Merge tag 'arm64-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-aarch64

Pull arm64 patches from Catalin Marinas:

 - SMP support for the PSCI booting protocol (power state coordination
   interface).

 - Simple earlyprintk support.

 - Platform devices populated by default from the DT (SoC-agnostic).

 - CONTEXTIDR support (used by external trace tools).

* tag 'arm64-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-aarch64:
  arm64: mm: update CONTEXTIDR register to contain PID of current process
  arm64: atomics: fix grossly inconsistent asm constraints for exclusives
  arm64: compat: use compat_uptr_t type for compat_ucontext.uc_link
  arm64: Select ARCH_WANT_FRAME_POINTERS
  arm64: Add kvm_para.h and xor.h generic headers
  arm64: SMP: enable PSCI boot method
  arm64: psci: add support for PSCI invocations from the kernel
  arm64: SMP: rework the SMP code to be enabling method agnostic
  arm64: perf: add guest vs host discrimination
  arm64: add COMPAT_PSR_*_BIT flags
  arm64: Add simple earlyprintk support
  arm64: Populate the platform devices

29 files changed, 855 insertions, 173 deletions

diff --git a/Documentation/arm64/memory.txt b/Documentation/arm64/memory.txt
index d758702fc03c..5f583af0a6e1 100644
--- a/Documentation/arm64/memory.txt
+++ b/Documentation/arm64/memory.txt
@@ -35,6 +35,8 @@ ffffffbc00000000	ffffffbdffffffff	   8GB		vmemmap
 
 ffffffbe00000000        ffffffbffbbfffff          ~8GB          [guard, future vmmemap]
 
+ffffffbffbc00000        ffffffbffbdfffff           2MB          earlyprintk device
+
 ffffffbffbe00000        ffffffbffbe0ffff          64KB          PCI I/O space
 
 ffffffbbffff0000        ffffffbcffffffff          ~2MB          [guard]
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 75e915b72471..7c43569e3141 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -2,6 +2,7 @@ config ARM64
         def_bool y
         select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
         select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
+        select ARCH_WANT_FRAME_POINTERS
         select ARM_AMBA
         select CLONE_BACKWARDS
         select COMMON_CLK
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index d7553f2bda66..51493430f142 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -24,4 +24,21 @@ config DEBUG_STACK_USAGE
           Enables the display of the minimum amount of free stack which each
           task has ever had available in the sysrq-T output.
 
+config EARLY_PRINTK
+        bool "Early printk support"
+        default y
+        help
+          Say Y here if you want to have an early console using the
+          earlyprintk=<name>[,<addr>][,<options>] kernel parameter. It
+          is assumed that the early console device has been initialised
+          by the boot loader prior to starting the Linux kernel.
+
+config PID_IN_CONTEXTIDR
+        bool "Write the current PID to the CONTEXTIDR register"
+        help
+          Enabling this option causes the kernel to write the current PID to
+          the CONTEXTIDR register, at the expense of some additional
+          instructions during context switch. Say Y here only if you are
+          planning to use hardware trace tools with this kernel.
+
 endmenu
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 14a9d5a2b85b..e5fe4f99fe10 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -19,6 +19,7 @@ generic-y += ipcbuf.h
 generic-y += irq_regs.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
+generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mman.h
@@ -48,3 +49,4 @@ generic-y += trace_clock.h
 generic-y += types.h
 generic-y += unaligned.h
 generic-y += user.h
+generic-y += xor.h
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 407717ba060e..836364468571 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -49,12 +49,12 @@ static inline void atomic_add(int i, atomic_t *v)
         int result;
 
         asm volatile("// atomic_add\n"
-"1:     ldxr    %w0, [%3]\n"
-"       add     %w0, %w0, %w4\n"
-"       stxr    %w1, %w0, [%3]\n"
+"1:     ldxr    %w0, %2\n"
+"       add     %w0, %w0, %w3\n"
+"       stxr    %w1, %w0, %2\n"
 "       cbnz    %w1, 1b"
-        : "=&r" (result), "=&r" (tmp), "+o" (v->counter)
-        : "r" (&v->counter), "Ir" (i)
+        : "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
+        : "Ir" (i)
         : "cc");
 }
 
@@ -64,13 +64,13 @@ static inline int atomic_add_return(int i, atomic_t *v)
         int result;
 
         asm volatile("// atomic_add_return\n"
-"1:     ldaxr   %w0, [%3]\n"
-"       add     %w0, %w0, %w4\n"
-"       stlxr   %w1, %w0, [%3]\n"
+"1:     ldaxr   %w0, %2\n"
+"       add     %w0, %w0, %w3\n"
+"       stlxr   %w1, %w0, %2\n"
 "       cbnz    %w1, 1b"
-        : "=&r" (result), "=&r" (tmp), "+o" (v->counter)
-        : "r" (&v->counter), "Ir" (i)
-        : "cc");
+        : "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
+        : "Ir" (i)
+        : "cc", "memory");
 
         return result;
 }
@@ -81,12 +81,12 @@ static inline void atomic_sub(int i, atomic_t *v)
         int result;
 
         asm volatile("// atomic_sub\n"
-"1:     ldxr    %w0, [%3]\n"
-"       sub     %w0, %w0, %w4\n"
-"       stxr    %w1, %w0, [%3]\n"
+"1:     ldxr    %w0, %2\n"
+"       sub     %w0, %w0, %w3\n"
+"       stxr    %w1, %w0, %2\n"
 "       cbnz    %w1, 1b"
-        : "=&r" (result), "=&r" (tmp), "+o" (v->counter)
-        : "r" (&v->counter), "Ir" (i)
+        : "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
+        : "Ir" (i)
         : "cc");
 }
 
@@ -96,13 +96,13 @@ static inline int atomic_sub_return(int i, atomic_t *v)
         int result;
 
         asm volatile("// atomic_sub_return\n"
-"1:     ldaxr   %w0, [%3]\n"
-"       sub     %w0, %w0, %w4\n"
-"       stlxr   %w1, %w0, [%3]\n"
+"1:     ldaxr   %w0, %2\n"
+"       sub     %w0, %w0, %w3\n"
+"       stlxr   %w1, %w0, %2\n"
 "       cbnz    %w1, 1b"
-        : "=&r" (result), "=&r" (tmp), "+o" (v->counter)
-        : "r" (&v->counter), "Ir" (i)
-        : "cc");
+        : "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
+        : "Ir" (i)
+        : "cc", "memory");
 
         return result;
 }
@@ -113,15 +113,15 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
         int oldval;
 
