[PATCH v8 2/3] iommu/arm-smmu-v3: Introduce CFGI/TLBI-repeat workaround infrastructure

[Ashish Mhetre]

Tegra264 SMMU instances need every CFGI/TLBI command sequence issued
twice, with the second issue executing only after the first issue's
CMD_SYNC has completed:

    TLBI/CFGI ... CMD_SYNC TLBI/CFGI ... CMD_SYNC

ATC_INV is not affected and must never be doubled.

Add arm_smmu_erratum_repeat_tlbi_cfgi_key and an
arm_smmu_erratum_cmd_needs_repeating() helper that gates on the static
key first and then range-checks the opcode (CFGI_STE .. ATC_INV), so
subsequent changes wiring the workaround into the CMDQ submission path
can share a single predicate.

Rename the existing arm_smmu_cmdq_issue_cmdlist() to
__arm_smmu_cmdq_issue_cmdlist() and add a thin wrapper of the original
name that re-issues the same cmdlist a second time when the predicate
fires. Host-internal callers go through the wrapper and get the repeat;
register the new condition with arm_smmu_cmdq_batch_force_sync() too.

The iommufd user-invalidation path (arm_vsmmu_cache_invalidate()) keeps
issuing user commands exactly once by calling the raw
__arm_smmu_cmdq_issue_cmdlist(). The erratum is reported to user space
in a subsequent change so an affected guest doubles its own CFGI/TLBI,
doubling them again on the host would be wrong.

No callers enable the static key yet, so there is no functional change.
A subsequent change will enable the key on affected instances.

Suggested-by: Nicolin Chen <nicolinc@xxxxxxxxxx>
Reviewed-by: Nicolin Chen <nicolinc@xxxxxxxxxx>
Reviewed-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
Signed-off-by: Ashish Mhetre <amhetre@xxxxxxxxxx>
---
 .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c     |  4 +-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   | 57 +++++++++++++++++--
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  5 ++
 3 files changed, 60 insertions(+), 6 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
index 85ebfdb3d2a7..032d0c272f3f 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
@@ -400,8 +400,8 @@ int arm_vsmmu_cache_invalidate(struct iommufd_viommu *viommu,
 			continue;
 
 		/* FIXME always uses the main cmdq rather than trying to group by type */
-		ret = arm_smmu_cmdq_issue_cmdlist(smmu, &smmu->cmdq, &last->cmd,
-						  cur - last, true);
+		ret = __arm_smmu_cmdq_issue_cmdlist(smmu, &smmu->cmdq, &last->cmd,
+						    cur - last, true);
 		if (ret) {
 			cur--;
 			goto out;
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 dd7475c50afc..f0f8b2daf8d5 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/io-pgtable.h>
 #include <linux/iopoll.h>
+#include <linux/jump_label.h>
 #include <linux/module.h>
 #include <linux/msi.h>
 #include <linux/of.h>
@@ -42,6 +43,14 @@ MODULE_PARM_DESC(disable_msipolling,
 static const struct iommu_ops arm_smmu_ops;
 static struct iommu_dirty_ops arm_smmu_dirty_ops;
 
+/*
+ * Repeat every {CFGI,TLBI};CMD_SYNC command sequence so that the second
+ * issue executes only after the first issue's CMD_SYNC has completed.
+ * Does not apply to ATC_INV. The key is global and is enabled from DT
+ * probe on affected hardware (currently Tegra264 only).
+ */
+static DEFINE_STATIC_KEY_FALSE(arm_smmu_erratum_repeat_tlbi_cfgi_key);
+
 enum arm_smmu_msi_index {
 	EVTQ_MSI_INDEX,
 	GERROR_MSI_INDEX,
@@ -698,10 +707,10 @@ static void arm_smmu_cmdq_write_entries(struct arm_smmu_cmdq *cmdq,
  *   insert their own list of commands then all of the commands from one
  *   CPU will appear before any of the commands from the other CPU.
  */
-int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
-				struct arm_smmu_cmdq *cmdq,
-				struct arm_smmu_cmd *cmds, int n,
-				bool sync)
+int __arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
+				  struct arm_smmu_cmdq *cmdq,
+				  struct arm_smmu_cmd *cmds, int n,
+				  bool sync)
 {
 	struct arm_smmu_cmd cmd_sync;
 	u32 prod;
@@ -820,6 +829,38 @@ int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
 	return ret;
 }
 
+bool arm_smmu_erratum_cmd_needs_repeating(struct arm_smmu_cmd *cmd)
+{
+	u8 opcode;
+
+	if (!static_branch_unlikely(&arm_smmu_erratum_repeat_tlbi_cfgi_key))
+		return false;
+
+	opcode = FIELD_GET(CMDQ_0_OP, cmd->data[0]);
+	return opcode >= CMDQ_OP_CFGI_STE && opcode < CMDQ_OP_ATC_INV;
+}
+
+int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
+				struct arm_smmu_cmdq *cmdq,
+				struct arm_smmu_cmd *cmds, int n,
+				bool sync)
+{
+	int ret = __arm_smmu_cmdq_issue_cmdlist(smmu, cmdq, cmds, n, sync);
+
+	/*
+	 * A bare CMD_SYNC can be issued with n == 0 (e.g. an empty
+	 * batch_submit()), in which case there is no cmds[0] to inspect
+	 * and nothing to repeat.
+	 */
+	if (!n || ret || !sync)
+		return ret;
+
+	if (arm_smmu_erratum_cmd_needs_repeating(&cmds[0]))
+		ret = __arm_smmu_cmdq_issue_cmdlist(smmu, cmdq, cmds, n, sync);
+
+	return ret;
+}
+
 static int arm_smmu_cmdq_issue_cmd_p(struct arm_smmu_device *smmu,
 				     struct arm_smmu_cmd *cmd, bool sync)
 {
@@ -860,6 +901,14 @@ static bool arm_smmu_cmdq_batch_force_sync(struct arm_smmu_device *smmu,
 	    (smmu->options & ARM_SMMU_OPT_CMDQ_FORCE_SYNC))
 		return true;
 
+	/*
+	 * See the description at arm_smmu_erratum_repeat_tlbi_cfgi_key. Batches
+	 * never mix CFGI/TLBI with others, so checking cmds[0] alone is enough.
+	 */
+	if (cmds->num == CMDQ_BATCH_ENTRIES &&
+	    arm_smmu_erratum_cmd_needs_repeating(&cmds->cmds[0]))
+		return true;
+
 	return false;
 }
 
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 c909c9a88538..9508bf50d14c 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -1207,10 +1207,15 @@ void arm_smmu_attach_commit(struct arm_smmu_attach_state *state);
 void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master,
 				  const struct arm_smmu_ste *target);
 
+int __arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
+				  struct arm_smmu_cmdq *cmdq,
+				  struct arm_smmu_cmd *cmds, int n,
+				  bool sync);
 int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
 				struct arm_smmu_cmdq *cmdq,
 				struct arm_smmu_cmd *cmds, int n,
 				bool sync);
+bool arm_smmu_erratum_cmd_needs_repeating(struct arm_smmu_cmd *cmd);
 
 #ifdef CONFIG_ARM_SMMU_V3_SVA
 bool arm_smmu_sva_supported(struct arm_smmu_device *smmu);
-- 
2.50.1