From 3f3b8d0c9c1838271543df9e655032117a663f88 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Wed, 18 Sep 2019 17:17:48 +0100
Subject: iommu/arm-smmu: Remove .tlb_inv_range indirection

Fill in 'native' iommu_flush_ops callbacks for all the
arm_smmu_flush_ops variants, and clear up the remains of the previous
.tlb_inv_range abstraction.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu.c | 106 +++++++++++++++++++++++++++--------------------
 1 file changed, 61 insertions(+), 45 deletions(-)

(limited to 'drivers/iommu/arm-smmu.c')

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index b18aac4c105e..78292e8e31a5 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -312,7 +312,7 @@ static void arm_smmu_tlb_inv_context_s2(void *cookie)
 }
 
 static void arm_smmu_tlb_inv_range_s1(unsigned long iova, size_t size,
-				      size_t granule, bool leaf, void *cookie)
+				      size_t granule, void *cookie, bool leaf)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
@@ -342,7 +342,7 @@ static void arm_smmu_tlb_inv_range_s1(unsigned long iova, size_t size,
 }
 
 static void arm_smmu_tlb_inv_range_s2(unsigned long iova, size_t size,
-				      size_t granule, bool leaf, void *cookie)
+				      size_t granule, void *cookie, bool leaf)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
@@ -362,84 +362,100 @@ static void arm_smmu_tlb_inv_range_s2(unsigned long iova, size_t size,
 	} while (size -= granule);
 }
 
-/*
- * On MMU-401 at least, the cost of firing off multiple TLBIVMIDs appears
- * almost negligible, but the benefit of getting the first one in as far ahead
- * of the sync as possible is significant, hence we don't just make this a
- * no-op and set .tlb_sync to arm_smmu_tlb_inv_context_s2() as you might think.
- */
-static void arm_smmu_tlb_inv_vmid_nosync(unsigned long iova, size_t size,
-					 size_t granule, bool leaf, void *cookie)
+static void arm_smmu_tlb_inv_walk_s1(unsigned long iova, size_t size,
+				     size_t granule, void *cookie)
 {
-	struct arm_smmu_domain *smmu_domain = cookie;
-	struct arm_smmu_device *smmu = smmu_domain->smmu;
-
-	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
-		wmb();
+	arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie, false);
+	arm_smmu_tlb_sync_context(cookie);
+}
 
-	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, smmu_domain->cfg.vmid);
+static void arm_smmu_tlb_inv_leaf_s1(unsigned long iova, size_t size,
+				     size_t granule, void *cookie)
+{
+	arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie, true);
+	arm_smmu_tlb_sync_context(cookie);
 }
 
-static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size,
-				  size_t granule, void *cookie)
+static void arm_smmu_tlb_add_page_s1(struct iommu_iotlb_gather *gather,
+				     unsigned long iova, size_t granule,
+				     void *cookie)
 {
-	struct arm_smmu_domain *smmu_domain = cookie;
-	const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
+	arm_smmu_tlb_inv_range_s1(iova, granule, granule, cookie, true);
+}
 
-	ops->tlb_inv_range(iova, size, granule, false, cookie);
-	ops->tlb_sync(cookie);
+static void arm_smmu_tlb_inv_walk_s2(unsigned long iova, size_t size,
+				     size_t granule, void *cookie)
+{
+	arm_smmu_tlb_inv_range_s2(iova, size, granule, cookie, false);
+	arm_smmu_tlb_sync_context(cookie);
 }
 
-static void arm_smmu_tlb_inv_leaf(unsigned long iova, size_t size,
-				  size_t granule, void *cookie)
+static void arm_smmu_tlb_inv_leaf_s2(unsigned long iova, size_t size,
+				     size_t granule, void *cookie)
 {
-	struct arm_smmu_domain *smmu_domain = cookie;
-	const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
+	arm_smmu_tlb_inv_range_s2(iova, size, granule, cookie, true);
+	arm_smmu_tlb_sync_context(cookie);
+}
 
-	ops->tlb_inv_range(iova, size, granule, true, cookie);
-	ops->tlb_sync(cookie);
+static void arm_smmu_tlb_add_page_s2(struct iommu_iotlb_gather *gather,
+				     unsigned long iova, size_t granule,
+				     void *cookie)
+{
+	arm_smmu_tlb_inv_range_s2(iova, granule, granule, cookie, true);
 }
 
-static void arm_smmu_tlb_add_page(struct iommu_iotlb_gather *gather,
-				  unsigned long iova, size_t granule,
-				  void *cookie)
+static void arm_smmu_tlb_inv_any_s2_v1(unsigned long iova, size_t size,
+				       size_t granule, void *cookie)
+{
+	arm_smmu_tlb_inv_context_s2(cookie);
+}
+/*
+ * On MMU-401 at least, the cost of firing off multiple TLBIVMIDs appears
+ * almost negligible, but the benefit of getting the first one in as far ahead
+ * of the sync as possible is significant, hence we don't just make this a
+ * no-op and call arm_smmu_tlb_inv_context_s2() from .iotlb_sync as you might
+ * think.
+ */
+static void arm_smmu_tlb_add_page_s2_v1(struct iommu_iotlb_gather *gather,
+					unsigned long iova, size_t granule,
+					void *cookie)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
-	const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
 
