2005-04-17 06:20:36 +08:00
|
|
|
#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>
|
2006-12-08 18:37:49 +08:00
|
|
|
#include <linux/log2.h>
|
2008-07-25 16:45:24 +08:00
|
|
|
#include <linux/typecheck.h>
|
2010-11-16 05:37:37 +08:00
|
|
|
#include <linux/printk.h>
|
2009-02-06 00:51:38 +08:00
|
|
|
#include <linux/dynamic_debug.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <asm/byteorder.h>
|
2012-10-13 17:46:48 +08:00
|
|
|
#include <uapi/linux/kernel.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-05-25 05:33:03 +08:00
|
|
|
#define USHRT_MAX ((u16)(~0U))
|
|
|
|
#define SHRT_MAX ((s16)(USHRT_MAX>>1))
|
|
|
|
#define SHRT_MIN ((s16)(-SHRT_MAX - 1))
|
2005-04-17 06:20:36 +08:00
|
|
|
#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)
|
2012-06-01 07:26:04 +08:00
|
|
|
#define SIZE_MAX (~(size_t)0)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#define STACK_MAGIC 0xdeadbeef
|
|
|
|
|
2012-05-24 11:12:50 +08:00
|
|
|
#define REPEAT_BYTE(x) ((~0ul / 0xff) * (x))
|
|
|
|
|
2010-04-13 17:21:46 +08:00
|
|
|
#define ALIGN(x, a) __ALIGN_KERNEL((x), (a))
|
2010-04-13 20:09:15 +08:00
|
|
|
#define __ALIGN_MASK(x, mask) __ALIGN_KERNEL_MASK((x), (mask))
|
2007-09-12 06:23:47 +08:00
|
|
|
#define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a)))
|
2008-02-06 17:37:05 +08:00
|
|
|
#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0)
|
2006-11-27 11:05:22 +08:00
|
|
|
|
2007-05-07 05:51:05 +08:00
|
|
|
#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
|
|
|
|
|
2010-02-10 17:20:29 +08:00
|
|
|
/*
|
|
|
|
* 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))
|
|
|
|
|
2006-06-26 19:57:28 +08:00
|
|
|
#define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
|
2006-09-26 14:32:40 +08:00
|
|
|
#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
|
2011-07-26 15:35:26 +08:00
|
|
|
#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
|
2010-11-10 06:01:31 +08:00
|
|
|
|
|
|
|
/* The `const' in roundup() prevents gcc-3.3 from calling __divdi3 */
|
2010-10-14 05:50:08 +08:00
|
|
|
#define roundup(x, y) ( \
|
|
|
|
{ \
|
2010-11-08 10:20:49 +08:00
|
|
|
const typeof(y) __y = y; \
|
2010-10-14 05:50:08 +08:00
|
|
|
(((x) + (__y - 1)) / __y) * __y; \
|
|
|
|
} \
|
|
|
|
)
|
2010-10-14 05:50:02 +08:00
|
|
|
#define rounddown(x, y) ( \
|
|
|
|
{ \
|
|
|
|
typeof(x) __x = (x); \
|
|
|
|
__x - (__x % (y)); \
|
|
|
|
} \
|
|
|
|
)
|
2012-08-25 08:25:01 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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.
