* Fixed SMP synchronization, 08/08/99, Manfred Spraul
* manfred@colorfullife.com
* Rewrote bits to get rid of console_lock
- * 01Mar01 Andrew Morton <andrewm@uow.edu.au>
+ * 01Mar01 Andrew Morton
*/
#include <linux/kernel.h>
#include <linux/smp.h>
#include <linux/security.h>
#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/syscalls.h>
+#include <linux/kexec.h>
+#include <linux/kdb.h>
+#include <linux/ratelimit.h>
+#include <linux/kmsg_dump.h>
+#include <linux/syslog.h>
+#include <linux/cpu.h>
+#include <linux/notifier.h>
+#include <linux/rculist.h>
#include <asm/uaccess.h>
/*
* Architectures can override it:
*/
-void __attribute__((weak)) early_printk(const char *fmt, ...)
+void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...)
{
}
#define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
/* printk's without a loglevel use this.. */
-#define DEFAULT_MESSAGE_LOGLEVEL 4 /* KERN_WARNING */
+#define DEFAULT_MESSAGE_LOGLEVEL CONFIG_DEFAULT_MESSAGE_LOGLEVEL
/* We show everything that is MORE important than this.. */
#define MINIMUM_CONSOLE_LOGLEVEL 1 /* Minimum loglevel we let people use */
* provides serialisation for access to the entire console
* driver system.
*/
-static DECLARE_MUTEX(console_sem);
-static DECLARE_MUTEX(secondary_console_sem);
+static DEFINE_SEMAPHORE(console_sem);
struct console *console_drivers;
+EXPORT_SYMBOL_GPL(console_drivers);
+
/*
* This is used for debugging the mess that is the VT code by
* keeping track if we have the console semaphore held. It's
/*
* logbuf_lock protects log_buf, log_start, log_end, con_start and logged_chars
* It is also used in interesting ways to provide interlocking in
- * release_console_sem().
+ * console_unlock();.
*/
static DEFINE_SPINLOCK(logbuf_lock);
static unsigned con_start; /* Index into log_buf: next char to be sent to consoles */
static unsigned log_end; /* Index into log_buf: most-recently-written-char + 1 */
+/*
+ * If exclusive_console is non-NULL then only this console is to be printed to.
+ */
+static struct console *exclusive_console;
+
/*
* Array of consoles built from command line options (console=)
*/
static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES];
static int selected_console = -1;
static int preferred_console = -1;
+int console_set_on_cmdline;
+EXPORT_SYMBOL(console_set_on_cmdline);
/* Flag: console code may call schedule() */
static int console_may_schedule;
static char *log_buf = __log_buf;
static int log_buf_len = __LOG_BUF_LEN;
static unsigned logged_chars; /* Number of chars produced since last read+clear operation */
+static int saved_console_loglevel = -1;
+#ifdef CONFIG_KEXEC
+/*
+ * This appends the listed symbols to /proc/vmcoreinfo
+ *
+ * /proc/vmcoreinfo is used by various utiilties, like crash and makedumpfile to
+ * obtain access to symbols that are otherwise very difficult to locate. These
+ * symbols are specifically used so that utilities can access and extract the
+ * dmesg log from a vmcore file after a crash.
+ */
+void log_buf_kexec_setup(void)
+{
+ VMCOREINFO_SYMBOL(log_buf);
+ VMCOREINFO_SYMBOL(log_end);
+ VMCOREINFO_SYMBOL(log_buf_len);
+ VMCOREINFO_SYMBOL(logged_chars);
+}
+#endif
+
+/* requested log_buf_len from kernel cmdline */
+static unsigned long __initdata new_log_buf_len;
+
+/* save requested log_buf_len since it's too early to process it */
static int __init log_buf_len_setup(char *str)
{
unsigned size = memparse(str, &str);
- unsigned long flags;
if (size)
size = roundup_pow_of_two(size);
- if (size > log_buf_len) {
- unsigned start, dest_idx, offset;
- char *new_log_buf;
+ if (size > log_buf_len)
+ new_log_buf_len = size;
- new_log_buf = alloc_bootmem(size);
- if (!new_log_buf) {
- printk(KERN_WARNING "log_buf_len: allocation failed\n");
- goto out;
- }
+ return 0;
+}
+early_param("log_buf_len", log_buf_len_setup);
- spin_lock_irqsave(&logbuf_lock, flags);
- log_buf_len = size;
- log_buf = new_log_buf;
-
- offset = start = min(con_start, log_start);
- dest_idx = 0;
- while (start != log_end) {
- log_buf[dest_idx] = __log_buf[start & (__LOG_BUF_LEN - 1)];
- start++;
- dest_idx++;
- }
- log_start -= offset;
- con_start -= offset;
- log_end -= offset;
- spin_unlock_irqrestore(&logbuf_lock, flags);
+void __init setup_log_buf(int early)
+{
+ unsigned long flags;
+ unsigned start, dest_idx, offset;
+ char *new_log_buf;
