#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
+#include <linux/task_io_accounting_ops.h>
#include <linux/init.h>
#include <linux/capability.h>
#include <linux/file.h>
+#include <linux/fdtable.h>
#include <linux/string.h>
#include <linux/seq_file.h>
#include <linux/namei.h>
#include <linux/mm.h>
#include <linux/rcupdate.h>
#include <linux/kallsyms.h>
+#include <linux/stacktrace.h>
#include <linux/resource.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/ptrace.h>
+#include <linux/tracehook.h>
#include <linux/cgroup.h>
#include <linux/cpuset.h>
#include <linux/audit.h>
#include <linux/oom.h>
#include <linux/elf.h>
#include <linux/pid_namespace.h>
+#include <linux/fs_struct.h>
+#include <linux/slab.h>
#include "internal.h"
/* NOTE:
.op = OP, \
}
-#define DIR(NAME, MODE, OTYPE) \
- NOD(NAME, (S_IFDIR|(MODE)), \
- &proc_##OTYPE##_inode_operations, &proc_##OTYPE##_operations, \
- {} )
-#define LNK(NAME, OTYPE) \
+#define DIR(NAME, MODE, iops, fops) \
+ NOD(NAME, (S_IFDIR|(MODE)), &iops, &fops, {} )
+#define LNK(NAME, get_link) \
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) \
+ { .proc_get_link = get_link } )
+#define REG(NAME, MODE, fops) \
+ NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {})
+#define INF(NAME, MODE, read) \
NOD(NAME, (S_IFREG|(MODE)), \
NULL, &proc_info_file_operations, \
- { .proc_read = &proc_##OTYPE } )
-#define ONE(NAME, MODE, OTYPE) \
+ { .proc_read = read } )
+#define ONE(NAME, MODE, show) \
NOD(NAME, (S_IFREG|(MODE)), \
NULL, &proc_single_file_operations, \
- { .proc_show = &proc_##OTYPE } )
+ { .proc_show = show } )
-int maps_protect;
-EXPORT_SYMBOL(maps_protect);
+/*
+ * Count the number of hardlinks for the pid_entry table, excluding the .
+ * and .. links.
+ */
+static unsigned int pid_entry_count_dirs(const struct pid_entry *entries,
+ unsigned int n)
+{
+ unsigned int i;
+ unsigned int count;
+
+ count = 0;
+ for (i = 0; i < n; ++i) {
+ if (S_ISDIR(entries[i].mode))
+ ++count;
+ }
+
+ return count;
+}
-static struct fs_struct *get_fs_struct(struct task_struct *task)
+static int get_fs_path(struct task_struct *task, struct path *path, bool root)
{
struct fs_struct *fs;
+ int result = -ENOENT;
+
task_lock(task);
fs = task->fs;
- if(fs)
- atomic_inc(&fs->count);
+ if (fs) {
+ read_lock(&fs->lock);
+ *path = root ? fs->root : fs->pwd;
+ path_get(path);
+ read_unlock(&fs->lock);
+ result = 0;
+ }
task_unlock(task);
- return fs;
+ return result;
}
static int get_nr_threads(struct task_struct *tsk)
{
- /* Must be called with the rcu_read_lock held */
unsigned long flags;
int count = 0;
static int proc_cwd_link(struct inode *inode, struct path *path)
{
struct task_struct *task = get_proc_task(inode);
- struct fs_struct *fs = NULL;
int result = -ENOENT;
if (task) {
- fs = get_fs_struct(task);
+ result = get_fs_path(task, path, 0);
put_task_struct(task);
}
- if (fs) {
- read_lock(&fs->lock);
- *path = fs->pwd;
- path_get(&fs->pwd);
- read_unlock(&fs->lock);
- result = 0;
- put_fs_struct(fs);
- }
return result;
}
static int proc_root_link(struct inode *inode, struct path *path)
{
struct task_struct *task = get_proc_task(inode);
- struct fs_struct *fs = NULL;
int result = -ENOENT;
if (task) {
- fs = get_fs_struct(task);
+ result = get_fs_path(task, path, 1);
put_task_struct(task);
}
- if (fs) {
- read_lock(&fs->lock);
- *path = fs->root;
- path_get(&fs->root);
- read_unlock(&fs->lock);
- result = 0;
- put_fs_struct(fs);
- }
return result;
}
-#define MAY_PTRACE(task) \
- (task == current || \
- (task->parent == current && \
- (task->ptrace & PT_PTRACED) && \
- (task_is_stopped_or_traced(task)) && \
- security_ptrace(current,task) == 0))
+/*
+ * Return zero if current may access user memory in @task, -error if not.
+ */
+static int check_mem_permission(struct task_struct *task)
+{
+ /*
+ * A task can always look at itself, in case it chooses
+ * to use system calls instead of load instructions.
+ */
+ if (task == current)
+ return 0;
+
+ /*
+ * If current is actively ptrace'ing, and would also be
+ * permitted to freshly attach with ptrace now, permit it.
+ */
+ if (task_is_stopped_or_traced(task)) {
+ int match;
+ rcu_read_lock();
+ match = (tracehook_tracer_task(task) == current);
+ rcu_read_unlock();
+ if (match && ptrace_may_access(task, PTRACE_MODE_ATTACH))
+ return 0;
+ }
+
+ /*
+ * Noone else is allowed.
