diff options
Diffstat (limited to 'fs/proc')
-rw-r--r-- | fs/proc/array.c | 15 | ||||
-rw-r--r-- | fs/proc/base.c | 570 | ||||
-rw-r--r-- | fs/proc/generic.c | 10 | ||||
-rw-r--r-- | fs/proc/inode.c | 21 | ||||
-rw-r--r-- | fs/proc/internal.h | 1 | ||||
-rw-r--r-- | fs/proc/meminfo.c | 7 | ||||
-rw-r--r-- | fs/proc/namespaces.c | 1 | ||||
-rw-r--r-- | fs/proc/proc_net.c | 2 | ||||
-rw-r--r-- | fs/proc/proc_sysctl.c | 48 | ||||
-rw-r--r-- | fs/proc/root.c | 78 | ||||
-rw-r--r-- | fs/proc/stat.c | 82 | ||||
-rw-r--r-- | fs/proc/task_mmu.c | 5 | ||||
-rw-r--r-- | fs/proc/uptime.c | 11 | ||||
-rw-r--r-- | fs/proc/vmcore.c | 1 |
14 files changed, 658 insertions, 194 deletions
diff --git a/fs/proc/array.c b/fs/proc/array.c index ddffd7a..c602b8d 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -394,8 +394,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, sigemptyset(&sigign); sigemptyset(&sigcatch); - cutime = cstime = utime = stime = cputime_zero; - cgtime = gtime = cputime_zero; + cutime = cstime = utime = stime = 0; + cgtime = gtime = 0; if (lock_task_sighand(task, &flags)) { struct signal_struct *sig = task->signal; @@ -423,14 +423,14 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, do { min_flt += t->min_flt; maj_flt += t->maj_flt; - gtime = cputime_add(gtime, t->gtime); + gtime += t->gtime; t = next_thread(t); } while (t != task); min_flt += sig->min_flt; maj_flt += sig->maj_flt; thread_group_times(task, &utime, &stime); - gtime = cputime_add(gtime, sig->gtime); + gtime += sig->gtime; } sid = task_session_nr_ns(task, ns); @@ -464,7 +464,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, seq_printf(m, "%d (%s) %c %d %d %d %d %d %u %lu \ %lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \ -%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld\n", +%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld %lu %lu %lu\n", pid_nr_ns(pid, ns), tcomm, state, @@ -511,7 +511,10 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, task->policy, (unsigned long long)delayacct_blkio_ticks(task), cputime_to_clock_t(gtime), - cputime_to_clock_t(cgtime)); + cputime_to_clock_t(cgtime), + (mm && permitted) ? mm->start_data : 0, + (mm && permitted) ? mm->end_data : 0, + (mm && permitted) ? mm->start_brk : 0); if (mm) mmput(mm); return 0; diff --git a/fs/proc/base.c b/fs/proc/base.c index 5eb0206..5485a53 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -83,9 +83,11 @@ #include <linux/pid_namespace.h> #include <linux/fs_struct.h> #include <linux/slab.h> +#include <linux/flex_array.h> #ifdef CONFIG_HARDWALL #include <asm/hardwall.h> #endif +#include <trace/events/oom.h> #include "internal.h" /* NOTE: @@ -101,7 +103,7 @@ struct pid_entry { char *name; int len; - mode_t mode; + umode_t mode; const struct inode_operations *iop; const struct file_operations *fop; union proc_op op; @@ -133,6 +135,8 @@ struct pid_entry { NULL, &proc_single_file_operations, \ { .proc_show = show } ) +static int proc_fd_permission(struct inode *inode, int mask); + /* * Count the number of hardlinks for the pid_entry table, excluding the . * and .. links. @@ -165,9 +169,9 @@ static int get_task_root(struct task_struct *task, struct path *root) return result; } -static int proc_cwd_link(struct inode *inode, struct path *path) +static int proc_cwd_link(struct dentry *dentry, struct path *path) { - struct task_struct *task = get_proc_task(inode); + struct task_struct *task = get_proc_task(dentry->d_inode); int result = -ENOENT; if (task) { @@ -182,9 +186,9 @@ static int proc_cwd_link(struct inode *inode, struct path *path) return result; } -static int proc_root_link(struct inode *inode, struct path *path) +static int proc_root_link(struct dentry *dentry, struct path *path) { - struct task_struct *task = get_proc_task(inode); + struct task_struct *task = get_proc_task(dentry->d_inode); int result = -ENOENT; if (task) { @@ -627,122 +631,54 @@ int proc_setattr(struct dentry *dentry, struct iattr *attr) return 0; } -static const struct inode_operations proc_def_inode_operations = { - .setattr = proc_setattr, -}; - -static int mounts_open_common(struct inode *inode, struct file *file, - const struct seq_operations *op) +/* + * May current process learn task's sched/cmdline info (for hide_pid_min=1) + * or euid/egid (for hide_pid_min=2)? + */ +static bool has_pid_permissions(struct pid_namespace *pid, + struct task_struct *task, + int hide_pid_min) { - struct task_struct *task = get_proc_task(inode); - struct nsproxy *nsp; - struct mnt_namespace *ns = NULL; - struct path root; - struct proc_mounts *p; - int ret = -EINVAL; - - if (task) { - rcu_read_lock(); - nsp = task_nsproxy(task); - if (nsp) { - ns = nsp->mnt_ns; - if (ns) - get_mnt_ns(ns); - } - rcu_read_unlock(); - if (ns && get_task_root(task, &root) == 0) - ret = 0; - put_task_struct(task); - } - - if (!ns) - goto err; - if (ret) - goto