Lennert,
On 7/26/2021 11:31 AM, Lennert Buytenhek wrote:
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.
I'm mainly interested in (2). We have a daemon with some rasdaemon-like
functionality for handling platform errors, and being able to be notified
of I/O page faults for initiating corrective action is very useful -- and
receiving such events via event tracing is a lot nicer than having to
scrape them from kmsg.
A number of other IOMMU drivers already use report_iommu_fault(), and
I/O page faults on those IOMMUs therefore already seem to trigger this
tracepoint -- but this isn't (yet) the case for AMD-Vi and Intel DMAR.
I copied the logic from the other callers of report_iommu_fault(), where
if that function returns zero, the driver will have handled the fault,
in which case we avoid logging information about the fault to the printk
buffer from the IOMMU driver.
With this patch I see io_page_fault event tracing entries as expected:
irq/24-AMD-Vi-48 [002] .... 978.554289: io_page_fault: IOMMU:[drvname]
0000:05:00.0 iova=0x0000000091482640 flags=0x0000
irq/24-AMD-Vi-48 [002] .... 978.554294: io_page_fault: IOMMU:[drvname]
0000:05:00.0 iova=0x0000000091482650 flags=0x0000
irq/24-AMD-Vi-48 [002] .... 978.554299: io_page_fault: IOMMU:[drvname]
0000:05:00.0 iova=0x0000000091482660 flags=0x0000
irq/24-AMD-Vi-48 [002] .... 978.554305: io_page_fault: IOMMU:[drvname]
0000:05:00.0 iova=0x0000000091482670 flags=0x0000
irq/24-AMD-Vi-48 [002] .... 978.554310: io_page_fault: IOMMU:[drvname]
0000:05:00.0 iova=0x0000000091482680 flags=0x0000
irq/24-AMD-Vi-48 [002] .... 978.554315: io_page_fault: IOMMU:[drvname]
0000:05:00.0 iova=0x00000000914826a0 flags=0x0000
For determining IOMMU_FAULT_{READ,WRITE}, I followed the AMD IOMMU
spec, but I haven't tested that bit of the code, as the page faults I
encounter are all to non-present (!EVENT_FLAG_PR) mappings, in which
case EVENT_FLAG_RW doesn't make sense.
Signed-off-by: Lennert Buytenhek <buyt...@wantstofly.org>
---
Changes since v1 RFC:
- Don't call report_iommu_fault() for IRQ remapping faults.
(Suggested by Joerg Roedel.)
drivers/iommu/amd/amd_iommu_types.h | 4 ++++
drivers/iommu/amd/iommu.c | 29 +++++++++++++++++++++++++++++
2 files changed, 33 insertions(+)
diff --git a/drivers/iommu/amd/amd_iommu_types.h
b/drivers/iommu/amd/amd_iommu_types.h
index 94c1a7a9876d..2f2c6630c24c 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -138,6 +138,10 @@
#define EVENT_DOMID_MASK_HI 0xf0000
#define EVENT_FLAGS_MASK 0xfff
#define EVENT_FLAGS_SHIFT 0x10
+#define EVENT_FLAG_TR 0x100
+#define EVENT_FLAG_RW 0x020
+#define EVENT_FLAG_PR 0x010
+#define EVENT_FLAG_I 0x008
/* feature control bits */
#define CONTROL_IOMMU_EN 0x00ULL
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index a7d6d78147b7..d9fb2c22d44a 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
What if we introduce:
+/*
+ * AMD I/O Virtualization Technology (IOMMU) Specification,
+ * revision 3.00, section 2.5.3 ("IO_PAGE_FAULT Event") says
+ * that the RW ("read-write") bit is only valid if the I/O
+ * page fault was caused by a memory transaction request
+ * referencing a page that was marked present.
+ */
+#define IO_PAGE_FAULT_MEM_MASK \
+ (EVENT_FLAG_TR | EVENT_FLAG_PR | EVENT_FLAG_I)
+#define IS_IOMMU_MEM_TRANSACTION(x) \
+ ((x & IO_PAGE_FAULT_MEM_MASK) == EVENT_FLAG_PR)
Note that this should have already checked w/ EVENT_FLAG_I == 0.
@@ -484,6 +484,34 @@ static void amd_iommu_report_page_fault(u16 devid, u16
domain_id,
if (pdev)
dev_data = dev_iommu_priv_get(&pdev->dev);
+ /*
+ * If this is a DMA fault (for which the I(nterrupt) bit will
+ * be unset), allow report_iommu_fault() to prevent logging it.
+ */
+ if (dev_data && ((flags & EVENT_FLAG_I) == 0)) {
+ int report_flags;
+
+ /*
+ * AMD I/O Virtualization Technology (IOMMU) Specification,
+ * revision 3.00, section 2.5.3 ("IO_PAGE_FAULT Event") says
+ * that the RW ("read-write") bit is only valid if the I/O
+ * page fault was caused by a memory transaction request
+ * referencing a page that was marked present.
+ */
+ report_flags = 0;
+ if ((flags & (EVENT_FLAG_TR | EVENT_FLAG_PR)) ==
+ EVENT_FLAG_PR) {
+ if (flags & EVENT_FLAG_RW)
+ report_flags |= IOMMU_FAULT_WRITE;
+ else
+ report_flags |= IOMMU_FAULT_READ;
+ }
+
+ if (!report_iommu_fault(&dev_data->domain->domain,
+ &pdev->dev, address, report_flags))
+ goto out;
+ }
+
if (dev_data) {
Here we do:
+ /*
+ * Since report_iommu_fault() only report DMA-remapping related
fault,
+ * convert AMD IO_PAGE_FAULT flags to IOMMU_FAULT_xx flags.
+ */
+ if (IS_IOMMU_MEM_TRANSACTION(flags) &&
+ !report_iommu_fault(&dev_data->domain->domain, &pdev->dev,
+ address,
+ (flags & EVENT_FLAG_RW) ?
+ IOMMU_FAULT_WRITE : IOMMU_FAULT_READ))
+ goto out;
+
Regards,
Suravee
if (__ratelimit(&dev_data->rs)) {
pci_err(pdev, "Event logged [IO_PAGE_FAULT domain=0x%04x
address=0x%llx flags=0x%04x]\n",
@@ -495,6 +523,7 @@ static void amd_iommu_report_page_fault(u16 devid, u16
domain_id,
domain_id, address, flags);
}
+out:
if (pdev)
pci_dev_put(pdev);
}
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
