[PATCH v8 5/9] iommu/arm-smmu-v3: Make arm_smmu_alloc_cd_ptr()

[Jason Gunthorpe]

Only the attach callers can perform an allocation for the CD table entry,
the other callers must not do so, they do not have the correct locking and
they cannot sleep. Split up the functions so this is clear.

arm_smmu_get_cd_ptr() will return pointer to a CD table entry without
doing any kind of allocation.

arm_smmu_alloc_cd_ptr() will allocate the table and any required
leaf.

A following patch will add lockdep assertions to arm_smmu_alloc_cd_ptr()
once the restructuring is completed and arm_smmu_alloc_cd_ptr() is never
called in the wrong context.

Tested-by: Nicolin Chen <nicolinc at nvidia.com>
Reviewed-by: Nicolin Chen <nicolinc at nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg at nvidia.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 61 +++++++++++++--------
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  3 +-
 2 files changed, 40 insertions(+), 24 deletions(-)

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 14beba55c32ff2..e8da2f7763d102 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -97,6 +97,7 @@ static struct arm_smmu_option_prop arm_smmu_options[] = {
 
 static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain,
 				    struct arm_smmu_device *smmu);
+static int arm_smmu_alloc_cd_tables(struct arm_smmu_master *master);
 
 static void parse_driver_options(struct arm_smmu_device *smmu)
 {
@@ -1206,29 +1207,51 @@ static void arm_smmu_write_cd_l1_desc(__le64 *dst,
 struct arm_smmu_cd *arm_smmu_get_cd_ptr(struct arm_smmu_master *master,
 					u32 ssid)
 {
-	__le64 *l1ptr;
-	unsigned int idx;
 	struct arm_smmu_l1_ctx_desc *l1_desc;
-	struct arm_smmu_device *smmu = master->smmu;
 	struct arm_smmu_ctx_desc_cfg *cd_table = &master->cd_table;
 
+	if (!cd_table->cdtab)
+		return NULL;
+
 	if (cd_table->s1fmt == STRTAB_STE_0_S1FMT_LINEAR)
 		return (struct arm_smmu_cd *)(cd_table->cdtab +
 					      ssid * CTXDESC_CD_DWORDS);
 
-	idx = ssid >> CTXDESC_SPLIT;
-	l1_desc = &cd_table->l1_desc[idx];
-	if (!l1_desc->l2ptr) {
-		if (arm_smmu_alloc_cd_leaf_table(smmu, l1_desc))
-			return NULL;
+	l1_desc = &cd_table->l1_desc[ssid / CTXDESC_L2_ENTRIES];
+	if (!l1_desc->l2ptr)
+		return NULL;
+	return &l1_desc->l2ptr[ssid % CTXDESC_L2_ENTRIES];
+}
 
-		l1ptr = cd_table->cdtab + idx * CTXDESC_L1_DESC_DWORDS;
-		arm_smmu_write_cd_l1_desc(l1ptr, l1_desc);
-		/* An invalid L1CD can be cached */
-		arm_smmu_sync_cd(master, ssid, false);
+static struct arm_smmu_cd *arm_smmu_alloc_cd_ptr(struct arm_smmu_master *master,
+						 u32 ssid)
+{
+	struct arm_smmu_ctx_desc_cfg *cd_table = &master->cd_table;
+	struct arm_smmu_device *smmu = master->smmu;
+
+	if (!cd_table->cdtab) {
+		if (arm_smmu_alloc_cd_tables(master))
+			return NULL;
 	}
-	idx = ssid & (CTXDESC_L2_ENTRIES - 1);
-	return &l1_desc->l2ptr[idx];
+
+	if (cd_table->s1fmt == STRTAB_STE_0_S1FMT_64K_L2) {
+		unsigned int idx = ssid / CTXDESC_L2_ENTRIES;
+		struct arm_smmu_l1_ctx_desc *l1_desc;
+
+		l1_desc = &cd_table->l1_desc[idx];
+		if (!l1_desc->l2ptr) {
+			__le64 *l1ptr;
+
+			if (arm_smmu_alloc_cd_leaf_table(smmu, l1_desc))
+				return NULL;
+
+			l1ptr = cd_table->cdtab + idx * CTXDESC_L1_DESC_DWORDS;
+			arm_smmu_write_cd_l1_desc(l1ptr, l1_desc);
+			/* An invalid L1CD can be cached */
+			arm_smmu_sync_cd(master, ssid, false);
+		}
+	}
+	return arm_smmu_get_cd_ptr(master, ssid);
 }
 
 struct arm_smmu_cd_writer {
@@ -1354,7 +1377,7 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 	if (WARN_ON(ssid >= (1 << cd_table->s1cdmax)))
 		return -E2BIG;
 
-	cd_table_entry = arm_smmu_get_cd_ptr(master, ssid);
+	cd_table_entry = arm_smmu_alloc_cd_ptr(master, ssid);
 	if (!cd_table_entry)
 		return -ENOMEM;
 
@@ -2673,13 +2696,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		struct arm_smmu_cd target_cd;
 		struct arm_smmu_cd *cdptr;
 
-		if (!master->cd_table.cdtab) {
-			ret = arm_smmu_alloc_cd_tables(master);
-			if (ret)
-				goto out_list_del;
-		}
-
-		cdptr = arm_smmu_get_cd_ptr(master, IOMMU_NO_PASID);
+		cdptr = arm_smmu_alloc_cd_ptr(master, IOMMU_NO_PASID);
 		if (!cdptr) {
 			ret = -ENOMEM;
 			goto out_list_del;
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 99fd6f24caa818..c5c55d3e281865 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -275,8 +275,7 @@ struct arm_smmu_ste {
  * 2lvl: at most 1024 L1 entries,
  *       1024 lazy entries per table.
  */
-#define CTXDESC_SPLIT			10
-#define CTXDESC_L2_ENTRIES		(1 << CTXDESC_SPLIT)
+#define CTXDESC_L2_ENTRIES		1024
 
 #define CTXDESC_L1_DESC_DWORDS		1
 #define CTXDESC_L1_DESC_V		(1UL << 0)
-- 
2.43.2