Merge tag 'ceph-for-7.0-rc1' of https://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "This adds support for the upcoming aes256k key type in CephX that is
  based on Kerberos 5 and brings a bunch of assorted CephFS fixes from
  Ethan and Sam. One of Sam's patches in particular undoes a change in
  the fscrypt area that had an inadvertent side effect of making CephFS
  behave as if mounted with wsize=4096 and leading to the corresponding
  degradation in performance, especially for sequential writes"

* tag 'ceph-for-7.0-rc1' of https://github.com/ceph/ceph-client:
  ceph: assert loop invariants in ceph_writepages_start()
  ceph: remove error return from ceph_process_folio_batch()
  ceph: fix write storm on fscrypted files
  ceph: do not propagate page array emplacement errors as batch errors
  ceph: supply snapshot context in ceph_uninline_data()
  ceph: supply snapshot context in ceph_zero_partial_object()
  libceph: adapt ceph_x_challenge_blob hashing and msgr1 message signing
  libceph: add support for CEPH_CRYPTO_AES256KRB5
  libceph: introduce ceph_crypto_key_prepare()
  libceph: generalize ceph_x_encrypt_offset() and ceph_x_encrypt_buflen()
  libceph: define and enforce CEPH_MAX_KEY_LEN

2 files changed, 48 insertions, 16 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 63b75d214210..ce09ff3e020f 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1000,7 +1000,8 @@ unsigned int ceph_define_write_size(struct address_space *mapping)
 {
 	struct inode *inode = mapping->host;
 	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
-	unsigned int wsize = i_blocksize(inode);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	unsigned int wsize = ci->i_layout.stripe_unit;
 
 	if (fsc->mount_options->wsize < wsize)
 		wsize = fsc->mount_options->wsize;
@@ -1283,16 +1284,16 @@ static inline int move_dirty_folio_in_page_array(struct address_space *mapping,
 }
 
 static
-int ceph_process_folio_batch(struct address_space *mapping,
-			     struct writeback_control *wbc,
-			     struct ceph_writeback_ctl *ceph_wbc)
+void ceph_process_folio_batch(struct address_space *mapping,
+			      struct writeback_control *wbc,
+			      struct ceph_writeback_ctl *ceph_wbc)
 {
 	struct inode *inode = mapping->host;
 	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 	struct ceph_client *cl = fsc->client;
 	struct folio *folio = NULL;
 	unsigned i;
-	int rc = 0;
+	int rc;
 
 	for (i = 0; can_next_page_be_processed(ceph_wbc, i); i++) {
 		folio = ceph_wbc->fbatch.folios[i];
@@ -1322,12 +1323,10 @@ int ceph_process_folio_batch(struct address_space *mapping,
 		rc = ceph_check_page_before_write(mapping, wbc,
 						  ceph_wbc, folio);
 		if (rc == -ENODATA) {
-			rc = 0;
 			folio_unlock(folio);
 			ceph_wbc->fbatch.folios[i] = NULL;
 			continue;
 		} else if (rc == -E2BIG) {
-			rc = 0;
 			folio_unlock(folio);
 			ceph_wbc->fbatch.folios[i] = NULL;
 			break;
@@ -1379,8 +1378,6 @@ int ceph_process_folio_batch(struct address_space *mapping,
 	}
 
 	ceph_wbc->processed_in_fbatch = i;
-
-	return rc;
 }
 
 static inline
@@ -1666,7 +1663,9 @@ retry:
 		tag_pages_for_writeback(mapping, ceph_wbc.index, ceph_wbc.end);
 
 	while (!has_writeback_done(&ceph_wbc)) {
-		ceph_wbc.locked_pages = 0;
+		BUG_ON(ceph_wbc.locked_pages);
+		BUG_ON(ceph_wbc.pages);
+
 		ceph_wbc.max_pages = ceph_wbc.wsize >> PAGE_SHIFT;
 
 get_more_pages:
@@ -1684,10 +1683,8 @@ get_more_pages:
 			break;
 
 process_folio_batch:
-		rc = ceph_process_folio_batch(mapping, wbc, &ceph_wbc);
+		ceph_process_folio_batch(mapping, wbc, &ceph_wbc);
 		ceph_shift_unused_folios_left(&ceph_wbc.fbatch);
-		if (rc)
-			goto release_folios;
 
