OpenCloudOS-Kernel/include/linux/kernel.h

862 lines
28 KiB
C
Raw Normal View History

#ifndef _LINUX_KERNEL_H
#define _LINUX_KERNEL_H
#include <stdarg.h>
#include <linux/linkage.h>
#include <linux/stddef.h>
#include <linux/types.h>
#include <linux/compiler.h>
#include <linux/bitops.h>
#include <linux/log2.h>
#include <linux/typecheck.h>
#include <linux/printk.h>
#include <linux/dynamic_debug.h>
#include <asm/byteorder.h>
#include <uapi/linux/kernel.h>
#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)
#define LONG_MAX ((long)(~0UL>>1))
#define LONG_MIN (-LONG_MAX - 1)
#define ULONG_MAX (~0UL)
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:26 +08:00
#define LLONG_MAX ((long long)(~0ULL>>1))
#define LLONG_MIN (-LLONG_MAX - 1)
#define ULLONG_MAX (~0ULL)
#define SIZE_MAX (~(size_t)0)
#define U8_MAX ((u8)~0U)
#define S8_MAX ((s8)(U8_MAX>>1))
#define S8_MIN ((s8)(-S8_MAX - 1))
#define U16_MAX ((u16)~0U)
#define S16_MAX ((s16)(U16_MAX>>1))
#define S16_MIN ((s16)(-S16_MAX - 1))
#define U32_MAX ((u32)~0U)
#define S32_MAX ((s32)(U32_MAX>>1))
#define S32_MIN ((s32)(-S32_MAX - 1))
#define U64_MAX ((u64)~0ULL)
#define S64_MAX ((s64)(U64_MAX>>1))
#define S64_MIN ((s64)(-S64_MAX - 1))
#define STACK_MAGIC 0xdeadbeef
#define REPEAT_BYTE(x) ((~0ul / 0xff) * (x))
#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)
#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 DIV_ROUND_UP_ULL(ll,d) \
({ unsigned long long _tmp = (ll)+(d)-1; do_div(_tmp, d); _tmp; })
#if BITS_PER_LONG == 32
# define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP_ULL(ll, d)
#else
# define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP(ll,d)
#endif
/* The `const' in roundup() prevents gcc-3.3 from calling __divdi3 */
#define roundup(x, y) ( \
{ \
const typeof(y) __y = y; \
(((x) + (__y - 1)) / __y) * __y; \
} \
)
#define rounddown(x, y) ( \
{ \
typeof(x) __x = (x); \
__x - (__x % (y)); \
} \
)
/*
* Divide positive or negative dividend by positive divisor and round
linux/kernel.h: fix DIV_ROUND_CLOSEST with unsigned divisors Commit 263a523d18bc ("linux/kernel.h: Fix warning seen with W=1 due to change in DIV_ROUND_CLOSEST") fixes a warning seen with W=1 due to change in DIV_ROUND_CLOSEST. Unfortunately, the C compiler converts divide operations with unsigned divisors to unsigned, even if the dividend is signed and negative (for example, -10 / 5U = 858993457). The C standard says "If one operand has unsigned int type, the other operand is converted to unsigned int", so the compiler is not to blame. As a result, DIV_ROUND_CLOSEST(0, 2U) and similar operations now return bad values, since the automatic conversion of expressions such as "0 - 2U/2" to unsigned was not taken into account. Fix by checking for the divisor variable type when deciding which operation to perform. This fixes DIV_ROUND_CLOSEST(0, 2U), but still returns bad values for negative dividends divided by unsigned divisors. Mark the latter case as unsupported. One observed effect of this problem is that the s2c_hwmon driver reports a value of 4198403 instead of 0 if the ADC reads 0. Other impact is unpredictable. Problem is seen if the divisor is an unsigned variable or constant and the dividend is less than (divisor/2). Signed-off-by: Guenter Roeck <linux@roeck-us.net> Reported-by: Juergen Beisert <jbe@pengutronix.de> Tested-by: Juergen Beisert <jbe@pengutronix.de> Cc: Jean Delvare <khali@linux-fr.org> Cc: <stable@vger.kernel.org> [3.7.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-21 07:05:42 +08:00
* to closest integer. Result is undefined for negative divisors and
* for negative dividends if the divisor variable type is unsigned.
*/
#define DIV_ROUND_CLOSEST(x, divisor)( \
{ \
typeof(x) __x = x; \
typeof(divisor) __d = divisor; \
linux/kernel.h: fix DIV_ROUND_CLOSEST with unsigned divisors Commit 263a523d18bc ("linux/kernel.h: Fix warning seen with W=1 due to change in DIV_ROUND_CLOSEST") fixes a warning seen with W=1 due to change in DIV_ROUND_CLOSEST. Unfortunately, the C compiler converts divide operations with unsigned divisors to unsigned, even if the dividend is signed and negative (for example, -10 / 5U = 858993457). The C standard says "If one operand has unsigned int type, the other operand is converted to unsigned int", so the compiler is not to blame. As a result, DIV_ROUND_CLOSEST(0, 2U) and similar operations now return bad values, since the automatic conversion of expressions such as "0 - 2U/2" to unsigned was not taken into account. Fix by checking for the divisor variable type when deciding which operation to perform. This fixes DIV_ROUND_CLOSEST(0, 2U), but still returns bad values for negative dividends divided by unsigned divisors. Mark the latter case as unsupported. One observed effect of this problem is that the s2c_hwmon driver reports a value of 4198403 instead of 0 if the ADC reads 0. Other impact is unpredictable. Problem is seen if the divisor is an unsigned variable or constant and the dividend is less than (divisor/2). Signed-off-by: Guenter Roeck <linux@roeck-us.net> Reported-by: Juergen Beisert <jbe@pengutronix.de> Tested-by: Juergen Beisert <jbe@pengutronix.de> Cc: Jean Delvare <khali@linux-fr.org> Cc: <stable@vger.kernel.org> [3.7.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-21 07:05:42 +08:00
(((typeof(x))-1) > 0 || \
((typeof(divisor))-1) > 0 || (__x) > 0) ? \
(((__x) + ((__d) / 2)) / (__d)) : \
(((__x) - ((__d) / 2)) / (__d)); \
} \
)
/*
* Same as above but for u64 dividends. divisor must be a 32-bit
* number.
*/
#define DIV_ROUND_CLOSEST_ULL(x, divisor)( \
{ \
typeof(divisor) __d = divisor; \
unsigned long long _tmp = (x) + (__d) / 2; \
do_div(_tmp, __d); \
_tmp; \
} \
)
/*
* Multiplies an integer by a fraction, while avoiding unnecessary
* overflow or loss of precision.
*/
#define mult_frac(x, numer, denom)( \
{ \
typeof(x) quot = (x) / (denom); \
typeof(x) rem = (x) % (denom); \
(quot * (numer)) + ((rem * (numer)) / (denom)); \
} \
)
#define _RET_IP_ (unsigned long)__builtin_return_address(0)
#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; })
#ifdef CONFIG_LBDAF
# include <asm/div64.h>
# define sector_div(a, b) do_div(a, b)
#else
# define sector_div(n, b)( \
{ \
int _res; \
_res = (n) % (b); \
(n) /= (b); \
_res; \
} \
)
#endif
/**
* upper_32_bits - return bits 32-63 of a number
* @n: the number we're accessing
*
* A basic shift-right of a 64- or 32-bit quantity. Use this to suppress
* the "right shift count >= width of type" warning when that quantity is
* 32-bits.
*/
#define upper_32_bits(n) ((u32)(((n) >> 16) >> 16))
/**
* lower_32_bits - return bits 0-31 of a number
* @n: the number we're accessing
*/
#define lower_32_bits(n) ((u32)(n))
struct completion;
struct pt_regs;
struct user;
#ifdef CONFIG_PREEMPT_VOLUNTARY
extern int _cond_resched(void);
# define might_resched() _cond_resched()
#else
# define might_resched() do { } while (0)
#endif
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
void ___might_sleep(const 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
*
* this macro will print a stack trace if it is executed in an atomic
* context (spinlock, irq-handler, ...).
*
* This is a useful debugging help to be able to catch problems early and not
* be bitten later when the calling function happens to sleep when it is not
* supposed to.
*/
# define might_sleep() \
do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
sched: don't cause task state changes in nested sleep debugging Commit 8eb23b9f35aa ("sched: Debug nested sleeps") added code to report on nested sleep conditions, which we generally want to avoid because the inner sleeping operation can re-set the thread state to TASK_RUNNING, but that will then cause the outer sleep loop not actually sleep when it calls schedule. However, that's actually valid traditional behavior, with the inner sleep being some fairly rare case (like taking a sleeping lock that normally doesn't actually need to sleep). And the debug code would actually change the state of the task to TASK_RUNNING internally, which makes that kind of traditional and working code not work at all, because now the nested sleep doesn't just sometimes cause the outer one to not block, but will cause it to happen every time. In particular, it will cause the cardbus kernel daemon (pccardd) to basically busy-loop doing scheduling, converting a laptop into a heater, as reported by Bruno Prémont. But there may be other legacy uses of that nested sleep model in other drivers that are also likely to never get converted to the new model. This fixes both cases: - don't set TASK_RUNNING when the nested condition happens (note: even if WARN_ONCE() only _warns_ once, the return value isn't whether the warning happened, but whether the condition for the warning was true. So despite the warning only happening once, the "if (WARN_ON(..))" would trigger for every nested sleep. - in the cases where we knowingly disable the warning by using "sched_annotate_sleep()", don't change the task state (that is used for all core scheduling decisions), instead use '->task_state_change' that is used for the debugging decision itself. (Credit for the second part of the fix goes to Oleg Nesterov: "Can't we avoid this subtle change in behaviour DEBUG_ATOMIC_SLEEP adds?" with the suggested change to use 'task_state_change' as part of the test) Reported-and-bisected-by: Bruno Prémont <bonbons@linux-vserver.org> Tested-by: Rafael J Wysocki <rjw@rjwysocki.net> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de>, Cc: Ilya Dryomov <ilya.dryomov@inktank.com>, Cc: Mike Galbraith <umgwanakikbuti@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Hurley <peter@hurleysoftware.com>, Cc: Davidlohr Bueso <dave@stgolabs.net>, Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-02 04:23:32 +08:00
# define sched_annotate_sleep() (current->task_state_change = 0)
#else
static inline void ___might_sleep(const 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)
sched, exit: Deal with nested sleeps do_wait() is a big wait loop, but we set TASK_RUNNING too late; we end up calling potential sleeps before we reset it. Not strictly a bug since we're guaranteed to exit the loop and not call schedule(); put in annotations to quiet might_sleep(). WARNING: CPU: 0 PID: 1 at ../kernel/sched/core.c:7123 __might_sleep+0x7e/0x90() do not call blocking ops when !TASK_RUNNING; state=1 set at [<ffffffff8109a788>] do_wait+0x88/0x270 Call Trace: [<ffffffff81694991>] dump_stack+0x4e/0x7a [<ffffffff8109877c>] warn_slowpath_common+0x8c/0xc0 [<ffffffff8109886c>] warn_slowpath_fmt+0x4c/0x50 [<ffffffff810bca6e>] __might_sleep+0x7e/0x90 [<ffffffff811a1c15>] might_fault+0x55/0xb0 [<ffffffff8109a3fb>] wait_consider_task+0x90b/0xc10 [<ffffffff8109a804>] do_wait+0x104/0x270 [<ffffffff8109b837>] SyS_wait4+0x77/0x100 [<ffffffff8169d692>] system_call_fastpath+0x16/0x1b Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: tglx@linutronix.de Cc: umgwanakikbuti@gmail.com Cc: ilya.dryomov@inktank.com Cc: Alex Elder <alex.elder@linaro.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Axel Lin <axel.lin@ingics.com> Cc: Daniel Borkmann <dborkman@redhat.com> Cc: Dave Jones <davej@redhat.com> Cc: Guillaume Morin <guillaume@morinfr.org> Cc: Ionut Alexa <ionut.m.alexa@gmail.com> Cc: Jason Baron <jbaron@akamai.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Michal Schmidt <mschmidt@redhat.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/20140924082242.186408915@infradead.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-09-24 16:18:49 +08:00
# define sched_annotate_sleep() do { } while (0)
#endif
#define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0)
kernel.h: make abs() work with 64-bit types For 64-bit arguments, the abs macro casts it to an int which leads to lost precision and may cause incorrect results. To deal with 64-bit types abs64 macro has been introduced but still there are places where abs macro is used incorrectly. To deal with the problem, expand abs macro such that it operates on s64 type when dealing with 64-bit types while still returning long when dealing with smaller types. This fixes one known bug (per John): The internal clocksteering done for fine-grained error correction uses a : logarithmic approximation, so any time adjtimex() adjusts the clock : steering, timekeeping_freqadjust() quickly approximates the correct clock : frequency over a series of ticks. : : Unfortunately, the logic in timekeeping_freqadjust(), introduced in commit : dc491596f639438 (Rework frequency adjustments to work better w/ nohz), : used the abs() function with a s64 error value to calculate the size of : the approximated adjustment to be made. : : Per include/linux/kernel.h: "abs() should not be used for 64-bit types : (s64, u64, long long) - use abs64()". : : Thus on 32-bit platforms, this resulted in the clocksteering to take a : quite dampended random walk trying to converge on the proper frequency, : which caused the adjustments to be made much slower then intended (most : easily observed when large adjustments are made). Signed-off-by: Michal Nazarewicz <mina86@mina86.com> Reported-by: John Stultz <john.stultz@linaro.org> Tested-by: John Stultz <john.stultz@linaro.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-10 06:58:10 +08:00
/**
* abs - return absolute value of an argument
include/linux/kernel.h: change abs() macro so it uses consistent return type Rewrite abs() so that its return type does not depend on the architecture and no unexpected type conversion happen inside of it. The only conversion is from unsigned to signed type. char is left as a return type but treated as a signed type regradless of it's actual signedness. With the old version, int arguments were promoted to long and depending on architecture a long argument might result in s64 or long return type (which may or may not be the same). This came after some back and forth with Nicolas. The current macro has different return type (for the same input type) depending on architecture which might be midly iritating. An alternative version would promote to int like so: #define abs(x) __abs_choose_expr(x, long long, \ __abs_choose_expr(x, long, \ __builtin_choose_expr( \ sizeof(x) <= sizeof(int), \ ({ int __x = (x); __x<0?-__x:__x; }), \ ((void)0)))) I have no preference but imagine Linus might. :] Nicolas argument against is that promoting to int causes iconsistent behaviour: int main(void) { unsigned short a = 0, b = 1, c = a - b; unsigned short d = abs(a - b); unsigned short e = abs(c); printf("%u %u\n", d, e); // prints: 1 65535 } Then again, no sane person expects consistent behaviour from C integer arithmetic. ;) Note: __builtin_types_compatible_p(unsigned char, char) is always false, and __builtin_types_compatible_p(signed char, char) is also always false. Signed-off-by: Michal Nazarewicz <mina86@mina86.com> Reviewed-by: Nicolas Pitre <nico@linaro.org> Cc: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> Cc: Wey-Yi Guy <wey-yi.w.guy@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:57:58 +08:00
* @x: the value. If it is unsigned type, it is converted to signed type first.
