x86/alternatives for 2.6.36
H. Peter Anvin
reviewerHi Linus,
The following changes since commit fc1caf6eafb30ea185720e29f7f5eccca61ecd60:
Merge branch 'drm-core-next' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6 (2010-08-05 16:02:01 -0700)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git x86-alternatives-for-linus
H. Peter Anvin (3):
x86, alternatives: Use 16-bit numbers for cpufeature index x86, alternatives: Fix one more open-coded 8-bit alternative number x86, alternatives: BUG on encountering an invalid CPU feature number
arch/x86/include/asm/alternative.h | 7 ++++--- arch/x86/include/asm/cpufeature.h | 14 ++++++++------ arch/x86/kernel/alternative.c | 1 + arch/x86/kernel/entry_32.S | 2 +- arch/x86/lib/clear_page_64.S | 2 +- arch/x86/lib/copy_page_64.S | 2 +- arch/x86/lib/copy_user_64.S | 2 +- arch/x86/lib/memcpy_64.S | 2 +- arch/x86/lib/memset_64.S | 2 +- 9 files changed, 19 insertions(+), 15 deletions(-)
arch/x86/include/asm/alternative.h +4 -3
@@ -45,10 +45,9 @@struct alt_instr {u8 *instr;/* original instruction */ u8 *replacement; -u8 cpuid;/* cpuid bit set for replacement */ +u16 cpuid;/* cpuid bit set for replacement */ u8 instrlen;/* length of original instruction */ u8 replacementlen;/* length of new instruction, <= instrlen */ -u8 pad1;#ifdef CONFIG_X86_64 u32 pad2;#endif
@@ -86,9 +85,11 @@ static inline int alternatives_text_reserved(void *start, void *end) _ASM_ALIGN"\n" \ _ASM_PTR"661b\n" /* label */ \ _ASM_PTR"663f\n" /* new instruction */ \ - " .byte " __stringify(feature) "\n" /* feature bit */ \ + " .word " __stringify(feature) "\n" /* feature bit */ \" .byte 662b-661b\n" /* sourcelen */ \" .byte 664f-663f\n" /* replacementlen */ \ +".previous\n" \ +".section .discard,\"aw\",@progbits\n" \" .byte 0xff + (664f-663f) - (662b-661b)\n" /* rlen <= slen */ \".previous\n" \".section .altinstr_replacement, \"ax\"\n" \
arch/x86/include/asm/cpufeature.h +8 -6
@@ -291,7 +291,7 @@ extern const char * const x86_power_flags[32];* patch the target code for additional performance. * */ -static __always_inline __pure bool __static_cpu_has(u8 bit) +static __always_inline __pure bool __static_cpu_has(u16 bit) {#if __GNUC__ >4 || (__GNUC__ ==4 && __GNUC_MINOR__ >=5 ) asm goto("1: jmp %l[t_no]\n"
@@ -300,11 +300,11 @@ static __always_inline __pure bool __static_cpu_has(u8 bit) _ASM_ALIGN "\n" _ASM_PTR "1b\n" _ASM_PTR "0\n" /* no replacement */ - " .byte %P0\n" /* feature bit */ + " .word %P0\n" /* feature bit */ " .byte 2b - 1b\n" /* source len */ " .byte 0\n" /* replacement len */ - " .byte 0xff + 0 - (2b-1b)\n" /* padding */ ".previous\n" + /* skipping size check since replacement size = 0 */ : : "i" (bit) : : t_no);return true; t_no:
@@ -318,10 +318,12 @@ static __always_inline __pure bool __static_cpu_has(u8 bit) _ASM_ALIGN"\n" _ASM_PTR"1b\n" _ASM_PTR"3f\n" -" .byte %P1\n" /* feature bit */ +" .word %P1\n" /* feature bit */ " .byte 2b - 1b\n" /* source len */ " .byte 4f - 3f\n" /* replacement len */ -" .byte 0xff + (4f-3f) - (2b-1b)\n" /* padding */ +".previous\n" +".section .discard,\"aw\",@progbits\n" +" .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */ ".previous\n" ".section .altinstr_replacement,\"ax\"\n" "3: movb $1,%0\n"
@@ -337,7 +339,7 @@ static __always_inline __pure bool __static_cpu_has(u8 bit) ( \__builtin_constant_p (boot_cpu_has (bit)) ? \boot_cpu_has (bit) : \ - (__builtin_constant_p (bit) && !((bit) & ~0xff )) ? \ +__builtin_constant_p (bit) ? \__static_cpu_has (bit) : \boot_cpu_has (bit) \ )
arch/x86/kernel/alternative.c +1 -0
@@ -214,6 +214,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start,u8 *instr = a->instr;BUG_ON (a->replacementlen > a->instrlen);BUG_ON (a->instrlen >sizeof (insnbuf)); +BUG_ON (a->cpuid >=NCAPINTS *32 );if (!boot_cpu_has (a->cpuid))continue ;#ifdef CONFIG_X86_64
arch/x86/kernel/entry_32.S +1 -1
@@ -914,7 +914,7 @@ ENTRY(simd_coprocessor_error) .balign 4 .long 661b .long 663f - .byte X86_FEATURE_XMM + .word X86_FEATURE_XMM .byte 662b-661b .byte 664f-663f .previous
arch/x86/lib/clear_page_64.S +1 -1
@@ -52,7 +52,7 @@ ENDPROC(clear_page) .align 8 .quad clear_page .quad 1b - .byte X86_FEATURE_REP_GOOD + .word X86_FEATURE_REP_GOOD .byte .Lclear_page_end - clear_page .byte 2b - 1b .previous
arch/x86/lib/copy_page_64.S +1 -1
@@ -113,7 +113,7 @@ ENDPROC(copy_page) .align 8 .quad copy_page .quad 1b - .byte X86_FEATURE_REP_GOOD + .word X86_FEATURE_REP_GOOD .byte .Lcopy_page_end - copy_page .byte 2b - 1b .previous
arch/x86/lib/copy_user_64.S +1 -1
@@ -29,7 +29,7 @@ .align 8 .quad 0b .quad 2b - .byte \feature /* when feature is set */ + .word \feature /* when feature is set */ .byte 5 .byte 5 .previous
arch/x86/lib/memcpy_64.S +1 -1
@@ -131,7 +131,7 @@ ENDPROC(__memcpy) .align 8 .quad memcpy .quad .Lmemcpy_c - .byte X86_FEATURE_REP_GOOD + .word X86_FEATURE_REP_GOOD /* * Replace only beginning, memcpy is used to apply alternatives,
arch/x86/lib/memset_64.S +1 -1
@@ -121,7 +121,7 @@ ENDPROC(__memset) .align 8 .quad memset .quad .Lmemset_c - .byte X86_FEATURE_REP_GOOD + .word X86_FEATURE_REP_GOOD .byte .Lfinal - memset .byte .Lmemset_e - .Lmemset_c .previous