From 5211a242d0cbdded372aee59da18f80552b0a80a Mon Sep 17 00:00:00 2001 From: Kurt Garloff Date: Wed, 24 Jun 2009 14:32:11 -0700 Subject: x86: Add sysctl to allow panic on IOCK NMI error This patch introduces a new sysctl: /proc/sys/kernel/panic_on_io_nmi which defaults to 0 (off). When enabled, the kernel panics when the kernel receives an NMI caused by an IO error. The IO error triggered NMI indicates a serious system condition, which could result in IO data corruption. Rather than contiuing, panicing and dumping might be a better choice, so one can figure out what's causing the IO error. This could be especially important to companies running IO intensive applications where corruption must be avoided, e.g. a bank's databases. [ SuSE has been shipping it for a while, it was done at the request of a large database vendor, for their users. ] Signed-off-by: Kurt Garloff Signed-off-by: Roberto Angelino Signed-off-by: Greg Kroah-Hartman Cc: "Eric W. Biederman" LKML-Reference: <20090624213211.GA11291@kroah.com> Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index fac104e7186a..d6320a3e8def 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -303,6 +303,7 @@ extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in extern int panic_timeout; extern int panic_on_oops; extern int panic_on_unrecovered_nmi; +extern int panic_on_io_nmi; extern const char *print_tainted(void); extern void add_taint(unsigned flag); extern int test_taint(unsigned flag); -- cgit v1.2.2 From e09758fae8ccde97e026c704319eaa18d488dc86 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 16 Jul 2009 15:44:29 +0200 Subject: sched: Cover the CONFIG_DEBUG_SPINLOCK_SLEEP off-case for __might_sleep() Cover the off case for __might_sleep(), so that we avoid #ifdefs in files that make use of it. Especially, this prepares for the __might_sleep() pull up on cond_resched(). Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra LKML-Reference: <1247725694-6082-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d6320a3e8def..b804f694ae6a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -139,6 +139,7 @@ extern int _cond_resched(void); # define might_sleep() \ do { __might_sleep(__FILE__, __LINE__); might_resched(); } while (0) #else + static inline void __might_sleep(char *file, int line) { } # define might_sleep() do { might_resched(); } while (0) #endif -- cgit v1.2.2 From e4aafea2d4bde8b44d6500c4ee7195bbfc51269e Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 16 Jul 2009 15:44:29 +0200 Subject: sched: Add a preempt count base offset to __might_sleep() Add a preempt count base offset to compare against the current preempt level count. It prepares to pull up the might_sleep check from cond_resched() to cond_resched_lock() and cond_resched_bh(). For these two helpers, we need to respectively ensure that once we'll unlock the given spinlock / reenable local softirqs, we will reach a sleepable state. Signed-off-by: Frederic Weisbecker [ Move and rename preempt_count_equals() ] Signed-off-by: Peter Zijlstra LKML-Reference: <1247725694-6082-4-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index b804f694ae6a..2b5b1e0899a8 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -125,7 +125,7 @@ extern int _cond_resched(void); #endif #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP - void __might_sleep(char *file, int line); + void __might_sleep(char *file, int line, int preempt_offset); /** * might_sleep - annotation for functions that can sleep * @@ -137,9 +137,9 @@ extern int _cond_resched(void); * supposed to. */ # define might_sleep() \ - do { __might_sleep(__FILE__, __LINE__); might_resched(); } while (0) + do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) #else - static inline void __might_sleep(char *file, int line) { } + static inline void __might_sleep(char *file, int line, int preempt_offset) { } # define might_sleep() do { might_resched(); } while (0) #endif -- cgit v1.2.2 From 3fff4c42bd0a89869a0eb1e7874cc06ffa4aa0f5 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 22 Sep 2009 16:18:09 +0200 Subject: printk: Remove ratelimit.h from kernel.h Decouple kernel.h from ratelimit.h: the global declaration of printk's ratelimit_state is not needed, and it leads to messy circular dependencies due to ratelimit.h's (new) adding of a spinlock_types.h include. Cc: Peter Zijlstra Cc: Andrew Morton Cc: Linus Torvalds Cc: David S. Miller LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2b5b1e0899a8..3305f33201be 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include @@ -241,7 +240,6 @@ asmlinkage int vprintk(const char *fmt, va_list args) asmlinkage int printk(const char * fmt, ...) __attribute__ ((format (printf, 1, 2))) __cold; -extern struct ratelimit_state printk_ratelimit_state; extern int printk_ratelimit(void); extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); -- cgit v1.2.2 From af91322ef3f29ae4114e736e2a72e28b4d619cf9 Mon Sep 17 00:00:00 2001 From: Dave Young Date: Tue, 22 Sep 2009 16:43:33 -0700 Subject: printk: add printk_delay to make messages readable for some scenarios When syslog is not possible, at the same time there's no serial/net console available, it will be hard to read the printk messages. For example oops/panic/warning messages in shutdown phase. Add a printk delay feature, we can make each printk message delay some milliseconds. Setting the delay by proc/sysctl interface: /proc/sys/kernel/printk_delay The value range from 0 - 10000, default value is 0 [akpm@linux-foundation.org: fix a few things] Signed-off-by: Dave Young Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2b5b1e0899a8..0a2a19087863 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -246,6 +246,8 @@ extern int printk_ratelimit(void); extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); +extern int printk_delay_msec; + /* * Print a one-time message (analogous to WARN_ONCE() et al): */ -- cgit v1.2.2 From 70867453092297be9afb2249e712a1f960ec0a09 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Tue, 22 Sep 2009 16:43:46 -0700 Subject: printk_once(): use bool for boolean flag Using the type bool (instead of int) for the __print_once flag in the printk_once() macro matches the intent of the code better, and allows the compiler to generate smaller code; eg a typical callsite with gcc 4.3.3 on i386: add/remove: 0/0 grow/shrink: 0/2 up/down: 0/-6 (-6) function old new delta static.__print_once 4 1 -3 get_cpu_vendor 146 143 -3 Saving 6 bytes of object size per callsite by slightly improving the readability of the source seems like a win to me. Signed-off-by: Roland Dreier Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 0a2a19087863..55723afa097b 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -252,10 +252,10 @@ extern int printk_delay_msec; * Print a one-time message (analogous to WARN_ONCE() et al): */ #define printk_once(x...) ({ \ - static int __print_once = 1; \ + static bool __print_once = true; \ \ if (__print_once) { \ - __print_once = 0; \ + __print_once = false; \ printk(x); \ } \ }) -- cgit v1.2.2 From 8c87df457cb58fe75b9b893007917cf8095660a0 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 22 Sep 2009 16:43:52 -0700 Subject: BUILD_BUG_ON(): fix it and a couple of bogus uses of it gcc permitting variable length arrays makes the current construct used for BUILD_BUG_ON() useless, as that doesn't produce any diagnostic if the controlling expression isn't really constant. Instead, this patch makes it so that a bit field gets used here. Consequently, those uses where the condition isn't really constant now also need fixing. Note that in the gfp.h, kmemcheck.h, and virtio_config.h cases MAYBE_BUILD_BUG_ON() really just serves documentation purposes - even if the expression is compile time constant (__builtin_constant_p() yields true), the array is still deemed of variable length by gcc, and hence the whole expression doesn't have the intended effect. [akpm@linux-foundation.org: make arch/sparc/include/asm/vio.h compile] [akpm@linux-foundation.org: more nonsensical assertions in tpm.c..] Signed-off-by: Jan Beulich Cc: Andi Kleen Cc: Rusty Russell Cc: Catalin Marinas Cc: "David S. Miller" Cc: Rajiv Andrade Cc: Mimi Zohar Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 55723afa097b..63dcaece1ac5 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -678,13 +678,17 @@ struct sysinfo { }; /* Force a compilation error if condition is true */ -#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) +#define BUILD_BUG_ON(condition) ((void)BUILD_BUG_ON_ZERO(condition)) + +/* Force a compilation error if condition is constant and true */ +#define MAYBE_BUILD_BUG_ON(cond) ((void)sizeof(char[1 - 2 * !!