x86 optimization of the immediate values which uses a movl with code patching to set/unset the value used to populate the register used as variable source. It uses a breakpoint to bypass the instruction being changed, which lessens the interrupt latency of the operation and protects against NMIs and MCE. Changelog: - Use text_poke_early with cr0 WP save/restore to patch the bypass. We are doing non atomic writes to a code region only touched by us (nobody can execute it since we are protected by the imv_mutex). - Add x86_64 support, ready for i386+x86_64 -> x86 merge. - Use asm-x86/asm.h. - Change the immediate.c update code to support variable length opcodes. - Use imv_* instead of immediate_*. Signed-off-by: Mathieu Desnoyers CC: Andi Kleen CC: "H. Peter Anvin" CC: Chuck Ebbert CC: Christoph Hellwig CC: Jeremy Fitzhardinge CC: Thomas Gleixner CC: Ingo Molnar --- arch/x86/kernel/Makefile_32 | 1 arch/x86/kernel/Makefile_64 | 1 arch/x86/kernel/immediate.c | 278 ++++++++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/traps_32.c | 10 - include/asm-x86/immediate.h | 42 +++++- 5 files changed, 323 insertions(+), 9 deletions(-) Index: linux-2.6-lttng/include/asm-x86/immediate.h =================================================================== --- linux-2.6-lttng.orig/include/asm-x86/immediate.h 2007-11-28 09:32:11.000000000 -0500 +++ linux-2.6-lttng/include/asm-x86/immediate.h 2007-11-28 09:32:23.000000000 -0500 @@ -12,6 +12,18 @@ #include +struct __imv { + unsigned long var; /* Pointer to the identifier variable of the + * immediate value + */ + unsigned long imv; /* + * Pointer to the memory location of the + * immediate value within the instruction. + */ + unsigned char size; /* Type size. */ + unsigned char insn_size;/* Type size. */ +} __attribute__ ((packed)); + /** * imv_read - read immediate variable * @name: immediate value name @@ -26,6 +38,11 @@ * what will generate an instruction with 8 bytes immediate value (not the REX.W * prefixed one that loads a sign extended 32 bits immediate value in a r64 * register). + * + * Create the instruction in a discarded section to calculate its size. This is + * how we can align the beginning of the instruction on an address that will + * permit atomic modification of the immediate value without knowing the size of + * the opcode used by the compiler. The operand size is known in advance. */ #define imv_read(name) \ ({ \ @@ -35,8 +52,9 @@ case 1: \ asm(".section __imv,\"a\",@progbits\n\t" \ _ASM_PTR "%c1, (3f)-%c2\n\t" \ - ".byte %c2\n\t" \ + ".byte %c2, (3f-2f)\n\t" \ ".previous\n\t" \ + "2:\n\t" \ "mov $0,%0\n\t" \ "3:\n\t" \ : "=q" (value) \ @@ -45,10 +63,16 @@ break; \ case 2: \ case 4: \ - asm(".section __imv,\"a\",@progbits\n\t" \ + asm(".section __discard,\"\",@progbits\n\t" \ + "1:\n\t" \ + "mov $0,%0\n\t" \ + "2:\n\t" \ + ".previous\n\t" \ + ".section __imv,\"a\",@progbits\n\t" \ _ASM_PTR "%c1, (3f)-%c2\n\t" \ - ".byte %c2\n\t" \ + ".byte %c2, (2b-1b)\n\t" \ ".previous\n\t" \ + ".org . + ((-.-(2b-1b)) & (%c2-1)), 0x90\n\t" \ "mov $0,%0\n\t" \ "3:\n\t" \ : "=r" (value) \ @@ -60,10 +84,16 @@ value = name##__imv; \ break; \ } \ - asm(".section __imv,\"a\",@progbits\n\t" \ + asm(".section __discard,\"\",@progbits\n\t" \ + "1:\n\t" \ + "mov $0xFEFEFEFE01010101,%0\n\t" \ + "2:\n\t" \ + ".previous\n\t" \ + ".section __imv,\"a\",@progbits\n\t" \ _ASM_PTR "%c1, (3f)-%c2\n\t" \ - ".byte %c2\n\t" \ + ".byte %c2, (2b-1b)\n\t" \ ".previous\n\t" \ + ".org . + ((-.