diff options
Diffstat (limited to 'init')
| -rw-r--r-- | init/.kunitconfig | 3 | ||||
| -rw-r--r-- | init/Kconfig | 135 | ||||
| -rw-r--r-- | init/Makefile | 1 | ||||
| -rw-r--r-- | init/initramfs.c | 67 | ||||
| -rw-r--r-- | init/initramfs_internal.h | 8 | ||||
| -rw-r--r-- | init/initramfs_test.c | 407 | ||||
| -rw-r--r-- | init/main.c | 24 |
7 files changed, 575 insertions, 70 deletions
diff --git a/init/.kunitconfig b/init/.kunitconfig new file mode 100644 index 000000000000..acb906b1a5f9 --- /dev/null +++ b/init/.kunitconfig @@ -0,0 +1,3 @@ +CONFIG_KUNIT=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_TEST=y diff --git a/init/Kconfig b/init/Kconfig index 5ab47c346ef9..2e15b4a8478e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -87,11 +87,6 @@ config CC_CAN_LINK default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m64-flag)) if 64BIT default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m32-flag)) -config CC_CAN_LINK_STATIC - bool - default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m64-flag) -static) if 64BIT - default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m32-flag) -static) - # Fixed in GCC 14, 13.3, 12.4 and 11.5 # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 config GCC_ASM_GOTO_OUTPUT_BROKEN @@ -121,13 +116,17 @@ config CC_HAS_NO_PROFILE_FN_ATTR def_bool $(success,echo '__attribute__((no_profile_instrument_function)) int x();' | $(CC) -x c - -c -o /dev/null -Werror) config CC_HAS_COUNTED_BY - # TODO: when gcc 15 is released remove the build test and add - # a gcc version check - def_bool $(success,echo 'struct flex { int count; int array[] __attribute__((__counted_by__(count))); };' | $(CC) $(CLANG_FLAGS) -x c - -c -o /dev/null -Werror) + bool # clang needs to be at least 19.1.3 to avoid __bdos miscalculations # https://github.com/llvm/llvm-project/pull/110497 # https://github.com/llvm/llvm-project/pull/112636 - depends on !(CC_IS_CLANG && CLANG_VERSION < 190103) + default y if CC_IS_CLANG && CLANG_VERSION >= 190103 + # supported since gcc 15.1.0 + # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108896 + default y if CC_IS_GCC && GCC_VERSION >= 150100 + +config CC_HAS_MULTIDIMENSIONAL_NONSTRING + def_bool $(success,echo 'char tag[][4] __attribute__((__nonstring__)) = { };' | $(CC) $(CLANG_FLAGS) -x c - -c -o /dev/null -Werror) config LD_CAN_USE_KEEP_IN_OVERLAY # ld.lld prior to 21.0.0 did not support KEEP within an overlay description @@ -137,6 +136,12 @@ config LD_CAN_USE_KEEP_IN_OVERLAY config RUSTC_HAS_COERCE_POINTEE def_bool RUSTC_VERSION >= 108400 +config RUSTC_HAS_SPAN_FILE + def_bool RUSTC_VERSION >= 108800 + +config RUSTC_HAS_UNNECESSARY_TRANSMUTES + def_bool RUSTC_VERSION >= 108800 + config PAHOLE_VERSION int default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE)) @@ -476,16 +481,6 @@ config CROSS_MEMORY_ATTACH to directly read from or write to another process' address space. See the man page for more details. -config USELIB - bool "uselib syscall (for libc5 and earlier)" - default ALPHA || M68K || SPARC - help - This option enables the uselib syscall, a system call used in the - dynamic linker from libc5 and earlier. glibc does not use this - system call. If you intend to run programs built on libc5 or - earlier, you may need to enable this syscall. Current systems - running glibc can safely disable this. - config AUDIT bool "Auditing support" depends on NET @@ -711,7 +706,7 @@ endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION bool "CPU isolation" - depends on SMP || COMPILE_TEST + depends on SMP default y help Make sure that CPUs running critical tasks are not disturbed by @@ -1000,6 +995,20 @@ config MEMCG help Provides control over the memory footprint of tasks in a cgroup. +config MEMCG_NMI_UNSAFE + bool + depends on MEMCG + depends on HAVE_NMI + depends on !