summaryrefslogtreecommitdiff
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/base.c56
-rw-r--r--fs/proc/fd.h5
-rw-r--r--fs/proc/generic.c377
-rw-r--r--fs/proc/inode.c283
-rw-r--r--fs/proc/internal.h313
-rw-r--r--fs/proc/kcore.c2
-rw-r--r--fs/proc/namespaces.c17
-rw-r--r--fs/proc/proc_devtree.c2
-rw-r--r--fs/proc/proc_net.c4
-rw-r--r--fs/proc/root.c2
-rw-r--r--fs/proc/self.c47
-rw-r--r--fs/proc/vmcore.c5
12 files changed, 501 insertions, 612 deletions
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 3861bcec41ff..dd51e50001fe 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -405,6 +405,37 @@ 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 task_struct *task, char *buffer)
{
unsigned long totalpages = totalram_pages + total_swap_pages;
@@ -1621,6 +1652,15 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags)
return 0;
}
+int pid_delete_dentry(const struct dentry *dentry)
+{
+ /* Is the task we represent dead?
+ * If so, then don't put the dentry on the lru list,
+ * kill it immediately.
+ */
+ return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first;
+}
+
const struct dentry_operations pid_dentry_operations =
{
.d_revalidate = pid_revalidate,
@@ -2893,7 +2933,7 @@ retry:
return iter;
}
-#define TGID_OFFSET (FIRST_PROCESS_ENTRY)
+#define TGID_OFFSET (FIRST_PROCESS_ENTRY + 1)
static int proc_pid_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
struct tgid_iter iter)
@@ -2916,13 +2956,21 @@ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir)
struct tgid_iter iter;
struct pid_namespace *ns;
filldir_t __filldir;
+ loff_t pos = filp->f_pos;
- if (filp->f_pos >= PID_MAX_LIMIT + TGID_OFFSET)
+ if (pos >= PID_MAX_LIMIT + TGID_OFFSET)
goto out;
- ns = filp->f_dentry->d_sb->s_fs_info;
+ if (pos == TGID_OFFSET - 1) {
+ if (proc_fill_cache(filp, dirent, filldir, "self", 4,
+ NULL, NULL, NULL) < 0)
+ goto out;
+ iter.tgid = 0;
+ } else {
+ iter.tgid = pos - TGID_OFFSET;
+ }
iter.task = NULL;
- iter.tgid = filp->f_pos - TGID_OFFSET;
+ ns = filp->f_dentry->d_sb->s_fs_info;
for (iter = next_tgid(ns, iter);
iter.task;
iter.tgid += 1, iter = next_tgid(ns, iter)) {
diff --git a/fs/proc/fd.h b/fs/proc/fd.h
index cbb1d47deda8..7c047f256ae2 100644
--- a/fs/proc/fd.h
+++ b/fs/proc/fd.h
@@ -11,4 +11,9 @@ extern const struct inode_operations proc_fdinfo_inode_operations;
extern int proc_fd_permission(struct inode *inode, int mask);
+static inline int proc_fd(struct inode *inode)
+{
+ return PROC_I(inode)->fd;
+}
+
#endif /* __PROCFS_FD_H__ */
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 21e1a8f1659d..a2596afffae6 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -36,212 +36,6 @@ static int proc_match(unsigned int len, const char *name, struct proc_dir_entry
return !memcmp(name, de->name, len);
}
-/* buffer size is one page but our output routines use some slack for overruns */
-#define PROC_BLOCK_SIZE (PAGE_SIZE - 1024)
-
-static ssize_t
-__proc_file_read(struct file *file, char __user *buf, size_t nbytes,
- loff_t *ppos)
-{
- struct inode * inode = file_inode(file);
- char *page;
- ssize_t retval=0;
- int eof=0;
- ssize_t n, count;
- char *start;
- struct proc_dir_entry * dp;
- unsigned long long pos;
-
- /*
- * Gaah, please just use "seq_file" instead. The legacy /proc
- * interfaces cut loff_t down to off_t for reads, and ignore
- * the offset entirely for writes..
- */
- pos = *ppos;
- if (pos > MAX_NON_LFS)
- return 0;
- if (nbytes > MAX_NON_LFS - pos)
- nbytes = MAX_NON_LFS - pos;
-
- dp = PDE(inode);
- if (!(page = (char*) __get_free_page(GFP_TEMPORARY)))
- return -ENOMEM;
-
- while ((nbytes > 0) && !eof) {
- count = min_t(size_t, PROC_BLOCK_SIZE, nbytes);
-
- start = NULL;
- if (dp->read_proc) {
- /*
- * How to be a proc read function
- * ------------------------------
- * Prototype:
- * int f(char *buffer, char **start, off_t offset,
- * int count, int *peof, void *dat)
- *
- * Assume that the buffer is "count" bytes in size.
- *
- * If you know you have supplied all the data you
- * have, set *peof.
- *
- * You have three ways to return data:
- * 0) Leave *start = NULL. (This is the default.)
- * Put the data of the requested offset at that
- * offset within the buffer. Return the number (n)
- * of bytes there are from the beginning of the
- * buffer up to the last byte of data. If the
- * number of supplied bytes (= n - offset) is
- * greater than zero and you didn't signal eof
- * and the reader is prepared to take more data
- * you will be called again with the requested
- * offset advanced by the number of bytes
- * absorbed. This interface is useful for files
- * no larger than the buffer.
- * 1) Set *start = an unsigned long value less than
- * the buffer address but greater than zero.
- * Put the data of the requested offset at the
- * beginning of the buffer. Return the number of
- * bytes of data placed there. If this number is
- * greater than zero and you didn't signal eof
- * and the reader is prepared to take more data
- * you will be called again with the requested
- * offset advanced by *start. This interface is
- * useful when you have a large file consisting
- * of a series of blocks which you want to count
- * and return as wholes.
- * (Hack by Paul.Russell@rustcorp.com.au)
- * 2) Set *start = an address within the buffer.
- * Put the data of the requested offset at *start.
- * Return the number of bytes of data placed there.
- * If this number is greater than zero and you
- * didn't signal eof and the reader is prepared to
- * take more data you will be called again with the
- * requested offset advanced by the number of bytes
- * absorbed.
