251 files changed, 2541 insertions, 1114 deletions
diff --git a/arch/alpha/include/asm/dma-mapping.h b/arch/alpha/include/asm/dma-mapping.h
index 4567aca6fdd6..dfa32f061320 100644
--- a/arch/alpha/include/asm/dma-mapping.h
+++ b/arch/alpha/include/asm/dma-mapping.h
@@ -12,16 +12,22 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 #include <asm-generic/dma-mapping-common.h>
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+#define dma_alloc_coherent(d,s,h,f)     dma_alloc_attrs(d,s,h,f,NULL)
-                                       dma_addr_t *dma_handle, gfp_t gfp)
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+                                    dma_addr_t *dma_handle, gfp_t gfp,
+                                    struct dma_attrs *attrs)
 {
-        return get_dma_ops(dev)->alloc_coherent(dev, size, dma_handle, gfp);
+        return get_dma_ops(dev)->alloc(dev, size, dma_handle, gfp, attrs);
 }
-static inline void dma_free_coherent(struct device *dev, size_t size,
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
-                                     void *vaddr, dma_addr_t dma_handle)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+                                  void *vaddr, dma_addr_t dma_handle,
+                                  struct dma_attrs *attrs)
 {
-        get_dma_ops(dev)->free_coherent(dev, size, vaddr, dma_handle);
+        get_dma_ops(dev)->free(dev, size, vaddr, dma_handle, attrs);
 }
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/alpha/kernel/pci-noop.c b/arch/alpha/kernel/pci-noop.c
index 04eea4894ef3..df24b76f9246 100644
--- a/arch/alpha/kernel/pci-noop.c
+++ b/arch/alpha/kernel/pci-noop.c
@@ -108,7 +108,8 @@ sys_pciconfig_write(unsigned long bus, unsigned long dfn,
 }
 static void *alpha_noop_alloc_coherent(struct device *dev, size_t size,
-                                       dma_addr_t *dma_handle, gfp_t gfp)
+                                       dma_addr_t *dma_handle, gfp_t gfp,
+                                       struct dma_attrs *attrs)
 {
        void *ret;
@@ -123,7 +124,8 @@ static void *alpha_noop_alloc_coherent(struct device *dev, size_t size,
 }
 static void alpha_noop_free_coherent(struct device *dev, size_t size,
-                                     void *cpu_addr, dma_addr_t dma_addr)
+                                     void *cpu_addr, dma_addr_t dma_addr,
+                                     struct dma_attrs *attrs)
 {
        free_pages((unsigned long)cpu_addr, get_order(size));
 }
@@ -174,8 +176,8 @@ static int alpha_noop_set_mask(struct device *dev, u64 mask)
 }
 struct dma_map_ops alpha_noop_ops = {
-        .alloc_coherent         = alpha_noop_alloc_coherent,
+        .alloc                  = alpha_noop_alloc_coherent,
-        .free_coherent          = alpha_noop_free_coherent,
+        .free                   = alpha_noop_free_coherent,
        .map_page               = alpha_noop_map_page,
        .map_sg                 = alpha_noop_map_sg,
        .mapping_error          = alpha_noop_mapping_error,
diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 43610804987d..cd634795aa9c 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -434,7 +434,8 @@ static void alpha_pci_unmap_page(struct device *dev, dma_addr_t dma_addr,
   else DMA_ADDRP is undefined.  */
 static void *alpha_pci_alloc_coherent(struct device *dev, size_t size,
-                                      dma_addr_t *dma_addrp, gfp_t gfp)
+                                      dma_addr_t *dma_addrp, gfp_t gfp,
+                                      struct dma_attrs *attrs)
 {
        struct pci_dev *pdev = alpha_gendev_to_pci(dev);
        void *cpu_addr;
@@ -478,7 +479,8 @@ try_again:
   DMA_ADDR past this call are illegal.  */
 static void alpha_pci_free_coherent(struct device *dev, size_t size,
-                                    void *cpu_addr, dma_addr_t dma_addr)
+                                    void *cpu_addr, dma_addr_t dma_addr,
+                                    struct dma_attrs *attrs)
 {
        struct pci_dev *pdev = alpha_gendev_to_pci(dev);
        pci_unmap_single(pdev, dma_addr, size, PCI_DMA_BIDIRECTIONAL);
@@ -952,8 +954,8 @@ static int alpha_pci_set_mask(struct device *dev, u64 mask)
 }
 struct dma_map_ops alpha_pci_ops = {
-        .alloc_coherent         = alpha_pci_alloc_coherent,
+        .alloc                  = alpha_pci_alloc_coherent,
-        .free_coherent          = alpha_pci_free_coherent,
+        .free                   = alpha_pci_free_coherent,
        .map_page               = alpha_pci_map_page,
        .unmap_page             = alpha_pci_unmap_page,
        .map_sg                 = alpha_pci_map_sg,
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index 6f7feb5db271..35f2ef44de12 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -120,12 +120,13 @@ SYSCALL_DEFINE5(rt_sigaction, int, sig, const struct sigaction __user *, act,
 */
 SYSCALL_DEFINE1(sigsuspend, old_sigset_t, mask)
 {
-        mask &= _BLOCKABLE;
+        sigset_t blocked;
-        spin_lock_irq(&current->sighand->siglock);
        current->saved_sigmask = current->blocked;
-        siginitset(&current->blocked, mask);
-        recalc_sigpending();
+        mask &= _BLOCKABLE;
-        spin_unlock_irq(&current->sighand->siglock);
+        siginitset(&blocked, mask);
+        set_current_blocked(&blocked);
        current->state = TASK_INTERRUPTIBLE;
        schedule();
@@ -238,10 +239,7 @@ do_sigreturn(struct sigcontext __user *sc, struct pt_regs *regs,
                goto give_sigsegv;
        sigdelsetmask(&set, ~_BLOCKABLE);
-        spin_lock_irq(&current->sighand->siglock);
+        set_current_blocked(&set);
-        current->blocked = set;
-        recalc_sigpending();
-        spin_unlock_irq(&current->sighand->siglock);
        if (restore_sigcontext(sc, regs, sw))
                goto give_sigsegv;
@@ -276,10 +274,7 @@ do_rt_sigreturn(struct rt_sigframe __user *frame, struct pt_regs *regs,
                goto give_sigsegv;
        sigdelsetmask(&set, ~_BLOCKABLE);
-        spin_lock_irq(&current->sighand->siglock);
+        set_current_blocked(&set);
-        current->blocked = set;
-        recalc_sigpending();
-        spin_unlock_irq(&current->sighand->siglock);
        if (restore_sigcontext(&frame->uc.uc_mcontext, regs, sw))
                goto give_sigsegv;
@@ -501,14 +496,8 @@ handle_signal(int sig, struct k_sigaction *ka, siginfo_t *info,
        else
                ret = setup_frame(sig, ka, oldset, regs, sw);
-        if (ret == 0) {
+        if (ret == 0)
-                spin_lock_irq(&current->sighand->siglock);
+                block_sigmask(ka, sig);
-                sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
-                if (!(ka->sa.sa_flags & SA_NODEFER)) 
-                        sigaddset(&current->blocked,sig);
-                recalc_sigpending();
-                spin_unlock_irq(&current->sighand->siglock);
-        }
        return ret;
 }
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 4087a569b43b..50d438db1f6b 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -450,7 +450,7 @@ setup_smp(void)
                smp_num_probed = 1;
        }
-        printk(KERN_INFO "SMP: %d CPUs probed -- cpu_present_map = %lx\n",
+        printk(KERN_INFO "SMP: %d CPUs probed -- cpu_present_mask = %lx\n",
               smp_num_probed, cpumask_bits(cpu_present_mask)[0]);
 }
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 93180845ae16..cf006d40342c 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -338,6 +338,7 @@ config ARCH_AT91
        select HAVE_CLK
        select CLKDEV_LOOKUP
        select IRQ_DOMAIN
+        select NEED_MACH_IO_H if PCCARD
        help
          This enables support for systems based on the Atmel AT91RM9200,
          AT91SAM9 processors.
diff --git a/arch/arm/boot/dts/at91sam9g20.dtsi b/arch/arm/boot/dts/at91sam9g20.dtsi
index 92f36627e7f8..799ad1889b51 100644
--- a/arch/arm/boot/dts/at91sam9g20.dtsi
+++ b/arch/arm/boot/dts/at91sam9g20.dtsi
@@ -35,7 +35,7 @@
                };
        };
-        memory@20000000 {
+        memory {
                reg = <0x20000000 0x08000000>;
        };
diff --git a/arch/arm/boot/dts/at91sam9g25ek.dts b/arch/arm/boot/dts/at91sam9g25ek.dts
index ac0dc0031dda..7829a4d0cb22 100644
--- a/arch/arm/boot/dts/at91sam9g25ek.dts
+++ b/arch/arm/boot/dts/at91sam9g25ek.dts
@@ -37,8 +37,8 @@
                usb0: ohci@00600000 {
                        status = "okay";
                        num-ports = <2>;
-                        atmel,vbus-gpio = <&pioD 19 0
+                        atmel,vbus-gpio = <&pioD 19 1
-                                           &pioD 20 0
+                                           &pioD 20 1
                                          >;
                };
diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi
index 3d0c32fb218f..9e6eb6ecea0e 100644
--- a/arch/arm/boot/dts/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/at91sam9g45.dtsi
@@ -36,7 +36,7 @@
                };
        };
-        memory@70000000 {
+        memory {
                reg = <0x70000000 0x10000000>;
        };
diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts
index c4c8ae4123d5..a3633bd13111 100644
--- a/arch/arm/boot/dts/at91sam9m10g45ek.dts
+++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts
@@ -17,7 +17,7 @@
                bootargs = "mem=64M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2";
        };
-        memory@70000000 {
+        memory {
                reg = <0x70000000 0x4000000>;
        };
@@ -73,8 +73,8 @@
                usb0: ohci@00700000 {
                        status = "okay";
                        num-ports = <2>;
-                        atmel,vbus-gpio = <&pioD 1 0
+                        atmel,vbus-gpio = <&pioD 1 1
-                                           &pioD 3 0>;
+                                           &pioD 3 1>;
                };
                usb1: ehci@00800000 {
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index c111001f254e..70ab3a4e026f 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -34,7 +34,7 @@
                };
        };
-        memory@20000000 {
+        memory {
                reg = <0x20000000 0x10000000>;
        };
@@ -201,8 +201,8 @@
                              >;
                        atmel,nand-addr-offset = <21>;
                        atmel,nand-cmd-offset = <22>;
-                        gpios = <&pioC 8 0
+                        gpios = <&pioD 5 0
-                                 &pioC 14 0
+                                 &pioD 4 0
                                 0
                                >;
                        status = "disabled";
diff --git a/arch/arm/boot/dts/at91sam9x5cm.dtsi b/arch/arm/boot/dts/at91sam9x5cm.dtsi
index 67936f83c694..31e7be23703d 100644
--- a/arch/arm/boot/dts/at91sam9x5cm.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5cm.dtsi
@@ -8,7 +8,7 @@
 */
 / {
-        memory@20000000 {
+        memory {
                reg = <0x20000000 0x8000000>;
        };
diff --git a/arch/arm/boot/dts/usb_a9g20.dts b/arch/arm/boot/dts/usb_a9g20.dts
index 3b3c4e0fa79f..7c2399c532e5 100644
--- a/arch/arm/boot/dts/usb_a9g20.dts
+++ b/arch/arm/boot/dts/usb_a9g20.dts
@@ -16,7 +16,7 @@
                bootargs = "mem=64M console=ttyS0,115200 root=/dev/mtdblock5 rw rootfstype=ubifs";
        };
-        memory@20000000 {
+        memory {
                reg = <0x20000000 0x4000000>;
        };
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 44f4a09ff37b..05112380dc53 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -2,6 +2,7 @@
 #define __ASM_BARRIER_H
 #ifndef __ASSEMBLY__
+#include <asm/outercache.h>
 #define nop() __asm__ __volatile__("mov\tr0,r0\t@ nop\n\t");
@@ -39,7 +40,6 @@
 #ifdef CONFIG_ARCH_HAS_BARRIERS
 #include <mach/barriers.h>
 #elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
-#include <asm/outercache.h>
 #define mb()            do { dsb(); outer_sync(); } while (0)
 #define rmb()           dsb()
 #define wmb()           mb()
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index df0ac0bb39aa..9af5563dd3eb 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -119,7 +119,7 @@ static inline void __iomem *__typesafe_io(unsigned long addr)
 #ifdef CONFIG_NEED_MACH_IO_H
 #include <mach/io.h>
 #else
-#define __io(a)         ({ (void)(a); __typesafe_io(0); })
+#define __io(a)         __typesafe_io((a) & IO_SPACE_LIMIT)
 #endif
 /*
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 632df9a66f8c..ede5f7741c42 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -299,7 +299,6 @@ static inline int pdev_bad_for_parity(struct pci_dev *dev)
 */
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
-        struct pci_sys_data *root = bus->sysdata;
        struct pci_dev *dev;
        u16 features = PCI_COMMAND_SERR | PCI_COMMAND_PARITY | PCI_COMMAND_FAST_BACK;
diff --git a/arch/arm/kernel/insn.c b/arch/arm/kernel/insn.c
index ab312e516546..b760340b7014 100644
--- a/arch/arm/kernel/insn.c
+++ b/arch/arm/kernel/insn.c
@@ -1,3 +1,4 @@
+#include <linux/bug.h>
 #include <linux/kernel.h>
 #include <asm/opcodes.h>
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index ab1869dac97a..4dd41fc9e235 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -152,7 +152,7 @@ int __kprobes __arch_disarm_kprobe(void *p)
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
-        stop_machine(__arch_disarm_kprobe, p, &cpu_online_map);
+        stop_machine(__arch_disarm_kprobe, p, cpu_online_mask);
 }
 void __kprobes arch_remove_kprobe(struct kprobe *p)
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 45956c9d0ef0..80abafb9bf33 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -256,7 +256,7 @@ static int ptrace_read_user(struct task_struct *tsk, unsigned long off,
 {
        unsigned long tmp;
-        if (off & 3 || off >= sizeof(struct user))
+        if (off & 3)
                return -EIO;
        tmp = 0;
@@ -268,6 +268,8 @@ static int ptrace_read_user(struct task_struct *tsk, unsigned long off,
                tmp = tsk->mm->end_code;
        else if (off < sizeof(struct pt_regs))
                tmp = get_user_reg(tsk, off >> 2);
+        else if (off >= sizeof(struct user))
+                return -EIO;
        return put_user(tmp, ret);
 }
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 2cee7d1eb958..addbbe8028c2 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -349,7 +349,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
                 * re-initialize the map in platform_smp_prepare_cpus() if
                 * present != possible (e.g. physical hotplug).
                 */
-                init_cpu_present(&cpu_possible_map);
+                init_cpu_present(cpu_possible_mask);
                /*
                 * Initialise the SCU if there are more than one CPU
@@ -581,8 +581,9 @@ void smp_send_stop(void)
        unsigned long timeout;
        if (num_online_cpus() > 1) {
-                cpumask_t mask = cpu_online_map;
+                struct cpumask mask;
-                cpu_clear(smp_processor_id(), mask);
+                cpumask_copy(&mask, cpu_online_mask);
+                cpumask_clear_cpu(smp_processor_id(), &mask);
                smp_cross_call(&mask, IPI_CPU_STOP);
        }
diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
index 7e5651ee9f85..5652dde4bbe2 100644
--- a/arch/arm/mach-at91/at91sam9260_devices.c
+++ b/arch/arm/mach-at91/at91sam9260_devices.c
@@ -598,6 +598,9 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
                else
                        cs_pin = spi1_standard_cs[devices[i].chip_select];
+                if (!gpio_is_valid(cs_pin))
+                        continue;
                if (devices[i].bus_num == 0)
                        enable_spi0 = 1;
                else
diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index 096da87dc00d..4db961a93085 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -415,6 +415,9 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
                else
                        cs_pin = spi1_standard_cs[devices[i].chip_select];
+                if (!gpio_is_valid(cs_pin))
+                        continue;
                if (devices[i].bus_num == 0)
                        enable_spi0 = 1;
                else
diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
index 53688c46f956..fe99206de880 100644
--- a/arch/arm/mach-at91/at91sam9263_devices.c
+++ b/arch/arm/mach-at91/at91sam9263_devices.c
@@ -72,7 +72,8 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data)
        /* Enable VBus control for UHP ports */
        for (i = 0; i < data->ports; i++) {
                if (gpio_is_valid(data->vbus_pin[i]))
-                        at91_set_gpio_output(data->vbus_pin[i], 0);
+                        at91_set_gpio_output(data->vbus_pin[i],
+                                             data->vbus_pin_active_low[i]);
        }
        /* Enable overcurrent notification */
@@ -671,6 +672,9 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
                else
                        cs_pin = spi1_standard_cs[devices[i].chip_select];
+                if (!gpio_is_valid(cs_pin))
+                        continue;
                if (devices[i].bus_num == 0)
                        enable_spi0 = 1;
                else
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index 698479f1e197..6b008aee1dff 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -127,12 +127,13 @@ void __init at91_add_device_usbh_ohci(struct at91_usbh_data *data)
        /* Enable VBus control for UHP ports */
        for (i = 0; i < data->ports; i++) {
                if (gpio_is_valid(data->vbus_pin[i]))
-                        at91_set_gpio_output(data->vbus_pin[i], 0);
+                        at91_set_gpio_output(data->vbus_pin[i],
+                                             data->vbus_pin_active_low[i]);
        }
        /* Enable overcurrent notification */
        for (i = 0; i < data->ports; i++) {
-                if (data->overcurrent_pin[i])
+                if (gpio_is_valid(data->overcurrent_pin[i]))
                        at91_set_gpio_input(data->overcurrent_pin[i], 1);
        }
@@ -188,7 +189,8 @@ void __init at91_add_device_usbh_ehci(struct at91_usbh_data *data)
        /* Enable VBus control for UHP ports */
        for (i = 0; i < data->ports; i++) {
                if (gpio_is_valid(data->vbus_pin[i]))
-                        at91_set_gpio_output(data->vbus_pin[i], 0);
+                        at91_set_gpio_output(data->vbus_pin[i],
+                                             data->vbus_pin_active_low[i]);
        }
        usbh_ehci_data = *data;
@@ -785,6 +787,9 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
                else
                        cs_pin = spi1_standard_cs[devices[i].chip_select];
+                if (!gpio_is_valid(cs_pin))
+                        continue;
                if (devices[i].bus_num == 0)
                        enable_spi0 = 1;
                else
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index eda72e83037d..fe4ae22e8561 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -419,6 +419,9 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
                else
                        cs_pin = spi_standard_cs[devices[i].chip_select];
+                if (!gpio_is_valid(cs_pin))
+                        continue;
                /* enable chip-select pin */
                at91_set_gpio_output(cs_pin, 1);
diff --git a/arch/arm/mach-at91/at91sam9x5.c b/arch/arm/mach-at91/at91sam9x5.c
index b6831eeb7b76..13c8cae60462 100644
--- a/arch/arm/mach-at91/at91sam9x5.c
+++ b/arch/arm/mach-at91/at91sam9x5.c
@@ -223,6 +223,8 @@ static struct clk_lookup periph_clocks_lookups[] = {
        CLKDEV_CON_DEV_ID("usart", "f8028000.serial", &usart3_clk),
        CLKDEV_CON_DEV_ID("t0_clk", "f8008000.timer", &tcb0_clk),
        CLKDEV_CON_DEV_ID("t0_clk", "f800c000.timer", &tcb0_clk),
+        CLKDEV_CON_DEV_ID("dma_clk", "ffffec00.dma-controller", &dma0_clk),
+        CLKDEV_CON_DEV_ID("dma_clk", "ffffee00.dma-controller", &dma1_clk),
        CLKDEV_CON_ID("pioA", &pioAB_clk),
        CLKDEV_CON_ID("pioB", &pioAB_clk),
        CLKDEV_CON_ID("pioC", &pioCD_clk),
diff --git a/arch/arm/mach-at91/board-sam9263ek.c b/arch/arm/mach-at91/board-sam9263ek.c
index 66f0ddf4b2ae..2ffe50f3a9e9 100644
--- a/arch/arm/mach-at91/board-sam9263ek.c
+++ b/arch/arm/mach-at91/board-sam9263ek.c
@@ -74,6 +74,7 @@ static void __init ek_init_early(void)
 static struct at91_usbh_data __initdata ek_usbh_data = {
        .ports          = 2,
        .vbus_pin       = { AT91_PIN_PA24, AT91_PIN_PA21 },
+        .vbus_pin_active_low = {1, 1},
        .overcurrent_pin= {-EINVAL, -EINVAL},
 };
diff --git a/arch/arm/mach-at91/board-sam9m10g45ek.c b/arch/arm/mach-at91/board-sam9m10g45ek.c
index e1bea73e6b30..c88e908ddd82 100644
--- a/arch/arm/mach-at91/board-sam9m10g45ek.c
+++ b/arch/arm/mach-at91/board-sam9m10g45ek.c
@@ -71,6 +71,7 @@ static void __init ek_init_early(void)
 static struct at91_usbh_data __initdata ek_usbh_hs_data = {
        .ports          = 2,
        .vbus_pin       = {AT91_PIN_PD1, AT91_PIN_PD3},
+        .vbus_pin_active_low = {1, 1},
        .overcurrent_pin= {-EINVAL, -EINVAL},
 };
diff --git a/arch/arm/mach-at91/include/mach/board.h b/arch/arm/mach-at91/include/mach/board.h
index 544a5d5ce416..49a821192c65 100644
--- a/arch/arm/mach-at91/include/mach/board.h
+++ b/arch/arm/mach-at91/include/mach/board.h
@@ -86,14 +86,15 @@ extern void __init at91_add_device_mci(short mmc_id, struct mci_platform_data *d
 extern void __init at91_add_device_eth(struct macb_platform_data *data);
 /* USB Host */
+#define AT91_MAX_USBH_PORTS     3
 struct at91_usbh_data {
-        u8              ports;          /* number of ports on root hub */
+        int             vbus_pin[AT91_MAX_USBH_PORTS];  /* port power-control pin */
-        int             vbus_pin[2];    /* port power-control pin */
+        int             overcurrent_pin[AT91_MAX_USBH_PORTS];
-        u8              vbus_pin_active_low[2];
+        u8              ports;                          /* number of ports on root hub */
        u8              overcurrent_supported;
-        int             overcurrent_pin[2];
+        u8              vbus_pin_active_low[AT91_MAX_USBH_PORTS];
-        u8              overcurrent_status[2];
+        u8              overcurrent_status[AT91_MAX_USBH_PORTS];
-        u8              overcurrent_changed[2];
+        u8              overcurrent_changed[AT91_MAX_USBH_PORTS];
 };
 extern void __init at91_add_device_usbh(struct at91_usbh_data *data);
 extern void __init at91_add_device_usbh_ohci(struct at91_usbh_data *data);
diff --git a/arch/arm/mach-at91/include/mach/io.h b/arch/arm/mach-at91/include/mach/io.h
new file mode 100644
index 000000000000..2d9ca0455745
--- /dev/null
+++ b/arch/arm/mach-at91/include/mach/io.h
@@ -0,0 +1,27 @@
+/*
+ * arch/arm/mach-at91/include/mach/io.h
+ *
+ *  Copyright (C) 2003 SAN People
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+#ifndef __ASM_ARCH_IO_H
+#define __ASM_ARCH_IO_H
+#define IO_SPACE_LIMIT          0xFFFFFFFF
+#define __io(a)                 __typesafe_io(a)
+#endif
diff --git a/arch/arm/mach-exynos/common.c b/arch/arm/mach-exynos/common.c
index e6cc50e94a58..8614aab47cc0 100644
--- a/arch/arm/mach-exynos/common.c
+++ b/arch/arm/mach-exynos/common.c
@@ -583,10 +583,11 @@ core_initcall(exynos_core_init);
 #ifdef CONFIG_CACHE_L2X0
 static int __init exynos4_l2x0_cache_init(void)
 {
+        int ret;
        if (soc_is_exynos5250())
                return 0;
-        int ret;
        ret = l2x0_of_init(L2_AUX_VAL, L2_AUX_MASK);
        if (!ret) {
                l2x0_regs_phys = virt_to_phys(&l2x0_saved_regs);
diff --git a/arch/arm/mach-exynos/dma.c b/arch/arm/mach-exynos/dma.c
index 3983abee4264..69aaa4503205 100644
--- a/arch/arm/mach-exynos/dma.c
+++ b/arch/arm/mach-exynos/dma.c
@@ -35,8 +35,6 @@
 #include <mach/irqs.h>
 #include <mach/dma.h>
-static u64 dma_dmamask = DMA_BIT_MASK(32);
 static u8 exynos4210_pdma0_peri[] = {
        DMACH_PCM0_RX,
        DMACH_PCM0_TX,
diff --git a/arch/arm/mach-exynos/include/mach/debug-macro.S b/arch/arm/mach-exynos/include/mach/debug-macro.S
index 6c857ff0b5d8..e0c86ea475e7 100644
--- a/arch/arm/mach-exynos/include/mach/debug-macro.S
+++ b/arch/arm/mach-exynos/include/mach/debug-macro.S
@@ -21,10 +21,9 @@
         */
        .macro addruart, rp, rv, tmp
-                mov     \rp, #0x10000000
+                mrc     p15, 0, \tmp, c0, c0, 0
-                ldr     \rp, [\rp, #0x0]
+                and     \tmp, \tmp, #0xf0
-                and     \rp, \rp, #0xf00000
+                teq     \tmp, #0xf0             @@ A15
-                teq     \rp, #0x500000          @@ EXYNOS5
                ldreq   \rp, =EXYNOS5_PA_UART
                movne   \rp, #EXYNOS4_PA_UART   @@ EXYNOS4
                ldr     \rv, =S3C_VA_UART
diff --git a/arch/arm/mach-exynos/include/mach/uncompress.h b/arch/arm/mach-exynos/include/mach/uncompress.h
index 493f4f365ddf..2979995d5a6a 100644
--- a/arch/arm/mach-exynos/include/mach/uncompress.h
+++ b/arch/arm/mach-exynos/include/mach/uncompress.h
@@ -20,9 +20,24 @@ volatile u8 *uart_base;
 #include <plat/uncompress.h>
+static unsigned int __raw_readl(unsigned int ptr)
+{
+        return *((volatile unsigned int *)ptr);
+}
 static void arch_detect_cpu(void)
 {
-        if (machine_is_smdk5250())
+        u32 chip_id = __raw_readl(EXYNOS_PA_CHIPID);
+        /*
+         * product_id is bits 31:12
+         *    bits 23:20 describe the exynosX family
+         *
+         */
+        chip_id >>= 20;
+        chip_id &= 0xf;
+        if (chip_id == 0x5)
                uart_base = (volatile u8 *)EXYNOS5_PA_UART + (S3C_UART_OFFSET * CONFIG_S3C_LOWLEVEL_UART_PORT);
        else
                uart_base = (volatile u8 *)EXYNOS4_PA_UART + (S3C_UART_OFFSET * CONFIG_S3C_LOWLEVEL_UART_PORT);
diff --git a/arch/arm/mach-imx/clock-imx27.c b/arch/arm/mach-imx/clock-imx27.c
index b9a95ed75553..98e04f5a87dd 100644
--- a/arch/arm/mach-imx/clock-imx27.c
+++ b/arch/arm/mach-imx/clock-imx27.c
@@ -662,6 +662,7 @@ static struct clk_lookup lookups[] = {
        _REGISTER_CLOCK(NULL, "dma", dma_clk)
        _REGISTER_CLOCK(NULL, "rtic", rtic_clk)
        _REGISTER_CLOCK(NULL, "brom", brom_clk)
+        _REGISTER_CLOCK(NULL, "emma", emma_clk)
        _REGISTER_CLOCK("m2m-emmaprp.0", NULL, emma_clk)
        _REGISTER_CLOCK(NULL, "slcdc", slcdc_clk)
        _REGISTER_CLOCK("imx27-fec.0", NULL, fec_clk)
diff --git a/arch/arm/mach-imx/clock-imx35.c b/arch/arm/mach-imx/clock-imx35.c
index 1e279af656ad..e56c1a83eee3 100644
--- a/arch/arm/mach-imx/clock-imx35.c
+++ b/arch/arm/mach-imx/clock-imx35.c
@@ -483,7 +483,7 @@ static struct clk_lookup lookups[] = {
        _REGISTER_CLOCK("imx2-wdt.0", NULL, wdog_clk)
        _REGISTER_CLOCK(NULL, "max", max_clk)
        _REGISTER_CLOCK(NULL, "audmux", audmux_clk)
-        _REGISTER_CLOCK(NULL, "csi", csi_clk)
+        _REGISTER_CLOCK("mx3-camera.0", NULL, csi_clk)
        _REGISTER_CLOCK(NULL, "iim", iim_clk)
        _REGISTER_CLOCK(NULL, "gpu2d", gpu2d_clk)
        _REGISTER_CLOCK("mxc_nand.0", NULL, nfc_clk)
diff --git a/arch/arm/mach-imx/mach-armadillo5x0.c b/arch/arm/mach-imx/mach-armadillo5x0.c
index 27bc27e6ea41..c650145d1646 100644
--- a/arch/arm/mach-imx/mach-armadillo5x0.c
+++ b/arch/arm/mach-imx/mach-armadillo5x0.c
@@ -38,6 +38,8 @@
 #include <linux/usb/otg.h>
 #include <linux/usb/ulpi.h>
 #include <linux/delay.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/fixed.h>
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
@@ -479,6 +481,11 @@ static struct platform_device *devices[] __initdata = {
        &armadillo5x0_smc911x_device,
 };
+static struct regulator_consumer_supply dummy_supplies[] = {
+        REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+        REGULATOR_SUPPLY("vddvario", "smsc911x"),
+};
 /*
 * Perform board specific initializations
 */
@@ -489,6 +496,8 @@ static void __init armadillo5x0_init(void)
        mxc_iomux_setup_multiple_pins(armadillo5x0_pins,
                        ARRAY_SIZE(armadillo5x0_pins), "armadillo5x0");
+        regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
        platform_add_devices(devices, ARRAY_SIZE(devices));
        imx_add_gpio_keys(&armadillo5x0_button_data);
        imx31_add_imx_i2c1(NULL);
diff --git a/arch/arm/mach-imx/mach-kzm_arm11_01.c b/arch/arm/mach-imx/mach-kzm_arm11_01.c
index fc78e8071cd1..15a26e908260 100644
--- a/arch/arm/mach-imx/mach-kzm_arm11_01.c
+++ b/arch/arm/mach-imx/mach-kzm_arm11_01.c
@@ -24,6 +24,8 @@
 #include <linux/serial_8250.h>
 #include <linux/smsc911x.h>
 #include <linux/types.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/fixed.h>
 #include <asm/irq.h>
 #include <asm/mach-types.h>
@@ -166,6 +168,11 @@ static struct platform_device kzm_smsc9118_device = {
                          },
 };
+static struct regulator_consumer_supply dummy_supplies[] = {
+        REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+        REGULATOR_SUPPLY("vddvario", "smsc911x"),
+};
 static int __init kzm_init_smsc9118(void)
 {
        /*
@@ -175,6 +182,8 @@ static int __init kzm_init_smsc9118(void)
        gpio_request(IOMUX_TO_GPIO(MX31_PIN_GPIO1_2), "smsc9118-int");
        gpio_direction_input(IOMUX_TO_GPIO(MX31_PIN_GPIO1_2));
+        regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
        return platform_device_register(&kzm_smsc9118_device);
 }
 #else
diff --git a/arch/arm/mach-imx/mach-mx31lilly.c b/arch/arm/mach-imx/mach-mx31lilly.c
index 02401bbd6d53..83714b0cc290 100644
--- a/arch/arm/mach-imx/mach-mx31lilly.c
+++ b/arch/arm/mach-imx/mach-mx31lilly.c
@@ -34,6 +34,8 @@
 #include <linux/mfd/mc13783.h>
 #include <linux/usb/otg.h>
 #include <linux/usb/ulpi.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/fixed.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -242,6 +244,11 @@ static struct platform_device *devices[] __initdata = {
 static int mx31lilly_baseboard;
 core_param(mx31lilly_baseboard, mx31lilly_baseboard, int, 0444);
+static struct regulator_consumer_supply dummy_supplies[] = {
+        REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+        REGULATOR_SUPPLY("vddvario", "smsc911x"),
+};
 static void __init mx31lilly_board_init(void)
 {
        imx31_soc_init();
@@ -280,6 +287,8 @@ static void __init mx31lilly_board_init(void)
        imx31_add_spi_imx1(&spi1_pdata);
        spi_register_board_info(&mc13783_dev, 1);
+        regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
        platform_add_devices(devices, ARRAY_SIZE(devices));
        /* USB */
diff --git a/arch/arm/mach-imx/mach-mx31lite.c b/arch/arm/mach-imx/mach-mx31lite.c
index ef80751712e7..0abef5f13df5 100644
--- a/arch/arm/mach-imx/mach-mx31lite.c
+++ b/arch/arm/mach-imx/mach-mx31lite.c
@@ -29,6 +29,8 @@
 #include <linux/usb/ulpi.h>
 #include <linux/mtd/physmap.h>
 #include <linux/delay.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/fixed.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -226,6 +228,11 @@ void __init mx31lite_map_io(void)
 static int mx31lite_baseboard;
 core_param(mx31lite_baseboard, mx31lite_baseboard, int, 0444);
+static struct regulator_consumer_supply dummy_supplies[] = {
+        REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+        REGULATOR_SUPPLY("vddvario", "smsc911x"),
+};
 static void __init mx31lite_init(void)
 {
        int ret;
@@ -259,6 +266,8 @@ static void __init mx31lite_init(void)
        if (usbh2_pdata.otg)
                imx31_add_mxc_ehci_hs(2, &usbh2_pdata);
+        regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
        /* SMSC9117 IRQ pin */
        ret = gpio_request(IOMUX_TO_GPIO(MX31_PIN_SFS6), "sms9117-irq");
        if (ret)
diff --git a/arch/arm/mach-imx/mach-mx35_3ds.c b/arch/arm/mach-imx/mach-mx35_3ds.c
index e14291d89e4f..6ae51c6b95b7 100644
--- a/arch/arm/mach-imx/mach-mx35_3ds.c
+++ b/arch/arm/mach-imx/mach-mx35_3ds.c
@@ -97,7 +97,7 @@ static struct i2c_board_info __initdata i2c_devices_3ds[] = {
 static int lcd_power_gpio = -ENXIO;
 static int mc9s08dz60_gpiochip_match(struct gpio_chip *chip,
-                                                     void *data)
+                                                     const void *data)
 {
        return !strcmp(chip->label, data);
 }
diff --git a/arch/arm/mach-imx/mach-mx53_ard.c b/arch/arm/mach-imx/mach-mx53_ard.c
index 753f4fc9ec04..05641980dc5e 100644
--- a/arch/arm/mach-imx/mach-mx53_ard.c
+++ b/arch/arm/mach-imx/mach-mx53_ard.c
@@ -23,6 +23,8 @@
 #include <linux/delay.h>
 #include <linux/gpio.h>
 #include <linux/smsc911x.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/fixed.h>
 #include <mach/common.h>
 #include <mach/hardware.h>
@@ -214,6 +216,11 @@ static int weim_cs_config(void)
        return 0;
 }
+static struct regulator_consumer_supply dummy_supplies[] = {
+        REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+        REGULATOR_SUPPLY("vddvario", "smsc911x"),
+};
 void __init imx53_ard_common_init(void)
 {
        mxc_iomux_v3_setup_multiple_pads(mx53_ard_pads,
@@ -232,6 +239,7 @@ static void __init mx53_ard_board_init(void)
        imx53_ard_common_init();
        mx53_ard_io_init();
+        regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
        platform_add_devices(devices, ARRAY_SIZE(devices));
        imx53_add_sdhci_esdhc_imx(0, &mx53_ard_sd1_data);
diff --git a/arch/arm/mach-msm/include/mach/uncompress.h b/arch/arm/mach-msm/include/mach/uncompress.h
index 169a84007456..c14011fe832d 100644
--- a/arch/arm/mach-msm/include/mach/uncompress.h
+++ b/arch/arm/mach-msm/include/mach/uncompress.h
@@ -16,6 +16,7 @@
 #ifndef __ASM_ARCH_MSM_UNCOMPRESS_H
 #define __ASM_ARCH_MSM_UNCOMPRESS_H
+#include <asm/barrier.h>
 #include <asm/processor.h>
 #include <mach/msm_iomap.h>
diff --git a/arch/arm/mach-msm/smd_debug.c b/arch/arm/mach-msm/smd_debug.c
index 0c56a5aaf588..c56df9e932ae 100644
--- a/arch/arm/mach-msm/smd_debug.c
+++ b/arch/arm/mach-msm/smd_debug.c
@@ -203,15 +203,9 @@ static ssize_t debug_read(struct file *file, char __user *buf,
        return simple_read_from_buffer(buf, count, ppos, debug_buffer, bsize);
 }
-static int debug_open(struct inode *inode, struct file *file)
-{
-        file->private_data = inode->i_private;
-        return 0;
-}
 static const struct file_operations debug_ops = {
        .read = debug_read,
-        .open = debug_open,
+        .open = simple_open,
        .llseek = default_llseek,
 };
diff --git a/arch/arm/mach-omap1/include/mach/io.h b/arch/arm/mach-omap1/include/mach/io.h
new file mode 100644
index 000000000000..ce4f8005b26f
--- /dev/null
+++ b/arch/arm/mach-omap1/include/mach/io.h
@@ -0,0 +1,45 @@
+/*
+ * arch/arm/mach-omap1/include/mach/io.h
+ *
+ * IO definitions for TI OMAP processors and boards
+ *
+ * Copied from arch/arm/mach-sa1100/include/mach/io.h
+ * Copyright (C) 1997-1999 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
+ * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
+ * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
+ * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Modifications:
+ *  06-12-1997  RMK     Created.
+ *  07-04-1999  RMK     Major cleanup
+ */
+#ifndef __ASM_ARM_ARCH_IO_H
+#define __ASM_ARM_ARCH_IO_H
+#define IO_SPACE_LIMIT 0xffffffff
+/*
+ * We don't actually have real ISA nor PCI buses, but there is so many
+ * drivers out there that might just work if we fake them...