* char is treated as if it was signed (regardless of whether it really is)
* but the macro's return type is preserved as char.
kernel.h: make abs() work with 64-bit types For 64-bit arguments, the abs macro casts it to an int which leads to lost precision and may cause incorrect results. To deal with 64-bit types abs64 macro has been introduced but still there are places where abs macro is used incorrectly. To deal with the problem, expand abs macro such that it operates on s64 type when dealing with 64-bit types while still returning long when dealing with smaller types. This fixes one known bug (per John): The internal clocksteering done for fine-grained error correction uses a : logarithmic approximation, so any time adjtimex() adjusts the clock : steering, timekeeping_freqadjust() quickly approximates the correct clock : frequency over a series of ticks. : : Unfortunately, the logic in timekeeping_freqadjust(), introduced in commit : dc491596f639438 (Rework frequency adjustments to work better w/ nohz), : used the abs() function with a s64 error value to calculate the size of : the approximated adjustment to be made. : : Per include/linux/kernel.h: "abs() should not be used for 64-bit types : (s64, u64, long long) - use abs64()". : : Thus on 32-bit platforms, this resulted in the clocksteering to take a : quite dampended random walk trying to converge on the proper frequency, : which caused the adjustments to be made much slower then intended (most : easily observed when large adjustments are made). Signed-off-by: Michal Nazarewicz <mina86@mina86.com> Reported-by: John Stultz <john.stultz@linaro.org> Tested-by: John Stultz <john.stultz@linaro.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-10 06:58:10 +08:00
*
include/linux/kernel.h: change abs() macro so it uses consistent return type Rewrite abs() so that its return type does not depend on the architecture and no unexpected type conversion happen inside of it. The only conversion is from unsigned to signed type. char is left as a return type but treated as a signed type regradless of it's actual signedness. With the old version, int arguments were promoted to long and depending on architecture a long argument might result in s64 or long return type (which may or may not be the same). This came after some back and forth with Nicolas. The current macro has different return type (for the same input type) depending on architecture which might be midly iritating. An alternative version would promote to int like so: #define abs(x) __abs_choose_expr(x, long long, \ __abs_choose_expr(x, long, \ __builtin_choose_expr( \ sizeof(x) <= sizeof(int), \ ({ int __x = (x); __x<0?-__x:__x; }), \ ((void)0)))) I have no preference but imagine Linus might. :] Nicolas argument against is that promoting to int causes iconsistent behaviour: int main(void) { unsigned short a = 0, b = 1, c = a - b; unsigned short d = abs(a - b); unsigned short e = abs(c); printf("%u %u\n", d, e); // prints: 1 65535 } Then again, no sane person expects consistent behaviour from C integer arithmetic. ;) Note: __builtin_types_compatible_p(unsigned char, char) is always false, and __builtin_types_compatible_p(signed char, char) is also always false. Signed-off-by: Michal Nazarewicz <mina86@mina86.com> Reviewed-by: Nicolas Pitre <nico@linaro.org> Cc: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> Cc: Wey-Yi Guy <wey-yi.w.guy@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:57:58 +08:00
* Return: an absolute value of x.
include/linux/kernel.h: abs(): fix handling of 32-bit unsigneds on 64-bit Michal reports: In the framebuffer subsystem the abs() macro is often used as a part of the calculation of a Manhattan metric, which in turn is used as a measure of similarity between video modes. The arguments of abs() are sometimes unsigned numbers. This worked fine until commit a49c59c0 ("Make sure the value in abs() does not get truncated if it is greater than 2^32:) , which changed the definition of abs() to prevent truncation. As a result of this change, in the following piece of code: u32 a = 0, b = 1; u32 c = abs(a - b); 'c' will end up with a value of 0xffffffff instead of the expected 0x1. A problem caused by this change and visible by the end user is that framebuffer drivers relying on functions from modedb.c will fail to find high resolution video modes similar to that explicitly requested by the user if an exact match cannot be found (see e.g. Fix this by special-casing `long' types within abs(). This patch reduces x86_64 code size a bit - drivers/video/uvesafb.o shrunk by 15 bytes, presumably because it is doing abs() on 4-byte quantities, and expanding those to 8-byte longs adds code. testcase: #define oldabs(x) ({ \ long __x = (x); \ (__x < 0) ? -__x : __x; \ }) #define newabs(x) ({ \ long ret; \ if (sizeof(x) == sizeof(long)) { \ long __x = (x); \ ret = (__x < 0) ? -__x : __x; \ } else { \ int __x = (x); \ ret = (__x < 0) ? -__x : __x; \ } \ ret; \ }) typedef unsigned int u32; main() { u32 a = 0; u32 b = 1; u32 oldc = oldabs(a - b); u32 newc = newabs(a - b); printf("%u %u\n", oldc, newc); } akpm:/home/akpm> gcc t.c akpm:/home/akpm> ./a.out 4294967295 1 Reported-by: Michal Januszewski <michalj@gmail.com> Cc: Rolf Eike Beer <eike-kernel@sf-tec.de Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-13 08:59:35 +08:00
*/
include/linux/kernel.h: change abs() macro so it uses consistent return type Rewrite abs() so that its return type does not depend on the architecture and no unexpected type conversion happen inside of it. The only conversion is from unsigned to signed type. char is left as a return type but treated as a signed type regradless of it's actual signedness. With the old version, int arguments were promoted to long and depending on architecture a long argument might result in s64 or long return type (which may or may not be the same). This came after some back and forth with Nicolas. The current macro has different return type (for the same input type) depending on architecture which might be midly iritating. An alternative version would promote to int like so: #define abs(x) __abs_choose_expr(x, long long, \ __abs_choose_expr(x, long, \ __builtin_choose_expr( \ sizeof(x) <= sizeof(int), \ ({ int __x = (x); __x<0?-__x:__x; }), \ ((void)0)))) I have no preference but imagine Linus might. :] Nicolas argument against is that promoting to int causes iconsistent behaviour: int main(void) { unsigned short a = 0, b = 1, c = a - b; unsigned short d = abs(a - b); unsigned short e = abs(c); printf("%u %u\n", d, e); // prints: 1 65535 } Then again, no sane person expects consistent behaviour from C integer arithmetic. ;) Note: __builtin_types_compatible_p(unsigned char, char) is always false, and __builtin_types_compatible_p(signed char, char) is also always false. Signed-off-by: Michal Nazarewicz <mina86@mina86.com> Reviewed-by: Nicolas Pitre <nico@linaro.org> Cc: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> Cc: Wey-Yi Guy <wey-yi.w.guy@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:57:58 +08:00
#define abs(x) __abs_choose_expr(x, long long, \
__abs_choose_expr(x, long, \
__abs_choose_expr(x, int, \
__abs_choose_expr(x, short, \
__abs_choose_expr(x, char, \
__builtin_choose_expr( \
__builtin_types_compatible_p(typeof(x), char), \
(char)({ signed char __x = (x); __x<0?-__x:__x; }), \
((void)0)))))))
#define __abs_choose_expr(x, type, other) __builtin_choose_expr( \
__builtin_types_compatible_p(typeof(x), signed type) || \
__builtin_types_compatible_p(typeof(x), unsigned type), \
({ signed type __x = (x); __x < 0 ? -__x : __x; }), other)
kernel.h: make abs() work with 64-bit types For 64-bit arguments, the abs macro casts it to an int which leads to lost precision and may cause incorrect results. To deal with 64-bit types abs64 macro has been introduced but still there are places where abs macro is used incorrectly. To deal with the problem, expand abs macro such that it operates on s64 type when dealing with 64-bit types while still returning long when dealing with smaller types. This fixes one known bug (per John): The internal clocksteering done for fine-grained error correction uses a : logarithmic approximation, so any time adjtimex() adjusts the clock : steering, timekeeping_freqadjust() quickly approximates the correct clock : frequency over a series of ticks. : : Unfortunately, the logic in timekeeping_freqadjust(), introduced in commit : dc491596f639438 (Rework frequency adjustments to work better w/ nohz), : used the abs() function with a s64 error value to calculate the size of : the approximated adjustment to be made. : : Per include/linux/kernel.h: "abs() should not be used for 64-bit types : (s64, u64, long long) - use abs64()". : : Thus on 32-bit platforms, this resulted in the clocksteering to take a : quite dampended random walk trying to converge on the proper frequency, : which caused the adjustments to be made much slower then intended (most : easily observed when large adjustments are made). Signed-off-by: Michal Nazarewicz <mina86@mina86.com> Reported-by: John Stultz <john.stultz@linaro.org> Tested-by: John Stultz <john.stultz@linaro.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-10 06:58:10 +08:00
/**
* reciprocal_scale - "scale" a value into range [0, ep_ro)
* @val: value
* @ep_ro: right open interval endpoint
*
* Perform a "reciprocal multiplication" in order to "scale" a value into
* range [0, ep_ro), where the upper interval endpoint is right-open.
* This is useful, e.g. for accessing a index of an array containing
* ep_ro elements, for example. Think of it as sort of modulus, only that
* the result isn't that of modulo. ;) Note that if initial input is a
* small value, then result will return 0.
*
* Return: a result based on val in interval [0, ep_ro).