- */
- n = dp->read_proc(page, &start, *ppos,
- count, &eof, dp->data);
- } else
- break;
-
- if (n == 0) /* end of file */
- break;
- if (n < 0) { /* error */
- if (retval == 0)
- retval = n;
- break;
- }
-
- if (start == NULL) {
- if (n > PAGE_SIZE) /* Apparent buffer overflow */
- n = PAGE_SIZE;
- n -= *ppos;
- if (n <= 0)
- break;
- if (n > count)
- n = count;
- start = page + *ppos;
- } else if (start < page) {
- if (n > PAGE_SIZE) /* Apparent buffer overflow */
- n = PAGE_SIZE;
- if (n > count) {
- /*
- * Don't reduce n because doing so might
- * cut off part of a data block.
- */
- pr_warn("proc_file_read: count exceeded\n");
- }
- } else /* start >= page */ {
- unsigned long startoff = (unsigned long)(start - page);
- if (n > (PAGE_SIZE - startoff)) /* buffer overflow? */
- n = PAGE_SIZE - startoff;
- if (n > count)
- n = count;
- }
-
- n -= copy_to_user(buf, start < page ? page : start, n);
- if (n == 0) {
- if (retval == 0)
- retval = -EFAULT;
- break;
- }
-
- *ppos += start < page ? (unsigned long)start : n;
- nbytes -= n;
- buf += n;
- retval += n;
- }
- free_page((unsigned long) page);
- return retval;
-}
-
-static ssize_t
-proc_file_read(struct file *file, char __user *buf, size_t nbytes,
- loff_t *ppos)
-{
- struct proc_dir_entry *pde = PDE(file_inode(file));
- ssize_t rv = -EIO;
-
- spin_lock(&pde->pde_unload_lock);
- if (!pde->proc_fops) {
- spin_unlock(&pde->pde_unload_lock);
- return rv;
- }
- pde->pde_users++;
- spin_unlock(&pde->pde_unload_lock);
-
- rv = __proc_file_read(file, buf, nbytes, ppos);
-
- pde_users_dec(pde);
- return rv;
-}
-
-static ssize_t
-proc_file_write(struct file *file, const char __user *buffer,
- size_t count, loff_t *ppos)
-{
- struct proc_dir_entry *pde = PDE(file_inode(file));
- ssize_t rv = -EIO;
-
- if (pde->write_proc) {
- spin_lock(&pde->pde_unload_lock);
- if (!pde->proc_fops) {
- spin_unlock(&pde->pde_unload_lock);
- return rv;
- }
- pde->pde_users++;
- spin_unlock(&pde->pde_unload_lock);
-
- /* FIXME: does this routine need ppos? probably... */
- rv = pde->write_proc(file, buffer, count, pde->data);
- pde_users_dec(pde);
- }
- return rv;
-}
-
-
-static loff_t
-proc_file_lseek(struct file *file, loff_t offset, int orig)
-{
- loff_t retval = -EINVAL;
- switch (orig) {
- case 1:
- offset += file->f_pos;
- /* fallthrough */
- case 0:
- if (offset < 0 || offset > MAX_NON_LFS)
- break;
- file->f_pos = retval = offset;
- }
- return retval;
-}
-
-static const struct file_operations proc_file_operations = {
- .llseek = proc_file_lseek,
- .read = proc_file_read,
- .write = proc_file_write,
-};
-
static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = dentry->d_inode;
@@ -371,7 +165,7 @@ void proc_free_inum(unsigned int inum)
static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
{
- nd_set_link(nd, PDE(dentry->d_inode)->data);
+ nd_set_link(nd, __PDE_DATA(dentry->d_inode));
return NULL;
}
@@ -541,19 +335,17 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
return ret;
if (S_ISDIR(dp->mode)) {
- if (dp->proc_iops == NULL) {
- dp->proc_fops = &proc_dir_operations;
- dp->proc_iops = &proc_dir_inode_operations;
- }
+ dp->proc_fops = &proc_dir_operations;
+ dp->proc_iops = &proc_dir_inode_operations;
dir->nlink++;
} else if (S_ISLNK(dp->mode)) {
- if (dp->proc_iops == NULL)
- dp->proc_iops = &proc_link_inode_operations;
+ dp->proc_iops = &proc_link_inode_operations;
} else if (S_ISREG(dp->mode)) {
- if (dp->proc_fops == NULL)
- dp->proc_fops = &proc_file_operations;
- if (dp->proc_iops == NULL)
- dp->proc_iops = &proc_file_inode_operations;
+ BUG_ON(dp->proc_fops == NULL);
+ dp->proc_iops = &proc_file_inode_operations;
+ } else {
+ WARN_ON(1);
+ return -EINVAL;
}
spin_lock(&proc_subdir_lock);
@@ -636,13 +428,17 @@ struct proc_dir_entry *proc_symlink(const char *name,
}
EXPORT_SYMBOL(proc_symlink);
-struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode,
- struct proc_dir_entry *parent)
+struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
+ struct proc_dir_entry *parent, void *data)
{
struct proc_dir_entry *ent;
+ if (mode == 0)
+ mode = S_IRUGO | S_IXUGO;
+
ent = __proc_create(&parent, name, S_IFDIR | mode, 2);
if (ent) {
+ ent->data = data;
if (proc_register(parent, ent) < 0) {
kfree(ent);
ent = NULL;
@@ -650,82 +446,39 @@ struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode,
}
return ent;
}
-EXPORT_SYMBOL(proc_mkdir_mode);
+EXPORT_SYMBOL_GPL(proc_mkdir_data);
-struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
- struct proc_dir_entry *parent)
+struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode,
+ struct proc_dir_entry *parent)
{
- struct proc_dir_entry *ent;
-
- ent = __proc_create(&parent, name, S_IFDIR | S_IRUGO | S_IXUGO, 2);
- if (ent) {
- ent->data = net;
- if (proc_register(parent, ent) < 0) {
- kfree(ent);
- ent = NULL;
- }
- }
- return ent;
+ return proc_mkdir_data(name, mode, parent, NULL);
}
-EXPORT_SYMBOL_GPL(proc_net_mkdir);
+EXPORT_SYMBOL(proc_mkdir_mode);
