Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull more perf updates from Ingo Molnar: "A second round of perf updates: - wide reaching kprobes sanitization and robustization, with the hope of fixing all 'probe this function crashes the kernel' bugs, by Masami Hiramatsu. - uprobes updates from Oleg Nesterov: tmpfs support, corner case fixes and robustization work. - perf tooling updates and fixes from Jiri Olsa, Namhyung Ki, Arnaldo et al: * Add support to accumulate hist periods (Namhyung Kim) * various fixes, refactorings and enhancements" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (101 commits) perf: Differentiate exec() and non-exec() comm events perf: Fix perf_event_comm() vs. exec() assumption uprobes/x86: Rename arch_uprobe->def to ->defparam, minor comment updates perf/documentation: Add description for conditional branch filter perf/x86: Add conditional branch filtering support perf/tool: Add conditional branch filter 'cond' to perf record perf: Add new conditional branch filter 'PERF_SAMPLE_BRANCH_COND' uprobes: Teach copy_insn() to support tmpfs uprobes: Shift ->readpage check from __copy_insn() to uprobe_register() perf/x86: Use common PMU interrupt disabled code perf/ARM: Use common PMU interrupt disabled code perf: Disable sampled events if no PMU interrupt perf: Fix use after free in perf_remove_from_context() perf tools: Fix 'make help' message error perf record: Fix poll return value propagation perf tools: Move elide bool into perf_hpp_fmt struct perf tools: Remove elide setup for SORT_MODE__MEMORY mode perf tools: Fix "==" into "=" in ui_browser__warning assignment perf tools: Allow overriding sysfs and proc finding with env var perf tools: Consider header files outside perf directory in tags target ...
2026-03-06 15:25:10 -08:00 · 2014-06-12 19:18:49 -07:00
parent c29deef32e 82b897782d
commit 3737a12761
81 changed files with 2993 additions and 1196 deletions
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -22,8 +22,9 @@ Appendix B: The kprobes sysctl interface

 Kprobes enables you to dynamically break into any kernel routine and
 collect debugging and performance information non-disruptively. You
-can trap at almost any kernel code address, specifying a handler
+can trap at almost any kernel code address(*), specifying a handler
 routine to be invoked when the breakpoint is hit.
+(*: some parts of the kernel code can not be trapped, see 1.5 Blacklist)

 There are currently three types of probes: kprobes, jprobes, and
 kretprobes (also called return probes).  A kprobe can be inserted
@@ -273,6 +274,19 @@ using one of the following techniques:
 or
 - Execute 'sysctl -w debug.kprobes_optimization=n'

+1.5 Blacklist
+
+Kprobes can probe most of the kernel except itself. This means
+that there are some functions where kprobes cannot probe. Probing
+(trapping) such functions can cause a recursive trap (e.g. double
+fault) or the nested probe handler may never be called.
+Kprobes manages such functions as a blacklist.
+If you want to add a function into the blacklist, you just need
+to (1) include linux/kprobes.h and (2) use NOKPROBE_SYMBOL() macro
+to specify a blacklisted function.
+Kprobes checks the given probe address against the blacklist and
+rejects registering it, if the given address is in the blacklist.
+
 2. Architectures Supported

 Kprobes, jprobes, and return probes are implemented on the following
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -410,7 +410,7 @@ __hw_perf_event_init(struct perf_event *event)
 	 */
 	hwc->config_base	    |= (unsigned long)mapping;

-	if (!hwc->sample_period) {
+	if (!is_sampling_event(event)) {
 		/*
 		 * For non-sampling runs, limit the sample_period to half
 		 * of the counter width. That way, the new counter value
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -126,8 +126,8 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)

 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 	if (irqs < 1) {
-		pr_err("no irqs for PMUs defined\n");
-		return -ENODEV;
+		printk_once("perf/ARM: No irqs for PMU defined, sampling events not supported\n");
+		return 0;
 	}

 	irq = platform_get_irq(pmu_device, 0);
@@ -191,6 +191,10 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 	/* Ensure the PMU has sane values out of reset. */
 	if (cpu_pmu->reset)
 		on_each_cpu(cpu_pmu->reset, cpu_pmu, 1);
+
+	/* If no interrupts available, set the corresponding capability flag */
+	if (!platform_get_irq(cpu_pmu->plat_device, 0))
+		cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 }

