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

Pull ARM64 update from Catalin Marinas:
 - User tagged pointers support (top 8-bit of user pointers
   automatically ignored by the CPU).
 - Kernel mode NEON (no users for arm64 yet but work in progress).
 - arm64 kernel Image header extended to accommodate future EFI stub.
 - Remove BogoMIPS reporting (not relevant, it's just the timer
   frequency).
 - Clean-up (EM_AARCH64/EM_ARM to elf-em.h, ELF notes in read-only
   segment, unused variable).
 - Bug-fixes (RAM boundaries not 2MB aligned, perf, includes).

* tag 'arm64-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-aarch64:
  Documentation/arm64: clarify requirements for DTB placement
  arm64: mm: permit use of tagged pointers at EL0
  Move the EM_ARM and EM_AARCH64 definitions to uapi/linux/elf-em.h
  arm64: Remove unused cpu_name ascii in arch/arm64/mm/proc.S
  arm64: delay: don't bother reporting bogomips in /proc/cpuinfo
  arm64: Fix mapping of memory banks not ending on a PMD_SIZE boundary
  arm64: move elf notes into readonly segment
  arm64: Enable interrupts in the EL0 undef handler
  arm64: Expand arm64 image header
  ARM64: include: asm: include "asm/types.h" in "pgtable-2level-types.h" and "pgtable-3level-types.h"
  arm64: add support for kernel mode NEON
  arm64: perf: fix ARMv8 EVTYPE_MASK to include NSH bit
  arm64: perf: fix group validation when using enable_on_exec

19 files changed, 142 insertions, 30 deletions

diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt
index 9c4d388daddc..98df4a03807e 100644
--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -45,9 +45,9 @@ sees fit.)
 
 Requirement: MANDATORY
 
-The device tree blob (dtb) must be no bigger than 2 megabytes in size
-and placed at a 2-megabyte boundary within the first 512 megabytes from
-the start of the kernel image. This is to allow the kernel to map the
+The device tree blob (dtb) must be placed on an 8-byte boundary within
+the first 512 megabytes from the start of the kernel image and must not
+cross a 2-megabyte boundary. This is to allow the kernel to map the
 blob using a single section mapping in the initial page tables.
 
 
@@ -68,13 +68,23 @@ Image target is available instead.
 
 Requirement: MANDATORY
 
-The decompressed kernel image contains a 32-byte header as follows:
+The decompressed kernel image contains a 64-byte header as follows:
 
-  u32 magic     = 0x14000008;   /* branch to stext, little-endian */
-  u32 res0      = 0;            /* reserved */
+  u32 code0;                    /* Executable code */
+  u32 code1;                    /* Executable code */
   u64 text_offset;              /* Image load offset */
+  u64 res0      = 0;            /* reserved */
   u64 res1      = 0;            /* reserved */
   u64 res2      = 0;            /* reserved */
+  u64 res3      = 0;            /* reserved */
+  u64 res4      = 0;            /* reserved */
+  u32 magic     = 0x644d5241;   /* Magic number, little endian, "ARM\x64" */
+  u32 res5 = 0;                 /* reserved */
+
+
+Header notes:
+
+- code0/code1 are responsible for branching to stext.
 
 The image must be placed at the specified offset (currently 0x80000)
 from the start of the system RAM and called there. The start of the
diff --git a/Documentation/arm64/tagged-pointers.txt b/Documentation/arm64/tagged-pointers.txt
new file mode 100644
index 000000000000..264e9841563a
--- /dev/null
+++ b/Documentation/arm64/tagged-pointers.txt
@@ -0,0 +1,34 @@
+                Tagged virtual addresses in AArch64 Linux
+                =========================================
+
+Author: Will Deacon <will.deacon@arm.com>
+Date  : 12 June 2013
+
+This document briefly describes the provision of tagged virtual
+addresses in the AArch64 translation system and their potential uses
+in AArch64 Linux.
+
+The kernel configures the translation tables so that translations made
+via TTBR0 (i.e. userspace mappings) have the top byte (bits 63:56) of
+the virtual address ignored by the translation hardware. This frees up
+this byte for application use, with the following caveats:
+
+        (1) The kernel requires that all user addresses passed to EL1
+            are tagged with tag 0x00. This means that any syscall
+            parameters containing user virtual addresses *must* have
+            their top byte cleared before trapping to the kernel.
+
+        (2) Tags are not guaranteed to be preserved when delivering
+            signals. This means that signal handlers in applications
+            making use of tags cannot rely on the tag information for
+            user virtual addresses being maintained for fields inside
+            siginfo_t. One exception to this rule is for signals raised
+            in response to debug exceptions, where the tag information
+            will be preserved.
+
+        (3) Special care should be taken when using tagged pointers,
+            since it is likely that C compilers will not hazard two
+            addresses differing only in the upper bits.
+
+The architecture prevents the use of a tagged PC, so the upper byte will
+be set to a sign-extension of bit 55 on exception return.
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 56211f2084ef..f4b46d39b9cf 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -19,8 +19,6 @@ typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 
 typedef struct user_fp elf_fpregset_t;
 
