support booting of arbitrary non-blockdevice file systems
v3 cover support booting of arbitrary non-blockdevice file systems
Hi,
This is V3 of patches. Christoph had posted V2 here.
https://lore.kernel.org/linux-fsdevel/[email protected]/
There was a small issue in last patch series that list_bdev_fs_names() did not put an extra '\0' at the end as current callers were expecting.
To fix this, I have modified list_bdev_fs_names() and split_fs_names() to return number of null terminated strings they have parsed. And modified callers to use that to loop through strings (instead of relying on an extra null at the end).
Christoph was finding it hard to find time so I took his patches, added my changes in patch3 and reposting the patch series.
I have tested it with 9p, virtiofs and ext4 filesystems as rootfs and it works for me.
Thanks
Vivek
Christoph Hellwig (3):
init: split get_fs_names
init: allow mounting arbitrary non-blockdevice filesystems as root
fs: simplify get_filesystem_list / get_all_fs_names
fs/filesystems.c | 27 ++++++++------ include/linux/fs.h | 2 +- init/do_mounts.c | 90 +++++++++++++++++++++++++++++++++------------- 3 files changed, 83 insertions(+), 36 deletions(-)
Signature · 1 line
2.31.1
PATCH v3 1/3 init: split get_fs_names
From: Christoph Hellwig <[email protected]>
Split get_fs_names into one function that splits up the command line argument, and one that gets the list of all registered file systems.
--- init/do_mounts.c | 48 ++++++++++++++++++++++++++---------------------- 1 file changed, 26 insertions(+), 22 deletions(-)
init/do_mounts.c +26 -22
@@ -338,30 +338,31 @@ __setup("rootflags=", root_data_setup);__setup ("rootfstype=" , fs_names_setup);__setup ("rootdelay=" , root_delay_setup); -static void __init get_fs_names (char *page) +static void __init split_fs_names (char *page,char *names) { -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; +strcpy (page, root_fs_names); +while (*page++) { +if (page[-1 ] ==',' ) + page[-1 ] ='\0' ; + } + *page ='\0' ; +} - 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' ; - } +static void __init get_all_fs_names (char *page) +{ +int len =get_filesystem_list (page); +char *s = page, *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' ; }
@@ -411,7 +412,10 @@ void __init mount_block_root(char *name, int flags)scnprintf (b,BDEVNAME_SIZE ,"unknown-block(%u,%u)" ,MAJOR (ROOT_DEV ),MINOR (ROOT_DEV )); -get_fs_names (fs_names); +if (root_fs_names) +split_fs_names (fs_names, root_fs_names); +else +get_all_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);
Signature · 1 line
2.31.1
Re: [PATCH v3 1/3] init: split get_fs_names
Quoted 9 lines · Vivek Goyal
From: Christoph Hellwig <[email protected]>
Split
get_fs_namesinto one function that splits up the command line argument, and one that gets the list of all registered file systems.Signed-off-by Christoph Hellwig <[email protected]>--- init/do_mounts.c | 48 ++++++++++++++++++++++++++---------------------- 1 file changed, 26 insertions(+), 22 deletions(-)
PATCH v3 2/3 init: allow mounting arbitrary non-blockdevice filesystems as root
In reply to Vivek GoyalFrom: Christoph Hellwig <[email protected]>
Currently the only non-blockdevice filesystems that can be used as the initial root filesystem are NFS and CIFS, which use the magic "root=/dev/nfs" and "root=/dev/cifs" syntax that requires the root device file system details to come from filesystem specific kernel command line options.
Add a little bit of new code that allows to just pass arbitrary string mount options to any non-blockdevice filesystems so that it can be mounted as the root file system.
For example a virtiofs root file system can be mounted using the following syntax:
"root=myfs rootfstype=virtiofs rw"
Based on an earlier patch from Vivek Goyal <[email protected]>.
