Unify the CPU features vectors between i386 and x86-64

Unify the handling of the CPU features vectors between i386 and x86-64.
This also adopts the collapsing of features which are required at
compile-time into constant tests from x86-64 to i386.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 133 insertions, 152 deletions

diff --git a/include/asm-i386/cpufeature.h b/include/asm-i386/cpufeature.h
index f514e906643a..7ea5f4a6706f 100644
--- a/include/asm-i386/cpufeature.h
+++ b/include/asm-i386/cpufeature.h
@@ -81,6 +81,7 @@
 #define X86_FEATURE_BTS         (3*32+13)  /* Branch Trace Store */
 #define X86_FEATURE_LAPIC_TIMER_BROKEN (3*32+ 14) /* lapic timer broken in C1 */
 #define X86_FEATURE_SYNC_RDTSC  (3*32+15)  /* RDTSC synchronizes the CPU */
+#define X86_FEATURE_REP_GOOD   (3*32+16) /* rep microcode works well on this CPU */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3        (4*32+ 0) /* Streaming SIMD Extensions-3 */
@@ -108,11 +109,17 @@
 #define X86_FEATURE_LAHF_LM     (6*32+ 0) /* LAHF/SAHF in long mode */
 #define X86_FEATURE_CMP_LEGACY  (6*32+ 1) /* If yes HyperThreading not valid */
 
-#define cpu_has(c, bit)                                 \
-        ((__builtin_constant_p(bit) && (bit) < 32 &&    \
-                (1UL << (bit)) & REQUIRED_MASK1) ?      \
-                1 :                                     \
-        test_bit(bit, (c)->x86_capability))
+#define cpu_has(c, bit)                                                 \
+        (__builtin_constant_p(bit) &&                                   \
+         ( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) ||     \
+           (((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) ||     \
+           (((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) ||     \
+           (((bit)>>5)==3 && (1UL<<((bit)&31) & REQUIRED_MASK3)) ||     \
+           (((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4)) ||     \
+           (((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5)) ||     \
+           (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) )      \
+          ? 1 :                                                         \
+          test_bit(bit, (c)->x86_capability))
 #define boot_cpu_has(bit)       cpu_has(&boot_cpu_data, bit)
 
 #define cpu_has_fpu             boot_cpu_has(X86_FEATURE_FPU)
diff --git a/include/asm-i386/required-features.h b/include/asm-i386/required-features.h
index 9db866c1e64c..a9c3b1147bd0 100644
--- a/include/asm-i386/required-features.h
+++ b/include/asm-i386/required-features.h
@@ -3,32 +3,52 @@
 
 /* Define minimum CPUID feature set for kernel These bits are checked
    really early to actually display a visible error message before the
-   kernel dies.  Only add word 0 bits here
+   kernel dies.  Make sure to assign features to the proper mask!
 
    Some requirements that are not in CPUID yet are also in the
-   CONFIG_X86_MINIMUM_CPU mode which is checked too.
+   CONFIG_X86_MINIMUM_CPU_FAMILY which is checked too.
 
    The real information is in arch/i386/Kconfig.cpu, this just converts
    the CONFIGs into a bitmask */
 
+#ifndef CONFIG_MATH_EMULATION
+# define NEED_FPU       (1<<(X86_FEATURE_FPU & 31))
+#else
+# define NEED_FPU       0
+#endif
+
 #ifdef CONFIG_X86_PAE
-#define NEED_PAE        (1<<X86_FEATURE_PAE)
+# define NEED_PAE       (1<<(X86_FEATURE_PAE & 31))
 #else
-#define NEED_PAE        0
+# define NEED_PAE       0
 #endif
 
 #ifdef CONFIG_X86_CMOV
-#define NEED_CMOV       (1<<X86_FEATURE_CMOV)
+# define NEED_CMOV      (1<<(X86_FEATURE_CMOV & 31))
 #else
-#define NEED_CMOV       0
+# define NEED_CMOV      0
 #endif
 
 #ifdef CONFIG_X86_CMPXCHG64
-#define NEED_CMPXCHG64  (1<<X86_FEATURE_CX8)
+# define NEED_CX8       (1<<(X86_FEATURE_CX8 & 31))
+#else
+# define NEED_CX8       0
+#endif
+
+#define REQUIRED_MASK0  (NEED_FPU|NEED_PAE|NEED_CMOV|NEED_CX8)
+
+#ifdef CONFIG_X86_USE_3DNOW
+# define NEED_3DNOW     (1<<(X86_FEATURE_3DNOW & 31))
 #else
-#define NEED_CMPXCHG64  0
+# define NEED_3DNOW     0
 #endif
 
