* go into icache. We cache the reference to task_struct upon lookup too.
* Eventually it should become a filesystem in its own. We don't use the
* rest of procfs anymore.
+ *
+ *
+ * Changelog:
+ * 17-Jan-2005
+ * Allan Bezerra
+ * Bruna Moreira <bruna.moreira@indt.org.br>
+ * Edjard Mota <edjard.mota@indt.org.br>
+ * Ilias Biris <ilias.biris@indt.org.br>
+ * Mauricio Lin <mauricio.lin@indt.org.br>
+ *
+ * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
+ *
+ * A new process specific entry (smaps) included in /proc. It shows the
+ * size of rss for each memory area. The maps entry lacks information
+ * about physical memory size (rss) for each mapped file, i.e.,
+ * rss information for executables and library files.
+ * This additional information is useful for any tools that need to know
+ * about physical memory consumption for a process specific library.
+ *
+ * Changelog:
+ * 21-Feb-2005
+ * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
+ * Pud inclusion in the page table walking.
+ *
+ * ChangeLog:
+ * 10-Mar-2005
+ * 10LE Instituto Nokia de Tecnologia - INdT:
+ * A better way to walks through the page table as suggested by Hugh Dickins.
+ *
+ * Simo Piiroinen <simo.piiroinen@nokia.com>:
+ * Smaps information related to shared, private, clean and dirty pages.
+ *
+ * Paul Mundt <paul.mundt@nokia.com>:
+ * Overall revision about smaps.
*/
#include <asm/uaccess.h>
-#include <linux/config.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>
+#include <linux/capability.h>
#include <linux/file.h>
#include <linux/string.h>
#include <linux/seq_file.h>
#include <linux/namespace.h>
#include <linux/mm.h>
#include <linux/smp_lock.h>
+#include <linux/rcupdate.h>
#include <linux/kallsyms.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/ptrace.h>
-#include <linux/vs_context.h>
-#include <linux/vs_network.h>
-#include <linux/vs_cvirt.h>
-
+#include <linux/tracehook.h>
+#include <linux/seccomp.h>
+#include <linux/cpuset.h>
+#include <linux/audit.h>
+#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.
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_STAT,
PROC_TGID_STATM,
PROC_TGID_MAPS,
+ PROC_TGID_NUMA_MAPS,
PROC_TGID_MOUNTS,
+ PROC_TGID_MOUNTSTATS,
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,
+ PROC_TGID_ATTR_KEYCREATE,
+ PROC_TGID_ATTR_SOCKCREATE,
#endif
PROC_TGID_VX_INFO,
PROC_TGID_IP_INFO,
- PROC_TGID_FD_DIR,
+#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_STAT,
PROC_TID_STATM,
PROC_TID_MAPS,
+ PROC_TID_NUMA_MAPS,
PROC_TID_MOUNTS,
+ PROC_TID_MOUNTSTATS,
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,
+ PROC_TID_ATTR_KEYCREATE,
+ PROC_TID_ATTR_SOCKCREATE,
#endif
PROC_TID_VX_INFO,
PROC_TID_IP_INFO,
-#ifdef CONFIG_DELAY_ACCT
- PROC_TID_DELAY_ACCT,
- PROC_TGID_DELAY_ACCT,
+#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 10
+
struct pid_entry {
int type;
int len;
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_IRUSR),
+#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),
+ E(PROC_TGID_MOUNTSTATS, "mountstats", S_IFREG|S_IRUSR),
+#ifdef CONFIG_MMU
+ E(PROC_TGID_SMAPS, "smaps", S_IFREG|S_IRUSR),
+#endif
#ifdef CONFIG_SECURITY
E(PROC_TGID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO),
#endif
-#ifdef CONFIG_DELAY_ACCT
- E(PROC_TGID_DELAY_ACCT,"delay", S_IFREG|S_IRUGO),
-#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_STAT, "stat", S_IFREG|S_IRUGO),
E(PROC_TID_STATM, "statm", S_IFREG|S_IRUGO),
E(PROC_TID_MAPS, "maps", S_IFREG|S_IRUSR),
+#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_IRUSR),
+#endif
#ifdef CONFIG_SECURITY
E(PROC_TID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO),
#endif
-#ifdef CONFIG_DELAY_ACCT
- E(PROC_TGID_DELAY_ACCT,"delay", S_IFREG|S_IRUGO),
-#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}
};
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),
+ E(PROC_TGID_ATTR_SOCKCREATE, "sockcreate", 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),
+ E(PROC_TID_ATTR_SOCKCREATE, "sockcreate", S_IFREG|S_IRUGO|S_IWUGO),
{0,0,NULL,0}
};
#endif
#undef E
