X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fexec.c;h=632b02e34ec72b17564602f9c944996e4889a9cf;hb=d5aa407f59f5b83d2c50ec88f5bf56d40f1f8978;hp=c466fec5de2005cee77acfc7a2f120afefcd33f8;hpb=8c744fb83da0771afa04695028e3550b798dad90;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/exec.c b/fs/exec.c index c466fec..632b02e 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -22,90 +22,73 @@ * formats. */ -#include #include #include -#include -#include +#include +#include #include #include #include +#include +#include #include #include +#include #include #include #include #include #include -#include #include +#include #include #include #include -#include #include #include #include -#include -#include +#include #include +#include +#include +#include +#include +#include +#include #include #include - -#ifdef CONFIG_KMOD -#include -#endif +#include +#include "internal.h" int core_uses_pid; -char core_pattern[65] = "core"; +char core_pattern[CORENAME_MAX_SIZE] = "core"; +unsigned int core_pipe_limit; int suid_dumpable = 0; -EXPORT_SYMBOL(suid_dumpable); /* The maximal length of core_pattern is also specified in sysctl.c */ -static struct linux_binfmt *formats; +static LIST_HEAD(formats); static DEFINE_RWLOCK(binfmt_lock); -int register_binfmt(struct linux_binfmt * fmt) +int __register_binfmt(struct linux_binfmt * fmt, int insert) { - struct linux_binfmt ** tmp = &formats; - if (!fmt) return -EINVAL; - if (fmt->next) - return -EBUSY; write_lock(&binfmt_lock); - while (*tmp) { - if (fmt == *tmp) { - write_unlock(&binfmt_lock); - return -EBUSY; - } - tmp = &(*tmp)->next; - } - fmt->next = formats; - formats = fmt; + insert ? list_add(&fmt->lh, &formats) : + list_add_tail(&fmt->lh, &formats); write_unlock(&binfmt_lock); return 0; } -EXPORT_SYMBOL(register_binfmt); +EXPORT_SYMBOL(__register_binfmt); -int unregister_binfmt(struct linux_binfmt * fmt) +void unregister_binfmt(struct linux_binfmt * fmt) { - struct linux_binfmt ** tmp = &formats; - write_lock(&binfmt_lock); - while (*tmp) { - if (fmt == *tmp) { - *tmp = fmt->next; - write_unlock(&binfmt_lock); - return 0; - } - tmp = &(*tmp)->next; - } + list_del(&fmt->lh); write_unlock(&binfmt_lock); - return -EINVAL; } EXPORT_SYMBOL(unregister_binfmt); @@ -121,35 +104,39 @@ static inline void put_binfmt(struct linux_binfmt * fmt) * * Also note that we take the address to load from from the file itself. */ -asmlinkage long sys_uselib(const char __user * library) +SYSCALL_DEFINE1(uselib, const char __user *, library) { - struct file * file; - struct nameidata nd; - int error; + struct file *file; + char *tmp = getname(library); + int error = PTR_ERR(tmp); + + if (IS_ERR(tmp)) + goto out; - error = __user_path_lookup_open(library, LOOKUP_FOLLOW, &nd, FMODE_READ); - if (error) + file = do_filp_open(AT_FDCWD, tmp, + O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0, + MAY_READ | MAY_EXEC | MAY_OPEN); + putname(tmp); + error = PTR_ERR(file); + if (IS_ERR(file)) goto out; error = -EINVAL; - if (!S_ISREG(nd.dentry->d_inode->i_mode)) + if (!S_ISREG(file->f_path.dentry->d_inode->i_mode)) goto exit; - error = vfs_permission(&nd, MAY_READ | MAY_EXEC); - if (error) + error = -EACCES; + if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) goto exit; - file = nameidata_to_filp(&nd, O_RDONLY); - error = PTR_ERR(file); - if (IS_ERR(file)) - goto out; + fsnotify_open(file->f_path.dentry); error = -ENOEXEC; if(file->f_op) { struct linux_binfmt * fmt; read_lock(&binfmt_lock); - for (fmt = formats ; fmt ; fmt = fmt->next) { + list_for_each_entry(fmt, &formats, lh) { if (!fmt->load_shlib) continue; if (!try_module_get(fmt->module)) @@ -163,13 +150,211 @@ asmlinkage long sys_uselib(const char __user * library) } read_unlock(&binfmt_lock); } +exit: fput(file); out: return error; -exit: - release_open_intent(&nd); - path_release(&nd); - goto out; +} + +#ifdef CONFIG_MMU + +static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, + int write) +{ + struct page *page; + int ret; + +#ifdef CONFIG_STACK_GROWSUP + if (write) { + ret = expand_stack_downwards(bprm->vma, pos); + if (ret < 0) + return NULL; + } +#endif + ret = get_user_pages(current, bprm->mm, pos, + 1, write, 1, &page, NULL); + if (ret <= 0) + return NULL; + + if (write) { + unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start; + struct rlimit *rlim; + + /* + * We've historically supported up to 32 pages (ARG_MAX) + * of argument strings even with small stacks + */ + if (size <= ARG_MAX) + return page; + + /* + * Limit to 1/4-th the stack size 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. + */ + rlim = current->signal->rlim; + if (size > rlim[RLIMIT_STACK].rlim_cur / 4) { + put_page(page); + return NULL; + } + } + + return page; +} + +static void put_arg_page(struct page *page) +{ + put_page(page); +} + +static void free_arg_page(struct linux_binprm *bprm, int i) +{ +} + +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 int __bprm_mm_init(struct linux_binprm *bprm) +{ + int err; + struct vm_area_struct *vma = NULL; + struct mm_struct *mm = bprm->mm; + + bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + if (!vma) + return -ENOMEM; + + down_write(&mm->mmap_sem); + vma->vm_mm = mm; + + /* + * Place the stack at the largest stack address the architecture + * supports. Later, we'll move this to an appropriate place. We don't + * use STACK_TOP because that can depend on attributes which aren't + * configured yet. + */ + vma->vm_end = STACK_TOP_MAX; + vma->vm_start = vma->vm_end - PAGE_SIZE; + vma->vm_flags = VM_STACK_FLAGS; + vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); + err = insert_vm_struct(mm, vma); + if (err) + goto err; + + mm->stack_vm = mm->total_vm = 1; + up_write(&mm->mmap_sem); + bprm->p = vma->vm_end - sizeof(void *); + return 0; +err: + up_write(&mm->mmap_sem); + bprm->vma = NULL; + kmem_cache_free(vm_area_cachep, vma); + return err; +} + +static bool valid_arg_len(struct linux_binprm *bprm, long len) +{ + return len <= MAX_ARG_STRLEN; +} + +#else + +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 int __bprm_mm_init(struct linux_binprm *bprm) +{ + bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *); + return 0; +} + +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(). + */ +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; + + err = init_new_context(current, mm); + if (err) + goto err; + + err = __bprm_mm_init(bprm); + if (err) + goto err; + + return 0; + +err: + if (mm) { + bprm->mm = NULL; + mmdrop(mm); + } + + return err; } /* @@ -188,7 +373,7 @@ static int count(char __user * __user * argv, int max) if (!p) break; argv++; - if(++i > max) + if (i++ >= max) return -E2BIG; cond_resched(); } @@ -197,15 +382,16 @@ static int count(char __user * __user * argv, int max) } /* - * 'copy_strings()' copies argument/environment strings from user - * memory to free pages in kernel mem. These are in a format ready - * to be put directly into the top of new user memory. + * '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, char __user * __user * argv, struct linux_binprm *bprm) { struct page *kmapped_page = NULL; char *kaddr = NULL; + unsigned long kpos = 0; int ret; while (argc-- > 0) { @@ -214,69 +400,69 @@ static int copy_strings(int argc, char __user * __user * argv, unsigned long pos; if (get_user(str, argv+argc) || - !