// SPDX-License-Identifier: GPL-2.0-only/* * linux/fs/exec.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * #!-checking implemented by tytso. *//* * Demand-loading implemented 01.12.91 - no need to read anything but * the header into memory. The inode of the executable is put into * "current->executable", and page faults do the actual loading. Clean. * * Once more I can proudly say that linux stood up to being changed: it * was less than 2 hours work to get demand-loading completely implemented. * * Demand loading changed July 1993 by Eric Youngdale. Use mmap instead, * current->executable is only used by the procfs. This allows a dispatch * table to check for several different types of binary formats. We keep * trying until we recognize the file or we run out of supported binary * formats. */ #include <linux/kernel_read_file.h>#include <linux/slab.h>#include <linux/file.h>#include <linux/fdtable.h>#include <linux/mm.h>#include <linux/stat.h>#include <linux/fcntl.h>#include <linux/swap.h>#include <linux/string.h>#include <linux/init.h>#include <linux/sched/mm.h>#include <linux/sched/coredump.h>#include <linux/sched/signal.h>#include <linux/sched/numa_balancing.h>#include <linux/sched/task.h>#include <linux/pagemap.h>#include <linux/perf_event.h>#include <linux/highmem.h>#include <linux/spinlock.h>#include <linux/key.h>#include <linux/personality.h>#include <linux/binfmts.h>#include <linux/utsname.h>#include <linux/pid_namespace.h>#include <linux/module.h>#include <linux/namei.h>#include <linux/mount.h>#include <linux/security.h>#include <linux/syscalls.h>#include <linux/tsacct_kern.h>#include <linux/cn_proc.h>#include <linux/audit.h>#include <linux/kmod.h>#include <linux/fsnotify.h>#include <linux/fs_struct.h>#include <linux/oom.h>#include <linux/compat.h>#include <linux/vmalloc.h>#include <linux/io_uring.h>#include <linux/syscall_user_dispatch.h>#include <linux/coredump.h>#include <linux/time_namespace.h>#include <linux/user_events.h>#include <linux/rseq.h>#include <linux/ksm.h> #include <linux/uaccess.h>#include <asm/mmu_context.h>#include <asm/tlb.h> #include <trace/events/task.h>#include "internal.h" #include <trace/events/sched.h> /* For vma exec functions. */#include "../mm/internal.h" static int bprm_creds_from_file(struct linux_binprm *bprm); int suid_dumpable = 0; static LIST_HEAD(formats);static DEFINE_RWLOCK(binfmt_lock); void __register_binfmt(struct linux_binfmt * fmt, int insert){ write_lock(&binfmt_lock); insert ? list_add(&fmt->lh, &formats) : list_add_tail(&fmt->lh, &formats); write_unlock(&binfmt_lock);} EXPORT_SYMBOL(__register_binfmt); void unregister_binfmt(struct linux_binfmt * fmt){ write_lock(&binfmt_lock); list_del(&fmt->lh); write_unlock(&binfmt_lock);} EXPORT_SYMBOL(unregister_binfmt); static inline void put_binfmt(struct linux_binfmt * fmt){ module_put(fmt->module);} bool path_noexec(const struct path *path){ /* If it's an anonymous inode make sure that we catch any shenanigans. */ VFS_WARN_ON_ONCE(IS_ANON_FILE(d_inode(path->dentry)) && !(path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC)); return (path->mnt->mnt_flags & MNT_NOEXEC) || (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC);} #ifdef CONFIG_MMU/* * The nascent bprm->mm is not visible until exec_mmap() but it can * use a lot of memory, account these pages in current->mm temporary * for oom_badness()->get_mm_rss(). Once exec succeeds or fails, we * change the counter back via acct_arg_size(0). */static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages){ struct mm_struct *mm = current->mm; long diff = (long)(pages - bprm->vma_pages); if (!mm || !diff) return; bprm->vma_pages = pages; add_mm_counter(mm, MM_ANONPAGES, diff);} static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write){ struct page *page; struct vm_area_struct *vma = bprm->vma; struct mm_struct *mm = bprm->mm; int ret; /* * Avoid relying on expanding the stack down in GUP (which * does not work for STACK_GROWSUP anyway), and just do it * ahead of time. */ if (!mmap_read_lock_maybe_expand(mm, vma, pos, write)) return NULL; /* * We are doing an exec(). 