|
2012-08-25 08:25:01 +08:00
|
|
|
*/
|
2009-01-07 06:40:51 +08:00
|
|
|
#define DIV_ROUND_CLOSEST(x, divisor)( \
|
|
|
|
{ \
|
2012-08-25 08:25:01 +08:00
|
|
|
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) ? \
|
2012-08-25 08:25:01 +08:00
|
|
|
(((__x) + ((__d) / 2)) / (__d)) : \
|
|
|
|
(((__x) - ((__d) / 2)) / (__d)); \
|
2009-01-07 06:40:51 +08:00
|
|
|
} \
|
|
|
|
)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2012-03-10 08:41:01 +08:00
|
|
|
/*
|
|
|
|
* 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)); \
|
|
|
|
} \
|
|
|
|
)
|
|
|
|
|
|
|
|
|
2008-07-05 17:14:23 +08:00
|
|
|
#define _RET_IP_ (unsigned long)__builtin_return_address(0)
|
|
|
|
#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; })
|
|
|
|
|
2009-06-19 14:08:50 +08:00
|
|
|
#ifdef CONFIG_LBDAF
|
2007-10-12 18:40:38 +08:00
|
|
|
# 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
|
|
|
|
|
2007-05-10 18:15:18 +08:00
|
|
|
/**
|
|
|
|
* 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))
|
|
|
|
|
2008-07-30 13:33:42 +08:00
|
|
|
/**
|
|
|
|
* lower_32_bits - return bits 0-31 of a number
|
|
|
|
* @n: the number we're accessing
|
|
|
|
*/
|
|
|
|
#define lower_32_bits(n) ((u32)(n))
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
struct completion;
|
2006-01-10 12:51:37 +08:00
|
|
|
struct pt_regs;
|
|
|
|
struct user;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-08-13 06:08:59 +08:00
|
|
|
#ifdef CONFIG_PREEMPT_VOLUNTARY
|
|
|
|
extern int _cond_resched(void);
|
|
|
|
# define might_resched() _cond_resched()
|
|
|
|
#else
|
|
|
|
# define might_resched() do { } while (0)
|
|
|
|
#endif
|
|
|
|
|
2011-06-09 01:31:56 +08:00
|
|
|
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
|
2009-12-23 18:08:18 +08:00
|
|
|
void __might_sleep(const char *file, int line, int preempt_offset);
|
2005-04-17 06:20:36 +08:00
|
|
|
/**
|
|
|
|
* 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
|
2006-11-30 11:46:13 +08:00
|
|
|
* be bitten later when the calling function happens to sleep when it is not
|
2005-04-17 06:20:36 +08:00
|
|
|
* supposed to.
|
|
|
|
*/
|
2005-06-26 05:57:39 +08:00
|
|
|
# define might_sleep() \
|
2009-07-16 21:44:29 +08:00
|
|
|
do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
|
2005-04-17 06:20:36 +08:00
|
|
|
#else
|
2009-12-23 18:08:18 +08:00
|
|
|
static inline void __might_sleep(const char *file, int line,
|
|
|
|
int preempt_offset) { }
|
2005-06-26 05:57:39 +08:00
|
|
|
# define might_sleep() do { might_resched(); } while (0)
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
2006-06-23 17:05:42 +08:00
|
|
|
#define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0)
|
2005-06-26 05:57:39 +08:00
|
|
|
|
2011-01-13 08:59:35 +08:00
|
|
|
/*
|
|
|
|
* abs() handles unsigned and signed longs, ints, shorts and chars. For all
|
|
|
|
* input types abs() returns a signed long.
|
|
|
|
* abs() should not be used for 64-bit types (s64, u64, long long) - use abs64()
|
|
|
|
* for those.
|
|
|
|
*/
|
|
|
|
#define abs(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; \
|
2005-04-17 06:20:36 +08:00
|
|
|
})
|
|
|
|
|
2010-10-27 05:23:10 +08:00
|
|
|
#define abs64(x) ({ \
|
|
|
|
s64 __x = (x); \
|
|
|
|
(__x < 0) ? -__x : __x; \
|
|
|
|
})
|
|
|
|
|
2008-09-10 19:37:17 +08:00
|
|
|
#ifdef CONFIG_PROVE_LOCKING
|
|
|
|
void might_fault(void);
|
|
|
|
#else
|
|
|
|
static inline void might_fault(void)
|
|
|
|
{
|
|
|
|
might_sleep();
|
|
|
|
}
|
|
|
|
#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;
|
2010-08-11 09:03:28 +08:00
|
|
|
extern long (*panic_blink)(int state);
|
2012-01-13 09:17:17 +08:00
|
|
|
__printf(1, 2)
|
2012-01-13 09:17:13 +08:00
|
|
|
void panic(const char *fmt, ...)
