Merge git://git.infradead.org/intel-iommu

Pull VT-d hardware workarounds from David Woodhouse:
 "This contains a workaround for hardware issues which I *thought* were
  never going to be seen on production hardware.  I'm glad I checked
  that before the 4.1 release...

  Firstly, PASID support is so broken on existing chips that we're just
  going to declare the old capability bit 28 as 'reserved' and change
  the VT-d spec to move PASID support to another bit.  So any existing
  hardware doesn't support SVM; it only sets that (now) meaningless bit
  28.

  That patch *wasn't* imperative for 4.1 because we don't have PASID
  support yet.  But *even* the extended context tables are broken — if
  you just enable the wider tables and use none of the new bits in them,
  which is precisely what 4.1 does, you find that translations don't
  work.  It's this problem which I thought was caught in time to be
  fixed before production, but wasn't.

  To avoid triggering this issue, we now *only* enable the extended
  context tables on hardware which also advertises "we have PASID
  support and we actually tested it this time" with the new PASID
  feature bit.

  In addition, I've added an 'intel_iommu=ecs_off' command line
  parameter to allow us to disable it manually if we need to"

* git://git.infradead.org/intel-iommu:
  iommu/vt-d: Only enable extended context tables if PASID is supported
  iommu/vt-d: Change PASID support to bit 40 of Extended Capability Register

3 files changed, 23 insertions, 4 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 61ab1628a057..6726139bd289 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1481,6 +1481,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
                         By default, super page will be supported if Intel IOMMU
                         has the capability. With this option, super page will
                         not be supported.
+                ecs_off [Default Off]
+                        By default, extended context tables will be supported if
+                        the hardware advertises that it has support both for the
+                        extended tables themselves, and also PASID support. With
+                        this option set, extended tables will not be used even
+                        on hardware which claims to support them.
 
         intel_idle.max_cstate=  [KNL,HW,ACPI,X86]
                         0       disables intel_idle and fall back on acpi_idle.
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 2ffe58969944..5ecfaf29933a 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -422,6 +422,14 @@ static int dmar_map_gfx = 1;
 static int dmar_forcedac;
 static int intel_iommu_strict;
 static int intel_iommu_superpage = 1;
+static int intel_iommu_ecs = 1;
+
+/* We only actually use ECS when PASID support (on the new bit 40)
+ * is also advertised. Some early implementations — the ones with
+ * PASID support on bit 28 — have issues even when we *only* use
+ * extended root/context tables. */
+#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap) && \
+                            ecap_pasid(iommu->ecap))
 
 int intel_iommu_gfx_mapped;
 EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
@@ -465,6 +473,10 @@ static int __init intel_iommu_setup(char *str)
                         printk(KERN_INFO
                                 "Intel-IOMMU: disable supported super page\n");
                         intel_iommu_superpage = 0;
+                } else if (!strncmp(str, "ecs_off", 7)) {
+                        printk(KERN_INFO
+                                "Intel-IOMMU: disable extended context table support\n");
+                        intel_iommu_ecs = 0;
                 }
 
                 str += strcspn(str, ",");
@@ -669,7 +681,7 @@ static inline struct context_entry *iommu_context_addr(struct intel_iommu *iommu
         struct context_entry *context;
         u64 *entry;
 
-        if (ecap_ecs(iommu->ecap)) {
+        if (ecs_enabled(iommu)) {
                 if (devfn >= 0x80) {
                         devfn -= 0x80;
                         entry = &root->hi;
@@ -806,7 +818,7 @@ static void free_context_table(struct intel_iommu *iommu)
                 if (context)
                         free_pgtable_page(context);
 
-                if (!ecap_ecs(iommu->ecap))
+                if (!ecs_enabled(iommu))
                         continue;
 
                 context = iommu_context_addr(iommu, i, 0x80, 0);
@@ -1141,7 +1153,7 @@ static void iommu_set_root_entry(struct intel_iommu *iommu)
         unsigned long flag;
 
         addr = virt_to_phys(iommu->root_entry);
-        if (ecap_ecs(iommu->ecap))
+        if (ecs_enabled(iommu))
                 addr |= DMA_RTADDR_RTT;
 
         raw_spin_lock_irqsave(&iommu->register_lock, flag);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 796ef9645827..a240e61a7700 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -115,13 +115,14 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
  * Extended Capability Register
  */
 
+#define ecap_pasid(e)           ((e >> 40) & 0x1)
 #define ecap_pss(e)             ((e >> 35) & 0x1f)
 #define ecap_eafs(e)            ((e >> 34) & 0x1)
 #define ecap_nwfs(e)            ((e >> 33) & 0x1)
 #define ecap_srs(e)             ((e >> 31) & 0x1)
 #define ecap_ers(e)             ((e >> 30) & 0x1)
 #define ecap_prs(e)             ((e >> 29) & 0x1)
-#define ecap_pasid(e)           ((e >> 28) & 0x1)
+/* PASID support used to be on bit 28 */
 #define ecap_dis(e)             ((e >> 27) & 0x1)
 #define ecap_nest(e)            ((e >> 26) & 0x1)
 #define ecap_mts(e)             ((e >> 25) & 0x1)