iommu/arm-smmu-v3: Separate s/w and h/w views of prod and cons indexes

mainline inclusion
from mainline-v5.4-rc1
commit 2a8868f1
category: bugfix
bugzilla: 21306
CVE: NA

-------------------------------------------------------------------------

In preparation for rewriting the command queue insertion code to use a
new algorithm, separate the software and hardware views of the prod and
cons indexes so that manipulating the software state doesn't
automatically update the hardware state at the same time.

No functional change.
Tested-by: NGanapatrao Kulkarni  <gkulkarni@marvell.com>
Signed-off-by: NWill Deacon <will@kernel.org>
Conflicts:
	drivers/iommu/arm-smmu-v3.c
Signed-off-by: NZhen Lei <thunder.leizhen@huawei.com>
Reviewed-by: NHanjun Guo <guohanjun@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>
Signed-off-by: NCheng Jian <cj.chengjian@huawei.com>

drivers/iommu/arm-smmu-v3.c

@@ -781,17 +781,13 @@ static bool queue_empty(struct arm_smmu_queue *q)
 	       Q_WRP(q, q->prod) == Q_WRP(q, q->cons);
 }
 
-static void queue_sync_cons(struct arm_smmu_queue *q)
+static void queue_sync_cons_in(struct arm_smmu_queue *q)
 {
 	q->cons = readl_relaxed(q->cons_reg);
 }
 
-static void queue_inc_cons(struct arm_smmu_queue *q)
+static void queue_sync_cons_out(struct arm_smmu_queue *q)
 {
-	u32 cons = (Q_WRP(q, q->cons) | Q_IDX(q, q->cons)) + 1;
-
-	q->cons = Q_OVF(q, q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons);
-
 	/*
 	 * Ensure that all CPU accesses (reads and writes) to the queue
 	 * are complete before we update the cons pointer.
@@ -800,7 +796,13 @@ static void queue_inc_cons(struct arm_smmu_queue *q)
 	writel_relaxed(q->cons, q->cons_reg);
 }
 
-static int queue_sync_prod(struct arm_smmu_queue *q)
+static void queue_inc_cons(struct arm_smmu_queue *q)
+{
+	u32 cons = (Q_WRP(q, q->cons) | Q_IDX(q, q->cons)) + 1;
+	q->cons = Q_OVF(q, q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons);
+}
+
+static int queue_sync_prod_in(struct arm_smmu_queue *q)
 {
 	int ret = 0;
 	u32 prod = readl_relaxed(q->prod_reg);
@@ -812,12 +814,15 @@ static int queue_sync_prod(struct arm_smmu_queue *q)
 	return ret;
 }
 
+static void queue_sync_prod_out(struct arm_smmu_queue *q)
+{
+	writel(q->prod, q->prod_reg);
+}
+
 static void queue_inc_prod(struct arm_smmu_queue *q)
 {
 	u32 prod = (Q_WRP(q, q->prod) | Q_IDX(q, q->prod)) + 1;
-
 	q->prod = Q_OVF(q, q->prod) | Q_WRP(q, prod) | Q_IDX(q, prod);
-	writel(q->prod, q->prod_reg);
 }
 
 /*
@@ -834,7 +839,7 @@ static int queue_poll_cons(struct arm_smmu_queue *q, bool sync, bool wfe)
 					    ARM_SMMU_CMDQ_SYNC_TIMEOUT_US :
 					    ARM_SMMU_POLL_TIMEOUT_US);
 
-	while (queue_sync_cons(q), (sync ? !queue_empty(q) : queue_full(q))) {
+	while (queue_sync_cons_in(q), (sync ? !queue_empty(q) : queue_full(q))) {
 		if (ktime_compare(ktime_get(), timeout) > 0)
 			return -ETIMEDOUT;
 
@@ -868,6 +873,7 @@ static int queue_insert_raw(struct arm_smmu_queue *q, u64 *ent)
 
 	queue_write(Q_ENT(q, q->prod), ent, q->ent_dwords);
 	queue_inc_prod(q);
+	queue_sync_prod_out(q);
 	return 0;
 }
 
@@ -886,6 +892,7 @@ static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent)
 
 	queue_read(ent, Q_ENT(q, q->cons), q->ent_dwords);
 	queue_inc_cons(q);
+	queue_sync_cons_out(q);
 	return 0;
 }
 
@@ -1498,7 +1505,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
 		 * Not much we can do on overflow, so scream and pretend we're
 		 * trying harder.
 		 */
-		if (queue_sync_prod(q) == -EOVERFLOW)
+		if (queue_sync_prod_in(q) == -EOVERFLOW)
 			dev_err(smmu->dev, "EVTQ overflow detected -- events lost\n");
 	} while (!queue_empty(q));
 
@@ -1571,7 +1578,7 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
 			}
 		}
 
-		if (queue_sync_prod(q) == -EOVERFLOW)
+		if (queue_sync_prod_in(q) == -EOVERFLOW)
 			dev_err(smmu->dev, "PRIQ overflow detected -- requests lost\n");
 	} while (!queue_empty(q));
 
@@ -1601,7 +1608,7 @@ static int arm_smmu_flush_queue(struct arm_smmu_device *smmu,
 	u64 batch;
 
 	spin_lock(&q->wq.lock);
-	if (queue_sync_prod(q) == -EOVERFLOW)
+	if (queue_sync_prod_in(q) == -EOVERFLOW)
 		dev_err(smmu->dev, "%s overflow detected -- requests lost\n",
 			name);
 
@@ -1733,8 +1740,9 @@ static void arm_smmu_tlb_inv_context(void *cookie)
 	/*
 	 * NOTE: when io-pgtable is in non-strict mode, we may get here with
 	 * PTEs previously cleared by unmaps on the current CPU not yet visible
-	 * to the SMMU. We are relying on the DSB implicit in queue_inc_prod()
-	 * to guarantee those are observed before the TLBI. Do be careful, 007.
+	 * to the SMMU. We are relying on the DSB implicit in
+	 * queue_sync_prod_out() to guarantee those are observed before the
+	 * TLBI. Do be careful, 007.
 	 */
 	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
 	__arm_smmu_tlb_sync(smmu);