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

[Xen-changelog] [xen staging-4.7] xen/x86: support per-domain flag for xpti



commit 53c6a024699165314a02fde4f427148cda8546fb
Author:     Juergen Gross <jgross@xxxxxxxx>
AuthorDate: Thu Apr 26 13:33:12 2018 +0200
Commit:     Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Tue May 29 10:43:44 2018 +0200

    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.
    
    Move the xpti boot parameter handling to xen/arch/x86/pv/domain.c as
    it is pv-domain specific.
    
    Signed-off-by: Juergen Gross <jgross@xxxxxxxx>
    Reviewed-by: Jan Beulich <jbeulich@xxxxxxxx>
---
 docs/misc/xen-command-line.markdown | 14 ++++++-
 xen/arch/x86/domain.c               |  7 ++++
 xen/arch/x86/domain_build.c         |  1 +
 xen/arch/x86/mm.c                   | 17 ++++++++-
 xen/arch/x86/setup.c                | 19 ----------
 xen/arch/x86/smpboot.c              |  4 +-
 xen/arch/x86/spec_ctrl.c            | 75 ++++++++++++++++++++++++++++++++++++-
 xen/include/asm-x86/current.h       |  3 +-
 xen/include/asm-x86/domain.h        |  3 ++
 xen/include/asm-x86/flushtlb.h      |  2 +-
 xen/include/asm-x86/spec_ctrl.h     |  4 ++
 11 files changed, 120 insertions(+), 29 deletions(-)

diff --git a/docs/misc/xen-command-line.markdown 
b/docs/misc/xen-command-line.markdown
index b4e009c7ce..843b3e82ba 100644
--- a/docs/misc/xen-command-line.markdown
+++ b/docs/misc/xen-command-line.markdown
@@ -1717,14 +1717,24 @@ 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.
+
 ### xsave
 > `= <boolean>`
 
diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index aa81f9e1f2..bb421435c4 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -394,6 +394,8 @@ int switch_compat(struct domain *d)
 
     d->arch.x87_fip_width = 4;
 
+    d->arch.pv_domain.xpti = 0;
+
     return 0;
 
  undo_and_fail:
@@ -667,9 +669,14 @@ 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);
diff --git a/xen/arch/x86/domain_build.c b/xen/arch/x86/domain_build.c
index d449535891..cdb7b66617 100644
--- a/xen/arch/x86/domain_build.c
+++ b/xen/arch/x86/domain_build.c
@@ -1001,6 +1001,7 @@ 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();
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 12adc1e1b4..54f7351644 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -499,8 +499,21 @@ 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;
+    }
 }
 
 /*
diff --git a/xen/arch/x86/setup.c b/xen/arch/x86/setup.c
index 0ad69d02bb..6ce807bf6d 100644
--- a/xen/arch/x86/setup.c
+++ b/xen/arch/x86/setup.c
@@ -112,9 +112,6 @@ struct cpuinfo_x86 __read_mostly boot_cpu_data = { 0, 0, 0, 
0, -1 };
 
 unsigned long __read_mostly mmu_cr4_features = XEN_MINIMAL_CR4;
 
-static int8_t __initdata opt_xpti = -1;
-boolean_param("xpti", opt_xpti);
-
 bool_t __read_mostly acpi_disabled;
 bool_t __initdata acpi_force;
 static char __initdata acpi_param[10] = "";
@@ -1424,22 +1421,6 @@ void __init noreturn __start_xen(unsigned long mbi_p)
 
     cr4_pv32_mask = mmu_cr4_features & XEN_CR4_PV32_BITS;
 
-    if ( opt_xpti < 0 )
-    {
-        uint64_t caps = 0;
-
-        if ( boot_cpu_data.x86_vendor == X86_VENDOR_AMD )
-            caps = ARCH_CAPABILITIES_RDCL_NO;
-        else if ( boot_cpu_has(X86_FEATURE_ARCH_CAPS) )
-            rdmsrl(MSR_ARCH_CAPABILITIES, caps);
-
-        opt_xpti = !(caps & ARCH_CAPABILITIES_RDCL_NO);
-    }
-    if ( opt_xpti )
-        setup_clear_cpu_cap(X86_FEATURE_NO_XPTI);
-    else
-        __set_bit(X86_FEATURE_NO_XPTI, boot_cpu_data.x86_capability);
-
     if ( cpu_has_fsgsbase )
         set_in_cr4(X86_CR4_FSGSBASE);
 
diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c
index bb3b1eccb7..9caba91b7d 100644
--- a/xen/arch/x86/smpboot.c
+++ b/xen/arch/x86/smpboot.c
@@ -322,7 +322,7 @@ 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();
 
@@ -1047,7 +1047,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
         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;
 
         /*
          * All entry points which may need to switch page tables have to start
diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c
index e2a3fdb561..d8528e30c5 100644
--- a/xen/arch/x86/spec_ctrl.c
+++ b/xen/arch/x86/spec_ctrl.c
@@ -233,8 +233,9 @@ static void __init print_details(enum ind_thunk thunk, 
uint64_t caps)
            boot_cpu_has(X86_FEATURE_SC_MSR_HVM)      ? " MSR_SPEC_CTRL" : "",
            boot_cpu_has(X86_FEATURE_SC_RSB_HVM)      ? " RSB"           : "");
 
-    printk("XPTI: %s\n",
-           boot_cpu_has(X86_FEATURE_NO_XPTI) ? "disabled" : "enabled");
+    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. */
@@ -320,6 +321,70 @@ static bool_t __init 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)
+{
+    uint64_t caps = 0;
+
+    if ( !force && (opt_xpti != OPT_XPTI_DEFAULT) )
+        return;
+
+    if ( boot_cpu_data.x86_vendor == X86_VENDOR_AMD )
+        caps = ARCH_CAPABILITIES_RDCL_NO;
+    else if ( boot_cpu_has(X86_FEATURE_ARCH_CAPS) )
+        rdmsrl(MSR_ARCH_CAPABILITIES, caps);
+
+    if ( caps & ARCH_CAPABILITIES_RDCL_NO )
+        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;
@@ -461,6 +526,12 @@ 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);
 
     /*
diff --git a/xen/include/asm-x86/current.h b/xen/include/asm-x86/current.h
index e4c6b0224a..7baa737c7c 100644
--- a/xen/include/asm-x86/current.h
+++ b/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
diff --git a/xen/include/asm-x86/domain.h b/xen/include/asm-x86/domain.h
index af80e7d172..c495c119e1 100644
--- a/xen/include/asm-x86/domain.h
+++ b/xen/include/asm-x86/domain.h
@@ -257,6 +257,9 @@ struct pv_domain
 
     atomic_t nr_l4_pages;
 
+    /* XPTI active? */
+    bool_t xpti;
+
     /* map_domain_page() mapping cache. */
     struct mapcache_domain mapcache;
 
diff --git a/xen/include/asm-x86/flushtlb.h b/xen/include/asm-x86/flushtlb.h
index ab855f9393..9b73eb7c80 100644
--- a/xen/include/asm-x86/flushtlb.h
+++ b/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 ( !cpu_has_no_xpti && 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);         \
 }
 
diff --git a/xen/include/asm-x86/spec_ctrl.h b/xen/include/asm-x86/spec_ctrl.h
index dd084d2d4d..45ac200f11 100644
--- a/xen/include/asm-x86/spec_ctrl.h
+++ b/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();
--
generated by git-patchbot for /home/xen/git/xen.git#staging-4.7

_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/xen-changelog

 


Rackspace

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