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && !ARCH_HAVE_NMI_SAFE_CMPXCHG + default y + +config MEMCG_NMI_SAFETY_REQUIRES_ATOMIC + bool + depends on MEMCG + depends on HAVE_NMI + depends on !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && ARCH_HAVE_NMI_SAFE_CMPXCHG + default y + config MEMCG_V1 bool "Legacy cgroup v1 memory controller" depends on MEMCG @@ -1084,6 +1093,17 @@ config RT_GROUP_SCHED realtime bandwidth for them. See Documentation/scheduler/sched-rt-group.rst for more information. +config RT_GROUP_SCHED_DEFAULT_DISABLED + bool "Require boot parameter to enable group scheduling for SCHED_RR/FIFO" + depends on RT_GROUP_SCHED + default n + help + When set, the RT group scheduling is disabled by default. The option + is in inverted form so that mere RT_GROUP_SCHED enables the group + scheduling. + + Say N if unsure. + config EXT_GROUP_SCHED bool depends on SCHED_CLASS_EXT && CGROUP_SCHED @@ -1200,7 +1220,8 @@ config CPUSETS_V1 help Legacy cgroup v1 cpusets controller which has been deprecated by cgroup v2 implementation. The v1 is there for legacy applications - which haven't migrated to the new cgroup v2 interface yet. If you + which haven't migrated to the new cgroup v2 interface yet. Legacy + interface includes cpuset filesystem and /proc/<pid>/cpuset. If you do not have any such application then you are completely fine leaving this option disabled. @@ -1208,7 +1229,7 @@ config CPUSETS_V1 config PROC_PID_CPUSET bool "Include legacy /proc/<pid>/cpuset file" - depends on CPUSETS + depends on CPUSETS_V1 default y config CGROUP_DEVICE @@ -1459,6 +1480,13 @@ config INITRAMFS_PRESERVE_MTIME If unsure, say Y. +config INITRAMFS_TEST + bool "Test initramfs cpio archive extraction" if !KUNIT_ALL_TESTS + depends on BLK_DEV_INITRD && KUNIT=y + default KUNIT_ALL_TESTS + help + Build KUnit tests for initramfs. See Documentation/dev-tools/kunit + choice prompt "Compiler optimization level" default CC_OPTIMIZE_FOR_PERFORMANCE @@ -1544,6 +1572,16 @@ config SYSCTL_ARCH_UNALIGN_ALLOW the unaligned access emulation. see arch/parisc/kernel/unaligned.c for reference +config SYSFS_SYSCALL + bool "Sysfs syscall support" + default n + help + sys_sysfs is an obsolete system call no longer supported in libc. + Note that disabling this option is more secure but might break + compatibility with some systems. + + If unsure say N here. + config HAVE_PCSPKR_PLATFORM bool @@ -1588,16 +1626,6 @@ config SGETMASK_SYSCALL If unsure, leave the default option here. -config SYSFS_SYSCALL - bool "Sysfs syscall support" if EXPERT - default y - help - sys_sysfs is an obsolete system call no longer supported in libc. - Note that disabling this option is more secure but might break - compatibility with some systems. - - If unsure say Y here. - config FHANDLE bool "open by fhandle syscalls" if EXPERT select EXPORTFS @@ -1688,6 +1716,20 @@ config FUTEX_PI depends on FUTEX && RT_MUTEXES default y +# +# marked broken for performance reasons; gives us one more cycle to sort things out. +# +config FUTEX_PRIVATE_HASH + bool + depends on FUTEX && !BASE_SMALL && MMU + depends on BROKEN + default y + +config FUTEX_MPOL + bool + depends on FUTEX && NUMA + default y + config EPOLL bool "Enable eventpoll