#include <asm/kprobes.h>
#include <asm/stacktrace.h>
#include <asm/nmi.h>
+#include <asm/disassemble.h>
#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE)
int (*__debugger)(struct pt_regs *regs) __read_mostly;
extern void panic_flush_kmsg_end(void)
{
- printk_safe_flush_on_panic();
kmsg_dump(KMSG_DUMP_PANIC);
bust_spinlocks(0);
debug_locks_off();
return;
nonrecoverable:
- regs->msr &= ~MSR_RI;
+ regs_set_return_msr(regs, regs->msr & ~MSR_RI);
#endif
}
DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
* For the debug message, we look at the preceding
* load or store.
*/
- if (*nip == PPC_INST_NOP)
+ if (*nip == PPC_RAW_NOP())
nip -= 2;
- else if (*nip == PPC_INST_ISYNC)
+ else if (*nip == PPC_RAW_ISYNC())
--nip;
- if (*nip == PPC_INST_SYNC || (*nip >> 26) == OP_TRAP) {
+ if (*nip == PPC_RAW_SYNC() || get_op(*nip) == OP_TRAP) {
unsigned int rb;
--nip;
printk(KERN_DEBUG "%s bad port %lx at %p\n",
(*nip & 0x100)? "OUT to": "IN from",
regs->gpr[rb] - _IO_BASE, nip);
- regs->msr |= MSR_RI;
- regs->nip = extable_fixup(entry);
+ regs_set_return_msr(regs, regs->msr | MSR_RI);
+ regs_set_return_ip(regs, extable_fixup(entry));
return 1;
}
}
#define REASON_BOUNDARY SRR1_BOUNDARY
#define single_stepping(regs) ((regs)->msr & MSR_SE)
-#define clear_single_step(regs) ((regs)->msr &= ~MSR_SE)
-#define clear_br_trace(regs) ((regs)->msr &= ~MSR_BE)
+#define clear_single_step(regs) (regs_set_return_msr((regs), (regs)->msr & ~MSR_SE))
+#define clear_br_trace(regs) (regs_set_return_msr((regs), (regs)->msr & ~MSR_BE))
#endif
#define inst_length(reason) (((reason) & REASON_PREFIXED) ? 8 : 4)
#endif /* !__LITTLE_ENDIAN__ */
/* Go to next instruction */
- regs->nip += 4;
+ regs_add_return_ip(regs, 4);
}
#endif /* CONFIG_VSX */
if (!(regs->msr & MSR_PR) && /* not user-mode */
report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) {
- regs->nip += 4;
+ regs_add_return_ip(regs, 4);
return;
}
_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
if (reason & (REASON_ILLEGAL | REASON_PRIVILEGED)) {
switch (emulate_instruction(regs)) {
case 0:
- regs->nip += 4;
+ regs_add_return_ip(regs, 4);
emulate_single_step(regs);
return;
case -EFAULT:
*/
DEFINE_INTERRUPT_HANDLER(emulation_assist_interrupt)
{
- regs->msr |= REASON_ILLEGAL;
+ regs_set_return_msr(regs, regs->msr | REASON_ILLEGAL);
do_program_check(regs);
}
if (fixed == 1) {
/* skip over emulated instruction */
- regs->nip += inst_length(reason);
+ regs_add_return_ip(regs, inst_length(reason));
emulate_single_step(regs);
return;
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
if (user_mode(regs)) {
current->thread.load_tm++;
- regs->msr |= MSR_TM;
+ regs_set_return_msr(regs, regs->msr | MSR_TM);
tm_enable();
tm_restore_sprs(¤t->thread);
return;
pr_err("DSCR based mfspr emulation failed\n");
return;
}
- regs->nip += 4;
+ regs_add_return_ip(regs, 4);
emulate_single_step(regs);
}
return;
*/
if (DBCR_ACTIVE_EVENTS(current->thread.debug.dbcr0,
current->thread.debug.dbcr1))
- regs->msr |= MSR_DE;
+ regs_set_return_msr(regs, regs->msr | MSR_DE);
else
/* Make sure the IDM flag is off */
current->thread.debug.dbcr0 &= ~DBCR0_IDM;
* instead of stopping here when hitting a BT
*/
if (debug_status & DBSR_BT) {
- regs->msr &= ~MSR_DE;
+ regs_set_return_msr(regs, regs->msr & ~MSR_DE);
/* Disable BT */
mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~DBCR0_BT);
if (user_mode(regs)) {
current->thread.debug.dbcr0 &= ~DBCR0_BT;
current->thread.debug.dbcr0 |= DBCR0_IDM | DBCR0_IC;
- regs->msr |= MSR_DE;
+ regs_set_return_msr(regs, regs->msr | MSR_DE);
return;
}
if (debugger_sstep(regs))
return;
} else if (debug_status & DBSR_IC) { /* Instruction complete */
- regs->msr &= ~MSR_DE;
+ regs_set_return_msr(regs, regs->msr & ~MSR_DE);
/* Disable instruction completion */
mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~DBCR0_IC);
current->thread.debug.dbcr0 &= ~DBCR0_IC;
if (DBCR_ACTIVE_EVENTS(current->thread.debug.dbcr0,
current->thread.debug.dbcr1))
- regs->msr |= MSR_DE;
+ regs_set_return_msr(regs, regs->msr | MSR_DE);
else
/* Make sure the IDM bit is off */
current->thread.debug.dbcr0 &= ~DBCR0_IDM;
PPC_WARN_EMULATED(altivec, regs);
err = emulate_altivec(regs);
if (err == 0) {
- regs->nip += 4; /* skip emulated instruction */
+ regs_add_return_ip(regs, 4); /* skip emulated instruction */
emulate_single_step(regs);
return;
}
err = do_spe_mathemu(regs);
if (err == 0) {
- regs->nip += 4; /* skip emulated instruction */
+ regs_add_return_ip(regs, 4); /* skip emulated instruction */
emulate_single_step(regs);
return;
}
giveup_spe(current);
preempt_enable();
- regs->nip -= 4;
+ regs_add_return_ip(regs, -4);
err = speround_handler(regs);
if (err == 0) {
- regs->nip += 4; /* skip emulated instruction */
+ regs_add_return_ip(regs, 4); /* skip emulated instruction */
emulate_single_step(regs);
return;
}
#include <linux/kdebug.h>
#include <linux/sched/debug.h>
#include <linux/delay.h>
+#include <linux/processor.h>
#include <linux/smp.h>
#include <asm/interrupt.h>
wd_smp_unlock(&flags);
- printk_safe_flush();
- /*
- * printk_safe_flush() seems to require another print
- * before anything actually goes out to console.