(cond)])) /* Force a compilation error if condition is true, but also produce a result (of value 0 and type size_t), so the expression can be used e.g. in a structure initializer (or where-ever else comma expressions aren't permitted). */ -#define BUILD_BUG_ON_ZERO(e) (sizeof(char[1 - 2 * !!(e)]) - 1) +#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); })) +#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); })) /* Trap pasters of __FUNCTION__ at compile-time */ #define __FUNCTION__ (__func__) -- cgit v1.2.2 From a49c59c042c63b432307c1bbf7dac5a104c786e6 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Tue, 22 Sep 2009 16:44:03 -0700 Subject: Make sure the value in abs() does not get truncated if it is greater than 2^32 abs() will truncate the input if is it outside the 2^32 range. Fix that by assuming `long' input. This might generate worse code in the common case. Signed-off-by: Rolf Eike Beer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 63dcaece1ac5..d3cd23f30039 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -146,7 +146,7 @@ extern int _cond_resched(void); #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0) #define abs(x) ({ \ - int __x = (x); \ + long __x = (x); \ (__x < 0) ? -__x : __x; \ }) -- cgit v1.2.2 From c01226c3145d173a0d38f9d5b4f229cc23d99ae2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 21 Sep 2009 16:37:12 +0200 Subject: warn about use of uninstalled kernel headers User applications frequently hit problems when they try to use the kernel headers directly, rather than the exported headers. This adds an explicit warning for this case, and points to a URL holding an explanation of why this is wrong and what to do about it. Signed-off-by: Arnd Bergmann Signed-off-by: Sam Ravnborg --- include/linux/kernel.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d3cd23f30039..f4e3184fa054 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -659,6 +659,12 @@ extern int do_sysinfo(struct sysinfo *info); #endif /* __KERNEL__ */ +#ifndef __EXPORTED_HEADERS__ +#ifndef __KERNEL__ +#warning Attempt to use kernel headers from user space, see http://kernelnewbies.org/KernelHeaders +#endif /* __KERNEL__ */ +#endif /* __EXPORTED_HEADERS__ */ + #define SI_LOAD_SHIFT 16 struct sysinfo { long uptime; /* Seconds since boot */ -- cgit v1.2.2 From 5c828713358cb9df8aa174371edcbbb62203a490 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Fri, 23 Oct 2009 14:58:11 +0200 Subject: ratelimit: Make suppressed output messages more useful Today I got: [39648.224782] Registered led device: iwl-phy0::TX [40676.545099] __ratelimit: 246 callbacks suppressed [40676.545103] abcdef[23675]: segfault at 0 ... as you can see the ratelimit message contains a function prefix. Since this is always __ratelimit, this wont help much. This patch changes __ratelimit and printk_ratelimit to print the function name that calls ratelimit. This will pinpoint the responsible function, as long as not several different places call ratelimit with the same ratelimit state at the same time. In that case we catch only one random function that calls ratelimit after the wait period. Signed-off-by: Christian Borntraeger Cc: Dave Young Cc: Linus Torvalds CC: Andrew Morton LKML-Reference: <200910231458.11832.borntraeger@de.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3305f33201be..21d0d822c716 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -240,7 +240,8 @@ asmlinkage int vprintk(const char *fmt, va_list args) asmlinkage int printk(const char * fmt, ...) __attribute__ ((format (printf, 1, 2))) __cold; -extern int printk_ratelimit(void); +extern int __printk_ratelimit(const char *func); +#define printk_ratelimit() __printk_ratelimit(__func__) extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); -- cgit v1.2.2 From 03889384cee7a198a79447c1ea6aca2c8e54d155 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 11 Dec 2009 09:48:22 -0500 Subject: tracing: Add trace_dump_stack() I've been asked a few times about how to find out what is calling some location in the kernel. One way is to use dynamic function tracing and implement the func_stack_trace. But this only finds out who is calling a particular function. It does not tell you who is calling that function and entering a specific if conditional. I have myself implemented a quick version of trace_dump_stack() for this purpose a few times, and just needed it now. This is when I realized that this would be a good tool to have in the kernel like trace_printk(). Using trace_dump_stack() is similar to dump_stack() except that it writes to the trace buffer instead and can be used in critical locations. For example: @@ -5485,8 +5485,12 @@ need_resched_nonpreemptible: if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { if (unlikely(signal_pending_state(prev->state, prev))) prev->state = TASK_RUNNING; - else + else { deactivate_task(rq, prev, 1); + trace_printk("Deactivating task %s:%d\n", + prev->comm, prev->pid); + trace_dump_stack(); + } switch_count = &prev->nvcsw; } Produces: <...>-3249 [001] 296.105269: schedule: Deactivating task ntpd:3249 <...>-3249 [001] 296.105270: => schedule => schedule_hrtimeout_range => poll_schedule_timeout => do_select => core_sys_select => sys_select => system_call_fastpath Signed-off-by: Steven Rostedt --- include/linux/kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3fa4c590cf12..5ad4199fb073 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -492,6 +492,8 @@ extern int __trace_printk(unsigned long ip, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); +extern void trace_dump_stack(void); + /* * The double __builtin_constant_p is because gcc will give us an error * if we try to allocate the static variable to fmt if it is not a -- cgit v1.2.2 From e36c54582c6f14adc9e10473e2aec2cc4f0acc03 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 14 Dec 2009 15:58:33 -0500 Subject: tracing: Fix return of trace_dump_stack() The trace_dump_stack() returned a value for a void function. Also, added the missing stub for trace_dump_stack() when tracing is not configured. Reported-by: Ingo Molnar LKML-Reference: <20091214162713.GA31060@elte.hu> Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5ad4199fb073..f1dc752da0d2 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -527,6 +527,7 @@ trace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); static inline void tracing_start(void) { } static inline void tracing_stop(void) { } static inline void ftrace_off_permanent(void) { } +static inline void trace_dump_stack(void) { } static inline int trace_printk(const char *fmt, ...) { -- cgit v1.2.2 From 00b55864bb37200d7f05143c44f5e2edfc8c4578 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 14 Dec 2009 18:00:14 -0800 Subject: dynamic_debug.h/kernel.h: Remove KBUILD_MODNAME from dynamic_pr_debug If CONFIG_DYNAMIC_DEBUG is enabled and a source file has: #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include dynamic_debug.h will duplicate KBUILD_MODNAME in the output string. Remove the use of KBUILD_MODNAME from the output format string generated by dynamic_debug.h If CONFIG_DYNAMIC_DEBUG is not enabled, no compile-time check is done to printk/dev_printk arguments. Add it. Signed-off-by: Joe Perches Cc: Jason Baron Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3fa4c590cf12..a93cdd031aee 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -397,9 +397,8 @@ static inline char *pack_hex_byte(char *buf, u8 byte) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #elif defined(CONFIG_DYNAMIC_DEBUG) /* dynamic_pr_debug() uses pr_fmt() internally so we don't need it here */ -#define pr_debug(fmt, ...) do { \ - dynamic_pr_debug(fmt, ##__VA_ARGS__); \ - } while (0) +#define pr_debug(fmt, ...) \ + dynamic_pr_debug(fmt, ##__VA_ARGS__) #else #define pr_debug(fmt, ...) \ ({ if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); 0; }) -- cgit v1.2.2 From 0b2749aa6ca40ff3fe12ebb3fdf010ebad2e9085 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 14 Dec 2009 18:00:19 -0800 Subject: kernel.h: remove initialization of bool in printk_once Don't initialize __print_once. Invert the test to reduce initialized data. defconfig before: $size vmlinux text data bss dec hex filename 6976022 679572 1359668 9015262 898fde vmlinux defconfig after: $size vmlinux text data bss dec hex filename 6976006 679508 1359700 9015214 898fae vmlinux Signed-off-by: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index a93cdd031aee..910db75b1a72 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -251,10 +251,10 @@ extern int printk_delay_msec; * Print a one-time message (analogous to WARN_ONCE() et al): */ #define printk_once(x...) ({ \ - static bool __print_once = true; \ + static bool __print_once; \ \ - if (__print_once) { \ - __print_once = false; \ + if (!