|
2012-01-13 09:17:21 +08:00
|
|
|
__noreturn __cold;
|
2006-03-23 19:00:57 +08:00
|
|
|
extern void oops_enter(void);
|
|
|
|
extern void oops_exit(void);
|
2010-08-11 09:03:30 +08:00
|
|
|
void print_oops_end_marker(void);
|
2006-03-23 19:00:57 +08:00
|
|
|
extern int oops_may_print(void);
|
2012-01-13 09:17:17 +08:00
|
|
|
void do_exit(long error_code)
|
2012-01-13 09:17:21 +08:00
|
|
|
__noreturn;
|
2012-01-13 09:17:17 +08:00
|
|
|
void complete_and_exit(struct completion *, long)
|
2012-01-13 09:17:21 +08:00
|
|
|
__noreturn;
|
2011-03-23 07:34:40 +08:00
|
|
|
|
|
|
|
/* 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);
|
2012-12-18 08:03:04 +08:00
|
|
|
|
|
|
|
/**
|
|
|
|
* 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.
|
|
|
|
*/
|
2011-03-23 07:34:40 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2012-12-18 08:03:04 +08:00
|
|
|
/**
|
|
|
|
* 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.
|
|
|
|
*/
|
2011-03-23 07:34:40 +08:00
|
|
|
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);
|
|
|
|
|
2011-05-25 08:13:31 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2011-11-01 08:13:10 +08:00
|
|
|
/* Obsolete, do not use. Use kstrto<foo> instead */
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
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);
|
2011-03-23 07:34:40 +08:00
|
|
|
#define strict_strtoul kstrtoul
|
|
|
|
#define strict_strtol kstrtol
|
|
|
|
#define strict_strtoull kstrtoull
|
|
|
|
#define strict_strtoll kstrtoll
|
|
|
|
|
2012-03-24 06:02:54 +08:00
|
|
|
extern int num_to_str(char *buf, int size, unsigned long long num);
|
|
|
|
|
2011-11-01 08:13:10 +08:00
|
|
|
/* lib/printf utilities */
|
|
|
|
|
2011-11-01 08:11:33 +08:00
|
|
|
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, ...);
|
2007-05-01 06:09:56 +08:00
|
|
|
extern char *kvasprintf(gfp_t gfp, const char *fmt, va_list args);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2012-03-24 06:02:16 +08:00
|
|
|
extern __scanf(2, 3)
|
|
|
|
int sscanf(const char *, const char *, ...);
|
|
|
|
extern __scanf(2, 0)
|
|
|
|
int vsscanf(const char *, const char *, va_list);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
extern int get_option(char **str, int *pint);
|
|
|
|
extern char *get_options(const char *str, int nints, int *ints);
|
2008-07-25 07:27:46 +08:00
|
|
|
extern unsigned long long memparse(const char *ptr, char **retptr);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-05-16 00:44:06 +08:00
|
|
|
extern int core_kernel_text(unsigned long addr);
|
2011-05-06 09:14:55 +08:00
|
|
|
extern int core_kernel_data(unsigned long addr);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int __kernel_text_address(unsigned long addr);
|
|
|
|
extern int kernel_text_address(unsigned long addr);
|
2008-08-16 06:29:38 +08:00
|
|
|
extern int func_ptr_is_kernel_text(void *ptr);
|
|
|
|
|
2007-02-12 16:52:56 +08:00
|
|
|
struct pid;
|
|
|
|
extern struct pid *session_of_pgrp(struct pid *pgrp);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
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 */
|
2006-04-11 13:53:59 +08:00
|
|
|
extern int panic_timeout;
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int panic_on_oops;
|
2006-09-26 16:52:27 +08:00
|
|
|
extern int panic_on_unrecovered_nmi;
|
2009-06-25 05:32:11 +08:00
|
|
|
extern int panic_on_io_nmi;
|
2011-11-29 14:08:36 +08:00
|
|
|