(len = strnlen_user(str, bprm->p))) { + !(len = strnlen_user(str, MAX_ARG_STRLEN))) { ret = -EFAULT; goto out; } - if (bprm->p < len) { + if (!valid_arg_len(bprm, len)) { ret = -E2BIG; goto out; } - bprm->p -= len; - /* XXX: add architecture specific overflow check here. */ + /* We're going to work our way backwords. */ pos = bprm->p; + str += len; + bprm->p -= len; while (len > 0) { - int i, new, err; int offset, bytes_to_copy; - struct page *page; offset = pos % PAGE_SIZE; - i = pos/PAGE_SIZE; - page = bprm->page[i]; - new = 0; - if (!page) { - page = alloc_page(GFP_HIGHUSER); - bprm->page[i] = page; + 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; + len -= bytes_to_copy; + + if (!kmapped_page || kpos != (pos & PAGE_MASK)) { + struct page *page; + + page = get_arg_page(bprm, pos, 1); if (!page) { - ret = -ENOMEM; + ret = -E2BIG; goto out; } - new = 1; - } - if (page != kmapped_page) { - if (kmapped_page) + if (kmapped_page) { + flush_kernel_dcache_page(kmapped_page); kunmap(kmapped_page); + put_arg_page(kmapped_page); + } kmapped_page = page; kaddr = kmap(kmapped_page); + kpos = pos & PAGE_MASK; + flush_arg_page(bprm, kpos, kmapped_page); } - if (new && offset) - memset(kaddr, 0, offset); - bytes_to_copy = PAGE_SIZE - offset; - if (bytes_to_copy > len) { - bytes_to_copy = len; - if (new) - memset(kaddr+offset+len, 0, - PAGE_SIZE-offset-len); - } - err = copy_from_user(kaddr+offset, str, bytes_to_copy); - if (err) { + if (copy_from_user(kaddr+offset, str, bytes_to_copy)) { ret = -EFAULT; goto out; } - - pos += bytes_to_copy; - str += bytes_to_copy; - len -= bytes_to_copy; } } ret = 0; out: - if (kmapped_page) + if (kmapped_page) { + flush_kernel_dcache_page(kmapped_page); kunmap(kmapped_page); + put_arg_page(kmapped_page); + } return ret; } @@ -292,236 +478,207 @@ int copy_strings_kernel(int argc,char ** argv, struct linux_binprm *bprm) set_fs(oldfs); return r; } - EXPORT_SYMBOL(copy_strings_kernel); #ifdef CONFIG_MMU + /* - * This routine is used to map in a page into an address space: needed by - * execve() for the initial stack and environment pages. + * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX. Once + * the binfmt code determines where the new stack should reside, we shift it to + * its final location. The process proceeds as follows: * - * vma->vm_mm->mmap_sem is held for writing. + * 1) Use shift to calculate the new vma endpoints. + * 2) Extend vma to cover both the old and new ranges. This ensures the + * arguments passed to subsequent functions are consistent. + * 3) Move vma's page tables to the new range. + * 4) Free up any cleared pgd range. + * 5) Shrink the vma to cover only the new range. */ -void install_arg_page(struct vm_area_struct *vma, - struct page *page, unsigned long address) +static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) { struct mm_struct *mm = vma->vm_mm; - pgd_t * pgd; - pud_t * pud; - pmd_t * pmd; - pte_t * pte; - spinlock_t *ptl; + unsigned long old_start = vma->vm_start; + unsigned long old_end = vma->vm_end; + unsigned long length = old_end - old_start; + unsigned long new_start = old_start - shift; + unsigned long new_end = old_end - shift; + struct mmu_gather *tlb; - if (unlikely(anon_vma_prepare(vma))) - goto out; + BUG_ON(new_start > new_end); - flush_dcache_page(page); - pgd = pgd_offset(mm, address); - pud = pud_alloc(mm, pgd, address); - if (!pud) - goto out; - pmd = pmd_alloc(mm, pud, address); - if (!pmd) - goto out; - pte = pte_alloc_map_lock(mm, pmd, address, &ptl); - if (!pte) - goto out; - if (!pte_none(*pte)) { - pte_unmap_unlock(pte, ptl); - goto out; + /* + * ensure there are no vmas between where we want to go + * and where we are + */ + if (vma != find_vma(mm, new_start)) + return -EFAULT; + + /* + * cover the whole range: [new_start, old_end) + */ + vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL); + + /* + * move the page tables downwards, on failure we rely on + * process cleanup to remove whatever mess we made. + */ + if (length != move_page_tables(vma, old_start, + vma, new_start, length)) + return -ENOMEM; + + lru_add_drain(); + tlb = tlb_gather_mmu(mm, 0); + if (new_end > old_start) { + /* + * when the old and new regions overlap clear from new_end. + */ + free_pgd_range(tlb, new_end, old_end, new_end, + vma->vm_next ? vma->vm_next->vm_start : 0); + } else { + /* + * otherwise, clean from old_start; this is done to not touch + * the address space in [new_end, old_start) some architectures + * have constraints on va-space that make this illegal (IA64) - + * for the others its just a little faster. + */ + free_pgd_range(tlb, old_start, old_end, new_end, + vma->vm_next ? vma->vm_next->vm_start : 0); } - inc_mm_counter(mm, anon_rss); - lru_cache_add_active(page); - set_pte_at(mm, address, pte, pte_mkdirty(pte_mkwrite(mk_pte( - page, vma->vm_page_prot)))); - page_add_anon_rmap(page, vma, address); - pte_unmap_unlock(pte, ptl); - - /* no need for flush_tlb */ - return; -out: - __free_page(page); - force_sig(SIGKILL, current); + tlb_finish_mmu(tlb, new_end, old_end); + + /* + * shrink the vma to just the new range. + */ + vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL); + + return 0; } #define EXTRA_STACK_VM_PAGES 20 /* random */ +/* + * Finalizes the stack vm_area_struct. The flags and permissions are updated, + * the stack is optionally relocated, and some extra space is added. + */ int setup_arg_pages(struct linux_binprm *bprm, unsigned long stack_top, int executable_stack) { - unsigned long stack_base; - struct vm_area_struct *mpnt; + unsigned long ret; + unsigned long stack_shift; struct mm_struct *mm = current->mm; - int i, ret; - long arg_size; + struct vm_area_struct *vma = bprm->vma; + struct vm_area_struct *prev = NULL; + unsigned long vm_flags; + unsigned long stack_base; #ifdef CONFIG_STACK_GROWSUP - /* Move the argument and environment strings to the bottom of the - * stack space. - */ - int offset, j; - char *to, *from; - - /* Start by shifting all the pages down */ - i = 0; - for (j = 0; j < MAX_ARG_PAGES; j++) { - struct page *page = bprm->page[j]; - if (!page) - continue; - bprm->page[i++] = page; - } - - /* Now move them within their pages */ - offset = bprm->p % PAGE_SIZE; - to = kmap(bprm->page[0]); - for (j = 1; j < i; j++) { - memmove(to, to + offset, PAGE_SIZE - offset); - from = kmap(bprm->page[j]); - memcpy(to + PAGE_SIZE - offset, from, offset); - kunmap(bprm->page[j - 1]); - to = from; - } - memmove(to, to + offset, PAGE_SIZE - offset); - kunmap(bprm->page[j - 1]); - /* Limit stack size to 1GB */ stack_base = current->signal->rlim[RLIMIT_STACK].rlim_max; if (stack_base > (1 << 30)) stack_base = 1 << 30; - stack_base = PAGE_ALIGN(stack_top - stack_base); - /* Adjust bprm->p to point to the end of the strings. */ - bprm->p = stack_base + PAGE_SIZE * i - offset; + /* Make sure we didn't let the argument array grow too large. */ + if (vma->vm_end - vma->vm_start > stack_base) + return -ENOMEM; - mm->arg_start = stack_base; - arg_size = i << PAGE_SHIFT; + stack_base = PAGE_ALIGN(stack_top - stack_base); - /* zero pages that were copied above */ - while (i < MAX_ARG_PAGES) - bprm->page[i++] = NULL; + stack_shift = vma->vm_start - stack_base; + mm->arg_start = bprm->p - stack_shift; + bprm->p = vma->vm_end - stack_shift; #else - stack_base = arch_align_stack(stack_top - MAX_ARG_PAGES*PAGE_SIZE); - stack_base = PAGE_ALIGN(stack_base); - bprm->p += stack_base; + stack_top = arch_align_stack(stack_top); + stack_top = PAGE_ALIGN(stack_top); + stack_shift = vma->vm_end - stack_top; + + bprm->p -= stack_shift; mm->arg_start = bprm->p; - arg_size = stack_top - (PAGE_MASK & (unsigned long) mm->arg_start); #endif - arg_size += EXTRA_STACK_VM_PAGES * PAGE_SIZE; - if (bprm->loader) - bprm->loader += stack_base; - bprm->exec += stack_base; + bprm->loader -= stack_shift; + bprm->exec -= stack_shift; - mpnt = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL); - if (!mpnt) - return -ENOMEM; + down_write(&mm->mmap_sem); + vm_flags = VM_STACK_FLAGS; - memset(mpnt, 0, sizeof(*mpnt)); + /* + * Adjust stack execute permissions; explicitly enable for + * EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X and leave alone + * (arch default) otherwise. + */ + if (unlikely(executable_stack == EXSTACK_ENABLE_X)) + vm_flags |= VM_EXEC; + else if (executable_stack == EXSTACK_DISABLE_X) + vm_flags &= ~VM_EXEC; + vm_flags |= mm->def_flags; + + ret = mprotect_fixup(vma, &prev, vma->vm_start, vma->vm_end, + vm_flags); + if (ret) + goto out_unlock; + BUG_ON(prev != vma); + + /* Move stack pages down in memory. */ + if (stack_shift) { + ret = shift_arg_pages(vma, stack_shift); + if (ret) + goto out_unlock; + } - down_write(&mm->mmap_sem); - { - mpnt->vm_mm = mm; #ifdef CONFIG_STACK_GROWSUP - mpnt->vm_start = stack_base; - mpnt->vm_end = stack_base + arg_size; + stack_base = vma->vm_end + EXTRA_STACK_VM_PAGES * PAGE_SIZE; #else - mpnt->vm_end = stack_top; - mpnt->vm_start = mpnt->vm_end - arg_size; + stack_base = vma->vm_start - EXTRA_STACK_VM_PAGES * PAGE_SIZE; #endif - /* Adjust stack execute permissions; explicitly enable - * for EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X - * and leave alone (arch default) otherwise. */ - if (unlikely(executable_stack == EXSTACK_ENABLE_X)) - mpnt->vm_flags = VM_STACK_FLAGS | VM_EXEC; - else if (executable_stack == EXSTACK_DISABLE_X) - mpnt->vm_flags = VM_STACK_FLAGS & ~VM_EXEC; - else - mpnt->vm_flags = VM_STACK_FLAGS; - mpnt->vm_flags |= mm->def_flags; - mpnt->vm_page_prot = protection_map[mpnt->vm_flags & 0x7]; - if ((ret = insert_vm_struct(mm, mpnt))) { - up_write(&mm->mmap_sem); - kmem_cache_free(vm_area_cachep, mpnt); - return ret; - } - mm->stack_vm = mm->total_vm = vma_pages(mpnt); - } + ret = expand_stack(vma, stack_base); + if (ret) + ret = -EFAULT; - for (i = 0 ; i < MAX_ARG_PAGES ; i++) { - struct page *page = bprm->page[i]; - if (page) { - bprm->page[i] = NULL; - install_arg_page(mpnt, page, stack_base); - } - stack_base += PAGE_SIZE; - } +out_unlock: up_write(&mm->mmap_sem); - - return 0; + return ret; } - EXPORT_SYMBOL(setup_arg_pages); -#define free_arg_pages(bprm) do { } while (0) - -#else - -static inline void free_arg_pages(struct linux_binprm *bprm) -{ - int i; - - for (i = 0; i < MAX_ARG_PAGES; i++) { - if (bprm->page[i]) - __free_page(bprm->page[i]); - bprm->page[i] = NULL; - } -} - #endif /* CONFIG_MMU */ struct file *open_exec(const char *name) { - struct nameidata nd; - int err; struct file *file; + int err; + + file = do_filp_open(AT_FDCWD, name, + O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0, + MAY_EXEC | MAY_OPEN); + if (IS_ERR(file)) + goto out; + + err = -EACCES; + if (!S_ISREG(file->f_path.dentry->d_inode->i_mode)) + goto exit; + + if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) + goto exit; + + fsnotify_open(file->f_path.dentry); + + err = deny_write_access(file); + if (err) + goto exit; - err = path_lookup_open(name, LOOKUP_FOLLOW, &nd, FMODE_READ); - file = ERR_PTR(err); - - if (!err) { - struct inode *inode = nd.dentry->d_inode; - file = ERR_PTR(-EACCES); - if (!(nd.mnt->mnt_flags & MNT_NOEXEC) && - S_ISREG(inode->i_mode)) { - int err = vfs_permission(&nd, MAY_EXEC); - if (!err && !(inode->i_mode & 0111)) - err = -EACCES; - file = ERR_PTR(err); - if (!err) { - file = nameidata_to_filp(&nd, O_RDONLY); - if (!IS_ERR(file)) { - err = deny_write_access(file); - if (err) { - fput(file); - file = ERR_PTR(err); - } - } out: - return file; - } - } - release_open_intent(&nd); - path_release(&nd); - } - goto out; -} + return file; +exit: + fput(file); + return ERR_PTR(err); +} EXPORT_SYMBOL(open_exec); -int kernel_read(struct file *file, unsigned long offset, - char *addr, unsigned long count) +int kernel_read(struct file *file, loff_t offset, + char *addr, unsigned long count) { mm_segment_t old_fs; loff_t pos = offset; @@ -552,12 +709,10 @@ static int exec_mmap(struct mm_struct *mm) * Make sure that if there is a core dump in progress * for the old mm, we get out and die instead of going * through with the exec. We must hold mmap_sem around - * checking core_waiters and changing tsk->mm. The - * core-inducing thread will increment core_waiters for - * each thread whose ->mm == old_mm. + * checking core_state and changing tsk->mm. */ down_read(&old_mm->mmap_sem); - if (unlikely(old_mm->core_waiters)) { + if (unlikely(old_mm->core_state)) { up_read(&old_mm->mmap_sem); return -EINTR; } @@ -571,7 +726,8 @@ static int exec_mmap(struct mm_struct *mm) arch_pick_mmap_layout(mm); if (old_mm) { up_read(&old_mm->mmap_sem); - if (active_mm != old_mm) BUG(); + BUG_ON(active_mm != old_mm); + mm_update_next_owner(old_mm); mmput(old_mm); return 0; } @@ -585,79 +741,40 @@ static int exec_mmap(struct mm_struct *mm) * disturbing other processes. (Other processes might share the signal * table via the CLONE_SIGHAND option to clone().) */ -static inline int de_thread(struct task_struct *tsk) +static int de_thread(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; - struct sighand_struct *newsighand, *oldsighand = tsk->sighand; + struct sighand_struct *oldsighand = tsk->sighand; spinlock_t *lock = &oldsighand->siglock; - struct task_struct *leader = NULL; int count; - /* - * If we don't share sighandlers, then we aren't sharing anything - * and we can just re-use it all. - */ - if (atomic_read(&oldsighand->count) <= 1) { - BUG_ON(atomic_read(&sig->count) != 1); - exit_itimers(sig); - return 0; - } - - newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); - if (!newsighand) - return -ENOMEM; - - if (thread_group_empty(current)) + if (thread_group_empty(tsk)) goto no_thread_group; /* * Kill all other threads in the thread group. - * We must hold tasklist_lock to call zap_other_threads. */ - read_lock(&tasklist_lock); spin_lock_irq(lock); - if (sig->flags & SIGNAL_GROUP_EXIT) { + if (signal_group_exit(sig)) { /* * Another group action in progress, just * return so that the signal is processed. */ spin_unlock_irq(lock); - read_unlock(&tasklist_lock); - kmem_cache_free(sighand_cachep, newsighand); return -EAGAIN; } - zap_other_threads(current); - read_unlock(&tasklist_lock); + sig->group_exit_task = tsk; + zap_other_threads(tsk); - /* - * Account for the thread group leader hanging around: - */ - count = 1; - if (!thread_group_leader(current)) { - count = 2; - /* - * The SIGALRM timer survives the exec, but needs to point - * at us as the new group leader now. We have a race with - * a timer firing now getting the old leader, so we need to - * synchronize with any firing (by calling del_timer_sync) - * before we can safely let the old group leader die. - */ - sig->real_timer.data = (unsigned long)current; - spin_unlock_irq(lock); - if (del_timer_sync(&sig->real_timer)) - add_timer(&sig->real_timer); - spin_lock_irq(lock); - } + /* Account for the thread group leader hanging around: */ + count = thread_group_leader(tsk) ? 