#include <linux/poll.h>
#include "internal.h"
+/* 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.
+ */
+
/*
* 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
PROC_TGID_ATTR_PREV,
PROC_TGID_ATTR_EXEC,
PROC_TGID_ATTR_FSCREATE,
+ PROC_TGID_ATTR_KEYCREATE,
#endif
#ifdef CONFIG_AUDITSYSCALL
PROC_TGID_LOGINUID,
PROC_TID_ATTR_PREV,
PROC_TID_ATTR_EXEC,
PROC_TID_ATTR_FSCREATE,
+ PROC_TID_ATTR_KEYCREATE,
#endif
#ifdef CONFIG_AUDITSYSCALL
PROC_TID_LOGINUID,
PROC_TID_FD_DIR = 0x8000, /* 0x8000-0xffff */
};
+/* Worst case buffer size needed for holding an integer. */
+#define PROC_NUMBUF 10
+
struct pid_entry {
int type;
int len;
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),
+ E(PROC_TGID_ATTR_KEYCREATE, "keycreate", S_IFREG|S_IRUGO|S_IWUGO),
{0,0,NULL,0}
};
static struct pid_entry tid_attr_stuff[] = {
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),
+ E(PROC_TID_ATTR_KEYCREATE, "keycreate", S_IFREG|S_IRUGO|S_IWUGO),
{0,0,NULL,0}
};
#endif
struct task_struct *task = proc_task(inode);
struct files_struct *files;
struct file *file;
- int fd = proc_type(inode) - PROC_TID_FD_DIR;
+ int fd = proc_fd(inode);
files = get_files_struct(task);
if (files) {
- rcu_read_lock();
+ /*
+ * 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);
- rcu_read_unlock();
+ spin_unlock(&files->file_lock);
put_files_struct(files);
return 0;
}
- rcu_read_unlock();
+ spin_unlock(&files->file_lock);
put_files_struct(files);
}
return -ENOENT;
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;
- 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 (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;
-}
-
-
#define MAY_PTRACE(task) \
(task == current || \
(task->parent == current && \
/* If the process being read is separated by chroot from the reading process,
* don't let the reader access the threads.
- *
- * note: this does dput(root) and mntput(vfsmnt) on exit.
*/
-static int proc_check_chroot(struct dentry *root, struct vfsmount *vfsmnt)
+static int proc_check_chroot(struct dentry *de, struct vfsmount *mnt)
{
- struct dentry *de, *base;
- struct vfsmount *our_vfsmnt, *mnt;
+ struct dentry *base;
+ struct vfsmount *our_vfsmnt;
int res = 0;
read_lock(¤t->fs->lock);
read_unlock(¤t->fs->lock);
spin_lock(&vfsmount_lock);
- de = root;
- mnt = vfsmnt;
while (mnt != our_vfsmnt) {
if (mnt == mnt->mnt_parent)
exit:
dput(base);
mntput(our_vfsmnt);
- dput(root);
- mntput(vfsmnt);
return res;
out:
spin_unlock(&vfsmount_lock);
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);
-}
-
-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;
size_t count, loff_t *ppos)
{
struct task_struct *task = proc_task(file->f_dentry->d_inode);
- char buffer[8];
+ char buffer[PROC_NUMBUF];
size_t len;
int oom_adjust = task->oomkilladj;
loff_t __ppos = *ppos;
- len = sprintf(buffer, "%i\n", oom_adjust);
+ len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust);
if (__ppos >= len)
return 0;
if (count > len-__ppos)
size_t count, loff_t *ppos)
{
struct task_struct *task = proc_task(file->f_dentry->d_inode);
- char buffer[8], *end;
+ 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);
.write = oom_adjust_write,
};
-static struct inode_operations proc_mem_inode_operations = {
- .permission = proc_permission,
-};
-
#ifdef CONFIG_AUDITSYSCALL
#define TMPBUFLEN 21
static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
if (current != task)
return -EPERM;
- if (count > PAGE_SIZE)
- count = PAGE_SIZE;
+ if (count >= PAGE_SIZE)
+ count = PAGE_SIZE - 1;
if (*ppos != 0) {
/* No partial writes. */
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;
};
#endif /* CONFIG_SECCOMP */
+static int proc_check_dentry_visible(struct inode *inode,
+ struct dentry *dentry, struct vfsmount *mnt)
+{
+ /* Verify that the current process can already see the
+ * file pointed at by the file descriptor.