*/
static inline u32 reciprocal_scale(u32 val, u32 ep_ro)
{
return (u32)(((u64) val * ep_ro) >> 32);
}
#if defined(CONFIG_MMU) && \
(defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP))
sched/preempt, mm/fault: Trigger might_sleep() in might_fault() with disabled pagefaults Commit 662bbcb2747c ("mm, sched: Allow uaccess in atomic with pagefault_disable()") removed might_sleep() checks for all user access code (that uses might_fault()). The reason was to disable wrong "sleep in atomic" warnings in the following scenario: pagefault_disable() rc = copy_to_user(...) pagefault_enable() Which is valid, as pagefault_disable() increments the preempt counter and therefore disables the pagefault handler. copy_to_user() will not sleep and return an error code if a page is not available. However, as all might_sleep() checks are removed, CONFIG_DEBUG_ATOMIC_SLEEP would no longer detect the following scenario: spin_lock(&lock); rc = copy_to_user(...) spin_unlock(&lock) If the kernel is compiled with preemption turned on, preempt_disable() will make in_atomic() detect disabled preemption. The fault handler would correctly never sleep on user access. However, with preemption turned off, preempt_disable() is usually a NOP (with !CONFIG_PREEMPT_COUNT), therefore in_atomic() will not be able to detect disabled preemption nor disabled pagefaults. The fault handler could sleep. We really want to enable CONFIG_DEBUG_ATOMIC_SLEEP checks for user access functions again, otherwise we can end up with horrible deadlocks. Root of all evil is that pagefault_disable() acts almost as preempt_disable(), depending on preemption being turned on/off. As we now have pagefault_disabled(), we can use it to distinguish whether user acces functions might sleep. Convert might_fault() into a makro that calls __might_fault(), to allow proper file + line messages in case of a might_sleep() warning. Reviewed-and-tested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: airlied@linux.ie Cc: akpm@linux-foundation.org Cc: benh@kernel.crashing.org Cc: bigeasy@linutronix.de Cc: borntraeger@de.ibm.com Cc: daniel.vetter@intel.com Cc: heiko.carstens@de.ibm.com Cc: herbert@gondor.apana.org.au Cc: hocko@suse.cz Cc: hughd@google.com Cc: mst@redhat.com Cc: paulus@samba.org Cc: ralf@linux-mips.org Cc: schwidefsky@de.ibm.com Cc: yang.shi@windriver.com Link: http://lkml.kernel.org/r/1431359540-32227-3-git-send-email-dahi@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-11 23:52:07 +08:00
#define might_fault() __might_fault(__FILE__, __LINE__)
void __might_fault(const char *file, int line);
#else
static inline void might_fault(void) { }
#endif
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 17:16:30 +08:00
extern struct atomic_notifier_head panic_notifier_list;
extern long (*panic_blink)(int state);
__printf(1, 2)
void panic(const char *fmt, ...)
__noreturn __cold;
panic, x86: Allow CPUs to save registers even if looping in NMI context Currently, kdump_nmi_shootdown_cpus(), a subroutine of crash_kexec(), sends an NMI IPI to CPUs which haven't called panic() to stop them, save their register information and do some cleanups for crash dumping. However, if such a CPU is infinitely looping in NMI context, we fail to save its register information into the crash dump. For example, this can happen when unknown NMIs are broadcast to all CPUs as follows: CPU 0 CPU 1 =========================== ========================== receive an unknown NMI unknown_nmi_error() panic() receive an unknown NMI spin_trylock(&panic_lock) unknown_nmi_error() crash_kexec() panic() spin_trylock(&panic_lock) panic_smp_self_stop() infinite loop kdump_nmi_shootdown_cpus() issue NMI IPI -----------> blocked until IRET infinite loop... Here, since CPU 1 is in NMI context, the second NMI from CPU 0 is blocked until CPU 1 executes IRET. However, CPU 1 never executes IRET, so the NMI is not handled and the callback function to save registers is never called. In practice, this can happen on some servers which broadcast NMIs to all CPUs when the NMI button is pushed. To save registers in this case, we need to: a) Return from NMI handler instead of looping infinitely or b) Call the callback function directly from the infinite loop Inherently, a) is risky because NMI is also used to prevent corrupted data from being propagated to devices. So, we chose b). This patch does the following: 1. Move the infinite looping of CPUs which haven't called panic() in NMI context (actually done by panic_smp_self_stop()) outside of panic() to enable us to refer pt_regs. Please note that panic_smp_self_stop() is still used for normal context. 2. Call a callback of kdump_nmi_shootdown_cpus() directly to save registers and do some cleanups after setting waiting_for_crash_ipi which is used for counting down the number of CPUs which handled the callback Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Dave Young <dyoung@redhat.com> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml <linux-kernel@vger.kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Seth Jennings <sjenning@redhat.com> Cc: Stefan Lippers-Hollmann <s.l-h@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Link: http://lkml.kernel.org/r/20151210014628.25437.75256.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:10 +08:00
void nmi_panic_self_stop(struct pt_regs *);
extern void oops_enter(void);
extern void oops_exit(void);
void print_oops_end_marker(void);
extern int oops_may_print(void);
void do_exit(long error_code)
__noreturn;
void complete_and_exit(struct completion *, long)
__noreturn;
/* Internal, do not use. */
int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res);
int __must_check _kstrtol(const char *s, unsigned int base, long *res);
int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res);
int __must_check kstrtoll(const char *s, unsigned int base, long long *res);
/**
* kstrtoul - convert a string to an unsigned long
* @s: The start of the string. The string must be null-terminated, and may also
* include a single newline before its terminating null. The first character
* may also be a plus sign, but not a minus sign.
* @base: The number base to use. The maximum supported base is 16. If base is
* given as 0, then the base of the string is automatically detected with the
* conventional semantics - If it begins with 0x the number will be parsed as a
* hexadecimal (case insensitive), if it otherwise begins with 0, it will be
* parsed as an octal number. Otherwise it will be parsed as a decimal.
* @res: Where to write the result of the conversion on success.
*
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Used as a replacement for the obsolete simple_strtoull. Return code must
* be checked.
*/
static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res)
{
/*
* We want to shortcut function call, but
* __builtin_types_compatible_p(unsigned long, unsigned long long) = 0.
*/
if (sizeof(unsigned long) == sizeof(unsigned long long) &&
__alignof__(unsigned long) == __alignof__(unsigned long long))
return kstrtoull(s, base, (unsigned long long *)res);
else
return _kstrtoul(s, base, res);
}
/**
* kstrtol - convert a string to a long
* @s: The start of the string. The string must be null-terminated, and may also
* include a single newline before its terminating null. The first character
* may also be a plus sign or a minus sign.
* @base: The number base to use. The maximum supported base is 16. If base is
* given as 0, then the base of the string is automatically detected with the
* conventional semantics - If it begins with 0x the number will be parsed as a
* hexadecimal (case insensitive), if it otherwise begins with 0, it will be
* parsed as an octal number. Otherwise it will be parsed as a decimal.
* @res: Where to write the result of the conversion on success.
*
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Used as a replacement for the obsolete simple_strtoull. Return code must
* be checked.
*/
static inline int __must_check kstrtol(const char *s, unsigned int base, long *res)
{
/*
* We want to shortcut function call, but
* __builtin_types_compatible_p(long, long long) = 0.
*/
if (sizeof(long) == sizeof(long long) &&
__alignof__(long) == __alignof__(long long))
return kstrtoll(s, base, (long long *)res);
else
return _kstrtol(s, base, res);
}
int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res);
int __must_check kstrtoint(const char *s, unsigned int base, int *res);
static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res)
{
return kstrtoull(s, base, res);
}
static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res)
{
return kstrtoll(s, base, res);
}
static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res)
{
return kstrtouint(s, base, res);
}
static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res)
{
return kstrtoint(s, base, res);
}
int __must_check kstrtou16(const char *s, unsigned int base, u16 *res);
int __must_check kstrtos16(const char *s, unsigned int base, s16 *res);
int __must_check kstrtou8(const char *s, unsigned int base, u8 *res);
int __must_check kstrtos8(const char *s, unsigned int base, s8 *res);
int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res);
int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res);
int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res);
int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res);
int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res);
int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res);
int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res);
int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res);
int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res);
int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res);
static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res)
{
return kstrtoull_from_user(s, count, base, res);
}
static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res)
{
return kstrtoll_from_user(s, count, base, res);
}
static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res)
{
return kstrtouint_from_user(s, count, base, res);
}
static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res)
{
return kstrtoint_from_user(s, count, base, res);
}
/* Obsolete, do not use. Use kstrto<foo> instead */
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);
procfs: add num_to_str() to speed up /proc/stat == stat_check.py num = 0 with open("/proc/stat") as f: while num < 1000 : data = f.read() f.seek(0, 0) num = num + 1 == perf shows 20.39% stat_check.py [kernel.kallsyms] [k] format_decode 13.41% stat_check.py [kernel.kallsyms] [k] number 12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf 10.85% stat_check.py [kernel.kallsyms] [k] memcpy 4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup 4.43% stat_check.py [kernel.kallsyms] [k] seq_printf This patch removes most of calls to vsnprintf() by adding num_to_str() and seq_print_decimal_ull(), which prints decimal numbers without rich functions provided by printf(). On my 8cpu box. == Before patch == [root@bluextal test]# time ./stat_check.py real 0m0.150s user 0m0.026s sys 0m0.121s == After patch == [root@bluextal test]# time ./stat_check.py real 0m0.055s user 0m0.022s sys 0m0.030s [akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()] [andrea@betterlinux.com: avoid breaking the ABI in /proc/stat] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrea Righi <andrea@betterlinux.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Glauber Costa <glommer@parallels.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Turner <pjt@google.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 06:02:54 +08:00
extern int num_to_str(char *buf, int size, unsigned long long num);
/* lib/printf utilities */
extern __printf(2, 3) int sprintf(char *buf, const char * fmt, ...);
extern __printf(2, 0) int vsprintf(char *buf, const char *, va_list);
extern __printf(3, 4)
int snprintf(char *buf, size_t size, const char *fmt, ...);
extern __printf(3, 0)
int vsnprintf(char *buf, size_t size, const char *fmt, va_list args);
extern __printf(3, 4)
int scnprintf(char *buf, size_t size, const char *fmt, ...);
extern __printf(3, 0)
int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
extern __printf(2, 3)
char *kasprintf(gfp_t gfp, const char *fmt, ...);
extern __printf(2, 0)
char *kvasprintf(gfp_t gfp, const char *fmt, va_list args);
extern __printf(2, 0)
const char *kvasprintf_const(gfp_t gfp, const char *fmt, va_list args);
extern __scanf(2, 3)
int sscanf(const char *, const char *, ...);
extern __scanf(2, 0)
int vsscanf(const char *, const char *, va_list);
extern int get_option(char **str, int *pint);
extern char *get_options(const char *str, int nints, int *ints);
extern unsigned long long memparse(const char *ptr, char **retptr);
extern bool parse_option_str(const char *str, const char *option);
extern int core_kernel_text(unsigned long addr);
extern int core_kernel_data(unsigned long addr);
extern int __kernel_text_address(unsigned long addr);
extern int kernel_text_address(unsigned long addr);
extern int func_ptr_is_kernel_text(void *ptr);
unsigned long int_sqrt(unsigned long);
extern void bust_spinlocks(int yes);
extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */
extern int panic_timeout;
extern int panic_on_oops;
extern int panic_on_unrecovered_nmi;
extern int panic_on_io_nmi;
kernel: add panic_on_warn There have been several times where I have had to rebuild a kernel to cause a panic when hitting a WARN() in the code in order to get a crash dump from a system. Sometimes this is easy to do, other times (such as in the case of a remote admin) it is not trivial to send new images to the user. A much easier method would be a switch to change the WARN() over to a panic. This makes debugging easier in that I can now test the actual image the WARN() was seen on and I do not have to engage in remote debugging. This patch adds a panic_on_warn kernel parameter and /proc/sys/kernel/panic_on_warn calls panic() in the warn_slowpath_common() path. The function will still print out the location of the warning. An example of the panic_on_warn output: The first line below is from the WARN_ON() to output the WARN_ON()'s location. After that the panic() output is displayed. WARNING: CPU: 30 PID: 11698 at /home/prarit/dummy_module/dummy-module.c:25 init_dummy+0x1f/0x30 [dummy_module]() Kernel panic - not syncing: panic_on_warn set ... CPU: 30 PID: 11698 Comm: insmod Tainted: G W OE 3.17.0+ #57 Hardware name: Intel Corporation S2600CP/S2600CP, BIOS RMLSDP.86I.00.29.D696.1311111329 11/11/2013 0000000000000000 000000008e3f87df ffff88080f093c38 ffffffff81665190 0000000000000000 ffffffff818aea3d ffff88080f093cb8 ffffffff8165e2ec ffffffff00000008 ffff88080f093cc8 ffff88080f093c68 000000008e3f87df Call Trace: [<ffffffff81665190>] dump_stack+0x46/0x58 [<ffffffff8165e2ec>] panic+0xd0/0x204 [<ffffffffa038e05f>] ? init_dummy+0x1f/0x30 [dummy_module] [<ffffffff81076b90>] warn_slowpath_common+0xd0/0xd0 [<ffffffffa038e040>] ? dummy_greetings+0x40/0x40 [dummy_module] [<ffffffff81076c8a>] warn_slowpath_null+0x1a/0x20 [<ffffffffa038e05f>] init_dummy+0x1f/0x30 [dummy_module] [<ffffffff81002144>] do_one_initcall+0xd4/0x210 [<ffffffff811b52c2>] ? __vunmap+0xc2/0x110 [<ffffffff810f8889>] load_module+0x16a9/0x1b30 [<ffffffff810f3d30>] ? store_uevent+0x70/0x70 [<ffffffff810f49b9>] ? copy_module_from_fd.isra.44+0x129/0x180 [<ffffffff810f8ec6>] SyS_finit_module+0xa6/0xd0 [<ffffffff8166cf29>] system_call_fastpath+0x12/0x17 Successfully tested by me. hpa said: There is another very valid use for this: many operators would rather a machine shuts down than being potentially compromised either functionally or security-wise. Signed-off-by: Prarit Bhargava <prarit@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Acked-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Fabian Frederick <fabf@skynet.be> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-11 07:45:50 +08:00
extern int panic_on_warn;
extern int sysctl_panic_on_stackoverflow;
extern bool crash_kexec_post_notifiers;
panic, x86: Fix re-entrance problem due to panic on NMI If panic on NMI happens just after panic() on the same CPU, panic() is recursively called. Kernel stalls, as a result, after failing to acquire panic_lock. To avoid this problem, don't call panic() in NMI context if we've already entered panic(). For that, introduce nmi_panic() macro to reduce code duplication. In the case of panic on NMI, don't return from NMI handlers if another CPU already panicked. Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Don Zickus <dzickus@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml <linux-kernel@vger.kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seth Jennings <sjenning@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Link: http://lkml.kernel.org/r/20151210014626.25437.13302.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:09 +08:00
/*
* panic_cpu is used for synchronizing panic() and crash_kexec() execution. It
* holds a CPU number which is executing panic() currently. A value of
* PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec().
