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

…inux/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

arch/powerpc/kernel/vmlinux.lds.S

@@ -90,6 +90,7 @@ SECTIONS
 #ifdef CONFIG_PPC64
 		*(.tramp.ftrace.text);
 #endif
+		NOINSTR_TEXT
 		SCHED_TEXT
 		CPUIDLE_TEXT
 		LOCK_TEXT

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 */

include/asm-generic/vmlinux.lds.h

@@ -540,6 +540,15 @@
 	. = ALIGN((align));						\
 	__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*)						\

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

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

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? */

kernel/kprobes.c

@@ -2179,6 +2179,24 @@ int kprobe_add_area_blacklist(unsigned long start, unsigned long end)
 	return 0;
 }
 
+/* Remove all symbols in given area from kprobe blacklist */
+static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end)
+{
+	struct kprobe_blacklist_entry *ent, *n;
+
+	list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) {
+		if (ent->start_addr < start || ent->start_addr >= end)
+			continue;
+		list_del(&ent->list);
+		kfree(ent);
+	}
+}
+
+static void kprobe_remove_ksym_blacklist(unsigned long entry)
+{
+	kprobe_remove_area_blacklist(entry, entry + 1);
+}
+
 int __init __weak arch_populate_kprobe_blacklist(void)
 {
 	return 0;
@@ -2211,10 +2229,62 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
 	/* Symbols in __kprobes_text are blacklisted */
 	ret = kprobe_add_area_blacklist((unsigned long)__kprobes_text_start,
 					(unsigned long)__kprobes_text_end);
+	if (ret)
+		return ret;
+
+	/* Symbols in noinstr section are blacklisted */
+	ret = kprobe_add_area_blacklist((unsigned long)__noinstr_text_start,
+					(unsigned long)__noinstr_text_end);
 
 	return ret ? : arch_populate_kprobe_blacklist();
 }
 
+static void add_module_kprobe_blacklist(struct module *mod)
+{
+	unsigned long start, end;
+	int i;
+
+	if (mod->kprobe_blacklist) {
+		for (i = 0; i < mod->num_kprobe_blacklist; i++)
+			kprobe_add_ksym_blacklist(mod->kprobe_blacklist[i]);
+	}
+
+	start = (unsigned long)mod->kprobes_text_start;
+	if (start) {
+		end = start + mod->kprobes_text_size;
+		kprobe_add_area_blacklist(start, end);
+	}
+
+	start = (unsigned long)mod->noinstr_text_start;
+	if (start) {
+		end = start + mod->noinstr_text_size;
+		kprobe_add_area_blacklist(start, end);
+	}
+}
+
+static void remove_module_kprobe_blacklist(struct module *mod)
+{
+	unsigned long start, end;
+	int i;
+
+	if (mod->kprobe_blacklist) {
+		for (i = 0; i < mod->num_kprobe_blacklist; i++)
+			kprobe_remove_ksym_blacklist(mod->kprobe_blacklist[i]);
+	}
+
+	start = (unsigned long)mod->kprobes_text_start;
+	if (start) {
+		end = start + mod->kprobes_text_size;
+		kprobe_remove_area_blacklist(start, end);
+	}
+
+	start = (unsigned long)mod->noinstr_text_start;
+	if (start) {
+		end = start + mod->noinstr_text_size;
+		kprobe_remove_area_blacklist(start, end);
+	}
+}
+
 /* Module notifier call back, checking kprobes on the module */
 static int kprobes_module_callback(struct notifier_block *nb,
 				   unsigned long val, void *data)
@@ -2225,6 +2295,11 @@ static int kprobes_module_callback(struct notifier_block *nb,
 	unsigned int i;
 	int checkcore = (val == MODULE_STATE_GOING);
 
+	if (val == MODULE_STATE_COMING) {
+		mutex_lock(&kprobe_mutex);
+		add_module_kprobe_blacklist(mod);
+		mutex_unlock(&kprobe_mutex);
+	}
 	if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE)
 		return NOTIFY_DONE;
 
