OpenCloudOS-Kernel/init/do_mounts_rd.c

355 lines
8.3 KiB
C
Raw Normal View History

/*
* Many of the syscalls used in this file expect some of the arguments
* to be __user pointers not __kernel pointers. To limit the sparse
* noise, turn off sparse checking for this file.
*/
#ifdef __CHECKER__
#undef __CHECKER__
#warning "Sparse checking disabled for this file"
#endif
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/minix_fs.h>
#include <linux/ext2_fs.h>
#include <linux/romfs_fs.h>
#include <uapi/linux/cramfs_fs.h>
#include <linux/initrd.h>
#include <linux/string.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 "do_mounts.h"
#include "../fs/squashfs/squashfs_fs.h"
#include <linux/decompress/generic.h>
int __initdata rd_prompt = 1;/* 1 = prompt for RAM disk, 0 = don't prompt */
static int __init prompt_ramdisk(char *str)
{
rd_prompt = simple_strtol(str,NULL,0) & 1;
return 1;
}
__setup("prompt_ramdisk=", prompt_ramdisk);
int __initdata rd_image_start; /* starting block # of image */
static int __init ramdisk_start_setup(char *str)
{
rd_image_start = simple_strtol(str,NULL,0);
return 1;
}
__setup("ramdisk_start=", ramdisk_start_setup);
static int __init crd_load(int in_fd, int out_fd, decompress_fn deco);
/*
* This routine tries to find a RAM disk image to load, and returns the
* number of blocks to read for a non-compressed image, 0 if the image
* is a compressed image, and -1 if an image with the right magic
* numbers could not be found.
*
* We currently check for the following magic numbers:
* minix
* ext2
* romfs
* cramfs
* squashfs
* gzip
* bzip2
* lzma
* xz
* lzo
* lz4
*/
static int __init
identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
{
const int size = 512;
struct minix_super_block *minixsb;
struct romfs_super_block *romfsb;
struct cramfs_super *cramfsb;
struct squashfs_super_block *squashfsb;
int nblocks = -1;
unsigned char *buf;
const char *compress_name;
unsigned long n;
buf = kmalloc(size, GFP_KERNEL);
if (!buf)
return -ENOMEM;
minixsb = (struct minix_super_block *) buf;
romfsb = (struct romfs_super_block *) buf;
cramfsb = (struct cramfs_super *) buf;
squashfsb = (struct squashfs_super_block *) buf;
memset(buf, 0xe5, size);
/*
* Read block 0 to test for compressed kernel
*/
sys_lseek(fd, start_block * BLOCK_SIZE, 0);
sys_read(fd, buf, size);
*decompressor = decompress_method(buf, size, &compress_name);
if (compress_name) {
printk(KERN_NOTICE "RAMDISK: %s image found at block %d\n",
compress_name, start_block);
if (!*decompressor)
printk(KERN_EMERG
"RAMDISK: %s decompressor not configured!\n",
compress_name);
nblocks = 0;
goto done;
}
/* romfs is at block zero too */
if (romfsb->word0 == ROMSB_WORD0 &&
romfsb->word1 == ROMSB_WORD1) {
printk(KERN_NOTICE
"RAMDISK: romfs filesystem found at block %d\n",
start_block);
nblocks = (ntohl(romfsb->size)+BLOCK_SIZE-1)>>BLOCK_SIZE_BITS;
goto done;
}
if (cramfsb->magic == CRAMFS_MAGIC) {
printk(KERN_NOTICE
"RAMDISK: cramfs filesystem found at block %d\n",
start_block);
nblocks = (cramfsb->size + BLOCK_SIZE - 1) >> BLOCK_SIZE_BITS;
goto done;
}
/* squashfs is at block zero too */
if (le32_to_cpu(squashfsb->s_magic) == SQUASHFS_MAGIC) {
printk(KERN_NOTICE
"RAMDISK: squashfs filesystem found at block %d\n",
start_block);
nblocks = (le64_to_cpu(squashfsb->bytes_used) + BLOCK_SIZE - 1)
>> BLOCK_SIZE_BITS;
goto done;
}
/*
* Read 512 bytes further to check if cramfs is padded
*/
sys_lseek(fd, start_block * BLOCK_SIZE + 0x200, 0);
sys_read(fd, buf, size);
if (cramfsb->magic == CRAMFS_MAGIC) {
printk(KERN_NOTICE
"RAMDISK: cramfs filesystem found at block %d\n",
start_block);
nblocks = (cramfsb->size + BLOCK_SIZE - 1) >> BLOCK_SIZE_BITS;
goto done;
}
/*
* Read block 1 to test for minix and ext2 superblock
*/