*/
extern atomic_t panic_cpu;
#define PANIC_CPU_INVALID -1
/*
* A variant of panic() called from NMI context. We return if we've already
panic, x86: Allow CPUs to save registers even if looping in NMI context Currently, kdump_nmi_shootdown_cpus(), a subroutine of crash_kexec(), sends an NMI IPI to CPUs which haven't called panic() to stop them, save their register information and do some cleanups for crash dumping. However, if such a CPU is infinitely looping in NMI context, we fail to save its register information into the crash dump. For example, this can happen when unknown NMIs are broadcast to all CPUs as follows: CPU 0 CPU 1 =========================== ========================== receive an unknown NMI unknown_nmi_error() panic() receive an unknown NMI spin_trylock(&panic_lock) unknown_nmi_error() crash_kexec() panic() spin_trylock(&panic_lock) panic_smp_self_stop() infinite loop kdump_nmi_shootdown_cpus() issue NMI IPI -----------> blocked until IRET infinite loop... Here, since CPU 1 is in NMI context, the second NMI from CPU 0 is blocked until CPU 1 executes IRET. However, CPU 1 never executes IRET, so the NMI is not handled and the callback function to save registers is never called. In practice, this can happen on some servers which broadcast NMIs to all CPUs when the NMI button is pushed. To save registers in this case, we need to: a) Return from NMI handler instead of looping infinitely or b) Call the callback function directly from the infinite loop Inherently, a) is risky because NMI is also used to prevent corrupted data from being propagated to devices. So, we chose b). This patch does the following: 1. Move the infinite looping of CPUs which haven't called panic() in NMI context (actually done by panic_smp_self_stop()) outside of panic() to enable us to refer pt_regs. Please note that panic_smp_self_stop() is still used for normal context. 2. Call a callback of kdump_nmi_shootdown_cpus() directly to save registers and do some cleanups after setting waiting_for_crash_ipi which is used for counting down the number of CPUs which handled the callback Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Dave Young <dyoung@redhat.com> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml <linux-kernel@vger.kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Seth Jennings <sjenning@redhat.com> Cc: Stefan Lippers-Hollmann <s.l-h@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Link: http://lkml.kernel.org/r/20151210014628.25437.75256.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:10 +08:00
* panicked on this CPU. If another CPU already panicked, loop in
* nmi_panic_self_stop() which can provide architecture dependent code such
* as saving register state for crash dump.
panic, x86: Fix re-entrance problem due to panic on NMI If panic on NMI happens just after panic() on the same CPU, panic() is recursively called. Kernel stalls, as a result, after failing to acquire panic_lock. To avoid this problem, don't call panic() in NMI context if we've already entered panic(). For that, introduce nmi_panic() macro to reduce code duplication. In the case of panic on NMI, don't return from NMI handlers if another CPU already panicked. Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Don Zickus <dzickus@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml <linux-kernel@vger.kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seth Jennings <sjenning@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Link: http://lkml.kernel.org/r/20151210014626.25437.13302.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:09 +08:00
*/
panic, x86: Allow CPUs to save registers even if looping in NMI context Currently, kdump_nmi_shootdown_cpus(), a subroutine of crash_kexec(), sends an NMI IPI to CPUs which haven't called panic() to stop them, save their register information and do some cleanups for crash dumping. However, if such a CPU is infinitely looping in NMI context, we fail to save its register information into the crash dump. For example, this can happen when unknown NMIs are broadcast to all CPUs as follows: CPU 0 CPU 1 =========================== ========================== receive an unknown NMI unknown_nmi_error() panic() receive an unknown NMI spin_trylock(&panic_lock) unknown_nmi_error() crash_kexec() panic() spin_trylock(&panic_lock) panic_smp_self_stop() infinite loop kdump_nmi_shootdown_cpus() issue NMI IPI -----------> blocked until IRET infinite loop... Here, since CPU 1 is in NMI context, the second NMI from CPU 0 is blocked until CPU 1 executes IRET. However, CPU 1 never executes IRET, so the NMI is not handled and the callback function to save registers is never called. In practice, this can happen on some servers which broadcast NMIs to all CPUs when the NMI button is pushed. To save registers in this case, we need to: a) Return from NMI handler instead of looping infinitely or b) Call the callback function directly from the infinite loop Inherently, a) is risky because NMI is also used to prevent corrupted data from being propagated to devices. So, we chose b). This patch does the following: 1. Move the infinite looping of CPUs which haven't called panic() in NMI context (actually done by panic_smp_self_stop()) outside of panic() to enable us to refer pt_regs. Please note that panic_smp_self_stop() is still used for normal context. 2. Call a callback of kdump_nmi_shootdown_cpus() directly to save registers and do some cleanups after setting waiting_for_crash_ipi which is used for counting down the number of CPUs which handled the callback Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Dave Young <dyoung@redhat.com> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml <linux-kernel@vger.kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Seth Jennings <sjenning@redhat.com> Cc: Stefan Lippers-Hollmann <s.l-h@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Link: http://lkml.kernel.org/r/20151210014628.25437.75256.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:10 +08:00
#define nmi_panic(regs, fmt, ...) \
panic, x86: Fix re-entrance problem due to panic on NMI If panic on NMI happens just after panic() on the same CPU, panic() is recursively called. Kernel stalls, as a result, after failing to acquire panic_lock. To avoid this problem, don't call panic() in NMI context if we've already entered panic(). For that, introduce nmi_panic() macro to reduce code duplication. In the case of panic on NMI, don't return from NMI handlers if another CPU already panicked. Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Don Zickus <dzickus@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml <linux-kernel@vger.kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seth Jennings <sjenning@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Link: http://lkml.kernel.org/r/20151210014626.25437.13302.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:09 +08:00
do { \
panic, x86: Allow CPUs to save registers even if looping in NMI context Currently, kdump_nmi_shootdown_cpus(), a subroutine of crash_kexec(), sends an NMI IPI to CPUs which haven't called panic() to stop them, save their register information and do some cleanups for crash dumping. However, if such a CPU is infinitely looping in NMI context, we fail to save its register information into the crash dump. For example, this can happen when unknown NMIs are broadcast to all CPUs as follows: CPU 0 CPU 1 =========================== ========================== receive an unknown NMI unknown_nmi_error() panic() receive an unknown NMI spin_trylock(&panic_lock) unknown_nmi_error() crash_kexec() panic() spin_trylock(&panic_lock) panic_smp_self_stop() infinite loop kdump_nmi_shootdown_cpus() issue NMI IPI -----------> blocked until IRET infinite loop... Here, since CPU 1 is in NMI context, the second NMI from CPU 0 is blocked until CPU 1 executes IRET. However, CPU 1 never executes IRET, so the NMI is not handled and the callback function to save registers is never called. In practice, this can happen on some servers which broadcast NMIs to all CPUs when the NMI button is pushed. To save registers in this case, we need to: a) Return from NMI handler instead of looping infinitely or b) Call the callback function directly from the infinite loop Inherently, a) is risky because NMI is also used to prevent corrupted data from being propagated to devices. So, we chose b). This patch does the following: 1. Move the infinite looping of CPUs which haven't called panic() in NMI context (actually done by panic_smp_self_stop()) outside of panic() to enable us to refer pt_regs. Please note that panic_smp_self_stop() is still used for normal context. 2. Call a callback of kdump_nmi_shootdown_cpus() directly to save registers and do some cleanups after setting waiting_for_crash_ipi which is used for counting down the number of CPUs which handled the callback Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Dave Young <dyoung@redhat.com> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml <linux-kernel@vger.kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Seth Jennings <sjenning@redhat.com> Cc: Stefan Lippers-Hollmann <s.l-h@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Link: http://lkml.kernel.org/r/20151210014628.25437.75256.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:10 +08:00
int old_cpu, cpu; \
panic, x86: Fix re-entrance problem due to panic on NMI If panic on NMI happens just after panic() on the same CPU, panic() is recursively called. Kernel stalls, as a result, after failing to acquire panic_lock. To avoid this problem, don't call panic() in NMI context if we've already entered panic(). For that, introduce nmi_panic() macro to reduce code duplication. In the case of panic on NMI, don't return from NMI handlers if another CPU already panicked. Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Don Zickus <dzickus@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml <linux-kernel@vger.kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seth Jennings <sjenning@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Link: http://lkml.kernel.org/r/20151210014626.25437.13302.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:09 +08:00
\
panic, x86: Allow CPUs to save registers even if looping in NMI context Currently, kdump_nmi_shootdown_cpus(), a subroutine of crash_kexec(), sends an NMI IPI to CPUs which haven't called panic() to stop them, save their register information and do some cleanups for crash dumping. However, if such a CPU is infinitely looping in NMI context, we fail to save its register information into the crash dump. For example, this can happen when unknown NMIs are broadcast to all CPUs as follows: CPU 0 CPU 1 =========================== ========================== receive an unknown NMI unknown_nmi_error() panic() receive an unknown NMI spin_trylock(&panic_lock) unknown_nmi_error() crash_kexec() panic() spin_trylock(&panic_lock) panic_smp_self_stop() infinite loop kdump_nmi_shootdown_cpus() issue NMI IPI -----------> blocked until IRET infinite loop... Here, since CPU 1 is in NMI context, the second NMI from CPU 0 is blocked until CPU 1 executes IRET. However, CPU 1 never executes IRET, so the NMI is not handled and the callback function to save registers is never called. In practice, this can happen on some servers which broadcast NMIs to all CPUs when the NMI button is pushed. To save registers in this case, we need to: a) Return from NMI handler instead of looping infinitely or b) Call the callback function directly from the infinite loop Inherently, a) is risky because NMI is also used to prevent corrupted data from being propagated to devices. So, we chose b). This patch does the following: 1. Move the infinite looping of CPUs which haven't called panic() in NMI context (actually done by panic_smp_self_stop()) outside of panic() to enable us to refer pt_regs. Please note that panic_smp_self_stop() is still used for normal context. 2. Call a callback of kdump_nmi_shootdown_cpus() directly to save registers and do some cleanups after setting waiting_for_crash_ipi which is used for counting down the number of CPUs which handled the callback Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Dave Young <dyoung@redhat.com> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml <linux-kernel@vger.kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Seth Jennings <sjenning@redhat.com> Cc: Stefan Lippers-Hollmann <s.l-h@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Link: http://lkml.kernel.org/r/20151210014628.25437.75256.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:10 +08:00
