Merge tag 'vfs-7.0-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull misc vfs updates from Christian Brauner:
 "This contains a mix of VFS cleanups, performance improvements, API
  fixes, documentation, and a deprecation notice.

  Scalability and performance:

   - Rework pid allocation to only take pidmap_lock once instead of
     twice during alloc_pid(), improving thread creation/teardown
     throughput by 10-16% depending on false-sharing luck. Pad the
     namespace refcount to reduce false-sharing

   - Track file lock presence via a flag in ->i_opflags instead of
     reading ->i_flctx, avoiding false-sharing with ->i_readcount on
     open/close hot paths. Measured 4-16% improvement on 24-core
     open-in-a-loop benchmarks

   - Use a consume fence in locks_inode_context() to match the
     store-release/load-consume idiom, eliminating a hardware fence on
     some architectures

   - Annotate cdev_lock with __cacheline_aligned_in_smp to prevent
     false-sharing

   - Remove a redundant DCACHE_MANAGED_DENTRY check in
     __follow_mount_rcu() that never fires since the caller already
     verifies it, eliminating a 100% mispredicted branch

   - Fix a 100% mispredicted likely() in devcgroup_inode_permission()
     that became wrong after a prior code reorder

  Bug fixes and correctness:

   - Make insert_inode_locked() wait for inode destruction instead of
     skipping, fixing a corner case where two matching inodes could
     exist in the hash

   - Move f_mode initialization before file_ref_init() in alloc_file()
     to respect the SLAB_TYPESAFE_BY_RCU ordering contract

   - Add a WARN_ON_ONCE guard in try_to_free_buffers() for folios with
     no buffers attached, preventing a null pointer dereference when
     AS_RELEASE_ALWAYS is set but no release_folio op exists

   - Fix select restart_block to store end_time as timespec64, avoiding
     truncation of tv_sec on 32-bit architectures

   - Make dump_inode() use get_kernel_nofault() to safely access inode
     and superblock fields, matching the dump_mapping() pattern

  API modernization:

   - Make posix_acl_to_xattr() allocate the buffer internally since
     every single caller was doing it anyway. Reduces boilerplate and
     unnecessary error checking across ~15 filesystems

   - Replace deprecated simple_strtoul() with kstrtoul() for the
     ihash_entries, dhash_entries, mhash_entries, and mphash_entries
     boot parameters, adding proper error handling

   - Convert chardev code to use guard(mutex) and __free(kfree) cleanup
     patterns

   - Replace min_t() with min() or umin() in VFS code to avoid silently
     truncating unsigned long to unsigned int

   - Gate LOOKUP_RCU assertions behind CONFIG_DEBUG_VFS since callers
     already check the flag

  Deprecation:

   - Begin deprecating legacy BSD process accounting (acct(2)). The
     interface has numerous footguns and better alternatives exist
     (eBPF)

  Documentation:

   - Fix and complete kernel-doc for struct export_operations, removing
     duplicated documentation between ReST and source

   - Fix kernel-doc warnings for __start_dirop() and ilookup5_nowait()

  Testing:

   - Add a kunit test for initramfs cpio handling of entries with
     filesize > PATH_MAX

  Misc:

   - Add missing <linux/init_task.h> include in fs_struct.c"

* tag 'vfs-7.0-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (28 commits)
  posix_acl: make posix_acl_to_xattr() alloc the buffer
  fs: make insert_inode_locked() wait for inode destruction
  initramfs_test: kunit test for cpio.filesize > PATH_MAX
  fs: improve dump_inode() to safely access inode fields
  fs: add <linux/init_task.h> for 'init_fs'
  docs: exportfs: Use source code struct documentation
  fs: move initializing f_mode before file_ref_init()
  exportfs: Complete kernel-doc for struct export_operations
  exportfs: Mark struct export_operations functions at kernel-doc
  exportfs: Fix kernel-doc output for get_name()
  acct(2): begin the deprecation of legacy BSD process accounting
  device_cgroup: remove branch hint after code refactor
  VFS: fix __start_dirop() kernel-doc warnings
  fs: Describe @isnew parameter in ilookup5_nowait()
  fs/namei: Remove redundant DCACHE_MANAGED_DENTRY check in __follow_mount_rcu
  fs: only assert on LOOKUP_RCU when built with CONFIG_DEBUG_VFS
  select: store end_time as timespec64 in restart block
  chardev: Switch to guard(mutex) and __free(kfree)
  namespace: Replace simple_strtoul with kstrtoul to parse boot params
  dcache: Replace simple_strtoul with kstrtoul in set_dhash_entries
  ...