+ int free;
- printk(KERN_NOTICE "log_buf_len: %d\n", log_buf_len);
+ if (!new_log_buf_len)
+ return;
+
+ if (early) {
+ unsigned long mem;
+
+ mem = memblock_alloc(new_log_buf_len, PAGE_SIZE);
+ if (mem == MEMBLOCK_ERROR)
+ return;
+ new_log_buf = __va(mem);
+ } else {
+ new_log_buf = alloc_bootmem_nopanic(new_log_buf_len);
+ }
+
+ if (unlikely(!new_log_buf)) {
+ pr_err("log_buf_len: %ld bytes not available\n",
+ new_log_buf_len);
+ return;
}
-out:
- return 1;
-}
-__setup("log_buf_len=", log_buf_len_setup);
+ spin_lock_irqsave(&logbuf_lock, flags);
+ log_buf_len = new_log_buf_len;
+ log_buf = new_log_buf;
+ new_log_buf_len = 0;
+ free = __LOG_BUF_LEN - log_end;
+
+ offset = start = min(con_start, log_start);
+ dest_idx = 0;
+ while (start != log_end) {
+ unsigned log_idx_mask = start & (__LOG_BUF_LEN - 1);
+
+ log_buf[dest_idx] = __log_buf[log_idx_mask];
+ start++;
+ dest_idx++;
+ }
+ log_start -= offset;
+ con_start -= offset;
+ log_end -= offset;
+ spin_unlock_irqrestore(&logbuf_lock, flags);
+
+ pr_info("log_buf_len: %d\n", log_buf_len);
+ pr_info("early log buf free: %d(%d%%)\n",
+ free, (free * 100) / __LOG_BUF_LEN);
+}
#ifdef CONFIG_BOOT_PRINTK_DELAY
-static unsigned int boot_delay; /* msecs delay after each printk during bootup */
-static unsigned long long printk_delay_msec; /* per msec, based on boot_delay */
+static int boot_delay; /* msecs delay after each printk during bootup */
+static unsigned long long loops_per_msec; /* based on boot_delay */
static int __init boot_delay_setup(char *str)
{
unsigned long lpj;
- unsigned long long loops_per_msec;
lpj = preset_lpj ? preset_lpj : 1000000; /* some guess */
loops_per_msec = (unsigned long long)lpj / 1000 * HZ;
if (boot_delay > 10 * 1000)
boot_delay = 0;
- printk_delay_msec = loops_per_msec;
- printk(KERN_DEBUG "boot_delay: %u, preset_lpj: %ld, lpj: %lu, "
- "HZ: %d, printk_delay_msec: %llu\n",
- boot_delay, preset_lpj, lpj, HZ, printk_delay_msec);
+ pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, "
+ "HZ: %d, loops_per_msec: %llu\n",
+ boot_delay, preset_lpj, lpj, HZ, loops_per_msec);
return 1;
}
__setup("boot_delay=", boot_delay_setup);
if (boot_delay == 0 || system_state != SYSTEM_BOOTING)
return;
- k = (unsigned long long)printk_delay_msec * boot_delay;
+ k = (unsigned long long)loops_per_msec * boot_delay;
timeout = jiffies + msecs_to_jiffies(boot_delay);
while (k) {
}
#endif
-/*
- * Return the number of unread characters in the log buffer.
- */
-static int log_buf_get_len(void)
+#ifdef CONFIG_SECURITY_DMESG_RESTRICT
+int dmesg_restrict = 1;
+#else
+int dmesg_restrict;
+#endif
+
+static int syslog_action_restricted(int type)
{
- return logged_chars;
+ if (dmesg_restrict)
+ return 1;
+ /* Unless restricted, we allow "read all" and "get buffer size" for everybody */
+ return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER;
}
-/*
- * Copy a range of characters from the log buffer.
- */
-int log_buf_copy(char *dest, int idx, int len)
+static int check_syslog_permissions(int type, bool from_file)
{
- int ret, max;
- bool took_lock = false;
-
- if (!oops_in_progress) {
- spin_lock_irq(&logbuf_lock);
- took_lock = true;
- }
-
- max = log_buf_get_len();
- if (idx < 0 || idx >= max) {
- ret = -1;
- } else {
- if (len > max)
- len = max;
- ret = len;
- idx += (log_end - max);
- while (len-- > 0)
- dest[len] = LOG_BUF(idx + len);
+ /*
+ * If this is from /proc/kmsg and we've already opened it, then we've
+ * already done the capabilities checks at open time.
+ */
+ if (from_file && type != SYSLOG_ACTION_OPEN)
+ return 0;
+
+ if (syslog_action_restricted(type)) {
+ if (capable(CAP_SYSLOG))
+ return 0;
+ /* For historical reasons, accept CAP_SYS_ADMIN too, with a warning */
+ if (capable(CAP_SYS_ADMIN)) {
+ printk_once(KERN_WARNING "%s (%d): "
+ "Attempt to access syslog with CAP_SYS_ADMIN "
+ "but no CAP_SYSLOG (deprecated).\n",
+ current->comm, task_pid_nr(current));
+ return 0;
+ }
+ return -EPERM;
}
-
- if (took_lock)
- spin_unlock_irq(&logbuf_lock);
-
- return ret;
+ return 0;
}
-/*
- * Commands to do_syslog:
- *
- * 0 -- Close the log. Currently a NOP.
- * 1 -- Open the log. Currently a NOP.
- * 2 -- Read from the log.
- * 3 -- Read all messages remaining in the ring buffer.
- * 4 -- Read and clear all messages remaining in the ring buffer
- * 5 -- Clear ring buffer.