support" if EXPERT default y @@ -1752,7 +1794,7 @@ config IO_URING config GCOV_PROFILE_URING bool "Enable GCOV profiling on the io_uring subsystem" - depends on GCOV_KERNEL + depends on IO_URING && GCOV_KERNEL help Enable GCOV profiling on the io_uring subsystem, to facilitate code coverage testing. @@ -1874,11 +1916,6 @@ config KALLSYMS_ALL Say N unless you really need all symbols, or kernel live patching. -config KALLSYMS_ABSOLUTE_PERCPU - bool - depends on KALLSYMS - default X86_64 && SMP - # end of the "standard kernel features (expert users)" menu config ARCH_HAS_MEMBARRIER_CALLBACKS @@ -1887,6 +1924,28 @@ config ARCH_HAS_MEMBARRIER_CALLBACKS config ARCH_HAS_MEMBARRIER_SYNC_CORE bool +config ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS + bool + help + Control MSEAL_SYSTEM_MAPPINGS access based on architecture. + + A 64-bit kernel is required for the memory sealing feature. + No specific hardware features from the CPU are needed. + + To enable this feature, the architecture needs to update their + special mappings calls to include the sealing flag and confirm + that it doesn't unmap/remap system mappings during the life + time of the process. The existence of this flag for an architecture + implies that it does not require the remapping of the system + mappings during process lifetime, so sealing these mappings is safe + from a kernel perspective. + + After the architecture enables this, a distribution can set + CONFIG_MSEAL_SYSTEM_MAPPING to manage access to the feature. + + For complete descriptions of memory sealing, please see + Documentation/userspace-api/mseal.rst + config HAVE_PERF_EVENTS bool help diff --git a/init/Makefile b/init/Makefile index 10b652d33e87..d6f75d8907e0 100644 --- a/init/Makefile +++ b/init/Makefile @@ -12,6 +12,7 @@ else obj-$(CONFIG_BLK_DEV_INITRD) += initramfs.o endif obj-$(CONFIG_GENERIC_CALIBRATE_DELAY) += calibrate.o +obj-$(CONFIG_INITRAMFS_TEST) += initramfs_test.o obj-y += init_task.o diff --git a/init/initramfs.c b/init/initramfs.c index b2f7583bb1f5..097673b97784 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/async.h> +#include <linux/export.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/types.h> @@ -20,6 +21,7 @@ #include <linux/security.h> #include "do_mounts.h" +#include "initramfs_internal.h" static __initdata bool csum_present; static __initdata u32 io_csum; @@ -75,6 +77,7 @@ static __initdata struct hash { struct hash *next; char name[N_ALIGN(PATH_MAX)]; } *head[32]; +static __initdata bool hardlink_seen; static inline int hash(int major, int minor, int ino) { @@ -108,19 +111,21 @@ static char __init *find_link(int major, int minor, int ino, strcpy(q->name, name); q->next = NULL; *p = q; + hardlink_seen = true; return NULL; } static void __init free_hash(void) { struct hash **p, *q; - for (p = head; p < head + 32; p++) { + for (p = head; hardlink_seen && p < head + 32; p++) { while (*p) { q = *p; *p = q->next; kfree(q); } } + hardlink_seen = false; } #ifdef CONFIG_INITRAMFS_PRESERVE_MTIME @@ -143,9 +148,8 @@ struct dir_entry { char name[]; }; -static void __init dir_add(const char *name, time64_t mtime) +static void __init dir_add(const char *name, size_t nlen, time64_t mtime) { - size_t nlen = strlen(name) + 1; struct dir_entry *de; de = kmalloc(sizeof(struct dir_entry) + nlen, GFP_KERNEL); @@ -169,7 +173,7 @@ static void __init dir_utime(void) #else static void __init do_utime(char *filename, time64_t mtime) {} static void __init do_utime_path(const struct path *path, time64_t mtime) {} -static void __init dir_add(const char *name, time64_t mtime) {} +static void __init dir_add(const char *name, size_t nlen, time64_t mtime) {} static void __init dir_utime(void) {} #endif @@ -188,14 +192,11 @@ static __initdata u32 hdr_csum; static void __init parse_header(char *s) { unsigned long parsed[13]; - char buf[9]; int i; - buf[8] = '\0'; - for (i = 0, s += 6; i < 13; i++, s += 8) { - memcpy(buf, s, 8); - parsed[i] = simple_strtoul(buf, NULL, 16); - } + for (i = 0, s += 6; i < 13; i++, s += 8) + parsed[i] = simple_strntoul(s, NULL, 16, 8); + ino = parsed[0]; mode = parsed[1]; uid = parsed[2]; @@ -256,7 +257,7 @@ static __initdata char *header_buf, *symlink_buf, *name_buf; static int __init do_start(void) { - read_into(header_buf, 110, GotHeader); + read_into(header_buf, CPIO_HDRLEN, GotHeader); return 0; } @@ -396,7 +397,7 @@ static int __init do_name(void) init_mkdir(collected, mode); init_chown(collected, uid, gid, 0); init_chmod(collected, mode); - dir_add(collected, mtime); + dir_add(collected, name_len, mtime); } else if (S_ISBLK(mode) || S_ISCHR(mode) || S_ISFIFO(mode) || S_ISSOCK(mode)) { if (maybe_link() == 0) { @@ -497,20 +498,33 @@ static unsigned long my_inptr __initdata; /* index of next byte to be processed #include <linux/decompress/generic.h> -static char * __init unpack_to_rootfs(char *buf, unsigned long len) +/** + * unpack_to_rootfs - decompress and extract an initramfs archive + * @buf: input initramfs archive to extract + * @len: length of initramfs data to process + * + * Returns: NULL for success or an error message string + * + * This symbol shouldn't be used externally. It's available for unit tests. + */ +char * __init unpack_to_rootfs(char *buf, unsigned long len) { long written; decompress_fn decompress; const char *compress_name; - static __initdata char msg_buf[64]; + struct { + char header[CPIO_HDRLEN]; + char symlink[PATH_MAX + N_ALIGN(PATH_MAX) + 1]; + char name[N_ALIGN(PATH_MAX)]; + } *bufs = kmalloc(sizeof(*bufs), GFP_KERNEL); - header_buf = kmalloc(110, GFP_KERNEL); - symlink_buf = kmalloc(PATH_MAX + N_ALIGN(PATH_MAX) + 1, GFP_KERNEL); - name_buf = kmalloc(N_ALIGN(PATH_MAX), GFP_KERNEL); - - if (!header_buf || !symlink_buf || !name_buf) + if (!bufs) panic_show_mem("can't allocate buffers"); + header_buf = bufs->header; + symlink_buf = bufs->symlink; + name_buf = bufs->name; + state = Start; this_header = 0; message = NULL; @@ -538,12 +552,9 @@ static char * __init unpack_to_rootfs(char *buf, unsigned long len) if (res) error("decompressor failed"); } else if (compress_name) { - if (!message) { - snprintf(msg_buf, sizeof msg_buf, - "compression method %s not configured", - compress_name); - message = msg_buf; - } + pr_err("compression method %s not configured\n", + compress_name); + error("decompressor failed"); } else error("invalid magic at start of compressed archive"); if (state != Reset) @@ -553,9 +564,9 @@ static char * __init unpack_to_rootfs(char *buf, unsigned long len) len -= my_inptr; } dir_utime(); - kfree(name_buf); - kfree(symlink_buf); - kfree(header_buf); + /* free any hardlink state collected without optional TRAILER!!! */ + free_hash(); + kfree(bufs); return message; } diff --git a/init/initramfs_internal.h b/init/initramfs_internal.h new file mode 100644 index 000000000000..233dad16b0a0 --- /dev/null +++ b/init/initramfs_internal.h @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef __INITRAMFS_INTERNAL_H__ +#define __INITRAMFS_INTERNAL_H__ + +char *unpack_to_rootfs(char *buf, unsigned long len); +#define CPIO_HDRLEN 