43 files changed, 362 insertions, 181 deletions
diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S
index d1273c1a1364..6d159cee5f2f 100644
--- a/arch/alpha/kernel/entry.S
+++ b/arch/alpha/kernel/entry.S
@@ -915,15 +915,6 @@ sys_execve:
 .end sys_execve
        .align  4
-        .globl  osf_sigprocmask
-        .ent    osf_sigprocmask
-osf_sigprocmask:
-        .prologue 0
-        mov     $sp, $18
-        jmp     $31, sys_osf_sigprocmask
-.end osf_sigprocmask
-        .align  4
        .globl  alpha_ni_syscall
        .ent    alpha_ni_syscall
 alpha_ni_syscall:
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index 0f6b51ae865a..6f7feb5db271 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -41,46 +41,20 @@ static void do_signal(struct pt_regs *, struct switch_stack *,
 /*
 * The OSF/1 sigprocmask calling sequence is different from the
 * C sigprocmask() sequence..
- *
- * how:
- * 1 - SIG_BLOCK
- * 2 - SIG_UNBLOCK
- * 3 - SIG_SETMASK
- *
- * We change the range to -1 .. 1 in order to let gcc easily
- * use the conditional move instructions.
- *
- * Note that we don't need to acquire the kernel lock for SMP
- * operation, as all of this is local to this thread.
 */
-SYSCALL_DEFINE3(osf_sigprocmask, int, how, unsigned long, newmask,
+SYSCALL_DEFINE2(osf_sigprocmask, int, how, unsigned long, newmask)
-                struct pt_regs *, regs)
 {
-        unsigned long oldmask = -EINVAL;
+        sigset_t oldmask;
+        sigset_t mask;
-        if ((unsigned long)how-1 <= 2) {
+        unsigned long res;
-                long sign = how-2;              /* -1 .. 1 */
-                unsigned long block, unblock;
+        siginitset(&mask, newmask & _BLOCKABLE);
+        res = sigprocmask(how, &mask, &oldmask);
-                newmask &= _BLOCKABLE;
+        if (!res) {
-                spin_lock_irq(&current->sighand->siglock);
+                force_successful_syscall_return();
-                oldmask = current->blocked.sig[0];
+                res = oldmask.sig[0];
-                unblock = oldmask & ~newmask;
-                block = oldmask | newmask;
-                if (!sign)
-                        block = unblock;
-                if (sign <= 0)
-                        newmask = block;
-                if (_NSIG_WORDS > 1 && sign > 0)
-                        sigemptyset(&current->blocked);
-                current->blocked.sig[0] = newmask;
-                recalc_sigpending();
-                spin_unlock_irq(&current->sighand->siglock);
-                regs->r0 = 0;           /* special no error return */
        }
-        return oldmask;
+        return res;
 }
 SYSCALL_DEFINE3(osf_sigaction, int, sig,
@@ -94,9 +68,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig,
                old_sigset_t mask;
                if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
                    __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
-                    __get_user(new_ka.sa.sa_flags, &act->sa_flags))
+                    __get_user(new_ka.sa.sa_flags, &act->sa_flags) ||
+                    __get_user(mask, &act->sa_mask))
                        return -EFAULT;
-                __get_user(mask, &act->sa_mask);
                siginitset(&new_ka.sa.sa_mask, mask);
                new_ka.ka_restorer = NULL;
        }
@@ -106,9 +80,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig,
        if (!ret && oact) {
                if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
                    __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
-                    __put_user(old_ka.sa.sa_flags, &oact->sa_flags))
+                    __put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
+                    __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask))
                        return -EFAULT;
-                __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
        }
        return ret;
diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S
index ce594ef533cc..a6a1de9db16f 100644
--- a/arch/alpha/kernel/systbls.S
+++ b/arch/alpha/kernel/systbls.S
@@ -58,7 +58,7 @@ sys_call_table:
        .quad sys_open                          /* 45 */
        .quad alpha_ni_syscall
        .quad sys_getxgid
-        .quad osf_sigprocmask
+        .quad sys_osf_sigprocmask
        .quad alpha_ni_syscall
        .quad alpha_ni_syscall                  /* 50 */
        .quad sys_acct
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 553b7cf17bfb..88c97bc7a6f5 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -271,7 +271,6 @@ config ARCH_AT91
        bool "Atmel AT91"
        select ARCH_REQUIRE_GPIOLIB
        select HAVE_CLK
-        select ARCH_USES_GETTIMEOFFSET
        help
          This enables support for systems based on the Atmel AT91RM9200,
          AT91SAM9 and AT91CAP9 processors.
@@ -1051,6 +1050,32 @@ config ARM_ERRATA_460075
          ACTLR register. Note that setting specific bits in the ACTLR register
          may not be available in non-secure mode.
+config ARM_ERRATA_742230
+        bool "ARM errata: DMB operation may be faulty"
+        depends on CPU_V7 && SMP
+        help
+          This option enables the workaround for the 742230 Cortex-A9
+          (r1p0..r2p2) erratum. Under rare circumstances, a DMB instruction
+          between two write operations may not ensure the correct visibility
+          ordering of the two writes. This workaround sets a specific bit in
+          the diagnostic register of the Cortex-A9 which causes the DMB
+          instruction to behave as a DSB, ensuring the correct behaviour of
+          the two writes.
+config ARM_ERRATA_742231
+        bool "ARM errata: Incorrect hazard handling in the SCU may lead to data corruption"
+        depends on CPU_V7 && SMP
+        help
+          This option enables the workaround for the 742231 Cortex-A9
+          (r2p0..r2p2) erratum. Under certain conditions, specific to the
+          Cortex-A9 MPCore micro-architecture, two CPUs working in SMP mode,
+          accessing some data located in the same cache line, may get corrupted
+          data due to bad handling of the address hazard when the line gets
+          replaced from one of the CPUs at the same time as another CPU is
+          accessing it. This workaround sets specific bits in the diagnostic
+          register of the Cortex-A9 which reduces the linefill issuing
+          capabilities of the processor.
 config PL310_ERRATA_588369
        bool "Clean & Invalidate maintenance operations do not invalidate clean lines"
        depends on CACHE_L2X0 && ARCH_OMAP4
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index b23f6bc46cfa..65a7c1c588a9 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -116,5 +116,5 @@ CFLAGS_font.o := -Dstatic=
 $(obj)/font.c: $(FONTC)
        $(call cmd,shipped)
-$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile .config
+$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile $(KCONFIG_CONFIG)
        @sed "$(SEDFLAGS)" < $< > $@
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index ab68cf1ef80f..e90b167ea848 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -317,6 +317,10 @@ static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
 #define pgprot_dmacoherent(prot) \
        __pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_BUFFERABLE)
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+                                     unsigned long size, pgprot_t vma_prot);
 #else
 #define pgprot_dmacoherent(prot) \
        __pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_UNCACHED)
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 1b560825e1cf..7885722bdf4e 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -48,6 +48,8 @@ work_pending:
        beq     no_work_pending
        mov     r0, sp                          @ 'regs'
        mov     r2, why                         @ 'syscall'
+        tst     r1, #_TIF_SIGPENDING            @ delivering a signal?