__print_once) { \ + __print_once = true; \ printk(x); \ } \ }) -- cgit v1.2.2 From 8a64f336bc1d4aa203b138d29d5a9c414a9fbb47 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 14 Dec 2009 18:00:25 -0800 Subject: kernel.h: add printk_ratelimited and pr__rl Add a printk_ratelimited statement expression macro that uses a per-call ratelimit_state so that multiple subsystems output messages are not suppressed by a global __ratelimit state. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: s/_rl/_ratelimited/g] Signed-off-by: Joe Perches Cc: Naohiro Ooiwa Cc: Ingo Molnar Cc: Hiroshi Shimamoto Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 910db75b1a72..4d9c916d06d9 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -404,6 +404,50 @@ static inline char *pack_hex_byte(char *buf, u8 byte) ({ if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); 0; }) #endif +/* + * ratelimited messages with local ratelimit_state, + * no local ratelimit_state used in the !PRINTK case + */ +#ifdef CONFIG_PRINTK +#define printk_ratelimited(fmt, ...) ({ \ + static struct ratelimit_state _rs = { \ + .interval = DEFAULT_RATELIMIT_INTERVAL, \ + .burst = DEFAULT_RATELIMIT_BURST, \ + }; \ + \ + if (!__ratelimit(&_rs)) \ + printk(fmt, ##__VA_ARGS__); \ +}) +#else +/* No effect, but we still get type checking even in the !PRINTK case: */ +#define printk_ratelimited printk +#endif + +#define pr_emerg_ratelimited(fmt, ...) \ + printk_ratelimited(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) +#define pr_alert_ratelimited(fmt, ...) \ + printk_ratelimited(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) +#define pr_crit_ratelimited(fmt, ...) \ + printk_ratelimited(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) +#define pr_err_ratelimited(fmt, ...) \ + printk_ratelimited(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warning_ratelimited(fmt, ...) \ + printk_ratelimited(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) +#define pr_notice_ratelimited(fmt, ...) \ + printk_ratelimited(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) +#define pr_info_ratelimited(fmt, ...) \ + printk_ratelimited(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) +/* no pr_cont_ratelimited, don't do that... */ +/* If you are writing a driver, please use dev_dbg instead */ +#if defined(DEBUG) +#define pr_debug_ratelimited(fmt, ...) \ + printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) +#else +#define pr_debug_ratelimited(fmt, ...) \ + ({ if (0) printk_ratelimited(KERN_DEBUG pr_fmt(fmt), \ + ##__VA_ARGS__); 0; }) +#endif + /* * General tracing related utility functions - trace_printk(), * tracing_on/tracing_off and tracing_start()/tracing_stop -- cgit v1.2.2 From d894837f23f491aa7ed167aae767fc07cfe6e6e6 Mon Sep 17 00:00:00 2001 From: Simon Kagstrom Date: Wed, 23 Dec 2009 11:08:18 +0100 Subject: sched: might_sleep(): Make file parameter const char * Fixes a warning when building with g++: warning: deprecated conversion from string constant to 'char*' And the file parameter use is constant, so mark it as such. Signed-off-by: Simon Kagstrom Cc: peterz@infradead.org LKML-Reference: <20091223110818.442d848e@marrow.netinsight.se> Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3fc9f5aab5f8..785d7d1099d4 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -124,7 +124,7 @@ extern int _cond_resched(void); #endif #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP - void __might_sleep(char *file, int line, int preempt_offset); + void __might_sleep(const char *file, int line, int preempt_offset); /** * might_sleep - annotation for functions that can sleep * @@ -138,7 +138,8 @@ extern int _cond_resched(void); # define might_sleep() \ do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) #else - static inline void __might_sleep(char *file, int line, int preempt_offset) { } + static inline void __might_sleep(const char *file, int line, + int preempt_offset) { } # define might_sleep() do { might_resched(); } while (0) #endif -- cgit v1.2.2 From cc8ef6eb21e964b1c5eb97b2d0e8ac9893e1bf86 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Fri, 15 Jan 2010 17:01:22 -0800 Subject: kernel.h: add BUILD_BUG_ON_NOT_POWER_OF_2() Add BUILD_BUG_ON_NOT_POWER_OF_2() When code relies on a constant being a power of 2: #define FOO 512 /* must be a power of 2 */ it would be nice to be able to do: BUILD_BUG_ON(!is_power_of_2(FOO)); However applying an inline function does not result in a compile-time constant that can be used with BUILD_BUG_ON(), so trying that gives results in: error: bit-field '' width not an integer constant As suggested by akpm, rather than monkeying around with is_power_of_2() and risking gcc warts about constant expressions, just create a macro BUILD_BUG_ON_NOT_POWER_OF_2() to encapsulate this common requirement. Signed-off-by: Roland Dreier Cc: Bart Van Assche Cc: David Dillow Cc: "Robert P. J. Day" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3fc9f5aab5f8..328bca609b9b 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -734,6 +734,10 @@ struct sysinfo { /* Force a compilation error if condition is constant and true */ #define MAYBE_BUILD_BUG_ON(cond) ((void)sizeof(char[1 - 2 * !!(cond)])) +/* Force a compilation error if a constant expression is not a power of 2 */ +#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0)) + /* Force a compilation error if condition is true, but also produce a result (of value 0 and type size_t), so the expression can be used e.g. in a structure initializer (or where-ever else comma expressions -- cgit v1.2.2 From 9b3be9f99203d9a400e8547f0e80f1d8f8e5738c Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:29 -0800 Subject: Move round_up/down to kernel.h ... in preparation of moving early_res to kernel/. Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-26-git-send-email-yinghai@kernel.org> Signed-off-by: H. Peter Anvin --- include/linux/kernel.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 328bca609b9b..d45e372fad81 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -44,6 +44,16 @@ extern const char linux_proc_banner[]; #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) +/* + * This looks more complex than it should be. But we need to + * get the type for the ~ right in round_down (it needs to be + * as wide as the result!), and we want to evaluate the macro + * arguments just once each. + */ +#define __round_mask(x, y) ((__typeof__(x))((y)-1)) +#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) +#define round_down(x, y) ((x) & ~__round_mask(x, y)) + #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) #define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (y)) -- cgit v1.2.2 From bb1dc0bacb8ddd7ba6a5906c678a5a5a110cf695 Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Tue, 6 Apr 2010 14:35:02 -0700 Subject: kernel.h: fix wrong usage of __ratelimit() When __ratelimit() returns 1 this means that we can go ahead. Signed-off-by: Yong Zhang Cc: Ingo Molnar Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7f0707463360..9365227dbaf6 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -426,7 +426,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) .burst = DEFAULT_RATELIMIT_BURST, \ }; \ \ - if (!