diff options
Diffstat (limited to 'init')
| -rw-r--r-- | init/Kconfig | 43 | ||||
| -rw-r--r-- | init/Makefile | 1 | ||||
| -rw-r--r-- | init/do_mounts.c | 82 | ||||
| -rw-r--r-- | init/do_mounts.h | 28 | ||||
| -rw-r--r-- | init/do_mounts_initrd.c | 44 | ||||
| -rw-r--r-- | init/do_mounts_md.c | 304 | ||||
| -rw-r--r-- | init/do_mounts_rd.c | 101 | ||||
| -rw-r--r-- | init/init_task.c | 6 | ||||
| -rw-r--r-- | init/initramfs.c | 148 | ||||
| -rw-r--r-- | init/main.c | 60 | ||||
| -rw-r--r-- | init/noinitramfs.c | 8 |
11 files changed, 206 insertions, 619 deletions
diff --git a/init/Kconfig b/init/Kconfig index 0498af567f70..d6a0b31b13dc 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -191,13 +191,16 @@ config HAVE_KERNEL_LZO config HAVE_KERNEL_LZ4 bool +config HAVE_KERNEL_ZSTD + bool + config HAVE_KERNEL_UNCOMPRESSED bool choice prompt "Kernel compression mode" default KERNEL_GZIP - depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4 || HAVE_KERNEL_UNCOMPRESSED + depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4 || HAVE_KERNEL_ZSTD || HAVE_KERNEL_UNCOMPRESSED help The linux kernel is a kind of self-extracting executable. Several compression algorithms are available, which differ @@ -276,6 +279,16 @@ config KERNEL_LZ4 is about 8% bigger than LZO. But the decompression speed is faster than LZO. +config KERNEL_ZSTD + bool "ZSTD" + depends on HAVE_KERNEL_ZSTD + help + ZSTD is a compression algorithm targeting intermediate compression + with fast decompression speed. It will compress better than GZIP and + decompress around the same speed as LZO, but slower than LZ4. You + will need at least 192 KB RAM or more for booting. The zstd command + line tool is required for compression. + config KERNEL_UNCOMPRESSED bool "None" depends on HAVE_KERNEL_UNCOMPRESSED @@ -492,8 +505,23 @@ config HAVE_SCHED_AVG_IRQ depends on SMP config SCHED_THERMAL_PRESSURE - bool "Enable periodic averaging of thermal pressure" + bool + default y if ARM && ARM_CPU_TOPOLOGY + default y if ARM64 depends on SMP + depends on CPU_FREQ_THERMAL + help + Select this option to enable thermal pressure accounting in the + scheduler. Thermal pressure is the value conveyed to the scheduler + that reflects the reduction in CPU compute capacity resulted from + thermal throttling. Thermal throttling occurs when the performance of + a CPU is capped due to high operating temperatures. + + If selected, the scheduler will be able to balance tasks accordingly, + i.e. put less load on throttled CPUs than on non/less throttled ones. + + This requires the architecture to implement + arch_set_thermal_pressure() and arch_get_thermal_pressure(). config BSD_PROCESS_ACCT bool "BSD Process Accounting" @@ -1885,9 +1913,8 @@ config SLAB_MERGE_DEFAULT command line. config SLAB_FREELIST_RANDOM - default n + bool "Randomize slab freelist" depends on SLAB || SLUB - bool "SLAB freelist randomization" help Randomizes the freelist order used on creating new pages. This security feature reduces the predictability of the kernel slab @@ -1895,12 +1922,14 @@ config SLAB_FREELIST_RANDOM config SLAB_FREELIST_HARDENED bool "Harden slab freelist metadata" - depends on SLUB + depends on SLAB || SLUB help Many kernel heap attacks try to target slab cache metadata and other infrastructure. This options makes minor performance sacrifices to harden the kernel slab allocator against common - freelist exploit methods. + freelist exploit methods. Some slab implementations have more + sanity-checking than others. This option is most effective with + CONFIG_SLUB. config SHUFFLE_PAGE_ALLOCATOR bool "Page allocator randomization" @@ -1957,7 +1986,7 @@ config MMAP_ALLOW_UNINITIALIZED userspace. Since that isn't generally a problem on no-MMU systems, it is normally safe to say Y here. - See Documentation/nommu-mmap.txt for more information. + See Documentation/mm/nommu-mmap.rst for more information. config SYSTEM_DATA_VERIFICATION def_bool n diff --git a/init/Makefile b/init/Makefile index 57499b1ff471..6bc37f64b361 100644 --- a/init/Makefile +++ b/init/Makefile @@ -18,7 +18,6 @@ obj-y += init_task.o mounts-y := do_mounts.o mounts-$(CONFIG_BLK_DEV_RAM) += do_mounts_rd.o mounts-$(CONFIG_BLK_DEV_INITRD) += do_mounts_initrd.o -mounts-$(CONFIG_BLK_DEV_MD) += do_mounts_md.o # dependencies on generated files need to be listed explicitly $(obj)/version.o: include/generated/compile.h diff --git a/init/do_mounts.c b/init/do_mounts.c index 29d326b6c29d..b5f9604d0c98 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -23,12 +23,11 @@ #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 __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]; @@ -38,7 +37,7 @@ dev_t ROOT_DEV; static int __init load_ramdisk(char *str) { - rd_doload = simple_strtol(str,NULL,0) & 3; + pr_warn("ignoring the deprecated