+        movne   why, #0                         @ prevent further restarts
        bl      do_notify_resume
        b       ret_slow_syscall                @ Check work again
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index 5e71ccd5e7d3..1276babf84d5 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -426,7 +426,7 @@ static struct i2c_gpio_platform_data pdata_i2c0 = {
        .sda_is_open_drain      = 1,
        .scl_pin                = AT91_PIN_PA21,
        .scl_is_open_drain      = 1,
-        .udelay                 = 2,            /* ~100 kHz */
+        .udelay                 = 5,            /* ~100 kHz */
 };
 static struct platform_device at91sam9g45_twi0_device = {
@@ -440,7 +440,7 @@ static struct i2c_gpio_platform_data pdata_i2c1 = {
        .sda_is_open_drain      = 1,
        .scl_pin                = AT91_PIN_PB11,
        .scl_is_open_drain      = 1,
-        .udelay                 = 2,            /* ~100 kHz */
+        .udelay                 = 5,            /* ~100 kHz */
 };
 static struct platform_device at91sam9g45_twi1_device = {
diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index 3d996b659ff4..9be261beae7d 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -769,8 +769,7 @@ static struct map_desc dm355_io_desc[] = {
                .virtual        = SRAM_VIRT,
                .pfn            = __phys_to_pfn(0x00010000),
                .length         = SZ_32K,
-                /* MT_MEMORY_NONCACHED requires supersection alignment */
+                .type           = MT_MEMORY_NONCACHED,
-                .type           = MT_DEVICE,
        },
 };
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index 6b6f4c643709..7781e35daec3 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -969,8 +969,7 @@ static struct map_desc dm365_io_desc[] = {
                .virtual        = SRAM_VIRT,
                .pfn            = __phys_to_pfn(0x00010000),
                .length         = SZ_32K,
-                /* MT_MEMORY_NONCACHED requires supersection alignment */
+                .type           = MT_MEMORY_NONCACHED,
-                .type           = MT_DEVICE,
        },
 };
diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c
index 40fec315c99a..5e5b0a7831fb 100644
--- a/arch/arm/mach-davinci/dm644x.c
+++ b/arch/arm/mach-davinci/dm644x.c
@@ -653,8 +653,7 @@ static struct map_desc dm644x_io_desc[] = {
                .virtual        = SRAM_VIRT,
                .pfn            = __phys_to_pfn(0x00008000),
                .length         = SZ_16K,
-                /* MT_MEMORY_NONCACHED requires supersection alignment */
+                .type           = MT_MEMORY_NONCACHED,
-                .type           = MT_DEVICE,
        },
 };
diff --git a/arch/arm/mach-davinci/dm646x.c b/arch/arm/mach-davinci/dm646x.c
index e4a3df1872ac..26e8a9c7f50b 100644
--- a/arch/arm/mach-davinci/dm646x.c
+++ b/arch/arm/mach-davinci/dm646x.c
@@ -737,8 +737,7 @@ static struct map_desc dm646x_io_desc[] = {
                .virtual        = SRAM_VIRT,
                .pfn            = __phys_to_pfn(0x00010000),
                .length         = SZ_32K,
-                /* MT_MEMORY_NONCACHED requires supersection alignment */
+                .type           = MT_MEMORY_NONCACHED,
-                .type           = MT_DEVICE,
        },
 };
diff --git a/arch/arm/mach-dove/include/mach/io.h b/arch/arm/mach-dove/include/mach/io.h
index 3b3e4721ce2e..eb4936ff90ad 100644
--- a/arch/arm/mach-dove/include/mach/io.h
+++ b/arch/arm/mach-dove/include/mach/io.h
@@ -13,8 +13,8 @@
 #define IO_SPACE_LIMIT          0xffffffff
-#define __io(a)  ((void __iomem *)(((a) - DOVE_PCIE0_IO_PHYS_BASE) +\
+#define __io(a)         ((void __iomem *)(((a) - DOVE_PCIE0_IO_BUS_BASE) + \
-                                   DOVE_PCIE0_IO_VIRT_BASE))
+                                                 DOVE_PCIE0_IO_VIRT_BASE))
-#define __mem_pci(a)            (a)
+#define __mem_pci(a)    (a)
 #endif
diff --git a/arch/arm/mach-kirkwood/include/mach/kirkwood.h b/arch/arm/mach-kirkwood/include/mach/kirkwood.h
index 93fc2ec95e76..6e924b398919 100644
--- a/arch/arm/mach-kirkwood/include/mach/kirkwood.h
+++ b/arch/arm/mach-kirkwood/include/mach/kirkwood.h
@@ -38,7 +38,7 @@
 #define KIRKWOOD_PCIE1_IO_PHYS_BASE     0xf3000000
 #define KIRKWOOD_PCIE1_IO_VIRT_BASE     0xfef00000
-#define KIRKWOOD_PCIE1_IO_BUS_BASE      0x00000000
+#define KIRKWOOD_PCIE1_IO_BUS_BASE      0x00100000
 #define KIRKWOOD_PCIE1_IO_SIZE          SZ_1M
 #define KIRKWOOD_PCIE_IO_PHYS_BASE      0xf2000000
diff --git a/arch/arm/mach-kirkwood/pcie.c b/arch/arm/mach-kirkwood/pcie.c
index 55e7f00836b7..513ad3102d7c 100644
--- a/arch/arm/mach-kirkwood/pcie.c
+++ b/arch/arm/mach-kirkwood/pcie.c
@@ -117,7 +117,7 @@ static void __init pcie0_ioresources_init(struct pcie_port *pp)
         * IORESOURCE_IO
         */
        pp->res[0].name = "PCIe 0 I/O Space";
-        pp->res[0].start = KIRKWOOD_PCIE_IO_PHYS_BASE;
+        pp->res[0].start = KIRKWOOD_PCIE_IO_BUS_BASE;
        pp->res[0].end = pp->res[0].start + KIRKWOOD_PCIE_IO_SIZE - 1;
        pp->res[0].flags = IORESOURCE_IO;
@@ -139,7 +139,7 @@ static void __init pcie1_ioresources_init(struct pcie_port *pp)
         * IORESOURCE_IO
         */
        pp->res[0].name = "PCIe 1 I/O Space";
-        pp->res[0].start = KIRKWOOD_PCIE1_IO_PHYS_BASE;
+        pp->res[0].start = KIRKWOOD_PCIE1_IO_BUS_BASE;
        pp->res[0].end = pp->res[0].start + KIRKWOOD_PCIE1_IO_SIZE - 1;
        pp->res[0].flags = IORESOURCE_IO;
diff --git a/arch/arm/mach-mmp/include/mach/system.h b/arch/arm/mach-mmp/include/mach/system.h
index 4f5b0e0ce6cf..1a8a25edb1b4 100644
--- a/arch/arm/mach-mmp/include/mach/system.h
+++ b/arch/arm/mach-mmp/include/mach/system.h
@@ -9,6 +9,8 @@
 #ifndef __ASM_MACH_SYSTEM_H
 #define __ASM_MACH_SYSTEM_H
+#include <mach/cputype.h>