- * 6 -- Disable printk's to console
- * 7 -- Enable printk's to console
- * 8 -- Set level of messages printed to console
- * 9 -- Return number of unread characters in the log buffer
- * 10 -- Return size of the log buffer
- */
-int do_syslog(int type, char __user *buf, int len)
+int do_syslog(int type, char __user *buf, int len, bool from_file)
{
unsigned i, j, limit, count;
int do_clear = 0;
char c;
- int error = 0;
+ int error;
+
+ error = check_syslog_permissions(type, from_file);
+ if (error)
+ goto out;
error = security_syslog(type);
if (error)
return error;
switch (type) {
- case 0: /* Close log */
+ case SYSLOG_ACTION_CLOSE: /* Close log */
break;
- case 1: /* Open log */
+ case SYSLOG_ACTION_OPEN: /* Open log */
break;
- case 2: /* Read from log */
+ case SYSLOG_ACTION_READ: /* Read from log */
error = -EINVAL;
if (!buf || len < 0)
goto out;
if (!error)
error = i;
break;
- case 4: /* Read/clear last kernel messages */
+ /* Read/clear last kernel messages */
+ case SYSLOG_ACTION_READ_CLEAR:
do_clear = 1;
/* FALL THRU */
- case 3: /* Read last kernel messages */
+ /* Read last kernel messages */
+ case SYSLOG_ACTION_READ_ALL:
error = -EINVAL;
if (!buf || len < 0)
goto out;
}
}
break;
- case 5: /* Clear ring buffer */
+ /* Clear ring buffer */
+ case SYSLOG_ACTION_CLEAR:
logged_chars = 0;
break;
- case 6: /* Disable logging to console */
+ /* Disable logging to console */
+ case SYSLOG_ACTION_CONSOLE_OFF:
+ if (saved_console_loglevel == -1)
+ saved_console_loglevel = console_loglevel;
console_loglevel = minimum_console_loglevel;
break;
- case 7: /* Enable logging to console */
- console_loglevel = default_console_loglevel;
+ /* Enable logging to console */
+ case SYSLOG_ACTION_CONSOLE_ON:
+ if (saved_console_loglevel != -1) {
+ console_loglevel = saved_console_loglevel;
+ saved_console_loglevel = -1;
+ }
break;
- case 8: /* Set level of messages printed to console */
+ /* Set level of messages printed to console */
+ case SYSLOG_ACTION_CONSOLE_LEVEL:
error = -EINVAL;
if (len < 1 || len > 8)
goto out;
if (len < minimum_console_loglevel)
len = minimum_console_loglevel;
console_loglevel = len;
+ /* Implicitly re-enable logging to console */
+ saved_console_loglevel = -1;
error = 0;
break;
- case 9: /* Number of chars in the log buffer */
+ /* Number of chars in the log buffer */
+ case SYSLOG_ACTION_SIZE_UNREAD:
error = log_end - log_start;
break;
- case 10: /* Size of the log buffer */
+ /* Size of the log buffer */
+ case SYSLOG_ACTION_SIZE_BUFFER:
error = log_buf_len;
break;
default:
return error;
}
-asmlinkage long sys_syslog(int type, char __user *buf, int len)
+SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
{
- return do_syslog(type, buf, len);
+ return do_syslog(type, buf, len, SYSLOG_FROM_CALL);
}
+#ifdef CONFIG_KGDB_KDB
+/* kdb dmesg command needs access to the syslog buffer. do_syslog()
+ * uses locks so it cannot be used during debugging. Just tell kdb
+ * where the start and end of the physical and logical logs are. This
+ * is equivalent to do_syslog(3).
+ */
+void kdb_syslog_data(char *syslog_data[4])
+{
+ syslog_data[0] = log_buf;
+ syslog_data[1] = log_buf + log_buf_len;
+ syslog_data[2] = log_buf + log_end -
+ (logged_chars < log_buf_len ? logged_chars : log_buf_len);
+ syslog_data[3] = log_buf + log_end;
+}
+#endif /* CONFIG_KGDB_KDB */
+
/*
* Call the console drivers on a range of log_buf
*/
{
struct console *con;
- for (con = console_drivers; con; con = con->next) {
+ for_each_console(con) {
+ if (exclusive_console && con != exclusive_console)
+ continue;
if ((con->flags & CON_ENABLED) && con->write &&
(cpu_online(smp_processor_id()) ||
(con->flags & CON_ANYTIME)))
}
}
+/*
+ * Parse the syslog header <[0-9]*>. The decimal value represents 32bit, the
+ * lower 3 bit are the log level, the rest are the log facility. In case
+ * userspace passes usual userspace syslog messages to /dev/kmsg or
+ * /dev/ttyprintk, the log prefix might contain the facility. Printk needs
+ * to extract the correct log level for in-kernel processing, and not mangle
+ * the original value.
+ *
+ * If a prefix is found, the length of the prefix is returned. If 'level' is
+ * passed, it will be filled in with the log level without a possible facility
+ * value. If 'special' is passed, the special printk prefix chars are accepted
+ * and returned. If no valid header is found, 0 is returned and the passed
+ * variables are not touched.
+ */
+static size_t log_prefix(const char *p, unsigned int *level, char *special)
+{
+ unsigned int lev = 0;
+ char sp = '\0';
+ size_t len;
+
+ if (p[0] != '<' || !p[1])
+ return 0;
+ if (p[2] == '>') {
+ /* usual single digit level number or special char */
+ switch (p[1]) {
+ case '0' ... '7':
+ lev = p[1] - '0';
+ break;
+ case 'c': /* KERN_CONT */
+ case 'd': /* KERN_DEFAULT */
+ sp = p[1];
+ break;
+ default:
+ return 0;
+ }
+ len = 3;
+ } else {
+ /* multi digit including the level and facility number */
+ char *endp = NULL;
+
+ if (p[1] < '0' && p[1] > '9')
+ return 0;
+
+ lev = (simple_strtoul(&p[1], &endp, 10) & 7);
+ if (endp == NULL || endp[0] != '>')
+ return 0;
+ len = (endp + 1) - p;
+ }
+
+ /* do not accept special char if not asked for */
+ if (sp && !special)
+ return 0;
+
+ if (special) {
+ *special = sp;
+ /* return special char, do not touch level */
+ if (sp)
+ return len;
+ }
+
+ if (level)
+ *level = lev;
+ return len;
+}
+
/*
* Call the console drivers, asking them to write out
* log_buf[start] to log_buf[end - 1].
- * The console_sem must be held.
+ * The console_lock must be held.
