printk: move to separate directory for easier modification

Make it easier to break up printk into bite-sized chunks.

Remove printk path/filename from comment.

Signed-off-by: Joe Perches <joe@perches.com>
Cc: Samuel Thibault <samuel.thibault@ens-lyon.org>
Cc: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 2925 insertions, 0 deletions

diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile
new file mode 100644
index 00000000000..36d306d9273
--- /dev/null
+++ b/kernel/printk/Makefile
@@ -0,0 +1 @@
+obj-y	= printk.o
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
new file mode 100644
index 00000000000..69b0890ed7e
--- /dev/null
+++ b/kernel/printk/printk.c
@@ -0,0 +1,2924 @@
+/*
+ *  linux/kernel/printk.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * Modified to make sys_syslog() more flexible: added commands to
+ * return the last 4k of kernel messages, regardless of whether
+ * they've been read or not.  Added option to suppress kernel printk's
+ * to the console.  Added hook for sending the console messages
+ * elsewhere, in preparation for a serial line console (someday).
+ * Ted Ts'o, 2/11/93.
+ * Modified for sysctl support, 1/8/97, Chris Horn.
+ * Fixed SMP synchronization, 08/08/99, Manfred Spraul
+ *     manfred@colorfullife.com
+ * Rewrote bits to get rid of console_lock
+ *	01Mar01 Andrew Morton
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/tty.h>
+#include <linux/tty_driver.h>
+#include <linux/console.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/nmi.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/interrupt.h>			/* For in_interrupt() */
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/security.h>
+#include <linux/bootmem.h>
+#include <linux/memblock.h>
+#include <linux/aio.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 <linux/poll.h>
+#include <linux/irq_work.h>
+#include <linux/utsname.h>
+
+#include <asm/uaccess.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/printk.h>
+
+/* printk's without a loglevel use this.. */
+#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 */
+#define DEFAULT_CONSOLE_LOGLEVEL 7 /* anything MORE serious than KERN_DEBUG */
+
+int console_printk[4] = {
+	DEFAULT_CONSOLE_LOGLEVEL,	/* console_loglevel */
+	DEFAULT_MESSAGE_LOGLEVEL,	/* default_message_loglevel */
+	MINIMUM_CONSOLE_LOGLEVEL,	/* minimum_console_loglevel */
+	DEFAULT_CONSOLE_LOGLEVEL,	/* default_console_loglevel */
+};
+
+/*
+ * Low level drivers may need that to know if they can schedule in
+ * their unblank() callback or not. So let's export it.
+ */
+int oops_in_progress;
+EXPORT_SYMBOL(oops_in_progress);
+
+/*
+ * console_sem protects the console_drivers list, and also
+ * provides serialisation for access to the entire console
+ * driver system.
+ */
+static DEFINE_SEMAPHORE(console_sem);
+struct console *console_drivers;
+EXPORT_SYMBOL_GPL(console_drivers);
+
+#ifdef CONFIG_LOCKDEP
+static struct lockdep_map console_lock_dep_map = {
+	.name = "console_lock"
+};
+#endif
+
+/*
+ * This is used for debugging the mess that is the VT code by
+ * keeping track if we have the console semaphore held. It's
+ * definitely not the perfect debug tool (we don't know if _WE_
+ * hold it are racing, but it helps tracking those weird code
+ * path in the console code where we end up in places I want
+ * locked without the console sempahore held
+ */
+static int console_locked, console_suspended;
+
+/*
+ * 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=)
+ */
+struct console_cmdline
+{
+	char	name[8];			/* Name of the driver	    */
+	int	index;				/* Minor dev. to use	    */
+	char	*options;			/* Options for the driver   */
+#ifdef CONFIG_A11Y_BRAILLE_CONSOLE
+	char	*brl_options;			/* Options for braille driver */
+#endif
+};
+
+#define MAX_CMDLINECONSOLES 8
+
+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;
+
+/*
+ * The printk log buffer consists of a chain of concatenated variable
+ * length records. Every record starts with a record header, containing
+ * the overall length of the record.
+ *
+ * The heads to the first and last entry in the buffer, as well as the
+ * sequence numbers of these both entries are maintained when messages
+ * are stored..
