arm64: mm: rewrite ASID allocator and MM context-switching code

Our current switch_mm implementation suffers from a number of problems:

  (1) The ASID allocator relies on IPIs to synchronise the CPUs on a
      rollover event

  (2) Because of (1), we cannot allocate ASIDs with interrupts disabled
      and therefore make use of a TIF_SWITCH_MM flag to postpone the
      actual switch to finish_arch_post_lock_switch

  (3) We run context switch with a reserved (invalid) TTBR0 value, even
      though the ASID and pgd are updated atomically

  (4) We take a global spinlock (cpu_asid_lock) during context-switch

  (5) We use h/w broadcast TLB operations when they are not required
      (e.g. in flush_context)

This patch addresses these problems by rewriting the ASID algorithm to
match the bitmap-based arch/arm/ implementation more closely. This in
turn allows us to remove much of the complications surrounding switch_mm,
including the ugly thread flag.

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

3 files changed, 19 insertions, 73 deletions

diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 0302087..990124a 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -17,15 +17,16 @@
 #define __ASM_MMU_H
 
 typedef struct {
-	unsigned int id;
-	raw_spinlock_t id_lock;
-	void *vdso;
+	atomic64_t	id;
+	void		*vdso;
 } mm_context_t;
 
-#define INIT_MM_CONTEXT(name) \
-	.context.id_lock = __RAW_SPIN_LOCK_UNLOCKED(name.context.id_lock),
-
-#define ASID(mm)	((mm)->context.id & 0xffff)
+/*
+ * This macro is only used by the TLBI code, which cannot race with an
+ * ASID change and therefore doesn't need to reload the counter using
+ * atomic64_read.
+ */
+#define ASID(mm)	((mm)->context.id.counter & 0xffff)
 
 extern void paging_init(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 549b895..f4c74a9 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -28,13 +28,6 @@
 #include <asm/cputype.h>
 #include <asm/pgtable.h>
 
-#define MAX_ASID_BITS	16
-
-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);
-
 #ifdef CONFIG_PID_IN_CONTEXTIDR
 static inline void contextidr_thread_switch(struct task_struct *next)
 {
@@ -96,66 +89,19 @@ static inline void cpu_set_default_tcr_t0sz(void)
 	: "r"(TCR_T0SZ(VA_BITS)), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH));
 }
 
-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)
-{
-	/*
-	 * 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) >> MAX_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.
-		 */
-		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)
+/*
+ * It would be nice to return ASIDs back to the allocator, but unfortunately
+ * that introduces a race with a generation rollover where we could erroneously
+ * free an ASID allocated in a future generation. We could workaround this by
+ * freeing the ASID from the context of the dying mm (e.g. in arch_exit_mmap),
+ * but we'd then need to make sure that we didn't dirty any TLBs afterwards.
+ * Setting a reserved TTBR0 or EPD0 would work, but it all gets ugly when you
+ * take CPU migration into account.
+ */
 #define destroy_context(mm)		do { } while(0)
+void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
 
-#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;
-		unsigned long flags;
-
-		__new_context(mm);
-
-		local_irq_save(flags);
-		cpu_switch_mm(mm->pgd, mm);
-		local_irq_restore(flags);
-	}
-}
+#define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })
 
 /*
  * This is called when "tsk" is about to enter lazy TLB mode.
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index dcd06d1..555c6de 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -111,7 +111,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_RESTORE_SIGMASK	20
 #define TIF_SINGLESTEP		21
 #define TIF_32BIT		22	/* 32bit process */
-#define TIF_SWITCH_MM		23	/* deferred switch_mm */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)