kernel-ark/init/do_mounts.c
Chuck Lever 43717c7dae NFS: Retry mounting NFSROOT
Lukas Razik <linux@razik.name> reports that on his SPARC system,
booting with an NFS root file system stopped working after commit
56463e50 "NFS: Use super.c for NFSROOT mount option parsing."

We found that the network switch to which Lukas' client was attached
was delaying access to the LAN after the client's NIC driver reported
that its link was up.  The delay was longer than the timeouts used in
the NFS client during mounting.

NFSROOT worked for Lukas before commit 56463e50 because in those
kernels, the client's first operation was an rpcbind request to
determine which port the NFS server was listening on.  When that
request failed after a long timeout, the client simply selected the
default NFS port (2049).  By that time the switch was allowing access
to the LAN, and the mount succeeded.

Neither of these client behaviors is desirable, so reverting 56463e50
is really not a choice.  Instead, introduce a mechanism that retries
the NFSROOT mount request several times.  This is the same tactic that
normal user space NFS mounts employ to overcome server and network
delays.

Signed-off-by: Lukas Razik <linux@razik.name>
[ cel: match kernel coding style, add proper patch description ]
[ cel: add exponential back-off ]
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Lukas Razik <linux@razik.name>
Cc: stable@kernel.org # > 2.6.38
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2012-01-05 10:42:39 -05:00

559 lines
13 KiB
C

#include <linux/module.h>
#include <linux/sched.h>
#include <linux/ctype.h>
#include <linux/fd.h>
#include <linux/tty.h>
#include <linux/suspend.h>
#include <linux/root_dev.h>
#include <linux/security.h>
#include <linux/delay.h>
#include <linux/genhd.h>
#include <linux/mount.h>
#include <linux/device.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/initrd.h>
#include <linux/async.h>
#include <linux/fs_struct.h>
#include <linux/slab.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_fs_sb.h>
#include <linux/nfs_mount.h>
#include "do_mounts.h"
int __initdata rd_doload; /* 1 = load RAM disk, 0 = don't load */
int root_mountflags = MS_RDONLY | MS_SILENT;
static char * __initdata root_device_name;
static char __initdata saved_root_name[64];
static int root_wait;
dev_t ROOT_DEV;
static int __init load_ramdisk(char *str)
{
rd_doload = simple_strtol(str,NULL,0) & 3;
return 1;
}
__setup("load_ramdisk=", load_ramdisk);
static int __init readonly(char *str)
{
if (*str)
return 0;
root_mountflags |= MS_RDONLY;
return 1;
}
static int __init readwrite(char *str)
{
if (*str)
return 0;
root_mountflags &= ~MS_RDONLY;
return 1;
}
__setup("ro", readonly);
__setup("rw", readwrite);
#ifdef CONFIG_BLOCK
/**
* match_dev_by_uuid - callback for finding a partition using its uuid
* @dev: device passed in by the caller
* @data: opaque pointer to a 36 byte char array with a UUID
*
* Returns 1 if the device matches, and 0 otherwise.
*/
static int match_dev_by_uuid(struct device *dev, void *data)
{
u8 *uuid = data;
struct hd_struct *part = dev_to_part(dev);
if (!part->info)
goto no_match;
if (memcmp(uuid, part->info->uuid, sizeof(part->info->uuid)))
goto no_match;
return 1;
no_match:
return 0;
}
/**
* devt_from_partuuid - looks up the dev_t of a partition by its UUID
* @uuid: min 36 byte char array containing a hex ascii UUID
*
* The function will return the first partition which contains a matching
* UUID value in its partition_meta_info struct. This does not search
* by filesystem UUIDs.
*
* If @uuid is followed by a "/PARTNROFF=%d", then the number will be
* extracted and used as an offset from the partition identified by the UUID.
*
* Returns the matching dev_t on success or 0 on failure.