 /*
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -57,6 +57,12 @@
 	.long (from) - . ;					\
 	.long (to) - . + 0x7ffffff0 ;				\
 	.popsection
+
+# define _ASM_NOKPROBE(entry)					\
+	.pushsection "_kprobe_blacklist","aw" ;			\
+	_ASM_ALIGN ;						\
+	_ASM_PTR (entry);					\
+	.popsection
 #else
 # define _ASM_EXTABLE(from,to)					\
 	" .pushsection \"__ex_table\",\"a\"\n"			\
@@ -71,6 +77,7 @@
 	" .long (" #from ") - .\n"				\
 	" .long (" #to ") - . + 0x7ffffff0\n"			\
 	" .popsection\n"
+/* For C file, we already have NOKPROBE_SYMBOL macro */
 #endif

 #endif /* _ASM_X86_ASM_H */
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -116,4 +116,6 @@ struct kprobe_ctlblk {
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 extern int kprobe_exceptions_notify(struct notifier_block *self,
 				    unsigned long val, void *data);
+extern int kprobe_int3_handler(struct pt_regs *regs);
+extern int kprobe_debug_handler(struct pt_regs *regs);
 #endif /* _ASM_X86_KPROBES_H */
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -68,7 +68,7 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long);
 dotraplinkage void do_stack_segment(struct pt_regs *, long);
 #ifdef CONFIG_X86_64
 dotraplinkage void do_double_fault(struct pt_regs *, long);
-asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *);
+asmlinkage struct pt_regs *sync_regs(struct pt_regs *);
 #endif
 dotraplinkage void do_general_protection(struct pt_regs *, long);
 dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
@@ -103,7 +103,6 @@ static inline int get_si_code(unsigned long condition)

 extern int panic_on_unrecovered_nmi;

-void math_error(struct pt_regs *, int, int);
 void math_emulate(struct math_emu_info *);
 #ifndef CONFIG_X86_32
 asmlinkage void smp_thermal_interrupt(void);
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -41,18 +41,18 @@ struct arch_uprobe {
 		u8			ixol[MAX_UINSN_BYTES];
 	};

-	u16				fixups;
 	const struct uprobe_xol_ops	*ops;

 	union {
-#ifdef CONFIG_X86_64
-		unsigned long			rip_rela_target_address;
-#endif
 		struct {
 			s32	offs;
 			u8	ilen;
 			u8	opc1;
-		}				branch;
+		}			branch;
+		struct {
+			u8	fixups;
+			u8	ilen;
+		} 			defparam;
 	};
 };

--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -5,7 +5,6 @@
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/stringify.h>
-#include <linux/kprobes.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/memory.h>
@@ -551,7 +550,7 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
 *
 * Note: Must be called under text_mutex.
 */
-void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
+void *text_poke(void *addr, const void *opcode, size_t len)
 {
 	unsigned long flags;
 	char *vaddr;
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -60,7 +60,7 @@ void arch_trigger_all_cpu_backtrace(void)
 	smp_mb__after_atomic();
 }

-static int __kprobes
+static int
 arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
 {
 	int cpu;
@@ -80,6 +80,7 @@ arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)

 	return NMI_DONE;
 }
+NOKPROBE_SYMBOL(arch_trigger_all_cpu_backtrace_handler);

 static int __init register_trigger_all_cpu_backtrace(void)
 {
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -8,6 +8,7 @@
 #include <linux/delay.h>
 #include <linux/sched.h>
 #include <linux/init.h>
+#include <linux/kprobes.h>
 #include <linux/kgdb.h>
 #include <linux/smp.h>
 #include <linux/io.h>
@@ -1193,6 +1194,7 @@ int is_debug_stack(unsigned long addr)
 		(addr <= __get_cpu_var(debug_stack_addr) &&
 		 addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ));
 }
+NOKPROBE_SYMBOL(is_debug_stack);

 DEFINE_PER_CPU(u32, debug_idt_ctr);

@@ -1201,6 +1203,7 @@ void debug_stack_set_zero(void)
 	this_cpu_inc(debug_idt_ctr);
 	load_current_idt();
 }
+NOKPROBE_SYMBOL(debug_stack_set_zero);

 void debug_stack_reset(void)
 {
@@ -1209,6 +1212,7 @@ void debug_stack_reset(void)
 	if (this_cpu_dec_return(debug_idt_ctr) == 0)
 		load_current_idt();
 }
+NOKPROBE_SYMBOL(debug_stack_reset);

