Merge tag 'core-kprobes-2020-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull kprobes updates from Ingo Molnar:
 "Various kprobes updates, mostly centered around cleaning up the
  no-instrumentation logic.

  Instead of the current per debug facility blacklist, use the more
  generic .noinstr.text approach, combined with a 'noinstr' marker for
  functions.

  Also add instrumentation_begin()/end() to better manage the exact
  place in entry code where instrumentation may be used.

  And add a kprobes blacklist for modules"

* tag 'core-kprobes-2020-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  kprobes: Prevent probes in .noinstr.text section
  vmlinux.lds.h: Create section for protection against instrumentation
  samples/kprobes: Add __kprobes and NOKPROBE_SYMBOL() for handlers.
  kprobes: Support NOKPROBE_SYMBOL() in modules
  kprobes: Support __kprobes blacklist in modules
  kprobes: Lock kprobe_mutex while showing kprobe_blacklist

5 files changed, 78 insertions, 0 deletions

diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index d1779d442aa5..66397ed10acb 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 71e387a5fe90..db600ef218d7 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -541,6 +541,15 @@
 	__end_rodata = .;
 
 /*
+ * 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
  *
@@ -551,6 +560,7 @@
 #define TEXT_TEXT							\
 		ALIGN_FUNCTION();					\
 		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely)	\
+		NOINSTR_TEXT						\
 		*(.text..refcount)					\
 		*(.ref.text)						\
 	MEM_KEEP(init.text*)						\
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 448c91bf543b..6325d64e3c3b 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -120,12 +120,65 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 /* Annotate a C jump table to allow objtool to follow the code flow */
 #define __annotate_jump_table __section(.rodata..c_jump_table)
 
+#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()
 #define __annotate_jump_table
 #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 e970f97a7fcb..5da257cbebf1 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -118,6 +118,10 @@ struct ftrace_likely_data {
 #define notrace			__attribute__((__no_instrument_function__))
 #endif
 
+/* Section for code which can't be instrumented at all */
+#define noinstr								\
+	noinline notrace __attribute((__section__(".noinstr.text")))
+
 /*
  * 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/include/linux/module.h b/include/linux/module.h
index 1ad393e62bef..d849d06e4d44 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -458,6 +458,8 @@ struct module {
 	void __percpu *percpu;
 	unsigned int percpu_size;
 #endif
+	void *noinstr_text_start;
+	unsigned int noinstr_text_size;
 
 #ifdef CONFIG_TRACEPOINTS
 	unsigned int num_tracepoints;
@@ -489,6 +491,12 @@ struct module {
 	unsigned int num_ftrace_callsites;
 	unsigned long *ftrace_callsites;
 #endif
+#ifdef CONFIG_KPROBES
+	void *kprobes_text_start;
+	unsigned int kprobes_text_size;
+	unsigned long *kprobe_blacklist;
+	unsigned int num_kprobe_blacklist;
+#endif
 
 #ifdef CONFIG_LIVEPATCH
 	bool klp; /* Is this a livepatch module? */