From d7627467b7a8dd6944885290a03a07ceb28c10eb Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 17 Aug 2010 23:52:56 +0100 Subject: Make do_execve() take a const filename pointer Make do_execve() take a const filename pointer so that kernel_execve() compiles correctly on ARM: arch/arm/kernel/sys_arm.c:88: warning: passing argument 1 of 'do_execve' discards qualifiers from pointer target type This also requires the argv and envp arguments to be consted twice, once for the pointer array and once for the strings the array points to. This is because do_execve() passes a pointer to the filename (now const) to copy_strings_kernel(). A simpler alternative would be to cast the filename pointer in do_execve() when it's passed to copy_strings_kernel(). do_execve() may not change any of the strings it is passed as part of the argv or envp lists as they are some of them in .rodata, so marking these strings as const should be fine. Further kernel_execve() and sys_execve() need to be changed to match. This has been test built on x86_64, frv, arm and mips. Signed-off-by: David Howells Tested-by: Ralf Baechle Acked-by: Russell King Signed-off-by: Linus Torvalds --- fs/exec.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 7761837e450..05c7d6b84df 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -361,13 +361,13 @@ err: /* * count() counts the number of strings in array ARGV. */ -static int count(char __user * __user * argv, int max) +static int count(const char __user * const __user * argv, int max) { int i = 0; if (argv != NULL) { for (;;) { - char __user * p; + const char __user * p; if (get_user(p, argv)) return -EFAULT; @@ -387,7 +387,7 @@ static int count(char __user * __user * argv, int max) * 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, +static int copy_strings(int argc, const char __user *const __user *argv, struct linux_binprm *bprm) { struct page *kmapped_page = NULL; @@ -396,7 +396,7 @@ static int copy_strings(int argc, char __user * __user * argv, int ret; while (argc-- > 0) { - char __user *str; + const char __user *str; int len; unsigned long pos; @@ -470,12 +470,13 @@ out: /* * Like copy_strings, but get argv and its values from kernel memory. */ -int copy_strings_kernel(int argc,char ** argv, struct linux_binprm *bprm) +int copy_strings_kernel(int argc, const char *const *argv, + struct linux_binprm *bprm) { int r; mm_segment_t oldfs = get_fs(); set_fs(KERNEL_DS); - r = copy_strings(argc, (char __user * __user *)argv, bprm); + r = copy_strings(argc, (const char __user *const __user *)argv, bprm); set_fs(oldfs); return r; } @@ -997,7 +998,7 @@ EXPORT_SYMBOL(flush_old_exec); void setup_new_exec(struct linux_binprm * bprm) { int i, ch; - char * name; + const char *name; char tcomm[sizeof(current->comm)]; arch_pick_mmap_layout(current->mm); @@ -1316,9 +1317,9 @@ EXPORT_SYMBOL(search_binary_handler); /* * sys_execve() executes a new program. */ -int do_execve(char * filename, - char __user *__user *argv, - char __user *__user *envp, +int do_execve(const char * filename, + const char __user *const __user *argv, + const char __user *const __user *envp, struct pt_regs * regs) { struct linux_binprm *bprm; -- cgit v1.2.3-70-g09d2 From 2a4419b5b2a77f3f4537c14f7ad7df95770655dd Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 18 Aug 2010 04:37:33 +1000 Subject: fs: fs_struct rwlock to spinlock fs: fs_struct rwlock to spinlock struct fs_struct.lock is an rwlock with the read-side used to protect root and pwd members while taking references to them. Taking a reference to a path typically requires just 2 atomic ops, so the critical section is very small. Parallel read-side operations would have cacheline contention on the lock, the dentry, and the vfsmount cachelines, so the rwlock is unlikely to ever give a real parallelism increase. Replace it with a spinlock to avoid one or two atomic operations in typical path lookup fastpath. Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- drivers/staging/pohmelfs/path_entry.c | 8 ++++---- fs/exec.c | 4 ++-- fs/fs_struct.c | 32 ++++++++++++++++---------------- include/linux/fs_struct.h | 14 +++++++------- kernel/fork.c | 10 +++++----- 5 files changed, 34 insertions(+), 34 deletions(-) (limited to 'fs/exec.c') diff --git a/drivers/staging/pohmelfs/path_entry.c b/drivers/staging/pohmelfs/path_entry.c index cdc4dd50d63..8ec83d2dffb 100644 --- a/drivers/staging/pohmelfs/path_entry.c +++ b/drivers/staging/pohmelfs/path_entry.c @@ -44,9 +44,9 @@ int pohmelfs_construct_path_string(struct pohmelfs_inode *pi, void *data, int le return -ENOENT; } - read_lock(¤t->fs->lock); + spin_lock(¤t->fs->lock); path.mnt = mntget(current->fs->root.mnt); - read_unlock(¤t->fs->lock); + spin_unlock(¤t->fs->lock); path.dentry = d; @@ -91,9 +91,9 @@ int pohmelfs_path_length(struct pohmelfs_inode *pi) return -ENOENT; } - read_lock(¤t->fs->lock); + spin_lock(¤t->fs->lock); root = dget(current->fs->root.dentry); - read_unlock(¤t->fs->lock); + spin_unlock(¤t->fs->lock); spin_lock(&dcache_lock); diff --git a/fs/exec.c b/fs/exec.c index 7761837e450..5adab2c93ec 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1117,7 +1117,7 @@ int check_unsafe_exec(struct linux_binprm *bprm) bprm->unsafe = tracehook_unsafe_exec(p); n_fs = 1; - write_lock(&p->fs->lock); + spin_lock(&p->fs->lock); rcu_read_lock(); for (t = next_thread(p); t != p; t = next_thread(t)) { if (t->fs == p->fs) @@ -1134,7 +1134,7 @@ int check_unsafe_exec(struct linux_binprm *bprm) res = 1; } } - write_unlock(&p->fs->lock); + spin_unlock(&p->fs->lock); return res; } diff --git a/fs/fs_struct.c b/fs/fs_struct.c index 1ee40eb9a2c..ed45a9cf5f3 100644 --- a/fs/fs_struct.c +++ b/fs/fs_struct.c @@ -13,11 +13,11 @@ void set_fs_root(struct fs_struct *fs, struct path *path) { struct path old_root; - write_lock(&fs->lock); + spin_lock(&fs->lock); old_root = fs->root; fs->root = *path; path_get(path); - write_unlock(&fs->lock); + spin_unlock(&fs->lock); if (old_root.dentry) path_put(&old_root); } @@ -30,11 +30,11 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path) { struct path old_pwd; - write_lock(&fs->lock); + spin_lock(&fs->lock); old_pwd = fs->pwd; fs->pwd = *path; path_get(path); - write_unlock(&fs->lock); + spin_unlock(&fs->lock); if (old_pwd.dentry) path_put(&old_pwd); @@ -51,7 +51,7 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root) task_lock(p); fs = p->fs; if (fs) { - write_lock(&fs->lock); + spin_lock(&fs->lock); if (fs->root.dentry == old_root->dentry && fs->root.mnt == old_root->mnt) { path_get(new_root); @@ -64,7 +64,7 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root) fs->pwd = *new_root; count++; } - write_unlock(&fs->lock); + spin_unlock(&fs->lock); } task_unlock(p); } while_each_thread(g, p); @@ -87,10 +87,10 @@ void exit_fs(struct task_struct *tsk) if (fs) { int kill; task_lock(tsk); - write_lock(&fs->lock); + spin_lock(&fs->lock); tsk->fs = NULL; kill = !--fs->users; - write_unlock(&fs->lock); + spin_unlock(&fs->lock); task_unlock(tsk); if (kill) free_fs_struct(fs); @@ -104,7 +104,7 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old) if (fs) { fs->users = 1; fs->in_exec = 0; - rwlock_init(&fs->lock); + spin_lock_init(&fs->lock); fs->umask = old->umask; get_fs_root_and_pwd(old, &fs->root, &fs->pwd); } @@ -121,10 +121,10 @@ int unshare_fs_struct(void) return -ENOMEM; task_lock(current); - write_lock(&fs->lock); + spin_lock(&fs->lock); kill = !--fs->users; current->fs = new_fs; - write_unlock(&fs->lock); + spin_unlock(&fs->lock); task_unlock(current); if (kill) @@ -143,7 +143,7 @@ EXPORT_SYMBOL(current_umask); /* to be mentioned only in INIT_TASK */ struct fs_struct init_fs = { .users = 1, - .lock = __RW_LOCK_UNLOCKED(init_fs.lock), + .lock = __SPIN_LOCK_UNLOCKED(init_fs.lock), .umask = 0022, }; @@ -156,14 +156,14 @@ void daemonize_fs_struct(void) task_lock(current); - write_lock(&init_fs.lock); + spin_lock(&init_fs.lock); init_fs.users++; - write_unlock(&init_fs.lock); + spin_unlock(&init_fs.lock); - write_lock(&fs->lock); + spin_lock(&fs->lock); current->fs = &init_fs; kill = !--fs->users; - write_unlock(&fs->lock); + spin_unlock(&fs->lock); task_unlock(current); if (kill) diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index eca3d520213..a42b5bf02f8 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -5,7 +5,7 @@ struct fs_struct { int users; - rwlock_t lock; + spinlock_t lock; int umask; int in_exec; struct path root, pwd; @@ -23,29 +23,29 @@ extern int unshare_fs_struct(void); static inline void get_fs_root(struct fs_struct *fs, struct path *root) { - read_lock(&fs->lock); + spin_lock(&fs->lock); *root = fs->root; path_get(root); - read_unlock(&fs->lock); + spin_unlock(&fs->lock); } static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) { - read_lock(&fs->lock); + spin_lock(&fs->lock); *pwd = fs->pwd; path_get(pwd); - read_unlock(&fs->lock); + spin_unlock(&fs->lock); } static inline void get_fs_root_and_pwd(struct fs_struct *fs, struct path *root, struct path *pwd) { - read_lock(&fs->lock); + spin_lock(&fs->lock); *root = fs->root; path_get(root); *pwd = fs->pwd; path_get(pwd); - read_unlock(&fs->lock); + spin_unlock(&fs->lock); } #endif /* _LINUX_FS_STRUCT_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 98b450876f9..856eac3ec52 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -752,13 +752,13 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ - write_lock(&fs->lock); + spin_lock(&fs->lock); if (fs->in_exec) { - write_unlock(&fs->lock); + spin_unlock(&fs->lock); return -EAGAIN; } fs->users++; - write_unlock(&fs->lock); + spin_unlock(&fs->lock); return 0; } tsk->fs = copy_fs_struct(fs); @@ -1676,13 +1676,13 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) if (new_fs) { fs = current->fs; - write_lock(&fs->lock); + spin_lock(&fs->lock); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; - write_unlock(&fs->lock); + spin_unlock(&fs->lock); } if (new_mm) { -- cgit v1.2.3-70-g09d2 From 1b528181b2ffa14721fb28ad1bd539fe1732c583 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Tue, 7 Sep 2010 19:35:49 -0700 Subject: setup_arg_pages: diagnose excessive argument size The CONFIG_STACK_GROWSDOWN variant of setup_arg_pages() does not check the size of the argument/environment area on the stack. When it is unworkably large, shift_arg_pages() hits its BUG_ON. This is exploitable with a very large RLIMIT_STACK limit, to create a crash pretty easily. Check that the initial stack is not too large to make it possible to map in any executable. We're not checking that the actual executable (or intepreter, for binfmt_elf) will fit. So those mappings might clobber part of the initial stack mapping. But that is just userland lossage that userland made happen, not a kernel problem. Signed-off-by: Roland McGrath Reviewed-by: KOSAKI Motohiro Signed-off-by: Linus Torvalds --- fs/exec.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 2d945528274..1b63237fc6d 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -594,6 +594,11 @@ int setup_arg_pages(struct linux_binprm *bprm, #else stack_top = arch_align_stack(stack_top); stack_top = PAGE_ALIGN(stack_top); + + if (unlikely(stack_top < mmap_min_addr) || + unlikely(vma->vm_end - vma->vm_start >= stack_top - mmap_min_addr)) + return -ENOMEM; + stack_shift = vma->vm_end - stack_top; bprm->p -= stack_shift; -- cgit v1.2.3-70-g09d2 From 7993bc1f4663c0db67bb8f0d98e6678145b387cd Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Tue, 7 Sep 2010 19:36:28 -0700 Subject: execve: improve interactivity with large arguments This adds a preemption point during the copying of the argument and environment strings for execve, in copy_strings(). There is already a preemption point in the count() loop, so this doesn't add any new points in the abstract sense. When the total argument+environment strings are very large, the time spent copying them can be much more than a normal user time slice. So this change improves the interactivity of the rest of the system when one process is doing an execve with very large arguments. Signed-off-by: Roland McGrath Reviewed-by: KOSAKI Motohiro Signed-off-by: Linus Torvalds --- fs/exec.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 1b63237fc6d..6f2d777431a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -419,6 +419,8 @@ static int copy_strings(int argc, const char __user *const __user *argv, while (len > 0) { int offset, bytes_to_copy; + cond_resched(); + offset = pos % PAGE_SIZE; if (offset == 0) offset = PAGE_SIZE; -- cgit v1.2.3-70-g09d2 From 9aea5a65aa7a1af9a4236dfaeb0088f1624f9919 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Tue, 7 Sep 2010 19:37:06 -0700 Subject: execve: make responsive to SIGKILL with large arguments An execve with a very large total of argument/environment strings can take a really long time in the execve system call. It runs uninterruptibly to count and copy all the strings. This change makes it abort the exec quickly if sent a SIGKILL. Note that this is the conservative change, to interrupt only for SIGKILL, by using fatal_signal_pending(). It would be perfectly correct semantics to let any signal interrupt the string-copying in execve, i.e. use signal_pending() instead of fatal_signal_pending(). We'll save that change for later, since it could have user-visible consequences, such as having a timer set too quickly make it so that an execve can never complete, though it always happened to work before. Signed-off-by: Roland McGrath Reviewed-by: KOSAKI Motohiro Signed-off-by: Linus Torvalds --- fs/exec.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 6f2d777431a..828dd2461d6 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -376,6 +376,9 @@ static int count(const char __user * const __user * argv, int max) argv++; if (i++ >= max) return -E2BIG; + + if (fatal_signal_pending(current)) + return -ERESTARTNOHAND; cond_resched(); } } @@ -419,6 +422,10 @@ static int copy_strings(int argc, const char __user *const __user *argv, while (len > 0) { int offset, bytes_to_copy; + if (fatal_signal_pending(current)) { + ret = -ERESTARTNOHAND; + goto out; + } cond_resched(); offset = pos % PAGE_SIZE; -- cgit v1.2.3-70-g09d2