         asm volatile("// atomic_cmpxchg\n"
-"1:     ldaxr   %w1, [%3]\n"
-"       cmp     %w1, %w4\n"
+"1:     ldaxr   %w1, %2\n"
+"       cmp     %w1, %w3\n"
 "       b.ne    2f\n"
-"       stlxr   %w0, %w5, [%3]\n"
+"       stlxr   %w0, %w4, %2\n"
 "       cbnz    %w0, 1b\n"
 "2:"
-        : "=&r" (tmp), "=&r" (oldval), "+o" (ptr->counter)
-        : "r" (&ptr->counter), "Ir" (old), "r" (new)
-        : "cc");
+        : "=&r" (tmp), "=&r" (oldval), "+Q" (ptr->counter)
+        : "Ir" (old), "r" (new)
+        : "cc", "memory");
 
         return oldval;
 }
@@ -131,12 +131,12 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
         unsigned long tmp, tmp2;
 
         asm volatile("// atomic_clear_mask\n"
-"1:     ldxr    %0, [%3]\n"
-"       bic     %0, %0, %4\n"
-"       stxr    %w1, %0, [%3]\n"
+"1:     ldxr    %0, %2\n"
+"       bic     %0, %0, %3\n"
+"       stxr    %w1, %0, %2\n"
 "       cbnz    %w1, 1b"
-        : "=&r" (tmp), "=&r" (tmp2), "+o" (*addr)
-        : "r" (addr), "Ir" (mask)
+        : "=&r" (tmp), "=&r" (tmp2), "+Q" (*addr)
+        : "Ir" (mask)
         : "cc");
 }
 
@@ -182,12 +182,12 @@ static inline void atomic64_add(u64 i, atomic64_t *v)
         unsigned long tmp;
 
         asm volatile("// atomic64_add\n"
-"1:     ldxr    %0, [%3]\n"
-"       add     %0, %0, %4\n"
-"       stxr    %w1, %0, [%3]\n"
+"1:     ldxr    %0, %2\n"
+"       add     %0, %0, %3\n"
+"       stxr    %w1, %0, %2\n"
 "       cbnz    %w1, 1b"
-        : "=&r" (result), "=&r" (tmp), "+o" (v->counter)
-        : "r" (&v->counter), "Ir" (i)
+        : "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
+        : "Ir" (i)
         : "cc");
 }
 
@@ -197,13 +197,13 @@ static inline long atomic64_add_return(long i, atomic64_t *v)
         unsigned long tmp;
 
         asm volatile("// atomic64_add_return\n"
-"1:     ldaxr   %0, [%3]\n"
-"       add     %0, %0, %4\n"
-"       stlxr   %w1, %0, [%3]\n"
+"1:     ldaxr   %0, %2\n"
+"       add     %0, %0, %3\n"
+"       stlxr   %w1, %0, %2\n"
 "       cbnz    %w1, 1b"
-        : "=&r" (result), "=&r" (tmp), "+o" (v->counter)
-        : "r" (&v->counter), "Ir" (i)
-        : "cc");
+        : "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
+        : "Ir" (i)
+        : "cc", "memory");
 
         return result;
 }
@@ -214,12 +214,12 @@ static inline void atomic64_sub(u64 i, atomic64_t *v)
         unsigned long tmp;
 
         asm volatile("// atomic64_sub\n"
-"1:     ldxr    %0, [%3]\n"
-"       sub     %0, %0, %4\n"
-"       stxr    %w1, %0, [%3]\n"
+"1:     ldxr    %0, %2\n"
+"       sub     %0, %0, %3\n"
+"       stxr    %w1, %0, %2\n"
 "       cbnz    %w1, 1b"
-        : "=&r" (result), "=&r" (tmp), "+o" (v->counter)
-        : "r" (&v->counter), "Ir" (i)
+        : "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
+        : "Ir" (i)
         : "cc");
 }
 
@@ -229,13 +229,13 @@ static inline long atomic64_sub_return(long i, atomic64_t *v)
         unsigned long tmp;
 
         asm volatile("// atomic64_sub_return\n"
-"1:     ldaxr   %0, [%3]\n"
-"       sub     %0, %0, %4\n"
-"       stlxr   %w1, %0, [%3]\n"
+"1:     ldaxr   %0, %2\n"
+"       sub     %0, %0, %3\n"
+"       stlxr   %w1, %0, %2\n"
 "       cbnz    %w1, 1b"
-        : "=&r" (result), "=&r" (tmp), "+o" (v->counter)
-        : "r" (&v->counter), "Ir" (i)
-        : "cc");
+        : "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
+        : "Ir" (i)
+        : "cc", "memory");
 
         return result;
 }
@@ -246,15 +246,15 @@ static inline long atomic64_cmpxchg(atomic64_t *ptr, long old, long new)
         unsigned long res;
 
         asm volatile("// atomic64_cmpxchg\n"
-"1:     ldaxr   %1, [%3]\n"
-"       cmp     %1, %4\n"
+"1:     ldaxr   %1, %2\n"
+"       cmp     %1, %3\n"
 "       b.ne    2f\n"
-"       stlxr   %w0, %5, [%3]\n"
+"       stlxr   %w0, %4, %2\n"
 "       cbnz    %w0, 1b\n"
 "2:"
-        : "=&r" (res), "=&r" (oldval), "+o" (ptr->counter)
-        : "r" (&ptr->counter), "Ir" (old), "r" (new)
-        : "cc");
+        : "=&r" (res), "=&r" (oldval), "+Q" (ptr->counter)
+        : "Ir" (old), "r" (new)
+        : "cc", "memory");
 
         return oldval;
 }
@@ -267,15 +267,15 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
         unsigned long tmp;
 
         asm volatile("// atomic64_dec_if_positive\n"
-"1:     ldaxr   %0, [%3]\n"
+"1:     ldaxr   %0, %2\n"
 "       subs    %0, %0, #1\n"
 "       b.mi    2f\n"
-"       stlxr   %w1, %0, [%3]\n"
+"       stlxr   %w1, %0, %2\n"
 "       cbnz    %w1, 1b\n"
 "2:"
-        : "=&r" (result), "=&r" (tmp), "+o" (v->counter)
-        : "r" (&v->counter)
-        : "cc");
+        : "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
+        :
+        : "cc", "memory");
 