struct proc_dir_entry *proc_mkdir(const char *name,
struct proc_dir_entry *parent)
{
- return proc_mkdir_mode(name, S_IRUGO | S_IXUGO, parent);
+ return proc_mkdir_data(name, 0, parent, NULL);
}
EXPORT_SYMBOL(proc_mkdir);
-struct proc_dir_entry *create_proc_entry(const char *name, umode_t mode,
- struct proc_dir_entry *parent)
-{
- struct proc_dir_entry *ent;
- nlink_t nlink;
-
- if (S_ISDIR(mode)) {
- if ((mode & S_IALLUGO) == 0)
- mode |= S_IRUGO | S_IXUGO;
- nlink = 2;
- } else {
- if ((mode & S_IFMT) == 0)
- mode |= S_IFREG;
- if ((mode & S_IALLUGO) == 0)
- mode |= S_IRUGO;
- nlink = 1;
- }
-
- ent = __proc_create(&parent, name, mode, nlink);
- if (ent) {
- if (proc_register(parent, ent) < 0) {
- kfree(ent);
- ent = NULL;
- }
- }
- return ent;
-}
-EXPORT_SYMBOL(create_proc_entry);
-
struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
struct proc_dir_entry *parent,
const struct file_operations *proc_fops,
void *data)
{
struct proc_dir_entry *pde;
- nlink_t nlink;
+ if ((mode & S_IFMT) == 0)
+ mode |= S_IFREG;
- if (S_ISDIR(mode)) {
- if ((mode & S_IALLUGO) == 0)
- mode |= S_IRUGO | S_IXUGO;
- nlink = 2;
- } else {
- if ((mode & S_IFMT) == 0)
- mode |= S_IFREG;
- if ((mode & S_IALLUGO) == 0)
- mode |= S_IRUGO;
- nlink = 1;
+ if (!S_ISREG(mode)) {
+ WARN_ON(1); /* use proc_mkdir() */
+ return NULL;
}
- pde = __proc_create(&parent, name, mode, nlink);
+ if ((mode & S_IALLUGO) == 0)
+ mode |= S_IRUGO;
+ pde = __proc_create(&parent, name, mode, 1);
if (!pde)
goto out;
pde->proc_fops = proc_fops;
@@ -739,6 +492,19 @@ out:
return NULL;
}
EXPORT_SYMBOL(proc_create_data);
+
+void proc_set_size(struct proc_dir_entry *de, loff_t size)
+{
+ de->size = size;
+}
+EXPORT_SYMBOL(proc_set_size);
+
+void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid)
+{
+ de->uid = uid;
+ de->gid = gid;
+}
+EXPORT_SYMBOL(proc_set_user);
static void free_proc_entry(struct proc_dir_entry *de)
{
@@ -755,41 +521,6 @@ void pde_put(struct proc_dir_entry *pde)
free_proc_entry(pde);
}
-static void entry_rundown(struct proc_dir_entry *de)
-{
- spin_lock(&de->pde_unload_lock);
- /*
- * Stop accepting new callers into module. If you're
- * dynamically allocating ->proc_fops, save a pointer somewhere.
- */
- de->proc_fops = NULL;
- /* Wait until all existing callers into module are done. */
- if (de->pde_users > 0) {
- DECLARE_COMPLETION_ONSTACK(c);
-
- if (!de->pde_unload_completion)
- de->pde_unload_completion = &c;
-
- spin_unlock(&de->pde_unload_lock);
-
- wait_for_completion(de->pde_unload_completion);
-
- spin_lock(&de->pde_unload_lock);
- }
-
- while (!list_empty(&de->pde_openers)) {
- struct pde_opener *pdeo;
-
- pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh);
- list_del(&pdeo->lh);
- spin_unlock(&de->pde_unload_lock);
- pdeo->release(pdeo->inode, pdeo->file);
- kfree(pdeo);
- spin_lock(&de->pde_unload_lock);
- }
- spin_unlock(&de->pde_unload_lock);
-}
-
/*
* Remove a /proc entry and free it if it's not currently in use.
*/
@@ -821,7 +552,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
return;
}
- entry_rundown(de);
+ proc_entry_rundown(de);
if (S_ISDIR(de->mode))
parent->nlink--;
@@ -870,7 +601,7 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
}
spin_unlock(&proc_subdir_lock);
- entry_rundown(de);
+ proc_entry_rundown(de);
next = de->parent;
if (S_ISDIR(de->mode))
next->nlink--;
@@ -886,3 +617,23 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
return 0;
}
EXPORT_SYMBOL(remove_proc_subtree);
+
+void *proc_get_parent_data(const struct inode *inode)
+{
+ struct proc_dir_entry *de = PDE(inode);
+ return de->parent->data;
+}
+EXPORT_SYMBOL_GPL(proc_get_parent_data);
+
+void proc_remove(struct proc_dir_entry *de)
+{
+ if (de)
+ remove_proc_subtree(de->name, de->parent);
+}
+EXPORT_SYMBOL(proc_remove);
+
+void *PDE_DATA(const struct inode *inode)
+{
+ return __PDE_DATA(inode);
+}
+EXPORT_SYMBOL(PDE_DATA);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 869116c2afbe..073aea60cf8f 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -22,6 +22,7 @@
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/mount.h>
+#include <linux/magic.h>
#include <asm/uaccess.h>
@@ -50,8 +51,8 @@ static void proc_evict_inode(struct inode *inode)
sysctl_head_put(head);
}
/* Release any associated namespace */
- ns_ops = PROC_I(inode)->ns_ops;
- ns = PROC_I(inode)->ns;
+ ns_ops = PROC_I(inode)->ns.ns_ops;
+ ns = PROC_I(inode)->ns.ns;
if (ns_ops && ns)
ns_ops->put(ns);
}
@@ -72,8 +73,8 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
ei->pde = NULL;
ei->sysctl = NULL;
ei->sysctl_entry = NULL;
- ei->ns = NULL;
- ei->ns_ops = NULL;
+ ei->ns.ns = NULL;
+ ei->ns.ns_ops = NULL;
inode = &ei->vfs_inode;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
return inode;
@@ -129,96 +130,100 @@ static const struct super_operations proc_sops = {
.show_options = proc_show_options,
};
-static void __pde_users_dec(struct proc_dir_entry *pde)
+enum {BIAS = -1U<<31};
+
+static inline int use_pde(struct proc_dir_entry *pde)