sys_lseek(fd, (start_block+1) * BLOCK_SIZE, 0);
sys_read(fd, buf, size);
/* Try minix */
if (minixsb->s_magic == MINIX_SUPER_MAGIC ||
minixsb->s_magic == MINIX_SUPER_MAGIC2) {
printk(KERN_NOTICE
"RAMDISK: Minix filesystem found at block %d\n",
start_block);
nblocks = minixsb->s_nzones << minixsb->s_log_zone_size;
goto done;
}
/* Try ext2 */
n = ext2_image_size(buf);
if (n) {
printk(KERN_NOTICE
"RAMDISK: ext2 filesystem found at block %d\n",
start_block);
nblocks = n;
goto done;
}
printk(KERN_NOTICE
"RAMDISK: Couldn't find valid RAM disk image starting at %d.\n",
start_block);
done:
sys_lseek(fd, start_block * BLOCK_SIZE, 0);
kfree(buf);
return nblocks;
}
int __init rd_load_image(char *from)
{
int res = 0;
int in_fd, out_fd;
unsigned long rd_blocks, devblocks;
int nblocks, i, disk;
char *buf = NULL;
unsigned short rotate = 0;
decompress_fn decompressor = NULL;
#if !defined(CONFIG_S390)
char rotator[4] = { '|' , '/' , '-' , '\\' };
#endif
out_fd = sys_open("/dev/ram", O_RDWR, 0);
if (out_fd < 0)
goto out;
in_fd = sys_open(from, O_RDONLY, 0);
if (in_fd < 0)
goto noclose_input;
nblocks = identify_ramdisk_image(in_fd, rd_image_start, &decompressor);
if (nblocks < 0)
goto done;
if (nblocks == 0) {
if (crd_load(in_fd, out_fd, decompressor) == 0)
goto successful_load;
goto done;
}
/*
* NOTE NOTE: nblocks is not actually blocks but
* the number of kibibytes of data to load into a ramdisk.
*/
if (sys_ioctl(out_fd, BLKGETSIZE, (unsigned long)&rd_blocks) < 0)
rd_blocks = 0;
else
rd_blocks >>= 1;
if (nblocks > rd_blocks) {
printk("RAMDISK: image too big! (%dKiB/%ldKiB)\n",
nblocks, rd_blocks);
goto done;
}
/*
* OK, time to copy in the data
*/
if (sys_ioctl(in_fd, BLKGETSIZE, (unsigned long)&devblocks) < 0)
devblocks = 0;
else
devblocks >>= 1;
if (strcmp(from, "/initrd.image") == 0)
devblocks = nblocks;
if (devblocks == 0) {
printk(KERN_ERR "RAMDISK: could not determine device size\n");
goto done;
}
buf = kmalloc(BLOCK_SIZE, GFP_KERNEL);
if (!buf) {
printk(KERN_ERR "RAMDISK: could not allocate buffer\n");
goto done;
}
printk(KERN_NOTICE "RAMDISK: Loading %dKiB [%ld disk%s] into ram disk... ",
nblocks, ((nblocks-1)/devblocks)+1, nblocks>devblocks ? "s" : "");
for (i = 0, disk = 1; i < nblocks; i++) {
if (i && (i % devblocks == 0)) {
printk("done disk #%d.\n", disk++);
rotate = 0;
if (sys_close(in_fd)) {
printk("Error closing the disk.\n");
goto noclose_input;
}
change_floppy("disk #%d", disk);
in_fd = sys_open(from, O_RDONLY, 0);
if (in_fd < 0) {
printk("Error opening disk.\n");
goto noclose_input;
}
printk("Loading disk #%d... ", disk);
}
sys_read(in_fd, buf, BLOCK_SIZE);
sys_write(out_fd, buf, BLOCK_SIZE);
#if !defined(CONFIG_S390)
if (!(i % 16)) {
pr_cont("%c\b", rotator[rotate & 0x3]);
rotate++;
}
#endif
}
printk("done.\n");
successful_load:
res = 1;
done:
sys_close(in_fd);
noclose_input:
sys_close(out_fd);
out:
kfree(buf);
sys_unlink("/dev/ram");
return res;
}
int __init rd_load_disk(int n)
{
if (rd_prompt)
change_floppy("root floppy disk to be loaded into RAM disk");
create_dev("/dev/root", ROOT_DEV);
create_dev("/dev/ram", MKDEV(RAMDISK_MAJOR, n));
return rd_load_image("/dev/root");
}
static int exit_code;
static int decompress_error;
static int crd_infd, crd_outfd;