-	ops->tlb_inv_range(iova, granule, granule, true, cookie);
+	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
+		wmb();
+
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, smmu_domain->cfg.vmid);
 }
 
 static const struct arm_smmu_flush_ops arm_smmu_s1_tlb_ops = {
 	.tlb = {
 		.tlb_flush_all	= arm_smmu_tlb_inv_context_s1,
-		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
-		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
-		.tlb_add_page	= arm_smmu_tlb_add_page,
+		.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s1,
+		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf_s1,
+		.tlb_add_page	= arm_smmu_tlb_add_page_s1,
 	},
-	.tlb_inv_range		= arm_smmu_tlb_inv_range_s1,
 	.tlb_sync		= arm_smmu_tlb_sync_context,
 };
 
 static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
 	.tlb = {
 		.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
-		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
-		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
-		.tlb_add_page	= arm_smmu_tlb_add_page,
+		.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s2,
+		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf_s2,
+		.tlb_add_page	= arm_smmu_tlb_add_page_s2,
 	},
-	.tlb_inv_range		= arm_smmu_tlb_inv_range_s2,
 	.tlb_sync		= arm_smmu_tlb_sync_context,
 };
 
 static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
 	.tlb = {
 		.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
-		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
-		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf,
-		.tlb_add_page	= arm_smmu_tlb_add_page,
+		.tlb_flush_walk	= arm_smmu_tlb_inv_any_s2_v1,
+		.tlb_flush_leaf	= arm_smmu_tlb_inv_any_s2_v1,
+		.tlb_add_page	= arm_smmu_tlb_add_page_s2_v1,
 	},
-	.tlb_inv_range		= arm_smmu_tlb_inv_vmid_nosync,
 	.tlb_sync		= arm_smmu_tlb_sync_vmid,
 };
 
-- 
cgit v1.2.3


From 3370cb6bf64f6896a30eb7ad97721b9598c8fb10 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Wed, 18 Sep 2019 17:17:49 +0100
Subject: iommu/arm-smmu: Remove "leaf" indirection

Now that the "leaf" flag is no longer part of an external interface,
there's no need to use it to infer a register offset at runtime when
we can just as easily encode the offset directly in its place.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu.c | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

(limited to 'drivers/iommu/arm-smmu.c')

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 78292e8e31a5..4edbe58a303a 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -312,18 +312,16 @@ static void arm_smmu_tlb_inv_context_s2(void *cookie)
 }
 
 static void arm_smmu_tlb_inv_range_s1(unsigned long iova, size_t size,
-				      size_t granule, void *cookie, bool leaf)
+				      size_t granule, void *cookie, int reg)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
-	int reg, idx = cfg->cbndx;
+	int idx = cfg->cbndx;
 
 	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
 		wmb();
 
-	reg = leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA;
-
 	if (cfg->fmt != ARM_SMMU_CTX_FMT_AARCH64) {
 		iova = (iova >> 12) << 12;
 		iova |= cfg->asid;
@@ -342,16 +340,15 @@ static void arm_smmu_tlb_inv_range_s1(unsigned long iova, size_t size,
 }
 
 static void arm_smmu_tlb_inv_range_s2(unsigned long iova, size_t size,
-				      size_t granule, void *cookie, bool leaf)
+				      size_t granule, void *cookie, int reg)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
-	int reg, idx = smmu_domain->cfg.cbndx;
+	int idx = smmu_domain->cfg.cbndx;
 
 	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
 		wmb();
 
-	reg = leaf ? ARM_SMMU_CB_S2_TLBIIPAS2L : ARM_SMMU_CB_S2_TLBIIPAS2;
 	iova >>= 12;
 	do {
 		if (smmu_domain->cfg.fmt == ARM_SMMU_CTX_FMT_AARCH64)
@@ -365,14 +362,16 @@ static void arm_smmu_tlb_inv_range_s2(unsigned long iova, size_t size,
 static void arm_smmu_tlb_inv_walk_s1(unsigned long iova, size_t size,
 				     size_t granule, void *cookie)
 {
-	arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie, false);
+	arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie,
+				  ARM_SMMU_CB_S1_TLBIVA);
 	arm_smmu_tlb_sync_context(cookie);
 }
 
 static void arm_smmu_tlb_inv_leaf_s1(unsigned long iova, size_t size,
 				     size_t granule, void *cookie)
 {
-	arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie, true);
+	arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie,
+				  ARM_SMMU_CB_S1_TLBIVAL);
 	arm_smmu_tlb_sync_context(cookie);
 }
 
@@ -380,20 +379,23 @@ static void arm_smmu_tlb_add_page_s1(struct iommu_iotlb_gather *gather,
 				     unsigned long iova, size_t granule,
 				     void *cookie)
 {
-	arm_smmu_tlb_inv_range_s1(iova, granule, granule, cookie, true);
+	arm_smmu_tlb_inv_range_s1(iova, granule, granule, cookie,
+				  ARM_SMMU_CB_S1_TLBIVAL);
 }
 
 static void arm_smmu_tlb_inv_walk_s2(unsigned long iova, size_t size,
 				     size_t granule, void *cookie)
 {
-	arm_smmu_tlb_inv_range_s2(iova, size, granule, cookie, false);
+	arm_smmu_tlb_inv_range_s2(iova, size, granule, cookie,
+				  ARM_SMMU_CB_S2_TLBIIPAS2);
 	arm_smmu_tlb_sync_context(cookie);
 }
 
 static void arm_smmu_tlb_inv_leaf_s2(unsigned long iova, size_t size,
 				     size_t granule, void *cookie)
 {
-	arm_smmu_tlb_inv_range_s2(iova, size, granule, cookie, true);
+	arm_smmu_tlb_inv_range_s2(iova, size, granule, cookie,
+				  ARM_SMMU_CB_S2_TLBIIPAS2L);
 	arm_smmu_tlb_sync_context(cookie);
 }
 
