[PATCH] amd iommu: force flush of iommu prior during shutdown

[Neil Horman]

Flush iommu during shutdown

When using an iommu, its possible, if a kdump kernel boot follows a primary
kernel crash, that dma operations might still be in flight from the previous
kernel during the kdump kernel boot.  This can lead to memory corruption,
crashes, and other erroneous behavior, specifically I've seen it manifest during
a kdump boot as endless iommu error log entries of the form:
AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.1 domain=0x000d
address=0x000000000245a0c0 flags=0x0070]

Followed by an inability to access hard drives, and various other resources.

I've written this fix for it.  In short it just forces a flush of the in flight
dma operations on shutdown, so that the new kernel is certain not to have any
in-flight dmas trying to complete after we've reset all the iommu page tables,
causing the above errors.  I've tested it and it fixes the problem for me quite
well.

Signed-off-by: Neil Horman <nhorman@xxxxxxxxxxxxx>


amd_iommu_init.c |   25 ++++++++++++++++++++++---
1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 9dc91b4..8fbdf58 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -265,8 +265,26 @@ static void iommu_enable(struct amd_iommu *iommu)
 	iommu_feature_enable(iommu, CONTROL_IOMMU_EN);
 }
 
-static void iommu_disable(struct amd_iommu *iommu)
+static void iommu_disable(struct amd_iommu *iommu, bool flush)
 {
+
+	/*
+	 * This ensures that all in-flight dmas for this iommu
+	 * are complete prior to shutting it down
+	 * its a bit racy, but I think its ok, given that if we're flushing
+	 * we're in a shutdown path (either a graceful shutdown or a
+	 * crash leading to a kdump boot.  That means we're down to one
+	 * cpu, and the other system hardware isn't going to issue
+	 * subsequent dma operations.
+	 * Also note that we gate the flusing on the flush boolean because
+	 * the enable_iommus path uses this function and we can't flush any
+	 * data in that path until later when the iommus are fully initialized
+	 */
+	if (flush) {
+		amd_iommu_flush_all_devices();
+		amd_iommu_flush_all_domains();
+	}
+
 	/* Disable command buffer */
 	iommu_feature_disable(iommu, CONTROL_CMDBUF_EN);
 
@@ -276,6 +294,7 @@ static void iommu_disable(struct amd_iommu *iommu)
 
 	/* Disable IOMMU hardware itself */
 	iommu_feature_disable(iommu, CONTROL_IOMMU_EN);
+
 }
 
 /*
@@ -1114,7 +1133,7 @@ static void enable_iommus(void)
 	struct amd_iommu *iommu;
 
 	for_each_iommu(iommu) {
-		iommu_disable(iommu);
+		iommu_disable(iommu, false);
 		iommu_set_device_table(iommu);
 		iommu_enable_command_buffer(iommu);
 		iommu_enable_event_buffer(iommu);
@@ -1129,7 +1148,7 @@ static void disable_iommus(void)
 	struct amd_iommu *iommu;
 
 	for_each_iommu(iommu)
-		iommu_disable(iommu);
+		iommu_disable(iommu, true);
 }
 
 /*
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/