Merge branch 'core/urgent' into sched/core

Merge in asm goto fix, to be able to apply the asm/rmwcc.h fix.

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

29 files changed, 187 insertions, 110 deletions

diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index a37a50f575a2..db50b626be98 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -296,10 +296,15 @@ archprepare:
 # Convert bzImage to zImage
 bzImage: zImage
 
-zImage Image xipImage bootpImage uImage: vmlinux
+BOOT_TARGETS    = zImage Image xipImage bootpImage uImage
+INSTALL_TARGETS = zinstall uinstall install
+
+PHONY += bzImage $(BOOT_TARGETS) $(INSTALL_TARGETS)
+
+$(BOOT_TARGETS): vmlinux
         $(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
-zinstall uinstall install: vmlinux
+$(INSTALL_TARGETS):
         $(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@
 
 %.dtb: | scripts
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 84aa2caf07ed..ec2f8065f955 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -95,24 +95,24 @@ initrd:
         @test "$(INITRD)" != "" || \
         (echo You must specify INITRD; exit -1)
 
-install: $(obj)/Image
-        $(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+install:
+        $(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
         $(obj)/Image System.map "$(INSTALL_PATH)"
 
-zinstall: $(obj)/zImage
-        $(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+zinstall:
+        $(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
         $(obj)/zImage System.map "$(INSTALL_PATH)"
 
-uinstall: $(obj)/uImage
-        $(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+uinstall:
+        $(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
         $(obj)/uImage System.map "$(INSTALL_PATH)"
 
 zi:
-        $(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+        $(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
         $(obj)/zImage System.map "$(INSTALL_PATH)"
 
 i:
-        $(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+        $(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
         $(obj)/Image System.map "$(INSTALL_PATH)"
 
 subdir-     := bootp compressed dts
diff --git a/arch/arm/boot/install.sh b/arch/arm/boot/install.sh
index 06ea7d42ce8e..2a45092a40e3 100644
--- a/arch/arm/boot/install.sh
+++ b/arch/arm/boot/install.sh
@@ -20,6 +20,20 @@
 #   $4 - default install path (blank if root directory)
 #
 
+verify () {
+        if [ ! -f "$1" ]; then
+                echo ""                                                   1>&2
+                echo " *** Missing file: $1"                              1>&2
+                echo ' *** You need to run "make" before "make install".' 1>&2
+                echo ""                                                   1>&2
+                exit 1
+        fi
+}
+
+# Make sure the files actually exist
+verify "$2"
+verify "$3"
+
 # User may have a custom install script
 if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
 if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index bfc198c75913..863c892b4aaa 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -16,7 +16,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-        asm goto("1:\n\t"
+        asm_volatile_goto("1:\n\t"
                  JUMP_LABEL_NOP "\n\t"
                  ".pushsection __jump_table,  \"aw\"\n\t"
                  ".word 1b, %l[l_yes], %c0\n\t"
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 4d6d77ed9b9d..e194f957ca8c 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -22,7 +22,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-        asm goto("1:\tnop\n\t"
+        asm_volatile_goto("1:\tnop\n\t"
                 "nop\n\t"
                 ".pushsection __jump_table,  \"aw\"\n\t"
                 WORD_INSN " 1b, %l[l_yes], %0\n\t"
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index ae098c438f00..f016bb699b5f 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -19,7 +19,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-        asm goto("1:\n\t"
+        asm_volatile_goto("1:\n\t"
                  "nop\n\t"
                  ".pushsection __jump_table,  \"aw\"\n\t"
                  JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 57d286a78f86..c7cb8c232d2f 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -495,14 +495,15 @@ void __do_irq(struct pt_regs *regs)
 void do_IRQ(struct pt_regs *regs)
 {
         struct pt_regs *old_regs = set_irq_regs(regs);
-        struct thread_info *curtp, *irqtp;
+        struct thread_info *curtp, *irqtp, *sirqtp;
 
         /* Switch to the irq stack to handle this */
         curtp = current_thread_info();
         irqtp = hardirq_ctx[raw_smp_processor_id()];
+        sirqtp = softirq_ctx[raw_smp_processor_id()];
 
