kexec: Fix race between panic() and crash_kexec()

Currently, panic() and crash_kexec() can be called at the same time.
For example (x86 case):

CPU 0:
  oops_end()
    crash_kexec()
      mutex_trylock() // acquired
        nmi_shootdown_cpus() // stop other CPUs

CPU 1:
  panic()
    crash_kexec()
      mutex_trylock() // failed to acquire
    smp_send_stop() // stop other CPUs
    infinite loop

If CPU 1 calls smp_send_stop() before nmi_shootdown_cpus(), kdump
fails.

In another case:

CPU 0:
  oops_end()
    crash_kexec()
      mutex_trylock() // acquired
        <NMI>
        io_check_error()
          panic()
            crash_kexec()
              mutex_trylock() // failed to acquire
            infinite loop

Clearly, this is an undesirable result.

To fix this problem, this patch changes crash_kexec() to exclude others
by using the panic_cpu atomic.

Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: kexec@lists.infradead.org
Cc: linux-doc@vger.kernel.org
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Minfei Huang <mnfhuang@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: x86-ml <x86@kernel.org>
Link: http://lkml.kernel.org/r/20151210014630.25437.94161.stgit@softrs
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

3 files changed, 37 insertions, 3 deletions

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index d140b1e..7b68d27 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -237,6 +237,7 @@ extern int kexec_purgatory_get_set_symbol(struct kimage *image,
 					  unsigned int size, bool get_value);
 extern void *kexec_purgatory_get_symbol_addr(struct kimage *image,
 					     const char *name);
+extern void __crash_kexec(struct pt_regs *);
 extern void crash_kexec(struct pt_regs *);
 int kexec_should_crash(struct task_struct *);
 void crash_save_cpu(struct pt_regs *regs, int cpu);
@@ -332,6 +333,7 @@ int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 #else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
 struct task_struct;
+static inline void __crash_kexec(struct pt_regs *regs) { }
 static inline void crash_kexec(struct pt_regs *regs) { }
 static inline int kexec_should_crash(struct task_struct *p) { return 0; }
 #define kexec_in_progress false
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 11b64a6..c823f30 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -853,7 +853,12 @@ struct kimage *kexec_image;
 struct kimage *kexec_crash_image;
 int kexec_load_disabled;
 
-void crash_kexec(struct pt_regs *regs)
+/*
+ * No panic_cpu check version of crash_kexec().  This function is called
+ * only when panic_cpu holds the current CPU number; this is the only CPU
+ * which processes crash_kexec routines.
+ */
+void __crash_kexec(struct pt_regs *regs)
 {
 	/* Take the kexec_mutex here to prevent sys_kexec_load
 	 * running on one cpu from replacing the crash kernel
@@ -876,6 +881,29 @@ void crash_kexec(struct pt_regs *regs)
 	}
 }
 
+void crash_kexec(struct pt_regs *regs)
+{
+	int old_cpu, this_cpu;
+
+	/*
+	 * Only one CPU is allowed to execute the crash_kexec() code as with
+	 * panic().  Otherwise parallel calls of panic() and crash_kexec()
+	 * may stop each other.  To exclude them, we use panic_cpu here too.
+	 */
+	this_cpu = raw_smp_processor_id();
+	old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
+	if (old_cpu == PANIC_CPU_INVALID) {
+		/* This is the 1st CPU which comes here, so go ahead. */
+		__crash_kexec(regs);
+
+		/*
+		 * Reset panic_cpu to allow another panic()/crash_kexec()
+		 * call.
+		 */
+		atomic_set(&panic_cpu, PANIC_CPU_INVALID);
+	}
+}
+
 size_t crash_get_memory_size(void)
 {
 	size_t size = 0;
diff --git a/kernel/panic.c b/kernel/panic.c
index 06f31b49..b333380 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -136,9 +136,11 @@ void panic(const char *fmt, ...)
 	 * everything else.
 	 * If we want to run this after calling panic_notifiers, pass
 	 * the "crash_kexec_post_notifiers" option to the kernel.
+	 *
+	 * Bypass the panic_cpu check and call __crash_kexec directly.
 	 */
 	if (!crash_kexec_post_notifiers)
-		crash_kexec(NULL);
+		__crash_kexec(NULL);
 
 	/*
 	 * Note smp_send_stop is the usual smp shutdown function, which
@@ -161,9 +163,11 @@ void panic(const char *fmt, ...)
 	 * panic_notifiers and dumping kmsg before kdump.
 	 * Note: since some panic_notifiers can make crashed kernel
 	 * more unstable, it can increase risks of the kdump failure too.
+	 *
+	 * Bypass the panic_cpu check and call __crash_kexec directly.
 	 */
 	if (crash_kexec_post_notifiers)
-		crash_kexec(NULL);
+		__crash_kexec(NULL);
 
 	bust_spinlocks(0);