err_put_ns; - - ret = -ENOMEM; - p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL); - if (!p) - goto err_put_path; - - file->private_data = &p->m; - ret = seq_open(file, op); - if (ret) - goto err_free; - - p->m.private = p; - p->ns = ns; - p->root = root; - p->m.poll_event = ns->event; - - return 0; - - err_free: - kfree(p); - err_put_path: - path_put(&root); - err_put_ns: - put_mnt_ns(ns); - err: - return ret; + if (pid->hide_pid < hide_pid_min) + return true; + if (in_group_p(pid->pid_gid)) + return true; + return ptrace_may_access(task, PTRACE_MODE_READ); } -static int mounts_release(struct inode *inode, struct file *file) -{ - struct proc_mounts *p = file->private_data; - path_put(&p->root); - put_mnt_ns(p->ns); - return seq_release(inode, file); -} -static unsigned mounts_poll(struct file *file, poll_table *wait) +static int proc_pid_permission(struct inode *inode, int mask) { - struct proc_mounts *p = file->private_data; - unsigned res = POLLIN | POLLRDNORM; - - poll_wait(file, &p->ns->poll, wait); - if (mnt_had_events(p)) - res |= POLLERR | POLLPRI; - - return res; -} + struct pid_namespace *pid = inode->i_sb->s_fs_info; + struct task_struct *task; + bool has_perms; -static int mounts_open(struct inode *inode, struct file *file) -{ - return mounts_open_common(inode, file, &mounts_op); -} + task = get_proc_task(inode); + if (!task) + return -ESRCH; + has_perms = has_pid_permissions(pid, task, 1); + put_task_struct(task); -static const struct file_operations proc_mounts_operations = { - .open = mounts_open, - .read = seq_read, - .llseek = seq_lseek, - .release = mounts_release, - .poll = mounts_poll, -}; + if (!has_perms) { + if (pid->hide_pid == 2) { + /* + * Let's make getdents(), stat(), and open() + * consistent with each other. If a process + * may not stat() a file, it shouldn't be seen + * in procfs at all. + */ + return -ENOENT; + } -static int mountinfo_open(struct inode *inode, struct file *file) -{ - return mounts_open_common(inode, file, &mountinfo_op); + return -EPERM; + } + return generic_permission(inode, mask); } -static const struct file_operations proc_mountinfo_operations = { - .open = mountinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = mounts_release, - .poll = mounts_poll, -}; -static int mountstats_open(struct inode *inode, struct file *file) -{ - return mounts_open_common(inode, file, &mountstats_op); -} -static const struct file_operations proc_mountstats_operations = { - .open = mountstats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = mounts_release, +static const struct inode_operations proc_def_inode_operations = { + .setattr = proc_setattr, }; #define PROC_BLOCK_SIZE (3*1024) /* 4K page size but our output routines use some slack for overruns */ @@ -1107,13 +1043,6 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, goto err_sighand; } - if (oom_adjust != task->signal->oom_adj) { - if (oom_adjust == OOM_DISABLE) - atomic_inc(&task->mm->oom_disable_count); - if (task->signal->oom_adj == OOM_DISABLE) - atomic_dec(&task->mm->oom_disable_count); - } - /* * Warn that /proc/pid/oom_adj is deprecated, see * Documentation/feature-removal-schedule.txt. @@ -1131,6 +1060,7 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, else task->signal->oom_score_adj = (oom_adjust * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; + trace_oom_score_adj_update(task); err_sighand: unlock_task_sighand(task, &flags); err_task_lock: @@ -1215,15 +1145,10 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, goto err_sighand; } - if (oom_score_adj != task->signal->oom_score_adj) { - if (oom_score_adj == OOM_SCORE_ADJ_MIN) - atomic_inc(&task->mm->oom_disable_count); - if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) - atomic_dec(&task->mm->oom_disable_count); - } task->signal->oom_score_adj = oom_score_adj; if (has_capability_noaudit(current, CAP_SYS_RESOURCE)) task->signal->oom_score_adj_min = oom_score_adj; + trace_oom_score_adj_update(task); /* * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is * always attainable. @@ -1580,13 +1505,13 @@ static const struct file_operations proc_pid_set_comm_operations = { .release = single_release, }; -static int proc_exe_link(struct inode *inode, struct path *exe_path) +static int proc_exe_link(struct dentry *dentry, struct path *exe_path) { struct task_struct *task; struct mm_struct *mm; struct file *exe_file; - task = get_proc_task(inode); + task = get_proc_task(dentry->d_inode); if (!task) return -ENOENT; mm = get_task_mm(task); @@ -1616,7 +1541,7 @@ static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) if (!proc_fd_access_allowed(inode)) goto out; - error = PROC_I(inode)->op.proc_get_link(inode, &nd->path); + error = PROC_I(inode)->op.proc_get_link(dentry, &nd->path); out: return ERR_PTR(error); } @@ -1655,7 +1580,7 @@ static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int