1 files changed, 207 insertions, 146 deletions

diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 75f2890abbd8..9eeccff49b2a 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -1,16 +1,22 @@
-#include <linux/sched.h>
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/dcache.h>
 #include <linux/path.h>
 #include <linux/fdtable.h>
 #include <linux/namei.h>
 #include <linux/pid.h>
+#include <linux/ptrace.h>
+#include <linux/bitmap.h>
 #include <linux/security.h>
 #include <linux/file.h>
 #include <linux/seq_file.h>
+#include <linux/fs.h>
+#include <linux/filelock.h>
 
 #include <linux/proc_fs.h>
 
+#include "../mount.h"
 #include "internal.h"
 #include "fd.h"
 
@@ -25,37 +31,45 @@ static int seq_show(struct seq_file *m, void *v)
 	if (!task)
 		return -ENOENT;
 
-	files = get_files_struct(task);
-	put_task_struct(task);
-
+	task_lock(task);
+	files = task->files;
 	if (files) {
-		int fd = proc_fd(m->private);
+		unsigned int fd = proc_fd(m->private);
 
 		spin_lock(&files->file_lock);
-		file = fcheck_files(files, fd);
+		file = files_lookup_fd_locked(files, fd);
 		if (file) {
-			struct fdtable *fdt = files_fdtable(files);
-
 			f_flags = file->f_flags;
-			if (close_on_exec(fd, fdt))
+			if (close_on_exec(fd, files))
 				f_flags |= O_CLOEXEC;
 
 			get_file(file);
 			ret = 0;
 		}
 		spin_unlock(&files->file_lock);
-		put_files_struct(files);
 	}
+	task_unlock(task);
+	put_task_struct(task);
 
-	if (!ret) {
-                seq_printf(m, "pos:\t%lli\nflags:\t0%o\n",
-			   (long long)file->f_pos, f_flags);
-		if (file->f_op->show_fdinfo)
-			ret = file->f_op->show_fdinfo(m, file);
-		fput(file);
-	}
+	if (ret)
+		return ret;
 
-	return ret;
+	seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\nino:\t%lu\n",
+		   (long long)file->f_pos, f_flags,
+		   real_mount(file->f_path.mnt)->mnt_id,
+		   file_inode(file)->i_ino);
+
+	/* show_fd_locks() never dereferences files, so a stale value is safe */
+	show_fd_locks(m, file, files);
+	if (seq_has_overflowed(m))
+		goto out;
+
+	if (file->f_op->show_fdinfo)
+		file->f_op->show_fdinfo(m, file);
+
+out:
+	fput(file);
+	return 0;
 }
 
 static int seq_fdinfo_open(struct inode *inode, struct file *file)
@@ -63,6 +77,34 @@ static int seq_fdinfo_open(struct inode *inode, struct file *file)
 	return single_open(file, seq_show, inode);
 }
 
+/*
+ * Shared /proc/pid/fdinfo and /proc/pid/fdinfo/fd permission helper to ensure
+ * that the current task has PTRACE_MODE_READ in addition to the normal
+ * POSIX-like checks.
+ */
+static int proc_fdinfo_permission(struct mnt_idmap *idmap, struct inode *inode,
+				  int mask)
+{
+	bool allowed = false;
+	struct task_struct *task = get_proc_task(inode);
+
+	if (!task)
+		return -ESRCH;
+
+	allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
+	put_task_struct(task);
+
+	if (!allowed)
+		return -EACCES;
+
+	return generic_permission(idmap, inode, mask);
+}
+
+static const struct inode_operations proc_fdinfo_file_inode_operations = {
+	.permission	= proc_fdinfo_permission,
+	.setattr	= proc_setattr,
+};
+
 static const struct file_operations proc_fdinfo_file_operations = {
 	.open		= seq_fdinfo_open,
 	.read		= seq_read,
@@ -70,65 +112,57 @@ static const struct file_operations proc_fdinfo_file_operations = {
 	.release	= single_release,
 };
 
