summaryrefslogtreecommitdiff
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/array.c4
-rw-r--r--fs/proc/base.c189
-rw-r--r--fs/proc/generic.c8
-rw-r--r--fs/proc/inode.c2
-rw-r--r--fs/proc/internal.h1
-rw-r--r--fs/proc/root.c32
-rw-r--r--fs/proc/task_mmu.c138
-rw-r--r--fs/proc/task_nommu.c6
8 files changed, 233 insertions, 147 deletions
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 7c99c1cf7e5c..5e4f776b0917 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -489,8 +489,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
vsize,
mm ? get_mm_rss(mm) : 0,
rsslim,
- mm ? mm->start_code : 0,
- mm ? mm->end_code : 0,
+ mm ? (permitted ? mm->start_code : 1) : 0,
+ mm ? (permitted ? mm->end_code : 1) : 0,
(permitted && mm) ? mm->start_stack : 0,
esp,
eip,
diff --git a/fs/proc/base.c b/fs/proc/base.c
index d49c4b5d2c3e..dfa532730e55 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -191,17 +191,20 @@ static int proc_root_link(struct inode *inode, struct path *path)
return result;
}
-/*
- * Return zero if current may access user memory in @task, -error if not.
- */
-static int check_mem_permission(struct task_struct *task)
+static struct mm_struct *__check_mem_permission(struct task_struct *task)
{
+ struct mm_struct *mm;
+
+ mm = get_task_mm(task);
+ if (!mm)
+ return ERR_PTR(-EINVAL);
+
/*
* A task can always look at itself, in case it chooses
* to use system calls instead of load instructions.
*/
if (task == current)
- return 0;
+ return mm;
/*
* If current is actively ptrace'ing, and would also be
@@ -213,27 +216,53 @@ static int check_mem_permission(struct task_struct *task)
match = (tracehook_tracer_task(task) == current);
rcu_read_unlock();
if (match && ptrace_may_access(task, PTRACE_MODE_ATTACH))
- return 0;
+ return mm;
}
/*
- * Noone else is allowed.
+ * No one else is allowed.
+ */
+ mmput(mm);
+ return ERR_PTR(-EPERM);
+}
+
+/*
+ * If current may access user memory in @task return a reference to the
+ * corresponding mm, otherwise ERR_PTR.
+ */
+static struct mm_struct *check_mem_permission(struct task_struct *task)
+{
+ struct mm_struct *mm;
+ int err;
+
+ /*
+ * Avoid racing if task exec's as we might get a new mm but validate
+ * against old credentials.
*/
- return -EPERM;
+ err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+ if (err)
+ return ERR_PTR(err);
+
+ mm = __check_mem_permission(task);
+ mutex_unlock(&task->signal->cred_guard_mutex);
+
+ return mm;
}
struct mm_struct *mm_for_maps(struct task_struct *task)
{
struct mm_struct *mm;
+ int err;
- if (mutex_lock_killable(&task->signal->cred_guard_mutex))
- return NULL;
+ err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+ if (err)
+ return ERR_PTR(err);
mm = get_task_mm(task);
if (mm && mm != current->mm &&
!ptrace_may_access(task, PTRACE_MODE_READ)) {
mmput(mm);
- mm = NULL;
+ mm = ERR_PTR(-EACCES);
}
mutex_unlock(&task->signal->cred_guard_mutex);
@@ -279,9 +308,9 @@ out:
static int proc_pid_auxv(struct task_struct *task, char *buffer)
{
- int res = 0;
- struct mm_struct *mm = get_task_mm(task);
- if (mm) {
+ struct mm_struct *mm = mm_for_maps(task);
+ int res = PTR_ERR(mm);
+ if (mm && !IS_ERR(mm)) {
unsigned int nwords = 0;
do {
nwords += 2;
@@ -318,6 +347,23 @@ static int proc_pid_wchan(struct task_struct *task, char *buffer)
}
#endif /* CONFIG_KALLSYMS */
+static int lock_trace(struct task_struct *task)
+{
+ int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+ if (err)
+ return err;
+ if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
+ mutex_unlock(&task->signal->cred_guard_mutex);
+ return -EPERM;
+ }
+ return 0;
+}
+
+static void unlock_trace(struct task_struct *task)
+{
+ mutex_unlock(&task->signal->cred_guard_mutex);
+}
+
#ifdef CONFIG_STACKTRACE
#define MAX_STACK_TRACE_DEPTH 64
@@ -327,6 +373,7 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
{
struct stack_trace trace;
unsigned long *entries;
+ int err;
int i;
entries = kmalloc(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL);
@@ -337,15 +384,20 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
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]);
+ err = lock_trace(task);
+ if (!err) {
+ save_stack_trace_tsk(task, &trace);
+
+ for (i = 0; i < trace.nr_entries; i++) {
+ seq_printf(m, "[<%pK>] %pS\n",
+ (void *)entries[i], (void *)entries[i]);
+ }
+ unlock_trace(task);
}
kfree(entries);
- return 0;
+ return err;
}
#endif
@@ -508,18 +560,22 @@ static int proc_pid_syscall(struct task_struct *task, char *buffer)
{
long nr;
unsigned long args[6], sp, pc;
+ int res = lock_trace(task);
+ if (res)
+ return res;
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,
+ res = sprintf(buffer, "running\n");
+ else if (nr < 0)
+ res = sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
+ else
+ res = 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);
+ unlock_trace(task);
+ return res;
}
#endif /* CONFIG_HAVE_ARCH_TRACEHOOK */
@@ -775,18 +831,14 @@ static ssize_t mem_read(struct file * file, char __user * buf,
if (!task)
goto out_no_task;
- if (check_mem_permission(task))
- goto out;
-
ret = -ENOMEM;
page = (char *)__get_free_page(GFP_TEMPORARY);
if (!page)
goto out;
- ret = 0;
-
- mm = get_task_mm(task);
- if (!mm)
+ mm = check_mem_permission(task);
+ ret = PTR_ERR(mm);
+ if (IS_ERR(mm))
goto out_free;
ret = -EIO;
@@ -800,8 +852,8 @@ static ssize_t mem_read(struct file * file, char __user * buf,
int this_len, retval;
this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
- retval = access_process_vm(task, src, page, this_len, 0);
- if (!retval || check_mem_permission(task)) {
+ retval = access_remote_vm(mm, src, page, this_len, 0);
+ if (!retval) {
if (!ret)
ret = -EIO;
break;
@@ -829,10 +881,6 @@ out_no_task:
return ret;
}
-#define mem_write NULL
-
-#ifndef mem_write
-/* This is a security hazard */
static ssize_t mem_write(struct file * file, const char __user *buf,
size_t count, loff_t *ppos)
{
@@ -840,18 +888,25 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
char *page;
struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
unsigned long dst = *ppos;
+ struct mm_struct *mm;
copied = -ESRCH;
if (!task)
goto out_no_task;
- if (check_mem_permission(task))
- goto out;
+ mm = check_mem_permission(task);
+ copied = PTR_ERR(mm);
+ if (IS_ERR(mm))
+ goto out_task;
+
+ copied = -EIO;
+ if (file->private_data != (void *)((long)current->self_exec_id))
+ goto out_mm;
copied = -ENOMEM;
page = (char *)__get_free_page(GFP_TEMPORARY);
if (!page)
- goto out;
+ goto out_mm;
copied = 0;
while (count > 0) {
@@ -862,7 +917,7 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
copied = -EFAULT;
break;
}
- retval = access_process_vm(task, dst, page, this_len, 1);
+ retval = access_remote_vm(mm, dst, page, this_len, 1);
if (!retval) {
if (!copied)
copied = -EIO;
@@ -875,12 +930,13 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
}
*ppos = dst;
free_page((unsigned long) page);
-out:
+out_mm:
+ mmput(mm);
+out_task:
put_task_struct(task);
out_no_task:
return copied;
}
-#endif
loff_t mem_lseek(struct file *file, loff_t offset, int orig)
{
@@ -917,20 +973,18 @@ static ssize_t environ_read(struct file *file, char __user *buf,
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)
+ mm = mm_for_maps(task);
+ ret = PTR_ERR(mm);
+ if (!mm || IS_ERR(mm))
goto out_free;
+ ret = 0;
while (count > 0) {
int this_len, retval, max_len;
@@ -2748,8 +2802,12 @@ static int proc_tgid_io_accounting(struct task_struct *task, char *buffer)
static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
- seq_printf(m, "%08x\n", task->personality);
- return 0;
+ int err = lock_trace(task);
+ if (!err) {
+ seq_printf(m, "%08x\n", task->personality);
+ unlock_trace(task);
+ }
+ return err;
}
/*
@@ -2768,7 +2826,7 @@ static const struct pid_entry tgid_base_stuff[] = {
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),
+ ONE("personality", S_IRUGO, proc_pid_personality),
INF("limits", S_IRUGO, proc_pid_limits),
#ifdef CONFIG_SCHED_DEBUG
REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations),
@@ -2778,7 +2836,7 @@ static const struct pid_entry tgid_base_stuff[] = {
#endif
REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
- INF("syscall", S_IRUSR, proc_pid_syscall),
+ INF("syscall", S_IRUGO, proc_pid_syscall),
#endif
INF("cmdline", S_IRUGO, proc_pid_cmdline),
ONE("stat", S_IRUGO, proc_tgid_stat),
@@ -2797,7 +2855,7 @@ static const struct pid_entry tgid_base_stuff[] = {
#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),
+ REG("pagemap", S_IRUGO, proc_pagemap_operations),
#endif
#ifdef CONFIG_SECURITY
DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
@@ -2806,7 +2864,7 @@ static const struct pid_entry tgid_base_stuff[] = {
INF("wchan", S_IRUGO, proc_pid_wchan),
#endif
#ifdef CONFIG_STACKTRACE
- ONE("stack", S_IRUSR, proc_pid_stack),
+ ONE("stack", S_IRUGO, proc_pid_stack),
#endif
#ifdef CONFIG_SCHEDSTATS
INF("schedstat", S_IRUGO, proc_pid_schedstat),
@@ -3066,11 +3124,16 @@ static int proc_pid_fill_cache(struct file *filp, void *dirent, filldir_t filldi
/* for the /proc/ directory itself, after non-process stuff has been done */
int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
- unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY;
- struct task_struct *reaper = get_proc_task(filp->f_path.dentry->d_inode);
+ unsigned int nr;
+ struct task_struct *reaper;
struct tgid_iter iter;
struct pid_namespace *ns;
+ if (filp->f_pos >= PID_MAX_LIMIT + TGID_OFFSET)
+ goto out_no_task;
+ nr = filp->f_pos - FIRST_PROCESS_ENTRY;
+
+ reaper = get_proc_task(filp->f_path.dentry->d_inode);
if (!reaper)
goto out_no_task;
@@ -3108,14 +3171,14 @@ static const struct pid_entry tid_base_stuff[] = {
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),
+ ONE("personality", S_IRUGO, proc_pid_personality),
INF("limits", S_IRUGO, 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),
+ INF("syscall", S_IRUGO, proc_pid_syscall),
#endif
INF("cmdline", S_IRUGO, proc_pid_cmdline),
ONE("stat", S_IRUGO, proc_tid_stat),
@@ -3133,7 +3196,7 @@ static const struct pid_entry tid_base_stuff[] = {
#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),
+ REG("pagemap", S_IRUGO, proc_pagemap_operations),
#endif
#ifdef CONFIG_SECURITY
DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
@@ -3142,7 +3205,7 @@ static const struct pid_entry tid_base_stuff[] = {
INF("wchan", S_IRUGO, proc_pid_wchan),
#endif
#ifdef CONFIG_STACKTRACE
- ONE("stack", S_IRUSR, proc_pid_stack),
+ ONE("stack", S_IRUGO, proc_pid_stack),
#endif
#ifdef CONFIG_SCHEDSTATS
INF("schedstat", S_IRUGO, proc_pid_schedstat),
@@ -3161,7 +3224,7 @@ static const struct pid_entry tid_base_stuff[] = {
REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
#ifdef CONFIG_AUDITSYSCALL
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
- REG("sessionid", S_IRUSR, proc_sessionid_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),
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 01e07f2a188f..f1281339b6fa 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -28,7 +28,7 @@
DEFINE_SPINLOCK(proc_subdir_lock);
-static int proc_match(int len, const char *name, struct proc_dir_entry *de)
+static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de)
{
if (de->namelen != len)
return 0;
@@ -303,7 +303,7 @@ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
{
const char *cp = name, *next;
struct proc_dir_entry *de;
- int len;
+ unsigned int len;
de = *ret;
if (!de)
@@ -602,7 +602,7 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
{
struct proc_dir_entry *ent = NULL;
const char *fn = name;
- int len;
+ unsigned int len;
/* make sure name is valid */
if (!name || !strlen(name)) goto out;
@@ -786,7 +786,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
struct proc_dir_entry **p;
struct proc_dir_entry *de = NULL;
const char *fn = name;
- int len;
+ unsigned int len;
spin_lock(&proc_subdir_lock);
if (__xlate_proc_name(name, &parent, &fn) != 0) {
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index d6a7ca1fdac5..d15aa1b1cc8f 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -46,8 +46,6 @@ static void proc_evict_inode(struct inode *inode)
}
}
-struct vfsmount *proc_mnt;
-
static struct kmem_cache * proc_inode_cachep;
static struct inode *proc_alloc_inode(struct super_block *sb)
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 9ad561ded409..c03e8d3a3a5b 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -107,7 +107,6 @@ static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde)
}
void pde_put(struct proc_dir_entry *pde);
-extern struct vfsmount *proc_mnt;
int proc_fill_super(struct super_block *);
struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
diff --git a/fs/proc/root.c b/fs/proc/root.c
index ef9fa8e24ad6..a9000e9cfee5 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -43,17 +43,6 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
struct pid_namespace *ns;
struct proc_inode *ei;
- if (proc_mnt) {
- /* Seed the root directory with a pid so it doesn't need
- * to be special in base.c. I would do this earlier but
- * the only task alive when /proc is mounted the first time
- * is the init_task and it doesn't have any pids.
- */
- ei = PROC_I(proc_mnt->mnt_sb->s_root->d_inode);
- if (!ei->pid)
- ei->pid = find_get_pid(1);
- }
-
if (flags & MS_KERNMOUNT)
ns = (struct pid_namespace *)data;
else
@@ -71,16 +60,16 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
return ERR_PTR(err);
}
- ei = PROC_I(sb->s_root->d_inode);
- if (!ei->pid) {
- rcu_read_lock();
- ei->pid = get_pid(find_pid_ns(1, ns));
- rcu_read_unlock();
- }
-
sb->s_flags |= MS_ACTIVE;
}
+ ei = PROC_I(sb->s_root->d_inode);
+ if (!ei->pid) {
+ rcu_read_lock();
+ ei->pid = get_pid(find_pid_ns(1, ns));
+ rcu_read_unlock();
+ }
+
return dget(sb->s_root);
}
@@ -101,19 +90,20 @@ static struct file_system_type proc_fs_type = {
void __init proc_root_init(void)
{
+ struct vfsmount *mnt;
int err;
proc_init_inodecache();
err = register_filesystem(&proc_fs_type);
if (err)
return;
- proc_mnt = kern_mount_data(&proc_fs_type, &init_pid_ns);
- if (IS_ERR(proc_mnt)) {
+ mnt = kern_mount_data(&proc_fs_type, &init_pid_ns);
+ if (IS_ERR(mnt)) {
unregister_filesystem(&proc_fs_type);
return;
}
- init_pid_ns.proc_mnt = proc_mnt;
+ init_pid_ns.proc_mnt = mnt;
proc_symlink("mounts", NULL, "self/mounts");
proc_net_init();
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 60b914860f81..2e7addfd9803 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1,5 +1,6 @@
#include <linux/mm.h>
#include <linux/hugetlb.h>
+#include <linux/huge_mm.h>
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/highmem.h>
@@ -7,6 +8,7 @@
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
+#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
@@ -119,14 +121,14 @@ static void *m_start(struct seq_file *m, loff_t *pos)
priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
if (!priv->task)
- return NULL;
+ return ERR_PTR(-ESRCH);
mm = mm_for_maps(priv->task);
- if (!mm)
- return NULL;
+ if (!mm || IS_ERR(mm))
+ return mm;
down_read(&mm->mmap_sem);
- tail_vma = get_gate_vma(priv->task);
+ tail_vma = get_gate_vma(priv->task->mm);
priv->tail_vma = tail_vma;
/* Start with last addr hint */
@@ -180,7 +182,8 @@ static void m_stop(struct seq_file *m, void *v)
struct proc_maps_private *priv = m->private;
struct vm_area_struct *vma = v;
- vma_stop(priv, vma);
+ if (!IS_ERR(vma))
+ vma_stop(priv, vma);
if (priv->task)
put_task_struct(priv->task);
}
@@ -249,8 +252,8 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
const char *name = arch_vma_name(vma);
if (!name) {
if (mm) {
- if (vma->vm_start <= mm->start_brk &&
- vma->vm_end >= mm->brk) {
+ if (vma->vm_start <= mm->brk &&
+ vma->vm_end >= mm->start_brk) {
name = "[heap]";
} else if (vma->vm_start <= mm->start_stack &&
vma->vm_end >= mm->start_stack) {
@@ -277,7 +280,8 @@ static int show_map(struct seq_file *m, void *v)
show_map_vma(m, vma);
if (m->count < m->size) /* vma is copied successfully */
- m->version = (vma != get_gate_vma(task))? vma->vm_start: 0;
+ m->version = (vma != get_gate_vma(task->mm))
+ ? vma->vm_start : 0;
return 0;
}
@@ -329,58 +333,86 @@ struct mem_size_stats {
unsigned long private_dirty;
unsigned long referenced;
unsigned long anonymous;
+ unsigned long anonymous_thp;
unsigned long swap;
u64 pss;
};
-static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
- struct mm_walk *walk)
+
+static void smaps_pte_entry(pte_t ptent, unsigned long addr,
+ unsigned long ptent_size, struct mm_walk *walk)
{
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = mss->vma;
- pte_t *pte, ptent;
- spinlock_t *ptl;
struct page *page;
int mapcount;
- pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
- for (; addr != end; pte++, addr += PAGE_SIZE) {
- ptent = *pte;
-
- if (is_swap_pte(ptent)) {
- mss->swap += PAGE_SIZE;
- continue;
- }
+ if (is_swap_pte(ptent)) {
+ mss->swap += ptent_size;
+ return;
+ }
- if (!pte_present(ptent))
- continue;
+ if (!pte_present(ptent))
+ return;
+
+ page = vm_normal_page(vma, addr, ptent);
+ if (!page)
+ return;
+
+ if (PageAnon(page))
+ mss->anonymous += ptent_size;
+
+ mss->resident += ptent_size;
+ /* Accumulate the size in pages that have been accessed. */
+ if (pte_young(ptent) || PageReferenced(page))
+ mss->referenced += ptent_size;
+ mapcount = page_mapcount(page);
+ if (mapcount >= 2) {
+ if (pte_dirty(ptent) || PageDirty(page))
+ mss->shared_dirty += ptent_size;
+ else
+ mss->shared_clean += ptent_size;
+ mss->pss += (ptent_size << PSS_SHIFT) / mapcount;
+ } else {
+ if (pte_dirty(ptent) || PageDirty(page))
+ mss->private_dirty += ptent_size;
+ else
+ mss->private_clean += ptent_size;
+ mss->pss += (ptent_size << PSS_SHIFT);
+ }
+}
- page = vm_normal_page(vma, addr, ptent);
- if (!page)
- continue;
+static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ struct mem_size_stats *mss = walk->private;
+ struct vm_area_struct *vma = mss->vma;
+ pte_t *pte;
+ spinlock_t *ptl;
- if (PageAnon(page))
- mss->anonymous += PAGE_SIZE;
-
- mss->resident += PAGE_SIZE;
- /* Accumulate the size in pages that have been accessed. */
- if (pte_young(ptent) || PageReferenced(page))
- mss->referenced += PAGE_SIZE;
- mapcount = page_mapcount(page);
- if (mapcount >= 2) {
- if (pte_dirty(ptent) || PageDirty(page))
- mss->shared_dirty += PAGE_SIZE;
- else
- mss->shared_clean += PAGE_SIZE;
- mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
+ spin_lock(&walk->mm->page_table_lock);
+ if (pmd_trans_huge(*pmd)) {
+ if (pmd_trans_splitting(*pmd)) {
+ spin_unlock(&walk->mm->page_table_lock);
+ wait_split_huge_page(vma->anon_vma, pmd);
} else {
- if (pte_dirty(ptent) || PageDirty(page))
- mss->private_dirty += PAGE_SIZE;
- else
- mss->private_clean += PAGE_SIZE;
- mss->pss += (PAGE_SIZE << PSS_SHIFT);
+ smaps_pte_entry(*(pte_t *)pmd, addr,
+ HPAGE_PMD_SIZE, walk);
+ spin_unlock(&walk->mm->page_table_lock);
+ mss->anonymous_thp += HPAGE_PMD_SIZE;
+ return 0;
}
+ } else {
+ spin_unlock(&walk->mm->page_table_lock);
}
+ /*
+ * The mmap_sem held all the way back in m_start() is what
+ * keeps khugepaged out of here and from collapsing things
+ * in here.
+ */
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ for (; addr != end; pte++, addr += PAGE_SIZE)
+ smaps_pte_entry(*pte, addr, PAGE_SIZE, walk);
pte_unmap_unlock(pte - 1, ptl);
cond_resched();
return 0;
@@ -416,6 +448,7 @@ static int show_smap(struct seq_file *m, void *v)
"Private_Dirty: %8lu kB\n"
"Referenced: %8lu kB\n"
"Anonymous: %8lu kB\n"
+ "AnonHugePages: %8lu kB\n"
"Swap: %8lu kB\n"
"KernelPageSize: %8lu kB\n"
"MMUPageSize: %8lu kB\n"
@@ -429,6 +462,7 @@ static int show_smap(struct seq_file *m, void *v)
mss.private_dirty >> 10,
mss.referenced >> 10,
mss.anonymous >> 10,
+ mss.anonymous_thp >> 10,
mss.swap >> 10,
vma_kernel_pagesize(vma) >> 10,
vma_mmu_pagesize(vma) >> 10,
@@ -436,7 +470,8 @@ static int show_smap(struct seq_file *m, void *v)
(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
if (m->count < m->size) /* vma is copied successfully */
- m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
+ m->version = (vma != get_gate_vma(task->mm))
+ ? vma->vm_start : 0;
return 0;
}
@@ -467,6 +502,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
spinlock_t *ptl;
struct page *page;
+ split_huge_page_pmd(walk->mm, pmd);
+
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = *pte;
@@ -623,6 +660,8 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
pte_t *pte;
int err = 0;
+ split_huge_page_pmd(walk->mm, pmd);
+
/* find the first VMA at or above 'addr' */
vma = find_vma(walk->mm, addr);
for (; addr != end; addr += PAGE_SIZE) {
@@ -728,8 +767,9 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
if (!task)
goto out;
- ret = -EACCES;
- if (!ptrace_may_access(task, PTRACE_MODE_READ))
+ mm = mm_for_maps(task);
+ ret = PTR_ERR(mm);
+ if (!mm || IS_ERR(mm))
goto out_task;
ret = -EINVAL;
@@ -742,10 +782,6 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
if (!count)
goto out_task;
- mm = get_task_mm(task);
- if (!mm)
- goto out_task;
-
pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
ret = -ENOMEM;
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index b535d3e5d5f1..980de547c070 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -199,13 +199,13 @@ static void *m_start(struct seq_file *m, loff_t *pos)
/* pin the task and mm whilst we play with them */
priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
if (!priv->task)
- return NULL;
+ return ERR_PTR(-ESRCH);
mm = mm_for_maps(priv->task);
- if (!mm) {
+ if (!mm || IS_ERR(mm)) {
put_task_struct(priv->task);
priv->task = NULL;
- return NULL;
+ return mm;
}
down_read(&mm->mmap_sem);
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-15 03:02:03 +0300