts
@@ -117,7 +117,6 @@
                         interrupt-parent = <&ipic>;
                         dfsrr;
                         rtc@68 {
-                                device_type = "rtc";
                                 compatible = "dallas,ds1339";
                                 reg = <0x68>;
                         };
diff --git a/arch/powerpc/boot/dts/mpc8378_rdb.dts b/arch/powerpc/boot/dts/mpc8378_rdb.dts
index 7a2bad038bd6..23c10ce22c2c 100644
--- a/arch/powerpc/boot/dts/mpc8378_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8378_rdb.dts
@@ -117,7 +117,6 @@
                         interrupt-parent = <&ipic>;
                         dfsrr;
                         rtc@68 {
-                                device_type = "rtc";
                                 compatible = "dallas,ds1339";
                                 reg = <0x68>;
                         };
diff --git a/arch/powerpc/boot/dts/mpc8379_rdb.dts b/arch/powerpc/boot/dts/mpc8379_rdb.dts
index e067616f3f42..72cdc3c4c7e3 100644
--- a/arch/powerpc/boot/dts/mpc8379_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8379_rdb.dts
@@ -117,7 +117,6 @@
                         interrupt-parent = <&ipic>;
                         dfsrr;
                         rtc@68 {
-                                device_type = "rtc";
                                 compatible = "dallas,ds1339";
                                 reg = <0x68>;
                         };
diff --git a/arch/powerpc/boot/dts/mpc8572ds.dts b/arch/powerpc/boot/dts/mpc8572ds.dts
index 05f67253b49f..21459e161d02 100644
--- a/arch/powerpc/boot/dts/mpc8572ds.dts
+++ b/arch/powerpc/boot/dts/mpc8572ds.dts
@@ -63,6 +63,119 @@
                 device_type = "memory";
         };
 
+        localbus@ffe05000 {
+                #address-cells = <2>;
+                #size-cells = <1>;
+                compatible = "fsl,mpc8572-elbc", "fsl,elbc", "simple-bus";
+                reg = <0 0xffe05000 0 0x1000>;
+                interrupts = <19 2>;
+                interrupt-parent = <&mpic>;
+
+                ranges = <0x0 0x0 0x0 0xe8000000 0x08000000
+                          0x1 0x0 0x0 0xe0000000 0x08000000
+                          0x2 0x0 0x0 0xffa00000 0x00040000
+                          0x3 0x0 0x0 0xffdf0000 0x00008000
+                          0x4 0x0 0x0 0xffa40000 0x00040000
+                          0x5 0x0 0x0 0xffa80000 0x00040000
+                          0x6 0x0 0x0 0xffac0000 0x00040000>;
+
+                nor@0,0 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "cfi-flash";
+                        reg = <0x0 0x0 0x8000000>;
+                        bank-width = <2>;
+                        device-width = <1>;
+
+                        ramdisk@0 {
+                                reg = <0x0 0x03000000>;
+                                readl-only;
+                        };
+
+                        diagnostic@3000000 {
+                                reg = <0x03000000 0x00e00000>;
+                                read-only;
+                        };
+
+                        dink@3e00000 {
+                                reg = <0x03e00000 0x00200000>;
+                                read-only;
+                        };
+
+                        kernel@4000000 {
+                                reg = <0x04000000 0x00400000>;
+                                read-only;
+                        };
+
+                        jffs2@4400000 {
+                                reg = <0x04400000 0x03b00000>;
+                        };
+
+                        dtb@7f00000 {
+                                reg = <0x07f00000 0x00080000>;
+                                read-only;
+                        };
+
+                        u-boot@7f80000 {
+                                reg = <0x07f80000 0x00080000>;
+                                read-only;
+                        };
+                };
+
+                nand@2,0 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "fsl,mpc8572-fcm-nand",
+                                     "fsl,elbc-fcm-nand";
+                        reg = <0x2 0x0 0x40000>;
+
+                        u-boot@0 {
+                                reg = <0x0 0x02000000>;
+                                read-only;
+                        };
+
+                        jffs2@2000000 {
+                                reg = <0x02000000 0x10000000>;
+                        };
+
+                        ramdisk@12000000 {
+                                reg = <0x12000000 0x08000000>;
+                                read-only;
+                        };
+
+                        kernel@1a000000 {
+                                reg = <0x1a000000 0x04000000>;
+                        };
+
+                        dtb@1e000000 {
+                                reg = <0x1e000000 0x01000000>;
+                                read-only;
+                        };
+
+                        empty@1f000000 {
+                                reg = <0x1f000000 0x21000000>;
+                        };
+                };
+
+                nand@4,0 {
+                        compatible = "fsl,mpc8572-fcm-nand",
+                                     "fsl,elbc-fcm-nand";
+                        reg = <0x4 0x0 0x40000>;
+                };
+
+                nand@5,0 {
+                        compatible = "fsl,mpc8572-fcm-nand",
+                                     "fsl,elbc-fcm-nand";
+                        reg = <0x5 0x0 0x40000>;
+                };
+
+                nand@6,0 {
+                        compatible = "fsl,mpc8572-fcm-nand",
+                                     "fsl,elbc-fcm-nand";
+                        reg = <0x6 0x0 0x40000>;
+                };
+        };
+
         soc8572@ffe00000 {
                 #address-cells = <1>;
                 #size-cells = <1>;
diff --git a/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts b/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts
new file mode 100644
index 000000000000..c114c4ee9931
--- /dev/null
+++ b/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts
@@ -0,0 +1,483 @@
+/*
+ * MPC8572 DS Core0 Device Tree Source in CAMP mode.
+ *
+ * In CAMP mode, each core needs to have its own dts. Only mpic and L2 cache
+ * can be shared, all the other devices must be assigned to one core only.
+ * This dts file allows core0 to have memory, l2, i2c, dma1, global-util, eth0,
+ * eth1, crypto, pci0, pci1.
+ *
+ * Copyright 2007, 2008 Freescale Semiconductor Inc.
+ *
+ * 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.
+ */
+
+/dts-v1/;
+/ {
+        model = "fsl,MPC8572DS";
+        compatible = "fsl,MPC8572DS", "fsl,MPC8572DS-CAMP";
+        #address-cells = <1>;
+        #size-cells = <1>;
+
+        aliases {
+                ethernet0 = &enet0;
+                ethernet1 = &enet1;
+                serial0 = &serial0;
+                pci0 = &pci0;
+                pci1 = &pci1;
+        };
+
+        cpus {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                PowerPC,8572@0 {
+                        device_type = "cpu";
+                        reg = <0x0>;
+                        d-cache-line-size = <32>;       // 32 bytes
+                        i-cache-line-size = <32>;       // 32 bytes
+                        d-cache-size = <0x8000>;                // L1, 32K
+                        i-cache-size = <0x8000>;                // L1, 32K
+                        timebase-frequency = <0>;
+                        bus-frequency = <0>;
+                        clock-frequency = <0>;
+                        next-level-cache = <&L2>;
+                };
+
+        };
+
+        memory {
+                device_type = "memory";
+                reg = <0x0 0x0>;        // Filled by U-Boot
+        };
+
+        soc8572@ffe00000 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                device_type = "soc";
+                compatible = "simple-bus";
+                ranges = <0x0 0xffe00000 0x100000>;
+                reg = <0xffe00000 0x1000>;      // CCSRBAR & soc regs, remove once parse code for immrbase fixed
+                bus-frequency = <0>;            // Filled out by uboot.
+
+                memory-controller@2000 {
+                        compatible = "fsl,mpc8572-memory-controller";
+                        reg = <0x2000 0x1000>;
+                        interrupt-parent = <&mpic>;
+                        interrupts = <18 2>;
+                };
+
+                memory-controller@6000 {
+                        compatible = "fsl,mpc8572-memory-controller";
+                        reg = <0x6000 0x1000>;
+                        interrupt-parent = <&mpic>;
+                        interrupts = <18 2>;
+                };
+
+                L2: l2-cache-controller@20000 {
+                        compatible = "fsl,mpc8572-l2-cache-controller";
+                        reg = <0x20000 0x1000>;
+                        cache-line-size = <32>; // 32 bytes
+                        cache-size = <0x80000>; // L2, 512K
+                        interrupt-parent = <&mpic>;
+                        interrupts = <16 2>;
+                };
+
+                i2c@3000 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        cell-index = <0>;
+                        compatible = "fsl-i2c";
+                        reg = <0x3000 0x100>;
+                        interrupts = <43 2>;
+                        interrupt-parent = <&mpic>;
+                        dfsrr;
+                };
+
+                i2c@3100 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        cell-index = <1>;
+                        compatible = "fsl-i2c";
+                        reg = <0x3100 0x100>;
+                        interrupts = <43 2>;
+                        interrupt-parent = <&mpic>;
+                        dfsrr;
+                };
+
+                dma@21300 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "fsl,mpc8572-dma", "fsl,eloplus-dma";
+                        reg = <0x21300 0x4>;
+                        ranges = <0x0 0x21100 0x200>;
+                        cell-index = <0>;
+                        dma-channel@0 {
+                                compatible = "fsl,mpc8572-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x0 0x80>;
+                                cell-index = <0>;
+                                interrupt-parent = <&mpic>;
+                                interrupts = <20 2>;
+                        };
+                        dma-channel@80 {
+                                compatible = "fsl,mpc8572-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x80 0x80>;
+                                cell-index = <1>;
+                                interrupt-parent = <&mpic>;
+                                interrupts = <21 2>;
+                        };
+                        dma-channel@100 {
+                                compatible = "fsl,mpc8572-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x100 0x80>;
+                                cell-index = <2>;
+                                interrupt-parent = <&mpic>;
+                                interrupts = <22 2>;
+                        };
+                        dma-channel@180 {
+                                compatible = "fsl,mpc8572-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x180 0x80>;
+                                cell-index = <3>;
+                                interrupt-parent = <&mpic>;
+                                interrupts = <23 2>;
+                        };
+                };
+
+                mdio@24520 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        compatible = "fsl,gianfar-mdio";
+                        reg = <0x24520 0x20>;
+
+                        phy0: ethernet-phy@0 {
+                                interrupt-parent = <&mpic>;
+                                interrupts = <10 1>;
+                                reg = <0x0>;
+                        };
+                        phy1: ethernet-phy@1 {
+                                interrupt-parent = <&mpic>;
+                                interrupts = <10 1>;
+                                reg = <0x1>;
+                        };
+                };
+
+                enet0: ethernet@24000 {
+                        cell-index = <0>;
+                        device_type = "network";
+                        model = "eTSEC";
+                        compatible = "gianfar";
+                        reg = <0x24000 0x1000>;
+                        local-mac-address = [ 00 00 00 00 00 00 ];
+                        interrupts = <29 2 30 2 34 2>;
+                        interrupt-parent = <&mpic>;
+                        phy-handle = <&phy0>;
+                        phy-connection-type = "rgmii-id";
+                };
+
+                enet1: ethernet@25000 {
+                        cell-index = <1>;
+                        device_type = "network";
+                        model = "eTSEC";
+                        compatible = "gianfar";
+                        reg = <0x25000 0x1000>;
+                        local-mac-address = [ 00 00 00 00 00 00 ];
+                        interrupts = <35 2 36 2 40 2>;
+                        interrupt-parent = <&mpic>;
+                        phy-handle = <&phy1>;
+                        phy-connection-type = "rgmii-id";
+                };
+
+                serial0: serial@4500 {
+                        cell-index = <0>;
+                        device_type = "serial";
+                        compatible = "ns16550";
+                        reg = <0x4500 0x100>;
+                        clock-frequency = <0>;
+                };
+
+                global-utilities@e0000 {        //global utilities block
+                        compatible = "fsl,mpc8572-guts";
+                        reg = <0xe0000 0x1000>;
+                        fsl,has-rstcr;
+                };
+
+                crypto@30000 {
+                        compatible = "fsl,sec3.0", "fsl,sec2.4", "fsl,sec2.2",
+                                     "fsl,sec2.1", "fsl,sec2.0";
+                        reg = <0x30000 0x10000>;
+                        interrupts = <45 2 58 2>;
+                        interrupt-parent = <&mpic>;
+                        fsl,num-channels = <4>;
+                        fsl,channel-fifo-len = <24>;
+                        fsl,exec-units-mask = <0x9fe>;
+                        fsl,descriptor-types-mask = <0x3ab0ebf>;
+                };
+
+                mpic: pic@40000 {
+                        interrupt-controller;
+                        #address-cells = <0>;
+                        #interrupt-cells = <2>;
+                        reg = <0x40000 0x40000>;
+                        compatible = "chrp,open-pic";
+                        device_type = "open-pic";
+                        protected-sources = <
+                        31 32 33 37 38 39       /* enet2 enet3 */
+                        76 77 78 79 27 42       /* dma2 pci2 serial*/
+                        0xe0 0xe1 0xe2 0xe3     /* msi */
+                        0xe4 0xe5 0xe6 0xe7
+                        >;
+                };
+        };
+
+        pci0: pcie@ffe08000 {
+                cell-index = <0>;
+                compatible = "fsl,mpc8548-pcie";
+                device_type = "pci";
+                #interrupt-cells = <1>;
+                #size-cells = <2>;
+                #address-cells = <3>;
+                reg = <0xffe08000 0x1000>;
+                bus-range = <0 255>;
+                ranges = <0x2000000 0x0 0x80000000 0x80000000 0x0 0x20000000
+                          0x1000000 0x0 0x0 0xffc00000 0x0 0x10000>;
+                clock-frequency = <33333333>;
+                interrupt-parent = <&mpic>;
+                interrupts = <24 2>;
+                interrupt-map-mask = <0xff00 0x0 0x0 0x7>;
+                interrupt-map = <
+                        /* IDSEL 0x11 func 0 - PCI slot 1 */
+                        0x8800 0x0 0x0 0x1 &mpic 0x2 0x1
+                        0x8800 0x0 0x0 0x2 &mpic 0x3 0x1
+                        0x8800 0x0 0x0 0x3 &mpic 0x4 0x1
+                        0x8800 0x0 0x0 0x4 &mpic 0x1 0x1
+
+                        /* IDSEL 0x11 func 1 - PCI slot 1 */
+                        0x8900 0x0 0x0 0x1 &mpic 0x2 0x1
+                        0x8900 0x0 0x0 0x2 &mpic 0x3 0x1
+                        0x8900 0x0 0x0 0x3 &mpic 0x4 0x1
+                        0x8900 0x0 0x0 0x4 &mpic 0x1 0x1
+
+                        /* IDSEL 0x11 func 2 - PCI slot 1 */
+                        0x8a00 0x0 0x0 0x1 &mpic 0x2 0x1
+                        0x8a00 0x0 0x0 0x2 &mpic 0x3 0x1
+                        0x8a00 0x0 0x0 0x3 &mpic 0x4 0x1
+                        0x8a00 0x0 0x0 0x4 &mpic 0x1 0x1
+
+                        /* IDSEL 0x11 func 3 - PCI slot 1 */
+                        0x8b00 0x0 0x0 0x1 &mpic 0x2 0x1
+                        0x8b00 0x0 0x0 0x2 &mpic 0x3 0x1
+                        0x8b00 0x0 0x0 0x3 &mpic 0x4 0x1
+                        0x8b00 0x0 0x0 0x4 &mpic 0x1 0x1
+
+                        /* IDSEL 0x11 func 4 - PCI slot 1 */
+                        0x8c00 0x0 0x0 0x1 &mpic 0x2 0x1
+                        0x8c00 0x0 0x0 0x2 &mpic 0x3 0x1
+                        0x8c00 0x0 0x0 0x3 &mpic 0x4 0x1
+                        0x8c00 0x0 0x0 0x4 &mpic 0x1 0x1
+
+                        /* IDSEL 0x11 func 5 - PCI slot 1 */
+                        0x8d00 0x0 0x0 0x1 &mpic 0x2 0x1
+                        0x8d00 0x0 0x0 0x2 &mpic 0x3 0x1
+                        0x8d00 0x0 0x0 0x3 &mpic 0x4 0x1
+                        0x8d00 0x0 0x0 0x4 &mpic 0x1 0x1
+
+                        /* IDSEL 0x11 func 6 - PCI slot 1 */
+                        0x8e00 0x0 0x0 0x1 &mpic 0x2 0x1
+                        0x8e00 0x0 0x0 0x2 &mpic 0x3 0x1
+                        0x8e00 0x0 0x0 0x3 &mpic 0x4 0x1
+                        0x8e00 0x0 0x0 0x4 &mpic 0x1 0x1
+
+                        /* IDSEL 0x11 func 7 - PCI slot 1 */
+                        0x8f00 0x0 0x0 0x1 &mpic 0x2 0x1
+                        0x8f00 0x0 0x0 0x2 &mpic 0x3 0x1
+                        0x8f00 0x0 0x0 0x3 &mpic 0x4 0x1
+                        0x8f00 0x0 0x0 0x4 &mpic 0x1 0x1
+
+                        /* IDSEL 0x12 func 0 - PCI slot 2 */
+                        0x9000 0x0 0x0 0x1 &mpic 0x3 0x1
+                        0x9000 0x0 0x0 0x2 &mpic 0x4 0x1
+                        0x9000 0x0 0x0 0x3 &mpic 0x1 0x1
+                        0x9000 0x0 0x0 0x4 &mpic 0x2 0x1
+
+                        /* IDSEL 0x12 func 1 - PCI slot 2 */
+                        0x9100 0x0 0x0 0x1 &mpic 0x3 0x1
+                        0x9100 0x0 0x0 0x2 &mpic 0x4 0x1
+                        0x9100 0x0 0x0 0x3 &mpic 0x1 0x1
+                        0x9100 0x0 0x0 0x4 &mpic 0x2 0x1
+
+                        /* IDSEL 0x12 func 2 - PCI slot 2 */
+                        0x9200 0x0 0x0 0x1 &mpic 0x3 0x1
+                        0x9200 0x0 0x0 0x2 &mpic 0x4 0x1
+                        0x9200 0x0 0x0 0x3 &mpic 0x1 0x1
+                        0x9200 0x0 0x0 0x4 &mpic 0x2 0x1
+
+                        /* IDSEL 0x12 func 3 - PCI slot 2 */
+                        0x9300 0x0 0x0 0x1 &mpic 0x3 0x1
+                        0x9300 0x0 0x0 0x2 &mpic 0x4 0x1
+                        0x9300 0x0 0x0 0x3 &mpic 0x1 0x1
+                        0x9300 0x0 0x0 0x4 &mpic 0x2 0x1
+
+                        /* IDSEL 0x12 func 4 - PCI slot 2 */
+                        0x9400 0x0 0x0 0x1 &mpic 0x3 0x1
+                        0x9400 0x0 0x0 0x2 &mpic 0x4 0x1
+                        0x9400 0x0 0x0 0x3 &mpic 0x1 0x1
+                        0x9400 0x0 0x0 0x4 &mpic 0x2 0x1
+
+                        /* IDSEL 0x12 func 5 - PCI slot 2 */
+                        0x9500 0x0 0x0 0x1 &mpic 0x3 0x1
+                        0x9500 0x0 0x0 0x2 &mpic 0x4 0x1
+                        0x9500 0x0 0x0 0x3 &mpic 0x1 0x1
+                        0x9500 0x0 0x0 0x4 &mpic 0x2 0x1
+
+                        /* IDSEL 0x12 func 6 - PCI slot 2 */
+                        0x9600 0x0 0x0 0x1 &mpic 0x3 0x1
+                        0x9600 0x0 0x0 0x2 &mpic 0x4 0x1
+                        0x9600 0x0 0x0 0x3 &mpic 0x1 0x1
+                        0x9600 0x0 0x0 0x4 &mpic 0x2 0x1
+
+                        /* IDSEL 0x12 func 7 - PCI slot 2 */
+                        0x9700 0x0 0x0 0x1 &mpic 0x3 0x1
+                        0x9700 0x0 0x0 0x2 &mpic 0x4 0x1
+                        0x9700 0x0 0x0 0x3 &mpic 0x1 0x1
+                        0x9700 0x0 0x0 0x4 &mpic 0x2 0x1
+
+                        // IDSEL 0x1c  USB
+                        0xe000 0x0 0x0 0x1 &i8259 0xc 0x2
+                        0xe100 0x0 0x0 0x2 &i8259 0x9 0x2
+                        0xe200 0x0 0x0 0x3 &i8259 0xa 0x2
+                        0xe300 0x0 0x0 0x4 &i8259 0xb 0x2
+
+                        // IDSEL 0x1d  Audio
+                        0xe800 0x0 0x0 0x1 &i8259 0x6 0x2
+
+                        // IDSEL 0x1e Legacy
+                        0xf000 0x0 0x0 0x1 &i8259 0x7 0x2
+                        0xf100 0x0 0x0 0x1 &i8259 0x7 0x2
+
+                        // IDSEL 0x1f IDE/SATA
+                        0xf800 0x0 0x0 0x1 &i8259 0xe 0x2
+                        0xf900 0x0 0x0 0x1 &i8259 0x5 0x2
+
+                        >;
+
+                pcie@0 {
+                        reg = <0x0 0x0 0x0 0x0 0x0>;
+                        #size-cells = <2>;
+                        #address-cells = <3>;
+                        device_type = "pci";
+                        ranges = <0x2000000 0x0 0x80000000
+                                  0x2000000 0x0 0x80000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                        uli1575@0 {
+                                reg = <0x0 0x0 0x0 0x0 0x0>;
+                                #size-cells = <2>;
+                                #address-cells = <3>;
+                                ranges = <0x2000000 0x0 0x80000000
+                                          0x2000000 0x0 0x80000000
+                                          0x0 0x20000000
+
+                                          0x1000000 0x0 0x0
+                                          0x1000000 0x0 0x0
+                                          0x0 0x100000>;
+                                isa@1e {
+                                        device_type = "isa";
+                                        #interrupt-cells = <2>;
+                                        #size-cells = <1>;
+                                        #address-cells = <2>;
+                                        reg = <0xf000 0x0 0x0 0x0 0x0>;
+                                        ranges = <0x1 0x0 0x1000000 0x0 0x0
+                                                  0x1000>;
+                                        interrupt-parent = <&i8259>;
+
+                                        i8259: interrupt-controller@20 {
+                                                reg = <0x1 0x20 0x2
+                                                       0x1 0xa0 0x2
+                                                       0x1 0x4d0 0x2>;
+                                                interrupt-controller;
+                                                device_type = "interrupt-controller";
+                                                #address-cells = <0>;
+                                                #interrupt-cells = <2>;
+                                                compatible = "chrp,iic";
+                                                interrupts = <9 2>;
+                                                interrupt-parent = <&mpic>;
+                                        };
+
+                                        i8042@60 {
+                                                #size-cells = <0>;
+                                                #address-cells = <1>;
+                                                reg = <0x1 0x60 0x1 0x1 0x64 0x1>;
+                                                interrupts = <1 3 12 3>;
+                                                interrupt-parent =
+                                                        <&i8259>;
+
+                                                keyboard@0 {
+                                                        reg = <0x0>;
+                                                        compatible = "pnpPNP,303";
+                                                };
+
+                                                mouse@1 {
+                                                        reg = <0x1>;
+                                                        compatible = "pnpPNP,f03";
+                                                };
+                                        };
+
+                                        rtc@70 {
+                                                compatible = "pnpPNP,b00";
+                                                reg = <0x1 0x70 0x2>;
+                                        };
+
+                                        gpio@400 {
+                                                reg = <0x1 0x400 0x80>;
+                                        };
+                                };
+                        };
+                };
+
+        };
+
+        pci1: pcie@ffe09000 {
+                cell-index = <1>;
+                compatible = "fsl,mpc8548-pcie";
+                device_type = "pci";
+                #interrupt-cells = <1>;
+                #size-cells = <2>;
+                #address-cells = <3>;
+                reg = <0xffe09000 0x1000>;
+                bus-range = <0 255>;
+                ranges = <0x2000000 0x0 0xa0000000 0xa0000000 0x0 0x20000000
+                          0x1000000 0x0 0x0 0xffc10000 0x0 0x10000>;
+                clock-frequency = <33333333>;
+                interrupt-parent = <&mpic>;
+                interrupts = <26 2>;
+                interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+                interrupt-map = <
+                        /* IDSEL 0x0 */
+                        0000 0x0 0x0 0x1 &mpic 0x4 0x1
+                        0000 0x0 0x0 0x2 &mpic 0x5 0x1
+                        0000 0x0 0x0 0x3 &mpic 0x6 0x1
+                        0000 0x0 0x0 0x4 &mpic 0x7 0x1
+                        >;
+                pcie@0 {
+                        reg = <0x0 0x0 0x0 0x0 0x0>;
+                        #size-cells = <2>;
+                        #address-cells = <3>;
+                        device_type = "pci";
+                        ranges = <0x2000000 0x0 0xa0000000
+                                  0x2000000 0x0 0xa0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+};
diff --git a/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts b/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts
new file mode 100644
index 000000000000..04ecda18d206
--- /dev/null
+++ b/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts
@@ -0,0 +1,234 @@
+/*
+ * MPC8572 DS Core1 Device Tree Source in CAMP mode.
+ *
+ * In CAMP mode, each core needs to have its own dts. Only mpic and L2 cache
+ * can be shared, all the other devices must be assigned to one core only.
+ * This dts allows core1 to have l2, dma2, eth2, eth3, pci2, msi.
+ *
+ * Please note to add "-b 1" for core1's dts compiling.
+ *
+ * Copyright 2007, 2008 Freescale Semiconductor Inc.
+ *
+ * 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.
+ */
+
+/dts-v1/;
+/ {
+        model = "fsl,MPC8572DS";
+        compatible = "fsl,MPC8572DS", "fsl,MPC8572DS-CAMP";
+        #address-cells = <1>;
+        #size-cells = <1>;
+
+        aliases {
+                ethernet2 = &enet2;
+                ethernet3 = &enet3;
+                serial0 = &serial0;
+                pci2 = &pci2;
+        };
+
+        cpus {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                PowerPC,8572@1 {
+                        device_type = "cpu";
+                        reg = <0x1>;
+                        d-cache-line-size = <32>;       // 32 bytes
+                        i-cache-line-size = <32>;       // 32 bytes
+                        d-cache-size = <0x8000>;                // L1, 32K
+                        i-cache-size = <0x8000>;                // L1, 32K
+                        timebase-frequency = <0>;
+                        bus-frequency = <0>;
+                        clock-frequency = <0>;
+                        next-level-cache = <&L2>;
+                };
+        };
+
+        memory {
+                device_type = "memory";
+                reg = <0x0 0x0>;        // Filled by U-Boot
+        };
+
+        soc8572@ffe00000 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                device_type = "soc";
+                compatible = "simple-bus";
+                ranges = <0x0 0xffe00000 0x100000>;
+                reg = <0xffe00000 0x1000>;      // CCSRBAR & soc regs, remove once parse code for immrbase fixed
+                bus-frequency = <0>;            // Filled out by uboot.
+
+                L2: l2-cache-controller@20000 {
+                        compatible = "fsl,mpc8572-l2-cache-controller";
+                        reg = <0x20000 0x1000>;
+                        cache-line-size = <32>; // 32 bytes
+                        cache-size = <0x80000>; // L2, 512K
+                        interrupt-parent = <&mpic>;
+                };
+
+                dma@c300 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "fsl,mpc8572-dma", "fsl,eloplus-dma";
+                        reg = <0xc300 0x4>;
+                        ranges = <0x0 0xc100 0x200>;
+                        cell-index = <0>;
+                        dma-channel@0 {
+                                compatible = "fsl,mpc8572-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x0 0x80>;
+                                cell-index = <0>;
+                                interrupt-parent = <&mpic>;
+                                interrupts = <76 2>;
+                        };
+                        dma-channel@80 {
+                                compatible = "fsl,mpc8572-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x80 0x80>;
+                                cell-index = <1>;
+                                interrupt-parent = <&mpic>;
+                                interrupts = <77 2>;
+                        };
+                        dma-channel@100 {
+                                compatible = "fsl,mpc8572-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x100 0x80>;
+                                cell-index = <2>;
+                                interrupt-parent = <&mpic>;
+                                interrupts = <78 2>;
+                        };
+                        dma-channel@180 {
+                                compatible = "fsl,mpc8572-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x180 0x80>;
+                                cell-index = <3>;
+                                interrupt-parent = <&mpic>;
+                                interrupts = <79 2>;
+                        };
+                };
+
+                mdio@24520 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        compatible = "fsl,gianfar-mdio";
+                        reg = <0x24520 0x20>;
+
+                        phy2: ethernet-phy@2 {
+                                interrupt-parent = <&mpic>;
+                                reg = <0x2>;
+                        };
+                        phy3: ethernet-phy@3 {
+                                interrupt-parent = <&mpic>;
+                                reg = <0x3>;
+                        };
+                };
+
+                enet2: ethernet@26000 {
+                        cell-index = <2>;
+                        device_type = "network";
+                        model = "eTSEC";
+                        compatible = "gianfar";
+                        reg = <0x26000 0x1000>;
+                        local-mac-address = [ 00 00 00 00 00 00 ];
+                        interrupts = <31 2 32 2 33 2>;
+                        interrupt-parent = <&mpic>;
+                        phy-handle = <&phy2>;
+                        phy-connection-type = "rgmii-id";
+                };
+
+                enet3: ethernet@27000 {
+                        cell-index = <3>;
+                        device_type = "network";
+                        model = "eTSEC";
+                        compatible = "gianfar";
+                        reg = <0x27000 0x1000>;
+                        local-mac-address = [ 00 00 00 00 00 00 ];
+                        interrupts = <37 2 38 2 39 2>;
+                        interrupt-parent = <&mpic>;
+                        phy-handle = <&phy3>;
+                        phy-connection-type = "rgmii-id";
+                };
+
+                msi@41600 {
+                        compatible = "fsl,mpc8572-msi", "fsl,mpic-msi";
+                        reg = <0x41600 0x80>;
+                        msi-available-ranges = <0 0x100>;
+                        interrupts = <
+                                0xe0 0
+                                0xe1 0
+                                0xe2 0
+                                0xe3 0
+                                0xe4 0
+                                0xe5 0
+                                0xe6 0
+                                0xe7 0>;
+                        interrupt-parent = <&mpic>;
+                };
+
+                serial0: serial@4600 {
+                        cell-index = <1>;
+                        device_type = "serial";
+                        compatible = "ns16550";
+                        reg = <0x4600 0x100>;
+                        clock-frequency = <0>;
+                };
+
+                mpic: pic@40000 {
+                        interrupt-controller;
+                        #address-cells = <0>;
+                        #interrupt-cells = <2>;
+                        reg = <0x40000 0x40000>;
+                        compatible = "chrp,open-pic";
+                        device_type = "open-pic";
+                        protected-sources = <
+                        18 16 10 42 45 58       /* MEM L2 mdio serial crypto */
+                        29 30 34 35 36 40       /* enet0 enet1 */
+                        24 26 20 21 22 23       /* pcie0 pcie1 dma1 */
+                        43                      /* i2c */
+                        0x1 0x2 0x3 0x4         /* pci slot */
+                        0x9 0xa 0xb 0xc         /* usb */
+                        0x6 0x7 0xe 0x5         /* Audio elgacy SATA */
+                        >;
+                };
+        };
+
+        pci2: pcie@ffe0a000 {
+                cell-index = <2>;
+                compatible = "fsl,mpc8548-pcie";
+                device_type = "pci";
+                #interrupt-cells = <1>;
+                #size-cells = <2>;
+                #address-cells = <3>;
+                reg = <0xffe0a000 0x1000>;
+                bus-range = <0 255>;
+                ranges = <0x2000000 0x0 0xc0000000 0xc0000000 0x0 0x20000000
+                          0x1000000 0x0 0x0 0xffc20000 0x0 0x10000>;
+                clock-frequency = <33333333>;
+                interrupt-parent = <&mpic>;
+                interrupts = <27 2>;
+                interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+                interrupt-map = <
+                        /* IDSEL 0x0 */
+                        0000 0x0 0x0 0x1 &mpic 0x0 0x1
+                        0000 0x0 0x0 0x2 &mpic 0x1 0x1
+                        0000 0x0 0x0 0x3 &mpic 0x2 0x1
+                        0000 0x0 0x0 0x4 &mpic 0x3 0x1
+                        >;
+                pcie@0 {
+                        reg = <0x0 0x0 0x0 0x0 0x0>;
+                        #size-cells = <2>;
+                        #address-cells = <3>;
+                        device_type = "pci";
+                        ranges = <0x2000000 0x0 0xc0000000
+                                  0x2000000 0x0 0xc0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+};
diff --git a/arch/powerpc/boot/dts/pcm030.dts b/arch/powerpc/boot/dts/pcm030.dts
index 7c1bb952360c..be2c11ca0594 100644
--- a/arch/powerpc/boot/dts/pcm030.dts
+++ b/arch/powerpc/boot/dts/pcm030.dts
@@ -143,7 +143,6 @@
 
                 rtc@800 {       // Real time clock
                         compatible = "fsl,mpc5200b-rtc","fsl,mpc5200-rtc";
-                        device_type = "rtc";
                         reg = <0x800 0x100>;
                         interrupts = <0x1 0x5 0x0 0x1 0x6 0x0>;
                         interrupt-parent = <&mpc5200_pic>;
@@ -301,7 +300,6 @@
                         interrupt-parent = <&mpc5200_pic>;
                         fsl5200-clocking;
                         rtc@51 {
-                                device_type = "rtc";
                                 compatible = "nxp,pcf8563";
                                 reg = <0x51>;
                         };
diff --git a/arch/powerpc/boot/dts/tqm5200.dts b/arch/powerpc/boot/dts/tqm5200.dts
index 3008bf8830c1..906302e26a62 100644
--- a/arch/powerpc/boot/dts/tqm5200.dts
+++ b/arch/powerpc/boot/dts/tqm5200.dts
@@ -181,7 +181,6 @@
                         fsl5200-clocking;
 
                          rtc@68 {
-                                device_type = "rtc";
                                 compatible = "dallas,ds1307";
                                 reg = <0x68>;
                         };
diff --git a/arch/powerpc/boot/libfdt-wrapper.c b/arch/powerpc/boot/libfdt-wrapper.c
index 9276327bc2bb..bb8b9b3505ee 100644
--- a/arch/powerpc/boot/libfdt-wrapper.c
+++ b/arch/powerpc/boot/libfdt-wrapper.c
@@ -185,7 +185,7 @@ void fdt_init(void *blob)
 
         /* Make sure the dt blob is the right version and so forth */
         fdt = blob;
-        bufsize = fdt_totalsize(fdt) + 4;
+        bufsize = fdt_totalsize(fdt) + EXPAND_GRANULARITY;
         buf = malloc(bufsize);
         if(!buf)
                 fatal("malloc failed. can't relocate the device tree\n\r");
diff --git a/arch/powerpc/configs/86xx/gef_sbc610_defconfig b/arch/powerpc/configs/86xx/gef_sbc610_defconfig
index 07ccaf89f379..cd1ffa449327 100644
--- a/arch/powerpc/configs/86xx/gef_sbc610_defconfig
+++ b/arch/powerpc/configs/86xx/gef_sbc610_defconfig
@@ -1397,8 +1397,11 @@ CONFIG_USB_STORAGE=y
 # CONFIG_ACCESSIBILITY is not set
 # CONFIG_INFINIBAND is not set
 # CONFIG_EDAC is not set
-CONFIG_RTC_LIB=m
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_HCTOSYS=y
+CONFIG_RTC_HCTOSYS_DEVICE="rtc0"
+# CONFIG_RTC_DEBUG is not set
 
 #
 # RTC interfaces
@@ -1424,6 +1427,7 @@ CONFIG_RTC_INTF_DEV=y
 # CONFIG_RTC_DRV_M41T80 is not set
 # CONFIG_RTC_DRV_S35390A is not set
 # CONFIG_RTC_DRV_FM3130 is not set
+CONFIG_RTC_DRV_RX8581=y
 
 #
 # SPI RTC drivers
diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig
index cfc94cfcf4cb..034a1fbdc887 100644
--- a/arch/powerpc/configs/ppc44x_defconfig
+++ b/arch/powerpc/configs/ppc44x_defconfig
@@ -267,7 +267,7 @@ CONFIG_PCI_SYSCALL=y
 # CONFIG_PCIEPORTBUS is not set
 CONFIG_ARCH_SUPPORTS_MSI=y
 # CONFIG_PCI_MSI is not set
-CONFIG_PCI_LEGACY=y
+# CONFIG_PCI_LEGACY is not set
 # CONFIG_PCI_DEBUG is not set
 # CONFIG_PCCARD is not set
 # CONFIG_HOTPLUG_PCI is not set
@@ -354,7 +354,7 @@ CONFIG_IPV6_NDISC_NODETYPE=y
 # CONFIG_IP_SCTP is not set
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
-# CONFIG_BRIDGE is not set
+CONFIG_BRIDGE=m
 # CONFIG_NET_DSA is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
@@ -579,7 +579,7 @@ CONFIG_NETDEVICES=y
 # CONFIG_BONDING is not set
 # CONFIG_MACVLAN is not set
 # CONFIG_EQUALIZER is not set
-# CONFIG_TUN is not set
+CONFIG_TUN=m
 # CONFIG_VETH is not set
 # CONFIG_ARCNET is not set
 # CONFIG_PHYLIB is not set
@@ -1001,11 +1001,11 @@ CONFIG_USB_OHCI_LITTLE_ENDIAN=y
 # CONFIG_USB_TMC is not set
 
 #
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed;
 #
 
 #
-# may also be needed; see USB_STORAGE Help for more information
+# see USB_STORAGE Help for more information
 #
 CONFIG_USB_STORAGE=m
 # CONFIG_USB_STORAGE_DEBUG is not set
@@ -1418,6 +1418,6 @@ CONFIG_CRYPTO_LZO=m
 # CONFIG_PPC_CLOCK is not set
 CONFIG_VIRTUALIZATION=y
 CONFIG_KVM=y
-CONFIG_KVM_BOOKE_HOST=y
+CONFIG_KVM_440=y
 # CONFIG_VIRTIO_PCI is not set
 # CONFIG_VIRTIO_BALLOON is not set
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index f3fc733758f5..499be5bdd6fa 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -111,7 +111,7 @@ static __inline__ void atomic_inc(atomic_t *v)
         bne-    1b"
         : "=&r" (t), "+m" (v->counter)
         : "r" (&v->counter)
-        : "cc");
+        : "cc", "xer");
 }
 
 static __inline__ int atomic_inc_return(atomic_t *v)
@@ -128,7 +128,7 @@ static __inline__ int atomic_inc_return(atomic_t *v)
         ISYNC_ON_SMP
         : "=&r" (t)
         : "r" (&v->counter)
-        : "cc", "memory");
+        : "cc", "xer", "memory");
 
         return t;
 }
@@ -155,7 +155,7 @@ static __inline__ void atomic_dec(atomic_t *v)
         bne-    1b"
         : "=&r" (t), "+m" (v->counter)
         : "r" (&v->counter)
-        : "cc");
+        : "cc", "xer");
 }
 
 static __inline__ int atomic_dec_return(atomic_t *v)
@@ -172,7 +172,7 @@ static __inline__ int atomic_dec_return(atomic_t *v)
         ISYNC_ON_SMP
         : "=&r" (t)
         : "r" (&v->counter)
-        : "cc", "memory");
+        : "cc", "xer", "memory");
 
         return t;
 }
@@ -346,7 +346,7 @@ static __inline__ void atomic64_inc(atomic64_t *v)
         bne-    1b"
         : "=&r" (t), "+m" (v->counter)
         : "r" (&v->counter)
-        : "cc");
+        : "cc", "xer");
 }
 
 static __inline__ long atomic64_inc_return(atomic64_t *v)
@@ -362,7 +362,7 @@ static __inline__ long atomic64_inc_return(atomic64_t *v)
         ISYNC_ON_SMP
         : "=&r" (t)
         : "r" (&v->counter)
-        : "cc", "memory");
+        : "cc", "xer", "memory");
 
         return t;
 }
@@ -388,7 +388,7 @@ static __inline__ void atomic64_dec(atomic64_t *v)
         bne-    1b"
         : "=&r" (t), "+m" (v->counter)
         : "r" (&v->counter)
-        : "cc");
+        : "cc", "xer");
 }
 
 static __inline__ long atomic64_dec_return(atomic64_t *v)
@@ -404,7 +404,7 @@ static __inline__ long atomic64_dec_return(atomic64_t *v)
         ISYNC_ON_SMP
         : "=&r" (t)
         : "r" (&v->counter)
-        : "cc", "memory");
+        : "cc", "xer", "memory");
 
         return t;
 }
@@ -431,7 +431,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
         "\n\
 2:"     : "=&r" (t)
         : "r" (&v->counter)
-        : "cc", "memory");
+        : "cc", "xer", "memory");
 
         return t;
 }
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index e55d1f66b86f..64e1fdca233e 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -3,6 +3,7 @@
 #ifdef __KERNEL__
 
 #include <asm/asm-compat.h>
+
 /*
  * Define an illegal instr to trap on the bug.
  * We don't use 0 because that marks the end of a function
@@ -14,6 +15,7 @@
 #ifdef CONFIG_BUG
 
 #ifdef __ASSEMBLY__
+#include <asm/asm-offsets.h>
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 .macro EMIT_BUG_ENTRY addr,file,line,flags
          .section __bug_table,"a"
@@ -26,7 +28,7 @@
          .previous
 .endm
 #else
- .macro EMIT_BUG_ENTRY addr,file,line,flags
+.macro EMIT_BUG_ENTRY addr,file,line,flags
          .section __bug_table,"a"
 5001:    PPC_LONG \addr
          .short \flags
@@ -113,6 +115,13 @@
 #define HAVE_ARCH_BUG_ON
 #define HAVE_ARCH_WARN_ON
 #endif /* __ASSEMBLY __ */
+#else
+#ifdef __ASSEMBLY__
+.macro EMIT_BUG_ENTRY addr,file,line,flags
+.endm
+#else /* !__ASSEMBLY__ */
+#define _EMIT_BUG_ENTRY
+#endif
 #endif /* CONFIG_BUG */
 
 #include <asm-generic/bug.h>
diff --git a/arch/powerpc/include/asm/byteorder.h b/arch/powerpc/include/asm/byteorder.h
index b37752214a16..d5de325472e9 100644
--- a/arch/powerpc/include/asm/byteorder.h
+++ b/arch/powerpc/include/asm/byteorder.h
@@ -11,6 +11,8 @@
 #include <asm/types.h>
 #include <linux/compiler.h>
 
+#define __BIG_ENDIAN
+
 #ifdef __GNUC__
 #ifdef __KERNEL__
 
@@ -21,12 +23,19 @@ static __inline__ __u16 ld_le16(const volatile __u16 *addr)
         __asm__ __volatile__ ("lhbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr));
         return val;
 }
+#define __arch_swab16p ld_le16
 
 static __inline__ void st_le16(volatile __u16 *addr, const __u16 val)
 {
         __asm__ __volatile__ ("sthbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr));
 }
 
+static inline void __arch_swab16s(__u16 *addr)
+{
+        st_le16(addr, *addr);
+}
+#define __arch_swab16s __arch_swab16s
+
 static __inline__ __u32 ld_le32(const volatile __u32 *addr)
 {
         __u32 val;
@@ -34,13 +43,20 @@ static __inline__ __u32 ld_le32(const volatile __u32 *addr)
         __asm__ __volatile__ ("lwbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr));
         return val;
 }
+#define __arch_swab32p ld_le32
 
 static __inline__ void st_le32(volatile __u32 *addr, const __u32 val)
 {
         __asm__ __volatile__ ("stwbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr));
 }
 
-static __inline__ __attribute_const__ __u16 ___arch__swab16(__u16 value)
+static inline void __arch_swab32s(__u32 *addr)
+{
+        st_le32(addr, *addr);
+}
+#define __arch_swab32s __arch_swab32s
+
+static inline __attribute_const__ __u16 __arch_swab16(__u16 value)
 {
         __u16 result;
 
@@ -49,8 +65,9 @@ static __inline__ __attribute_const__ __u16 ___arch__swab16(__u16 value)
             : "r" (value), "0" (value >> 8));
         return result;
 }
+#define __arch_swab16 __arch_swab16
 
-static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 value)
+static inline __attribute_const__ __u32 __arch_swab32(__u32 value)
 {
         __u32 result;
 
@@ -61,29 +78,16 @@ static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 value)
             : "r" (value), "0" (value >> 24));
         return result;
 }
-
-#define __arch__swab16(x) ___arch__swab16(x)
-#define __arch__swab32(x) ___arch__swab32(x)
-
-/* The same, but returns converted value from the location pointer by addr. */
-#define __arch__swab16p(addr) ld_le16(addr)
-#define __arch__swab32p(addr) ld_le32(addr)
-
-/* The same, but do the conversion in situ, ie. put the value back to addr. */
-#define __arch__swab16s(addr) st_le16(addr,*addr)
-#define __arch__swab32s(addr) st_le32(addr,*addr)
+#define __arch_swab32 __arch_swab32
 
 #endif /* __KERNEL__ */
 
-#ifndef __STRICT_ANSI__
-#define __BYTEORDER_HAS_U64__
 #ifndef __powerpc64__
 #define __SWAB_64_THRU_32__
 #endif /* __powerpc64__ */
-#endif /* __STRICT_ANSI__ */
 
 #endif /* __GNUC__ */
 
-#include <linux/byteorder/big_endian.h>
+#include <linux/byteorder.h>
 
 #endif /* _ASM_POWERPC_BYTEORDER_H */
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 1e94b07a020e..4911104791c3 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -82,6 +82,7 @@ struct cpu_spec {
         char            *cpu_name;
         unsigned long   cpu_features;           /* Kernel features */
         unsigned int    cpu_user_features;      /* Userland features */
+        unsigned int    mmu_features;           /* MMU features */
 
         /* cache line sizes */
         unsigned int    icache_bsize;
@@ -144,17 +145,14 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_USE_TB                  ASM_CONST(0x0000000000000040)
 #define CPU_FTR_L2CSR                   ASM_CONST(0x0000000000000080)
 #define CPU_FTR_601                     ASM_CONST(0x0000000000000100)
-#define CPU_FTR_HPTE_TABLE              ASM_CONST(0x0000000000000200)
 #define CPU_FTR_CAN_NAP                 ASM_CONST(0x0000000000000400)
 #define CPU_FTR_L3CR                    ASM_CONST(0x0000000000000800)
 #define CPU_FTR_L3_DISABLE_NAP          ASM_CONST(0x0000000000001000)
 #define CPU_FTR_NAP_DISABLE_L2_PR       ASM_CONST(0x0000000000002000)
 #define CPU_FTR_DUAL_PLL_750FX          ASM_CONST(0x0000000000004000)
 #define CPU_FTR_NO_DPM                  ASM_CONST(0x0000000000008000)
-#define CPU_FTR_HAS_HIGH_BATS           ASM_CONST(0x0000000000010000)
 #define CPU_FTR_NEED_COHERENT           ASM_CONST(0x0000000000020000)
 #define CPU_FTR_NO_BTIC                 ASM_CONST(0x0000000000040000)
-#define CPU_FTR_BIG_PHYS                ASM_CONST(0x0000000000080000)
 #define CPU_FTR_NODSISRALIGN            ASM_CONST(0x0000000000100000)
 #define CPU_FTR_PPC_LE                  ASM_CONST(0x0000000000200000)
 #define CPU_FTR_REAL_LE                 ASM_CONST(0x0000000000400000)
@@ -163,6 +161,8 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_SPE                     ASM_CONST(0x0000000002000000)
 #define CPU_FTR_NEED_PAIRED_STWCX       ASM_CONST(0x0000000004000000)
 #define CPU_FTR_LWSYNC                  ASM_CONST(0x0000000008000000)
+#define CPU_FTR_NOEXECUTE               ASM_CONST(0x0000000010000000)
+#define CPU_FTR_INDEXED_DCR             ASM_CONST(0x0000000020000000)
 
 /*
  * Add the 64-bit processor unique features in the top half of the word;
@@ -177,7 +177,6 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_SLB                     LONG_ASM_CONST(0x0000000100000000)
 #define CPU_FTR_16M_PAGE                LONG_ASM_CONST(0x0000000200000000)
 #define CPU_FTR_TLBIEL                  LONG_ASM_CONST(0x0000000400000000)
-#define CPU_FTR_NOEXECUTE               LONG_ASM_CONST(0x0000000800000000)
 #define CPU_FTR_IABR                    LONG_ASM_CONST(0x0000002000000000)
 #define CPU_FTR_MMCRA                   LONG_ASM_CONST(0x0000004000000000)
 #define CPU_FTR_CTRL                    LONG_ASM_CONST(0x0000008000000000)
@@ -194,6 +193,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_VSX                     LONG_ASM_CONST(0x0010000000000000)
 #define CPU_FTR_SAO                     LONG_ASM_CONST(0x0020000000000000)
 #define CPU_FTR_CP_USE_DCBTZ            LONG_ASM_CONST(0x0040000000000000)
+#define CPU_FTR_UNALIGNED_LD_STD        LONG_ASM_CONST(0x0080000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -264,164 +264,159 @@ extern const char *powerpc_base_platform;
                      !defined(CONFIG_POWER3) && !defined(CONFIG_POWER4) && \
                      !defined(CONFIG_BOOKE))
 
-#define CPU_FTRS_PPC601 (CPU_FTR_COMMON | CPU_FTR_601 | CPU_FTR_HPTE_TABLE | \
+#define CPU_FTRS_PPC601 (CPU_FTR_COMMON | CPU_FTR_601 | \
         CPU_FTR_COHERENT_ICACHE | CPU_FTR_UNIFIED_ID_CACHE)
 #define CPU_FTRS_603    (CPU_FTR_COMMON | \
             CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
             CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
 #define CPU_FTRS_604    (CPU_FTR_COMMON | \
-            CPU_FTR_USE_TB | CPU_FTR_HPTE_TABLE | CPU_FTR_PPC_LE)
+            CPU_FTR_USE_TB | CPU_FTR_PPC_LE)
 #define CPU_FTRS_740_NOTAU      (CPU_FTR_COMMON | \
             CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
+            CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
 #define CPU_FTRS_740    (CPU_FTR_COMMON | \
             CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
-            CPU_FTR_TAU | CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP | \
+            CPU_FTR_TAU | CPU_FTR_MAYBE_CAN_NAP | \
             CPU_FTR_PPC_LE)
 #define CPU_FTRS_750    (CPU_FTR_COMMON | \
             CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
-            CPU_FTR_TAU | CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP | \
+            CPU_FTR_TAU | CPU_FTR_MAYBE_CAN_NAP | \
             CPU_FTR_PPC_LE)
-#define CPU_FTRS_750CL  (CPU_FTRS_750 | CPU_FTR_HAS_HIGH_BATS)
+#define CPU_FTRS_750CL  (CPU_FTRS_750)
 #define CPU_FTRS_750FX1 (CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX | CPU_FTR_NO_DPM)
 #define CPU_FTRS_750FX2 (CPU_FTRS_750 | CPU_FTR_NO_DPM)
-#define CPU_FTRS_750FX  (CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX | \
-                CPU_FTR_HAS_HIGH_BATS)
+#define CPU_FTRS_750FX  (CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX)
 #define CPU_FTRS_750GX  (CPU_FTRS_750FX)
 #define CPU_FTRS_7400_NOTAU     (CPU_FTR_COMMON | \
             CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
-            CPU_FTR_ALTIVEC_COMP | CPU_FTR_HPTE_TABLE | \
+            CPU_FTR_ALTIVEC_COMP | \
             CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7400   (CPU_FTR_COMMON | \
             CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \
-            CPU_FTR_TAU | CPU_FTR_ALTIVEC_COMP | CPU_FTR_HPTE_TABLE | \
+            CPU_FTR_TAU | CPU_FTR_ALTIVEC_COMP | \
             CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7450_20        (CPU_FTR_COMMON | \
             CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-            CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
+            CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
             CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7450_21        (CPU_FTR_COMMON | \
             CPU_FTR_USE_TB | \
             CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-            CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
+            CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
             CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP | \
             CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7450_23        (CPU_FTR_COMMON | \
             CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \
             CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-            CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
+            CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
             CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7455_1 (CPU_FTR_COMMON | \
             CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \
             CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | CPU_FTR_HAS_HIGH_BATS | \
-            CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
+            CPU_FTR_SPEC7450 | CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7455_20        (CPU_FTR_COMMON | \
             CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \
             CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-            CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
+            CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
             CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP | \
-            CPU_FTR_NEED_COHERENT | CPU_FTR_HAS_HIGH_BATS | CPU_FTR_PPC_LE)
+            CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
 #define CPU_FTRS_7455   (CPU_FTR_COMMON | \
             CPU_FTR_USE_TB | \
             CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-            CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
-            CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \
+            CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
             CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7447_10        (CPU_FTR_COMMON | \
             CPU_FTR_USE_TB | \
             CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-            CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
-            CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \
+            CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
             CPU_FTR_NEED_COHERENT | CPU_FTR_NO_BTIC | CPU_FTR_PPC_LE | \
             CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7447   (CPU_FTR_COMMON | \
             CPU_FTR_USE_TB | \
             CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-            CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
-            CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \
+            CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
             CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7447A  (CPU_FTR_COMMON | \
             CPU_FTR_USE_TB | \
             CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
-            CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \
+            CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
             CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_7448   (CPU_FTR_COMMON | \
             CPU_FTR_USE_TB | \
             CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \
-            CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \
+            CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
             CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
 #define CPU_FTRS_82XX   (CPU_FTR_COMMON | \
             CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB)
 #define CPU_FTRS_G2_LE  (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \
-            CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS)
+            CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP)
 #define CPU_FTRS_E300   (CPU_FTR_MAYBE_CAN_DOZE | \
-            CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS | \
+            CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | \
             CPU_FTR_COMMON)
 #define CPU_FTRS_E300C2 (CPU_FTR_MAYBE_CAN_DOZE | \
-            CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS | \
+            CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | \
             CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE)
-#define CPU_FTRS_CLASSIC32      (CPU_FTR_COMMON | \
-            CPU_FTR_USE_TB | CPU_FTR_HPTE_TABLE)
+#define CPU_FTRS_CLASSIC32      (CPU_FTR_COMMON | CPU_FTR_USE_TB)
 #define CPU_FTRS_8XX    (CPU_FTR_USE_TB)
-#define CPU_FTRS_40X    (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN)
-#define CPU_FTRS_44X    (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN)
+#define CPU_FTRS_40X    (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_44X    (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_440x6  (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE | \
+            CPU_FTR_INDEXED_DCR)
 #define CPU_FTRS_E200   (CPU_FTR_USE_TB | CPU_FTR_SPE_COMP | \
             CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \
-            CPU_FTR_UNIFIED_ID_CACHE)
+            CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_E500   (CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
-            CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN)
+            CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \
+            CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_E500_2 (CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
-            CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_BIG_PHYS | \
-            CPU_FTR_NODSISRALIGN)
+            CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \
+            CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_E500MC (CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
-            CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_BIG_PHYS | CPU_FTR_NODSISRALIGN | \
-            CPU_FTR_L2CSR | CPU_FTR_LWSYNC)
+            CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \
+            CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_GENERIC_32     (CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN)
 
 /* 64-bit CPUs */
 #define CPU_FTRS_POWER3 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_IABR | CPU_FTR_PPC_LE)
+            CPU_FTR_IABR | CPU_FTR_PPC_LE)
 #define CPU_FTRS_RS64   (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_IABR | \
+            CPU_FTR_IABR | \
             CPU_FTR_MMCRA | CPU_FTR_CTRL)
 #define CPU_FTRS_POWER4 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+            CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
             CPU_FTR_MMCRA | CPU_FTR_CP_USE_DCBTZ)
 #define CPU_FTRS_PPC970 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+            CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
             CPU_FTR_ALTIVEC_COMP | CPU_FTR_CAN_NAP | CPU_FTR_MMCRA | \
             CPU_FTR_CP_USE_DCBTZ)
 #define CPU_FTRS_POWER5 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+            CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
             CPU_FTR_MMCRA | CPU_FTR_SMT | \
             CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
             CPU_FTR_PURR)
 #define CPU_FTRS_POWER6 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+            CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
             CPU_FTR_MMCRA | CPU_FTR_SMT | \
             CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
             CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-            CPU_FTR_DSCR)
+            CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD)
 #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+            CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
             CPU_FTR_MMCRA | CPU_FTR_SMT | \
             CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
             CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
             CPU_FTR_DSCR | CPU_FTR_SAO)
 #define CPU_FTRS_CELL   (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+            CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
             CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
             CPU_FTR_PAUSE_ZERO | CPU_FTR_CI_LARGE_PAGE | \
-            CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ)
+            CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \
+            CPU_FTR_UNALIGNED_LD_STD)
 #define CPU_FTRS_PA6T (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | \
+            CPU_FTR_PPCAS_ARCH_V2 | \
             CPU_FTR_ALTIVEC_COMP | CPU_FTR_CI_LARGE_PAGE | \
             CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_NO_SLBIE_B)
-#define CPU_FTRS_COMPATIBLE     (CPU_FTR_USE_TB | \
-            CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2)
+#define CPU_FTRS_COMPATIBLE     (CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2)
 
 #ifdef __powerpc64__
 #define CPU_FTRS_POSSIBLE       \
@@ -452,7 +447,7 @@ enum {
             CPU_FTRS_40X |
 #endif
 #ifdef CONFIG_44x
-            CPU_FTRS_44X |
+            CPU_FTRS_44X | CPU_FTRS_440x6 |
 #endif
 #ifdef CONFIG_E200
             CPU_FTRS_E200 |
@@ -492,7 +487,7 @@ enum {
             CPU_FTRS_40X &
 #endif
 #ifdef CONFIG_44x
-            CPU_FTRS_44X &
+            CPU_FTRS_44X & CPU_FTRS_440x6 &
 #endif
 #ifdef CONFIG_E200
             CPU_FTRS_E200 &
diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h
index 72d2b72c7390..7d2e6235726d 100644
--- a/arch/powerpc/include/asm/dcr-native.h
+++ b/arch/powerpc/include/asm/dcr-native.h
@@ -23,6 +23,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/spinlock.h>
+#include <asm/cputable.h>
 
 typedef struct {
         unsigned int base;
@@ -39,23 +40,45 @@ static inline bool dcr_map_ok_native(dcr_host_native_t host)
 #define dcr_read_native(host, dcr_n)            mfdcr(dcr_n + host.base)
 #define dcr_write_native(host, dcr_n, value)    mtdcr(dcr_n + host.base, value)
 
-/* Device Control Registers */
-void __mtdcr(int reg, unsigned int val);
-unsigned int __mfdcr(int reg);
+/* Table based DCR accessors */
+extern void __mtdcr(unsigned int reg, unsigned int val);
+extern unsigned int __mfdcr(unsigned int reg);
+
+/* mfdcrx/mtdcrx instruction based accessors. We hand code
+ * the opcodes in order not to depend on newer binutils
+ */
+static inline unsigned int mfdcrx(unsigned int reg)
+{
+        unsigned int ret;
+        asm volatile(".long 0x7c000206 | (%0 << 21) | (%1 << 16)"
+                     : "=r" (ret) : "r" (reg));
+        return ret;
+}
+
+static inline void mtdcrx(unsigned int reg, unsigned int val)
+{
+        asm volatile(".long 0x7c000306 | (%0 << 21) | (%1 << 16)"
+                     : : "r" (val), "r" (reg));
+}
+
 #define mfdcr(rn)                                               \
         ({unsigned int rval;                                    \
-        if (__builtin_constant_p(rn))                           \
+        if (__builtin_constant_p(rn) && rn < 1024)              \
                 asm volatile("mfdcr %0," __stringify(rn)        \
                               : "=r" (rval));                   \
+        else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR)))  \
+                rval = mfdcrx(rn);                              \
         else                                                    \
                 rval = __mfdcr(rn);                             \
         rval;})
 
 #define mtdcr(rn, v)                                            \
 do {                                                            \
-        if (__builtin_constant_p(rn))                           \
+        if (__builtin_constant_p(rn) && rn < 1024)              \
                 asm volatile("mtdcr " __stringify(rn) ",%0"     \
                               : : "r" (v));                     \
+        else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR)))  \
+                mtdcrx(rn, v);                                  \
         else                                                    \
                 __mtdcr(rn, v);                                 \
 } while (0)
@@ -69,8 +92,13 @@ static inline unsigned __mfdcri(int base_addr, int base_data, int reg)
         unsigned int val;
 
         spin_lock_irqsave(&dcr_ind_lock, flags);
-        __mtdcr(base_addr, reg);
-        val = __mfdcr(base_data);
+        if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) {
+                mtdcrx(base_addr, reg);
+                val = mfdcrx(base_data);
+        } else {
+                __mtdcr(base_addr, reg);
+                val = __mfdcr(base_data);
+        }
         spin_unlock_irqrestore(&dcr_ind_lock, flags);
         return val;
 }
@@ -81,8 +109,13 @@ static inline void __mtdcri(int base_addr, int base_data, int reg,
         unsigned long flags;
 
         spin_lock_irqsave(&dcr_ind_lock, flags);
-        __mtdcr(base_addr, reg);
-        __mtdcr(base_data, val);
+        if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) {
+                mtdcrx(base_addr, reg);
+                mtdcrx(base_data, val);
+        } else {
+                __mtdcr(base_addr, reg);
+                __mtdcr(base_data, val);
+        }
         spin_unlock_irqrestore(&dcr_ind_lock, flags);
 }
 
@@ -93,9 +126,15 @@ static inline void __dcri_clrset(int base_addr, int base_data, int reg,
         unsigned int val;
 
         spin_lock_irqsave(&dcr_ind_lock, flags);
-        __mtdcr(base_addr, reg);
-        val = (__mfdcr(base_data) & ~clr) | set;
-        __mtdcr(base_data, val);
+        if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) {
+                mtdcrx(base_addr, reg);
+                val = (mfdcrx(base_data) & ~clr) | set;
+                mtdcrx(base_data, val);
+        } else {
+                __mtdcr(base_addr, reg);
+                val = (__mfdcr(base_data) & ~clr) | set;
+                __mtdcr(base_data, val);
+        }
         spin_unlock_irqrestore(&dcr_ind_lock, flags);
 }
 
diff --git a/arch/powerpc/include/asm/dcr.h b/arch/powerpc/include/asm/dcr.h
index d13fb68bb5c0..9d6851cfb841 100644
--- a/arch/powerpc/include/asm/dcr.h
+++ b/arch/powerpc/include/asm/dcr.h
@@ -68,9 +68,9 @@ typedef dcr_host_mmio_t dcr_host_t;
  * additional helpers to read the DCR * base from the device-tree
  */
 struct device_node;
-extern unsigned int dcr_resource_start(struct device_node *np,
+extern unsigned int dcr_resource_start(const struct device_node *np,
                                        unsigned int index);
-extern unsigned int dcr_resource_len(struct device_node *np,
+extern unsigned int dcr_resource_len(const struct device_node *np,
                                      unsigned int index);
 #endif /* CONFIG_PPC_DCR */
 #endif /* __ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index dfd504caccc1..7d2277cef09a 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -18,4 +18,16 @@ struct dev_archdata {
         void                    *dma_data;
 };
 
+static inline void dev_archdata_set_node(struct dev_archdata *ad,
+                                         struct device_node *np)
+{
+        ad->of_node = np;
+}
+
+static inline struct device_node *
+dev_archdata_get_node(const struct dev_archdata *ad)
+{
+        return ad->of_node;
+}
+
 #endif /* _ASM_POWERPC_DEVICE_H */
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index fddb229bd74f..86cef7ddc8d5 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -60,12 +60,6 @@ struct dma_mapping_ops {
                                 dma_addr_t *dma_handle, gfp_t flag);
         void            (*free_coherent)(struct device *dev, size_t size,
                                 void *vaddr, dma_addr_t dma_handle);
-        dma_addr_t      (*map_single)(struct device *dev, void *ptr,
-                                size_t size, enum dma_data_direction direction,
-                                struct dma_attrs *attrs);
-        void            (*unmap_single)(struct device *dev, dma_addr_t dma_addr,
-                                size_t size, enum dma_data_direction direction,
-                                struct dma_attrs *attrs);
         int             (*map_sg)(struct device *dev, struct scatterlist *sg,
                                 int nents, enum dma_data_direction direction,
                                 struct dma_attrs *attrs);
@@ -82,6 +76,22 @@ struct dma_mapping_ops {
                                 dma_addr_t dma_address, size_t size,
                                 enum dma_data_direction direction,
                                 struct dma_attrs *attrs);
+#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
+        void            (*sync_single_range_for_cpu)(struct device *hwdev,
+                                dma_addr_t dma_handle, unsigned long offset,
+                                size_t size,
+                                enum dma_data_direction direction);
+        void            (*sync_single_range_for_device)(struct device *hwdev,
+                                dma_addr_t dma_handle, unsigned long offset,
+                                size_t size,
+                                enum dma_data_direction direction);
+        void            (*sync_sg_for_cpu)(struct device *hwdev,
+                                struct scatterlist *sg, int nelems,
+                                enum dma_data_direction direction);
+        void            (*sync_sg_for_device)(struct device *hwdev,
+                                struct scatterlist *sg, int nelems,
+                                enum dma_data_direction direction);
+#endif
 };
 
 /*
@@ -149,10 +159,9 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask)
 }
 
 /*
- * TODO: map_/unmap_single will ideally go away, to be completely
- * replaced by map/unmap_page.   Until then, we allow dma_ops to have
- * one or the other, or both by checking to see if the specific
- * function requested exists; and if not, falling back on the other set.
+ * map_/unmap_single actually call through to map/unmap_page now that all the
+ * dma_mapping_ops have been converted over. We just have to get the page and
+ * offset to pass through to map_page
  */
 static inline dma_addr_t dma_map_single_attrs(struct device *dev,
                                               void *cpu_addr,
@@ -164,10 +173,6 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev,
 
         BUG_ON(!dma_ops);
 
-        if (dma_ops->map_single)
-                return dma_ops->map_single(dev, cpu_addr, size, direction,
-                                           attrs);
-
         return dma_ops->map_page(dev, virt_to_page(cpu_addr),
                                  (unsigned long)cpu_addr % PAGE_SIZE, size,
                                  direction, attrs);
@@ -183,11 +188,6 @@ static inline void dma_unmap_single_attrs(struct device *dev,
 
