x86/cpu-policy: Derive RSBA/RRSBA for guest policies

The RSBA bit, "RSB Alternative", means that the RSB may use alternative
predictors when empty.  From a practical point of view, this mean "Retpoline
not safe".

Enhanced IBRS (officially IBRS_ALL in Intel's docs, previously IBRS_ATT) is a
statement that IBRS is implemented in hardware (as opposed to the form
retrofitted to existing CPUs in microcode).

The RRSBA bit, "Restricted-RSBA", is a combination of RSBA, and the eIBRS
property that predictions are tagged with the mode in which they were learnt.
Therefore, it means "when eIBRS is active, the RSB may fall back to
alternative predictors but restricted to the current prediction mode".  As
such, it's stronger statement than RSBA, but still means "Retpoline not safe".

CPUs are not expected to enumerate both RSBA and RRSBA.

Add feature dependencies for EIBRS and RRSBA.  While technically they're not
linked, absolutely nothing good can come of letting the guest see RRSBA
without EIBRS.  Nor a guest seeing EIBRS without IBRSB.  Furthermore, we use
this dependency to simplify the max derivation logic.

The max policies gets RSBA and RRSBA unconditionally set (with the EIBRS
dependency maybe hiding RRSBA).  We can run any VM, even if it has been told
"somewhere you might run, Retpoline isn't safe".

The default policies are more complicated.  A guest shouldn't see both bits,
but it needs to see one if the current host suffers from any form of RSBA, and
which bit it needs to see depends on whether eIBRS is visible or not.
Therefore, the calculation must be performed after sanitise_featureset().

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>

diff --git a/xen/arch/x86/cpu-policy.c b/xen/arch/x86/cpu-policy.c
index ee256ff5a13760ec3da4483b30650ec4cf88f7d6..f40eeb8be8dcbf2fe59ef08d76b71cbc13be8404 100644 (file)
--- a/xen/arch/x86/cpu-policy.c
+++ b/xen/arch/x86/cpu-policy.c
@@ -423,8 +423,17 @@ static void __init guest_common_max_feature_adjustments(uint32_t *fs)
          * Retpoline not safe)", so these need to be visible to a guest in all
          * cases, even when it's only some other server in the pool which
          * suffers the identified behaviour.
+         *
+         * We can always run any VM which has previously (or will
+         * subsequently) run on hardware where Retpoline is not safe.
+         * Note:
+         *  - The dependency logic may hide RRSBA for other reasons.
+         *  - The max policy does not constitute a sensible configuration to
+         *    run a guest in.
          */
         __set_bit(X86_FEATURE_ARCH_CAPS, fs);
+        __set_bit(X86_FEATURE_RSBA, fs);
+        __set_bit(X86_FEATURE_RRSBA, fs);
     }
 }
 
@@ -532,6 +541,21 @@ static void __init calculate_pv_def_policy(void)
     guest_common_default_feature_adjustments(fs);
 
     sanitise_featureset(fs);
+
+    /*
+     * If the host suffers from RSBA of any form, and the guest can see
+     * MSR_ARCH_CAPS, reflect the appropriate RSBA/RRSBA property to the guest
+     * depending on the visibility of eIBRS.
+     */
+    if ( test_bit(X86_FEATURE_ARCH_CAPS, fs) &&
+         (cpu_has_rsba || cpu_has_rrsba) )
+    {
+        bool eibrs = test_bit(X86_FEATURE_EIBRS, fs);
+
+        __set_bit(eibrs ? X86_FEATURE_RRSBA
+                        : X86_FEATURE_RSBA, fs);
+    }
+
     x86_cpu_featureset_to_policy(fs, p);
     recalculate_xstate(p);
 }
@@ -664,6 +688,21 @@ static void __init calculate_hvm_def_policy(void)
         __set_bit(X86_FEATURE_VIRT_SSBD, fs);
 
     sanitise_featureset(fs);
+
+    /*
+     * If the host suffers from RSBA of any form, and the guest can see
+     * MSR_ARCH_CAPS, reflect the appropriate RSBA/RRSBA property to the guest
+     * depending on the visibility of eIBRS.
+     */
+    if ( test_bit(X86_FEATURE_ARCH_CAPS, fs) &&
+         (cpu_has_rsba || cpu_has_rrsba) )
+    {
+        bool eibrs = test_bit(X86_FEATURE_EIBRS, fs);
+
+        __set_bit(eibrs ? X86_FEATURE_RRSBA
+                        : X86_FEATURE_RSBA, fs);
+    }
+
     x86_cpu_featureset_to_policy(fs, p);
     recalculate_xstate(p);
 }