@@ -401,7 +403,8 @@ static void arm_smmu_tlb_add_page_s2(struct iommu_iotlb_gather *gather,
 				     unsigned long iova, size_t granule,
 				     void *cookie)
 {
-	arm_smmu_tlb_inv_range_s2(iova, granule, granule, cookie, true);
+	arm_smmu_tlb_inv_range_s2(iova, granule, granule, cookie,
+				  ARM_SMMU_CB_S2_TLBIIPAS2L);
 }
 
 static void arm_smmu_tlb_inv_any_s2_v1(unsigned long iova, size_t size,
-- 
cgit v1.2.3


From ae2b60f34ab21780bc30d01ae976cc7340446bde Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Wed, 18 Sep 2019 17:17:50 +0100
Subject: iommu/arm-smmu: Move .tlb_sync method to implementation

With the .tlb_sync interface no longer exposed directly to io-pgtable,
strip away the remains of that abstraction layer. Retain the callback
in spirit, though, by transforming it into an implementation override
for the low-level sync routine itself, for which we will have at least
one user.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu.c | 33 +++++++++++++++------------------
 drivers/iommu/arm-smmu.h |  3 ++-
 2 files changed, 17 insertions(+), 19 deletions(-)

(limited to 'drivers/iommu/arm-smmu.c')

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 4edbe58a303a..25876eb9266d 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -244,6 +244,9 @@ static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
 	unsigned int spin_cnt, delay;
 	u32 reg;
 
+	if (smmu->impl && unlikely(smmu->impl->tlb_sync))
+		return smmu->impl->tlb_sync(smmu, page, sync, status);
+
 	arm_smmu_writel(smmu, page, sync, QCOM_DUMMY_VAL);
 	for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
 		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
@@ -268,9 +271,8 @@ static void arm_smmu_tlb_sync_global(struct arm_smmu_device *smmu)
 	spin_unlock_irqrestore(&smmu->global_sync_lock, flags);
 }
 
-static void arm_smmu_tlb_sync_context(void *cookie)
+static void arm_smmu_tlb_sync_context(struct arm_smmu_domain *smmu_domain)
 {
-	struct arm_smmu_domain *smmu_domain = cookie;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	unsigned long flags;
 
@@ -280,13 +282,6 @@ static void arm_smmu_tlb_sync_context(void *cookie)
 	spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
 }
 
-static void arm_smmu_tlb_sync_vmid(void *cookie)
-{
-	struct arm_smmu_domain *smmu_domain = cookie;
-
-	arm_smmu_tlb_sync_global(smmu_domain->smmu);
-}
-
 static void arm_smmu_tlb_inv_context_s1(void *cookie)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
@@ -297,7 +292,7 @@ static void arm_smmu_tlb_inv_context_s1(void *cookie)
 	wmb();
 	arm_smmu_cb_write(smmu_domain->smmu, smmu_domain->cfg.cbndx,
 			  ARM_SMMU_CB_S1_TLBIASID, smmu_domain->cfg.asid);
-	arm_smmu_tlb_sync_context(cookie);
+	arm_smmu_tlb_sync_context(smmu_domain);
 }
 
 static void arm_smmu_tlb_inv_context_s2(void *cookie)
@@ -439,7 +434,6 @@ static const struct arm_smmu_flush_ops arm_smmu_s1_tlb_ops = {
 		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf_s1,
 		.tlb_add_page	= arm_smmu_tlb_add_page_s1,
 	},
-	.tlb_sync		= arm_smmu_tlb_sync_context,
 };
 
 static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
@@ -449,7 +443,6 @@ static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
 		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf_s2,
 		.tlb_add_page	= arm_smmu_tlb_add_page_s2,
 	},
-	.tlb_sync		= arm_smmu_tlb_sync_context,
 };
 
 static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
@@ -459,7 +452,6 @@ static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
 		.tlb_flush_leaf	= arm_smmu_tlb_inv_any_s2_v1,
 		.tlb_add_page	= arm_smmu_tlb_add_page_s2_v1,
 	},
-	.tlb_sync		= arm_smmu_tlb_sync_vmid,
 };
 
 static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
@@ -1229,11 +1221,16 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 
-	if (smmu_domain->flush_ops) {
-		arm_smmu_rpm_get(smmu);
-		smmu_domain->flush_ops->tlb_sync(smmu_domain);
-		arm_smmu_rpm_put(smmu);
-	}
+	if (!smmu)
+		return;
+
+	arm_smmu_rpm_get(smmu);
+	if (smmu->version == ARM_SMMU_V2 ||
+	    smmu_domain->stage == ARM_SMMU_DOMAIN_S1)
+		arm_smmu_tlb_sync_context(smmu_domain);
+	else
+		arm_smmu_tlb_sync_global(smmu);
+	arm_smmu_rpm_put(smmu);
 }
 
 static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index 6edd35ca983c..5032102f05b7 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -306,7 +306,6 @@ enum arm_smmu_domain_stage {
 
 struct arm_smmu_flush_ops {
 	struct iommu_flush_ops		tlb;
-	void (*tlb_sync)(void *cookie);
 };
 
 struct arm_smmu_domain {
@@ -333,6 +332,8 @@ struct arm_smmu_impl {
 	int (*cfg_probe)(struct arm_smmu_device *smmu);
 	int (*reset)(struct arm_smmu_device *smmu);
 	int (*init_context)(struct arm_smmu_domain *smmu_domain);
+	void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync,
+			 int status);
 };
 
 static inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n)
-- 
cgit v1.2.3


From 696bcfb709862077e8fd0e484cca952db7f2001a Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Wed, 18 Sep 2019 17:17:51 +0100
Subject: iommu/arm-smmu: Remove arm_smmu_flush_ops