-static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
+static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode)
+{
+	struct file *file;
+
+	file = fget_task(task, fd);
+	if (file) {
+		*mode = file->f_mode;
+		fput(file);
+	}
+	return !!file;
+}
+
+static void tid_fd_update_inode(struct task_struct *task, struct inode *inode,
+				fmode_t f_mode)
+{
+	task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
+
+	if (S_ISLNK(inode->i_mode)) {
+		unsigned i_mode = S_IFLNK;
+		if (f_mode & FMODE_READ)
+			i_mode |= S_IRUSR | S_IXUSR;
+		if (f_mode & FMODE_WRITE)
+			i_mode |= S_IWUSR | S_IXUSR;
+		inode->i_mode = i_mode;
+	}
+	security_task_to_inode(task, inode);
+}
+
+static int tid_fd_revalidate(struct inode *dir, const struct qstr *name,
+			     struct dentry *dentry, unsigned int flags)
 {
-	struct files_struct *files;
 	struct task_struct *task;
-	const struct cred *cred;
 	struct inode *inode;
-	int fd;
+	unsigned int fd;
 
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
-	inode = dentry->d_inode;
+	inode = d_inode(dentry);
 	task = get_proc_task(inode);
 	fd = proc_fd(inode);
 
 	if (task) {
-		files = get_files_struct(task);
-		if (files) {
-			struct file *file;
-
-			rcu_read_lock();
-			file = fcheck_files(files, fd);
-			if (file) {
-				unsigned f_mode = file->f_mode;
-
-				rcu_read_unlock();
-				put_files_struct(files);
-
-				if (task_dumpable(task)) {
-					rcu_read_lock();
-					cred = __task_cred(task);
-					inode->i_uid = cred->euid;
-					inode->i_gid = cred->egid;
-					rcu_read_unlock();
-				} else {
-					inode->i_uid = GLOBAL_ROOT_UID;
-					inode->i_gid = GLOBAL_ROOT_GID;
-				}
-
-				if (S_ISLNK(inode->i_mode)) {
-					unsigned i_mode = S_IFLNK;
-					if (f_mode & FMODE_READ)
-						i_mode |= S_IRUSR | S_IXUSR;
-					if (f_mode & FMODE_WRITE)
-						i_mode |= S_IWUSR | S_IXUSR;
-					inode->i_mode = i_mode;
-				}
-
-				security_task_to_inode(task, inode);
-				put_task_struct(task);
-				return 1;
-			}
-			rcu_read_unlock();
-			put_files_struct(files);
+		fmode_t f_mode;
+		if (tid_fd_mode(task, fd, &f_mode)) {
+			tid_fd_update_inode(task, inode, f_mode);
+			put_task_struct(task);
+			return 1;
 		}
 		put_task_struct(task);
 	}
-
-	d_drop(dentry);
 	return 0;
 }
 
@@ -139,63 +173,54 @@ static const struct dentry_operations tid_fd_dentry_operations = {
 
 static int proc_fd_link(struct dentry *dentry, struct path *path)
 {
-	struct files_struct *files = NULL;
 	struct task_struct *task;
 	int ret = -ENOENT;
 
-	task = get_proc_task(dentry->d_inode);
+	task = get_proc_task(d_inode(dentry));
 	if (task) {
-		files = get_files_struct(task);
-		put_task_struct(task);
-	}
-
-	if (files) {
-		int fd = proc_fd(dentry->d_inode);
+		unsigned int fd = proc_fd(d_inode(dentry));
 		struct file *fd_file;
 
-		spin_lock(&files->file_lock);
-		fd_file = fcheck_files(files, fd);
+		fd_file = fget_task(task, fd);
 		if (fd_file) {
 			*path = fd_file->f_path;
 			path_get(&fd_file->f_path);
 			ret = 0;
+			fput(fd_file);
 		}
-		spin_unlock(&files->file_lock);
-		put_files_struct(files);
+		put_task_struct(task);
 	}
 
 	return ret;
 }
 
-static int
-proc_fd_instantiate(struct inode *dir, struct dentry *dentry,
-		    struct task_struct *task, const void *ptr)
+struct fd_data {
+	fmode_t mode;
+	unsigned fd;
+};
+
+static struct dentry *proc_fd_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
 {
-	unsigned fd = (unsigned long)ptr;
+	const struct fd_data *data = ptr;
 	struct proc_inode *ei;
 	struct inode *inode;
 
