Merge branch 'intr-ctxsw' of...

Merge branch 'intr-ctxsw' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux into devel-stable

arch/arm/include/asm/mmu.h

@@ -34,11 +34,4 @@ typedef struct {
 
 #endif
 
-/*
- * switch_mm() may do a full cache flush over the context switch,
- * so enable interrupts over the context switch to avoid high
- * latency.
- */
-#define __ARCH_WANT_INTERRUPTS_ON_CTXSW
-
 #endif

arch/arm/include/asm/mmu_context.h

@@ -43,45 +43,104 @@ void __check_kvm_seq(struct mm_struct *mm);
 #define ASID_FIRST_VERSION	(1 << ASID_BITS)
 
 extern unsigned int cpu_last_asid;
-#ifdef CONFIG_SMP
-DECLARE_PER_CPU(struct mm_struct *, current_mm);
-#endif
 
 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
-
-static inline void check_context(struct mm_struct *mm)
+#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);
+}
+
+#else	/* !CONFIG_CPU_HAS_ASID */
+
 #ifdef CONFIG_MMU
+
+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);
-#endif
+
+	if (irqs_disabled())
+		/*
+		 * cpu_switch_mm() needs to flush the VIVT caches. To avoid
+		 * high interrupt latencies, defer the call and continue
+		 * running with the old mm. Since we only support UP systems
+		 * on non-ASID CPUs, the old mm will remain valid until the
+		 * finish_arch_post_lock_switch() call.
+		 */
+		set_ti_thread_flag(task_thread_info(tsk), TIF_SWITCH_MM);
+	else
+		cpu_switch_mm(mm->pgd, mm);
 }
 
+#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)) {
+		struct mm_struct *mm = current->mm;
+		cpu_switch_mm(mm->pgd, mm);
+	}
+}
+
+#endif	/* CONFIG_MMU */
+
 #define init_new_context(tsk,mm)	0
 
-#endif
+#endif	/* CONFIG_CPU_HAS_ASID */
 
 #define destroy_context(mm)		do { } while(0)
 
@@ -119,12 +178,7 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		__flush_icache_all();
 #endif
 	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) {
-#ifdef CONFIG_SMP
-		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

@@ -18,30 +18,39 @@
 
 static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
 unsigned int cpu_last_asid = ASID_FIRST_VERSION;
-#ifdef CONFIG_SMP
-DEFINE_PER_CPU(struct mm_struct *, current_mm);
-#endif
 
 #ifdef CONFIG_ARM_LPAE
-#define cpu_set_asid(asid) {						\
-	unsigned long ttbl, ttbh;					\
-	asm volatile(							\
-	"	mrrc	p15, 0, %0, %1, c2		@ read TTBR0\n"	\
-	"	mov	%1, %2, lsl #(48 - 32)		@ set ASID\n"	\
-	"	mcrr	p15, 0, %0, %1, c2		@ set TTBR0\n"	\
-	: "=&r" (ttbl), "=&r" (ttbh)					\
-	: "r" (asid & ~ASID_MASK));					\
+void cpu_set_reserved_ttbr0(void)
+{
+	unsigned long ttbl = __pa(swapper_pg_dir);
+	unsigned long ttbh = 0;
+
+	/*
+	 * Set TTBR0 to swapper_pg_dir which contains only global entries. The
+	 * ASID is set to 0.
+	 */
+	asm volatile(
+	"	mcrr	p15, 0, %0, %1, c2		@ set TTBR0\n"
+	:
+	: "r" (ttbl), "r" (ttbh));
+	isb();
 }
 #else
-#define cpu_set_asid(asid) \
-	asm("	mcr	p15, 0, %0, c13, c0, 1\n" : : "r" (asid))
+void cpu_set_reserved_ttbr0(void)
+{
+	u32 ttb;
+	/* Copy TTBR1 into TTBR0 */
+	asm volatile(
+	"	mrc	p15, 0, %0, c2, c0, 1		@ read TTBR1\n"
+	"	mcr	p15, 0, %0, c2, c0, 0		@ set TTBR0\n"
+	: "=r" (ttb));
+	isb();
+}
 #endif
 
 /*
  * We fork()ed a process, and we need a new context for the child
- * to run in.  We reserve version 0 for initial tasks so we will
- * always allocate an ASID. The ASID 0 is reserved for the TTBR
- * register changing sequence.
+ * to run in.
  */
 void __init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
@@ -51,9 +60,7 @@ void __init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 
 static void flush_context(void)
 {
-	/* set the reserved ASID before flushing the TLB */
-	cpu_set_asid(0);
-	isb();
+	cpu_set_reserved_ttbr0();
 	local_flush_tlb_all();
 	if (icache_is_vivt_asid_tagged()) {
 		__flush_icache_all();
@@ -98,14 +105,7 @@ static void reset_context(void *info)
 {
 	unsigned int asid;
 	unsigned int cpu = smp_processor_id();
-	struct mm_struct *mm = per_cpu(current_mm, cpu);
-
-	/*
-	 * Check if a current_mm was set on this CPU as it might still
-	 * be in the early booting stages and using the reserved ASID.
-	 */
-	if (!mm)
-		return;
+	struct mm_struct *mm = current->active_mm;
 
 	smp_rmb();
 	asid = cpu_last_asid + cpu + 1;
@@ -114,8 +114,7 @@ static void reset_context(void *info)
 	set_mm_context(mm, asid);
 
 	/* set the new ASID */
-	cpu_set_asid(mm->context.id);
-	isb();
+	cpu_switch_mm(mm->pgd, mm);
 }
 
 #else

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

@@ -46,18 +46,13 @@ ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_ARM_ERRATA_430973
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 #endif
-#ifdef CONFIG_ARM_ERRATA_754322
-	dsb
-#endif
-	mcr	p15, 0, r2, c13, c0, 1		@ set reserved context ID
-	isb
-1:	mcr	p15, 0, r0, c2, c0, 0		@ set TTB 0
-	isb
 #ifdef CONFIG_ARM_ERRATA_754322
 	dsb
 #endif
 	mcr	p15, 0, r1, c13, c0, 1		@ set context ID
 	isb
+	mcr	p15, 0, r0, c2, c0, 0		@ set TTB 0
+	isb
 #endif
 	mov	pc, lr
 ENDPROC(cpu_v7_switch_mm)