summaryrefslogtreecommitdiffstats
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/array.c47
-rw-r--r--fs/proc/base.c92
-rw-r--r--fs/proc/fd.c5
-rw-r--r--fs/proc/generic.c163
-rw-r--r--fs/proc/internal.h16
-rw-r--r--fs/proc/kcore.c4
-rw-r--r--fs/proc/page.c3
-rw-r--r--fs/proc/proc_net.c1
-rw-r--r--fs/proc/root.c1
-rw-r--r--fs/proc/task_mmu.c458
-rw-r--r--fs/proc/task_nommu.c88
11 files changed, 493 insertions, 385 deletions
diff --git a/fs/proc/array.c b/fs/proc/array.c
index cd3653e4f35c..bd117d065b82 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -157,20 +157,29 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
struct user_namespace *user_ns = seq_user_ns(m);
struct group_info *group_info;
int g;
- struct fdtable *fdt = NULL;
+ struct task_struct *tracer;
const struct cred *cred;
- pid_t ppid, tpid;
+ pid_t ppid, tpid = 0, tgid, ngid;
+ unsigned int max_fds = 0;
rcu_read_lock();
ppid = pid_alive(p) ?
task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
- tpid = 0;
- if (pid_alive(p)) {
- struct task_struct *tracer = ptrace_parent(p);
- if (tracer)
- tpid = task_pid_nr_ns(tracer, ns);
- }
+
+ tracer = ptrace_parent(p);
+ if (tracer)
+ tpid = task_pid_nr_ns(tracer, ns);
+
+ tgid = task_tgid_nr_ns(p, ns);
+ ngid = task_numa_group_id(p);
cred = get_task_cred(p);
+
+ task_lock(p);
+ if (p->files)
+ max_fds = files_fdtable(p->files)->max_fds;
+ task_unlock(p);
+ rcu_read_unlock();
+
seq_printf(m,
"State:\t%s\n"
"Tgid:\t%d\n"
@@ -179,12 +188,10 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
"PPid:\t%d\n"
"TracerPid:\t%d\n"
"Uid:\t%d\t%d\t%d\t%d\n"
- "Gid:\t%d\t%d\t%d\t%d\n",
+ "Gid:\t%d\t%d\t%d\t%d\n"
+ "FDSize:\t%d\nGroups:\t",
get_task_state(p),
- task_tgid_nr_ns(p, ns),
- task_numa_group_id(p),
- pid_nr_ns(pid, ns),
- ppid, tpid,
+ tgid, ngid, pid_nr_ns(pid, ns), ppid, tpid,
from_kuid_munged(user_ns, cred->uid),
from_kuid_munged(user_ns, cred->euid),
from_kuid_munged(user_ns, cred->suid),
@@ -192,20 +199,10 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
from_kgid_munged(user_ns, cred->gid),
from_kgid_munged(user_ns, cred->egid),
from_kgid_munged(user_ns, cred->sgid),
- from_kgid_munged(user_ns, cred->fsgid));
-
- task_lock(p);
- if (p->files)
- fdt = files_fdtable(p->files);
- seq_printf(m,
- "FDSize:\t%d\n"
- "Groups:\t",
- fdt ? fdt->max_fds : 0);
- rcu_read_unlock();
+ from_kgid_munged(user_ns, cred->fsgid),
+ max_fds);
group_info = cred->group_info;
- task_unlock(p);
-
for (g = 0; g < group_info->ngroups; g++)
seq_printf(m, "%d ",
from_kgid_munged(user_ns, GROUP_AT(group_info, g)));
diff --git a/fs/proc/base.c b/fs/proc/base.c
index baf852b648ad..590aeda5af12 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -376,37 +376,6 @@ static const struct file_operations proc_lstats_operations = {
#endif
-#ifdef CONFIG_CGROUPS
-static int cgroup_open(struct inode *inode, struct file *file)
-{
- struct pid *pid = PROC_I(inode)->pid;
- return single_open(file, proc_cgroup_show, pid);
-}
-
-static const struct file_operations proc_cgroup_operations = {
- .open = cgroup_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-#endif
-
-#ifdef CONFIG_PROC_PID_CPUSET
-
-static int cpuset_open(struct inode *inode, struct file *file)
-{
- struct pid *pid = PROC_I(inode)->pid;
- return single_open(file, proc_cpuset_show, pid);
-}
-
-static const struct file_operations proc_cpuset_operations = {
- .open = cpuset_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-#endif
-
static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
@@ -632,29 +601,35 @@ static const struct file_operations proc_single_file_operations = {
.release = single_release,
};
-static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
+
+struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode)
{
- struct task_struct *task = get_proc_task(file_inode(file));
- struct mm_struct *mm;
+ struct task_struct *task = get_proc_task(inode);
+ struct mm_struct *mm = ERR_PTR(-ESRCH);
- if (!task)
- return -ESRCH;
+ if (task) {
+ mm = mm_access(task, mode);
+ put_task_struct(task);
- mm = mm_access(task, mode);
- put_task_struct(task);
+ if (!IS_ERR_OR_NULL(mm)) {
+ /* ensure this mm_struct can't be freed */
+ atomic_inc(&mm->mm_count);
+ /* but do not pin its memory */
+ mmput(mm);
+ }
+ }
+
+ return mm;
+}
+
+static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
+{
+ struct mm_struct *mm = proc_mem_open(inode, mode);
if (IS_ERR(mm))
return PTR_ERR(mm);
- if (mm) {
- /* ensure this mm_struct can't be freed */
- atomic_inc(&mm->mm_count);
- /* but do not pin its memory */
- mmput(mm);
- }
-
file->private_data = mm;
-
return 0;
}
@@ -1590,7 +1565,6 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags)
put_task_struct(task);
return 1;
}
- d_drop(dentry);
return 0;
}
@@ -1727,9 +1701,6 @@ out:
put_task_struct(task);
out_notask:
- if (status <= 0)
- d_drop(dentry);
-
return status;
}
@@ -2573,10 +2544,10 @@ static const struct pid_entry tgid_base_stuff[] = {