'current' is the process * doing the exec and 'mm' is the new process's mm. */ ret = get_user_pages_remote(mm, pos, 1, write ? FOLL_WRITE : 0, &page, NULL); mmap_read_unlock(mm); if (ret <= 0) return NULL; if (write) acct_arg_size(bprm, vma_pages(vma)); return page;} static void put_arg_page(struct page *page){ put_page(page);} static void free_arg_pages(struct linux_binprm *bprm){} static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page){ flush_cache_page(bprm->vma, pos, page_to_pfn(page));} static bool valid_arg_len(struct linux_binprm *bprm, long len){ return len <= MAX_ARG_STRLEN;} #else static inline void acct_arg_size(struct linux_binprm *bprm, unsigned long pages){} static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write){ struct page *page; page = bprm->page[pos / PAGE_SIZE]; if (!page && write) { page = alloc_page(GFP_HIGHUSER|__GFP_ZERO); if (!page) return NULL; bprm->page[pos / PAGE_SIZE] = page; } return page;} static void put_arg_page(struct page *page){} static void free_arg_page(struct linux_binprm *bprm, int i){ if (bprm->page[i]) { __free_page(bprm->page[i]); bprm->page[i] = NULL; }} static void free_arg_pages(struct linux_binprm *bprm){ int i; for (i = 0; i < MAX_ARG_PAGES; i++) free_arg_page(bprm, i);} static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page){} static bool valid_arg_len(struct linux_binprm *bprm, long len){ return len <= bprm->p;} #endif /* CONFIG_MMU */ /* * Create a new mm_struct and populate it with a temporary stack * vm_area_struct. We don't have enough context at this point to set the stack * flags, permissions, and offset, so we use temporary values. We'll update * them later in setup_arg_pages(). */static int bprm_mm_init(struct linux_binprm *bprm){ int err; struct mm_struct *mm = NULL; bprm->mm = mm = mm_alloc(); err = -ENOMEM; if (!mm) goto err; /* Save current stack limit for all calculations made during exec. */ task_lock(current->group_leader); bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK]; task_unlock(current->group_leader); #ifndef CONFIG_MMU bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *);#else err = create_init_stack_vma(bprm->mm, &bprm->vma, &bprm->p); if (err) goto err;#endif return 0; err: if (mm) { bprm->mm = NULL; mmdrop(mm); } return err;} struct user_arg_ptr {#ifdef CONFIG_COMPAT bool is_compat;#endif union { const char __user *const __user *native;#ifdef CONFIG_COMPAT const compat_uptr_t __user *compat;#endif } ptr;}; static const char __user *get_user_arg_ptr(struct user_arg_ptr argv, int nr){ const char __user *native; #ifdef CONFIG_COMPAT if (unlikely(argv.is_compat)) { compat_uptr_t compat; if (get_user(compat, argv.ptr.compat + nr)) return ERR_PTR(-EFAULT); return compat_ptr(compat); }#endif if (get_user(native, argv.ptr.native + nr)) return ERR_PTR(-EFAULT); return native;} /* * count() counts the number of strings in array ARGV. */static int count(struct user_arg_ptr argv, int max){ int i = 0; if (argv.ptr.native != NULL) { for (;;) { const char __user *p = get_user_arg_ptr(argv, i); if (!p) break; if (IS_ERR(p)) return -EFAULT; if (i >= max) return -E2BIG; ++i; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } } return i;} static int count_strings_kernel(const char *const *argv){ int i; if (!argv) return 0; for (i = 0; argv[i]; ++i) { if (i >= MAX_ARG_STRINGS) return -E2BIG; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } return i;} static inline int bprm_set_stack_limit(struct linux_binprm *bprm, unsigned long limit){#ifdef CONFIG_MMU /* Avoid a pathological bprm->p. */ if (bprm->p < limit) return -E2BIG; bprm->argmin = bprm->p - limit;#endif return 0;}static inline bool bprm_hit_stack_limit(struct linux_binprm *bprm){#ifdef CONFIG_MMU return bprm->p < bprm->argmin;#else return false;#endif} /* * Calculate bprm->argmin from: * - _STK_LIM * - ARG_MAX * - bprm->rlim_stack.rlim_cur * - bprm->argc * - bprm->envc * - bprm->p */static int bprm_stack_limits(struct linux_binprm *bprm){ unsigned long limit, ptr_size; /* * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM * (whichever is smaller) for the argv+env strings. * This ensures that: * - the remaining binfmt code will not run out of stack space, * - the program will have a reasonable amount of stack left * to work from. */ limit = _STK_LIM / 4 * 3; limit = min(limit, bprm->rlim_stack.rlim_cur / 4); /* * We've historically supported up to 32 pages (ARG_MAX) * of argument strings even with small stacks */ limit = max_t(unsigned long, limit, ARG_MAX); /* Reject totally pathological counts. */ if (bprm->argc < 0 || bprm->envc < 0) return -E2BIG; /* * We must account for the size of all the argv and envp pointers to * the argv and envp strings, since they will also take up space in * the stack. They aren't stored until much later when we can't * signal to the parent that the child has run out of stack space. * Instead, calculate it here so it's possible to fail gracefully. * * In the case of argc = 0, make sure there is space for adding a * empty string (which will bump argc to 1), to ensure confused * userspace programs don't start processing from argv[1], thinking * argc can never be 0, to keep them from walking envp by accident. * See do_execveat_common(). */ if (check_add_overflow(max(bprm->argc, 1), bprm->envc, &ptr_size) || check_mul_overflow(ptr_size, sizeof(void *), &ptr_size)) return -E2BIG; if (limit <= ptr_size) return -E2BIG; limit -= ptr_size; return bprm_set_stack_limit(bprm, limit);} /* * 'copy_strings()' copies argument/environment strings from the old * processes's memory to the new process's stack. The call to get_user_pages() * ensures the destination page is created and not swapped out. */static int copy_strings(int argc, struct user_arg_ptr argv, struct linux_binprm *bprm){ struct page *kmapped_page = NULL; char *kaddr = NULL; unsigned long kpos = 0; int ret; while (argc-- > 0) { const char __user *str; int len; unsigned long pos; ret = -EFAULT; str = get_user_arg_ptr(argv, argc); if (IS_ERR(str)) goto out; len = strnlen_user(str, MAX_ARG_STRLEN); if (!len) goto out; ret = -E2BIG; if (!valid_arg_len(bprm, len)) goto out; /* We're going to work our way backwards. */ pos = bprm->p; str += len; bprm->p -= len; if (bprm_hit_stack_limit(bprm)) goto out; while (len > 0) { int offset, bytes_to_copy; if (fatal_signal_pending(current)) { ret = -ERESTARTNOHAND; goto out; } cond_resched(); offset = pos % PAGE_SIZE; if (offset == 0) offset = PAGE_SIZE; bytes_to_copy = offset; if (bytes_to_copy > len) bytes_to_copy = len; offset -= bytes_to_copy; pos -= bytes_to_copy; str -= bytes_to_copy;Lines 1–500 of 2079. Load more
// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/exec.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * #!-checking implemented by tytso. */ /* * Demand-loading implemented 01.12.91 - no need to read anything but * the header into memory. The inode of the executable is put into * "current->executable", and page faults do the actual loading. Clean. * * Once more I can proudly say that linux stood up to being changed: it * was less than 2 hours work to get demand-loading completely implemented. * * Demand loading changed July 1993 by Eric Youngdale. Use mmap instead, * current->executable is only used by the procfs. This allows a dispatch * table to check for several different types of binary formats. We keep * trying until we recognize the file or we run out of supported binary * formats. */ #include <linux/kernel_read_file.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/mm.h> #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/signal.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/perf_event.h> #include <linux/highmem.h> #include <linux/spinlock.h> #include <linux/key.h> #include <linux/personality.h> #include <linux/binfmts.h> #include <linux/utsname.h> #include <linux/pid_namespace.h> #include <linux/module.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/audit.h> #include <linux/kmod.h> #include <linux/fsnotify.h> #include <linux/fs_struct.h> #include <linux/oom.h> #include <linux/compat.h> #include <linux/vmalloc.h> #include <linux/io_uring.h> #include <linux/syscall_user_dispatch.h> #include <linux/coredump.h> #include <linux/time_namespace.h> #include <linux/user_events.h> #include <linux/rseq.h> #include <linux/ksm.