xen/x86: support per-domain flag for xpti

Instead of switching XPTI globally on or off add a per-domain flag for
that purpose. This allows to modify the xpti boot parameter to support
running dom0 without Meltdown mitigations. Using "xpti=no-dom0" as boot
parameter will achieve that.

Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

docs/misc/xen-command-line.markdown

@@ -1655,14 +1655,24 @@ clustered mode.  The default, given no hint from the **FADT**, is cluster
 mode.
 
 ### xpti
-> `= <boolean>`
+> `= List of [ default | <boolean> | dom0=<bool> | domu=<bool> ]`
 
-> Default: `false` on AMD hardware
+> Default: `false` on hardware not to be vulnerable to Meltdown (e.g. AMD)
 > Default: `true` everywhere else
 
 Override default selection of whether to isolate 64-bit PV guest page
 tables.
 
+`true` activates page table isolation even on hardware not vulnerable by
+Meltdown for all domains.
+
+`false` deactivates page table isolation on all systems for all domains.
+
+`default` sets the default behaviour.
+
+With `dom0` and `domu` it is possible to control page table isolation
+for dom0 or guest domains only.
+
 ** WARNING: Not yet a complete isolation implementation, but better than
 nothing. **
 

xen/arch/x86/cpu/common.c

@@ -374,6 +374,9 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 		if (test_bit(X86_FEATURE_SC_MSR_IDLE,
 			     boot_cpu_data.x86_capability))
 			__set_bit(X86_FEATURE_SC_MSR_IDLE, c->x86_capability);
+		if (test_bit(X86_FEATURE_NO_XPTI,
+		             boot_cpu_data.x86_capability))
+			__set_bit(X86_FEATURE_NO_XPTI, c->x86_capability);
 
 		/* AND the already accumulated flags with these */
 		for ( i = 0 ; i < NCAPINTS ; i++ )

xen/arch/x86/domain.c

@@ -419,6 +419,8 @@ int switch_compat(struct domain *d)
 
     d->arch.x87_fip_width = 4;
 
+    d->arch.pv_domain.xpti = 0;
+
     return 0;
 
  undo_and_fail:
@@ -655,9 +657,14 @@ int arch_domain_create(struct domain *d, unsigned int domcr_flags,
             goto fail;
     }
     else
+    {
         /* 64-bit PV guest by default. */
         d->arch.is_32bit_pv = d->arch.has_32bit_shinfo = 0;
 
+        d->arch.pv_domain.xpti = opt_xpti & (is_hardware_domain(d)
+                                             ? OPT_XPTI_DOM0 : OPT_XPTI_DOMU);
+    }
+
     /* initialize default tsc behavior in case tools don't */
     tsc_set_info(d, TSC_MODE_DEFAULT, 0UL, 0, 0);
     spin_lock_init(&d->arch.vtsc_lock);

xen/arch/x86/domain_build.c

@@ -1000,6 +1000,7 @@ int __init construct_dom0(
     if ( compat32 )
     {
         d->arch.is_32bit_pv = d->arch.has_32bit_shinfo = 1;
+        d->arch.pv_domain.xpti = 0;
         v->vcpu_info = (void *)&d->shared_info->compat.vcpu_info[0];
         if ( setup_compat_arg_xlat(v) != 0 )
             BUG();

xen/arch/x86/mm.c

@@ -488,8 +488,21 @@ void make_cr3(struct vcpu *v, unsigned long mfn)
 
 void write_ptbase(struct vcpu *v)
 {
-    get_cpu_info()->root_pgt_changed = 1;
-    switch_cr3(v->arch.cr3);
+    struct cpu_info *cpu_info = get_cpu_info();
+
+    if ( is_pv_vcpu(v) && v->domain->arch.pv_domain.xpti )
+    {
+        cpu_info->root_pgt_changed = 1;
+        cpu_info->pv_cr3 = __pa(this_cpu(root_pgt));
+        switch_cr3(v->arch.cr3);
+    }
+    else
+    {
+        /* Make sure to clear xen_cr3 before pv_cr3; switch_cr3() serializes. */
+        cpu_info->xen_cr3 = 0;
+        switch_cr3(v->arch.cr3);
+        cpu_info->pv_cr3 = 0;
+    }
 }
 