b if (!proc_fd_access_allowed(inode)) goto out; - error = PROC_I(inode)->op.proc_get_link(inode, &path); + error = PROC_I(inode)->op.proc_get_link(dentry, &path); if (error) goto out; @@ -1736,6 +1661,7 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) struct inode *inode = dentry->d_inode; struct task_struct *task; const struct cred *cred; + struct pid_namespace *pid = dentry->d_sb->s_fs_info; generic_fillattr(inode, stat); @@ -1744,6 +1670,14 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) stat->gid = 0; task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { + if (!has_pid_permissions(pid, task, 2)) { + rcu_read_unlock(); + /* + * This doesn't prevent learning whether PID exists, + * it only makes getattr() consistent with readdir(). + */ + return -ENOENT; + } if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || task_dumpable(task)) { cred = __task_cred(task); @@ -1947,9 +1881,9 @@ static int proc_fd_info(struct inode *inode, struct path *path, char *info) return -ENOENT; } -static int proc_fd_link(struct inode *inode, struct path *path) +static int proc_fd_link(struct dentry *dentry, struct path *path) { - return proc_fd_info(inode, path, NULL); + return proc_fd_info(dentry->d_inode, path, NULL); } static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) @@ -2170,6 +2104,355 @@ static const struct file_operations proc_fd_operations = { .llseek = default_llseek, }; +#ifdef CONFIG_CHECKPOINT_RESTORE + +/* + * dname_to_vma_addr - maps a dentry name into two unsigned longs + * which represent vma start and end addresses. + */ +static int dname_to_vma_addr(struct dentry *dentry, + unsigned long *start, unsigned long *end) +{ + if (sscanf(dentry->d_name.name, "%lx-%lx", start, end) != 2) + return -EINVAL; + + return 0; +} + +static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd) +{ + unsigned long vm_start, vm_end; + bool exact_vma_exists = false; + struct mm_struct *mm = NULL; + struct task_struct *task; + const struct cred *cred; + struct inode *inode; + int status = 0; + + if (nd && nd->flags & LOOKUP_RCU) + return -ECHILD; + + if (!capable(CAP_SYS_ADMIN)) { + status = -EACCES; + goto out_notask; + } + + inode = dentry->d_inode; + task = get_proc_task(inode); + if (!task) + goto out_notask; + + if (!ptrace_may_access(task, PTRACE_MODE_READ)) + goto out; + + mm = get_task_mm(task); + if (!mm) + goto out; + + if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) { + down_read(&mm->mmap_sem); + exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end); + up_read(&mm->mmap_sem); + } + + mmput(mm); + + if (exact_vma_exists) { + if (task_dumpable(task)) { + rcu_read_lock(); + cred = __task_cred(task); + inode->i_uid = cred->euid; + inode->i_gid = cred->egid; + rcu_read_unlock(); + } else { + inode->i_uid = 0; + inode->i_gid = 0; + } + security_task_to_inode(task, inode); + status = 1; + } + +out: + put_task_struct(task); + +out_notask: + if (status <= 0) + d_drop(dentry); + + return status; +} + +static const struct dentry_operations tid_map_files_dentry_operations = { + .d_revalidate = map_files_d_revalidate, + .d_delete = pid_delete_dentry, +}; + +static int proc_map_files_get_link(struct dentry *dentry, struct path *path) +{ + unsigned long vm_start, vm_end; + struct vm_area_struct *vma; + struct task_struct *task; + struct mm_struct *mm; + int rc; + + rc = -ENOENT; + task = get_proc_task(dentry->d_inode); + if (!task) + goto out; + + mm = get_task_mm(task); + put_task_struct(task); + if (!mm) + goto out; + + rc = dname_to_vma_addr(dentry, &vm_start, &vm_end); + if (rc) + goto out_mmput; + + down_read(&mm->mmap_sem); + vma = find_exact_vma(mm, vm_start, vm_end); + if (vma && vma->vm_file) { + *path = vma->vm_file->f_path; + path_get(path); + rc = 0; + } + up_read(&mm->mmap_sem); + +out_mmput: + mmput(mm); +out: + return rc; +} + +struct map_files_info { + struct file *file; + unsigned long len; + unsigned char name[4*sizeof(long)+2]; /* max: %lx-%lx\0 */ +}; + +static struct dentry * +proc_map_files_instantiate(struct inode *dir, struct dentry *dentry, + struct task_struct *task, const void *ptr) +{ + const struct file *file = ptr; + struct proc_inode *ei; + struct inode *inode; + + if (!file) + return ERR_PTR(-ENOENT); + + inode = proc_pid_make_inode(dir->i_sb, task); + if (!inode) + return ERR_PTR(-ENOENT); + + ei = PROC_I(inode); + ei->op.proc_get_link = proc_map_files_get_link; + + inode->i_op = &proc_pid_link_inode_operations; + inode->i_size = 64; + inode->i_mode = S_IFLNK; + + if (file->f_mode & FMODE_READ) + inode->i_mode |= S_IRUSR; + if (file->f_mode & FMODE_WRITE) + inode->i_mode |= S_IWUSR; + + d_set_d_op(dentry, &tid_map_files_dentry_operations); + d_add(dentry, inode); + + return NULL; +} + +static struct dentry *proc_map_files_lookup(struct inode *dir, + struct dentry *dentry, struct nameidata *nd) +{ + unsigned