*/
static void call_console_drivers(unsigned start, unsigned end)
{
cur_index = start;
start_print = start;
while (cur_index != end) {
- if (msg_level < 0 && ((end - cur_index) > 2) &&
- LOG_BUF(cur_index + 0) == '<' &&
- LOG_BUF(cur_index + 1) >= '0' &&
- LOG_BUF(cur_index + 1) <= '7' &&
- LOG_BUF(cur_index + 2) == '>') {
- msg_level = LOG_BUF(cur_index + 1) - '0';
- cur_index += 3;
+ if (msg_level < 0 && ((end - cur_index) > 2)) {
+ /* strip log prefix */
+ cur_index += log_prefix(&LOG_BUF(cur_index), &msg_level, NULL);
start_print = cur_index;
}
while (cur_index != end) {
/* If a crash is occurring, make sure we can't deadlock */
spin_lock_init(&logbuf_lock);
/* And make sure that we print immediately */
- init_MUTEX(&console_sem);
+ sema_init(&console_sem, 1);
}
#if defined(CONFIG_PRINTK_TIME)
{
struct console *con;
- for (con = console_drivers; con; con = con->next)
+ for_each_console(con)
if (con->flags & CON_ANYTIME)
return 1;
* @fmt: format string
*
* This is printk(). It can be called from any context. We want it to work.
- * Be aware of the fact that if oops_in_progress is not set, we might try to
- * wake klogd up which could deadlock on runqueue lock if printk() is called
- * from scheduler code.
*
- * We try to grab the console_sem. If we succeed, it's easy - we log the output and
+ * 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 release_console_sem() and will send it to the
- * consoles before releasing the semaphore.
+ * 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
*
* See also:
* printf(3)
+ *
+ * See the vsnprintf() documentation for format string extensions over C99.
*/
asmlinkage int printk(const char *fmt, ...)
va_list args;
int r;
+#ifdef CONFIG_KGDB_KDB
+ if (unlikely(kdb_trap_printk)) {
+ va_start(args, fmt);
+ r = vkdb_printf(fmt, args);
+ va_end(args);
+ return r;
+ }
+#endif
va_start(args, fmt);
r = vprintk(fmt, args);
va_end(args);
/*
* Try to get console ownership to actually show the kernel
* messages from a 'printk'. Return true (and with the
- * console_semaphore held, and 'console_locked' set) if it
+ * console_lock held, and 'console_locked' set) if it
* is successful, false otherwise.
*
* This gets called with the 'logbuf_lock' spinlock held and
* interrupts disabled. It should return with 'lockbuf_lock'
* released but interrupts still disabled.
*/
-static int acquire_console_semaphore_for_printk(unsigned int cpu)
+static int console_trylock_for_printk(unsigned int cpu)
+ __releases(&logbuf_lock)
{
- int retval = 0;
+ int retval = 0, wake = 0;
- if (!try_acquire_console_sem()) {
+ if (console_trylock()) {
retval = 1;
/*
*/
if (!can_use_console(cpu)) {
console_locked = 0;
- up(&console_sem);
+ wake = 1;
retval = 0;
}
}
printk_cpu = UINT_MAX;
spin_unlock(&logbuf_lock);
+ if (wake)
+ up(&console_sem);
return retval;
}
static const char recursion_bug_msg [] =
KERN_CRIT "BUG: recent printk recursion!\n";
static int recursion_bug;
- static int new_text_line = 1;
+static int new_text_line = 1;
static char printk_buf[1024];
+int printk_delay_msec __read_mostly;
+
+static inline void printk_delay(void)
+{
+ if (unlikely(printk_delay_msec)) {
+ int m = printk_delay_msec;
+
+ while (m--) {
+ mdelay(1);
+ touch_nmi_watchdog();
+ }
+ }
+}
+
asmlinkage int vprintk(const char *fmt, va_list args)
{
int printed_len = 0;
unsigned long flags;
int this_cpu;
char *p;
+ size_t plen;
+ char special;
boot_delay_msec();
+ printk_delay();
preempt_disable();
/* This stops the holder of console_sem just where we want him */
if (recursion_bug) {
recursion_bug = 0;
strcpy(printk_buf, recursion_bug_msg);
- printed_len = sizeof(recursion_bug_msg);
+ printed_len = strlen(recursion_bug_msg);
}
/* Emit the output into the temporary buffer */
printed_len += vscnprintf(printk_buf + printed_len,
sizeof(printk_buf) - printed_len, fmt, args);
+ p = printk_buf;
+
+ /* Read log level and handle special printk prefix */
+ plen = log_prefix(p, ¤t_log_level, &special);
+ if (plen) {
+ p += plen;
+
+ switch (special) {
+ case 'c': /* Strip <c> KERN_CONT, continue line */
+ plen = 0;
+ break;
+ case 'd': /* Strip <d> KERN_DEFAULT, start new line */
+ plen = 0;
+ default:
+ if (!new_text_line) {
+ emit_log_char('\n');
+ new_text_line = 1;
+ }
+ }
+ }
/*
- * Copy the output into log_buf. If the caller didn't provide
- * appropriate log level tags, we insert them here
+ * Copy the output into log_buf. If the caller didn't provide
+ * the appropriate log prefix, we insert them here
*/
- for (p = printk_buf; *p; p++) {
+ for (; *p; p++) {
if (new_text_line) {
- /* If a token, set current_log_level and skip over */
- if (p[0] == '<' && p[1] >= '0' && p[1] <= '7' &&
- p[2] == '>') {
- current_log_level = p[1] - '0';
- p += 3;
- printed_len -= 3;
- }
-
- /* Always output the token */
- emit_log_char('<');
- emit_log_char(current_log_level + '0');
- emit_log_char('>');
- printed_len += 3;
new_text_line = 0;
+ if (plen) {
+ /* Copy original log prefix */
+ int i;
+
+ for (i = 0; i < plen; i++)
+ emit_log_char(printk_buf[i]);
+ printed_len += plen;
+ } else {
+ /* Add log prefix */
+ emit_log_char('<');
+ emit_log_char(current_log_level + '0');
+ emit_log_char('>');
+ printed_len += 3;
+ }
+
if (printk_time) {
- /* Follow the token with the time */
+ /* Add the current time stamp */
char tbuf[50], *tp;
unsigned tlen;
unsigned long long t;
* actual magic (print out buffers, wake up klogd,
* etc).