 static inline void arch_idle(void)
 {
        cpu_do_idle();
@@ -16,6 +18,9 @@ static inline void arch_idle(void)
 static inline void arch_reset(char mode, const char *cmd)
 {
-        cpu_reset(0);
+        if (cpu_is_pxa168())
+                cpu_reset(0xffff0000);
+        else
+                cpu_reset(0);
 }
 #endif /* __ASM_MACH_SYSTEM_H */
diff --git a/arch/arm/mach-pxa/cpufreq-pxa2xx.c b/arch/arm/mach-pxa/cpufreq-pxa2xx.c
index 50d5939a78f1..58093d9e07be 100644
--- a/arch/arm/mach-pxa/cpufreq-pxa2xx.c
+++ b/arch/arm/mach-pxa/cpufreq-pxa2xx.c
@@ -312,8 +312,7 @@ static int pxa_set_target(struct cpufreq_policy *policy,
        freqs.cpu = policy->cpu;
        if (freq_debug)
-                pr_debug(KERN_INFO "Changing CPU frequency to %d Mhz, "
+                pr_debug("Changing CPU frequency to %d Mhz, (SDRAM %d Mhz)\n",
-                         "(SDRAM %d Mhz)\n",
                         freqs.new / 1000, (pxa_freq_settings[idx].div2) ?
                         (new_freq_mem / 2000) : (new_freq_mem / 1000));
diff --git a/arch/arm/mach-pxa/include/mach/hardware.h b/arch/arm/mach-pxa/include/mach/hardware.h
index 428cc7bda9a4..814f1458a06a 100644
--- a/arch/arm/mach-pxa/include/mach/hardware.h
+++ b/arch/arm/mach-pxa/include/mach/hardware.h
@@ -264,23 +264,35 @@
 * <= 0x2 for pxa21x/pxa25x/pxa26x/pxa27x
 * == 0x3 for pxa300/pxa310/pxa320
 */
+#if defined(CONFIG_PXA25x) || defined(CONFIG_PXA27x)
 #define __cpu_is_pxa2xx(id)                             \
        ({                                              \
                unsigned int _id = (id) >> 13 & 0x7;    \
                _id <= 0x2;                             \
         })
+#else
+#define __cpu_is_pxa2xx(id)     (0)
+#endif
+#ifdef CONFIG_PXA3xx
 #define __cpu_is_pxa3xx(id)                             \
        ({                                              \
                unsigned int _id = (id) >> 13 & 0x7;    \
                _id == 0x3;                             \
         })
+#else
+#define __cpu_is_pxa3xx(id)     (0)
+#endif
+#if defined(CONFIG_CPU_PXA930) || defined(CONFIG_CPU_PXA935)
 #define __cpu_is_pxa93x(id)                             \
        ({                                              \
                unsigned int _id = (id) >> 4 & 0xfff;   \
                _id == 0x683 || _id == 0x693;           \
         })
+#else
+#define __cpu_is_pxa93x(id)     (0)
+#endif
 #define cpu_is_pxa2xx()                                 \
        ({                                              \
diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c
index 77ad6d34ab5b..405b92a29793 100644
--- a/arch/arm/mach-pxa/palm27x.c
+++ b/arch/arm/mach-pxa/palm27x.c
@@ -469,9 +469,13 @@ static struct i2c_board_info __initdata palm27x_pi2c_board_info[] = {
        },
 };
+static struct i2c_pxa_platform_data palm27x_i2c_power_info = {
+        .use_pio        = 1,
+};
 void __init palm27x_pmic_init(void)
 {
        i2c_register_board_info(1, ARRAY_AND_SIZE(palm27x_pi2c_board_info));
-        pxa27x_set_i2c_power_info(NULL);
+        pxa27x_set_i2c_power_info(&palm27x_i2c_power_info);
 }
 #endif
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index c9b747cedea8..37d6173bbb66 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -240,6 +240,7 @@ static void __init vpac270_onenand_init(void) {}
 #if defined(CONFIG_MMC_PXA) || defined(CONFIG_MMC_PXA_MODULE)
 static struct pxamci_platform_data vpac270_mci_platform_data = {
        .ocr_mask               = MMC_VDD_32_33 | MMC_VDD_33_34,
+        .gpio_power             = -1,
        .gpio_card_detect       = GPIO53_VPAC270_SD_DETECT_N,
        .gpio_card_ro           = GPIO52_VPAC270_SD_READONLY,
        .detect_delay_ms        = 200,
diff --git a/arch/arm/mach-u300/include/mach/gpio.h b/arch/arm/mach-u300/include/mach/gpio.h
index 7b1fc984abb6..d5a71abcbaea 100644
--- a/arch/arm/mach-u300/include/mach/gpio.h
+++ b/arch/arm/mach-u300/include/mach/gpio.h
@@ -273,6 +273,9 @@ extern void gpio_pullup(unsigned gpio, int value);
 extern int gpio_get_value(unsigned gpio);
 extern void gpio_set_value(unsigned gpio, int value);
+#define gpio_get_value_cansleep gpio_get_value
+#define gpio_set_value_cansleep gpio_set_value
 /* wrappers to sleep-enable the previous two functions */
 static inline unsigned gpio_to_irq(unsigned gpio)
 {
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
index 577df6cccb08..efb127022d42 100644
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ b/arch/arm/mach-vexpress/ct-ca9x4.c
@@ -227,7 +227,13 @@ static void ct_ca9x4_init(void)
        int i;
 #ifdef CONFIG_CACHE_L2X0
-        l2x0_init(MMIO_P2V(CT_CA9X4_L2CC), 0x00000000, 0xfe0fffff);
+        void __iomem *l2x0_base = MMIO_P2V(CT_CA9X4_L2CC);
+        /* set RAM latencies to 1 cycle for this core tile. */
+        writel(0, l2x0_base + L2X0_TAG_LATENCY_CTRL);
+        writel(0, l2x0_base + L2X0_DATA_LATENCY_CTRL);
+        l2x0_init(l2x0_base, 0x00400000, 0xfe0fffff);
 #endif
        clkdev_add_table(lookups, ARRAY_SIZE(lookups));
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index d073b64ae87e..724ba3bce72c 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -885,8 +885,23 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
        if (ai_usermode & UM_SIGNAL)
                force_sig(SIGBUS, current);
-        else
+        else {
-                set_cr(cr_no_alignment);
+                /*
+                 * We're about to disable the alignment trap and return to
+                 * user space.  But if an interrupt occurs before actually
+                 * reaching user space, then the IRQ vector entry code will
+                 * notice that we were still in kernel space and therefore
+                 * the alignment trap won't be re-enabled in that case as it
+                 * is presumed to be always on from kernel space.