-(2b-1b)) & (%c2-1)), 0x90\n\t" \ "mov $0xFEFEFEFE01010101,%0\n\t" \ "3:\n\t" \ : "=r" (value) \ @@ -74,4 +104,6 @@ value; \ }) +extern int arch_imv_update(const struct __imv *imv, int early); + #endif /* _ASM_X86_IMMEDIATE_H */ Index: linux-2.6-lttng/arch/x86/kernel/traps_32.c =================================================================== --- linux-2.6-lttng.orig/arch/x86/kernel/traps_32.c 2007-11-28 09:27:33.000000000 -0500 +++ linux-2.6-lttng/arch/x86/kernel/traps_32.c 2007-11-28 09:32:23.000000000 -0500 @@ -549,7 +549,7 @@ fastcall void do_##name(struct pt_regs * } DO_VM86_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->eip) -#ifndef CONFIG_KPROBES +#if !defined(CONFIG_KPROBES) && !defined(CONFIG_IMMEDIATE) DO_VM86_ERROR( 3, SIGTRAP, "int3", int3) #endif DO_VM86_ERROR( 4, SIGSEGV, "overflow", overflow) @@ -791,7 +791,7 @@ void restart_nmi(void) acpi_nmi_enable(); } -#ifdef CONFIG_KPROBES +#if defined(CONFIG_KPROBES) || defined(CONFIG_IMMEDIATE) fastcall void __kprobes do_int3(struct pt_regs *regs, long error_code) { trace_hardirqs_fixup(); @@ -799,8 +799,10 @@ fastcall void __kprobes do_int3(struct p if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) return; - /* This is an interrupt gate, because kprobes wants interrupts - disabled. Normal trap handlers don't. */ + /* + * This is an interrupt gate, because kprobes and immediate values wants + * interrupts disabled. Normal trap handlers don't. + */ restore_interrupts(regs); do_trap(3, SIGTRAP, "int3", 1, regs, error_code, NULL); } Index: linux-2.6-lttng/arch/x86/kernel/Makefile_64 =================================================================== --- linux-2.6-lttng.orig/arch/x86/kernel/Makefile_64 2007-11-28 09:27:33.000000000 -0500 +++ linux-2.6-lttng/arch/x86/kernel/Makefile_64 2007-11-28 09:32:23.000000000 -0500 @@ -35,6 +35,7 @@ obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64 obj-$(CONFIG_X86_VSMP) += vsmp_64.o obj-$(CONFIG_K8_NB) += k8.o obj-$(CONFIG_AUDIT) += audit_64.o +obj-$(CONFIG_IMMEDIATE) += immediate.o obj-$(CONFIG_MODULES) += module_64.o obj-$(CONFIG_PCI) += early-quirks.o Index: linux-2.6-lttng/arch/x86/kernel/Makefile_32 =================================================================== --- linux-2.6-lttng.orig/arch/x86/kernel/Makefile_32 2007-11-28 09:27:33.000000000 -0500 +++ linux-2.6-lttng/arch/x86/kernel/Makefile_32 2007-11-28 09:32:23.000000000 -0500 @@ -35,6 +35,7 @@ obj-$(CONFIG_KPROBES) += kprobes_32.o obj-$(CONFIG_MODULES) += module_32.o obj-y += sysenter_32.o vsyscall_32.o obj-$(CONFIG_ACPI_SRAT) += srat_32.o +obj-$(CONFIG_IMMEDIATE) += immediate.o obj-$(CONFIG_EFI) += efi_32.o efi_stub_32.o obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o obj-$(CONFIG_VM86) += vm86_32.o Index: linux-2.6-lttng/arch/x86/kernel/immediate.c =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6-lttng/arch/x86/kernel/immediate.c 2007-11-28 09:32:23.000000000 -0500 @@ -0,0 +1,278 @@ +/* + * Immediate Value - x86 architecture specific code. + * + * Rationale + * + * Required because of : + * - Erratum 49 fix for Intel PIII. + * - Still present on newer processors : Intel Core 2 Duo Processor for Intel + * Centrino Duo Processor Technology Specification Update, AH33. + * Unsynchronized Cross-Modifying Code Operations Can Cause Unexpected + * Instruction Execution Results. + * + * Permits immediate value modification by XMC with correct serialization. + * + * Reentrant for NMI and trap handler instrumentation. Permits XMC to a + * location that has preemption enabled because it involves no temporary or + * reused data structure. + * + * Quoting Richard J Moore, source of the information motivating this + * implementation which differs from the one proposed by Intel which is not + * suitable for kernel context (does not support NMI and would require disabling + * interrupts on every CPU for a long period) : + * + * "There is another issue to consider when looking into using probes other + * then int3: + * + * Intel erratum 54 - Unsynchronized Cross-modifying code - refers to the + * practice of modifying code on one processor where another has prefetched + * the unmodified version of the code. Intel states that unpredictable general + * protection faults may result if a synchronizing instruction (iret, int, + * int3, cpuid, etc ) is not executed on the second processor before it + * executes the pre-fetched out-of-date copy of the