extern int sysctl_panic_on_stackoverflow;
|
2005-04-17 06:20:36 +08:00
|
|
|
extern const char *print_tainted(void);
|
2013-01-21 14:47:39 +08:00
|
|
|
enum lockdep_ok {
|
|
|
|
LOCKDEP_STILL_OK,
|
|
|
|
LOCKDEP_NOW_UNRELIABLE
|
|
|
|
};
|
|
|
|
extern void add_taint(unsigned flag, enum lockdep_ok);
|
2008-10-16 13:01:41 +08:00
|
|
|
extern int test_taint(unsigned flag);
|
|
|
|
extern unsigned long get_taint(void);
|
2008-02-08 20:19:31 +08:00
|
|
|
extern int root_mountflags;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-01-20 19:06:35 +08:00
|
|
|
extern bool early_boot_irqs_disabled;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Values used for system_state */
|
|
|
|
extern enum system_states {
|
|
|
|
SYSTEM_BOOTING,
|
|
|
|
SYSTEM_RUNNING,
|
|
|
|
SYSTEM_HALT,
|
|
|
|
SYSTEM_POWER_OFF,
|
|
|
|
SYSTEM_RESTART,
|
|
|
|
} system_state;
|
|
|
|
|
2008-10-16 13:01:41 +08:00
|
|
|
#define TAINT_PROPRIETARY_MODULE 0
|
|
|
|
#define TAINT_FORCED_MODULE 1
|
|
|
|
#define TAINT_UNSAFE_SMP 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
|
2008-10-18 00:50:12 +08:00
|
|
|
#define TAINT_CRAP 10
|
2010-04-04 02:36:42 +08:00
|
|
|
#define TAINT_FIRMWARE_WORKAROUND 11
|
2011-10-24 21:12:28 +08:00
|
|
|
#define TAINT_OOT_MODULE 12
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-05-15 07:05:49 +08:00
|
|
|
extern const char hex_asc[];
|
|
|
|
#define hex_asc_lo(x) hex_asc[((x) & 0x0f)]
|
|
|
|
#define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4]
|
|
|
|
|
2011-11-01 08:12:41 +08:00
|
|
|
static inline char *hex_byte_pack(char *buf, u8 byte)
|
2008-05-15 07:05:49 +08:00
|
|
|
{
|
|
|
|
*buf++ = hex_asc_hi(byte);
|
|
|
|
*buf++ = hex_asc_lo(byte);
|
|
|
|
return buf;
|
|
|
|
}
|
2007-05-11 13:22:39 +08:00
|
|
|
|
2011-11-01 08:12:41 +08:00
|
|
|
static inline char * __deprecated pack_hex_byte(char *buf, u8 byte)
|
|
|
|
{
|
|
|
|
return hex_byte_pack(buf, byte);
|
|
|
|
}
|
|
|
|
|
2010-05-25 05:33:23 +08:00
|
|
|
extern int hex_to_bin(char ch);
|
2011-09-20 23:23:49 +08:00
|
|
|
extern int __must_check hex2bin(u8 *dst, const char *src, size_t count);
|
2010-05-25 05:33:23 +08:00
|
|
|
|
2009-03-05 17:28:45 +08:00
|
|
|
/*
|
|
|
|
* General tracing related utility functions - trace_printk(),
|
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.
|
2009-06-02 14:01:37 +08:00
|
|
|
* This also corresponds to the user space /sys/kernel/debug/tracing/tracing_on
|
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.
|
2009-03-05 17:28:45 +08:00
|
|
|
*/
|
2009-03-05 23:35:56 +08:00
|
|
|
#ifdef CONFIG_RING_BUFFER
|
|
|
|
/* trace_off_permanent stops recording with no way to bring it back */
|
|
|
|
void tracing_off_permanent(void);
|
|
|
|
#else
|
|
|
|
static inline void tracing_off_permanent(void) { }
|
|
|
|
#endif
|
2010-04-19 01:08:41 +08:00
|
|
|
|
|
|
|
enum ftrace_dump_mode {
|
|
|
|
DUMP_NONE,
|
|
|
|
DUMP_ALL,
|
|
|
|
DUMP_ORIG,
|
|
|
|
};
|
|
|
|
|
2009-03-05 17:28:45 +08:00
|
|
|
#ifdef CONFIG_TRACING
|
2012-03-21 00:28:29 +08:00
|
|
|
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);
|
2012-03-21 00:28:29 +08:00
|
|
|
|
2009-03-05 17:28:45 +08:00
|
|
|
extern void tracing_start(void);
|
|
|
|
extern void tracing_stop(void);
|
|
|
|
extern void ftrace_off_permanent(void);
|
|
|
|
|
2011-11-01 08:11:33 +08:00
|
|
|
static inline __printf(1, 2)
|
|
|
|
void ____trace_printk_check_format(const char *fmt, ...)