-static inline struct task_struct *proc_task(struct inode *inode)
-{
- return PROC_I(inode)->task;
-}
-
-static inline int proc_type(struct inode *inode)
-{
- return PROC_I(inode)->type;
-}
-
-int proc_pid_stat(struct task_struct*,char*);
-int proc_pid_status(struct task_struct*,char*);
-int proc_pid_statm(struct task_struct*,char*);
-int proc_pid_cpu(struct task_struct*,char*);
-int proc_pid_delay(struct task_struct*,char*);
-
static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
{
- struct task_struct *task = proc_task(inode);
- struct files_struct *files;
+ struct task_struct *task = get_proc_task(inode);
+ struct files_struct *files = NULL;
struct file *file;
- int fd = proc_type(inode) - PROC_TID_FD_DIR;
+ int fd = proc_fd(inode);
- files = get_files_struct(task);
+ 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) {
return -ENOENT;
}
-static int proc_exe_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
+static struct fs_struct *get_fs_struct(struct task_struct *task)
{
- struct vm_area_struct * vma;
- int result = -ENOENT;
- struct task_struct *task = proc_task(inode);
- struct mm_struct * mm = get_task_mm(task);
+ struct fs_struct *fs;
+ task_lock(task);
+ fs = task->fs;
+ if(fs)
+ atomic_inc(&fs->count);
+ task_unlock(task);
+ return fs;
+}
- if (!mm)
- goto out;
- down_read(&mm->mmap_sem);
- vma = mm->mmap;
- while (vma) {
- if ((vma->vm_flags & VM_EXECUTABLE) &&
- vma->vm_file) {
- *mnt = mntget(vma->vm_file->f_vfsmnt);
- *dentry = dget(vma->vm_file->f_dentry);
- result = 0;
- break;
- }
- vma = vma->vm_next;
+static int get_nr_threads(struct task_struct *tsk)
+{
+ /* Must be called with the rcu_read_lock held */
+ unsigned long flags;
+ int count = 0;
+
+ if (lock_task_sighand(tsk, &flags)) {
+ count = atomic_read(&tsk->signal->count);
+ unlock_task_sighand(tsk, &flags);
}
- up_read(&mm->mmap_sem);
- mmput(mm);
-out:
- return result;
+ return count;
}
static int proc_cwd_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;
- task_lock(proc_task(inode));
- fs = proc_task(inode)->fs;
- if(fs)
- atomic_inc(&fs->count);
- task_unlock(proc_task(inode));
+
+ if (task) {
+ fs = get_fs_struct(task);
+ put_task_struct(task);
+ }
if (fs) {
read_lock(&fs->lock);
*mnt = mntget(fs->pwdmnt);
static int proc_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;
- task_lock(proc_task(inode));
- fs = proc_task(inode)->fs;
- if(fs)
- atomic_inc(&fs->count);
- task_unlock(proc_task(inode));
+
+ if (task) {
+ fs = get_fs_struct(task);
+ put_task_struct(task);
+ }
if (fs) {
read_lock(&fs->lock);
*mnt = mntget(fs->rootmnt);
return result;
}
-#define MAY_PTRACE(task) \
- (task == current || \
- (task->parent == current && \
- (task->ptrace & PT_PTRACED) && task->state == TASK_STOPPED && \
- security_ptrace(current,task) == 0))
-
-static int may_ptrace_attach(struct task_struct *task)
+struct mm_struct *mm_for_maps(struct task_struct *task)
{
- int retval = 0;
-
+ struct mm_struct *mm = get_task_mm(task);
+ if (!mm)
+ return NULL;
+ down_read(&mm->mmap_sem);
task_lock(task);
-
- if (!task->mm)
- goto out;
- 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))
- goto out;
- rmb();
- if (!task->mm->dumpable && !capable(CAP_SYS_PTRACE))
+ if (task->mm != mm)
goto out;
- if (security_ptrace(current, task))
+ if (task->mm != current->mm && __ptrace_may_attach(task) < 0)
goto out;
-
- retval = 1;
+ task_unlock(task);
+ return mm;
out:
task_unlock(task);
- return retval;
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+ return NULL;
}
static int proc_pid_environ(struct task_struct *task, char * buffer)
if (len > PAGE_SIZE)
len = PAGE_SIZE;
res = access_process_vm(task, mm->env_start, buffer, len, 0);
- if (!may_ptrace_attach(task))
+ if (!ptrace_may_attach(task))
res = -ESRCH;
mmput(mm);
}
struct mm_struct *mm = get_task_mm(task);
if (!mm)
goto out;
+ if (!mm->arg_end)
+ goto out_mm; /* Shh! No looking before we're done */
len = mm->arg_end - mm->arg_start;
// If the nul at the end of args has been overwritten, then
// assume application is using setproctitle(3).