+ */
+#define __io(a)         __typesafe_io(a)
+#endif
diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c
index 41b0a2fe0b04..909a8b91b564 100644
--- a/arch/arm/mach-omap2/board-cm-t35.c
+++ b/arch/arm/mach-omap2/board-cm-t35.c
@@ -26,6 +26,7 @@
 #include <linux/i2c/at24.h>
 #include <linux/i2c/twl.h>
+#include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
 #include <linux/mmc/host.h>
@@ -81,8 +82,23 @@ static struct omap_smsc911x_platform_data sb_t35_smsc911x_cfg = {
        .flags          = SMSC911X_USE_32BIT | SMSC911X_SAVE_MAC_ADDRESS,
 };
+static struct regulator_consumer_supply cm_t35_smsc911x_supplies[] = {
+        REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+        REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
+static struct regulator_consumer_supply sb_t35_smsc911x_supplies[] = {
+        REGULATOR_SUPPLY("vddvario", "smsc911x.1"),
+        REGULATOR_SUPPLY("vdd33a", "smsc911x.1"),
+};
 static void __init cm_t35_init_ethernet(void)
 {
+        regulator_register_fixed(0, cm_t35_smsc911x_supplies,
+                                 ARRAY_SIZE(cm_t35_smsc911x_supplies));
+        regulator_register_fixed(1, sb_t35_smsc911x_supplies,
+                                 ARRAY_SIZE(sb_t35_smsc911x_supplies));
        gpmc_smsc911x_init(&cm_t35_smsc911x_cfg);
        gpmc_smsc911x_init(&sb_t35_smsc911x_cfg);
 }
diff --git a/arch/arm/mach-omap2/board-igep0020.c b/arch/arm/mach-omap2/board-igep0020.c
index e558800adfdf..930c0d380435 100644
--- a/arch/arm/mach-omap2/board-igep0020.c
+++ b/arch/arm/mach-omap2/board-igep0020.c
@@ -634,8 +634,14 @@ static void __init igep_wlan_bt_init(void)
 static inline void __init igep_wlan_bt_init(void) { }
 #endif
+static struct regulator_consumer_supply dummy_supplies[] = {
+        REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+        REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
 static void __init igep_init(void)
 {
+        regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
        omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
        /* Get IGEP2 hardware revision */
diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c
index d50a562adfa0..1b6049567ab4 100644
--- a/arch/arm/mach-omap2/board-ldp.c
+++ b/arch/arm/mach-omap2/board-ldp.c
@@ -22,6 +22,7 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/spi/spi.h>
+#include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
 #include <linux/i2c/twl.h>
 #include <linux/io.h>
@@ -410,8 +411,14 @@ static struct mtd_partition ldp_nand_partitions[] = {
 };
+static struct regulator_consumer_supply dummy_supplies[] = {
+        REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+        REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
 static void __init omap_ldp_init(void)
 {
+        regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
        omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
        ldp_init_smsc911x();
        omap_i2c_init();
diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c
index 4c90f078abe1..49df12735b41 100644
--- a/arch/arm/mach-omap2/board-omap3evm.c
+++ b/arch/arm/mach-omap2/board-omap3evm.c
@@ -114,15 +114,6 @@ static struct omap_smsc911x_platform_data smsc911x_cfg = {
 static inline void __init omap3evm_init_smsc911x(void)
 {
-        struct clk *l3ck;
-        unsigned int rate;
-        l3ck = clk_get(NULL, "l3_ck");
-        if (IS_ERR(l3ck))
-                rate = 100000000;
-        else
-                rate = clk_get_rate(l3ck);
        /* Configure ethernet controller reset gpio */
        if (cpu_is_omap3430()) {
                if (get_omap3_evm_rev() == OMAP3EVM_BOARD_GEN_1)
@@ -632,9 +623,15 @@ static void __init omap3_evm_wl12xx_init(void)
 #endif
 }
+static struct regulator_consumer_supply dummy_supplies[] = {
+        REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+        REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
 static void __init omap3_evm_init(void)
 {
        omap3_evm_get_revision();
+        regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
        if (cpu_is_omap3630())
                omap3_mux_init(omap36x_board_mux, OMAP_PACKAGE_CBB);
diff --git a/arch/arm/mach-omap2/board-omap3logic.c b/arch/arm/mach-omap2/board-omap3logic.c
index 4a7d8c8a75da..9b3c141ff51b 100644
--- a/arch/arm/mach-omap2/board-omap3logic.c
+++ b/arch/arm/mach-omap2/board-omap3logic.c
@@ -23,6 +23,7 @@
 #include <linux/io.h>
 #include <linux/gpio.h>
+#include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
 #include <linux/i2c/twl.h>
@@ -188,8 +189,14 @@ static struct omap_board_mux board_mux[] __initdata = {
 };
 #endif
+static struct regulator_consumer_supply dummy_supplies[] = {
+        REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+        REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
 static void __init omap3logic_init(void)
 {
+        regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
        omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
        omap3torpedo_fix_pbias_voltage();
        omap3logic_i2c_init();
diff --git a/arch/arm/mach-omap2/board-omap3stalker.c b/arch/arm/mach-omap2/board-omap3stalker.c
index 641004380795..4dffc95bddd2 100644
--- a/arch/arm/mach-omap2/board-omap3stalker.c
+++ b/arch/arm/mach-omap2/board-omap3stalker.c
@@ -24,6 +24,7 @@
 #include <linux/input.h>
 #include <linux/gpio_keys.h>
+#include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
 #include <linux/i2c/twl.h>
 #include <linux/mmc/host.h>
@@ -72,15 +73,6 @@ static struct omap_smsc911x_platform_data smsc911x_cfg = {
 static inline void __init omap3stalker_init_eth(void)
 {
-        struct clk *l3ck;
-        unsigned int rate;
-        l3ck = clk_get(NULL, "l3_ck");
-        if (IS_ERR(l3ck))
-                rate = 100000000;
-        else
-                rate = clk_get_rate(l3ck);
        omap_mux_init_gpio(19, OMAP_PIN_INPUT_PULLUP);
        gpmc_smsc911x_init(&smsc911x_cfg);
 }
@@ -419,8 +411,14 @@ static struct omap_board_mux board_mux[] __initdata = {
 };
 #endif
+static struct regulator_consumer_supply dummy_supplies[] = {
+        REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+        REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
 static void __init omap3_stalker_init(void)
 {
+        regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
        omap3_mux_init(board_mux, OMAP_PACKAGE_CUS);
        omap_board_config = omap3_stalker_config;
        omap_board_config_size = ARRAY_SIZE(omap3_stalker_config);
diff --git a/arch/arm/mach-omap2/board-overo.c b/arch/arm/mach-omap2/board-overo.c
index 668533e2a379..33aa3910b09e 100644
--- a/arch/arm/mach-omap2/board-overo.c
+++ b/arch/arm/mach-omap2/board-overo.c
@@ -498,10 +498,18 @@ static struct gpio overo_bt_gpios[] __initdata = {
        { OVERO_GPIO_BT_NRESET, GPIOF_OUT_INIT_HIGH,    "lcd bl enable" },
 };
+static struct regulator_consumer_supply dummy_supplies[] = {
+        REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+        REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+        REGULATOR_SUPPLY("vddvario", "smsc911x.1"),
+        REGULATOR_SUPPLY("vdd33a", "smsc911x.1"),
+};
 static void __init overo_init(void)
 {
        int ret;
+        regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
        omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
        omap_hsmmc_init(mmc);
        overo_i2c_init();
diff --git a/arch/arm/mach-omap2/board-zoom-debugboard.c b/arch/arm/mach-omap2/board-zoom-debugboard.c
index 1e8540eabde9..f64f44173061 100644
--- a/arch/arm/mach-omap2/board-zoom-debugboard.c
+++ b/arch/arm/mach-omap2/board-zoom-debugboard.c
@@ -14,6 +14,9 @@
 #include <linux/smsc911x.h>
 #include <linux/interrupt.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
 #include <plat/gpmc.h>
 #include <plat/gpmc-smsc911x.h>
@@ -117,11 +120,17 @@ static struct platform_device *zoom_devices[] __initdata = {
        &zoom_debugboard_serial_device,
 };
+static struct regulator_consumer_supply dummy_supplies[] = {
+        REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
+        REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
+};
 int __init zoom_debugboard_init(void)
 {
        if (!omap_zoom_debugboard_detect())
                return 0;
+        regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
        zoom_init_smsc911x();
        zoom_init_quaduart();
        return platform_add_devices(zoom_devices, ARRAY_SIZE(zoom_devices));
diff --git a/arch/arm/mach-omap2/clock3xxx_data.c b/arch/arm/mach-omap2/clock3xxx_data.c
index 480fb8f09aed..f4a626f7c79e 100644
--- a/arch/arm/mach-omap2/clock3xxx_data.c
+++ b/arch/arm/mach-omap2/clock3xxx_data.c
@@ -747,7 +747,7 @@ static struct clk dpll4_m3_ck = {
        .parent         = &dpll4_ck,
        .init           = &omap2_init_clksel_parent,
        .clksel_reg     = OMAP_CM_REGADDR(OMAP3430_DSS_MOD, CM_CLKSEL),
-        .clksel_mask    = OMAP3430_CLKSEL_TV_MASK,
+        .clksel_mask    = OMAP3630_CLKSEL_TV_MASK,
        .clksel         = dpll4_clksel,
        .clkdm_name     = "dpll4_clkdm",
        .recalc         = &omap2_clksel_recalc,
@@ -832,7 +832,7 @@ static struct clk dpll4_m4_ck = {
        .parent         = &dpll4_ck,
        .init           = &omap2_init_clksel_parent,
        .clksel_reg     = OMAP_CM_REGADDR(OMAP3430_DSS_MOD, CM_CLKSEL),
-        .clksel_mask    = OMAP3430_CLKSEL_DSS1_MASK,
+        .clksel_mask    = OMAP3630_CLKSEL_DSS1_MASK,
        .clksel         = dpll4_clksel,
        .clkdm_name     = "dpll4_clkdm",
        .recalc         = &omap2_clksel_recalc,
@@ -859,7 +859,7 @@ static struct clk dpll4_m5_ck = {
        .parent         = &dpll4_ck,
        .init           = &omap2_init_clksel_parent,
        .clksel_reg     = OMAP_CM_REGADDR(OMAP3430_CAM_MOD, CM_CLKSEL),
-        .clksel_mask    = OMAP3430_CLKSEL_CAM_MASK,
+        .clksel_mask    = OMAP3630_CLKSEL_CAM_MASK,
        .clksel         = dpll4_clksel,
        .clkdm_name     = "dpll4_clkdm",
        .set_rate       = &omap2_clksel_set_rate,
@@ -886,7 +886,7 @@ static struct clk dpll4_m6_ck = {
        .parent         = &dpll4_ck,
        .init           = &omap2_init_clksel_parent,
        .clksel_reg     = OMAP_CM_REGADDR(OMAP3430_EMU_MOD, CM_CLKSEL1),
-        .clksel_mask    = OMAP3430_DIV_DPLL4_MASK,
+        .clksel_mask    = OMAP3630_DIV_DPLL4_MASK,
        .clksel         = dpll4_clksel,
        .clkdm_name     = "dpll4_clkdm",
        .recalc         = &omap2_clksel_recalc,
@@ -1394,6 +1394,7 @@ static struct clk cpefuse_fck = {
        .name           = "cpefuse_fck",
        .ops            = &clkops_omap2_dflt,
        .parent         = &sys_ck,
+        .clkdm_name     = "core_l4_clkdm",
        .enable_reg     = OMAP_CM_REGADDR(CORE_MOD, OMAP3430ES2_CM_FCLKEN3),
        .enable_bit     = OMAP3430ES2_EN_CPEFUSE_SHIFT,
        .recalc         = &followparent_recalc,
@@ -1403,6 +1404,7 @@ static struct clk ts_fck = {
        .name           = "ts_fck",
        .ops            = &clkops_omap2_dflt,
        .parent         = &omap_32k_fck,
+        .clkdm_name     = "core_l4_clkdm",
        .enable_reg     = OMAP_CM_REGADDR(CORE_MOD, OMAP3430ES2_CM_FCLKEN3),
        .enable_bit     = OMAP3430ES2_EN_TS_SHIFT,
        .recalc         = &followparent_recalc,
@@ -1412,6 +1414,7 @@ static struct clk usbtll_fck = {
        .name           = "usbtll_fck",
        .ops            = &clkops_omap2_dflt_wait,
        .parent         = &dpll5_m2_ck,
+        .clkdm_name     = "core_l4_clkdm",
        .enable_reg     = OMAP_CM_REGADDR(CORE_MOD, OMAP3430ES2_CM_FCLKEN3),
        .enable_bit     = OMAP3430ES2_EN_USBTLL_SHIFT,
        .recalc         = &followparent_recalc,
@@ -1617,6 +1620,7 @@ static struct clk fshostusb_fck = {
        .name           = "fshostusb_fck",
        .ops            = &clkops_omap2_dflt_wait,
        .parent         = &core_48m_fck,
+        .clkdm_name     = "core_l4_clkdm",
        .enable_reg     = OMAP_CM_REGADDR(CORE_MOD, CM_FCLKEN1),
        .enable_bit     = OMAP3430ES1_EN_FSHOSTUSB_SHIFT,
        .recalc         = &followparent_recalc,
@@ -2043,6 +2047,7 @@ static struct clk omapctrl_ick = {
        .enable_reg     = OMAP_CM_REGADDR(CORE_MOD, CM_ICLKEN1),
        .enable_bit     = OMAP3430_EN_OMAPCTRL_SHIFT,
        .flags          = ENABLE_ON_INIT,
+        .clkdm_name     = "core_l4_clkdm",
        .recalc         = &followparent_recalc,
 };
@@ -2094,6 +2099,7 @@ static struct clk usb_l4_ick = {
        .clksel_reg     = OMAP_CM_REGADDR(CORE_MOD, CM_CLKSEL),
        .clksel_mask    = OMAP3430ES1_CLKSEL_FSHOSTUSB_MASK,
        .clksel         = usb_l4_clksel,
+        .clkdm_name     = "core_l4_clkdm",
        .recalc         = &omap2_clksel_recalc,
 };
@@ -3467,8 +3473,8 @@ static struct omap_clk omap3xxx_clks[] = {
        CLK(NULL,       "ipss_ick",     &ipss_ick,      CK_AM35XX),
        CLK(NULL,       "rmii_ck",      &rmii_ck,       CK_AM35XX),
        CLK(NULL,       "pclk_ck",      &pclk_ck,       CK_AM35XX),
-        CLK("davinci_emac",     "emac_clk",     &emac_ick,      CK_AM35XX),
+        CLK("davinci_emac",     NULL,   &emac_ick,      CK_AM35XX),
-        CLK("davinci_emac",     "phy_clk",      &emac_fck,      CK_AM35XX),
+        CLK("davinci_mdio.0",   NULL,   &emac_fck,      CK_AM35XX),
        CLK("vpfe-capture",     "master",       &vpfe_ick,      CK_AM35XX),
        CLK("vpfe-capture",     "slave",        &vpfe_fck,      CK_AM35XX),
        CLK("musb-am35x",       "ick",          &hsotgusb_ick_am35xx,   CK_AM35XX),
diff --git a/arch/arm/mach-omap2/clock44xx_data.c b/arch/arm/mach-omap2/clock44xx_data.c
index c03c1108468e..fa6ea65ad44b 100644
--- a/arch/arm/mach-omap2/clock44xx_data.c
+++ b/arch/arm/mach-omap2/clock44xx_data.c
@@ -957,8 +957,8 @@ static struct dpll_data dpll_usb_dd = {
        .modes          = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
        .autoidle_reg   = OMAP4430_CM_AUTOIDLE_DPLL_USB,
        .idlest_reg     = OMAP4430_CM_IDLEST_DPLL_USB,
-        .mult_mask      = OMAP4430_DPLL_MULT_MASK,
+        .mult_mask      = OMAP4430_DPLL_MULT_USB_MASK,
-        .div1_mask      = OMAP4430_DPLL_DIV_MASK,
+        .div1_mask      = OMAP4430_DPLL_DIV_0_7_MASK,
        .enable_mask    = OMAP4430_DPLL_EN_MASK,
        .autoidle_mask  = OMAP4430_AUTO_DPLL_MODE_MASK,
        .idlest_mask    = OMAP4430_ST_DPLL_CLK_MASK,
@@ -978,6 +978,7 @@ static struct clk dpll_usb_ck = {
        .recalc         = &omap3_dpll_recalc,
        .round_rate     = &omap2_dpll_round_rate,
        .set_rate       = &omap3_noncore_dpll_set_rate,
+        .clkdm_name     = "l3_init_clkdm",
 };
 static struct clk dpll_usb_clkdcoldo_ck = {
diff --git a/arch/arm/mach-omap2/clockdomains44xx_data.c b/arch/arm/mach-omap2/clockdomains44xx_data.c
index 9299ac291d28..bd7ed13515cc 100644
--- a/arch/arm/mach-omap2/clockdomains44xx_data.c
+++ b/arch/arm/mach-omap2/clockdomains44xx_data.c
@@ -390,7 +390,7 @@ static struct clockdomain emu_sys_44xx_clkdm = {
        .prcm_partition   = OMAP4430_PRM_PARTITION,
        .cm_inst          = OMAP4430_PRM_EMU_CM_INST,
        .clkdm_offs       = OMAP4430_PRM_EMU_CM_EMU_CDOFFS,
-        .flags            = CLKDM_CAN_HWSUP,
+        .flags            = CLKDM_CAN_ENABLE_AUTO | CLKDM_CAN_FORCE_WAKEUP,
 };
 static struct clockdomain l3_dma_44xx_clkdm = {
diff --git a/arch/arm/mach-omap2/gpmc-smsc911x.c b/arch/arm/mach-omap2/gpmc-smsc911x.c
index 5e5880d6d099..b6c77be3e8f7 100644
--- a/arch/arm/mach-omap2/gpmc-smsc911x.c
+++ b/arch/arm/mach-omap2/gpmc-smsc911x.c
@@ -19,15 +19,11 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/smsc911x.h>
-#include <linux/regulator/fixed.h>
-#include <linux/regulator/machine.h>
 #include <plat/board.h>
 #include <plat/gpmc.h>
 #include <plat/gpmc-smsc911x.h>
-static struct omap_smsc911x_platform_data *gpmc_cfg;
 static struct resource gpmc_smsc911x_resources[] = {
        [0] = {
                .flags          = IORESOURCE_MEM,
@@ -41,51 +37,6 @@ static struct smsc911x_platform_config gpmc_smsc911x_config = {
        .phy_interface  = PHY_INTERFACE_MODE_MII,
        .irq_polarity   = SMSC911X_IRQ_POLARITY_ACTIVE_LOW,
        .irq_type       = SMSC911X_IRQ_TYPE_OPEN_DRAIN,
-        .flags          = SMSC911X_USE_16BIT,
-};
-static struct regulator_consumer_supply gpmc_smsc911x_supply[] = {
-        REGULATOR_SUPPLY("vddvario", "smsc911x.0"),
-        REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
-};
-/* Generic regulator definition to satisfy smsc911x */
-static struct regulator_init_data gpmc_smsc911x_reg_init_data = {
-        .constraints = {
-                .min_uV                 = 3300000,
-                .max_uV                 = 3300000,
-                .valid_modes_mask       = REGULATOR_MODE_NORMAL
-                                        | REGULATOR_MODE_STANDBY,
-                .valid_ops_mask         = REGULATOR_CHANGE_MODE
-                                        | REGULATOR_CHANGE_STATUS,
-        },
-        .num_consumer_supplies  = ARRAY_SIZE(gpmc_smsc911x_supply),
-        .consumer_supplies      = gpmc_smsc911x_supply,
-};
-static struct fixed_voltage_config gpmc_smsc911x_fixed_reg_data = {
-        .supply_name            = "gpmc_smsc911x",
-        .microvolts             = 3300000,
-        .gpio                   = -EINVAL,
-        .startup_delay          = 0,
-        .enable_high            = 0,
-        .enabled_at_boot        = 1,
-        .init_data              = &gpmc_smsc911x_reg_init_data,
-};
-/*
- * Platform device id of 42 is a temporary fix to avoid conflicts
- * with other reg-fixed-voltage devices. The real fix should
- * involve the driver core providing a way of dynamically
- * assigning a unique id on registration for platform devices
- * in the same name space.
- */
-static struct platform_device gpmc_smsc911x_regulator = {
-        .name           = "reg-fixed-voltage",
-        .id             = 42,
-        .dev = {
-                .platform_data  = &gpmc_smsc911x_fixed_reg_data,
-        },
 };
 /*
@@ -93,23 +44,12 @@ static struct platform_device gpmc_smsc911x_regulator = {
 * assume that pin multiplexing is done in the board-*.c file,
 * or in the bootloader.
 */
-void __init gpmc_smsc911x_init(struct omap_smsc911x_platform_data *board_data)
+void __init gpmc_smsc911x_init(struct omap_smsc911x_platform_data *gpmc_cfg)
 {
        struct platform_device *pdev;
        unsigned long cs_mem_base;
        int ret;
-        gpmc_cfg = board_data;
-        if (!gpmc_cfg->id) {
-                ret = platform_device_register(&gpmc_smsc911x_regulator);
-                if (ret < 0) {
-                        pr_err("Unable to register smsc911x regulators: %d\n",
-                               ret);
-                        return;
-                }
-        }
        if (gpmc_cs_request(gpmc_cfg->cs, SZ_16M, &cs_mem_base) < 0) {
                pr_err("Failed to request GPMC mem region\n");
                return;
@@ -139,8 +79,7 @@ void __init gpmc_smsc911x_init(struct omap_smsc911x_platform_data *board_data)
                gpio_set_value(gpmc_cfg->gpio_reset, 1);
        }
-        if (gpmc_cfg->flags)
+        gpmc_smsc911x_config.flags = gpmc_cfg->flags ? : SMSC911X_USE_16BIT;
-                gpmc_smsc911x_config.flags = gpmc_cfg->flags;
        pdev = platform_device_register_resndata(NULL, "smsc911x", gpmc_cfg->id,
                 gpmc_smsc911x_resources, ARRAY_SIZE(gpmc_smsc911x_resources),
diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c
index 100db6217f39..b0268eaffe13 100644
--- a/arch/arm/mach-omap2/hsmmc.c
+++ b/arch/arm/mach-omap2/hsmmc.c
@@ -506,6 +506,13 @@ static void __init omap_hsmmc_init_one(struct omap2_hsmmc_info *hsmmcinfo,
        if (oh->dev_attr != NULL) {
                mmc_dev_attr = oh->dev_attr;
                mmc_data->controller_flags = mmc_dev_attr->flags;
+                /*
+                 * erratum 2.1.1.128 doesn't apply if board has
+                 * a transceiver is attached
+                 */
+                if (hsmmcinfo->transceiver)
+                        mmc_data->controller_flags &=
+                                ~OMAP_HSMMC_BROKEN_MULTIBLOCK_READ;
        }
        pdev = platform_device_alloc(name, ctrl_nr - 1);
diff --git a/arch/arm/mach-omap2/include/mach/barriers.h b/arch/arm/mach-omap2/include/mach/barriers.h
index 4fa72c7cc7cd..1c582a8592b9 100644
--- a/arch/arm/mach-omap2/include/mach/barriers.h
+++ b/arch/arm/mach-omap2/include/mach/barriers.h
@@ -22,6 +22,8 @@
 #ifndef __MACH_BARRIERS_H
 #define __MACH_BARRIERS_H
+#include <asm/outercache.h>
 extern void omap_bus_sync(void);
 #define rmb()           dsb()
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index eba6cd3816f5..2c27fdb61e66 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1395,7 +1395,7 @@ static int _read_hardreset(struct omap_hwmod *oh, const char *name)
 */
 static int _ocp_softreset(struct omap_hwmod *oh)
 {
-        u32 v;
+        u32 v, softrst_mask;
        int c = 0;
        int ret = 0;
@@ -1427,11 +1427,13 @@ static int _ocp_softreset(struct omap_hwmod *oh)
                                                    oh->class->sysc->syss_offs)
                                   & SYSS_RESETDONE_MASK),
                                  MAX_MODULE_SOFTRESET_WAIT, c);
-        else if (oh->class->sysc->sysc_flags & SYSC_HAS_RESET_STATUS)
+        else if (oh->class->sysc->sysc_flags & SYSC_HAS_RESET_STATUS) {
+                softrst_mask = (0x1 << oh->class->sysc->sysc_fields->srst_shift);
                omap_test_timeout(!(omap_hwmod_read(oh,
                                                     oh->class->sysc->sysc_offs)
-                                   & SYSC_TYPE2_SOFTRESET_MASK),
+                                   & softrst_mask),
                                  MAX_MODULE_SOFTRESET_WAIT, c);
+        }
        if (c == MAX_MODULE_SOFTRESET_WAIT)
                pr_warning("omap_hwmod: %s: softreset failed (waited %d usec)\n",
@@ -1477,6 +1479,11 @@ static int _reset(struct omap_hwmod *oh)
        ret = (oh->class->reset) ? oh->class->reset(oh) : _ocp_softreset(oh);
+        if (oh->class->sysc) {
+                _update_sysc_cache(oh);
+                _enable_sysc(oh);
+        }
        return ret;
 }
@@ -1786,20 +1793,9 @@ static int _setup(struct omap_hwmod *oh, void *data)
                return 0;
        }
-        if (!(oh->flags & HWMOD_INIT_NO_RESET)) {
+        if (!(oh->flags & HWMOD_INIT_NO_RESET))
                _reset(oh);
-                /*
-                 * OCP_SYSCONFIG bits need to be reprogrammed after a softreset.
-                 * The _enable() function should be split to
-                 * avoid the rewrite of the OCP_SYSCONFIG register.
-                 */
-                if (oh->class->sysc) {
-                        _update_sysc_cache(oh);
-                        _enable_sysc(oh);
-                }
-        }
        postsetup_state = oh->_postsetup_state;
        if (postsetup_state == _HWMOD_STATE_UNKNOWN)
                postsetup_state = _HWMOD_STATE_ENABLED;
@@ -1907,20 +1903,10 @@ void omap_hwmod_write(u32 v, struct omap_hwmod *oh, u16 reg_offs)
 */
 int omap_hwmod_softreset(struct omap_hwmod *oh)
 {
-        u32 v;
+        if (!oh)
-        int ret;
-        if (!oh || !(oh->_sysc_cache))
                return -EINVAL;
-        v = oh->_sysc_cache;
+        return _ocp_softreset(oh);
-        ret = _set_softreset(oh, &v);
-        if (ret)
-                goto error;
-        _write_sysconfig(v, oh);
-error:
-        return ret;
 }
 /**
@@ -2463,26 +2449,28 @@ int omap_hwmod_del_initiator_dep(struct omap_hwmod *oh,
 * @oh: struct omap_hwmod *
 *
 * Sets the module OCP socket ENAWAKEUP bit to allow the module to
- * send wakeups to the PRCM.  Eventually this should sets PRCM wakeup
+ * send wakeups to the PRCM, and enable I/O ring wakeup events for
- * registers to cause the PRCM to receive wakeup events from the
+ * this IP block if it has dynamic mux entries.  Eventually this
- * module.  Does not set any wakeup routing registers beyond this
+ * should set PRCM wakeup registers to cause the PRCM to receive
- * point - if the module is to wake up any other module or subsystem,
+ * wakeup events from the module.  Does not set any wakeup routing
- * that must be set separately.  Called by omap_device code.  Returns
+ * registers beyond this point - if the module is to wake up any other
- * -EINVAL on error or 0 upon success.
+ * module or subsystem, that must be set separately.  Called by
+ * omap_device code.  Returns -EINVAL on error or 0 upon success.
 */
 int omap_hwmod_enable_wakeup(struct omap_hwmod *oh)
 {
        unsigned long flags;
        u32 v;
-        if (!oh->class->sysc ||
-            !(oh->class->sysc->sysc_flags & SYSC_HAS_ENAWAKEUP))
-                return -EINVAL;
        spin_lock_irqsave(&oh->_lock, flags);
-        v = oh->_sysc_cache;
-        _enable_wakeup(oh, &v);
+        if (oh->class->sysc &&
-        _write_sysconfig(v, oh);
+            (oh->class->sysc->sysc_flags & SYSC_HAS_ENAWAKEUP)) {
+                v = oh->_sysc_cache;
+                _enable_wakeup(oh, &v);
+                _write_sysconfig(v, oh);
+        }
        _set_idle_ioring_wakeup(oh, true);
        spin_unlock_irqrestore(&oh->_lock, flags);
@@ -2494,26 +2482,28 @@ int omap_hwmod_enable_wakeup(struct omap_hwmod *oh)
 * @oh: struct omap_hwmod *
 *
 * Clears the module OCP socket ENAWAKEUP bit to prevent the module
- * from sending wakeups to the PRCM.  Eventually this should clear
+ * from sending wakeups to the PRCM, and disable I/O ring wakeup
- * PRCM wakeup registers to cause the PRCM to ignore wakeup events
+ * events for this IP block if it has dynamic mux entries.  Eventually
- * from the module.  Does not set any wakeup routing registers beyond
+ * this should clear PRCM wakeup registers to cause the PRCM to ignore
- * this point - if the module is to wake up any other module or
+ * wakeup events from the module.  Does not set any wakeup routing
- * subsystem, that must be set separately.  Called by omap_device
+ * registers beyond this point - if the module is to wake up any other
- * code.  Returns -EINVAL on error or 0 upon success.
+ * module or subsystem, that must be set separately.  Called by
+ * omap_device code.  Returns -EINVAL on error or 0 upon success.
 */
 int omap_hwmod_disable_wakeup(struct omap_hwmod *oh)
 {
        unsigned long flags;
        u32 v;
-        if (!oh->class->sysc ||
-            !(oh->class->sysc->sysc_flags & SYSC_HAS_ENAWAKEUP))
-                return -EINVAL;
        spin_lock_irqsave(&oh->_lock, flags);
-        v = oh->_sysc_cache;
-        _disable_wakeup(oh, &v);
+        if (oh->class->sysc &&
-        _write_sysconfig(v, oh);
+            (oh->class->sysc->sysc_flags & SYSC_HAS_ENAWAKEUP)) {
+                v = oh->_sysc_cache;
+                _disable_wakeup(oh, &v);
+                _write_sysconfig(v, oh);
+        }
        _set_idle_ioring_wakeup(oh, false);
        spin_unlock_irqrestore(&oh->_lock, flags);
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index 08daa5e0eb5f..cc9bd106a854 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -2996,6 +2996,11 @@ static struct omap_hwmod_ocp_if *omap44xx_mcbsp1_slaves[] = {
        &omap44xx_l4_abe__mcbsp1_dma,
 };
+static struct omap_hwmod_opt_clk mcbsp1_opt_clks[] = {
+        { .role = "pad_fck", .clk = "pad_clks_ck" },
+        { .role = "prcm_clk", .clk = "mcbsp1_sync_mux_ck" },
+};
 static struct omap_hwmod omap44xx_mcbsp1_hwmod = {
        .name           = "mcbsp1",
        .class          = &omap44xx_mcbsp_hwmod_class,
@@ -3012,6 +3017,8 @@ static struct omap_hwmod omap44xx_mcbsp1_hwmod = {
        },
        .slaves         = omap44xx_mcbsp1_slaves,
        .slaves_cnt     = ARRAY_SIZE(omap44xx_mcbsp1_slaves),
+        .opt_clks       = mcbsp1_opt_clks,
+        .opt_clks_cnt   = ARRAY_SIZE(mcbsp1_opt_clks),
 };
 /* mcbsp2 */
@@ -3071,6 +3078,11 @@ static struct omap_hwmod_ocp_if *omap44xx_mcbsp2_slaves[] = {
        &omap44xx_l4_abe__mcbsp2_dma,
 };
+static struct omap_hwmod_opt_clk mcbsp2_opt_clks[] = {
+        { .role = "pad_fck", .clk = "pad_clks_ck" },
+        { .role = "prcm_clk", .clk = "mcbsp2_sync_mux_ck" },
+};
 static struct omap_hwmod omap44xx_mcbsp2_hwmod = {
        .name           = "mcbsp2",
        .class          = &omap44xx_mcbsp_hwmod_class,
@@ -3087,6 +3099,8 @@ static struct omap_hwmod omap44xx_mcbsp2_hwmod = {
        },
        .slaves         = omap44xx_mcbsp2_slaves,
        .slaves_cnt     = ARRAY_SIZE(omap44xx_mcbsp2_slaves),
+        .opt_clks       = mcbsp2_opt_clks,
+        .opt_clks_cnt   = ARRAY_SIZE(mcbsp2_opt_clks),
 };
 /* mcbsp3 */
@@ -3146,6 +3160,11 @@ static struct omap_hwmod_ocp_if *omap44xx_mcbsp3_slaves[] = {
        &omap44xx_l4_abe__mcbsp3_dma,
 };
+static struct omap_hwmod_opt_clk mcbsp3_opt_clks[] = {
+        { .role = "pad_fck", .clk = "pad_clks_ck" },
+        { .role = "prcm_clk", .clk = "mcbsp3_sync_mux_ck" },
+};
 static struct omap_hwmod omap44xx_mcbsp3_hwmod = {
        .name           = "mcbsp3",
        .class          = &omap44xx_mcbsp_hwmod_class,
@@ -3162,6 +3181,8 @@ static struct omap_hwmod omap44xx_mcbsp3_hwmod = {
        },
        .slaves         = omap44xx_mcbsp3_slaves,
        .slaves_cnt     = ARRAY_SIZE(omap44xx_mcbsp3_slaves),
+        .opt_clks       = mcbsp3_opt_clks,
+        .opt_clks_cnt   = ARRAY_SIZE(mcbsp3_opt_clks),
 };
 /* mcbsp4 */
@@ -3200,6 +3221,11 @@ static struct omap_hwmod_ocp_if *omap44xx_mcbsp4_slaves[] = {
        &omap44xx_l4_per__mcbsp4,
 };
+static struct omap_hwmod_opt_clk mcbsp4_opt_clks[] = {
+        { .role = "pad_fck", .clk = "pad_clks_ck" },
+        { .role = "prcm_clk", .clk = "mcbsp4_sync_mux_ck" },
+};
 static struct omap_hwmod omap44xx_mcbsp4_hwmod = {
        .name           = "mcbsp4",
        .class          = &omap44xx_mcbsp_hwmod_class,
@@ -3216,6 +3242,8 @@ static struct omap_hwmod omap44xx_mcbsp4_hwmod = {
        },
        .slaves         = omap44xx_mcbsp4_slaves,
        .slaves_cnt     = ARRAY_SIZE(omap44xx_mcbsp4_slaves),
+        .opt_clks       = mcbsp4_opt_clks,
+        .opt_clks_cnt   = ARRAY_SIZE(mcbsp4_opt_clks),
 };
 /*
diff --git a/arch/arm/mach-omap2/opp.c b/arch/arm/mach-omap2/opp.c
index 9262a6b47702..de6d46451746 100644
--- a/arch/arm/mach-omap2/opp.c
+++ b/arch/arm/mach-omap2/opp.c
@@ -64,10 +64,10 @@ int __init omap_init_opp_table(struct omap_opp_def *opp_def,
                }
                oh = omap_hwmod_lookup(opp_def->hwmod_name);
                if (!oh || !oh->od) {
-                        pr_warn("%s: no hwmod or odev for %s, [%d] "
+                        pr_debug("%s: no hwmod or odev for %s, [%d] "
                                "cannot add OPPs.\n", __func__,
                                opp_def->hwmod_name, i);
-                        return -EINVAL;
+                        continue;
                }
                dev = &oh->od->pdev->dev;
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 238defc6f6df..703bd1099259 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -153,8 +153,7 @@ static void omap3_save_secure_ram_context(void)
                pwrdm_set_next_pwrst(mpu_pwrdm, mpu_next_state);
                /* Following is for error tracking, it should not happen */
                if (ret) {
-                        printk(KERN_ERR "save_secure_sram() returns %08x\n",
+                        pr_err("save_secure_sram() returns %08x\n", ret);
-                                ret);
                        while (1)
                                ;
                }
@@ -289,7 +288,7 @@ void omap_sram_idle(void)
                break;
        default:
                /* Invalid state */
-                printk(KERN_ERR "Invalid mpu state in sram_idle\n");
+                pr_err("Invalid mpu state in sram_idle\n");
                return;
        }
@@ -439,18 +438,17 @@ restore:
        list_for_each_entry(pwrst, &pwrst_list, node) {
                state = pwrdm_read_prev_pwrst(pwrst->pwrdm);
                if (state > pwrst->next_state) {
-                        printk(KERN_INFO "Powerdomain (%s) didn't enter "
+                        pr_info("Powerdomain (%s) didn't enter "
-                               "target state %d\n",
+                                "target state %d\n",
                               pwrst->pwrdm->name, pwrst->next_state);
                        ret = -1;
                }
                omap_set_pwrdm_state(pwrst->pwrdm, pwrst->saved_state);
        }
        if (ret)
-                printk(KERN_ERR "Could not enter target state in pm_suspend\n");
+                pr_err("Could not enter target state in pm_suspend\n");
        else
-                printk(KERN_INFO "Successfully put all powerdomains "
+                pr_info("Successfully put all powerdomains to target state\n");
-                       "to target state\n");
        return ret;
 }
@@ -734,21 +732,22 @@ static int __init omap3_pm_init(void)
        if (ret) {
                pr_err("pm: Failed to request pm_io irq\n");
-                goto err1;
+                goto err2;
        }
        ret = pwrdm_for_each(pwrdms_setup, NULL);
        if (ret) {
-                printk(KERN_ERR "Failed to setup powerdomains\n");
+                pr_err("Failed to setup powerdomains\n");
-                goto err2;
+                goto err3;
        }
        (void) clkdm_for_each(omap_pm_clkdms_setup, NULL);
        mpu_pwrdm = pwrdm_lookup("mpu_pwrdm");
        if (mpu_pwrdm == NULL) {
-                printk(KERN_ERR "Failed to get mpu_pwrdm\n");
+                pr_err("Failed to get mpu_pwrdm\n");
-                goto err2;
+                ret = -EINVAL;
+                goto err3;
        }
        neon_pwrdm = pwrdm_lookup("neon_pwrdm");
@@ -781,8 +780,8 @@ static int __init omap3_pm_init(void)
                omap3_secure_ram_storage =
                        kmalloc(0x803F, GFP_KERNEL);
                if (!omap3_secure_ram_storage)
-                        printk(KERN_ERR "Memory allocation failed when"
+                        pr_err("Memory allocation failed when "
-                                        "allocating for secure sram context\n");
+                               "allocating for secure sram context\n");
                local_irq_disable();
                local_fiq_disable();
@@ -796,14 +795,17 @@ static int __init omap3_pm_init(void)
        }
        omap3_save_scratchpad_contents();
-err1:
        return ret;
-err2:
-        free_irq(INT_34XX_PRCM_MPU_IRQ, NULL);
+err3:
        list_for_each_entry_safe(pwrst, tmp, &pwrst_list, node) {
                list_del(&pwrst->node);
                kfree(pwrst);
        }
+        free_irq(omap_prcm_event_to_irq("io"), omap3_pm_init);
+err2:
+        free_irq(omap_prcm_event_to_irq("wkup"), NULL);
+err1:
        return ret;
 }
diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c
index 9ccaadc2cf07..885625352429 100644
--- a/arch/arm/mach-omap2/pm44xx.c
+++ b/arch/arm/mach-omap2/pm44xx.c
@@ -144,7 +144,7 @@ static void omap_default_idle(void)
 static int __init omap4_pm_init(void)
 {
        int ret;
-        struct clockdomain *emif_clkdm, *mpuss_clkdm, *l3_1_clkdm;
+        struct clockdomain *emif_clkdm, *mpuss_clkdm, *l3_1_clkdm, *l4wkup;
        struct clockdomain *ducati_clkdm, *l3_2_clkdm, *l4_per_clkdm;
        if (!cpu_is_omap44xx())
@@ -168,14 +168,19 @@ static int __init omap4_pm_init(void)
         * MPUSS -> L4_PER/L3_* and DUCATI -> L3_* doesn't work as
         * expected. The hardware recommendation is to enable static
         * dependencies for these to avoid system lock ups or random crashes.