Now it's just an empty wrapper.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu.c | 40 +++++++++++++++++-----------------------
 drivers/iommu/arm-smmu.h |  6 +-----
 2 files changed, 18 insertions(+), 28 deletions(-)

(limited to 'drivers/iommu/arm-smmu.c')

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 25876eb9266d..d2d357c87b61 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -427,31 +427,25 @@ static void arm_smmu_tlb_add_page_s2_v1(struct iommu_iotlb_gather *gather,
 	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, smmu_domain->cfg.vmid);
 }
 
-static const struct arm_smmu_flush_ops arm_smmu_s1_tlb_ops = {
-	.tlb = {
-		.tlb_flush_all	= arm_smmu_tlb_inv_context_s1,
-		.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s1,
-		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf_s1,
-		.tlb_add_page	= arm_smmu_tlb_add_page_s1,
-	},
+static const struct iommu_flush_ops arm_smmu_s1_tlb_ops = {
+	.tlb_flush_all	= arm_smmu_tlb_inv_context_s1,
+	.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s1,
+	.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf_s1,
+	.tlb_add_page	= arm_smmu_tlb_add_page_s1,
 };
 
-static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
-	.tlb = {
-		.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
-		.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s2,
-		.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf_s2,
-		.tlb_add_page	= arm_smmu_tlb_add_page_s2,
-	},
+static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
+	.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
+	.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s2,
+	.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf_s2,
+	.tlb_add_page	= arm_smmu_tlb_add_page_s2,
 };
 
-static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
-	.tlb = {
-		.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
-		.tlb_flush_walk	= arm_smmu_tlb_inv_any_s2_v1,
-		.tlb_flush_leaf	= arm_smmu_tlb_inv_any_s2_v1,
-		.tlb_add_page	= arm_smmu_tlb_add_page_s2_v1,
-	},
+static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
+	.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
+	.tlb_flush_walk	= arm_smmu_tlb_inv_any_s2_v1,
+	.tlb_flush_leaf	= arm_smmu_tlb_inv_any_s2_v1,
+	.tlb_add_page	= arm_smmu_tlb_add_page_s2_v1,
 };
 
 static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
@@ -781,7 +775,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		.ias		= ias,
 		.oas		= oas,
 		.coherent_walk	= smmu->features & ARM_SMMU_FEAT_COHERENT_WALK,
-		.tlb		= &smmu_domain->flush_ops->tlb,
+		.tlb		= smmu_domain->flush_ops,
 		.iommu_dev	= smmu->dev,
 	};
 
@@ -1210,7 +1204,7 @@ static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
 
 	if (smmu_domain->flush_ops) {
 		arm_smmu_rpm_get(smmu);
-		smmu_domain->flush_ops->tlb.tlb_flush_all(smmu_domain);
+		smmu_domain->flush_ops->tlb_flush_all(smmu_domain);
 		arm_smmu_rpm_put(smmu);
 	}
 }
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index 5032102f05b7..ba0f05952dd9 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -304,14 +304,10 @@ enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_BYPASS,
 };
 
-struct arm_smmu_flush_ops {
-	struct iommu_flush_ops		tlb;
-};
-
 struct arm_smmu_domain {
 	struct arm_smmu_device		*smmu;
 	struct io_pgtable_ops		*pgtbl_ops;
-	const struct arm_smmu_flush_ops	*flush_ops;
+	const struct iommu_flush_ops	*flush_ops;
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
 	bool				non_strict;
-- 
cgit v1.2.3


From 931a0ba638e09a707e9a905cb6bea1fb1c6d4183 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Tue, 17 Sep 2019 15:45:34 +0100
Subject: iommu/arm-smmu: Report USF more clearly

Although CONFIG_ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT is a welcome tool
for smoking out inadequate firmware, the failure mode is non-obvious
and can be confusing for end users. Add some special-case reporting of
Unidentified Stream Faults to help clarify this particular symptom.
Since we're adding yet another print to the mix, also break out an
explicit ratelimit state to make sure everything stays together (and
reduce the static storage footprint a little).

Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu.c | 21 ++++++++++++++++-----
 drivers/iommu/arm-smmu.h |  2 ++
 2 files changed, 18 insertions(+), 5 deletions(-)

(limited to 'drivers/iommu/arm-smmu.c')

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index d2d357c87b61..bd6683c210da 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -36,6 +36,7 @@
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/ratelimit.h>
 #include <linux/slab.h>
 
 #include <linux/amba/bus.h>
@@ -477,6 +478,8 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
 {
 	u32 gfsr, gfsynr0, gfsynr1, gfsynr2;
 	struct arm_smmu_device *smmu = dev;
+	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
 
 	gfsr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSR);
 	gfsynr0 = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSYNR0);
@@ -486,11 +489,19 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
 	if (!gfsr)
 		return IRQ_NONE;
 
-	dev_err_ratelimited(smmu->dev,
-		"Unexpected global fault, this could be serious\n");
-	dev_err_ratelimited(smmu->dev,
-		"\tGFSR 0x%08x, GFSYNR0 0x%08x, GFSYNR1 0x%08x, GFSYNR2 0x%08x\n",
-		gfsr, gfsynr0, gfsynr1, gfsynr2);
+	if (__ratelimit(&rs)) {
+		if (IS_ENABLED(CONFIG_ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT) &&
+		    (gfsr & sGFSR_USF))
+			dev_err(smmu->dev,
+				"Blocked unknown Stream ID 0x%hx; boot with \"arm-smmu.disable_bypass=0\" to allow, but this may have security implications\n",
+				(u16)gfsynr1);
+		else
+			dev_err(smmu->dev,
+				"Unexpected global fault, this could be serious\n");
+		dev_err(smmu->dev,
+			"\tGFSR 0x%08x, GFSYNR0 0x%08x, GFSYNR1 0x%08x, GFSYNR2 0x%08x\n",
+			gfsr, gfsynr0, gfsynr1, gfsynr2);
+	}
 
