[PATCH 4/6] remove remaining uses of iommu_legacy_map/unmap

[Paul Durrant <paul@xen.org>]

From: Paul Durrant <pdurrant@amazon.com>

The 'legacy' functions do implicit flushing so amend the callers to do the
appropriate flushing.

Unfortunately, because of the structure of the P2M code, we cannot remove
the per-CPU 'iommu_dont_flush_iotlb' global and the optimization it
facilitates. It is now checked directly iommu_iotlb_flush(). Also, it is
now declared as bool (rather than bool_t) and setting/clearing it are no
longer pointlessly gated on is_iommu_enabled() returning true. (Arguably
it is also pointless to gate the call to iommu_iotlb_flush() on that
condition - since it is a no-op in that case - but the if clause allows
the scope of a stack variable to be restricted).

Signed-off-by: Paul Durrant <pdurrant@amazon.com>
---
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Wei Liu <wl@xen.org>
Cc: "Roger Pau Monné" <roger.pau@citrix.com>
Cc: George Dunlap <george.dunlap@citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Julien Grall <julien@xen.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Jun Nakajima <jun.nakajima@intel.com>
Cc: Kevin Tian <kevin.tian@intel.com>
---
 xen/arch/x86/mm.c               | 22 +++++++++++++++-----
 xen/arch/x86/mm/p2m-ept.c       | 22 +++++++++++++-------
 xen/arch/x86/mm/p2m-pt.c        | 17 +++++++++++----
 xen/arch/x86/mm/p2m.c           | 28 ++++++++++++++++++-------
 xen/arch/x86/x86_64/mm.c        | 27 ++++++++++++++++++------
 xen/common/grant_table.c        | 36 +++++++++++++++++++++++++-------
 xen/common/memory.c             |  7 +++----
 xen/drivers/passthrough/iommu.c | 37 +--------------------------------
 xen/include/xen/iommu.h         | 20 +++++-------------
 9 files changed, 123 insertions(+), 93 deletions(-)

diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 82bc676553..8a5658b97a 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -2446,10 +2446,16 @@ static int cleanup_page_mappings(struct page_info *page)
 
         if ( d && unlikely(need_iommu_pt_sync(d)) && is_pv_domain(d) )
         {
-            int rc2 = iommu_legacy_unmap(d, _dfn(mfn), PAGE_ORDER_4K);
+            unsigned int flush_flags = 0;
+            int err;
 
+            err = iommu_unmap(d, _dfn(mfn), PAGE_ORDER_4K, &flush_flags);
             if ( !rc )
-                rc = rc2;
+                rc = err;
+
+            err = iommu_iotlb_flush(d, _dfn(mfn), 1, flush_flags);
+            if ( !rc )
+                rc = err;
         }
 
         if ( likely(!is_special_page(page)) )
@@ -2971,13 +2977,19 @@ static int _get_page_type(struct page_info *page, unsigned long type,
         if ( d && unlikely(need_iommu_pt_sync(d)) && is_pv_domain(d) )
         {
             mfn_t mfn = page_to_mfn(page);
+            dfn_t dfn = _dfn(mfn_x(mfn));
+            unsigned int flush_flags = 0;
+            int err;
 
             if ( (x & PGT_type_mask) == PGT_writable_page )
-                rc = iommu_legacy_unmap(d, _dfn(mfn_x(mfn)), PAGE_ORDER_4K);
+                rc = iommu_unmap(d, dfn, PAGE_ORDER_4K, &flush_flags);
             else
-                rc = iommu_legacy_map(d, _dfn(mfn_x(mfn)), mfn, PAGE_ORDER_4K,
-                                      IOMMUF_readable | IOMMUF_writable);
+                rc = iommu_map(d, dfn, mfn, PAGE_ORDER_4K,
+                               IOMMUF_readable | IOMMUF_writable, &flush_flags);
 