         BUG_ON(!dma_ops);
 
-        if (dma_ops->unmap_single) {
-                dma_ops->unmap_single(dev, dma_addr, size, direction, attrs);
-                return;
-        }
-
         dma_ops->unmap_page(dev, dma_addr, size, direction, attrs);
 }
 
@@ -201,12 +201,7 @@ static inline dma_addr_t dma_map_page_attrs(struct device *dev,
 
         BUG_ON(!dma_ops);
 
-        if (dma_ops->map_page)
-                return dma_ops->map_page(dev, page, offset, size, direction,
-                                         attrs);
-
-        return dma_ops->map_single(dev, page_address(page) + offset, size,
-                                   direction, attrs);
+        return dma_ops->map_page(dev, page, offset, size, direction, attrs);
 }
 
 static inline void dma_unmap_page_attrs(struct device *dev,
@@ -219,12 +214,7 @@ static inline void dma_unmap_page_attrs(struct device *dev,
 
         BUG_ON(!dma_ops);
 
-        if (dma_ops->unmap_page) {
-                dma_ops->unmap_page(dev, dma_address, size, direction, attrs);
-                return;
-        }
-
-        dma_ops->unmap_single(dev, dma_address, size, direction, attrs);
+        dma_ops->unmap_page(dev, dma_address, size, direction, attrs);
 }
 
 static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
@@ -308,47 +298,107 @@ static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
         dma_unmap_sg_attrs(dev, sg, nhwentries, direction, NULL);
 }
 
+#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
 static inline void dma_sync_single_for_cpu(struct device *dev,
                 dma_addr_t dma_handle, size_t size,
                 enum dma_data_direction direction)
 {
-        BUG_ON(direction == DMA_NONE);
-        __dma_sync(bus_to_virt(dma_handle), size, direction);
+        struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+        BUG_ON(!dma_ops);
+        dma_ops->sync_single_range_for_cpu(dev, dma_handle, 0,
+                                           size, direction);
 }
 
 static inline void dma_sync_single_for_device(struct device *dev,
                 dma_addr_t dma_handle, size_t size,
                 enum dma_data_direction direction)
 {
-        BUG_ON(direction == DMA_NONE);
-        __dma_sync(bus_to_virt(dma_handle), size, direction);
+        struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+        BUG_ON(!dma_ops);
+        dma_ops->sync_single_range_for_device(dev, dma_handle,
+                                              0, size, direction);
 }
 
 static inline void dma_sync_sg_for_cpu(struct device *dev,
                 struct scatterlist *sgl, int nents,
                 enum dma_data_direction direction)
 {
-        struct scatterlist *sg;
-        int i;
+        struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
 
-        BUG_ON(direction == DMA_NONE);
+        BUG_ON(!dma_ops);
+        dma_ops->sync_sg_for_cpu(dev, sgl, nents, direction);
+}
+
+static inline void dma_sync_sg_for_device(struct device *dev,
+                struct scatterlist *sgl, int nents,
+                enum dma_data_direction direction)
+{
+        struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+        BUG_ON(!dma_ops);
+        dma_ops->sync_sg_for_device(dev, sgl, nents, direction);
+}
+
+static inline void dma_sync_single_range_for_cpu(struct device *dev,
+                dma_addr_t dma_handle, unsigned long offset, size_t size,
+                enum dma_data_direction direction)
+{
+        struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
 
-        for_each_sg(sgl, sg, nents, i)
-                __dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
+        BUG_ON(!dma_ops);
+        dma_ops->sync_single_range_for_cpu(dev, dma_handle,
+                                           offset, size, direction);
+}
+
+static inline void dma_sync_single_range_for_device(struct device *dev,
+                dma_addr_t dma_handle, unsigned long offset, size_t size,
+                enum dma_data_direction direction)
+{
+        struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+        BUG_ON(!dma_ops);
+        dma_ops->sync_single_range_for_device(dev, dma_handle, offset,
+                                              size, direction);
+}
+#else /* CONFIG_PPC_NEED_DMA_SYNC_OPS */
+static inline void dma_sync_single_for_cpu(struct device *dev,
+                dma_addr_t dma_handle, size_t size,
+                enum dma_data_direction direction)
+{
+}
+
+static inline void dma_sync_single_for_device(struct device *dev,
+                dma_addr_t dma_handle, size_t size,
+                enum dma_data_direction direction)
+{
+}
+
+static inline void dma_sync_sg_for_cpu(struct device *dev,
+                struct scatterlist *sgl, int nents,
+                enum dma_data_direction direction)
+{
 }
 
 static inline void dma_sync_sg_for_device(struct device *dev,
                 struct scatterlist *sgl, int nents,
                 enum dma_data_direction direction)
 {
-        struct scatterlist *sg;
-        int i;
+}
 
-        BUG_ON(direction == DMA_NONE);
+static inline void dma_sync_single_range_for_cpu(struct device *dev,
+                dma_addr_t dma_handle, unsigned long offset, size_t size,
+                enum dma_data_direction direction)
+{
+}
 
-        for_each_sg(sgl, sg, nents, i)
-                __dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
+static inline void dma_sync_single_range_for_device(struct device *dev,
+                dma_addr_t dma_handle, unsigned long offset, size_t size,
+                enum dma_data_direction direction)
+{
 }
+#endif
 
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
@@ -382,22 +432,6 @@ static inline int dma_get_cache_alignment(void)
 #endif
 }
 
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-                dma_addr_t dma_handle, unsigned long offset, size_t size,
-                enum dma_data_direction direction)
-{
-        /* just sync everything for now */
-        dma_sync_single_for_cpu(dev, dma_handle, offset + size, direction);
-}
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
-                dma_addr_t dma_handle, unsigned long offset, size_t size,
-                enum dma_data_direction direction)
-{
-        /* just sync everything for now */
-        dma_sync_single_for_device(dev, dma_handle, offset + size, direction);
-}
-
 static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
                 enum dma_data_direction direction)
 {
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index b886bec67016..66ea9b8b95c5 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -17,8 +17,8 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#ifndef _PPC64_EEH_H
-#define _PPC64_EEH_H
+#ifndef _POWERPC_EEH_H
+#define _POWERPC_EEH_H
 #ifdef __KERNEL__
 
 #include <linux/init.h>
@@ -110,6 +110,7 @@ static inline void eeh_remove_bus_device(struct pci_dev *dev) { }
 #define EEH_IO_ERROR_VALUE(size) (-1UL)
 #endif /* CONFIG_EEH */
 
+#ifdef CONFIG_PPC64
 /*
  * MMIO read/write operations with EEH support.
  */
@@ -207,5 +208,6 @@ static inline void eeh_readsl(const volatile void __iomem *addr, void * buf,
                 eeh_check_failure(addr, *(u32*)buf);
 }
 
+#endif /* CONFIG_PPC64 */
 #endif /* __KERNEL__ */
-#endif /* _PPC64_EEH_H */
+#endif /* _POWERPC_EEH_H */
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index a1029967620b..e4094a5cb05b 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -81,6 +81,36 @@ label##5:					       	\
 #define ALT_FTR_SECTION_END_IFCLR(msk)  \
         ALT_FTR_SECTION_END_NESTED_IFCLR(msk, 97)
 
+/* MMU feature dependent sections */
+#define BEGIN_MMU_FTR_SECTION_NESTED(label)     START_FTR_SECTION(label)
+#define BEGIN_MMU_FTR_SECTION                   START_FTR_SECTION(97)
+
+#define END_MMU_FTR_SECTION_NESTED(msk, val, label)             \
+        FTR_SECTION_ELSE_NESTED(label)                          \
+        MAKE_FTR_SECTION_ENTRY(msk, val, label, __mmu_ftr_fixup)
+
+#define END_MMU_FTR_SECTION(msk, val)           \
+        END_MMU_FTR_SECTION_NESTED(msk, val, 97)
+
+#define END_MMU_FTR_SECTION_IFSET(msk)  END_MMU_FTR_SECTION((msk), (msk))
+#define END_MMU_FTR_SECTION_IFCLR(msk)  END_MMU_FTR_SECTION((msk), 0)
+
+/* MMU feature sections with alternatives, use BEGIN_FTR_SECTION to start */
+#define MMU_FTR_SECTION_ELSE_NESTED(label)      FTR_SECTION_ELSE_NESTED(label)
+#define MMU_FTR_SECTION_ELSE    MMU_FTR_SECTION_ELSE_NESTED(97)
+#define ALT_MMU_FTR_SECTION_END_NESTED(msk, val, label) \
+        MAKE_FTR_SECTION_ENTRY(msk, val, label, __mmu_ftr_fixup)
+#define ALT_MMU_FTR_SECTION_END_NESTED_IFSET(msk, label)        \
+        ALT_MMU_FTR_SECTION_END_NESTED(msk, msk, label)
+#define ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(msk, label)        \
+        ALT_MMU_FTR_SECTION_END_NESTED(msk, 0, label)
+#define ALT_MMU_FTR_SECTION_END(msk, val)       \
+        ALT_MMU_FTR_SECTION_END_NESTED(msk, val, 97)
+#define ALT_MMU_FTR_SECTION_END_IFSET(msk)      \
+        ALT_MMU_FTR_SECTION_END_NESTED_IFSET(msk, 97)
+#define ALT_MMU_FTR_SECTION_END_IFCLR(msk)      \
+        ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(msk, 97)
+
 /* Firmware feature dependent sections */
 #define BEGIN_FW_FTR_SECTION_NESTED(label)      START_FTR_SECTION(label)
 #define BEGIN_FW_FTR_SECTION                    START_FTR_SECTION(97)
diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h
index 91c589520c0a..04e4a620952e 100644
--- a/arch/powerpc/include/asm/highmem.h
+++ b/arch/powerpc/include/asm/highmem.h
@@ -38,9 +38,24 @@ extern pte_t *pkmap_page_table;
  * easily, subsequent pte tables have to be allocated in one physical
  * chunk of RAM.
  */
-#define LAST_PKMAP      (1 << PTE_SHIFT)
-#define LAST_PKMAP_MASK (LAST_PKMAP-1)
+/*
+ * We use one full pte table with 4K pages. And with 16K/64K pages pte
+ * table covers enough memory (32MB and 512MB resp.) that both FIXMAP
+ * and PKMAP can be placed in single pte table. We use 1024 pages for
+ * PKMAP in case of 16K/64K pages.
+ */
+#ifdef CONFIG_PPC_4K_PAGES
+#define PKMAP_ORDER     PTE_SHIFT
+#else
+#define PKMAP_ORDER     10
+#endif
+#define LAST_PKMAP      (1 << PKMAP_ORDER)
+#ifndef CONFIG_PPC_4K_PAGES
+#define PKMAP_BASE      (FIXADDR_START - PAGE_SIZE*(LAST_PKMAP + 1))
+#else
 #define PKMAP_BASE      ((FIXADDR_START - PAGE_SIZE*(LAST_PKMAP + 1)) & PMD_MASK)
+#endif
+#define LAST_PKMAP_MASK (LAST_PKMAP-1)
 #define PKMAP_NR(virt)  ((virt-PKMAP_BASE) >> PAGE_SHIFT)
 #define PKMAP_ADDR(nr)  (PKMAP_BASE + ((nr) << PAGE_SHIFT))
 
@@ -85,7 +100,7 @@ static inline void *kmap_atomic_prot(struct page *page, enum km_type type, pgpro
         BUG_ON(!pte_none(*(kmap_pte-idx)));
 #endif
         __set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot));
-        flush_tlb_page(NULL, vaddr);
+        local_flush_tlb_page(NULL, vaddr);
 
         return (void*) vaddr;
 }
@@ -113,7 +128,7 @@ static inline void kunmap_atomic(void *kvaddr, enum km_type type)
          * this pte without first remap it
          */
         pte_clear(&init_mm, vaddr, kmap_pte-idx);
-        flush_tlb_page(NULL, vaddr);
+        local_flush_tlb_page(NULL, vaddr);
 #endif
         pagefault_enable();
 }
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 08266d2728b3..494cd8b0a278 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -713,13 +713,6 @@ static inline void * phys_to_virt(unsigned long address)
  */
 #define page_to_phys(page)      ((phys_addr_t)page_to_pfn(page) << PAGE_SHIFT)
 
-/* We do NOT want virtual merging, it would put too much pressure on
- * our iommu allocator. Instead, we want drivers to be smart enough
- * to coalesce sglists that happen to have been mapped in a contiguous
- * way by the iommu
- */
-#define BIO_VMERGE_BOUNDARY     0
-
 /*
  * 32 bits still uses virt_to_bus() for it's implementation of DMA
  * mappings se we have to keep it defined here. We also have some old
diff --git a/arch/powerpc/include/asm/kdump.h b/arch/powerpc/include/asm/kdump.h
index b07ebb9784d3..5ebfe5d3c61f 100644
--- a/arch/powerpc/include/asm/kdump.h
+++ b/arch/powerpc/include/asm/kdump.h
@@ -1,6 +1,8 @@
 #ifndef _PPC64_KDUMP_H
 #define _PPC64_KDUMP_H
 
+#include <asm/page.h>
+
 /* Kdump kernel runs at 32 MB, change at your peril. */
 #define KDUMP_KERNELBASE        0x2000000
 
@@ -11,8 +13,19 @@
 
 #ifdef CONFIG_CRASH_DUMP
 
+/*
+ * On PPC64 translation is disabled during trampoline setup, so we use
+ * physical addresses. Though on PPC32 translation is already enabled,
+ * so we can't do the same. Luckily create_trampoline() creates relative
+ * branches, so we can just add the PAGE_OFFSET and don't worry about it.
+ */
+#ifdef __powerpc64__
 #define KDUMP_TRAMPOLINE_START  0x0100
 #define KDUMP_TRAMPOLINE_END    0x3000
+#else
+#define KDUMP_TRAMPOLINE_START  (0x0100 + PAGE_OFFSET)
+#define KDUMP_TRAMPOLINE_END    (0x3000 + PAGE_OFFSET)
+#endif /* __powerpc64__ */
 
 #define KDUMP_MIN_TCE_ENTRIES   2048
 
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 3736d9b33289..6dbffc981702 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -33,12 +33,12 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
+#include <asm/reg.h>
 
 typedef void (*crash_shutdown_t)(void);
 
 #ifdef CONFIG_KEXEC
 
-#ifdef __powerpc64__
 /*
  * This function is responsible for capturing register states if coming
  * via panic or invoking dump using sysrq-trigger.
@@ -48,6 +48,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 {
         if (oldregs)
                 memcpy(newregs, oldregs, sizeof(*newregs));
+#ifdef __powerpc64__
         else {
                 /* FIXME Merge this with xmon_save_regs ?? */
                 unsigned long tmp1, tmp2;
@@ -100,15 +101,11 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
                         : "b" (newregs)
                         : "memory");
         }
-}
 #else
-/*
- * Provide a dummy definition to avoid build failures. Will remain
- * empty till crash dump support is enabled.
- */
-static inline void crash_setup_regs(struct pt_regs *newregs,
-                                        struct pt_regs *oldregs) { }
-#endif /* !__powerpc64 __ */
+        else
+                ppc_save_regs(newregs);
+#endif /* __powerpc64__ */
+}
 
 extern void kexec_smp_wait(void);       /* get and clear naca physid, wait for
                                           master to copy new code to 0 */
diff --git a/arch/powerpc/include/asm/local.h b/arch/powerpc/include/asm/local.h
index 612d83276653..84b457a3c1bc 100644
--- a/arch/powerpc/include/asm/local.h
+++ b/arch/powerpc/include/asm/local.h
@@ -67,7 +67,7 @@ static __inline__ long local_inc_return(local_t *l)
         bne-    1b"
         : "=&r" (t)
         : "r" (&(l->a.counter))
-        : "cc", "memory");
+        : "cc", "xer", "memory");
 
         return t;
 }
@@ -94,7 +94,7 @@ static __inline__ long local_dec_return(local_t *l)
         bne-    1b"
         : "=&r" (t)
         : "r" (&(l->a.counter))
-        : "cc", "memory");
+        : "cc", "xer", "memory");
 
         return t;
 }
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 2fe268b10333..25aaa97facd8 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -133,7 +133,8 @@ struct lppaca {
 //=============================================================================
 // CACHE_LINE_4-5 0x0180 - 0x027F Contains PMC interrupt data
 //=============================================================================
-        u8      pmc_save_area[256];     // PMC interrupt Area           x00-xFF
+        u32     page_ins;                       // CMO Hint - # page ins by OS  x00-x04
+        u8      pmc_save_area[252];     // PMC interrupt Area           x04-xFF
 } __attribute__((__aligned__(0x400)));
 
 extern struct lppaca lppaca[];
diff --git a/arch/powerpc/include/asm/mmu-40x.h b/arch/powerpc/include/asm/mmu-40x.h
index 3d108676584c..776f415a36aa 100644
--- a/arch/powerpc/include/asm/mmu-40x.h
+++ b/arch/powerpc/include/asm/mmu-40x.h
@@ -54,8 +54,9 @@
 #ifndef __ASSEMBLY__
 
 typedef struct {
-        unsigned long id;
-        unsigned long vdso_base;
+        unsigned int    id;
+        unsigned int    active;
+        unsigned long   vdso_base;
 } mm_context_t;
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/mmu-44x.h b/arch/powerpc/include/asm/mmu-44x.h
index a825524c981a..8a97cfb08b7e 100644
--- a/arch/powerpc/include/asm/mmu-44x.h
+++ b/arch/powerpc/include/asm/mmu-44x.h
@@ -4,6 +4,8 @@
  * PPC440 support
  */
 
+#include <asm/page.h>
+
 #define PPC44x_MMUCR_TID        0x000000ff
 #define PPC44x_MMUCR_STS        0x00010000
 
@@ -56,8 +58,9 @@
 extern unsigned int tlb_44x_hwater;
 
 typedef struct {
-        unsigned long id;
-        unsigned long vdso_base;
+        unsigned int    id;
+        unsigned int    active;
+        unsigned long   vdso_base;
 } mm_context_t;
 
 #endif /* !__ASSEMBLY__ */
@@ -73,4 +76,19 @@ typedef struct {
 /* Size of the TLBs used for pinning in lowmem */
 #define PPC_PIN_SIZE    (1 << 28)       /* 256M */
 
+#if (PAGE_SHIFT == 12)
+#define PPC44x_TLBE_SIZE        PPC44x_TLB_4K
+#elif (PAGE_SHIFT == 14)
+#define PPC44x_TLBE_SIZE        PPC44x_TLB_16K
+#elif (PAGE_SHIFT == 16)
+#define PPC44x_TLBE_SIZE        PPC44x_TLB_64K
+#else
+#error "Unsupported PAGE_SIZE"
+#endif
+
+#define PPC44x_PGD_OFF_SHIFT    (32 - PGDIR_SHIFT + PGD_T_LOG2)
+#define PPC44x_PGD_OFF_MASK_BIT (PGDIR_SHIFT - PGD_T_LOG2)
+#define PPC44x_PTE_ADD_SHIFT    (32 - PGDIR_SHIFT + PTE_SHIFT + PTE_T_LOG2)
+#define PPC44x_PTE_ADD_MASK_BIT (32 - PTE_T_LOG2 - PTE_SHIFT)
+
 #endif /* _ASM_POWERPC_MMU_44X_H_ */
diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h
index 9db877eb88db..07865a357848 100644
--- a/arch/powerpc/include/asm/mmu-8xx.h
+++ b/arch/powerpc/include/asm/mmu-8xx.h
@@ -137,7 +137,8 @@
 
 #ifndef __ASSEMBLY__
 typedef struct {
-        unsigned long id;
+        unsigned int id;
+        unsigned int active;
         unsigned long vdso_base;
 } mm_context_t;
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/mmu-fsl-booke.h b/arch/powerpc/include/asm/mmu-fsl-booke.h
index 925d93cf64d8..3f941c0f7e8e 100644
--- a/arch/powerpc/include/asm/mmu-fsl-booke.h
+++ b/arch/powerpc/include/asm/mmu-fsl-booke.h
@@ -40,6 +40,8 @@
 #define MAS2_M          0x00000004
 #define MAS2_G          0x00000002
 #define MAS2_E          0x00000001
+#define MAS2_EPN_MASK(size)             (~0 << (2*(size) + 10))
+#define MAS2_VAL(addr, size, flags)     ((addr) & MAS2_EPN_MASK(size) | (flags))
 
 #define MAS3_RPN        0xFFFFF000
 #define MAS3_U0         0x00000200
@@ -74,8 +76,9 @@
 #ifndef __ASSEMBLY__
 
 typedef struct {
-        unsigned long id;
-        unsigned long vdso_base;
+        unsigned int    id;
+        unsigned int    active;
+        unsigned long   vdso_base;
 } mm_context_t;
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 4c0e1b4f975c..6e7639911318 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -2,6 +2,63 @@
 #define _ASM_POWERPC_MMU_H_
 #ifdef __KERNEL__
 
+#include <asm/asm-compat.h>
+#include <asm/feature-fixups.h>
+
+/*
+ * MMU features bit definitions
+ */
+
+/*
+ * First half is MMU families
+ */
+#define MMU_FTR_HPTE_TABLE              ASM_CONST(0x00000001)
+#define MMU_FTR_TYPE_8xx                ASM_CONST(0x00000002)
+#define MMU_FTR_TYPE_40x                ASM_CONST(0x00000004)
+#define MMU_FTR_TYPE_44x                ASM_CONST(0x00000008)
+#define MMU_FTR_TYPE_FSL_E              ASM_CONST(0x00000010)
+
+/*
+ * This is individual features
+ */
+
+/* Enable use of high BAT registers */
+#define MMU_FTR_USE_HIGH_BATS           ASM_CONST(0x00010000)
+
+/* Enable >32-bit physical addresses on 32-bit processor, only used
+ * by CONFIG_6xx currently as BookE supports that from day 1
+ */
+#define MMU_FTR_BIG_PHYS                ASM_CONST(0x00020000)
+
+/* Enable use of broadcast TLB invalidations. We don't always set it
+ * on processors that support it due to other constraints with the
+ * use of such invalidations
+ */
+#define MMU_FTR_USE_TLBIVAX_BCAST       ASM_CONST(0x00040000)
+
+/* Enable use of tlbilx invalidate-by-PID variant.
+ */
+#define MMU_FTR_USE_TLBILX_PID          ASM_CONST(0x00080000)
+
+/* This indicates that the processor cannot handle multiple outstanding
+ * broadcast tlbivax or tlbsync. This makes the code use a spinlock
+ * around such invalidate forms.
+ */
+#define MMU_FTR_LOCK_BCAST_INVAL        ASM_CONST(0x00100000)
+
+#ifndef __ASSEMBLY__
+#include <asm/cputable.h>
+
+static inline int mmu_has_feature(unsigned long feature)
+{
+        return (cur_cpu_spec->mmu_features & feature);
+}
+
+extern unsigned int __start___mmu_ftr_fixup, __stop___mmu_ftr_fixup;
+
+#endif /* !__ASSEMBLY__ */
+
+
 #ifdef CONFIG_PPC64
 /* 64-bit classic hash table MMU */
 #  include <asm/mmu-hash64.h>
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 6b993ef452ff..ab4f19263c42 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -2,237 +2,26 @@
 #define __ASM_POWERPC_MMU_CONTEXT_H
 #ifdef __KERNEL__
 
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
 #include <asm/mmu.h>    
 #include <asm/cputable.h>
 #include <asm-generic/mm_hooks.h>
-
-#ifndef CONFIG_PPC64
-#include <asm/atomic.h>
-#include <linux/bitops.h>
-
-/*
- * On 32-bit PowerPC 6xx/7xx/7xxx CPUs, we use a set of 16 VSIDs
- * (virtual segment identifiers) for each context.  Although the
- * hardware supports 24-bit VSIDs, and thus >1 million contexts,
- * we only use 32,768 of them.  That is ample, since there can be
- * at most around 30,000 tasks in the system anyway, and it means
- * that we can use a bitmap to indicate which contexts are in use.
- * Using a bitmap means that we entirely avoid all of the problems
- * that we used to have when the context number overflowed,
- * particularly on SMP systems.
- *  -- paulus.
- */
-
-/*
- * This function defines the mapping from contexts to VSIDs (virtual
- * segment IDs).  We use a skew on both the context and the high 4 bits
- * of the 32-bit virtual address (the "effective segment ID") in order
- * to spread out the entries in the MMU hash table.  Note, if this
- * function is changed then arch/ppc/mm/hashtable.S will have to be
- * changed to correspond.
- */
-#define CTX_TO_VSID(ctx, va)    (((ctx) * (897 * 16) + ((va) >> 28) * 0x111) \
-                                 & 0xffffff)
-
-/*
-   The MPC8xx has only 16 contexts.  We rotate through them on each
-   task switch.  A better way would be to keep track of tasks that
-   own contexts, and implement an LRU usage.  That way very active
-   tasks don't always have to pay the TLB reload overhead.  The
-   kernel pages are mapped shared, so the kernel can run on behalf
-   of any task that makes a kernel entry.  Shared does not mean they
-   are not protected, just that the ASID comparison is not performed.
-        -- Dan
-
-   The IBM4xx has 256 contexts, so we can just rotate through these
-   as a way of "switching" contexts.  If the TID of the TLB is zero,
-   the PID/TID comparison is disabled, so we can use a TID of zero
-   to represent all kernel pages as shared among all contexts.
-        -- Dan
- */
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-}
-
-#ifdef CONFIG_8xx
-#define NO_CONTEXT              16
-#define LAST_CONTEXT            15
-#define FIRST_CONTEXT           0
-
-#elif defined(CONFIG_4xx)
-#define NO_CONTEXT              256
-#define LAST_CONTEXT            255
-#define FIRST_CONTEXT           1
-
-#elif defined(CONFIG_E200) || defined(CONFIG_E500)
-#define NO_CONTEXT              256
-#define LAST_CONTEXT            255
-#define FIRST_CONTEXT           1
-
-#else
-
-/* PPC 6xx, 7xx CPUs */
-#define NO_CONTEXT              ((unsigned long) -1)
-#define LAST_CONTEXT            32767
-#define FIRST_CONTEXT           1
-#endif
-
-/*
- * Set the current MMU context.
- * On 32-bit PowerPCs (other than the 8xx embedded chips), this is done by
- * loading up the segment registers for the user part of the address space.
- *
- * Since the PGD is immediately available, it is much faster to simply
- * pass this along as a second parameter, which is required for 8xx and
- * can be used for debugging on all processors (if you happen to have
- * an Abatron).
- */
-extern void set_context(unsigned long contextid, pgd_t *pgd);
-
-/*
- * Bitmap of contexts in use.
- * The size of this bitmap is LAST_CONTEXT + 1 bits.
- */
-extern unsigned long context_map[];
-
-/*
- * This caches the next context number that we expect to be free.
- * Its use is an optimization only, we can't rely on this context
- * number to be free, but it usually will be.
- */
-extern unsigned long next_mmu_context;
-
-/*
- * If we don't have sufficient contexts to give one to every task
- * that could be in the system, we need to be able to steal contexts.
- * These variables support that.
- */
-#if LAST_CONTEXT < 30000
-#define FEW_CONTEXTS    1
-extern atomic_t nr_free_contexts;
-extern struct mm_struct *context_mm[LAST_CONTEXT+1];
-extern void steal_context(void);
-#endif
-
-/*
- * Get a new mmu context for the address space described by `mm'.
- */
-static inline void get_mmu_context(struct mm_struct *mm)
-{
-        unsigned long ctx;
-
-        if (mm->context.id != NO_CONTEXT)
-                return;
-#ifdef FEW_CONTEXTS
-        while (atomic_dec_if_positive(&nr_free_contexts) < 0)
-                steal_context();
-#endif
-        ctx = next_mmu_context;
-        while (test_and_set_bit(ctx, context_map)) {
-                ctx = find_next_zero_bit(context_map, LAST_CONTEXT+1, ctx);
-                if (ctx > LAST_CONTEXT)
-                        ctx = 0;
-        }
-        next_mmu_context = (ctx + 1) & LAST_CONTEXT;
-        mm->context.id = ctx;
-#ifdef FEW_CONTEXTS
-        context_mm[ctx] = mm;
-#endif
-}
-
-/*
- * Set up the context for a new address space.
- */
-static inline int init_new_context(struct task_struct *t, struct mm_struct *mm)
-{
-        mm->context.id = NO_CONTEXT;
-        return 0;
-}
-
-/*
- * We're finished using the context for an address space.
- */
-static inline void destroy_context(struct mm_struct *mm)
-{
-        preempt_disable();
-        if (mm->context.id != NO_CONTEXT) {
-                clear_bit(mm->context.id, context_map);
-                mm->context.id = NO_CONTEXT;
-#ifdef FEW_CONTEXTS
-                atomic_inc(&nr_free_contexts);
-#endif
-        }
-        preempt_enable();
-}
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
-                             struct task_struct *tsk)
-{
-#ifdef CONFIG_ALTIVEC
-        if (cpu_has_feature(CPU_FTR_ALTIVEC))
-        asm volatile ("dssall;\n"
-#ifndef CONFIG_POWER4
-         "sync;\n" /* G4 needs a sync here, G5 apparently not */
-#endif
-         : : );
-#endif /* CONFIG_ALTIVEC */
-
-        tsk->thread.pgdir = next->pgd;
-
-        /* No need to flush userspace segments if the mm doesnt change */
-        if (prev == next)
-                return;
-
-        /* Setup new userspace context */
-        get_mmu_context(next);
-        set_context(next->context.id, next->pgd);
-}
-
-#define deactivate_mm(tsk,mm)   do { } while (0)
+#include <asm/cputhreads.h>
 
 /*
- * After we have set current->mm to a new value, this activates
- * the context for the new mm so we see the new mappings.
+ * Most if the context management is out of line
  */
-#define activate_mm(active_mm, mm)   switch_mm(active_mm, mm, current)
-
 extern void mmu_context_init(void);
-
-
-#else
-
-#include <linux/kernel.h>       
-#include <linux/mm.h>   
-#include <linux/sched.h>
-
-/*
- * Copyright (C) 2001 PPC 64 Team, IBM Corp
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-static inline void enter_lazy_tlb(struct mm_struct *mm,
-                                  struct task_struct *tsk)
-{
-}
-
-/*
- * The proto-VSID space has 2^35 - 1 segments available for user mappings.
- * Each segment contains 2^28 bytes.  Each context maps 2^44 bytes,
- * so we can support 2^19-1 contexts (19 == 35 + 28 - 44).
- */
-#define NO_CONTEXT      0
-#define MAX_CONTEXT     ((1UL << 19) - 1)
-
 extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 extern void destroy_context(struct mm_struct *mm);
 
+extern void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next);
 extern void switch_stab(struct task_struct *tsk, struct mm_struct *mm);
 extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm);
+extern void set_context(unsigned long id, pgd_t *pgd);
 
 /*
  * switch_mm is the entry point called from the architecture independent
@@ -241,22 +30,39 @@ extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm);
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
                              struct task_struct *tsk)
 {
-        if (!cpu_isset(smp_processor_id(), next->cpu_vm_mask))
-                cpu_set(smp_processor_id(), next->cpu_vm_mask);
+        /* Mark this context has been used on the new CPU */
+        cpu_set(smp_processor_id(), next->cpu_vm_mask);
+
+        /* 32-bit keeps track of the current PGDIR in the thread struct */
+#ifdef CONFIG_PPC32
+        tsk->thread.pgdir = next->pgd;
+#endif /* CONFIG_PPC32 */
 
-        /* No need to flush userspace segments if the mm doesnt change */
+        /* Nothing else to do if we aren't actually switching */
         if (prev == next)
                 return;
 
+        /* We must stop all altivec streams before changing the HW
+         * context
+         */
 #ifdef CONFIG_ALTIVEC
         if (cpu_has_feature(CPU_FTR_ALTIVEC))
                 asm volatile ("dssall");
 #endif /* CONFIG_ALTIVEC */
 
+        /* The actual HW switching method differs between the various
+         * sub architectures.
+         */
+#ifdef CONFIG_PPC_STD_MMU_64
         if (cpu_has_feature(CPU_FTR_SLB))
                 switch_slb(tsk, next);
         else
                 switch_stab(tsk, next);
+#else
+        /* Out of line for now */
+        switch_mmu_context(prev, next);
+#endif
+
 }
 
 #define deactivate_mm(tsk,mm)   do { } while (0)
@@ -274,6 +80,11 @@ static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
         local_irq_restore(flags);
 }
 
-#endif /* CONFIG_PPC64 */
+/* We don't currently use enter_lazy_tlb() for anything */
+static inline void enter_lazy_tlb(struct mm_struct *mm,
+                                  struct task_struct *tsk)
+{
+}
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_POWERPC_MMU_CONTEXT_H */
diff --git a/arch/powerpc/include/asm/mpc52xx.h b/arch/powerpc/include/asm/mpc52xx.h
index 81ef10b6b672..81a23932a160 100644
--- a/arch/powerpc/include/asm/mpc52xx.h
+++ b/arch/powerpc/include/asm/mpc52xx.h
@@ -239,6 +239,25 @@ struct mpc52xx_cdm {
         u16 mclken_div_psc6;    /* CDM + 0x36  reg13 byte2,3 */
 };
 
+/* Interrupt controller Register set */
+struct mpc52xx_intr {
+        u32 per_mask;           /* INTR + 0x00 */
+        u32 per_pri1;           /* INTR + 0x04 */
+        u32 per_pri2;           /* INTR + 0x08 */
+        u32 per_pri3;           /* INTR + 0x0c */
+        u32 ctrl;               /* INTR + 0x10 */
+        u32 main_mask;          /* INTR + 0x14 */
+        u32 main_pri1;          /* INTR + 0x18 */
+        u32 main_pri2;          /* INTR + 0x1c */
+        u32 reserved1;          /* INTR + 0x20 */
+        u32 enc_status;         /* INTR + 0x24 */
+        u32 crit_status;        /* INTR + 0x28 */
+        u32 main_status;        /* INTR + 0x2c */
+        u32 per_status;         /* INTR + 0x30 */
+        u32 reserved2;          /* INTR + 0x34 */
+        u32 per_error;          /* INTR + 0x38 */
+};
+
 #endif /* __ASSEMBLY__ */
 
 
diff --git a/arch/powerpc/include/asm/mpc52xx_psc.h b/arch/powerpc/include/asm/mpc52xx_psc.h
index 8917ed630565..a218da6bec7c 100644
--- a/arch/powerpc/include/asm/mpc52xx_psc.h
+++ b/arch/powerpc/include/asm/mpc52xx_psc.h
@@ -68,12 +68,20 @@
 #define MPC52xx_PSC_IMR_ORERR           0x1000
 #define MPC52xx_PSC_IMR_IPC             0x8000
 
-/* PSC input port change bit */
+/* PSC input port change bits */
 #define MPC52xx_PSC_CTS                 0x01
 #define MPC52xx_PSC_DCD                 0x02
 #define MPC52xx_PSC_D_CTS               0x10
 #define MPC52xx_PSC_D_DCD               0x20
 
+/* PSC acr bits */
+#define MPC52xx_PSC_IEC_CTS             0x01
+#define MPC52xx_PSC_IEC_DCD             0x02
+
+/* PSC output port bits */
+#define MPC52xx_PSC_OP_RTS              0x01
+#define MPC52xx_PSC_OP_RES              0x02
+
 /* PSC mode fields */
 #define MPC52xx_PSC_MODE_5_BITS                 0x00
 #define MPC52xx_PSC_MODE_6_BITS                 0x01
@@ -91,6 +99,7 @@
 #define MPC52xx_PSC_MODE_ONE_STOP_5_BITS        0x00
 #define MPC52xx_PSC_MODE_ONE_STOP               0x07
 #define MPC52xx_PSC_MODE_TWO_STOP               0x0f
+#define MPC52xx_PSC_MODE_TXCTS                  0x10
 
 #define MPC52xx_PSC_RFNUM_MASK  0x01ff
 
diff --git a/arch/powerpc/include/asm/mutex.h b/arch/powerpc/include/asm/mutex.h
index 458c1f7fbc18..dabc01c727b8 100644
--- a/arch/powerpc/include/asm/mutex.h
+++ b/arch/powerpc/include/asm/mutex.h
@@ -1,9 +1,134 @@
 /*
- * Pull in the generic implementation for the mutex fastpath.
+ * Optimised mutex implementation of include/asm-generic/mutex-dec.h algorithm
+ */
+#ifndef _ASM_POWERPC_MUTEX_H
+#define _ASM_POWERPC_MUTEX_H
+
+static inline int __mutex_cmpxchg_lock(atomic_t *v, int old, int new)
+{
+        int t;
+
+        __asm__ __volatile__ (
+"1:     lwarx   %0,0,%1         # mutex trylock\n\
+        cmpw    0,%0,%2\n\
+        bne-    2f\n"
+        PPC405_ERR77(0,%1)
+"       stwcx.  %3,0,%1\n\
+        bne-    1b"
+        ISYNC_ON_SMP
+        "\n\
+2:"
+        : "=&r" (t)
+        : "r" (&v->counter), "r" (old), "r" (new)
+        : "cc", "memory");
+
+        return t;
+}
+
+static inline int __mutex_dec_return_lock(atomic_t *v)
+{
+        int t;
+
+        __asm__ __volatile__(
+"1:     lwarx   %0,0,%1         # mutex lock\n\
+        addic   %0,%0,-1\n"
+        PPC405_ERR77(0,%1)
+"       stwcx.  %0,0,%1\n\
+        bne-    1b"
+        ISYNC_ON_SMP
+        : "=&r" (t)
+        : "r" (&v->counter)
+        : "cc", "memory");
+
+        return t;
+}
+
+static inline int __mutex_inc_return_unlock(atomic_t *v)
+{
+        int t;
+
+        __asm__ __volatile__(
+        LWSYNC_ON_SMP
+"1:     lwarx   %0,0,%1         # mutex unlock\n\
+        addic   %0,%0,1\n"
+        PPC405_ERR77(0,%1)
+"       stwcx.  %0,0,%1 \n\
+        bne-    1b"
+        : "=&r" (t)
+        : "r" (&v->counter)
+        : "cc", "memory");
+
+        return t;
+}
+
+/**
+ *  __mutex_fastpath_lock - try to take the lock by moving the count
+ *                          from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if
+ * it wasn't 1 originally. This function MUST leave the value lower than
+ * 1 even when the "1" assertion wasn't true.
+ */
+static inline void
+__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+        if (unlikely(__mutex_dec_return_lock(count) < 0))
+                fail_fn(count);
+}
+
+/**
+ *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ *                                 from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if
+ * it wasn't 1 originally. This function returns 0 if the fastpath succeeds,
+ * or anything the slow path function returns.
+ */
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+        if (unlikely(__mutex_dec_return_lock(count) < 0))
+                return fail_fn(count);
+        return 0;
+}
+
+/**
+ *  __mutex_fastpath_unlock - try to promote the count from 0 to 1
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 0
+ *
+ * Try to promote the count from 0 to 1. If it wasn't 0, call <fail_fn>.
+ * In the failure case, this function is allowed to either set the value to
+ * 1, or to set it to a value lower than 1.
+ */
+static inline void
+__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+        if (unlikely(__mutex_inc_return_unlock(count) <= 0))
+                fail_fn(count);
+}
+
+#define __mutex_slowpath_needs_to_unlock()              1
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: fallback function
  *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
+ * Change the count from 1 to 0, and return 1 (success), or if the count
+ * was not 1, then return 0 (failure).
  */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+        if (likely(__mutex_cmpxchg_lock(count, 1, 0) == 1))
+                return 1;
+        return 0;
+}
 
-#include <asm-generic/mutex-dec.h>
+#endif
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index c0b8d4a29a91..197d569f5bd3 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -19,12 +19,15 @@
 #include <asm/kdump.h>
 
 /*
- * On PPC32 page size is 4K. For PPC64 we support either 4K or 64K software
+ * On regular PPC32 page size is 4K (but we support 4K/16K/64K pages
+ * on PPC44x). For PPC64 we support either 4K or 64K software
  * page size. When using 64K pages however, whether we are really supporting
  * 64K pages in HW or not is irrelevant to those definitions.
  */
-#ifdef CONFIG_PPC_64K_PAGES
+#if defined(CONFIG_PPC_64K_PAGES)
 #define PAGE_SHIFT              16
+#elif defined(CONFIG_PPC_16K_PAGES)
+#define PAGE_SHIFT              14
 #else
 #define PAGE_SHIFT              12
 #endif
@@ -151,7 +154,7 @@ typedef struct { pte_basic_t pte; } pte_t;
 /* 64k pages additionally define a bigger "real PTE" type that gathers
  * the "second half" part of the PTE for pseudo 64k pages
  */
-#ifdef CONFIG_PPC_64K_PAGES
+#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
 typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
 #else
 typedef struct { pte_t pte; } real_pte_t;
@@ -191,10 +194,10 @@ typedef pte_basic_t pte_t;
 #define pte_val(x)      (x)
 #define __pte(x)        (x)
 
-#ifdef CONFIG_PPC_64K_PAGES
+#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
 typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
 #else
-typedef unsigned long real_pte_t;
+typedef pte_t real_pte_t;
 #endif
 
 
diff --git a/arch/powerpc/include/asm/page_32.h b/arch/powerpc/include/asm/page_32.h
index d77072a32cc6..1458d9500381 100644
--- a/arch/powerpc/include/asm/page_32.h
+++ b/arch/powerpc/include/asm/page_32.h
@@ -19,6 +19,8 @@
 #define PTE_FLAGS_OFFSET        0
 #endif
 
+#define PTE_SHIFT       (PAGE_SHIFT - PTE_T_LOG2)       /* full page */
+
 #ifndef __ASSEMBLY__
 /*
  * The basic type of a PTE - 64 bits for those CPUs with > 32 bit
@@ -26,10 +28,8 @@
  */
 #ifdef CONFIG_PTE_64BIT
 typedef unsigned long long pte_basic_t;
-#define PTE_SHIFT       (PAGE_SHIFT - 3)        /* 512 ptes per page */
 #else
 typedef unsigned long pte_basic_t;
-#define PTE_SHIFT       (PAGE_SHIFT - 2)        /* 1024 ptes per page */
 #endif
 
 struct page;
@@ -39,6 +39,9 @@ extern void copy_page(void *to, void *from);
 
 #include <asm-generic/page.h>
 
+#define PGD_T_LOG2      (__builtin_ffs(sizeof(pgd_t)) - 1)
+#define PTE_T_LOG2      (__builtin_ffs(sizeof(pte_t)) - 1)
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_PAGE_32_H */
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 9047af7baa69..84007afabdb5 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -13,7 +13,6 @@
 
 struct device_node;
 
-extern unsigned int ppc_pci_flags;
 enum {
         /* Force re-assigning all resources (ignore firmware
          * setup completely)
@@ -36,6 +35,31 @@ enum {
         /* ... except for domain 0 */
         PPC_PCI_COMPAT_DOMAIN_0         = 0x00000020,
 };
+#ifdef CONFIG_PCI
+extern unsigned int ppc_pci_flags;
+
+static inline void ppc_pci_set_flags(int flags)
+{
+        ppc_pci_flags = flags;
+}
+
+static inline void ppc_pci_add_flags(int flags)
+{
+        ppc_pci_flags |= flags;
+}
+
+static inline int ppc_pci_has_flag(int flag)
+{
+        return (ppc_pci_flags & flag);
+}
+#else
+static inline void ppc_pci_set_flags(int flags) { }
+static inline void ppc_pci_add_flags(int flags) { }
+static inline int ppc_pci_has_flag(int flag)
+{
+        return 0;
+}
+#endif
 
 
 /*
@@ -241,9 +265,6 @@ extern void pcibios_remove_pci_devices(struct pci_bus *bus);
 
 /** Discover new pci devices under this bus, and add them */
 extern void pcibios_add_pci_devices(struct pci_bus *bus);
-extern void pcibios_fixup_new_pci_devices(struct pci_bus *bus);
-
-extern int pcibios_remove_root_bus(struct pci_controller *phb);
 
 static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus)
 {
@@ -290,6 +311,7 @@ extern void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 /* Allocate & free a PCI host bridge structure */
 extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev);
 extern void pcibios_free_controller(struct pci_controller *phb);
+extern void pcibios_setup_phb_resources(struct pci_controller *hose);
 
 #ifdef CONFIG_PCI
 extern unsigned long pci_address_to_pio(phys_addr_t address);
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 57a2a494886b..3548159a1beb 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -38,8 +38,8 @@ struct pci_dev;
  * Set this to 1 if you want the kernel to re-assign all PCI
  * bus numbers (don't do that on ppc64 yet !)
  */
-#define pcibios_assign_all_busses()     (ppc_pci_flags & \
-                                         PPC_PCI_REASSIGN_ALL_BUS)
+#define pcibios_assign_all_busses() \
+        (ppc_pci_has_flag(PPC_PCI_REASSIGN_ALL_BUS))
 #define pcibios_scan_all_fns(a, b)      0
 
 static inline void pcibios_set_master(struct pci_dev *dev)
@@ -204,15 +204,14 @@ static inline struct resource *pcibios_select_root(struct pci_dev *pdev,
         return root;
 }
 
-extern void pcibios_setup_new_device(struct pci_dev *dev);
-
 extern void pcibios_claim_one_bus(struct pci_bus *b);
 
-extern void pcibios_allocate_bus_resources(struct pci_bus *bus);
+extern void pcibios_finish_adding_to_bus(struct pci_bus *bus);
 
 extern void pcibios_resource_survey(void);
 
 extern struct pci_controller *init_phb_dynamic(struct device_node *dn);
+extern int remove_phb_dynamic(struct pci_controller *phb);
 
 extern struct pci_dev *of_create_pci_dev(struct device_node *node,
                                         struct pci_bus *bus, int devfn);
@@ -221,6 +220,7 @@ extern void of_scan_pci_bridge(struct device_node *node,
                                 struct pci_dev *dev);
 
 extern void of_scan_bus(struct device_node *node, struct pci_bus *bus);
+extern void of_rescan_bus(struct device_node *node, struct pci_bus *bus);
 
 extern int pci_read_irq_line(struct pci_dev *dev);
 
@@ -235,9 +235,8 @@ extern void pci_resource_to_user(const struct pci_dev *dev, int bar,
                                  const struct resource *rsrc,
                                  resource_size_t *start, resource_size_t *end);
 
-extern void pcibios_do_bus_setup(struct pci_bus *bus);
-extern void pcibios_fixup_of_probed_bus(struct pci_bus *bus);
-
+extern void pcibios_setup_bus_devices(struct pci_bus *bus);
+extern void pcibios_setup_bus_self(struct pci_bus *bus);
 
 #endif  /* __KERNEL__ */
 #endif /* __ASM_POWERPC_PCI_H */
diff --git a/arch/powerpc/include/asm/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h
index 58c07147b3ea..0815eb40acae 100644
--- a/arch/powerpc/include/asm/pgalloc-32.h
+++ b/arch/powerpc/include/asm/pgalloc-32.h
@@ -3,6 +3,8 @@
 
 #include <linux/threads.h>
 
+#define PTE_NONCACHE_NUM        0  /* dummy for now to share code w/ppc64 */
+
 extern void __bad_pte(pmd_t *pmd);
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
@@ -33,10 +35,13 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
 extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr);
-extern void pte_free_kernel(struct mm_struct *mm, pte_t *pte);
-extern void pte_free(struct mm_struct *mm, pgtable_t pte);
 
-#define __pte_free_tlb(tlb, pte)        pte_free((tlb)->mm, (pte))
+static inline void pgtable_free(pgtable_free_t pgf)
+{
+        void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
+
+        free_page((unsigned long)p);
+}
 
 #define check_pgt_cache()       do { } while (0)
 
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 812a1d8f35cb..afda2bdd860f 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -7,7 +7,6 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
@@ -108,31 +107,6 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
         return page;
 }
 
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-        free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
-        pgtable_page_dtor(ptepage);
-        __free_page(ptepage);
-}
-
-#define PGF_CACHENUM_MASK       0x7
-
-typedef struct pgtable_free {
-        unsigned long val;
-} pgtable_free_t;
-
-static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
-                                                unsigned long mask)
-{
-        BUG_ON(cachenum > PGF_CACHENUM_MASK);
-
-        return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum};
-}
-
 static inline void pgtable_free(pgtable_free_t pgf)
 {
         void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
@@ -144,14 +118,6 @@ static inline void pgtable_free(pgtable_free_t pgf)
                 kmem_cache_free(pgtable_cache[cachenum], p);
 }
 
-extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
-
-#define __pte_free_tlb(tlb,ptepage)     \
-do { \
-        pgtable_page_dtor(ptepage); \
-        pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \
-                PTE_NONCACHE_NUM, PTE_TABLE_SIZE-1)); \
-} while (0)
 #define __pmd_free_tlb(tlb, pmd)        \
         pgtable_free_tlb(tlb, pgtable_free_cache(pmd, \
                 PMD_CACHE_NUM, PMD_TABLE_SIZE-1))
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index b4505ed0f0f2..5d8480265a77 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -2,11 +2,52 @@
 #define _ASM_POWERPC_PGALLOC_H
 #ifdef __KERNEL__
 
+#include <linux/mm.h>
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+        free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
+{
+        pgtable_page_dtor(ptepage);
+        __free_page(ptepage);
+}
+
+typedef struct pgtable_free {
+        unsigned long val;
+} pgtable_free_t;
+
+#define PGF_CACHENUM_MASK       0x7
+
+static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
+                                                unsigned long mask)
+{
+        BUG_ON(cachenum > PGF_CACHENUM_MASK);
+
+        return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum};
+}
+
 #ifdef CONFIG_PPC64
 #include <asm/pgalloc-64.h>
 #else
 #include <asm/pgalloc-32.h>
 #endif
 
+extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
+
+#ifdef CONFIG_SMP
+#define __pte_free_tlb(tlb,ptepage)     \
+do { \
+        pgtable_page_dtor(ptepage); \
+        pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \
+                PTE_NONCACHE_NUM, PTE_TABLE_SIZE-1)); \
+} while (0)
+#else
+#define __pte_free_tlb(tlb, pte)        pte_free((tlb)->mm, (pte))
+#endif
+
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_PGALLOC_H */
diff --git a/arch/powerpc/include/asm/pgtable-ppc32.h b/arch/powerpc/include/asm/pgtable-ppc32.h
index 6ab7c67cb5ab..f69a4d977729 100644
--- a/arch/powerpc/include/asm/pgtable-ppc32.h
+++ b/arch/powerpc/include/asm/pgtable-ppc32.h
@@ -228,9 +228,10 @@ extern int icache_44x_need_flush;
  *   - FILE *must* be in the bottom three bits because swap cache
  *     entries use the top 29 bits for TLB2.
  *
- *   - CACHE COHERENT bit (M) has no effect on PPC440 core, because it
- *     doesn't support SMP. So we can use this as software bit, like
- *     DIRTY.
+ *   - CACHE COHERENT bit (M) has no effect on original PPC440 cores,
+ *     because it doesn't support SMP. However, some later 460 variants
+ *     have -some- form of SMP support and so I keep the bit there for
+ *     future use
  *
  * With the PPC 44x Linux implementation, the 0-11th LSBs of the PTE are used
  * for memory protection related functions (see PTE structure in
@@ -436,20 +437,23 @@ extern int icache_44x_need_flush;
                          _PAGE_USER | _PAGE_ACCESSED | \
                          _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | \
                          _PAGE_EXEC | _PAGE_HWEXEC)
+
 /*
- * Note: the _PAGE_COHERENT bit automatically gets set in the hardware
- * PTE if CONFIG_SMP is defined (hash_page does this); there is no need
- * to have it in the Linux PTE, and in fact the bit could be reused for
- * another purpose.  -- paulus.
+ * We define 2 sets of base prot bits, one for basic pages (ie,
+ * cacheable kernel and user pages) and one for non cacheable
+ * pages. We always set _PAGE_COHERENT when SMP is enabled or
+ * the processor might need it for DMA coherency.
  */
-
-#ifdef CONFIG_44x
-#define _PAGE_BASE      (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_GUARDED)
+#if defined(CONFIG_SMP) || defined(CONFIG_PPC_STD_MMU)
+#define _PAGE_BASE      (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_COHERENT)
 #else
 #define _PAGE_BASE      (_PAGE_PRESENT | _PAGE_ACCESSED)
 #endif
+#define _PAGE_BASE_NC   (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_NO_CACHE)
+
 #define _PAGE_WRENABLE  (_PAGE_RW | _PAGE_DIRTY | _PAGE_HWWRITE)
 #define _PAGE_KERNEL    (_PAGE_BASE | _PAGE_SHARED | _PAGE_WRENABLE)
+#define _PAGE_KERNEL_NC (_PAGE_BASE_NC | _PAGE_SHARED | _PAGE_WRENABLE)
 
 #ifdef CONFIG_PPC_STD_MMU
 /* On standard PPC MMU, no user access implies kernel read/write access,
@@ -459,7 +463,7 @@ extern int icache_44x_need_flush;
 #define _PAGE_KERNEL_RO (_PAGE_BASE | _PAGE_SHARED)
 #endif
 
-#define _PAGE_IO        (_PAGE_KERNEL | _PAGE_NO_CACHE | _PAGE_GUARDED)
+#define _PAGE_IO        (_PAGE_KERNEL_NC | _PAGE_GUARDED)
 #define _PAGE_RAM       (_PAGE_KERNEL | _PAGE_HWEXEC)
 
 #if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\
@@ -552,9 +556,6 @@ static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED;
 static inline int pte_file(pte_t pte)           { return pte_val(pte) & _PAGE_FILE; }
 static inline int pte_special(pte_t pte)        { return pte_val(pte) & _PAGE_SPECIAL; }
 
-static inline void pte_uncache(pte_t pte)       { pte_val(pte) |= _PAGE_NO_CACHE; }
-static inline void pte_cache(pte_t pte)         { pte_val(pte) &= ~_PAGE_NO_CACHE; }
-
 static inline pte_t pte_wrprotect(pte_t pte) {
         pte_val(pte) &= ~(_PAGE_RW | _PAGE_HWWRITE); return pte; }
 static inline pte_t pte_mkclean(pte_t pte) {
@@ -693,10 +694,11 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 #endif
 }
 
+
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
                               pte_t *ptep, pte_t pte)
 {
-#if defined(CONFIG_PTE_64BIT) && defined(CONFIG_SMP)
+#if defined(CONFIG_PTE_64BIT) && defined(CONFIG_SMP) && defined(CONFIG_DEBUG_VM)
         WARN_ON(pte_present(*ptep));
 #endif
         __set_pte_at(mm, addr, ptep, pte);
@@ -760,16 +762,6 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty)
         __changed;                                                         \
 })
 
-/*
- * Macro to mark a page protection value as "uncacheable".
- */
-#define pgprot_noncached(prot)  (__pgprot(pgprot_val(prot) | _PAGE_NO_CACHE | _PAGE_GUARDED))
-
-struct file;
-extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-                                     unsigned long size, pgprot_t vma_prot);
-#define __HAVE_PHYS_MEM_ACCESS_PROT
-
 #define __HAVE_ARCH_PTE_SAME
 #define pte_same(A,B)   (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0)
 
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 4c0a8c62859d..b0f18be81d9f 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -100,7 +100,7 @@
 
 #define _PAGE_WRENABLE  (_PAGE_RW | _PAGE_DIRTY)
 
-/* __pgprot defined in arch/powerpc/incliude/asm/page.h */
+/* __pgprot defined in arch/powerpc/include/asm/page.h */
 #define PAGE_NONE       __pgprot(_PAGE_PRESENT | _PAGE_ACCESSED)
 
 #define PAGE_SHARED     __pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_USER)
@@ -245,9 +245,6 @@ static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED;}
 static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE;}
 static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; }
 
-static inline void pte_uncache(pte_t pte) { pte_val(pte) |= _PAGE_NO_CACHE; }
-static inline void pte_cache(pte_t pte)   { pte_val(pte) &= ~_PAGE_NO_CACHE; }
-
 static inline pte_t pte_wrprotect(pte_t pte) {
         pte_val(pte) &= ~(_PAGE_RW); return pte; }
 static inline pte_t pte_mkclean(pte_t pte) {
@@ -405,16 +402,6 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty)
         __changed;                                                         \
 })
 
-/*
- * Macro to mark a page protection value as "uncacheable".
- */
-#define pgprot_noncached(prot)  (__pgprot(pgprot_val(prot) | _PAGE_NO_CACHE | _PAGE_GUARDED))
-
-struct file;
-extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-                                     unsigned long size, pgprot_t vma_prot);
-#define __HAVE_PHYS_MEM_ACCESS_PROT
-
 #define __HAVE_ARCH_PTE_SAME
 #define pte_same(A,B)   (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0)
 
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index dbb8ca172e44..07f55e601696 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -16,6 +16,32 @@ struct mm_struct;
 #endif
 
 #ifndef __ASSEMBLY__
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+
+#define _PAGE_CACHE_CTL (_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \
+                         _PAGE_WRITETHRU)
+
+#define pgprot_noncached(prot)    (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+                                            _PAGE_NO_CACHE | _PAGE_GUARDED))
+
+#define pgprot_noncached_wc(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+                                            _PAGE_NO_CACHE))
+
+#define pgprot_cached(prot)       (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+                                            _PAGE_COHERENT))
+
+#define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+                                            _PAGE_COHERENT | _PAGE_WRITETHRU))
+
+
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+                                     unsigned long size, pgprot_t vma_prot);
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index c4a029ccb4d3..1a0d628eb114 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -425,14 +425,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 #define fromreal(rd)    tovirt(rd,rd)
 
 #define tophys(rd,rs)                           \
-0:      addis   rd,rs,-KERNELBASE@h;            \
+0:      addis   rd,rs,-PAGE_OFFSET@h;           \
         .section ".vtop_fixup","aw";            \
         .align  1;                              \
         .long   0b;                             \
         .previous
 
 #define tovirt(rd,rs)                           \
-0:      addis   rd,rs,KERNELBASE@h;             \
+0:      addis   rd,rs,PAGE_OFFSET@h;            \
         .section ".ptov_fixup","aw";            \
         .align  1;                              \
         .long   0b;                             \
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 101ed87f7d84..d3466490104a 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -69,8 +69,6 @@ extern int _prep_type;
 
 #ifdef __KERNEL__
 
-extern int have_of;
-
 struct task_struct;
 void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp);
 void release_thread(struct task_struct *);
@@ -207,6 +205,11 @@ struct thread_struct {
 #define INIT_SP_LIMIT \
         (_ALIGN_UP(sizeof(init_thread_info), 16) + (unsigned long) &init_stack)
 
+#ifdef CONFIG_SPE
+#define SPEFSCR_INIT .spefscr = SPEFSCR_FINVE | SPEFSCR_FDBZE | SPEFSCR_FUNFE | SPEFSCR_FOVFE,
+#else
+#define SPEFSCR_INIT
+#endif
 
 #ifdef CONFIG_PPC32
 #define INIT_THREAD { \
@@ -215,6 +218,7 @@ struct thread_struct {
         .fs = KERNEL_DS, \
         .pgdir = swapper_pg_dir, \
         .fpexc_mode = MSR_FE0 | MSR_FE1, \
+        SPEFSCR_INIT \
 }
 #else
 #define INIT_THREAD  { \
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index eb3bd2e1c7f6..6ff04185d2aa 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -253,6 +253,9 @@ extern void kdump_move_device_tree(void);
 /* CPU OF node matching */
 struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
 
+/* cache lookup */
+struct device_node *of_find_next_cache_node(struct device_node *np);
+
 /* Get the MAC address */
 extern const void *of_get_mac_address(struct device_node *np);
 
diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h
index f9e34c493cbb..cff30c0ef1ff 100644
--- a/arch/powerpc/include/asm/ps3.h
+++ b/arch/powerpc/include/asm/ps3.h
@@ -305,30 +305,34 @@ static inline const char* ps3_result(int result)
 /* system bus routines */
 
 enum ps3_match_id {
-        PS3_MATCH_ID_EHCI           = 1,
-        PS3_MATCH_ID_OHCI           = 2,
-        PS3_MATCH_ID_GELIC          = 3,
-        PS3_MATCH_ID_AV_SETTINGS    = 4,
-        PS3_MATCH_ID_SYSTEM_MANAGER = 5,
-        PS3_MATCH_ID_STOR_DISK      = 6,
-        PS3_MATCH_ID_STOR_ROM       = 7,
-        PS3_MATCH_ID_STOR_FLASH     = 8,
-        PS3_MATCH_ID_SOUND          = 9,
-        PS3_MATCH_ID_GRAPHICS       = 10,
-        PS3_MATCH_ID_LPM            = 11,
+        PS3_MATCH_ID_EHCI               = 1,
+        PS3_MATCH_ID_OHCI               = 2,
+        PS3_MATCH_ID_GELIC              = 3,
+        PS3_MATCH_ID_AV_SETTINGS        = 4,
+        PS3_MATCH_ID_SYSTEM_MANAGER     = 5,
+        PS3_MATCH_ID_STOR_DISK          = 6,
+        PS3_MATCH_ID_STOR_ROM           = 7,
+        PS3_MATCH_ID_STOR_FLASH         = 8,
+        PS3_MATCH_ID_SOUND              = 9,
+        PS3_MATCH_ID_GPU                = 10,
+        PS3_MATCH_ID_LPM                = 11,
 };
 
-#define PS3_MODULE_ALIAS_EHCI           "ps3:1"
-#define PS3_MODULE_ALIAS_OHCI           "ps3:2"
-#define PS3_MODULE_ALIAS_GELIC          "ps3:3"
-#define PS3_MODULE_ALIAS_AV_SETTINGS    "ps3:4"
-#define PS3_MODULE_ALIAS_SYSTEM_MANAGER "ps3:5"
-#define PS3_MODULE_ALIAS_STOR_DISK      "ps3:6"
-#define PS3_MODULE_ALIAS_STOR_ROM       "ps3:7"
-#define PS3_MODULE_ALIAS_STOR_FLASH     "ps3:8"
-#define PS3_MODULE_ALIAS_SOUND          "ps3:9"
-#define PS3_MODULE_ALIAS_GRAPHICS       "ps3:10"
-#define PS3_MODULE_ALIAS_LPM            "ps3:11"
+enum ps3_match_sub_id {
+        PS3_MATCH_SUB_ID_GPU_FB         = 1,
+};
+
+#define PS3_MODULE_ALIAS_EHCI           "ps3:1:0"
+#define PS3_MODULE_ALIAS_OHCI           "ps3:2:0"
+#define PS3_MODULE_ALIAS_GELIC          "ps3:3:0"
+#define PS3_MODULE_ALIAS_AV_SETTINGS    "ps3:4:0"
+#define PS3_MODULE_ALIAS_SYSTEM_MANAGER "ps3:5:0"
+#define PS3_MODULE_ALIAS_STOR_DISK      "ps3:6:0"
+#define PS3_MODULE_ALIAS_STOR_ROM       "ps3:7:0"
+#define PS3_MODULE_ALIAS_STOR_FLASH     "ps3:8:0"
+#define PS3_MODULE_ALIAS_SOUND          "ps3:9:0"
+#define PS3_MODULE_ALIAS_GPU_FB         "ps3:10:1"
+#define PS3_MODULE_ALIAS_LPM            "ps3:11:0"
 
 enum ps3_system_bus_device_type {
         PS3_DEVICE_TYPE_IOC0 = 1,
@@ -337,11 +341,6 @@ enum ps3_system_bus_device_type {
         PS3_DEVICE_TYPE_LPM,
 };
 
-enum ps3_match_sub_id {
-        /* for PS3_MATCH_ID_GRAPHICS */
-        PS3_MATCH_SUB_ID_FB             = 1,
-};
-
 /**
  * struct ps3_system_bus_device - a device on the system bus
  */
@@ -516,4 +515,7 @@ void ps3_sync_irq(int node);
 u32 ps3_get_hw_thread_id(int cpu);
 u64 ps3_get_spe_id(void *arg);
 
+/* mutex synchronizing GPU accesses and video mode changes */
+extern struct mutex ps3_gpu_mutex;
+
 #endif
diff --git a/arch/powerpc/include/asm/ps3av.h b/arch/powerpc/include/asm/ps3av.h
index 5aa22cffdbd6..cd24ac16660a 100644
--- a/arch/powerpc/include/asm/ps3av.h
+++ b/arch/powerpc/include/asm/ps3av.h
@@ -740,8 +740,4 @@ extern int ps3av_audio_mute(int);
 extern int ps3av_audio_mute_analog(int);
 extern int ps3av_dev_open(void);
 extern int ps3av_dev_close(void);
-extern void ps3av_register_flip_ctl(void (*flip_ctl)(int on, void *data),
-                                    void *flip_data);
-extern void ps3av_flip_ctl(int on);
-
 #endif  /* _ASM_POWERPC_PS3AV_H_ */
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index c6d1ab650778..f484a343efba 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -783,6 +783,10 @@ extern void scom970_write(unsigned int address, unsigned long value);
 #define __get_SP()      ({unsigned long sp; \
                         asm volatile("mr %0,1": "=r" (sp)); sp;})
 
+struct pt_regs;
+
+extern void ppc_save_regs(struct pt_regs *regs);
+
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_REG_H */
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 8eaa7b28d9d0..e0175beb4462 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -168,6 +168,7 @@ extern void rtas_os_term(char *str);
 extern int rtas_get_sensor(int sensor, int index, int *state);
 extern int rtas_get_power_level(int powerdomain, int *level);
 extern int rtas_set_power_level(int powerdomain, int level, int *setlevel);
+extern bool rtas_indicator_present(int token, int *maxindex);
 extern int rtas_set_indicator(int indicator, int index, int new_value);
 extern int rtas_set_indicator_fast(int indicator, int index, int new_value);
 extern void rtas_progress(char *s, unsigned short hex);
diff --git a/arch/powerpc/include/asm/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h
index ced34f1dc8f8..3d9f831c3c55 100644
--- a/arch/powerpc/include/asm/sfp-machine.h
+++ b/arch/powerpc/include/asm/sfp-machine.h
@@ -82,7 +82,7 @@
 #define _FP_MUL_MEAT_S(R,X,Y)   _FP_MUL_MEAT_1_wide(_FP_WFRACBITS_S,R,X,Y,umul_ppmm)
 #define _FP_MUL_MEAT_D(R,X,Y)   _FP_MUL_MEAT_2_wide(_FP_WFRACBITS_D,R,X,Y,umul_ppmm)
 