- */
if (sysctl_hardlockup_all_cpu_backtrace)
trigger_allbutself_cpu_backtrace();
static void crash_kexec_prepare_cpus(int cpu)
{
unsigned int msecs;
- unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */
- int tries = 0;
+ volatile unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */
+ volatile int tries = 0;
int (*old_handler)(struct pt_regs *regs);
printk(KERN_EMERG "Sending IPI to other CPUs\n");
int (*old_handler)(struct pt_regs *regs);
/* Avoid hardlocking with irresponsive CPU holding logbuf_lock */
- printk_nmi_enter();
+ printk_deferred_enter();
/*
* This function is only called after the system
#include <linux/linkage.h>
#include <linux/cache.h>
#include <linux/ratelimit_types.h>
+#include <linux/once_lite.h>
extern const char linux_banner[];
extern const char linux_proc_banner[];
#define minimum_console_loglevel (console_printk[2])
#define default_console_loglevel (console_printk[3])
-static inline void console_silent(void)
-{
- console_loglevel = CONSOLE_LOGLEVEL_SILENT;
-}
-
-static inline void console_verbose(void)
-{
- if (console_loglevel)
- console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
-}
+extern void console_verbose(void);
/* strlen("ratelimit") + 1 */
#define DEVKMSG_STR_MAX_SIZE 10
void early_printk(const char *s, ...) { }
#endif
- #ifdef CONFIG_PRINTK_NMI
- extern void printk_nmi_enter(void);
- extern void printk_nmi_exit(void);
- extern void printk_nmi_direct_enter(void);
- extern void printk_nmi_direct_exit(void);
- #else
- static inline void printk_nmi_enter(void) { }
- static inline void printk_nmi_exit(void) { }
- static inline void printk_nmi_direct_enter(void) { }
- static inline void printk_nmi_direct_exit(void) { }
- #endif /* PRINTK_NMI */
-
struct dev_printk_info;
#ifdef CONFIG_PRINTK
int vprintk(const char *fmt, va_list args);
asmlinkage __printf(1, 2) __cold
-int printk(const char *fmt, ...);
+int _printk(const char *fmt, ...);
/*
* Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ !
*/
-__printf(1, 2) __cold int printk_deferred(const char *fmt, ...);
+__printf(1, 2) __cold int _printk_deferred(const char *fmt, ...);
+ extern void __printk_safe_enter(void);
+ extern void __printk_safe_exit(void);
+ /*
+ * The printk_deferred_enter/exit macros are available only as a hack for
+ * some code paths that need to defer all printk console printing. Interrupts
+ * must be disabled for the deferred duration.
+ */
+ #define printk_deferred_enter __printk_safe_enter
+ #define printk_deferred_exit __printk_safe_exit
+
/*
* Please don't use printk_ratelimit(), because it shares ratelimiting state
* with all other unrelated printk_ratelimit() callsites. Instead use
void show_regs_print_info(const char *log_lvl);
extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold;
extern asmlinkage void dump_stack(void) __cold;
- extern void printk_safe_flush(void);
- extern void printk_safe_flush_on_panic(void);
#else
static inline __printf(1, 0)
int vprintk(const char *s, va_list args)
return 0;
}
static inline __printf(1, 2) __cold
-int printk(const char *s, ...)
+int _printk(const char *s, ...)
{
return 0;
}
static inline __printf(1, 2) __cold
-int printk_deferred(const char *s, ...)
+int _printk_deferred(const char *s, ...)
{
return 0;
}
+
+ static inline void printk_deferred_enter(void)
+ {
+ }
+
+ static inline void printk_deferred_exit(void)
+ {
+ }
+
static inline int printk_ratelimit(void)
{
return 0;
static inline void dump_stack(void)
{
}
-
- static inline void printk_safe_flush(void)
- {
- }
-
- static inline void printk_safe_flush_on_panic(void)
- {
- }
#endif
#ifdef CONFIG_SMP
#define pr_fmt(fmt) fmt
#endif
+struct module;
+
+#ifdef CONFIG_PRINTK_INDEX
+struct pi_entry {
+ const char *fmt;
+ const char *func;
+ const char *file;
+ unsigned int line;
+
+ /*
+ * While printk and pr_* have the level stored in the string at compile
+ * time, some subsystems dynamically add it at runtime through the
+ * format string. For these dynamic cases, we allow the subsystem to
+ * tell us the level at compile time.
+ *
+ * NULL indicates that the level, if any, is stored in fmt.
+ */
+ const char *level;
+
+ /*
+ * The format string used by various subsystem specific printk()
+ * wrappers to prefix the message.
+ *
+ * Note that the static prefix defined by the pr_fmt() macro is stored
+ * directly in the message format (@fmt), not here.
+ */
+ const char *subsys_fmt_prefix;
+} __packed;
+
+#define __printk_index_emit(_fmt, _level, _subsys_fmt_prefix) \
+ do { \
+ if (__builtin_constant_p(_fmt) && __builtin_constant_p(_level)) { \
+ /*
+ * We check __builtin_constant_p multiple times here
+ * for the same input because GCC will produce an error
+ * if we try to assign a static variable to fmt if it
+ * is not a constant, even with the outer if statement.
+ */ \
+ static const struct pi_entry _entry \
+ __used = { \
+ .fmt = __builtin_constant_p(_fmt) ? (_fmt) : NULL, \
+ .func = __func__, \
+ .file = __FILE__, \
+ .line = __LINE__, \
+ .level = __builtin_constant_p(_level) ? (_level) : NULL, \
+ .subsys_fmt_prefix = _subsys_fmt_prefix,\
+ }; \
+ static const struct pi_entry *_entry_ptr \
+ __used __section(".printk_index") = &_entry; \
+ } \
+ } while (0)
+
+#else /* !CONFIG_PRINTK_INDEX */
+#define __printk_index_emit(...) do {} while (0)
+#endif /* CONFIG_PRINTK_INDEX */
+
+/*
+ * Some subsystems have their own custom printk that applies a va_format to a
+ * generic format, for example, to include a device number or other metadata
+ * alongside the format supplied by the caller.
+ *
+ * In order to store these in the way they would be emitted by the printk
+ * infrastructure, the subsystem provides us with the start, fixed string, and
+ * any subsequent text in the format string.
+ *
+ * We take a variable argument list as pr_fmt/dev_fmt/etc are sometimes passed
+ * as multiple arguments (eg: `"%s: ", "blah"`), and we must only take the
+ * first one.
+ *
+ * subsys_fmt_prefix must be known at compile time, or compilation will fail
+ * (since this is a mistake). If fmt or level is not known at compile time, no
+ * index entry will be made (since this can legitimately happen).
+ */
+#define printk_index_subsys_emit(subsys_fmt_prefix, level, fmt, ...) \
+ __printk_index_emit(fmt, level, subsys_fmt_prefix)
+
+#define printk_index_wrap(_p_func, _fmt, ...) \
+ ({ \
+ __printk_index_emit(_fmt, NULL, NULL); \
+ _p_func(_fmt, ##__VA_ARGS__); \
+ })
+
+
+/**
+ * printk - print a kernel message
+ * @fmt: format string
+ *
+ * This is printk(). It can be called from any context. We want it to work.
+ *
+ * If printk indexing is enabled, _printk() is called from printk_index_wrap.