instruction. + * + * When we became aware of this I had a long discussion with Intel's + * microarchitecture guys. It turns out that the reason for this erratum + * (which incidentally Intel does not intend to fix) is because the trace + * cache - the stream of micro-ops resulting from instruction interpretation - + * cannot be guaranteed to be valid. Reading between the lines I assume this + * issue arises because of optimization done in the trace cache, where it is + * no longer possible to identify the original instruction boundaries. If the + * CPU discoverers that the trace cache has been invalidated because of + * unsynchronized cross-modification then instruction execution will be + * aborted with a GPF. Further discussion with Intel revealed that replacing + * the first opcode byte with an int3 would not be subject to this erratum. + * + * So, is cmpxchg reliable? One has to guarantee more than mere atomicity." + * + * Overall design + * + * The algorithm proposed by Intel applies not so well in kernel context: it + * would imply disabling interrupts and looping on every CPUs while modifying + * the code and would not support instrumentation of code called from interrupt + * sources that cannot be disabled. + * + * Therefore, we use a different algorithm to respect Intel's erratum (see the + * quoted discussion above). We make sure that no CPU sees an out-of-date copy + * of a pre-fetched instruction by 1 - using a breakpoint, which skips the + * instruction that is going to be modified, 2 - issuing an IPI to every CPU to + * execute a sync_core(), to make sure that even when the breakpoint is removed, + * no cpu could possibly still have the out-of-date copy of the instruction, + * modify the now unused 2nd byte of the instruction, and then put back the + * original 1st byte of the instruction. + * + * It has exactly the same intent as the algorithm proposed by Intel, but + * it has less side-effects, scales better and supports NMI, SMI and MCE. + * + * Mathieu Desnoyers + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define BREAKPOINT_INSTRUCTION 0xcc +#define BREAKPOINT_INS_LEN 1 +#define NR_NOPS 10 + +static unsigned long target_after_int3; /* EIP of the target after the int3 */ +static unsigned long bypass_eip; /* EIP of the bypass. */ +static unsigned long bypass_after_int3; /* EIP after the end-of-bypass int3 */ +static unsigned long after_imv; /* + * EIP where to resume after the + * single-stepping. + */ + +/* + * Internal bypass used during value update. The bypass is skipped by the + * function in which it is inserted. + * No need to be aligned because we exclude readers from the site during + * update. + * Layout is: + * (10x nop) int3 + * (maximum size is 2 bytes opcode + 8 bytes immediate value for long on x86_64) + * The nops are the target replaced by the instruction to single-step. + */ +static inline void _imv_bypass(unsigned long *bypassaddr, + unsigned long *breaknextaddr) +{ + asm volatile("jmp 2f;\n\t" + "0:\n\t" + ".space 10, 0x90;\n\t" + "1:\n\t" + "int3;\n\t" + "2:\n\t" + "mov $(0b),%0;\n\t" + "mov $((1b)+1),%1;\n\t" + : "=r" (*bypassaddr), + "=r" (*breaknextaddr)); +} + +static void imv_synchronize_core(void *info) +{ + sync_core(); /* use cpuid to stop speculative execution */ +} + +/* + * The eip value points right after the breakpoint instruction, in the second + * byte of the movl. + * Disable preemption in the bypass to make sure no thread will be preempted in + * it. We can then use synchronize_sched() to make sure every bypass users have + * ended. + */ +static int imv_notifier(struct notifier_block *nb, + unsigned long val, void *data) +{ + enum die_val die_val = (enum die_val) val; + struct die_args *args = data; + + if (!args->regs || user_mode_vm(args->regs)) + return NOTIFY_DONE; + + if (die_val == DIE_INT3) { + if (instruction_pointer(args->regs) == target_after_int3) { + preempt_disable(); + instruction_pointer(args->regs) = bypass_eip; + return