         return result;
 }
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index e0e65b069d9e..968b5cbfc260 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -29,39 +29,39 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
         switch (size) {
         case 1:
                 asm volatile("//        __xchg1\n"
-                "1:     ldaxrb  %w0, [%3]\n"
-                "       stlxrb  %w1, %w2, [%3]\n"
+                "1:     ldaxrb  %w0, %2\n"
+                "       stlxrb  %w1, %w3, %2\n"
                 "       cbnz    %w1, 1b\n"
-                        : "=&r" (ret), "=&r" (tmp)
-                        : "r" (x), "r" (ptr)
-                        : "memory", "cc");
+                        : "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)
+                        : "r" (x)
+                        : "cc", "memory");
                 break;
         case 2:
                 asm volatile("//        __xchg2\n"
-                "1:     ldaxrh  %w0, [%3]\n"
-                "       stlxrh  %w1, %w2, [%3]\n"
+                "1:     ldaxrh  %w0, %2\n"
+                "       stlxrh  %w1, %w3, %2\n"
                 "       cbnz    %w1, 1b\n"
-                        : "=&r" (ret), "=&r" (tmp)
-                        : "r" (x), "r" (ptr)
-                        : "memory", "cc");
+                        : "=&r" (ret), "=&r" (tmp), "+Q" (*(u16 *)ptr)
+                        : "r" (x)
+                        : "cc", "memory");
                 break;
         case 4:
                 asm volatile("//        __xchg4\n"
-                "1:     ldaxr   %w0, [%3]\n"
-                "       stlxr   %w1, %w2, [%3]\n"
+                "1:     ldaxr   %w0, %2\n"
+                "       stlxr   %w1, %w3, %2\n"
                 "       cbnz    %w1, 1b\n"
-                        : "=&r" (ret), "=&r" (tmp)
-                        : "r" (x), "r" (ptr)
-                        : "memory", "cc");
+                        : "=&r" (ret), "=&r" (tmp), "+Q" (*(u32 *)ptr)
+                        : "r" (x)
+                        : "cc", "memory");
                 break;
         case 8:
                 asm volatile("//        __xchg8\n"
-                "1:     ldaxr   %0, [%3]\n"
-                "       stlxr   %w1, %2, [%3]\n"
+                "1:     ldaxr   %0, %2\n"
+                "       stlxr   %w1, %3, %2\n"
                 "       cbnz    %w1, 1b\n"
-                        : "=&r" (ret), "=&r" (tmp)
-                        : "r" (x), "r" (ptr)
-                        : "memory", "cc");
+                        : "=&r" (ret), "=&r" (tmp), "+Q" (*(u64 *)ptr)
+                        : "r" (x)
+                        : "cc", "memory");
                 break;
         default:
                 BUILD_BUG();
@@ -82,14 +82,14 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
         case 1:
                 do {
                         asm volatile("// __cmpxchg1\n"
-                        "       ldxrb   %w1, [%2]\n"
+                        "       ldxrb   %w1, %2\n"
                         "       mov     %w0, #0\n"
                         "       cmp     %w1, %w3\n"
                         "       b.ne    1f\n"
-                        "       stxrb   %w0, %w4, [%2]\n"
+                        "       stxrb   %w0, %w4, %2\n"
                         "1:\n"
-                                : "=&r" (res), "=&r" (oldval)
-                                : "r" (ptr), "Ir" (old), "r" (new)
+                                : "=&r" (res), "=&r" (oldval), "+Q" (*(u8 *)ptr)
+                                : "Ir" (old), "r" (new)
                                 : "cc");
                 } while (res);
                 break;
@@ -97,29 +97,29 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
         case 2:
                 do {
                         asm volatile("// __cmpxchg2\n"
-                        "       ldxrh   %w1, [%2]\n"
+                        "       ldxrh   %w1, %2\n"
                         "       mov     %w0, #0\n"
                         "       cmp     %w1, %w3\n"
                         "       b.ne    1f\n"
-                        "       stxrh   %w0, %w4, [%2]\n"
+                        "       stxrh   %w0, %w4, %2\n"
                         "1:\n"
-                                : "=&r" (res), "=&r" (oldval)
-                                : "r" (ptr), "Ir" (old), "r" (new)
-                                : "memory", "cc");
+                                : "=&r" (res), "=&r" (oldval), "+Q" (*(u16 *)ptr)
+                                : "Ir" (old), "r" (new)
+                                : "cc");
                 } while (res);
                 break;
 
         case 4:
                 do {
                         asm volatile("// __cmpxchg4\n"
-                        "       ldxr    %w1, [%2]\n"
+                        "       ldxr    %w1, %2\n"
                         "       mov     %w0, #0\n"
                         "       cmp     %w1, %w3\n"
                         "       b.ne    1f\n"
-                        "       stxr    %w0, %w4, [%2]\n"
+                        "       stxr    %w0, %w4, %2\n"
                         "1:\n"
-                                : "=&r" (res), "=&r" (oldval)
-                                : "r" (ptr), "Ir" (old), "r" (new)
+                                : "=&r" (res), "=&r" (oldval), "+Q" (*(u32 *)ptr)
+                                : "Ir" (old), "r" (new)
                                 : "cc");
                 } while (res);
                 break;
@@ -127,14 +127,14 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
         case 8:
                 do {
                         asm volatile("// __cmpxchg8\n"
-                        "       ldxr    %1, [%2]\n"
+                        "       ldxr    %1, %2\n"
                         "       mov     %w0, #0\n"
                         "       cmp     %1, %3\n"
                         "       b.ne    1f\n"
-                        "       stxr    %w0, %4, [%2]\n"
+                        "       stxr    %w0, %4, %2\n"
                         "1:\n"
-                                : "=&r" (res), "=&r" (oldval)
-                                : "r" (ptr), "Ir" (old), "r" (new)
+                                : "=&r" (res), "=&r" (oldval), "+Q" (*(u64 *)ptr)
+                                : "Ir" (old), "r" (new)
                                 : "cc");
                 } while (res);
                 break;
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 3468ae8439fa..c582fa316366 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -39,7 +39,7 @@
 "       .popsection\n"                                                  \
         : "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)       \
         : "r" (oparg), "Ir" (-EFAULT)                                   \
-        : "cc")
+        : "cc", "memory")
 
 static inline int
 futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index d2f05a608274..57f12c991de2 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -230,6 +230,9 @@ extern void __iounmap(volatile void __iomem *addr);
 #define ioremap_wc(addr, size)          __ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
 #define iounmap                         __iounmap
 
+#define PROT_SECT_DEFAULT       (PMD_TYPE_SECT | PMD_SECT_AF)
+#define PROT_SECT_DEVICE_nGnRE  (PROT_SECT_DEFAULT | PTE_PXN | PTE_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
+
 #define ARCH_HAS_IOREMAP_WC
 #include <asm-generic/iomap.h>
 
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 1cac16a001cb..381f556b664e 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -43,6 +43,7 @@
 #define PAGE_OFFSET             UL(0xffffffc000000000)
 #define MODULES_END             (PAGE_OFFSET)
 #define MODULES_VADDR           (MODULES_END - SZ_64M)
+#define EARLYCON_IOBASE         (MODULES_VADDR - SZ_4M)
 #define VA_BITS                 (39)
 #define TASK_SIZE_64            (UL(1) << VA_BITS)
 
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index d4f7fd5b9e33..2494fc01896a 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -26,5 +26,6 @@ typedef struct {
 
 extern void paging_init(void);
 extern void setup_mm_for_reboot(void);
+extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
 
 #endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index f68465dee026..e2bc385adb6b 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -35,6 +35,21 @@ extern unsigned int cpu_last_asid;
 void __init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void __new_context(struct mm_struct *mm);
 