+ *
+ * If the heads indicate available messages, the length in the header
+ * tells the start next message. A length == 0 for the next message
+ * indicates a wrap-around to the beginning of the buffer.
+ *
+ * Every record carries the monotonic timestamp in microseconds, as well as
+ * the standard userspace syslog level and syslog facility. The usual
+ * kernel messages use LOG_KERN; userspace-injected messages always carry
+ * a matching syslog facility, by default LOG_USER. The origin of every
+ * message can be reliably determined that way.
+ *
+ * The human readable log message directly follows the message header. The
+ * length of the message text is stored in the header, the stored message
+ * is not terminated.
+ *
+ * Optionally, a message can carry a dictionary of properties (key/value pairs),
+ * to provide userspace with a machine-readable message context.
+ *
+ * Examples for well-defined, commonly used property names are:
+ *   DEVICE=b12:8               device identifier
+ *                                b12:8         block dev_t
+ *                                c127:3        char dev_t
+ *                                n8            netdev ifindex
+ *                                +sound:card0  subsystem:devname
+ *   SUBSYSTEM=pci              driver-core subsystem name
+ *
+ * Valid characters in property names are [a-zA-Z0-9.-_]. The plain text value
+ * follows directly after a '=' character. Every property is terminated by
+ * a '\0' character. The last property is not terminated.
+ *
+ * Example of a message structure:
+ *   0000  ff 8f 00 00 00 00 00 00      monotonic time in nsec
+ *   0008  34 00                        record is 52 bytes long
+ *   000a        0b 00                  text is 11 bytes long
+ *   000c              1f 00            dictionary is 23 bytes long
+ *   000e                    03 00      LOG_KERN (facility) LOG_ERR (level)
+ *   0010  69 74 27 73 20 61 20 6c      "it's a l"
+ *         69 6e 65                     "ine"
+ *   001b           44 45 56 49 43      "DEVIC"
+ *         45 3d 62 38 3a 32 00 44      "E=b8:2\0D"
+ *         52 49 56 45 52 3d 62 75      "RIVER=bu"
+ *         67                           "g"
+ *   0032     00 00 00                  padding to next message header
+ *
+ * The 'struct log' buffer header must never be directly exported to
+ * userspace, it is a kernel-private implementation detail that might
+ * need to be changed in the future, when the requirements change.
+ *
+ * /dev/kmsg exports the structured data in the following line format:
+ *   "level,sequnum,timestamp;<message text>\n"
+ *
+ * The optional key/value pairs are attached as continuation lines starting
+ * with a space character and terminated by a newline. All possible
+ * non-prinatable characters are escaped in the "\xff" notation.
+ *
+ * Users of the export format should ignore possible additional values
+ * separated by ',', and find the message after the ';' character.
+ */
+
+enum log_flags {
+	LOG_NOCONS	= 1,	/* already flushed, do not print to console */
+	LOG_NEWLINE	= 2,	/* text ended with a newline */
+	LOG_PREFIX	= 4,	/* text started with a prefix */
+	LOG_CONT	= 8,	/* text is a fragment of a continuation line */
+};
+
+struct log {
+	u64 ts_nsec;		/* timestamp in nanoseconds */
+	u16 len;		/* length of entire record */
+	u16 text_len;		/* length of text buffer */
+	u16 dict_len;		/* length of dictionary buffer */
+	u8 facility;		/* syslog facility */
+	u8 flags:5;		/* internal record flags */
+	u8 level:3;		/* syslog level */
+};
+
+/*
+ * The logbuf_lock protects kmsg buffer, indices, counters. It is also
