[PATCH v7 0/6] iommu/arm-smmu: Enable split pagetable support

[PATCH v7 0/6] iommu/arm-smmu: Enable split pagetable support

[Jordan Crouse]

Another iteration of the split-pagetable support for arm-smmu and the Adreno GPU
SMMU. After email discussions [1] we opted to make a arm-smmu implementation for
specifically for the Adreno GPU and use that to enable split pagetable support
and later other implementation specific bits that we need.

On the hardware side this is very close to the same code from before [2] only
the TTBR1 quirk is turned on by the implementation and not a domain attribute.
In drm/msm we use the returned size of the aperture as a clue to let us know
which virtual address space we should use for global memory objects.

There are two open items that you should be aware of. First, in the
implementation specific code we have to check the compatible string of the
device so that we only enable TTBR1 for the GPU (SID 0) and not the GMU (SID 4).
I went back and forth trying to decide if I wanted to use the compatbile string
or the SID as the filter and settled on the compatible string but I could be
talked out of it.

The other open item is that in drm/msm the hardware only uses 49 bits of the
address space but arm-smmu expects the address to be sign extended all the way
to 64 bits. This isn't a problem normally unless you look at the hardware
registers that contain a IOVA and then the upper bits will be zero. I opted to
restrict the internal drm/msm IOVA range to only 49 bits and then sign extend
right before calling iommu_map / iommu_unmap. This is a bit wonky but I thought
that matching the hardware would be less confusing when debugging a hang.

[1] https://lists.linuxfoundation.org/pipermail/iommu/2020-May/044537.html
[2] https://patchwork.kernel.org/patch/11482591/


Jordan Crouse (6):
  iommu/arm-smmu: Pass io-pgtable config to implementation specific
    function
  iommu/arm-smmu: Add support for split pagetables
  dt-bindings: arm-smmu: Add compatible string for Adreno GPU SMMU
  iommu/arm-smmu: Add implementation for the adreno GPU SMMU
  drm/msm: Set the global virtual address range from the IOMMU domain
  arm6: dts: qcom: sm845: Set the compatible string for the GPU SMMU

 .../devicetree/bindings/iommu/arm,smmu.yaml   |  4 ++
 arch/arm64/boot/dts/qcom/sdm845.dtsi          |  2 +-
 drivers/gpu/drm/msm/adreno/adreno_gpu.c       | 13 ++++++-
 drivers/gpu/drm/msm/msm_iommu.c               |  7 ++++
 drivers/iommu/arm-smmu-impl.c                 |  6 ++-
 drivers/iommu/arm-smmu-qcom.c                 | 38 ++++++++++++++++++-
 drivers/iommu/arm-smmu.c                      | 32 +++++++++++-----
 drivers/iommu/arm-smmu.h                      | 29 ++++++++++----
 8 files changed, 108 insertions(+), 23 deletions(-)

-- 
2.17.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v7 1/6] iommu/arm-smmu: Pass io-pgtable config to implementation specific function

[Jordan Crouse]

Construct the io-pgtable config before calling the implementation specific
init_context function and pass it so the implementation specific function
can get a chance to change it before the io-pgtable is created.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
---

 drivers/iommu/arm-smmu-impl.c |  3 ++-
 drivers/iommu/arm-smmu.c      | 11 ++++++-----
 drivers/iommu/arm-smmu.h      |  3 ++-
 3 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c
index c75b9d957b70..a20e426d81ac 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -68,7 +68,8 @@ static int cavium_cfg_probe(struct arm_smmu_device *smmu)
 	return 0;
 }
 