-#define EM_ARM  40
-
 #define EF_ARM_EABI_MASK        0xff000000
 #define EF_ARM_EABI_UNKNOWN     0x00000000
 #define EF_ARM_EABI_VER1        0x01000000
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 9737e97f9f38..ae323a45c28c 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -96,6 +96,9 @@ config SWIOTLB
 config IOMMU_HELPER
         def_bool SWIOTLB
 
+config KERNEL_MODE_NEON
+        def_bool y
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index fe32c0e4ac01..e7fa87f9201b 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -33,8 +33,6 @@ typedef unsigned long elf_greg_t;
 typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 typedef struct user_fpsimd_state elf_fpregset_t;
 
-#define EM_AARCH64              183
-
 /*
  * AArch64 static relocation types.
  */
@@ -151,7 +149,6 @@ extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
 #ifdef CONFIG_COMPAT
-#define EM_ARM                          40
 #define COMPAT_ELF_PLATFORM             ("v8l")
 
 #define COMPAT_ELF_ET_DYN_BASE          (randomize_et_dyn(2 * TASK_SIZE_32 / 3))
diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h
new file mode 100644
index 000000000000..b0cc58a97780
--- /dev/null
+++ b/arch/arm64/include/asm/neon.h
@@ -0,0 +1,14 @@
+/*
+ * linux/arch/arm64/include/asm/neon.h
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#define cpu_has_neon()          (1)
+
+void kernel_neon_begin(void);
+void kernel_neon_end(void);
diff --git a/arch/arm64/include/asm/pgtable-2level-types.h b/arch/arm64/include/asm/pgtable-2level-types.h
index 3c3ca7d361e4..5f101e63dfc1 100644
--- a/arch/arm64/include/asm/pgtable-2level-types.h
+++ b/arch/arm64/include/asm/pgtable-2level-types.h
@@ -16,6 +16,8 @@
 #ifndef __ASM_PGTABLE_2LEVEL_TYPES_H
 #define __ASM_PGTABLE_2LEVEL_TYPES_H
 
+#include <asm/types.h>
+
 typedef u64 pteval_t;
 typedef u64 pgdval_t;
 typedef pgdval_t pmdval_t;
diff --git a/arch/arm64/include/asm/pgtable-3level-types.h b/arch/arm64/include/asm/pgtable-3level-types.h
index 4489615f14a9..4e94424938a4 100644
--- a/arch/arm64/include/asm/pgtable-3level-types.h
+++ b/arch/arm64/include/asm/pgtable-3level-types.h
@@ -16,6 +16,8 @@
 #ifndef __ASM_PGTABLE_3LEVEL_TYPES_H
 #define __ASM_PGTABLE_3LEVEL_TYPES_H
 
+#include <asm/types.h>
+
 typedef u64 pteval_t;
 typedef u64 pmdval_t;
 typedef u64 pgdval_t;
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index e182a356c979..d57e66845c86 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -122,5 +122,6 @@
 #define TCR_TG1_64K             (UL(1) << 30)
 #define TCR_IPS_40BIT           (UL(2) << 32)
 #define TCR_ASID16              (UL(1) << 36)
+#define TCR_TBI0                (UL(1) << 37)
 
