kmsg: export printk records to the /dev/kmsg interface

Support for multiple concurrent readers of /dev/kmsg, with read(),
seek(), poll() support. Output of message sequence numbers, to allow
userspace log consumers to reliably reconnect and reconstruct their
state at any given time. After open("/dev/kmsg"), read() always
returns *all* buffered records. If only future messages should be
read, SEEK_END can be used. In case records get overwritten while
/dev/kmsg is held open, or records get faster overwritten than they
are read, the next read() will return -EPIPE and the current reading
position gets updated to the next available record. The passed
sequence numbers allow the log consumer to calculate the amount of
lost messages.

  [root@mop ~]# cat /dev/kmsg
  5,0,0;Linux version 3.4.0-rc1+ (kay@mop) (gcc version 4.7.0 20120315 ...
  6,159,423091;ACPI: PCI Root Bridge [PCI0] (domain 0000 [bus 00-ff])
  7,160,424069;pci_root PNP0A03:00: host bridge window [io  0x0000-0x0cf7] (ignored)
   SUBSYSTEM=acpi
   DEVICE=+acpi:PNP0A03:00
  6,339,5140900;NET: Registered protocol family 10
  30,340,5690716;udevd[80]: starting version 181
  6,341,6081421;FDC 0 is a S82078B
  6,345,6154686;microcode: CPU0 sig=0x623, pf=0x0, revision=0x0
  7,346,6156968;sr 1:0:0:0: Attached scsi CD-ROM sr0
   SUBSYSTEM=scsi
   DEVICE=+scsi:1:0:0:0
  6,347,6289375;microcode: CPU1 sig=0x623, pf=0x0, revision=0x0

Cc: Karel Zak <kzak@redhat.com>
Tested-by: William Douglas <william.douglas@intel.com>
Signed-off-by: Kay Sievers <kay@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/char/mem.c

@@ -807,65 +807,6 @@ static const struct file_operations oldmem_fops = {
 };
 #endif
 
-static ssize_t kmsg_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 > 1024)
-		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))
-			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 const struct file_operations kmsg_fops = {
-	.aio_write = kmsg_writev,
-	.llseek = noop_llseek,
-};
-
 static const struct memdev {
 	const char *name;
 	umode_t mode;
@@ -884,7 +825,7 @@ static const struct memdev {
 	 [7] = { "full", 0666, &full_fops, NULL },
 	 [8] = { "random", 0666, &random_fops, NULL },
 	 [9] = { "urandom", 0666, &urandom_fops, NULL },
-	[11] = { "kmsg", 0, &kmsg_fops, NULL },
+	[11] = { "kmsg", 0644, &kmsg_fops, NULL },
 #ifdef CONFIG_CRASH_DUMP
 	[12] = { "oldmem", 0, &oldmem_fops, NULL },
 #endif

include/linux/printk.h

@@ -300,6 +300,8 @@ extern void dump_stack(void) __cold;
 	no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
 #endif
 
+extern const struct file_operations kmsg_fops;
+
 enum {
 	DUMP_PREFIX_NONE,
 	DUMP_PREFIX_ADDRESS,