Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git...

[sfrench/cifs-2.6.git] / arch / x86 / include / asm / cpufeature.h

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index c1553b70fed4fa2b560a89fd0b918ab3d7683ba7..7ee9b94d9921bf0a1ea7e010c76985cb6a8595ce 100644 (file)
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -233,7 +233,9 @@
 #define X86_FEATURE_RDSEED     ( 9*32+18) /* The RDSEED instruction */
 #define X86_FEATURE_ADX                ( 9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP       ( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_PCOMMIT    ( 9*32+22) /* PCOMMIT instruction */
 #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_CLWB       ( 9*32+24) /* CLWB instruction */
 #define X86_FEATURE_AVX512PF   ( 9*32+26) /* AVX-512 Prefetch */
 #define X86_FEATURE_AVX512ER   ( 9*32+27) /* AVX-512 Exponential and Reciprocal */
 #define X86_FEATURE_AVX512CD   ( 9*32+28) /* AVX-512 Conflict Detection */
@@ -426,6 +428,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
                         " .word %P0\n"         /* 1: do replace */
                         " .byte 2b - 1b\n"     /* source len */
                         " .byte 0\n"           /* replacement len */
+                        " .byte 0\n"           /* pad len */
                         ".previous\n"
                         /* skipping size check since replacement size = 0 */
                         : : "i" (X86_FEATURE_ALWAYS) : : t_warn);
@@ -440,6 +443,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
                         " .word %P0\n"         /* feature bit */
                         " .byte 2b - 1b\n"     /* source len */
                         " .byte 0\n"           /* replacement len */
+                        " .byte 0\n"           /* pad len */
                         ".previous\n"
                         /* skipping size check since replacement size = 0 */
                         : : "i" (bit) : : t_no);
@@ -465,6 +469,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
                             " .word %P1\n"             /* feature bit */
                             " .byte 2b - 1b\n"         /* source len */
                             " .byte 4f - 3f\n"         /* replacement len */
+                            " .byte 0\n"               /* pad len */
                             ".previous\n"
                             ".section .discard,\"aw\",@progbits\n"
                             " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */
@@ -491,31 +496,30 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 {
 #ifdef CC_HAVE_ASM_GOTO
-/*
- * We need to spell the jumps to the compiler because, depending on the offset,
- * the replacement jump can be bigger than the original jump, and this we cannot
- * have. Thus, we force the jump to the widest, 4-byte, signed relative
- * offset even though the last would often fit in less bytes.
- */
-               asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
+               asm_volatile_goto("1: jmp %l[t_dynamic]\n"
                         "2:\n"
+                        ".skip -(((5f-4f) - (2b-1b)) > 0) * "
+                                "((5f-4f) - (2b-1b)),0x90\n"
+                        "3:\n"
                         ".section .altinstructions,\"a\"\n"
                         " .long 1b - .\n"              /* src offset */
-                        " .long 3f - .\n"              /* repl offset */
+                        " .long 4f - .\n"              /* repl offset */
                         " .word %P1\n"                 /* always replace */
-                        " .byte 2b - 1b\n"             /* src len */
-                        " .byte 4f - 3f\n"             /* repl len */
+                        " .byte 3b - 1b\n"             /* src len */
+                        " .byte 5f - 4f\n"             /* repl len */
+                        " .byte 3b - 2b\n"             /* pad len */
                         ".previous\n"
                         ".section .altinstr_replacement,\"ax\"\n"
-                        "3: .byte 0xe9\n .long %l[t_no] - 2b\n"
-                        "4:\n"
+                        "4: jmp %l[t_no]\n"
+                        "5:\n"
                         ".previous\n"
                         ".section .altinstructions,\"a\"\n"
                         " .long 1b - .\n"              /* src offset */
                         " .long 0\n"                   /* no replacement */
                         " .word %P0\n"                 /* feature bit */
-                        " .byte 2b - 1b\n"             /* src len */
+                        " .byte 3b - 1b\n"             /* src len */
                         " .byte 0\n"                   /* repl len */
+                        " .byte 0\n"                   /* pad len */
                         ".previous\n"
                         : : "i" (bit), "i" (X86_FEATURE_ALWAYS)
                         : : t_dynamic, t_no);
@@ -535,6 +539,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
                             " .word %P2\n"             /* always replace */
                             " .byte 2b - 1b\n"         /* source len */
                             " .byte 4f - 3f\n"         /* replacement len */
+                            " .byte 0\n"               /* pad len */
                             ".previous\n"
                             ".section .discard,\"aw\",@progbits\n"
                             " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */
@@ -549,6 +554,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
                             " .word %P1\n"             /* feature bit */
                             " .byte 4b - 3b\n"         /* src len */
                             " .byte 6f - 5f\n"         /* repl len */
+                            " .byte 0\n"               /* pad len */
                             ".previous\n"
                             ".section .discard,\"aw\",@progbits\n"
                             " .byte 0xff + (6f-5f) - (4b-3b)\n" /* size check */