REG("latency", S_IRUGO, proc_lstats_operations),
#endif
#ifdef CONFIG_PROC_PID_CPUSET
- REG("cpuset", S_IRUGO, proc_cpuset_operations),
+ ONE("cpuset", S_IRUGO, proc_cpuset_show),
#endif
#ifdef CONFIG_CGROUPS
- REG("cgroup", S_IRUGO, proc_cgroup_operations),
+ ONE("cgroup", S_IRUGO, proc_cgroup_show),
#endif
ONE("oom_score", S_IRUGO, proc_oom_score),
REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations),
@@ -2643,11 +2614,13 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
/* no ->d_hash() rejects on procfs */
dentry = d_hash_and_lookup(mnt->mnt_root, &name);
if (dentry) {
- shrink_dcache_parent(dentry);
- d_drop(dentry);
+ d_invalidate(dentry);
dput(dentry);
}
+ if (pid == tgid)
+ return;
+
name.name = buf;
name.len = snprintf(buf, sizeof(buf), "%d", tgid);
leader = d_hash_and_lookup(mnt->mnt_root, &name);
@@ -2664,8 +2637,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
name.len = snprintf(buf, sizeof(buf), "%d", pid);
dentry = d_hash_and_lookup(dir, &name);
if (dentry) {
- shrink_dcache_parent(dentry);
- d_drop(dentry);
+ d_invalidate(dentry);
dput(dentry);
}
@@ -2820,7 +2792,7 @@ retry:
int proc_pid_readdir(struct file *file, struct dir_context *ctx)
{
struct tgid_iter iter;
- struct pid_namespace *ns = file->f_dentry->d_sb->s_fs_info;
+ struct pid_namespace *ns = file_inode(file)->i_sb->s_fs_info;
loff_t pos = ctx->pos;
if (pos >= PID_MAX_LIMIT + TGID_OFFSET)
@@ -2919,10 +2891,10 @@ static const struct pid_entry tid_base_stuff[] = {
REG("latency", S_IRUGO, proc_lstats_operations),
#endif
#ifdef CONFIG_PROC_PID_CPUSET
- REG("cpuset", S_IRUGO, proc_cpuset_operations),
+ ONE("cpuset", S_IRUGO, proc_cpuset_show),
#endif
#ifdef CONFIG_CGROUPS
- REG("cgroup", S_IRUGO, proc_cgroup_operations),
+ ONE("cgroup", S_IRUGO, proc_cgroup_show),
#endif
ONE("oom_score", S_IRUGO, proc_oom_score),
REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations),
@@ -3126,7 +3098,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx)
/* f_version caches the tgid value that the last readdir call couldn't
* return. lseek aka telldir automagically resets f_version to 0.
*/
- ns = file->f_dentry->d_sb->s_fs_info;
+ ns = inode->i_sb->s_fs_info;
tid = (int)file->f_version;
file->f_version = 0;
for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns);
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 955bb55fab8c..8e5ad83b629a 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -53,7 +53,8 @@ static int seq_show(struct seq_file *m, void *v)
(long long)file->f_pos, f_flags,
real_mount(file->f_path.mnt)->mnt_id);
if (file->f_op->show_fdinfo)
- ret = file->f_op->show_fdinfo(m, file);
+ file->f_op->show_fdinfo(m, file);
+ ret = seq_has_overflowed(m);
fput(file);
}
@@ -129,8 +130,6 @@ static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
}
put_task_struct(task);
}
-
- d_drop(dentry);
return 0;
}
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 317b72641ebf..7fea13229f33 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -31,9 +31,73 @@ static DEFINE_SPINLOCK(proc_subdir_lock);
static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de)
{
- if (de->namelen != len)
- return 0;
- return !memcmp(name, de->name, len);
+ if (len < de->namelen)
+ return -1;
+ if (len > de->namelen)
+ return 1;
+
+ return memcmp(name, de->name, len);
+}
+
+static struct proc_dir_entry *pde_subdir_first(struct proc_dir_entry *dir)
+{
+ return rb_entry_safe(rb_first(&dir->subdir), struct proc_dir_entry,
+ subdir_node);
+}
+
+static struct proc_dir_entry *pde_subdir_next(struct proc_dir_entry *dir)
+{
+ return rb_entry_safe(rb_next(&dir->subdir_node), struct proc_dir_entry,
+ subdir_node);
+}
+
+static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir,
+ const char *name,
+ unsigned int len)
+{
+ struct rb_node *node = dir->subdir.rb_node;
+
+ while (node) {
+ struct proc_dir_entry *de = container_of(node,
+ struct proc_dir_entry,
+ subdir_node);
+ int result = proc_match(len, name, de);
+
+ if (result < 0)
+ node = node->rb_left;
+ else if (result > 0)
+ node = node->rb_right;
+ else
+ return de;
+ }
+ return NULL;
+}
+
+static bool pde_subdir_insert(struct proc_dir_entry *dir,
+ struct proc_dir_entry *de)
+{
+ struct rb_root *root = &dir->subdir;
+ struct rb_node **new = &root->rb_node, *parent = NULL;
+
+ /* Figure out where to put new node */
+ while (*new) {
+ struct proc_dir_entry *this =
+ container_of(*new, struct proc_dir_entry, subdir_node);
+ int result = proc_match(de->namelen, de->name, this);
+
+ parent = *new;
+ if (result < 0)
+ new = &(*new)->rb_left;
+ else if (result > 0)
+ new = &(*new)->rb_right;
+ else
+ return false;
+ }
+
+ /* Add new node and rebalance tree. */
+ rb_link_node(&de->subdir_node, parent, new);
+ rb_insert_color(&de->subdir_node, root);
+ return true;
}
static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
@@ -92,10 +156,7 @@ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
break;
len = next - cp;
- for (de = de->subdir; de ; de = de->next) {
- if (proc_match(len, cp, de))
- break;
- }
+ de = pde_subdir_find(de, cp, len);
if (!de) {
WARN(1, "name '%s'\n", name);
return -ENOENT;
@@ -183,19 +244,16 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
struct inode *inode;
spin_lock(&proc_subdir_lock);
- for (de = de->subdir; de ; de = de->next) {
- if (de->namelen != dentry->d_name.len)
- continue;
- if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
- pde_get(de);
- spin_unlock(&proc_subdir_lock);
- inode = proc_get_inode(dir->i_sb, de);
- if (!inode)
- return ERR_PTR(-ENOMEM);
- d_set_d_op(dentry, &simple_dentry_operations);
- d_add(dentry, inode);
- return NULL;
- }
+ de = pde_subdir_find(de, dentry->d_name.name, dentry->d_name.len);
+ if (de) {
+ pde_get(de);
+ spin_unlock(&proc_subdir_lock);
+ inode = proc_get_inode(dir->i_sb, de);
+ if (!inode)
+ return ERR_PTR(-ENOMEM);
+ d_set_d_op(dentry, &simple_dentry_operations);
+ d_add(dentry, inode);
+ return NULL;
}
spin_unlock(&proc_subdir_lock);
return ERR_PTR(-ENOENT);
@@ -225,7 +283,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
return 0;
spin_lock(&proc_subdir_lock);
- de = de->subdir;
+ de = pde_subdir_first(de);
i = ctx->pos - 2;
for (;;) {
if (!de) {
@@ -234,7 +292,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
}
if (!i)
break;
- de = de->next;
+ de = pde_subdir_next(de);
i--;
}
@@ -249,7 +307,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
}
spin_lock(&proc_subdir_lock);
ctx->pos++;
- next = de->next;
+ next = pde_subdir_next(de);
pde_put(de);
de = next;
} while (de);
@@ -286,9 +344,8 @@ static const struct inode_operations proc_dir_inode_operations = {
static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp)
{
- struct proc_dir_entry *tmp;
int ret;
-
+
ret = proc_alloc_inum(&dp->low_ino);
if (ret)
return ret;
@@ -304,21 +361,21 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
dp->proc_iops = &proc_file_inode_operations;
} else {
WARN_ON(1);
+ proc_free_inum(dp->low_ino);
return -EINVAL;
}
spin_lock(&proc_subdir_lock);
-
- for (tmp = dir->subdir; tmp; tmp = tmp->next)
- if (strcmp(tmp->name, dp->name) == 0) {
- WARN(1, "proc_dir_entry '%s/%s' already registered\n",
- dir->name, dp->name);
- break;
- }
-
- dp->next = dir->subdir;
dp->parent = dir;
- dir->subdir = dp;
+ if (pde_subdir_insert(dir, dp) == false) {
+ WARN(1, "proc_dir_entry '%s/%s' already registered\n",
+ dir->name, dp->name);
+ spin_unlock(&proc_subdir_lock);
+ if (S_ISDIR(dp->mode))
+ dir->nlink--;
+ proc_free_inum(dp->low_ino);
+ return -EEXIST;
+ }
spin_unlock(&proc_subdir_lock);
return 0;
@@ -354,6 +411,7 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
ent->namelen = qstr.len;
ent->mode = mode;
ent->nlink = nlink;
+ ent->subdir = RB_ROOT;
atomic_set(&ent->count, 1);
spin_lock_init(&ent->pde_unload_lock);
INIT_LIST_HEAD(&ent->pde_openers);
@@ -485,7 +543,6 @@ void pde_put(struct proc_dir_entry *pde)
*/
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;
unsigned int len;
@@ -497,14 +554,9 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
}
len = strlen(fn);
- for (p = &parent->subdir; *p; p=&(*p)->next ) {
- if (proc_match(len, fn, *p)) {
- de = *p;
- *p = de->next;
- de->next = NULL;
- break;
- }
- }
+ de = pde_subdir_find(parent, fn, len);
+ if (de)
+ rb_erase(&de->subdir_node, &parent->subdir);
spin_unlock(&proc_subdir_lock);
if (!de) {
WARN(1, "name '%s'\n", name);
@@ -516,16 +568,15 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
if (S_ISDIR(de->mode))
parent->nlink--;
de->nlink = 0;
- WARN(de->subdir, "%s: removing non-empty directory "
- "'%s/%s', leaking at least '%s'\n", __func__,
- de->parent->name, de->name, de->subdir->name);
+ WARN(pde_subdir_first(de),
+ "%s: removing non-empty directory '%s/%s', leaking at least '%s'\n",
+ __func__, de->parent->name, de->name, pde_subdir_first(de)->name);
pde_put(de);
}
EXPORT_SYMBOL(remove_proc_entry);
int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
{
- struct proc_dir_entry **p;
struct proc_dir_entry *root = NULL, *de, *next;
const char *fn = name;
unsigned int len;
@@ -537,24 +588,18 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
}
len = strlen(fn);
- for (p = &parent->subdir; *p; p=&(*p)->next ) {
- if (proc_match(len, fn, *p)) {
- root = *p;
- *p = root->next;
- root->next = NULL;
- break;
- }
- }
+ root = pde_subdir_find(parent, fn, len);
if (!root) {
spin_unlock(&proc_subdir_lock);
return -ENOENT;
}
+ rb_erase(&root->subdir_node, &parent->subdir);
+
de = root;
while (1) {
- next = de->subdir;
+ next = pde_subdir_first(de);
if (next) {
- de->subdir = next->next;
- next->next = NULL;
+ rb_erase(&next->subdir_node, &de->subdir);
de = next;
continue;
}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 7da13e49128a..7fb1a4869fd0 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -24,10 +24,9 @@ struct mempolicy;
* tree) of these proc_dir_entries, so that we can dynamically
* add new files to /proc.
*
- * The "next" pointer creates a linked list of one /proc directory,
- * while parent/subdir create the directory structure (every
- * /proc file has a parent, but "subdir" is NULL for all
- * non-directory entries).
+ * parent/subdir are used for the directory structure (every /proc file has a
+ * parent, but "subdir" is empty for all non-directory entries).
+ * subdir_node is used to build the rb tree "subdir" of the parent.
*/
struct proc_dir_entry {
unsigned int low_ino;
@@ -38,7 +37,9 @@ struct proc_dir_entry {
loff_t size;
const struct inode_operations *proc_iops;
const struct file_operations *proc_fops;
- struct proc_dir_entry *next, *parent, *subdir;
+ struct proc_dir_entry *parent;
+ struct rb_root subdir;
+ struct rb_node subdir_node;
void *data;
atomic_t count; /* use count */
atomic_t in_use; /* number of callers into module in progress; */
@@ -268,8 +269,9 @@ extern int proc_remount(struct super_block *, int *, char *);
* task_[no]mmu.c
*/
struct proc_maps_private {
- struct pid *pid;
+ struct inode *inode;
struct task_struct *task;
+ struct mm_struct *mm;
#ifdef CONFIG_MMU
struct vm_area_struct *tail_vma;
#endif
@@ -278,6 +280,8 @@ struct proc_maps_private {
#endif
};
+struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode);
+
extern const struct file_operations proc_pid_maps_operations;
extern const struct file_operations proc_tid_maps_operations;
extern const struct file_operations proc_pid_numa_maps_operations;
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 6df8d0722c97..91a4e6426321 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -610,8 +610,10 @@ static void __init proc_kcore_text_init(void)
struct kcore_list kcore_modules;
static void __init add_modules_range(void)
{
- kclist_add(&kcore_modules, (void *)MODULES_VADDR,
+ if (MODULES_VADDR != VMALLOC_START && MODULES_END != VMALLOC_END) {
+ kclist_add(&kcore_modules, (void *)MODULES_VADDR,
MODULES_END - MODULES_VADDR, KCORE_VMALLOC);
+ }
}
#else
static void __init add_modules_range(void)
diff --git a/fs/proc/page.c b/fs/proc/page.c
index e647c55275d9..1e3187da1fed 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -133,6 +133,9 @@ u64 stable_page_flags(struct page *page)
if (PageBuddy(page))
u |= 1 << KPF_BUDDY;
+ if (PageBalloon(page))
+ u |= 1 << KPF_BALLOON;
+
u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked);
u |= kpf_copy_bit(k, KPF_SLAB, PG_slab);
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index a63af3e0a612..1bde894bc624 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -192,6 +192,7 @@ static __net_init int proc_net_ns_init(struct net *net)
if (!netd)
goto out;
+ netd->subdir = RB_ROOT;
netd->data = net;
netd->nlink = 2;
netd->namelen = 3;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 094e44d4a6be..e74ac9f1a2c0 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -251,6 +251,7 @@ struct proc_dir_entry proc_root = {
.proc_iops = &proc_root_inode_operations,
.proc_fops = &proc_root_operations,
.parent = &proc_root,
+ .subdir = RB_ROOT,
.name = "/proc",
};
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index c34156888d70..246eae84b13b 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -87,32 +87,14 @@ unsigned long task_statm(struct mm_struct *mm,
#ifdef CONFIG_NUMA
/*
- * These functions are for numa_maps but called in generic **maps seq_file
- * ->start(), ->stop() ops.
- *
- * numa_maps scans all vmas under mmap_sem and checks their mempolicy.
- * Each mempolicy object is controlled by reference counting. The problem here
- * is how to avoid accessing dead mempolicy object.
- *
- * Because we're holding mmap_sem while reading seq_file, it's safe to access
- * each vma's mempolicy, no vma objects will never drop refs to mempolicy.
- *
- * A task's mempolicy (task->mempolicy) has different behavior. task->mempolicy
- * is set and replaced under mmap_sem but unrefed and cleared under task_lock().
- * So, without task_lock(), we cannot trust get_vma_policy() because we cannot
- * gurantee the task never exits under us. But taking task_lock() around
- * get_vma_plicy() causes lock order problem.
- *
- * To access task->mempolicy without lock, we hold a reference count of an
- * object pointed by task->mempolicy and remember it. This will guarantee
- * that task->mempolicy points to an alive object or NULL in numa_maps accesses.
+ * Save get_task_policy() for show_numa_map().
*/
static void hold_task_mempolicy(struct proc_maps_private *priv)
{
struct task_struct *task = priv->task;
task_lock(task);
- priv->task_mempolicy = task->mempolicy;
+ priv->task_mempolicy = get_task_policy(task);
mpol_get(priv->task_mempolicy);
task_unlock(task);
}
@@ -129,124 +111,154 @@ static void release_task_mempolicy(struct proc_maps_private *priv)
}
#endif
-static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
+static void vma_stop(struct proc_maps_private *priv)
{
- if (vma && vma != priv->tail_vma) {
- struct mm_struct *mm = vma->vm_mm;
- release_task_mempolicy(priv);
- up_read(&mm->mmap_sem);
- mmput(mm);
- }
+ struct mm_struct *mm = priv->mm;
+
+ release_task_mempolicy(priv);
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+}
+
+static struct vm_area_struct *
+m_next_vma(struct proc_maps_private *priv, struct vm_area_struct *vma)
+{
+ if (vma == priv->tail_vma)
+ return NULL;
+ return vma->vm_next ?: priv->tail_vma;
}
-static void *m_start(struct seq_file *m, loff_t *pos)
+static void m_cache_vma(struct seq_file *m, struct vm_area_struct *vma)
+{
+ if (m->count < m->size) /* vma is copied successfully */
+ m->version = m_next_vma(m->private, vma) ? vma->vm_start : -1UL;
+}
+
+static void *m_start(struct seq_file *m, loff_t *ppos)
{
struct proc_maps_private *priv = m->private;
unsigned long last_addr = m->version;
struct mm_struct *mm;
- struct vm_area_struct *vma, *tail_vma = NULL;
- loff_t l = *pos;
-
- /* Clear the per syscall fields in priv */
- priv->task = NULL;
- priv->tail_vma = NULL;
-
- /*
- * We remember last_addr rather than next_addr to hit with
- * vmacache most of the time. We have zero last_addr at
- * the beginning and also after lseek. We will have -1 last_addr
- * after the end of the vmas.
- */
+ struct vm_area_struct *vma;
+ unsigned int pos = *ppos;
+ /* See m_cache_vma(). Zero at the start or after lseek. */
if (last_addr == -1UL)
return NULL;
- priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
+ priv->task = get_proc_task(priv->inode);
if (!priv->task)
return ERR_PTR(-ESRCH);
- mm = mm_access(priv->task, PTRACE_MODE_READ);
- if (!mm || IS_ERR(mm))
- return mm;
- down_read(&mm->mmap_sem);
+ mm = priv->mm;
+ if (!mm || !atomic_inc_not_zero(&mm->mm_users))
+ return NULL;
- tail_vma = get_gate_vma(priv->task->mm);
- priv->tail_vma = tail_vma;
+ down_read(&mm->mmap_sem);
hold_task_mempolicy(priv);
- /* Start with last addr hint */
- vma = find_vma(mm, last_addr);
- if (last_addr && vma) {
- vma = vma->vm_next;
- goto out;
+ priv->tail_vma = get_gate_vma(mm);
+
+ if (last_addr) {
+ vma = find_vma(mm, last_addr);
+ if (vma && (vma = m_next_vma(priv, vma)))
+ return vma;
}
- /*
- * Check the vma index is within the range and do
- * sequential scan until m_index.
- */
- vma = NULL;
- if ((unsigned long)l < mm->map_count) {
- vma = mm->mmap;
- while (l-- && vma)
+ m->version = 0;
+ if (pos < mm->map_count) {
+ for (vma = mm->mmap; pos; pos--) {
+ m->version = vma->vm_start;
vma = vma->vm_next;
- goto out;
+ }
+ return vma;
}
- if (l != mm->map_count)
- tail_vma = NULL; /* After gate vma */
-
-out:
- if (vma)
- return vma;
+ /* we do not bother to update m->version in this case */
+ if (pos == mm->map_count && priv->tail_vma)
+ return priv->tail_vma;
- release_task_mempolicy(priv);
- /* End of vmas has been reached */
- m->version = (tail_vma != NULL)? 0: -1UL;
- up_read(&mm->mmap_sem);
- mmput(mm);
- return tail_vma;
+ vma_stop(priv);
+ return NULL;
}
static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
struct proc_maps_private *priv = m->private;
- struct vm_area_struct *vma = v;
- struct vm_area_struct *tail_vma = priv->tail_vma;
+ struct vm_area_struct *next;
(*pos)++;
- if (vma && (vma != tail_vma) && vma->vm_next)
- return vma->vm_next;
- vma_stop(priv, vma);
- return (vma != tail_vma)? tail_vma: NULL;
+ next = m_next_vma(priv, v);
+ if (!next)
+ vma_stop(priv);
+ return next;
}
static void m_stop(struct seq_file *m, void *v)
{
struct proc_maps_private *priv = m->private;
- struct vm_area_struct *vma = v;
- if (!IS_ERR(vma))
- vma_stop(priv, vma);
- if (priv->task)
+ if (!IS_ERR_OR_NULL(v))
+ vma_stop(priv);
+ if (priv->task) {
put_task_struct(priv->task);
+ priv->task = NULL;
+ }
+}
+
+static int proc_maps_open(struct inode *inode, struct file *file,
+ const struct seq_operations *ops, int psize)
+{
+ struct proc_maps_private *priv = __seq_open_private(file, ops, psize);
+
+ if (!priv)
+ return -ENOMEM;
+
+ priv->inode = inode;
+ priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
+ if (IS_ERR(priv->mm)) {
+ int err = PTR_ERR(priv->mm);
+
+ seq_release_private(inode, file);
+ return err;
+ }
+
+ return 0;
+}
+
+static int proc_map_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+ struct proc_maps_private *priv = seq->private;
+
+ if (priv->mm)
+ mmdrop(priv->mm);
+
+ return seq_release_private(inode, file);
}
static int do_maps_open(struct inode *inode, struct file *file,
const struct seq_operations *ops)
{
- struct proc_maps_private *priv;
- int ret = -ENOMEM;
- priv = kzalloc(sizeof(*priv), GFP_KERNEL);
- if (priv) {
- priv->pid = proc_pid(inode);
- ret = seq_open(file, ops);
- if (!ret) {
- struct seq_file *m = file->private_data;
- m->private = priv;
- } else {
- kfree(priv);
- }
+ return proc_maps_open(inode, file, ops,
+ sizeof(struct proc_maps_private));
+}
+
+static pid_t pid_of_stack(struct proc_maps_private *priv,
+ struct vm_area_struct *vma, bool is_pid)
+{
+ struct inode *inode = priv->inode;
+ struct task_struct *task;
+ pid_t ret = 0;
+
+ rcu_read_lock();
+ task = pid_task(proc_pid(inode), PIDTYPE_PID);
+ if (task) {
+ task = task_of_stack(task, vma, is_pid);
+ if (task)
+ ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
}
+ rcu_read_unlock();
+
return ret;
}
@@ -256,7 +268,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
struct mm_struct *mm = vma->vm_mm;
struct file *file = vma->vm_file;
struct proc_maps_private *priv = m->private;
- struct task_struct *task = priv->task;
vm_flags_t flags = vma->vm_flags;
unsigned long ino = 0;
unsigned long long pgoff = 0;
@@ -321,8 +332,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
goto done;
}
- tid = vm_is_stack(task, vma, is_pid);
-
+ tid = pid_of_stack(priv, vma, is_pid);
if (tid != 0) {
/*
* Thread stack in /proc/PID/task/TID/maps or
@@ -349,15 +359,8 @@ done:
static int show_map(struct seq_file *m, void *v, int is_pid)
{
- struct vm_area_struct *vma = v;
- struct proc_maps_private *priv = m->private;
- struct task_struct *task = priv->task;
-
- show_map_vma(m, vma, is_pid);
-
- if (m->count < m->size) /* vma is copied successfully */
- m->version = (vma != get_gate_vma(task->mm))
- ? vma->vm_start : 0;
+ show_map_vma(m, v, is_pid);
+ m_cache_vma(m, v);
return 0;
}
@@ -399,14 +402,14 @@ const struct file_operations proc_pid_maps_operations = {
.open = pid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = proc_map_release,
};
const struct file_operations proc_tid_maps_operations = {
.open = tid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = proc_map_release,
};
/*
@@ -444,59 +447,92 @@ struct mem_size_stats {
u64 pss;
};
+static void smaps_account(struct mem_size_stats *mss, struct page *page,
+ unsigned long size, bool young, bool dirty)
+{
+ int mapcount;
+
+ if (PageAnon(page))
+ mss->anonymous += size;
+
+ mss->resident += size;
+ /* Accumulate the size in pages that have been accessed. */
+ if (young || PageReferenced(page))
+ mss->referenced += size;
+ mapcount = page_mapcount(page);
+ if (mapcount >= 2) {
+ u64 pss_delta;
-static void smaps_pte_entry(pte_t ptent, unsigned long addr,
- unsigned long ptent_size, struct mm_walk *walk)
+ if (dirty || PageDirty(page))
+ mss->shared_dirty += size;
+ else
+ mss->shared_clean += size;
+ pss_delta = (u64)size << PSS_SHIFT;
+ do_div(pss_delta, mapcount);
+ mss->pss += pss_delta;
+ } else {
+ if (dirty || PageDirty(page))
+ mss->private_dirty += size;
+ else
+ mss->private_clean += size;
+ mss->pss += (u64)size << PSS_SHIFT;
+ }
+}
+
+static void smaps_pte_entry(pte_t *pte, unsigned long addr,
+ struct mm_walk *walk)
{
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = mss->vma;
pgoff_t pgoff = linear_page_index(vma, addr);
struct page *page = NULL;
- int mapcount;
- if (pte_present(ptent)) {
- page = vm_normal_page(vma, addr, ptent);
- } else if (is_swap_pte(ptent)) {
- swp_entry_t swpent = pte_to_swp_entry(ptent);
+ if (pte_present(*pte)) {
+ page = vm_normal_page(vma, addr, *pte);
+ } else if (is_swap_pte(*pte)) {
+ swp_entry_t swpent = pte_to_swp_entry(*pte);
if (!non_swap_entry(swpent))
- mss->swap += ptent_size;
+ mss->swap += PAGE_SIZE;
else if (is_migration_entry(swpent))
page = migration_entry_to_page(swpent);
- } else if (pte_file(ptent)) {
- if (pte_to_pgoff(ptent) != pgoff)
- mss->nonlinear += ptent_size;
+ } else if (pte_file(*pte)) {
+ if (pte_to_pgoff(*pte) != pgoff)
+ mss->nonlinear += PAGE_SIZE;
}
if (!page)
return;
- if (PageAnon(page))
- mss->anonymous += ptent_size;
-
if (page->index != pgoff)
- mss->nonlinear += ptent_size;
+ mss->nonlinear += PAGE_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);
- }
+ smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte));
}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
+ struct mm_walk *walk)
+{
+ struct mem_size_stats *mss = walk->private;
+ struct vm_area_struct *vma = mss->vma;
+ struct page *page;
+
+ /* FOLL_DUMP will return -EFAULT on huge zero page */
+ page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
+ if (IS_ERR_OR_NULL(page))
+ return;
+ mss->anonymous_thp += HPAGE_PMD_SIZE;
+ smaps_account(mss, page, HPAGE_PMD_SIZE,
+ pmd_young(*pmd), pmd_dirty(*pmd));
+}
+#else
+static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
+ struct mm_walk *walk)
+{
+}
+#endif
+
static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
@@ -506,9 +542,8 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
spinlock_t *ptl;
if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
- smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
+ smaps_pmd_entry(pmd, addr, walk);
spin_unlock(ptl);
- mss->anonymous_thp += HPAGE_PMD_SIZE;
return 0;
}
@@ -521,7 +556,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
*/
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);
+ smaps_pte_entry(pte, addr, walk);
pte_unmap_unlock(pte - 1, ptl);
cond_resched();
return 0;
@@ -549,6 +584,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
[ilog2(VM_GROWSDOWN)] = "gd",
[ilog2(VM_PFNMAP)] = "pf",
[ilog2(VM_DENYWRITE)] = "dw",
+#ifdef CONFIG_X86_INTEL_MPX
+ [ilog2(VM_MPX)] = "mp",
+#endif
[ilog2(VM_LOCKED)] = "lo",
[ilog2(VM_IO)] = "io",
[ilog2(VM_SEQ_READ)] = "sr",
@@ -583,8 +621,6 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
static int show_smap(struct seq_file *m, void *v, int is_pid)
{
- struct proc_maps_private *priv = m->private;
- struct task_struct *task = priv->task;
struct vm_area_struct *vma = v;
struct mem_size_stats mss;
struct mm_walk smaps_walk = {
@@ -637,10 +673,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
mss.nonlinear >> 10);
show_smap_vma_flags(m, vma);
-
- if (m->count < m->size) /* vma is copied successfully */
- m->version = (vma != get_gate_vma(task->mm))
- ? vma->vm_start : 0;
+ m_cache_vma(m, vma);
return 0;
}
@@ -682,14 +715,14 @@ const struct file_operations proc_pid_smaps_operations = {
.open = pid_smaps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = proc_map_release,
};
const struct file_operations proc_tid_smaps_operations = {
.open = tid_smaps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = proc_map_release,
};
/*
@@ -829,8 +862,21 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
.private = &cp,
};
down_read(&mm->mmap_sem);
- if (type == CLEAR_REFS_SOFT_DIRTY)
+ if (type == CLEAR_REFS_SOFT_DIRTY) {
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (!(vma->vm_flags & VM_SOFTDIRTY))
+ continue;
+ up_read(&mm->mmap_sem);
+ down_write(&mm->mmap_sem);
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ vma->vm_flags &= ~VM_SOFTDIRTY;
+ vma_set_page_prot(vma);
+ }
+ downgrade_write(&mm->mmap_sem);
+ break;
+ }
mmu_notifier_invalidate_range_start(mm, 0, -1);
+ }
for (vma = mm->mmap; vma; vma = vma->vm_next) {
cp.vma = vma;
if (is_vm_hugetlb_page(vma))
@@ -850,10 +896,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
continue;
if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
continue;
- if (type == CLEAR_REFS_SOFT_DIRTY) {
- if (vma->vm_flags & VM_SOFTDIRTY)
- vma->vm_flags &= ~VM_SOFTDIRTY;
- }
walk_page_range(vma->vm_start, vma->vm_end,
&clear_refs_walk);
}
@@ -1029,7 +1071,6 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
spinlock_t *ptl;
pte_t *pte;
int err = 0;
- pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
/* find the first VMA at or above 'addr' */
vma = find_vma(walk->mm, addr);
@@ -1043,6 +1084,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
for (; addr != end; addr += PAGE_SIZE) {
unsigned long offset;
+ pagemap_entry_t pme;
offset = (addr & ~PAGEMAP_WALK_MASK) >>
PAGE_SHIFT;
@@ -1057,32 +1099,51 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
if (pmd_trans_unstable(pmd))
return 0;
- for (; addr != end; addr += PAGE_SIZE) {
- int flags2;
-
- /* check to see if we've left 'vma' behind
- * and need a new, higher one */
- if (vma && (addr >= vma->vm_end)) {
- vma = find_vma(walk->mm, addr);
- if (vma && (vma->vm_flags & VM_SOFTDIRTY))
- flags2 = __PM_SOFT_DIRTY;
- else
- flags2 = 0;
- pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
+
+ while (1) {
+ /* End of address space hole, which we mark as non-present. */
+ unsigned long hole_end;
+
+ if (vma)
+ hole_end = min(end, vma->vm_start);
+ else
+ hole_end = end;
+
+ for (; addr < hole_end; addr += PAGE_SIZE) {
+ pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
+
+ err = add_to_pagemap(addr, &pme, pm);
+ if (err)
+ return err;
}
- /* check that 'vma' actually covers this address,
- * and that it isn't a huge page vma */
- if (vma && (vma->vm_start <= addr) &&
- !is_vm_hugetlb_page(vma)) {
+ if (!vma || vma->vm_start >= end)
+ break;
+ /*
+ * We can't possibly be in a hugetlb VMA. In general,
+ * for a mm_walk with a pmd_entry and a hugetlb_entry,
+ * the pmd_entry can only be called on addresses in a
+ * hugetlb if the walk starts in a non-hugetlb VMA and
+ * spans a hugepage VMA. Since pagemap_read walks are
+ * PMD-sized and PMD-aligned, this will never be true.
+ */
+ BUG_ON(is_vm_hugetlb_page(vma));
+
+ /* Addresses in the VMA. */
+ for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
+ pagemap_entry_t pme;
pte = pte_offset_map(pmd, addr);
pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
- /* unmap before userspace copy */
pte_unmap(pte);
+ err = add_to_pagemap(addr, &pme, pm);
+ if (err)
+ return err;
}
- err = add_to_pagemap(addr, &pme, pm);
- if (err)
- return err;
+
+ if (addr == end)
+ break;
+
+ vma = find_vma(walk->mm, addr);
}
cond_resched();
@@ -1415,7 +1476,6 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
struct vm_area_struct *vma = v;
struct numa_maps *md = &numa_priv->md;
struct file *file = vma->vm_file;
- struct task_struct *task = proc_priv->task;
struct mm_struct *mm = vma->vm_mm;
struct mm_walk walk = {};
struct mempolicy *pol;
@@ -1435,9 +1495,13 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
walk.private = md;
walk.mm = mm;
- pol = get_vma_policy(task, vma, vma->vm_start);
- mpol_to_str(buffer, sizeof(buffer), pol);
- mpol_cond_put(pol);
+ pol = __get_vma_policy(vma, vma->vm_start);
+ if (pol) {
+ mpol_to_str(buffer, sizeof(buffer), pol);
+ mpol_cond_put(pol);
+ } else {
+ mpol_to_str(buffer, sizeof(buffer), proc_priv->task_mempolicy);
+ }
seq_printf(m, "%08lx %s", vma->vm_start, buffer);
@@ -1447,7 +1511,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
seq_puts(m, " heap");
} else {
- pid_t tid = vm_is_stack(task, vma, is_pid);
+ pid_t tid = pid_of_stack(proc_priv, vma, is_pid);
if (tid != 0) {
/*
* Thread stack in /proc/PID/task/TID/maps or
@@ -1495,9 +1559,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
seq_printf(m, " N%d=%lu", nid, md->node[nid]);
out:
seq_putc(m, '\n');
-
- if (m->count < m->size)
- m->version = (vma != proc_priv->tail_vma) ? vma->vm_start : 0;
+ m_cache_vma(m, vma);
return 0;
}
@@ -1528,20 +1590,8 @@ static const struct seq_operations proc_tid_numa_maps_op = {
static int numa_maps_open(struct inode *inode, struct file *file,
const struct seq_operations *ops)
{
- struct numa_maps_private *priv;
- int ret = -ENOMEM;
- priv = kzalloc(sizeof(*priv), GFP_KERNEL);
- if (priv) {
- priv->proc_maps.pid = proc_pid(inode);
- ret = seq_open(file, ops);
- if (!ret) {
- struct seq_file *m = file->private_data;
- m->private = priv;
- } else {
- kfree(priv);
- }
- }
- return ret;
+ return proc_maps_open(inode, file, ops,
+ sizeof(struct numa_maps_private));
}
static int pid_numa_maps_open(struct inode *inode, struct file *file)
@@ -1558,13 +1608,13 @@ const struct file_operations proc_pid_numa_maps_operations = {
.open = pid_numa_maps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = proc_map_release,
};
const struct file_operations proc_tid_numa_maps_operations = {
.open = tid_numa_maps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = proc_map_release,
};
#endif /* CONFIG_NUMA */
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 678455d2d683..599ec2e20104 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -123,6 +123,25 @@ unsigned long task_statm(struct mm_struct *mm,
return size;
}
+static pid_t pid_of_stack(struct proc_maps_private *priv,
+ struct vm_area_struct *vma, bool is_pid)
+{
+ struct inode *inode = priv->inode;
+ struct task_struct *task;
+ pid_t ret = 0;
+
+ rcu_read_lock();
+ task = pid_task(proc_pid(inode), PIDTYPE_PID);
+ if (task) {
+ task = task_of_stack(task, vma, is_pid);
+ if (task)
+ ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
/*
* display a single VMA to a sequenced file
*/
@@ -163,7 +182,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
seq_pad(m, ' ');
seq_path(m, &file->f_path, "");
} else if (mm) {
- pid_t tid = vm_is_stack(priv->task, vma, is_pid);
+ pid_t tid = pid_of_stack(priv, vma, is_pid);
if (tid != 0) {
seq_pad(m, ' ');
@@ -212,22 +231,22 @@ static void *m_start(struct seq_file *m, loff_t *pos)
loff_t n = *pos;
/* pin the task and mm whilst we play with them */
- priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
+ priv->task = get_proc_task(priv->inode);
if (!priv->task)
return ERR_PTR(-ESRCH);
- mm = mm_access(priv->task, PTRACE_MODE_READ);
- if (!mm || IS_ERR(mm)) {
- put_task_struct(priv->task);
- priv->task = NULL;
- return mm;
- }
- down_read(&mm->mmap_sem);
+ mm = priv->mm;
+ if (!mm || !atomic_inc_not_zero(&mm->mm_users))
+ return NULL;
+ down_read(&mm->mmap_sem);
/* start from the Nth VMA */
for (p = rb_first(&mm->mm_rb); p; p = rb_next(p))
if (n-- == 0)
return p;
+
+ up_read(&mm->mmap_sem);
+ mmput(mm);
return NULL;
}
@@ -235,11 +254,13 @@ static void m_stop(struct seq_file *m, void *_vml)
{
struct proc_maps_private *priv = m->private;
+ if (!IS_ERR_OR_NULL(_vml)) {
+ up_read(&priv->mm->mmap_sem);
+ mmput(priv->mm);
+ }
if (priv->task) {
- struct mm_struct *mm = priv->task->mm;
- up_read(&mm->mmap_sem);
- mmput(mm);
put_task_struct(priv->task);
+ priv->task = NULL;
}
}
@@ -269,20 +290,33 @@ static int maps_open(struct inode *inode, struct file *file,
const struct seq_operations *ops)
{
struct proc_maps_private *priv;
- int ret = -ENOMEM;
-
- priv = kzalloc(sizeof(*priv), GFP_KERNEL);
- if (priv) {
- priv->pid = proc_pid(inode);
- ret = seq_open(file, ops);
- if (!ret) {
- struct seq_file *m = file->private_data;
- m->private = priv;
- } else {
- kfree(priv);
- }
+
+ priv = __seq_open_private(file, ops, sizeof(*priv));
+ if (!priv)
+ return -ENOMEM;
+
+ priv->inode = inode;
+ priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
+ if (IS_ERR(priv->mm)) {
+ int err = PTR_ERR(priv->mm);
+
+ seq_release_private(inode, file);
+ return err;
}
- return ret;
+
+ return 0;
+}
+
+
+static int map_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+ struct proc_maps_private *priv = seq->private;
+
+ if (priv->mm)
+ mmdrop(priv->mm);
+
+ return seq_release_private(inode, file);
}
static int pid_maps_open(struct inode *inode, struct file *file)
@@ -299,13 +333,13 @@ const struct file_operations proc_pid_maps_operations = {
.open = pid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = map_release,
};
const struct file_operations proc_tid_maps_operations = {
.open = tid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = map_release,
};
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 12:37:03 +0000