+ */
+ return -EPERM;
+}
struct mm_struct *mm_for_maps(struct task_struct *task)
{
- struct mm_struct *mm = get_task_mm(task);
- if (!mm)
+ struct mm_struct *mm;
+
+ if (mutex_lock_killable(&task->cred_guard_mutex))
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);
+
+ mm = get_task_mm(task);
+ if (mm && mm != current->mm &&
+ !ptrace_may_access(task, PTRACE_MODE_READ)) {
+ mmput(mm);
+ mm = NULL;
+ }
+ mutex_unlock(&task->cred_guard_mutex);
+
return mm;
-out:
- task_unlock(task);
- up_read(&mm->mmap_sem);
- mmput(mm);
- return NULL;
}
static int proc_pid_cmdline(struct task_struct *task, char * buffer)
struct mm_struct *mm = get_task_mm(task);
if (mm) {
unsigned int nwords = 0;
- do
+ do {
nwords += 2;
- while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
+ } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
res = nwords * sizeof(mm->saved_auxv[0]);
if (res > PAGE_SIZE)
res = PAGE_SIZE;
wchan = get_wchan(task);
if (lookup_symbol_name(wchan, symname) < 0)
- return sprintf(buffer, "%lu", wchan);
+ if (!ptrace_may_access(task, PTRACE_MODE_READ))
+ return 0;
+ else
+ return sprintf(buffer, "%lu", wchan);
else
return sprintf(buffer, "%s", symname);
}
#endif /* CONFIG_KALLSYMS */
+#ifdef CONFIG_STACKTRACE
+
+#define MAX_STACK_TRACE_DEPTH 64
+
+static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
+{
+ struct stack_trace trace;
+ unsigned long *entries;
+ int i;
+
+ entries = kmalloc(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL);
+ if (!entries)
+ return -ENOMEM;
+
+ trace.nr_entries = 0;
+ trace.max_entries = MAX_STACK_TRACE_DEPTH;
+ trace.entries = entries;
+ trace.skip = 0;
+ save_stack_trace_tsk(task, &trace);
+
+ for (i = 0; i < trace.nr_entries; i++) {
+ seq_printf(m, "[<%p>] %pS\n",
+ (void *)entries[i], (void *)entries[i]);
+ }
+ kfree(entries);
+
+ return 0;
+}
+#endif
+
#ifdef CONFIG_SCHEDSTATS
/*
* Provides /proc/PID/schedstat
static int proc_pid_schedstat(struct task_struct *task, char *buffer)
{
return sprintf(buffer, "%llu %llu %lu\n",
- task->sched_info.cpu_time,
- task->sched_info.run_delay,
+ (unsigned long long)task->se.sum_exec_runtime,
+ (unsigned long long)task->sched_info.run_delay,
task->sched_info.pcount);
}
#endif
task->latency_record[i].time,
task->latency_record[i].max);
for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
- char sym[KSYM_NAME_LEN];
+ char sym[KSYM_SYMBOL_LEN];
char *c;
if (!task->latency_record[i].backtrace[q])
break;
unsigned long badness(struct task_struct *p, unsigned long uptime);
static int proc_oom_score(struct task_struct *task, char *buffer)
{
- unsigned long points;
+ unsigned long points = 0;
struct timespec uptime;
do_posix_clock_monotonic_gettime(&uptime);
read_lock(&tasklist_lock);
- points = badness(task, uptime.tv_sec);
+ if (pid_alive(task))
+ points = badness(task, uptime.tv_sec);
read_unlock(&tasklist_lock);
return sprintf(buffer, "%lu\n", points);
}
};
static const struct limit_names lnames[RLIM_NLIMITS] = {
- [RLIMIT_CPU] = {"Max cpu time", "ms"},
+ [RLIMIT_CPU] = {"Max cpu time", "seconds"},
[RLIMIT_FSIZE] = {"Max file size", "bytes"},
[RLIMIT_DATA] = {"Max data size", "bytes"},
[RLIMIT_STACK] = {"Max stack size", "bytes"},
struct rlimit rlim[RLIM_NLIMITS];
- rcu_read_lock();
- if (!lock_task_sighand(task,&flags)) {
- rcu_read_unlock();
+ if (!lock_task_sighand(task, &flags))
return 0;
- }
memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS);
unlock_task_sighand(task, &flags);
- rcu_read_unlock();
/*
* print the file header
return count;
}
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+static int proc_pid_syscall(struct task_struct *task, char *buffer)
+{
+ long nr;
+ unsigned long args[6], sp, pc;
+
+ if (task_current_syscall(task, &nr, args, 6, &sp, &pc))
+ return sprintf(buffer, "running\n");
+
+ if (nr < 0)
+ return sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
+
+ return sprintf(buffer,
+ "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n",
+ nr,
+ args[0], args[1], args[2], args[3], args[4], args[5],
+ sp, pc);
+}
+#endif /* CONFIG_HAVE_ARCH_TRACEHOOK */
+
/************************************************************************/
/* Here the fs part begins */
/************************************************************************/
*/
task = get_proc_task(inode);
if (task) {
- allowed = ptrace_may_attach(task);
+ allowed = ptrace_may_access(task, PTRACE_MODE_READ);