1 : 2; + sig->notify_count = count; while (atomic_read(&sig->count) > count) { - sig->group_exit_task = current; - sig->notify_count = count; __set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock_irq(lock); schedule(); spin_lock_irq(lock); } - sig->group_exit_task = NULL; - sig->notify_count = 0; spin_unlock_irq(lock); /* @@ -665,132 +782,108 @@ static inline int de_thread(struct task_struct *tsk) * do is to wait for the thread group leader to become inactive, * and to assume its PID: */ - if (!thread_group_leader(current)) { - struct task_struct *parent; - struct dentry *proc_dentry1, *proc_dentry2; - unsigned long exit_state, ptrace; + if (!thread_group_leader(tsk)) { + struct task_struct *leader = tsk->group_leader; + + sig->notify_count = -1; /* for exit_notify() */ + for (;;) { + write_lock_irq(&tasklist_lock); + if (likely(leader->exit_state)) + break; + __set_current_state(TASK_UNINTERRUPTIBLE); + write_unlock_irq(&tasklist_lock); + schedule(); + } /* - * Wait for the thread group leader to be a zombie. - * It should already be zombie at this point, most - * of the time. + * The only record we have of the real-time age of a + * process, regardless of execs it's done, is start_time. + * All the past CPU time is accumulated in signal_struct + * from sister threads now dead. But in this non-leader + * exec, nothing survives from the original leader thread, + * whose birth marks the true age of this process now. + * When we take on its identity by switching to its PID, we + * also take its birthdate (always earlier than our own). */ - leader = current->group_leader; - while (leader->exit_state != EXIT_ZOMBIE) - yield(); - - spin_lock(&leader->proc_lock); - spin_lock(¤t->proc_lock); - proc_dentry1 = proc_pid_unhash(current); - proc_dentry2 = proc_pid_unhash(leader); - write_lock_irq(&tasklist_lock); + tsk->start_time = leader->start_time; - BUG_ON(leader->tgid != current->tgid); - BUG_ON(current->pid == current->tgid); + BUG_ON(!same_thread_group(leader, tsk)); + BUG_ON(has_group_leader_pid(tsk)); /* * An exec() starts a new thread group with the * TGID of the previous thread group. Rehash the * two threads with a switched PID, and release * the former thread group leader: */ - ptrace = leader->ptrace; - parent = leader->parent; - if (unlikely(ptrace) && unlikely(parent == current)) { - /* - * Joker was ptracing his own group leader, - * and now he wants to be his own parent! - * We can't have that. - */ - ptrace = 0; - } - - ptrace_unlink(current); - ptrace_unlink(leader); - remove_parent(current); - remove_parent(leader); - switch_exec_pids(leader, current); + /* Become a process group leader with the old leader's pid. + * The old leader becomes a thread of the this thread group. + * Note: The old leader also uses this pid until release_task + * is called. Odd but simple and correct. + */ + detach_pid(tsk, PIDTYPE_PID); + tsk->pid = leader->pid; + attach_pid(tsk, PIDTYPE_PID, task_pid(leader)); + transfer_pid(leader, tsk, PIDTYPE_PGID); + transfer_pid(leader, tsk, PIDTYPE_SID); - current->parent = current->real_parent = leader->real_parent; - leader->parent = leader->real_parent = child_reaper; - current->group_leader = current; - leader->group_leader = leader; + list_replace_rcu(&leader->tasks, &tsk->tasks); + list_replace_init(&leader->sibling, &tsk->sibling); - add_parent(current, current->parent); - add_parent(leader, leader->parent); - if (ptrace) { - current->ptrace = ptrace; - __ptrace_link(current, parent); - } + tsk->group_leader = tsk; + leader->group_leader = tsk; - list_del(¤t->tasks); - list_add_tail(¤t->tasks, &init_task.tasks); - current->exit_signal = SIGCHLD; - exit_state = leader->exit_state; + tsk->exit_signal = SIGCHLD; + BUG_ON(leader->exit_state != EXIT_ZOMBIE); + leader->exit_state = EXIT_DEAD; write_unlock_irq(&tasklist_lock); - spin_unlock(&leader->proc_lock); - spin_unlock(¤t->proc_lock); - proc_pid_flush(proc_dentry1); - proc_pid_flush(proc_dentry2); - BUG_ON(exit_state != EXIT_ZOMBIE); - } + release_task(leader); + } - /* - * There may be one thread left which is just exiting, - * but it's safe to stop telling the group to kill themselves. - */ - sig->flags = 0; + sig->group_exit_task = NULL; + sig->notify_count = 0; no_thread_group: - exit_itimers(sig); - if (leader) - release_task(leader); + if (current->mm) + setmax_mm_hiwater_rss(&sig->maxrss, current->mm); - BUG_ON(atomic_read(&sig->count) != 1); + exit_itimers(sig); + flush_itimer_signals(); - if (atomic_read(&oldsighand->count) == 1) { + if (atomic_read(&oldsighand->count) != 1) { + struct sighand_struct *newsighand; /* - * Now that we nuked the rest of the thread group, - * it turns out we are not sharing sighand any more either. - * So we can just keep it. + * This ->sighand is shared with the CLONE_SIGHAND + * but not CLONE_THREAD task, switch to the new one. */ - kmem_cache_free(sighand_cachep, newsighand); - } else { - /* - * Move our state over to newsighand and switch it in. - */ - spin_lock_init(&newsighand->siglock); + newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); + if (!newsighand) + return -ENOMEM; + atomic_set(&newsighand->count, 1); memcpy(newsighand->action, oldsighand->action, sizeof(newsighand->action)); write_lock_irq(&tasklist_lock); spin_lock(&oldsighand->siglock); - spin_lock(&newsighand->siglock); - - current->sighand = newsighand; - recalc_sigpending(); - - spin_unlock(&newsighand->siglock); + rcu_assign_pointer(tsk->sighand, newsighand); spin_unlock(&oldsighand->siglock); write_unlock_irq(&tasklist_lock); - if (atomic_dec_and_test(&oldsighand->count)) - kmem_cache_free(sighand_cachep, oldsighand); + __cleanup_sighand(oldsighand); } - BUG_ON(!thread_group_leader(current)); + BUG_ON(!thread_group_leader(tsk)); return 0; } - + /* * These functions flushes out all traces of the currently running executable * so that a new one can be started */ - -static inline void flush_old_files(struct files_struct * files) +static void flush_old_files(struct files_struct * files) { long j = -1; struct fdtable *fdt; @@ -802,7 +895,7 @@ static inline void flush_old_files(struct files_struct * files) j++; i = j * __NFDBITS; fdt = files_fdtable(files); - if (i >= fdt->max_fds || i >= fdt->max_fdset) + if (i >= fdt->max_fds) break; set = fdt->close_on_exec->fds_bits[j]; if (!set) @@ -820,26 +913,36 @@ static inline void flush_old_files(struct files_struct * files) spin_unlock(&files->file_lock); } -void get_task_comm(char *buf, struct task_struct *tsk) +char *get_task_comm(char *buf, struct task_struct *tsk) { /* buf must be at least sizeof(tsk->comm) in size */ task_lock(tsk); strncpy(buf, tsk->comm, sizeof(tsk->comm)); task_unlock(tsk); + return buf; } void set_task_comm(struct task_struct *tsk, char *buf) { task_lock(tsk); + + /* + * Threads may access current->comm without holding + * the task lock, so write the string carefully. + * Readers without a lock may see incomplete new + * names but are safe from non-terminating string reads. + */ + memset(tsk->comm, 0, TASK_COMM_LEN); + wmb(); strlcpy(tsk->comm, buf, sizeof(tsk->comm)); task_unlock(tsk); + perf_event_comm(tsk); } int