Merge branch 'work.fdtable' into vfs.file

Bring in the fdtable changes for this cycle.

Signed-off-by: Christian Brauner <brauner@kernel.org>

26 files changed, 88 insertions, 198 deletions

diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 18daafbe2e65..301ee7d8b7df 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -73,9 +73,7 @@ static struct spu_context *coredump_next_context(int *fd)
 		return NULL;
 	*fd = n - 1;
 
-	rcu_read_lock();
-	file = lookup_fdget_rcu(*fd);
-	rcu_read_unlock();
+	file = fget_raw(*fd);
 	if (file) {
 		ctx = SPUFS_I(file_inode(file))->i_ctx;
 		get_spu_context(ctx);
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 22dd9dcce7ec..8928874c8a2e 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -12,7 +12,6 @@
 #include <linux/fs.h>
 #include <linux/filelock.h>
 #include <linux/file.h>
-#include <linux/fdtable.h>
 #include <linux/capability.h>
 #include <linux/dnotify.h>
 #include <linux/slab.h>
diff --git a/fs/file.c b/fs/file.c
index 9598c577f713..efd9959b03c2 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -152,18 +152,11 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
  * 'unsigned long' in some places, but simply because that is how the Linux
  * kernel bitmaps are defined to work: they are not "bits in an array of bytes",
  * they are very much "bits in an array of unsigned long".
- *
- * The ALIGN(nr, BITS_PER_LONG) here is for clarity: since we just multiplied
- * by that "1024/sizeof(ptr)" before, we already know there are sufficient
- * clear low bits. Clang seems to realize that, gcc ends up being confused.
- *
- * On a 128-bit machine, the ALIGN() would actually matter. In the meantime,
- * let's consider it documentation (and maybe a test-case for gcc to improve
- * its code generation ;)
  */
-static struct fdtable * alloc_fdtable(unsigned int nr)
+static struct fdtable *alloc_fdtable(unsigned int slots_wanted)
 {
 	struct fdtable *fdt;
+	unsigned int nr;
 	void *data;
 
 	/*
@@ -171,22 +164,32 @@ static struct fdtable * alloc_fdtable(unsigned int nr)
 	 * Allocation steps are keyed to the size of the fdarray, since it
 	 * grows far faster than any of the other dynamic data. We try to fit
 	 * the fdarray into comfortable page-tuned chunks: starting at 1024B
-	 * and growing in powers of two from there on.
+	 * and growing in powers of two from there on.  Since we called only
+	 * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab
+	 * already gives BITS_PER_LONG slots), the above boils down to
+	 * 1.  use the smallest power of two large enough to give us that many
+	 * slots.
+	 * 2.  on 32bit skip 64 and 128 - the minimal capacity we want there is
+	 * 256 slots (i.e. 1Kb fd array).
+	 * 3.  on 64bit don't skip anything, 1Kb fd array means 128 slots there
+	 * and we are never going to be asked for 64 or less.
 	 */
-	nr /= (1024 / sizeof(struct file *));
-	nr = roundup_pow_of_two(nr + 1);
-	nr *= (1024 / sizeof(struct file *));
-	nr = ALIGN(nr, BITS_PER_LONG);
+	if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256)
+		nr = 256;
+	else
+		nr = roundup_pow_of_two(slots_wanted);
 	/*
 	 * Note that this can drive nr *below* what we had passed if sysctl_nr_open
-	 * had been set lower between the check in expand_files() and here.  Deal
-	 * with that in caller, it's cheaper that way.
+	 * had been set lower between the check in expand_files() and here.
 	 *
 	 * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise
 	 * bitmaps handling below becomes unpleasant, to put it mildly...
 	 */
-	if (unlikely(nr > sysctl_nr_open))
-		nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1;
+	if (unlikely(nr > sysctl_nr_open)) {
+		nr = round_down(sysctl_nr_open, BITS_PER_LONG);
+		if (nr < slots_wanted)
+			return ERR_PTR(-EMFILE);
+	}
 