- if (res > 0 && buffer[res-1] != '\0') {
+ if (res > 0 && buffer[res-1] != '\0' && len < PAGE_SIZE) {
len = strnlen(buffer, res);
if (len < res) {
res = len;
res = strnlen(buffer, res);
}
}
+out_mm:
mmput(mm);
-
out:
return res;
}
char *modname;
const char *sym_name;
unsigned long wchan, size, offset;
- char namebuf[128];
+ char namebuf[KSYM_NAME_LEN+1];
wchan = get_wchan(task);
}
#endif /* CONFIG_KALLSYMS */
+#ifdef CONFIG_SCHEDSTATS
+/*
+ * Provides /proc/PID/schedstat
+ */
+static int proc_pid_schedstat(struct task_struct *task, char *buffer)
+{
+ return sprintf(buffer, "%lu %lu %lu\n",
+ task->sched_info.cpu_time,
+ task->sched_info.run_delay,
+ task->sched_info.pcnt);
+}
+#endif
+
+/* The badness from the OOM killer */
+unsigned long badness(struct task_struct *p, unsigned long uptime);
+static int proc_oom_score(struct task_struct *task, char *buffer)
+{
+ unsigned long points;
+ struct timespec uptime;
+
+ do_posix_clock_monotonic_gettime(&uptime);
+ points = badness(task, uptime.tv_sec);
+ return sprintf(buffer, "%lu\n", points);
+}
+
/************************************************************************/
/* Here the fs part begins */
/************************************************************************/
/* permission checks */
-
-static int proc_check_root(struct inode *inode)
+static int proc_fd_access_allowed(struct inode *inode)
{
- struct dentry *de, *base, *root;
- struct vfsmount *our_vfsmnt, *vfsmnt, *mnt;
- int res = 0;
-
- if (proc_root_link(inode, &root, &vfsmnt)) /* Ewww... */
- return -ENOENT;
- 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 (vfsmnt != our_vfsmnt) {
- if (vfsmnt == vfsmnt->mnt_parent)
- goto out;
- de = vfsmnt->mnt_mountpoint;
- vfsmnt = vfsmnt->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);
- dput(root);
- mntput(mnt);
- return res;
-out:
- spin_unlock(&vfsmount_lock);
- res = -EACCES;
- goto exit;
+ return allowed;
}
-static int proc_permission(struct inode *inode, int mask, struct nameidata *nd)
+static int proc_setattr(struct dentry *dentry, struct iattr *attr)
{
- if (vfs_permission(inode, mask) != 0)
- return -EACCES;
- return proc_check_root(inode);
-}
+ int error;
+ struct inode *inode = dentry->d_inode;
-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;
+ if (attr->ia_valid & ATTR_MODE)
+ return -EPERM;
+
+ error = inode_change_ok(inode, attr);
+ if (!error) {
+ error = security_inode_setattr(dentry, attr);
+ if (!error)
+ error = inode_setattr(inode, attr);
}
- return ret;
+ return error;
}
-static struct file_operations proc_maps_operations = {
- .open = maps_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
+static struct inode_operations proc_def_inode_operations = {
+ .setattr = proc_setattr,
};
extern struct seq_operations mounts_op;
+struct proc_mounts {
+ struct seq_file m;
+ int event;
+};
+
static int mounts_open(struct inode *inode, struct file *file)
{
- struct task_struct *task = proc_task(inode);
- int ret = seq_open(file, &mounts_op);
+ struct task_struct *task = get_proc_task(inode);
+ struct namespace *namespace = NULL;
+ struct proc_mounts *p;
+ int ret = -EINVAL;
- if (!ret) {
- struct seq_file *m = file->private_data;
- struct namespace *namespace;
+ if (task) {
task_lock(task);
namespace = task->namespace;
if (namespace)
get_namespace(namespace);
task_unlock(task);
+ put_task_struct(task);
+ }
- if (namespace)
- m->private = namespace;
- else {
- seq_release(inode, file);
- ret = -EINVAL;
+ if (namespace) {
+ 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;
+ return 0;
+ }
+ kfree(p);
}
+ put_namespace(namespace);
}
return ret;
}
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;
+ unsigned res = 0;
+
+ poll_wait(file, &ns->poll, wait);
+
+ spin_lock(&vfsmount_lock);
+ if (p->event != ns->event) {
+ p->event = ns->event;
+ res = POLLERR;
+ }
+ spin_unlock(&vfsmount_lock);
+
+ return res;
+}
+
static struct file_operations proc_mounts_operations = {
.open = mounts_open,