+            err = iommu_iotlb_flush(d, dfn, 1, flush_flags);
+            if ( !rc )
+                rc = err;
             if ( unlikely(rc) )
             {
                 _put_page_type(page, 0, NULL);
diff --git a/xen/arch/x86/mm/p2m-ept.c b/xen/arch/x86/mm/p2m-ept.c
index b8154a7ecc..d71c949b35 100644
--- a/xen/arch/x86/mm/p2m-ept.c
+++ b/xen/arch/x86/mm/p2m-ept.c
@@ -842,15 +842,21 @@ out:
     if ( rc == 0 && p2m_is_hostp2m(p2m) &&
          need_modify_vtd_table )
     {
-        if ( iommu_use_hap_pt(d) )
-            rc = iommu_iotlb_flush(d, _dfn(gfn), (1u << order),
-                                   (iommu_flags ? IOMMU_FLUSHF_added : 0) |
-                                   (vtd_pte_present ? IOMMU_FLUSHF_modified
-                                                    : 0));
-        else if ( need_iommu_pt_sync(d) )
+        unsigned int flush_flags = 0;
+        int err;
+
+        if ( need_iommu_pt_sync(d) )
             rc = iommu_flags ?
-                iommu_legacy_map(d, _dfn(gfn), mfn, order, iommu_flags) :
-                iommu_legacy_unmap(d, _dfn(gfn), order);
+                iommu_map(d, _dfn(gfn), mfn, order, iommu_flags, &flush_flags) :
+                iommu_unmap(d, _dfn(gfn), order, &flush_flags);
+        else if ( iommu_use_hap_pt(d) )
+            flush_flags =
+                (iommu_flags ? IOMMU_FLUSHF_added : 0) |
+                (vtd_pte_present ? IOMMU_FLUSHF_modified : 0);
+
+        err = iommu_iotlb_flush(d, _dfn(gfn), 1u << order, flush_flags);
+        if ( !rc )
+            rc = err;
     }
 
     unmap_domain_page(table);
diff --git a/xen/arch/x86/mm/p2m-pt.c b/xen/arch/x86/mm/p2m-pt.c
index badb26bc34..c48245cfe4 100644
--- a/xen/arch/x86/mm/p2m-pt.c
+++ b/xen/arch/x86/mm/p2m-pt.c
@@ -678,10 +678,19 @@ p2m_pt_set_entry(struct p2m_domain *p2m, gfn_t gfn_, mfn_t mfn,
 
     if ( need_iommu_pt_sync(p2m->domain) &&
          (iommu_old_flags != iommu_pte_flags || old_mfn != mfn_x(mfn)) )
-        rc = iommu_pte_flags
-             ? iommu_legacy_map(d, _dfn(gfn), mfn, page_order,
-                                iommu_pte_flags)
-             : iommu_legacy_unmap(d, _dfn(gfn), page_order);
+    {
+        unsigned int flush_flags = 0;
+        int err;
+
+        rc = iommu_pte_flags ?
+            iommu_map(d, _dfn(gfn), mfn, page_order, iommu_pte_flags,
+                      &flush_flags) :
+            iommu_unmap(d, _dfn(gfn), page_order, &flush_flags);
+
+        err = iommu_iotlb_flush(d, _dfn(gfn), 1u << page_order, flush_flags);
+        if ( !rc )
+            rc = err;
+    }
 
     /*
      * Free old intermediate tables if necessary.  This has to be the
diff --git a/xen/arch/x86/mm/p2m.c b/xen/arch/x86/mm/p2m.c
index db7bde0230..c5f52a4118 100644
--- a/xen/arch/x86/mm/p2m.c
+++ b/xen/arch/x86/mm/p2m.c
@@ -1350,10 +1350,17 @@ int set_identity_p2m_entry(struct domain *d, unsigned long gfn_l,
 
