diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -160,6 +160,7 @@ struct amdgpu_watchdog_timer {
  * Modules parameters.
  */
 extern int amdgpu_modeset;
+extern int amdgpu_iommu_perfopt;
 extern unsigned int amdgpu_vram_limit;
 extern int amdgpu_vis_vram_limit;
 extern int amdgpu_gart_size;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -33,6 +33,7 @@
 #include <linux/console.h>
 #include <linux/slab.h>
 #include <linux/iommu.h>
+#include <linux/amd-iommu.h>
 #include <linux/pci.h>
 #include <linux/pci-p2pdma.h>
 #include <linux/apple-gmux.h>
@@ -3842,6 +3843,28 @@ amdgpu_device_should_register_switcheroo(struct amdgpu_device *adev, bool px)
 		       apple_gmux_detect(NULL, NULL)));
 }
 
+static inline bool amdgpu_device_identity(struct amdgpu_device *adev)
+{
+	struct pci_dev *pdev = adev->pdev;
+	struct iommu_domain *domain = iommu_get_domain_for_dev(&pdev->dev);
+
+	if (!domain)
+		return false;
+
+	return domain->type == IOMMU_DOMAIN_IDENTITY;
+}
+
+static bool amdgpu_device_use_perfopt(struct amdgpu_device *adev)
+{
+	if (amdgpu_iommu_perfopt == 0)
+		return false;
+
+	if (!(adev->flags & AMD_IS_APU))
+		return false;
+
+	return amdgpu_device_identity(adev);
+}
+
 /**
  * amdgpu_device_init - initialize the driver
  *
@@ -4048,6 +4071,16 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
+	if (amdgpu_device_use_perfopt(adev)) {
+		int perfopt_ret = amd_iommu_enable_perfopt(pdev);
+
+		/* Optional optimization; a failure to arm it must not abort probe. */
+		if (perfopt_ret)
+			dev_warn(adev->dev,
+				 "Failed to enable IOMMU PerfOpt (%d); continuing without it\n",
+				 perfopt_ret);
+	}
+
 	/*
 	 * No need to remove conflicting FBs for non-display class devices.
 	 * This prevents the sysfb from being freed accidently.
@@ -4416,6 +4449,9 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 
 	amdgpu_gart_dummy_page_fini(adev);
 
+	if (amdgpu_device_use_perfopt(adev))
+		amd_iommu_disable_perfopt(adev->pdev);
+
 	if (pci_dev_is_disconnected(adev->pdev))
 		amdgpu_device_unmap_mmio(adev);
 
@@ -4779,6 +4815,20 @@ int amdgpu_device_resume(struct drm_device *dev, bool notify_clients)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
+	if (amdgpu_device_use_perfopt(adev)) {
+		int perfopt_ret = amd_iommu_enable_perfopt(adev->pdev);
+
+		/*
+		 * Must not return on failure: a bare return would leak the
+		 * SR-IOV VF exclusive-mode acquisition taken above (released
+		 * via the exit: path).
+		 */
+		if (perfopt_ret)
+			dev_warn(adev->dev,
+				 "Failed to enable IOMMU PerfOpt (%d); continuing without it\n",
+				 perfopt_ret);
+	}
+
 	if (adev->in_s0ix)
 		amdgpu_dpm_gfx_state_change(adev, sGpuChangeState_D0Entry);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -185,6 +185,7 @@ char *amdgpu_disable_cu;
 char *amdgpu_virtual_display;
 int amdgpu_enforce_isolation = -1;
 int amdgpu_modeset = -1;
+int amdgpu_iommu_perfopt = -1;
 
 /* Specifies the default granularity for SVM, used in buffer
  * migration and restoration of backing memory when handling
@@ -393,6 +394,17 @@ module_param_named(fw_load_type, amdgpu_fw_load_type, int, 0444);
 MODULE_PARM_DESC(aspm, "ASPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(aspm, amdgpu_aspm, int, 0444);
 
+/**
+ * DOC: iommu_perfopt (int)
+ * Control the AMD IOMMU PerfOpt DMA-latency optimization
+ * (0 = disable; -1 = enable on supported devices).
+ * This arms the IOMMU PerfOpt control (IOMMU spec, MMIO Offset 016Ch, EFR PerfOptSup / PerfOptEn)
+ * Arming it disables ATS, PRI, PASID and SVA for the GPU and removes IOMMU DMA containment for it,
+ * trading isolation for lower DMA latency.
+ */
+MODULE_PARM_DESC(iommu_perfopt, "Control IOMMU PerfOpt DMA-latency optimization (-1 = enable on supported devices, 0 = disable)");
+module_param_named(iommu_perfopt, amdgpu_iommu_perfopt, int, 0444);
+
 /**
  * DOC: runpm (int)
  * Override for runtime power management control for dGPUs. The amdgpu driver can dynamically power down