long vm_start, vm_end; + struct vm_area_struct *vma; + struct task_struct *task; + struct dentry *result; + struct mm_struct *mm; + + result = ERR_PTR(-EACCES); + if (!capable(CAP_SYS_ADMIN)) + goto out; + + result = ERR_PTR(-ENOENT); + task = get_proc_task(dir); + if (!task) + goto out; + + result = ERR_PTR(-EACCES); + if (lock_trace(task)) + goto out_put_task; + + result = ERR_PTR(-ENOENT); + if (dname_to_vma_addr(dentry, &vm_start, &vm_end)) + goto out_unlock; + + mm = get_task_mm(task); + if (!mm) + goto out_unlock; + + down_read(&mm->mmap_sem); + vma = find_exact_vma(mm, vm_start, vm_end); + if (!vma) + goto out_no_vma; + + result = proc_map_files_instantiate(dir, dentry, task, vma->vm_file); + +out_no_vma: + up_read(&mm->mmap_sem); + mmput(mm); +out_unlock: + unlock_trace(task); +out_put_task: + put_task_struct(task); +out: + return result; +} + +static const struct inode_operations proc_map_files_inode_operations = { + .lookup = proc_map_files_lookup, + .permission = proc_fd_permission, + .setattr = proc_setattr, +}; + +static int +proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) +{ + struct dentry *dentry = filp->f_path.dentry; + struct inode *inode = dentry->d_inode; + struct vm_area_struct *vma; + struct task_struct *task; + struct mm_struct *mm; + ino_t ino; + int ret; + + ret = -EACCES; + if (!capable(CAP_SYS_ADMIN)) + goto out; + + ret = -ENOENT; + task = get_proc_task(inode); + if (!task) + goto out; + + ret = -EACCES; + if (lock_trace(task)) + goto out_put_task; + + ret = 0; + switch (filp->f_pos) { + case 0: + ino = inode->i_ino; + if (filldir(dirent, ".", 1, 0, ino, DT_DIR) < 0) + goto out_unlock; + filp->f_pos++; + case 1: + ino = parent_ino(dentry); + if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0) + goto out_unlock; + filp->f_pos++; + default: + { + unsigned long nr_files, pos, i; + struct flex_array *fa = NULL; + struct map_files_info info; + struct map_files_info *p; + + mm = get_task_mm(task); + if (!mm) + goto out_unlock; + down_read(&mm->mmap_sem); + + nr_files = 0; + + /* + * We need two passes here: + * + * 1) Collect vmas of mapped files with mmap_sem taken + * 2) Release mmap_sem and instantiate entries + * + * otherwise we get lockdep complained, since filldir() + * routine might require mmap_sem taken in might_fault(). + */ + + for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) { + if (vma->vm_file && ++pos > filp->f_pos) + nr_files++; + } + + if (nr_files) { + fa = flex_array_alloc(sizeof(info), nr_files, + GFP_KERNEL); + if (!fa || flex_array_prealloc(fa, 0, nr_files, + GFP_KERNEL)) { + ret = -ENOMEM; + if (fa) + flex_array_free(fa); + up_read(&mm->mmap_sem); + mmput(mm); + goto out_unlock; + } + for (i = 0, vma = mm->mmap, pos = 2; vma; + vma = vma->vm_next) { + if (!vma->vm_file) + continue; + if (++pos <= filp->f_pos) + continue; + + get_file(vma->vm_file); + info.file = vma->vm_file; + info.len = snprintf(info.name, + sizeof(info.name), "%lx-%lx", + vma->vm_start, vma->vm_end); + if (flex_array_put(fa, i++, &info, GFP_KERNEL)) + BUG(); + } + } + up_read(&mm->mmap_sem); + + for (i = 0; i < nr_files; i++) { + p = flex_array_get(fa, i); + ret = proc_fill_cache(filp, dirent, filldir, + p->name, p->len, + proc_map_files_instantiate, + task, p->file); + if (ret) + break; + filp->f_pos++; + fput(p->file); + } + for (; i < nr_files; i++) { + /* + * In case of error don't forget + * to put rest of file refs. + */ + p = flex_array_get(fa, i); + fput(p->file); + } + if (fa) + flex_array_free(fa); + mmput(mm); + } + } + +out_unlock: + unlock_trace(task); +out_put_task: + put_task_struct(task); +out: + return ret; +} + +static const struct file_operations proc_map_files_operations = { + .read = generic_read_dir, + .readdir = proc_map_files_readdir, + .llseek = default_llseek, +}; + +#endif /* CONFIG_CHECKPOINT_RESTORE */ + /* * /proc/pid/fd needs a special permission handler so that a process can still * access /proc/self/fd after it has executed a setuid(). @@ -2261,7 +2544,7 @@ static struct dentry *proc_pident_instantiate(struct inode *dir, ei = PROC_I(inode); inode->i_mode = p->mode; if (S_ISDIR(inode->i_mode)) - inode->i_nlink = 2; /* Use getattr to fix if necessary */ + set_nlink(inode, 2); /* Use getattr to fix if necessary */ if (p->iop) inode->i_op = p->iop; if (p->fop) @@ -2655,7 +2938,7 @@ static struct dentry *proc_base_instantiate(struct inode *dir, inode->i_mode = p->mode; if (S_ISDIR(inode->i_mode)) - inode->i_nlink = 2; + set_nlink(inode, 2); if (S_ISLNK(inode->i_mode)) inode->i_size = 64; if (p->iop) @@ -2785,6 +3068,9 @@ static const struct inode_operations proc_task_inode_operations; static const struct pid_entry tgid_base_stuff[] = { DIR("task", S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations), DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), +#ifdef CONFIG_CHECKPOINT_RESTORE + DIR("map_files", S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations), +#endif DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET @@ -2888,6 +3174,7 @@ static const struct inode_operations proc_tgid_base_inode_operations = { .lookup = proc_tgid_base_lookup, .getattr = pid_getattr, .setattr = proc_setattr, + .permission = proc_pid_permission, }; static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) @@ -2994,8 +3281,8 @@ static struct dentry *proc_pid_instantiate(struct inode *dir, inode->i_fop = &proc_tgid_base_operations; inode->i_flags|=S_IMMUTABLE; - inode->i_nlink = 2 + pid_entry_count_dirs(tgid_base_stuff, - ARRAY_SIZE(tgid_base_stuff)); + set_nlink(inode, 2 + pid_entry_count_dirs(tgid_base_stuff, + ARRAY_SIZE(tgid_base_stuff))); d_set_d_op(dentry, &pid_dentry_operations); @@ -3091,6 +3378,12 @@ static int proc_pid_fill_cache(struct file *filp, void *dirent, filldir_t filldi proc_pid_instantiate, iter.task, NULL); } +static int fake_filldir(void *buf, const char *name, int namelen, + loff_t offset, u64 ino, unsigned d_type) +{ + return 0; +} + /* for the /proc/ directory itself, after non-process stuff has been done */ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) { @@ -3098,6 +3391,7 @@ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) struct task_struct *reaper; struct tgid_iter iter; struct pid_namespace *ns; + filldir_t __filldir; if (filp->f_pos >= PID_MAX_LIMIT + TGID_OFFSET) goto out_no_task; @@ -3119,8 +3413,13 @@ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) for (iter = next_tgid(ns, iter); iter.task; iter.tgid += 1, iter = next_tgid(ns, iter)) { + if (has_pid_permissions(ns, iter.task, 2)) + __filldir = filldir; + else + __filldir = fake_filldir; + filp->f_pos = iter.tgid + TGID_OFFSET; - if (proc_pid_fill_cache(filp, dirent, filldir, iter) < 0) { + if (proc_pid_fill_cache(filp, dirent, __filldir, iter) < 0) { put_task_struct(iter.task); goto out; } @@ -3246,8 +3545,8 @@ static struct dentry *proc_task_instantiate(struct inode *dir, inode->i_fop = &proc_tid_base_operations; inode->i_flags|=S_IMMUTABLE; - inode->i_nlink = 2 + pid_entry_count_dirs(tid_base_stuff, - ARRAY_SIZE(tid_base_stuff)); + set_nlink(inode, 2 + pid_entry_count_dirs(tid_base_stuff, + ARRAY_SIZE(tid_base_stuff))); d_set_d_op(dentry, &pid_dentry_operations); @@ -3455,6 +3754,7 @@ static const struct inode_operations proc_task_inode_operations = { .lookup = proc_task_lookup, .getattr = proc_task_getattr, .setattr = proc_setattr, + .permission = proc_pid_permission, }; static const struct file_operations proc_task_operations = { diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 9d99131..2edf34f 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -283,7 +283,7 @@ static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry, struct inode *inode = dentry->d_inode; struct proc_dir_entry *de = PROC_I(inode)->pde; if (de && de->nlink) - inode->i_nlink = de->nlink; + set_nlink(inode, de->nlink); generic_fillattr(inode, stat); return 0; @@ -597,7 +597,7 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, const char *name, - mode_t mode, + umode_t mode, nlink_t nlink) { struct proc_dir_entry *ent = NULL; @@ -659,7 +659,7 @@ struct proc_dir_entry *proc_symlink(const char *name, } EXPORT_SYMBOL(proc_symlink); -struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode, +struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent) { struct proc_dir_entry *ent; @@ -699,7 +699,7 @@ struct proc_dir_entry *proc_mkdir(const char *name, } EXPORT_SYMBOL(proc_mkdir); -struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode, +struct proc_dir_entry *create_proc_entry(const char *name, umode_t mode, struct proc_dir_entry *parent) { struct proc_dir_entry *ent; @@ -728,7 +728,7 @@ struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode, } EXPORT_SYMBOL(create_proc_entry); -struct proc_dir_entry *proc_create_data(const char *name, mode_t mode, +struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct file_operations *proc_fops, void *data) diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 7ed72d6..84fd323 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -7,6 +7,7 @@ #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/kernel.h> +#include <linux/pid_namespace.