+ * used in interesting ways to provide interlocking in console_unlock();
+ */
+static DEFINE_RAW_SPINLOCK(logbuf_lock);
+
+#ifdef CONFIG_PRINTK
+DECLARE_WAIT_QUEUE_HEAD(log_wait);
+/* the next printk record to read by syslog(READ) or /proc/kmsg */
+static u64 syslog_seq;
+static u32 syslog_idx;
+static enum log_flags syslog_prev;
+static size_t syslog_partial;
+
+/* index and sequence number of the first record stored in the buffer */
+static u64 log_first_seq;
+static u32 log_first_idx;
+
+/* index and sequence number of the next record to store in the buffer */
+static u64 log_next_seq;
+static u32 log_next_idx;
+
+/* the next printk record to write to the console */
+static u64 console_seq;
+static u32 console_idx;
+static enum log_flags console_prev;
+
+/* the next printk record to read after the last 'clear' command */
+static u64 clear_seq;
+static u32 clear_idx;
+
+#define PREFIX_MAX		32
+#define LOG_LINE_MAX		1024 - PREFIX_MAX
+
+/* record buffer */
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+#define LOG_ALIGN 4
+#else
+#define LOG_ALIGN __alignof__(struct log)
+#endif
+#define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
+static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
+static char *log_buf = __log_buf;
+static u32 log_buf_len = __LOG_BUF_LEN;
+
+/* cpu currently holding logbuf_lock */
+static volatile unsigned int logbuf_cpu = UINT_MAX;
+
+/* human readable text of the record */
+static char *log_text(const struct log *msg)
+{
+	return (char *)msg + sizeof(struct log);
+}
+
+/* optional key/value pair dictionary attached to the record */
+static char *log_dict(const struct log *msg)
+{
+	return (char *)msg + sizeof(struct log) + msg->text_len;
+}
+
+/* get record by index; idx must point to valid msg */
+static struct log *log_from_idx(u32 idx)
+{
+	struct log *msg = (struct log *)(log_buf + idx);
+
+	/*
+	 * A length == 0 record is the end of buffer marker. Wrap around and
+	 * read the message at the start of the buffer.
+	 */
+	if (!msg->len)
+		return (struct log *)log_buf;
+	return msg;
+}
+
+/* get next record; idx must point to valid msg */
+static u32 log_next(u32 idx)
+{
+	struct log *msg = (struct log *)(log_buf + idx);
+
+	/* length == 0 indicates the end of the buffer; wrap */
+	/*
+	 * A length == 0 record is the end of buffer marker. Wrap around and
+	 * read the message at the start of the buffer as *this* one, and
+	 * return the one after that.
+	 */
+	if (!msg->len) {
+		msg = (struct log *)log_buf;
+		return msg->len;
+	}
+	return idx + msg->len;
+}
+
+/* insert record into the buffer, discard old ones, update heads */
+static void log_store(int facility, int level,
+		      enum log_flags flags, u64 ts_nsec,
+		      const char *dict, u16 dict_len,
+		      const char *text, u16 text_len)
+{
+	struct log *msg;
+	u32 size, pad_len;
+
+	/* number of '\0' padding bytes to next message */
+	size = sizeof(struct log) + text_len + dict_len;
+	pad_len = (-size) & (LOG_ALIGN - 1);
+	size += pad_len;
+
+	while (log_first_seq < log_next_seq) {
+		u32 free;
+
+		if (log_next_idx > log_first_idx)
+			free = max(log_buf_len - log_next_idx, log_first_idx);
+		else
+			free = log_first_idx - log_next_idx;
+
+		if (free > size + sizeof(struct log))
+			break;
+
+		/* drop old messages until we have enough contiuous space */
+		log_first_idx = log_next(log_first_idx);
+		log_first_seq++;
+	}
+
+	if (log_next_idx + size + sizeof(struct log) >= log_buf_len) {
+		/*
+		 * This message + an additional empty header does not fit
+		 * at the end of the buffer. Add an empty header with len == 0
+		 * to signify a wrap around.