+ * This prevents /proc from being an accidental information leak.
+ *
+ * This prevents access to files that are not visible do to
+ * being on the otherside of a chroot, in a different
+ * namespace, or are simply process local (like pipes).
+ */
+ struct task_struct *task;
+ struct files_struct *task_files, *files;
+ int error = -EACCES;
+
+ /* See if the the two tasks share a commone set of
+ * file descriptors. If so everything is visible.
+ */
+ task = proc_task(inode);
+ if (!task)
+ goto out;
+ files = get_files_struct(current);
+ task_files = get_files_struct(task);
+ if (files && task_files && (files == task_files))
+ error = 0;
+ if (task_files)
+ put_files_struct(task_files);
+ if (files)
+ put_files_struct(files);
+ if (!error)
+ goto out;
+
+ /* If the two tasks don't share a common set of file
+ * descriptors see if the destination dentry is already
+ * visible in the current tasks filesystem namespace.
+ */
+ error = proc_check_chroot(dentry, mnt);
+out:
+ return error;
+
+}
+
static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
{
struct inode *inode = dentry->d_inode;
if (current->fsuid != inode->i_uid && !capable(CAP_DAC_OVERRIDE))
goto out;
- error = proc_check_root(inode);
- if (error)
- goto out;
error = PROC_I(inode)->op.proc_get_link(inode, &nd->dentry, &nd->mnt);
nd->last_type = LAST_BIND;
+ if (error)
+ goto out;
+
+ /* Only return files this task can already see */
+ error = proc_check_dentry_visible(inode, nd->dentry, nd->mnt);
+ if (error)
+ path_release(nd);
out:
return ERR_PTR(error);
}
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)
- goto out;
error = PROC_I(inode)->op.proc_get_link(inode, &de, &mnt);
if (error)
goto out;
+ /* Only return files this task can already see */
+ error = proc_check_dentry_visible(inode, de, mnt);
+ if (error)
+ goto out_put;
+
error = do_proc_readlink(de, mnt, buffer, buflen);
+out_put:
dput(de);
mntput(mnt);
out:
- unlock_kernel();
return error;
}
.follow_link = proc_pid_follow_link
};
-#define NUMBUF 10
-
static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct dentry *dentry = filp->f_dentry;
+ struct inode *inode = dentry->d_inode;
struct task_struct *p = proc_task(inode);
unsigned int fd, tid, ino;
int retval;
- char buf[NUMBUF];
+ char buf[PROC_NUMBUF];
struct files_struct * files;
struct fdtable *fdt;
goto out;
filp->f_pos++;
case 1:
- ino = fake_ino(tid, PROC_TID_INO);
+ ino = parent_ino(dentry);
if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0)
goto out;
filp->f_pos++;
continue;
rcu_read_unlock();
- j = NUMBUF;
+ j = PROC_NUMBUF;
i = fd;
do {
j--;
} while (i);
ino = fake_ino(tid, PROC_TID_FD_DIR + fd);
- if (filldir(dirent, buf+j, NUMBUF-j, fd+2, ino, DT_LNK) < 0) {
+ if (filldir(dirent, buf+j, PROC_NUMBUF-j, fd+2, ino, DT_LNK) < 0) {
rcu_read_lock();
break;
}
/* 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);
*/
get_task_struct(task);
ei->task = task;
- ei->type = ino;
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;
}
return inode;
out_unlock:
- ei->pde = NULL;
iput(inode);
return NULL;
}
struct inode *inode = dentry->d_inode;
struct task_struct *task = proc_task(inode);
if (pid_alive(task)) {
- if (proc_type(inode) == PROC_TGID_INO || proc_type(inode) == PROC_TID_INO || task_dumpable(task)) {
+ if (task_dumpable(task)) {
inode->i_uid = task->euid;
inode->i_gid = task->egid;
} else {
{
struct inode *inode = dentry->d_inode;
struct task_struct *task = proc_task(inode);
- int fd = proc_type(inode) - PROC_TID_FD_DIR;
+ int fd = proc_fd(inode);
struct files_struct *files;
files = get_files_struct(task);
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?