 #else	/* CONFIG_X86_64 */

--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -303,15 +303,6 @@ int x86_setup_perfctr(struct perf_event *event)
 		hwc->sample_period = x86_pmu.max_period;
 		hwc->last_period = hwc->sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
-	} else {
-		/*
-		 * If we have a PMU initialized but no APIC
-		 * interrupts, we cannot sample hardware
-		 * events (user-space has to fall back and
-		 * sample via a hrtimer based software event):
-		 */
-		if (!x86_pmu.apic)
-			return -EOPNOTSUPP;
 	}

 	if (attr->type == PERF_TYPE_RAW)
@@ -1293,7 +1284,7 @@ void perf_events_lapic_init(void)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 }

-static int __kprobes
+static int
 perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
 	u64 start_clock;
@@ -1311,6 +1302,7 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)

 	return ret;
 }
+NOKPROBE_SYMBOL(perf_event_nmi_handler);

 struct event_constraint emptyconstraint;
 struct event_constraint unconstrained;
@@ -1366,6 +1358,15 @@ static void __init pmu_check_apic(void)
 	x86_pmu.apic = 0;
 	pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n");
 	pr_info("no hardware sampling interrupt available.\n");
+
+	/*
+	 * If we have a PMU initialized but no APIC
+	 * interrupts, we cannot sample hardware
+	 * events (user-space has to fall back and
+	 * sample via a hrtimer based software event):
+	 */
+	pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 }

 static struct attribute_group x86_pmu_format_group = {
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -593,7 +593,7 @@ out:
 	return 1;
 }

-static int __kprobes
+static int
 perf_ibs_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
 	int handled = 0;
@@ -606,6 +606,7 @@ perf_ibs_nmi_handler(unsigned int cmd, struct pt_regs *regs)

 	return handled;
 }
+NOKPROBE_SYMBOL(perf_ibs_nmi_handler);

 static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name)
 {
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -384,6 +384,9 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 	if (br_type & PERF_SAMPLE_BRANCH_NO_TX)
 		mask |= X86_BR_NO_TX;

+	if (br_type & PERF_SAMPLE_BRANCH_COND)
+		mask |= X86_BR_JCC;
+
 	/*
 	 * stash actual user request into reg, it may
 	 * be used by fixup code for some CPU
@@ -678,6 +681,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
 	 * NHM/WSM erratum: must include IND_JMP to capture IND_CALL
 	 */
 	[PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP,
+	[PERF_SAMPLE_BRANCH_COND]     = LBR_JCC,
 };

 static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
@@ -689,6 +693,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
 	[PERF_SAMPLE_BRANCH_ANY_CALL]	= LBR_REL_CALL | LBR_IND_CALL
 					| LBR_FAR,
 	[PERF_SAMPLE_BRANCH_IND_CALL]	= LBR_IND_CALL,
+	[PERF_SAMPLE_BRANCH_COND]       = LBR_JCC,
 };

 /* core */
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -200,7 +200,7 @@ static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED;
 static int die_owner = -1;
 static unsigned int die_nest_count;

-unsigned __kprobes long oops_begin(void)
+unsigned long oops_begin(void)
 {
 	int cpu;
 	unsigned long flags;
@@ -223,8 +223,9 @@ unsigned __kprobes long oops_begin(void)
 	return flags;
 }
 EXPORT_SYMBOL_GPL(oops_begin);
+NOKPROBE_SYMBOL(oops_begin);

-void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
+void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
 {
 	if (regs && kexec_should_crash(current))
 		crash_kexec(regs);
@@ -247,8 +248,9 @@ void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
 		panic("Fatal exception");
 	do_exit(signr);
 }
+NOKPROBE_SYMBOL(oops_end);

-int __kprobes __die(const char *str, struct pt_regs *regs, long err)
+int __die(const char *str, struct pt_regs *regs, long err)
 {
 #ifdef CONFIG_X86_32
 	unsigned short ss;
@@ -291,6 +293,7 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err)
 #endif
 	return 0;
 }
+NOKPROBE_SYMBOL(__die);

 /*
 * This is gone through when something in the kernel has done something bad
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -314,10 +314,6 @@ ENTRY(ret_from_kernel_thread)
 	CFI_ENDPROC
 ENDPROC(ret_from_kernel_thread)

-/*
- * Interrupt exit functions should be protected against kprobes
- */
-	.pushsection .kprobes.text, "ax"
 /*
 * Return to user mode is not as complex as all this looks,
 * but we want the default path for a system call return to
@@ -372,10 +368,6 @@ need_resched:
 END(resume_kernel)
 #endif
 	CFI_ENDPROC
-/*
- * End of kprobes section
- */
-	.popsection