.read = seq_read,
.llseek = seq_lseek,
.release = mounts_release,
+ .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 namespace *namespace = NULL;
+ struct task_struct *task = get_proc_task(inode);
+
+ if (task) {
+ task_lock(task);
+ namespace = task->namespace;
+ if (namespace)
+ get_namespace(namespace);
+ task_unlock(task);
+ put_task_struct(task);
+ }
+
+ if (namespace)
+ m->private = namespace;
+ 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 */
struct inode * inode = file->f_dentry->d_inode;
unsigned long page;
ssize_t length;
- ssize_t end;
- 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) {
- free_page(page);
- return length;
- }
- /* Static 4kB (or whatever) block capacity */
- if (*ppos >= length) {
- free_page(page);
- return 0;
- }
- if (count + *ppos > length)
- count = length - *ppos;
- end = count + *ppos;
- if (copy_to_user(buf, (char *) page + *ppos, count))
- count = -EFAULT;
- else
- *ppos = end;
+ if (length >= 0)
+ length = simple_read_from_buffer(buf, count, ppos, (char *)page, length);
free_page(page);
- return count;
+out:
+ put_task_struct(task);
+out_no_task:
+ return length;
}
static struct file_operations proc_info_file_operations = {
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_dentry->d_inode);
char *page;
unsigned long src = *ppos;
int ret = -ESRCH;
struct mm_struct *mm;
- if (!MAY_PTRACE(task) || !may_ptrace_attach(task))
+ if (!task)
+ goto out_no_task;
+
+ if (!tracehook_allow_access_process_vm(task)
+ || !ptrace_may_attach(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) || !may_ptrace_attach(task)) {
+ if (!retval || !tracehook_allow_access_process_vm(task)
+ || !ptrace_may_attach(task)) {
if (!ret)
ret = -EIO;
break;
out_free:
free_page((unsigned long) page);
out:
+ put_task_struct(task);
+out_no_task:
return ret;
}
{
int copied = 0;
char *page;
- struct task_struct *task = proc_task(file->f_dentry->d_inode);
+ struct task_struct *task = get_proc_task(file->f_dentry->d_inode);
unsigned long dst = *ppos;
- if (!MAY_PTRACE(task) || !may_ptrace_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;
while (count > 0) {
int this_len, retval;
}
*ppos = dst;
free_page((unsigned long) page);
+out:
+ put_task_struct(task);
+out_no_task:
return copied;
}
#endif
.open = mem_open,
};
-static struct inode_operations proc_mem_inode_operations = {
- .permission = proc_permission,
+static ssize_t oom_adjust_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 oom_adjust;
+ loff_t __ppos = *ppos;
+
+ 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)
+ count = len-__ppos;
+ if (copy_to_user(buf, buffer + __ppos, count))
+ return -EFAULT;
+ *ppos = __ppos + count;
+ return count;
+}
+
+static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct task_struct *task;
+ char buffer[PROC_NUMBUF], *end;
+ int oom_adjust;
+
+ 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;
+ oom_adjust = simple_strtol(buffer, &end, 0);
+ if ((oom_adjust < -16 || oom_adjust > 15) && oom_adjust != OOM_DISABLE)
+ return -EINVAL;
+ if (*end == '\n')
+ end++;
+ task = get_proc_task(file->f_dentry->d_inode);
+ if (!task)
+ return -ESRCH;
+ task->oomkilladj = oom_adjust;
+ put_task_struct(task);
+ if (end - buffer == 0)
+ return -EIO;
+ return end - buffer;
+}
+
+static struct file_operations proc_oom_adjust_operations = {
+ .read = oom_adjust_read,
+ .write = oom_adjust_write,
+};
+
+#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 = 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;
+ char *page, *tmp;
+ ssize_t length;
+ uid_t loginuid;
+
+ if (!capable(CAP_AUDIT_CONTROL))
+ return -EPERM;
+
+ if (current != pid_task(proc_pid(inode), PIDTYPE_PID))
+ return -EPERM;
+
+ if (count >= PAGE_SIZE)
+ count = PAGE_SIZE - 1;
+
+ 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))
+ 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(current, loginuid);
+ if (likely(length == 0))
+ length = count;
+
+out_free_page:
+ free_page((unsigned long) page);