-#define REQUIRED_MASK1  (NEED_PAE|NEED_CMOV|NEED_CMPXCHG64)
+#define REQUIRED_MASK1  (NEED_3DNOW)
+
+#define REQUIRED_MASK2  0
+#define REQUIRED_MASK3  0
+#define REQUIRED_MASK4  0
+#define REQUIRED_MASK5  0
+#define REQUIRED_MASK6  0
 
 #endif
diff --git a/include/asm-x86_64/alternative.h b/include/asm-x86_64/alternative.h
index a09427640764..eea7aecfac78 100644
--- a/include/asm-x86_64/alternative.h
+++ b/include/asm-x86_64/alternative.h
@@ -5,6 +5,41 @@
 
 #include <linux/types.h>
 #include <linux/stddef.h>
+
+/*
+ * Alternative inline assembly for SMP.
+ *
+ * The LOCK_PREFIX macro defined here replaces the LOCK and
+ * LOCK_PREFIX macros used everywhere in the source tree.
+ *
+ * SMP alternatives use the same data structures as the other
+ * alternatives and the X86_FEATURE_UP flag to indicate the case of a
+ * UP system running a SMP kernel.  The existing apply_alternatives()
+ * works fine for patching a SMP kernel for UP.
+ *
+ * The SMP alternative tables can be kept after boot and contain both
+ * UP and SMP versions of the instructions to allow switching back to
+ * SMP at runtime, when hotplugging in a new CPU, which is especially
+ * useful in virtualized environments.
+ *
+ * The very common lock prefix is handled as special case in a
+ * separate table which is a pure address list without replacement ptr
+ * and size information.  That keeps the table sizes small.
+ */
+
+#ifdef CONFIG_SMP
+#define LOCK_PREFIX \
+                ".section .smp_locks,\"a\"\n"   \
+                "  .align 8\n"                  \
+                "  .quad 661f\n" /* address */  \
+                ".previous\n"                   \
+                "661:\n\tlock; "
+
+#else /* ! CONFIG_SMP */
+#define LOCK_PREFIX ""
+#endif
+
+/* This must be included *after* the definition of LOCK_PREFIX */
 #include <asm/cpufeature.h>
 
 struct alt_instr {
@@ -108,39 +143,6 @@ static inline void alternatives_smp_switch(int smp) {}
  */
 #define ASM_OUTPUT2(a, b) a, b
 
-/*
- * Alternative inline assembly for SMP.
- *
- * The LOCK_PREFIX macro defined here replaces the LOCK and
- * LOCK_PREFIX macros used everywhere in the source tree.
- *
- * SMP alternatives use the same data structures as the other
- * alternatives and the X86_FEATURE_UP flag to indicate the case of a
- * UP system running a SMP kernel.  The existing apply_alternatives()
- * works fine for patching a SMP kernel for UP.
- *
- * The SMP alternative tables can be kept after boot and contain both
- * UP and SMP versions of the instructions to allow switching back to
- * SMP at runtime, when hotplugging in a new CPU, which is especially
- * useful in virtualized environments.
- *
- * The very common lock prefix is handled as special case in a
- * separate table which is a pure address list without replacement ptr
- * and size information.  That keeps the table sizes small.
- */
-
-#ifdef CONFIG_SMP
-#define LOCK_PREFIX \
-                ".section .smp_locks,\"a\"\n"   \
-                "  .align 8\n"                  \
-                "  .quad 661f\n" /* address */  \
-                ".previous\n"                   \
-                "661:\n\tlock; "
-
-#else /* ! CONFIG_SMP */
-#define LOCK_PREFIX ""
-#endif
-
 struct paravirt_patch;
 #ifdef CONFIG_PARAVIRT
 void apply_paravirt(struct paravirt_patch *start, struct paravirt_patch *end);
diff --git a/include/asm-x86_64/cpufeature.h b/include/asm-x86_64/cpufeature.h
index 0b3c686139f1..8baefc3beb2e 100644
--- a/include/asm-x86_64/cpufeature.h
+++ b/include/asm-x86_64/cpufeature.h
@@ -7,115 +7,24 @@
 #ifndef __ASM_X8664_CPUFEATURE_H
 #define __ASM_X8664_CPUFEATURE_H
 
-#define NCAPINTS        7       /* N 32-bit words worth of info */
+#include <asm-i386/cpufeature.h>
 