 	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sGFSR, gfsr);
 	return IRQ_HANDLED;
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index ba0f05952dd9..409716410b0d 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -79,6 +79,8 @@
 #define ID7_MINOR			GENMASK(3, 0)
 
 #define ARM_SMMU_GR0_sGFSR		0x48
+#define sGFSR_USF			BIT(1)
+
 #define ARM_SMMU_GR0_sGFSYNR0		0x50
 #define ARM_SMMU_GR0_sGFSYNR1		0x54
 #define ARM_SMMU_GR0_sGFSYNR2		0x58
-- 
cgit v1.2.3


From bdde4718aba368c33705ccff8f3e29586d41b69b Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 15 Sep 2019 21:34:01 +0200
Subject: iommu/arm-smmu: Axe a useless test in 'arm_smmu_master_alloc_smes()'

'iommu_group_get_for_dev()' never returns NULL, so this test can be removed.

Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'drivers/iommu/arm-smmu.c')

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index bd6683c210da..080af0326816 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1054,8 +1054,6 @@ static int arm_smmu_master_alloc_smes(struct device *dev)
 	}
 
 	group = iommu_group_get_for_dev(dev);
-	if (!group)
-		group = ERR_PTR(-ENOMEM);
 	if (IS_ERR(group)) {
 		ret = PTR_ERR(group);
 		goto out_err;
-- 
cgit v1.2.3


From 781ca2de89bae1b1d2c96df9ef33e9a324415995 Mon Sep 17 00:00:00 2001
From: Tom Murphy <murphyt7@tcd.ie>
Date: Sun, 8 Sep 2019 09:56:38 -0700
Subject: iommu: Add gfp parameter to iommu_ops::map

Add a gfp_t parameter to the iommu_ops::map function.
Remove the needless locking in the AMD iommu driver.

The iommu_ops::map function (or the iommu_map function which calls it)
was always supposed to be sleepable (according to Joerg's comment in
this thread: https://lore.kernel.org/patchwork/patch/977520/ ) and so
should probably have had a "might_sleep()" since it was written. However
currently the dma-iommu api can call iommu_map in an atomic context,
which it shouldn't do. This doesn't cause any problems because any iommu
driver which uses the dma-iommu api uses gfp_atomic in it's
iommu_ops::map function. But doing this wastes the memory allocators
atomic pools.

Signed-off-by: Tom Murphy <murphyt7@tcd.ie>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd_iommu.c      |  3 ++-
 drivers/iommu/arm-smmu-v3.c    |  2 +-
 drivers/iommu/arm-smmu.c       |  2 +-
 drivers/iommu/dma-iommu.c      |  6 +++---
 drivers/iommu/exynos-iommu.c   |  2 +-
 drivers/iommu/intel-iommu.c    |  2 +-
 drivers/iommu/iommu.c          | 43 ++++++++++++++++++++++++++++++++++++------
 drivers/iommu/ipmmu-vmsa.c     |  2 +-
 drivers/iommu/msm_iommu.c      |  2 +-
 drivers/iommu/mtk_iommu.c      |  2 +-
 drivers/iommu/mtk_iommu_v1.c   |  2 +-
 drivers/iommu/omap-iommu.c     |  2 +-
 drivers/iommu/qcom_iommu.c     |  2 +-
 drivers/iommu/rockchip-iommu.c |  2 +-
 drivers/iommu/s390-iommu.c     |  2 +-
 drivers/iommu/tegra-gart.c     |  2 +-
 drivers/iommu/tegra-smmu.c     |  2 +-
 drivers/iommu/virtio-iommu.c   |  2 +-
 include/linux/iommu.h          | 21 ++++++++++++++++++++-
 19 files changed, 77 insertions(+), 26 deletions(-)

(limited to 'drivers/iommu/arm-smmu.c')

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 97ca4ed4ce0c..1444757f0ff9 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3106,7 +3106,8 @@ static int amd_iommu_attach_device(struct iommu_domain *dom,
 }
 
 static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova,
-			 phys_addr_t paddr, size_t page_size, int iommu_prot)
+			 phys_addr_t paddr, size_t page_size, int iommu_prot,
+			 gfp_t gfp)
 {
 	struct protection_domain *domain = to_pdomain(dom);
 	int prot = 0;
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 8da93e730d6f..f1bdaaa8c5de 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -2448,7 +2448,7 @@ out_unlock:
 }
 
 static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
-			phys_addr_t paddr, size_t size, int prot)
+			phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
 
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index b18aac4c105e..e85bc0e8d564 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1159,7 +1159,7 @@ rpm_put:
 }
 
 static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
-			phys_addr_t paddr, size_t size, int prot)
+			phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
 	struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index f321279baf9e..cc3bf5cf0a90 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -476,7 +476,7 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 	if (!iova)
 		return DMA_MAPPING_ERROR;
 
-	if (iommu_map(domain, iova, phys - iova_off, size, prot)) {
+	if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) {
 		iommu_dma_free_iova(cookie, iova, size);
 		return DMA_MAPPING_ERROR;
 	}
@@ -611,7 +611,7 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
 			arch_dma_prep_coherent(sg_page(sg), sg->length);
 	}
 