     if ( !paging_mode_translate(p2m->domain) )
     {
-        if ( !is_iommu_enabled(d) )
-            return 0;
-        return iommu_legacy_map(d, _dfn(gfn_l), _mfn(gfn_l), PAGE_ORDER_4K,
-                                IOMMUF_readable | IOMMUF_writable);
+        unsigned int flush_flags = 0;
+        int err;
+
+        ret = iommu_map(d, _dfn(gfn_l), _mfn(gfn_l), PAGE_ORDER_4K,
+                        IOMMUF_readable | IOMMUF_writable, &flush_flags);
+
+        err = iommu_iotlb_flush(d, _dfn(gfn_l), 1, flush_flags);
+        if ( !ret )
+            ret = err;
+
+        return ret;
     }
 
     gfn_lock(p2m, gfn, 0);
@@ -1441,9 +1448,16 @@ int clear_identity_p2m_entry(struct domain *d, unsigned long gfn_l)
 
     if ( !paging_mode_translate(d) )
     {
-        if ( !is_iommu_enabled(d) )
-            return 0;
-        return iommu_legacy_unmap(d, _dfn(gfn_l), PAGE_ORDER_4K);
+        unsigned int flush_flags = 0;
+        int err;
+
+        ret = iommu_unmap(d, _dfn(gfn_l), PAGE_ORDER_4K, &flush_flags);
+
+        err = iommu_iotlb_flush(d, _dfn(gfn_l), 1, flush_flags);
+        if ( !ret )
+            ret = err;
+
+        return ret;
     }
 
     gfn_lock(p2m, gfn, 0);
diff --git a/xen/arch/x86/x86_64/mm.c b/xen/arch/x86/x86_64/mm.c
index 102079a801..3e0bff228e 100644
--- a/xen/arch/x86/x86_64/mm.c
+++ b/xen/arch/x86/x86_64/mm.c
@@ -1413,21 +1413,36 @@ int memory_add(unsigned long spfn, unsigned long epfn, unsigned int pxm)
          !iommu_use_hap_pt(hardware_domain) &&
          !need_iommu_pt_sync(hardware_domain) )
     {
+        unsigned int flush_flags = 0;
+        bool failed = false;
+        unsigned int n;
+
         for ( i = spfn; i < epfn; i++ )
-            if ( iommu_legacy_map(hardware_domain, _dfn(i), _mfn(i),
-                                  PAGE_ORDER_4K,
-                                  IOMMUF_readable | IOMMUF_writable) )
+            if ( iommu_map(hardware_domain, _dfn(i), _mfn(i),
+                           PAGE_ORDER_4K, IOMMUF_readable | IOMMUF_writable,
+                           &flush_flags) )
                 break;
         if ( i != epfn )
         {
+            failed = true;
+
             while (i-- > old_max)
                 /* If statement to satisfy __must_check. */
-                if ( iommu_legacy_unmap(hardware_domain, _dfn(i),
-                                        PAGE_ORDER_4K) )
+                if ( iommu_unmap(hardware_domain, _dfn(i), PAGE_ORDER_4K,
+                                 &flush_flags) )
                     continue;
+        }
 
-            goto destroy_m2p;
+        for ( i = spfn; i < epfn; i += n )
+        {
+            n = epfn - i; /* may truncate */
+
+            /* If statement to satisfy __must_check. */
+            if ( iommu_iotlb_flush(hardware_domain, _dfn(i), n, flush_flags) )
+                continue;
         }
+        if ( failed )
+            goto destroy_m2p;
     }
 