-/* Intel-defined CPU features, CPUID level 0x00000001, word 0 */
-#define X86_FEATURE_FPU         (0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME         (0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE          (0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE         (0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC         (0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR         (0*32+ 5) /* Model-Specific Registers, RDMSR, WRMSR */
-#define X86_FEATURE_PAE         (0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE         (0*32+ 7) /* Machine Check Architecture */
-#define X86_FEATURE_CX8         (0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC        (0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP         (0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR        (0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE         (0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA         (0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV        (0*32+15) /* CMOV instruction (FCMOVCC and FCOMI too if FPU present) */
-#define X86_FEATURE_PAT         (0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36       (0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN          (0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLSH      (0*32+19) /* Supports the CLFLUSH instruction */
-#define X86_FEATURE_DS          (0*32+21) /* Debug Store */
-#define X86_FEATURE_ACPI        (0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX         (0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR        (0*32+24) /* FXSAVE and FXRSTOR instructions (fast save and restore */
-                                          /* of FPU context), and CR4.OSFXSR available */
-#define X86_FEATURE_XMM         (0*32+25) /* Streaming SIMD Extensions */
-#define X86_FEATURE_XMM2        (0*32+26) /* Streaming SIMD Extensions-2 */
-#define X86_FEATURE_SELFSNOOP   (0*32+27) /* CPU self snoop */
-#define X86_FEATURE_HT          (0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC         (0*32+29) /* Automatic clock control */
-#define X86_FEATURE_IA64        (0*32+30) /* IA-64 processor */
-
-/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
-/* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL     (1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MMXEXT      (1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT    (1*32+25) /* FXSR optimizations */
-#define X86_FEATURE_RDTSCP      (1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM          (1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT    (1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW       (1*32+31) /* 3DNow! */
-
-/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY    (2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN     (2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI        (2*32+ 3) /* LongRun table interface */
-
-/* Other features, Linux-defined mapping, word 3 */
-/* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX       (3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR     (3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR   (3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR (3*32+ 3) /* Centaur MCRs (= MTRRs) */
-#define X86_FEATURE_REP_GOOD    (3*32+ 4) /* rep microcode works well on this CPU */
-#define X86_FEATURE_CONSTANT_TSC (3*32+5) /* TSC runs at constant rate */
-#define X86_FEATURE_SYNC_RDTSC  (3*32+6)  /* RDTSC syncs CPU core */
-#define X86_FEATURE_FXSAVE_LEAK (3*32+7)  /* FIP/FOP/FDP leaks through FXSAVE */
-#define X86_FEATURE_UP          (3*32+8) /* SMP kernel running on UP */
-#define X86_FEATURE_ARCH_PERFMON (3*32+9) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS        (3*32+10) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS         (3*32+11) /* Branch Trace Store */
-
-/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3        (4*32+ 0) /* Streaming SIMD Extensions-3 */
-#define X86_FEATURE_MWAIT       (4*32+ 3) /* Monitor/Mwait support */
-#define X86_FEATURE_DSCPL       (4*32+ 4) /* CPL Qualified Debug Store */
-#define X86_FEATURE_EST         (4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2         (4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_CID         (4*32+10) /* Context ID */
-#define X86_FEATURE_CX16        (4*32+13) /* CMPXCHG16B */
-#define X86_FEATURE_XTPR        (4*32+14) /* Send Task Priority Messages */
-
-/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE      (5*32+ 2) /* on-CPU RNG present (xstore insn) */
-#define X86_FEATURE_XSTORE_EN   (5*32+ 3) /* on-CPU RNG enabled */
-#define X86_FEATURE_XCRYPT      (5*32+ 6) /* on-CPU crypto (xcrypt insn) */
-#define X86_FEATURE_XCRYPT_EN   (5*32+ 7) /* on-CPU crypto enabled */
-
-/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
-#define X86_FEATURE_LAHF_LM     (6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY  (6*32+ 1) /* If yes HyperThreading not valid */
-
-#define cpu_has(c, bit)                test_bit(bit, (c)->x86_capability)
-#define boot_cpu_has(bit)      test_bit(bit, boot_cpu_data.x86_capability)
-
-#define cpu_has_fpu            1
+#undef  cpu_has_vme
 #define cpu_has_vme            0
-#define cpu_has_de             1
-#define cpu_has_pse            1
-#define cpu_has_tsc            1
+
+#undef  cpu_has_pae
 #define cpu_has_pae            ___BUG___
-#define cpu_has_pge            1
-#define cpu_has_apic           boot_cpu_has(X86_FEATURE_APIC)
-#define cpu_has_mtrr           1
-#define cpu_has_mmx            1
-#define cpu_has_fxsr           1
-#define cpu_has_xmm            1
-#define cpu_has_xmm2           1
-#define cpu_has_xmm3           boot_cpu_has(X86_FEATURE_XMM3)
-#define cpu_has_ht             boot_cpu_has(X86_FEATURE_HT)
+
+#undef  cpu_has_mp
 #define cpu_has_mp             1 /* XXX */
+
+#undef  cpu_has_k6_mtrr
 #define cpu_has_k6_mtrr        0
+
+#undef  cpu_has_cyrix_arr
 #define cpu_has_cyrix_arr      0
+
+#undef  cpu_has_centaur_mcr
 #define cpu_has_centaur_mcr    0
-#define cpu_has_clflush        boot_cpu_has(X86_FEATURE_CLFLSH)
-#define cpu_has_ds             boot_cpu_has(X86_FEATURE_DS)
-#define cpu_has_pebs           boot_cpu_has(X86_FEATURE_PEBS)
-#define cpu_has_bts            boot_cpu_has(X86_FEATURE_BTS)
 
