Merge branch 'linus' into perf/core

Pick up the latest upstream fixes.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

68 files changed, 477 insertions, 184 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 8d2ae24b9f4a..1feb169274fe 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -407,6 +407,12 @@ config CLONE_BACKWARDS2
         help
           Architecture has the first two arguments of clone(2) swapped.
 
+config CLONE_BACKWARDS3
+        bool
+        help
+          Architecture has tls passed as the 3rd argument of clone(2),
+          not the 5th one.
+
 config ODD_RT_SIGACTION
         bool
         help
diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S
index 99c10475d477..9c548c7cf001 100644
--- a/arch/arc/lib/strchr-700.S
+++ b/arch/arc/lib/strchr-700.S
@@ -39,9 +39,18 @@ ARC_ENTRY strchr
         ld.a    r2,[r0,4]
         sub     r12,r6,r7
         bic     r12,r12,r6
+#ifdef __LITTLE_ENDIAN__
         and     r7,r12,r4
         breq    r7,0,.Loop ; For speed, we want this branch to be unaligned.
         b       .Lfound_char ; Likewise this one.
+#else
+        and     r12,r12,r4
+        breq    r12,0,.Loop ; For speed, we want this branch to be unaligned.
+        lsr_s   r12,r12,7
+        bic     r2,r7,r6
+        b.d     .Lfound_char_b
+        and_s   r2,r2,r12
+#endif
 ; /* We require this code address to be unaligned for speed...  */
 .Laligned:
         ld_s    r2,[r0]
@@ -95,6 +104,7 @@ ARC_ENTRY strchr
         lsr     r7,r7,7
 
         bic     r2,r7,r6
+.Lfound_char_b:
         norm    r2,r2
         sub_s   r0,r0,4
         asr_s   r2,r2,3
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index d59b70c6a6a0..3d77dbe406f4 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -14,11 +14,11 @@
         compatible = "atmel,at91sam9n12ek", "atmel,at91sam9n12", "atmel,at91sam9";
 
         chosen {
-                bootargs = "mem=128M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2";
+                bootargs = "console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2";
         };
 
         memory {
-                reg = <0x20000000 0x10000000>;
+                reg = <0x20000000 0x8000000>;
         };
 
         clocks {
diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi
index b753855b2058..49e3c45818c2 100644
--- a/arch/arm/boot/dts/at91sam9x5ek.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi
@@ -94,8 +94,9 @@
 
                 usb0: ohci@00600000 {
                         status = "okay";
-                        num-ports = <2>;
-                        atmel,vbus-gpio = <&pioD 19 GPIO_ACTIVE_LOW
+                        num-ports = <3>;
+                        atmel,vbus-gpio = <0 /* &pioD 18 GPIO_ACTIVE_LOW *//* Activate to have access to port A */
+                                           &pioD 19 GPIO_ACTIVE_LOW
                                            &pioD 20 GPIO_ACTIVE_LOW
                                           >;
                 };
diff --git a/arch/arm/boot/dts/tegra20-seaboard.dts b/arch/arm/boot/dts/tegra20-seaboard.dts
index 365760b33a26..40e6fb280333 100644
--- a/arch/arm/boot/dts/tegra20-seaboard.dts
+++ b/arch/arm/boot/dts/tegra20-seaboard.dts
@@ -830,6 +830,8 @@
                         regulator-max-microvolt = <5000000>;
                         enable-active-high;
                         gpio = <&gpio 24 0>; /* PD0 */
+                        regulator-always-on;
+                        regulator-boot-on;
                 };
         };
 
diff --git a/arch/arm/boot/dts/tegra20-trimslice.dts b/arch/arm/boot/dts/tegra20-trimslice.dts
index ed4b901b0227..37c93d3c4812 100644
--- a/arch/arm/boot/dts/tegra20-trimslice.dts
+++ b/arch/arm/boot/dts/tegra20-trimslice.dts
@@ -412,6 +412,8 @@
                         regulator-max-microvolt = <5000000>;
                         enable-active-high;
                         gpio = <&gpio 170 0>; /* PV2 */
+                        regulator-always-on;
+                        regulator-boot-on;
                 };
         };
 
diff --git a/arch/arm/boot/dts/tegra20-whistler.dts b/arch/arm/boot/dts/tegra20-whistler.dts
index ab67c94db280..a3d0ebad78a1 100644
--- a/arch/arm/boot/dts/tegra20-whistler.dts
+++ b/arch/arm/boot/dts/tegra20-whistler.dts
@@ -588,6 +588,8 @@
                         regulator-max-microvolt = <5000000>;
                         enable-active-high;
                         gpio = <&tca6416 0 0>; /* GPIO_PMU0 */
+                        regulator-always-on;
+                        regulator-boot-on;
                 };
 
                 vbus3_reg: regulator@3 {
@@ -598,6 +600,8 @@
                         regulator-max-microvolt = <5000000>;
                         enable-active-high;
                         gpio = <&tca6416 1 0>; /* GPIO_PMU1 */
+                        regulator-always-on;
+                        regulator-boot-on;
                 };
         };
 
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index 6462a721ebd4..a252c0bfacf5 100644
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@@ -88,4 +88,7 @@ static inline u32 mpidr_hash_size(void)
 {
         return 1 << mpidr_hash.bits;
 }
+
+extern int platform_can_cpu_hotplug(void);
+
 #endif
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index f8b8965666e9..b07c09e5a0ac 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -107,7 +107,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
                 "       subs    %1, %0, %0, ror #16\n"
                 "       addeq   %0, %0, %4\n"
                 "       strexeq %2, %0, [%3]"
-                : "=&r" (slock), "=&r" (contended), "=r" (res)
+                : "=&r" (slock), "=&r" (contended), "=&r" (res)
                 : "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
                 : "cc");
         } while (res);
@@ -168,17 +168,20 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
-        unsigned long tmp;
+        unsigned long contended, res;
 
-        __asm__ __volatile__(
-"       ldrex   %0, [%1]\n"
-"       teq     %0, #0\n"
-"       strexeq %0, %2, [%1]"
-        : "=&r" (tmp)
-        : "r" (&rw->lock), "r" (0x80000000)
-        : "cc");
+        do {
+                __asm__ __volatile__(
+                "       ldrex   %0, [%2]\n"
+                "       mov     %1, #0\n"
+                "       teq     %0, #0\n"
+                "       strexeq %1, %3, [%2]"
+                : "=&r" (contended), "=&r" (res)
+                : "r" (&rw->lock), "r" (0x80000000)
+                : "cc");
+        } while (res);
 
-        if (tmp == 0) {
+        if (!contended) {
                 smp_mb();
                 return 1;
         } else {
@@ -254,18 +257,26 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
-        unsigned long tmp, tmp2 = 1;
+        unsigned long contended, res;
 
-        __asm__ __volatile__(
-"       ldrex   %0, [%2]\n"
-"       adds    %0, %0, #1\n"
-"       strexpl %1, %0, [%2]\n"
-        : "=&r" (tmp), "+r" (tmp2)
-        : "r" (&rw->lock)
-        : "cc");
+        do {
+                __asm__ __volatile__(
+                "       ldrex   %0, [%2]\n"
+                "       mov     %1, #0\n"
+                "       adds    %0, %0, #1\n"
+                "       strexpl %1, %0, [%2]"
+                : "=&r" (contended), "=&r" (res)
+                : "r" (&rw->lock)
+                : "cc");
+        } while (res);
 
-        smp_mb();
-        return tmp2 == 0;
+        /* If the lock is negative, then it is already held for write. */
+        if (contended < 0x80000000) {
+                smp_mb();
+                return 1;
+        } else {
+                return 0;
+        }
 }
 
