HYPERCALL_version_op. New hypercall mirroring XENVER_ but sane.

This hypercall mirrors the XENVER_ in that it has similar functionality.
However it is designed differently:
 - No compat layer. The data structures are the same size on 32
   as on 64-bit.
 - The hypercall accepts three arguments - the command, pointer to
   an buffer, and the length of the buffer.
 - Each sub-ops can be "probed" for size by returning the size of
   buffer that will be needed - if the buffer is NULL.
 - Subops can complete even if the buffer is too small - truncated
   data will be filled and hypercall will return -ENOBUFS.
 - VERSION_commandline, VERSION_changeset are privileged.
 - There is no XENVER_compile_info equivalent.
 - The hypercall can return -EPERM and toolstack/OSes are expected
   to deal with. However there are three subops: XEN_VERSION_version,
   XEN_VERSION_platform_parameters and XEN_VERSION_get_features
   that will always return an value as guests cannot survive without them.

While we combine some of the common code between XENVER_ and VERSION_
take the liberty of moving pae_extended_cr3 in x86 area.

Suggested-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Daniel De Graaf <dgdegra@tycho.nsa.gov> [XSM bits]
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>

tools/flask/policy/policy/modules/xen/xen.te

@@ -74,11 +74,12 @@ allow dom0_t xen_t:xen2 {
     get_symbol
 };
 
-# Allow dom0 to use all XENVER_ subops that have checks.
+# Allow dom0 to use all XENVER_ subops and VERSION subops that have checks.
 # Note that dom0 is part of domain_type so this has duplicates.
 allow dom0_t xen_t:version {
     xen_extraversion xen_compile_info xen_capabilities
     xen_changeset xen_pagesize xen_guest_handle xen_commandline
+    extraversion capabilities changeset pagesize guest_handle commandline
 };
 
 allow dom0_t xen_t:mmu memorymap;
@@ -145,10 +146,12 @@ if (guest_writeconsole) {
 # pmu_ctrl is for)
 allow domain_type xen_t:xen2 pmu_use;
 
-# For normal guests all possible except XENVER_commandline.
+# For normal guests all possible except XENVER_commandline, VERSION_changeset,
+# and VERSION_commandline
 allow domain_type xen_t:version {
     xen_extraversion xen_compile_info xen_capabilities
     xen_changeset xen_pagesize xen_guest_handle
+    extraversion capabilities pagesize guest_handle
 };
 
 ###############################################################################

xen/arch/arm/traps.c

@@ -1235,6 +1235,7 @@ static arm_hypercall_t arm_hypercall_table[] = {
     HYPERCALL(multicall, 2),
     HYPERCALL(platform_op, 1),
     HYPERCALL_ARM(vcpu_op, 3),
+    HYPERCALL(version_op, 3),
 };
 
 #ifndef NDEBUG

xen/arch/x86/hvm/hvm.c

@@ -5324,6 +5324,7 @@ static const struct {
     COMPAT_CALL(platform_op),
     COMPAT_CALL(mmuext_op),
     HYPERCALL(xenpmu_op),
+    HYPERCALL(version_op),
     HYPERCALL(arch_1)
 };
 

xen/arch/x86/x86_64/compat/entry.S

@@ -394,6 +394,7 @@ ENTRY(compat_hypercall_table)
         .quad do_tmem_op
         .quad do_ni_hypercall           /* reserved for XenClient */
         .quad do_xenpmu_op              /* 40 */
+        .quad do_version_op
         .rept __HYPERVISOR_arch_0-((.-compat_hypercall_table)/8)
         .quad compat_ni_hypercall
         .endr
@@ -445,6 +446,7 @@ ENTRY(compat_hypercall_args_table)
         .byte 1 /* do_tmem_op               */
         .byte 0 /* reserved for XenClient   */
         .byte 2 /* do_xenpmu_op             */  /* 40 */
+        .byte 3 /* do_version_op            */
         .rept __HYPERVISOR_arch_0-(.-compat_hypercall_args_table)
         .byte 0 /* compat_ni_hypercall      */
         .endr