load_ramdisk= option\n"); return 1; } __setup("load_ramdisk=", load_ramdisk); @@ -396,20 +395,20 @@ static int __init do_mount_root(const char *name, const char *fs, int ret; if (data) { - /* do_mount() requires a full page as fifth argument */ + /* 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. do_mount() will make sure it's terminated */ + /* zero-pad. init_mount() will make sure it's terminated */ strncpy(data_page, data, PAGE_SIZE); } - ret = do_mount(name, "/root", fs, flags, data_page); + ret = init_mount(name, "/root", fs, flags, data_page); if (ret) goto out; - ksys_chdir("/root"); + init_chdir("/root"); s = current->fs->pwd.dentry->d_sb; ROOT_DEV = s->s_dev; printk(KERN_INFO @@ -552,66 +551,20 @@ static int __init mount_cifs_root(void) } #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 = ksys_open("/dev/root", O_RDWR | O_NDELAY, 0); - if (fd >= 0) { - ksys_ioctl(fd, FDEJECT, 0); - ksys_close(fd); - } - printk(KERN_NOTICE "VFS: Insert %s and press ENTER\n", buf); - fd = ksys_open("/dev/console", O_RDWR, 0); - if (fd >= 0) { - ksys_ioctl(fd, TCGETS, (long)&termios); - termios.c_lflag &= ~ICANON; - ksys_ioctl(fd, TCSETSF, (long)&termios); - ksys_read(fd, &c, 1); - termios.c_lflag |= ICANON; - ksys_ioctl(fd, TCSETSF, (long)&termios); - ksys_close(fd); - } -} -#endif - void __init mount_root(void) { #ifdef CONFIG_ROOT_NFS if (ROOT_DEV == Root_NFS) { - if (mount_nfs_root()) - return; - - printk(KERN_ERR "VFS: Unable to mount root fs via NFS, trying floppy.\n"); - ROOT_DEV = Root_FD0; + if (!mount_nfs_root()) + printk(KERN_ERR "VFS: Unable to mount root fs via NFS.\n"); + return; } #endif #ifdef CONFIG_CIFS_ROOT if (ROOT_DEV == Root_CIFS) { - if (mount_cifs_root()) - return; - - printk(KERN_ERR "VFS: Unable to mount root fs via SMB, 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"); + if (!mount_cifs_root()) + printk(KERN_ERR "VFS: Unable to mount root fs via SMB.\n"); + return; } #endif #ifdef CONFIG_BLOCK @@ -630,8 +583,6 @@ void __init mount_root(void) */ void __init prepare_namespace(void) { - int is_floppy; - if (root_delay) { printk(KERN_INFO "Waiting %d sec before mounting root device...\n", root_delay); @@ -674,16 +625,11 @@ void __init prepare_namespace(void) 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(); - do_mount(".", "/", NULL, MS_MOVE, NULL); - ksys_chroot("."); + init_mount(".", "/", NULL, MS_MOVE, NULL); + init_chroot("."); } static bool is_tmpfs; diff --git a/init/do_mounts.h b/init/do_mounts.h index 0bb0806de4ce..7a29ac3e427b 100644 --- a/init/do_mounts.h +++ b/init/do_mounts.h @@ -8,26 +8,16 @@ #include <linux/mount.h> #include <linux/major.h> #include <linux/root_dev.h> +#include <linux/init_syscalls.h> -void change_floppy(char *fmt, ...); void mount_block_root(char *name, int flags); void mount_root(void); extern int root_mountflags; -static inline int create_dev(char *name, dev_t dev) +static inline __init int create_dev(char *name, dev_t dev) { - ksys_unlink(name); - return ksys_mknod(name, S_IFBLK|0600, new_encode_dev(dev)); -} - -static inline u32 bstat(char *name) -{ - struct kstat stat; - if (vfs_stat(name, &stat) != 0) - return 0; - if (!S_ISBLK(stat.mode)) - return 0; - return stat.rdev; + init_unlink(name); + return init_mknod(name, S_IFBLK | 0600, new_encode_dev(dev)); } #ifdef CONFIG_BLK_DEV_RAM @@ -51,13 +41,3 @@ bool __init initrd_load(void); static inline bool initrd_load(void) { return false; } #endif - -#ifdef CONFIG_BLK_DEV_MD - -void md_run_setup(void); - -#else - -static inline void md_run_setup(void) {} - -#endif diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index d72beda824aa..533d81ed74d4 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -45,25 +45,20 @@ static int __init early_initrdmem(char *p) } early_param("initrdmem", early_initrdmem); -/* - * This is here as the initrd keyword has been in use since 11/2018 - * on ARM, PowerPC, and MIPS. - * It should not be; it is reserved for bootloaders. - */ static int __init early_initrd(char *p) { return early_initrdmem(p); } early_param("initrd", early_initrd); -static int init_linuxrc(struct subprocess_info *info, struct cred *new) +static int __init init_linuxrc(struct subprocess_info *info, struct cred *new) { ksys_unshare(CLONE_FS | CLONE_FILES); console_on_rootfs(); /* move initrd over / and chdir/chroot in initrd root */ - ksys_chdir("/root"); - do_mount(".", "/", NULL, MS_MOVE, NULL); - ksys_chroot("."); + init_chdir("/root"); + init_mount(".", "/", NULL, MS_MOVE, NULL); + init_chroot("."); ksys_setsid(); return 0; } @@ -75,12 +70,14 @@ static void __init handle_initrd(void) extern char *envp_init[]; int error; + pr_warn("using deprecated initrd support, will be removed in 2021.