-	if (iommu_map_sg(domain, iova, sgt.sgl, sgt.orig_nents, ioprot)
+	if (iommu_map_sg_atomic(domain, iova, sgt.sgl, sgt.orig_nents, ioprot)
 			< size)
 		goto out_free_sg;
 
@@ -871,7 +871,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	 * We'll leave any physical concatenation to the IOMMU driver's
 	 * implementation - it knows better than we do.
 	 */
-	if (iommu_map_sg(domain, iova, sg, nents, prot) < iova_len)
+	if (iommu_map_sg_atomic(domain, iova, sg, nents, prot) < iova_len)
 		goto out_free_iova;
 
 	return __finalise_sg(dev, sg, nents, iova);
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 9c94e16fb127..186ff5cc975c 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -1073,7 +1073,7 @@ static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size,
  */
 static int exynos_iommu_map(struct iommu_domain *iommu_domain,
 			    unsigned long l_iova, phys_addr_t paddr, size_t size,
-			    int prot)
+			    int prot, gfp_t gfp)
 {
 	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
 	sysmmu_pte_t *entry;
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 3f974919d3bd..615495aa613e 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -5432,7 +5432,7 @@ static void intel_iommu_aux_detach_device(struct iommu_domain *domain,
 
 static int intel_iommu_map(struct iommu_domain *domain,
 			   unsigned long iova, phys_addr_t hpa,
-			   size_t size, int iommu_prot)
+			   size_t size, int iommu_prot, gfp_t gfp)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	u64 max_addr;
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index d658c7c6a2ab..f8853dbf1c4e 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1854,8 +1854,8 @@ static size_t iommu_pgsize(struct iommu_domain *domain,
 	return pgsize;
 }
 
-int iommu_map(struct iommu_domain *domain, unsigned long iova,
-	      phys_addr_t paddr, size_t size, int prot)
+int __iommu_map(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	const struct iommu_ops *ops = domain->ops;
 	unsigned long orig_iova = iova;
@@ -1892,8 +1892,8 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 
 		pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n",
 			 iova, &paddr, pgsize);
+		ret = ops->map(domain, iova, paddr, pgsize, prot, gfp);
 
-		ret = ops->map(domain, iova, paddr, pgsize, prot);
 		if (ret)
 			break;
 
@@ -1913,8 +1913,22 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 
 	return ret;
 }
+
+int iommu_map(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot)
+{
+	might_sleep();
+	return __iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
+}
 EXPORT_SYMBOL_GPL(iommu_map);
 
+int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot)
+{
+	return __iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC);
+}
+EXPORT_SYMBOL_GPL(iommu_map_atomic);
+
 static size_t __iommu_unmap(struct iommu_domain *domain,
 			    unsigned long iova, size_t size,
 			    struct iommu_iotlb_gather *iotlb_gather)
@@ -1991,8 +2005,9 @@ size_t iommu_unmap_fast(struct iommu_domain *domain,
 }
 EXPORT_SYMBOL_GPL(iommu_unmap_fast);
 
-size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
-		    struct scatterlist *sg, unsigned int nents, int prot)
+size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		    struct scatterlist *sg, unsigned int nents, int prot,
+		    gfp_t gfp)
 {
 	size_t len = 0, mapped = 0;
 	phys_addr_t start;
@@ -2003,7 +2018,9 @@ size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 		phys_addr_t s_phys = sg_phys(sg);
 
 		if (len && s_phys != start + len) {
-			ret = iommu_map(domain, iova + mapped, start, len, prot);
+			ret = __iommu_map(domain, iova + mapped, start,
+					len, prot, gfp);
+
 			if (ret)
 				goto out_err;
 
@@ -2031,8 +2048,22 @@ out_err:
 	return 0;
 
 }
+
+size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		    struct scatterlist *sg, unsigned int nents, int prot)
+{
+	might_sleep();
+	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL);
+}
 EXPORT_SYMBOL_GPL(iommu_map_sg);
 
+size_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova,
+		    struct scatterlist *sg, unsigned int nents, int prot)
+{
+	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC);
+}
+EXPORT_SYMBOL_GPL(iommu_map_sg_atomic);
+
 int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
 			       phys_addr_t paddr, u64 size, int prot)
 {
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 9da8309f7170..35f3edaba0e2 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -724,7 +724,7 @@ static void ipmmu_detach_device(struct iommu_domain *io_domain,
 }
 
 static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova,
-		     phys_addr_t paddr, size_t size, int prot)
+		     phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
 
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index be99d408cf35..93f14bca26ee 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -504,7 +504,7 @@ fail:
 }
 
 static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			 phys_addr_t pa, size_t len, int prot)
+			 phys_addr_t pa, size_t len, int prot, gfp_t gfp)
 {
 	struct msm_priv *priv = to_msm_priv(domain);
 	unsigned long flags;
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 67a483c1a935..556beaa110b3 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -412,7 +412,7 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain,
 }
 
 static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			 phys_addr_t paddr, size_t size, int prot)
+			 phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index b5efd6dac953..e93b94ecac45 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -295,7 +295,7 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain,
 }
 
 static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			 phys_addr_t paddr, size_t size, int prot)
+			 phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	unsigned int page_num = size >> MT2701_IOMMU_PAGE_SHIFT;
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index 09c6e1c680db..be551cc34be4 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -1339,7 +1339,7 @@ static u32 iotlb_init_entry(struct iotlb_entry *e, u32 da, u32 pa, int pgsz)
 }
 
 static int omap_iommu_map(struct iommu_domain *domain, unsigned long da,
-			  phys_addr_t pa, size_t bytes, int prot)
+			  phys_addr_t pa, size_t bytes, int prot, gfp_t gfp)
 {
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 	struct device *dev = omap_domain->dev;
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index c31e7bc4ccbe..6ad5f934f00f 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -423,7 +423,7 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de
 }
 