+ return length;
+}
+
+static struct file_operations proc_loginuid_operations = {
+ .read = proc_loginuid_read,
+ .write = proc_loginuid_write,
+};
+#endif
+
+#ifdef CONFIG_SECCOMP
+static ssize_t seccomp_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ 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)
+ count = len - __ppos;
+ if (copy_to_user(buf, __buf + __ppos, count))
+ return -EFAULT;
+ *ppos = __ppos + count;
+ return count;
+}
+
+static ssize_t seccomp_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ 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))
+ goto out;
+
+ result = -EFAULT;
+ memset(__buf, 0, sizeof(__buf));
+ count = min(count, sizeof(__buf) - 1);
+ if (copy_from_user(__buf, buf, count))
+ 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
+ goto out;
+ result = -EIO;
+ if (unlikely(!(end - __buf)))
+ goto out;
+ result = end - __buf;
+out:
+ put_task_struct(tsk);
+out_no_task:
+ return result;
+}
+
+static struct file_operations proc_seccomp_operations = {
+ .read = seccomp_read,
+ .write = seccomp_write,
};
+#endif /* CONFIG_SECCOMP */
-static int proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
+static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
{
struct inode *inode = dentry->d_inode;
int error = -EACCES;
/* 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);
nd->last_type = LAST_BIND;
out:
- return error;
+ return ERR_PTR(error);
}
static int do_proc_readlink(struct dentry *dentry, struct vfsmount *mnt,
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);
dput(de);
mntput(mnt);
out:
- unlock_kernel();
return error;
}
static struct inode_operations proc_pid_link_inode_operations = {
.readlink = proc_pid_readlink,
- .follow_link = proc_pid_follow_link
+ .follow_link = proc_pid_follow_link,
+ .setattr = proc_setattr,
};
-static int pid_alive(struct task_struct *p)
-{
- BUG_ON(p->pids[PIDTYPE_PID].pidptr != &p->pids[PIDTYPE_PID].pid);
- return atomic_read(&p->pids[PIDTYPE_PID].pid.count);
-}
-
-#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);
+ struct dentry *dentry = filp->f_dentry;
+ struct inode *inode = dentry->d_inode;
+ struct task_struct *p = get_proc_task(inode);
unsigned int fd, tid, ino;
int retval;
- char buf[NUMBUF];
+ char buf[PROC_NUMBUF];
struct files_struct * files;
+ struct fdtable *fdt;
retval = -ENOENT;
- if (!pid_alive(p))
- goto out;
+ if (!p)
+ goto out_no_task;
retval = 0;
tid = p->pid;
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++;
files = get_files_struct(p);
if (!files)
goto out;
- spin_lock(&files->file_lock);
+ rcu_read_lock();
+ fdt = files_fdtable(files);
for (fd = filp->f_pos-2;
- fd < files->max_fds;
+ fd < fdt->max_fds;
fd++, filp->f_pos++) {
unsigned int i,j;
if (!fcheck_files(files, fd))
continue;
- spin_unlock(&files->file_lock);
+ 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) {
- spin_lock(&files->file_lock);
+ if (filldir(dirent, buf+j, PROC_NUMBUF-j, fd+2, ino, DT_LNK) < 0) {
+ rcu_read_lock();
break;
}
- spin_lock(&files->file_lock);
+ rcu_read_lock();
}
- spin_unlock(&files->file_lock);
+ rcu_read_unlock();
put_files_struct(files);
}
out:
+ put_task_struct(p);
+out_no_task:
return retval;
}
int pid;
struct dentry *dentry = filp->f_dentry;
struct inode *inode = dentry->d_inode;
+ struct task_struct *task = get_proc_task(inode);
struct pid_entry *p;
ino_t ino;
- int ret;
+ int ret, hide;
ret = -ENOENT;
- if (!pid_alive(proc_task(inode)))
+ if (!task)
goto out;
ret = 0;
- pid = proc_task(inode)->pid;
+ pid = task->pid;
+ put_task_struct(task);
i = filp->f_pos;
switch (i) {
case 0:
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++;
}
}
if (mm)
dumpable = mm->dumpable;
task_unlock(task);
- return dumpable;
+ if(dumpable == 1)
+ return 1;
+ return 0;
}
/* 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);
-
- if (!pid_alive(task))
- goto out_unlock;
+ inode->i_op = &proc_def_inode_operations;
/*
* grab the reference to task.