 /* read_can_lock - would read_trylock() succeed? */
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 46e7cfb3e721..0baf7f0d9394 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -43,6 +43,7 @@ struct mmu_gather {
         struct mm_struct        *mm;
         unsigned int            fullmm;
         struct vm_area_struct   *vma;
+        unsigned long           start, end;
         unsigned long           range_start;
         unsigned long           range_end;
         unsigned int            nr;
@@ -107,10 +108,12 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
         tlb->mm = mm;
-        tlb->fullmm = fullmm;
+        tlb->fullmm = !(start | (end+1));
+        tlb->start = start;
+        tlb->end = end;
         tlb->vma = NULL;
         tlb->max = ARRAY_SIZE(tlb->local);
         tlb->pages = tlb->local;
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index d40d0ef389db..9cbe70c8b0ef 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -357,7 +357,8 @@ ENDPROC(__pabt_svc)
         .endm
 
         .macro  kuser_cmpxchg_check
-#if !defined(CONFIG_CPU_32v6K) && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
+#if !defined(CONFIG_CPU_32v6K) && defined(CONFIG_KUSER_HELPERS) && \
+    !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
 #ifndef CONFIG_MMU
 #warning "NPTL on non MMU needs fixing"
 #else
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index 25442f451148..918875d96d5d 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -84,17 +84,14 @@ int show_fiq_list(struct seq_file *p, int prec)
 
 void set_fiq_handler(void *start, unsigned int length)
 {
-#if defined(CONFIG_CPU_USE_DOMAINS)
-        void *base = (void *)0xffff0000;
-#else
         void *base = vectors_page;
-#endif
         unsigned offset = FIQ_OFFSET;
 
         memcpy(base + offset, start, length);
+        if (!cache_is_vipt_nonaliasing())
+                flush_icache_range((unsigned long)base + offset, offset +
+                                   length);
         flush_icache_range(0xffff0000 + offset, 0xffff0000 + offset + length);
-        if (!vectors_high())
-                flush_icache_range(offset, offset + length);
 }
 
 int claim_fiq(struct fiq_handler *f)
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 4fb074c446bf..57221e349a7c 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -15,6 +15,7 @@
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/mach-types.h>
+#include <asm/smp_plat.h>
 #include <asm/system_misc.h>
 
 extern const unsigned char relocate_new_kernel[];
@@ -39,6 +40,14 @@ int machine_kexec_prepare(struct kimage *image)
         int i, err;
 
         /*
+         * Validate that if the current HW supports SMP, then the SW supports
+         * and implements CPU hotplug for the current HW. If not, we won't be
+         * able to kexec reliably, so fail the prepare operation.
+         */
+        if (num_possible_cpus() > 1 && !platform_can_cpu_hotplug())
+                return -EINVAL;
+
+        /*
          * No segment at default ATAGs address. try to locate
          * a dtb using magic.
          */
@@ -73,6 +82,7 @@ void machine_crash_nonpanic_core(void *unused)
         crash_save_cpu(&regs, smp_processor_id());
         flush_cache_all();
 
+        set_cpu_online(smp_processor_id(), false);
         atomic_dec(&waiting_for_crash_ipi);
         while (1)
                 cpu_relax();
@@ -134,10 +144,13 @@ void machine_kexec(struct kimage *image)
         unsigned long reboot_code_buffer_phys;
         void *reboot_code_buffer;
 
-        if (num_online_cpus() > 1) {
-                pr_err("kexec: error: multiple CPUs still online\n");
-                return;
-        }
+        /*
+         * This can only happen if machine_shutdown() failed to disable some
+         * CPU, and that can only happen if the checks in
+         * machine_kexec_prepare() were not correct. If this fails, we can't
+         * reliably kexec anyway, so BUG_ON is appropriate.
+         */
+        BUG_ON(num_online_cpus() > 1);
 
         page_list = image->head & PAGE_MASK;
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index d9f5cd4e533f..e186ee1e63f6 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -53,7 +53,12 @@ armpmu_map_cache_event(const unsigned (*cache_map)
 static int
 armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 {
-        int mapping = (*event_map)[config];
+        int mapping;
+
+        if (config >= PERF_COUNT_HW_MAX)
+                return -EINVAL;
+
+        mapping = (*event_map)[config];
         return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
 }
 
@@ -253,6 +258,9 @@ validate_event(struct pmu_hw_events *hw_events,
         struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
         struct pmu *leader_pmu = event->group_leader->pmu;
 
+        if (is_software_event(event))
+                return 1;
+
         if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
                 return 1;
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 536c85fe72a8..94f6b05f9e24 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -462,7 +462,7 @@ int in_gate_area_no_mm(unsigned long addr)
 {
         return in_gate_area(NULL, addr);
 }
-#define is_gate_vma(vma)        ((vma) = &gate_vma)
+#define is_gate_vma(vma)        ((vma) == &gate_vma)
 #else
 #define is_gate_vma(vma)        0
 #endif
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index c2b4f8f0be9a..2dc19349eb19 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -145,6 +145,16 @@ int boot_secondary(unsigned int cpu, struct task_struct *idle)
         return -ENOSYS;
 }
 
+int platform_can_cpu_hotplug(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+        if (smp_ops.cpu_kill)
+                return 1;
+#endif
+
+        return 0;
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 static void percpu_timer_stop(void);
 
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 4a5199070430..db9cf692d4dd 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -146,7 +146,11 @@ static bool pm_fake(struct kvm_vcpu *vcpu,
 #define access_pmintenclr pm_fake
 
 /* Architected CP15 registers.
- * Important: Must be sorted ascending by CRn, CRM, Op1, Op2
+ * CRn denotes the primary register number, but is copied to the CRm in the
+ * user space API for 64-bit register access in line with the terminology used
+ * in the ARM ARM.
+ * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit
+ *            registers preceding 32-bit ones.
  */
 static const struct coproc_reg cp15_regs[] = {
         /* CSSELR: swapped by interrupt.S. */
@@ -154,8 +158,8 @@ static const struct coproc_reg cp15_regs[] = {
                         NULL, reset_unknown, c0_CSSELR },
 
         /* TTBR0/TTBR1: swapped by interrupt.S. */
-        { CRm( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 },
-        { CRm( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 },
+        { CRm64( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 },
+        { CRm64( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 },
 
         /* TTBCR: swapped by interrupt.S. */
         { CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32,
@@ -182,7 +186,7 @@ static const struct coproc_reg cp15_regs[] = {
                         NULL, reset_unknown, c6_IFAR },
 
         /* PAR swapped by interrupt.S */
-        { CRn( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR },
+        { CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR },
 
         /*
          * DC{C,I,CI}SW operations:
@@ -399,12 +403,13 @@ static bool index_to_params(u64 id, struct coproc_params *params)
                               | KVM_REG_ARM_OPC1_MASK))
                         return false;
                 params->is_64bit = true;
-                params->CRm = ((id & KVM_REG_ARM_CRM_MASK)
+                /* CRm to CRn: see cp15_to_index for details */
+                params->CRn = ((id & KVM_REG_ARM_CRM_MASK)
                                >> KVM_REG_ARM_CRM_SHIFT);
                 params->Op1 = ((id & KVM_REG_ARM_OPC1_MASK)
                                >> KVM_REG_ARM_OPC1_SHIFT);
                 params->Op2 = 0;
-                params->CRn = 0;
+                params->CRm = 0;
                 return true;
         default:
                 return false;
@@ -898,7 +903,14 @@ static u64 cp15_to_index(const struct coproc_reg *reg)
         if (reg->is_64) {
                 val |= KVM_REG_SIZE_U64;
                 val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT);
-                val |= (reg->CRm << KVM_REG_ARM_CRM_SHIFT);
+                /*
+                 * CRn always denotes the primary coproc. reg. nr. for the
+                 * in-kernel representation, but the user space API uses the
+                 * CRm for the encoding, because it is modelled after the
+                 * MRRC/MCRR instructions: see the ARM ARM rev. c page
+                 * B3-1445
+                 */
+                val |= (reg->CRn << KVM_REG_ARM_CRM_SHIFT);
         } else {
                 val |= KVM_REG_SIZE_U32;
                 val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT);
diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h
index b7301d3e4799..0461d5c8d3de 100644
--- a/arch/arm/kvm/coproc.h
+++ b/arch/arm/kvm/coproc.h
@@ -135,6 +135,8 @@ static inline int cmp_reg(const struct coproc_reg *i1,
                 return -1;
         if (i1->CRn != i2->CRn)
                 return i1->CRn - i2->CRn;
+        if (i1->is_64 != i2->is_64)
+                return i2->is_64 - i1->is_64;
         if (i1->CRm != i2->CRm)
                 return i1->CRm - i2->CRm;
         if (i1->Op1 != i2->Op1)
@@ -145,6 +147,7 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 
 #define CRn(_x)         .CRn = _x
 #define CRm(_x)         .CRm = _x
+#define CRm64(_x)       .CRn = _x, .CRm = 0
 #define Op1(_x)         .Op1 = _x
 #define Op2(_x)         .Op2 = _x
 #define is64            .is_64 = true
diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c
index 685063a6d0cf..cf93472b9dd6 100644
--- a/arch/arm/kvm/coproc_a15.c
+++ b/arch/arm/kvm/coproc_a15.c
@@ -114,7 +114,11 @@ static bool access_l2ectlr(struct kvm_vcpu *vcpu,
 