--- init/do_mounts.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+)
init/do_mounts.c +43 -0
@@ -534,6 +534,45 @@ static int __init mount_cifs_root(void) }#endif +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 (void ) +{ +char *fs_names, *fstype; +int err = -EINVAL ; + + fs_names = (void *)__get_free_page (GFP_KERNEL ); +if (!fs_names) +return -EINVAL ; +split_fs_names (fs_names, root_fs_names); + +for (fstype = fs_names; *fstype; fstype +=strlen (fstype) +1 ) { +if (!fs_is_nodev (fstype)) +continue ; + err =do_mount_root (root_device_name, fstype, root_mountflags, + root_mount_data); +if (!err) +break ; +if (err != -EACCES && err != -EINVAL ) +panic ("VFS: Unable to mount root \"%s\" (%s), err=%d\n" , + root_device_name, fstype, err); + } + +free_page ((unsigned long )fs_names); +return err; +} +void __init mount_root (void ) {#ifdef CONFIG_ROOT_NFS
@@ -550,6 +589,10 @@ void __init mount_root(void)return ; }#endif +if (ROOT_DEV ==0 && root_device_name && root_fs_names) { +if (mount_nodev_root () ==0 ) +return ; + }#ifdef CONFIG_BLOCK {int err =create_dev ("/dev/root" ,ROOT_DEV );
Signature · 1 line
2.31.1
Re: [PATCH v3 2/3] init: allow mounting arbitrary non-blockdevice filesystems as root
Quoted 15 lines · Vivek Goyal
From: Christoph Hellwig <[email protected]>
Currently the only non-blockdevice filesystems that can be used as the initial root filesystem are NFS and CIFS, which use the magic "root=/dev/nfs" and "root=/dev/cifs" syntax that requires the root device file system details to come from filesystem specific kernel command line options.
Add a little bit of new code that allows to just pass arbitrary string mount options to any non-blockdevice filesystems so that it can be mounted as the root file system.
For example a virtiofs root file system can be mounted using the following syntax:
Quoted 8 lines
"root=myfs rootfstype=virtiofs rw"
Based on an earlier patch from Vivek Goyal <[email protected]>.
Signed-off-by Christoph Hellwig <[email protected]>--- init/do_mounts.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+)
PATCH v3 3/3 fs: simplify get_filesystem_list / get_all_fs_names
In reply to Vivek GoyalFrom: Christoph Hellwig <[email protected]>
Just output the '\0' separate list of supported file systems for block devices directly rather than going through a pointless round of string manipulation.
Based on an earlier patch from Al Viro <[email protected]>.
Vivek:
Modified list_bdev_fs_names() and split_fs_names() to return number of null terminted strings to caller. Callers now use that information to loop through all the strings instead of relying on one extra null char being present at the end.
--- fs/filesystems.c | 27 +++++++++++++++---------- include/linux/fs.h | 2 +- init/do_mounts.c | 49 ++++++++++++++++++++-------------------------- 3 files changed, 39 insertions(+), 39 deletions(-)
fs/filesystems.c +17 -10
@@ -209,21 +209,28 @@ SYSCALL_DEFINE3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2) }#endif -int __init get_filesystem_list (char *buf) +int __init list_bdev_fs_names (char *buf,size_t size) { -int len =0 ; -struct file_system_type * tmp; +struct file_system_type *p; +size_t len; +int count =0 ;read_lock (&file_systems_lock); - tmp = file_systems; -while (tmp && len <PAGE_SIZE -80 ) { - len +=sprintf (buf+len,"%s\t%s\n" , - (tmp->fs_flags &FS_REQUIRES_DEV ) ?"" :"nodev" , - tmp->name); - tmp = tmp->next; +for (p = file_systems; p; p = p->next) { +if (!(p->fs_flags &FS_REQUIRES_DEV )) +continue ; + len =strlen (p->name) +1 ; +if (len > size) { +pr_warn ("%s: truncating file system list\n" , __func__); +break ; + } +memcpy (buf, p->name, len); + buf += len; + size -= len; + count++; }read_unlock (&file_systems_lock); -return len; +return count; }#ifdef CONFIG_PROC_FS
include/linux/fs.h +1 -1
@@ -3622,7 +3622,7 @@ int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos);int proc_nr_inodes (struct ctl_table *table,int write,void *buffer,size_t *lenp,loff_t *ppos); -int __init get_filesystem_list (char *buf); +int __init list_bdev_fs_names (char *buf,size_t size);#define __FMODE_EXEC ((__force int) FMODE_EXEC)#define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY)
init/do_mounts.c +21 -28
88 lines not on this page · raw message
Signature · 1 line
2.31.1
Re: [PATCH v3 3/3] fs: simplify get_filesystem_list / get_all_fs_names
Quoted 14 lines · Vivek Goyal
From: Christoph Hellwig <[email protected]>
Just output the '\0' separate list of supported file systems for block devices directly rather than going through a pointless round of string manipulation.
Based on an earlier patch from Al Viro <[email protected]>.
Vivek:
Modifiedlist_bdev_fs_names()andsplit_fs_names()to return number of null terminted strings to caller. Callers now use that information to loop through all the strings instead of relying on one extra null char being present at the end.