 	fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT);
 	if (!fdt)
@@ -215,14 +218,14 @@ out_arr:
 out_fdt:
 	kfree(fdt);
 out:
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 
 /*
  * Expand the file descriptor table.
  * This function will allocate a new fdtable and both fd array and fdset, of
  * the given size.
- * Return <0 error code on error; 1 on successful completion.
+ * Return <0 error code on error; 0 on successful completion.
  * The files->file_lock should be held on entry, and will be held on exit.
  */
 static int expand_fdtable(struct files_struct *files, unsigned int nr)
@@ -232,7 +235,7 @@ static int expand_fdtable(struct files_struct *files, unsigned int nr)
 	struct fdtable *new_fdt, *cur_fdt;
 
 	spin_unlock(&files->file_lock);
-	new_fdt = alloc_fdtable(nr);
+	new_fdt = alloc_fdtable(nr + 1);
 
 	/* make sure all fd_install() have seen resize_in_progress
 	 * or have finished their rcu_read_lock_sched() section.
@@ -241,16 +244,8 @@ static int expand_fdtable(struct files_struct *files, unsigned int nr)
 		synchronize_rcu();
 
 	spin_lock(&files->file_lock);
-	if (!new_fdt)
-		return -ENOMEM;
-	/*
-	 * extremely unlikely race - sysctl_nr_open decreased between the check in
-	 * caller and alloc_fdtable().  Cheaper to catch it here...
-	 */
-	if (unlikely(new_fdt->max_fds <= nr)) {
-		__free_fdtable(new_fdt);
-		return -EMFILE;
-	}
+	if (IS_ERR(new_fdt))
+		return PTR_ERR(new_fdt);
 	cur_fdt = files_fdtable(files);
 	BUG_ON(nr < cur_fdt->max_fds);
 	copy_fdtable(new_fdt, cur_fdt);
@@ -259,15 +254,14 @@ static int expand_fdtable(struct files_struct *files, unsigned int nr)
 		call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
 	/* coupled with smp_rmb() in fd_install() */
 	smp_wmb();
-	return 1;
+	return 0;
 }
 
 /*
  * Expand files.
  * This function will expand the file structures, if the requested size exceeds
  * the current capacity and there is room for expansion.
- * Return <0 error code on error; 0 when nothing done; 1 when files were
- * expanded and execution may have blocked.
+ * Return <0 error code on error; 0 on success.
  * The files->file_lock should be held on entry, and will be held on exit.
  */
 static int expand_files(struct files_struct *files, unsigned int nr)
@@ -275,14 +269,14 @@ static int expand_files(struct files_struct *files, unsigned int nr)
 	__acquires(files->file_lock)
 {
 	struct fdtable *fdt;
-	int expanded = 0;
+	int error;
 
 repeat:
 	fdt = files_fdtable(files);
 
 	/* Do we need to expand? */
 	if (nr < fdt->max_fds)
-		return expanded;
+		return 0;
 
 	/* Can we expand? */
 	if (nr >= sysctl_nr_open)
@@ -290,7 +284,6 @@ repeat:
 
 	if (unlikely(files->resize_in_progress)) {
 		spin_unlock(&files->file_lock);
-		expanded = 1;
 		wait_event(files->resize_wait, !files->resize_in_progress);
 		spin_lock(&files->file_lock);
 		goto repeat;
@@ -298,27 +291,28 @@ repeat:
 
 	/* All good, so we try */
 	files->resize_in_progress = true;
-	expanded = expand_fdtable(files, nr);
+	error = expand_fdtable(files, nr);
 	files->resize_in_progress = false;
 
 	wake_up_all(&files->resize_wait);
-	return expanded;
-}
-
-static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt)
-{
-	__set_bit(fd, fdt->close_on_exec);
+	return error;
 }
 
-static inline void __clear_close_on_exec(unsigned int fd, struct fdtable *fdt)
+static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt,
+				       bool set)
 {
-	if (test_bit(fd, fdt->close_on_exec))
-		__clear_bit(fd, fdt->close_on_exec);
+	if (set) {
+		__set_bit(fd, fdt->close_on_exec);
+	} else {
+		if (test_bit(fd, fdt->close_on_exec))
+			__clear_bit(fd, fdt->close_on_exec);
+	}
 }
 