*/
- get_task_struct(task);
- ei->task = task;
- ei->type = ino;
+ ei->pid = get_pid(task->pids[PIDTYPE_PID].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;
}
return inode;
out_unlock:
- ei->pde = NULL;
iput(inode);
return NULL;
}
*
* 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);
+ struct task_struct *task = get_proc_task(inode);
+ int ret = 0;
- if (!vx_check(vx_task_xid(task), VX_WATCH|VX_IDENT))
- goto out_drop;
- /* discard wrong fakeinit */
+ if (task) {
+ int pid = (inode->i_ino >> 16) & 0xFFFF;
- if (pid_alive(task)) {
- if (proc_type(inode) == PROC_TGID_INO || proc_type(inode) == PROC_TID_INO || task_dumpable(task)) {
+ if (!vx_proc_pid_visible(task, pid))
+ goto out_drop;
+
+ ret = 1;
+ if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
+ 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;
+ goto out_put;
}
out_drop:
d_drop(dentry);
+out_put:
+ if (task)
+ put_task_struct(task);
+ return ret;
+}
+
+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;
}
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 task_struct *task = get_proc_task(inode);
+ int fd = proc_fd(inode);
struct files_struct *files;
- files = get_files_struct(task);
- if (files) {
- spin_lock(&files->file_lock);
- if (fcheck_files(files, fd)) {
- spin_unlock(&files->file_lock);
- 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;
+ 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;
}
- security_task_to_inode(task, inode);
- return 1;
+ rcu_read_unlock();
+ put_files_struct(files);
}
- spin_unlock(&files->file_lock);
- put_files_struct(files);
+ put_task_struct(task);
}
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_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)
/* SMP-safe */
static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
{
- struct task_struct *task = proc_task(dir);
+ struct task_struct *task = get_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;
struct proc_inode *ei;
+ if (!task)
+ goto out_no_task;
if (fd == ~0U)
goto out;
- if (!pid_alive(task))
- goto out;
inode = proc_pid_make_inode(dir->i_sb, task, PROC_TID_FD_DIR+fd);
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;
+
+ /*
+ * 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)
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:
+ put_task_struct(task);
+out_no_task:
+ 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 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,
+ .setattr = proc_setattr,
};
static struct inode_operations proc_task_inode_operations = {
.lookup = proc_task_lookup,
- .permission = proc_permission,
+ .getattr = proc_task_getattr,
+ .setattr = proc_setattr,
};
#ifdef CONFIG_SECURITY
struct inode * inode = file->f_dentry->d_inode;
unsigned long page;
ssize_t length;
- ssize_t end;
- 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,
(void*)page, count);
- if (length < 0) {
- free_page(page);
- return length;
- }
- /* Static 4kB (or whatever) block capacity */
- if (*ppos >= length) {
- free_page(page);
- return 0;
- }
- if (count + *ppos > length)
- count = length - *ppos;
- end = count + *ppos;
- if (copy_to_user(buf, (char *) page + *ppos, count))
- count = -EFAULT;
- else
- *ppos = end;
+ if (length >= 0)
+ length = simple_read_from_buffer(buf, count, ppos, (char *)page, length);
free_page(page);
- return count;
+out:
+ put_task_struct(task);
+out_no_task:
+ return length;
}
static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
struct inode * inode = file->f_dentry->d_inode;
char *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;
- if (*ppos != 0) {
- /* No partial writes. */
- return -EINVAL;
- }
+
+ /* No partial writes. */
+ length = -EINVAL;
+ if (*ppos != 0)
+ goto out;
+
+ length = -ENOMEM;
page = (char*)__get_free_page(GFP_USER);
if (!page)
- return -ENOMEM;
+ goto out;
+
length = -EFAULT;
if (copy_from_user(page, buf, count))
- goto out;
+ goto out_free;
length = security_setprocattr(task,
(char*)file->f_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 inode_operations proc_tgid_attr_inode_operations;
#endif
+extern int proc_pid_vx_info(struct task_struct *, char *);
+extern int proc_pid_nx_info(struct task_struct *, char *);
+
+extern int proc_pid_vx_info(struct task_struct *, char *);
+extern int proc_pid_nx_info(struct task_struct *, char *);
+
/* SMP-safe */
static struct dentry *proc_pident_lookup(struct inode *dir,