+ * Otherwise, printk is simply #defined to _printk.
+ *
+ * We try to grab the console_lock. If we succeed, it's easy - we log the
+ * output and call the console drivers. If we fail to get the semaphore, we
+ * place the output into the log buffer and return. The current holder of
+ * the console_sem will notice the new output in console_unlock(); and will
+ * send it to the consoles before releasing the lock.
+ *
+ * One effect of this deferred printing is that code which calls printk() and
+ * then changes console_loglevel may break. This is because console_loglevel
+ * is inspected when the actual printing occurs.
+ *
+ * See also:
+ * printf(3)
+ *
+ * See the vsnprintf() documentation for format string extensions over C99.
+ */
+#define printk(fmt, ...) printk_index_wrap(_printk, fmt, ##__VA_ARGS__)
+#define printk_deferred(fmt, ...) \
+ printk_index_wrap(_printk_deferred, fmt, ##__VA_ARGS__)
+
/**
* pr_emerg - Print an emergency-level message
* @fmt: format string
#ifdef CONFIG_PRINTK
#define printk_once(fmt, ...) \
-({ \
- static bool __section(".data.once") __print_once; \
- bool __ret_print_once = !__print_once; \
- \
- if (!__print_once) { \
- __print_once = true; \
- printk(fmt, ##__VA_ARGS__); \
- } \
- unlikely(__ret_print_once); \
-})
+ DO_ONCE_LITE(printk, fmt, ##__VA_ARGS__)
#define printk_deferred_once(fmt, ...) \
-({ \
- static bool __section(".data.once") __print_once; \
- bool __ret_print_once = !__print_once; \
- \
- if (!__print_once) { \
- __print_once = true; \
- printk_deferred(fmt, ##__VA_ARGS__); \
- } \
- unlikely(__ret_print_once); \
-})
+ DO_ONCE_LITE(printk_deferred, fmt, ##__VA_ARGS__)
#else
#define printk_once(fmt, ...) \
no_printk(fmt, ##__VA_ARGS__)
config CC_HAS_ASM_INLINE
def_bool $(success,echo 'void foo(void) { asm inline (""); }' | $(CC) -x c - -c -o /dev/null)
+config CC_HAS_NO_PROFILE_FN_ATTR
+ def_bool $(success,echo '__attribute__((no_profile_instrument_function)) int x();' | $(CC) -x c - -c -o /dev/null -Werror)
+
config CONSTRUCTORS
bool
13 => 8 KB for each CPU
12 => 4 KB for each CPU
+config PRINTK_INDEX
+ bool "Printk indexing debugfs interface"
+ depends on PRINTK && DEBUG_FS
+ help
+ Add support for indexing of all printk formats known at compile time
+ at <debugfs>/printk/index/<module>.
+
+ This can be used as part of maintaining daemons which monitor
+ /dev/kmsg, as it permits auditing the printk formats present in a
+ kernel, allowing detection of cases where monitored printks are
+ changed or no longer present.
+
+ There is no additional runtime cost to printk with this enabled.
+
#
# Architectures with an unreliable sched_clock() should select this:
#
very difficult to diagnose system problems, saying N here is
strongly discouraged.
- config PRINTK_NMI
- def_bool y
- depends on PRINTK
- depends on HAVE_NMI
-
config BUG
bool "BUG() support" if EXPERT
default y
default y
bool "Enable SLUB debugging support" if EXPERT
depends on SLUB && SYSFS
+ select STACKDEPOT if STACKTRACE_SUPPORT
help
SLUB has extensive debug support features. Disabling these can
result in significant savings in code size. This also disables
#include <linux/suspend.h>
#include <linux/device.h>
#include <linux/freezer.h>
+#include <linux/panic_notifier.h>
#include <linux/pm.h>
#include <linux/cpu.h>
#include <linux/uaccess.h>
old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
if (old_cpu == PANIC_CPU_INVALID) {
/* This is the 1st CPU which comes here, so go ahead. */
- printk_safe_flush_on_panic();
__crash_kexec(regs);
/*
#include <linux/reboot.h>
#include <linux/delay.h>
#include <linux/kexec.h>
+#include <linux/panic_notifier.h>
#include <linux/sched.h>
#include <linux/sysrq.h>
#include <linux/init.h>
* Bypass the panic_cpu check and call __crash_kexec directly.
*/
if (!_crash_kexec_post_notifiers) {
- printk_safe_flush_on_panic();
__crash_kexec(NULL);
/*
*/
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
- /* Call flush even twice. It tries harder with a single online CPU */
- printk_safe_flush_on_panic();
kmsg_dump(KMSG_DUMP_PANIC);
/*
#ifdef CONFIG_PRINTK
- #define PRINTK_SAFE_CONTEXT_MASK 0x007ffffff
- #define PRINTK_NMI_DIRECT_CONTEXT_MASK 0x008000000
- #define PRINTK_NMI_CONTEXT_MASK 0xff0000000
-
- #define PRINTK_NMI_CONTEXT_OFFSET 0x010000000
-
+/* Flags for a single printk record. */
+enum printk_info_flags {
+ LOG_NEWLINE = 2, /* text ended with a newline */
+ LOG_CONT = 8, /* text is a fragment of a continuation line */
+};
+
__printf(4, 0)
int vprintk_store(int facility, int level,
const struct dev_printk_info *dev_info,
__printf(1, 0) int vprintk_default(const char *fmt, va_list args);
__printf(1, 0) int vprintk_deferred(const char *fmt, va_list args);
- void __printk_safe_enter(void);
- void __printk_safe_exit(void);
- void printk_safe_init(void);
bool printk_percpu_data_ready(void);
#define printk_safe_enter_irqsave(flags) \
local_irq_restore(flags); \
} while (0)
- #define printk_safe_enter_irq() \
- do { \
- local_irq_disable(); \
- __printk_safe_enter(); \
- } while (0)
-
- #define printk_safe_exit_irq() \
- do { \
- __printk_safe_exit(); \
- local_irq_enable(); \
- } while (0)
-
void defer_console_output(void);
+u16 printk_parse_prefix(const char *text, int *level,
+ enum printk_info_flags *flags);
#else
/*
#define printk_safe_enter_irqsave(flags) local_irq_save(flags)
#define printk_safe_exit_irqrestore(flags) local_irq_restore(flags)
- #define printk_safe_enter_irq() local_irq_disable()
- #define printk_safe_exit_irq() local_irq_enable()
-
- static inline void printk_safe_init(void) { }
static inline bool printk_percpu_data_ready(void) { return false; }
#endif /* CONFIG_PRINTK */
* non-prinatable characters are escaped in the "\xff" notation.
*/
-enum log_flags {
- LOG_NEWLINE = 2, /* text ended with a newline */
- LOG_CONT = 8, /* text is a fragment of a continuation line */
-};
-
/* syslog_lock protects syslog_* variables and write access to clear_seq. */
- static DEFINE_RAW_SPINLOCK(syslog_lock);
+ static DEFINE_MUTEX(syslog_lock);
#ifdef CONFIG_PRINTK
DECLARE_WAIT_QUEUE_HEAD(log_wait);
if (ret)
return ret;
- printk_safe_enter_irq();
if (!prb_read_valid(prb, atomic64_read(&user->seq), r)) {
if (file->f_flags & O_NONBLOCK) {
ret = -EAGAIN;
- printk_safe_exit_irq();
goto out;
}
- printk_safe_exit_irq();
ret = wait_event_interruptible(log_wait,
prb_read_valid(prb, atomic64_read(&user->seq), r));
if (ret)
goto out;
- printk_safe_enter_irq();
}
if (r->info->seq != atomic64_read(&user->seq)) {
/* our last seen message is gone, return error and reset */
atomic64_set(&user->seq, r->info->seq);
ret = -EPIPE;
- printk_safe_exit_irq();
goto out;
}
&r->info->dev_info);
atomic64_set(&user->seq, r->info->seq + 1);
- printk_safe_exit_irq();
if (len > count) {
ret = -EINVAL;
if (offset)
return -ESPIPE;
- printk_safe_enter_irq();
switch (whence) {
case SEEK_SET:
/* the first record */
default:
ret = -EINVAL;
}
- printk_safe_exit_irq();
return ret;
}
poll_wait(file, &log_wait, wait);
- printk_safe_enter_irq();
if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) {
/* return error when data has vanished underneath us */
if (info.seq != atomic64_read(&user->seq))
else
ret = EPOLLIN|EPOLLRDNORM;
}
- printk_safe_exit_irq();
return ret;
}
prb_rec_init_rd(&user->record, &user->info,
&user->text_buf[0], sizeof(user->text_buf));
- printk_safe_enter_irq();
atomic64_set(&user->seq, prb_first_valid_seq(prb));
- printk_safe_exit_irq();
file->private_data = user;
return 0;
static void __init set_percpu_data_ready(void)
{
- printk_safe_init();
- /* Make sure we set this flag only after printk_safe() init is done */
- barrier();
__printk_percpu_data_ready = true;
}
struct prb_desc *new_descs;
struct printk_info info;
struct printk_record r;
+ unsigned int text_size;
size_t new_descs_size;
size_t new_infos_size;
unsigned long flags;
new_descs, ilog2(new_descs_count),
new_infos);
- printk_safe_enter_irqsave(flags);
+ local_irq_save(flags);
log_buf_len = new_log_buf_len;
log_buf = new_log_buf;
new_log_buf_len = 0;
free = __LOG_BUF_LEN;
- prb_for_each_record(0, &printk_rb_static, seq, &r)
- free -= add_to_rb(&printk_rb_dynamic, &r);
+ prb_for_each_record(0, &printk_rb_static, seq, &r) {
+ text_size = add_to_rb(&printk_rb_dynamic, &r);
+ if (text_size > free)
+ free = 0;
+ else
+ free -= text_size;
+ }
- /*
- * This is early enough that everything is still running on the
- * boot CPU and interrupts are disabled. So no new messages will
- * appear during the transition to the dynamic buffer.
- */
prb = &printk_rb_dynamic;
- printk_safe_exit_irqrestore(flags);
+ local_irq_restore(flags);
+
+ /*
+ * Copy any remaining messages that might have appeared from
+ * NMI context after copying but before switching to the
+ * dynamic buffer.
+ */
+ prb_for_each_record(seq, &printk_rb_static, seq, &r) {
+ text_size = add_to_rb(&printk_rb_dynamic, &r);
+ if (text_size > free)
+ free = 0;
+ else
+ free -= text_size;
+ }
if (seq != prb_next_seq(&printk_rb_static)) {
pr_err("dropped %llu messages\n",
return seq;
}
+ /* The caller is responsible for making sure @size is greater than 0. */
static int syslog_print(char __user *buf, int size)
{
struct printk_info info;
struct printk_record r;
char *text;
int len = 0;
+ u64 seq;
text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL);
if (!text)
prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX);
- while (size > 0) {
+ mutex_lock(&syslog_lock);
+
+ /*
+ * Wait for the @syslog_seq record to be available. @syslog_seq may
+ * change while waiting.
+ */
+ do {
+ seq = syslog_seq;
+
+ mutex_unlock(&syslog_lock);
+ len = wait_event_interruptible(log_wait, prb_read_valid(prb, seq, NULL));
+ mutex_lock(&syslog_lock);
+
+ if (len)
+ goto out;
+ } while (syslog_seq != seq);
+
+ /*
+ * Copy records that fit into the buffer. The above cycle makes sure
+ * that the first record is always available.
+ */
+ do {
size_t n;
size_t skip;
+ int err;
- printk_safe_enter_irq();
- raw_spin_lock(&syslog_lock);
- if (!prb_read_valid(prb, syslog_seq, &r)) {
- raw_spin_unlock(&syslog_lock);
- printk_safe_exit_irq();
+ if (!prb_read_valid(prb, syslog_seq, &r))
break;
- }
+
if (r.info->seq != syslog_seq) {
/* message is gone, move to next valid one */
syslog_seq = r.info->seq;
syslog_partial += n;
} else
n = 0;
- raw_spin_unlock(&syslog_lock);
- printk_safe_exit_irq();
if (!n)
break;
- if (copy_to_user(buf, text + skip, n)) {
+ mutex_unlock(&syslog_lock);
+ err = copy_to_user(buf, text + skip, n);
+ mutex_lock(&syslog_lock);
+
+ if (err) {
if (!len)
len = -EFAULT;
break;
len += n;
size -= n;
buf += n;
- }
-
+ } while (size);
+ out:
+ mutex_unlock(&syslog_lock);
kfree(text);
return len;
}
return -ENOMEM;
time = printk_time;
- printk_safe_enter_irq();
/*
* Find first record that fits, including all following records,
* into the user-provided buffer for this dump.