flush_old_exec(struct linux_binprm * bprm) { char * name; int i, ch, retval; - struct files_struct *files; char tcomm[sizeof(current->comm)]; /* @@ -850,34 +953,24 @@ int flush_old_exec(struct linux_binprm * bprm) if (retval) goto out; - /* - * Make sure we have private file handles. Ask the - * fork helper to do the work for us and the exit - * helper to do the cleanup of the old one. - */ - files = current->files; /* refcounted so safe to hold */ - retval = unshare_files(); - if (retval) - goto out; + set_mm_exe_file(bprm->mm, bprm->file); + /* * Release all of the old mmap stuff */ retval = exec_mmap(bprm->mm); if (retval) - goto mmap_failed; + goto out; bprm->mm = NULL; /* We're using it now */ /* This is the point of no return */ - steal_locks(files); - put_files_struct(files); - current->sas_ss_sp = current->sas_ss_size = 0; - if (current->euid == current->uid && current->egid == current->gid) - current->mm->dumpable = 1; + if (current_euid() == current_uid() && current_egid() == current_gid()) + set_dumpable(current->mm, 1); else - current->mm->dumpable = suid_dumpable; + set_dumpable(current->mm, suid_dumpable); name = bprm->filename; @@ -895,13 +988,30 @@ int flush_old_exec(struct linux_binprm * bprm) current->flags &= ~PF_RANDOMIZE; flush_thread(); - if (bprm->e_uid != current->euid || bprm->e_gid != current->egid || - file_permission(bprm->file, MAY_READ) || - (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) { - suid_keys(current); - current->mm->dumpable = suid_dumpable; + /* Set the new mm task size. We have to do that late because it may + * depend on TIF_32BIT which is only updated in flush_thread() on + * some architectures like powerpc + */ + current->mm->task_size = TASK_SIZE; + + /* install the new credentials */ + if (bprm->cred->uid != current_euid() || + bprm->cred->gid != current_egid()) { + current->pdeath_signal = 0; + } else if (file_permission(bprm->file, MAY_READ) || + bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP) { + set_dumpable(current->mm, suid_dumpable); } + current->personality &= ~bprm->per_clear; + + /* + * Flush performance counters when crossing a + * security domain: + */ + if (!get_dumpable(current->mm)) + perf_event_exit_task(current); + /* An exec changes our domain. We are no longer part of the thread group */ @@ -912,43 +1022,121 @@ int flush_old_exec(struct linux_binprm * bprm) return 0; -mmap_failed: - put_files_struct(current->files); - current->files = files; out: return retval; } EXPORT_SYMBOL(flush_old_exec); +/* + * Prepare credentials and lock ->cred_guard_mutex. + * install_exec_creds() commits the new creds and drops the lock. + * Or, if exec fails before, free_bprm() should release ->cred and + * and unlock. + */ +int prepare_bprm_creds(struct linux_binprm *bprm) +{ + if (mutex_lock_interruptible(¤t->cred_guard_mutex)) + return -ERESTARTNOINTR; + + bprm->cred = prepare_exec_creds(); + if (likely(bprm->cred)) + return 0; + + mutex_unlock(¤t->cred_guard_mutex); + return -ENOMEM; +} + +void free_bprm(struct linux_binprm *bprm) +{ + free_arg_pages(bprm); + if (bprm->cred) { + mutex_unlock(¤t->cred_guard_mutex); + abort_creds(bprm->cred); + } + kfree(bprm); +} + +/* + * install the new credentials for this executable + */ +void install_exec_creds(struct linux_binprm *bprm) +{ + security_bprm_committing_creds(bprm); + + commit_creds(bprm->cred); + bprm->cred = NULL; + /* + * cred_guard_mutex must be held at least to this point to prevent + * ptrace_attach() from altering our determination of the task's + * credentials; any time after this it may be unlocked. + */ + security_bprm_committed_creds(bprm); + mutex_unlock(¤t->cred_guard_mutex); +} +EXPORT_SYMBOL(install_exec_creds); + +/* + * determine how safe it is to execute the proposed program + * - the caller must hold current->cred_guard_mutex to protect against + * PTRACE_ATTACH + */ +int check_unsafe_exec(struct linux_binprm *bprm) +{ + struct task_struct *p = current, *t; + unsigned n_fs; + int res = 0; + + bprm->unsafe = tracehook_unsafe_exec(p); + + n_fs = 1; + write_lock(&p->fs->lock); + rcu_read_lock(); + for (t = next_thread(p); t != p; t = next_thread(t)) { + if (t->fs == p->fs) + n_fs++; + } + rcu_read_unlock(); + + if (p->fs->users > n_fs) { + bprm->unsafe |= LSM_UNSAFE_SHARE; + } else { + res = -EAGAIN; + if (!p->fs->in_exec) { + p->fs->in_exec = 1; + res = 1; + } + } + write_unlock(&p->fs->lock); + + return res; +} + /* * Fill the binprm structure from the inode. * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes + * + * This may be called multiple times for binary chains (scripts for example). */ int prepare_binprm(struct linux_binprm *bprm) { - int mode; - struct inode * inode = bprm->file->f_dentry->d_inode; + umode_t mode; + struct inode * inode = bprm->file->f_path.dentry->d_inode; int retval; mode = inode->i_mode; - /* - * Check execute perms again - if the caller has CAP_DAC_OVERRIDE, - * generic_permission lets a non-executable through - */ - if (!(mode & 0111)) /* with at least _one_ execute bit set */ - return -EACCES; if (bprm->file->f_op == NULL) return -EACCES; - bprm->e_uid = current->euid; - bprm->e_gid = current->egid; + /* clear any previous set[ug]id data from a previous binary */ + bprm->cred->euid = current_euid(); + bprm->cred->egid = current_egid(); - if(!(bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID)) { + if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) { /* Set-uid? */ if (mode & S_ISUID) { - current->personality &= ~PER_CLEAR_ON_SETID; - bprm->e_uid = inode->i_uid; + bprm->per_clear |= PER_CLEAR_ON_SETID; + bprm->cred->euid = inode->i_uid; } /* Set-gid? */ @@ -958,80 +1146,65 @@ int prepare_binprm(struct linux_binprm *bprm) * executable. */ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { - current->personality &= ~PER_CLEAR_ON_SETID; - bprm->e_gid = inode->i_gid; + bprm->per_clear |= PER_CLEAR_ON_SETID; + bprm->cred->egid = inode->i_gid; } } /* fill in binprm security blob */ - retval = security_bprm_set(bprm); + retval = security_bprm_set_creds(bprm); if (retval) return retval; + bprm->cred_prepared = 1; - memset(bprm->buf,0,BINPRM_BUF_SIZE); - return kernel_read(bprm->file,0,bprm->buf,BINPRM_BUF_SIZE); + memset(bprm->buf, 0, BINPRM_BUF_SIZE); + return kernel_read(bprm->file, 0, bprm->buf, BINPRM_BUF_SIZE); } EXPORT_SYMBOL(prepare_binprm); -static inline int unsafe_exec(struct task_struct *p) +/* + * Arguments are '\0' separated strings found at the location bprm->p + * points to; chop off the first by relocating brpm->p to right after + * the first '\0' encountered. + */ +int remove_arg_zero(struct linux_binprm *bprm) { - int unsafe = 0; - if (p->ptrace & PT_PTRACED) { - if (p->ptrace & PT_PTRACE_CAP) - unsafe |= LSM_UNSAFE_PTRACE_CAP; - else - unsafe |= LSM_UNSAFE_PTRACE; - } - if (atomic_read(&p->fs->count) > 1 || - atomic_read(&p->files->count) > 1 || - atomic_read(&p->sighand->count) > 1) - unsafe |= LSM_UNSAFE_SHARE; - - return unsafe; -} + int ret = 0; + unsigned long offset; + char *kaddr; + struct page *page; -void compute_creds(struct linux_binprm *bprm) -{ - int unsafe; + if (!bprm->argc) + return 0; - if (bprm->e_uid != current->uid) - suid_keys(current); - exec_keys(current); + do { + offset = bprm->p & ~PAGE_MASK; + page = get_arg_page(bprm, bprm->p, 