[PATCH v6 14/14] x86: extend the map and unmap iommu_ops to support grant references

[Paul Durrant <paul.durrant@citrix.com>]

This patch allows a domain to add or remove foreign frames from its
IOMMU mappings by grant reference as well as GFN. This is necessary,
for example, to support a PV network backend that needs to construct a
packet buffer that can be directly accessed by a NIC.

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
---
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: George Dunlap <George.Dunlap@eu.citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Julien Grall <julien.grall@arm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tim Deegan <tim@xen.org>
Cc: Wei Liu <wei.liu2@citrix.com>

v6:
 - Re-base.

v2:
 - New in v2.
---
 xen/common/grant_table.c      | 143 ++++++++++++++++++++++++++++++++++++++++++
 xen/common/iommu_op.c         |  83 ++++++++++++++++--------
 xen/include/public/iommu_op.h |  29 +++++++--
 xen/include/xen/grant_table.h |   7 +++
 4 files changed, 232 insertions(+), 30 deletions(-)

diff --git a/xen/common/grant_table.c b/xen/common/grant_table.c
index f3b2fad7a8..01a95c05ed 100644
--- a/xen/common/grant_table.c
+++ b/xen/common/grant_table.c
@@ -3961,6 +3961,149 @@ int gnttab_get_status_frame(struct domain *d, unsigned long idx,
     return rc;
 }
 
+int
+acquire_gref_for_iommu(struct domain *d, grant_ref_t gref,
+                       bool readonly, mfn_t *mfn)
+{
+    struct domain *currd = current->domain;
+    struct grant_table *gt = d->grant_table;
+    grant_entry_header_t *shah;
+    struct active_grant_entry *act;
+    uint16_t *status;
+    int rc;
+
+    grant_read_lock(gt);
+
+    rc = -ENOENT;
+    if ( gref > nr_grant_entries(gt) )
+        goto unlock;
+
+    act = active_entry_acquire(gt, gref);
+    shah = shared_entry_header(gt, gref);
+    status = ( gt->gt_version == 2 ) ?
+        &status_entry(gt, gref) :
+        &shah->flags;
+
+    rc = -EACCES;
+    if ( (shah->flags & GTF_type_mask) != GTF_permit_access ||
+         (shah->flags & GTF_sub_page) )
+        goto release;
+
+    rc = -ERANGE;
+    if ( act->pin && ((act->domid != currd->domain_id) ||
+                      (act->pin & 0x80808080U) != 0) )
+        goto release;
+
+    rc = -EINVAL;
+    if ( !act->pin ||
+         (!readonly && !(act->pin & GNTPIN_devw_mask)) ) {
+        if ( _set_status(gt->gt_version, currd->domain_id, readonly,
+                         0, shah, act, status) != GNTST_okay )
+            goto release;
+    }
+
+    if ( !act->pin )
+    {
+        gfn_t gfn = gt->gt_version == 1 ?
+            _gfn(shared_entry_v1(gt, gref).frame) :
+            _gfn(shared_entry_v2(gt, gref).full_page.frame);
+        struct page_info *page;
+
+        rc =  get_paged_gfn(d, gfn, readonly, NULL, &page);
+        if ( rc )
+            goto clear;
+
+        act_set_gfn(act, gfn);
+        act->mfn = page_to_mfn(page);
+        act->domid = currd->domain_id;
+        act->start = 0;
+        act->length = PAGE_SIZE;
+        act->is_sub_page = false;
+        act->trans_domain = d;
+        act->trans_gref = gref;
+    }
+    else
+    {
+        ASSERT(mfn_valid(act->mfn));
+        if ( !get_page(mfn_to_page(act->mfn), d) )
+            goto clear;
+    }
+
+    rc = 0;
+    act->pin += readonly ? GNTPIN_devr_inc : GNTPIN_devw_inc;
+    *mfn = act->mfn;
+    goto release;
+
+ clear:
+    if ( !readonly && !(act->pin & GNTPIN_devw_mask) )
+        gnttab_clear_flag(_GTF_writing, status);
+
+    if ( !act->pin )
+        gnttab_clear_flag(_GTF_reading, status);
+
+ release:
+    active_entry_release(act);
+
+ unlock:
+    grant_read_unlock(gt);
+
+    return rc;
+}
+
+int
+release_gref_for_iommu(struct domain *d, grant_ref_t gref,
+                       bool readonly, mfn_t mfn)
+{
+    struct domain *currd = current->domain;
+    struct grant_table *gt = d->grant_table;
+    grant_entry_header_t *shah;
+    struct active_grant_entry *act;
+    uint16_t *status;
+    int rc;
+
+    grant_read_lock(gt);
+
+    rc = -ENOENT;
+    if ( gref > nr_grant_entries(gt) )
+        goto unlock;
+
+    act = active_entry_acquire(gt, gref);
+    shah = shared_entry_header(gt, gref);
+    status = ( gt->gt_version == 2 ) ?
+        &status_entry(gt, gref) :
+        &shah->flags;
+
+    rc = -EINVAL;
+    if ( !act->pin || (act->domid != currd->domain_id) ||
+         !mfn_eq(act->mfn, mfn) )
+        goto release;
+
+    rc = 0;
+    if ( readonly )
+        act->pin -= GNTPIN_devr_inc;
+    else
+    {
+        gnttab_mark_dirty(d, mfn);
+
+        act->pin -= GNTPIN_devw_inc;
+        if ( !(act->pin & GNTPIN_devw_mask) )
+            gnttab_clear_flag(_GTF_writing, status);
+    }
+
+    if ( !act->pin )
+        gnttab_clear_flag(_GTF_reading, status);
+
+    put_page(mfn_to_page(mfn));
+
+ release:
+    active_entry_release(act);
+
+ unlock:
+    grant_read_unlock(gt);
+
+    return rc;
+}
+
 static void gnttab_usage_print(struct domain *rd)
 {
     int first = 1;
diff --git a/xen/common/iommu_op.c b/xen/common/iommu_op.c
index 328522f245..272f53298f 100644
--- a/xen/common/iommu_op.c
+++ b/xen/common/iommu_op.c
@@ -23,6 +23,7 @@
 #include <xen/guest_access.h>
 #include <xen/hypercall.h>
 #include <xen/nospec.h>
+#include <xen/grant_table.h>
 
