linux/init/do_mounts.c

474 lines
10 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
#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/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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/ramfs.h>
#include <linux/shmem_fs.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_fs_sb.h>
#include <linux/nfs_mount.h>
#include <linux/raid/detect.h>
#include <uapi/linux/mount.h>
#include "do_mounts.h"
int root_mountflags = MS_RDONLY | MS_SILENT;
static char __initdata saved_root_name[64];
init: add root=PARTUUID=UUID/PARTNROFF=%d support Expand root=PARTUUID=UUID syntax to support selecting a root partition by integer offset from a known, unique partition. This approach provides similar properties to specifying a device and partition number, but using the UUID as the unique path prior to evaluating the offset. For example, root=PARTUUID=99DE9194-FC15-4223-9192-FC243948F88B/PARTNROFF=1 selects the partition with UUID 99DE.. then select the next partition. This change is motivated by a particular usecase in Chromium OS where the bootloader can easily determine what partition it is on (by UUID) but doesn't perform general partition table walking. That said, support for this model provides a direct mechanism for the user to modify the root partition to boot without specifically needing to extract each UUID or update the bootloader explicitly when the root partition UUID is changed (if it is recreated to be larger, for instance). Pinning to a /boot-style partition UUID allows the arbitrary root partition reconfiguration/modifications with slightly less ambiguity than just [dev][partition] and less stringency than the specific root partition UUID. [sfr@canb.auug.org.au: fix init sections warning] Signed-off-by: Will Drewry <wad@chromium.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Randy Dunlap <rdunlap@xenotime.net> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-03 04:38:59 +08:00
static int root_wait;
dev_t ROOT_DEV;
static int __init load_ramdisk(char *str)
{
pr_warn("ignoring the deprecated load_ramdisk= option\n");
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);
static int __init root_dev_setup(char *line)
{
strscpy(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);
init/do_mounts.c: Harden split_fs_names() against buffer overflow split_fs_names() currently takes comma separate list of filesystems and converts it into individual filesystem strings. Pleaces these strings in the input buffer passed by caller and returns number of strings. If caller manages to pass input string bigger than buffer, then we can write beyond the buffer. Or if string just fits buffer, we will still write beyond the buffer as we append a '\0' byte at the end. Pass size of input buffer to split_fs_names() and put enough checks in place so such buffer overrun possibilities do not occur. This patch does few things. - Add a parameter "size" to split_fs_names(). This specifies size of input buffer. - Use strlcpy() (instead of strcpy()) so that we can't go beyond buffer size. If input string "names" is larger than passed in buffer, input string will be truncated to fit in buffer. - Stop appending extra '\0' character at the end and avoid one possibility of going beyond the input buffer size. - Do not use extra loop to count number of strings. - Previously if one passed "rootfstype=foo,,bar", split_fs_names() will return only 1 string "foo" (and "bar" will be truncated due to extra ,). After this patch, now split_fs_names() will return 3 strings ("foo", zero-sized-string, and "bar"). Callers of split_fs_names() have been modified to check for zero sized string and skip to next one. Reported-by: xu xin <xu.xin16@zte.com.cn> Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2021-09-17 21:13:23 +08:00
/* This can return zero length strings. Caller should check */
static int __init split_fs_names(char *page, size_t size)
{
init/do_mounts.c: Harden split_fs_names() against buffer overflow split_fs_names() currently takes comma separate list of filesystems and converts it into individual filesystem strings. Pleaces these strings in the input buffer passed by caller and returns number of strings. If caller manages to pass input string bigger than buffer, then we can write beyond the buffer. Or if string just fits buffer, we will still write beyond the buffer as we append a '\0' byte at the end. Pass size of input buffer to split_fs_names() and put enough checks in place so such buffer overrun possibilities do not occur. This patch does few things. - Add a parameter "size" to split_fs_names(). This specifies size of input