0); + if (!page) { + ret = -EFAULT; + goto out; + } + kaddr = kmap_atomic(page, KM_USER0); - task_lock(current); - unsafe = unsafe_exec(current); - security_bprm_apply_creds(bprm, unsafe); - task_unlock(current); - security_bprm_post_apply_creds(bprm); -} + for (; offset < PAGE_SIZE && kaddr[offset]; + offset++, bprm->p++) + ; -EXPORT_SYMBOL(compute_creds); + kunmap_atomic(kaddr, KM_USER0); + put_arg_page(page); -void remove_arg_zero(struct linux_binprm *bprm) -{ - if (bprm->argc) { - unsigned long offset; - char * kaddr; - struct page *page; + if (offset == PAGE_SIZE) + free_arg_page(bprm, (bprm->p >> PAGE_SHIFT) - 1); + } while (offset == PAGE_SIZE); - offset = bprm->p % PAGE_SIZE; - goto inside; + bprm->p++; + bprm->argc--; + ret = 0; - while (bprm->p++, *(kaddr+offset++)) { - if (offset != PAGE_SIZE) - continue; - offset = 0; - kunmap_atomic(kaddr, KM_USER0); -inside: - page = bprm->page[bprm->p/PAGE_SIZE]; - kaddr = kmap_atomic(page, KM_USER0); - } - kunmap_atomic(kaddr, KM_USER0); - bprm->argc--; - } +out: + return ret; } - EXPORT_SYMBOL(remove_arg_zero); /* @@ -1039,43 +1212,10 @@ EXPORT_SYMBOL(remove_arg_zero); */ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) { + unsigned int depth = bprm->recursion_depth; int try,retval; struct linux_binfmt *fmt; -#ifdef __alpha__ - /* handle /sbin/loader.. */ - { - struct exec * eh = (struct exec *) bprm->buf; - if (!bprm->loader && eh->fh.f_magic == 0x183 && - (eh->fh.f_flags & 0x3000) == 0x3000) - { - struct file * file; - unsigned long loader; - - allow_write_access(bprm->file); - fput(bprm->file); - bprm->file = NULL; - - loader = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *); - - file = open_exec("/sbin/loader"); - retval = PTR_ERR(file); - if (IS_ERR(file)) - return retval; - - /* Remember if the application is TASO. */ - bprm->sh_bang = eh->ah.entry < 0x100000000UL; - - bprm->file = file; - bprm->loader = loader; - retval = prepare_binprm(bprm); - if (retval<0) - return retval; - /* should call search_binary_handler recursively here, - but it does not matter */ - } - } -#endif retval = security_bprm_check(bprm); if (retval) return retval; @@ -1083,10 +1223,15 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) /* kernel module loader fixup */ /* so we don't try to load run modprobe in kernel space. */ set_fs(USER_DS); + + retval = audit_bprm(bprm); + if (retval) + return retval; + retval = -ENOENT; for (try=0; try<2; try++) { read_lock(&binfmt_lock); - for (fmt = formats ; fmt ; fmt = fmt->next) { + list_for_each_entry(fmt, &formats, lh) { int (*fn)(struct linux_binprm *, struct pt_regs *) = fmt->load_binary; if (!fn) continue; @@ -1094,7 +1239,15 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) continue; read_unlock(&binfmt_lock); retval = fn(bprm, regs); + /* + * Restore the depth counter to its starting value + * in this call, so we don't have to rely on every + * load_binary function to restore it on return. + */ + bprm->recursion_depth = depth; if (retval >= 0) { + if (depth == 0) + tracehook_report_exec(fmt, bprm, regs); put_binfmt(fmt); allow_write_access(bprm->file); if (bprm->file) @@ -1116,8 +1269,8 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) read_unlock(&binfmt_lock); if (retval != -ENOEXEC || bprm->mm == NULL) { break; -#ifdef CONFIG_KMOD - }else{ +#ifdef CONFIG_MODULES + } else { #define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e)) if (printable(bprm->buf[0]) && printable(bprm->buf[1]) && @@ -1143,46 +1296,50 @@ int do_execve(char * filename, { struct linux_binprm *bprm; struct file *file; + struct files_struct *displaced; + bool clear_in_exec; int retval; - int i; + + retval = unshare_files(&displaced); + if (retval) + goto out_ret; retval = -ENOMEM; - bprm = kmalloc(sizeof(*bprm), GFP_KERNEL); + bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); if (!bprm) - goto out_ret; - memset(bprm, 0, sizeof(*bprm)); + goto out_files; + + retval = prepare_bprm_creds(bprm); + if (retval) + goto out_free; + + retval = check_unsafe_exec(bprm); + if (retval < 0) + goto out_free; + clear_in_exec = retval; + current->in_execve = 1; file = open_exec(filename); retval = PTR_ERR(file); if (IS_ERR(file)) - goto out_kfree; + goto out_unmark; sched_exec(); - bprm->p = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *); - bprm->file = file; bprm->filename = filename; bprm->interp = filename; - bprm->mm = mm_alloc(); - retval = -ENOMEM; - if (!bprm->mm) - goto out_file; - retval = init_new_context(current, bprm->mm); - if (retval < 0) - goto out_mm; + retval = bprm_mm_init(bprm); + if (retval) + goto out_file; - bprm->argc = count(argv, bprm->p / sizeof(void *)); + bprm->argc = count(argv, MAX_ARG_STRINGS); if ((retval = bprm->argc) < 0) - goto out_mm; + goto out; - bprm->envc = count(envp, bprm->p / sizeof(void *)); + bprm->envc = count(envp, MAX_ARG_STRINGS); if ((retval = bprm->envc) < 0) - goto out_mm; - - retval = security_bprm_alloc(bprm); - if (retval) goto out; retval = prepare_binprm(bprm); @@ -1202,31 +1359,25 @@ int do_execve(char * filename, if (retval < 0) goto out; + current->flags &= ~PF_KTHREAD; retval = search_binary_handler(bprm,regs); - if (retval >= 0) { - free_arg_pages(bprm); - - /* execve success */ - security_bprm_free(bprm); - acct_update_integrals(current); - kfree(bprm); - return retval; - } + if (retval < 0) + goto out; -out: - /* Something went wrong, return the inode and free the argument pages*/ - for (i = 0 ; i < MAX_ARG_PAGES ; i++) { - struct page * page = bprm->page[i]; - if (page) - __free_page(page); - } + current->stack_start = current->mm->start_stack; - if (bprm->security) - security_bprm_free(bprm); + /* execve succeeded */ + current->fs->in_exec = 0; + current->in_execve = 0; + acct_update_integrals(current); + free_bprm(bprm); + if (displaced) + put_files_struct(displaced); + return retval; -out_mm: +out: if (bprm->mm) - mmdrop(bprm->mm); + mmput (bprm->mm); out_file: if (bprm->file) { @@ -1234,38 +1385,44 @@ out_file: fput(bprm->file); } -out_kfree: - kfree(bprm); +out_unmark: + if (clear_in_exec) + current->fs->in_exec = 0; + current->in_execve = 0; + +out_free: + free_bprm(bprm); +out_files: + if (displaced) + reset_files_struct(displaced); out_ret: return retval; } -int set_binfmt(struct linux_binfmt *new) +void set_binfmt(struct linux_binfmt *new) { - struct linux_binfmt *old = current->binfmt; + struct mm_struct *mm = current->mm; - if (new) { - if (!try_module_get(new->module)) - return -1; - } - current->binfmt = new; - if (old) - module_put(old->module); - return 0; + if (mm->binfmt) + module_put(mm->binfmt->module); + + mm->binfmt = new; + if (new) + __module_get(new->module); } EXPORT_SYMBOL(set_binfmt); -#define CORENAME_MAX_SIZE 64 - /* format_corename will inspect the pattern parameter, and output a * name into corename, which must have space for at least * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator. */ -static void format_corename(char *corename, const char *pattern, long signr) +static int format_corename(char *corename, long signr) { - const char *pat_ptr = pattern; + const struct cred *cred = current_cred(); + const char *pat_ptr = core_pattern; + int ispipe = (*pat_ptr == '|'); char *out_ptr = corename; char *const out_end = corename + CORENAME_MAX_SIZE; int rc; @@ -1292,7 +1449,7 @@ static void