@@ -2255,6 +2330,8 @@ static int kprobes_module_callback(struct notifier_block *nb,
 				kill_kprobe(p);
 			}
 	}
+	if (val == MODULE_STATE_GOING)
+		remove_module_kprobe_blacklist(mod);
 	mutex_unlock(&kprobe_mutex);
 	return NOTIFY_DONE;
 }
@@ -2420,6 +2497,7 @@ static const struct file_operations debugfs_kprobes_operations = {
 /* kprobes/blacklist -- shows which functions can not be probed */
 static void *kprobe_blacklist_seq_start(struct seq_file *m, loff_t *pos)
 {
+	mutex_lock(&kprobe_mutex);
 	return seq_list_start(&kprobe_blacklist, *pos);
 }
 
@@ -2446,10 +2524,15 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
 	return 0;
 }
 
+static void kprobe_blacklist_seq_stop(struct seq_file *f, void *v)
+{
+	mutex_unlock(&kprobe_mutex);
+}
+
 static const struct seq_operations kprobe_blacklist_seq_ops = {
 	.start = kprobe_blacklist_seq_start,
 	.next  = kprobe_blacklist_seq_next,
-	.stop  = kprobe_seq_stop,	/* Reuse void function */
+	.stop  = kprobe_blacklist_seq_stop,
 	.show  = kprobe_blacklist_seq_show,
 };
 

kernel/module.c

@@ -3150,6 +3150,9 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 	}
 #endif
 
+	mod->noinstr_text_start = section_objs(info, ".noinstr.text", 1,
+						&mod->noinstr_text_size);
+
 #ifdef CONFIG_TRACEPOINTS
 	mod->tracepoints_ptrs = section_objs(info, "__tracepoints_ptrs",
 					     sizeof(*mod->tracepoints_ptrs),
@@ -3193,6 +3196,13 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 	mod->ei_funcs = section_objs(info, "_error_injection_whitelist",
 					    sizeof(*mod->ei_funcs),
 					    &mod->num_ei_funcs);
+#endif
+#ifdef CONFIG_KPROBES
+	mod->kprobes_text_start = section_objs(info, ".kprobes.text", 1,
+						&mod->kprobes_text_size);
+	mod->kprobe_blacklist = section_objs(info, "_kprobe_blacklist",
+						sizeof(unsigned long),
+						&mod->num_kprobe_blacklist);
 #endif
 	mod->extable = section_objs(info, "__ex_table",
 				    sizeof(*mod->extable), &mod->num_exentries);

samples/kprobes/kprobe_example.c

@@ -25,7 +25,7 @@ static struct kprobe kp = {
 };
 
 /* kprobe pre_handler: called just before the probed instruction is executed */
-static int handler_pre(struct kprobe *p, struct pt_regs *regs)
+static int __kprobes handler_pre(struct kprobe *p, struct pt_regs *regs)
 {
 #ifdef CONFIG_X86
 	pr_info("<%s> pre_handler: p->addr = 0x%p, ip = %lx, flags = 0x%lx\n",
@@ -54,7 +54,7 @@ static int handler_pre(struct kprobe *p, struct pt_regs *regs)
 }
 
 /* kprobe post_handler: called after the probed instruction is executed */
-static void handler_post(struct kprobe *p, struct pt_regs *regs,
+static void __kprobes handler_post(struct kprobe *p, struct pt_regs *regs,
 				unsigned long flags)
 {
 #ifdef CONFIG_X86
@@ -90,6 +90,8 @@ static int handler_fault(struct kprobe *p, struct pt_regs *regs, int trapnr)
 	/* Return 0 because we don't handle the fault. */
 	return 0;
 }
+/* NOKPROBE_SYMBOL() is also available */
+NOKPROBE_SYMBOL(handler_fault);
 
 static int __init kprobe_init(void)
 {

samples/kprobes/kretprobe_example.c

@@ -48,6 +48,7 @@ static int entry_handler(struct kretprobe_instance *ri, struct pt_regs *regs)
 	data->entry_stamp = ktime_get();
 	return 0;
 }
+NOKPROBE_SYMBOL(entry_handler);
 
 /*
  * Return-probe handler: Log the return value and duration. Duration may turn
@@ -67,6 +68,7 @@ static int ret_handler(struct kretprobe_instance *ri, struct pt_regs *regs)
 			func_name, retval, (long long)delta);
 	return 0;
 }
+NOKPROBE_SYMBOL(ret_handler);
 
 static struct kretprobe my_kretprobe = {
 	.handler		= ret_handler,

scripts/mod/modpost.c

@@ -948,7 +948,7 @@ 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"