Merge remote-tracking branch 'rostedt/tip/perf/urgent-2' into x86-urgent-for-linus

6 files changed, 154 insertions, 16 deletions

diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 18d9005d9e4..b0767bc0874 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -34,7 +34,7 @@
 
 #ifndef __ASSEMBLY__
 extern void mcount(void);
-extern int modifying_ftrace_code;
+extern atomic_t modifying_ftrace_code;
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 82f29e70d05..6b9333b429b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1101,14 +1101,20 @@ int is_debug_stack(unsigned long addr)
 		 addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ));
 }
 
+static DEFINE_PER_CPU(u32, debug_stack_use_ctr);
+
 void debug_stack_set_zero(void)
 {
+	this_cpu_inc(debug_stack_use_ctr);
 	load_idt((const struct desc_ptr *)&nmi_idt_descr);
 }
 
 void debug_stack_reset(void)
 {
-	load_idt((const struct desc_ptr *)&idt_descr);
+	if (WARN_ON(!this_cpu_read(debug_stack_use_ctr)))
+		return;
+	if (this_cpu_dec_return(debug_stack_use_ctr) == 0)
+		load_idt((const struct desc_ptr *)&idt_descr);
 }
 
 #else	/* CONFIG_X86_64 */
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 320852d0202..7d65133b51b 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -191,6 +191,44 @@ ENDPROC(native_usergs_sysret64)
 .endm
 
 /*
+ * When dynamic function tracer is enabled it will add a breakpoint
+ * to all locations that it is about to modify, sync CPUs, update
+ * all the code, sync CPUs, then remove the breakpoints. In this time
+ * if lockdep is enabled, it might jump back into the debug handler
+ * outside the updating of the IST protection. (TRACE_IRQS_ON/OFF).
+ *
+ * We need to change the IDT table before calling TRACE_IRQS_ON/OFF to
+ * make sure the stack pointer does not get reset back to the top
+ * of the debug stack, and instead just reuses the current stack.
+ */
+#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS)
+
+.macro TRACE_IRQS_OFF_DEBUG
+	call debug_stack_set_zero
+	TRACE_IRQS_OFF
+	call debug_stack_reset
+.endm
+
+.macro TRACE_IRQS_ON_DEBUG
+	call debug_stack_set_zero
+	TRACE_IRQS_ON
+	call debug_stack_reset
+.endm
+
+.macro TRACE_IRQS_IRETQ_DEBUG offset=ARGOFFSET
+	bt   $9,EFLAGS-\offset(%rsp)	/* interrupts off? */
+	jnc  1f
+	TRACE_IRQS_ON_DEBUG
+1:
+.endm
+
+#else
+# define TRACE_IRQS_OFF_DEBUG		TRACE_IRQS_OFF
+# define TRACE_IRQS_ON_DEBUG		TRACE_IRQS_ON
+# define TRACE_IRQS_IRETQ_DEBUG		TRACE_IRQS_IRETQ
+#endif
+
+/*
  * C code is not supposed to know about undefined top of stack. Every time
  * a C function with an pt_regs argument is called from the SYSCALL based
  * fast path FIXUP_TOP_OF_STACK is needed.
@@ -1098,7 +1136,7 @@ ENTRY(\sym)
 	subq $ORIG_RAX-R15, %rsp
 	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
 	call save_paranoid
-	TRACE_IRQS_OFF
+	TRACE_IRQS_OFF_DEBUG
 	movq %rsp,%rdi		/* pt_regs pointer */
 	xorl %esi,%esi		/* no error code */
 	subq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist)
@@ -1393,7 +1431,7 @@ paranoidzeroentry machine_check *machine_check_vector(%rip)
 ENTRY(paranoid_exit)
 	DEFAULT_FRAME
 	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
+	TRACE_IRQS_OFF_DEBUG
 	testl %ebx,%ebx				/* swapgs needed? */
 	jnz paranoid_restore
 	testl $3,CS(%rsp)
@@ -1404,7 +1442,7 @@ paranoid_swapgs:
 	RESTORE_ALL 8
 	jmp irq_return
 paranoid_restore:
-	TRACE_IRQS_IRETQ 0
+	TRACE_IRQS_IRETQ_DEBUG 0
 	RESTORE_ALL 8
 	jmp irq_return
 paranoid_userspace:
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 32ff36596ab..c3a7cb4bf6e 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -100,7 +100,7 @@ static const unsigned char *ftrace_nop_replace(void)
 }
 
 static int
-ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
+ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
 		   unsigned const char *new_code)
 {
 	unsigned char replaced[MCOUNT_INSN_SIZE];
@@ -141,7 +141,20 @@ int ftrace_make_nop(struct module *mod,
 	old = ftrace_call_replace(ip, addr);
 	new = ftrace_nop_replace();
 
-	return ftrace_modify_code(rec->ip, old, new);
+	/*
+	 * On boot up, and when modules are loaded, the MCOUNT_ADDR
+	 * is converted to a nop, and will never become MCOUNT_ADDR
+	 * again. This code is either running before SMP (on boot up)
+	 * or before the code will ever be executed (module load).
+	 * We do not want to use the breakpoint version in this case,
+	 * just modify the code directly.
+	 */
+	if (addr == MCOUNT_ADDR)
+		return ftrace_modify_code_direct(rec->ip, old, new);
+
+	/* Normal cases use add_brk_on_nop */
+	WARN_ONCE(1, "invalid use of ftrace_make_nop");
+	return -EINVAL;
 }
 