break;
}
- printk_safe_exit_irq();
if (copy_to_user(buf + len, text, textlen))
len = -EFAULT;
else
len += textlen;
- printk_safe_enter_irq();
if (len < 0)
break;
}
if (clear) {
- raw_spin_lock(&syslog_lock);
+ mutex_lock(&syslog_lock);
latched_seq_write(&clear_seq, seq);
- raw_spin_unlock(&syslog_lock);
+ mutex_unlock(&syslog_lock);
}
- printk_safe_exit_irq();
kfree(text);
return len;
static void syslog_clear(void)
{
- printk_safe_enter_irq();
- raw_spin_lock(&syslog_lock);
+ mutex_lock(&syslog_lock);
latched_seq_write(&clear_seq, prb_next_seq(prb));
- raw_spin_unlock(&syslog_lock);
- printk_safe_exit_irq();
- }
-
- /* Return a consistent copy of @syslog_seq. */
- static u64 read_syslog_seq_irq(void)
- {
- u64 seq;
-
- raw_spin_lock_irq(&syslog_lock);
- seq = syslog_seq;
- raw_spin_unlock_irq(&syslog_lock);
-
- return seq;
+ mutex_unlock(&syslog_lock);
}
int do_syslog(int type, char __user *buf, int len, int source)
return 0;
if (!access_ok(buf, len))
return -EFAULT;
-
- error = wait_event_interruptible(log_wait,
- prb_read_valid(prb, read_syslog_seq_irq(), NULL));
- if (error)
- return error;
error = syslog_print(buf, len);
break;
/* Read/clear last kernel messages */
break;
/* Number of chars in the log buffer */
case SYSLOG_ACTION_SIZE_UNREAD:
- printk_safe_enter_irq();
- raw_spin_lock(&syslog_lock);
+ mutex_lock(&syslog_lock);
if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) {
/* No unread messages. */
- raw_spin_unlock(&syslog_lock);
- printk_safe_exit_irq();
+ mutex_unlock(&syslog_lock);
return 0;
}
if (info.seq != syslog_seq) {
}
error -= syslog_partial;
}
- raw_spin_unlock(&syslog_lock);
- printk_safe_exit_irq();
+ mutex_unlock(&syslog_lock);
break;
/* Size of the log buffer */
case SYSLOG_ACTION_SIZE_BUFFER:
}
}
+ /*
+ * Recursion is tracked separately on each CPU. If NMIs are supported, an
+ * additional NMI context per CPU is also separately tracked. Until per-CPU
+ * is available, a separate "early tracking" is performed.
+ */
+ static DEFINE_PER_CPU(u8, printk_count);
+ static u8 printk_count_early;
+ #ifdef CONFIG_HAVE_NMI
+ static DEFINE_PER_CPU(u8, printk_count_nmi);
+ static u8 printk_count_nmi_early;
+ #endif
+
+ /*
+ * Recursion is limited to keep the output sane. printk() should not require
+ * more than 1 level of recursion (allowing, for example, printk() to trigger
+ * a WARN), but a higher value is used in case some printk-internal errors
+ * exist, such as the ringbuffer validation checks failing.
+ */
+ #define PRINTK_MAX_RECURSION 3
+
+ /*
+ * Return a pointer to the dedicated counter for the CPU+context of the
+ * caller.
+ */
+ static u8 *__printk_recursion_counter(void)
+ {
+ #ifdef CONFIG_HAVE_NMI
+ if (in_nmi()) {
+ if (printk_percpu_data_ready())
+ return this_cpu_ptr(&printk_count_nmi);
+ return &printk_count_nmi_early;
+ }
+ #endif
+ if (printk_percpu_data_ready())
+ return this_cpu_ptr(&printk_count);
+ return &printk_count_early;
+ }
+
+ /*
+ * Enter recursion tracking. Interrupts are disabled to simplify tracking.
+ * The caller must check the boolean return value to see if the recursion is
+ * allowed. On failure, interrupts are not disabled.
+ *
+ * @recursion_ptr must be a variable of type (u8 *) and is the same variable
+ * that is passed to printk_exit_irqrestore().
+ */
+ #define printk_enter_irqsave(recursion_ptr, flags) \
+ ({ \
+ bool success = true; \
+ \
+ typecheck(u8 *, recursion_ptr); \
+ local_irq_save(flags); \
+ (recursion_ptr) = __printk_recursion_counter(); \
+ if (*(recursion_ptr) > PRINTK_MAX_RECURSION) { \
+ local_irq_restore(flags); \
+ success = false; \
+ } else { \
+ (*(recursion_ptr))++; \
+ } \
+ success; \
+ })
+
+ /* Exit recursion tracking, restoring interrupts. */
+ #define printk_exit_irqrestore(recursion_ptr, flags) \
+ do { \
+ typecheck(u8 *, recursion_ptr); \
+ (*(recursion_ptr))--; \
+ local_irq_restore(flags); \
+ } while (0)
+
int printk_delay_msec __read_mostly;
static inline void printk_delay(void)
}
/**
- * parse_prefix - Parse level and control flags.
+ * printk_parse_prefix - Parse level and control flags.
*
* @text: The terminated text message.
* @level: A pointer to the current level value, will be updated.
- * @lflags: A pointer to the current log flags, will be updated.
+ * @flags: A pointer to the current printk_info flags, will be updated.
*
* @level may be NULL if the caller is not interested in the parsed value.
* Otherwise the variable pointed to by @level must be set to
* LOGLEVEL_DEFAULT in order to be updated with the parsed value.
*
- * @lflags may be NULL if the caller is not interested in the parsed value.
- * Otherwise the variable pointed to by @lflags will be OR'd with the parsed
+ * @flags may be NULL if the caller is not interested in the parsed value.
+ * Otherwise the variable pointed to by @flags will be OR'd with the parsed
* value.
*
* Return: The length of the parsed level and control flags.
*/
-static u16 parse_prefix(char *text, int *level, enum log_flags *lflags)
+u16 printk_parse_prefix(const char *text, int *level,
+ enum printk_info_flags *flags)
{
u16 prefix_len = 0;
int kern_level;
*level = kern_level - '0';
break;
case 'c': /* KERN_CONT */
- if (lflags)
- *lflags |= LOG_CONT;
+ if (flags)
+ *flags |= LOG_CONT;
}
prefix_len += 2;
return prefix_len;
}
-static u16 printk_sprint(char *text, u16 size, int facility, enum log_flags *lflags,
- const char *fmt, va_list args)
+static u16 printk_sprint(char *text, u16 size, int facility,
+ enum printk_info_flags *flags, const char *fmt,
+ va_list args)
{
u16 text_len;
/* Mark and strip a trailing newline. */
if (text_len && text[text_len - 1] == '\n') {
text_len--;
- *lflags |= LOG_NEWLINE;
+ *flags |= LOG_NEWLINE;
}
/* Strip log level and control flags. */
if (facility == 0) {
u16 prefix_len;
- prefix_len = parse_prefix(text, NULL, NULL);
+ prefix_len = printk_parse_prefix(text, NULL, NULL);
if (prefix_len) {
text_len -= prefix_len;
memmove(text, text + prefix_len, text_len);
{
const u32 caller_id = printk_caller_id();
struct prb_reserved_entry e;
- enum log_flags lflags = 0;
+ enum printk_info_flags flags = 0;
struct printk_record r;
+ unsigned long irqflags;
u16 trunc_msg_len = 0;
char prefix_buf[8];
+ u8 *recursion_ptr;
u16 reserve_size;
va_list args2;
u16 text_len;
+ int ret = 0;
u64 ts_nsec;
/*
*/
ts_nsec = local_clock();
+ if (!printk_enter_irqsave(recursion_ptr, irqflags))
+ return 0;