+         * The L4 wakeup depedency is added to workaround the OCP sync hardware
+         * BUG with 32K synctimer which lead to incorrect timer value read
+         * from the 32K counter. The BUG applies for GPTIMER1 and WDT2 which
+         * are part of L4 wakeup clockdomain.
         */
        mpuss_clkdm = clkdm_lookup("mpuss_clkdm");
        emif_clkdm = clkdm_lookup("l3_emif_clkdm");
        l3_1_clkdm = clkdm_lookup("l3_1_clkdm");
        l3_2_clkdm = clkdm_lookup("l3_2_clkdm");
        l4_per_clkdm = clkdm_lookup("l4_per_clkdm");
+        l4wkup = clkdm_lookup("l4_wkup_clkdm");
        ducati_clkdm = clkdm_lookup("ducati_clkdm");
-        if ((!mpuss_clkdm) || (!emif_clkdm) || (!l3_1_clkdm) ||
+        if ((!mpuss_clkdm) || (!emif_clkdm) || (!l3_1_clkdm) || (!l4wkup) ||
                (!l3_2_clkdm) || (!ducati_clkdm) || (!l4_per_clkdm))
                goto err2;
@@ -183,6 +188,7 @@ static int __init omap4_pm_init(void)
        ret |= clkdm_add_wkdep(mpuss_clkdm, l3_1_clkdm);
        ret |= clkdm_add_wkdep(mpuss_clkdm, l3_2_clkdm);
        ret |= clkdm_add_wkdep(mpuss_clkdm, l4_per_clkdm);
+        ret |= clkdm_add_wkdep(mpuss_clkdm, l4wkup);
        ret |= clkdm_add_wkdep(ducati_clkdm, l3_1_clkdm);
        ret |= clkdm_add_wkdep(ducati_clkdm, l3_2_clkdm);
        if (ret) {
diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c
index 8a18d1bd61c8..96ad3dbeac34 100644
--- a/arch/arm/mach-omap2/powerdomain.c
+++ b/arch/arm/mach-omap2/powerdomain.c
@@ -972,7 +972,13 @@ int pwrdm_wait_transition(struct powerdomain *pwrdm)
 int pwrdm_state_switch(struct powerdomain *pwrdm)
 {
-        return _pwrdm_state_switch(pwrdm, PWRDM_STATE_NOW);
+        int ret;
+        ret = pwrdm_wait_transition(pwrdm);
+        if (!ret)
+                ret = _pwrdm_state_switch(pwrdm, PWRDM_STATE_NOW);
+        return ret;
 }
 int pwrdm_clkdm_state_switch(struct clockdomain *clkdm)
diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c
index eac623c7c3d8..f106d21ff581 100644
--- a/arch/arm/mach-omap2/prm44xx.c
+++ b/arch/arm/mach-omap2/prm44xx.c
@@ -147,8 +147,9 @@ static inline u32 _read_pending_irq_reg(u16 irqen_offs, u16 irqst_offs)
        u32 mask, st;
        /* XXX read mask from RAM? */
-        mask = omap4_prm_read_inst_reg(OMAP4430_PRM_DEVICE_INST, irqen_offs);
+        mask = omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
-        st = omap4_prm_read_inst_reg(OMAP4430_PRM_DEVICE_INST, irqst_offs);
+                                       irqen_offs);
+        st = omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST, irqst_offs);
        return mask & st;
 }
@@ -180,7 +181,7 @@ void omap44xx_prm_read_pending_irqs(unsigned long *events)
 */
 void omap44xx_prm_ocp_barrier(void)
 {
-        omap4_prm_read_inst_reg(OMAP4430_PRM_DEVICE_INST,
+        omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
                                OMAP4_REVISION_PRM_OFFSET);
 }
@@ -198,19 +199,19 @@ void omap44xx_prm_ocp_barrier(void)
 void omap44xx_prm_save_and_clear_irqen(u32 *saved_mask)
 {
        saved_mask[0] =
-                omap4_prm_read_inst_reg(OMAP4430_PRM_DEVICE_INST,
+                omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
                                        OMAP4_PRM_IRQSTATUS_MPU_OFFSET);
        saved_mask[1] =
-                omap4_prm_read_inst_reg(OMAP4430_PRM_DEVICE_INST,
+                omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
                                        OMAP4_PRM_IRQSTATUS_MPU_2_OFFSET);
-        omap4_prm_write_inst_reg(0, OMAP4430_PRM_DEVICE_INST,
+        omap4_prm_write_inst_reg(0, OMAP4430_PRM_OCP_SOCKET_INST,
                                 OMAP4_PRM_IRQENABLE_MPU_OFFSET);
-        omap4_prm_write_inst_reg(0, OMAP4430_PRM_DEVICE_INST,
+        omap4_prm_write_inst_reg(0, OMAP4430_PRM_OCP_SOCKET_INST,
                                 OMAP4_PRM_IRQENABLE_MPU_2_OFFSET);
        /* OCP barrier */
-        omap4_prm_read_inst_reg(OMAP4430_PRM_DEVICE_INST,
+        omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
                                OMAP4_REVISION_PRM_OFFSET);
 }
@@ -226,9 +227,9 @@ void omap44xx_prm_save_and_clear_irqen(u32 *saved_mask)
 */
 void omap44xx_prm_restore_irqen(u32 *saved_mask)
 {
-        omap4_prm_write_inst_reg(saved_mask[0], OMAP4430_PRM_DEVICE_INST,
+        omap4_prm_write_inst_reg(saved_mask[0], OMAP4430_PRM_OCP_SOCKET_INST,
                                 OMAP4_PRM_IRQENABLE_MPU_OFFSET);
-        omap4_prm_write_inst_reg(saved_mask[1], OMAP4430_PRM_DEVICE_INST,
+        omap4_prm_write_inst_reg(saved_mask[1], OMAP4430_PRM_OCP_SOCKET_INST,
                                 OMAP4_PRM_IRQENABLE_MPU_2_OFFSET);
 }
diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c
index 873b51d494ea..d28f848897d6 100644
--- a/arch/arm/mach-omap2/prm_common.c
+++ b/arch/arm/mach-omap2/prm_common.c
@@ -290,7 +290,7 @@ int omap_prcm_register_chain_handler(struct omap_prcm_irq_setup *irq_setup)
                goto err;
        }
-        for (i = 0; i <= irq_setup->nr_regs; i++) {
+        for (i = 0; i < irq_setup->nr_regs; i++) {
                gc = irq_alloc_generic_chip("PRCM", 1,
                        irq_setup->base_irq + i * 32, prm_base,
                        handle_level_irq);
diff --git a/arch/arm/mach-omap2/usb-host.c b/arch/arm/mach-omap2/usb-host.c
index f51348dafafd..dde8a11f47d5 100644
--- a/arch/arm/mach-omap2/usb-host.c
+++ b/arch/arm/mach-omap2/usb-host.c
@@ -54,7 +54,7 @@ static struct omap_device_pm_latency omap_uhhtll_latency[] = {
 /*
 * setup_ehci_io_mux - initialize IO pad mux for USBHOST
 */
-static void setup_ehci_io_mux(const enum usbhs_omap_port_mode *port_mode)
+static void __init setup_ehci_io_mux(const enum usbhs_omap_port_mode *port_mode)
 {
        switch (port_mode[0]) {
        case OMAP_EHCI_PORT_MODE_PHY:
@@ -197,7 +197,8 @@ static void setup_ehci_io_mux(const enum usbhs_omap_port_mode *port_mode)
        return;
 }
-static void setup_4430ehci_io_mux(const enum usbhs_omap_port_mode *port_mode)
+static
+void __init setup_4430ehci_io_mux(const enum usbhs_omap_port_mode *port_mode)
 {
        switch (port_mode[0]) {
        case OMAP_EHCI_PORT_MODE_PHY:
@@ -315,7 +316,7 @@ static void setup_4430ehci_io_mux(const enum usbhs_omap_port_mode *port_mode)
        }
 }
-static void setup_ohci_io_mux(const enum usbhs_omap_port_mode *port_mode)
+static void __init setup_ohci_io_mux(const enum usbhs_omap_port_mode *port_mode)
 {
        switch (port_mode[0]) {
        case OMAP_OHCI_PORT_MODE_PHY_6PIN_DATSE0:
@@ -412,7 +413,8 @@ static void setup_ohci_io_mux(const enum usbhs_omap_port_mode *port_mode)
        }
 }
-static void setup_4430ohci_io_mux(const enum usbhs_omap_port_mode *port_mode)
+static
+void __init setup_4430ohci_io_mux(const enum usbhs_omap_port_mode *port_mode)
 {
        switch (port_mode[0]) {
        case OMAP_OHCI_PORT_MODE_PHY_6PIN_DATSE0:
diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig
index 109ccd2a8885..fe2d1f80ef50 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -113,6 +113,7 @@ config MACH_ARMCORE
        select IWMMXT
        select PXA25x
        select MIGHT_HAVE_PCI
+        select NEED_MACH_IO_H if PCI
 config MACH_EM_X270
        bool "CompuLab EM-x270 platform"
diff --git a/arch/arm/mach-pxa/include/mach/io.h b/arch/arm/mach-pxa/include/mach/io.h
new file mode 100644
index 000000000000..cd78b7fe3567
--- /dev/null
+++ b/arch/arm/mach-pxa/include/mach/io.h
@@ -0,0 +1,17 @@
+/*
+ * arch/arm/mach-pxa/include/mach/io.h
+ *
+ * Copied from asm/arch/sa1100/io.h
+ */
+#ifndef __ASM_ARM_ARCH_IO_H
+#define __ASM_ARM_ARCH_IO_H
+#define IO_SPACE_LIMIT 0xffffffff
+/*
+ * We don't actually have real ISA nor PCI buses, but there is so many
+ * drivers out there that might just work if we fake them...
+ */
+#define __io(a)         __typesafe_io(a)
+#endif
diff --git a/arch/arm/mach-s3c24xx/common.h b/arch/arm/mach-s3c24xx/common.h
new file mode 100644
index 000000000000..c2f596e7bc2d
--- /dev/null
+++ b/arch/arm/mach-s3c24xx/common.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *              http://www.samsung.com
+ *
+ * Common Header for S3C24XX SoCs
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ARCH_ARM_MACH_S3C24XX_COMMON_H
+#define __ARCH_ARM_MACH_S3C24XX_COMMON_H __FILE__
+void s3c2410_restart(char mode, const char *cmd);
+void s3c244x_restart(char mode, const char *cmd);
+#endif /* __ARCH_ARM_MACH_S3C24XX_COMMON_H */
diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c
index 48885b7efd6b..c7f418b0cde9 100644
--- a/arch/arm/mach-sa1100/collie.c
+++ b/arch/arm/mach-sa1100/collie.c
@@ -313,6 +313,10 @@ static struct sa1100fb_mach_info collie_lcd_info = {
        .lccr0          = LCCR0_Color | LCCR0_Sngl | LCCR0_Act,
        .lccr3          = LCCR3_OutEnH | LCCR3_PixRsEdg | LCCR3_ACBsDiv(2),
+#ifdef CONFIG_BACKLIGHT_LOCOMO
+        .lcd_power      = locomolcd_power
+#endif
 };
 static void __init collie_init(void)
diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h
index 52acda7061b7..f33679d2d3ee 100644
--- a/arch/arm/mach-sa1100/include/mach/collie.h
+++ b/arch/arm/mach-sa1100/include/mach/collie.h
@@ -1,7 +1,7 @@
 /*
 * arch/arm/mach-sa1100/include/mach/collie.h
 *
- * This file contains the hardware specific definitions for Assabet
+ * This file contains the hardware specific definitions for Collie
 * Only include this file from SA1100-specific files.
 *
 * ChangeLog:
@@ -13,6 +13,7 @@
 #ifndef __ASM_ARCH_COLLIE_H
 #define __ASM_ARCH_COLLIE_H
+extern void locomolcd_power(int on);
 #define COLLIE_SCOOP_GPIO_BASE  (GPIO_MAX + 1)
 #define COLLIE_GPIO_CHARGE_ON   (COLLIE_SCOOP_GPIO_BASE + 0)
diff --git a/arch/arm/mach-versatile/pci.c b/arch/arm/mach-versatile/pci.c
index a6e23f464528..d2268be8c34c 100644
--- a/arch/arm/mach-versatile/pci.c
+++ b/arch/arm/mach-versatile/pci.c
@@ -190,7 +190,7 @@ static struct resource pre_mem = {
        .flags  = IORESOURCE_MEM | IORESOURCE_PREFETCH,
 };
-static int __init pci_versatile_setup_resources(struct list_head *resources)
+static int __init pci_versatile_setup_resources(struct pci_sys_data *sys)
 {
        int ret = 0;
@@ -218,9 +218,9 @@ static int __init pci_versatile_setup_resources(struct list_head *resources)
         * the mem resource for this bus
         * the prefetch mem resource for this bus
         */
-        pci_add_resource_offset(resources, &io_mem, sys->io_offset);
+        pci_add_resource_offset(&sys->resources, &io_mem, sys->io_offset);
-        pci_add_resource_offset(resources, &non_mem, sys->mem_offset);
+        pci_add_resource_offset(&sys->resources, &non_mem, sys->mem_offset);
-        pci_add_resource_offset(resources, &pre_mem, sys->mem_offset);
+        pci_add_resource_offset(&sys->resources, &pre_mem, sys->mem_offset);
        goto out;
@@ -249,7 +249,7 @@ int __init pci_versatile_setup(int nr, struct pci_sys_data *sys)
        if (nr == 0) {
                sys->mem_offset = 0;
-                ret = pci_versatile_setup_resources(&sys->resources);
+                ret = pci_versatile_setup_resources(sys);
                if (ret < 0) {
                        printk("pci_versatile_setup: resources... oops?\n");
                        goto out;
diff --git a/arch/arm/plat-mxc/3ds_debugboard.c b/arch/arm/plat-mxc/3ds_debugboard.c
index d1e31fa1b0c3..5cac2c540f4f 100644
--- a/arch/arm/plat-mxc/3ds_debugboard.c
+++ b/arch/arm/plat-mxc/3ds_debugboard.c
@@ -80,7 +80,7 @@ static struct smsc911x_platform_config smsc911x_config = {
 static struct platform_device smsc_lan9217_device = {
        .name = "smsc911x",
-        .id = 0,
+        .id = -1,
        .dev = {
                .platform_data = &smsc911x_config,
        },
diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig
index ce1e9b96ba1a..ad95c7a5d009 100644
--- a/arch/arm/plat-omap/Kconfig
+++ b/arch/arm/plat-omap/Kconfig
@@ -17,6 +17,7 @@ config ARCH_OMAP1
        select IRQ_DOMAIN
        select HAVE_IDE
        select NEED_MACH_MEMORY_H
+        select NEED_MACH_IO_H if PCCARD
        help
          "Systems based on omap7xx, omap15xx or omap16xx"
diff --git a/arch/arm/plat-omap/clock.c b/arch/arm/plat-omap/clock.c
index 56b6f8b7053e..8506cbb7fea4 100644
--- a/arch/arm/plat-omap/clock.c
+++ b/arch/arm/plat-omap/clock.c
@@ -441,6 +441,8 @@ static int __init clk_disable_unused(void)
                return 0;
        pr_info("clock: disabling unused clocks to save power\n");
+        spin_lock_irqsave(&clockfw_lock, flags);
        list_for_each_entry(ck, &clocks, node) {
                if (ck->ops == &clkops_null)
                        continue;
@@ -448,10 +450,9 @@ static int __init clk_disable_unused(void)
                if (ck->usecount > 0 || !ck->enable_reg)
                        continue;
-                spin_lock_irqsave(&clockfw_lock, flags);
                arch_clock->clk_disable_unused(ck);
-                spin_unlock_irqrestore(&clockfw_lock, flags);
        }
+        spin_unlock_irqrestore(&clockfw_lock, flags);
        return 0;
 }
diff --git a/arch/arm/plat-omap/include/plat/omap_hwmod.h b/arch/arm/plat-omap/include/plat/omap_hwmod.h
index 9e8e63d52aab..8070145ccb98 100644
--- a/arch/arm/plat-omap/include/plat/omap_hwmod.h
+++ b/arch/arm/plat-omap/include/plat/omap_hwmod.h
@@ -47,17 +47,17 @@ extern struct omap_hwmod_sysc_fields omap_hwmod_sysc_type2;
 * with the original PRCM protocol defined for OMAP2420
 */
 #define SYSC_TYPE1_MIDLEMODE_SHIFT      12
-#define SYSC_TYPE1_MIDLEMODE_MASK       (0x3 << SYSC_MIDLEMODE_SHIFT)
+#define SYSC_TYPE1_MIDLEMODE_MASK       (0x3 << SYSC_TYPE1_MIDLEMODE_SHIFT)
 #define SYSC_TYPE1_CLOCKACTIVITY_SHIFT  8
-#define SYSC_TYPE1_CLOCKACTIVITY_MASK   (0x3 << SYSC_CLOCKACTIVITY_SHIFT)
+#define SYSC_TYPE1_CLOCKACTIVITY_MASK   (0x3 << SYSC_TYPE1_CLOCKACTIVITY_SHIFT)
 #define SYSC_TYPE1_SIDLEMODE_SHIFT      3
-#define SYSC_TYPE1_SIDLEMODE_MASK       (0x3 << SYSC_SIDLEMODE_SHIFT)
+#define SYSC_TYPE1_SIDLEMODE_MASK       (0x3 << SYSC_TYPE1_SIDLEMODE_SHIFT)
 #define SYSC_TYPE1_ENAWAKEUP_SHIFT      2
-#define SYSC_TYPE1_ENAWAKEUP_MASK       (1 << SYSC_ENAWAKEUP_SHIFT)
+#define SYSC_TYPE1_ENAWAKEUP_MASK       (1 << SYSC_TYPE1_ENAWAKEUP_SHIFT)
 #define SYSC_TYPE1_SOFTRESET_SHIFT      1
-#define SYSC_TYPE1_SOFTRESET_MASK       (1 << SYSC_SOFTRESET_SHIFT)
+#define SYSC_TYPE1_SOFTRESET_MASK       (1 << SYSC_TYPE1_SOFTRESET_SHIFT)
 #define SYSC_TYPE1_AUTOIDLE_SHIFT       0
-#define SYSC_TYPE1_AUTOIDLE_MASK        (1 << SYSC_AUTOIDLE_SHIFT)
+#define SYSC_TYPE1_AUTOIDLE_MASK        (1 << SYSC_TYPE1_AUTOIDLE_SHIFT)
 /*
 * OCP SYSCONFIG bit shifts/masks TYPE2. These are for IPs compliant
diff --git a/arch/avr32/include/asm/barrier.h b/arch/avr32/include/asm/barrier.h
index 808001c9cf8c..0961275373db 100644
--- a/arch/avr32/include/asm/barrier.h
+++ b/arch/avr32/include/asm/barrier.h
@@ -8,6 +8,8 @@
 #ifndef __ASM_AVR32_BARRIER_H
 #define __ASM_AVR32_BARRIER_H
+#define nop()                   asm volatile("nop")
 #define mb()                    asm volatile("" : : : "memory")
 #define rmb()                   mb()
 #define wmb()                   asm volatile("sync 0" : : : "memory")
diff --git a/arch/avr32/include/asm/special_insns.h b/arch/avr32/include/asm/special_insns.h
deleted file mode 100644
index f922218dfaa5..000000000000
--- a/arch/avr32/include/asm/special_insns.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_SPECIAL_INSNS_H
-#define __ASM_AVR32_SPECIAL_INSNS_H
-#define nop() asm volatile("nop")
-#endif /* __ASM_AVR32_SPECIAL_INSNS_H */
diff --git a/arch/avr32/mach-at32ap/include/mach/board.h b/arch/avr32/mach-at32ap/include/mach/board.h
index 71733866cb4f..70742ec997f8 100644
--- a/arch/avr32/mach-at32ap/include/mach/board.h
+++ b/arch/avr32/mach-at32ap/include/mach/board.h
@@ -7,7 +7,7 @@
 #include <linux/types.h>
 #include <linux/serial.h>
 #include <linux/platform_data/macb.h>
-#include <linux/platform_data/atmel_nand.h>
+#include <linux/platform_data/atmel.h>
 #define GPIO_PIN_NONE   (-1)
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index c1269a1085e1..373a6902d8fa 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -823,7 +823,7 @@ config CACHELINE_ALIGNED_L1
        bool "Locate cacheline_aligned data to L1 Data Memory"
        default y if !BF54x
        default n if BF54x
-        depends on !SMP && !BF531
+        depends on !SMP && !BF531 && !CRC32
        help
          If enabled, cacheline_aligned data is linked
          into L1 data memory. (less latency)
diff --git a/arch/blackfin/configs/BF527-EZKIT_defconfig b/arch/blackfin/configs/BF527-EZKIT_defconfig
index 9ccc18a6b4df..90b175323644 100644
--- a/arch/blackfin/configs/BF527-EZKIT_defconfig
+++ b/arch/blackfin/configs/BF527-EZKIT_defconfig
@@ -147,6 +147,7 @@ CONFIG_USB_OTG_BLACKLIST_HUB=y
 CONFIG_USB_MON=y
 CONFIG_USB_MUSB_HDRC=y
 CONFIG_USB_MUSB_BLACKFIN=y
+CONFIG_MUSB_PIO_ONLY=y
 CONFIG_USB_STORAGE=y
 CONFIG_USB_GADGET=y
 CONFIG_RTC_CLASS=y
diff --git a/arch/blackfin/include/asm/cmpxchg.h b/arch/blackfin/include/asm/cmpxchg.h
index ba2484f4cb2a..c05868cc61c1 100644
--- a/arch/blackfin/include/asm/cmpxchg.h
+++ b/arch/blackfin/include/asm/cmpxchg.h
@@ -122,7 +122,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
                        (unsigned long)(n), sizeof(*(ptr))))
 #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-#include <asm-generic/cmpxchg.h>
+#define cmpxchg(ptr, o, n)      cmpxchg_local((ptr), (o), (n))
+#define cmpxchg64(ptr, o, n)    cmpxchg64_local((ptr), (o), (n))
 #endif /* !CONFIG_SMP */
diff --git a/arch/blackfin/include/asm/gpio.h b/arch/blackfin/include/asm/gpio.h
index 5a25856381ff..12d3571b5232 100644
--- a/arch/blackfin/include/asm/gpio.h
+++ b/arch/blackfin/include/asm/gpio.h
@@ -244,16 +244,26 @@ static inline int gpio_set_debounce(unsigned gpio, unsigned debounce)
        return -EINVAL;
 }
-static inline int gpio_get_value(unsigned gpio)
+static inline int __gpio_get_value(unsigned gpio)
 {
        return bfin_gpio_get_value(gpio);
 }
-static inline void gpio_set_value(unsigned gpio, int value)
+static inline void __gpio_set_value(unsigned gpio, int value)
 {
        return bfin_gpio_set_value(gpio, value);
 }
+static inline int gpio_get_value(unsigned gpio)
+{
+        return __gpio_get_value(gpio);
+}
+static inline void gpio_set_value(unsigned gpio, int value)
+{
+        return __gpio_set_value(gpio, value);
+}
 static inline int gpio_to_irq(unsigned gpio)
 {
        if (likely(gpio < MAX_BLACKFIN_GPIOS))
diff --git a/arch/c6x/kernel/signal.c b/arch/c6x/kernel/signal.c
index 304f675826e9..3b5a05099989 100644
--- a/arch/c6x/kernel/signal.c
+++ b/arch/c6x/kernel/signal.c
@@ -85,10 +85,7 @@ asmlinkage int do_rt_sigreturn(struct pt_regs *regs)
                goto badframe;
        sigdelsetmask(&set, ~_BLOCKABLE);
-        spin_lock_irq(&current->sighand->siglock);
+        set_current_blocked(&set);
-        current->blocked = set;
-        recalc_sigpending();
-        spin_unlock_irq(&current->sighand->siglock);
        if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
                goto badframe;
@@ -279,15 +276,8 @@ static int handle_signal(int sig,
        /* Set up the stack frame */
        ret = setup_rt_frame(sig, ka, info, oldset, regs);
-        if (ret == 0) {
+        if (ret == 0)
-                spin_lock_irq(&current->sighand->siglock);
+                block_sigmask(ka, sig);
-                sigorsets(&current->blocked, &current->blocked,
-                          &ka->sa.sa_mask);
-                if (!(ka->sa.sa_flags & SA_NODEFER))
-                        sigaddset(&current->blocked, sig);
-                recalc_sigpending();
-                spin_unlock_irq(&current->sighand->siglock);
-        }
        return ret;
 }
diff --git a/arch/frv/mb93090-mb00/pci-dma.c b/arch/frv/mb93090-mb00/pci-dma.c
index 41098a3803a2..4f8d8bcdc7de 100644
--- a/arch/frv/mb93090-mb00/pci-dma.c
+++ b/arch/frv/mb93090-mb00/pci-dma.c
@@ -13,6 +13,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/list.h>
 #include <linux/pci.h>
+#include <linux/export.h>
 #include <linux/highmem.h>
 #include <linux/scatterlist.h>
 #include <asm/io.h>
diff --git a/arch/hexagon/include/asm/dma-mapping.h b/arch/hexagon/include/asm/dma-mapping.h
index 448b224ba4ef..233ed3d2d25e 100644
--- a/arch/hexagon/include/asm/dma-mapping.h
+++ b/arch/hexagon/include/asm/dma-mapping.h
@@ -71,29 +71,35 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
        return (dma_addr == bad_dma_address);
 }
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+#define dma_alloc_coherent(d,s,h,f)     dma_alloc_attrs(d,s,h,f,NULL)
-                                       dma_addr_t *dma_handle, gfp_t flag)
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+                                    dma_addr_t *dma_handle, gfp_t flag,
+                                    struct dma_attrs *attrs)
 {
        void *ret;
        struct dma_map_ops *ops = get_dma_ops(dev);
        BUG_ON(!dma_ops);
-        ret = ops->alloc_coherent(dev, size, dma_handle, flag);
+        ret = ops->alloc(dev, size, dma_handle, flag, attrs);
        debug_dma_alloc_coherent(dev, size, *dma_handle, ret);
        return ret;
 }
-static inline void dma_free_coherent(struct device *dev, size_t size,
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
-                                     void *cpu_addr, dma_addr_t dma_handle)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+                                  void *cpu_addr, dma_addr_t dma_handle,
+                                  struct dma_attrs *attrs)
 {
        struct dma_map_ops *dma_ops = get_dma_ops(dev);
        BUG_ON(!dma_ops);
-        dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
+        dma_ops->free(dev, size, cpu_addr, dma_handle, attrs);
        debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
 }
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index e711ace62fdf..37302218ca4a 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -54,7 +54,8 @@ static struct gen_pool *coherent_pool;
 /* Allocates from a pool of uncached memory that was reserved at boot time */
 void *hexagon_dma_alloc_coherent(struct device *dev, size_t size,
-                                 dma_addr_t *dma_addr, gfp_t flag)
+                                 dma_addr_t *dma_addr, gfp_t flag,
+                                 struct dma_attrs *attrs)
 {
        void *ret;
@@ -81,7 +82,7 @@ void *hexagon_dma_alloc_coherent(struct device *dev, size_t size,
 }
 static void hexagon_free_coherent(struct device *dev, size_t size, void *vaddr,
-                                  dma_addr_t dma_addr)
+                                  dma_addr_t dma_addr, struct dma_attrs *attrs)
 {
        gen_pool_free(coherent_pool, (unsigned long) vaddr, size);
 }
@@ -202,8 +203,8 @@ static void hexagon_sync_single_for_device(struct device *dev,
 }
 struct dma_map_ops hexagon_dma_ops = {
-        .alloc_coherent = hexagon_dma_alloc_coherent,
+        .alloc          = hexagon_dma_alloc_coherent,
-        .free_coherent  = hexagon_free_coherent,
+        .free           = hexagon_free_coherent,
        .map_sg         = hexagon_map_sg,
        .map_page       = hexagon_map_page,
        .sync_single_for_cpu = hexagon_sync_single_for_cpu,
diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c
index 15d1fd22bbc5..9b44a9e2d05a 100644
--- a/arch/hexagon/kernel/smp.c
+++ b/arch/hexagon/kernel/smp.c
@@ -35,7 +35,7 @@
 #define BASE_IPI_IRQ 26
 /*
- * cpu_possible_map needs to be filled out prior to setup_per_cpu_areas
+ * cpu_possible_mask needs to be filled out prior to setup_per_cpu_areas
 * (which is prior to any of our smp_prepare_cpu crap), in order to set
 * up the...  per_cpu areas.
 */
@@ -208,7 +208,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
        stack_start =  ((void *) thread) + THREAD_SIZE;
        __vmstart(start_secondary, stack_start);
-        while (!cpu_isset(cpu, cpu_online_map))
+        while (!cpu_online(cpu))
                barrier();
        return 0;
@@ -229,7 +229,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
        /*  Right now, let's just fake it. */
        for (i = 0; i < max_cpus; i++)
-                cpu_set(i, cpu_present_map);
+                set_cpu_present(i, true);
        /*  Also need to register the interrupts for IPI  */
        if (max_cpus > 1)
@@ -269,5 +269,5 @@ void smp_start_cpus(void)
        int i;
        for (i = 0; i < NR_CPUS; i++)
-                cpu_set(i, cpu_possible_map);
+                set_cpu_possible(i, true);
 }
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index f6ea3a3b4a84..bcda5b2d121a 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -1129,7 +1129,8 @@ void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size,
 * See Documentation/DMA-API-HOWTO.txt
 */
 static void *
-sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags)
+sba_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
+                   gfp_t flags, struct dma_attrs *attrs)
 {
        struct ioc *ioc;
        void *addr;
@@ -1191,8 +1192,8 @@ sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp
 *
 * See Documentation/DMA-API-HOWTO.txt
 */
-static void sba_free_coherent (struct device *dev, size_t size, void *vaddr,
+static void sba_free_coherent(struct device *dev, size_t size, void *vaddr,
-                               dma_addr_t dma_handle)
+                              dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
        sba_unmap_single_attrs(dev, dma_handle, size, 0, NULL);
        free_pages((unsigned long) vaddr, get_order(size));
@@ -2212,8 +2213,8 @@ sba_page_override(char *str)
 __setup("sbapagesize=",sba_page_override);
 struct dma_map_ops sba_dma_ops = {
-        .alloc_coherent         = sba_alloc_coherent,
+        .alloc                  = sba_alloc_coherent,
-        .free_coherent          = sba_free_coherent,
+        .free                   = sba_free_coherent,
        .map_page               = sba_map_page,
        .unmap_page             = sba_unmap_page,
        .map_sg                 = sba_map_sg_attrs,
diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h
index 4336d080b241..4f5e8148440d 100644
--- a/arch/ia64/include/asm/dma-mapping.h
+++ b/arch/ia64/include/asm/dma-mapping.h
@@ -23,23 +23,29 @@ extern void machvec_dma_sync_single(struct device *, dma_addr_t, size_t,
 extern void machvec_dma_sync_sg(struct device *, struct scatterlist *, int,
                                enum dma_data_direction);
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+#define dma_alloc_coherent(d,s,h,f)     dma_alloc_attrs(d,s,h,f,NULL)
-                                       dma_addr_t *daddr, gfp_t gfp)
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+                                    dma_addr_t *daddr, gfp_t gfp,
+                                    struct dma_attrs *attrs)
 {
        struct dma_map_ops *ops = platform_dma_get_ops(dev);
        void *caddr;
-        caddr = ops->alloc_coherent(dev, size, daddr, gfp);
+        caddr = ops->alloc(dev, size, daddr, gfp, attrs);
        debug_dma_alloc_coherent(dev, size, *daddr, caddr);
        return caddr;
 }
-static inline void dma_free_coherent(struct device *dev, size_t size,
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
-                                     void *caddr, dma_addr_t daddr)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+                                  void *caddr, dma_addr_t daddr,
+                                  struct dma_attrs *attrs)
 {
        struct dma_map_ops *ops = platform_dma_get_ops(dev);
        debug_dma_free_coherent(dev, size, caddr, daddr);
-        ops->free_coherent(dev, size, caddr, daddr);
+        ops->free(dev, size, caddr, daddr, attrs);
 }
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index ac795d311f44..6f38b6120d96 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -839,7 +839,7 @@ static __init int setup_additional_cpus(char *s)
 early_param("additional_cpus", setup_additional_cpus);
 /*
- * cpu_possible_map should be static, it cannot change as CPUs
+ * cpu_possible_mask should be static, it cannot change as CPUs
 * are onlined, or offlined. The reason is per-cpu data-structures
 * are allocated by some modules at init time, and dont expect to
 * do this dynamically on cpu arrival/departure.
diff --git a/arch/ia64/kernel/pci-swiotlb.c b/arch/ia64/kernel/pci-swiotlb.c
index d9485d952ed0..939260aeac98 100644
--- a/arch/ia64/kernel/pci-swiotlb.c
+++ b/arch/ia64/kernel/pci-swiotlb.c
@@ -15,16 +15,24 @@ int swiotlb __read_mostly;
 EXPORT_SYMBOL(swiotlb);
 static void *ia64_swiotlb_alloc_coherent(struct device *dev, size_t size,
-                                         dma_addr_t *dma_handle, gfp_t gfp)
+                                         dma_addr_t *dma_handle, gfp_t gfp,
+                                         struct dma_attrs *attrs)
 {
        if (dev->coherent_dma_mask != DMA_BIT_MASK(64))
                gfp |= GFP_DMA;
        return swiotlb_alloc_coherent(dev, size, dma_handle, gfp);
 }
+static void ia64_swiotlb_free_coherent(struct device *dev, size_t size,
+                                       void *vaddr, dma_addr_t dma_addr,
+                                       struct dma_attrs *attrs)
+{
+        swiotlb_free_coherent(dev, size, vaddr, dma_addr);
+}
 struct dma_map_ops swiotlb_dma_ops = {
-        .alloc_coherent = ia64_swiotlb_alloc_coherent,
+        .alloc = ia64_swiotlb_alloc_coherent,
-        .free_coherent = swiotlb_free_coherent,
+        .free = ia64_swiotlb_free_coherent,
        .map_page = swiotlb_map_page,
        .unmap_page = swiotlb_unmap_page,
        .map_sg = swiotlb_map_sg_attrs,
diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c
index a9d310de57da..3290d6e00c31 100644
--- a/arch/ia64/sn/pci/pci_dma.c
+++ b/arch/ia64/sn/pci/pci_dma.c
@@ -76,7 +76,8 @@ EXPORT_SYMBOL(sn_dma_set_mask);
 * more information.
 */
 static void *sn_dma_alloc_coherent(struct device *dev, size_t size,
-                                   dma_addr_t * dma_handle, gfp_t flags)
+                                   dma_addr_t * dma_handle, gfp_t flags,
+                                   struct dma_attrs *attrs)
 {
        void *cpuaddr;
        unsigned long phys_addr;
@@ -137,7 +138,7 @@ static void *sn_dma_alloc_coherent(struct device *dev, size_t size,
 * any associated IOMMU mappings.
