1 files changed, 58 insertions, 62 deletions

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index adc8fc3c5d85..689e3ffd29d7 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -78,9 +78,21 @@ struct inode *ceph_get_snapdir(struct inode *parent)
 	struct inode *inode = ceph_get_inode(parent->i_sb, vino);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
-	BUG_ON(!S_ISDIR(parent->i_mode));
 	if (IS_ERR(inode))
 		return inode;
+
+	if (!S_ISDIR(parent->i_mode)) {
+		pr_warn_once("bad snapdir parent type (mode=0%o)\n",
+			     parent->i_mode);
+		return ERR_PTR(-ENOTDIR);
+	}
+
+	if (!(inode->i_state & I_NEW) && !S_ISDIR(inode->i_mode)) {
+		pr_warn_once("bad snapdir inode type (mode=0%o)\n",
+			     inode->i_mode);
+		return ERR_PTR(-ENOTDIR);
+	}
+
 	inode->i_mode = parent->i_mode;
 	inode->i_uid = parent->i_uid;
 	inode->i_gid = parent->i_gid;
@@ -757,11 +769,32 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 	bool queue_trunc = false;
 	bool new_version = false;
 	bool fill_inline = false;
+	umode_t mode = le32_to_cpu(info->mode);
+	dev_t rdev = le32_to_cpu(info->rdev);
 
 	dout("%s %p ino %llx.%llx v %llu had %llu\n", __func__,
 	     inode, ceph_vinop(inode), le64_to_cpu(info->version),
 	     ci->i_version);
 
+	/* Once I_NEW is cleared, we can't change type or dev numbers */
+	if (inode->i_state & I_NEW) {
+		inode->i_mode = mode;
+	} else {
+		if (inode_wrong_type(inode, mode)) {
+			pr_warn_once("inode type changed! (ino %llx.%llx is 0%o, mds says 0%o)\n",
+				     ceph_vinop(inode), inode->i_mode, mode);
+			return -ESTALE;
+		}
+
+		if ((S_ISCHR(mode) || S_ISBLK(mode)) && inode->i_rdev != rdev) {
+			pr_warn_once("dev inode rdev changed! (ino %llx.%llx is %u:%u, mds says %u:%u)\n",
+				     ceph_vinop(inode), MAJOR(inode->i_rdev),
+				     MINOR(inode->i_rdev), MAJOR(rdev),
+				     MINOR(rdev));
+			return -ESTALE;
+		}
+	}
+
 	info_caps = le32_to_cpu(info->cap.caps);
 
 	/* prealloc new cap struct */
@@ -815,8 +848,6 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 	issued |= __ceph_caps_dirty(ci);
 	new_issued = ~issued & info_caps;
 
-	/* update inode */
-	inode->i_rdev = le32_to_cpu(info->rdev);
 	/* directories have fl_stripe_unit set to zero */
 	if (le32_to_cpu(info->layout.fl_stripe_unit))
 		inode->i_blkbits =
@@ -828,7 +859,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 
 	if ((new_version || (new_issued & CEPH_CAP_AUTH_SHARED)) &&
 	    (issued & CEPH_CAP_AUTH_EXCL) == 0) {
-		inode->i_mode = le32_to_cpu(info->mode);
+		inode->i_mode = mode;
 		inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(info->uid));
 		inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(info->gid));
 		dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
@@ -926,7 +957,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 	case S_IFCHR:
 	case S_IFSOCK:
 		inode->i_blkbits = PAGE_SHIFT;
-		init_special_inode(inode, inode->i_mode, inode->i_rdev);
+		init_special_inode(inode, inode->i_mode, rdev);
 		inode->i_op = &ceph_file_iops;
 		break;
 	case S_IFREG:
@@ -1816,60 +1847,17 @@ void ceph_async_iput(struct inode *inode)
 	}
 }
 