-	inode = proc_pid_make_inode(dir->i_sb, task);
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK);
 	if (!inode)
-		goto out;
+		return ERR_PTR(-ENOENT);
 
 	ei = PROC_I(inode);
-	ei->fd = fd;
+	ei->fd = data->fd;
 
-	inode->i_mode = S_IFLNK;
 	inode->i_op = &proc_pid_link_inode_operations;
 	inode->i_size = 64;
 
 	ei->op.proc_get_link = proc_fd_link;
+	tid_fd_update_inode(task, inode, data->mode);
 
-	d_set_d_op(dentry, &tid_fd_dentry_operations);
-	d_add(dentry, inode);
-
-	/* Close the race of the process dying before we return the dentry */
-	if (tid_fd_revalidate(dentry, 0))
-		return 0;
- out:
-	return -ENOENT;
+	return proc_splice_unmountable(inode, dentry,
+				       &tid_fd_dentry_operations);
 }
 
 static struct dentry *proc_lookupfd_common(struct inode *dir,
@@ -203,26 +228,27 @@ static struct dentry *proc_lookupfd_common(struct inode *dir,
 					   instantiate_t instantiate)
 {
 	struct task_struct *task = get_proc_task(dir);
-	int result = -ENOENT;
-	unsigned fd = name_to_int(dentry);
+	struct fd_data data = {.fd = name_to_int(&dentry->d_name)};
+	struct dentry *result = ERR_PTR(-ENOENT);
 
 	if (!task)
 		goto out_no_task;
-	if (fd == ~0U)
+	if (data.fd == ~0U)
+		goto out;
+	if (!tid_fd_mode(task, data.fd, &data.mode))
 		goto out;
 
-	result = instantiate(dir, dentry, task, (void *)(unsigned long)fd);
+	result = instantiate(dentry, task, &data);
 out:
 	put_task_struct(task);
 out_no_task:
-	return ERR_PTR(result);
+	return result;
 }
 
 static int proc_readfd_common(struct file *file, struct dir_context *ctx,
 			      instantiate_t instantiate)
 {
 	struct task_struct *p = get_proc_task(file_inode(file));
-	struct files_struct *files;
 	unsigned int fd;
 
 	if (!p)
@@ -230,47 +256,66 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
 
 	if (!dir_emit_dots(file, ctx))
 		goto out;
-	if (!dir_emit_dots(file, ctx))
-		goto out;
-	files = get_files_struct(p);
-	if (!files)
-		goto out;
 
-	rcu_read_lock();
-	for (fd = ctx->pos - 2;
-	     fd < files_fdtable(files)->max_fds;
-	     fd++, ctx->pos++) {
-		char name[PROC_NUMBUF];
-		int len;
-
-		if (!fcheck_files(files, fd))
-			continue;
-		rcu_read_unlock();
-
-		len = snprintf(name, sizeof(name), "%d", fd);
+	for (fd = ctx->pos - 2;; fd++) {
+		struct file *f;
+		struct fd_data data;
+		char name[10 + 1];
+		unsigned int len;
+
+		f = fget_task_next(p, &fd);
+		ctx->pos = fd + 2LL;
+		if (!f)
+			break;
+		data.mode = f->f_mode;
+		fput(f);
+		data.fd = fd;
+
+		len = snprintf(name, sizeof(name), "%u", fd);
 		if (!proc_fill_cache(file, ctx,
 				     name, len, instantiate, p,
-				     (void *)(unsigned long)fd))
-			goto out_fd_loop;
-		rcu_read_lock();
+				     &data))
+			break;
+		cond_resched();
 	}
-	rcu_read_unlock();
-out_fd_loop:
-	put_files_struct(files);
 out:
 	put_task_struct(p);
 	return 0;
 }
 
