#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/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/namespace.h>
+#include <linux/mnt_namespace.h>
#include <linux/mm.h>
-#include <linux/smp_lock.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/seccomp.h>
+#include <linux/tracehook.h>
+#include <linux/cgroup.h>
#include <linux/cpuset.h>
#include <linux/audit.h>
#include <linux/poll.h>
+#include <linux/nsproxy.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:
* in /proc for a task before it execs a suid executable.
*/
-/*
- * For hysterical raisins we keep the same inumbers as in the old procfs.
- * Feel free to change the macro below - just keep the range distinct from
- * inumbers of the rest of procfs (currently those are in 0x0000--0xffff).
- * As soon as we'll get a separate superblock we will be able to forget
- * about magical ranges too.
- */
-
-#define fake_ino(pid,ino) (((pid)<<16)|(ino))
-
-enum pid_directory_inos {
- PROC_TGID_INO = 2,
- PROC_TGID_TASK,
- PROC_TGID_STATUS,
- PROC_TGID_MEM,
-#ifdef CONFIG_SECCOMP
- PROC_TGID_SECCOMP,
-#endif
- PROC_TGID_CWD,
- PROC_TGID_ROOT,
- PROC_TGID_EXE,
- PROC_TGID_FD,
- PROC_TGID_ENVIRON,
- PROC_TGID_AUXV,
- PROC_TGID_CMDLINE,
- PROC_TGID_STAT,
- PROC_TGID_STATM,
- PROC_TGID_MAPS,
- PROC_TGID_NUMA_MAPS,
- PROC_TGID_MOUNTS,
- PROC_TGID_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,
-#endif
-#ifdef CONFIG_AUDITSYSCALL
- PROC_TGID_LOGINUID,
-#endif
- PROC_TGID_OOM_SCORE,
- PROC_TGID_OOM_ADJUST,
- PROC_TID_INO,
- PROC_TID_STATUS,
- PROC_TID_MEM,
-#ifdef CONFIG_SECCOMP
- PROC_TID_SECCOMP,
-#endif
- PROC_TID_CWD,
- PROC_TID_ROOT,
- PROC_TID_EXE,
- PROC_TID_FD,
- PROC_TID_ENVIRON,
- PROC_TID_AUXV,
- PROC_TID_CMDLINE,
- PROC_TID_STAT,
- PROC_TID_STATM,
- PROC_TID_MAPS,
- PROC_TID_NUMA_MAPS,
- PROC_TID_MOUNTS,
- PROC_TID_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,
-#endif
-#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 */
-};
-
struct pid_entry {
- int type;
- int len;
char *name;
+ int len;
mode_t mode;
+ const struct inode_operations *iop;
+ const struct file_operations *fop;
+ union proc_op op;
};
-#define E(type,name,mode) {(type),sizeof(name)-1,(name),(mode)}
-
-static struct pid_entry tgid_base_stuff[] = {
- E(PROC_TGID_TASK, "task", S_IFDIR|S_IRUGO|S_IXUGO),
- E(PROC_TGID_FD, "fd", S_IFDIR|S_IRUSR|S_IXUSR),
- E(PROC_TGID_ENVIRON, "environ", S_IFREG|S_IRUSR),
- E(PROC_TGID_AUXV, "auxv", S_IFREG|S_IRUSR),
- E(PROC_TGID_STATUS, "status", S_IFREG|S_IRUGO),
- E(PROC_TGID_CMDLINE, "cmdline", S_IFREG|S_IRUGO),
- E(PROC_TGID_STAT, "stat", S_IFREG|S_IRUGO),
- E(PROC_TGID_STATM, "statm", S_IFREG|S_IRUGO),
- E(PROC_TGID_MAPS, "maps", S_IFREG|S_IRUGO),
-#ifdef CONFIG_NUMA
- E(PROC_TGID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO),
-#endif
- E(PROC_TGID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR),
-#ifdef CONFIG_SECCOMP
- E(PROC_TGID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR),
-#endif
- E(PROC_TGID_CWD, "cwd", S_IFLNK|S_IRWXUGO),
- E(PROC_TGID_ROOT, "root", S_IFLNK|S_IRWXUGO),
- E(PROC_TGID_EXE, "exe", S_IFLNK|S_IRWXUGO),
- E(PROC_TGID_MOUNTS, "mounts", S_IFREG|S_IRUGO),
- E(PROC_TGID_MOUNTSTATS, "mountstats", S_IFREG|S_IRUSR),
-#ifdef CONFIG_MMU
- E(PROC_TGID_SMAPS, "smaps", S_IFREG|S_IRUGO),
-#endif
-#ifdef CONFIG_SECURITY
- E(PROC_TGID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO),
-#endif
-#ifdef CONFIG_KALLSYMS
- E(PROC_TGID_WCHAN, "wchan", S_IFREG|S_IRUGO),
-#endif
-#ifdef CONFIG_SCHEDSTATS
- E(PROC_TGID_SCHEDSTAT, "schedstat", S_IFREG|S_IRUGO),
-#endif
-#ifdef CONFIG_CPUSETS
- E(PROC_TGID_CPUSET, "cpuset", S_IFREG|S_IRUGO),
-#endif
- E(PROC_TGID_OOM_SCORE, "oom_score",S_IFREG|S_IRUGO),
- E(PROC_TGID_OOM_ADJUST,"oom_adj", S_IFREG|S_IRUGO|S_IWUSR),
-#ifdef CONFIG_AUDITSYSCALL
- E(PROC_TGID_LOGINUID, "loginuid", S_IFREG|S_IWUSR|S_IRUGO),
-#endif
- {0,0,NULL,0}
-};
-static struct pid_entry tid_base_stuff[] = {
- E(PROC_TID_FD, "fd", S_IFDIR|S_IRUSR|S_IXUSR),
- E(PROC_TID_ENVIRON, "environ", S_IFREG|S_IRUSR),
- E(PROC_TID_AUXV, "auxv", S_IFREG|S_IRUSR),
- E(PROC_TID_STATUS, "status", S_IFREG|S_IRUGO),
- E(PROC_TID_CMDLINE, "cmdline", S_IFREG|S_IRUGO),
- E(PROC_TID_STAT, "stat", S_IFREG|S_IRUGO),
- E(PROC_TID_STATM, "statm", S_IFREG|S_IRUGO),
- E(PROC_TID_MAPS, "maps", S_IFREG|S_IRUGO),
-#ifdef CONFIG_NUMA
- E(PROC_TID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO),
-#endif
- E(PROC_TID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR),
-#ifdef CONFIG_SECCOMP
- E(PROC_TID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR),
-#endif
- E(PROC_TID_CWD, "cwd", S_IFLNK|S_IRWXUGO),
- E(PROC_TID_ROOT, "root", S_IFLNK|S_IRWXUGO),
- E(PROC_TID_EXE, "exe", S_IFLNK|S_IRWXUGO),
- E(PROC_TID_MOUNTS, "mounts", S_IFREG|S_IRUGO),
-#ifdef CONFIG_MMU
- E(PROC_TID_SMAPS, "smaps", S_IFREG|S_IRUGO),
-#endif
-#ifdef CONFIG_SECURITY
- E(PROC_TID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO),
-#endif
-#ifdef CONFIG_KALLSYMS
- E(PROC_TID_WCHAN, "wchan", S_IFREG|S_IRUGO),
-#endif
-#ifdef CONFIG_SCHEDSTATS
- E(PROC_TID_SCHEDSTAT, "schedstat",S_IFREG|S_IRUGO),
-#endif
-#ifdef CONFIG_CPUSETS
- E(PROC_TID_CPUSET, "cpuset", S_IFREG|S_IRUGO),
-#endif
- E(PROC_TID_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}
-};
-
-#ifdef CONFIG_SECURITY
-static struct pid_entry tgid_attr_stuff[] = {
- E(PROC_TGID_ATTR_CURRENT, "current", S_IFREG|S_IRUGO|S_IWUGO),
- E(PROC_TGID_ATTR_PREV, "prev", S_IFREG|S_IRUGO),
- E(PROC_TGID_ATTR_EXEC, "exec", S_IFREG|S_IRUGO|S_IWUGO),
- E(PROC_TGID_ATTR_FSCREATE, "fscreate", S_IFREG|S_IRUGO|S_IWUGO),
- E(PROC_TGID_ATTR_KEYCREATE, "keycreate", S_IFREG|S_IRUGO|S_IWUGO),
- {0,0,NULL,0}
-};
-static struct pid_entry tid_attr_stuff[] = {
- E(PROC_TID_ATTR_CURRENT, "current", S_IFREG|S_IRUGO|S_IWUGO),
- E(PROC_TID_ATTR_PREV, "prev", S_IFREG|S_IRUGO),
- E(PROC_TID_ATTR_EXEC, "exec", S_IFREG|S_IRUGO|S_IWUGO),
- E(PROC_TID_ATTR_FSCREATE, "fscreate", S_IFREG|S_IRUGO|S_IWUGO),
- E(PROC_TID_ATTR_KEYCREATE, "keycreate", S_IFREG|S_IRUGO|S_IWUGO),
- {0,0,NULL,0}
-};
-#endif
+#define NOD(NAME, MODE, IOP, FOP, OP) { \
+ .name = (NAME), \
+ .len = sizeof(NAME) - 1, \
+ .mode = MODE, \
+ .iop = IOP, \
+ .fop = FOP, \
+ .op = OP, \
+}
-#undef E
+#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 = 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 = read } )
+#define ONE(NAME, MODE, show) \
+ NOD(NAME, (S_IFREG|(MODE)), \
+ NULL, &proc_single_file_operations, \
+ { .proc_show = show } )
-static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
+/*
+ * 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)
{
- struct task_struct *task = proc_task(inode);
- struct files_struct *files;
- struct file *file;
- int fd = proc_fd(inode);
+ unsigned int i;
+ unsigned int count;
- files = get_files_struct(task);
- if (files) {
- /*
- * We are not taking a ref to the file structure, so we must
- * hold ->file_lock.
