[PATCH v3 04/12] iommu/arm-smmu-v3: Add support for Hardware Translation Table Update

[Keqian Zhu <zhukeqian1@huawei.com>]

From: Jean-Philippe Brucker <jean-philippe@linaro.org>

If the SMMU supports it and the kernel was built with HTTU support,
enable hardware update of access and dirty flags. This is essential for
shared page tables, to reduce the number of access faults on the fault
queue. Normal DMA with io-pgtables doesn't currently use the access or
dirty flags.

We can enable HTTU even if CPUs don't support it, because the kernel
always checks for HW dirty bit and updates the PTE flags atomically.

Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
---
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c   |  2 +
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   | 41 ++++++++++++++++++-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  8 ++++
 3 files changed, 50 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index bb251cab61f3..ae075e675892 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -121,10 +121,12 @@ static struct arm_smmu_ctx_desc *arm_smmu_alloc_shared_cd(struct mm_struct *mm)
 	if (err)
 		goto out_free_asid;
 
+	/* HA and HD will be filtered out later if not supported by the SMMU */
 	tcr = FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, 64ULL - vabits_actual) |
 	      FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, ARM_LPAE_TCR_RGN_WBWA) |
 	      FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, ARM_LPAE_TCR_RGN_WBWA) |
 	      FIELD_PREP(CTXDESC_CD_0_TCR_SH0, ARM_LPAE_TCR_SH_IS) |
+	      CTXDESC_CD_0_TCR_HA | CTXDESC_CD_0_TCR_HD |
 	      CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64;
 
 	switch (PAGE_SIZE) {
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 8594b4a83043..b6d965504f44 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1012,10 +1012,17 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
 		 * this substream's traffic
 		 */
 	} else { /* (1) and (2) */
+		u64 tcr = cd->tcr;
+
 		cdptr[1] = cpu_to_le64(cd->ttbr & CTXDESC_CD_1_TTB0_MASK);
 		cdptr[2] = 0;
 		cdptr[3] = cpu_to_le64(cd->mair);
 
+		if (!(smmu->features & ARM_SMMU_FEAT_HD))
+			tcr &= ~CTXDESC_CD_0_TCR_HD;
+		if (!(smmu->features & ARM_SMMU_FEAT_HA))
+			tcr &= ~CTXDESC_CD_0_TCR_HA;
+
 		/*
 		 * STE is live, and the SMMU might read dwords of this CD in any
 		 * order. Ensure that it observes valid values before reading
@@ -1023,7 +1030,7 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
 		 */
 		arm_smmu_sync_cd(smmu_domain, ssid, true);
 
-		val = cd->tcr |
+		val = tcr |
 #ifdef __BIG_ENDIAN
 			CTXDESC_CD_0_ENDI |
 #endif
@@ -3196,6 +3203,28 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
 	return 0;
 }
 
+static void arm_smmu_get_httu(struct arm_smmu_device *smmu, u32 reg)
+{
+	u32 fw_features = smmu->features & (ARM_SMMU_FEAT_HA | ARM_SMMU_FEAT_HD);
+	u32 features = 0;
+
+	switch (FIELD_GET(IDR0_HTTU, reg)) {
+	case IDR0_HTTU_ACCESS_DIRTY:
+		features |= ARM_SMMU_FEAT_HD;
+		fallthrough;
+	case IDR0_HTTU_ACCESS:
+		features |= ARM_SMMU_FEAT_HA;
+	}
+
+	if (smmu->dev->of_node)
+		smmu->features |= features;
+	else if (features != fw_features)
+		/* ACPI IORT sets the HTTU bits */
+		dev_warn(smmu->dev,
+			 "IDR0.HTTU overridden by FW configuration (0x%x)\n",
+			 fw_features);
+}
+
 static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 {
 	u32 reg;
@@ -3256,6 +3285,8 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 			smmu->features |= ARM_SMMU_FEAT_E2H;
 	}
 
+	arm_smmu_get_httu(smmu, reg);
+
 	/*
 	 * The coherency feature as set by FW is used in preference to the ID
 	 * register, but warn on mismatch.
@@ -3441,6 +3472,14 @@ static int arm_smmu_device_acpi_probe(struct platform_device *pdev,
 	if (iort_smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE)
 		smmu->features |= ARM_SMMU_FEAT_COHERENCY;
 
+	switch (FIELD_GET(ACPI_IORT_SMMU_V3_HTTU_OVERRIDE, iort_smmu->flags)) {
+	case IDR0_HTTU_ACCESS_DIRTY:
+		smmu->features |= ARM_SMMU_FEAT_HD;
+		fallthrough;
+	case IDR0_HTTU_ACCESS:
+		smmu->features |= ARM_SMMU_FEAT_HA;
+	}
+
 	return 0;
 }
 #else
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index f985817c967a..26d6b935b383 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -33,6 +33,9 @@
 #define IDR0_ASID16			(1 << 12)
 #define IDR0_ATS			(1 << 10)
 #define IDR0_HYP			(1 << 9)
+#define IDR0_HTTU			GENMASK(7, 6)
+#define IDR0_HTTU_ACCESS		1
+#define IDR0_HTTU_ACCESS_DIRTY		2
 #define IDR0_COHACC			(1 << 4)
 #define IDR0_TTF			GENMASK(3, 2)
 #define IDR0_TTF_AARCH64		2
@@ -285,6 +288,9 @@
 #define CTXDESC_CD_0_TCR_IPS		GENMASK_ULL(34, 32)
 #define CTXDESC_CD_0_TCR_TBI0		(1ULL << 38)
 
+#define CTXDESC_CD_0_TCR_HA		(1UL << 43)
+#define CTXDESC_CD_0_TCR_HD		(1UL << 42)
+
 #define CTXDESC_CD_0_AA64		(1UL << 41)
 #define CTXDESC_CD_0_S			(1UL << 44)
 #define CTXDESC_CD_0_R			(1UL << 45)
@@ -607,6 +613,8 @@ struct arm_smmu_device {
 #define ARM_SMMU_FEAT_BTM		(1 << 16)
 #define ARM_SMMU_FEAT_SVA		(1 << 17)
 #define ARM_SMMU_FEAT_E2H		(1 << 18)
+#define ARM_SMMU_FEAT_HA		(1 << 19)
+#define ARM_SMMU_FEAT_HD		(1 << 20)
 	u32				features;
 
 #define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)
-- 
2.19.1