[RFC PATCH 4/6] ARM: Remove __ARCH_WANT_INTERRUPTS_ON_CTXSW on ASID-capable CPUs
Catalin Marinas
catalin.marinas at arm.com
Tue Nov 29 07:22:30 EST 2011
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, 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().
Signed-off-by: Catalin Marinas <catalin.marinas at arm.com>
Cc: Russell King <linux at arm.linux.org.uk>
---
arch/arm/include/asm/mmu_context.h | 81 ++++++++++++++++++++++++++++--------
arch/arm/include/asm/system.h | 2 +
arch/arm/include/asm/thread_info.h | 1 +
arch/arm/mm/context.c | 4 +-
arch/arm/mm/proc-v7.S | 3 -
5 files changed, 69 insertions(+), 22 deletions(-)
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index 71605d9..3e4b219 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -48,39 +48,75 @@ 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 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);
+
/*
- * 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).
+ * Required during context switch to avoid speculative page table
+ * walking with the wrong TTBR.
*/
- if (unlikely((mm->context.id ^ cpu_last_asid) >> ASID_BITS))
- __new_context(mm);
+ cpu_set_reserved_ttbr0();
- if (unlikely(mm->context.kvm_seq != init_mm.context.kvm_seq))
- __check_kvm_seq(mm);
+ /*
+ * This code is executed with interrupts disabled. If mm->context.id
+ * and cpu_last_asid are from the same generation (condition below
+ * false), they cannot be updated on a different CPU without an IPI
+ * being issued to reset the context. However, smp_call_function() on
+ * a different CPU will need to wait for the current context switch to
+ * complete and interrupts to be enabled before using the new
+ * generation of ASIDs.
+ */
+ if (unlikely((mm->context.id ^ cpu_last_asid) >> ASID_BITS))
+ /*
+ * 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
+ cpu_switch_mm(mm->pgd, 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)) {
+ 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);
+ }
+}
+
+#else /* !CONFIG_CPU_HAS_ASID */
-static inline void check_context(struct mm_struct *mm)
+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)
@@ -122,8 +158,7 @@ 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));
}
@@ -131,7 +166,19 @@ 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)
+
+static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
+{
+#ifdef CONFIG_MMU
+ unsigned long flags;
+
+ local_irq_save(flags);
+ switch_mm(prev, next, current);
+ local_irq_restore(flags);
+
+ finish_arch_post_lock_switch();
+#endif
+}
/*
* We are inserting a "fake" vma for the user-accessible vector page so
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 984014b..3daebde 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -222,7 +222,9 @@ static inline void set_copro_access(unsigned int val)
* so enable interrupts over the context switch to avoid high
* latency.
*/
+#ifndef CONFIG_CPU_HAS_ASID
#define __ARCH_WANT_INTERRUPTS_ON_CTXSW
+#endif
/*
* switch_to(prev, next) should switch from task `prev' to `next'
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 7b5cc8d..119e4eb 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -145,6 +145,7 @@ extern void vfp_flush_hwstate(struct thread_info *);
#define TIF_FREEZE 19
#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)
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 1d5014b..d80aef0 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -22,7 +22,7 @@ unsigned int cpu_last_asid = ASID_FIRST_VERSION;
DEFINE_PER_CPU(struct mm_struct *, current_mm);
#endif
-static void cpu_set_reserved_ttbr0(void)
+void cpu_set_reserved_ttbr0(void)
{
u32 ttb;
/* Copy TTBR1 into TTBR0 */
@@ -43,7 +43,7 @@ void __init_new_context(struct task_struct *tsk, struct mm_struct *mm)
raw_spin_lock_init(&mm->context.id_lock);
}
-static void flush_context(void)
+void flush_context(void)
{
cpu_set_reserved_ttbr0();
local_flush_tlb_all();
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 2faff3b..d5334d9 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -116,9 +116,6 @@ 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
More information about the linux-arm-kernel
mailing list