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;
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);
.follow_link = proc_pid_follow_link
};
-#define NUMBUF 10
-
static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir)
{
struct dentry *dentry = filp->f_dentry;
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;
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;
}
{
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;
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:
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 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;
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));
}
void proc_flush_task(struct task_struct *task)
{
struct dentry *dentry, *leader, *dir;
- char buf[30];
+ char buf[PROC_NUMBUF];
struct qstr name;
name.name = buf;
/* 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;
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;
dentry->d_op = &pid_dentry_operations;
d_add(dentry, inode);
- if (!pid_alive(task)) {
- d_drop(dentry);
- shrink_dcache_parent(dentry);
- goto out;
- }
+ /* 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);
- 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)
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);
-
- 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;