xen/arch/x86/x86_64/entry.S

@@ -730,6 +730,7 @@ ENTRY(hypercall_table)
         .quad do_tmem_op
         .quad do_ni_hypercall       /* reserved for XenClient */
         .quad do_xenpmu_op          /* 40 */
+        .quad do_version_op
         .rept __HYPERVISOR_arch_0-((.-hypercall_table)/8)
         .quad do_ni_hypercall
         .endr
@@ -781,6 +782,7 @@ ENTRY(hypercall_args_table)
         .byte 1 /* do_tmem_op           */
         .byte 0 /* reserved for XenClient */
         .byte 2 /* do_xenpmu_op         */  /* 40 */
+        .byte 3 /* do_version_op        */
         .rept __HYPERVISOR_arch_0-(.-hypercall_args_table)
         .byte 0 /* do_ni_hypercall      */
         .endr

xen/common/compat/kernel.c

@@ -39,6 +39,8 @@ CHECK_TYPE(capabilities_info);
 
 CHECK_TYPE(domain_handle);
 
+CHECK_TYPE(version_op_val);
+
 #define xennmi_callback compat_nmi_callback
 #define xennmi_callback_t compat_nmi_callback_t
 

xen/common/kernel.c

@@ -221,6 +221,47 @@ void __init do_initcalls(void)
 
 #endif
 
+static int get_features(struct domain *d, xen_feature_info_t *fi)
+{
+    switch ( fi->submap_idx )
+    {
+    case 0:
+        fi->submap = (1U << XENFEAT_memory_op_vnode_supported);
+        if ( paging_mode_translate(d) )
+            fi->submap |=
+                (1U << XENFEAT_writable_page_tables) |
+                (1U << XENFEAT_auto_translated_physmap);
+        if ( is_hardware_domain(d) )
+            fi->submap |= 1U << XENFEAT_dom0;
+#ifdef CONFIG_X86
+        if ( VM_ASSIST(d, pae_extended_cr3) )
+            fi->submap |= (1U << XENFEAT_pae_pgdir_above_4gb);
+        switch ( d->guest_type )
+        {
+        case guest_type_pv:
+            fi->submap |= (1U << XENFEAT_mmu_pt_update_preserve_ad) |
+                          (1U << XENFEAT_highmem_assist) |
+                          (1U << XENFEAT_gnttab_map_avail_bits);
+            break;
+        case guest_type_pvh:
+            fi->submap |= (1U << XENFEAT_hvm_safe_pvclock) |
+                          (1U << XENFEAT_supervisor_mode_kernel) |
+                          (1U << XENFEAT_hvm_callback_vector);
+            break;
+        case guest_type_hvm:
+            fi->submap |= (1U << XENFEAT_hvm_safe_pvclock) |
+                          (1U << XENFEAT_hvm_callback_vector) |
+                          (1U << XENFEAT_hvm_pirqs);
+           break;
+        }
+#endif
+        break;
+    default:
+        return -EINVAL;
+    }
+    return 0;
+}
+
 /*
  * Simple hypercalls.
  */
@@ -298,47 +339,14 @@ DO(xen_version)(int cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
     case XENVER_get_features:
     {
         xen_feature_info_t fi;
-        struct domain *d = current->domain;
+        int rc;
 
         if ( copy_from_guest(&fi, arg, 1) )
             return -EFAULT;
 