 */
 static void sn_dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
-                                 dma_addr_t dma_handle)
+                                 dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
        struct pci_dev *pdev = to_pci_dev(dev);
        struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
@@ -466,8 +467,8 @@ int sn_pci_legacy_write(struct pci_bus *bus, u16 port, u32 val, u8 size)
 }
 static struct dma_map_ops sn_dma_ops = {
-        .alloc_coherent         = sn_dma_alloc_coherent,
+        .alloc                  = sn_dma_alloc_coherent,
-        .free_coherent          = sn_dma_free_coherent,
+        .free                   = sn_dma_free_coherent,
        .map_page               = sn_dma_map_page,
        .unmap_page             = sn_dma_unmap_page,
        .map_sg                 = sn_dma_map_sg,
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 336e6173794f..f4e32de263a7 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -3,6 +3,7 @@
 #include <linux/types.h>
 #include <linux/irqflags.h>
+#include <asm/cmpxchg.h>
 /*
 * Atomic operations that C can't guarantee us.  Useful for
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 96fa6ed7e799..d9f62e0f46c0 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -980,6 +980,9 @@ int __init mac_platform_init(void)
 {
        u8 *swim_base;
+        if (!MACH_IS_MAC)
+                return -ENODEV;
        /*
         * Serial devices
         */
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index 512adb64f7dd..8a1ce327c963 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -334,6 +334,9 @@ static __init int q40_add_kbd_device(void)
 {
        struct platform_device *pdev;
+        if (!MACH_IS_Q40)
+                return -ENODEV;
        pdev = platform_device_register_simple("q40kbd", -1, NULL, 0);
        if (IS_ERR(pdev))
                return PTR_ERR(pdev);
diff --git a/arch/microblaze/include/asm/cmpxchg.h b/arch/microblaze/include/asm/cmpxchg.h
index 0094859abd9b..538afc0ab9f3 100644
--- a/arch/microblaze/include/asm/cmpxchg.h
+++ b/arch/microblaze/include/asm/cmpxchg.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_MICROBLAZE_CMPXCHG_H
 #define _ASM_MICROBLAZE_CMPXCHG_H
+#include <linux/irqflags.h>
 void __bad_xchg(volatile void *ptr, int size);
 static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
diff --git a/arch/microblaze/include/asm/dma-mapping.h b/arch/microblaze/include/asm/dma-mapping.h
index 3a3e5b886854..01d228286cb0 100644
--- a/arch/microblaze/include/asm/dma-mapping.h
+++ b/arch/microblaze/include/asm/dma-mapping.h
@@ -123,28 +123,34 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL)
-                                        dma_addr_t *dma_handle, gfp_t flag)
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+                                    dma_addr_t *dma_handle, gfp_t flag,
+                                    struct dma_attrs *attrs)
 {
        struct dma_map_ops *ops = get_dma_ops(dev);
        void *memory;
        BUG_ON(!ops);
-        memory = ops->alloc_coherent(dev, size, dma_handle, flag);
+        memory = ops->alloc(dev, size, dma_handle, flag, attrs);
        debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
        return memory;
 }
-static inline void dma_free_coherent(struct device *dev, size_t size,
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d, s, c, h, NULL)
-                                     void *cpu_addr, dma_addr_t dma_handle)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+                                  void *cpu_addr, dma_addr_t dma_handle,
+                                  struct dma_attrs *attrs)
 {
        struct dma_map_ops *ops = get_dma_ops(dev);
        BUG_ON(!ops);
        debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-        ops->free_coherent(dev, size, cpu_addr, dma_handle);
+        ops->free(dev, size, cpu_addr, dma_handle, attrs);
 }
 static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
diff --git a/arch/microblaze/include/asm/futex.h b/arch/microblaze/include/asm/futex.h
index b0526d2716fa..ff8cde159d9a 100644
--- a/arch/microblaze/include/asm/futex.h
+++ b/arch/microblaze/include/asm/futex.h
@@ -24,7 +24,7 @@
                        .word   1b,4b,2b,4b;                            \
                        .previous;"                                     \
        : "=&r" (oldval), "=&r" (ret)                                   \
-        : "b" (uaddr), "i" (-EFAULT), "r" (oparg)                       \
+        : "r" (uaddr), "i" (-EFAULT), "r" (oparg)                       \
        );                                                              \
 })
diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h
index 510a8e1c16ba..bffb54527299 100644
--- a/arch/microblaze/include/asm/processor.h
+++ b/arch/microblaze/include/asm/processor.h
@@ -31,6 +31,8 @@ extern const struct seq_operations cpuinfo_op;
 /* Do necessary setup to start up a newly executed thread. */
 void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long usp);
+extern void ret_from_fork(void);
 # endif /* __ASSEMBLY__ */
 # ifndef CONFIG_MMU
@@ -143,8 +145,6 @@ static inline void exit_thread(void)
 unsigned long get_wchan(struct task_struct *p);
-extern void ret_from_fork(void);
 /* The size allocated for kernel stacks. This _must_ be a power of two! */
 # define KERNEL_STACK_SIZE      0x2000
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index 65a4af4cbbbe..a2bfa2ca5730 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -33,7 +33,8 @@ static unsigned long get_dma_direct_offset(struct device *dev)
 #define NOT_COHERENT_CACHE
 static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
-                                dma_addr_t *dma_handle, gfp_t flag)
+                                       dma_addr_t *dma_handle, gfp_t flag,
+                                       struct dma_attrs *attrs)
 {
 #ifdef NOT_COHERENT_CACHE
        return consistent_alloc(flag, size, dma_handle);
@@ -57,7 +58,8 @@ static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 }
 static void dma_direct_free_coherent(struct device *dev, size_t size,
-                              void *vaddr, dma_addr_t dma_handle)
+                                     void *vaddr, dma_addr_t dma_handle,
+                                     struct dma_attrs *attrs)
 {
 #ifdef NOT_COHERENT_CACHE
        consistent_free(size, vaddr);
@@ -176,8 +178,8 @@ dma_direct_sync_sg_for_device(struct device *dev,
 }
 struct dma_map_ops dma_direct_ops = {
-        .alloc_coherent = dma_direct_alloc_coherent,
+        .alloc          = dma_direct_alloc_coherent,
-        .free_coherent  = dma_direct_free_coherent,
+        .free           = dma_direct_free_coherent,
        .map_sg         = dma_direct_map_sg,
        .unmap_sg       = dma_direct_unmap_sg,
        .dma_supported  = dma_direct_dma_supported,
diff --git a/arch/microblaze/kernel/early_printk.c b/arch/microblaze/kernel/early_printk.c
index ec485876d0d0..aba1f9a97d5d 100644
--- a/arch/microblaze/kernel/early_printk.c
+++ b/arch/microblaze/kernel/early_printk.c
@@ -176,6 +176,7 @@ void __init remap_early_printk(void)
        base_addr = (u32) ioremap(base_addr, PAGE_SIZE);
        printk(KERN_CONT "0x%x\n", base_addr);
+#ifdef CONFIG_MMU
        /*
         * Early console is on the top of skipped TLB entries
         * decrease tlb_skip size ensure that hardcoded TLB entry will be
@@ -189,6 +190,7 @@ void __init remap_early_printk(void)
         *  cmp rX, orig_base_addr
         */
        tlb_skip -= 1;
+#endif
 }
 void __init disable_early_printk(void)
diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c
index 71af974aa24a..16d8dfd9094b 100644
--- a/arch/microblaze/kernel/setup.c
+++ b/arch/microblaze/kernel/setup.c
@@ -206,6 +206,7 @@ static int microblaze_debugfs_init(void)
 }
 arch_initcall(microblaze_debugfs_init);
+# ifdef CONFIG_MMU
 static int __init debugfs_tlb(void)
 {
        struct dentry *d;
@@ -218,6 +219,7 @@ static int __init debugfs_tlb(void)
                return -ENOMEM;
 }
 device_initcall(debugfs_tlb);
+# endif
 #endif
 static int dflt_bus_notify(struct notifier_block *nb,
diff --git a/arch/microblaze/kernel/unwind.c b/arch/microblaze/kernel/unwind.c
index 9781a528cfc9..6be4ae3c3351 100644
--- a/arch/microblaze/kernel/unwind.c
+++ b/arch/microblaze/kernel/unwind.c
@@ -24,6 +24,7 @@
 #include <asm/sections.h>
 #include <asm/exceptions.h>
 #include <asm/unwind.h>
+#include <asm/switch_to.h>
 struct stack_trace;
diff --git a/arch/microblaze/lib/uaccess_old.S b/arch/microblaze/lib/uaccess_old.S
index f037266cdaf3..f085995ee848 100644
--- a/arch/microblaze/lib/uaccess_old.S
+++ b/arch/microblaze/lib/uaccess_old.S
@@ -122,22 +122,22 @@ __strnlen_user:
 15:     swi     r24, r5, 0x0018 + offset;       \
 16:     swi     r25, r5, 0x001C + offset;       \
        .section __ex_table,"a";                \
-        .word   1b, 0f;                         \
+        .word   1b, 33f;                        \
-        .word   2b, 0f;                         \
+        .word   2b, 33f;                        \
-        .word   3b, 0f;                         \
+        .word   3b, 33f;                        \
-        .word   4b, 0f;                         \
+        .word   4b, 33f;                        \
-        .word   5b, 0f;                         \
+        .word   5b, 33f;                        \
-        .word   6b, 0f;                         \
+        .word   6b, 33f;                        \
-        .word   7b, 0f;                         \
+        .word   7b, 33f;                        \
-        .word   8b, 0f;                         \
+        .word   8b, 33f;                        \
-        .word   9b, 0f;                         \
+        .word   9b, 33f;                        \
-        .word   10b, 0f;                        \
+        .word   10b, 33f;                       \
-        .word   11b, 0f;                        \
+        .word   11b, 33f;                       \
-        .word   12b, 0f;                        \
+        .word   12b, 33f;                       \
-        .word   13b, 0f;                        \
+        .word   13b, 33f;                       \
-        .word   14b, 0f;                        \
+        .word   14b, 33f;                       \
-        .word   15b, 0f;                        \
+        .word   15b, 33f;                       \
-        .word   16b, 0f;                        \
+        .word   16b, 33f;                       \
        .text
 #define COPY_80(offset) \
@@ -190,14 +190,17 @@ w2:	sw	r4, r5, r3
 .align 4 /* Alignment is important to keep icache happy */
 page:   /* Create room on stack and save registers for storign values */
-        addik   r1, r1, -32
+        addik   r1, r1, -40
-        swi     r19, r1, 4
+        swi     r5, r1, 0
-        swi     r20, r1, 8
+        swi     r6, r1, 4
-        swi     r21, r1, 12
+        swi     r7, r1, 8
-        swi     r22, r1, 16
+        swi     r19, r1, 12
-        swi     r23, r1, 20
+        swi     r20, r1, 16
-        swi     r24, r1, 24
+        swi     r21, r1, 20
-        swi     r25, r1, 28
+        swi     r22, r1, 24
+        swi     r23, r1, 28
+        swi     r24, r1, 32
+        swi     r25, r1, 36
 loop:   /* r4, r19, r20, r21, r22, r23, r24, r25 are used for storing values */
        /* Loop unrolling to get performance boost */
        COPY_80(0x000);
@@ -205,21 +208,44 @@ loop:	/* r4, r19, r20, r21, r22, r23, r24, r25 are used for storing values */
        COPY_80(0x100);
        COPY_80(0x180);
        /* copy loop */
-        addik   r6, r6, 0x200
+        addik   r6, r6, 0x200
-        addik   r7, r7, -0x200
+        addik   r7, r7, -0x200
-        bneid   r7, loop
+        bneid   r7, loop
-        addik   r5, r5, 0x200
+        addik   r5, r5, 0x200
        /* Restore register content */
-        lwi     r19, r1, 4
+        lwi     r5, r1, 0
-        lwi     r20, r1, 8
+        lwi     r6, r1, 4
-        lwi     r21, r1, 12
+        lwi     r7, r1, 8
-        lwi     r22, r1, 16
+        lwi     r19, r1, 12
-        lwi     r23, r1, 20
+        lwi     r20, r1, 16
-        lwi     r24, r1, 24
+        lwi     r21, r1, 20
-        lwi     r25, r1, 28
+        lwi     r22, r1, 24
-        addik   r1, r1, 32
+        lwi     r23, r1, 28
+        lwi     r24, r1, 32
+        lwi     r25, r1, 36
+        addik   r1, r1, 40
        /* return back */
+        addik   r3, r0, 0
+        rtsd    r15, 8
+        nop
+/* Fault case - return temp count */
+33:
        addik   r3, r7, 0
+        /* Restore register content */
+        lwi     r5, r1, 0
+        lwi     r6, r1, 4
+        lwi     r7, r1, 8
+        lwi     r19, r1, 12
+        lwi     r20, r1, 16
+        lwi     r21, r1, 20
+        lwi     r22, r1, 24
+        lwi     r23, r1, 28
+        lwi     r24, r1, 32
+        lwi     r25, r1, 36
+        addik   r1, r1, 40
+        /* return back */
        rtsd    r15, 8
        nop
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index b6bb92c16a47..41dd00884975 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -157,7 +157,7 @@ static void octeon_dma_sync_sg_for_device(struct device *dev,
 }
 static void *octeon_dma_alloc_coherent(struct device *dev, size_t size,
-        dma_addr_t *dma_handle, gfp_t gfp)
+        dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs)
 {
        void *ret;
@@ -192,7 +192,7 @@ static void *octeon_dma_alloc_coherent(struct device *dev, size_t size,
 }
 static void octeon_dma_free_coherent(struct device *dev, size_t size,
-        void *vaddr, dma_addr_t dma_handle)
+        void *vaddr, dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
        int order = get_order(size);
@@ -240,8 +240,8 @@ EXPORT_SYMBOL(dma_to_phys);
 static struct octeon_dma_map_ops octeon_linear_dma_map_ops = {
        .dma_map_ops = {
-                .alloc_coherent = octeon_dma_alloc_coherent,
+                .alloc = octeon_dma_alloc_coherent,
-                .free_coherent = octeon_dma_free_coherent,
+                .free = octeon_dma_free_coherent,
                .map_page = octeon_dma_map_page,
                .unmap_page = swiotlb_unmap_page,
                .map_sg = octeon_dma_map_sg,
@@ -325,8 +325,8 @@ void __init plat_swiotlb_setup(void)
 #ifdef CONFIG_PCI
 static struct octeon_dma_map_ops _octeon_pci_dma_map_ops = {
        .dma_map_ops = {
-                .alloc_coherent = octeon_dma_alloc_coherent,
+                .alloc = octeon_dma_alloc_coherent,
-                .free_coherent = octeon_dma_free_coherent,
+                .free = octeon_dma_free_coherent,
                .map_page = octeon_dma_map_page,
                .unmap_page = swiotlb_unmap_page,
                .map_sg = octeon_dma_map_sg,
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index c3e2b85c3b02..97e7ce9b50ed 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -78,7 +78,7 @@ static inline void octeon_send_ipi_mask(const struct cpumask *mask,
 }
 /**
- * Detect available CPUs, populate cpu_possible_map
+ * Detect available CPUs, populate cpu_possible_mask
 */
 static void octeon_smp_hotplug_setup(void)
 {
@@ -268,7 +268,7 @@ static int octeon_cpu_disable(void)
        spin_lock(&smp_reserve_lock);
-        cpu_clear(cpu, cpu_online_map);
+        set_cpu_online(cpu, false);
        cpu_clear(cpu, cpu_callin_map);
        local_irq_disable();
        fixup_irqs();
diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index 7aa37ddfca4b..be39a12901c6 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -57,25 +57,31 @@ dma_set_mask(struct device *dev, u64 mask)
 extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
               enum dma_data_direction direction);
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+#define dma_alloc_coherent(d,s,h,f)     dma_alloc_attrs(d,s,h,f,NULL)
-                                       dma_addr_t *dma_handle, gfp_t gfp)
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+                                    dma_addr_t *dma_handle, gfp_t gfp,
+                                    struct dma_attrs *attrs)
 {
        void *ret;
        struct dma_map_ops *ops = get_dma_ops(dev);
-        ret = ops->alloc_coherent(dev, size, dma_handle, gfp);
+        ret = ops->alloc(dev, size, dma_handle, gfp, attrs);
        debug_dma_alloc_coherent(dev, size, *dma_handle, ret);
        return ret;
 }
-static inline void dma_free_coherent(struct device *dev, size_t size,
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
-                                     void *vaddr, dma_addr_t dma_handle)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+                                  void *vaddr, dma_addr_t dma_handle,
+                                  struct dma_attrs *attrs)
 {
        struct dma_map_ops *ops = get_dma_ops(dev);
-        ops->free_coherent(dev, size, vaddr, dma_handle);
+        ops->free(dev, size, vaddr, dma_handle, attrs);
        debug_dma_free_coherent(dev, size, vaddr, dma_handle);
 }
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index 802e6160f37e..33f63bab478a 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -173,7 +173,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
        if (retval)
                goto out_unlock;
-        cpus_and(mask, p->thread.user_cpus_allowed, cpu_possible_map);
+        cpumask_and(&mask, &p->thread.user_cpus_allowed, cpu_possible_mask);
 out_unlock:
        read_unlock(&tasklist_lock);
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index e309665b6c81..f8b2c592514d 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -25,7 +25,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
        int i;
 #ifdef CONFIG_SMP
-        if (!cpu_isset(n, cpu_online_map))
+        if (!cpu_online(n))
                return 0;
 #endif
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index ca673569fd24..3046e2986006 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -317,7 +317,7 @@ static int bmips_cpu_disable(void)
        pr_info("SMP: CPU%d is offline\n", cpu);
-        cpu_clear(cpu, cpu_online_map);
+        set_cpu_online(cpu, false);
        cpu_clear(cpu, cpu_callin_map);
        local_flush_tlb_all();
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 9c1cce9de35f..ba9376bf52a1 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -148,7 +148,7 @@ static void stop_this_cpu(void *dummy)
        /*
         * Remove this CPU:
         */
-        cpu_clear(smp_processor_id(), cpu_online_map);
+        set_cpu_online(smp_processor_id(), false);
        for (;;) {
                if (cpu_wait)
                        (*cpu_wait)();          /* Wait if available. */
@@ -174,7 +174,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
        mp_ops->prepare_cpus(max_cpus);
        set_cpu_sibling_map(0);
 #ifndef CONFIG_HOTPLUG_CPU
-        init_cpu_present(&cpu_possible_map);
+        init_cpu_present(cpu_possible_mask);
 #endif
 }
@@ -248,7 +248,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
        while (!cpu_isset(cpu, cpu_callin_map))
                udelay(100);
-        cpu_set(cpu, cpu_online_map);
+        set_cpu_online(cpu, true);
        return 0;
 }
@@ -320,13 +320,12 @@ void flush_tlb_mm(struct mm_struct *mm)
        if ((atomic_read(&mm->mm_users) != 1) || (current->mm != mm)) {
                smp_on_other_tlbs(flush_tlb_mm_ipi, mm);
        } else {
-                cpumask_t mask = cpu_online_map;
                unsigned int cpu;
-                cpu_clear(smp_processor_id(), mask);
+                for_each_online_cpu(cpu) {
-                for_each_cpu_mask(cpu, mask)
+                        if (cpu != smp_processor_id() && cpu_context(cpu, mm))
-                        if (cpu_context(cpu, mm))
                                cpu_context(cpu, mm) = 0;
+                }
        }
        local_flush_tlb_mm(mm);
@@ -360,13 +359,12 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned l
                smp_on_other_tlbs(flush_tlb_range_ipi, &fd);
        } else {
-                cpumask_t mask = cpu_online_map;
                unsigned int cpu;
-                cpu_clear(smp_processor_id(), mask);
+                for_each_online_cpu(cpu) {
-                for_each_cpu_mask(cpu, mask)
+                        if (cpu != smp_processor_id() && cpu_context(cpu, mm))
-                        if (cpu_context(cpu, mm))
                                cpu_context(cpu, mm) = 0;
+                }
        }
        local_flush_tlb_range(vma, start, end);
        preempt_enable();
@@ -407,13 +405,12 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
                smp_on_other_tlbs(flush_tlb_page_ipi, &fd);
        } else {
-                cpumask_t mask = cpu_online_map;
                unsigned int cpu;
-                cpu_clear(smp_processor_id(), mask);
+                for_each_online_cpu(cpu) {
-                for_each_cpu_mask(cpu, mask)
+                        if (cpu != smp_processor_id() && cpu_context(cpu, vma->vm_mm))
-                        if (cpu_context(cpu, vma->vm_mm))
                                cpu_context(cpu, vma->vm_mm) = 0;
+                }
        }
        local_flush_tlb_page(vma, page);
        preempt_enable();
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index c4f75bbc0bd6..f5dd38f1d015 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -291,7 +291,7 @@ static void smtc_configure_tlb(void)
 * possibly leave some TCs/VPEs as "slave" processors.
 *
 * Use c0_MVPConf0 to find out how many TCs are available, setting up
- * cpu_possible_map and the logical/physical mappings.
+ * cpu_possible_mask and the logical/physical mappings.
 */
 int __init smtc_build_cpu_map(int start_cpu_slot)
diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c
index 1f9ca07f53c8..47037ec5589b 100644
--- a/arch/mips/mm/c-octeon.c
+++ b/arch/mips/mm/c-octeon.c
@@ -80,9 +80,9 @@ static void octeon_flush_icache_all_cores(struct vm_area_struct *vma)
        if (vma)
                mask = *mm_cpumask(vma->vm_mm);
        else
-                mask = cpu_online_map;
+                mask = *cpu_online_mask;
-        cpu_clear(cpu, mask);
+        cpumask_clear_cpu(cpu, &mask);
-        for_each_cpu_mask(cpu, mask)
+        for_each_cpu(cpu, &mask)
                octeon_send_ipi_single(cpu, SMP_ICACHE_FLUSH);
        preempt_enable();
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index 46084912e588..3fab2046c8a4 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -98,7 +98,7 @@ void *dma_alloc_noncoherent(struct device *dev, size_t size,
 EXPORT_SYMBOL(dma_alloc_noncoherent);
 static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
-        dma_addr_t * dma_handle, gfp_t gfp)
+        dma_addr_t * dma_handle, gfp_t gfp, struct dma_attrs *attrs)
 {
        void *ret;
@@ -132,7 +132,7 @@ void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
 EXPORT_SYMBOL(dma_free_noncoherent);
 static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
-        dma_addr_t dma_handle)
+        dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
        unsigned long addr = (unsigned long) vaddr;
        int order = get_order(size);
@@ -323,8 +323,8 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 EXPORT_SYMBOL(dma_cache_sync);
 static struct dma_map_ops mips_default_dma_map_ops = {
-        .alloc_coherent = mips_dma_alloc_coherent,
+        .alloc = mips_dma_alloc_coherent,
-        .free_coherent = mips_dma_free_coherent,
+        .free = mips_dma_free_coherent,
        .map_page = mips_dma_map_page,
        .unmap_page = mips_dma_unmap_page,
        .map_sg = mips_dma_map_sg,
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index db17f49886c2..fab316de57e9 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -165,7 +165,7 @@ void __init nlm_smp_setup(void)
        cpu_set(boot_cpu, phys_cpu_present_map);
        __cpu_number_map[boot_cpu] = 0;
        __cpu_logical_map[0] = boot_cpu;
-        cpu_set(0, cpu_possible_map);
+        set_cpu_possible(0, true);
        num_cpus = 1;
        for (i = 0; i < NR_CPUS; i++) {
@@ -177,14 +177,14 @@ void __init nlm_smp_setup(void)
                        cpu_set(i, phys_cpu_present_map);
                        __cpu_number_map[i] = num_cpus;
                        __cpu_logical_map[num_cpus] = i;
-                        cpu_set(num_cpus, cpu_possible_map);
+                        set_cpu_possible(num_cpus, true);
                        ++num_cpus;
                }
        }
        pr_info("Phys CPU present map: %lx, possible map %lx\n",
                (unsigned long)phys_cpu_present_map.bits[0],
-                (unsigned long)cpu_possible_map.bits[0]);
+                (unsigned long)cpumask_bits(cpu_possible_mask)[0]);
        pr_info("Detected %i Slave CPU(s)\n", num_cpus);
        nlm_set_nmi_handler(nlm_boot_secondary_cpus);
diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c
index 2608752898c0..b71fae231049 100644
--- a/arch/mips/pmc-sierra/yosemite/smp.c
+++ b/arch/mips/pmc-sierra/yosemite/smp.c
@@ -146,7 +146,7 @@ static void __cpuinit yos_boot_secondary(int cpu, struct task_struct *idle)
 }
 /*
- * Detect available CPUs, populate cpu_possible_map before smp_init
+ * Detect available CPUs, populate cpu_possible_mask before smp_init
 *
 * We don't want to start the secondary CPU yet nor do we have a nice probing
 * feature in PMON so we just assume presence of the secondary core.
@@ -155,10 +155,10 @@ static void __init yos_smp_setup(void)
 {
        int i;
-        cpus_clear(cpu_possible_map);
+        init_cpu_possible(cpu_none_mask);
        for (i = 0; i < 2; i++) {
-                cpu_set(i, cpu_possible_map);
+                set_cpu_possible(i, true);
                __cpu_number_map[i]     = i;
                __cpu_logical_map[i]    = i;
        }
@@ -169,7 +169,7 @@ static void __init yos_prepare_cpus(unsigned int max_cpus)
        /*
         * Be paranoid.  Enable the IPI only if we're really about to go SMP.
         */
-        if (cpus_weight(cpu_possible_map))
+        if (num_possible_cpus())
                set_c0_status(STATUSF_IP5);
 }
diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index c6851df9ab74..735b43bf8f82 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -76,7 +76,7 @@ static int do_cpumask(cnodeid_t cnode, nasid_t nasid, int highest)
                        /* Only let it join in if it's marked enabled */
                        if ((acpu->cpu_info.flags & KLINFO_ENABLE) &&
                            (tot_cpus_found != NR_CPUS)) {
-                                cpu_set(cpuid, cpu_possible_map);
+                                set_cpu_possible(cpuid, true);
                                alloc_cpupda(cpuid, tot_cpus_found);
                                cpus_found++;
                                tot_cpus_found++;
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index d667875be564..de88e22694a0 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -138,7 +138,7 @@ static void __cpuinit bcm1480_boot_secondary(int cpu, struct task_struct *idle)
 /*
 * Use CFE to find out how many CPUs are available, setting up
- * cpu_possible_map and the logical/physical mappings.
+ * cpu_possible_mask and the logical/physical mappings.
 * XXXKW will the boot CPU ever not be physical 0?
 *
 * Common setup before any secondaries are started
@@ -147,14 +147,13 @@ static void __init bcm1480_smp_setup(void)
 {
        int i, num;
-        cpus_clear(cpu_possible_map);
+        init_cpu_possible(cpumask_of(0));
-        cpu_set(0, cpu_possible_map);
        __cpu_number_map[0] = 0;
        __cpu_logical_map[0] = 0;
        for (i = 1, num = 0; i < NR_CPUS; i++) {
                if (cfe_cpu_stop(i) == 0) {
-                        cpu_set(i, cpu_possible_map);
+                        set_cpu_possible(i, true);
                        __cpu_number_map[i] = ++num;
                        __cpu_logical_map[num] = i;
                }
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index 38e7f6bd7922..285cfef4ebc0 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -126,7 +126,7 @@ static void __cpuinit sb1250_boot_secondary(int cpu, struct task_struct *idle)
 /*
 * Use CFE to find out how many CPUs are available, setting up
- * cpu_possible_map and the logical/physical mappings.
+ * cpu_possible_mask and the logical/physical mappings.
 * XXXKW will the boot CPU ever not be physical 0?
 *
 * Common setup before any secondaries are started
@@ -135,14 +135,13 @@ static void __init sb1250_smp_setup(void)
 {
        int i, num;
-        cpus_clear(cpu_possible_map);
+        init_cpu_possible(cpumask_of(0));
-        cpu_set(0, cpu_possible_map);
        __cpu_number_map[0] = 0;
        __cpu_logical_map[0] = 0;
        for (i = 1, num = 0; i < NR_CPUS; i++) {
                if (cfe_cpu_stop(i) == 0) {
-                        cpu_set(i, cpu_possible_map);
+                        set_cpu_possible(i, true);
                        __cpu_number_map[i] = ++num;
                        __cpu_logical_map[num] = i;
                }
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 3ae56073cc3d..6c6defc24619 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -6,6 +6,7 @@
 #define _ASM_PARISC_ATOMIC_H_
 #include <linux/types.h>
+#include <asm/cmpxchg.h>
 /*
 * Atomic operations that C can't guarantee us.  Useful for
@@ -48,112 +49,6 @@ extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
 #  define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0)
 #endif
-/* This should get optimized out since it's never called.
-** Or get a link error if xchg is used "wrong".
-*/
-extern void __xchg_called_with_bad_pointer(void);
-/* __xchg32/64 defined in arch/parisc/lib/bitops.c */
-extern unsigned long __xchg8(char, char *);
-extern unsigned long __xchg32(int, int *);
-#ifdef CONFIG_64BIT
-extern unsigned long __xchg64(unsigned long, unsigned long *);
-#endif
-/* optimizer better get rid of switch since size is a constant */
-static __inline__ unsigned long
-__xchg(unsigned long x, __volatile__ void * ptr, int size)
-{
-        switch(size) {
-#ifdef CONFIG_64BIT
-        case 8: return __xchg64(x,(unsigned long *) ptr);
-#endif
-        case 4: return __xchg32((int) x, (int *) ptr);
-        case 1: return __xchg8((char) x, (char *) ptr);
-        }
-        __xchg_called_with_bad_pointer();
-        return x;
-}
-/*
-** REVISIT - Abandoned use of LDCW in xchg() for now:
-** o need to test sizeof(*ptr) to avoid clearing adjacent bytes
-** o and while we are at it, could CONFIG_64BIT code use LDCD too?
-**
-**      if (__builtin_constant_p(x) && (x == NULL))
-**              if (((unsigned long)p & 0xf) == 0)
-**                      return __ldcw(p);
-*/
-#define xchg(ptr,x) \
-        ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
-#define __HAVE_ARCH_CMPXCHG     1
-/* bug catcher for when unsupported size is used - won't link */
-extern void __cmpxchg_called_with_bad_pointer(void);
-/* __cmpxchg_u32/u64 defined in arch/parisc/lib/bitops.c */
-extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old, unsigned int new_);
-extern unsigned long __cmpxchg_u64(volatile unsigned long *ptr, unsigned long old, unsigned long new_);
-/* don't worry...optimizer will get rid of most of this */
-static __inline__ unsigned long
-__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
-{
-        switch(size) {
-#ifdef CONFIG_64BIT
-        case 8: return __cmpxchg_u64((unsigned long *)ptr, old, new_);
-#endif
-        case 4: return __cmpxchg_u32((unsigned int *)ptr, (unsigned int) old, (unsigned int) new_);
-        }
-        __cmpxchg_called_with_bad_pointer();
-        return old;
-}
-#define cmpxchg(ptr,o,n)                                                 \
-  ({                                                                     \
-     __typeof__(*(ptr)) _o_ = (o);                                       \
-     __typeof__(*(ptr)) _n_ = (n);                                       \
-     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,           \
-                                    (unsigned long)_n_, sizeof(*(ptr))); \
-  })
-#include <asm-generic/cmpxchg-local.h>
-static inline unsigned long __cmpxchg_local(volatile void *ptr,
-                                      unsigned long old,
-                                      unsigned long new_, int size)
-{
-        switch (size) {
-#ifdef CONFIG_64BIT
-        case 8: return __cmpxchg_u64((unsigned long *)ptr, old, new_);
-#endif
-        case 4: return __cmpxchg_u32(ptr, old, new_);
-        default:
-                return __cmpxchg_local_generic(ptr, old, new_, size);
-        }
-}
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-#define cmpxchg_local(ptr, o, n)                                        \
-        ((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o), \
-                        (unsigned long)(n), sizeof(*(ptr))))
-#ifdef CONFIG_64BIT
-#define cmpxchg64_local(ptr, o, n)                                      \
-  ({                                                                    \
-        BUILD_BUG_ON(sizeof(*(ptr)) != 8);                              \
-        cmpxchg_local((ptr), (o), (n));                                 \
-  })
-#else
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-#endif
 /*
 * Note that we need not lock read accesses - aligned word writes/reads
 * are atomic, so a reader never sees inconsistent values.
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..dbd13354ec41
--- /dev/null
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -0,0 +1,116 @@
+/*
+ * forked from parisc asm/atomic.h which was:
+ *      Copyright (C) 2000 Philipp Rumpf <prumpf@tux.org>
+ *      Copyright (C) 2006 Kyle McMartin <kyle@parisc-linux.org>
+ */
+#ifndef _ASM_PARISC_CMPXCHG_H_
+#define _ASM_PARISC_CMPXCHG_H_
+/* This should get optimized out since it's never called.
+** Or get a link error if xchg is used "wrong".
+*/
+extern void __xchg_called_with_bad_pointer(void);
+/* __xchg32/64 defined in arch/parisc/lib/bitops.c */
+extern unsigned long __xchg8(char, char *);
+extern unsigned long __xchg32(int, int *);
+#ifdef CONFIG_64BIT
+extern unsigned long __xchg64(unsigned long, unsigned long *);
+#endif
+/* optimizer better get rid of switch since size is a constant */
+static inline unsigned long
+__xchg(unsigned long x, __volatile__ void *ptr, int size)
+{
+        switch (size) {
+#ifdef CONFIG_64BIT
+        case 8: return __xchg64(x, (unsigned long *) ptr);
+#endif
+        case 4: return __xchg32((int) x, (int *) ptr);
+        case 1: return __xchg8((char) x, (char *) ptr);
+        }
+        __xchg_called_with_bad_pointer();
+        return x;
+}
+/*
+** REVISIT - Abandoned use of LDCW in xchg() for now:
+** o need to test sizeof(*ptr) to avoid clearing adjacent bytes
+** o and while we are at it, could CONFIG_64BIT code use LDCD too?
+**
+**      if (__builtin_constant_p(x) && (x == NULL))
+**              if (((unsigned long)p & 0xf) == 0)
+**                      return __ldcw(p);
+*/
+#define xchg(ptr, x) \
+        ((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
+#define __HAVE_ARCH_CMPXCHG     1
+/* bug catcher for when unsupported size is used - won't link */
+extern void __cmpxchg_called_with_bad_pointer(void);
+/* __cmpxchg_u32/u64 defined in arch/parisc/lib/bitops.c */
+extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old,
+                                   unsigned int new_);
+extern unsigned long __cmpxchg_u64(volatile unsigned long *ptr,
+                                   unsigned long old, unsigned long new_);
+/* don't worry...optimizer will get rid of most of this */
+static inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
+{
+        switch (size) {
+#ifdef CONFIG_64BIT
+        case 8: return __cmpxchg_u64((unsigned long *)ptr, old, new_);
+#endif
+        case 4: return __cmpxchg_u32((unsigned int *)ptr,
+                                     (unsigned int)old, (unsigned int)new_);
+        }
+        __cmpxchg_called_with_bad_pointer();
+        return old;
+}
+#define cmpxchg(ptr, o, n)                                               \
+({                                                                       \
+        __typeof__(*(ptr)) _o_ = (o);                                    \
+        __typeof__(*(ptr)) _n_ = (n);                                    \
+        (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,        \
+                                    (unsigned long)_n_, sizeof(*(ptr))); \
+})
+#include <asm-generic/cmpxchg-local.h>
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+                                      unsigned long old,
+                                      unsigned long new_, int size)
+{
+        switch (size) {
+#ifdef CONFIG_64BIT
+        case 8: return __cmpxchg_u64((unsigned long *)ptr, old, new_);
+#endif
+        case 4: return __cmpxchg_u32(ptr, old, new_);
+        default:
+                return __cmpxchg_local_generic(ptr, old, new_, size);
+        }
+}
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)                                        \
+        ((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o), \
+                        (unsigned long)(n), sizeof(*(ptr))))
+#ifdef CONFIG_64BIT
+#define cmpxchg64_local(ptr, o, n)                                      \
+({                                                                      \
+        BUILD_BUG_ON(sizeof(*(ptr)) != 8);                              \
+        cmpxchg_local((ptr), (o), (n));                                 \
+})
+#else
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+#endif
+#endif /* _ASM_PARISC_CMPXCHG_H_ */
diff --git a/arch/powerpc/boot/dts/p1020mbg-pc.dtsi b/arch/powerpc/boot/dts/p1020mbg-pc.dtsi
new file mode 100644
index 000000000000..a24699cfea9c
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020mbg-pc.dtsi
@@ -0,0 +1,151 @@
+/*
+ * P1020 MBG-PC Device Tree Source stub (no addresses or top-level ranges)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+&lbc {
+        nor@0,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "cfi-flash";
+                reg = <0x0 0x0 0x4000000>;
+                bank-width = <2>;
+                device-width = <1>;
+                partition@0 {
+                        /* 128KB for DTB Image */
+                        reg = <0x0 0x00020000>;
+                        label = "NOR DTB Image";
+                };
+                partition@20000 {
+                        /* 3.875 MB for Linux Kernel Image */
+                        reg = <0x00020000 0x003e0000>;
+                        label = "NOR Linux Kernel Image";
+                };
+                partition@400000 {
+                        /* 58MB for Root file System */
+                        reg = <0x00400000 0x03a00000>;
+                        label = "NOR Root File System";
+                };
+                partition@3e00000 {
+                        /* This location must not be altered  */
+                        /* 1M for Vitesse 7385 Switch firmware */
+                        reg = <0x3e00000 0x00100000>;
+                        label = "NOR Vitesse-7385 Firmware";
+                        read-only;
+                };
+                partition@3f00000 {
+                        /* This location must not be altered  */
+                        /* 512KB for u-boot Bootloader Image */
+                        /* 512KB for u-boot Environment Variables */
+                        reg = <0x03f00000 0x00100000>;
+                        label = "NOR U-Boot Image";
+                        read-only;
+                };
+        };
+        L2switch@2,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "vitesse-7385";
+                reg = <0x2 0x0 0x20000>;
+        };
+};
+&soc {
+        i2c@3000 {
+                rtc@68 {
+                        compatible = "dallas,ds1339";
+                        reg = <0x68>;
+                };
+        };
+        mdio@24000 {
+                phy0: ethernet-phy@0 {
+                        interrupts = <3 1 0 0>;
+                        reg = <0x0>;
+                };
+                phy1: ethernet-phy@1 {
+                        interrupts = <2 1 0 0>;
+                        reg = <0x1>;
+                };
+        };
+        mdio@25000 {
+                tbi1: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+        mdio@26000 {
+                tbi2: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+        enet0: ethernet@b0000 {
+                fixed-link = <1 1 1000 0 0>;
+                phy-connection-type = "rgmii-id";
+        };
+        enet1: ethernet@b1000 {
+                phy-handle = <&phy0>;
+                tbi-handle = <&tbi1>;
+                phy-connection-type = "sgmii";
+        };
+        enet2: ethernet@b2000 {
+                phy-handle = <&phy1>;
+                phy-connection-type = "rgmii-id";
+        };
+        usb@22000 {
+                phy_type = "ulpi";
+        };
+        /* USB2 is shared with localbus, so it must be disabled
+           by default. We can't put 'status = "disabled";' here
+           since U-Boot doesn't clear the status property when
+           it enables USB2. OTOH, U-Boot does create a new node
+           when there isn't any. So, just comment it out.
+        */
+        usb@23000 {
+                status = "disabled";
+                phy_type = "ulpi";
+        };
+};
diff --git a/arch/powerpc/boot/dts/p1020mbg-pc_32b.dts b/arch/powerpc/boot/dts/p1020mbg-pc_32b.dts
new file mode 100644
index 000000000000..ab8f076eae90
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020mbg-pc_32b.dts
@@ -0,0 +1,89 @@
+/*
+ * P1020 MBG-PC Device Tree Source (32-bit address map)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+/include/ "fsl/p1020si-pre.dtsi"
+/ {
+        model = "fsl,P1020MBG-PC";
+        compatible = "fsl,P1020MBG-PC";
+        memory {
+                device_type = "memory";
+        };
+        lbc: localbus@ffe05000 {
+                reg = <0x0 0xffe05000 0x0 0x1000>;
+                /* NOR and L2 switch */
+                ranges = <0x0 0x0 0x0 0xec000000 0x04000000
+                          0x1 0x0 0x0 0xffa00000 0x00040000
+                          0x2 0x0 0x0 0xffb00000 0x00020000>;
+        };
+        soc: soc@ffe00000 {
+                ranges = <0x0 0x0 0xffe00000 0x100000>;
+        };
+        pci0: pcie@ffe09000 {
+                reg = <0x0 0xffe09000 0x0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0x0 0xa0000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0x0 0xffc10000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+        pci1: pcie@ffe0a000 {
+                reg = <0x0 0xffe0a000 0x0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0x0 0x80000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0x0 0xffc00000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+};
+/include/ "p1020mbg-pc.dtsi"
+/include/ "fsl/p1020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1020mbg-pc_36b.dts b/arch/powerpc/boot/dts/p1020mbg-pc_36b.dts
new file mode 100644
index 000000000000..9e9f401419b1
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020mbg-pc_36b.dts
@@ -0,0 +1,89 @@
+/*
+ * P1020 MBG-PC Device Tree Source (36-bit address map)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+/include/ "fsl/p1020si-pre.dtsi"
+/ {
+        model = "fsl,P1020MBG-PC";
+        compatible = "fsl,P1020MBG-PC";
+        memory {
+                device_type = "memory";
+        };
+        lbc: localbus@fffe05000 {
+                reg = <0xf 0xffe05000 0x0 0x1000>;
+                /* NOR and L2 switch */
+                ranges = <0x0 0x0 0xf 0xec000000 0x04000000
+                          0x1 0x0 0xf 0xffa00000 0x00040000
+                          0x2 0x0 0xf 0xffb00000 0x00020000>;
+        };
+        soc: soc@fffe00000 {
+                ranges = <0x0 0xf 0xffe00000 0x100000>;
+        };
+        pci0: pcie@fffe09000 {
+                reg = <0xf 0xffe09000 0x0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc10000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+        pci1: pcie@fffe0a000 {
+                reg = <0xf 0xffe0a000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+};
+/include/ "p1020mbg-pc.dtsi"
+/include/ "fsl/p1020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1020utm-pc.dtsi b/arch/powerpc/boot/dts/p1020utm-pc.dtsi
new file mode 100644
index 000000000000..7ea85eabcc5c
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020utm-pc.dtsi
@@ -0,0 +1,140 @@
+/*
+ * P1020 UTM-PC Device Tree Source stub (no addresses or top-level ranges)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+&lbc {
+        nor@0,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "cfi-flash";
+                reg = <0x0 0x0 0x2000000>;
+                bank-width = <2>;
+                device-width = <1>;
+                partition@0 {
+                        /* 256KB for DTB Image */
+                        reg = <0x0 0x00040000>;
+                        label = "NOR DTB Image";
+                };
+                partition@40000 {
+                        /* 3.75 MB for Linux Kernel Image */
+                        reg = <0x00040000 0x003c0000>;
+                        label = "NOR Linux Kernel Image";
+                };
+                partition@400000 {
+                        /* 27MB for Root file System */
+                        reg = <0x00400000 0x01b00000>;
+                        label = "NOR Root File System";
+                };
+                partition@1f00000 {
+                        /* This location must not be altered  */
+                        /* 512KB for u-boot Bootloader Image */
+                        /* 512KB for u-boot Environment Variables */
+                        reg = <0x01f00000 0x00100000>;
+                        label = "NOR U-Boot Image";
+                        read-only;
+                };
+        };
+};
+&soc {
+        i2c@3000 {
+                rtc@68 {
+                        compatible = "dallas,ds1339";
+                        reg = <0x68>;
+                };
+        };
+        mdio@24000 {
+                phy0: ethernet-phy@0 {
+                        interrupts = <3 1 0 0>;
+                        reg = <0x0>;
+                };
+                phy1: ethernet-phy@1 {
+                        interrupts = <2 1 0 0>;
+                        reg = <0x1>;
+                };
+                phy2: ethernet-phy@2 {
+                        interrupts = <1 1 0 0>;
+                        reg = <0x2>;
+                };
+        };
+        mdio@25000 {
+                tbi1: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+        mdio@26000 {
+                tbi2: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+        enet0: ethernet@b0000 {
+                phy-handle = <&phy2>;
+                phy-connection-type = "rgmii-id";
+        };
+        enet1: ethernet@b1000 {
+                phy-handle = <&phy0>;
+                tbi-handle = <&tbi1>;
+                phy-connection-type = "sgmii";
+        };
+        enet2: ethernet@b2000 {
+                phy-handle = <&phy1>;
+                phy-connection-type = "rgmii-id";
+        };
+        usb@22000 {
+                phy_type = "ulpi";
+        };
+        /* USB2 is shared with localbus, so it must be disabled
+           by default. We can't put 'status = "disabled";' here
+           since U-Boot doesn't clear the status property when
+           it enables USB2. OTOH, U-Boot does create a new node
+           when there isn't any. So, just comment it out.
