Merge tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linuxgrafted

Pull io_uring fixes from Jens Axboe:

 - Fix a task_work add use-after-free with SQPOLL.

   The sqpoll thread could pop and complete the last request while
   io_req_normal_work_add() was still looking at them after the mpscq
   push.

   Use the same approach as DEFER_TASKRUN to protect from that, holding
   an RCU read lock across the add, and have exit wait for an RCU grace
   period for SQPOLL rings as well.

 - CQE32 ring fixes: correct the free entry check for 32b CQEs, zero the
   big_cqe for aux CQEs, and only post the dummy skip CQE on CQE_MIXED
   rings

 - Mark the source filter table as COW when cloning bpf filters, so
   registering another filter on the source doesn't modify the shared
   table in place

 - Initialize the task context before running the BPF loop

 - Requeue zcrx multishot receives stopped by a local resource

 - End a TX_TIMESTAMP multishot cmd when the CQ is full (lollipopkit)

* tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring: fix task_work add use-after-free with SQPOLL
  io_uring/cmd_net: end TX_TIMESTAMP multishot when the CQ is full
  io_uring/zcrx: requeue multishot receives stopped by a local resource
  io_uring: initialize task context before running the BPF loop
  io_uring: zero big_cqe for aux CQEs on CQE32 rings
  io_uring: fix free entry check for 32b CQEs on CQE32 rings
  io_uring: only post the dummy skip CQE on CQE_MIXED rings
  io_uring/bpf_filter: mark source as COW when cloning filters

