File xsa435-0-02.patch of Package xen.31135
From e9b4fe26364950258c9f57f0f68eccb778eeadbb Mon Sep 17 00:00:00 2001
From: Roger Pau Monné <roger.pau@citrix.com>
Date: Thu, 15 Apr 2021 16:47:31 +0200
Subject: 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>
From d4012d50082c2eae2f3cbe7770be13b9227fbc3f Mon Sep 17 00:00:00 2001
From: Andrew Cooper <andrew.cooper3@citrix.com>
Date: Wed, 6 Apr 2022 22:40:20 +0100
Subject: x86/cpuid: Clobber CPUID leaves 0x800000{1d..20} in policies
c/s 1a914256dca5 increased the AMD max leaf from 0x8000001c to 0x80000021, but
did not adjust anything in the calculate_*_policy() chain. As a result, on
hardware supporting these leaves, we read the real hardware values into the
raw policy, then copy into host, and all the way into the PV/HVM default
policies.
All 4 of these leaves have enable bits (first two by TopoExt, next by SEV,
next by PQOS), so any software following the rules is fine and will leave them
alone. However, leaf 0x8000001d takes a subleaf input and at least two
userspace utilities have been observed to loop indefinitely under Xen (clearly
waiting for eax to report "no more cache levels").
Such userspace is buggy, but Xen's behaviour isn't great either.
In the short term, clobber all information in these leaves. This is a giant
bodge, but there are complexities with implementing all of these leaves
properly.
Fixes: 1a914256dca5 ("x86/cpuid: support LFENCE always serialising CPUID bit")
Link: https://github.com/QubesOS/qubes-issues/issues/7392
Reported-by: fosslinux <fosslinux@aussies.space>
Reported-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
--- a/tools/libxl/libxl_cpuid.c
+++ b/tools/libxl/libxl_cpuid.c
@@ -288,6 +288,8 @@ int libxl_cpuid_parse_config(libxl_cpuid
{"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}
--- a/tools/misc/xen-cpuid.c
+++ b/tools/misc/xen-cpuid.c
@@ -182,6 +182,11 @@ 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;
@@ -199,6 +204,7 @@ 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"
--- a/xen/arch/x86/cpu/amd.c
+++ b/xen/arch/x86/cpu/amd.c
@@ -732,8 +732,13 @@ static void init_amd(struct cpuinfo_x86
* value in but silently discard writes), as well as being per-core
* rather than per-thread, so do a full safe read/write/readback cycle
* in the worst case.
+ *
+ * Some hardware has LFENCE dispatch serialising always enabled,
+ * nothing to do on that case.
*/
- if (c->x86 == 0x0f || c->x86 == 0x11)
+ if (test_bit(X86_FEATURE_LFENCE_DISPATCH, c->x86_capability))
+ /* nothing */;
+ else if (c->x86 == 0x0f || c->x86 == 0x11)
/* Always dispatch serialising on this hardare. */
__set_bit(X86_FEATURE_LFENCE_DISPATCH, c->x86_capability);
else /* Implicily "== 0x10 || >= 0x12" by being 64bit. */ {
--- a/xen/arch/x86/cpu/common.c
+++ b/xen/arch/x86/cpu/common.c
@@ -406,6 +406,9 @@ static void generic_identify(struct cpui
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 ) {
--- a/xen/arch/x86/cpuid.c
+++ b/xen/arch/x86/cpuid.c
@@ -278,8 +278,15 @@ static void recalculate_misc(struct cpui
zero_leaves(p->extd.raw, 0xb, 0x18);
+ /* 0x19 - TLB details. Pass through. */
+ /* 0x1a - Perf hints. Pass through. */
+
p->extd.raw[0x1b] = EMPTY_LEAF; /* IBS - not supported. */
p->extd.raw[0x1c] = EMPTY_LEAF; /* LWP - not supported. */
+ p->extd.raw[0x1d] = EMPTY_LEAF; /* TopoExt Cache */
+ p->extd.raw[0x1e] = EMPTY_LEAF; /* TopoExt APIC ID/Core/Node */
+ p->extd.raw[0x1f] = EMPTY_LEAF; /* SEV */
+ p->extd.raw[0x20] = EMPTY_LEAF; /* Platform QoS */
break;
}
}
@@ -297,6 +304,7 @@ static void __init calculate_raw_policy(
static void __init calculate_host_policy(void)
{
struct cpuid_policy *p = &host_cpuid_policy;
+ unsigned int max_extd_leaf;
*p = raw_cpuid_policy;
@@ -304,7 +312,19 @@ static void __init calculate_host_policy
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);
--- a/xen/include/asm-x86/cpufeatures.h
+++ b/xen/include/asm-x86/cpufeatures.h
@@ -24,7 +24,7 @@ XEN_CPUFEATURE(APERFMPERF, X86_SY
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 */
--- a/xen/include/public/arch-x86/cpufeatureset.h
+++ b/xen/include/public/arch-x86/cpufeatureset.h
@@ -277,6 +277,9 @@ XEN_CPUFEATURE(SSBD, 9*32+31) /
/* Intel-defined CPU features, CPUID level 0x00000007:1.eax, word 10 */
XEN_CPUFEATURE(AVX512_BF16, 10*32+ 5) /* 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). */
--- a/xen/include/xen/lib/x86/cpuid.h
+++ b/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(unsi
#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_featu
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_p
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)