__ratelimit(&_rs)) \ + if (__ratelimit(&_rs)) \ printk(fmt, ##__VA_ARGS__); \ }) #else -- cgit v1.2.2 From a79ff731a1b277d0e92d9453bdf374e04cec717a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 13 Apr 2010 11:21:46 +0200 Subject: netfilter: xtables: make XT_ALIGN() usable in exported headers by exporting __ALIGN_KERNEL() XT_ALIGN() was rewritten through ALIGN() by commit 42107f5009da223daa800d6da6904d77297ae829 "netfilter: xtables: symmetric COMPAT_XT_ALIGN definition". ALIGN() is not exported in userspace headers, which created compile problem for tc(8) and will create problem for iptables(8). We can't export generic looking name ALIGN() but we can export less generic __ALIGN_KERNEL() (suggested by Ben Hutchings). Google knows nothing about __ALIGN_KERNEL(). COMPAT_XT_ALIGN() changed for symmetry. Reported-by: Andreas Henriksson Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- include/linux/kernel.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7f0707463360..284ea995646e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -4,6 +4,8 @@ /* * 'kernel.h' contains some often-used function prototypes etc */ +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #ifdef __KERNEL__ @@ -37,8 +39,7 @@ extern const char linux_proc_banner[]; #define STACK_MAGIC 0xdeadbeef -#define ALIGN(x,a) __ALIGN_MASK(x,(typeof(x))(a)-1) -#define __ALIGN_MASK(x,mask) (((x)+(mask))&~(mask)) +#define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) #define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a))) #define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) -- cgit v1.2.2 From 9f93ff5be54108066372d1c4100c515d9d9acc1b Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 13 Apr 2010 14:09:15 +0200 Subject: Restore __ALIGN_MASK() Fix lib/bitmap.c compile failure due to __ALIGN_KERNEL changes. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 284ea995646e..db6717d0fd6f 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -40,6 +40,7 @@ extern const char linux_proc_banner[]; #define STACK_MAGIC 0xdeadbeef #define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) +#define __ALIGN_MASK(x, mask) __ALIGN_KERNEL_MASK((x), (mask)) #define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a))) #define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) -- cgit v1.2.2 From cecbca96da387428e220e307a9c945e37e2f4d9e Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 18 Apr 2010 19:08:41 +0200 Subject: tracing: Dump either the oops's cpu source or all cpus buffers The ftrace_dump_on_oops kernel parameter, sysctl and sysrq let one dump every cpu buffers when an oops or panic happens. It's nice when you have few cpus but it may take ages if have many, plus you miss the real origin of the problem in all the cpu traces. Sometimes, all you need is to dump the cpu buffer that triggered the opps, most of the time it is our main interest. This patch modifies ftrace_dump_on_oops to handle this choice. The ftrace_dump_on_oops kernel parameter, when it comes alone, has the same behaviour than before. But ftrace_dump_on_oops=orig_cpu will only dump the buffer of the cpu that oops'ed. Similarly, sysctl kernel.ftrace_dump_on_oops=1 and echo 1 > /proc/sys/kernel/ftrace_dump_on_oops keep their previous behaviour. But setting 2 jumps into cpu origin dump mode. v2: Fix double setup v3: Fix spelling issues reported by Randy Dunlap v4: Also update __ftrace_dump in the selftests Signed-off-by: Frederic Weisbecker Acked-by: David S. Miller Acked-by: Steven Rostedt Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Li Zefan Cc: Lai Jiangshan --- include/linux/kernel.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 9365227dbaf6..9fb1c1299032 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -490,6 +490,13 @@ static inline void tracing_off(void) { } static inline void tracing_off_permanent(void) { } static inline int tracing_is_on(void) { return 0; } #endif + +enum ftrace_dump_mode { + DUMP_NONE, + DUMP_ALL, + DUMP_ORIG, +}; + #ifdef CONFIG_TRACING extern void tracing_start(void); extern void tracing_stop(void); @@ -571,7 +578,7 @@ __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap); extern int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap); -extern void ftrace_dump(void); +extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode); #else static inline void ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { } @@ -592,7 +599,7 @@ ftrace_vprintk(const char *fmt, va_list ap) { return 0; } -static inline void ftrace_dump(void) { } +static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } #endif /* CONFIG_TRACING */ /* -- cgit v1.2.2 From 92946bc72f2e74c3281b7fc12be9704d455fb3ed Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sat, 3 Apr 2010 19:36:42 +0100 Subject: panic: Add taint flag TAINT_FIRMWARE_WORKAROUND ('I') This taint flag will initially be used when warning about invalid ACPI DMAR tables. Signed-off-by: Ben Hutchings Signed-off-by: David Woodhouse --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7f0707463360..7f2f7b34dd08 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -344,6 +344,7 @@ extern enum system_states { #define TAINT_OVERRIDDEN_ACPI_TABLE 8 #define TAINT_WARN 9 #define TAINT_CRAP 10 +#define TAINT_FIRMWARE_WORKAROUND 11 extern void dump_stack(void) __cold; -- cgit v1.2.2 From 4be929be34f9bdeffa40d815d32d7d60d2c7f03b Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 24 May 2010 14:33:03 -0700 Subject: kernel-wide: replace USHORT_MAX, SHORT_MAX and SHORT_MIN with USHRT_MAX, SHRT_MAX and SHRT_MIN - C99 knows about USHRT_MAX/SHRT_MAX/SHRT_MIN, not USHORT_MAX/SHORT_MAX/SHORT_MIN. - Make SHRT_MIN of type s16, not int, for consistency. [akpm@linux-foundation.org: fix drivers/dma/timb_dma.c] [akpm@linux-foundation.org: fix security/keys/keyring.c] Signed-off-by: Alexey Dobriyan Acked-by: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index cc5e3ffe9fce..a2e7c32e17e7 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -24,9 +24,9 @@ extern const char linux_banner[]; extern const char linux_proc_banner[]; -#define USHORT_MAX ((u16)(~0U)) -#define SHORT_MAX ((s16)(USHORT_MAX>>1)) -#define SHORT_MIN (-SHORT_MAX - 1) +#define USHRT_MAX ((u16)(~0U)) +#define SHRT_MAX ((s16)(USHRT_MAX>>1)) +#define SHRT_MIN ((s16)(-SHRT_MAX - 1)) #define INT_MAX ((int)(~0U>>1)) #define INT_MIN (-INT_MAX - 1) #define UINT_MAX (~0U) -- cgit v1.2.2 From fc62f2f19edf46c9bdbd1a54725b56b18c43e94f Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 24 May 2010 14:33:08 -0700 Subject: kernel.h: add pr_warn for symmetry to dev_warn, netdev_warn The current logging macros are pr_, dev_, netdev_, and netif_. pr_ uses warning, the other use warn. Standardize these logging macros a bit more by adding pr_warn and pr_warn_ratelimited. Right now, there are: $ for level in emerg alert crit err warn warning notice info ; do \ for prefix in pr dev netdev netif ; do \ echo -n "${prefix}_${level}: `git grep -w "${prefix}_${level}" | wc -l` " ; \ done ; \ echo ; \ done pr_emerg: 45 dev_emerg: 4 netdev_emerg: 1 netif_emerg: 4 pr_alert: 24 dev_alert: 36 netdev_alert: 1 netif_alert: 6 pr_crit: 24 dev_crit: 22 netdev_crit: 1 netif_crit: 4 pr_err: 2013 dev_err: 8467 netdev_err: 267 netif_err: 240 pr_warn: 0 dev_warn: 1818 netdev_warn: 126 netif_warn: 23 pr_warning: 773 dev_warning: 0 netdev_warning: 0 netif_warning: 0 pr_notice: 148 dev_notice: 111 netdev_notice: 9 netif_notice: 3 pr_info: 1717 dev_info: 3007 netdev_info: 101 netif_info: 85 Signed-off-by: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index a2e7c32e17e7..ea8490d7020e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -389,6 +389,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) #define pr_warning(fmt, ...) \ printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warn pr_warning #define pr_notice(fmt, ...) \ printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info(fmt, ...) \ @@ -447,6 +448,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) printk_ratelimited(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) #define pr_warning_ratelimited(fmt, ...) \ printk_ratelimited(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warn_ratelimited pr_warning_ratelimited #define pr_notice_ratelimited(fmt, ...) \ printk_ratelimited(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info_ratelimited(fmt, ...) \ -- cgit v1.2.2 From d8521fcc5e0ad3e79bbc4231bb20a6cdc2b50164 Mon Sep 17 00:00:00 2001 From: OGAWA Hirofumi Date: Mon, 24 May 2010 14:33:11 -0700 Subject: printk_ratelimited(): fix uninitialized spinlock ratelimit_state initialization of printk_ratelimited() seems broken. This fixes it by using DEFINE_RATELIMIT_STATE() to initialize spinlock properly. Signed-off-by: OGAWA Hirofumi Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index ea8490d7020e..05f332afc9e0 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -424,14 +424,13 @@ static inline char *pack_hex_byte(char *buf, u8 byte) * no local ratelimit_state used in the !PRINTK case */ #ifdef CONFIG_PRINTK -#define printk_ratelimited(fmt, ...) ({ \ - static struct ratelimit_state _rs = { \ - .interval = DEFAULT_RATELIMIT_INTERVAL, \ - .burst = DEFAULT_RATELIMIT_BURST, \ - }; \ - \ - if (__ratelimit(&_rs)) \ - printk(fmt, ##__VA_ARGS__); \ +#define printk_ratelimited(fmt, ...) ({ \ + static DEFINE_RATELIMIT_STATE(_rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + \ + if (__ratelimit(&_rs)) \ + printk(fmt, ##__VA_ARGS__); \ }) #else /* No effect, but we still get type checking even in the !PRINTK case: */ -- cgit v1.2.2 From 903788892ea0fc7fcaf7e8e5fac9a77379fc215b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 24 May 2010 14:33:23 -0700 Subject: lib: introduce common method to convert hex digits hex_to_bin() is a little method which converts hex digit to its actual value. There are plenty of places where such functionality is needed. [akpm@linux-foundation.org: use tolower(), saving 3 bytes, test the more common case first - it's quicker] [akpm@linux-foundation.org: relocate tolower to make it even faster! (Joe)] Signed-off-by: Andy Shevchenko Cc: Tilman Schmidt Cc: Duncan Sands Cc: Eric W. Biederman Cc: Greg Kroah-Hartman Cc: "Richard Russon (FlatCap)" Cc: John W. Linville Cc: Len Brown Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 05f332afc9e0..8317ec4b9f3b 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -375,6 +375,8 @@ static inline char *pack_hex_byte(char *buf, u8 byte) return buf; } +extern int hex_to_bin(char ch); + #ifndef pr_fmt #define pr_fmt(fmt) fmt #endif -- cgit v1.2.2 From c6de9f08912311ddc1b3502b90e10fd449acd401 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 31 May 2010 16:48:09 +0800 Subject: x86, mce: Add HW_ERR printk prefix for hardware error logging This makes hardware error related log in printk log more explicit. So that the users can report it to hardware vendor instead of LKML or software vendor. Signed-off-by: Huang Ying Reviewed-by: Hidetoshi Seto LKML-Reference: <1275295689.3444.462.camel@yhuang-dev.sh.intel.com> Signed-off-by: H. Peter Anvin --- include/linux/kernel.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 8317ec4b9f3b..3bf740bb069e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -247,6 +247,13 @@ extern struct pid *session_of_pgrp(struct pid *pgrp); #define FW_WARN "[Firmware Warn]: " #define FW_INFO "[Firmware Info]: " +/* + * HW_ERR + * Add this to a message for hardware errors, so that user can report + * it to hardware vendor instead of LKML or software vendor. + */ +#define HW_ERR "[Hardware Error]: " + #ifdef CONFIG_PRINTK asmlinkage int vprintk(const char *fmt, va_list args) __attribute__ ((format (printf, 1, 0))); -- cgit v1.2.2 From 7db6f5fb65a82af03229eef104dc9899c5eecf33 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sun, 27 Jun 2010 01:02:33 +0000 Subject: vsprintf: Recursive vsnprintf: Add "%pV", struct va_format Add the ability to print a format and va_list from a structure pointer Allows __dev_printk to be implemented as a single printk while minimizing string space duplication. %pV should not be used without some mechanism to verify the format and argument use ala __attribute__(format (printf(...))). Signed-off-by: Joe Perches Acked-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- include/linux/kernel.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 8317ec4b9f3b..01dfc05ef4ac 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -171,6 +171,11 @@ static inline void might_fault(void) } #endif +struct va_format { + const char *fmt; + va_list *va; +}; + extern struct atomic_notifier_head panic_notifier_list; extern long (*panic_blink)(long time); NORET_TYPE void panic(const char * fmt, ...) -- cgit v1.2.2 From 69c8f52b3897f2faf8510ea7ede8fffabe26c531 Mon Sep 17 00:00:00 2001 From: "Justin P. Mattock" Date: Thu, 1 Jul 2010 14:28:27 -0700 Subject: fix #warning about using kernel headers in userpsace Move the preprocessor #warning message: warning: #warning Attempt to use kernel headers from user space, see http://kernelnewbies.org/KernelHeaders from kernel.h to types.h. And also fixe the #warning message due to the preprocessor not being able to read the web address due to it thinking it was the start of a comment. also remove the extra #ifndef _KERNEL_ since it's already there. Signed-off-by: Justin P. Mattock Cc: Arnd Bergmann Signed-off-by: Jiri Kosina --- include/linux/kernel.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 8317ec4b9f3b..bd8501a8ca1c 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -728,12 +728,6 @@ extern int do_sysinfo(struct sysinfo *info); #endif /* __KERNEL__ */ -#ifndef __EXPORTED_HEADERS__ -#ifndef __KERNEL__ -#warning Attempt to use kernel headers from user space, see http://kernelnewbies.org/KernelHeaders -#endif /* __KERNEL__ */ -#endif /* __EXPORTED_HEADERS__ */ - #define SI_LOAD_SHIFT 16 struct sysinfo { long uptime; /* Seconds since boot */ -- cgit v1.2.2 From eb7beb5c09af75494234ea6acd09d0a647cf7338 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 16 Jul 2010 00:50:03 +0200 Subject: tracing: Remove special traces Special traces type was only used by sysprof. Lets remove it now that sysprof ftrace plugin has been dropped. Signed-off-by: Frederic Weisbecker Acked-by: Soeren Sandmann Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Steven Rostedt Cc: Li Zefan --- include/linux/kernel.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 8317ec4b9f3b..adee958b5989 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -508,9 +508,6 @@ extern void tracing_start(void); extern void tracing_stop(void); extern void ftrace_off_permanent(void); -extern void -ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3); - static inline void __attribute__ ((format (printf, 1, 2))) ____trace_printk_check_format(const char *fmt, ...) { @@ -586,8 +583,6 @@ __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap); extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode); #else -static inline void -ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { } static inline int trace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); -- cgit v1.2.2 From cf4ca4874fc45166198424384275f443a672d0b7 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 9 Aug 2010 17:20:20 -0700 Subject: kernel.h: remove unused NIPQUAD and NIPQUAD_FMT There are no more uses of NIPQUAD or NIPQUAD_FMT. Remove the definitions. Signed-off-by: Joe Perches Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7d5b10ff63e0..5b57236dfbd0 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -615,17 +615,6 @@ ftrace_vprintk(const char *fmt, va_list ap) static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } #endif /* CONFIG_TRACING */ -/* - * Display an IP address in readable format. - */ - -#define NIPQUAD(addr) \ - ((unsigned char *)&addr)[0], \ - ((unsigned char *)&addr)[1], \ - ((unsigned char *)&addr)[2], \ - ((unsigned char *)&addr)[3] -#define NIPQUAD_FMT "%u.%u.%u.