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/tlb.h> #include <trace/events/task.h> #include "internal.h" #include <trace/events/sched.h> /* For vma exec functions. */ #include "../mm/internal.h" static int bprm_creds_from_file(struct linux_binprm *bprm); int suid_dumpable = 0; static LIST_HEAD(formats); static DEFINE_RWLOCK(binfmt_lock); void __register_binfmt(struct linux_binfmt * fmt, int insert) { write_lock(&binfmt_lock); insert ? list_add(&fmt->lh, &formats) : list_add_tail(&fmt->lh, &formats); write_unlock(&binfmt_lock); } EXPORT_SYMBOL(__register_binfmt); void unregister_binfmt(struct linux_binfmt * fmt) { write_lock(&binfmt_lock); list_del(&fmt->lh); write_unlock(&binfmt_lock); } EXPORT_SYMBOL(unregister_binfmt); static inline void put_binfmt(struct linux_binfmt * fmt) { module_put(fmt->module); } bool path_noexec(const struct path *path) { /* If it's an anonymous inode make sure that we catch any shenanigans. */ VFS_WARN_ON_ONCE(IS_ANON_FILE(d_inode(path->dentry)) && !(path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC)); return (path->mnt->mnt_flags & MNT_NOEXEC) || (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC); } #ifdef CONFIG_MMU /* * The nascent bprm->mm is not visible until exec_mmap() but it can * use a lot of memory, account these pages in current->mm temporary * for oom_badness()->get_mm_rss(). Once exec succeeds or fails, we * change the counter back via acct_arg_size(0). */ static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { struct mm_struct *mm = current->mm; long diff = (long)(pages - bprm->vma_pages); if (!mm || !diff) return; bprm->vma_pages = pages; add_mm_counter(mm, MM_ANONPAGES, diff); } static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; struct vm_area_struct *vma = bprm->vma; struct mm_struct *mm = bprm->mm; int ret; /* * Avoid relying on expanding the stack down in GUP (which * does not work for STACK_GROWSUP anyway), and just do it * ahead of time. */ if (!mmap_read_lock_maybe_expand(mm, vma, pos, write)) return NULL; /* * We are doing an exec(). 'current' is the process * doing the exec and 'mm' is the new process's mm. */ ret = get_user_pages_remote(mm, pos, 1, write ? FOLL_WRITE : 0, &page, NULL); mmap_read_unlock(mm); if (ret <= 0) return NULL; if (write) acct_arg_size(bprm, vma_pages(vma)); return page; } static void put_arg_page(struct page *page) { put_page(page); } static void free_arg_pages(struct linux_binprm *bprm) { } static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page) { flush_cache_page(bprm->vma, pos, page_to_pfn(page)); } static bool valid_arg_len(struct linux_binprm *bprm, long len) { return len <= MAX_ARG_STRLEN; } #else static inline void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { } static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; page = bprm->page[pos / PAGE_SIZE]; if (!page && write) { page = alloc_page(GFP_HIGHUSER|__GFP_ZERO); if (!page) return NULL; bprm->page[pos / PAGE_SIZE] = page; } return page; } static void put_arg_page(struct page *page) { } static void free_arg_page(struct linux_binprm *bprm, int i) { if (bprm->page[i]) { __free_page(bprm->page[i]); bprm->page[i] = NULL; } } static void free_arg_pages(struct linux_binprm *bprm) { int i; for (i = 0; i < MAX_ARG_PAGES; i++) free_arg_page(bprm, i); } static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page) { } static bool valid_arg_len(struct linux_binprm *bprm, long len) { return len <= bprm->p; } #endif /* CONFIG_MMU */ /* * Create a new mm_struct and populate it with a temporary stack * vm_area_struct. We don't have enough context at this point to set the stack * flags, permissions, and offset, so we use temporary values. We'll update * them later in setup_arg_pages(). */ static int bprm_mm_init(struct linux_binprm *bprm) { int err; struct mm_struct *mm = NULL; bprm->mm = mm = mm_alloc(); err = -ENOMEM; if (!mm) goto err; /* Save current stack limit for all calculations made during exec. */ task_lock(current->group_leader); bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK]; task_unlock(current->group_leader); #ifndef CONFIG_MMU bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *); #else err = create_init_stack_vma(bprm->mm, &bprm->vma, &bprm->p); if (err) goto err; #endif return 0; err: if (mm) { bprm->mm = NULL; mmdrop(mm); } return err; } struct user_arg_ptr { #ifdef CONFIG_COMPAT bool is_compat; #endif union { const char __user *const __user *native; #ifdef