+#ifdef CONFIG_PID_IN_CONTEXTIDR
+static inline void contextidr_thread_switch(struct task_struct *next)
+{
+        asm(
+        "       msr     contextidr_el1, %0\n"
+        "       isb"
+        :
+        : "r" (task_pid_nr(next)));
+}
+#else
+static inline void contextidr_thread_switch(struct task_struct *next)
+{
+}
+#endif
+
 /*
  * Set TTBR0 to empty_zero_page. No translations will be possible via TTBR0.
  */
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index a6fffd511c5e..d26d1d53c0d7 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -17,6 +17,11 @@
 #ifndef __ASM_PERF_EVENT_H
 #define __ASM_PERF_EVENT_H
 
-/* It's quiet around here... */
+#ifdef CONFIG_HW_PERF_EVENTS
+struct pt_regs;
+extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_misc_flags(struct pt_regs *regs);
+#define perf_misc_flags(regs)   perf_misc_flags(regs)
+#endif
 
 #endif
diff --git a/arch/arm64/include/asm/psci.h b/arch/arm64/include/asm/psci.h
new file mode 100644
index 000000000000..0604237ecd99
--- /dev/null
+++ b/arch/arm64/include/asm/psci.h
@@ -0,0 +1,38 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2013 ARM Limited
+ */
+
+#ifndef __ASM_PSCI_H
+#define __ASM_PSCI_H
+
+#define PSCI_POWER_STATE_TYPE_STANDBY           0
+#define PSCI_POWER_STATE_TYPE_POWER_DOWN        1
+
+struct psci_power_state {
+        u16     id;
+        u8      type;
+        u8      affinity_level;
+};
+
+struct psci_operations {
+        int (*cpu_suspend)(struct psci_power_state state,
+                           unsigned long entry_point);
+        int (*cpu_off)(struct psci_power_state state);
+        int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
+        int (*migrate)(unsigned long cpuid);
+};
+
+extern struct psci_operations psci_ops;
+
+int psci_init(void);
+
+#endif /* __ASM_PSCI_H */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 4ce845f8ee1c..41a71ee4c3df 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -42,6 +42,16 @@
 #define COMPAT_PSR_MODE_UND     0x0000001b
 #define COMPAT_PSR_MODE_SYS     0x0000001f
 #define COMPAT_PSR_T_BIT        0x00000020
+#define COMPAT_PSR_F_BIT        0x00000040
+#define COMPAT_PSR_I_BIT        0x00000080
+#define COMPAT_PSR_A_BIT        0x00000100
+#define COMPAT_PSR_E_BIT        0x00000200
+#define COMPAT_PSR_J_BIT        0x01000000
+#define COMPAT_PSR_Q_BIT        0x08000000
+#define COMPAT_PSR_V_BIT        0x10000000
+#define COMPAT_PSR_C_BIT        0x20000000
+#define COMPAT_PSR_Z_BIT        0x40000000
+#define COMPAT_PSR_N_BIT        0x80000000
 #define COMPAT_PSR_IT_MASK      0x0600fc00      /* If-Then execution state mask */
 /*
  * These are 'magic' values for PTRACE_PEEKUSR that return info about where a
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 7e34295f78e3..4b8023c5d146 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -66,4 +66,15 @@ extern volatile unsigned long secondary_holding_pen_release;
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
+struct device_node;
+
+struct smp_enable_ops {
+        const char      *name;
+        int             (*init_cpu)(struct device_node *, int);
+        int             (*prepare_cpu)(int);
+};
+
+extern const struct smp_enable_ops smp_spin_table_ops;
+extern const struct smp_enable_ops smp_psci_ops;
+
 #endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 41112fe2f8b1..7065e920149d 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -45,13 +45,13 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
         asm volatile(
         "       sevl\n"
         "1:     wfe\n"
-        "2:     ldaxr   %w0, [%1]\n"
+        "2:     ldaxr   %w0, %1\n"
         "       cbnz    %w0, 1b\n"
-        "       stxr    %w0, %w2, [%1]\n"
+        "       stxr    %w0, %w2, %1\n"
         "       cbnz    %w0, 2b\n"
-        : "=&r" (tmp)
-        : "r" (&lock->lock), "r" (1)
-        : "memory");
+        : "=&r" (tmp), "+Q" (lock->lock)
+        : "r" (1)
+        : "cc", "memory");
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
@@ -59,13 +59,13 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
         unsigned int tmp;
 
         asm volatile(
-        "       ldaxr   %w0, [%1]\n"
+        "       ldaxr   %w0, %1\n"
         "       cbnz    %w0, 1f\n"
-        "       stxr    %w0, %w2, [%1]\n"
+        "       stxr    %w0, %w2, %1\n"
         "1:\n"
-        : "=&r" (tmp)
-        : "r" (&lock->lock), "r" (1)
-        : "memory");
+        : "=&r" (tmp), "+Q" (lock->lock)
+        : "r" (1)
+        : "cc", "memory");
 
         return !tmp;
 }
@@ -73,8 +73,8 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
         asm volatile(
-        "       stlr    %w1, [%0]\n"
-        : : "r" (&lock->lock), "r" (0) : "memory");
+        "       stlr    %w1, %0\n"
+        : "=Q" (lock->lock) : "r" (0) : "memory");
 }
 
 /*
@@ -94,13 +94,13 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
         asm volatile(
         "       sevl\n"
         "1:     wfe\n"
-        "2:     ldaxr   %w0, [%1]\n"
+        "2:     ldaxr   %w0, %1\n"
         "       cbnz    %w0, 1b\n"
-        "       stxr    %w0, %w2, [%1]\n"
+        "       stxr    %w0, %w2, %1\n"
         "       cbnz    %w0, 2b\n"
-        : "=&r" (tmp)
-        : "r" (&rw->lock), "r" (0x80000000)
-        : "memory");
+        : "=&r" (tmp), "+Q" (rw->lock)
+        : "r" (0x80000000)
+        : "cc", "memory");
 }
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
@@ -108,13 +108,13 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
         unsigned int tmp;
 
         asm volatile(
-        "       ldaxr   %w0, [%1]\n"
+        "       ldaxr   %w0, %1\n"
         "       cbnz    %w0, 1f\n"
-        "       stxr    %w0, %w2, [%1]\n"
+        "       stxr    %w0, %w2, %1\n"
         "1:\n"
-        : "=&r" (tmp)
-        : "r" (&rw->lock), "r" (0x80000000)
-        : "memory");
+        : "=&r" (tmp), "+Q" (rw->lock)
+        : "r" (0x80000000)
+        : "cc", "memory");
 
         return !tmp;
 }
@@ -122,8 +122,8 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
         asm volatile(
-        "       stlr    %w1, [%0]\n"
-        : : "r" (&rw->lock), "r" (0) : "memory");
+        "       stlr    %w1, %0\n"
+        : "=Q" (rw->lock) : "r" (0) : "memory");
 }
 
