From ffd71da4e3f323b7673b061e6f7e0d0c12dc2b49 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 13 Mar 2009 10:54:24 +0100 Subject: panic: decrease oops_in_progress only after having done the panic Impact: eliminate secondary warnings during panic() We can panic() in a number of difficult, atomic contexts, hence we use bust_spinlocks(1) in panic() to increase oops_in_progress, which prevents various debug checks we have in place. But in practice this protection only covers the first few printk's done by panic() - it does not cover the later attempt to stop all other CPUs and kexec(). If a secondary warning triggers in one of those facilities that can make the panic message scroll off. So do bust_spinlocks(0) only much later in panic(). (which code is only reached if panic policy is relaxed that it can return after a warning message) Reported-by: Jan Beulich LKML-Reference: <49B91A7E.76E4.0078.0@novell.com> Signed-off-by: Ingo Molnar --- kernel/panic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/panic.c') diff --git a/kernel/panic.c b/kernel/panic.c index 32fe4eff1b89..57fb005de546 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -77,7 +77,6 @@ NORET_TYPE void panic(const char * fmt, ...) #ifdef CONFIG_DEBUG_BUGVERBOSE dump_stack(); #endif - bust_spinlocks(0); /* * If we have crashed and we have a crash kernel loaded let it handle @@ -136,6 +135,7 @@ NORET_TYPE void panic(const char * fmt, ...) mdelay(1); i++; } + bust_spinlocks(0); } EXPORT_SYMBOL(panic); -- cgit v1.2.3 From d1dedb52acd98bd5e13e1ff4c4d045d58bbd16fe Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 13 Mar 2009 11:14:06 +0100 Subject: panic, smp: provide smp_send_stop() wrapper on UP too Impact: cleanup, no code changed Remove an ugly #ifdef CONFIG_SMP from panic(), by providing an smp_send_stop() wrapper on UP too. LKML-Reference: <49B91A7E.76E4.0078.0@novell.com> Signed-off-by: Ingo Molnar --- kernel/panic.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/panic.c') diff --git a/kernel/panic.c b/kernel/panic.c index 57fb005de546..ca75e819d0ea 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -85,14 +85,12 @@ NORET_TYPE void panic(const char * fmt, ...) */ crash_kexec(NULL); -#ifdef CONFIG_SMP /* * Note smp_send_stop is the usual smp shutdown function, which * unfortunately means it may not be hardened to work in a panic * situation. */ smp_send_stop(); -#endif atomic_notifier_call_chain(&panic_notifier_list, 0, buf); -- cgit v1.2.3 From c95dbf27e201587b2a6cf63f8501a0313d9b4801 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 13 Mar 2009 11:14:06 +0100 Subject: panic: clean up kernel/panic.c Impact: cleanup, no code changed Clean up kernel/panic.c some more and make it more consistent. LKML-Reference: <49B91A7E.76E4.0078.0@novell.com> Signed-off-by: Ingo Molnar --- kernel/panic.c | 111 ++++++++++++++++++++++++++++++--------------------------- 1 file changed, 59 insertions(+), 52 deletions(-) (limited to 'kernel/panic.c') diff --git a/kernel/panic.c b/kernel/panic.c index ca75e819d0ea..3fd8c5bf8b39 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -8,19 +8,19 @@ * This function is used through-out the kernel (including mm and fs) * to indicate a major problem. */ +#include +#include +#include +#include #include -#include -#include +#include #include -#include -#include +#include +#include +#include #include -#include +#include #include -#include -#include -#include -#include #include int panic_on_oops; @@ -52,19 +52,15 @@ EXPORT_SYMBOL(panic_blink); * * This function never returns. */ - NORET_TYPE void panic(const char * fmt, ...) { - long i; static char buf[1024]; va_list args; -#if defined(CONFIG_S390) - unsigned long caller = (unsigned long) __builtin_return_address(0); -#endif + long i; /* - * It's possible to come here directly from a panic-assertion and not - * have preempt disabled. Some functions called from here want + * It's possible to come here directly from