Merge tag 'iommu-fixes-v4.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull IOMMU fixes from Joerg Roedel:
"Three fixes queued up:
- fix an issue with command buffer overflow handling in the AMD IOMMU
driver
- add an additional context entry flush to the Intel VT-d driver to
make sure any old context entry from kdump copying is flushed out
of the cache
- correct the encoding of the PASID table size in the Intel VT-d
driver"
* tag 'iommu-fixes-v4.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
iommu/amd: Fix the left value check of cmd buffer
iommu/vt-d: Fix pasid table size encoding
iommu/vt-d: Flush old iommu caches for kdump when the device gets context mapped
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 019e027..3ef0f42 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1023,7 +1023,7 @@ static int __iommu_queue_command_sync(struct amd_iommu *iommu,
next_tail = (tail + sizeof(*cmd)) % CMD_BUFFER_SIZE;
left = (head - next_tail) % CMD_BUFFER_SIZE;
- if (left <= 2) {
+ if (left <= 0x20) {
struct iommu_cmd sync_cmd;
int ret;
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index c66c273..8a18525 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2037,6 +2037,25 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
if (context_present(context))
goto out_unlock;
+ /*
+ * For kdump cases, old valid entries may be cached due to the
+ * in-flight DMA and copied pgtable, but there is no unmapping
+ * behaviour for them, thus we need an explicit cache flush for
+ * the newly-mapped device. For kdump, at this point, the device
+ * is supposed to finish reset at its driver probe stage, so no
+ * in-flight DMA will exist, and we don't need to worry anymore
+ * hereafter.
+ */
+ if (context_copied(context)) {
+ u16 did_old = context_domain_id(context);
+
+ if (did_old >= 0 && did_old < cap_ndoms(iommu->cap))
+ iommu->flush.flush_context(iommu, did_old,
+ (((u16)bus) << 8) | devfn,
+ DMA_CCMD_MASK_NOBIT,
+ DMA_CCMD_DEVICE_INVL);
+ }
+
pgd = domain->pgd;
context_clear_entry(context);
@@ -5185,6 +5204,25 @@ static void intel_iommu_remove_device(struct device *dev)
}
#ifdef CONFIG_INTEL_IOMMU_SVM
+#define MAX_NR_PASID_BITS (20)
+static inline unsigned long intel_iommu_get_pts(struct intel_iommu *iommu)
+{
+ /*
+ * Convert ecap_pss to extend context entry pts encoding, also
+ * respect the soft pasid_max value set by the iommu.
+ * - number of PASID bits = ecap_pss + 1
+ * - number of PASID table entries = 2^(pts + 5)
+ * Therefore, pts = ecap_pss - 4
+ * e.g. KBL ecap_pss = 0x13, PASID has 20 bits, pts = 15
+ */
+ if (ecap_pss(iommu->ecap) < 5)
+ return 0;
+
+ /* pasid_max is encoded as actual number of entries not the bits */
+ return find_first_bit((unsigned long *)&iommu->pasid_max,
+ MAX_NR_PASID_BITS) - 5;
+}
+
int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev)
{
struct device_domain_info *info;
@@ -5217,7 +5255,9 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd
if (!(ctx_lo & CONTEXT_PASIDE)) {
context[1].hi = (u64)virt_to_phys(iommu->pasid_state_table);
- context[1].lo = (u64)virt_to_phys(iommu->pasid_table) | ecap_pss(iommu->ecap);
+ context[1].lo = (u64)virt_to_phys(iommu->pasid_table) |
+ intel_iommu_get_pts(iommu);
+
wmb();
/* CONTEXT_TT_MULTI_LEVEL and CONTEXT_TT_DEV_IOTLB are both
* extended to permit requests-with-PASID if the PASIDE bit