Merge tag 'x86_urgent_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:

 - Add the model number of a new, Raptor Lake CPU, to intel-family.h

 - Do not log spurious corrected MCEs on SKL too, due to an erratum

 - Clarify the path of paravirt ops patches upstream

 - Add an optimization to avoid writing out AMX components to sigframes
   when former are in init state

* tag 'x86_urgent_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu: Add Raptor Lake to Intel family
  x86/mce: Add errata workaround for Skylake SKX37
  MAINTAINERS: Add some information to PARAVIRT_OPS entry
  x86/fpu: Optimize out sigframe xfeatures when in init state

Author: torvalds

Documentation/x86/xstate.rst

@@ -63,3 +63,12 @@ kernel sends SIGILL to the application. If the process has permission then
 the handler allocates a larger xstate buffer for the task so the large
 state can be context switched. In the unlikely cases that the allocation
 fails, the kernel sends SIGSEGV.
+
+Dynamic features in signal frames
+---------------------------------
+
+Dynamcally enabled features are not written to the signal frame upon signal
+entry if the feature is in its initial configuration.  This differs from
+non-dynamic features which are always written regardless of their
+configuration.  Signal handlers can examine the XSAVE buffer's XSTATE_BV
+field to determine if a features was written.

MAINTAINERS

@@ -14412,7 +14412,9 @@ M:	Juergen Gross <[email protected]>
 M:	Deep Shah <[email protected]>
 M:	"VMware, Inc." <[email protected]>
 L:	[email protected]
+L:	[email protected]
 S:	Supported
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
 F:	Documentation/virt/paravirt_ops.rst
 F:	arch/*/include/asm/paravirt*.h
 F:	arch/*/kernel/paravirt*

arch/x86/include/asm/fpu/xcr.h

@@ -3,6 +3,7 @@
 #define _ASM_X86_FPU_XCR_H
 
 #define XCR_XFEATURE_ENABLED_MASK	0x00000000
+#define XCR_XFEATURE_IN_USE_MASK	0x00000001
 
 static inline u64 xgetbv(u32 index)
 {
@@ -20,4 +21,15 @@ static inline void xsetbv(u32 index, u64 value)
 	asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
 }
 
+/*
+ * Return a mask of xfeatures which are currently being tracked
+ * by the processor as being in the initial configuration.
+ *
+ * Callers should check X86_FEATURE_XGETBV1.
+ */
+static inline u64 xfeatures_in_use(void)
+{
+	return xgetbv(XCR_XFEATURE_IN_USE_MASK);
+}
+
 #endif /* _ASM_X86_FPU_XCR_H */

arch/x86/include/asm/fpu/xstate.h

@@ -92,6 +92,13 @@
 #define XFEATURE_MASK_FPSTATE	(XFEATURE_MASK_USER_RESTORE | \
 				 XFEATURE_MASK_SUPERVISOR_SUPPORTED)
 
+/*
+ * Features in this mask have space allocated in the signal frame, but may not
+ * have that space initialized when the feature is in its init state.
+ */
+#define XFEATURE_MASK_SIGFRAME_INITOPT	(XFEATURE_MASK_XTILE | \
+					 XFEATURE_MASK_USER_DYNAMIC)
+
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
 extern void __init update_regset_xstate_info(unsigned int size,

arch/x86/include/asm/intel-family.h

@@ -108,6 +108,8 @@
 #define INTEL_FAM6_ALDERLAKE		0x97	/* Golden Cove / Gracemont */
 #define INTEL_FAM6_ALDERLAKE_L		0x9A	/* Golden Cove / Gracemont */
 
+#define INTEL_FAM6_RAPTOR_LAKE		0xB7
+
 /* "Small Core" Processors (Atom) */
 
 #define INTEL_FAM6_ATOM_BONNELL		0x1C /* Diamondville, Pineview */

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       },
 	{}
 };

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;

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);
@@ -198,6 +199,32 @@ static inline void os_xrstor_supervisor(struct fpstate *fpstate)
 	XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask);
 }
 
+/*
+ * 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.
  *
@@ -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();