[PATCH v5 2/2] arm64: mte: avoid clearing PSTATE.TCO on entry unless necessary

[Peter Collingbourne]

On some microarchitectures, clearing PSTATE.TCO is expensive. Clearing
TCO is only necessary if in-kernel MTE is enabled, or if MTE is
enabled in the userspace process in synchronous (or, soon, asymmetric)
mode, because we do not report uaccess faults to userspace in none
or asynchronous modes. Therefore, adjust the kernel entry code to
clear TCO only if necessary.

Because it is now possible to switch to a task in which TCO needs to
be clear from a task in which TCO is set, we also need to do the same
thing on task switch.

Signed-off-by: Peter Collingbourne <pcc at google.com>
Link: https://linux-review.googlesource.com/id/I52d82a580bd0500d420be501af2c35fa8c90729e
Reviewed-by: Catalin Marinas <catalin.marinas at arm.com>
---
v5:
- fix header circular dependency with KASAN_GENERIC/KASAN_SW_TAGS
  enabled with a dependent patch

v4:
- some changes suggested by Catalin

v3:
- switch to a C implementation

v2:
- do the same thing in cpu_switch_to()

 arch/arm64/include/asm/mte.h     | 22 ++++++++++++++++++++++
 arch/arm64/kernel/entry-common.c |  3 +++
 arch/arm64/kernel/entry.S        |  7 -------
 arch/arm64/kernel/mte.c          |  3 +++
 4 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
index 075539f5f1c8..adcb937342f1 100644
--- a/arch/arm64/include/asm/mte.h
+++ b/arch/arm64/include/asm/mte.h
@@ -11,7 +11,9 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/bitfield.h>
+#include <linux/kasan-enabled.h>
 #include <linux/page-flags.h>
+#include <linux/sched.h>
 #include <linux/types.h>
 
 #include <asm/pgtable-types.h>
@@ -86,6 +88,26 @@ static inline int mte_ptrace_copy_tags(struct task_struct *child,
 
 #endif /* CONFIG_ARM64_MTE */
 
+static inline void mte_disable_tco_entry(struct task_struct *task)
+{
+	if (!system_supports_mte())
+		return;
+
+	/*
+	 * Re-enable tag checking (TCO set on exception entry). This is only
+	 * necessary if MTE is enabled in either the kernel or the userspace
+	 * task in synchronous or asymmetric mode (SCTLR_EL1.TCF0 bit 0 is set
+	 * for both). With MTE disabled in the kernel and disabled or
+	 * asynchronous in userspace, tag check faults (including in uaccesses)
+	 * are not reported, therefore there is no need to re-enable checking.
+	 * This is beneficial on microarchitectures where re-enabling TCO is
+	 * expensive.
+	 */
+	if (kasan_hw_tags_enabled() ||
+	    (task->thread.sctlr_user & (1UL << SCTLR_EL1_TCF0_SHIFT)))
+		asm volatile(SET_PSTATE_TCO(0));
+}
+
 #ifdef CONFIG_KASAN_HW_TAGS
 /* Whether the MTE asynchronous mode is enabled. */
 DECLARE_STATIC_KEY_FALSE(mte_async_or_asymm_mode);
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index ef7fcefb96bd..7093b578e325 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/context_tracking.h>
+#include <linux/kasan.h>
 #include <linux/linkage.h>
 #include <linux/lockdep.h>
 #include <linux/ptrace.h>
@@ -56,6 +57,7 @@ static void noinstr enter_from_kernel_mode(struct pt_regs *regs)
 {
 	__enter_from_kernel_mode(regs);
 	mte_check_tfsr_entry();
+	mte_disable_tco_entry(current);
 }
 
 /*
@@ -103,6 +105,7 @@ static __always_inline void __enter_from_user_mode(void)
 	CT_WARN_ON(ct_state() != CONTEXT_USER);
 	user_exit_irqoff();
 	trace_hardirqs_off_finish();
+	mte_disable_tco_entry(current);
 }
 
 static __always_inline void enter_from_user_mode(struct pt_regs *regs)
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 772ec2ecf488..e1013a83d4f0 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -308,13 +308,6 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	msr_s	SYS_ICC_PMR_EL1, x20
 alternative_else_nop_endif
 
-	/* Re-enable tag checking (TCO set on exception entry) */
-#ifdef CONFIG_ARM64_MTE
-alternative_if ARM64_MTE
-	SET_PSTATE_TCO(0)
-alternative_else_nop_endif
-#endif
-
 	/*
 	 * Registers that may be useful after this macro is invoked:
 	 *
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index f418ebc65f95..f983795b5eda 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -253,6 +253,9 @@ void mte_thread_switch(struct task_struct *next)
 	mte_update_sctlr_user(next);
 	mte_update_gcr_excl(next);
 
+	/* TCO may not have been disabled on exception entry for the current task. */
+	mte_disable_tco_entry(next);
+
 	/*
 	 * Check if an async tag exception occurred at EL1.
 	 *
-- 
2.35.1.473.g83b2b277ed-goog