 /* write_can_lock - would write_trylock() succeed? */
@@ -148,14 +148,14 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
         asm volatile(
         "       sevl\n"
         "1:     wfe\n"
-        "2:     ldaxr   %w0, [%2]\n"
+        "2:     ldaxr   %w0, %2\n"
         "       add     %w0, %w0, #1\n"
         "       tbnz    %w0, #31, 1b\n"
-        "       stxr    %w1, %w0, [%2]\n"
+        "       stxr    %w1, %w0, %2\n"
         "       cbnz    %w1, 2b\n"
-        : "=&r" (tmp), "=&r" (tmp2)
-        : "r" (&rw->lock)
-        : "memory");
+        : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
+        :
+        : "cc", "memory");
 }
 
 static inline void arch_read_unlock(arch_rwlock_t *rw)
@@ -163,13 +163,13 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
         unsigned int tmp, tmp2;
 
         asm volatile(
-        "1:     ldxr    %w0, [%2]\n"
+        "1:     ldxr    %w0, %2\n"
         "       sub     %w0, %w0, #1\n"
-        "       stlxr   %w1, %w0, [%2]\n"
+        "       stlxr   %w1, %w0, %2\n"
         "       cbnz    %w1, 1b\n"
-        : "=&r" (tmp), "=&r" (tmp2)
-        : "r" (&rw->lock)
-        : "memory");
+        : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
+        :
+        : "cc", "memory");
 }
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
@@ -177,14 +177,14 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
         unsigned int tmp, tmp2 = 1;
 
         asm volatile(
-        "       ldaxr   %w0, [%2]\n"
+        "       ldaxr   %w0, %2\n"
         "       add     %w0, %w0, #1\n"
         "       tbnz    %w0, #31, 1f\n"
-        "       stxr    %w1, %w0, [%2]\n"
+        "       stxr    %w1, %w0, %2\n"
         "1:\n"
-        : "=&r" (tmp), "+r" (tmp2)
-        : "r" (&rw->lock)
-        : "memory");
+        : "=&r" (tmp), "+r" (tmp2), "+Q" (rw->lock)
+        :
+        : "cc", "memory");
 
         return !tmp2;
 }
diff --git a/arch/arm64/include/uapi/asm/Kbuild b/arch/arm64/include/uapi/asm/Kbuild
index ca5b65f75c7b..e4b78bdca19e 100644
--- a/arch/arm64/include/uapi/asm/Kbuild
+++ b/arch/arm64/include/uapi/asm/Kbuild
@@ -1,11 +1,14 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += kvm_para.h
+
 header-y += auxvec.h
 header-y += bitsperlong.h
 header-y += byteorder.h
 header-y += fcntl.h
 header-y += hwcap.h
+header-y += kvm_para.h
 header-y += param.h
 header-y += ptrace.h
 header-y += setup.h
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 74239c31e25a..7b4b564961d4 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -9,14 +9,15 @@ AFLAGS_head.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 arm64-obj-y             := cputable.o debug-monitors.o entry.o irq.o fpsimd.o   \
                            entry-fpsimd.o process.o ptrace.o setup.o signal.o   \
                            sys.o stacktrace.o time.o traps.o io.o vdso.o        \
-                           hyp-stub.o
+                           hyp-stub.o psci.o
 
 arm64-obj-$(CONFIG_COMPAT)              += sys32.o kuser32.o signal32.o         \
                                            sys_compat.o
 arm64-obj-$(CONFIG_MODULES)             += arm64ksyms.o module.o
-arm64-obj-$(CONFIG_SMP)                 += smp.o
+arm64-obj-$(CONFIG_SMP)                 += smp.o smp_spin_table.o smp_psci.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)      += perf_event.o
 arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o
+arm64-obj-$(CONFIG_EARLY_PRINTK)        += early_printk.o
 
 obj-y                                   += $(arm64-obj-y) vdso/
 obj-m                                   += $(arm64-obj-m)
diff --git a/arch/arm64/kernel/early_printk.c b/arch/arm64/kernel/early_printk.c
new file mode 100644
index 000000000000..7e320a2edb9b
--- /dev/null
+++ b/arch/arm64/kernel/early_printk.c
@@ -0,0 +1,118 @@
+/*
+ * Earlyprintk support.
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/kernel.h>
+#include <linux/console.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/io.h>
+
+#include <linux/amba/serial.h>
+
+static void __iomem *early_base;
+static void (*printch)(char ch);
+
+/*
+ * PL011 single character TX.
+ */
+static void pl011_printch(char ch)
+{
+        while (readl_relaxed(early_base + UART01x_FR) & UART01x_FR_TXFF)
+                ;
+        writeb_relaxed(ch, early_base + UART01x_DR);
+        while (readl_relaxed(early_base + UART01x_FR) & UART01x_FR_BUSY)
+                ;
+}
+
+struct earlycon_match {
+        const char *name;
+        void (*printch)(char ch);
+};
+
+static const struct earlycon_match earlycon_match[] __initconst = {
+        { .name = "pl011", .printch = pl011_printch, },
+        {}
+};
+
+static void early_write(struct console *con, const char *s, unsigned n)
+{
+        while (n-- > 0) {
+                if (*s == '\n')
+                        printch('\r');
+                printch(*s);
+                s++;
+        }
+}
+
+static struct console early_console = {
+        .name =         "earlycon",
+        .write =        early_write,
+        .flags =        CON_PRINTBUFFER | CON_BOOT,
+        .index =        -1,
+};
+
+/*
+ * Parse earlyprintk=... parameter in the format:
+ *
+ *   <name>[,<addr>][,<options>]
+ *
+ * and register the early console. It is assumed that the UART has been
+ * initialised by the bootloader already.
+ */
+static int __init setup_early_printk(char *buf)
+{
+        const struct earlycon_match *match = earlycon_match;
+        phys_addr_t paddr = 0;
+
+        if (!buf) {
+                pr_warning("No earlyprintk arguments passed.\n");
+                return 0;
+        }
+
+        while (match->name) {
+                size_t len = strlen(match->name);
+                if (!strncmp(buf, match->name, len)) {
+                        buf += len;
+                        break;
+                }
+                match++;
+        }
+        if (!match->name) {
+                pr_warning("Unknown earlyprintk arguments: %s\n", buf);
+                return 0;
+        }
+
+        /* I/O address */
+        if (!strncmp(buf, ",0x", 3)) {
+                char *e;
+                paddr = simple_strtoul(buf + 1, &e, 16);
+                buf = e;
+        }
+        /* no options parsing yet */
+
+        if (paddr)
+                early_base = early_io_map(paddr, EARLYCON_IOBASE);
+
+        printch = match->printch;
+        register_console(&early_console);
+
+        return 0;
+}
+
+early_param("earlyprintk", setup_early_printk);
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 368ad1f7c36c..0a0a49756826 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -82,10 +82,8 @@
 