|
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)
|
|
|
|
|
2009-03-05 17:28:45 +08:00
|
|
|
/**
|
|
|
|
* 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
|
2013-03-09 10:02:34 +08:00
|
|
|
* 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.
|
2009-03-05 17:28:45 +08:00
|
|
|
*/
|
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...) \
|
2009-03-07 00:21:49 +08:00
|
|
|
do { \
|
tracing: Add percpu buffers for trace_printk()
Currently, trace_printk() uses a single buffer to write into
to calculate the size and format needed to save the trace. To
do this safely in an SMP environment, a spin_lock() is taken
to only allow one writer at a time to the buffer. But this could
also affect what is being traced, and add synchronization that
would not be there otherwise.
Ideally, using percpu buffers would be useful, but since trace_printk()
is only used in development, having per cpu buffers for something
never used is a waste of space. Thus, the use of the trace_bprintk()
format section is changed to be used for static fmts as well as dynamic ones.
Then at boot up, we can check if the section that holds the trace_printk
formats is non-empty, and if it does contain something, then we
know a trace_printk() has been added to the kernel. At this time
the trace_printk per cpu buffers are allocated. A check is also
done at module load time in case a module is added that contains a
trace_printk().
Once the buffers are allocated, they are never freed. If you use
a trace_printk() then you should know what you are doing.
A buffer is made for each type of context:
normal
softirq
irq
nmi
The context is checked and the appropriate buffer is used.
This allows for totally lockless usage of trace_printk(),
and they no longer even disable interrupts.
Requested-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
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; \
|
|
|
|
\
|
2009-03-07 00:21:49 +08:00
|
|
|
__trace_printk_check_format(fmt, ##args); \
|
2009-03-13 01:24:49 +08:00
|
|
|
\
|
tracing: Add percpu buffers for trace_printk()
Currently, trace_printk() uses a single buffer to write into
to calculate the size and format needed to save the trace. To
do this safely in an SMP environment, a spin_lock() is taken
to only allow one writer at a time to the buffer. But this could
also affect what is being traced, and add synchronization that
would not be there otherwise.
Ideally, using percpu buffers would be useful, but since trace_printk()
is only used in development, having per cpu buffers for something
never used is a waste of space. Thus, the use of the trace_bprintk()
format section is changed to be used for static fmts as well as dynamic ones.
Then at boot up, we can check if the section that holds the trace_printk
formats is non-empty, and if it does contain something, then we
know a trace_printk() has been added to the kernel. At this time
the trace_printk per cpu buffers are allocated. A check is also
done at module load time in case a module is added that contains a
trace_printk().
Once the buffers are allocated, they are never freed. If you use
a trace_printk() then you should know what you are doing.
A buffer is made for each type of context:
normal
softirq
irq
nmi
The context is checked and the appropriate buffer is used.
This allows for totally lockless usage of trace_printk(),
and they no longer even disable interrupts.
Requested-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-09-23 02:01:55 +08:00
|
|
|
if (__builtin_constant_p(fmt)) \
|
2009-03-13 01:24:49 +08:00
|
|
|
__trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args); \
|
tracing: Add percpu buffers for trace_printk()
Currently, trace_printk() uses a single buffer to write into
to calculate the size and format needed to save the trace. To
do this safely in an SMP environment, a spin_lock() is taken
to only allow one writer at a time to the buffer. But this could
also affect what is being traced, and add synchronization that
would not be there otherwise.
Ideally, using percpu buffers would be useful, but since trace_printk()
is only used in development, having per cpu buffers for something
never used is a waste of space. Thus, the use of the trace_bprintk()
format section is changed to be used for static fmts as well as dynamic ones.
Then at boot up, we can check if the section that holds the trace_printk
formats is non-empty, and if it does contain something, then we
know a trace_printk() has been added to the kernel. At this time
the trace_printk per cpu buffers are allocated. A check is also
done at module load time in case a module is added that contains a
trace_printk().
Once the buffers are allocated, they are never freed. If you use
a trace_printk() then you should know what you are doing.