put_task_struct(task);
}
return allowed;
struct task_struct *task = get_proc_task(inode);
struct nsproxy *nsp;
struct mnt_namespace *ns = NULL;
- struct fs_struct *fs = NULL;
struct path root;
struct proc_mounts *p;
int ret = -EINVAL;
get_mnt_ns(ns);
}
rcu_read_unlock();
- if (ns)
- fs = get_fs_struct(task);
+ if (ns && get_fs_path(task, &root, 1) == 0)
+ ret = 0;
put_task_struct(task);
}
if (!ns)
goto err;
- if (!fs)
+ if (ret)
goto err_put_ns;
- read_lock(&fs->lock);
- root = fs->root;
- path_get(&root);
- read_unlock(&fs->lock);
- put_fs_struct(fs);
-
ret = -ENOMEM;
p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL);
if (!p)
static unsigned mounts_poll(struct file *file, poll_table *wait)
{
struct proc_mounts *p = file->private_data;
- struct mnt_namespace *ns = p->ns;
- unsigned res = 0;
-
- poll_wait(file, &ns->poll, wait);
+ unsigned res = POLLIN | POLLRDNORM;
- spin_lock(&vfsmount_lock);
- if (p->event != ns->event) {
- p->event = ns->event;
- res = POLLERR;
- }
- spin_unlock(&vfsmount_lock);
+ poll_wait(file, &p->ns->poll, wait);
+ if (mnt_had_events(p))
+ res |= POLLERR | POLLPRI;
return res;
}
static const struct file_operations proc_info_file_operations = {
.read = proc_info_read,
+ .llseek = generic_file_llseek,
};
static int proc_single_show(struct seq_file *m, void *v)
if (!task)
goto out_no_task;
- if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
+ if (check_mem_permission(task))
goto out;
ret = -ENOMEM;
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 || check_mem_permission(task)) {
if (!ret)
ret = -EIO;
break;
if (!task)
goto out_no_task;
- if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
+ if (check_mem_permission(task))
goto out;
copied = -ENOMEM;
if (!task)
goto out_no_task;
- if (!ptrace_may_attach(task))
+ if (!ptrace_may_access(task, PTRACE_MODE_READ))
goto out;
ret = -ENOMEM;
static const struct file_operations proc_environ_operations = {
.read = environ_read,
+ .llseek = generic_file_llseek,
};
static ssize_t oom_adjust_read(struct file *file, char __user *buf,
struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
char buffer[PROC_NUMBUF];
size_t len;
- int oom_adjust;
+ int oom_adjust = OOM_DISABLE;
+ unsigned long flags;
if (!task)
return -ESRCH;
- oom_adjust = task->oomkilladj;
+
+ if (lock_task_sighand(task, &flags)) {
+ oom_adjust = task->signal->oom_adj;
+ unlock_task_sighand(task, &flags);
+ }
+
put_task_struct(task);
len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust);
size_t count, loff_t *ppos)
{
struct task_struct *task;
- char buffer[PROC_NUMBUF], *end;
- int oom_adjust;
+ char buffer[PROC_NUMBUF];
+ long oom_adjust;
+ unsigned long flags;
+ int err;
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);
+
+ err = strict_strtol(strstrip(buffer), 0, &oom_adjust);
+ if (err)
+ return -EINVAL;
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)) {
+ if (!lock_task_sighand(task, &flags)) {
+ put_task_struct(task);
+ return -ESRCH;
+ }
+
+ if (oom_adjust < task->signal->oom_adj && !capable(CAP_SYS_RESOURCE)) {
+ unlock_task_sighand(task, &flags);
put_task_struct(task);
return -EACCES;
}
- task->oomkilladj = oom_adjust;
+
+ task->signal->oom_adj = oom_adjust;
+
+ unlock_task_sighand(task, &flags);
put_task_struct(task);
- if (end - buffer == 0)
- return -EIO;
- return end - buffer;
+
+ return count;
}
static const struct file_operations proc_oom_adjust_operations = {
.read = oom_adjust_read,
.write = oom_adjust_write,
+ .llseek = generic_file_llseek,
};
#ifdef CONFIG_AUDITSYSCALL
if (!capable(CAP_AUDIT_CONTROL))
return -EPERM;
- if (current != pid_task(proc_pid(inode), PIDTYPE_PID))
+ rcu_read_lock();
+ if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) {
+ rcu_read_unlock();
return -EPERM;
+ }
+ rcu_read_unlock();
if (count >= PAGE_SIZE)
count = PAGE_SIZE - 1;
static const struct file_operations proc_loginuid_operations = {
.read = proc_loginuid_read,
.write = proc_loginuid_write,
+ .llseek = generic_file_llseek,
};
static ssize_t proc_sessionid_read(struct file * file, char __user * buf,
static const struct file_operations proc_sessionid_operations = {
.read = proc_sessionid_read,
+ .llseek = generic_file_llseek,
};
#endif
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++;
+ make_it_fail = simple_strtol(strstrip(buffer), &end, 0);
+ if (*end)
+ return -EINVAL;
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;
