@@ -25,6 +25,7 @@
typedef struct {
atomic64_t id;
+ unsigned long pinned;
void *vdso;
unsigned long flags;
} mm_context_t;
@@ -168,7 +168,13 @@ static inline void cpu_replace_ttbr1(pgd_t *pgd)
#define destroy_context(mm) do { } while(0)
void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
-#define init_new_context(tsk,mm) ({ atomic64_set(&(mm)->context.id, 0); 0; })
+static inline int
+init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+ atomic64_set(&mm->context.id, 0);
+ mm->context.pinned = 0;
+ return 0;
+}
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
static inline void update_saved_ttbr0(struct task_struct *tsk,
@@ -241,6 +247,9 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
void verify_cpu_asid_bits(void);
void post_ttbr_update_workaround(void);
+unsigned long mm_context_get(struct mm_struct *mm);
+void mm_context_put(struct mm_struct *mm);
+
#endif /* !__ASSEMBLY__ */
#endif /* !__ASM_MMU_CONTEXT_H */
@@ -37,6 +37,10 @@ static DEFINE_PER_CPU(atomic64_t, active_asids);
static DEFINE_PER_CPU(u64, reserved_asids);
static cpumask_t tlb_flush_pending;
+static unsigned long max_pinned_asids;
+static unsigned long nr_pinned_asids;
+static unsigned long *pinned_asid_map;
+
#define ASID_MASK (~GENMASK(asid_bits - 1, 0))
#define ASID_FIRST_VERSION (1UL << asid_bits)
@@ -88,13 +92,16 @@ void verify_cpu_asid_bits(void)
}
}
+#define asid_gen_match(asid) \
+ (!(((asid) ^ atomic64_read(&asid_generation)) >> asid_bits))
+
static void flush_context(unsigned int cpu)
{
int i;
u64 asid;
/* Update the list of reserved ASIDs and the ASID bitmap. */
- bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
+ bitmap_copy(asid_map, pinned_asid_map, NUM_USER_ASIDS);
for_each_possible_cpu(i) {
asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0);
@@ -151,6 +158,9 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
if (asid != 0) {
u64 newasid = generation | (asid & ~ASID_MASK);
+ if (mm->context.pinned)
+ return newasid;
+
/*
* If our current ASID was active during a rollover, we
* can continue to use it and this was just a false alarm.
@@ -213,8 +223,7 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
* because atomic RmWs are totally ordered for a given location.
*/
old_active_asid = atomic64_read(&per_cpu(active_asids, cpu));
- if (old_active_asid &&
- !((asid ^ atomic64_read(&asid_generation)) >> asid_bits) &&
+ if (old_active_asid && asid_gen_match(asid) &&
atomic64_cmpxchg_relaxed(&per_cpu(active_asids, cpu),
old_active_asid, asid))
goto switch_mm_fastpath;
@@ -222,7 +231,7 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
raw_spin_lock_irqsave(&cpu_asid_lock, flags);
/* Check that our ASID belongs to the current generation. */
asid = atomic64_read(&mm->context.id);
- if ((asid ^ atomic64_read(&asid_generation)) >> asid_bits) {
+ if (!asid_gen_match(asid)) {
asid = new_context(mm, cpu);
atomic64_set(&mm->context.id, asid);
}
@@ -245,6 +254,63 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
cpu_switch_mm(mm->pgd, mm);
}
+unsigned long mm_context_get(struct mm_struct *mm)
+{
+ unsigned long flags;
+ u64 asid;
+
+ raw_spin_lock_irqsave(&cpu_asid_lock, flags);
+
+ asid = atomic64_read(&mm->context.id);
+
+ if (mm->context.pinned) {
+ mm->context.pinned++;
+ asid &= ~ASID_MASK;
+ goto out_unlock;
+ }
+
+ if (nr_pinned_asids >= max_pinned_asids) {
+ asid = 0;
+ goto out_unlock;
+ }
+
+ if (!asid_gen_match(asid)) {
+ /*
+ * We went through one or more rollover since that ASID was
+ * used. Ensure that it is still valid, or generate a new one.