A buffer is made for each type of context:
normal
softirq
irq
nmi
The context is checked and the appropriate buffer is used.
This allows for totally lockless usage of trace_printk(),
and they no longer even disable interrupts.
Requested-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-09-23 02:01:55 +08:00
|
|
|
else \
|
|
|
|
__trace_printk(_THIS_IP_, fmt, ##args); \
|
2009-03-07 00:21:49 +08:00
|
|
|
} while (0)
|
|
|
|
|
2011-11-01 08:11:33 +08:00
|
|
|
extern __printf(2, 3)
|
|
|
|
int __trace_bprintk(unsigned long ip, const char *fmt, ...);
|
2009-03-13 01:24:49 +08:00
|
|
|
|
2011-11-01 08:11:33 +08:00
|
|
|
extern __printf(2, 3)
|
|
|
|
int __trace_printk(unsigned long ip, const char *fmt, ...);
|
2009-03-07 00:21:49 +08:00
|
|
|
|
2013-05-25 06:55:20 +08:00
|
|
|
extern int __trace_bputs(unsigned long ip, const char *str);
|
|
|
|
extern int __trace_puts(unsigned long ip, const char *str, int size);
|
|
|
|
|
2013-03-09 10:02:34 +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)); \
|
|
|
|
})
|
|
|
|
|
2013-03-13 21:55:57 +08:00
|
|
|
extern void trace_dump_stack(int skip);
|
2009-12-11 22:48:22 +08:00
|
|
|
|
2009-03-13 01:24:49 +08:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2009-03-07 00:21:49 +08:00
|
|
|
#define ftrace_vprintk(fmt, vargs) \
|
|
|
|
do { \
|
2009-03-13 01:24:49 +08:00
|
|
|
if (__builtin_constant_p(fmt)) { \
|
|
|
|
static const char *trace_printk_fmt \
|
|
|
|
__attribute__((section("__trace_printk_fmt"))) = \
|
|
|
|
__builtin_constant_p(fmt) ? fmt : NULL; \
|
2009-03-09 17:11:36 +08:00
|
|
|
\
|
2009-03-13 01:24:49 +08:00
|
|
|
__ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs); \
|
|
|
|
} else \
|
|
|
|
__ftrace_vprintk(_THIS_IP_, fmt, vargs); \
|
2009-03-07 00:21:49 +08:00
|
|
|
} while (0)
|
|
|
|
|
2009-03-13 01:24:49 +08:00
|
|
|
extern int
|
|
|
|
__ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap);
|
|
|
|
|
2009-03-05 17:28:45 +08:00
|
|
|
extern int
|
|
|
|
__ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
|
2009-03-07 00:21:49 +08:00
|
|
|
|
2010-04-19 01:08:41 +08:00
|
|
|
extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode);
|
2009-03-05 17:28:45 +08:00
|
|
|
#else
|
|
|
|
static inline void tracing_start(void) { }
|
|
|
|
static inline void tracing_stop(void) { }
|
|
|
|
static inline void ftrace_off_permanent(void) { }
|
2009-12-15 04:58:33 +08:00
|
|
|
static inline void trace_dump_stack(void) { }
|
2012-03-21 00:28:29 +08:00
|
|
|
|
|
|
|
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) { }
|
2012-03-21 00:28:29 +08:00
|
|
|
|
2012-10-25 21:41:51 +08:00
|
|
|
static inline __printf(1, 2)
|
|
|
|
int trace_printk(const char *fmt, ...)
|
2009-03-05 17:28:45 +08:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
static inline int
|
|
|
|
ftrace_vprintk(const char *fmt, va_list ap)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2010-04-19 01:08:41 +08:00
|
|
|
static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
|
2009-03-07 00:21:49 +08:00
|
|
|
#endif /* CONFIG_TRACING */
|
2009-03-05 17:28:45 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
2008-04-30 15:54:55 +08:00
|
|
|
* min()/max()/clamp() macros that also do
|
2005-04-17 06:20:36 +08:00
|
|
|
* strict type-checking.. See the
|
|
|
|
* "unnecessary" pointer comparison.
