From 4f5b246b37e024955c0fcca0c7f5952089052d1d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 7 Jun 2020 16:18:59 +0200 Subject: md: move the early init autodetect code to drivers/md/ Just like the NFS and CIFS root code this better lives with the driver it is tightly integrated with. Signed-off-by: Christoph Hellwig Acked-by: Song Liu Acked-by: Linus Torvalds --- drivers/md/Makefile | 3 + drivers/md/md-autodetect.c | 315 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 318 insertions(+) create mode 100644 drivers/md/md-autodetect.c (limited to 'drivers') diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 31840f95cd40..6d3e234dc46a 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -43,6 +43,9 @@ obj-$(CONFIG_MD_FAULTY) += faulty.o obj-$(CONFIG_MD_CLUSTER) += md-cluster.o obj-$(CONFIG_BCACHE) += bcache/ obj-$(CONFIG_BLK_DEV_MD) += md-mod.o +ifeq ($(CONFIG_BLK_DEV_MD),y) +obj-y += md-autodetect.o +endif obj-$(CONFIG_BLK_DEV_DM) += dm-mod.o obj-$(CONFIG_BLK_DEV_DM_BUILTIN) += dm-builtin.o obj-$(CONFIG_DM_UNSTRIPED) += dm-unstripe.o diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c new file mode 100644 index 000000000000..fe806f7b9759 --- /dev/null +++ b/drivers/md/md-autodetect.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * 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 + * 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 inline int create_dev(char *name, dev_t dev) +{ + ksys_unlink(name); + return ksys_mknod(name, S_IFBLK|0600, new_encode_dev(dev)); +} + +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++) { + struct kstat stat; + char *p; + char comp_name[64]; + + 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); + if (vfs_stat(comp_name, &stat) == 0 && + S_ISBLK(stat.mode)) + dev = new_decode_dev(stat.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<= 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(); +} -- cgit v1.2.3 From d82fa81c2364a464ae585eed523496aa00909c17 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 6 Jun 2020 15:00:24 +0200 Subject: md: replace the RAID_AUTORUN ioctl with a direct function call Instead of using a spcial RAID_AUTORUN ioctl that only exists for non-modular builds and is only called from the early init code, just call the actual function directly. Signed-off-by: Christoph Hellwig Reviewed-by: NeilBrown Acked-by: Song Liu Acked-by: Linus Torvalds --- drivers/md/md-autodetect.c | 10 ++-------- drivers/md/md.c | 14 +------------- drivers/md/md.h | 3 +++ 3 files changed, 6 insertions(+), 21 deletions(-) (limited to 'drivers') diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c index fe806f7b9759..0eb746211ed5 100644 --- a/drivers/md/md-autodetect.c +++ b/drivers/md/md-autodetect.c @@ -9,6 +9,7 @@ #include #include #include +#include "md.h" /* * When md (and any require personalities) are compiled into the kernel @@ -285,8 +286,6 @@ __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 @@ -295,12 +294,7 @@ static void __init autodetect_raid(void) 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); - } + md_autostart_arrays(raid_autopart); } void __init md_run_setup(void) diff --git a/drivers/md/md.c b/drivers/md/md.c index f567f536b529..6e9a48da4748 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -68,10 +68,6 @@ #include "md-bitmap.h" #include "md-cluster.h" -#ifndef MODULE -static void autostart_arrays(int part); -#endif - /* pers_list is a list of registered personalities protected * by pers_lock. * pers_lock does extra service to protect accesses to @@ -7421,7 +7417,6 @@ static inline bool md_ioctl_valid(unsigned int cmd) case GET_DISK_INFO: case HOT_ADD_DISK: case HOT_REMOVE_DISK: - case RAID_AUTORUN: case RAID_VERSION: case RESTART_ARRAY_RW: case RUN_ARRAY: @@ -7467,13 +7462,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, case RAID_VERSION: err = get_version(argp); goto out; - -#ifndef MODULE - case RAID_AUTORUN: - err = 0; - autostart_arrays(arg); - goto out; -#endif default:; } @@ -9721,7 +9709,7 @@ void md_autodetect_dev(dev_t dev) } } -static void autostart_arrays(int part) +void md_autostart_arrays(int part) { struct md_rdev *rdev; struct detected_devices_node *node_detected_dev; diff --git a/drivers/md/md.h b/drivers/md/md.h index 612814d07d35..37315a3f28e9 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -800,4 +800,7 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio !bio->bi_disk->queue->limits.max_write_zeroes_sectors) mddev->queue->limits.max_write_zeroes_sectors = 0; } + +void md_autostart_arrays(int part); + #endif /* _MD_MD_H */ -- cgit v1.2.3 From a1d6bc018911390274e3904bdd28240cd96ddc54 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 6 Jun 2020 14:56:41 +0200 Subject: md: remove the autoscan partition re-read devfs is long gone, and autoscan works just fine without this these days. Signed-off-by: Christoph Hellwig Reviewed-by: NeilBrown Acked-by: Song Liu Acked-by: Linus Torvalds --- drivers/md/md-autodetect.c | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'drivers') diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c index 0eb746211ed5..6bc9b734eee6 100644 --- a/drivers/md/md-autodetect.c +++ b/drivers/md/md-autodetect.c @@ -240,16 +240,6 @@ static void __init md_setup_drive(void) 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); } } -- cgit v1.2.3 From 1a6a050620e496abf42749a2e1d3882645cc053f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 7 Jun 2020 16:33:01 +0200 Subject: md: remove the kernel version of md_u.h mdp_major can just move to drivers/md/md.h. Signed-off-by: Christoph Hellwig Acked-by: Song Liu Acked-by: Linus Torvalds --- drivers/md/md.h | 1 + include/linux/raid/md_u.h | 13 ------------- 2 files changed, 1 insertion(+), 13 deletions(-) delete mode 100644 include/linux/raid/md_u.h (limited to 'drivers') diff --git a/drivers/md/md.h b/drivers/md/md.h index 37315a3f28e9..6f8fff77ce10 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -801,6 +801,7 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio mddev->queue->limits.max_write_zeroes_sectors = 0; } +extern int mdp_major; void md_autostart_arrays(int part); #endif /* _MD_MD_H */ diff --git a/include/linux/raid/md_u.h b/include/linux/raid/md_u.h deleted file mode 100644 index 8dfec085a20e..000000000000 --- a/include/linux/raid/md_u.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - md_u.h : user <=> kernel API between Linux raidtools and RAID drivers - Copyright (C) 1998 Ingo Molnar - -*/ -#ifndef _MD_U_H -#define _MD_U_H - -#include - -extern int mdp_major; -#endif -- cgit v1.2.3 From d1100488c3ce11b853785cf15ee4c19bfab4c842 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 7 Jun 2020 16:56:05 +0200 Subject: md: simplify md_setup_drive Move the loop over the possible arrays into the caller to remove a level of indentation for the whole function. Signed-off-by: Christoph Hellwig Reviewed-by: NeilBrown Acked-by: Song Liu Acked-by: Linus Torvalds --- drivers/md/md-autodetect.c | 203 ++++++++++++++++++++++----------------------- 1 file changed, 101 insertions(+), 102 deletions(-) (limited to 'drivers') diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c index 6bc9b734eee6..a43a8f158058 100644 --- a/drivers/md/md-autodetect.c +++ b/drivers/md/md-autodetect.c @@ -27,7 +27,7 @@ static int __initdata raid_noautodetect=1; #endif static int __initdata raid_autopart; -static struct { +static struct md_setup_args { int minor; int partitioned; int level; @@ -126,122 +126,117 @@ static inline int create_dev(char *name, dev_t dev) return ksys_mknod(name, S_IFBLK|0600, new_encode_dev(dev)); } -static void __init md_setup_drive(void) +static void __init md_setup_drive(struct md_setup_args *args) { - int minor, i, ent, partitioned; + int minor, i, partitioned; dev_t dev; dev_t devices[MD_SB_DISKS+1]; + int fd; + int err = 0; + char *devname; + mdu_disk_info_t dinfo; + char name[16]; - for (ent = 0; ent < md_setup_ents ; ent++) { - int fd; - int err = 0; - char *devname; - mdu_disk_info_t dinfo; - char name[16]; + minor = args->minor; + partitioned = args->partitioned; + devname = args->device_names; - 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++) { + struct kstat stat; + char *p; + char comp_name[64]; - 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++) { - struct kstat stat; - char *p; - char comp_name[64]; + p = strchr(devname, ','); + if (p) + *p++ = 0; - 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); + if (vfs_stat(comp_name, &stat) == 0 && S_ISBLK(stat.mode)) + dev = new_decode_dev(stat.rdev); + if (!dev) { + printk(KERN_WARNING "md: Unknown device name: %s\n", devname); + break; + } - dev = name_to_dev_t(devname); - if (strncmp(devname, "/dev/", 5) == 0) - devname += 5; - snprintf(comp_name, 63, "/dev/%s", devname); - if (vfs_stat(comp_name, &stat) == 0 && - S_ISBLK(stat.mode)) - dev = new_decode_dev(stat.rdev); - if (!dev) { - printk(KERN_WARNING "md: Unknown device name: %s\n", devname); - break; - } + devices[i] = dev; + devname = p; + } + devices[i] = 0; - devices[i] = dev; + if (!i) + return; - devname = p; - } - devices[i] = 0; + printk(KERN_INFO "md: Loading md%s%d: %s\n", + partitioned ? "_d" : "", minor, + args->device_names); - if (!i) - continue; + fd = ksys_open(name, 0, 0); + if (fd < 0) { + printk(KERN_ERR "md: open failed - cannot start " + "array %s\n", name); + return; + } + 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); + return; + } - printk(KERN_INFO "md: Loading md%s%d: %s\n", - partitioned ? "_d" : "", minor, - md_setup_args[ent].device_names); + if (args->level != LEVEL_NONE) { + /* non-persistent */ + mdu_array_info_t ainfo; + ainfo.level = args->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; - 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; + ainfo.state = (1 << MD_SB_CLEAN); + ainfo.layout = 0; + ainfo.chunk_size = args->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< Date: Sun, 7 Jun 2020 17:31:19 +0200 Subject: md: rewrite md_setup_drive to avoid ioctls md_setup_drive knows it works with md devices, so it is rather pointless to open a file descriptor and issue ioctls. Just call directly into the relevant low-level md routines after getting a handle to the device using blkdev_get_by_dev instead. Signed-off-by: Christoph Hellwig Reviewed-by: NeilBrown Acked-by: Song Liu Acked-by: Linus Torvalds --- drivers/md/md-autodetect.c | 134 +++++++++++++++++++++------------------------ drivers/md/md.c | 24 ++++---- drivers/md/md.h | 8 +++ 3 files changed, 81 insertions(+), 85 deletions(-) (limited to 'drivers') diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c index a43a8f158058..14b6e86814c0 100644 --- a/drivers/md/md-autodetect.c +++ b/drivers/md/md-autodetect.c @@ -2,7 +2,6 @@ #include #include #include -#include #include #include #include @@ -120,37 +119,29 @@ static int __init md_setup(char *str) return 1; } -static inline int create_dev(char *name, dev_t dev) -{ - ksys_unlink(name); - return ksys_mknod(name, S_IFBLK|0600, new_encode_dev(dev)); -} - static void __init md_setup_drive(struct md_setup_args *args) { - int minor, i, partitioned; - dev_t dev; - dev_t devices[MD_SB_DISKS+1]; - int fd; - int err = 0; - char *devname; - mdu_disk_info_t dinfo; + char *devname = args->device_names; + dev_t devices[MD_SB_DISKS + 1], mdev; + struct mdu_array_info_s ainfo = { }; + struct block_device *bdev; + struct mddev *mddev; + int err = 0, i; char name[16]; - minor = args->minor; - partitioned = args->partitioned; - devname = args->device_names; + if (args->partitioned) { + mdev = MKDEV(mdp_major, args->minor << MdpMinorShift); + sprintf(name, "md_d%d", args->minor); + } else { + mdev = MKDEV(MD_MAJOR, args->minor); + sprintf(name, "md%d", args->minor); + } - 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++) { struct kstat stat; char *p; char comp_name[64]; + dev_t dev; p = strchr(devname, ','); if (p) @@ -163,7 +154,7 @@ static void __init md_setup_drive(struct md_setup_args *args) if (vfs_stat(comp_name, &stat) == 0 && S_ISBLK(stat.mode)) dev = new_decode_dev(stat.rdev); if (!dev) { - printk(KERN_WARNING "md: Unknown device name: %s\n", devname); + pr_warn("md: Unknown device name: %s\n", devname); break; } @@ -175,68 +166,71 @@ static void __init md_setup_drive(struct md_setup_args *args) if (!i) return; - printk(KERN_INFO "md: Loading md%s%d: %s\n", - partitioned ? "_d" : "", minor, - args->device_names); + pr_info("md: Loading %s: %s\n", name, args->device_names); - fd = ksys_open(name, 0, 0); - if (fd < 0) { - printk(KERN_ERR "md: open failed - cannot start " - "array %s\n", name); + bdev = blkdev_get_by_dev(mdev, FMODE_READ, NULL); + if (IS_ERR(bdev)) { + pr_err("md: open failed - cannot start array %s\n", name); return; } - 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); - return; + + err = -EIO; + if (WARN(bdev->bd_disk->fops != &md_fops, + "Opening block device %x resulted in non-md device\n", + mdev)) + goto out_blkdev_put; + + mddev = bdev->bd_disk->private_data; + + err = mddev_lock(mddev); + if (err) { + pr_err("md: failed to lock array %s\n", name); + goto out_blkdev_put; + } + + if (!list_empty(&mddev->disks) || mddev->raid_disks) { + pr_warn("md: Ignoring %s, already autodetected. (Use raid=noautodetect)\n", + name); + goto out_unlock; } if (args->level != LEVEL_NONE) { /* non-persistent */ - mdu_array_info_t