+
+ return count;
}
static const struct file_operations proc_fault_inject_operations = {
.read = proc_fault_inject_read,
.write = proc_fault_inject_write,
+ .llseek = generic_file_llseek,
};
#endif
struct inode *inode = m->private;
struct task_struct *p;
- WARN_ON(!inode);
-
p = get_proc_task(inode);
if (!p)
return -ESRCH;
struct inode *inode = file->f_path.dentry->d_inode;
struct task_struct *p;
- WARN_ON(!inode);
-
p = get_proc_task(inode);
if (!p)
return -ESRCH;
#endif
+static ssize_t comm_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *offset)
+{
+ struct inode *inode = file->f_path.dentry->d_inode;
+ struct task_struct *p;
+ char buffer[TASK_COMM_LEN];
+
+ memset(buffer, 0, sizeof(buffer));
+ if (count > sizeof(buffer) - 1)
+ count = sizeof(buffer) - 1;
+ if (copy_from_user(buffer, buf, count))
+ return -EFAULT;
+
+ p = get_proc_task(inode);
+ if (!p)
+ return -ESRCH;
+
+ if (same_thread_group(current, p))
+ set_task_comm(p, buffer);
+ else
+ count = -EINVAL;
+
+ put_task_struct(p);
+
+ return count;
+}
+
+static int comm_show(struct seq_file *m, void *v)
+{
+ struct inode *inode = m->private;
+ struct task_struct *p;
+
+ p = get_proc_task(inode);
+ if (!p)
+ return -ESRCH;
+
+ task_lock(p);
+ seq_printf(m, "%s\n", p->comm);
+ task_unlock(p);
+
+ put_task_struct(p);
+
+ return 0;
+}
+
+static int comm_open(struct inode *inode, struct file *filp)
+{
+ int ret;
+
+ ret = single_open(filp, comm_show, NULL);
+ if (!ret) {
+ struct seq_file *m = filp->private_data;
+
+ m->private = inode;
+ }
+ return ret;
+}
+
+static const struct file_operations proc_pid_set_comm_operations = {
+ .open = comm_open,
+ .read = seq_read,
+ .write = comm_write,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+/*
+ * We added or removed a vma mapping the executable. The vmas are only mapped
+ * during exec and are not mapped with the mmap system call.
+ * Callers must hold down_write() on the mm's mmap_sem for these
+ */
+void added_exe_file_vma(struct mm_struct *mm)
+{
+ mm->num_exe_file_vmas++;
+}
+
+void removed_exe_file_vma(struct mm_struct *mm)
+{
+ mm->num_exe_file_vmas--;
+ if ((mm->num_exe_file_vmas == 0) && mm->exe_file){
+ fput(mm->exe_file);
+ mm->exe_file = NULL;
+ }
+
+}
+
+void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
+{
+ if (new_exe_file)
+ get_file(new_exe_file);
+ if (mm->exe_file)
+ fput(mm->exe_file);
+ mm->exe_file = new_exe_file;
+ mm->num_exe_file_vmas = 0;
+}
+
+struct file *get_mm_exe_file(struct mm_struct *mm)
+{
+ struct file *exe_file;
+
+ /* We need mmap_sem to protect against races with removal of
+ * VM_EXECUTABLE vmas */
+ down_read(&mm->mmap_sem);
+ exe_file = mm->exe_file;
+ if (exe_file)
+ get_file(exe_file);
+ up_read(&mm->mmap_sem);
+ return exe_file;
+}
+
+void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm)
+{
+ /* It's safe to write the exe_file pointer without exe_file_lock because
+ * this is called during fork when the task is not yet in /proc */
+ newmm->exe_file = get_mm_exe_file(oldmm);
+}
+
+static int proc_exe_link(struct inode *inode, struct path *exe_path)
+{
+ struct task_struct *task;
+ struct mm_struct *mm;
+ struct file *exe_file;
+
+ task = get_proc_task(inode);
+ if (!task)
+ return -ENOENT;
+ mm = get_task_mm(task);
+ put_task_struct(task);
+ if (!mm)
+ return -ENOENT;
+ exe_file = get_mm_exe_file(mm);
+ mmput(mm);
+ if (exe_file) {
+ *exe_path = exe_file->f_path;
+ path_get(&exe_file->f_path);
+ fput(exe_file);
+ return 0;
+ } else
+ return -ENOENT;
+}
+
static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
{
struct inode *inode = dentry->d_inode;
goto out;
error = PROC_I(inode)->op.proc_get_link(inode, &nd->path);
- nd->last_type = LAST_BIND;
out:
return ERR_PTR(error);
}
{
struct inode * inode;
struct proc_inode *ei;
+ const struct cred *cred;
/* We need a new inode */
if (!ei->pid)
goto out_unlock;
- inode->i_uid = 0;
- inode->i_gid = 0;
if (task_dumpable(task)) {
- inode->i_uid = task->euid;
- inode->i_gid = task->egid;
+ rcu_read_lock();
+ cred = __task_cred(task);
+ inode->i_uid = cred->euid;
+ inode->i_gid = cred->egid;
+ rcu_read_unlock();
}
security_task_to_inode(task, inode);
{
struct inode *inode = dentry->d_inode;
struct task_struct *task;
+ const struct cred *cred;
+
generic_fillattr(inode, stat);
rcu_read_lock();
if (task) {
if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