1 files changed, 85 insertions, 46 deletions

diff --git a/kernel/pid.c b/kernel/pid.c
index a31771bc89c1..f45ae56db7da 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -159,58 +159,86 @@ void free_pids(struct pid **pids)
 			free_pid(pids[tmp]);
 }
 
-struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
-		      size_t set_tid_size)
+struct pid *alloc_pid(struct pid_namespace *ns, pid_t *arg_set_tid,
+		      size_t arg_set_tid_size)
 {
+	int set_tid[MAX_PID_NS_LEVEL + 1] = {};
+	int pid_max[MAX_PID_NS_LEVEL + 1] = {};
 	struct pid *pid;
 	enum pid_type type;
 	int i, nr;
 	struct pid_namespace *tmp;
 	struct upid *upid;
 	int retval = -ENOMEM;
+	bool retried_preload;
 
 	/*
-	 * set_tid_size contains the size of the set_tid array. Starting at
+	 * arg_set_tid_size contains the size of the arg_set_tid array. Starting at
 	 * the most nested currently active PID namespace it tells alloc_pid()
 	 * which PID to set for a process in that most nested PID namespace
-	 * up to set_tid_size PID namespaces. It does not have to set the PID
-	 * for a process in all nested PID namespaces but set_tid_size must
+	 * up to arg_set_tid_size PID namespaces. It does not have to set the PID
+	 * for a process in all nested PID namespaces but arg_set_tid_size must
 	 * never be greater than the current ns->level + 1.
 	 */
-	if (set_tid_size > ns->level + 1)
+	if (arg_set_tid_size > ns->level + 1)
 		return ERR_PTR(-EINVAL);
 
+	/*
+	 * Prep before we take locks:
+	 *
+	 * 1. allocate and fill in pid struct
+	 */
 	pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
 	if (!pid)
 		return ERR_PTR(retval);
 
-	tmp = ns;
+	get_pid_ns(ns);
 	pid->level = ns->level;
+	refcount_set(&pid->count, 1);
+	spin_lock_init(&pid->lock);
+	for (type = 0; type < PIDTYPE_MAX; ++type)
+		INIT_HLIST_HEAD(&pid->tasks[type]);
+	init_waitqueue_head(&pid->wait_pidfd);
+	INIT_HLIST_HEAD(&pid->inodes);
 
-	for (i = ns->level; i >= 0; i--) {
-		int tid = 0;
-		int pid_max = READ_ONCE(tmp->pid_max);
+	/*
+	 * 2. perm check checkpoint_restore_ns_capable()
+	 *
+	 * This stores found pid_max to make sure the used value is the same should
+	 * later code need it.
+	 */
+	for (tmp = ns, i = ns->level; i >= 0; i--) {
+		pid_max[ns->level - i] = READ_ONCE(tmp->pid_max);
 
-		if (set_tid_size) {
-			tid = set_tid[ns->level - i];
+		if (arg_set_tid_size) {
+			int tid = set_tid[ns->level - i] = arg_set_tid[ns->level - i];
 
 			retval = -EINVAL;
-			if (tid < 1 || tid >= pid_max)
-				goto out_free;
+			if (tid < 1 || tid >= pid_max[ns->level - i])
+				goto out_abort;
 			/*
 			 * Also fail if a PID != 1 is requested and
 			 * no PID 1 exists.
 			 */
 			if (tid != 1 && !tmp->child_reaper)
-				goto out_free;
+				goto out_abort;
 			retval = -EPERM;
 			if (!checkpoint_restore_ns_capable(tmp->user_ns))
-				goto out_free;
-			set_tid_size--;
+				goto out_abort;
+			arg_set_tid_size--;
 		}
 