-        switch ( fi.submap_idx )
-        {
-        case 0:
-            fi.submap = (1U << XENFEAT_memory_op_vnode_supported);
-            if ( VM_ASSIST(d, pae_extended_cr3) )
-                fi.submap |= (1U << XENFEAT_pae_pgdir_above_4gb);
-            if ( paging_mode_translate(d) )
-                fi.submap |= 
-                    (1U << XENFEAT_writable_page_tables) |
-                    (1U << XENFEAT_auto_translated_physmap);
-            if ( is_hardware_domain(d) )
-                fi.submap |= 1U << XENFEAT_dom0;
-#ifdef CONFIG_X86
-            switch ( d->guest_type )
-            {
-            case guest_type_pv:
-                fi.submap |= (1U << XENFEAT_mmu_pt_update_preserve_ad) |
-                             (1U << XENFEAT_highmem_assist) |
-                             (1U << XENFEAT_gnttab_map_avail_bits);
-                break;
-            case guest_type_pvh:
-                fi.submap |= (1U << XENFEAT_hvm_safe_pvclock) |
-                             (1U << XENFEAT_supervisor_mode_kernel) |
-                             (1U << XENFEAT_hvm_callback_vector);
-                break;
-            case guest_type_hvm:
-                fi.submap |= (1U << XENFEAT_hvm_safe_pvclock) |
-                             (1U << XENFEAT_hvm_callback_vector) |
-                             (1U << XENFEAT_hvm_pirqs);
-                break;
-            }
-#endif
-            break;
-        default:
-            return -EINVAL;
-        }
+        rc = get_features(current->domain, &fi);
+        if ( rc )
+            return rc;
 
         if ( __copy_to_guest(arg, &fi, 1) )
             return -EFAULT;
@@ -381,6 +389,122 @@ DO(xen_version)(int cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
     return -ENOSYS;
 }
 
+/* Computed by capabilities_cache_init. */
+static xen_capabilities_info_t __read_mostly cached_cap;
+static unsigned int __read_mostly cached_cap_len;
+
+/*
+ * Similar to HYPERVISOR_xen_version but with a sane interface
+ * (has a length, one can probe for the length) and with one less sub-ops:
+ * missing XENVER_compile_info.
+ */
+DO(version_op)(unsigned int cmd, XEN_GUEST_HANDLE_PARAM(void) arg,
+               unsigned int len)
+{
+    union {
+        xen_version_op_val_t val;
+        xen_feature_info_t fi;
+    } u = {};
+    unsigned int sz = 0;
+    const void *ptr = NULL;
+    int rc = xsm_version_op(XSM_OTHER, cmd);
+
+    if ( rc )
+        return rc;
+
+    /*
+     * The HYPERVISOR_xen_version sub-ops differ in that some return the value,
+     * and some copy it on back on argument. We follow the same rule for all
+     * sub-ops: return the number of bytes written, or negative errno on
+     * failure, and always copy the result in arg. Yeey sanity!
+     */
+    switch ( cmd )
+    {
+    case XEN_VERSION_version:
+        sz = sizeof(xen_version_op_val_t);
+        u.val = (xen_major_version() << 16) | xen_minor_version();
+        break;
+
+    case XEN_VERSION_extraversion:
+        sz = strlen(xen_extra_version()) + 1;
+        ptr = xen_extra_version();
+        break;
+
+    case XEN_VERSION_capabilities:
+        sz = cached_cap_len;
+        ptr = cached_cap;
+        break;
+
+    case XEN_VERSION_changeset:
+        sz = strlen(xen_changeset()) + 1;
+        ptr = xen_changeset();
+        break;
+
+    case XEN_VERSION_platform_parameters:
+        sz = sizeof(xen_version_op_val_t);
+        u.val = HYPERVISOR_VIRT_START;
+        break;
+
+    case XEN_VERSION_get_features:
+        sz = sizeof(xen_feature_info_t);
+
+        if ( guest_handle_is_null(arg) )
+            break;
+
+        if ( copy_from_guest(&u.fi, arg, 1) )
+        {
+            rc = -EFAULT;
+            break;
+        }
+        rc = get_features(current->domain, &u.fi);
+        break;
+
+    case XEN_VERSION_pagesize:
+        sz = sizeof(xen_version_op_val_t);
+        u.val = PAGE_SIZE;
+        break;
+
+    case XEN_VERSION_guest_handle:
+        sz = ARRAY_SIZE(current->domain->handle);
+        ptr = current->domain->handle;
+        break;
+
+    case XEN_VERSION_commandline:
+        sz = strlen(saved_cmdline) + 1;
+        ptr = saved_cmdline;
+        break;
+
+    default:
+        rc = -ENOSYS;
+    }
+
+    if ( rc )
+        return rc;
+
+    /*
+     * This hypercall also allows the client to probe. If it provides
+     * a NULL arg we will return the size of the space it has to
+     * allocate for the specific sub-op.
+     */
+    ASSERT(sz);
+    if ( guest_handle_is_null(arg) )
+        return sz;
+
+    if ( !rc )
+    {
+        unsigned int bytes = min(sz, len);
+
+        if ( copy_to_guest(arg, ptr ? : &u, bytes) )
+            rc = -EFAULT;
+
+        /* We return len (truncate) worth of data even if we fail. */
+        if ( !rc && sz > len )
+            rc = -ENOBUFS;
+    }
+
+    return rc == 0 ? sz : rc;
+}
+
 DO(nmi_op)(unsigned int cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
 {
     struct xennmi_callback cb;
@@ -418,6 +542,20 @@ DO(ni_hypercall)(void)
     return -ENOSYS;
 }
 
