Merge branch 'perf/core'

8 files changed, 46 insertions, 24 deletions

diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 061ac17ee974ae..f438a44bf8f9c0 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1148,7 +1148,6 @@ ENTRY(ftrace_regs_caller)
 	 * ip location, and move flags into the return ip location.
 	 */
 	pushl 4(%esp)	/* save return ip into ip slot */
-	subl $MCOUNT_INSN_SIZE, (%esp)	/* Adjust ip */
 
 	pushl $0	/* Load 0 into orig_ax */
 	pushl %gs
@@ -1169,6 +1168,7 @@ ENTRY(ftrace_regs_caller)
 	movl $__KERNEL_CS,13*4(%esp)
 
 	movl 12*4(%esp), %eax	/* Load ip (1st parameter) */
+	subl $MCOUNT_INSN_SIZE, %eax	/* Adjust ip */
 	movl 0x4(%ebp), %edx	/* Load parent ip (2nd parameter) */
 	leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
 	pushl %esp		/* Save pt_regs as 4th parameter */
@@ -1180,7 +1180,6 @@ GLOBAL(ftrace_regs_call)
 	movl 14*4(%esp), %eax	/* Move flags back into cs */
 	movl %eax, 13*4(%esp)	/* Needed to keep addl from modifying flags */
 	movl 12*4(%esp), %eax	/* Get return ip from regs->ip */
-	addl $MCOUNT_INSN_SIZE, %eax
 	movl %eax, 14*4(%esp)	/* Put return ip back for ret */
 
 	popl %ebx
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 8985987b9e149c..1d5c61b20bf2ba 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -165,6 +165,10 @@ GLOBAL(ftrace_regs_call)
 	movq EFLAGS(%rsp), %rax
 	movq %rax, SS(%rsp)
 
+	/* Handlers can change the RIP */
+	movq RIP(%rsp), %rax
+	movq %rax, SS+8(%rsp)
+
 	/* restore the rest of pt_regs */
 	movq R15(%rsp), %r15
 	movq R14(%rsp), %r14
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 47ae1023a93c13..b7c2a85d1926bd 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -541,6 +541,8 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb
 	return 1;
 }
 
+static void __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+				      struct kprobe_ctlblk *kcb);
 /*
  * Interrupts are disabled on entry as trap3 is an interrupt gate and they
  * remain disabled throughout this function.
@@ -599,6 +601,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	} else if (kprobe_running()) {
 		p = __this_cpu_read(current_kprobe);
 		if (p->break_handler && p->break_handler(p, regs)) {
+#ifdef KPROBES_CAN_USE_FTRACE
+			if (kprobe_ftrace(p)) {
+				skip_singlestep(p, regs, kcb);
+				return 1;
+			}
+#endif
 			setup_singlestep(p, regs, kcb, 0);
 			return 1;
 		}
@@ -1053,6 +1061,21 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 }
 
 #ifdef KPROBES_CAN_USE_FTRACE
+static void __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+				      struct kprobe_ctlblk *kcb)
+{
+	/*
+	 * Emulate singlestep (and also recover regs->ip)
+	 * as if there is a 5byte nop
+	 */
+	regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
+	if (unlikely(p->post_handler)) {
+		kcb->kprobe_status = KPROBE_HIT_SSDONE;
+		p->post_handler(p, regs, 0);
+	}
+	__this_cpu_write(current_kprobe, NULL);
+}
+
 /* 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)
@@ -1072,21 +1095,17 @@ void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	if (kprobe_running()) {
 		kprobes_inc_nmissed_count(p);
 	} else {
-		regs->ip += sizeof(kprobe_opcode_t);
+		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
+		regs->ip = ip + sizeof(kprobe_opcode_t);
 
 		__this_cpu_write(current_kprobe, p);
 		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-		if (p->pre_handler)
-			p->pre_handler(p, regs);
-
-		if (unlikely(p->post_handler)) {
-			/* Emulate singlestep as if there is a 5byte nop */
-			regs->ip = ip + MCOUNT_INSN_SIZE;
-			kcb->kprobe_status = KPROBE_HIT_SSDONE;
-			p->post_handler(p, regs, 0);
-		}
-		__this_cpu_write(current_kprobe, NULL);
-		regs->ip = ip;	/* Recover for next callback */
+		if (!p->pre_handler || !p->pre_handler(p, regs))
+			skip_singlestep(p, regs, kcb);
+		/*
+		 * If pre_handler returns !0, it sets regs->ip and
+		 * resets current kprobe.
+		 */
 	}
 end:
 	local_irq_restore(flags);
diff --git a/kernel/Makefile b/kernel/Makefile
index e5602d32acb33f..5404911eaee927 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -97,7 +97,7 @@ obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o
 obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
-obj-$(CONFIG_X86_DS) += trace/
+obj-$(CONFIG_TRACE_CLOCK) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_TRACEPOINTS) += trace/
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 35b4315d84f578..098f396aa40984 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1418,9 +1418,6 @@ static __kprobes int check_kprobe_address_safe(struct kprobe *p,
 		/* Given address is not on the instruction boundary */
 		if ((unsigned long)p->addr != ftrace_addr)
 			return -EILSEQ;
-		/* break_handler (jprobe) can not work with ftrace */
-		if (p->break_handler)
-			return -EINVAL;
 		p->flags |= KPROBE_FLAG_FTRACE;
 #else	/* !KPROBES_CAN_USE_FTRACE */
 		return -EINVAL;
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 9301a0e35e0cf8..4cea4f41c1d9ed 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -62,8 +62,12 @@ config HAVE_C_RECORDMCOUNT
 config TRACER_MAX_TRACE
 	bool
 
+config TRACE_CLOCK
+	bool
+
 config RING_BUFFER
 	bool
+	select TRACE_CLOCK
 
 config FTRACE_NMI_ENTER
        bool
@@ -114,6 +118,7 @@ config TRACING
 	select NOP_TRACER
 	select BINARY_PRINTF
 	select EVENT_TRACING
+	select TRACE_CLOCK
 
 config GENERIC_TRACER
 	bool
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 837090808aac03..d7e2068e4b71ce 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -19,11 +19,7 @@ endif
 
 CFLAGS_trace_events_filter.o := -I$(src)
 
-#
-# Make the trace clocks available generally: it's infrastructure
-# relied on by ptrace for example:
-#
-obj-y += trace_clock.o
+obj-$(CONFIG_TRACE_CLOCK) += trace_clock.o
 
 obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
 obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 6825d833a25711..bbb0e63d78e918 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1646,9 +1646,11 @@ static __init void event_trace_self_tests(void)
 		event_test_stuff();
 
 		ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0);
-		if (WARN_ON_ONCE(ret))
+		if (WARN_ON_ONCE(ret)) {
 			pr_warning("error disabling system %s\n",
 				   system->name);
+			continue;
+		}
 
 		pr_cont("OK\n");
 	}