ainfo; ainfo.level = args->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.md_minor = args->minor; ainfo.not_persistent = 1; - ainfo.state = (1 << MD_SB_CLEAN); - ainfo.layout = 0; ainfo.chunk_size = args->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; + while (devices[ainfo.raid_disks]) + ainfo.raid_disks++; + } + + err = md_set_array_info(mddev, &ainfo); + + for (i = 0; i <= MD_SB_DISKS && devices[i]; i++) { + struct mdu_disk_info_s dinfo = { + .major = MAJOR(devices[i]), + .minor = MINOR(devices[i]), + }; + + if (args->level != LEVEL_NONE) { dinfo.number = i; dinfo.raid_disk = i; - dinfo.state = (1<major_version != 0) { @@ -7055,7 +7052,7 @@ static int set_bitmap_file(struct mddev *mddev, int fd) } /* - * set_array_info is used two different ways + * md_set_array_info is used two different ways * The original usage is when creating a new array. * In this usage, raid_disks is > 0 and it together with * level, size, not_persistent,layout,chunksize determine the @@ -7067,9 +7064,8 @@ static int set_bitmap_file(struct mddev *mddev, int fd) * The minor and patch _version numbers are also kept incase the * super_block handler wishes to interpret them. */ -static int set_array_info(struct mddev *mddev, mdu_array_info_t *info) +int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info) { - if (info->raid_disks == 0) { /* just setting version number for superblock loading */ if (info->major_version < 0 || @@ -7560,7 +7556,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, err = -EBUSY; goto unlock; } - err = set_array_info(mddev, &info); + err = md_set_array_info(mddev, &info); if (err) { pr_warn("md: couldn't set array info. %d\n", err); goto unlock; @@ -7614,7 +7610,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, /* Need to clear read-only for this */ break; else - err = add_new_disk(mddev, &info); + err = md_add_new_disk(mddev, &info); goto unlock; } break; @@ -7682,7 +7678,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, if (copy_from_user(&info, argp, sizeof(info))) err = -EFAULT; else - err = add_new_disk(mddev, &info); + err = md_add_new_disk(mddev, &info); goto unlock; } @@ -7808,7 +7804,7 @@ static int md_revalidate(struct gendisk *disk) mddev->changed = 0; return 0; } -static const struct block_device_operations md_fops = +const struct block_device_operations md_fops = { .owner = THIS_MODULE, .open = md_open, diff --git a/drivers/md/md.h b/drivers/md/md.h index 6f8fff77ce10..ada3106cb1dd 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -801,7 +801,15 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio mddev->queue->limits.max_write_zeroes_sectors = 0; } +struct mdu_array_info_s; +struct mdu_disk_info_s; + extern int mdp_major; void md_autostart_arrays(int part); +int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info); +int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info); +int do_md_run(struct mddev *mddev); + +extern const struct block_device_operations md_fops; #endif /* _MD_MD_H */ -- cgit v1.2.3 From bcbacc4909f1b93242ba2894d0282c151c9d0e68 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 10:48:25 +0200 Subject: devtmpfs: refactor devtmpfsd() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Split the main worker loop into a separate function. This allows devtmpfsd_setup to be marked __init, which will allows us to call __init routines for the setup work. devtmpfѕ itself needs a __ref marker for that to work, and a comment explaining why it works. Signed-off-by: Christoph Hellwig --- drivers/base/devtmpfs.c | 52 +++++++++++++++++++++++++++++-------------------- 1 file changed, 31 insertions(+), 21 deletions(-) (limited to 'drivers') diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index c9017e0584c0..d697634bc0d4 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -378,7 +378,30 @@ static int handle(const char *name, umode_t mode, kuid_t uid, kgid_t gid, return handle_remove(name, dev); } -static int devtmpfs_setup(void *p) +static void __noreturn devtmpfs_work_loop(void) +{ + while (1) { + spin_lock(&req_lock); + while (requests) { + struct req *req = requests; + requests = NULL; + spin_unlock(&req_lock); + while (req) { + struct req *next = req->next; + req->err = handle(req->name, req->mode, + req->uid, req->gid, req->dev); + complete(&req->done); + req = next; + } + spin_lock(&req_lock); + } + __set_current_state(TASK_INTERRUPTIBLE); + spin_unlock(&req_lock); + schedule(); + } +} + +static