5 files changed, 61 insertions, 14 deletions

diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index cb2fdd130aae..c881bcafba7d 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -76,6 +76,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_SGX1,			X86_FEATURE_SGX       },
 	{ X86_FEATURE_SGX2,			X86_FEATURE_SGX1      },
 	{ X86_FEATURE_XFD,			X86_FEATURE_XSAVES    },
+	{ X86_FEATURE_XFD,			X86_FEATURE_XGETBV1   },
 	{ X86_FEATURE_AMX_TILE,			X86_FEATURE_XFD       },
 	{}
 };
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index acfd5d9f93c6..bb9a46a804bf 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -547,12 +547,13 @@ bool intel_filter_mce(struct mce *m)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	/* MCE errata HSD131, HSM142, HSW131, BDM48, and HSM142 */
+	/* MCE errata HSD131, HSM142, HSW131, BDM48, HSM142 and SKX37 */
 	if ((c->x86 == 6) &&
 	    ((c->x86_model == INTEL_FAM6_HASWELL) ||
 	     (c->x86_model == INTEL_FAM6_HASWELL_L) ||
 	     (c->x86_model == INTEL_FAM6_BROADWELL) ||
-	     (c->x86_model == INTEL_FAM6_HASWELL_G)) &&
+	     (c->x86_model == INTEL_FAM6_HASWELL_G) ||
+	     (c->x86_model == INTEL_FAM6_SKYLAKE_X)) &&
 	    (m->bank == 0) &&
 	    ((m->status & 0xa0000000ffffffff) == 0x80000000000f0005))
 		return true;
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index e18210dff88c..86ea7c0fa2f6 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -4,6 +4,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/fpu/xstate.h>
+#include <asm/fpu/xcr.h>
 
 #ifdef CONFIG_X86_64
 DECLARE_PER_CPU(u64, xfd_state);
@@ -199,6 +200,32 @@ static inline void os_xrstor_supervisor(struct fpstate *fpstate)
 }
 
 /*
+ * XSAVE itself always writes all requested xfeatures.  Removing features
+ * from the request bitmap reduces the features which are written.
+ * Generate a mask of features which must be written to a sigframe.  The
+ * unset features can be optimized away and not written.
+ *
+ * This optimization is user-visible.  Only use for states where
+ * uninitialized sigframe contents are tolerable, like dynamic features.
+ *
+ * Users of buffers produced with this optimization must check XSTATE_BV
+ * to determine which features have been optimized out.
+ */
+static inline u64 xfeatures_need_sigframe_write(void)
+{
+	u64 xfeaures_to_write;
+
+	/* In-use features must be written: */
+	xfeaures_to_write = xfeatures_in_use();
+
+	/* Also write all non-optimizable sigframe features: */
+	xfeaures_to_write |= XFEATURE_MASK_USER_SUPPORTED &
+			     ~XFEATURE_MASK_SIGFRAME_INITOPT;
+
+	return xfeaures_to_write;
+}
+
+/*
  * Save xstate to user space xsave area.
  *
  * We don't use modified optimization because xrstor/xrstors might track
@@ -220,10 +247,16 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
 	 */
 	struct fpstate *fpstate = current->thread.fpu.fpstate;
 	u64 mask = fpstate->user_xfeatures;
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
+	u32 lmask;
+	u32 hmask;
 	int err;
 
+	/* Optimize away writing unnecessary xfeatures: */
+	if (fpu_state_size_dynamic())
+		mask &= xfeatures_need_sigframe_write();
+
+	lmask = mask;
+	hmask = mask >> 32;
 	xfd_validate_state(fpstate, mask, false);
 
 	stac();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8241927addff..ac2909f0cab3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1350,12 +1350,7 @@ static void __init smp_get_logical_apicid(void)
 		cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
 }
 
-/*
- * Prepare for SMP bootup.
- * @max_cpus: configured maximum number of CPUs, It is a legacy parameter
- *            for common interface support.
- */
-void __init native_smp_prepare_cpus(unsigned int max_cpus)
+void __init smp_prepare_cpus_common(void)
 {
 	unsigned int i;
 
@@ -1386,6 +1381,17 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	set_sched_topology(x86_topology);
 
 	set_cpu_sibling_map(0);
+}
+
+/*
+ * Prepare for SMP bootup.
+ * @max_cpus: configured maximum number of CPUs, It is a legacy parameter
+ *            for common interface support.
+ */
+void __init native_smp_prepare_cpus(unsigned int max_cpus)
+{
+	smp_prepare_cpus_common();
+
 	init_freq_invariance(false, false);
 	smp_sanity_check();
 
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index ea028e736831..9c407a33a774 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -56,10 +56,15 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void
 	text_poke_bp(insn, code, size, emulate);
 }
 
-static void __static_call_validate(void *insn, bool tail)
+static void __static_call_validate(void *insn, bool tail, bool tramp)
 {
 	u8 opcode = *(u8 *)insn;
 
+	if (tramp && memcmp(insn+5, "SCT", 3)) {
+		pr_err("trampoline signature fail");
+		BUG();
+	}
+
 	if (tail) {
 		if (opcode == JMP32_INSN_OPCODE ||
 		    opcode == RET_INSN_OPCODE)
@@ -74,7 +79,8 @@ static void __static_call_validate(void *insn, bool tail)
 	/*
 	 * If we ever trigger this, our text is corrupt, we'll probably not live long.
 	 */
-	WARN_ONCE(1, "unexpected static_call insn opcode 0x%x at %pS\n", opcode, insn);
+	pr_err("unexpected static_call insn opcode 0x%x at %pS\n", opcode, insn);
+	BUG();
 }
 
 static inline enum insn_type __sc_insn(bool null, bool tail)
@@ -97,12 +103,12 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 	mutex_lock(&text_mutex);
 
 	if (tramp) {
-		__static_call_validate(tramp, true);
+		__static_call_validate(tramp, true, true);
 		__static_call_transform(tramp, __sc_insn(!func, true), func);
 	}
 
 	if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site) {
-		__static_call_validate(site, tail);
+		__static_call_validate(site, tail, false);
 		__static_call_transform(site, __sc_insn(!func, tail), func);
 	}