[PATCH] amd/iommu: flush old domains in kdump kernel

[Stuart Hayes]

When devices are attached to the amd_iommu in a kdump kernel, the old device
table entries (DTEs), which were copied from the crashed kernel, will be
overwritten with a new domain number.  When the new DTE is written, the IOMMU
is told to flush the DTE from its internal cache--but it is not told to flush
the translation cache entries for the old domain number.

Without this patch, AMD systems using the tg3 network driver fail when kdump
tries to save the vmcore to a network system, showing network timeouts and
(sometimes) IOMMU errors in the kernel log.

This patch will flush IOMMU translation cache entries for the old domain when
a DTE gets overwritten with a new domain number.


Signed-off-by: Stuart Hayes <stuart.w.hayes@xxxxxxxxx>

---

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index b607a92..f853b96 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1143,6 +1143,17 @@ static void amd_iommu_flush_tlb_all(struct amd_iommu *iommu)
 	iommu_completion_wait(iommu);
 }
 
+static void amd_iommu_flush_tlb_domid(struct amd_iommu *iommu, u32 dom_id)
+{
+	struct iommu_cmd cmd;
+
+	build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
+			      dom_id, 1);
+	iommu_queue_command(iommu, &cmd);
+
+	iommu_completion_wait(iommu);
+}
+
 static void amd_iommu_flush_all(struct amd_iommu *iommu)
 {
 	struct iommu_cmd cmd;
@@ -1873,6 +1884,7 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain,
 {
 	u64 pte_root = 0;
 	u64 flags = 0;
+	u32 old_domid;
 
 	if (domain->mode != PAGE_MODE_NONE)
 		pte_root = iommu_virt_to_phys(domain->pt_root);
@@ -1922,8 +1934,20 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain,
 	flags &= ~DEV_DOMID_MASK;
 	flags |= domain->id;
 
+	old_domid = amd_iommu_dev_table[devid].data[1] & DEV_DOMID_MASK;
 	amd_iommu_dev_table[devid].data[1]  = flags;
 	amd_iommu_dev_table[devid].data[0]  = pte_root;
+
+	/*
+	 * A kdump kernel might be replacing a domain ID that was copied from
+	 * the previous kernel--if so, it needs to flush the translation cache
+	 * entries for the old domain ID that is being overwritten
+	 */
+	if (old_domid) {
+		struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+
+		amd_iommu_flush_tlb_domid(iommu, old_domid);
+	}
 }
 
 static void clear_dte_entry(u16 devid)