 #endif
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 6ad781b21c08..3881fd115ebb 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -423,6 +423,7 @@ el0_da:
          * Data abort handling
          */
         mrs     x0, far_el1
+        bic     x0, x0, #(0xff << 56)
         disable_step x1
         isb
         enable_dbg
@@ -476,6 +477,8 @@ el0_undef:
          * Undefined instruction
          */
         mov     x0, sp
+        // enable interrupts before calling the main handler
+        enable_irq
         b       do_undefinstr
 el0_dbg:
         /*
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index e8b8357aedb4..1f2e4d5a5c0f 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/signal.h>
+#include <linux/hardirq.h>
 
 #include <asm/fpsimd.h>
 #include <asm/cputype.h>
@@ -83,6 +84,33 @@ void fpsimd_flush_thread(void)
         fpsimd_load_state(&current->thread.fpsimd_state);
 }
 
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+/*
+ * Kernel-side NEON support functions
+ */
+void kernel_neon_begin(void)
+{
+        /* Avoid using the NEON in interrupt context */
+        BUG_ON(in_interrupt());
+        preempt_disable();
+
+        if (current->mm)
+                fpsimd_save_state(&current->thread.fpsimd_state);
+}
+EXPORT_SYMBOL(kernel_neon_begin);
+
+void kernel_neon_end(void)
+{
+        if (current->mm)
+                fpsimd_load_state(&current->thread.fpsimd_state);
+
+        preempt_enable();
+}
+EXPORT_SYMBOL(kernel_neon_end);
+
+#endif /* CONFIG_KERNEL_MODE_NEON */
+
 /*
  * FP/SIMD support code initialisation.
  */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 53dcae49e729..7090c126797c 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -112,6 +112,14 @@
         .quad   TEXT_OFFSET                     // Image load offset from start of RAM
         .quad   0                               // reserved
         .quad   0                               // reserved
+        .quad   0                               // reserved
+        .quad   0                               // reserved
+        .quad   0                               // reserved
+        .byte   0x41                            // Magic number, "ARM\x64"
+        .byte   0x52
+        .byte   0x4d
+        .byte   0x64
+        .word   0                               // reserved
 
 ENTRY(stext)
         mov     x21, x0                         // x21=FDT
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 12e6ccb88691..cea1594ff933 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -325,7 +325,10 @@ validate_event(struct pmu_hw_events *hw_events,
         if (is_software_event(event))
                 return 1;
 
-        if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
+        if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
+                return 1;
+
+        if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
                 return 1;
 
         return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
@@ -781,7 +784,7 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 /*
  * PMXEVTYPER: Event selection reg
  */
-#define ARMV8_EVTYPE_MASK       0xc00000ff      /* Mask for writable bits */
+#define ARMV8_EVTYPE_MASK       0xc80000ff      /* Mask for writable bits */
 #define ARMV8_EVTYPE_EVENT      0xff            /* Mask for EVENT bits */
 
 /*
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index add6ea616843..bca4c1c2052a 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -328,9 +328,6 @@ static int c_show(struct seq_file *m, void *v)
 #ifdef CONFIG_SMP
                 seq_printf(m, "processor\t: %d\n", i);
 #endif
-                seq_printf(m, "BogoMIPS\t: %lu.%02lu\n\n",
-                           loops_per_jiffy / (500000UL/HZ),
-                           loops_per_jiffy / (5000UL/HZ) % 100);
         }
 
         /* dump out the processor features */
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index fee5cce83450..78db90dcc910 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -223,11 +223,7 @@ asmlinkage void secondary_start_kernel(void)
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-        unsigned long bogosum = loops_per_jiffy * num_online_cpus();
-
-        pr_info("SMP: Total of %d processors activated (%lu.%02lu BogoMIPS).\n",
-                num_online_cpus(), bogosum / (500000/HZ),
-                (bogosum / (5000/HZ)) % 100);
+        pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
 }
 
 void __init smp_prepare_boot_cpu(void)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index f5e55747242f..f8ab9d8e2ea3 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -71,6 +71,7 @@ SECTIONS
 
         RO_DATA(PAGE_SIZE)
         EXCEPTION_TABLE(8)
+        NOTES
         _etext = .;                     /* End of text and rodata section */
 