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
@@ -152,9 +165,47 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	old = ftrace_nop_replace();
 	new = ftrace_call_replace(ip, addr);
 
-	return ftrace_modify_code(rec->ip, old, new);
+	/* Should only be called when module is loaded */
+	return ftrace_modify_code_direct(rec->ip, old, new);
 }
 
+/*
+ * The modifying_ftrace_code is used to tell the breakpoint
+ * handler to call ftrace_int3_handler(). If it fails to
+ * call this handler for a breakpoint added by ftrace, then
+ * the kernel may crash.
+ *
+ * As atomic_writes on x86 do not need a barrier, we do not
+ * need to add smp_mb()s for this to work. It is also considered
+ * that we can not read the modifying_ftrace_code before
+ * executing the breakpoint. That would be quite remarkable if
+ * it could do that. Here's the flow that is required:
+ *
+ *   CPU-0                          CPU-1
+ *
+ * atomic_inc(mfc);
+ * write int3s
+ *				<trap-int3> // implicit (r)mb
+ *				if (atomic_read(mfc))
+ *					call ftrace_int3_handler()
+ *
+ * Then when we are finished:
+ *
+ * atomic_dec(mfc);
+ *
+ * If we hit a breakpoint that was not set by ftrace, it does not
+ * matter if ftrace_int3_handler() is called or not. It will
+ * simply be ignored. But it is crucial that a ftrace nop/caller
+ * breakpoint is handled. No other user should ever place a
+ * breakpoint on an ftrace nop/caller location. It must only
+ * be done by this code.
+ */
+atomic_t modifying_ftrace_code __read_mostly;
+
+static int
+ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
+		   unsigned const char *new_code);
+
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	unsigned long ip = (unsigned long)(&ftrace_call);
@@ -163,13 +214,17 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 	memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
 	new = ftrace_call_replace(ip, (unsigned long)func);
+
+	/* See comment above by declaration of modifying_ftrace_code */
+	atomic_inc(&modifying_ftrace_code);
+
 	ret = ftrace_modify_code(ip, old, new);
 
+	atomic_dec(&modifying_ftrace_code);
+
 	return ret;
 }
 
-int modifying_ftrace_code __read_mostly;
-
 /*
  * A breakpoint was added to the code address we are about to
  * modify, and this is the handle that will just skip over it.
@@ -489,13 +544,46 @@ void ftrace_replace_code(int enable)
 	}
 }
 
+static int
+ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
+		   unsigned const char *new_code)
+{
+	int ret;
+
+	ret = add_break(ip, old_code);
+	if (ret)
+		goto out;
+
+	run_sync();
+
+	ret = add_update_code(ip, new_code);
+	if (ret)
+		goto fail_update;
+
+	run_sync();
+
+	ret = ftrace_write(ip, new_code, 1);
+	if (ret) {
+		ret = -EPERM;
+		goto out;
+	}
+	run_sync();
+ out:
+	return ret;
+
+ fail_update:
+	probe_kernel_write((void *)ip, &old_code[0], 1);
+	goto out;
+}
+
 void arch_ftrace_update_code(int command)
 {
-	modifying_ftrace_code++;
+	/* See comment above by declaration of modifying_ftrace_code */
+	atomic_inc(&modifying_ftrace_code);
 
 	ftrace_modify_all_code(command);
 
-	modifying_ftrace_code--;
+	atomic_dec(&modifying_ftrace_code);
 }
 
 int __init ftrace_dyn_arch_init(void *data)
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 90875279ef3..a0b2f84457b 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -444,14 +444,16 @@ static inline void nmi_nesting_preprocess(struct pt_regs *regs)
 	 */
 	if (unlikely(is_debug_stack(regs->sp))) {
 		debug_stack_set_zero();
-		__get_cpu_var(update_debug_stack) = 1;
+		this_cpu_write(update_debug_stack, 1);
 	}
 }
 
 static inline void nmi_nesting_postprocess(void)
 {
-	if (unlikely(__get_cpu_var(update_debug_stack)))
+	if (unlikely(this_cpu_read(update_debug_stack))) {
 		debug_stack_reset();
+		this_cpu_write(update_debug_stack, 0);
+	}
 }
 #endif
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ff08457a025..05b31d92f69 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -303,8 +303,12 @@ gp_in_kernel:
 dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code)
 {
 #ifdef CONFIG_DYNAMIC_FTRACE
-	/* ftrace must be first, everything else may cause a recursive crash */
-	if (unlikely(modifying_ftrace_code) && ftrace_int3_handler(regs))
+	/*
+	 * ftrace must be first, everything else may cause a recursive crash.
+	 * See note by declaration of modifying_ftrace_code in ftrace.c
+	 */
+	if (unlikely(atomic_read(&modifying_ftrace_code)) &&
+	    ftrace_int3_handler(regs))
 		return;
 #endif
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP