#include <linux/mm.h>
#include <linux/rcupdate.h>
#include <linux/kallsyms.h>
+#include <linux/resource.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/ptrace.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 "internal.h"
/* NOTE:
* in /proc for a task before it execs a suid executable.
*/
-
-/* Worst case buffer size needed for holding an integer. */
-#define PROC_NUMBUF 13
-
struct pid_entry {
char *name;
int len;
(task == current || \
(task->parent == current && \
(task->ptrace & PT_PTRACED) && \
- (task->state == TASK_STOPPED || task->state == TASK_TRACED) && \
+ (task_is_stopped_or_traced(task)) && \
security_ptrace(current,task) == 0))
+struct mm_struct *mm_for_maps(struct task_struct *task)
+{
+ struct mm_struct *mm = get_task_mm(task);
+ if (!mm)
+ return NULL;
+ down_read(&mm->mmap_sem);
+ task_lock(task);
+ if (task->mm != mm)
+ goto out;
+ if (task->mm != current->mm && __ptrace_may_attach(task) < 0)
+ goto out;
+ task_unlock(task);
+ return mm;
+out:
+ task_unlock(task);
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+ return NULL;
+}
+
static int proc_pid_cmdline(struct task_struct *task, char * buffer)
{
int res = 0;
}
#endif
+#ifdef CONFIG_LATENCYTOP
+static int lstats_show_proc(struct seq_file *m, void *v)
+{
+ int i;
+ struct task_struct *task = m->private;
+ 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_NAME_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");
+ }
+
+ }
+ return 0;
+}
+
+static int lstats_open(struct inode *inode, struct file *file)
+{
+ int ret;
+ struct seq_file *m;
+ struct task_struct *task = get_proc_task(inode);
+
+ ret = single_open(file, lstats_show_proc, NULL);
+ if (!ret) {
+ m = file->private_data;
+ m->private = task;
+ }
+ return ret;
+}
+
+static ssize_t lstats_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *offs)
+{
+ struct seq_file *m;
+ struct task_struct *task;
+
+ m = file->private_data;
+ task = m->private;
+ clear_all_latency_tracing(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)
return sprintf(buffer, "%lu\n", points);
}
+struct limit_names {
+ char *name;
+ char *unit;
+};
+
+static const struct limit_names lnames[RLIM_NLIMITS] = {
+ [RLIMIT_CPU] = {"Max cpu time", "ms"},
+ [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},
+};
+
+/* Display limits for a process */
+static int proc_pid_limits(struct task_struct *task, char *buffer)
+{
+ unsigned int i;
+ int count = 0;
+ unsigned long flags;
+ char *bufptr = buffer;
+
+ struct rlimit rlim[RLIM_NLIMITS];
+
+ rcu_read_lock();
+ if (!lock_task_sighand(task,&flags)) {
+ rcu_read_unlock();
+ return 0;
+ }
+ memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS);
+ unlock_task_sighand(task, &flags);
+ rcu_read_unlock();
+
+ /*
+ * 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");
+ }
+
+ return count;
+}
+
/************************************************************************/
/* Here the fs part begins */
/************************************************************************/
static int mounts_open(struct inode *inode, struct file *file)
{
struct task_struct *task = get_proc_task(inode);
+ struct nsproxy *nsp;
struct mnt_namespace *ns = NULL;
struct proc_mounts *p;
int ret = -EINVAL;
if (task) {
- task_lock(task);
- if (task->nsproxy) {
- ns = task->nsproxy->mnt_ns;
+ rcu_read_lock();
+ nsp = task_nsproxy(task);
+ if (nsp) {
+ ns = nsp->mnt_ns;
if (ns)
get_mnt_ns(ns);
}
- task_unlock(task);
+ rcu_read_unlock();
+
put_task_struct(task);
}
if (!ret) {
struct seq_file *m = file->private_data;
+ struct nsproxy *nsp;
struct mnt_namespace *mnt_ns = NULL;
struct task_struct *task = get_proc_task(inode);
if (task) {
- task_lock(task);
- if (task->nsproxy)
- mnt_ns = task->nsproxy->mnt_ns;
- if (mnt_ns)
- get_mnt_ns(mnt_ns);
- task_unlock(task);
+ rcu_read_lock();
+ nsp = task_nsproxy(task);
+ if (nsp) {
+ mnt_ns = nsp->mnt_ns;
+ if (mnt_ns)
+ get_mnt_ns(mnt_ns);
+ }
+ rcu_read_unlock();
+
put_task_struct(task);
}
}
#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:
.write = oom_adjust_write,
};
-#ifdef CONFIG_MMU
-static ssize_t clear_refs_write(struct file *file, const char __user *buf,
- size_t count, loff_t *ppos)
-{
- struct task_struct *task;
- char buffer[PROC_NUMBUF], *end;
- struct mm_struct *mm;
-
- memset(buffer, 0, sizeof(buffer));
- if (count > sizeof(buffer) - 1)
- count = sizeof(buffer) - 1;
- if (copy_from_user(buffer, buf, count))
- return -EFAULT;
- if (!simple_strtol(buffer, &end, 0))
- return -EINVAL;
- if (*end == '\n')
- end++;
- task = get_proc_task(file->f_path.dentry->d_inode);
- if (!task)
- return -ESRCH;
- mm = get_task_mm(task);
- if (mm) {
- clear_refs_smap(mm);
- mmput(mm);
- }
- put_task_struct(task);
- if (end - buffer == 0)
- return -EIO;
- return end - buffer;
-}
-
-static struct file_operations proc_clear_refs_operations = {
- .write = clear_refs_write,
-};
-#endif
-
#ifdef CONFIG_AUDITSYSCALL
#define TMPBUFLEN 21
static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
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);
}
};
#endif
+
#ifdef CONFIG_SCHED_DEBUG
/*
* Print out various scheduling related per-task fields:
struct dentry *dentry = filp->f_path.dentry;
struct inode *inode = dentry->d_inode;
struct task_struct *p = get_proc_task(inode);
- unsigned int fd, tid, ino;
+ unsigned int fd, ino;
int retval;
struct files_struct * files;
struct fdtable *fdt;
if (!p)
goto out_no_task;
retval = 0;
- tid = p->pid;
fd = filp->f_pos;
switch (fd) {
const struct pid_entry *ents, unsigned int nents)
{
int i;
- int pid;
struct dentry *dentry = filp->f_path.dentry;
struct inode *inode = dentry->d_inode;
struct task_struct *task = get_proc_task(inode);
goto out_no_task;
ret = 0;
- pid = task->pid;
i = filp->f_pos;
switch (i) {
case 0:
int buflen)
{
char tmp[PROC_NUMBUF];
- sprintf(tmp, "%d", current->tgid);
+ sprintf(tmp, "%d", task_tgid_vnr(current));
return vfs_readlink(dentry,buffer,buflen,tmp);
}
static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
{
char tmp[PROC_NUMBUF];
- sprintf(tmp, "%d", current->tgid);
+ sprintf(tmp, "%d", task_tgid_vnr(current));
return ERR_PTR(vfs_follow_link(nd,tmp));
}
REG("environ", S_IRUSR, environ),
INF("auxv", S_IRUSR, pid_auxv),
INF("status", S_IRUGO, pid_status),
+ INF("limits", S_IRUSR, pid_limits),
#ifdef CONFIG_SCHED_DEBUG
REG("sched", S_IRUGO|S_IWUSR, pid_sched),
#endif
LNK("exe", exe),
REG("mounts", S_IRUGO, mounts),
REG("mountstats", S_IRUSR, mountstats),
-#ifdef CONFIG_MMU
+#ifdef CONFIG_PROC_PAGE_MONITOR
REG("clear_refs", S_IWUSR, clear_refs),
REG("smaps", S_IRUGO, smaps),
+ REG("pagemap", S_IRUSR, pagemap),
#endif
#ifdef CONFIG_SECURITY
DIR("attr", S_IRUGO|S_IXUGO, attr_dir),
#ifdef CONFIG_SCHEDSTATS
INF("schedstat", S_IRUGO, pid_schedstat),
#endif
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_LATENCYTOP
+ REG("latency", S_IRUGO, lstats),
+#endif
+#ifdef CONFIG_PROC_PID_CPUSET
REG("cpuset", S_IRUGO, cpuset),
+#endif
+#ifdef CONFIG_CGROUPS
+ REG("cgroup", S_IRUGO, cgroup),
#endif
INF("oom_score", S_IRUGO, oom_score),
REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust),
.setattr = proc_setattr,
};
-/**
- * proc_flush_task - Remove dcache entries for @task from the /proc dcache.
- *
- * @task: task that should be flushed.
- *
- * Looks in the dcache for
- * /proc/@pid
- * /proc/@tgid/task/@pid
- * if either directory is present flushes it and all of it'ts children
- * from the dcache.
- *
- * It is safe and reasonable to cache /proc entries for a task until
- * that task exits. After that they just clog up the dcache with
- * useless entries, possibly causing useful dcache entries to be
- * flushed instead. This routine is proved to flush those useless
- * dcache entries at process exit time.
- *
- * NOTE: This routine is just an optimization so it does not guarantee
- * that no dcache entries will exist at process exit time it
- * just makes it very unlikely that any will persist.
- */
-void proc_flush_task(struct task_struct *task)
+static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
{
struct dentry *dentry, *leader, *dir;
char buf[PROC_NUMBUF];
struct qstr name;
name.name = buf;
- name.len = snprintf(buf, sizeof(buf), "%d", task->pid);
- dentry = d_hash_and_lookup(proc_mnt->mnt_root, &name);
+ 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);
}
- if (thread_group_leader(task))
+ if (tgid == 0)
goto out;
name.name = buf;
- name.len = snprintf(buf, sizeof(buf), "%d", task->tgid);
- leader = d_hash_and_lookup(proc_mnt->mnt_root, &name);
+ name.len = snprintf(buf, sizeof(buf), "%d", tgid);
+ leader = d_hash_and_lookup(mnt->mnt_root, &name);
if (!leader)
goto out;
goto out_put_leader;
name.name = buf;
- name.len = snprintf(buf, sizeof(buf), "%d", task->pid);
+ name.len = snprintf(buf, sizeof(buf), "%d", pid);
dentry = d_hash_and_lookup(dir, &name);
if (dentry) {
shrink_dcache_parent(dentry);
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
+ * if either directory is present flushes it and all of it'ts children
+ * from the dcache.
+ *
+ * It is safe and reasonable to cache /proc entries for a task until
+ * that task exits. After that they just clog up the dcache with
+ * useless entries, possibly causing useful dcache entries to be
+ * flushed instead. This routine is proved to flush those useless
+ * dcache entries at process exit time.
+ *
+ * NOTE: This routine is just an optimization so it does not guarantee
+ * that no dcache entries will exist at process exit time it
+ * just makes it very unlikely that any will persist.
+ */
+
+void proc_flush_task(struct task_struct *task)
+{
+ int i;
+ struct pid *pid, *tgid = NULL;
+ struct upid *upid;
+
+ pid = task_pid(task);
+ if (thread_group_leader(task))
+ tgid = task_tgid(task);
+
+ for (i = 0; i <= pid->level; i++) {
+ upid = &pid->numbers[i];
+ proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr,
+ tgid ? tgid->numbers[i].nr : 0);
+ }
+
+ upid = &pid->numbers[pid->level];
+ if (upid->nr == 1)
+ pid_ns_release_proc(upid->ns);
+}
+
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;
unsigned tgid;
+ struct pid_namespace *ns;
result = proc_base_lookup(dir, dentry);
if (!IS_ERR(result) || PTR_ERR(result) != -ENOENT)
if (tgid == ~0U)
goto out;
+ ns = dentry->d_sb->s_fs_info;
rcu_read_lock();
- task = find_task_by_pid(tgid);
+ task = find_task_by_pid_ns(tgid, ns);
if (task)
get_task_struct(task);
rcu_read_unlock();
* Find the first task with tgid >= tgid
*
*/
-static struct task_struct *next_tgid(unsigned int tgid)
-{
+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 pid *pid;
+ if (iter.task)
+ put_task_struct(iter.task);
rcu_read_lock();
retry:
- task = NULL;
- pid = find_ge_pid(tgid);
+ iter.task = NULL;
+ pid = find_ge_pid(iter.tgid, ns);
if (pid) {
- tgid = pid->nr + 1;
- task = pid_task(pid, PIDTYPE_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
* found doesn't happen to be a thread group leader.
* As we don't care in the case of readdir.
*/
- if (!task || !has_group_leader_pid(task))
+ if (!iter.task || !has_group_leader_pid(iter.task)) {
+ iter.tgid += 1;
goto retry;
- get_task_struct(task);
+ }
+ get_task_struct(iter.task);
}
rcu_read_unlock();
- return task;
+ return iter;
}
#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 task_struct *task, int tgid)
+ struct tgid_iter iter)
{
char name[PROC_NUMBUF];
- int len = snprintf(name, sizeof(name), "%d", tgid);
+ int len = snprintf(name, sizeof(name), "%d", iter.tgid);
return proc_fill_cache(filp, dirent, filldir, name, len,
- proc_pid_instantiate, task, NULL);
+ proc_pid_instantiate, iter.task, NULL);
}
/* for the /proc/ directory itself, after non-process stuff has been done */
{
unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY;
struct task_struct *reaper = get_proc_task(filp->f_path.dentry->d_inode);
- struct task_struct *task;
- int tgid;
+ struct tgid_iter iter;
+ struct pid_namespace *ns;
if (!reaper)
goto out_no_task;
goto out;
}
- tgid = filp->f_pos - TGID_OFFSET;
- for (task = next_tgid(tgid);
- task;
- put_task_struct(task), task = next_tgid(tgid + 1)) {
- tgid = task->pid;
- filp->f_pos = tgid + TGID_OFFSET;
- if (proc_pid_fill_cache(filp, dirent, filldir, task, tgid) < 0) {
- put_task_struct(task);
+ 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;
}
}
REG("environ", S_IRUSR, environ),
INF("auxv", S_IRUSR, pid_auxv),
INF("status", S_IRUGO, pid_status),
+ INF("limits", S_IRUSR, pid_limits),
#ifdef CONFIG_SCHED_DEBUG
REG("sched", S_IRUGO|S_IWUSR, pid_sched),
#endif
LNK("root", root),
LNK("exe", exe),
REG("mounts", S_IRUGO, mounts),
-#ifdef CONFIG_MMU
+#ifdef CONFIG_PROC_PAGE_MONITOR
REG("clear_refs", S_IWUSR, clear_refs),
REG("smaps", S_IRUGO, smaps),
+ REG("pagemap", S_IRUSR, pagemap),
#endif
#ifdef CONFIG_SECURITY
DIR("attr", S_IRUGO|S_IXUGO, attr_dir),
#ifdef CONFIG_SCHEDSTATS
INF("schedstat", S_IRUGO, pid_schedstat),
#endif
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_LATENCYTOP
+ REG("latency", S_IRUGO, lstats),
+#endif
+#ifdef CONFIG_PROC_PID_CPUSET
REG("cpuset", S_IRUGO, cpuset),
+#endif
+#ifdef CONFIG_CGROUPS
+ REG("cgroup", S_IRUGO, cgroup),
#endif
INF("oom_score", S_IRUGO, oom_score),
REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust),
struct task_struct *task;
struct task_struct *leader = get_proc_task(dir);
unsigned tid;
+ struct pid_namespace *ns;
if (!leader)
goto out_no_task;
if (tid == ~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(tid, ns);
if (task)
get_task_struct(task);
rcu_read_unlock();
if (!task)
goto out;
- if (leader->tgid != task->tgid)
+ if (!same_thread_group(leader, task))
goto out_drop_task;
result = proc_task_instantiate(dir, dentry, task, NULL);
* threads past it.
*/
static struct task_struct *first_tid(struct task_struct *leader,
- int tid, int nr)
+ int tid, int nr, struct pid_namespace *ns)
{
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);
+ pos = find_task_by_pid_ns(tid, ns);
if (pos && (pos->group_leader == leader))
goto found;
}
ino_t ino;
int tid;
unsigned long pos = filp->f_pos; /* avoiding "long long" filp->f_pos */
+ struct pid_namespace *ns;
task = get_proc_task(inode);
if (!task)
/* f_version caches the tgid value that the last readdir call couldn't
* return. lseek aka telldir automagically resets f_version to 0.
*/
+ 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, pos - 2, ns);
task;
task = next_tid(task), pos++) {
- tid = task->pid;
+ 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 */
projects / mirror_ubuntu-bionic-kernel.git / blobdiff