 /*
  * A15-specific CP15 registers.
- * Important: Must be sorted ascending by CRn, CRM, Op1, Op2
+ * CRn denotes the primary register number, but is copied to the CRm in the
+ * user space API for 64-bit register access in line with the terminology used
+ * in the ARM ARM.
+ * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit
+ *            registers preceding 32-bit ones.
  */
 static const struct coproc_reg a15_regs[] = {
         /* MPIDR: we use VMPIDR for guest access. */
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index b8e06b7a2833..0c25d9487d53 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -63,7 +63,8 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
                       struct kvm_exit_mmio *mmio)
 {
-        unsigned long rt, len;
+        unsigned long rt;
+        int len;
         bool is_write, sign_extend;
 
         if (kvm_vcpu_dabt_isextabt(vcpu)) {
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index ca6bea4859b4..0988d9e04dd4 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -85,6 +85,12 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
         return p;
 }
 
+static bool page_empty(void *ptr)
+{
+        struct page *ptr_page = virt_to_page(ptr);
+        return page_count(ptr_page) == 1;
+}
+
 static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
 {
         pmd_t *pmd_table = pmd_offset(pud, 0);
@@ -103,12 +109,6 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
         put_page(virt_to_page(pmd));
 }
 
-static bool pmd_empty(pmd_t *pmd)
-{
-        struct page *pmd_page = virt_to_page(pmd);
-        return page_count(pmd_page) == 1;
-}
-
 static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
 {
         if (pte_present(*pte)) {
@@ -118,12 +118,6 @@ static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
         }
 }
 
-static bool pte_empty(pte_t *pte)
-{
-        struct page *pte_page = virt_to_page(pte);
-        return page_count(pte_page) == 1;
-}
-
 static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
                         unsigned long long start, u64 size)
 {
@@ -132,37 +126,37 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
         pmd_t *pmd;
         pte_t *pte;
         unsigned long long addr = start, end = start + size;
-        u64 range;
+        u64 next;
 
         while (addr < end) {
                 pgd = pgdp + pgd_index(addr);
                 pud = pud_offset(pgd, addr);
                 if (pud_none(*pud)) {
-                        addr += PUD_SIZE;
+                        addr = pud_addr_end(addr, end);
                         continue;
                 }
 
                 pmd = pmd_offset(pud, addr);
                 if (pmd_none(*pmd)) {
-                        addr += PMD_SIZE;
+                        addr = pmd_addr_end(addr, end);
                         continue;
                 }
 
                 pte = pte_offset_kernel(pmd, addr);
                 clear_pte_entry(kvm, pte, addr);
-                range = PAGE_SIZE;
+                next = addr + PAGE_SIZE;
 
                 /* If we emptied the pte, walk back up the ladder */
-                if (pte_empty(pte)) {
+                if (page_empty(pte)) {
                         clear_pmd_entry(kvm, pmd, addr);
-                        range = PMD_SIZE;
-                        if (pmd_empty(pmd)) {
+                        next = pmd_addr_end(addr, end);
+                        if (page_empty(pmd) && !page_empty(pud)) {
                                 clear_pud_entry(kvm, pud, addr);
-                                range = PUD_SIZE;
+                                next = pud_addr_end(addr, end);
                         }
                 }
 
-                addr += range;
+                addr = next;
         }
 }
 
diff --git a/arch/arm/mach-at91/at91sam9x5.c b/arch/arm/mach-at91/at91sam9x5.c
index 2abee6626aac..916e5a142917 100644
--- a/arch/arm/mach-at91/at91sam9x5.c
+++ b/arch/arm/mach-at91/at91sam9x5.c
@@ -227,6 +227,8 @@ static struct clk_lookup periph_clocks_lookups[] = {
         CLKDEV_CON_DEV_ID("usart", "f8020000.serial", &usart1_clk),
         CLKDEV_CON_DEV_ID("usart", "f8024000.serial", &usart2_clk),
         CLKDEV_CON_DEV_ID("usart", "f8028000.serial", &usart3_clk),
+        CLKDEV_CON_DEV_ID("usart", "f8040000.serial", &uart0_clk),
+        CLKDEV_CON_DEV_ID("usart", "f8044000.serial", &uart1_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("mci_clk", "f0008000.mmc", &mmc0_clk),
diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c
index dff4ddc5ef81..139e42da25f0 100644
--- a/arch/arm/mach-davinci/board-dm355-leopard.c
+++ b/arch/arm/mach-davinci/board-dm355-leopard.c
@@ -75,6 +75,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
         .parts                  = davinci_nand_partitions,
         .nr_parts               = ARRAY_SIZE(davinci_nand_partitions),
         .ecc_mode               = NAND_ECC_HW_SYNDROME,
+        .ecc_bits               = 4,
         .bbt_options            = NAND_BBT_USE_FLASH,
 };
 
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index a33686a6fbb2..fa4bfaf952d8 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -153,6 +153,7 @@ static struct davinci_nand_pdata davinci_evm_nandflash_data = {
         .parts          = davinci_evm_nandflash_partition,
         .nr_parts       = ARRAY_SIZE(davinci_evm_nandflash_partition),
         .ecc_mode       = NAND_ECC_HW,
+        .ecc_bits       = 1,
         .bbt_options    = NAND_BBT_USE_FLASH,
         .timing         = &davinci_evm_nandflash_timing,
 };
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index fbb8e5ab1dc1..0c005e876cac 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -90,6 +90,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
         .parts                  = davinci_nand_partitions,
         .nr_parts               = ARRAY_SIZE(davinci_nand_partitions),
         .ecc_mode               = NAND_ECC_HW,
+        .ecc_bits               = 1,
         .options                = 0,
 };
 
diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c
index 2bc112adf565..808233b60e3d 100644
--- a/arch/arm/mach-davinci/board-neuros-osd2.c
+++ b/arch/arm/mach-davinci/board-neuros-osd2.c
@@ -88,6 +88,7 @@ static struct davinci_nand_pdata davinci_ntosd2_nandflash_data = {
         .parts          = davinci_ntosd2_nandflash_partition,
         .nr_parts       = ARRAY_SIZE(davinci_ntosd2_nandflash_partition),
         .ecc_mode       = NAND_ECC_HW,
+        .ecc_bits       = 1,
         .bbt_options    = NAND_BBT_USE_FLASH,
 };
 
diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c
index f6eeb87e4e95..827d15009a86 100644
--- a/arch/arm/mach-omap2/board-n8x0.c
+++ b/arch/arm/mach-omap2/board-n8x0.c
@@ -122,11 +122,7 @@ static struct musb_hdrc_config musb_config = {
 };
 