-static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt)
+static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt, bool set)
 {
 	__set_bit(fd, fdt->open_fds);
+	__set_close_on_exec(fd, fdt, set);
 	fd /= BITS_PER_LONG;
 	if (!~fdt->open_fds[fd])
 		__set_bit(fd, fdt->full_fds_bits);
@@ -327,7 +321,9 @@ static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt)
 static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt)
 {
 	__clear_bit(fd, fdt->open_fds);
-	__clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits);
+	fd /= BITS_PER_LONG;
+	if (test_bit(fd, fdt->full_fds_bits))
+		__clear_bit(fd, fdt->full_fds_bits);
 }
 
 static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt)
@@ -369,7 +365,6 @@ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_ho
 	struct file **old_fds, **new_fds;
 	unsigned int open_files, i;
 	struct fdtable *old_fdt, *new_fdt;
-	int error;
 
 	newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
 	if (!newf)
@@ -401,17 +396,10 @@ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_ho
 		if (new_fdt != &newf->fdtab)
 			__free_fdtable(new_fdt);
 
-		new_fdt = alloc_fdtable(open_files - 1);
-		if (!new_fdt) {
-			error = -ENOMEM;
-			goto out_release;
-		}
-
-		/* beyond sysctl_nr_open; nothing to do */
-		if (unlikely(new_fdt->max_fds < open_files)) {
-			__free_fdtable(new_fdt);
-			error = -EMFILE;
-			goto out_release;
+		new_fdt = alloc_fdtable(open_files);
+		if (IS_ERR(new_fdt)) {
+			kmem_cache_free(files_cachep, newf);
+			return ERR_CAST(new_fdt);
 		}
 
 		/*
@@ -452,10 +440,6 @@ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_ho
 	rcu_assign_pointer(newf->fdt, new_fdt);
 
 	return newf;
-
-out_release:
-	kmem_cache_free(files_cachep, newf);
-	return ERR_PTR(error);
 }
 
 static struct fdtable *close_files(struct files_struct * files)
@@ -476,7 +460,7 @@ static struct fdtable *close_files(struct files_struct * files)
 		set = fdt->open_fds[j++];
 		while (set) {
 			if (set & 1) {
-				struct file * file = xchg(&fdt->fd[i], NULL);
+				struct file *file = fdt->fd[i];
 				if (file) {
 					filp_close(file, files);
 					cond_resched();
@@ -533,6 +517,15 @@ static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start)
 	unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */
 	unsigned int maxbit = maxfd / BITS_PER_LONG;
 	unsigned int bitbit = start / BITS_PER_LONG;
+	unsigned int bit;
+
+	/*
+	 * Try to avoid looking at the second level bitmap
+	 */
+	bit = find_next_zero_bit(&fdt->open_fds[bitbit], BITS_PER_LONG,
+				 start & (BITS_PER_LONG - 1));
+	if (bit < BITS_PER_LONG)
+		return bit + bitbit * BITS_PER_LONG;
 
 	bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG;
 	if (bitbit >= maxfd)
@@ -559,7 +552,7 @@ repeat:
 	if (fd < files->next_fd)
 		fd = files->next_fd;
 
-	if (fd < fdt->max_fds)
+	if (likely(fd < fdt->max_fds))
 		fd = find_next_fd(fdt, fd);
 
 	/*
@@ -567,36 +560,22 @@ repeat:
 	 * will limit the total number of files that can be opened.
 	 */
 	error = -EMFILE;
-	if (fd >= end)
+	if (unlikely(fd >= end))
 		goto out;
 
-	error = expand_files(files, fd);
-	if (error < 0)
-		goto out;
+	if (unlikely(fd >= fdt->max_fds)) {
+		error = expand_files(files, fd);
+		if (error < 0)
+			goto out;
 
-	/*
-	 * If we needed to expand the fs array we
-	 * might have blocked - try again.
-	 */
-	if (error)
 		goto repeat;
+	}
 
 	if (start <= files->next_fd)
 		files->next_fd = fd + 1;
 