format_corename(char *corename, const char *pattern, long signr) case 'p': pid_in_pattern = 1; rc = snprintf(out_ptr, out_end - out_ptr, - "%d", current->tgid); + "%d", task_tgid_vnr(current)); if (rc > out_end - out_ptr) goto out; out_ptr += rc; @@ -1300,7 +1457,7 @@ static void format_corename(char *corename, const char *pattern, long signr) /* uid */ case 'u': rc = snprintf(out_ptr, out_end - out_ptr, - "%d", current->uid); + "%d", cred->uid); if (rc > out_end - out_ptr) goto out; out_ptr += rc; @@ -1308,7 +1465,7 @@ static void format_corename(char *corename, const char *pattern, long signr) /* gid */ case 'g': rc = snprintf(out_ptr, out_end - out_ptr, - "%d", current->gid); + "%d", cred->gid); if (rc > out_end - out_ptr) goto out; out_ptr += rc; @@ -1336,7 +1493,7 @@ static void format_corename(char *corename, const char *pattern, long signr) case 'h': down_read(&uts_sem); rc = snprintf(out_ptr, out_end - out_ptr, - "%s", system_utsname.nodename); + "%s", utsname()->nodename); up_read(&uts_sem); if (rc > out_end - out_ptr) goto out; @@ -1350,6 +1507,14 @@ static void format_corename(char *corename, const char *pattern, long signr) goto out; out_ptr += rc; break; + /* core limit size */ + case 'c': + rc = snprintf(out_ptr, out_end - out_ptr, + "%lu", current->signal->rlim[RLIMIT_CORE].rlim_cur); + if (rc > out_end - out_ptr) + goto out; + out_ptr += rc; + break; default: break; } @@ -1360,99 +1525,278 @@ static void format_corename(char *corename, const char *pattern, long signr) * * If core_pattern does not include a %p (as is the default) * and core_uses_pid is set, then .%pid will be appended to - * the filename */ - if (!pid_in_pattern - && (core_uses_pid || atomic_read(¤t->mm->mm_users) != 1)) { + * the filename. Do not do this for piped commands. */ + if (!ispipe && !pid_in_pattern && core_uses_pid) { rc = snprintf(out_ptr, out_end - out_ptr, - ".%d", current->tgid); + ".%d", task_tgid_vnr(current)); if (rc > out_end - out_ptr) goto out; out_ptr += rc; } - out: +out: *out_ptr = 0; + return ispipe; } -static void zap_threads (struct mm_struct *mm) +static int zap_process(struct task_struct *start) +{ + struct task_struct *t; + int nr = 0; + + start->signal->flags = SIGNAL_GROUP_EXIT; + start->signal->group_stop_count = 0; + + t = start; + do { + if (t != current && t->mm) { + sigaddset(&t->pending.signal, SIGKILL); + signal_wake_up(t, 1); + nr++; + } + } while_each_thread(start, t); + + return nr; +} + +static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm, + struct core_state *core_state, int exit_code) { struct task_struct *g, *p; + unsigned long flags; + int nr = -EAGAIN; + + spin_lock_irq(&tsk->sighand->siglock); + if (!signal_group_exit(tsk->signal)) { + mm->core_state = core_state; + tsk->signal->group_exit_code = exit_code; + nr = zap_process(tsk); + } + spin_unlock_irq(&tsk->sighand->siglock); + if (unlikely(nr < 0)) + return nr; + + if (atomic_read(&mm->mm_users) == nr + 1) + goto done; + /* + * We should find and kill all tasks which use this mm, and we should + * count them correctly into ->nr_threads. We don't take tasklist + * lock, but this is safe wrt: + * + * fork: + * None of sub-threads can fork after zap_process(leader). All + * processes which were created before this point should be + * visible to zap_threads() because copy_process() adds the new + * process to the tail of init_task.tasks list, and lock/unlock + * of ->siglock provides a memory barrier. + * + * do_exit: + * The caller holds mm->mmap_sem. This means that the task which + * uses this mm can't pass exit_mm(), so it can't exit or clear + * its ->mm. + * + * de_thread: + * It does list_replace_rcu(&leader->tasks, ¤t->tasks), + * we must see either old or new leader, this does not matter. + * However, it can change p->sighand, so lock_task_sighand(p) + * must be used. Since p->mm != NULL and we hold ->mmap_sem + * it can't fail. + * + * Note also that "g" can be the old leader with ->mm == NULL + * and already unhashed and thus removed from ->thread_group. + * This is OK, __unhash_process()->list_del_rcu() does not + * clear the ->next pointer, we will find the new leader via + * next_thread(). + */ + rcu_read_lock(); + for_each_process(g) { + if (g == tsk->group_leader) + continue; + if (g->flags & PF_KTHREAD) + continue; + p = g; + do { + if (p->mm) { + if (unlikely(p->mm == mm)) { + lock_task_sighand(p, &flags); + nr += zap_process(p); + unlock_task_sighand(p, &flags); + } + break; + } + } while_each_thread(g, p); + } + rcu_read_unlock(); +done: + atomic_set(&core_state->nr_threads, nr); + return nr; +} + +static int coredump_wait(int exit_code, struct core_state *core_state) +{ struct task_struct *tsk = current; - struct completion *vfork_done = tsk->vfork_done; - int traced = 0; + struct mm_struct *mm = tsk->mm; + struct completion *vfork_done; + int core_waiters; + + init_completion(&core_state->startup); + core_state->dumper.task = tsk; + core_state->dumper.next = NULL; + core_waiters = zap_threads(tsk, mm, core_state, exit_code); + up_write(&mm->mmap_sem); + + if (unlikely(core_waiters < 0)) + goto fail; /* * Make sure nobody is waiting for us to release the VM, * otherwise we can deadlock when we wait on each other */ + vfork_done = tsk->vfork_done; if (vfork_done) { tsk->vfork_done = NULL; complete(vfork_done); } - read_lock(&tasklist_lock); - do_each_thread(g,p) - if (mm == p->mm && p != tsk) { - force_sig_specific(SIGKILL, p); - mm->core_waiters++; - if (unlikely(p->ptrace) && - unlikely(p->parent->mm == mm)) - traced = 1; - } - while_each_thread(g,p); + if (core_waiters) + wait_for_completion(&core_state->startup); +fail: + return core_waiters; +} - read_unlock(&tasklist_lock); +static void coredump_finish(struct mm_struct *mm) +{ + struct core_thread *curr, *next; + struct task_struct *task; - if (unlikely(traced)) { + next = mm->core_state->dumper.next; + while ((curr = next) != NULL) { + next = curr->next; + task = curr->task; /* - * We are zapping a thread and the thread it ptraces. - * If the tracee went into a ptrace stop for exit tracing, - * we could deadlock since the tracer is waiting for this - * coredump to finish. Detach them so they can both die. + * see exit_mm(), curr->task must not see + * ->task == NULL before we read ->next. */ - write_lock_irq(&tasklist_lock); - do_each_thread(g,p) { - if (mm == p->mm && p != tsk && - p->ptrace && p->parent->mm == mm) { - __ptrace_unlink(p); - } - } while_each_thread(g,p); - write_unlock_irq(&tasklist_lock); + smp_mb(); + curr->task = NULL; + wake_up_process(task); } + + mm->core_state = NULL; } -static void coredump_wait(struct mm_struct *mm) +/* + * set_dumpable converts traditional three-value dumpable to two flags and + * stores them into mm->flags. It modifies lower two bits of mm->flags, but + * these bits are not changed atomically. So get_dumpable can observe the + * intermediate state. To avoid doing unexpected behavior, get get_dumpable + * return either old dumpable or new one by paying attention to the order of + * modifying the bits. + * + * dumpable | mm->flags (binary) + * old new | initial interim final + * ---------+----------------------- + * 0 1 | 00 01 01 + * 0 2 | 00 10(*) 11 + * 1 0 | 01 00 00 + * 1 2 | 01 11 11 + * 2 0 | 11 10(*) 00 + * 2 1 | 11 11 01 + * + * (*) get_dumpable regards interim value of 10 as 11. + */ +void set_dumpable(struct mm_struct *mm, int value) { - DECLARE_COMPLETION(startup_done); - int core_waiters; + switch (value) { + case 0: + clear_bit(MMF_DUMPABLE, &mm->flags); + smp_wmb(); + clear_bit(MMF_DUMP_SECURELY, &mm->flags); + break; + case 1: + set_bit(MMF_DUMPABLE, &mm->flags); + smp_wmb(); + clear_bit(MMF_DUMP_SECURELY, &mm->flags); + break; + case 2: + set_bit(MMF_DUMP_SECURELY, &mm->flags); + smp_wmb(); + set_bit(MMF_DUMPABLE, &mm->flags); + break; + } +} - mm->core_startup_done = &startup_done; +int get_dumpable(struct mm_struct *mm) +{ + int ret; - zap_threads(mm); - core_waiters = mm->core_waiters; - up_write(&mm->mmap_sem); + ret = mm->flags & 0x3; + return (ret >= 2) ? 