 static struct musb_hdrc_platform_data tusb_data = {
-#ifdef CONFIG_USB_GADGET_MUSB_HDRC
         .mode           = MUSB_OTG,
-#else
-        .mode           = MUSB_HOST,
-#endif
         .set_power      = tusb_set_power,
         .min_power      = 25,   /* x2 = 50 mA drawn from VBUS as peripheral */
         .power          = 100,  /* Max 100 mA VBUS for host mode */
diff --git a/arch/arm/mach-omap2/board-rx51.c b/arch/arm/mach-omap2/board-rx51.c
index d2ea68ea678a..7735105561d8 100644
--- a/arch/arm/mach-omap2/board-rx51.c
+++ b/arch/arm/mach-omap2/board-rx51.c
@@ -85,7 +85,7 @@ static struct omap_board_mux board_mux[] __initdata = {
 
 static struct omap_musb_board_data musb_board_data = {
         .interface_type         = MUSB_INTERFACE_ULPI,
-        .mode                   = MUSB_PERIPHERAL,
+        .mode                   = MUSB_OTG,
         .power                  = 0,
 };
 
diff --git a/arch/arm/mach-omap2/usb-musb.c b/arch/arm/mach-omap2/usb-musb.c
index 8c4de2708cf2..bc897231bd10 100644
--- a/arch/arm/mach-omap2/usb-musb.c
+++ b/arch/arm/mach-omap2/usb-musb.c
@@ -38,11 +38,8 @@ static struct musb_hdrc_config musb_config = {
 };
 
 static struct musb_hdrc_platform_data musb_plat = {
-#ifdef CONFIG_USB_GADGET_MUSB_HDRC
         .mode           = MUSB_OTG,
-#else
-        .mode           = MUSB_HOST,
-#endif
+
         /* .clock is set dynamically */
         .config         = &musb_config,
 
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index db5c2cab8fda..cd2c88e7a8f7 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -809,15 +809,18 @@ config KUSER_HELPERS
           the CPU type fitted to the system.  This permits binaries to be
           run on ARMv4 through to ARMv7 without modification.
 
+          See Documentation/arm/kernel_user_helpers.txt for details.
+
           However, the fixed address nature of these helpers can be used
           by ROP (return orientated programming) authors when creating
           exploits.
 
           If all of the binaries and libraries which run on your platform
           are built specifically for your platform, and make no use of
-          these helpers, then you can turn this option off.  However,
-          when such an binary or library is run, it will receive a SIGILL
-          signal, which will terminate the program.
+          these helpers, then you can turn this option off to hinder
+          such exploits. However, in that case, if a binary or library
+          relying on those helpers is run, it will receive a SIGILL signal,
+          which will terminate the program.
 
           Say N here only if you are absolutely certain that you do not
           need these helpers; otherwise, the safe option is to say Y.
diff --git a/arch/arm/plat-samsung/init.c b/arch/arm/plat-samsung/init.c
index 3e5c4619caa5..50a3ea0037db 100644
--- a/arch/arm/plat-samsung/init.c
+++ b/arch/arm/plat-samsung/init.c
@@ -55,12 +55,13 @@ void __init s3c_init_cpu(unsigned long idcode,
 
         printk("CPU %s (id 0x%08lx)\n", cpu->name, idcode);
 
-        if (cpu->map_io == NULL || cpu->init == NULL) {
+        if (cpu->init == NULL) {
                 printk(KERN_ERR "CPU %s support not enabled\n", cpu->name);
                 panic("Unsupported Samsung CPU");
         }
 
-        cpu->map_io();
+        if (cpu->map_io)
+                cpu->map_io();
 }
 
 /* s3c24xx_init_clocks
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index c9770ba5c7df..8a6295c86209 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -170,6 +170,7 @@ static void __init xen_percpu_init(void *unused)
         per_cpu(xen_vcpu, cpu) = vcpup;
 
         enable_percpu_irq(xen_events_irq, 0);
+        put_cpu();
 }
 
 static void xen_restart(enum reboot_mode reboot_mode, const char *cmd)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index c92de4163eba..b25763bc0ec4 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -42,14 +42,15 @@
 #define TPIDR_EL1       18      /* Thread ID, Privileged */
 #define AMAIR_EL1       19      /* Aux Memory Attribute Indirection Register */
 #define CNTKCTL_EL1     20      /* Timer Control Register (EL1) */
+#define PAR_EL1         21      /* Physical Address Register */
 /* 32bit specific registers. Keep them at the end of the range */
-#define DACR32_EL2      21      /* Domain Access Control Register */
-#define IFSR32_EL2      22      /* Instruction Fault Status Register */
-#define FPEXC32_EL2     23      /* Floating-Point Exception Control Register */
-#define DBGVCR32_EL2    24      /* Debug Vector Catch Register */
-#define TEECR32_EL1     25      /* ThumbEE Configuration Register */
-#define TEEHBR32_EL1    26      /* ThumbEE Handler Base Register */
-#define NR_SYS_REGS     27
+#define DACR32_EL2      22      /* Domain Access Control Register */
+#define IFSR32_EL2      23      /* Instruction Fault Status Register */
+#define FPEXC32_EL2     24      /* Floating-Point Exception Control Register */
+#define DBGVCR32_EL2    25      /* Debug Vector Catch Register */
+#define TEECR32_EL1     26      /* ThumbEE Configuration Register */
+#define TEEHBR32_EL1    27      /* ThumbEE Handler Base Register */
+#define NR_SYS_REGS     28
 
 /* 32bit mapping */
 #define c0_MPIDR        (MPIDR_EL1 * 2) /* MultiProcessor ID Register */
@@ -69,6 +70,8 @@
 #define c5_AIFSR        (AFSR1_EL1 * 2) /* Auxiliary Instr Fault Status R */
 #define c6_DFAR         (FAR_EL1 * 2)   /* Data Fault Address Register */
 #define c6_IFAR         (c6_DFAR + 1)   /* Instruction Fault Address Register */
+#define c7_PAR          (PAR_EL1 * 2)   /* Physical Address Register */
+#define c7_PAR_high     (c7_PAR + 1)    /* PAR top 32 bits */
 #define c10_PRRR        (MAIR_EL1 * 2)  /* Primary Region Remap Register */
 #define c10_NMRR        (c10_PRRR + 1)  /* Normal Memory Remap Register */
 #define c12_VBAR        (VBAR_EL1 * 2)  /* Vector Base Address Register */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 644d73956864..0859a4ddd1e7 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -129,7 +129,7 @@ struct kvm_vcpu_arch {
         struct kvm_mmu_memory_cache mmu_page_cache;
 
         /* Target CPU and feature flags */
-        u32 target;
+        int target;
         DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);
 
         /* Detect first run of a vcpu */
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 46b3beb4b773..717031a762c2 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -35,6 +35,7 @@ struct mmu_gather {
         struct mm_struct        *mm;
         unsigned int            fullmm;
         struct vm_area_struct   *vma;
+        unsigned long           start, end;
         unsigned long           range_start;
         unsigned long           range_end;
         unsigned int            nr;
@@ -97,10 +98,12 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
         tlb->mm = mm;
-        tlb->fullmm = fullmm;
+        tlb->fullmm = !(start | (end+1));
+        tlb->start = start;
+        tlb->end = end;
         tlb->vma = NULL;
         tlb->max = ARRAY_SIZE(tlb->local);
         tlb->pages = tlb->local;
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 9ba33c40cdf8..12e6ccb88691 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -107,7 +107,12 @@ armpmu_map_cache_event(const unsigned (*cache_map)
 static int
 armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 {
-        int mapping = (*event_map)[config];
+        int mapping;
+
+        if (config >= PERF_COUNT_HW_MAX)
+                return -EINVAL;
+
+        mapping = (*event_map)[config];
         return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
 }
 
@@ -317,6 +322,9 @@ validate_event(struct pmu_hw_events *hw_events,
         struct hw_perf_event fake_event = event->hw;
         struct pmu *leader_pmu = event->group_leader->pmu;
 
+        if (is_software_event(event))
+                return 1;
+
         if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
                 return 1;
 