buffer. - Use strlcpy() (instead of strcpy()) so that we can't go beyond buffer size. If input string "names" is larger than passed in buffer, input string will be truncated to fit in buffer. - Stop appending extra '\0' character at the end and avoid one possibility of going beyond the input buffer size. - Do not use extra loop to count number of strings. - Previously if one passed "rootfstype=foo,,bar", split_fs_names() will return only 1 string "foo" (and "bar" will be truncated due to extra ,). After this patch, now split_fs_names() will return 3 strings ("foo", zero-sized-string, and "bar"). Callers of split_fs_names() have been modified to check for zero sized string and skip to next one. Reported-by: xu xin <xu.xin16@zte.com.cn> Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2021-09-17 21:13:23 +08:00
int count = 1;
char *p = page;
strscpy(p, root_fs_names, size);
while (*p++) {
init/do_mounts.c: Harden split_fs_names() against buffer overflow split_fs_names() currently takes comma separate list of filesystems and converts it into individual filesystem strings. Pleaces these strings in the input buffer passed by caller and returns number of strings. If caller manages to pass input string bigger than buffer, then we can write beyond the buffer. Or if string just fits buffer, we will still write beyond the buffer as we append a '\0' byte at the end. Pass size of input buffer to split_fs_names() and put enough checks in place so such buffer overrun possibilities do not occur. This patch does few things. - Add a parameter "size" to split_fs_names(). This specifies size of input buffer. - Use strlcpy() (instead of strcpy()) so that we can't go beyond buffer size. If input string "names" is larger than passed in buffer, input string will be truncated to fit in buffer. - Stop appending extra '\0' character at the end and avoid one possibility of going beyond the input buffer size. - Do not use extra loop to count number of strings. - Previously if one passed "rootfstype=foo,,bar", split_fs_names() will return only 1 string "foo" (and "bar" will be truncated due to extra ,). After this patch, now split_fs_names() will return 3 strings ("foo", zero-sized-string, and "bar"). Callers of split_fs_names() have been modified to check for zero sized string and skip to next one. Reported-by: xu xin <xu.xin16@zte.com.cn> Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2021-09-17 21:13:23 +08:00
if (p[-1] == ',') {
p[-1] = '\0';
init/do_mounts.c: Harden split_fs_names() against buffer overflow split_fs_names() currently takes comma separate list of filesystems and converts it into individual filesystem strings. Pleaces these strings in the input buffer passed by caller and returns number of strings. If caller manages to pass input string bigger than buffer, then we can write beyond the buffer. Or if string just fits buffer, we will still write beyond the buffer as we append a '\0' byte at the end. Pass size of input buffer to split_fs_names() and put enough checks in place so such buffer overrun possibilities do not occur. This patch does few things. - Add a parameter "size" to split_fs_names(). This specifies size of input buffer. - Use strlcpy() (instead of strcpy()) so that we can't go beyond buffer size. If input string "names" is larger than passed in buffer, input string will be truncated to fit in buffer. - Stop appending extra '\0' character at the end and avoid one possibility of going beyond the input buffer size. - Do not use extra loop to count number of strings. - Previously if one passed "rootfstype=foo,,bar", split_fs_names() will return only 1 string "foo" (and "bar" will be truncated due to extra ,). After this patch, now split_fs_names() will return 3 strings ("foo", zero-sized-string, and "bar"). Callers of split_fs_names() have been modified to check for zero sized string and skip to next one. Reported-by: xu xin <xu.xin16@zte.com.cn> Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2021-09-17 21:13:23 +08:00
count++;
}
}
return count;
}
static int __init do_mount_root(const char *name, const char *fs,
const int flags, const void *data)
{
struct super_block *s;
struct page *p = NULL;
char *data_page = NULL;
int ret;
if (data) {
/* init_mount() requires a full page as fifth argument */
p = alloc_page(GFP_KERNEL);
if (!p)
return -ENOMEM;
data_page = page_address(p);
/* zero-pad. init_mount() will make sure it's terminated */
strncpy(data_page, data, PAGE_SIZE);
}
ret = init_mount(name, "/root", fs, flags, data_page);
if (ret)
goto out;
init_chdir("/root");
s = current->fs->pwd.dentry->d_sb;
ROOT_DEV = s->s_dev;
printk(KERN_INFO