task_dumpable(task)) {
- stat->uid = task->euid;
- stat->gid = task->egid;
+ cred = __task_cred(task);
+ stat->uid = cred->euid;
+ stat->gid = cred->egid;
}
}
rcu_read_unlock();
{
struct inode *inode = dentry->d_inode;
struct task_struct *task = get_proc_task(inode);
+ const struct cred *cred;
+
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;
+ rcu_read_lock();
+ cred = __task_cred(task);
+ inode->i_uid = cred->euid;
+ inode->i_gid = cred->egid;
+ rcu_read_unlock();
} else {
inode->i_uid = 0;
inode->i_gid = 0;
return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first;
}
-static struct dentry_operations pid_dentry_operations =
+static const struct dentry_operations pid_dentry_operations =
{
.d_revalidate = pid_revalidate,
.d_delete = pid_delete_dentry,
struct task_struct *task = get_proc_task(inode);
int fd = proc_fd(inode);
struct files_struct *files;
+ const struct cred *cred;
if (task) {
files = get_files_struct(task);
rcu_read_unlock();
put_files_struct(files);
if (task_dumpable(task)) {
- inode->i_uid = task->euid;
- inode->i_gid = task->egid;
+ rcu_read_lock();
+ cred = __task_cred(task);
+ inode->i_uid = cred->euid;
+ inode->i_gid = cred->egid;
+ rcu_read_unlock();
} else {
inode->i_uid = 0;
inode->i_gid = 0;
return 0;
}
-static struct dentry_operations tid_fd_dentry_operations =
+static const struct dentry_operations tid_fd_dentry_operations =
{
.d_revalidate = tid_fd_revalidate,
.d_delete = pid_delete_dentry,
file = fcheck_files(files, fd);
if (!file)
goto out_unlock;
- if (file->f_mode & 1)
+ if (file->f_mode & FMODE_READ)
inode->i_mode |= S_IRUSR | S_IXUSR;
- if (file->f_mode & 2)
+ if (file->f_mode & FMODE_WRITE)
inode->i_mode |= S_IWUSR | S_IXUSR;
spin_unlock(&files->file_lock);
put_files_struct(files);
}
static const struct file_operations proc_fdinfo_file_operations = {
- .open = nonseekable_open,
+ .open = nonseekable_open,
.read = proc_fdinfo_read,
};
* /proc/pid/fd needs a special permission handler so that a process can still
* access /proc/self/fd after it has executed a setuid().
*/
-static int proc_fd_permission(struct inode *inode, int mask,
- struct nameidata *nd)
+static int proc_fd_permission(struct inode *inode, int mask)
{
int rv;
const struct pid_entry *p = ptr;
struct inode *inode;
struct proc_inode *ei;
- struct dentry *error = ERR_PTR(-EINVAL);
+ struct dentry *error = ERR_PTR(-ENOENT);
inode = proc_pid_make_inode(dir->i_sb, task);
if (!inode)
const struct pid_entry *ents,
unsigned int nents)
{
- struct inode *inode;
struct dentry *error;
struct task_struct *task = get_proc_task(dir);
const struct pid_entry *p, *last;
error = ERR_PTR(-ENOENT);
- inode = NULL;
if (!task)
goto out_no_task;
if (copy_from_user(page, buf, count))
goto out_free;
+ /* Guard against adverse ptrace interaction */
+ length = mutex_lock_interruptible(&task->cred_guard_mutex);
+ if (length < 0)
+ goto out_free;
+
length = security_setprocattr(task,
(char*)file->f_path.dentry->d_name.name,
(void*)page, count);
+ mutex_unlock(&task->cred_guard_mutex);
out_free:
free_page((unsigned long) page);
out:
static const struct file_operations proc_pid_attr_operations = {
.read = proc_pid_attr_read,
.write = proc_pid_attr_write,
+ .llseek = generic_file_llseek,
};
static const 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),
+ REG("current", S_IRUGO|S_IWUGO, proc_pid_attr_operations),
+ REG("prev", S_IRUGO, proc_pid_attr_operations),
+ REG("exec", S_IRUGO|S_IWUGO, proc_pid_attr_operations),
+ REG("fscreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations),
+ REG("keycreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations),
+ REG("sockcreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations),
};
static int proc_attr_dir_readdir(struct file * filp,
#endif
-#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
+#ifdef CONFIG_ELF_CORE
static ssize_t proc_coredump_filter_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
static const struct file_operations proc_coredump_filter_operations = {
.read = proc_coredump_filter_read,
.write = proc_coredump_filter_write,
+ .llseek = generic_file_llseek,
};
#endif
{
struct pid_namespace *ns = dentry->d_sb->s_fs_info;
pid_t tgid = task_tgid_nr_ns(current, ns);
- char tmp[PROC_NUMBUF];
- if (!tgid)
- return ERR_PTR(-ENOENT);
- sprintf(tmp, "%d", task_tgid_nr_ns(current, ns));
- return ERR_PTR(vfs_follow_link(nd,tmp));