a panic-assertion and + * not have preempt disabled. Some functions called from here want * preempt to be disabled. No point enabling it later though... */ preempt_disable(); @@ -99,19 +95,21 @@ NORET_TYPE void panic(const char * fmt, ...) if (panic_timeout > 0) { /* - * Delay timeout seconds before rebooting the machine. - * We can't use the "normal" timers since we just panicked.. - */ - printk(KERN_EMERG "Rebooting in %d seconds..",panic_timeout); + * Delay timeout seconds before rebooting the machine. + * We can't use the "normal" timers since we just panicked. + */ + printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout); + for (i = 0; i < panic_timeout*1000; ) { touch_nmi_watchdog(); i += panic_blink(i); mdelay(1); i++; } - /* This will not be a clean reboot, with everything - * shutting down. But if there is a chance of - * rebooting the system it will be rebooted. + /* + * This will not be a clean reboot, with everything + * shutting down. But if there is a chance of + * rebooting the system it will be rebooted. */ emergency_restart(); } @@ -124,10 +122,15 @@ NORET_TYPE void panic(const char * fmt, ...) } #endif #if defined(CONFIG_S390) - disabled_wait(caller); + { + unsigned long caller; + + caller = (unsigned long)__builtin_return_address(0); + disabled_wait(caller); + } #endif local_irq_enable(); - for (i = 0;;) { + for (i = 0; ; ) { touch_softlockup_watchdog(); i += panic_blink(i); mdelay(1); @@ -140,23 +143,23 @@ EXPORT_SYMBOL(panic); struct tnt { - u8 bit; - char true; - char false; + u8 bit; + char true; + char false; }; static const struct tnt tnts[] = { - { TAINT_PROPRIETARY_MODULE, 'P', 'G' }, - { TAINT_FORCED_MODULE, 'F', ' ' }, - { TAINT_UNSAFE_SMP, 'S', ' ' }, - { TAINT_FORCED_RMMOD, 'R', ' ' }, - { TAINT_MACHINE_CHECK, 'M', ' ' }, - { TAINT_BAD_PAGE, 'B', ' ' }, - { TAINT_USER, 'U', ' ' }, - { TAINT_DIE, 'D', ' ' }, - { TAINT_OVERRIDDEN_ACPI_TABLE, 'A', ' ' }, - { TAINT_WARN, 'W', ' ' }, - { TAINT_CRAP, 'C', ' ' }, + { TAINT_PROPRIETARY_MODULE, 'P', 'G' }, + { TAINT_FORCED_MODULE, 'F', ' ' }, + { TAINT_UNSAFE_SMP, 'S', ' ' }, + { TAINT_FORCED_RMMOD, 'R', ' ' }, + { TAINT_MACHINE_CHECK, 'M', ' ' }, + { TAINT_BAD_PAGE, 'B', ' ' }, + { TAINT_USER, 'U', ' ' }, + { TAINT_DIE, 'D', ' ' }, + { TAINT_OVERRIDDEN_ACPI_TABLE, 'A', ' ' }, + { TAINT_WARN, 'W', ' ' }, + { TAINT_CRAP, 'C', ' ' }, }; /** @@ -193,7 +196,8 @@ const char *print_tainted(void) *s = 0; } else snprintf(buf, sizeof(buf), "Not tainted"); - return(buf); + + return buf; } int test_taint(unsigned flag) @@ -209,7 +213,8 @@ unsigned long get_taint(void) void add_taint(unsigned flag) { - debug_locks = 0; /* can't trust the integrity of the kernel anymore */ + /* can't trust the integrity of the kernel anymore: */ + debug_locks = 0; set_bit(flag, &tainted_mask); } EXPORT_SYMBOL(add_taint); @@ -264,8 +269,8 @@ static void do_oops_enter_exit(void) } /* - * Return true if the calling CPU is allowed to print oops-related info. This - * is a bit racy.. + * Return true if the calling CPU is allowed to print oops-related info. + * This is a bit racy.. */ int oops_may_print(void) { @@ -274,20 +279,22 @@ int oops_may_print(void) /* * Called when the architecture enters its oops handler, before it prints - * anything. If this is the first CPU to oops, and it's oopsing the first time - * then let it proceed. + * anything. If this is the first CPU to oops, and it's oopsing the first + * time then let it proceed. * - * This is all enabled by the pause_on_oops kernel boot option. We do all this - * to ensure that oopses don't scroll off the screen. It has the side-effect - * of preventing later-oopsing CPUs from mucking up the display, too. + * This is all enabled by the pause_on_oops kernel boot option. We do all + * this to ensure that oopses don't scroll off the screen. It has the + * side-effect of preventing later-oopsing CPUs from mucking up the display, + * too. * - * It turns out that the