x86/mce: Disable tracing and kprobes on do_machine_check()

do_machine_check() can be raised in almost any context including the most
fragile ones. Prevent kprobes and tracing.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Link: https://lkml.kernel.org/r/20200225220216.315548935@linutronix.de

arch/x86/include/asm/traps.h

@@ -88,9 +88,6 @@ dotraplinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
 dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code);
 dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code);
 dotraplinkage void do_alignment_check(struct pt_regs *regs, long error_code);
-#ifdef CONFIG_X86_MCE
-dotraplinkage void do_machine_check(struct pt_regs *regs, long error_code);
-#endif
 dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code);
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code);

arch/x86/kernel/cpu/mce/core.c

@@ -1213,8 +1213,14 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
  * On Intel systems this is entered on all CPUs in parallel through
  * MCE broadcast. However some CPUs might be broken beyond repair,
  * so be always careful when synchronizing with others.
+ *
+ * Tracing and kprobes are disabled: if we interrupted a kernel context
+ * with IF=1, we need to minimize stack usage.  There are also recursion
+ * issues: if the machine check was due to a failure of the memory
+ * backing the user stack, tracing that reads the user stack will cause
+ * potentially infinite recursion.
  */
-void do_machine_check(struct pt_regs *regs, long error_code)
+void notrace do_machine_check(struct pt_regs *regs, long error_code)
 {
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
@@ -1360,6 +1366,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	ist_exit(regs);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
+NOKPROBE_SYMBOL(do_machine_check);
 
 #ifndef CONFIG_MEMORY_FAILURE
 int memory_failure(unsigned long pfn, int flags)
@@ -1892,10 +1899,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code)
 void (*machine_check_vector)(struct pt_regs *, long error_code) =
 						unexpected_machine_check;
 
-dotraplinkage void do_mce(struct pt_regs *regs, long error_code)
+dotraplinkage notrace void do_mce(struct pt_regs *regs, long error_code)
 {
 	machine_check_vector(regs, error_code);
 }
+NOKPROBE_SYMBOL(do_mce);
 
 /*
  * Called for each booted CPU to set up machine checks.