1 files changed, 295 insertions, 272 deletions

diff --git a/fs/file.c b/fs/file.c
index 3b683b9101d8..3a3146664cf3 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -20,10 +20,79 @@
 #include <linux/spinlock.h>
 #include <linux/rcupdate.h>
 #include <linux/close_range.h>
+#include <linux/file_ref.h>
 #include <net/sock.h>
+#include <linux/init_task.h>
 
 #include "internal.h"
 
+static noinline bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt)
+{
+	/*
+	 * If the reference count was already in the dead zone, then this
+	 * put() operation is imbalanced. Warn, put the reference count back to
+	 * DEAD and tell the caller to not deconstruct the object.
+	 */
+	if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) {
+		atomic_long_set(&ref->refcnt, FILE_REF_DEAD);
+		return false;
+	}
+
+	/*
+	 * This is a put() operation on a saturated refcount. Restore the
+	 * mean saturation value and tell the caller to not deconstruct the
+	 * object.
+	 */
+	if (cnt > FILE_REF_MAXREF)
+		atomic_long_set(&ref->refcnt, FILE_REF_SATURATED);
+	return false;
+}
+
+/**
+ * __file_ref_put - Slowpath of file_ref_put()
+ * @ref:	Pointer to the reference count
+ * @cnt:	Current reference count
+ *
+ * Invoked when the reference count is outside of the valid zone.
+ *
+ * Return:
+ *	True if this was the last reference with no future references
+ *	possible. This signals the caller that it can safely schedule the
+ *	object, which is protected by the reference counter, for
+ *	deconstruction.
+ *
+ *	False if there are still active references or the put() raced
+ *	with a concurrent get()/put() pair. Caller is not allowed to
+ *	deconstruct the protected object.
+ */
+bool __file_ref_put(file_ref_t *ref, unsigned long cnt)
+{
+	/* Did this drop the last reference? */
+	if (likely(cnt == FILE_REF_NOREF)) {
+		/*
+		 * Carefully try to set the reference count to FILE_REF_DEAD.
+		 *
+		 * This can fail if a concurrent get() operation has
+		 * elevated it again or the corresponding put() even marked
+		 * it dead already. Both are valid situations and do not
+		 * require a retry. If this fails the caller is not
+		 * allowed to deconstruct the object.
+		 */
+		if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD))
+			return false;
+
+		/*
+		 * The caller can safely schedule the object for
+		 * deconstruction. Provide acquire ordering.
+		 */
+		smp_acquire__after_ctrl_dep();
+		return true;
+	}
+
+	return __file_ref_put_badval(ref, cnt);
+}
+EXPORT_SYMBOL_GPL(__file_ref_put);
+
 unsigned int sysctl_nr_open __read_mostly = 1024*1024;
 unsigned int sysctl_nr_open_min = BITS_PER_LONG;
 /* our min() is unusable in constant expressions ;-/ */
@@ -46,27 +115,23 @@ static void free_fdtable_rcu(struct rcu_head *rcu)
 #define BITBIT_NR(nr)	BITS_TO_LONGS(BITS_TO_LONGS(nr))
 #define BITBIT_SIZE(nr)	(BITBIT_NR(nr) * sizeof(long))
 
+#define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds
 /*
  * Copy 'count' fd bits from the old table to the new table and clear the extra
  * space if any.  This does not copy the file pointers.  Called with the files
  * spinlock held for write.
  */
-static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
-			    unsigned int count)
+static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
+			    unsigned int copy_words)
 {
-	unsigned int cpy, set;
-
-	cpy = count / BITS_PER_BYTE;
-	set = (nfdt->max_fds - count) / BITS_PER_BYTE;
-	memcpy(nfdt->open_fds, ofdt->open_fds, cpy);
-	memset((char *)nfdt->open_fds + cpy, 0, set);
-	memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy);
-	memset((char *)nfdt->close_on_exec + cpy, 0, set);
-
-	cpy = BITBIT_SIZE(count);
-	set = BITBIT_SIZE(nfdt->max_fds) - cpy;
-	memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy);
-	memset((char *)nfdt->full_fds_bits + cpy, 0, set);
+	unsigned int nwords = fdt_words(nfdt);
+
+	bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds,
+			copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG);
+	bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec,
+			copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG);
+	bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits,
+			copy_words, nwords);
 }
 