"VFS: Mounted root (%s filesystem)%s on device %u:%u.\n",
s->s_type->name,
sb_rdonly(s) ? " readonly" : "",
MAJOR(ROOT_DEV), MINOR(ROOT_DEV));
out:
if (p)
put_page(p);
return ret;
}
void __init mount_root_generic(char *name, char *pretty_name, int flags)
{
struct page *page = alloc_page(GFP_KERNEL);
char *fs_names = page_address(page);
char *p;
char b[BDEVNAME_SIZE];
int num_fs, i;
scnprintf(b, BDEVNAME_SIZE, "unknown-block(%u,%u)",
MAJOR(ROOT_DEV), MINOR(ROOT_DEV));
if (root_fs_names)
num_fs = split_fs_names(fs_names, PAGE_SIZE);
else
num_fs = list_bdev_fs_names(fs_names, PAGE_SIZE);
retry:
for (i = 0, p = fs_names; i < num_fs; i++, p += strlen(p)+1) {
init/do_mounts.c: Harden split_fs_names() against buffer overflow split_fs_names() currently takes comma separate list of filesystems and converts it into individual filesystem strings. Pleaces these strings in the input buffer passed by caller and returns number of strings. If caller manages to pass input string bigger than buffer, then we can write beyond the buffer. Or if string just fits buffer, we will still write beyond the buffer as we append a '\0' byte at the end. Pass size of input buffer to split_fs_names() and put enough checks in place so such buffer overrun possibilities do not occur. This patch does few things. - Add a parameter "size" to split_fs_names(). This specifies size of input buffer. - Use strlcpy() (instead of strcpy()) so that we can't go beyond buffer size. If input string "names" is larger than passed in buffer, input string will be truncated to fit in buffer. - Stop appending extra '\0' character at the end and avoid one possibility of going beyond the input buffer size. - Do not use extra loop to count number of strings. - Previously if one passed "rootfstype=foo,,bar", split_fs_names() will return only 1 string "foo" (and "bar" will be truncated due to extra ,). After this patch, now split_fs_names() will return 3 strings ("foo", zero-sized-string, and "bar"). Callers of split_fs_names() have been modified to check for zero sized string and skip to next one. Reported-by: xu xin <xu.xin16@zte.com.cn> Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2021-09-17 21:13:23 +08:00
int err;
if (!*p)
continue;
err = do_mount_root(name, p, flags, root_mount_data);
switch (err) {
case 0:
goto out;
case -EACCES:
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
*/
printk("VFS: Cannot open root device \"%s\" or %s: error %d\n",
pretty_name, b, err);
printk("Please append a correct \"root=\" boot option; here are the available partitions:\n");
printk_all_partitions();
panic("VFS: Unable to mount root fs on %s", b);
}
if (!(flags & SB_RDONLY)) {
flags |= SB_RDONLY;
goto retry;
}
printk("List of all partitions:\n");
printk_all_partitions();
printk("No filesystem could mount root, tried: ");
for (i = 0, p = fs_names; i < num_fs; i++, p += strlen(p)+1)
printk(" %s", p);
printk("\n");
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
panic("VFS: Unable to mount root fs on %s", b);
out:
put_page(page);
}
#ifdef CONFIG_ROOT_NFS
#define NFSROOT_TIMEOUT_MIN 5
#define NFSROOT_TIMEOUT_MAX 30
#define NFSROOT_RETRY_MAX 5
static void __init mount_nfs_root(void)
{
char *root_dev, *root_data;
unsigned int timeout;
int try;
if (nfs_root_data(&root_dev, &root_data))
goto fail;
/*
* 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++) {
if (!do_mount_root(root_dev, "nfs", root_mountflags, root_data))
return;
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;
}
fail:
pr_err("VFS: Unable to mount root fs via NFS.\n");
}
#else
static inline void mount_nfs_root(void)
{
}
#endif /* CONFIG_ROOT_NFS */
#ifdef CONFIG_CIFS_ROOT
extern int cifs_root_data(char **dev, char **opts);
#define CIFSROOT_TIMEOUT_MIN 5
#define CIFSROOT_TIMEOUT_MAX 30
#define CIFSROOT_RETRY_MAX 5
static void __init mount_cifs_root(void)
{
char *root_dev, *root_data;
unsigned int timeout;
int try;
if (cifs_root_data(&root_dev, &root_data))
goto fail;
timeout = CIFSROOT_TIMEOUT_MIN;
for (try = 1; ; try++) {
if (!do_mount_root(root_dev, "cifs", root_mountflags,
root_data))
return;
if (try > CIFSROOT_RETRY_MAX)
break;
ssleep(timeout);
timeout <<= 1;
if (timeout > CIFSROOT_TIMEOUT_MAX)
timeout = CIFSROOT_TIMEOUT_MAX;
}
fail:
pr_err("VFS: Unable to mount root fs via SMB.\n");
}
#else
static inline void mount_cifs_root(void)
{
}
#endif /* CONFIG_CIFS_ROOT */
static bool __init fs_is_nodev(char *fstype)
{
struct file_system_type *fs = get_fs_type(fstype);
bool ret = false;
if (fs) {
ret = !(fs->fs_flags & FS_REQUIRES_DEV);
put_filesystem(fs);
}
return ret;
}
static int __init mount_nodev_root(char *root_device_name)
{
char *fs_names, *fstype;
int err = -EINVAL;