+        */
+        usb@23000 {
+                status = "disabled";
+                phy_type = "ulpi";
+        };
+};
diff --git a/arch/powerpc/boot/dts/p1020utm-pc_32b.dts b/arch/powerpc/boot/dts/p1020utm-pc_32b.dts
new file mode 100644
index 000000000000..4bfdd8971cdb
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020utm-pc_32b.dts
@@ -0,0 +1,89 @@
+/*
+ * P1020 UTM-PC Device Tree Source (32-bit address map)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+/include/ "fsl/p1020si-pre.dtsi"
+/ {
+        model = "fsl,P1020UTM-PC";
+        compatible = "fsl,P1020UTM-PC";
+        memory {
+                device_type = "memory";
+        };
+        lbc: localbus@ffe05000 {
+                reg = <0x0 0xffe05000 0x0 0x1000>;
+                /* NOR */
+                ranges = <0x0 0x0 0x0 0xec000000 0x02000000
+                          0x1 0x0 0x0 0xffa00000 0x00040000
+                          0x2 0x0 0x0 0xffb00000 0x00020000>;
+        };
+        soc: soc@ffe00000 {
+                ranges = <0x0 0x0 0xffe00000 0x100000>;
+        };
+        pci0: pcie@ffe09000 {
+                reg = <0x0 0xffe09000 0x0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0x0 0xa0000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0x0 0xffc10000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+        pci1: pcie@ffe0a000 {
+                reg = <0x0 0xffe0a000 0x0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0x0 0x80000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0x0 0xffc00000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+};
+/include/ "p1020utm-pc.dtsi"
+/include/ "fsl/p1020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1020utm-pc_36b.dts b/arch/powerpc/boot/dts/p1020utm-pc_36b.dts
new file mode 100644
index 000000000000..abec53557501
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020utm-pc_36b.dts
@@ -0,0 +1,89 @@
+/*
+ * P1020 UTM-PC Device Tree Source (36-bit address map)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+/include/ "fsl/p1020si-pre.dtsi"
+/ {
+        model = "fsl,P1020UTM-PC";
+        compatible = "fsl,P1020UTM-PC";
+        memory {
+                device_type = "memory";
+        };
+        lbc: localbus@fffe05000 {
+                reg = <0xf 0xffe05000 0x0 0x1000>;
+                /* NOR */
+                ranges = <0x0 0x0 0xf 0xec000000 0x02000000
+                          0x1 0x0 0xf 0xffa00000 0x00040000
+                          0x2 0x0 0xf 0xffb00000 0x00020000>;
+        };
+        soc: soc@fffe00000 {
+                ranges = <0x0 0xf 0xffe00000 0x100000>;
+        };
+        pci0: pcie@fffe09000 {
+                reg = <0xf 0xffe09000 0x0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc10000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+        pci1: pcie@fffe0a000 {
+                reg = <0xf 0xffe0a000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+};
+/include/ "p1020utm-pc.dtsi"
+/include/ "fsl/p1020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p2041rdb.dts b/arch/powerpc/boot/dts/p2041rdb.dts
index 4f957db01230..285213976a7f 100644
--- a/arch/powerpc/boot/dts/p2041rdb.dts
+++ b/arch/powerpc/boot/dts/p2041rdb.dts
@@ -135,7 +135,6 @@
                reg = <0xf 0xfe200000 0 0x1000>;
                ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000
                          0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
-                fsl,msi = <&msi0>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
@@ -151,7 +150,6 @@
                reg = <0xf 0xfe201000 0 0x1000>;
                ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
                          0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
-                fsl,msi = <&msi1>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
@@ -167,7 +165,6 @@
                reg = <0xf 0xfe202000 0 0x1000>;
                ranges = <0x02000000 0 0xe0000000 0xc 0x40000000 0 0x20000000
                          0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
-                fsl,msi = <&msi2>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
diff --git a/arch/powerpc/boot/dts/p3041ds.dts b/arch/powerpc/boot/dts/p3041ds.dts
index f469145abaeb..22a215e94162 100644
--- a/arch/powerpc/boot/dts/p3041ds.dts
+++ b/arch/powerpc/boot/dts/p3041ds.dts
@@ -173,7 +173,6 @@
                reg = <0xf 0xfe200000 0 0x1000>;
                ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000
                          0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
-                fsl,msi = <&msi0>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
@@ -189,7 +188,6 @@
                reg = <0xf 0xfe201000 0 0x1000>;
                ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
                          0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
-                fsl,msi = <&msi1>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
@@ -205,7 +203,6 @@
                reg = <0xf 0xfe202000 0 0x1000>;
                ranges = <0x02000000 0 0xe0000000 0xc 0x40000000 0 0x20000000
                          0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
-                fsl,msi = <&msi2>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
@@ -221,7 +218,6 @@
                reg = <0xf 0xfe203000 0 0x1000>;
                ranges = <0x02000000 0 0xe0000000 0xc 0x60000000 0 0x20000000
                          0x01000000 0 0x00000000 0xf 0xf8030000 0 0x00010000>;
-                fsl,msi = <&msi2>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
diff --git a/arch/powerpc/boot/dts/p3060qds.dts b/arch/powerpc/boot/dts/p3060qds.dts
index 529042e4b9a2..9ae875c8a211 100644
--- a/arch/powerpc/boot/dts/p3060qds.dts
+++ b/arch/powerpc/boot/dts/p3060qds.dts
@@ -212,7 +212,6 @@
                reg = <0xf 0xfe200000 0 0x1000>;
                ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000
                          0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
-                fsl,msi = <&msi0>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
@@ -228,7 +227,6 @@
                reg = <0xf 0xfe201000 0 0x1000>;
                ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
                          0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
-                fsl,msi = <&msi1>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
diff --git a/arch/powerpc/boot/dts/p4080ds.dts b/arch/powerpc/boot/dts/p4080ds.dts
index 6d60e54e50a0..3e204609d02e 100644
--- a/arch/powerpc/boot/dts/p4080ds.dts
+++ b/arch/powerpc/boot/dts/p4080ds.dts
@@ -141,7 +141,6 @@
                reg = <0xf 0xfe200000 0 0x1000>;
                ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000
                          0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
-                fsl,msi = <&msi0>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
@@ -157,7 +156,6 @@
                reg = <0xf 0xfe201000 0 0x1000>;
                ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
                          0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
-                fsl,msi = <&msi1>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
@@ -173,7 +171,6 @@
                reg = <0xf 0xfe202000 0 0x1000>;
                ranges = <0x02000000 0 0xe0000000 0xc 0x40000000 0 0x20000000
                          0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
-                fsl,msi = <&msi2>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
diff --git a/arch/powerpc/boot/dts/p5020ds.dts b/arch/powerpc/boot/dts/p5020ds.dts
index 1c250684c902..27c07ed6adc1 100644
--- a/arch/powerpc/boot/dts/p5020ds.dts
+++ b/arch/powerpc/boot/dts/p5020ds.dts
@@ -173,7 +173,6 @@
                reg = <0xf 0xfe200000 0 0x1000>;
                ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000
                          0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
-                fsl,msi = <&msi0>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
@@ -189,7 +188,6 @@
                reg = <0xf 0xfe201000 0 0x1000>;
                ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
                          0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
-                fsl,msi = <&msi1>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
@@ -205,7 +203,6 @@
                reg = <0xf 0xfe202000 0 0x1000>;
                ranges = <0x02000000 0 0xe0000000 0xc 0x40000000 0 0x20000000
                          0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
-                fsl,msi = <&msi2>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
@@ -221,7 +218,6 @@
                reg = <0xf 0xfe203000 0 0x1000>;
                ranges = <0x02000000 0 0xe0000000 0xc 0x60000000 0 0x20000000
                          0x01000000 0 0x00000000 0xf 0xf8030000 0 0x00010000>;
-                fsl,msi = <&msi2>;
                pcie@0 {
                        ranges = <0x02000000 0 0xe0000000
                                  0x02000000 0 0xe0000000
diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig
index f8aef205d222..91db656294e8 100644
--- a/arch/powerpc/configs/corenet32_smp_defconfig
+++ b/arch/powerpc/configs/corenet32_smp_defconfig
@@ -116,6 +116,7 @@ CONFIG_SERIAL_8250_RSA=y
 CONFIG_HW_RANDOM=y
 CONFIG_NVRAM=y
 CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_MPC=y
 CONFIG_SPI=y
 CONFIG_SPI_GPIO=y
diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig
index 82b13bfcf3c0..6798343580f0 100644
--- a/arch/powerpc/configs/corenet64_smp_defconfig
+++ b/arch/powerpc/configs/corenet64_smp_defconfig
@@ -71,6 +71,8 @@ CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
 CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_MPC=y
 # CONFIG_HWMON is not set
 CONFIG_VIDEO_OUTPUT_CONTROL=y
 # CONFIG_HID_SUPPORT is not set
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
index b7ac92a8b28f..62bb723c5b54 100644
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ b/arch/powerpc/configs/mpc85xx_defconfig
@@ -117,6 +117,7 @@ CONFIG_SERIAL_8250_RSA=y
 CONFIG_SERIAL_QE=m
 CONFIG_NVRAM=y
 CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_CPM=m
 CONFIG_I2C_MPC=y
 CONFIG_SPI=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
index 41d5e4709a08..d1828427ae55 100644
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ b/arch/powerpc/configs/mpc85xx_smp_defconfig
@@ -119,6 +119,7 @@ CONFIG_SERIAL_8250_RSA=y
 CONFIG_SERIAL_QE=m
 CONFIG_NVRAM=y
 CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_CPM=m
 CONFIG_I2C_MPC=y
 CONFIG_SPI=y
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index dd70fac57ec8..62678e365ca0 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -22,9 +22,11 @@
 /* Some dma direct funcs must be visible for use in other dma_ops */
 extern void *dma_direct_alloc_coherent(struct device *dev, size_t size,
-                                       dma_addr_t *dma_handle, gfp_t flag);
+                                       dma_addr_t *dma_handle, gfp_t flag,
+                                       struct dma_attrs *attrs);
 extern void dma_direct_free_coherent(struct device *dev, size_t size,
-                                     void *vaddr, dma_addr_t dma_handle);
+                                     void *vaddr, dma_addr_t dma_handle,
+                                     struct dma_attrs *attrs);
 #ifdef CONFIG_NOT_COHERENT_CACHE
@@ -130,23 +132,29 @@ static inline int dma_supported(struct device *dev, u64 mask)
 extern int dma_set_mask(struct device *dev, u64 dma_mask);
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+#define dma_alloc_coherent(d,s,h,f)     dma_alloc_attrs(d,s,h,f,NULL)
-                                       dma_addr_t *dma_handle, gfp_t flag)
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+                                    dma_addr_t *dma_handle, gfp_t flag,
+                                    struct dma_attrs *attrs)
 {
        struct dma_map_ops *dma_ops = get_dma_ops(dev);
        void *cpu_addr;
        BUG_ON(!dma_ops);
-        cpu_addr = dma_ops->alloc_coherent(dev, size, dma_handle, flag);
+        cpu_addr = dma_ops->alloc(dev, size, dma_handle, flag, attrs);
        debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
        return cpu_addr;
 }
-static inline void dma_free_coherent(struct device *dev, size_t size,
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
-                                     void *cpu_addr, dma_addr_t dma_handle)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+                                  void *cpu_addr, dma_addr_t dma_handle,
+                                  struct dma_attrs *attrs)
 {
        struct dma_map_ops *dma_ops = get_dma_ops(dev);
@@ -154,7 +162,7 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
        debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-        dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
+        dma_ops->free(dev, size, cpu_addr, dma_handle, attrs);
 }
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h
index f3b0c2cc9fea..976835d8f22e 100644
--- a/arch/powerpc/include/asm/epapr_hcalls.h
+++ b/arch/powerpc/include/asm/epapr_hcalls.h
@@ -134,10 +134,15 @@
 * whether they will be clobbered.
 *
 * Note that r11 can be used as an output parameter.
+ *
+ * The "memory" clobber is only necessary for hcalls where the Hypervisor
+ * will read or write guest memory. However, we add it to all hcalls because
+ * the impact is minimal, and we want to ensure that it's present for the
+ * hcalls that need it.
 */
 /* List of common clobbered registers.  Do not use this macro. */
-#define EV_HCALL_CLOBBERS "r0", "r12", "xer", "ctr", "lr", "cc"
+#define EV_HCALL_CLOBBERS "r0", "r12", "xer", "ctr", "lr", "cc", "memory"
 #define EV_HCALL_CLOBBERS8 EV_HCALL_CLOBBERS
 #define EV_HCALL_CLOBBERS7 EV_HCALL_CLOBBERS8, "r10"
diff --git a/arch/powerpc/include/asm/fsl_guts.h b/arch/powerpc/include/asm/fsl_guts.h
index ce04530d2000..aa4c488589ce 100644
--- a/arch/powerpc/include/asm/fsl_guts.h
+++ b/arch/powerpc/include/asm/fsl_guts.h
@@ -16,15 +16,6 @@
 #define __ASM_POWERPC_FSL_GUTS_H__
 #ifdef __KERNEL__
-/*
- * These #ifdefs are safe because it's not possible to build a kernel that
- * runs on e500 and e600 cores.
- */
-#if !defined(CONFIG_PPC_85xx) && !defined(CONFIG_PPC_86xx)
-#error Only 85xx and 86xx SOCs are supported
-#endif
 /**
 * Global Utility Registers.
 *
@@ -36,11 +27,7 @@
 * different names.  In these cases, one name is chosen to avoid extraneous
 * #ifdefs.
 */
-#ifdef CONFIG_PPC_85xx
+struct ccsr_guts {
-struct ccsr_guts_85xx {
-#else
-struct ccsr_guts_86xx {
-#endif
        __be32  porpllsr;       /* 0x.0000 - POR PLL Ratio Status Register */
        __be32  porbmsr;        /* 0x.0004 - POR Boot Mode Status Register */
        __be32  porimpscr;      /* 0x.0008 - POR I/O Impedance Status and Control Register */
@@ -77,11 +64,8 @@ struct ccsr_guts_86xx {
        u8      res0a8[0xb0 - 0xa8];
        __be32  rstcr;          /* 0x.00b0 - Reset Control Register */
        u8      res0b4[0xc0 - 0xb4];
-#ifdef CONFIG_PPC_85xx
+        __be32  iovselsr;       /* 0x.00c0 - I/O voltage select status register
-        __be32  iovselsr;       /* 0x.00c0 - I/O voltage select status register */
+                                             Called 'elbcvselcr' on 86xx SOCs */
-#else
-        __be32  elbcvselcr;     /* 0x.00c0 - eLBC Voltage Select Ctrl Reg */
-#endif
        u8      res0c4[0x224 - 0xc4];
        __be32  iodelay1;       /* 0x.0224 - IO delay control register 1 */
        __be32  iodelay2;       /* 0x.0228 - IO delay control register 2 */
@@ -136,7 +120,7 @@ struct ccsr_guts_86xx {
 * ch: The channel on the DMA controller (0, 1, 2, or 3)
 * device: The device to set as the source (CCSR_GUTS_DMACR_DEV_xx)
 */
-static inline void guts_set_dmacr(struct ccsr_guts_86xx __iomem *guts,
+static inline void guts_set_dmacr(struct ccsr_guts __iomem *guts,
        unsigned int co, unsigned int ch, unsigned int device)
 {
        unsigned int shift = 16 + (8 * (1 - co) + 2 * (3 - ch));
@@ -172,7 +156,7 @@ static inline void guts_set_dmacr(struct ccsr_guts_86xx __iomem *guts,
 * ch: The channel on the DMA controller (0, 1, 2, or 3)
 * value: the new value for the bit (0 or 1)
 */
-static inline void guts_set_pmuxcr_dma(struct ccsr_guts_86xx __iomem *guts,
+static inline void guts_set_pmuxcr_dma(struct ccsr_guts __iomem *guts,
        unsigned int co, unsigned int ch, unsigned int value)
 {
        if ((ch == 0) || (ch == 3)) {
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 3f6464b4d970..bcfdcd22c766 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -17,7 +17,8 @@
 * to the dma address (mapping) of the first page.
 */
 static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
-                                      dma_addr_t *dma_handle, gfp_t flag)
+                                      dma_addr_t *dma_handle, gfp_t flag,
+                                      struct dma_attrs *attrs)
 {
        return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
                                    dma_handle, dev->coherent_dma_mask, flag,
@@ -25,7 +26,8 @@ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
 }
 static void dma_iommu_free_coherent(struct device *dev, size_t size,
-                                    void *vaddr, dma_addr_t dma_handle)
+                                    void *vaddr, dma_addr_t dma_handle,
+                                    struct dma_attrs *attrs)
 {
        iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
 }
@@ -105,8 +107,8 @@ static u64 dma_iommu_get_required_mask(struct device *dev)
 }
 struct dma_map_ops dma_iommu_ops = {
-        .alloc_coherent         = dma_iommu_alloc_coherent,
+        .alloc                  = dma_iommu_alloc_coherent,
-        .free_coherent          = dma_iommu_free_coherent,
+        .free                   = dma_iommu_free_coherent,
        .map_sg                 = dma_iommu_map_sg,
        .unmap_sg               = dma_iommu_unmap_sg,
        .dma_supported          = dma_iommu_dma_supported,
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 1ebc9189aada..4ab88dafb235 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -47,8 +47,8 @@ static u64 swiotlb_powerpc_get_required(struct device *dev)
 * for everything else.
 */
 struct dma_map_ops swiotlb_dma_ops = {
-        .alloc_coherent = dma_direct_alloc_coherent,
+        .alloc = dma_direct_alloc_coherent,
-        .free_coherent = dma_direct_free_coherent,
+        .free = dma_direct_free_coherent,
        .map_sg = swiotlb_map_sg_attrs,
        .unmap_sg = swiotlb_unmap_sg_attrs,
        .dma_supported = swiotlb_dma_supported,
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 7d0233c12ee3..b1ec983dcec8 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -26,7 +26,8 @@
 void *dma_direct_alloc_coherent(struct device *dev, size_t size,
-                                dma_addr_t *dma_handle, gfp_t flag)
+                                dma_addr_t *dma_handle, gfp_t flag,
+                                struct dma_attrs *attrs)
 {
        void *ret;
 #ifdef CONFIG_NOT_COHERENT_CACHE
@@ -54,7 +55,8 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 }
 void dma_direct_free_coherent(struct device *dev, size_t size,
-                              void *vaddr, dma_addr_t dma_handle)
+                              void *vaddr, dma_addr_t dma_handle,
+                              struct dma_attrs *attrs)
 {
 #ifdef CONFIG_NOT_COHERENT_CACHE
        __dma_free_coherent(size, vaddr);
@@ -150,8 +152,8 @@ static inline void dma_direct_sync_single(struct device *dev,
 #endif
 struct dma_map_ops dma_direct_ops = {
-        .alloc_coherent                 = dma_direct_alloc_coherent,
+        .alloc                          = dma_direct_alloc_coherent,
-        .free_coherent                  = dma_direct_free_coherent,
+        .free                           = dma_direct_free_coherent,
        .map_sg                         = dma_direct_map_sg,
        .unmap_sg                       = dma_direct_unmap_sg,
        .dma_supported                  = dma_direct_dma_supported,
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index cfe7a38708c3..18bdf74fa164 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -40,6 +40,8 @@
 #include <asm/prom.h>
 #include <asm/rtas.h>
 #include <asm/fadump.h>
+#include <asm/debug.h>
+#include <asm/setup.h>
 static struct fw_dump fw_dump;
 static struct fadump_mem_struct fdm;
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 79bb282e6501..b01d14eeca8d 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -65,7 +65,8 @@ static struct of_device_id __initdata ibmebus_matches[] = {
 static void *ibmebus_alloc_coherent(struct device *dev,
                                    size_t size,
                                    dma_addr_t *dma_handle,
-                                    gfp_t flag)
+                                    gfp_t flag,
+                                    struct dma_attrs *attrs)
 {
        void *mem;
@@ -77,7 +78,8 @@ static void *ibmebus_alloc_coherent(struct device *dev,
 static void ibmebus_free_coherent(struct device *dev,
                                  size_t size, void *vaddr,
-                                  dma_addr_t dma_handle)
+                                  dma_addr_t dma_handle,
+                                  struct dma_attrs *attrs)
 {
        kfree(vaddr);
 }
@@ -136,8 +138,8 @@ static u64 ibmebus_dma_get_required_mask(struct device *dev)
 }
 static struct dma_map_ops ibmebus_dma_ops = {
-        .alloc_coherent     = ibmebus_alloc_coherent,
+        .alloc              = ibmebus_alloc_coherent,
-        .free_coherent      = ibmebus_free_coherent,
+        .free               = ibmebus_free_coherent,
        .map_sg             = ibmebus_map_sg,
        .unmap_sg           = ibmebus_unmap_sg,
        .dma_supported      = ibmebus_dma_supported,
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 76a6e40a6f7c..782bd0a3c2f0 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -24,6 +24,7 @@
 #include <asm/current.h>
 #include <asm/processor.h>
 #include <asm/machdep.h>
+#include <asm/debug.h>
 /*
 * This table contains the mapping between PowerPC hardware trap types, and
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index b2f7c8480bf6..a3a99901c8ec 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -482,7 +482,8 @@ static void vio_cmo_balance(struct work_struct *work)
 }
 static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size,
-                                          dma_addr_t *dma_handle, gfp_t flag)
+                                          dma_addr_t *dma_handle, gfp_t flag,
+                                          struct dma_attrs *attrs)
 {
        struct vio_dev *viodev = to_vio_dev(dev);
        void *ret;
@@ -492,7 +493,7 @@ static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size,
                return NULL;
        }
-        ret = dma_iommu_ops.alloc_coherent(dev, size, dma_handle, flag);
+        ret = dma_iommu_ops.alloc(dev, size, dma_handle, flag, attrs);
        if (unlikely(ret == NULL)) {
                vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
                atomic_inc(&viodev->cmo.allocs_failed);
@@ -502,11 +503,12 @@ static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size,
 }
 static void vio_dma_iommu_free_coherent(struct device *dev, size_t size,
-                                        void *vaddr, dma_addr_t dma_handle)
+                                        void *vaddr, dma_addr_t dma_handle,
+                                        struct dma_attrs *attrs)
 {
        struct vio_dev *viodev = to_vio_dev(dev);
-        dma_iommu_ops.free_coherent(dev, size, vaddr, dma_handle);
+        dma_iommu_ops.free(dev, size, vaddr, dma_handle, attrs);
        vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
 }
@@ -607,8 +609,8 @@ static u64 vio_dma_get_required_mask(struct device *dev)
 }
 struct dma_map_ops vio_dma_mapping_ops = {
-        .alloc_coherent    = vio_dma_iommu_alloc_coherent,
+        .alloc             = vio_dma_iommu_alloc_coherent,
-        .free_coherent     = vio_dma_iommu_free_coherent,
+        .free              = vio_dma_iommu_free_coherent,
        .map_sg            = vio_dma_iommu_map_sg,
        .unmap_sg          = vio_dma_iommu_unmap_sg,
        .map_page          = vio_dma_iommu_map_page,
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index f1950d131827..135663a3e4fc 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -21,6 +21,7 @@
 #include <asm/disassemble.h>
 #include <asm/kvm_book3s.h>
 #include <asm/reg.h>
+#include <asm/switch_to.h>
 #define OP_19_XOP_RFID          18
 #define OP_19_XOP_RFI           50
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index bed1279aa6a8..e1b60f56f2a1 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -173,9 +173,9 @@ static void __init kvm_linear_init_one(ulong size, int count, int type)
 static struct kvmppc_linear_info *kvm_alloc_linear(int type)
 {
-        struct kvmppc_linear_info *ri;
+        struct kvmppc_linear_info *ri, *ret;
-        ri = NULL;
+        ret = NULL;
        spin_lock(&linear_lock);
        list_for_each_entry(ri, &free_linears, list) {
                if (ri->type != type)
@@ -183,11 +183,12 @@ static struct kvmppc_linear_info *kvm_alloc_linear(int type)
                list_del(&ri->list);
                atomic_inc(&ri->use_count);
+                memset(ri->base_virt, 0, ri->npages << PAGE_SHIFT);
+                ret = ri;
                break;
        }
        spin_unlock(&linear_lock);
-        memset(ri->base_virt, 0, ri->npages << PAGE_SHIFT);
+        return ret;
-        return ri;
 }
 static void kvm_release_linear(struct kvmppc_linear_info *ri)
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 3f7b674dd4bf..d3fb4df02c41 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -46,8 +46,10 @@ _GLOBAL(__kvmppc_vcore_entry)
        /* Save host state to the stack */
        stdu    r1, -SWITCH_FRAME_SIZE(r1)
-        /* Save non-volatile registers (r14 - r31) */
+        /* Save non-volatile registers (r14 - r31) and CR */
        SAVE_NVGPRS(r1)
+        mfcr    r3
+        std     r3, _CCR(r1)
        /* Save host DSCR */
 BEGIN_FTR_SECTION
@@ -157,8 +159,10 @@ kvmppc_handler_highmem:
         * R13      = PACA
         */
-        /* Restore non-volatile host registers (r14 - r31) */
+        /* Restore non-volatile host registers (r14 - r31) and CR */
        REST_NVGPRS(r1)
+        ld      r4, _CCR(r1)
+        mtcr    r4
        addi    r1, r1, SWITCH_FRAME_SIZE
        ld      r0, PPC_LR_STKOFF(r1)
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index 0a8515a5c042..3e35383bdb21 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -84,6 +84,10 @@ kvm_start_entry:
        /* Save non-volatile registers (r14 - r31) */
        SAVE_NVGPRS(r1)
+        /* Save CR */
+        mfcr    r14
+        stw     r14, _CCR(r1)
        /* Save LR */
        PPC_STL r0, _LINK(r1)
@@ -165,6 +169,9 @@ kvm_exit_loop:
        PPC_LL  r4, _LINK(r1)
        mtlr    r4
+        lwz     r14, _CCR(r1)
+        mtcr    r14
        /* Restore non-volatile host registers (r14 - r31) */
        REST_NVGPRS(r1)
diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c
index e70ef2d86431..a59a25a13218 100644
--- a/arch/powerpc/kvm/book3s_paired_singles.c
+++ b/arch/powerpc/kvm/book3s_paired_singles.c
@@ -24,6 +24,7 @@
 #include <asm/kvm_fpu.h>
 #include <asm/reg.h>
 #include <asm/cacheflush.h>
+#include <asm/switch_to.h>
 #include <linux/vmalloc.h>
 /* #define DEBUG */
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 7340e1090b77..7759053d391b 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -33,6 +33,7 @@
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 #include <asm/mmu_context.h>
+#include <asm/switch_to.h>
 #include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
@@ -776,6 +777,7 @@ program_interrupt:
        }
        }
+        preempt_disable();
        if (!(r & RESUME_HOST)) {
                /* To avoid clobbering exit_reason, only check for signals if
                 * we aren't already exiting to userspace for some other
@@ -797,8 +799,6 @@ program_interrupt:
                        run->exit_reason = KVM_EXIT_INTR;
                        r = -EINTR;
                } else {
-                        preempt_disable();
                        /* In case an interrupt came in that was triggered
                         * from userspace (like DEC), we need to check what
                         * to inject now! */
@@ -880,7 +880,8 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
        switch (reg->id) {
        case KVM_REG_PPC_HIOR:
-                r = put_user(to_book3s(vcpu)->hior, (u64 __user *)reg->addr);
+                r = copy_to_user((u64 __user *)(long)reg->addr,
+                                &to_book3s(vcpu)->hior, sizeof(u64));
                break;
        default:
                break;
@@ -895,7 +896,8 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
        switch (reg->id) {
        case KVM_REG_PPC_HIOR:
-                r = get_user(to_book3s(vcpu)->hior, (u64 __user *)reg->addr);
+                r = copy_from_user(&to_book3s(vcpu)->hior,
+                                   (u64 __user *)(long)reg->addr, sizeof(u64));
                if (!r)
                        to_book3s(vcpu)->hior_explicit = true;
                break;
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index 10d8ef602e5c..c8c4b878795a 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -34,7 +34,8 @@
 /* r2 is special: it holds 'current', and it made nonvolatile in the
 * kernel with the -ffixed-r2 gcc option. */
 #define HOST_R2         12
-#define HOST_NV_GPRS    16
+#define HOST_CR         16
+#define HOST_NV_GPRS    20
 #define HOST_NV_GPR(n)  (HOST_NV_GPRS + ((n - 14) * 4))
 #define HOST_MIN_STACK_SIZE (HOST_NV_GPR(31) + 4)
 #define HOST_STACK_SIZE (((HOST_MIN_STACK_SIZE + 15) / 16) * 16) /* Align. */
@@ -296,8 +297,10 @@ heavyweight_exit:
        /* Return to kvm_vcpu_run(). */
        lwz     r4, HOST_STACK_LR(r1)
+        lwz     r5, HOST_CR(r1)
        addi    r1, r1, HOST_STACK_SIZE
        mtlr    r4
+        mtcr    r5
        /* r3 still contains the return code from kvmppc_handle_exit(). */
        blr
@@ -314,6 +317,8 @@ _GLOBAL(__kvmppc_vcpu_run)
        stw     r3, HOST_RUN(r1)
        mflr    r3
        stw     r3, HOST_STACK_LR(r1)
+        mfcr    r5
+        stw     r5, HOST_CR(r1)
        /* Save host non-volatile register state to stack. */
        stw     r14, HOST_NV_GPR(r14)(r1)
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pci.c b/arch/powerpc/platforms/52xx/mpc52xx_pci.c
index bfb11e01133e..e2d401ad8fbb 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pci.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pci.c
@@ -93,7 +93,7 @@ struct mpc52xx_pci {
 };
 /* MPC5200 device tree match tables */
-const struct of_device_id mpc52xx_pci_ids[] __initdata = {
+const struct of_device_id mpc52xx_pci_ids[] __initconst = {
        { .type = "pci", .compatible = "fsl,mpc5200-pci", },
        { .type = "pci", .compatible = "mpc5200-pci", },
        {}
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index 3754ddc00af7..9a6f04406e0d 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -270,7 +270,7 @@ static void __init mpc85xx_mds_qe_init(void)
        if (machine_is(p1021_mds)) {
-                struct ccsr_guts_85xx __iomem *guts;
+                struct ccsr_guts __iomem *guts;
                np = of_find_node_by_name(NULL, "global-utilities");
                if (np) {
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index 9848f9e39853..313fce4f5574 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -127,7 +127,7 @@ static void __init mpc85xx_rdb_setup_arch(void)
 #if defined(CONFIG_UCC_GETH) || defined(CONFIG_SERIAL_QE)
        if (machine_is(p1025_rdb)) {
-                struct ccsr_guts_85xx __iomem *guts;
+                struct ccsr_guts __iomem *guts;
                np = of_find_node_by_name(NULL, "global-utilities");
                if (np) {
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 0fe88e39945e..e74b7cde9aee 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -150,7 +150,7 @@ static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port)
 {
        struct device_node *guts_node;
        struct device_node *indirect_node = NULL;
-        struct ccsr_guts_85xx __iomem *guts;
+        struct ccsr_guts __iomem *guts;
        u8 __iomem *lbc_lcs0_ba = NULL;
        u8 __iomem *lbc_lcs1_ba = NULL;
        u8 b;
@@ -269,7 +269,7 @@ exit:
 void p1022ds_set_pixel_clock(unsigned int pixclock)
 {
        struct device_node *guts_np = NULL;
-        struct ccsr_guts_85xx __iomem *guts;
+        struct ccsr_guts __iomem *guts;
        unsigned long freq;
        u64 temp;
        u32 pxclk;
diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
index bbc615206c67..62cd3c555bfb 100644
--- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
+++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
@@ -225,7 +225,7 @@ void mpc8610hpcd_set_monitor_port(enum fsl_diu_monitor_port port)
 void mpc8610hpcd_set_pixel_clock(unsigned int pixclock)
 {
        struct device_node *guts_np = NULL;
-        struct ccsr_guts_86xx __iomem *guts;
+        struct ccsr_guts __iomem *guts;
        unsigned long freq;
        u64 temp;
        u32 pxclk;
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index ae9fc7bc17d6..b9f509a34c01 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -564,7 +564,8 @@ static struct iommu_table *cell_get_iommu_table(struct device *dev)
 /* A coherent allocation implies strong ordering */
 static void *dma_fixed_alloc_coherent(struct device *dev, size_t size,
-                                      dma_addr_t *dma_handle, gfp_t flag)
+                                      dma_addr_t *dma_handle, gfp_t flag,
+                                      struct dma_attrs *attrs)
 {
        if (iommu_fixed_is_weak)
                return iommu_alloc_coherent(dev, cell_get_iommu_table(dev),
@@ -572,18 +573,19 @@ static void *dma_fixed_alloc_coherent(struct device *dev, size_t size,
                                            device_to_mask(dev), flag,
                                            dev_to_node(dev));
        else
-                return dma_direct_ops.alloc_coherent(dev, size, dma_handle,
+                return dma_direct_ops.alloc(dev, size, dma_handle, flag,
-                                                     flag);
+                                            attrs);
 }
 static void dma_fixed_free_coherent(struct device *dev, size_t size,
-                                    void *vaddr, dma_addr_t dma_handle)
+                                    void *vaddr, dma_addr_t dma_handle,
+                                    struct dma_attrs *attrs)
 {
        if (iommu_fixed_is_weak)
                iommu_free_coherent(cell_get_iommu_table(dev), size, vaddr,
                                    dma_handle);
        else
-                dma_direct_ops.free_coherent(dev, size, vaddr, dma_handle);
+                dma_direct_ops.free(dev, size, vaddr, dma_handle, attrs);
 }
 static dma_addr_t dma_fixed_map_page(struct device *dev, struct page *page,
@@ -642,8 +644,8 @@ static int dma_fixed_dma_supported(struct device *dev, u64 mask)
 static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask);
 struct dma_map_ops dma_iommu_fixed_ops = {
-        .alloc_coherent = dma_fixed_alloc_coherent,
+        .alloc          = dma_fixed_alloc_coherent,
-        .free_coherent  = dma_fixed_free_coherent,
+        .free           = dma_fixed_free_coherent,
        .map_sg         = dma_fixed_map_sg,
        .unmap_sg       = dma_fixed_unmap_sg,
        .dma_supported  = dma_fixed_dma_supported,
diff --git a/arch/powerpc/platforms/cell/qpace_setup.c b/arch/powerpc/platforms/cell/qpace_setup.c
index 7f9b6742f8b6..6e3409d590ac 100644
--- a/arch/powerpc/platforms/cell/qpace_setup.c
+++ b/arch/powerpc/platforms/cell/qpace_setup.c
@@ -61,7 +61,7 @@ static void qpace_progress(char *s, unsigned short hex)
        printk("*** %04x : %s\n", hex, s ? s : "");
 }
-static const struct of_device_id qpace_bus_ids[] __initdata = {
+static const struct of_device_id qpace_bus_ids[] __initconst = {
        { .type = "soc", },
        { .compatible = "soc", },
        { .type = "spider", },
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index fa3e294fd343..4ab087671185 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -140,7 +140,7 @@ static int __devinit cell_setup_phb(struct pci_controller *phb)
        return 0;
 }
-static const struct of_device_id cell_bus_ids[] __initdata = {
+static const struct of_device_id cell_bus_ids[] __initconst = {
        { .type = "soc", },
        { .compatible = "soc", },
        { .type = "spider", },
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 880eb9ce22c5..5606fe36faf2 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -515,7 +515,8 @@ core_initcall(ps3_system_bus_init);
 * to the dma address (mapping) of the first page.
 */
 static void * ps3_alloc_coherent(struct device *_dev, size_t size,
-                                      dma_addr_t *dma_handle, gfp_t flag)
+                                 dma_addr_t *dma_handle, gfp_t flag,
+                                 struct dma_attrs *attrs)
 {
        int result;
        struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
@@ -552,7 +553,7 @@ clean_none:
 }
 static void ps3_free_coherent(struct device *_dev, size_t size, void *vaddr,
-        dma_addr_t dma_handle)
+                              dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
        struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
@@ -701,8 +702,8 @@ static u64 ps3_dma_get_required_mask(struct device *_dev)
 }
 static struct dma_map_ops ps3_sb_dma_ops = {
-        .alloc_coherent = ps3_alloc_coherent,
+        .alloc = ps3_alloc_coherent,
-        .free_coherent = ps3_free_coherent,
+        .free = ps3_free_coherent,
        .map_sg = ps3_sb_map_sg,
        .unmap_sg = ps3_sb_unmap_sg,
        .dma_supported = ps3_dma_supported,
@@ -712,8 +713,8 @@ static struct dma_map_ops ps3_sb_dma_ops = {
 };
 static struct dma_map_ops ps3_ioc0_dma_ops = {
-        .alloc_coherent = ps3_alloc_coherent,
+        .alloc = ps3_alloc_coherent,
-        .free_coherent = ps3_free_coherent,
+        .free = ps3_free_coherent,
        .map_sg = ps3_ioc0_map_sg,
        .unmap_sg = ps3_ioc0_unmap_sg,
        .dma_supported = ps3_dma_supported,
diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c
index 4a4752565856..4cb375c0f8d1 100644
--- a/arch/powerpc/platforms/pseries/eeh_event.c
+++ b/arch/powerpc/platforms/pseries/eeh_event.c
@@ -59,8 +59,7 @@ static int eeh_event_handler(void * dummy)
        struct eeh_event *event;
        struct eeh_dev *edev;
-        daemonize("eehd");
+        set_task_comm(current, "eehd");
-        set_current_state(TASK_INTERRUPTIBLE);
        spin_lock_irqsave(&eeh_eventlist_lock, flags);
        event = NULL;
@@ -83,6 +82,7 @@ static int eeh_event_handler(void * dummy)
        printk(KERN_INFO "EEH: Detected PCI bus error on device %s\n",
               eeh_pci_name(edev->pdev));
+        set_current_state(TASK_INTERRUPTIBLE);  /* Don't add to load average */
        edev = handle_eeh_events(event);
        eeh_clear_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING);
diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index ceb09cbd2329..818e763f8265 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2006 Freescale Semicondutor, Inc. All rights reserved.