+{
+ return atomic_inc_unless_negative(&pde->in_use);
+}
+
+static void unuse_pde(struct proc_dir_entry *pde)
{
- pde->pde_users--;
- if (pde->pde_unload_completion && pde->pde_users == 0)
+ if (atomic_dec_return(&pde->in_use) == BIAS)
complete(pde->pde_unload_completion);
}
-void pde_users_dec(struct proc_dir_entry *pde)
+/* pde is locked */
+static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
{
- spin_lock(&pde->pde_unload_lock);
- __pde_users_dec(pde);
- spin_unlock(&pde->pde_unload_lock);
+ if (pdeo->closing) {
+ /* somebody else is doing that, just wait */
+ DECLARE_COMPLETION_ONSTACK(c);
+ pdeo->c = &c;
+ spin_unlock(&pde->pde_unload_lock);
+ wait_for_completion(&c);
+ spin_lock(&pde->pde_unload_lock);
+ } else {
+ struct file *file;
+ pdeo->closing = 1;
+ spin_unlock(&pde->pde_unload_lock);
+ file = pdeo->file;
+ pde->proc_fops->release(file_inode(file), file);
+ spin_lock(&pde->pde_unload_lock);
+ list_del_init(&pdeo->lh);
+ if (pdeo->c)
+ complete(pdeo->c);
+ kfree(pdeo);
+ }
+}
+
+void proc_entry_rundown(struct proc_dir_entry *de)
+{
+ DECLARE_COMPLETION_ONSTACK(c);
+ /* Wait until all existing callers into module are done. */
+ de->pde_unload_completion = &c;
+ if (atomic_add_return(BIAS, &de->in_use) != BIAS)
+ wait_for_completion(&c);
+
+ spin_lock(&de->pde_unload_lock);
+ while (!list_empty(&de->pde_openers)) {
+ struct pde_opener *pdeo;
+ pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh);
+ close_pdeo(de, pdeo);
+ }
+ spin_unlock(&de->pde_unload_lock);
}
static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
{
struct proc_dir_entry *pde = PDE(file_inode(file));
loff_t rv = -EINVAL;
- loff_t (*llseek)(struct file *, loff_t, int);
-
- spin_lock(&pde->pde_unload_lock);
- /*
- * remove_proc_entry() is going to delete PDE (as part of module
- * cleanup sequence). No new callers into module allowed.
- */
- if (!pde->proc_fops) {
- spin_unlock(&pde->pde_unload_lock);
- return rv;
+ if (use_pde(pde)) {
+ loff_t (*llseek)(struct file *, loff_t, int);
+ llseek = pde->proc_fops->llseek;
+ if (!llseek)
+ llseek = default_llseek;
+ rv = llseek(file, offset, whence);
+ unuse_pde(pde);
}
- /*
- * Bump refcount so that remove_proc_entry will wail for ->llseek to
- * complete.
- */
- pde->pde_users++;
- /*
- * Save function pointer under lock, to protect against ->proc_fops
- * NULL'ifying right after ->pde_unload_lock is dropped.
- */
- llseek = pde->proc_fops->llseek;
- spin_unlock(&pde->pde_unload_lock);
-
- if (!llseek)
- llseek = default_llseek;
- rv = llseek(file, offset, whence);
-
- pde_users_dec(pde);
return rv;
}
static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
+ ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
struct proc_dir_entry *pde = PDE(file_inode(file));
ssize_t rv = -EIO;
- ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
-
- spin_lock(&pde->pde_unload_lock);
- if (!pde->proc_fops) {
- spin_unlock(&pde->pde_unload_lock);
- return rv;
+ if (use_pde(pde)) {
+ read = pde->proc_fops->read;
+ if (read)
+ rv = read(file, buf, count, ppos);
+ unuse_pde(pde);
}
- pde->pde_users++;
- read = pde->proc_fops->read;
- spin_unlock(&pde->pde_unload_lock);
-
- if (read)
- rv = read(file, buf, count, ppos);
-
- pde_users_dec(pde);
return rv;
}
static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
{
+ ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
struct proc_dir_entry *pde = PDE(file_inode(file));
ssize_t rv = -EIO;
- ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
-
- spin_lock(&pde->pde_unload_lock);
- if (!pde->proc_fops) {
- spin_unlock(&pde->pde_unload_lock);
- return rv;
+ if (use_pde(pde)) {
+ write = pde->proc_fops->write;
+ if (write)
+ rv = write(file, buf, count, ppos);
+ unuse_pde(pde);
}
- pde->pde_users++;
- write = pde->proc_fops->write;
- spin_unlock(&pde->pde_unload_lock);
-
- if (write)
- rv = write(file, buf, count, ppos);
-
- pde_users_dec(pde);
return rv;
}
@@ -227,20 +232,12 @@ static unsigned int proc_reg_poll(struct file *file, struct poll_table_struct *p
struct proc_dir_entry *pde = PDE(file_inode(file));
unsigned int rv = DEFAULT_POLLMASK;
unsigned int (*poll)(struct file *, struct poll_table_struct *);
-
- spin_lock(&pde->pde_unload_lock);
- if (!pde->proc_fops) {
- spin_unlock(&pde->pde_unload_lock);
- return rv;
+ if (use_pde(pde)) {
+ poll = pde->proc_fops->poll;
+ if (poll)
+ rv = poll(file, pts);
+ unuse_pde(pde);
}
- pde->pde_users++;
- poll = pde->proc_fops->poll;
- spin_unlock(&pde->pde_unload_lock);
-
- if (poll)
- rv = poll(file, pts);
-
- pde_users_dec(pde);
return rv;
}
@@ -249,20 +246,12 @@ static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigne
struct proc_dir_entry *pde = PDE(file_inode(file));
long rv = -ENOTTY;
long (*ioctl)(struct file *, unsigned int, unsigned long);
-
- spin_lock(&pde->pde_unload_lock);
- if (!pde->proc_fops) {
- spin_unlock(&pde->pde_unload_lock);
- return rv;
+ if (use_pde(pde)) {
+ ioctl = pde->proc_fops->unlocked_ioctl;