         /* Already there ? */
-        if (unlikely(curtp == irqtp)) {
+        if (unlikely(curtp == irqtp || curtp == sirqtp)) {
                 __do_irq(regs);
                 set_irq_regs(old_regs);
                 return;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 294b7af28cdd..c71103b8a748 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1066,7 +1066,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 BEGIN_FTR_SECTION
         mfspr   r8, SPRN_DSCR
         ld      r7, HSTATE_DSCR(r13)
-        std     r8, VCPU_DSCR(r7)
+        std     r8, VCPU_DSCR(r9)
         mtspr   SPRN_DSCR, r7
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 1c6a9d729df4..c65593abae8e 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -332,6 +332,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
         unsigned long hva;
         int pfnmap = 0;
         int tsize = BOOK3E_PAGESZ_4K;
+        int ret = 0;
+        unsigned long mmu_seq;
+        struct kvm *kvm = vcpu_e500->vcpu.kvm;
+
+        /* used to check for invalidations in progress */
+        mmu_seq = kvm->mmu_notifier_seq;
+        smp_rmb();
 
         /*
          * Translate guest physical to true physical, acquiring
@@ -449,6 +456,12 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
                 gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
         }
 
+        spin_lock(&kvm->mmu_lock);
+        if (mmu_notifier_retry(kvm, mmu_seq)) {
+                ret = -EAGAIN;
+                goto out;
+        }
+
         kvmppc_e500_ref_setup(ref, gtlbe, pfn);
 
         kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
@@ -457,10 +470,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
         /* Clear i-cache for new pages */
         kvmppc_mmu_flush_icache(pfn);
 
+out:
+        spin_unlock(&kvm->mmu_lock);
+
         /* Drop refcount on page, so that mmu notifiers can clear it */
         kvm_release_pfn_clean(pfn);
 
-        return 0;
+        return ret;
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 6c32190dc73e..346b1c85ffb4 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -15,7 +15,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-        asm goto("0:    brcl 0,0\n"
+        asm_volatile_goto("0:   brcl 0,0\n"
                 ".pushsection __jump_table, \"aw\"\n"
                 ASM_ALIGN "\n"
                 ASM_PTR " 0b, %l[label], %0\n"
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index c84f33d51f7b..7dd21720e5b0 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -40,28 +40,26 @@ static inline void *load_real_addr(void *addr)
 }
 
 /*
- * Copy up to one page to vmalloc or real memory
+ * Copy real to virtual or real memory
  */
-static ssize_t copy_page_real(void *buf, void *src, size_t csize)
+static int copy_from_realmem(void *dest, void *src, size_t count)
 {
-        size_t size;
+        unsigned long size;
+        int rc;
 
-        if (is_vmalloc_addr(buf)) {
-                BUG_ON(csize >= PAGE_SIZE);
-                /* If buf is not page aligned, copy first part */
-                size = min(roundup(__pa(buf), PAGE_SIZE) - __pa(buf), csize);
-                if (size) {
-                        if (memcpy_real(load_real_addr(buf), src, size))
-                                return -EFAULT;
-                        buf += size;
-                        src += size;
-                }
-                /* Copy second part */
-                size = csize - size;
-                return (size) ? memcpy_real(load_real_addr(buf), src, size) : 0;
-        } else {
-                return memcpy_real(buf, src, csize);
-        }
+        if (!count)
+                return 0;
+        if (!is_vmalloc_or_module_addr(dest))
+                return memcpy_real(dest, src, count);
+        do {
+                size = min(count, PAGE_SIZE - (__pa(dest) & ~PAGE_MASK));
+                if (memcpy_real(load_real_addr(dest), src, size))
+                        return -EFAULT;
+                count -= size;
+                dest += size;
+                src += size;
+        } while (count);
+        return 0;
 }
 
 /*
@@ -114,7 +112,7 @@ static ssize_t copy_oldmem_page_kdump(char *buf, size_t csize,
                 rc = copy_to_user_real((void __force __user *) buf,
                                        (void *) src, csize);
         else
-                rc = copy_page_real(buf, (void *) src, csize);
+                rc = copy_from_realmem(buf, (void *) src, csize);
         return (rc == 0) ? rc : csize;
 }
 