 /* SYSENTER_RETURN points to after the "sysenter" instruction in
   the vsyscall page.  See vsyscall-sysentry.S, which defines the symbol.  */
@@ -495,10 +487,6 @@ sysexit_audit:
 	PTGS_TO_GS_EX
 ENDPROC(ia32_sysenter_target)

-/*
- * syscall stub including irq exit should be protected against kprobes
- */
-	.pushsection .kprobes.text, "ax"
 	# system call handler stub
 ENTRY(system_call)
 	RING0_INT_FRAME			# can't unwind into user space anyway
@@ -690,10 +678,6 @@ syscall_badsys:
 	jmp resume_userspace
 END(syscall_badsys)
 	CFI_ENDPROC
-/*
- * End of kprobes section
- */
-	.popsection

 .macro FIXUP_ESPFIX_STACK
 /*
@@ -784,10 +768,6 @@ common_interrupt:
 ENDPROC(common_interrupt)
 	CFI_ENDPROC

-/*
- *  Irq entries should be protected against kprobes
- */
-	.pushsection .kprobes.text, "ax"
 #define BUILD_INTERRUPT3(name, nr, fn)	\
 ENTRY(name)				\
 	RING0_INT_FRAME;		\
@@ -964,10 +944,6 @@ ENTRY(spurious_interrupt_bug)
 	jmp error_code
 	CFI_ENDPROC
 END(spurious_interrupt_bug)
-/*
- * End of kprobes section
- */
-	.popsection

 #ifdef CONFIG_XEN
 /* Xen doesn't set %esp to be precisely what the normal sysenter
@@ -1242,11 +1218,6 @@ return_to_handler:
 	jmp *%ecx
 #endif

-/*
- * Some functions should be protected against kprobes
- */
-	.pushsection .kprobes.text, "ax"
-
 #ifdef CONFIG_TRACING
 ENTRY(trace_page_fault)
 	RING0_EC_FRAME
@@ -1460,7 +1431,3 @@ ENTRY(async_page_fault)
 END(async_page_fault)
 #endif

-/*
- * End of kprobes section
- */
-	.popsection
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -284,8 +284,6 @@ ENDPROC(native_usergs_sysret64)
 	TRACE_IRQS_OFF
 	.endm

-/* save complete stack frame */
-	.pushsection .kprobes.text, "ax"
 ENTRY(save_paranoid)
 	XCPT_FRAME 1 RDI+8
 	cld
@@ -314,7 +312,6 @@ ENTRY(save_paranoid)
 1:	ret
 	CFI_ENDPROC
 END(save_paranoid)
-	.popsection

 /*
 * A newly forked process directly context switches into this address.
@@ -772,10 +769,6 @@ END(interrupt)
 	call \func
 	.endm

-/*
- * Interrupt entry/exit should be protected against kprobes
- */
-	.pushsection .kprobes.text, "ax"
 	/*
 	 * The interrupt stubs push (~vector+0x80) onto the stack and
 	 * then jump to common_interrupt.
@@ -982,11 +975,6 @@ END(__do_double_fault)
 # define __do_double_fault do_double_fault
 #endif

-/*
- * End of kprobes section
- */
-       .popsection
-
 /*
 * APIC interrupts.
 */
@@ -1321,11 +1309,6 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
 	hyperv_callback_vector hyperv_vector_handler
 #endif /* CONFIG_HYPERV */

-/*
- * Some functions should be protected against kprobes
- */
-	.pushsection .kprobes.text, "ax"
-
 idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
 idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
 idtentry stack_segment do_stack_segment has_error_code=1 paranoid=1
@@ -1742,7 +1725,3 @@ ENTRY(ignore_sysret)
 	CFI_ENDPROC
 END(ignore_sysret)

-/*
- * End of kprobes section
- */
-	.popsection
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -32,7 +32,6 @@
 #include <linux/irqflags.h>
 #include <linux/notifier.h>
 #include <linux/kallsyms.h>
-#include <linux/kprobes.h>
 #include <linux/percpu.h>
 #include <linux/kdebug.h>
 #include <linux/kernel.h>
@@ -424,7 +423,7 @@ EXPORT_SYMBOL_GPL(hw_breakpoint_restore);
 * NOTIFY_STOP returned for all other cases
 *
 */
-static int __kprobes hw_breakpoint_handler(struct die_args *args)
+static int hw_breakpoint_handler(struct die_args *args)
 {
 	int i, cpu, rc = NOTIFY_STOP;
 	struct perf_event *bp;
@@ -511,7 +510,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 /*
 * Handle debug exception notifications.
 */
-int __kprobes hw_breakpoint_exceptions_notify(
+int hw_breakpoint_exceptions_notify(
 		struct notifier_block *unused, unsigned long val, void *data)
 {
 	if (val != DIE_DEBUG)
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -112,7 +112,8 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = {

 const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist);

