iommu/arm-smmu-v3: Increase CMDQ drain timeout value

Waiting for a CMD_SYNC to be processed involves waiting for the command
queue to drain, which can take an awful lot longer than waiting for a
single entry to become available. Consequently, the common timeout value
of 100us has been observed to be too short on some platforms when a
CMD_SYNC is issued into a queued full of TLBI commands.

This patch resolves the issue by using a different (1s) timeout when
waiting for the CMDQ to drain and using a simple back-off mechanism
when polling the cons pointer in the absence of WFE support.

Signed-off-by: Sunil Goutham <sgoutham@cavium.com>
[will: rewrote commit message and cosmetic changes]
Signed-off-by: Will Deacon <will.deacon@arm.com>

drivers/iommu/arm-smmu-v3.c

@@ -408,6 +408,7 @@
 
 /* High-level queue structures */
 #define ARM_SMMU_POLL_TIMEOUT_US	100
+#define ARM_SMMU_CMDQ_DRAIN_TIMEOUT_US	1000000 /* 1s! */
 
 #define MSI_IOVA_BASE			0x8000000
 #define MSI_IOVA_LENGTH			0x100000
@@ -737,7 +738,13 @@ static void queue_inc_prod(struct arm_smmu_queue *q)
  */
 static int queue_poll_cons(struct arm_smmu_queue *q, bool drain, bool wfe)
 {
-	ktime_t timeout = ktime_add_us(ktime_get(), ARM_SMMU_POLL_TIMEOUT_US);
+	ktime_t timeout;
+	unsigned int delay = 1;
+
+	/* Wait longer if it's queue drain */
+	timeout = ktime_add_us(ktime_get(), drain ?
+					    ARM_SMMU_CMDQ_DRAIN_TIMEOUT_US :
+					    ARM_SMMU_POLL_TIMEOUT_US);
 
 	while (queue_sync_cons(q), (drain ? !queue_empty(q) : queue_full(q))) {
 		if (ktime_compare(ktime_get(), timeout) > 0)
@@ -747,7 +754,8 @@ static int queue_poll_cons(struct arm_smmu_queue *q, bool drain, bool wfe)
 			wfe();
 		} else {
 			cpu_relax();
-			udelay(1);
+			udelay(delay);
+			delay *= 2;
 		}
 	}