@@ -210,7 +208,7 @@ int copy_from_oldmem(void *dest, void *src, size_t count)
         if (OLDMEM_BASE) {
                 if ((unsigned long) src < OLDMEM_SIZE) {
                         copied = min(count, OLDMEM_SIZE - (unsigned long) src);
-                        rc = memcpy_real(dest, src + OLDMEM_BASE, copied);
+                        rc = copy_from_realmem(dest, src + OLDMEM_BASE, copied);
                         if (rc)
                                 return rc;
                 }
@@ -223,7 +221,7 @@ int copy_from_oldmem(void *dest, void *src, size_t count)
                                 return rc;
                 }
         }
-        return memcpy_real(dest + copied, src + copied, count - copied);
+        return copy_from_realmem(dest + copied, src + copied, count - copied);
 }
 
 /*
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index cc30d1fb000c..0dc2b6d0a1ec 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -266,6 +266,7 @@ sysc_sigpending:
         tm      __TI_flags+3(%r12),_TIF_SYSCALL
         jno     sysc_return
         lm      %r2,%r7,__PT_R2(%r11)   # load svc arguments
+        l       %r10,__TI_sysc_table(%r12)      # 31 bit system call table
         xr      %r8,%r8                 # svc 0 returns -ENOSYS
         clc     __PT_INT_CODE+2(2,%r11),BASED(.Lnr_syscalls+2)
         jnl     sysc_nr_ok              # invalid svc number -> do svc 0
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 2b2188b97c6a..e5b43c97a834 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -297,6 +297,7 @@ sysc_sigpending:
         tm      __TI_flags+7(%r12),_TIF_SYSCALL
         jno     sysc_return
         lmg     %r2,%r7,__PT_R2(%r11)   # load svc arguments
+        lg      %r10,__TI_sysc_table(%r12)      # address of system call table
         lghi    %r8,0                   # svc 0 returns -ENOSYS
         llgh    %r1,__PT_INT_CODE+2(%r11)       # load new svc number
         cghi    %r1,NR_syscalls
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 0ce9fb245034..d86e64eddb42 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -67,6 +67,11 @@ static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn)
         case 0xac:      /* stnsm */
         case 0xad:      /* stosm */
                 return -EINVAL;
+        case 0xc6:
+                switch (insn[0] & 0x0f) {
+                case 0x00: /* exrl   */
+                        return -EINVAL;
+                }
         }
         switch (insn[0]) {
         case 0x0101:    /* pr    */
@@ -180,7 +185,6 @@ static int __kprobes is_insn_relative_long(kprobe_opcode_t *insn)
                 break;
         case 0xc6:
                 switch (insn[0] & 0x0f) {
-                case 0x00: /* exrl   */
                 case 0x02: /* pfdrl  */
                 case 0x04: /* cghrl  */
                 case 0x05: /* chrl   */
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 5080d16a832f..ec2e2e2aba7d 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -9,7 +9,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-                asm goto("1:\n\t"
+                asm_volatile_goto("1:\n\t"
                          "nop\n\t"
                          "nop\n\t"
                          ".pushsection __jump_table,  \"aw\"\n\t"
diff --git a/arch/tile/include/asm/atomic.h b/arch/tile/include/asm/atomic.h
index d385eaadece7..709798460763 100644
--- a/arch/tile/include/asm/atomic.h
+++ b/arch/tile/include/asm/atomic.h
@@ -166,7 +166,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int o, int n)
  *
  * Atomically sets @v to @i and returns old @v
  */
-static inline u64 atomic64_xchg(atomic64_t *v, u64 n)
+static inline long long atomic64_xchg(atomic64_t *v, long long n)
 {
         return xchg64(&v->counter, n);
 }
@@ -180,7 +180,8 @@ static inline u64 atomic64_xchg(atomic64_t *v, u64 n)
  * Atomically checks if @v holds @o and replaces it with @n if so.
  * Returns the old value at @v.
  */
-static inline u64 atomic64_cmpxchg(atomic64_t *v, u64 o, u64 n)
+static inline long long atomic64_cmpxchg(atomic64_t *v, long long o,
+                                        long long n)
 {
         return cmpxchg64(&v->counter, o, n);
 }
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index 0d0395b1b152..1ad4a1f7d42b 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -80,7 +80,7 @@ static inline void atomic_set(atomic_t *v, int n)
 /* A 64bit atomic type */
 