-#define _FP_DIV_MEAT_S(R,X,Y)   _FP_DIV_MEAT_1_udiv(S,R,X,Y)
+#define _FP_DIV_MEAT_S(R,X,Y)   _FP_DIV_MEAT_1_udiv_norm(S,R,X,Y)
 #define _FP_DIV_MEAT_D(R,X,Y)   _FP_DIV_MEAT_2_udiv(D,R,X,Y)
 
 /* These macros define what NaN looks like. They're supposed to expand to
@@ -97,6 +97,20 @@
 
 #define _FP_KEEPNANFRACP 1
 
+#ifdef FP_EX_BOOKE_E500_SPE
+#define FP_EX_INEXACT           (1 << 21)
+#define FP_EX_INVALID           (1 << 20)
+#define FP_EX_DIVZERO           (1 << 19)
+#define FP_EX_UNDERFLOW         (1 << 18)
+#define FP_EX_OVERFLOW          (1 << 17)
+#define FP_INHIBIT_RESULTS      0
+
+#define __FPU_FPSCR     (current->thread.spefscr)
+#define __FPU_ENABLED_EXC               \
+({                                      \
+        (__FPU_FPSCR >> 2) & 0x1f;      \
+})
+#else
 /* Exception flags.  We use the bit positions of the appropriate bits
    in the FPSCR, which also correspond to the FE_* bits.  This makes
    everything easier ;-).  */
@@ -111,22 +125,6 @@
 #define FP_EX_DIVZERO         (1 << (31 - 5))
 #define FP_EX_INEXACT         (1 << (31 - 6))
 
-/* This macro appears to be called when both X and Y are NaNs, and
- * has to choose one and copy it to R. i386 goes for the larger of the
- * two, sparc64 just picks Y. I don't understand this at all so I'll
- * go with sparc64 because it's shorter :->   -- PMM
- */
-#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP)              \
-  do {                                                  \
-    R##_s = Y##_s;                                      \
-    _FP_FRAC_COPY_##wc(R,Y);                            \
-    R##_c = FP_CLS_NAN;                                 \
-  } while (0)
-
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-
 #define __FPU_FPSCR     (current->thread.fpscr.val)
 
 /* We only actually write to the destination register
@@ -137,6 +135,32 @@
         (__FPU_FPSCR >> 3) & 0x1f;      \
 })
 
+#endif
+
+/*
+ * If one NaN is signaling and the other is not,
+ * we choose that one, otherwise we choose X.
+ */
+#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP)                      \
+  do {                                                          \
+    if ((_FP_FRAC_HIGH_RAW_##fs(Y) & _FP_QNANBIT_##fs)          \
+        && !(_FP_FRAC_HIGH_RAW_##fs(X) & _FP_QNANBIT_##fs))     \
+      {                                                         \
+        R##_s = X##_s;                                          \
+        _FP_FRAC_COPY_##wc(R,X);                                \
+      }                                                         \
+    else                                                        \
+      {                                                         \
+        R##_s = Y##_s;                                          \
+        _FP_FRAC_COPY_##wc(R,Y);                                \
+      }                                                         \
+    R##_c = FP_CLS_NAN;                                         \
+  } while (0)
+
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+
 #define __FPU_TRAP_P(bits) \
         ((__FPU_ENABLED_EXC & (bits)) != 0)
 
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 1866cec4f967..c25f73d1d842 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -81,6 +81,13 @@ extern int cpu_to_core_id(int cpu);
 #define PPC_MSG_CALL_FUNC_SINGLE        2
 #define PPC_MSG_DEBUGGER_BREAK  3
 
+/*
+ * irq controllers that have dedicated ipis per message and don't
+ * need additional code in the action handler may use this
+ */
+extern int smp_request_message_ipi(int virq, int message);
+extern const char *smp_ipi_name[];
+
 void smp_init_iSeries(void);
 void smp_init_pSeries(void);
 void smp_init_cell(void);
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index f56a843f4705..36864364e601 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -277,7 +277,7 @@ static inline void __raw_read_unlock(raw_rwlock_t *rw)
         bne-            1b"
         : "=&r"(tmp)
         : "r"(&rw->lock)
-        : "cr0", "memory");
+        : "cr0", "xer", "memory");
 }
 
 static inline void __raw_write_unlock(raw_rwlock_t *rw)
diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h
index 45963e80f557..28f6ddbff4cf 100644
--- a/arch/powerpc/include/asm/synch.h
+++ b/arch/powerpc/include/asm/synch.h
@@ -5,6 +5,10 @@
 #include <linux/stringify.h>
 #include <asm/feature-fixups.h>
 
+#if defined(__powerpc64__) || defined(CONFIG_PPC_E500MC)
+#define __SUBARCH_HAS_LWSYNC
+#endif
+
 #ifndef __ASSEMBLY__
 extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup;
 extern void do_lwsync_fixups(unsigned long value, void *fixup_start,
diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h
index d6648c143322..2a4be19a92c4 100644
--- a/arch/powerpc/include/asm/system.h
+++ b/arch/powerpc/include/asm/system.h
@@ -23,15 +23,17 @@
  * read_barrier_depends() prevents data-dependent loads being reordered
  *      across this point (nop on PPC).
  *
- * We have to use the sync instructions for mb(), since lwsync doesn't
- * order loads with respect to previous stores.  Lwsync is fine for
- * rmb(), though. Note that rmb() actually uses a sync on 32-bit
- * architectures.
+ * *mb() variants without smp_ prefix must order all types of memory
+ * operations with one another. sync is the only instruction sufficient
+ * to do this.
  *
- * For wmb(), we use sync since wmb is used in drivers to order
- * stores to system memory with respect to writes to the device.
- * However, smp_wmb() can be a lighter-weight lwsync or eieio barrier
- * on SMP since it is only used to order updates to system memory.
+ * For the smp_ barriers, ordering is for cacheable memory operations
+ * only. We have to use the sync instruction for smp_mb(), since lwsync
+ * doesn't order loads with respect to previous stores.  Lwsync can be
+ * used for smp_rmb() and smp_wmb().
+ *
+ * However, on CPUs that don't support lwsync, lwsync actually maps to a
+ * heavy-weight sync, so smp_wmb() can be a lighter-weight eieio.
  */
 #define mb()   __asm__ __volatile__ ("sync" : : : "memory")
 #define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
@@ -45,14 +47,14 @@
 #ifdef CONFIG_SMP
 
 #ifdef __SUBARCH_HAS_LWSYNC
-#    define SMPWMB      lwsync
+#    define SMPWMB      LWSYNC
 #else
 #    define SMPWMB      eieio
 #endif
 
 #define smp_mb()        mb()
-#define smp_rmb()       rmb()
-#define smp_wmb()       __asm__ __volatile__ (__stringify(SMPWMB) : : :"memory")
+#define smp_rmb()       __asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+#define smp_wmb()       __asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
 #define smp_read_barrier_depends()      read_barrier_depends()
 #else
 #define smp_mb()        barrier()
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index febd581ec9b0..27ccb764fdab 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -48,26 +48,6 @@ extern unsigned long ppc_proc_freq;
 extern unsigned long ppc_tb_freq;
 #define DEFAULT_TB_FREQ         125000000UL
 
-/*
- * By putting all of this stuff into a single struct we 
- * reduce the number of cache lines touched by do_gettimeofday.
- * Both by collecting all of the data in one cache line and
- * by touching only one TOC entry on ppc64.
- */
-struct gettimeofday_vars {
-        u64 tb_to_xs;
-        u64 stamp_xsec;
-        u64 tb_orig_stamp;
-};
-
-struct gettimeofday_struct {
-        unsigned long tb_ticks_per_sec;
-        struct gettimeofday_vars vars[2];
-        struct gettimeofday_vars * volatile varp;
-        unsigned      var_idx;
-        unsigned      tb_to_us;
-};
-
 struct div_result {
         u64 result_high;
         u64 result_low;
diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index a2c6bfd85fb7..abbe3419d1dd 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -6,6 +6,9 @@
  *
  *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
  *  - flush_tlb_page(vma, vmaddr) flushes one page
+ *  - local_flush_tlb_mm(mm) flushes the specified mm context on
+ *                           the local processor
+ *  - local_flush_tlb_page(vma, vmaddr) flushes one page on the local processor
  *  - flush_tlb_page_nohash(vma, vmaddr) flushes one page if SW loaded TLB
  *  - flush_tlb_range(vma, start, end) flushes a range of pages
  *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
@@ -17,7 +20,7 @@
  */
 #ifdef __KERNEL__
 
-#if defined(CONFIG_4xx) || defined(CONFIG_8xx) || defined(CONFIG_FSL_BOOKE)
+#ifdef CONFIG_PPC_MMU_NOHASH
 /*
  * TLB flushing for software loaded TLB chips
  *
@@ -28,63 +31,49 @@
 
 #include <linux/mm.h>
 
-extern void _tlbie(unsigned long address, unsigned int pid);
-extern void _tlbil_all(void);
-extern void _tlbil_pid(unsigned int pid);
-extern void _tlbil_va(unsigned long address, unsigned int pid);
+#define MMU_NO_CONTEXT          ((unsigned int)-1)
 
-#if defined(CONFIG_40x) || defined(CONFIG_8xx)
-#define _tlbia()        asm volatile ("tlbia; sync" : : : "memory")
-#else /* CONFIG_44x || CONFIG_FSL_BOOKE */
-extern void _tlbia(void);
-#endif
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-        _tlbil_pid(mm->context.id);
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma,
-                                  unsigned long vmaddr)
-{
-        _tlbil_va(vmaddr, vma ? vma->vm_mm->context.id : 0);
-}
+extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+                            unsigned long end);
+extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
-static inline void flush_tlb_page_nohash(struct vm_area_struct *vma,
-                                         unsigned long vmaddr)
-{
-        flush_tlb_page(vma, vmaddr);
-}
+extern void local_flush_tlb_mm(struct mm_struct *mm);
+extern void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 
-static inline void flush_tlb_range(struct vm_area_struct *vma,
-                                   unsigned long start, unsigned long end)
-{
-        _tlbil_pid(vma->vm_mm->context.id);
-}
+#ifdef CONFIG_SMP
+extern void flush_tlb_mm(struct mm_struct *mm);
+extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+#else
+#define flush_tlb_mm(mm)                local_flush_tlb_mm(mm)
+#define flush_tlb_page(vma,addr)        local_flush_tlb_page(vma,addr)
+#endif
+#define flush_tlb_page_nohash(vma,addr) flush_tlb_page(vma,addr)
 
-static inline void flush_tlb_kernel_range(unsigned long start,
-                                          unsigned long end)
-{
-        _tlbil_pid(0);
-}
+#elif defined(CONFIG_PPC_STD_MMU_32)
 
-#elif defined(CONFIG_PPC32)
 /*
- * TLB flushing for "classic" hash-MMMU 32-bit CPUs, 6xx, 7xx, 7xxx
+ * TLB flushing for "classic" hash-MMU 32-bit CPUs, 6xx, 7xx, 7xxx
  */
-extern void _tlbie(unsigned long address);
-extern void _tlbia(void);
-
 extern void flush_tlb_mm(struct mm_struct *mm);
 extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 extern void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr);
 extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
                             unsigned long end);
 extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+static inline void local_flush_tlb_page(struct vm_area_struct *vma,
+                                        unsigned long vmaddr)
+{
+        flush_tlb_page(vma, vmaddr);
+}
+static inline void local_flush_tlb_mm(struct mm_struct *mm)
+{
+        flush_tlb_mm(mm);
+}
+
+#elif defined(CONFIG_PPC_STD_MMU_64)
 
-#else
 /*
- * TLB flushing for 64-bit has-MMU CPUs
+ * TLB flushing for 64-bit hash-MMU CPUs
  */
 
 #include <linux/percpu.h>
@@ -134,10 +123,19 @@ extern void flush_hash_page(unsigned long va, real_pte_t pte, int psize,
 extern void flush_hash_range(unsigned long number, int local);
 
 
+static inline void local_flush_tlb_mm(struct mm_struct *mm)
+{
+}
+
 static inline void flush_tlb_mm(struct mm_struct *mm)
 {
 }
 
+static inline void local_flush_tlb_page(struct vm_area_struct *vma,
+                                        unsigned long vmaddr)
+{
+}
+
 static inline void flush_tlb_page(struct vm_area_struct *vma,
                                   unsigned long vmaddr)
 {
@@ -162,7 +160,8 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 extern void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
                                      unsigned long end);
 
-
+#else
+#error Unsupported MMU type
 #endif
 
 #endif /*__KERNEL__ */
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index f01393224b52..13c2c283e178 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -39,6 +39,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/unistd.h>
+#include <linux/time.h>
 
 #define SYSCALL_MAP_SIZE      ((__NR_syscalls + 31) / 32)
 
@@ -83,6 +84,7 @@ struct vdso_data {
         __u32 icache_log_block_size;            /* L1 i-cache log block size */
         __s32 wtom_clock_sec;                   /* Wall to monotonic clock */
         __s32 wtom_clock_nsec;
+        struct timespec stamp_xtime;    /* xtime as at tb_orig_stamp */
         __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls  */
         __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
 };
@@ -102,6 +104,7 @@ struct vdso_data {
         __u32 tz_dsttime;               /* Type of dst correction       0x5C */
         __s32 wtom_clock_sec;                   /* Wall to monotonic clock */
         __s32 wtom_clock_nsec;
+        struct timespec stamp_xtime;    /* xtime as at tb_orig_stamp */
         __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
         __u32 dcache_block_size;        /* L1 d-cache block size     */
         __u32 icache_block_size;        /* L1 i-cache block size     */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index d17edb4a2f9d..1308a86e9070 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -103,6 +103,10 @@ endif
 
 obj-$(CONFIG_PPC64)             += $(obj64-y)
 
+ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
+obj-y                           += ppc_save_regs.o
+endif
+
 extra-$(CONFIG_PPC_FPU)         += fpu.o
 extra-$(CONFIG_PPC64)           += entry_64.o
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 75c5dd0138fd..661d07d2146b 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -60,6 +60,7 @@ int main(void)
 {
         DEFINE(THREAD, offsetof(struct task_struct, thread));
         DEFINE(MM, offsetof(struct task_struct, mm));
+        DEFINE(MMCONTEXTID, offsetof(struct mm_struct, context.id));
 #ifdef CONFIG_PPC64
         DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context));
 #else
@@ -306,6 +307,7 @@ int main(void)
         DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32));
         DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec));
         DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
+        DEFINE(STAMP_XTIME, offsetof(struct vdso_data, stamp_xtime));
         DEFINE(CFG_ICACHE_BLOCKSZ, offsetof(struct vdso_data, icache_block_size));
         DEFINE(CFG_DCACHE_BLOCKSZ, offsetof(struct vdso_data, dcache_block_size));
         DEFINE(CFG_ICACHE_LOGBLOCKSZ, offsetof(struct vdso_data, icache_log_block_size));
@@ -378,6 +380,10 @@ int main(void)
         DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
         DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
 #endif
+#ifdef CONFIG_44x
+        DEFINE(PGD_T_LOG2, PGD_T_LOG2);
+        DEFINE(PTE_T_LOG2, PTE_T_LOG2);
+#endif
 
         return 0;
 }
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 7e8719504f39..923f87aff20a 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -19,6 +19,7 @@
 #include <asm/oprofile_impl.h>
 #include <asm/cputable.h>
 #include <asm/prom.h>           /* for PTRRELOC on ARCH=ppc */
+#include <asm/mmu.h>
 
 struct cpu_spec* cur_cpu_spec = NULL;
 EXPORT_SYMBOL(cur_cpu_spec);
@@ -94,6 +95,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "POWER3 (630)",
                 .cpu_features           = CPU_FTRS_POWER3,
                 .cpu_user_features      = COMMON_USER_PPC64|PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
@@ -109,6 +111,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "POWER3 (630+)",
                 .cpu_features           = CPU_FTRS_POWER3,
                 .cpu_user_features      = COMMON_USER_PPC64|PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
@@ -124,6 +127,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "RS64-II (northstar)",
                 .cpu_features           = CPU_FTRS_RS64,
                 .cpu_user_features      = COMMON_USER_PPC64,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
@@ -139,6 +143,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "RS64-III (pulsar)",
                 .cpu_features           = CPU_FTRS_RS64,
                 .cpu_user_features      = COMMON_USER_PPC64,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
@@ -154,6 +159,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "RS64-III (icestar)",
                 .cpu_features           = CPU_FTRS_RS64,
                 .cpu_user_features      = COMMON_USER_PPC64,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
@@ -169,6 +175,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "RS64-IV (sstar)",
                 .cpu_features           = CPU_FTRS_RS64,
                 .cpu_user_features      = COMMON_USER_PPC64,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
@@ -184,6 +191,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "POWER4 (gp)",
                 .cpu_features           = CPU_FTRS_POWER4,
                 .cpu_user_features      = COMMON_USER_POWER4,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
@@ -199,6 +207,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "POWER4+ (gq)",
                 .cpu_features           = CPU_FTRS_POWER4,
                 .cpu_user_features      = COMMON_USER_POWER4,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
@@ -215,6 +224,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_PPC970,
                 .cpu_user_features      = COMMON_USER_POWER4 |
                         PPC_FEATURE_HAS_ALTIVEC_COMP,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
@@ -233,6 +243,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_PPC970,
                 .cpu_user_features      = COMMON_USER_POWER4 |
                         PPC_FEATURE_HAS_ALTIVEC_COMP,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
@@ -251,6 +262,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_PPC970,
                 .cpu_user_features      = COMMON_USER_POWER4 |
                         PPC_FEATURE_HAS_ALTIVEC_COMP,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
@@ -269,6 +281,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_PPC970,
                 .cpu_user_features      = COMMON_USER_POWER4 |
                         PPC_FEATURE_HAS_ALTIVEC_COMP,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
@@ -287,6 +300,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_PPC970,
                 .cpu_user_features      = COMMON_USER_POWER4 |
                         PPC_FEATURE_HAS_ALTIVEC_COMP,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 8,
@@ -303,6 +317,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "POWER5 (gr)",
                 .cpu_features           = CPU_FTRS_POWER5,
                 .cpu_user_features      = COMMON_USER_POWER5,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 6,
@@ -323,6 +338,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "POWER5+ (gs)",
                 .cpu_features           = CPU_FTRS_POWER5,
                 .cpu_user_features      = COMMON_USER_POWER5_PLUS,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 6,
@@ -339,6 +355,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "POWER5+ (gs)",
                 .cpu_features           = CPU_FTRS_POWER5,
                 .cpu_user_features      = COMMON_USER_POWER5_PLUS,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 6,
@@ -356,6 +373,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "POWER5+",
                 .cpu_features           = CPU_FTRS_POWER5,
                 .cpu_user_features      = COMMON_USER_POWER5_PLUS,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .machine_check          = machine_check_generic,
@@ -369,6 +387,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_POWER6,
                 .cpu_user_features      = COMMON_USER_POWER6 |
                         PPC_FEATURE_POWER6_EXT,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 6,
@@ -388,6 +407,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "POWER6 (architected)",
                 .cpu_features           = CPU_FTRS_POWER6,
                 .cpu_user_features      = COMMON_USER_POWER6,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .machine_check          = machine_check_generic,
@@ -400,6 +420,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "POWER7 (architected)",
                 .cpu_features           = CPU_FTRS_POWER7,
                 .cpu_user_features      = COMMON_USER_POWER7,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .machine_check          = machine_check_generic,
@@ -412,6 +433,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "POWER7 (raw)",
                 .cpu_features           = CPU_FTRS_POWER7,
                 .cpu_user_features      = COMMON_USER_POWER7,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 6,
@@ -434,6 +456,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_user_features      = COMMON_USER_PPC64 |
                         PPC_FEATURE_CELL | PPC_FEATURE_HAS_ALTIVEC_COMP |
                         PPC_FEATURE_SMT,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 4,
@@ -449,6 +472,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "PA6T",
                 .cpu_features           = CPU_FTRS_PA6T,
                 .cpu_user_features      = COMMON_USER_PA6T,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 64,
                 .dcache_bsize           = 64,
                 .num_pmcs               = 6,
@@ -466,6 +490,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "POWER4 (compatible)",
                 .cpu_features           = CPU_FTRS_COMPATIBLE,
                 .cpu_user_features      = COMMON_USER_PPC64,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 128,
                 .dcache_bsize           = 128,
                 .num_pmcs               = 6,
@@ -483,6 +508,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_PPC601,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_601_INSTR |
                         PPC_FEATURE_UNIFIED_CACHE | PPC_FEATURE_NO_TB,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_generic,
@@ -494,6 +520,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "603",
                 .cpu_features           = CPU_FTRS_603,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = 0,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_603,
@@ -506,6 +533,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "603e",
                 .cpu_features           = CPU_FTRS_603,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = 0,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_603,
@@ -518,6 +546,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "603ev",
                 .cpu_features           = CPU_FTRS_603,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = 0,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_603,
@@ -530,6 +559,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "604",
                 .cpu_features           = CPU_FTRS_604,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 2,
@@ -543,6 +573,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "604e",
                 .cpu_features           = CPU_FTRS_604,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -556,6 +587,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "604r",
                 .cpu_features           = CPU_FTRS_604,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -569,6 +601,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "604ev",
                 .cpu_features           = CPU_FTRS_604,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -582,6 +615,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "740/750",
                 .cpu_features           = CPU_FTRS_740_NOTAU,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -595,6 +629,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "750CX",
                 .cpu_features           = CPU_FTRS_750,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -608,6 +643,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "750CX",
                 .cpu_features           = CPU_FTRS_750,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -622,6 +658,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "750CXe",
                 .cpu_features           = CPU_FTRS_750,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -636,6 +673,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "750CXe",
                 .cpu_features           = CPU_FTRS_750,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -650,6 +688,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "750CL",
                 .cpu_features           = CPU_FTRS_750CL,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -664,6 +703,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "745/755",
                 .cpu_features           = CPU_FTRS_750,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -678,6 +718,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "750FX",
                 .cpu_features           = CPU_FTRS_750FX1,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -692,6 +733,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "750FX",
                 .cpu_features           = CPU_FTRS_750FX2,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -706,6 +748,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "750FX",
                 .cpu_features           = CPU_FTRS_750FX,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -720,6 +763,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "750GX",
                 .cpu_features           = CPU_FTRS_750GX,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -734,6 +778,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "740/750",
                 .cpu_features           = CPU_FTRS_740,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -749,6 +794,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_7400_NOTAU,
                 .cpu_user_features      = COMMON_USER |
                         PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -764,6 +810,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_7400,
                 .cpu_user_features      = COMMON_USER |
                         PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -779,6 +826,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_7400,
                 .cpu_user_features      = COMMON_USER |
                         PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -794,6 +842,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_7450_20,
                 .cpu_user_features      = COMMON_USER |
                         PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 6,
@@ -811,6 +860,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_7450_21,
                 .cpu_user_features      = COMMON_USER |
                         PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 6,
@@ -828,6 +878,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_7450_23,
                 .cpu_user_features      = COMMON_USER |
                         PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 6,
@@ -845,6 +896,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_7455_1,
                 .cpu_user_features      = COMMON_USER |
                         PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 6,
@@ -862,6 +914,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_7455_20,
                 .cpu_user_features      = COMMON_USER |
                         PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 6,
@@ -879,6 +932,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_7455,
                 .cpu_user_features      = COMMON_USER |
                         PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 6,
@@ -896,6 +950,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_7447_10,
                 .cpu_user_features      = COMMON_USER |
                         PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 6,
@@ -913,6 +968,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_7447_10,
                 .cpu_user_features      = COMMON_USER |
                         PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 6,
@@ -929,6 +985,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "7447/7457",
                 .cpu_features           = CPU_FTRS_7447,
                 .cpu_user_features      = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 6,
@@ -946,6 +1003,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_7447A,
                 .cpu_user_features      = COMMON_USER |
                         PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 6,
@@ -963,6 +1021,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_7448,
                 .cpu_user_features      = COMMON_USER |
                         PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+                .mmu_features           = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 6,
@@ -979,6 +1038,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "82xx",
                 .cpu_features           = CPU_FTRS_82XX,
                 .cpu_user_features      = COMMON_USER,
+                .mmu_features           = 0,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_603,
@@ -991,6 +1051,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "G2_LE",
                 .cpu_features           = CPU_FTRS_G2_LE,
                 .cpu_user_features      = COMMON_USER,
+                .mmu_features           = MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_603,
@@ -1003,6 +1064,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "e300c1",
                 .cpu_features           = CPU_FTRS_E300,
                 .cpu_user_features      = COMMON_USER,
+                .mmu_features           = MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_603,
@@ -1015,6 +1077,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "e300c2",
                 .cpu_features           = CPU_FTRS_E300C2,
                 .cpu_user_features      = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+                .mmu_features           = MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_603,
@@ -1027,6 +1090,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "e300c3",
                 .cpu_features           = CPU_FTRS_E300,
                 .cpu_user_features      = COMMON_USER,
+                .mmu_features           = MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_603,
@@ -1041,6 +1105,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "e300c4",
                 .cpu_features           = CPU_FTRS_E300,
                 .cpu_user_features      = COMMON_USER,
+                .mmu_features           = MMU_FTR_USE_HIGH_BATS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_603,
@@ -1056,6 +1121,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "(generic PPC)",
                 .cpu_features           = CPU_FTRS_CLASSIC32,
                 .cpu_user_features      = COMMON_USER,
+                .mmu_features           = MMU_FTR_HPTE_TABLE,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_generic,
@@ -1071,6 +1137,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                  * if the 8xx code is there.... */
                 .cpu_features           = CPU_FTRS_8XX,
                 .cpu_user_features      = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+                .mmu_features           = MMU_FTR_TYPE_8xx,
                 .icache_bsize           = 16,
                 .dcache_bsize           = 16,
                 .platform               = "ppc823",
@@ -1083,6 +1150,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "403GC",
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 16,
                 .dcache_bsize           = 16,
                 .machine_check          = machine_check_4xx,
@@ -1095,6 +1163,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_NO_TB,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 16,
                 .dcache_bsize           = 16,
                 .machine_check          = machine_check_4xx,
@@ -1106,6 +1175,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "403G ??",
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 16,
                 .dcache_bsize           = 16,
                 .machine_check          = machine_check_4xx,
@@ -1118,6 +1188,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1130,6 +1201,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1142,6 +1214,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1154,6 +1227,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1166,6 +1240,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1178,6 +1253,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1190,6 +1266,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1202,6 +1279,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1213,6 +1291,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "405LP",
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1225,6 +1304,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1237,6 +1317,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1249,6 +1330,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1261,6 +1343,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1273,6 +1356,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1286,6 +1370,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1298,6 +1383,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_features           = CPU_FTRS_40X,
                 .cpu_user_features      = PPC_FEATURE_32 |
                         PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+                .mmu_features           = MMU_FTR_TYPE_40x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1312,6 +1398,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440GR Rev. A",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1323,6 +1410,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440EP Rev. A",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_440ep,
@@ -1335,6 +1423,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440GR Rev. B",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1346,6 +1435,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440EP Rev. C",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_440ep,
@@ -1358,6 +1448,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440EP Rev. B",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_440ep,
@@ -1370,6 +1461,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440GRX",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_440grx,
@@ -1382,6 +1474,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440EPX",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_440epx,
@@ -1394,6 +1487,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440GP Rev. B",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1405,6 +1499,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440GP Rev. C",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1416,6 +1511,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440GX Rev. A",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_440gx,
@@ -1428,6 +1524,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440GX Rev. B",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_440gx,
@@ -1440,6 +1537,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440GX Rev. C",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_440gx,
@@ -1452,6 +1550,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440GX Rev. F",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_440gx,
@@ -1464,6 +1563,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440SP Rev. A",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1475,6 +1575,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440SPe Rev. A",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_440spe,
@@ -1487,6 +1588,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440SPe Rev. B",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_440spe,
@@ -1499,6 +1601,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "440 in Virtex-5 FXT",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_440x5,
@@ -1509,8 +1612,9 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .pvr_mask               = 0xffff0002,
                 .pvr_value              = 0x13020002,
                 .cpu_name               = "460EX",
-                .cpu_features           = CPU_FTRS_44X,
+                .cpu_features           = CPU_FTRS_440x6,
                 .cpu_user_features      = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_460ex,
@@ -1521,8 +1625,9 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .pvr_mask               = 0xffff0002,
                 .pvr_value              = 0x13020000,
                 .cpu_name               = "460GT",
-                .cpu_features           = CPU_FTRS_44X,
+                .cpu_features           = CPU_FTRS_440x6,
                 .cpu_user_features      = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .cpu_setup              = __setup_cpu_460gt,
@@ -1535,6 +1640,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "(generic 44x PPC)",
                 .cpu_features           = CPU_FTRS_44X,
                 .cpu_user_features      = COMMON_USER_BOOKE,
+                .mmu_features           = MMU_FTR_TYPE_44x,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_4xx,
@@ -1551,6 +1657,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_user_features      = COMMON_USER_BOOKE |
                         PPC_FEATURE_HAS_EFP_SINGLE |
                         PPC_FEATURE_UNIFIED_CACHE,
+                .mmu_features           = MMU_FTR_TYPE_FSL_E,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_e200,
                 .platform               = "ppc5554",
@@ -1565,6 +1672,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                         PPC_FEATURE_HAS_SPE_COMP |
                         PPC_FEATURE_HAS_EFP_SINGLE_COMP |
                         PPC_FEATURE_UNIFIED_CACHE,
+                .mmu_features           = MMU_FTR_TYPE_FSL_E,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_e200,
                 .platform               = "ppc5554",
@@ -1577,6 +1685,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_user_features      = COMMON_USER_BOOKE |
                         PPC_FEATURE_HAS_EFP_SINGLE |
                         PPC_FEATURE_UNIFIED_CACHE,
+                .mmu_features           = MMU_FTR_TYPE_FSL_E,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_e200,
                 .platform               = "ppc5554",
@@ -1591,6 +1700,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_user_features      = COMMON_USER_BOOKE |
                         PPC_FEATURE_HAS_SPE_COMP |
                         PPC_FEATURE_HAS_EFP_SINGLE_COMP,
+                .mmu_features           = MMU_FTR_TYPE_FSL_E,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -1608,6 +1718,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                         PPC_FEATURE_HAS_SPE_COMP |
                         PPC_FEATURE_HAS_EFP_SINGLE_COMP |
                         PPC_FEATURE_HAS_EFP_DOUBLE_COMP,
+                .mmu_features           = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .num_pmcs               = 4,
@@ -1622,6 +1733,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_name               = "e500mc",
                 .cpu_features           = CPU_FTRS_E500MC,
                 .cpu_user_features      = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+                .mmu_features           = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS,
                 .icache_bsize           = 64,
                 .dcache_bsize           = 64,
                 .num_pmcs               = 4,
@@ -1638,6 +1750,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .cpu_user_features      = COMMON_USER_BOOKE |
                         PPC_FEATURE_HAS_SPE_COMP |
                         PPC_FEATURE_HAS_EFP_SINGLE_COMP,
+                .mmu_features           = MMU_FTR_TYPE_FSL_E,
                 .icache_bsize           = 32,
                 .dcache_bsize           = 32,
                 .machine_check          = machine_check_e500,
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 3a6eaa876ee1..1c5c8a6fc129 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -120,6 +120,26 @@ static inline void dma_direct_unmap_page(struct device *dev,
 {
 }
 
+#ifdef CONFIG_NOT_COHERENT_CACHE
+static inline void dma_direct_sync_sg(struct device *dev,
+                struct scatterlist *sgl, int nents,
+                enum dma_data_direction direction)
+{
+        struct scatterlist *sg;
+        int i;
+
+        for_each_sg(sgl, sg, nents, i)
+                __dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
+}
+
+static inline void dma_direct_sync_single_range(struct device *dev,
+                dma_addr_t dma_handle, unsigned long offset, size_t size,
+                enum dma_data_direction direction)
+{
+        __dma_sync(bus_to_virt(dma_handle+offset), size, direction);
+}
+#endif
+
 struct dma_mapping_ops dma_direct_ops = {
         .alloc_coherent = dma_direct_alloc_coherent,
         .free_coherent  = dma_direct_free_coherent,
@@ -128,5 +148,11 @@ struct dma_mapping_ops dma_direct_ops = {
         .dma_supported  = dma_direct_dma_supported,
         .map_page       = dma_direct_map_page,
         .unmap_page     = dma_direct_unmap_page,
+#ifdef CONFIG_NOT_COHERENT_CACHE
+        .sync_single_range_for_cpu      = dma_direct_sync_single_range,
+        .sync_single_range_for_device   = dma_direct_sync_single_range,
+        .sync_sg_for_cpu                = dma_direct_sync_sg,
+        .sync_sg_for_device             = dma_direct_sync_sg,
+#endif
 };
 EXPORT_SYMBOL(dma_direct_ops);
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 0c326823c6d4..a1c4cfd25ded 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -31,6 +31,7 @@
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
+#include <asm/bug.h>
 
 /* 601 only have IBAT; cr0.eq is set on 601 when using this macro */
 #define LOAD_BAT(n, reg, RA, RB)        \
@@ -182,7 +183,8 @@ __after_mmu_off:
         bl      reloc_offset
         mr      r26,r3
         addis   r4,r3,KERNELBASE@h      /* current address of _start */
-        cmpwi   0,r4,0                  /* are we already running at 0? */
+        lis     r5,PHYSICAL_START@h
+        cmplw   0,r4,r5                 /* already running at PHYSICAL_START? */
         bne     relocate_kernel
 /*
  * we now have the 1st 16M of ram mapped with the bats.
@@ -810,13 +812,13 @@ giveup_altivec:
 
 /*
  * This code is jumped to from the startup code to copy
- * the kernel image to physical address 0.
+ * the kernel image to physical address PHYSICAL_START.
  */
 relocate_kernel:
         addis   r9,r26,klimit@ha        /* fetch klimit */
         lwz     r25,klimit@l(r9)
         addis   r25,r25,-KERNELBASE@h
-        li      r3,0                    /* Destination base address */
+        lis     r3,PHYSICAL_START@h     /* Destination base address */
         li      r6,0                    /* Destination offset */
         li      r5,0x4000               /* # bytes of memory to copy */
         bl      copy_and_flush          /* copy the first 0x4000 bytes */
@@ -989,12 +991,12 @@ load_up_mmu:
         LOAD_BAT(1,r3,r4,r5)
         LOAD_BAT(2,r3,r4,r5)
         LOAD_BAT(3,r3,r4,r5)
-BEGIN_FTR_SECTION
+BEGIN_MMU_FTR_SECTION
         LOAD_BAT(4,r3,r4,r5)
         LOAD_BAT(5,r3,r4,r5)
         LOAD_BAT(6,r3,r4,r5)
         LOAD_BAT(7,r3,r4,r5)
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
         blr
 
 /*
@@ -1070,9 +1072,14 @@ start_here:
         RFI
 
 /*
+ * void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next);
+ *
  * Set up the segment registers for a new context.
  */
-_ENTRY(set_context)
+_ENTRY(switch_mmu_context)
+        lwz     r3,MMCONTEXTID(r4)
+        cmpwi   cr0,r3,0
+        blt-    4f
         mulli   r3,r3,897       /* multiply context by skew factor */
         rlwinm  r3,r3,4,8,27    /* VSID = (context & 0xfffff) << 4 */
         addis   r3,r3,0x6000    /* Set Ks, Ku bits */
@@ -1083,6 +1090,7 @@ _ENTRY(set_context)
         /* Context switch the PTE pointer for the Abatron BDI2000.
          * The PGDIR is passed as second argument.
          */
+        lwz     r4,MM_PGD(r4)
         lis     r5, KERNELBASE@h
         lwz     r5, 0xf0(r5)
         stw     r4, 0x4(r5)
@@ -1098,6 +1106,9 @@ _ENTRY(set_context)
         sync
         isync
         blr
+4:      trap
+        EMIT_BUG_ENTRY 4b,__FILE__,__LINE__,0
+        blr
 
 /*
  * An undocumented "feature" of 604e requires that the v bit
@@ -1131,7 +1142,7 @@ clear_bats:
         mtspr   SPRN_IBAT2L,r10
         mtspr   SPRN_IBAT3U,r10
         mtspr   SPRN_IBAT3L,r10
-BEGIN_FTR_SECTION
+BEGIN_MMU_FTR_SECTION
         /* Here's a tweak: at this point, CPU setup have
          * not been called yet, so HIGH_BAT_EN may not be
          * set in HID0 for the 745x processors. However, it
@@ -1154,7 +1165,7 @@ BEGIN_FTR_SECTION
         mtspr   SPRN_IBAT6L,r10
         mtspr   SPRN_IBAT7U,r10
         mtspr   SPRN_IBAT7L,r10
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
         blr
 
 flush_tlbs:
@@ -1178,11 +1189,11 @@ mmu_off:
 
 /*
  * Use the first pair of BAT registers to map the 1st 16MB
- * of RAM to KERNELBASE.  From this point on we can't safely
+ * of RAM to PAGE_OFFSET.  From this point on we can't safely
  * call OF any more.
  */
 initial_bats:
-        lis     r11,KERNELBASE@h
+        lis     r11,PAGE_OFFSET@h
         mfspr   r9,SPRN_PVR
         rlwinm  r9,r9,16,16,31          /* r9 = 1 for 601, 4 for 604 */
         cmpwi   0,r9,1
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index f3a1ea9d7fe4..b56fecc93a16 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -69,6 +69,17 @@ _ENTRY(_start);
         li      r24,0           /* CPU number */
 
 /*
+ * In case the firmware didn't do it, we apply some workarounds
+ * that are good for all 440 core variants here
+ */
+        mfspr   r3,SPRN_CCR0
+        rlwinm  r3,r3,0,0,27    /* disable icache prefetch */
+        isync
+        mtspr   SPRN_CCR0,r3
+        isync
+        sync
+
+/*
  * Set up the initial MMU state
  *
  * We are still executing code at the virtual address
@@ -391,12 +402,14 @@ interrupt_base:
         rlwimi  r13,r12,10,30,30
 
         /* Load the PTE */
-        rlwinm  r12, r10, 13, 19, 29    /* Compute pgdir/pmd offset */
+        /* Compute pgdir/pmd offset */
+        rlwinm  r12, r10, PPC44x_PGD_OFF_SHIFT, PPC44x_PGD_OFF_MASK_BIT, 29
         lwzx    r11, r12, r11           /* Get pgd/pmd entry */
         rlwinm. r12, r11, 0, 0, 20      /* Extract pt base address */
         beq     2f                      /* Bail if no table */
 
-        rlwimi  r12, r10, 23, 20, 28    /* Compute pte address */
+        /* Compute pte address */
+        rlwimi  r12, r10, PPC44x_PTE_ADD_SHIFT, PPC44x_PTE_ADD_MASK_BIT, 28
         lwz     r11, 0(r12)             /* Get high word of pte entry */
         lwz     r12, 4(r12)             /* Get low word of pte entry */
 
@@ -485,12 +498,14 @@ tlb_44x_patch_hwater_D:
         /* Make up the required permissions */
         li      r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_HWEXEC
 
-        rlwinm  r12, r10, 13, 19, 29    /* Compute pgdir/pmd offset */
+        /* Compute pgdir/pmd offset */
+        rlwinm  r12, r10, PPC44x_PGD_OFF_SHIFT, PPC44x_PGD_OFF_MASK_BIT, 29
         lwzx    r11, r12, r11           /* Get pgd/pmd entry */
         rlwinm. r12, r11, 0, 0, 20      /* Extract pt base address */
         beq     2f                      /* Bail if no table */
 
-        rlwimi  r12, r10, 23, 20, 28    /* Compute pte address */
+        /* Compute pte address */
+        rlwimi  r12, r10, PPC44x_PTE_ADD_SHIFT, PPC44x_PTE_ADD_MASK_BIT, 28
         lwz     r11, 0(r12)             /* Get high word of pte entry */
         lwz     r12, 4(r12)             /* Get low word of pte entry */
 
@@ -554,15 +569,16 @@ tlb_44x_patch_hwater_I:
  */
 finish_tlb_load:
         /* Combine RPN & ERPN an write WS 0 */
-        rlwimi  r11,r12,0,0,19
+        rlwimi  r11,r12,0,0,31-PAGE_SHIFT
         tlbwe   r11,r13,PPC44x_TLB_XLAT
 
         /*
          * Create WS1. This is the faulting address (EPN),
          * page size, and valid flag.
          */
-        li      r11,PPC44x_TLB_VALID | PPC44x_TLB_4K
-        rlwimi  r10,r11,0,20,31                 /* Insert valid and page size*/
+        li      r11,PPC44x_TLB_VALID | PPC44x_TLBE_SIZE
+        /* Insert valid and page size */
+        rlwimi  r10,r11,0,PPC44x_PTE_ADD_MASK_BIT,31
         tlbwe   r10,r13,PPC44x_TLB_PAGEID       /* Write PAGEID */
 
         /* And WS 2 */
@@ -634,12 +650,12 @@ _GLOBAL(set_context)
  * goes at the beginning of the data segment, which is page-aligned.
  */
         .data
-        .align  12
+        .align  PAGE_SHIFT
         .globl  sdata
 sdata:
         .globl  empty_zero_page
 empty_zero_page:
-        .space  4096
+        .space  PAGE_SIZE
 
 /*
  * To support >32-bit physical addresses, we use an 8KB pgdir.
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 590304c24dad..11b549acc034 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -92,6 +92,7 @@ _ENTRY(_start);
  * if needed
  */
 
+_ENTRY(__early_start)
 /* 1. Find the index of the entry we're executing in */
         bl      invstr                          /* Find our address */
 invstr: mflr    r6                              /* Make it accessible */
@@ -235,36 +236,40 @@ skpinv:	addi	r6,r6,1				/* Increment */
         tlbivax 0,r9
         TLBSYNC
 
+/* The mapping only needs to be cache-coherent on SMP */
+#ifdef CONFIG_SMP
+#define M_IF_SMP        MAS2_M
+#else
+#define M_IF_SMP        0
+#endif
+
 /* 6. Setup KERNELBASE mapping in TLB1[0] */
         lis     r6,0x1000               /* Set MAS0(TLBSEL) = TLB1(1), ESEL = 0 */
         mtspr   SPRN_MAS0,r6
         lis     r6,(MAS1_VALID|MAS1_IPROT)@h
         ori     r6,r6,(MAS1_TSIZE(BOOKE_PAGESZ_64M))@l
         mtspr   SPRN_MAS1,r6
-        li      r7,0
-        lis     r6,PAGE_OFFSET@h
-        ori     r6,r6,PAGE_OFFSET@l
-        rlwimi  r6,r7,0,20,31
+        lis     r6,MAS2_VAL(PAGE_OFFSET, BOOKE_PAGESZ_64M, M_IF_SMP)@h
+        ori     r6,r6,MAS2_VAL(PAGE_OFFSET, BOOKE_PAGESZ_64M, M_IF_SMP)@l
         mtspr   SPRN_MAS2,r6
         mtspr   SPRN_MAS3,r8
         tlbwe
 
 /* 7. Jump to KERNELBASE mapping */
-        lis     r6,KERNELBASE@h
-        ori     r6,r6,KERNELBASE@l
-        rlwimi  r6,r7,0,20,31
+        lis     r6,(KERNELBASE & ~0xfff)@h
+        ori     r6,r6,(KERNELBASE & ~0xfff)@l
         lis     r7,MSR_KERNEL@h
         ori     r7,r7,MSR_KERNEL@l
         bl      1f                      /* Find our address */
 1:      mflr    r9
         rlwimi  r6,r9,0,20,31
-        addi    r6,r6,24
+        addi    r6,r6,(2f - 1b)
         mtspr   SPRN_SRR0,r6
         mtspr   SPRN_SRR1,r7
         rfi                             /* start execution out of TLB1[0] entry */
 
 /* 8. Clear out the temp mapping */
-        lis     r7,0x1000       /* Set MAS0(TLBSEL) = 1 */
+2:      lis     r7,0x1000       /* Set MAS0(TLBSEL) = 1 */
         rlwimi  r7,r5,16,4,15   /* Setup MAS0 = TLBSEL | ESEL(r5) */
         mtspr   SPRN_MAS0,r7
         tlbre
@@ -344,6 +349,15 @@ skpinv:	addi	r6,r6,1				/* Increment */
         mtspr   SPRN_DBSR,r2
 #endif
 
+#ifdef CONFIG_SMP
+        /* Check to see if we're the second processor, and jump
+         * to the secondary_start code if so
+         */
+        mfspr   r24,SPRN_PIR
+        cmpwi   r24,0
+        bne     __secondary_start
+#endif
+
         /*
          * This is where the main kernel code starts.
          */
@@ -685,12 +699,13 @@ interrupt_base:
         /* SPE Floating Point Data */
 #ifdef CONFIG_SPE
         EXCEPTION(0x2030, SPEFloatingPointData, SPEFloatingPointException, EXC_XFER_EE);
-#else
-        EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE)
-#endif /* CONFIG_SPE */
 
         /* SPE Floating Point Round */
+        EXCEPTION(0x2050, SPEFloatingPointRound, SPEFloatingPointRoundException, EXC_XFER_EE)
+#else
+        EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE)
         EXCEPTION(0x2050, SPEFloatingPointRound, unknown_exception, EXC_XFER_EE)
+#endif /* CONFIG_SPE */
 
         /* Performance Monitor */
         EXCEPTION(0x2060, PerformanceMonitor, performance_monitor_exception, EXC_XFER_STD)
@@ -735,6 +750,9 @@ finish_tlb_load:
 #else
         rlwimi  r12, r11, 26, 27, 31    /* extract WIMGE from pte */
 #endif
+#ifdef CONFIG_SMP
+        ori     r12, r12, MAS2_M
+#endif
         mtspr   SPRN_MAS2, r12
 
         li      r10, (_PAGE_HWEXEC | _PAGE_PRESENT)
@@ -746,15 +764,15 @@ finish_tlb_load:
         iseleq  r12, r12, r10
         
 #ifdef CONFIG_PTE_64BIT
-2:      rlwimi  r12, r13, 24, 0, 7      /* grab RPN[32:39] */
+        rlwimi  r12, r13, 24, 0, 7      /* grab RPN[32:39] */
         rlwimi  r12, r11, 24, 8, 19     /* grab RPN[40:51] */
         mtspr   SPRN_MAS3, r12
-BEGIN_FTR_SECTION
+BEGIN_MMU_FTR_SECTION
         srwi    r10, r13, 8             /* grab RPN[8:31] */
         mtspr   SPRN_MAS7, r10
-END_FTR_SECTION_IFSET(CPU_FTR_BIG_PHYS)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS)
 #else
-2:      rlwimi  r11, r12, 0, 20, 31     /* Extract RPN from PTE and merge with perms */
+        rlwimi  r11, r12, 0, 20, 31     /* Extract RPN from PTE and merge with perms */
         mtspr   SPRN_MAS3, r11
 #endif
 #ifdef CONFIG_E200
@@ -1037,6 +1055,63 @@ _GLOBAL(flush_dcache_L1)
 
         blr
 
+#ifdef CONFIG_SMP
+/* When we get here, r24 needs to hold the CPU # */
+        .globl __secondary_start
+__secondary_start:
+        lis     r3,__secondary_hold_acknowledge@h
+        ori     r3,r3,__secondary_hold_acknowledge@l
+        stw     r24,0(r3)
+
+        li      r3,0
+        mr      r4,r24          /* Why? */
+        bl      call_setup_cpu
+
+        lis     r3,tlbcam_index@ha
+        lwz     r3,tlbcam_index@l(r3)
+        mtctr   r3
+        li      r26,0           /* r26 safe? */
+
+        /* Load each CAM entry */
+1:      mr      r3,r26
+        bl      loadcam_entry
+        addi    r26,r26,1
+        bdnz    1b
+
+        /* get current_thread_info and current */
+        lis     r1,secondary_ti@ha
+        lwz     r1,secondary_ti@l(r1)
+        lwz     r2,TI_TASK(r1)
+
+        /* stack */
+        addi    r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
+        li      r0,0
+        stw     r0,0(r1)
+
+        /* ptr to current thread */
+        addi    r4,r2,THREAD    /* address of our thread_struct */
+        mtspr   SPRN_SPRG3,r4
+
+        /* Setup the defaults for TLB entries */
+        li      r4,(MAS4_TSIZED(BOOKE_PAGESZ_4K))@l
+        mtspr   SPRN_MAS4,r4
+
+        /* Jump to start_secondary */
+        lis     r4,MSR_KERNEL@h
+        ori     r4,r4,MSR_KERNEL@l
+        lis     r3,start_secondary@h
+        ori     r3,r3,start_secondary@l
+        mtspr   SPRN_SRR0,r3
+        mtspr   SPRN_SRR1,r4
+        sync
+        rfi
+        sync
+
+        .globl __secondary_hold_acknowledge
+__secondary_hold_acknowledge:
+        .long   -1
+#endif
+
 /*
  * We put a few things here that have to be page-aligned. This stuff
  * goes at the beginning of the data segment, which is page-aligned.
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 64299d28f364..6e3f62493659 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -47,7 +47,7 @@
 #include <asm/abs_addr.h>
 
 static struct device ibmebus_bus_device = { /* fake "parent" device */
-        .bus_id = "ibmebus",
+        .init_name = "ibmebus",
 };
 
 struct bus_type ibmebus_bus_type;
@@ -231,6 +231,7 @@ void ibmebus_free_irq(u32 ist, void *dev_id)
         unsigned int irq = irq_find_mapping(NULL, ist);
 
         free_irq(irq, dev_id);
+        irq_dispose_mapping(irq);
 }
 EXPORT_SYMBOL(ibmebus_free_irq);
 
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index ac2a21f45c75..b3abebb7ee64 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -13,13 +13,17 @@
 #include <linux/reboot.h>
 #include <linux/threads.h>
 #include <linux/lmb.h>
+#include <linux/of.h>
 #include <asm/machdep.h>
 #include <asm/prom.h>
+#include <asm/sections.h>
 
 void machine_crash_shutdown(struct pt_regs *regs)
 {
         if (ppc_md.machine_crash_shutdown)
                 ppc_md.machine_crash_shutdown(regs);
+        else
+                default_machine_crash_shutdown(regs);
 }
 
 /*
@@ -31,11 +35,8 @@ int machine_kexec_prepare(struct kimage *image)
 {
         if (ppc_md.machine_kexec_prepare)
                 return ppc_md.machine_kexec_prepare(image);
-        /*
-         * Fail if platform doesn't provide its own machine_kexec_prepare
-         * implementation.
-         */
-        return -ENOSYS;
+        else
+                return default_machine_kexec_prepare(image);
 }
 
 void machine_kexec_cleanup(struct kimage *image)
@@ -52,13 +53,11 @@ void machine_kexec(struct kimage *image)
 {
         if (ppc_md.machine_kexec)
                 ppc_md.machine_kexec(image);
-        else {
-                /*
-                 * Fall back to normal restart if platform doesn't provide
-                 * its own kexec function, and user insist to kexec...
-                 */
-                machine_restart(NULL);
-        }
+        else
+                default_machine_kexec(image);
+
+        /* Fall back to normal restart if we're still alive. */
+        machine_restart(NULL);
         for(;;);
 }
 
@@ -118,3 +117,71 @@ int overlaps_crashkernel(unsigned long start, unsigned long size)
 {
         return (start + size) > crashk_res.start && start <= crashk_res.end;
 }
+
+/* Values we need to export to the second kernel via the device tree. */
+static unsigned long kernel_end;
+static unsigned long crashk_size;
+
+static struct property kernel_end_prop = {
+        .name = "linux,kernel-end",
+        .length = sizeof(unsigned long),
+        .value = &kernel_end,
+};
+
+static struct property crashk_base_prop = {
+        .name = "linux,crashkernel-base",
+        .length = sizeof(unsigned long),
+        .value = &crashk_res.start,
+};
+
+static struct property crashk_size_prop = {
+        .name = "linux,crashkernel-size",
+        .length = sizeof(unsigned long),
+        .value = &crashk_size,
+};
+
+static void __init export_crashk_values(struct device_node *node)
+{
+        struct property *prop;
+
+        /* There might be existing crash kernel properties, but we can't
+         * be sure what's in them, so remove them. */
+        prop = of_find_property(node, "linux,crashkernel-base", NULL);
+        if (prop)
+                prom_remove_property(node, prop);
+
+        prop = of_find_property(node, "linux,crashkernel-size", NULL);
+        if (prop)
+                prom_remove_property(node, prop);
+
+        if (crashk_res.start != 0) {
+                prom_add_property(node, &crashk_base_prop);
+                crashk_size = crashk_res.end - crashk_res.start + 1;
+                prom_add_property(node, &crashk_size_prop);
+        }
+}
+
+static int __init kexec_setup(void)
+{
+        struct device_node *node;
+        struct property *prop;
+
+        node = of_find_node_by_path("/chosen");
+        if (!node)
+                return -ENOENT;
+
+        /* remove any stale properties so ours can be found */
+        prop = of_find_property(node, kernel_end_prop.name, NULL);
+        if (prop)
+                prom_remove_property(node, prop);
+
+        /* information needed by userspace when using default_machine_kexec */
+        kernel_end = __pa(_end);
+        prom_add_property(node, &kernel_end_prop);
+
+        export_crashk_values(node);
+
+        of_node_put(node);
+        return 0;
+}
+late_initcall(kexec_setup);
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 3c4ca046e854..49e705fcee6d 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -289,7 +289,7 @@ void default_machine_kexec(struct kimage *image)
 }
 
 /* Values we need to export to the second kernel via the device tree. */
-static unsigned long htab_base, kernel_end;
+static unsigned long htab_base;
 
 static struct property htab_base_prop = {
         .name = "linux,htab-base",
@@ -303,25 +303,20 @@ static struct property htab_size_prop = {
         .value = &htab_size_bytes,
 };
 
-static struct property kernel_end_prop = {
-        .name = "linux,kernel-end",
-        .length = sizeof(unsigned long),
-        .value = &kernel_end,
-};
-
-static void __init export_htab_values(void)
+static int __init export_htab_values(void)
 {
         struct device_node *node;
         struct property *prop;
 
+        /* On machines with no htab htab_address is NULL */
+        if (!htab_address)
+                return -ENODEV;
+
         node = of_find_node_by_path("/chosen");
         if (!node)
-                return;
+                return -ENODEV;
 
         /* remove any stale propertys so ours can be found */
-        prop = of_find_property(node, kernel_end_prop.name, NULL);
-        if (prop)
-                prom_remove_property(node, prop);
         prop = of_find_property(node, htab_base_prop.name, NULL);
         if (prop)
                 prom_remove_property(node, prop);
@@ -329,68 +324,11 @@ static void __init export_htab_values(void)
         if (prop)
                 prom_remove_property(node, prop);
 
-        /* information needed by userspace when using default_machine_kexec */
-        kernel_end = __pa(_end);
-        prom_add_property(node, &kernel_end_prop);
-
-        /* On machines with no htab htab_address is NULL */
-        if (NULL == htab_address)
-                goto out;
-
         htab_base = __pa(htab_address);
         prom_add_property(node, &htab_base_prop);
         prom_add_property(node, &htab_size_prop);
 
- out:
-        of_node_put(node);
-}
-
-static struct property crashk_base_prop = {
-        .name = "linux,crashkernel-base",
-        .length = sizeof(unsigned long),
-        .value = &crashk_res.start,
-};
-
-static unsigned long crashk_size;
-
-static struct property crashk_size_prop = {
-        .name = "linux,crashkernel-size",
-        .length = sizeof(unsigned long),
-        .value = &crashk_size,
-};
-
-static void __init export_crashk_values(void)
-{
-        struct device_node *node;
-        struct property *prop;
-
-        node = of_find_node_by_path("/chosen");
-        if (!node)
-                return;
-
-        /* There might be existing crash kernel properties, but we can't
-         * be sure what's in them, so remove them. */
-        prop = of_find_property(node, "linux,crashkernel-base", NULL);
-        if (prop)
-                prom_remove_property(node, prop);
-
-        prop = of_find_property(node, "linux,crashkernel-size", NULL);
-        if (prop)
-                prom_remove_property(node, prop);
-
-        if (crashk_res.start != 0) {
-                prom_add_property(node, &crashk_base_prop);
-                crashk_size = crashk_res.end - crashk_res.start + 1;
-                prom_add_property(node, &crashk_size_prop);
-        }
-
         of_node_put(node);
-}
-
-static int __init kexec_setup(void)
-{
-        export_htab_values();
-        export_crashk_values();
         return 0;
 }
-__initcall(kexec_setup);
+late_initcall(export_htab_values);
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 5c33bc14bd9f..15f28e0de78d 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -29,6 +29,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/processor.h>
 #include <asm/kexec.h>
+#include <asm/bug.h>
 
         .text
 
@@ -271,231 +272,6 @@ _GLOBAL(real_writeb)
 
 #endif /* CONFIG_40x */
 
-/*
- * Flush MMU TLB
- */
-#ifndef CONFIG_FSL_BOOKE
-_GLOBAL(_tlbil_all)
-_GLOBAL(_tlbil_pid)
-#endif
-_GLOBAL(_tlbia)
-#if defined(CONFIG_40x)
-        sync                    /* Flush to memory before changing mapping */
-        tlbia
-        isync                   /* Flush shadow TLB */
-#elif defined(CONFIG_44x)
-        li      r3,0
-        sync
-
-        /* Load high watermark */
-        lis     r4,tlb_44x_hwater@ha
-        lwz     r5,tlb_44x_hwater@l(r4)
-
-1:      tlbwe   r3,r3,PPC44x_TLB_PAGEID
-        addi    r3,r3,1
-        cmpw    0,r3,r5
-        ble     1b
-
-        isync
-#elif defined(CONFIG_FSL_BOOKE)
-        /* Invalidate all entries in TLB0 */
-        li      r3, 0x04
-        tlbivax 0,3
-        /* Invalidate all entries in TLB1 */
-        li      r3, 0x0c
-        tlbivax 0,3
-        msync
-#ifdef CONFIG_SMP
-        tlbsync
-#endif /* CONFIG_SMP */
-#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */
-#if defined(CONFIG_SMP)
-        rlwinm  r8,r1,0,0,(31-THREAD_SHIFT)
-        lwz     r8,TI_CPU(r8)
-        oris    r8,r8,10
-        mfmsr   r10
-        SYNC
-        rlwinm  r0,r10,0,17,15          /* clear bit 16 (MSR_EE) */
-        rlwinm  r0,r0,0,28,26           /* clear DR */
-        mtmsr   r0
-        SYNC_601
-        isync
-        lis     r9,mmu_hash_lock@h
-        ori     r9,r9,mmu_hash_lock@l
-        tophys(r9,r9)
-10:     lwarx   r7,0,r9
-        cmpwi   0,r7,0
-        bne-    10b
-        stwcx.  r8,0,r9
-        bne-    10b
-        sync
-        tlbia
-        sync
-        TLBSYNC
-        li      r0,0
-        stw     r0,0(r9)                /* clear mmu_hash_lock */
-        mtmsr   r10
-        SYNC_601
-        isync
-#else /* CONFIG_SMP */
-        sync
-        tlbia
-        sync
-#endif /* CONFIG_SMP */
-#endif /* ! defined(CONFIG_40x) */
-        blr
-
-/*
- * Flush MMU TLB for a particular address
- */
-#ifndef CONFIG_FSL_BOOKE
-_GLOBAL(_tlbil_va)
-#endif
-_GLOBAL(_tlbie)
-#if defined(CONFIG_40x)
-        /* We run the search with interrupts disabled because we have to change
-         * the PID and I don't want to preempt when that happens.
-         */
-        mfmsr   r5
-        mfspr   r6,SPRN_PID
-        wrteei  0
-        mtspr   SPRN_PID,r4
-        tlbsx.  r3, 0, r3
-        mtspr   SPRN_PID,r6
-        wrtee   r5
-        bne     10f
-        sync
-        /* There are only 64 TLB entries, so r3 < 64, which means bit 25 is clear.
-         * Since 25 is the V bit in the TLB_TAG, loading this value will invalidate
-         * the TLB entry. */
-        tlbwe   r3, r3, TLB_TAG
-        isync
-10:
-
-#elif defined(CONFIG_44x)
-        mfspr   r5,SPRN_MMUCR
-        rlwimi  r5,r4,0,24,31                   /* Set TID */
-
-        /* We have to run the search with interrupts disabled, even critical
-         * and debug interrupts (in fact the only critical exceptions we have
-         * are debug and machine check).  Otherwise  an interrupt which causes
-         * a TLB miss can clobber the MMUCR between the mtspr and the tlbsx. */
-        mfmsr   r4
-        lis     r6,(MSR_EE|MSR_CE|MSR_ME|MSR_DE)@ha
-        addi    r6,r6,(MSR_EE|MSR_CE|MSR_ME|MSR_DE)@l
-        andc    r6,r4,r6
-        mtmsr   r6
-        mtspr   SPRN_MMUCR,r5
-        tlbsx.  r3, 0, r3
-        mtmsr   r4
-        bne     10f
-        sync
-        /* There are only 64 TLB entries, so r3 < 64,
-         * which means bit 22, is clear.  Since 22 is
-         * the V bit in the TLB_PAGEID, loading this
-         * value will invalidate the TLB entry.
-         */
-        tlbwe   r3, r3, PPC44x_TLB_PAGEID
-        isync
-10:
-#elif defined(CONFIG_FSL_BOOKE)
-        rlwinm  r4, r3, 0, 0, 19
-        ori     r5, r4, 0x08    /* TLBSEL = 1 */
-        tlbivax 0, r4
-        tlbivax 0, r5
-        msync
-#if defined(CONFIG_SMP)
-        tlbsync
-#endif /* CONFIG_SMP */
-#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */
-#if defined(CONFIG_SMP)
-        rlwinm  r8,r1,0,0,(31-THREAD_SHIFT)
-        lwz     r8,TI_CPU(r8)
-        oris    r8,r8,11
-        mfmsr   r10
-        SYNC
-        rlwinm  r0,r10,0,17,15          /* clear bit 16 (MSR_EE) */
-        rlwinm  r0,r0,0,28,26           /* clear DR */
-        mtmsr   r0
-        SYNC_601
-        isync
-        lis     r9,mmu_hash_lock@h
-        ori     r9,r9,mmu_hash_lock@l
-        tophys(r9,r9)
-10:     lwarx   r7,0,r9
-        cmpwi   0,r7,0
-        bne-    10b
-        stwcx.  r8,0,r9
-        bne-    10b
-        eieio
-        tlbie   r3
-        sync
-        TLBSYNC
-        li      r0,0
-        stw     r0,0(r9)                /* clear mmu_hash_lock */
-        mtmsr   r10
-        SYNC_601
-        isync
-#else /* CONFIG_SMP */
-        tlbie   r3
-        sync
-#endif /* CONFIG_SMP */
-#endif /* ! CONFIG_40x */
-        blr
-
-#if defined(CONFIG_FSL_BOOKE)
-/*
- * Flush MMU TLB, but only on the local processor (no broadcast)
- */
-_GLOBAL(_tlbil_all)
-#define MMUCSR0_TLBFI   (MMUCSR0_TLB0FI | MMUCSR0_TLB1FI | \
-                         MMUCSR0_TLB2FI | MMUCSR0_TLB3FI)
-        li      r3,(MMUCSR0_TLBFI)@l
-        mtspr   SPRN_MMUCSR0, r3
-1:
-        mfspr   r3,SPRN_MMUCSR0
-        andi.   r3,r3,MMUCSR0_TLBFI@l
-        bne     1b
-        blr
-
-/*
- * Flush MMU TLB for a particular process id, but only on the local processor
- * (no broadcast)
- */
-_GLOBAL(_tlbil_pid)
-/* we currently do an invalidate all since we don't have per pid invalidate */
-        li      r3,(MMUCSR0_TLBFI)@l
-        mtspr   SPRN_MMUCSR0, r3
-1:
-        mfspr   r3,SPRN_MMUCSR0
-        andi.   r3,r3,MMUCSR0_TLBFI@l
-        bne     1b
-        msync
-        isync
-        blr
-
-/*
- * Flush MMU TLB for a particular address, but only on the local processor
- * (no broadcast)
- */
-_GLOBAL(_tlbil_va)
-        mfmsr   r10
-        wrteei  0
-        slwi    r4,r4,16
-        mtspr   SPRN_MAS6,r4            /* assume AS=0 for now */
-        tlbsx   0,r3
-        mfspr   r4,SPRN_MAS1            /* check valid */
-        andis.  r3,r4,MAS1_VALID@h
-        beq     1f
-        rlwinm  r4,r4,0,1,31
-        mtspr   SPRN_MAS1,r4
-        tlbwe
-        msync
-        isync
-1:      wrtee   r10
-        blr
-#endif /* CONFIG_FSL_BOOKE */
-
 
 /*
  * Flush instruction cache.
@@ -650,8 +426,8 @@ _GLOBAL(__flush_dcache_icache)
 BEGIN_FTR_SECTION
         blr
 END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
-        rlwinm  r3,r3,0,0,19                    /* Get page base address */
-        li      r4,4096/L1_CACHE_BYTES  /* Number of lines in a page */
+        rlwinm  r3,r3,0,0,31-PAGE_SHIFT         /* Get page base address */
+        li      r4,PAGE_SIZE/L1_CACHE_BYTES     /* Number of lines in a page */
         mtctr   r4
         mr      r6,r3
 0:      dcbst   0,r3                            /* Write line to ram */
@@ -691,8 +467,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
         rlwinm  r0,r10,0,28,26                  /* clear DR */
         mtmsr   r0
         isync
-        rlwinm  r3,r3,0,0,19                    /* Get page base address */
-        li      r4,4096/L1_CACHE_BYTES  /* Number of lines in a page */
+        rlwinm  r3,r3,0,0,31-PAGE_SHIFT         /* Get page base address */
+        li      r4,PAGE_SIZE/L1_CACHE_BYTES     /* Number of lines in a page */
         mtctr   r4
         mr      r6,r3
 0:      dcbst   0,r3                            /* Write line to ram */
@@ -716,7 +492,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
  * void clear_pages(void *page, int order) ;
  */
 _GLOBAL(clear_pages)
-        li      r0,4096/L1_CACHE_BYTES
+        li      r0,PAGE_SIZE/L1_CACHE_BYTES
         slw     r0,r0,r4
         mtctr   r0
 #ifdef CONFIG_8xx
@@ -774,7 +550,7 @@ _GLOBAL(copy_page)
         dcbt    r5,r4
         li      r11,L1_CACHE_BYTES+4
 #endif /* MAX_COPY_PREFETCH */
-        li      r0,4096/L1_CACHE_BYTES - MAX_COPY_PREFETCH
+        li      r0,PAGE_SIZE/L1_CACHE_BYTES - MAX_COPY_PREFETCH
         crclr   4*cr0+eq
 2:
         mtctr   r0
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index 7ff292475269..43e7e3a7f130 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -78,6 +78,12 @@ int module_finalize(const Elf_Ehdr *hdr,
                                   (void *)sect->sh_addr,
                                   (void *)sect->sh_addr + sect->sh_size);
 
