[V4 PATCH 3/4] kexec: Fix race between panic() and crash_kexec() called directly

[Hidehiro Kawai]

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 atomic_t panic_cpu.

V4:
- Use new __crash_kexec(), no exclusion check version of crash_kexec(),
  instead of checking if panic_cpu is the current cpu or not

V2:
- Use atomic_cmpxchg() instead of spin_trylock() on panic_lock
  to exclude concurrent accesses
- Don't introduce no-lock version of crash_kexec()

Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez at hitachi.com>
Cc: Eric Biederman <ebiederm at xmission.com>
Cc: Vivek Goyal <vgoyal at redhat.com>
Cc: Andrew Morton <akpm at linux-foundation.org>
Cc: Michal Hocko <mhocko at kernel.org>
---
 include/linux/kexec.h |    1 +
 kernel/kexec_core.c   |   26 +++++++++++++++++++++++++-
 kernel/panic.c        |    4 ++--
 3 files changed, 28 insertions(+), 3 deletions(-)

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index d140b1e..f0cd2fa 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);
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 201b453..4edb20a 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -853,7 +853,8 @@ int kimage_load_segment(struct kimage *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 */
+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 +877,29 @@ 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, -1, this_cpu);
+	if (old_cpu == -1) {
+		/* 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_xchg(&panic_cpu, -1);
+	}
+}
+
 size_t crash_get_memory_size(void)
 {
 	size_t size = 0;
diff --git a/kernel/panic.c b/kernel/panic.c
index cddbfe0..994be45 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -137,7 +137,7 @@ void panic(const char *fmt, ...)
 	 * the "crash_kexec_post_notifiers" option to the kernel.
 	 */
 	if (!crash_kexec_post_notifiers)
-		crash_kexec(NULL);
+		__crash_kexec(NULL);
 
 	/*
 	 * Note smp_send_stop is the usual smp shutdown function, which
@@ -162,7 +162,7 @@ void panic(const char *fmt, ...)
 	 * more unstable, it can increase risks of the kdump failure too.
 	 */
 	if (crash_kexec_post_notifiers)
-		crash_kexec(NULL);
+		__crash_kexec(NULL);
 
 	bust_spinlocks(0);