-static int cavium_init_context(struct arm_smmu_domain *smmu_domain)
+static int cavium_init_context(struct arm_smmu_domain *smmu_domain,
+		struct io_pgtable_cfg *pgtbl_cfg)
 {
 	struct cavium_smmu *cs = container_of(smmu_domain->smmu,
 					      struct cavium_smmu, smmu);
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 243bc4cb2705..8a3a6c8c887a 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -797,11 +797,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		cfg->asid = cfg->cbndx;
 
 	smmu_domain->smmu = smmu;
-	if (smmu->impl && smmu->impl->init_context) {
-		ret = smmu->impl->init_context(smmu_domain);
-		if (ret)
-			goto out_unlock;
-	}
 
 	pgtbl_cfg = (struct io_pgtable_cfg) {
 		.pgsize_bitmap	= smmu->pgsize_bitmap,
@@ -812,6 +807,12 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		.iommu_dev	= smmu->dev,
 	};
 
+	if (smmu->impl && smmu->impl->init_context) {
+		ret = smmu->impl->init_context(smmu_domain, &pgtbl_cfg);
+		if (ret)
+			goto out_unlock;
+	}
+
 	if (smmu_domain->non_strict)
 		pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
 
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index d172c024be61..38b041530a4f 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -383,7 +383,8 @@ struct arm_smmu_impl {
 			    u64 val);
 	int (*cfg_probe)(struct arm_smmu_device *smmu);
 	int (*reset)(struct arm_smmu_device *smmu);
-	int (*init_context)(struct arm_smmu_domain *smmu_domain);
+	int (*init_context)(struct arm_smmu_domain *smmu_domain,
+			struct io_pgtable_cfg *cfg);
 	void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync,
 			 int status);
 	int (*def_domain_type)(struct device *dev);
-- 
2.17.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v7 2/6] iommu/arm-smmu: Add support for split pagetables

[Jordan Crouse]

Enable TTBR1 for a context bank if IO_PGTABLE_QUIRK_ARM_TTBR1 is selected
by the io-pgtable configuration.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
---

 drivers/iommu/arm-smmu.c | 21 ++++++++++++++++-----
 drivers/iommu/arm-smmu.h | 25 +++++++++++++++++++------
 2 files changed, 35 insertions(+), 11 deletions(-)

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 8a3a6c8c887a..048de2681670 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -555,11 +555,15 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 			cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr;
 			cb->ttbr[1] = 0;
 		} else {
-			cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
-			cb->ttbr[0] |= FIELD_PREP(ARM_SMMU_TTBRn_ASID,
-						  cfg->asid);
+			cb->ttbr[0] = FIELD_PREP(ARM_SMMU_TTBRn_ASID,
+				cfg->asid);
 			cb->ttbr[1] = FIELD_PREP(ARM_SMMU_TTBRn_ASID,
-						 cfg->asid);
+				cfg->asid);
+
+			if (pgtbl_cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+				cb->ttbr[1] |= pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
+			else
+				cb->ttbr[0] |= pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
 		}
 	} else {
 		cb->ttbr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
@@ -824,7 +828,14 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 
 	/* Update the domain's page sizes to reflect the page table format */
 	domain->pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
-	domain->geometry.aperture_end = (1UL << ias) - 1;
+
+	if (pgtbl_cfg.quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) {
+		domain->geometry.aperture_start = ~0UL << ias;
+		domain->geometry.aperture_end = ~0UL;
+	} else {
+		domain->geometry.aperture_end = (1UL << ias) - 1;
+	}
+
 	domain->geometry.force_aperture = true;
 
 	/* Initialise the context bank with our page table cfg */
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index 38b041530a4f..5f2de20e883b 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -168,10 +168,12 @@ enum arm_smmu_cbar_type {
 #define ARM_SMMU_CB_TCR			0x30
 #define ARM_SMMU_TCR_EAE		BIT(31)
 #define ARM_SMMU_TCR_EPD1		BIT(23)
+#define ARM_SMMU_TCR_A1			BIT(22)
 #define ARM_SMMU_TCR_TG0		GENMASK(15, 14)
 #define ARM_SMMU_TCR_SH0		GENMASK(13, 12)
 #define ARM_SMMU_TCR_ORGN0		GENMASK(11, 10)
 #define ARM_SMMU_TCR_IRGN0		GENMASK(9, 8)
+#define ARM_SMMU_TCR_EPD0		BIT(7)
 #define ARM_SMMU_TCR_T0SZ		GENMASK(5, 0)
 