cpu = raw_smp_processor_id(); \
old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu); \
\
if (old_cpu == PANIC_CPU_INVALID) \
panic, x86: Fix re-entrance problem due to panic on NMI If panic on NMI happens just after panic() on the same CPU, panic() is recursively called. Kernel stalls, as a result, after failing to acquire panic_lock. To avoid this problem, don't call panic() in NMI context if we've already entered panic(). For that, introduce nmi_panic() macro to reduce code duplication. In the case of panic on NMI, don't return from NMI handlers if another CPU already panicked. Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Don Zickus <dzickus@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml <linux-kernel@vger.kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seth Jennings <sjenning@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Link: http://lkml.kernel.org/r/20151210014626.25437.13302.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:09 +08:00
panic(fmt, ##__VA_ARGS__); \
panic, x86: Allow CPUs to save registers even if looping in NMI context Currently, kdump_nmi_shootdown_cpus(), a subroutine of crash_kexec(), sends an NMI IPI to CPUs which haven't called panic() to stop them, save their register information and do some cleanups for crash dumping. However, if such a CPU is infinitely looping in NMI context, we fail to save its register information into the crash dump. For example, this can happen when unknown NMIs are broadcast to all CPUs as follows: CPU 0 CPU 1 =========================== ========================== receive an unknown NMI unknown_nmi_error() panic() receive an unknown NMI spin_trylock(&panic_lock) unknown_nmi_error() crash_kexec() panic() spin_trylock(&panic_lock) panic_smp_self_stop() infinite loop kdump_nmi_shootdown_cpus() issue NMI IPI -----------> blocked until IRET infinite loop... Here, since CPU 1 is in NMI context, the second NMI from CPU 0 is blocked until CPU 1 executes IRET. However, CPU 1 never executes IRET, so the NMI is not handled and the callback function to save registers is never called. In practice, this can happen on some servers which broadcast NMIs to all CPUs when the NMI button is pushed. To save registers in this case, we need to: a) Return from NMI handler instead of looping infinitely or b) Call the callback function directly from the infinite loop Inherently, a) is risky because NMI is also used to prevent corrupted data from being propagated to devices. So, we chose b). This patch does the following: 1. Move the infinite looping of CPUs which haven't called panic() in NMI context (actually done by panic_smp_self_stop()) outside of panic() to enable us to refer pt_regs. Please note that panic_smp_self_stop() is still used for normal context. 2. Call a callback of kdump_nmi_shootdown_cpus() directly to save registers and do some cleanups after setting waiting_for_crash_ipi which is used for counting down the number of CPUs which handled the callback Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Dave Young <dyoung@redhat.com> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml <linux-kernel@vger.kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Seth Jennings <sjenning@redhat.com> Cc: Stefan Lippers-Hollmann <s.l-h@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Link: http://lkml.kernel.org/r/20151210014628.25437.75256.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:10 +08:00
else if (old_cpu != cpu) \
nmi_panic_self_stop(regs); \
panic, x86: Fix re-entrance problem due to panic on NMI If panic on NMI happens just after panic() on the same CPU, panic() is recursively called. Kernel stalls, as a result, after failing to acquire panic_lock. To avoid this problem, don't call panic() in NMI context if we've already entered panic(). For that, introduce nmi_panic() macro to reduce code duplication. In the case of panic on NMI, don't return from NMI handlers if another CPU already panicked. Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Don Zickus <dzickus@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml <linux-kernel@vger.kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seth Jennings <sjenning@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Link: http://lkml.kernel.org/r/20151210014626.25437.13302.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-12-14 18:19:09 +08:00
} while (0)
/*
* Only to be used by arch init code. If the user over-wrote the default
* CONFIG_PANIC_TIMEOUT, honor it.
*/
static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout)
{
if (panic_timeout == arch_default_timeout)
panic_timeout = timeout;
}
extern const char *print_tainted(void);
enum lockdep_ok {
LOCKDEP_STILL_OK,
LOCKDEP_NOW_UNRELIABLE
};
extern void add_taint(unsigned flag, enum lockdep_ok);
extern int test_taint(unsigned flag);
extern unsigned long get_taint(void);
extern int root_mountflags;
extern bool early_boot_irqs_disabled;
/* Values used for system_state */
extern enum system_states {
SYSTEM_BOOTING,
SYSTEM_RUNNING,
SYSTEM_HALT,
SYSTEM_POWER_OFF,
SYSTEM_RESTART,
} system_state;
#define TAINT_PROPRIETARY_MODULE 0
#define TAINT_FORCED_MODULE 1
#define TAINT_CPU_OUT_OF_SPEC 2
#define TAINT_FORCED_RMMOD 3
#define TAINT_MACHINE_CHECK 4
#define TAINT_BAD_PAGE 5
#define TAINT_USER 6
#define TAINT_DIE 7
#define TAINT_OVERRIDDEN_ACPI_TABLE 8
#define TAINT_WARN 9
#define TAINT_CRAP 10
#define TAINT_FIRMWARE_WORKAROUND 11
#define TAINT_OOT_MODULE 12
Fix: module signature vs tracepoints: add new TAINT_UNSIGNED_MODULE Users have reported being unable to trace non-signed modules loaded within a kernel supporting module signature. This is caused by tracepoint.c:tracepoint_module_coming() refusing to take into account tracepoints sitting within force-loaded modules (TAINT_FORCED_MODULE). The reason for this check, in the first place, is that a force-loaded module may have a struct module incompatible with the layout expected by the kernel, and can thus cause a kernel crash upon forced load of that module on a kernel with CONFIG_TRACEPOINTS=y. Tracepoints, however, specifically accept TAINT_OOT_MODULE and TAINT_CRAP, since those modules do not lead to the "very likely system crash" issue cited above for force-loaded modules. With kernels having CONFIG_MODULE_SIG=y (signed modules), a non-signed module is tainted re-using the TAINT_FORCED_MODULE taint flag. Unfortunately, this means that Tracepoints treat that module as a force-loaded module, and thus silently refuse to consider any tracepoint within this module. Since an unsigned module does not fit within the "very likely system crash" category of tainting, add a new TAINT_UNSIGNED_MODULE taint flag to specifically address this taint behavior, and accept those modules within Tracepoints. We use the letter 'X' as a taint flag character for a module being loaded that doesn't know how to sign its name (proposed by Steven Rostedt). Also add the missing 'O' entry to trace event show_module_flags() list for the sake of completeness. Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> NAKed-by: Ingo Molnar <mingo@redhat.com> CC: Thomas Gleixner <tglx@linutronix.de> CC: David Howells <dhowells@redhat.com> CC: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2014-03-13 09:41:30 +08:00
#define TAINT_UNSIGNED_MODULE 13
#define TAINT_SOFTLOCKUP 14
#define TAINT_LIVEPATCH 15
extern const char hex_asc[];
#define hex_asc_lo(x) hex_asc[((x) & 0x0f)]
#define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4]
static inline char *hex_byte_pack(char *buf, u8 byte)
{
*buf++ = hex_asc_hi(byte);
*buf++ = hex_asc_lo(byte);
return buf;
}
extern const char hex_asc_upper[];
#define hex_asc_upper_lo(x) hex_asc_upper[((x) & 0x0f)]
#define hex_asc_upper_hi(x) hex_asc_upper[((x) & 0xf0) >> 4]
static inline char *hex_byte_pack_upper(char *buf, u8 byte)
{
*buf++ = hex_asc_upper_hi(byte);
*buf++ = hex_asc_upper_lo(byte);
return buf;
}
extern int hex_to_bin(char ch);
extern int __must_check hex2bin(u8 *dst, const char *src, size_t count);
extern char *bin2hex(char *dst, const void *src, size_t count);
bool mac_pton(const char *s, u8 *mac);
/*
* General tracing related utility functions - trace_printk(),
tracing: add tracing_on/tracing_off to kernel.h Impact: cleanup The functions tracing_start/tracing_stop have been moved to kernel.h. These are not the functions a developer most likely wants to use when they want to insert a place to stop tracing and restart it from user space. tracing_start/tracing_stop was created to work with things like suspend to ram, where even calling smp_processor_id() can crash the system. The tracing_start/tracing_stop was used to stop the tracer from doing anything. These are still light weight functions, but add a bit more overhead to be able to stop the tracers. They also have no interface back to userland. That is, if the kernel calls tracing_stop, userland can not start tracing. What a developer most likely wants to use is tracing_on/tracing_off. These are very light weight functions (simply sets or clears a bit). These functions just stop recording into the ring buffer. The tracers don't even know that this happens except that they would receive NULL from the ring_buffer_lock_reserve function. Also, there's a way for the user land to enable or disable this bit. In debugfs/tracing/tracing_on, a user may echo "0" (same as tracing_off()) or echo "1" (same as tracing_on()) into this file. This becomes handy when a kernel developer is debugging and wants tracing to turn off when it hits an anomaly. Then the developer can examine the trace, and restart tracing if they want to try again (echo 1 > tracing_on). This patch moves the prototypes for tracing_on/tracing_off to kernel.h and comments their use, so that a kernel developer will know how to use them. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-03-05 23:35:56 +08:00
* tracing_on/tracing_off and tracing_start()/tracing_stop
*
* Use tracing_on/tracing_off when you want to quickly turn on or off
* tracing. It simply enables or disables the recording of the trace events.
* This also corresponds to the user space /sys/kernel/debug/tracing/tracing_on
tracing: add tracing_on/tracing_off to kernel.h Impact: cleanup The functions tracing_start/tracing_stop have been moved to kernel.h. These are not the functions a developer most likely wants to use when they want to insert a place to stop tracing and restart it from user space. tracing_start/tracing_stop was created to work with things like suspend to ram, where even calling smp_processor_id() can crash the system. The tracing_start/tracing_stop was used to stop the tracer from doing anything. These are still light weight functions, but add a bit more overhead to be able to stop the tracers. They also have no interface back to userland. That is, if the kernel calls tracing_stop, userland can not start tracing. What a developer most likely wants to use is tracing_on/tracing_off. These are very light weight functions (simply sets or clears a bit). These functions just stop recording into the ring buffer. The tracers don't even know that this happens except that they would receive NULL from the ring_buffer_lock_reserve function. Also, there's a way for the user land to enable or disable this bit. In debugfs/tracing/tracing_on, a user may echo "0" (same as tracing_off()) or echo "1" (same as tracing_on()) into this file. This becomes handy when a kernel developer is debugging and wants tracing to turn off when it hits an anomaly. Then the developer can examine the trace, and restart tracing if they want to try again (echo 1 > tracing_on). This patch moves the prototypes for tracing_on/tracing_off to kernel.h and comments their use, so that a kernel developer will know how to use them. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-03-05 23:35:56 +08:00
* file, which gives a means for the kernel and userspace to interact.
* Place a tracing_off() in the kernel where you want tracing to end.
* From user space, examine the trace, and then echo 1 > tracing_on
* to continue tracing.
*
* tracing_stop/tracing_start has slightly more overhead. It is used
* by things like suspend to ram where disabling the recording of the
* trace is not enough, but tracing must actually stop because things
* like calling smp_processor_id() may crash the system.
*
* Most likely, you want to use tracing_on/tracing_off.