110 + +#endif diff --git a/init/initramfs_test.c b/init/initramfs_test.c new file mode 100644 index 000000000000..517e5e04e5cc --- /dev/null +++ b/init/initramfs_test.c @@ -0,0 +1,407 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <kunit/test.h> +#include <linux/fcntl.h> +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/init_syscalls.h> +#include <linux/stringify.h> +#include <linux/timekeeping.h> +#include "initramfs_internal.h" + +struct initramfs_test_cpio { + char *magic; + unsigned int ino; + unsigned int mode; + unsigned int uid; + unsigned int gid; + unsigned int nlink; + unsigned int mtime; + unsigned int filesize; + unsigned int devmajor; + unsigned int devminor; + unsigned int rdevmajor; + unsigned int rdevminor; + unsigned int namesize; + unsigned int csum; + char *fname; + char *data; +}; + +static size_t fill_cpio(struct initramfs_test_cpio *cs, size_t csz, char *out) +{ + int i; + size_t off = 0; + + for (i = 0; i < csz; i++) { + char *pos = &out[off]; + struct initramfs_test_cpio *c = &cs[i]; + size_t thislen; + + /* +1 to account for nulterm */ + thislen = sprintf(pos, "%s" + "%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x" + "%s", + c->magic, c->ino, c->mode, c->uid, c->gid, c->nlink, + c->mtime, c->filesize, c->devmajor, c->devminor, + c->rdevmajor, c->rdevminor, c->namesize, c->csum, + c->fname) + 1; + pr_debug("packing (%zu): %.*s\n", thislen, (int)thislen, pos); + off += thislen; + while (off & 3) + out[off++] = '\0'; + + memcpy(&out[off], c->data, c->filesize); + off += c->filesize; + while (off & 3) + out[off++] = '\0'; + } + + return off; +} + +static void __init initramfs_test_extract(struct kunit *test) +{ + char *err, *cpio_srcbuf; + size_t len; + struct timespec64 ts_before, ts_after; + struct kstat st = {}; + struct initramfs_test_cpio c[] = { { + .magic = "070701", + .ino = 1, + .mode = S_IFREG | 0777, + .uid = 12, + .gid = 34, + .nlink = 1, + .mtime = 56, + .filesize = 0, + .devmajor = 0, + .devminor = 1, + .rdevmajor = 0, + .rdevminor = 0, + .namesize = sizeof("initramfs_test_extract"), + .csum = 0, + .fname = "initramfs_test_extract", + }, { + .magic = "070701", + .ino = 2, + .mode = S_IFDIR | 0777, + .nlink = 1, + .mtime = 57, + .devminor = 1, + .namesize = sizeof("initramfs_test_extract_dir"), + .fname = "initramfs_test_extract_dir", + }, { + .magic = "070701", + .namesize = sizeof("TRAILER!!!"), + .fname = "TRAILER!!!", + } }; + + /* +3 to cater for any 4-byte end-alignment */ + cpio_srcbuf = kzalloc(ARRAY_SIZE(c) * (CPIO_HDRLEN + PATH_MAX + 3), + GFP_KERNEL); + len = fill_cpio(c, ARRAY_SIZE(c), cpio_srcbuf); + + ktime_get_real_ts64(&ts_before); + err = unpack_to_rootfs(cpio_srcbuf, len); + ktime_get_real_ts64(&ts_after); + if (err) { + KUNIT_FAIL(test, "unpack failed %s", err); + goto out; + } + + KUNIT_EXPECT_EQ(test, init_stat(c[0].fname, &st, 0), 0); + KUNIT_EXPECT_TRUE(test, S_ISREG(st.mode)); + KUNIT_EXPECT_TRUE(test, uid_eq(st.uid, KUIDT_INIT(c[0].uid))); + KUNIT_EXPECT_TRUE(test, gid_eq(st.gid, KGIDT_INIT(c[0].gid))); + KUNIT_EXPECT_EQ(test, st.nlink, 1); + if (IS_ENABLED(CONFIG_INITRAMFS_PRESERVE_MTIME)) { + KUNIT_EXPECT_EQ(test, st.mtime.tv_sec, c[0].mtime); + } else { + KUNIT_EXPECT_GE(test, st.mtime.tv_sec, ts_before.tv_sec); + KUNIT_EXPECT_LE(test, st.mtime.tv_sec, ts_after.tv_sec); + } + KUNIT_EXPECT_EQ(test, st.blocks, c[0].filesize); + + KUNIT_EXPECT_EQ(test, init_stat(c[1].fname, &st, 0), 0); + KUNIT_EXPECT_TRUE(test, S_ISDIR(st.mode)); + if (IS_ENABLED(CONFIG_INITRAMFS_PRESERVE_MTIME)) { + KUNIT_EXPECT_EQ(test, st.mtime.tv_sec, c[1].mtime); + } else { + KUNIT_EXPECT_GE(test, st.mtime.tv_sec, ts_before.tv_sec); + KUNIT_EXPECT_LE(test, st.mtime.tv_sec, ts_after.tv_sec); + } + + KUNIT_EXPECT_EQ(test, init_unlink(c[0].fname), 0); + KUNIT_EXPECT_EQ(test, init_rmdir(c[1].fname), 0); +out: + kfree(cpio_srcbuf); +} + +/* + * Don't terminate filename. Previously, the cpio filename field was passed + * directly to filp_open(collected, O_CREAT|..) without nulterm checks. See + * https://lore.kernel.org/linux-fsdevel/20241030035509.20194-2-ddiss@suse.de + */ +static void __init initramfs_test_fname_overrun(struct kunit *test) +{ + char *err, *cpio_srcbuf; + size_t len, suffix_off; + struct initramfs_test_cpio c[] = { { + .magic = "070701", + .ino = 1, + .mode = S_IFREG | 0777, + .uid = 0, + .gid = 0, + .nlink = 1, + .mtime = 1, + .filesize = 0, + .devmajor = 0, + .devminor = 1, + .rdevmajor = 0, + .rdevminor = 0, + .namesize = sizeof("initramfs_test_fname_overrun"), + .csum = 0, + .fname = "initramfs_test_fname_overrun", + } }; + + /* + * poison cpio source buffer, so we can detect overrun. source + * buffer is used by read_into() when hdr or fname + * are already available (e.g. no compression). + */ + cpio_srcbuf = kmalloc(CPIO_HDRLEN + PATH_MAX + 3, GFP_KERNEL); + memset(cpio_srcbuf, 'B', CPIO_HDRLEN + PATH_MAX + 3); + /* limit overrun to avoid crashes / filp_open() ENAMETOOLONG */ + cpio_srcbuf[CPIO_HDRLEN + strlen(c[0].fname) + 20] = '\0'; + + len = fill_cpio(c, ARRAY_SIZE(c), cpio_srcbuf); + /* overwrite trailing fname terminator and padding */ + suffix_off = len - 1; + while (cpio_srcbuf[suffix_off] == '\0') { + cpio_srcbuf[suffix_off] = 'P'; + suffix_off--; + } + + err = unpack_to_rootfs(cpio_srcbuf, len); + KUNIT_EXPECT_NOT_NULL(test, err); + + kfree(cpio_srcbuf); +} + +static void __init initramfs_test_data(struct kunit *test) +{ + char *err, *cpio_srcbuf; + size_t len; + struct file *file; + struct initramfs_test_cpio c[] = { { + .magic = "070701", + .ino = 1, + .mode = S_IFREG | 0777, + .uid = 0, + .gid = 0, + .nlink = 1, + .mtime = 1, + .filesize = sizeof("ASDF") - 1, + .devmajor = 0, + .devminor = 1, + .rdevmajor = 0, + .rdevminor = 0, + .namesize = sizeof("initramfs_test_data"), + .csum = 0, + .fname = "initramfs_test_data", + .data = "ASDF", + } }; + + /* +6 for max name and data 4-byte padding */ + cpio_srcbuf = kmalloc(CPIO_HDRLEN + c[0].namesize + c[0].filesize + 6, + GFP_KERNEL); + + len = fill_cpio(c, ARRAY_SIZE(c), cpio_srcbuf); + + err = unpack_to_rootfs(cpio_srcbuf, len); + KUNIT_EXPECT_NULL(test, err); + + file = filp_open(c[0].fname, O_RDONLY, 0); + if (IS_ERR(file)) { + KUNIT_FAIL(test, "open failed"); + goto out; + } + + /* read back file contents into @cpio_srcbuf and confirm match */ + len = kernel_read(file, cpio_srcbuf, c[0].filesize, NULL); + KUNIT_EXPECT_EQ(test, len, c[0].filesize); + KUNIT_EXPECT_MEMEQ(test, cpio_srcbuf, c[0].data, len); + + fput(file); + KUNIT_EXPECT_EQ(test, init_unlink(c[0].fname), 0); +out: + kfree(cpio_srcbuf); +} + +static void __init initramfs_test_csum(struct kunit *test) +{ + char *err, *cpio_srcbuf; + size_t len; + struct initramfs_test_cpio c[] = { { + /* 070702 magic indicates a valid csum is present */ + .magic = "070702", + .ino = 1, + .mode = S_IFREG | 0777, + .nlink = 1, + .filesize = sizeof("ASDF") - 1, + .devminor = 1, + .namesize = sizeof("initramfs_test_csum"), + .csum = 'A' + 'S' + 'D' + 'F', + .fname = "initramfs_test_csum", + .data = "ASDF", + }, { + /* mix csum entry above with no-csum entry