iommu/amd: Use report_iommu_fault()

This patch makes iommu/amd call report_iommu_fault() when an I/O page
fault occurs, which has two effects:

1) It allows device drivers to register a callback to be notified of
   I/O page faults, via the iommu_set_fault_handler() API.

2) It triggers the io_page_fault tracepoint in report_iommu_fault()
   when an I/O page fault occurs.

The latter point is the main aim of this patch, as it allows
rasdaemon-like daemons to be notified of I/O page faults, and to
possibly initiate corrective action in response.

A number of other IOMMU drivers already use report_iommu_fault(), and
I/O page faults on those IOMMUs therefore already trigger this
tracepoint -- but this isn't yet the case for AMD-Vi and Intel DMAR.

The AMD IOMMU specification suggests that the bit in an I/O page fault
event log entry that signals whether an I/O page fault was for a read
request or for a write request is only meaningful when the faulting
access was to a present page, but some testing on a Ryzen 3700X suggests
that this bit encodes the correct value even for I/O page faults to
non-present pages, and therefore, this patch passes the R/W information
up the stack even for I/O page faults to non-present pages.
Signed-off-by: Lennert Buytenhek <buytenh@arista.com>
Link: https://lore.kernel.org/r/YVLyBW97vZLpOaAp@wantstofly.orgSigned-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/amd/amd_iommu_types.h

@@ -138,6 +138,8 @@
 #define EVENT_DOMID_MASK_HI	0xf0000
 #define EVENT_FLAGS_MASK	0xfff
 #define EVENT_FLAGS_SHIFT	0x10
+#define EVENT_FLAG_RW		0x020
+#define EVENT_FLAG_I		0x008
 
 /* feature control bits */
 #define CONTROL_IOMMU_EN        0x00ULL

drivers/iommu/amd/iommu.c

@@ -473,6 +473,12 @@ static void amd_iommu_report_rmp_fault(volatile u32 *event)
 		pci_dev_put(pdev);
 }
 
+#define IS_IOMMU_MEM_TRANSACTION(flags)		\
+	(((flags) & EVENT_FLAG_I) == 0)
+
+#define IS_WRITE_REQUEST(flags)			\
+	((flags) & EVENT_FLAG_RW)
+
 static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 					u64 address, int flags)
 {
@@ -485,6 +491,20 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 		dev_data = dev_iommu_priv_get(&pdev->dev);
 
 	if (dev_data) {
+		/*
+		 * If this is a DMA fault (for which the I(nterrupt)
+		 * bit will be unset), allow report_iommu_fault() to
+		 * prevent logging it.
+		 */
+		if (IS_IOMMU_MEM_TRANSACTION(flags)) {
+			if (!report_iommu_fault(&dev_data->domain->domain,
+						&pdev->dev, address,
+						IS_WRITE_REQUEST(flags) ?
+							IOMMU_FAULT_WRITE :
+							IOMMU_FAULT_READ))
+				goto out;
+		}
+
 		if (__ratelimit(&dev_data->rs)) {
 			pci_err(pdev, "Event logged [IO_PAGE_FAULT domain=0x%04x address=0x%llx flags=0x%04x]\n",
 				domain_id, address, flags);
@@ -495,6 +515,7 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 			domain_id, address, flags);
 	}
 
+out:
 	if (pdev)
 		pci_dev_put(pdev);
 }