- */
- spin_lock(&files->file_lock);
- file = fcheck_files(files, fd);
- if (file) {
- *mnt = mntget(file->f_vfsmnt);
- *dentry = dget(file->f_dentry);
- spin_unlock(&files->file_lock);
- put_files_struct(files);
- return 0;
- }
- spin_unlock(&files->file_lock);
- put_files_struct(files);
+ count = 0;
+ for (i = 0; i < n; ++i) {
+ if (S_ISDIR(entries[i].mode))
+ ++count;
}
- return -ENOENT;
+
+ 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)
+{
+ unsigned long flags;
+ int count = 0;
+
+ if (lock_task_sighand(tsk, &flags)) {
+ count = atomic_read(&tsk->signal->count);
+ unlock_task_sighand(tsk, &flags);
+ }
+ return count;
}
-static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
+static int proc_cwd_link(struct inode *inode, struct path *path)
{
- struct fs_struct *fs = get_fs_struct(proc_task(inode));
+ struct task_struct *task = get_proc_task(inode);
int result = -ENOENT;
- if (fs) {
- read_lock(&fs->lock);
- *mnt = mntget(fs->pwdmnt);
- *dentry = dget(fs->pwd);
- read_unlock(&fs->lock);
- result = 0;
- put_fs_struct(fs);
+
+ if (task) {
+ result = get_fs_path(task, path, 0);
+ put_task_struct(task);
}
return result;
}
-static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
+static int proc_root_link(struct inode *inode, struct path *path)
{
- struct fs_struct *fs = get_fs_struct(proc_task(inode));
+ struct task_struct *task = get_proc_task(inode);
int result = -ENOENT;
- if (fs) {
- read_lock(&fs->lock);
- *mnt = mntget(fs->rootmnt);
- *dentry = dget(fs->root);
- read_unlock(&fs->lock);
- result = 0;
- put_fs_struct(fs);
+
+ if (task) {
+ result = get_fs_path(task, path, 1);
+ put_task_struct(task);
}
return result;
}
-#define MAY_PTRACE(task) \
- (task == current || \
- (task->parent == current && \
- (task->ptrace & PT_PTRACED) && \
- (task->state == TASK_STOPPED || task->state == TASK_TRACED) && \
- security_ptrace(current,task) == 0))
+/*
+ * 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;
+}
-static int proc_pid_environ(struct task_struct *task, char * buffer)
+struct mm_struct *mm_for_maps(struct task_struct *task)
{
- int res = 0;
- struct mm_struct *mm = get_task_mm(task);
- if (mm) {
- unsigned int len = mm->env_end - mm->env_start;
- if (len > PAGE_SIZE)
- len = PAGE_SIZE;
- res = access_process_vm(task, mm->env_start, buffer, len, 0);
- if (!ptrace_may_attach(task))
- res = -ESRCH;
+ struct mm_struct *mm;
+
+ if (mutex_lock_killable(&task->cred_guard_mutex))
+ return NULL;
+
+ mm = get_task_mm(task);
+ if (mm && mm != current->mm &&
+ !ptrace_may_access(task, PTRACE_MODE_READ)) {
mmput(mm);
+ mm = NULL;
}
- return res;
+ mutex_unlock(&task->cred_guard_mutex);
+
+ return mm;
}
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;
*/
static int proc_pid_wchan(struct task_struct *task, char *buffer)
{
- char *modname;
- const char *sym_name;
- unsigned long wchan, size, offset;
- char namebuf[KSYM_NAME_LEN+1];
+ unsigned long wchan;
+ char symname[KSYM_NAME_LEN];
wchan = get_wchan(task);
- sym_name = kallsyms_lookup(wchan, &size, &offset, &modname, namebuf);
- if (sym_name)
- return sprintf(buffer, "%s", sym_name);
- return sprintf(buffer, "%lu", wchan);
+ if (lookup_symbol_name(wchan, symname) < 0)
+ 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, "%lu %lu %lu\n",
- task->sched_info.cpu_time,
- task->sched_info.run_delay,
- task->sched_info.pcnt);
+ return sprintf(buffer, "%llu %llu %lu\n",
+ (unsigned long long)task->se.sum_exec_runtime,
+ (unsigned long long)task->sched_info.run_delay,
+ task->sched_info.pcount);
+}
+#endif
+
+#ifdef CONFIG_LATENCYTOP
+static int lstats_show_proc(struct seq_file *m, void *v)
+{
+ int i;
+ struct inode *inode = m->private;
+ struct task_struct *task = get_proc_task(inode);
+
+ if (!task)
+ return -ESRCH;
+ seq_puts(m, "Latency Top version : v0.1\n");
+ for (i = 0; i < 32; i++) {
+ if (task->latency_record[i].backtrace[0]) {
+ int q;
+ seq_printf(m, "%i %li %li ",
+ task->latency_record[i].count,
+ task->latency_record[i].time,
+ task->latency_record[i].max);
+ for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
+ char sym[KSYM_SYMBOL_LEN];
+ char *c;
+ if (!task->latency_record[i].backtrace[q])
+ break;
+ if (task->latency_record[i].backtrace[q] == ULONG_MAX)
+ break;
+ sprint_symbol(sym, task->latency_record[i].backtrace[q]);
+ c = strchr(sym, '+');
+ if (c)
+ *c = 0;
+ seq_printf(m, "%s ", sym);
+ }
+ seq_printf(m, "\n");
+ }
+
+ }
+ put_task_struct(task);
+ return 0;
+}
+
+static int lstats_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, lstats_show_proc, inode);
+}
+
+static ssize_t lstats_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *offs)
+{
+ struct task_struct *task = get_proc_task(file->f_dentry->d_inode);
+
+ if (!task)
+ return -ESRCH;
+ clear_all_latency_tracing(task);
+ put_task_struct(task);
+
+ return count;
}
+
+static const struct file_operations proc_lstats_operations = {
+ .open = lstats_open,
+ .read = seq_read,
+ .write = lstats_write,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
#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;
+ unsigned long points = 0;
struct timespec uptime;
do_posix_clock_monotonic_gettime(&uptime);
- points = badness(task, uptime.tv_sec);
+ read_lock(&tasklist_lock);
+ if (pid_alive(task))
+ points = badness(task, uptime.tv_sec);
+ read_unlock(&tasklist_lock);
return sprintf(buffer, "%lu\n", points);
}
-/************************************************************************/
-/* Here the fs part begins */
-/************************************************************************/
+struct limit_names {
+ char *name;
+ char *unit;
+};
-/* permission checks */
+static const struct limit_names lnames[RLIM_NLIMITS] = {
+ [RLIMIT_CPU] = {"Max cpu time", "seconds"},
+ [RLIMIT_FSIZE] = {"Max file size", "bytes"},
+ [RLIMIT_DATA] = {"Max data size", "bytes"},
+ [RLIMIT_STACK] = {"Max stack size", "bytes"},
+ [RLIMIT_CORE] = {"Max core file size", "bytes"},
+ [RLIMIT_RSS] = {"Max resident set", "bytes"},
+ [RLIMIT_NPROC] = {"Max processes", "processes"},
+ [RLIMIT_NOFILE] = {"Max open files", "files"},
+ [RLIMIT_MEMLOCK] = {"Max locked memory", "bytes"},
+ [RLIMIT_AS] = {"Max address space", "bytes"},
+ [RLIMIT_LOCKS] = {"Max file locks", "locks"},
+ [RLIMIT_SIGPENDING] = {"Max pending signals", "signals"},
+ [RLIMIT_MSGQUEUE] = {"Max msgqueue size", "bytes"},
+ [RLIMIT_NICE] = {"Max nice priority", NULL},
+ [RLIMIT_RTPRIO] = {"Max realtime priority", NULL},
+ [RLIMIT_RTTIME] = {"Max realtime timeout", "us"},
+};
-/* If the process being read is separated by chroot from the reading process,
- * don't let the reader access the threads.
- */
-static int proc_check_chroot(struct dentry *de, struct vfsmount *mnt)
+/* Display limits for a process */
+static int proc_pid_limits(struct task_struct *task, char *buffer)
{
- struct dentry *base;
- struct vfsmount *our_vfsmnt;
- int res = 0;
+ unsigned int i;
+ int count = 0;
+ unsigned long flags;
+ char *bufptr = buffer;
- read_lock(¤t->fs->lock);
- our_vfsmnt = mntget(current->fs->rootmnt);
- base = dget(current->fs->root);
- read_unlock(¤t->fs->lock);
+ struct rlimit rlim[RLIM_NLIMITS];
- spin_lock(&vfsmount_lock);
+ if (!lock_task_sighand(task, &flags))
+ return 0;
+ memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS);
+ unlock_task_sighand(task, &flags);
- while (mnt != our_vfsmnt) {
- if (mnt == mnt->mnt_parent)
- goto out;
- de = mnt->mnt_mountpoint;
- mnt = mnt->mnt_parent;
+ /*
+ * print the file header
+ */
+ count += sprintf(&bufptr[count], "%-25s %-20s %-20s %-10s\n",
+ "Limit", "Soft Limit", "Hard Limit", "Units");
+
+ for (i = 0; i < RLIM_NLIMITS; i++) {
+ if (rlim[i].rlim_cur == RLIM_INFINITY)
+ count += sprintf(&bufptr[count], "%-25s %-20s ",
+ lnames[i].name, "unlimited");
+ else
+ count += sprintf(&bufptr[count], "%-25s %-20lu ",
+ lnames[i].name, rlim[i].rlim_cur);
+
+ if (rlim[i].rlim_max == RLIM_INFINITY)
+ count += sprintf(&bufptr[count], "%-20s ", "unlimited");
+ else
+ count += sprintf(&bufptr[count], "%-20lu ",
+ rlim[i].rlim_max);
+
+ if (lnames[i].unit)
+ count += sprintf(&bufptr[count], "%-10s\n",
+ lnames[i].unit);
+ else
+ count += sprintf(&bufptr[count], "\n");
}
- if (!is_subdir(de, base))
- goto out;
- spin_unlock(&vfsmount_lock);
+ return count;
+}
-exit:
- dput(base);
- mntput(our_vfsmnt);
- return res;
-out:
- spin_unlock(&vfsmount_lock);
- res = -EACCES;
- goto exit;
+#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 */
+/************************************************************************/
+
+/* permission checks */
+static int proc_fd_access_allowed(struct inode *inode)
+{
+ 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_access(task, PTRACE_MODE_READ);
+ put_task_struct(task);
+ }
+ return allowed;
+}
+
+static int proc_setattr(struct dentry *dentry, struct iattr *attr)
+{
+ int error;
+ struct inode *inode = dentry->d_inode;
+
+ if (attr->ia_valid & ATTR_MODE)
+ return -EPERM;
+
+ error = inode_change_ok(inode, attr);
+ if (!error)
+ error = inode_setattr(inode, attr);
+ return error;
}
-extern struct seq_operations mounts_op;
-struct proc_mounts {
- struct seq_file m;
- int event;
+static const struct inode_operations proc_def_inode_operations = {
+ .setattr = proc_setattr,
};
-static int mounts_open(struct inode *inode, struct file *file)
+static int mounts_open_common(struct inode *inode, struct file *file,
+ const struct seq_operations *op)
{
- struct task_struct *task = proc_task(inode);
- struct namespace *namespace;
+ struct task_struct *task = get_proc_task(inode);
+ struct nsproxy *nsp;
+ struct mnt_namespace *ns = NULL;
+ struct path root;
struct proc_mounts *p;
int ret = -EINVAL;
- task_lock(task);
- namespace = task->namespace;
- if (namespace)
- get_namespace(namespace);
- task_unlock(task);
-
- 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);
+ if (task) {
+ rcu_read_lock();
+ nsp = task_nsproxy(task);
+ if (nsp) {
+ ns = nsp->mnt_ns;
+ if (ns)
+ get_mnt_ns(ns);
}
- put_namespace(namespace);
+ rcu_read_unlock();
+ if (ns && get_fs_path(task, &root, 1) == 0)
+ ret = 0;
+ put_task_struct(task);
}
+
+ if (!ns)
+ goto err;
+ if (ret)
+ goto err_put_ns;
+
+ ret = -ENOMEM;
+ p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL);
+ if (!p)
+ goto err_put_path;
+
+ file->private_data = &p->m;
+ ret = seq_open(file, op);
+ if (ret)
+ goto err_free;
+
+ p->m.private = p;
+ p->ns = ns;
+ p->root = root;
+ p->event = ns->event;
+
+ return 0;
+
+ err_free:
+ kfree(p);
+ err_put_path:
+ path_put(&root);
+ err_put_ns:
+ put_mnt_ns(ns);
+ err:
return ret;
}
static int mounts_release(struct inode *inode, struct file *file)
{
- struct seq_file *m = file->private_data;
- struct namespace *namespace = m->private;
- put_namespace(namespace);
+ struct proc_mounts *p = file->private_data;
+ path_put(&p->root);
+ put_mnt_ns(p->ns);
return seq_release(inode, file);
}
static unsigned mounts_poll(struct file *file, poll_table *wait)
{
struct proc_mounts *p = file->private_data;
- struct namespace *ns = p->m.private;
- unsigned res = 0;
+ unsigned res = POLLIN | POLLRDNORM;
- 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);
+ poll_wait(file, &p->ns->poll, wait);
+ if (mnt_had_events(p))
+ res |= POLLERR | POLLPRI;
return res;
}
-static struct file_operations proc_mounts_operations = {
+static int mounts_open(struct inode *inode, struct file *file)
+{
+ return mounts_open_common(inode, file, &mounts_op);
+}
+
+static const struct file_operations proc_mounts_operations = {
.open = mounts_open,
.read = seq_read,
.llseek = seq_lseek,
.poll = mounts_poll,
};
-extern struct seq_operations mountstats_op;
-static int mountstats_open(struct inode *inode, struct file *file)
+static int mountinfo_open(struct inode *inode, struct file *file)
{
- struct task_struct *task = proc_task(inode);
- int ret = seq_open(file, &mountstats_op);
-
- if (!ret) {
- struct seq_file *m = file->private_data;
- struct namespace *namespace;
- task_lock(task);
- namespace = task->namespace;
- if (namespace)
- get_namespace(namespace);
- task_unlock(task);
-
- if (namespace)
- m->private = namespace;
- else {
- seq_release(inode, file);
- ret = -EINVAL;
- }
- }
- return ret;
+ return mounts_open_common(inode, file, &mountinfo_op);
}
-static struct file_operations proc_mountstats_operations = {
+static const struct file_operations proc_mountinfo_operations = {
+ .open = mountinfo_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = mounts_release,
+ .poll = mounts_poll,
+};
+
+static int mountstats_open(struct inode *inode, struct file *file)
+{