+ if (ioctl)
+ rv = ioctl(file, cmd, arg);
+ unuse_pde(pde);
}
- pde->pde_users++;
- ioctl = pde->proc_fops->unlocked_ioctl;
- spin_unlock(&pde->pde_unload_lock);
-
- if (ioctl)
- rv = ioctl(file, cmd, arg);
-
- pde_users_dec(pde);
return rv;
}
@@ -272,20 +261,12 @@ static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned
struct proc_dir_entry *pde = PDE(file_inode(file));
long rv = -ENOTTY;
long (*compat_ioctl)(struct file *, unsigned int, unsigned long);
-
- spin_lock(&pde->pde_unload_lock);
- if (!pde->proc_fops) {
- spin_unlock(&pde->pde_unload_lock);
- return rv;
+ if (use_pde(pde)) {
+ compat_ioctl = pde->proc_fops->compat_ioctl;
+ if (compat_ioctl)
+ rv = compat_ioctl(file, cmd, arg);
+ unuse_pde(pde);
}
- pde->pde_users++;
- compat_ioctl = pde->proc_fops->compat_ioctl;
- spin_unlock(&pde->pde_unload_lock);
-
- if (compat_ioctl)
- rv = compat_ioctl(file, cmd, arg);
-
- pde_users_dec(pde);
return rv;
}
#endif
@@ -295,20 +276,12 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
struct proc_dir_entry *pde = PDE(file_inode(file));
int rv = -EIO;
int (*mmap)(struct file *, struct vm_area_struct *);
-
- spin_lock(&pde->pde_unload_lock);
- if (!pde->proc_fops) {
- spin_unlock(&pde->pde_unload_lock);
- return rv;
+ if (use_pde(pde)) {
+ mmap = pde->proc_fops->mmap;
+ if (mmap)
+ rv = mmap(file, vma);
+ unuse_pde(pde);
}
- pde->pde_users++;
- mmap = pde->proc_fops->mmap;
- spin_unlock(&pde->pde_unload_lock);
-
- if (mmap)
- rv = mmap(file, vma);
-
- pde_users_dec(pde);
return rv;
}
@@ -330,91 +303,47 @@ static int proc_reg_open(struct inode *inode, struct file *file)
* by hand in remove_proc_entry(). For this, save opener's credentials
* for later.
*/
- pdeo = kmalloc(sizeof(struct pde_opener), GFP_KERNEL);
+ pdeo = kzalloc(sizeof(struct pde_opener), GFP_KERNEL);
if (!pdeo)
return -ENOMEM;
- spin_lock(&pde->pde_unload_lock);
- if (!pde->proc_fops) {
- spin_unlock(&pde->pde_unload_lock);
+ if (!use_pde(pde)) {
kfree(pdeo);
return -ENOENT;
}
- pde->pde_users++;
open = pde->proc_fops->open;
release = pde->proc_fops->release;
- spin_unlock(&pde->pde_unload_lock);
if (open)
rv = open(inode, file);
- spin_lock(&pde->pde_unload_lock);
if (rv == 0 && release) {
/* To know what to release. */
- pdeo->inode = inode;
pdeo->file = file;
/* Strictly for "too late" ->release in proc_reg_release(). */
- pdeo->release = release;
+ spin_lock(&pde->pde_unload_lock);
list_add(&pdeo->lh, &pde->pde_openers);
+ spin_unlock(&pde->pde_unload_lock);
} else
kfree(pdeo);
- __pde_users_dec(pde);
- spin_unlock(&pde->pde_unload_lock);
- return rv;
-}
-
-static struct pde_opener *find_pde_opener(struct proc_dir_entry *pde,
- struct inode *inode, struct file *file)
-{
- struct pde_opener *pdeo;
- list_for_each_entry(pdeo, &pde->pde_openers, lh) {
- if (pdeo->inode == inode && pdeo->file == file)
- return pdeo;
- }
- return NULL;
+ unuse_pde(pde);
+ return rv;
}
static int proc_reg_release(struct inode *inode, struct file *file)
{
struct proc_dir_entry *pde = PDE(inode);
- int rv = 0;
- int (*release)(struct inode *, struct file *);
struct pde_opener *pdeo;
-
spin_lock(&pde->pde_unload_lock);
- pdeo = find_pde_opener(pde, inode, file);
- if (!pde->proc_fops) {
- /*
- * Can't simply exit, __fput() will think that everything is OK,
- * and move on to freeing struct file. remove_proc_entry() will
- * find slacker in opener's list and will try to do non-trivial
- * things with struct file. Therefore, remove opener from list.
- *
- * But if opener is removed from list, who will ->release it?
- */
- if (pdeo) {
- list_del(&pdeo->lh);
- spin_unlock(&pde->pde_unload_lock);
- rv = pdeo->release(inode, file);
- kfree(pdeo);
- } else
- spin_unlock(&pde->pde_unload_lock);
- return rv;
- }
- pde->pde_users++;
- release = pde->proc_fops->release;
- if (pdeo) {
- list_del(&pdeo->lh);
- kfree(pdeo);
+ list_for_each_entry(pdeo, &pde->pde_openers, lh) {
+ if (pdeo->file == file) {
+ close_pdeo(pde, pdeo);
+ break;
+ }
}
spin_unlock(&pde->pde_unload_lock);
-
- if (release)
- rv = release(inode, file);
-
- pde_users_dec(pde);
- return rv;
+ return 0;
}
static const struct file_operations proc_reg_file_ops = {
@@ -462,8 +391,8 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
inode->i_size = de->size;
if (de->nlink)
set_nlink(inode, de->nlink);
- if (de->proc_iops)
- inode->i_op = de->proc_iops;
+ WARN_ON(!de->proc_iops);
+ inode->i_op = de->proc_iops;
if (de->proc_fops) {
if (S_ISREG(inode->i_mode)) {
#ifdef CONFIG_COMPAT
@@ -506,5 +435,5 @@ int proc_fill_super(struct super_block *s)
return -ENOMEM;
}
- return 0;
+ return proc_setup_self(s);
}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 75710357a517..d600fb098b6a 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -1,4 +1,4 @@
-/* internal.h: internal procfs definitions
+/* Internal procfs definitions
*
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
@@ -9,62 +9,83 @@
* 2 of the License, or (at your option) any later version.