-static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
+static nokprobe_inline void
+__synthesize_relative_insn(void *from, void *to, u8 op)
 {
 	struct __arch_relative_insn {
 		u8 op;
@@ -125,21 +126,23 @@ static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
 }

 /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/
-void __kprobes synthesize_reljump(void *from, void *to)
+void synthesize_reljump(void *from, void *to)
 {
 	__synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE);
 }
+NOKPROBE_SYMBOL(synthesize_reljump);

 /* Insert a call instruction at address 'from', which calls address 'to'.*/
-void __kprobes synthesize_relcall(void *from, void *to)
+void synthesize_relcall(void *from, void *to)
 {
 	__synthesize_relative_insn(from, to, RELATIVECALL_OPCODE);
 }
+NOKPROBE_SYMBOL(synthesize_relcall);

 /*
 * Skip the prefixes of the instruction.
 */
-static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn)
+static kprobe_opcode_t *skip_prefixes(kprobe_opcode_t *insn)
 {
 	insn_attr_t attr;

@@ -154,12 +157,13 @@ static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn)
 #endif
 	return insn;
 }
+NOKPROBE_SYMBOL(skip_prefixes);

 /*
 * Returns non-zero if opcode is boostable.
 * RIP relative instructions are adjusted at copying time in 64 bits mode
 */
-int __kprobes can_boost(kprobe_opcode_t *opcodes)
+int can_boost(kprobe_opcode_t *opcodes)
 {
 	kprobe_opcode_t opcode;
 	kprobe_opcode_t *orig_opcodes = opcodes;
@@ -260,7 +264,7 @@ unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long add
 }

 /* Check if paddr is at an instruction boundary */
-static int __kprobes can_probe(unsigned long paddr)
+static int can_probe(unsigned long paddr)
 {
 	unsigned long addr, __addr, offset = 0;
 	struct insn insn;
@@ -299,7 +303,7 @@ static int __kprobes can_probe(unsigned long paddr)
 /*
 * Returns non-zero if opcode modifies the interrupt flag.
 */
-static int __kprobes is_IF_modifier(kprobe_opcode_t *insn)
+static int is_IF_modifier(kprobe_opcode_t *insn)
 {
 	/* Skip prefixes */
 	insn = skip_prefixes(insn);
@@ -322,7 +326,7 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn)
 * If not, return null.
 * Only applicable to 64-bit x86.
 */
-int __kprobes __copy_instruction(u8 *dest, u8 *src)
+int __copy_instruction(u8 *dest, u8 *src)
 {
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
@@ -365,7 +369,7 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src)
 	return insn.length;
 }

-static int __kprobes arch_copy_kprobe(struct kprobe *p)
+static int arch_copy_kprobe(struct kprobe *p)
 {
 	int ret;

@@ -392,7 +396,7 @@ static int __kprobes arch_copy_kprobe(struct kprobe *p)
 	return 0;
 }

-int __kprobes arch_prepare_kprobe(struct kprobe *p)
+int arch_prepare_kprobe(struct kprobe *p)
 {
 	if (alternatives_text_reserved(p->addr, p->addr))
 		return -EINVAL;
@@ -407,17 +411,17 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	return arch_copy_kprobe(p);
 }

-void __kprobes arch_arm_kprobe(struct kprobe *p)
+void arch_arm_kprobe(struct kprobe *p)
 {
 	text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1);
 }

-void __kprobes arch_disarm_kprobe(struct kprobe *p)
+void arch_disarm_kprobe(struct kprobe *p)
 {
 	text_poke(p->addr, &p->opcode, 1);
 }

-void __kprobes arch_remove_kprobe(struct kprobe *p)
+void arch_remove_kprobe(struct kprobe *p)
 {
 	if (p->ainsn.insn) {
 		free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1));
@@ -425,7 +429,8 @@ void __kprobes arch_remove_kprobe(struct kprobe *p)
 	}
 }

-static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
+static nokprobe_inline void
+save_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
 	kcb->prev_kprobe.kp = kprobe_running();
 	kcb->prev_kprobe.status = kcb->kprobe_status;
@@ -433,7 +438,8 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
 	kcb->prev_kprobe.saved_flags = kcb->kprobe_saved_flags;
 }

