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 ...
2014-06-12 19:18:49 -07:00
parent c29deef32e 82b897782d
commit 3737a12761
81 changed files with 2993 additions and 1196 deletions
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -109,6 +109,15 @@
 #define BRANCH_PROFILE()
 #endif

+#ifdef CONFIG_KPROBES
+#define KPROBE_BLACKLIST()	. = ALIGN(8);				      \
+				VMLINUX_SYMBOL(__start_kprobe_blacklist) = .; \
+				*(_kprobe_blacklist)			      \
+				VMLINUX_SYMBOL(__stop_kprobe_blacklist) = .;
+#else
+#define KPROBE_BLACKLIST()
+#endif
+
 #ifdef CONFIG_EVENT_TRACING
 #define FTRACE_EVENTS()	. = ALIGN(8);					\
 			VMLINUX_SYMBOL(__start_ftrace_events) = .;	\
@@ -478,6 +487,7 @@
 	*(.init.rodata)							\
 	FTRACE_EVENTS()							\
 	TRACE_SYSCALLS()						\
+	KPROBE_BLACKLIST()						\
 	MEM_DISCARD(init.rodata)					\
 	CLK_OF_TABLES()							\
 	RESERVEDMEM_OF_TABLES()						\
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -383,7 +383,9 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 /* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */
 #ifdef CONFIG_KPROBES
 # define __kprobes	__attribute__((__section__(".kprobes.text")))
+# define nokprobe_inline	__always_inline
 #else
 # define __kprobes
+# define nokprobe_inline	inline
 #endif
 #endif /* __LINUX_COMPILER_H */
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -205,10 +205,10 @@ struct kretprobe_blackpoint {
 	void *addr;
 };

-struct kprobe_blackpoint {
-	const char *name;
+struct kprobe_blacklist_entry {
+	struct list_head list;
 	unsigned long start_addr;
-	unsigned long range;
+	unsigned long end_addr;
 };

 #ifdef CONFIG_KPROBES
@@ -265,6 +265,7 @@ extern void arch_disarm_kprobe(struct kprobe *p);
 extern int arch_init_kprobes(void);
 extern void show_registers(struct pt_regs *regs);
 extern void kprobes_inc_nmissed_count(struct kprobe *p);
+extern bool arch_within_kprobe_blacklist(unsigned long addr);

 struct kprobe_insn_cache {
 	struct mutex mutex;
@@ -476,4 +477,18 @@ static inline int enable_jprobe(struct jprobe *jp)
 	return enable_kprobe(&jp->kp);
 }

+#ifdef CONFIG_KPROBES
+/*
+ * Blacklist ganerating macro. Specify functions which is not probed
+ * by using this macro.
+ */
+#define __NOKPROBE_SYMBOL(fname)			\
+static unsigned long __used				\
+	__attribute__((section("_kprobe_blacklist")))	\
+	_kbl_addr_##fname = (unsigned long)fname;
+#define NOKPROBE_SYMBOL(fname)	__NOKPROBE_SYMBOL(fname)
+#else
+#define NOKPROBE_SYMBOL(fname)
+#endif
+
 #endif /* _LINUX_KPROBES_H */
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -166,6 +166,11 @@ struct perf_event;
 */
 #define PERF_EVENT_TXN 0x1

+/**
+ * pmu::capabilities flags
+ */
+#define PERF_PMU_CAP_NO_INTERRUPT		0x01
+
 /**
 * struct pmu - generic performance monitoring unit
 */
@@ -178,6 +183,11 @@ struct pmu {
 	const char			*name;
 	int				type;

+	/*
+	 * various common per-pmu feature flags
+	 */
+	int				capabilities;
+
 	int * __percpu			pmu_disable_count;
 	struct perf_cpu_context * __percpu pmu_cpu_context;
 	int				task_ctx_nr;
@@ -696,7 +706,8 @@ extern struct perf_guest_info_callbacks *perf_guest_cbs;
 extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
 extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);

-extern void perf_event_comm(struct task_struct *tsk);
+extern void perf_event_exec(void);
+extern void perf_event_comm(struct task_struct *tsk, bool exec);
 extern void perf_event_fork(struct task_struct *tsk);

 /* Callchains */
@@ -773,7 +784,7 @@ extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
 extern int __perf_event_disable(void *info);
 extern void perf_event_task_tick(void);
-#else
+#else /* !CONFIG_PERF_EVENTS: */
 static inline void
 perf_event_task_sched_in(struct task_struct *prev,
 			 struct task_struct *task)			{ }
@@ -803,7 +814,8 @@ static inline int perf_unregister_guest_info_callbacks
 (struct perf_guest_info_callbacks *callbacks)				{ return 0; }

 static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
-static inline void perf_event_comm(struct task_struct *tsk)		{ }
+static inline void perf_event_exec(void)				{ }
+static inline void perf_event_comm(struct task_struct *tsk, bool exec)	{ }
 static inline void perf_event_fork(struct task_struct *tsk)		{ }
 static inline void perf_event_init(void)				{ }
 static inline int  perf_swevent_get_recursion_context(void)		{ return -1; }
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2421,7 +2421,11 @@ extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, i
 struct task_struct *fork_idle(int);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);

-extern void set_task_comm(struct task_struct *tsk, const char *from);
+extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);
+static inline void set_task_comm(struct task_struct *tsk, const char *from)
+{
+	__set_task_comm(tsk, from, false);
+}
 extern char *get_task_comm(char *to, struct task_struct *tsk);

 #ifdef CONFIG_SMP
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -103,6 +103,7 @@ extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, u
 extern bool __weak is_swbp_insn(uprobe_opcode_t *insn);
 extern bool __weak is_trap_insn(uprobe_opcode_t *insn);
 extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs);
+extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
 extern int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
 extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
@@ -133,6 +134,9 @@ extern void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
+
+#define uprobe_get_trap_addr(regs)	instruction_pointer(regs)
+
 static inline int
 uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
 {
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -163,8 +163,9 @@ enum perf_branch_sample_type {
 	PERF_SAMPLE_BRANCH_ABORT_TX	= 1U << 7, /* transaction aborts */
 	PERF_SAMPLE_BRANCH_IN_TX	= 1U << 8, /* in transaction */
 	PERF_SAMPLE_BRANCH_NO_TX	= 1U << 9, /* not in transaction */
+	PERF_SAMPLE_BRANCH_COND		= 1U << 10, /* conditional branches */

-	PERF_SAMPLE_BRANCH_MAX		= 1U << 10, /* non-ABI */
+	PERF_SAMPLE_BRANCH_MAX		= 1U << 11, /* non-ABI */
 };

 #define PERF_SAMPLE_BRANCH_PLM_ALL \
@@ -301,8 +302,8 @@ struct perf_event_attr {
 				exclude_callchain_kernel : 1, /* exclude kernel callchains */
 				exclude_callchain_user   : 1, /* exclude user callchains */
 				mmap2          :  1, /* include mmap with inode data     */
-
-				__reserved_1   : 40;
+				comm_exec      :  1, /* flag comm events that are due to an exec */
+				__reserved_1   : 39;

 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -501,7 +502,12 @@ struct perf_event_mmap_page {
 #define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
 #define PERF_RECORD_MISC_GUEST_USER		(5 << 0)

+/*
+ * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
+ * different events so can reuse the same bit position.
+ */
 #define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
+#define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
 /*
 * Indicates that the content of PERF_SAMPLE_IP points to
 * the actual instruction that triggered the event. See also