-/*
- * Write back inode data in a worker thread.  (This can't be done
- * in the message handler context.)
- */
-void ceph_queue_writeback(struct inode *inode)
-{
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	set_bit(CEPH_I_WORK_WRITEBACK, &ci->i_work_mask);
-
-	ihold(inode);
-	if (queue_work(ceph_inode_to_client(inode)->inode_wq,
-		       &ci->i_work)) {
-		dout("ceph_queue_writeback %p\n", inode);
-	} else {
-		dout("ceph_queue_writeback %p already queued, mask=%lx\n",
-		     inode, ci->i_work_mask);
-		iput(inode);
-	}
-}
-
-/*
- * queue an async invalidation
- */
-void ceph_queue_invalidate(struct inode *inode)
-{
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	set_bit(CEPH_I_WORK_INVALIDATE_PAGES, &ci->i_work_mask);
-
-	ihold(inode);
-	if (queue_work(ceph_inode_to_client(inode)->inode_wq,
-		       &ceph_inode(inode)->i_work)) {
-		dout("ceph_queue_invalidate %p\n", inode);
-	} else {
-		dout("ceph_queue_invalidate %p already queued, mask=%lx\n",
-		     inode, ci->i_work_mask);
-		iput(inode);
-	}
-}
-
-/*
- * Queue an async vmtruncate.  If we fail to queue work, we will handle
- * the truncation the next time we call __ceph_do_pending_vmtruncate.
- */
-void ceph_queue_vmtruncate(struct inode *inode)
+void ceph_queue_inode_work(struct inode *inode, int work_bit)
 {
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	set_bit(CEPH_I_WORK_VMTRUNCATE, &ci->i_work_mask);
+	set_bit(work_bit, &ci->i_work_mask);
 
 	ihold(inode);
-	if (queue_work(ceph_inode_to_client(inode)->inode_wq,
-		       &ci->i_work)) {
-		dout("ceph_queue_vmtruncate %p\n", inode);
+	if (queue_work(fsc->inode_wq, &ci->i_work)) {
+		dout("queue_inode_work %p, mask=%lx\n", inode, ci->i_work_mask);
 	} else {
-		dout("ceph_queue_vmtruncate %p already queued, mask=%lx\n",
+		dout("queue_inode_work %p already queued, mask=%lx\n",
 		     inode, ci->i_work_mask);
 		iput(inode);
 	}
@@ -2008,6 +1996,12 @@ static void ceph_inode_work(struct work_struct *work)
 	if (test_and_clear_bit(CEPH_I_WORK_VMTRUNCATE, &ci->i_work_mask))
 		__ceph_do_pending_vmtruncate(inode);
 
+	if (test_and_clear_bit(CEPH_I_WORK_CHECK_CAPS, &ci->i_work_mask))
+		ceph_check_caps(ci, 0, NULL);
+
+	if (test_and_clear_bit(CEPH_I_WORK_FLUSH_SNAPS, &ci->i_work_mask))
+		ceph_flush_snaps(ci, NULL);
+
 	iput(inode);
 }
 
@@ -2238,7 +2232,8 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 /*
  * setattr
  */
-int ceph_setattr(struct dentry *dentry, struct iattr *attr)
+int ceph_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+		 struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
@@ -2247,7 +2242,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 	if (ceph_snap(inode) != CEPH_NOSNAP)
 		return -EROFS;
 
-	err = setattr_prepare(dentry, attr);
+	err = setattr_prepare(&init_user_ns, dentry, attr);
 	if (err != 0)
 		return err;
 
@@ -2262,7 +2257,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 	err = __ceph_setattr(inode, attr);
 
 	if (err >= 0 && (attr->ia_valid & ATTR_MODE))
-		err = posix_acl_chmod(inode, attr->ia_mode);
+		err = posix_acl_chmod(&init_user_ns, inode, attr->ia_mode);
 
 	return err;
 }
@@ -2321,7 +2316,8 @@ int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
  * Check inode permissions.  We verify we have a valid value for
  * the AUTH cap, then call the generic handler.
  */
-int ceph_permission(struct inode *inode, int mask)
+int ceph_permission(struct user_namespace *mnt_userns, struct inode *inode,
+		    int mask)
 {
 	int err;
 
@@ -2331,7 +2327,7 @@ int ceph_permission(struct inode *inode, int mask)
 	err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED, false);
 
 	if (!err)
-		err = generic_permission(inode, mask);
+		err = generic_permission(&init_user_ns, inode, mask);
 	return err;
 }
 
@@ -2368,8 +2364,8 @@ static int statx_to_caps(u32 want, umode_t mode)
  * Get all the attributes. If we have sufficient caps for the requested attrs,
  * then we can avoid talking to the MDS at all.
  */
-int ceph_getattr(const struct path *path, struct kstat *stat,
-		 u32 request_mask, unsigned int flags)
+int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path,
+		 struct kstat *stat, u32 request_mask, unsigned int flags)
 {
 	struct inode *inode = d_inode(path->dentry);
 	struct ceph_inode_info *ci = ceph_inode(inode);
@@ -2385,7 +2381,7 @@ int ceph_getattr(const struct path *path, struct kstat *stat,
 			return err;
 	}
 
-	generic_fillattr(inode, stat);
+	generic_fillattr(&init_user_ns, inode, stat);
 	stat->ino = ceph_present_inode(inode);
 
 	/*