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index ff985e3d8b72..1ac0bbbdddb2 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -214,6 +214,7 @@ __kvm_hyp_code_start:
         mrs     x21,    tpidr_el1
         mrs     x22,    amair_el1
         mrs     x23,    cntkctl_el1
+        mrs     x24,    par_el1
 
         stp     x4, x5, [x3]
         stp     x6, x7, [x3, #16]
@@ -225,6 +226,7 @@ __kvm_hyp_code_start:
         stp     x18, x19, [x3, #112]
         stp     x20, x21, [x3, #128]
         stp     x22, x23, [x3, #144]
+        str     x24, [x3, #160]
 .endm
 
 .macro restore_sysregs
@@ -243,6 +245,7 @@ __kvm_hyp_code_start:
         ldp     x18, x19, [x3, #112]
         ldp     x20, x21, [x3, #128]
         ldp     x22, x23, [x3, #144]
+        ldr     x24, [x3, #160]
 
         msr     vmpidr_el2,     x4
         msr     csselr_el1,     x5
@@ -264,6 +267,7 @@ __kvm_hyp_code_start:
         msr     tpidr_el1,      x21
         msr     amair_el1,      x22
         msr     cntkctl_el1,    x23
+        msr     par_el1,        x24
 .endm
 
 .macro skip_32bit_state tmp, target
@@ -600,6 +604,8 @@ END(__kvm_vcpu_run)
 
 // void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 ENTRY(__kvm_tlb_flush_vmid_ipa)
+        dsb     ishst
+
         kern_hyp_va     x0
         ldr     x2, [x0, #KVM_VTTBR]
         msr     vttbr_el2, x2
@@ -621,6 +627,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 ENDPROC(__kvm_tlb_flush_vmid_ipa)
 
 ENTRY(__kvm_flush_vm_context)
+        dsb     ishst
         tlbi    alle1is
         ic      ialluis
         dsb     sy
@@ -753,6 +760,10 @@ el1_trap:
          */
         tbnz    x1, #7, 1f      // S1PTW is set
 
+        /* Preserve PAR_EL1 */
+        mrs     x3, par_el1
+        push    x3, xzr
+
         /*
          * Permission fault, HPFAR_EL2 is invalid.
          * Resolve the IPA the hard way using the guest VA.
@@ -766,6 +777,8 @@ el1_trap:
 
         /* Read result */
         mrs     x3, par_el1
+        pop     x0, xzr                 // Restore PAR_EL1 from the stack
+        msr     par_el1, x0
         tbnz    x3, #0, 3f              // Bail out if we failed the translation
         ubfx    x3, x3, #12, #36        // Extract IPA
         lsl     x3, x3, #4              // and present it like HPFAR
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 94923609753b..02e9d09e1d80 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -211,6 +211,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
         /* FAR_EL1 */
         { Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000),
           NULL, reset_unknown, FAR_EL1 },
+        /* PAR_EL1 */
+        { Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000),
+          NULL, reset_unknown, PAR_EL1 },
 
         /* PMINTENSET_EL1 */
         { Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001),
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 33a97929d055..77d442ab28c8 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -158,6 +158,7 @@ source "kernel/Kconfig.hz"
 endmenu
 
 source "init/Kconfig"
+source "kernel/Kconfig.freezer"
 source "drivers/Kconfig"
 source "fs/Kconfig"
 
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index ef3a9de01954..bc5efc7c3f3f 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -22,7 +22,7 @@
  * unmapping a portion of the virtual address space, these hooks are called according to
  * the following template:
  *
- *      tlb <- tlb_gather_mmu(mm, full_mm_flush);       // start unmap for address space MM
+ *      tlb <- tlb_gather_mmu(mm, start, end);          // start unmap for address space MM
  *      {
  *        for each vma that needs a shootdown do {
  *          tlb_start_vma(tlb, vma);
@@ -58,6 +58,7 @@ struct mmu_gather {
         unsigned int            max;
         unsigned char           fullmm;         /* non-zero means full mm flush */
         unsigned char           need_flush;     /* really unmapped some PTEs? */
+        unsigned long           start, end;
         unsigned long           start_addr;
         unsigned long           end_addr;
         struct page             **pages;
@@ -155,13 +156,15 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
         tlb->mm = mm;
         tlb->max = ARRAY_SIZE(tlb->local);
         tlb->pages = tlb->local;
         tlb->nr = 0;
-        tlb->fullmm = full_mm_flush;
+        tlb->fullmm = !(start | (end+1));
+        tlb->start = start;
+        tlb->end = end;
         tlb->start_addr = ~0UL;
 }
 
diff --git a/arch/m68k/emu/natfeat.c b/arch/m68k/emu/natfeat.c
index 2291a7d69d49..fa277aecfb78 100644
--- a/arch/m68k/emu/natfeat.c
+++ b/arch/m68k/emu/natfeat.c
@@ -18,9 +18,11 @@
 #include <asm/machdep.h>
 #include <asm/natfeat.h>
 
+extern long nf_get_id2(const char *feature_name);
+
 asm("\n"
-"       .global nf_get_id,nf_call\n"
-"nf_get_id:\n"
+"       .global nf_get_id2,nf_call\n"
+"nf_get_id2:\n"
 "       .short  0x7300\n"
 "       rts\n"
 "nf_call:\n"
@@ -29,12 +31,25 @@ asm("\n"
 "1:     moveq.l #0,%d0\n"
 "       rts\n"
 "       .section __ex_table,\"a\"\n"
-"       .long   nf_get_id,1b\n"
+"       .long   nf_get_id2,1b\n"
 "       .long   nf_call,1b\n"
 "       .previous");
-EXPORT_SYMBOL_GPL(nf_get_id);
 EXPORT_SYMBOL_GPL(nf_call);
 
+long nf_get_id(const char *feature_name)
+{
+        /* feature_name may be in vmalloc()ed memory, so make a copy */
+        char name_copy[32];
+        size_t n;
+
+        n = strlcpy(name_copy, feature_name, sizeof(name_copy));
+        if (n >= sizeof(name_copy))
+                return 0;
+
+        return nf_get_id2(name_copy);
+}
+EXPORT_SYMBOL_GPL(nf_get_id);
+
 void nfprint(const char *fmt, ...)
 {
         static char buf[256];
diff --git a/arch/m68k/include/asm/div64.h b/arch/m68k/include/asm/div64.h
index 444ea8a09e9f..ef881cfbbca9 100644
--- a/arch/m68k/include/asm/div64.h
+++ b/arch/m68k/include/asm/div64.h
@@ -15,16 +15,17 @@
                 unsigned long long n64;                         \
         } __n;                                                  \
         unsigned long __rem, __upper;                           \
+        unsigned long __base = (base);                          \
                                                                 \
         __n.n64 = (n);                                          \
         if ((__upper = __n.n32[0])) {                           \
                 asm ("divul.l %2,%1:%0"                         \
-                        : "=d" (__n.n32[0]), "=d" (__upper)     \
-                        : "d" (base), "0" (__n.n32[0]));        \
+                     : "=d" (__n.n32[0]), "=d" (__upper)        \
+                     : "d" (__base), "0" (__n.n32[0]));         \
         }                                                       \
         asm ("divu.l %2,%1:%0"                                  \
-                : "=d" (__n.n32[1]), "=d" (__rem)               \
-                : "d" (base), "1" (__upper), "0" (__n.n32[1])); \
+             : "=d" (__n.n32[1]), "=d" (__rem)                  \
+             : "d" (__base), "1" (__upper), "0" (__n.n32[1]));  \
         (n) = __n.n64;                                          \
         __rem;                                                  \
 })
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index d22a4ecffff4..4fab52294d98 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -28,7 +28,7 @@ config MICROBLAZE
         select GENERIC_CLOCKEVENTS
         select GENERIC_IDLE_POLL_SETUP
         select MODULES_USE_ELF_RELA
-        select CLONE_BACKWARDS
+        select CLONE_BACKWARDS3
 