*/
enum ftrace_dump_mode {
DUMP_NONE,
DUMP_ALL,
DUMP_ORIG,
};
#ifdef CONFIG_TRACING
void tracing_on(void);
void tracing_off(void);
int tracing_is_on(void);
tracing: Add internal tracing_snapshot() functions The new snapshot feature is quite handy. It's a way for the user to take advantage of the spare buffer that, until then, only the latency tracers used to "snapshot" the buffer when it hit a max latency. Now users can trigger a "snapshot" manually when some condition is hit in a program. But a snapshot currently can not be triggered by a condition inside the kernel. With the addition of tracing_snapshot() and tracing_snapshot_alloc(), snapshots can now be taking when a condition is hit, and the developer wants to snapshot the case without stopping the trace. Note, any snapshot will overwrite the old one, so take care in how this is done. These new functions are to be used like tracing_on(), tracing_off() and trace_printk() are. That is, they should never be called in the mainline Linux kernel. They are solely for the purpose of debugging. The tracing_snapshot() will not allocate a buffer, but it is safe to be called from any context (except NMIs). But if a snapshot buffer isn't allocated when it is called, it will write to the live buffer, complaining about the lack of a snapshot buffer, and then stop tracing (giving you the "permanent snapshot"). tracing_snapshot_alloc() will allocate the snapshot buffer if it was not already allocated and then take the snapshot. This routine *may sleep*, and must be called from context that can sleep. The allocation is done with GFP_KERNEL and not atomic. If you need a snapshot in an atomic context, say in early boot, then it is best to call the tracing_snapshot_alloc() before then, where it will allocate the buffer, and then you can use the tracing_snapshot() anywhere you want and still get snapshots. Cc: Hiraku Toyooka <hiraku.toyooka.gu@hitachi.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-03-07 10:45:37 +08:00
void tracing_snapshot(void);
void tracing_snapshot_alloc(void);
extern void tracing_start(void);
extern void tracing_stop(void);
static inline __printf(1, 2)
void ____trace_printk_check_format(const char *fmt, ...)
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
{
}
#define __trace_printk_check_format(fmt, args...) \
do { \
if (0) \
____trace_printk_check_format(fmt, ##args); \
} while (0)
/**
* trace_printk - printf formatting in the ftrace buffer
* @fmt: the printf format for printing
*
* Note: __trace_printk is an internal function for trace_printk and
* the @ip is passed in via the trace_printk macro.
*
* This function allows a kernel developer to debug fast path sections
* that printk is not appropriate for. By scattering in various
* printk like tracing in the code, a developer can quickly see
* where problems are occurring.
*
* This is intended as a debugging tool for the developer only.
* Please refrain from leaving trace_printks scattered around in
* your code. (Extra memory is used for special buffers that are
* allocated when trace_printk() is used)
tracing: Optimize trace_printk() with one arg to use trace_puts() Although trace_printk() is extremely fast, especially when it uses trace_bprintk() (writes args straight to buffer instead of inserting into string), it still has the overhead of calling one of the printf sprintf() functions, that need to scan the fmt string to determine what, if any args it has. This is a waste of precious CPU cycles if the printk format has no args but a single constant string. It is better to use trace_puts() which does not have the overhead of the fmt scanning. But wouldn't it be nice if the developer didn't have to think about such things, and the compile would just do it for them? trace_printk("this string has no args\n"); [...] trace_printk("this sting does %p %d\n", foo, bar); As tracing is critical to have the least amount of overhead, especially when dealing with race conditions, and you want to eliminate any "Heisenbugs", you want the trace_printk() to use the fastest possible means of tracing. Currently the macro magic determines if it will use trace_bprintk() or if the fmt is a dynamic string (a variable), it will fall back to the slow trace_printk() method that does a full snprintf() before copying it into the buffer, where as trace_bprintk() only copys the pointer to the fmt and the args into the buffer. Well, now there's a way to spend some more Hogwarts cash and come up with new fancy macro magic. #define trace_printk(fmt, ...) \ do { \ char _______STR[] = __stringify((__VA_ARGS__)); \ if (sizeof(_______STR) > 3) \ do_trace_printk(fmt, ##__VA_ARGS__); \ else \ trace_puts(fmt); \ } while (0) The above needs a bit of explaining (both here and in the comments). By stringifying the __VA_ARGS__, we can, at compile time, determine the number of args that are being passed to trace_printk(). The extra parenthesis are required, otherwise the compiler complains about too many parameters for __stringify if there is more than one arg. When there are no args, the __stringify((__VA_ARGS__)) converts into "()\0", a string of 3 characters. Anything else, will be a string containing more than 3 characters. Now we assign that string to a dynamic char array, and then take the sizeof() of that array. If it is greater than 3 characters, we know trace_printk() has args and we need to do the full "do_trace_printk()" on them, otherwise it was only passed a single arg and we can optimize to use trace_puts(). Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven "The King of Nasty Macros!" Rostedt <rostedt@goodmis.org>
2013-03-09 11:11:57 +08:00
*
* A little optization trick is done here. If there's only one
* argument, there's no need to scan the string for printf formats.
* The trace_puts() will suffice. But how can we take advantage of
* using trace_puts() when trace_printk() has only one argument?
* By stringifying the args and checking the size we can tell
* whether or not there are args. __stringify((__VA_ARGS__)) will
* turn into "()\0" with a size of 3 when there are no args, anything
* else will be bigger. All we need to do is define a string to this,
* and then take its size and compare to 3. If it's bigger, use
* do_trace_printk() otherwise, optimize it to trace_puts(). Then just
* let gcc optimize the rest.
*/
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
tracing: Optimize trace_printk() with one arg to use trace_puts() Although trace_printk() is extremely fast, especially when it uses trace_bprintk() (writes args straight to buffer instead of inserting into string), it still has the overhead of calling one of the printf sprintf() functions, that need to scan the fmt string to determine what, if any args it has. This is a waste of precious CPU cycles if the printk format has no args but a single constant string. It is better to use trace_puts() which does not have the overhead of the fmt scanning. But wouldn't it be nice if the developer didn't have to think about such things, and the compile would just do it for them? trace_printk("this string has no args\n"); [...] trace_printk("this sting does %p %d\n", foo, bar); As tracing is critical to have the least amount of overhead, especially when dealing with race conditions, and you want to eliminate any "Heisenbugs", you want the trace_printk() to use the fastest possible means of tracing. Currently the macro magic determines if it will use trace_bprintk() or if the fmt is a dynamic string (a variable), it will fall back to the slow trace_printk() method that does a full snprintf() before copying it into the buffer, where as trace_bprintk() only copys the pointer to the fmt and the args into the buffer. Well, now there's a way to spend some more Hogwarts cash and come up with new fancy macro magic. #define trace_printk(fmt, ...) \ do { \ char _______STR[] = __stringify((__VA_ARGS__)); \ if (sizeof(_______STR) > 3) \ do_trace_printk(fmt, ##__VA_ARGS__); \ else \ trace_puts(fmt); \ } while (0) The above needs a bit of explaining (both here and in the comments). By stringifying the __VA_ARGS__, we can, at compile time, determine the number of args that are being passed to trace_printk(). The extra parenthesis are required, otherwise the compiler complains about too many parameters for __stringify if there is more than one arg. When there are no args, the __stringify((__VA_ARGS__)) converts into "()\0", a string of 3 characters. Anything else, will be a string containing more than 3 characters. Now we assign that string to a dynamic char array, and then take the sizeof() of that array. If it is greater than 3 characters, we know trace_printk() has args and we need to do the full "do_trace_printk()" on them, otherwise it was only passed a single arg and we can optimize to use trace_puts(). Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven "The King of Nasty Macros!" Rostedt <rostedt@goodmis.org>
2013-03-09 11:11:57 +08:00
#define trace_printk(fmt, ...) \
do { \
char _______STR[] = __stringify((__VA_ARGS__)); \
if (sizeof(_______STR) > 3) \
do_trace_printk(fmt, ##__VA_ARGS__); \
else \
trace_puts(fmt); \
} while (0)
#define do_trace_printk(fmt, args...) \
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
do { \
2011-09-23 02:01:55 +08:00
static const char *trace_printk_fmt \
__attribute__((section("__trace_printk_fmt"))) = \
__builtin_constant_p(fmt) ? fmt : NULL; \
\
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
__trace_printk_check_format(fmt, ##args); \
\
2011-09-23 02:01:55 +08:00
if (__builtin_constant_p(fmt)) \
__trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args); \
2011-09-23 02:01:55 +08:00
else \
__trace_printk(_THIS_IP_, fmt, ##args); \
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
} while (0)
extern __printf(2, 3)
int __trace_bprintk(unsigned long ip, const char *fmt, ...);
extern __printf(2, 3)
int __trace_printk(unsigned long ip, const char *fmt, ...);
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
/**
* trace_puts - write a string into the ftrace buffer
* @str: the string to record
*
* Note: __trace_bputs is an internal function for trace_puts and
* the @ip is passed in via the trace_puts macro.
*
* This is similar to trace_printk() but is made for those really fast
* paths that a developer wants the least amount of "Heisenbug" affects,
* where the processing of the print format is still too much.
*
* This function allows a kernel developer to debug fast path sections
* that printk is not appropriate for. By scattering in various
* printk like tracing in the code, a developer can quickly see
* where problems are occurring.
*
* This is intended as a debugging tool for the developer only.
* Please refrain from leaving trace_puts scattered around in
* your code. (Extra memory is used for special buffers that are
* allocated when trace_puts() is used)
*
* Returns: 0 if nothing was written, positive # if string was.
* (1 when __trace_bputs is used, strlen(str) when __trace_puts is used)
*/
#define trace_puts(str) ({ \
static const char *trace_printk_fmt \
__attribute__((section("__trace_printk_fmt"))) = \
__builtin_constant_p(str) ? str : NULL; \
\
if (__builtin_constant_p(str)) \
__trace_bputs(_THIS_IP_, trace_printk_fmt); \
else \
__trace_puts(_THIS_IP_, str, strlen(str)); \
})
extern int __trace_bputs(unsigned long ip, const char *str);
extern int __trace_puts(unsigned long ip, const char *str, int size);
extern void trace_dump_stack(int skip);
/*
* 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
* constant. Even with the outer if statement.
*/
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
#define ftrace_vprintk(fmt, vargs) \
do { \
if (__builtin_constant_p(fmt)) { \
static const char *trace_printk_fmt \
__attribute__((section("__trace_printk_fmt"))) = \
__builtin_constant_p(fmt) ? fmt : NULL; \
\
__ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs); \
} else \
__ftrace_vprintk(_THIS_IP_, fmt, vargs); \
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
} while (0)
extern __printf(2, 0) int
__ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap);
extern __printf(2, 0) int
__ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode);
#else
static inline void tracing_start(void) { }
static inline void tracing_stop(void) { }
static inline void trace_dump_stack(int skip) { }
static inline void tracing_on(void) { }
static inline void tracing_off(void) { }
static inline int tracing_is_on(void) { return 0; }
tracing: Add internal tracing_snapshot() functions The new snapshot feature is quite handy. It's a way for the user to take advantage of the spare buffer that, until then, only the latency tracers used to "snapshot" the buffer when it hit a max latency. Now users can trigger a "snapshot" manually when some condition is hit in a program. But a snapshot currently can not be triggered by a condition inside the kernel. With the addition of tracing_snapshot() and tracing_snapshot_alloc(), snapshots can now be taking when a condition is hit, and the developer wants to snapshot the case without stopping the trace. Note, any snapshot will overwrite the old one, so take care in how this is done. These new functions are to be used like tracing_on(), tracing_off() and trace_printk() are. That is, they should never be called in the mainline Linux kernel. They are solely for the purpose of debugging. The tracing_snapshot() will not allocate a buffer, but it is safe to be called from any context (except NMIs). But if a snapshot buffer isn't allocated when it is called, it will write to the live buffer, complaining about the lack of a snapshot buffer, and then stop tracing (giving you the "permanent snapshot"). tracing_snapshot_alloc() will allocate the snapshot buffer if it was not already allocated and then take the snapshot. This routine *may sleep*, and must be called from context that can sleep. The allocation is done with GFP_KERNEL and not atomic. If you need a snapshot in an atomic context, say in early boot, then it is best to call the tracing_snapshot_alloc() before then, where it will allocate the buffer, and then you can use the tracing_snapshot() anywhere you want and still get snapshots. Cc: Hiraku Toyooka <hiraku.toyooka.gu@hitachi.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-03-07 10:45:37 +08:00
static inline void tracing_snapshot(void) { }
static inline void tracing_snapshot_alloc(void) { }
static inline __printf(1, 2)
int trace_printk(const char *fmt, ...)