\n"); + real_root_dev = new_encode_dev(ROOT_DEV); create_dev("/dev/root.old", Root_RAM0); /* mount initrd on rootfs' /root */ mount_block_root("/dev/root.old", root_mountflags & ~MS_RDONLY); - ksys_mkdir("/old", 0700); - ksys_chdir("/old"); + init_mkdir("/old", 0700); + init_chdir("/old"); /* * In case that a resume from disk is carried out by linuxrc or one of @@ -97,39 +94,30 @@ static void __init handle_initrd(void) current->flags &= ~PF_FREEZER_SKIP; /* move initrd to rootfs' /old */ - do_mount("..", ".", NULL, MS_MOVE, NULL); + init_mount("..", ".", NULL, MS_MOVE, NULL); /* switch root and cwd back to / of rootfs */ - ksys_chroot(".."); + init_chroot(".."); if (new_decode_dev(real_root_dev) == Root_RAM0) { - ksys_chdir("/old"); + init_chdir("/old"); return; } - ksys_chdir("/"); + init_chdir("/"); ROOT_DEV = new_decode_dev(real_root_dev); mount_root(); printk(KERN_NOTICE "Trying to move old root to /initrd ... "); - error = do_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL); + error = init_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL); if (!error) printk("okay\n"); else { - int fd = ksys_open("/dev/root.old", O_RDWR, 0); if (error == -ENOENT) printk("/initrd does not exist. Ignored.\n"); else printk("failed\n"); printk(KERN_NOTICE "Unmounting old root\n"); - ksys_umount("/old", MNT_DETACH); - printk(KERN_NOTICE "Trying to free ramdisk memory ... "); - if (fd < 0) { - error = fd; - } else { - error = ksys_ioctl(fd, BLKFLSBUF, 0); - ksys_close(fd); - } - printk(!error ? "okay\n" : "failed\n"); + init_umount("/old", MNT_DETACH); } } @@ -144,11 +132,11 @@ bool __init initrd_load(void) * mounted in the normal path. */ if (rd_load_image("/initrd.image") && ROOT_DEV != Root_RAM0) { - ksys_unlink("/initrd.image"); + init_unlink("/initrd.image"); handle_initrd(); return true; } } - ksys_unlink("/initrd.image"); + init_unlink("/initrd.image"); return false; } diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c deleted file mode 100644 index b84031528dd4..000000000000 --- a/init/do_mounts_md.c +++ /dev/null @@ -1,304 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/delay.h> -#include <linux/raid/md_u.h> -#include <linux/raid/md_p.h> - -#include "do_mounts.h" - -/* - * When md (and any require personalities) are compiled into the kernel - * (not a module), arrays can be assembles are boot time using with AUTODETECT - * where specially marked partitions are registered with md_autodetect_dev(), - * and with MD_BOOT where devices to be collected are given on the boot line - * with md=..... - * The code for that is here. - */ - -#ifdef CONFIG_MD_AUTODETECT -static int __initdata raid_noautodetect; -#else -static int __initdata raid_noautodetect=1; -#endif -static int __initdata raid_autopart; - -static struct { - int minor; - int partitioned; - int level; - int chunk; - char *device_names; -} md_setup_args[256] __initdata; - -static int md_setup_ents __initdata; - -/* - * Parse the command-line parameters given our kernel, but do not - * actually try to invoke the MD device now; that is handled by - * md_setup_drive after the low-level disk drivers have initialised. - * - * 27/11/1999: Fixed to work correctly with the 2.3 kernel (which - * assigns the task of parsing integer arguments to the - * invoked program now). Added ability to initialise all - * the MD devices (by specifying multiple "md=" lines) - * instead of just one. -- KTK - * 18May2000: Added support for persistent-superblock arrays: - * md=n,0,factor,fault,device-list uses RAID0 for device n - * md=n,-1,factor,fault,device-list uses LINEAR for device n - * md=n,device-list reads a RAID superblock from the devices - * elements in device-list are read by name_to_kdev_t so can be - * a hex number or something like /dev/hda1 /dev/sdb - * 2001-06-03: Dave Cinege <dcinege@psychosis.com> - * Shifted name_to_kdev_t() and related operations to md_set_drive() - * for later execution. Rewrote section to make devfs compatible. - */ -static int __init md_setup(char *str) -{ - int minor, level, factor, fault, partitioned = 0; - char *pername = ""; - char *str1; - int ent; - - if (*str == 'd') { - partitioned = 1; - str++; - } - if (get_option(&str, &minor) != 2) { /* MD Number */ - printk(KERN_WARNING "md: Too few arguments supplied to md=.\n"); - return 0; - } - str1 = str; - for (ent=0 ; ent< md_setup_ents ; ent++) - if (md_setup_args[ent].minor == minor && - md_setup_args[ent].partitioned == partitioned) { - printk(KERN_WARNING "md: md=%s%d, Specified more than once. " - "Replacing previous definition.\n", partitioned?"d":"", minor); - break; - } - if (ent >= ARRAY_SIZE(md_setup_args)) { - printk(KERN_WARNING "md: md=%s%d - too many md initialisations\n", partitioned?"d":"", minor); - return 0; - } - if (ent >= md_setup_ents) - md_setup_ents++; - switch (get_option(&str, &level)) { /* RAID level */ - case 2: /* could be 0 or -1.. */ - if (level == 0 || level == LEVEL_LINEAR) { - if (get_option(&str, &factor) != 2 || /* Chunk Size */ - get_option(&str, &fault) != 2) { - printk(KERN_WARNING "md: Too few arguments supplied to md=.