initramfs: support initramfs that is bigger than 2GiB Now with 64bit bzImage and kexec tools, we support ramdisk that size is bigger than 2g, as we could put it above 4G. Found compressed initramfs image could not be decompressed properly. It turns out that image length is int during decompress detection, and it will become < 0 when length is more than 2G. Furthermore, during decompressing len as int is used for inbuf count, that has problem too. Change len to long, that should be ok as on 32 bit platform long is 32bits. Tested with following compressed initramfs image as root with kexec. gzip, bzip2, xz, lzma, lzop, lz4. run time for populate_rootfs(): size name Nehalem-EX Westmere-EX Ivybridge-EX 9034400256 root_img : 26s 24s 30s 3561095057 root_img.lz4 : 28s 27s 27s 3459554629 root_img.lzo : 29s 29s 28s 3219399480 root_img.gz : 64s 62s 49s 2251594592 root_img.xz : 262s 260s 183s 2226366598 root_img.lzma: 386s 376s 277s 2901482513 root_img.bz2 : 635s 599s Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Rashika Kheria <rashika.kheria@gmail.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Kyungsik Lee <kyungsik.lee@lge.com> Cc: P J P <ppandit@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Cc: "Daniel M. Weeks" <dan@danweeks.net> Cc: Alexandre Courbot <acourbot@nvidia.com> Cc: Jan Beulich <JBeulich@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:23:14 +08:00
static long __init compr_fill(void *buf, unsigned long len)
{
initramfs: support initramfs that is bigger than 2GiB Now with 64bit bzImage and kexec tools, we support ramdisk that size is bigger than 2g, as we could put it above 4G. Found compressed initramfs image could not be decompressed properly. It turns out that image length is int during decompress detection, and it will become < 0 when length is more than 2G. Furthermore, during decompressing len as int is used for inbuf count, that has problem too. Change len to long, that should be ok as on 32 bit platform long is 32bits. Tested with following compressed initramfs image as root with kexec. gzip, bzip2, xz, lzma, lzop, lz4. run time for populate_rootfs(): size name Nehalem-EX Westmere-EX Ivybridge-EX 9034400256 root_img : 26s 24s 30s 3561095057 root_img.lz4 : 28s 27s 27s 3459554629 root_img.lzo : 29s 29s 28s 3219399480 root_img.gz : 64s 62s 49s 2251594592 root_img.xz : 262s 260s 183s 2226366598 root_img.lzma: 386s 376s 277s 2901482513 root_img.bz2 : 635s 599s Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Rashika Kheria <rashika.kheria@gmail.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Kyungsik Lee <kyungsik.lee@lge.com> Cc: P J P <ppandit@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Cc: "Daniel M. Weeks" <dan@danweeks.net> Cc: Alexandre Courbot <acourbot@nvidia.com> Cc: Jan Beulich <JBeulich@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:23:14 +08:00
long r = sys_read(crd_infd, buf, len);
if (r < 0)
printk(KERN_ERR "RAMDISK: error while reading compressed data");
else if (r == 0)
printk(KERN_ERR "RAMDISK: EOF while reading compressed data");
return r;
}
initramfs: support initramfs that is bigger than 2GiB Now with 64bit bzImage and kexec tools, we support ramdisk that size is bigger than 2g, as we could put it above 4G. Found compressed initramfs image could not be decompressed properly. It turns out that image length is int during decompress detection, and it will become < 0 when length is more than 2G. Furthermore, during decompressing len as int is used for inbuf count, that has problem too. Change len to long, that should be ok as on 32 bit platform long is 32bits. Tested with following compressed initramfs image as root with kexec. gzip, bzip2, xz, lzma, lzop, lz4. run time for populate_rootfs(): size name Nehalem-EX Westmere-EX Ivybridge-EX 9034400256 root_img : 26s 24s 30s 3561095057 root_img.lz4 : 28s 27s 27s 3459554629 root_img.lzo : 29s 29s 28s 3219399480 root_img.gz : 64s 62s 49s 2251594592 root_img.xz : 262s 260s 183s 2226366598 root_img.lzma: 386s 376s 277s 2901482513 root_img.bz2 : 635s 599s Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Rashika Kheria <rashika.kheria@gmail.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Kyungsik Lee <kyungsik.lee@lge.com> Cc: P J P <ppandit@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Cc: "Daniel M. Weeks" <dan@danweeks.net> Cc: Alexandre Courbot <acourbot@nvidia.com> Cc: Jan Beulich <JBeulich@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:23:14 +08:00