 /*
@@ -3912,7 +3925,7 @@ long do_mmu_update(
                 case PGT_l4_page_table:
                     rc = mod_l4_entry(va, l4e_from_intpte(req.val), mfn,
                                       cmd == MMU_PT_UPDATE_PRESERVE_AD, v);
-                    if ( !rc && this_cpu(root_pgt) )
+                    if ( !rc && pt_owner->arch.pv_domain.xpti )
                     {
                         sync_guest = 1;
                         if ( pagetable_get_pfn(curr->arch.guest_table) == mfn )

xen/arch/x86/smpboot.c

@@ -357,7 +357,7 @@ void start_secondary(void *unused)
     spin_debug_disable();
 
     get_cpu_info()->xen_cr3 = 0;
-    get_cpu_info()->pv_cr3 = this_cpu(root_pgt) ? __pa(this_cpu(root_pgt)) : 0;
+    get_cpu_info()->pv_cr3 = 0;
 
     load_system_tables();
 
@@ -779,8 +779,6 @@ static int clone_mapping(const void *ptr, root_pgentry_t *rpt)
     return 0;
 }
 
-static __read_mostly int8_t opt_xpti = -1;
-boolean_param("xpti", opt_xpti);
 DEFINE_PER_CPU(root_pgentry_t *, root_pgt);
 
 static int setup_cpu_root_pgt(unsigned int cpu)
@@ -1034,14 +1032,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 
     stack_base[0] = stack_start;
 
-    if ( opt_xpti < 0 )
-        opt_xpti = boot_cpu_data.x86_vendor != X86_VENDOR_AMD;
-
     rc = setup_cpu_root_pgt(0);
     if ( rc )
         panic("Error %d setting up PV root page table\n", rc);
     if ( per_cpu(root_pgt, 0) )
-        get_cpu_info()->pv_cr3 = __pa(per_cpu(root_pgt, 0));
+        get_cpu_info()->pv_cr3 = 0;
 
     set_nr_sockets();
 

xen/arch/x86/spec_ctrl.c

@@ -233,6 +233,10 @@ static void __init print_details(enum ind_thunk thunk, uint64_t caps)
             boot_cpu_has(X86_FEATURE_SC_RSB_HVM))    ? ""               : " None",
            boot_cpu_has(X86_FEATURE_SC_MSR_HVM)      ? " MSR_SPEC_CTRL" : "",
            boot_cpu_has(X86_FEATURE_SC_RSB_HVM)      ? " RSB"           : "");
+
+    printk("  XPTI (64-bit PV only): Dom0 %s, DomU %s\n",
+           opt_xpti & OPT_XPTI_DOM0 ? "enabled" : "disabled",
+           opt_xpti & OPT_XPTI_DOMU ? "enabled" : "disabled");
 }
 
 /* Calculate whether Retpoline is known-safe on this CPU. */
@@ -318,6 +322,63 @@ static bool_t __init __maybe_unused retpoline_safe(uint64_t caps)
     }
 }
 