 #ifdef CONFIG_ARM64_64K_PAGES
 #define MM_MMUFLAGS     PTE_ATTRINDX(MT_NORMAL) | PTE_FLAGS
-#define IO_MMUFLAGS     PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_XN | PTE_FLAGS
 #else
 #define MM_MMUFLAGS     PMD_ATTRINDX(MT_NORMAL) | PMD_FLAGS
-#define IO_MMUFLAGS     PMD_ATTRINDX(MT_DEVICE_nGnRE) | PMD_SECT_XN | PMD_FLAGS
 #endif
 
 /*
@@ -368,6 +366,7 @@ ENDPROC(__calc_phys_offset)
  *   - identity mapping to enable the MMU (low address, TTBR0)
  *   - first few MB of the kernel linear mapping to jump to once the MMU has
  *     been enabled, including the FDT blob (TTBR1)
+ *   - UART mapping if CONFIG_EARLY_PRINTK is enabled (TTBR1)
  */
 __create_page_tables:
         pgtbl   x25, x26, x24                   // idmap_pg_dir and swapper_pg_dir addresses
@@ -420,6 +419,15 @@ __create_page_tables:
         sub     x6, x6, #1                      // inclusive range
         create_block_map x0, x7, x3, x5, x6
 1:
+#ifdef CONFIG_EARLY_PRINTK
+        /*
+         * Create the pgd entry for the UART mapping. The full mapping is done
+         * later based earlyprintk kernel parameter.
+         */
+        ldr     x5, =EARLYCON_IOBASE            // UART virtual address
+        add     x0, x26, #2 * PAGE_SIZE         // section table address
+        create_pgd_entry x26, x0, x5, x6, x7
+#endif
         ret
 ENDPROC(__create_page_tables)
         .ltorg
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index f7073c7b1ca9..1e49e5eb81e9 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1331,6 +1331,11 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
 {
         struct frame_tail __user *tail;
 
+        if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+                /* We don't support guest os callchain now */
+                return;
+        }
+
         tail = (struct frame_tail __user *)regs->regs[29];
 
         while (entry->nr < PERF_MAX_STACK_DEPTH &&
@@ -1355,8 +1360,40 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 {
         struct stackframe frame;
 
+        if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+                /* We don't support guest os callchain now */
+                return;
+        }
+
         frame.fp = regs->regs[29];
         frame.sp = regs->sp;
         frame.pc = regs->pc;
         walk_stackframe(&frame, callchain_trace, entry);
 }
+
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
+        if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
+                return perf_guest_cbs->get_guest_ip();
+
+        return instruction_pointer(regs);
+}
+
+unsigned long perf_misc_flags(struct pt_regs *regs)
+{
+        int misc = 0;
+
+        if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+                if (perf_guest_cbs->is_user_mode())
+                        misc |= PERF_RECORD_MISC_GUEST_USER;
+                else
+                        misc |= PERF_RECORD_MISC_GUEST_KERNEL;
+        } else {
+                if (user_mode(regs))
+                        misc |= PERF_RECORD_MISC_USER;
+                else
+                        misc |= PERF_RECORD_MISC_KERNEL;
+        }
+
+        return misc;
+}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index c7002d40a9b0..0337cdb0667b 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -45,9 +45,10 @@
 
 #include <asm/compat.h>
 #include <asm/cacheflush.h>
+#include <asm/fpsimd.h>
+#include <asm/mmu_context.h>
 #include <asm/processor.h>
 #include <asm/stacktrace.h>
-#include <asm/fpsimd.h>
 
 static void setup_restart(void)
 {
@@ -314,6 +315,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
         /* the actual thread switch */
         last = cpu_switch_to(prev, next);
 