 #endif /* __ASM_X8664_CPUFEATURE_H */
diff --git a/include/asm-x86_64/processor.h b/include/asm-x86_64/processor.h
index 461ffe4c1fcc..df6457248d62 100644
--- a/include/asm-x86_64/processor.h
+++ b/include/asm-x86_64/processor.h
@@ -368,8 +368,6 @@ static inline void sync_core(void)
         asm volatile("cpuid" : "=a" (tmp) : "0" (1) : "ebx","ecx","edx","memory");
 } 
 
-#define cpu_has_fpu 1
-
 #define ARCH_HAS_PREFETCH
 static inline void prefetch(void *x) 
 { 
diff --git a/include/asm-x86_64/required-features.h b/include/asm-x86_64/required-features.h
new file mode 100644
index 000000000000..262f3159d032
--- /dev/null
+++ b/include/asm-x86_64/required-features.h
@@ -0,0 +1,45 @@
+#ifndef _ASM_REQUIRED_FEATURES_H
+#define _ASM_REQUIRED_FEATURES_H 1
+
+/* Define minimum CPUID feature set for kernel These bits are checked
+   really early to actually display a visible error message before the
+   kernel dies.  Make sure to assign features to the proper mask!
+
+   The real information is in arch/x86_64/Kconfig.cpu, this just converts
+   the CONFIGs into a bitmask */
+
+/* x86-64 baseline features */
+#define NEED_FPU        (1<<(X86_FEATURE_FPU & 31))
+#define NEED_PSE        (1<<(X86_FEATURE_PSE & 31))
+#define NEED_MSR        (1<<(X86_FEATURE_MSR & 31))
+#define NEED_PAE        (1<<(X86_FEATURE_PAE & 31))
+#define NEED_CX8        (1<<(X86_FEATURE_CX8 & 31))
+#define NEED_PGE        (1<<(X86_FEATURE_PGE & 31))
+#define NEED_FXSR       (1<<(X86_FEATURE_FXSR & 31))
+#define NEED_CMOV       (1<<(X86_FEATURE_CMOV & 31))
+#define NEED_XMM        (1<<(X86_FEATURE_XMM & 31))
+#define NEED_XMM2       (1<<(X86_FEATURE_XMM2 & 31))
+
+#define REQUIRED_MASK0  (NEED_FPU|NEED_PSE|NEED_MSR|NEED_PAE|\
+                         NEED_CX8|NEED_PGE|NEED_FXSR|NEED_CMOV|\
+                         NEED_XMM|NEED_XMM2)
+#define SSE_MASK        (NEED_XMM|NEED_XMM2)
+
+/* x86-64 baseline features */
+#define NEED_LM         (1<<(X86_FEATURE_LM & 31))
+
+#ifdef CONFIG_X86_USE_3DNOW
+# define NEED_3DNOW     (1<<(X86_FEATURE_3DNOW & 31))
+#else
+# define NEED_3DNOW     0
+#endif
+
+#define REQUIRED_MASK1  (NEED_LM|NEED_3DNOW)
+
+#define REQUIRED_MASK2  0
+#define REQUIRED_MASK3  0
+#define REQUIRED_MASK4  0
+#define REQUIRED_MASK5  0
+#define REQUIRED_MASK6  0
+
+#endif