+ return mounts_open_common(inode, file, &mountstats_op);
+}
+
+static const struct file_operations proc_mountstats_operations = {
.open = mountstats_open,
.read = seq_read,
.llseek = seq_lseek,
static ssize_t proc_info_read(struct file * file, char __user * buf,
size_t count, loff_t *ppos)
{
- struct inode * inode = file->f_dentry->d_inode;
+ struct inode * inode = file->f_path.dentry->d_inode;
unsigned long page;
ssize_t length;
- struct task_struct *task = proc_task(inode);
+ struct task_struct *task = get_proc_task(inode);
+
+ length = -ESRCH;
+ if (!task)
+ goto out_no_task;
if (count > PROC_BLOCK_SIZE)
count = PROC_BLOCK_SIZE;
- if (!(page = __get_free_page(GFP_KERNEL)))
- return -ENOMEM;
+
+ length = -ENOMEM;
+ if (!(page = __get_free_page(GFP_TEMPORARY)))
+ goto out;
length = PROC_I(inode)->op.proc_read(task, (char*)page);
if (length >= 0)
length = simple_read_from_buffer(buf, count, ppos, (char *)page, length);
free_page(page);
+out:
+ put_task_struct(task);
+out_no_task:
return length;
}
-static struct file_operations proc_info_file_operations = {
+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)
+{
+ struct inode *inode = m->private;
+ struct pid_namespace *ns;
+ struct pid *pid;
+ struct task_struct *task;
+ int ret;
+
+ ns = inode->i_sb->s_fs_info;
+ pid = proc_pid(inode);
+ task = get_pid_task(pid, PIDTYPE_PID);
+ if (!task)
+ return -ESRCH;
+
+ ret = PROC_I(inode)->op.proc_show(m, ns, pid, task);
+
+ put_task_struct(task);
+ return ret;
+}
+
+static int proc_single_open(struct inode *inode, struct file *filp)
+{
+ int ret;
+ ret = single_open(filp, proc_single_show, NULL);
+ if (!ret) {
+ struct seq_file *m = filp->private_data;
+
+ m->private = inode;
+ }
+ return ret;
+}
+
+static const struct file_operations proc_single_file_operations = {
+ .open = proc_single_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
};
static int mem_open(struct inode* inode, struct file* file)
static ssize_t mem_read(struct file * file, char __user * buf,
size_t count, loff_t *ppos)
{
- struct task_struct *task = proc_task(file->f_dentry->d_inode);
+ struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
char *page;
unsigned long src = *ppos;
int ret = -ESRCH;
struct mm_struct *mm;
- if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
+ if (!task)
+ goto out_no_task;
+
+ if (check_mem_permission(task))
goto out;
ret = -ENOMEM;
- page = (char *)__get_free_page(GFP_USER);
+ page = (char *)__get_free_page(GFP_TEMPORARY);
if (!page)
goto out;
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;
out_free:
free_page((unsigned long) page);
out:
+ put_task_struct(task);
+out_no_task:
return ret;
}
#ifndef mem_write
/* This is a security hazard */
-static ssize_t mem_write(struct file * file, const char * buf,
+static ssize_t mem_write(struct file * file, const char __user *buf,
size_t count, loff_t *ppos)
{
- int copied = 0;
+ int copied;
char *page;
- struct task_struct *task = proc_task(file->f_dentry->d_inode);
+ struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
unsigned long dst = *ppos;
- if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
- return -ESRCH;
+ copied = -ESRCH;
+ if (!task)
+ goto out_no_task;
+
+ if (check_mem_permission(task))
+ goto out;
- page = (char *)__get_free_page(GFP_USER);
+ copied = -ENOMEM;
+ page = (char *)__get_free_page(GFP_TEMPORARY);
if (!page)
- return -ENOMEM;
+ goto out;
+ copied = 0;
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
-static loff_t mem_lseek(struct file * file, loff_t offset, int orig)
+loff_t mem_lseek(struct file *file, loff_t offset, int orig)
{
switch (orig) {
case 0:
return file->f_pos;
}
-static struct file_operations proc_mem_operations = {
+static const struct file_operations proc_mem_operations = {
.llseek = mem_lseek,
.read = mem_read,
.write = mem_write,
.open = mem_open,
};
+static ssize_t environ_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 *page;
+ unsigned long src = *ppos;
+ int ret = -ESRCH;
+ struct mm_struct *mm;
+
+ if (!task)
+ goto out_no_task;
+
+ if (!ptrace_may_access(task, PTRACE_MODE_READ))
+ goto out;
+
+ ret = -ENOMEM;
+ page = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!page)
+ goto out;
+
+ ret = 0;
+
+ mm = get_task_mm(task);
+ if (!mm)
+ goto out_free;
+
+ while (count > 0) {
+ int this_len, retval, max_len;
+
+ this_len = mm->env_end - (mm->env_start + src);
+
+ if (this_len <= 0)
+ break;
+
+ max_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
+ this_len = (this_len > max_len) ? max_len : this_len;
+
+ retval = access_process_vm(task, (mm->env_start + src),
+ page, this_len, 0);
+
+ if (retval <= 0) {
+ ret = retval;
+ break;
+ }
+
+ if (copy_to_user(buf, page, retval)) {
+ ret = -EFAULT;
+ break;
+ }
+
+ ret += retval;
+ src += retval;
+ buf += retval;
+ count -= retval;
+ }
+ *ppos = src;
+
+ mmput(mm);
+out_free:
+ free_page((unsigned long) page);
+out:
+ put_task_struct(task);
+out_no_task:
+ return ret;
+}
+
+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,
size_t count, loff_t *ppos)
{
- struct task_struct *task = proc_task(file->f_dentry->d_inode);
- char buffer[8];
+ struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+ char buffer[PROC_NUMBUF];
size_t len;
- int oom_adjust = task->oomkilladj;
- loff_t __ppos = *ppos;
+ int oom_adjust = OOM_DISABLE;
+ unsigned long flags;
- len = sprintf(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;
+ if (!task)
+ return -ESRCH;
+
+ 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);
+
+ return simple_read_from_buffer(buf, count, ppos, buffer, len);
}
static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
- struct task_struct *task = proc_task(file->f_dentry->d_inode);
- char buffer[8], *end;
- int oom_adjust;
-
- if (!capable(CAP_SYS_RESOURCE))
- return -EPERM;
- memset(buffer, 0, 8);
- if (count > 6)
- count = 6;
+ struct task_struct *task;
+ 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);
- if ((oom_adjust < -16 || oom_adjust > 15) && oom_adjust != OOM_DISABLE)
+
+ err = strict_strtol(strstrip(buffer), 0, &oom_adjust);
+ if (err)
return -EINVAL;
- if (*end == '\n')
- end++;
- task->oomkilladj = oom_adjust;
- if (end - buffer == 0)
- return -EIO;
- return end - buffer;
+ if ((oom_adjust < OOM_ADJUST_MIN || oom_adjust > OOM_ADJUST_MAX) &&
+ oom_adjust != OOM_DISABLE)
+ return -EINVAL;
+
+ task = get_proc_task(file->f_path.dentry->d_inode);
+ if (!task)
+ return -ESRCH;
+ 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->signal->oom_adj = oom_adjust;
+
+ unlock_task_sighand(task, &flags);
+ put_task_struct(task);
+
+ return count;
}
-static struct file_operations proc_oom_adjust_operations = {
+static const struct file_operations proc_oom_adjust_operations = {
.read = oom_adjust_read,
.write = oom_adjust_write,
+ .llseek = generic_file_llseek,
};
#ifdef CONFIG_AUDITSYSCALL
static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
size_t count, loff_t *ppos)
{
- struct inode * inode = file->f_dentry->d_inode;
- struct task_struct *task = proc_task(inode);
+ struct inode * inode = file->f_path.dentry->d_inode;
+ struct task_struct *task = get_proc_task(inode);
ssize_t length;
char tmpbuf[TMPBUFLEN];
+ if (!task)
+ return -ESRCH;
length = scnprintf(tmpbuf, TMPBUFLEN, "%u",
- audit_get_loginuid(task->audit_context));
+ audit_get_loginuid(task));
+ put_task_struct(task);
return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
}
static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
size_t count, loff_t *ppos)
{
- struct inode * inode = file->f_dentry->d_inode;
+ struct inode * inode = file->f_path.dentry->d_inode;
char *page, *tmp;
ssize_t length;
- struct task_struct *task = proc_task(inode);
uid_t loginuid;
if (!capable(CAP_AUDIT_CONTROL))
return -EPERM;
- if (current != task)
+ 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;
/* No partial writes. */
return -EINVAL;
}
- page = (char*)__get_free_page(GFP_USER);
+ page = (char*)__get_free_page(GFP_TEMPORARY);
if (!page)
return -ENOMEM;
length = -EFAULT;
goto out_free_page;
}
- length = audit_set_loginuid(task, loginuid);
+ length = audit_set_loginuid(current, loginuid);
if (likely(length == 0))
length = count;
return length;
}
-static struct file_operations proc_loginuid_operations = {
+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,
+ size_t count, loff_t *ppos)
+{
+ struct inode * inode = file->f_path.dentry->d_inode;
+ struct task_struct *task = get_proc_task(inode);
+ ssize_t length;
+ char tmpbuf[TMPBUFLEN];
+
+ if (!task)
+ return -ESRCH;
+ length = scnprintf(tmpbuf, TMPBUFLEN, "%u",
+ audit_get_sessionid(task));
+ put_task_struct(task);
+ return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
+}
+
+static const struct file_operations proc_sessionid_operations = {
+ .read = proc_sessionid_read,
+ .llseek = generic_file_llseek,
};
#endif
-#ifdef CONFIG_SECCOMP
-static ssize_t seccomp_read(struct file *file, char __user *buf,
- size_t count, loff_t *ppos)
+#ifdef CONFIG_FAULT_INJECTION
+static ssize_t proc_fault_inject_read(struct file * file, char __user * buf,
+ size_t count, loff_t *ppos)
{
- struct task_struct *tsk = proc_task(file->f_dentry->d_inode);
- char __buf[20];
- loff_t __ppos = *ppos;
+ struct task_struct *task = get_proc_task(file->f_dentry->d_inode);
+ char buffer[PROC_NUMBUF];
size_t len;
+ int make_it_fail;
- /* no need to print the trailing zero, so use only len */
- len = sprintf(__buf, "%u\n", tsk->seccomp.mode);
- 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;
+ if (!task)
+ return -ESRCH;
+ make_it_fail = task->make_it_fail;
+ put_task_struct(task);
+
+ len = snprintf(buffer, sizeof(buffer), "%i\n", make_it_fail);
+
+ return simple_read_from_buffer(buf, count, ppos, buffer, len);
}
-static ssize_t seccomp_write(struct file *file, const char __user *buf,
- size_t count, loff_t *ppos)
+static ssize_t proc_fault_inject_write(struct file * file,
+ const char __user * buf, size_t count, loff_t *ppos)
{
- struct task_struct *tsk = proc_task(file->f_dentry->d_inode);
- char __buf[20], *end;
- unsigned int seccomp_mode;
+ struct task_struct *task;
+ char buffer[PROC_NUMBUF], *end;
+ int make_it_fail;
- /* can set it only once to be even more secure */
- if (unlikely(tsk->seccomp.mode))
+ if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
-
- memset(__buf, 0, sizeof(__buf));
- count = min(count, sizeof(__buf) - 1);
- if (copy_from_user(__buf, buf, count))
+ memset(buffer, 0, sizeof(buffer));
+ if (count > sizeof(buffer) - 1)
+ count = sizeof(buffer) - 1;
+ if (copy_from_user(buffer, buf, count))
return -EFAULT;
- seccomp_mode = simple_strtoul(__buf, &end, 0);
- if (*end == '\n')
- end++;
- if (seccomp_mode && seccomp_mode <= NR_SECCOMP_MODES) {
- tsk->seccomp.mode = seccomp_mode;
- set_tsk_thread_flag(tsk, TIF_SECCOMP);
- } else
+ make_it_fail = simple_strtol(strstrip(buffer), &end, 0);
+ if (*end)
return -EINVAL;
- if (unlikely(!(end - __buf)))
- return -EIO;
- return end - __buf;
+ task = get_proc_task(file->f_dentry->d_inode);
+ if (!task)
+ return -ESRCH;
+ task->make_it_fail = make_it_fail;
+ put_task_struct(task);
+
+ return count;
}
-static struct file_operations proc_seccomp_operations = {
- .read = seccomp_read,
- .write = seccomp_write,
+static const struct file_operations proc_fault_inject_operations = {
+ .read = proc_fault_inject_read,
+ .write = proc_fault_inject_write,
+ .llseek = generic_file_llseek,
};
-#endif /* CONFIG_SECCOMP */
-
-static int proc_check_dentry_visible(struct inode *inode,
- struct dentry *dentry, struct vfsmount *mnt)
-{
- /* Verify that the current process can already see the
- * file pointed at by the file descriptor.
- * This prevents /proc from being an accidental information leak.
- *
- * This prevents access to files that are not visible do to
- * being on the otherside of a chroot, in a different
- * namespace, or are simply process local (like pipes).
- */
- struct task_struct *task;
- struct files_struct *task_files, *files;
- int error = -EACCES;
+#endif
- /* See if the the two tasks share a commone set of
- * file descriptors. If so everything is visible.
- */
- task = proc_task(inode);
- if (!task)
- goto out;
- files = get_files_struct(current);
- task_files = get_files_struct(task);
- if (files && task_files && (files == task_files))
- error = 0;
- if (task_files)
- put_files_struct(task_files);
- if (files)
- put_files_struct(files);
- if (!error)
- goto out;
- /* If the two tasks don't share a common set of file
- * descriptors see if the destination dentry is already
- * visible in the current tasks filesystem namespace.