int __init devtmpfs_setup(void *p) { int err; @@ -396,31 +419,18 @@ out: return err; } -static int devtmpfsd(void *p) +/* + * The __ref is because devtmpfs_setup needs to be __init for the routines it + * calls. That call is done while devtmpfs_init, which is marked __init, + * synchronously waits for it to complete. + */ +static int __ref devtmpfsd(void *p) { int err = devtmpfs_setup(p); if (err) return err; - while (1) { - spin_lock(&req_lock); - while (requests) { - struct req *req = requests; - requests = NULL; - spin_unlock(&req_lock); - while (req) { - struct req *next = req->next; - req->err = handle(req->name, req->mode, - req->uid, req->gid, req->dev); - complete(&req->done); - req = next; - } - spin_lock(&req_lock); - } - __set_current_state(TASK_INTERRUPTIBLE); - spin_unlock(&req_lock); - schedule(); - } + devtmpfs_work_loop(); return 0; } -- cgit v1.2.3 From c60166f04283ffba7b88b45d824bbfb2bfccee24 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 21 Jul 2020 11:12:08 +0200 Subject: init: add an init_mount helper Like do_mount, but takes a kernel pointer for the destination path. Switch over the mounts in the init code and devtmpfs to it, which just happen to work due to the implicit set_fs(KERNEL_DS) during early init right now. Signed-off-by: Christoph Hellwig --- drivers/base/devtmpfs.c | 5 +++-- fs/Makefile | 2 +- fs/init.c | 25 +++++++++++++++++++++++++ fs/internal.h | 4 ++++ fs/namespace.c | 2 +- include/linux/init_syscalls.h | 4 ++++ init/do_mounts.c | 8 ++++---- init/do_mounts.h | 1 + init/do_mounts_initrd.c | 6 +++--- 9 files changed, 46 insertions(+), 11 deletions(-) create mode 100644 fs/init.c create mode 100644 include/linux/init_syscalls.h (limited to 'drivers') diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index d697634bc0d4..32af6cb987b4 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include "base.h" @@ -359,7 +360,7 @@ int __init devtmpfs_mount(void) if (!thread) return 0; - err = do_mount("devtmpfs", "dev", "devtmpfs", MS_SILENT, NULL); + err = init_mount("devtmpfs", "dev", "devtmpfs", MS_SILENT, NULL); if (err) printk(KERN_INFO "devtmpfs: error mounting %i\n", err); else @@ -408,7 +409,7 @@ static int __init devtmpfs_setup(void *p) err = ksys_unshare(CLONE_NEWNS); if (err) goto out; - err = do_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, NULL); + err = init_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, NULL); if (err) goto out; ksys_chdir("/.."); /* will traverse into overmounted root */ diff --git a/fs/Makefile b/fs/Makefile index 2ce5112b02c8..1c7b0e3f6daa 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -13,7 +13,7 @@ obj-y := open.o read_write.o file_table.o super.o \ seq_file.o xattr.o libfs.o fs-writeback.o \ pnode.o splice.o sync.o utimes.o d_path.o \ stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \ - fs_types.o fs_context.o fs_parser.o fsopen.o + fs_types.o fs_context.o fs_parser.o fsopen.o init.o ifeq ($(CONFIG_BLOCK),y) obj-y += buffer.o block_dev.o direct-io.o mpage.o diff --git a/fs/init.c b/fs/init.c new file mode 100644 index 000000000000..c6eb724e1c7b --- /dev/null +++ b/fs/init.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Routines that mimic syscalls, but don't use the user address space or file + * descriptors. Only for init/ and related early init code. + */ +#include +#include +#include +#include +#include +#include "internal.h" + +int __init init_mount(const char *dev_name, const char *dir_name, + const char *type_page, unsigned long flags, void *data_page) +{ + struct path path; + int ret; + + ret = kern_path(dir_name, LOOKUP_FOLLOW, &path); + if (ret) + return ret; + ret = path_mount(dev_name, &path, type_page, flags, data_page); + path_put(&path); + return ret; +} diff --git a/fs/internal.h b/fs/internal.h index e903d5aae139..72ea0b6f7435 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -89,6 +89,10 @@ extern int __mnt_want_write_file(struct file *); extern void __mnt_drop_write_file(struct file *); extern void dissolve_on_fput(struct vfsmount *); + +int path_mount(const char *dev_name, struct path *path, + const char *type_page, unsigned long flags, void *data_page); + /* * fs_struct.c */ diff --git a/fs/namespace.c b/fs/namespace.c index 43834b59eff6..2c4d75920974 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -3111,7 +3111,7 @@ char *copy_mount_string(const void __user *data) * Therefore, if this magic number is present, it