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/stat.h> @@ -17,7 +18,9 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/sysctl.h> +#include <linux/seq_file.h> #include <linux/slab.h> +#include <linux/mount.h> #include <asm/system.h> #include <asm/uaccess.h> @@ -77,7 +80,6 @@ static struct inode *proc_alloc_inode(struct super_block *sb) static void proc_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - INIT_LIST_HEAD(&inode->i_dentry); kmem_cache_free(proc_inode_cachep, PROC_I(inode)); } @@ -102,12 +104,27 @@ void __init proc_init_inodecache(void) init_once); } +static int proc_show_options(struct seq_file *seq, struct dentry *root) +{ + struct super_block *sb = root->d_sb; + struct pid_namespace *pid = sb->s_fs_info; + + if (pid->pid_gid) + seq_printf(seq, ",gid=%lu", (unsigned long)pid->pid_gid); + if (pid->hide_pid != 0) + seq_printf(seq, ",hidepid=%u", pid->hide_pid); + + return 0; +} + static const struct super_operations proc_sops = { .alloc_inode = proc_alloc_inode, .destroy_inode = proc_destroy_inode, .drop_inode = generic_delete_inode, .evict_inode = proc_evict_inode, .statfs = simple_statfs, + .remount_fs = proc_remount, + .show_options = proc_show_options, }; static void __pde_users_dec(struct proc_dir_entry *pde) @@ -445,7 +462,7 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) if (de->size) inode->i_size = de->size; if (de->nlink) - inode->i_nlink = de->nlink; + set_nlink(inode, de->nlink); if (de->proc_iops) inode->i_op = de->proc_iops; if (de->proc_fops) { diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 7838e5c..2925775 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -117,6 +117,7 @@ void pde_put(struct proc_dir_entry *pde); int proc_fill_super(struct super_block *); struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *); +int proc_remount(struct super_block *sb, int *flags, char *data); /* * These are generic /proc routines that use the internal diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 5861741..80e4645 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -131,12 +131,13 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(i.freeswap), K(global_page_state(NR_FILE_DIRTY)), K(global_page_state(NR_WRITEBACK)), - K(global_page_state(NR_ANON_PAGES) #ifdef CONFIG_TRANSPARENT_HUGEPAGE + K(global_page_state(NR_ANON_PAGES) + global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) * - HPAGE_PMD_NR + HPAGE_PMD_NR), +#else + K(global_page_state(NR_ANON_PAGES)), #endif - ), K(global_page_state(NR_FILE_MAPPED)), K(global_page_state(NR_SHMEM)), K(global_page_state(NR_SLAB_RECLAIMABLE) + diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index be177f7..27da860 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -9,7 +9,6 @@ #include <linux/file.h> #include <linux/utsname.h> #include <net/net_namespace.h> -#include <linux/mnt_namespace.h> #include <linux/ipc_namespace.h> #include <linux/pid_namespace.h> #include "internal.h" diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index f738024..06e1cc1 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -179,7 +179,7 @@ const struct file_operations proc_net_operations = { struct proc_dir_entry *proc_net_fops_create(struct net *net, - const char *name, mode_t mode, const struct file_operations *fops) + const char *name, umode_t mode, const struct file_operations *fops) { return proc_create(name, mode, net->proc_net, fops); } diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 1a77dbe..a6b6217 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -3,6 +3,7 @@ */ #include <linux/init.h> #include <linux/sysctl.h> +#include <linux/poll.h> #include <linux/proc_fs.h> #include <linux/security.h> #include <linux/namei.h> @@ -14,6 +15,15 @@ static const struct inode_operations proc_sys_inode_operations; static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; +void proc_sys_poll_notify(struct ctl_table_poll *poll) +{ + if (!poll) + return; + + atomic_inc(&poll->event); + wake_up_interruptible(&poll->wait); +} + static struct inode *proc_sys_make_inode(struct super_block *sb, struct ctl_table_header *head, struct ctl_table *table) { @@ -39,7 +49,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, inode->i_fop = &proc_sys_file_operations; } else { inode->i_mode |= S_IFDIR; - inode->i_nlink = 0; + clear_nlink(inode); inode->i_op = &proc_sys_dir_operations; inode->i_fop = &proc_sys_dir_file_operations; } @@ -176,6 +186,39 @@ static ssize_t proc_sys_write(struct file *filp, const char __user *buf, return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1); } +static int proc_sys_open(struct inode *inode, struct file *filp) +{ + struct ctl_table *table = PROC_I(inode)->sysctl_entry; + + if (table->poll) + filp->private_data = proc_sys_poll_event(table->poll); + + return 0; +} + +static unsigned int proc_sys_poll(struct file *filp, poll_table *wait) +{ + struct inode *inode = filp->f_path.dentry->d_inode; + struct ctl_table *table = PROC_I(inode)->sysctl_entry; + unsigned long event = (unsigned long)filp->private_data; + unsigned int ret = DEFAULT_POLLMASK; + + if (!table->proc_handler) + goto out; + + if (!table->poll) + goto out; + + poll_wait(filp, &table->poll->wait, wait); + + if (event != atomic_read(&table->poll->event)) { + filp->private_data = proc_sys_poll_event(table->poll); + ret = POLLIN | POLLRDNORM | POLLERR | POLLPRI; + } + +out: + return ret; +} static int proc_sys_fill_cache(struct file *filp, void *dirent, filldir_t filldir, @@ -364,12 +407,15 @@ static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct } static const struct file_operations proc_sys_file_operations = { + .open = proc_sys_open, + .poll = proc_sys_poll, .read = proc_sys_read, .write = proc_sys_write, .llseek = default_llseek, }; static const struct file_operations proc_sys_dir_file_operations = { + .read = generic_read_dir, .readdir = proc_sys_readdir, .llseek = generic_file_llseek, }; diff --git a/fs/proc/root.c b/fs/proc/root.c index 9a8a2b7..46a15d8 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -18,6 +18,7 @@ #include <linux/bitops.h> #include <linux/mount.h> #include <linux/pid_namespace.h> +#include <linux/parser.h> #include "internal.h" @@ -36,6 +37,63 @@ static int proc_set_super(struct super_block *sb, void *data) return err; } +enum { + Opt_gid, Opt_hidepid, Opt_err, +}; + +static const match_table_t tokens = { + {Opt_hidepid, "hidepid=%u"}, + {Opt_gid, "gid=%u"}, + {Opt_err, NULL}, +}; + +static int proc_parse_options(char *options, struct pid_namespace *pid) +{ + char *p; + substring_t args[MAX_OPT_ARGS]; + int option; + + if (!options) + return 1; + + while ((p = strsep(&options, ",")) != NULL) { + int token; + if (!*p) + continue; + + args[0].to = args[0].from = 0; + token = match_token(p, tokens, args); + switch (token) { + case Opt_gid: + if (match_int(&args[0], &option)) + return 0; + pid->pid_gid = option; + break; + case Opt_hidepid: + if (match_int(&args[0], &option)) + return 0; + if (option < 0 || option > 2) { + pr_err("proc: hidepid value must be between 0 and 2.\n"); + return 0; + } + pid->hide_pid = option; + break; + default: + pr_err("proc: unrecognized mount option \"%s\" " + "or missing value\n", p); + return 0; + } + } + + return 1; +} + +int proc_remount(struct super_block *sb, int *flags, char *data) +{ + struct pid_namespace *pid = sb->s_fs_info; + return !proc_parse_options(data, pid); +} + static struct dentry *proc_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { @@ -43,11 +101,15 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, struct super_block *sb; struct pid_namespace *ns; struct proc_inode *ei; + char *options; - if (flags & MS_KERNMOUNT) + if (flags & MS_KERNMOUNT) { ns = (struct pid_namespace *)data; - else + options = NULL; + } else { ns = current->nsproxy->pid_ns; + options = data; + } sb = sget(fs_type, proc_test_super, proc_set_super, ns); if (IS_ERR(sb)) @@ -55,6 +117,10 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, if (!sb->s_root) { sb->s_flags = flags; + if (!proc_parse_options(options, ns)) { + deactivate_locked_super(sb); + return ERR_PTR(-EINVAL); + } err = proc_fill_super(sb); if (err) { deactivate_locked_super(sb); @@ -91,20 +157,18 @@ static struct file_system_type proc_fs_type = { void __init proc_root_init(void) { - struct vfsmount *mnt; int err; proc_init_inodecache(); err = register_filesystem(&proc_fs_type); if (err) return; - mnt = kern_mount_data(&proc_fs_type, &init_pid_ns); - if (IS_ERR(mnt)) { + err = pid_ns_prepare_proc(&init_pid_ns); + if (err) { unregister_filesystem(&proc_fs_type); return; } - init_pid_ns.proc_mnt = mnt; proc_symlink("mounts", NULL, "self/mounts"); proc_net_init(); @@ -209,5 +273,5 @@ int pid_ns_prepare_proc(struct pid_namespace *ns) void pid_ns_release_proc(struct pid_namespace *ns) { - mntput(ns->proc_mnt); + kern_unmount(ns->proc_mnt); } diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 9758b65..d76ca6a 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -10,6 +10,7 @@ #include <linux/time.h> #include <linux/irqnr.h> #include <asm/cputime.h> +#include <linux/tick.h> #ifndef arch_irq_stat_cpu #define arch_irq_stat_cpu(cpu) 0 @@ -21,38 +22,61 @@ #define arch_idle_time(cpu) 0 #endif +static u64 get_idle_time(int cpu) +{ + u64 idle, idle_time = get_cpu_idle_time_us(cpu, NULL); + + if (idle_time == -1ULL) { + /* !NO_HZ so we can rely on cpustat.idle */ + idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; + idle += arch_idle_time(cpu); + } else + idle = usecs_to_cputime64(idle_time); + + return idle; +} + +static u64 get_iowait_time(int cpu) +{ + u64 iowait, iowait_time = get_cpu_iowait_time_us(cpu, NULL); + + if (iowait_time == -1ULL) + /* !NO_HZ so we can rely on cpustat.iowait */ + iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; + else + iowait = usecs_to_cputime64(iowait_time); + + return iowait; +} + static int show_stat(struct seq_file *p, void *v) { int i, j; unsigned long jif; - cputime64_t user, nice, system, idle, iowait, irq, softirq, steal; - cputime64_t guest, guest_nice; + u64 user, nice, system, idle, iowait, irq, softirq, steal; + u64 guest, guest_nice; u64 sum = 0; u64 sum_softirq = 0; unsigned int per_softirq_sums[NR_SOFTIRQS] = {0}; struct timespec boottime; user = nice = system = idle = iowait = - irq = softirq = steal = cputime64_zero; - guest = guest_nice = cputime64_zero; + irq = softirq = steal = 0; + guest = guest_nice = 0; getboottime(&boottime); jif = boottime.tv_sec; for_each_possible_cpu(i) { - user = cputime64_add(user, kstat_cpu(i).cpustat.user); - nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice); - system = cputime64_add(system, kstat_cpu(i).cpustat.system); - idle = cputime64_add(idle, kstat_cpu(i).cpustat.idle); - idle = cputime64_add(idle, arch_idle_time(i)); - iowait = cputime64_add(iowait, kstat_cpu(i).cpustat.iowait); - irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq); - softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq); - steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal); - guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest); - guest_nice = cputime64_add(guest_nice, - kstat_cpu(i).cpustat.guest_nice); - sum += kstat_cpu_irqs_sum(i); - sum += arch_irq_stat_cpu(i); + user += kcpustat_cpu(i).cpustat[CPUTIME_USER]; + nice += kcpustat_cpu(i).cpustat[CPUTIME_NICE]; + system += kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]; + idle += get_idle_time(i); + iowait += get_iowait_time(i); + irq += kcpustat_cpu(i).cpustat[CPUTIME_IRQ]; + softirq += kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]; + steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL]; + guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; + guest_nice += kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; for (j = 0; j < NR_SOFTIRQS; j++) { unsigned int softirq_stat = kstat_softirqs_cpu(j, i); @@ -76,19 +100,17 @@ static int show_stat(struct seq_file *p, void *v) (unsigned long long)cputime64_to_clock_t(guest), (unsigned long long)cputime64_to_clock_t(guest_nice)); for_each_online_cpu(i) { - /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ - user = kstat_cpu(i).cpustat.user; - nice = kstat_cpu(i).cpustat.nice; - system = kstat_cpu(i).cpustat.system; - idle = kstat_cpu(i).cpustat.idle; - idle = cputime64_add(idle, arch_idle_time(i)); - iowait = kstat_cpu(i).cpustat.iowait; - irq = kstat_cpu(i).cpustat.irq; - softirq = kstat_cpu(i).cpustat.softirq; - steal = kstat_cpu(i).cpustat.steal; - guest = kstat_cpu(i).cpustat.guest; - guest_nice = kstat_cpu(i).cpustat.guest_nice; + user = kcpustat_cpu(i).cpustat[CPUTIME_USER]; + nice = kcpustat_cpu(i).cpustat[CPUTIME_NICE]; + system = kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]; + idle = get_idle_time(i); + iowait = get_iowait_time(i); + irq = kcpustat_cpu(i).cpustat[CPUTIME_IRQ]; + softirq = kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]; + steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL]; + guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; + guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; seq_printf(p, "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu " "%llu\n", diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5afaa58..e418c5a 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -44,6 +44,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) "VmPeak:\t%8lu kB\n" "VmSize:\t%8lu kB\n" "VmLck:\t%8lu kB\n" + "VmPin:\t%8lu kB\n" "VmHWM:\t%8lu kB\n" "VmRSS:\t%8lu kB\n" "VmData:\t%8lu kB\n" @@ -55,6 +56,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) hiwater_vm << (PAGE_SHIFT-10), (total_vm - mm->reserved_vm) << (PAGE_SHIFT-10), mm->locked_vm << (PAGE_SHIFT-10), + mm->pinned_vm << (PAGE_SHIFT-10), hiwater_rss << (PAGE_SHIFT-10), total_rss << (PAGE_SHIFT-10), data << (PAGE_SHIFT-10), @@ -1039,6 +1041,9 @@ static int show_numa_map(struct seq_file *m, void *v) seq_printf(m, " stack"); } + if (is_vm_hugetlb_page(vma)) + seq_printf(m, " huge"); + walk_page_range(vma->vm_start, vma->vm_end, &walk); if (!md->pages) diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c index 766b1d4..9610ac7 100644 --- a/fs/proc/uptime.c +++ b/fs/proc/uptime.c @@ -11,15 +11,20 @@ static int uptime_proc_show(struct seq_file *m, void *v) { struct timespec uptime; struct timespec idle; + u64 idletime; + u64 nsec; + u32 rem; int i; - cputime_t idletime = cputime_zero; + idletime = 0; for_each_possible_cpu(i) - idletime = cputime64_add(idletime, kstat_cpu(i).cpustat.idle); + idletime += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE]; do_posix_clock_monotonic_gettime(&uptime); monotonic_to_bootbased(&uptime); - cputime_to_timespec(idletime, &idle); + nsec = cputime64_to_jiffies64(idletime) * TICK_NSEC; + idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); + idle.tv_nsec = rem; seq_printf(m, "%lu.%02lu %lu.%02lu\n", (unsigned long) uptime.tv_sec, (uptime.tv_nsec / (NSEC_PER_SEC / 100)), diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index cd99bf5..b0f450a 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -12,6 +12,7 @@ #include <linux/user.h> #include <linux/elf.h> #include <linux/elfcore.h> +#include <linux/export.h> #include <linux/slab.h> #include <linux/highmem.h> #include <linux/bootmem.h> |