From f0daed0242d514033b9ecca9187108d3c4e281a5 Mon Sep 17 00:00:00 2001 From: David Miller Date: Sat, 23 Oct 2010 11:06:24 -0700 Subject: jump_label: Fix unaligned traps on sparc. The vmlinux.lds.h knobs to emit the __jump_table section in the main kernel image takes care to align the section, but this doesn't help for the __jump_table section that gets emitted into modules. Fix the resulting lack of section alignment by explicitly specifying it in the assembler. Signed-off-by: David S. Miller LKML-Reference: <20101023.110624.226758370.davem@davemloft.net> Signed-off-by: Steven Rostedt --- arch/sparc/include/asm/jump_label.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h index 62e66d7b2fb6..d95cf44fb40d 100644 --- a/arch/sparc/include/asm/jump_label.h +++ b/arch/sparc/include/asm/jump_label.h @@ -14,6 +14,7 @@ "nop\n\t" \ "nop\n\t" \ ".pushsection __jump_table, \"a\"\n\t"\ + ".align 4\n\t" \ ".word 1b, %l[" #label "], %c0\n\t" \ ".popsection \n\t" \ : : "i" (key) : : label);\ -- cgit v1.2.2 From 2d1d7126bbde53989f1d7de174816c123bb7ecb0 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 27 Oct 2010 21:09:15 -0700 Subject: x86, ftrace: Use safe noops, drop trap test Always use a safe 5-byte noop sequence. Drop the trap test, since it is known to return false negatives on some virtualization platforms on 32 bits. The resulting code is both simpler and safer. Cc: Daniel Drake Cc: Jason Baron Cc: Mathieu Desnoyers Signed-off-by: H. Peter Anvin Signed-off-by: Steven Rostedt --- arch/x86/kernel/alternative.c | 69 ++++++++++--------------------------------- 1 file changed, 15 insertions(+), 54 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index a36bb90aef53..0b30214282a8 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -644,65 +644,26 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len) #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) -unsigned char ideal_nop5[IDEAL_NOP_SIZE_5]; +#ifdef CONFIG_X86_64 +unsigned char ideal_nop5[5] = { 0x66, 0x66, 0x66, 0x66, 0x90 }; +#else +unsigned char ideal_nop5[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 }; +#endif void __init arch_init_ideal_nop5(void) { - extern const unsigned char ftrace_test_p6nop[]; - extern const unsigned char ftrace_test_nop5[]; - extern const unsigned char ftrace_test_jmp[]; - int faulted = 0; - /* - * There is no good nop for all x86 archs. - * We will default to using the P6_NOP5, but first we - * will test to make sure that the nop will actually - * work on this CPU. If it faults, we will then - * go to a lesser efficient 5 byte nop. If that fails - * we then just use a jmp as our nop. This isn't the most - * efficient nop, but we can not use a multi part nop - * since we would then risk being preempted in the middle - * of that nop, and if we enabled tracing then, it might - * cause a system crash. + * There is no good nop for all x86 archs. This selection + * algorithm should be unified with the one in find_nop_table(), + * but this should be good enough for now. * - * TODO: check the cpuid to determine the best nop. + * For cases other than the ones below, use the safe (as in + * always functional) defaults above. */ - asm volatile ( - "ftrace_test_jmp:" - "jmp ftrace_test_p6nop\n" - "nop\n" - "nop\n" - "nop\n" /* 2 byte jmp + 3 bytes */ - "ftrace_test_p6nop:" - P6_NOP5 - "jmp 1f\n" - "ftrace_test_nop5:" - ".byte 0x66,0x66,0x66,0x66,0x90\n" - "1:" - ".section .fixup, \"ax\"\n" - "2: movl $1, %0\n" - " jmp ftrace_test_nop5\n" - "3: movl $2, %0\n" - " jmp 1b\n" - ".previous\n" - _ASM_EXTABLE(ftrace_test_p6nop, 2b) - _ASM_EXTABLE(ftrace_test_nop5, 3b) - : "=r"(faulted) : "0" (faulted)); - - switch (faulted) { - case 0: - pr_info("converting mcount calls to 0f 1f 44 00 00\n"); - memcpy(ideal_nop5, ftrace_test_p6nop, IDEAL_NOP_SIZE_5); - break; - case 1: - pr_info("converting mcount calls to 66 66 66 66 90\n"); - memcpy(ideal_nop5, ftrace_test_nop5, IDEAL_NOP_SIZE_5); - break; - case 2: - pr_info("converting mcount calls to jmp . + 5\n"); - memcpy(ideal_nop5, ftrace_test_jmp, IDEAL_NOP_SIZE_5); - break; - } - +#ifdef CONFIG_X86_64 + /* Don't use these on 32 bits due to broken virtualizers */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + memcpy(ideal_nop5, p6_nops[5], 5); +#endif } #endif -- cgit v1.2.2 From 45f81b1c96d9793e47ce925d257ea693ce0b193e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 29 Oct 2010 12:33:43 -0400 Subject: jump label: Add work around to i386 gcc asm goto bug On i386 (not x86_64) early implementations of gcc would have a bug with asm goto causing it to produce code like the following: (This was noticed by Peter Zijlstra) 56 pushl 0 67 nopl jmp 0x6f popl jmp 0x8c 6f mov test je 0x8c 8c mov call *(%esp) The jump added in the asm goto skipped over the popl that matched the pushl 0, which lead up to a quick crash of the system when the jump was enabled. The nopl is defined in the asm goto () statement