+        sect = find_section(hdr, sechdrs, "__mmu_ftr_fixup");
+        if (sect != NULL)
+                do_feature_fixups(cur_cpu_spec->mmu_features,
+                                  (void *)sect->sh_addr,
+                                  (void *)sect->sh_addr + sect->sh_size);
+
 #ifdef CONFIG_PPC64
         sect = find_section(hdr, sechdrs, "__fw_ftr_fixup");
         if (sect != NULL)
diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c
index f3c9cae01dd5..fa983a59c4ce 100644
--- a/arch/powerpc/kernel/of_device.c
+++ b/arch/powerpc/kernel/of_device.c
@@ -14,7 +14,6 @@ static void of_device_make_bus_id(struct of_device *dev)
 {
         static atomic_t bus_no_reg_magic;
         struct device_node *node = dev->node;
-        char *name = dev->dev.bus_id;
         const u32 *reg;
         u64 addr;
         int magic;
@@ -27,14 +26,12 @@ static void of_device_make_bus_id(struct of_device *dev)
         reg = of_get_property(node, "dcr-reg", NULL);
         if (reg) {
 #ifdef CONFIG_PPC_DCR_NATIVE
-                snprintf(name, BUS_ID_SIZE, "d%x.%s",
-                         *reg, node->name);
+                dev_set_name(&dev->dev, "d%x.%s", *reg, node->name);
 #else /* CONFIG_PPC_DCR_NATIVE */
                 addr = of_translate_dcr_address(node, *reg, NULL);
                 if (addr != OF_BAD_ADDR) {
-                        snprintf(name, BUS_ID_SIZE,
-                                 "D%llx.%s", (unsigned long long)addr,
-                                 node->name);
+                        dev_set_name(&dev->dev, "D%llx.%s",
+                                     (unsigned long long)addr, node->name);
                         return;
                 }
 #endif /* !CONFIG_PPC_DCR_NATIVE */
@@ -48,9 +45,8 @@ static void of_device_make_bus_id(struct of_device *dev)
         if (reg) {
                 addr = of_translate_address(node, reg);
                 if (addr != OF_BAD_ADDR) {
-                        snprintf(name, BUS_ID_SIZE,
-                                 "%llx.%s", (unsigned long long)addr,
-                                 node->name);
+                        dev_set_name(&dev->dev, "%llx.%s",
+                                     (unsigned long long)addr, node->name);
                         return;
                 }
         }
@@ -60,7 +56,7 @@ static void of_device_make_bus_id(struct of_device *dev)
          * counter (and pray...)
          */
         magic = atomic_add_return(1, &bus_no_reg_magic);
-        snprintf(name, BUS_ID_SIZE, "%s.%d", node->name, magic - 1);
+        dev_set_name(&dev->dev, "%s.%d", node->name, magic - 1);
 }
 
 struct of_device *of_device_alloc(struct device_node *np,
@@ -80,7 +76,7 @@ struct of_device *of_device_alloc(struct device_node *np,
         dev->dev.archdata.of_node = np;
 
         if (bus_id)
-                strlcpy(dev->dev.bus_id, bus_id, BUS_ID_SIZE);
+                dev_set_name(&dev->dev, bus_id);
         else
                 of_device_make_bus_id(dev);
 
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 48a347133f41..c744b327bcab 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -37,6 +37,7 @@ struct lppaca lppaca[] = {
                 .end_of_quantum = 0xfffffffffffffffful,
                 .slb_count = 64,
                 .vmxregs_in_use = 0,
+                .page_ins = 0,
         },
 };
 
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index f36936d9fda3..2538030954d8 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -37,13 +37,7 @@
 #include <asm/machdep.h>
 #include <asm/ppc-pci.h>
 #include <asm/firmware.h>
-
-#ifdef DEBUG
-#include <asm/udbg.h>
-#define DBG(fmt...) printk(fmt)
-#else
-#define DBG(fmt...)
-#endif
+#include <asm/eeh.h>
 
 static DEFINE_SPINLOCK(hose_spinlock);
 
@@ -53,8 +47,9 @@ static int global_phb_number;		/* Global phb counter */
 /* ISA Memory physical address */
 resource_size_t isa_mem_base;
 
-/* Default PCI flags is 0 */
-unsigned int ppc_pci_flags;
+/* Default PCI flags is 0 on ppc32, modified at boot on ppc64 */
+unsigned int ppc_pci_flags = 0;
+
 
 static struct dma_mapping_ops *pci_dma_ops;
 
@@ -165,8 +160,6 @@ EXPORT_SYMBOL(pci_domain_nr);
  */
 struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node)
 {
-        if (!have_of)
-                return NULL;
         while(node) {
                 struct pci_controller *hose, *tmp;
                 list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
@@ -208,26 +201,6 @@ char __devinit *pcibios_setup(char *str)
         return str;
 }
 
-void __devinit pcibios_setup_new_device(struct pci_dev *dev)
-{
-        struct dev_archdata *sd = &dev->dev.archdata;
-
-        sd->of_node = pci_device_to_OF_node(dev);
-
-        DBG("PCI: device %s OF node: %s\n", pci_name(dev),
-            sd->of_node ? sd->of_node->full_name : "<none>");
-
-        sd->dma_ops = pci_dma_ops;
-#ifdef CONFIG_PPC32
-        sd->dma_data = (void *)PCI_DRAM_OFFSET;
-#endif
-        set_dev_node(&dev->dev, pcibus_to_node(dev->bus));
-
-        if (ppc_md.pci_dma_dev_setup)
-                ppc_md.pci_dma_dev_setup(dev);
-}
-EXPORT_SYMBOL(pcibios_setup_new_device);
-
 /*
  * Reads the interrupt pin to determine if interrupt is use by card.
  * If the interrupt is used, then gets the interrupt line from the
@@ -252,7 +225,7 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
                 return -1;
 #endif
 
-        DBG("Try to map irq for %s...\n", pci_name(pci_dev));
+        pr_debug("PCI: Try to map irq for %s...\n", pci_name(pci_dev));
 
 #ifdef DEBUG
         memset(&oirq, 0xff, sizeof(oirq));
@@ -276,26 +249,26 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
                     line == 0xff || line == 0) {
                         return -1;
                 }
-                DBG(" -> no map ! Using line %d (pin %d) from PCI config\n",
-                    line, pin);
+                pr_debug(" No map ! Using line %d (pin %d) from PCI config\n",
+                         line, pin);
 
                 virq = irq_create_mapping(NULL, line);
                 if (virq != NO_IRQ)
                         set_irq_type(virq, IRQ_TYPE_LEVEL_LOW);
         } else {
-                DBG(" -> got one, spec %d cells (0x%08x 0x%08x...) on %s\n",
-                    oirq.size, oirq.specifier[0], oirq.specifier[1],
+                pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %s\n",
+                         oirq.size, oirq.specifier[0], oirq.specifier[1],
                     oirq.controller->full_name);
 
                 virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
                                              oirq.size);
         }
         if(virq == NO_IRQ) {
-                DBG(" -> failed to map !\n");
+                pr_debug(" Failed to map !\n");
                 return -1;
         }
 
-        DBG(" -> mapped to linux irq %d\n", virq);
+        pr_debug(" Mapped to linux irq %d\n", virq);
 
         pci_dev->irq = virq;
 
@@ -397,13 +370,10 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
         }
 
         /* XXX would be nice to have a way to ask for write-through */
-        prot |= _PAGE_NO_CACHE;
         if (write_combine)
-                prot &= ~_PAGE_GUARDED;
+                return pgprot_noncached_wc(prot);
         else
-                prot |= _PAGE_GUARDED;
-
-        return __pgprot(prot);
+                return pgprot_noncached(prot);
 }
 
 /*
@@ -414,19 +384,17 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
 pgprot_t pci_phys_mem_access_prot(struct file *file,
                                   unsigned long pfn,
                                   unsigned long size,
-                                  pgprot_t protection)
+                                  pgprot_t prot)
 {
         struct pci_dev *pdev = NULL;
         struct resource *found = NULL;
-        unsigned long prot = pgprot_val(protection);
         resource_size_t offset = ((resource_size_t)pfn) << PAGE_SHIFT;
         int i;
 
         if (page_is_ram(pfn))
-                return __pgprot(prot);
-
-        prot |= _PAGE_NO_CACHE | _PAGE_GUARDED;
+                return prot;
 
+        prot = pgprot_noncached(prot);
         for_each_pci_dev(pdev) {
                 for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
                         struct resource *rp = &pdev->resource[i];
@@ -447,14 +415,14 @@ pgprot_t pci_phys_mem_access_prot(struct file *file,
         }
         if (found) {
                 if (found->flags & IORESOURCE_PREFETCH)
-                        prot &= ~_PAGE_GUARDED;
+                        prot = pgprot_noncached_wc(prot);
                 pci_dev_put(pdev);
         }
 
-        DBG("non-PCI map for %llx, prot: %lx\n",
-            (unsigned long long)offset, prot);
+        pr_debug("PCI: Non-PCI map for %llx, prot: %lx\n",
+                 (unsigned long long)offset, pgprot_val(prot));
 
-        return __pgprot(prot);
+        return prot;
 }
 
 
@@ -610,8 +578,7 @@ int pci_mmap_legacy_page_range(struct pci_bus *bus,
         pr_debug(" -> mapping phys %llx\n", (unsigned long long)offset);
 
         vma->vm_pgoff = offset >> PAGE_SHIFT;
-        vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
-                                     | _PAGE_NO_CACHE | _PAGE_GUARDED);
+        vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
         return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
                                vma->vm_end - vma->vm_start,
                                vma->vm_page_prot);
@@ -853,15 +820,12 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose,
 int pci_proc_domain(struct pci_bus *bus)
 {
         struct pci_controller *hose = pci_bus_to_host(bus);
-#ifdef CONFIG_PPC64
-        return hose->buid != 0;
-#else
+
         if (!(ppc_pci_flags & PPC_PCI_ENABLE_PROC_DOMAINS))
                 return 0;
         if (ppc_pci_flags & PPC_PCI_COMPAT_DOMAIN_0)
                 return hose->global_number != 0;
         return 1;
-#endif
 }
 
 void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
@@ -1083,27 +1047,50 @@ static void __devinit pcibios_fixup_bridge(struct pci_bus *bus)
         }
 }
 
-static void __devinit __pcibios_fixup_bus(struct pci_bus *bus)
+void __devinit pcibios_setup_bus_self(struct pci_bus *bus)
 {
-        struct pci_dev *dev = bus->self;
-
-        pr_debug("PCI: Fixup bus %d (%s)\n", bus->number, dev ? pci_name(dev) : "PHB");
-
-        /* Fixup PCI<->PCI bridges. Host bridges are handled separately, for
-         * now differently between 32 and 64 bits.
-         */
-        if (dev != NULL)
+        /* Fix up the bus resources for P2P bridges */
+        if (bus->self != NULL)
                 pcibios_fixup_bridge(bus);
 
-        /* Additional setup that is different between 32 and 64 bits for now */
-        pcibios_do_bus_setup(bus);
-
-        /* Platform specific bus fixups */
+        /* Platform specific bus fixups. This is currently only used
+         * by fsl_pci and I'm hoping to get rid of it at some point
+         */
         if (ppc_md.pcibios_fixup_bus)
                 ppc_md.pcibios_fixup_bus(bus);
 
-        /* Read default IRQs and fixup if necessary */
+        /* Setup bus DMA mappings */
+        if (ppc_md.pci_dma_bus_setup)
+                ppc_md.pci_dma_bus_setup(bus);
+}
+
+void __devinit pcibios_setup_bus_devices(struct pci_bus *bus)
+{
+        struct pci_dev *dev;
+
+        pr_debug("PCI: Fixup bus devices %d (%s)\n",
+                 bus->number, bus->self ? pci_name(bus->self) : "PHB");
+
         list_for_each_entry(dev, &bus->devices, bus_list) {
+                struct dev_archdata *sd = &dev->dev.archdata;
+
+                /* Setup OF node pointer in archdata */
+                sd->of_node = pci_device_to_OF_node(dev);
+
+                /* Fixup NUMA node as it may not be setup yet by the generic
+                 * code and is needed by the DMA init
+                 */
+                set_dev_node(&dev->dev, pcibus_to_node(dev->bus));
+
+                /* Hook up default DMA ops */
+                sd->dma_ops = pci_dma_ops;
+                sd->dma_data = (void *)PCI_DRAM_OFFSET;
+
+                /* Additional platform DMA/iommu setup */
+                if (ppc_md.pci_dma_dev_setup)
+                        ppc_md.pci_dma_dev_setup(dev);
+
+                /* Read default IRQs and fixup if necessary */
                 pci_read_irq_line(dev);
                 if (ppc_md.pci_irq_fixup)
                         ppc_md.pci_irq_fixup(dev);
@@ -1113,22 +1100,19 @@ static void __devinit __pcibios_fixup_bus(struct pci_bus *bus)
 void __devinit pcibios_fixup_bus(struct pci_bus *bus)
 {
         /* When called from the generic PCI probe, read PCI<->PCI bridge
-         * bases before proceeding
+         * bases. This is -not- called when generating the PCI tree from
+         * the OF device-tree.
          */
         if (bus->self != NULL)
                 pci_read_bridge_bases(bus);
-        __pcibios_fixup_bus(bus);
-}
-EXPORT_SYMBOL(pcibios_fixup_bus);
 
-/* When building a bus from the OF tree rather than probing, we need a
- * slightly different version of the fixup which doesn't read the
- * bridge bases using config space accesses
- */
-void __devinit pcibios_fixup_of_probed_bus(struct pci_bus *bus)
-{
-        __pcibios_fixup_bus(bus);
+        /* Now fixup the bus bus */
+        pcibios_setup_bus_self(bus);
+
+        /* Now fixup devices on that bus */
+        pcibios_setup_bus_devices(bus);
 }
+EXPORT_SYMBOL(pcibios_fixup_bus);
 
 static int skip_isa_ioresource_align(struct pci_dev *dev)
 {
@@ -1198,10 +1182,10 @@ static int __init reparent_resources(struct resource *parent,
         *pp = NULL;
         for (p = res->child; p != NULL; p = p->sibling) {
                 p->parent = res;
-                DBG(KERN_INFO "PCI: reparented %s [%llx..%llx] under %s\n",
-                    p->name,
-                    (unsigned long long)p->start,
-                    (unsigned long long)p->end, res->name);
+                pr_debug("PCI: Reparented %s [%llx..%llx] under %s\n",
+                         p->name,
+                         (unsigned long long)p->start,
+                         (unsigned long long)p->end, res->name);
         }
         return 0;
 }
@@ -1245,9 +1229,12 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus)
         int i;
         struct resource *res, *pr;
 
+        pr_debug("PCI: Allocating bus resources for %04x:%02x...\n",
+                 pci_domain_nr(bus), bus->number);
+
         for (i = 0; i < PCI_BUS_NUM_RESOURCES; ++i) {
                 if ((res = bus->resource[i]) == NULL || !res->flags
-                    || res->start > res->end)
+                    || res->start > res->end || res->parent)
                         continue;
                 if (bus->parent == NULL)
                         pr = (res->flags & IORESOURCE_IO) ?
@@ -1271,14 +1258,14 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus)
                         }
                 }
 
-                DBG("PCI: %s (bus %d) bridge rsrc %d: %016llx-%016llx "
-                    "[0x%x], parent %p (%s)\n",
-                    bus->self ? pci_name(bus->self) : "PHB",
-                    bus->number, i,
-                    (unsigned long long)res->start,
-                    (unsigned long long)res->end,
-                    (unsigned int)res->flags,
-                    pr, (pr && pr->name) ? pr->name : "nil");
+                pr_debug("PCI: %s (bus %d) bridge rsrc %d: %016llx-%016llx "
+                         "[0x%x], parent %p (%s)\n",
+                         bus->self ? pci_name(bus->self) : "PHB",
+                         bus->number, i,
+                         (unsigned long long)res->start,
+                         (unsigned long long)res->end,
+                         (unsigned int)res->flags,
+                         pr, (pr && pr->name) ? pr->name : "nil");
 
                 if (pr && !(pr->flags & IORESOURCE_UNSET)) {
                         if (request_resource(pr, res) == 0)
@@ -1305,11 +1292,11 @@ static inline void __devinit alloc_resource(struct pci_dev *dev, int idx)
 {
         struct resource *pr, *r = &dev->resource[idx];
 
-        DBG("PCI: Allocating %s: Resource %d: %016llx..%016llx [%x]\n",
-            pci_name(dev), idx,
-            (unsigned long long)r->start,
-            (unsigned long long)r->end,
-            (unsigned int)r->flags);
+        pr_debug("PCI: Allocating %s: Resource %d: %016llx..%016llx [%x]\n",
+                 pci_name(dev), idx,
+                 (unsigned long long)r->start,
+                 (unsigned long long)r->end,
+                 (unsigned int)r->flags);
 
         pr = pci_find_parent_resource(dev, r);
         if (!pr || (pr->flags & IORESOURCE_UNSET) ||
@@ -1317,10 +1304,11 @@ static inline void __devinit alloc_resource(struct pci_dev *dev, int idx)
                 printk(KERN_WARNING "PCI: Cannot allocate resource region %d"
                        " of device %s, will remap\n", idx, pci_name(dev));
                 if (pr)
-                        DBG("PCI:  parent is %p: %016llx-%016llx [%x]\n", pr,
-                            (unsigned long long)pr->start,
-                            (unsigned long long)pr->end,
-                            (unsigned int)pr->flags);
+                        pr_debug("PCI:  parent is %p: %016llx-%016llx [%x]\n",
+                                 pr,
+                                 (unsigned long long)pr->start,
+                                 (unsigned long long)pr->end,
+                                 (unsigned int)pr->flags);
                 /* We'll assign a new address later */
                 r->flags |= IORESOURCE_UNSET;
                 r->end -= r->start;
@@ -1358,7 +1346,8 @@ static void __init pcibios_allocate_resources(int pass)
                          * but keep it unregistered.
                          */
                         u32 reg;
-                        DBG("PCI: Switching off ROM of %s\n", pci_name(dev));
+                        pr_debug("PCI: Switching off ROM of %s\n",
+                                 pci_name(dev));
                         r->flags &= ~IORESOURCE_ROM_ENABLE;
                         pci_read_config_dword(dev, dev->rom_base_reg, &reg);
                         pci_write_config_dword(dev, dev->rom_base_reg,
@@ -1383,7 +1372,7 @@ void __init pcibios_resource_survey(void)
         }
 
         if (!(ppc_pci_flags & PPC_PCI_PROBE_ONLY)) {
-                DBG("PCI: Assigning unassigned resouces...\n");
+                pr_debug("PCI: Assigning unassigned resouces...\n");
                 pci_assign_unassigned_resources();
         }
 
@@ -1393,9 +1382,11 @@ void __init pcibios_resource_survey(void)
 }
 
 #ifdef CONFIG_HOTPLUG
-/* This is used by the pSeries hotplug driver to allocate resource
+
+/* This is used by the PCI hotplug driver to allocate resource
  * of newly plugged busses. We can try to consolidate with the
- * rest of the code later, for now, keep it as-is
+ * rest of the code later, for now, keep it as-is as our main
+ * resource allocation function doesn't deal with sub-trees yet.
  */
 void __devinit pcibios_claim_one_bus(struct pci_bus *bus)
 {
@@ -1410,6 +1401,14 @@ void __devinit pcibios_claim_one_bus(struct pci_bus *bus)
 
                         if (r->parent || !r->start || !r->flags)
                                 continue;
+
+                        pr_debug("PCI: Claiming %s: "
+                                 "Resource %d: %016llx..%016llx [%x]\n",
+                                 pci_name(dev), i,
+                                 (unsigned long long)r->start,
+                                 (unsigned long long)r->end,
+                                 (unsigned int)r->flags);
+
                         pci_claim_resource(dev, i);
                 }
         }
@@ -1418,6 +1417,31 @@ void __devinit pcibios_claim_one_bus(struct pci_bus *bus)
                 pcibios_claim_one_bus(child_bus);
 }
 EXPORT_SYMBOL_GPL(pcibios_claim_one_bus);
+
+
+/* pcibios_finish_adding_to_bus
+ *
+ * This is to be called by the hotplug code after devices have been
+ * added to a bus, this include calling it for a PHB that is just
+ * being added
+ */
+void pcibios_finish_adding_to_bus(struct pci_bus *bus)
+{
+        pr_debug("PCI: Finishing adding to hotplug bus %04x:%02x\n",
+                 pci_domain_nr(bus), bus->number);
+
+        /* Allocate bus and devices resources */
+        pcibios_allocate_bus_resources(bus);
+        pcibios_claim_one_bus(bus);
+
+        /* Add new devices to global lists.  Register in proc, sysfs. */
+        pci_bus_add_devices(bus);
+
+        /* Fixup EEH */
+        eeh_add_device_tree_late(bus);
+}
+EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus);
+
 #endif /* CONFIG_HOTPLUG */
 
 int pcibios_enable_device(struct pci_dev *dev, int mask)
@@ -1428,3 +1452,61 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 
         return pci_enable_resources(dev, mask);
 }
+
+void __devinit pcibios_setup_phb_resources(struct pci_controller *hose)
+{
+        struct pci_bus *bus = hose->bus;
+        struct resource *res;
+        int i;
+
+        /* Hookup PHB IO resource */
+        bus->resource[0] = res = &hose->io_resource;
+
+        if (!res->flags) {
+                printk(KERN_WARNING "PCI: I/O resource not set for host"
+                       " bridge %s (domain %d)\n",
+                       hose->dn->full_name, hose->global_number);
+#ifdef CONFIG_PPC32
+                /* Workaround for lack of IO resource only on 32-bit */
+                res->start = (unsigned long)hose->io_base_virt - isa_io_base;
+                res->end = res->start + IO_SPACE_LIMIT;
+                res->flags = IORESOURCE_IO;
+#endif /* CONFIG_PPC32 */
+        }
+
+        pr_debug("PCI: PHB IO resource    = %016llx-%016llx [%lx]\n",
+                 (unsigned long long)res->start,
+                 (unsigned long long)res->end,
+                 (unsigned long)res->flags);
+
+        /* Hookup PHB Memory resources */
+        for (i = 0; i < 3; ++i) {
+                res = &hose->mem_resources[i];
+                if (!res->flags) {
+                        if (i > 0)
+                                continue;
+                        printk(KERN_ERR "PCI: Memory resource 0 not set for "
+                               "host bridge %s (domain %d)\n",
+                               hose->dn->full_name, hose->global_number);
+#ifdef CONFIG_PPC32
+                        /* Workaround for lack of MEM resource only on 32-bit */
+                        res->start = hose->pci_mem_offset;
+                        res->end = (resource_size_t)-1LL;
+                        res->flags = IORESOURCE_MEM;
+#endif /* CONFIG_PPC32 */
+                }
+                bus->resource[i+1] = res;
+
+                pr_debug("PCI: PHB MEM resource %d = %016llx-%016llx [%lx]\n", i,
+                         (unsigned long long)res->start,
+                         (unsigned long long)res->end,
+                         (unsigned long)res->flags);
+        }
+
+        pr_debug("PCI: PHB MEM offset     = %016llx\n",
+                 (unsigned long long)hose->pci_mem_offset);
+        pr_debug("PCI: PHB IO  offset     = %08lx\n",
+                 (unsigned long)hose->io_base_virt - _IO_BASE);
+
+}
+
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 131b1dfa68c6..132cd80afa21 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -26,12 +26,6 @@
 
 #undef DEBUG
 
-#ifdef DEBUG
-#define DBG(x...) printk(x)
-#else
-#define DBG(x...)
-#endif
-
 unsigned long isa_io_base     = 0;
 unsigned long pci_dram_offset = 0;
 int pcibios_assign_bus_offset = 1;
@@ -272,17 +266,14 @@ pci_busdev_to_OF_node(struct pci_bus *bus, int devfn)
 {
         struct device_node *parent, *np;
 
-        if (!have_of)
-                return NULL;
-
-        DBG("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn);
+        pr_debug("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn);
         parent = scan_OF_for_pci_bus(bus);
         if (parent == NULL)
                 return NULL;
-        DBG(" parent is %s\n", parent ? parent->full_name : "<NULL>");
+        pr_debug(" parent is %s\n", parent ? parent->full_name : "<NULL>");
         np = scan_OF_for_pci_dev(parent, devfn);
         of_node_put(parent);
-        DBG(" result is %s\n", np ? np->full_name : "<NULL>");
+        pr_debug(" result is %s\n", np ? np->full_name : "<NULL>");
 
         /* XXX most callers don't release the returned node
          * mostly because ppc64 doesn't increase the refcount,
@@ -315,8 +306,6 @@ pci_device_from_OF_node(struct device_node* node, u8* bus, u8* devfn)
         struct pci_controller* hose;
         struct pci_dev* dev = NULL;
         
-        if (!have_of)
-                return -ENODEV;
         /* Make sure it's really a PCI device */
         hose = pci_find_hose_for_OF_device(node);
         if (!hose || !hose->dn)
@@ -379,10 +368,41 @@ void pcibios_make_OF_bus_map(void)
 }
 #endif /* CONFIG_PPC_OF */
 
+static void __devinit pcibios_scan_phb(struct pci_controller *hose)
+{
+        struct pci_bus *bus;
+        struct device_node *node = hose->dn;
+        unsigned long io_offset;
+        struct resource *res = &hose->io_resource;
+
+        pr_debug("PCI: Scanning PHB %s\n",
+                 node ? node->full_name : "<NO NAME>");
+
+        /* Create an empty bus for the toplevel */
+        bus = pci_create_bus(hose->parent, hose->first_busno, hose->ops, hose);
+        if (bus == NULL) {
+                printk(KERN_ERR "Failed to create bus for PCI domain %04x\n",
+                       hose->global_number);
+                return;
+        }
+        bus->secondary = hose->first_busno;
+        hose->bus = bus;
+
+        /* Fixup IO space offset */
+        io_offset = (unsigned long)hose->io_base_virt - isa_io_base;
+        res->start = (res->start + io_offset) & 0xffffffffu;
+        res->end = (res->end + io_offset) & 0xffffffffu;
+
+        /* Wire up PHB bus resources */
+        pcibios_setup_phb_resources(hose);
+
+        /* Scan children */
+        hose->last_busno = bus->subordinate = pci_scan_child_bus(bus);
+}
+
 static int __init pcibios_init(void)
 {
         struct pci_controller *hose, *tmp;
-        struct pci_bus *bus;
         int next_busno = 0;
 
         printk(KERN_INFO "PCI: Probing PCI hardware\n");
@@ -395,12 +415,8 @@ static int __init pcibios_init(void)
                 if (pci_assign_all_buses)
                         hose->first_busno = next_busno;
                 hose->last_busno = 0xff;
-                bus = pci_scan_bus_parented(hose->parent, hose->first_busno,
-                                            hose->ops, hose);
-                if (bus) {
-                        pci_bus_add_devices(bus);
-                        hose->last_busno = bus->subordinate;
-                }
+                pcibios_scan_phb(hose);
+                pci_bus_add_devices(hose->bus);
                 if (pci_assign_all_buses || next_busno <= hose->last_busno)
                         next_busno = hose->last_busno + pcibios_assign_bus_offset;
         }
@@ -410,7 +426,7 @@ static int __init pcibios_init(void)
          * numbers vs. kernel bus numbers since we may have to
          * remap them.
          */
-        if (pci_assign_all_buses && have_of)
+        if (pci_assign_all_buses)
                 pcibios_make_OF_bus_map();
 
         /* Call common code to handle resource allocation */
@@ -425,54 +441,6 @@ static int __init pcibios_init(void)
 
 subsys_initcall(pcibios_init);
 
-void __devinit pcibios_do_bus_setup(struct pci_bus *bus)
-{
-        struct pci_controller *hose = (struct pci_controller *) bus->sysdata;
-        unsigned long io_offset;
-        struct resource *res;
-        int i;
-        struct pci_dev *dev;
-
-        /* Hookup PHB resources */
-        io_offset = (unsigned long)hose->io_base_virt - isa_io_base;
-        if (bus->parent == NULL) {
-                /* This is a host bridge - fill in its resources */
-                hose->bus = bus;
-
-                bus->resource[0] = res = &hose->io_resource;
-                if (!res->flags) {
-                        if (io_offset)
-                                printk(KERN_ERR "I/O resource not set for host"
-                                       " bridge %d\n", hose->global_number);
-                        res->start = 0;
-                        res->end = IO_SPACE_LIMIT;
-                        res->flags = IORESOURCE_IO;
-                }
-                res->start = (res->start + io_offset) & 0xffffffffu;
-                res->end = (res->end + io_offset) & 0xffffffffu;
-
-                for (i = 0; i < 3; ++i) {
-                        res = &hose->mem_resources[i];
-                        if (!res->flags) {
-                                if (i > 0)
-                                        continue;
-                                printk(KERN_ERR "Memory resource not set for "
-                                       "host bridge %d\n", hose->global_number);
-                                res->start = hose->pci_mem_offset;
-                                res->end = ~0U;
-                                res->flags = IORESOURCE_MEM;
-                        }
-                        bus->resource[i+1] = res;
-                }
-        }
-
-        if (ppc_md.pci_dma_bus_setup)
-                ppc_md.pci_dma_bus_setup(bus);
-
-        list_for_each_entry(dev, &bus->devices, bus_list)
-                pcibios_setup_new_device(dev);
-}
-
 /* the next one is stolen from the alpha port... */
 void __init
 pcibios_update_irq(struct pci_dev *dev, int irq)
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 3502b9101e6b..39fadc6e1492 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -32,13 +32,6 @@
 #include <asm/machdep.h>
 #include <asm/ppc-pci.h>
 
-#ifdef DEBUG
-#include <asm/udbg.h>
-#define DBG(fmt...) printk(fmt)
-#else
-#define DBG(fmt...)
-#endif
-
 unsigned long pci_probe_only = 1;
 
 /* pci_io_base -- the base address from which io bars are offsets.
@@ -102,7 +95,7 @@ static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev)
         addrs = of_get_property(node, "assigned-addresses", &proplen);
         if (!addrs)
                 return;
-        DBG("    parse addresses (%d bytes) @ %p\n", proplen, addrs);
+        pr_debug("    parse addresses (%d bytes) @ %p\n", proplen, addrs);
         for (; proplen >= 20; proplen -= 20, addrs += 5) {
                 flags = pci_parse_of_flags(addrs[0]);
                 if (!flags)
@@ -112,8 +105,9 @@ static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev)
                 if (!size)
                         continue;
                 i = addrs[0] & 0xff;
-                DBG("  base: %llx, size: %llx, i: %x\n",
-                    (unsigned long long)base, (unsigned long long)size, i);
+                pr_debug("  base: %llx, size: %llx, i: %x\n",
+                         (unsigned long long)base,
+                         (unsigned long long)size, i);
 
                 if (PCI_BASE_ADDRESS_0 <= i && i <= PCI_BASE_ADDRESS_5) {
                         res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2];
@@ -144,7 +138,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
         if (type == NULL)
                 type = "";
 
-        DBG("    create device, devfn: %x, type: %s\n", devfn, type);
+        pr_debug("    create device, devfn: %x, type: %s\n", devfn, type);
 
         dev->bus = bus;
         dev->sysdata = node;
@@ -165,8 +159,8 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
         dev->class = get_int_prop(node, "class-code", 0);
         dev->revision = get_int_prop(node, "revision-id", 0);
 
-        DBG("    class: 0x%x\n", dev->class);
-        DBG("    revision: 0x%x\n", dev->revision);
+        pr_debug("    class: 0x%x\n", dev->class);
+        pr_debug("    revision: 0x%x\n", dev->revision);
 
         dev->current_state = 4;         /* unknown power state */
         dev->error_state = pci_channel_io_normal;
@@ -187,7 +181,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 
         pci_parse_of_addrs(node, dev);
 
-        DBG("    adding to system ...\n");
+        pr_debug("    adding to system ...\n");
 
         pci_device_add(dev, bus);
 
@@ -195,19 +189,20 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 }
 EXPORT_SYMBOL(of_create_pci_dev);
 
-void __devinit of_scan_bus(struct device_node *node,
-                           struct pci_bus *bus)
+static void __devinit __of_scan_bus(struct device_node *node,
+                                    struct pci_bus *bus, int rescan_existing)
 {
         struct device_node *child;
         const u32 *reg;
         int reglen, devfn;
         struct pci_dev *dev;
 
-        DBG("of_scan_bus(%s) bus no %d... \n", node->full_name, bus->number);
+        pr_debug("of_scan_bus(%s) bus no %d... \n",
+                 node->full_name, bus->number);
 
         /* Scan direct children */
         for_each_child_of_node(node, child) {
-                DBG("  * %s\n", child->full_name);
+                pr_debug("  * %s\n", child->full_name);
                 reg = of_get_property(child, "reg", &reglen);
                 if (reg == NULL || reglen < 20)
                         continue;
@@ -217,11 +212,15 @@ void __devinit of_scan_bus(struct device_node *node,
                 dev = of_create_pci_dev(child, bus, devfn);
                 if (!dev)
                         continue;
-                DBG("    dev header type: %x\n", dev->hdr_type);
+                pr_debug("    dev header type: %x\n", dev->hdr_type);
         }
 
-        /* Ally all fixups */
-        pcibios_fixup_of_probed_bus(bus);
+        /* Apply all fixups necessary. We don't fixup the bus "self"
+         * for an existing bridge that is being rescanned
+         */
+        if (!rescan_existing)
+                pcibios_setup_bus_self(bus);
+        pcibios_setup_bus_devices(bus);
 
         /* Now scan child busses */
         list_for_each_entry(dev, &bus->devices, bus_list) {
@@ -233,7 +232,20 @@ void __devinit of_scan_bus(struct device_node *node,
                 }
         }
 }
-EXPORT_SYMBOL(of_scan_bus);
+
+void __devinit of_scan_bus(struct device_node *node,
+                           struct pci_bus *bus)
+{
+        __of_scan_bus(node, bus, 0);
+}
+EXPORT_SYMBOL_GPL(of_scan_bus);
+
+void __devinit of_rescan_bus(struct device_node *node,
+                             struct pci_bus *bus)
+{
+        __of_scan_bus(node, bus, 1);
+}
+EXPORT_SYMBOL_GPL(of_rescan_bus);
 
 void __devinit of_scan_pci_bridge(struct device_node *node,
                                   struct pci_dev *dev)
@@ -245,7 +257,7 @@ void __devinit of_scan_pci_bridge(struct device_node *node,
         unsigned int flags;
         u64 size;
 
-        DBG("of_scan_pci_bridge(%s)\n", node->full_name);
+        pr_debug("of_scan_pci_bridge(%s)\n", node->full_name);
 
         /* parse bus-range property */
         busrange = of_get_property(node, "bus-range", &len);
@@ -309,12 +321,12 @@ void __devinit of_scan_pci_bridge(struct device_node *node,
         }
         sprintf(bus->name, "PCI Bus %04x:%02x", pci_domain_nr(bus),
                 bus->number);
-        DBG("    bus name: %s\n", bus->name);
+        pr_debug("    bus name: %s\n", bus->name);
 
         mode = PCI_PROBE_NORMAL;
         if (ppc_md.pci_probe_mode)
                 mode = ppc_md.pci_probe_mode(bus);
-        DBG("    probe mode: %d\n", mode);
+        pr_debug("    probe mode: %d\n", mode);
 
         if (mode == PCI_PROBE_DEVTREE)
                 of_scan_bus(node, bus);
@@ -327,9 +339,10 @@ void __devinit scan_phb(struct pci_controller *hose)
 {
         struct pci_bus *bus;
         struct device_node *node = hose->dn;
-        int i, mode;
+        int mode;
 
-        DBG("PCI: Scanning PHB %s\n", node ? node->full_name : "<NO NAME>");
+        pr_debug("PCI: Scanning PHB %s\n",
+                 node ? node->full_name : "<NO NAME>");
 
         /* Create an empty bus for the toplevel */
         bus = pci_create_bus(hose->parent, hose->first_busno, hose->ops, node);
@@ -345,26 +358,13 @@ void __devinit scan_phb(struct pci_controller *hose)
         pcibios_map_io_space(bus);
 
         /* Wire up PHB bus resources */
-        DBG("PCI: PHB IO resource    = %016lx-%016lx [%lx]\n",
-            hose->io_resource.start, hose->io_resource.end,
-            hose->io_resource.flags);
-        bus->resource[0] = &hose->io_resource;
-        for (i = 0; i < 3; ++i) {
-                DBG("PCI: PHB MEM resource %d = %016lx-%016lx [%lx]\n", i,
-                    hose->mem_resources[i].start,
-                    hose->mem_resources[i].end,
-                    hose->mem_resources[i].flags);
-                bus->resource[i+1] = &hose->mem_resources[i];
-        }
-        DBG("PCI: PHB MEM offset     = %016lx\n", hose->pci_mem_offset);
-        DBG("PCI: PHB IO  offset     = %08lx\n",
-            (unsigned long)hose->io_base_virt - _IO_BASE);
+        pcibios_setup_phb_resources(hose);
 
         /* Get probe mode and perform scan */
         mode = PCI_PROBE_NORMAL;
         if (node && ppc_md.pci_probe_mode)
                 mode = ppc_md.pci_probe_mode(bus);
-        DBG("    probe mode: %d\n", mode);
+        pr_debug("    probe mode: %d\n", mode);
         if (mode == PCI_PROBE_DEVTREE) {
                 bus->subordinate = hose->last_busno;
                 of_scan_bus(node, bus);
@@ -380,7 +380,7 @@ static int __init pcibios_init(void)
 
         printk(KERN_INFO "PCI: Probing PCI hardware\n");
 
-        /* For now, override phys_mem_access_prot. If we need it,
+        /* For now, override phys_mem_access_prot. If we need it,g
          * later, we may move that initialization to each ppc_md
          */
         ppc_md.phys_mem_access_prot = pci_phys_mem_access_prot;
@@ -388,6 +388,11 @@ static int __init pcibios_init(void)
         if (pci_probe_only)
                 ppc_pci_flags |= PPC_PCI_PROBE_ONLY;
 
+        /* On ppc64, we always enable PCI domains and we keep domain 0
+         * backward compatible in /proc for video cards
+         */
+        ppc_pci_flags |= PPC_PCI_ENABLE_PROC_DOMAINS | PPC_PCI_COMPAT_DOMAIN_0;
+
         /* Scan all of the recorded PCI controllers.  */
         list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
                 scan_phb(hose);
@@ -422,8 +427,8 @@ int pcibios_unmap_io_space(struct pci_bus *bus)
         if (bus->self) {
                 struct resource *res = bus->resource[0];
 
-                DBG("IO unmapping for PCI-PCI bridge %s\n",
-                    pci_name(bus->self));
+                pr_debug("IO unmapping for PCI-PCI bridge %s\n",
+                         pci_name(bus->self));
 
                 __flush_hash_table_range(&init_mm, res->start + _IO_BASE,
                                          res->end + _IO_BASE + 1);
@@ -437,8 +442,8 @@ int pcibios_unmap_io_space(struct pci_bus *bus)
         if (hose->io_base_alloc == 0)
                 return 0;
 
-        DBG("IO unmapping for PHB %s\n", hose->dn->full_name);
-        DBG("  alloc=0x%p\n", hose->io_base_alloc);
+        pr_debug("IO unmapping for PHB %s\n", hose->dn->full_name);
+        pr_debug("  alloc=0x%p\n", hose->io_base_alloc);
 
         /* This is a PHB, we fully unmap the IO area */
         vunmap(hose->io_base_alloc);
@@ -463,11 +468,11 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
          * thus HPTEs will be faulted in when needed
          */
         if (bus->self) {
-                DBG("IO mapping for PCI-PCI bridge %s\n",
-                    pci_name(bus->self));
-                DBG("  virt=0x%016lx...0x%016lx\n",
-                    bus->resource[0]->start + _IO_BASE,
-                    bus->resource[0]->end + _IO_BASE);
+                pr_debug("IO mapping for PCI-PCI bridge %s\n",
+                         pci_name(bus->self));
+                pr_debug("  virt=0x%016lx...0x%016lx\n",
+                         bus->resource[0]->start + _IO_BASE,
+                         bus->resource[0]->end + _IO_BASE);
                 return 0;
         }
 
@@ -496,11 +501,11 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
         hose->io_base_virt = (void __iomem *)(area->addr +
                                               hose->io_base_phys - phys_page);
 
-        DBG("IO mapping for PHB %s\n", hose->dn->full_name);
-        DBG("  phys=0x%016lx, virt=0x%p (alloc=0x%p)\n",
-            hose->io_base_phys, hose->io_base_virt, hose->io_base_alloc);
-        DBG("  size=0x%016lx (alloc=0x%016lx)\n",
-            hose->pci_io_size, size_page);
+        pr_debug("IO mapping for PHB %s\n", hose->dn->full_name);
+        pr_debug("  phys=0x%016lx, virt=0x%p (alloc=0x%p)\n",
+                 hose->io_base_phys, hose->io_base_virt, hose->io_base_alloc);
+        pr_debug("  size=0x%016lx (alloc=0x%016lx)\n",
+                 hose->pci_io_size, size_page);
 
         /* Establish the mapping */
         if (__ioremap_at(phys_page, area->addr, size_page,
@@ -512,24 +517,13 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
         hose->io_resource.start += io_virt_offset;
         hose->io_resource.end += io_virt_offset;
 
-        DBG("  hose->io_resource=0x%016lx...0x%016lx\n",
-            hose->io_resource.start, hose->io_resource.end);
+        pr_debug("  hose->io_resource=0x%016lx...0x%016lx\n",
+                 hose->io_resource.start, hose->io_resource.end);
 
         return 0;
 }
 EXPORT_SYMBOL_GPL(pcibios_map_io_space);
 
-void __devinit pcibios_do_bus_setup(struct pci_bus *bus)
-{
-        struct pci_dev *dev;
-
-        if (ppc_md.pci_dma_bus_setup)
-                ppc_md.pci_dma_bus_setup(bus);
-
-        list_for_each_entry(dev, &bus->devices, bus_list)
-                pcibios_setup_new_device(dev);
-}
-
 unsigned long pci_address_to_pio(phys_addr_t address)
 {
         struct pci_controller *hose, *tmp;
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 260089dccfb0..dcec1325d340 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -116,12 +116,6 @@ EXPORT_SYMBOL(giveup_spe);
 
 #ifndef CONFIG_PPC64
 EXPORT_SYMBOL(flush_instruction_cache);
-EXPORT_SYMBOL(flush_tlb_kernel_range);
-EXPORT_SYMBOL(flush_tlb_page);
-EXPORT_SYMBOL(_tlbie);
-#if defined(CONFIG_4xx) || defined(CONFIG_8xx) || defined(CONFIG_FSL_BOOKE)
-EXPORT_SYMBOL(_tlbil_va);
-#endif
 #endif
 EXPORT_SYMBOL(__flush_icache_range);
 EXPORT_SYMBOL(flush_dcache_range);
@@ -174,8 +168,7 @@ EXPORT_SYMBOL(cacheable_memcpy);
 #endif
 
 #ifdef CONFIG_PPC32
-EXPORT_SYMBOL(next_mmu_context);
-EXPORT_SYMBOL(set_context);
+EXPORT_SYMBOL(switch_mmu_context);
 #endif
 
 #ifdef CONFIG_PPC_STD_MMU_32
diff --git a/arch/powerpc/xmon/setjmp.S b/arch/powerpc/kernel/ppc_save_regs.S
index 04c0b305ad4a..5113bd2285e1 100644
--- a/arch/powerpc/xmon/setjmp.S
+++ b/arch/powerpc/kernel/ppc_save_regs.S
@@ -22,7 +22,7 @@
  * that will be different for 32-bit and 64-bit, because of the
  * different ABIs, though).
  */
-_GLOBAL(xmon_save_regs)
+_GLOBAL(ppc_save_regs)
         PPC_STL r0,0*SZL(r3)
         PPC_STL r2,2*SZL(r3)
         PPC_STL r3,3*SZL(r3)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 957bded0020d..51b201ddf9a1 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -467,6 +467,8 @@ static struct regbit {
         {MSR_VEC,       "VEC"},
         {MSR_VSX,       "VSX"},
         {MSR_ME,        "ME"},
+        {MSR_CE,        "CE"},
+        {MSR_DE,        "DE"},
         {MSR_IR,        "IR"},
         {MSR_DR,        "DR"},
         {0,             NULL}
@@ -998,7 +1000,7 @@ unsigned long get_wchan(struct task_struct *p)
         return 0;
 }
 
-static int kstack_depth_to_print = 64;
+static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH;
 
 void show_stack(struct task_struct *tsk, unsigned long *stack)
 {
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 3a2dc7e6586a..6f73c739f1e2 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -1160,6 +1160,8 @@ static inline void __init phyp_dump_reserve_mem(void) {}
 
 void __init early_init_devtree(void *params)
 {
+        unsigned long limit;
+
         DBG(" -> early_init_devtree(%p)\n", params);
 
         /* Setup flat device-tree pointer */
@@ -1200,7 +1202,19 @@ void __init early_init_devtree(void *params)
         early_reserve_mem();
         phyp_dump_reserve_mem();
 
-        lmb_enforce_memory_limit(memory_limit);
+        limit = memory_limit;
+        if (! limit) {
+                unsigned long memsize;
+
+                /* Ensure that total memory size is page-aligned, because
+                 * otherwise mark_bootmem() gets upset. */
+                lmb_analyze();
+                memsize = lmb_phys_mem_size();
+                if ((memsize & PAGE_MASK) != memsize)
+                        limit = memsize & PAGE_MASK;
+        }
+        lmb_enforce_memory_limit(limit);
+
         lmb_analyze();
 
         DBG("Phys. mem: %lx\n", lmb_phys_mem_size());
@@ -1271,6 +1285,37 @@ struct device_node *of_find_node_by_phandle(phandle handle)
 EXPORT_SYMBOL(of_find_node_by_phandle);
 
 /**
+ *      of_find_next_cache_node - Find a node's subsidiary cache
+ *      @np:    node of type "cpu" or "cache"
+ *
+ *      Returns a node pointer with refcount incremented, use
+ *      of_node_put() on it when done.  Caller should hold a reference
+ *      to np.
+ */
+struct device_node *of_find_next_cache_node(struct device_node *np)
+{
+        struct device_node *child;
+        const phandle *handle;
+
+        handle = of_get_property(np, "l2-cache", NULL);
+        if (!handle)
+                handle = of_get_property(np, "next-level-cache", NULL);
+
+        if (handle)
+                return of_find_node_by_phandle(*handle);
+
+        /* OF on pmac has nodes instead of properties named "l2-cache"
+         * beneath CPU nodes.
+         */
+        if (!strcmp(np->type, "cpu"))
+                for_each_child_of_node(np, child)
+                        if (!strcmp(child->type, "cache"))
+                                return child;
+
+        return NULL;
+}
+
+/**
  *      of_find_all_nodes - Get next node in global list
  *      @prev:  Previous node or NULL to start iteration
  *              of_node_put() will be called on it
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
index a11d68976dc8..8c1335566089 100644
--- a/arch/powerpc/kernel/prom_parse.c
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -734,10 +734,7 @@ void of_irq_map_init(unsigned int flags)
         if (flags & OF_IMAP_NO_PHANDLE) {
                 struct device_node *np;
 
-                for(np = NULL; (np = of_find_all_nodes(np)) != NULL;) {
-                        if (of_get_property(np, "interrupt-controller", NULL)
-                            == NULL)
-                                continue;
+                for_each_node_with_property(np, "interrupt-controller") {
                         /* Skip /chosen/interrupt-controller */
                         if (strcmp(np->name, "chosen") == 0)
                                 continue;
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 1f8505c23548..fdfe14c4bdef 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -566,6 +566,32 @@ int rtas_get_sensor(int sensor, int index, int *state)
 }
 EXPORT_SYMBOL(rtas_get_sensor);
 
+bool rtas_indicator_present(int token, int *maxindex)
+{
+        int proplen, count, i;
+        const struct indicator_elem {
+                u32 token;
+                u32 maxindex;
+        } *indicators;
+
+        indicators = of_get_property(rtas.dev, "rtas-indicators", &proplen);
+        if (!indicators)
+                return false;
+
+        count = proplen / sizeof(struct indicator_elem);
+
+        for (i = 0; i < count; i++) {
+                if (indicators[i].token != token)
+                        continue;
+                if (maxindex)
+                        *maxindex = indicators[i].maxindex;
+                return true;
+        }
+
+        return false;
+}
+EXPORT_SYMBOL(rtas_indicator_present);
+
 int rtas_set_indicator(int indicator, int index, int new_value)
 {
         int token = rtas_token("set-indicator");
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index 589a2797eac2..8869001ab5d7 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -301,51 +301,3 @@ void __init find_and_init_phbs(void)
 #endif /* CONFIG_PPC32 */
         }
 }
-
-/* RPA-specific bits for removing PHBs */
-int pcibios_remove_root_bus(struct pci_controller *phb)
-{
-        struct pci_bus *b = phb->bus;
-        struct resource *res;
-        int rc, i;
-
-        res = b->resource[0];
-        if (!res->flags) {
-                printk(KERN_ERR "%s: no IO resource for PHB %s\n", __func__,
-                                b->name);
-                return 1;
-        }
-
-        rc = pcibios_unmap_io_space(b);
-        if (rc) {
-                printk(KERN_ERR "%s: failed to unmap IO on bus %s\n",
-                        __func__, b->name);
-                return 1;
-        }
-
-        if (release_resource(res)) {
-                printk(KERN_ERR "%s: failed to release IO on bus %s\n",
-                                __func__, b->name);
-                return 1;
-        }
-
-        for (i = 1; i < 3; ++i) {
-                res = b->resource[i];
-                if (!res->flags && i == 0) {
-                        printk(KERN_ERR "%s: no MEM resource for PHB %s\n",
-                                __func__, b->name);
-                        return 1;
-                }
-                if (res->flags && release_resource(res)) {
-                        printk(KERN_ERR
-                               "%s: failed to release IO %d on bus %s\n",
-                                __func__, i, b->name);
-                        return 1;
-                }
-        }
-
-        pcibios_free_controller(phb);
-
-        return 0;
-}
-EXPORT_SYMBOL(pcibios_remove_root_bus);
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index c1a27626a940..9e1ca745d8f0 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -38,6 +38,7 @@
 #include <asm/time.h>
 #include <asm/serial.h>
 #include <asm/udbg.h>
+#include <asm/mmu_context.h>
 
 #include "setup.h"
 
@@ -49,12 +50,12 @@ int boot_cpuid;
 EXPORT_SYMBOL_GPL(boot_cpuid);
 int boot_cpuid_phys;
 
+int smp_hw_index[NR_CPUS];
+
 unsigned long ISA_DMA_THRESHOLD;
 unsigned int DMA_MODE_READ;
 unsigned int DMA_MODE_WRITE;
 
-int have_of = 1;
-
 #ifdef CONFIG_VGA_CONSOLE
 unsigned long vgacon_remap_base;
 EXPORT_SYMBOL(vgacon_remap_base);
@@ -97,6 +98,10 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
                           PTRRELOC(&__start___ftr_fixup),
                           PTRRELOC(&__stop___ftr_fixup));
 
+        do_feature_fixups(spec->mmu_features,
+                          PTRRELOC(&__start___mmu_ftr_fixup),
+                          PTRRELOC(&__stop___mmu_ftr_fixup));
+
         do_lwsync_fixups(spec->cpu_features,
                          PTRRELOC(&__start___lwsync_fixup),
                          PTRRELOC(&__stop___lwsync_fixup));
@@ -121,6 +126,8 @@ notrace void __init machine_init(unsigned long dt_ptr)
 
         probe_machine();
 
+        setup_kdump_trampoline();
+
 #ifdef CONFIG_6xx
         if (cpu_has_feature(CPU_FTR_CAN_DOZE) ||
             cpu_has_feature(CPU_FTR_CAN_NAP))
@@ -326,4 +333,8 @@ void __init setup_arch(char **cmdline_p)
         if ( ppc_md.progress ) ppc_md.progress("arch: exit", 0x3eab);
 
         paging_init();
+
+        /* Initialize the MMU context management stuff */
+        mmu_context_init();
+
 }
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 169d74cef157..d8bd2161e738 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -70,7 +70,6 @@
 #define DBG(fmt...)
 #endif
 
-int have_of = 1;
 int boot_cpuid = 0;
 u64 ppc64_pft_size;
 
@@ -362,6 +361,8 @@ void __init setup_system(void)
          */
         do_feature_fixups(cur_cpu_spec->cpu_features,
                           &__start___ftr_fixup, &__stop___ftr_fixup);
+        do_feature_fixups(cur_cpu_spec->mmu_features,
+                          &__start___mmu_ftr_fixup, &__stop___mmu_ftr_fixup);
         do_feature_fixups(powerpc_firmware_features,
                           &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
         do_lwsync_fixups(cur_cpu_spec->cpu_features,
@@ -606,8 +607,6 @@ void __init setup_per_cpu_areas(void)
 
         for_each_possible_cpu(i) {
                 ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size);
-                if (!ptr)
-                        panic("Cannot allocate cpu data for CPU %d\n", i);
 
                 paca[i].data_offset = ptr - __per_cpu_start;
                 memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c
index bc892e69b4f7..a5e54526403d 100644
--- a/arch/powerpc/kernel/smp-tbsync.c
+++ b/arch/powerpc/kernel/smp-tbsync.c
@@ -113,7 +113,7 @@ void __devinit smp_generic_give_timebase(void)
 {
         int i, score, score2, old, min=0, max=5000, offset=1000;
 
-        printk("Synchronizing timebase\n");
+        pr_debug("Software timebase sync\n");
 
         /* if this fails then this kernel won't work anyway... */
         tbsync = kzalloc( sizeof(*tbsync), GFP_KERNEL );
@@ -123,13 +123,13 @@ void __devinit smp_generic_give_timebase(void)
         while (!tbsync->ack)
                 barrier();
 
-        printk("Got ack\n");
+        pr_debug("Got ack\n");
 
         /* binary search */
         for (old = -1; old != offset ; offset = (min+max) / 2) {
                 score = start_contest(kSetAndTest, offset, NUM_ITER);
 
-                printk("score %d, offset %d\n", score, offset );
+                pr_debug("score %d, offset %d\n", score, offset );
 
                 if( score > 0 )
                         max = offset;
@@ -140,8 +140,8 @@ void __devinit smp_generic_give_timebase(void)
         score = start_contest(kSetAndTest, min, NUM_ITER);
         score2 = start_contest(kSetAndTest, max, NUM_ITER);
 
-        printk("Min %d (score %d), Max %d (score %d)\n",
-               min, score, max, score2);
+        pr_debug("Min %d (score %d), Max %d (score %d)\n",
+                 min, score, max, score2);
         score = abs(score);
         score2 = abs(score2);
         offset = (score < score2) ? min : max;
@@ -155,7 +155,7 @@ void __devinit smp_generic_give_timebase(void)
                 if (score2 <= score || score2 < 20)
                         break;
         }
-        printk("Final offset: %d (%d/%d)\n", offset, score2, NUM_ITER );
+        pr_debug("Final offset: %d (%d/%d)\n", offset, score2, NUM_ITER );
 
         /* exiting */
         tbsync->cmd = kExit;
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ff9f7010097d..8ac3f721d235 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -57,7 +57,6 @@
 #define DBG(fmt...)
 #endif
 
-int smp_hw_index[NR_CPUS];
 struct thread_info *secondary_ti;
 
 cpumask_t cpu_possible_map = CPU_MASK_NONE;
@@ -123,6 +122,65 @@ void smp_message_recv(int msg)
         }
 }
 
+static irqreturn_t call_function_action(int irq, void *data)
+{
+        generic_smp_call_function_interrupt();
+        return IRQ_HANDLED;
+}
+
+static irqreturn_t reschedule_action(int irq, void *data)
+{
+        /* we just need the return path side effect of checking need_resched */
+        return IRQ_HANDLED;
+}
+
+static irqreturn_t call_function_single_action(int irq, void *data)
+{
+        generic_smp_call_function_single_interrupt();
+        return IRQ_HANDLED;
+}
+
+static irqreturn_t debug_ipi_action(int irq, void *data)
+{
+        smp_message_recv(PPC_MSG_DEBUGGER_BREAK);
+        return IRQ_HANDLED;
+}
+
+static irq_handler_t smp_ipi_action[] = {
+        [PPC_MSG_CALL_FUNCTION] =  call_function_action,
+        [PPC_MSG_RESCHEDULE] = reschedule_action,
+        [PPC_MSG_CALL_FUNC_SINGLE] = call_function_single_action,
+        [PPC_MSG_DEBUGGER_BREAK] = debug_ipi_action,
+};
+
+const char *smp_ipi_name[] = {
+        [PPC_MSG_CALL_FUNCTION] =  "ipi call function",
+        [PPC_MSG_RESCHEDULE] = "ipi reschedule",
+        [PPC_MSG_CALL_FUNC_SINGLE] = "ipi call function single",
+        [PPC_MSG_DEBUGGER_BREAK] = "ipi debugger",
+};
+
+/* optional function to request ipi, for controllers with >= 4 ipis */
+int smp_request_message_ipi(int virq, int msg)
+{
+        int err;
+
+        if (msg < 0 || msg > PPC_MSG_DEBUGGER_BREAK) {
+                return -EINVAL;
+        }
+#if !defined(CONFIG_DEBUGGER) && !defined(CONFIG_KEXEC)
+        if (msg == PPC_MSG_DEBUGGER_BREAK) {
+                return 1;
+        }
+#endif
+        err = request_irq(virq, smp_ipi_action[msg], IRQF_DISABLED|IRQF_PERCPU,
+                          smp_ipi_name[msg], 0);
+        WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
+                virq, smp_ipi_name[msg], err);
+
+        return err;
+}
+
 void smp_send_reschedule(int cpu)
 {
         if (likely(smp_ops))
@@ -408,8 +466,7 @@ out:
 static struct device_node *cpu_to_l2cache(int cpu)
 {
         struct device_node *np;
-        const phandle *php;
-        phandle ph;
+        struct device_node *cache;
 
         if (!cpu_present(cpu))
                 return NULL;
@@ -418,13 +475,11 @@ static struct device_node *cpu_to_l2cache(int cpu)
         if (np == NULL)
                 return NULL;
 
-        php = of_get_property(np, "l2-cache", NULL);
-        if (php == NULL)
-                return NULL;
-        ph = *php;
+        cache = of_find_next_cache_node(np);
+
         of_node_put(np);
 
-        return of_find_node_by_phandle(ph);
+        return cache;
 }
 
 /* Activate a secondary processor. */
diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c
index 77b7b34b5955..560c96119501 100644
--- a/arch/powerpc/kernel/swsusp.c
+++ b/arch/powerpc/kernel/swsusp.c
@@ -34,6 +34,6 @@ void save_processor_state(void)
 void restore_processor_state(void)
 {
 #ifdef CONFIG_PPC32
-        set_context(current->active_mm->context.id, current->active_mm->pgd);
+        switch_mmu_context(NULL, current->active_mm);
 #endif
 }
diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S
index 77fc76607ab2..b47d8ceffb52 100644
--- a/arch/powerpc/kernel/swsusp_32.S
+++ b/arch/powerpc/kernel/swsusp_32.S
@@ -5,7 +5,7 @@
 #include <asm/thread_info.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
-
+#include <asm/mmu.h>
 
 /*
  * Structure for storing CPU registers on the save area.
@@ -279,7 +279,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
         mtibatl 3,r4
 #endif
 
-BEGIN_FTR_SECTION
+BEGIN_MMU_FTR_SECTION
         li      r4,0
         mtspr   SPRN_DBAT4U,r4
         mtspr   SPRN_DBAT4L,r4
@@ -297,7 +297,7 @@ BEGIN_FTR_SECTION
         mtspr   SPRN_IBAT6L,r4
         mtspr   SPRN_IBAT7U,r4
         mtspr   SPRN_IBAT7L,r4
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 
         /* Flush all TLBs */
         lis     r4,0x1000
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 20885a38237a..0c64f10087b9 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -566,7 +566,6 @@ static bool cache_is_unified(struct device_node *np)
 
 static struct cache_desc * __cpuinit create_cache_index_info(struct device_node *np, struct kobject *parent, int index, int level)
 {
-        const phandle *next_cache_phandle;
         struct device_node *next_cache;
         struct cache_desc *new, **end;
 
@@ -591,11 +590,7 @@ static struct cache_desc * __cpuinit create_cache_index_info(struct device_node
         while (*end)
                 end = &(*end)->next;
 
-        next_cache_phandle = of_get_property(np, "l2-cache", NULL);
-        if (!next_cache_phandle)
-                goto out;
-
-        next_cache = of_find_node_by_phandle(*next_cache_phandle);
+        next_cache = of_find_next_cache_node(np);
         if (!next_cache)
                 goto out;
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index e2ee66b5831d..e1f3a5140429 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -164,8 +164,6 @@ static u64 tb_to_ns_scale __read_mostly;
 static unsigned tb_to_ns_shift __read_mostly;
 static unsigned long boot_tb __read_mostly;
 
-static struct gettimeofday_struct do_gtod;
-
 extern struct timezone sys_tz;
 static long timezone_offset;
 
@@ -415,31 +413,9 @@ void udelay(unsigned long usecs)
 }
 EXPORT_SYMBOL(udelay);
 
-
-/*
- * There are two copies of tb_to_xs and stamp_xsec so that no
- * lock is needed to access and use these values in
- * do_gettimeofday.  We alternate the copies and as long as a
- * reasonable time elapses between changes, there will never
- * be inconsistent values.  ntpd has a minimum of one minute
- * between updates.
- */
 static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
                                u64 new_tb_to_xs)
 {
-        unsigned temp_idx;
-        struct gettimeofday_vars *temp_varp;
-
-        temp_idx = (do_gtod.var_idx == 0);
-        temp_varp = &do_gtod.vars[temp_idx];
-
-        temp_varp->tb_to_xs = new_tb_to_xs;
-        temp_varp->tb_orig_stamp = new_tb_stamp;
-        temp_varp->stamp_xsec = new_stamp_xsec;
-        smp_mb();
-        do_gtod.varp = temp_varp;
-        do_gtod.var_idx = temp_idx;
-
         /*
          * tb_update_count is used to allow the userspace gettimeofday code
          * to assure itself that it sees a consistent view of the tb_to_xs and
@@ -456,6 +432,7 @@ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
         vdso_data->tb_to_xs = new_tb_to_xs;
         vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec;
         vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec;
+        vdso_data->stamp_xtime = xtime;
         smp_wmb();
         ++(vdso_data->tb_update_count);
 }
@@ -514,9 +491,7 @@ static int __init iSeries_tb_recal(void)
                                 tb_ticks_per_sec   = new_tb_ticks_per_sec;
                                 calc_cputime_factors();
                                 div128_by_32( XSEC_PER_SEC, 0, tb_ticks_per_sec, &divres );
-                                do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
                                 tb_to_xs = divres.result_low;
-                                do_gtod.varp->tb_to_xs = tb_to_xs;
                                 vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
                                 vdso_data->tb_to_xs = tb_to_xs;
                         }
@@ -988,15 +963,6 @@ void __init time_init(void)
                 sys_tz.tz_dsttime = 0;
         }
 
-        do_gtod.varp = &do_gtod.vars[0];
-        do_gtod.var_idx = 0;
-        do_gtod.varp->tb_orig_stamp = tb_last_jiffy;
-        __get_cpu_var(last_jiffy) = tb_last_jiffy;
-        do_gtod.varp->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC;
-        do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
-        do_gtod.varp->tb_to_xs = tb_to_xs;
-        do_gtod.tb_to_us = tb_to_us;
-
         vdso_data->tb_orig_stamp = tb_last_jiffy;
         vdso_data->tb_update_count = 0;
         vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index f5def6cf5cd6..5457e9575685 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1160,37 +1160,85 @@ void CacheLockingException(struct pt_regs *regs, unsigned long address,
 #ifdef CONFIG_SPE
 void SPEFloatingPointException(struct pt_regs *regs)
 {
+        extern int do_spe_mathemu(struct pt_regs *regs);
         unsigned long spefscr;
         int fpexc_mode;
         int code = 0;
+        int err;
+
+        preempt_disable();
+        if (regs->msr & MSR_SPE)
+                giveup_spe(current);
+        preempt_enable();
 
         spefscr = current->thread.spefscr;
         fpexc_mode = current->thread.fpexc_mode;
 
-        /* Hardware does not neccessarily set sticky
-         * underflow/overflow/invalid flags */
         if ((spefscr & SPEFSCR_FOVF) && (fpexc_mode & PR_FP_EXC_OVF)) {
                 code = FPE_FLTOVF;
-                spefscr |= SPEFSCR_FOVFS;
         }
         else if ((spefscr & SPEFSCR_FUNF) && (fpexc_mode & PR_FP_EXC_UND)) {
                 code = FPE_FLTUND;
-                spefscr |= SPEFSCR_FUNFS;
         }
         else if ((spefscr & SPEFSCR_FDBZ) && (fpexc_mode & PR_FP_EXC_DIV))
                 code = FPE_FLTDIV;
         else if ((spefscr & SPEFSCR_FINV) && (fpexc_mode & PR_FP_EXC_INV)) {
                 code = FPE_FLTINV;
-                spefscr |= SPEFSCR_FINVS;
         }
         else if ((spefscr & (SPEFSCR_FG | SPEFSCR_FX)) && (fpexc_mode & PR_FP_EXC_RES))
                 code = FPE_FLTRES;
 