below */ + .magic = "070701", + .ino = 2, + .mode = S_IFREG | 0777, + .nlink = 1, + .filesize = sizeof("ASDF") - 1, + .devminor = 1, + .namesize = sizeof("initramfs_test_csum_not_here"), + /* csum ignored */ + .csum = 5555, + .fname = "initramfs_test_csum_not_here", + .data = "ASDF", + } }; + + cpio_srcbuf = kmalloc(8192, GFP_KERNEL); + + len = fill_cpio(c, ARRAY_SIZE(c), cpio_srcbuf); + + err = unpack_to_rootfs(cpio_srcbuf, len); + KUNIT_EXPECT_NULL(test, err); + + KUNIT_EXPECT_EQ(test, init_unlink(c[0].fname), 0); + KUNIT_EXPECT_EQ(test, init_unlink(c[1].fname), 0); + + /* mess up the csum and confirm that unpack fails */ + c[0].csum--; + len = fill_cpio(c, ARRAY_SIZE(c), cpio_srcbuf); + + err = unpack_to_rootfs(cpio_srcbuf, len); + KUNIT_EXPECT_NOT_NULL(test, err); + + /* + * file (with content) is still retained in case of bad-csum abort. + * Perhaps we should change this. + */ + KUNIT_EXPECT_EQ(test, init_unlink(c[0].fname), 0); + KUNIT_EXPECT_EQ(test, init_unlink(c[1].fname), -ENOENT); + kfree(cpio_srcbuf); +} + +/* + * hardlink hashtable may leak when the archive omits a trailer: + * https://lore.kernel.org/r/20241107002044.16477-10-ddiss@suse.de/ + */ +static void __init initramfs_test_hardlink(struct kunit *test) +{ + char *err, *cpio_srcbuf; + size_t len; + struct kstat st0, st1; + struct initramfs_test_cpio c[] = { { + .magic = "070701", + .ino = 1, + .mode = S_IFREG | 0777, + .nlink = 2, + .devminor = 1, + .namesize = sizeof("initramfs_test_hardlink"), + .fname = "initramfs_test_hardlink", + }, { + /* hardlink data is present in last archive entry */ + .magic = "070701", + .ino = 1, + .mode = S_IFREG | 0777, + .nlink = 2, + .filesize = sizeof("ASDF") - 1, + .devminor = 1, + .namesize = sizeof("initramfs_test_hardlink_link"), + .fname = "initramfs_test_hardlink_link", + .data = "ASDF", + } }; + + cpio_srcbuf = kmalloc(8192, GFP_KERNEL); + + len = fill_cpio(c, ARRAY_SIZE(c), cpio_srcbuf); + + err = unpack_to_rootfs(cpio_srcbuf, len); + KUNIT_EXPECT_NULL(test, err); + + KUNIT_EXPECT_EQ(test, init_stat(c[0].fname, &st0, 0), 0); + KUNIT_EXPECT_EQ(test, init_stat(c[1].fname, &st1, 0), 0); + KUNIT_EXPECT_EQ(test, st0.ino, st1.ino); + KUNIT_EXPECT_EQ(test, st0.nlink, 2); + KUNIT_EXPECT_EQ(test, st1.nlink, 2); + + KUNIT_EXPECT_EQ(test, init_unlink(c[0].fname), 0); + KUNIT_EXPECT_EQ(test, init_unlink(c[1].fname), 0); + + kfree(cpio_srcbuf); +} + +#define INITRAMFS_TEST_MANY_LIMIT 1000 +#define INITRAMFS_TEST_MANY_PATH_MAX (sizeof("initramfs_test_many-") \ + + sizeof(__stringify(INITRAMFS_TEST_MANY_LIMIT))) +static void __init initramfs_test_many(struct kunit *test) +{ + char *err, *cpio_srcbuf, *p; + size_t len = INITRAMFS_TEST_MANY_LIMIT * + (CPIO_HDRLEN + INITRAMFS_TEST_MANY_PATH_MAX + 3); + char thispath[INITRAMFS_TEST_MANY_PATH_MAX]; + int i; + + p = cpio_srcbuf = kmalloc(len, GFP_KERNEL); + + for (i = 0; i < INITRAMFS_TEST_MANY_LIMIT; i++) { + struct initramfs_test_cpio c = { + .magic = "070701", + .ino = i, + .mode = S_IFREG | 0777, + .nlink = 1, + .devminor = 1, + .fname = thispath, + }; + + c.namesize = 1 + sprintf(thispath, "initramfs_test_many-%d", i); + p += fill_cpio(&c, 1, p); + } + + len = p - cpio_srcbuf; + err = unpack_to_rootfs(cpio_srcbuf, len); + KUNIT_EXPECT_NULL(test, err); + + for (i = 0; i < INITRAMFS_TEST_MANY_LIMIT; i++) { + sprintf(thispath, "initramfs_test_many-%d", i); + KUNIT_EXPECT_EQ(test, init_unlink(thispath), 0); + } + + kfree(cpio_srcbuf); +} + +/* + * The kunit_case/_suite struct cannot be marked as __initdata as this will be + * used