iommupt/vtd: Support mgaw's less than a 4 level walk for first stage

If the IOVA is limited to less than 48 the page table will be constructed
with a 3 level configuration which is unsupported by hardware.

Like the second stage the caller needs to pass in both the top_level an
the vasz to specify a table that has more levels than required to hold the
IOVA range.

Fixes: 6cbc09b ("iommu/vt-d: Restore previous domain::aperture_end calculation")
Reported-by: Calvin Owens <calvin@wbinvd.org>
Closes: https://lore.kernel.org/r/8f257d2651eb8a4358fcbd47b0145002e5f1d638.1764237717.git.calvin@wbinvd.org
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Tested-by: Calvin Owens <calvin@wbinvd.org>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

Author: jgunthorpe

drivers/iommu/amd/iommu.c

@@ -2708,10 +2708,13 @@ static struct iommu_domain *amd_iommu_domain_alloc_paging_v2(struct device *dev,
 	 * in both modes the top bit is removed and PT_FEAT_SIGN_EXTEND is not
 	 * set which creates a table that is compatible in both modes.
 	 */
-	if (amd_iommu_gpt_level == PAGE_MODE_5_LEVEL)
+	if (amd_iommu_gpt_level == PAGE_MODE_5_LEVEL) {
 		cfg.common.hw_max_vasz_lg2 = 56;
-	else
+		cfg.top_level = 4;
+	} else {
 		cfg.common.hw_max_vasz_lg2 = 47;
+		cfg.top_level = 3;
+	}
 	cfg.common.hw_max_oasz_lg2 = 52;
 	domain->domain.ops = &amdv2_ops;
 

drivers/iommu/generic_pt/fmt/x86_64.h

@@ -241,13 +241,10 @@ x86_64_pt_iommu_fmt_init(struct pt_iommu_x86_64 *iommu_table,
 {
 	struct pt_x86_64 *table = &iommu_table->x86_64_pt;
 
-	if (cfg->common.hw_max_vasz_lg2 < 31 ||
-	    cfg->common.hw_max_vasz_lg2 > 57)
-		return -EINVAL;
+	if (cfg->top_level < 3 || cfg->top_level > 4)
+		return -EOPNOTSUPP;
 
-	/* Top of 2, 3, 4 */
-	pt_top_set_level(&table->common,
-			 (cfg->common.hw_max_vasz_lg2 - 31) / 9 + 2);
+	pt_top_set_level(&table->common, cfg->top_level);
 
 	table->common.max_oasz_lg2 =
 		min(PT_MAX_OUTPUT_ADDRESS_LG2, cfg->common.hw_max_oasz_lg2);
@@ -269,12 +266,12 @@ x86_64_pt_iommu_fmt_hw_info(struct pt_iommu_x86_64 *table,
 #if defined(GENERIC_PT_KUNIT)
 static const struct pt_iommu_x86_64_cfg x86_64_kunit_fmt_cfgs[] = {
 	[0] = { .common.features = BIT(PT_FEAT_SIGN_EXTEND),
-		.common.hw_max_vasz_lg2 = 48 },
+		.common.hw_max_vasz_lg2 = 48, .top_level = 3 },
 	[1] = { .common.features = BIT(PT_FEAT_SIGN_EXTEND),
-		.common.hw_max_vasz_lg2 = 57 },
+		.common.hw_max_vasz_lg2 = 57, .top_level = 4 },
 	/* AMD IOMMU PASID 0 formats with no SIGN_EXTEND */
-	[2] = { .common.hw_max_vasz_lg2 = 47 },
-	[3] = { .common.hw_max_vasz_lg2 = 56 },
+	[2] = { .common.hw_max_vasz_lg2 = 47, .top_level = 3 },
+	[3] = { .common.hw_max_vasz_lg2 = 56, .top_level = 4},
 };
 #define kunit_fmt_cfgs x86_64_kunit_fmt_cfgs
 enum { KUNIT_FMT_FEATURES =  BIT(PT_FEAT_SIGN_EXTEND)};

drivers/iommu/intel/iommu.c

@@ -2794,6 +2794,28 @@ static struct dmar_domain *paging_domain_alloc(void)
 	return domain;
 }
 
+static unsigned int compute_vasz_lg2_fs(struct intel_iommu *iommu,
+					unsigned int *top_level)
+{
+	unsigned int mgaw = cap_mgaw(iommu->cap);
+
+	/*
+	 * Spec 3.6 First-Stage Translation:
+	 *
+	 * Software must limit addresses to less than the minimum of MGAW
+	 * and the lower canonical address width implied by FSPM (i.e.,
+	 * 47-bit when FSPM is 4-level and 56-bit when FSPM is 5-level).
+	 */
+	if (mgaw > 48 && cap_fl5lp_support(iommu->cap)) {
+		*top_level = 4;
+		return min(57, mgaw);
+	}
+
+	/* Four level is always supported */
+	*top_level = 3;
+	return min(48, mgaw);
+}
+
 static struct iommu_domain *
 intel_iommu_domain_alloc_first_stage(struct device *dev,
 				     struct intel_iommu *iommu, u32 flags)
@@ -2813,20 +2835,8 @@ intel_iommu_domain_alloc_first_stage(struct device *dev,
 	if (IS_ERR(dmar_domain))
 		return ERR_CAST(dmar_domain);
 
-	if (cap_fl5lp_support(iommu->cap))
-		cfg.common.hw_max_vasz_lg2 = 57;
-	else
-		cfg.common.hw_max_vasz_lg2 = 48;
-
-	/*
-	 * Spec 3.6 First-Stage Translation:
-	 *
-	 * Software must limit addresses to less than the minimum of MGAW
-	 * and the lower canonical address width implied by FSPM (i.e.,
-	 * 47-bit when FSPM is 4-level and 56-bit when FSPM is 5-level).
-	 */
-	cfg.common.hw_max_vasz_lg2 = min(cap_mgaw(iommu->cap),
-					 cfg.common.hw_max_vasz_lg2);
+	cfg.common.hw_max_vasz_lg2 =
+		compute_vasz_lg2_fs(iommu, &cfg.top_level);
 	cfg.common.hw_max_oasz_lg2 = 52;
 	cfg.common.features = BIT(PT_FEAT_SIGN_EXTEND) |
 			      BIT(PT_FEAT_FLUSH_RANGE);

include/linux/generic_pt/iommu.h

@@ -277,6 +277,8 @@ IOMMU_FORMAT(vtdss, vtdss_pt);
 
 struct pt_iommu_x86_64_cfg {
 	struct pt_iommu_cfg common;
+	/* 4 is a 57 bit 5 level table */
+	unsigned int top_level;
 };
 
 struct pt_iommu_x86_64_hw_info {