*/
static dev_t devt_from_partuuid(char *uuid_str)
{
dev_t res = 0;
struct device *dev = NULL;
u8 uuid[16];
struct gendisk *disk;
struct hd_struct *part;
int offset = 0;
if (strlen(uuid_str) < 36)
goto done;
/* Check for optional partition number offset attributes. */
if (uuid_str[36]) {
char c = 0;
/* Explicitly fail on poor PARTUUID syntax. */
if (sscanf(&uuid_str[36],
"/PARTNROFF=%d%c", &offset, &c) != 1) {
printk(KERN_ERR "VFS: PARTUUID= is invalid.\n"
"Expected PARTUUID=<valid-uuid-id>[/PARTNROFF=%%d]\n");
if (root_wait)
printk(KERN_ERR
"Disabling rootwait; root= is invalid.\n");
root_wait = 0;
goto done;
}
}
/* Pack the requested UUID in the expected format. */
part_pack_uuid(uuid_str, uuid);
dev = class_find_device(&block_class, NULL, uuid, &match_dev_by_uuid);
if (!dev)
goto done;
res = dev->devt;
/* Attempt to find the partition by offset. */
if (!offset)
goto no_offset;
res = 0;
disk = part_to_disk(dev_to_part(dev));
part = disk_get_part(disk, dev_to_part(dev)->partno + offset);
if (part) {
res = part_devt(part);
put_device(part_to_dev(part));
}
no_offset:
put_device(dev);
done:
return res;
}
#endif
/*
* Convert a name into device number. We accept the following variants:
*
* 1) device number in hexadecimal represents itself
* 2) /dev/nfs represents Root_NFS (0xff)
* 3) /dev/<disk_name> represents the device number of disk
* 4) /dev/<disk_name><decimal> represents the device number
* of partition - device number of disk plus the partition number
* 5) /dev/<disk_name>p<decimal> - same as the above, that form is
* used when disk name of partitioned disk ends on a digit.
* 6) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the
* unique id of a partition if the partition table provides it.
* 7) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to
* a partition with a known unique id.
*
* If name doesn't have fall into the categories above, we return (0,0).
* block_class is used to check if something is a disk name. If the disk
* name contains slashes, the device name has them replaced with
* bangs.
*/
dev_t name_to_dev_t(char *name)
{
char s[32];
char *p;
dev_t res = 0;
int part;
#ifdef CONFIG_BLOCK
if (strncmp(name, "PARTUUID=", 9) == 0) {
name += 9;
res = devt_from_partuuid(name);
if (!res)
goto fail;
goto done;
}
#endif
if (strncmp(name, "/dev/", 5) != 0) {
unsigned maj, min;
if (sscanf(name, "%u:%u", &maj, &min) == 2) {
res = MKDEV(maj, min);
if (maj != MAJOR(res) || min != MINOR(res))
goto fail;
} else {
res = new_decode_dev(simple_strtoul(name, &p, 16));
if (*p)
goto fail;
}
goto done;
}
name += 5;
res = Root_NFS;
if (strcmp(name, "nfs") == 0)
goto done;
res = Root_RAM0;
if (strcmp(name, "ram") == 0)
goto done;
if (strlen(name) > 31)
goto fail;
strcpy(s, name);
for (p = s; *p; p++)
if (*p == '/')
*p = '!';
res = blk_lookup_devt(s, 0);
if (res)
goto done;
/*
* try non-existent, but valid partition, which may only exist
* after revalidating the disk, like partitioned md devices
*/
while (p > s && isdigit(p[-1]))
p--;
if (p == s || !*p || *p == '0')
goto fail;
/* try disk name without <part number> */
part = simple_strtoul(p, NULL, 10);
*p = '\0';
res = blk_lookup_devt(s, part);
if (res)
goto done;
/* try disk name without p<part number> */
if (p < s + 2 || !isdigit(p[-2]) || p[-1] != 'p')
goto fail;
p[-1] = '\0';
res = blk_lookup_devt(s, part);
if (res)
goto done;
fail:
return 0;
done:
return res;
}
static int __init root_dev_setup(char *line)
{
