From: Steven Rostedt Have the jump labels add a "jmp" in the assembly instead of a default nop. This will cause the assembler to put in either a 2 byte or 5 byte jmp depending on where the target lable is. Then at compile time, the update_jump_label code will replace the jmps with either 2 or 5 byte nops. On boot up, the code can be examined to see if the jump label uses either a 2 or 5 byte nop and replace it. By allowing the jump labels to be 2 bytes, it speeds up the nops, not only 2 byte nops are faster than 5 byte nops, but also because it saves on cache foot print. text data bss dec hex filename 13403667 3666856 2998272 20068795 13239bb ../nobackup/mxtest/vmlinux-old 13398536 3666856 2998272 20063664 13225b0 ../nobackup/mxtest/vmlinux-new Converting the current v3.2 trace points saved 5,131 bytes. As more places use jump labels, this will have a bigger savings. Signed-off-by: Steven Rostedt --- arch/x86/Kconfig | 1 + arch/x86/include/asm/jump_label.h | 2 +- arch/x86/kernel/jump_label.c | 86 ++++++++++++++++++++++++++++-------- 3 files changed, 69 insertions(+), 20 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index efb4294..b5004c1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -61,6 +61,7 @@ config X86 select HAVE_ARCH_KMEMCHECK select HAVE_USER_RETURN_NOTIFIER select HAVE_ARCH_JUMP_LABEL + select HAVE_BUILD_TIME_JUMP_LABEL select HAVE_TEXT_POKE_SMP select HAVE_GENERIC_HARDIRQS select HAVE_SPARSE_IRQ diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index cefcfd3..bde5323 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -19,7 +19,7 @@ static __always_inline bool arch_static_branch(struct jump_label_key *key) { asm goto("1:" - ".byte " __stringify(JUMP_LABEL_INIT_NOP) "\n\t" + "jmp %l[l_yes]\n" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" _ASM_PTR "1b, %l[l_yes], %c0 \n\t" diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index 44f2528..8abd2a3 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -16,12 +16,21 @@ #ifdef HAVE_JUMP_LABEL +static unsigned char nop_short[] = { P6_NOP2 }; + +/* These are the nops added at compile time */ +static unsigned char default_nop[] = { JUMP_LABEL_INIT_NOP }; + union jump_code_union { char code[JUMP_LABEL_NOP_SIZE]; struct { char jump; int offset; - } __attribute__((packed)); + } __packed; + struct { + char jump_short; + char offset_short; + } __packed; }; static void __jump_label_transform(struct jump_entry *entry, @@ -30,18 +39,33 @@ static void __jump_label_transform(struct jump_entry *entry, int init) { union jump_code_union code; + unsigned char nop; + unsigned char op; + unsigned size; + void *ip = (void *)entry->code; const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; - if (type == JUMP_LABEL_ENABLE) { - /* - * We are enabling this jump label. If it is not a nop - * then something must have gone wrong. - */ - BUG_ON(memcmp((void *)entry->code, ideal_nop, 5) != 0); + /* Use probe_kernel_read()? */ + op = *(unsigned char *)ip; + nop = ideal_nops[NOP_ATOMIC5][0]; - code.jump = 0xe9; - code.offset = entry->target - - (entry->code + JUMP_LABEL_NOP_SIZE); + if (type == JUMP_LABEL_ENABLE) { + if (memcmp(ip, nop_short, 2) == 0) { + size = 2; + code.jump_short = 0xeb; + code.offset = entry->target - (entry->code + 2); + /* Check for overflow ? */ + } else if (memcmp(ip, ideal_nop, 5) == 0) { + size = JUMP_LABEL_NOP_SIZE; + code.jump = 0xe9; + code.offset = entry->target - (entry->code + size); + } else + /* + * The location is not a nop that we were expecting, + * something went wrong. Crash the box, as something could be + * corrupting the kernel. + */ + BUG(); } else { /* * We are disabling this jump label. If it is not what @@ -50,18 +74,44 @@ static void __jump_label_transform(struct jump_entry *entry, * are converting the default nop to the ideal nop. */ if (init) { - unsigned char default_nop[] = { JUMP_LABEL_INIT_NOP }; - BUG_ON(memcmp((void *)entry->code, default_nop, 5) != 0); - } else { + /* Ignore short nops, we do not change them */ + if (memcmp(ip, nop_short, 2) == 0) + return; + + /* We are initializing from the default nop */ + BUG_ON(memcmp(ip, default_nop, 5) != 0); + + /* Set to the ideal nop */ + size = JUMP_LABEL_NOP_SIZE; + memcpy(&code, ideal_nops[NOP_ATOMIC5], size); + + } else if (op == 0xe9) { + /* Replace a 5 byte jmp */ + + /* Make sure this is what we expected it to be */ code.jump = 0xe9; code.offset = entry->target - (entry->code + JUMP_LABEL_NOP_SIZE); - BUG_ON(memcmp((void *)entry->code, &code, 5) != 0); - } - memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE); + BUG_ON(memcmp(ip, &code, 5) != 0); + + size = JUMP_LABEL_NOP_SIZE; + memcpy(&code, ideal_nops[NOP_ATOMIC5], size); + } else if (op == 0xeb) { + /* Replace a 2 byte jmp */ + + /* Had better be a 2 byte jmp */ + code.jump_short = 0xeb; + code.offset = entry->target - (entry->code + 2); + BUG_ON(memcmp(ip, &code, 2) != 0); + + size = 2; + memcpy(&code, nop_short, size); + } else + /* The code was not what we expected! */ + BUG(); } - (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE); + (*poker)(ip, &code, size); } void arch_jump_label_transform(struct jump_entry *entry, @@ -88,7 +138,6 @@ void arch_jump_label_transform_static(struct jump_entry *entry, * If it is not, then we need to update the nop to the ideal nop. */ if (!once) { - unsigned char default_nop[] = { JUMP_LABEL_INIT_NOP }; const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; once++; if (memcmp(ideal_nop, default_nop, 5) != 0) @@ -97,5 +146,4 @@ void arch_jump_label_transform_static(struct jump_entry *entry, if (update) __jump_label_transform(entry, type, text_poke_early, 1); } - #endif -- 1.7.8.3