summaryrefslogtreecommitdiff
path: root/arch/x86/include/asm/cpufeature.h
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2015-03-04 06:33:49 +0100
committerIngo Molnar <mingo@kernel.org>2015-03-04 06:36:15 +0100
commitf8e92fb4b0ffc4d62279ab39f34e798e37e90b0b (patch)
tree9caa8df664792e64ddcb4ea03fd418a8a529c82e /arch/x86/include/asm/cpufeature.h
parentd2c032e3dc58137a7261a7824d3acce435db1d66 (diff)
parentdfecb95cdfeaf7872d83a96bec3a606e9cd95c8d (diff)
Merge tag 'alternatives_padding' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp into x86/asm
Pull alternative instructions framework improvements from Borislav Petkov: "A more involved rework of the alternatives framework to be able to pad instructions and thus make using the alternatives macros more straightforward and without having to figure out old and new instruction sizes but have the toolchain figure that out for us. Furthermore, it optimizes JMPs used so that fetch and decode can be relieved with smaller versions of the JMPs, where possible. Some stats: x86_64 defconfig: Alternatives sites total: 2478 Total padding added (in Bytes): 6051 The padding is currently done for: X86_FEATURE_ALWAYS X86_FEATURE_ERMS X86_FEATURE_LFENCE_RDTSC X86_FEATURE_MFENCE_RDTSC X86_FEATURE_SMAP This is with the latest version of the patchset. Of course, on each machine the alternatives sites actually being patched are a proper subset of the total number." Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/include/asm/cpufeature.h')
-rw-r--r--arch/x86/include/asm/cpufeature.h30
1 files changed, 17 insertions, 13 deletions
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index d6428ea5d316..0f7a5a1a8db2 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -419,6 +419,7 @@ 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);
@@ -433,6 +434,7 @@ 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);
@@ -458,6 +460,7 @@ 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 */
@@ -484,31 +487,30 @@ 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);
@@ -528,6 +530,7 @@ 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 */
@@ -542,6 +545,7 @@ 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 */