{
return 0;
}
static __printf(1, 0) inline int
ftrace_vprintk(const char *fmt, va_list ap)
{
return 0;
}
static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
#endif /* CONFIG_TRACING */
/*
* min()/max()/clamp() macros that also do
* strict type-checking.. See the
* "unnecessary" pointer comparison.
*/
#define min(x, y) ({ \
typeof(x) _min1 = (x); \
typeof(y) _min2 = (y); \
(void) (&_min1 == &_min2); \
_min1 < _min2 ? _min1 : _min2; })
#define max(x, y) ({ \
typeof(x) _max1 = (x); \
typeof(y) _max2 = (y); \
(void) (&_max1 == &_max2); \
_max1 > _max2 ? _max1 : _max2; })
include/linux/kernel.h: rewrite min3, max3 and clamp using min and max It appears that gcc is better at optimising a double call to min and max rather than open coded min3 and max3. This can be observed here: $ cat min-max.c #define min(x, y) ({ \ typeof(x) _min1 = (x); \ typeof(y) _min2 = (y); \ (void) (&_min1 == &_min2); \ _min1 < _min2 ? _min1 : _min2; }) #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); }) int fmin3(int x, int y, int z) { return min3(x, y, z); } int fmin2(int x, int y, int z) { return min(min(x, y), z); } $ gcc -O2 -o min-max.s -S min-max.c; cat min-max.s .file "min-max.c" .text .p2align 4,,15 .globl fmin3 .type fmin3, @function fmin3: .LFB0: .cfi_startproc cmpl %esi, %edi jl .L5 cmpl %esi, %edx movl %esi, %eax cmovle %edx, %eax ret .p2align 4,,10 .p2align 3 .L5: cmpl %edi, %edx movl %edi, %eax cmovle %edx, %eax ret .cfi_endproc .LFE0: .size fmin3, .-fmin3 .p2align 4,,15 .globl fmin2 .type fmin2, @function fmin2: .LFB1: .cfi_startproc cmpl %edi, %esi movl %edx, %eax cmovle %esi, %edi cmpl %edx, %edi cmovle %edi, %eax ret .cfi_endproc .LFE1: .size fmin2, .-fmin2 .ident "GCC: (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3" .section .note.GNU-stack,"",@progbits fmin3 function, which uses open-coded min3 macro, is compiled into total of ten instructions including a conditional branch, whereas fmin2 function, which uses two calls to min2 macro, is compiled into six instructions with no branches. Similarly, open-coded clamp produces the same code as clamp using min and max macros, but the latter is much shorter: $ cat clamp.c #define clamp(val, min, max) ({ \ typeof(val) __val = (val); \ typeof(min) __min = (min); \ typeof(max) __max = (max); \ (void) (&__val == &__min); \ (void) (&__val == &__max); \ __val = __val < __min ? __min: __val; \ __val > __max ? __max: __val; }) #define min(x, y) ({ \ typeof(x) _min1 = (x); \ typeof(y) _min2 = (y); \ (void) (&_min1 == &_min2); \ _min1 < _min2 ? _min1 : _min2; }) #define max(x, y) ({ \ typeof(x) _max1 = (x); \ typeof(y) _max2 = (y); \ (void) (&_max1 == &_max2); \ _max1 > _max2 ? _max1 : _max2; }) int fclamp(int v, int min, int max) { return clamp(v, min, max); } int fclampmm(int v, int min, int max) { return min(max(v, min), max); } $ gcc -O2 -o clamp.s -S clamp.c; cat clamp.s .file "clamp.c" .text .p2align 4,,15 .globl fclamp .type fclamp, @function fclamp: .LFB0: .cfi_startproc cmpl %edi, %esi movl %edx, %eax cmovge %esi, %edi cmpl %edx, %edi cmovle %edi, %eax ret .cfi_endproc .LFE0: .size fclamp, .-fclamp .p2align 4,,15 .globl fclampmm .type fclampmm, @function fclampmm: .LFB1: .cfi_startproc cmpl %edi, %esi cmovge %esi, %edi cmpl %edi, %edx movl %edi, %eax cmovle %edx, %eax ret .cfi_endproc .LFE1: .size fclampmm, .-fclampmm .ident "GCC: (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3" .section .note.GNU-stack,"",@progbits Linux mpn-glaptop 3.13.0-29-generic #53~precise1-Ubuntu SMP Wed Jun 4 22:06:25 UTC 2014 x86_64 x86_64 x86_64 GNU/Linux gcc (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3 Copyright (C) 2011 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. -rwx------ 1 mpn eng 51224656 Jun 17 14:15 vmlinux.before -rwx------ 1 mpn eng 51224608 Jun 17 13:57 vmlinux.after 48 bytes reduction. The do_fault_around was a few instruction shorter and as far as I can tell saved 12 bytes on the stack, i.e.: $ grep -e rsp -e pop -e push do_fault_around.* do_fault_around.before.s:push %rbp do_fault_around.before.s:mov %rsp,%rbp do_fault_around.before.s:push %r13 do_fault_around.before.s:push %r12 do_fault_around.before.s:push %rbx do_fault_around.before.s:sub $0x38,%rsp do_fault_around.before.s:add $0x38,%rsp do_fault_around.before.s:pop %rbx do_fault_around.before.s:pop %r12 do_fault_around.before.s:pop %r13 do_fault_around.before.s:pop %rbp do_fault_around.after.s:push %rbp do_fault_around.after.s:mov %rsp,%rbp do_fault_around.after.s:push %r12 do_fault_around.after.s:push %rbx do_fault_around.after.s:sub $0x30,%rsp do_fault_around.after.s:add $0x30,%rsp do_fault_around.after.s:pop %rbx do_fault_around.after.s:pop %r12 do_fault_around.after.s:pop %rbp or here side-by-side: Before After push %rbp push %rbp mov %rsp,%rbp mov %rsp,%rbp push %r13 push %r12 push %r12 push %rbx push %rbx sub $0x38,%rsp sub $0x30,%rsp add $0x38,%rsp add $0x30,%rsp pop %rbx pop %rbx pop %r12 pop %r12 pop %r13 pop %rbp pop %rbp There are also fewer branches: $ grep ^j do_fault_around.* do_fault_around.before.s:jae ffffffff812079b7 do_fault_around.before.s:jmp ffffffff812079c5 do_fault_around.before.s:jmp ffffffff81207a14 do_fault_around.before.s:ja ffffffff812079f9 do_fault_around.before.s:jb ffffffff81207a10 do_fault_around.before.s:jmp ffffffff81207a63 do_fault_around.before.s:jne ffffffff812079df do_fault_around.after.s:jmp ffffffff812079fd do_fault_around.after.s:ja ffffffff812079e2 do_fault_around.after.s:jb ffffffff812079f9 do_fault_around.after.s:jmp ffffffff81207a4c do_fault_around.after.s:jne ffffffff812079c8 And here's with allyesconfig on a different machine: $ uname -a; gcc --version; ls -l vmlinux.* Linux erwin 3.14.7-mn #54 SMP Sun Jun 15 11:25:08 CEST 2014 x86_64 AMD Phenom(tm) II X3 710 Processor AuthenticAMD GNU/Linux gcc (GCC) 4.8.3 Copyright (C) 2013 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. -rwx------ 1 mpn eng 437027411 Jun 20 16:04 vmlinux.before -rwx------ 1 mpn eng 437026881 Jun 20 15:30 vmlinux.after 530 bytes reduction. Signed-off-by: Michal Nazarewicz <mina86@mina86.com> Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Cc: David Rientjes <rientjes@google.com> Cc: "Rustad, Mark D" <mark.d.rustad@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-10 06:30:13 +08:00
#define min3(x, y, z) min((typeof(x))min(x, y), z)
#define max3(x, y, z) max((typeof(x))max(x, y), z)
/**
* 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
include/linux/kernel.h: rewrite min3, max3 and clamp using min and max It appears that gcc is better at optimising a double call to min and max rather than open coded min3 and max3. This can be observed here: $ cat min-max.c #define min(x, y) ({ \ typeof(x) _min1 = (x); \ typeof(y) _min2 = (y); \ (void) (&_min1 == &_min2); \ _min1 < _min2 ? _min1 : _min2; }) #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); }) int fmin3(int x, int y, int z) { return min3(x, y, z); } int fmin2(int x, int y, int z) { return min(min(x, y), z); } $ gcc -O2 -o min-max.s -S min-max.c; cat min-max.s .file "min-max.c" .text .p2align 4,,15 .globl fmin3 .type fmin3, @function fmin3: .LFB0: .cfi_startproc cmpl %esi, %edi jl .L5 cmpl %esi, %edx movl %esi, %eax cmovle %edx, %eax ret .p2align 4,,10 .p2align 3 .L5: cmpl %edi, %edx movl %edi, %eax cmovle %edx, %eax ret .cfi_endproc .LFE0: .size fmin3, .-fmin3 .p2align 4,,15 .globl fmin2 .type fmin2, @function fmin2: .LFB1: .cfi_startproc cmpl %edi, %esi movl %edx, %eax cmovle %esi, %edi cmpl %edx, %edi cmovle %edi, %eax ret .cfi_endproc .LFE1: .size fmin2, .-fmin2 .ident "GCC: (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3" .section .note.GNU-stack,"",@progbits fmin3 function, which uses open-coded min3 macro, is compiled into total of ten instructions including a conditional branch, whereas fmin2 function, which uses two calls to min2 macro, is compiled into six instructions with no branches. Similarly, open-coded clamp produces the same code as clamp using min and max macros, but the latter is much shorter: $ cat clamp.c #define clamp(val, min, max) ({ \ typeof(val) __val = (val); \ typeof(min) __min = (min); \ typeof(max) __max = (max); \ (void) (&__val == &__min); \ (void) (&__val == &__max); \ __val = __val < __min ? __min: __val; \ __val > __max ? __max: __val; }) #define min(x, y) ({ \ typeof(x) _min1 = (x); \ typeof(y) _min2 = (y); \ (void) (&_min1 == &_min2); \ _min1 < _min2 ? _min1 : _min2; }) #define max(x, y) ({ \ typeof(x) _max1 = (x); \ typeof(y) _max2 = (y); \ (void) (&_max1 == &_max2); \ _max1 > _max2 ? _max1 : _max2; }) int fclamp(int v, int min, int max) { return clamp(v, min, max); } int fclampmm(int v, int min, int max) { return min(max(v, min), max); } $ gcc -O2 -o clamp.s -S clamp.c; cat clamp.s .file "clamp.c" .text .p2align 4,,15 .globl fclamp .type fclamp, @function fclamp: .LFB0: .cfi_startproc cmpl %edi, %esi movl %edx, %eax cmovge %esi, %edi cmpl %edx, %edi cmovle %edi, %eax ret .cfi_endproc .LFE0: .size fclamp, .-fclamp .p2align 4,,15 .globl fclampmm .type fclampmm, @function fclampmm: .LFB1: .cfi_startproc cmpl %edi, %esi cmovge %esi, %edi cmpl %edi, %edx movl %edi, %eax cmovle %edx, %eax ret .cfi_endproc .LFE1: .size fclampmm, .-fclampmm .ident "GCC: (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3" .section .note.GNU-stack,"",@progbits Linux mpn-glaptop 3.13.0-29-generic #53~precise1-Ubuntu SMP Wed Jun 4 22:06:25 UTC 2014 x86_64 x86_64 x86_64 GNU/Linux gcc (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3 Copyright (C) 2011 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. -rwx------ 1 mpn eng 51224656 Jun 17 14:15 vmlinux.before -rwx------ 1 mpn eng 51224608 Jun 17 13:57 vmlinux.after 48 bytes reduction. The do_fault_around was a few instruction shorter and as far as I can tell saved 12 bytes on the stack, i.e.: $ grep -e rsp -e pop -e push do_fault_around.* do_fault_around.before.s:push %rbp do_fault_around.before.s:mov %rsp,%rbp do_fault_around.before.s:push %r13 do_fault_around.before.s:push %r12 do_fault_around.before.s:push %rbx do_fault_around.before.s:sub $0x38,%rsp do_fault_around.before.s:add $0x38,%rsp do_fault_around.before.s:pop %rbx do_fault_around.before.s:pop %r12 do_fault_around.before.s:pop %r13 do_fault_around.before.s:pop %rbp do_fault_around.after.s:push %rbp do_fault_around.after.s:mov %rsp,%rbp do_fault_around.after.s:push %r12 do_fault_around.after.s:push %rbx do_fault_around.after.s:sub $0x30,%rsp do_fault_around.after.s:add $0x30,%rsp do_fault_around.after.s:pop %rbx do_fault_around.after.s:pop %r12 do_fault_around.after.s:pop %rbp or here side-by-side: Before After push %rbp push %rbp mov %rsp,%rbp mov %rsp,%rbp push %r13 push %r12 push %r12 push %rbx push %rbx sub $0x38,%rsp sub $0x30,%rsp add $0x38,%rsp add $0x30,%rsp pop %rbx pop %rbx pop %r12 pop %r12 pop %r13 pop %rbp pop %rbp There are also fewer branches: $ grep ^j do_fault_around.* do_fault_around.before.s:jae ffffffff812079b7 do_fault_around.before.s:jmp ffffffff812079c5 do_fault_around.before.s:jmp ffffffff81207a14 do_fault_around.before.s:ja ffffffff812079f9 do_fault_around.before.s:jb ffffffff81207a10 do_fault_around.before.s:jmp ffffffff81207a63 do_fault_around.before.s:jne ffffffff812079df do_fault_around.after.s:jmp ffffffff812079fd do_fault_around.after.s:ja ffffffff812079e2 do_fault_around.after.s:jb ffffffff812079f9 do_fault_around.after.s:jmp ffffffff81207a4c do_fault_around.after.s:jne ffffffff812079c8 And here's with allyesconfig on a different machine: $ uname -a; gcc --version; ls -l vmlinux.* Linux erwin 3.14.7-mn #54 SMP Sun Jun 15 11:25:08 CEST 2014 x86_64 AMD Phenom(tm) II X3 710 Processor AuthenticAMD GNU/Linux gcc (GCC) 4.8.3 Copyright (C) 2013 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. -rwx------ 1 mpn eng 437027411 Jun 20 16:04 vmlinux.before -rwx------ 1 mpn eng 437026881 Jun 20 15:30 vmlinux.after 530 bytes reduction. Signed-off-by: Michal Nazarewicz <mina86@mina86.com> Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Cc: David Rientjes <rientjes@google.com> Cc: "Rustad, Mark D" <mark.d.rustad@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-10 06:30:13 +08:00
* @lo: lowest allowable value
* @hi: highest allowable value
*
* This macro does strict typechecking of lo/hi to make sure they are of the
* same type as val. See the unnecessary pointer comparisons.