Quoted 7 lines
Signed-off-by Christoph Hellwig <[email protected]>Signed-off-by Vivek Goyal <[email protected]>--- fs/filesystems.c | 27 +++++++++++++++---------- include/linux/fs.h | 2 +- init/do_mounts.c | 49 ++++++++++++++++++++-------------------------- 3 files changed, 39 insertions(+), 39 deletions(-)
Al Viro
maintainerRe: [PATCH v3 3/3] fs: simplify get_filesystem_list / get_all_fs_names
In reply to Vivek GoyalQuoted 7 lines · Vivek Goyal
init/do_mounts.c +5
-0+static int __init split_fs_names (char *page,char *names) { +int count =0 ; +char *p = page; +strcpy (p, root_fs_names); +while (*p++) {
init/do_mounts.c __setup("rootflags=", root_data_setup); · line 357
Quoted 10 lines
init/do_mounts.c +7
-0+if (p[-1 ] ==',' ) + p[-1 ] ='\0' ; } + *p ='\0' ; + +for (p = page; *p; p +=strlen (p)+1 ) + count++; +return count; }
Ummm.... The last part makes no sense - it counts '\0' in the array pointed to be page, until the first double '\0' in there. All of which had been put there by the loop immediately prior to that one...
Incidentally, it treats stray ,, in root_fs_names as termination; is that intentional?
Re: [PATCH v3 3/3] fs: simplify get_filesystem_list / get_all_fs_names
Quoted 17 lines · Al Viro
Quoted 15 lines · Vivek Goyal
init/do_mounts.c +11
-0+static int __init split_fs_names (char *page,char *names) { +int count =0 ; +char *p = page; +strcpy (p, root_fs_names); +while (*p++) { +if (p[-1 ] ==',' ) + p[-1 ] ='\0' ; } + *p ='\0' ; + +for (p = page; *p; p +=strlen (p)+1 ) + count++;
Quoted 6 lines
Review
Quoted 2 lines
(quoted diff) +1
-0+ return count; }Ummm.... The last part makes no sense - it counts '\0' in the array pointed to be page, until the first double '\0' in there. All of which had been put there by the loop immediately prior to that one...
I want split_fs_names() to replace ',' with space as well as return number of null terminated strings found. So first loop just replaces ',' with '\0' and second loop counts number of strings.
Previously split_fs_names() was only replacing ',' with '\0'. Now we are changing the semantics and returning number of strings left in the buffer after the replacement.
I initilaly thought that if I can manage it with single loop but there were quite a few corner cases. So I decided to use two loops instead. One for replacement and one for counting.
Quoted 3 lines
Incidentally, it treats stray ,, in
root_fs_namesas termination; is that intentional?
Just trying to keep the existing behavior. Existing get_fs_names(), also replaces all instances of ',' with '\0'. So if there are two consecutive, ',', that will result in two consecutive '\0' and caller will view it as end of buffer.
IOW, rootfsnames=foo,,bar will effectively be treated as "rootfsname=foo".
That's the current behavior and I did not try to improve on it just keeps on increasing the size of patches. That's probably an improvement for some other day if somebody cares.
Thanks
Vivek
Quoted 3 lines · Vivek Goyal
Hi,
This is V3 of patches. Christoph had posted V2 here.
Hi,
Ping?
Vivek
Quoted 33 lines
https://lore.kernel.org/linux-fsdevel/[email protected]/
There was a small issue in last patch series that
list_bdev_fs_names()did not put an extra '\0' at the end as current callers were expecting.To fix this, I have modified
list_bdev_fs_names()andsplit_fs_names()to return number of null terminated strings they have parsed. And modified callers to use that to loop through strings (instead of relying on an extra null at the end).Christoph was finding it hard to find time so I took his patches, added my changes in patch3 and reposting the patch series.
I have tested it with 9p, virtiofs and ext4 filesystems as rootfs and it works for me.
Thanks
VivekChristoph Hellwig (3):
init: splitget_fs_names
init: allow mounting arbitrary non-blockdevice filesystems as root
fs: simplifyget_filesystem_list/get_all_fs_namesfs/filesystems.c | 27 ++++++++------ include/linux/fs.h | 2 +- init/do_mounts.c | 90 +++++++++++++++++++++++++++++++++------------- 3 files changed, 83 insertions(+), 36 deletions(-)Signature · 1 line
2.31.1
Quoted 14 lines · Vivek Goyal
Hi,
This is V3 of patches. Christoph had posted V2 here.
https://lore.kernel.org/linux-fsdevel/[email protected]/
There was a small issue in last patch series that
list_bdev_fs_names()did not put an extra '\0' at the end as current callers were expecting.To fix this, I have modified
list_bdev_fs_names()andsplit_fs_names()to return number of null terminated strings they have parsed. And modified callers to use that to loop through strings (instead of relying on an extra null at the end).
Quoted 5 lines
Christoph was finding it hard to find time so I took his patches, added my changes in patch3 and reposting the patch series.
I have tested it with 9p, virtiofs and ext4 filesystems as rootfs and it works for me.
lgtm,