CONFIG_COMPAT const compat_uptr_t __user *compat; #endif } ptr; }; static const char __user *get_user_arg_ptr(struct user_arg_ptr argv, int nr) { const char __user *native; #ifdef CONFIG_COMPAT if (unlikely(argv.is_compat)) { compat_uptr_t compat; if (get_user(compat, argv.ptr.compat + nr)) return ERR_PTR(-EFAULT); return compat_ptr(compat); } #endif if (get_user(native, argv.ptr.native + nr)) return ERR_PTR(-EFAULT); return native; } /* * count() counts the number of strings in array ARGV. */ static int count(struct user_arg_ptr argv, int max) { int i = 0; if (argv.ptr.native != NULL) { for (;;) { const char __user *p = get_user_arg_ptr(argv, i); if (!p) break; if (IS_ERR(p)) return -EFAULT; if (i >= max) return -E2BIG; ++i; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } } return i; } static int count_strings_kernel(const char *const *argv) { int i; if (!argv) return 0; for (i = 0; argv[i]; ++i) { if (i >= MAX_ARG_STRINGS) return -E2BIG; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } return i; } static inline int bprm_set_stack_limit(struct linux_binprm *bprm, unsigned long limit) { #ifdef CONFIG_MMU /* Avoid a pathological bprm->p. */ if (bprm->p < limit) return -E2BIG; bprm->argmin = bprm->p - limit; #endif return 0; } static inline bool bprm_hit_stack_limit(struct linux_binprm *bprm) { #ifdef CONFIG_MMU return bprm->p < bprm->argmin; #else return false; #endif } /* * Calculate bprm->argmin from: * - _STK_LIM * - ARG_MAX * - bprm->rlim_stack.rlim_cur * - bprm->argc * - bprm->envc * - bprm->p */ static int bprm_stack_limits(struct linux_binprm *bprm) { unsigned long limit, ptr_size; /* * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM * (whichever is smaller) for the argv+env strings. * This ensures that: * - the remaining binfmt code will not run out of stack space, * - the program will have a reasonable amount of stack left * to work from. */ limit = _STK_LIM / 4 * 3; limit = min(limit, bprm->rlim_stack.rlim_cur / 4); /* * We've historically supported up to 32 pages (ARG_MAX) * of argument strings even with small stacks */ limit = max_t(unsigned long, limit, ARG_MAX); /* Reject totally pathological counts. */ if (bprm->argc < 0 || bprm->envc < 0) return -E2BIG; /* * We must account for the size of all the argv and envp pointers to * the argv and envp strings, since they will also take up space in * the stack. They aren't stored until much later when we can't * signal to the parent that the child has run out of stack space. * Instead, calculate it here so it's possible to fail gracefully. * * In the case of argc = 0, make sure there is space for adding a * empty string (which will bump argc to 1), to ensure confused * userspace programs don't start processing from argv[1], thinking * argc can never be 0, to keep them from walking envp by accident. * See do_execveat_common(). */ if (check_add_overflow(max(bprm->argc, 1), bprm->envc, &ptr_size) || check_mul_overflow(ptr_size, sizeof(void *), &ptr_size)) return -E2BIG; if (limit <= ptr_size) return -E2BIG; limit -= ptr_size; return bprm_set_stack_limit(bprm, limit); } /* * 'copy_strings()' copies argument/environment strings from the old * processes's memory to the new process's stack. The call to get_user_pages() * ensures the destination page is created and not swapped out. */ static int copy_strings(int argc, struct user_arg_ptr argv, struct linux_binprm *bprm) { struct page *kmapped_page = NULL; char *kaddr = NULL; unsigned long kpos = 0; int ret; while (argc-- > 0) { const char __user *str; int len; unsigned long pos; ret = -EFAULT; str = get_user_arg_ptr(argv, argc); if (IS_ERR(str)) goto out; len = strnlen_user(str, MAX_ARG_STRLEN); if (!len) goto out; ret = -E2BIG; if (!valid_arg_len(bprm, len)) goto out; /* We're going to work our way backwards. */ pos = bprm->p; str += len; bprm->p -= len; if (bprm_hit_stack_limit(bprm)) goto out; while (len > 0) { int offset, bytes_to_copy; if (fatal_signal_pending(current)) { ret = -ERESTARTNOHAND; goto out; } cond_resched(); offset = pos % PAGE_SIZE; if (offset == 0) offset = PAGE_SIZE; bytes_to_copy = offset; if (bytes_to_copy > len) bytes_to_copy = len; offset -= bytes_to_copy; pos -= bytes_to_copy; str -= bytes_to_copy;