*
- * The acquire_console_semaphore_for_printk() function
+ * The console_trylock_for_printk() function
* will release 'logbuf_lock' regardless of whether it
* actually gets the semaphore or not.
*/
- if (acquire_console_semaphore_for_printk(this_cpu))
- release_console_sem();
+ if (console_trylock_for_printk(this_cpu))
+ console_unlock();
lockdep_on();
out_restore_irqs:
#else
-asmlinkage long sys_syslog(int type, char __user *buf, int len)
-{
- return -ENOSYS;
-}
-
static void call_console_drivers(unsigned start, unsigned end)
{
}
*s = 0;
__add_preferred_console(buf, idx, options, brl_options);
+ console_set_on_cmdline = 1;
return 1;
}
__setup("console=", console_setup);
{
if (!console_suspend_enabled)
return;
- printk("Suspending console(s)\n");
- acquire_console_sem();
+ printk("Suspending console(s) (use no_console_suspend to debug)\n");
+ console_lock();
console_suspended = 1;
+ up(&console_sem);
}
void resume_console(void)
{
if (!console_suspend_enabled)
return;
+ down(&console_sem);
console_suspended = 0;
- release_console_sem();
+ console_unlock();
+}
+
+/**
+ * console_cpu_notify - print deferred console messages after CPU hotplug
+ * @self: notifier struct
+ * @action: CPU hotplug event
+ * @hcpu: unused
+ *
+ * If printk() is called from a CPU that is not online yet, the messages
+ * will be spooled but will not show up on the console. This function is
+ * called when a new CPU comes online (or fails to come up), and ensures
+ * that any such output gets printed.
+ */
+static int __cpuinit console_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ switch (action) {
+ case CPU_ONLINE:
+ case CPU_DEAD:
+ case CPU_DYING:
+ case CPU_DOWN_FAILED:
+ case CPU_UP_CANCELED:
+ console_lock();
+ console_unlock();
+ }
+ return NOTIFY_OK;
}
/**
- * acquire_console_sem - lock the console system for exclusive use.
+ * console_lock - lock the console system for exclusive use.
*
- * Acquires a semaphore which guarantees that the caller has
+ * Acquires a lock which guarantees that the caller has
* exclusive access to the console system and the console_drivers list.
*
* Can sleep, returns nothing.
*/
-void acquire_console_sem(void)
+void console_lock(void)
{
BUG_ON(in_interrupt());
- if (console_suspended) {
- down(&secondary_console_sem);
- return;
- }
down(&console_sem);
+ if (console_suspended)
+ return;
console_locked = 1;
console_may_schedule = 1;
}
-EXPORT_SYMBOL(acquire_console_sem);
+EXPORT_SYMBOL(console_lock);
-int try_acquire_console_sem(void)
+/**
+ * console_trylock - try to lock the console system for exclusive use.
+ *
+ * Tried to acquire a lock which guarantees that the caller has
+ * exclusive access to the console system and the console_drivers list.
+ *
+ * returns 1 on success, and 0 on failure to acquire the lock.
+ */
+int console_trylock(void)
{
if (down_trylock(&console_sem))
- return -1;
+ return 0;
+ if (console_suspended) {
+ up(&console_sem);
+ return 0;
+ }
console_locked = 1;
console_may_schedule = 0;
- return 0;
+ return 1;
}
-EXPORT_SYMBOL(try_acquire_console_sem);
+EXPORT_SYMBOL(console_trylock);
int is_console_locked(void)
{
return console_locked;
}
-void wake_up_klogd(void)
+static DEFINE_PER_CPU(int, printk_pending);
+
+void printk_tick(void)
{
- if (!oops_in_progress && waitqueue_active(&log_wait))
+ if (__this_cpu_read(printk_pending)) {
+ __this_cpu_write(printk_pending, 0);
wake_up_interruptible(&log_wait);
+ }
+}
+
+int printk_needs_cpu(int cpu)
+{
+ if (cpu_is_offline(cpu))
+ printk_tick();
+ return __this_cpu_read(printk_pending);
+}
+
+void wake_up_klogd(void)
+{
+ if (waitqueue_active(&log_wait))
+ this_cpu_write(printk_pending, 1);
}
/**
- * release_console_sem - unlock the console system
+ * console_unlock - unlock the console system
*
- * Releases the semaphore which the caller holds on the console system
+ * Releases the console_lock which the caller holds on the console system
* and the console driver list.
*
- * While the semaphore was held, console output may have been buffered
- * by printk(). If this is the case, release_console_sem() emits
- * the output prior to releasing the semaphore.
+ * While the console_lock was held, console output may have been buffered
+ * by printk(). If this is the case, console_unlock(); emits
+ * the output prior to releasing the lock.
*
* If there is output waiting for klogd, we wake it up.
*
- * release_console_sem() may be called from any context.
+ * console_unlock(); may be called from any context.