 static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t paddr, size_t size, int prot)
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	int ret;
 	unsigned long flags;
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 26290f310f90..a4f6425fd12d 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -757,7 +757,7 @@ unwind:
 }
 
 static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova,
-			phys_addr_t paddr, size_t size, int prot)
+			phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
 	unsigned long flags;
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index 3b0b18e23187..1137f3ddcb85 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -265,7 +265,7 @@ undo_cpu_trans:
 }
 
 static int s390_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t paddr, size_t size, int prot)
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct s390_domain *s390_domain = to_s390_domain(domain);
 	int flags = ZPCI_PTE_VALID, rc = 0;
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index 3924f7c05544..3fb7ba72507d 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -178,7 +178,7 @@ static inline int __gart_iommu_map(struct gart_device *gart, unsigned long iova,
 }
 
 static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t pa, size_t bytes, int prot)
+			  phys_addr_t pa, size_t bytes, int prot, gfp_t gfp)
 {
 	struct gart_device *gart = gart_handle;
 	int ret;
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 7293fc3f796d..99f85fb5a704 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -650,7 +650,7 @@ static void tegra_smmu_set_pte(struct tegra_smmu_as *as, unsigned long iova,
 }
 
 static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t paddr, size_t size, int prot)
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct tegra_smmu_as *as = to_smmu_as(domain);
 	dma_addr_t pte_dma;
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 3ea9d7682999..2ebcf4bae0c6 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -713,7 +713,7 @@ static int viommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 }
 
 static int viommu_map(struct iommu_domain *domain, unsigned long iova,
-		      phys_addr_t paddr, size_t size, int prot)
+		      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	int ret;
 	u32 flags;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 29bac5345563..6ca3fb2873d7 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -256,7 +256,7 @@ struct iommu_ops {
 	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
 	void (*detach_dev)(struct iommu_domain *domain, struct device *dev);
 	int (*map)(struct iommu_domain *domain, unsigned long iova,
-		   phys_addr_t paddr, size_t size, int prot);
+		   phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
 	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
 		     size_t size, struct iommu_iotlb_gather *iotlb_gather);
 	void (*flush_iotlb_all)(struct iommu_domain *domain);
@@ -421,6 +421,8 @@ extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
 		     phys_addr_t paddr, size_t size, int prot);
+extern int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova,
+			    phys_addr_t paddr, size_t size, int prot);
 extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 			  size_t size);
 extern size_t iommu_unmap_fast(struct iommu_domain *domain,
@@ -428,6 +430,9 @@ extern size_t iommu_unmap_fast(struct iommu_domain *domain,
 			       struct iommu_iotlb_gather *iotlb_gather);
 extern size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			   struct scatterlist *sg,unsigned int nents, int prot);
+extern size_t iommu_map_sg_atomic(struct iommu_domain *domain,
+				  unsigned long iova, struct scatterlist *sg,
+				  unsigned int nents, int prot);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova);
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
@@ -662,6 +667,13 @@ static inline int iommu_map(struct iommu_domain *domain, unsigned long iova,
 	return -ENODEV;
 }
 
+static inline int iommu_map_atomic(struct iommu_domain *domain,
+				   unsigned long iova, phys_addr_t paddr,
+				   size_t size, int prot)
+{
+	return -ENODEV;
+}
+
 static inline size_t iommu_unmap(struct iommu_domain *domain,
 				 unsigned long iova, size_t size)
 {
@@ -682,6 +694,13 @@ static inline size_t iommu_map_sg(struct iommu_domain *domain,
 	return 0;
 }
 
+static inline size_t iommu_map_sg_atomic(struct iommu_domain *domain,
+				  unsigned long iova, struct scatterlist *sg,
+				  unsigned int nents, int prot)
+{
+	return 0;
+}
+
 static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
 {
 }
-- 
cgit v1.2.3


From ee9bdfedd3dc1b3303390663189defa4d6b9e458 Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Thu, 31 Oct 2019 14:31:02 -0700
Subject: iommu/arm-smmu: Avoid pathological RPM behaviour for unmaps

When games, browser, or anything using a lot of GPU buffers exits, there
can be many hundreds or thousands of buffers to unmap and free.  If the
GPU is otherwise suspended, this can cause arm-smmu to resume/suspend
for each buffer, resulting 5-10 seconds worth of reprogramming the
context bank (arm_smmu_write_context_bank()/arm_smmu_write_s2cr()/etc).
To the user it would appear that the system just locked up.

A simple solution is to use pm_runtime_put_autosuspend() instead, so we
don't immediately suspend the SMMU device.

Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

(limited to 'drivers/iommu/arm-smmu.c')

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 080af0326816..a2b1ca55b73e 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -123,7 +123,7 @@ static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
 static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
 {
 	if (pm_runtime_enabled(smmu->dev))
-		pm_runtime_put(smmu->dev);
+		pm_runtime_put_autosuspend(smmu->dev);
 }
 
 static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
@@ -1167,6 +1167,20 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	/* Looks ok, so add the device to the domain */
 	ret = arm_smmu_domain_add_master(smmu_domain, fwspec);
 