int num_fs, i;
fs_names = (void *)__get_free_page(GFP_KERNEL);
if (!fs_names)
return -EINVAL;
num_fs = split_fs_names(fs_names, PAGE_SIZE);
for (i = 0, fstype = fs_names; i < num_fs;
i++, fstype += strlen(fstype) + 1) {
init/do_mounts.c: Harden split_fs_names() against buffer overflow split_fs_names() currently takes comma separate list of filesystems and converts it into individual filesystem strings. Pleaces these strings in the input buffer passed by caller and returns number of strings. If caller manages to pass input string bigger than buffer, then we can write beyond the buffer. Or if string just fits buffer, we will still write beyond the buffer as we append a '\0' byte at the end. Pass size of input buffer to split_fs_names() and put enough checks in place so such buffer overrun possibilities do not occur. This patch does few things. - Add a parameter "size" to split_fs_names(). This specifies size of input buffer. - Use strlcpy() (instead of strcpy()) so that we can't go beyond buffer size. If input string "names" is larger than passed in buffer, input string will be truncated to fit in buffer. - Stop appending extra '\0' character at the end and avoid one possibility of going beyond the input buffer size. - Do not use extra loop to count number of strings. - Previously if one passed "rootfstype=foo,,bar", split_fs_names() will return only 1 string "foo" (and "bar" will be truncated due to extra ,). After this patch, now split_fs_names() will return 3 strings ("foo", zero-sized-string, and "bar"). Callers of split_fs_names() have been modified to check for zero sized string and skip to next one. Reported-by: xu xin <xu.xin16@zte.com.cn> Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2021-09-17 21:13:23 +08:00
if (!*fstype)
continue;
if (!fs_is_nodev(fstype))
continue;
err = do_mount_root(root_device_name, fstype, root_mountflags,
root_mount_data);
if (!err)
break;
}
free_page((unsigned long)fs_names);
return err;
}
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#ifdef CONFIG_BLOCK
static void __init mount_block_root(char *root_device_name)
{
int err = create_dev("/dev/root", ROOT_DEV);
if (err < 0)
pr_emerg("Failed to create /dev/root: %d\n", err);
mount_root_generic("/dev/root", root_device_name, root_mountflags);
}
#else
static inline void mount_block_root(char *root_device_name)
{
}
#endif /* CONFIG_BLOCK */
void __init mount_root(char *root_device_name)
{
switch (ROOT_DEV) {
case Root_NFS:
mount_nfs_root();
break;
case Root_CIFS:
mount_cifs_root();
break;
case Root_Generic:
mount_root_generic(root_device_name, root_device_name,
root_mountflags);
break;
case 0:
if (root_device_name && root_fs_names &&
mount_nodev_root(root_device_name) == 0)
break;
fallthrough;
default:
mount_block_root(root_device_name);
break;
}
}
/* wait for any asynchronous scanning to complete */
static void __init wait_for_root(char *root_device_name)
{
if (ROOT_DEV != 0)
return;
pr_info("Waiting for root device %s...\n", root_device_name);
while (!driver_probe_done() ||
early_lookup_bdev(root_device_name, &ROOT_DEV) < 0)
msleep(5);
async_synchronize_full();
}
static dev_t __init parse_root_device(char *root_device_name)
{
int error;
dev_t dev;
if (!strncmp(root_device_name, "mtd", 3) ||
!strncmp(root_device_name, "ubi", 3))
return Root_Generic;
if (strcmp(root_device_name, "/dev/nfs") == 0)
return Root_NFS;
if (strcmp(root_device_name, "/dev/cifs") == 0)
return Root_CIFS;
if (strcmp(root_device_name, "/dev/ram") == 0)
return Root_RAM0;
error = early_lookup_bdev(root_device_name, &dev);
if (error) {
if (error == -EINVAL && root_wait) {
pr_err("Disabling rootwait; root= is invalid.\n");
root_wait = 0;
}
return 0;
}
return dev;
}
/*
* Prepare the namespace - decide what/where to mount, load ramdisks, etc.
*/
void __init prepare_namespace(void)
{
if (root_delay) {
printk(KERN_INFO "Waiting %d sec 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_DEV = parse_root_device(saved_root_name);
if (initrd_load(saved_root_name))
goto out;
if (root_wait)
wait_for_root(saved_root_name);
mount_root(saved_root_name);
out:
devtmpfs_mount();
init_mount(".", "/", NULL, MS_MOVE, NULL);
init_chroot(".");
}
static bool is_tmpfs;
static int rootfs_init_fs_context(struct fs_context *fc)
{
if (IS_ENABLED(CONFIG_TMPFS) && is_tmpfs)
return shmem_init_fs_context(fc);
return ramfs_init_fs_context(fc);
}
struct file_system_type rootfs_fs_type = {
.name = "rootfs",
.init_fs_context = rootfs_init_fs_context,
.kill_sb = kill_litter_super,
};
void __init init_rootfs(void)
{
if (IS_ENABLED(CONFIG_TMPFS) && !saved_root_name[0] &&
(!root_fs_names || strstr(root_fs_names, "tmpfs")))
is_tmpfs = true;
}