|
|
|
|
*/
|
2008-04-30 15:54:55 +08:00
|
|
|
#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; })
|
|
|
|
|
2010-10-27 05:22:21 +08:00
|
|
|
#define min3(x, y, z) ({ \
|
|
|
|
typeof(x) _min1 = (x); \
|
|
|
|
typeof(y) _min2 = (y); \
|
|
|
|
typeof(z) _min3 = (z); \
|
|
|
|
(void) (&_min1 == &_min2); \
|
|
|
|
(void) (&_min1 == &_min3); \
|
|
|
|
_min1 < _min2 ? (_min1 < _min3 ? _min1 : _min3) : \
|
|
|
|
(_min2 < _min3 ? _min2 : _min3); })
|
|
|
|
|
|
|
|
#define max3(x, y, z) ({ \
|
|
|
|
typeof(x) _max1 = (x); \
|
|
|
|
typeof(y) _max2 = (y); \
|
|
|
|
typeof(z) _max3 = (z); \
|
|
|
|
(void) (&_max1 == &_max2); \
|
|
|
|
(void) (&_max1 == &_max3); \
|
|
|
|
_max1 > _max2 ? (_max1 > _max3 ? _max1 : _max3) : \
|
|
|
|
(_max2 > _max3 ? _max2 : _max3); })
|
|
|
|
|
2010-09-11 02:07:38 +08:00
|
|
|
/**
|
|
|
|
* 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)); })
|
|
|
|
|
2008-04-30 15:54:55 +08:00
|
|
|
/**
|
|
|
|
* clamp - return a value clamped to a given range with strict typechecking
|
|
|
|
* @val: current value
|
|
|
|
* @min: minimum allowable value
|
|
|
|
* @max: maximum allowable value
|
|
|
|
*
|
|
|
|
* This macro does strict typechecking of min/max to make sure they are of the
|
|
|
|
* same type as val. See the unnecessary pointer comparisons.
|
|
|
|
*/
|
|
|
|
#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; })
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* ..and if you can't take the strict
|
|
|
|
* types, you can specify one yourself.
|
|
|
|
*
|
2008-04-30 15:54:55 +08:00
|
|
|
* 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
|
|
|
|
* @min: minimum allowable value
|
|
|
|
* @max: maximum allowable value
|
|
|
|
*
|
|
|
|
* This macro does no typechecking and uses temporary variables of type
|
|
|
|
* 'type' to make all the comparisons.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2008-04-30 15:54:55 +08:00
|
|
|
#define clamp_t(type, val, min, max) ({ \
|
|
|
|
type __val = (val); \
|
|
|
|
type __min = (min); \
|
|
|
|
type __max = (max); \
|
|
|
|
__val = __val < __min ? __min: __val; \
|
|
|
|
__val > __max ? __max: __val; })
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-04-30 15:54:55 +08:00
|
|
|
/**
|
|
|
|
* clamp_val - return a value clamped to a given range using val's type
|
|
|
|
* @val: current value
|
|
|
|
* @min: minimum allowable value
|
|
|
|
* @max: 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, min, max) ({ \
|
|
|
|
typeof(val) __val = (val); \
|
|
|
|
typeof(val) __min = (min); \
|
|
|
|
typeof(val) __max = (max); \
|
|
|
|
__val = __val < __min ? __min: __val; \
|
|
|
|
__val > __max ? __max: __val; })
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-01-08 10:09:12 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* swap - swap value of @a and @b
|
|
|
|
*/
|
2009-02-05 07:11:59 +08:00
|
|
|
#define swap(a, b) \
|
|
|
|
do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
|
2009-01-08 10:09:12 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/**
|
|
|
|
* 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) ({ \
|
2007-05-13 07:28:35 +08:00
|
|
|
const typeof( ((type *)0)->member ) *__mptr = (ptr); \
|
|
|
|
(type *)( (char *)__mptr - offsetof(type,member) );})
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-07-26 08:13:03 +08:00
|
|
|
/* Trap pasters of __FUNCTION__ at compile-time */
|
|
|
|
#define __FUNCTION__ (__func__)
|
|
|
|
|
|
|
|
/* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
|
|
|
|
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
|
|
|
|
# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
|
|
|
|
#endif
|
2011-07-26 08:13:02 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|