iommu/amd: Recover from event log overflow

BugLink: https://bugs.launchpad.net/bugs/1964361
commit 5ce97f4ec5e0f8726a5dda1710727b1ee9badcac upstream.

The AMD IOMMU logs I/O page faults and such to a ring buffer in
system memory, and this ring buffer can overflow.  The AMD IOMMU
spec has the following to say about the interrupt status bit that
signals this overflow condition:

	EventOverflow: Event log overflow. RW1C. Reset 0b. 1 = IOMMU
	event log overflow has occurred. This bit is set when a new
	event is to be written to the event log and there is no usable
	entry in the event log, causing the new event information to
	be discarded. An interrupt is generated when EventOverflow = 1b
	and MMIO Offset 0018h[EventIntEn] = 1b. No new event log
	entries are written while this bit is set. Software Note: To
	resume logging, clear EventOverflow (W1C), and write a 1 to
	MMIO Offset 0018h[EventLogEn].

The AMD IOMMU driver doesn't currently implement this recovery
sequence, meaning that if a ring buffer overflow occurs, logging
of EVT/PPR/GA events will cease entirely.

This patch implements the spec-mandated reset sequence, with the
minor tweak that the hardware seems to want to have a 0 written to
MMIO Offset 0018h[EventLogEn] first, before writing an 1 into this
field, or the IOMMU won't actually resume logging events.

Signed-off-by: Lennert Buytenhek <buytenh@arista.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/YVrSXEdW2rzEfOvk@wantstofly.org
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Paolo Pisati <paolo.pisati@canonical.com>

diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 416815a525d671916a896297b67b28006bb03236..bb95edf74415b0a6806237ade2382c8090e1b465 100644 (file)
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -14,6 +14,7 @@
 extern irqreturn_t amd_iommu_int_thread(int irq, void *data);
 extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
 extern void amd_iommu_apply_erratum_63(u16 devid);
+extern void amd_iommu_restart_event_logging(struct amd_iommu *iommu);
 extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
 extern int amd_iommu_init_devices(void);
 extern void amd_iommu_uninit_devices(void);

diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 8394c2787ff890ddb389ef824ae414e5efb61406..b6e0bf186cf5468c44ea34f0a5a9e56e2e5ba334 100644 (file)
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -110,6 +110,7 @@
 #define PASID_MASK             0x0000ffff
 
 /* MMIO status bits */
+#define MMIO_STATUS_EVT_OVERFLOW_INT_MASK      (1 << 0)
 #define MMIO_STATUS_EVT_INT_MASK       (1 << 1)
 #define MMIO_STATUS_COM_WAIT_INT_MASK  (1 << 2)
 #define MMIO_STATUS_PPR_INT_MASK       (1 << 6)

diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 72cad85e5e5f3511ac03312d7b3dc6e796c1357e..204ed33c56dce5ee780d52e6b19b32d0ee63f162 100644 (file)
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -655,6 +655,16 @@ static int __init alloc_command_buffer(struct amd_iommu *iommu)
        return iommu->cmd_buf ? 0 : -ENOMEM;
 }
 
+/*
+ * This function restarts event logging in case the IOMMU experienced
+ * an event log buffer overflow.
+ */
+void amd_iommu_restart_event_logging(struct amd_iommu *iommu)
+{
+       iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN);
+       iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
+}
+
 /*
  * This function resets the command buffer if the IOMMU stopped fetching
  * commands from it.

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index bdb150e0a18b3e7779e92f625b9b2e3f94d03c48..d425586b67546ac54803dae617eab7b78fb8df0f 100644 (file)
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -742,7 +742,8 @@ amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) { }
 #endif /* !CONFIG_IRQ_REMAP */
 
 #define AMD_IOMMU_INT_MASK     \
-       (MMIO_STATUS_EVT_INT_MASK | \
+       (MMIO_STATUS_EVT_OVERFLOW_INT_MASK | \
+        MMIO_STATUS_EVT_INT_MASK | \
         MMIO_STATUS_PPR_INT_MASK | \
         MMIO_STATUS_GALOG_INT_MASK)
 
@@ -752,7 +753,7 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data)
        u32 status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
 
        while (status & AMD_IOMMU_INT_MASK) {
-               /* Enable EVT and PPR and GA interrupts again */
+               /* Enable interrupt sources again */
                writel(AMD_IOMMU_INT_MASK,
                        iommu->mmio_base + MMIO_STATUS_OFFSET);
 
@@ -773,6 +774,11 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data)
                }
 #endif
 
+               if (status & MMIO_STATUS_EVT_OVERFLOW_INT_MASK) {
+                       pr_info_ratelimited("IOMMU event log overflow\n");
+                       amd_iommu_restart_event_logging(iommu);
+               }
+
                /*
                 * Hardware bug: ERBT1312
                 * When re-enabling interrupt (by writing 1