\n"); - return 0; - } - md_setup_args[ent].level = level; - md_setup_args[ent].chunk = 1 << (factor+12); - if (level == LEVEL_LINEAR) - pername = "linear"; - else - pername = "raid0"; - break; - } - /* FALL THROUGH */ - case 1: /* the first device is numeric */ - str = str1; - /* FALL THROUGH */ - case 0: - md_setup_args[ent].level = LEVEL_NONE; - pername="super-block"; - } - - printk(KERN_INFO "md: Will configure md%d (%s) from %s, below.\n", - minor, pername, str); - md_setup_args[ent].device_names = str; - md_setup_args[ent].partitioned = partitioned; - md_setup_args[ent].minor = minor; - - return 1; -} - -static void __init md_setup_drive(void) -{ - int minor, i, ent, partitioned; - dev_t dev; - dev_t devices[MD_SB_DISKS+1]; - - for (ent = 0; ent < md_setup_ents ; ent++) { - int fd; - int err = 0; - char *devname; - mdu_disk_info_t dinfo; - char name[16]; - - minor = md_setup_args[ent].minor; - partitioned = md_setup_args[ent].partitioned; - devname = md_setup_args[ent].device_names; - - sprintf(name, "/dev/md%s%d", partitioned?"_d":"", minor); - if (partitioned) - dev = MKDEV(mdp_major, minor << MdpMinorShift); - else - dev = MKDEV(MD_MAJOR, minor); - create_dev(name, dev); - for (i = 0; i < MD_SB_DISKS && devname != NULL; i++) { - char *p; - char comp_name[64]; - u32 rdev; - - p = strchr(devname, ','); - if (p) - *p++ = 0; - - dev = name_to_dev_t(devname); - if (strncmp(devname, "/dev/", 5) == 0) - devname += 5; - snprintf(comp_name, 63, "/dev/%s", devname); - rdev = bstat(comp_name); - if (rdev) - dev = new_decode_dev(rdev); - if (!dev) { - printk(KERN_WARNING "md: Unknown device name: %s\n", devname); - break; - } - - devices[i] = dev; - - devname = p; - } - devices[i] = 0; - - if (!i) - continue; - - printk(KERN_INFO "md: Loading md%s%d: %s\n", - partitioned ? "_d" : "", minor, - md_setup_args[ent].device_names); - - fd = ksys_open(name, 0, 0); - if (fd < 0) { - printk(KERN_ERR "md: open failed - cannot start " - "array %s\n", name); - continue; - } - if (ksys_ioctl(fd, SET_ARRAY_INFO, 0) == -EBUSY) { - printk(KERN_WARNING - "md: Ignoring md=%d, already autodetected. (Use raid=noautodetect)\n", - minor); - ksys_close(fd); - continue; - } - - if (md_setup_args[ent].level != LEVEL_NONE) { - /* non-persistent */ - mdu_array_info_t ainfo; - ainfo.level = md_setup_args[ent].level; - ainfo.size = 0; - ainfo.nr_disks =0; - ainfo.raid_disks =0; - while (devices[ainfo.raid_disks]) - ainfo.raid_disks++; - ainfo.md_minor =minor; - ainfo.not_persistent = 1; - - ainfo.state = (1 << MD_SB_CLEAN); - ainfo.layout = 0; - ainfo.chunk_size = md_setup_args[ent].chunk; - err = ksys_ioctl(fd, SET_ARRAY_INFO, (long)&ainfo); - for (i = 0; !err && i <= MD_SB_DISKS; i++) { - dev = devices[i]; - if (!dev) - break; - dinfo.number = i; - dinfo.raid_disk = i; - dinfo.state = (1<<MD_DISK_ACTIVE)|(1<<MD_DISK_SYNC); - dinfo.major = MAJOR(dev); - dinfo.minor = MINOR(dev); - err = ksys_ioctl(fd, ADD_NEW_DISK, - (long)&dinfo); - } - } else { - /* persistent */ - for (i = 0; i <= MD_SB_DISKS; i++) { - dev = devices[i]; - if (!dev) - break; - dinfo.major = MAJOR(dev); - dinfo.minor = MINOR(dev); - ksys_ioctl(fd, ADD_NEW_DISK, (long)&dinfo); - } - } - if (!err) - err = ksys_ioctl(fd, RUN_ARRAY, 0); - if (err) - printk(KERN_WARNING "md: starting md%d failed\n", minor); - else { - /* reread the partition table. - * I (neilb) and not sure why this is needed, but I cannot - * boot a kernel with devfs compiled in from partitioned md - * array without it - */ - ksys_close(fd); - fd = ksys_open(name, 0, 0); - ksys_ioctl(fd, BLKRRPART, 0); - } - ksys_close(fd); - } -} - -static int __init raid_setup(char *str) -{ - int len, pos; - - len = strlen(str) + 1; - pos = 0; - - while (pos < len) { - char *comma = strchr(str+pos, ','); - int wlen; - if (comma) - wlen = (comma-str)-pos; - else wlen = (len-1)-pos; - - if (!strncmp(str, "noautodetect", wlen)) - raid_noautodetect = 1; - if (!strncmp(str, "autodetect", wlen)) - raid_noautodetect = 0; - if (strncmp(str, "partitionable", wlen)==0) - raid_autopart = 1; - if (strncmp(str, "part", wlen)==0) - raid_autopart = 1; - pos += wlen+1; - } - return 1; -} - -__setup("raid=", raid_setup); -__setup("md=", md_setup); - -static void __init autodetect_raid(void) -{ - int fd; - - /* - * Since we don't want to detect and use half a raid array, we need to - * wait for the known devices to complete their probing - */ - printk(KERN_INFO "md: Waiting for all devices to be available before autodetect\n"); - printk(KERN_INFO "md: If you don't use raid, use raid=noautodetect\n"); - - wait_for_device_probe(); - - fd = ksys_open("/dev/md0", 0, 0); - if (fd >= 