* [PATCH v3 1/2] iommu/arm-smmu-v3: Fix CMDQ timeout warning
2025-11-05 19:06 [PATCH v3 0/2] SMMU v3 CMDQ fix and improvement Jacob Pan
@ 2025-11-05 19:06 ` Jacob Pan
2025-11-05 19:44 ` Nicolin Chen
2025-11-05 19:06 ` [PATCH v3 2/2] iommu/arm-smmu-v3: Improve CMDQ lock fairness and efficiency Jacob Pan
1 sibling, 1 reply; 5+ messages in thread
From: Jacob Pan @ 2025-11-05 19:06 UTC (permalink / raw)
To: linux-kernel, iommu@lists.linux.dev, Will Deacon, Joerg Roedel,
Mostafa Saleh, Jason Gunthorpe, Robin Murphy, Nicolin Chen
Cc: Jacob Pan, Zhang Yu, Jean Philippe-Brucker, Alexander Grest
While polling for n spaces in the cmdq, the current code instead checks
if the queue is full. If the queue is almost full but not enough space
(<n), then the CMDQ timeout warning is never triggered even if the
polling has exceeded timeout limit.
The existing arm_smmu_cmdq_poll_until_not_full() doesn't fit efficiently
nor ideally to the only caller arm_smmu_cmdq_issue_cmdlist():
- It uses a new timer at every single call, which fails to limit to the
preset ARM_SMMU_POLL_TIMEOUT_US per issue.
- It has a redundant internal queue_full(), which doesn't detect whether
there is a enough space for number of n commands.
This patch polls for the availability of exact space instead of full and
emit timeout warning accordingly.
Fixes: 587e6c10a7ce ("iommu/arm-smmu-v3: Reduce contention during command-queue insertion")
Co-developed-by: Yu Zhang <zhangyu1@linux.microsoft.com>
Signed-off-by: Yu Zhang <zhangyu1@linux.microsoft.com>
Signed-off-by: Jacob Pan <jacob.pan@linux.microsoft.com>
---
v3:
- Use a helper for cmdq poll instead of open coding (Nicolin)
- Add more explanation in the commit message (Nicolin)
v2: - Reduced debug print info (Nicolin)
- Use a separate irq flags for exclusive lock
- Handle queue_poll err code other than ETIMEOUT
---
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 43 +++++++++------------
1 file changed, 19 insertions(+), 24 deletions(-)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index bf67d9abc901..86be84c14036 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -117,12 +117,6 @@ static bool queue_has_space(struct arm_smmu_ll_queue *q, u32 n)
return space >= n;
}
-static bool queue_full(struct arm_smmu_ll_queue *q)
-{
- return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
- Q_WRP(q, q->prod) != Q_WRP(q, q->cons);
-}
-
static bool queue_empty(struct arm_smmu_ll_queue *q)
{
return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
@@ -612,13 +606,13 @@ static void arm_smmu_cmdq_poll_valid_map(struct arm_smmu_cmdq *cmdq,
__arm_smmu_cmdq_poll_set_valid_map(cmdq, sprod, eprod, false);
}
-/* Wait for the command queue to become non-full */
-static int arm_smmu_cmdq_poll_until_not_full(struct arm_smmu_device *smmu,
- struct arm_smmu_cmdq *cmdq,
- struct arm_smmu_ll_queue *llq)
+
+static inline void arm_smmu_cmdq_poll(struct arm_smmu_device *smmu,
+ struct arm_smmu_cmdq *cmdq,
+ struct arm_smmu_ll_queue *llq,
+ struct arm_smmu_queue_poll *qp)
{
unsigned long flags;
- struct arm_smmu_queue_poll qp;
int ret = 0;
/*
@@ -629,19 +623,19 @@ static int arm_smmu_cmdq_poll_until_not_full(struct arm_smmu_device *smmu,
WRITE_ONCE(cmdq->q.llq.cons, readl_relaxed(cmdq->q.cons_reg));
arm_smmu_cmdq_exclusive_unlock_irqrestore(cmdq, flags);
llq->val = READ_ONCE(cmdq->q.llq.val);
- return 0;
+ return;
}
- queue_poll_init(smmu, &qp);
- do {
- llq->val = READ_ONCE(cmdq->q.llq.val);
- if (!queue_full(llq))
- break;
-
- ret = queue_poll(&qp);
- } while (!ret);
-
- return ret;
+ ret = queue_poll(qp);
+ if (ret == -ETIMEDOUT) {
+ dev_err_ratelimited(smmu->dev, "CMDQ timed out, cons: %08x, prod: 0x%08x\n",
+ llq->cons, llq->prod);
+ /* Restart the timer */
+ queue_poll_init(smmu, qp);
+ } else if (ret) {
+ dev_err_ratelimited(smmu->dev, "CMDQ poll error %d\n", ret);
+ }
+ llq->val = READ_ONCE(cmdq->q.llq.val);
}
/*
@@ -783,12 +777,13 @@ static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
local_irq_save(flags);
llq.val = READ_ONCE(cmdq->q.llq.val);
do {
+ struct arm_smmu_queue_poll qp;
u64 old;
+ queue_poll_init(smmu, &qp);
while (!queue_has_space(&llq, n + sync)) {
local_irq_restore(flags);
- if (arm_smmu_cmdq_poll_until_not_full(smmu, cmdq, &llq))
- dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
+ arm_smmu_cmdq_poll(smmu, cmdq, &llq, &qp);
local_irq_save(flags);
}
--
2.43.0
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH v3 2/2] iommu/arm-smmu-v3: Improve CMDQ lock fairness and efficiency
2025-11-05 19:06 [PATCH v3 0/2] SMMU v3 CMDQ fix and improvement Jacob Pan
2025-11-05 19:06 ` [PATCH v3 1/2] iommu/arm-smmu-v3: Fix CMDQ timeout warning Jacob Pan
@ 2025-11-05 19:06 ` Jacob Pan
1 sibling, 0 replies; 5+ messages in thread
From: Jacob Pan @ 2025-11-05 19:06 UTC (permalink / raw)
To: linux-kernel, iommu@lists.linux.dev, Will Deacon, Joerg Roedel,
Mostafa Saleh, Jason Gunthorpe, Robin Murphy, Nicolin Chen
Cc: Jacob Pan, Zhang Yu, Jean Philippe-Brucker, Alexander Grest
From: Alexander Grest <Alexander.Grest@microsoft.com>
The SMMU CMDQ lock is highly contentious when there are multiple CPUs
issuing commands and the queue is nearly full.
