From: Thomas Gleixner <tglx@xxxxxxxxxxxxx> commit 6553896666433e7efec589838b400a2a652b3ffa upstream. Some code pathes, especially the low level entry code, must be protected against instrumentation for various reasons: - Low level entry code can be a fragile beast, especially on x86. - With NO_HZ_FULL RCU state needs to be established before using it. Having a dedicated section for such code allows to validate with tooling that no unsafe functions are invoked. Add the .noinstr.text section and the noinstr attribute to mark functions. noinstr implies notrace. Kprobes will gain a section check later. Provide also a set of markers: instrumentation_begin()/end() These are used to mark code inside a noinstr function which calls into regular instrumentable text section as safe. The instrumentation markers are only active when CONFIG_DEBUG_ENTRY is enabled as the end marker emits a NOP to prevent the compiler from merging the annotation points. This means the objtool verification requires a kernel compiled with this option. Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Reviewed-by: Alexandre Chartre <alexandre.chartre@xxxxxxxxxx> Acked-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Link: https://lkml.kernel.org/r/20200505134100.075416272@xxxxxxxxxxxxx [Nicolas: Guard noinstr macro in include/linux/compiler_types.h in __KERNEL__ && !__ASSEMBLY__, otherwise noinstr is expanded in the linker script construct. Upstream does not have this problem as many macros were moved by commit 71391bdd2e9a ("include/linux/compiler_types.h: don't pollute userspace with macro definitions"). We take the minimal approach here and just guard the new macro. Minor context conflicts in: arch/powerpc/kernel/vmlinux.lds.S include/asm-generic/vmlinux.lds.h include/linux/compiler.h] Signed-off-by: Nicolas Boichat <drinkcat@xxxxxxxxxxxx> --- Technically guarding with !__ASSEMBLY__ should be enough, but there seems to be no reason to expose this new macro when !__KERNEL__, so let's just match what upstream does. Changes in v2: - Guard noinstr macro by __KERNEL__ && !__ASSEMBLY__ to prevent expansion in linker script and match upstream. arch/powerpc/kernel/vmlinux.lds.S | 1 + include/asm-generic/sections.h | 3 ++ include/asm-generic/vmlinux.lds.h | 10 ++++++ include/linux/compiler.h | 54 +++++++++++++++++++++++++++++++ include/linux/compiler_types.h | 6 ++++ scripts/mod/modpost.c | 2 +- 6 files changed, 75 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 695432965f20..9b346f3d2814 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -99,6 +99,7 @@ SECTIONS #endif /* careful! __ftr_alt_* sections need to be close to .text */ *(.text.hot TEXT_MAIN .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text); + NOINSTR_TEXT SCHED_TEXT CPUIDLE_TEXT LOCK_TEXT diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index 849cd8eb5ca0..ea5987bb0b84 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -53,6 +53,9 @@ extern char __ctors_start[], __ctors_end[]; /* Start and end of .opd section - used for function descriptors. */ extern char __start_opd[], __end_opd[]; +/* Start and end of instrumentation protected text section */ +extern char __noinstr_text_start[], __noinstr_text_end[]; + extern __visible const void __nosave_begin, __nosave_end; /* Function descriptor handling (if any). Override in asm/sections.h */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 2d632a74cc5e..88484ee023ca 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -482,6 +482,15 @@ __security_initcall_end = .; \ } +/* + * Non-instrumentable text section + */ +#define NOINSTR_TEXT \ + ALIGN_FUNCTION(); \ + __noinstr_text_start = .; \ + *(.noinstr.text) \ + __noinstr_text_end = .; + /* * .text section. Map to function alignment to avoid address changes * during second ld run in second ld pass when generating System.map @@ -496,6 +505,7 @@ *(TEXT_MAIN .text.fixup) \ *(.text.unlikely .text.unlikely.*) \ *(.text.unknown .text.unknown.*) \ + NOINSTR_TEXT \ *(.text..refcount) \ *(.ref.text) \ MEM_KEEP(init.text*) \ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 6b6505e3b2c7..6a53300cbd1e 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -129,11 +129,65 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, ".pushsection .discard.unreachable\n\t" \ ".long 999b - .\n\t" \ ".popsection\n\t" + +#ifdef CONFIG_DEBUG_ENTRY +/* Begin/end of an instrumentation safe region */ +#define instrumentation_begin() ({ \ + asm volatile("%c0:\n\t" \ + ".pushsection .discard.instr_begin\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__COUNTER__)); \ +}) + +/* + * Because instrumentation_{begin,end}() can nest, objtool validation considers + * _begin() a +1 and _end() a -1 and computes a sum over the instructions. + * When the value is greater than 0, we consider instrumentation allowed. + * + * There is a problem with code like: + * + * noinstr void foo() + * { + * instrumentation_begin(); + * ... + * if (cond) { + * instrumentation_begin(); + * ... + * instrumentation_end(); + * } + * bar(); + * instrumentation_end(); + * } + * + * If instrumentation_end() would be an empty label, like all the other + * annotations, the inner _end(), which is at the end of a conditional block, + * would land on the instruction after the block. + * + * If we then consider the sum of the !cond path, we'll see that the call to + * bar() is with a 0-value, even though, we meant it to happen with a positive + * value. + * + * To avoid this, have _end() be a NOP instruction, this ensures it will be + * part of the condition block and does not escape. + */ +#define instrumentation_end() ({ \ + asm volatile("%c0: nop\n\t" \ + ".pushsection .discard.instr_end\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__COUNTER__)); \ +}) +#endif /* CONFIG_DEBUG_ENTRY */ + #else #define annotate_reachable() #define annotate_unreachable() #endif +#ifndef instrumentation_begin +#define instrumentation_begin() do { } while(0) +#define instrumentation_end() do { } while(0) +#endif + #ifndef ASM_UNREACHABLE # define ASM_UNREACHABLE #endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 2b8ed70c4c77..c01100318b25 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -234,6 +234,12 @@ struct ftrace_likely_data { #define notrace __attribute__((no_instrument_function)) #endif +#if defined(__KERNEL__) && !defined(__ASSEMBLY__) +/* Section for code which can't be instrumented at all */ +#define noinstr \ + noinline notrace __attribute((__section__(".noinstr.text"))) +#endif + /* * it doesn't make sense on ARM (currently the only user of __naked) * to trace naked functions because then mcount is called without diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 91a80036c05d..7c693bd775c1 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -895,7 +895,7 @@ static void check_section(const char *modname, struct elf_info *elf, #define DATA_SECTIONS ".data", ".data.rel" #define TEXT_SECTIONS ".text", ".text.unlikely", ".sched.text", \ - ".kprobes.text", ".cpuidle.text" + ".kprobes.text", ".cpuidle.text", ".noinstr.text" #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \ ".fixup", ".entry.text", ".exception.text", ".text.*", \ ".coldtext" -- 2.31.0.rc2.261.g7f71774620-goog