-	__set_open_fd(fd, fdt);
-	if (flags & O_CLOEXEC)
-		__set_close_on_exec(fd, fdt);
-	else
-		__clear_close_on_exec(fd, fdt);
+	__set_open_fd(fd, fdt, flags & O_CLOEXEC);
 	error = fd;
-#if 1
-	/* Sanity check */
-	if (rcu_access_pointer(fdt->fd[fd]) != NULL) {
-		printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd);
-		rcu_assign_pointer(fdt->fd[fd], NULL);
-	}
-#endif
 
 out:
 	spin_unlock(&files->file_lock);
@@ -662,7 +641,7 @@ void fd_install(unsigned int fd, struct file *file)
 		rcu_read_unlock_sched();
 		spin_lock(&files->file_lock);
 		fdt = files_fdtable(files);
-		BUG_ON(fdt->fd[fd] != NULL);
+		WARN_ON(fdt->fd[fd] != NULL);
 		rcu_assign_pointer(fdt->fd[fd], file);
 		spin_unlock(&files->file_lock);
 		return;
@@ -776,7 +755,7 @@ static inline void __range_close(struct files_struct *files, unsigned int fd,
 }
 
 /**
- * __close_range() - Close all file descriptors in a given range.
+ * sys_close_range() - Close all file descriptors in a given range.
  *
  * @fd:     starting file descriptor to close
  * @max_fd: last file descriptor to close
@@ -784,8 +763,10 @@ static inline void __range_close(struct files_struct *files, unsigned int fd,
  *
  * This closes a range of file descriptors. All file descriptors
  * from @fd up to and including @max_fd are closed.
+ * Currently, errors to close a given file descriptor are ignored.
  */
-int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
+SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd,
+		unsigned int, flags)
 {
 	struct task_struct *me = current;
 	struct files_struct *cur_fds = me->files, *fds = NULL;
@@ -1100,29 +1081,7 @@ struct file *fget_task(struct task_struct *task, unsigned int fd)
 	return file;
 }
 
-struct file *lookup_fdget_rcu(unsigned int fd)
-{
-	return __fget_files_rcu(current->files, fd, 0);
-
-}
-EXPORT_SYMBOL_GPL(lookup_fdget_rcu);
-
-struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd)
-{
-	/* Must be called with rcu_read_lock held */
-	struct files_struct *files;
-	struct file *file = NULL;
-
-	task_lock(task);
-	files = task->files;
-	if (files)
-		file = __fget_files_rcu(files, fd, 0);
-	task_unlock(task);
-
-	return file;
-}
-
-struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *ret_fd)
+struct file *fget_task_next(struct task_struct *task, unsigned int *ret_fd)
 {
 	/* Must be called with rcu_read_lock held */
 	struct files_struct *files;
@@ -1132,17 +1091,19 @@ struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *
 	task_lock(task);
 	files = task->files;
 	if (files) {
+		rcu_read_lock();
 		for (; fd < files_fdtable(files)->max_fds; fd++) {
 			file = __fget_files_rcu(files, fd, 0);
 			if (file)
 				break;
 		}
+		rcu_read_unlock();
 	}
 	task_unlock(task);
 	*ret_fd = fd;
 	return file;
 }
-EXPORT_SYMBOL(task_lookup_next_fdget_rcu);
+EXPORT_SYMBOL(fget_task_next);
 
 /*
  * Lightweight file lookup - no refcnt increment if fd table isn't shared.
@@ -1239,13 +1200,8 @@ void __f_unlock_pos(struct file *f)
 void set_close_on_exec(unsigned int fd, int flag)
 {
 	struct files_struct *files = current->files;
-	struct fdtable *fdt;
 	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
-	if (flag)
-		__set_close_on_exec(fd, fdt);
-	else
-		__clear_close_on_exec(fd, fdt);
+	__set_close_on_exec(fd, files_fdtable(files), flag);
 	spin_unlock(&files->file_lock);
 }
 