 /*
@@ -84,7 +149,7 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
 	memcpy(nfdt->fd, ofdt->fd, cpy);
 	memset((char *)nfdt->fd + cpy, 0, set);
 
-	copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds);
+	copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt));
 }
 
 /*
@@ -93,18 +158,11 @@ 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;
 
 	/*
@@ -112,22 +170,32 @@ 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)
@@ -156,14 +224,14 @@ 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)
@@ -173,7 +241,7 @@ 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.
@@ -182,16 +250,8 @@ 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);
@@ -200,15 +260,14 @@ 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)
@@ -216,50 +275,50 @@ 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;
-
-	/* Can we expand? */
-	if (nr >= sysctl_nr_open)
-		return -EMFILE;
+		return 0;
 
 	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;
 	}
 
+	/* Can we expand? */
+	if (unlikely(nr >= sysctl_nr_open))
+		return -EMFILE;
+
 	/* 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);
@@ -268,62 +327,54 @@ 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 unsigned int count_open_files(struct fdtable *fdt)
+static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt)
 {
-	unsigned int size = fdt->max_fds;
-	unsigned int i;
-
-	/* Find the last open fd */
-	for (i = size / BITS_PER_LONG; i > 0; ) {
-		if (fdt->open_fds[--i])
-			break;
-	}
-	i = (i + 1) * BITS_PER_LONG;
-	return i;
+	return test_bit(fd, fdt->open_fds);
 }
 
 /*
  * Note that a sane fdtable size always has to be a multiple of
  * BITS_PER_LONG, since we have bitmaps that are sized by this.
  *
- * 'max_fds' will normally already be properly aligned, but it
- * turns out that in the close_range() -> __close_range() ->
- * unshare_fd() -> dup_fd() -> sane_fdtable_size() we can end
- * up having a 'max_fds' value that isn't already aligned.
- *
- * Rather than make close_range() have to worry about this,
- * just make that BITS_PER_LONG alignment be part of a sane
- * fdtable size. Becuase that's really what it is.
+ * punch_hole is optional - when close_range() is asked to unshare
+ * and close, we don't need to copy descriptors in that range, so
+ * a smaller cloned descriptor table might suffice if the last
+ * currently opened descriptor falls into that range.
  */
-static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds)
+static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole)
 {
-	unsigned int count;
-
-	count = count_open_files(fdt);
-	if (max_fds < NR_OPEN_DEFAULT)
-		max_fds = NR_OPEN_DEFAULT;
-	return ALIGN(min(count, max_fds), BITS_PER_LONG);
+	unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds);
+
+	if (last == fdt->max_fds)
+		return NR_OPEN_DEFAULT;
+	if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) {
+		last = find_last_bit(fdt->open_fds, punch_hole->from);
+		if (last == punch_hole->from)
+			return NR_OPEN_DEFAULT;
+	}
+	return ALIGN(last + 1, BITS_PER_LONG);
 }
 
 /*
- * Allocate a new files structure and copy contents from the
- * passed in files structure.
- * errorp will be valid only when the returned files_struct is NULL.
+ * Allocate a new descriptor table and copy contents from the passed in
+ * instance.  Returns a pointer to cloned table on success, ERR_PTR()
+ * on failure.  For 'punch_hole' see sane_fdtable_size().
  */
-struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp)
+struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole)
 {
 	struct files_struct *newf;
 	struct file **old_fds, **new_fds;
 	unsigned int open_files, i;
 	struct fdtable *old_fdt, *new_fdt;
 
-	*errorp = -ENOMEM;
 	newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
 	if (!newf)
-		goto out;
+		return ERR_PTR(-ENOMEM);
 
 	atomic_set(&newf->count, 1);
 