- */
- error = proc_check_chroot(dentry, mnt);
-out:
- return error;
+#ifdef CONFIG_SCHED_DEBUG
+/*
+ * Print out various scheduling related per-task fields:
+ */
+static int sched_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;
+ proc_sched_show_task(p, m);
+ put_task_struct(p);
+
+ return 0;
}
-static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
+static ssize_t
+sched_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *offset)
{
- struct inode *inode = dentry->d_inode;
- int error = -EACCES;
-
- /* We don't need a base pointer in the /proc filesystem */
- path_release(nd);
+ struct inode *inode = file->f_path.dentry->d_inode;
+ struct task_struct *p;
- if (current->fsuid != inode->i_uid && !capable(CAP_DAC_OVERRIDE))
- goto out;
+ p = get_proc_task(inode);
+ if (!p)
+ return -ESRCH;
+ proc_sched_set_task(p);
- error = PROC_I(inode)->op.proc_get_link(inode, &nd->dentry, &nd->mnt);
- nd->last_type = LAST_BIND;
- if (error)
- goto out;
+ put_task_struct(p);
- /* Only return files this task can already see */
- error = proc_check_dentry_visible(inode, nd->dentry, nd->mnt);
- if (error)
- path_release(nd);
-out:
- return ERR_PTR(error);
+ return count;
}
-static int do_proc_readlink(struct dentry *dentry, struct vfsmount *mnt,
- char __user *buffer, int buflen)
+static int sched_open(struct inode *inode, struct file *filp)
{
- struct inode * inode;
- char *tmp = (char*)__get_free_page(GFP_KERNEL), *path;
- int len;
+ int ret;
- if (!tmp)
- return -ENOMEM;
-
- inode = dentry->d_inode;
- path = d_path(dentry, mnt, tmp, PAGE_SIZE);
- len = PTR_ERR(path);
- if (IS_ERR(path))
- goto out;
- len = tmp + PAGE_SIZE - 1 - path;
+ ret = single_open(filp, sched_show, NULL);
+ if (!ret) {
+ struct seq_file *m = filp->private_data;
- if (len > buflen)
- len = buflen;
- if (copy_to_user(buffer, path, len))
- len = -EFAULT;
- out:
- free_page((unsigned long)tmp);
- return len;
+ m->private = inode;
+ }
+ return ret;
}
-static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int buflen)
+static const struct file_operations proc_pid_sched_operations = {
+ .open = sched_open,
+ .read = seq_read,
+ .write = sched_write,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+#endif
+
+static ssize_t comm_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *offset)
{
- int error = -EACCES;
- struct inode *inode = dentry->d_inode;
- struct dentry *de;
- struct vfsmount *mnt = NULL;
+ 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;
- if (current->fsuid != inode->i_uid && !capable(CAP_DAC_OVERRIDE))
- goto out;
+ p = get_proc_task(inode);
+ if (!p)
+ return -ESRCH;
- error = PROC_I(inode)->op.proc_get_link(inode, &de, &mnt);
- if (error)
- goto out;
+ if (same_thread_group(current, p))
+ set_task_comm(p, buffer);
+ else
+ count = -EINVAL;
- /* Only return files this task can already see */
- error = proc_check_dentry_visible(inode, de, mnt);
- if (error)
- goto out_put;
+ put_task_struct(p);
- error = do_proc_readlink(de, mnt, buffer, buflen);
-out_put:
- dput(de);
- mntput(mnt);
-out:
- return error;
+ return count;
}
-static struct inode_operations proc_pid_link_inode_operations = {
- .readlink = proc_pid_readlink,
- .follow_link = proc_pid_follow_link
-};
+static int comm_show(struct seq_file *m, void *v)
+{
+ struct inode *inode = m->private;
+ struct task_struct *p;
-#define NUMBUF 10
+ p = get_proc_task(inode);
+ if (!p)
+ return -ESRCH;
-static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir)
-{
- struct dentry *dentry = filp->f_dentry;
- struct inode *inode = dentry->d_inode;
- struct task_struct *p = proc_task(inode);
- unsigned int fd, tid, ino;
- int retval;
- char buf[NUMBUF];
- struct files_struct * files;
- struct fdtable *fdt;
+ task_lock(p);
+ seq_printf(m, "%s\n", p->comm);
+ task_unlock(p);
- retval = -ENOENT;
- if (!pid_alive(p))
- goto out;
- retval = 0;
- tid = p->pid;
+ put_task_struct(p);
- fd = filp->f_pos;
- switch (fd) {
- case 0:
- if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0)
- goto out;
- filp->f_pos++;
- case 1:
- ino = parent_ino(dentry);
- if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0)
- goto out;
- filp->f_pos++;
- default:
- files = get_files_struct(p);
- if (!files)
- goto out;
- rcu_read_lock();
- fdt = files_fdtable(files);
- for (fd = filp->f_pos-2;
- fd < fdt->max_fds;
- fd++, filp->f_pos++) {
- unsigned int i,j;
+ return 0;
+}
- if (!fcheck_files(files, fd))
- continue;
- rcu_read_unlock();
+static int comm_open(struct inode *inode, struct file *filp)
+{
+ int ret;
- j = NUMBUF;
- i = fd;
- do {
- j--;
- buf[j] = '0' + (i % 10);
- i /= 10;
- } while (i);
+ ret = single_open(filp, comm_show, NULL);
+ if (!ret) {
+ struct seq_file *m = filp->private_data;
- ino = fake_ino(tid, PROC_TID_FD_DIR + fd);
- if (filldir(dirent, buf+j, NUMBUF-j, fd+2, ino, DT_LNK) < 0) {
- rcu_read_lock();
- break;
- }
- rcu_read_lock();
- }
- rcu_read_unlock();
- put_files_struct(files);
+ m->private = inode;
}
-out:
- return retval;
+ return ret;
}
-static int proc_pident_readdir(struct file *filp,
- void *dirent, filldir_t filldir,
- struct pid_entry *ents, unsigned int nents)
+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)
{
- int i;
- int pid;
- struct dentry *dentry = filp->f_dentry;
struct inode *inode = dentry->d_inode;
- struct pid_entry *p;
- ino_t ino;
- int ret;
+ int error = -EACCES;
- ret = -ENOENT;
- if (!pid_alive(proc_task(inode)))
- goto out;
+ /* We don't need a base pointer in the /proc filesystem */
+ path_put(&nd->path);
- ret = 0;
- pid = proc_task(inode)->pid;
- i = filp->f_pos;
- switch (i) {
- case 0:
- ino = inode->i_ino;
- if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
- goto out;
- i++;
- filp->f_pos++;
- /* fall through */
- case 1:
- ino = parent_ino(dentry);
- if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
- goto out;
- i++;
- filp->f_pos++;
- /* fall through */
- default:
- i -= 2;
- if (i >= nents) {
- ret = 1;
- goto out;
- }
- p = ents + i;
- while (p->name) {
- if (filldir(dirent, p->name, p->len, filp->f_pos,
- fake_ino(pid, p->type), p->mode >> 12) < 0)
- goto out;
- filp->f_pos++;
- p++;
- }
- }
+ /* Are we allowed to snoop on the tasks file descriptors? */
+ if (!proc_fd_access_allowed(inode))
+ goto out;
- ret = 1;
+ error = PROC_I(inode)->op.proc_get_link(inode, &nd->path);
out:
- return ret;
+ return ERR_PTR(error);
}
-static int proc_tgid_base_readdir(struct file * filp,
- void * dirent, filldir_t filldir)
+static int do_proc_readlink(struct path *path, char __user *buffer, int buflen)
{
- return proc_pident_readdir(filp,dirent,filldir,
- tgid_base_stuff,ARRAY_SIZE(tgid_base_stuff));
+ char *tmp = (char*)__get_free_page(GFP_TEMPORARY);
+ char *pathname;
+ int len;
+
+ if (!tmp)
+ return -ENOMEM;
+
+ pathname = d_path(path, tmp, PAGE_SIZE);
+ len = PTR_ERR(pathname);
+ if (IS_ERR(pathname))
+ goto out;
+ len = tmp + PAGE_SIZE - 1 - pathname;
+
+ if (len > buflen)
+ len = buflen;
+ if (copy_to_user(buffer, pathname, len))
+ len = -EFAULT;
+ out:
+ free_page((unsigned long)tmp);
+ return len;
}
-static int proc_tid_base_readdir(struct file * filp,
- void * dirent, filldir_t filldir)
+static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int buflen)
{
- return proc_pident_readdir(filp,dirent,filldir,
- tid_base_stuff,ARRAY_SIZE(tid_base_stuff));
+ int error = -EACCES;
+ struct inode *inode = dentry->d_inode;
+ struct path path;
+
+ /* 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, &path);
+ if (error)
+ goto out;
+
+ error = do_proc_readlink(&path, buffer, buflen);
+ path_put(&path);
+out:
+ return error;
}
+static const struct inode_operations proc_pid_link_inode_operations = {
+ .readlink = proc_pid_readlink,
+ .follow_link = proc_pid_follow_link,
+ .setattr = proc_setattr,
+};
+
+
/* building an inode */
static int task_dumpable(struct task_struct *task)
task_lock(task);
mm = task->mm;
if (mm)
- dumpable = mm->dumpable;
+ dumpable = get_dumpable(mm);
task_unlock(task);
if(dumpable == 1)
return 1;
}
-static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task, int ino)
+static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task)
{
struct inode * inode;
struct proc_inode *ei;
+ const struct cred *cred;
/* We need a new inode */
-
+
inode = new_inode(sb);
if (!inode)
goto out;
/* Common stuff */
ei = PROC_I(inode);
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;
- inode->i_uid = 0;
- inode->i_gid = 0;
+ ei->pid = get_task_pid(task, PIDTYPE_PID);
+ if (!ei->pid)
+ goto out_unlock;
+
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);
return NULL;
}
+static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+{
+ struct inode *inode = dentry->d_inode;
+ struct task_struct *task;
+ const struct cred *cred;
+
+ 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)) {
+ cred = __task_cred(task);
+ stat->uid = cred->euid;
+ stat->gid = cred->egid;
+ }
+ }
+ rcu_read_unlock();
+ return 0;
+}
+
/* dentry stuff */
/*
*
* Rewrite the inode's ownerships here because the owning task may have
* performed a setuid(), etc.
+ *
+ * Before the /proc/pid/status file was created the only way to read
+ * the effective uid of a /process was to stat /proc/pid. Reading
+ * /proc/pid/status is slow enough that procps and other packages
+ * kept stating /proc/pid. To keep the rules in /proc simple I have
+ * made this apply to all per process world readable and executable
+ * directories.
*/
static int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
{
struct inode *inode = dentry->d_inode;
- struct task_struct *task = proc_task(inode);
- if (pid_alive(task)) {
- if (task_dumpable(task)) {
- inode->i_uid = task->euid;
- inode->i_gid = task->egid;
+ 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)) {
+ 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;
}
+ inode->i_mode &= ~(S_ISUID | S_ISGID);
security_task_to_inode(task, inode);
+ put_task_struct(task);
return 1;
}
d_drop(dentry);
return 0;
}
-static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
-{
- struct inode *inode = dentry->d_inode;
- struct task_struct *task = proc_task(inode);
- int fd = proc_fd(inode);
- struct files_struct *files;
-
- files = get_files_struct(task);
- if (files) {
- rcu_read_lock();
- if (fcheck_files(files, fd)) {
- rcu_read_unlock();
- put_files_struct(files);
- if (task_dumpable(task)) {
- inode->i_uid = task->euid;
- inode->i_gid = task->egid;
- } else {
- inode->i_uid = 0;
- inode->i_gid = 0;
- }
- security_task_to_inode(task, inode);
- return 1;
- }
- rcu_read_unlock();
- put_files_struct(files);
- }
- d_drop(dentry);
- return 0;
-}
-
static int pid_delete_dentry(struct dentry * dentry)
{
/* Is the task we represent dead?
* If so, then don't put the dentry on the lru list,
* kill it immediately.
*/
- return !pid_alive(proc_task(dentry->d_inode));
+ return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first;
}
-static struct dentry_operations tid_fd_dentry_operations =
-{
- .d_revalidate = tid_fd_revalidate,
- .d_delete = pid_delete_dentry,
-};
-
-static struct dentry_operations pid_dentry_operations =
+static const struct dentry_operations pid_dentry_operations =
{
.d_revalidate = pid_revalidate,
.d_delete = pid_delete_dentry,
/* Lookups */
+typedef struct dentry *instantiate_t(struct inode *, struct dentry *,
+ struct task_struct *, const void *);
+
+/*
+ * Fill a directory entry.
+ *
+ * If possible create the dcache entry and derive our inode number and
+ * file type from dcache entry.
+ *
+ * Since all of the proc inode numbers are dynamically generated, the inode
+ * numbers do not exist until the inode is cache. This means creating the
+ * the dcache entry in readdir is necessary to keep the inode numbers
+ * reported by readdir in sync with the inode numbers reported
+ * by stat.
+ */
+static int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
+ char *name, int len,
+ instantiate_t instantiate, struct task_struct *task, const void *ptr)
+{
+ struct dentry *child, *dir = filp->f_path.dentry;
+ struct inode *inode;
+ struct qstr qname;
+ ino_t ino = 0;
+ unsigned type = DT_UNKNOWN;
+
+ qname.name = name;
+ qname.len = len;
+ qname.hash = full_name_hash(name, len);
+
+ child = d_lookup(dir, &qname);
+ if (!child) {
+ struct dentry *new;
+ new = d_alloc(dir, &qname);
+ if (new) {
+ child = instantiate(dir->d_inode, new, task, ptr);
+ if (child)
+ dput(new);
+ else
+ child = new;
+ }
+ }
+ if (!child || IS_ERR(child) || !child->d_inode)
+ goto end_instantiate;
+ inode = child->d_inode;
+ if (inode) {
+ ino = inode->i_ino;
+ type = inode->i_mode >> 12;
+ }
+ dput(child);
+end_instantiate:
+ if (!ino)
+ ino = find_inode_number(dir, &qname);
+ if (!ino)
+ ino = 1;
+ return filldir(dirent, name, len, filp->f_pos, ino, type);
+}
+
static unsigned name_to_int(struct dentry *dentry)
{
const char *name = dentry->d_name.name;
return ~0U;
}
-/* SMP-safe */
-static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
-{
- struct task_struct *task = proc_task(dir);
- unsigned fd = name_to_int(dentry);
- struct dentry *result = ERR_PTR(-ENOENT);
- struct file * file;
- struct files_struct * files;
- struct inode *inode;
- struct proc_inode *ei;
+#define PROC_FDINFO_MAX 64
- if (fd == ~0U)
- goto out;
- if (!pid_alive(task))
- goto out;
+static int proc_fd_info(struct inode *inode, struct path *path, char *info)
+{
+ struct task_struct *task = get_proc_task(inode);
+ struct files_struct *files = NULL;
+ struct file *file;
+ int fd = proc_fd(inode);
- 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;
+ 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) {
+ if (path) {
+ *path = file->f_path;
+ path_get(&file->f_path);
+ }
+ if (info)
+ snprintf(info, PROC_FDINFO_MAX,
+ "pos:\t%lli\n"
+ "flags:\t0%o\n",
+ (long long) file->f_pos,
+ file->f_flags);
+ spin_unlock(&files->file_lock);
+ put_files_struct(files);
+ return 0;
+ }
+ spin_unlock(&files->file_lock);
+ put_files_struct(files);
+ }
+ return -ENOENT;
+}
+
+static int proc_fd_link(struct inode *inode, struct path *path)
+{
+ return proc_fd_info(inode, path, NULL);
+}
+
+static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
+{
+ struct inode *inode = dentry->d_inode;
+ struct task_struct *task = get_proc_task(inode);
+ int fd = proc_fd(inode);
+ struct files_struct *files;
+ const struct cred *cred;
+
+ 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)) {
+ 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;
+ }
+ inode->i_mode &= ~(S_ISUID | S_ISGID);
+ security_task_to_inode(task, inode);
+ put_task_struct(task);
+ return 1;
+ }
+ rcu_read_unlock();
+ put_files_struct(files);
+ }
+ put_task_struct(task);
+ }
+ d_drop(dentry);
+ return 0;
+}
+
+static const struct dentry_operations tid_fd_dentry_operations =
+{
+ .d_revalidate = tid_fd_revalidate,
+ .d_delete = pid_delete_dentry,
+};
+
+static struct dentry *proc_fd_instantiate(struct inode *dir,
+ struct dentry *dentry, struct task_struct *task, const void *ptr)
+{
+ unsigned fd = *(const unsigned *)ptr;
+ struct file *file;
+ struct files_struct *files;
+ struct inode *inode;
+ struct proc_inode *ei;
+ struct dentry *error = ERR_PTR(-ENOENT);
+
+ inode = proc_pid_make_inode(dir->i_sb, task);
+ if (!inode)
+ goto out;
+ ei = PROC_I(inode);
+ ei->fd = fd;
+ files = get_files_struct(task);
+ if (!files)
+ goto out_iput;
+ inode->i_mode = S_IFLNK;
/*
* We are not taking a ref to the file structure, so we must
spin_lock(&files->file_lock);
file = fcheck_files(files, fd);
if (!file)
- goto out_unlock2;
- if (file->f_mode & 1)
+ goto out_unlock;
+ 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);
+
inode->i_op = &proc_pid_link_inode_operations;
inode->i_size = 64;
ei->op.proc_get_link = proc_fd_link;
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
if (tid_fd_revalidate(dentry, NULL))
- result = NULL;
-out:
- return result;
+ error = NULL;
-out_unlock2:
+ out:
+ return error;
+out_unlock:
spin_unlock(&files->file_lock);
put_files_struct(files);
-out_unlock:
+out_iput:
iput(inode);
goto out;
}
-static 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 dentry *proc_lookupfd_common(struct inode *dir,
+ struct dentry *dentry,
+ instantiate_t instantiate)
+{
+ struct task_struct *task = get_proc_task(dir);
+ unsigned fd = name_to_int(dentry);
+ struct dentry *result = ERR_PTR(-ENOENT);
+
+ if (!task)
+ goto out_no_task;
+ if (fd == ~0U)
+ goto out;
+
+ result = instantiate(dir, dentry, task, &fd);
+out:
+ put_task_struct(task);
+out_no_task:
+ return result;
+}
+
+static int proc_readfd_common(struct file * filp, void * dirent,
+ filldir_t filldir, instantiate_t instantiate)
+{
+ struct dentry *dentry = filp->f_path.dentry;
+ struct inode *inode = dentry->d_inode;
+ struct task_struct *p = get_proc_task(inode);
+ unsigned int fd, ino;
+ int retval;
+ struct files_struct * files;
+
+ retval = -ENOENT;
+ if (!p)
+ goto out_no_task;
+ retval = 0;
+
+ fd = filp->f_pos;
+ switch (fd) {
+ case 0:
+ if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0)
+ goto out;
+ filp->f_pos++;
+ case 1:
+ ino = parent_ino(dentry);
+ if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0)
+ goto out;
+ filp->f_pos++;
+ default:
+ files = get_files_struct(p);
+ if (!files)
+ goto out;
+ rcu_read_lock();
+ for (fd = filp->f_pos-2;
+ fd < files_fdtable(files)->max_fds;
+ fd++, filp->f_pos++) {
+ char name[PROC_NUMBUF];
+ int len;
+
+ if (!fcheck_files(files, fd))
+ continue;
+ rcu_read_unlock();
+
+ len = snprintf(name, sizeof(name), "%d", fd);
+ if (proc_fill_cache(filp, dirent, filldir,
+ name, len, instantiate,
+ p, &fd) < 0) {
+ rcu_read_lock();
+ break;
+ }
+ rcu_read_lock();
+ }
+ rcu_read_unlock();
+ put_files_struct(files);
+ }
+out:
+ put_task_struct(p);
+out_no_task:
+ return retval;
+}
+
+static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
+ struct nameidata *nd)
+{
+ return proc_lookupfd_common(dir, dentry, proc_fd_instantiate);
+}
+
+static int proc_readfd(struct file *filp, void *dirent, filldir_t filldir)
+{
+ return proc_readfd_common(filp, dirent, filldir, proc_fd_instantiate);
+}
-static struct file_operations proc_fd_operations = {
+static ssize_t proc_fdinfo_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ char tmp[PROC_FDINFO_MAX];
+ int err = proc_fd_info(file->f_path.dentry->d_inode, NULL, tmp);
+ if (!err)
+ err = simple_read_from_buffer(buf, len, ppos, tmp, strlen(tmp));
+ return err;
+}
+
+static const struct file_operations proc_fdinfo_file_operations = {
+ .open = nonseekable_open,
+ .read = proc_fdinfo_read,
+};
+
+static const struct file_operations proc_fd_operations = {
.read = generic_read_dir,
.readdir = proc_readfd,
};
-static struct file_operations proc_task_operations = {
+/*
+ * /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)
+{
+ int rv;
+
+ rv = generic_permission(inode, mask, NULL);
+ if (rv == 0)
+ return 0;
+ if (task_pid(current) == proc_pid(inode))
+ rv = 0;
+ return rv;
+}
+
+/*
+ * proc directories can do almost nothing..
+ */
+static const struct inode_operations proc_fd_inode_operations = {
+ .lookup = proc_lookupfd,
+ .permission = proc_fd_permission,
+ .setattr = proc_setattr,
+};
+
+static struct dentry *proc_fdinfo_instantiate(struct inode *dir,
+ struct dentry *dentry, struct task_struct *task, const void *ptr)
+{
+ unsigned fd = *(unsigned *)ptr;
+ struct inode *inode;
+ struct proc_inode *ei;
+ struct dentry *error = ERR_PTR(-ENOENT);
+
+ inode = proc_pid_make_inode(dir->i_sb, task);
+ if (!inode)
+ goto out;
+ ei = PROC_I(inode);
+ ei->fd = fd;
+ inode->i_mode = S_IFREG | S_IRUSR;
+ inode->i_fop = &proc_fdinfo_file_operations;
+ dentry->d_op = &tid_fd_dentry_operations;
+ d_add(dentry, inode);
+ /* Close the race of the process dying before we return the dentry */
+ if (tid_fd_revalidate(dentry, NULL))
+ error = NULL;
+
+ out:
+ return error;
+}
+
+static struct dentry *proc_lookupfdinfo(struct inode *dir,
+ struct dentry *dentry,
+ struct nameidata *nd)
+{
+ return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
+}
+
+static int proc_readfdinfo(struct file *filp, void *dirent, filldir_t filldir)
+{
+ return proc_readfd_common(filp, dirent, filldir,
+ proc_fdinfo_instantiate);
+}
+
+static const struct file_operations proc_fdinfo_operations = {
.read = generic_read_dir,
- .readdir = proc_task_readdir,
+ .readdir = proc_readfdinfo,
};
/*
* proc directories can do almost nothing..
*/
-static struct inode_operations proc_fd_inode_operations = {
- .lookup = proc_lookupfd,
+static const struct inode_operations proc_fdinfo_inode_operations = {
+ .lookup = proc_lookupfdinfo,
+ .setattr = proc_setattr,
};
-static struct inode_operations proc_task_inode_operations = {
- .lookup = proc_task_lookup,
- .getattr = proc_task_getattr,
+
+static struct dentry *proc_pident_instantiate(struct inode *dir,
+ struct dentry *dentry, struct task_struct *task, const void *ptr)
+{
+ const struct pid_entry *p = ptr;
+ struct inode *inode;
+ struct proc_inode *ei;
+ struct dentry *error = ERR_PTR(-ENOENT);
+
+ inode = proc_pid_make_inode(dir->i_sb, task);
+ if (!inode)
+ goto out;
+
+ ei = PROC_I(inode);
+ inode->i_mode = p->mode;
+ if (S_ISDIR(inode->i_mode))
+ inode->i_nlink = 2; /* Use getattr to fix if necessary */
+ if (p->iop)
+ inode->i_op = p->iop;
+ if (p->fop)
+ inode->i_fop = p->fop;
+ ei->op = p->op;
+ dentry->d_op = &pid_dentry_operations;
+ d_add(dentry, inode);
+ /* Close the race of the process dying before we return the dentry */
+ if (pid_revalidate(dentry, NULL))
+ error = NULL;
+out:
+ return error;
+}
+
+static struct dentry *proc_pident_lookup(struct inode *dir,
+ struct dentry *dentry,
+ const struct pid_entry *ents,
+ unsigned int nents)
+{
+ struct dentry *error;
+ struct task_struct *task = get_proc_task(dir);
+ const struct pid_entry *p, *last;
+
+ error = ERR_PTR(-ENOENT);
+
+ if (!task)
+ goto out_no_task;
+
+ /*
+ * Yes, it does not scale. And it should not. Don't add
+ * new entries into /proc/<tgid>/ without very good reasons.
+ */
+ last = &ents[nents - 1];
+ for (p = ents; p <= last; p++) {
+ if (p->len != dentry->d_name.len)
+ continue;
+ if (!memcmp(dentry->d_name.name, p->name, p->len))
+ break;
+ }
+ if (p > last)
+ goto out;
+
+ error = proc_pident_instantiate(dir, dentry, task, p);
+out:
+ put_task_struct(task);
+out_no_task:
+ return error;
+}
+
+static int proc_pident_fill_cache(struct file *filp, void *dirent,
+ filldir_t filldir, struct task_struct *task, const struct pid_entry *p)
+{
+ return proc_fill_cache(filp, dirent, filldir, p->name, p->len,
+ proc_pident_instantiate, task, p);
+}
+
+static int proc_pident_readdir(struct file *filp,
+ void *dirent, filldir_t filldir,
+ const struct pid_entry *ents, unsigned int nents)
+{
+ int i;
+ struct dentry *dentry = filp->f_path.dentry;
+ struct inode *inode = dentry->d_inode;
+ struct task_struct *task = get_proc_task(inode);
+ const struct pid_entry *p, *last;
+ ino_t ino;
+ int ret;
+
+ ret = -ENOENT;
+ if (!task)
+ goto out_no_task;
+
+ ret = 0;
+ i = filp->f_pos;
+ switch (i) {
+ case 0:
+ ino = inode->i_ino;
+ if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
+ goto out;
+ i++;
+ filp->f_pos++;
+ /* fall through */
+ case 1:
+ ino = parent_ino(dentry);
+ if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
+ goto out;
+ i++;
+ filp->f_pos++;
+ /* fall through */
+ default:
+ i -= 2;
+ if (i >= nents) {
+ ret = 1;
+ goto out;
+ }
+ p = ents + i;
+ last = &ents[nents - 1];
+ while (p <= last) {
+ if (proc_pident_fill_cache(filp, dirent, filldir, task, p) < 0)
+ goto out;
+ filp->f_pos++;
+ p++;
+ }
+ }
+
+ ret = 1;
+out:
+ put_task_struct(task);
+out_no_task:
+ return ret;
+}
+
+#ifdef CONFIG_SECURITY
+static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ struct inode * inode = file->f_path.dentry->d_inode;
+ char *p = NULL;
+ ssize_t length;
+ struct task_struct *task = get_proc_task(inode);
+
+ if (!task)
+ return -ESRCH;
+
+ length = security_getprocattr(task,
+ (char*)file->f_path.dentry->d_name.name,
+ &p);
+ put_task_struct(task);
+ if (length > 0)
+ length = simple_read_from_buffer(buf, count, ppos, p, length);
+ kfree(p);
+ return length;
+}
+
+static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ struct inode * inode = file->f_path.dentry->d_inode;
+ char *page;
+ ssize_t length;
+ struct task_struct *task = get_proc_task(inode);
+
+ length = -ESRCH;
+ if (!task)
+ goto out_no_task;
+ if (count > PAGE_SIZE)
+ count = PAGE_SIZE;
+
+ /* No partial writes. */
+ length = -EINVAL;
+ if (*ppos != 0)
+ goto out;
+
+ length = -ENOMEM;
+ page = (char*)__get_free_page(GFP_TEMPORARY);
+ if (!page)
+ goto out;
+
+ length = -EFAULT;
+ 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:
+ put_task_struct(task);
+out_no_task:
+ return length;
+}
+
+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, 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,
+ void * dirent, filldir_t filldir)
+{
+ return proc_pident_readdir(filp,dirent,filldir,
+ attr_dir_stuff,ARRAY_SIZE(attr_dir_stuff));
+}
+
+static const struct file_operations proc_attr_dir_operations = {
+ .read = generic_read_dir,
+ .readdir = proc_attr_dir_readdir,
+};
+
+static struct dentry *proc_attr_dir_lookup(struct inode *dir,
+ struct dentry *dentry, struct nameidata *nd)
+{
+ return proc_pident_lookup(dir, dentry,
+ attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff));
+}
+
+static const struct inode_operations proc_attr_dir_inode_operations = {
+ .lookup = proc_attr_dir_lookup,
+ .getattr = pid_getattr,
+ .setattr = proc_setattr,
+};
+
+#endif
+
+#ifdef CONFIG_ELF_CORE
+static ssize_t proc_coredump_filter_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);
+ struct mm_struct *mm;
+ char buffer[PROC_NUMBUF];
+ size_t len;
+ int ret;
+
+ if (!task)
+ return -ESRCH;
+
+ ret = 0;
+ mm = get_task_mm(task);
+ if (mm) {
+ len = snprintf(buffer, sizeof(buffer), "%08lx\n",
+ ((mm->flags & MMF_DUMP_FILTER_MASK) >>
+ MMF_DUMP_FILTER_SHIFT));
+ mmput(mm);
+ ret = simple_read_from_buffer(buf, count, ppos, buffer, len);
+ }
+
+ put_task_struct(task);
+
+ return ret;
+}
+
+static ssize_t proc_coredump_filter_write(struct file *file,
+ const char __user *buf,
+ size_t count,
+ loff_t *ppos)
+{
+ struct task_struct *task;
+ struct mm_struct *mm;
+ char buffer[PROC_NUMBUF], *end;
+ unsigned int val;
+ int ret;
+ int i;
+ unsigned long mask;
+
+ ret = -EFAULT;
+ memset(buffer, 0, sizeof(buffer));
+ if (count > sizeof(buffer) - 1)
+ count = sizeof(buffer) - 1;
+ if (copy_from_user(buffer, buf, count))
+ goto out_no_task;
+
+ ret = -EINVAL;
+ val = (unsigned int)simple_strtoul(buffer, &end, 0);
+ if (*end == '\n')
+ end++;
+ if (end - buffer == 0)
+ goto out_no_task;
+
+ ret = -ESRCH;
+ task = get_proc_task(file->f_dentry->d_inode);
+ if (!task)
+ goto out_no_task;
+
+ ret = end - buffer;
+ mm = get_task_mm(task);
+ if (!mm)
+ goto out_no_mm;
+
+ for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) {
+ if (val & mask)
+ set_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags);
+ else
+ clear_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags);
+ }
+
+ mmput(mm);
+ out_no_mm:
+ put_task_struct(task);
+ out_no_task:
+ return ret;
+}
+
+static const struct file_operations proc_coredump_filter_operations = {
+ .read = proc_coredump_filter_read,
+ .write = proc_coredump_filter_write,
+ .llseek = generic_file_llseek,
+};
+#endif
+
+/*
+ * /proc/self:
+ */
+static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
+ int buflen)
+{
+ 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 -ENOENT;
+ sprintf(tmp, "%d", tgid);
+ return vfs_readlink(dentry,buffer,buflen,tmp);
+}
+
+static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+ struct pid_namespace *ns = dentry->d_sb->s_fs_info;
+ pid_t tgid = task_tgid_nr_ns(current, ns);
+ 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,
+};
+
+/*
+ * proc base
+ *
+ * These are the directory entries in the root directory of /proc
+ * that properly belong to the /proc filesystem, as they describe
+ * describe something that is process related.
+ */
+static const struct pid_entry proc_base_stuff[] = {
+ NOD("self", S_IFLNK|S_IRWXUGO,
+ &proc_self_inode_operations, NULL, {}),
+};
+
+/*
+ * Exceptional case: normally we are not allowed to unhash a busy
+ * directory. In this case, however, we can do it - no aliasing problems
+ * due to the way we treat inodes.
+ */
+static int proc_base_revalidate(struct dentry *dentry, struct nameidata *nd)
+{
+ struct inode *inode = dentry->d_inode;
+ struct task_struct *task = get_proc_task(inode);
+ if (task) {
+ put_task_struct(task);
+ return 1;
+ }
+ d_drop(dentry);
+ return 0;
+}
+
+static const struct dentry_operations proc_base_dentry_operations =
+{
+ .d_revalidate = proc_base_revalidate,
+ .d_delete = pid_delete_dentry,
};
-#ifdef CONFIG_SECURITY
-static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
- size_t count, loff_t *ppos)
+static struct dentry *proc_base_instantiate(struct inode *dir,
+ struct dentry *dentry, struct task_struct *task, const void *ptr)
{
- struct inode * inode = file->f_dentry->d_inode;
- unsigned long page;
- ssize_t length;
- struct task_struct *task = proc_task(inode);
-
- if (count > PAGE_SIZE)
- count = PAGE_SIZE;
- if (!(page = __get_free_page(GFP_KERNEL)))
- return -ENOMEM;
-
- length = security_getprocattr(task,
- (char*)file->f_dentry->d_name.name,
- (void*)page, count);
- if (length >= 0)
- length = simple_read_from_buffer(buf, count, ppos, (char *)page, length);
- free_page(page);
- return length;
-}
+ const struct pid_entry *p = ptr;
+ struct inode *inode;
+ struct proc_inode *ei;
+ struct dentry *error = ERR_PTR(-EINVAL);
-static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
- size_t count, loff_t *ppos)
-{
- struct inode * inode = file->f_dentry->d_inode;
- char *page;
- ssize_t length;
- struct task_struct *task = proc_task(inode);
-
- if (count > PAGE_SIZE)
- count = PAGE_SIZE;
- if (*ppos != 0) {
- /* No partial writes. */
- return -EINVAL;
- }
- page = (char*)__get_free_page(GFP_USER);
- if (!page)
- return -ENOMEM;
- length = -EFAULT;
- if (copy_from_user(page, buf, count))
+ /* Allocate the inode */
+ error = ERR_PTR(-ENOMEM);
+ inode = new_inode(dir->i_sb);
+ if (!inode)
goto out;
- length = security_setprocattr(task,
- (char*)file->f_dentry->d_name.name,
- (void*)page, count);
-out:
- free_page((unsigned long) page);
- return length;
-}
+ /* Initialize the inode */
+ ei = PROC_I(inode);
+ inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
-static struct file_operations proc_pid_attr_operations = {
- .read = proc_pid_attr_read,
- .write = proc_pid_attr_write,
-};
+ /*
+ * grab the reference to the task.
+ */
+ ei->pid = get_task_pid(task, PIDTYPE_PID);
+ if (!ei->pid)
+ goto out_iput;
-static struct file_operations proc_tid_attr_operations;
-static struct inode_operations proc_tid_attr_inode_operations;
-static struct file_operations proc_tgid_attr_operations;
-static struct inode_operations proc_tgid_attr_inode_operations;
-#endif
+ inode->i_mode = p->mode;
+ if (S_ISDIR(inode->i_mode))
+ inode->i_nlink = 2;
+ if (S_ISLNK(inode->i_mode))
+ inode->i_size = 64;
+ if (p->iop)
+ inode->i_op = p->iop;
+ if (p->fop)
+ inode->i_fop = p->fop;
+ ei->op = p->op;
+ dentry->d_op = &proc_base_dentry_operations;
+ d_add(dentry, inode);
+ error = NULL;
+out:
+ return error;
+out_iput:
+ iput(inode);
+ goto out;
+}
-/* SMP-safe */
-static struct dentry *proc_pident_lookup(struct inode *dir,
- struct dentry *dentry,
- struct pid_entry *ents)
+static struct dentry *proc_base_lookup(struct inode *dir, struct dentry *dentry)
{
- struct inode *inode;
struct dentry *error;
- struct task_struct *task = proc_task(dir);
- struct pid_entry *p;
- struct proc_inode *ei;
+ struct task_struct *task = get_proc_task(dir);
+ const struct pid_entry *p, *last;
error = ERR_PTR(-ENOENT);
- inode = NULL;
- if (!pid_alive(task))
- goto out;
+ if (!task)
+ goto out_no_task;
- for (p = ents; p->name; p++) {
+ /* Lookup the directory entry */
+ last = &proc_base_stuff[ARRAY_SIZE(proc_base_stuff) - 1];
+ for (p = proc_base_stuff; p <= last; p++) {
if (p->len != dentry->d_name.len)
continue;
if (!memcmp(dentry->d_name.name, p->name, p->len))
break;
}
- if (!p->name)
+ if (p > last)
goto out;
- error = ERR_PTR(-EINVAL);
- inode = proc_pid_make_inode(dir->i_sb, task, p->type);
- if (!inode)
- goto out;
+ error = proc_base_instantiate(dir, dentry, task, p);
- ei = PROC_I(inode);
- inode->i_mode = p->mode;
- /*
- * Yes, it does not scale. And it should not. Don't add
- * new entries into /proc/<tgid>/ without very good reasons.
- */
- switch(p->type) {
- case PROC_TGID_TASK:
- inode->i_nlink = 2;
- inode->i_op = &proc_task_inode_operations;
- inode->i_fop = &proc_task_operations;
- break;
- case PROC_TID_FD:
- case PROC_TGID_FD:
- inode->i_nlink = 2;
- inode->i_op = &proc_fd_inode_operations;
- inode->i_fop = &proc_fd_operations;
- break;
- case PROC_TID_EXE:
- case PROC_TGID_EXE:
- inode->i_op = &proc_pid_link_inode_operations;
- ei->op.proc_get_link = proc_exe_link;
- break;
- case PROC_TID_CWD:
- case PROC_TGID_CWD:
- inode->i_op = &proc_pid_link_inode_operations;
- ei->op.proc_get_link = proc_cwd_link;
- break;
- case PROC_TID_ROOT:
- case PROC_TGID_ROOT:
- inode->i_op = &proc_pid_link_inode_operations;
- ei->op.proc_get_link = proc_root_link;
- break;
- case PROC_TID_ENVIRON:
- case PROC_TGID_ENVIRON:
- inode->i_fop = &proc_info_file_operations;
- ei->op.proc_read = proc_pid_environ;
- break;
- case PROC_TID_AUXV:
- case PROC_TGID_AUXV:
- inode->i_fop = &proc_info_file_operations;
- ei->op.proc_read = proc_pid_auxv;
- break;
- case PROC_TID_STATUS:
- case PROC_TGID_STATUS:
- inode->i_fop = &proc_info_file_operations;
- ei->op.proc_read = proc_pid_status;
- break;
- case PROC_TID_STAT:
- inode->i_fop = &proc_info_file_operations;
- ei->op.proc_read = proc_tid_stat;
- break;
- case PROC_TGID_STAT:
- inode->i_fop = &proc_info_file_operations;
- ei->op.proc_read = proc_tgid_stat;
- break;
- case PROC_TID_CMDLINE:
- case PROC_TGID_CMDLINE:
- inode->i_fop = &proc_info_file_operations;
- ei->op.proc_read = proc_pid_cmdline;
- break;
- case PROC_TID_STATM:
- case PROC_TGID_STATM:
- inode->i_fop = &proc_info_file_operations;
- ei->op.proc_read = proc_pid_statm;
- break;
- case PROC_TID_MAPS:
- case PROC_TGID_MAPS:
- inode->i_fop = &proc_maps_operations;
- break;
-#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_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;
- inode->i_op = &proc_tid_attr_inode_operations;
- inode->i_fop = &proc_tid_attr_operations;
- break;
- case PROC_TGID_ATTR:
- inode->i_nlink = 2;
- inode->i_op = &proc_tgid_attr_inode_operations;
- inode->i_fop = &proc_tgid_attr_operations;
- break;
- case PROC_TID_ATTR_CURRENT:
- case PROC_TGID_ATTR_CURRENT:
- case PROC_TID_ATTR_PREV:
- case PROC_TGID_ATTR_PREV:
- case PROC_TID_ATTR_EXEC:
- case PROC_TGID_ATTR_EXEC:
- case PROC_TID_ATTR_FSCREATE:
- case PROC_TGID_ATTR_FSCREATE:
- case PROC_TID_ATTR_KEYCREATE:
- case PROC_TGID_ATTR_KEYCREATE:
- inode->i_fop = &proc_pid_attr_operations;
- break;
-#endif
-#ifdef CONFIG_KALLSYMS
- case PROC_TID_WCHAN:
- case PROC_TGID_WCHAN:
- inode->i_fop = &proc_info_file_operations;
- ei->op.proc_read = proc_pid_wchan;
- break;
-#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
- default:
- printk("procfs: impossible type (%d)",p->type);
- iput(inode);
- error = ERR_PTR(-EINVAL);
- goto out;
- }
- dentry->d_op = &pid_dentry_operations;
- d_add(dentry, inode);
- /* Close the race of the process dying before we return the dentry */
- if (pid_revalidate(dentry, NULL))
- error = NULL;
out:
+ 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){
- return proc_pident_lookup(dir, dentry, tgid_base_stuff);
+static int proc_base_fill_cache(struct file *filp, void *dirent,
+ filldir_t filldir, struct task_struct *task, const struct pid_entry *p)
+{
+ return proc_fill_cache(filp, dirent, filldir, p->name, p->len,
+ proc_base_instantiate, task, p);
}
-static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
- return proc_pident_lookup(dir, dentry, tid_base_stuff);
-}
+#ifdef CONFIG_TASK_IO_ACCOUNTING
+static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
+{
+ struct task_io_accounting acct = task->ioac;
+ unsigned long flags;
-static struct file_operations proc_tgid_base_operations = {
- .read = generic_read_dir,
- .readdir = proc_tgid_base_readdir,
-};
+ if (whole && lock_task_sighand(task, &flags)) {
+ struct task_struct *t = task;
-static struct file_operations proc_tid_base_operations = {
- .read = generic_read_dir,
- .readdir = proc_tid_base_readdir,
-};
+ task_io_accounting_add(&acct, &task->signal->ioac);
+ while_each_thread(task, t)
+ task_io_accounting_add(&acct, &t->ioac);
-static struct inode_operations proc_tgid_base_inode_operations = {
- .lookup = proc_tgid_base_lookup,
-};
+ unlock_task_sighand(task, &flags);
+ }
+ return sprintf(buffer,
+ "rchar: %llu\n"
+ "wchar: %llu\n"
+ "syscr: %llu\n"
+ "syscw: %llu\n"
+ "read_bytes: %llu\n"
+ "write_bytes: %llu\n"
+ "cancelled_write_bytes: %llu\n",
+ (unsigned long long)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 struct inode_operations proc_tid_base_inode_operations = {
- .lookup = proc_tid_base_lookup,
-};
+static int proc_tid_io_accounting(struct task_struct *task, char *buffer)
+{
+ return do_io_accounting(task, buffer, 0);
+}
-#ifdef CONFIG_SECURITY
-static int proc_tgid_attr_readdir(struct file * filp,
- void * dirent, filldir_t filldir)
+static int proc_tgid_io_accounting(struct task_struct *task, char *buffer)
{
- return proc_pident_readdir(filp,dirent,filldir,
- tgid_attr_stuff,ARRAY_SIZE(tgid_attr_stuff));
+ return do_io_accounting(task, buffer, 1);
}
+#endif /* CONFIG_TASK_IO_ACCOUNTING */
-static int proc_tid_attr_readdir(struct file * filp,
- void * dirent, filldir_t filldir)
+static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
{
- return proc_pident_readdir(filp,dirent,filldir,
- tid_attr_stuff,ARRAY_SIZE(tid_attr_stuff));
+ seq_printf(m, "%08x\n", task->personality);
+ return 0;
}
-static struct file_operations proc_tgid_attr_operations = {
- .read = generic_read_dir,
- .readdir = proc_tgid_attr_readdir,
+/*
+ * Thread groups
+ */
+static const struct file_operations proc_task_operations;
+static const struct inode_operations proc_task_inode_operations;
+
+static const struct pid_entry tgid_base_stuff[] = {
+ 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, proc_net_inode_operations, proc_net_operations),
+#endif
+ 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, 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, 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, proc_numa_maps_operations),
+#endif
+ 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, 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, proc_attr_dir_inode_operations, proc_attr_dir_operations),
+#endif
+#ifdef CONFIG_KALLSYMS
+ 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, proc_pid_schedstat),
+#endif
+#ifdef CONFIG_LATENCYTOP
+ REG("latency", S_IRUGO, proc_lstats_operations),
+#endif
+#ifdef CONFIG_PROC_PID_CPUSET
+ REG("cpuset", S_IRUGO, proc_cpuset_operations),
+#endif
+#ifdef CONFIG_CGROUPS
+ REG("cgroup", S_IRUGO, proc_cgroup_operations),
+#endif
+ 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, proc_loginuid_operations),
+ REG("sessionid", S_IRUGO, proc_sessionid_operations),
+#endif
+#ifdef CONFIG_FAULT_INJECTION
+ REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
+#endif
+#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, proc_tgid_io_accounting),
+#endif
};
-static struct file_operations proc_tid_attr_operations = {
+static int proc_tgid_base_readdir(struct file * filp,
+ void * dirent, filldir_t filldir)
+{
+ return proc_pident_readdir(filp,dirent,filldir,
+ tgid_base_stuff,ARRAY_SIZE(tgid_base_stuff));
+}
+
+static const struct file_operations proc_tgid_base_operations = {
.read = generic_read_dir,
- .readdir = proc_tid_attr_readdir,
+ .readdir = proc_tgid_base_readdir,
};
-static struct dentry *proc_tgid_attr_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
-{
- return proc_pident_lookup(dir, dentry, tgid_attr_stuff);
+static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
+ return proc_pident_lookup(dir, dentry,
+ tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff));
}
-static struct dentry *proc_tid_attr_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
+static const struct inode_operations proc_tgid_base_inode_operations = {
+ .lookup = proc_tgid_base_lookup,
+ .getattr = pid_getattr,
+ .setattr = proc_setattr,
+};
+
+static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
{
- return proc_pident_lookup(dir, dentry, tid_attr_stuff);
-}
+ struct dentry *dentry, *leader, *dir;
+ char buf[PROC_NUMBUF];
+ struct qstr name;
-static struct inode_operations proc_tgid_attr_inode_operations = {
- .lookup = proc_tgid_attr_lookup,
-};
+ name.name = buf;
+ name.len = snprintf(buf, sizeof(buf), "%d", pid);
+ dentry = d_hash_and_lookup(mnt->mnt_root, &name);
+ if (dentry) {
+ shrink_dcache_parent(dentry);
+ d_drop(dentry);
+ dput(dentry);
+ }
-static struct inode_operations proc_tid_attr_inode_operations = {
- .lookup = proc_tid_attr_lookup,
-};
-#endif
+ name.name = buf;
+ name.len = snprintf(buf, sizeof(buf), "%d", tgid);
+ leader = d_hash_and_lookup(mnt->mnt_root, &name);
+ if (!leader)
+ goto out;
-/*
- * /proc/self:
- */
-static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
- int buflen)
-{
- char tmp[30];
- sprintf(tmp, "%d", current->tgid);
- return vfs_readlink(dentry,buffer,buflen,tmp);
-}
+ name.name = "task";
+ name.len = strlen(name.name);
+ dir = d_hash_and_lookup(leader, &name);
+ if (!dir)
+ goto out_put_leader;
-static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- char tmp[30];
- sprintf(tmp, "%d", current->tgid);
- return ERR_PTR(vfs_follow_link(nd,tmp));
-}
+ name.name = buf;
+ name.len = snprintf(buf, sizeof(buf), "%d", pid);
+ dentry = d_hash_and_lookup(dir, &name);
+ if (dentry) {
+ shrink_dcache_parent(dentry);
+ d_drop(dentry);
+ dput(dentry);
+ }
-static struct inode_operations proc_self_inode_operations = {
- .readlink = proc_self_readlink,
- .follow_link = proc_self_follow_link,
-};
+ dput(dir);
+out_put_leader:
+ dput(leader);
+out:
+ return;
+}
/**
* proc_flush_task - Remove dcache entries for @task from the /proc dcache.
- *
* @task: task that should be flushed.
*
+ * When flushing dentries from proc, one needs to flush them from global
+ * proc (proc_mnt) and from all the namespaces' procs this task was seen
+ * in. This call is supposed to do all of this job.
+ *
* Looks in the dcache for
* /proc/@pid
* /proc/@tgid/task/@pid
* that no dcache entries will exist at process exit time it
* just makes it very unlikely that any will persist.
*/
-void proc_flush_task(struct task_struct *task)
-{
- struct dentry *dentry, *leader, *dir;
- char buf[30];
- struct qstr name;
-
- name.name = buf;
- name.len = snprintf(buf, sizeof(buf), "%d", task->pid);
- dentry = d_hash_and_lookup(proc_mnt->mnt_root, &name);
- if (dentry) {
- shrink_dcache_parent(dentry);
- d_drop(dentry);
- dput(dentry);
- }
-
- if (thread_group_leader(task))
- goto out;
-
- name.name = buf;
- name.len = snprintf(buf, sizeof(buf), "%d", task->tgid);
- leader = d_hash_and_lookup(proc_mnt->mnt_root, &name);
- if (!leader)
- goto out;
- name.name = "task";
- name.len = strlen(name.name);
- dir = d_hash_and_lookup(leader, &name);
- if (!dir)
- goto out_put_leader;
+void proc_flush_task(struct task_struct *task)
+{
+ int i;
+ struct pid *pid, *tgid;
+ struct upid *upid;
- 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);
+ pid = task_pid(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->numbers[i].nr);
}
- dput(dir);
-out_put_leader:
- dput(leader);
-out:
- return;
+ upid = &pid->numbers[pid->level];
+ if (upid->nr == 1)
+ pid_ns_release_proc(upid->ns);
}
-/* SMP-safe */
-struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
+static struct dentry *proc_pid_instantiate(struct inode *dir,
+ struct dentry * dentry,
+ struct task_struct *task, const void *ptr)
{
- struct dentry *result = ERR_PTR(-ENOENT);
- struct task_struct *task;
+ struct dentry *error = ERR_PTR(-ENOENT);
struct inode *inode;
- struct proc_inode *ei;
- unsigned tgid;
-
- if (dentry->d_name.len == 4 && !memcmp(dentry->d_name.name,"self",4)) {
- inode = new_inode(dir->i_sb);
- if (!inode)
- return ERR_PTR(-ENOMEM);
- ei = PROC_I(inode);
- inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
- inode->i_ino = fake_ino(0, PROC_TGID_INO);
- ei->pde = NULL;
- inode->i_mode = S_IFLNK|S_IRWXUGO;
- inode->i_uid = inode->i_gid = 0;
- inode->i_size = 64;
- inode->i_op = &proc_self_inode_operations;
- d_add(dentry, inode);
- return NULL;
- }
- tgid = name_to_int(dentry);
- if (tgid == ~0U)
- goto out;
-
- rcu_read_lock();
- task = find_task_by_pid(tgid);
- if (task)
- get_task_struct(task);
- rcu_read_unlock();
- if (!task)
- goto out;
- inode = proc_pid_make_inode(dir->i_sb, task, PROC_TGID_INO);
+ inode = proc_pid_make_inode(dir->i_sb, task);
if (!inode)
- goto out_put_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_flags|=S_IMMUTABLE;
-#ifdef CONFIG_SECURITY
- inode->i_nlink = 5;
-#else
- inode->i_nlink = 4;
-#endif
+
+ inode->i_nlink = 2 + pid_entry_count_dirs(tgid_base_stuff,
+ ARRAY_SIZE(tgid_base_stuff));
dentry->d_op = &pid_dentry_operations;
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
if (pid_revalidate(dentry, NULL))
- result = NULL;
-
-out_put_task:
- put_task_struct(task);
+ error = NULL;
out:
- return result;
+ return error;
}
-/* SMP-safe */
-static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
+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 task_struct *leader = proc_task(dir);
- struct inode *inode;
- unsigned tid;
+ unsigned tgid;
+ struct pid_namespace *ns;
- tid = name_to_int(dentry);
- if (tid == ~0U)
+ result = proc_base_lookup(dir, dentry);
+ if (!IS_ERR(result) || PTR_ERR(result) != -ENOENT)
+ goto out;
+
+ tgid = name_to_int(dentry);
+ if (tgid == ~0U)
goto out;
+ ns = dentry->d_sb->s_fs_info;
rcu_read_lock();
- task = find_task_by_pid(tid);
+ task = find_task_by_pid_ns(tgid, ns);
if (task)
get_task_struct(task);
rcu_read_unlock();
if (!task)
goto out;
- if (leader->tgid != task->tgid)
- goto out_drop_task;
-
- inode = proc_pid_make_inode(dir->i_sb, task, PROC_TID_INO);
-
-
- if (!inode)
- goto out_drop_task;
- inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO;
- inode->i_op = &proc_tid_base_inode_operations;
- inode->i_fop = &proc_tid_base_operations;
- inode->i_flags|=S_IMMUTABLE;
-#ifdef CONFIG_SECURITY
- inode->i_nlink = 4;
-#else
- inode->i_nlink = 3;
-#endif
-
- dentry->d_op = &pid_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;
-out_drop_task:
+ result = proc_pid_instantiate(dir, dentry, task, NULL);
put_task_struct(task);
out:
return result;
}
-#define PROC_NUMBUF 10
-
/*
- * 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.
+ * Find the first task with tgid >= tgid
*
- * In the case of a seek we start with &init_task and walk nr
- * threads past it.
*/
-static struct task_struct *first_tgid(int tgid, int nr)
+struct tgid_iter {
+ unsigned int tgid;
+ struct task_struct *task;
+};
+static struct tgid_iter next_tgid(struct pid_namespace *ns, struct tgid_iter iter)
{
- struct task_struct *pos = NULL;
- rcu_read_lock();
- if (tgid && nr) {
- pos = find_task_by_pid(tgid);
- if (pos && !thread_group_leader(pos))
- pos = NULL;
- if (pos)
- nr = 0;
- }
- /* If nr exceeds the number of processes get out quickly */
- if (nr && nr >= nr_processes())
- goto done;
+ struct pid *pid;
- /* If we haven't found our starting place yet start with
- * the init_task and walk nr tasks forward.
- */
- if (!pos && (nr >= 0))
- pos = next_task(&init_task);
-
- for (; pos && pid_alive(pos); pos = next_task(pos)) {
- if (--nr > 0)
- continue;
- get_task_struct(pos);
- goto done;
+ if (iter.task)
+ put_task_struct(iter.task);
+ rcu_read_lock();
+retry:
+ iter.task = NULL;
+ pid = find_ge_pid(iter.tgid, ns);
+ if (pid) {
+ iter.tgid = pid_nr_ns(pid, ns);
+ iter.task = pid_task(pid, PIDTYPE_PID);
+ /* What we to know is if the pid we have find is the
+ * pid of a thread_group_leader. Testing for task
+ * being a thread_group_leader is the obvious thing
+ * todo but there is a window when it fails, due to
+ * the pid transfer logic in de_thread.
+ *
+ * So we perform the straight forward test of seeing
+ * if the pid we have found is the pid of a thread
+ * group leader, and don't worry if the task we have
+ * found doesn't happen to be a thread group leader.
+ * As we don't care in the case of readdir.
+ */
+ if (!iter.task || !has_group_leader_pid(iter.task)) {
+ iter.tgid += 1;
+ goto retry;
+ }
+ get_task_struct(iter.task);
}
- pos = NULL;
-done:
rcu_read_unlock();
- return pos;
+ return iter;
}
-/*
- * 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 struct task_struct *next_tgid(struct task_struct *start)
+#define TGID_OFFSET (FIRST_PROCESS_ENTRY + ARRAY_SIZE(proc_base_stuff))
+
+static int proc_pid_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
+ struct tgid_iter iter)
{
- 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;
+ char name[PROC_NUMBUF];
+ int len = snprintf(name, sizeof(name), "%d", iter.tgid);
+ return proc_fill_cache(filp, dirent, filldir, name, len,
+ proc_pid_instantiate, iter.task, NULL);
}
/* for the /proc/ directory itself, after non-process stuff has been done */
int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
- char buf[PROC_NUMBUF];
unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY;
- struct task_struct *task;
- int tgid;
+ struct task_struct *reaper = get_proc_task(filp->f_path.dentry->d_inode);
+ struct tgid_iter iter;
+ struct pid_namespace *ns;
- if (!nr) {
- ino_t ino = fake_ino(0,PROC_TGID_INO);
- if (filldir(dirent, "self", 4, filp->f_pos, ino, DT_LNK) < 0)
- return 0;
- filp->f_pos++;
- nr++;
+ if (!reaper)
+ goto out_no_task;
+
+ for (; nr < ARRAY_SIZE(proc_base_stuff); filp->f_pos++, nr++) {
+ const struct pid_entry *p = &proc_base_stuff[nr];
+ if (proc_base_fill_cache(filp, dirent, filldir, reaper, p) < 0)
+ goto out;
}
- nr -= 1;
- /* f_version caches the tgid value that the last readdir call couldn't
- * return. lseek aka telldir automagically resets f_version to 0.
- */
- 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 = task->pid;
- len = snprintf(buf, sizeof(buf), "%d", tgid);
- ino = fake_ino(tgid, PROC_TGID_INO);
- if (filldir(dirent, buf, len, filp->f_pos, ino, DT_DIR) < 0) {
- /* returning this tgid failed, save it as the first
- * pid for the next readir call */
- filp->f_version = tgid;
- put_task_struct(task);
- break;
+ ns = filp->f_dentry->d_sb->s_fs_info;
+ iter.task = NULL;
+ iter.tgid = filp->f_pos - TGID_OFFSET;
+ for (iter = next_tgid(ns, iter);
+ iter.task;
+ iter.tgid += 1, iter = next_tgid(ns, iter)) {
+ filp->f_pos = iter.tgid + TGID_OFFSET;
+ if (proc_pid_fill_cache(filp, dirent, filldir, iter) < 0) {
+ put_task_struct(iter.task);
+ goto out;
}
}
+ filp->f_pos = PID_MAX_LIMIT + TGID_OFFSET;
+out:
+ put_task_struct(reaper);
+out_no_task:
return 0;
}
/*
+ * Tasks
+ */
+static const struct pid_entry tid_base_stuff[] = {
+ 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, 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, 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, proc_numa_maps_operations),
+#endif
+ 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, 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, proc_attr_dir_inode_operations, proc_attr_dir_operations),
+#endif
+#ifdef CONFIG_KALLSYMS
+ 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, proc_pid_schedstat),
+#endif
+#ifdef CONFIG_LATENCYTOP
+ REG("latency", S_IRUGO, proc_lstats_operations),
+#endif
+#ifdef CONFIG_PROC_PID_CPUSET
+ REG("cpuset", S_IRUGO, proc_cpuset_operations),
+#endif
+#ifdef CONFIG_CGROUPS
+ REG("cgroup", S_IRUGO, proc_cgroup_operations),
+#endif
+ 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, proc_loginuid_operations),
+ REG("sessionid", S_IRUSR, proc_sessionid_operations),
+#endif
+#ifdef CONFIG_FAULT_INJECTION
+ 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
+};
+
+static int proc_tid_base_readdir(struct file * filp,
+ void * dirent, filldir_t filldir)
+{
+ return proc_pident_readdir(filp,dirent,filldir,
+ tid_base_stuff,ARRAY_SIZE(tid_base_stuff));
+}
+
+static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
+ return proc_pident_lookup(dir, dentry,
+ tid_base_stuff, ARRAY_SIZE(tid_base_stuff));
+}
+
+static const struct file_operations proc_tid_base_operations = {
+ .read = generic_read_dir,
+ .readdir = proc_tid_base_readdir,
+};
+
+static const struct inode_operations proc_tid_base_inode_operations = {
+ .lookup = proc_tid_base_lookup,
+ .getattr = pid_getattr,
+ .setattr = proc_setattr,
+};
+
+static struct dentry *proc_task_instantiate(struct inode *dir,
+ struct dentry *dentry, struct task_struct *task, const void *ptr)
+{
+ struct dentry *error = ERR_PTR(-ENOENT);
+ struct inode *inode;
+ inode = proc_pid_make_inode(dir->i_sb, task);
+
+ if (!inode)
+ goto out;
+ inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO;
+ inode->i_op = &proc_tid_base_inode_operations;
+ inode->i_fop = &proc_tid_base_operations;
+ inode->i_flags|=S_IMMUTABLE;
+
+ inode->i_nlink = 2 + pid_entry_count_dirs(tid_base_stuff,
+ ARRAY_SIZE(tid_base_stuff));
+
+ dentry->d_op = &pid_dentry_operations;
+
+ d_add(dentry, inode);
+ /* Close the race of the process dying before we return the dentry */
+ if (pid_revalidate(dentry, NULL))
+ error = NULL;
+out:
+ return error;
+}
+
+static struct dentry *proc_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 = get_proc_task(dir);
+ unsigned tid;
+ struct pid_namespace *ns;
+
+ if (!leader)
+ goto out_no_task;
+
+ tid = name_to_int(dentry);
+ if (tid == ~0U)
+ goto out;
+
+ ns = dentry->d_sb->s_fs_info;
+ rcu_read_lock();
+ task = find_task_by_pid_ns(tid, ns);
+ if (task)
+ get_task_struct(task);
+ rcu_read_unlock();
+ if (!task)
+ goto out;
+ if (!same_thread_group(leader, task))
+ goto out_drop_task;
+
+ result = proc_task_instantiate(dir, dentry, task, NULL);
+out_drop_task:
+ put_task_struct(task);
+out:
+ put_task_struct(leader);
+out_no_task:
+ return result;
+}
+
+/*
* 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
* 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)
+static struct task_struct *first_tid(struct task_struct *leader,
+ int tid, int nr, struct pid_namespace *ns)
{
- struct task_struct *pos = NULL;
- read_lock(&tasklist_lock);
+ struct task_struct *pos;
+ rcu_read_lock();
/* Attempt to start with the pid of a thread */
if (tid && (nr > 0)) {
- pos = find_task_by_pid(tid);
- if (pos && (pos->group_leader != leader))
- pos = NULL;
- if (pos)
- nr = 0;
+ pos = find_task_by_pid_ns(tid, ns);
+ if (pos && (pos->group_leader == leader))
+ goto found;
}
/* If nr exceeds the number of threads there is nothing todo */
- if (nr) {
- int threads = 0;
- task_lock(leader);
- if (leader->signal)
- threads = atomic_read(&leader->signal->count);
- task_unlock(leader);
- if (nr >= threads)
- goto done;
- }
+ 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.
+ /* If we haven't found our starting place yet start
+ * with the leader and walk nr threads forward.
*/
- if (!pos && (nr >= 0))
- pos = leader;
-
- for (; pos && pid_alive(pos); pos = next_thread(pos)) {
- if (--nr > 0)
- continue;
- get_task_struct(pos);
- goto done;
+ for (pos = leader; nr > 0; --nr) {
+ pos = next_thread(pos);
+ if (pos == leader) {
+ pos = NULL;
+ goto out;
+ }
}
- pos = NULL;
-done:
- read_unlock(&tasklist_lock);
+found:
+ get_task_struct(pos);
+out:
+ rcu_read_unlock();
return pos;
}
*/
static struct task_struct *next_tid(struct task_struct *start)
{
- struct task_struct *pos;
- read_lock(&tasklist_lock);
- pos = start;
- if (pid_alive(start))
+ struct task_struct *pos = NULL;
+ rcu_read_lock();
+ if (pid_alive(start)) {
pos = next_thread(start);
- if (pid_alive(pos) && (pos != start->group_leader))
- get_task_struct(pos);
- else
- pos = NULL;
- read_unlock(&tasklist_lock);
+ if (thread_group_leader(pos))
+ pos = NULL;
+ else
+ get_task_struct(pos);
+ }
+ rcu_read_unlock();
put_task_struct(start);
return pos;
}
+static int proc_task_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
+ struct task_struct *task, int tid)
+{
+ char name[PROC_NUMBUF];
+ int len = snprintf(name, sizeof(name), "%d", tid);
+ return proc_fill_cache(filp, dirent, filldir, name, len,
+ proc_task_instantiate, task, NULL);
+}
+
/* for the /proc/TGID/task/ directories */
static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
- char buf[PROC_NUMBUF];
- struct dentry *dentry = filp->f_dentry;
+ struct dentry *dentry = filp->f_path.dentry;
struct inode *inode = dentry->d_inode;
- struct task_struct *leader = proc_task(inode);
+ struct task_struct *leader = NULL;
struct task_struct *task;
int retval = -ENOENT;
ino_t ino;
int tid;
- unsigned long pos = filp->f_pos; /* avoiding "long long" filp->f_pos */
+ struct pid_namespace *ns;
- if (!pid_alive(leader))
- goto out;
+ task = get_proc_task(inode);
+ if (!task)
+ goto out_no_task;
+ rcu_read_lock();
+ if (pid_alive(task)) {
+ leader = task->group_leader;
+ get_task_struct(leader);
+ }
+ rcu_read_unlock();
+ put_task_struct(task);
+ if (!leader)
+ goto out_no_task;
retval = 0;
- switch (pos) {
+ 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 */
}
/* 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;
+ 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);
+ for (task = first_tid(leader, tid, filp->f_pos - 2, ns);
task;
- task = next_tid(task), pos++) {
- int len;
- tid = task->pid;
- len = snprintf(buf, sizeof(buf), "%d", tid);
- ino = fake_ino(tid, PROC_TID_INO);
- if (filldir(dirent, buf, len, pos, ino, DT_DIR < 0)) {
+ 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
* pid for the next readir call */
- filp->f_version = tid;
+ filp->f_version = (u64)tid;
put_task_struct(task);
break;
}
}
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 = proc_task(inode);
+ struct task_struct *p = get_proc_task(inode);
generic_fillattr(inode, stat);
- if (pid_alive(p)) {
- task_lock(p);
- if (p->signal)
- stat->nlink += atomic_read(&p->signal->count);
- task_unlock(p);
+ if (p) {
+ stat->nlink += get_nr_threads(p);
+ put_task_struct(p);
}
return 0;
}
+
+static const struct inode_operations proc_task_inode_operations = {
+ .lookup = proc_task_lookup,
+ .getattr = proc_task_getattr,
+ .setattr = proc_setattr,
+};
+
+static const struct file_operations proc_task_operations = {
+ .read = generic_read_dir,
+ .readdir = proc_task_readdir,
+};