ARM: Remove __ARCH_WANT_INTERRUPTS_ON_CTXSW on ASID-capable CPUs

Since the ASIDs must be unique to an mm across all the CPUs in a system,
the __new_context() function needs to broadcast a context reset event to
all the CPUs during ASID allocation if a roll-over occurred. Such IPIs
cannot be issued with interrupts disabled and ARM had to define
__ARCH_WANT_INTERRUPTS_ON_CTXSW.

This patch changes the check_context() function to
check_and_switch_context() called from switch_mm(). In case of
ASID-capable CPUs (ARMv6 onwards), if a new ASID is needed and the
interrupts are disabled, it defers the __new_context() and
cpu_switch_mm() calls to the post-lock switch hook where the interrupts
are enabled. Setting the reserved TTBR0 was also moved to
check_and_switch_context() from cpu_v7_switch_mm().
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Tested-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NFrank Rowand <frank.rowand@am.sony.com>
Tested-by: NMarc Zyngier <Marc.Zyngier@arm.com>
Signed-off-by: NCatalin Marinas <catalin.marinas@arm.com>

arch/arm/include/asm/mmu.h

@@ -39,6 +39,8 @@ typedef struct {
  * so enable interrupts over the context switch to avoid high
  * latency.
  */
+#ifndef CONFIG_CPU_HAS_ASID
 #define __ARCH_WANT_INTERRUPTS_ON_CTXSW
+#endif
 
 #endif

arch/arm/include/asm/mmu_context.h

@@ -49,39 +49,80 @@ DECLARE_PER_CPU(struct mm_struct *, current_mm);
 
 void __init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void __new_context(struct mm_struct *mm);
+void cpu_set_reserved_ttbr0(void);
 
-static inline void check_context(struct mm_struct *mm)
+static inline void switch_new_context(struct mm_struct *mm)
 {
-	/*
-	 * This code is executed with interrupts enabled. Therefore,
-	 * mm->context.id cannot be updated to the latest ASID version
-	 * on a different CPU (and condition below not triggered)
-	 * without first getting an IPI to reset the context. The
-	 * alternative is to take a read_lock on mm->context.id_lock
-	 * (after changing its type to rwlock_t).
-	 */
-	if (unlikely((mm->context.id ^ cpu_last_asid) >> ASID_BITS))
-		__new_context(mm);
+	unsigned long flags;
 
+	__new_context(mm);
+
+	local_irq_save(flags);
+	cpu_switch_mm(mm->pgd, mm);
+	local_irq_restore(flags);
+}
+
+static inline void check_and_switch_context(struct mm_struct *mm,
+					    struct task_struct *tsk)
+{
 	if (unlikely(mm->context.kvm_seq != init_mm.context.kvm_seq))
 		__check_kvm_seq(mm);
+
+	/*
+	 * Required during context switch to avoid speculative page table
+	 * walking with the wrong TTBR.
+	 */
+	cpu_set_reserved_ttbr0();
+
+	if (!((mm->context.id ^ cpu_last_asid) >> ASID_BITS))
+		/*
+		 * The ASID is from the current generation, just switch to the
+		 * new pgd. This condition is only true for calls from
+		 * context_switch() and interrupts are already disabled.
+		 */
+		cpu_switch_mm(mm->pgd, mm);
+	else if (irqs_disabled())
+		/*
+		 * Defer the new ASID allocation until after the context
+		 * switch critical region since __new_context() cannot be
+		 * called with interrupts disabled (it sends IPIs).
+		 */
+		set_ti_thread_flag(task_thread_info(tsk), TIF_SWITCH_MM);
+	else
+		/*
+		 * That is a direct call to switch_mm() or activate_mm() with
+		 * interrupts enabled and a new context.
+		 */
+		switch_new_context(mm);
 }
 
 #define init_new_context(tsk,mm)	(__init_new_context(tsk,mm),0)
 
-#else
+#define finish_arch_post_lock_switch \
+	finish_arch_post_lock_switch
+static inline void finish_arch_post_lock_switch(void)
+{
+	if (test_and_clear_thread_flag(TIF_SWITCH_MM))
+		switch_new_context(current->mm);
+}
 
-static inline void check_context(struct mm_struct *mm)
+#else	/* !CONFIG_CPU_HAS_ASID */
+
+static inline void check_and_switch_context(struct mm_struct *mm,
+					    struct task_struct *tsk)
 {
 #ifdef CONFIG_MMU
 	if (unlikely(mm->context.kvm_seq != init_mm.context.kvm_seq))
 		__check_kvm_seq(mm);
+	cpu_switch_mm(mm->pgd, mm);
 #endif
 }
 
 #define init_new_context(tsk,mm)	0
 
-#endif
+#define finish_arch_post_lock_switch()	do { } while (0)
+
+#endif	/* CONFIG_CPU_HAS_ASID */
 
 #define destroy_context(mm)		do { } while(0)
 
@@ -123,8 +164,7 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		struct mm_struct **crt_mm = &per_cpu(current_mm, cpu);
 		*crt_mm = next;
 #endif
-		check_context(next);
-		cpu_switch_mm(next->pgd, next);
+		check_and_switch_context(next, tsk);
 		if (cache_is_vivt())
 			cpumask_clear_cpu(cpu, mm_cpumask(prev));
 	}

arch/arm/include/asm/thread_info.h

@@ -146,6 +146,7 @@ extern void vfp_flush_hwstate(struct thread_info *);
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	20
 #define TIF_SECCOMP		21
+#define TIF_SWITCH_MM		22	/* deferred switch_mm */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)

arch/arm/mm/context.c

@@ -23,7 +23,7 @@ DEFINE_PER_CPU(struct mm_struct *, current_mm);
 #endif
 
 #ifdef CONFIG_ARM_LPAE
-static void cpu_set_reserved_ttbr0(void)
+void cpu_set_reserved_ttbr0(void)
 {
 	unsigned long ttbl = __pa(swapper_pg_dir);
 	unsigned long ttbh = 0;
@@ -39,7 +39,7 @@ static void cpu_set_reserved_ttbr0(void)
 	isb();
 }
 #else
-static void cpu_set_reserved_ttbr0(void)
+void cpu_set_reserved_ttbr0(void)
 {
 	u32 ttb;
 	/* Copy TTBR1 into TTBR0 */

arch/arm/mm/proc-v7-2level.S

@@ -46,9 +46,6 @@ ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_ARM_ERRATA_430973
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 #endif
-	mrc	p15, 0, r2, c2, c0, 1		@ load TTB 1
-	mcr	p15, 0, r2, c2, c0, 0		@ into TTB 0
-	isb
 #ifdef CONFIG_ARM_ERRATA_754322
 	dsb
 #endif