+
/*
* The sprintf needs to come first since the syslog prefix might be
* passed in as a parameter. An extra byte must be reserved so that
/* Extract log level or control flags. */
if (facility == 0)
- parse_prefix(&prefix_buf[0], &level, &lflags);
+ printk_parse_prefix(&prefix_buf[0], &level, &flags);
if (level == LOGLEVEL_DEFAULT)
level = default_message_loglevel;
if (dev_info)
- lflags |= LOG_NEWLINE;
+ flags |= LOG_NEWLINE;
- if (lflags & LOG_CONT) {
+ if (flags & LOG_CONT) {
prb_rec_init_wr(&r, reserve_size);
if (prb_reserve_in_last(&e, prb, &r, caller_id, LOG_LINE_MAX)) {
text_len = printk_sprint(&r.text_buf[r.info->text_len], reserve_size,
- facility, &lflags, fmt, args);
+ facility, &flags, fmt, args);
r.info->text_len += text_len;
- if (lflags & LOG_NEWLINE) {
+ if (flags & LOG_NEWLINE) {
r.info->flags |= LOG_NEWLINE;
prb_final_commit(&e);
} else {
prb_commit(&e);
}
- return text_len;
+ ret = text_len;
+ goto out;
}
}
prb_rec_init_wr(&r, reserve_size + trunc_msg_len);
if (!prb_reserve(&e, prb, &r))
- return 0;
+ goto out;
}
/* fill message */
- text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &lflags, fmt, args);
+ text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &flags, fmt, args);
if (trunc_msg_len)
memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len);
r.info->text_len = text_len + trunc_msg_len;
r.info->facility = facility;
r.info->level = level & 7;
- r.info->flags = lflags & 0x1f;
+ r.info->flags = flags & 0x1f;
r.info->ts_nsec = ts_nsec;
r.info->caller_id = caller_id;
if (dev_info)
memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info));
/* A message without a trailing newline can be continued. */
- if (!(lflags & LOG_NEWLINE))
+ if (!(flags & LOG_NEWLINE))
prb_commit(&e);
else
prb_final_commit(&e);
- return (text_len + trunc_msg_len);
+ ret = text_len + trunc_msg_len;
+ out:
+ printk_exit_irqrestore(recursion_ptr, irqflags);
+ return ret;
}
asmlinkage int vprintk_emit(int facility, int level,
{
int printed_len;
bool in_sched = false;
- unsigned long flags;
/* Suppress unimportant messages after panic happens */
if (unlikely(suppress_printk))
boot_delay_msec(level);
printk_delay();
- printk_safe_enter_irqsave(flags);
printed_len = vprintk_store(facility, level, dev_info, fmt, args);
- printk_safe_exit_irqrestore(flags);
/* If called from the scheduler, we can not call up(). */
if (!in_sched) {
}
EXPORT_SYMBOL_GPL(vprintk_default);
-/**
- * printk - print a kernel message
- * @fmt: format string
- *
- * This is printk(). It can be called from any context. We want it to work.
- *
- * We try to grab the console_lock. If we succeed, it's easy - we log the
- * output and call the console drivers. If we fail to get the semaphore, we
- * place the output into the log buffer and return. The current holder of
- * the console_sem will notice the new output in console_unlock(); and will
- * send it to the consoles before releasing the lock.
- *
- * One effect of this deferred printing is that code which calls printk() and
- * then changes console_loglevel may break. This is because console_loglevel
- * is inspected when the actual printing occurs.
- *
- * See also:
- * printf(3)
- *
- * See the vsnprintf() documentation for format string extensions over C99.
- */
-asmlinkage __visible int printk(const char *fmt, ...)
+asmlinkage __visible int _printk(const char *fmt, ...)
{
va_list args;
int r;
return r;
}
-EXPORT_SYMBOL(printk);
+EXPORT_SYMBOL(_printk);
#else /* CONFIG_PRINTK */
MODULE_PARM_DESC(console_suspend, "suspend console during suspend"
" and hibernate operations");
+static bool printk_console_no_auto_verbose;
+
+void console_verbose(void)
+{
+ if (console_loglevel && !printk_console_no_auto_verbose)
+ console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
+}
+EXPORT_SYMBOL_GPL(console_verbose);
+
+module_param_named(console_no_auto_verbose, printk_console_no_auto_verbose, bool, 0644);
+MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to highest on oops/panic/etc");
+
/**
* suspend_console - suspend the console subsystem
*
bool do_cond_resched, retry;
struct printk_info info;
struct printk_record r;
+ u64 __maybe_unused next_seq;
if (console_suspended) {
up_console_sem();
for (;;) {
size_t ext_len = 0;
+ int handover;
size_t len;
- printk_safe_enter_irqsave(flags);
skip:
if (!prb_read_valid(prb, console_seq, &r))
break;
* were to occur on another CPU, it may wait for this one to
* finish. This task can not be preempted if there is a
* waiter waiting to take over.
+ *
+ * Interrupts are disabled because the hand over to a waiter
+ * must not be interrupted until the hand over is completed
+ * (@console_waiter is cleared).
*/
+ printk_safe_enter_irqsave(flags);
console_lock_spinning_enable();
stop_critical_timings(); /* don't trace print latency */
call_console_drivers(ext_text, ext_len, text, len);
start_critical_timings();
- if (console_lock_spinning_disable_and_check()) {
- printk_safe_exit_irqrestore(flags);
- return;
- }
-
+ handover = console_lock_spinning_disable_and_check();
printk_safe_exit_irqrestore(flags);
+ if (handover)
+ return;
if (do_cond_resched)
cond_resched();
}
- console_locked = 0;
+ /* Get consistent value of the next-to-be-used sequence number. */
+ next_seq = console_seq;
+ console_locked = 0;
up_console_sem();
/*
* there's a new owner and the console_unlock() from them will do the
* flush, no worries.
*/
- retry = prb_read_valid(prb, console_seq, NULL);
+ retry = prb_read_valid(prb, next_seq, NULL);
- printk_safe_exit_irqrestore(flags);
-
if (retry && console_trylock())
goto again;
}
console_trylock();
console_may_schedule = 0;
- if (mode == CONSOLE_REPLAY_ALL) {
- unsigned long flags;
-
- printk_safe_enter_irqsave(flags);
+ if (mode == CONSOLE_REPLAY_ALL)
console_seq = prb_first_valid_seq(prb);
- printk_safe_exit_irqrestore(flags);
- }
console_unlock();
}
*/
void register_console(struct console *newcon)
{
- unsigned long flags;
struct console *bcon = NULL;
int err;
exclusive_console_stop_seq = console_seq;
/* Get a consistent copy of @syslog_seq. */
- raw_spin_lock_irqsave(&syslog_lock, flags);
+ mutex_lock(&syslog_lock);
console_seq = syslog_seq;
- raw_spin_unlock_irqrestore(&syslog_lock, flags);
+ mutex_unlock(&syslog_lock);
}
console_unlock();
console_sysfs_notify();
return r;
}
-int printk_deferred(const char *fmt, ...)
+int _printk_deferred(const char *fmt, ...)