@@ -340,7 +391,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
 
 	spin_lock(&oldf->file_lock);
 	old_fdt = files_fdtable(oldf);
-	open_files = sane_fdtable_size(old_fdt, max_fds);
+	open_files = sane_fdtable_size(old_fdt, punch_hole);
 
 	/*
 	 * Check whether we need to allocate a larger fd array and fd set.
@@ -351,17 +402,10 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
 		if (new_fdt != &newf->fdtab)
 			__free_fdtable(new_fdt);
 
-		new_fdt = alloc_fdtable(open_files - 1);
-		if (!new_fdt) {
-			*errorp = -ENOMEM;
-			goto out_release;
-		}
-
-		/* beyond sysctl_nr_open; nothing to do */
-		if (unlikely(new_fdt->max_fds < open_files)) {
-			__free_fdtable(new_fdt);
-			*errorp = -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);
 		}
 
 		/*
@@ -371,25 +415,33 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
 		 */
 		spin_lock(&oldf->file_lock);
 		old_fdt = files_fdtable(oldf);
-		open_files = sane_fdtable_size(old_fdt, max_fds);
+		open_files = sane_fdtable_size(old_fdt, punch_hole);
 	}
 
-	copy_fd_bitmaps(new_fdt, old_fdt, open_files);
+	copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG);
 
 	old_fds = old_fdt->fd;
 	new_fds = new_fdt->fd;
 
+	/*
+	 * We may be racing against fd allocation from other threads using this
+	 * files_struct, despite holding ->file_lock.
+	 *
+	 * alloc_fd() might have already claimed a slot, while fd_install()
+	 * did not populate it yet. Note the latter operates locklessly, so
+	 * the file can show up as we are walking the array below.
+	 *
+	 * At the same time we know no files will disappear as all other
+	 * operations take the lock.
+	 *
+	 * Instead of trying to placate userspace racing with itself, we
+	 * ref the file if we see it and mark the fd slot as unused otherwise.
+	 */
 	for (i = open_files; i != 0; i--) {
-		struct file *f = *old_fds++;
+		struct file *f = rcu_dereference_raw(*old_fds++);
 		if (f) {
 			get_file(f);
 		} else {
-			/*
-			 * The fd may be claimed in the fd bitmap but not yet
-			 * instantiated in the files array if a sibling thread
-			 * is partway through open().  So make sure that this
-			 * fd is available to the new process.
-			 */
 			__clear_open_fd(open_files - i, new_fdt);
 		}
 		rcu_assign_pointer(*new_fds++, f);
@@ -402,11 +454,6 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
 	rcu_assign_pointer(newf->fdt, new_fdt);
 
 	return newf;
-
-out_release:
-	kmem_cache_free(files_cachep, newf);
-out:
-	return NULL;
 }
 
 static struct fdtable *close_files(struct files_struct * files)
@@ -427,7 +474,7 @@ 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();
@@ -481,12 +528,21 @@ struct files_struct init_files = {
 
 static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start)
 {
-	unsigned int maxfd = fdt->max_fds;
+	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)
+	if (bitbit >= maxfd)
 		return maxfd;
 	if (bitbit > start)
 		start = bitbit;
@@ -510,7 +566,7 @@ 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);
 
 	/*
@@ -518,36 +574,23 @@ 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
+	VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL);
 
 out:
 	spin_unlock(&files->file_lock);
@@ -583,22 +626,14 @@ void put_unused_fd(unsigned int fd)
 
 EXPORT_SYMBOL(put_unused_fd);
 