@@ -1286,11 +1242,7 @@ __releases(&files->file_lock)
 		goto Ebusy;
 	get_file(file);
 	rcu_assign_pointer(fdt->fd[fd], file);
-	__set_open_fd(fd, fdt);
-	if (flags & O_CLOEXEC)
-		__set_close_on_exec(fd, fdt);
-	else
-		__clear_close_on_exec(fd, fdt);
+	__set_open_fd(fd, fdt, flags & O_CLOEXEC);
 	spin_unlock(&files->file_lock);
 
 	if (tofree)
diff --git a/fs/file_table.c b/fs/file_table.c
index db4fde6fe620..976736be47cb 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -9,7 +9,6 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/file.h>
-#include <linux/fdtable.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/fs.h>
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 269c3bc7fced..4701c4aafbf4 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -34,7 +34,6 @@
 #include <linux/lockref.h>
 #include <linux/rhashtable.h>
 #include <linux/pid_namespace.h>
-#include <linux/fdtable.h>
 #include <linux/file.h>
 
 #include "gfs2.h"
@@ -2768,25 +2767,18 @@ static struct file *gfs2_glockfd_next_file(struct gfs2_glockfd_iter *i)
 		i->file = NULL;
 	}
 
-	rcu_read_lock();
 	for(;; i->fd++) {
-		struct inode *inode;
-
-		i->file = task_lookup_next_fdget_rcu(i->task, &i->fd);
+		i->file = fget_task_next(i->task, &i->fd);
 		if (!i->file) {
 			i->fd = 0;
 			break;
 		}
 
-		inode = file_inode(i->file);
-		if (inode->i_sb == i->sb)
+		if (file_inode(i->file)->i_sb == i->sb)
 			break;
 
-		rcu_read_unlock();
 		fput(i->file);
-		rcu_read_lock();
 	}
-	rcu_read_unlock();
 	return i->file;
 }
 
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index d5dbef7f5c95..6004dfdfdf0f 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -16,7 +16,6 @@
 #include <linux/security.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
-#include <linux/fdtable.h>
 #include <linux/fsnotify_backend.h>
 
 static int dir_notify_enable __read_mostly = 1;
@@ -347,9 +346,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg)
 		new_fsn_mark = NULL;
 	}
 
-	rcu_read_lock();
-	f = lookup_fdget_rcu(fd);
-	rcu_read_unlock();
+	f = fget_raw(fd);
 
 	/* if (f != filp) means that we lost a race and another task/thread
 	 * actually closed the fd we are still playing with before we grabbed
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 224bccaab4cc..24c7c5df4998 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/fanotify.h>
-#include <linux/fdtable.h>
 #include <linux/fsnotify_backend.h>
 #include <linux/init.h>
 #include <linux/jiffies.h>
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 9644bc72e457..61b83039771e 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/fanotify.h>
 #include <linux/fcntl.h>
-#include <linux/fdtable.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/anon_inodes.h>
diff --git a/fs/open.c b/fs/open.c
index acaeb3e25c88..62dd1383d6f9 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1574,23 +1574,6 @@ SYSCALL_DEFINE1(close, unsigned int, fd)
 	return retval;
 }
 
-/**
- * sys_close_range() - Close all file descriptors in a given range.
- *
- * @fd:     starting file descriptor to close
- * @max_fd: last file descriptor to close
- * @flags:  reserved for future extensions
- *
- * This closes a range of file descriptors. All file descriptors
- * from @fd up to and including @max_fd are closed.
- * Currently, errors to close a given file descriptor are ignored.
- */
-SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd,
-		unsigned int, flags)
-{
-	return __close_range(fd, max_fd, flags);
-}
-
 /*
  * This routine simulates a hangup on the tty, to arrange that users
  * are given clean terminals at login time.
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 2ed6ad641a20..ee2cbd044ce6 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -16,7 +16,6 @@
 #include <linux/sched/signal.h>
 #include <linux/cred.h>
 #include <linux/namei.h>
-#include <linux/fdtable.h>
 #include <linux/ratelimit.h>
 #include <linux/exportfs.h>
 #include "overlayfs.h"
diff --git a/fs/proc/base.c b/fs/proc/base.c
index b31283d81c52..e9d7ddc52f69 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -58,7 +58,6 @@
 #include <linux/init.h>
 #include <linux/capability.h>
 #include <linux/file.h>
-#include <linux/fdtable.h>
 #include <linux/generic-radix-tree.h>
 #include <linux/string.h>
 #include <linux/seq_file.h>
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 1f54a54bfb91..18d0dddc8e2f 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -116,9 +116,7 @@ static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode)
 {
 	struct file *file;
 