{
va_list args;
int r;
struct printk_info info;
unsigned int line_count;
struct printk_record r;
- unsigned long flags;
size_t l = 0;
bool ret = false;
if (iter->cur_seq < min_seq)
iter->cur_seq = min_seq;
- printk_safe_enter_irqsave(flags);
prb_rec_init_rd(&r, &info, line, size);
/* Read text or count text lines? */
iter->cur_seq = r.info->seq + 1;
ret = true;
out:
- printk_safe_exit_irqrestore(flags);
if (len)
*len = l;
return ret;
u64 min_seq = latched_seq_read_nolock(&clear_seq);
struct printk_info info;
struct printk_record r;
- unsigned long flags;
u64 seq;
u64 next_seq;
size_t len = 0;
if (iter->cur_seq < min_seq)
iter->cur_seq = min_seq;
- printk_safe_enter_irqsave(flags);
if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) {
if (info.seq != iter->cur_seq) {
/* messages are gone, move to first available one */
}
/* last entry */
- if (iter->cur_seq >= iter->next_seq) {
- printk_safe_exit_irqrestore(flags);
+ if (iter->cur_seq >= iter->next_seq)
goto out;
- }
/*
* Find first record that fits, including all following records,
iter->next_seq = next_seq;
ret = true;
- printk_safe_exit_irqrestore(flags);
out:
if (len_out)
*len_out = len;
*/
void kmsg_dump_rewind(struct kmsg_dump_iter *iter)
{
- unsigned long flags;
-
- printk_safe_enter_irqsave(flags);
iter->cur_seq = latched_seq_read_nolock(&clear_seq);
iter->next_seq = prb_next_seq(prb);
- printk_safe_exit_irqrestore(flags);
}
EXPORT_SYMBOL_GPL(kmsg_dump_rewind);
#include <linux/slab.h>
#include <linux/ctype.h>
#include <linux/init.h>
+#include <linux/panic_notifier.h>
#include <linux/poll.h>
#include <linux/nmi.h>
#include <linux/fs.h>
/* Pipe tracepoints to printk */
struct trace_iterator *tracepoint_print_iter;
int tracepoint_printk;
+static bool tracepoint_printk_stop_on_boot __initdata;
static DEFINE_STATIC_KEY_FALSE(tracepoint_printk_key);
/* For tracers that don't implement custom flags */
static int __init set_ftrace_dump_on_oops(char *str)
{
- if (*str++ != '=' || !*str) {
+ if (*str++ != '=' || !*str || !strcmp("1", str)) {
ftrace_dump_on_oops = DUMP_ALL;
return 1;
}
- if (!strcmp("orig_cpu", str)) {
+ if (!strcmp("orig_cpu", str) || !strcmp("2", str)) {
ftrace_dump_on_oops = DUMP_ORIG;
return 1;
}
}
__setup("tp_printk", set_tracepoint_printk);
+static int __init set_tracepoint_printk_stop(char *str)
+{
+ tracepoint_printk_stop_on_boot = true;
+ return 1;
+}
+__setup("tp_printk_stop_on_boot", set_tracepoint_printk_stop);
+
unsigned long long ns2usecs(u64 nsec)
{
nsec += 500;
unsigned long __read_mostly tracing_thresh;
static const struct file_operations tracing_max_lat_fops;
-#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
- defined(CONFIG_FSNOTIFY)
+#ifdef LATENCY_FS_NOTIFY
static struct workqueue_struct *fsnotify_wq;
}
}
+/*
+ * The tgid_map array maps from pid to tgid; i.e. the value stored at index i
+ * is the tgid last observed corresponding to pid=i.
+ */
static int *tgid_map;
+/* The maximum valid index into tgid_map. */
+static size_t tgid_map_max;
+
#define SAVED_CMDLINES_DEFAULT 128
#define NO_CMDLINE_MAP UINT_MAX
static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
preempt_enable();
}
+static int *trace_find_tgid_ptr(int pid)
+{
+ /*
+ * Pairs with the smp_store_release in set_tracer_flag() to ensure that
+ * if we observe a non-NULL tgid_map then we also observe the correct
+ * tgid_map_max.
+ */
+ int *map = smp_load_acquire(&tgid_map);
+
+ if (unlikely(!map || pid > tgid_map_max))
+ return NULL;
+
+ return &map[pid];
+}
+
int trace_find_tgid(int pid)
{
- if (unlikely(!tgid_map || !pid || pid > PID_MAX_DEFAULT))
- return 0;
+ int *ptr = trace_find_tgid_ptr(pid);
- return tgid_map[pid];
+ return ptr ? *ptr : 0;
}
static int trace_save_tgid(struct task_struct *tsk)
{
+ int *ptr;
+
/* treat recording of idle task as a success */
if (!tsk->pid)
return 1;
- if (unlikely(!tgid_map || tsk->pid > PID_MAX_DEFAULT))
+ ptr = trace_find_tgid_ptr(tsk->pid);
+ if (!ptr)
return 0;
- tgid_map[tsk->pid] = tsk->tgid;
+ *ptr = tsk->tgid;
return 1;
}
if (!tr->no_filter_buffering_ref &&
(trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) &&
(entry = this_cpu_read(trace_buffered_event))) {
- /* Try to use the per cpu buffer first */
+ /*
+ * Filtering is on, so try to use the per cpu buffer first.
+ * This buffer will simulate a ring_buffer_event,
+ * where the type_len is zero and the array[0] will
+ * hold the full length.
+ * (see include/linux/ring-buffer.h for details on
+ * how the ring_buffer_event is structured).
+ *
+ * Using a temp buffer during filtering and copying it
+ * on a matched filter is quicker than writing directly
+ * into the ring buffer and then discarding it when
+ * it doesn't match. That is because the discard
+ * requires several atomic operations to get right.
+ * Copying on match and doing nothing on a failed match
+ * is still quicker than no copy on match, but having
+ * to discard out of the ring buffer on a failed match.
+ */
+ int max_len = PAGE_SIZE - struct_size(entry, array, 1);
+
val = this_cpu_inc_return(trace_buffered_event_cnt);
- if ((len < (PAGE_SIZE - sizeof(*entry) - sizeof(entry->array[0]))) && val == 1) {
+
+ /*
+ * Preemption is disabled, but interrupts and NMIs
+ * can still come in now. If that happens after
+ * the above increment, then it will have to go
+ * back to the old method of allocating the event
+ * on the ring buffer, and if the filter fails, it
+ * will have to call ring_buffer_discard_commit()
+ * to remove it.
+ *
+ * Need to also check the unlikely case that the
+ * length is bigger than the temp buffer size.
+ * If that happens, then the reserve is pretty much
+ * guaranteed to fail, as the ring buffer currently
+ * only allows events less than a page. But that may
+ * change in the future, so let the ring buffer reserve
+ * handle the failure in that case.