-        current->thread.spefscr = spefscr;
+        err = do_spe_mathemu(regs);
+        if (err == 0) {
+                regs->nip += 4;         /* skip emulated instruction */
+                emulate_single_step(regs);
+                return;
+        }
+
+        if (err == -EFAULT) {
+                /* got an error reading the instruction */
+                _exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip);
+        } else if (err == -EINVAL) {
+                /* didn't recognize the instruction */
+                printk(KERN_ERR "unrecognized spe instruction "
+                       "in %s at %lx\n", current->comm, regs->nip);
+        } else {
+                _exception(SIGFPE, regs, code, regs->nip);
+        }
 
-        _exception(SIGFPE, regs, code, regs->nip);
         return;
 }
+
+void SPEFloatingPointRoundException(struct pt_regs *regs)
+{
+        extern int speround_handler(struct pt_regs *regs);
+        int err;
+
+        preempt_disable();
+        if (regs->msr & MSR_SPE)
+                giveup_spe(current);
+        preempt_enable();
+
+        regs->nip -= 4;
+        err = speround_handler(regs);
+        if (err == 0) {
+                regs->nip += 4;         /* skip emulated instruction */
+                emulate_single_step(regs);
+                return;
+        }
+
+        if (err == -EFAULT) {
+                /* got an error reading the instruction */
+                _exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip);
+        } else if (err == -EINVAL) {
+                /* didn't recognize the instruction */
+                printk(KERN_ERR "unrecognized spe instruction "
+                       "in %s at %lx\n", current->comm, regs->nip);
+        } else {
+                _exception(SIGFPE, regs, 0, regs->nip);
+                return;
+        }
+}
 #endif
 
 /*
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index f7ec7d0888fe..ad06d5c75b15 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -566,6 +566,11 @@ static __init int vdso_fixup_features(struct lib32_elfinfo *v32,
                 do_feature_fixups(cur_cpu_spec->cpu_features,
                                   start64, start64 + size64);
 
+        start64 = find_section64(v64->hdr, "__mmu_ftr_fixup", &size64);
+        if (start64)
+                do_feature_fixups(cur_cpu_spec->mmu_features,
+                                  start64, start64 + size64);
+
         start64 = find_section64(v64->hdr, "__fw_ftr_fixup", &size64);
         if (start64)
                 do_feature_fixups(powerpc_firmware_features,
@@ -582,6 +587,11 @@ static __init int vdso_fixup_features(struct lib32_elfinfo *v32,
                 do_feature_fixups(cur_cpu_spec->cpu_features,
                                   start32, start32 + size32);
 
+        start32 = find_section32(v32->hdr, "__mmu_ftr_fixup", &size32);
+        if (start32)
+                do_feature_fixups(cur_cpu_spec->mmu_features,
+                                  start32, start32 + size32);
+
 #ifdef CONFIG_PPC64
         start32 = find_section32(v32->hdr, "__fw_ftr_fixup", &size32);
         if (start32)
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 72ca26df457e..ee038d4bf252 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -16,6 +16,13 @@
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
 
+/* Offset for the low 32-bit part of a field of long type */
+#ifdef CONFIG_PPC64
+#define LOPART  4
+#else
+#define LOPART  0
+#endif
+
         .text
 /*
  * Exact prototype of gettimeofday
@@ -90,101 +97,53 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 
         mflr    r12                     /* r12 saves lr */
   .cfi_register lr,r12
-        mr      r10,r3                  /* r10 saves id */
         mr      r11,r4                  /* r11 saves tp */
         bl      __get_datapage@local    /* get data page */
         mr      r9,r3                   /* datapage ptr in r9 */
-        beq     cr1,50f                 /* if monotonic -> jump there */
-
-        /*
-         * CLOCK_REALTIME
-         */
-
-        bl      __do_get_xsec@local     /* get xsec from tb & kernel */
-        bne-    98f                     /* out of line -> do syscall */
-
-        /* seconds are xsec >> 20 */
-        rlwinm  r5,r4,12,20,31
-        rlwimi  r5,r3,12,0,19
-        stw     r5,TSPC32_TV_SEC(r11)
 
-        /* get remaining xsec and convert to nsec. we scale
-         * up remaining xsec by 12 bits and get the top 32 bits
-         * of the multiplication, then we multiply by 1000
-         */
-        rlwinm  r5,r4,12,0,19
-        lis     r6,1000000@h
-        ori     r6,r6,1000000@l
-        mulhwu  r5,r5,r6
-        mulli   r5,r5,1000
-        stw     r5,TSPC32_TV_NSEC(r11)
-        mtlr    r12
-        crclr   cr0*4+so
-        li      r3,0
-        blr
+50:     bl      __do_get_tspec@local    /* get sec/nsec from tb & kernel */
+        bne     cr1,80f                 /* not monotonic -> all done */
 
         /*
          * CLOCK_MONOTONIC
          */
 
-50:     bl      __do_get_xsec@local     /* get xsec from tb & kernel */
-        bne-    98f                     /* out of line -> do syscall */
-
-        /* seconds are xsec >> 20 */
-        rlwinm  r6,r4,12,20,31
-        rlwimi  r6,r3,12,0,19
-
-        /* get remaining xsec and convert to nsec. we scale
-         * up remaining xsec by 12 bits and get the top 32 bits
-         * of the multiplication, then we multiply by 1000
-         */
-        rlwinm  r7,r4,12,0,19
-        lis     r5,1000000@h
-        ori     r5,r5,1000000@l
-        mulhwu  r7,r7,r5
-        mulli   r7,r7,1000
-
         /* now we must fixup using wall to monotonic. We need to snapshot
          * that value and do the counter trick again. Fortunately, we still
          * have the counter value in r8 that was returned by __do_get_xsec.
-         * At this point, r6,r7 contain our sec/nsec values, r3,r4 and r5
-         * can be used
+         * At this point, r3,r4 contain our sec/nsec values, r5 and r6
+         * can be used, r7 contains NSEC_PER_SEC.
          */
 
-        lwz     r3,WTOM_CLOCK_SEC(r9)
-        lwz     r4,WTOM_CLOCK_NSEC(r9)
+        lwz     r5,WTOM_CLOCK_SEC(r9)
+        lwz     r6,WTOM_CLOCK_NSEC(r9)
 
-        /* We now have our result in r3,r4. We create a fake dependency
-         * on that result and re-check the counter
+        /* We now have our offset in r5,r6. We create a fake dependency
+         * on that value and re-check the counter
          */
-        or      r5,r4,r3
-        xor     r0,r5,r5
+        or      r0,r6,r5
+        xor     r0,r0,r0
         add     r9,r9,r0
-#ifdef CONFIG_PPC64
-        lwz     r0,(CFG_TB_UPDATE_COUNT+4)(r9)
-#else
-        lwz     r0,(CFG_TB_UPDATE_COUNT)(r9)
-#endif
+        lwz     r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
         cmpl    cr0,r8,r0               /* check if updated */
         bne-    50b
 
-        /* Calculate and store result. Note that this mimmics the C code,
+        /* Calculate and store result. Note that this mimics the C code,
          * which may cause funny results if nsec goes negative... is that
          * possible at all ?
          */
-        add     r3,r3,r6
-        add     r4,r4,r7
-        lis     r5,NSEC_PER_SEC@h
-        ori     r5,r5,NSEC_PER_SEC@l
-        cmpl    cr0,r4,r5
-        cmpli   cr1,r4,0
+        add     r3,r3,r5
+        add     r4,r4,r6
+        cmpw    cr0,r4,r7
+        cmpwi   cr1,r4,0
         blt     1f
-        subf    r4,r5,r4
+        subf    r4,r7,r4
         addi    r3,r3,1
-1:      bge     cr1,1f
+1:      bge     cr1,80f
         addi    r3,r3,-1
-        add     r4,r4,r5
-1:      stw     r3,TSPC32_TV_SEC(r11)
+        add     r4,r4,r7
+
+80:     stw     r3,TSPC32_TV_SEC(r11)
         stw     r4,TSPC32_TV_NSEC(r11)
 
         mtlr    r12
@@ -195,10 +154,6 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
         /*
          * syscall fallback
          */
-98:
-        mtlr    r12
-        mr      r3,r10
-        mr      r4,r11
 99:
         li      r0,__NR_clock_gettime
         sc
@@ -254,11 +209,7 @@ __do_get_xsec:
         /* Check for update count & load values. We use the low
          * order 32 bits of the update count
          */
-#ifdef CONFIG_PPC64
-1:      lwz     r8,(CFG_TB_UPDATE_COUNT+4)(r9)
-#else
-1:      lwz     r8,(CFG_TB_UPDATE_COUNT)(r9)
-#endif
+1:      lwz     r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
         andi.   r0,r8,1                 /* pending update ? loop */
         bne-    1b
         xor     r0,r8,r8                /* create dependency */
@@ -305,11 +256,7 @@ __do_get_xsec:
         or      r6,r4,r3
         xor     r0,r6,r6
         add     r9,r9,r0
-#ifdef CONFIG_PPC64
-        lwz     r0,(CFG_TB_UPDATE_COUNT+4)(r9)
-#else
-        lwz     r0,(CFG_TB_UPDATE_COUNT)(r9)
-#endif
+        lwz     r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
         cmpl    cr0,r8,r0               /* check if updated */
         bne-    1b
 
@@ -322,3 +269,98 @@ __do_get_xsec:
          */
 3:      blr
   .cfi_endproc
+
+/*
+ * This is the core of clock_gettime(), it returns the current
+ * time in seconds and nanoseconds in r3 and r4.
+ * It expects the datapage ptr in r9 and doesn't clobber it.
+ * It clobbers r0, r5, r6, r10 and returns NSEC_PER_SEC in r7.
+ * On return, r8 contains the counter value that can be reused.
+ * This clobbers cr0 but not any other cr field.
+ */
+__do_get_tspec:
+  .cfi_startproc
+        /* Check for update count & load values. We use the low
+         * order 32 bits of the update count
+         */
+1:      lwz     r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
+        andi.   r0,r8,1                 /* pending update ? loop */
+        bne-    1b
+        xor     r0,r8,r8                /* create dependency */
+        add     r9,r9,r0
+
+        /* Load orig stamp (offset to TB) */
+        lwz     r5,CFG_TB_ORIG_STAMP(r9)
+        lwz     r6,(CFG_TB_ORIG_STAMP+4)(r9)
+
+        /* Get a stable TB value */
+2:      mftbu   r3
+        mftbl   r4
+        mftbu   r0
+        cmpl    cr0,r3,r0
+        bne-    2b
+
+        /* Subtract tb orig stamp and shift left 12 bits.
+         */
+        subfc   r7,r6,r4
+        subfe   r0,r5,r3
+        slwi    r0,r0,12
+        rlwimi. r0,r7,12,20,31
+        slwi    r7,r7,12
+
+        /* Load scale factor & do multiplication */
+        lwz     r5,CFG_TB_TO_XS(r9)     /* load values */
+        lwz     r6,(CFG_TB_TO_XS+4)(r9)
+        mulhwu  r3,r7,r6
+        mullw   r10,r7,r5
+        mulhwu  r4,r7,r5
+        addc    r10,r3,r10
+        li      r3,0
+
+        beq+    4f                      /* skip high part computation if 0 */
+        mulhwu  r3,r0,r5
+        mullw   r7,r0,r5
+        mulhwu  r5,r0,r6
+        mullw   r6,r0,r6
+        adde    r4,r4,r7
+        addze   r3,r3
+        addc    r4,r4,r5
+        addze   r3,r3
+        addc    r10,r10,r6
+
+4:      addze   r4,r4                   /* add in carry */
+        lis     r7,NSEC_PER_SEC@h
+        ori     r7,r7,NSEC_PER_SEC@l
+        mulhwu  r4,r4,r7                /* convert to nanoseconds */
+
+        /* At this point, we have seconds & nanoseconds since the xtime
+         * stamp in r3+CA and r4.  Load & add the xtime stamp.
+         */
+#ifdef CONFIG_PPC64
+        lwz     r5,STAMP_XTIME+TSPC64_TV_SEC+LOPART(r9)
+        lwz     r6,STAMP_XTIME+TSPC64_TV_NSEC+LOPART(r9)
+#else
+        lwz     r5,STAMP_XTIME+TSPC32_TV_SEC(r9)
+        lwz     r6,STAMP_XTIME+TSPC32_TV_NSEC(r9)
+#endif
+        add     r4,r4,r6
+        adde    r3,r3,r5
+
+        /* We now have our result in r3,r4. We create a fake dependency
+         * on that result and re-check the counter
+         */
+        or      r6,r4,r3
+        xor     r0,r6,r6
+        add     r9,r9,r0
+        lwz     r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
+        cmpl    cr0,r8,r0               /* check if updated */
+        bne-    1b
+
+        /* check for nanosecond overflow and adjust if necessary */
+        cmpw    r4,r7
+        bltlr                           /* all done if no overflow */
+        subf    r4,r7,r4                /* adjust if overflow */
+        addi    r3,r3,1
+
+        blr
+  .cfi_endproc
diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
index be3b6a41dc09..904ef1360dd7 100644
--- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
@@ -34,6 +34,9 @@ SECTIONS
         __ftr_fixup     : { *(__ftr_fixup) }
 
         . = ALIGN(8);
+        __mmu_ftr_fixup : { *(__mmu_ftr_fixup) }
+
+        . = ALIGN(8);
         __lwsync_fixup  : { *(__lwsync_fixup) }
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index c6401f9e37f1..262cd5857a56 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -75,90 +75,49 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 
         mflr    r12                     /* r12 saves lr */
   .cfi_register lr,r12
-        mr      r10,r3                  /* r10 saves id */
         mr      r11,r4                  /* r11 saves tp */
         bl      V_LOCAL_FUNC(__get_datapage)    /* get data page */
-        beq     cr1,50f                 /* if monotonic -> jump there */
-
-        /*
-         * CLOCK_REALTIME
-         */
-
-        bl      V_LOCAL_FUNC(__do_get_xsec)     /* get xsec from tb & kernel */
-
-        lis     r7,15                   /* r7 = 1000000 = USEC_PER_SEC */
-        ori     r7,r7,16960
-        rldicl  r5,r4,44,20             /* r5 = sec = xsec / XSEC_PER_SEC */
-        rldicr  r6,r5,20,43             /* r6 = sec * XSEC_PER_SEC */
-        std     r5,TSPC64_TV_SEC(r11)   /* store sec in tv */
-        subf    r0,r6,r4                /* r0 = xsec = (xsec - r6) */
-        mulld   r0,r0,r7                /* usec = (xsec * USEC_PER_SEC) /
-                                         * XSEC_PER_SEC
-                                         */
-        rldicl  r0,r0,44,20
-        mulli   r0,r0,1000              /* nsec = usec * 1000 */
-        std     r0,TSPC64_TV_NSEC(r11)  /* store nsec in tp */
-
-        mtlr    r12
-        crclr   cr0*4+so
-        li      r3,0
-        blr
+50:     bl      V_LOCAL_FUNC(__do_get_tspec)    /* get time from tb & kernel */
+        bne     cr1,80f                 /* if not monotonic, all done */
 
         /*
          * CLOCK_MONOTONIC
          */
 
-50:     bl      V_LOCAL_FUNC(__do_get_xsec)     /* get xsec from tb & kernel */
-
-        lis     r7,15                   /* r7 = 1000000 = USEC_PER_SEC */
-        ori     r7,r7,16960
-        rldicl  r5,r4,44,20             /* r5 = sec = xsec / XSEC_PER_SEC */
-        rldicr  r6,r5,20,43             /* r6 = sec * XSEC_PER_SEC */
-        subf    r0,r6,r4                /* r0 = xsec = (xsec - r6) */
-        mulld   r0,r0,r7                /* usec = (xsec * USEC_PER_SEC) /
-                                         * XSEC_PER_SEC
-                                         */
-        rldicl  r6,r0,44,20
-        mulli   r6,r6,1000              /* nsec = usec * 1000 */
-
         /* now we must fixup using wall to monotonic. We need to snapshot
          * that value and do the counter trick again. Fortunately, we still
-         * have the counter value in r8 that was returned by __do_get_xsec.
-         * At this point, r5,r6 contain our sec/nsec values.
-         * can be used
+         * have the counter value in r8 that was returned by __do_get_tspec.
+         * At this point, r4,r5 contain our sec/nsec values.
          */
 
-        lwa     r4,WTOM_CLOCK_SEC(r3)
-        lwa     r7,WTOM_CLOCK_NSEC(r3)
+        lwa     r6,WTOM_CLOCK_SEC(r3)
+        lwa     r9,WTOM_CLOCK_NSEC(r3)
 
-        /* We now have our result in r4,r7. We create a fake dependency
+        /* We now have our result in r6,r9. We create a fake dependency
          * on that result and re-check the counter
          */
-        or      r9,r4,r7
-        xor     r0,r9,r9
+        or      r0,r6,r9
+        xor     r0,r0,r0
         add     r3,r3,r0
         ld      r0,CFG_TB_UPDATE_COUNT(r3)
         cmpld   cr0,r0,r8               /* check if updated */
         bne-    50b
 
-        /* Calculate and store result. Note that this mimmics the C code,
-         * which may cause funny results if nsec goes negative... is that
-         * possible at all ?
+        /* Add wall->monotonic offset and check for overflow or underflow.
          */
-        add     r4,r4,r5
-        add     r7,r7,r6
-        lis     r9,NSEC_PER_SEC@h
-        ori     r9,r9,NSEC_PER_SEC@l
-        cmpl    cr0,r7,r9
-        cmpli   cr1,r7,0
+        add     r4,r4,r6
+        add     r5,r5,r9
+        cmpd    cr0,r5,r7
+        cmpdi   cr1,r5,0
         blt     1f
-        subf    r7,r9,r7
+        subf    r5,r7,r5
         addi    r4,r4,1
-1:      bge     cr1,1f
+1:      bge     cr1,80f
         addi    r4,r4,-1
-        add     r7,r7,r9
-1:      std     r4,TSPC64_TV_SEC(r11)
-        std     r7,TSPC64_TV_NSEC(r11)
+        add     r5,r5,r7
+
+80:     std     r4,TSPC64_TV_SEC(r11)
+        std     r5,TSPC64_TV_NSEC(r11)
 
         mtlr    r12
         crclr   cr0*4+so
@@ -168,10 +127,6 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
         /*
          * syscall fallback
          */
-98:
-        mtlr    r12
-        mr      r3,r10
-        mr      r4,r11
 99:
         li      r0,__NR_clock_gettime
         sc
@@ -253,3 +208,59 @@ V_FUNCTION_BEGIN(__do_get_xsec)
         blr
   .cfi_endproc
 V_FUNCTION_END(__do_get_xsec)
+
+/*
+ * This is the core of clock_gettime(), it returns the current
+ * time in seconds and nanoseconds in r4 and r5.
+ * It expects the datapage ptr in r3 and doesn't clobber it.
+ * It clobbers r0 and r6 and returns NSEC_PER_SEC in r7.
+ * On return, r8 contains the counter value that can be reused.
+ * This clobbers cr0 but not any other cr field.
+ */
+V_FUNCTION_BEGIN(__do_get_tspec)
+  .cfi_startproc
+        /* check for update count & load values */
+1:      ld      r8,CFG_TB_UPDATE_COUNT(r3)
+        andi.   r0,r8,1                 /* pending update ? loop */
+        bne-    1b
+        xor     r0,r8,r8                /* create dependency */
+        add     r3,r3,r0
+
+        /* Get TB & offset it. We use the MFTB macro which will generate
+         * workaround code for Cell.
+         */
+        MFTB(r7)
+        ld      r9,CFG_TB_ORIG_STAMP(r3)
+        subf    r7,r9,r7
+
+        /* Scale result */
+        ld      r5,CFG_TB_TO_XS(r3)
+        sldi    r7,r7,12                /* compute time since stamp_xtime */
+        mulhdu  r6,r7,r5                /* in units of 2^-32 seconds */
+
+        /* Add stamp since epoch */
+        ld      r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
+        ld      r5,STAMP_XTIME+TSPC64_TV_NSEC(r3)
+        or      r0,r4,r5
+        or      r0,r0,r6
+        xor     r0,r0,r0
+        add     r3,r3,r0
+        ld      r0,CFG_TB_UPDATE_COUNT(r3)
+        cmpld   r0,r8                   /* check if updated */
+        bne-    1b                      /* reload if so */
+
+        /* convert to seconds & nanoseconds and add to stamp */
+        lis     r7,NSEC_PER_SEC@h
+        ori     r7,r7,NSEC_PER_SEC@l
+        mulhwu  r0,r6,r7                /* compute nanoseconds and */
+        srdi    r6,r6,32                /* seconds since stamp_xtime */
+        clrldi  r0,r0,32
+        add     r5,r5,r0                /* add nanoseconds together */
+        cmpd    r5,r7                   /* overflow? */
+        add     r4,r4,r6
+        bltlr                           /* all done if no overflow */
+        subf    r5,r7,r5                /* if overflow, adjust */
+        addi    r4,r4,1
+        blr
+  .cfi_endproc
+V_FUNCTION_END(__do_get_tspec)
diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S
index d0b2526dd38d..0e615404e247 100644
--- a/arch/powerpc/kernel/vdso64/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S
@@ -35,6 +35,9 @@ SECTIONS
         __ftr_fixup     : { *(__ftr_fixup) }
 
         . = ALIGN(8);
+        __mmu_ftr_fixup : { *(__mmu_ftr_fixup) }
+
+        . = ALIGN(8);
         __lwsync_fixup  : { *(__lwsync_fixup) }
 
         . = ALIGN(8);
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index a11e6bc59b30..94aa7b011b27 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -41,9 +41,9 @@
 static struct bus_type vio_bus_type;
 
 static struct vio_dev vio_bus_device  = { /* fake "parent" device */
-        .name = vio_bus_device.dev.bus_id,
+        .name = "vio",
         .type = "",
-        .dev.bus_id = "vio",
+        .dev.init_name = "vio",
         .dev.bus = &vio_bus_type,
 };
 
@@ -1216,7 +1216,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 
         viodev->irq = irq_of_parse_and_map(of_node, 0);
 
-        snprintf(viodev->dev.bus_id, BUS_ID_SIZE, "%x", *unit_address);
+        dev_set_name(&viodev->dev, "%x", *unit_address);
         viodev->name = of_node->name;
         viodev->type = of_node->type;
         viodev->unit_address = *unit_address;
@@ -1243,7 +1243,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
         /* register with generic device framework */
         if (device_register(&viodev->dev)) {
                 printk(KERN_ERR "%s: failed to register device %s\n",
-                                __func__, viodev->dev.bus_id);
+                                __func__, dev_name(&viodev->dev));
                 /* XXX free TCE table */
                 kfree(viodev);
                 return NULL;
@@ -1400,13 +1400,13 @@ static struct vio_dev *vio_find_name(const char *name)
 struct vio_dev *vio_find_node(struct device_node *vnode)
 {
         const uint32_t *unit_address;
-        char kobj_name[BUS_ID_SIZE];
+        char kobj_name[20];
 
         /* construct the kobject name from the device node */
         unit_address = of_get_property(vnode, "reg", NULL);
         if (!unit_address)
                 return NULL;
-        snprintf(kobj_name, BUS_ID_SIZE, "%x", *unit_address);
+        snprintf(kobj_name, sizeof(kobj_name), "%x", *unit_address);
 
         return vio_find_name(kobj_name);
 }
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 2412c056baa4..47bf15cd2c9e 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -152,6 +152,12 @@ SECTIONS
                 __stop___ftr_fixup = .;
         }
         . = ALIGN(8);
+        __mmu_ftr_fixup : AT(ADDR(__mmu_ftr_fixup) - LOAD_OFFSET) {
+                __start___mmu_ftr_fixup = .;
+                *(__mmu_ftr_fixup)
+                __stop___mmu_ftr_fixup = .;
+        }
+        . = ALIGN(8);
         __lwsync_fixup : AT(ADDR(__lwsync_fixup) - LOAD_OFFSET) {
                 __start___lwsync_fixup = .;
                 *(__lwsync_fixup)
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index fda9baada132..8bef0efcdfe1 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -28,6 +28,7 @@
 #include <asm/uaccess.h>
 #include <asm/kvm_ppc.h>
 #include <asm/tlbflush.h>
+#include "../mm/mmu_decl.h"
 
 
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
@@ -330,7 +331,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
         /* XXX It would be nice to differentiate between heavyweight exit and
          * sched_out here, since we could avoid the TLB flush for heavyweight
          * exits. */
-        _tlbia();
+        _tlbil_all();
 }
 
 int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index 25ec5378afa4..70693a5c12a1 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -26,11 +26,24 @@ _GLOBAL(__copy_tofrom_user)
         andi.   r6,r6,7
         PPC_MTOCRF      0x01,r5
         blt     cr1,.Lshort_copy
+/* Below we want to nop out the bne if we're on a CPU that has the
+ * CPU_FTR_UNALIGNED_LD_STD bit set and the CPU_FTR_CP_USE_DCBTZ bit
+ * cleared.
+ * At the time of writing the only CPU that has this combination of bits
+ * set is Power6.
+ */
+BEGIN_FTR_SECTION
+        nop
+FTR_SECTION_ELSE
         bne     .Ldst_unaligned
+ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \
+                    CPU_FTR_UNALIGNED_LD_STD)
 .Ldst_aligned:
-        andi.   r0,r4,7
         addi    r3,r3,-16
+BEGIN_FTR_SECTION
+        andi.   r0,r4,7
         bne     .Lsrc_unaligned
+END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
         srdi    r7,r5,4
 20:     ld      r9,0(r4)
         addi    r4,r4,-8
@@ -138,7 +151,7 @@ _GLOBAL(__copy_tofrom_user)
         PPC_MTOCRF      0x01,r6         /* put #bytes to 8B bdry into cr7 */
         subf    r5,r6,r5
         li      r7,0
-        cmpldi  r1,r5,16
+        cmpldi  cr1,r5,16
         bf      cr7*4+3,1f
 35:     lbz     r0,0(r4)
 81:     stb     r0,0(r3)
diff --git a/arch/powerpc/lib/dma-noncoherent.c b/arch/powerpc/lib/dma-noncoherent.c
index 31734c0969cd..b7dc4c19f582 100644
--- a/arch/powerpc/lib/dma-noncoherent.c
+++ b/arch/powerpc/lib/dma-noncoherent.c
@@ -77,26 +77,26 @@ static DEFINE_SPINLOCK(consistent_lock);
  * the amount of RAM found at boot time.)  I would imagine that get_vm_area()
  * would have to initialise this each time prior to calling vm_region_alloc().
  */
-struct vm_region {
+struct ppc_vm_region {
         struct list_head        vm_list;
         unsigned long           vm_start;
         unsigned long           vm_end;
 };
 
-static struct vm_region consistent_head = {
+static struct ppc_vm_region consistent_head = {
         .vm_list        = LIST_HEAD_INIT(consistent_head.vm_list),
         .vm_start       = CONSISTENT_BASE,
         .vm_end         = CONSISTENT_END,
 };
 
-static struct vm_region *
-vm_region_alloc(struct vm_region *head, size_t size, gfp_t gfp)
+static struct ppc_vm_region *
+ppc_vm_region_alloc(struct ppc_vm_region *head, size_t size, gfp_t gfp)
 {
         unsigned long addr = head->vm_start, end = head->vm_end - size;
         unsigned long flags;
-        struct vm_region *c, *new;
+        struct ppc_vm_region *c, *new;
 
-        new = kmalloc(sizeof(struct vm_region), gfp);
+        new = kmalloc(sizeof(struct ppc_vm_region), gfp);
         if (!new)
                 goto out;
 
@@ -130,9 +130,9 @@ vm_region_alloc(struct vm_region *head, size_t size, gfp_t gfp)
         return NULL;
 }
 
-static struct vm_region *vm_region_find(struct vm_region *head, unsigned long addr)
+static struct ppc_vm_region *ppc_vm_region_find(struct ppc_vm_region *head, unsigned long addr)
 {
-        struct vm_region *c;
+        struct ppc_vm_region *c;
 
         list_for_each_entry(c, &head->vm_list, vm_list) {
                 if (c->vm_start == addr)
@@ -151,7 +151,7 @@ void *
 __dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp)
 {
         struct page *page;
-        struct vm_region *c;
+        struct ppc_vm_region *c;
         unsigned long order;
         u64 mask = 0x00ffffff, limit; /* ISA default */
 
@@ -191,7 +191,7 @@ __dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp)
         /*
          * Allocate a virtual address in the consistent mapping region.
          */
-        c = vm_region_alloc(&consistent_head, size,
+        c = ppc_vm_region_alloc(&consistent_head, size,
                             gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
         if (c) {
                 unsigned long vaddr = c->vm_start;
@@ -239,7 +239,7 @@ EXPORT_SYMBOL(__dma_alloc_coherent);
  */
 void __dma_free_coherent(size_t size, void *vaddr)
 {
-        struct vm_region *c;
+        struct ppc_vm_region *c;
         unsigned long flags, addr;
         pte_t *ptep;
 
@@ -247,7 +247,7 @@ void __dma_free_coherent(size_t size, void *vaddr)
 
         spin_lock_irqsave(&consistent_lock, flags);
 
-        c = vm_region_find(&consistent_head, (unsigned long)vaddr);
+        c = ppc_vm_region_find(&consistent_head, (unsigned long)vaddr);
         if (!c)
                 goto no_area;
 
@@ -320,7 +320,6 @@ static int __init dma_alloc_init(void)
                         ret = -ENOMEM;
                         break;
                 }
-                WARN_ON(!pmd_none(*pmd));
 
                 pte = pte_alloc_kernel(pmd, CONSISTENT_BASE);
                 if (!pte) {
diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
index 3f131129d1c1..fe2d34e5332d 100644
--- a/arch/powerpc/lib/memcpy_64.S
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -18,11 +18,23 @@ _GLOBAL(memcpy)
         andi.   r6,r6,7
         dcbt    0,r4
         blt     cr1,.Lshort_copy
+/* Below we want to nop out the bne if we're on a CPU that has the
+   CPU_FTR_UNALIGNED_LD_STD bit set and the CPU_FTR_CP_USE_DCBTZ bit
+   cleared.
+   At the time of writing the only CPU that has this combination of bits
+   set is Power6. */
+BEGIN_FTR_SECTION
+        nop
+FTR_SECTION_ELSE
         bne     .Ldst_unaligned
+ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \
+                    CPU_FTR_UNALIGNED_LD_STD)
 .Ldst_aligned:
-        andi.   r0,r4,7
         addi    r3,r3,-16
+BEGIN_FTR_SECTION
+        andi.   r0,r4,7
         bne     .Lsrc_unaligned
+END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
         srdi    r7,r5,4
         ld      r9,0(r4)
         addi    r4,r4,-8
@@ -131,7 +143,7 @@ _GLOBAL(memcpy)
         PPC_MTOCRF      0x01,r6         # put #bytes to 8B bdry into cr7
         subf    r5,r6,r5
         li      r7,0
-        cmpldi  r1,r5,16
+        cmpldi  cr1,r5,16
         bf      cr7*4+3,1f
         lbz     r0,0(r4)
         stb     r0,0(r3)
diff --git a/arch/powerpc/math-emu/Makefile b/arch/powerpc/math-emu/Makefile
index 03aa98dd9f0a..f9e506a735ae 100644
--- a/arch/powerpc/math-emu/Makefile
+++ b/arch/powerpc/math-emu/Makefile
@@ -11,6 +11,8 @@ obj-$(CONFIG_MATH_EMULATION)	+= fabs.o fadd.o fadds.o fcmpo.o fcmpu.o \
                                         mcrfs.o mffs.o mtfsb0.o mtfsb1.o \
                                         mtfsf.o mtfsfi.o stfiwx.o stfs.o
 
+obj-$(CONFIG_SPE)               += math_efp.o
+
 CFLAGS_fabs.o = -fno-builtin-fabs
 CFLAGS_math.o = -fno-builtin-fabs
 
diff --git a/arch/powerpc/math-emu/fadd.c b/arch/powerpc/math-emu/fadd.c
index 04d3b4aa32ce..0158a16e2b82 100644
--- a/arch/powerpc/math-emu/fadd.c
+++ b/arch/powerpc/math-emu/fadd.c
@@ -13,7 +13,6 @@ fadd(void *frD, void *frA, void *frB)
         FP_DECL_D(B);
         FP_DECL_D(R);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p\n", __func__, frD, frA, frB);
diff --git a/arch/powerpc/math-emu/fcmpo.c b/arch/powerpc/math-emu/fcmpo.c
index b5dc4498cd71..5bce011c2aec 100644
--- a/arch/powerpc/math-emu/fcmpo.c
+++ b/arch/powerpc/math-emu/fcmpo.c
@@ -14,7 +14,6 @@ fcmpo(u32 *ccr, int crfD, void *frA, void *frB)
         FP_DECL_EX;
         int code[4] = { (1 << 3), (1 << 1), (1 << 2), (1 << 0) };
         long cmp;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p (%08x) %d %p %p\n", __func__, ccr, *ccr, crfD, frA, frB);
@@ -29,7 +28,7 @@ fcmpo(u32 *ccr, int crfD, void *frA, void *frB)
 #endif
 
         if (A_c == FP_CLS_NAN || B_c == FP_CLS_NAN)
-                ret |= EFLAG_VXVC;
+                FP_SET_EXCEPTION(EFLAG_VXVC);
 
         FP_CMP_D(cmp, A, B, 2);
         cmp = code[(cmp + 1) & 3];
@@ -44,5 +43,5 @@ fcmpo(u32 *ccr, int crfD, void *frA, void *frB)
         printk("CR: %08x\n", *ccr);
 #endif
 
-        return ret;
+        return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fdiv.c b/arch/powerpc/math-emu/fdiv.c
index 2db15097d98e..a29239c05e3e 100644
--- a/arch/powerpc/math-emu/fdiv.c
+++ b/arch/powerpc/math-emu/fdiv.c
@@ -13,7 +13,6 @@ fdiv(void *frD, void *frA, void *frB)
         FP_DECL_D(B);
         FP_DECL_D(R);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p\n", __func__, frD, frA, frB);
@@ -28,22 +27,22 @@ fdiv(void *frD, void *frA, void *frB)
 #endif
 
         if (A_c == FP_CLS_ZERO && B_c == FP_CLS_ZERO) {
-                ret |= EFLAG_VXZDZ;
+                FP_SET_EXCEPTION(EFLAG_VXZDZ);
 #ifdef DEBUG
                 printk("%s: FPSCR_VXZDZ raised\n", __func__);
 #endif
         }
         if (A_c == FP_CLS_INF && B_c == FP_CLS_INF) {
-                ret |= EFLAG_VXIDI;
+                FP_SET_EXCEPTION(EFLAG_VXIDI);
 #ifdef DEBUG
                 printk("%s: FPSCR_VXIDI raised\n", __func__);
 #endif
         }
 
         if (B_c == FP_CLS_ZERO && A_c != FP_CLS_ZERO) {
-                ret |= EFLAG_DIVZERO;
+                FP_SET_EXCEPTION(EFLAG_DIVZERO);
                 if (__FPU_TRAP_P(EFLAG_DIVZERO))
-                        return ret;
+                        return FP_CUR_EXCEPTIONS;
         }
         FP_DIV_D(R, A, B);
 
diff --git a/arch/powerpc/math-emu/fdivs.c b/arch/powerpc/math-emu/fdivs.c
index 797f6a9a20b5..526bc261275f 100644
--- a/arch/powerpc/math-emu/fdivs.c
+++ b/arch/powerpc/math-emu/fdivs.c
@@ -14,7 +14,6 @@ fdivs(void *frD, void *frA, void *frB)
         FP_DECL_D(B);
         FP_DECL_D(R);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p\n", __func__, frD, frA, frB);
@@ -29,22 +28,22 @@ fdivs(void *frD, void *frA, void *frB)
 #endif
 
         if (A_c == FP_CLS_ZERO && B_c == FP_CLS_ZERO) {
-                ret |= EFLAG_VXZDZ;
+                FP_SET_EXCEPTION(EFLAG_VXZDZ);
 #ifdef DEBUG
                 printk("%s: FPSCR_VXZDZ raised\n", __func__);
 #endif
         }
         if (A_c == FP_CLS_INF && B_c == FP_CLS_INF) {
-                ret |= EFLAG_VXIDI;
+                FP_SET_EXCEPTION(EFLAG_VXIDI);
 #ifdef DEBUG
                 printk("%s: FPSCR_VXIDI raised\n", __func__);
 #endif
         }
 
         if (B_c == FP_CLS_ZERO && A_c != FP_CLS_ZERO) {
-                ret |= EFLAG_DIVZERO;
+                FP_SET_EXCEPTION(EFLAG_DIVZERO);
                 if (__FPU_TRAP_P(EFLAG_DIVZERO))
-                        return ret;
+                        return FP_CUR_EXCEPTIONS;
         }
 
         FP_DIV_D(R, A, B);
diff --git a/arch/powerpc/math-emu/fmadd.c b/arch/powerpc/math-emu/fmadd.c
index 925313aa6f82..8c3f20aa5a95 100644
--- a/arch/powerpc/math-emu/fmadd.c
+++ b/arch/powerpc/math-emu/fmadd.c
@@ -15,7 +15,6 @@ fmadd(void *frD, void *frA, void *frB, void *frC)
         FP_DECL_D(C);
         FP_DECL_D(T);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -33,12 +32,12 @@ fmadd(void *frD, void *frA, void *frB, void *frC)
 
         if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
             (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
         FP_MUL_D(T, A, C);
 
         if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-                ret |= EFLAG_VXISI;
+                FP_SET_EXCEPTION(EFLAG_VXISI);
 
         FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fmadds.c b/arch/powerpc/math-emu/fmadds.c
index aea80ef79399..794fb31e59d1 100644
--- a/arch/powerpc/math-emu/fmadds.c
+++ b/arch/powerpc/math-emu/fmadds.c
@@ -16,7 +16,6 @@ fmadds(void *frD, void *frA, void *frB, void *frC)
         FP_DECL_D(C);
         FP_DECL_D(T);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -34,12 +33,12 @@ fmadds(void *frD, void *frA, void *frB, void *frC)
 
         if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
             (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
         FP_MUL_D(T, A, C);
 
         if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-                ret |= EFLAG_VXISI;
+                FP_SET_EXCEPTION(EFLAG_VXISI);
 
         FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fmsub.c b/arch/powerpc/math-emu/fmsub.c
index a644d525fca6..626f6fed84ac 100644
--- a/arch/powerpc/math-emu/fmsub.c
+++ b/arch/powerpc/math-emu/fmsub.c
@@ -15,7 +15,6 @@ fmsub(void *frD, void *frA, void *frB, void *frC)
         FP_DECL_D(C);
         FP_DECL_D(T);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -33,7 +32,7 @@ fmsub(void *frD, void *frA, void *frB, void *frC)
 
         if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
             (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
         FP_MUL_D(T, A, C);
 
@@ -41,7 +40,7 @@ fmsub(void *frD, void *frA, void *frB, void *frC)
                 B_s ^= 1;
 
         if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-                ret |= EFLAG_VXISI;
+                FP_SET_EXCEPTION(EFLAG_VXISI);
 
         FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fmsubs.c b/arch/powerpc/math-emu/fmsubs.c
index 2fdeeb9bb569..3425bc899760 100644
--- a/arch/powerpc/math-emu/fmsubs.c
+++ b/arch/powerpc/math-emu/fmsubs.c
@@ -16,7 +16,6 @@ fmsubs(void *frD, void *frA, void *frB, void *frC)
         FP_DECL_D(C);
         FP_DECL_D(T);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -34,7 +33,7 @@ fmsubs(void *frD, void *frA, void *frB, void *frC)
 
         if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
             (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
         FP_MUL_D(T, A, C);
 
@@ -42,7 +41,7 @@ fmsubs(void *frD, void *frA, void *frB, void *frC)
                 B_s ^= 1;
 
         if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-                ret |= EFLAG_VXISI;
+                FP_SET_EXCEPTION(EFLAG_VXISI);
 
         FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fmul.c b/arch/powerpc/math-emu/fmul.c
index 391fd17d3440..2c1929779892 100644
--- a/arch/powerpc/math-emu/fmul.c
+++ b/arch/powerpc/math-emu/fmul.c
@@ -13,7 +13,6 @@ fmul(void *frD, void *frA, void *frB)
         FP_DECL_D(B);
         FP_DECL_D(R);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p\n", __func__, frD, frA, frB);
@@ -31,7 +30,7 @@ fmul(void *frD, void *frA, void *frB)
 
         if ((A_c == FP_CLS_INF && B_c == FP_CLS_ZERO) ||
             (A_c == FP_CLS_ZERO && B_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
         FP_MUL_D(R, A, B);
 
diff --git a/arch/powerpc/math-emu/fmuls.c b/arch/powerpc/math-emu/fmuls.c
index 2d3ec5f7da20..f5ad5c9c77d0 100644
--- a/arch/powerpc/math-emu/fmuls.c
+++ b/arch/powerpc/math-emu/fmuls.c
@@ -14,7 +14,6 @@ fmuls(void *frD, void *frA, void *frB)
         FP_DECL_D(B);
         FP_DECL_D(R);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p\n", __func__, frD, frA, frB);
@@ -32,7 +31,7 @@ fmuls(void *frD, void *frA, void *frB)
 
         if ((A_c == FP_CLS_INF && B_c == FP_CLS_ZERO) ||
             (A_c == FP_CLS_ZERO && B_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
         FP_MUL_D(R, A, B);
 
diff --git a/arch/powerpc/math-emu/fnmadd.c b/arch/powerpc/math-emu/fnmadd.c
index 2497b86494e5..e817bc5453ef 100644
--- a/arch/powerpc/math-emu/fnmadd.c
+++ b/arch/powerpc/math-emu/fnmadd.c
@@ -15,7 +15,6 @@ fnmadd(void *frD, void *frA, void *frB, void *frC)
         FP_DECL_D(C);
         FP_DECL_D(T);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -33,12 +32,12 @@ fnmadd(void *frD, void *frA, void *frB, void *frC)
 
         if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
             (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
         FP_MUL_D(T, A, C);
 
         if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-                ret |= EFLAG_VXISI;
+                FP_SET_EXCEPTION(EFLAG_VXISI);
 
         FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fnmadds.c b/arch/powerpc/math-emu/fnmadds.c
index ee9d71e0b376..4db4b7d9ba8d 100644
--- a/arch/powerpc/math-emu/fnmadds.c
+++ b/arch/powerpc/math-emu/fnmadds.c
@@ -16,7 +16,6 @@ fnmadds(void *frD, void *frA, void *frB, void *frC)
         FP_DECL_D(C);
         FP_DECL_D(T);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -34,12 +33,12 @@ fnmadds(void *frD, void *frA, void *frB, void *frC)
 
         if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
             (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
         FP_MUL_D(T, A, C);
 
         if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-                ret |= EFLAG_VXISI;
+                FP_SET_EXCEPTION(EFLAG_VXISI);
 
         FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fnmsub.c b/arch/powerpc/math-emu/fnmsub.c
index 3885a77acc93..f65979fa770e 100644
--- a/arch/powerpc/math-emu/fnmsub.c
+++ b/arch/powerpc/math-emu/fnmsub.c
@@ -15,7 +15,6 @@ fnmsub(void *frD, void *frA, void *frB, void *frC)
         FP_DECL_D(C);
         FP_DECL_D(T);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -33,7 +32,7 @@ fnmsub(void *frD, void *frA, void *frB, void *frC)
 
         if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
             (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
         FP_MUL_D(T, A, C);
 
@@ -41,7 +40,7 @@ fnmsub(void *frD, void *frA, void *frB, void *frC)
                 B_s ^= 1;
 
         if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-                ret |= EFLAG_VXISI;
+                FP_SET_EXCEPTION(EFLAG_VXISI);
 
         FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fnmsubs.c b/arch/powerpc/math-emu/fnmsubs.c
index f835dfeb0fd1..9021dacc03b8 100644
--- a/arch/powerpc/math-emu/fnmsubs.c
+++ b/arch/powerpc/math-emu/fnmsubs.c
@@ -16,7 +16,6 @@ fnmsubs(void *frD, void *frA, void *frB, void *frC)
         FP_DECL_D(C);
         FP_DECL_D(T);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -34,7 +33,7 @@ fnmsubs(void *frD, void *frA, void *frB, void *frC)
 
         if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
             (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
         FP_MUL_D(T, A, C);
 
@@ -42,7 +41,7 @@ fnmsubs(void *frD, void *frA, void *frB, void *frC)
                 B_s ^= 1;
 
         if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-                ret |= EFLAG_VXISI;
+                FP_SET_EXCEPTION(EFLAG_VXISI);
 
         FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fsqrt.c b/arch/powerpc/math-emu/fsqrt.c
index 3e90072693a0..a55fc7d49983 100644
--- a/arch/powerpc/math-emu/fsqrt.c
+++ b/arch/powerpc/math-emu/fsqrt.c
@@ -12,7 +12,6 @@ fsqrt(void *frD, void *frB)
         FP_DECL_D(B);
         FP_DECL_D(R);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p %p\n", __func__, frD, frB);
@@ -25,9 +24,9 @@ fsqrt(void *frD, void *frB)
 #endif
 
         if (B_s && B_c != FP_CLS_ZERO)
-                ret |= EFLAG_VXSQRT;
+                FP_SET_EXCEPTION(EFLAG_VXSQRT);
         if (B_c == FP_CLS_NAN)
-                ret |= EFLAG_VXSNAN;
+                FP_SET_EXCEPTION(EFLAG_VXSNAN);
 
         FP_SQRT_D(R, B);
 
diff --git a/arch/powerpc/math-emu/fsqrts.c b/arch/powerpc/math-emu/fsqrts.c
index 2843be986e2e..31dccbfc39ff 100644
--- a/arch/powerpc/math-emu/fsqrts.c
+++ b/arch/powerpc/math-emu/fsqrts.c
@@ -13,7 +13,6 @@ fsqrts(void *frD, void *frB)
         FP_DECL_D(B);
         FP_DECL_D(R);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p %p\n", __func__, frD, frB);
@@ -26,9 +25,9 @@ fsqrts(void *frD, void *frB)
 #endif
 
         if (B_s && B_c != FP_CLS_ZERO)
-                ret |= EFLAG_VXSQRT;
+                FP_SET_EXCEPTION(EFLAG_VXSQRT);
         if (B_c == FP_CLS_NAN)
-                ret |= EFLAG_VXSNAN;
+                FP_SET_EXCEPTION(EFLAG_VXSNAN);
 
         FP_SQRT_D(R, B);
 
diff --git a/arch/powerpc/math-emu/fsub.c b/arch/powerpc/math-emu/fsub.c
index 78b09446a0e1..02c5dff458ba 100644
--- a/arch/powerpc/math-emu/fsub.c
+++ b/arch/powerpc/math-emu/fsub.c
@@ -13,7 +13,6 @@ fsub(void *frD, void *frA, void *frB)
         FP_DECL_D(B);
         FP_DECL_D(R);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p\n", __func__, frD, frA, frB);
@@ -31,7 +30,7 @@ fsub(void *frD, void *frA, void *frB)
                 B_s ^= 1;
 
         if (A_s != B_s && A_c == FP_CLS_INF && B_c == FP_CLS_INF)
-                ret |= EFLAG_VXISI;
+                FP_SET_EXCEPTION(EFLAG_VXISI);
 
         FP_ADD_D(R, A, B);
 
diff --git a/arch/powerpc/math-emu/fsubs.c b/arch/powerpc/math-emu/fsubs.c
index d3bf90863cf2..5d9b18c35e07 100644
--- a/arch/powerpc/math-emu/fsubs.c
+++ b/arch/powerpc/math-emu/fsubs.c
@@ -14,7 +14,6 @@ fsubs(void *frD, void *frA, void *frB)
         FP_DECL_D(B);
         FP_DECL_D(R);
         FP_DECL_EX;
-        int ret = 0;
 
 #ifdef DEBUG
         printk("%s: %p %p %p\n", __func__, frD, frA, frB);
@@ -32,7 +31,7 @@ fsubs(void *frD, void *frA, void *frB)
                 B_s ^= 1;
 
         if (A_s != B_s && A_c == FP_CLS_INF && B_c == FP_CLS_INF)
-                ret |= EFLAG_VXISI;
+                FP_SET_EXCEPTION(EFLAG_VXISI);
 
         FP_ADD_D(R, A, B);
 
diff --git a/arch/powerpc/math-emu/math_efp.c b/arch/powerpc/math-emu/math_efp.c
new file mode 100644
index 000000000000..41f4ef30e480
--- /dev/null
+++ b/arch/powerpc/math-emu/math_efp.c
@@ -0,0 +1,720 @@
+/*
+ * arch/powerpc/math-emu/math_efp.c
+ *
+ * Copyright (C) 2006-2008 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Ebony Zhu,   <ebony.zhu@freescale.com>
+ *         Yu Liu,      <yu.liu@freescale.com>
+ *
+ * Derived from arch/alpha/math-emu/math.c
+ *              arch/powerpc/math-emu/math.c
+ *
+ * Description:
+ * This file is the exception handler to make E500 SPE instructions
+ * fully comply with IEEE-754 floating point standard.
+ *
+ * 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/types.h>
+
+#include <asm/uaccess.h>
+#include <asm/reg.h>
+
+#define FP_EX_BOOKE_E500_SPE
+#include <asm/sfp-machine.h>
+
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+#include <math-emu/double.h>
+
+#define EFAPU           0x4
+
+#define VCT             0x4
+#define SPFP            0x6
+#define DPFP            0x7
+
+#define EFSADD          0x2c0
+#define EFSSUB          0x2c1
+#define EFSABS          0x2c4
+#define EFSNABS         0x2c5
+#define EFSNEG          0x2c6
+#define EFSMUL          0x2c8
+#define EFSDIV          0x2c9
+#define EFSCMPGT        0x2cc
+#define EFSCMPLT        0x2cd
+#define EFSCMPEQ        0x2ce
+#define EFSCFD          0x2cf
+#define EFSCFSI         0x2d1
+#define EFSCTUI         0x2d4
+#define EFSCTSI         0x2d5
+#define EFSCTUF         0x2d6
+#define EFSCTSF         0x2d7
+#define EFSCTUIZ        0x2d8
+#define EFSCTSIZ        0x2da
+
+#define EVFSADD         0x280
+#define EVFSSUB         0x281
+#define EVFSABS         0x284
+#define EVFSNABS        0x285
+#define EVFSNEG         0x286
+#define EVFSMUL         0x288
+#define EVFSDIV         0x289
+#define EVFSCMPGT       0x28c
+#define EVFSCMPLT       0x28d
+#define EVFSCMPEQ       0x28e
+#define EVFSCTUI        0x294
+#define EVFSCTSI        0x295
+#define EVFSCTUF        0x296
+#define EVFSCTSF        0x297
+#define EVFSCTUIZ       0x298
+#define EVFSCTSIZ       0x29a
+
+#define EFDADD          0x2e0
+#define EFDSUB          0x2e1
+#define EFDABS          0x2e4
+#define EFDNABS         0x2e5
+#define EFDNEG          0x2e6
+#define EFDMUL          0x2e8
+#define EFDDIV          0x2e9
+#define EFDCTUIDZ       0x2ea
+#define EFDCTSIDZ       0x2eb
+#define EFDCMPGT        0x2ec
+#define EFDCMPLT        0x2ed
+#define EFDCMPEQ        0x2ee
+#define EFDCFS          0x2ef
+#define EFDCTUI         0x2f4
+#define EFDCTSI         0x2f5
+#define EFDCTUF         0x2f6
+#define EFDCTSF         0x2f7
+#define EFDCTUIZ        0x2f8
+#define EFDCTSIZ        0x2fa
+
+#define AB      2
+#define XA      3
+#define XB      4
+#define XCR     5
+#define NOTYPE  0
+
+#define SIGN_BIT_S      (1UL << 31)
+#define SIGN_BIT_D      (1ULL << 63)
+#define FP_EX_MASK      (FP_EX_INEXACT | FP_EX_INVALID | FP_EX_DIVZERO | \
+                        FP_EX_UNDERFLOW | FP_EX_OVERFLOW)
+
+union dw_union {
+        u64 dp[1];
+        u32 wp[2];
+};
+
+static unsigned long insn_type(unsigned long speinsn)
+{
+        unsigned long ret = NOTYPE;
+
+        switch (speinsn & 0x7ff) {
+        case EFSABS:    ret = XA;       break;
+        case EFSADD:    ret = AB;       break;
+        case EFSCFD:    ret = XB;       break;
+        case EFSCMPEQ:  ret = XCR;      break;
+        case EFSCMPGT:  ret = XCR;      break;
+        case EFSCMPLT:  ret = XCR;      break;
+        case EFSCTSF:   ret = XB;       break;
+        case EFSCTSI:   ret = XB;       break;
+        case EFSCTSIZ:  ret = XB;       break;
+        case EFSCTUF:   ret = XB;       break;
+        case EFSCTUI:   ret = XB;       break;
+        case EFSCTUIZ:  ret = XB;       break;
+        case EFSDIV:    ret = AB;       break;
+        case EFSMUL:    ret = AB;       break;
+        case EFSNABS:   ret = XA;       break;
+        case EFSNEG:    ret = XA;       break;
+        case EFSSUB:    ret = AB;       break;
+        case EFSCFSI:   ret = XB;       break;
+
+        case EVFSABS:   ret = XA;       break;
+        case EVFSADD:   ret = AB;       break;
+        case EVFSCMPEQ: ret = XCR;      break;
+        case EVFSCMPGT: ret = XCR;      break;
+        case EVFSCMPLT: ret = XCR;      break;
+        case EVFSCTSF:  ret = XB;       break;
+        case EVFSCTSI:  ret = XB;       break;
+        case EVFSCTSIZ: ret = XB;       break;
+        case EVFSCTUF:  ret = XB;       break;
+        case EVFSCTUI:  ret = XB;       break;
+        case EVFSCTUIZ: ret = XB;       break;
+        case EVFSDIV:   ret = AB;       break;
+        case EVFSMUL:   ret = AB;       break;
+        case EVFSNABS:  ret = XA;       break;
+        case EVFSNEG:   ret = XA;       break;
+        case EVFSSUB:   ret = AB;       break;
+
+        case EFDABS:    ret = XA;       break;
+        case EFDADD:    ret = AB;       break;
+        case EFDCFS:    ret = XB;       break;
+        case EFDCMPEQ:  ret = XCR;      break;
+        case EFDCMPGT:  ret = XCR;      break;
+        case EFDCMPLT:  ret = XCR;      break;
+        case EFDCTSF:   ret = XB;       break;
+        case EFDCTSI:   ret = XB;       break;
+        case EFDCTSIDZ: ret = XB;       break;
+        case EFDCTSIZ:  ret = XB;       break;
+        case EFDCTUF:   ret = XB;       break;
+        case EFDCTUI:   ret = XB;       break;
+        case EFDCTUIDZ: ret = XB;       break;
+        case EFDCTUIZ:  ret = XB;       break;
+        case EFDDIV:    ret = AB;       break;
+        case EFDMUL:    ret = AB;       break;
+        case EFDNABS:   ret = XA;       break;
+        case EFDNEG:    ret = XA;       break;
+        case EFDSUB:    ret = AB;       break;
+
+        default:
+                printk(KERN_ERR "\nOoops! SPE instruction no type found.");
+                printk(KERN_ERR "\ninst code: %08lx\n", speinsn);
+        }
+
+        return ret;
+}
+
+int do_spe_mathemu(struct pt_regs *regs)
+{
+        FP_DECL_EX;
+        int IR, cmp;
+
+        unsigned long type, func, fc, fa, fb, src, speinsn;
+        union dw_union vc, va, vb;
+
+        if (get_user(speinsn, (unsigned int __user *) regs->nip))
+                return -EFAULT;
+        if ((speinsn >> 26) != EFAPU)
+                return -EINVAL;         /* not an spe instruction */
+
+        type = insn_type(speinsn);
+        if (type == NOTYPE)
+                return -ENOSYS;
+
+        func = speinsn & 0x7ff;
+        fc = (speinsn >> 21) & 0x1f;
+        fa = (speinsn >> 16) & 0x1f;
+        fb = (speinsn >> 11) & 0x1f;
+        src = (speinsn >> 5) & 0x7;
+
+        vc.wp[0] = current->thread.evr[fc];
+        vc.wp[1] = regs->gpr[fc];
+        va.wp[0] = current->thread.evr[fa];
+        va.wp[1] = regs->gpr[fa];
+        vb.wp[0] = current->thread.evr[fb];
+        vb.wp[1] = regs->gpr[fb];
+
+        __FPU_FPSCR = mfspr(SPRN_SPEFSCR);
+
+#ifdef DEBUG
+        printk("speinsn:%08lx spefscr:%08lx\n", speinsn, __FPU_FPSCR);
+        printk("vc: %08x  %08x\n", vc.wp[0], vc.wp[1]);
+        printk("va: %08x  %08x\n", va.wp[0], va.wp[1]);
+        printk("vb: %08x  %08x\n", vb.wp[0], vb.wp[1]);
+#endif
+
+        switch (src) {
+        case SPFP: {
+                FP_DECL_S(SA); FP_DECL_S(SB); FP_DECL_S(SR);
+
+                switch (type) {
+                case AB:
+                case XCR:
+                        FP_UNPACK_SP(SA, va.wp + 1);
+                case XB:
+                        FP_UNPACK_SP(SB, vb.wp + 1);
+                        break;
+                case XA:
+                        FP_UNPACK_SP(SA, va.wp + 1);
+                        break;
+                }
+
+#ifdef DEBUG
+                printk("SA: %ld %08lx %ld (%ld)\n", SA_s, SA_f, SA_e, SA_c);
+                printk("SB: %ld %08lx %ld (%ld)\n", SB_s, SB_f, SB_e, SB_c);
+#endif
+
+                switch (func) {
+                case EFSABS:
+                        vc.wp[1] = va.wp[1] & ~SIGN_BIT_S;
+                        goto update_regs;
+
+                case EFSNABS:
+                        vc.wp[1] = va.wp[1] | SIGN_BIT_S;
+                        goto update_regs;
+
+                case EFSNEG:
+                        vc.wp[1] = va.wp[1] ^ SIGN_BIT_S;
+                        goto update_regs;
+
+                case EFSADD:
+                        FP_ADD_S(SR, SA, SB);
+                        goto pack_s;
+
+                case EFSSUB:
+                        FP_SUB_S(SR, SA, SB);
+                        goto pack_s;
+
+                case EFSMUL:
+                        FP_MUL_S(SR, SA, SB);
+                        goto pack_s;
+
+                case EFSDIV:
+                        FP_DIV_S(SR, SA, SB);
+                        goto pack_s;
+
+                case EFSCMPEQ:
+                        cmp = 0;
+                        goto cmp_s;
+
+                case EFSCMPGT:
+                        cmp = 1;
+                        goto cmp_s;
+
+                case EFSCMPLT:
+                        cmp = -1;
+                        goto cmp_s;
+
+                case EFSCTSF:
+                case EFSCTUF:
+                        if (!((vb.wp[1] >> 23) == 0xff && ((vb.wp[1] & 0x7fffff) > 0))) {
+                                /* NaN */
+                                if (((vb.wp[1] >> 23) & 0xff) == 0) {
+                                        /* denorm */
+                                        vc.wp[1] = 0x0;
+                                } else if ((vb.wp[1] >> 31) == 0) {
+                                        /* positive normal */
+                                        vc.wp[1] = (func == EFSCTSF) ?
+                                                0x7fffffff : 0xffffffff;
+                                } else { /* negative normal */
+                                        vc.wp[1] = (func == EFSCTSF) ?
+                                                0x80000000 : 0x0;
+                                }
+                        } else { /* rB is NaN */
+                                vc.wp[1] = 0x0;
+                        }
+                        goto update_regs;
+
+                case EFSCFD: {
+                        FP_DECL_D(DB);
+                        FP_CLEAR_EXCEPTIONS;
+                        FP_UNPACK_DP(DB, vb.dp);
+#ifdef DEBUG
+                        printk("DB: %ld %08lx %08lx %ld (%ld)\n",
+                                        DB_s, DB_f1, DB_f0, DB_e, DB_c);
+#endif
+                        FP_CONV(S, D, 1, 2, SR, DB);
+                        goto pack_s;
+                }
+
+                case EFSCTSI:
+                case EFSCTSIZ:
+                case EFSCTUI:
+                case EFSCTUIZ:
+                        if (func & 0x4) {
+                                _FP_ROUND(1, SB);
+                        } else {
+                                _FP_ROUND_ZERO(1, SB);
+                        }
+                        FP_TO_INT_S(vc.wp[1], SB, 32, ((func & 0x3) != 0));
+                        goto update_regs;
+
+                default:
+                        goto illegal;
+                }
+                break;
+
+pack_s:
+#ifdef DEBUG
+                printk("SR: %ld %08lx %ld (%ld)\n", SR_s, SR_f, SR_e, SR_c);
+#endif
+                FP_PACK_SP(vc.wp + 1, SR);
+                goto update_regs;
+
+cmp_s:
+                FP_CMP_S(IR, SA, SB, 3);
+                if (IR == 3 && (FP_ISSIGNAN_S(SA) || FP_ISSIGNAN_S(SB)))
+                        FP_SET_EXCEPTION(FP_EX_INVALID);
+                if (IR == cmp) {
+                        IR = 0x4;
+                } else {
+                        IR = 0;
+                }
+                goto update_ccr;
+        }
+
+        case DPFP: {
+                FP_DECL_D(DA); FP_DECL_D(DB); FP_DECL_D(DR);
+
+                switch (type) {
+                case AB:
+                case XCR:
+                        FP_UNPACK_DP(DA, va.dp);
+                case XB:
+                        FP_UNPACK_DP(DB, vb.dp);
+                        break;
+                case XA:
+                        FP_UNPACK_DP(DA, va.dp);
+                        break;
+                }
+
+#ifdef DEBUG
+                printk("DA: %ld %08lx %08lx %ld (%ld)\n",
+                                DA_s, DA_f1, DA_f0, DA_e, DA_c);
+                printk("DB: %ld %08lx %08lx %ld (%ld)\n",
+                                DB_s, DB_f1, DB_f0, DB_e, DB_c);
+#endif
+
+                switch (func) {
+                case EFDABS:
+                        vc.dp[0] = va.dp[0] & ~SIGN_BIT_D;
+                        goto update_regs;
+
+                case EFDNABS:
+                        vc.dp[0] = va.dp[0] | SIGN_BIT_D;
+                        goto update_regs;
+
+                case EFDNEG:
+                        vc.dp[0] = va.dp[0] ^ SIGN_BIT_D;
+                        goto update_regs;
+
+                case EFDADD:
+                        FP_ADD_D(DR, DA, DB);
+                        goto pack_d;
+
+                case EFDSUB:
+                        FP_SUB_D(DR, DA, DB);
+                        goto pack_d;
+
+                case EFDMUL:
+                        FP_MUL_D(DR, DA, DB);
+                        goto pack_d;
+
+                case EFDDIV:
+                        FP_DIV_D(DR, DA, DB);
+                        goto pack_d;
+
+                case EFDCMPEQ:
+                        cmp = 0;
+                        goto cmp_d;
+
+                case EFDCMPGT:
+                        cmp = 1;
+                        goto cmp_d;
+
+                case EFDCMPLT:
+                        cmp = -1;
+                        goto cmp_d;
+
+                case EFDCTSF:
+                case EFDCTUF:
+                        if (!((vb.wp[0] >> 20) == 0x7ff &&
+                           ((vb.wp[0] & 0xfffff) > 0 || (vb.wp[1] > 0)))) {
+                                /* not a NaN */
+                                if (((vb.wp[0] >> 20) & 0x7ff) == 0) {
+                                        /* denorm */
+                                        vc.wp[1] = 0x0;
+                                } else if ((vb.wp[0] >> 31) == 0) {
+                                        /* positive normal */
+                                        vc.wp[1] = (func == EFDCTSF) ?
+                                                0x7fffffff : 0xffffffff;
+                                } else { /* negative normal */
+                                        vc.wp[1] = (func == EFDCTSF) ?
+                                                0x80000000 : 0x0;
+                                }
+                        } else { /* NaN */
+                                vc.wp[1] = 0x0;
+                        }
+                        goto update_regs;
+
+                case EFDCFS: {
+                        FP_DECL_S(SB);
+                        FP_CLEAR_EXCEPTIONS;
+                        FP_UNPACK_SP(SB, vb.wp + 1);
+#ifdef DEBUG
+                        printk("SB: %ld %08lx %ld (%ld)\n",
+                                        SB_s, SB_f, SB_e, SB_c);
+#endif
+                        FP_CONV(D, S, 2, 1, DR, SB);
+                        goto pack_d;
+                }
+
+                case EFDCTUIDZ:
+                case EFDCTSIDZ:
+                        _FP_ROUND_ZERO(2, DB);
+                        FP_TO_INT_D(vc.dp[0], DB, 64, ((func & 0x1) == 0));
+                        goto update_regs;
+
+                case EFDCTUI:
+                case EFDCTSI:
+                case EFDCTUIZ:
+                case EFDCTSIZ:
+                        if (func & 0x4) {
+                                _FP_ROUND(2, DB);
+                        } else {
+                                _FP_ROUND_ZERO(2, DB);
+                        }
+                        FP_TO_INT_D(vc.wp[1], DB, 32, ((func & 0x3) != 0));
+                        goto update_regs;
+
+                default:
+                        goto illegal;
+                }
+                break;
+
+pack_d:
+#ifdef DEBUG
+                printk("DR: %ld %08lx %08lx %ld (%ld)\n",
+                                DR_s, DR_f1, DR_f0, DR_e, DR_c);
+#endif
+                FP_PACK_DP(vc.dp, DR);
+                goto update_regs;
+
+cmp_d:
+                FP_CMP_D(IR, DA, DB, 3);
+                if (IR == 3 && (FP_ISSIGNAN_D(DA) || FP_ISSIGNAN_D(DB)))
+                        FP_SET_EXCEPTION(FP_EX_INVALID);
+                if (IR == cmp) {
+                        IR = 0x4;
+                } else {
+                        IR = 0;
+                }
+                goto update_ccr;
+
+        }
+
+        case VCT: {
+                FP_DECL_S(SA0); FP_DECL_S(SB0); FP_DECL_S(SR0);
+                FP_DECL_S(SA1); FP_DECL_S(SB1); FP_DECL_S(SR1);
+                int IR0, IR1;
+
+                switch (type) {
+                case AB:
+                case XCR:
+                        FP_UNPACK_SP(SA0, va.wp);
+                        FP_UNPACK_SP(SA1, va.wp + 1);
+                case XB:
+                        FP_UNPACK_SP(SB0, vb.wp);
+                        FP_UNPACK_SP(SB1, vb.wp + 1);
+                        break;
+                case XA:
+                        FP_UNPACK_SP(SA0, va.wp);
+                        FP_UNPACK_SP(SA1, va.wp + 1);
+                        break;
+                }
+
+#ifdef DEBUG
+                printk("SA0: %ld %08lx %ld (%ld)\n", SA0_s, SA0_f, SA0_e, SA0_c);
+                printk("SA1: %ld %08lx %ld (%ld)\n", SA1_s, SA1_f, SA1_e, SA1_c);
+                printk("SB0: %ld %08lx %ld (%ld)\n", SB0_s, SB0_f, SB0_e, SB0_c);
+                printk("SB1: %ld %08lx %ld (%ld)\n", SB1_s, SB1_f, SB1_e, SB1_c);
+#endif
+
+                switch (func) {
+                case EVFSABS:
+                        vc.wp[0] = va.wp[0] & ~SIGN_BIT_S;
+                        vc.wp[1] = va.wp[1] & ~SIGN_BIT_S;
+                        goto update_regs;
+
+                case EVFSNABS:
+                        vc.wp[0] = va.wp[0] | SIGN_BIT_S;
+                        vc.wp[1] = va.wp[1] | SIGN_BIT_S;
+                        goto update_regs;
+
+                case EVFSNEG:
+                        vc.wp[0] = va.wp[0] ^ SIGN_BIT_S;
+                        vc.wp[1] = va.wp[1] ^ SIGN_BIT_S;
+                        goto update_regs;
+
+                case EVFSADD:
+                        FP_ADD_S(SR0, SA0, SB0);
+                        FP_ADD_S(SR1, SA1, SB1);
+                        goto pack_vs;
+
+                case EVFSSUB:
+                        FP_SUB_S(SR0, SA0, SB0);
+                        FP_SUB_S(SR1, SA1, SB1);
+                        goto pack_vs;
+
+                case EVFSMUL:
+                        FP_MUL_S(SR0, SA0, SB0);
+                        FP_MUL_S(SR1, SA1, SB1);
+                        goto pack_vs;
+
+                case EVFSDIV:
+                        FP_DIV_S(SR0, SA0, SB0);
+                        FP_DIV_S(SR1, SA1, SB1);
+                        goto pack_vs;
+
+                case EVFSCMPEQ:
+                        cmp = 0;
+                        goto cmp_vs;
+
+                case EVFSCMPGT:
+                        cmp = 1;
+                        goto cmp_vs;
+
+                case EVFSCMPLT:
+                        cmp = -1;
+                        goto cmp_vs;
+
+                case EVFSCTSF:
+                        __asm__ __volatile__ ("mtspr 512, %4\n"
+                                "efsctsf %0, %2\n"
+                                "efsctsf %1, %3\n"
+                                : "=r" (vc.wp[0]), "=r" (vc.wp[1])
+                                : "r" (vb.wp[0]), "r" (vb.wp[1]), "r" (0));
+                        goto update_regs;
+
+                case EVFSCTUF:
+                        __asm__ __volatile__ ("mtspr 512, %4\n"
+                                "efsctuf %0, %2\n"
+                                "efsctuf %1, %3\n"
+                                : "=r" (vc.wp[0]), "=r" (vc.wp[1])
+                                : "r" (vb.wp[0]), "r" (vb.wp[1]), "r" (0));
+                        goto update_regs;
+
+                case EVFSCTUI:
+                case EVFSCTSI:
+                case EVFSCTUIZ:
+                case EVFSCTSIZ:
+                        if (func & 0x4) {
+                                _FP_ROUND(1, SB0);
+                                _FP_ROUND(1, SB1);
+                        } else {
+                                _FP_ROUND_ZERO(1, SB0);
+                                _FP_ROUND_ZERO(1, SB1);
+                        }
+                        FP_TO_INT_S(vc.wp[0], SB0, 32, ((func & 0x3) != 0));
+                        FP_TO_INT_S(vc.wp[1], SB1, 32, ((func & 0x3) != 0));
+                        goto update_regs;
+
+                default:
+                        goto illegal;
+                }
+                break;
+
+pack_vs:
+#ifdef DEBUG
+                printk("SR0: %ld %08lx %ld (%ld)\n", SR0_s, SR0_f, SR0_e, SR0_c);
+                printk("SR1: %ld %08lx %ld (%ld)\n", SR1_s, SR1_f, SR1_e, SR1_c);
+#endif
+                FP_PACK_SP(vc.wp, SR0);
+                FP_PACK_SP(vc.wp + 1, SR1);
+                goto update_regs;
+
+cmp_vs:
+                {
+                        int ch, cl;
+
+                        FP_CMP_S(IR0, SA0, SB0, 3);
+                        FP_CMP_S(IR1, SA1, SB1, 3);
+                        if (IR0 == 3 && (FP_ISSIGNAN_S(SA0) || FP_ISSIGNAN_S(SB0)))
+                                FP_SET_EXCEPTION(FP_EX_INVALID);
+                        if (IR1 == 3 && (FP_ISSIGNAN_S(SA1) || FP_ISSIGNAN_S(SB1)))
+                                FP_SET_EXCEPTION(FP_EX_INVALID);
+                        ch = (IR0 == cmp) ? 1 : 0;
+                        cl = (IR1 == cmp) ? 1 : 0;
+                        IR = (ch << 3) | (cl << 2) | ((ch | cl) << 1) |
+                                ((ch & cl) << 0);
+                        goto update_ccr;
+                }
+        }
+        default:
+                return -EINVAL;
+        }
+
+update_ccr:
+        regs->ccr &= ~(15 << ((7 - ((speinsn >> 23) & 0x7)) << 2));
+        regs->ccr |= (IR << ((7 - ((speinsn >> 23) & 0x7)) << 2));
+
+update_regs:
+        __FPU_FPSCR &= ~FP_EX_MASK;
+        __FPU_FPSCR |= (FP_CUR_EXCEPTIONS & FP_EX_MASK);
+        mtspr(SPRN_SPEFSCR, __FPU_FPSCR);
+
+        current->thread.evr[fc] = vc.wp[0];
+        regs->gpr[fc] = vc.wp[1];
+
+#ifdef DEBUG
+        printk("ccr = %08lx\n", regs->ccr);
+        printk("cur exceptions = %08x spefscr = %08lx\n",
+                        FP_CUR_EXCEPTIONS, __FPU_FPSCR);
+        printk("vc: %08x  %08x\n", vc.wp[0], vc.wp[1]);
+        printk("va: %08x  %08x\n", va.wp[0], va.wp[1]);
+        printk("vb: %08x  %08x\n", vb.wp[0], vb.wp[1]);
+#endif
+
+        return 0;
+
+illegal:
+        printk(KERN_ERR "\nOoops! IEEE-754 compliance handler encountered un-supported instruction.\ninst code: %08lx\n", speinsn);
+        return -ENOSYS;
+}
+
+int speround_handler(struct pt_regs *regs)
+{
+        union dw_union fgpr;
+        int s_lo, s_hi;
+        unsigned long speinsn, type, fc;
+
+        if (get_user(speinsn, (unsigned int __user *) regs->nip))
+                return -EFAULT;
+        if ((speinsn >> 26) != 4)
+                return -EINVAL;         /* not an spe instruction */
+
+        type = insn_type(speinsn & 0x7ff);
+        if (type == XCR) return -ENOSYS;
+
+        fc = (speinsn >> 21) & 0x1f;
+        s_lo = regs->gpr[fc] & SIGN_BIT_S;
+        s_hi = current->thread.evr[fc] & SIGN_BIT_S;
+        fgpr.wp[0] = current->thread.evr[fc];
+        fgpr.wp[1] = regs->gpr[fc];
+
+        __FPU_FPSCR = mfspr(SPRN_SPEFSCR);
+
+        switch ((speinsn >> 5) & 0x7) {
+        /* Since SPE instructions on E500 core can handle round to nearest
+         * and round toward zero with IEEE-754 complied, we just need
+         * to handle round toward +Inf and round toward -Inf by software.
+         */
+        case SPFP:
+                if ((FP_ROUNDMODE) == FP_RND_PINF) {
+                        if (!s_lo) fgpr.wp[1]++; /* Z > 0, choose Z1 */
+                } else { /* round to -Inf */
+                        if (s_lo) fgpr.wp[1]++; /* Z < 0, choose Z2 */
+                }
+                break;
+
+        case DPFP:
+                if (FP_ROUNDMODE == FP_RND_PINF) {
+                        if (!s_hi) fgpr.dp[0]++; /* Z > 0, choose Z1 */
+                } else { /* round to -Inf */
+                        if (s_hi) fgpr.dp[0]++; /* Z < 0, choose Z2 */
+                }
+                break;
+
+        case VCT:
+                if (FP_ROUNDMODE == FP_RND_PINF) {
+                        if (!s_lo) fgpr.wp[1]++; /* Z_low > 0, choose Z1 */
+                        if (!s_hi) fgpr.wp[0]++; /* Z_high word > 0, choose Z1 */
+                } else { /* round to -Inf */
+                        if (s_lo) fgpr.wp[1]++; /* Z_low < 0, choose Z2 */
+                        if (s_hi) fgpr.wp[0]++; /* Z_high < 0, choose Z2 */
+                }
+                break;
+
+        default:
+                return -EINVAL;
+        }
+
+        current->thread.evr[fc] = fgpr.wp[0];
+        regs->gpr[fc] = fgpr.wp[1];
+
+        return 0;
+}
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index e7392b45a5ef..953cc4a1cde5 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -6,17 +6,19 @@ ifeq ($(CONFIG_PPC64),y)
 EXTRA_CFLAGS    += -mno-minimal-toc
 endif
 