1 files changed, 259 insertions, 0 deletions

diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
new file mode 100644
index 000000000..85d3dd48b
--- /dev/null
+++ b/fs/ceph/acl.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/fs/ceph/acl.c
+ *
+ * Copyright (C) 2013 Guangliang Zhao, <lucienchao@gmail.com>
+ */
+
+#include <linux/ceph/ceph_debug.h>
+#include <linux/fs.h>
+#include <linux/string.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/posix_acl.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include "super.h"
+#include "mds_client.h"
+
+static inline void ceph_set_cached_acl(struct inode *inode,
+					int type, struct posix_acl *acl)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	spin_lock(&ci->i_ceph_lock);
+	if (__ceph_caps_issued_mask_metric(ci, CEPH_CAP_XATTR_SHARED, 0))
+		set_cached_acl(inode, type, acl);
+	else
+		forget_cached_acl(inode, type);
+	spin_unlock(&ci->i_ceph_lock);
+}
+
+struct posix_acl *ceph_get_acl(struct inode *inode, int type, bool rcu)
+{
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	int size;
+	unsigned int retry_cnt = 0;
+	const char *name;
+	char *value = NULL;
+	struct posix_acl *acl;
+
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+
+retry:
+	size = __ceph_getxattr(inode, name, "", 0);
+	if (size > 0) {
+		value = kzalloc(size, GFP_NOFS);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		size = __ceph_getxattr(inode, name, value, size);
+	}
+
+	if (size == -ERANGE && retry_cnt < 10) {
+		retry_cnt++;
+		kfree(value);
+		value = NULL;
+		goto retry;
+	}
+
+	if (size > 0) {
+		acl = posix_acl_from_xattr(&init_user_ns, value, size);
+	} else if (size == -ENODATA || size == 0) {
+		acl = NULL;
+	} else {
+		pr_err_ratelimited_client(cl, "%llx.%llx failed, err=%d\n",
+					  ceph_vinop(inode), size);
+		acl = ERR_PTR(-EIO);
+	}
+
+	kfree(value);
+
+	if (!IS_ERR(acl))
+		ceph_set_cached_acl(inode, type, acl);
+
+	return acl;
+}
+
+int ceph_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+		 struct posix_acl *acl, int type)
+{
+	int ret = 0;
+	size_t size = 0;
+	const char *name = NULL;
+	char *value = NULL;
+	struct iattr newattrs;
+	struct inode *inode = d_inode(dentry);
+	struct timespec64 old_ctime = inode_get_ctime(inode);
+	umode_t new_mode = inode->i_mode, old_mode = inode->i_mode;
+
+	if (ceph_snap(inode) != CEPH_NOSNAP) {
+		ret = -EROFS;
+		goto out;
+	}
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
+		if (acl) {
+			ret = posix_acl_update_mode(idmap, inode,
+						    &new_mode, &acl);
+			if (ret)
+				goto out;
+		}
+		break;
+	case ACL_TYPE_DEFAULT:
+		if (!S_ISDIR(inode->i_mode)) {
+			ret = acl ? -EINVAL : 0;
+			goto out;
+		}
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
+		break;
+	default:
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (acl) {
+		value = posix_acl_to_xattr(&init_user_ns, acl, &size, GFP_NOFS);
+		if (!value) {
+			ret = -ENOMEM;
+			goto out;
+		}
+	}
+
+	if (new_mode != old_mode) {
+		newattrs.ia_ctime = current_time(inode);
+		newattrs.ia_mode = new_mode;
+		newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
+		ret = __ceph_setattr(idmap, inode, &newattrs, NULL);
+		if (ret)
+			goto out_free;
+	}
+
+	ret = __ceph_setxattr(inode, name, value, size, 0);
+	if (ret) {
+		if (new_mode != old_mode) {
+			newattrs.ia_ctime = old_ctime;
+			newattrs.ia_mode = old_mode;
+			newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
+			__ceph_setattr(idmap, inode, &newattrs, NULL);
+		}
+		goto out_free;
+	}
+
+	ceph_set_cached_acl(inode, type, acl);
+
+out_free:
+	kfree(value);
+out:
+	return ret;
+}
+
+int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
+		       struct ceph_acl_sec_ctx *as_ctx)
+{
+	struct posix_acl *acl, *default_acl;
+	size_t val_size1 = 0, val_size2 = 0;
+	struct ceph_pagelist *pagelist = NULL;
+	void *tmp_buf1 = NULL, *tmp_buf2 = NULL;
+	int err;
+
+	err = posix_acl_create(dir, mode, &default_acl, &acl);
+	if (err)
+		return err;
+
+	if (acl) {
+		err = posix_acl_equiv_mode(acl, mode);
+		if (err < 0)
+			goto out_err;
+		if (err == 0) {
+			posix_acl_release(acl);
+			acl = NULL;
+		}
+	}
+
+	if (!default_acl && !acl)
+		return 0;
+
+	err = -ENOMEM;
+	pagelist = ceph_pagelist_alloc(GFP_KERNEL);
+	if (!pagelist)
+		goto out_err;
+
+	err = ceph_pagelist_reserve(pagelist, PAGE_SIZE);
+	if (err)
+		goto out_err;
+
+	ceph_pagelist_encode_32(pagelist, acl && default_acl ? 2 : 1);
+
+	if (acl) {
+		size_t len = strlen(XATTR_NAME_POSIX_ACL_ACCESS);
+
+		err = -ENOMEM;
+		tmp_buf1 = posix_acl_to_xattr(&init_user_ns, acl,
+					      &val_size1, GFP_KERNEL);
+		if (!tmp_buf1)
+			goto out_err;
+		err = ceph_pagelist_reserve(pagelist, len + val_size1 + 8);
+		if (err)
+			goto out_err;
+		ceph_pagelist_encode_string(pagelist, XATTR_NAME_POSIX_ACL_ACCESS,
+					    len);
+		ceph_pagelist_encode_32(pagelist, val_size1);
+		ceph_pagelist_append(pagelist, tmp_buf1, val_size1);
+	}
+	if (default_acl) {
+		size_t len = strlen(XATTR_NAME_POSIX_ACL_DEFAULT);
+
+		err = -ENOMEM;
+		tmp_buf2 = posix_acl_to_xattr(&init_user_ns, default_acl,
+					      &val_size2, GFP_KERNEL);
+		if (!tmp_buf2)
+			goto out_err;
+		err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8);
+		if (err)
+			goto out_err;
+		ceph_pagelist_encode_string(pagelist,
+					  XATTR_NAME_POSIX_ACL_DEFAULT, len);
+		ceph_pagelist_encode_32(pagelist, val_size2);
+		ceph_pagelist_append(pagelist, tmp_buf2, val_size2);
+	}
+
+	kfree(tmp_buf1);
+	kfree(tmp_buf2);
+
+	as_ctx->acl = acl;
+	as_ctx->default_acl = default_acl;
+	as_ctx->pagelist = pagelist;
+	return 0;
+
+out_err:
+	posix_acl_release(acl);
+	posix_acl_release(default_acl);
+	kfree(tmp_buf1);
+	kfree(tmp_buf2);
+	if (pagelist)
+		ceph_pagelist_release(pagelist);
+	return err;
+}
+
+void ceph_init_inode_acls(struct inode *inode, struct ceph_acl_sec_ctx *as_ctx)
+{
+	if (!inode)
+		return;
+	ceph_set_cached_acl(inode, ACL_TYPE_ACCESS, as_ctx->acl);
+	ceph_set_cached_acl(inode, ACL_TYPE_DEFAULT, as_ctx->default_acl);
+}