carries no information * and must be discarded. */ -static int path_mount(const char *dev_name, struct path *path, +int path_mount(const char *dev_name, struct path *path, const char *type_page, unsigned long flags, void *data_page) { unsigned int mnt_flags = 0, sb_flags; diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h new file mode 100644 index 000000000000..af9ea88a60e0 --- /dev/null +++ b/include/linux/init_syscalls.h @@ -0,0 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +int __init init_mount(const char *dev_name, const char *dir_name, + const char *type_page, unsigned long flags, void *data_page); diff --git a/init/do_mounts.c b/init/do_mounts.c index a7f22cf58c7e..83db87b6e5d1 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -395,16 +395,16 @@ 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; @@ -628,7 +628,7 @@ void __init prepare_namespace(void) mount_root(); out: devtmpfs_mount(); - do_mount(".", "/", NULL, MS_MOVE, NULL); + init_mount(".", "/", NULL, MS_MOVE, NULL); ksys_chroot("."); } diff --git a/init/do_mounts.h b/init/do_mounts.h index 021e2f60223e..20e7fec8cb49 100644 --- a/init/do_mounts.h +++ b/init/do_mounts.h @@ -8,6 +8,7 @@ #include #include #include +#include void mount_block_root(char *name, int flags); void mount_root(void); diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index e08669187d63..1f9336209ad9 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -62,7 +62,7 @@ static int __init init_linuxrc(struct subprocess_info *info, struct cred *new) console_on_rootfs(); /* move initrd over / and chdir/chroot in initrd root */ ksys_chdir("/root"); - do_mount(".", "/", NULL, MS_MOVE, NULL); + init_mount(".", "/", NULL, MS_MOVE, NULL); ksys_chroot("."); ksys_setsid(); return 0; @@ -99,7 +99,7 @@ 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(".."); @@ -113,7 +113,7 @@ static void __init handle_initrd(void) 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 { -- cgit v1.2.3 From db63f1e315384590b979f8f74abd1b5363b69894 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:25:21 +0200 Subject: init: add an init_chdir helper Add a simple helper to chdir with a kernel space file name and switch the early init code over to it. Remove the now unused ksys_chdir. Signed-off-by: Christoph Hellwig --- drivers/base/devtmpfs.c | 2 +- fs/init.c | 16 ++++++++++++++++ fs/open.c | 7 +------ include/linux/init_syscalls.h | 1 + include/linux/syscalls.h | 1 - init/do_mounts.c | 2 +- init/do_mounts_initrd.c | 8 ++++---- 7 files changed, 24 insertions(+), 13 deletions(-) (limited to 'drivers') diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 32af6cb987b4..e48aaba3166b 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -412,7 +412,7 @@ static int __init devtmpfs_setup(void *p) err = init_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, NULL); if (err) goto out; - ksys_chdir("/.."); /* will traverse into overmounted root */ + init_chdir("/.."); /* will traverse into overmounted root */ ksys_chroot("."); out: *(int *)p = err; diff --git a/fs/init.c b/fs/init.c index eabd9ed2b510..64d4e12eba93 100644 --- a/fs/init.c +++ b/fs/init.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include "internal.h" @@ -38,6 +39,21 @@ int __init init_umount(const char *name, int flags) return path_umount(&path, flags); } +int __init init_chdir(const char *filename) +{ + struct path path; + int error; + + error = kern_path(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path); + if (error) + return error; + error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); + if (!error) + set_fs_pwd(current->fs, &path); + path_put(&path); + return error; +} + int __init init_unlink(const char *pathname) { return do_unlinkat(AT_FDCWD, getname_kernel(pathname)); diff --git a/fs/open.c b/fs/open.c index b316dd6a86a8..723e0ac89893 100644 --- a/fs/open.c +++ b/fs/open.c @@ -482,7 +482,7 @@ SYSCALL_DEFINE2(access, const char __user *, filename, int, mode) return do_faccessat(AT_FDCWD, filename, mode, 0); } -int ksys_chdir(const char __user *filename) +SYSCALL_DEFINE1(chdir, const char __user *, filename) { struct path path; int error; @@ -508,11 +508,6 @@ out: return error; } -SYSCALL_DEFINE1(chdir, const char __user *, filename) -{ - return ksys_chdir(filename); -} - SYSCALL_DEFINE1(fchdir, unsigned int, fd) { struct fd f = fdget_raw(fd); diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index abf3af563c0b..1e845910ae56 