+                 * Let's prevent that race by disabling interrupts here (they
+                 * are disabled on the way back to user space anyway in
+                 * entry-common.S) and disable the alignment trap only if
+                 * there is no work pending for this thread.
+                 */
+                raw_local_irq_disable();
+                if (!(current_thread_info()->flags & _TIF_WORK_MASK))
+                        set_cr(cr_no_alignment);
+        }
        return 0;
 }
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 6e1c4f6a2b3f..6a3a2d0cd6db 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -15,6 +15,7 @@
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
 #include <linux/sort.h>
+#include <linux/fs.h>
 #include <asm/cputype.h>
 #include <asm/sections.h>
@@ -246,6 +247,9 @@ static struct mem_type mem_types[] = {
                .domain    = DOMAIN_USER,
        },
        [MT_MEMORY] = {
+                .prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+                                L_PTE_USER | L_PTE_EXEC,
+                .prot_l1   = PMD_TYPE_TABLE,
                .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
                .domain    = DOMAIN_KERNEL,
        },
@@ -254,6 +258,9 @@ static struct mem_type mem_types[] = {
                .domain    = DOMAIN_KERNEL,
        },
        [MT_MEMORY_NONCACHED] = {
+                .prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+                                L_PTE_USER | L_PTE_EXEC | L_PTE_MT_BUFFERABLE,
+                .prot_l1   = PMD_TYPE_TABLE,
                .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
                .domain    = DOMAIN_KERNEL,
        },
@@ -411,9 +418,12 @@ static void __init build_mem_type_table(void)
         * Enable CPU-specific coherency if supported.
         * (Only available on XSC3 at the moment.)
         */
-        if (arch_is_coherent() && cpu_is_xsc3())
+        if (arch_is_coherent() && cpu_is_xsc3()) {
                mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
+                mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+                mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+                mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
+        }
        /*
         * ARMv6 and above have extended page tables.
         */
@@ -438,7 +448,9 @@ static void __init build_mem_type_table(void)
                mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
                mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
                mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
+                mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
                mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+                mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
 #endif
        }
@@ -475,6 +487,8 @@ static void __init build_mem_type_table(void)
        mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask;
        mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask;
        mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd;
+        mem_types[MT_MEMORY].prot_pte |= kern_pgprot;
+        mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask;
        mem_types[MT_ROM].prot_sect |= cp->pmd;
        switch (cp->pmd) {
@@ -498,6 +512,19 @@ static void __init build_mem_type_table(void)
        }
 }
+#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
+pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+                              unsigned long size, pgprot_t vma_prot)
+{
+        if (!pfn_valid(pfn))
+                return pgprot_noncached(vma_prot);
+        else if (file->f_flags & O_SYNC)
+                return pgprot_writecombine(vma_prot);
+        return vma_prot;
+}
+EXPORT_SYMBOL(phys_mem_access_prot);
+#endif
 #define vectors_base()  (vectors_high() ? 0xffff0000 : 0)
 static void __init *early_alloc(unsigned long sz)
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 6a8506d99ee9..7563ff0141bd 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -186,13 +186,14 @@ cpu_v7_name:
 *      It is assumed that:
 *      - cache type register is implemented
 */
-__v7_setup:
+__v7_ca9mp_setup:
 #ifdef CONFIG_SMP
        mrc     p15, 0, r0, c1, c0, 1
        tst     r0, #(1 << 6)                   @ SMP/nAMP mode enabled?
        orreq   r0, r0, #(1 << 6) | (1 << 0)    @ Enable SMP/nAMP mode and
        mcreq   p15, 0, r0, c1, c0, 1           @ TLB ops broadcasting
 #endif
+__v7_setup:
        adr     r12, __v7_setup_stack           @ the local stack
        stmia   r12, {r0-r5, r7, r9, r11, lr}
        bl      v7_flush_dcache_all
@@ -201,11 +202,16 @@ __v7_setup:
        mrc     p15, 0, r0, c0, c0, 0           @ read main ID register
        and     r10, r0, #0xff000000            @ ARM?