.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)
{
struct task_struct *task = proc_task(dir);
unsigned fd = name_to_int(dentry);
+ struct dentry *result = ERR_PTR(-ENOENT);
struct file * file;
struct files_struct * files;
struct inode *inode;
if (!inode)
goto out;
ei = PROC_I(inode);
+ ei->fd = fd;
files = get_files_struct(task);
if (!files)
goto out_unlock;
inode->i_mode = S_IFLNK;
- rcu_read_lock();
+
+ /*
+ * 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)
goto out_unlock2;
inode->i_mode |= S_IRUSR | S_IXUSR;
if (file->f_mode & 2)
inode->i_mode |= S_IWUSR | S_IXUSR;
- rcu_read_unlock();
+ 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))
+ result = NULL;
+out:
+ return result;
out_unlock2:
- rcu_read_unlock();
+ spin_unlock(&files->file_lock);
put_files_struct(files);
out_unlock:
iput(inode);
-out:
- return ERR_PTR(-ENOENT);
+ goto out;
}
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_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat);
static struct file_operations proc_fd_operations = {
.read = generic_read_dir,
*/
static struct inode_operations proc_fd_inode_operations = {
.lookup = proc_lookupfd,
- .permission = proc_permission,
};
static struct inode_operations proc_task_inode_operations = {
.lookup = proc_task_lookup,
- .permission = proc_task_permission,
+ .getattr = proc_task_getattr,
};
#ifdef CONFIG_SECURITY
static struct inode_operations proc_tgid_attr_inode_operations;
#endif
-static int get_tid_list(int index, unsigned int *tids, struct inode *dir);
-
/* SMP-safe */
static struct dentry *proc_pident_lookup(struct inode *dir,
struct dentry *dentry,
struct pid_entry *ents)
{
struct inode *inode;
- int error;
+ struct dentry *error;
struct task_struct *task = proc_task(dir);
struct pid_entry *p;
struct proc_inode *ei;
- error = -ENOENT;
+ error = ERR_PTR(-ENOENT);
inode = NULL;
if (!pid_alive(task))
if (!p->name)
goto out;
- error = -EINVAL;
+ error = ERR_PTR(-EINVAL);
inode = proc_pid_make_inode(dir->i_sb, task, p->type);
if (!inode)
goto out;
*/
switch(p->type) {
case PROC_TGID_TASK:
- inode->i_nlink = 2 + get_tid_list(2, NULL, dir);
+ inode->i_nlink = 2;
inode->i_op = &proc_task_inode_operations;
inode->i_fop = &proc_task_operations;
break;
#endif
case PROC_TID_MEM:
case PROC_TGID_MEM:
- inode->i_op = &proc_mem_inode_operations;
inode->i_fop = &proc_mem_operations;
break;
#ifdef CONFIG_SECCOMP
case PROC_TGID_ATTR_EXEC:
case PROC_TID_ATTR_FSCREATE:
case PROC_TGID_ATTR_FSCREATE:
+ case PROC_TID_ATTR_KEYCREATE:
+ case PROC_TGID_ATTR_KEYCREATE:
inode->i_fop = &proc_pid_attr_operations;
break;
#endif
default:
printk("procfs: impossible type (%d)",p->type);
iput(inode);
- return ERR_PTR(-EINVAL);
+ error = ERR_PTR(-EINVAL);
+ goto out;
}
dentry->d_op = &pid_dentry_operations;
d_add(dentry, inode);
- return NULL;
-
+ /* Close the race of the process dying before we return the dentry */
+ if (pid_revalidate(dentry, NULL))
+ error = NULL;
out:
- return ERR_PTR(error);
+ return error;
}
static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
int buflen)
{
- char tmp[30];
+ char tmp[PROC_NUMBUF];
sprintf(tmp, "%d", current->tgid);
return vfs_readlink(dentry,buffer,buflen,tmp);
}
static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
{
- char tmp[30];
+ char tmp[PROC_NUMBUF];
sprintf(tmp, "%d", current->tgid);
return ERR_PTR(vfs_follow_link(nd,tmp));
}
};
/**
- * proc_pid_unhash - Unhash /proc/@pid entry from the dcache.
- * @p: task that should be flushed.
+ * proc_flush_task - Remove dcache entries for @task from the /proc dcache.
*
- * Drops the /proc/@pid dcache entry from the hash chains.
+ * @task: task that should be flushed.
*
- * 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.
+ * 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.
