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 18d9005d9e4f..b0767bc08740 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 82f29e70d058..6b9333b429ba 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 320852d02026..7d65133b51be 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 32ff36596ab1..c3a7cb4bf6e6 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
+ *