x86/cpuid: support LFENCE always serialising CPUID bit

AMD Milan (Zen3) CPUs have an LFENCE Always Serialising CPUID bit in
leaf 80000021.eax. Previous AMD versions used to have a user settable
bit in DE_CFG MSR to select whether LFENCE was dispatch serialising,
which Xen always attempts to set. The forcefully always on setting is
due to the addition of SEV-SNP so that a VMM cannot break the
confidentiality of a guest.

In order to support this new CPUID bit move the LFENCE_DISPATCH
synthetic CPUID bit to map the hardware bit (leaving a hole in the
synthetic range) and either rely on the bit already being set by the
native CPUID output, or attempt to fake it in Xen by modifying the
DE_CFG MSR. This requires adding one more entry to the featureset to
support leaf 80000021.eax.

The bit is always exposed to guests by default even if the underlying
hardware doesn't support leaf 80000021. Note that Xen doesn't allow
guests to change the DE_CFG value, so once set by Xen LFENCE will always
be serialising.

Note that the access to DE_CFG by guests is left as-is: reads will
unconditionally return LFENCE_SERIALISE bit set, while writes are
silently dropped.

Suggested-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
[Always expose to guests by default]
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
(cherry picked from commit e9b4fe2)

x86/cpuid: do not expand max leaves on restore

When restoring limit the maximum leaves to the ones supported by Xen
4.12 in order to not expand the maximum leaves a guests sees. Note
this is unlikely to cause real issues.

Guests restored from Xen versions 4.13 or greater will contain CPUID
data on the stream that will override the values set by
xc_cpuid_apply_policy.

Fixes: e9b4fe2 ("x86/cpuid: support LFENCE always serialising CPUID bit")
Reported-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
(cherry picked from commit 111c8c3)

tools/libxenguest: Fix max_extd_leaf calculation for legacy restore

0x1c is lower than any value which will actually be observed in
p->extd.max_leaf, but higher than the logical 9 leaves worth of extended data
on Intel systems, causing x86_cpuid_copy_to_buffer() to fail with -ENOBUFS.

Correct the calculation.

The problem was first noticed in c/s 3499044 "libxl: don't ignore the
return value from xc_cpuid_apply_policy" but introduced earlier.

Fixes: 111c8c3 ("x86/cpuid: do not expand max leaves on restore")
Reported-by: Olaf Hering <olaf@aepfle.de>
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
(cherry picked from commit 5fa174c)

tools/guest: Fix comment regarding CPUID compatibility

It was Xen 4.14 where CPUID data was added to the migration stream, and 4.13
that we need to worry about with regards to compatibility.  Xen 4.12 isn't
relevant.

Expand and correct the commentary.

Fixes: 111c8c3 ("x86/cpuid: do not expand max leaves on restore")
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
(cherry picked from commit 820cc39)

tools/libxc/xc_cpuid_x86.c

@@ -497,12 +497,22 @@ int xc_cpuid_apply_policy(xc_interface *xch, uint32_t domid, bool restore,
         goto out;
     }
 
-    /*
-     * Account for feature which have been disabled by default since Xen 4.13,
-     * so migrated-in VM's don't risk seeing features disappearing.
-     */
     if ( restore )
     {
+        /*
+         * Xen 4.14 introduced support to move the guest's CPUID data in the
+         * migration stream.  Previously, the destination side would invent a
+         * policy out of thin air in the hopes that it was ok.
+         *
+         * This restore path is used for incoming VMs with no CPUID data
+         * i.e. originated on Xen 4.13 or earlier.  We must invent a policy
+         * compatible with what Xen 4.13 would have done on the same hardware.
+         *
+         * Specifically:
+         * - Clamp max leaves.
+         * - Re-enable features which have become (possibly) off by default.
+         */
+
         p->basic.rdrand = test_bit(X86_FEATURE_RDRAND, host_featureset);
         p->feat.hle = test_bit(X86_FEATURE_HLE, host_featureset);
         p->feat.rtm = test_bit(X86_FEATURE_RTM, host_featureset);
@@ -511,6 +521,10 @@ int xc_cpuid_apply_policy(xc_interface *xch, uint32_t domid, bool restore,
         {
             p->feat.mpx = test_bit(X86_FEATURE_MPX, host_featureset);
         }
+
+        p->basic.max_leaf = min(p->basic.max_leaf, 0xdu);
+        p->feat.max_subleaf = 0;
+        p->extd.max_leaf = min(p->extd.max_leaf, 0x8000001c);
     }
 
     if ( featureset )

tools/libxl/libxl_cpuid.c

@@ -290,6 +290,8 @@ int libxl_cpuid_parse_config(libxl_cpuid_policy_list *cpuid, const char* str)
         {"svm_decode",   0x8000000a, NA, CPUID_REG_EDX,  7,  1},
         {"svm_pausefilt",0x8000000a, NA, CPUID_REG_EDX, 10,  1},
 
+        {"lfence+",      0x80000021, NA, CPUID_REG_EAX,  2,  1},
+
         {"maxhvleaf",    0x40000000, NA, CPUID_REG_EAX,  0,  8},
 
         {NULL, 0, NA, CPUID_REG_INV, 0, 0}

tools/misc/xen-cpuid.c

@@ -183,6 +183,11 @@ static const char *const str_7a1[32] =
     /* 4 */                 [ 5] = "avx512_bf16",
 };
 
+static const char *const str_e21a[32] =
+{
+    [ 2] = "lfence+",
+};
+
 static const struct {
     const char *name;
     const char *abbr;
@@ -200,6 +205,7 @@ static const struct {
     { "0x80000008.ebx",   "e8b", str_e8b },
     { "0x00000007:0.edx", "7d0", str_7d0 },
     { "0x00000007:1.eax", "7a1", str_7a1 },
+    { "0x80000021.eax",  "e21a", str_e21a },
 };
 
 #define COL_ALIGN "18"

xen/arch/x86/cpu/amd.c

@@ -646,6 +646,13 @@ void amd_init_lfence(struct cpuinfo_x86 *c)
 {
 	uint64_t value;
 
+	/*
+	 * Some hardware has LFENCE dispatch serialising always enabled,
+	 * nothing to do on that case.
+	 */
+	if (test_bit(X86_FEATURE_LFENCE_DISPATCH, c->x86_capability))
+		return;
+
 	/*
 	 * Attempt to set lfence to be Dispatch Serialising.  This MSR almost
 	 * certainly isn't virtualised (and Xen at least will leak the real

xen/arch/x86/cpu/common.c

@@ -419,6 +419,9 @@ static void generic_identify(struct cpuinfo_x86 *c)
 	if (c->extended_cpuid_level >= 0x80000008)
 		c->x86_capability[cpufeat_word(X86_FEATURE_CLZERO)]
 			= cpuid_ebx(0x80000008);
+	if (c->extended_cpuid_level >= 0x80000021)
+		c->x86_capability[cpufeat_word(X86_FEATURE_LFENCE_DISPATCH)]
+			= cpuid_eax(0x80000021);
 
 	/* Intel-defined flags: level 0x00000007 */
 	if ( c->cpuid_level >= 0x00000007 ) {

xen/arch/x86/cpuid.c

@@ -308,14 +308,27 @@ static void __init calculate_raw_policy(void)
 static void __init calculate_host_policy(void)
 {
     struct cpuid_policy *p = &host_cpuid_policy;
+    unsigned int max_extd_leaf;
 
     *p = raw_cpuid_policy;
 
     p->basic.max_leaf =
         min_t(uint32_t, p->basic.max_leaf,   ARRAY_SIZE(p->basic.raw) - 1);
     p->feat.max_subleaf =
         min_t(uint32_t, p->feat.max_subleaf, ARRAY_SIZE(p->feat.raw) - 1);
-    p->extd.max_leaf = 0x80000000 | min_t(uint32_t, p->extd.max_leaf & 0xffff,
+
+    max_extd_leaf = p->extd.max_leaf;
+
+    /*
+     * For AMD/Hygon hardware before Zen3, we unilaterally modify LFENCE to be
+     * dispatch serialising for Spectre mitigations.  Extend max_extd_leaf
+     * beyond what hardware supports, to include the feature leaf containing
+     * this information.
+     */
+    if ( cpu_has_lfence_dispatch )
+        max_extd_leaf = max(max_extd_leaf, 0x80000021);
+
+    p->extd.max_leaf = 0x80000000 | min_t(uint32_t, max_extd_leaf & 0xffff,
                                           ARRAY_SIZE(p->extd.raw) - 1);
 
     cpuid_featureset_to_policy(boot_cpu_data.x86_capability, p);

xen/include/asm-x86/cpufeatures.h

@@ -24,7 +24,7 @@ XEN_CPUFEATURE(APERFMPERF,        X86_SYNTH( 8)) /* APERFMPERF */
 XEN_CPUFEATURE(MFENCE_RDTSC,      X86_SYNTH( 9)) /* MFENCE synchronizes RDTSC */
 XEN_CPUFEATURE(XEN_SMEP,          X86_SYNTH(10)) /* SMEP gets used by Xen itself */
 XEN_CPUFEATURE(XEN_SMAP,          X86_SYNTH(11)) /* SMAP gets used by Xen itself */
-XEN_CPUFEATURE(LFENCE_DISPATCH,   X86_SYNTH(12)) /* lfence set as Dispatch Serialising */
+/* Bit 12 - unused. */
 XEN_CPUFEATURE(IND_THUNK_LFENCE,  X86_SYNTH(13)) /* Use IND_THUNK_LFENCE */
 XEN_CPUFEATURE(IND_THUNK_JMP,     X86_SYNTH(14)) /* Use IND_THUNK_JMP */
 XEN_CPUFEATURE(SC_BRANCH_HARDEN,  X86_SYNTH(15)) /* Conditional Branch Hardening */

xen/include/public/arch-x86/cpufeatureset.h

@@ -285,6 +285,9 @@ XEN_CPUFEATURE(SSBD,          9*32+31) /*A  MSR_SPEC_CTRL.SSBD available */
 /* Intel-defined CPU features, CPUID level 0x00000007:1.eax, word 10 */
 XEN_CPUFEATURE(AVX512_BF16,  10*32+ 5) /*A  AVX512 BFloat16 Instructions */
 
+/* AMD-defined CPU features, CPUID level 0x80000021.eax, word 11 */
+XEN_CPUFEATURE(LFENCE_DISPATCH,    11*32+ 2) /*A  LFENCE always serializing */
+
 #endif /* XEN_CPUFEATURE */
 
 /* Clean up from a default include.  Close the enum (for C). */

xen/include/xen/lib/x86/cpuid.h

@@ -15,6 +15,7 @@
 #define FEATURESET_e8b    8 /* 0x80000008.ebx      */
 #define FEATURESET_7d0    9 /* 0x00000007:0.edx    */
 #define FEATURESET_7a1   10 /* 0x00000007:1.eax    */
+#define FEATURESET_e21a  11 /* 0x80000021.eax      */
 
 struct cpuid_leaf
 {
@@ -84,7 +85,7 @@ const char *x86_cpuid_vendor_to_str(unsigned int vendor);
 #define CPUID_GUEST_NR_TOPO       (1u + 1)
 #define CPUID_GUEST_NR_XSTATE     (62u + 1)
 #define CPUID_GUEST_NR_EXTD_INTEL (0x8u + 1)
-#define CPUID_GUEST_NR_EXTD_AMD   (0x1cu + 1)
+#define CPUID_GUEST_NR_EXTD_AMD   (0x21u + 1)
 #define CPUID_GUEST_NR_EXTD       MAX(CPUID_GUEST_NR_EXTD_INTEL, \
                                       CPUID_GUEST_NR_EXTD_AMD)
 
@@ -264,6 +265,38 @@ struct cpuid_policy
             };
             uint32_t nc:8, :4, apic_id_size:4, :16;
             uint32_t /* d */:32;
+
+            uint64_t :64, :64; /* Leaf 0x80000009. */
+            uint64_t :64, :64; /* Leaf 0x8000000a - SVM rev and features. */
+            uint64_t :64, :64; /* Leaf 0x8000000b. */
+            uint64_t :64, :64; /* Leaf 0x8000000c. */
+            uint64_t :64, :64; /* Leaf 0x8000000d. */
+            uint64_t :64, :64; /* Leaf 0x8000000e. */
+            uint64_t :64, :64; /* Leaf 0x8000000f. */
+            uint64_t :64, :64; /* Leaf 0x80000010. */
+            uint64_t :64, :64; /* Leaf 0x80000011. */
+            uint64_t :64, :64; /* Leaf 0x80000012. */
+            uint64_t :64, :64; /* Leaf 0x80000013. */
+            uint64_t :64, :64; /* Leaf 0x80000014. */
+            uint64_t :64, :64; /* Leaf 0x80000015. */
+            uint64_t :64, :64; /* Leaf 0x80000016. */
+            uint64_t :64, :64; /* Leaf 0x80000017. */
+            uint64_t :64, :64; /* Leaf 0x80000018. */
+            uint64_t :64, :64; /* Leaf 0x80000019 - TLB 1GB Identifiers. */
+            uint64_t :64, :64; /* Leaf 0x8000001a - Performance related info. */
+            uint64_t :64, :64; /* Leaf 0x8000001b - IBS feature information. */
+            uint64_t :64, :64; /* Leaf 0x8000001c. */
+            uint64_t :64, :64; /* Leaf 0x8000001d - Cache properties. */
+            uint64_t :64, :64; /* Leaf 0x8000001e - Extd APIC/Core/Node IDs. */
+            uint64_t :64, :64; /* Leaf 0x8000001f - AMD Secure Encryption. */
+            uint64_t :64, :64; /* Leaf 0x80000020 - Platform QoS. */
+
+            /* Leaf 0x80000021 - Extended Feature 2 */
+            union {
+                uint32_t e21a;
+                struct { DECL_BITFIELD(e21a); };
+            };
+            uint32_t /* b */:32, /* c */:32, /* d */:32;
         };
     } extd;
 
@@ -293,6 +326,7 @@ static inline void cpuid_policy_to_featureset(
     fs[FEATURESET_e8b] = p->extd.e8b;
     fs[FEATURESET_7d0] = p->feat._7d0;
     fs[FEATURESET_7a1] = p->feat._7a1;
+    fs[FEATURESET_e21a] = p->extd.e21a;
 }
 
 /* Fill in a CPUID policy from a featureset bitmap. */
@@ -310,6 +344,7 @@ static inline void cpuid_featureset_to_policy(
     p->extd.e8b   = fs[FEATURESET_e8b];
     p->feat._7d0  = fs[FEATURESET_7d0];
     p->feat._7a1  = fs[FEATURESET_7a1];
+    p->extd.e21a  = fs[FEATURESET_e21a];
 }
 
 static inline uint64_t cpuid_policy_xcr0_max(const struct cpuid_policy *p)