*/
-void release_console_sem(void)
+void console_unlock(void)
{
unsigned long flags;
unsigned _con_start, _log_end;
- unsigned wake_klogd = 0;
+ unsigned wake_klogd = 0, retry = 0;
if (console_suspended) {
- up(&secondary_console_sem);
+ up(&console_sem);
return;
}
console_may_schedule = 0;
+again:
for ( ; ; ) {
spin_lock_irqsave(&logbuf_lock, flags);
wake_klogd |= log_start - log_end;
_log_end = log_end;
con_start = log_end; /* Flush */
spin_unlock(&logbuf_lock);
+ stop_critical_timings(); /* don't trace print latency */
call_console_drivers(_con_start, _log_end);
+ start_critical_timings();
local_irq_restore(flags);
}
console_locked = 0;
+
+ /* Release the exclusive_console once it is used */
+ if (unlikely(exclusive_console))
+ exclusive_console = NULL;
+
+ spin_unlock(&logbuf_lock);
+
up(&console_sem);
+
+ /*
+ * Someone could have filled up the buffer again, so re-check if there's
+ * something to flush. In case we cannot trylock the console_sem again,
+ * there's a new owner and the console_unlock() from them will do the
+ * flush, no worries.
+ */
+ spin_lock(&logbuf_lock);
+ if (con_start != log_end)
+ retry = 1;
spin_unlock_irqrestore(&logbuf_lock, flags);
+ if (retry && console_trylock())
+ goto again;
+
if (wake_klogd)
wake_up_klogd();
}
-EXPORT_SYMBOL(release_console_sem);
+EXPORT_SYMBOL(console_unlock);
/**
* console_conditional_schedule - yield the CPU if required
* if this CPU should yield the CPU to another task, do
* so here.
*
- * Must be called within acquire_console_sem().
+ * Must be called within console_lock();.
*/
void __sched console_conditional_schedule(void)
{
}
EXPORT_SYMBOL(console_conditional_schedule);
-void console_print(const char *s)
-{
- printk(KERN_EMERG "%s", s);
-}
-EXPORT_SYMBOL(console_print);
-
void console_unblank(void)
{
struct console *c;
if (down_trylock(&console_sem) != 0)
return;
} else
- acquire_console_sem();
+ console_lock();
console_locked = 1;
console_may_schedule = 0;
- for (c = console_drivers; c != NULL; c = c->next)
+ for_each_console(c)
if ((c->flags & CON_ENABLED) && c->unblank)
c->unblank();
- release_console_sem();
+ console_unlock();
}
/*
struct console *c;
struct tty_driver *driver = NULL;
- acquire_console_sem();
- for (c = console_drivers; c != NULL; c = c->next) {
+ console_lock();
+ for_each_console(c) {
if (!c->device)
continue;
driver = c->device(c, index);
if (driver)
break;
}
- release_console_sem();
+ console_unlock();
return driver;
}
*/
void console_stop(struct console *console)
{
- acquire_console_sem();
+ console_lock();
console->flags &= ~CON_ENABLED;
- release_console_sem();
+ console_unlock();
}
EXPORT_SYMBOL(console_stop);
void console_start(struct console *console)
{
- acquire_console_sem();
+ console_lock();
console->flags |= CON_ENABLED;
- release_console_sem();
+ console_unlock();
}
EXPORT_SYMBOL(console_start);
+static int __read_mostly keep_bootcon;
+
+static int __init keep_bootcon_setup(char *str)
+{
+ keep_bootcon = 1;
+ printk(KERN_INFO "debug: skip boot console de-registration.\n");
+
+ return 0;
+}
+
+early_param("keep_bootcon", keep_bootcon_setup);
+
/*
* The console driver calls this routine during kernel initialization
* to register the console printing procedure with printk() and to
* print any messages that were printed by the kernel before the
* console driver was initialized.
+ *
+ * This can happen pretty early during the boot process (because of
+ * early_printk) - sometimes before setup_arch() completes - be careful
+ * of what kernel features are used - they may not be initialised yet.
+ *
+ * There are two types of consoles - bootconsoles (early_printk) and
+ * "real" consoles (everything which is not a bootconsole) which are
+ * handled differently.
+ * - Any number of bootconsoles can be registered at any time.
+ * - As soon as a "real" console is registered, all bootconsoles
+ * will be unregistered automatically.
+ * - Once a "real" console is registered, any attempt to register a
+ * bootconsoles will be rejected
*/
-void register_console(struct console *console)
+void register_console(struct console *newcon)
{
int i;
unsigned long flags;
- struct console *bootconsole = NULL;
+ struct console *bcon = NULL;
- if (console_drivers) {
- if (console->flags & CON_BOOT)
- return;
- if (console_drivers->flags & CON_BOOT)
- bootconsole = console_drivers;
+ /*
+ * before we register a new CON_BOOT console, make sure we don't
+ * already have a valid console
+ */
+ if (console_drivers && newcon->flags & CON_BOOT) {
+ /* find the last or real console */
+ for_each_console(bcon) {
+ if (!(bcon->flags & CON_BOOT)) {
+ printk(KERN_INFO "Too late to register bootconsole %s%d\n",
+ newcon->name, newcon->index);
+ return;
+ }
+ }
}
- if (preferred_console < 0 || bootconsole || !console_drivers)
+ if (console_drivers && console_drivers->flags & CON_BOOT)
+ bcon = console_drivers;
+
+ if (preferred_console < 0 || bcon || !console_drivers)
preferred_console = selected_console;
- if (console->early_setup)
- console->early_setup();
+ if (newcon->early_setup)
+ newcon->early_setup();
/*
* See if we want to use this console driver. If we
* that registers here.
