[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] [PATCH v13 06/11] x86/hvm/ioreq: add a new mappable resource type...



... XENMEM_resource_ioreq_server

This patch adds support for a new resource type that can be mapped using
the XENMEM_acquire_resource memory op.

If an emulator makes use of this resource type then, instead of mapping
gfns, the IOREQ server will allocate pages from the heap. These pages
will never be present in the P2M of the guest at any point and so are
not vulnerable to any direct attack by the guest. They are only ever
accessible by Xen and any domain that has mapping privilege over the
guest (which may or may not be limited to the domain running the emulator).

NOTE: Use of the new resource type is not compatible with use of
      XEN_DMOP_get_ioreq_server_info unless the XEN_DMOP_no_gfns flag is
      set.

Signed-off-by: Paul Durrant <paul.durrant@xxxxxxxxxx>
---
Cc: George Dunlap <George.Dunlap@xxxxxxxxxxxxx>
Cc: Wei Liu <wei.liu2@xxxxxxxxxx>
Cc: Jan Beulich <jbeulich@xxxxxxxx>
Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
Cc: Ian Jackson <ian.jackson@xxxxxxxxxxxxx>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
Cc: Stefano Stabellini <sstabellini@xxxxxxxxxx>
Cc: Tim Deegan <tim@xxxxxxx>
Cc: Julien Grall <julien.grall@xxxxxxx>

v13:
 - Introduce an arch_acquire_resource() as suggested by Julien (and have
   the ARM varient simply return -EOPNOTSUPP).
 - Check for ioreq server id truncation as requested by Jan.
 - Not added Jan's R-b due to substantive change from v12.

v12:
 - Addressed more comments from Jan.
 - Dropped George's A-b and Wei's R-b because of material change.

v11:
 - Addressed more comments from Jan.

v10:
 - Addressed comments from Jan.

v8:
 - Re-base on new boilerplate.
 - Adjust function signature of hvm_get_ioreq_server_frame(), and test
   whether the bufioreq page is present.

v5:
 - Use get_ioreq_server() function rather than indexing array directly.
 - Add more explanation into comments to state than mapping guest frames
   and allocation of pages for ioreq servers are not simultaneously
   permitted.
 - Add a comment into asm/ioreq.h stating the meaning of the index
   value passed to hvm_get_ioreq_server_frame().
---
 xen/arch/x86/hvm/ioreq.c        | 156 ++++++++++++++++++++++++++++++++++++++++
 xen/arch/x86/mm.c               |  49 +++++++++++++
 xen/common/memory.c             |   3 +-
 xen/include/asm-arm/mm.h        |   7 ++
 xen/include/asm-x86/hvm/ioreq.h |   2 +
 xen/include/asm-x86/mm.h        |   5 ++
 xen/include/public/hvm/dm_op.h  |   4 ++
 xen/include/public/memory.h     |   9 +++
 8 files changed, 234 insertions(+), 1 deletion(-)

diff --git a/xen/arch/x86/hvm/ioreq.c b/xen/arch/x86/hvm/ioreq.c
index 39de659ddf..d991ac9cdc 100644
--- a/xen/arch/x86/hvm/ioreq.c
+++ b/xen/arch/x86/hvm/ioreq.c
@@ -259,6 +259,19 @@ static int hvm_map_ioreq_gfn(struct hvm_ioreq_server *s, 
bool buf)
     struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
     int rc;
 
+    if ( iorp->page )
+    {
+        /*
+         * If a page has already been allocated (which will happen on
+         * demand if hvm_get_ioreq_server_frame() is called), then
+         * mapping a guest frame is not permitted.
+         */
+        if ( gfn_eq(iorp->gfn, INVALID_GFN) )
+            return -EPERM;
+
+        return 0;
+    }
+
     if ( d->is_dying )
         return -EINVAL;
 
@@ -281,6 +294,70 @@ static int hvm_map_ioreq_gfn(struct hvm_ioreq_server *s, 
bool buf)
     return rc;
 }
 
+static int hvm_alloc_ioreq_mfn(struct hvm_ioreq_server *s, bool buf)
+{
+    struct domain *currd = current->domain;
+    struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
+
+    if ( iorp->page )
+    {
+        /*
+         * If a guest frame has already been mapped (which may happen
+         * on demand if hvm_get_ioreq_server_info() is called), then
+         * allocating a page is not permitted.
+         */
+        if ( !gfn_eq(iorp->gfn, INVALID_GFN) )
+            return -EPERM;
+
+        return 0;
+    }
+
+    /*
+     * Allocated IOREQ server pages are assigned to the emulating
+     * domain, not the target domain. This is because the emulator is
+     * likely to be destroyed after the target domain has been torn
+     * down, and we must use MEMF_no_refcount otherwise page allocation
+     * could fail if the emulating domain has already reached its
+     * maximum allocation.
+     */
+    iorp->page = alloc_domheap_page(currd, MEMF_no_refcount);
+    if ( !iorp->page )
+        return -ENOMEM;
+
+    if ( !get_page_type(iorp->page, PGT_writable_page) )
+    {
+        ASSERT_UNREACHABLE();
+        put_page(iorp->page);
+        iorp->page = NULL;
+        return -ENOMEM;
+    }
+
+    iorp->va = __map_domain_page_global(iorp->page);
+    if ( !iorp->va )
+    {
+        put_page_and_type(iorp->page);
+        iorp->page = NULL;
+        return -ENOMEM;
+    }
+
+    clear_page(iorp->va);
+    return 0;
+}
+
+static void hvm_free_ioreq_mfn(struct hvm_ioreq_server *s, bool buf)
+{
+    struct hvm_ioreq_page *iorp = buf ? &s->bufioreq : &s->ioreq;
+
+    if ( !iorp->page )
+        return;
+
+    unmap_domain_page_global(iorp->va);
+    iorp->va = NULL;
+
+    put_page_and_type(iorp->page);
+    iorp->page = NULL;
+}
+
 bool is_ioreq_server_page(struct domain *d, const struct page_info *page)
 {
     const struct hvm_ioreq_server *s;
@@ -484,6 +561,27 @@ static void hvm_ioreq_server_unmap_pages(struct 
hvm_ioreq_server *s)
     hvm_unmap_ioreq_gfn(s, false);
 }
 
+static int hvm_ioreq_server_alloc_pages(struct hvm_ioreq_server *s)
+{
+    int rc;
+
+    rc = hvm_alloc_ioreq_mfn(s, false);
+
+    if ( !rc && (s->bufioreq_handling != HVM_IOREQSRV_BUFIOREQ_OFF) )
+        rc = hvm_alloc_ioreq_mfn(s, true);
+
+    if ( rc )
+        hvm_free_ioreq_mfn(s, false);
+
+    return rc;
+}
+
+static void hvm_ioreq_server_free_pages(struct hvm_ioreq_server *s)
+{
+    hvm_free_ioreq_mfn(s, true);
+    hvm_free_ioreq_mfn(s, false);
+}
+
 static void hvm_ioreq_server_free_rangesets(struct hvm_ioreq_server *s)
 {
     unsigned int i;
@@ -612,7 +710,18 @@ static int hvm_ioreq_server_init(struct hvm_ioreq_server 
*s,
 
  fail_add:
     hvm_ioreq_server_remove_all_vcpus(s);
+
+    /*
+     * NOTE: It is safe to call both hvm_ioreq_server_unmap_pages() and
+     *       hvm_ioreq_server_free_pages() in that order.
+     *       This is because the former will do nothing if the pages
+     *       are not mapped, leaving the page to be freed by the latter.
+     *       However if the pages are mapped then the former will set
+     *       the page_info pointer to NULL, meaning the latter will do
+     *       nothing.
+     */
     hvm_ioreq_server_unmap_pages(s);
+    hvm_ioreq_server_free_pages(s);
 
     return rc;
 }
@@ -622,6 +731,7 @@ static void hvm_ioreq_server_deinit(struct hvm_ioreq_server 
*s)
     ASSERT(!s->enabled);
     hvm_ioreq_server_remove_all_vcpus(s);
     hvm_ioreq_server_unmap_pages(s);
+    hvm_ioreq_server_free_pages(s);
     hvm_ioreq_server_free_rangesets(s);
 }
 