 typedef struct {
-        u64 __aligned(8) counter;
+        long long counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(val) { (val) }
@@ -91,14 +91,14 @@ typedef struct {
  *
  * Atomically reads the value of @v.
  */
-static inline u64 atomic64_read(const atomic64_t *v)
+static inline long long atomic64_read(const atomic64_t *v)
 {
         /*
          * Requires an atomic op to read both 32-bit parts consistently.
          * Casting away const is safe since the atomic support routines
          * do not write to memory if the value has not been modified.
          */
-        return _atomic64_xchg_add((u64 *)&v->counter, 0);
+        return _atomic64_xchg_add((long long *)&v->counter, 0);
 }
 
 /**
@@ -108,7 +108,7 @@ static inline u64 atomic64_read(const atomic64_t *v)
  *
  * Atomically adds @i to @v.
  */
-static inline void atomic64_add(u64 i, atomic64_t *v)
+static inline void atomic64_add(long long i, atomic64_t *v)
 {
         _atomic64_xchg_add(&v->counter, i);
 }
@@ -120,7 +120,7 @@ static inline void atomic64_add(u64 i, atomic64_t *v)
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
+static inline long long atomic64_add_return(long long i, atomic64_t *v)
 {
         smp_mb();  /* barrier for proper semantics */
         return _atomic64_xchg_add(&v->counter, i) + i;
@@ -135,7 +135,8 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
  * Atomically adds @a to @v, so long as @v was not already @u.
  * Returns non-zero if @v was not @u, and zero otherwise.
  */
-static inline u64 atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
+static inline long long atomic64_add_unless(atomic64_t *v, long long a,
+                                        long long u)
 {
         smp_mb();  /* barrier for proper semantics */
         return _atomic64_xchg_add_unless(&v->counter, a, u) != u;
@@ -151,7 +152,7 @@ static inline u64 atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
  * atomic64_set() can't be just a raw store, since it would be lost if it
  * fell between the load and store of one of the other atomic ops.
  */
-static inline void atomic64_set(atomic64_t *v, u64 n)
+static inline void atomic64_set(atomic64_t *v, long long n)
 {
         _atomic64_xchg(&v->counter, n);
 }
@@ -236,11 +237,13 @@ extern struct __get_user __atomic_xchg_add_unless(volatile int *p,
 extern struct __get_user __atomic_or(volatile int *p, int *lock, int n);
 extern struct __get_user __atomic_andn(volatile int *p, int *lock, int n);
 extern struct __get_user __atomic_xor(volatile int *p, int *lock, int n);
-extern u64 __atomic64_cmpxchg(volatile u64 *p, int *lock, u64 o, u64 n);
-extern u64 __atomic64_xchg(volatile u64 *p, int *lock, u64 n);
-extern u64 __atomic64_xchg_add(volatile u64 *p, int *lock, u64 n);
-extern u64 __atomic64_xchg_add_unless(volatile u64 *p,
-                                      int *lock, u64 o, u64 n);
+extern long long __atomic64_cmpxchg(volatile long long *p, int *lock,
+                                        long long o, long long n);
+extern long long __atomic64_xchg(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_xchg_add(volatile long long *p, int *lock,
+                                        long long n);
+extern long long __atomic64_xchg_add_unless(volatile long long *p,
+                                        int *lock, long long o, long long n);
 