+		 */
+		memset(log_buf + log_next_idx, 0, sizeof(struct log));
+		log_next_idx = 0;
+	}
+
+	/* fill message */
+	msg = (struct log *)(log_buf + log_next_idx);
+	memcpy(log_text(msg), text, text_len);
+	msg->text_len = text_len;
+	memcpy(log_dict(msg), dict, dict_len);
+	msg->dict_len = dict_len;
+	msg->facility = facility;
+	msg->level = level & 7;
+	msg->flags = flags & 0x1f;
+	if (ts_nsec > 0)
+		msg->ts_nsec = ts_nsec;
+	else
+		msg->ts_nsec = local_clock();
+	memset(log_dict(msg) + dict_len, 0, pad_len);
+	msg->len = sizeof(struct log) + text_len + dict_len + pad_len;
+
+	/* insert message */
+	log_next_idx += msg->len;
+	log_next_seq++;
+}
+
+#ifdef CONFIG_SECURITY_DMESG_RESTRICT
+int dmesg_restrict = 1;
+#else
+int dmesg_restrict;
+#endif
+
+static int syslog_action_restricted(int type)
+{
+	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;
+}
+
+static int check_syslog_permissions(int type, bool from_file)
+{
+	/*
+	 * 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)) {
+			pr_warn_once("%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;
+	}
+	return security_syslog(type);
+}
+
+
+/* /dev/kmsg - userspace message inject/listen interface */
+struct devkmsg_user {
+	u64 seq;
+	u32 idx;
+	enum log_flags prev;
+	struct mutex lock;
+	char buf[8192];
+};
+
+static ssize_t devkmsg_writev(struct kiocb *iocb, const struct iovec *iv,
+			      unsigned long count, loff_t pos)
+{
+	char *buf, *line;
+	int i;
+	int level = default_message_loglevel;
+	int facility = 1;	/* LOG_USER */
+	size_t len = iov_length(iv, count);
+	ssize_t ret = len;
+
+	if (len > LOG_LINE_MAX)
+		return -EINVAL;
+	buf = kmalloc(len+1, GFP_KERNEL);
+	if (buf == NULL)
+		return -ENOMEM;
+
+	line = buf;
+	for (i = 0; i < count; i++) {
+		if (copy_from_user(line, iv[i].iov_base, iv[i].iov_len)) {
+			ret = -EFAULT;
+			goto out;
+		}
+		line += iv[i].iov_len;
+	}
+
+	/*
+	 * Extract and skip the syslog prefix <[0-9]*>. Coming from userspace
+	 * the decimal value represents 32bit, the lower 3 bit are the log
+	 * level, the rest are the log facility.
+	 *
+	 * If no prefix or no userspace facility is specified, we
+	 * enforce LOG_USER, to be able to reliably distinguish
+	 * kernel-generated messages from userspace-injected ones.
+	 */
+	line = buf;
+	if (line[0] == '<') {
+		char *endp = NULL;
+
+		i = simple_strtoul(line+1, &endp, 10);
+		if (endp && endp[0] == '>') {
+			level = i & 7;
+			if (i >> 3)
+				facility = i >> 3;
+			endp++;
+			len -= endp - line;
+			line = endp;
+		}
+	}
+	line[len] = '\0';
+
+	printk_emit(facility, level, NULL, 0, "%s", line);
+out:
+	kfree(buf);
+	return ret;
+}
+
+static ssize_t devkmsg_read(struct file *file, char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	struct devkmsg_user *user = file->private_data;
+	struct log *msg;
+	u64 ts_usec;
+	size_t i;
+	char cont = '-';
+	size_t len;
+	ssize_t ret;
+
+	if (!user)
+		return -EBADF;
+
+	ret = mutex_lock_interruptible(&user->lock);
+	if (ret)
+		return ret;
+	raw_spin_lock_irq(&logbuf_lock);
+	while (user->seq == log_next_seq) {
+		if (file->f_flags & O_NONBLOCK) {
+			ret = -EAGAIN;
+			raw_spin_unlock_irq(&logbuf_lock);
+			goto out;
+		}
+
+		raw_spin_unlock_irq(&logbuf_lock);
+		ret = wait_event_interruptible(log_wait,
+					       user->seq != log_next_seq);
+		if (ret)
+			goto out;
+		raw_spin_lock_irq(&logbuf_lock);
+	}
+
+	if (user->seq < log_first_seq) {
+		/* our last seen message is gone, return error and reset */
+		user->idx = log_first_idx;
+		user->seq = log_first_seq;
+		ret = -EPIPE;
+		raw_spin_unlock_irq(&logbuf_lock);
+		goto out;
+	}
+
+	msg = log_from_idx(user->idx);
+	ts_usec = msg->ts_nsec;
+	do_div(ts_usec, 1000);
+
+	/*
+	 * If we couldn't merge continuation line fragments during the print,
+	 * export the stored flags to allow an optional external merge of the
+	 * records. Merging the records isn't always neccessarily correct, like
+	 * when we hit a race during printing. In most cases though, it produces
+	 * better readable output. 'c' in the record flags mark the first
+	 * fragment of a line, '+' the following.