*/
-
-struct dentry *proc_pid_unhash(struct task_struct *p)
+void proc_flush_task(struct task_struct *task)
{
- struct dentry *proc_dentry;
+ 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);
+ }
- proc_dentry = p->proc_dentry;
- if (proc_dentry != NULL) {
+ if (thread_group_leader(task))
+ goto out;
- 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;
- }
- spin_unlock(&dcache_lock);
- }
- return proc_dentry;
-}
+ 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;
-/**
- * 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.
- */
-
-void proc_pid_flush(struct dentry *proc_dentry)
-{
- might_sleep();
- if(proc_dentry != NULL) {
- shrink_dcache_parent(proc_dentry);
- dput(proc_dentry);
+ 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;
}
/* SMP-safe */
struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
{
+ struct dentry *result = ERR_PTR(-ENOENT);
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 (tgid == ~0U)
goto out;
- read_lock(&tasklist_lock);
+ rcu_read_lock();
task = find_task_by_pid(tgid);
if (task)
get_task_struct(task);
- read_unlock(&tasklist_lock);
+ rcu_read_unlock();
if (!task)
goto out;
inode = proc_pid_make_inode(dir->i_sb, task, PROC_TGID_INO);
+ if (!inode)
+ goto out_put_task;
-
- if (!inode) {
- put_task_struct(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_nlink = 4;
#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);
+ /* Close the race of the process dying before we return the dentry */
+ if (pid_revalidate(dentry, NULL))
+ result = NULL;
+out_put_task:
put_task_struct(task);
- if (died) {
- proc_pid_flush(dentry);
- goto out;
- }
- return NULL;
out:
- return ERR_PTR(-ENOENT);
+ return result;
}
/* 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;
if (tid == ~0U)
goto out;
- read_lock(&tasklist_lock);
+ rcu_read_lock();
task = find_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)
inode->i_nlink = 3;
#endif
- dentry->d_op = &pid_base_dentry_operations;
+ 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))
+ result = NULL;
- put_task_struct(task);
- return NULL;
out_drop_task:
put_task_struct(task);
out:
- return ERR_PTR(-ENOENT);
+ 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 tgid to return to user space.
+ *
+ * Usually this is just whatever follows &init_task, but if the users
+ * buffer was too small to hold the full list or there was a seek into
+ * the middle of the directory we have more work to do.
+ *
+ * In the case of a short read we start with find_task_by_pid.
+ *
+ * In the case of a seek we start with &init_task and walk nr
+ * threads past it.
*/
-static int get_tgid_list(int index, unsigned long version, unsigned int *tgids)
+static struct task_struct *first_tgid(int tgid, unsigned int nr)
{
- struct task_struct *p;
- int nr_tgids = 0;
-
- index--;
- read_lock(&tasklist_lock);
- p = NULL;
- if (version) {
- p = find_task_by_pid(version);
- if (p && !thread_group_leader(p))
- p = NULL;
+ struct task_struct *pos;
+ rcu_read_lock();
+ if (tgid && nr) {
+ pos = find_task_by_pid(tgid);
+ if (pos && thread_group_leader(pos))
+ goto found;
}
+ /* If nr exceeds the number of processes get out quickly */
+ pos = NULL;
+ if (nr && nr >= nr_processes())
+ goto done;
- if (p)
- index = 0;
- else
- p = next_task(&init_task);
-
- for ( ; p != &init_task; p = next_task(p)) {
- int tgid = p->pid;
- if (!pid_alive(p))
- continue;
- if (--index >= 0)
- continue;
- tgids[nr_tgids] = tgid;
- nr_tgids++;
- if (nr_tgids >= PROC_MAXPIDS)
- break;
+ /* If we haven't found our starting place yet start with
+ * the init_task and walk nr tasks forward.
+ */
+ for (pos = next_task(&init_task); nr > 0; --nr) {
+ pos = next_task(pos);
+ if (pos == &init_task) {
+ pos = NULL;
+ goto done;
+ }
}
- read_unlock(&tasklist_lock);
- return nr_tgids;
+found:
+ get_task_struct(pos);
+done:
+ 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 task in the task list.
+ * Return NULL if we loop or there is any error.
+ *
+ * The reference to the input task_struct is released.