        teq     r10, #0x41000000
-        bne     2f
+        bne     3f
        and     r5, r0, #0x00f00000             @ variant
        and     r6, r0, #0x0000000f             @ revision
-        orr     r0, r6, r5, lsr #20-4           @ combine variant and revision
+        orr     r6, r6, r5, lsr #20-4           @ combine variant and revision
+        ubfx    r0, r0, #4, #12                 @ primary part number
+        /* Cortex-A8 Errata */
+        ldr     r10, =0x00000c08                @ Cortex-A8 primary part number
+        teq     r0, r10
+        bne     2f
 #ifdef CONFIG_ARM_ERRATA_430973
        teq     r5, #0x00100000                 @ only present in r1p*
        mrceq   p15, 0, r10, c1, c0, 1          @ read aux control register
@@ -213,21 +219,42 @@ __v7_setup:
        mcreq   p15, 0, r10, c1, c0, 1          @ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_458693
-        teq     r0, #0x20                       @ only present in r2p0
+        teq     r6, #0x20                       @ only present in r2p0
        mrceq   p15, 0, r10, c1, c0, 1          @ read aux control register
        orreq   r10, r10, #(1 << 5)             @ set L1NEON to 1
        orreq   r10, r10, #(1 << 9)             @ set PLDNOP to 1
        mcreq   p15, 0, r10, c1, c0, 1          @ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_460075
-        teq     r0, #0x20                       @ only present in r2p0
+        teq     r6, #0x20                       @ only present in r2p0
        mrceq   p15, 1, r10, c9, c0, 2          @ read L2 cache aux ctrl register
        tsteq   r10, #1 << 22
        orreq   r10, r10, #(1 << 22)            @ set the Write Allocate disable bit
        mcreq   p15, 1, r10, c9, c0, 2          @ write the L2 cache aux ctrl register
 #endif
+        b       3f
+        /* Cortex-A9 Errata */
+2:      ldr     r10, =0x00000c09                @ Cortex-A9 primary part number
+        teq     r0, r10
+        bne     3f
+#ifdef CONFIG_ARM_ERRATA_742230
+        cmp     r6, #0x22                       @ only present up to r2p2
+        mrcle   p15, 0, r10, c15, c0, 1         @ read diagnostic register
+        orrle   r10, r10, #1 << 4               @ set bit #4
+        mcrle   p15, 0, r10, c15, c0, 1         @ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_742231
+        teq     r6, #0x20                       @ present in r2p0
+        teqne   r6, #0x21                       @ present in r2p1
+        teqne   r6, #0x22                       @ present in r2p2
+        mrceq   p15, 0, r10, c15, c0, 1         @ read diagnostic register
+        orreq   r10, r10, #1 << 12              @ set bit #12
+        orreq   r10, r10, #1 << 22              @ set bit #22
+        mcreq   p15, 0, r10, c15, c0, 1         @ write diagnostic register
+#endif
-2:      mov     r10, #0
+3:      mov     r10, #0
 #ifdef HARVARD_CACHE
        mcr     p15, 0, r10, c7, c5, 0          @ I+BTB cache invalidate
 #endif
@@ -323,6 +350,29 @@ cpu_elf_name:
        .section ".proc.info.init", #alloc, #execinstr
+        .type   __v7_ca9mp_proc_info, #object
+__v7_ca9mp_proc_info:
+        .long   0x410fc090              @ Required ID value
+        .long   0xff0ffff0              @ Mask for ID
+        .long   PMD_TYPE_SECT | \
+                PMD_SECT_AP_WRITE | \
+                PMD_SECT_AP_READ | \
+                PMD_FLAGS
+        .long   PMD_TYPE_SECT | \
+                PMD_SECT_XN | \
+                PMD_SECT_AP_WRITE | \
+                PMD_SECT_AP_READ
+        b       __v7_ca9mp_setup
+        .long   cpu_arch_name
+        .long   cpu_elf_name
+        .long   HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
+        .long   cpu_v7_name
+        .long   v7_processor_functions
+        .long   v7wbi_tlb_fns
+        .long   v6_user_fns
+        .long   v7_cache_fns
+        .size   __v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
        /*
         * Match any ARMv7 processor core.
         */
diff --git a/arch/arm/plat-nomadik/timer.c b/arch/arm/plat-nomadik/timer.c
index ea3ca86c5283..aedf9c1d645e 100644
--- a/arch/arm/plat-nomadik/timer.c
+++ b/arch/arm/plat-nomadik/timer.c
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/arm/mach-nomadik/timer.c
+ *  linux/arch/arm/plat-nomadik/timer.c
 *
 * Copyright (C) 2008 STMicroelectronics
 * Copyright (C) 2010 Alessandro Rubini
@@ -75,7 +75,7 @@ static void nmdk_clkevt_mode(enum clock_event_mode mode,
                cr = readl(mtu_base + MTU_CR(1));
                writel(0, mtu_base + MTU_LR(1));
                writel(cr | MTU_CRn_ENA, mtu_base + MTU_CR(1));
-                writel(0x2, mtu_base + MTU_IMSC);
+                writel(1 << 1, mtu_base + MTU_IMSC);
                break;
        case CLOCK_EVT_MODE_SHUTDOWN:
        case CLOCK_EVT_MODE_UNUSED:
@@ -131,25 +131,23 @@ void __init nmdk_timer_init(void)
 {
        unsigned long rate;
        struct clk *clk0;
-        struct clk *clk1;
+        u32 cr = MTU_CRn_32BITS;
-        u32 cr;
        clk0 = clk_get_sys("mtu0", NULL);
        BUG_ON(IS_ERR(clk0));
-        clk1 = clk_get_sys("mtu1", NULL);
-        BUG_ON(IS_ERR(clk1));
        clk_enable(clk0);
-        clk_enable(clk1);
        /*
-         * Tick rate is 2.4MHz for Nomadik and 110MHz for ux500:
+         * Tick rate is 2.4MHz for Nomadik and 2.4Mhz, 100MHz or 133 MHz
-         * use a divide-by-16 counter if it's more than 16MHz
+         * for ux500.
+         * Use a divide-by-16 counter if the tick rate is more than 32MHz.
+         * At 32 MHz, the timer (with 32 bit counter) can be programmed
+         * to wake-up at a max 127s a head in time. Dividing a 2.4 MHz timer
+         * with 16 gives too low timer resolution.