%u" - /* * min()/max()/clamp() macros that also do * strict type-checking.. See the -- cgit v1.2.2 From c7ff0d9c92435e836e13aaa8d0e56d4000424bcc Mon Sep 17 00:00:00 2001 From: TAMUKI Shoichi Date: Tue, 10 Aug 2010 18:03:28 -0700 Subject: panic: keep blinking in spite of long spin timer mode To keep panic_timeout accuracy when running under a hypervisor, the current implementation only spins on long time (1 second) calls to mdelay. That brings a good effect, but the problem is the keyboard LEDs don't blink at all on that situation. This patch changes to call to panic_blink_enter() between every mdelay and keeps blinking in spite of long spin timer mode. The time to call to mdelay is now 100ms. Even this change will keep panic_timeout accuracy enough when running under a hypervisor. Signed-off-by: TAMUKI Shoichi Cc: Ben Dooks Cc: Russell King Acked-by: Dmitry Torokhov Cc: Anton Blanchard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5b57236dfbd0..452833d67b21 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -177,7 +177,7 @@ struct va_format { }; extern struct atomic_notifier_head panic_notifier_list; -extern long (*panic_blink)(long time); +extern long (*panic_blink)(int state); NORET_TYPE void panic(const char * fmt, ...) __attribute__ ((NORET_AND format (printf, 1, 2))) __cold; extern void oops_enter(void); -- cgit v1.2.2 From 863a6049202412a6d655d052eb1c45ca7dd74a83 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 10 Aug 2010 18:03:30 -0700 Subject: lib/bug.c: add oops end marker to WARN implementation We are missing the oops end marker for the exception based WARN implementation in lib/bug.c. This is useful for logfile analysis tools. Signed-off-by: Anton Blanchard Cc: Ingo Molnar Cc: Arjan van de Ven Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 452833d67b21..d848cb854655 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -182,6 +182,7 @@ NORET_TYPE void panic(const char * fmt, ...) __attribute__ ((NORET_AND format (printf, 1, 2))) __cold; extern void oops_enter(void); extern void oops_exit(void); +void print_oops_end_marker(void); extern int oops_may_print(void); NORET_TYPE void do_exit(long error_code) ATTRIB_NORET; -- cgit v1.2.2 From 12fdff3fc2483f906ae6404a6e8dcf2550310b6f Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 12 Aug 2010 16:54:57 +0100 Subject: Add a dummy printk function for the maintenance of unused printks Add a dummy printk function for the maintenance of unused printks through gcc format checking, and also so that side-effect checking is maintained too. Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d848cb854655..2b0a35e6bc69 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -306,6 +306,13 @@ static inline void log_buf_kexec_setup(void) } #endif +/* + * Dummy printk for disabled debugging statements to use whilst maintaining + * gcc's format and side-effect checking. + */ +static inline __attribute__ ((format (printf, 1, 2))) +int no_printk(const char *s, ...) { return 0; } + extern int printk_needs_cpu(int cpu); extern void printk_tick(void); -- cgit v1.2.2 From c8bf1336824ebd698d37b71763e1c43190f2229a Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 10 Sep 2010 20:07:38 +0200 Subject: Consolidate min_not_zero We have several users of min_not_zero, each of them using their own definition. Move the define to kernel.h. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/kernel.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2b0a35e6bc69..f5df2f4acb0d 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -640,6 +640,16 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } (void) (&_max1 == &_max2); \ _max1 > _max2 ? _max1 : _max2; }) +/** + * min_not_zero - return the minimum that is _not_ zero, unless both are zero + * @x: value1 + * @y: value2 + */ +#define min_not_zero(x, y) ({ \ + typeof(x) __x = (x); \ + typeof(y) __y = (y); \ + __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); }) + /** * clamp - return a value clamped to a given range with strict typechecking * @val: current value -- cgit v1.2.2 From 686a0f3d71203bbfcc186900bbb8ac2cfc3d803c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 13 Oct 2010 17:50:02 -0400 Subject: kernel: rounddown helper function The roundup() helper function will round a given value up to a multiple of another given value. aka roundup(11, 7) would give 14 = 7 * 2. This new function does the opposite. It will round a given number down to the nearest multiple of the second number: rounddown(11, 7) would give 7. I need this in some future SELinux code and can carry the macro myself, but figured I would put it in the core kernel so others might find and use it if need be. Signed-off-by: Eric Paris Signed-off-by: James Morris --- include/linux/kernel.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2b0a35e6bc69..6d6eea7f7b1e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -59,6 +59,12 @@ extern const char linux_proc_banner[]; #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) #define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (y)) +#define rounddown(x, y) ( \ +{ \ + typeof(x) __x = (x); \ + __x - (__x % (y)); \ +} \ +) #define DIV_ROUND_CLOSEST(x, divisor)( \ { \ typeof(divisor) __divisor = divisor; \ -- cgit v1.2.2 From b28efd54d9d5c8005a29cd8782335beb9daaa32d Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 13 Oct 2010 17:50:08 -0400 Subject: kernel: roundup should only reference arguments once Currently the roundup macro references it's arguments more than one time. This patch changes it so it will only use its arguments once. Suggested-by: Andrew Morton Signed-off-by: Eric Paris Signed-off-by: James Morris --- include/linux/kernel.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 6d6eea7f7b1e..1759ba5adce8 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -58,7 +58,12 @@ extern const char linux_proc_banner[]; #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) -#define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (y)) +#define roundup(x, y) ( \ +{ \ + typeof(y) __y = y; \ + (((x) + (__y - 1)) / __y) * __y; \ +} \ +) #define rounddown(x, y) ( \ { \ typeof(x) __x = (x); \ -- cgit v1.2.2 From f27c85c56b32c42bcc54a43189c1e00fdceb23ec Mon Sep 17 00:00:00 2001 From: Hagen Paul Pfeifer Date: Tue, 26 Oct 2010 14:22:21 -0700 Subject: kernel.h: add {min,max}3 macros Introduce two additional min/max macros to compare three operands. This will save some cycles as well as some bytes on the stack and last but not least more pleasing as macro nesting. [akpm@linux-foundation.org: fix warnings] Signed-off-by: Hagen Paul Pfeifer Cc: Joe Perches Cc: Ingo Molnar Cc: Hartley Sweeten Cc: Russell King Cc: Benjamin Herrenschmidt Cc: Thomas Gleixner Cc: Herbert Xu Cc: Roland Dreier Cc: Sean Hefty Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index edef168a0406..8e786a27cfe6 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -651,6 +651,24 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } (void) (&_max1 == &_max2); \ _max1 > _max2 ? _max1 : _max2; }) +#define min3(x, y, z) ({ \ + typeof(x) _min1 = (x); \ + typeof(y) _min2 = (y); \ + typeof(z) _min3 = (z); \ + (void) (&_min1 == &_min2); \ + (void) (&_min1 == &_min3); \ + _min1 < _min2 ? (_min1 < _min3 ? _min1 : _min3) : \ + (_min2 < _min3 ? _min2 : _min3); }) + +#define max3(x, y, z) ({ \ + typeof(x) _max1 = (x); \ + typeof(y) _max2 = (y); \ + typeof(z) _max3 = (z); \ + (void) (&_max1 == &_max2); \ + (void) (&_max1 == &_max3); \ + _max1 > _max2 ? (_max1 > _max3 ? _max1 : _max3) : \ + (_max2 > _max3 ? _max2 : _max3); }) + /** * min_not_zero - return the minimum that is _not_ zero, unless both are zero * @x: value1 -- cgit v1.2.2 From a55621f15bc61826969a29e111ba131a55ef45de Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 26 Oct 2010 14:22:25 -0700 Subject: include/linux/kernel.h: add __must_check to strict_strto*() The whole point to using the strict functions is to check the return value. If you don't, strict_strto*() will return you uninitialised garbage. Offenders have been observed in the wild. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 8e786a27cfe6..e9b492b33032 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -203,10 +203,10 @@ extern unsigned long simple_strtoul(const char *,char **,unsigned int); extern long simple_strtol(const char *,char **,unsigned int); extern unsigned long long simple_strtoull(const char *,char **,unsigned int); extern long long simple_strtoll(const char *,char **,unsigned int); -extern int strict_strtoul(const char *, unsigned int, unsigned long *); -extern int strict_strtol(const char *, unsigned int, long *); -extern int strict_strtoull(const char *, unsigned int, unsigned long long *); -extern int strict_strtoll(const char *, unsigned int, long long *); +extern int __must_check strict_strtoul(const char *, unsigned int, unsigned long *); +extern int __must_check strict_strtol(const char *, unsigned int, long *); +extern int __must_check strict_strtoull(const char *, unsigned int, unsigned long long *); +extern int __must_check strict_strtoll(const char *, unsigned int, long long *); extern int sprintf(char * buf, const char * fmt, ...) __attribute__ ((format (printf, 2, 3))); extern int vsprintf(char *buf, const char *, va_list) -- cgit v1.2.2 From 77006a0a828249dd69341f960043ee41e7487aa0 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 26 Oct 2010 14:22:49 -0700 Subject: ratelimit: add comment warning people off printk_ratelimit() printk_ratelimit() was a bad idea - we don't want subsytem A causing ratelimiting of subsystem B's messages. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e9b492b33032..77b04ed037df 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -277,6 +277,11 @@ asmlinkage int vprintk(const char *fmt, va_list args) asmlinkage int printk(const char * fmt, ...) __attribute__ ((format (printf, 1, 2))) __cold; +/* + * Please don't use printk_ratelimit(), because it shares ratelimiting state + * with all other unrelated printk_ratelimit() callsites. Instead use + * printk_ratelimited() or plain old __ratelimit(). + */ extern int __printk_ratelimit(const char *func); #define printk_ratelimit() __printk_ratelimit(__func__) extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, -- cgit v1.2.2 From 658716d19f8f155c67d4677ba68034b8e492dfbe Mon Sep 17 00:00:00 2001 From: Brian Behlendorf Date: Tue, 26 Oct 2010 14:23:10 -0700 Subject: div64_u64(): improve precision on 32bit platforms The current implementation of div64_u64 for 32bit systems returns an approximately correct result when the divisor exceeds 32bits. Since doing 64bit division using 32bit hardware is a long since solved problem we just use one of the existing proven methods. Additionally, add a div64_s64 function to correctly handle doing signed 64bit division. Addresses https://bugzilla.redhat.com/show_bug.cgi?id=616105 Signed-off-by: Brian Behlendorf Signed-off-by: Oleg Nesterov Cc: Ben Woodard Cc: Jeremy Fitzhardinge Cc: Mark Grondona Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 77b04ed037df..450092c1e35f 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -173,6 +173,11 @@ extern int _cond_resched(void); (__x < 0) ? -__x : __x; \ }) +#define abs64(x) ({ \ + s64 __x = (x); \ + (__x < 0) ? -__x : __x; \ + }) + #ifdef CONFIG_PROVE_LOCKING void might_fault(void); #else -- cgit v1.2.2 From 6070bf3596f3b5a54091a08d5b2bc90c143dc264 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 8 Nov 2010 11:20:49 +0900 Subject: kernel: Constify temporary variable in roundup() Fix build error with GCC 3.x caused by commit b28efd54 "kernel: roundup should only reference arguments once" by constifying temporary variable used in that macro. Signed-off-by: Tetsuo Handa Suggested-by: Andrew Morton Acked-by: Eric Paris Signed-off-by: James Morris --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 450092c1e35f..b526947bdf48 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -60,7 +60,7 @@ extern const char linux_proc_banner[]; #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) #define roundup(x, y) ( \ { \ - typeof(y) __y = y; \ + const typeof(y) __y = y; \ (((x) + (__y - 1)) / __y) * __y; \ } \ ) -- cgit v1.2.2 From 074e61ec3751da9ab88ee66d3818574556c03489 Mon Sep 17 00:00:00 2001 From: James Morris Date: Wed, 10 Nov 2010 09:01:31 +1100 Subject: kernel: add roundup() code comment from akpm Add roundup() code comment from akpm. Signed-off-by: Andrew Morton Signed-off-by: James Morris --- include/linux/kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index b526947bdf48..3f648d204c37 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -58,6 +58,8 @@ extern const char linux_proc_banner[]; #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) + +/* The `const' in roundup() prevents gcc-3.3 from calling __divdi3 */ #define roundup(x, y) ( \ { \ const typeof(y) __y = y; \ -- cgit v1.2.2 From eaf06b241b091357e72b76863ba16e89610d31bd Mon Sep 17 00:00:00 2001 From: Dan Rosenberg Date: Thu, 11 Nov 2010 14:05:18 -0800 Subject: Restrict unprivileged access to kernel syslog The kernel syslog contains debugging information that is often useful during exploitation of other vulnerabilities, such as kernel heap addresses. Rather than futilely attempt to sanitize hundreds (or thousands) of printk statements and simultaneously cripple useful debugging functionality, it is far simpler to create an option that prevents unprivileged users from reading the syslog. This patch, loosely based on grsecurity's GRKERNSEC_DMESG, creates the dmesg_restrict sysctl. When set to "0", the default, no restrictions are enforced. When set to "1", only users with CAP_SYS_ADMIN can read the kernel syslog via dmesg(8) or other mechanisms. [akpm@linux-foundation.org: explain the config option in kernel.txt] Signed-off-by: Dan Rosenberg Acked-by: Ingo Molnar Acked-by: Eugene Teo Acked-by: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index b526947bdf48..fc3da9e4da19 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -293,6 +293,7 @@ extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); extern int printk_delay_msec; +extern int dmesg_restrict; /* * Print a one-time message (analogous to WARN_ONCE() et al): -- cgit v1.2.2 From 968ab1838a5d48f02f5b471aa1d0e59e2cc2ccbc Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 15 Nov 2010 13:37:37 -0800 Subject: include/linux/kernel.h: Move logging bits to include/linux/printk.h Move the logging bits from kernel.h into printk.h so that there is a bit more logical separation of the generic from the printk logging specific parts. Signed-off-by: Joe Perches Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 245 +------------------------------------------------ 1 file changed, 1 insertion(+), 244 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index fc3da9e4da19..b6de9a6f7018 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -17,13 +17,11 @@ #include #include #include +#include #include #include #include -extern const char linux_banner[]; -extern const char linux_proc_banner[]; - #define USHRT_MAX ((u16)(~0U)) #define SHRT_MAX ((s16)(USHRT_MAX>>1)) #define SHRT_MIN ((s16)(-SHRT_MAX - 1)) @@ -110,31 +108,6 @@ extern const char linux_proc_banner[]; */ #define lower_32_bits(n) ((u32)(n)) -#define KERN_EMERG "<0>" /* system is unusable */ -#define KERN_ALERT "<1>" /* action must be taken immediately */ -#define KERN_CRIT "<2>" /* critical conditions */ -#define KERN_ERR "<3>" /* error conditions */ -#define KERN_WARNING "<4>" /* warning conditions */ -#define KERN_NOTICE "<5>" /* normal but significant condition */ -#define KERN_INFO "<6>" /* informational */ -#define KERN_DEBUG "<7>" /* debug-level messages */ - -/* Use the default kernel loglevel */ -#define KERN_DEFAULT "" -/* - * Annotation for a "continued" line of log printout (only done after a - * line that had no enclosing \n). Only to be used by core/arch code - * during early bootup (a continued line is not SMP-safe otherwise). - */ -#define KERN_CONT "" - -extern int console_printk[]; - -#define console_loglevel (console_printk[0]) -#define default_message_loglevel (console_printk[1]) -#define minimum_console_loglevel (console_printk[2]) -#define default_console_loglevel (console_printk[3]) - struct completion; struct pt_regs; struct user; @@ -187,11 +160,6 @@ static inline void might_fault(void) } #endif -struct va_format { - const char *fmt; - va_list *va; -}; - extern struct atomic_notifier_head panic_notifier_list; extern long (*panic_blink)(int state); NORET_TYPE void panic(const char * fmt, ...) @@ -245,115 +213,8 @@ extern int func_ptr_is_kernel_text(void *ptr); struct pid; extern struct pid *session_of_pgrp(struct pid *pgrp); -/* - * FW_BUG - * Add this to a message where you are sure the firmware is buggy or behaves - * really stupid or out of spec. Be aware that the responsible BIOS developer - * should be able to fix this issue or at least get a concrete idea of the - * problem by reading your message without the need of looking at the kernel - * code. - * - * Use it for