strlcpy(saved_root_name, line, sizeof(saved_root_name));
return 1;
}
__setup("root=", root_dev_setup);
static int __init rootwait_setup(char *str)
{
if (*str)
return 0;
root_wait = 1;
return 1;
}
__setup("rootwait", rootwait_setup);
static char * __initdata root_mount_data;
static int __init root_data_setup(char *str)
{
root_mount_data = str;
return 1;
}
static char * __initdata root_fs_names;
static int __init fs_names_setup(char *str)
{
root_fs_names = str;
return 1;
}
static unsigned int __initdata root_delay;
static int __init root_delay_setup(char *str)
{
root_delay = simple_strtoul(str, NULL, 0);
return 1;
}
__setup("rootflags=", root_data_setup);
__setup("rootfstype=", fs_names_setup);
__setup("rootdelay=", root_delay_setup);
static void __init get_fs_names(char *page)
{
char *s = page;
if (root_fs_names) {
strcpy(page, root_fs_names);
while (*s++) {
if (s[-1] == ',')
s[-1] = '\0';
}
} else {
int len = get_filesystem_list(page);
char *p, *next;
page[len] = '\0';
for (p = page-1; p; p = next) {
next = strchr(++p, '\n');
if (*p++ != '\t')
continue;
while ((*s++ = *p++) != '\n')
;
s[-1] = '\0';
}
}
*s = '\0';
}
static int __init do_mount_root(char *name, char *fs, int flags, void *data)
{
int err = sys_mount(name, "/root", fs, flags, data);
if (err)
return err;
sys_chdir((const char __user __force *)"/root");
ROOT_DEV = current->fs->pwd.mnt->mnt_sb->s_dev;
printk(KERN_INFO
"VFS: Mounted root (%s filesystem)%s on device %u:%u.\n",
current->fs->pwd.mnt->mnt_sb->s_type->name,
current->fs->pwd.mnt->mnt_sb->s_flags & MS_RDONLY ?
" readonly" : "", MAJOR(ROOT_DEV), MINOR(ROOT_DEV));
return 0;
}
void __init mount_block_root(char *name, int flags)
{
char *fs_names = __getname_gfp(GFP_KERNEL
| __GFP_NOTRACK_FALSE_POSITIVE);
char *p;
#ifdef CONFIG_BLOCK
char b[BDEVNAME_SIZE];
#else
const char *b = name;
#endif
get_fs_names(fs_names);
retry:
for (p = fs_names; *p; p += strlen(p)+1) {
int err = do_mount_root(name, p, flags, root_mount_data);
switch (err) {
case 0:
goto out;
case -EACCES:
flags |= MS_RDONLY;
goto retry;
case -EINVAL:
continue;
}
/*
* Allow the user to distinguish between failed sys_open
* and bad superblock on root device.
* and give them a list of the available devices
*/
#ifdef CONFIG_BLOCK
__bdevname(ROOT_DEV, b);
#endif
printk("VFS: Cannot open root device \"%s\" or %s\n",
root_device_name, b);
printk("Please append a correct \"root=\" boot option; here are the available partitions:\n");
printk_all_partitions();
#ifdef CONFIG_DEBUG_BLOCK_EXT_DEVT
printk("DEBUG_BLOCK_EXT_DEVT is enabled, you need to specify "
"explicit textual name for \"root=\" boot option.\n");
#endif
panic("VFS: Unable to mount root fs on %s", b);
}
printk("List of all partitions:\n");
printk_all_partitions();
printk("No filesystem could mount root, tried: ");
for (p = fs_names; *p; p += strlen(p)+1)
printk(" %s", p);
printk("\n");
#ifdef CONFIG_BLOCK
__bdevname(ROOT_DEV, b);
#endif
panic("VFS: Unable to mount root fs on %s", b);
out:
putname(fs_names);
}
#ifdef CONFIG_ROOT_NFS
#define NFSROOT_TIMEOUT_MIN 5
#define NFSROOT_TIMEOUT_MAX 30
#define NFSROOT_RETRY_MAX 5
static int __init mount_nfs_root(void)
{
char *root_dev, *root_data;
unsigned int timeout;
int try, err;
err = nfs_root_data(&root_dev, &root_data);
if (err != 0)
return 0;
/*
* The server or network may not be ready, so try several
* times. Stop after a few tries in case the client wants
* to fall back to other boot methods.
