Merge branch 'for-next/late-arrivals' into for-next/core

Late patches for 5.10: MTE selftests, minor KCSAN preparation and removal
of some unused prototypes.

(Amit Daniel Kachhap and others)
* for-next/late-arrivals:
  arm64: random: Remove no longer needed prototypes
  arm64: initialize per-cpu offsets earlier
  kselftest/arm64: Check mte tagged user address in kernel
  kselftest/arm64: Verify KSM page merge for MTE pages
  kselftest/arm64: Verify all different mmap MTE options
  kselftest/arm64: Check forked child mte memory accessibility
  kselftest/arm64: Verify mte tag inclusion via prctl
  kselftest/arm64: Add utilities and a test to validate mte memory

3 files changed, 17 insertions, 11 deletions

diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index d8d9caf02834..e28c9d4e5278 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -448,6 +448,8 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 	bl	__pi_memset
 	dsb	ishst				// Make zero page visible to PTW
 
+	bl	init_this_cpu_offset
+
 #ifdef CONFIG_KASAN
 	bl	kasan_early_init
 #endif
@@ -754,6 +756,7 @@ SYM_FUNC_START_LOCAL(__secondary_switched)
 	ptrauth_keys_init_cpu x2, x3, x4, x5
 #endif
 
+	bl	init_this_cpu_offset
 	b	secondary_start_kernel
 SYM_FUNC_END(__secondary_switched)
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 77c4c9bad1b8..005171972764 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -87,12 +87,6 @@ void __init smp_setup_processor_id(void)
 	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
 	set_cpu_logical_map(0, mpidr);
 
-	/*
-	 * clear __my_cpu_offset on boot CPU to avoid hang caused by
-	 * using percpu variable early, for example, lockdep will
-	 * access percpu variable inside lock_release
-	 */
-	set_my_cpu_offset(0);
 	pr_info("Booting Linux on physical CPU 0x%010lx [0x%08x]\n",
 		(unsigned long)mpidr, read_cpuid_id());
 }
@@ -282,6 +276,12 @@ u64 cpu_logical_map(int cpu)
 }
 EXPORT_SYMBOL_GPL(cpu_logical_map);
 
+void noinstr init_this_cpu_offset(void)
+{
+	unsigned int cpu = task_cpu(current);
+	set_my_cpu_offset(per_cpu_offset(cpu));
+}
+
 void __init __no_sanitize_address setup_arch(char **cmdline_p)
 {
 	init_mm.start_code = (unsigned long) _text;
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 355ee9eed4dd..7714310fba22 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -192,10 +192,7 @@ asmlinkage notrace void secondary_start_kernel(void)
 	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
 	struct mm_struct *mm = &init_mm;
 	const struct cpu_operations *ops;
-	unsigned int cpu;
-
-	cpu = task_cpu(current);
-	set_my_cpu_offset(per_cpu_offset(cpu));
+	unsigned int cpu = smp_processor_id();
 
 	/*
 	 * All kernel threads share the same mm context; grab a
@@ -435,7 +432,13 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
 void __init smp_prepare_boot_cpu(void)
 {
-	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+	/*
+	 * Now that setup_per_cpu_areas() has allocated the runtime per-cpu
+	 * areas it is only safe to read the CPU0 boot-time area, and we must
+	 * reinitialize the offset to point to the runtime area.
+	 */
+	init_this_cpu_offset();
+
 	cpuinfo_store_boot_cpu();
 
 	/*