*/
-#include <linux/sched.h>
#include <linux/proc_fs.h>
+#include <linux/proc_ns.h>
+#include <linux/spinlock.h>
+#include <linux/atomic.h>
#include <linux/binfmts.h>
-struct ctl_table_header;
-struct mempolicy;
-extern struct proc_dir_entry proc_root;
-extern void proc_self_init(void);
-#ifdef CONFIG_PROC_SYSCTL
-extern int proc_sys_init(void);
-extern void sysctl_head_put(struct ctl_table_header *head);
-#else
-static inline void proc_sys_init(void) { }
-static inline void sysctl_head_put(struct ctl_table_header *head) { }
-#endif
-#ifdef CONFIG_NET
-extern int proc_net_init(void);
-#else
-static inline int proc_net_init(void) { return 0; }
-#endif
+struct ctl_table_header;
+struct mempolicy;
-extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
- struct pid *pid, struct task_struct *task);
-extern int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
- struct pid *pid, struct task_struct *task);
-extern int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
- struct pid *pid, struct task_struct *task);
-extern int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
- struct pid *pid, struct task_struct *task);
-extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);
+/*
+ * This is not completely implemented yet. The idea is to
+ * create an in-memory tree (like the actual /proc filesystem
+ * 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).
+ */
+struct proc_dir_entry {
+ unsigned int low_ino;
+ umode_t mode;
+ nlink_t nlink;
+ kuid_t uid;
+ kgid_t gid;
+ loff_t size;
+ const struct inode_operations *proc_iops;
+ const struct file_operations *proc_fops;
+ struct proc_dir_entry *next, *parent, *subdir;
+ void *data;
+ atomic_t count; /* use count */
+ atomic_t in_use; /* number of callers into module in progress; */
+ /* negative -> it's going away RSN */
+ struct completion *pde_unload_completion;
+ struct list_head pde_openers; /* who did ->open, but not ->release */
+ spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */
+ u8 namelen;
+ char name[];
+};
-extern const struct file_operations proc_tid_children_operations;
-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;
-extern const struct file_operations proc_tid_numa_maps_operations;
-extern const struct file_operations proc_pid_smaps_operations;
-extern const struct file_operations proc_tid_smaps_operations;
-extern const struct file_operations proc_clear_refs_operations;
-extern const struct file_operations proc_pagemap_operations;
-extern const struct file_operations proc_net_operations;
-extern const struct inode_operations proc_net_inode_operations;
-extern const struct inode_operations proc_pid_link_inode_operations;
+union proc_op {
+ int (*proc_get_link)(struct dentry *, struct path *);
+ int (*proc_read)(struct task_struct *task, char *page);
+ int (*proc_show)(struct seq_file *m,
+ struct pid_namespace *ns, struct pid *pid,
+ struct task_struct *task);
+};
-struct proc_maps_private {
+struct proc_inode {
struct pid *pid;
- struct task_struct *task;
-#ifdef CONFIG_MMU
- struct vm_area_struct *tail_vma;
-#endif
-#ifdef CONFIG_NUMA
- struct mempolicy *task_mempolicy;
-#endif
+ int fd;
+ union proc_op op;
+ struct proc_dir_entry *pde;
+ struct ctl_table_header *sysctl;
+ struct ctl_table *sysctl_entry;
+ struct proc_ns ns;
+ struct inode vfs_inode;
};
-void proc_init_inodecache(void);
+/*
+ * General functions
+ */
+static inline struct proc_inode *PROC_I(const struct inode *inode)
+{
+ return container_of(inode, struct proc_inode, vfs_inode);
+}
+
+static inline struct proc_dir_entry *PDE(const struct inode *inode)
+{
+ return PROC_I(inode)->pde;
+}
+
+static inline void *__PDE_DATA(const struct inode *inode)
+{
+ return PDE(inode)->data;
+}
static inline struct pid *proc_pid(struct inode *inode)
{
@@ -76,11 +97,6 @@ static inline struct task_struct *get_proc_task(struct inode *inode)
return get_pid_task(proc_pid(inode), PIDTYPE_PID);
}
-static inline int proc_fd(struct inode *inode)
-{
- return PROC_I(inode)->fd;
-}
-
static inline int task_dumpable(struct task_struct *task)
{
int dumpable = 0;
@@ -96,15 +112,6 @@ static inline int task_dumpable(struct task_struct *task)
return 0;
}
-static inline int pid_delete_dentry(const struct dentry * dentry)
-{
- /* Is the task we represent dead?
- * If so, then don't put the dentry on the lru list,
- * kill it immediately.
- */
- return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first;
-}
-
static inline unsigned name_to_int(struct dentry *dentry)
{
const char *name = dentry->d_name.name;
@@ -127,63 +134,165 @@ out:
return ~0U;
}
-struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *ino,
- struct dentry *dentry);
-int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
- filldir_t filldir);
+/*
+ * Offset of the first process in the /proc root directory..