2 : ret; +} + +static void wait_for_dump_helpers(struct file *file) +{ + struct pipe_inode_info *pipe; + + pipe = file->f_path.dentry->d_inode->i_pipe; + + pipe_lock(pipe); + pipe->readers++; + pipe->writers--; + + while ((pipe->readers > 1) && (!signal_pending(current))) { + wake_up_interruptible_sync(&pipe->wait); + kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); + pipe_wait(pipe); + } + + pipe->readers--; + pipe->writers++; + pipe_unlock(pipe); - if (core_waiters) - wait_for_completion(&startup_done); - BUG_ON(mm->core_waiters); } -int do_coredump(long signr, int exit_code, struct pt_regs * regs) + +void do_coredump(long signr, int exit_code, struct pt_regs *regs) { + struct core_state core_state; char corename[CORENAME_MAX_SIZE + 1]; struct mm_struct *mm = current->mm; struct linux_binfmt * binfmt; struct inode * inode; - struct file * file; + const struct cred *old_cred; + struct cred *cred; int retval = 0; - int fsuid = current->fsuid; int flag = 0; - - binfmt = current->binfmt; + int ispipe = 0; + char **helper_argv = NULL; + int helper_argc = 0; + int dump_count = 0; + static atomic_t core_dump_count = ATOMIC_INIT(0); + struct coredump_params cprm = { + .signr = signr, + .regs = regs, + .limit = current->signal->rlim[RLIMIT_CORE].rlim_cur, + }; + + audit_core_dumps(signr); + + binfmt = mm->binfmt; if (!binfmt || !binfmt->core_dump) goto fail; + + cred = prepare_creds(); + if (!cred) { + retval = -ENOMEM; + goto fail; + } + down_write(&mm->mmap_sem); - if (!mm->dumpable) { + /* + * If another thread got here first, or we are not dumpable, bail out. + */ + if (mm->core_state || !get_dumpable(mm)) { up_write(&mm->mmap_sem); + put_cred(cred); goto fail; } @@ -1461,72 +1805,131 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) * process nor do we know its entire history. We only know it * was tainted so we dump it as root in mode 2. */ - if (mm->dumpable == 2) { /* Setuid core dump mode */ + if (get_dumpable(mm) == 2) { /* Setuid core dump mode */ flag = O_EXCL; /* Stop rewrite attacks */ - current->fsuid = 0; /* Dump root private */ - } - mm->dumpable = 0; - - retval = -EAGAIN; - spin_lock_irq(¤t->sighand->siglock); - if (!(current->signal->flags & SIGNAL_GROUP_EXIT)) { - current->signal->flags = SIGNAL_GROUP_EXIT; - current->signal->group_exit_code = exit_code; - retval = 0; + cred->fsuid = 0; /* Dump root private */ } - spin_unlock_irq(¤t->sighand->siglock); - if (retval) { - up_write(&mm->mmap_sem); + + retval = coredump_wait(exit_code, &core_state); + if (retval < 0) { + put_cred(cred); goto fail; } - init_completion(&mm->core_done); - coredump_wait(mm); + old_cred = override_creds(cred); /* * Clear any false indication of pending signals that might * be seen by the filesystem code called to write the core file. */ - current->signal->group_stop_count = 0; clear_thread_flag(TIF_SIGPENDING); - if (current->signal->rlim[RLIMIT_CORE].rlim_cur < binfmt->min_coredump) - goto fail_unlock; - /* * lock_kernel() because format_corename() is controlled by sysctl, which * uses lock_kernel() */ lock_kernel(); - format_corename(corename, core_pattern, signr); + ispipe = format_corename(corename, signr); unlock_kernel(); - file = filp_open(corename, O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag, 0600); - if (IS_ERR(file)) + + if ((!ispipe) && (cprm.limit < binfmt->min_coredump)) goto fail_unlock; - inode = file->f_dentry->d_inode; + + if (ispipe) { + if (cprm.limit == 0) { + /* + * Normally core limits are irrelevant to pipes, since + * we're not writing to the file system, but we use + * cprm.limit of 0 here as a speacial value. Any + * non-zero limit gets set to RLIM_INFINITY below, but + * a limit of 0 skips the dump. This is a consistent + * way to catch recursive crashes. We can still crash + * if the core_pattern binary sets RLIM_CORE = !0 + * but it runs as root, and can do lots of stupid things + * Note that we use task_tgid_vnr here to grab the pid + * of the process group leader. That way we get the + * right pid if a thread in a multi-threaded + * core_pattern process dies. + */ + printk(KERN_WARNING + "Process %d(%s) has RLIMIT_CORE set to 0\n", + task_tgid_vnr(current), current->comm); + printk(KERN_WARNING "Aborting core\n"); + goto fail_unlock; + } + + dump_count = atomic_inc_return(&core_dump_count); + if (core_pipe_limit && (core_pipe_limit < dump_count)) { + printk(KERN_WARNING "Pid %d(%s) over core_pipe_limit\n", + task_tgid_vnr(current), current->comm); + printk(KERN_WARNING "Skipping core dump\n"); + goto fail_dropcount; + } + + helper_argv = argv_split(GFP_KERNEL, corename+1, &helper_argc); + if (!helper_argv) { + printk(KERN_WARNING "%s failed to allocate memory\n", + __func__); + goto fail_dropcount; + } + + cprm.limit = RLIM_INFINITY; + + /* SIGPIPE can happen, but it's just never processed */ + if (call_usermodehelper_pipe(helper_argv[0], helper_argv, NULL, + &cprm.file)) { + printk(KERN_INFO "Core dump to %s pipe failed\n", + corename); + goto fail_dropcount; + } + } else + cprm.file = filp_open(corename, + O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag, + 0600); + if (IS_ERR(cprm.file)) + goto fail_dropcount; + inode = cprm.file->f_path.dentry->d_inode; if (inode->i_nlink > 1) goto close_fail; /* multiple links - don't dump */ - if (d_unhashed(file->f_dentry)) + if (!ispipe && d_unhashed(cprm.file->f_path.dentry)) goto close_fail; - if (!S_ISREG(inode->i_mode)) + /* AK: actually i see no reason to not allow this for named pipes etc., + but keep the previous behaviour for now. */ + if (!ispipe && !S_ISREG(inode->i_mode)) + goto close_fail; + /* + * Dont allow local users get cute and trick others to coredump + * into their pre-created files: + */ + if (inode->i_uid != current_fsuid()) goto close_fail; - if (!file->f_op) + if (!cprm.file->f_op) goto close_fail; - if (!file->f_op->write) + if (!cprm.file->f_op->write) goto close_fail; - if (do_truncate(file->f_dentry, 0, file) != 0) + if (!ispipe && + do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file) != 0) goto close_fail; - retval = binfmt->core_dump(signr, regs, file); + retval = binfmt->core_dump(&cprm); if (retval) current->signal->group_exit_code |= 0x80; close_fail: - filp_close(file, NULL); + if (ispipe && core_pipe_limit) + wait_for_dump_helpers(cprm.file); + filp_close(cprm.file, NULL); +fail_dropcount: + if (dump_count) + atomic_dec(&core_dump_count); fail_unlock: - current->fsuid = fsuid; - complete_all(&mm->core_done); + if (helper_argv) + argv_free(helper_argv); + + revert_creds(old_cred); + put_cred(cred); + coredump_finish(mm); fail: - return retval; + return; }