+static int __init capabilities_cache_init(void)
+{
+    /*
+     * Pre-populate the cache so we do not have to worry about
+     * simultaneous invocations on safe_strcat by guests and the cache
+     * data becoming garbage.
+     */
+    arch_get_xen_caps(&cached_cap);
+    cached_cap_len = strlen(cached_cap) + 1;
+
+    return 0;
+}
+__initcall(capabilities_cache_init);
+
 /*
  * Local variables:
  * mode: C

xen/include/public/arch-arm.h

@@ -128,6 +128,8 @@
  *    * VCPUOP_register_vcpu_info
  *    * VCPUOP_register_runstate_memory_area
  *
+ *  HYPERVISOR_version_op
+ *   All generic sub-operations
  *
  * Other notes on the ARM ABI:
  *

xen/include/public/version.h

@@ -30,7 +30,16 @@
 
 #include "xen.h"
 
-/* NB. All ops return zero on success, except XENVER_{version,pagesize} */
+/*
+ * There are two hypercalls mentioned in here. The XENVER_ are for
+ * HYPERCALL_xen_version (17), while VERSION_ are for the
+ * HYPERCALL_version_op (41).
+ *
+ * The subops are very similar except that the later hypercall has a
+ * sane interface.
+ *
+ * NB. All XENVER_ ops return zero on success, except XENVER_{version,pagesize}
+ */
 
 /* arg == NULL; returns major:minor (16:16). */
 #define XENVER_version      0
@@ -87,6 +96,67 @@ typedef struct xen_feature_info xen_feature_info_t;
 #define XENVER_commandline 9
 typedef char xen_commandline_t[1024];
 
+/*
+ * The HYPERCALL_version_op has a set of sub-ops which mirror the
+ * sub-ops of HYPERCALL_xen_version. However this hypercall differs
+ * radically from the former:
+ *  - It returns the amount of bytes copied, or
+ *  - It will return -XEN_EPERM if the sub-op is denied to the guest.
+ *    (Albeit XEN_VERSION_version, XEN_VERSION_platform_parameters, and
+ *    XEN_VERSION_get_features will always return an value as guest cannot
+ *    survive without this information).
+ *  - It will return the requested data in arg.
+ *  - It requires an third argument (len) for the length of the
+ *    arg. Naturally the arg has to fit the requested data otherwise
+ *    -XEN_ENOBUFS is returned.
+ *
+ * It also offers a mechanism to probe for the amount of bytes an
+ * sub-op will require. Having the arg have a NULL handle will
+ * return the number of bytes requested for the operation.
+ * Or a negative value if an error is encountered.
+ */
+
+typedef uint64_t xen_version_op_val_t;
+DEFINE_XEN_GUEST_HANDLE(xen_version_op_val_t);
+
+/*
+ * arg == xen_version_op_val_t. Encoded as major:minor (31..16:15..0), while
+ * 63..32 are zero.
+ */
+#define XEN_VERSION_version             0
+
+/* arg == char[]. Contains NUL terminated utf-8 string. */
+#define XEN_VERSION_extraversion        1
+
+/* arg == char[]. Contains NUL terminated utf-8 string. */
+#define XEN_VERSION_capabilities        3
+
+/* arg == char[]. Contains NUL terminated utf-8 string. */
+#define XEN_VERSION_changeset           4
+
+/* arg == xen_version_op_val_t. */
+#define XEN_VERSION_platform_parameters 5
+
+/*
+ * arg = xen_feature_info_t - shares the same structure
+ * as the XENVER_get_features.
+ */
+#define XEN_VERSION_get_features        6
+
+/* arg == xen_version_op_val_t. */
+#define XEN_VERSION_pagesize            7
+
+/*
+ * arg == void.
+ *
+ * The toolstack fills it out for guest consumption. It is intended to hold
+ * the UUID of the guest.
+ */
+#define XEN_VERSION_guest_handle        8
+
+/* arg = char[]. Contains NUL terminated utf-8 string. */
+#define XEN_VERSION_commandline         9
+
 #endif /* __XEN_PUBLIC_VERSION_H__ */
 