@@ -777,6 +887,52 @@ int hvm_get_ioreq_server_info(struct domain *d, ioservid_t 
id,
     return rc;
 }
 
+int hvm_get_ioreq_server_frame(struct domain *d, ioservid_t id,
+                               unsigned long idx, mfn_t *mfn)
+{
+    struct hvm_ioreq_server *s;
+    int rc;
+
+    spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
+
+    if ( id == DEFAULT_IOSERVID )
+        return -EOPNOTSUPP;
+
+    s = get_ioreq_server(d, id);
+
+    ASSERT(!IS_DEFAULT(s));
+
+    rc = hvm_ioreq_server_alloc_pages(s);
+    if ( rc )
+        goto out;
+
+    switch ( idx )
+    {
+    case XENMEM_resource_ioreq_server_frame_bufioreq:
+        rc = -ENOENT;
+        if ( !HANDLE_BUFIOREQ(s) )
+            goto out;
+
+        *mfn = _mfn(page_to_mfn(s->bufioreq.page));
+        rc = 0;
+        break;
+
+    case XENMEM_resource_ioreq_server_frame_ioreq(0):
+        *mfn = _mfn(page_to_mfn(s->ioreq.page));
+        rc = 0;
+        break;
+
+    default:
+        rc = -EINVAL;
+        break;
+    }
+
+ out:
+    spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
+
+    return rc;
+}
+
 int hvm_map_io_range_to_ioreq_server(struct domain *d, ioservid_t id,
                                      uint32_t type, uint64_t start,
                                      uint64_t end)
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 62d313e3f5..a8c207b973 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -122,6 +122,7 @@
 #include <asm/fixmap.h>
 #include <asm/io_apic.h>
 #include <asm/pci.h>
+#include <asm/hvm/ioreq.h>
 
 #include <asm/hvm/grant_table.h>
 #include <asm/pv/grant_table.h>
@@ -4009,6 +4010,54 @@ int xenmem_add_to_physmap_one(
     return rc;
 }
 
+static int acquire_ioreq_server(struct domain *d, ioservid_t id,
+                                unsigned long frame,
+                                unsigned int nr_frames,
+                                xen_pfn_t mfn_list[])
+{
+    unsigned int i;
+
+    for ( i = 0; i < nr_frames; i++ )
+    {
+        mfn_t mfn;
+        int rc = hvm_get_ioreq_server_frame(d, id, frame + i, &mfn);
+
+        if ( rc )
+            return rc;
+
+        mfn_list[i] = mfn_x(mfn);
+    }
+
+    return 0;
+}
+
+int arch_acquire_resource(struct domain *d, unsigned int type,
+                          unsigned int id, unsigned long frame,
+                          unsigned int nr_frames, xen_pfn_t mfn_list[])
+{
+    int rc;
+
+    switch ( type )
+    {
+    case XENMEM_resource_ioreq_server:
+    {
+        ioservid_t ioservid = id;
+
+        if ( id != (unsigned int)ioservid )
+            return -EINVAL;
+
+        rc = acquire_ioreq_server(d, ioservid, frame, nr_frames, mfn_list);
+        break;
+    }
+
+    default:
+        rc = -EOPNOTSUPP;
+        break;
+    }
+
+    return rc;
+}
+
 long arch_memory_op(unsigned long cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
 {
     int rc;
diff --git a/xen/common/memory.c b/xen/common/memory.c
index fb3ba5cc28..1c6932fd85 100644
--- a/xen/common/memory.c
+++ b/xen/common/memory.c
@@ -1011,7 +1011,8 @@ static int acquire_resource(
     switch ( xmar.type )
     {
     default:
-        rc = -EOPNOTSUPP;
+        rc = arch_acquire_resource(d, xmar.type, xmar.id, xmar.frame,
+                                   xmar.nr_frames, mfn_list);
         break;
     }
 
diff --git a/xen/include/asm-arm/mm.h b/xen/include/asm-arm/mm.h
index cd6dfb54b9..9e0ea526aa 100644
--- a/xen/include/asm-arm/mm.h
+++ b/xen/include/asm-arm/mm.h
@@ -376,6 +376,13 @@ static inline void put_page_and_type(struct page_info 
*page)
 
 void clear_and_clean_page(struct page_info *page);
 