 struct get_reserved_ctxt {
     unsigned int max_entries;
@@ -130,12 +131,14 @@ static int iommuop_map(struct xen_iommu_op_map *op)
     bool readonly = op->flags & XEN_IOMMUOP_map_readonly;
     bfn_t bfn = _bfn(op->bfn);
     struct page_info *page;
+    mfn_t mfn;
     unsigned int prot;
     int rc, ignore;
 
     if ( op->pad ||
          (op->flags & ~(XEN_IOMMUOP_map_all |
-                        XEN_IOMMUOP_map_readonly)) )
+                        XEN_IOMMUOP_map_readonly |
+                        XEN_IOMMUOP_map_gref)) )
         return -EINVAL;
 
     if ( !iommu->iommu_op_ranges )
@@ -153,15 +156,28 @@ static int iommuop_map(struct xen_iommu_op_map *op)
     if ( !d )
         return -ESRCH;
 
-    rc = get_paged_gfn(d, _gfn(op->gfn), readonly, NULL, &page);
-    if ( rc )
-        goto unlock;
+    if ( op->flags & XEN_IOMMUOP_map_gref )
+    {
+        rc = acquire_gref_for_iommu(d, op->u.gref, readonly, &mfn);
+        if ( rc )
+            goto unlock;
 
-    rc = -EINVAL;
-    if ( !readonly && !get_page_type(page, PGT_writable_page) )
+        page = mfn_to_page(mfn);
+    }
+    else
     {
-        put_page(page);
-        goto unlock;
+        rc = get_paged_gfn(d, _gfn(op->u.gfn), readonly, NULL, &page);
+        if ( rc )
+            goto unlock;
+
+        rc = -EINVAL;
+        if ( !readonly && !get_page_type(page, PGT_writable_page) )
+        {
+            put_page(page);
+            goto unlock;
+        }
+
+        mfn = page_to_mfn(page);
     }
 
     prot = IOMMUF_readable;
@@ -169,7 +185,7 @@ static int iommuop_map(struct xen_iommu_op_map *op)
         prot |= IOMMUF_writable;
 
     rc = -EIO;
-    if ( iommu_map_page(currd, bfn, page_to_mfn(page), prot) )
+    if ( iommu_map_page(currd, bfn, mfn, prot) )
         goto release;
 
     rc = rangeset_add_singleton(iommu->iommu_op_ranges, bfn_x(bfn));
@@ -183,9 +199,14 @@ static int iommuop_map(struct xen_iommu_op_map *op)
     ignore = iommu_unmap_page(currd, bfn);
 
  release:
-    if ( !readonly )
-        put_page_type(page);
-    put_page(page);
+    if ( op->flags & XEN_IOMMUOP_map_gref )
+        release_gref_for_iommu(d, op->u.gref, readonly, mfn);
+    else
+    {
+        if ( !readonly )
+            put_page_type(page);
+        put_page(page);
+    }
 
  unlock:
     rcu_unlock_domain(d);
@@ -200,11 +221,11 @@ static int iommuop_unmap(struct xen_iommu_op_unmap *op)
     mfn_t mfn;
     bool readonly;
     unsigned int prot;
-    struct page_info *page;
     int rc;
 
     if ( op->pad ||
-         (op->flags & ~XEN_IOMMUOP_unmap_all) )
+         (op->flags & ~(XEN_IOMMUOP_unmap_all |
+                        XEN_IOMMUOP_unmap_gref)) )
         return -EINVAL;
 
     if ( !iommu->iommu_op_ranges )
@@ -225,21 +246,31 @@ static int iommuop_unmap(struct xen_iommu_op_unmap *op)
     if ( !d )
         return -ESRCH;
 
