iommu/amd: serialize sequence allocation under concurrent TLB invalidations

With concurrent TLB invalidations, completion wait randomly gets timed out
because cmd_sem_val was incremented outside the IOMMU spinlock, allowing
CMD_COMPL_WAIT commands to be queued out of sequence and breaking the
ordering assumption in wait_on_sem().
Move the cmd_sem_val increment under iommu->lock so completion sequence
allocation is serialized with command queuing.
And remove the unnecessary return.

Fixes: d2a0cac ("iommu/amd: move wait_on_sem() out of spinlock")

Tested-by: Srikanth Aithal <sraithal@amd.com>
Reported-by: Srikanth Aithal <sraithal@amd.com>
Signed-off-by: Ankit Soni <Ankit.Soni@amd.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

Author: ankitvvsoni

drivers/iommu/amd/amd_iommu_types.h

@@ -752,7 +752,7 @@ struct amd_iommu {
 
 	u32 flags;
 	volatile u64 *cmd_sem;
-	atomic64_t cmd_sem_val;
+	u64 cmd_sem_val;
 	/*
 	 * Track physical address to directly use it in build_completion_wait()
 	 * and avoid adding any special checks and handling for kdump.

drivers/iommu/amd/init.c

@@ -1885,7 +1885,7 @@ 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);
-	atomic64_set(&iommu->cmd_sem_val, 0);
+	iommu->cmd_sem_val = 0;
 
 	/* Add IOMMU to internal data structures */
 	list_add_tail(&iommu->list, &amd_iommu_list);

drivers/iommu/amd/iommu.c

@@ -1439,6 +1439,12 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
 	return iommu_queue_command_sync(iommu, cmd, true);
 }
 
+static u64 get_cmdsem_val(struct amd_iommu *iommu)
+{
+	lockdep_assert_held(&iommu->lock);
+	return ++iommu->cmd_sem_val;
+}
+
 /*
  * This function queues a completion wait command into the command
  * buffer of an IOMMU
@@ -1453,11 +1459,11 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 	if (!iommu->need_sync)
 		return 0;
 
-	data = atomic64_inc_return(&iommu->cmd_sem_val);
-	build_completion_wait(&cmd, iommu, data);
-
 	raw_spin_lock_irqsave(&iommu->lock, flags);
 
+	data = get_cmdsem_val(iommu);
+	build_completion_wait(&cmd, iommu, data);
+
 	ret = __iommu_queue_command_sync(iommu, &cmd, false);
 	raw_spin_unlock_irqrestore(&iommu->lock, flags);
 
@@ -3177,10 +3183,11 @@ static void iommu_flush_irt_and_complete(struct amd_iommu *iommu, u16 devid)
 		return;
 
 	build_inv_irt(&cmd, devid);
-	data = atomic64_inc_return(&iommu->cmd_sem_val);
-	build_completion_wait(&cmd2, iommu, data);
 
 	raw_spin_lock_irqsave(&iommu->lock, flags);
+	data = get_cmdsem_val(iommu);
+	build_completion_wait(&cmd2, iommu, data);
+
 	ret = __iommu_queue_command_sync(iommu, &cmd, true);
 	if (ret)
 		goto out_err;
@@ -3194,7 +3201,6 @@ static void iommu_flush_irt_and_complete(struct amd_iommu *iommu, u16 devid)
 
 out_err:
 	raw_spin_unlock_irqrestore(&iommu->lock, flags);
-	return;
 }
 
 static inline u8 iommu_get_int_tablen(struct iommu_dev_data *dev_data)