summaryrefslogtreecommitdiff
path: root/drivers/iommu/arm-smmu.c
diff options
context:
space:
mode:
authorRobin Murphy <robin.murphy@arm.com>2017-03-30 17:56:32 +0100
committerWill Deacon <will.deacon@arm.com>2017-04-06 16:06:43 +0100
commit8513c89300696a68963cc504c21d034c6369e183 (patch)
treed45e868a1851e92cb66afaa463a97b93726a2c83 /drivers/iommu/arm-smmu.c
parent11febfca2419652f28804879a58ffd32adce2372 (diff)
iommu/arm-smmu: Poll for TLB sync completion more effectively
On relatively slow development platforms and software models, the inefficiency of our TLB sync loop tends not to show up - for instance on a Juno r1 board I typically see the TLBI has completed of its own accord by the time we get to the sync, such that the latter finishes instantly. However, on larger systems doing real I/O, it's less realistic for the TLBs to go idle immediately, and at that point falling into the 1MHz polling loop turns out to throw away performance drastically. Let's strike a balance by polling more than once between pauses, such that we have much more chance of catching normal operations completing before committing to the fixed delay, but also backing off exponentially, since if a sync really hasn't completed within one or two "reasonable time" periods, it becomes increasingly unlikely that it ever will. Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org> Signed-off-by: Robin Murphy <robin.murphy@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
Diffstat (limited to 'drivers/iommu/arm-smmu.c')
-rw-r--r--drivers/iommu/arm-smmu.c18
1 files changed, 10 insertions, 8 deletions
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 83f50142e63e..618e133f643a 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -162,6 +162,7 @@
#define ARM_SMMU_GR0_sTLBGSTATUS 0x74
#define sTLBGSTATUS_GSACTIVE (1 << 0)
#define TLB_LOOP_TIMEOUT 1000000 /* 1s! */
+#define TLB_SPIN_COUNT 10
/* Stream mapping registers */
#define ARM_SMMU_GR0_SMR(n) (0x800 + ((n) << 2))
@@ -574,18 +575,19 @@ static void __arm_smmu_free_bitmap(unsigned long *map, int idx)
static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu,
void __iomem *sync, void __iomem *status)
{
- int count = 0;
+ unsigned int spin_cnt, delay;
writel_relaxed(0, sync);
- while (readl_relaxed(status) & sTLBGSTATUS_GSACTIVE) {
- cpu_relax();
- if (++count == TLB_LOOP_TIMEOUT) {
- dev_err_ratelimited(smmu->dev,
- "TLB sync timed out -- SMMU may be deadlocked\n");
- return;
+ for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+ for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+ if (!(readl_relaxed(status) & sTLBGSTATUS_GSACTIVE))
+ return;
+ cpu_relax();
}
- udelay(1);
+ udelay(delay);
}
+ dev_err_ratelimited(smmu->dev,
+ "TLB sync timed out -- SMMU may be deadlocked\n");
}
static void arm_smmu_tlb_sync_global(struct arm_smmu_device *smmu)