struct dentry *dentry,
struct pid_entry *ents)
{
struct inode *inode;
- int error;
- struct task_struct *task = proc_task(dir);
+ struct dentry *error;
+ struct task_struct *task = get_proc_task(dir);
struct pid_entry *p;
struct proc_inode *ei;
- error = -ENOENT;
+ error = ERR_PTR(-ENOENT);
inode = NULL;
- if (!pid_alive(task))
- goto out;
+ if (!task)
+ goto out_no_task;
for (p = ents; p->name; p++) {
if (p->len != dentry->d_name.len)
if (!p->name)
goto out;
- error = -EINVAL;
+ 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 = 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 = 3;
+ inode->i_nlink = 2;
inode->i_op = &proc_task_inode_operations;
inode->i_fop = &proc_task_operations;
break;
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_pid_stat;
+ ei->op.proc_read = proc_tgid_stat;
break;
case PROC_TID_CMDLINE:
case PROC_TGID_CMDLINE:
case PROC_TGID_MAPS:
inode->i_fop = &proc_maps_operations;
break;
+#ifdef CONFIG_NUMA
+ case PROC_TID_NUMA_MAPS:
+ case PROC_TGID_NUMA_MAPS:
+ inode->i_fop = &proc_numa_maps_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_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;
+#ifdef CONFIG_MMU
+ case PROC_TID_SMAPS:
+ case PROC_TGID_SMAPS:
+ inode->i_fop = &proc_smaps_operations;
+ break;
+#endif
+ case PROC_TID_MOUNTSTATS:
+ case PROC_TGID_MOUNTSTATS:
+ inode->i_fop = &proc_mountstats_operations;
+ break;
#ifdef CONFIG_SECURITY
case PROC_TID_ATTR:
inode->i_nlink = 2;
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:
+ case PROC_TID_ATTR_SOCKCREATE:
+ case PROC_TGID_ATTR_SOCKCREATE:
inode->i_fop = &proc_pid_attr_operations;
break;
#endif
inode->i_fop = &proc_info_file_operations;
ei->op.proc_read = proc_pid_wchan;
break;
+#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;
+#endif
+#ifdef CONFIG_CPUSETS
+ case PROC_TID_CPUSET:
+ case PROC_TGID_CPUSET:
+ inode->i_fop = &proc_cpuset_operations;
+ break;
+#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;
+#ifdef CONFIG_AUDITSYSCALL
+ case PROC_TID_LOGINUID:
+ case PROC_TGID_LOGINUID:
+ inode->i_fop = &proc_loginuid_operations;
+ break;
#endif
case PROC_TID_VX_INFO:
case PROC_TGID_VX_INFO:
inode->i_fop = &proc_info_file_operations;
ei->op.proc_read = proc_pid_nx_info;
break;
-#ifdef CONFIG_DELAY_ACCT
- case PROC_TID_DELAY_ACCT:
- case PROC_TGID_DELAY_ACCT:
- inode->i_fop = &proc_info_file_operations;
- ei->op.proc_read = proc_pid_delay;
- 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);
+ put_task_struct(task);
+out_no_task:
+ return error;
}
static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
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,
+ .getattr = pid_getattr,
+ .setattr = proc_setattr,
};
#ifdef CONFIG_SECURITY
static struct inode_operations proc_tgid_attr_inode_operations = {
.lookup = proc_tgid_attr_lookup,
+ .getattr = pid_getattr,
+ .setattr = proc_setattr,
};
static struct inode_operations proc_tid_attr_inode_operations = {
.lookup = proc_tid_attr_lookup,
+ .getattr = pid_getattr,
+ .setattr = proc_setattr,
};
#endif
/*
* /proc/self:
*/
-static int proc_self_readlink(struct dentry *dentry, char *buffer, int buflen)
+static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
+ int buflen)
{
- char tmp[30];
- sprintf(tmp, "%d", current->tgid);
+ char tmp[PROC_NUMBUF];
+ sprintf(tmp, "%d", vx_map_tgid(current->tgid));
return vfs_readlink(dentry,buffer,buflen,tmp);
}
-static int proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
{
- char tmp[30];
- sprintf(tmp, "%d", current->tgid);
- return vfs_follow_link(nd,tmp);
+ char tmp[PROC_NUMBUF];
+ sprintf(tmp, "%d", vx_map_tgid(current->tgid));
+ return ERR_PTR(vfs_follow_link(nd,tmp));
}
static struct inode_operations proc_self_inode_operations = {
};
/**
- * 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.
+ *
+ * @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.
*
- * Drops the /proc/<pid> dcache entry from the hash chains.
+ * 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.
*
- * 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.
+ * 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);
- if (!d_unhashed(proc_dentry)) {
- dget_locked(proc_dentry);
- __d_drop(proc_dentry);
- } else
- 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_entry: directoy to prune.
- *
- * Shrink the /proc directory that was used by the just killed thread.