     /* We can't revert any more */
diff --git a/xen/common/grant_table.c b/xen/common/grant_table.c
index 9f0cae52c0..bc2b5000cf 100644
--- a/xen/common/grant_table.c
+++ b/xen/common/grant_table.c
@@ -1225,11 +1225,25 @@ map_grant_ref(
             kind = IOMMUF_readable;
         else
             kind = 0;
-        if ( kind && iommu_legacy_map(ld, _dfn(mfn_x(mfn)), mfn, 0, kind) )
+        if ( kind )
         {
-            double_gt_unlock(lgt, rgt);
-            rc = GNTST_general_error;
-            goto undo_out;
+            dfn_t dfn = _dfn(mfn_x(mfn));
+            unsigned int flush_flags = 0;
+            int err;
+
+            err = iommu_map(ld, dfn, mfn, 0, kind, &flush_flags);
+            if ( err )
+                rc = GNTST_general_error;
+
+            err = iommu_iotlb_flush(ld, dfn, 1, flush_flags);
+            if ( err )
+                rc = GNTST_general_error;
+
+            if ( rc != GNTST_okay )
+            {
+                double_gt_unlock(lgt, rgt);
+                goto undo_out;
+            }
         }
     }
 
@@ -1473,21 +1487,27 @@ unmap_common(
     if ( rc == GNTST_okay && gnttab_need_iommu_mapping(ld) )
     {
         unsigned int kind;
+        dfn_t dfn = _dfn(mfn_x(op->mfn));
+        unsigned int flush_flags = 0;
         int err = 0;
 
         double_gt_lock(lgt, rgt);
 
         kind = mapkind(lgt, rd, op->mfn);
         if ( !kind )
-            err = iommu_legacy_unmap(ld, _dfn(mfn_x(op->mfn)), 0);
+            err = iommu_unmap(ld, dfn, 0, &flush_flags);
         else if ( !(kind & MAPKIND_WRITE) )
-            err = iommu_legacy_map(ld, _dfn(mfn_x(op->mfn)), op->mfn, 0,
-                                   IOMMUF_readable);
+            err = iommu_map(ld, dfn, op->mfn, 0, IOMMUF_readable,
+                            &flush_flags);
 
-        double_gt_unlock(lgt, rgt);
+        if ( err )
+            rc = GNTST_general_error;
 
+        err = iommu_iotlb_flush(ld, dfn, 1, flush_flags);
         if ( err )
             rc = GNTST_general_error;
+
+        double_gt_unlock(lgt, rgt);
     }
 
     /* If just unmapped a writable mapping, mark as dirtied */
diff --git a/xen/common/memory.c b/xen/common/memory.c
index 714077c1e5..fedbd9019e 100644
--- a/xen/common/memory.c
+++ b/xen/common/memory.c
@@ -824,8 +824,7 @@ int xenmem_add_to_physmap(struct domain *d, struct xen_add_to_physmap *xatp,
     xatp->gpfn += start;
     xatp->size -= start;
 
-    if ( is_iommu_enabled(d) )
-       this_cpu(iommu_dont_flush_iotlb) = 1;
+    this_cpu(iommu_dont_flush_iotlb) = true;
 
     while ( xatp->size > done )
     {
@@ -845,12 +844,12 @@ int xenmem_add_to_physmap(struct domain *d, struct xen_add_to_physmap *xatp,
         }
     }
 
+    this_cpu(iommu_dont_flush_iotlb) = false;
+
     if ( is_iommu_enabled(d) )
     {
         int ret;
 
-        this_cpu(iommu_dont_flush_iotlb) = 0;
-
         ret = iommu_iotlb_flush(d, _dfn(xatp->idx - done), done,
                                 IOMMU_FLUSHF_added | IOMMU_FLUSHF_modified);
         if ( unlikely(ret) && rc >= 0 )
diff --git a/xen/drivers/passthrough/iommu.c b/xen/drivers/passthrough/iommu.c
index 327df17c5d..f32d8e25a8 100644
--- a/xen/drivers/passthrough/iommu.c
+++ b/xen/drivers/passthrough/iommu.c
@@ -277,24 +277,6 @@ int iommu_map(struct domain *d, dfn_t dfn, mfn_t mfn,
     return rc;
 }
 