+ * The cpu argument isn't used by new_context.
+ */
+ asid = new_context(mm, 0);
+ atomic64_set(&mm->context.id, asid);
+ }
+
+ asid &= ~ASID_MASK;
+
+ nr_pinned_asids++;
+ __set_bit(asid2idx(asid), pinned_asid_map);
+ mm->context.pinned++;
+
+out_unlock:
+ raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
+
+ return asid;
+}
+
+void mm_context_put(struct mm_struct *mm)
+{
+ unsigned long flags;
+ u64 asid = atomic64_read(&mm->context.id) & ~ASID_MASK;
+
+ raw_spin_lock_irqsave(&cpu_asid_lock, flags);
+
+ if (--mm->context.pinned == 0) {
+ __clear_bit(asid2idx(asid), pinned_asid_map);
+ nr_pinned_asids--;
+ }
+
+ raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
+}
+
/* Errata workaround post TTBRx_EL1 update. */
asmlinkage void post_ttbr_update_workaround(void)
{
@@ -269,6 +335,19 @@ static int asids_init(void)
panic("Failed to allocate bitmap for %lu ASIDs\n",
NUM_USER_ASIDS);
+ pinned_asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS)
+ * sizeof(*pinned_asid_map), GFP_KERNEL);
+ if (!pinned_asid_map)
+ panic("Failed to allocate pinned bitmap\n");
+
+ /*
+ * We assume that an ASID is always available after a rollover. This
+ * means that even if all CPUs have a reserved ASID, there still is at
+ * least one slot available in the asid map.
+ */
+ max_pinned_asids = NUM_USER_ASIDS - num_possible_cpus() - 2;
+ nr_pinned_asids = 0;
+
pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS);
return 0;
}
To enable address space sharing with the IOMMU, introduce mm_context_get() and mm_context_put(), that pin down a context and ensure that it will keep its ASID after a rollover. Pinning is necessary because a device constantly needs a valid ASID, unlike tasks that only require one when running. Without pinning, we would need to notify the IOMMU when we're about to use a new ASID for a task, and it would get complicated when a new task is assigned a shared ASID. Consider the following scenario with no ASID pinned: 1. Task t1 is running on CPUx with shared ASID (gen=1, asid=1) 2. Task t2 is scheduled on CPUx, gets ASID (1, 2) 3. Task tn is scheduled on CPUy, a rollover occurs, tn gets ASID (2, 1) We would now have to immediately generate a new ASID for t1, notify the IOMMU, and finally enable task tn. We are holding the lock during all that time, since we can't afford having another CPU trigger a rollover. The IOMMU issues invalidation commands that can take tens of milliseconds. It gets needlessly complicated. All we wanted to do was schedule task tn, that has no business with the IOMMU. By letting the IOMMU pin tasks when needed, we avoid stalling the slow path, and let the pinning fail when we're out of shareable ASIDs. After a rollover, the allocator expects at least one ASID to be available in addition to the reserved ones (one per CPU). So (NR_ASIDS - NR_CPUS - 1) is the maxium number of ASIDs that can be shared with the IOMMU. Signed-off-by: Jean-Philippe Brucker <jean-philippe.brucker@arm.com> --- I started adding these changes to the TLA+ specification of the ASID allocator, but I'm having trouble finding a good configuration. So far I haven't been able to complete a full check in reasonable time (4 days and counting for the current version). More details on this patch: http://jpbrucker.net/cgit.cgi/kernel-tla/commit/?id=4d4fd17429a516e1bf2495b2dc7d036daab2dab9 --- arch/arm64/include/asm/mmu.h | 1 + arch/arm64/include/asm/mmu_context.h | 11 ++++- arch/arm64/mm/context.c | 87 ++++++++++++++++++++++++++++++++++-- 3 files changed, 94 insertions(+), 5 deletions(-)