CPU which is allowed to print ends up pausing for the - * right duration, whereas all the other CPUs pause for twice as long: once in - * oops_enter(), once in oops_exit(). + * It turns out that the CPU which is allowed to print ends up pausing for + * the right duration, whereas all the other CPUs pause for twice as long: + * once in oops_enter(), once in oops_exit(). */ void oops_enter(void) { - debug_locks_off(); /* can't trust the integrity of the kernel anymore */ + /* can't trust the integrity of the kernel anymore: */ + debug_locks_off(); do_oops_enter_exit(); } -- cgit v1.2.3 From 9eeba6138cefc0435695463ddadb0d95e0a6bcd2 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 11 Apr 2009 03:17:17 +0200 Subject: lockdep: warn about lockdep disabling after kernel taint Impact: provide useful missing info for developers Kernel taint can occur in several situations such as warnings, load of prorietary or staging modules, bad page, etc... But when such taint happens, a developer might still be working on the kernel, expecting that lockdep is still enabled. But a taint disables lockdep without ever warning about it. Such a kernel behaviour doesn't really help for kernel development. This patch adds this missing warning. Since the taint is done most of the time after the main message that explain the real source issue, it seems safe to warn about it inside add_taint() so that it appears at last, without hurting the main information. v2: Use a generic helper to disable lockdep instead of an open coded xchg(). Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra LKML-Reference: <1239412638-6739-1-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- kernel/panic.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'kernel/panic.c') diff --git a/kernel/panic.c b/kernel/panic.c index 3fd8c5bf8b39..940ca14f6dbf 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -213,8 +213,14 @@ unsigned long get_taint(void) void add_taint(unsigned flag) { - /* can't trust the integrity of the kernel anymore: */ - debug_locks = 0; + /* + * Can't trust the integrity of the kernel anymore. + * We don't call directly debug_locks_off() because the issue + * is not necessarily serious enough to set oops_in_progress to 1 + */ + if (__debug_locks_off()) + printk(KERN_WARNING "Disabling lockdep due to kernel taint\n"); + set_bit(flag, &tainted_mask); } EXPORT_SYMBOL(add_taint); -- cgit v1.2.3 From 574bbe782057fdf0490dc7dec906a2dc26363e20 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 11 Apr 2009 03:17:18 +0200 Subject: lockdep: continue lock debugging despite some taints Impact: broaden lockdep checks Lockdep is disabled after any kernel taints. This might be convenient to ignore bad locking issues which sources come from outside the kernel tree. Nevertheless, it might be a frustrating experience for the staging developers or those who experience a warning but are focused on another things that require lockdep. The v2 of this patch simply don't disable anymore lockdep in case of TAINT_CRAP and TAINT_WARN events. Signed-off-by: Frederic Weisbecker Cc: LTP Cc: Peter Zijlstra Cc: Greg KH LKML-Reference: <1239412638-6739-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- kernel/panic.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/panic.c') diff --git a/kernel/panic.c b/kernel/panic.c index 940ca14f6dbf..934fb377f4b3 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -217,8 +217,10 @@ void add_taint(unsigned flag) * Can't trust the integrity of the kernel anymore. * We don't call directly debug_locks_off() because the issue * is not necessarily serious enough to set oops_in_progress to 1 + * Also we want to keep up lockdep for staging development and + * post-warning case. */ - if (__debug_locks_off()) + if (flag != TAINT_CRAP && flag != TAINT_WARN && __debug_locks_off()) printk(KERN_WARNING "Disabling lockdep due to kernel taint\n"); set_bit(flag, &tainted_mask); -- cgit v1.2.3