+ */
+#define FIRST_PROCESS_ENTRY 256
+
+/* Worst case buffer size needed for holding an integer. */
+#define PROC_NUMBUF 13
-struct pde_opener {
- struct inode *inode;
- struct file *file;
- int (*release)(struct inode *, struct file *);
- struct list_head lh;
-};
-void pde_users_dec(struct proc_dir_entry *pde);
+/*
+ * array.c
+ */
+extern const struct file_operations proc_tid_children_operations;
+extern int proc_tid_stat(struct seq_file *, struct pid_namespace *,
+ struct pid *, struct task_struct *);
+extern int proc_tgid_stat(struct seq_file *, struct pid_namespace *,
+ struct pid *, struct task_struct *);
+extern int proc_pid_status(struct seq_file *, struct pid_namespace *,
+ struct pid *, struct task_struct *);
+extern int proc_pid_statm(struct seq_file *, struct pid_namespace *,
+ struct pid *, struct task_struct *);
+
+/*
+ * base.c
+ */
+extern const struct dentry_operations pid_dentry_operations;
+extern int pid_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int proc_setattr(struct dentry *, struct iattr *);
+extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *);
+extern int pid_revalidate(struct dentry *, unsigned int);
+extern int pid_delete_dentry(const struct dentry *);
+extern int proc_pid_readdir(struct file *, void *, filldir_t);
+extern struct dentry *proc_pid_lookup(struct inode *, struct dentry *, unsigned int);
+extern loff_t mem_lseek(struct file *, loff_t, int);
+
+/* Lookups */
+typedef struct dentry *instantiate_t(struct inode *, struct dentry *,
+ struct task_struct *, const void *);
+extern int proc_fill_cache(struct file *, void *, filldir_t, const char *, int,
+ instantiate_t, struct task_struct *, const void *);
+
+/*
+ * generic.c
+ */
extern spinlock_t proc_subdir_lock;
-struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int);
-int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir);
-unsigned long task_vsize(struct mm_struct *);
-unsigned long task_statm(struct mm_struct *,
- unsigned long *, unsigned long *, unsigned long *, unsigned long *);
-void task_mem(struct seq_file *, struct mm_struct *);
+extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int);
+extern struct dentry *proc_lookup_de(struct proc_dir_entry *, struct inode *,
+ struct dentry *);
+extern int proc_readdir(struct file *, void *, filldir_t);
+extern int proc_readdir_de(struct proc_dir_entry *, struct file *, void *, filldir_t);
static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde)
{
atomic_inc(&pde->count);
return pde;
}
-void pde_put(struct proc_dir_entry *pde);
-
-int proc_fill_super(struct super_block *);
-struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
-int proc_remount(struct super_block *sb, int *flags, char *data);
+extern void pde_put(struct proc_dir_entry *);
/*
- * These are generic /proc routines that use the internal
- * "struct proc_dir_entry" tree to traverse the filesystem.
- *
- * The /proc root directory has extended versions to take care
- * of the /proc/<pid> subdirectories.
+ * inode.c
*/
-int proc_readdir(struct file *, void *, filldir_t);
-struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int);
+struct pde_opener {
+ struct file *file;
+ struct list_head lh;
+ int closing;
+ struct completion *c;
+};
+extern const struct inode_operations proc_pid_link_inode_operations;
+extern void proc_init_inodecache(void);
+extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
+extern int proc_fill_super(struct super_block *);
+extern void proc_entry_rundown(struct proc_dir_entry *);
-/* Lookups */
-typedef struct dentry *instantiate_t(struct inode *, struct dentry *,
- struct task_struct *, const void *);
-int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
- const char *name, int len,
- instantiate_t instantiate, struct task_struct *task, const void *ptr);
-int pid_revalidate(struct dentry *dentry, unsigned int flags);
-struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task);
-extern const struct dentry_operations pid_dentry_operations;
-int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat);
-int proc_setattr(struct dentry *dentry, struct iattr *attr);
+/*
+ * proc_devtree.c
+ */
+#ifdef CONFIG_PROC_DEVICETREE
+extern void proc_device_tree_init(void);
+#endif
+/*
+ * proc_namespaces.c
+ */
extern const struct inode_operations proc_ns_dir_inode_operations;
extern const struct file_operations proc_ns_dir_operations;
+/*
+ * proc_net.c
+ */
+extern const struct file_operations proc_net_operations;
+extern const struct inode_operations proc_net_inode_operations;
+
+#ifdef CONFIG_NET
+extern int proc_net_init(void);
+#else
+static inline int proc_net_init(void) { return 0; }
+#endif
+
+/*
+ * proc_self.c
+ */
+extern int proc_setup_self(struct super_block *);
+
+/*
+ * proc_sysctl.c
+ */
+#ifdef CONFIG_PROC_SYSCTL
+extern int proc_sys_init(void);
+extern void sysctl_head_put(struct ctl_table_header *);
+#else
+static inline void proc_sys_init(void) { }
+static inline void sysctl_head_put(struct ctl_table_header *head) { }
+#endif
+
+/*
+ * proc_tty.c
+ */
+#ifdef CONFIG_TTY
+extern void proc_tty_init(void);
+#else
+static inline void proc_tty_init(void) {}
+#endif
+
+/*
+ * root.c
+ */
+extern struct proc_dir_entry proc_root;
+
+extern void proc_self_init(void);
+extern int proc_remount(struct super_block *, int *, char *);
+
+/*
+ * task_[no]mmu.c
+ */
+struct proc_maps_private {
+ struct pid *pid;
+ struct task_struct *task;
+#ifdef CONFIG_MMU
+ struct vm_area_struct *tail_vma;
+#endif
+#ifdef CONFIG_NUMA
+ struct mempolicy *task_mempolicy;
+#endif
+};
+
+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;
+extern const struct file_operations proc_tid_numa_maps_operations;
+extern const struct file_operations proc_pid_smaps_operations;
+extern const struct file_operations proc_tid_smaps_operations;
+extern const struct file_operations proc_clear_refs_operations;
+extern const struct file_operations proc_pagemap_operations;
+
+extern unsigned long task_vsize(struct mm_struct *);
+extern unsigned long task_statm(struct mm_struct *,
+ unsigned long *, unsigned long *,
+ unsigned long *, unsigned long *);