-static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
+static nokprobe_inline void
+restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
 	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
@@ -441,8 +447,9 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 	kcb->kprobe_saved_flags = kcb->prev_kprobe.saved_flags;
 }

-static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
-				struct kprobe_ctlblk *kcb)
+static nokprobe_inline void
+set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
+		   struct kprobe_ctlblk *kcb)
 {
 	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_saved_flags = kcb->kprobe_old_flags
@@ -451,7 +458,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 		kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF;
 }

-static void __kprobes clear_btf(void)
+static nokprobe_inline void clear_btf(void)
 {
 	if (test_thread_flag(TIF_BLOCKSTEP)) {
 		unsigned long debugctl = get_debugctlmsr();
@@ -461,7 +468,7 @@ static void __kprobes clear_btf(void)
 	}
 }

-static void __kprobes restore_btf(void)
+static nokprobe_inline void restore_btf(void)
 {
 	if (test_thread_flag(TIF_BLOCKSTEP)) {
 		unsigned long debugctl = get_debugctlmsr();
@@ -471,8 +478,7 @@ static void __kprobes restore_btf(void)
 	}
 }

-void __kprobes
-arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
+void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	unsigned long *sara = stack_addr(regs);

@@ -481,9 +487,10 @@ arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 	/* Replace the return addr with trampoline addr */
 	*sara = (unsigned long) &kretprobe_trampoline;
 }
+NOKPROBE_SYMBOL(arch_prepare_kretprobe);

-static void __kprobes
-setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter)
+static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
+			     struct kprobe_ctlblk *kcb, int reenter)
 {
 	if (setup_detour_execution(p, regs, reenter))
 		return;
@@ -519,22 +526,24 @@ setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *k
 	else
 		regs->ip = (unsigned long)p->ainsn.insn;
 }
+NOKPROBE_SYMBOL(setup_singlestep);

 /*
 * We have reentered the kprobe_handler(), since another probe was hit while
 * within the handler. We save the original kprobes variables and just single
 * step on the instruction of the new probe without calling any user handlers.
 */
-static int __kprobes
-reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
+static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
+			  struct kprobe_ctlblk *kcb)
 {
 	switch (kcb->kprobe_status) {
 	case KPROBE_HIT_SSDONE:
 	case KPROBE_HIT_ACTIVE:
+	case KPROBE_HIT_SS:
 		kprobes_inc_nmissed_count(p);
 		setup_singlestep(p, regs, kcb, 1);
 		break;
-	case KPROBE_HIT_SS:
+	case KPROBE_REENTER:
 		/* A probe has been hit in the codepath leading up to, or just
 		 * after, single-stepping of a probed instruction. This entire
 		 * codepath should strictly reside in .kprobes.text section.
@@ -553,12 +562,13 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb

 	return 1;
 }
+NOKPROBE_SYMBOL(reenter_kprobe);

 /*
 * Interrupts are disabled on entry as trap3 is an interrupt gate and they
 * remain disabled throughout this function.
 */
-static int __kprobes kprobe_handler(struct pt_regs *regs)
+int kprobe_int3_handler(struct pt_regs *regs)
 {
 	kprobe_opcode_t *addr;
 	struct kprobe *p;
@@ -621,12 +631,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	preempt_enable_no_resched();
 	return 0;
 }
+NOKPROBE_SYMBOL(kprobe_int3_handler);

 /*
 * When a retprobed function returns, this code saves registers and
 * calls trampoline_handler() runs, which calls the kretprobe's handler.
 */
-static void __used __kprobes kretprobe_trampoline_holder(void)
+static void __used kretprobe_trampoline_holder(void)
 {
 	asm volatile (
 			".global kretprobe_trampoline\n"
@@ -657,11 +668,13 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 #endif
 			"	ret\n");
 }
+NOKPROBE_SYMBOL(kretprobe_trampoline_holder);
+NOKPROBE_SYMBOL(kretprobe_trampoline);

 /*
 * Called from kretprobe_trampoline
 */
-__visible __used __kprobes void *trampoline_handler(struct pt_regs *regs)
+__visible __used void *trampoline_handler(struct pt_regs *regs)
 {
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
@@ -747,6 +760,7 @@ __visible __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	}
 	return (void *)orig_ret_address;
 }
+NOKPROBE_SYMBOL(trampoline_handler);

 /*
 * Called after single-stepping.  p->addr is the address of the
@@ -775,8 +789,8 @@ __visible __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 * jump instruction after the copied instruction, that jumps to the next
 * instruction after the probepoint.
 */
-static void __kprobes
-resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
+static void resume_execution(struct kprobe *p, struct pt_regs *regs,
+			     struct kprobe_ctlblk *kcb)
 {
 	unsigned long *tos = stack_addr(regs);
 	unsigned long copy_ip = (unsigned long)p->ainsn.insn;
@@ -851,12 +865,13 @@ resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *k
 no_change:
 	restore_btf();
 }
+NOKPROBE_SYMBOL(resume_execution);

 /*
 * Interrupts are disabled on entry as trap1 is an interrupt gate and they
 * remain disabled throughout this function.
 */
-static int __kprobes post_kprobe_handler(struct pt_regs *regs)
+int kprobe_debug_handler(struct pt_regs *regs)
 {
 	struct kprobe *cur = kprobe_running();
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
@@ -891,8 +906,9 @@ out:

 	return 1;
 }
+NOKPROBE_SYMBOL(kprobe_debug_handler);

-int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 {
 	struct kprobe *cur = kprobe_running();
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
@@ -949,12 +965,13 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)

 	return 0;
 }
+NOKPROBE_SYMBOL(kprobe_fault_handler);

 /*
 * Wrapper routine for handling exceptions.
 */
-int __kprobes
-kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data)
+int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
+			     void *data)
 {
 	struct die_args *args = data;
 	int ret = NOTIFY_DONE;
@@ -962,22 +979,7 @@ kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *d
 	if (args->regs && user_mode_vm(args->regs))
 		return ret;

-	switch (val) {
-	case DIE_INT3:
-		if (kprobe_handler(args->regs))
-			ret = NOTIFY_STOP;
-		break;
-	case DIE_DEBUG:
-		if (post_kprobe_handler(args->regs)) {
-			/*
-			 * Reset the BS bit in dr6 (pointed by args->err) to
-			 * denote completion of processing
-			 */
-			(*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP;
-			ret = NOTIFY_STOP;
-		}
-		break;
-	case DIE_GPF:
+	if (val == DIE_GPF) {
 		/*
 		 * To be potentially processing a kprobe fault and to
 		 * trust the result from kprobe_running(), we have
@@ -986,14 +988,12 @@ kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *d
 		if (!preemptible() && kprobe_running() &&
 		    kprobe_fault_handler(args->regs, args->trapnr))
 			ret = NOTIFY_STOP;
-		break;
-	default:
-		break;
 	}
 	return ret;
 }
+NOKPROBE_SYMBOL(kprobe_exceptions_notify);

-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
+int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct jprobe *jp = container_of(p, struct jprobe, kp);
 	unsigned long addr;
@@ -1017,8 +1017,9 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->ip = (unsigned long)(jp->entry);
 	return 1;
 }
+NOKPROBE_SYMBOL(setjmp_pre_handler);

-void __kprobes jprobe_return(void)
+void jprobe_return(void)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();

@@ -1034,8 +1035,10 @@ void __kprobes jprobe_return(void)
 			"       nop			\n"::"b"
 			(kcb->jprobe_saved_sp):"memory");
 }
+NOKPROBE_SYMBOL(jprobe_return);
+NOKPROBE_SYMBOL(jprobe_return_end);

-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
+int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	u8 *addr = (u8 *) (regs->ip - 1);
@@ -1063,13 +1066,22 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	}
 	return 0;
 }
+NOKPROBE_SYMBOL(longjmp_break_handler);
+
+bool arch_within_kprobe_blacklist(unsigned long addr)
+{
+	return  (addr >= (unsigned long)__kprobes_text_start &&
+		 addr < (unsigned long)__kprobes_text_end) ||
+		(addr >= (unsigned long)__entry_text_start &&
+		 addr < (unsigned long)__entry_text_end);
+}

 int __init arch_init_kprobes(void)
 {
 	return 0;
 }

-int __kprobes arch_trampoline_kprobe(struct kprobe *p)
+int arch_trampoline_kprobe(struct kprobe *p)
 {
 	return 0;
 }
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -25,8 +25,9 @@

 #include "common.h"

-static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			     struct kprobe_ctlblk *kcb)
+static nokprobe_inline
+int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+		      struct kprobe_ctlblk *kcb)
 {
 	/*
 	 * Emulate singlestep (and also recover regs->ip)
@@ -41,18 +42,19 @@ static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
 	return 1;
 }