         */
-        cr = MTU_CRn_32BITS;;
        rate = clk_get_rate(clk0);
-        if (rate > 16 << 20) {
+        if (rate > 32000000) {
                rate /= 16;
                cr |= MTU_CRn_PRESCALE_16;
        } else {
@@ -170,15 +168,8 @@ void __init nmdk_timer_init(void)
                pr_err("timer: failed to initialize clock source %s\n",
                       nmdk_clksrc.name);
-        /* Timer 1 is used for events, fix according to rate */
+        /* Timer 1 is used for events */
-        cr = MTU_CRn_32BITS;
-        rate = clk_get_rate(clk1);
-        if (rate > 16 << 20) {
-                rate /= 16;
-                cr |= MTU_CRn_PRESCALE_16;
-        } else {
-                cr |= MTU_CRn_PRESCALE_1;
-        }
        clockevents_calc_mult_shift(&nmdk_clkevt, rate, MTU_MIN_RANGE);
        writel(cr | MTU_CRn_ONESHOT, mtu_base + MTU_CR(1)); /* off, currently */
diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig
index e39a417a368d..a92cb499313f 100644
--- a/arch/arm/plat-omap/Kconfig
+++ b/arch/arm/plat-omap/Kconfig
@@ -33,7 +33,7 @@ config OMAP_DEBUG_DEVICES
 config OMAP_DEBUG_LEDS
        bool
        depends on OMAP_DEBUG_DEVICES
-        default y if LEDS
+        default y if LEDS_CLASS
 config OMAP_RESET_CLOCKS
        bool "Reset unused clocks during boot"
diff --git a/arch/arm/plat-omap/mcbsp.c b/arch/arm/plat-omap/mcbsp.c
index e31496e35b0f..0c8612fd8312 100644
--- a/arch/arm/plat-omap/mcbsp.c
+++ b/arch/arm/plat-omap/mcbsp.c
@@ -156,7 +156,7 @@ static irqreturn_t omap_mcbsp_rx_irq_handler(int irq, void *dev_id)
                /* Writing zero to RSYNC_ERR clears the IRQ */
                MCBSP_WRITE(mcbsp_rx, SPCR1, MCBSP_READ_CACHE(mcbsp_rx, SPCR1));
        } else {
-                complete(&mcbsp_rx->tx_irq_completion);
+                complete(&mcbsp_rx->rx_irq_completion);
        }
        return IRQ_HANDLED;
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index 226b2e858d6c..10b3b4c63372 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -220,20 +220,7 @@ void __init omap_map_sram(void)
        if (omap_sram_size == 0)
                return;
-        if (cpu_is_omap24xx()) {
-                omap_sram_io_desc[0].virtual = OMAP2_SRAM_VA;
-                base = OMAP2_SRAM_PA;
-                base = ROUND_DOWN(base, PAGE_SIZE);
-                omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
-        }
        if (cpu_is_omap34xx()) {
-                omap_sram_io_desc[0].virtual = OMAP3_SRAM_VA;
-                base = OMAP3_SRAM_PA;
-                base = ROUND_DOWN(base, PAGE_SIZE);
-                omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
                /*
                 * SRAM must be marked as non-cached on OMAP3 since the
                 * CORE DPLL M2 divider change code (in SRAM) runs with the
@@ -244,13 +231,11 @@ void __init omap_map_sram(void)
                omap_sram_io_desc[0].type = MT_MEMORY_NONCACHED;
        }
-        if (cpu_is_omap44xx()) {
+        omap_sram_io_desc[0].virtual = omap_sram_base;
-                omap_sram_io_desc[0].virtual = OMAP4_SRAM_VA;
+        base = omap_sram_start;
-                base = OMAP4_SRAM_PA;
+        base = ROUND_DOWN(base, PAGE_SIZE);
-                base = ROUND_DOWN(base, PAGE_SIZE);
+        omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
-                omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
+        omap_sram_io_desc[0].length = ROUND_DOWN(omap_sram_size, PAGE_SIZE);
-        }
-        omap_sram_io_desc[0].length = 1024 * 1024;      /* Use section desc */
        iotable_init(omap_sram_io_desc, ARRAY_SIZE(omap_sram_io_desc));
        printk(KERN_INFO "SRAM: Mapped pa 0x%08lx to va 0x%08lx size: 0x%lx\n",
diff --git a/arch/m68k/mac/macboing.c b/arch/m68k/mac/macboing.c
index 8f0640847ad2..05285d08e547 100644
--- a/arch/m68k/mac/macboing.c
+++ b/arch/m68k/mac/macboing.c
@@ -162,7 +162,7 @@ static void mac_init_asc( void )
 void mac_mksound( unsigned int freq, unsigned int length )
 {
        __u32 cfreq = ( freq << 5 ) / 468;
-        __u32 flags;
+        unsigned long flags;
        int i;
        if ( mac_special_bell == NULL )
@@ -224,7 +224,7 @@ static void mac_nosound( unsigned long ignored )
 */
 static void mac_quadra_start_bell( unsigned int freq, unsigned int length, unsigned int volume )
 {
-        __u32 flags;
+        unsigned long flags;
        /* if the bell is already ringing, ring longer */
        if ( mac_bell_duration > 0 )
@@ -271,7 +271,7 @@ static void mac_quadra_start_bell( unsigned int freq, unsigned int length, unsig
 static void mac_quadra_ring_bell( unsigned long ignored )
 {
        int     i, count = mac_asc_samplespersec / HZ;
-        __u32 flags;
+        unsigned long flags;
        /*
         * we neither want a sound buffer overflow nor underflow, so we need to match
diff --git a/arch/mn10300/Kconfig.debug b/arch/mn10300/Kconfig.debug
index ff80e86b9bd2..ce83c74b3fd7 100644
--- a/arch/mn10300/Kconfig.debug
+++ b/arch/mn10300/Kconfig.debug
@@ -101,7 +101,7 @@ config GDBSTUB_DEBUG_BREAKPOINT
 choice
        prompt "GDB stub port"
-        default GDBSTUB_TTYSM0
+        default GDBSTUB_ON_TTYSM0
        depends on GDBSTUB
        help
          Select the serial port used for GDB-stub.
diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c
index 717db14c2cc3..d4de05ab7864 100644
--- a/arch/mn10300/kernel/signal.c
+++ b/arch/mn10300/kernel/signal.c
@@ -65,10 +65,10 @@ asmlinkage long sys_sigaction(int sig,
                old_sigset_t mask;
                if (verify_area(VERIFY_READ, act, sizeof(*act)) ||
                    __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
-                    __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
+                    __get_user(new_ka.sa.sa_restorer, &act->sa_restorer) ||
+                    __get_user(new_ka.sa.sa_flags, &act->sa_flags) ||
+                    __get_user(mask, &act->sa_mask))
                        return -EFAULT;
-                __get_user(new_ka.sa.sa_flags, &act->sa_flags);
-                __get_user(mask, &act->sa_mask);
                siginitset(&new_ka.sa.sa_mask, mask);
        }
@@ -77,10 +77,10 @@ asmlinkage long sys_sigaction(int sig,
        if (!ret && oact) {
                if (verify_area(VERIFY_WRITE, oact, sizeof(*oact)) ||
                    __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
-                    __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
+                    __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer) ||
+                    __put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
+                    __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask))
                        return -EFAULT;
-                __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
-                __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
        }
        return ret;
@@ -102,6 +102,9 @@ static int restore_sigcontext(struct pt_regs *regs,
 {
        unsigned int err = 0;
+        /* Always make any pending restarted system calls return -EINTR */
+        current_thread_info()->restart_block.fn = do_no_restart_syscall;
        if (is_using_fpu(current))
                fpu_kill_state(current);
@@ -330,8 +333,6 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
        regs->d0 = sig;
        regs->d1 = (unsigned long) &frame->sc;
-        set_fs(USER_DS);
        /* the tracer may want to single-step inside the handler */
        if (test_thread_flag(TIF_SINGLESTEP))
                ptrace_notify(SIGTRAP);
@@ -345,7 +346,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
        return 0;
 give_sigsegv:
-        force_sig(SIGSEGV, current);
+        force_sigsegv(sig, current);
        return -EFAULT;
 }
@@ -413,8 +414,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
        regs->d0 = sig;
        regs->d1 = (long) &frame->info;
-        set_fs(USER_DS);
        /* the tracer may want to single-step inside the handler */
        if (test_thread_flag(TIF_SINGLESTEP))
                ptrace_notify(SIGTRAP);
@@ -428,10 +427,16 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
        return 0;
 give_sigsegv:
-        force_sig(SIGSEGV, current);
+        force_sigsegv(sig, current);
        return -EFAULT;
 }
+static inline void stepback(struct pt_regs *regs)
+{
+        regs->pc -= 2;
+        regs->orig_d0 = -1;
+}
 /*
 * handle the actual delivery of a signal to userspace
 */
@@ -459,7 +464,7 @@ static int handle_signal(int sig,
                        /* fallthrough */
                case -ERESTARTNOINTR:
                        regs->d0 = regs->orig_d0;
-                        regs->pc -= 2;
+                        stepback(regs);
                }
        }
@@ -527,12 +532,12 @@ static void do_signal(struct pt_regs *regs)
                case -ERESTARTSYS:
                case -ERESTARTNOINTR:
                        regs->d0 = regs->orig_d0;
-                        regs->pc -= 2;
+                        stepback(regs);
                        break;
                case -ERESTART_RESTARTBLOCK:
                        regs->d0 = __NR_restart_syscall;
-                        regs->pc -= 2;
+                        stepback(regs);
                        break;
                }
        }
diff --git a/arch/mn10300/mm/Makefile b/arch/mn10300/mm/Makefile
index 28b9d983db0c..1557277fbc5c 100644
--- a/arch/mn10300/mm/Makefile
+++ b/arch/mn10300/mm/Makefile
@@ -2,13 +2,11 @@
 # Makefile for the MN10300-specific memory management code
 #
+cacheflush-y    := cache.o cache-mn10300.o
+cacheflush-$(CONFIG_MN10300_CACHE_WBACK) += cache-flush-mn10300.o
+cacheflush-$(CONFIG_MN10300_CACHE_DISABLED) := cache-disabled.o
 obj-y := \
        init.o fault.o pgtable.o extable.o tlb-mn10300.o mmu-context.o \
-        misalignment.o dma-alloc.o
+        misalignment.o dma-alloc.o $(cacheflush-y)
-ifneq ($(CONFIG_MN10300_CACHE_DISABLED),y)
-obj-y   += cache.o cache-mn10300.o
-ifeq ($(CONFIG_MN10300_CACHE_WBACK),y)
-obj-y   += cache-flush-mn10300.o
-endif
-endif
diff --git a/arch/mn10300/mm/cache-disabled.c b/arch/mn10300/mm/cache-disabled.c
new file mode 100644
index 000000000000..f669ea42aba6
--- /dev/null
+++ b/arch/mn10300/mm/cache-disabled.c
@@ -0,0 +1,21 @@
+/* Handle the cache being disabled
+ *
+ * Copyright (C) 2010 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#include <linux/mm.h>
+/*
+ * allow userspace to flush the instruction cache
+ */
+asmlinkage long sys_cacheflush(unsigned long start, unsigned long end)
+{
+        if (end < start)
+                return -EINVAL;
+        return 0;
+}
diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c
index 030f4b93e255..5df2869c874b 100644
--- a/arch/x86/boot/early_serial_console.c
+++ b/arch/x86/boot/early_serial_console.c
@@ -58,7 +58,19 @@ static void parse_earlyprintk(void)
                if (arg[pos] == ',')
                        pos++;
-                if (!strncmp(arg, "ttyS", 4)) {
+                /*
+                 * make sure we have
+                 *      "serial,0x3f8,115200"
+                 *      "serial,ttyS0,115200"
+                 *      "ttyS0,115200"
+                 */
+                if (pos == 7 && !strncmp(arg + pos, "0x", 2)) {
+                        port = simple_strtoull(arg + pos, &e, 16);
+                        if (port == 0 || arg + pos == e)
+                                port = DEFAULT_SERIAL_PORT;
+                        else
+                                pos = e - arg;
+                } else if (!strncmp(arg + pos, "ttyS", 4)) {
                        static const int bases[] = { 0x3f8, 0x2f8 };
                        int idx = 0;
diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h
index d2544f1d705d..cb030374b90a 100644
--- a/arch/x86/include/asm/amd_iommu_proto.h
+++ b/arch/x86/include/asm/amd_iommu_proto.h
@@ -38,4 +38,10 @@ static inline void amd_iommu_stats_init(void) { }
 #endif /* !CONFIG_AMD_IOMMU_STATS */
+static inline bool is_rd890_iommu(struct pci_dev *pdev)
+{
+        return (pdev->vendor == PCI_VENDOR_ID_ATI) &&
+               (pdev->device == PCI_DEVICE_ID_RD890_IOMMU);
+}
 #endif /* _ASM_X86_AMD_IOMMU_PROTO_H  */
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 7014e88bc779..08616180deaf 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -368,6 +368,9 @@ struct amd_iommu {
        /* capabilities of that IOMMU read from ACPI */
        u32 cap;
+        /* flags read from acpi table */
+        u8 acpi_flags;
        /*
         * Capability pointer. There could be more than one IOMMU per PCI
         * device function if there are more than one AMD IOMMU capability
@@ -411,6 +414,15 @@ struct amd_iommu {
        /* default dma_ops domain for that IOMMU */
        struct dma_ops_domain *default_dom;
+        /*
+         * This array is required to work around a potential BIOS bug.
+         * The BIOS may miss to restore parts of the PCI configuration
+         * space when the system resumes from S3. The result is that the
+         * IOMMU does not execute commands anymore which leads to system
+         * failure.