-/*
- * Install a file pointer in the fd array.
- *
- * The VFS is full of places where we drop the files lock between
- * setting the open_fds bitmap and installing the file in the file
- * array.  At any such point, we are vulnerable to a dup2() race
- * installing a file in the array before us.  We need to detect this and
- * fput() the struct file we are about to overwrite in this case.
- *
- * It should never happen - if we allow dup2() do it, _really_ bad things
- * will follow.
+/**
+ * fd_install - install a file pointer in the fd array
+ * @fd: file descriptor to install the file in
+ * @file: the file to install
  *
  * This consumes the "file" refcount, so callers should treat it
  * as if they had called fput(file).
  */
-
 void fd_install(unsigned int fd, struct file *file)
 {
 	struct files_struct *files = current->files;
@@ -613,7 +648,7 @@ 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);
+		VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL);
 		rcu_assign_pointer(fdt->fd[fd], file);
 		spin_unlock(&files->file_lock);
 		return;
@@ -621,7 +656,7 @@ void fd_install(unsigned int fd, struct file *file)
 	/* coupled with smp_wmb() in expand_fdtable() */
 	smp_rmb();
 	fdt = rcu_dereference_sched(files->fdt);
-	BUG_ON(fdt->fd[fd] != NULL);
+	VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL);
 	rcu_assign_pointer(fdt->fd[fd], file);
 	rcu_read_unlock_sched();
 }
@@ -650,7 +685,7 @@ struct file *file_close_fd_locked(struct files_struct *files, unsigned fd)
 		return NULL;
 
 	fd = array_index_nospec(fd, fdt->max_fds);
-	file = fdt->fd[fd];
+	file = rcu_dereference_raw(fdt->fd[fd]);
 	if (file) {
 		rcu_assign_pointer(fdt->fd[fd], NULL);
 		__put_unused_fd(files, fd);
@@ -671,7 +706,7 @@ int close_fd(unsigned fd)
 
 	return filp_close(file, files);
 }
-EXPORT_SYMBOL(close_fd); /* for ksys_close() */
+EXPORT_SYMBOL(close_fd);
 
 /**
  * last_fd - return last valid index into fd table
@@ -727,7 +762,7 @@ 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
@@ -735,8 +770,10 @@ 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;
@@ -747,37 +784,25 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
 	if (fd > max_fd)
 		return -EINVAL;
 
-	if (flags & CLOSE_RANGE_UNSHARE) {
-		int ret;
-		unsigned int max_unshare_fds = NR_OPEN_MAX;
+	if ((flags & CLOSE_RANGE_UNSHARE) && atomic_read(&cur_fds->count) > 1) {
+		struct fd_range range = {fd, max_fd}, *punch_hole = &range;
 
 		/*
 		 * If the caller requested all fds to be made cloexec we always
 		 * copy all of the file descriptors since they still want to
 		 * use them.
 		 */
-		if (!(flags & CLOSE_RANGE_CLOEXEC)) {
-			/*
-			 * If the requested range is greater than the current
-			 * maximum, we're closing everything so only copy all
-			 * file descriptors beneath the lowest file descriptor.
-			 */
-			rcu_read_lock();
-			if (max_fd >= last_fd(files_fdtable(cur_fds)))
-				max_unshare_fds = fd;
-			rcu_read_unlock();
-		}
-
-		ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds);
-		if (ret)
-			return ret;
+		if (flags & CLOSE_RANGE_CLOEXEC)
+			punch_hole = NULL;
 
+		fds = dup_fd(cur_fds, punch_hole);
+		if (IS_ERR(fds))
+			return PTR_ERR(fds);
 		/*
 		 * We used to share our file descriptor table, and have now
 		 * created a private one, make sure we're using it below.
 		 */
-		if (fds)
-			swap(cur_fds, fds);
+		swap(cur_fds, fds);
 	}
 
 	if (flags & CLOSE_RANGE_CLOEXEC)
@@ -865,7 +890,7 @@ static struct file *__get_file_rcu(struct file __rcu **f)
 	if (!file)
 		return NULL;
 
-	if (unlikely(!atomic_long_inc_not_zero(&file->f_count)))
+	if (unlikely(!file_ref_get(&file->f_ref)))
 		return ERR_PTR(-EAGAIN);
 
 	file_reloaded = rcu_dereference_raw(*f);
@@ -879,8 +904,8 @@ static struct file *__get_file_rcu(struct file __rcu **f)
 	OPTIMIZER_HIDE_VAR(file_reloaded_cmp);
 
