iommu/amd: Improving Interrupt Remapping Table Invalidation

Invalidating Interrupt Remapping Table (IRT) requires, the AMD IOMMU driver
to issue INVALIDATE_INTERRUPT_TABLE and COMPLETION_WAIT commands.
Currently, the driver issues the two commands separately, which requires
calling raw_spin_lock_irqsave() twice. In addition, the COMPLETION_WAIT
could potentially be interleaved with other commands causing delay of
the COMPLETION_WAIT command.

Therefore, combine issuing of the two commands in one spin-lock, and
changing struct amd_iommu.cmd_sem_val to use atomic64 to minimize
locking.

Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20230530141137.14376-6-suravee.suthikulpanit@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>

Author: ssuthiku-amd

drivers/iommu/amd/amd_iommu_types.h

@@ -752,7 +752,7 @@ struct amd_iommu {
 
 	u32 flags;
 	volatile u64 *cmd_sem;
-	u64 cmd_sem_val;
+	atomic64_t cmd_sem_val;
 
 #ifdef CONFIG_AMD_IOMMU_DEBUGFS
 	/* DebugFS Info */

drivers/iommu/amd/init.c

@@ -1733,7 +1733,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h,
 	iommu->pci_seg = pci_seg;
 
 	raw_spin_lock_init(&iommu->lock);
-	iommu->cmd_sem_val = 0;
+	atomic64_set(&iommu->cmd_sem_val, 0);
 
 	/* Add IOMMU to internal data structures */
 	list_add_tail(&iommu->list, &amd_iommu_list);

drivers/iommu/amd/iommu.c

@@ -1175,11 +1175,11 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 	if (!iommu->need_sync)
 		return 0;
 
-	raw_spin_lock_irqsave(&iommu->lock, flags);
-
-	data = ++iommu->cmd_sem_val;
+	data = atomic64_add_return(1, &iommu->cmd_sem_val);
 	build_completion_wait(&cmd, iommu, data);
 
+	raw_spin_lock_irqsave(&iommu->lock, flags);
+
 	ret = __iommu_queue_command_sync(iommu, &cmd, false);
 	if (ret)
 		goto out_unlock;
@@ -1277,11 +1277,28 @@ static void amd_iommu_flush_irt_all(struct amd_iommu *iommu)
 
 static void iommu_flush_irt_and_complete(struct amd_iommu *iommu, u16 devid)
 {
+	int ret;
+	u64 data;
+	unsigned long flags;
+	struct iommu_cmd cmd, cmd2;
+
 	if (iommu->irtcachedis_enabled)
 		return;
 
-	iommu_flush_irt(iommu, devid);
-	iommu_completion_wait(iommu);
+	build_inv_irt(&cmd, devid);
+	data = atomic64_add_return(1, &iommu->cmd_sem_val);
+	build_completion_wait(&cmd2, iommu, data);
+
+	raw_spin_lock_irqsave(&iommu->lock, flags);
+	ret = __iommu_queue_command_sync(iommu, &cmd, true);
+	if (ret)
+		goto out;
+	ret = __iommu_queue_command_sync(iommu, &cmd2, false);
+	if (ret)
+		goto out;
+	wait_on_sem(iommu, data);
+out:
+	raw_spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
 void iommu_flush_all_caches(struct amd_iommu *iommu)