X-Git-Url: http://git.onelab.eu/?p=linux-2.6.git;a=blobdiff_plain;f=fs%2Fproc%2Fbase.c;fp=fs%2Fproc%2Fbase.c;h=3e37b5f77a87e2f488af8a332866699782fd22d0;hp=7bd6c8d653d616299009740b2190a17842a5f456;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hpb=76828883507a47dae78837ab5dec5a5b4513c667 diff --git a/fs/proc/base.c b/fs/proc/base.c index 7bd6c8d65..3e37b5f77 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -49,7 +49,6 @@ #include -#include #include #include #include @@ -60,7 +59,7 @@ #include #include #include -#include +#include #include #include #include @@ -68,276 +67,145 @@ #include #include #include +#include #include #include #include #include -#include +#include +#include +#include #include + #include "internal.h" -/* - * For hysterical raisins we keep the same inumbers as in the old procfs. - * Feel free to change the macro below - just keep the range distinct from - * inumbers of the rest of procfs (currently those are in 0x0000--0xffff). - * As soon as we'll get a separate superblock we will be able to forget - * about magical ranges too. +/* NOTE: + * Implementing inode permission operations in /proc is almost + * certainly an error. Permission checks need to happen during + * each system call not at open time. The reason is that most of + * what we wish to check for permissions in /proc varies at runtime. + * + * The classic example of a problem is opening file descriptors + * in /proc for a task before it execs a suid executable. */ -#define fake_ino(pid,ino) (((pid)<<16)|(ino)) - -enum pid_directory_inos { - PROC_TGID_INO = 2, - PROC_TGID_TASK, - PROC_TGID_STATUS, - PROC_TGID_MEM, -#ifdef CONFIG_SECCOMP - PROC_TGID_SECCOMP, -#endif - PROC_TGID_CWD, - PROC_TGID_ROOT, - PROC_TGID_EXE, - PROC_TGID_FD, - PROC_TGID_ENVIRON, - PROC_TGID_AUXV, - PROC_TGID_CMDLINE, - PROC_TGID_STAT, - PROC_TGID_STATM, - PROC_TGID_MAPS, - PROC_TGID_NUMA_MAPS, - PROC_TGID_MOUNTS, - PROC_TGID_WCHAN, -#ifdef CONFIG_MMU - PROC_TGID_SMAPS, -#endif -#ifdef CONFIG_SCHEDSTATS - PROC_TGID_SCHEDSTAT, -#endif -#ifdef CONFIG_CPUSETS - PROC_TGID_CPUSET, -#endif -#ifdef CONFIG_SECURITY - PROC_TGID_ATTR, - PROC_TGID_ATTR_CURRENT, - PROC_TGID_ATTR_PREV, - PROC_TGID_ATTR_EXEC, - PROC_TGID_ATTR_FSCREATE, -#endif - PROC_TGID_VX_INFO, - PROC_TGID_IP_INFO, -#ifdef CONFIG_AUDITSYSCALL - PROC_TGID_LOGINUID, -#endif - PROC_TGID_OOM_SCORE, - PROC_TGID_OOM_ADJUST, - PROC_TID_INO, - PROC_TID_STATUS, - PROC_TID_MEM, -#ifdef CONFIG_SECCOMP - PROC_TID_SECCOMP, -#endif - PROC_TID_CWD, - PROC_TID_ROOT, - PROC_TID_EXE, - PROC_TID_FD, - PROC_TID_ENVIRON, - PROC_TID_AUXV, - PROC_TID_CMDLINE, - PROC_TID_STAT, - PROC_TID_STATM, - PROC_TID_MAPS, - PROC_TID_NUMA_MAPS, - PROC_TID_MOUNTS, - PROC_TID_WCHAN, -#ifdef CONFIG_MMU - PROC_TID_SMAPS, -#endif -#ifdef CONFIG_SCHEDSTATS - PROC_TID_SCHEDSTAT, -#endif -#ifdef CONFIG_CPUSETS - PROC_TID_CPUSET, -#endif -#ifdef CONFIG_SECURITY - PROC_TID_ATTR, - PROC_TID_ATTR_CURRENT, - PROC_TID_ATTR_PREV, - PROC_TID_ATTR_EXEC, - PROC_TID_ATTR_FSCREATE, -#endif - PROC_TID_VX_INFO, - PROC_TID_IP_INFO, -#ifdef CONFIG_AUDITSYSCALL - PROC_TID_LOGINUID, -#endif - PROC_TID_OOM_SCORE, - PROC_TID_OOM_ADJUST, - /* Add new entries before this */ - PROC_TID_FD_DIR = 0x8000, /* 0x8000-0xffff */ -}; +/* Worst case buffer size needed for holding an integer. */ +#define PROC_NUMBUF 13 struct pid_entry { - int type; int len; char *name; mode_t mode; + struct inode_operations *iop; + struct file_operations *fop; + union proc_op op; }; -#define E(type,name,mode) {(type),sizeof(name)-1,(name),(mode)} +#define NOD(NAME, MODE, IOP, FOP, OP) { \ + .len = sizeof(NAME) - 1, \ + .name = (NAME), \ + .mode = MODE, \ + .iop = IOP, \ + .fop = FOP, \ + .op = OP, \ +} + +#define DIR(NAME, MODE, OTYPE) \ + NOD(NAME, (S_IFDIR|(MODE)), \ + &proc_##OTYPE##_inode_operations, &proc_##OTYPE##_operations, \ + {} ) +#define LNK(NAME, OTYPE) \ + NOD(NAME, (S_IFLNK|S_IRWXUGO), \ + &proc_pid_link_inode_operations, NULL, \ + { .proc_get_link = &proc_##OTYPE##_link } ) +#define REG(NAME, MODE, OTYPE) \ + NOD(NAME, (S_IFREG|(MODE)), NULL, \ + &proc_##OTYPE##_operations, {}) +#define INF(NAME, MODE, OTYPE) \ + NOD(NAME, (S_IFREG|(MODE)), \ + NULL, &proc_info_file_operations, \ + { .proc_read = &proc_##OTYPE } ) -static struct pid_entry tgid_base_stuff[] = { - E(PROC_TGID_TASK, "task", S_IFDIR|S_IRUGO|S_IXUGO), - E(PROC_TGID_FD, "fd", S_IFDIR|S_IRUSR|S_IXUSR), - E(PROC_TGID_ENVIRON, "environ", S_IFREG|S_IRUSR), - E(PROC_TGID_AUXV, "auxv", S_IFREG|S_IRUSR), - E(PROC_TGID_STATUS, "status", S_IFREG|S_IRUGO), - E(PROC_TGID_CMDLINE, "cmdline", S_IFREG|S_IRUGO), - E(PROC_TGID_STAT, "stat", S_IFREG|S_IRUGO), - E(PROC_TGID_STATM, "statm", S_IFREG|S_IRUGO), - E(PROC_TGID_MAPS, "maps", S_IFREG|S_IRUGO), -#ifdef CONFIG_NUMA - E(PROC_TGID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO), -#endif - E(PROC_TGID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR), -#ifdef CONFIG_SECCOMP - E(PROC_TGID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR), -#endif - E(PROC_TGID_CWD, "cwd", S_IFLNK|S_IRWXUGO), - E(PROC_TGID_ROOT, "root", S_IFLNK|S_IRWXUGO), - E(PROC_TGID_EXE, "exe", S_IFLNK|S_IRWXUGO), - E(PROC_TGID_MOUNTS, "mounts", S_IFREG|S_IRUGO), -#ifdef CONFIG_MMU - E(PROC_TGID_SMAPS, "smaps", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_SECURITY - E(PROC_TGID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), -#endif -#ifdef CONFIG_KALLSYMS - E(PROC_TGID_WCHAN, "wchan", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_SCHEDSTATS - E(PROC_TGID_SCHEDSTAT, "schedstat", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_CPUSETS - E(PROC_TGID_CPUSET, "cpuset", S_IFREG|S_IRUGO), -#endif - E(PROC_TGID_VX_INFO, "vinfo", S_IFREG|S_IRUGO), - E(PROC_TGID_IP_INFO, "ninfo", S_IFREG|S_IRUGO), - E(PROC_TGID_OOM_SCORE, "oom_score",S_IFREG|S_IRUGO), - E(PROC_TGID_OOM_ADJUST,"oom_adj", S_IFREG|S_IRUGO|S_IWUSR), -#ifdef CONFIG_AUDITSYSCALL - E(PROC_TGID_LOGINUID, "loginuid", S_IFREG|S_IWUSR|S_IRUGO), -#endif - {0,0,NULL,0} -}; -static struct pid_entry tid_base_stuff[] = { - E(PROC_TID_FD, "fd", S_IFDIR|S_IRUSR|S_IXUSR), - E(PROC_TID_ENVIRON, "environ", S_IFREG|S_IRUSR), - E(PROC_TID_AUXV, "auxv", S_IFREG|S_IRUSR), - E(PROC_TID_STATUS, "status", S_IFREG|S_IRUGO), - E(PROC_TID_CMDLINE, "cmdline", S_IFREG|S_IRUGO), - E(PROC_TID_STAT, "stat", S_IFREG|S_IRUGO), - E(PROC_TID_STATM, "statm", S_IFREG|S_IRUGO), - E(PROC_TID_MAPS, "maps", S_IFREG|S_IRUGO), -#ifdef CONFIG_NUMA - E(PROC_TID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO), -#endif - E(PROC_TID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR), -#ifdef CONFIG_SECCOMP - E(PROC_TID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR), -#endif - E(PROC_TID_CWD, "cwd", S_IFLNK|S_IRWXUGO), - E(PROC_TID_ROOT, "root", S_IFLNK|S_IRWXUGO), - E(PROC_TID_EXE, "exe", S_IFLNK|S_IRWXUGO), - E(PROC_TID_MOUNTS, "mounts", S_IFREG|S_IRUGO), -#ifdef CONFIG_MMU - E(PROC_TID_SMAPS, "smaps", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_SECURITY - E(PROC_TID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), -#endif -#ifdef CONFIG_KALLSYMS - E(PROC_TID_WCHAN, "wchan", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_SCHEDSTATS - E(PROC_TID_SCHEDSTAT, "schedstat",S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_CPUSETS - E(PROC_TID_CPUSET, "cpuset", S_IFREG|S_IRUGO), -#endif - E(PROC_TID_VX_INFO, "vinfo", S_IFREG|S_IRUGO), - E(PROC_TID_IP_INFO, "ninfo", S_IFREG|S_IRUGO), - E(PROC_TID_OOM_SCORE, "oom_score",S_IFREG|S_IRUGO), - E(PROC_TID_OOM_ADJUST, "oom_adj", S_IFREG|S_IRUGO|S_IWUSR), -#ifdef CONFIG_AUDITSYSCALL - E(PROC_TID_LOGINUID, "loginuid", S_IFREG|S_IWUSR|S_IRUGO), -#endif - {0,0,NULL,0} -}; +static struct fs_struct *get_fs_struct(struct task_struct *task) +{ + struct fs_struct *fs; + task_lock(task); + fs = task->fs; + if(fs) + atomic_inc(&fs->count); + task_unlock(task); + return fs; +} -#ifdef CONFIG_SECURITY -static struct pid_entry tgid_attr_stuff[] = { - E(PROC_TGID_ATTR_CURRENT, "current", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TGID_ATTR_PREV, "prev", S_IFREG|S_IRUGO), - E(PROC_TGID_ATTR_EXEC, "exec", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TGID_ATTR_FSCREATE, "fscreate", S_IFREG|S_IRUGO|S_IWUGO), - {0,0,NULL,0} -}; -static struct pid_entry tid_attr_stuff[] = { - E(PROC_TID_ATTR_CURRENT, "current", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TID_ATTR_PREV, "prev", S_IFREG|S_IRUGO), - E(PROC_TID_ATTR_EXEC, "exec", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TID_ATTR_FSCREATE, "fscreate", S_IFREG|S_IRUGO|S_IWUGO), - {0,0,NULL,0} -}; -#endif +static int get_nr_threads(struct task_struct *tsk) +{ + /* Must be called with the rcu_read_lock held */ + unsigned long flags; + int count = 0; -#undef E + if (lock_task_sighand(tsk, &flags)) { + count = atomic_read(&tsk->signal->count); + unlock_task_sighand(tsk, &flags); + } + return count; +} -static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +static int __ptrace_may_attach(struct task_struct *task) { - struct task_struct *task = proc_task(inode); - struct files_struct *files; - struct file *file; - int fd = proc_type(inode) - PROC_TID_FD_DIR; + /* May we inspect the given task? + * This check is used both for attaching with ptrace + * and for allowing access to sensitive information in /proc. + * + * ptrace_attach denies several cases that /proc allows + * because setting up the necessary parent/child relationship + * or halting the specified task is impossible. + */ + int dumpable = 0; + /* Don't let security modules deny introspection */ + if (task == current) + return 0; + if (((current->uid != task->euid) || + (current->uid != task->suid) || + (current->uid != task->uid) || + (current->gid != task->egid) || + (current->gid != task->sgid) || + (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE)) + return -EPERM; + smp_rmb(); + if (task->mm) + dumpable = task->mm->dumpable; + if (!dumpable && !capable(CAP_SYS_PTRACE)) + return -EPERM; + if (!vx_check(task->xid, VS_ADMIN_P|VS_IDENT)) + return -EPERM; + if (!vx_check(task->xid, VS_IDENT) && + !task_vx_flags(task, VXF_STATE_ADMIN, 0)) + return -EACCES; - files = get_files_struct(task); - if (files) { - /* - * We are not taking a ref to the file structure, so we must - * hold ->file_lock. - */ - spin_lock(&files->file_lock); - file = fcheck_files(files, fd); - if (file) { - *mnt = mntget(file->f_vfsmnt); - *dentry = dget(file->f_dentry); - spin_unlock(&files->file_lock); - put_files_struct(files); - return 0; - } - spin_unlock(&files->file_lock); - put_files_struct(files); - } - return -ENOENT; + return security_ptrace(current, task); } -static struct fs_struct *get_fs_struct(struct task_struct *task) +int ptrace_may_attach(struct task_struct *task) { - struct fs_struct *fs; + int err; task_lock(task); - fs = task->fs; - if(fs) - atomic_inc(&fs->count); + err = __ptrace_may_attach(task); task_unlock(task); - return fs; + return !err; } + static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) { - struct fs_struct *fs = get_fs_struct(proc_task(inode)); + struct task_struct *task = get_proc_task(inode); + struct fs_struct *fs = NULL; int result = -ENOENT; + + if (task) { + fs = get_fs_struct(task); + put_task_struct(task); + } if (fs) { read_lock(&fs->lock); *mnt = mntget(fs->pwdmnt); @@ -351,55 +219,14 @@ static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfs static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) { - struct fs_struct *fs = get_fs_struct(proc_task(inode)); - int result = -ENOENT; - if (fs) { - read_lock(&fs->lock); - *mnt = mntget(fs->rootmnt); - *dentry = dget(fs->root); - read_unlock(&fs->lock); - result = 0; - put_fs_struct(fs); - } - return result; -} - - -/* Same as proc_root_link, but this addionally tries to get fs from other - * threads in the group */ -static int proc_task_root_link(struct inode *inode, struct dentry **dentry, - struct vfsmount **mnt) -{ - struct fs_struct *fs; + struct task_struct *task = get_proc_task(inode); + struct fs_struct *fs = NULL; int result = -ENOENT; - struct task_struct *leader = proc_task(inode); - task_lock(leader); - fs = leader->fs; - if (fs) { - atomic_inc(&fs->count); - task_unlock(leader); - } else { - /* Try to get fs from other threads */ - task_unlock(leader); - read_lock(&tasklist_lock); - if (pid_alive(leader)) { - struct task_struct *task = leader; - - while ((task = next_thread(task)) != leader) { - task_lock(task); - fs = task->fs; - if (fs) { - atomic_inc(&fs->count); - task_unlock(task); - break; - } - task_unlock(task); - } - } - read_unlock(&tasklist_lock); + if (task) { + fs = get_fs_struct(task); + put_task_struct(task); } - if (fs) { read_lock(&fs->lock); *mnt = mntget(fs->rootmnt); @@ -411,13 +238,25 @@ static int proc_task_root_link(struct inode *inode, struct dentry **dentry, return result; } - -#define MAY_PTRACE(task) \ - (task == current || \ - (task->parent == current && \ - (task->ptrace & PT_PTRACED) && \ - (task->state == TASK_STOPPED || task->state == TASK_TRACED) && \ - security_ptrace(current,task) == 0)) +struct mm_struct *mm_for_maps(struct task_struct *task) +{ + struct mm_struct *mm = get_task_mm(task); + if (!mm) + return NULL; + down_read(&mm->mmap_sem); + task_lock(task); + if (task->mm != mm) + goto out; + if (task->mm != current->mm && __ptrace_may_attach(task) < 0) + goto out; + task_unlock(task); + return mm; +out: + task_unlock(task); + up_read(&mm->mmap_sem); + mmput(mm); + return NULL; +} static int proc_pid_environ(struct task_struct *task, char * buffer) { @@ -542,68 +381,20 @@ static int proc_oom_score(struct task_struct *task, char *buffer) /************************************************************************/ /* permission checks */ - -/* If the process being read is separated by chroot from the reading process, - * don't let the reader access the threads. - */ -static int proc_check_chroot(struct dentry *root, struct vfsmount *vfsmnt) +static int proc_fd_access_allowed(struct inode *inode) { - struct dentry *de, *base; - struct vfsmount *our_vfsmnt, *mnt; - int res = 0; - - /* context admin override */ - if (capable(CAP_CONTEXT)) - goto override; - - read_lock(¤t->fs->lock); - our_vfsmnt = mntget(current->fs->rootmnt); - base = dget(current->fs->root); - read_unlock(¤t->fs->lock); - - spin_lock(&vfsmount_lock); - de = root; - mnt = vfsmnt; - - while (mnt != our_vfsmnt) { - if (mnt == mnt->mnt_parent) - goto out; - de = mnt->mnt_mountpoint; - mnt = mnt->mnt_parent; + struct task_struct *task; + int allowed = 0; + /* Allow access to a task's file descriptors if it is us or we + * may use ptrace attach to the process and find out that + * information. + */ + task = get_proc_task(inode); + if (task) { + allowed = ptrace_may_attach(task); + put_task_struct(task); } - - if (!is_subdir(de, base)) - goto out; - spin_unlock(&vfsmount_lock); - -exit: - dput(base); - mntput(our_vfsmnt); -override: - dput(root); - mntput(vfsmnt); - return res; -out: - spin_unlock(&vfsmount_lock); - res = -EACCES; - goto exit; -} - -static int proc_check_root(struct inode *inode) -{ - struct dentry *root; - struct vfsmount *vfsmnt; - - if (proc_root_link(inode, &root, &vfsmnt)) /* Ewww... */ - return -ENOENT; - return proc_check_chroot(root, vfsmnt); -} - -static int proc_permission(struct inode *inode, int mask, struct nameidata *nd) -{ - if (generic_permission(inode, mask, NULL) != 0) - return -EACCES; - return proc_check_root(inode); + return allowed; } static int proc_setattr(struct dentry *dentry, struct iattr *attr) @@ -627,81 +418,6 @@ static struct inode_operations proc_def_inode_operations = { .setattr = proc_setattr, }; -static int proc_task_permission(struct inode *inode, int mask, struct nameidata *nd) -{ - struct dentry *root; - struct vfsmount *vfsmnt; - - if (generic_permission(inode, mask, NULL) != 0) - return -EACCES; - - if (proc_task_root_link(inode, &root, &vfsmnt)) - return -ENOENT; - - return proc_check_chroot(root, vfsmnt); -} - -extern struct seq_operations proc_pid_maps_op; -static int maps_open(struct inode *inode, struct file *file) -{ - struct task_struct *task = proc_task(inode); - int ret = seq_open(file, &proc_pid_maps_op); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = task; - } - return ret; -} - -static struct file_operations proc_maps_operations = { - .open = maps_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -#ifdef CONFIG_NUMA -extern struct seq_operations proc_pid_numa_maps_op; -static int numa_maps_open(struct inode *inode, struct file *file) -{ - struct task_struct *task = proc_task(inode); - int ret = seq_open(file, &proc_pid_numa_maps_op); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = task; - } - return ret; -} - -static struct file_operations proc_numa_maps_operations = { - .open = numa_maps_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; -#endif - -#ifdef CONFIG_MMU -extern struct seq_operations proc_pid_smaps_op; -static int smaps_open(struct inode *inode, struct file *file) -{ - struct task_struct *task = proc_task(inode); - int ret = seq_open(file, &proc_pid_smaps_op); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = task; - } - return ret; -} - -static struct file_operations proc_smaps_operations = { - .open = smaps_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; -#endif - extern struct seq_operations mounts_op; struct proc_mounts { struct seq_file m; @@ -710,31 +426,36 @@ struct proc_mounts { static int mounts_open(struct inode *inode, struct file *file) { - struct task_struct *task = proc_task(inode); - struct namespace *namespace; + struct task_struct *task = get_proc_task(inode); + struct mnt_namespace *ns = NULL; struct proc_mounts *p; int ret = -EINVAL; - task_lock(task); - namespace = task->namespace; - if (namespace) - get_namespace(namespace); - task_unlock(task); + if (task) { + task_lock(task); + if (task->nsproxy) { + ns = task->nsproxy->mnt_ns; + if (ns) + get_mnt_ns(ns); + } + task_unlock(task); + put_task_struct(task); + } - if (namespace) { + if (ns) { ret = -ENOMEM; p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL); if (p) { file->private_data = &p->m; ret = seq_open(file, &mounts_op); if (!ret) { - p->m.private = namespace; - p->event = namespace->event; + p->m.private = ns; + p->event = ns->event; return 0; } kfree(p); } - put_namespace(namespace); + put_mnt_ns(ns); } return ret; } @@ -742,15 +463,15 @@ static int mounts_open(struct inode *inode, struct file *file) static int mounts_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; - struct namespace *namespace = m->private; - put_namespace(namespace); + struct mnt_namespace *ns = m->private; + put_mnt_ns(ns); return seq_release(inode, file); } static unsigned mounts_poll(struct file *file, poll_table *wait) { struct proc_mounts *p = file->private_data; - struct namespace *ns = p->m.private; + struct mnt_namespace *ns = p->m.private; unsigned res = 0; poll_wait(file, &ns->poll, wait); @@ -773,26 +494,72 @@ static struct file_operations proc_mounts_operations = { .poll = mounts_poll, }; +extern struct seq_operations mountstats_op; +static int mountstats_open(struct inode *inode, struct file *file) +{ + int ret = seq_open(file, &mountstats_op); + + if (!ret) { + struct seq_file *m = file->private_data; + struct mnt_namespace *mnt_ns = NULL; + struct task_struct *task = get_proc_task(inode); + + if (task) { + task_lock(task); + if (task->nsproxy) + mnt_ns = task->nsproxy->mnt_ns; + if (mnt_ns) + get_mnt_ns(mnt_ns); + task_unlock(task); + put_task_struct(task); + } + + if (mnt_ns) + m->private = mnt_ns; + else { + seq_release(inode, file); + ret = -EINVAL; + } + } + return ret; +} + +static struct file_operations proc_mountstats_operations = { + .open = mountstats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mounts_release, +}; + #define PROC_BLOCK_SIZE (3*1024) /* 4K page size but our output routines use some slack for overruns */ static ssize_t proc_info_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { - struct inode * inode = file->f_dentry->d_inode; + struct inode * inode = file->f_path.dentry->d_inode; unsigned long page; ssize_t length; - struct task_struct *task = proc_task(inode); + struct task_struct *task = get_proc_task(inode); + + length = -ESRCH; + if (!task) + goto out_no_task; if (count > PROC_BLOCK_SIZE) count = PROC_BLOCK_SIZE; + + length = -ENOMEM; if (!