NOTIFY_STOP; + } else if (instruction_pointer(args->regs) + == bypass_after_int3) { + instruction_pointer(args->regs) = after_imv; + preempt_enable(); + return NOTIFY_STOP; + } + } + return NOTIFY_DONE; +} + +static struct notifier_block imv_notify = { + .notifier_call = imv_notifier, + .priority = 0x7fffffff, /* we need to be notified first */ +}; + +/** + * arch_imv_update - update one immediate value + * @imv: pointer of type const struct __imv to update + * @early: early boot (1) or normal (0) + * + * Update one immediate value. Must be called with imv_mutex held. + */ +__kprobes int arch_imv_update(const struct __imv *imv, int early) +{ + int ret; + unsigned char opcode_size = imv->insn_size - imv->size; + unsigned long insn = imv->imv - opcode_size; + unsigned long len; + unsigned long cr0; + +#ifdef CONFIG_KPROBES + /* + * Fail if a kprobe has been set on this instruction. + * (TODO: we could eventually do better and modify all the (possibly + * nested) kprobes for this site if kprobes had an API for this. + */ + if (unlikely(!early && *(unsigned char *)insn == BREAKPOINT_INSTRUCTION)) { + printk(KERN_WARNING "Immediate value in conflict with kprobe. " + "Variable at %p, " + "instruction at %p, size %hu\n", + (void *)imv->imv, + (void *)imv->var, imv->size); + return -EBUSY; + } +#endif + + /* + * If the variable and the instruction have the same value, there is + * nothing to do. + */ + switch (imv->size) { + case 1: if (*(uint8_t *)imv->imv + == *(uint8_t *)imv->var) + return 0; + break; + case 2: if (*(uint16_t *)imv->imv + == *(uint16_t *)imv->var) + return 0; + break; + case 4: if (*(uint32_t *)imv->imv + == *(uint32_t *)imv->var) + return 0; + break; +#ifdef CONFIG_X86_64 + case 8: if (*(uint64_t *)imv->imv + == *(uint64_t *)imv->var) + return 0; + break; +#endif + default:return -EINVAL; + } + + if (!early) { + /* bypass is 10 bytes long for x86_64 long */ + WARN_ON(imv->insn_size > 10); + _imv_bypass(&bypass_eip, &bypass_after_int3); + + after_imv = imv->imv + imv->size; + + /* + * Using the _early variants because nobody is executing the + * bypass code while we patch it. It is protected by the + * imv_mutex. Since we modify the instructions non atomically (for + * nops), we have to use the _early variant. + * We must however deal with the WP flag in cr0 by ourself. + */ + kernel_wp_save(cr0); + text_poke_early((void *)bypass_eip, (void *)insn, + imv->insn_size); + /* + * Fill the rest with nops. + */ + len = NR_NOPS - imv->insn_size; + add_nops((void *)(bypass_eip + imv->insn_size), len); + kernel_wp_restore(cr0); + + target_after_int3 = insn + BREAKPOINT_INS_LEN; + /* register_die_notifier has memory barriers */ + register_die_notifier(&imv_notify); + /* The breakpoint will single-step the bypass */ + text_poke((void *)insn, + INIT_ARRAY(unsigned char, BREAKPOINT_INSTRUCTION, 1), 1); + /* + * Make sure the breakpoint is set before we continue (visible to other + * CPUs and interrupts). + */ + wmb(); + /* + * Execute serializing instruction on each CPU. + */ + ret = on_each_cpu(imv_synchronize_core, NULL, 1, 1); + BUG_ON(ret != 0); + + text_poke((void *)(insn + opcode_size), (void *)imv->var, + imv->size); + /* + * Make sure the value can be seen from other CPUs and interrupts. + */ + wmb(); + text_poke((void *)insn, (unsigned char *)bypass_eip, 1); + /* + * Wait for all int3 handlers to end (interrupts are disabled in int3). + * This CPU is clearly not in a int3 handler, because int3 handler is + * not preemptible and there cannot be any more int3 handler called for + * this site, because we placed the original instruction back. + * synchronize_sched has memory barriers. + */ + synchronize_sched(); + unregister_die_notifier(&imv_notify); + /* unregister_die_notifier has memory barriers */ + } else + text_poke_early((void *)imv->imv, (void *)imv->var, + imv->size); + return 0; +} -- Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/