         . = ALIGN(PAGE_SIZE);
@@ -122,8 +123,6 @@ SECTIONS
         }
         _edata_loc = __data_loc + SIZEOF(.data);
 
-        NOTES
-
         BSS_SECTION(0, 0, 0)
         _end = .;
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index a8d1059b91b2..f557ebbe7013 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -296,6 +296,7 @@ void __iomem * __init early_io_map(phys_addr_t phys, unsigned long virt)
 static void __init map_mem(void)
 {
         struct memblock_region *reg;
+        phys_addr_t limit;
 
         /*
          * Temporarily limit the memblock range. We need to do this as
@@ -303,9 +304,11 @@ static void __init map_mem(void)
          * memory addressable from the initial direct kernel mapping.
          *
          * The initial direct kernel mapping, located at swapper_pg_dir,
-         * gives us PGDIR_SIZE memory starting from PHYS_OFFSET (aligned).
+         * gives us PGDIR_SIZE memory starting from PHYS_OFFSET (which must be
+         * aligned to 2MB as per Documentation/arm64/booting.txt).
          */
-        memblock_set_current_limit((PHYS_OFFSET & PGDIR_MASK) + PGDIR_SIZE);
+        limit = PHYS_OFFSET + PGDIR_SIZE;
+        memblock_set_current_limit(limit);
 
         /* map all the memory banks */
         for_each_memblock(memory, reg) {
@@ -315,6 +318,22 @@ static void __init map_mem(void)
                 if (start >= end)
                         break;
 
+#ifndef CONFIG_ARM64_64K_PAGES
+                /*
+                 * For the first memory bank align the start address and
+                 * current memblock limit to prevent create_mapping() from
+                 * allocating pte page tables from unmapped memory.
+                 * When 64K pages are enabled, the pte page table for the
+                 * first PGDIR_SIZE is already present in swapper_pg_dir.
+                 */
+                if (start < limit)
+                        start = ALIGN(start, PMD_SIZE);
+                if (end < limit) {
+                        limit = end & PMD_MASK;
+                        memblock_set_current_limit(limit);
+                }
+#endif
+
                 create_mapping(start, __phys_to_virt(start), end - start);
         }
 
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index a82ae8868077..b1b31bbc967b 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -95,10 +95,6 @@ ENTRY(cpu_do_switch_mm)
         ret
 ENDPROC(cpu_do_switch_mm)
 
-cpu_name:
-        .ascii  "AArch64 Processor"
-        .align
-
         .section ".text.init", #alloc, #execinstr
 
 /*
@@ -151,7 +147,7 @@ ENTRY(__cpu_setup)
          * both user and kernel.
          */
         ldr     x10, =TCR_TxSZ(VA_BITS) | TCR_FLAGS | TCR_IPS_40BIT | \
-                      TCR_ASID16 | (1 << 31)
+                      TCR_ASID16 | TCR_TBI0 | (1 << 31)
 #ifdef CONFIG_ARM64_64K_PAGES
         orr     x10, x10, TCR_TG0_64K
         orr     x10, x10, TCR_TG1_64K
diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h
index 8e2b7bac4378..59c17a2d38ad 100644
--- a/include/uapi/linux/elf-em.h
+++ b/include/uapi/linux/elf-em.h
@@ -22,6 +22,7 @@
 #define EM_PPC          20      /* PowerPC */
 #define EM_PPC64        21       /* PowerPC64 */
 #define EM_SPU          23      /* Cell BE SPU */
+#define EM_ARM          40      /* ARM 32 bit */
 #define EM_SH           42      /* SuperH */
 #define EM_SPARCV9      43      /* SPARC v9 64-bit */
 #define EM_IA_64        50      /* HP/Intel IA-64 */
@@ -34,6 +35,7 @@
 #define EM_MN10300      89      /* Panasonic/MEI MN10300, AM33 */
 #define EM_BLACKFIN     106     /* ADI Blackfin Processor */
 #define EM_TI_C6000     140     /* TI C6X DSPs */
+#define EM_AARCH64      183     /* ARM 64 bit */
 #define EM_FRV          0x5441  /* Fujitsu FR-V */
 #define EM_AVR32        0x18ad  /* Atmel AVR32 */