static long __init compr_flush(void *window, unsigned long outcnt)
{
initramfs: support initramfs that is bigger than 2GiB Now with 64bit bzImage and kexec tools, we support ramdisk that size is bigger than 2g, as we could put it above 4G. Found compressed initramfs image could not be decompressed properly. It turns out that image length is int during decompress detection, and it will become < 0 when length is more than 2G. Furthermore, during decompressing len as int is used for inbuf count, that has problem too. Change len to long, that should be ok as on 32 bit platform long is 32bits. Tested with following compressed initramfs image as root with kexec. gzip, bzip2, xz, lzma, lzop, lz4. run time for populate_rootfs(): size name Nehalem-EX Westmere-EX Ivybridge-EX 9034400256 root_img : 26s 24s 30s 3561095057 root_img.lz4 : 28s 27s 27s 3459554629 root_img.lzo : 29s 29s 28s 3219399480 root_img.gz : 64s 62s 49s 2251594592 root_img.xz : 262s 260s 183s 2226366598 root_img.lzma: 386s 376s 277s 2901482513 root_img.bz2 : 635s 599s Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Rashika Kheria <rashika.kheria@gmail.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Kyungsik Lee <kyungsik.lee@lge.com> Cc: P J P <ppandit@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Cc: "Daniel M. Weeks" <dan@danweeks.net> Cc: Alexandre Courbot <acourbot@nvidia.com> Cc: Jan Beulich <JBeulich@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:23:14 +08:00
long written = sys_write(crd_outfd, window, outcnt);
if (written != outcnt) {
if (decompress_error == 0)
printk(KERN_ERR
initramfs: support initramfs that is bigger than 2GiB Now with 64bit bzImage and kexec tools, we support ramdisk that size is bigger than 2g, as we could put it above 4G. Found compressed initramfs image could not be decompressed properly. It turns out that image length is int during decompress detection, and it will become < 0 when length is more than 2G. Furthermore, during decompressing len as int is used for inbuf count, that has problem too. Change len to long, that should be ok as on 32 bit platform long is 32bits. Tested with following compressed initramfs image as root with kexec. gzip, bzip2, xz, lzma, lzop, lz4. run time for populate_rootfs(): size name Nehalem-EX Westmere-EX Ivybridge-EX 9034400256 root_img : 26s 24s 30s 3561095057 root_img.lz4 : 28s 27s 27s 3459554629 root_img.lzo : 29s 29s 28s 3219399480 root_img.gz : 64s 62s 49s 2251594592 root_img.xz : 262s 260s 183s 2226366598 root_img.lzma: 386s 376s 277s 2901482513 root_img.bz2 : 635s 599s Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Rashika Kheria <rashika.kheria@gmail.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Kyungsik Lee <kyungsik.lee@lge.com> Cc: P J P <ppandit@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Cc: "Daniel M. Weeks" <dan@danweeks.net> Cc: Alexandre Courbot <acourbot@nvidia.com> Cc: Jan Beulich <JBeulich@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:23:14 +08:00
"RAMDISK: incomplete write (%ld != %ld)\n",
written, outcnt);
decompress_error = 1;
return -1;
}
return outcnt;
}
static void __init error(char *x)
{
printk(KERN_ERR "%s\n", x);
exit_code = 1;
decompress_error = 1;
}
static int __init crd_load(int in_fd, int out_fd, decompress_fn deco)
{
int result;
crd_infd = in_fd;
crd_outfd = out_fd;
if (!deco) {
pr_emerg("Invalid ramdisk decompression routine. "
"Select appropriate config option.\n");
panic("Could not decompress initial ramdisk image.");
}
result = deco(NULL, 0, compr_fill, compr_flush, NULL, NULL, error);
if (decompress_error)
result = 1;
return result;
}