-	rcu_read_lock();
-	file = task_lookup_fdget_rcu(task, fd);
-	rcu_read_unlock();
+	file = fget_task(task, fd);
 	if (file) {
 		*mode = file->f_mode;
 		fput(file);
@@ -258,19 +256,17 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
 	if (!dir_emit_dots(file, ctx))
 		goto out;
 
-	rcu_read_lock();
 	for (fd = ctx->pos - 2;; fd++) {
 		struct file *f;
 		struct fd_data data;
 		char name[10 + 1];
 		unsigned int len;
 
-		f = task_lookup_next_fdget_rcu(p, &fd);
+		f = fget_task_next(p, &fd);
 		ctx->pos = fd + 2LL;
 		if (!f)
 			break;
 		data.mode = f->f_mode;
-		rcu_read_unlock();
 		fput(f);
 		data.fd = fd;
 
@@ -278,11 +274,9 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
 		if (!proc_fill_cache(file, ctx,
 				     name, len, instantiate, p,
 				     &data))
-			goto out;
+			break;
 		cond_resched();
-		rcu_read_lock();
 	}
-	rcu_read_unlock();
 out:
 	put_task_struct(p);
 	return 0;
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index b1c5722f2b3c..c45306a9f007 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -92,10 +92,6 @@ static inline struct file *files_lookup_fd_locked(struct files_struct *files, un
 	return files_lookup_fd_raw(files, fd);
 }
 
-struct file *lookup_fdget_rcu(unsigned int fd);
-struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd);
-struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *fd);
-
 static inline bool close_on_exec(unsigned int fd, const struct files_struct *files)
 {
 	return test_bit(fd, files_fdtable(files)->close_on_exec);
@@ -115,7 +111,6 @@ int iterate_fd(struct files_struct *, unsigned,
 		const void *);
 
 extern int close_fd(unsigned int fd);
-extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
 extern struct file *file_close_fd(unsigned int fd);
 
 extern struct kmem_cache *files_cachep;
diff --git a/include/linux/file.h b/include/linux/file.h
index f98de143245a..ec4ad5e6a061 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -72,6 +72,7 @@ static inline void fdput(struct fd fd)
 extern struct file *fget(unsigned int fd);
 extern struct file *fget_raw(unsigned int fd);
 extern struct file *fget_task(struct task_struct *task, unsigned int fd);
+extern struct file *fget_task_next(struct task_struct *task, unsigned int *fd);
 extern void __f_unlock_pos(struct file *);
 
 struct fd fdget(unsigned int fd);
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index b2736e3491b8..5a1676bab998 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -51,7 +51,6 @@
 #include <linux/sched/signal.h>
 #include <linux/fs.h>
 #include <linux/file.h>
-#include <linux/fdtable.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/percpu.h>
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 29da6d3838f6..e16e79f8cd6d 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -16,7 +16,6 @@
 #include <uapi/linux/btf.h>
 #include <linux/bpf_lsm.h>
 #include <linux/btf_ids.h>
-#include <linux/fdtable.h>
 #include <linux/rcupdate_trace.h>
 
 DEFINE_BPF_STORAGE_CACHE(inode_cache);
diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c
index adf6dfe0ba68..1eb9852a9f8e 100644
--- a/kernel/bpf/bpf_task_storage.c
+++ b/kernel/bpf/bpf_task_storage.c
@@ -16,7 +16,6 @@
 #include <linux/filter.h>
 #include <uapi/linux/btf.h>
 #include <linux/btf_ids.h>
-#include <linux/fdtable.h>
 #include <linux/rcupdate_trace.h>
 