 	/*
-	 * atomic_long_inc_not_zero() above provided a full memory
-	 * barrier when we acquired a reference.
+	 * file_ref_get() above provided a full memory barrier when we
+	 * acquired a reference.
 	 *
 	 * This is paired with the write barrier from assigning to the
 	 * __rcu protected file pointer so that if that pointer still
@@ -915,13 +940,8 @@ struct file *get_file_rcu(struct file __rcu **f)
 		struct file __rcu *file;
 
 		file = __get_file_rcu(f);
-		if (unlikely(!file))
-			return NULL;
-
-		if (unlikely(IS_ERR(file)))
-			continue;
-
-		return file;
+		if (!IS_ERR(file))
+			return file;
 	}
 }
 EXPORT_SYMBOL_GPL(get_file_rcu);
@@ -983,11 +1003,11 @@ static inline struct file *__fget_files_rcu(struct files_struct *files,
 		 * We need to confirm it by incrementing the refcount
 		 * and then check the lookup again.
 		 *
-		 * atomic_long_inc_not_zero() gives us a full memory
-		 * barrier. We only really need an 'acquire' one to
-		 * protect the loads below, but we don't have that.
+		 * file_ref_get() gives us a full memory barrier. We
+		 * only really need an 'acquire' one to protect the
+		 * loads below, but we don't have that.
 		 */
-		if (unlikely(!atomic_long_inc_not_zero(&file->f_count)))
+		if (unlikely(!file_ref_get(&file->f_ref)))
 			continue;
 
 		/*
@@ -1068,29 +1088,7 @@ 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;
@@ -1100,17 +1098,19 @@ 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.
@@ -1127,8 +1127,15 @@ EXPORT_SYMBOL(task_lookup_next_fdget_rcu);
  *
  * The fput_needed flag returned by fget_light should be passed to the
  * corresponding fput_light.
+ *
+ * (As an exception to rule 2, you can call filp_close between fget_light and
+ * fput_light provided that you capture a real refcount with get_file before
+ * the call to filp_close, and ensure that this real refcount is fput *after*
+ * the fput_light call.)
+ *
+ * See also the documentation in rust/kernel/file.rs.
  */
-static unsigned long __fget_light(unsigned int fd, fmode_t mask)
+static inline struct fd __fget_light(unsigned int fd, fmode_t mask)
 {
 	struct files_struct *files = current->files;
 	struct file *file;
@@ -1145,22 +1152,22 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask)
 	if (likely(atomic_read_acquire(&files->count) == 1)) {
 		file = files_lookup_fd_raw(files, fd);
 		if (!file || unlikely(file->f_mode & mask))
-			return 0;
-		return (unsigned long)file;
+			return EMPTY_FD;
+		return BORROWED_FD(file);
 	} else {
 		file = __fget_files(files, fd, mask);
 		if (!file)
-			return 0;
-		return FDPUT_FPUT | (unsigned long)file;
+			return EMPTY_FD;
+		return CLONED_FD(file);
 	}
 }
-unsigned long __fdget(unsigned int fd)
+struct fd fdget(unsigned int fd)
 {
 	return __fget_light(fd, FMODE_PATH);
 }
-EXPORT_SYMBOL(__fdget);
+EXPORT_SYMBOL(fdget);
 
-unsigned long __fdget_raw(unsigned int fd)
+struct fd fdget_raw(unsigned int fd)
 {
 	return __fget_light(fd, 0);
 }
@@ -1177,20 +1184,35 @@ unsigned long __fdget_raw(unsigned int fd)
  */
 static inline bool file_needs_f_pos_lock(struct file *file)
 {
-	return (file->f_mode & FMODE_ATOMIC_POS) &&
-		(file_count(file) > 1 || file->f_op->iterate_shared);
+	if (!(file->f_mode & FMODE_ATOMIC_POS))
+		return false;
+	if (__file_ref_read_raw(&file->f_ref) != FILE_REF_ONEREF)
+		return true;
+	if (file->f_op->iterate_shared)
+		return true;
+	return false;
+}
+
+bool file_seek_cur_needs_f_lock(struct file *file)
+{
+	if (!(file->f_mode & FMODE_ATOMIC_POS) && !file->f_op->iterate_shared)
+		return false;
+
+	VFS_WARN_ON_ONCE((file_count(file) > 1) &&
+			 !mutex_is_locked(&file->f_pos_lock));
+	return true;
 }
 