 #define ARM_SMMU_VTCR_RES1		BIT(31)
@@ -347,12 +349,23 @@ struct arm_smmu_domain {
 
 static inline u32 arm_smmu_lpae_tcr(struct io_pgtable_cfg *cfg)
 {
-	return ARM_SMMU_TCR_EPD1 |
-	       FIELD_PREP(ARM_SMMU_TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) |
-	       FIELD_PREP(ARM_SMMU_TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) |
-	       FIELD_PREP(ARM_SMMU_TCR_ORGN0, cfg->arm_lpae_s1_cfg.tcr.orgn) |
-	       FIELD_PREP(ARM_SMMU_TCR_IRGN0, cfg->arm_lpae_s1_cfg.tcr.irgn) |
-	       FIELD_PREP(ARM_SMMU_TCR_T0SZ, cfg->arm_lpae_s1_cfg.tcr.tsz);
+	u32 tcr = FIELD_PREP(ARM_SMMU_TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) |
+		FIELD_PREP(ARM_SMMU_TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) |
+		FIELD_PREP(ARM_SMMU_TCR_ORGN0, cfg->arm_lpae_s1_cfg.tcr.orgn) |
+		FIELD_PREP(ARM_SMMU_TCR_IRGN0, cfg->arm_lpae_s1_cfg.tcr.irgn) |
+		FIELD_PREP(ARM_SMMU_TCR_T0SZ, cfg->arm_lpae_s1_cfg.tcr.tsz);
+
+       /*
+	* When TTBR1 is selected shift the TCR fields by 16 bits and disable
+	* translation in TTBR0
+	*/
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) {
+		tcr = (tcr << 16) & ~ARM_SMMU_TCR_A1;
+		tcr |= ARM_SMMU_TCR_EPD0;
+	} else
+		tcr |= ARM_SMMU_TCR_EPD1;
+
+	return tcr;
 }
 
 static inline u32 arm_smmu_lpae_tcr2(struct io_pgtable_cfg *cfg)
-- 
2.17.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v7 3/6] dt-bindings: arm-smmu: Add compatible string for Adreno GPU SMMU

[Jordan Crouse]

Every Qcom Adreno GPU has an embedded SMMU for its own use. These
devices depend on unique features such as split pagetables,
different stall/halt requirements and other settings. Identify them
with a compatible string so that they can be identified in the
arm-smmu implementation specific code.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
---

 Documentation/devicetree/bindings/iommu/arm,smmu.yaml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index d7ceb4c34423..e52a1b146c97 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -38,6 +38,10 @@ properties:
               - qcom,sc7180-smmu-500
               - qcom,sdm845-smmu-500
           - const: arm,mmu-500
+      - description: Qcom Adreno GPUs implementing "arm,smmu-v2"
+        items:
+          - const: qcom,adreno-smmu
+          - const: qcom,smmu-v2
       - items:
           - const: arm,mmu-500
           - const: arm,smmu-v2
-- 
2.17.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v7 4/6] iommu/arm-smmu: Add implementation for the adreno GPU SMMU

[Jordan Crouse]

Add a special implementation for the SMMU attached to most Adreno GPU
target triggered from the qcom,adreno-gpu-smmu compatible string. When
selected the driver will attempt to enable split pagetables.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
---

 drivers/iommu/arm-smmu-impl.c |  5 ++++-
 drivers/iommu/arm-smmu-qcom.c | 38 +++++++++++++++++++++++++++++++++--
 drivers/iommu/arm-smmu.c      |  2 +-
 drivers/iommu/arm-smmu.h      |  3 ++-
 4 files changed, 43 insertions(+), 5 deletions(-)

diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c
index a20e426d81ac..3bb1ef4e85f7 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -69,7 +69,7 @@ static int cavium_cfg_probe(struct arm_smmu_device *smmu)
 }
 
 static int cavium_init_context(struct arm_smmu_domain *smmu_domain,
-		struct io_pgtable_cfg *pgtbl_cfg)
+		struct io_pgtable_cfg *pgtbl_cfg, struct device *dev)
 {
 	struct cavium_smmu *cs = container_of(smmu_domain->smmu,
 					      struct cavium_smmu, smmu);
@@ -176,5 +176,8 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 	    of_device_is_compatible(np, "qcom,sc7180-smmu-500"))
 		return qcom_smmu_impl_init(smmu);
 