+         */
+        u32 cache_cfg[4];
 };
 /*
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 545776efeb16..bafd80defa43 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -309,7 +309,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
 {
        return ((1UL << (nr % BITS_PER_LONG)) &
-                (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
+                (addr[nr / BITS_PER_LONG])) != 0;
 }
 static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 0925676266bd..fedf32a8c3ec 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -11,6 +11,8 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
+CFLAGS_REMOVE_pvclock.o = -pg
+CFLAGS_REMOVE_kvmclock.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index fb7a5f052e2b..fb16f17e59be 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -61,7 +61,7 @@ struct cstate_entry {
                unsigned int ecx;
        } states[ACPI_PROCESSOR_MAX_POWER];
 };
-static struct cstate_entry *cpu_cstate_entry;   /* per CPU ptr */
+static struct cstate_entry __percpu *cpu_cstate_entry;  /* per CPU ptr */
 static short mwait_supported[ACPI_PROCESSOR_MAX_POWER];
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index fa044e1e30a2..679b6450382b 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1953,6 +1953,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
                           size_t size,
                           int dir)
 {
+        dma_addr_t flush_addr;
        dma_addr_t i, start;
        unsigned int pages;
@@ -1960,6 +1961,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
            (dma_addr + size > dma_dom->aperture_size))
                return;
+        flush_addr = dma_addr;
        pages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
        dma_addr &= PAGE_MASK;
        start = dma_addr;
@@ -1974,7 +1976,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
        dma_ops_free_addresses(dma_dom, dma_addr, pages);
        if (amd_iommu_unmap_flush || dma_dom->need_flush) {
-                iommu_flush_pages(&dma_dom->domain, dma_addr, size);
+                iommu_flush_pages(&dma_dom->domain, flush_addr, size);
                dma_dom->need_flush = false;
        }
 }
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 3cc63e2b8dd4..5a170cbbbed8 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -632,6 +632,13 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu)
        iommu->last_device = calc_devid(MMIO_GET_BUS(range),
                                        MMIO_GET_LD(range));
        iommu->evt_msi_num = MMIO_MSI_NUM(misc);
+        if (is_rd890_iommu(iommu->dev)) {
+                pci_read_config_dword(iommu->dev, 0xf0, &iommu->cache_cfg[0]);
+                pci_read_config_dword(iommu->dev, 0xf4, &iommu->cache_cfg[1]);
+                pci_read_config_dword(iommu->dev, 0xf8, &iommu->cache_cfg[2]);
+                pci_read_config_dword(iommu->dev, 0xfc, &iommu->cache_cfg[3]);
+        }
 }
 /*
@@ -649,29 +656,9 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
        struct ivhd_entry *e;
        /*
-         * First set the recommended feature enable bits from ACPI
+         * First save the recommended feature enable bits from ACPI
-         * into the IOMMU control registers
         */
-        h->flags & IVHD_FLAG_HT_TUN_EN_MASK ?
+        iommu->acpi_flags = h->flags;
-                iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) :
-                iommu_feature_disable(iommu, CONTROL_HT_TUN_EN);
-        h->flags & IVHD_FLAG_PASSPW_EN_MASK ?
-                iommu_feature_enable(iommu, CONTROL_PASSPW_EN) :
-                iommu_feature_disable(iommu, CONTROL_PASSPW_EN);
-        h->flags & IVHD_FLAG_RESPASSPW_EN_MASK ?
-                iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) :
-                iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN);
-        h->flags & IVHD_FLAG_ISOC_EN_MASK ?
-                iommu_feature_enable(iommu, CONTROL_ISOC_EN) :
-                iommu_feature_disable(iommu, CONTROL_ISOC_EN);
-        /*
-         * make IOMMU memory accesses cache coherent
-         */
-        iommu_feature_enable(iommu, CONTROL_COHERENT_EN);
        /*
         * Done. Now parse the device entries
@@ -1116,6 +1103,40 @@ static void init_device_table(void)
        }
 }
+static void iommu_init_flags(struct amd_iommu *iommu)
+{
+        iommu->acpi_flags & IVHD_FLAG_HT_TUN_EN_MASK ?
+                iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) :
+                iommu_feature_disable(iommu, CONTROL_HT_TUN_EN);
+        iommu->acpi_flags & IVHD_FLAG_PASSPW_EN_MASK ?
+                iommu_feature_enable(iommu, CONTROL_PASSPW_EN) :
+                iommu_feature_disable(iommu, CONTROL_PASSPW_EN);
+        iommu->acpi_flags & IVHD_FLAG_RESPASSPW_EN_MASK ?
+                iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) :
+                iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN);
+        iommu->acpi_flags & IVHD_FLAG_ISOC_EN_MASK ?
+                iommu_feature_enable(iommu, CONTROL_ISOC_EN) :
+                iommu_feature_disable(iommu, CONTROL_ISOC_EN);
+        /*
+         * make IOMMU memory accesses cache coherent
+         */
+        iommu_feature_enable(iommu, CONTROL_COHERENT_EN);
+}
+static void iommu_apply_quirks(struct amd_iommu *iommu)
+{
+        if (is_rd890_iommu(iommu->dev)) {
+                pci_write_config_dword(iommu->dev, 0xf0, iommu->cache_cfg[0]);
+                pci_write_config_dword(iommu->dev, 0xf4, iommu->cache_cfg[1]);
+                pci_write_config_dword(iommu->dev, 0xf8, iommu->cache_cfg[2]);
+                pci_write_config_dword(iommu->dev, 0xfc, iommu->cache_cfg[3]);
+        }
+}
 /*
 * This function finally enables all IOMMUs found in the system after
 * they have been initialized
@@ -1126,6 +1147,8 @@ static void enable_iommus(void)
        for_each_iommu(iommu) {
                iommu_disable(iommu);
+                iommu_apply_quirks(iommu);
+                iommu_init_flags(iommu);
                iommu_set_device_table(iommu);
                iommu_enable_command_buffer(iommu);
                iommu_enable_event_buffer(iommu);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3efdf2870a35..03a5b0385ad6 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -102,6 +102,7 @@ struct cpu_hw_events {
         */
        struct perf_event       *events[X86_PMC_IDX_MAX]; /* in counter order */
        unsigned long           active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+        unsigned long           running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
        int                     enabled;
        int                     n_events;
@@ -1010,6 +1011,7 @@ static int x86_pmu_start(struct perf_event *event)
        x86_perf_event_set_period(event);
        cpuc->events[idx] = event;
        __set_bit(idx, cpuc->active_mask);
+        __set_bit(idx, cpuc->running);
        x86_pmu.enable(event);
        perf_event_update_userpage(event);
@@ -1141,8 +1143,16 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
        cpuc = &__get_cpu_var(cpu_hw_events);
        for (idx = 0; idx < x86_pmu.num_counters; idx++) {
-                if (!test_bit(idx, cpuc->active_mask))
+                if (!test_bit(idx, cpuc->active_mask)) {
+                        /*
+                         * Though we deactivated the counter some cpus
+                         * might still deliver spurious interrupts still
+                         * in flight. Catch them:
+                         */
+                        if (__test_and_clear_bit(idx, cpuc->running))
+                                handled++;
                        continue;
+                }
                event = cpuc->events[idx];
                hwc = &event->hw;