Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1189707 > unrolled thread

[PATCH 0/3] x86: Fix panic vs. NMI issues

Back to article view | Back to linux.kernel

Contents

  [PATCH 0/3] x86: Fix panic vs. NMI issues Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> - 2015-07-22 09:40 +0200
    [PATCH 3/3] x86/apic: Introduce noextnmi boot option Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> - 2015-07-22 09:40 +0200
    [PATCH 2/3] kexec: Fix race between panic() and crash_kexec()  directly called Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> - 2015-07-22 09:40 +0200

#1189707 — [PATCH 0/3] x86: Fix panic vs. NMI issues

When an HA cluster software or administrator detects non-response
of a host, they issue an NMI to the host to completely stop current
works and take a crash dump.  If the kernel has already panicked
or is capturing a crash dump at that time, further NMI can cause
a crash dump failure.

To solve this issue, this patch set does two things:

- Don't panic on NMI if the kernel has already panicked
- Introduce "noextnmi" boot option which masks external NMI at the
  boot time (supported only for x86)

---

Hidehiro Kawai (3):
      x86/panic: Fix re-entrance problem due to panic on NMI
      kexec: Fix race between panic() and crash_kexec() directly called
      x86/apic: Introduce noextnmi boot option


 Documentation/kernel-parameters.txt |    4 ++++
 arch/x86/kernel/apic/apic.c         |   17 +++++++++++++++-
 arch/x86/kernel/nmi.c               |   18 +++++++++++------
 include/linux/kernel.h              |    4 ++++
 include/linux/kexec.h               |    2 ++
 kernel/kexec.c                      |   12 ++++++++++-
 kernel/panic.c                      |   37 ++++++++++++++++++++++++++---------
 7 files changed, 76 insertions(+), 18 deletions(-)


-- 
Hidehiro Kawai
Hitachi, Ltd. Research & Development Group


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [next] | [standalone]

#1189709 — [PATCH 3/3] x86/apic: Introduce noextnmi boot option

This patch introduces new boot option "noextnmi" which disables
external NMI.  This option is useful for the dump capture kernel
so that an HA application or administrator wouldn't mistakenly
shoot down the kernel by NMI.

Currently, only x86 supports this option.

Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/kernel-parameters.txt |    4 ++++
 arch/x86/kernel/apic/apic.c         |   17 ++++++++++++++++-
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 1d6f045..2cbd40b 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2364,6 +2364,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			noexec=on: enable non-executable mappings (default)
 			noexec=off: disable non-executable mappings
 
+	noextnmi	[X86]
+			Mask external NMI.  This option is useful for a
+			dump capture kernel to be shot down by NMI.
+
 	nosmap		[X86]
 			Disable SMAP (Supervisor Mode Access Prevention)
 			even if it is supported by processor.
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index dcb5285..a140410 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -82,6 +82,12 @@
 static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID;
 
 /*
+ * Don't enable external NMI via LINT1 on BSP.  This is useful for
+ * the dump capture kernel.
+ */
+static bool apic_noextnmi;
+
+/*
  * Map cpu index to physical APIC ID
  */
 DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID);
@@ -1150,6 +1156,8 @@ void __init init_bsp_APIC(void)
 	value = APIC_DM_NMI;
 	if (!lapic_is_integrated())		/* 82489DX */
 		value |= APIC_LVT_LEVEL_TRIGGER;
+	if (apic_noextnmi)
+		value |= APIC_LVT_MASKED;
 	apic_write(APIC_LVT1, value);
 }
 
@@ -1369,7 +1377,7 @@ void setup_local_APIC(void)
 	/*
 	 * only the BP should see the LINT1 NMI signal, obviously.
 	 */
-	if (!cpu)
+	if (!cpu && !apic_noextnmi)
 		value = APIC_DM_NMI;
 	else
 		value = APIC_DM_NMI | APIC_LVT_MASKED;
@@ -2537,3 +2545,10 @@ static int __init apic_set_disabled_cpu_apicid(char *arg)
 	return 0;
 }
 early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid);
+
+static int __init apic_set_noextnmi(char *arg)
+{
+	apic_noextnmi = true;
+	return 0;
+}
+early_param("noextnmi", apic_set_noextnmi);


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1189712 — [PATCH 2/3] kexec: Fix race between panic() and crash_kexec() directly called

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 panic_lock.

Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kexec.h |    2 ++
 kernel/kexec.c        |   12 +++++++++++-
 kernel/panic.c        |    4 ++--
 3 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index e804306..bd6e477 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -238,6 +238,7 @@ extern int kexec_purgatory_get_set_symbol(struct kimage *image,
 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);
 void crash_save_vmcoreinfo(void);
@@ -322,6 +323,7 @@ int parse_crashkernel_low(char *cmdline, unsigned long long system_ram,
 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; }
 #endif /* CONFIG_KEXEC */
 
diff --git a/kernel/kexec.c b/kernel/kexec.c
index a785c10..fcdd825 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1470,7 +1470,7 @@ void __weak crash_unmap_reserved_pages(void)
 
 #endif /* CONFIG_KEXEC_FILE */
 
-void crash_kexec(struct pt_regs *regs)
+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
@@ -1493,6 +1493,16 @@ void crash_kexec(struct pt_regs *regs)
 	}
 }
 
+void crash_kexec(struct pt_regs *regs)
+{
+	unsigned long flags;
+
+	if (spin_trylock_irqsave(&panic_lock, flags)) {
+		__crash_kexec(regs);
+		spin_unlock_irqrestore(&panic_lock, flags);
+	}
+}
+
 size_t crash_get_memory_size(void)
 {
 	size_t size = 0;
diff --git a/kernel/panic.c b/kernel/panic.c
index 3c8338b..ce5c8ab 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -135,7 +135,7 @@ void __panic(char *msg)
 	 * 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
@@ -160,7 +160,7 @@ void __panic(char *msg)
 	 * 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);
 


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web