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

…nux/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
  ...

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

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

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;
 }
 
 /*

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 */

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 */

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);

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;
 	};
 };
 

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;

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)
 {

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 */
 

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 = {

arch/x86/kernel/cpu/perf_event_amd_ibs.c

@@ -593,7 +593,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 	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)
 {

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 */

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