0) { - ksys_ioctl(fd, RAID_AUTORUN, raid_autopart); - ksys_close(fd); - } -} - -void __init md_run_setup(void) -{ - create_dev("/dev/md0", MKDEV(MD_MAJOR, 0)); - - if (raid_noautodetect) - printk(KERN_INFO "md: Skipping autodetection of RAID arrays. (raid=autodetect will force)\n"); - else - autodetect_raid(); - md_setup_drive(); -} diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index 32fb049d18f9..ac021ae6e6fa 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -14,12 +14,12 @@ #include <linux/decompress/generic.h> - -int __initdata rd_prompt = 1;/* 1 = prompt for RAM disk, 0 = don't prompt */ +static struct file *in_file, *out_file; +static loff_t in_pos, out_pos; static int __init prompt_ramdisk(char *str) { - rd_prompt = simple_strtol(str,NULL,0) & 1; + pr_warn("ignoring the deprecated prompt_ramdisk= option\n"); return 1; } __setup("prompt_ramdisk=", prompt_ramdisk); @@ -33,7 +33,7 @@ static int __init ramdisk_start_setup(char *str) } __setup("ramdisk_start=", ramdisk_start_setup); -static int __init crd_load(int in_fd, int out_fd, decompress_fn deco); +static int __init crd_load(decompress_fn deco); /* * This routine tries to find a RAM disk image to load, and returns the @@ -55,7 +55,8 @@ static int __init crd_load(int in_fd, int out_fd, decompress_fn deco); * lz4 */ static int __init -identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) +identify_ramdisk_image(struct file *file, loff_t pos, + decompress_fn *decompressor) { const int size = 512; struct minix_super_block *minixsb; @@ -66,6 +67,7 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) unsigned char *buf; const char *compress_name; unsigned long n; + int start_block = rd_image_start; buf = kmalloc(size, GFP_KERNEL); if (!buf) @@ -80,8 +82,8 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) /* * Read block 0 to test for compressed kernel */ - ksys_lseek(fd, start_block * BLOCK_SIZE, 0); - ksys_read(fd, buf, size); + pos = start_block * BLOCK_SIZE; + kernel_read(file, buf, size, &pos); *decompressor = decompress_method(buf, size, &compress_name); if (compress_name) { @@ -126,8 +128,8 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) /* * Read 512 bytes further to check if cramfs is padded */ - ksys_lseek(fd, start_block * BLOCK_SIZE + 0x200, 0); - ksys_read(fd, buf, size); + pos = start_block * BLOCK_SIZE + 0x200; + kernel_read(file, buf, size, &pos); if (cramfsb->magic == CRAMFS_MAGIC) { printk(KERN_NOTICE @@ -140,8 +142,8 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) /* * Read block 1 to test for minix and ext2 superblock */ - ksys_lseek(fd, (start_block+1) * BLOCK_SIZE, 0); - ksys_read(fd, buf, size); + pos = (start_block + 1) * BLOCK_SIZE; + kernel_read(file, buf, size, &pos); /* Try minix */ if (minixsb->s_magic == MINIX_SUPER_MAGIC || @@ -168,17 +170,24 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) start_block); done: - ksys_lseek(fd, start_block * BLOCK_SIZE, 0); kfree(buf); return nblocks; } +static unsigned long nr_blocks(struct file *file) +{ + struct inode *inode = file->f_mapping->host; + + if (!S_ISBLK(inode->i_mode)) + return 0; + return i_size_read(inode) >> 10; +} + int __init rd_load_image(char *from) { int res = 0; - int in_fd, out_fd; unsigned long rd_blocks, devblocks; - int nblocks, i, disk; + int nblocks, i; char *buf = NULL; unsigned short rotate = 0; decompress_fn decompressor = NULL; @@ -186,20 +195,21 @@ int __init rd_load_image(char *from) char rotator[4] = { '|' , '/' , '-' , '\\' }; #endif - out_fd = ksys_open("/dev/ram", O_RDWR, 0); - if (out_fd < 0) + out_file = filp_open("/dev/ram", O_RDWR, 0); + if (IS_ERR(out_file)) goto out; - in_fd = ksys_open(from, O_RDONLY, 0); - if (in_fd < 0) + in_file = filp_open(from, O_RDONLY, 0); + if (IS_ERR(in_file)) goto noclose_input; - nblocks = identify_ramdisk_image(in_fd, rd_image_start, &decompressor); + in_pos = rd_image_start * BLOCK_SIZE; + nblocks = identify_ramdisk_image(in_file, in_pos, &decompressor); if (nblocks < 0) goto done; if (nblocks == 0) { - if (crd_load(in_fd, out_fd, decompressor) == 0) + if (crd_load(decompressor) == 0) goto successful_load; goto done; } @@ -208,11 +218,7 @@ int __init rd_load_image(char *from) * NOTE NOTE: nblocks is not actually blocks but * the number of kibibytes of data to load into a ramdisk. */ - if (ksys_ioctl(out_fd, BLKGETSIZE, (unsigned long)&rd_blocks) < 0) - rd_blocks = 0; - else - rd_blocks >>= 1; - + rd_blocks = nr_blocks(out_file); if (nblocks > rd_blocks) { printk("RAMDISK: image too big! (%dKiB/%ldKiB)\n", nblocks, rd_blocks); @@ -222,13 +228,10 @@ int __init rd_load_image(char *from) /* * OK, time to copy in the data */ - if (ksys_ioctl(in_fd, BLKGETSIZE, (unsigned long)&devblocks) < 0) - devblocks = 0; - else - devblocks >>= 1; - if (strcmp(from, "/initrd.image") == 0) devblocks = nblocks; + else + devblocks = nr_blocks(in_file); if (devblocks == 0) { printk(KERN_ERR "RAMDISK: could not determine device size\n"); @@ -243,24 +246,15 @@ int __init rd_load_image(char *from) 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++) { + for (i = 0; i < nblocks; i++) { if (i && (i % devblocks == 0)) { - pr_cont("done disk #%d.