(page = __get_free_page(GFP_KERNEL))) - return -ENOMEM; + goto out; length = PROC_I(inode)->op.proc_read(task, (char*)page); if (length >= 0) length = simple_read_from_buffer(buf, count, ppos, (char *)page, length); free_page(page); +out: + put_task_struct(task); +out_no_task: return length; } @@ -809,13 +576,17 @@ static int mem_open(struct inode* inode, struct file* file) static ssize_t mem_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { - struct task_struct *task = proc_task(file->f_dentry->d_inode); + struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode); char *page; unsigned long src = *ppos; int ret = -ESRCH; struct mm_struct *mm; - if (!MAY_PTRACE(task) || !ptrace_may_attach(task)) + if (!task) + goto out_no_task; + + if (!tracehook_allow_access_process_vm(task) + || !ptrace_may_attach(task)) goto out; ret = -ENOMEM; @@ -841,7 +612,8 @@ static ssize_t mem_read(struct file * file, char __user * buf, this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count; retval = access_process_vm(task, src, page, this_len, 0); - if (!retval || !MAY_PTRACE(task) || !ptrace_may_attach(task)) { + if (!retval || !tracehook_allow_access_process_vm(task) + || !ptrace_may_attach(task)) { if (!ret) ret = -EIO; break; @@ -864,6 +636,8 @@ out_put: out_free: free_page((unsigned long) page); out: + put_task_struct(task); +out_no_task: return ret; } @@ -874,18 +648,25 @@ out: static ssize_t mem_write(struct file * file, const char * buf, size_t count, loff_t *ppos) { - int copied = 0; + int copied; char *page; - struct task_struct *task = proc_task(file->f_dentry->d_inode); + struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode); unsigned long dst = *ppos; - if (!MAY_PTRACE(task) || !ptrace_may_attach(task)) - return -ESRCH; + copied = -ESRCH; + if (!task) + goto out_no_task; + + if (!tracehook_allow_access_process_vm(task) + || !ptrace_may_attach(task)) + goto out; + copied = -ENOMEM; page = (char *)__get_free_page(GFP_USER); if (!page) - return -ENOMEM; + goto out; + copied = 0; while (count > 0) { int this_len, retval; @@ -907,6 +688,9 @@ static ssize_t mem_write(struct file * file, const char * buf, } *ppos = dst; free_page((unsigned long) page); +out: + put_task_struct(task); +out_no_task: return copied; } #endif @@ -937,13 +721,18 @@ static struct file_operations proc_mem_operations = { static ssize_t oom_adjust_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct task_struct *task = proc_task(file->f_dentry->d_inode); - char buffer[8]; + struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode); + char buffer[PROC_NUMBUF]; size_t len; - int oom_adjust = task->oomkilladj; + int oom_adjust; loff_t __ppos = *ppos; - len = sprintf(buffer, "%i\n", oom_adjust); + if (!task) + return -ESRCH; + oom_adjust = task->oomkilladj; + put_task_struct(task); + + len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust); if (__ppos >= len) return 0; if (count > len-__ppos) @@ -957,23 +746,30 @@ static ssize_t oom_adjust_read(struct file *file, char __user *buf, static ssize_t oom_adjust_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct task_struct *task = proc_task(file->f_dentry->d_inode); - char buffer[8], *end; + struct task_struct *task; + char buffer[PROC_NUMBUF], *end; int oom_adjust; - if (!capable(CAP_SYS_RESOURCE)) - return -EPERM; - memset(buffer, 0, 8); - if (count > 6) - count = 6; + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; oom_adjust = simple_strtol(buffer, &end, 0); - if ((oom_adjust < -16 || oom_adjust > 15) && oom_adjust != OOM_DISABLE) + if ((oom_adjust < OOM_ADJUST_MIN || oom_adjust > OOM_ADJUST_MAX) && + oom_adjust != OOM_DISABLE) return -EINVAL; if (*end == '\n') end++; + task = get_proc_task(file->f_path.dentry->d_inode); + if (!task) + return -ESRCH; + if (oom_adjust < task->oomkilladj && !capable(CAP_SYS_RESOURCE)) { + put_task_struct(task); + return -EACCES; + } task->oomkilladj = oom_adjust; + put_task_struct(task); if (end - buffer == 0) return -EIO; return end - buffer; @@ -984,43 +780,40 @@ static struct file_operations proc_oom_adjust_operations = { .write = oom_adjust_write, }; -static struct inode_operations proc_mem_inode_operations = { - .permission = proc_permission, - .setattr = proc_setattr, -}; - #ifdef CONFIG_AUDITSYSCALL #define TMPBUFLEN 21 static ssize_t proc_loginuid_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { - struct inode * inode = file->f_dentry->d_inode; - struct task_struct *task = proc_task(inode); + struct inode * inode = file->f_path.dentry->d_inode; + struct task_struct *task = get_proc_task(inode); ssize_t length; char tmpbuf[TMPBUFLEN]; + if (!task) + return -ESRCH; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", audit_get_loginuid(task->audit_context)); + put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static ssize_t proc_loginuid_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { - struct inode * inode = file->f_dentry->d_inode; + struct inode * inode = file->f_path.dentry->d_inode; char *page, *tmp; ssize_t length; - struct task_struct *task = proc_task(inode); uid_t loginuid; if (!capable(CAP_AUDIT_CONTROL)) return -EPERM; - if (current != task) + if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) return -EPERM; - if (count > PAGE_SIZE) - count = PAGE_SIZE; + if (count >= PAGE_SIZE) + count = PAGE_SIZE - 1; if (*ppos != 0) { /* No partial writes. */ @@ -1033,13 +826,14 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf, if (copy_from_user(page, buf, count)) goto out_free_page; + page[count] = '\0'; loginuid = simple_strtoul(page, &tmp, 10); if (tmp == page) { length = -EINVAL; goto out_free_page; } - length = audit_set_loginuid(task, loginuid); + length = audit_set_loginuid(current, loginuid); if (likely(length == 0)) length = count; @@ -1058,13 +852,16 @@ static struct file_operations proc_loginuid_operations = { static ssize_t seccomp_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct task_struct *tsk = proc_task(file->f_dentry->d_inode); + struct task_struct *tsk = get_proc_task(file->f_dentry->d_inode); char __buf[20]; loff_t __ppos = *ppos; size_t len; + if (!tsk) + return -ESRCH; /* no need to print the trailing zero, so use only len */ len = sprintf(__buf, "%u\n", tsk->seccomp.mode); + put_task_struct(tsk); if (__ppos >= len) return 0; if (count > len - __ppos) @@ -1078,29 +875,43 @@ static ssize_t seccomp_read(struct file *file, char __user *buf, static ssize_t seccomp_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct task_struct *tsk = proc_task(file->f_dentry->d_inode); + struct task_struct *tsk = get_proc_task(file->f_dentry->d_inode); char __buf[20], *end; unsigned int seccomp_mode; + ssize_t result; + + result = -ESRCH; + if (!tsk) + goto out_no_task; /* can set it only once to be even more secure */ + result = -EPERM; if (unlikely(tsk->seccomp.mode)) - return -EPERM; + goto out; + result = -EFAULT; memset(__buf, 0, sizeof(__buf)); count = min(count, sizeof(__buf) - 1); if (copy_from_user(__buf, buf, count)) - return -EFAULT; + goto out; + seccomp_mode = simple_strtoul(__buf, &end, 0); if (*end == '\n') end++; + result = -EINVAL; if (seccomp_mode && seccomp_mode <= NR_SECCOMP_MODES) { tsk->seccomp.mode = seccomp_mode; set_tsk_thread_flag(tsk, TIF_SECCOMP); } else - return -EINVAL; + goto out; + result = -EIO; if (unlikely(!(end - __buf))) - return -EIO; - return end - __buf; + goto out; + result = end - __buf; +out: + put_task_struct(tsk); +out_no_task: + return result; } static struct file_operations proc_seccomp_operations = { @@ -1109,6 +920,65 @@ static struct file_operations proc_seccomp_operations = { }; #endif /* CONFIG_SECCOMP */ +#ifdef CONFIG_FAULT_INJECTION +static ssize_t proc_fault_inject_read(struct file * file, char __user * buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task = get_proc_task(file->f_dentry->d_inode); + char buffer[PROC_NUMBUF]; + size_t len; + int make_it_fail; + loff_t __ppos = *ppos; + + if (!task) + return -ESRCH; + make_it_fail = task->make_it_fail; + put_task_struct(task); + + len = snprintf(buffer, sizeof(buffer), "%i\n", make_it_fail); + if (__ppos >= len) + return 0; + if (count > len-__ppos) + count = len-__ppos; + if (copy_to_user(buf, buffer + __ppos, count)) + return -EFAULT; + *ppos = __ppos + count; + return count; +} + +static ssize_t proc_fault_inject_write(struct file * file, + const char __user * buf, size_t count, loff_t *ppos) +{ + struct task_struct *task; + char buffer[PROC_NUMBUF], *end; + int make_it_fail; + + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) + return -EFAULT; + make_it_fail = simple_strtol(buffer, &end, 0); + if (*end == '\n') + end++; + task = get_proc_task(file->f_dentry->d_inode); + if (!task) + return -ESRCH; + task->make_it_fail = make_it_fail; + put_task_struct(task); + if (end - buffer == 0) + return -EIO; + return end - buffer; +} + +static struct file_operations proc_fault_inject_operations = { + .read = proc_fault_inject_read, + .write = proc_fault_inject_write, +}; +#endif + static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; @@ -1117,10 +987,8 @@ static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) /* We don't need a base pointer in the /proc filesystem */ path_release(nd); - if (current->fsuid != inode->i_uid && !capable(CAP_DAC_OVERRIDE)) - goto out; - error = proc_check_root(inode); - if (error) + /* Are we allowed to snoop on the tasks file descriptors? */ + if (!proc_fd_access_allowed(inode)) goto out; error = PROC_I(inode)->op.proc_get_link(inode, &nd->dentry, &nd->mnt); @@ -1162,12 +1030,8 @@ static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int b struct dentry *de; struct vfsmount *mnt = NULL; - lock_kernel(); - - if (current->fsuid != inode->i_uid && !capable(CAP_DAC_OVERRIDE)) - goto out; - error = proc_check_root(inode); - if (error) + /* Are we allowed to snoop on the tasks file descriptors? */ + if (!proc_fd_access_allowed(inode)) goto out; error = PROC_I(inode)->op.proc_get_link(inode, &de, &mnt); @@ -1178,7 +1042,6 @@ static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int b dput(de); mntput(mnt); out: - unlock_kernel(); return error; } @@ -1188,149 +1051,6 @@ static struct inode_operations proc_pid_link_inode_operations = { .setattr = proc_setattr, }; -#define NUMBUF 10 - -static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir) -{ - struct inode *inode = filp->f_dentry->d_inode; - struct task_struct *p = proc_task(inode); - unsigned int fd, tid, ino; - int retval; - char buf[NUMBUF]; - struct files_struct * files; - struct fdtable *fdt; - - retval = -ENOENT; - if (!pid_alive(p)) - goto out; - retval = 0; - tid = p->pid; - - fd = filp->f_pos; - switch (fd) { - case 0: - if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0) - goto out; - filp->f_pos++; - case 1: - ino = fake_ino(tid, PROC_TID_INO); - if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0) - goto out; - filp->f_pos++; - default: - files = get_files_struct(p); - if (!files) - goto out; - rcu_read_lock(); - fdt = files_fdtable(files); - for (fd = filp->f_pos-2; - fd < fdt->max_fds; - fd++, filp->f_pos++) { - unsigned int i,j; - - if (!fcheck_files(files, fd)) - continue; - rcu_read_unlock(); - - j = NUMBUF; - i = fd; - do { - j--; - buf[j] = '0' + (i % 10); - i /= 10; - } while (i); - - ino = fake_ino(tid, PROC_TID_FD_DIR + fd); - if (filldir(dirent, buf+j, NUMBUF-j, fd+2, ino, DT_LNK) < 0) { - rcu_read_lock(); - break; - } - rcu_read_lock(); - } - rcu_read_unlock(); - put_files_struct(files); - } -out: - return retval; -} - -static int proc_pident_readdir(struct file *filp, - void *dirent, filldir_t filldir, - struct pid_entry *ents, unsigned int nents) -{ - int i; - int pid; - struct dentry *dentry = filp->f_dentry; - struct inode *inode = dentry->d_inode; - struct pid_entry *p; - ino_t ino; - int ret, hide; - - ret = -ENOENT; - if (!pid_alive(proc_task(inode))) - goto out; - - ret = 0; - pid = proc_task(inode)->pid; - i = filp->f_pos; - switch (i) { - case 0: - ino = inode->i_ino; - if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0) - goto out; - i++; - filp->f_pos++; - /* fall through */ - case 1: - ino = parent_ino(dentry); - if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0) - goto out; - i++; - filp->f_pos++; - /* fall through */ - default: - i -= 2; - if (i >= nents) { - ret = 1; - goto out; - } - p = ents + i; - hide = vx_flags(VXF_INFO_HIDE, 0); - while (p->name) { - if (hide) { - switch (p->type) { - case PROC_TGID_VX_INFO: - case PROC_TGID_IP_INFO: - goto skip; - } - } - if (filldir(dirent, p->name, p->len, filp->f_pos, - fake_ino(pid, p->type), p->mode >> 12) < 0) - goto out; - filp->f_pos++; - skip: - p++; - } - } - - ret = 1; -out: - return ret; -} - -static int proc_tgid_base_readdir(struct file * filp, - void * dirent, filldir_t filldir) -{ - return proc_pident_readdir(filp,dirent,filldir, - tgid_base_stuff,ARRAY_SIZE(tgid_base_stuff)); -} - -static int proc_tid_base_readdir(struct file * filp, - void * dirent, filldir_t filldir) -{ - return proc_pident_readdir(filp,dirent,filldir, - tid_base_stuff,ARRAY_SIZE(tid_base_stuff)); -} /* building an inode */ @@ -1350,51 +1070,68 @@ static int task_dumpable(struct task_struct *task) } -static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task, int ino) +static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task) { struct inode * inode; struct proc_inode *ei; /* We need a new inode */ - + inode = new_inode(sb); if (!inode) goto out; /* Common stuff */ ei = PROC_I(inode); - ei->task = NULL; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; - inode->i_ino = fake_ino(task->pid, ino); inode->i_op = &proc_def_inode_operations; - if (!pid_alive(task)) - goto out_unlock; - /* * grab the reference to task. */ - get_task_struct(task); - ei->task = task; - ei->type = ino; + ei->pid = get_task_pid(task, PIDTYPE_PID); + if (!ei->pid) + goto out_unlock; + inode->i_uid = 0; inode->i_gid = 0; - if (ino == PROC_TGID_INO || ino == PROC_TID_INO || task_dumpable(task)) { + if (task_dumpable(task)) { inode->i_uid = task->euid; inode->i_gid = task->egid; } - inode->i_xid = vx_task_xid(task); + /* procfs is xid tagged */ + inode->i_tag = (tag_t)vx_task_xid(task); security_task_to_inode(task, inode); out: return inode; out_unlock: - ei->pde = NULL; iput(inode); return NULL; } +static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +{ + struct inode *inode = dentry->d_inode; + struct task_struct *task; + generic_fillattr(inode, stat); + + rcu_read_lock(); + stat->uid = 0; + stat->gid = 0; + task = pid_task(proc_pid(inode), PIDTYPE_PID); + if (task) { + if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || + task_dumpable(task)) { + stat->uid = task->euid; + stat->gid = task->egid; + } + } + rcu_read_unlock(); + return 0; +} + /* dentry stuff */ /* @@ -1404,18 +1141,21 @@ out_unlock: * * Rewrite the inode's ownerships here because the owning task may have * performed a setuid(), etc. + * + * Before the /proc/pid/status file was created the only way to read + * the effective uid of a /process was to stat /proc/pid. Reading + * /proc/pid/status is slow enough that procps and other packages + * kept stating /proc/pid. To keep the rules in /proc simple I have + * made this apply to all per process world readable and executable + * directories. */ static int pid_revalidate(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; - struct task_struct *task = proc_task(inode); - - if (!vx_check(vx_task_xid(task), VX_IDENT)) - goto out_drop; - /* discard wrong fakeinit */ - - if (pid_alive(task)) { - if (proc_type(inode) == PROC_TGID_INO || proc_type(inode) == PROC_TID_INO || task_dumpable(task)) { + struct task_struct *task = get_proc_task(inode); + if (task) { + if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || + task_dumpable(task)) { inode->i_uid = task->euid; inode->i_gid = task->egid; } else { @@ -1424,94 +1164,96 @@ static int pid_revalidate(struct dentry *dentry, struct nameidata *nd) } inode->i_mode &= ~(S_ISUID | S_ISGID); security_task_to_inode(task, inode); + put_task_struct(task); return 1; } -out_drop: - d_drop(dentry); - return 0; -} - -static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) -{ - struct inode *inode = dentry->d_inode; - struct task_struct *task = proc_task(inode); - int fd = proc_type(inode) - PROC_TID_FD_DIR; - struct files_struct *files; - - files = get_files_struct(task); - if (files) { - rcu_read_lock(); - if (fcheck_files(files, fd)) { - rcu_read_unlock(); - put_files_struct(files); - if (task_dumpable(task)) { - inode->i_uid = task->euid; - inode->i_gid = task->egid; - } else { - inode->i_uid = 0; - inode->i_gid = 0; - } - inode->i_mode &= ~(S_ISUID | S_ISGID); - security_task_to_inode(task, inode); - return 1; - } - rcu_read_unlock(); - put_files_struct(files); - } d_drop(dentry); return 0; } -static void pid_base_iput(struct dentry *dentry, struct inode *inode) -{ - struct task_struct *task = proc_task(inode); - spin_lock(&task->proc_lock); - if (task->proc_dentry == dentry) - task->proc_dentry = NULL; - spin_unlock(&task->proc_lock); - iput(inode); -} - static int pid_delete_dentry(struct dentry * dentry) { /* Is the task we represent dead? * If so, then don't put the dentry on the lru list, * kill it immediately. */ - return !pid_alive(proc_task(dentry->d_inode)); + return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first; } -static struct dentry_operations tid_fd_dentry_operations = -{ - .d_revalidate = tid_fd_revalidate, - .d_delete = pid_delete_dentry, -}; - static struct dentry_operations pid_dentry_operations = { .d_revalidate = pid_revalidate, .d_delete = pid_delete_dentry, }; -static struct dentry_operations pid_base_dentry_operations = -{ - .d_revalidate = pid_revalidate, - .d_iput = pid_base_iput, - .d_delete = pid_delete_dentry, -}; - /* Lookups */ -static unsigned name_to_int(struct dentry *dentry) -{ - const char *name = dentry->d_name.name; - int len = dentry->d_name.len; - unsigned n = 0; +typedef struct dentry *instantiate_t(struct inode *, struct dentry *, struct task_struct *, void *); - if (len > 1 && *name == '0') - goto out; - while (len-- > 0) { - unsigned c = *name++ - '0'; +/* + * Fill a directory entry. + * + * If possible create the dcache entry and derive our inode number and + * file type from dcache entry. + * + * Since all of the proc inode numbers are dynamically generated, the inode + * numbers do not exist until the inode is cache. This means creating the + * the dcache entry in readdir is necessary to keep the inode numbers + * reported by readdir in sync with the inode numbers reported + * by stat. + */ +static int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir, + char *name, int len, + instantiate_t instantiate, struct task_struct *task, void *ptr) +{ + struct dentry *child, *dir = filp->f_path.dentry; + struct inode *inode; + struct qstr qname; + ino_t ino = 0; + unsigned type = DT_UNKNOWN; + + qname.name = name; + qname.len = len; + qname.hash = full_name_hash(name, len); + + child = d_lookup(dir, &qname); + if (!child) { + struct dentry *new; + new = d_alloc(dir, &qname); + if (new) { + child = instantiate(dir->d_inode, new, task, ptr); + if (child) + dput(new); + else + child = new; + } + } + if (!child || IS_ERR(child) || !child->d_inode) + goto end_instantiate; + inode = child->d_inode; + if (inode) { + ino = inode->i_ino; + type = inode->i_mode >> 12; + } + dput(child); +end_instantiate: + if (!ino) + ino = find_inode_number(dir, &qname); + if (!ino) + ino = 1; + return filldir(dirent, name, len, filp->f_pos, ino, type); +} + +static unsigned name_to_int(struct dentry *dentry) +{ + const char *name = dentry->d_name.name; + int len = dentry->d_name.len; + unsigned n = 0; + + if (len > 1 && *name == '0') + goto out; + while (len-- > 0) { + unsigned c = *name++ - '0'; if (c > 9) goto out; if (n >= (~0U-9)/10) @@ -1524,28 +1266,96 @@ out: return ~0U; } -/* SMP-safe */ -static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, struct nameidata *nd) +static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) { - struct task_struct *task = proc_task(dir); - unsigned fd = name_to_int(dentry); - struct file * file; - struct files_struct * files; - struct inode *inode; - struct proc_inode *ei; + struct task_struct *task = get_proc_task(inode); + struct files_struct *files = NULL; + struct file *file; + int fd = proc_fd(inode); - if (fd == ~0U) - goto out; - if (!pid_alive(task)) - goto out; + if (task) { + files = get_files_struct(task); + put_task_struct(task); + } + if (files) { + /* + * We are not taking a ref to the file structure, so we must + * hold ->file_lock. + */ + spin_lock(&files->file_lock); + file = fcheck_files(files, fd); + if (file) { + *mnt = mntget(file->f_path.mnt); + *dentry = dget(file->f_path.dentry); + spin_unlock(&files->file_lock); + put_files_struct(files); + return 0; + } + spin_unlock(&files->file_lock); + put_files_struct(files); + } + return -ENOENT; +} + +static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) +{ + struct inode *inode = dentry->d_inode; + struct task_struct *task = get_proc_task(inode); + int fd = proc_fd(inode); + struct files_struct *files; + + if (task) { + files = get_files_struct(task); + if (files) { + rcu_read_lock(); + if (fcheck_files(files, fd)) { + rcu_read_unlock(); + put_files_struct(files); + if (task_dumpable(task)) { + inode->i_uid = task->euid; + inode->i_gid = task->egid; + } else { + inode->i_uid = 0; + inode->i_gid = 0; + } + inode->i_mode &= ~(S_ISUID | S_ISGID); + security_task_to_inode(task, inode); + put_task_struct(task); + return 1; + } + rcu_read_unlock(); + put_files_struct(files); + } + put_task_struct(task); + } + d_drop(dentry); + return 0; +} + +static struct dentry_operations tid_fd_dentry_operations = +{ + .d_revalidate = tid_fd_revalidate, + .d_delete = pid_delete_dentry, +}; + +static struct dentry *proc_fd_instantiate(struct inode *dir, + struct dentry *dentry, struct task_struct *task, void *ptr) +{ + unsigned fd = *(unsigned *)ptr; + struct file *file; + struct files_struct *files; + struct inode *inode; + struct proc_inode *ei; + struct dentry *error = ERR_PTR(-ENOENT); - inode = proc_pid_make_inode(dir->i_sb, task, PROC_TID_FD_DIR+fd); + inode = proc_pid_make_inode(dir->i_sb, task); if (!inode) goto out; ei = PROC_I(inode); + ei->fd = fd; files = get_files_struct(task); if (!files) - goto out_unlock; + goto out_iput; inode->i_mode = S_IFLNK; /* @@ -1555,352 +1365,608 @@ static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, spin_lock(&files->file_lock); file = fcheck_files(files, fd); if (!file) - goto out_unlock2; + goto out_unlock; if (file->f_mode & 1) inode->i_mode |= S_IRUSR | S_IXUSR; if (file->f_mode & 2) inode->i_mode |= S_IWUSR | S_IXUSR; spin_unlock(&files->file_lock); put_files_struct(files); + inode->i_op = &proc_pid_link_inode_operations; inode->i_size = 64; ei->op.proc_get_link = proc_fd_link; dentry->d_op = &tid_fd_dentry_operations; d_add(dentry, inode); - return NULL; + /* Close the race of the process dying before we return the dentry */ + if (tid_fd_revalidate(dentry, NULL)) + error = NULL; -out_unlock2: + out: + return error; +out_unlock: spin_unlock(&files->file_lock); put_files_struct(files); -out_unlock: +out_iput: iput(inode); + goto out; +} + +static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, struct nameidata *nd) +{ + struct task_struct *task = get_proc_task(dir); + unsigned fd = name_to_int(dentry); + struct dentry *result = ERR_PTR(-ENOENT); + + if (!task) + goto out_no_task; + if (fd == ~0U) + goto out; + + result = proc_fd_instantiate(dir, dentry, task, &fd); out: - return ERR_PTR(-ENOENT); + put_task_struct(task); +out_no_task: + return result; +} + +static int proc_fd_fill_cache(struct file *filp, void *dirent, filldir_t filldir, + struct task_struct *task, int fd) +{ + char name[PROC_NUMBUF]; + int len = snprintf(name, sizeof(name), "%d", fd); + return proc_fill_cache(filp, dirent, filldir, name, len, + proc_fd_instantiate, task, &fd); } -static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldir); -static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd); +static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir) +{ + struct dentry *dentry = filp->f_path.dentry; + struct inode *inode = dentry->d_inode; + struct task_struct *p = get_proc_task(inode); + unsigned int fd, tid, ino; + int retval; + struct files_struct * files; + struct fdtable *fdt; + + retval = -ENOENT; + if (!p) + goto out_no_task; + retval = 0; + tid = p->pid; + + fd = filp->f_pos; + switch (fd) { + case 0: + if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0) + goto out; + filp->f_pos++; + case 1: + ino = parent_ino(dentry); + if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0) + goto out; + filp->f_pos++; + default: + files = get_files_struct(p); + if (!files) + goto out; + rcu_read_lock(); + fdt = files_fdtable(files); + for (fd = filp->f_pos-2; + fd < fdt->max_fds; + fd++, filp->f_pos++) { + + if (!fcheck_files(files, fd)) + continue; + rcu_read_unlock(); + + if (proc_fd_fill_cache(filp, dirent, filldir, p, fd) < 0) { + rcu_read_lock(); + break; + } + rcu_read_lock(); + } + rcu_read_unlock(); + put_files_struct(files); + } +out: + put_task_struct(p); +out_no_task: + return retval; +} static struct file_operations proc_fd_operations = { .read = generic_read_dir, .readdir = proc_readfd, }; -static struct file_operations proc_task_operations = { - .read = generic_read_dir, - .readdir = proc_task_readdir, -}; - /* * proc directories can do almost nothing.. */ static struct inode_operations proc_fd_inode_operations = { .lookup = proc_lookupfd, - .permission = proc_permission, .setattr = proc_setattr, }; -static struct inode_operations proc_task_inode_operations = { - .lookup = proc_task_lookup, - .permission = proc_task_permission, - .setattr = proc_setattr, -}; +static struct dentry *proc_pident_instantiate(struct inode *dir, + struct dentry *dentry, struct task_struct *task, void *ptr) +{ + struct pid_entry *p = ptr; + struct inode *inode; + struct proc_inode *ei; + struct dentry *error = ERR_PTR(-EINVAL); + + inode = proc_pid_make_inode(dir->i_sb, task); + if (!inode) + goto out; + + 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 */ + if (p->iop) + inode->i_op = p->iop; + if (p->fop) + inode->i_fop = p->fop; + ei->op = p->op; + dentry->d_op = &pid_dentry_operations; + d_add(dentry, inode); + /* Close the race of the process dying before we return the dentry */ + if (pid_revalidate(dentry, NULL)) + error = NULL; +out: + return error; +} + +static struct dentry *proc_pident_lookup(struct inode *dir, + struct dentry *dentry, + struct pid_entry *ents, + unsigned int nents) +{ + struct inode *inode; + struct dentry *error; + struct task_struct *task = get_proc_task(dir); + struct pid_entry *p, *last; + + error = ERR_PTR(-ENOENT); + inode = NULL; + + if (!task) + goto out_no_task; + + /* TODO: maybe we can come up with a generic approach? */ + if (task_vx_flags(task, VXF_HIDE_VINFO, 0) && + (dentry->d_name.len == 5) && + (!memcmp(dentry->d_name.name, "vinfo", 5) || + !memcmp(dentry->d_name.name, "ninfo", 5))) + goto out; + + /* + * Yes, it does not scale. And it should not. Don't add + * new entries into /proc// without very good reasons. + */ + last = &ents[nents - 1]; + for (p = ents; p <= last; p++) { + if (p->len != dentry->d_name.len) + continue; + if (!memcmp(dentry->d_name.name, p->name, p->len)) + break; + } + if (p > last) + goto out; + + error = proc_pident_instantiate(dir, dentry, task, p); +out: + put_task_struct(task); +out_no_task: + return error; +} + +static int proc_pident_fill_cache(struct file *filp, void *dirent, filldir_t filldir, + struct task_struct *task, struct pid_entry *p) +{ + return proc_fill_cache(filp, dirent, filldir, p->name, p->len, + proc_pident_instantiate, task, p); +} + +static int proc_pident_readdir(struct file *filp, + void *dirent, filldir_t filldir, + struct pid_entry *ents, unsigned int nents) +{ + int i; + int pid; + struct dentry *dentry = filp->f_path.dentry; + struct inode *inode = dentry->d_inode; + struct task_struct *task = get_proc_task(inode); + struct pid_entry *p, *last; + ino_t ino; + int ret; + + ret = -ENOENT; + if (!task) + goto out_no_task; + + ret = 0; + pid = task->pid; + i = filp->f_pos; + switch (i) { + case 0: + ino = inode->i_ino; + if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0) + goto out; + i++; + filp->f_pos++; + /* fall through */ + case 1: + ino = parent_ino(dentry); + if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0) + goto out; + i++; + filp->f_pos++; + /* fall through */ + default: + i -= 2; + if (i >= nents) { + ret = 1; + goto out; + } + p = ents + i; + last = &ents[nents - 1]; + while (p <= last) { + if (proc_pident_fill_cache(filp, dirent, filldir, task, p) < 0) + goto out; + filp->f_pos++; + p++; + } + } + + ret = 1; +out: + put_task_struct(task); +out_no_task: + return ret; +} #ifdef CONFIG_SECURITY static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { - struct inode * inode = file->f_dentry->d_inode; + struct inode * inode = file->f_path.dentry->d_inode; unsigned long page; ssize_t length; - struct task_struct *task = proc_task(inode); + struct task_struct *task = get_proc_task(inode); + + length = -ESRCH; + if (!task) + goto out_no_task; if (count > PAGE_SIZE) count = PAGE_SIZE; + length = -ENOMEM; if (!(page = __get_free_page(GFP_KERNEL))) - return -ENOMEM; + goto out; - length = security_getprocattr(task, - (char*)file->f_dentry->d_name.name, + length = security_getprocattr(task, + (char*)file->f_path.dentry->d_name.name, (void*)page, count); if (length >= 0) length = simple_read_from_buffer(buf, count, ppos, (char *)page, length); free_page(page); +out: + put_task_struct(task); +out_no_task: return length; } static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) -{ - struct inode * inode = file->f_dentry->d_inode; - char *page; - ssize_t length; - struct task_struct *task = proc_task(inode); - - if (count > PAGE_SIZE) - count = PAGE_SIZE; - if (*ppos != 0) { - /* No partial writes. */ - return -EINVAL; - } - page = (char*)__get_free_page(GFP_USER); - if (!page) - return -ENOMEM; - length = -EFAULT; - if (copy_from_user(page, buf, count)) +{ + struct inode * inode = file->f_path.dentry->d_inode; + char *page; + ssize_t length; + struct task_struct *task = get_proc_task(inode); + + length = -ESRCH; + if (!task) + goto out_no_task; + if (count > PAGE_SIZE) + count = PAGE_SIZE; + + /* No partial writes. */ + length = -EINVAL; + if (*ppos != 0) + goto out; + + length = -ENOMEM; + page = (char*)__get_free_page(GFP_USER); + if (!page) goto out; - length = security_setprocattr(task, - (char*)file->f_dentry->d_name.name, + length = -EFAULT; + if (copy_from_user(page, buf, count)) + goto out_free; + + length = security_setprocattr(task, + (char*)file->f_path.dentry->d_name.name, (void*)page, count); -out: +out_free: free_page((unsigned long) page); +out: + put_task_struct(task); +out_no_task: return length; -} +} static struct file_operations proc_pid_attr_operations = { .read = proc_pid_attr_read, .write = proc_pid_attr_write, }; -static struct file_operations proc_tid_attr_operations; -static struct inode_operations proc_tid_attr_inode_operations; -static struct file_operations proc_tgid_attr_operations; -static struct inode_operations proc_tgid_attr_inode_operations; +static struct pid_entry attr_dir_stuff[] = { + REG("current", S_IRUGO|S_IWUGO, pid_attr), + REG("prev", S_IRUGO, pid_attr), + REG("exec", S_IRUGO|S_IWUGO, pid_attr), + REG("fscreate", S_IRUGO|S_IWUGO, pid_attr), + REG("keycreate", S_IRUGO|S_IWUGO, pid_attr), + REG("sockcreate", S_IRUGO|S_IWUGO, pid_attr), +}; + +static int proc_attr_dir_readdir(struct file * filp, + void * dirent, filldir_t filldir) +{ + return proc_pident_readdir(filp,dirent,filldir, + attr_dir_stuff,ARRAY_SIZE(attr_dir_stuff)); +} + +static struct file_operations proc_attr_dir_operations = { + .read = generic_read_dir, + .readdir = proc_attr_dir_readdir, +}; + +static struct dentry *proc_attr_dir_lookup(struct inode *dir, + struct dentry *dentry, struct nameidata *nd) +{ + return proc_pident_lookup(dir, dentry, + attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff)); +} + +static struct inode_operations proc_attr_dir_inode_operations = { + .lookup = proc_attr_dir_lookup, + .getattr = pid_getattr, + .setattr = proc_setattr, +}; + #endif -extern int proc_pid_vx_info(struct task_struct *, char *); -extern int proc_pid_nx_info(struct task_struct *, char *); +/* + * /proc/self: + */ +static int proc_self_readlink(struct dentry *dentry, char __user *buffer, + int buflen) +{ + char tmp[PROC_NUMBUF]; + sprintf(tmp, "%d", vx_map_tgid(current->tgid)); + return vfs_readlink(dentry,buffer,buflen,tmp); +} -static int get_tid_list(int index, unsigned int *tids, struct inode *dir); +static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + char tmp[PROC_NUMBUF]; + sprintf(tmp, "%d", vx_map_tgid(current->tgid)); + return ERR_PTR(vfs_follow_link(nd,tmp)); +} -/* SMP-safe */ -static struct dentry *proc_pident_lookup(struct inode *dir, - struct dentry *dentry, - struct pid_entry *ents) +static struct inode_operations proc_self_inode_operations = { + .readlink = proc_self_readlink, + .follow_link = proc_self_follow_link, +}; + +/* + * proc base + * + * These are the directory entries in the root directory of /proc + * that properly belong to the /proc filesystem, as they describe + * describe something that is process related. + */ +static struct pid_entry proc_base_stuff[] = { + NOD("self", S_IFLNK|S_IRWXUGO, + &proc_self_inode_operations, NULL, {}), +}; + +/* + * Exceptional case: normally we are not allowed to unhash a busy + * directory. In this case, however, we can do it - no aliasing problems + * due to the way we treat inodes. + */ +static int proc_base_revalidate(struct dentry *dentry, struct nameidata *nd) +{ + struct inode *inode = dentry->d_inode; + struct task_struct *task = get_proc_task(inode); + if (task) { + put_task_struct(task); + return 1; + } + d_drop(dentry); + return 0; +} + +static struct dentry_operations proc_base_dentry_operations = +{ + .d_revalidate = proc_base_revalidate, + .d_delete = pid_delete_dentry, +}; + +static struct dentry *proc_base_instantiate(struct inode *dir, + struct dentry *dentry, struct task_struct *task, void *ptr) { + struct pid_entry *p = ptr; struct inode *inode; - int error; - struct task_struct *task = proc_task(dir); - struct pid_entry *p; struct proc_inode *ei; + struct dentry *error = ERR_PTR(-EINVAL); - error = -ENOENT; - inode = NULL; - - if (!pid_alive(task)) + /* Allocate the inode */ + error = ERR_PTR(-ENOMEM); + inode = new_inode(dir->i_sb); + if (!inode) goto out; - for (p = ents; p->name; p++) { + /* Initialize the inode */ + ei = PROC_I(inode); + inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; + + /* + * grab the reference to the task. + */ + ei->pid = get_task_pid(task, PIDTYPE_PID); + if (!ei->pid) + goto out_iput; + + inode->i_uid = 0; + inode->i_gid = 0; + inode->i_mode = p->mode; + if (S_ISDIR(inode->i_mode)) + inode->i_nlink = 2; + if (S_ISLNK(inode->i_mode)) + inode->i_size = 64; + if (p->iop) + inode->i_op = p->iop; + if (p->fop) + inode->i_fop = p->fop; + ei->op = p->op; + dentry->d_op = &proc_base_dentry_operations; + d_add(dentry, inode); + error = NULL; +out: + return error; +out_iput: + iput(inode); + goto out; +} + +static struct dentry *proc_base_lookup(struct inode *dir, struct dentry *dentry) +{ + struct dentry *error; + struct task_struct *task = get_proc_task_real(dir); + struct pid_entry *p, *last; + + error = ERR_PTR(-ENOENT); + + if (!task) + goto out_no_task; + + /* Lookup the directory entry */ + last = &proc_base_stuff[ARRAY_SIZE(proc_base_stuff) - 1]; + for (p = proc_base_stuff; p <= last; p++) { if (p->len != dentry->d_name.len) continue; if (!memcmp(dentry->d_name.name, p->name, p->len)) break; } - if (!p->name) + if (p > last) goto out; - switch (p->type) { - case PROC_TID_VX_INFO: - case PROC_TGID_VX_INFO: - case PROC_TID_IP_INFO: - case PROC_TGID_IP_INFO: - if (task_vx_flags(task, VXF_INFO_HIDE, 0)) - goto out; - default: - break; - } + error = proc_base_instantiate(dir, dentry, task, p); - error = -EINVAL; - inode = proc_pid_make_inode(dir->i_sb, task, p->type); - if (!inode) - goto out; +out: + put_task_struct(task); +out_no_task: + return error; +} - ei = PROC_I(inode); - inode->i_mode = p->mode; - /* - * Yes, it does not scale. And it should not. Don't add - * new entries into /proc// without very good reasons. - */ - switch(p->type) { - case PROC_TGID_TASK: - inode->i_nlink = 2 + get_tid_list(2, NULL, dir); - inode->i_op = &proc_task_inode_operations; - inode->i_fop = &proc_task_operations; - break; - case PROC_TID_FD: - case PROC_TGID_FD: - inode->i_nlink = 2; - inode->i_op = &proc_fd_inode_operations; - inode->i_fop = &proc_fd_operations; - break; - case PROC_TID_EXE: - case PROC_TGID_EXE: - inode->i_op = &proc_pid_link_inode_operations; - ei->op.proc_get_link = proc_exe_link; - break; - case PROC_TID_CWD: - case PROC_TGID_CWD: - inode->i_op = &proc_pid_link_inode_operations; - ei->op.proc_get_link = proc_cwd_link; - break; - case PROC_TID_ROOT: - case PROC_TGID_ROOT: - inode->i_op = &proc_pid_link_inode_operations; - ei->op.proc_get_link = proc_root_link; - break; - case PROC_TID_ENVIRON: - case PROC_TGID_ENVIRON: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_environ; - break; - case PROC_TID_AUXV: - case PROC_TGID_AUXV: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_auxv; - break; - case PROC_TID_STATUS: - case PROC_TGID_STATUS: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_status; - break; - case PROC_TID_STAT: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_tid_stat; - break; - case PROC_TGID_STAT: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_tgid_stat; - break; - case PROC_TID_CMDLINE: - case PROC_TGID_CMDLINE: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_cmdline; - break; - case PROC_TID_STATM: - case PROC_TGID_STATM: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_statm; - break; - case PROC_TID_MAPS: - case PROC_TGID_MAPS: - inode->i_fop = &proc_maps_operations; - break; +static int proc_base_fill_cache(struct file *filp, void *dirent, filldir_t filldir, + struct task_struct *task, struct pid_entry *p) +{ + return proc_fill_cache(filp, dirent, filldir, p->name, p->len, + proc_base_instantiate, task, p); +} + +#ifdef CONFIG_TASK_IO_ACCOUNTING +static int proc_pid_io_accounting(struct task_struct *task, char *buffer) +{ + return sprintf(buffer, + "rchar: %llu\n" + "wchar: %llu\n" + "syscr: %llu\n" + "syscw: %llu\n" + "read_bytes: %llu\n" + "write_bytes: %llu\n" + "cancelled_write_bytes: %llu\n", + (unsigned long long)task->rchar, + (unsigned long long)task->wchar, + (unsigned long long)task->syscr, + (unsigned long long)task->syscw, + (unsigned long long)task->ioac.read_bytes, + (unsigned long long)task->ioac.write_bytes, + (unsigned long long)task->ioac.cancelled_write_bytes); +} +#endif + +/* + * Thread groups + */ +static struct file_operations proc_task_operations; +static struct inode_operations proc_task_inode_operations; + +extern int proc_pid_vx_info(struct task_struct *, char *); +extern int proc_pid_nx_info(struct task_struct *, char *); + +static struct pid_entry tgid_base_stuff[] = { + DIR("task", S_IRUGO|S_IXUGO, task), + DIR("fd", S_IRUSR|S_IXUSR, fd), + INF("environ", S_IRUSR, pid_environ), + INF("auxv", S_IRUSR, pid_auxv), + INF("status", S_IRUGO, pid_status), + INF("cmdline", S_IRUGO, pid_cmdline), + INF("stat", S_IRUGO, tgid_stat), + INF("statm", S_IRUGO, pid_statm), + REG("maps", S_IRUSR, maps), #ifdef CONFIG_NUMA - case PROC_TID_NUMA_MAPS: - case PROC_TGID_NUMA_MAPS: - inode->i_fop = &proc_numa_maps_operations; - break; + REG("numa_maps", S_IRUGO, numa_maps), #endif - case PROC_TID_MEM: - case PROC_TGID_MEM: - inode->i_op = &proc_mem_inode_operations; - inode->i_fop = &proc_mem_operations; - break; + REG("mem", S_IRUSR|S_IWUSR, mem), #ifdef CONFIG_SECCOMP - case PROC_TID_SECCOMP: - case PROC_TGID_SECCOMP: - inode->i_fop = &proc_seccomp_operations; - break; -#endif /* CONFIG_SECCOMP */ - case PROC_TID_MOUNTS: - case PROC_TGID_MOUNTS: - inode->i_fop = &proc_mounts_operations; - break; + REG("seccomp", S_IRUSR|S_IWUSR, seccomp), +#endif + LNK("cwd", cwd), + LNK("root", root), + LNK("exe", exe), + REG("mounts", S_IRUGO, mounts), + REG("mountstats", S_IRUSR, mountstats), #ifdef CONFIG_MMU - case PROC_TID_SMAPS: - case PROC_TGID_SMAPS: - inode->i_fop = &proc_smaps_operations; - break; + REG("smaps", S_IRUSR, smaps), #endif #ifdef CONFIG_SECURITY - case PROC_TID_ATTR: - inode->i_nlink = 2; - inode->i_op = &proc_tid_attr_inode_operations; - inode->i_fop = &proc_tid_attr_operations; - break; - case PROC_TGID_ATTR: - inode->i_nlink = 2; - inode->i_op = &proc_tgid_attr_inode_operations; - inode->i_fop = &proc_tgid_attr_operations; - break; - case PROC_TID_ATTR_CURRENT: - case PROC_TGID_ATTR_CURRENT: - case PROC_TID_ATTR_PREV: - case PROC_TGID_ATTR_PREV: - case PROC_TID_ATTR_EXEC: - case PROC_TGID_ATTR_EXEC: - case PROC_TID_ATTR_FSCREATE: - case PROC_TGID_ATTR_FSCREATE: - inode->i_fop = &proc_pid_attr_operations; - break; + DIR("attr", S_IRUGO|S_IXUGO, attr_dir), #endif #ifdef CONFIG_KALLSYMS - case PROC_TID_WCHAN: - case PROC_TGID_WCHAN: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_wchan; - break; + INF("wchan", S_IRUGO, pid_wchan), #endif #ifdef CONFIG_SCHEDSTATS - case PROC_TID_SCHEDSTAT: - case PROC_TGID_SCHEDSTAT: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_schedstat; - break; + INF("schedstat", S_IRUGO, pid_schedstat), #endif #ifdef CONFIG_CPUSETS - case PROC_TID_CPUSET: - case PROC_TGID_CPUSET: - inode->i_fop = &proc_cpuset_operations; - break; + REG("cpuset", S_IRUGO, cpuset), #endif - case PROC_TID_OOM_SCORE: - case PROC_TGID_OOM_SCORE: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_oom_score; - break; - case PROC_TID_OOM_ADJUST: - case PROC_TGID_OOM_ADJUST: - inode->i_fop = &proc_oom_adjust_operations; - break; + INF("vinfo", S_IRUGO, pid_vx_info), + INF("ninfo", S_IRUGO, pid_nx_info), + INF("oom_score", S_IRUGO, oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust), #ifdef CONFIG_AUDITSYSCALL - case PROC_TID_LOGINUID: - case PROC_TGID_LOGINUID: - inode->i_fop = &proc_loginuid_operations; - break; + REG("loginuid", S_IWUSR|S_IRUGO, loginuid), #endif - case PROC_TID_VX_INFO: - case PROC_TGID_VX_INFO: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_vx_info; - break; - case PROC_TID_IP_INFO: - case PROC_TGID_IP_INFO: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_nx_info; - break; - default: - printk("procfs: impossible type (%d)",p->type); - error = -EINVAL; - goto out_put; - } - dentry->d_op = &pid_dentry_operations; - d_add(dentry, inode); - return NULL; - -out_put: - iput(inode); -out: - return ERR_PTR(error); -} - -static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ - return proc_pident_lookup(dir, dentry, tgid_base_stuff); -} +#ifdef CONFIG_FAULT_INJECTION + REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject), +#endif +#ifdef CONFIG_TASK_IO_ACCOUNTING + INF("io", S_IRUGO, pid_io_accounting), +#endif +}; -static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ - return proc_pident_lookup(dir, dentry, tid_base_stuff); +static int proc_tgid_base_readdir(struct file * filp, + void * dirent, filldir_t filldir) +{ + return proc_pident_readdir(filp,dirent,filldir, + tgid_base_stuff,ARRAY_SIZE(tgid_base_stuff)); } static struct file_operations proc_tgid_base_operations = { @@ -1908,451 +1974,462 @@ static struct file_operations proc_tgid_base_operations = { .readdir = proc_tgid_base_readdir, }; -static struct file_operations proc_tid_base_operations = { - .read = generic_read_dir, - .readdir = proc_tid_base_readdir, -}; +static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ + return proc_pident_lookup(dir, dentry, + tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); +} static struct inode_operations proc_tgid_base_inode_operations = { .lookup = proc_tgid_base_lookup, + .getattr = pid_getattr, .setattr = proc_setattr, }; -static struct inode_operations proc_tid_base_inode_operations = { - .lookup = proc_tid_base_lookup, - .setattr = proc_setattr, -}; - -#ifdef CONFIG_SECURITY -static int proc_tgid_attr_readdir(struct file * filp, - void * dirent, filldir_t filldir) +/** + * proc_flush_task - Remove dcache entries for @task from the /proc dcache. + * + * @task: task that should be flushed. + * + * Looks in the dcache for + * /proc/@pid + * /proc/@tgid/task/@pid + * if either directory is present flushes it and all of it'ts children + * from the dcache. + * + * It is safe and reasonable to cache /proc entries for a task until + * that task exits. After that they just clog up the dcache with + * useless entries, possibly causing useful dcache entries to be + * flushed instead. This routine is proved to flush those useless + * dcache entries at process exit time. + * + * NOTE: This routine is just an optimization so it does not guarantee + * that no dcache entries will exist at process exit time it + * just makes it very unlikely that any will persist. + */ +void proc_flush_task(struct task_struct *task) { - return proc_pident_readdir(filp,dirent,filldir, - tgid_attr_stuff,ARRAY_SIZE(tgid_attr_stuff)); + struct dentry *dentry, *leader, *dir; + char buf[PROC_NUMBUF]; + struct qstr name; + + name.name = buf; + name.len = snprintf(buf, sizeof(buf), "%d", task->pid); + dentry = d_hash_and_lookup(proc_mnt->mnt_root, &name); + if (dentry) { + shrink_dcache_parent(dentry); + d_drop(dentry); + dput(dentry); + } + + if (thread_group_leader(task)) + goto out; + + name.name = buf; + name.len = snprintf(buf, sizeof(buf), "%d", task->tgid); + leader = d_hash_and_lookup(proc_mnt->mnt_root, &name); + if (!leader) + goto out; + + name.name = "task"; + name.len = strlen(name.name); + dir = d_hash_and_lookup(leader, &name); + if (!dir) + goto out_put_leader; + + name.name = buf; + name.len = snprintf(buf, sizeof(buf), "%d", task->pid); + dentry = d_hash_and_lookup(dir, &name); + if (dentry) { + shrink_dcache_parent(dentry); + d_drop(dentry); + dput(dentry); + } + + dput(dir); +out_put_leader: + dput(leader); +out: + return; } -static int proc_tid_attr_readdir(struct file * filp, - void * dirent, filldir_t filldir) +static struct dentry *proc_pid_instantiate(struct inode *dir, + struct dentry * dentry, + struct task_struct *task, void *ptr) { - return proc_pident_readdir(filp,dirent,filldir, - tid_attr_stuff,ARRAY_SIZE(tid_attr_stuff)); -} + struct dentry *error = ERR_PTR(-ENOENT); + struct inode *inode; -static struct file_operations proc_tgid_attr_operations = { - .read = generic_read_dir, - .readdir = proc_tgid_attr_readdir, -}; + inode = proc_pid_make_inode(dir->i_sb, task); + if (!inode) + goto out; -static struct file_operations proc_tid_attr_operations = { - .read = generic_read_dir, - .readdir = proc_tid_attr_readdir, -}; + inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; + inode->i_op = &proc_tgid_base_inode_operations; + inode->i_fop = &proc_tgid_base_operations; + inode->i_flags|=S_IMMUTABLE; + inode->i_nlink = 4; +#ifdef CONFIG_SECURITY + inode->i_nlink += 1; +#endif -static struct dentry *proc_tgid_attr_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) -{ - return proc_pident_lookup(dir, dentry, tgid_attr_stuff); + dentry->d_op = &pid_dentry_operations; + + d_add(dentry, inode); + /* Close the race of the process dying before we return the dentry */ + if (pid_revalidate(dentry, NULL)) + error = NULL; +out: + return error; } -static struct dentry *proc_tid_attr_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) +struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) { - return proc_pident_lookup(dir, dentry, tid_attr_stuff); -} + struct dentry *result = ERR_PTR(-ENOENT); + struct task_struct *task; + unsigned tgid; -static struct inode_operations proc_tgid_attr_inode_operations = { - .lookup = proc_tgid_attr_lookup, - .setattr = proc_setattr, -}; + result = proc_base_lookup(dir, dentry); + if (!IS_ERR(result) || PTR_ERR(result) != -ENOENT) + goto out; -static struct inode_operations proc_tid_attr_inode_operations = { - .lookup = proc_tid_attr_lookup, - .setattr = proc_setattr, -}; -#endif + tgid = name_to_int(dentry); + if (tgid == ~0U) + goto out; + + rcu_read_lock(); + task = vx_find_proc_task_by_pid(tgid); + if (task) + get_task_struct(task); + rcu_read_unlock(); + if (!task) + goto out; + + result = proc_pid_instantiate(dir, dentry, task, NULL); + put_task_struct(task); +out: + return result; +} /* - * /proc/self: + * Find the first task with tgid >= tgid + * */ -static int proc_self_readlink(struct dentry *dentry, char __user *buffer, - int buflen) +static struct task_struct *next_tgid(unsigned int tgid) { - char tmp[30]; - sprintf(tmp, "%d", vx_map_tgid(current->tgid)); - return vfs_readlink(dentry,buffer,buflen,tmp); + struct task_struct *task; + struct pid *pid; + + rcu_read_lock(); +retry: + task = NULL; + pid = find_ge_pid(tgid); + if (pid) { + tgid = pid->nr + 1; + task = pid_task(pid, PIDTYPE_PID); + /* What we to know is if the pid we have find is the + * pid of a thread_group_leader. Testing for task + * being a thread_group_leader is the obvious thing + * todo but there is a window when it fails, due to + * the pid transfer logic in de_thread. + * + * So we perform the straight forward test of seeing + * if the pid we have found is the pid of a thread + * group leader, and don't worry if the task we have + * found doesn't happen to be a thread group leader. + * As we don't care in the case of readdir. + */ + if (!task || !has_group_leader_pid(task)) + goto retry; + get_task_struct(task); + } + rcu_read_unlock(); + return task; } -static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd) -{ - char tmp[30]; - sprintf(tmp, "%d", vx_map_tgid(current->tgid)); - return ERR_PTR(vfs_follow_link(nd,tmp)); -} - -static struct inode_operations proc_self_inode_operations = { - .readlink = proc_self_readlink, - .follow_link = proc_self_follow_link, - .setattr = proc_setattr, -}; +#define TGID_OFFSET (FIRST_PROCESS_ENTRY + ARRAY_SIZE(proc_base_stuff)) -/** - * proc_pid_unhash - Unhash /proc/@pid entry from the dcache. - * @p: task that should be flushed. - * - * Drops the /proc/@pid dcache entry from the hash chains. - * - * Dropping /proc/@pid entries and detach_pid must be synchroneous, - * otherwise e.g. /proc/@pid/exe might point to the wrong executable, - * if the pid value is immediately reused. This is enforced by - * - caller must acquire spin_lock(p->proc_lock) - * - must be called before detach_pid() - * - proc_pid_lookup acquires proc_lock, and checks that - * the target is not dead by looking at the attach count - * of PIDTYPE_PID. - */ +static int proc_pid_fill_cache(struct file *filp, void *dirent, filldir_t filldir, + struct task_struct *task, int tgid) +{ + char name[PROC_NUMBUF]; + int len = snprintf(name, sizeof(name), "%d", tgid); + return proc_fill_cache(filp, dirent, filldir, name, len, + proc_pid_instantiate, task, NULL); +} -struct dentry *proc_pid_unhash(struct task_struct *p) +/* for the /proc/ directory itself, after non-process stuff has been done */ +int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) { - struct dentry *proc_dentry; + unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY; + struct task_struct *reaper = get_proc_task_real(filp->f_path.dentry->d_inode); + struct task_struct *task; + int tgid; - proc_dentry = p->proc_dentry; - if (proc_dentry != NULL) { + if (!reaper) + goto out_no_task; - spin_lock(&dcache_lock); - spin_lock(&proc_dentry->d_lock); - if (!d_unhashed(proc_dentry)) { - dget_locked(proc_dentry); - __d_drop(proc_dentry); - spin_unlock(&proc_dentry->d_lock); - } else { - spin_unlock(&proc_dentry->d_lock); - proc_dentry = NULL; + for (; nr < ARRAY_SIZE(proc_base_stuff); filp->f_pos++, nr++) { + struct pid_entry *p = &proc_base_stuff[nr]; + if (proc_base_fill_cache(filp, dirent, filldir, reaper, p) < 0) + goto out; + } + + tgid = filp->f_pos - TGID_OFFSET; + for (task = next_tgid(tgid); + task; + put_task_struct(task), task = next_tgid(tgid + 1)) { + tgid = task->pid; + filp->f_pos = tgid + TGID_OFFSET; + if (!vx_proc_task_visible(task)) + continue; + if (proc_pid_fill_cache(filp, dirent, filldir, task, tgid) < 0) { + put_task_struct(task); + goto out; } - spin_unlock(&dcache_lock); } - return proc_dentry; + filp->f_pos = PID_MAX_LIMIT + TGID_OFFSET; +out: + put_task_struct(reaper); +out_no_task: + return 0; } -/** - * proc_pid_flush - recover memory used by stale /proc/@pid/x entries - * @proc_dentry: directoy to prune. - * - * Shrink the /proc directory that was used by the just killed thread. +/* + * Tasks */ - -void proc_pid_flush(struct dentry *proc_dentry) +static struct pid_entry tid_base_stuff[] = { + DIR("fd", S_IRUSR|S_IXUSR, fd), + INF("environ", S_IRUSR, pid_environ), + INF("auxv", S_IRUSR, pid_auxv), + INF("status", S_IRUGO, pid_status), + INF("cmdline", S_IRUGO, pid_cmdline), + INF("stat", S_IRUGO, tid_stat), + INF("statm", S_IRUGO, pid_statm), + REG("maps", S_IRUSR, maps), +#ifdef CONFIG_NUMA + REG("numa_maps", S_IRUGO, numa_maps), +#endif + REG("mem", S_IRUSR|S_IWUSR, mem), +#ifdef CONFIG_SECCOMP + REG("seccomp", S_IRUSR|S_IWUSR, seccomp), +#endif + LNK("cwd", cwd), + LNK("root", root), + LNK("exe", exe), + REG("mounts", S_IRUGO, mounts), +#ifdef CONFIG_MMU + REG("smaps", S_IRUSR, smaps), +#endif +#ifdef CONFIG_SECURITY + DIR("attr", S_IRUGO|S_IXUGO, attr_dir), +#endif +#ifdef CONFIG_KALLSYMS + INF("wchan", S_IRUGO, pid_wchan), +#endif +#ifdef CONFIG_SCHEDSTATS + INF("schedstat", S_IRUGO, pid_schedstat), +#endif +#ifdef CONFIG_CPUSETS + REG("cpuset", S_IRUGO, cpuset), +#endif + INF("oom_score", S_IRUGO, oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust), +#ifdef CONFIG_AUDITSYSCALL + REG("loginuid", S_IWUSR|S_IRUGO, loginuid), +#endif +#ifdef CONFIG_FAULT_INJECTION + REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject), +#endif +}; + +static int proc_tid_base_readdir(struct file * filp, + void * dirent, filldir_t filldir) { - might_sleep(); - if(proc_dentry != NULL) { - shrink_dcache_parent(proc_dentry); - dput(proc_dentry); - } + return proc_pident_readdir(filp,dirent,filldir, + tid_base_stuff,ARRAY_SIZE(tid_base_stuff)); } -#define VXF_FAKE_INIT (VXF_INFO_INIT|VXF_STATE_INIT) - -static inline int proc_pid_visible(struct task_struct *task, int pid) -{ - if ((pid == 1) && - !vx_flags(VXF_FAKE_INIT, VXF_FAKE_INIT)) - goto visible; - if (vx_check(vx_task_xid(task), VX_WATCH|VX_IDENT)) - goto visible; - return 0; -visible: - return 1; +static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ + return proc_pident_lookup(dir, dentry, + tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); } -/* SMP-safe */ -struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) -{ - struct task_struct *task; - struct inode *inode; - struct proc_inode *ei; - unsigned tgid; - int died; - - if (dentry->d_name.len == 4 && !memcmp(dentry->d_name.name,"self",4)) { - inode = new_inode(dir->i_sb); - if (!inode) - return ERR_PTR(-ENOMEM); - ei = PROC_I(inode); - inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; - inode->i_ino = fake_ino(0, PROC_TGID_INO); - ei->pde = NULL; - inode->i_mode = S_IFLNK|S_IRWXUGO; - inode->i_uid = inode->i_gid = 0; - inode->i_size = 64; - inode->i_op = &proc_self_inode_operations; - d_add(dentry, inode); - return NULL; - } - tgid = name_to_int(dentry); - if (tgid == ~0U) - goto out; +static struct file_operations proc_tid_base_operations = { + .read = generic_read_dir, + .readdir = proc_tid_base_readdir, +}; - read_lock(&tasklist_lock); - task = find_task_by_pid(tgid); - if (task) - get_task_struct(task); - read_unlock(&tasklist_lock); - if (!task) - goto out; +static struct inode_operations proc_tid_base_inode_operations = { + .lookup = proc_tid_base_lookup, + .getattr = pid_getattr, + .setattr = proc_setattr, +}; - /* check for context visibility */ - if (!proc_pid_visible(task, tgid)) - goto out_drop_task; +static struct dentry *proc_task_instantiate(struct inode *dir, + struct dentry *dentry, struct task_struct *task, void *ptr) +{ + struct dentry *error = ERR_PTR(-ENOENT); + struct inode *inode; + inode = proc_pid_make_inode(dir->i_sb, task); - inode = proc_pid_make_inode(dir->i_sb, task, PROC_TGID_INO); if (!inode) - goto out_drop_task; - + goto out; inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; - inode->i_op = &proc_tgid_base_inode_operations; - inode->i_fop = &proc_tgid_base_operations; + inode->i_op = &proc_tid_base_inode_operations; + inode->i_fop = &proc_tid_base_operations; inode->i_flags|=S_IMMUTABLE; + inode->i_nlink = 3; #ifdef CONFIG_SECURITY - inode->i_nlink = 5; -#else - inode->i_nlink = 4; + inode->i_nlink += 1; #endif - dentry->d_op = &pid_base_dentry_operations; + dentry->d_op = &pid_dentry_operations; - died = 0; d_add(dentry, inode); - spin_lock(&task->proc_lock); - task->proc_dentry = dentry; - if (!pid_alive(task)) { - dentry = proc_pid_unhash(task); - died = 1; - } - spin_unlock(&task->proc_lock); - - put_task_struct(task); - if (died) { - proc_pid_flush(dentry); - goto out; - } - return NULL; -out_drop_task: - put_task_struct(task); + /* Close the race of the process dying before we return the dentry */ + if (pid_revalidate(dentry, NULL)) + error = NULL; out: - return ERR_PTR(-ENOENT); + return error; } -/* SMP-safe */ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) { + struct dentry *result = ERR_PTR(-ENOENT); struct task_struct *task; - struct task_struct *leader = proc_task(dir); - struct inode *inode; + struct task_struct *leader = get_proc_task(dir); unsigned tid; + if (!leader) + goto out_no_task; + tid = name_to_int(dentry); if (tid == ~0U) goto out; if (vx_current_initpid(tid)) goto out; - read_lock(&tasklist_lock); - task = find_task_by_pid(tid); + rcu_read_lock(); + task = vx_find_proc_task_by_pid(tid); if (task) get_task_struct(task); - read_unlock(&tasklist_lock); + rcu_read_unlock(); if (!task) goto out; if (leader->tgid != task->tgid) goto out_drop_task; - /* check for context visibility */ - if (!proc_pid_visible(task, tid)) - goto out_drop_task; - - inode = proc_pid_make_inode(dir->i_sb, task, PROC_TID_INO); - if (!inode) - goto out_drop_task; - - inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; - inode->i_op = &proc_tid_base_inode_operations; - inode->i_fop = &proc_tid_base_operations; - inode->i_flags|=S_IMMUTABLE; -#ifdef CONFIG_SECURITY - inode->i_nlink = 4; -#else - inode->i_nlink = 3; -#endif - - dentry->d_op = &pid_base_dentry_operations; - - d_add(dentry, inode); - - put_task_struct(task); - return NULL; + result = proc_task_instantiate(dir, dentry, task, NULL); out_drop_task: put_task_struct(task); out: - return ERR_PTR(-ENOENT); + put_task_struct(leader); +out_no_task: + return result; } -#define PROC_NUMBUF 10 -#define PROC_MAXPIDS 20 - /* - * Get a few tgid's to return for filldir - we need to hold the - * tasklist lock while doing this, and we must release it before - * we actually do the filldir itself, so we use a temp buffer.. + * Find the first tid of a thread group to return to user space. + * + * Usually this is just the thread group leader, but if the users + * buffer was too small or there was a seek into the middle of the + * directory we have more work todo. + * + * In the case of a short read we start with find_task_by_pid. + * + * In the case of a seek we start with the leader and walk nr + * threads past it. */ -static int get_tgid_list(int index, unsigned long version, unsigned int *tgids) -{ - struct task_struct *p; - int nr_tgids = 0; - - index--; - read_lock(&tasklist_lock); - p = NULL; - if (version) { - p = find_task_by_real_pid(version); - if (p && !thread_group_leader(p)) - p = NULL; - } +static struct task_struct *first_tid(struct task_struct *leader, + int tid, int nr) +{ + struct task_struct *pos; - if (p) - index = 0; - else - p = next_task(&init_task); + rcu_read_lock(); + /* Attempt to start with the pid of a thread */ + if (tid && (nr > 0)) { + pos = find_task_by_pid(tid); + if (pos && (pos->group_leader == leader)) + goto found; + } - for ( ; p != &init_task; p = next_task(p)) { - int tgid = p->pid; + /* If nr exceeds the number of threads there is nothing todo */ + pos = NULL; + if (nr && nr >= get_nr_threads(leader)) + goto out; - if (!pid_alive(p)) - continue; - /* check for context visibility */ - if (!proc_pid_visible(p, tgid)) - continue; - if (--index >= 0) - continue; - tgids[nr_tgids] = vx_map_tgid(tgid); - nr_tgids++; - if (nr_tgids >= PROC_MAXPIDS) - break; + /* If we haven't found our starting place yet start + * with the leader and walk nr threads forward. + */ + for (pos = leader; nr > 0; --nr) { + pos = next_thread(pos); + if (pos == leader) { + pos = NULL; + goto out; + } } - read_unlock(&tasklist_lock); - return nr_tgids; +found: + get_task_struct(pos); +out: + rcu_read_unlock(); + return pos; } /* - * Get a few tid's to return for filldir - we need to hold the - * tasklist lock while doing this, and we must release it before - * we actually do the filldir itself, so we use a temp buffer.. + * Find the next thread in the thread list. + * Return NULL if there is an error or no next thread. + * + * The reference to the input task_struct is released. */ -static int get_tid_list(int index, unsigned int *tids, struct inode *dir) -{ - struct task_struct *leader_task = proc_task(dir); - struct task_struct *task = leader_task; - int nr_tids = 0; - - index -= 2; - read_lock(&tasklist_lock); - /* - * The starting point task (leader_task) might be an already - * unlinked task, which cannot be used to access the task-list - * via next_thread(). - */ - if (pid_alive(task)) do { - int tid = task->pid; - - /* check for context visibility */ - if (!proc_pid_visible(task, tid)) - continue; - if (--index >= 0) - continue; - if (tids != NULL) - tids[nr_tids] = vx_map_pid(tid); - nr_tids++; - if (nr_tids >= PROC_MAXPIDS) - break; - } while ((task = next_thread(task)) != leader_task); - read_unlock(&tasklist_lock); - return nr_tids; +static struct task_struct *next_tid(struct task_struct *start) +{ + struct task_struct *pos = NULL; + rcu_read_lock(); + if (pid_alive(start)) { + pos = next_thread(start); + if (thread_group_leader(pos)) + pos = NULL; + else + get_task_struct(pos); + } + rcu_read_unlock(); + put_task_struct(start); + return pos; } -/* for the /proc/ directory itself, after non-process stuff has been done */ -int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) +static int proc_task_fill_cache(struct file *filp, void *dirent, filldir_t filldir, + struct task_struct *task, int tid) { - unsigned int tgid_array[PROC_MAXPIDS]; - char buf[PROC_NUMBUF]; - unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY; - unsigned int nr_tgids, i; - int next_tgid; - - if (!nr) { - ino_t ino = fake_ino(0,PROC_TGID_INO); - if (filldir(dirent, "self", 4, filp->f_pos, ino, DT_LNK) < 0) - return 0; - filp->f_pos++; - nr++; - } - - /* f_version caches the tgid value that the last readdir call couldn't - * return. lseek aka telldir automagically resets f_version to 0. - */ - next_tgid = filp->f_version; - filp->f_version = 0; - for (;;) { - nr_tgids = get_tgid_list(nr, next_tgid, tgid_array); - if (!nr_tgids) { - /* no more entries ! */ - break; - } - next_tgid = 0; - - /* do not use the last found pid, reserve it for next_tgid */ - if (nr_tgids == PROC_MAXPIDS) { - nr_tgids--; - next_tgid = tgid_array[nr_tgids]; - } - - for (i=0;if_pos, ino, DT_DIR) < 0) { - /* returning this tgid failed, save it as the first - * pid for the next readir call */ - filp->f_version = tgid_array[i]; - goto out; - } - filp->f_pos++; - nr++; - } - } -out: - return 0; + char name[PROC_NUMBUF]; + int len = snprintf(name, sizeof(name), "%d", tid); + return proc_fill_cache(filp, dirent, filldir, name, len, + proc_task_instantiate, task, NULL); } /* for the /proc/TGID/task/ directories */ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldir) { - unsigned int tid_array[PROC_MAXPIDS]; - char buf[PROC_NUMBUF]; - unsigned int nr_tids, i; - struct dentry *dentry = filp->f_dentry; + struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; - struct task_struct *task = proc_task(inode); + struct task_struct *leader = NULL; + struct task_struct *task; int retval = -ENOENT; ino_t ino; + int tid; unsigned long pos = filp->f_pos; /* avoiding "long long" filp->f_pos */ - if (!vx_check(vx_task_xid(task), VX_WATCH|VX_IDENT)) - goto out; - if (!pid_alive(task)) - goto out; + task = get_proc_task(inode); + if (!task) + goto out_no_task; + rcu_read_lock(); + if (pid_alive(task)) { + leader = task->group_leader; + get_task_struct(leader); + } + rcu_read_unlock(); + put_task_struct(task); + if (!leader) + goto out_no_task; retval = 0; switch (pos) { @@ -2370,24 +2447,53 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi /* fall through */ } - nr_tids = get_tid_list(pos, tid_array, inode); - inode->i_nlink = pos + nr_tids; - - for (i = 0; i < nr_tids; i++) { - unsigned long j = PROC_NUMBUF; - int tid = tid_array[i]; - - ino = fake_ino(tid,PROC_TID_INO); - - do - buf[--j] = '0' + (tid % 10); - while ((tid /= 10) != 0); - - if (filldir(dirent, buf+j, PROC_NUMBUF-j, pos, ino, DT_DIR) < 0) + /* f_version caches the tgid value that the last readdir call couldn't + * return. lseek aka telldir automagically resets f_version to 0. + */ + tid = filp->f_version; + filp->f_version = 0; + for (task = first_tid(leader, tid, pos - 2); + task; + task = next_tid(task), pos++) { + tid = vx_map_pid(task->pid); + if (proc_task_fill_cache(filp, dirent, filldir, task, tid) < 0) { + /* returning this tgid failed, save it as the first + * pid for the next readir call */ + filp->f_version = tid; + put_task_struct(task); break; - pos++; + } } out: filp->f_pos = pos; + put_task_struct(leader); +out_no_task: return retval; } + +static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +{ + struct inode *inode = dentry->d_inode; + struct task_struct *p = get_proc_task(inode); + generic_fillattr(inode, stat); + + if (p) { + rcu_read_lock(); + stat->nlink += get_nr_threads(p); + rcu_read_unlock(); + put_task_struct(p); + } + + return 0; +} + +static struct inode_operations proc_task_inode_operations = { + .lookup = proc_task_lookup, + .getattr = proc_task_getattr, + .setattr = proc_setattr, +}; + +static struct file_operations proc_task_operations = { + .read = generic_read_dir, + .readdir = proc_task_readdir, +};