*/
-static int get_tid_list(int index, unsigned int *tids, struct inode *dir)
+static struct task_struct *next_tgid(struct task_struct *start)
{
- 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;
-
- if (--index >= 0)
- continue;
- if (tids != NULL)
- tids[nr_tids] = tid;
- nr_tids++;
- if (nr_tids >= PROC_MAXPIDS)
- break;
- } while ((task = next_thread(task)) != leader_task);
- read_unlock(&tasklist_lock);
- return nr_tids;
+ struct task_struct *pos;
+ rcu_read_lock();
+ pos = start;
+ if (pid_alive(start))
+ pos = next_task(start);
+ if (pid_alive(pos) && (pos != &init_task)) {
+ get_task_struct(pos);
+ goto done;
+ }
+ pos = NULL;
+done:
+ 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)
{
- 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;
+ struct task_struct *task;
+ int tgid;
if (!nr) {
ino_t ino = fake_ino(0,PROC_TGID_INO);
filp->f_pos++;
nr++;
}
+ nr -= 1;
/* 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;
+ 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 ! */
+ for (task = first_tgid(tgid, nr);
+ task;
+ task = next_tgid(task), filp->f_pos++) {
+ int len;
+ ino_t ino;
+ tgid = task->pid;
+ len = snprintf(buf, sizeof(buf), "%d", tgid);
+ ino = fake_ino(tgid, PROC_TGID_INO);
+ if (filldir(dirent, buf, len, filp->f_pos, ino, DT_DIR) < 0) {
+ /* returning this tgid failed, save it as the first
+ * pid for the next readir call */
+ filp->f_version = tgid;
+ put_task_struct(task);
break;
}
- next_tgid = 0;
+ }
+ return 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];
- }
+/*
+ * 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 struct task_struct *first_tid(struct task_struct *leader, int tid, int nr)
+{
+ struct task_struct *pos = NULL;
+ read_lock(&tasklist_lock);
- for (i=0;i<nr_tgids;i++) {
- int tgid = tgid_array[i];
- ino_t ino = fake_ino(tgid,PROC_TGID_INO);
- unsigned long j = PROC_NUMBUF;
+ /* 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))
+ pos = NULL;
+ if (pos)
+ nr = 0;
+ }
- do
- buf[--j] = '0' + (tgid % 10);
- while ((tgid /= 10) != 0);
+ /* If nr exceeds the number of threads there is nothing todo */
+ if (nr) {
+ int threads = 0;
+ task_lock(leader);
+ if (leader->signal)
+ threads = atomic_read(&leader->signal->count);
+ task_unlock(leader);
+ if (nr >= threads)
+ goto done;
+ }
- if (filldir(dirent, buf+j, PROC_NUMBUF-j, filp->f_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++;
- }
+ /* If we haven't found our starting place yet start with the
+ * leader and walk nr threads forward.
+ */
+ if (!pos && (nr >= 0))
+ pos = leader;
+
+ for (; pos && pid_alive(pos); pos = next_thread(pos)) {
+ if (--nr > 0)
+ continue;
+ get_task_struct(pos);
+ goto done;
}
-out:
- return 0;
+ pos = NULL;
+done:
+ read_unlock(&tasklist_lock);
+ return pos;
+}
+
+/*
+ * 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 struct task_struct *next_tid(struct task_struct *start)
+{
+ struct task_struct *pos;
+ read_lock(&tasklist_lock);
+ pos = start;
+ if (pid_alive(start))
+ pos = next_thread(start);
+ if (pid_alive(pos) && (pos != start->group_leader))
+ get_task_struct(pos);
+ else
+ pos = NULL;
+ read_unlock(&tasklist_lock);
+ put_task_struct(start);
+ return pos;
}
/* 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 inode *inode = dentry->d_inode;
+ struct task_struct *leader = proc_task(inode);
+ 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 (!pid_alive(proc_task(inode)))
+ if (!pid_alive(leader))
goto out;
retval = 0;
/* 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++) {
+ int len;
+ tid = task->pid;
+ len = snprintf(buf, sizeof(buf), "%d", tid);
+ ino = fake_ino(tid, PROC_TID_INO);
+ if (filldir(dirent, buf, len, pos, ino, DT_DIR < 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;
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 = proc_task(inode);
+ generic_fillattr(inode, stat);
+
+ if (pid_alive(p)) {
+ task_lock(p);
+ if (p->signal)
+ stat->nlink += atomic_read(&p->signal->count);
+ task_unlock(p);
+ }
+
+ return 0;
+}