 /* Return failure from the atomic wrappers. */
 struct __get_user __atomic_bad_address(int __user *addr);
diff --git a/arch/tile/include/asm/cmpxchg.h b/arch/tile/include/asm/cmpxchg.h
index 4001d5eab4bb..0ccda3c425be 100644
--- a/arch/tile/include/asm/cmpxchg.h
+++ b/arch/tile/include/asm/cmpxchg.h
@@ -35,10 +35,10 @@ int _atomic_xchg(int *ptr, int n);
 int _atomic_xchg_add(int *v, int i);
 int _atomic_xchg_add_unless(int *v, int a, int u);
 int _atomic_cmpxchg(int *ptr, int o, int n);
-u64 _atomic64_xchg(u64 *v, u64 n);
-u64 _atomic64_xchg_add(u64 *v, u64 i);
-u64 _atomic64_xchg_add_unless(u64 *v, u64 a, u64 u);
-u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n);
+long long _atomic64_xchg(long long *v, long long n);
+long long _atomic64_xchg_add(long long *v, long long i);
+long long _atomic64_xchg_add_unless(long long *v, long long a, long long u);
+long long _atomic64_cmpxchg(long long *v, long long o, long long n);
 
 #define xchg(ptr, n)                                                    \
         ({                                                              \
@@ -53,7 +53,8 @@ u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n);
                 if (sizeof(*(ptr)) != 4)                                \
                         __cmpxchg_called_with_bad_pointer();            \
                 smp_mb();                                               \
-                (typeof(*(ptr)))_atomic_cmpxchg((int *)ptr, (int)o, (int)n); \
+                (typeof(*(ptr)))_atomic_cmpxchg((int *)ptr, (int)o,     \
+                                                (int)n);                \
         })
 
 #define xchg64(ptr, n)                                                  \
@@ -61,7 +62,8 @@ u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n);
                 if (sizeof(*(ptr)) != 8)                                \
                         __xchg_called_with_bad_pointer();               \
                 smp_mb();                                               \
-                (typeof(*(ptr)))_atomic64_xchg((u64 *)(ptr), (u64)(n)); \
+                (typeof(*(ptr)))_atomic64_xchg((long long *)(ptr),      \
+                                                (long long)(n));        \
         })
 
 #define cmpxchg64(ptr, o, n)                                            \
@@ -69,7 +71,8 @@ u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n);
                 if (sizeof(*(ptr)) != 8)                                \
                         __cmpxchg_called_with_bad_pointer();            \
                 smp_mb();                                               \
-                (typeof(*(ptr)))_atomic64_cmpxchg((u64 *)ptr, (u64)o, (u64)n); \
+                (typeof(*(ptr)))_atomic64_cmpxchg((long long *)ptr,     \
+                                        (long long)o, (long long)n);    \
         })
 
 #else
@@ -81,10 +84,11 @@ u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n);
                 switch (sizeof(*(ptr))) {                               \
                 case 4:                                                 \
                         __x = (typeof(__x))(unsigned long)              \
-                                __insn_exch4((ptr), (u32)(unsigned long)(n)); \
+                                __insn_exch4((ptr),                     \
+                                        (u32)(unsigned long)(n));       \
                         break;                                          \
                 case 8:                                                 \
-                        __x = (typeof(__x))                     \
+                        __x = (typeof(__x))                             \
                                 __insn_exch((ptr), (unsigned long)(n)); \
                         break;                                          \
                 default:                                                \
@@ -103,10 +107,12 @@ u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n);
                 switch (sizeof(*(ptr))) {                               \
                 case 4:                                                 \
                         __x = (typeof(__x))(unsigned long)              \
-                                __insn_cmpexch4((ptr), (u32)(unsigned long)(n)); \
+                                __insn_cmpexch4((ptr),                  \
+                                        (u32)(unsigned long)(n));       \
                         break;                                          \
                 case 8:                                                 \
-                        __x = (typeof(__x))__insn_cmpexch((ptr), (u64)(n)); \
+                        __x = (typeof(__x))__insn_cmpexch((ptr),        \
+                                                (long long)(n));        \
                         break;                                          \
                 default:                                                \
                         __cmpxchg_called_with_bad_pointer();            \
diff --git a/arch/tile/include/asm/percpu.h b/arch/tile/include/asm/percpu.h
index 63294f5a8efb..4f7ae39fa202 100644
--- a/arch/tile/include/asm/percpu.h
+++ b/arch/tile/include/asm/percpu.h
@@ -15,9 +15,37 @@
 #ifndef _ASM_TILE_PERCPU_H
 #define _ASM_TILE_PERCPU_H
 