+	 */
+	if (msg->flags & LOG_CONT && !(user->prev & LOG_CONT))
+		cont = 'c';
+	else if ((msg->flags & LOG_CONT) ||
+		 ((user->prev & LOG_CONT) && !(msg->flags & LOG_PREFIX)))
+		cont = '+';
+
+	len = sprintf(user->buf, "%u,%llu,%llu,%c;",
+		      (msg->facility << 3) | msg->level,
+		      user->seq, ts_usec, cont);
+	user->prev = msg->flags;
+
+	/* escape non-printable characters */
+	for (i = 0; i < msg->text_len; i++) {
+		unsigned char c = log_text(msg)[i];
+
+		if (c < ' ' || c >= 127 || c == '\\')
+			len += sprintf(user->buf + len, "\\x%02x", c);
+		else
+			user->buf[len++] = c;
+	}
+	user->buf[len++] = '\n';
+
+	if (msg->dict_len) {
+		bool line = true;
+
+		for (i = 0; i < msg->dict_len; i++) {
+			unsigned char c = log_dict(msg)[i];
+
+			if (line) {
+				user->buf[len++] = ' ';
+				line = false;
+			}
+
+			if (c == '\0') {
+				user->buf[len++] = '\n';
+				line = true;
+				continue;
+			}
+
+			if (c < ' ' || c >= 127 || c == '\\') {
+				len += sprintf(user->buf + len, "\\x%02x", c);
+				continue;
+			}
+
+			user->buf[len++] = c;
+		}
+		user->buf[len++] = '\n';
+	}
+
+	user->idx = log_next(user->idx);
+	user->seq++;
+	raw_spin_unlock_irq(&logbuf_lock);
+
+	if (len > count) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (copy_to_user(buf, user->buf, len)) {
+		ret = -EFAULT;
+		goto out;
+	}
+	ret = len;
+out:
+	mutex_unlock(&user->lock);
+	return ret;
+}
+
+static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct devkmsg_user *user = file->private_data;
+	loff_t ret = 0;
+
+	if (!user)
+		return -EBADF;
+	if (offset)
+		return -ESPIPE;
+
+	raw_spin_lock_irq(&logbuf_lock);
+	switch (whence) {
+	case SEEK_SET:
+		/* the first record */
+		user->idx = log_first_idx;
+		user->seq = log_first_seq;
+		break;
+	case SEEK_DATA:
+		/*
+		 * The first record after the last SYSLOG_ACTION_CLEAR,
+		 * like issued by 'dmesg -c'. Reading /dev/kmsg itself
+		 * changes no global state, and does not clear anything.
+		 */
+		user->idx = clear_idx;
+		user->seq = clear_seq;
+		break;
+	case SEEK_END:
+		/* after the last record */
+		user->idx = log_next_idx;
+		user->seq = log_next_seq;
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	raw_spin_unlock_irq(&logbuf_lock);
+	return ret;
+}
+
+static unsigned int devkmsg_poll(struct file *file, poll_table *wait)
+{
+	struct devkmsg_user *user = file->private_data;
+	int ret = 0;
+
+	if (!user)
+		return POLLERR|POLLNVAL;
+
+	poll_wait(file, &log_wait, wait);
+
+	raw_spin_lock_irq(&logbuf_lock);
+	if (user->seq < log_next_seq) {
+		/* return error when data has vanished underneath us */
+		if (user->seq < log_first_seq)
+			ret = POLLIN|POLLRDNORM|POLLERR|POLLPRI;
+		else
+			ret = POLLIN|POLLRDNORM;
+	}
+	raw_spin_unlock_irq(&logbuf_lock);
+
+	return ret;
+}
+
+static int devkmsg_open(struct inode *inode, struct file *file)
+{
+	struct devkmsg_user *user;
+	int err;
+
+	/* write-only does not need any file context */
+	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
+		return 0;
+
+	err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
+				       SYSLOG_FROM_READER);
+	if (err)
+		return err;
+
+	user = kmalloc(sizeof(struct devkmsg_user), GFP_KERNEL);
+	if (!user)
+		return -ENOMEM;
+
+	mutex_init(&user->lock);
+
+	raw_spin_lock_irq(&logbuf_lock);
+	user->idx = log_first_idx;
+	user->seq = log_first_seq;
+	raw_spin_unlock_irq(&logbuf_lock);
+
+	file->private_data = user;
+	return 0;
+}
+
+static int devkmsg_release(struct inode *inode, struct file *file)
+{
+	struct devkmsg_user *user = file->private_data;
+
+	if (!user)
+		return 0;
+
+	mutex_destroy(&user->lock);
+	kfree(user);
+	return 0;
+}
+
+const struct file_operations kmsg_fops = {
+	.open = devkmsg_open,
+	.read = devkmsg_read,
+	.aio_write = devkmsg_writev,
+	.llseek = devkmsg_llseek,
+	.poll = devkmsg_poll,
+	.release = devkmsg_release,
+};
+
+#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_buf_len);
+	VMCOREINFO_SYMBOL(log_first_idx);
+	VMCOREINFO_SYMBOL(log_next_idx);
+	/*
+	 * Export struct log size and field offsets. User space tools can
+	 * parse it and detect any changes to structure down the line.