+ char *name = ERR_PTR(-ENOENT);
+ if (tgid) {
+ name = __getname();
+ if (!name)
+ name = ERR_PTR(-ENOMEM);
+ else
+ sprintf(name, "%d", tgid);
+ }
+ nd_set_link(nd, name);
+ return NULL;
+}
+
+static void proc_self_put_link(struct dentry *dentry, struct nameidata *nd,
+ void *cookie)
+{
+ char *s = nd_get_link(nd);
+ if (!IS_ERR(s))
+ __putname(s);
}
static const struct inode_operations proc_self_inode_operations = {
.readlink = proc_self_readlink,
.follow_link = proc_self_follow_link,
+ .put_link = proc_self_put_link,
};
/*
return 0;
}
-static struct dentry_operations proc_base_dentry_operations =
+static const struct dentry_operations proc_base_dentry_operations =
{
.d_revalidate = proc_base_revalidate,
.d_delete = pid_delete_dentry,
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;
}
#ifdef CONFIG_TASK_IO_ACCOUNTING
-static int proc_pid_io_accounting(struct task_struct *task, char *buffer)
+static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
{
+ struct task_io_accounting acct = task->ioac;
+ unsigned long flags;
+
+ if (whole && lock_task_sighand(task, &flags)) {
+ struct task_struct *t = task;
+
+ task_io_accounting_add(&acct, &task->signal->ioac);
+ while_each_thread(task, t)
+ task_io_accounting_add(&acct, &t->ioac);
+
+ unlock_task_sighand(task, &flags);
+ }
return sprintf(buffer,
-#ifdef CONFIG_TASK_XACCT
"rchar: %llu\n"
"wchar: %llu\n"
"syscr: %llu\n"
"syscw: %llu\n"
-#endif
"read_bytes: %llu\n"
"write_bytes: %llu\n"
"cancelled_write_bytes: %llu\n",
-#ifdef CONFIG_TASK_XACCT
- (unsigned long long)task->rchar,
- (unsigned long long)task->wchar,
- (unsigned long long)task->syscr,
- (unsigned long long)task->syscw,
-#endif
- (unsigned long long)task->ioac.read_bytes,
- (unsigned long long)task->ioac.write_bytes,
- (unsigned long long)task->ioac.cancelled_write_bytes);
+ (unsigned long long)acct.rchar,
+ (unsigned long long)acct.wchar,
+ (unsigned long long)acct.syscr,
+ (unsigned long long)acct.syscw,
+ (unsigned long long)acct.read_bytes,
+ (unsigned long long)acct.write_bytes,
+ (unsigned long long)acct.cancelled_write_bytes);
+}
+
+static int proc_tid_io_accounting(struct task_struct *task, char *buffer)
+{
+ return do_io_accounting(task, buffer, 0);
+}
+
+static int proc_tgid_io_accounting(struct task_struct *task, char *buffer)
+{
+ return do_io_accounting(task, buffer, 1);
+}
+#endif /* CONFIG_TASK_IO_ACCOUNTING */
+
+static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
+{
+ seq_printf(m, "%08x\n", task->personality);
+ return 0;
}
-#endif
/*
* Thread groups
static const struct inode_operations proc_task_inode_operations;
static const struct pid_entry tgid_base_stuff[] = {
- DIR("task", S_IRUGO|S_IXUGO, task),
- DIR("fd", S_IRUSR|S_IXUSR, fd),
- DIR("fdinfo", S_IRUSR|S_IXUSR, fdinfo),
+ DIR("task", S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations),
+ DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
+ DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
#ifdef CONFIG_NET
- DIR("net", S_IRUGO|S_IXUGO, net),
+ DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
#endif
- REG("environ", S_IRUSR, environ),
- INF("auxv", S_IRUSR, pid_auxv),
- ONE("status", S_IRUGO, pid_status),
- INF("limits", S_IRUSR, pid_limits),
+ REG("environ", S_IRUSR, proc_environ_operations),
+ INF("auxv", S_IRUSR, proc_pid_auxv),
+ ONE("status", S_IRUGO, proc_pid_status),
+ ONE("personality", S_IRUSR, proc_pid_personality),
+ INF("limits", S_IRUSR, proc_pid_limits),
#ifdef CONFIG_SCHED_DEBUG
- REG("sched", S_IRUGO|S_IWUSR, pid_sched),
+ REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations),
#endif
- INF("cmdline", S_IRUGO, pid_cmdline),
- ONE("stat", S_IRUGO, tgid_stat),
- ONE("statm", S_IRUGO, pid_statm),
- REG("maps", S_IRUGO, maps),
+ REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+ INF("syscall", S_IRUSR, proc_pid_syscall),
+#endif
+ INF("cmdline", S_IRUGO, proc_pid_cmdline),
+ ONE("stat", S_IRUGO, proc_tgid_stat),
+ ONE("statm", S_IRUGO, proc_pid_statm),
+ REG("maps", S_IRUGO, proc_maps_operations),
#ifdef CONFIG_NUMA
- REG("numa_maps", S_IRUGO, numa_maps),
+ REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
#endif
- REG("mem", S_IRUSR|S_IWUSR, mem),
- LNK("cwd", cwd),
- LNK("root", root),
- LNK("exe", exe),
- REG("mounts", S_IRUGO, mounts),
- REG("mountinfo", S_IRUGO, mountinfo),
- REG("mountstats", S_IRUSR, mountstats),
+ REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations),
+ LNK("cwd", proc_cwd_link),
+ LNK("root", proc_root_link),
+ LNK("exe", proc_exe_link),
+ REG("mounts", S_IRUGO, proc_mounts_operations),
+ REG("mountinfo", S_IRUGO, proc_mountinfo_operations),
+ REG("mountstats", S_IRUSR, proc_mountstats_operations),
#ifdef CONFIG_PROC_PAGE_MONITOR
- REG("clear_refs", S_IWUSR, clear_refs),
- REG("smaps", S_IRUGO, smaps),
- REG("pagemap", S_IRUSR, pagemap),
+ REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
+ REG("smaps", S_IRUGO, proc_smaps_operations),
+ REG("pagemap", S_IRUSR, proc_pagemap_operations),
#endif
#ifdef CONFIG_SECURITY
- DIR("attr", S_IRUGO|S_IXUGO, attr_dir),
+ DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
#endif
#ifdef CONFIG_KALLSYMS
- INF("wchan", S_IRUGO, pid_wchan),
+ INF("wchan", S_IRUGO, proc_pid_wchan),
+#endif
+#ifdef CONFIG_STACKTRACE
+ ONE("stack", S_IRUSR, proc_pid_stack),
#endif
#ifdef CONFIG_SCHEDSTATS
- INF("schedstat", S_IRUGO, pid_schedstat),
+ INF("schedstat", S_IRUGO, proc_pid_schedstat),
#endif
#ifdef CONFIG_LATENCYTOP
- REG("latency", S_IRUGO, lstats),
+ REG("latency", S_IRUGO, proc_lstats_operations),
#endif
#ifdef CONFIG_PROC_PID_CPUSET
- REG("cpuset", S_IRUGO, cpuset),
+ REG("cpuset", S_IRUGO, proc_cpuset_operations),
#endif
#ifdef CONFIG_CGROUPS
- REG("cgroup", S_IRUGO, cgroup),
+ REG("cgroup", S_IRUGO, proc_cgroup_operations),
#endif
- INF("oom_score", S_IRUGO, oom_score),
- REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust),
+ INF("oom_score", S_IRUGO, proc_oom_score),
+ REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adjust_operations),
#ifdef CONFIG_AUDITSYSCALL
- REG("loginuid", S_IWUSR|S_IRUGO, loginuid),
- REG("sessionid", S_IRUSR, sessionid),
+ REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
+ REG("sessionid", S_IRUGO, proc_sessionid_operations),
#endif
#ifdef CONFIG_FAULT_INJECTION
- REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject),
+ REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
#endif
-#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
- REG("coredump_filter", S_IRUGO|S_IWUSR, coredump_filter),
+#ifdef CONFIG_ELF_CORE
+ REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations),
#endif
#ifdef CONFIG_TASK_IO_ACCOUNTING
- INF("io", S_IRUGO, pid_io_accounting),
+ INF("io", S_IRUGO, proc_tgid_io_accounting),
#endif
};
name.len = snprintf(buf, sizeof(buf), "%d", pid);
dentry = d_hash_and_lookup(mnt->mnt_root, &name);
if (dentry) {
- if (!(current->flags & PF_EXITING))
- shrink_dcache_parent(dentry);
+ shrink_dcache_parent(dentry);
d_drop(dentry);
dput(dentry);
}
- if (tgid == 0)
- goto out;
-
name.name = buf;
name.len = snprintf(buf, sizeof(buf), "%d", tgid);
leader = d_hash_and_lookup(mnt->mnt_root, &name);
void proc_flush_task(struct task_struct *task)
{
int i;
- struct pid *pid, *tgid = NULL;
+ struct pid *pid, *tgid;
struct upid *upid;
pid = task_pid(task);
- if (thread_group_leader(task))
- tgid = task_tgid(task);
+ tgid = task_tgid(task);
for (i = 0; i <= pid->level; i++) {
upid = &pid->numbers[i];
proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr,
- tgid ? tgid->numbers[i].nr : 0);
+ tgid->numbers[i].nr);
}
upid = &pid->numbers[pid->level];
inode->i_op = &proc_tgid_base_inode_operations;
inode->i_fop = &proc_tgid_base_operations;
inode->i_flags|=S_IMMUTABLE;
- inode->i_nlink = 5;
-#ifdef CONFIG_SECURITY
- inode->i_nlink += 1;
-#endif
+
+ inode->i_nlink = 2 + pid_entry_count_dirs(tgid_base_stuff,
+ ARRAY_SIZE(tgid_base_stuff));
dentry->d_op = &pid_dentry_operations;
* Tasks
*/
static const struct pid_entry tid_base_stuff[] = {
- DIR("fd", S_IRUSR|S_IXUSR, fd),
- DIR("fdinfo", S_IRUSR|S_IXUSR, fdinfo),
- REG("environ", S_IRUSR, environ),
- INF("auxv", S_IRUSR, pid_auxv),
- ONE("status", S_IRUGO, pid_status),
- INF("limits", S_IRUSR, pid_limits),
+ DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
+ DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
+ REG("environ", S_IRUSR, proc_environ_operations),
+ INF("auxv", S_IRUSR, proc_pid_auxv),
+ ONE("status", S_IRUGO, proc_pid_status),
+ ONE("personality", S_IRUSR, proc_pid_personality),
+ INF("limits", S_IRUSR, proc_pid_limits),
#ifdef CONFIG_SCHED_DEBUG
- REG("sched", S_IRUGO|S_IWUSR, pid_sched),
+ REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations),
+#endif
+ REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+ INF("syscall", S_IRUSR, proc_pid_syscall),
#endif
- INF("cmdline", S_IRUGO, pid_cmdline),
- ONE("stat", S_IRUGO, tid_stat),
- ONE("statm", S_IRUGO, pid_statm),
- REG("maps", S_IRUGO, maps),
+ INF("cmdline", S_IRUGO, proc_pid_cmdline),
+ ONE("stat", S_IRUGO, proc_tid_stat),
+ ONE("statm", S_IRUGO, proc_pid_statm),
+ REG("maps", S_IRUGO, proc_maps_operations),
#ifdef CONFIG_NUMA
- REG("numa_maps", S_IRUGO, numa_maps),
+ REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
#endif
- REG("mem", S_IRUSR|S_IWUSR, mem),
- LNK("cwd", cwd),
- LNK("root", root),
- LNK("exe", exe),
- REG("mounts", S_IRUGO, mounts),
- REG("mountinfo", S_IRUGO, mountinfo),
+ REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations),
+ LNK("cwd", proc_cwd_link),
+ LNK("root", proc_root_link),
+ LNK("exe", proc_exe_link),
+ REG("mounts", S_IRUGO, proc_mounts_operations),
+ REG("mountinfo", S_IRUGO, proc_mountinfo_operations),
#ifdef CONFIG_PROC_PAGE_MONITOR
- REG("clear_refs", S_IWUSR, clear_refs),
- REG("smaps", S_IRUGO, smaps),
- REG("pagemap", S_IRUSR, pagemap),
+ REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
+ REG("smaps", S_IRUGO, proc_smaps_operations),
+ REG("pagemap", S_IRUSR, proc_pagemap_operations),
#endif
#ifdef CONFIG_SECURITY
- DIR("attr", S_IRUGO|S_IXUGO, attr_dir),
+ DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
#endif
#ifdef CONFIG_KALLSYMS
- INF("wchan", S_IRUGO, pid_wchan),
+ INF("wchan", S_IRUGO, proc_pid_wchan),
+#endif
+#ifdef CONFIG_STACKTRACE
+ ONE("stack", S_IRUSR, proc_pid_stack),
#endif
#ifdef CONFIG_SCHEDSTATS
- INF("schedstat", S_IRUGO, pid_schedstat),
+ INF("schedstat", S_IRUGO, proc_pid_schedstat),
#endif
#ifdef CONFIG_LATENCYTOP
- REG("latency", S_IRUGO, lstats),
+ REG("latency", S_IRUGO, proc_lstats_operations),
#endif
#ifdef CONFIG_PROC_PID_CPUSET
- REG("cpuset", S_IRUGO, cpuset),
+ REG("cpuset", S_IRUGO, proc_cpuset_operations),
#endif
#ifdef CONFIG_CGROUPS
- REG("cgroup", S_IRUGO, cgroup),
+ REG("cgroup", S_IRUGO, proc_cgroup_operations),
#endif
- INF("oom_score", S_IRUGO, oom_score),
- REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust),
+ INF("oom_score", S_IRUGO, proc_oom_score),
+ REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adjust_operations),
#ifdef CONFIG_AUDITSYSCALL
- REG("loginuid", S_IWUSR|S_IRUGO, loginuid),
- REG("sessionid", S_IRUSR, sessionid),
+ REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
+ REG("sessionid", S_IRUSR, proc_sessionid_operations),
#endif
#ifdef CONFIG_FAULT_INJECTION
- REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject),
+ REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
+#endif
+#ifdef CONFIG_TASK_IO_ACCOUNTING
+ INF("io", S_IRUGO, proc_tid_io_accounting),
#endif
};
inode->i_op = &proc_tid_base_inode_operations;
inode->i_fop = &proc_tid_base_operations;
inode->i_flags|=S_IMMUTABLE;
- inode->i_nlink = 4;
-#ifdef CONFIG_SECURITY
- inode->i_nlink += 1;
-#endif
+
+ inode->i_nlink = 2 + pid_entry_count_dirs(tid_base_stuff,
+ ARRAY_SIZE(tid_base_stuff));
dentry->d_op = &pid_dentry_operations;
int retval = -ENOENT;
ino_t ino;
int tid;
- unsigned long pos = filp->f_pos; /* avoiding "long long" filp->f_pos */
struct pid_namespace *ns;
task = get_proc_task(inode);
goto out_no_task;
retval = 0;
- switch (pos) {
+ switch ((unsigned long)filp->f_pos) {
case 0:
ino = inode->i_ino;
- if (filldir(dirent, ".", 1, pos, ino, DT_DIR) < 0)
+ if (filldir(dirent, ".", 1, filp->f_pos, ino, DT_DIR) < 0)
goto out;
- pos++;
+ filp->f_pos++;
/* fall through */
case 1:
ino = parent_ino(dentry);
- if (filldir(dirent, "..", 2, pos, ino, DT_DIR) < 0)
+ if (filldir(dirent, "..", 2, filp->f_pos, ino, DT_DIR) < 0)
goto out;
- pos++;
+ filp->f_pos++;
/* fall through */
}
ns = filp->f_dentry->d_sb->s_fs_info;
tid = (int)filp->f_version;
filp->f_version = 0;
- for (task = first_tid(leader, tid, pos - 2, ns);
+ for (task = first_tid(leader, tid, filp->f_pos - 2, ns);
task;
- task = next_tid(task), pos++) {
+ task = next_tid(task), filp->f_pos++) {
tid = task_pid_nr_ns(task, ns);
if (proc_task_fill_cache(filp, dirent, filldir, task, tid) < 0) {
/* returning this tgid failed, save it as the first
}
}
out:
- filp->f_pos = pos;
put_task_struct(leader);
out_no_task:
return retval;
generic_fillattr(inode, stat);
if (p) {
- rcu_read_lock();
stat->nlink += get_nr_threads(p);
- rcu_read_unlock();
put_task_struct(p);
}