-unsigned long __fdget_pos(unsigned int fd)
+struct fd fdget_pos(unsigned int fd)
 {
-	unsigned long v = __fdget(fd);
-	struct file *file = (struct file *)(v & ~3);
+	struct fd f = fdget(fd);
+	struct file *file = fd_file(f);
 
-	if (file && file_needs_f_pos_lock(file)) {
-		v |= FDPUT_POS_UNLOCK;
+	if (likely(file) && file_needs_f_pos_lock(file)) {
+		f.word |= FDPUT_POS_UNLOCK;
 		mutex_lock(&file->f_pos_lock);
 	}
-	return v;
+	return f;
 }
 
 void __f_unlock_pos(struct file *f)
@@ -1207,24 +1229,16 @@ 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);
 }
 
 bool get_close_on_exec(unsigned int fd)
 {
-	struct files_struct *files = current->files;
-	struct fdtable *fdt;
 	bool res;
 	rcu_read_lock();
-	fdt = files_fdtable(files);
-	res = close_on_exec(fd, fdt);
+	res = close_on_exec(fd, current->files);
 	rcu_read_unlock();
 	return res;
 }
@@ -1237,30 +1251,39 @@ __releases(&files->file_lock)
 	struct fdtable *fdt;
 
 	/*
-	 * We need to detect attempts to do dup2() over allocated but still
-	 * not finished descriptor.  NB: OpenBSD avoids that at the price of
-	 * extra work in their equivalent of fget() - they insert struct
-	 * file immediately after grabbing descriptor, mark it larval if
-	 * more work (e.g. actual opening) is needed and make sure that
-	 * fget() treats larval files as absent.  Potentially interesting,
-	 * but while extra work in fget() is trivial, locking implications
-	 * and amount of surgery on open()-related paths in VFS are not.
-	 * FreeBSD fails with -EBADF in the same situation, NetBSD "solution"
-	 * deadlocks in rather amusing ways, AFAICS.  All of that is out of
-	 * scope of POSIX or SUS, since neither considers shared descriptor
-	 * tables and this condition does not arise without those.
+	 * dup2() is expected to close the file installed in the target fd slot
+	 * (if any). However, userspace hand-picking a fd may be racing against
+	 * its own threads which happened to allocate it in open() et al but did
+	 * not populate it yet.
+	 *
+	 * Broadly speaking we may be racing against the following:
+	 * fd = get_unused_fd_flags();     // fd slot reserved, ->fd[fd] == NULL
+	 * file = hard_work_goes_here();
+	 * fd_install(fd, file);           // only now ->fd[fd] == file
+	 *
+	 * It is an invariant that a successfully allocated fd has a NULL entry
+	 * in the array until the matching fd_install().
+	 *
+	 * If we fit the window, we have the fd to populate, yet no target file
+	 * to close. Trying to ignore it and install our new file would violate
+	 * the invariant and make fd_install() overwrite our file.
+	 *
+	 * Things can be done(tm) to handle this. However, the issue does not
+	 * concern legitimate programs and we only need to make sure the kernel
+	 * does not trip over it.
+	 *
+	 * The simplest way out is to return an error if we find ourselves here.
+	 *
+	 * POSIX is silent on the issue, we return -EBUSY.
 	 */
 	fdt = files_fdtable(files);
-	tofree = fdt->fd[fd];
+	fd = array_index_nospec(fd, fdt->max_fds);
+	tofree = rcu_dereference_raw(fdt->fd[fd]);
 	if (!tofree && fd_is_open(fd, fdt))
 		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)