 config SWAP
         def_bool n
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index e773659ccf9f..46048d24328c 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -803,6 +803,32 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
                                 dec_insn.next_pc_inc;
                 return 1;
                 break;
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+        case lwc2_op: /* This is bbit0 on Octeon */
+                if ((regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt)) == 0)
+                        *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2);
+                else
+                        *contpc = regs->cp0_epc + 8;
+                return 1;
+        case ldc2_op: /* This is bbit032 on Octeon */
+                if ((regs->regs[insn.i_format.rs] & (1ull<<(insn.i_format.rt + 32))) == 0)
+                        *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2);
+                else
+                        *contpc = regs->cp0_epc + 8;
+                return 1;
+        case swc2_op: /* This is bbit1 on Octeon */
+                if (regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt))
+                        *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2);
+                else
+                        *contpc = regs->cp0_epc + 8;
+                return 1;
+        case sdc2_op: /* This is bbit132 on Octeon */
+                if (regs->regs[insn.i_format.rs] & (1ull<<(insn.i_format.rt + 32)))
+                        *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2);
+                else
+                        *contpc = regs->cp0_epc + 8;
+                return 1;
+#endif
         case cop0_op:
         case cop1_op:
         case cop2_op:
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 99dbab1c59ac..d60bf98fa5cf 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -55,6 +55,7 @@ config GENERIC_CSUM
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
 
 menu "Processor type and features"
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index dbd9d3c991e8..9cf59816d3e9 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -979,6 +979,7 @@ config RELOCATABLE
           must live at a different physical address than the primary
           kernel.
 
+# This value must have zeroes in the bottom 60 bits otherwise lots will break
 config PAGE_OFFSET
         hex
         default "0xc000000000000000"
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 988c812aab5b..b9f426212d3a 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -211,9 +211,19 @@ extern long long virt_phys_offset;
 #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + VIRT_PHYS_OFFSET))
 #define __pa(x) ((unsigned long)(x) - VIRT_PHYS_OFFSET)
 #else
+#ifdef CONFIG_PPC64
+/*
+ * gcc miscompiles (unsigned long)(&static_var) - PAGE_OFFSET
+ * with -mcmodel=medium, so we use & and | instead of - and + on 64-bit.
+ */
+#define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) | PAGE_OFFSET))
+#define __pa(x) ((unsigned long)(x) & 0x0fffffffffffffffUL)
+
+#else /* 32-bit, non book E */
 #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + PAGE_OFFSET - MEMORY_START))
 #define __pa(x) ((unsigned long)(x) - PAGE_OFFSET + MEMORY_START)
 #endif
+#endif
 
 /*
  * Unfortunately the PLT is in the BSS in the PPC32 ELF ABI,
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index d92f3871e9cf..e2a0a162299b 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -35,7 +35,13 @@
 #include <asm/vdso_datapage.h>
 #include <asm/vio.h>
 #include <asm/mmu.h>
+#include <asm/machdep.h>
 
+
+/*
+ * This isn't a module but we expose that to userspace
+ * via /proc so leave the definitions here
+ */
 #define MODULE_VERS "1.9"
 #define MODULE_NAME "lparcfg"
 
@@ -418,7 +424,8 @@ static void parse_em_data(struct seq_file *m)
 {
         unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
 
-        if (plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS)
+        if (firmware_has_feature(FW_FEATURE_LPAR) &&
+            plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS)
                 seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]);
 }
 
@@ -677,7 +684,6 @@ static int lparcfg_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations lparcfg_fops = {
-        .owner          = THIS_MODULE,
         .read           = seq_read,
         .write          = lparcfg_write,
         .open           = lparcfg_open,
@@ -699,14 +705,4 @@ static int __init lparcfg_init(void)
         }
         return 0;
 }
-
-static void __exit lparcfg_cleanup(void)
-{
-        remove_proc_subtree("powerpc/lparcfg", NULL);
-}
-
-module_init(lparcfg_init);
-module_exit(lparcfg_cleanup);
-MODULE_DESCRIPTION("Interface for LPAR configuration data");
-MODULE_AUTHOR("Dave Engebretsen");
-MODULE_LICENSE("GPL");
+machine_device_initcall(pseries, lparcfg_init);
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index b75d7d686684..6d6d92b4ea11 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -32,6 +32,7 @@ struct mmu_gather {
         struct mm_struct *mm;
         struct mmu_table_batch *batch;
         unsigned int fullmm;
+        unsigned long start, end;
 };
 
 struct mmu_table_batch {
@@ -48,10 +49,13 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
 static inline void tlb_gather_mmu(struct mmu_gather *tlb,
                                   struct mm_struct *mm,
-                                  unsigned int full_mm_flush)
+                                  unsigned long start,
+                                  unsigned long end)
 {
         tlb->mm = mm;
-        tlb->fullmm = full_mm_flush;
+        tlb->start = start;
+        tlb->end = end;
+        tlb->fullmm = !(start | (end+1));
         tlb->batch = NULL;
         if (tlb->fullmm)
                 __tlb_flush_mm(mm);
diff --git a/arch/score/Kconfig b/arch/score/Kconfig
index c8def8bc9020..5fc237581caf 100644
--- a/arch/score/Kconfig
+++ b/arch/score/Kconfig
@@ -87,6 +87,8 @@ config STACKTRACE_SUPPORT
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 config MMU
         def_bool y
 
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index e61d43d9f689..362192ed12fe 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -36,10 +36,12 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
         tlb->mm = mm;
-        tlb->fullmm = full_mm_flush;
+        tlb->start = start;
+        tlb->end = end;
+        tlb->fullmm = !(start | (end+1));
 
         init_tlb_gather(tlb);
 }
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 4febacd1a8a1..29b0301c18aa 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -45,10 +45,12 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
         tlb->mm = mm;
-        tlb->fullmm = full_mm_flush;
+        tlb->start = start;
+        tlb->end = end;
+        tlb->fullmm = !(start | (end+1));
 
         init_tlb_gather(tlb);
 }
diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h
index 653668d140f9..4a8cb8d7cbd5 100644
--- a/arch/x86/include/asm/bootparam_utils.h
+++ b/arch/x86/include/asm/bootparam_utils.h
@@ -35,9 +35,9 @@ static void sanitize_boot_params(struct boot_params *boot_params)
          */
         if (boot_params->sentinel) {
                 /* fields in boot_params are left uninitialized, clear them */
-                memset(&boot_params->olpc_ofw_header, 0,
+                memset(&boot_params->ext_ramdisk_image, 0,
                        (char *)&boot_params->efi_info -
-                        (char *)&boot_params->olpc_ofw_header);
+                        (char *)&boot_params->ext_ramdisk_image);
                 memset(&boot_params->kbd_status, 0,
                        (char *)&boot_params->hdr -
                        (char *)&boot_params->kbd_status);
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 50e5c58ced23..4c019179a57d 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -59,7 +59,7 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table,
 
 extern int __apply_microcode_amd(struct microcode_amd *mc_amd);
 extern int apply_microcode_amd(int cpu);
-extern enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size);
+extern enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
 
 #ifdef CONFIG_MICROCODE_AMD_EARLY
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index f2b489cf1602..3bf2dd0cf61f 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -55,9 +55,53 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
 #endif
 