\n", disk++); + pr_cont("done disk #1.\n"); rotate = 0; - if (ksys_close(in_fd)) { - printk("Error closing the disk.\n"); - goto noclose_input; - } - change_floppy("disk #%d", disk); - in_fd = ksys_open(from, O_RDONLY, 0); - if (in_fd < 0) { - printk("Error opening disk.\n"); - goto noclose_input; - } - printk("Loading disk #%d... ", disk); + fput(in_file); + break; } - ksys_read(in_fd, buf, BLOCK_SIZE); - ksys_write(out_fd, buf, BLOCK_SIZE); + kernel_read(in_file, buf, BLOCK_SIZE, &in_pos); + kernel_write(out_file, buf, BLOCK_SIZE, &out_pos); #if !defined(CONFIG_S390) if (!(i % 16)) { pr_cont("%c\b", rotator[rotate & 0x3]); @@ -273,19 +267,17 @@ int __init rd_load_image(char *from) successful_load: res = 1; done: - ksys_close(in_fd); + fput(in_file); noclose_input: - ksys_close(out_fd); + fput(out_file); out: kfree(buf); - ksys_unlink("/dev/ram"); + init_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"); @@ -293,11 +285,10 @@ int __init rd_load_disk(int n) static int exit_code; static int decompress_error; -static int crd_infd, crd_outfd; static long __init compr_fill(void *buf, unsigned long len) { - long r = ksys_read(crd_infd, buf, len); + long r = kernel_read(in_file, buf, len, &in_pos); if (r < 0) printk(KERN_ERR "RAMDISK: error while reading compressed data"); else if (r == 0) @@ -307,7 +298,7 @@ static long __init compr_fill(void *buf, unsigned long len) static long __init compr_flush(void *window, unsigned long outcnt) { - long written = ksys_write(crd_outfd, window, outcnt); + long written = kernel_write(out_file, window, outcnt, &out_pos); if (written != outcnt) { if (decompress_error == 0) printk(KERN_ERR @@ -326,11 +317,9 @@ static void __init error(char *x) decompress_error = 1; } -static int __init crd_load(int in_fd, int out_fd, decompress_fn deco) +static int __init crd_load(decompress_fn deco) { int result; - crd_infd = in_fd; - crd_outfd = out_fd; if (!deco) { pr_emerg("Invalid ramdisk decompression routine. " diff --git a/init/init_task.c b/init/init_task.c index ab6173f8e6a8..f6889fce64af 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -155,7 +155,8 @@ struct task_struct init_task .trc_holdout_list = LIST_HEAD_INIT(init_task.trc_holdout_list), #endif #ifdef CONFIG_CPUSETS - .mems_allowed_seq = SEQCNT_ZERO(init_task.mems_allowed_seq), + .mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq, + &init_task.alloc_lock), #endif #ifdef CONFIG_RT_MUTEXES .pi_waiters = RB_ROOT_CACHED, @@ -205,6 +206,9 @@ struct task_struct init_task #ifdef CONFIG_SECURITY .security = NULL, #endif +#ifdef CONFIG_SECCOMP + .seccomp = { .filter_count = ATOMIC_INIT(0) }, +#endif }; EXPORT_SYMBOL(init_task); diff --git a/init/initramfs.c b/init/initramfs.c index 7a38012e1af7..e6dbfb767057 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -11,14 +11,17 @@ #include <linux/utime.h> #include <linux/file.h> #include <linux/memblock.h> +#include <linux/namei.h> +#include <linux/init_syscalls.h> -static ssize_t __init xwrite(int fd, const char *p, size_t count) +static ssize_t __init xwrite(struct file *file, const char *p, size_t count, + loff_t *pos) { ssize_t out = 0; /* sys_write only can write MAX_RW_COUNT aka 2G-4K bytes at most */ while (count) { - ssize_t rv = ksys_write(fd, p, count); + ssize_t rv = kernel_write(file, p, count, pos); if (rv < 0) { if (rv == -EINTR || rv == -EAGAIN) @@ -108,8 +111,7 @@ static long __init do_utime(char *filename, time64_t mtime) t[0].tv_nsec = 0; t[1].tv_sec = mtime; t[1].tv_nsec = 0; - - return do_utimes(AT_FDCWD, filename, t, AT_SYMLINK_NOFOLLOW); + return init_utimes(filename, t); } static __initdata LIST_HEAD(dir_list); @@ -200,7 +202,6 @@ static inline void __init eat(unsigned n) byte_count -= n; } -static __initdata char *vcollected; static __initdata char *collected; static long remains __initdata; static __initdata char *collect; @@ -296,11 +297,12 @@ static void __init clean_path(char *path, umode_t fmode) { struct kstat st; - if (!vfs_lstat(path, &st) && (st.mode ^ fmode) & S_IFMT) { + if (init_stat(path, &st, AT_SYMLINK_NOFOLLOW) && + (st.mode ^ fmode) & S_IFMT) { if (S_ISDIR(st.mode)) - ksys_rmdir(path); + init_rmdir(path); else - ksys_unlink(path); + init_unlink(path); } } @@ -310,13 +312,14 @@ static int __init maybe_link(void) char *old = find_link(major, minor, ino, mode, collected); if (old) { clean_path(collected, 0); - return (ksys_link(old, collected) < 0) ? -1 : 1; + return (init_link(old, collected) < 0) ? -1 : 1; } } return 0; } -static __initdata int wfd; +static __initdata struct file *wfile; +static __initdata loff_t wfile_pos; static int __init do_name(void) { @@ -333,28 +336,28 @@ static int __init do_name(void) int openflags = O_WRONLY|O_CREAT; if (ml != 1) openflags |= O_TRUNC; - wfd = ksys_open(collected, openflags, mode); - - if (wfd >= 0) { - ksys_fchown(wfd, uid, gid); - ksys_fchmod(wfd, mode); - if (body_len) - ksys_ftruncate(wfd, body_len); - vcollected = kstrdup(collected, GFP_KERNEL); - state = CopyFile; - } + wfile = filp_open(collected, openflags, mode); + if (IS_ERR(wfile)) + return 0; + wfile_pos = 0; + + vfs_fchown(wfile, uid, gid); + vfs_fchmod(wfile, mode); + if (body_len) + vfs_truncate(&wfile->f_path, body_len); + state = CopyFile; } } else if (S_ISDIR(mode)) { - ksys_mkdir(collected, mode); - ksys_chown(collected, uid, gid); - ksys_chmod(collected, mode); + init_mkdir(collected, mode); + init_chown(collected, uid, gid, 0); + init_chmod(collected, mode); dir_add(collected, mtime); } else if (S_ISBLK(mode) || S_ISCHR(mode) || S_ISFIFO(mode) || S_ISSOCK(mode)) { if (maybe_link() == 0) { - ksys_mknod(collected, mode, rdev); - ksys_chown(collected, uid, gid); - ksys_chmod(collected, mode); + init_mknod(collected, mode, rdev); + init_chown(collected, uid, gid, 0); + init_chmod(collected, mode); do_utime(collected, mtime); } } @@ -364,16 +367,20 @@ static int __init do_name(void) static int __init do_copy(void) { if (byte_count >= body_len) { - if (xwrite(wfd, victim, body_len) != body_len) + struct timespec64 t[2] = { }; + if (xwrite(wfile, victim, body_len, &wfile_pos) != body_len) error("write error"); - ksys_close(wfd); - do_utime(vcollected, mtime); - kfree(vcollected); + + t[0].tv_sec = mtime; + t[1].tv_sec = mtime; + vfs_utimes(&wfile->f_path, t); + + fput(wfile); eat(body_len); state = SkipIt; return 0; } else { - if (xwrite(wfd, victim, byte_count) != byte_count) + if (xwrite(wfile, victim, byte_count, &wfile_pos) != byte_count) error("write error"); body_len -= byte_count; eat(byte_count); @@ -385,8 +392,8 @@ static int __init do_symlink(void) { collected[N_ALIGN(name_len) + body_len] = '\0'; clean_path(collected, 0); - ksys_symlink(collected + N_ALIGN(name_len), collected); - ksys_lchown(collected, uid, gid); + init_symlink(collected + N_ALIGN(name_len), collected); + init_chown(collected, uid, gid, AT_SYMLINK_NOFOLLOW); do_utime(collected, mtime); state = SkipIt; next_state = Reset; @@ -572,82 +579,26 @@ static inline bool kexec_free_initrd(void) #endif /* CONFIG_KEXEC_CORE */ #ifdef CONFIG_BLK_DEV_RAM -#define BUF_SIZE 1024 -static void __init clean_rootfs(void) -{ - int fd; - void *buf; - struct linux_dirent64 *dirp; - int num; - - fd = ksys_open("/", O_RDONLY, 0); - WARN_ON(fd < 0); - if (fd < 0) - return; - buf = kzalloc(BUF_SIZE, GFP_KERNEL); - WARN_ON(!buf); - if (!buf) { - ksys_close(fd); - return; - } - - dirp = buf; - num = ksys_getdents64(fd, dirp, BUF_SIZE); - while (num > 0) { - while (num > 0) { - struct kstat st; - int ret; - - ret = vfs_lstat(dirp->d_name, &st); - WARN_ON_ONCE(ret); - if (!ret) { - if (S_ISDIR(st.mode)) - ksys_rmdir(dirp->d_name); - else - ksys_unlink(dirp->d_name); - } - - num -= dirp->d_reclen; - dirp = (void *)dirp + dirp->d_reclen; - } - dirp = buf; - memset(buf, 0, BUF_SIZE); - num = ksys_getdents64(fd, dirp, BUF_SIZE); - } - - ksys_close(fd); - kfree(buf); -} -#else -static inline void clean_rootfs(void) -{ -} -#endif /* CONFIG_BLK_DEV_RAM */ - -#ifdef CONFIG_BLK_DEV_RAM static void __init populate_initrd_image(char *err) { ssize_t written; - int fd; + struct file *file; + loff_t pos = 0; unpack_to_rootfs(__initramfs_start, __initramfs_size); printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n", err); - fd = ksys_open("/initrd.image", O_WRONLY | O_CREAT, 0700); - if (fd < 0) + file = filp_open("/initrd.image", O_WRONLY | O_CREAT, 0700); + if (IS_ERR(file)) return; - written = xwrite(fd, (char *)initrd_start, initrd_end - initrd_start); + written = xwrite(file, (char *)initrd_start, initrd_end - initrd_start, + &pos); if (written != initrd_end - initrd_start) pr_err("/initrd.image: incomplete write (%zd != %ld)\n", written, initrd_end - initrd_start); - ksys_close(fd); -} -#else -static void __init populate_initrd_image(char *err) -{ - printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err); + fput(file); } #endif /* CONFIG_BLK_DEV_RAM */ @@ -668,8 +619,11 @@ static int __init populate_rootfs(void) err = unpack_to_rootfs((char *)initrd_start, initrd_end - initrd_start); if (err) { - clean_rootfs(); +#ifdef CONFIG_BLK_DEV_RAM populate_initrd_image(err); +#else + printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err); +#endif } done: diff --git a/init/main.c b/init/main.c index 0ead83e86b5a..ae78fb68d231 100644 --- a/init/main.c +++ b/init/main.c @@ -96,6 +96,7 @@ #include <linux/jump_label.h> #include <linux/mem_encrypt.h> #include <linux/kcsan.h> +#include <linux/init_syscalls.h> #include <asm/io.h> #include <asm/bugs.h> @@ -154,7 +155,7 @@ static bool initargs_found; #endif static char *execute_command; -static char *ramdisk_execute_command; +static char *ramdisk_execute_command = "/init"; /* * Used to generate warnings if static_key manipulation functions are used @@ -387,8 +388,6 @@ static int __init bootconfig_params(char *param, char *val, { if (strcmp(param, "bootconfig") == 0) { bootconfig_found = true; - } else if (strcmp(param, "--") == 0) { - initargs_found = true; } return 0; } @@ -399,19 +398,23 @@ static void __init setup_boot_config(const char *cmdline) const char *msg; int pos; u32 size, csum; - char *data, *copy; + char *data, *copy, *err; int ret; /* Cut out the bootconfig data even if we have no bootconfig option */ data = get_boot_config_from_initrd(&size, &csum); strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE); - parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL, - bootconfig_params); + err = parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL, + bootconfig_params); - if (!bootconfig_found) + if (IS_ERR(err) || !bootconfig_found) return; + /* parse_args() stops at '--' and returns an address */ + if (err) + initargs_found = true; + if (!data) { pr_err("'bootconfig' found on command line, but no bootconfig found\n"); return; @@ -779,14 +782,16 @@ static void __init report_meminit(void) { const char *stack; - if (IS_ENABLED(CONFIG_INIT_STACK_ALL)) - stack = "all"; + if (IS_ENABLED(CONFIG_INIT_STACK_ALL_PATTERN)) + stack = "all(pattern)"; + else if (IS_ENABLED(CONFIG_INIT_STACK_ALL_ZERO)) + stack = "all(zero)"; else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL)) - stack = "byref_all"; + stack = "byref_all(zero)"; else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF)) - stack = "byref"; + stack = "byref(zero)"; else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_USER)) - stack = "__user"; + stack = "__user(zero)"; else stack = "off"; @@ -827,7 +832,7 @@ void __init __weak arch_call_rest_init(void) rest_init(); } -asmlinkage __visible void __init start_kernel(void) +asmlinkage __visible void __init __no_sanitize_address start_kernel(void) { char *command_line; char *after_dashes; @@ -1329,9 +1334,7 @@ static int run_init_process(const char *init_filename) pr_debug(" with environment:\n"); for (p = envp_init; *p; p++) pr_debug(" %s\n", *p); - return do_execve(getname_kernel(init_filename), - (const char __user *const __user *)argv_init, - (const char __user *const __user *)envp_init); + return kernel_execve(init_filename, argv_init, envp_init); } static int try_to_run_init_process(const char *init_filename) @@ -1457,15 +1460,19 @@ static int __ref kernel_init(void *unused) "See Linux Documentation/admin-guide/init.rst for guidance."); } -void console_on_rootfs(void) +/* Open /dev/console, for stdin/stdout/stderr, this should never fail */ +void __init console_on_rootfs(void) { - /* Open the /dev/console as stdin, this should never fail */ - if (ksys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) - pr_err("Warning: unable to open an initial console.\n"); + struct file *file = filp_open("/dev/console", O_RDWR, 0); - /* create stdout/stderr */ - (void) ksys_dup(0); - (void) ksys_dup(0); + if (IS_ERR(file)) { + pr_err("Warning: unable to open an initial console.\n"); + return; + } + init_dup(file); + init_dup(file); + init_dup(file); + fput(file); } static noinline void __init kernel_init_freeable(void) @@ -1510,12 +1517,7 @@ static noinline void __init kernel_init_freeable(void) * check if there is an early userspace init. If yes, let it do all * the work */ - - if (!ramdisk_execute_command) - ramdisk_execute_command = "/init"; - - if (ksys_access((const char __user *) - ramdisk_execute_command, 0) != 0) { + if (init_eaccess(ramdisk_execute_command) != 0) { ramdisk_execute_command = NULL; prepare_namespace(); } diff --git a/init/noinitramfs.c b/init/noinitramfs.c index fa9cdfa7101d..3d62b07f3bb9 100644 --- a/init/noinitramfs.c +++ b/init/noinitramfs.c @@ -9,6 +9,7 @@ #include <linux/stat.h> #include <linux/kdev_t.h> #include <linux/syscalls.h> +#include <linux/init_syscalls.h> /* * Create a simple rootfs that is similar to the default initramfs @@ -17,17 +18,16 @@ static int __init default_rootfs(void) { int err; - err = ksys_mkdir((const char __user __force *) "/dev", 0755); + err = init_mkdir("/dev", 0755); if (err < 0) goto out; - err = ksys_mknod((const char __user __force *) "/dev/console", - S_IFCHR | S_IRUSR | S_IWUSR, + err = init_mknod("/dev/console", S_IFCHR | S_IRUSR | S_IWUSR, new_encode_dev(MKDEV(5, 1))); if (err < 0) goto out; - err = ksys_mkdir((const char __user __force *) "/root", 0700); + err = init_mkdir("/root", 0700); if (err < 0) goto out; |