+static inline int arch_acquire_resource(
+    struct domain *d, unsigned int type, unsigned int id,
+    unsigned long frame,unsigned int nr_frames, xen_pfn_t mfn_list[])
+{
+    return -EOPNOTSUPP;
+}
+
 #endif /*  __ARCH_ARM_MM__ */
 /*
  * Local variables:
diff --git a/xen/include/asm-x86/hvm/ioreq.h b/xen/include/asm-x86/hvm/ioreq.h
index 1829fcf43e..9e37c97a37 100644
--- a/xen/include/asm-x86/hvm/ioreq.h
+++ b/xen/include/asm-x86/hvm/ioreq.h
@@ -31,6 +31,8 @@ int hvm_get_ioreq_server_info(struct domain *d, ioservid_t id,
                               unsigned long *ioreq_gfn,
                               unsigned long *bufioreq_gfn,
                               evtchn_port_t *bufioreq_port);
+int hvm_get_ioreq_server_frame(struct domain *d, ioservid_t id,
+                               unsigned long idx, mfn_t *mfn);
 int hvm_map_io_range_to_ioreq_server(struct domain *d, ioservid_t id,
                                      uint32_t type, uint64_t start,
                                      uint64_t end);
diff --git a/xen/include/asm-x86/mm.h b/xen/include/asm-x86/mm.h
index 26f0153164..5b1ae02723 100644
--- a/xen/include/asm-x86/mm.h
+++ b/xen/include/asm-x86/mm.h
@@ -626,4 +626,9 @@ static inline bool arch_mfn_in_directmap(unsigned long mfn)
     return mfn <= (virt_to_mfn(eva - 1) + 1);
 }
 
+int arch_acquire_resource(struct domain *d, unsigned int type,
+                          unsigned int id, unsigned long frame,
+                          unsigned int nr_frames,
+                          xen_pfn_t mfn_list[]);
+
 #endif /* __ASM_X86_MM_H__ */
diff --git a/xen/include/public/hvm/dm_op.h b/xen/include/public/hvm/dm_op.h
index 13b3737c2f..add68ea192 100644
--- a/xen/include/public/hvm/dm_op.h
+++ b/xen/include/public/hvm/dm_op.h
@@ -90,6 +90,10 @@ struct xen_dm_op_create_ioreq_server {
  * the frame numbers passed back in gfns <ioreq_gfn> and <bufioreq_gfn>
  * respectively. (If the IOREQ Server is not handling buffered emulation
  * only <ioreq_gfn> will be valid).
+ *
+ * NOTE: To access the synchronous ioreq structures and buffered ioreq
+ *       ring, it is preferable to use the XENMEM_acquire_resource memory
+ *       op specifying resource type XENMEM_resource_ioreq_server.
  */
 #define XEN_DMOP_get_ioreq_server_info 2
 
diff --git a/xen/include/public/memory.h b/xen/include/public/memory.h
index 83e60b6603..838f248a59 100644
--- a/xen/include/public/memory.h
+++ b/xen/include/public/memory.h
@@ -609,9 +609,14 @@ struct xen_mem_acquire_resource {
     domid_t domid;
     /* IN - the type of resource */
     uint16_t type;
+
+#define XENMEM_resource_ioreq_server 0
+
     /*
      * IN - a type-specific resource identifier, which must be zero
      *      unless stated otherwise.
+     *
+     * type == XENMEM_resource_ioreq_server -> id == ioreq server id
      */
     uint32_t id;
     /* IN/OUT - As an IN parameter number of frames of the resource
@@ -625,6 +630,10 @@ struct xen_mem_acquire_resource {
      *      is ignored if nr_frames is 0.
      */
     uint64_aligned_t frame;
+
+#define XENMEM_resource_ioreq_server_frame_bufioreq 0
+#define XENMEM_resource_ioreq_server_frame_ioreq(n) (1 + (n))
+
     /* IN/OUT - If the tools domain is PV then, upon return, frame_list
      *          will be populated with the MFNs of the resource.
      *          If the tools domain is HVM then it is expected that, on
-- 
2.11.0


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
https://lists.xen.org/xen-devel

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.