+ * Copyright (C) 2006-2010 Freescale Semicondutor, Inc. All rights reserved.
 *
 * Authors:     Shlomi Gridish <gridish@freescale.com>
 *              Li Yang <leoli@freescale.com>
@@ -266,7 +266,19 @@ EXPORT_SYMBOL(qe_clock_source);
 static void qe_snums_init(void)
 {
        int i;
-        static const u8 snum_init[] = {
+        static const u8 snum_init_76[] = {
+                0x04, 0x05, 0x0C, 0x0D, 0x14, 0x15, 0x1C, 0x1D,
+                0x24, 0x25, 0x2C, 0x2D, 0x34, 0x35, 0x88, 0x89,
+                0x98, 0x99, 0xA8, 0xA9, 0xB8, 0xB9, 0xC8, 0xC9,
+                0xD8, 0xD9, 0xE8, 0xE9, 0x44, 0x45, 0x4C, 0x4D,
+                0x54, 0x55, 0x5C, 0x5D, 0x64, 0x65, 0x6C, 0x6D,
+                0x74, 0x75, 0x7C, 0x7D, 0x84, 0x85, 0x8C, 0x8D,
+                0x94, 0x95, 0x9C, 0x9D, 0xA4, 0xA5, 0xAC, 0xAD,
+                0xB4, 0xB5, 0xBC, 0xBD, 0xC4, 0xC5, 0xCC, 0xCD,
+                0xD4, 0xD5, 0xDC, 0xDD, 0xE4, 0xE5, 0xEC, 0xED,
+                0xF4, 0xF5, 0xFC, 0xFD,
+        };
+        static const u8 snum_init_46[] = {
                0x04, 0x05, 0x0C, 0x0D, 0x14, 0x15, 0x1C, 0x1D,
                0x24, 0x25, 0x2C, 0x2D, 0x34, 0x35, 0x88, 0x89,
                0x98, 0x99, 0xA8, 0xA9, 0xB8, 0xB9, 0xC8, 0xC9,
@@ -274,9 +286,15 @@ static void qe_snums_init(void)
                0x28, 0x29, 0x38, 0x39, 0x48, 0x49, 0x58, 0x59,
                0x68, 0x69, 0x78, 0x79, 0x80, 0x81,
        };
+        static const u8 *snum_init;
        qe_num_of_snum = qe_get_num_of_snums();
+        if (qe_num_of_snum == 76)
+                snum_init = snum_init_76;
+        else
+                snum_init = snum_init_46;
        for (i = 0; i < qe_num_of_snum; i++) {
                snums[i].num = snum_init[i];
                snums[i].state = QE_SNUM_STATE_FREE;
diff --git a/arch/sh/Kconfig.debug b/arch/sh/Kconfig.debug
index c1d5a820b1aa..5f2bb4242c0f 100644
--- a/arch/sh/Kconfig.debug
+++ b/arch/sh/Kconfig.debug
@@ -61,6 +61,7 @@ config DUMP_CODE
 config DWARF_UNWINDER
        bool "Enable the DWARF unwinder for stacktraces"
        select FRAME_POINTER
+        depends on SUPERH32
        default n
        help
          Enabling this option will make stacktraces more accurate, at
diff --git a/arch/sh/boards/board-sh7785lcr.c b/arch/sh/boards/board-sh7785lcr.c
index d879848f3cdd..d0d6221d7c2e 100644
--- a/arch/sh/boards/board-sh7785lcr.c
+++ b/arch/sh/boards/board-sh7785lcr.c
@@ -28,6 +28,7 @@
 #include <cpu/sh7785.h>
 #include <asm/heartbeat.h>
 #include <asm/clock.h>
+#include <asm/bl_bit.h>
 /*
 * NOTE: This board has 2 physical memory maps.
diff --git a/arch/sh/boards/mach-hp6xx/pm.c b/arch/sh/boards/mach-hp6xx/pm.c
index adc9b4bba828..8b50cf763c06 100644
--- a/arch/sh/boards/mach-hp6xx/pm.c
+++ b/arch/sh/boards/mach-hp6xx/pm.c
@@ -14,6 +14,7 @@
 #include <linux/gfp.h>
 #include <asm/io.h>
 #include <asm/hd64461.h>
+#include <asm/bl_bit.h>
 #include <mach/hp6xx.h>
 #include <cpu/dac.h>
 #include <asm/freq.h>
diff --git a/arch/sh/drivers/dma/dma-sysfs.c b/arch/sh/drivers/dma/dma-sysfs.c
index b1cb2715ad6e..67ee95603813 100644
--- a/arch/sh/drivers/dma/dma-sysfs.c
+++ b/arch/sh/drivers/dma/dma-sysfs.c
@@ -54,7 +54,7 @@ static int __init dma_subsys_init(void)
        if (unlikely(ret))
                return ret;
-        return device_create_file(dma_subsys.dev_root, &dev_attr_devices.attr);
+        return device_create_file(dma_subsys.dev_root, &dev_attr_devices);
 }
 postcore_initcall(dma_subsys_init);
diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h
index 1a73c3e759a7..8bd965e00a15 100644
--- a/arch/sh/include/asm/dma-mapping.h
+++ b/arch/sh/include/asm/dma-mapping.h
@@ -52,25 +52,31 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
        return dma_addr == 0;
 }
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+#define dma_alloc_coherent(d,s,h,f)     dma_alloc_attrs(d,s,h,f,NULL)
-                                       dma_addr_t *dma_handle, gfp_t gfp)
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+                                    dma_addr_t *dma_handle, gfp_t gfp,
+                                    struct dma_attrs *attrs)
 {
        struct dma_map_ops *ops = get_dma_ops(dev);
        void *memory;
        if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
                return memory;
-        if (!ops->alloc_coherent)
+        if (!ops->alloc)
                return NULL;
-        memory = ops->alloc_coherent(dev, size, dma_handle, gfp);
+        memory = ops->alloc(dev, size, dma_handle, gfp, attrs);
        debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
        return memory;
 }
-static inline void dma_free_coherent(struct device *dev, size_t size,
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
-                                     void *vaddr, dma_addr_t dma_handle)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+                                  void *vaddr, dma_addr_t dma_handle,
+                                  struct dma_attrs *attrs)
 {
        struct dma_map_ops *ops = get_dma_ops(dev);
@@ -78,14 +84,16 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
                return;
        debug_dma_free_coherent(dev, size, vaddr, dma_handle);
-        if (ops->free_coherent)
+        if (ops->free)
-                ops->free_coherent(dev, size, vaddr, dma_handle);
+                ops->free(dev, size, vaddr, dma_handle, attrs);
 }
 /* arch/sh/mm/consistent.c */
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-                                        dma_addr_t *dma_addr, gfp_t flag);
+                                        dma_addr_t *dma_addr, gfp_t flag,
+                                        struct dma_attrs *attrs);
 extern void dma_generic_free_coherent(struct device *dev, size_t size,
-                                      void *vaddr, dma_addr_t dma_handle);
+                                      void *vaddr, dma_addr_t dma_handle,
+                                      struct dma_attrs *attrs);
 #endif /* __ASM_SH_DMA_MAPPING_H */
diff --git a/arch/sh/kernel/cpu/fpu.c b/arch/sh/kernel/cpu/fpu.c
index 7f1b70cace35..f8f7af51c128 100644
--- a/arch/sh/kernel/cpu/fpu.c
+++ b/arch/sh/kernel/cpu/fpu.c
@@ -2,6 +2,7 @@
 #include <linux/slab.h>
 #include <asm/processor.h>
 #include <asm/fpu.h>
+#include <asm/traps.h>
 int init_fpu(struct task_struct *tsk)
 {
diff --git a/arch/sh/kernel/cpu/sh2a/fpu.c b/arch/sh/kernel/cpu/sh2a/fpu.c
index 488d24e0cdf0..98bbaa447c93 100644
--- a/arch/sh/kernel/cpu/sh2a/fpu.c
+++ b/arch/sh/kernel/cpu/sh2a/fpu.c
@@ -14,6 +14,7 @@
 #include <asm/processor.h>
 #include <asm/io.h>
 #include <asm/fpu.h>
+#include <asm/traps.h>
 /* The PR (precision) bit in the FP Status Register must be clear when
 * an frchg instruction is executed, otherwise the instruction is undefined.
diff --git a/arch/sh/kernel/cpu/sh4/fpu.c b/arch/sh/kernel/cpu/sh4/fpu.c
index e74cd6c0f10d..69ab4d3c8d41 100644
--- a/arch/sh/kernel/cpu/sh4/fpu.c
+++ b/arch/sh/kernel/cpu/sh4/fpu.c
@@ -16,6 +16,7 @@
 #include <cpu/fpu.h>
 #include <asm/processor.h>
 #include <asm/fpu.h>
+#include <asm/traps.h>
 /* The PR (precision) bit in the FP Status Register must be clear when
 * an frchg instruction is executed, otherwise the instruction is undefined.
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
index 5853989586ed..04ab5aeaf920 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
@@ -113,7 +113,7 @@ static struct clk_lookup lookups[] = {
        CLKDEV_CON_ID("cpu_clk", &div4_clks[DIV4_I]),
        /* MSTP32 clocks */
-        CLKDEV_CON_ID("sdhi0", &mstp_clks[MSTP004]),
+        CLKDEV_DEV_ID("sh_mobile_sdhi.0", &mstp_clks[MSTP004]),
        CLKDEV_CON_ID("riic0", &mstp_clks[MSTP000]),
        CLKDEV_CON_ID("riic1", &mstp_clks[MSTP000]),
        CLKDEV_CON_ID("riic2", &mstp_clks[MSTP000]),
diff --git a/arch/sh/kernel/cpu/shmobile/pm.c b/arch/sh/kernel/cpu/shmobile/pm.c
index a6f95ae4aae7..08d27fac8d08 100644
--- a/arch/sh/kernel/cpu/shmobile/pm.c
+++ b/arch/sh/kernel/cpu/shmobile/pm.c
@@ -16,6 +16,7 @@
 #include <asm/suspend.h>
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
+#include <asm/bl_bit.h>
 /*
 * Notifier lists for pre/post sleep notification
diff --git a/arch/sh/kernel/dma-nommu.c b/arch/sh/kernel/dma-nommu.c
index 3c55b87f8b63..5b0bfcda6d0b 100644
--- a/arch/sh/kernel/dma-nommu.c
+++ b/arch/sh/kernel/dma-nommu.c
@@ -63,8 +63,8 @@ static void nommu_sync_sg(struct device *dev, struct scatterlist *sg,
 #endif
 struct dma_map_ops nommu_dma_ops = {
-        .alloc_coherent         = dma_generic_alloc_coherent,
+        .alloc                  = dma_generic_alloc_coherent,
-        .free_coherent          = dma_generic_free_coherent,
+        .free                   = dma_generic_free_coherent,
        .map_page               = nommu_map_page,
        .map_sg                 = nommu_map_sg,
 #ifdef CONFIG_DMA_NONCOHERENT
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index 64852ecc6881..ee226e20c20c 100644
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -17,8 +17,8 @@
 #include <linux/irqflags.h>
 #include <linux/smp.h>
 #include <linux/cpuidle.h>
-#include <asm/pgalloc.h>
 #include <linux/atomic.h>
+#include <asm/pgalloc.h>
 #include <asm/smp.h>
 #include <asm/bl_bit.h>
diff --git a/arch/sh/kernel/kgdb.c b/arch/sh/kernel/kgdb.c
index efb6d398dec3..b117781bfea2 100644
--- a/arch/sh/kernel/kgdb.c
+++ b/arch/sh/kernel/kgdb.c
@@ -14,6 +14,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <asm/cacheflush.h>
+#include <asm/traps.h>
 /* Macros for single step instruction identification */
 #define OPCODE_BT(op)           (((op) & 0xff00) == 0x8900)
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index f72e3a951588..94273aaf78c1 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -26,6 +26,7 @@
 #include <asm/mmu_context.h>
 #include <asm/fpu.h>
 #include <asm/syscalls.h>
+#include <asm/switch_to.h>
 void show_regs(struct pt_regs * regs)
 {
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index a17a14d32340..eaebdf6a5c77 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -27,6 +27,7 @@
 #include <asm/smp.h>
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
+#include <asm/setup.h>
 int __cpu_number_map[NR_CPUS];          /* Map physical to logical */
 int __cpu_logical_map[NR_CPUS];         /* Map logical to physical */
diff --git a/arch/sh/kernel/vsyscall/vsyscall-sigreturn.S b/arch/sh/kernel/vsyscall/vsyscall-sigreturn.S
index 555a64f124ca..23af17584054 100644
--- a/arch/sh/kernel/vsyscall/vsyscall-sigreturn.S
+++ b/arch/sh/kernel/vsyscall/vsyscall-sigreturn.S
@@ -34,6 +34,41 @@ __kernel_rt_sigreturn:
 1:      .short  __NR_rt_sigreturn
 .LEND_rt_sigreturn:
        .size __kernel_rt_sigreturn,.-.LSTART_rt_sigreturn
+        .previous
        .section .eh_frame,"a",@progbits
+.LCIE1:
+        .ualong .LCIE1_end - .LCIE1_start
+.LCIE1_start:
+        .ualong 0               /* CIE ID */
+        .byte   0x1             /* Version number */
+        .string "zRS"           /* NUL-terminated augmentation string */
+        .uleb128 0x1            /* Code alignment factor */
+        .sleb128 -4             /* Data alignment factor */
+        .byte   0x11            /* Return address register column */
+        .uleb128 0x1            /* Augmentation length and data */
+        .byte 0x1b              /* DW_EH_PE_pcrel | DW_EH_PE_sdata4. */
+        .byte   0xc, 0xf, 0x0   /* DW_CFA_def_cfa: r15 ofs 0 */
+        .align 2
+.LCIE1_end:
+        .ualong .LFDE0_end-.LFDE0_start /* Length FDE0 */
+.LFDE0_start:
+        .ualong .LFDE0_start-.LCIE1     /* CIE pointer */
+        .ualong .LSTART_sigreturn-.     /* PC-relative start address */
+        .ualong .LEND_sigreturn-.LSTART_sigreturn
+        .uleb128 0                      /* Augmentation */
+        .align 2
+.LFDE0_end:
+        .ualong .LFDE1_end-.LFDE1_start /* Length FDE1 */
+.LFDE1_start:
+        .ualong .LFDE1_start-.LCIE1     /* CIE pointer */
+        .ualong .LSTART_rt_sigreturn-.  /* PC-relative start address */
+        .ualong .LEND_rt_sigreturn-.LSTART_rt_sigreturn
+        .uleb128 0                      /* Augmentation */
+        .align 2
+.LFDE1_end:
        .previous
diff --git a/arch/sh/kernel/vsyscall/vsyscall-trapa.S b/arch/sh/kernel/vsyscall/vsyscall-trapa.S
index 3e70f851cdc6..0eb74d00690a 100644
--- a/arch/sh/kernel/vsyscall/vsyscall-trapa.S
+++ b/arch/sh/kernel/vsyscall/vsyscall-trapa.S
@@ -3,37 +3,34 @@
        .type __kernel_vsyscall,@function
 __kernel_vsyscall:
 .LSTART_vsyscall:
-        /* XXX: We'll have to do something here once we opt to use the vDSO
+        trapa   #0x10
-         * page for something other than the signal trampoline.. as well as
+         nop
-         * fill out .eh_frame -- PFM. */
 .LEND_vsyscall:
        .size __kernel_vsyscall,.-.LSTART_vsyscall
+        .previous
        .section .eh_frame,"a",@progbits
-        .previous
 .LCIE:
        .ualong .LCIE_end - .LCIE_start
 .LCIE_start:
        .ualong 0               /* CIE ID */
        .byte   0x1             /* Version number */
-        .string "zRS"           /* NUL-terminated augmentation string */
+        .string "zR"            /* NUL-terminated augmentation string */
        .uleb128 0x1            /* Code alignment factor */
        .sleb128 -4             /* Data alignment factor */
        .byte   0x11            /* Return address register column */
-                                /* Augmentation length and data (none) */
+        .uleb128 0x1            /* Augmentation length and data */
-        .byte   0xc             /* DW_CFA_def_cfa */
+        .byte 0x1b              /* DW_EH_PE_pcrel | DW_EH_PE_sdata4. */
-        .uleb128 0xf            /* r15 */
+        .byte   0xc,0xf,0x0     /* DW_CFA_def_cfa: r15 ofs 0 */
-        .uleb128 0x0            /* offset 0 */
        .align 2
 .LCIE_end:
        .ualong .LFDE_end-.LFDE_start   /* Length FDE */
 .LFDE_start:
-        .ualong .LCIE                   /* CIE pointer */
+        .ualong .LFDE_start-.LCIE       /* CIE pointer */
-        .ualong .LSTART_vsyscall-.      /* start address */
+        .ualong .LSTART_vsyscall-.      /* PC-relative start address */
        .ualong .LEND_vsyscall-.LSTART_vsyscall
-        .uleb128 0
+        .uleb128 0                      /* Augmentation */
        .align 2
 .LFDE_end:
        .previous
diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c
index 112fea12522a..0e529285b28d 100644
--- a/arch/sh/mm/cache-sh4.c
+++ b/arch/sh/mm/cache-sh4.c
@@ -18,6 +18,7 @@
 #include <linux/highmem.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
+#include <asm/cache_insns.h>
 #include <asm/cacheflush.h>
 /*
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index f251b5f27652..b81d9dbf9fef 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -33,7 +33,8 @@ static int __init dma_init(void)
 fs_initcall(dma_init);
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-                                 dma_addr_t *dma_handle, gfp_t gfp)
+                                 dma_addr_t *dma_handle, gfp_t gfp,
+                                 struct dma_attrs *attrs)
 {
        void *ret, *ret_nocache;
        int order = get_order(size);
@@ -64,7 +65,8 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 }
 void dma_generic_free_coherent(struct device *dev, size_t size,
-                               void *vaddr, dma_addr_t dma_handle)
+                               void *vaddr, dma_addr_t dma_handle,
+                               struct dma_attrs *attrs)
 {
        int order = get_order(size);
        unsigned long pfn = dma_handle >> PAGE_SHIFT;
diff --git a/arch/sh/mm/flush-sh4.c b/arch/sh/mm/flush-sh4.c
index 75a17f5bfa14..0b85dd9dd3a7 100644
--- a/arch/sh/mm/flush-sh4.c
+++ b/arch/sh/mm/flush-sh4.c
@@ -1,5 +1,6 @@
 #include <linux/mm.h>
 #include <asm/mmu_context.h>
+#include <asm/cache_insns.h>
 #include <asm/cacheflush.h>
 #include <asm/traps.h>
diff --git a/arch/sh/mm/sram.c b/arch/sh/mm/sram.c
index bc156ec4545e..2d8fa718d55e 100644
--- a/arch/sh/mm/sram.c
+++ b/arch/sh/mm/sram.c
@@ -9,6 +9,7 @@
 */
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/errno.h>
 #include <asm/sram.h>
 /*
diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h
index 8c0e4f7bb204..48a7c65731d2 100644
--- a/arch/sparc/include/asm/dma-mapping.h
+++ b/arch/sparc/include/asm/dma-mapping.h
@@ -26,24 +26,30 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 #include <asm-generic/dma-mapping-common.h>
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+#define dma_alloc_coherent(d,s,h,f)     dma_alloc_attrs(d,s,h,f,NULL)
-                                       dma_addr_t *dma_handle, gfp_t flag)
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+                                    dma_addr_t *dma_handle, gfp_t flag,
+                                    struct dma_attrs *attrs)
 {
        struct dma_map_ops *ops = get_dma_ops(dev);
        void *cpu_addr;
-        cpu_addr = ops->alloc_coherent(dev, size, dma_handle, flag);
+        cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
        debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
        return cpu_addr;
 }
-static inline void dma_free_coherent(struct device *dev, size_t size,
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
-                                     void *cpu_addr, dma_addr_t dma_handle)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+                                  void *cpu_addr, dma_addr_t dma_handle,
+                                  struct dma_attrs *attrs)
 {
        struct dma_map_ops *ops = get_dma_ops(dev);
        debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-        ops->free_coherent(dev, size, cpu_addr, dma_handle);
+        ops->free(dev, size, cpu_addr, dma_handle, attrs);
 }
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 6fa2f7980e6b..76e4a52aa85e 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -12,8 +12,6 @@
 * the SpitFire page tables.
 */
-#include <asm-generic/pgtable-nopud.h>
 #include <linux/compiler.h>
 #include <linux/const.h>
 #include <asm/types.h>
@@ -22,6 +20,8 @@
 #include <asm/page.h>
 #include <asm/processor.h>
+#include <asm-generic/pgtable-nopud.h>
 /* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB).
 * The page copy blockops can use 0x6000000 to 0x8000000.
 * The TSB is mapped in the 0x8000000 to 0xa000000 range.
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 4643d68713fa..070ed141aac7 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -280,7 +280,8 @@ static inline void iommu_free_ctx(struct iommu *iommu, int ctx)
 }
 static void *dma_4u_alloc_coherent(struct device *dev, size_t size,
-                                   dma_addr_t *dma_addrp, gfp_t gfp)
+                                   dma_addr_t *dma_addrp, gfp_t gfp,
+                                   struct dma_attrs *attrs)
 {
        unsigned long flags, order, first_page;
        struct iommu *iommu;
@@ -330,7 +331,8 @@ static void *dma_4u_alloc_coherent(struct device *dev, size_t size,
 }
 static void dma_4u_free_coherent(struct device *dev, size_t size,
-                                 void *cpu, dma_addr_t dvma)
+                                 void *cpu, dma_addr_t dvma,
+                                 struct dma_attrs *attrs)
 {
        struct iommu *iommu;
        unsigned long flags, order, npages;
@@ -825,8 +827,8 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev,
 }
 static struct dma_map_ops sun4u_dma_ops = {
-        .alloc_coherent         = dma_4u_alloc_coherent,
+        .alloc                  = dma_4u_alloc_coherent,
-        .free_coherent          = dma_4u_free_coherent,
+        .free                   = dma_4u_free_coherent,
        .map_page               = dma_4u_map_page,
        .unmap_page             = dma_4u_unmap_page,
        .map_sg                 = dma_4u_map_sg,
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index d0479e2163fa..21bd73943f7f 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -261,7 +261,8 @@ EXPORT_SYMBOL(sbus_set_sbus64);
 * CPU may access them without any explicit flushing.
 */
 static void *sbus_alloc_coherent(struct device *dev, size_t len,
-                                 dma_addr_t *dma_addrp, gfp_t gfp)
+                                 dma_addr_t *dma_addrp, gfp_t gfp,
+                                 struct dma_attrs *attrs)
 {
        struct platform_device *op = to_platform_device(dev);
        unsigned long len_total = PAGE_ALIGN(len);
@@ -315,7 +316,7 @@ err_nopages:
 }
 static void sbus_free_coherent(struct device *dev, size_t n, void *p,
-                               dma_addr_t ba)
+                               dma_addr_t ba, struct dma_attrs *attrs)
 {
        struct resource *res;
        struct page *pgv;
@@ -407,8 +408,8 @@ static void sbus_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 }
 struct dma_map_ops sbus_dma_ops = {
-        .alloc_coherent         = sbus_alloc_coherent,
+        .alloc                  = sbus_alloc_coherent,
-        .free_coherent          = sbus_free_coherent,
+        .free                   = sbus_free_coherent,
        .map_page               = sbus_map_page,
        .unmap_page             = sbus_unmap_page,
        .map_sg                 = sbus_map_sg,
@@ -436,7 +437,8 @@ arch_initcall(sparc_register_ioport);
 * hwdev should be valid struct pci_dev pointer for PCI devices.
 */
 static void *pci32_alloc_coherent(struct device *dev, size_t len,
-                                  dma_addr_t *pba, gfp_t gfp)
+                                  dma_addr_t *pba, gfp_t gfp,
+                                  struct dma_attrs *attrs)
 {
        unsigned long len_total = PAGE_ALIGN(len);
        void *va;
@@ -489,7 +491,7 @@ err_nopages:
 * past this call are illegal.
 */
 static void pci32_free_coherent(struct device *dev, size_t n, void *p,
-                                dma_addr_t ba)
+                                dma_addr_t ba, struct dma_attrs *attrs)
 {
        struct resource *res;
@@ -645,8 +647,8 @@ static void pci32_sync_sg_for_device(struct device *device, struct scatterlist *
 }
 struct dma_map_ops pci32_dma_ops = {
-        .alloc_coherent         = pci32_alloc_coherent,
+        .alloc                  = pci32_alloc_coherent,
-        .free_coherent          = pci32_free_coherent,
+        .free                   = pci32_free_coherent,
        .map_page               = pci32_map_page,
        .unmap_page             = pci32_unmap_page,
        .map_sg                 = pci32_map_sg,
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index a19c8a063683..35e43673c453 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -104,11 +104,11 @@ static int irq_choose_cpu(const struct cpumask *affinity)
 {
        cpumask_t mask;
-        cpus_and(mask, cpu_online_map, *affinity);
+        cpumask_and(&mask, cpu_online_mask, affinity);
-        if (cpus_equal(mask, cpu_online_map) || cpus_empty(mask))
+        if (cpumask_equal(&mask, cpu_online_mask) || cpumask_empty(&mask))
                return boot_cpu_id;
        else
-                return first_cpu(mask);
+                return cpumask_first(&mask);
 }
 #else
 #define irq_choose_cpu(affinity) boot_cpu_id
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index af5755d20fbe..7661e84a05a0 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -128,7 +128,8 @@ static inline long iommu_batch_end(void)
 }
 static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
-                                   dma_addr_t *dma_addrp, gfp_t gfp)
+                                   dma_addr_t *dma_addrp, gfp_t gfp,
+                                   struct dma_attrs *attrs)
 {
        unsigned long flags, order, first_page, npages, n;
        struct iommu *iommu;
@@ -198,7 +199,7 @@ range_alloc_fail:
 }
 static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
-                                 dma_addr_t dvma)
+                                 dma_addr_t dvma, struct dma_attrs *attrs)
 {
        struct pci_pbm_info *pbm;
        struct iommu *iommu;
@@ -527,8 +528,8 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 }
 static struct dma_map_ops sun4v_dma_ops = {
-        .alloc_coherent                 = dma_4v_alloc_coherent,
+        .alloc                          = dma_4v_alloc_coherent,
-        .free_coherent                  = dma_4v_free_coherent,
+        .free                           = dma_4v_free_coherent,
        .map_page                       = dma_4v_map_page,
        .unmap_page                     = dma_4v_unmap_page,
        .map_sg                         = dma_4v_map_sg,
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 11270ca22c0a..96033e2d6845 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -12,7 +12,7 @@ config TILE
        select GENERIC_PENDING_IRQ if SMP
        select GENERIC_IRQ_SHOW
        select SYS_HYPERVISOR
-        select ARCH_HAVE_NMI_SAFE_CMPXCHG if !M386
+        select ARCH_HAVE_NMI_SAFE_CMPXCHG
 # FIXME: investigate whether we need/want these options.
 #       select HAVE_IOREMAP_PROT
@@ -69,6 +69,9 @@ config ARCH_PHYS_ADDR_T_64BIT
 config ARCH_DMA_ADDR_T_64BIT
        def_bool y
+config NEED_DMA_MAP_STATE
+        def_bool y
 config LOCKDEP_SUPPORT
        def_bool y
@@ -118,7 +121,7 @@ config 64BIT
 config ARCH_DEFCONFIG
        string
-        default "arch/tile/configs/tile_defconfig" if !TILEGX
+        default "arch/tile/configs/tilepro_defconfig" if !TILEGX
        default "arch/tile/configs/tilegx_defconfig" if TILEGX
 source "init/Kconfig"
@@ -240,6 +243,7 @@ endchoice
 config PAGE_OFFSET
        hex
+        depends on !64BIT
        default 0xF0000000 if VMSPLIT_3_75G
        default 0xE0000000 if VMSPLIT_3_5G
        default 0xB0000000 if VMSPLIT_2_75G
diff --git a/arch/tile/Makefile b/arch/tile/Makefile
index 17acce70569b..9520bc5a4b7f 100644
--- a/arch/tile/Makefile
+++ b/arch/tile/Makefile
@@ -30,7 +30,8 @@ ifneq ($(CONFIG_DEBUG_EXTRA_FLAGS),"")
 KBUILD_CFLAGS   += $(CONFIG_DEBUG_EXTRA_FLAGS)
 endif
-LIBGCC_PATH     := $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
+LIBGCC_PATH     := \
+  $(shell $(CC) $(KBUILD_CFLAGS) $(KCFLAGS) -print-libgcc-file-name)
 # Provide the path to use for "make defconfig".
 KBUILD_DEFCONFIG := $(ARCH)_defconfig
@@ -53,8 +54,6 @@ libs-y		+= $(LIBGCC_PATH)
 # See arch/tile/Kbuild for content of core part of the kernel
 core-y          += arch/tile/
-core-$(CONFIG_KVM) += arch/tile/kvm/
 ifdef TILERA_ROOT
 INSTALL_PATH ?= $(TILERA_ROOT)/tile/boot
 endif
diff --git a/arch/tile/include/arch/spr_def.h b/arch/tile/include/arch/spr_def.h
index f548efeb2de3..d6ba449b5363 100644
--- a/arch/tile/include/arch/spr_def.h
+++ b/arch/tile/include/arch/spr_def.h
@@ -60,8 +60,8 @@
        _concat4(SPR_IPI_EVENT_, CONFIG_KERNEL_PL,,)
 #define SPR_IPI_EVENT_RESET_K \
        _concat4(SPR_IPI_EVENT_RESET_, CONFIG_KERNEL_PL,,)
-#define SPR_IPI_MASK_SET_K \
+#define SPR_IPI_EVENT_SET_K \
-        _concat4(SPR_IPI_MASK_SET_, CONFIG_KERNEL_PL,,)
+        _concat4(SPR_IPI_EVENT_SET_, CONFIG_KERNEL_PL,,)
 #define INT_IPI_K \
        _concat4(INT_IPI_, CONFIG_KERNEL_PL,,)
diff --git a/arch/tile/include/asm/atomic.h b/arch/tile/include/asm/atomic.h
index bb696da5d7cd..f2461429a4a4 100644
--- a/arch/tile/include/asm/atomic.h
+++ b/arch/tile/include/asm/atomic.h
@@ -17,6 +17,8 @@
 #ifndef _ASM_TILE_ATOMIC_H
 #define _ASM_TILE_ATOMIC_H
+#include <asm/cmpxchg.h>
 #ifndef __ASSEMBLY__
 #include <linux/compiler.h>
@@ -121,54 +123,6 @@ static inline int atomic_read(const atomic_t *v)
 */
 #define atomic_add_negative(i, v)       (atomic_add_return((i), (v)) < 0)
-/* Nonexistent functions intended to cause link errors. */
-extern unsigned long __xchg_called_with_bad_pointer(void);
-extern unsigned long __cmpxchg_called_with_bad_pointer(void);
-#define xchg(ptr, x)                                                    \
-        ({                                                              \
-                typeof(*(ptr)) __x;                                     \
-                switch (sizeof(*(ptr))) {                               \
-                case 4:                                                 \
-                        __x = (typeof(__x))(typeof(__x-__x))atomic_xchg( \
-                                (atomic_t *)(ptr),                      \
-                                (u32)(typeof((x)-(x)))(x));             \
-                        break;                                          \
-                case 8:                                                 \
-                        __x = (typeof(__x))(typeof(__x-__x))atomic64_xchg( \
-                                (atomic64_t *)(ptr),                    \
-                                (u64)(typeof((x)-(x)))(x));             \
-                        break;                                          \
-                default:                                                \
-                        __xchg_called_with_bad_pointer();               \
-                }                                                       \
-                __x;                                                    \
-        })
-#define cmpxchg(ptr, o, n)                                              \
-        ({                                                              \
-                typeof(*(ptr)) __x;                                     \
-                switch (sizeof(*(ptr))) {                               \
-                case 4:                                                 \
-                        __x = (typeof(__x))(typeof(__x-__x))atomic_cmpxchg( \
-                                (atomic_t *)(ptr),                      \
-                                (u32)(typeof((o)-(o)))(o),              \
-                                (u32)(typeof((n)-(n)))(n));             \
-                        break;                                          \
-                case 8:                                                 \
-                        __x = (typeof(__x))(typeof(__x-__x))atomic64_cmpxchg( \
-                                (atomic64_t *)(ptr),                    \
-                                (u64)(typeof((o)-(o)))(o),              \
-                                (u64)(typeof((n)-(n)))(n));             \
-                        break;                                          \
-                default:                                                \
-                        __cmpxchg_called_with_bad_pointer();            \
-                }                                                       \
-                __x;                                                    \
-        })
-#define tas(ptr) (xchg((ptr), 1))
 #endif /* __ASSEMBLY__ */
 #ifndef __tilegx__
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index 466dc4a39a4f..54d1da826f93 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -200,7 +200,7 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
 * @u: ...unless v is equal to u.
 *
 * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns the old value of @v.
+ * Returns non-zero if @v was not @u, and zero otherwise.
 */
 static inline u64 atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
 {
diff --git a/arch/tile/include/asm/bitops_64.h b/arch/tile/include/asm/bitops_64.h
index 58d021a9834f..60b87ee54fb8 100644
--- a/arch/tile/include/asm/bitops_64.h
+++ b/arch/tile/include/asm/bitops_64.h
@@ -38,10 +38,10 @@ static inline void clear_bit(unsigned nr, volatile unsigned long *addr)
 static inline void change_bit(unsigned nr, volatile unsigned long *addr)
 {
-        unsigned long old, mask = (1UL << (nr % BITS_PER_LONG));
+        unsigned long mask = (1UL << (nr % BITS_PER_LONG));
-        long guess, oldval;
+        unsigned long guess, oldval;
        addr += nr / BITS_PER_LONG;
-        old = *addr;
+        oldval = *addr;
        do {
                guess = oldval;
                oldval = atomic64_cmpxchg((atomic64_t *)addr,
@@ -85,7 +85,7 @@ static inline int test_and_change_bit(unsigned nr,
                                      volatile unsigned long *addr)
 {
        unsigned long mask = (1UL << (nr % BITS_PER_LONG));
-        long guess, oldval = *addr;
+        unsigned long guess, oldval;
        addr += nr / BITS_PER_LONG;
        oldval = *addr;
        do {
diff --git a/arch/tile/include/asm/cmpxchg.h b/arch/tile/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..276f067e3640
--- /dev/null
+++ b/arch/tile/include/asm/cmpxchg.h
@@ -0,0 +1,73 @@
+/*
+ * cmpxchg.h -- forked from asm/atomic.h with this copyright:
+ *
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ */
+#ifndef _ASM_TILE_CMPXCHG_H
+#define _ASM_TILE_CMPXCHG_H
+#ifndef __ASSEMBLY__
+/* Nonexistent functions intended to cause link errors. */
+extern unsigned long __xchg_called_with_bad_pointer(void);
+extern unsigned long __cmpxchg_called_with_bad_pointer(void);
+#define xchg(ptr, x)                                                    \
+        ({                                                              \
+                typeof(*(ptr)) __x;                                     \
+                switch (sizeof(*(ptr))) {                               \
+                case 4:                                                 \
+                        __x = (typeof(__x))(typeof(__x-__x))atomic_xchg( \
+                                (atomic_t *)(ptr),                      \
+                                (u32)(typeof((x)-(x)))(x));             \
+                        break;                                          \
+                case 8:                                                 \
+                        __x = (typeof(__x))(typeof(__x-__x))atomic64_xchg( \
+                                (atomic64_t *)(ptr),                    \
+                                (u64)(typeof((x)-(x)))(x));             \
+                        break;                                          \
+                default:                                                \
+                        __xchg_called_with_bad_pointer();               \
+                }                                                       \
+                __x;                                                    \
+        })
+#define cmpxchg(ptr, o, n)                                              \
+        ({                                                              \
+                typeof(*(ptr)) __x;                                     \
+                switch (sizeof(*(ptr))) {                               \
+                case 4:                                                 \
+                        __x = (typeof(__x))(typeof(__x-__x))atomic_cmpxchg( \
+                                (atomic_t *)(ptr),                      \
+                                (u32)(typeof((o)-(o)))(o),              \
+                                (u32)(typeof((n)-(n)))(n));             \
+                        break;                                          \
+                case 8:                                                 \
+                        __x = (typeof(__x))(typeof(__x-__x))atomic64_cmpxchg( \
+                                (atomic64_t *)(ptr),                    \
+                                (u64)(typeof((o)-(o)))(o),              \
+                                (u64)(typeof((n)-(n)))(n));             \
+                        break;                                          \
+                default:                                                \
+                        __cmpxchg_called_with_bad_pointer();            \
+                }                                                       \
+                __x;                                                    \
+        })
+#define tas(ptr) (xchg((ptr), 1))
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_TILE_CMPXCHG_H */
diff --git a/arch/tile/include/asm/irq.h b/arch/tile/include/asm/irq.h
index f80f8ceabc67..33cff9a3058b 100644
--- a/arch/tile/include/asm/irq.h
+++ b/arch/tile/include/asm/irq.h
@@ -21,7 +21,7 @@
 #define NR_IRQS 32
 /* IRQ numbers used for linux IPIs. */
-#define IRQ_RESCHEDULE 1
+#define IRQ_RESCHEDULE 0
 #define irq_canonicalize(irq)   (irq)
diff --git a/arch/tile/include/asm/spinlock_64.h b/arch/tile/include/asm/spinlock_64.h
index 72be5904e020..5f8b6a095fd8 100644
--- a/arch/tile/include/asm/spinlock_64.h
+++ b/arch/tile/include/asm/spinlock_64.h
@@ -137,7 +137,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
        __insn_mf();
-        rw->lock = 0;
+        __insn_exch4(&rw->lock, 0);  /* Avoid waiting in the write buffer. */
 }
 static inline int arch_read_trylock(arch_rwlock_t *rw)
diff --git a/arch/tile/include/asm/stack.h b/arch/tile/include/asm/stack.h
index 4d97a2db932e..0e9d382a2d45 100644
--- a/arch/tile/include/asm/stack.h
+++ b/arch/tile/include/asm/stack.h
@@ -25,7 +25,6 @@
 struct KBacktraceIterator {
        BacktraceIterator it;
        struct task_struct *task;     /* task we are backtracing */
-        pte_t *pgtable;               /* page table for user space access */
        int end;                      /* iteration complete. */
        int new_context;              /* new context is starting */
        int profile;                  /* profiling, so stop on async intrpt */
diff --git a/arch/tile/include/asm/traps.h b/arch/tile/include/asm/traps.h
index 5f20f920f932..e28c3df4176a 100644
--- a/arch/tile/include/asm/traps.h
+++ b/arch/tile/include/asm/traps.h
@@ -64,7 +64,11 @@ void do_breakpoint(struct pt_regs *, int fault_num);
 #ifdef __tilegx__
+/* kernel/single_step.c */
 void gx_singlestep_handle(struct pt_regs *, int fault_num);
+/* kernel/intvec_64.S */
+void fill_ra_stack(void);
 #endif
-#endif /* _ASM_TILE_SYSCALLS_H */
+#endif /* _ASM_TILE_TRAPS_H */
diff --git a/arch/tile/kernel/entry.S b/arch/tile/kernel/entry.S
index 431e9ae60488..ec91568df880 100644
--- a/arch/tile/kernel/entry.S
+++ b/arch/tile/kernel/entry.S
@@ -85,6 +85,7 @@ STD_ENTRY(cpu_idle_on_new_stack)
 /* Loop forever on a nap during SMP boot. */
 STD_ENTRY(smp_nap)
        nap
+        nop       /* avoid provoking the icache prefetch with a jump */
        j smp_nap /* we are not architecturally guaranteed not to exit nap */
        jrp lr    /* clue in the backtracer */
        STD_ENDPROC(smp_nap)
@@ -105,5 +106,6 @@ STD_ENTRY(_cpu_idle)
        .global _cpu_idle_nap
 _cpu_idle_nap:
        nap
+        nop       /* avoid provoking the icache prefetch with a jump */
        jrp lr
        STD_ENDPROC(_cpu_idle)
diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S
index aecc8ed5f39b..5d56a1ef5ba5 100644
--- a/arch/tile/kernel/intvec_32.S
+++ b/arch/tile/kernel/intvec_32.S
@@ -799,6 +799,10 @@ handle_interrupt:
 * This routine takes a boolean in r30 indicating if this is an NMI.
 * If so, we also expect a boolean in r31 indicating whether to
 * re-enable the oprofile interrupts.
+ *
+ * Note that .Lresume_userspace is jumped to directly in several
+ * places, and we need to make sure r30 is set correctly in those
+ * callers as well.
 */
 STD_ENTRY(interrupt_return)
        /* If we're resuming to kernel space, don't check thread flags. */
@@ -1237,7 +1241,10 @@ handle_syscall:
        bzt     r30, 1f
        jal     do_syscall_trace
        FEEDBACK_REENTER(handle_syscall)
-1:      j       .Lresume_userspace   /* jump into middle of interrupt_return */
+1:      {
+         movei  r30, 0               /* not an NMI */
+         j      .Lresume_userspace   /* jump into middle of interrupt_return */
+        }
 .Linvalid_syscall:
        /* Report an invalid syscall back to the user program */
@@ -1246,7 +1253,10 @@ handle_syscall:
         movei  r28, -ENOSYS
        }
        sw      r29, r28
-        j       .Lresume_userspace   /* jump into middle of interrupt_return */
+        {
+         movei  r30, 0               /* not an NMI */
+         j      .Lresume_userspace   /* jump into middle of interrupt_return */
+        }
        STD_ENDPROC(handle_syscall)
        /* Return the address for oprofile to suppress in backtraces. */
@@ -1262,7 +1272,10 @@ STD_ENTRY(ret_from_fork)
        jal     sim_notify_fork
        jal     schedule_tail
        FEEDBACK_REENTER(ret_from_fork)
-        j       .Lresume_userspace   /* jump into middle of interrupt_return */
+        {
+         movei  r30, 0               /* not an NMI */
+         j      .Lresume_userspace   /* jump into middle of interrupt_return */
+        }
        STD_ENDPROC(ret_from_fork)
        /*
@@ -1376,7 +1389,10 @@ handle_ill:
        jal     send_sigtrap    /* issue a SIGTRAP */
        FEEDBACK_REENTER(handle_ill)
-        j       .Lresume_userspace   /* jump into middle of interrupt_return */
+        {
+         movei  r30, 0               /* not an NMI */
+         j      .Lresume_userspace   /* jump into middle of interrupt_return */
+        }
 .Ldispatch_normal_ill:
        {
diff --git a/arch/tile/kernel/intvec_64.S b/arch/tile/kernel/intvec_64.S
index 79c93e10ba27..49d9d6621682 100644
--- a/arch/tile/kernel/intvec_64.S
+++ b/arch/tile/kernel/intvec_64.S
@@ -22,6 +22,7 @@
 #include <asm/irqflags.h>
 #include <asm/asm-offsets.h>
 #include <asm/types.h>
+#include <asm/signal.h>
 #include <hv/hypervisor.h>
 #include <arch/abi.h>
 #include <arch/interrupts.h>
@@ -605,6 +606,10 @@ handle_interrupt:
 * This routine takes a boolean in r30 indicating if this is an NMI.
 * If so, we also expect a boolean in r31 indicating whether to
 * re-enable the oprofile interrupts.
+ *
+ * Note that .Lresume_userspace is jumped to directly in several
+ * places, and we need to make sure r30 is set correctly in those
+ * callers as well.
 */
 STD_ENTRY(interrupt_return)
        /* If we're resuming to kernel space, don't check thread flags. */
@@ -1039,11 +1044,28 @@ handle_syscall:
        /* Do syscall trace again, if requested. */
        ld      r30, r31
-        andi    r30, r30, _TIF_SYSCALL_TRACE
+        andi    r0, r30, _TIF_SYSCALL_TRACE
-        beqzt   r30, 1f
+        {
+         andi    r0, r30, _TIF_SINGLESTEP
+         beqzt   r0, 1f
+        }
        jal     do_syscall_trace
        FEEDBACK_REENTER(handle_syscall)
-1:      j       .Lresume_userspace   /* jump into middle of interrupt_return */
+        andi    r0, r30, _TIF_SINGLESTEP
+1:      beqzt   r0, 2f
+        /* Single stepping -- notify ptrace. */
+        {
+         movei   r0, SIGTRAP
+         jal     ptrace_notify
+        }
+        FEEDBACK_REENTER(handle_syscall)
+2:      {
+         movei  r30, 0               /* not an NMI */
+         j      .Lresume_userspace   /* jump into middle of interrupt_return */
+        }
 .Lcompat_syscall:
        /*
@@ -1077,7 +1099,10 @@ handle_syscall:
         movei  r28, -ENOSYS
        }
        st      r29, r28
-        j       .Lresume_userspace   /* jump into middle of interrupt_return */
+        {
+         movei  r30, 0               /* not an NMI */
+         j      .Lresume_userspace   /* jump into middle of interrupt_return */
+        }
        STD_ENDPROC(handle_syscall)
        /* Return the address for oprofile to suppress in backtraces. */
@@ -1093,7 +1118,10 @@ STD_ENTRY(ret_from_fork)
        jal     sim_notify_fork
        jal     schedule_tail
        FEEDBACK_REENTER(ret_from_fork)
-        j       .Lresume_userspace
+        {
+         movei  r30, 0               /* not an NMI */
+         j      .Lresume_userspace   /* jump into middle of interrupt_return */
+        }
        STD_ENDPROC(ret_from_fork)
 /* Various stub interrupt handlers and syscall handlers */
@@ -1156,6 +1184,18 @@ int_unalign:
        push_extra_callee_saves r0
        j       do_trap
+/* Fill the return address stack with nonzero entries. */
+STD_ENTRY(fill_ra_stack)
+        {
+         move   r0, lr
+         jal    1f
+        }
+1:      jal     2f
+2:      jal     3f
+3:      jal     4f
+4:      jrp     r0
+        STD_ENDPROC(fill_ra_stack)
 /* Include .intrpt1 array of interrupt vectors */
        .section ".intrpt1", "ax"
@@ -1166,7 +1206,7 @@ int_unalign:
 #define do_hardwall_trap bad_intr
 #endif
-        int_hand     INT_MEM_ERROR, MEM_ERROR, bad_intr
+        int_hand     INT_MEM_ERROR, MEM_ERROR, do_trap
        int_hand     INT_SINGLE_STEP_3, SINGLE_STEP_3, bad_intr
 #if CONFIG_KERNEL_PL == 2
        int_hand     INT_SINGLE_STEP_2, SINGLE_STEP_2, gx_singlestep_handle
diff --git a/arch/tile/kernel/module.c b/arch/tile/kernel/module.c
index b90ab9925674..98d476920106 100644
--- a/arch/tile/kernel/module.c
+++ b/arch/tile/kernel/module.c
@@ -67,6 +67,8 @@ void *module_alloc(unsigned long size)
        area = __get_vm_area(size, VM_ALLOC, MEM_MODULE_START, MEM_MODULE_END);
        if (!area)
                goto error;
+        area->nr_pages = npages;
+        area->pages = pages;
        if (map_vm_area(area, prot_rwx, &pages)) {
                vunmap(area->addr);
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 30caecac94dc..2d5ef617bb39 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -28,6 +28,7 @@
 #include <linux/tracehook.h>
 #include <linux/signal.h>
 #include <asm/stack.h>
+#include <asm/switch_to.h>
 #include <asm/homecache.h>
 #include <asm/syscalls.h>
 #include <asm/traps.h>
@@ -285,7 +286,7 @@ struct task_struct *validate_current(void)
        static struct task_struct corrupt = { .comm = "<corrupt>" };
        struct task_struct *tsk = current;
        if (unlikely((unsigned long)tsk < PAGE_OFFSET ||
-                     (void *)tsk > high_memory ||
+                     (high_memory && (void *)tsk > high_memory) ||
                     ((unsigned long)tsk & (__alignof__(*tsk) - 1)) != 0)) {
                pr_err("Corrupt 'current' %p (sp %#lx)\n", tsk, stack_pointer);
                tsk = &corrupt;
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 5f85d8b34dbb..bff23f476110 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -103,13 +103,11 @@ unsigned long __initdata pci_reserve_end_pfn = -1U;
 static int __init setup_maxmem(char *str)
 {
-        long maxmem_mb;
+        unsigned long long maxmem;
-        if (str == NULL || strict_strtol(str, 0, &maxmem_mb) != 0 ||
+        if (str == NULL || (maxmem = memparse(str, NULL)) == 0)
-            maxmem_mb == 0)
                return -EINVAL;
-        maxmem_pfn = (maxmem_mb >> (HPAGE_SHIFT - 20)) <<
+        maxmem_pfn = (maxmem >> HPAGE_SHIFT) << (HPAGE_SHIFT - PAGE_SHIFT);
-                (HPAGE_SHIFT - PAGE_SHIFT);
        pr_info("Forcing RAM used to no more than %dMB\n",
               maxmem_pfn >> (20 - PAGE_SHIFT));
        return 0;
@@ -119,14 +117,15 @@ early_param("maxmem", setup_maxmem);
 static int __init setup_maxnodemem(char *str)
 {
        char *endp;
-        long maxnodemem_mb, node;
+        unsigned long long maxnodemem;
+        long node;
        node = str ? simple_strtoul(str, &endp, 0) : INT_MAX;
-        if (node >= MAX_NUMNODES || *endp != ':' ||
+        if (node >= MAX_NUMNODES || *endp != ':')
-            strict_strtol(endp+1, 0, &maxnodemem_mb) != 0)
                return -EINVAL;
-        maxnodemem_pfn[node] = (maxnodemem_mb >> (HPAGE_SHIFT - 20)) <<
+        maxnodemem = memparse(endp+1, NULL);
+        maxnodemem_pfn[node] = (maxnodemem >> HPAGE_SHIFT) <<
                (HPAGE_SHIFT - PAGE_SHIFT);
        pr_info("Forcing RAM used on node %ld to no more than %dMB\n",
               node, maxnodemem_pfn[node] >> (20 - PAGE_SHIFT));
@@ -913,6 +912,13 @@ void __cpuinit setup_cpu(int boot)
 #ifdef CONFIG_BLK_DEV_INITRD
+/*
+ * Note that the kernel can potentially support other compression
+ * techniques than gz, though we don't do so by default.  If we ever
+ * decide to do so we can either look for other filename extensions,
+ * or just allow a file with this name to be compressed with an
+ * arbitrary compressor (somewhat counterintuitively).
+ */
 static int __initdata set_initramfs_file;
 static char __initdata initramfs_file[128] = "initramfs.cpio.gz";
@@ -928,9 +934,9 @@ static int __init setup_initramfs_file(char *str)
 early_param("initramfs_file", setup_initramfs_file);
 /*
- * We look for an additional "initramfs.cpio.gz" file in the hvfs.
+ * We look for an "initramfs.cpio.gz" file in the hvfs.
 * If there is one, we allocate some memory for it and it will be
- * unpacked to the initramfs after any built-in initramfs_data.
+ * unpacked to the initramfs.
 */
 static void __init load_hv_initrd(void)
 {
@@ -1100,7 +1106,7 @@ EXPORT_SYMBOL(hash_for_home_map);
 /*
 * cpu_cacheable_map lists all the cpus whose caches the hypervisor can
- * flush on our behalf.  It is set to cpu_possible_map OR'ed with
+ * flush on our behalf.  It is set to cpu_possible_mask OR'ed with
 * hash_for_home_map, and it is what should be passed to
 * hv_flush_remote() to flush all caches.  Note that if there are
 * dedicated hypervisor driver tiles that have authorized use of their
@@ -1186,7 +1192,7 @@ static void __init setup_cpu_maps(void)
                              sizeof(cpu_lotar_map));
        if (rc < 0) {
                pr_err("warning: no HV_INQ_TILES_LOTAR; using AVAIL\n");
-                cpu_lotar_map = cpu_possible_map;
+                cpu_lotar_map = *cpu_possible_mask;
        }
 #if CHIP_HAS_CBOX_HOME_MAP()
@@ -1196,9 +1202,9 @@ static void __init setup_cpu_maps(void)
                              sizeof(hash_for_home_map));
        if (rc < 0)
                early_panic("hv_inquire_tiles(HFH_CACHE) failed: rc %d\n", rc);
-        cpumask_or(&cpu_cacheable_map, &cpu_possible_map, &hash_for_home_map);
+        cpumask_or(&cpu_cacheable_map, cpu_possible_mask, &hash_for_home_map);
 #else
-        cpu_cacheable_map = cpu_possible_map;
+        cpu_cacheable_map = *cpu_possible_mask;
 #endif
 }
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index bc1eb586e24d..9efbc1391b3c 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -153,6 +153,25 @@ static tile_bundle_bits rewrite_load_store_unaligned(
        if (((unsigned long)addr % size) == 0)
                return bundle;
+        /*
+         * Return SIGBUS with the unaligned address, if requested.
+         * Note that we return SIGBUS even for completely invalid addresses
+         * as long as they are in fact unaligned; this matches what the
+         * tilepro hardware would be doing, if it could provide us with the
+         * actual bad address in an SPR, which it doesn't.
+         */
+        if (unaligned_fixup == 0) {
+                siginfo_t info = {
+                        .si_signo = SIGBUS,
+                        .si_code = BUS_ADRALN,
+                        .si_addr = addr
+                };
+                trace_unhandled_signal("unaligned trap", regs,
+                                       (unsigned long)addr, SIGBUS);
+                force_sig_info(info.si_signo, &info, current);
+                return (tilepro_bundle_bits) 0;
+        }
 #ifndef __LITTLE_ENDIAN
 # error We assume little-endian representation with copy_xx_user size 2 here
 #endif
@@ -192,18 +211,6 @@ static tile_bundle_bits rewrite_load_store_unaligned(
                return (tile_bundle_bits) 0;
        }
-        if (unaligned_fixup == 0) {
-                siginfo_t info = {
-                        .si_signo = SIGBUS,
-                        .si_code = BUS_ADRALN,
-                        .si_addr = addr
-                };
-                trace_unhandled_signal("unaligned trap", regs,
-                                       (unsigned long)addr, SIGBUS);
-                force_sig_info(info.si_signo, &info, current);
-                return (tile_bundle_bits) 0;
-        }
        if (unaligned_printk || unaligned_fixup_count == 0) {
                pr_info("Process %d/%s: PC %#lx: Fixup of"
                        " unaligned %s at %#lx.\n",
diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c
index a44e103c5a63..91da0f721958 100644
--- a/arch/tile/kernel/smp.c
+++ b/arch/tile/kernel/smp.c
@@ -103,7 +103,7 @@ static void smp_stop_cpu_interrupt(void)
        set_cpu_online(smp_processor_id(), 0);
        arch_local_irq_disable_all();
        for (;;)
-                asm("nap");
+                asm("nap; nop");
 }
 /* This function calls the 'stop' function on all other CPUs in the system. */
@@ -113,6 +113,12 @@ void smp_send_stop(void)
        send_IPI_allbutself(MSG_TAG_STOP_CPU);
 }
+/* On panic, just wait; we may get an smp_send_stop() later on. */
+void panic_smp_self_stop(void)
+{
+        while (1)
+                asm("nap; nop");
+}
 /*
 * Dispatch code called from hv_message_intr() for HV_MSG_TILE hv messages.
diff --git a/arch/tile/kernel/stack.c b/arch/tile/kernel/stack.c
index 37ee4d037e0b..b2f44c28dda6 100644
--- a/arch/tile/kernel/stack.c
+++ b/arch/tile/kernel/stack.c
@@ -21,10 +21,12 @@
 #include <linux/stacktrace.h>
 #include <linux/uaccess.h>
 #include <linux/mmzone.h>
+#include <linux/dcache.h>
+#include <linux/fs.h>
 #include <asm/backtrace.h>
 #include <asm/page.h>
-#include <asm/tlbflush.h>
 #include <asm/ucontext.h>
+#include <asm/switch_to.h>
 #include <asm/sigframe.h>
 #include <asm/stack.h>
 #include <arch/abi.h>
@@ -44,72 +46,23 @@ static int in_kernel_stack(struct KBacktraceIterator *kbt, unsigned long sp)
        return sp >= kstack_base && sp < kstack_base + THREAD_SIZE;
 }
-/* Is address valid for reading? */
-static int valid_address(struct KBacktraceIterator *kbt, unsigned long address)
-{
-        HV_PTE *l1_pgtable = kbt->pgtable;
-        HV_PTE *l2_pgtable;
-        unsigned long pfn;
-        HV_PTE pte;
-        struct page *page;
-        if (l1_pgtable == NULL)
-                return 0;       /* can't read user space in other tasks */
-#ifdef CONFIG_64BIT
-        /* Find the real l1_pgtable by looking in the l0_pgtable. */
-        pte = l1_pgtable[HV_L0_INDEX(address)];
-        if (!hv_pte_get_present(pte))
-                return 0;
-        pfn = hv_pte_get_pfn(pte);
-        if (pte_huge(pte)) {
-                if (!pfn_valid(pfn)) {
-                        pr_err("L0 huge page has bad pfn %#lx\n", pfn);
-                        return 0;
-                }
-                return hv_pte_get_present(pte) && hv_pte_get_readable(pte);
-        }
-        page = pfn_to_page(pfn);
-        BUG_ON(PageHighMem(page));  /* No HIGHMEM on 64-bit. */
-        l1_pgtable = (HV_PTE *)pfn_to_kaddr(pfn);
-#endif
-        pte = l1_pgtable[HV_L1_INDEX(address)];
-        if (!hv_pte_get_present(pte))
-                return 0;
-        pfn = hv_pte_get_pfn(pte);
-        if (pte_huge(pte)) {
-                if (!pfn_valid(pfn)) {
-                        pr_err("huge page has bad pfn %#lx\n", pfn);
-                        return 0;
-                }
-                return hv_pte_get_present(pte) && hv_pte_get_readable(pte);
-        }
-        page = pfn_to_page(pfn);
-        if (PageHighMem(page)) {
-                pr_err("L2 page table not in LOWMEM (%#llx)\n",
-                       HV_PFN_TO_CPA(pfn));
-                return 0;
-        }
-        l2_pgtable = (HV_PTE *)pfn_to_kaddr(pfn);
-        pte = l2_pgtable[HV_L2_INDEX(address)];
-        return hv_pte_get_present(pte) && hv_pte_get_readable(pte);
-}
 /* Callback for backtracer; basically a glorified memcpy */
 static bool read_memory_func(void *result, unsigned long address,
                             unsigned int size, void *vkbt)
 {
        int retval;
        struct KBacktraceIterator *kbt = (struct KBacktraceIterator *)vkbt;
+        if (address == 0)
+                return 0;
        if (__kernel_text_address(address)) {
                /* OK to read kernel code. */
        } else if (address >= PAGE_OFFSET) {
                /* We only tolerate kernel-space reads of this task's stack */
                if (!in_kernel_stack(kbt, address))
                        return 0;
-        } else if (!valid_address(kbt, address)) {
+        } else if (!kbt->is_current) {
-                return 0;       /* invalid user-space address */
+                return 0;       /* can't read from other user address spaces */
        }
        pagefault_disable();
        retval = __copy_from_user_inatomic(result,
@@ -127,6 +80,8 @@ static struct pt_regs *valid_fault_handler(struct KBacktraceIterator* kbt)
        unsigned long sp = kbt->it.sp;
        struct pt_regs *p;
+        if (sp % sizeof(long) != 0)
+                return NULL;
        if (!in_kernel_stack(kbt, sp))
                return NULL;
        if (!in_kernel_stack(kbt, sp + C_ABI_SAVE_AREA_SIZE + PTREGS_SIZE-1))
@@ -169,27 +124,27 @@ static int is_sigreturn(unsigned long pc)
 }
 /* Return a pt_regs pointer for a valid signal handler frame */
-static struct pt_regs *valid_sigframe(struct KBacktraceIterator* kbt)
+static struct pt_regs *valid_sigframe(struct KBacktraceIterator* kbt,
+                                      struct rt_sigframe* kframe)
 {
        BacktraceIterator *b = &kbt->it;
-        if (b->pc == VDSO_BASE) {
+        if (b->pc == VDSO_BASE && b->sp < PAGE_OFFSET &&
-                struct rt_sigframe *frame;
+            b->sp % sizeof(long) == 0) {
-                unsigned long sigframe_top =
+                int retval;
-                        b->sp + sizeof(struct rt_sigframe) - 1;
+                pagefault_disable();
-                if (!valid_address(kbt, b->sp) ||
+                retval = __copy_from_user_inatomic(
-                    !valid_address(kbt, sigframe_top)) {
+                        kframe, (void __user __force *)b->sp,
-                        if (kbt->verbose)
+                        sizeof(*kframe));
-                                pr_err("  (odd signal: sp %#lx?)\n",
+                pagefault_enable();
-                                       (unsigned long)(b->sp));
+                if (retval != 0 ||
+                    (unsigned int)(kframe->info.si_signo) >= _NSIG)
                        return NULL;
-                }
-                frame = (struct rt_sigframe *)b->sp;
                if (kbt->verbose) {
                        pr_err("  <received signal %d>\n",
-                               frame->info.si_signo);
+                               kframe->info.si_signo);
                }
-                return (struct pt_regs *)&frame->uc.uc_mcontext;
+                return (struct pt_regs *)&kframe->uc.uc_mcontext;
        }
        return NULL;
 }
@@ -202,10 +157,11 @@ static int KBacktraceIterator_is_sigreturn(struct KBacktraceIterator *kbt)
 static int KBacktraceIterator_restart(struct KBacktraceIterator *kbt)
 {
        struct pt_regs *p;
+        struct rt_sigframe kframe;
        p = valid_fault_handler(kbt);
        if (p == NULL)
-                p = valid_sigframe(kbt);
+                p = valid_sigframe(kbt, &kframe);
        if (p == NULL)
                return 0;
        backtrace_init(&kbt->it, read_memory_func, kbt,
@@ -265,41 +221,19 @@ void KBacktraceIterator_init(struct KBacktraceIterator *kbt,
        /*
         * Set up callback information.  We grab the kernel stack base
-         * so we will allow reads of that address range, and if we're
+         * so we will allow reads of that address range.
-         * asking about the current process we grab the page table
-         * so we can check user accesses before trying to read them.
-         * We flush the TLB to avoid any weird skew issues.
         */
-        is_current = (t == NULL);
+        is_current = (t == NULL || t == current);
        kbt->is_current = is_current;
        if (is_current)
                t = validate_current();
        kbt->task = t;
-        kbt->pgtable = NULL;
        kbt->verbose = 0;   /* override in caller if desired */
        kbt->profile = 0;   /* override in caller if desired */
        kbt->end = KBT_ONGOING;
-        kbt->new_context = 0;
+        kbt->new_context = 1;
-        if (is_current) {
+        if (is_current)
-                HV_PhysAddr pgdir_pa = hv_inquire_context().page_table;
-                if (pgdir_pa == (unsigned long)swapper_pg_dir - PAGE_OFFSET) {
-                        /*
-                         * Not just an optimization: this also allows
-                         * this to work at all before va/pa mappings
-                         * are set up.
-                         */
-                        kbt->pgtable = swapper_pg_dir;
-                } else {
-                        struct page *page = pfn_to_page(PFN_DOWN(pgdir_pa));
-                        if (!PageHighMem(page))
-                                kbt->pgtable = __va(pgdir_pa);
-                        else
-                                pr_err("page table not in LOWMEM"
-                                       " (%#llx)\n", pgdir_pa);
-                }
-                local_flush_tlb_all();
                validate_stack(regs);
-        }
        if (regs == NULL) {
                if (is_current || t->state == TASK_RUNNING) {
@@ -345,6 +279,78 @@ void KBacktraceIterator_next(struct KBacktraceIterator *kbt)
 }
 EXPORT_SYMBOL(KBacktraceIterator_next);
+static void describe_addr(struct KBacktraceIterator *kbt,
+                          unsigned long address,
+                          int have_mmap_sem, char *buf, size_t bufsize)
+{
+        struct vm_area_struct *vma;
+        size_t namelen, remaining;
+        unsigned long size, offset, adjust;
+        char *p, *modname;
+        const char *name;
+        int rc;
+        /*
+         * Look one byte back for every caller frame (i.e. those that
+         * aren't a new context) so we look up symbol data for the
+         * call itself, not the following instruction, which may be on
+         * a different line (or in a different function).
+         */
+        adjust = !kbt->new_context;
+        address -= adjust;
+        if (address >= PAGE_OFFSET) {
+                /* Handle kernel symbols. */
+                BUG_ON(bufsize < KSYM_NAME_LEN);
+                name = kallsyms_lookup(address, &size, &offset,
+                                       &modname, buf);
+                if (name == NULL) {
+                        buf[0] = '\0';
+                        return;
+                }
+                namelen = strlen(buf);
+                remaining = (bufsize - 1) - namelen;
+                p = buf + namelen;
+                rc = snprintf(p, remaining, "+%#lx/%#lx ",
+                              offset + adjust, size);
+                if (modname && rc < remaining)
+                        snprintf(p + rc, remaining - rc, "[%s] ", modname);
+                buf[bufsize-1] = '\0';
+                return;
+        }
+        /* If we don't have the mmap_sem, we can't show any more info. */
+        buf[0] = '\0';
+        if (!have_mmap_sem)
+                return;
+        /* Find vma info. */
+        vma = find_vma(kbt->task->mm, address);
+        if (vma == NULL || address < vma->vm_start) {
+                snprintf(buf, bufsize, "[unmapped address] ");
+                return;
+        }
+        if (vma->vm_file) {
+                char *s;
+                p = d_path(&vma->vm_file->f_path, buf, bufsize);
+                if (IS_ERR(p))
+                        p = "?";
+                s = strrchr(p, '/');
+                if (s)
+                        p = s+1;
+        } else {
+                p = "anon";
+        }
+        /* Generate a string description of the vma info. */
+        namelen = strlen(p);
+        remaining = (bufsize - 1) - namelen;
+        memmove(buf, p, namelen);
+        snprintf(buf + namelen, remaining, "[%lx+%lx] ",
+                 vma->vm_start, vma->vm_end - vma->vm_start);
+}
 /*
 * This method wraps the backtracer's more generic support.
 * It is only invoked from the architecture-specific code; show_stack()
@@ -353,6 +359,7 @@ EXPORT_SYMBOL(KBacktraceIterator_next);
 void tile_show_stack(struct KBacktraceIterator *kbt, int headers)
 {
        int i;
+        int have_mmap_sem = 0;
        if (headers) {
                /*
@@ -369,31 +376,16 @@ void tile_show_stack(struct KBacktraceIterator *kbt, int headers)
        kbt->verbose = 1;
        i = 0;
        for (; !KBacktraceIterator_end(kbt); KBacktraceIterator_next(kbt)) {
-                char *modname;
-                const char *name;
-                unsigned long address = kbt->it.pc;
-                unsigned long offset, size;
                char namebuf[KSYM_NAME_LEN+100];
+                unsigned long address = kbt->it.pc;
-                if (address >= PAGE_OFFSET)
+                /* Try to acquire the mmap_sem as we pass into userspace. */
-                        name = kallsyms_lookup(address, &size, &offset,
+                if (address < PAGE_OFFSET && !have_mmap_sem && kbt->task->mm)
-                                               &modname, namebuf);
+                        have_mmap_sem =
-                else
+                                down_read_trylock(&kbt->task->mm->mmap_sem);
-                        name = NULL;
+                describe_addr(kbt, address, have_mmap_sem,
-                if (!name)
+                              namebuf, sizeof(namebuf));
-                        namebuf[0] = '\0';
-                else {
-                        size_t namelen = strlen(namebuf);
-                        size_t remaining = (sizeof(namebuf) - 1) - namelen;
-                        char *p = namebuf + namelen;
-                        int rc = snprintf(p, remaining, "+%#lx/%#lx ",
-                                          offset, size);
-                        if (modname && rc < remaining)
-                                snprintf(p + rc, remaining - rc,
-                                         "[%s] ", modname);
-                        namebuf[sizeof(namebuf)-1] = '\0';
-                }
                pr_err("  frame %d: 0x%lx %s(sp 0x%lx)\n",
                       i++, address, namebuf, (unsigned long)(kbt->it.sp));
@@ -408,6 +400,8 @@ void tile_show_stack(struct KBacktraceIterator *kbt, int headers)
                pr_err("Stack dump stopped; next frame identical to this one\n");
        if (headers)
                pr_err("Stack dump complete\n");
+        if (have_mmap_sem)
+                up_read(&kbt->task->mm->mmap_sem);
 }
 EXPORT_SYMBOL(tile_show_stack);
diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c
index 2bb6602a1ee7..73cff814ac57 100644
--- a/arch/tile/kernel/traps.c
+++ b/arch/tile/kernel/traps.c
@@ -200,7 +200,7 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 {
        siginfo_t info = { 0 };
        int signo, code;
-        unsigned long address;
+        unsigned long address = 0;
        bundle_bits instr;
        /* Re-enable interrupts. */
@@ -223,6 +223,10 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
        }
        switch (fault_num) {
+        case INT_MEM_ERROR:
+                signo = SIGBUS;
+                code = BUS_OBJERR;
+                break;
        case INT_ILL:
                if (copy_from_user(&instr, (void __user *)regs->pc,
                                   sizeof(instr))) {
@@ -289,7 +293,10 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
                address = regs->pc;
                break;
 #ifdef __tilegx__
-        case INT_ILL_TRANS:
+        case INT_ILL_TRANS: {
+                /* Avoid a hardware erratum with the return address stack. */
+                fill_ra_stack();
                signo = SIGSEGV;
                code = SEGV_MAPERR;
                if (reason & SPR_ILL_TRANS_REASON__I_STREAM_VA_RMASK)
@@ -297,6 +304,7 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
                else
                        address = 0;  /* FIXME: GX: single-step for address */
                break;
+        }
 #endif
        default:
                panic("Unexpected do_trap interrupt number %d", fault_num);
@@ -308,7 +316,8 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
        info.si_addr = (void __user *)address;
        if (signo == SIGILL)
                info.si_trapno = fault_num;
-        trace_unhandled_signal("trap", regs, address, signo);
+        if (signo != SIGTRAP)
+                trace_unhandled_signal("trap", regs, address, signo);
        force_sig_info(signo, &info, current);
 }
diff --git a/arch/tile/lib/Makefile b/arch/tile/lib/Makefile
index 0c26086ecbef..985f59858234 100644
--- a/arch/tile/lib/Makefile
+++ b/arch/tile/lib/Makefile
@@ -7,6 +7,7 @@ lib-y = cacheflush.o checksum.o cpumask.o delay.o uaccess.o \
        strchr_$(BITS).o strlen_$(BITS).o
 ifeq ($(CONFIG_TILEGX),y)
+CFLAGS_REMOVE_memcpy_user_64.o = -fno-omit-frame-pointer
 lib-y += memcpy_user_64.o
 else
 lib-y += atomic_32.o atomic_asm_32.o memcpy_tile64.o
diff --git a/arch/tile/lib/cacheflush.c b/arch/tile/lib/cacheflush.c
index 8928aace7a64..db4fb89e12d8 100644
--- a/arch/tile/lib/cacheflush.c
+++ b/arch/tile/lib/cacheflush.c
@@ -39,7 +39,21 @@ void finv_buffer_remote(void *buffer, size_t size, int hfh)
 {
        char *p, *base;
        size_t step_size, load_count;
+        /*
+         * On TILEPro the striping granularity is a fixed 8KB; on
+         * TILE-Gx it is configurable, and we rely on the fact that
+         * the hypervisor always configures maximum striping, so that
+         * bits 9 and 10 of the PA are part of the stripe function, so
+         * every 512 bytes we hit a striping boundary.
+         *
+         */
+#ifdef __tilegx__
+        const unsigned long STRIPE_WIDTH = 512;
+#else
        const unsigned long STRIPE_WIDTH = 8192;
+#endif
 #ifdef __tilegx__
        /*
         * On TILE-Gx, we must disable the dstream prefetcher before doing
@@ -74,7 +88,7 @@ void finv_buffer_remote(void *buffer, size_t size, int hfh)
         * memory, that one load would be sufficient, but since we may
         * be, we also need to back up to the last load issued to
         * another memory controller, which would be the point where
-         * we crossed an 8KB boundary (the granularity of striping
+         * we crossed a "striping" boundary (the granularity of striping
         * across memory controllers).  Keep backing up and doing this
         * until we are before the beginning of the buffer, or have
         * hit all the controllers.
@@ -88,12 +102,22 @@ void finv_buffer_remote(void *buffer, size_t size, int hfh)
         * every cache line on a full memory stripe on each
         * controller" that we simply do that, to simplify the logic.
         *
-         * FIXME: See bug 9535 for some issues with this code.
+         * On TILE-Gx the hash-for-home function is much more complex,
+         * with the upshot being we can't readily guarantee we have
+         * hit both entries in the 128-entry AMT that were hit by any
+         * load in the entire range, so we just re-load them all.
+         * With larger buffers, we may want to consider using a hypervisor
+         * trap to issue loads directly to each hash-for-home tile for
+         * each controller (doing it from Linux would trash the TLB).
         */
        if (hfh) {
                step_size = L2_CACHE_BYTES;
+#ifdef __tilegx__
+                load_count = (size + L2_CACHE_BYTES - 1) / L2_CACHE_BYTES;
+#else
                load_count = (STRIPE_WIDTH / L2_CACHE_BYTES) *
                              (1 << CHIP_LOG_NUM_MSHIMS());
+#endif
        } else {
                step_size = STRIPE_WIDTH;
                load_count = (1 << CHIP_LOG_NUM_MSHIMS());
@@ -109,7 +133,7 @@ void finv_buffer_remote(void *buffer, size_t size, int hfh)
        /* Figure out how far back we need to go. */
        base = p - (step_size * (load_count - 2));
-        if ((long)base < (long)buffer)
+        if ((unsigned long)base < (unsigned long)buffer)
                base = buffer;
        /*
diff --git a/arch/tile/lib/memcpy_user_64.c b/arch/tile/lib/memcpy_user_64.c
index 4763b3aff1cc..37440caa7370 100644
--- a/arch/tile/lib/memcpy_user_64.c
+++ b/arch/tile/lib/memcpy_user_64.c
@@ -14,7 +14,13 @@
 * Do memcpy(), but trap and return "n" when a load or store faults.
 *
 * Note: this idiom only works when memcpy() compiles to a leaf function.
- * If "sp" is updated during memcpy, the "jrp lr" will be incorrect.
+ * Here leaf function not only means it does not have calls, but also
+ * requires no stack operations (sp, stack frame pointer) and no
+ * use of callee-saved registers, else "jrp lr" will be incorrect since
+ * unwinding stack frame is bypassed. Since memcpy() is not complex so
+ * these conditions are satisfied here, but we need to be careful when
+ * modifying this file. This is not a clean solution but is the best
+ * one so far.
 *
 * Also note that we are capturing "n" from the containing scope here.
 */
diff --git a/arch/tile/lib/spinlock_common.h b/arch/tile/lib/spinlock_common.h
index c10109809132..6ac37509faca 100644
--- a/arch/tile/lib/spinlock_common.h
+++ b/arch/tile/lib/spinlock_common.h
@@ -60,5 +60,5 @@ static void delay_backoff(int iterations)
        loops += __insn_crc32_32(stack_pointer, get_cycles_low()) &
                (loops - 1);
-        relax(1 << exponent);
+        relax(loops);
 }
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index cba30e9547b4..22e58f51ed23 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -130,7 +130,7 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 }
 /*
- * Handle a fault on the vmalloc or module mapping area
+ * Handle a fault on the vmalloc area.
 */
 static inline int vmalloc_fault(pgd_t *pgd, unsigned long address)
 {
@@ -203,9 +203,14 @@ static pgd_t *get_current_pgd(void)
 * interrupt or a critical region, and must do as little as possible.
 * Similarly, we can't use atomic ops here, since we may be handling a
 * fault caused by an atomic op access.
+ *
+ * If we find a migrating PTE while we're in an NMI context, and we're
+ * at a PC that has a registered exception handler, we don't wait,
+ * since this thread may (e.g.) have been interrupted while migrating
+ * its own stack, which would then cause us to self-deadlock.
 */
 static int handle_migrating_pte(pgd_t *pgd, int fault_num,
-                                unsigned long address,
+                                unsigned long address, unsigned long pc,
                                int is_kernel_mode, int write)
 {
        pud_t *pud;
@@ -227,6 +232,8 @@ static int handle_migrating_pte(pgd_t *pgd, int fault_num,
                pte_offset_kernel(pmd, address);
        pteval = *pte;
        if (pte_migrating(pteval)) {
+                if (in_nmi() && search_exception_tables(pc))
+                        return 0;
                wait_for_migration(pte);
                return 1;
        }
@@ -300,7 +307,7 @@ static int handle_page_fault(struct pt_regs *regs,
         * rather than trying to patch up the existing PTE.
         */
        pgd = get_current_pgd();
-        if (handle_migrating_pte(pgd, fault_num, address,
+        if (handle_migrating_pte(pgd, fault_num, address, regs->pc,
                                 is_kernel_mode, write))
                return 1;
@@ -335,9 +342,12 @@ static int handle_page_fault(struct pt_regs *regs,
        /*
         * If we're trying to touch user-space addresses, we must
         * be either at PL0, or else with interrupts enabled in the
-         * kernel, so either way we can re-enable interrupts here.
+         * kernel, so either way we can re-enable interrupts here
+         * unless we are doing atomic access to user space with
+         * interrupts disabled.
         */
-        local_irq_enable();
+        if (!(regs->flags & PT_FLAGS_DISABLE_IRQ))
+                local_irq_enable();
        mm = tsk->mm;
@@ -665,7 +675,7 @@ struct intvec_state do_page_fault_ics(struct pt_regs *regs, int fault_num,
         */
        if (fault_num == INT_DTLB_ACCESS)
                write = 1;
-        if (handle_migrating_pte(pgd, fault_num, address, 1, write))
+        if (handle_migrating_pte(pgd, fault_num, address, pc, 1, write))
                return state;
        /* Return zero so that we continue on with normal fault handling. */
diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c
index 1cc6ae477c98..499f73770b05 100644
--- a/arch/tile/mm/homecache.c
+++ b/arch/tile/mm/homecache.c
@@ -394,6 +394,7 @@ int page_home(struct page *page)
                return pte_to_home(*virt_to_pte(NULL, kva));
        }
 }
+EXPORT_SYMBOL(page_home);
 void homecache_change_page_home(struct page *page, int order, int home)
 {
diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index 830c4908ea76..6a9d20ddc34f 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -254,11 +254,6 @@ static pgprot_t __init init_pgprot(ulong address)
                return construct_pgprot(PAGE_KERNEL_RO, PAGE_HOME_IMMUTABLE);
        }
-        /* As a performance optimization, keep the boot init stack here. */
-        if (address >= (ulong)&init_thread_union &&
-            address < (ulong)&init_thread_union + THREAD_SIZE)
-                return construct_pgprot(PAGE_KERNEL, smp_processor_id());
 #ifndef __tilegx__
 #if !ATOMIC_LOCKS_FOUND_VIA_TABLE()
        /* Force the atomic_locks[] array page to be hash-for-home. */
@@ -557,6 +552,7 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
        address = MEM_SV_INTRPT;
        pmd = get_pmd(pgtables, address);
+        pfn = 0;  /* code starts at PA 0 */
        if (ktext_small) {
                /* Allocate an L2 PTE for the kernel text */
                int cpu = 0;
@@ -579,10 +575,15 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
                }
                BUG_ON(address != (unsigned long)_stext);
-                pfn = 0;  /* code starts at PA 0 */
+                pte = NULL;
-                pte = alloc_pte();
+                for (; address < (unsigned long)_einittext;
-                for (pte_ofs = 0; address < (unsigned long)_einittext;
+                     pfn++, address += PAGE_SIZE) {
-                     pfn++, pte_ofs++, address += PAGE_SIZE) {
+                        pte_ofs = pte_index(address);
+                        if (pte_ofs == 0) {
+                                if (pte)
+                                        assign_pte(pmd++, pte);
+                                pte = alloc_pte();
+                        }
                        if (!ktext_local) {
                                prot = set_remote_cache_cpu(prot, cpu);
                                cpu = cpumask_next(cpu, &ktext_mask);
@@ -591,7 +592,8 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
                        }
                        pte[pte_ofs] = pfn_pte(pfn, prot);
                }
-                assign_pte(pmd, pte);
+                if (pte)
+                        assign_pte(pmd, pte);
        } else {
                pte_t pteval = pfn_pte(0, PAGE_KERNEL_EXEC);
                pteval = pte_mkhuge(pteval);
@@ -614,7 +616,9 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
                else
                        pteval = hv_pte_set_mode(pteval,
                                                 HV_PTE_MODE_CACHE_NO_L3);
-                *(pte_t *)pmd = pteval;
+                for (; address < (unsigned long)_einittext;
+                     pfn += PFN_DOWN(HPAGE_SIZE), address += HPAGE_SIZE)
+                        *(pte_t *)(pmd++) = pfn_pte(pfn, pteval);
        }
        /* Set swapper_pgprot here so it is flushed to memory right away. */
diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index 87303693a072..2410aa899b3e 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -177,14 +177,10 @@ void shatter_huge_page(unsigned long addr)
        if (!pmd_huge_page(*pmd))
                return;
-        /*
+        spin_lock_irqsave(&init_mm.page_table_lock, flags);
-         * Grab the pgd_lock, since we may need it to walk the pgd_list,
-         * and since we need some kind of lock here to avoid races.
-         */
-        spin_lock_irqsave(&pgd_lock, flags);
        if (!pmd_huge_page(*pmd)) {
                /* Lost the race to convert the huge page. */
-                spin_unlock_irqrestore(&pgd_lock, flags);
+                spin_unlock_irqrestore(&init_mm.page_table_lock, flags);
                return;
        }
@@ -194,6 +190,7 @@ void shatter_huge_page(unsigned long addr)
 #ifdef __PAGETABLE_PMD_FOLDED
        /* Walk every pgd on the system and update the pmd there. */
+        spin_lock(&pgd_lock);
        list_for_each(pos, &pgd_list) {
                pmd_t *copy_pmd;
                pgd = list_to_pgd(pos) + pgd_index(addr);
@@ -201,6 +198,7 @@ void shatter_huge_page(unsigned long addr)
                copy_pmd = pmd_offset(pud, addr);
                __set_pmd(copy_pmd, *pmd);
        }
+        spin_unlock(&pgd_lock);
 #endif
        /* Tell every cpu to notice the change. */
@@ -208,7 +206,7 @@ void shatter_huge_page(unsigned long addr)
                     cpu_possible_mask, NULL, 0);
        /* Hold the lock until the TLB flush is finished to avoid races. */
-        spin_unlock_irqrestore(&pgd_lock, flags);
+        spin_unlock_irqrestore(&init_mm.page_table_lock, flags);
 }
 /*
@@ -217,9 +215,13 @@ void shatter_huge_page(unsigned long addr)
 * against pageattr.c; it is the unique case in which a valid change
 * of kernel pagetables can't be lazily synchronized by vmalloc faults.
 * vmalloc faults work because attached pagetables are never freed.
- * The locking scheme was chosen on the basis of manfred's
+ *
- * recommendations and having no core impact whatsoever.
+ * The lock is always taken with interrupts disabled, unlike on x86
- * -- wli
+ * and other platforms, because we need to take the lock in
+ * shatter_huge_page(), which may be called from an interrupt context.
+ * We are not at risk from the tlbflush IPI deadlock that was seen on
+ * x86, since we use the flush_remote() API to have the hypervisor do
+ * the TLB flushes regardless of irq disabling.
 */
 DEFINE_SPINLOCK(pgd_lock);
 LIST_HEAD(pgd_list);
@@ -469,10 +471,18 @@ void __set_pte(pte_t *ptep, pte_t pte)
 void set_pte(pte_t *ptep, pte_t pte)
 {
-        struct page *page = pfn_to_page(pte_pfn(pte));
+        if (pte_present(pte) &&
+            (!CHIP_HAS_MMIO() || hv_pte_get_mode(pte) != HV_PTE_MODE_MMIO)) {
-        /* Update the home of a PTE if necessary */
+                /* The PTE actually references physical memory. */
-        pte = pte_set_home(pte, page_home(page));
+                unsigned long pfn = pte_pfn(pte);
+                if (pfn_valid(pfn)) {
+                        /* Update the home of the PTE from the struct page. */
+                        pte = pte_set_home(pte, page_home(pfn_to_page(pfn)));
+                } else if (hv_pte_get_mode(pte) == 0) {
+                        /* remap_pfn_range(), etc, must supply PTE mode. */
+                        panic("set_pte(): out-of-range PFN and mode 0\n");
+                }
+        }
        __set_pte(ptep, pte);
 }
diff --git a/arch/um/kernel/skas/process.c b/arch/um/kernel/skas/process.c
index 2e9852c0d487..0a9e57e7446b 100644
--- a/arch/um/kernel/skas/process.c
+++ b/arch/um/kernel/skas/process.c
@@ -41,7 +41,7 @@ static int __init start_kernel_proc(void *unused)
        cpu_tasks[0].pid = pid;
        cpu_tasks[0].task = current;
 #ifdef CONFIG_SMP
-        cpu_online_map = cpumask_of_cpu(0);
+        init_cpu_online(get_cpu_mask(0));
 #endif
        start_kernel();
        return 0;
diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c
index 155206a66908..6f588e160fb0 100644
--- a/arch/um/kernel/smp.c
+++ b/arch/um/kernel/smp.c
@@ -76,7 +76,7 @@ static int idle_proc(void *cpup)
                cpu_relax();
        notify_cpu_starting(cpu);
-        cpu_set(cpu, cpu_online_map);
+        set_cpu_online(cpu, true);
        default_idle();
        return 0;
 }
@@ -110,8 +110,7 @@ void smp_prepare_cpus(unsigned int maxcpus)
        for (i = 0; i < ncpus; ++i)
                set_cpu_possible(i, true);
-        cpu_clear(me, cpu_online_map);
+        set_cpu_online(me, true);
-        cpu_set(me, cpu_online_map);
        cpu_set(me, cpu_callin_map);
        err = os_pipe(cpu_data[me].ipi_pipe, 1, 1);
@@ -138,13 +137,13 @@ void smp_prepare_cpus(unsigned int maxcpus)
 void smp_prepare_boot_cpu(void)
 {
-        cpu_set(smp_processor_id(), cpu_online_map);
+        set_cpu_online(smp_processor_id(), true);
 }
 int __cpu_up(unsigned int cpu)
 {
        cpu_set(cpu, smp_commenced_mask);
-        while (!cpu_isset(cpu, cpu_online_map))
+        while (!cpu_online(cpu))
                mb();
        return 0;
 }
diff --git a/arch/unicore32/include/asm/dma-mapping.h b/arch/unicore32/include/asm/dma-mapping.h
index 9258e592f414..366460a81796 100644
--- a/arch/unicore32/include/asm/dma-mapping.h
+++ b/arch/unicore32/include/asm/dma-mapping.h
@@ -82,20 +82,26 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask)
        return 0;
 }
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+#define dma_alloc_coherent(d,s,h,f)     dma_alloc_attrs(d,s,h,f,NULL)
-                                       dma_addr_t *dma_handle, gfp_t flag)
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+                                    dma_addr_t *dma_handle, gfp_t flag,
+                                    struct dma_attrs *attrs)
 {
        struct dma_map_ops *dma_ops = get_dma_ops(dev);
-        return dma_ops->alloc_coherent(dev, size, dma_handle, flag);
+        return dma_ops->alloc(dev, size, dma_handle, flag, attrs);
 }
-static inline void dma_free_coherent(struct device *dev, size_t size,
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
-                                     void *cpu_addr, dma_addr_t dma_handle)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+                                  void *cpu_addr, dma_addr_t dma_handle,
+                                  struct dma_attrs *attrs)
 {
        struct dma_map_ops *dma_ops = get_dma_ops(dev);
-        dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
+        dma_ops->free(dev, size, cpu_addr, dma_handle, attrs);
 }
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
diff --git a/arch/unicore32/mm/dma-swiotlb.c b/arch/unicore32/mm/dma-swiotlb.c
index bfa9fbb2bbb1..16c08b2143a7 100644
--- a/arch/unicore32/mm/dma-swiotlb.c
+++ b/arch/unicore32/mm/dma-swiotlb.c
@@ -17,9 +17,23 @@
 #include <asm/dma.h>
+static void *unicore_swiotlb_alloc_coherent(struct device *dev, size_t size,
+                                            dma_addr_t *dma_handle, gfp_t flags,
+                                            struct dma_attrs *attrs)
+{
+        return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
+}
+static void unicore_swiotlb_free_coherent(struct device *dev, size_t size,
+                                          void *vaddr, dma_addr_t dma_addr,
+                                          struct dma_attrs *attrs)
+{
+        swiotlb_free_coherent(dev, size, vaddr, dma_addr);
+}
 struct dma_map_ops swiotlb_dma_map_ops = {
-        .alloc_coherent = swiotlb_alloc_coherent,
+        .alloc = unicore_swiotlb_alloc_coherent,
-        .free_coherent = swiotlb_free_coherent,
+        .free = unicore_swiotlb_free_coherent,
        .map_sg = swiotlb_map_sg_attrs,
        .unmap_sg = swiotlb_unmap_sg_attrs,
        .dma_supported = swiotlb_dma_supported,
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 968dbe24a255..41a7237606a3 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -129,6 +129,7 @@ KBUILD_CFLAGS += -Wno-sign-compare
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 # prevent gcc from generating any FP code by mistake
 KBUILD_CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,)
+KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
 KBUILD_CFLAGS += $(mflags-y)
 KBUILD_AFLAGS += $(mflags-y)
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index ed3065fd6314..4b4331d71935 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -59,7 +59,8 @@ extern int dma_supported(struct device *hwdev, u64 mask);
 extern int dma_set_mask(struct device *dev, u64 mask);
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-                                        dma_addr_t *dma_addr, gfp_t flag);
+                                        dma_addr_t *dma_addr, gfp_t flag,
+                                        struct dma_attrs *attrs);
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
@@ -111,9 +112,11 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
       return gfp;
 }
+#define dma_alloc_coherent(d,s,h,f)     dma_alloc_attrs(d,s,h,f,NULL)
 static inline void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
+dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
-                gfp_t gfp)
+                gfp_t gfp, struct dma_attrs *attrs)
 {
        struct dma_map_ops *ops = get_dma_ops(dev);
        void *memory;
@@ -129,18 +132,21 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
        if (!is_device_dma_capable(dev))
                return NULL;
-        if (!ops->alloc_coherent)
+        if (!ops->alloc)
                return NULL;
-        memory = ops->alloc_coherent(dev, size, dma_handle,
+        memory = ops->alloc(dev, size, dma_handle,
-                                     dma_alloc_coherent_gfp_flags(dev, gfp));
+                            dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
        debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
        return memory;
 }
-static inline void dma_free_coherent(struct device *dev, size_t size,
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
-                                     void *vaddr, dma_addr_t bus)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+                                  void *vaddr, dma_addr_t bus,
+                                  struct dma_attrs *attrs)
 {
        struct dma_map_ops *ops = get_dma_ops(dev);
@@ -150,8 +156,8 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
                return;
        debug_dma_free_coherent(dev, size, vaddr, bus);
-        if (ops->free_coherent)
+        if (ops->free)
-                ops->free_coherent(dev, size, vaddr, bus);
+                ops->free(dev, size, vaddr, bus, attrs);
 }
 #endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7284c9a6a0b5..4fa7dcceb6c0 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -974,16 +974,6 @@ extern bool cpu_has_amd_erratum(const int *);
 #define cpu_has_amd_erratum(x)  (false)
 #endif /* CONFIG_CPU_SUP_AMD */
-#ifdef CONFIG_X86_32
-/*
- * disable hlt during certain critical i/o operations
- */
-#define HAVE_DISABLE_HLT
-#endif
-void disable_hlt(void);
-void enable_hlt(void);
 void cpu_idle_wait(void);
 extern unsigned long arch_align_stack(unsigned long sp);
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
new file mode 100644
index 000000000000..6fe6767b7124
--- /dev/null
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -0,0 +1,46 @@
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+/*
+ * This is largely generic for little-endian machines, but the
+ * optimal byte mask counting is probably going to be something
+ * that is architecture-specific. If you have a reliably fast
+ * bit count instruction, that might be better than the multiply
+ * and shift, for example.
+ */
+#ifdef CONFIG_64BIT
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+        return mask*0x0001020304050608ul >> 56;
+}
+#else   /* 32-bit case */
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+        /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+        long a = (0x0ff0001+mask) >> 23;
+        /* Fix the 1 for 00 case */
+        return a & mask;
+}
+#endif
+#define REPEAT_BYTE(x)  ((~0ul / 0xff) * (x))
+/* Return the high bit set in the first byte that is a zero */
+static inline unsigned long has_zero(unsigned long a)
+{
+        return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80);
+}
+#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index b1e7c7f7a0af..e66311200cbd 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -477,7 +477,7 @@ error:
 /* allocate and map a coherent mapping */
 static void *
 gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
-                    gfp_t flag)
+                    gfp_t flag, struct dma_attrs *attrs)
 {
        dma_addr_t paddr;
        unsigned long align_mask;
@@ -500,7 +500,8 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
                }
                __free_pages(page, get_order(size));
        } else
-                return dma_generic_alloc_coherent(dev, size, dma_addr, flag);
+                return dma_generic_alloc_coherent(dev, size, dma_addr, flag,
+                                                  attrs);
        return NULL;
 }
@@ -508,7 +509,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 /* free a coherent mapping */
 static void
 gart_free_coherent(struct device *dev, size_t size, void *vaddr,
-                   dma_addr_t dma_addr)
+                   dma_addr_t dma_addr, struct dma_attrs *attrs)
 {
        gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL);
        free_pages((unsigned long)vaddr, get_order(size));
@@ -700,8 +701,8 @@ static struct dma_map_ops gart_dma_ops = {
        .unmap_sg                       = gart_unmap_sg,
        .map_page                       = gart_map_page,
        .unmap_page                     = gart_unmap_page,
-        .alloc_coherent                 = gart_alloc_coherent,
+        .alloc                          = gart_alloc_coherent,
-        .free_coherent                  = gart_free_coherent,
+        .free                           = gart_free_coherent,
        .mapping_error                  = gart_mapping_error,
 };
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index ef484d9d0a25..a2dfacfd7103 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1271,6 +1271,17 @@ done:
        return num ? -EINVAL : 0;
 }
+PMU_FORMAT_ATTR(cccr, "config:0-31" );
+PMU_FORMAT_ATTR(escr, "config:32-62");
+PMU_FORMAT_ATTR(ht,   "config:63"   );
+static struct attribute *intel_p4_formats_attr[] = {
+        &format_attr_cccr.attr,
+        &format_attr_escr.attr,
+        &format_attr_ht.attr,
+        NULL,
+};
 static __initconst const struct x86_pmu p4_pmu = {
        .name                   = "Netburst P4/Xeon",
        .handle_irq             = p4_pmu_handle_irq,
@@ -1305,6 +1316,8 @@ static __initconst const struct x86_pmu p4_pmu = {
         * the former idea is taken from OProfile code
         */
        .perfctr_second_write   = 1,
+        .format_attrs           = intel_p4_formats_attr,
 };
 __init int p4_pmu_init(void)
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 7943e0c21bde..3dafc6003b7c 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -282,8 +282,13 @@ void fixup_irqs(void)
                else if (!(warned++))
                        set_affinity = 0;
+                /*
+                 * We unmask if the irq was not marked masked by the
+                 * core code. That respects the lazy irq disable
+                 * behaviour.
+                 */
                if (!irqd_can_move_in_process_context(data) &&
-                    !irqd_irq_disabled(data) && chip->irq_unmask)
+                    !irqd_irq_masked(data) && chip->irq_unmask)
                        chip->irq_unmask(data);
                raw_spin_unlock(&desc->lock);
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index 90fcf62854bb..1d5d31ea686b 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -68,16 +68,9 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf,
        return count;
 }
-static int setup_data_open(struct inode *inode, struct file *file)
-{
-        file->private_data = inode->i_private;
-        return 0;
-}
 static const struct file_operations fops_setup_data = {
        .read           = setup_data_read,
-        .open           = setup_data_open,
+        .open           = simple_open,
        .llseek         = default_llseek,
 };
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index db6720edfdd0..8bfb6146f753 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -43,6 +43,8 @@
 #include <linux/smp.h>
 #include <linux/nmi.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/uaccess.h>
+#include <linux/memory.h>
 #include <asm/debugreg.h>
 #include <asm/apicdef.h>
@@ -741,6 +743,64 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
        regs->ip = ip;
 }
+int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
+{
+        int err;
+        char opc[BREAK_INSTR_SIZE];
+        bpt->type = BP_BREAKPOINT;
+        err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+                                BREAK_INSTR_SIZE);
+        if (err)
+                return err;
+        err = probe_kernel_write((char *)bpt->bpt_addr,
+                                 arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
+#ifdef CONFIG_DEBUG_RODATA
+        if (!err)
+                return err;
+        /*
+         * It is safe to call text_poke() because normal kernel execution
+         * is stopped on all cores, so long as the text_mutex is not locked.
+         */
+        if (mutex_is_locked(&text_mutex))
+                return -EBUSY;
+        text_poke((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,
+                  BREAK_INSTR_SIZE);
+        err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
+        if (err)
+                return err;
+        if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE))
+                return -EINVAL;
+        bpt->type = BP_POKE_BREAKPOINT;
+#endif /* CONFIG_DEBUG_RODATA */
+        return err;
+}
+int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
+{
+#ifdef CONFIG_DEBUG_RODATA
+        int err;
+        char opc[BREAK_INSTR_SIZE];
+        if (bpt->type != BP_POKE_BREAKPOINT)
+                goto knl_write;
+        /*
+         * It is safe to call text_poke() because normal kernel execution
+         * is stopped on all cores, so long as the text_mutex is not locked.
+         */
+        if (mutex_is_locked(&text_mutex))
+                goto knl_write;
+        text_poke((void *)bpt->bpt_addr, bpt->saved_instr, BREAK_INSTR_SIZE);
+        err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
+        if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE))
+                goto knl_write;
+        return err;
+knl_write:
+#endif /* CONFIG_DEBUG_RODATA */
+        return probe_kernel_write((char *)bpt->bpt_addr,
+                                  (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
+}
 struct kgdb_arch arch_kgdb_ops = {
        /* Breakpoint instruction: */
        .gdb_bpt_instr          = { 0xcc },
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 694d801bf606..b8ba6e4a27e4 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -38,6 +38,7 @@
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/tlbflush.h>
+#include <asm/idle.h>
 static int kvmapf = 1;
@@ -253,7 +254,10 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
                kvm_async_pf_task_wait((u32)read_cr2());
                break;
        case KVM_PV_REASON_PAGE_READY:
+                rcu_irq_enter();
+                exit_idle();
                kvm_async_pf_task_wake((u32)read_cr2());
+                rcu_irq_exit();
                break;
        }
 }
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 6ac5782f4d6b..d0b2fb9ccbb1 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -430,7 +430,7 @@ static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr,
 }
 static void* calgary_alloc_coherent(struct device *dev, size_t size,
-        dma_addr_t *dma_handle, gfp_t flag)
+        dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs)
 {
        void *ret = NULL;
        dma_addr_t mapping;
@@ -463,7 +463,8 @@ error:
 }
 static void calgary_free_coherent(struct device *dev, size_t size,
-                                  void *vaddr, dma_addr_t dma_handle)
+                                  void *vaddr, dma_addr_t dma_handle,
+                                  struct dma_attrs *attrs)
 {
        unsigned int npages;
        struct iommu_table *tbl = find_iommu_table(dev);
@@ -476,8 +477,8 @@ static void calgary_free_coherent(struct device *dev, size_t size,
 }
 static struct dma_map_ops calgary_dma_ops = {
-        .alloc_coherent = calgary_alloc_coherent,
+        .alloc = calgary_alloc_coherent,
-        .free_coherent = calgary_free_coherent,
+        .free = calgary_free_coherent,
        .map_sg = calgary_map_sg,
        .unmap_sg = calgary_unmap_sg,
        .map_page = calgary_map_page,
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 28e5e06fcba4..3003250ac51d 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -96,7 +96,8 @@ void __init pci_iommu_alloc(void)
        }
 }
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-                                 dma_addr_t *dma_addr, gfp_t flag)
+                                 dma_addr_t *dma_addr, gfp_t flag,
+                                 struct dma_attrs *attrs)
 {
        unsigned long dma_mask;
        struct page *page;
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 3af4af810c07..f96050685b46 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -75,7 +75,7 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
 }
 static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
-                                dma_addr_t dma_addr)
+                                dma_addr_t dma_addr, struct dma_attrs *attrs)
 {
        free_pages((unsigned long)vaddr, get_order(size));
 }
@@ -96,8 +96,8 @@ static void nommu_sync_sg_for_device(struct device *dev,
 }
 struct dma_map_ops nommu_dma_ops = {
-        .alloc_coherent         = dma_generic_alloc_coherent,
+        .alloc                  = dma_generic_alloc_coherent,
-        .free_coherent          = nommu_free_coherent,
+        .free                   = nommu_free_coherent,
        .map_sg                 = nommu_map_sg,
        .map_page               = nommu_map_page,
        .sync_single_for_device = nommu_sync_single_for_device,
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 8f972cbddef0..6c483ba98b9c 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -15,21 +15,30 @@
 int swiotlb __read_mostly;
 static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-                                        dma_addr_t *dma_handle, gfp_t flags)
+                                        dma_addr_t *dma_handle, gfp_t flags,
+                                        struct dma_attrs *attrs)
 {
        void *vaddr;
-        vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags);
+        vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags,
+                                           attrs);
        if (vaddr)
                return vaddr;
        return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags);
 }
+static void x86_swiotlb_free_coherent(struct device *dev, size_t size,
+                                      void *vaddr, dma_addr_t dma_addr,
+                                      struct dma_attrs *attrs)
+{
+        swiotlb_free_coherent(dev, size, vaddr, dma_addr);
+}
 static struct dma_map_ops swiotlb_dma_ops = {
        .mapping_error = swiotlb_dma_mapping_error,
-        .alloc_coherent = x86_swiotlb_alloc_coherent,
+        .alloc = x86_swiotlb_alloc_coherent,
-        .free_coherent = swiotlb_free_coherent,
+        .free = x86_swiotlb_free_coherent,
        .sync_single_for_cpu = swiotlb_sync_single_for_cpu,
        .sync_single_for_device = swiotlb_sync_single_for_device,
        .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index a33afaa5ddb7..1d92a5ab6e8b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -362,34 +362,10 @@ void (*pm_idle)(void);
 EXPORT_SYMBOL(pm_idle);
 #endif
-#ifdef CONFIG_X86_32
-/*
- * This halt magic was a workaround for ancient floppy DMA
- * wreckage. It should be safe to remove.
- */
-static int hlt_counter;
-void disable_hlt(void)
-{
-        hlt_counter++;
-}
-EXPORT_SYMBOL(disable_hlt);
-void enable_hlt(void)
-{
-        hlt_counter--;
-}
-EXPORT_SYMBOL(enable_hlt);
-static inline int hlt_use_halt(void)
-{
-        return (!hlt_counter && boot_cpu_data.hlt_works_ok);
-}
-#else
 static inline int hlt_use_halt(void)
 {
        return 1;
 }
-#endif
 #ifndef CONFIG_SMP
 static inline void play_dead(void)
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index a73f0c104813..173df38dbda5 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -369,7 +369,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
        case MSR_CORE_PERF_FIXED_CTR_CTRL:
                if (pmu->fixed_ctr_ctrl == data)
                        return 0;
-                if (!(data & 0xfffffffffffff444)) {
+                if (!(data & 0xfffffffffffff444ull)) {
                        reprogram_fixed_counters(pmu, data);
                        return 0;
                }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 280751c84724..ad85adfef843 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3906,7 +3906,9 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
                vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
        vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
+        vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
        vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */
+        srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
        vmx_set_cr4(&vmx->vcpu, 0);
        vmx_set_efer(&vmx->vcpu, 0);
        vmx_fpu_activate(&vmx->vcpu);
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 66870223f8c5..877b9a1b2152 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -18,17 +18,17 @@
 * r9d : hlen = skb->len - skb->data_len
 */
 #define SKBDATA %r8
+#define SKF_MAX_NEG_OFF    $(-0x200000) /* SKF_LL_OFF from filter.h */
-sk_load_word_ind:
-        .globl  sk_load_word_ind
-        add     %ebx,%esi       /* offset += X */
-#       test    %esi,%esi       /* if (offset < 0) goto bpf_error; */
-        js      bpf_error
 sk_load_word:
        .globl  sk_load_word
+        test    %esi,%esi
+        js      bpf_slow_path_word_neg
+sk_load_word_positive_offset:
+        .globl  sk_load_word_positive_offset
        mov     %r9d,%eax               # hlen
        sub     %esi,%eax               # hlen - offset
        cmp     $3,%eax
@@ -37,16 +37,15 @@ sk_load_word:
        bswap   %eax                    /* ntohl() */
        ret
-sk_load_half_ind:
-        .globl sk_load_half_ind
-        add     %ebx,%esi       /* offset += X */
-        js      bpf_error
 sk_load_half:
        .globl  sk_load_half
+        test    %esi,%esi
+        js      bpf_slow_path_half_neg
+sk_load_half_positive_offset:
+        .globl  sk_load_half_positive_offset
        mov     %r9d,%eax
        sub     %esi,%eax               #       hlen - offset
        cmp     $1,%eax
@@ -55,14 +54,15 @@ sk_load_half:
        rol     $8,%ax                  # ntohs()
        ret
-sk_load_byte_ind:
-        .globl sk_load_byte_ind
-        add     %ebx,%esi       /* offset += X */
-        js      bpf_error
 sk_load_byte:
        .globl  sk_load_byte
+        test    %esi,%esi
+        js      bpf_slow_path_byte_neg
+sk_load_byte_positive_offset:
+        .globl  sk_load_byte_positive_offset
        cmp     %esi,%r9d   /* if (offset >= hlen) goto bpf_slow_path_byte */
        jle     bpf_slow_path_byte
        movzbl  (SKBDATA,%rsi),%eax
@@ -73,25 +73,21 @@ sk_load_byte:
 *
 * Implements BPF_S_LDX_B_MSH : ldxb  4*([offset]&0xf)
 * Must preserve A accumulator (%eax)
- * Inputs : %esi is the offset value, already known positive
+ * Inputs : %esi is the offset value
 */
-ENTRY(sk_load_byte_msh)
+sk_load_byte_msh:
-        CFI_STARTPROC
+        .globl  sk_load_byte_msh
+        test    %esi,%esi
+        js      bpf_slow_path_byte_msh_neg
+sk_load_byte_msh_positive_offset:
+        .globl  sk_load_byte_msh_positive_offset
        cmp     %esi,%r9d      /* if (offset >= hlen) goto bpf_slow_path_byte_msh */
        jle     bpf_slow_path_byte_msh
        movzbl  (SKBDATA,%rsi),%ebx
        and     $15,%bl
        shl     $2,%bl
        ret
-        CFI_ENDPROC
-ENDPROC(sk_load_byte_msh)
-bpf_error:
-# force a return 0 from jit handler
-        xor             %eax,%eax
-        mov             -8(%rbp),%rbx
-        leaveq
-        ret
 /* rsi contains offset and can be scratched */
 #define bpf_slow_path_common(LEN)               \
@@ -138,3 +134,67 @@ bpf_slow_path_byte_msh:
        shl     $2,%al
        xchg    %eax,%ebx
        ret
+#define sk_negative_common(SIZE)                                \
+        push    %rdi;   /* save skb */                          \
+        push    %r9;                                            \
+        push    SKBDATA;                                        \
+/* rsi already has offset */                                    \
+        mov     $SIZE,%ecx;     /* size */                      \
+        call    bpf_internal_load_pointer_neg_helper;           \
+        test    %rax,%rax;                                      \
+        pop     SKBDATA;                                        \
+        pop     %r9;                                            \
+        pop     %rdi;                                           \
+        jz      bpf_error
+bpf_slow_path_word_neg:
+        cmp     SKF_MAX_NEG_OFF, %esi   /* test range */
+        jl      bpf_error       /* offset lower -> error  */
+sk_load_word_negative_offset:
+        .globl  sk_load_word_negative_offset
+        sk_negative_common(4)
+        mov     (%rax), %eax
+        bswap   %eax
+        ret
+bpf_slow_path_half_neg:
+        cmp     SKF_MAX_NEG_OFF, %esi
+        jl      bpf_error
+sk_load_half_negative_offset:
+        .globl  sk_load_half_negative_offset
+        sk_negative_common(2)
+        mov     (%rax),%ax
+        rol     $8,%ax
+        movzwl  %ax,%eax
+        ret
+bpf_slow_path_byte_neg:
+        cmp     SKF_MAX_NEG_OFF, %esi
+        jl      bpf_error
+sk_load_byte_negative_offset:
+        .globl  sk_load_byte_negative_offset
+        sk_negative_common(1)
+        movzbl  (%rax), %eax
+        ret
+bpf_slow_path_byte_msh_neg:
+        cmp     SKF_MAX_NEG_OFF, %esi
+        jl      bpf_error
+sk_load_byte_msh_negative_offset:
+        .globl  sk_load_byte_msh_negative_offset
+        xchg    %eax,%ebx /* dont lose A , X is about to be scratched */
+        sk_negative_common(1)
+        movzbl  (%rax),%eax
+        and     $15,%al
+        shl     $2,%al
+        xchg    %eax,%ebx
+        ret
+bpf_error:
+# force a return 0 from jit handler
+        xor             %eax,%eax
+        mov             -8(%rbp),%rbx
+        leaveq
+        ret
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5671752f8d9c..0597f95b6da6 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -30,7 +30,10 @@ int bpf_jit_enable __read_mostly;
 * assembly code in arch/x86/net/bpf_jit.S
 */
 extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
-extern u8 sk_load_word_ind[], sk_load_half_ind[], sk_load_byte_ind[];
+extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
+extern u8 sk_load_byte_positive_offset[], sk_load_byte_msh_positive_offset[];
+extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
+extern u8 sk_load_byte_negative_offset[], sk_load_byte_msh_negative_offset[];
 static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -117,6 +120,8 @@ static inline void bpf_flush_icache(void *start, void *end)
        set_fs(old_fs);
 }
+#define CHOOSE_LOAD_FUNC(K, func) \
+        ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
 void bpf_jit_compile(struct sk_filter *fp)
 {
@@ -289,7 +294,7 @@ void bpf_jit_compile(struct sk_filter *fp)
                                        EMIT2(0x24, K & 0xFF); /* and imm8,%al */
                                } else if (K >= 0xFFFF0000) {
                                        EMIT2(0x66, 0x25);      /* and imm16,%ax */
-                                        EMIT2(K, 2);
+                                        EMIT(K, 2);
                                } else {
                                        EMIT1_off32(0x25, K);   /* and imm32,%eax */
                                }
@@ -473,44 +478,46 @@ void bpf_jit_compile(struct sk_filter *fp)
 #endif
                                break;
                        case BPF_S_LD_W_ABS:
-                                func = sk_load_word;
+                                func = CHOOSE_LOAD_FUNC(K, sk_load_word);
 common_load:                    seen |= SEEN_DATAREF;
-                                if ((int)K < 0) {
-                                        /* Abort the JIT because __load_pointer() is needed. */
-                                        goto out;
-                                }
                                t_offset = func - (image + addrs[i]);
                                EMIT1_off32(0xbe, K); /* mov imm32,%esi */
                                EMIT1_off32(0xe8, t_offset); /* call */
                                break;
                        case BPF_S_LD_H_ABS:
-                                func = sk_load_half;
+                                func = CHOOSE_LOAD_FUNC(K, sk_load_half);
                                goto common_load;
                        case BPF_S_LD_B_ABS:
-                                func = sk_load_byte;
+                                func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
                                goto common_load;
                        case BPF_S_LDX_B_MSH:
-                                if ((int)K < 0) {
+                                func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
-                                        /* Abort the JIT because __load_pointer() is needed. */
-                                        goto out;
-                                }
                                seen |= SEEN_DATAREF | SEEN_XREG;
-                                t_offset = sk_load_byte_msh - (image + addrs[i]);
+                                t_offset = func - (image + addrs[i]);
                                EMIT1_off32(0xbe, K);   /* mov imm32,%esi */
                                EMIT1_off32(0xe8, t_offset); /* call sk_load_byte_msh */
                                break;
                        case BPF_S_LD_W_IND:
-                                func = sk_load_word_ind;
+                                func = sk_load_word;
 common_load_ind:                seen |= SEEN_DATAREF | SEEN_XREG;
                                t_offset = func - (image + addrs[i]);
-                                EMIT1_off32(0xbe, K);   /* mov imm32,%esi   */
+                                if (K) {
+                                        if (is_imm8(K)) {
+                                                EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx), %esi */
+                                        } else {
+                                                EMIT2(0x8d, 0xb3); /* lea imm32(%rbx),%esi */
+                                                EMIT(K, 4);
+                                        }
+                                } else {
+                                        EMIT2(0x89,0xde); /* mov %ebx,%esi */
+                                }
                                EMIT1_off32(0xe8, t_offset);    /* call sk_load_xxx_ind */
                                break;
                        case BPF_S_LD_H_IND:
-                                func = sk_load_half_ind;
+                                func = sk_load_half;
                                goto common_load_ind;
                        case BPF_S_LD_B_IND:
-                                func = sk_load_byte_ind;
+                                func = sk_load_byte;
                                goto common_load_ind;
                        case BPF_S_JMP_JA:
                                t_offset = addrs[i + K] - addrs[i];
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 47936830968c..218cdb16163c 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -225,13 +225,13 @@ static void __restore_processor_state(struct saved_context *ctxt)
        fix_processor_context();
        do_fpu_end();
+        x86_platform.restore_sched_clock_state();
        mtrr_bp_restore();
 }
 /* Needed by apm.c */
 void restore_processor_state(void)
 {
-        x86_platform.restore_sched_clock_state();
        __restore_processor_state(&saved_context);
 }
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b132ade26f77..4f51bebac02c 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -967,7 +967,7 @@ void xen_setup_shared_info(void)
        xen_setup_mfn_list_list();
 }
-/* This is called once we have the cpu_possible_map */
+/* This is called once we have the cpu_possible_mask */
 void xen_setup_vcpu_info_placement(void)
 {
        int cpu;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 988828b479ed..b8e279479a6b 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1859,6 +1859,7 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 #endif  /* CONFIG_X86_64 */
 static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss;
+static unsigned char fake_ioapic_mapping[PAGE_SIZE] __page_aligned_bss;
 static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 {
@@ -1899,7 +1900,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
                 * We just don't map the IO APIC - all access is via
                 * hypercalls.  Keep the address in the pte for reference.
                 */
-                pte = pfn_pte(PFN_DOWN(__pa(dummy_mapping)), PAGE_KERNEL);
+                pte = pfn_pte(PFN_DOWN(__pa(fake_ioapic_mapping)), PAGE_KERNEL);
                break;
 #endif
@@ -2064,6 +2065,7 @@ void __init xen_init_mmu_ops(void)
        pv_mmu_ops = xen_mmu_ops;
        memset(dummy_mapping, 0xff, PAGE_SIZE);
+        memset(fake_ioapic_mapping, 0xfd, PAGE_SIZE);
 }
 /* Protected by xen_reservation_lock. */
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index b480d4207a4c..967633ad98c4 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -12,8 +12,8 @@ int xen_swiotlb __read_mostly;
 static struct dma_map_ops xen_swiotlb_dma_ops = {
        .mapping_error = xen_swiotlb_dma_mapping_error,
-        .alloc_coherent = xen_swiotlb_alloc_coherent,
+        .alloc = xen_swiotlb_alloc_coherent,
-        .free_coherent = xen_swiotlb_free_coherent,
+        .free = xen_swiotlb_free_coherent,
        .sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
        .sync_single_for_device = xen_swiotlb_sync_single_for_device,
        .sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 02900e8ce26c..5fac6919b957 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -59,7 +59,7 @@ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
 static void __cpuinit cpu_bringup(void)
 {
-        int cpu = smp_processor_id();
+        int cpu;
        cpu_init();
        touch_softlockup_watchdog();