+extern void task_mem(struct seq_file *, struct mm_struct *);
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index f6a13f489e30..0a22194e5d58 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -11,6 +11,7 @@
#include <linux/mm.h>
#include <linux/proc_fs.h>
+#include <linux/kcore.h>
#include <linux/user.h>
#include <linux/capability.h>
#include <linux/elf.h>
@@ -28,6 +29,7 @@
#include <linux/ioport.h>
#include <linux/memory.h>
#include <asm/sections.h>
+#include "internal.h"
#define CORE_STR "CORE"
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 66b51c0383da..54bdc6701e9f 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -51,7 +51,7 @@ static int ns_delete_dentry(const struct dentry *dentry)
static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
{
struct inode *inode = dentry->d_inode;
- const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
+ const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns.ns_ops;
return dynamic_dname(dentry, buffer, buflen, "%s:[%lu]",
ns_ops->name, inode->i_ino);
@@ -95,8 +95,8 @@ static struct dentry *proc_ns_get_dentry(struct super_block *sb,
inode->i_op = &ns_inode_operations;
inode->i_mode = S_IFREG | S_IRUGO;
inode->i_fop = &ns_file_operations;
- ei->ns_ops = ns_ops;
- ei->ns = ns;
+ ei->ns.ns_ops = ns_ops;
+ ei->ns.ns = ns;
unlock_new_inode(inode);
} else {
ns_ops->put(ns);
@@ -128,7 +128,7 @@ static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
if (!ptrace_may_access(task, PTRACE_MODE_READ))
goto out_put_task;
- ns_path.dentry = proc_ns_get_dentry(sb, task, ei->ns_ops);
+ ns_path.dentry = proc_ns_get_dentry(sb, task, ei->ns.ns_ops);
if (IS_ERR(ns_path.dentry)) {
error = ERR_CAST(ns_path.dentry);
goto out_put_task;
@@ -148,7 +148,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
{
struct inode *inode = dentry->d_inode;
struct proc_inode *ei = PROC_I(inode);
- const struct proc_ns_operations *ns_ops = ei->ns_ops;
+ const struct proc_ns_operations *ns_ops = ei->ns.ns_ops;
struct task_struct *task;
void *ns;
char name[50];
@@ -202,7 +202,7 @@ static struct dentry *proc_ns_instantiate(struct inode *dir,
ei = PROC_I(inode);
inode->i_mode = S_IFLNK|S_IRWXUGO;
inode->i_op = &proc_ns_link_inode_operations;
- ei->ns_ops = ns_ops;
+ ei->ns.ns_ops = ns_ops;
d_set_d_op(dentry, &pid_dentry_operations);
d_add(dentry, inode);
@@ -337,6 +337,11 @@ out_invalid:
return ERR_PTR(-EINVAL);
}
+struct proc_ns *get_proc_ns(struct inode *inode)
+{
+ return &PROC_I(inode)->ns;
+}
+
bool proc_ns_inode(struct inode *inode)
{
return inode->i_fop == &ns_file_operations;
diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c
index 30b590f5bd35..505afc950e0a 100644
--- a/fs/proc/proc_devtree.c
+++ b/fs/proc/proc_devtree.c
@@ -41,7 +41,7 @@ static int property_proc_show(struct seq_file *m, void *v)
static int property_proc_open(struct inode *inode, struct file *file)
{
- return single_open(file, property_proc_show, PDE(inode)->data);
+ return single_open(file, property_proc_show, __PDE_DATA(inode));
}
static const struct file_operations property_proc_fops = {
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index b4ac6572474f..986e83220d56 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -26,6 +26,10 @@
#include "internal.h"
+static inline struct net *PDE_NET(struct proc_dir_entry *pde)
+{
+ return pde->parent->data;
+}
static struct net *get_proc_net(const struct inode *inode)
{
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 9c7fab1d23f0..41a6ea93f486 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -141,6 +141,8 @@ static void proc_kill_sb(struct super_block *sb)
struct pid_namespace *ns;
ns = (struct pid_namespace *)sb->s_fs_info;
+ if (ns->proc_self)
+ dput(ns->proc_self);
kill_anon_super(sb);
put_pid_ns(ns);
}
diff --git a/fs/proc/self.c b/fs/proc/self.c
index aa5cc3bff140..6b6a993b5c25 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -1,6 +1,8 @@
-#include <linux/proc_fs.h>
#include <linux/sched.h>
#include <linux/namei.h>
+#include <linux/slab.h>
+#include <linux/pid_namespace.h>
+#include "internal.h"
/*
* /proc/self:
@@ -48,12 +50,43 @@ static const struct inode_operations proc_self_inode_operations = {
.put_link = proc_self_put_link,
};
-void __init proc_self_init(void)
+static unsigned self_inum;
+
+int proc_setup_self(struct super_block *s)
{
- struct proc_dir_entry *proc_self_symlink;
- mode_t mode;
+ struct inode *root_inode = s->s_root->d_inode;
+ struct pid_namespace *ns = s->s_fs_info;
+ struct dentry *self;
+
+ mutex_lock(&root_inode->i_mutex);
+ self = d_alloc_name(s->s_root, "self");
+ if (self) {
+ struct inode *inode = new_inode_pseudo(s);
+ if (inode) {
+ inode->i_ino = self_inum;
+ inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+ inode->i_mode = S_IFLNK | S_IRWXUGO;
+ inode->i_uid = GLOBAL_ROOT_UID;
+ inode->i_gid = GLOBAL_ROOT_GID;
+ inode->i_op = &proc_self_inode_operations;
+ d_add(self, inode);
+ } else {
+ dput(self);
+ self = ERR_PTR(-ENOMEM);
+ }
+ } else {
+ self = ERR_PTR(-ENOMEM);
+ }
+ mutex_unlock(&root_inode->i_mutex);
+ if (IS_ERR(self)) {
+ pr_err("proc_fill_super: can't allocate /proc/self\n");
+ return PTR_ERR(self);
+ }
+ ns->proc_self = self;
+ return 0;
+}
- mode = S_IFLNK | S_IRWXUGO;
- proc_self_symlink = proc_create("self", mode, NULL, NULL );
- proc_self_symlink->proc_iops = &proc_self_inode_operations;
+void __init proc_self_init(void)
+{
+ proc_alloc_inum(&self_inum);
}
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index b870f740ab5a..17f7e080d7ff 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -8,7 +8,7 @@
*/
#include <linux/mm.h>
-#include <linux/proc_fs.h>
+#include <linux/kcore.h>
#include <linux/user.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
@@ -22,6 +22,7 @@
#include <linux/list.h>
#include <asm/uaccess.h>
#include <asm/io.h>
+#include "internal.h"
/* List representing chunks of contiguous memory areas and their offsets in
* vmcore file.
@@ -698,7 +699,7 @@ void vmcore_cleanup(void)
struct list_head *pos, *next;
if (proc_vmcore) {
- remove_proc_entry(proc_vmcore->name, proc_vmcore->parent);
+ proc_remove(proc_vmcore);
proc_vmcore = NULL;
}