-obj-y                           := fault.o mem.o \
+obj-y                           := fault.o mem.o pgtable.o \
                                    init_$(CONFIG_WORD_SIZE).o \
-                                   pgtable_$(CONFIG_WORD_SIZE).o \
-                                   mmu_context_$(CONFIG_WORD_SIZE).o
+                                   pgtable_$(CONFIG_WORD_SIZE).o
+obj-$(CONFIG_PPC_MMU_NOHASH)    += mmu_context_nohash.o tlb_nohash.o \
+                                   tlb_nohash_low.o
 hash-$(CONFIG_PPC_NATIVE)       := hash_native_64.o
 obj-$(CONFIG_PPC64)             += hash_utils_64.o \
                                    slb_low.o slb.o stab.o \
                                    gup.o mmap.o $(hash-y)
 obj-$(CONFIG_PPC_STD_MMU_32)    += ppc_mmu_32.o
 obj-$(CONFIG_PPC_STD_MMU)       += hash_low_$(CONFIG_WORD_SIZE).o \
-                                   tlb_$(CONFIG_WORD_SIZE).o
+                                   tlb_hash$(CONFIG_WORD_SIZE).o \
+                                   mmu_context_hash$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_40x)               += 40x_mmu.o
 obj-$(CONFIG_44x)               += 44x_mmu.o
 obj-$(CONFIG_FSL_BOOKE)         += fsl_booke_mmu.o
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 866098686da8..91c7b8636b8a 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -30,6 +30,7 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 
+#include <asm/firmware.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
@@ -283,7 +284,7 @@ good_area:
                                 }
                                 pte_update(ptep, 0, _PAGE_HWEXEC |
                                            _PAGE_ACCESSED);
-                                _tlbie(address, mm->context.id);
+                                local_flush_tlb_page(vma, address);
                                 pte_unmap_unlock(ptep, ptl);
                                 up_read(&mm->mmap_sem);
                                 return 0;
@@ -318,9 +319,16 @@ good_area:
                         goto do_sigbus;
                 BUG();
         }
-        if (ret & VM_FAULT_MAJOR)
+        if (ret & VM_FAULT_MAJOR) {
                 current->maj_flt++;
-        else
+#ifdef CONFIG_PPC_SMLPAR
+                if (firmware_has_feature(FW_FEATURE_CMO)) {
+                        preempt_disable();
+                        get_lppaca()->page_ins += (1 << PAGE_FACTOR);
+                        preempt_enable();
+                }
+#endif
+        } else
                 current->min_flt++;
         up_read(&mm->mmap_sem);
         return 0;
diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index 7bffb70b9fe2..67850ec9feb3 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -36,36 +36,6 @@ mmu_hash_lock:
 #endif /* CONFIG_SMP */
 
 /*
- * Sync CPUs with hash_page taking & releasing the hash
- * table lock
- */
-#ifdef CONFIG_SMP
-        .text
-_GLOBAL(hash_page_sync)
-        mfmsr   r10
-        rlwinm  r0,r10,0,17,15          /* clear bit 16 (MSR_EE) */
-        mtmsr   r0
-        lis     r8,mmu_hash_lock@h
-        ori     r8,r8,mmu_hash_lock@l
-        lis     r0,0x0fff
-        b       10f
-11:     lwz     r6,0(r8)
-        cmpwi   0,r6,0
-        bne     11b
-10:     lwarx   r6,0,r8
-        cmpwi   0,r6,0
-        bne-    11b
-        stwcx.  r0,0,r8
-        bne-    10b
-        isync
-        eieio
-        li      r0,0
-        stw     r0,0(r8)
-        mtmsr   r10
-        blr
-#endif /* CONFIG_SMP */
-
-/*
  * Load a PTE into the hash table, if possible.
  * The address is in r4, and r3 contains an access flag:
  * _PAGE_RW (0x400) if a write.
@@ -353,8 +323,8 @@ _GLOBAL(create_hpte)
         ori     r8,r8,0xe14             /* clear out reserved bits and M */
         andc    r8,r5,r8                /* PP = user? (rw&dirty? 2: 3): 0 */
 BEGIN_FTR_SECTION
-        ori     r8,r8,_PAGE_COHERENT    /* set M (coherence required) */
-END_FTR_SECTION_IFSET(CPU_FTR_NEED_COHERENT)
+        rlwinm  r8,r8,0,~_PAGE_COHERENT /* clear M (coherence not required) */
+END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 #ifdef CONFIG_PTE_64BIT
         /* Put the XPN bits into the PTE */
         rlwimi  r8,r10,8,20,22
@@ -663,3 +633,80 @@ _GLOBAL(flush_hash_patch_B)
         SYNC_601
         isync
         blr
+
+/*
+ * Flush an entry from the TLB
+ */
+_GLOBAL(_tlbie)
+#ifdef CONFIG_SMP
+        rlwinm  r8,r1,0,0,(31-THREAD_SHIFT)
+        lwz     r8,TI_CPU(r8)
+        oris    r8,r8,11
+        mfmsr   r10
+        SYNC
+        rlwinm  r0,r10,0,17,15          /* clear bit 16 (MSR_EE) */
+        rlwinm  r0,r0,0,28,26           /* clear DR */
+        mtmsr   r0
+        SYNC_601
+        isync
+        lis     r9,mmu_hash_lock@h
+        ori     r9,r9,mmu_hash_lock@l
+        tophys(r9,r9)
+10:     lwarx   r7,0,r9
+        cmpwi   0,r7,0
+        bne-    10b
+        stwcx.  r8,0,r9
+        bne-    10b
+        eieio
+        tlbie   r3
+        sync
+        TLBSYNC
+        li      r0,0
+        stw     r0,0(r9)                /* clear mmu_hash_lock */
+        mtmsr   r10
+        SYNC_601
+        isync
+#else /* CONFIG_SMP */
+        tlbie   r3
+        sync
+#endif /* CONFIG_SMP */
+        blr
+
+/*
+ * Flush the entire TLB. 603/603e only
+ */
+_GLOBAL(_tlbia)
+#if defined(CONFIG_SMP)
+        rlwinm  r8,r1,0,0,(31-THREAD_SHIFT)
+        lwz     r8,TI_CPU(r8)
+        oris    r8,r8,10
+        mfmsr   r10
+        SYNC
+        rlwinm  r0,r10,0,17,15          /* clear bit 16 (MSR_EE) */
+        rlwinm  r0,r0,0,28,26           /* clear DR */
+        mtmsr   r0
+        SYNC_601
+        isync
+        lis     r9,mmu_hash_lock@h
+        ori     r9,r9,mmu_hash_lock@l
+        tophys(r9,r9)
+10:     lwarx   r7,0,r9
+        cmpwi   0,r7,0
+        bne-    10b
+        stwcx.  r8,0,r9
+        bne-    10b
+        sync
+        tlbia
+        sync
+        TLBSYNC
+        li      r0,0
+        stw     r0,0(r9)                /* clear mmu_hash_lock */
+        mtmsr   r10
+        SYNC_601
+        isync
+#else /* CONFIG_SMP */
+        sync
+        tlbia
+        sync
+#endif /* CONFIG_SMP */
+        blr
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index f0c3b88d50fa..201c7a5486cb 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -53,8 +53,7 @@ unsigned int mmu_huge_psizes[MMU_PAGE_COUNT] = { }; /* initialize all to 0 */
 
 /* Subtract one from array size because we don't need a cache for 4K since
  * is not a huge page size */
-#define huge_pgtable_cache(psize)       (pgtable_cache[HUGEPTE_CACHE_NUM \
-                                                        + psize-1])
+#define HUGE_PGTABLE_INDEX(psize)       (HUGEPTE_CACHE_NUM + psize - 1)
 #define HUGEPTE_CACHE_NAME(psize)       (huge_pgtable_cache_name[psize])
 
 static const char *huge_pgtable_cache_name[MMU_PAGE_COUNT] = {
@@ -113,7 +112,7 @@ static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
 static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
                            unsigned long address, unsigned int psize)
 {
-        pte_t *new = kmem_cache_zalloc(huge_pgtable_cache(psize),
+        pte_t *new = kmem_cache_zalloc(pgtable_cache[HUGE_PGTABLE_INDEX(psize)],
                                       GFP_KERNEL|__GFP_REPEAT);
 
         if (! new)
@@ -121,7 +120,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 
         spin_lock(&mm->page_table_lock);
         if (!hugepd_none(*hpdp))
-                kmem_cache_free(huge_pgtable_cache(psize), new);
+                kmem_cache_free(pgtable_cache[HUGE_PGTABLE_INDEX(psize)], new);
         else
                 hpdp->pd = (unsigned long)new | HUGEPD_OK;
         spin_unlock(&mm->page_table_lock);
@@ -763,13 +762,14 @@ static int __init hugetlbpage_init(void)
 
         for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
                 if (mmu_huge_psizes[psize]) {
-                        huge_pgtable_cache(psize) = kmem_cache_create(
-                                                HUGEPTE_CACHE_NAME(psize),
-                                                HUGEPTE_TABLE_SIZE(psize),
-                                                HUGEPTE_TABLE_SIZE(psize),
-                                                0,
-                                                NULL);
-                        if (!huge_pgtable_cache(psize))
+                        pgtable_cache[HUGE_PGTABLE_INDEX(psize)] =
+                                kmem_cache_create(
+                                        HUGEPTE_CACHE_NAME(psize),
+                                        HUGEPTE_TABLE_SIZE(psize),
+                                        HUGEPTE_TABLE_SIZE(psize),
+                                        0,
+                                        NULL);
+                        if (!pgtable_cache[HUGE_PGTABLE_INDEX(psize)])
                                 panic("hugetlbpage_init(): could not create %s"\
                                       "\n", HUGEPTE_CACHE_NAME(psize));
                 }
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 388ceda632f3..666a5e8a5be1 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -35,7 +35,6 @@
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
 #include <asm/io.h>
-#include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 #include <asm/smp.h>
@@ -49,7 +48,7 @@
 
 #if defined(CONFIG_KERNEL_START_BOOL) || defined(CONFIG_LOWMEM_SIZE_BOOL)
 /* The ammount of lowmem must be within 0xF0000000 - KERNELBASE. */
-#if (CONFIG_LOWMEM_SIZE > (0xF0000000 - KERNELBASE))
+#if (CONFIG_LOWMEM_SIZE > (0xF0000000 - PAGE_OFFSET))
 #error "You must adjust CONFIG_LOWMEM_SIZE or CONFIG_START_KERNEL"
 #endif
 #endif
@@ -180,9 +179,6 @@ void __init MMU_init(void)
         if (ppc_md.progress)
                 ppc_md.progress("MMU:setio", 0x302);
 
-        /* Initialize the context management stuff */
-        mmu_context_init();
-
         if (ppc_md.progress)
                 ppc_md.progress("MMU:exit", 0x211);
 
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index b9e1a1da6e52..53b06ebb3f2f 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -102,8 +102,8 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
                 return ppc_md.phys_mem_access_prot(file, pfn, size, vma_prot);
 
         if (!page_is_ram(pfn))
-                vma_prot = __pgprot(pgprot_val(vma_prot)
-                                    | _PAGE_GUARDED | _PAGE_NO_CACHE);
+                vma_prot = pgprot_noncached(vma_prot);
+
         return vma_prot;
 }
 EXPORT_SYMBOL(phys_mem_access_prot);
@@ -488,7 +488,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
                  * we invalidate the TLB here, thus avoiding dcbst
                  * misbehaviour.
                  */
-                _tlbie(address, 0 /* 8xx doesn't care about PID */);
+                _tlbil_va(address, 0 /* 8xx doesn't care about PID */);
 #endif
                 /* The _PAGE_USER test should really be _PAGE_EXEC, but
                  * older glibc versions execute some code from no-exec
diff --git a/arch/powerpc/mm/mmu_context_32.c b/arch/powerpc/mm/mmu_context_32.c
deleted file mode 100644
index cc32ba41d900..000000000000
--- a/arch/powerpc/mm/mmu_context_32.c
+++ /dev/null
@@ -1,84 +0,0 @@
-/*
- * This file contains the routines for handling the MMU on those
- * PowerPC implementations where the MMU substantially follows the
- * architecture specification.  This includes the 6xx, 7xx, 7xxx,
- * 8260, and POWER3 implementations but excludes the 8xx and 4xx.
- *  -- paulus
- *
- *  Derived from arch/ppc/mm/init.c:
- *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
- *
- *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
- *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
- *    Copyright (C) 1996 Paul Mackerras
- *
- *  Derived from "arch/i386/mm/init.c"
- *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- *
- *  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/mm.h>
-#include <linux/init.h>
-
-#include <asm/mmu_context.h>
-#include <asm/tlbflush.h>
-
-unsigned long next_mmu_context;
-unsigned long context_map[LAST_CONTEXT / BITS_PER_LONG + 1];
-#ifdef FEW_CONTEXTS
-atomic_t nr_free_contexts;
-struct mm_struct *context_mm[LAST_CONTEXT+1];
-void steal_context(void);
-#endif /* FEW_CONTEXTS */
-
-/*
- * Initialize the context management stuff.
- */
-void __init
-mmu_context_init(void)
-{
-        /*
-         * Some processors have too few contexts to reserve one for
-         * init_mm, and require using context 0 for a normal task.
-         * Other processors reserve the use of context zero for the kernel.
-         * This code assumes FIRST_CONTEXT < 32.
-         */
-        context_map[0] = (1 << FIRST_CONTEXT) - 1;
-        next_mmu_context = FIRST_CONTEXT;
-#ifdef FEW_CONTEXTS
-        atomic_set(&nr_free_contexts, LAST_CONTEXT - FIRST_CONTEXT + 1);
-#endif /* FEW_CONTEXTS */
-}
-
-#ifdef FEW_CONTEXTS
-/*
- * Steal a context from a task that has one at the moment.
- * This is only used on 8xx and 4xx and we presently assume that
- * they don't do SMP.  If they do then this will have to check
- * whether the MM we steal is in use.
- * We also assume that this is only used on systems that don't
- * use an MMU hash table - this is true for 8xx and 4xx.
- * This isn't an LRU system, it just frees up each context in
- * turn (sort-of pseudo-random replacement :).  This would be the
- * place to implement an LRU scheme if anyone was motivated to do it.
- *  -- paulus
- */
-void
-steal_context(void)
-{
-        struct mm_struct *mm;
-
-        /* free up context `next_mmu_context' */
-        /* if we shouldn't free context 0, don't... */
-        if (next_mmu_context < FIRST_CONTEXT)
-                next_mmu_context = FIRST_CONTEXT;
-        mm = context_mm[next_mmu_context];
-        flush_tlb_mm(mm);
-        destroy_context(mm);
-}
-#endif /* FEW_CONTEXTS */
diff --git a/arch/powerpc/mm/mmu_context_hash32.c b/arch/powerpc/mm/mmu_context_hash32.c
new file mode 100644
index 000000000000..0dfba2bf7f31
--- /dev/null
+++ b/arch/powerpc/mm/mmu_context_hash32.c
@@ -0,0 +1,103 @@
+/*
+ * This file contains the routines for handling the MMU on those
+ * PowerPC implementations where the MMU substantially follows the
+ * architecture specification.  This includes the 6xx, 7xx, 7xxx,
+ * 8260, and POWER3 implementations but excludes the 8xx and 4xx.
+ *  -- paulus
+ *
+ *  Derived from arch/ppc/mm/init.c:
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ *    Copyright (C) 1996 Paul Mackerras
+ *
+ *  Derived from "arch/i386/mm/init.c"
+ *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *
+ *  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/mm.h>
+#include <linux/init.h>
+
+#include <asm/mmu_context.h>
+#include <asm/tlbflush.h>
+
+/*
+ * On 32-bit PowerPC 6xx/7xx/7xxx CPUs, we use a set of 16 VSIDs
+ * (virtual segment identifiers) for each context.  Although the
+ * hardware supports 24-bit VSIDs, and thus >1 million contexts,
+ * we only use 32,768 of them.  That is ample, since there can be
+ * at most around 30,000 tasks in the system anyway, and it means
+ * that we can use a bitmap to indicate which contexts are in use.
+ * Using a bitmap means that we entirely avoid all of the problems
+ * that we used to have when the context number overflowed,
+ * particularly on SMP systems.
+ *  -- paulus.
+ */
+#define NO_CONTEXT              ((unsigned long) -1)
+#define LAST_CONTEXT            32767
+#define FIRST_CONTEXT           1
+
+/*
+ * This function defines the mapping from contexts to VSIDs (virtual
+ * segment IDs).  We use a skew on both the context and the high 4 bits
+ * of the 32-bit virtual address (the "effective segment ID") in order
+ * to spread out the entries in the MMU hash table.  Note, if this
+ * function is changed then arch/ppc/mm/hashtable.S will have to be
+ * changed to correspond.
+ *
+ *
+ * CTX_TO_VSID(ctx, va) (((ctx) * (897 * 16) + ((va) >> 28) * 0x111) \
+ *                               & 0xffffff)
+ */
+
+static unsigned long next_mmu_context;
+static unsigned long context_map[LAST_CONTEXT / BITS_PER_LONG + 1];
+
+
+/*
+ * Set up the context for a new address space.
+ */
+int init_new_context(struct task_struct *t, struct mm_struct *mm)
+{
+        unsigned long ctx = next_mmu_context;
+
+        while (test_and_set_bit(ctx, context_map)) {
+                ctx = find_next_zero_bit(context_map, LAST_CONTEXT+1, ctx);
+                if (ctx > LAST_CONTEXT)
+                        ctx = 0;
+        }
+        next_mmu_context = (ctx + 1) & LAST_CONTEXT;
+        mm->context.id = ctx;
+
+        return 0;
+}
+
+/*
+ * We're finished using the context for an address space.
+ */
+void destroy_context(struct mm_struct *mm)
+{
+        preempt_disable();
+        if (mm->context.id != NO_CONTEXT) {
+                clear_bit(mm->context.id, context_map);
+                mm->context.id = NO_CONTEXT;
+        }
+        preempt_enable();
+}
+
+/*
+ * Initialize the context management stuff.
+ */
+void __init mmu_context_init(void)
+{
+        /* Reserve context 0 for kernel use */
+        context_map[0] = (1 << FIRST_CONTEXT) - 1;
+        next_mmu_context = FIRST_CONTEXT;
+}
diff --git a/arch/powerpc/mm/mmu_context_64.c b/arch/powerpc/mm/mmu_context_hash64.c
index 1db38ba1f544..dbeb86ac90cd 100644
--- a/arch/powerpc/mm/mmu_context_64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -24,6 +24,14 @@
 static DEFINE_SPINLOCK(mmu_context_lock);
 static DEFINE_IDR(mmu_context_idr);
 
+/*
+ * The proto-VSID space has 2^35 - 1 segments available for user mappings.
+ * Each segment contains 2^28 bytes.  Each context maps 2^44 bytes,
+ * so we can support 2^19-1 contexts (19 == 35 + 28 - 44).
+ */
+#define NO_CONTEXT      0
+#define MAX_CONTEXT     ((1UL << 19) - 1)
+
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
         int index;
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
new file mode 100644
index 000000000000..52a0cfc38b64
--- /dev/null
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -0,0 +1,397 @@
+/*
+ * This file contains the routines for handling the MMU on those
+ * PowerPC implementations where the MMU is not using the hash
+ * table, such as 8xx, 4xx, BookE's etc...
+ *
+ * Copyright 2008 Ben Herrenschmidt <benh@kernel.crashing.org>
+ *                IBM Corp.
+ *
+ *  Derived from previous arch/powerpc/mm/mmu_context.c
+ *  and arch/powerpc/include/asm/mmu_context.h
+ *
+ *  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.
+ *
+ * TODO:
+ *
+ *   - The global context lock will not scale very well
+ *   - The maps should be dynamically allocated to allow for processors
+ *     that support more PID bits at runtime
+ *   - Implement flush_tlb_mm() by making the context stale and picking
+ *     a new one
+ *   - More aggressively clear stale map bits and maybe find some way to
+ *     also clear mm->cpu_vm_mask bits when processes are migrated
+ */
+
+#undef DEBUG
+#define DEBUG_STEAL_ONLY
+#undef DEBUG_MAP_CONSISTENCY
+/*#define DEBUG_CLAMP_LAST_CONTEXT   15 */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/bootmem.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+
+#include <asm/mmu_context.h>
+#include <asm/tlbflush.h>
+
+static unsigned int first_context, last_context;
+static unsigned int next_context, nr_free_contexts;
+static unsigned long *context_map;
+static unsigned long *stale_map[NR_CPUS];
+static struct mm_struct **context_mm;
+static spinlock_t context_lock = SPIN_LOCK_UNLOCKED;
+
+#define CTX_MAP_SIZE    \
+        (sizeof(unsigned long) * (last_context / BITS_PER_LONG + 1))
+
+
+/* Steal a context from a task that has one at the moment.
+ *
+ * This is used when we are running out of available PID numbers
+ * on the processors.
+ *
+ * This isn't an LRU system, it just frees up each context in
+ * turn (sort-of pseudo-random replacement :).  This would be the
+ * place to implement an LRU scheme if anyone was motivated to do it.
+ *  -- paulus
+ *
+ * For context stealing, we use a slightly different approach for
+ * SMP and UP. Basically, the UP one is simpler and doesn't use
+ * the stale map as we can just flush the local CPU
+ *  -- benh
+ */
+#ifdef CONFIG_SMP
+static unsigned int steal_context_smp(unsigned int id)
+{
+        struct mm_struct *mm;
+        unsigned int cpu, max;
+
+ again:
+        max = last_context - first_context;
+
+        /* Attempt to free next_context first and then loop until we manage */
+        while (max--) {
+                /* Pick up the victim mm */
+                mm = context_mm[id];
+
+                /* We have a candidate victim, check if it's active, on SMP
+                 * we cannot steal active contexts
+                 */
+                if (mm->context.active) {
+                        id++;
+                        if (id > last_context)
+                                id = first_context;
+                        continue;
+                }
+                pr_debug("[%d] steal context %d from mm @%p\n",
+                         smp_processor_id(), id, mm);
+
+                /* Mark this mm has having no context anymore */
+                mm->context.id = MMU_NO_CONTEXT;
+
+                /* Mark it stale on all CPUs that used this mm */
+                for_each_cpu_mask_nr(cpu, mm->cpu_vm_mask)
+                        __set_bit(id, stale_map[cpu]);
+                return id;
+        }
+
+        /* This will happen if you have more CPUs than available contexts,
+         * all we can do here is wait a bit and try again
+         */
+        spin_unlock(&context_lock);
+        cpu_relax();
+        spin_lock(&context_lock);
+        goto again;
+}
+#endif  /* CONFIG_SMP */
+
+/* Note that this will also be called on SMP if all other CPUs are
+ * offlined, which means that it may be called for cpu != 0. For
+ * this to work, we somewhat assume that CPUs that are onlined
+ * come up with a fully clean TLB (or are cleaned when offlined)
+ */
+static unsigned int steal_context_up(unsigned int id)
+{
+        struct mm_struct *mm;
+        int cpu = smp_processor_id();
+
+        /* Pick up the victim mm */
+        mm = context_mm[id];
+
+        pr_debug("[%d] steal context %d from mm @%p\n", cpu, id, mm);
+
+        /* Mark this mm has having no context anymore */
+        mm->context.id = MMU_NO_CONTEXT;
+
+        /* Flush the TLB for that context */
+        local_flush_tlb_mm(mm);
+
+        /* XXX This clear should ultimately be part of local_flush_tlb_mm */
+        __clear_bit(id, stale_map[cpu]);
+
+        return id;
+}
+
+#ifdef DEBUG_MAP_CONSISTENCY
+static void context_check_map(void)
+{
+        unsigned int id, nrf, nact;
+
+        nrf = nact = 0;
+        for (id = first_context; id <= last_context; id++) {
+                int used = test_bit(id, context_map);
+                if (!used)
+                        nrf++;
+                if (used != (context_mm[id] != NULL))
+                        pr_err("MMU: Context %d is %s and MM is %p !\n",
+                               id, used ? "used" : "free", context_mm[id]);
+                if (context_mm[id] != NULL)
+                        nact += context_mm[id]->context.active;
+        }
+        if (nrf != nr_free_contexts) {
+                pr_err("MMU: Free context count out of sync ! (%d vs %d)\n",
+                       nr_free_contexts, nrf);
+                nr_free_contexts = nrf;
+        }
+        if (nact > num_online_cpus())
+                pr_err("MMU: More active contexts than CPUs ! (%d vs %d)\n",
+                       nact, num_online_cpus());
+        if (first_context > 0 && !test_bit(0, context_map))
+                pr_err("MMU: Context 0 has been freed !!!\n");
+}
+#else
+static void context_check_map(void) { }
+#endif
+
+void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next)
+{
+        unsigned int id, cpu = smp_processor_id();
+        unsigned long *map;
+
+        /* No lockless fast path .. yet */
+        spin_lock(&context_lock);
+
+#ifndef DEBUG_STEAL_ONLY
+        pr_debug("[%d] activating context for mm @%p, active=%d, id=%d\n",
+                 cpu, next, next->context.active, next->context.id);
+#endif
+
+#ifdef CONFIG_SMP
+        /* Mark us active and the previous one not anymore */
+        next->context.active++;
+        if (prev) {
+#ifndef DEBUG_STEAL_ONLY
+                pr_debug(" old context %p active was: %d\n",
+                         prev, prev->context.active);
+#endif
+                WARN_ON(prev->context.active < 1);
+                prev->context.active--;
+        }
+#endif /* CONFIG_SMP */
+
+        /* If we already have a valid assigned context, skip all that */
+        id = next->context.id;
+        if (likely(id != MMU_NO_CONTEXT))
+                goto ctxt_ok;
+
+        /* We really don't have a context, let's try to acquire one */
+        id = next_context;
+        if (id > last_context)
+                id = first_context;
+        map = context_map;
+
+        /* No more free contexts, let's try to steal one */
+        if (nr_free_contexts == 0) {
+#ifdef CONFIG_SMP
+                if (num_online_cpus() > 1) {
+                        id = steal_context_smp(id);
+                        goto stolen;
+                }
+#endif /* CONFIG_SMP */
+                id = steal_context_up(id);
+                goto stolen;
+        }
+        nr_free_contexts--;
+
+        /* We know there's at least one free context, try to find it */
+        while (__test_and_set_bit(id, map)) {
+                id = find_next_zero_bit(map, last_context+1, id);
+                if (id > last_context)
+                        id = first_context;
+        }
+ stolen:
+        next_context = id + 1;
+        context_mm[id] = next;
+        next->context.id = id;
+
+#ifndef DEBUG_STEAL_ONLY
+        pr_debug("[%d] picked up new id %d, nrf is now %d\n",
+                 cpu, id, nr_free_contexts);
+#endif
+
+        context_check_map();
+ ctxt_ok:
+
+        /* If that context got marked stale on this CPU, then flush the
+         * local TLB for it and unmark it before we use it
+         */
+        if (test_bit(id, stale_map[cpu])) {
+                pr_debug("[%d] flushing stale context %d for mm @%p !\n",
+                         cpu, id, next);
+                local_flush_tlb_mm(next);
+
+                /* XXX This clear should ultimately be part of local_flush_tlb_mm */
+                __clear_bit(id, stale_map[cpu]);
+        }
+
+        /* Flick the MMU and release lock */
+        set_context(id, next->pgd);
+        spin_unlock(&context_lock);
+}
+
+/*
+ * Set up the context for a new address space.
+ */
+int init_new_context(struct task_struct *t, struct mm_struct *mm)
+{
+        mm->context.id = MMU_NO_CONTEXT;
+        mm->context.active = 0;
+
+        return 0;
+}
+
+/*
+ * We're finished using the context for an address space.
+ */
+void destroy_context(struct mm_struct *mm)
+{
+        unsigned int id;
+
+        if (mm->context.id == MMU_NO_CONTEXT)
+                return;
+
+        WARN_ON(mm->context.active != 0);
+
+        spin_lock(&context_lock);
+        id = mm->context.id;
+        if (id != MMU_NO_CONTEXT) {
+                __clear_bit(id, context_map);
+                mm->context.id = MMU_NO_CONTEXT;
+#ifdef DEBUG_MAP_CONSISTENCY
+                mm->context.active = 0;
+                context_mm[id] = NULL;
+#endif
+                nr_free_contexts++;
+        }
+        spin_unlock(&context_lock);
+}
+
+#ifdef CONFIG_SMP
+
+static int __cpuinit mmu_context_cpu_notify(struct notifier_block *self,
+                                            unsigned long action, void *hcpu)
+{
+        unsigned int cpu = (unsigned int)(long)hcpu;
+
+        /* We don't touch CPU 0 map, it's allocated at aboot and kept
+         * around forever
+         */
+        if (cpu == 0)
+                return NOTIFY_OK;
+
+        switch (action) {
+        case CPU_ONLINE:
+        case CPU_ONLINE_FROZEN:
+                pr_debug("MMU: Allocating stale context map for CPU %d\n", cpu);
+                stale_map[cpu] = kzalloc(CTX_MAP_SIZE, GFP_KERNEL);
+                break;
+#ifdef CONFIG_HOTPLUG_CPU
+        case CPU_DEAD:
+        case CPU_DEAD_FROZEN:
+                pr_debug("MMU: Freeing stale context map for CPU %d\n", cpu);
+                kfree(stale_map[cpu]);
+                stale_map[cpu] = NULL;
+                break;
+#endif
+        }
+        return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata mmu_context_cpu_nb = {
+        .notifier_call  = mmu_context_cpu_notify,
+};
+
+#endif /* CONFIG_SMP */
+
+/*
+ * Initialize the context management stuff.
+ */
+void __init mmu_context_init(void)
+{
+        /* Mark init_mm as being active on all possible CPUs since
+         * we'll get called with prev == init_mm the first time
+         * we schedule on a given CPU
+         */
+        init_mm.context.active = NR_CPUS;
+
+        /*
+         *   The MPC8xx has only 16 contexts.  We rotate through them on each
+         * task switch.  A better way would be to keep track of tasks that
+         * own contexts, and implement an LRU usage.  That way very active
+         * tasks don't always have to pay the TLB reload overhead.  The
+         * kernel pages are mapped shared, so the kernel can run on behalf
+         * of any task that makes a kernel entry.  Shared does not mean they
+         * are not protected, just that the ASID comparison is not performed.
+         *      -- Dan
+         *
+         * The IBM4xx has 256 contexts, so we can just rotate through these
+         * as a way of "switching" contexts.  If the TID of the TLB is zero,
+         * the PID/TID comparison is disabled, so we can use a TID of zero
+         * to represent all kernel pages as shared among all contexts.
+         *      -- Dan
+         */
+        if (mmu_has_feature(MMU_FTR_TYPE_8xx)) {
+                first_context = 0;
+                last_context = 15;
+        } else {
+                first_context = 1;
+                last_context = 255;
+        }
+
+#ifdef DEBUG_CLAMP_LAST_CONTEXT
+        last_context = DEBUG_CLAMP_LAST_CONTEXT;
+#endif
+        /*
+         * Allocate the maps used by context management
+         */
+        context_map = alloc_bootmem(CTX_MAP_SIZE);
+        context_mm = alloc_bootmem(sizeof(void *) * (last_context + 1));
+        stale_map[0] = alloc_bootmem(CTX_MAP_SIZE);
+
+#ifdef CONFIG_SMP
+        register_cpu_notifier(&mmu_context_cpu_nb);
+#endif
+
+        printk(KERN_INFO
+               "MMU: Allocated %d bytes of context maps for %d contexts\n",
+               2 * CTX_MAP_SIZE + (sizeof(void *) * (last_context + 1)),
+               last_context - first_context + 1);
+
+        /*
+         * Some processors have too few contexts to reserve one for
+         * init_mm, and require using context 0 for a normal task.
+         * Other processors reserve the use of context zero for the kernel.
+         * This code assumes first_context < 32.
+         */
+        context_map[0] = (1 << first_context) - 1;
+        next_context = first_context;
+        nr_free_contexts = last_context - first_context + 1;
+}
+
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index fab3cfad4099..4314b39b6faf 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -22,10 +22,58 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu.h>
 
+#ifdef CONFIG_PPC_MMU_NOHASH
+
+/*
+ * On 40x and 8xx, we directly inline tlbia and tlbivax
+ */
+#if defined(CONFIG_40x) || defined(CONFIG_8xx)
+static inline void _tlbil_all(void)
+{
+        asm volatile ("sync; tlbia; isync" : : : "memory")
+}
+static inline void _tlbil_pid(unsigned int pid)
+{
+        asm volatile ("sync; tlbia; isync" : : : "memory")
+}
+#else /* CONFIG_40x || CONFIG_8xx */
+extern void _tlbil_all(void);
+extern void _tlbil_pid(unsigned int pid);
+#endif /* !(CONFIG_40x || CONFIG_8xx) */
+
+/*
+ * On 8xx, we directly inline tlbie, on others, it's extern
+ */
+#ifdef CONFIG_8xx
+static inline void _tlbil_va(unsigned long address, unsigned int pid)
+{
+        asm volatile ("tlbie %0; sync" : : "r" (address) : "memory")
+}
+#else /* CONFIG_8xx */
+extern void _tlbil_va(unsigned long address, unsigned int pid);
+#endif /* CONIFG_8xx */
+
+/*
+ * As of today, we don't support tlbivax broadcast on any
+ * implementation. When that becomes the case, this will be
+ * an extern.
+ */
+static inline void _tlbivax_bcast(unsigned long address, unsigned int pid)
+{
+        BUG();
+}
+
+#else /* CONFIG_PPC_MMU_NOHASH */
+
 extern void hash_preload(struct mm_struct *mm, unsigned long ea,
                          unsigned long access, unsigned long trap);
 
 
+extern void _tlbie(unsigned long address);
+extern void _tlbia(void);
+
+#endif /* CONFIG_PPC_MMU_NOHASH */
+
 #ifdef CONFIG_PPC32
 extern void mapin_ram(void);
 extern int map_page(unsigned long va, phys_addr_t pa, int flags);
@@ -58,17 +106,14 @@ extern phys_addr_t lowmem_end_addr;
  * architectures.  -- Dan
  */
 #if defined(CONFIG_8xx)
-#define flush_HPTE(X, va, pg)   _tlbie(va, 0 /* 8xx doesn't care about PID */)
 #define MMU_init_hw()           do { } while(0)
 #define mmu_mapin_ram()         (0UL)
 
 #elif defined(CONFIG_4xx)
-#define flush_HPTE(pid, va, pg) _tlbie(va, pid)
 extern void MMU_init_hw(void);
 extern unsigned long mmu_mapin_ram(void);
 
 #elif defined(CONFIG_FSL_BOOKE)
-#define flush_HPTE(pid, va, pg) _tlbie(va, pid)
 extern void MMU_init_hw(void);
 extern unsigned long mmu_mapin_ram(void);
 extern void adjust_total_lowmem(void);
@@ -77,18 +122,4 @@ extern void adjust_total_lowmem(void);
 /* anything 32-bit except 4xx or 8xx */
 extern void MMU_init_hw(void);
 extern unsigned long mmu_mapin_ram(void);
-
-/* Be careful....this needs to be updated if we ever encounter 603 SMPs,
- * which includes all new 82xx processors.  We need tlbie/tlbsync here
- * in that case (I think). -- Dan.
- */
-static inline void flush_HPTE(unsigned context, unsigned long va,
-                              unsigned long pdval)
-{
-        if ((Hash != 0) &&
-            cpu_has_feature(CPU_FTR_HPTE_TABLE))
-                flush_hash_pages(0, va, pdval, 1);
-        else
-                _tlbie(va);
-}
 #endif
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
new file mode 100644
index 000000000000..6d94116fdea1
--- /dev/null
+++ b/arch/powerpc/mm/pgtable.c
@@ -0,0 +1,117 @@
+/*
+ * This file contains common routines for dealing with free of page tables
+ *
+ *  Derived from arch/powerpc/mm/tlb_64.c:
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ *    Copyright (C) 1996 Paul Mackerras
+ *
+ *  Derived from "arch/i386/mm/init.c"
+ *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *
+ *  Dave Engebretsen <engebret@us.ibm.com>
+ *      Rework for PPC64 port.
+ *
+ *  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/kernel.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+
+static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
+static unsigned long pte_freelist_forced_free;
+
+struct pte_freelist_batch
+{
+        struct rcu_head rcu;
+        unsigned int    index;
+        pgtable_free_t  tables[0];
+};
+
+#define PTE_FREELIST_SIZE \
+        ((PAGE_SIZE - sizeof(struct pte_freelist_batch)) \
+          / sizeof(pgtable_free_t))
+
+static void pte_free_smp_sync(void *arg)
+{
+        /* Do nothing, just ensure we sync with all CPUs */
+}
+
+/* This is only called when we are critically out of memory
+ * (and fail to get a page in pte_free_tlb).
+ */
+static void pgtable_free_now(pgtable_free_t pgf)
+{
+        pte_freelist_forced_free++;
+
+        smp_call_function(pte_free_smp_sync, NULL, 1);
+
+        pgtable_free(pgf);
+}
+
+static void pte_free_rcu_callback(struct rcu_head *head)
+{
+        struct pte_freelist_batch *batch =
+                container_of(head, struct pte_freelist_batch, rcu);
+        unsigned int i;
+
+        for (i = 0; i < batch->index; i++)
+                pgtable_free(batch->tables[i]);
+
+        free_page((unsigned long)batch);
+}
+
+static void pte_free_submit(struct pte_freelist_batch *batch)
+{
+        INIT_RCU_HEAD(&batch->rcu);
+        call_rcu(&batch->rcu, pte_free_rcu_callback);
+}
+
+void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf)
+{
+        /* This is safe since tlb_gather_mmu has disabled preemption */
+        cpumask_t local_cpumask = cpumask_of_cpu(smp_processor_id());
+        struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
+
+        if (atomic_read(&tlb->mm->mm_users) < 2 ||
+            cpus_equal(tlb->mm->cpu_vm_mask, local_cpumask)) {
+                pgtable_free(pgf);
+                return;
+        }
+
+        if (*batchp == NULL) {
+                *batchp = (struct pte_freelist_batch *)__get_free_page(GFP_ATOMIC);
+                if (*batchp == NULL) {
+                        pgtable_free_now(pgf);
+                        return;
+                }
+                (*batchp)->index = 0;
+        }
+        (*batchp)->tables[(*batchp)->index++] = pgf;
+        if ((*batchp)->index == PTE_FREELIST_SIZE) {
+                pte_free_submit(*batchp);
+                *batchp = NULL;
+        }
+}
+
+void pte_free_finish(void)
+{
+        /* This is safe since tlb_gather_mmu has disabled preemption */
+        struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
+
+        if (*batchp == NULL)
+                return;
+        pte_free_submit(*batchp);
+        *batchp = NULL;
+}
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index c31d6d26f0b5..38ff35f2142a 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -48,10 +48,6 @@ EXPORT_SYMBOL(ioremap_bot);	/* aka VMALLOC_END */
 
 extern char etext[], _stext[];
 
-#ifdef CONFIG_SMP
-extern void hash_page_sync(void);
-#endif
-
 #ifdef HAVE_BATS
 extern phys_addr_t v_mapped_by_bats(unsigned long va);
 extern unsigned long p_mapped_by_bats(phys_addr_t pa);
@@ -72,24 +68,29 @@ extern unsigned long p_mapped_by_tlbcam(unsigned long pa);
 #define p_mapped_by_tlbcam(x)   (0UL)
 #endif /* HAVE_TLBCAM */
 
-#ifdef CONFIG_PTE_64BIT
-/* Some processors use an 8kB pgdir because they have 8-byte Linux PTEs. */
-#define PGDIR_ORDER     1
-#else
-#define PGDIR_ORDER     0
-#endif
+#define PGDIR_ORDER     (32 + PGD_T_LOG2 - PGDIR_SHIFT)
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
         pgd_t *ret;
 
-        ret = (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, PGDIR_ORDER);
+        /* pgdir take page or two with 4K pages and a page fraction otherwise */
+#ifndef CONFIG_PPC_4K_PAGES
+        ret = (pgd_t *)kzalloc(1 << PGDIR_ORDER, GFP_KERNEL);
+#else
+        ret = (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO,
+                        PGDIR_ORDER - PAGE_SHIFT);
+#endif
         return ret;
 }
 
 void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-        free_pages((unsigned long)pgd, PGDIR_ORDER);
+#ifndef CONFIG_PPC_4K_PAGES
+        kfree((void *)pgd);
+#else
+        free_pages((unsigned long)pgd, PGDIR_ORDER - PAGE_SHIFT);
+#endif
 }
 
 __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
@@ -125,23 +126,6 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
         return ptepage;
 }
 
-void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-#ifdef CONFIG_SMP
-        hash_page_sync();
-#endif
-        free_page((unsigned long)pte);
-}
-
-void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
-#ifdef CONFIG_SMP
-        hash_page_sync();
-#endif
-        pgtable_page_dtor(ptepage);
-        __free_page(ptepage);
-}
-
 void __iomem *
 ioremap(phys_addr_t addr, unsigned long size)
 {
@@ -194,6 +178,7 @@ __ioremap(phys_addr_t addr, unsigned long size, unsigned long flags)
         if (p < 16*1024*1024)
                 p += _ISA_MEM_BASE;
 
+#ifndef CONFIG_CRASH_DUMP
         /*
          * Don't allow anybody to remap normal RAM that we're using.
          * mem_init() sets high_memory so only do the check after that.
@@ -203,6 +188,7 @@ __ioremap(phys_addr_t addr, unsigned long size, unsigned long flags)
                        (unsigned long long)p, __builtin_return_address(0));
                 return NULL;
         }
+#endif
 
         if (size == 0)
                 return NULL;
@@ -288,7 +274,7 @@ int map_page(unsigned long va, phys_addr_t pa, int flags)
 }
 
 /*
- * Map in a big chunk of physical memory starting at KERNELBASE.
+ * Map in a big chunk of physical memory starting at PAGE_OFFSET.
  */
 void __init mapin_ram(void)
 {
@@ -297,7 +283,7 @@ void __init mapin_ram(void)
         int ktext;
 
         s = mmu_mapin_ram();
-        v = KERNELBASE + s;
+        v = PAGE_OFFSET + s;
         p = memstart_addr + s;
         for (; s < total_lowmem; s += PAGE_SIZE) {
                 ktext = ((char *) v >= _stext && (char *) v < etext);
@@ -363,7 +349,11 @@ static int __change_page_attr(struct page *page, pgprot_t prot)
                 return -EINVAL;
         set_pte_at(&init_mm, address, kpte, mk_pte(page, prot));
         wmb();
-        flush_HPTE(0, address, pmd_val(*kpmd));
+#ifdef CONFIG_PPC_STD_MMU
+        flush_hash_pages(0, address, pmd_val(*kpmd), 1);
+#else
+        flush_tlb_page(NULL, address);
+#endif
         pte_unmap(kpte);
 
         return 0;
@@ -400,7 +390,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
 static int fixmaps;
-unsigned long FIXADDR_TOP = 0xfffff000;
+unsigned long FIXADDR_TOP = (-PAGE_SIZE);
 EXPORT_SYMBOL(FIXADDR_TOP);
 
 void __set_fixmap (enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags)
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index 6aa120813775..45d925360b89 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -95,16 +95,16 @@ unsigned long __init mmu_mapin_ram(void)
                         break;
         }
 
-        setbat(2, KERNELBASE, 0, bl, _PAGE_RAM);
-        done = (unsigned long)bat_addrs[2].limit - KERNELBASE + 1;
+        setbat(2, PAGE_OFFSET, 0, bl, _PAGE_RAM);
+        done = (unsigned long)bat_addrs[2].limit - PAGE_OFFSET + 1;
         if ((done < tot) && !bat_addrs[3].limit) {
                 /* use BAT3 to cover a bit more */
                 tot -= done;
                 for (bl = 128<<10; bl < max_size; bl <<= 1)
                         if (bl * 2 > tot)
                                 break;
-                setbat(3, KERNELBASE+done, done, bl, _PAGE_RAM);
-                done = (unsigned long)bat_addrs[3].limit - KERNELBASE + 1;
+                setbat(3, PAGE_OFFSET+done, done, bl, _PAGE_RAM);
+                done = (unsigned long)bat_addrs[3].limit - PAGE_OFFSET + 1;
         }
 
         return done;
@@ -192,7 +192,7 @@ void __init MMU_init_hw(void)
         extern unsigned int hash_page[];
         extern unsigned int flush_hash_patch_A[], flush_hash_patch_B[];
 
-        if (!cpu_has_feature(CPU_FTR_HPTE_TABLE)) {
+        if (!mmu_has_feature(MMU_FTR_HPTE_TABLE)) {
                 /*
                  * Put a blr (procedure return) instruction at the
                  * start of hash_page, since we can still get DSI
diff --git a/arch/powerpc/mm/tlb_32.c b/arch/powerpc/mm/tlb_hash32.c
index f9a47fee3927..65190587a365 100644
--- a/arch/powerpc/mm/tlb_32.c
+++ b/arch/powerpc/mm/tlb_hash32.c
@@ -137,6 +137,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
         flush_range(&init_mm, start, end);
         FINISH_FLUSH;
 }
+EXPORT_SYMBOL(flush_tlb_kernel_range);
 
 /*
  * Flush all the (user) entries for the address space described by mm.
@@ -160,6 +161,7 @@ void flush_tlb_mm(struct mm_struct *mm)
                 flush_range(mp->vm_mm, mp->vm_start, mp->vm_end);
         FINISH_FLUSH;
 }
+EXPORT_SYMBOL(flush_tlb_mm);
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 {
@@ -176,6 +178,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
                 flush_hash_pages(mm->context.id, vmaddr, pmd_val(*pmd), 1);
         FINISH_FLUSH;
 }
+EXPORT_SYMBOL(flush_tlb_page);
 
 /*
  * For each address in the range, find the pte for the address
@@ -188,3 +191,4 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
         flush_range(vma->vm_mm, start, end);
         FINISH_FLUSH;
 }
+EXPORT_SYMBOL(flush_tlb_range);
diff --git a/arch/powerpc/mm/tlb_64.c b/arch/powerpc/mm/tlb_hash64.c
index be7dd422c0fa..c931bc7d1079 100644
--- a/arch/powerpc/mm/tlb_64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -37,81 +37,6 @@ DEFINE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch);
  * arch/powerpc/include/asm/tlb.h file -- tgall
  */
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
-static unsigned long pte_freelist_forced_free;
-
-struct pte_freelist_batch
-{
-        struct rcu_head rcu;
-        unsigned int    index;
-        pgtable_free_t  tables[0];
-};
-
-#define PTE_FREELIST_SIZE \
-        ((PAGE_SIZE - sizeof(struct pte_freelist_batch)) \
-          / sizeof(pgtable_free_t))
-
-static void pte_free_smp_sync(void *arg)
-{
-        /* Do nothing, just ensure we sync with all CPUs */
-}
-
-/* This is only called when we are critically out of memory
- * (and fail to get a page in pte_free_tlb).
- */
-static void pgtable_free_now(pgtable_free_t pgf)
-{
-        pte_freelist_forced_free++;
-
-        smp_call_function(pte_free_smp_sync, NULL, 1);
-
-        pgtable_free(pgf);
-}
-
-static void pte_free_rcu_callback(struct rcu_head *head)
-{
-        struct pte_freelist_batch *batch =
-                container_of(head, struct pte_freelist_batch, rcu);
-        unsigned int i;
-
-        for (i = 0; i < batch->index; i++)
-                pgtable_free(batch->tables[i]);
-
-        free_page((unsigned long)batch);
-}
-
-static void pte_free_submit(struct pte_freelist_batch *batch)
-{
-        INIT_RCU_HEAD(&batch->rcu);
-        call_rcu(&batch->rcu, pte_free_rcu_callback);
-}
-
-void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf)
-{
-        /* This is safe since tlb_gather_mmu has disabled preemption */
-        cpumask_t local_cpumask = cpumask_of_cpu(smp_processor_id());
-        struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-
-        if (atomic_read(&tlb->mm->mm_users) < 2 ||
-            cpus_equal(tlb->mm->cpu_vm_mask, local_cpumask)) {
-                pgtable_free(pgf);
-                return;
-        }
-
-        if (*batchp == NULL) {
-                *batchp = (struct pte_freelist_batch *)__get_free_page(GFP_ATOMIC);
-                if (*batchp == NULL) {
-                        pgtable_free_now(pgf);
-                        return;
-                }
-                (*batchp)->index = 0;
-        }
-        (*batchp)->tables[(*batchp)->index++] = pgf;
-        if ((*batchp)->index == PTE_FREELIST_SIZE) {
-                pte_free_submit(*batchp);
-                *batchp = NULL;
-        }
-}
 
 /*
  * A linux PTE was changed and the corresponding hash table entry
@@ -229,17 +154,6 @@ void __flush_tlb_pending(struct ppc64_tlb_batch *batch)
         batch->index = 0;
 }
 
-void pte_free_finish(void)
-{
-        /* This is safe since tlb_gather_mmu has disabled preemption */
-        struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-
-        if (*batchp == NULL)
-                return;
-        pte_free_submit(*batchp);
-        *batchp = NULL;
-}
-
 /**
  * __flush_hash_table_range - Flush all HPTEs for a given address range
  *                            from the hash table (and the TLB). But keeps
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
new file mode 100644
index 000000000000..803a64c02b06
--- /dev/null
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -0,0 +1,209 @@
+/*
+ * This file contains the routines for TLB flushing.
+ * On machines where the MMU does not use a hash table to store virtual to
+ * physical translations (ie, SW loaded TLBs or Book3E compilant processors,
+ * this does -not- include 603 however which shares the implementation with
+ * hash based processors)
+ *
+ *  -- BenH
+ *
+ * Copyright 2008 Ben Herrenschmidt <benh@kernel.crashing.org>
+ *                IBM Corp.
+ *
+ *  Derived from arch/ppc/mm/init.c:
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ *    Copyright (C) 1996 Paul Mackerras
+ *
+ *  Derived from "arch/i386/mm/init.c"
+ *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *
+ *  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/kernel.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/preempt.h>
+#include <linux/spinlock.h>
+
+#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+
+#include "mmu_decl.h"
+
+/*
+ * Base TLB flushing operations:
+ *
+ *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ *  - flush_tlb_page(vma, vmaddr) flushes one page
+ *  - flush_tlb_range(vma, start, end) flushes a range of pages
+ *  - flush_tlb_kernel_range(start, end) flushes kernel pages
+ *
+ *  - local_* variants of page and mm only apply to the current
+ *    processor
+ */
+
+/*
+ * These are the base non-SMP variants of page and mm flushing
+ */
+void local_flush_tlb_mm(struct mm_struct *mm)
+{
+        unsigned int pid;
+
+        preempt_disable();
+        pid = mm->context.id;
+        if (pid != MMU_NO_CONTEXT)
+                _tlbil_pid(pid);
+        preempt_enable();
+}
+EXPORT_SYMBOL(local_flush_tlb_mm);
+
+void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+{
+        unsigned int pid;
+
+        preempt_disable();
+        pid = vma ? vma->vm_mm->context.id : 0;
+        if (pid != MMU_NO_CONTEXT)
+                _tlbil_va(vmaddr, pid);
+        preempt_enable();
+}
+EXPORT_SYMBOL(local_flush_tlb_page);
+
+
+/*
+ * And here are the SMP non-local implementations
+ */
+#ifdef CONFIG_SMP
+
+static DEFINE_SPINLOCK(tlbivax_lock);
+
+struct tlb_flush_param {
+        unsigned long addr;
+        unsigned int pid;
+};
+
+static void do_flush_tlb_mm_ipi(void *param)
+{
+        struct tlb_flush_param *p = param;
+
+        _tlbil_pid(p ? p->pid : 0);
+}
+
+static void do_flush_tlb_page_ipi(void *param)
+{
+        struct tlb_flush_param *p = param;
+
+        _tlbil_va(p->addr, p->pid);
+}
+
+
+/* Note on invalidations and PID:
+ *
+ * We snapshot the PID with preempt disabled. At this point, it can still
+ * change either because:
+ * - our context is being stolen (PID -> NO_CONTEXT) on another CPU
+ * - we are invaliating some target that isn't currently running here
+ *   and is concurrently acquiring a new PID on another CPU
+ * - some other CPU is re-acquiring a lost PID for this mm
+ * etc...
+ *
+ * However, this shouldn't be a problem as we only guarantee
+ * invalidation of TLB entries present prior to this call, so we
+ * don't care about the PID changing, and invalidating a stale PID
+ * is generally harmless.
+ */
+
+void flush_tlb_mm(struct mm_struct *mm)
+{
+        cpumask_t cpu_mask;
+        unsigned int pid;
+
+        preempt_disable();
+        pid = mm->context.id;
+        if (unlikely(pid == MMU_NO_CONTEXT))
+                goto no_context;
+        cpu_mask = mm->cpu_vm_mask;
+        cpu_clear(smp_processor_id(), cpu_mask);
+        if (!cpus_empty(cpu_mask)) {
+                struct tlb_flush_param p = { .pid = pid };
+                smp_call_function_mask(cpu_mask, do_flush_tlb_mm_ipi, &p, 1);
+        }
+        _tlbil_pid(pid);
+ no_context:
+        preempt_enable();
+}
+EXPORT_SYMBOL(flush_tlb_mm);
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+{
+        cpumask_t cpu_mask;
+        unsigned int pid;
+
+        preempt_disable();
+        pid = vma ? vma->vm_mm->context.id : 0;
+        if (unlikely(pid == MMU_NO_CONTEXT))
+                goto bail;
+        cpu_mask = vma->vm_mm->cpu_vm_mask;
+        cpu_clear(smp_processor_id(), cpu_mask);
+        if (!cpus_empty(cpu_mask)) {
+                /* If broadcast tlbivax is supported, use it */
+                if (mmu_has_feature(MMU_FTR_USE_TLBIVAX_BCAST)) {
+                        int lock = mmu_has_feature(MMU_FTR_LOCK_BCAST_INVAL);
+                        if (lock)
+                                spin_lock(&tlbivax_lock);
+                        _tlbivax_bcast(vmaddr, pid);
+                        if (lock)
+                                spin_unlock(&tlbivax_lock);
+                        goto bail;
+                } else {
+                        struct tlb_flush_param p = { .pid = pid, .addr = vmaddr };
+                        smp_call_function_mask(cpu_mask,
+                                               do_flush_tlb_page_ipi, &p, 1);
+                }
+        }
+        _tlbil_va(vmaddr, pid);
+ bail:
+        preempt_enable();
+}
+EXPORT_SYMBOL(flush_tlb_page);
+
+#endif /* CONFIG_SMP */
+
+/*
+ * Flush kernel TLB entries in the given range
+ */
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+#ifdef CONFIG_SMP
+        preempt_disable();
+        smp_call_function(do_flush_tlb_mm_ipi, NULL, 1);
+        _tlbil_pid(0);
+        preempt_enable();
+#endif
+        _tlbil_pid(0);
+}
+EXPORT_SYMBOL(flush_tlb_kernel_range);
+
+/*
+ * Currently, for range flushing, we just do a full mm flush. This should
+ * be optimized based on a threshold on the size of the range, since
+ * some implementation can stack multiple tlbivax before a tlbsync but
+ * for now, we keep it that way
+ */
+void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+                     unsigned long end)
+
+{
+        flush_tlb_mm(vma->vm_mm);
+}
+EXPORT_SYMBOL(flush_tlb_range);
diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S
new file mode 100644
index 000000000000..f900a39e6ec4
--- /dev/null
+++ b/arch/powerpc/mm/tlb_nohash_low.S
@@ -0,0 +1,166 @@
+/*
+ * This file contains low-level functions for performing various
+ * types of TLB invalidations on various processors with no hash
+ * table.
+ *
+ * This file implements the following functions for all no-hash
+ * processors. Some aren't implemented for some variants. Some
+ * are inline in tlbflush.h
+ *
+ *      - tlbil_va
+ *      - tlbil_pid
+ *      - tlbil_all
+ *      - tlbivax_bcast (not yet)
+ *
+ * Code mostly moved over from misc_32.S
+ *
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Partially rewritten by Cort Dougan (cort@cs.nmt.edu)
+ * Paul Mackerras, Kumar Gala and Benjamin Herrenschmidt.
+ *
+ * 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 <asm/reg.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/mmu.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/processor.h>
+
+#if defined(CONFIG_40x)
+
+/*
+ * 40x implementation needs only tlbil_va
+ */
+_GLOBAL(_tlbil_va)
+        /* We run the search with interrupts disabled because we have to change
+         * the PID and I don't want to preempt when that happens.
+         */
+        mfmsr   r5
+        mfspr   r6,SPRN_PID
+        wrteei  0
+        mtspr   SPRN_PID,r4
+        tlbsx.  r3, 0, r3
+        mtspr   SPRN_PID,r6
+        wrtee   r5
+        bne     1f
+        sync
+        /* There are only 64 TLB entries, so r3 < 64, which means bit 25 is
+         * clear. Since 25 is the V bit in the TLB_TAG, loading this value
+         * will invalidate the TLB entry. */
+        tlbwe   r3, r3, TLB_TAG
+        isync
+1:      blr
+
+#elif defined(CONFIG_8xx)
+
+/*
+ * Nothing to do for 8xx, everything is inline
+ */
+
+#elif defined(CONFIG_44x)
+
+/*
+ * 440 implementation uses tlbsx/we for tlbil_va and a full sweep
+ * of the TLB for everything else.
+ */
+_GLOBAL(_tlbil_va)
+        mfspr   r5,SPRN_MMUCR
+        rlwimi  r5,r4,0,24,31                   /* Set TID */
+
+        /* We have to run the search with interrupts disabled, otherwise
+         * an interrupt which causes a TLB miss can clobber the MMUCR
+         * between the mtspr and the tlbsx.
+         *
+         * Critical and Machine Check interrupts take care of saving
+         * and restoring MMUCR, so only normal interrupts have to be
+         * taken care of.
+         */
+        mfmsr   r4
+        wrteei  0
+        mtspr   SPRN_MMUCR,r5
+        tlbsx.  r3, 0, r3
+        wrtee   r4
+        bne     1f
+        sync
+        /* There are only 64 TLB entries, so r3 < 64,
+         * which means bit 22, is clear.  Since 22 is
+         * the V bit in the TLB_PAGEID, loading this
+         * value will invalidate the TLB entry.
+         */
+        tlbwe   r3, r3, PPC44x_TLB_PAGEID
+        isync
+1:      blr
+
+_GLOBAL(_tlbil_all)
+_GLOBAL(_tlbil_pid)
+        li      r3,0
+        sync
+
+        /* Load high watermark */
+        lis     r4,tlb_44x_hwater@ha
+        lwz     r5,tlb_44x_hwater@l(r4)
+
+1:      tlbwe   r3,r3,PPC44x_TLB_PAGEID
+        addi    r3,r3,1
+        cmpw    0,r3,r5
+        ble     1b
+
+        isync
+        blr
+
+#elif defined(CONFIG_FSL_BOOKE)
+/*
+ * FSL BookE implementations. Currently _pid and _all are the
+ * same. This will change when tlbilx is actually supported and
+ * performs invalidate-by-PID. This change will be driven by
+ * mmu_features conditional
+ */
+
+/*
+ * Flush MMU TLB on the local processor
+ */
+_GLOBAL(_tlbil_pid)
+_GLOBAL(_tlbil_all)
+#define MMUCSR0_TLBFI   (MMUCSR0_TLB0FI | MMUCSR0_TLB1FI | \
+                         MMUCSR0_TLB2FI | MMUCSR0_TLB3FI)
+        li      r3,(MMUCSR0_TLBFI)@l
+        mtspr   SPRN_MMUCSR0, r3
+1:
+        mfspr   r3,SPRN_MMUCSR0
+        andi.   r3,r3,MMUCSR0_TLBFI@l
+        bne     1b
+        msync
+        isync
+        blr
+
+/*
+ * Flush MMU TLB for a particular address, but only on the local processor
+ * (no broadcast)
+ */
+_GLOBAL(_tlbil_va)
+        mfmsr   r10
+        wrteei  0
+        slwi    r4,r4,16
+        mtspr   SPRN_MAS6,r4            /* assume AS=0 for now */
+        tlbsx   0,r3
+        mfspr   r4,SPRN_MAS1            /* check valid */
+        andis.  r3,r4,MAS1_VALID@h
+        beq     1f
+        rlwinm  r4,r4,0,1,31
+        mtspr   SPRN_MAS1,r4
+        tlbwe
+        msync
+        isync
+1:      wrtee   r10
+        blr
+#elif
+#error Unsupported processor type !
+#endif
diff --git a/arch/powerpc/platforms/40x/ep405.c b/arch/powerpc/platforms/40x/ep405.c
index ae2e7f67c18e..4058fd1e7fc7 100644
--- a/arch/powerpc/platforms/40x/ep405.c
+++ b/arch/powerpc/platforms/40x/ep405.c
@@ -100,7 +100,7 @@ static void __init ep405_setup_arch(void)
         /* Find & init the BCSR CPLD */
         ep405_init_bcsr();
 