- */
-
-void proc_pid_flush(struct dentry *proc_dentry)
-{
- 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);
d_add(dentry, inode);
return NULL;
}
- tgid = vx_rmap_tgid(current->vx_info, name_to_int(dentry));
+ tgid = name_to_int(dentry);
if (tgid == ~0U)
goto out;
- read_lock(&tasklist_lock);
- task = find_task_by_pid(tgid);
+ rcu_read_lock();
+ task = vx_find_proc_task_by_pid(tgid);
if (task)
get_task_struct(task);
- read_unlock(&tasklist_lock);
+ rcu_read_unlock();
if (!task)
goto out;
- inode = NULL;
- if (vx_check(vx_task_xid(task), VX_WATCH|VX_IDENT))
- inode = proc_pid_make_inode(dir->i_sb, task, PROC_TGID_INO);
+ 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 = 3;
inode->i_flags|=S_IMMUTABLE;
+#ifdef CONFIG_SECURITY
+ inode->i_nlink = 5;
+#else
+ 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 task_struct *leader = get_proc_task(dir);
struct inode *inode;
unsigned tid;
- tid = vx_rmap_tgid(current->vx_info, name_to_int(dentry));
+ if (!leader)
+ goto out_no_task;
+
+ tid = name_to_int(dentry);
if (tid == ~0U)
goto out;
+ if (vx_current_initpid(tid))
+ goto out;
-/* handle fakeinit */
-
- 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;
- inode = NULL;
- if (vx_check(vx_task_xid(task), VX_WATCH|VX_IDENT))
- inode = proc_pid_make_inode(dir->i_sb, task, PROC_TID_INO);
+ 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_nlink = 3;
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;
+ 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);
+ 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 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)
-{
- struct task_struct *p;
- int nr_tgids = 0;
-
- index--;
- read_lock(&tasklist_lock);
- p = NULL;
- if (version) {
- p = find_task_by_pid(version);
- if (!thread_group_leader(p))
- p = NULL;
+static struct task_struct *first_tgid(int tgid, unsigned int nr)
+{
+ struct task_struct *pos;
+ rcu_read_lock();
+ if (tgid && nr) {
+ pos = vx_find_proc_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 (!vx_check(vx_task_xid(p), VX_WATCH|VX_IDENT))
- continue;
- if (--index >= 0)
- continue;
- tgids[nr_tgids] = vx_map_tgid(current->vx_info, 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 (!vx_check(vx_task_xid(task), VX_WATCH|VX_IDENT))
- continue;
- if (--index >= 0)
- continue;
- tids[nr_tids] = vx_map_tgid(current->vx_info, 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;
+ 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 last tgid which was returned from readdir
+ /* f_version caches the tgid value that the last readdir call couldn't
+ * return. lseek aka telldir automagically resets f_version to 0.
*/
- nr_tgids = get_tgid_list(nr, filp->f_version, tgid_array);
-
- 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;
-
- do buf[--j] = '0' + (tgid % 10); while (tgid/=10);
+ tgid = filp->f_version;
+ filp->f_version = 0;
+ for (task = first_tgid(tgid, nr);
+ task;
+ task = next_tgid(task), filp->f_pos++) {
+ int len;
+ ino_t ino;
+ tgid = vx_map_tgid(task->pid);
+ if (!vx_proc_pid_visible(task, tgid))
+ continue;
- if (filldir(dirent, buf+j, PROC_NUMBUF-j, filp->f_pos, ino, DT_DIR) < 0) {
+ 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;
}
- filp->f_pos++;
}
return 0;
}
+/*
+ * 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;
+
+ rcu_read_lock();
+ /* Attempt to start with the pid of a thread */
+ if (tid && (nr > 0)) {
+ pos = vx_find_proc_task_by_pid(tid);
+ if (pos && (pos->group_leader == leader))
+ goto found;
+ }
+
+ /* If nr exceeds the number of threads there is nothing todo */
+ pos = NULL;
+ if (nr && nr >= get_nr_threads(leader))
+ goto out;
+
+ /* 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;
+ }
+ }
+found:
+ get_task_struct(pos);
+out:
+ rcu_read_unlock();
+ 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 = 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/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 *task = proc_task(inode);
+ struct task_struct *leader = get_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 (!vx_check(vx_task_xid(task), VX_WATCH|VX_IDENT))
- goto out;
- if (!pid_alive(task))
- goto out;
+ if (!leader)
+ goto out_no_task;
retval = 0;
switch (pos) {
/* 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);
+ /* 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 = vx_map_pid(task->pid);
+ if (!vx_proc_pid_visible(task, tid))
+ continue;
- if (filldir(dirent, buf+j, PROC_NUMBUF-j, pos, ino, DT_DIR) < 0)
+ 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;
+ 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;
+}