-register unsigned long __my_cpu_offset __asm__("tp");
-#define __my_cpu_offset __my_cpu_offset
-#define set_my_cpu_offset(tp) (__my_cpu_offset = (tp))
+register unsigned long my_cpu_offset_reg asm("tp");
+
+#ifdef CONFIG_PREEMPT
+/*
+ * For full preemption, we can't just use the register variable
+ * directly, since we need barrier() to hazard against it, causing the
+ * compiler to reload anything computed from a previous "tp" value.
+ * But we also don't want to use volatile asm, since we'd like the
+ * compiler to be able to cache the value across multiple percpu reads.
+ * So we use a fake stack read as a hazard against barrier().
+ * The 'U' constraint is like 'm' but disallows postincrement.
+ */
+static inline unsigned long __my_cpu_offset(void)
+{
+        unsigned long tp;
+        register unsigned long *sp asm("sp");
+        asm("move %0, tp" : "=r" (tp) : "U" (*sp));
+        return tp;
+}
+#define __my_cpu_offset __my_cpu_offset()
+#else
+/*
+ * We don't need to hazard against barrier() since "tp" doesn't ever
+ * change with PREEMPT_NONE, and with PREEMPT_VOLUNTARY it only
+ * changes at function call points, at which we are already re-reading
+ * the value of "tp" due to "my_cpu_offset_reg" being a global variable.
+ */
+#define __my_cpu_offset my_cpu_offset_reg
+#endif
+
+#define set_my_cpu_offset(tp) (my_cpu_offset_reg = (tp))
 
 #include <asm-generic/percpu.h>
 
diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c
index df27a1fd94a3..531f4c365351 100644
--- a/arch/tile/kernel/hardwall.c
+++ b/arch/tile/kernel/hardwall.c
@@ -66,7 +66,7 @@ static struct hardwall_type hardwall_types[] = {
                 0,
                 "udn",
                 LIST_HEAD_INIT(hardwall_types[HARDWALL_UDN].list),
-                __SPIN_LOCK_INITIALIZER(hardwall_types[HARDWALL_UDN].lock),
+                __SPIN_LOCK_UNLOCKED(hardwall_types[HARDWALL_UDN].lock),
                 NULL
         },
 #ifndef __tilepro__
@@ -77,7 +77,7 @@ static struct hardwall_type hardwall_types[] = {
                 1,  /* disabled pending hypervisor support */
                 "idn",
                 LIST_HEAD_INIT(hardwall_types[HARDWALL_IDN].list),
-                __SPIN_LOCK_INITIALIZER(hardwall_types[HARDWALL_IDN].lock),
+                __SPIN_LOCK_UNLOCKED(hardwall_types[HARDWALL_IDN].lock),
                 NULL
         },
         {  /* access to user-space IPI */
@@ -87,7 +87,7 @@ static struct hardwall_type hardwall_types[] = {
                 0,
                 "ipi",
                 LIST_HEAD_INIT(hardwall_types[HARDWALL_IPI].list),
-                __SPIN_LOCK_INITIALIZER(hardwall_types[HARDWALL_IPI].lock),
+                __SPIN_LOCK_UNLOCKED(hardwall_types[HARDWALL_IPI].lock),
                 NULL
         },
 #endif
diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S
index 088d5c141e68..2cbe6d5dd6b0 100644
--- a/arch/tile/kernel/intvec_32.S
+++ b/arch/tile/kernel/intvec_32.S
@@ -815,6 +815,9 @@ STD_ENTRY(interrupt_return)
         }
         bzt     r28, 1f
         bnz     r29, 1f
+        /* Disable interrupts explicitly for preemption. */
+        IRQ_DISABLE(r20,r21)
+        TRACE_IRQS_OFF
         jal     preempt_schedule_irq
         FEEDBACK_REENTER(interrupt_return)
 1:
diff --git a/arch/tile/kernel/intvec_64.S b/arch/tile/kernel/intvec_64.S
index ec755d3f3734..b8fc497f2437 100644
--- a/arch/tile/kernel/intvec_64.S
+++ b/arch/tile/kernel/intvec_64.S
@@ -841,6 +841,9 @@ STD_ENTRY(interrupt_return)
         }
         beqzt   r28, 1f
         bnez    r29, 1f
+        /* Disable interrupts explicitly for preemption. */
+        IRQ_DISABLE(r20,r21)
+        TRACE_IRQS_OFF
         jal     preempt_schedule_irq
         FEEDBACK_REENTER(interrupt_return)
 1:
diff --git a/arch/tile/kernel/stack.c b/arch/tile/kernel/stack.c
index 362284af3afd..c93977a62116 100644
--- a/arch/tile/kernel/stack.c
+++ b/arch/tile/kernel/stack.c
@@ -23,6 +23,7 @@
 #include <linux/mmzone.h>
 #include <linux/dcache.h>
 #include <linux/fs.h>
+#include <linux/string.h>
 #include <asm/backtrace.h>
 #include <asm/page.h>
 #include <asm/ucontext.h>
@@ -332,21 +333,18 @@ static void describe_addr(struct KBacktraceIterator *kbt,
         }
 