+#define OPT_XPTI_DEFAULT  0xff
+uint8_t __read_mostly opt_xpti = OPT_XPTI_DEFAULT;
+
+static __init void xpti_init_default(bool_t force)
+{
+    if ( !force && (opt_xpti != OPT_XPTI_DEFAULT) )
+        return;
+
+    if ( boot_cpu_data.x86_vendor == X86_VENDOR_AMD )
+        opt_xpti = 0;
+    else
+        opt_xpti = OPT_XPTI_DOM0 | OPT_XPTI_DOMU;
+}
+
+static __init int parse_xpti(char *s)
+{
+    char *ss;
+    int val, rc = 0;
+
+    xpti_init_default(0);
+
+    do {
+        ss = strchr(s, ',');
+        if ( ss )
+            *ss = '\0';
+
+        switch ( parse_bool(s) )
+        {
+        case 0:
+            opt_xpti = 0;
+            break;
+
+        case 1:
+            opt_xpti = OPT_XPTI_DOM0 | OPT_XPTI_DOMU;
+            break;
+
+        default:
+            if ( !strcmp(s, "default") )
+                xpti_init_default(1);
+            else if ( (val = parse_boolean("dom0", s, ss)) >= 0 )
+                opt_xpti = (opt_xpti & ~OPT_XPTI_DOM0) |
+                           (val ? OPT_XPTI_DOM0 : 0);
+            else if ( (val = parse_boolean("domu", s, ss)) >= 0 )
+                opt_xpti = (opt_xpti & ~OPT_XPTI_DOMU) |
+                           (val ? OPT_XPTI_DOMU : 0);
+            else
+                rc = -EINVAL;
+            break;
+        }
+
+        s = ss + 1;
+    } while ( ss );
+
+    return rc;
+}
+custom_param("xpti", parse_xpti);
+
 void __init init_speculation_mitigations(void)
 {
     enum ind_thunk thunk = THUNK_DEFAULT;
@@ -457,6 +518,12 @@ void __init init_speculation_mitigations(void)
     if ( default_xen_spec_ctrl )
         __set_bit(X86_FEATURE_SC_MSR_IDLE, boot_cpu_data.x86_capability);
 
+    xpti_init_default(0);
+    if ( opt_xpti == 0 )
+        __set_bit(X86_FEATURE_NO_XPTI, boot_cpu_data.x86_capability);
+    else
+        setup_clear_cpu_cap(X86_FEATURE_NO_XPTI);
+
     print_details(thunk, caps);
 
     /*

xen/include/asm-x86/cpufeature.h

@@ -78,6 +78,7 @@
 #define X86_FEATURE_CPUID_FAULTING (3*32+14) /* cpuid faulting */
 #define X86_FEATURE_CLFLUSH_MONITOR (3*32+15) /* clflush reqd with monitor */
 #define X86_FEATURE_SC_MSR_IDLE     (3*32+16) /* (SC_MSR_PV || SC_MSR_HVM) && default_xen_spec_ctrl */
+#define X86_FEATURE_NO_XPTI         (3*32+17) /* XPTI mitigation not in use */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* Streaming SIMD Extensions-3 */

xen/include/asm-x86/current.h

@@ -45,7 +45,8 @@ struct cpu_info {
     /*
      * Of the two following fields the latter is being set to the CR3 value
      * to be used on the given pCPU for loading whenever 64-bit PV guest
-     * context is being entered. The value never changes once set.
+     * context is being entered. A value of zero indicates no setting of CR3
+     * is to be performed.
      * The former is the value to restore when re-entering Xen, if any. IOW
      * its value being zero means there's nothing to restore. However, its
      * value can also be negative, indicating to the exit-to-Xen code that

xen/include/asm-x86/domain.h

@@ -252,6 +252,9 @@ struct pv_domain
 
     atomic_t nr_l4_pages;
 
+    /* XPTI active? */
+    bool_t xpti;
+
     /* map_domain_page() mapping cache. */
     struct mapcache_domain mapcache;
 };

xen/include/asm-x86/flushtlb.h

@@ -136,7 +136,7 @@ void flush_area_mask(const cpumask_t *, const void *va, unsigned int flags);
 
 #define flush_root_pgtbl_domain(d)                                       \
 {                                                                        \
-    if ( this_cpu(root_pgt) && is_pv_domain(d) && !is_pv_32bit_domain(d) ) \
+    if ( is_pv_domain(d) && (d)->arch.pv_domain.xpti )                   \
         flush_mask((d)->domain_dirty_cpumask, FLUSH_ROOT_PGTBL);         \
 }
 

xen/include/asm-x86/spec_ctrl.h

@@ -33,6 +33,10 @@ extern bool_t bsp_delay_spec_ctrl;
 extern uint8_t default_xen_spec_ctrl;
 extern uint8_t default_spec_ctrl_flags;
 
+extern uint8_t opt_xpti;
+#define OPT_XPTI_DOM0  0x01
+#define OPT_XPTI_DOMU  0x02
+
 static inline void init_shadow_spec_ctrl_state(void)
 {
     struct cpu_info *info = get_cpu_info();