 /*

xen/include/public/xen.h

@@ -115,6 +115,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_ulong_t);
 #define __HYPERVISOR_tmem_op              38
 #define __HYPERVISOR_xc_reserved_op       39 /* reserved for XenClient */
 #define __HYPERVISOR_xenpmu_op            40
+#define __HYPERVISOR_version_op           41 /* supersedes xen_version (17) */
 
 /* Architecture-specific hypercall definitions. */
 #define __HYPERVISOR_arch_0               48

xen/include/xen/hypercall.h

@@ -147,6 +147,10 @@ do_xenoprof_op(int op, XEN_GUEST_HANDLE_PARAM(void) arg);
 extern long
 do_xenpmu_op(unsigned int op, XEN_GUEST_HANDLE_PARAM(xen_pmu_params_t) arg);
 
+extern long
+do_version_op(unsigned int cmd,
+    XEN_GUEST_HANDLE_PARAM(void) arg, unsigned int len);
+
 #ifdef CONFIG_COMPAT
 
 extern int

xen/include/xsm/dummy.h

@@ -751,3 +751,24 @@ static XSM_INLINE int xsm_xen_version (XSM_DEFAULT_ARG uint32_t op)
         return xsm_default_action(XSM_PRIV, current->domain, NULL);
     }
 }
+
+static XSM_INLINE int xsm_version_op (XSM_DEFAULT_ARG uint32_t op)
+{
+    XSM_ASSERT_ACTION(XSM_OTHER);
+    switch ( op )
+    {
+    case XEN_VERSION_version:
+    case XEN_VERSION_platform_parameters:
+    case XEN_VERSION_get_features:
+        /* These MUST always be accessible to any guest by default. */
+        return 0;
+    case XEN_VERSION_extraversion:
+    case XEN_VERSION_capabilities:
+    case XEN_VERSION_pagesize:
+    case XEN_VERSION_guest_handle:
+        /* These can be accessible to a guest. */
+        return xsm_default_action(XSM_HOOK, current->domain, NULL);
+    default:
+        return xsm_default_action(XSM_PRIV, current->domain, NULL);
+    }
+}

xen/include/xsm/xsm.h

@@ -197,6 +197,7 @@ struct xsm_operations {
     int (*pmu_op) (struct domain *d, unsigned int op);
 #endif
     int (*xen_version) (uint32_t cmd);
+    int (*version_op) (uint32_t cmd);
 };
 
 #ifdef CONFIG_XSM
@@ -740,6 +741,11 @@ static inline int xsm_xen_version (xsm_default_t def, uint32_t op)
     return xsm_ops->xen_version(op);
 }
 
+static inline int xsm_version_op (xsm_default_t def, uint32_t op)
+{
+    return xsm_ops->version_op(op);
+}
+
 #endif /* XSM_NO_WRAPPERS */
 