-        ppc_pci_flags = PPC_PCI_REASSIGN_ALL_RSRC;
+        ppc_pci_set_flags(PPC_PCI_REASSIGN_ALL_RSRC);
 }
 
 static int __init ep405_probe(void)
diff --git a/arch/powerpc/platforms/40x/kilauea.c b/arch/powerpc/platforms/40x/kilauea.c
index 1dd24ffc0dc1..fd7d934dac8b 100644
--- a/arch/powerpc/platforms/40x/kilauea.c
+++ b/arch/powerpc/platforms/40x/kilauea.c
@@ -44,7 +44,7 @@ static int __init kilauea_probe(void)
         if (!of_flat_dt_is_compatible(root, "amcc,kilauea"))
                 return 0;
 
-        ppc_pci_flags = PPC_PCI_REASSIGN_ALL_RSRC;
+        ppc_pci_set_flags(PPC_PCI_REASSIGN_ALL_RSRC);
 
         return 1;
 }
diff --git a/arch/powerpc/platforms/40x/ppc40x_simple.c b/arch/powerpc/platforms/40x/ppc40x_simple.c
index 4498a86b46c3..f40ac9b8f99f 100644
--- a/arch/powerpc/platforms/40x/ppc40x_simple.c
+++ b/arch/powerpc/platforms/40x/ppc40x_simple.c
@@ -61,7 +61,7 @@ static int __init ppc40x_probe(void)
 
         for (i = 0; i < ARRAY_SIZE(board); i++) {
                 if (of_flat_dt_is_compatible(root, board[i])) {
-                        ppc_pci_flags = PPC_PCI_REASSIGN_ALL_RSRC;
+                        ppc_pci_set_flags(PPC_PCI_REASSIGN_ALL_RSRC);
                         return 1;
                 }
         }
diff --git a/arch/powerpc/platforms/44x/ebony.c b/arch/powerpc/platforms/44x/ebony.c
index a0e8fe4662f6..88b9117fa691 100644
--- a/arch/powerpc/platforms/44x/ebony.c
+++ b/arch/powerpc/platforms/44x/ebony.c
@@ -54,7 +54,7 @@ static int __init ebony_probe(void)
         if (!of_flat_dt_is_compatible(root, "ibm,ebony"))
                 return 0;
 
-        ppc_pci_flags = PPC_PCI_REASSIGN_ALL_RSRC;
+        ppc_pci_set_flags(PPC_PCI_REASSIGN_ALL_RSRC);
 
         return 1;
 }
diff --git a/arch/powerpc/platforms/44x/ppc44x_simple.c b/arch/powerpc/platforms/44x/ppc44x_simple.c
index 29671262801f..76fdc51dac8b 100644
--- a/arch/powerpc/platforms/44x/ppc44x_simple.c
+++ b/arch/powerpc/platforms/44x/ppc44x_simple.c
@@ -69,7 +69,7 @@ static int __init ppc44x_probe(void)
 
         for (i = 0; i < ARRAY_SIZE(board); i++) {
                 if (of_flat_dt_is_compatible(root, board[i])) {
-                        ppc_pci_flags = PPC_PCI_REASSIGN_ALL_RSRC;
+                        ppc_pci_set_flags(PPC_PCI_REASSIGN_ALL_RSRC);
                         return 1;
                 }
         }
diff --git a/arch/powerpc/platforms/44x/sam440ep.c b/arch/powerpc/platforms/44x/sam440ep.c
index 47f10e647735..a78e8eb6da41 100644
--- a/arch/powerpc/platforms/44x/sam440ep.c
+++ b/arch/powerpc/platforms/44x/sam440ep.c
@@ -51,7 +51,7 @@ static int __init sam440ep_probe(void)
         if (!of_flat_dt_is_compatible(root, "acube,sam440ep"))
                 return 0;
 
-        ppc_pci_flags = PPC_PCI_REASSIGN_ALL_RSRC;
+        ppc_pci_set_flags(PPC_PCI_REASSIGN_ALL_RSRC);
 
         return 1;
 }
diff --git a/arch/powerpc/platforms/52xx/lite5200_pm.c b/arch/powerpc/platforms/52xx/lite5200_pm.c
index fe92e65103ed..b5c753db125e 100644
--- a/arch/powerpc/platforms/52xx/lite5200_pm.c
+++ b/arch/powerpc/platforms/52xx/lite5200_pm.c
@@ -3,7 +3,6 @@
 #include <asm/io.h>
 #include <asm/time.h>
 #include <asm/mpc52xx.h>
-#include "mpc52xx_pic.h"
 
 /* defined in lite5200_sleep.S and only used here */
 extern void lite5200_low_power(void __iomem *sram, void __iomem *mbar);
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pci.c b/arch/powerpc/platforms/52xx/mpc52xx_pci.c
index b49a18527661..c3f2c21024e3 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pci.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pci.c
@@ -375,7 +375,7 @@ mpc52xx_add_bridge(struct device_node *node)
 
         pr_debug("Adding MPC52xx PCI host bridge %s\n", node->full_name);
 
-        ppc_pci_flags |= PPC_PCI_REASSIGN_ALL_BUS;
+        ppc_pci_add_flags(PPC_PCI_REASSIGN_ALL_BUS);
 
         if (of_address_to_resource(node, 0, &rsrc) != 0) {
                 printk(KERN_ERR "Can't get %s resources\n", node->full_name);
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
index 8479394e9ab4..72865e8e4b51 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -2,20 +2,100 @@
  *
  * Programmable Interrupt Controller functions for the Freescale MPC52xx.
  *
+ * Copyright (C) 2008 Secret Lab Technologies Ltd.
  * Copyright (C) 2006 bplan GmbH
+ * Copyright (C) 2004 Sylvain Munaut <tnt@246tNt.com>
+ * Copyright (C) 2003 Montavista Software, Inc
  *
  * Based on the code from the 2.4 kernel by
  * Dale Farnsworth <dfarnsworth@mvista.com> and Kent Borg.
  *
- * Copyright (C) 2004 Sylvain Munaut <tnt@246tNt.com>
- * Copyright (C) 2003 Montavista Software, Inc
- *
  * This file is licensed under the terms of the GNU General Public License
  * version 2. This program is licensed "as is" without any warranty of any
  * kind, whether express or implied.
  *
  */
 
+/*
+ * This is the device driver for the MPC5200 interrupt controller.
+ *
+ * hardware overview
+ * -----------------
+ * The MPC5200 interrupt controller groups the all interrupt sources into
+ * three groups called 'critical', 'main', and 'peripheral'.  The critical
+ * group has 3 irqs, External IRQ0, slice timer 0 irq, and wake from deep
+ * sleep.  Main group include the other 3 external IRQs, slice timer 1, RTC,
+ * gpios, and the general purpose timers.  Peripheral group contains the
+ * remaining irq sources from all of the on-chip peripherals (PSCs, Ethernet,
+ * USB, DMA, etc).
+ *
+ * virqs
+ * -----
+ * The Linux IRQ subsystem requires that each irq source be assigned a
+ * system wide unique IRQ number starting at 1 (0 means no irq).  Since
+ * systems can have multiple interrupt controllers, the virtual IRQ (virq)
+ * infrastructure lets each interrupt controller to define a local set
+ * of IRQ numbers and the virq infrastructure maps those numbers into
+ * a unique range of the global IRQ# space.
+ *
+ * To define a range of virq numbers for this controller, this driver first
+ * assigns a number to each of the irq groups (called the level 1 or L1
+ * value).  Within each group individual irq sources are also assigned a
+ * number, as defined by the MPC5200 user guide, and refers to it as the
+ * level 2 or L2 value.  The virq number is determined by shifting up the
+ * L1 value by MPC52xx_IRQ_L1_OFFSET and ORing it with the L2 value.
+ *
+ * For example, the TMR0 interrupt is irq 9 in the main group.  The
+ * virq for TMR0 is calculated by ((1 << MPC52xx_IRQ_L1_OFFSET) | 9).
+ *
+ * The observant reader will also notice that this driver defines a 4th
+ * interrupt group called 'bestcomm'.  The bestcomm group isn't physically
+ * part of the MPC5200 interrupt controller, but it is used here to assign
+ * a separate virq number for each bestcomm task (since any of the 16
+ * bestcomm tasks can cause the bestcomm interrupt to be raised).  When a
+ * bestcomm interrupt occurs (peripheral group, irq 0) this driver determines
+ * which task needs servicing and returns the irq number for that task.  This
+ * allows drivers which use bestcomm to define their own interrupt handlers.
+ *
+ * irq_chip structures
+ * -------------------
+ * For actually manipulating IRQs (masking, enabling, clearing, etc) this
+ * driver defines four separate 'irq_chip' structures, one for the main
+ * group, one for the peripherals group, one for the bestcomm group and one
+ * for external interrupts.  The irq_chip structures provide the hooks needed
+ * to manipulate each IRQ source, and since each group is has a separate set
+ * of registers for controlling the irq, it makes sense to divide up the
+ * hooks along those lines.
+ *
+ * You'll notice that there is not an irq_chip for the critical group and
+ * you'll also notice that there is an irq_chip defined for external
+ * interrupts even though there is no external interrupt group.  The reason
+ * for this is that the four external interrupts are all managed with the same
+ * register even though one of the external IRQs is in the critical group and
+ * the other three are in the main group.  For this reason it makes sense for
+ * the 4 external irqs to be managed using a separate set of hooks.  The
+ * reason there is no crit irq_chip is that of the 3 irqs in the critical
+ * group, only external interrupt is actually support at this time by this
+ * driver and since external interrupt is the only one used, it can just
+ * be directed to make use of the external irq irq_chip.
+ *
+ * device tree bindings
+ * --------------------
+ * The device tree bindings for this controller reflect the two level
+ * organization of irqs in the device.  #interrupt-cells = <3> where the
+ * first cell is the group number [0..3], the second cell is the irq
+ * number in the group, and the third cell is the sense type (level/edge).
+ * For reference, the following is a list of the interrupt property values
+ * associated with external interrupt sources on the MPC5200 (just because
+ * it is non-obvious to determine what the interrupts property should be
+ * when reading the mpc5200 manual and it is a frequently asked question).
+ *
+ * External interrupts:
+ * <0 0 n>      external irq0, n is sense       (n=0: level high,
+ * <1 1 n>      external irq1, n is sense        n=1: edge rising,
+ * <1 2 n>      external irq2, n is sense        n=2: edge falling,
+ * <1 3 n>      external irq3, n is sense        n=3: level low)
+ */
 #undef DEBUG
 
 #include <linux/interrupt.h>
@@ -24,11 +104,19 @@
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/mpc52xx.h>
-#include "mpc52xx_pic.h"
 
-/*
- *
-*/
+/* HW IRQ mapping */
+#define MPC52xx_IRQ_L1_CRIT     (0)
+#define MPC52xx_IRQ_L1_MAIN     (1)
+#define MPC52xx_IRQ_L1_PERP     (2)
+#define MPC52xx_IRQ_L1_SDMA     (3)
+
+#define MPC52xx_IRQ_L1_OFFSET   (6)
+#define MPC52xx_IRQ_L1_MASK     (0x00c0)
+#define MPC52xx_IRQ_L2_MASK     (0x003f)
+
+#define MPC52xx_IRQ_HIGHTESTHWIRQ (0xd0)
+
 
 /* MPC5200 device tree match tables */
 static struct of_device_id mpc52xx_pic_ids[] __initdata = {
@@ -53,10 +141,7 @@ static unsigned char mpc52xx_map_senses[4] = {
         IRQ_TYPE_LEVEL_LOW,
 };
 
-/*
- *
-*/
-
+/* Utility functions */
 static inline void io_be_setbit(u32 __iomem *addr, int bitno)
 {
         out_be32(addr, in_be32(addr) | (1 << bitno));
@@ -69,15 +154,14 @@ static inline void io_be_clrbit(u32 __iomem *addr, int bitno)
 
 /*
  * IRQ[0-3] interrupt irq_chip
-*/
-
+ */
 static void mpc52xx_extirq_mask(unsigned int virq)
 {
         int irq;
         int l2irq;
 
         irq = irq_map[virq].hwirq;
-        l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+        l2irq = irq & MPC52xx_IRQ_L2_MASK;
 
         pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
 
@@ -90,7 +174,7 @@ static void mpc52xx_extirq_unmask(unsigned int virq)
         int l2irq;
 
         irq = irq_map[virq].hwirq;
-        l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+        l2irq = irq & MPC52xx_IRQ_L2_MASK;
 
         pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
 
@@ -103,7 +187,7 @@ static void mpc52xx_extirq_ack(unsigned int virq)
         int l2irq;
 
         irq = irq_map[virq].hwirq;
-        l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+        l2irq = irq & MPC52xx_IRQ_L2_MASK;
 
         pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
 
@@ -117,7 +201,7 @@ static int mpc52xx_extirq_set_type(unsigned int virq, unsigned int flow_type)
         int l2irq;
 
         irq = irq_map[virq].hwirq;
-        l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+        l2irq = irq & MPC52xx_IRQ_L2_MASK;
 
         pr_debug("%s: irq=%x. l2=%d flow_type=%d\n", __func__, irq, l2irq, flow_type);
 
@@ -156,15 +240,14 @@ static struct irq_chip mpc52xx_extirq_irqchip = {
 
 /*
  * Main interrupt irq_chip
-*/
-
+ */
 static void mpc52xx_main_mask(unsigned int virq)
 {
         int irq;
         int l2irq;
 
         irq = irq_map[virq].hwirq;
-        l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+        l2irq = irq & MPC52xx_IRQ_L2_MASK;
 
         pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
 
@@ -177,7 +260,7 @@ static void mpc52xx_main_unmask(unsigned int virq)
         int l2irq;
 
         irq = irq_map[virq].hwirq;
-        l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+        l2irq = irq & MPC52xx_IRQ_L2_MASK;
 
         pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
 
@@ -193,15 +276,14 @@ static struct irq_chip mpc52xx_main_irqchip = {
 
 /*
  * Peripherals interrupt irq_chip
-*/
-
+ */
 static void mpc52xx_periph_mask(unsigned int virq)
 {
         int irq;
         int l2irq;
 
         irq = irq_map[virq].hwirq;
-        l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+        l2irq = irq & MPC52xx_IRQ_L2_MASK;
 
         pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
 
@@ -214,7 +296,7 @@ static void mpc52xx_periph_unmask(unsigned int virq)
         int l2irq;
 
         irq = irq_map[virq].hwirq;
-        l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+        l2irq = irq & MPC52xx_IRQ_L2_MASK;
 
         pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
 
@@ -230,15 +312,14 @@ static struct irq_chip mpc52xx_periph_irqchip = {
 
 /*
  * SDMA interrupt irq_chip
-*/
-
+ */
 static void mpc52xx_sdma_mask(unsigned int virq)
 {
         int irq;
         int l2irq;
 
         irq = irq_map[virq].hwirq;
-        l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+        l2irq = irq & MPC52xx_IRQ_L2_MASK;
 
         pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
 
@@ -251,7 +332,7 @@ static void mpc52xx_sdma_unmask(unsigned int virq)
         int l2irq;
 
         irq = irq_map[virq].hwirq;
-        l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+        l2irq = irq & MPC52xx_IRQ_L2_MASK;
 
         pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
 
@@ -264,7 +345,7 @@ static void mpc52xx_sdma_ack(unsigned int virq)
         int l2irq;
 
         irq = irq_map[virq].hwirq;
-        l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+        l2irq = irq & MPC52xx_IRQ_L2_MASK;
 
         pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
 
@@ -278,13 +359,12 @@ static struct irq_chip mpc52xx_sdma_irqchip = {
         .ack = mpc52xx_sdma_ack,
 };
 
-/*
- * irq_host
-*/
-
+/**
+ * mpc52xx_irqhost_xlate - translate virq# from device tree interrupts property
+ */
 static int mpc52xx_irqhost_xlate(struct irq_host *h, struct device_node *ct,
-                                 u32 * intspec, unsigned int intsize,
-                                 irq_hw_number_t * out_hwirq,
+                                 u32 *intspec, unsigned int intsize,
+                                 irq_hw_number_t *out_hwirq,
                                  unsigned int *out_flags)
 {
         int intrvect_l1;
@@ -299,10 +379,9 @@ static int mpc52xx_irqhost_xlate(struct irq_host *h, struct device_node *ct,
         intrvect_l2 = (int)intspec[1];
         intrvect_type = (int)intspec[2];
 
-        intrvect_linux =
-            (intrvect_l1 << MPC52xx_IRQ_L1_OFFSET) & MPC52xx_IRQ_L1_MASK;
-        intrvect_linux |=
-            (intrvect_l2 << MPC52xx_IRQ_L2_OFFSET) & MPC52xx_IRQ_L2_MASK;
+        intrvect_linux = (intrvect_l1 << MPC52xx_IRQ_L1_OFFSET) &
+                         MPC52xx_IRQ_L1_MASK;
+        intrvect_linux |= intrvect_l2 & MPC52xx_IRQ_L2_MASK;
 
         pr_debug("return %x, l1=%d, l2=%d\n", intrvect_linux, intrvect_l1,
                  intrvect_l2);
@@ -313,11 +392,11 @@ static int mpc52xx_irqhost_xlate(struct irq_host *h, struct device_node *ct,
         return 0;
 }
 
-/*
- * this function retrieves the correct IRQ type out
- * of the MPC regs
- * Only externals IRQs needs this
-*/
+/**
+ * mpc52xx_irqx_gettype - determine the IRQ sense type (level/edge)
+ *
+ * Only external IRQs need this.
+ */
 static int mpc52xx_irqx_gettype(int irq)
 {
         int type;
@@ -329,6 +408,9 @@ static int mpc52xx_irqx_gettype(int irq)
         return mpc52xx_map_senses[type];
 }
 
+/**
+ * mpc52xx_irqhost_map - Hook to map from virq to an irq_chip structure
+ */
 static int mpc52xx_irqhost_map(struct irq_host *h, unsigned int virq,
                                irq_hw_number_t irq)
 {
@@ -339,7 +421,7 @@ static int mpc52xx_irqhost_map(struct irq_host *h, unsigned int virq,
         int type;
 
         l1irq = (irq & MPC52xx_IRQ_L1_MASK) >> MPC52xx_IRQ_L1_OFFSET;
-        l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+        l2irq = irq & MPC52xx_IRQ_L2_MASK;
 
         /*
          * Most of ours IRQs will be level low
@@ -379,8 +461,7 @@ static int mpc52xx_irqhost_map(struct irq_host *h, unsigned int virq,
                 break;
 
         default:
-                pr_debug("%s: Error, unknown L1 IRQ (0x%x)\n", __func__, l1irq);
-                printk(KERN_ERR "Unknow IRQ!\n");
+                pr_err("%s: invalid virq requested (0x%x)\n", __func__, virq);
                 return -EINVAL;
         }
 
@@ -406,10 +487,15 @@ static struct irq_host_ops mpc52xx_irqhost_ops = {
         .map = mpc52xx_irqhost_map,
 };
 
-/*
- * init (public)
-*/
-
+/**
+ * mpc52xx_init_irq - Initialize and register with the virq subsystem
+ *
+ * Hook for setting up IRQs on an mpc5200 system.  A pointer to this function
+ * is to be put into the machine definition structure.
+ *
+ * This function searches the device tree for an MPC5200 interrupt controller,
+ * initializes it, and registers it with the virq subsystem.
+ */
 void __init mpc52xx_init_irq(void)
 {
         u32 intr_ctrl;
@@ -454,7 +540,6 @@ void __init mpc52xx_init_irq(void)
          * As last step, add an irq host to translate the real
          * hw irq information provided by the ofw to linux virq
          */
-
         mpc52xx_irqhost = irq_alloc_host(picnode, IRQ_HOST_MAP_LINEAR,
                                          MPC52xx_IRQ_HIGHTESTHWIRQ,
                                          &mpc52xx_irqhost_ops, -1);
@@ -462,12 +547,38 @@ void __init mpc52xx_init_irq(void)
         if (!mpc52xx_irqhost)
                 panic(__FILE__ ": Cannot allocate the IRQ host\n");
 
-        printk(KERN_INFO "MPC52xx PIC is up and running!\n");
+        irq_set_default_host(mpc52xx_irqhost);
+
+        pr_info("MPC52xx PIC is up and running!\n");
 }
 
-/*
- * get_irq (public)
-*/
+/**
+ * mpc52xx_get_irq - Get pending interrupt number hook function
+ *
+ * Called by the interupt handler to determine what IRQ handler needs to be
+ * executed.
+ *
+ * Status of pending interrupts is determined by reading the encoded status
+ * register.  The encoded status register has three fields; one for each of the
+ * types of interrupts defined by the controller - 'critical', 'main' and
+ * 'peripheral'.  This function reads the status register and returns the IRQ
+ * number associated with the highest priority pending interrupt.  'Critical'
+ * interrupts have the highest priority, followed by 'main' interrupts, and
+ * then 'peripheral'.
+ *
+ * The mpc5200 interrupt controller can be configured to boost the priority
+ * of individual 'peripheral' interrupts.  If this is the case then a special
+ * value will appear in either the crit or main fields indicating a high
+ * or medium priority peripheral irq has occurred.
+ *
+ * This function checks each of the 3 irq request fields and returns the
+ * first pending interrupt that it finds.
+ *
+ * This function also identifies a 4th type of interrupt; 'bestcomm'.  Each
+ * bestcomm DMA task can raise the bestcomm peripheral interrupt.  When this
+ * occurs at task-specific IRQ# is decoded so that each task can have its
+ * own IRQ handler.
+ */
 unsigned int mpc52xx_get_irq(void)
 {
         u32 status;
@@ -478,25 +589,21 @@ unsigned int mpc52xx_get_irq(void)
                 irq = (status >> 8) & 0x3;
                 if (irq == 2)   /* high priority peripheral */
                         goto peripheral;
-                irq |=  (MPC52xx_IRQ_L1_CRIT << MPC52xx_IRQ_L1_OFFSET) &
-                        MPC52xx_IRQ_L1_MASK;
+                irq |= (MPC52xx_IRQ_L1_CRIT << MPC52xx_IRQ_L1_OFFSET);
         } else if (status & 0x00200000) {       /* main */
                 irq = (status >> 16) & 0x1f;
                 if (irq == 4)   /* low priority peripheral */
                         goto peripheral;
-                irq |=  (MPC52xx_IRQ_L1_MAIN << MPC52xx_IRQ_L1_OFFSET) &
-                        MPC52xx_IRQ_L1_MASK;
+                irq |= (MPC52xx_IRQ_L1_MAIN << MPC52xx_IRQ_L1_OFFSET);
         } else if (status & 0x20000000) {       /* peripheral */
               peripheral:
                 irq = (status >> 24) & 0x1f;
                 if (irq == 0) { /* bestcomm */
                         status = in_be32(&sdma->IntPend);
                         irq = ffs(status) - 1;
-                        irq |=  (MPC52xx_IRQ_L1_SDMA << MPC52xx_IRQ_L1_OFFSET) &
-                                MPC52xx_IRQ_L1_MASK;
+                        irq |= (MPC52xx_IRQ_L1_SDMA << MPC52xx_IRQ_L1_OFFSET);
                 } else {
-                        irq |=  (MPC52xx_IRQ_L1_PERP << MPC52xx_IRQ_L1_OFFSET) &
-                                MPC52xx_IRQ_L1_MASK;
+                        irq |= (MPC52xx_IRQ_L1_PERP << MPC52xx_IRQ_L1_OFFSET);
                 }
         }
 
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.h b/arch/powerpc/platforms/52xx/mpc52xx_pic.h
deleted file mode 100644
index 1a26bcdb3049..000000000000
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * Header file for Freescale MPC52xx Interrupt controller
- *
- * Copyright (C) 2004-2005 Sylvain Munaut <tnt@246tNt.com>
- * Copyright (C) 2003 MontaVista, Software, Inc.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-#ifndef __POWERPC_SYSDEV_MPC52xx_PIC_H__
-#define __POWERPC_SYSDEV_MPC52xx_PIC_H__
-
-#include <asm/types.h>
-
-
-/* HW IRQ mapping */
-#define MPC52xx_IRQ_L1_CRIT     (0)
-#define MPC52xx_IRQ_L1_MAIN     (1)
-#define MPC52xx_IRQ_L1_PERP     (2)
-#define MPC52xx_IRQ_L1_SDMA     (3)
-
-#define MPC52xx_IRQ_L1_OFFSET   (6)
-#define MPC52xx_IRQ_L1_MASK     (0x00c0)
-
-#define MPC52xx_IRQ_L2_OFFSET   (0)
-#define MPC52xx_IRQ_L2_MASK     (0x003f)
-
-#define MPC52xx_IRQ_HIGHTESTHWIRQ (0xd0)
-
-
-/* Interrupt controller Register set */
-struct mpc52xx_intr {
-        u32 per_mask;           /* INTR + 0x00 */
-        u32 per_pri1;           /* INTR + 0x04 */
-        u32 per_pri2;           /* INTR + 0x08 */
-        u32 per_pri3;           /* INTR + 0x0c */
-        u32 ctrl;               /* INTR + 0x10 */
-        u32 main_mask;          /* INTR + 0x14 */
-        u32 main_pri1;          /* INTR + 0x18 */
-        u32 main_pri2;          /* INTR + 0x1c */
-        u32 reserved1;          /* INTR + 0x20 */
-        u32 enc_status;         /* INTR + 0x24 */
-        u32 crit_status;        /* INTR + 0x28 */
-        u32 main_status;        /* INTR + 0x2c */
-        u32 per_status;         /* INTR + 0x30 */
-        u32 reserved2;          /* INTR + 0x34 */
-        u32 per_error;          /* INTR + 0x38 */
-};
-
-#endif /* __POWERPC_SYSDEV_MPC52xx_PIC_H__ */
-
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pm.c b/arch/powerpc/platforms/52xx/mpc52xx_pm.c
index c72d3304387f..a55b0b6813ed 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pm.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pm.c
@@ -5,9 +5,6 @@
 #include <asm/cacheflush.h>
 #include <asm/mpc52xx.h>
 
-#include "mpc52xx_pic.h"
-
-
 /* these are defined in mpc52xx_sleep.S, and only used here */
 extern void mpc52xx_deep_sleep(void __iomem *sram, void __iomem *sdram_regs,
                 struct mpc52xx_cdm __iomem *, struct mpc52xx_intr __iomem*);
diff --git a/arch/powerpc/platforms/82xx/pq2.c b/arch/powerpc/platforms/82xx/pq2.c
index 1b75902fad64..9761a59f175f 100644
--- a/arch/powerpc/platforms/82xx/pq2.c
+++ b/arch/powerpc/platforms/82xx/pq2.c
@@ -53,7 +53,7 @@ static void __init pq2_pci_add_bridge(struct device_node *np)
         if (of_address_to_resource(np, 0, &r) || r.end - r.start < 0x10b)
                 goto err;
 
-        ppc_pci_flags |= PPC_PCI_REASSIGN_ALL_BUS;
+        ppc_pci_add_flags(PPC_PCI_REASSIGN_ALL_BUS);
 
         hose = pcibios_alloc_controller(np);
         if (!hose)
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index cb3054e1001d..f0798c09980f 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -1,6 +1,8 @@
 #
 # Makefile for the PowerPC 85xx linux kernel.
 #
+obj-$(CONFIG_SMP) += smp.o
+
 obj-$(CONFIG_MPC8540_ADS) += mpc85xx_ads.o
 obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o
 obj-$(CONFIG_MPC85xx_CDS) += mpc85xx_cds.o
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index 613bf8c2e30d..a8301c8ad537 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -63,6 +63,7 @@ void __init mpc85xx_ds_pic_init(void)
         struct device_node *cascade_node = NULL;
         int cascade_irq;
 #endif
+        unsigned long root = of_get_flat_dt_root();
 
         np = of_find_node_by_type(NULL, "open-pic");
         if (np == NULL) {
@@ -76,11 +77,19 @@ void __init mpc85xx_ds_pic_init(void)
                 return;
         }
 
-        mpic = mpic_alloc(np, r.start,
+        if (of_flat_dt_is_compatible(root, "fsl,MPC8572DS-CAMP")) {
+                mpic = mpic_alloc(np, r.start,
+                        MPIC_PRIMARY |
+                        MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS,
+                        0, 256, " OpenPIC  ");
+        } else {
+                mpic = mpic_alloc(np, r.start,
                           MPIC_PRIMARY | MPIC_WANTS_RESET |
                           MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS |
                           MPIC_SINGLE_DEST_CPU,
                         0, 256, " OpenPIC  ");
+        }
+
         BUG_ON(mpic == NULL);
         of_node_put(np);
 
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index 2494c5155919..658a36fab3ab 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -231,7 +231,7 @@ static void __init mpc85xx_mds_setup_arch(void)
 
 static int __init board_fixups(void)
 {
-        char phy_id[BUS_ID_SIZE];
+        char phy_id[20];
         char *compstrs[2] = {"fsl,gianfar-mdio", "fsl,ucc-mdio"};
         struct device_node *mdio;
         struct resource res;
@@ -241,13 +241,15 @@ static int __init board_fixups(void)
                 mdio = of_find_compatible_node(NULL, NULL, compstrs[i]);
 
                 of_address_to_resource(mdio, 0, &res);
-                snprintf(phy_id, BUS_ID_SIZE, "%x:%02x", res.start, 1);
+                snprintf(phy_id, sizeof(phy_id), "%llx:%02x",
+                        (unsigned long long)res.start, 1);
 
                 phy_register_fixup_for_id(phy_id, mpc8568_fixup_125_clock);
                 phy_register_fixup_for_id(phy_id, mpc8568_mds_phy_fixups);
 
                 /* Register a workaround for errata */
-                snprintf(phy_id, BUS_ID_SIZE, "%x:%02x", res.start, 7);
+                snprintf(phy_id, sizeof(phy_id), "%llx:%02x",
+                        (unsigned long long)res.start, 7);
                 phy_register_fixup_for_id(phy_id, mpc8568_mds_phy_fixups);
 
                 of_node_put(mdio);
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
new file mode 100644
index 000000000000..d652c713f496
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -0,0 +1,104 @@
+/*
+ * Author: Andy Fleming <afleming@freescale.com>
+ *         Kumar Gala <galak@kernel.crashing.org>
+ *
+ * Copyright 2006-2008 Freescale Semiconductor Inc.
+ *
+ * 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/stddef.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+
+#include <asm/machdep.h>
+#include <asm/pgtable.h>
+#include <asm/page.h>
+#include <asm/mpic.h>
+#include <asm/cacheflush.h>
+
+#include <sysdev/fsl_soc.h>
+
+extern volatile unsigned long __secondary_hold_acknowledge;
+extern void __early_start(void);
+
+#define BOOT_ENTRY_ADDR_UPPER   0
+#define BOOT_ENTRY_ADDR_LOWER   1
+#define BOOT_ENTRY_R3_UPPER     2
+#define BOOT_ENTRY_R3_LOWER     3
+#define BOOT_ENTRY_RESV         4
+#define BOOT_ENTRY_PIR          5
+#define BOOT_ENTRY_R6_UPPER     6
+#define BOOT_ENTRY_R6_LOWER     7
+#define NUM_BOOT_ENTRY          8
+#define SIZE_BOOT_ENTRY         (NUM_BOOT_ENTRY * sizeof(u32))
+
+static void __init
+smp_85xx_kick_cpu(int nr)
+{
+        unsigned long flags;
+        const u64 *cpu_rel_addr;
+        __iomem u32 *bptr_vaddr;
+        struct device_node *np;
+        int n = 0;
+
+        WARN_ON (nr < 0 || nr >= NR_CPUS);
+
+        pr_debug("smp_85xx_kick_cpu: kick CPU #%d\n", nr);
+
+        local_irq_save(flags);
+
+        np = of_get_cpu_node(nr, NULL);
+        cpu_rel_addr = of_get_property(np, "cpu-release-addr", NULL);
+
+        if (cpu_rel_addr == NULL) {
+                printk(KERN_ERR "No cpu-release-addr for cpu %d\n", nr);
+                return;
+        }
+
+        /* Map the spin table */
+        bptr_vaddr = ioremap(*cpu_rel_addr, SIZE_BOOT_ENTRY);
+
+        out_be32(bptr_vaddr + BOOT_ENTRY_PIR, nr);
+        out_be32(bptr_vaddr + BOOT_ENTRY_ADDR_LOWER, __pa(__early_start));
+
+        /* Wait a bit for the CPU to ack. */
+        while ((__secondary_hold_acknowledge != nr) && (++n < 1000))
+                mdelay(1);
+
+        iounmap(bptr_vaddr);
+
+        local_irq_restore(flags);
+
+        pr_debug("waited %d msecs for CPU #%d.\n", n, nr);
+}
+
+static void __init
+smp_85xx_setup_cpu(int cpu_nr)
+{
+        mpic_setup_this_cpu();
+
+        /* Clear any pending timer interrupts */
+        mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS);
+
+        /* Enable decrementer interrupt */
+        mtspr(SPRN_TCR, TCR_DIE);
+}
+
+struct smp_ops_t smp_85xx_ops = {
+        .message_pass = smp_mpic_message_pass,
+        .probe = smp_mpic_probe,
+        .kick_cpu = smp_85xx_kick_cpu,
+        .setup_cpu = smp_85xx_setup_cpu,
+};
+
+void __init
+mpc85xx_smp_init(void)
+{
+        smp_ops = &smp_85xx_ops;
+}
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 77dd797a2580..8e5693935975 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -34,6 +34,8 @@ config MPC8610_HPCD
 config GEF_SBC610
         bool "GE Fanuc SBC610"
         select DEFAULT_UIMAGE
+        select GENERIC_GPIO
+        select ARCH_REQUIRE_GPIOLIB
         select HAS_RAPIDIO
         help
           This option enables support for GE Fanuc's SBC610.
diff --git a/arch/powerpc/platforms/86xx/Makefile b/arch/powerpc/platforms/86xx/Makefile
index 4a56ff619afd..31e540c2ebbc 100644
--- a/arch/powerpc/platforms/86xx/Makefile
+++ b/arch/powerpc/platforms/86xx/Makefile
@@ -7,4 +7,5 @@ obj-$(CONFIG_SMP)		+= mpc86xx_smp.o
 obj-$(CONFIG_MPC8641_HPCN)      += mpc86xx_hpcn.o
 obj-$(CONFIG_SBC8641D)          += sbc8641d.o
 obj-$(CONFIG_MPC8610_HPCD)      += mpc8610_hpcd.o
-obj-$(CONFIG_GEF_SBC610)        += gef_sbc610.o gef_pic.o
+gef-gpio-$(CONFIG_GPIOLIB)      += gef_gpio.o
+obj-$(CONFIG_GEF_SBC610)        += gef_sbc610.o gef_pic.o $(gef-gpio-y)
diff --git a/arch/powerpc/platforms/86xx/gef_gpio.c b/arch/powerpc/platforms/86xx/gef_gpio.c
new file mode 100644
index 000000000000..85b2800f4cb7
--- /dev/null
+++ b/arch/powerpc/platforms/86xx/gef_gpio.c
@@ -0,0 +1,143 @@
+/*
+ * Driver for GE Fanuc's FPGA based GPIO pins
+ *
+ * Author: Martyn Welch <martyn.welch@gefanuc.com>
+ *
+ * 2008 (c) GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/* TODO
+ *
+ * Configuration of output modes (totem-pole/open-drain)
+ * Interrupt configuration - interrupts are always generated the FPGA relies on
+ *      the I/O interrupt controllers mask to stop them propergating
+ */
+
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/of_gpio.h>
+#include <linux/gpio.h>
+
+#define GEF_GPIO_DIRECT         0x00
+#define GEF_GPIO_IN             0x04
+#define GEF_GPIO_OUT            0x08
+#define GEF_GPIO_TRIG           0x0C
+#define GEF_GPIO_POLAR_A        0x10
+#define GEF_GPIO_POLAR_B        0x14
+#define GEF_GPIO_INT_STAT       0x18
+#define GEF_GPIO_OVERRUN        0x1C
+#define GEF_GPIO_MODE           0x20
+
+#define NUM_GPIO 19
+
+static void _gef_gpio_set(void __iomem *reg, unsigned int offset, int value)
+{
+        unsigned int data;
+
+        data = ioread32be(reg);
+        /* value: 0=low; 1=high */
+        if (value & 0x1)
+                data = data | (0x1 << offset);
+        else
+                data = data & ~(0x1 << offset);
+
+        iowrite32be(data, reg);
+}
+
+
+static int gef_gpio_dir_in(struct gpio_chip *chip, unsigned offset)
+{
+        unsigned int data;
+        struct of_mm_gpio_chip *mmchip = to_of_mm_gpio_chip(chip);
+
+        data = ioread32be(mmchip->regs + GEF_GPIO_DIRECT);
+        data = data | (0x1 << offset);
+        iowrite32be(data, mmchip->regs + GEF_GPIO_DIRECT);
+
+        return 0;
+}
+
+static int gef_gpio_dir_out(struct gpio_chip *chip, unsigned offset, int value)
+{
+        unsigned int data;
+        struct of_mm_gpio_chip *mmchip = to_of_mm_gpio_chip(chip);
+
+        /* Set direction before switching to input */
+        _gef_gpio_set(mmchip->regs + GEF_GPIO_OUT, offset, value);
+
+        data = ioread32be(mmchip->regs + GEF_GPIO_DIRECT);
+        data = data & ~(0x1 << offset);
+        iowrite32be(data, mmchip->regs + GEF_GPIO_DIRECT);
+
+        return 0;
+}
+
+static int gef_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+        unsigned int data;
+        int state = 0;
+        struct of_mm_gpio_chip *mmchip = to_of_mm_gpio_chip(chip);
+
+        data = ioread32be(mmchip->regs + GEF_GPIO_IN);
+        state = (int)((data >> offset) & 0x1);
+
+        return state;
+}
+
+static void gef_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+        struct of_mm_gpio_chip *mmchip = to_of_mm_gpio_chip(chip);
+
+        _gef_gpio_set(mmchip->regs + GEF_GPIO_OUT, offset, value);
+}
+
+static int __init gef_gpio_init(void)
+{
+        struct device_node *np;
+
+        for_each_compatible_node(np, NULL, "gef,sbc610-gpio") {
+                int retval;
+                struct of_mm_gpio_chip *gef_gpio_chip;
+
+                pr_debug("%s: Initialising GEF GPIO\n", np->full_name);
+
+                /* Allocate chip structure */
+                gef_gpio_chip = kzalloc(sizeof(*gef_gpio_chip), GFP_KERNEL);
+                if (!gef_gpio_chip) {
+                        pr_err("%s: Unable to allocate structure\n",
+                                np->full_name);
+                        continue;
+                }
+
+                /* Setup pointers to chip functions */
+                gef_gpio_chip->of_gc.gpio_cells = 2;
+                gef_gpio_chip->of_gc.gc.ngpio = NUM_GPIO;
+                gef_gpio_chip->of_gc.gc.direction_input = gef_gpio_dir_in;
+                gef_gpio_chip->of_gc.gc.direction_output = gef_gpio_dir_out;
+                gef_gpio_chip->of_gc.gc.get = gef_gpio_get;
+                gef_gpio_chip->of_gc.gc.set = gef_gpio_set;
+
+                /* This function adds a memory mapped GPIO chip */
+                retval = of_mm_gpiochip_add(np, gef_gpio_chip);
+                if (retval) {
+                        kfree(gef_gpio_chip);
+                        pr_err("%s: Unable to add GPIO\n", np->full_name);
+                }
+        }
+
+        return 0;
+};
+arch_initcall(gef_gpio_init);
+
+MODULE_DESCRIPTION("GE Fanuc I/O FPGA GPIO driver");
+MODULE_AUTHOR("Martyn Welch <martyn.welch@gefanuc.com");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 548efa55c8fe..3d0c776f888d 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -195,16 +195,24 @@ config SPE
 
 config PPC_STD_MMU
         bool
-        depends on 6xx || POWER3 || POWER4 || PPC64
+        depends on 6xx || PPC64
         default y
 
 config PPC_STD_MMU_32
         def_bool y
         depends on PPC_STD_MMU && PPC32
 
+config PPC_STD_MMU_64
+        def_bool y
+        depends on PPC_STD_MMU && PPC64
+
+config PPC_MMU_NOHASH
+        def_bool y
+        depends on !PPC_STD_MMU
+
 config PPC_MM_SLICES
         bool
-        default y if HUGETLB_PAGE || PPC_64K_PAGES
+        default y if HUGETLB_PAGE || (PPC_STD_MMU_64 && PPC_64K_PAGES)
         default n
 
 config VIRT_CPU_ACCOUNTING
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index c14d7d8d96c8..5cc3279559a4 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -2,13 +2,18 @@ config PPC_CELL
         bool
         default n
 
-config PPC_CELL_NATIVE
+config PPC_CELL_COMMON
         bool
         select PPC_CELL
         select PPC_DCR_MMIO
-        select PPC_OF_PLATFORM_PCI
         select PPC_INDIRECT_IO
         select PPC_NATIVE
+        select PPC_RTAS
+
+config PPC_CELL_NATIVE
+        bool
+        select PPC_CELL_COMMON
+        select PPC_OF_PLATFORM_PCI
         select MPIC
         select IBM_NEW_EMAC_EMAC4
         select IBM_NEW_EMAC_RGMII
@@ -20,7 +25,6 @@ config PPC_IBM_CELL_BLADE
         bool "IBM Cell Blade"
         depends on PPC_MULTIPLATFORM && PPC64
         select PPC_CELL_NATIVE
-        select PPC_RTAS
         select MMIO_NVRAM
         select PPC_UDBG_16550
         select UDBG_RTAS_CONSOLE
@@ -28,16 +32,17 @@ config PPC_IBM_CELL_BLADE
 config PPC_CELLEB
         bool "Toshiba's Cell Reference Set 'Celleb' Architecture"
         depends on PPC_MULTIPLATFORM && PPC64
-        select PPC_CELL
         select PPC_CELL_NATIVE
-        select PPC_RTAS
-        select PPC_INDIRECT_IO
-        select PPC_OF_PLATFORM_PCI
         select HAS_TXX9_SERIAL
         select PPC_UDBG_BEAT
         select USB_OHCI_BIG_ENDIAN_MMIO
         select USB_EHCI_BIG_ENDIAN_MMIO
 
+config PPC_CELL_QPACE
+        bool "IBM Cell - QPACE"
+        depends on PPC_MULTIPLATFORM && PPC64
+        select PPC_CELL_COMMON
+
 menu "Cell Broadband Engine options"
         depends on PPC_CELL
 
@@ -102,7 +107,7 @@ config PPC_IBM_CELL_POWERBUTTON
 config CBE_THERM
         tristate "CBE thermal support"
         default m
-        depends on CBE_RAS
+        depends on CBE_RAS && SPU_BASE
 
 config CBE_CPUFREQ
         tristate "CBE frequency scaling"
@@ -136,5 +141,5 @@ endmenu
 
 config OPROFILE_CELL
         def_bool y
-        depends on PPC_CELL_NATIVE && (OPROFILE = m || OPROFILE = y)
+        depends on PPC_CELL_NATIVE && (OPROFILE = m || OPROFILE = y) && SPU_BASE
 
diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile
index 7fd830872c43..43eccb270301 100644
--- a/arch/powerpc/platforms/cell/Makefile
+++ b/arch/powerpc/platforms/cell/Makefile
@@ -1,7 +1,7 @@
-obj-$(CONFIG_PPC_CELL_NATIVE)           += interrupt.o iommu.o setup.o \
-                                           cbe_regs.o spider-pic.o \
-                                           pervasive.o pmu.o io-workarounds.o \
-                                           spider-pci.o
+obj-$(CONFIG_PPC_CELL_COMMON)           += cbe_regs.o interrupt.o pervasive.o
+
+obj-$(CONFIG_PPC_CELL_NATIVE)           += iommu.o setup.o spider-pic.o \
+                                           pmu.o io-workarounds.o spider-pci.o
 obj-$(CONFIG_CBE_RAS)                   += ras.o
 
 obj-$(CONFIG_CBE_THERM)                 += cbe_thermal.o
@@ -14,13 +14,12 @@ obj-$(CONFIG_PPC_IBM_CELL_POWERBUTTON)	+= cbe_powerbutton.o
 
 ifeq ($(CONFIG_SMP),y)
 obj-$(CONFIG_PPC_CELL_NATIVE)           += smp.o
+obj-$(CONFIG_PPC_CELL_QPACE)            += smp.o
 endif
 
 # needed only when building loadable spufs.ko
-spu-priv1-$(CONFIG_PPC_CELL_NATIVE)     += spu_priv1_mmio.o
-
-spu-manage-$(CONFIG_PPC_CELLEB)         += spu_manage.o
-spu-manage-$(CONFIG_PPC_CELL_NATIVE)    += spu_manage.o
+spu-priv1-$(CONFIG_PPC_CELL_COMMON)     += spu_priv1_mmio.o
+spu-manage-$(CONFIG_PPC_CELL_COMMON)    += spu_manage.o
 
 obj-$(CONFIG_SPU_BASE)                  += spu_callbacks.o spu_base.o \
                                            spu_notify.o \
@@ -31,6 +30,8 @@ obj-$(CONFIG_SPU_BASE)			+= spu_callbacks.o spu_base.o \
 
 obj-$(CONFIG_PCI_MSI)                   += axon_msi.o
 
+# qpace setup
+obj-$(CONFIG_PPC_CELL_QPACE)            += qpace_setup.o
 
 # celleb stuff
 ifeq ($(CONFIG_PPC_CELLEB),y)
diff --git a/arch/powerpc/platforms/cell/celleb_setup.c b/arch/powerpc/platforms/cell/celleb_setup.c
index b11cb30decb2..07c234f6b2b6 100644
--- a/arch/powerpc/platforms/cell/celleb_setup.c
+++ b/arch/powerpc/platforms/cell/celleb_setup.c
@@ -45,7 +45,6 @@
 #include <asm/mmu.h>
 #include <asm/processor.h>
 #include <asm/io.h>
-#include <asm/kexec.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/cputable.h>
@@ -226,9 +225,6 @@ define_machine(celleb_beat) {
         .pci_setup_phb          = celleb_setup_phb,
 #ifdef CONFIG_KEXEC
         .kexec_cpu_down         = beat_kexec_cpu_down,
-        .machine_kexec          = default_machine_kexec,
-        .machine_kexec_prepare  = default_machine_kexec_prepare,
-        .machine_crash_shutdown = default_machine_crash_shutdown,
 #endif
 };
 
@@ -248,9 +244,4 @@ define_machine(celleb_native) {
         .pci_probe_mode         = celleb_pci_probe_mode,
         .pci_setup_phb          = celleb_setup_phb,
         .init_IRQ               = celleb_init_IRQ_native,
-#ifdef CONFIG_KEXEC
-        .machine_kexec          = default_machine_kexec,
-        .machine_kexec_prepare  = default_machine_kexec_prepare,
-        .machine_crash_shutdown = default_machine_crash_shutdown,
-#endif
 };
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 3168272ab0d7..86db4dd170a0 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -1053,10 +1053,7 @@ static int __init cell_iommu_fixed_mapping_init(void)
         }
 
         /* We must have dma-ranges properties for fixed mapping to work */
-        for (np = NULL; (np = of_find_all_nodes(np));) {
-                if (of_find_property(np, "dma-ranges", NULL))
-                        break;
-        }
+        np = of_find_node_with_property(NULL, "dma-ranges");
         of_node_put(np);
 
         if (!np) {
diff --git a/arch/powerpc/platforms/cell/qpace_setup.c b/arch/powerpc/platforms/cell/qpace_setup.c
new file mode 100644
index 000000000000..be84e6a16b30
--- /dev/null
+++ b/arch/powerpc/platforms/cell/qpace_setup.c
@@ -0,0 +1,152 @@
+/*
+ *  linux/arch/powerpc/platforms/cell/qpace_setup.c
+ *
+ *  Copyright (C) 1995  Linus Torvalds
+ *  Adapted from 'alpha' version by Gary Thomas
+ *  Modified by Cort Dougan (cort@cs.nmt.edu)
+ *  Modified by PPC64 Team, IBM Corp
+ *  Modified by Cell Team, IBM Deutschland Entwicklung GmbH
+ *  Modified by Benjamin Krill <ben@codiert.org>, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/console.h>
+#include <linux/of_platform.h>
+
+#include <asm/mmu.h>
+#include <asm/processor.h>
+#include <asm/io.h>
+#include <asm/kexec.h>
+#include <asm/pgtable.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+#include <asm/dma.h>
+#include <asm/machdep.h>
+#include <asm/time.h>
+#include <asm/cputable.h>
+#include <asm/irq.h>
+#include <asm/spu.h>
+#include <asm/spu_priv1.h>
+#include <asm/udbg.h>
+#include <asm/cell-regs.h>
+
+#include "interrupt.h"
+#include "pervasive.h"
+#include "ras.h"
+#include "io-workarounds.h"
+
+static void qpace_show_cpuinfo(struct seq_file *m)
+{
+        struct device_node *root;
+        const char *model = "";
+
+        root = of_find_node_by_path("/");
+        if (root)
+                model = of_get_property(root, "model", NULL);
+        seq_printf(m, "machine\t\t: CHRP %s\n", model);
+        of_node_put(root);
+}
+
+static void qpace_progress(char *s, unsigned short hex)
+{
+        printk("*** %04x : %s\n", hex, s ? s : "");
+}
+
+static int __init qpace_publish_devices(void)
+{
+        int node;
+
+        /* Publish OF platform devices for southbridge IOs */
+        of_platform_bus_probe(NULL, NULL, NULL);
+
+        /* There is no device for the MIC memory controller, thus we create
+         * a platform device for it to attach the EDAC driver to.
+         */
+        for_each_online_node(node) {
+                if (cbe_get_cpu_mic_tm_regs(cbe_node_to_cpu(node)) == NULL)
+                        continue;
+                platform_device_register_simple("cbe-mic", node, NULL, 0);
+        }
+
+        return 0;
+}
+machine_subsys_initcall(qpace, qpace_publish_devices);
+
+extern int qpace_notify(struct device *dev)
+{
+        /* set dma_ops for of_platform bus */
+        if (dev->bus && dev->bus->name
+                        && !strcmp(dev->bus->name, "of_platform"))
+                set_dma_ops(dev, &dma_direct_ops);
+
+        return 0;
+}
+
+static void __init qpace_setup_arch(void)
+{
+#ifdef CONFIG_SPU_BASE
+        spu_priv1_ops = &spu_priv1_mmio_ops;
+        spu_management_ops = &spu_management_of_ops;
+#endif
+
+        cbe_regs_init();
+
+#ifdef CONFIG_CBE_RAS
+        cbe_ras_init();
+#endif
+
+#ifdef CONFIG_SMP
+        smp_init_cell();
+#endif
+
+        /* init to some ~sane value until calibrate_delay() runs */
+        loops_per_jiffy = 50000000;
+
+        cbe_pervasive_init();
+#ifdef CONFIG_DUMMY_CONSOLE
+        conswitchp = &dummy_con;
+#endif
+
+        /* set notifier function */
+        platform_notify = &qpace_notify;
+}
+
+static int __init qpace_probe(void)
+{
+        unsigned long root = of_get_flat_dt_root();
+
+        if (!of_flat_dt_is_compatible(root, "IBM,QPACE"))
+                return 0;
+
+        hpte_init_native();
+
+        return 1;
+}
+
+define_machine(qpace) {
+        .name                   = "QPACE",
+        .probe                  = qpace_probe,
+        .setup_arch             = qpace_setup_arch,
+        .show_cpuinfo           = qpace_show_cpuinfo,
+        .restart                = rtas_restart,
+        .power_off              = rtas_power_off,
+        .halt                   = rtas_halt,
+        .get_boot_time          = rtas_get_boot_time,
+        .calibrate_decr         = generic_calibrate_decr,
+        .progress               = qpace_progress,
+        .init_IRQ               = iic_init_IRQ,
+#ifdef CONFIG_KEXEC
+        .machine_kexec          = default_machine_kexec,
+        .machine_kexec_prepare  = default_machine_kexec_prepare,
+        .machine_crash_shutdown = default_machine_crash_shutdown,
+#endif
+};
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index ab721b50fbba..59305369f6b2 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -35,7 +35,6 @@
 #include <asm/mmu.h>
 #include <asm/processor.h>
 #include <asm/io.h>
-#include <asm/kexec.h>
 #include <asm/pgtable.h>
 #include <asm/prom.h>
 #include <asm/rtas.h>
@@ -289,9 +288,4 @@ define_machine(cell) {
         .progress               = cell_progress,
         .init_IRQ               = cell_init_irq,
         .pci_setup_phb          = cell_setup_phb,
-#ifdef CONFIG_KEXEC
-        .machine_kexec          = default_machine_kexec,
-        .machine_kexec_prepare  = default_machine_kexec_prepare,
-        .machine_crash_shutdown = default_machine_crash_shutdown,
-#endif
 };
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 1b26071a86ca..7106b63d401b 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -273,12 +273,10 @@ spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
                 return VM_FAULT_NOPAGE;
 
         if (ctx->state == SPU_STATE_SAVED) {
-                vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
-                                                        & ~_PAGE_NO_CACHE);
+                vma->vm_page_prot = pgprot_cached(vma->vm_page_prot);
                 pfn = vmalloc_to_pfn(ctx->csa.lscsa->ls + offset);
         } else {
-                vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
-                                             | _PAGE_NO_CACHE);
+                vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot);
                 pfn = (ctx->spu->local_store_phys + offset) >> PAGE_SHIFT;
         }
         vm_insert_pfn(vma, address, pfn);
@@ -338,8 +336,7 @@ static int spufs_mem_mmap(struct file *file, struct vm_area_struct *vma)
                 return -EINVAL;
 
         vma->vm_flags |= VM_IO | VM_PFNMAP;
-        vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
-                                     | _PAGE_NO_CACHE);
+        vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot);
 
         vma->vm_ops = &spufs_mem_mmap_vmops;
         return 0;
@@ -452,8 +449,7 @@ static int spufs_cntl_mmap(struct file *file, struct vm_area_struct *vma)
                 return -EINVAL;
 
         vma->vm_flags |= VM_IO | VM_PFNMAP;
-        vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
-                                     | _PAGE_NO_CACHE | _PAGE_GUARDED);
+        vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
         vma->vm_ops = &spufs_cntl_mmap_vmops;
         return 0;
@@ -1155,8 +1151,7 @@ static int spufs_signal1_mmap(struct file *file, struct vm_area_struct *vma)
                 return -EINVAL;
 
         vma->vm_flags |= VM_IO | VM_PFNMAP;
-        vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
-                                     | _PAGE_NO_CACHE | _PAGE_GUARDED);
+        vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
         vma->vm_ops = &spufs_signal1_mmap_vmops;
         return 0;
@@ -1292,8 +1287,7 @@ static int spufs_signal2_mmap(struct file *file, struct vm_area_struct *vma)
                 return -EINVAL;
 
         vma->vm_flags |= VM_IO | VM_PFNMAP;
-        vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
-                                     | _PAGE_NO_CACHE | _PAGE_GUARDED);
+        vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
         vma->vm_ops = &spufs_signal2_mmap_vmops;
         return 0;
@@ -1414,8 +1408,7 @@ static int spufs_mss_mmap(struct file *file, struct vm_area_struct *vma)
                 return -EINVAL;
 
         vma->vm_flags |= VM_IO | VM_PFNMAP;
-        vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
-                                     | _PAGE_NO_CACHE | _PAGE_GUARDED);
+        vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
         vma->vm_ops = &spufs_mss_mmap_vmops;
         return 0;
@@ -1476,8 +1469,7 @@ static int spufs_psmap_mmap(struct file *file, struct vm_area_struct *vma)
                 return -EINVAL;
 
         vma->vm_flags |= VM_IO | VM_PFNMAP;
-        vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
-                                     | _PAGE_NO_CACHE | _PAGE_GUARDED);
+        vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
         vma->vm_ops = &spufs_psmap_mmap_vmops;
         return 0;
@@ -1536,8 +1528,7 @@ static int spufs_mfc_mmap(struct file *file, struct vm_area_struct *vma)
                 return -EINVAL;
 
         vma->vm_flags |= VM_IO | VM_PFNMAP;
-        vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
-                                     | _PAGE_NO_CACHE | _PAGE_GUARDED);
+        vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
         vma->vm_ops = &spufs_mfc_mmap_vmops;
         return 0;
diff --git a/arch/powerpc/platforms/chrp/pci.c b/arch/powerpc/platforms/chrp/pci.c
index d3cde6b9d2df..f6b0c519d5a2 100644
--- a/arch/powerpc/platforms/chrp/pci.c
+++ b/arch/powerpc/platforms/chrp/pci.c
@@ -141,6 +141,7 @@ hydra_init(void)
                 of_node_put(np);
                 return 0;
         }
+        of_node_put(np);
         Hydra = ioremap(r.start, r.end-r.start);
         printk("Hydra Mac I/O at %llx\n", (unsigned long long)r.start);
         printk("Hydra Feature_Control was %x",
@@ -198,7 +199,7 @@ static void __init setup_peg2(struct pci_controller *hose, struct device_node *d
                 printk ("RTAS supporting Pegasos OF not found, please upgrade"
                         " your firmware\n");
         }
-        ppc_pci_flags |= PPC_PCI_REASSIGN_ALL_BUS;
+        ppc_pci_add_flags(PPC_PCI_REASSIGN_ALL_BUS);
         /* keep the reference to the root node */
 }
 
diff --git a/arch/powerpc/platforms/embedded6xx/c2k.c b/arch/powerpc/platforms/embedded6xx/c2k.c
index 32ba0fa0ad03..8cab5731850f 100644
--- a/arch/powerpc/platforms/embedded6xx/c2k.c
+++ b/arch/powerpc/platforms/embedded6xx/c2k.c
@@ -20,7 +20,6 @@
 #include <linux/seq_file.h>
 #include <linux/time.h>
 #include <linux/of.h>
-#include <linux/kexec.h>
 
 #include <asm/machdep.h>
 #include <asm/prom.h>
@@ -147,9 +146,4 @@ define_machine(c2k) {
         .get_irq                = mv64x60_get_irq,
         .restart                = c2k_restart,
         .calibrate_decr         = generic_calibrate_decr,
-#ifdef CONFIG_KEXEC
-        .machine_kexec          = default_machine_kexec,
-        .machine_kexec_prepare  = default_machine_kexec_prepare,
-        .machine_crash_shutdown = default_machine_crash_shutdown,
-#endif
 };
diff --git a/arch/powerpc/platforms/embedded6xx/prpmc2800.c b/arch/powerpc/platforms/embedded6xx/prpmc2800.c
index 4c485e984236..670035f49a69 100644
--- a/arch/powerpc/platforms/embedded6xx/prpmc2800.c
+++ b/arch/powerpc/platforms/embedded6xx/prpmc2800.c
@@ -19,7 +19,6 @@
 #include <asm/prom.h>
 #include <asm/system.h>
 #include <asm/time.h>
-#include <asm/kexec.h>
 
 #include <mm/mmu_decl.h>
 
@@ -155,9 +154,4 @@ define_machine(prpmc2800){
         .get_irq                = mv64x60_get_irq,
         .restart                = prpmc2800_restart,
         .calibrate_decr         = generic_calibrate_decr,
-#ifdef CONFIG_KEXEC
-        .machine_kexec          = default_machine_kexec,
-        .machine_kexec_prepare  = default_machine_kexec_prepare,
-        .machine_crash_shutdown = default_machine_crash_shutdown,
-#endif
 };
diff --git a/arch/powerpc/platforms/iseries/Kconfig b/arch/powerpc/platforms/iseries/Kconfig
index 45ffd8e542f4..ed3753d8c109 100644
--- a/arch/powerpc/platforms/iseries/Kconfig
+++ b/arch/powerpc/platforms/iseries/Kconfig
@@ -9,6 +9,7 @@ menu "iSeries device drivers"
 
 config VIODASD
         tristate "iSeries Virtual I/O disk support"
+        depends on BLOCK
         help
           If you are running on an iSeries system and you want to use
           virtual disks created and managed by OS/400, say Y.
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index d4c61c3c9669..bfd60e4accee 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -50,7 +50,6 @@
 #include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
-#include <asm/kexec.h>
 #include <asm/pci-bridge.h>
 #include <asm/iommu.h>
 #include <asm/machdep.h>
@@ -335,9 +334,4 @@ define_machine(maple) {
         .calibrate_decr         = generic_calibrate_decr,
         .progress               = maple_progress,
         .power_save             = power4_idle,
-#ifdef CONFIG_KEXEC
-        .machine_kexec          = default_machine_kexec,
-        .machine_kexec_prepare  = default_machine_kexec_prepare,
-        .machine_crash_shutdown = default_machine_crash_shutdown,
-#endif
 };
diff --git a/arch/powerpc/platforms/powermac/cpufreq_32.c b/arch/powerpc/platforms/powermac/cpufreq_32.c
index 792d3ce8112e..65c585b8b00d 100644
--- a/arch/powerpc/platforms/powermac/cpufreq_32.c
+++ b/arch/powerpc/platforms/powermac/cpufreq_32.c
@@ -310,7 +310,7 @@ static int pmu_set_cpu_speed(int low_speed)
                 _set_L3CR(save_l3cr);
 