*/
if (preferred_console < 0) {
- if (console->index < 0)
- console->index = 0;
- if (console->setup == NULL ||
- console->setup(console, NULL) == 0) {
- console->flags |= CON_ENABLED;
- if (console->device) {
- console->flags |= CON_CONSDEV;
+ if (newcon->index < 0)
+ newcon->index = 0;
+ if (newcon->setup == NULL ||
+ newcon->setup(newcon, NULL) == 0) {
+ newcon->flags |= CON_ENABLED;
+ if (newcon->device) {
+ newcon->flags |= CON_CONSDEV;
preferred_console = 0;
}
}
*/
for (i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0];
i++) {
- if (strcmp(console_cmdline[i].name, console->name) != 0)
+ if (strcmp(console_cmdline[i].name, newcon->name) != 0)
continue;
- if (console->index >= 0 &&
- console->index != console_cmdline[i].index)
+ if (newcon->index >= 0 &&
+ newcon->index != console_cmdline[i].index)
continue;
- if (console->index < 0)
- console->index = console_cmdline[i].index;
+ if (newcon->index < 0)
+ newcon->index = console_cmdline[i].index;
#ifdef CONFIG_A11Y_BRAILLE_CONSOLE
if (console_cmdline[i].brl_options) {
- console->flags |= CON_BRL;
- braille_register_console(console,
+ newcon->flags |= CON_BRL;
+ braille_register_console(newcon,
console_cmdline[i].index,
console_cmdline[i].options,
console_cmdline[i].brl_options);
return;
}
#endif
- if (console->setup &&
- console->setup(console, console_cmdline[i].options) != 0)
+ if (newcon->setup &&
+ newcon->setup(newcon, console_cmdline[i].options) != 0)
break;
- console->flags |= CON_ENABLED;
- console->index = console_cmdline[i].index;
+ newcon->flags |= CON_ENABLED;
+ newcon->index = console_cmdline[i].index;
if (i == selected_console) {
- console->flags |= CON_CONSDEV;
+ newcon->flags |= CON_CONSDEV;
preferred_console = selected_console;
}
break;
}
- if (!(console->flags & CON_ENABLED))
+ if (!(newcon->flags & CON_ENABLED))
return;
- if (bootconsole && (console->flags & CON_CONSDEV)) {
- printk(KERN_INFO "console handover: boot [%s%d] -> real [%s%d]\n",
- bootconsole->name, bootconsole->index,
- console->name, console->index);
- unregister_console(bootconsole);
- console->flags &= ~CON_PRINTBUFFER;
- } else {
- printk(KERN_INFO "console [%s%d] enabled\n",
- console->name, console->index);
- }
+ /*
+ * If we have a bootconsole, and are switching to a real console,
+ * don't print everything out again, since when the boot console, and
+ * the real console are the same physical device, it's annoying to
+ * see the beginning boot messages twice
+ */
+ if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV))
+ newcon->flags &= ~CON_PRINTBUFFER;
/*
* Put this console in the list - keep the
* preferred driver at the head of the list.
*/
- acquire_console_sem();
- if ((console->flags & CON_CONSDEV) || console_drivers == NULL) {
- console->next = console_drivers;
- console_drivers = console;
- if (console->next)
- console->next->flags &= ~CON_CONSDEV;
+ console_lock();
+ if ((newcon->flags & CON_CONSDEV) || console_drivers == NULL) {
+ newcon->next = console_drivers;
+ console_drivers = newcon;
+ if (newcon->next)
+ newcon->next->flags &= ~CON_CONSDEV;
} else {
- console->next = console_drivers->next;
- console_drivers->next = console;
+ newcon->next = console_drivers->next;
+ console_drivers->next = newcon;
}
- if (console->flags & CON_PRINTBUFFER) {
+ if (newcon->flags & CON_PRINTBUFFER) {
/*
- * release_console_sem() will print out the buffered messages
+ * console_unlock(); will print out the buffered messages
* for us.
*/
spin_lock_irqsave(&logbuf_lock, flags);
con_start = log_start;
spin_unlock_irqrestore(&logbuf_lock, flags);
+ /*
+ * We're about to replay the log buffer. Only do this to the
+ * just-registered console to avoid excessive message spam to
+ * the already-registered consoles.
+ */
+ exclusive_console = newcon;
+ }
+ console_unlock();
+ console_sysfs_notify();
+
+ /*
+ * By unregistering the bootconsoles after we enable the real console
+ * we get the "console xxx enabled" message on all the consoles -
+ * boot consoles, real consoles, etc - this is to ensure that end
+ * users know there might be something in the kernel's log buffer that
+ * went to the bootconsole (that they do not see on the real console)
+ */
+ if (bcon &&
+ ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) &&
+ !keep_bootcon) {
+ /* we need to iterate through twice, to make sure we print
+ * everything out, before we unregister the console(s)
+ */
+ printk(KERN_INFO "console [%s%d] enabled, bootconsole disabled\n",
+ newcon->name, newcon->index);
+ for_each_console(bcon)
+ if (bcon->flags & CON_BOOT)
+ unregister_console(bcon);
+ } else {
+ printk(KERN_INFO "%sconsole [%s%d] enabled\n",
+ (newcon->flags & CON_BOOT) ? "boot" : "" ,
+ newcon->name, newcon->index);
}
- release_console_sem();
}
EXPORT_SYMBOL(register_console);
return braille_unregister_console(console);
#endif
- acquire_console_sem();
+ console_lock();
if (console_drivers == console) {
console_drivers=console->next;
res = 0;
if (console_drivers != NULL && console->flags & CON_CONSDEV)
console_drivers->flags |= CON_CONSDEV;
- release_console_sem();
+ console_unlock();
+ console_sysfs_notify();
return res;
}
EXPORT_SYMBOL(unregister_console);
-static int __init disable_boot_consoles(void)
+static int __init printk_late_init(void)
{
- if (console_drivers != NULL) {
- if (console_drivers->flags & CON_BOOT) {
+ struct console *con;
+
+ for_each_console(con) {
+ if (!keep_bootcon && con->flags & CON_BOOT) {
printk(KERN_INFO "turn off boot console %s%d\n",
- console_drivers->name, console_drivers->index);
- return unregister_console(console_drivers);
+ con->name, con->index);
+ unregister_console(con);
}
}
+ hotcpu_notifier(console_cpu_notify, 0);
return 0;
}
-late_initcall(disable_boot_consoles);
-
-/**
- * tty_write_message - write a message to a certain tty, not just the console.