-int iommu_legacy_map(struct domain *d, dfn_t dfn, mfn_t mfn,
-                     unsigned int page_order, unsigned int flags)
-{
-    unsigned int flush_flags = 0;
-    int rc = iommu_map(d, dfn, mfn, page_order, flags, &flush_flags);
-
-    if ( !this_cpu(iommu_dont_flush_iotlb) )
-    {
-        int err = iommu_iotlb_flush(d, dfn, (1u << page_order),
-                                    flush_flags);
-
-        if ( !rc )
-            rc = err;
-    }
-
-    return rc;
-}
-
 int iommu_unmap(struct domain *d, dfn_t dfn, unsigned int page_order,
                 unsigned int *flush_flags)
 {
@@ -333,23 +315,6 @@ int iommu_unmap(struct domain *d, dfn_t dfn, unsigned int page_order,
     return rc;
 }
 
-int iommu_legacy_unmap(struct domain *d, dfn_t dfn, unsigned int page_order)
-{
-    unsigned int flush_flags = 0;
-    int rc = iommu_unmap(d, dfn, page_order, &flush_flags);
-
-    if ( !this_cpu(iommu_dont_flush_iotlb) )
-    {
-        int err = iommu_iotlb_flush(d, dfn, (1u << page_order),
-                                    flush_flags);
-
-        if ( !rc )
-            rc = err;
-    }
-
-    return rc;
-}
-
 int iommu_iotlb_flush(struct domain *d, dfn_t dfn, unsigned int page_count,
                       unsigned int flush_flags)
 {
@@ -357,7 +322,7 @@ int iommu_iotlb_flush(struct domain *d, dfn_t dfn, unsigned int page_count,
     int rc;
 
     if ( !is_iommu_enabled(d) || !hd->platform_ops->iotlb_flush ||
-         !page_count || !flush_flags )
+         !page_count || !flush_flags || this_cpu(iommu_dont_flush_iotlb) )
         return 0;
 
     if ( dfn_eq(dfn, INVALID_DFN) )
diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
index 271bd8e546..ec639ba128 100644
--- a/xen/include/xen/iommu.h
+++ b/xen/include/xen/iommu.h
@@ -151,13 +151,6 @@ int __must_check iommu_map(struct domain *d, dfn_t dfn, mfn_t mfn,
 int __must_check iommu_unmap(struct domain *d, dfn_t dfn,
                              unsigned int page_order,
                              unsigned int *flush_flags);
-
-int __must_check iommu_legacy_map(struct domain *d, dfn_t dfn, mfn_t mfn,
-                                  unsigned int page_order,
-                                  unsigned int flags);
-int __must_check iommu_legacy_unmap(struct domain *d, dfn_t dfn,
-                                    unsigned int page_order);
-
 int __must_check iommu_iotlb_flush(struct domain *d, dfn_t dfn,
                                    unsigned int page_count,
                                    unsigned int flush_flags);
@@ -364,15 +357,12 @@ void iommu_dev_iotlb_flush_timeout(struct domain *d, struct pci_dev *pdev);
 
 /*
  * The purpose of the iommu_dont_flush_iotlb optional cpu flag is to
- * avoid unecessary iotlb_flush in the low level IOMMU code.
- *
- * iommu_map_page/iommu_unmap_page must flush the iotlb but somethimes
- * this operation can be really expensive. This flag will be set by the
- * caller to notify the low level IOMMU code to avoid the iotlb flushes.
- * iommu_iotlb_flush/iommu_iotlb_flush_all will be explicitly called by
- * the caller.
+ * avoid unecessary IOMMU flushing while updating the P2M.
+ * Setting the value to true will cause iommu_iotlb_flush() to return without
+ * actually performing a flush. A batch flush must therefore be done by the
+ * calling code after setting the value back to false.
  */
-DECLARE_PER_CPU(bool_t, iommu_dont_flush_iotlb);
+DECLARE_PER_CPU(bool, iommu_dont_flush_iotlb);
 
 #endif /* _IOMMU_H_ */
 
-- 
2.20.1