-static int proc_readfd(struct file *file, struct dir_context *ctx)
+static int proc_readfd_count(struct inode *inode, loff_t *count)
+{
+	struct task_struct *p = get_proc_task(inode);
+	struct fdtable *fdt;
+
+	if (!p)
+		return -ENOENT;
+
+	task_lock(p);
+	if (p->files) {
+		rcu_read_lock();
+
+		fdt = files_fdtable(p->files);
+		*count = bitmap_weight(fdt->open_fds, fdt->max_fds);
+
+		rcu_read_unlock();
+	}
+	task_unlock(p);
+
+	put_task_struct(p);
+
+	return 0;
+}
+
+static int proc_fd_iterate(struct file *file, struct dir_context *ctx)
 {
 	return proc_readfd_common(file, ctx, proc_fd_instantiate);
 }
 
 const struct file_operations proc_fd_operations = {
 	.read		= generic_read_dir,
-	.iterate	= proc_readfd,
-	.llseek		= default_llseek,
+	.iterate_shared	= proc_fd_iterate,
+	.llseek		= generic_file_llseek,
 };
 
 static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
@@ -283,48 +328,63 @@ static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
  * /proc/pid/fd needs a special permission handler so that a process can still
  * access /proc/self/fd after it has executed a setuid().
  */
-int proc_fd_permission(struct inode *inode, int mask)
+int proc_fd_permission(struct mnt_idmap *idmap,
+		       struct inode *inode, int mask)
 {
-	int rv = generic_permission(inode, mask);
+	struct task_struct *p;
+	int rv;
+
+	rv = generic_permission(&nop_mnt_idmap, inode, mask);
 	if (rv == 0)
-		return 0;
-	if (task_pid(current) == proc_pid(inode))
+		return rv;
+
+	rcu_read_lock();
+	p = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (p && same_thread_group(p, current))
 		rv = 0;
+	rcu_read_unlock();
+
 	return rv;
 }
 
+static int proc_fd_getattr(struct mnt_idmap *idmap,
+			const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int query_flags)
+{
+	struct inode *inode = d_inode(path->dentry);
+
+	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
+	return proc_readfd_count(inode, &stat->size);
+}
+
 const struct inode_operations proc_fd_inode_operations = {
 	.lookup		= proc_lookupfd,
 	.permission	= proc_fd_permission,
+	.getattr	= proc_fd_getattr,
 	.setattr	= proc_setattr,
 };
 
-static int
-proc_fdinfo_instantiate(struct inode *dir, struct dentry *dentry,
-			struct task_struct *task, const void *ptr)
+static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
 {
-	unsigned fd = (unsigned long)ptr;
+	const struct fd_data *data = ptr;
 	struct proc_inode *ei;
 	struct inode *inode;
 
-	inode = proc_pid_make_inode(dir->i_sb, task);
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFREG | S_IRUGO);
 	if (!inode)
-		goto out;
+		return ERR_PTR(-ENOENT);
 
 	ei = PROC_I(inode);
-	ei->fd = fd;
+	ei->fd = data->fd;
 
-	inode->i_mode = S_IFREG | S_IRUSR;
-	inode->i_fop = &proc_fdinfo_file_operations;
+	inode->i_op = &proc_fdinfo_file_inode_operations;
 
-	d_set_d_op(dentry, &tid_fd_dentry_operations);
-	d_add(dentry, inode);
+	inode->i_fop = &proc_fdinfo_file_operations;
+	tid_fd_update_inode(task, inode, 0);
 
-	/* Close the race of the process dying before we return the dentry */
-	if (tid_fd_revalidate(dentry, 0))
-		return 0;
- out:
-	return -ENOENT;
+	return proc_splice_unmountable(inode, dentry,
+				       &tid_fd_dentry_operations);
 }
 
 static struct dentry *
@@ -333,7 +393,7 @@ proc_lookupfdinfo(struct inode *dir, struct dentry *dentry, unsigned int flags)
 	return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
 }
 
-static int proc_readfdinfo(struct file *file, struct dir_context *ctx)
+static int proc_fdinfo_iterate(struct file *file, struct dir_context *ctx)
 {
 	return proc_readfd_common(file, ctx,
 				  proc_fdinfo_instantiate);
@@ -341,11 +401,12 @@ static int proc_readfdinfo(struct file *file, struct dir_context *ctx)
 
 const struct inode_operations proc_fdinfo_inode_operations = {
 	.lookup		= proc_lookupfdinfo,
+	.permission	= proc_fdinfo_permission,
 	.setattr	= proc_setattr,
 };
 
 const struct file_operations proc_fdinfo_operations = {
 	.read		= generic_read_dir,
-	.iterate	= proc_readfdinfo,
-	.llseek		= default_llseek,
+	.iterate_shared	= proc_fdinfo_iterate,
+	.llseek		= generic_file_llseek,
 };