+#ifdef CONFIG_MEM_SOFT_DIRTY
+
+/*
+ * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE, _PAGE_BIT_SOFT_DIRTY and
+ * _PAGE_BIT_PROTNONE are taken, split up the 28 bits of offset
+ * into this range.
+ */
+#define PTE_FILE_MAX_BITS       28
+#define PTE_FILE_SHIFT1         (_PAGE_BIT_PRESENT + 1)
+#define PTE_FILE_SHIFT2         (_PAGE_BIT_FILE + 1)
+#define PTE_FILE_SHIFT3         (_PAGE_BIT_PROTNONE + 1)
+#define PTE_FILE_SHIFT4         (_PAGE_BIT_SOFT_DIRTY + 1)
+#define PTE_FILE_BITS1          (PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1)
+#define PTE_FILE_BITS2          (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
+#define PTE_FILE_BITS3          (PTE_FILE_SHIFT4 - PTE_FILE_SHIFT3 - 1)
+
+#define pte_to_pgoff(pte)                                               \
+        ((((pte).pte_low >> (PTE_FILE_SHIFT1))                          \
+          & ((1U << PTE_FILE_BITS1) - 1)))                              \
+        + ((((pte).pte_low >> (PTE_FILE_SHIFT2))                        \
+            & ((1U << PTE_FILE_BITS2) - 1))                             \
+           << (PTE_FILE_BITS1))                                         \
+        + ((((pte).pte_low >> (PTE_FILE_SHIFT3))                        \
+            & ((1U << PTE_FILE_BITS3) - 1))                             \
+           << (PTE_FILE_BITS1 + PTE_FILE_BITS2))                        \
+        + ((((pte).pte_low >> (PTE_FILE_SHIFT4)))                       \
+            << (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3))
+
+#define pgoff_to_pte(off)                                               \
+        ((pte_t) { .pte_low =                                           \
+         ((((off)) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1)  \
+         + ((((off) >> PTE_FILE_BITS1)                                  \
+             & ((1U << PTE_FILE_BITS2) - 1))                            \
+            << PTE_FILE_SHIFT2)                                         \
+         + ((((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2))               \
+             & ((1U << PTE_FILE_BITS3) - 1))                            \
+            << PTE_FILE_SHIFT3)                                         \
+         + ((((off) >>                                                  \
+              (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3)))      \
+            << PTE_FILE_SHIFT4)                                         \
+         + _PAGE_FILE })
+
+#else /* CONFIG_MEM_SOFT_DIRTY */
+
 /*
  * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken,
- * split up the 29 bits of offset into this range:
+ * split up the 29 bits of offset into this range.
  */
 #define PTE_FILE_MAX_BITS       29
 #define PTE_FILE_SHIFT1         (_PAGE_BIT_PRESENT + 1)
@@ -88,6 +132,8 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
             << PTE_FILE_SHIFT3)                                         \
          + _PAGE_FILE })
 
+#endif /* CONFIG_MEM_SOFT_DIRTY */
+
 /* Encode and de-code a swap entry */
 #if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
 #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 4cc9f2b7cdc3..81bb91b49a88 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -179,6 +179,9 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
 /*
  * Bits 0, 6 and 7 are taken in the low part of the pte,
  * put the 32 bits of offset into the high part.
+ *
+ * For soft-dirty tracking 11 bit is taken from
+ * the low part of pte as well.
  */
 #define pte_to_pgoff(pte) ((pte).pte_high)
 #define pgoff_to_pte(off)                                               \
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 7dc305a46058..1c00631164c2 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -314,6 +314,36 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
         return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
 }
 
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+        return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+        return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+        return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline pte_t pte_file_clear_soft_dirty(pte_t pte)
+{
+        return pte_clear_flags(pte, _PAGE_SOFT_DIRTY);
+}
+
+static inline pte_t pte_file_mksoft_dirty(pte_t pte)
+{
+        return pte_set_flags(pte, _PAGE_SOFT_DIRTY);
+}
+
+static inline int pte_file_soft_dirty(pte_t pte)
+{
+        return pte_flags(pte) & _PAGE_SOFT_DIRTY;
+}
+
 /*
  * Mask out unsupported bits in a present pgprot.  Non-present pgprots
  * can use those bits for other purposes, so leave them be.
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index c98ac63aae48..f4843e031131 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -61,12 +61,27 @@
  * they do not conflict with each other.
  */
 
+#define _PAGE_BIT_SOFT_DIRTY    _PAGE_BIT_HIDDEN
+
 #ifdef CONFIG_MEM_SOFT_DIRTY
-#define _PAGE_SOFT_DIRTY        (_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN)
+#define _PAGE_SOFT_DIRTY        (_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY)
 #else
 #define _PAGE_SOFT_DIRTY        (_AT(pteval_t, 0))
 #endif
 
+/*
+ * Tracking soft dirty bit when a page goes to a swap is tricky.
+ * We need a bit which can be stored in pte _and_ not conflict
+ * with swap entry format. On x86 bits 6 and 7 are *not* involved
+ * into swap entry computation, but bit 6 is used for nonlinear
+ * file mapping, so we borrow bit 7 for soft dirty tracking.
+ */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _PAGE_SWP_SOFT_DIRTY    _PAGE_PSE
+#else
+#define _PAGE_SWP_SOFT_DIRTY    (_AT(pteval_t, 0))
+#endif
+
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX        (_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #else
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 33692eaabab5..e3ddd7db723f 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -233,8 +233,4 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 #define arch_read_relax(lock)   cpu_relax()
 #define arch_write_relax(lock)  cpu_relax()
 
-/* The {read|write|spin}_lock() on x86 are full memory barriers. */
-static inline void smp_mb__after_lock(void) { }
-#define ARCH_HAS_SMP_MB_AFTER_LOCK
-
 #endif /* _ASM_X86_SPINLOCK_H */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f654ecefea5b..08a089043ccf 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -512,7 +512,7 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 
 static const int amd_erratum_383[];
 static const int amd_erratum_400[];
-static bool cpu_has_amd_erratum(const int *erratum);
+static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
 
 static void init_amd(struct cpuinfo_x86 *c)
 {
@@ -729,11 +729,11 @@ static void init_amd(struct cpuinfo_x86 *c)
                 value &= ~(1ULL << 24);
                 wrmsrl_safe(MSR_AMD64_BU_CFG2, value);
 
-                if (cpu_has_amd_erratum(amd_erratum_383))
+                if (cpu_has_amd_erratum(c, amd_erratum_383))
                         set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
         }
 
-        if (cpu_has_amd_erratum(amd_erratum_400))
+        if (cpu_has_amd_erratum(c, amd_erratum_400))
                 set_cpu_bug(c, X86_BUG_AMD_APIC_C1E);
 
         rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
@@ -878,23 +878,13 @@ static const int amd_erratum_400[] =
 static const int amd_erratum_383[] =
         AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
 
-static bool cpu_has_amd_erratum(const int *erratum)
+
+static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 {
-        struct cpuinfo_x86 *cpu = __this_cpu_ptr(&cpu_info);
         int osvw_id = *erratum++;
         u32 range;
         u32 ms;
 
-        /*
-         * If called early enough that current_cpu_data hasn't been initialized
-         * yet, fall back to boot_cpu_data.
-         */
-        if (cpu->x86 == 0)
-                cpu = &boot_cpu_data;
-
-        if (cpu->x86_vendor != X86_VENDOR_AMD)
-                return false;
-
         if (osvw_id >= 0 && osvw_id < 65536 &&
             cpu_has(cpu, X86_FEATURE_OSVW)) {
                 u64 osvw_len;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index fbc9210b45bc..a45d8d4ace10 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2270,6 +2270,7 @@ __init int intel_pmu_init(void)
         case 70:
         case 71:
         case 63:
+        case 69:
                 x86_pmu.late_ack = true;
                 memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
                 memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index e9696d8269ba..34c11ae9bda3 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -352,8 +352,8 @@ static struct uncore_event_desc snbep_uncore_imc_events[] = {
 static struct uncore_event_desc snbep_uncore_qpi_events[] = {
         INTEL_UNCORE_EVENT_DESC(clockticks,       "event=0x14"),
         INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
-        INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x02,umask=0x08"),
-        INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x03,umask=0x04"),
+        INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x102,umask=0x08"),
+        INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x103,umask=0x04"),
         { /* end: all zeroes */ },
 };
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 7a0adb7ee433..7123b5df479d 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -145,10 +145,9 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
         return 0;
 }
 
-static unsigned int verify_patch_size(int cpu, u32 patch_size,
+static unsigned int verify_patch_size(u8 family, u32 patch_size,
                                       unsigned int size)
 {
-        struct cpuinfo_x86 *c = &cpu_data(cpu);
         u32 max_size;
 