-    rc = get_paged_gfn(d, _gfn(op->gfn), !(prot & IOMMUF_writable), NULL,
-                       &page);
-    if ( rc )
-        goto unlock;
+    if ( op->flags & XEN_IOMMUOP_unmap_gref )
+    {
+        rc = release_gref_for_iommu(d, op->u.gref, readonly, mfn);
+        if ( rc )
+            goto unlock;
+    }
+    else
+    {
+        struct page_info *page;
 
-    put_page(page); /* release extra reference just taken */
+        rc = get_paged_gfn(d, _gfn(op->u.gfn), readonly, NULL, &page);
+        if ( rc )
+            goto unlock;
 
-    rc = -EINVAL;
-    if ( !mfn_eq(page_to_mfn(page), mfn) )
-        goto unlock;
+        put_page(page); /* release extra reference just taken */
 
-    /* release reference taken in map */
-    if ( !readonly )
-        put_page_type(page);
-    put_page(page);
+        rc = -EINVAL;
+        if ( !mfn_eq(page_to_mfn(page), mfn) )
+            goto unlock;
+
+        /* release reference taken in map */
+        if ( !readonly )
+            put_page_type(page);
+        put_page(page);
+    }
 
     rc = rangeset_remove_singleton(iommu->iommu_op_ranges, bfn_x(bfn));
     if ( rc )
diff --git a/xen/include/public/iommu_op.h b/xen/include/public/iommu_op.h
index e6c08f4bdd..e3d702a8d0 100644
--- a/xen/include/public/iommu_op.h
+++ b/xen/include/public/iommu_op.h
@@ -24,6 +24,7 @@
 #define XEN_PUBLIC_IOMMU_OP_H
 
 #include "xen.h"
+#include "grant_table.h"
 
 typedef uint64_t xen_bfn_t;
 
@@ -107,6 +108,10 @@ struct xen_iommu_op_map {
 #define _XEN_IOMMUOP_map_readonly 1
 #define XEN_IOMMUOP_map_readonly (1 << (_XEN_IOMMUOP_map_readonly))
 
+    /* Is the memory specified by gfn or grant reference? */
+#define _XEN_IOMMUOP_map_gref 2
+#define XEN_IOMMUOP_map_gref (1 << (_XEN_IOMMUOP_map_gref))
+
     uint32_t pad;
     /*
      * IN - Segment/Bus/Device/Function of the initiator.
@@ -116,8 +121,14 @@ struct xen_iommu_op_map {
     uint64_t sbdf;
     /* IN - The IOMMU frame number which will hold the new mapping */
     xen_bfn_t bfn;
-    /* IN - The guest frame number of the page to be mapped */
-    xen_pfn_t gfn;
+    /*
+     * IN - The guest frame number or grant reference of the page to
+     * be mapped.
+     */
+    union {
+        xen_pfn_t gfn;
+        grant_ref_t gref;
+    } u;
 };
 
 /*
@@ -143,6 +154,10 @@ struct xen_iommu_op_unmap {
 #define _XEN_IOMMUOP_unmap_all 0
 #define XEN_IOMMUOP_unmap_all (1 << (_XEN_IOMMUOP_unmap_all))
 
+    /* Is the memory specified by gfn or grant reference? */
+#define _XEN_IOMMUOP_unmap_gref 1
+#define XEN_IOMMUOP_unmap_gref (1 << (_XEN_IOMMUOP_unmap_gref))
+
     uint32_t pad;
     /*
      * IN - Segment/Bus/Device/Function of the initiator.
@@ -152,8 +167,14 @@ struct xen_iommu_op_unmap {
     uint64_t sbdf;
     /* IN - The IOMMU frame number which holds the mapping to be removed */
     xen_bfn_t bfn;
-    /* IN - The guest frame number of the page that is mapped */
-    xen_pfn_t gfn;
+    /*
+     * IN - The guest frame number or grant reference of the page that
+     * is mapped.
+     */
+    union {
+        xen_pfn_t gfn;
+        grant_ref_t gref;
+    } u;
 };
 
 /*
diff --git a/xen/include/xen/grant_table.h b/xen/include/xen/grant_table.h
index c881414e5b..35afb27202 100644
--- a/xen/include/xen/grant_table.h
+++ b/xen/include/xen/grant_table.h
@@ -63,6 +63,13 @@ int gnttab_get_shared_frame(struct domain *d, unsigned long idx,
 int gnttab_get_status_frame(struct domain *d, unsigned long idx,
                             mfn_t *mfn);
 
+int
+acquire_gref_for_iommu(struct domain *d, grant_ref_t gref,
+                       bool readonly, mfn_t *mfn);
+int
+release_gref_for_iommu(struct domain *d, grant_ref_t gref,
+                       bool readonly, mfn_t mfn);
+
 unsigned int gnttab_dom0_frames(void);
 
 #endif /* __XEN_GRANT_TABLE_H__ */
-- 
2.11.0


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel