summaryrefslogtreecommitdiff
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/Kconfig10
-rw-r--r--fs/proc/array.c12
-rw-r--r--fs/proc/base.c231
-rw-r--r--fs/proc/inode.c9
-rw-r--r--fs/proc/kcore.c4
-rw-r--r--fs/proc/namespaces.c4
-rw-r--r--fs/proc/nommu.c7
-rw-r--r--fs/proc/self.c24
-rw-r--r--fs/proc/task_mmu.c11
-rw-r--r--fs/proc/task_nommu.c7
-rw-r--r--fs/proc/thread_self.c22
11 files changed, 270 insertions, 71 deletions
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index 2183fcf41..1ade1206b 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -71,3 +71,13 @@ config PROC_PAGE_MONITOR
/proc/pid/smaps, /proc/pid/clear_refs, /proc/pid/pagemap,
/proc/kpagecount, and /proc/kpageflags. Disabling these
interfaces will reduce the size of the kernel by approximately 4kb.
+
+config PROC_CHILDREN
+ bool "Include /proc/<pid>/task/<tid>/children file"
+ default n
+ help
+ Provides a fast way to retrieve first level children pids of a task. See
+ <file:Documentation/filesystems/proc.txt> for more information.
+
+ Say Y if you are running any user-space software which takes benefit from
+ this interface. For example, rkt is such a piece of software.
diff --git a/fs/proc/array.c b/fs/proc/array.c
index fd02a9ebf..ce065cf31 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -126,6 +126,14 @@ static inline const char *get_task_state(struct task_struct *tsk)
{
unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT;
+ /*
+ * Parked tasks do not run; they sit in __kthread_parkme().
+ * Without this check, we would report them as running, which is
+ * clearly wrong, so we report them as sleeping instead.
+ */
+ if (tsk->state == TASK_PARKED)
+ state = TASK_INTERRUPTIBLE;
+
BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1);
return task_state_array[fls(state)];
@@ -569,7 +577,7 @@ int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
return 0;
}
-#ifdef CONFIG_CHECKPOINT_RESTORE
+#ifdef CONFIG_PROC_CHILDREN
static struct pid *
get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos)
{
@@ -692,4 +700,4 @@ const struct file_operations proc_tid_children_operations = {
.llseek = seq_lseek,
.release = children_seq_release,
};
-#endif /* CONFIG_CHECKPOINT_RESTORE */
+#endif /* CONFIG_PROC_CHILDREN */
diff --git a/fs/proc/base.c b/fs/proc/base.c
index c439a9dcc..aa50d1ac2 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -196,18 +196,210 @@ static int proc_root_link(struct dentry *dentry, struct path *path)
return result;
}
-static int proc_pid_cmdline(struct seq_file *m, struct pid_namespace *ns,
- struct pid *pid, struct task_struct *task)
+static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
+ size_t _count, loff_t *pos)
{
+ struct task_struct *tsk;
+ struct mm_struct *mm;
+ char *page;
+ unsigned long count = _count;
+ unsigned long arg_start, arg_end, env_start, env_end;
+ unsigned long len1, len2, len;
+ unsigned long p;
+ char c;
+ ssize_t rv;
+
+ BUG_ON(*pos < 0);
+
+ tsk = get_proc_task(file_inode(file));
+ if (!tsk)
+ return -ESRCH;
+ mm = get_task_mm(tsk);
+ put_task_struct(tsk);
+ if (!mm)
+ return 0;
+ /* Check if process spawned far enough to have cmdline. */
+ if (!mm->env_end) {
+ rv = 0;
+ goto out_mmput;
+ }
+
+ page = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!page) {
+ rv = -ENOMEM;
+ goto out_mmput;
+ }
+
+ down_read(&mm->mmap_sem);
+ arg_start = mm->arg_start;
+ arg_end = mm->arg_end;
+ env_start = mm->env_start;
+ env_end = mm->env_end;
+ up_read(&mm->mmap_sem);
+
+ BUG_ON(arg_start > arg_end);
+ BUG_ON(env_start > env_end);
+
+ len1 = arg_end - arg_start;
+ len2 = env_end - env_start;
+
+ /* Empty ARGV. */
+ if (len1 == 0) {
+ rv = 0;
+ goto out_free_page;
+ }
/*
- * Rely on struct seq_operations::show() being called once
- * per internal buffer allocation. See single_open(), traverse().
+ * Inherently racy -- command line shares address space
+ * with code and data.
*/
- BUG_ON(m->size < PAGE_SIZE);
- m->count += get_cmdline(task, m->buf, PAGE_SIZE);
- return 0;
+ rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0);
+ if (rv <= 0)
+ goto out_free_page;
+
+ rv = 0;
+
+ if (c == '\0') {
+ /* Command line (set of strings) occupies whole ARGV. */
+ if (len1 <= *pos)
+ goto out_free_page;
+
+ p = arg_start + *pos;
+ len = len1 - *pos;
+ while (count > 0 && len > 0) {
+ unsigned int _count;
+ int nr_read;
+
+ _count = min3(count, len, PAGE_SIZE);
+ nr_read = access_remote_vm(mm, p, page, _count, 0);
+ if (nr_read < 0)
+ rv = nr_read;
+ if (nr_read <= 0)
+ goto out_free_page;
+
+ if (copy_to_user(buf, page, nr_read)) {
+ rv = -EFAULT;
+ goto out_free_page;
+ }
+
+ p += nr_read;
+ len -= nr_read;
+ buf += nr_read;
+ count -= nr_read;
+ rv += nr_read;
+ }
+ } else {
+ /*
+ * Command line (1 string) occupies ARGV and maybe
+ * extends into ENVP.
+ */
+ if (len1 + len2 <= *pos)
+ goto skip_argv_envp;
+ if (len1 <= *pos)
+ goto skip_argv;
+
+ p = arg_start + *pos;
+ len = len1 - *pos;
+ while (count > 0 && len > 0) {
+ unsigned int _count, l;
+ int nr_read;
+ bool final;
+
+ _count = min3(count, len, PAGE_SIZE);
+ nr_read = access_remote_vm(mm, p, page, _count, 0);
+ if (nr_read < 0)
+ rv = nr_read;
+ if (nr_read <= 0)
+ goto out_free_page;
+
+ /*
+ * Command line can be shorter than whole ARGV
+ * even if last "marker" byte says it is not.
+ */
+ final = false;
+ l = strnlen(page, nr_read);
+ if (l < nr_read) {
+ nr_read = l;
+ final = true;
+ }
+
+ if (copy_to_user(buf, page, nr_read)) {
+ rv = -EFAULT;
+ goto out_free_page;
+ }
+
+ p += nr_read;
+ len -= nr_read;
+ buf += nr_read;
+ count -= nr_read;
+ rv += nr_read;
+
+ if (final)
+ goto out_free_page;
+ }
+skip_argv:
+ /*
+ * Command line (1 string) occupies ARGV and
+ * extends into ENVP.
+ */
+ if (len1 <= *pos) {
+ p = env_start + *pos - len1;
+ len = len1 + len2 - *pos;
+ } else {
+ p = env_start;
+ len = len2;
+ }
+ while (count > 0 && len > 0) {
+ unsigned int _count, l;
+ int nr_read;
+ bool final;
+
+ _count = min3(count, len, PAGE_SIZE);
+ nr_read = access_remote_vm(mm, p, page, _count, 0);
+ if (nr_read < 0)
+ rv = nr_read;
+ if (nr_read <= 0)
+ goto out_free_page;
+
+ /* Find EOS. */
+ final = false;
+ l = strnlen(page, nr_read);
+ if (l < nr_read) {
+ nr_read = l;
+ final = true;
+ }
+
+ if (copy_to_user(buf, page, nr_read)) {
+ rv = -EFAULT;
+ goto out_free_page;
+ }
+
+ p += nr_read;
+ len -= nr_read;
+ buf += nr_read;
+ count -= nr_read;
+ rv += nr_read;
+
+ if (final)
+ goto out_free_page;
+ }
+skip_argv_envp:
+ ;
+ }
+
+out_free_page:
+ free_page((unsigned long)page);
+out_mmput:
+ mmput(mm);
+ if (rv > 0)
+ *pos += rv;
+ return rv;
}
+static const struct file_operations proc_pid_cmdline_ops = {
+ .read = proc_pid_cmdline_read,
+ .llseek = generic_file_llseek,
+};
+
static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
@@ -304,15 +496,18 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
}
#endif
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
/*
* Provides /proc/PID/schedstat
*/
static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
- seq_printf(m, "%llu %llu %lu\n",
- (unsigned long long)tsk_seruntime(task),
+ if (unlikely(!sched_info_on()))
+ seq_printf(m, "0 0 0\n");
+ else
+ seq_printf(m, "%llu %llu %lu\n",
+ (unsigned long long)task->se.sum_exec_runtime,
(unsigned long long)task->sched_info.run_delay,
task->sched_info.pcount);
@@ -1380,7 +1575,7 @@ static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
return -ENOENT;
}
-static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_pid_follow_link(struct dentry *dentry, void **cookie)
{
struct inode *inode = d_inode(dentry);
struct path path;
@@ -1394,7 +1589,7 @@ static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
if (error)
goto out;
- nd_jump_link(nd, &path);
+ nd_jump_link(&path);
return NULL;
out:
return ERR_PTR(error);
@@ -1744,7 +1939,7 @@ static int proc_map_files_get_link(struct dentry *dentry, struct path *path)
down_read(&mm->mmap_sem);
vma = find_exact_vma(mm, vm_start, vm_end);
if (vma && vma->vm_file) {
- *path = vma_pr_or_file(vma)->f_path;
+ *path = vma->vm_file->f_path;
path_get(path);
rc = 0;
}
@@ -2572,7 +2767,7 @@ static const struct pid_entry tgid_base_stuff[] = {
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
ONE("syscall", S_IRUSR, proc_pid_syscall),
#endif
- ONE("cmdline", S_IRUGO, proc_pid_cmdline),
+ REG("cmdline", S_IRUGO, proc_pid_cmdline_ops),
ONE("stat", S_IRUGO, proc_tgid_stat),
ONE("statm", S_IRUGO, proc_pid_statm),
REG("maps", S_IRUGO, proc_pid_maps_operations),
@@ -2600,7 +2795,7 @@ static const struct pid_entry tgid_base_stuff[] = {
#ifdef CONFIG_STACKTRACE
ONE("stack", S_IRUSR, proc_pid_stack),
#endif
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
ONE("schedstat", S_IRUGO, proc_pid_schedstat),
#endif
#ifdef CONFIG_LATENCYTOP
@@ -2918,11 +3113,11 @@ static const struct pid_entry tid_base_stuff[] = {
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
ONE("syscall", S_IRUSR, proc_pid_syscall),
#endif
- ONE("cmdline", S_IRUGO, proc_pid_cmdline),
+ REG("cmdline", S_IRUGO, proc_pid_cmdline_ops),
ONE("stat", S_IRUGO, proc_tid_stat),
ONE("statm", S_IRUGO, proc_pid_statm),
REG("maps", S_IRUGO, proc_tid_maps_operations),
-#ifdef CONFIG_CHECKPOINT_RESTORE
+#ifdef CONFIG_PROC_CHILDREN
REG("children", S_IRUGO, proc_tid_children_operations),
#endif
#ifdef CONFIG_NUMA
@@ -2948,7 +3143,7 @@ static const struct pid_entry tid_base_stuff[] = {
#ifdef CONFIG_STACKTRACE
ONE("stack", S_IRUSR, proc_pid_stack),
#endif
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
ONE("schedstat", S_IRUGO, proc_pid_schedstat),
#endif
#ifdef CONFIG_LATENCYTOP
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index e3eb55246..bd95b9fde 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -23,7 +23,6 @@
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/magic.h>
-#include <linux/namei.h>
#include <asm/uaccess.h>
@@ -394,16 +393,16 @@ static const struct file_operations proc_reg_file_ops_no_compat = {
};
#endif
-static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_follow_link(struct dentry *dentry, void **cookie)
{
struct proc_dir_entry *pde = PDE(d_inode(dentry));
if (unlikely(!use_pde(pde)))
return ERR_PTR(-EINVAL);
- nd_set_link(nd, pde->data);
- return pde;
+ *cookie = pde;
+ return pde->data;
}
-static void proc_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
+static void proc_put_link(struct inode *unused, void *p)
{
unuse_pde(p);
}
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 91a4e6426..92e6726f6 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -92,7 +92,7 @@ static size_t get_kcore_size(int *nphdr, size_t *elf_buflen)
roundup(sizeof(CORE_STR), 4)) +
roundup(sizeof(struct elf_prstatus), 4) +
roundup(sizeof(struct elf_prpsinfo), 4) +
- roundup(sizeof(struct task_struct), 4);
+ roundup(arch_task_struct_size, 4);
*elf_buflen = PAGE_ALIGN(*elf_buflen);
return size + *elf_buflen;
}
@@ -415,7 +415,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff)
/* set up the task structure */
notes[2].name = CORE_STR;
notes[2].type = NT_TASKSTRUCT;
- notes[2].datasz = sizeof(struct task_struct);
+ notes[2].datasz = arch_task_struct_size;
notes[2].data = current;
nhdr->p_filesz += notesize(&notes[2]);
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index e512642db..f6e8354b8 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -30,7 +30,7 @@ static const struct proc_ns_operations *ns_entries[] = {
&mntns_operations,
};
-static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie)
{
struct inode *inode = d_inode(dentry);
const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
@@ -45,7 +45,7 @@ static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
if (ptrace_may_access(task, PTRACE_MODE_READ)) {
error = ns_get_path(&ns_path, task, ns_ops);
if (!error)
- nd_jump_link(nd, &ns_path);
+ nd_jump_link(&ns_path);
}
put_task_struct(task);
return error;
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index 139718132..f8595e8b5 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -45,10 +45,7 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
file = region->vm_file;
if (file) {
- struct inode *inode;
-
- file = vmr_pr_or_file(region);
- inode = file_inode(file);
+ struct inode *inode = file_inode(region->vm_file);
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
}
@@ -67,7 +64,7 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
if (file) {
seq_pad(m, ' ');
- seq_path(m, &file->f_path, "");
+ seq_file_path(m, file, "");
}
seq_putc(m, '\n');
diff --git a/fs/proc/self.c b/fs/proc/self.c
index 6195b4a7c..113b8d061 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -1,5 +1,4 @@
#include <linux/sched.h>
-#include <linux/namei.h>
#include <linux/slab.h>
#include <linux/pid_namespace.h>
#include "internal.h"
@@ -19,21 +18,20 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
return readlink_copy(buffer, buflen, tmp);
}
-static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_self_follow_link(struct dentry *dentry, void **cookie)
{
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) {
- /* 11 for max length of signed int in decimal + NULL term */
- name = kmalloc(12, GFP_KERNEL);
- if (!name)
- name = ERR_PTR(-ENOMEM);
- else
- sprintf(name, "%d", tgid);
- }
- nd_set_link(nd, name);
- return NULL;
+ char *name;
+
+ if (!tgid)
+ return ERR_PTR(-ENOENT);
+ /* 11 for max length of signed int in decimal + NULL term */
+ name = kmalloc(12, GFP_KERNEL);
+ if (!name)
+ return ERR_PTR(-ENOMEM);
+ sprintf(name, "%d", tgid);
+ return *cookie = name;
}
static const struct inode_operations proc_self_inode_operations = {
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 9afa35d04..ca1e09188 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -279,10 +279,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
const char *name = NULL;
if (file) {
- struct inode *inode;
-
- file = vma_pr_or_file(vma);
- inode = file_inode(file);
+ struct inode *inode = file_inode(vma->vm_file);
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
@@ -313,7 +310,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
*/
if (file) {
seq_pad(m, ' ');
- seq_path(m, &file->f_path, "\n");
+ seq_file_path(m, file, "\n");
goto done;
}
@@ -1482,7 +1479,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
struct vm_area_struct *vma = v;
struct numa_maps *md = &numa_priv->md;
- struct file *file = vma_pr_or_file(vma);
+ struct file *file = vma->vm_file;
struct mm_struct *mm = vma->vm_mm;
struct mm_walk walk = {
.hugetlb_entry = gather_hugetlb_stats,
@@ -1512,7 +1509,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
if (file) {
seq_puts(m, " file=");
- seq_path(m, &file->f_path, "\n\t= ");
+ seq_file_path(m, file, "\n\t= ");
} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
seq_puts(m, " heap");
} else {
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 174020784..e0d64c92e 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -160,10 +160,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
file = vma->vm_file;
if (file) {
- struct inode *inode;
-
- file = vma_pr_or_file(vma);
- inode = file_inode(file);
+ struct inode *inode = file_inode(vma->vm_file);
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
@@ -183,7 +180,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
if (file) {
seq_pad(m, ' ');
- seq_path(m, &file->f_path, "");
+ seq_file_path(m, file, "");
} else if (mm) {
pid_t tid = pid_of_stack(priv, vma, is_pid);
diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
index a8371993b..947b0f4fd 100644
--- a/fs/proc/thread_self.c
+++ b/fs/proc/thread_self.c
@@ -1,5 +1,4 @@
#include <linux/sched.h>
-#include <linux/namei.h>
#include <linux/slab.h>
#include <linux/pid_namespace.h>
#include "internal.h"
@@ -20,21 +19,20 @@ static int proc_thread_self_readlink(struct dentry *dentry, char __user *buffer,
return readlink_copy(buffer, buflen, tmp);
}
-static void *proc_thread_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_thread_self_follow_link(struct dentry *dentry, void **cookie)
{
struct pid_namespace *ns = dentry->d_sb->s_fs_info;
pid_t tgid = task_tgid_nr_ns(current, ns);
pid_t pid = task_pid_nr_ns(current, ns);
- char *name = ERR_PTR(-ENOENT);
- if (pid) {
- name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL);
- if (!name)
- name = ERR_PTR(-ENOMEM);
- else
- sprintf(name, "%d/task/%d", tgid, pid);
- }
- nd_set_link(nd, name);
- return NULL;
+ char *name;
+
+ if (!pid)
+ return ERR_PTR(-ENOENT);
+ name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL);
+ if (!name)
+ return ERR_PTR(-ENOMEM);
+ sprintf(name, "%d/task/%d", tgid, pid);
+ return *cookie = name;
}
static const struct inode_operations proc_thread_self_inode_operations = {