+	/*
+	 * Setup an autosuspend delay to avoid bouncing runpm state.
+	 * Otherwise, if a driver for a suspended consumer device
+	 * unmaps buffers, it will runpm resume/suspend for each one.
+	 *
+	 * For example, when used by a GPU device, when an application
+	 * or game exits, it can trigger unmapping 100s or 1000s of
+	 * buffers.  With a runpm cycle for each buffer, that adds up
+	 * to 5-10sec worth of reprogramming the context bank, while
+	 * the system appears to be locked up to the user.
+	 */
+	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
+	pm_runtime_use_autosuspend(smmu->dev);
+
 rpm_put:
 	arm_smmu_rpm_put(smmu);
 	return ret;
-- 
cgit v1.2.3


From 205577ab6f7ade6185f764ed78fb6875dca40205 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Fri, 25 Oct 2019 19:08:36 +0100
Subject: iommu/io-pgtable-arm: Rationalise MAIR handling

Between VMSAv8-64 and the various 32-bit formats, there is either one
64-bit MAIR or a pair of 32-bit MAIR0/MAIR1 or NMRR/PMRR registers.
As such, keeping two 64-bit values in io_pgtable_cfg has always been
overkill.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu-v3.c    | 2 +-
 drivers/iommu/arm-smmu.c       | 4 ++--
 drivers/iommu/io-pgtable-arm.c | 3 +--
 drivers/iommu/ipmmu-vmsa.c     | 2 +-
 drivers/iommu/qcom_iommu.c     | 4 ++--
 include/linux/io-pgtable.h     | 2 +-
 6 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'drivers/iommu/arm-smmu.c')

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 8da93e730d6f..3f20e548f1ec 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -2172,7 +2172,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
 	cfg->cd.asid	= (u16)asid;
 	cfg->cd.ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
 	cfg->cd.tcr	= pgtbl_cfg->arm_lpae_s1_cfg.tcr;
-	cfg->cd.mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair[0];
+	cfg->cd.mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair;
 	return 0;
 
 out_free_asid:
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index a180665ea002..424ebf38cd09 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -552,8 +552,8 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 			cb->mair[0] = pgtbl_cfg->arm_v7s_cfg.prrr;
 			cb->mair[1] = pgtbl_cfg->arm_v7s_cfg.nmrr;
 		} else {
-			cb->mair[0] = pgtbl_cfg->arm_lpae_s1_cfg.mair[0];
-			cb->mair[1] = pgtbl_cfg->arm_lpae_s1_cfg.mair[1];
+			cb->mair[0] = pgtbl_cfg->arm_lpae_s1_cfg.mair;
+			cb->mair[1] = pgtbl_cfg->arm_lpae_s1_cfg.mair >> 32;
 		}
 	}
 }
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index fcb302704053..cd96442af44b 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -861,8 +861,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 	      (ARM_LPAE_MAIR_ATTR_INC_OWBRWA
 	       << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE));
 
-	cfg->arm_lpae_s1_cfg.mair[0] = reg;
-	cfg->arm_lpae_s1_cfg.mair[1] = 0;
+	cfg->arm_lpae_s1_cfg.mair = reg;
 
 	/* Looking good; allocate a pgd */
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 9da8309f7170..e4da6efbda49 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -438,7 +438,7 @@ static void ipmmu_domain_setup_context(struct ipmmu_vmsa_domain *domain)
 
 	/* MAIR0 */
 	ipmmu_ctx_write_root(domain, IMMAIR0,
-			     domain->cfg.arm_lpae_s1_cfg.mair[0]);
+			     domain->cfg.arm_lpae_s1_cfg.mair);
 
 	/* IMBUSCR */
 	if (domain->mmu->features->setup_imbuscr)
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index c31e7bc4ccbe..66e9b40e9275 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -284,9 +284,9 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
 
 		/* MAIRs (stage-1 only) */
 		iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR0,
-				pgtbl_cfg.arm_lpae_s1_cfg.mair[0]);
+				pgtbl_cfg.arm_lpae_s1_cfg.mair);
 		iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR1,
-				pgtbl_cfg.arm_lpae_s1_cfg.mair[1]);
+				pgtbl_cfg.arm_lpae_s1_cfg.mair >> 32);
 
 		/* SCTLR */
 		reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_AFE | SCTLR_TRE |
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index ec7a13405f10..ee21eedafe98 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -102,7 +102,7 @@ struct io_pgtable_cfg {
 		struct {
 			u64	ttbr[2];
 			u64	tcr;
-			u64	mair[2];
+			u64	mair;
 		} arm_lpae_s1_cfg;
 
 		struct {
-- 
cgit v1.2.3


From 34d1b0895dbd10713c73615d8f532e78509e12d9 Mon Sep 17 00:00:00 2001
From: Jean-Philippe Brucker <jean-philippe@linaro.org>
Date: Mon, 11 Nov 2019 12:17:21 +0100
Subject: iommu/arm-smmu: Remove duplicate error message

Since commit 7723f4c5ecdb ("driver core: platform: Add an error message
to platform_get_irq*()"), platform_get_irq() displays an error when the
IRQ isn't found. Remove the error print from the SMMU driver. Note the
slight change of behaviour: no message is printed if platform_get_irq()
returns -EPROBE_DEFER, which probably doesn't concern the SMMU.

Fixes: 7723f4c5ecdb ("driver core: platform: Add an error message to platform_get_irq*()")
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Acked-by: Will Deacon <will@kernel.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/arm-smmu.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'drivers/iommu/arm-smmu.c')

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 424ebf38cd09..f05c821dd181 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -2095,10 +2095,8 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	for (i = 0; i < num_irqs; ++i) {
 		int irq = platform_get_irq(pdev, i);
 
-		if (irq < 0) {
-			dev_err(dev, "failed to get irq index %d\n", i);
+		if (irq < 0)
 			return -ENODEV;
-		}
 		smmu->irqs[i] = irq;
 	}
 
-- 
cgit v1.2.3