The lock has the following states:
- 0: Unlocked
- >0: Shared lock held with count
- INT_MIN+N: Exclusive lock held, where N is the # of shared waiters
- INT_MIN: Exclusive lock held, no shared waiters
When multiple CPUs are polling for space in the queue, they attempt to
grab the exclusive lock to update the cons pointer from the hardware. If
they fail to get the lock, they will spin until either the cons pointer
is updated by another CPU.
The current code allows the possibility of shared lock starvation
if there is a constant stream of CPUs trying to grab the exclusive lock.
This leads to severe latency issues and soft lockups.
Consider the following scenario where CPU1's attempt to acquire the
shared lock is starved by CPU2 and CPU0 contending for the exclusive
lock.
CPU0 (exclusive) | CPU1 (shared) | CPU2 (exclusive) | `cmdq->lock`
--------------------------------------------------------------------------
trylock() //takes | | | 0
| shared_lock() | | INT_MIN
| fetch_inc() | | INT_MIN
| no return | | INT_MIN + 1
| spins // VAL >= 0 | | INT_MIN + 1
unlock() | spins... | | INT_MIN + 1
set_release(0) | spins... | | 0 see[NOTE]
(done) | (sees 0) | trylock() // takes | 0
| *exits loop* | cmpxchg(0, INT_MIN) | 0
| | *cuts in* | INT_MIN
| cmpxchg(0, 1) | | INT_MIN
| fails // != 0 | | INT_MIN
| spins // VAL >= 0 | | INT_MIN
| *starved* | | INT_MIN
[NOTE] The current code resets the exclusive lock to 0 regardless of the
state of the lock. This causes two problems:
1. It opens the possibility of back-to-back exclusive locks and the
downstream effect of starving shared lock.
2. The count of shared lock waiters are lost.
To mitigate this, we release the exclusive lock by only clearing the sign
bit while retaining the shared lock waiter count as a way to avoid
starving the shared lock waiters.
Also deleted cmpxchg loop while trying to acquire the shared lock as it
is not needed. The waiters can see the positive lock count and proceed
immediately after the exclusive lock is released.
Exclusive lock is not starved in that submitters will try exclusive lock
first when new spaces become available.
Reviewed-by: Mostafa Saleh <smostafa@google.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Alexander Grest <Alexander.Grest@microsoft.com>
Signed-off-by: Jacob Pan <jacob.pan@linux.microsoft.com>
---
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 31 ++++++++++++++-------
1 file changed, 21 insertions(+), 10 deletions(-)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index aa7d4696b351..b5ab2f330edf 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -481,20 +481,26 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
*/
static void arm_smmu_cmdq_shared_lock(struct arm_smmu_cmdq *cmdq)
{
- int val;
-
/*
- * We can try to avoid the cmpxchg() loop by simply incrementing the
- * lock counter. When held in exclusive state, the lock counter is set
- * to INT_MIN so these increments won't hurt as the value will remain
- * negative.
+ * When held in exclusive state, the lock counter is set to INT_MIN
+ * so these increments won't hurt as the value will remain negative.
+ * The increment will also signal the exclusive locker that there are
+ * shared waiters.
*/
if (atomic_fetch_inc_relaxed(&cmdq->lock) >= 0)
return;
- do {
- val = atomic_cond_read_relaxed(&cmdq->lock, VAL >= 0);
- } while (atomic_cmpxchg_relaxed(&cmdq->lock, val, val + 1) != val);
+ /*
+ * Someone else is holding the lock in exclusive state, so wait
+ * for them to finish. Since we already incremented the lock counter,
+ * no exclusive lock can be acquired until we finish. We don't need
+ * the return value since we only care that the exclusive lock is
+ * released (i.e. the lock counter is non-negative).
+ * Once the exclusive locker releases the lock, the sign bit will
+ * be cleared and our increment will make the lock counter positive,
+ * allowing us to proceed.
+ */
+ atomic_cond_read_relaxed(&cmdq->lock, VAL > 0);
}
static void arm_smmu_cmdq_shared_unlock(struct arm_smmu_cmdq *cmdq)
@@ -521,9 +527,14 @@ static bool arm_smmu_cmdq_shared_tryunlock(struct arm_smmu_cmdq *cmdq)
__ret; \
})
+/*
+ * Only clear the sign bit when releasing the exclusive lock this will
+ * allow any shared_lock() waiters to proceed without the possibility
+ * of entering the exclusive lock in a tight loop.
+ */
#define arm_smmu_cmdq_exclusive_unlock_irqrestore(cmdq, flags) \
({ \
- atomic_set_release(&cmdq->lock, 0); \
+ atomic_fetch_and_release(~INT_MIN, &cmdq->lock); \
local_irq_restore(flags); \
})
--
2.43.0
^ permalink raw reply related [flat|nested] 5+ messages in thread