+	 */
+	VMCOREINFO_STRUCT_SIZE(log);
+	VMCOREINFO_OFFSET(log, ts_nsec);
+	VMCOREINFO_OFFSET(log, len);
+	VMCOREINFO_OFFSET(log, text_len);
+	VMCOREINFO_OFFSET(log, dict_len);
+}
+#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);
+
+	if (size)
+		size = roundup_pow_of_two(size);
+	if (size > log_buf_len)
+		new_log_buf_len = size;
+
+	return 0;
+}
+early_param("log_buf_len", log_buf_len_setup);
+
+void __init setup_log_buf(int early)
+{
+	unsigned long flags;
+	char *new_log_buf;
+	int free;
+
+	if (!new_log_buf_len)
+		return;
+
+	if (early) {
+		unsigned long mem;
+
+		mem = memblock_alloc(new_log_buf_len, PAGE_SIZE);
+		if (!mem)
+			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;
+	}
+
+	raw_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_next_idx;
+	memcpy(log_buf, __log_buf, __LOG_BUF_LEN);
+	raw_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);
+}
+
+static bool __read_mostly ignore_loglevel;
+
+static int __init ignore_loglevel_setup(char *str)
+{
+	ignore_loglevel = 1;
+	printk(KERN_INFO "debug: ignoring loglevel setting.\n");
+
+	return 0;
+}
+
+early_param("ignore_loglevel", ignore_loglevel_setup);
+module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting, to"
+	"print all kernel messages to the console.");
+
+#ifdef CONFIG_BOOT_PRINTK_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;
+
+	lpj = preset_lpj ? preset_lpj : 1000000;	/* some guess */
+	loops_per_msec = (unsigned long long)lpj / 1000 * HZ;
+
+	get_option(&str, &boot_delay);
+	if (boot_delay > 10 * 1000)
+		boot_delay = 0;
+
+	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);
+
+static void boot_delay_msec(int level)
+{
+	unsigned long long k;
+	unsigned long timeout;
+
+	if ((boot_delay == 0 || system_state != SYSTEM_BOOTING)
+		|| (level >= console_loglevel && !ignore_loglevel)) {
+		return;
+	}
+
+	k = (unsigned long long)loops_per_msec * boot_delay;
+
+	timeout = jiffies + msecs_to_jiffies(boot_delay);
+	while (k) {
+		k--;
+		cpu_relax();
+		/*
+		 * use (volatile) jiffies to prevent
+		 * compiler reduction; loop termination via jiffies
+		 * is secondary and may or may not happen.