 DEFINE_BPF_STORAGE_CACHE(task_cache);
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 02aa9db8d796..7fe602ca74a0 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -5,7 +5,6 @@
 #include <linux/namei.h>
 #include <linux/pid_namespace.h>
 #include <linux/fs.h>
-#include <linux/fdtable.h>
 #include <linux/filter.h>
 #include <linux/bpf_mem_alloc.h>
 #include <linux/btf_ids.h>
@@ -286,17 +285,14 @@ again:
 			curr_fd = 0;
 	}
 
-	rcu_read_lock();
-	f = task_lookup_next_fdget_rcu(curr_task, &curr_fd);
+	f = fget_task_next(curr_task, &curr_fd);
 	if (f) {
 		/* set info->fd */
 		info->fd = curr_fd;
-		rcu_read_unlock();
 		return f;
 	}
 
 	/* the current task is done, go to the next task */
-	rcu_read_unlock();
 	put_task_struct(curr_task);
 
 	if (info->common.type == BPF_TASK_ITER_TID) {
diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c
index dcbec1a0dfb3..26057aa13503 100644
--- a/kernel/bpf/token.c
+++ b/kernel/bpf/token.c
@@ -1,6 +1,5 @@
 #include <linux/bpf.h>
 #include <linux/vmalloc.h>
-#include <linux/fdtable.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/kernel.h>
diff --git a/kernel/exit.c b/kernel/exit.c
index 619f0014c33b..1dcddfe537ee 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -25,7 +25,6 @@
 #include <linux/acct.h>
 #include <linux/tsacct_kern.h>
 #include <linux/file.h>
-#include <linux/fdtable.h>
 #include <linux/freezer.h>
 #include <linux/binfmts.h>
 #include <linux/nsproxy.h>
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index b0639f21041f..2c596851f8a9 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -63,9 +63,7 @@ get_file_raw_ptr(struct task_struct *task, unsigned int idx)
 {
 	struct file *file;
 
-	rcu_read_lock();
-	file = task_lookup_fdget_rcu(task, idx);
-	rcu_read_unlock();
+	file = fget_task(task, idx);
 	if (file)
 		fput(file);
 
diff --git a/kernel/module/dups.c b/kernel/module/dups.c
index 9a92f2f8c9d3..bd2149fbe117 100644
--- a/kernel/module/dups.c
+++ b/kernel/module/dups.c
@@ -18,7 +18,6 @@
 #include <linux/completion.h>
 #include <linux/cred.h>
 #include <linux/file.h>
-#include <linux/fdtable.h>
 #include <linux/workqueue.h>
 #include <linux/security.h>
 #include <linux/mount.h>
diff --git a/kernel/module/kmod.c b/kernel/module/kmod.c
index 0800d9891692..25f253812512 100644
--- a/kernel/module/kmod.c
+++ b/kernel/module/kmod.c
@@ -15,7 +15,6 @@
 #include <linux/completion.h>
 #include <linux/cred.h>
 #include <linux/file.h>
-#include <linux/fdtable.h>
 #include <linux/workqueue.h>
 #include <linux/security.h>
 #include <linux/mount.h>
diff --git a/kernel/umh.c b/kernel/umh.c
index ff1f13a27d29..be9234270777 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -13,7 +13,6 @@
 #include <linux/completion.h>
 #include <linux/cred.h>
 #include <linux/file.h>
-#include <linux/fdtable.h>
 #include <linux/fs_struct.h>
 #include <linux/workqueue.h>
 #include <linux/security.h>
diff --git a/net/handshake/request.c b/net/handshake/request.c
index 94d5cef3e048..274d2c89b6b2 100644
--- a/net/handshake/request.c
+++ b/net/handshake/request.c
@@ -13,7 +13,6 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/inet.h>
-#include <linux/fdtable.h>
 #include <linux/rhashtable.h>
 
 #include <net/sock.h>
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 571158ec6188..2bc34dce9a46 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -9,7 +9,6 @@
  */
 
 #include <linux/errno.h>
-#include <linux/fdtable.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/mount.h>