+        contextidr_thread_switch(next);
         return last;
 }
 
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
new file mode 100644
index 000000000000..14f73c445ff5
--- /dev/null
+++ b/arch/arm64/kernel/psci.c
@@ -0,0 +1,211 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2013 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#define pr_fmt(fmt) "psci: " fmt
+
+#include <linux/init.h>
+#include <linux/of.h>
+
+#include <asm/compiler.h>
+#include <asm/errno.h>
+#include <asm/psci.h>
+
+struct psci_operations psci_ops;
+
+static int (*invoke_psci_fn)(u64, u64, u64, u64);
+
+enum psci_function {
+        PSCI_FN_CPU_SUSPEND,
+        PSCI_FN_CPU_ON,
+        PSCI_FN_CPU_OFF,
+        PSCI_FN_MIGRATE,
+        PSCI_FN_MAX,
+};
+
+static u32 psci_function_id[PSCI_FN_MAX];
+
+#define PSCI_RET_SUCCESS                0
+#define PSCI_RET_EOPNOTSUPP             -1
+#define PSCI_RET_EINVAL                 -2
+#define PSCI_RET_EPERM                  -3
+
+static int psci_to_linux_errno(int errno)
+{
+        switch (errno) {
+        case PSCI_RET_SUCCESS:
+                return 0;
+        case PSCI_RET_EOPNOTSUPP:
+                return -EOPNOTSUPP;
+        case PSCI_RET_EINVAL:
+                return -EINVAL;
+        case PSCI_RET_EPERM:
+                return -EPERM;
+        };
+
+        return -EINVAL;
+}
+
+#define PSCI_POWER_STATE_ID_MASK        0xffff
+#define PSCI_POWER_STATE_ID_SHIFT       0
+#define PSCI_POWER_STATE_TYPE_MASK      0x1
+#define PSCI_POWER_STATE_TYPE_SHIFT     16
+#define PSCI_POWER_STATE_AFFL_MASK      0x3
+#define PSCI_POWER_STATE_AFFL_SHIFT     24
+
+static u32 psci_power_state_pack(struct psci_power_state state)
+{
+        return  ((state.id & PSCI_POWER_STATE_ID_MASK)
+                        << PSCI_POWER_STATE_ID_SHIFT)   |
+                ((state.type & PSCI_POWER_STATE_TYPE_MASK)
+                        << PSCI_POWER_STATE_TYPE_SHIFT) |
+                ((state.affinity_level & PSCI_POWER_STATE_AFFL_MASK)
+                        << PSCI_POWER_STATE_AFFL_SHIFT);
+}
+
+/*
+ * The following two functions are invoked via the invoke_psci_fn pointer
+ * and will not be inlined, allowing us to piggyback on the AAPCS.
+ */
+static noinline int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1,
+                                         u64 arg2)
+{
+        asm volatile(
+                        __asmeq("%0", "x0")
+                        __asmeq("%1", "x1")
+                        __asmeq("%2", "x2")
+                        __asmeq("%3", "x3")
+                        "hvc    #0\n"
+                : "+r" (function_id)
+                : "r" (arg0), "r" (arg1), "r" (arg2));
+
+        return function_id;
+}
+
+static noinline int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1,
+                                         u64 arg2)
+{
+        asm volatile(
+                        __asmeq("%0", "x0")
+                        __asmeq("%1", "x1")
+                        __asmeq("%2", "x2")
+                        __asmeq("%3", "x3")
+                        "smc    #0\n"
+                : "+r" (function_id)
+                : "r" (arg0), "r" (arg1), "r" (arg2));
+
+        return function_id;
+}
+
+static int psci_cpu_suspend(struct psci_power_state state,
+                            unsigned long entry_point)
+{
+        int err;
+        u32 fn, power_state;
+
+        fn = psci_function_id[PSCI_FN_CPU_SUSPEND];
+        power_state = psci_power_state_pack(state);
+        err = invoke_psci_fn(fn, power_state, entry_point, 0);
+        return psci_to_linux_errno(err);
+}
+
+static int psci_cpu_off(struct psci_power_state state)
+{
+        int err;
+        u32 fn, power_state;
+
+        fn = psci_function_id[PSCI_FN_CPU_OFF];
+        power_state = psci_power_state_pack(state);
+        err = invoke_psci_fn(fn, power_state, 0, 0);
+        return psci_to_linux_errno(err);
+}
+
+static int psci_cpu_on(unsigned long cpuid, unsigned long entry_point)
+{
+        int err;
+        u32 fn;
+
+        fn = psci_function_id[PSCI_FN_CPU_ON];
+        err = invoke_psci_fn(fn, cpuid, entry_point, 0);
+        return psci_to_linux_errno(err);
+}
+
+static int psci_migrate(unsigned long cpuid)
+{
+        int err;
+        u32 fn;
+
+        fn = psci_function_id[PSCI_FN_MIGRATE];
+        err = invoke_psci_fn(fn, cpuid, 0, 0);
+        return psci_to_linux_errno(err);
+}
+
+static const struct of_device_id psci_of_match[] __initconst = {
+        { .compatible = "arm,psci",     },
+        {},
+};
+
+int __init psci_init(void)
+{
+        struct device_node *np;
+        const char *method;
+        u32 id;
+        int err = 0;
+
+        np = of_find_matching_node(NULL, psci_of_match);
+        if (!np)
+                return -ENODEV;
+
+        pr_info("probing function IDs from device-tree\n");
+
+        if (of_property_read_string(np, "method", &method)) {
+                pr_warning("missing \"method\" property\n");
+                err = -ENXIO;
+                goto out_put_node;
+        }
+
+        if (!strcmp("hvc", method)) {
+                invoke_psci_fn = __invoke_psci_fn_hvc;
+        } else if (!strcmp("smc", method)) {
+                invoke_psci_fn = __invoke_psci_fn_smc;
+        } else {
+                pr_warning("invalid \"method\" property: %s\n", method);
+                err = -EINVAL;
+                goto out_put_node;
+        }
+
+        if (!of_property_read_u32(np, "cpu_suspend", &id)) {
+                psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
+                psci_ops.cpu_suspend = psci_cpu_suspend;
+        }
+
+        if (!of_property_read_u32(np, "cpu_off", &id)) {
+                psci_function_id[PSCI_FN_CPU_OFF] = id;
+                psci_ops.cpu_off = psci_cpu_off;
+        }
+
+        if (!of_property_read_u32(np, "cpu_on", &id)) {
+                psci_function_id[PSCI_FN_CPU_ON] = id;
+                psci_ops.cpu_on = psci_cpu_on;
+        }
+
+        if (!of_property_read_u32(np, "migrate", &id)) {
+                psci_function_id[PSCI_FN_MIGRATE] = id;
+                psci_ops.migrate = psci_migrate;
+        }
+
+out_put_node:
+        of_node_put(np);
+        return err;
+}
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 7665a9bfdb1e..113db863f832 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -39,6 +39,7 @@
 #include <linux/proc_fs.h>
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
+#include <linux/of_platform.h>
 
 #include <asm/cputype.h>
 #include <asm/elf.h>
@@ -49,6 +50,7 @@
 #include <asm/tlbflush.h>
 #include <asm/traps.h>
 #include <asm/memblock.h>
+#include <asm/psci.h>
 
 unsigned int processor_id;
 EXPORT_SYMBOL(processor_id);
@@ -260,6 +262,8 @@ void __init setup_arch(char **cmdline_p)
 
         unflatten_device_tree();
 
+        psci_init();
+
 #ifdef CONFIG_SMP
         smp_init_cpus();
 #endif
@@ -289,6 +293,13 @@ static int __init topology_init(void)
 }
 subsys_initcall(topology_init);
 
+static int __init arm64_device_probe(void)
+{
+        of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+        return 0;
+}
+device_initcall(arm64_device_probe);
+
 static const char *hwcap_str[] = {
         "fp",
         "asimd",
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index a4db3d22aac4..41db148a7eb9 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -76,7 +76,7 @@ struct compat_sigcontext {
 
 struct compat_ucontext {
         compat_ulong_t                  uc_flags;
-        struct compat_ucontext          *uc_link;
+        compat_uptr_t                   uc_link;
         compat_stack_t                  uc_stack;
         struct compat_sigcontext        uc_mcontext;
         compat_sigset_t                 uc_sigmask;
@@ -703,7 +703,7 @@ int compat_setup_rt_frame(int usig, struct k_sigaction *ka, siginfo_t *info,
         err |= copy_siginfo_to_user32(&frame->info, info);
 
         __put_user_error(0, &frame->sig.uc.uc_flags, err);
-        __put_user_error(NULL, &frame->sig.uc.uc_link, err);
+        __put_user_error(0, &frame->sig.uc.uc_link, err);
 
         memset(&stack, 0, sizeof(stack));
         stack.ss_sp = (compat_uptr_t)current->sas_ss_sp;
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 538300f2273d..bdd34597254b 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -233,7 +233,28 @@ void __init smp_prepare_boot_cpu(void)
 }
 
 static void (*smp_cross_call)(const struct cpumask *, unsigned int);
-static phys_addr_t cpu_release_addr[NR_CPUS];
+
+static const struct smp_enable_ops *enable_ops[] __initconst = {
+        &smp_spin_table_ops,
+        &smp_psci_ops,
+        NULL,
+};
+
+static const struct smp_enable_ops *smp_enable_ops[NR_CPUS];
+
+static const struct smp_enable_ops * __init smp_get_enable_ops(const char *name)
+{
+        const struct smp_enable_ops *ops = enable_ops[0];
+
+        while (ops) {
+                if (!strcmp(name, ops->name))
+                        return ops;
+
+                ops++;
+        }
+
+        return NULL;
+}
 
 /*
  * Enumerate the possible CPU set from the device tree.
@@ -252,22 +273,22 @@ void __init smp_init_cpus(void)
                  * We currently support only the "spin-table" enable-method.
                  */
                 enable_method = of_get_property(dn, "enable-method", NULL);
-                if (!enable_method || strcmp(enable_method, "spin-table")) {
-                        pr_err("CPU %d: missing or invalid enable-method property: %s\n",
-                               cpu, enable_method);
+                if (!enable_method) {
+                        pr_err("CPU %d: missing enable-method property\n", cpu);
                         goto next;
                 }
 