+ */
+ if (val == 1 && likely(len <= max_len)) {
trace_event_setup(entry, type, trace_ctx);
entry->array[0] = len;
return entry;
int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
{
+ int *map;
+
if ((mask == TRACE_ITER_RECORD_TGID) ||
(mask == TRACE_ITER_RECORD_CMD))
lockdep_assert_held(&event_mutex);
trace_event_enable_cmd_record(enabled);
if (mask == TRACE_ITER_RECORD_TGID) {
- if (!tgid_map)
- tgid_map = kvcalloc(PID_MAX_DEFAULT + 1,
- sizeof(*tgid_map),
- GFP_KERNEL);
+ if (!tgid_map) {
+ tgid_map_max = pid_max;
+ map = kvcalloc(tgid_map_max + 1, sizeof(*tgid_map),
+ GFP_KERNEL);
+
+ /*
+ * Pairs with smp_load_acquire() in
+ * trace_find_tgid_ptr() to ensure that if it observes
+ * the tgid_map we just allocated then it also observes
+ * the corresponding tgid_map_max value.
+ */
+ smp_store_release(&tgid_map, map);
+ }
if (!tgid_map) {
tr->trace_flags &= ~TRACE_ITER_RECORD_TGID;
return -ENOMEM;
static void *saved_tgids_next(struct seq_file *m, void *v, loff_t *pos)
{
- int *ptr = v;
-
- if (*pos || m->count)
- ptr++;
-
- (*pos)++;
-
- for (; ptr <= &tgid_map[PID_MAX_DEFAULT]; ptr++) {
- if (trace_find_tgid(*ptr))
- return ptr;
- }
+ int pid = ++(*pos);
- return NULL;
+ return trace_find_tgid_ptr(pid);
}
static void *saved_tgids_start(struct seq_file *m, loff_t *pos)
{
- void *v;
- loff_t l = 0;
-
- if (!tgid_map)
- return NULL;
+ int pid = *pos;
- v = &tgid_map[0];
- while (l <= *pos) {
- v = saved_tgids_next(m, v, &l);
- if (!v)
- return NULL;
- }
-
- return v;
+ return trace_find_tgid_ptr(pid);
}
static void saved_tgids_stop(struct seq_file *m, void *v)
static int saved_tgids_show(struct seq_file *m, void *v)
{
- int pid = (int *)v - tgid_map;
+ int *entry = (int *)v;
+ int pid = entry - tgid_map;
+ int tgid = *entry;
- seq_printf(m, "%d %d\n", pid, trace_find_tgid(pid));
+ if (tgid == 0)
+ return SEQ_SKIP;
+
+ seq_printf(m, "%d %d\n", pid, tgid);
return 0;
}
ssize_t tracing_resize_ring_buffer(struct trace_array *tr,
unsigned long size, int cpu_id)
{
- int ret = size;
+ int ret;
mutex_lock(&trace_types_lock);
#endif /* CONFIG_TRACER_SNAPSHOT */
+/*
+ * trace_min_max_write - Write a u64 value to a trace_min_max_param struct
+ * @filp: The active open file structure
+ * @ubuf: The userspace provided buffer to read value into
+ * @cnt: The maximum number of bytes to read
+ * @ppos: The current "file" position
+ *
+ * This function implements the write interface for a struct trace_min_max_param.
+ * The filp->private_data must point to a trace_min_max_param structure that
+ * defines where to write the value, the min and the max acceptable values,
+ * and a lock to protect the write.
+ */
+static ssize_t
+trace_min_max_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+ struct trace_min_max_param *param = filp->private_data;
+ u64 val;
+ int err;
+
+ if (!param)
+ return -EFAULT;
+
+ err = kstrtoull_from_user(ubuf, cnt, 10, &val);
+ if (err)
+ return err;
+
+ if (param->lock)
+ mutex_lock(param->lock);
+
+ if (param->min && val < *param->min)
+ err = -EINVAL;
+
+ if (param->max && val > *param->max)
+ err = -EINVAL;
+
+ if (!err)
+ *param->val = val;
+
+ if (param->lock)
+ mutex_unlock(param->lock);
+
+ if (err)
+ return err;
+
+ return cnt;
+}
+
+/*
+ * trace_min_max_read - Read a u64 value from a trace_min_max_param struct
+ * @filp: The active open file structure
+ * @ubuf: The userspace provided buffer to read value into
+ * @cnt: The maximum number of bytes to read
+ * @ppos: The current "file" position
+ *
+ * This function implements the read interface for a struct trace_min_max_param.
+ * The filp->private_data must point to a trace_min_max_param struct with valid
+ * data.
+ */
+static ssize_t
+trace_min_max_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+ struct trace_min_max_param *param = filp->private_data;
+ char buf[U64_STR_SIZE];
+ int len;
+ u64 val;
+
+ if (!param)
+ return -EFAULT;
+
+ val = *param->val;
+
+ if (cnt > sizeof(buf))
+ cnt = sizeof(buf);
+
+ len = snprintf(buf, sizeof(buf), "%llu\n", val);
+
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, len);
+}
+
+const struct file_operations trace_min_max_fops = {
+ .open = tracing_open_generic,
+ .read = trace_min_max_read,
+ .write = trace_min_max_write,
+};
+
#define TRACING_LOG_ERRS_MAX 8
#define TRACING_LOG_LOC_MAX 128
return 0;
}
+fs_initcall(tracer_init_tracefs);
+
static int trace_panic_handler(struct notifier_block *this,
unsigned long event, void *unused)
{
tracing_off();
local_irq_save(flags);
- printk_nmi_direct_enter();
/* Simulate the iterator */
trace_init_global_iter(&iter);
atomic_dec(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
}
atomic_dec(&dump_running);
- printk_nmi_direct_exit();
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(ftrace_dump);
trace_event_init();
}
-__init static int clear_boot_tracer(void)
+__init static void clear_boot_tracer(void)
{
/*
* The default tracer at boot buffer is an init section.
* about to be freed.
*/
if (!default_bootup_tracer)
- return 0;
+ return;
printk(KERN_INFO "ftrace bootup tracer '%s' not registered.\n",
default_bootup_tracer);
default_bootup_tracer = NULL;
-
- return 0;
}
-fs_initcall(tracer_init_tracefs);
-late_initcall_sync(clear_boot_tracer);
-
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-__init static int tracing_set_default_clock(void)
+__init static void tracing_set_default_clock(void)
{
/* sched_clock_stable() is determined in late_initcall */
if (!trace_boot_clock && !sched_clock_stable()) {
if (security_locked_down(LOCKDOWN_TRACEFS)) {
pr_warn("Can not set tracing clock due to lockdown\n");
- return -EPERM;
+ return;
}
printk(KERN_WARNING
"on the kernel command line\n");
tracing_set_clock(&global_trace, "global");
}
+}
+#else
+static inline void tracing_set_default_clock(void) { }
+#endif
+
+__init static int late_trace_init(void)
+{
+ if (tracepoint_printk && tracepoint_printk_stop_on_boot) {
+ static_key_disable(&tracepoint_printk_key.key);
+ tracepoint_printk = 0;
+ }
+ tracing_set_default_clock();
+ clear_boot_tracer();
return 0;
}
-late_initcall_sync(tracing_set_default_clock);
-#endif
+
+late_initcall_sync(late_trace_init);