diff mbox series

[v11,05/13] iommu/smmuv3: Get prepared for nested stage support

Message ID 20200414150607.28488-6-eric.auger@redhat.com (mailing list archive)
State New, archived
Headers show
Series SMMUv3 Nested Stage Setup (IOMMU part) | expand

Commit Message

Eric Auger April 14, 2020, 3:05 p.m. UTC
When nested stage translation is setup, both s1_cfg and
s2_cfg are allocated.

We introduce a new smmu domain abort field that will be set
upon guest stage1 configuration passing.

arm_smmu_write_strtab_ent() is modified to write both stage
fields in the STE and deal with the abort field.

In nested mode, only stage 2 is "finalized" as the host does
not own/configure the stage 1 context descriptor; guest does.

Signed-off-by: Eric Auger <eric.auger@redhat.com>

---
v10 -> v11:
- Fix an issue reported by Shameer when switching from with vSMMU
  to without vSMMU. Despite the spec does not seem to mention it
  seems to be needed to reset the 2 high 64b when switching from
  S1+S2 cfg to S1 only. Especially dst[3] needs to be reset (S2TTB).
  On some implementations, if the S2TTB is not reset, this causes
  a C_BAD_STE error

v7 -> v8:
- rebase on 8be39a1a04c1 iommu/arm-smmu-v3: Add a master->domain
  pointer
- restore live checks for not nested cases and add s1_live and
  s2_live to be more previse. Remove bypass local variable.
  In STE live case, move the ste to abort state and send a
  CFGI_STE before updating the rest of the fields.
- check s2ttb in case of live s2

v4 -> v5:
- reset ste.abort on detach

v3 -> v4:
- s1_cfg.nested_abort and nested_bypass removed.
- s/ste.nested/ste.abort
- arm_smmu_write_strtab_ent modifications with introduction
  of local abort, bypass and translate local variables
- comment updated
---
 drivers/iommu/arm-smmu-v3.c | 68 +++++++++++++++++++++++++++++++------
 1 file changed, 58 insertions(+), 10 deletions(-)
diff mbox series

Patch

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index da3739bb7323..dd3c12034e84 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -223,6 +223,7 @@ 
 #define STRTAB_STE_0_CFG_BYPASS		4
 #define STRTAB_STE_0_CFG_S1_TRANS	5
 #define STRTAB_STE_0_CFG_S2_TRANS	6
+#define STRTAB_STE_0_CFG_NESTED		7
 
 #define STRTAB_STE_0_S1FMT		GENMASK_ULL(5, 4)
 #define STRTAB_STE_0_S1FMT_LINEAR	0
@@ -721,6 +722,7 @@  struct arm_smmu_domain {
 	enum arm_smmu_domain_stage	stage;
 	struct arm_smmu_s1_cfg		*s1_cfg;
 	struct arm_smmu_s2_cfg		*s2_cfg;
+	bool				abort;
 
 	struct iommu_domain		domain;
 
@@ -1807,8 +1809,10 @@  static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	 * three cases at the moment:
 	 *
 	 * 1. Invalid (all zero) -> bypass/fault (init)
-	 * 2. Bypass/fault -> translation/bypass (attach)
-	 * 3. Translation/bypass -> bypass/fault (detach)
+	 * 2. Bypass/fault -> single stage translation/bypass (attach)
+	 * 3. Single or nested stage Translation/bypass -> bypass/fault (detach)
+	 * 4. S2 -> S1 + S2 (attach_pasid_table)
+	 * 5. S1 + S2 -> S2 (detach_pasid_table)
 	 *
 	 * Given that we can't update the STE atomically and the SMMU
 	 * doesn't read the thing in a defined order, that leaves us
@@ -1819,7 +1823,8 @@  static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	 * 3. Update Config, sync
 	 */
 	u64 val = le64_to_cpu(dst[0]);
-	bool ste_live = false;
+	bool abort, translate, s1_live = false, s2_live = false, ste_live;
+	bool nested = false;
 	struct arm_smmu_device *smmu = NULL;
 	struct arm_smmu_s1_cfg *s1_cfg = NULL;
 	struct arm_smmu_s2_cfg *s2_cfg = NULL;
@@ -1839,6 +1844,7 @@  static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	if (smmu_domain) {
 		s1_cfg = smmu_domain->s1_cfg;
 		s2_cfg = smmu_domain->s2_cfg;
+		nested = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
 	}
 
 	if (val & STRTAB_STE_0_V) {
@@ -1846,23 +1852,37 @@  static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		case STRTAB_STE_0_CFG_BYPASS:
 			break;
 		case STRTAB_STE_0_CFG_S1_TRANS:
+			s1_live = true;
+			break;
 		case STRTAB_STE_0_CFG_S2_TRANS:
-			ste_live = true;
+			s2_live = true;
+			break;
+		case STRTAB_STE_0_CFG_NESTED:
+			s1_live = true;
+			s2_live = true;
 			break;
 		case STRTAB_STE_0_CFG_ABORT:
-			BUG_ON(!disable_bypass);
 			break;
 		default:
 			BUG(); /* STE corruption */
 		}
 	}
 
+	ste_live = s1_live || s2_live;
+
 	/* Nuke the existing STE_0 value, as we're going to rewrite it */
 	val = STRTAB_STE_0_V;
 
 	/* Bypass/fault */
-	if (!smmu_domain || !(s1_cfg || s2_cfg)) {
-		if (!smmu_domain && disable_bypass)
+
+	if (!smmu_domain)
+		abort = disable_bypass;
+	else
+		abort = smmu_domain->abort;
+	translate = s1_cfg || s2_cfg;
+
+	if (abort || !translate) {
+		if (abort)
 			val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_ABORT);
 		else
 			val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
@@ -1880,8 +1900,18 @@  static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		return;
 	}
 
+	/* S1 or S2 translation */
+
+	BUG_ON(ste_live && !nested);
+
+	if (ste_live) {
+		/* First invalidate the live STE */
+		dst[0] = cpu_to_le64(STRTAB_STE_0_CFG_ABORT);
+		arm_smmu_sync_ste_for_sid(smmu, sid);
+	}
+
 	if (s1_cfg) {
-		BUG_ON(ste_live);
+		BUG_ON(s1_live);
 		dst[1] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) |
 			 FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
@@ -1900,7 +1930,14 @@  static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	}
 
 	if (s2_cfg) {
-		BUG_ON(ste_live);
+		u64 vttbr = s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK;
+
+		if (s2_live) {
+			u64 s2ttb = le64_to_cpu(dst[3] & STRTAB_STE_3_S2TTB_MASK);
+
+			BUG_ON(s2ttb != vttbr);
+		}
+
 		dst[2] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) |
 			 FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) |
@@ -1910,9 +1947,12 @@  static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 			 STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 |
 			 STRTAB_STE_2_S2R);
 
-		dst[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
+		dst[3] = cpu_to_le64(vttbr);
 
 		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS);
+	} else {
+		dst[2] = 0;
+		dst[3] = 0;
 	}
 
 	if (master->ats_enabled)
@@ -2602,6 +2642,14 @@  static int arm_smmu_domain_finalise(struct iommu_domain *domain,
 		return 0;
 	}
 
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED &&
+	    (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1) ||
+	     !(smmu->features & ARM_SMMU_FEAT_TRANS_S2))) {
+		dev_info(smmu_domain->smmu->dev,
+			 "does not implement two stages\n");
+		return -EINVAL;
+	}
+
 	/* Restrict the stage to what we can actually support */
 	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1))
 		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;