[PATCH v2 2/3] x86/spec-ctrl: Fix up the RSBA/RRSBA bits as appropriate

[Andrew Cooper <andrew.cooper3@xxxxxxxxxx>]

In order to level a VM safely for migration, the toolstack needs to know the
RSBA/RRSBA properties of the CPU, whether or not they happen to be enumerated.

See the code comment for details.

Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
---
CC: Jan Beulich <JBeulich@xxxxxxxx>
CC: Roger Pau Monné <roger.pau@xxxxxxxxxx>
CC: Wei Liu <wl@xxxxxxx>

v2:
 * Rewrite almost from scratch.
---
 xen/arch/x86/include/asm/cpufeature.h |  1 +
 xen/arch/x86/spec_ctrl.c              | 92 +++++++++++++++++++++++++--
 2 files changed, 88 insertions(+), 5 deletions(-)

diff --git a/xen/arch/x86/include/asm/cpufeature.h 
b/xen/arch/x86/include/asm/cpufeature.h
index ace31e3b1f1a..e2cb8f3cc728 100644
--- a/xen/arch/x86/include/asm/cpufeature.h
+++ b/xen/arch/x86/include/asm/cpufeature.h
@@ -193,6 +193,7 @@ static inline bool boot_cpu_has(unsigned int feat)
 #define cpu_has_tsx_ctrl        boot_cpu_has(X86_FEATURE_TSX_CTRL)
 #define cpu_has_taa_no          boot_cpu_has(X86_FEATURE_TAA_NO)
 #define cpu_has_fb_clear        boot_cpu_has(X86_FEATURE_FB_CLEAR)
+#define cpu_has_rrsba           boot_cpu_has(X86_FEATURE_RRSBA)
 
 /* Synthesized. */
 #define cpu_has_arch_perfmon    boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c
index daee61900afa..29ed410da47a 100644
--- a/xen/arch/x86/spec_ctrl.c
+++ b/xen/arch/x86/spec_ctrl.c
@@ -579,7 +579,10 @@ static bool __init check_smt_enabled(void)
     return false;
 }
 
-/* Calculate whether Retpoline is known-safe on this CPU. */
+/*
+ * Calculate whether Retpoline is known-safe on this CPU.  Fix up the
+ * RSBA/RRSBA bits as necessary.
+ */
 static bool __init retpoline_calculations(void)
 {
     unsigned int ucode_rev = this_cpu(cpu_sig).rev;
@@ -593,15 +596,85 @@ static bool __init retpoline_calculations(void)
         return false;
 
     /*
-     * RSBA may be set by a hypervisor to indicate that we may move to a
-     * processor which isn't retpoline-safe.
+     * The meaning of the RSBA and RRSBA bits have evolved over time.  The
+     * agreed upon meaning at the time of writing (May 2023) is thus:
+     *
+     * - RSBA (RSB Alternative) means that an RSB may fall back to an
+     *   alternative predictor on underflow.  Skylake uarch and later all have
+     *   this property.  Broadwell too, when running microcode versions prior
+     *   to Jan 2018.
+     *
+     * - All eIBRS-capable processors suffer RSBA, but eIBRS also introduces
+     *   tagging of predictions with the mode in which they were learned.  So
+     *   when eIBRS is active, RSBA becomes RRSBA (Restricted RSBA).
+     *
+     * - CPUs are not expected to enumerate both RSBA and RRSBA.
+     *
+     * Some parts (Broadwell) are not expected to ever enumerate this
+     * behaviour directly.  Other parts have differing enumeration with
+     * microcode version.  Fix up Xen's idea, so we can advertise them safely
+     * to guests, and so toolstacks can level a VM safety for migration.
+     *
+     * The following states exist:
+     *
+     * |   | RSBA | EIBRS | RRSBA | Notes              | Action        |
+     * |---+------+-------+-------+--------------------+---------------|
+     * | 1 |    0 |     0 |     0 | OK (older parts)   | Maybe +RSBA   |
+     * | 2 |    0 |     0 |     1 | Broken             | +RSBA, -RRSBA |
+     * | 3 |    0 |     1 |     0 | OK (pre-Aug ucode) | +RRSBA        |
+     * | 4 |    0 |     1 |     1 | OK                 |               |
+     * | 5 |    1 |     0 |     0 | OK                 |               |
+     * | 6 |    1 |     0 |     1 | Broken             | -RRSBA        |
+     * | 7 |    1 |     1 |     0 | Broken             | -RSBA, +RRSBA |
+     * | 8 |    1 |     1 |     1 | Broken             | -RSBA         |
      *
+     * However, we doesn't need perfect adherence to the spec.  Identify the
+     * broken cases (so we stand a chance of spotting violated assumptions),
+     * and fix up Rows 1 and 3 so Xen can use RSBA || RRSBA to identify
+     * "alternative predictors potentially in use".
+     */
+    if ( cpu_has_eibrs ? cpu_has_rsba  /* Rows 7, 8 */
+                       : cpu_has_rrsba /* Rows 2, 6 */ )
+        printk(XENLOG_ERR
+               "FIRMWARE BUG: CPU %02x-%02x-%02x, ucode 0x%08x: RSBA %u, EIBRS 
%u, RRSBA %u\n",
+               boot_cpu_data.x86, boot_cpu_data.x86_model,
+               boot_cpu_data.x86_mask, ucode_rev,
+               cpu_has_rsba, cpu_has_eibrs, cpu_has_rrsba);
+
+    /*
      * Processors offering Enhanced IBRS are not guarenteed to be
      * repoline-safe.
      */
-    if ( cpu_has_rsba || cpu_has_eibrs )
+    if ( cpu_has_eibrs )
+    {
+        /*
+         * Prior to the August 2023 microcode, many eIBRS-capable parts did
+         * not enumerate RRSBA.
+         */
+        if ( !cpu_has_rrsba )
+            setup_force_cpu_cap(X86_FEATURE_RRSBA);
+
+        return false;
+    }
+
+    /*
+     * RSBA is explicitly enumerated in some cases, but may also be set by a
+     * hypervisor to indicate that we may move to a processor which isn't
+     * retpoline-safe.
+     */
+    if ( cpu_has_rsba )
         return false;
 
+    /*
+     * At this point, we've filtered all the legal RSBA || RRSBA cases (or the
+     * known non-ideal cases).  If ARCH_CAPS is visible, trust the absence of
+     * RSBA || RRSBA.  There's no known microcode which advertises ARCH_CAPS
+     * without RSBA or EIBRS, and if we're virtualised we can't rely the model
+     * check anyway.
+     */
+    if ( cpu_has_arch_caps )
+        return true;
+
     switch ( boot_cpu_data.x86_model )
     {
     case 0x17: /* Penryn */
@@ -689,6 +762,15 @@ static bool __init retpoline_calculations(void)
         break;
     }
 
+    if ( !safe )
+    {
+        /*
+         * Note: the eIBRS-capable parts are filtered out earlier, so the
+         * remainder here are the ones which suffer only RSBA behaviour.
+         */
+        setup_force_cpu_cap(X86_FEATURE_RSBA);
+    }
+
     return safe;
 }
 
@@ -1148,7 +1230,7 @@ void __init init_speculation_mitigations(void)
             thunk = THUNK_JMP;
     }
 
-    /* Determine if retpoline is safe on this CPU. */
+    /* Determine if retpoline is safe on this CPU.  Fix up RSBA/RRSBA 
enumerations. */
     retpoline_safe = retpoline_calculations();
 
     /*
-- 
2.30.2