in debugfs to retrieve results after test has run. + */ +static struct kunit_case __refdata initramfs_test_cases[] = { + KUNIT_CASE(initramfs_test_extract), + KUNIT_CASE(initramfs_test_fname_overrun), + KUNIT_CASE(initramfs_test_data), + KUNIT_CASE(initramfs_test_csum), + KUNIT_CASE(initramfs_test_hardlink), + KUNIT_CASE(initramfs_test_many), + {}, +}; + +static struct kunit_suite initramfs_test_suite = { + .name = "initramfs", + .test_cases = initramfs_test_cases, +}; +kunit_test_init_section_suites(&initramfs_test_suite); + +MODULE_DESCRIPTION("Initramfs KUnit test suite"); +MODULE_LICENSE("GPL v2"); diff --git a/init/main.c b/init/main.c index 2a1757826397..225a58279acd 100644 --- a/init/main.c +++ b/init/main.c @@ -13,6 +13,7 @@ #define DEBUG /* Enable initcall_debug */ #include <linux/types.h> +#include <linux/export.h> #include <linux/extable.h> #include <linux/module.h> #include <linux/proc_fs.h> @@ -50,6 +51,7 @@ #include <linux/writeback.h> #include <linux/cpu.h> #include <linux/cpuset.h> +#include <linux/memcontrol.h> #include <linux/cgroup.h> #include <linux/efi.h> #include <linux/tick.h> @@ -1002,7 +1004,7 @@ void start_kernel(void) init_IRQ(); tick_init(); rcu_init_nohz(); - init_timers(); + timers_init(); srcu_init(); hrtimers_init(); softirq_init(); @@ -1087,6 +1089,7 @@ void start_kernel(void) nsfs_init(); pidfs_init(); cpuset_init(); + mem_cgroup_init(); cgroup_init(); taskstats_init_early(); delayacct_init(); @@ -1214,6 +1217,12 @@ trace_initcall_finish_cb(void *data, initcall_t fn, int ret) fn, ret, (unsigned long long)ktime_us_delta(rettime, *calltime)); } +static __init_or_module void +trace_initcall_level_cb(void *data, const char *level) +{ + printk(KERN_DEBUG "entering initcall level: %s\n", level); +} + static ktime_t initcall_calltime; #ifdef TRACEPOINTS_ENABLED @@ -1225,10 +1234,12 @@ static void __init initcall_debug_enable(void) &initcall_calltime); ret |= register_trace_initcall_finish(trace_initcall_finish_cb, &initcall_calltime); + ret |= register_trace_initcall_level(trace_initcall_level_cb, NULL); WARN(ret, "Failed to register initcall tracepoints\n"); } # define do_trace_initcall_start trace_initcall_start # define do_trace_initcall_finish trace_initcall_finish +# define do_trace_initcall_level trace_initcall_level #else static inline void do_trace_initcall_start(initcall_t fn) { @@ -1242,6 +1253,12 @@ static inline void do_trace_initcall_finish(initcall_t fn, int ret) return; trace_initcall_finish_cb(&initcall_calltime, fn, ret); } +static inline void do_trace_initcall_level(const char *level) +{ + if (!initcall_debug) + return; + trace_initcall_level_cb(NULL, level); +} #endif /* !TRACEPOINTS_ENABLED */ int __init_or_module do_one_initcall(initcall_t fn) @@ -1314,7 +1331,7 @@ static void __init do_initcall_level(int level, char *command_line) level, level, NULL, ignore_unknown_bootoption); - trace_initcall_level(initcall_level_names[level]); + do_trace_initcall_level(initcall_level_names[level]); for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++) do_one_initcall(initcall_from_entry(fn)); } @@ -1358,7 +1375,7 @@ static void __init do_pre_smp_initcalls(void) { initcall_entry_t *fn; - trace_initcall_level("early"); + do_trace_initcall_level("early"); for (fn = __initcall_start; fn < __initcall0_start; fn++) do_one_initcall(initcall_from_entry(fn)); } @@ -1553,7 +1570,6 @@ static noinline void __init kernel_init_freeable(void) init_mm_internals(); - rcu_init_tasks_generic(); do_pre_smp_initcalls(); lockup_detector_init(); |