-                /*
-                 * Determine the address from which the CPU is polling.
-                 */
-                if (of_property_read_u64(dn, "cpu-release-addr",
-                                         &cpu_release_addr[cpu])) {
-                        pr_err("CPU %d: missing or invalid cpu-release-addr property\n",
-                               cpu);
+                smp_enable_ops[cpu] = smp_get_enable_ops(enable_method);
+
+                if (!smp_enable_ops[cpu]) {
+                        pr_err("CPU %d: invalid enable-method property: %s\n",
+                               cpu, enable_method);
                         goto next;
                 }
 
+                if (smp_enable_ops[cpu]->init_cpu(dn, cpu))
+                        goto next;
+
                 set_cpu_possible(cpu, true);
 next:
                 cpu++;
@@ -281,8 +302,7 @@ next:
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-        int cpu;
-        void **release_addr;
+        int cpu, err;
         unsigned int ncores = num_possible_cpus();
 
         /*
@@ -291,30 +311,35 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
         if (max_cpus > ncores)
                 max_cpus = ncores;
 
+        /* Don't bother if we're effectively UP */
+        if (max_cpus <= 1)
+                return;
+
         /*
          * Initialise the present map (which describes the set of CPUs
          * actually populated at the present time) and release the
          * secondaries from the bootloader.
+         *
+         * Make sure we online at most (max_cpus - 1) additional CPUs.
          */
+        max_cpus--;
         for_each_possible_cpu(cpu) {
                 if (max_cpus == 0)
                         break;
 
-                if (!cpu_release_addr[cpu])
+                if (cpu == smp_processor_id())
+                        continue;
+
+                if (!smp_enable_ops[cpu])
                         continue;
 
-                release_addr = __va(cpu_release_addr[cpu]);
-                release_addr[0] = (void *)__pa(secondary_holding_pen);
-                __flush_dcache_area(release_addr, sizeof(release_addr[0]));
+                err = smp_enable_ops[cpu]->prepare_cpu(cpu);
+                if (err)
+                        continue;
 
                 set_cpu_present(cpu, true);
                 max_cpus--;
         }
-
-        /*
-         * Send an event to wake up the secondaries.
-         */
-        sev();
 }
 
 
diff --git a/arch/arm64/kernel/smp_psci.c b/arch/arm64/kernel/smp_psci.c
new file mode 100644
index 000000000000..112091684c22
--- /dev/null
+++ b/arch/arm64/kernel/smp_psci.c
@@ -0,0 +1,52 @@
+/*
+ * PSCI SMP initialisation
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/smp.h>
+
+#include <asm/psci.h>
+
+static int __init smp_psci_init_cpu(struct device_node *dn, int cpu)
+{
+        return 0;
+}
+
+static int __init smp_psci_prepare_cpu(int cpu)
+{
+        int err;
+
+        if (!psci_ops.cpu_on) {
+                pr_err("psci: no cpu_on method, not booting CPU%d\n", cpu);
+                return -ENODEV;
+        }
+
+        err = psci_ops.cpu_on(cpu, __pa(secondary_holding_pen));
+        if (err) {
+                pr_err("psci: failed to boot CPU%d (%d)\n", cpu, err);
+                return err;
+        }
+
+        return 0;
+}
+
+const struct smp_enable_ops smp_psci_ops __initconst = {
+        .name           = "psci",
+        .init_cpu       = smp_psci_init_cpu,
+        .prepare_cpu    = smp_psci_prepare_cpu,
+};
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
new file mode 100644
index 000000000000..7c35fa682f76
--- /dev/null
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -0,0 +1,66 @@
+/*
+ * Spin Table SMP initialisation
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/smp.h>
+
+#include <asm/cacheflush.h>
+
+static phys_addr_t cpu_release_addr[NR_CPUS];
+
+static int __init smp_spin_table_init_cpu(struct device_node *dn, int cpu)
+{
+        /*
+         * Determine the address from which the CPU is polling.
+         */
+        if (of_property_read_u64(dn, "cpu-release-addr",
+                                 &cpu_release_addr[cpu])) {
+                pr_err("CPU %d: missing or invalid cpu-release-addr property\n",
+                       cpu);
+
+                return -1;
+        }
+
+        return 0;
+}
+
+static int __init smp_spin_table_prepare_cpu(int cpu)
+{
+        void **release_addr;
+
+        if (!cpu_release_addr[cpu])
+                return -ENODEV;
+
+        release_addr = __va(cpu_release_addr[cpu]);
+        release_addr[0] = (void *)__pa(secondary_holding_pen);
+        __flush_dcache_area(release_addr, sizeof(release_addr[0]));
+
+        /*
+         * Send an event to wake up the secondary CPU.
+         */
+        sev();
+
+        return 0;
+}
+
+const struct smp_enable_ops smp_spin_table_ops __initconst = {
+        .name           = "spin-table",
+        .init_cpu       = smp_spin_table_init_cpu,
+        .prepare_cpu    = smp_spin_table_prepare_cpu,
+};
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index a6885d896ab6..f4dd585898c5 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -25,6 +25,7 @@
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
 #include <linux/fs.h>
+#include <linux/io.h>
 
 #include <asm/cputype.h>
 #include <asm/sections.h>
@@ -251,6 +252,47 @@ static void __init create_mapping(phys_addr_t phys, unsigned long virt,
         } while (pgd++, addr = next, addr != end);
 }
 
+#ifdef CONFIG_EARLY_PRINTK
+/*
+ * Create an early I/O mapping using the pgd/pmd entries already populated
+ * in head.S as this function is called too early to allocated any memory. The
+ * mapping size is 2MB with 4KB pages or 64KB or 64KB pages.
+ */
+void __iomem * __init early_io_map(phys_addr_t phys, unsigned long virt)
+{
+        unsigned long size, mask;
+        bool page64k = IS_ENABLED(ARM64_64K_PAGES);
+        pgd_t *pgd;
+        pud_t *pud;
+        pmd_t *pmd;
+        pte_t *pte;
+
+        /*
+         * No early pte entries with !ARM64_64K_PAGES configuration, so using
+         * sections (pmd).
+         */
+        size = page64k ? PAGE_SIZE : SECTION_SIZE;
+        mask = ~(size - 1);
+
+        pgd = pgd_offset_k(virt);
+        pud = pud_offset(pgd, virt);
+        if (pud_none(*pud))
+                return NULL;
+        pmd = pmd_offset(pud, virt);
+
+        if (page64k) {
+                if (pmd_none(*pmd))
+                        return NULL;
+                pte = pte_offset_kernel(pmd, virt);
+                set_pte(pte, __pte((phys & mask) | PROT_DEVICE_nGnRE));
+        } else {
+                set_pmd(pmd, __pmd((phys & mask) | PROT_SECT_DEVICE_nGnRE));
+        }
+
+        return (void __iomem *)((virt & mask) + (phys & ~mask));
+}
+#endif
+
 static void __init map_mem(void)
 {
         struct memblock_region *reg;