         if (vma->vm_file) {
-                char *s;
                 p = d_path(&vma->vm_file->f_path, buf, bufsize);
                 if (IS_ERR(p))
                         p = "?";
-                s = strrchr(p, '/');
-                if (s)
-                        p = s+1;
+                name = kbasename(p);
         } else {
-                p = "anon";
+                name = "anon";
         }
 
         /* Generate a string description of the vma info. */
-        namelen = strlen(p);
+        namelen = strlen(name);
         remaining = (bufsize - 1) - namelen;
-        memmove(buf, p, namelen);
+        memmove(buf, name, namelen);
         snprintf(buf + namelen, remaining, "[%lx+%lx] ",
                  vma->vm_start, vma->vm_end - vma->vm_start);
 }
diff --git a/arch/tile/lib/atomic_32.c b/arch/tile/lib/atomic_32.c
index 759efa337be8..c89b211fd9e7 100644
--- a/arch/tile/lib/atomic_32.c
+++ b/arch/tile/lib/atomic_32.c
@@ -107,19 +107,19 @@ unsigned long _atomic_xor(volatile unsigned long *p, unsigned long mask)
 EXPORT_SYMBOL(_atomic_xor);
 
 
-u64 _atomic64_xchg(u64 *v, u64 n)
+long long _atomic64_xchg(long long *v, long long n)
 {
         return __atomic64_xchg(v, __atomic_setup(v), n);
 }
 EXPORT_SYMBOL(_atomic64_xchg);
 
-u64 _atomic64_xchg_add(u64 *v, u64 i)
+long long _atomic64_xchg_add(long long *v, long long i)
 {
         return __atomic64_xchg_add(v, __atomic_setup(v), i);
 }
 EXPORT_SYMBOL(_atomic64_xchg_add);
 
-u64 _atomic64_xchg_add_unless(u64 *v, u64 a, u64 u)
+long long _atomic64_xchg_add_unless(long long *v, long long a, long long u)
 {
         /*
          * Note: argument order is switched here since it is easier
@@ -130,7 +130,7 @@ u64 _atomic64_xchg_add_unless(u64 *v, u64 a, u64 u)
 }
 EXPORT_SYMBOL(_atomic64_xchg_add_unless);
 
-u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n)
+long long _atomic64_cmpxchg(long long *v, long long o, long long n)
 {
         return __atomic64_cmpxchg(v, __atomic_setup(v), o, n);
 }
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index d3f5c63078d8..89270b4318db 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -374,7 +374,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
                  * Catch too early usage of this before alternatives
                  * have run.
                  */
-                asm goto("1: jmp %l[t_warn]\n"
+                asm_volatile_goto("1: jmp %l[t_warn]\n"
                          "2:\n"
                          ".section .altinstructions,\"a\"\n"
                          " .long 1b - .\n"
@@ -388,7 +388,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 
 #endif
 
