Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - MTE asynchronous support for KASan. Previously only synchronous
   (slower) mode was supported. Asynchronous is faster but does not
   allow precise identification of the illegal access.

 - Run kernel mode SIMD with softirqs disabled. This allows using NEON
   in softirq context for crypto performance improvements. The
   conditional yield support is modified to take softirqs into account
   and reduce the latency.

 - Preparatory patches for Apple M1: handle CPUs that only have the VHE
   mode available (host kernel running at EL2), add FIQ support.

 - arm64 perf updates: support for HiSilicon PA and SLLC PMU drivers,
   new functions for the HiSilicon HHA and L3C PMU, cleanups.

 - Re-introduce support for execute-only user permissions but only when
   the EPAN (Enhanced Privileged Access Never) architecture feature is
   available.

 - Disable fine-grained traps at boot and improve the documented boot
   requirements.

 - Support CONFIG_KASAN_VMALLOC on arm64 (only with KASAN_GENERIC).

 - Add hierarchical eXecute Never permissions for all page tables.

 - Add arm64 prctl(PR_PAC_{SET,GET}_ENABLED_KEYS) allowing user programs
   to control which PAC keys are enabled in a particular task.

 - arm64 kselftests for BTI and some improvements to the MTE tests.

 - Minor improvements to the compat vdso and sigpage.

 - Miscellaneous cleanups.

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (86 commits)
  arm64/sve: Add compile time checks for SVE hooks in generic functions
  arm64/kernel/probes: Use BUG_ON instead of if condition followed by BUG.
  arm64: pac: Optimize kernel entry/exit key installation code paths
  arm64: Introduce prctl(PR_PAC_{SET,GET}_ENABLED_KEYS)
  arm64: mte: make the per-task SCTLR_EL1 field usable elsewhere
  arm64/sve: Remove redundant system_supports_sve() tests
  arm64: fpsimd: run kernel mode NEON with softirqs disabled
  arm64: assembler: introduce wxN aliases for wN registers
  arm64: assembler: remove conditional NEON yield macros
  kasan, arm64: tests supports for HW_TAGS async mode
  arm64: mte: Report async tag faults before suspend
  arm64: mte: Enable async tag check fault
  arm64: mte: Conditionally compile mte_enable_kernel_*()
  arm64: mte: Enable TCO in functions that can read beyond buffer limits
  kasan: Add report for async mode
  arm64: mte: Drop arch_enable_tagging()
  kasan: Add KASAN mode kernel parameter
  arm64: mte: Add asynchronous mode support
  arm64: Get rid of CONFIG_ARM64_VHE
  arm64: Cope with CPUs stuck in VHE mode
  ...

1 files changed, 32 insertions, 3 deletions

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 6e60aa3b5ea9..cbf52109583b 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -86,7 +86,7 @@ static void noinstr __cpu_do_idle_irqprio(void)
 	unsigned long daif_bits;
 
 	daif_bits = read_sysreg(daif);
-	write_sysreg(daif_bits | PSR_I_BIT, daif);
+	write_sysreg(daif_bits | PSR_I_BIT | PSR_F_BIT, daif);
 
 	/*
 	 * Unmask PMR before going idle to make sure interrupts can
@@ -341,7 +341,6 @@ void flush_thread(void)
 	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
 	flush_tagged_addr_state();
-	flush_mte_state();
 }
 
 void release_thread(struct task_struct *dead_task)
@@ -531,6 +530,31 @@ static void erratum_1418040_thread_switch(struct task_struct *prev,
 	write_sysreg(val, cntkctl_el1);
 }
 
+static void update_sctlr_el1(u64 sctlr)
+{
+	/*
+	 * EnIA must not be cleared while in the kernel as this is necessary for
+	 * in-kernel PAC. It will be cleared on kernel exit if needed.
+	 */
+	sysreg_clear_set(sctlr_el1, SCTLR_USER_MASK & ~SCTLR_ELx_ENIA, sctlr);
+
+	/* ISB required for the kernel uaccess routines when setting TCF0. */
+	isb();
+}
+
+void set_task_sctlr_el1(u64 sctlr)
+{
+	/*
+	 * __switch_to() checks current->thread.sctlr as an
+	 * optimisation. Disable preemption so that it does not see
+	 * the variable update before the SCTLR_EL1 one.
+	 */
+	preempt_disable();
+	current->thread.sctlr_user = sctlr;
+	update_sctlr_el1(sctlr);
+	preempt_enable();
+}
+
 /*
  * Thread switching.
  */
@@ -546,6 +570,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	entry_task_switch(next);
 	ssbs_thread_switch(next);
 	erratum_1418040_thread_switch(prev, next);
+	ptrauth_thread_switch_user(next);
 
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
@@ -561,6 +586,9 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	 * registers.
 	 */
 	mte_thread_switch(next);
+	/* avoid expensive SCTLR_EL1 accesses if no change */
+	if (prev->thread.sctlr_user != next->thread.sctlr_user)
+		update_sctlr_el1(next->thread.sctlr_user);
 
 	/* the actual thread switch */
 	last = cpu_switch_to(prev, next);
@@ -610,7 +638,8 @@ void arch_setup_new_exec(void)
 {
 	current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0;
 
-	ptrauth_thread_init_user(current);
+	ptrauth_thread_init_user();
+	mte_thread_init_user();
 
 	if (task_spec_ssb_noexec(current)) {
 		arch_prctl_spec_ctrl_set(current, PR_SPEC_STORE_BYPASS,