diff --git a/xen/include/public/arch-x86/cpufeatureset.h b/xen/include/public/arch-x86/cpufeatureset.h
index ea779c29879e226558f228f59af7ee0a0e351373..ce7407d6a10c852e95bbcfccd3230b2862e2c32f 100644 (file)
--- a/xen/include/public/arch-x86/cpufeatureset.h
+++ b/xen/include/public/arch-x86/cpufeatureset.h
@@ -311,7 +311,7 @@ XEN_CPUFEATURE(CET_SSS,            15*32+18) /*   CET Supervisor Shadow Stacks s
 /* Intel-defined CPU features, MSR_ARCH_CAPS 0x10a.eax, word 16 */
 XEN_CPUFEATURE(RDCL_NO,            16*32+ 0) /*A  No Rogue Data Cache Load (Meltdown) */
 XEN_CPUFEATURE(EIBRS,              16*32+ 1) /*A  Enhanced IBRS */
-XEN_CPUFEATURE(RSBA,               16*32+ 2) /*!A RSB Alternative (Retpoline not safe) */
+XEN_CPUFEATURE(RSBA,               16*32+ 2) /*!  RSB Alternative (Retpoline not safe) */
 XEN_CPUFEATURE(SKIP_L1DFL,         16*32+ 3) /*   Don't need to flush L1D on VMEntry */
 XEN_CPUFEATURE(INTEL_SSB_NO,       16*32+ 4) /*A  No Speculative Store Bypass */
 XEN_CPUFEATURE(MDS_NO,             16*32+ 5) /*A  No Microarchitectural Data Sampling */
@@ -327,7 +327,7 @@ XEN_CPUFEATURE(FBSDP_NO,           16*32+14) /*A  No Fill Buffer Stale Data Prop
 XEN_CPUFEATURE(PSDP_NO,            16*32+15) /*A  No Primary Stale Data Propagation */
 XEN_CPUFEATURE(FB_CLEAR,           16*32+17) /*A  Fill Buffers cleared by VERW */
 XEN_CPUFEATURE(FB_CLEAR_CTRL,      16*32+18) /*   MSR_OPT_CPU_CTRL.FB_CLEAR_DIS */
-XEN_CPUFEATURE(RRSBA,              16*32+19) /*!A Restricted RSB Alternative */
+XEN_CPUFEATURE(RRSBA,              16*32+19) /*!  Restricted RSB Alternative */
 XEN_CPUFEATURE(BHI_NO,             16*32+20) /*A  No Branch History Injection  */
 XEN_CPUFEATURE(XAPIC_STATUS,       16*32+21) /*   MSR_XAPIC_DISABLE_STATUS */
 XEN_CPUFEATURE(OVRCLK_STATUS,      16*32+23) /*   MSR_OVERCLOCKING_STATUS */

diff --git a/xen/tools/gen-cpuid.py b/xen/tools/gen-cpuid.py
index 973fcc1c64e83109c5d3a569d0c8cb196cff6ad3..72cf11654ba9a35a6b3df86e9e23165be61f6359 100755 (executable)
--- a/xen/tools/gen-cpuid.py
+++ b/xen/tools/gen-cpuid.py
@@ -318,7 +318,7 @@ def crunch_numbers(state):
         # IBRSB/IBRS, and we pass this MSR directly to guests.  Treating them
         # as dependent features simplifies Xen's logic, and prevents the guest
         # from seeing implausible configurations.
-        IBRSB: [STIBP, SSBD, INTEL_PSFD],
+        IBRSB: [STIBP, SSBD, INTEL_PSFD, EIBRS],
         IBRS: [AMD_STIBP, AMD_SSBD, PSFD, AUTO_IBRS,
                IBRS_ALWAYS, IBRS_FAST, IBRS_SAME_MODE],
         AMD_STIBP: [STIBP_ALWAYS],
@@ -328,6 +328,9 @@ def crunch_numbers(state):
 
         # The ARCH_CAPS CPUID bit enumerates the availability of the whole register.
         ARCH_CAPS: list(range(RDCL_NO, RDCL_NO + 64)),
+
+        # The behaviour described by RRSBA depend on eIBRS being active.
+        EIBRS: [RRSBA],
     }
 
     deep_features = tuple(sorted(deps.keys()))