definite and high priority BIOS bugs. - * - * FW_WARN - * Use it for not that clear (e.g. could the kernel messed up things already?) - * and medium priority BIOS bugs. - * - * FW_INFO - * Use this one if you want to tell the user or vendor about something - * suspicious, but generally harmless related to the firmware. - * - * Use it for information or very low priority BIOS bugs. - */ -#define FW_BUG "[Firmware Bug]: " -#define FW_WARN "[Firmware Warn]: " -#define FW_INFO "[Firmware Info]: " - -/* - * HW_ERR - * Add this to a message for hardware errors, so that user can report - * it to hardware vendor instead of LKML or software vendor. - */ -#define HW_ERR "[Hardware Error]: " - -#ifdef CONFIG_PRINTK -asmlinkage int vprintk(const char *fmt, va_list args) - __attribute__ ((format (printf, 1, 0))); -asmlinkage int printk(const char * fmt, ...) - __attribute__ ((format (printf, 1, 2))) __cold; - -/* - * Please don't use printk_ratelimit(), because it shares ratelimiting state - * with all other unrelated printk_ratelimit() callsites. Instead use - * printk_ratelimited() or plain old __ratelimit(). - */ -extern int __printk_ratelimit(const char *func); -#define printk_ratelimit() __printk_ratelimit(__func__) -extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, - unsigned int interval_msec); - -extern int printk_delay_msec; -extern int dmesg_restrict; - -/* - * Print a one-time message (analogous to WARN_ONCE() et al): - */ -#define printk_once(x...) ({ \ - static bool __print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - printk(x); \ - } \ -}) - -void log_buf_kexec_setup(void); -#else -static inline int vprintk(const char *s, va_list args) - __attribute__ ((format (printf, 1, 0))); -static inline int vprintk(const char *s, va_list args) { return 0; } -static inline int printk(const char *s, ...) - __attribute__ ((format (printf, 1, 2))); -static inline int __cold printk(const char *s, ...) { return 0; } -static inline int printk_ratelimit(void) { return 0; } -static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, \ - unsigned int interval_msec) \ - { return false; } - -/* No effect, but we still get type checking even in the !PRINTK case: */ -#define printk_once(x...) printk(x) - -static inline void log_buf_kexec_setup(void) -{ -} -#endif - -/* - * Dummy printk for disabled debugging statements to use whilst maintaining - * gcc's format and side-effect checking. - */ -static inline __attribute__ ((format (printf, 1, 2))) -int no_printk(const char *s, ...) { return 0; } - -extern int printk_needs_cpu(int cpu); -extern void printk_tick(void); - -extern void asmlinkage __attribute__((format(printf, 1, 2))) - early_printk(const char *fmt, ...); - unsigned long int_sqrt(unsigned long); -static inline void console_silent(void) -{ - console_loglevel = 0; -} - -static inline void console_verbose(void) -{ - if (console_loglevel) - console_loglevel = 15; -} - extern void bust_spinlocks(int yes); extern void wake_up_klogd(void); extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ @@ -390,22 +251,6 @@ extern enum system_states { #define TAINT_CRAP 10 #define TAINT_FIRMWARE_WORKAROUND 11 -extern void dump_stack(void) __cold; - -enum { - DUMP_PREFIX_NONE, - DUMP_PREFIX_ADDRESS, - DUMP_PREFIX_OFFSET -}; -extern void hex_dump_to_buffer(const void *buf, size_t len, - int rowsize, int groupsize, - char *linebuf, size_t linebuflen, bool ascii); -extern void print_hex_dump(const char *level, const char *prefix_str, - int prefix_type, int rowsize, int groupsize, - const void *buf, size_t len, bool ascii); -extern void print_hex_dump_bytes(const char *prefix_str, int prefix_type, - const void *buf, size_t len); - extern const char hex_asc[]; #define hex_asc_lo(x) hex_asc[((x) & 0x0f)] #define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] @@ -419,94 +264,6 @@ static inline char *pack_hex_byte(char *buf, u8 byte) extern int hex_to_bin(char ch); -#ifndef pr_fmt -#define pr_fmt(fmt) fmt -#endif - -#define pr_emerg(fmt, ...) \ - printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) -#define pr_alert(fmt, ...) \ - printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_crit(fmt, ...) \ - printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_err(fmt, ...) \ - printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warning(fmt, ...) \ - printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warn pr_warning -#define pr_notice(fmt, ...) \ - printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) -#define pr_info(fmt, ...) \ - printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) -#define pr_cont(fmt, ...) \ - printk(KERN_CONT fmt, ##__VA_ARGS__) - -/* pr_devel() should produce zero code unless DEBUG is defined */ -#ifdef DEBUG -#define pr_devel(fmt, ...) \ - printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) -#else -#define pr_devel(fmt, ...) \ - ({ if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); 0; }) -#endif - -/* If you are writing a driver, please use dev_dbg instead */ -#if defined(DEBUG) -#define pr_debug(fmt, ...) \ - printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) -#elif defined(CONFIG_DYNAMIC_DEBUG) -/* dynamic_pr_debug() uses pr_fmt() internally so we don't need it here */ -#define pr_debug(fmt, ...) \ - dynamic_pr_debug(fmt, ##__VA_ARGS__) -#else -#define pr_debug(fmt, ...) \ - ({ if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); 0; }) -#endif - -/* - * ratelimited messages with local ratelimit_state, - * no local ratelimit_state used in the !PRINTK case - */ -#ifdef CONFIG_PRINTK -#define printk_ratelimited(fmt, ...) ({ \ - static DEFINE_RATELIMIT_STATE(_rs, \ - DEFAULT_RATELIMIT_INTERVAL, \ - DEFAULT_RATELIMIT_BURST); \ - \ - if (__ratelimit(&_rs)) \ - printk(fmt, ##__VA_ARGS__); \ -}) -#else -/* No effect, but we still get type checking even in the !PRINTK case: */ -#define printk_ratelimited printk -#endif - -#define pr_emerg_ratelimited(fmt, ...) \ - printk_ratelimited(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) -#define pr_alert_ratelimited(fmt, ...) \ - printk_ratelimited(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_crit_ratelimited(fmt, ...) \ - printk_ratelimited(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_err_ratelimited(fmt, ...) \ - printk_ratelimited(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warning_ratelimited(fmt, ...) \ - printk_ratelimited(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warn_ratelimited pr_warning_ratelimited -#define pr_notice_ratelimited(fmt, ...) \ - printk_ratelimited(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) -#define pr_info_ratelimited(fmt, ...) \ - printk_ratelimited(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) -/* no pr_cont_ratelimited, don't do that... */ -/* If you are writing a driver, please use dev_dbg instead */ -#if defined(DEBUG) -#define pr_debug_ratelimited(fmt, ...) \ - printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) -#else -#define pr_debug_ratelimited(fmt, ...) \ - ({ if (0) printk_ratelimited(KERN_DEBUG pr_fmt(fmt), \ - ##__VA_ARGS__); 0; }) -#endif - /* * General tracing related utility functions - trace_printk(), * tracing_on/tracing_off and tracing_start()/tracing_stop -- cgit v1.2.2 From dc88e46029486ed475c71fe1bb696d39511ac8fe Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Tue, 23 Nov 2010 17:50:31 -0500 Subject: lib: hex2bin converts ascii hexadecimal string to binary Similar to the kgdb_hex2mem() code, hex2bin converts a string to binary using the hex_to_bin() library call. Changelog: - Replace parameter names with src/dst (based on David Howell's comment) - Add 'const' where needed (based on David Howell's comment) - Replace int with size_t (based on David Howell's comment) Signed-off-by: Mimi Zohar Acked-by: Serge E. Hallyn Acked-by: David Howells Signed-off-by: James Morris --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index a35b4f7332f0..d0fbc043de60 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -265,6 +265,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) } extern int hex_to_bin(char ch); +extern void hex2bin(u8 *dst, const char *src, size_t count); /* * General tracing related utility functions - trace_printk(), -- cgit v1.2.2