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>
This commit is contained in:
Sunil Goutham 2017-05-05 16:47:46 +05:30 committed by Will Deacon
parent 2ea659a9ef
commit b847de4e50
1 changed files with 10 additions and 2 deletions

View File

@ -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;
}
}