*/
timeout = NFSROOT_TIMEOUT_MIN;
for (try = 1; ; try++) {
err = do_mount_root(root_dev, "nfs",
root_mountflags, root_data);
if (err == 0)
return 1;
if (try > NFSROOT_RETRY_MAX)
break;
/* Wait, in case the server refused us immediately */
ssleep(timeout);
timeout <<= 1;
if (timeout > NFSROOT_TIMEOUT_MAX)
timeout = NFSROOT_TIMEOUT_MAX;
}
return 0;
}
#endif
#if defined(CONFIG_BLK_DEV_RAM) || defined(CONFIG_BLK_DEV_FD)
void __init change_floppy(char *fmt, ...)
{
struct termios termios;
char buf[80];
char c;
int fd;
va_list args;
va_start(args, fmt);
vsprintf(buf, fmt, args);
va_end(args);
fd = sys_open("/dev/root", O_RDWR | O_NDELAY, 0);
if (fd >= 0) {
sys_ioctl(fd, FDEJECT, 0);
sys_close(fd);
}
printk(KERN_NOTICE "VFS: Insert %s and press ENTER\n", buf);
fd = sys_open("/dev/console", O_RDWR, 0);
if (fd >= 0) {
sys_ioctl(fd, TCGETS, (long)&termios);
termios.c_lflag &= ~ICANON;
sys_ioctl(fd, TCSETSF, (long)&termios);
sys_read(fd, &c, 1);
termios.c_lflag |= ICANON;
sys_ioctl(fd, TCSETSF, (long)&termios);
sys_close(fd);
}
}
#endif
void __init mount_root(void)
{
#ifdef CONFIG_ROOT_NFS
if (MAJOR(ROOT_DEV) == UNNAMED_MAJOR) {
if (mount_nfs_root())
return;
printk(KERN_ERR "VFS: Unable to mount root fs via NFS, trying floppy.\n");
ROOT_DEV = Root_FD0;
}
#endif
#ifdef CONFIG_BLK_DEV_FD
if (MAJOR(ROOT_DEV) == FLOPPY_MAJOR) {
/* rd_doload is 2 for a dual initrd/ramload setup */
if (rd_doload==2) {
if (rd_load_disk(1)) {
ROOT_DEV = Root_RAM1;
root_device_name = NULL;
}
} else
change_floppy("root floppy");
}
#endif
#ifdef CONFIG_BLOCK
create_dev("/dev/root", ROOT_DEV);
mount_block_root("/dev/root", root_mountflags);
#endif
}
/*
* Prepare the namespace - decide what/where to mount, load ramdisks, etc.
*/
void __init prepare_namespace(void)
{
int is_floppy;
if (root_delay) {
printk(KERN_INFO "Waiting %dsec before mounting root device...\n",
root_delay);
ssleep(root_delay);
}
/*
* wait for the known devices to complete their probing
*
* Note: this is a potential source of long boot delays.
* For example, it is not atypical to wait 5 seconds here
* for the touchpad of a laptop to initialize.
*/
wait_for_device_probe();
md_run_setup();
if (saved_root_name[0]) {
root_device_name = saved_root_name;
if (!strncmp(root_device_name, "mtd", 3) ||
!strncmp(root_device_name, "ubi", 3)) {
mount_block_root(root_device_name, root_mountflags);
goto out;
}
ROOT_DEV = name_to_dev_t(root_device_name);
if (strncmp(root_device_name, "/dev/", 5) == 0)
root_device_name += 5;
}
if (initrd_load())
goto out;
/* wait for any asynchronous scanning to complete */
if ((ROOT_DEV == 0) && root_wait) {
printk(KERN_INFO "Waiting for root device %s...\n",
saved_root_name);
while (driver_probe_done() != 0 ||
(ROOT_DEV = name_to_dev_t(saved_root_name)) == 0)
msleep(100);
async_synchronize_full();
}
is_floppy = MAJOR(ROOT_DEV) == FLOPPY_MAJOR;
if (is_floppy && rd_doload && rd_load_disk(0))
ROOT_DEV = Root_RAM0;
mount_root();
out:
devtmpfs_mount("dev");
sys_mount(".", "/", NULL, MS_MOVE, NULL);
sys_chroot((const char __user __force *)".");
}