         /* Restore userland MMU context */
-        set_context(current->active_mm->context.id, current->active_mm->pgd);
+        switch_mmu_context(NULL, current->active_mm);
 
 #ifdef DEBUG_FREQ
         printk(KERN_DEBUG "HID1, after: %x\n", mfspr(SPRN_HID1));
diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c
index bcf50d7056e9..54b7b76ed4f0 100644
--- a/arch/powerpc/platforms/powermac/pci.c
+++ b/arch/powerpc/platforms/powermac/pci.c
@@ -729,7 +729,7 @@ static void __init setup_bandit(struct pci_controller *hose,
 static int __init setup_uninorth(struct pci_controller *hose,
                                  struct resource *addr)
 {
-        ppc_pci_flags |= PPC_PCI_REASSIGN_ALL_BUS;
+        ppc_pci_add_flags(PPC_PCI_REASSIGN_ALL_BUS);
         has_uninorth = 1;
         hose->ops = &macrisc_pci_ops;
         hose->cfg_addr = ioremap(addr->start + 0x800000, 0x1000);
@@ -996,7 +996,7 @@ void __init pmac_pci_init(void)
         struct device_node *np, *root;
         struct device_node *ht = NULL;
 
-        ppc_pci_flags = PPC_PCI_CAN_SKIP_ISA_ALIGN;
+        ppc_pci_set_flags(PPC_PCI_CAN_SKIP_ISA_ALIGN);
 
         root = of_find_node_by_path("/");
         if (root == NULL) {
@@ -1055,7 +1055,7 @@ void __init pmac_pci_init(void)
          * some offset between bus number and domains for now when we
          * assign all busses should help for now
          */
-        if (ppc_pci_flags & PPC_PCI_REASSIGN_ALL_BUS)
+        if (ppc_pci_has_flag(PPC_PCI_REASSIGN_ALL_BUS))
                 pcibios_assign_bus_offset = 0x10;
 #endif
 }
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index 82c14d203d8b..9b78f5300c24 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -60,7 +60,6 @@
 #include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
-#include <asm/kexec.h>
 #include <asm/pci-bridge.h>
 #include <asm/ohare.h>
 #include <asm/mediabay.h>
@@ -310,9 +309,7 @@ static void __init pmac_setup_arch(void)
         }
 
         /* See if newworld or oldworld */
-        for (ic = NULL; (ic = of_find_all_nodes(ic)) != NULL; )
-                if (of_get_property(ic, "interrupt-controller", NULL))
-                        break;
+        ic = of_find_node_with_property(NULL, "interrupt-controller");
         if (ic) {
                 pmac_newworld = 1;
                 of_node_put(ic);
@@ -740,11 +737,6 @@ define_machine(powermac) {
         .pci_probe_mode         = pmac_pci_probe_mode,
         .power_save             = power4_idle,
         .enable_pmcs            = power4_enable_pmcs,
-#ifdef CONFIG_KEXEC
-        .machine_kexec          = default_machine_kexec,
-        .machine_kexec_prepare  = default_machine_kexec_prepare,
-        .machine_crash_shutdown = default_machine_crash_shutdown,
-#endif
 #endif /* CONFIG_PPC64 */
 #ifdef CONFIG_PPC32
         .pcibios_enable_device_hook = pmac_pci_enable_device_hook,
diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S
index adee28da353f..1c2802fabd57 100644
--- a/arch/powerpc/platforms/powermac/sleep.S
+++ b/arch/powerpc/platforms/powermac/sleep.S
@@ -17,6 +17,7 @@
 #include <asm/cache.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
+#include <asm/mmu.h>
 
 #define MAGIC   0x4c617273      /* 'Lars' */
 
@@ -323,7 +324,7 @@ grackle_wake_up:
         lwz     r4,SL_IBAT3+4(r1)
         mtibatl 3,r4
 
-BEGIN_FTR_SECTION
+BEGIN_MMU_FTR_SECTION
         li      r4,0
         mtspr   SPRN_DBAT4U,r4
         mtspr   SPRN_DBAT4L,r4
@@ -341,7 +342,7 @@ BEGIN_FTR_SECTION
         mtspr   SPRN_IBAT6L,r4
         mtspr   SPRN_IBAT7U,r4
         mtspr   SPRN_IBAT7L,r4
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 
         /* Flush all TLBs */
         lis     r4,0x1000
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 40f72c2a4699..6b0711c15eca 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -739,7 +739,7 @@ static void __init smp_core99_setup(int ncpus)
 
                 /* XXX should get this from reg properties */
                 for (i = 1; i < ncpus; ++i)
-                        smp_hw_index[i] = i;
+                        set_hard_smp_processor_id(i, i);
         }
 #endif
 
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index ffdd8e963fbd..dbc124e05646 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -314,11 +314,17 @@ static int __init ps3_setup_vuart_device(enum ps3_match_id match_id,
 
         result = ps3_system_bus_device_register(&p->dev);
 
-        if (result)
+        if (result) {
                 pr_debug("%s:%d ps3_system_bus_device_register failed\n",
                         __func__, __LINE__);
-
+                goto fail_device_register;
+        }
         pr_debug(" <- %s:%d\n", __func__, __LINE__);
+        return 0;
+
+fail_device_register:
+        kfree(p);
+        pr_debug(" <- %s:%d fail\n", __func__, __LINE__);
         return result;
 }
 
@@ -463,11 +469,17 @@ static int __init ps3_register_sound_devices(void)
 
         result = ps3_system_bus_device_register(&p->dev);
 
-        if (result)
+        if (result) {
                 pr_debug("%s:%d ps3_system_bus_device_register failed\n",
                         __func__, __LINE__);
-
+                goto fail_device_register;
+        }
         pr_debug(" <- %s:%d\n", __func__, __LINE__);
+        return 0;
+
+fail_device_register:
+        kfree(p);
+        pr_debug(" <- %s:%d failed\n", __func__, __LINE__);
         return result;
 }
 
@@ -485,17 +497,24 @@ static int __init ps3_register_graphics_devices(void)
         if (!p)
                 return -ENOMEM;
 
-        p->dev.match_id = PS3_MATCH_ID_GRAPHICS;
-        p->dev.match_sub_id = PS3_MATCH_SUB_ID_FB;
+        p->dev.match_id = PS3_MATCH_ID_GPU;
+        p->dev.match_sub_id = PS3_MATCH_SUB_ID_GPU_FB;
         p->dev.dev_type = PS3_DEVICE_TYPE_IOC0;
 
         result = ps3_system_bus_device_register(&p->dev);
 
-        if (result)
+        if (result) {
                 pr_debug("%s:%d ps3_system_bus_device_register failed\n",
                         __func__, __LINE__);
+                goto fail_device_register;
+        }
 
         pr_debug(" <- %s:%d\n", __func__, __LINE__);
+        return 0;
+
+fail_device_register:
+        kfree(p);
+        pr_debug(" <- %s:%d failed\n", __func__, __LINE__);
         return result;
 }
 
diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
index 3a58ffabccd9..a4d49dd9e8a9 100644
--- a/arch/powerpc/platforms/ps3/mm.c
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -649,7 +649,7 @@ static int dma_sb_region_create(struct ps3_dma_region *r)
 {
         int result;
 
-        pr_info(" -> %s:%d:\n", __func__, __LINE__);
+        DBG(" -> %s:%d:\n", __func__, __LINE__);
 
         BUG_ON(!r);
 
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 77bc330263c4..35f3e85cf60e 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -23,7 +23,6 @@
 #include <linux/fs.h>
 #include <linux/root_dev.h>
 #include <linux/console.h>
-#include <linux/kexec.h>
 #include <linux/bootmem.h>
 
 #include <asm/machdep.h>
@@ -42,6 +41,10 @@
 #define DBG pr_debug
 #endif
 
+/* mutex synchronizing GPU accesses and video mode changes */
+DEFINE_MUTEX(ps3_gpu_mutex);
+EXPORT_SYMBOL_GPL(ps3_gpu_mutex);
+
 #if !defined(CONFIG_SMP)
 static void smp_send_stop(void) {}
 #endif
@@ -277,8 +280,5 @@ define_machine(ps3) {
         .halt                           = ps3_halt,
 #if defined(CONFIG_KEXEC)
         .kexec_cpu_down                 = ps3_kexec_cpu_down,
-        .machine_kexec                  = default_machine_kexec,
-        .machine_kexec_prepare          = default_machine_kexec_prepare,
-        .machine_crash_shutdown         = default_machine_crash_shutdown,
 #endif
 };
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 661e9f77ebf6..ee0d22911621 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -31,7 +31,7 @@
 #include "platform.h"
 
 static struct device ps3_system_bus = {
-        .bus_id = "ps3_system",
+        .init_name = "ps3_system",
 };
 
 /* FIXME: need device usage counters! */
@@ -175,7 +175,7 @@ int ps3_open_hv_device(struct ps3_system_bus_device *dev)
                 return ps3_open_hv_device_sb(dev);
 
         case PS3_MATCH_ID_SOUND:
-        case PS3_MATCH_ID_GRAPHICS:
+        case PS3_MATCH_ID_GPU:
                 return ps3_open_hv_device_gpu(dev);
 
         case PS3_MATCH_ID_AV_SETTINGS:
@@ -213,7 +213,7 @@ int ps3_close_hv_device(struct ps3_system_bus_device *dev)
                 return ps3_close_hv_device_sb(dev);
 
         case PS3_MATCH_ID_SOUND:
-        case PS3_MATCH_ID_GRAPHICS:
+        case PS3_MATCH_ID_GPU:
                 return ps3_close_hv_device_gpu(dev);
 
         case PS3_MATCH_ID_AV_SETTINGS:
@@ -356,12 +356,12 @@ static int ps3_system_bus_match(struct device *_dev,
         if (result)
                 pr_info("%s:%d: dev=%u.%u(%s), drv=%u.%u(%s): match\n",
                         __func__, __LINE__,
-                        dev->match_id, dev->match_sub_id, dev->core.bus_id,
+                        dev->match_id, dev->match_sub_id, dev_name(&dev->core),
                         drv->match_id, drv->match_sub_id, drv->core.name);
         else
                 pr_debug("%s:%d: dev=%u.%u(%s), drv=%u.%u(%s): miss\n",
                         __func__, __LINE__,
-                        dev->match_id, dev->match_sub_id, dev->core.bus_id,
+                        dev->match_id, dev->match_sub_id, dev_name(&dev->core),
                         drv->match_id, drv->match_sub_id, drv->core.name);
 
         return result;
@@ -383,9 +383,9 @@ static int ps3_system_bus_probe(struct device *_dev)
                 result = drv->probe(dev);
         else
                 pr_debug("%s:%d: %s no probe method\n", __func__, __LINE__,
-                        dev->core.bus_id);
+                        dev_name(&dev->core));
 
-        pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev->core.bus_id);
+        pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev_name(&dev->core));
         return result;
 }
 
@@ -407,7 +407,7 @@ static int ps3_system_bus_remove(struct device *_dev)
                 dev_dbg(&dev->core, "%s:%d %s: no remove method\n",
                         __func__, __LINE__, drv->core.name);
 
-        pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev->core.bus_id);
+        pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev_name(&dev->core));
         return result;
 }
 
@@ -432,7 +432,7 @@ static void ps3_system_bus_shutdown(struct device *_dev)
         BUG_ON(!drv);
 
         dev_dbg(&dev->core, "%s:%d: %s -> %s\n", __func__, __LINE__,
-                dev->core.bus_id, drv->core.name);
+                dev_name(&dev->core), drv->core.name);
 
         if (drv->shutdown)
                 drv->shutdown(dev);
@@ -453,7 +453,8 @@ static int ps3_system_bus_uevent(struct device *_dev, struct kobj_uevent_env *en
 {
         struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
 
-        if (add_uevent_var(env, "MODALIAS=ps3:%d", dev->match_id))
+        if (add_uevent_var(env, "MODALIAS=ps3:%d:%d", dev->match_id,
+                           dev->match_sub_id))
                 return -ENOMEM;
         return 0;
 }
@@ -462,7 +463,8 @@ static ssize_t modalias_show(struct device *_dev, struct device_attribute *a,
         char *buf)
 {
         struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
-        int len = snprintf(buf, PAGE_SIZE, "ps3:%d\n", dev->match_id);
+        int len = snprintf(buf, PAGE_SIZE, "ps3:%d:%d\n", dev->match_id,
+                           dev->match_sub_id);
 
         return (len >= PAGE_SIZE) ? (PAGE_SIZE - 1) : len;
 }
@@ -742,22 +744,18 @@ int ps3_system_bus_device_register(struct ps3_system_bus_device *dev)
         switch (dev->dev_type) {
         case PS3_DEVICE_TYPE_IOC0:
                 dev->core.archdata.dma_ops = &ps3_ioc0_dma_ops;
-                snprintf(dev->core.bus_id, sizeof(dev->core.bus_id),
-                        "ioc0_%02x", ++dev_ioc0_count);
+                dev_set_name(&dev->core, "ioc0_%02x", ++dev_ioc0_count);
                 break;
         case PS3_DEVICE_TYPE_SB:
                 dev->core.archdata.dma_ops = &ps3_sb_dma_ops;
-                snprintf(dev->core.bus_id, sizeof(dev->core.bus_id),
-                        "sb_%02x", ++dev_sb_count);
+                dev_set_name(&dev->core, "sb_%02x", ++dev_sb_count);
 
                 break;
         case PS3_DEVICE_TYPE_VUART:
-                snprintf(dev->core.bus_id, sizeof(dev->core.bus_id),
-                        "vuart_%02x", ++dev_vuart_count);
+                dev_set_name(&dev->core, "vuart_%02x", ++dev_vuart_count);
                 break;
         case PS3_DEVICE_TYPE_LPM:
-                snprintf(dev->core.bus_id, sizeof(dev->core.bus_id),
-                        "lpm_%02x", ++dev_lpm_count);
+                dev_set_name(&dev->core, "lpm_%02x", ++dev_lpm_count);
                 break;
         default:
                 BUG();
@@ -766,7 +764,7 @@ int ps3_system_bus_device_register(struct ps3_system_bus_device *dev)
         dev->core.archdata.of_node = NULL;
         set_dev_node(&dev->core, 0);
 
-        pr_debug("%s:%d add %s\n", __func__, __LINE__, dev->core.bus_id);
+        pr_debug("%s:%d add %s\n", __func__, __LINE__, dev_name(&dev->core));
 
         result = device_register(&dev->core);
         return result;
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 97619fd51e39..ddc2a307cd50 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -54,7 +54,7 @@ config PPC_SMLPAR
 
 config CMM
         tristate "Collaborative memory management"
-        depends on PPC_SMLPAR
+        depends on PPC_SMLPAR && !CRASH_DUMP
         default y
         help
           Select this option, if you want to enable the kernel interface
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index 5cd4d2761620..6567439fe78d 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -28,6 +28,7 @@
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/oom.h>
+#include <linux/reboot.h>
 #include <linux/sched.h>
 #include <linux/stringify.h>
 #include <linux/swap.h>
@@ -384,6 +385,26 @@ static void cmm_unregister_sysfs(struct sys_device *sysdev)
 }
 
 /**
+ * cmm_reboot_notifier - Make sure pages are not still marked as "loaned"
+ *
+ **/
+static int cmm_reboot_notifier(struct notifier_block *nb,
+                               unsigned long action, void *unused)
+{
+        if (action == SYS_RESTART) {
+                if (cmm_thread_ptr)
+                        kthread_stop(cmm_thread_ptr);
+                cmm_thread_ptr = NULL;
+                cmm_free_pages(loaned_pages);
+        }
+        return NOTIFY_DONE;
+}
+
+static struct notifier_block cmm_reboot_nb = {
+        .notifier_call = cmm_reboot_notifier,
+};
+
+/**
  * cmm_init - Module initialization
  *
  * Return value:
@@ -399,9 +420,12 @@ static int cmm_init(void)
         if ((rc = register_oom_notifier(&cmm_oom_nb)) < 0)
                 return rc;
 
-        if ((rc = cmm_sysfs_register(&cmm_sysdev)))
+        if ((rc = register_reboot_notifier(&cmm_reboot_nb)))
                 goto out_oom_notifier;
 
+        if ((rc = cmm_sysfs_register(&cmm_sysdev)))
+                goto out_reboot_notifier;
+
         if (cmm_disabled)
                 return rc;
 
@@ -415,6 +439,8 @@ static int cmm_init(void)
 
 out_unregister_sysfs:
         cmm_unregister_sysfs(&cmm_sysdev);
+out_reboot_notifier:
+        unregister_reboot_notifier(&cmm_reboot_nb);
 out_oom_notifier:
         unregister_oom_notifier(&cmm_oom_nb);
         return rc;
@@ -431,6 +457,7 @@ static void cmm_exit(void)
         if (cmm_thread_ptr)
                 kthread_stop(cmm_thread_ptr);
         unregister_oom_notifier(&cmm_oom_nb);
+        unregister_reboot_notifier(&cmm_reboot_nb);
         cmm_free_pages(loaned_pages);
         cmm_unregister_sysfs(&cmm_sysdev);
 }
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 54816d75b578..989d6462c154 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -21,6 +21,8 @@
  * Please address comments and feedback to Linas Vepstas <linas@austin.ibm.com>
  */
 
+#undef DEBUG
+
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/list.h>
@@ -488,10 +490,8 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
         if (!(pdn->eeh_mode & EEH_MODE_SUPPORTED) ||
             pdn->eeh_mode & EEH_MODE_NOCHECK) {
                 ignored_check++;
-#ifdef DEBUG
-                printk ("EEH:ignored check (%x) for %s %s\n", 
-                        pdn->eeh_mode, pci_name (dev), dn->full_name);
-#endif
+                pr_debug("EEH: Ignored check (%x) for %s %s\n",
+                         pdn->eeh_mode, pci_name (dev), dn->full_name);
                 return 0;
         }
 
@@ -1014,10 +1014,9 @@ static void *early_enable_eeh(struct device_node *dn, void *data)
                         eeh_subsystem_enabled = 1;
                         pdn->eeh_mode |= EEH_MODE_SUPPORTED;
 
-#ifdef DEBUG
-                        printk(KERN_DEBUG "EEH: %s: eeh enabled, config=%x pe_config=%x\n",
-                               dn->full_name, pdn->eeh_config_addr, pdn->eeh_pe_config_addr);
-#endif
+                        pr_debug("EEH: %s: eeh enabled, config=%x pe_config=%x\n",
+                                 dn->full_name, pdn->eeh_config_addr,
+                                 pdn->eeh_pe_config_addr);
                 } else {
 
                         /* This device doesn't support EEH, but it may have an
@@ -1161,13 +1160,17 @@ static void eeh_add_device_late(struct pci_dev *dev)
         if (!dev || !eeh_subsystem_enabled)
                 return;
 
-#ifdef DEBUG
-        printk(KERN_DEBUG "EEH: adding device %s\n", pci_name(dev));
-#endif
+        pr_debug("EEH: Adding device %s\n", pci_name(dev));
 
-        pci_dev_get (dev);
         dn = pci_device_to_OF_node(dev);
         pdn = PCI_DN(dn);
+        if (pdn->pcidev == dev) {
+                pr_debug("EEH: Already referenced !\n");
+                return;
+        }
+        WARN_ON(pdn->pcidev);
+
+        pci_dev_get (dev);
         pdn->pcidev = dev;
 
         pci_addr_cache_insert_device(dev);
@@ -1206,17 +1209,18 @@ static void eeh_remove_device(struct pci_dev *dev)
                 return;
 
         /* Unregister the device with the EEH/PCI address search system */
-#ifdef DEBUG
-        printk(KERN_DEBUG "EEH: remove device %s\n", pci_name(dev));
-#endif
-        pci_addr_cache_remove_device(dev);
-        eeh_sysfs_remove_device(dev);
+        pr_debug("EEH: Removing device %s\n", pci_name(dev));
 
         dn = pci_device_to_OF_node(dev);
-        if (PCI_DN(dn)->pcidev) {
-                PCI_DN(dn)->pcidev = NULL;
-                pci_dev_put (dev);
+        if (PCI_DN(dn)->pcidev == NULL) {
+                pr_debug("EEH: Not referenced !\n");
+                return;
         }
+        PCI_DN(dn)->pcidev = NULL;
+        pci_dev_put (dev);
+
+        pci_addr_cache_remove_device(dev);
+        eeh_sysfs_remove_device(dev);
 }
 
 void eeh_remove_bus_device(struct pci_dev *dev)
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 1f032483c026..a20ead87153d 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -116,7 +116,7 @@ static void pseries_cpu_die(unsigned int cpu)
                 cpu_status = query_cpu_stopped(pcpu);
                 if (cpu_status == 0 || cpu_status == -1)
                         break;
-                msleep(200);
+                cpu_relax();
         }
         if (cpu_status != 0) {
                 printk("Querying DEAD? cpu %i (%i) shows %i\n",
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 7190493e9bdc..5e1ed3d60ee5 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -25,6 +25,8 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#undef DEBUG
+
 #include <linux/pci.h>
 #include <asm/pci-bridge.h>
 #include <asm/ppc-pci.h>
@@ -69,74 +71,25 @@ EXPORT_SYMBOL_GPL(pcibios_find_pci_bus);
  * Remove all of the PCI devices under this bus both from the
  * linux pci device tree, and from the powerpc EEH address cache.
  */
-void
-pcibios_remove_pci_devices(struct pci_bus *bus)
+void pcibios_remove_pci_devices(struct pci_bus *bus)
 {
-        struct pci_dev *dev, *tmp;
+        struct pci_dev *dev, *tmp;
+        struct pci_bus *child_bus;
+
+        /* First go down child busses */
+        list_for_each_entry(child_bus, &bus->children, node)
+                pcibios_remove_pci_devices(child_bus);
 
+        pr_debug("PCI: Removing devices on bus %04x:%02x\n",
+                 pci_domain_nr(bus),  bus->number);
         list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) {
+                pr_debug("     * Removing %s...\n", pci_name(dev));
                 eeh_remove_bus_device(dev);
-                pci_remove_bus_device(dev);
-        }
+                pci_remove_bus_device(dev);
+        }
 }
 EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices);
 
-/* Must be called before pci_bus_add_devices */
-void
-pcibios_fixup_new_pci_devices(struct pci_bus *bus)
-{
-        struct pci_dev *dev;
-
-        list_for_each_entry(dev, &bus->devices, bus_list) {
-                /* Skip already-added devices */
-                if (!dev->is_added) {
-                        int i;
-
-                        /* Fill device archdata and setup iommu table */
-                        pcibios_setup_new_device(dev);
-
-                        pci_read_irq_line(dev);
-                        for (i = 0; i < PCI_NUM_RESOURCES; i++) {
-                                struct resource *r = &dev->resource[i];
-
-                                if (r->parent || !r->start || !r->flags)
-                                        continue;
-                                pci_claim_resource(dev, i);
-                        }
-                }
-        }
-}
-EXPORT_SYMBOL_GPL(pcibios_fixup_new_pci_devices);
-
-static int
-pcibios_pci_config_bridge(struct pci_dev *dev)
-{
-        u8 sec_busno;
-        struct pci_bus *child_bus;
-
-        /* Get busno of downstream bus */
-        pci_read_config_byte(dev, PCI_SECONDARY_BUS, &sec_busno);
-
-        /* Add to children of PCI bridge dev->bus */
-        child_bus = pci_add_new_bus(dev->bus, dev, sec_busno);
-        if (!child_bus) {
-                printk (KERN_ERR "%s: could not add second bus\n", __func__);
-                return -EIO;
-        }
-        sprintf(child_bus->name, "PCI Bus #%02x", child_bus->number);
-
-        pci_scan_child_bus(child_bus);
-
-        /* Fixup new pci devices */
-        pcibios_fixup_new_pci_devices(child_bus);
-
-        /* Make the discovered devices available */
-        pci_bus_add_devices(child_bus);
-
-        eeh_add_device_tree_late(child_bus);
-        return 0;
-}
-
 /**
  * pcibios_add_pci_devices - adds new pci devices to bus
  *
@@ -147,10 +100,9 @@ pcibios_pci_config_bridge(struct pci_dev *dev)
  * is how this routine differs from other, similar pcibios
  * routines.)
  */
-void
-pcibios_add_pci_devices(struct pci_bus * bus)
+void pcibios_add_pci_devices(struct pci_bus * bus)
 {
-        int slotno, num, mode;
+        int slotno, num, mode, pass, max;
         struct pci_dev *dev;
         struct device_node *dn = pci_bus_to_OF_node(bus);
 
@@ -162,26 +114,23 @@ pcibios_add_pci_devices(struct pci_bus * bus)
 
         if (mode == PCI_PROBE_DEVTREE) {
                 /* use ofdt-based probe */
-                of_scan_bus(dn, bus);
-                if (!list_empty(&bus->devices)) {
-                        pcibios_fixup_new_pci_devices(bus);
-                        pci_bus_add_devices(bus);
-                        eeh_add_device_tree_late(bus);
-                }
+                of_rescan_bus(dn, bus);
         } else if (mode == PCI_PROBE_NORMAL) {
                 /* use legacy probe */
                 slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
                 num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
-                if (num) {
-                        pcibios_fixup_new_pci_devices(bus);
-                        pci_bus_add_devices(bus);
-                        eeh_add_device_tree_late(bus);
+                if (!num)
+                        return;
+                pcibios_setup_bus_devices(bus);
+                max = bus->secondary;
+                for (pass=0; pass < 2; pass++)
+                        list_for_each_entry(dev, &bus->devices, bus_list) {
+                        if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
+                            dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)
+                                max = pci_scan_bridge(bus, dev, max, pass);
                 }
-
-                list_for_each_entry(dev, &bus->devices, bus_list)
-                        if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
-                                pcibios_pci_config_bridge(dev);
         }
+        pcibios_finish_adding_to_bus(bus);
 }
 EXPORT_SYMBOL_GPL(pcibios_add_pci_devices);
 
@@ -190,6 +139,8 @@ struct pci_controller * __devinit init_phb_dynamic(struct device_node *dn)
         struct pci_controller *phb;
         int primary;
 
+        pr_debug("PCI: Initializing new hotplug PHB %s\n", dn->full_name);
+
         primary = list_empty(&hose_list);
         phb = pcibios_alloc_controller(dn);
         if (!phb)
@@ -203,11 +154,59 @@ struct pci_controller * __devinit init_phb_dynamic(struct device_node *dn)
                 eeh_add_device_tree_early(dn);
 
         scan_phb(phb);
-        pcibios_allocate_bus_resources(phb->bus);
-        pcibios_fixup_new_pci_devices(phb->bus);
-        pci_bus_add_devices(phb->bus);
-        eeh_add_device_tree_late(phb->bus);
+        pcibios_finish_adding_to_bus(phb->bus);
 
         return phb;
 }
 EXPORT_SYMBOL_GPL(init_phb_dynamic);
+
+/* RPA-specific bits for removing PHBs */
+int remove_phb_dynamic(struct pci_controller *phb)
+{
+        struct pci_bus *b = phb->bus;
+        struct resource *res;
+        int rc, i;
+
+        pr_debug("PCI: Removing PHB %04x:%02x... \n",
+                 pci_domain_nr(b), b->number);
+
+        /* We cannot to remove a root bus that has children */
+        if (!(list_empty(&b->children) && list_empty(&b->devices)))
+                return -EBUSY;
+
+        /* We -know- there aren't any child devices anymore at this stage
+         * and thus, we can safely unmap the IO space as it's not in use
+         */
+        res = &phb->io_resource;
+        if (res->flags & IORESOURCE_IO) {
+                rc = pcibios_unmap_io_space(b);
+                if (rc) {
+                        printk(KERN_ERR "%s: failed to unmap IO on bus %s\n",
+                               __func__, b->name);
+                        return 1;
+                }
+        }
+
+        /* Unregister the bridge device from sysfs and remove the PCI bus */
+        device_unregister(b->bridge);
+        phb->bus = NULL;
+        pci_remove_bus(b);
+
+        /* Now release the IO resource */
+        if (res->flags & IORESOURCE_IO)
+                release_resource(res);
+
+        /* Release memory resources */
+        for (i = 0; i < 3; ++i) {
+                res = &phb->mem_resources[i];
+                if (!(res->flags & IORESOURCE_MEM))
+                        continue;
+                release_resource(res);
+        }
+
+        /* Free pci_controller data structure */
+        pcibios_free_controller(phb);
+
+        return 0;
+}
+EXPORT_SYMBOL_GPL(remove_phb_dynamic);
diff --git a/arch/powerpc/platforms/pseries/phyp_dump.c b/arch/powerpc/platforms/pseries/phyp_dump.c
index edbc012c2ebc..6cf35cd8d0b5 100644
--- a/arch/powerpc/platforms/pseries/phyp_dump.c
+++ b/arch/powerpc/platforms/pseries/phyp_dump.c
@@ -130,6 +130,9 @@ static unsigned long init_dump_header(struct phyp_dump_header *ph)
 static void print_dump_header(const struct phyp_dump_header *ph)
 {
 #ifdef DEBUG
+        if (ph == NULL)
+                return;
+
         printk(KERN_INFO "dump header:\n");
         /* setup some ph->sections required */
         printk(KERN_INFO "version = %d\n", ph->version);
@@ -411,6 +414,8 @@ static int __init phyp_dump_setup(void)
                 of_node_put(rtas);
         }
 
+        ibm_configure_kernel_dump = rtas_token("ibm,configure-kernel-dump");
+
         print_dump_header(dump_header);
         dump_area_length = init_dump_header(&phdr);
         /* align down */
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index e1904774a70f..f7a69021b7bf 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -579,7 +579,7 @@ static void xics_update_irq_servers(void)
         int i, j;
         struct device_node *np;
         u32 ilen;
-        const u32 *ireg, *isize;
+        const u32 *ireg;
         u32 hcpuid;
 
         /* Find the server numbers for the boot cpu. */
@@ -607,11 +607,6 @@ static void xics_update_irq_servers(void)
                 }
         }
 
-        /* get the bit size of server numbers */
-        isize = of_get_property(np, "ibm,interrupt-server#-size", NULL);
-        if (isize)
-                interrupt_server_size = *isize;
-
         of_node_put(np);
 }
 
@@ -682,6 +677,7 @@ void __init xics_init_IRQ(void)
         struct device_node *np;
         u32 indx = 0;
         int found = 0;
+        const u32 *isize;
 
         ppc64_boot_msg(0x20, "XICS Init");
 
@@ -701,6 +697,26 @@ void __init xics_init_IRQ(void)
         if (found == 0)
                 return;
 
+        /* get the bit size of server numbers */
+        found = 0;
+
+        for_each_compatible_node(np, NULL, "ibm,ppc-xics") {
+                isize = of_get_property(np, "ibm,interrupt-server#-size", NULL);
+
+                if (!isize)
+                        continue;
+
+                if (!found) {
+                        interrupt_server_size = *isize;
+                        found = 1;
+                } else if (*isize != interrupt_server_size) {
+                        printk(KERN_WARNING "XICS: "
+                               "mismatched ibm,interrupt-server#-size\n");
+                        interrupt_server_size = max(*isize,
+                                                    interrupt_server_size);
+                }
+        }
+
         xics_update_irq_servers();
         xics_init_host();
 
@@ -728,9 +744,18 @@ static void xics_set_cpu_priority(unsigned char cppr)
 /* Have the calling processor join or leave the specified global queue */
 static void xics_set_cpu_giq(unsigned int gserver, unsigned int join)
 {
-        int status = rtas_set_indicator_fast(GLOBAL_INTERRUPT_QUEUE,
-                (1UL << interrupt_server_size) - 1 - gserver, join);
-        WARN_ON(status < 0);
+        int index;
+        int status;
+
+        if (!rtas_indicator_present(GLOBAL_INTERRUPT_QUEUE, NULL))
+                return;
+
+        index = (1UL << interrupt_server_size) - 1 - gserver;
+
+        status = rtas_set_indicator_fast(GLOBAL_INTERRUPT_QUEUE, index, join);
+
+        WARN(status < 0, "set-indicator(%d, %d, %u) returned %d\n",
+             GLOBAL_INTERRUPT_QUEUE, index, join, status);
 }
 
 void xics_setup_cpu(void)
diff --git a/arch/powerpc/sysdev/bestcomm/ata.c b/arch/powerpc/sysdev/bestcomm/ata.c
index 1f5258fb38c3..901c9f91e5dd 100644
--- a/arch/powerpc/sysdev/bestcomm/ata.c
+++ b/arch/powerpc/sysdev/bestcomm/ata.c
@@ -61,6 +61,9 @@ bcom_ata_init(int queue_len, int maxbufsize)
         struct bcom_ata_var *var;
         struct bcom_ata_inc *inc;
 
+        /* Prefetch breaks ATA DMA.  Turn it off for ATA DMA */
+        bcom_disable_prefetch();
+
         tsk = bcom_task_alloc(queue_len, sizeof(struct bcom_ata_bd), 0);
         if (!tsk)
                 return NULL;
diff --git a/arch/powerpc/sysdev/bestcomm/ata.h b/arch/powerpc/sysdev/bestcomm/ata.h
index 10982769c465..0b2371811334 100644
--- a/arch/powerpc/sysdev/bestcomm/ata.h
+++ b/arch/powerpc/sysdev/bestcomm/ata.h
@@ -16,22 +16,15 @@
 
 struct bcom_ata_bd {
         u32     status;
-        u32     dst_pa;
         u32     src_pa;
+        u32     dst_pa;
 };
 
-extern struct bcom_task *
-bcom_ata_init(int queue_len, int maxbufsize);
-
-extern void
-bcom_ata_rx_prepare(struct bcom_task *tsk);
-
-extern void
-bcom_ata_tx_prepare(struct bcom_task *tsk);
-
-extern void
-bcom_ata_reset_bd(struct bcom_task *tsk);
-
+extern struct bcom_task * bcom_ata_init(int queue_len, int maxbufsize);
+extern void bcom_ata_rx_prepare(struct bcom_task *tsk);
+extern void bcom_ata_tx_prepare(struct bcom_task *tsk);
+extern void bcom_ata_reset_bd(struct bcom_task *tsk);
+extern void bcom_ata_release(struct bcom_task *tsk);
 
 #endif /* __BESTCOMM_ATA_H__ */
 
diff --git a/arch/powerpc/sysdev/bestcomm/bestcomm.c b/arch/powerpc/sysdev/bestcomm/bestcomm.c
index 446c9ea85b30..378ebd9aac18 100644
--- a/arch/powerpc/sysdev/bestcomm/bestcomm.c
+++ b/arch/powerpc/sysdev/bestcomm/bestcomm.c
@@ -279,7 +279,6 @@ bcom_engine_init(void)
         int task;
         phys_addr_t tdt_pa, ctx_pa, var_pa, fdt_pa;
         unsigned int tdt_size, ctx_size, var_size, fdt_size;
-        u16 regval;
 
         /* Allocate & clear SRAM zones for FDT, TDTs, contexts and vars/incs */
         tdt_size = BCOM_MAX_TASKS * sizeof(struct bcom_tdt);
@@ -331,10 +330,8 @@ bcom_engine_init(void)
         out_8(&bcom_eng->regs->ipr[BCOM_INITIATOR_ALWAYS], BCOM_IPR_ALWAYS);
 
         /* Disable COMM Bus Prefetch on the original 5200; it's broken */
-        if ((mfspr(SPRN_SVR) & MPC5200_SVR_MASK) == MPC5200_SVR) {
-                regval = in_be16(&bcom_eng->regs->PtdCntrl);
-                out_be16(&bcom_eng->regs->PtdCntrl,  regval | 1);
-        }
+        if ((mfspr(SPRN_SVR) & MPC5200_SVR_MASK) == MPC5200_SVR)
+                bcom_disable_prefetch();
 
         /* Init lock */
         spin_lock_init(&bcom_eng->lock);
diff --git a/arch/powerpc/sysdev/bestcomm/bestcomm.h b/arch/powerpc/sysdev/bestcomm/bestcomm.h
index c960a8b49655..23a95f80dfdb 100644
--- a/arch/powerpc/sysdev/bestcomm/bestcomm.h
+++ b/arch/powerpc/sysdev/bestcomm/bestcomm.h
@@ -16,8 +16,19 @@
 #ifndef __BESTCOMM_H__
 #define __BESTCOMM_H__
 
-struct bcom_bd; /* defined later on ... */
-
+/**
+ * struct bcom_bd - Structure describing a generic BestComm buffer descriptor
+ * @status: The current status of this buffer. Exact meaning depends on the
+ *          task type
+ * @data: An array of u32 extra data.  Size of array is task dependant.
+ *
+ * Note: Don't dereference a bcom_bd pointer as an array.  The size of the
+ *       bcom_bd is variable.  Use bcom_get_bd() instead.
+ */
+struct bcom_bd {
+        u32     status;
+        u32     data[0];        /* variable payload size */
+};
 
 /* ======================================================================== */
 /* Generic task management                                                   */
@@ -84,17 +95,6 @@ bcom_get_task_irq(struct bcom_task *tsk) {
 /* BD based tasks helpers                                                   */
 /* ======================================================================== */
 
-/**
- * struct bcom_bd - Structure describing a generic BestComm buffer descriptor
- * @status: The current status of this buffer. Exact meaning depends on the
- *          task type
- * @data: An array of u32 whose meaning depends on the task type.
- */
-struct bcom_bd {
-        u32     status;
-        u32     data[1];        /* variable, but at least 1 */
-};
-
 #define BCOM_BD_READY   0x40000000ul
 
 /** _bcom_next_index - Get next input index.
@@ -140,15 +140,31 @@ bcom_queue_full(struct bcom_task *tsk)
 }
 
 /**
+ * bcom_get_bd - Get a BD from the queue
+ * @tsk: The BestComm task structure
+ * index: Index of the BD to fetch
+ */
+static inline struct bcom_bd
+*bcom_get_bd(struct bcom_task *tsk, unsigned int index)
+{
+        /* A cast to (void*) so the address can be incremented by the
+         * real size instead of by sizeof(struct bcom_bd) */
+        return ((void *)tsk->bd) + (index * tsk->bd_size);
+}
+
+/**
  * bcom_buffer_done - Checks if a BestComm 
  * @tsk: The BestComm task structure
  */
 static inline int
 bcom_buffer_done(struct bcom_task *tsk)
 {
+        struct bcom_bd *bd;
         if (bcom_queue_empty(tsk))
                 return 0;
-        return !(tsk->bd[tsk->outdex].status & BCOM_BD_READY);
+
+        bd = bcom_get_bd(tsk, tsk->outdex);
+        return !(bd->status & BCOM_BD_READY);
 }
 
 /**
@@ -160,16 +176,21 @@ bcom_buffer_done(struct bcom_task *tsk)
 static inline struct bcom_bd *
 bcom_prepare_next_buffer(struct bcom_task *tsk)
 {
-        tsk->bd[tsk->index].status = 0; /* cleanup last status */
-        return &tsk->bd[tsk->index];
+        struct bcom_bd *bd;
+
+        bd = bcom_get_bd(tsk, tsk->index);
+        bd->status = 0; /* cleanup last status */
+        return bd;
 }
 
 static inline void
 bcom_submit_next_buffer(struct bcom_task *tsk, void *cookie)
 {
+        struct bcom_bd *bd = bcom_get_bd(tsk, tsk->index);
+
         tsk->cookie[tsk->index] = cookie;
         mb();   /* ensure the bd is really up-to-date */
-        tsk->bd[tsk->index].status |= BCOM_BD_READY;
+        bd->status |= BCOM_BD_READY;
         tsk->index = _bcom_next_index(tsk);
         if (tsk->flags & BCOM_FLAGS_ENABLE_TASK)
                 bcom_enable(tsk);
@@ -179,10 +200,12 @@ static inline void *
 bcom_retrieve_buffer(struct bcom_task *tsk, u32 *p_status, struct bcom_bd **p_bd)
 {
         void *cookie = tsk->cookie[tsk->outdex];
+        struct bcom_bd *bd = bcom_get_bd(tsk, tsk->outdex);
+
         if (p_status)
-                *p_status = tsk->bd[tsk->outdex].status;
+                *p_status = bd->status;
         if (p_bd)
-                *p_bd = &tsk->bd[tsk->outdex];
+                *p_bd = bd;
         tsk->outdex = _bcom_next_outdex(tsk);
         return cookie;
 }
diff --git a/arch/powerpc/sysdev/bestcomm/bestcomm_priv.h b/arch/powerpc/sysdev/bestcomm/bestcomm_priv.h
index 866a2915ef2f..eb0d1c883c31 100644
--- a/arch/powerpc/sysdev/bestcomm/bestcomm_priv.h
+++ b/arch/powerpc/sysdev/bestcomm/bestcomm_priv.h
@@ -198,8 +198,8 @@ struct bcom_task_header {
 #define BCOM_IPR_SCTMR_1        2
 #define BCOM_IPR_FEC_RX         6
 #define BCOM_IPR_FEC_TX         5
-#define BCOM_IPR_ATA_RX         4
-#define BCOM_IPR_ATA_TX         3
+#define BCOM_IPR_ATA_RX         7
+#define BCOM_IPR_ATA_TX         7
 #define BCOM_IPR_SCPCI_RX       2
 #define BCOM_IPR_SCPCI_TX       2
 #define BCOM_IPR_PSC3_RX        2
@@ -241,6 +241,22 @@ extern void bcom_set_initiator(int task, int initiator);
 
 #define TASK_ENABLE             0x8000
 
+/**
+ * bcom_disable_prefetch - Hook to disable bus prefetching
+ *
+ * ATA DMA and the original MPC5200 need this due to silicon bugs.  At the
+ * moment disabling prefetch is a one-way street.  There is no mechanism
+ * in place to turn prefetch back on after it has been disabled.  There is
+ * no reason it couldn't be done, it would just be more complex to implement.
+ */
+static inline void bcom_disable_prefetch(void)
+{
+        u16 regval;
+
+        regval = in_be16(&bcom_eng->regs->PtdCntrl);
+        out_be16(&bcom_eng->regs->PtdCntrl, regval | 1);
+};
+
 static inline void
 bcom_enable_task(int task)
 {
diff --git a/arch/powerpc/sysdev/dcr-low.S b/arch/powerpc/sysdev/dcr-low.S
index 2078f39e2f17..d3098ef1404a 100644
--- a/arch/powerpc/sysdev/dcr-low.S
+++ b/arch/powerpc/sysdev/dcr-low.S
@@ -11,14 +11,20 @@
 
 #include <asm/ppc_asm.h>
 #include <asm/processor.h>
+#include <asm/bug.h>
 
 #define DCR_ACCESS_PROLOG(table) \
+        cmpli   cr0,r3,1024;     \
         rlwinm  r3,r3,4,18,27;   \
         lis     r5,table@h;      \
         ori     r5,r5,table@l;   \
         add     r3,r3,r5;        \
+        bge-    1f;              \
         mtctr   r3;              \
-        bctr
+        bctr;                    \
+1:      trap;                    \
+        EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0;  \
+        blr
 
 _GLOBAL(__mfdcr)
         DCR_ACCESS_PROLOG(__mfdcr_table)
diff --git a/arch/powerpc/sysdev/dcr.c b/arch/powerpc/sysdev/dcr.c
index a8ba9983dd5a..bb44aa9fd470 100644
--- a/arch/powerpc/sysdev/dcr.c
+++ b/arch/powerpc/sysdev/dcr.c
@@ -124,7 +124,8 @@ EXPORT_SYMBOL_GPL(dcr_write_generic);
 
 #endif /* defined(CONFIG_PPC_DCR_NATIVE) && defined(CONFIG_PPC_DCR_MMIO) */
 
-unsigned int dcr_resource_start(struct device_node *np, unsigned int index)
+unsigned int dcr_resource_start(const struct device_node *np,
+                                unsigned int index)
 {
         unsigned int ds;
         const u32 *dr = of_get_property(np, "dcr-reg", &ds);
@@ -136,7 +137,7 @@ unsigned int dcr_resource_start(struct device_node *np, unsigned int index)
 }
 EXPORT_SYMBOL_GPL(dcr_resource_start);
 
-unsigned int dcr_resource_len(struct device_node *np, unsigned int index)
+unsigned int dcr_resource_len(const struct device_node *np, unsigned int index)
 {
         unsigned int ds;
         const u32 *dr = of_get_property(np, "dcr-reg", &ds);
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 5b264eb4b1f7..d5f9ae0f1b75 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -187,7 +187,7 @@ int __init fsl_add_bridge(struct device_node *dev, int is_primary)
                 printk(KERN_WARNING "Can't get bus-range for %s, assume"
                         " bus 0\n", dev->full_name);
 
-        ppc_pci_flags |= PPC_PCI_REASSIGN_ALL_BUS;
+        ppc_pci_add_flags(PPC_PCI_REASSIGN_ALL_BUS);
         hose = pcibios_alloc_controller(dev);
         if (!hose)
                 return -ENOMEM;
@@ -300,7 +300,7 @@ int __init mpc83xx_add_bridge(struct device_node *dev)
                        " bus 0\n", dev->full_name);
         }
 
-        ppc_pci_flags |= PPC_PCI_REASSIGN_ALL_BUS;
+        ppc_pci_add_flags(PPC_PCI_REASSIGN_ALL_BUS);
         hose = pcibios_alloc_controller(dev);
         if (!hose)
                 return -ENOMEM;
diff --git a/arch/powerpc/sysdev/grackle.c b/arch/powerpc/sysdev/grackle.c
index d502927644c6..5da37c2f22ee 100644
--- a/arch/powerpc/sysdev/grackle.c
+++ b/arch/powerpc/sysdev/grackle.c
@@ -57,7 +57,7 @@ void __init setup_grackle(struct pci_controller *hose)
 {
         setup_indirect_pci(hose, 0xfec00000, 0xfee00000, 0);
         if (machine_is_compatible("PowerMac1,1"))
-                ppc_pci_flags |= PPC_PCI_REASSIGN_ALL_BUS;
+                ppc_pci_add_flags(PPC_PCI_REASSIGN_ALL_BUS);
         if (machine_is_compatible("AAPL,PowerBook1998"))
                 grackle_set_loop_snoop(hose, 1);
 #if 0   /* Disabled for now, HW problems ??? */
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 1890fb085cde..c82babb70074 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -661,17 +661,6 @@ static inline void mpic_eoi(struct mpic *mpic)
         (void)mpic_cpu_read(MPIC_INFO(CPU_WHOAMI));
 }
 
-#ifdef CONFIG_SMP
-static irqreturn_t mpic_ipi_action(int irq, void *data)
-{
-        long ipi = (long)data;
-
-        smp_message_recv(ipi);
-
-        return IRQ_HANDLED;
-}
-#endif /* CONFIG_SMP */
-
 /*
  * Linux descriptor level callbacks
  */
@@ -1548,13 +1537,7 @@ unsigned int mpic_get_mcirq(void)
 void mpic_request_ipis(void)
 {
         struct mpic *mpic = mpic_primary;
-        long i, err;
-        static char *ipi_names[] = {
-                "IPI0 (call function)",
-                "IPI1 (reschedule)",
-                "IPI2 (call function single)",
-                "IPI3 (debugger break)",
-        };
+        int i;
         BUG_ON(mpic == NULL);
 
         printk(KERN_INFO "mpic: requesting IPIs ... \n");
@@ -1563,17 +1546,10 @@ void mpic_request_ipis(void)
                 unsigned int vipi = irq_create_mapping(mpic->irqhost,
                                                        mpic->ipi_vecs[0] + i);
                 if (vipi == NO_IRQ) {
-                        printk(KERN_ERR "Failed to map IPI %ld\n", i);
-                        break;
-                }
-                err = request_irq(vipi, mpic_ipi_action,
-                                  IRQF_DISABLED|IRQF_PERCPU,
-                                  ipi_names[i], (void *)i);
-                if (err) {
-                        printk(KERN_ERR "Request of irq %d for IPI %ld failed\n",
-                               vipi, i);
-                        break;
+                        printk(KERN_ERR "Failed to map %s\n", smp_ipi_name[i]);
+                        continue;
                 }
+                smp_request_message_ipi(vipi, i);
         }
 }
 
diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c
index d3e4d61030b5..77fae5f64f2e 100644
--- a/arch/powerpc/sysdev/ppc4xx_pci.c
+++ b/arch/powerpc/sysdev/ppc4xx_pci.c
@@ -194,11 +194,41 @@ static int __init ppc4xx_parse_dma_ranges(struct pci_controller *hose,
  * 4xx PCI 2.x part
  */
 
+static int __init ppc4xx_setup_one_pci_PMM(struct pci_controller        *hose,
+                                           void __iomem                 *reg,
+                                           u64                          plb_addr,
+                                           u64                          pci_addr,
+                                           u64                          size,
+                                           unsigned int                 flags,
+                                           int                          index)
+{
+        u32 ma, pcila, pciha;
+
+        if ((plb_addr + size) > 0xffffffffull || !is_power_of_2(size) ||
+            size < 0x1000 || (plb_addr & (size - 1)) != 0) {
+                printk(KERN_WARNING "%s: Resource out of range\n",
+                       hose->dn->full_name);
+                return -1;
+        }
+        ma = (0xffffffffu << ilog2(size)) | 1;
+        if (flags & IORESOURCE_PREFETCH)
+                ma |= 2;
+
+        pciha = RES_TO_U32_HIGH(pci_addr);
+        pcila = RES_TO_U32_LOW(pci_addr);
+
+        writel(plb_addr, reg + PCIL0_PMM0LA + (0x10 * index));
+        writel(pcila, reg + PCIL0_PMM0PCILA + (0x10 * index));
+        writel(pciha, reg + PCIL0_PMM0PCIHA + (0x10 * index));
+        writel(ma, reg + PCIL0_PMM0MA + (0x10 * index));
+
+        return 0;
+}
+
 static void __init ppc4xx_configure_pci_PMMs(struct pci_controller *hose,
                                              void __iomem *reg)
 {
-        u32 la, ma, pcila, pciha;
-        int i, j;
+        int i, j, found_isa_hole = 0;
 
         /* Setup outbound memory windows */
         for (i = j = 0; i < 3; i++) {
@@ -213,28 +243,29 @@ static void __init ppc4xx_configure_pci_PMMs(struct pci_controller *hose,
                         break;
                 }
 
-                /* Calculate register values */
-                la = res->start;
-                pciha = RES_TO_U32_HIGH(res->start - hose->pci_mem_offset);
-                pcila = RES_TO_U32_LOW(res->start - hose->pci_mem_offset);
-
-                ma = res->end + 1 - res->start;
-                if (!is_power_of_2(ma) || ma < 0x1000 || ma > 0xffffffffu) {
-                        printk(KERN_WARNING "%s: Resource out of range\n",
-                               hose->dn->full_name);
-                        continue;
+                /* Configure the resource */
+                if (ppc4xx_setup_one_pci_PMM(hose, reg,
+                                             res->start,
+                                             res->start - hose->pci_mem_offset,
+                                             res->end + 1 - res->start,
+                                             res->flags,
+                                             j) == 0) {
+                        j++;
+
+                        /* If the resource PCI address is 0 then we have our
+                         * ISA memory hole
+                         */
+                        if (res->start == hose->pci_mem_offset)
+                                found_isa_hole = 1;
                 }
-                ma = (0xffffffffu << ilog2(ma)) | 0x1;
-                if (res->flags & IORESOURCE_PREFETCH)
-                        ma |= 0x2;
-
-                /* Program register values */
-                writel(la, reg + PCIL0_PMM0LA + (0x10 * j));
-                writel(pcila, reg + PCIL0_PMM0PCILA + (0x10 * j));
-                writel(pciha, reg + PCIL0_PMM0PCIHA + (0x10 * j));
-                writel(ma, reg + PCIL0_PMM0MA + (0x10 * j));
-                j++;
         }
+
+        /* Handle ISA memory hole if not already covered */
+        if (j <= 2 && !found_isa_hole && hose->isa_mem_size)
+                if (ppc4xx_setup_one_pci_PMM(hose, reg, hose->isa_mem_phys, 0,
+                                             hose->isa_mem_size, 0, j) == 0)
+                        printk(KERN_INFO "%s: Legacy ISA memory support enabled\n",
+                               hose->dn->full_name);
 }
 
 static void __init ppc4xx_configure_pci_PTMs(struct pci_controller *hose,
@@ -352,11 +383,52 @@ static void __init ppc4xx_probe_pci_bridge(struct device_node *np)
  * 4xx PCI-X part
  */
 
+static int __init ppc4xx_setup_one_pcix_POM(struct pci_controller       *hose,
+                                            void __iomem                *reg,
+                                            u64                         plb_addr,
+                                            u64                         pci_addr,
+                                            u64                         size,
+                                            unsigned int                flags,
+                                            int                         index)
+{
+        u32 lah, lal, pciah, pcial, sa;
+
+        if (!is_power_of_2(size) || size < 0x1000 ||
+            (plb_addr & (size - 1)) != 0) {
+                printk(KERN_WARNING "%s: Resource out of range\n",
+                       hose->dn->full_name);
+                return -1;
+        }
+
+        /* Calculate register values */
+        lah = RES_TO_U32_HIGH(plb_addr);
+        lal = RES_TO_U32_LOW(plb_addr);
+        pciah = RES_TO_U32_HIGH(pci_addr);
+        pcial = RES_TO_U32_LOW(pci_addr);
+        sa = (0xffffffffu << ilog2(size)) | 0x1;
+
+        /* Program register values */
+        if (index == 0) {
+                writel(lah, reg + PCIX0_POM0LAH);
+                writel(lal, reg + PCIX0_POM0LAL);
+                writel(pciah, reg + PCIX0_POM0PCIAH);
+                writel(pcial, reg + PCIX0_POM0PCIAL);
+                writel(sa, reg + PCIX0_POM0SA);
+        } else {
+                writel(lah, reg + PCIX0_POM1LAH);
+                writel(lal, reg + PCIX0_POM1LAL);
+                writel(pciah, reg + PCIX0_POM1PCIAH);
+                writel(pcial, reg + PCIX0_POM1PCIAL);
+                writel(sa, reg + PCIX0_POM1SA);
+        }
+
+        return 0;
+}
+
 static void __init ppc4xx_configure_pcix_POMs(struct pci_controller *hose,
                                               void __iomem *reg)
 {
-        u32 lah, lal, pciah, pcial, sa;
-        int i, j;
+        int i, j, found_isa_hole = 0;
 
         /* Setup outbound memory windows */
         for (i = j = 0; i < 3; i++) {
@@ -371,36 +443,29 @@ static void __init ppc4xx_configure_pcix_POMs(struct pci_controller *hose,
                         break;
                 }
 
-                /* Calculate register values */
-                lah = RES_TO_U32_HIGH(res->start);
-                lal = RES_TO_U32_LOW(res->start);
-                pciah = RES_TO_U32_HIGH(res->start - hose->pci_mem_offset);
-                pcial = RES_TO_U32_LOW(res->start - hose->pci_mem_offset);
-                sa = res->end + 1 - res->start;
-                if (!is_power_of_2(sa) || sa < 0x100000 ||
-                    sa > 0xffffffffu) {
-                        printk(KERN_WARNING "%s: Resource out of range\n",
-                               hose->dn->full_name);
-                        continue;
+                /* Configure the resource */
+                if (ppc4xx_setup_one_pcix_POM(hose, reg,
+                                              res->start,
+                                              res->start - hose->pci_mem_offset,
+                                              res->end + 1 - res->start,
+                                              res->flags,
+                                              j) == 0) {
+                        j++;
+
+                        /* If the resource PCI address is 0 then we have our
+                         * ISA memory hole
+                         */
+                        if (res->start == hose->pci_mem_offset)
+                                found_isa_hole = 1;
                 }
-                sa = (0xffffffffu << ilog2(sa)) | 0x1;
-
-                /* Program register values */
-                if (j == 0) {
-                        writel(lah, reg + PCIX0_POM0LAH);
-                        writel(lal, reg + PCIX0_POM0LAL);
-                        writel(pciah, reg + PCIX0_POM0PCIAH);
-                        writel(pcial, reg + PCIX0_POM0PCIAL);
-                        writel(sa, reg + PCIX0_POM0SA);
-                } else {
-                        writel(lah, reg + PCIX0_POM1LAH);
-                        writel(lal, reg + PCIX0_POM1LAL);
-                        writel(pciah, reg + PCIX0_POM1PCIAH);
-                        writel(pcial, reg + PCIX0_POM1PCIAL);
-                        writel(sa, reg + PCIX0_POM1SA);
-                }
-                j++;
         }
+
+        /* Handle ISA memory hole if not already covered */
+        if (j <= 1 && !found_isa_hole && hose->isa_mem_size)
+                if (ppc4xx_setup_one_pcix_POM(hose, reg, hose->isa_mem_phys, 0,
+                                              hose->isa_mem_size, 0, j) == 0)
+                        printk(KERN_INFO "%s: Legacy ISA memory support enabled\n",
+                               hose->dn->full_name);
 }
 
 static void __init ppc4xx_configure_pcix_PIMs(struct pci_controller *hose,
@@ -1317,12 +1382,72 @@ static struct pci_ops ppc4xx_pciex_pci_ops =
         .write = ppc4xx_pciex_write_config,
 };
 
+static int __init ppc4xx_setup_one_pciex_POM(struct ppc4xx_pciex_port   *port,
+                                             struct pci_controller      *hose,
+                                             void __iomem               *mbase,
+                                             u64                        plb_addr,
+                                             u64                        pci_addr,
+                                             u64                        size,
+                                             unsigned int               flags,
+                                             int                        index)
+{
+        u32 lah, lal, pciah, pcial, sa;
+
+        if (!is_power_of_2(size) ||
+            (index < 2 && size < 0x100000) ||
+            (index == 2 && size < 0x100) ||
+            (plb_addr & (size - 1)) != 0) {
+                printk(KERN_WARNING "%s: Resource out of range\n",
+                       hose->dn->full_name);
+                return -1;
+        }
+
+        /* Calculate register values */
+        lah = RES_TO_U32_HIGH(plb_addr);
+        lal = RES_TO_U32_LOW(plb_addr);
+        pciah = RES_TO_U32_HIGH(pci_addr);
+        pcial = RES_TO_U32_LOW(pci_addr);
+        sa = (0xffffffffu << ilog2(size)) | 0x1;
+
+        /* Program register values */
+        switch (index) {
+        case 0:
+                out_le32(mbase + PECFG_POM0LAH, pciah);
+                out_le32(mbase + PECFG_POM0LAL, pcial);
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR1BAH, lah);
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR1BAL, lal);
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKH, 0x7fffffff);
+                /* Note that 3 here means enabled | single region */
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL, sa | 3);
+                break;
+        case 1:
+                out_le32(mbase + PECFG_POM1LAH, pciah);
+                out_le32(mbase + PECFG_POM1LAL, pcial);
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR2BAH, lah);
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR2BAL, lal);
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKH, 0x7fffffff);
+                /* Note that 3 here means enabled | single region */
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKL, sa | 3);
+                break;
+        case 2:
+                out_le32(mbase + PECFG_POM2LAH, pciah);
+                out_le32(mbase + PECFG_POM2LAL, pcial);
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR3BAH, lah);
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR3BAL, lal);
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKH, 0x7fffffff);
+                /* Note that 3 here means enabled | IO space !!! */
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKL, sa | 3);
+                break;
+        }
+
+        return 0;
+}
+
 static void __init ppc4xx_configure_pciex_POMs(struct ppc4xx_pciex_port *port,
                                                struct pci_controller *hose,
                                                void __iomem *mbase)
 {
-        u32 lah, lal, pciah, pcial, sa;
-        int i, j;
+        int i, j, found_isa_hole = 0;
 
         /* Setup outbound memory windows */
         for (i = j = 0; i < 3; i++) {
@@ -1337,53 +1462,38 @@ static void __init ppc4xx_configure_pciex_POMs(struct ppc4xx_pciex_port *port,
                         break;
                 }
 
-                /* Calculate register values */
-                lah = RES_TO_U32_HIGH(res->start);
-                lal = RES_TO_U32_LOW(res->start);
-                pciah = RES_TO_U32_HIGH(res->start - hose->pci_mem_offset);
-                pcial = RES_TO_U32_LOW(res->start - hose->pci_mem_offset);
-                sa = res->end + 1 - res->start;
-                if (!is_power_of_2(sa) || sa < 0x100000 ||
-                    sa > 0xffffffffu) {
-                        printk(KERN_WARNING "%s: Resource out of range\n",
-                               port->node->full_name);
-                        continue;
-                }
-                sa = (0xffffffffu << ilog2(sa)) | 0x1;
-
-                /* Program register values */
-                switch (j) {
-                case 0:
-                        out_le32(mbase + PECFG_POM0LAH, pciah);
-                        out_le32(mbase + PECFG_POM0LAL, pcial);
-                        dcr_write(port->dcrs, DCRO_PEGPL_OMR1BAH, lah);
-                        dcr_write(port->dcrs, DCRO_PEGPL_OMR1BAL, lal);
-                        dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKH, 0x7fffffff);
-                        dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL, sa | 3);
-                        break;
-                case 1:
-                        out_le32(mbase + PECFG_POM1LAH, pciah);
-                        out_le32(mbase + PECFG_POM1LAL, pcial);
-                        dcr_write(port->dcrs, DCRO_PEGPL_OMR2BAH, lah);
-                        dcr_write(port->dcrs, DCRO_PEGPL_OMR2BAL, lal);
-                        dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKH, 0x7fffffff);
-                        dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKL, sa | 3);
-                        break;
+                /* Configure the resource */
+                if (ppc4xx_setup_one_pciex_POM(port, hose, mbase,
+                                               res->start,
+                                               res->start - hose->pci_mem_offset,
+                                               res->end + 1 - res->start,
+                                               res->flags,
+                                               j) == 0) {
+                        j++;
+
+                        /* If the resource PCI address is 0 then we have our
+                         * ISA memory hole
+                         */
+                        if (res->start == hose->pci_mem_offset)
+                                found_isa_hole = 1;
                 }
-                j++;
         }
 
-        /* Configure IO, always 64K starting at 0 */
-        if (hose->io_resource.flags & IORESOURCE_IO) {
-                lah = RES_TO_U32_HIGH(hose->io_base_phys);
-                lal = RES_TO_U32_LOW(hose->io_base_phys);
-                out_le32(mbase + PECFG_POM2LAH, 0);
-                out_le32(mbase + PECFG_POM2LAL, 0);
-                dcr_write(port->dcrs, DCRO_PEGPL_OMR3BAH, lah);
-                dcr_write(port->dcrs, DCRO_PEGPL_OMR3BAL, lal);
-                dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKH, 0x7fffffff);
-                dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKL, 0xffff0000 | 3);
-        }
+        /* Handle ISA memory hole if not already covered */
+        if (j <= 1 && !found_isa_hole && hose->isa_mem_size)
+                if (ppc4xx_setup_one_pciex_POM(port, hose, mbase,
+                                               hose->isa_mem_phys, 0,
+                                               hose->isa_mem_size, 0, j) == 0)
+                        printk(KERN_INFO "%s: Legacy ISA memory support enabled\n",
+                               hose->dn->full_name);
+
+        /* Configure IO, always 64K starting at 0. We hard wire it to 64K !
+         * Note also that it -has- to be region index 2 on this HW
+         */
+        if (hose->io_resource.flags & IORESOURCE_IO)
+                ppc4xx_setup_one_pciex_POM(port, hose, mbase,
+                                           hose->io_base_phys, 0,
+                                           0x10000, IORESOURCE_IO, 2);
 }
 
 static void __init ppc4xx_configure_pciex_PIMs(struct ppc4xx_pciex_port *port,
diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index b3b73ae57d6d..01bce3784b0a 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/string.h>
+#include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/bootmem.h>
@@ -38,6 +39,8 @@ static void qe_snums_init(void);
 static int qe_sdma_init(void);
 
 static DEFINE_SPINLOCK(qe_lock);
+DEFINE_SPINLOCK(cmxgcr_lock);
+EXPORT_SYMBOL(cmxgcr_lock);
 
 /* QE snum state */
 enum qe_snum_state {
diff --git a/arch/powerpc/sysdev/qe_lib/ucc.c b/arch/powerpc/sysdev/qe_lib/ucc.c
index 1d78071aad7d..ebb442ea1917 100644
--- a/arch/powerpc/sysdev/qe_lib/ucc.c
+++ b/arch/powerpc/sysdev/qe_lib/ucc.c
@@ -18,6 +18,7 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/stddef.h>
+#include <linux/spinlock.h>
 #include <linux/module.h>
 
 #include <asm/irq.h>
@@ -26,9 +27,6 @@
 #include <asm/qe.h>
 #include <asm/ucc.h>
 
-DEFINE_SPINLOCK(cmxgcr_lock);
-EXPORT_SYMBOL(cmxgcr_lock);
-
 int ucc_set_qe_mux_mii_mng(unsigned int ucc_num)
 {
         unsigned long flags;
diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
index 51d97588e762..9cb03b71b9d6 100644
--- a/arch/powerpc/xmon/Makefile
+++ b/arch/powerpc/xmon/Makefile
@@ -4,7 +4,7 @@ ifdef CONFIG_PPC64
 EXTRA_CFLAGS += -mno-minimal-toc
 endif
 
-obj-y                   += xmon.o setjmp.o start.o nonstdio.o
+obj-y                   += xmon.o start.o nonstdio.o
 
 ifdef CONFIG_XMON_DISASSEMBLY
 obj-y                   += ppc-dis.o ppc-opc.o
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 076368c8b8a9..8dfad7d9a004 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -41,6 +41,7 @@
 #include <asm/spu_priv1.h>
 #include <asm/firmware.h>
 #include <asm/setjmp.h>
+#include <asm/reg.h>
 
 #ifdef CONFIG_PPC64
 #include <asm/hvcall.h>
@@ -159,8 +160,6 @@ static int xmon_no_auto_backtrace;
 extern void xmon_enter(void);
 extern void xmon_leave(void);
 
-extern void xmon_save_regs(struct pt_regs *);
-
 #ifdef CONFIG_PPC64
 #define REG             "%.16lx"
 #define REGS_PER_LINE   4
@@ -532,7 +531,7 @@ int xmon(struct pt_regs *excp)
         struct pt_regs regs;
 
         if (excp == NULL) {
-                xmon_save_regs(&regs);
+                ppc_save_regs(&regs);
                 excp = &regs;
         }