+
+ page = __page_cache_alloc(GFP_KERNEL);
+ if (page == NULL) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ pagelist = ceph_pagelist_alloc(GFP_KERNEL);
+ if (!pagelist) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ iov.iov_base = kmap_local_page(page);
+ iov.iov_len = len;
+ iov_iter_kvec(&iter, READ, &iov, 1, len);
+
+ pos = orig_pos;
+ ret = __ceph_sync_read(inode, &pos, &iter, &retry_op, &objvers);
+ ceph_put_cap_refs(ci, got);
+ if (ret < 0)
+ goto out;
+
+ WARN_ON_ONCE(objvers.count != 1);
+
+ /* Insert the header first */
+ header.ver = 1;
+ header.compat = 1;
+
+ /*
+ * If we hit a hole here, we should just skip filling
+ * the fscrypt for the request, because once the fscrypt
+ * is enabled, the file will be split into many blocks
+ * with the size of CEPH_FSCRYPT_BLOCK_SIZE, if there
+ * has a hole, the hole size should be multiple of block
+ * size.
+ *
+ * If the Rados object doesn't exist, it will be set 0.
+ */
+ if (!objvers.objvers[0].objver) {
+ dout("%s hit hole, ppos %lld < size %lld\n", __func__,
+ pos, i_size);
+
+ header.data_len = cpu_to_le32(8 + 8 + 4);
+ header.assert_ver = 0;
+ header.file_offset = 0;
+ header.block_size = 0;
+ ret = 0;
+ } else {
+ header.data_len = cpu_to_le32(8 + 8 + 4 + CEPH_FSCRYPT_BLOCK_SIZE);
+ header.assert_ver = cpu_to_le64(objvers.objvers[0].objver);
+ header.file_offset = cpu_to_le64(orig_pos);
+ header.block_size = cpu_to_le32(CEPH_FSCRYPT_BLOCK_SIZE);
+
+ /* truncate and zero out the extra contents for the last block */
+ memset(iov.iov_base + boff, 0, PAGE_SIZE - boff);
+
+#if 0 // Uncomment this when the fscrypt is enabled globally in kceph
+
+ /* encrypt the last block */
+ ret = fscrypt_encrypt_block_inplace(inode, page,
+ CEPH_FSCRYPT_BLOCK_SIZE,
+ 0, block,
+ GFP_KERNEL);
+ if (ret)
+ goto out;
+#endif
+ }
+
+ /* Insert the header */
+ ret = ceph_pagelist_append(pagelist, &header, sizeof(header));
+ if (ret)
+ goto out;
+
+ if (header.block_size) {
+ /* Append the last block contents to pagelist */
+ ret = ceph_pagelist_append(pagelist, iov.iov_base,
+ CEPH_FSCRYPT_BLOCK_SIZE);
+ if (ret)
+ goto out;
+ }
+ req->r_pagelist = pagelist;
+out:
+ dout("%s %p size dropping cap refs on %s\n", __func__,
+ inode, ceph_cap_string(got));
+ kunmap_local(iov.iov_base);
+ if (page)
+ __free_pages(page, 0);
+ if (ret && pagelist)
+ ceph_pagelist_release(pagelist);
+ kfree(objvers.objvers);
+ return ret;
+}
+
int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *cia)
{
struct ceph_inode_info *ci = ceph_inode(inode);
@@ -2239,12 +2383,15 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *c
struct ceph_mds_request *req;
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_cap_flush *prealloc_cf;
+ loff_t isize = i_size_read(inode);
int issued;
int release = 0, dirtied = 0;
int mask = 0;
int err = 0;
int inode_dirty_flags = 0;
bool lock_snap_rwsem = false;
+ bool fill_fscrypt;
+ int truncate_retry = 20; /* The RMW will take around 50ms */
prealloc_cf = ceph_alloc_cap_flush();
if (!prealloc_cf)
@@ -2257,6 +2404,8 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *c
return PTR_ERR(req);
}
+retry:
+ fill_fscrypt = false;
spin_lock(&ci->i_ceph_lock);
issued = __ceph_caps_issued(ci, NULL);
@@ -2378,10 +2527,27 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *c
}
}
if (ia_valid & ATTR_SIZE) {
- loff_t isize = i_size_read(inode);
-
dout("setattr %p size %lld -> %lld\n", inode, isize, attr->ia_size);
- if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size >= isize) {
+ /*
+ * Only when the new size is smaller and not aligned to
+ * CEPH_FSCRYPT_BLOCK_SIZE will the RMW is needed.
+ */
+ if (IS_ENCRYPTED(inode) && attr->ia_size < isize &&
+ (attr->ia_size % CEPH_FSCRYPT_BLOCK_SIZE)) {
+ mask |= CEPH_SETATTR_SIZE;
+ release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL |
+ CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR;
+ set_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags);
+ mask |= CEPH_SETATTR_FSCRYPT_FILE;
+ req->r_args.setattr.size =
+ cpu_to_le64(round_up(attr->ia_size,
+ CEPH_FSCRYPT_BLOCK_SIZE));
+ req->r_args.setattr.old_size =
+ cpu_to_le64(round_up(isize,
+ CEPH_FSCRYPT_BLOCK_SIZE));
+ req->r_fscrypt_file = attr->ia_size;
+ fill_fscrypt = true;
+ } else if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size >= isize) {
if (attr->ia_size > isize) {
i_size_write(inode, attr->ia_size);
inode->i_blocks = calc_inode_blocks(attr->ia_size);
@@ -2404,7 +2570,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *c
cpu_to_le64(round_up(isize,
CEPH_FSCRYPT_BLOCK_SIZE));
req->r_fscrypt_file = attr->ia_size;
- /* FIXME: client must zero out any partial blocks! */
} else {
req->r_args.setattr.size = cpu_to_le64(attr->ia_size);
req->r_args.setattr.old_size = cpu_to_le64(isize);
@@ -2476,7 +2641,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *c
if (inode_dirty_flags)
__mark_inode_dirty(inode, inode_dirty_flags);
-
if (mask) {
req->r_inode = inode;
ihold(inode);
@@ -2484,7 +2648,25 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *c
req->r_args.setattr.mask = cpu_to_le32(mask);
req->r_num_caps = 1;
req->r_stamp = attr->ia_ctime;
+ if (fill_fscrypt) {
+ err = fill_fscrypt_truncate(inode, req, attr);
+ if (err)
+ goto out;
+ }
+
+ /*
+ * The truncate request will return -EAGAIN when the
+ * last block has been updated just before the MDS
+ * successfully gets the xlock for the FILE lock. To
+ * avoid corrupting the file contents we need to retry
+ * it.
+ */
err = ceph_mdsc_do_request(mdsc, NULL, req);
+ if (err == -EAGAIN && truncate_retry--) {
+ dout("setattr %p result=%d (%s locally, %d remote), retry it!\n",
+ inode, err, ceph_cap_string(dirtied), mask);
+ goto retry;
+ }
}
out:
dout("setattr %p result=%d (%s locally, %d remote)\n", inode, err,
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b347b12e86a9..071857bb59d8 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -408,6 +408,11 @@ struct ceph_inode_info {
u32 i_truncate_seq; /* last truncate to smaller size */
u64 i_truncate_size; /* and the size we last truncated down to */
int i_truncate_pending; /* still need to call vmtruncate */
+ /*
+ * For none fscrypt case it equals to i_truncate_size or it will
+ * equals to fscrypt_file_size
+ */
+ u64 i_truncate_pagecache_size;
u64 i_max_size; /* max file size authorized by mds */
u64 i_reported_size; /* (max_)size reported to or requested of mds */