+		 */
+		if (time_after(jiffies, timeout))
+			break;
+		touch_nmi_watchdog();
+	}
+}
+#else
+static inline void boot_delay_msec(int level)
+{
+}
+#endif
+
+#if defined(CONFIG_PRINTK_TIME)
+static bool printk_time = 1;
+#else
+static bool printk_time;
+#endif
+module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR);
+
+static size_t print_time(u64 ts, char *buf)
+{
+	unsigned long rem_nsec;
+
+	if (!printk_time)
+		return 0;
+
+	rem_nsec = do_div(ts, 1000000000);
+
+	if (!buf)
+		return snprintf(NULL, 0, "[%5lu.000000] ", (unsigned long)ts);
+
+	return sprintf(buf, "[%5lu.%06lu] ",
+		       (unsigned long)ts, rem_nsec / 1000);
+}
+
+static size_t print_prefix(const struct log *msg, bool syslog, char *buf)
+{
+	size_t len = 0;
+	unsigned int prefix = (msg->facility << 3) | msg->level;
+
+	if (syslog) {
+		if (buf) {
+			len += sprintf(buf, "<%u>", prefix);
+		} else {
+			len += 3;
+			if (prefix > 999)
+				len += 3;
+			else if (prefix > 99)
+				len += 2;
+			else if (prefix > 9)
+				len++;
+		}
+	}
+
+	len += print_time(msg->ts_nsec, buf ? buf + len : NULL);
+	return len;
+}
+
+static size_t msg_print_text(const struct log *msg, enum log_flags prev,
+			     bool syslog, char *buf, size_t size)
+{
+	const char *text = log_text(msg);
+	size_t text_size = msg->text_len;
+	bool prefix = true;
+	bool newline = true;
+	size_t len = 0;
+
+	if ((prev & LOG_CONT) && !(msg->flags & LOG_PREFIX))
+		prefix = false;
+
+	if (msg->flags & LOG_CONT) {
+		if ((prev & LOG_CONT) && !(prev & LOG_NEWLINE))
+			prefix = false;
+
+		if (!(msg->flags & LOG_NEWLINE))
+			newline = false;
+	}
+
+	do {
+		const char *next = memchr(text, '\n', text_size);
+		size_t text_len;
+
+		if (next) {
+			text_len = next - text;
+			next++;
+			text_size -= next - text;
+		} else {
+			text_len = text_size;
+		}
+
+		if (buf) {
+			if (print_prefix(msg, syslog, NULL) +
+			    text_len + 1 >= size - len)
+				break;
+
+			if (prefix)
+				len += print_prefix(msg, syslog, buf + len);
+			memcpy(buf + len, text, text_len);
+			len += text_len;
+			if (next || newline)
+				buf[len++] = '\n';
+		} else {
+			/* SYSLOG_ACTION_* buffer size only calculation */
+			if (prefix)
+				len += print_prefix(msg, syslog, NULL);
+			len += text_len;
+			if (next || newline)
+				len++;
+		}
+
+		prefix = true;
+		text = next;
+	} while (text);
+
+	return len;
+}
+
+static int syslog_print(char __user *buf, int size)
+{
+	char *text;
+	struct log *msg;
+	int len = 0;
+
+	text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL);
+	if (!text)
+		return -ENOMEM;
+
+	while (size > 0) {
+		size_t n;
+		size_t skip;
+
+		raw_spin_lock_irq(&logbuf_lock);
+		if (syslog_seq < log_first_seq) {
+			/* messages are gone, move to first one */
+			syslog_seq = log_first_seq;
+			syslog_idx = log_first_idx;
+			syslog_prev = 0;
+			syslog_partial = 0;
+		}
+		if (syslog_seq == log_next_seq) {
+			raw_spin_unlock_irq(&logbuf_lock);
+			break;
+		}
+
+		skip = syslog_partial;
+		msg = log_from_idx(syslog_idx);
+		n = msg_print_text(msg, syslog_prev, true, text,
+				   LOG_LINE_MAX + PREFIX_MAX);
+		if (n - syslog_partial <= size) {
+			/* message fits into buffer, move forward */
+			syslog_idx = log_next(syslog_idx);
+			syslog_seq++;
+			syslog_prev = msg->flags;
+			n -= syslog_partial;
+			syslog_partial = 0;
+		} else if (!len){
+			/* partial read(), remember position */
+			n = size;
+			syslog_partial += n;
+		} else
+			n = 0;
+		raw_spin_unlock_irq(&logbuf_lock);
+
+		if (!n)
+			break;
+
+		if (copy_to_user(buf, text + skip, n)) {
+			if (!len)
+				len = -EFAULT;
+			break;
+		}
+
+		len += n;
+		size -= n;
+		buf += n;
+	}
+
+	kfree(text);
+	return len;
+}
+
+static int syslog_print_all(char __user *buf, int size, bool clear)
+{
+	char *text;
+	int len = 0;
+
+	text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL);
+	if (!text)
+		return -ENOMEM;
+
+	raw_spin_lock_irq(&logbuf_lock);
+	if (buf) {
+		u64 next_seq;
+		u64 seq;
+		u32 idx;
+		enum log_flags prev;
+
+		if (clear_seq < log_first_seq) {
+			/* messages are gone, move to first available one */
+			clear_seq = log_first_seq;
+			clear_idx = log_first_idx;
+		}
+
+		/*
+		 * Find first record that fits, including all following records,
+		 * into the user-provided buffer for this dump.
