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

7 files changed, 46 insertions, 12 deletions

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 6ad781b..3881fd1 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 e8b8357..1f2e4d5 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 53dcae4..7090c12 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 12e6ccb..cea1594 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 add6ea6..bca4c1c 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 fee5cce..78db90d 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 f5e5574..f8ab9d8 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 = .;