 #ifdef CONFIG_MULTIBOOT

xen/xsm/dummy.c

@@ -163,4 +163,5 @@ void xsm_fixup_ops (struct xsm_operations *ops)
     set_to_dummy_if_null(ops, pmu_op);
 #endif
     set_to_dummy_if_null(ops, xen_version);
+    set_to_dummy_if_null(ops, version_op);
 }

xen/xsm/flask/hooks.c

@@ -1658,6 +1658,40 @@ static int flask_xen_version (uint32_t op)
     }
 }
 
+static int flask_version_op (uint32_t op)
+{
+    u32 dsid = domain_sid(current->domain);
+
+    switch ( op )
+    {
+    case XEN_VERSION_version:
+    case XEN_VERSION_platform_parameters:
+    case XEN_VERSION_get_features:
+        /* These MUST always be accessible to any guest by default. */
+        return 0;
+    case XEN_VERSION_extraversion:
+        return avc_has_perm(dsid, SECINITSID_XEN, SECCLASS_VERSION,
+                            VERSION__EXTRAVERSION, NULL);
+    case XEN_VERSION_capabilities:
+        return avc_has_perm(dsid, SECINITSID_XEN, SECCLASS_VERSION,
+                            VERSION__CAPABILITIES, NULL);
+    case XEN_VERSION_changeset:
+        return avc_has_perm(dsid, SECINITSID_XEN, SECCLASS_VERSION,
+                            VERSION__CHANGESET, NULL);
+    case XEN_VERSION_pagesize:
+        return avc_has_perm(dsid, SECINITSID_XEN, SECCLASS_VERSION,
+                            VERSION__PAGESIZE, NULL);
+    case XEN_VERSION_guest_handle:
+        return avc_has_perm(dsid, SECINITSID_XEN, SECCLASS_VERSION,
+                            VERSION__GUEST_HANDLE, NULL);
+    case XEN_VERSION_commandline:
+        return avc_has_perm(dsid, SECINITSID_XEN, SECCLASS_VERSION,
+                            VERSION__COMMANDLINE, NULL);
+    default:
+        return -EPERM;
+    }
+}
+
 long do_flask_op(XEN_GUEST_HANDLE_PARAM(xsm_op_t) u_flask_op);
 int compat_flask_op(XEN_GUEST_HANDLE_PARAM(xsm_op_t) u_flask_op);
 
@@ -1797,6 +1831,7 @@ static struct xsm_operations flask_ops = {
     .pmu_op = flask_pmu_op,
 #endif
     .xen_version = flask_xen_version,
+    .version_op = flask_version_op,
 };
 
 static __init void flask_init(void)

xen/xsm/flask/policy/access_vectors

@@ -496,12 +496,14 @@ class security
     del_ocontext
 }
 
-# Class version is used to describe the XENVER_ hypercall.
+# Class version is used to describe the XENVER_ and VERSION hypercall.
 # Almost all sub-ops are described here - in the default case all of them should
-# be allowed except the XENVER_commandline.
+# be allowed except the XENVER_commandline, VERSION_commandline, and
+# VERSION_changeset.
 #
 # The ones that are omitted are XENVER_version, XENVER_platform_parameters,
-# and XENVER_get_features  - as they MUST always be returned to a guest.
+# XENVER_get_features, XEN_VERSION_version, XEN_VERSION_platform_parameters,
+# and XEN_VERSION_get_features - as they MUST always be returned to a guest.
 #
 class version
 {
@@ -519,4 +521,17 @@ class version
     xen_guest_handle
 # Xen command line.
     xen_commandline
+# --- VERSION hypercall ---
+# Extra informations (-unstable).
+    extraversion
+# Such as "xen-3.0-x86_64 xen-3.0-x86_32p hvm-3.0-x86_32 hvm-3.0-x86_32p hvm-3.0-x86_64".
+    capabilities
+# Source code changeset.
+    changeset
+# Page size the hypervisor uses.
+    pagesize
+# An value that the control stack can choose.
+    guest_handle
+# Xen command line.
+    commandline
 }