 #define F1XH_MPB_MAX_SIZE 2048
@@ -156,7 +155,7 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size,
 #define F15H_MPB_MAX_SIZE 4096
 #define F16H_MPB_MAX_SIZE 3458
 
-        switch (c->x86) {
+        switch (family) {
         case 0x14:
                 max_size = F14H_MPB_MAX_SIZE;
                 break;
@@ -277,9 +276,8 @@ static void cleanup(void)
  * driver cannot continue functioning normally. In such cases, we tear
  * down everything we've used up so far and exit.
  */
-static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
+static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover)
 {
-        struct cpuinfo_x86 *c = &cpu_data(cpu);
         struct microcode_header_amd *mc_hdr;
         struct ucode_patch *patch;
         unsigned int patch_size, crnt_size, ret;
@@ -299,7 +297,7 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
 
         /* check if patch is for the current family */
         proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff);
-        if (proc_fam != c->x86)
+        if (proc_fam != family)
                 return crnt_size;
 
         if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
@@ -308,7 +306,7 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
                 return crnt_size;
         }
 
-        ret = verify_patch_size(cpu, patch_size, leftover);
+        ret = verify_patch_size(family, patch_size, leftover);
         if (!ret) {
                 pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id);
                 return crnt_size;
@@ -339,7 +337,8 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
         return crnt_size;
 }
 
-static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t size)
+static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
+                                             size_t size)
 {
         enum ucode_state ret = UCODE_ERROR;
         unsigned int leftover;
@@ -362,7 +361,7 @@ static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t siz
         }
 
         while (leftover) {
-                crnt_size = verify_and_add_patch(cpu, fw, leftover);
+                crnt_size = verify_and_add_patch(family, fw, leftover);
                 if (crnt_size < 0)
                         return ret;
 
@@ -373,22 +372,22 @@ static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t siz
         return UCODE_OK;
 }
 
-enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size)
+enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
 {
         enum ucode_state ret;
 
         /* free old equiv table */
         free_equiv_cpu_table();
 
-        ret = __load_microcode_amd(cpu, data, size);
+        ret = __load_microcode_amd(family, data, size);
 
         if (ret != UCODE_OK)
                 cleanup();
 
 #if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32)
         /* save BSP's matching patch for early load */
-        if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) {
-                struct ucode_patch *p = find_patch(cpu);
+        if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) {
+                struct ucode_patch *p = find_patch(smp_processor_id());
                 if (p) {
                         memset(amd_bsp_mpb, 0, MPB_MAX_SIZE);
                         memcpy(amd_bsp_mpb, p->data, min_t(u32, ksize(p->data),
@@ -441,7 +440,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
                 goto fw_release;
         }
 
-        ret = load_microcode_amd(cpu, fw->data, fw->size);
+        ret = load_microcode_amd(c->x86, fw->data, fw->size);
 
  fw_release:
         release_firmware(fw);
diff --git a/arch/x86/kernel/microcode_amd_early.c b/arch/x86/kernel/microcode_amd_early.c
index 1d14ffee5749..6073104ccaa3 100644
--- a/arch/x86/kernel/microcode_amd_early.c
+++ b/arch/x86/kernel/microcode_amd_early.c
@@ -238,25 +238,17 @@ static void __init collect_cpu_sig_on_bsp(void *arg)
         uci->cpu_sig.sig = cpuid_eax(0x00000001);
 }
 #else
-static void collect_cpu_info_amd_early(struct cpuinfo_x86 *c,
-                                                 struct ucode_cpu_info *uci)
+void load_ucode_amd_ap(void)
 {
+        unsigned int cpu = smp_processor_id();
+        struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
         u32 rev, eax;
 
         rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax);
         eax = cpuid_eax(0x00000001);
 
-        uci->cpu_sig.sig = eax;
         uci->cpu_sig.rev = rev;
-        c->microcode = rev;
-        c->x86 = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
-}
-
-void load_ucode_amd_ap(void)
-{
-        unsigned int cpu = smp_processor_id();
-
-        collect_cpu_info_amd_early(&cpu_data(cpu), ucode_cpu_info + cpu);
+        uci->cpu_sig.sig = eax;
 
         if (cpu && !ucode_loaded) {
                 void *ucode;
@@ -265,8 +257,10 @@ void load_ucode_amd_ap(void)
                         return;
 
                 ucode = (void *)(initrd_start + ucode_offset);
-                if (load_microcode_amd(0, ucode, ucode_size) != UCODE_OK)
+                eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
+                if (load_microcode_amd(eax, ucode, ucode_size) != UCODE_OK)
                         return;
+
                 ucode_loaded = true;
         }
 
@@ -278,6 +272,8 @@ int __init save_microcode_in_initrd_amd(void)
 {
         enum ucode_state ret;
         void *ucode;
+        u32 eax;
+
 #ifdef CONFIG_X86_32
         unsigned int bsp = boot_cpu_data.cpu_index;
         struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
@@ -293,7 +289,10 @@ int __init save_microcode_in_initrd_amd(void)
                 return 0;
 
         ucode = (void *)(initrd_start + ucode_offset);
-        ret = load_microcode_amd(0, ucode, ucode_size);
+        eax   = cpuid_eax(0x00000001);
+        eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
+
+        ret = load_microcode_amd(eax, ucode, ucode_size);
         if (ret != UCODE_OK)
                 return -EINVAL;
 
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index dbded5aedb81..30277e27431a 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin,
                                 *begin = new_begin;
                 }
         } else {
-                *begin = TASK_UNMAPPED_BASE;
+                *begin = current->mm->mmap_legacy_base;
                 *end = TASK_SIZE;
         }
 }
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 62c29a5bfe26..25e7e1372bb2 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -112,11 +112,13 @@ static unsigned long mmap_legacy_base(void)
  */
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
+        mm->mmap_legacy_base = mmap_legacy_base();
+        mm->mmap_base = mmap_base();
+
         if (mmap_is_legacy()) {
-                mm->mmap_base = mmap_legacy_base();
+                mm->mmap_base = mm->mmap_legacy_base;
                 mm->get_unmapped_area = arch_get_unmapped_area;
         } else {
-                mm->mmap_base = mmap_base();
                 mm->get_unmapped_area = arch_get_unmapped_area_topdown;
         }
 }
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 056d11faef21..8f3eea6b80c5 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -313,6 +313,17 @@ static void xen_align_and_add_e820_region(u64 start, u64 size, int type)
         e820_add_region(start, end - start, type);
 }
 
+void xen_ignore_unusable(struct e820entry *list, size_t map_size)
+{
+        struct e820entry *entry;
+        unsigned int i;
+
+        for (i = 0, entry = list; i < map_size; i++, entry++) {
+                if (entry->type == E820_UNUSABLE)
+                        entry->type = E820_RAM;
+        }
+}
+
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
  **/
@@ -353,6 +364,17 @@ char * __init xen_memory_setup(void)
         }
         BUG_ON(rc);
 
+        /*
+         * Xen won't allow a 1:1 mapping to be created to UNUSABLE
+         * regions, so if we're using the machine memory map leave the
+         * region as RAM as it is in the pseudo-physical map.
+         *
+         * UNUSABLE regions in domUs are not handled and will need
+         * a patch in the future.
+         */
+        if (xen_initial_domain())
+                xen_ignore_unusable(map, memmap.nr_entries);
+
         /* Make sure the Xen-supplied memory map is well-ordered. */
         sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries);
 
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index ca92754eb846..b81c88e51daa 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -694,8 +694,15 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
         int rc;
-        rc = native_cpu_up(cpu, tidle);
-        WARN_ON (xen_smp_intr_init(cpu));
+        /*
+         * xen_smp_intr_init() needs to run before native_cpu_up()
+         * so that IPI vectors are set up on the booting CPU before
+         * it is marked online in native_cpu_up().
+        */
+        rc = xen_smp_intr_init(cpu);
+        WARN_ON(rc);
+        if (!rc)
+                rc =  native_cpu_up(cpu, tidle);
         return rc;
 }