x86/cpuid: Add generic table for CPUID dependencies

Some CPUID features depend on other features. Currently it's
possible to to clear dependent features, but not clear the base features,
which can cause various interesting problems.

This patch implements a generic table to describe dependencies
between CPUID features, to be used by all code that clears
CPUID.

Some subsystems (like XSAVE) had an own implementation of this,
but it's better to do it all in a single place for everyone.

Then clear_cpu_cap and setup_clear_cpu_cap always look up
this table and clear all dependencies too.

This is intended to be a practical table: only for features
that make sense to clear. If someone for example clears FPU,
or other features that are essentially part of the required
base feature set, not much is going to work. Handling
that is right now out of scope. We're only handling
features which can be usefully cleared.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Jonathan McDowell <noodles@earth.li>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20171013215645.23166-3-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/cpufeature.h

@@ -125,11 +125,10 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #define boot_cpu_has(bit)	cpu_has(&boot_cpu_data, bit)
 
 #define set_cpu_cap(c, bit)	set_bit(bit, (unsigned long *)((c)->x86_capability))
-#define clear_cpu_cap(c, bit)	clear_bit(bit, (unsigned long *)((c)->x86_capability))
-#define setup_clear_cpu_cap(bit) do { \
-	clear_cpu_cap(&boot_cpu_data, bit);	\
-	set_bit(bit, (unsigned long *)cpu_caps_cleared); \
-} while (0)
+
+extern void setup_clear_cpu_cap(unsigned int bit);
+extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
+
 #define setup_force_cpu_cap(bit) do { \
 	set_cpu_cap(&boot_cpu_data, bit);	\
 	set_bit(bit, (unsigned long *)cpu_caps_set);	\

arch/x86/include/asm/cpufeatures.h

@@ -21,6 +21,11 @@
  * this feature bit is not displayed in /proc/cpuinfo at all.
  */
 
+/*
+ * When adding new features here that depend on other features,
+ * please update the table in kernel/cpu/cpuid-deps.c
+ */
+
 /* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
 #define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
 #define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */

arch/x86/kernel/cpu/Makefile

@@ -22,6 +22,7 @@ obj-y			+= rdrand.o
 obj-y			+= match.o
 obj-y			+= bugs.o
 obj-$(CONFIG_CPU_FREQ)	+= aperfmperf.o
+obj-y			+= cpuid-deps.o
 
 obj-$(CONFIG_PROC_FS)	+= proc.o
 obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o

arch/x86/kernel/cpu/cpuid-deps.c

@@ -0,0 +1,113 @@
+/* Declare dependencies between CPUIDs */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <asm/cpufeature.h>
+
+struct cpuid_dep {
+	unsigned int	feature;
+	unsigned int	depends;
+};
+
+/*
+ * Table of CPUID features that depend on others.
+ *
+ * This only includes dependencies that can be usefully disabled, not
+ * features part of the base set (like FPU).
+ *
+ * Note this all is not __init / __initdata because it can be
+ * called from cpu hotplug. It shouldn't do anything in this case,
+ * but it's difficult to tell that to the init reference checker.
+ */
+const static struct cpuid_dep cpuid_deps[] = {
+	{ X86_FEATURE_XSAVEOPT,		X86_FEATURE_XSAVE     },
+	{ X86_FEATURE_XSAVEC,		X86_FEATURE_XSAVE     },
+	{ X86_FEATURE_XSAVES,		X86_FEATURE_XSAVE     },
+	{ X86_FEATURE_AVX,		X86_FEATURE_XSAVE     },
+	{ X86_FEATURE_PKU,		X86_FEATURE_XSAVE     },
+	{ X86_FEATURE_MPX,		X86_FEATURE_XSAVE     },
+	{ X86_FEATURE_XGETBV1,		X86_FEATURE_XSAVE     },
+	{ X86_FEATURE_FXSR_OPT,		X86_FEATURE_FXSR      },
+	{ X86_FEATURE_XMM,		X86_FEATURE_FXSR      },
+	{ X86_FEATURE_XMM2,		X86_FEATURE_XMM       },
+	{ X86_FEATURE_XMM3,		X86_FEATURE_XMM2      },
+	{ X86_FEATURE_XMM4_1,		X86_FEATURE_XMM2      },
+	{ X86_FEATURE_XMM4_2,		X86_FEATURE_XMM2      },
+	{ X86_FEATURE_XMM3,		X86_FEATURE_XMM2      },
+	{ X86_FEATURE_PCLMULQDQ,	X86_FEATURE_XMM2      },
+	{ X86_FEATURE_SSSE3,		X86_FEATURE_XMM2,     },
+	{ X86_FEATURE_F16C,		X86_FEATURE_XMM2,     },
+	{ X86_FEATURE_AES,		X86_FEATURE_XMM2      },
+	{ X86_FEATURE_SHA_NI,		X86_FEATURE_XMM2      },
+	{ X86_FEATURE_FMA,		X86_FEATURE_AVX       },
+	{ X86_FEATURE_AVX2,		X86_FEATURE_AVX,      },
+	{ X86_FEATURE_AVX512F,		X86_FEATURE_AVX,      },
+	{ X86_FEATURE_AVX512IFMA,	X86_FEATURE_AVX512F   },
+	{ X86_FEATURE_AVX512PF,		X86_FEATURE_AVX512F   },
+	{ X86_FEATURE_AVX512ER,		X86_FEATURE_AVX512F   },
+	{ X86_FEATURE_AVX512CD,		X86_FEATURE_AVX512F   },
+	{ X86_FEATURE_AVX512DQ,		X86_FEATURE_AVX512F   },
+	{ X86_FEATURE_AVX512BW,		X86_FEATURE_AVX512F   },
+	{ X86_FEATURE_AVX512VL,		X86_FEATURE_AVX512F   },
+	{ X86_FEATURE_AVX512VBMI,	X86_FEATURE_AVX512F   },
+	{ X86_FEATURE_AVX512_4VNNIW,	X86_FEATURE_AVX512F   },
+	{ X86_FEATURE_AVX512_4FMAPS,	X86_FEATURE_AVX512F   },
+	{ X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F   },
+	{}
+};
+
+static inline void __clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit)
+{
+	clear_bit32(bit, c->x86_capability);
+}
+
+static inline void __setup_clear_cpu_cap(unsigned int bit)
+{
+	clear_cpu_cap(&boot_cpu_data, bit);
+	set_bit32(bit, cpu_caps_cleared);
+}
+
+static inline void clear_feature(struct cpuinfo_x86 *c, unsigned int feature)
+{
+	if (!c)
+		__setup_clear_cpu_cap(feature);
+	else
+		__clear_cpu_cap(c, feature);
+}
+
+static void do_clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature)
+{
+	bool changed;
+	DECLARE_BITMAP(disable, NCAPINTS * sizeof(u32) * 8);
+	const struct cpuid_dep *d;
+
+	clear_feature(c, feature);
+
+	/* Collect all features to disable, handling dependencies */
+	memset(disable, 0, sizeof(disable));
+	__set_bit(feature, disable);
+
+	/* Loop until we get a stable state. */
+	do {
+		changed = false;
+		for (d = cpuid_deps; d->feature; d++) {
+			if (!test_bit(d->depends, disable))
+				continue;
+			if (__test_and_set_bit(d->feature, disable))
+				continue;
+
+			changed = true;
+			clear_feature(c, d->feature);
+		}
+	} while (changed);
+}
+
+void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature)
+{
+	do_clear_cpu_cap(c, feature);
+}
+
+void setup_clear_cpu_cap(unsigned int feature)
+{
+	do_clear_cpu_cap(NULL, feature);
+}