-int __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			      struct kprobe_ctlblk *kcb)
+int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+		    struct kprobe_ctlblk *kcb)
 {
 	if (kprobe_ftrace(p))
 		return __skip_singlestep(p, regs, kcb);
 	else
 		return 0;
 }
+NOKPROBE_SYMBOL(skip_singlestep);

 /* Ftrace callback handler for kprobes */
-void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-				     struct ftrace_ops *ops, struct pt_regs *regs)
+void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+			   struct ftrace_ops *ops, struct pt_regs *regs)
 {
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
@@ -84,8 +86,9 @@ void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 end:
 	local_irq_restore(flags);
 }
+NOKPROBE_SYMBOL(kprobe_ftrace_handler);

-int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p)
+int arch_prepare_kprobe_ftrace(struct kprobe *p)
 {
 	p->ainsn.insn = NULL;
 	p->ainsn.boostable = -1;
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -77,7 +77,7 @@ found:
 }

 /* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */
-static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val)
+static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val)
 {
 #ifdef CONFIG_X86_64
 	*addr++ = 0x48;
@@ -138,7 +138,8 @@ asm (
 #define INT3_SIZE sizeof(kprobe_opcode_t)

 /* Optimized kprobe call back function: called from optinsn */
-static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
+static void
+optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	unsigned long flags;
@@ -168,8 +169,9 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_
 	}
 	local_irq_restore(flags);
 }
+NOKPROBE_SYMBOL(optimized_callback);

-static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
+static int copy_optimized_instructions(u8 *dest, u8 *src)
 {
 	int len = 0, ret;

@@ -189,7 +191,7 @@ static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
 }

 /* Check whether insn is indirect jump */
-static int __kprobes insn_is_indirect_jump(struct insn *insn)
+static int insn_is_indirect_jump(struct insn *insn)
 {
 	return ((insn->opcode.bytes[0] == 0xff &&
 		(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
@@ -224,7 +226,7 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
 }

 /* Decode whole function to ensure any instructions don't jump into target */
-static int __kprobes can_optimize(unsigned long paddr)
+static int can_optimize(unsigned long paddr)
 {
 	unsigned long addr, size = 0, offset = 0;
 	struct insn insn;
@@ -275,7 +277,7 @@ static int __kprobes can_optimize(unsigned long paddr)
 }

 /* Check optimized_kprobe can actually be optimized. */
-int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op)
+int arch_check_optimized_kprobe(struct optimized_kprobe *op)
 {
 	int i;
 	struct kprobe *p;
@@ -290,15 +292,15 @@ int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op)
 }

 /* Check the addr is within the optimized instructions. */
-int __kprobes
-arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr)
+int arch_within_optimized_kprobe(struct optimized_kprobe *op,
+				 unsigned long addr)
 {
 	return ((unsigned long)op->kp.addr <= addr &&
 		(unsigned long)op->kp.addr + op->optinsn.size > addr);
 }

 /* Free optimized instruction slot */
-static __kprobes
+static
 void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
 {
 	if (op->optinsn.insn) {
@@ -308,7 +310,7 @@ void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
 	}
 }

-void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op)
+void arch_remove_optimized_kprobe(struct optimized_kprobe *op)
 {
 	__arch_remove_optimized_kprobe(op, 1);
 }
@@ -318,7 +320,7 @@ void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op)
 * Target instructions MUST be relocatable (checked inside)
 * This is called when new aggr(opt)probe is allocated or reused.
 */
-int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
+int arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
 {
 	u8 *buf;
 	int ret;
@@ -372,7 +374,7 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
 * Replace breakpoints (int3) with relative jumps.
 * Caller must call with locking kprobe_mutex and text_mutex.
 */
-void __kprobes arch_optimize_kprobes(struct list_head *oplist)
+void arch_optimize_kprobes(struct list_head *oplist)
 {
 	struct optimized_kprobe *op, *tmp;
 	u8 insn_buf[RELATIVEJUMP_SIZE];
@@ -398,7 +400,7 @@ void __kprobes arch_optimize_kprobes(struct list_head *oplist)
 }

 /* Replace a relative jump with a breakpoint (int3).  */
-void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
+void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
 	u8 insn_buf[RELATIVEJUMP_SIZE];

@@ -424,8 +426,7 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist,
 	}
 }

-int  __kprobes
-setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
+int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
 {
 	struct optimized_kprobe *op;

@@ -441,3 +442,4 @@ setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
 	}
 	return 0;
 }
+NOKPROBE_SYMBOL(setup_detour_execution);
--- a/Show More
+++ b/Show More