-                asm goto("1: jmp %l[t_no]\n"
+                asm_volatile_goto("1: jmp %l[t_no]\n"
                          "2:\n"
                          ".section .altinstructions,\"a\"\n"
                          " .long 1b - .\n"
@@ -453,7 +453,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
  * have. Thus, we force the jump to the widest, 4-byte, signed relative
  * offset even though the last would often fit in less bytes.
  */
-                asm goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
+                asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
                          "2:\n"
                          ".section .altinstructions,\"a\"\n"
                          " .long 1b - .\n"              /* src offset */
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 64507f35800c..6a2cefb4395a 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -18,7 +18,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-        asm goto("1:"
+        asm_volatile_goto("1:"
                 ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
                 ".pushsection __jump_table,  \"aw\" \n\t"
                 _ASM_ALIGN "\n\t"
diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
index e7e6751648ed..07537a44216e 100644
--- a/arch/x86/include/asm/mutex_64.h
+++ b/arch/x86/include/asm/mutex_64.h
@@ -20,7 +20,7 @@
 static inline void __mutex_fastpath_lock(atomic_t *v,
                                          void (*fail_fn)(atomic_t *))
 {
-        asm volatile goto(LOCK_PREFIX "   decl %0\n"
+        asm_volatile_goto(LOCK_PREFIX "   decl %0\n"
                           "   jns %l[exit]\n"
                           : : "m" (v->counter)
                           : "memory", "cc"
@@ -75,7 +75,7 @@ static inline int __mutex_fastpath_lock_retval(atomic_t *count)
 static inline void __mutex_fastpath_unlock(atomic_t *v,
                                            void (*fail_fn)(atomic_t *))
 {
-        asm volatile goto(LOCK_PREFIX "   incl %0\n"
+        asm_volatile_goto(LOCK_PREFIX "   incl %0\n"
                           "   jg %l[exit]\n"
                           : : "m" (v->counter)
                           : "memory", "cc"
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 897783b3302a..9d8449158cf9 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1888,10 +1888,7 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
         userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
         userpg->pmc_width = x86_pmu.cntval_bits;
 
-        if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
-                return;
-
-        if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+        if (!sched_clock_stable)
                 return;
 
         userpg->cap_user_time = 1;
@@ -1899,10 +1896,8 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
         userpg->time_shift = CYC2NS_SCALE_FACTOR;
         userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
 
-        if (sched_clock_stable && !check_tsc_disabled()) {
-                userpg->cap_user_time_zero = 1;
-                userpg->time_zero = this_cpu_read(cyc2ns_offset);
-        }
+        userpg->cap_user_time_zero = 1;
+        userpg->time_zero = this_cpu_read(cyc2ns_offset);
 }
 
 /*
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3b8e7459dd4d..2b2fce1b2009 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3255,25 +3255,29 @@ static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 
 static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
+        struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
         if (!test_bit(VCPU_EXREG_PDPTR,
                       (unsigned long *)&vcpu->arch.regs_dirty))
                 return;
 
         if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-                vmcs_write64(GUEST_PDPTR0, vcpu->arch.mmu.pdptrs[0]);
-                vmcs_write64(GUEST_PDPTR1, vcpu->arch.mmu.pdptrs[1]);
-                vmcs_write64(GUEST_PDPTR2, vcpu->arch.mmu.pdptrs[2]);
-                vmcs_write64(GUEST_PDPTR3, vcpu->arch.mmu.pdptrs[3]);
+                vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]);
+                vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]);
+                vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]);
+                vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]);
         }
 }
 
 static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
 {
+        struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
         if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-                vcpu->arch.mmu.pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
-                vcpu->arch.mmu.pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
-                vcpu->arch.mmu.pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
-                vcpu->arch.mmu.pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
+                mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
+                mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
+                mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
+                mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
         }
 
         __set_bit(VCPU_EXREG_PDPTR,
@@ -7777,10 +7781,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
                 vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
                 vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
                 vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
-                __clear_bit(VCPU_EXREG_PDPTR,
-                                (unsigned long *)&vcpu->arch.regs_avail);
-                __clear_bit(VCPU_EXREG_PDPTR,
-                                (unsigned long *)&vcpu->arch.regs_dirty);
         }
 
         kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);