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -3,5 +3,6 @@ int __init init_mount(const char *dev_name, const char *dir_name, const char *type_page, unsigned long flags, void *data_page); int __init init_umount(const char *name, int flags); +int __init init_chdir(const char *filename); int __init init_unlink(const char *pathname); int __init init_rmdir(const char *pathname); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a7b14258d245..31fa67fb9894 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1238,7 +1238,6 @@ asmlinkage long sys_ni_syscall(void); int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); -int ksys_chdir(const char __user *filename); int ksys_fchown(unsigned int fd, uid_t user, gid_t group); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); void ksys_sync(void); diff --git a/init/do_mounts.c b/init/do_mounts.c index 83db87b6e5d1..a7581c6e85f2 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -408,7 +408,7 @@ static int __init do_mount_root(const char *name, const char *fs, 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 diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 8b44dd017842..04627fd22a92 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -61,7 +61,7 @@ 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"); + init_chdir("/root"); init_mount(".", "/", NULL, MS_MOVE, NULL); ksys_chroot("."); ksys_setsid(); @@ -82,7 +82,7 @@ static void __init handle_initrd(void) /* mount initrd on rootfs' /root */ mount_block_root("/dev/root.old", root_mountflags & ~MS_RDONLY); ksys_mkdir("/old", 0700); - ksys_chdir("/old"); + init_chdir("/old"); /* * In case that a resume from disk is carried out by linuxrc or one of @@ -104,11 +104,11 @@ static void __init handle_initrd(void) ksys_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(); -- cgit v1.2.3 From 4b7ca5014cbef51cdb99fd644eae4f3773747a05 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:26:13 +0200 Subject: init: add an init_chroot helper Add a simple helper to chroot with a kernel space file name and switch the early init code over to it. Remove the now unused ksys_chroot. Signed-off-by: Christoph Hellwig --- drivers/base/devtmpfs.c | 2 +- fs/init.c | 24 ++++++++++++++++++++++++ fs/open.c | 7 +------ include/linux/init_syscalls.h | 1 + include/linux/syscalls.h | 2 -- init/do_mounts.c | 2 +- init/do_mounts_initrd.c | 4 ++-- 7 files changed, 30 insertions(+), 12 deletions(-) (limited to 'drivers') diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index e48aaba3166b..eac184e6d657 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -413,7 +413,7 @@ static int __init devtmpfs_setup(void *p) if (err) goto out; init_chdir("/.."); /* will traverse into overmounted root */ - ksys_chroot("."); + init_chroot("."); out: *(int *)p = err; complete(&setup_done); diff --git a/fs/init.c b/fs/init.c index 64d4e12eba93..2c78f24814dd 100644 --- a/fs/init.c +++ b/fs/init.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "internal.h" int __init init_mount(const char *dev_name, const char *dir_name, @@ -54,6 +55,29 @@ int __init init_chdir(const char *filename) return error; } +int __init init_chroot(const char *filename) +{ + struct path path; + int error; + + error = kern_path(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path); + if (error) + return error; + error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); + if (error) + goto dput_and_out; + error = -EPERM; + if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT)) + goto dput_and_out; + error = security_path_chroot(&path); + if (error) + goto dput_and_out; + set_fs_root(current->fs, &path); +dput_and_out: + path_put(&path); + return error; +} + int __init init_unlink(const char *pathname) { return do_unlinkat(AT_FDCWD, getname_kernel(pathname)); diff --git a/fs/open.c b/fs/open.c index 723e0ac89893..f62f4752bb43 100644 --- a/fs/open.c +++ b/fs/open.c @@ -530,7 +530,7 @@ out: return error; } -int ksys_chroot(const char __user *filename) +SYSCALL_DEFINE1(chroot, const char __user *, filename) { struct path path; int error; @@ -563,11 +563,6 @@ out: return error; } -SYSCALL_DEFINE1(chroot, const char __user *, filename) -{ - return ksys_chroot(filename); -} - static int chmod_common(const struct path *path, umode_t mode) { struct inode *inode = path->dentry->d_inode; diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index 1e845910ae56..e07099a14b91 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -4,5 +4,6 @@ int __init init_mount(const char *dev_name, const char *dir_name, const char *type_page, unsigned long flags, void *data_page); int __init init_umount(const char *name, int flags); int __init init_chdir(const char *filename); +int __init init_chroot(const char *filename); int __init init_unlink(const char *pathname); int __init init_rmdir(const char *pathname); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 31fa67fb9894..e89d62e944dc 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1235,8 +1235,6 @@ asmlinkage long sys_ni_syscall(void); * Instead, use one of the functions which work equivalently, such as * the ksys_xyzyyz() functions prototyped below. */ - -int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_fchown(unsigned int fd, uid_t user, gid_t group); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); diff --git a/init/do_mounts.c b/init/do_mounts.c index a7581c6e85f2..b5f9604d0c98 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -629,7 +629,7 @@ void __init prepare_namespace(void) out: devtmpfs_mount(); init_mount(".", "/", NULL, MS_MOVE, NULL); - ksys_chroot("."); + init_chroot("."); } static bool is_tmpfs; diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 04627fd22a92..a6b447b191db 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -63,7 +63,7 @@ static int __init init_linuxrc(struct subprocess_info *info, struct cred *new) /* move initrd over / and chdir/chroot in initrd root */ init_chdir("/root"); init_mount(".", "/", NULL, MS_MOVE, NULL); - ksys_chroot("."); + init_chroot("."); ksys_setsid(); return 0; } @@ -101,7 +101,7 @@ static void __init handle_initrd(void) /* move initrd to rootfs' /old */ 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) { init_chdir("/old"); -- cgit v1.2.3 From 716308a5331bf907b819f9db8dc942b19568f925 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:15:40 +0200 Subject: init: add an init_stat helper Add a simple helper to stat with a kernel space file name and switch the early init code over to it. Signed-off-by: Christoph Hellwig --- drivers/md/md-autodetect.c | 3 ++- fs/init.c | 15 +++++++++++++++ include/linux/init_syscalls.h | 1 + init/initramfs.c | 3 ++- 4 files changed, 20 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c index 14b6e86814c0..6bbec89976a7 100644 --- a/drivers/md/md-autodetect.c +++ b/drivers/md/md-autodetect.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -151,7 +152,7 @@ static void __init md_setup_drive(struct md_setup_args *args) if (strncmp(devname, "/dev/", 5) == 0) devname += 5; snprintf(comp_name, 63, "/dev/%s", devname); - if (vfs_stat(comp_name, &stat) == 0 && S_ISBLK(stat.mode)) + if (init_stat(comp_name, &stat, 0) == 0 && S_ISBLK(stat.mode)) dev = new_decode_dev(stat.rdev); if (!dev) { pr_warn("md: Unknown device name: %s\n", devname); diff --git a/fs/init.c b/fs/init.c index 145fb31b7a5f..51646ba38099 100644 --- a/fs/init.c +++ b/fs/init.c @@ -122,6 +122,21 @@ int __init init_eaccess(const char *filename) return error; } +int __init init_stat(const char *filename, struct kstat *stat, int flags) +{ + int lookup_flags = (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; + struct path path; + int error; + + error = kern_path(filename, lookup_flags, &path); + if (error) + return error; + error = vfs_getattr(&path, stat, STATX_BASIC_STATS, + flags | AT_NO_AUTOMOUNT); + path_put(&path); + return error; +} + int __init init_mknod(const char *filename, umode_t mode, unsigned int dev) { struct dentry *dentry; diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index fa1fe7a87779..b2fda50daca6 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -8,6 +8,7 @@ int __init init_chroot(const char *filename); int __init init_chown(const char *filename, uid_t user, gid_t group, int flags); int __init init_chmod(const char *filename, umode_t mode); int __init init_eaccess(const char *filename); +int __init init_stat(const char *filename, struct kstat *stat, int flags); int __init init_mknod(const char *filename, umode_t mode, unsigned int dev); int __init init_link(const char *oldname, const char *newname); int __init init_symlink(const char *oldname, const char *newname); diff --git a/init/initramfs.c b/init/initramfs.c index 425addaf7c69..744e111baba4 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -298,7 +298,8 @@ 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)) init_rmdir(path); else -- cgit v1.2.3