ARM: mm: remove IPI broadcasting on ASID rollover

ASIDs are allocated to MMU contexts based on a rolling counter. This
means that after 255 allocations we must invalidate all existing ASIDs
via an expensive IPI mechanism to synchronise all of the online CPUs and
ensure that all tasks execute with an ASID from the new generation.

This patch changes the rollover behaviour so that we rely instead on the
hardware broadcasting of the TLB invalidation to avoid the IPI calls.
This works by keeping track of the active ASID on each core, which is
then reserved in the case of a rollover so that currently scheduled
tasks can continue to run. For cores without hardware TLB broadcasting,
we keep track of pending flushes in a cpumask, so cores can flush their
local TLB before scheduling a new mm.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

1 files changed, 3 insertions, 79 deletions

diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index 0306bc642c0d..a64f61cb23d1 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -24,84 +24,8 @@ void __check_kvm_seq(struct mm_struct *mm);
 
 #ifdef CONFIG_CPU_HAS_ASID
 
-/*
- * On ARMv6, we have the following structure in the Context ID:
- *
- * 31                         7          0
- * +-------------------------+-----------+
- * |      process ID         |   ASID    |
- * +-------------------------+-----------+
- * |              context ID             |
- * +-------------------------------------+
- *
- * The ASID is used to tag entries in the CPU caches and TLBs.
- * The context ID is used by debuggers and trace logic, and
- * should be unique within all running processes.
- */
-#define ASID_BITS		8
-#define ASID_MASK		((~0) << ASID_BITS)
-#define ASID_FIRST_VERSION	(1 << ASID_BITS)
-
-extern unsigned int cpu_last_asid;
-
-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 switch_new_context(struct mm_struct *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)
-
-#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);
-}
+void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk);
+#define init_new_context(tsk,mm)	({ mm->context.id = 0; })
 
 #else	/* !CONFIG_CPU_HAS_ASID */
 
@@ -143,6 +67,7 @@ static inline void finish_arch_post_lock_switch(void)
 #endif	/* CONFIG_CPU_HAS_ASID */
 
 #define destroy_context(mm)		do { } while(0)
+#define activate_mm(prev,next)		switch_mm(prev, next, NULL)
 
 /*
  * This is called when "tsk" is about to enter lazy TLB mode.
@@ -186,6 +111,5 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 }
 
 #define deactivate_mm(tsk,mm)	do { } while (0)
-#define activate_mm(prev,next)	switch_mm(prev, next, NULL)
 
 #endif