-		idr_preload(GFP_KERNEL);
-		spin_lock(&pidmap_lock);
+		tmp = tmp->parent;
+	}
+
+	/*
+	 * Prep is done, id allocation goes here:
+	 */
+	retried_preload = false;
+	idr_preload(GFP_KERNEL);
+	spin_lock(&pidmap_lock);
+	for (tmp = ns, i = ns->level; i >= 0;) {
+		int tid = set_tid[ns->level - i];
 
 		if (tid) {
 			nr = idr_alloc(&tmp->idr, NULL, tid,
@@ -220,6 +248,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 			 * alreay in use. Return EEXIST in that case.
 			 */
 			if (nr == -ENOSPC)
+
 				nr = -EEXIST;
 		} else {
 			int pid_min = 1;
@@ -235,19 +264,42 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 			 * a partially initialized PID (see below).
 			 */
 			nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
-					      pid_max, GFP_ATOMIC);
+					      pid_max[ns->level - i], GFP_ATOMIC);
+			if (nr == -ENOSPC)
+				nr = -EAGAIN;
 		}
-		spin_unlock(&pidmap_lock);
-		idr_preload_end();
 
-		if (nr < 0) {
-			retval = (nr == -ENOSPC) ? -EAGAIN : nr;
+		if (unlikely(nr < 0)) {
+			/*
+			 * Preload more memory if idr_alloc{,cyclic} failed with -ENOMEM.
+			 *
+			 * The IDR API only allows us to preload memory for one call, while we may end
+			 * up doing several under pidmap_lock with GFP_ATOMIC. The situation may be
+			 * salvageable with GFP_KERNEL. But make sure to not loop indefinitely if preload
+			 * did not help (the routine unfortunately returns void, so we have no idea
+			 * if it got anywhere).
+			 *
+			 * The lock can be safely dropped and picked up as historically pid allocation
+			 * for different namespaces was *not* atomic -- we try to hold on to it the
+			 * entire time only for performance reasons.
+			 */
+			if (nr == -ENOMEM && !retried_preload) {
+				spin_unlock(&pidmap_lock);
+				idr_preload_end();
+				retried_preload = true;
+				idr_preload(GFP_KERNEL);
+				spin_lock(&pidmap_lock);
+				continue;
+			}
+			retval = nr;
 			goto out_free;
 		}
 
 		pid->numbers[i].nr = nr;
 		pid->numbers[i].ns = tmp;
 		tmp = tmp->parent;
+		i--;
+		retried_preload = false;
 	}
 
 	/*
@@ -257,25 +309,15 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 	 * is what we have exposed to userspace for a long time and it is
 	 * documented behavior for pid namespaces. So we can't easily
 	 * change it even if there were an error code better suited.
+	 *
+	 * This can't be done earlier because we need to preserve other
+	 * error conditions.
 	 */
 	retval = -ENOMEM;
-
-	get_pid_ns(ns);
-	refcount_set(&pid->count, 1);
-	spin_lock_init(&pid->lock);
-	for (type = 0; type < PIDTYPE_MAX; ++type)
-		INIT_HLIST_HEAD(&pid->tasks[type]);
-
-	init_waitqueue_head(&pid->wait_pidfd);
-	INIT_HLIST_HEAD(&pid->inodes);
-
-	upid = pid->numbers + ns->level;
-	idr_preload(GFP_KERNEL);
-	spin_lock(&pidmap_lock);
-	if (!(ns->pid_allocated & PIDNS_ADDING))
-		goto out_unlock;
+	if (unlikely(!(ns->pid_allocated & PIDNS_ADDING)))
+		goto out_free;
 	pidfs_add_pid(pid);
-	for ( ; upid >= pid->numbers; --upid) {
+	for (upid = pid->numbers + ns->level; upid >= pid->numbers; --upid) {
 		/* Make the PID visible to find_pid_ns. */
 		idr_replace(&upid->ns->idr, pid, upid->nr);
 		upid->ns->pid_allocated++;
@@ -286,13 +328,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 
 	return pid;
 
-out_unlock:
-	spin_unlock(&pidmap_lock);
-	idr_preload_end();
-	put_pid_ns(ns);
-
 out_free:
-	spin_lock(&pidmap_lock);
 	while (++i <= ns->level) {
 		upid = pid->numbers + i;
 		idr_remove(&upid->ns->idr, upid->nr);
@@ -303,7 +339,10 @@ out_free:
 		idr_set_cursor(&ns->idr, 0);
 
 	spin_unlock(&pidmap_lock);
+	idr_preload_end();
 
+out_abort:
+	put_pid_ns(ns);
 	kmem_cache_free(ns->pid_cachep, pid);
 	return ERR_PTR(retval);
 }