and when tracepoints are enabled, the nop changes to a jump to the label that was specified by the asm goto. asm goto is suppose to tell gcc that the code in the asm might jump to an external label. Here gcc obviously fails to make that work. The bug report for gcc is here: http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226 The bug only appears on x86 when not compiled with -maccumulate-outgoing-args. This option is always set on x86_64 and it is also the work around for a function graph tracer i386 bug. (See commit: 746357d6a526d6da9d89a2ec645b28406e959c2e) This explains why the bug only showed up on i386 when function graph tracer was not enabled. This patch now adds a CONFIG_JUMP_LABEL option that is default off instead of using jump labels by default. When jump labels are enabled, the -maccumulate-outgoing-args will be used (causing a slightly larger kernel image on i386). This option will exist until we have a way to detect if the gcc compiler in use is safe to use on all configurations without the work around. Note, there exists such a test, but for now we will keep the enabling of jump label as a manual option. Archs that know the compiler is safe with asm goto, may choose to select JUMP_LABEL and enable it by default. Reported-by: Ingo Molnar Cause-discovered-by: Peter Zijlstra Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Jason Baron Cc: H. Peter Anvin Cc: David Daney Cc: Mathieu Desnoyers Cc: Masami Hiramatsu Cc: David Miller Cc: Richard Henderson LKML-Reference: <1288028746.3673.11.camel@laptop> Signed-off-by: Steven Rostedt --- arch/Kconfig | 14 ++++++++++++++ arch/x86/Makefile_32.cpu | 13 ++++++++++++- 2 files changed, 26 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/Kconfig b/arch/Kconfig index 53d7f619a1b9..8bf0fa652eb6 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -42,6 +42,20 @@ config KPROBES for kernel debugging, non-intrusive instrumentation and testing. If in doubt, say "N". +config JUMP_LABEL + bool "Optimize trace point call sites" + depends on HAVE_ARCH_JUMP_LABEL + help + If it is detected that the compiler has support for "asm goto", + the kernel will compile trace point locations with just a + nop instruction. When trace points are enabled, the nop will + be converted to a jump to the trace function. This technique + lowers overhead and stress on the branch prediction of the + processor. + + On i386, options added to the compiler flags may increase + the size of the kernel slightly. + config OPTPROBES def_bool y depends on KPROBES && HAVE_OPTPROBES diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index 1255d953c65d..f2ee1abb1df9 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -51,7 +51,18 @@ cflags-$(CONFIG_X86_GENERIC) += $(call tune,generic,$(call tune,i686)) # prologue (push %ebp, mov %esp, %ebp) which breaks the function graph # tracer assumptions. For i686, generic, core2 this is set by the # compiler anyway -cflags-$(CONFIG_FUNCTION_GRAPH_TRACER) += $(call cc-option,-maccumulate-outgoing-args) +ifeq ($(CONFIG_FUNCTION_GRAPH_TRACER), y) +ADD_ACCUMULATE_OUTGOING_ARGS := y +endif + +# Work around to a bug with asm goto with first implementations of it +# in gcc causing gcc to mess up the push and pop of the stack in some +# uses of asm goto. +ifeq ($(CONFIG_JUMP_LABEL), y) +ADD_ACCUMULATE_OUTGOING_ARGS := y +endif + +cflags-$(ADD_ACCUMULATE_OUTGOING_ARGS) += $(call cc-option,-maccumulate-outgoing-args) # Bug fix for binutils: this option is required in order to keep # binutils from generating NOPL instructions against our will. -- cgit v1.2.2 From 7b79462a20826a7269322113c68ca78d5f67c0bd Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sat, 30 Oct 2010 01:19:29 -0700 Subject: x86: Check irq_remapped instead of remapping_enabled in destroy_irq() Russ Anderson reported: | There is a regression that is causing a NULL pointer dereference | in free_irte when shutting down xpc. git bisect narrowed it down | to git commit d585d06(intr_remap: Simplify the code further), which | changed free_irte(). Reverse applying the patch fixes the problem. We need to use irq_remapped() for each irq instead of checking only intr_remapping_enabled as there might be non remapped irqs even when remapping is enabled. [ tglx: use cfg instead of retrieving it again. Massaged changelog ] Reported-bisected-and-tested-by: Russ Anderson Signed-off-by: Yinghai Lu Cc: Suresh Siddha LKML-Reference: <4CCBD511.40607@kernel.org> Signed-off-by: Thomas Gleixner --- arch/x86/kernel/apic/io_apic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 0929191d83cf..7cc0a721f628 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3109,7 +3109,7 @@ void destroy_irq(unsigned int irq) irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE); - if (intr_remapping_enabled) + if (irq_remapped(cfg)) free_irte(irq); raw_spin_lock_irqsave(&vector_lock, flags); __clear_irq_vector(irq, cfg); -- cgit v1.2.2