[PATCH v4 12/22] iommu/smmuv3: Get prepared for nested stage support

[Eric Auger]

To allow nested stage support, we need to store both
stage 1 and stage 2 configurations (and remove the former
union).

A nested setup is characterized by both s1_cfg and s2_cfg
set. If s1_cfg is NULL, if ste.abort is set, traffic can't pass.
If abort is not set, S1 is bypassed. Abort can be induced by the
guest of by the host.

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

Only S2 stage is "finalized" as the host does not configure
S1 CD, guest does.

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

---

v2 -> v3:
- 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

v1 -> v2:
- invalidate the STE before moving from a live STE config to another
- add the nested_abort and nested_bypass fields
---
 drivers/iommu/arm-smmu-v3.c | 34 +++++++++++++++++++---------------
 1 file changed, 19 insertions(+), 15 deletions(-)

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 9af68266bbb1..80ab9a77cf80 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -212,6 +212,7 @@
 #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
@@ -515,6 +516,7 @@ struct arm_smmu_strtab_ent {
 	 * configured according to the domain type.
 	 */
 	bool				assigned;
+	bool				abort;
 	struct arm_smmu_s1_cfg		*s1_cfg;
 	struct arm_smmu_s2_cfg		*s2_cfg;
 };
@@ -629,10 +631,8 @@ struct arm_smmu_domain {
 	bool				non_strict;
 
 	enum arm_smmu_domain_stage	stage;
-	union {
-		struct arm_smmu_s1_cfg	s1_cfg;
-		struct arm_smmu_s2_cfg	s2_cfg;
-	};
+	struct arm_smmu_s1_cfg	s1_cfg;
+	struct arm_smmu_s2_cfg	s2_cfg;
 
 	struct iommu_domain		domain;
 
@@ -1109,12 +1109,13 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 				      __le64 *dst, struct arm_smmu_strtab_ent *ste)
 {
 	/*
-	 * This is hideously complicated, but we only really care about
-	 * three cases at the moment:
+	 * We care about the following transitions:
 	 *
 	 * 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 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
@@ -1125,7 +1126,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 	 * 3. Update Config, sync
 	 */
 	u64 val = le64_to_cpu(dst[0]);
-	bool ste_live = false;
+	bool abort, bypass, translate, ste_live = false;
 	struct arm_smmu_cmdq_ent prefetch_cmd = {
 		.opcode		= CMDQ_OP_PREFETCH_CFG,
 		.prefetch	= {
@@ -1139,11 +1140,11 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 			break;
 		case STRTAB_STE_0_CFG_S1_TRANS:
 		case STRTAB_STE_0_CFG_S2_TRANS:
+		case STRTAB_STE_0_CFG_NESTED:
 			ste_live = true;
 			break;
 		case STRTAB_STE_0_CFG_ABORT:
-			if (disable_bypass)
-				break;
+			break;
 		default:
 			BUG(); /* STE corruption */
 		}
@@ -1153,8 +1154,13 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 	val = STRTAB_STE_0_V;
 
 	/* Bypass/fault */
-	if (!ste->assigned || !(ste->s1_cfg || ste->s2_cfg)) {
-		if (!ste->assigned && disable_bypass)
+
+	abort = (!ste->assigned && disable_bypass) || ste->abort;
+	translate = ste->s1_cfg || ste->s2_cfg;
+	bypass = !abort && !translate;
+
+	if (abort || bypass) {
+		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);
@@ -1173,7 +1179,6 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 	}
 
 	if (ste->s1_cfg) {
-		BUG_ON(ste_live);
 		dst[1] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
 			 FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) |
@@ -1192,7 +1197,6 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 	}
 
 	if (ste->s2_cfg) {
-		BUG_ON(ste_live);
 		dst[2] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_2_S2VMID, ste->s2_cfg->vmid) |
 			 FIELD_PREP(STRTAB_STE_2_VTCR, ste->s2_cfg->vtcr) |
-- 
2.20.1