*/
include/linux/kernel.h: rewrite min3, max3 and clamp using min and max It appears that gcc is better at optimising a double call to min and max rather than open coded min3 and max3. This can be observed here: $ cat min-max.c #define min(x, y) ({ \ typeof(x) _min1 = (x); \ typeof(y) _min2 = (y); \ (void) (&_min1 == &_min2); \ _min1 < _min2 ? _min1 : _min2; }) #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); }) int fmin3(int x, int y, int z) { return min3(x, y, z); } int fmin2(int x, int y, int z) { return min(min(x, y), z); } $ gcc -O2 -o min-max.s -S min-max.c; cat min-max.s .file "min-max.c" .text .p2align 4,,15 .globl fmin3 .type fmin3, @function fmin3: .LFB0: .cfi_startproc cmpl %esi, %edi jl .L5 cmpl %esi, %edx movl %esi, %eax cmovle %edx, %eax ret .p2align 4,,10 .p2align 3 .L5: cmpl %edi, %edx movl %edi, %eax cmovle %edx, %eax ret .cfi_endproc .LFE0: .size fmin3, .-fmin3 .p2align 4,,15 .globl fmin2 .type fmin2, @function fmin2: .LFB1: .cfi_startproc cmpl %edi, %esi movl %edx, %eax cmovle %esi, %edi cmpl %edx, %edi cmovle %edi, %eax ret .cfi_endproc .LFE1: .size fmin2, .-fmin2 .ident "GCC: (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3" .section .note.GNU-stack,"",@progbits fmin3 function, which uses open-coded min3 macro, is compiled into total of ten instructions including a conditional branch, whereas fmin2 function, which uses two calls to min2 macro, is compiled into six instructions with no branches. Similarly, open-coded clamp produces the same code as clamp using min and max macros, but the latter is much shorter: $ cat clamp.c #define clamp(val, min, max) ({ \ typeof(val) __val = (val); \ typeof(min) __min = (min); \ typeof(max) __max = (max); \ (void) (&__val == &__min); \ (void) (&__val == &__max); \ __val = __val < __min ? __min: __val; \ __val > __max ? __max: __val; }) #define min(x, y) ({ \ typeof(x) _min1 = (x); \ typeof(y) _min2 = (y); \ (void) (&_min1 == &_min2); \ _min1 < _min2 ? _min1 : _min2; }) #define max(x, y) ({ \ typeof(x) _max1 = (x); \ typeof(y) _max2 = (y); \ (void) (&_max1 == &_max2); \ _max1 > _max2 ? _max1 : _max2; }) int fclamp(int v, int min, int max) { return clamp(v, min, max); } int fclampmm(int v, int min, int max) { return min(max(v, min), max); } $ gcc -O2 -o clamp.s -S clamp.c; cat clamp.s .file "clamp.c" .text .p2align 4,,15 .globl fclamp .type fclamp, @function fclamp: .LFB0: .cfi_startproc cmpl %edi, %esi movl %edx, %eax cmovge %esi, %edi cmpl %edx, %edi cmovle %edi, %eax ret .cfi_endproc .LFE0: .size fclamp, .-fclamp .p2align 4,,15 .globl fclampmm .type fclampmm, @function fclampmm: .LFB1: .cfi_startproc cmpl %edi, %esi cmovge %esi, %edi cmpl %edi, %edx movl %edi, %eax cmovle %edx, %eax ret .cfi_endproc .LFE1: .size fclampmm, .-fclampmm .ident "GCC: (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3" .section .note.GNU-stack,"",@progbits Linux mpn-glaptop 3.13.0-29-generic #53~precise1-Ubuntu SMP Wed Jun 4 22:06:25 UTC 2014 x86_64 x86_64 x86_64 GNU/Linux gcc (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3 Copyright (C) 2011 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. -rwx------ 1 mpn eng 51224656 Jun 17 14:15 vmlinux.before -rwx------ 1 mpn eng 51224608 Jun 17 13:57 vmlinux.after 48 bytes reduction. The do_fault_around was a few instruction shorter and as far as I can tell saved 12 bytes on the stack, i.e.: $ grep -e rsp -e pop -e push do_fault_around.* do_fault_around.before.s:push %rbp do_fault_around.before.s:mov %rsp,%rbp do_fault_around.before.s:push %r13 do_fault_around.before.s:push %r12 do_fault_around.before.s:push %rbx do_fault_around.before.s:sub $0x38,%rsp do_fault_around.before.s:add $0x38,%rsp do_fault_around.before.s:pop %rbx do_fault_around.before.s:pop %r12 do_fault_around.before.s:pop %r13 do_fault_around.before.s:pop %rbp do_fault_around.after.s:push %rbp do_fault_around.after.s:mov %rsp,%rbp do_fault_around.after.s:push %r12 do_fault_around.after.s:push %rbx do_fault_around.after.s:sub $0x30,%rsp do_fault_around.after.s:add $0x30,%rsp do_fault_around.after.s:pop %rbx do_fault_around.after.s:pop %r12 do_fault_around.after.s:pop %rbp or here side-by-side: Before After push %rbp push %rbp mov %rsp,%rbp mov %rsp,%rbp push %r13 push %r12 push %r12 push %rbx push %rbx sub $0x38,%rsp sub $0x30,%rsp add $0x38,%rsp add $0x30,%rsp pop %rbx pop %rbx pop %r12 pop %r12 pop %r13 pop %rbp pop %rbp There are also fewer branches: $ grep ^j do_fault_around.* do_fault_around.before.s:jae ffffffff812079b7 do_fault_around.before.s:jmp ffffffff812079c5 do_fault_around.before.s:jmp ffffffff81207a14 do_fault_around.before.s:ja ffffffff812079f9 do_fault_around.before.s:jb ffffffff81207a10 do_fault_around.before.s:jmp ffffffff81207a63 do_fault_around.before.s:jne ffffffff812079df do_fault_around.after.s:jmp ffffffff812079fd do_fault_around.after.s:ja ffffffff812079e2 do_fault_around.after.s:jb ffffffff812079f9 do_fault_around.after.s:jmp ffffffff81207a4c do_fault_around.after.s:jne ffffffff812079c8 And here's with allyesconfig on a different machine: $ uname -a; gcc --version; ls -l vmlinux.* Linux erwin 3.14.7-mn #54 SMP Sun Jun 15 11:25:08 CEST 2014 x86_64 AMD Phenom(tm) II X3 710 Processor AuthenticAMD GNU/Linux gcc (GCC) 4.8.3 Copyright (C) 2013 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. -rwx------ 1 mpn eng 437027411 Jun 20 16:04 vmlinux.before -rwx------ 1 mpn eng 437026881 Jun 20 15:30 vmlinux.after 530 bytes reduction. Signed-off-by: Michal Nazarewicz <mina86@mina86.com> Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Cc: David Rientjes <rientjes@google.com> Cc: "Rustad, Mark D" <mark.d.rustad@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-10 06:30:13 +08:00
#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
/*
* ..and if you can't take the strict
* types, you can specify one yourself.
*
* Or not use min/max/clamp at all, of course.
*/
#define min_t(type, x, y) ({ \
type __min1 = (x); \
type __min2 = (y); \
__min1 < __min2 ? __min1: __min2; })
#define max_t(type, x, y) ({ \
type __max1 = (x); \
type __max2 = (y); \
__max1 > __max2 ? __max1: __max2; })
/**
* clamp_t - return a value clamped to a given range using a given type
* @type: the type of variable to use
* @val: current value
* @lo: minimum allowable value
* @hi: maximum allowable value
*
* This macro does no typechecking and uses temporary variables of type
* 'type' to make all the comparisons.
*/
#define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi)
/**
* clamp_val - return a value clamped to a given range using val's type
* @val: current value
* @lo: minimum allowable value
* @hi: maximum allowable value
*
* This macro does no typechecking and uses temporary variables of whatever
* type the input argument 'val' is. This is useful when val is an unsigned
* type and min and max are literals that will otherwise be assigned a signed
* integer type.
*/
#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
/*
* swap - swap value of @a and @b
*/
#define swap(a, b) \
do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
/**
* container_of - cast a member of a structure out to the containing structure
* @ptr: the pointer to the member.
* @type: the type of the container struct this is embedded in.
* @member: the name of the member within the struct.
*
*/
#define container_of(ptr, type, member) ({ \
const typeof( ((type *)0)->member ) *__mptr = (ptr); \
(type *)( (char *)__mptr - offsetof(type,member) );})
/* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
#endif
/* Permissions on a sysfs file: you didn't miss the 0 prefix did you? */
#define VERIFY_OCTAL_PERMISSIONS(perms) \
(BUILD_BUG_ON_ZERO((perms) < 0) + \
BUILD_BUG_ON_ZERO((perms) > 0777) + \
/* USER_READABLE >= GROUP_READABLE >= OTHER_READABLE */ \
BUILD_BUG_ON_ZERO((((perms) >> 6) & 4) < (((perms) >> 3) & 4)) + \
BUILD_BUG_ON_ZERO((((perms) >> 3) & 4) < ((perms) & 4)) + \
/* USER_WRITABLE >= GROUP_WRITABLE */ \
BUILD_BUG_ON_ZERO((((perms) >> 6) & 2) < (((perms) >> 3) & 2)) + \
/* OTHER_WRITABLE? Generally considered a bad idea. */ \
BUILD_BUG_ON_ZERO((perms) & 2) + \
(perms))
#endif