+		 */
+		seq = clear_seq;
+		idx = clear_idx;
+		prev = 0;
+		while (seq < log_next_seq) {
+			struct log *msg = log_from_idx(idx);
+
+			len += msg_print_text(msg, prev, true, NULL, 0);
+			prev = msg->flags;
+			idx = log_next(idx);
+			seq++;
+		}
+
+		/* move first record forward until length fits into the buffer */
+		seq = clear_seq;
+		idx = clear_idx;
+		prev = 0;
+		while (len > size && seq < log_next_seq) {
+			struct log *msg = log_from_idx(idx);
+
+			len -= msg_print_text(msg, prev, true, NULL, 0);
+			prev = msg->flags;
+			idx = log_next(idx);
+			seq++;
+		}
+
+		/* last message fitting into this dump */
+		next_seq = log_next_seq;
+
+		len = 0;
+		prev = 0;
+		while (len >= 0 && seq < next_seq) {
+			struct log *msg = log_from_idx(idx);
+			int textlen;
+
+			textlen = msg_print_text(msg, prev, true, text,
+						 LOG_LINE_MAX + PREFIX_MAX);
+			if (textlen < 0) {
+				len = textlen;
+				break;
+			}
+			idx = log_next(idx);
+			seq++;
+			prev = msg->flags;
+
+			raw_spin_unlock_irq(&logbuf_lock);
+			if (copy_to_user(buf + len, text, textlen))
+				len = -EFAULT;
+			else
+				len += textlen;
+			raw_spin_lock_irq(&logbuf_lock);
+
+			if (seq < log_first_seq) {
+				/* messages are gone, move to next one */
+				seq = log_first_seq;
+				idx = log_first_idx;
+				prev = 0;
+			}
+		}
+	}
+
+	if (clear) {
+		clear_seq = log_next_seq;
+		clear_idx = log_next_idx;
+	}
+	raw_spin_unlock_irq(&logbuf_lock);
+
+	kfree(text);
+	return len;
+}
+
+int do_syslog(int type, char __user *buf, int len, bool from_file)
+{
+	bool clear = false;
+	static int saved_console_loglevel = -1;
+	int error;
+
+	error = check_syslog_permissions(type, from_file);
+	if (error)
+		goto out;
+
+	error = security_syslog(type);
+	if (error)
+		return error;
+
+	switch (type) {
+	case SYSLOG_ACTION_CLOSE:	/* Close log */
+		break;
+	case SYSLOG_ACTION_OPEN:	/* Open log */
+		break;
+	case SYSLOG_ACTION_READ:	/* Read from log */
+		error = -EINVAL;
+		if (!buf || len < 0)
+			goto out;
+		error = 0;
+		if (!len)
+			goto out;
+		if (!access_ok(VERIFY_WRITE, buf, len)) {
+			error = -EFAULT;
+			goto out;
+		}
+		error = wait_event_interruptible(log_wait,
+						 syslog_seq != log_next_seq);
+		if (error)
+			goto out;
+		error = syslog_print(buf, len);
+		break;
+	/* Read/clear last kernel messages */
+	case SYSLOG_ACTION_READ_CLEAR:
+		clear = true;
+		/* FALL THRU */
+	/* Read last kernel messages */
+	case SYSLOG_ACTION_READ_ALL:
+		error = -EINVAL;
+		if (!buf || len < 0)
+			goto out;
+		error = 0;
+		if (!len)
+			goto out;
+		if (!access_ok(VERIFY_WRITE, buf, len)) {