iommu/vt-d: Allow devices to have more than 32 outstanding PRs

The minimum per-IOMMU PRQ queue size is one 4K page, this is more entries
than the hardcoded limit of 32 in the current VT-d code. Some devices can
support up to 512 outstanding PRQs but underutilized by this limit of 32.
Although, 32 gives some rough fairness when multiple devices share the same
IOMMU PRQ queue, but far from optimal for customized use case. This extends
the per-IOMMU PRQ queue size to four 4K pages and let the devices have as
many outstanding page requests as they can.
Signed-off-by: NJacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: NLu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20210720013856.4143880-1-baolu.lu@linux.intel.com
Link: https://lore.kernel.org/r/20210818134852.1847070-7-baolu.lu@linux.intel.comSigned-off-by: NJoerg Roedel <jroedel@suse.de>

drivers/iommu/intel/iommu.c

@@ -33,6 +33,7 @@
 #include <linux/iommu.h>
 #include <linux/dma-iommu.h>
 #include <linux/intel-iommu.h>
+#include <linux/intel-svm.h>
 #include <linux/syscore_ops.h>
 #include <linux/tboot.h>
 #include <linux/dmi.h>
@@ -1541,7 +1542,7 @@ static void iommu_enable_dev_iotlb(struct device_domain_info *info)
 
 	if (info->pri_supported &&
 	    (info->pasid_enabled ? pci_prg_resp_pasid_required(pdev) : 1)  &&
-	    !pci_reset_pri(pdev) && !pci_enable_pri(pdev, 32))
+	    !pci_reset_pri(pdev) && !pci_enable_pri(pdev, PRQ_DEPTH))
 		info->pri_enabled = 1;
 #endif
 	if (info->ats_supported && pci_ats_page_aligned(pdev) &&

drivers/iommu/intel/svm.c

@@ -31,8 +31,6 @@ static irqreturn_t prq_event_thread(int irq, void *d);
 static void intel_svm_drain_prq(struct device *dev, u32 pasid);
 #define to_intel_svm_dev(handle) container_of(handle, struct intel_svm_dev, sva)
 
-#define PRQ_ORDER 0
-
 static DEFINE_XARRAY_ALLOC(pasid_private_array);
 static int pasid_private_add(ioasid_t pasid, void *priv)
 {
@@ -724,8 +722,6 @@ struct page_req_dsc {
 	u64 priv_data[2];
 };
 
-#define PRQ_RING_MASK	((0x1000 << PRQ_ORDER) - 0x20)
-
 static bool is_canonical_address(u64 addr)
 {
 	int shift = 64 - (__VIRTUAL_MASK_SHIFT + 1);

include/linux/intel-svm.h

@@ -14,6 +14,11 @@
 #define SVM_REQ_EXEC	(1<<1)
 #define SVM_REQ_PRIV	(1<<0)
 
+/* Page Request Queue depth */
+#define PRQ_ORDER	2
+#define PRQ_RING_MASK	((0x1000 << PRQ_ORDER) - 0x20)
+#define PRQ_DEPTH	((0x1000 << PRQ_ORDER) >> 5)
+
 /*
  * The SVM_FLAG_SUPERVISOR_MODE flag requests a PASID which can be used only
  * for access to kernel addresses. No IOTLB flushes are automatically done