+	if (of_device_is_compatible(smmu->dev->of_node, "qcom,adreno-smmu"))
+		return qcom_adreno_smmu_impl_init(smmu);
+
 	return smmu;
 }
diff --git a/drivers/iommu/arm-smmu-qcom.c b/drivers/iommu/arm-smmu-qcom.c
index be4318044f96..cc03f94fa458 100644
--- a/drivers/iommu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm-smmu-qcom.c
@@ -12,6 +12,22 @@ struct qcom_smmu {
 	struct arm_smmu_device smmu;
 };
 
+static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
+		struct io_pgtable_cfg *pgtbl_cfg, struct device *dev)
+{
+	/*
+	 * All targets that use the qcom,adreno-smmu compatible string *should*
+	 * be AARCH64 stage 1 but double check because the arm-smmu code assumes
+	 * that is the case when the TTBR1 quirk is enabled
+	 */
+	if (of_device_is_compatible(dev->of_node, "qcom,adreno") &&
+	    (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) &&
+	    (smmu_domain->cfg.fmt == ARM_SMMU_CTX_FMT_AARCH64))
+		pgtbl_cfg->quirks |= IO_PGTABLE_QUIRK_ARM_TTBR1;
+
+	return 0;
+}
+
 static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,adreno" },
 	{ .compatible = "qcom,mdp4" },
@@ -65,7 +81,15 @@ static const struct arm_smmu_impl qcom_smmu_impl = {
 	.reset = qcom_smmu500_reset,
 };
 
-struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)
+static const struct arm_smmu_impl qcom_adreno_smmu_impl = {
+	.init_context = qcom_adreno_smmu_init_context,
+	.def_domain_type = qcom_smmu_def_domain_type,
+	.reset = qcom_smmu500_reset,
+};
+
+
+static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
+		const struct arm_smmu_impl *impl)
 {
 	struct qcom_smmu *qsmmu;
 
@@ -75,8 +99,18 @@ struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)
 
 	qsmmu->smmu = *smmu;
 
-	qsmmu->smmu.impl = &qcom_smmu_impl;
+	qsmmu->smmu.impl = impl;
 	devm_kfree(smmu->dev, smmu);
 
 	return &qsmmu->smmu;
 }
+
+struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	return qcom_smmu_create(smmu, &qcom_smmu_impl);
+}
+
+struct arm_smmu_device *qcom_adreno_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	return qcom_smmu_create(smmu, &qcom_adreno_smmu_impl);
+}
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 048de2681670..f14dc4ecb422 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -812,7 +812,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	};
 
 	if (smmu->impl && smmu->impl->init_context) {
-		ret = smmu->impl->init_context(smmu_domain, &pgtbl_cfg);
+		ret = smmu->impl->init_context(smmu_domain, &pgtbl_cfg, dev);
 		if (ret)
 			goto out_unlock;
 	}
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index 5f2de20e883b..df70d410f77d 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -397,7 +397,7 @@ 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,
-			struct io_pgtable_cfg *cfg);
+			struct io_pgtable_cfg *cfg, struct device *dev);
 	void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync,
 			 int status);
 	int (*def_domain_type)(struct device *dev);
@@ -465,6 +465,7 @@ static inline void arm_smmu_writeq(struct arm_smmu_device *smmu, int page,
 
 struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu);
 struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu);
+struct arm_smmu_device *qcom_adreno_smmu_impl_init(struct arm_smmu_device *smmu);
 
 int arm_mmu500_reset(struct arm_smmu_device *smmu);
 
-- 
2.17.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu