When updating only within a 64-bit tuple of a DTE, just lock the DTE and
use WRITE_ONCE() because it is writing to memory read back by HW.

Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
---
 drivers/iommu/amd/amd_iommu.h |  1 +
 drivers/iommu/amd/iommu.c     | 43 +++++++++++++++++++----------------
 2 files changed, 25 insertions(+), 19 deletions(-)

diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 25c630bbcc0b..3bdceff30abf 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -179,3 +179,4 @@ struct dev_table_entry *get_dev_table(struct amd_iommu *iommu);
 #endif
 
 struct dev_table_entry *amd_iommu_get_ivhd_dte_flags(u16 segid, u16 devid);
+struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid);
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index f0ae0d7734b5..bfcf195736a5 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -333,7 +333,7 @@ static struct iommu_dev_data *alloc_dev_data(struct amd_iommu *iommu, u16 devid)
 	return dev_data;
 }
 
-static struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid)
+struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid)
 {
 	struct iommu_dev_data *dev_data;
 	struct llist_node *node;
@@ -2791,12 +2791,12 @@ static int amd_iommu_set_dirty_tracking(struct iommu_domain *domain,
 					bool enable)
 {
 	struct protection_domain *pdomain = to_pdomain(domain);
-	struct dev_table_entry *dev_table;
+	struct dev_table_entry *dte;
 	struct iommu_dev_data *dev_data;
 	bool domain_flush = false;
 	struct amd_iommu *iommu;
 	unsigned long flags;
-	u64 pte_root;
+	u64 new;
 
 	spin_lock_irqsave(&pdomain->lock, flags);
 	if (!(pdomain->dirty_tracking ^ enable)) {
@@ -2805,16 +2805,15 @@ static int amd_iommu_set_dirty_tracking(struct iommu_domain *domain,
 	}
 
 	list_for_each_entry(dev_data, &pdomain->dev_list, list) {
+		spin_lock(&dev_data->dte_lock);
 		iommu = get_amd_iommu_from_dev_data(dev_data);
-
-		dev_table = get_dev_table(iommu);
-		pte_root = dev_table[dev_data->devid].data[0];
-
-		pte_root = (enable ? pte_root | DTE_FLAG_HAD :
-				     pte_root & ~DTE_FLAG_HAD);
+		dte = &get_dev_table(iommu)[dev_data->devid];
+		new = READ_ONCE(dte->data[0]);
+		new = (enable ? new | DTE_FLAG_HAD : new & ~DTE_FLAG_HAD);
+		WRITE_ONCE(dte->data[0], new);
+		spin_unlock(&dev_data->dte_lock);
 
 		/* Flush device DTE */
-		dev_table[dev_data->devid].data[0] = pte_root;
 		device_flush_dte(dev_data);
 		domain_flush = true;
 	}
@@ -3079,17 +3078,23 @@ static void iommu_flush_irt_and_complete(struct amd_iommu *iommu, u16 devid)
 static void set_dte_irq_entry(struct amd_iommu *iommu, u16 devid,
 			      struct irq_remap_table *table)
 {
-	u64 dte;
-	struct dev_table_entry *dev_table = get_dev_table(iommu);
+	u64 new;
+	struct dev_table_entry *dte = &get_dev_table(iommu)[devid];
+	struct iommu_dev_data *dev_data = search_dev_data(iommu, devid);
+
+	if (dev_data)
+		spin_lock(&dev_data->dte_lock);
 
-	dte	= dev_table[devid].data[2];
-	dte	&= ~DTE_IRQ_PHYS_ADDR_MASK;
-	dte	|= iommu_virt_to_phys(table->table);
-	dte	|= DTE_IRQ_REMAP_INTCTL;
-	dte	|= DTE_INTTABLEN;
-	dte	|= DTE_IRQ_REMAP_ENABLE;
+	new = READ_ONCE(dte->data[2]);
+	new &= ~DTE_IRQ_PHYS_ADDR_MASK;
+	new |= iommu_virt_to_phys(table->table);
+	new |= DTE_IRQ_REMAP_INTCTL;
+	new |= DTE_INTTABLEN;
+	new |= DTE_IRQ_REMAP_ENABLE;
+	WRITE_ONCE(dte->data[2], new);
 
-	dev_table[devid].data[2] = dte;
+	if (dev_data)
+		spin_unlock(&dev_data->dte_lock);
 }
 
 static struct irq_remap_table *get_irq_table(struct amd_iommu *iommu, u16 devid)
-- 
2.34.1