- * @tty: the destination tty_struct
- * @msg: the message to write
- *
- * This is used for messages that need to be redirected to a specific tty.
- * We don't put it into the syslog queue right now maybe in the future if
- * really needed.
- */
-void tty_write_message(struct tty_struct *tty, char *msg)
-{
- if (tty && tty->ops->write)
- tty->ops->write(tty, msg, strlen(msg));
- return;
-}
+late_initcall(printk_late_init);
#if defined CONFIG_PRINTK
+
/*
* printk rate limiting, lifted from the networking subsystem.
*
- * This enforces a rate limit: not more than one kernel message
- * every printk_ratelimit_jiffies to make a denial-of-service
- * attack impossible.
+ * This enforces a rate limit: not more than 10 kernel messages
+ * every 5s to make a denial-of-service attack impossible.
*/
-int __printk_ratelimit(int ratelimit_jiffies, int ratelimit_burst)
-{
- return __ratelimit(ratelimit_jiffies, ratelimit_burst);
-}
-EXPORT_SYMBOL(__printk_ratelimit);
+DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10);
-/* minimum time in jiffies between messages */
-int printk_ratelimit_jiffies = 5 * HZ;
-
-/* number of messages we send before ratelimiting */
-int printk_ratelimit_burst = 10;
-
-int printk_ratelimit(void)
+int __printk_ratelimit(const char *func)
{
- return __printk_ratelimit(printk_ratelimit_jiffies,
- printk_ratelimit_burst);
+ return ___ratelimit(&printk_ratelimit_state, func);
}
-EXPORT_SYMBOL(printk_ratelimit);
+EXPORT_SYMBOL(__printk_ratelimit);
/**
* printk_timed_ratelimit - caller-controlled printk ratelimiting
bool printk_timed_ratelimit(unsigned long *caller_jiffies,
unsigned int interval_msecs)
{
- if (*caller_jiffies == 0 || time_after(jiffies, *caller_jiffies)) {
- *caller_jiffies = jiffies + msecs_to_jiffies(interval_msecs);
+ if (*caller_jiffies == 0
+ || !time_in_range(jiffies, *caller_jiffies,
+ *caller_jiffies
+ + msecs_to_jiffies(interval_msecs))) {
+ *caller_jiffies = jiffies;
return true;
}
return false;
}
EXPORT_SYMBOL(printk_timed_ratelimit);
+
+static DEFINE_SPINLOCK(dump_list_lock);
+static LIST_HEAD(dump_list);
+
+/**
+ * kmsg_dump_register - register a kernel log dumper.
+ * @dumper: pointer to the kmsg_dumper structure
+ *
+ * Adds a kernel log dumper to the system. The dump callback in the
+ * structure will be called when the kernel oopses or panics and must be
+ * set. Returns zero on success and %-EINVAL or %-EBUSY otherwise.
+ */
+int kmsg_dump_register(struct kmsg_dumper *dumper)
+{
+ unsigned long flags;
+ int err = -EBUSY;
+
+ /* The dump callback needs to be set */
+ if (!dumper->dump)
+ return -EINVAL;
+
+ spin_lock_irqsave(&dump_list_lock, flags);
+ /* Don't allow registering multiple times */
+ if (!dumper->registered) {
+ dumper->registered = 1;
+ list_add_tail_rcu(&dumper->list, &dump_list);
+ err = 0;
+ }
+ spin_unlock_irqrestore(&dump_list_lock, flags);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(kmsg_dump_register);
+
+/**
+ * kmsg_dump_unregister - unregister a kmsg dumper.
+ * @dumper: pointer to the kmsg_dumper structure
+ *
+ * Removes a dump device from the system. Returns zero on success and
+ * %-EINVAL otherwise.
+ */
+int kmsg_dump_unregister(struct kmsg_dumper *dumper)
+{
+ unsigned long flags;
+ int err = -EINVAL;
+
+ spin_lock_irqsave(&dump_list_lock, flags);
+ if (dumper->registered) {
+ dumper->registered = 0;
+ list_del_rcu(&dumper->list);
+ err = 0;
+ }
+ spin_unlock_irqrestore(&dump_list_lock, flags);
+ synchronize_rcu();
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(kmsg_dump_unregister);
+
+/**
+ * kmsg_dump - dump kernel log to kernel message dumpers.
+ * @reason: the reason (oops, panic etc) for dumping
+ *
+ * Iterate through each of the dump devices and call the oops/panic
+ * callbacks with the log buffer.
+ */
+void kmsg_dump(enum kmsg_dump_reason reason)
+{
+ unsigned long end;
+ unsigned chars;
+ struct kmsg_dumper *dumper;
+ const char *s1, *s2;
+ unsigned long l1, l2;
+ unsigned long flags;
+
+ /* Theoretically, the log could move on after we do this, but
+ there's not a lot we can do about that. The new messages
+ will overwrite the start of what we dump. */
+ spin_lock_irqsave(&logbuf_lock, flags);
+ end = log_end & LOG_BUF_MASK;
+ chars = logged_chars;
+ spin_unlock_irqrestore(&logbuf_lock, flags);
+
+ if (chars > end) {
+ s1 = log_buf + log_buf_len - chars + end;
+ l1 = chars - end;
+
+ s2 = log_buf;
+ l2 = end;
+ } else {
+ s1 = "";
+ l1 = 0;
+
+ s2 = log_buf + end - chars;
+ l2 = chars;
+ }
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(dumper, &dump_list, list)
+ dumper->dump(dumper, reason, s1, l1, s2, l2);
+ rcu_read_unlock();
+}
#endif