 		/* did we get anything? */
 		if (!ceph_wbc.locked_pages)
@@ -2199,6 +2196,7 @@ int ceph_uninline_data(struct file *file)
 	struct ceph_osd_request *req = NULL;
 	struct ceph_cap_flush *prealloc_cf = NULL;
 	struct folio *folio = NULL;
+	struct ceph_snap_context *snapc = NULL;
 	u64 inline_version = CEPH_INLINE_NONE;
 	struct page *pages[1];
 	int err = 0;
@@ -2226,6 +2224,24 @@ int ceph_uninline_data(struct file *file)
 	if (inline_version == 1) /* initial version, no data */
 		goto out_uninline;
 
+	down_read(&fsc->mdsc->snap_rwsem);
+	spin_lock(&ci->i_ceph_lock);
+	if (__ceph_have_pending_cap_snap(ci)) {
+		struct ceph_cap_snap *capsnap =
+				list_last_entry(&ci->i_cap_snaps,
+						struct ceph_cap_snap,
+						ci_item);
+		snapc = ceph_get_snap_context(capsnap->context);
+	} else {
+		if (!ci->i_head_snapc) {
+			ci->i_head_snapc = ceph_get_snap_context(
+				ci->i_snap_realm->cached_context);
+		}
+		snapc = ceph_get_snap_context(ci->i_head_snapc);
+	}
+	spin_unlock(&ci->i_ceph_lock);
+	up_read(&fsc->mdsc->snap_rwsem);
+
 	folio = read_mapping_folio(inode->i_mapping, 0, file);
 	if (IS_ERR(folio)) {
 		err = PTR_ERR(folio);
@@ -2241,7 +2257,7 @@ int ceph_uninline_data(struct file *file)
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 				    ceph_vino(inode), 0, &len, 0, 1,
 				    CEPH_OSD_OP_CREATE, CEPH_OSD_FLAG_WRITE,
-				    NULL, 0, 0, false);
+				    snapc, 0, 0, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto out_unlock;
@@ -2257,7 +2273,7 @@ int ceph_uninline_data(struct file *file)
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 				    ceph_vino(inode), 0, &len, 1, 3,
 				    CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE,
-				    NULL, ci->i_truncate_seq,
+				    snapc, ci->i_truncate_seq,
 				    ci->i_truncate_size, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
@@ -2320,6 +2336,7 @@ out_unlock:
 		folio_put(folio);
 	}
 out:
+	ceph_put_snap_context(snapc);
 	ceph_free_cap_flush(prealloc_cf);
 	doutc(cl, "%llx.%llx inline_version %llu = %d\n",
 	      ceph_vinop(inode), inline_version, err);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 31b691b2aea2..72cc67ab4ead 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -2568,6 +2568,7 @@ static int ceph_zero_partial_object(struct inode *inode,
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 	struct ceph_osd_request *req;
+	struct ceph_snap_context *snapc;
 	int ret = 0;
 	loff_t zero = 0;
 	int op;
@@ -2582,12 +2583,25 @@ static int ceph_zero_partial_object(struct inode *inode,
 		op = CEPH_OSD_OP_ZERO;
 	}
 
+	spin_lock(&ci->i_ceph_lock);
+	if (__ceph_have_pending_cap_snap(ci)) {
+		struct ceph_cap_snap *capsnap =
+				list_last_entry(&ci->i_cap_snaps,
+						struct ceph_cap_snap,
+						ci_item);
+		snapc = ceph_get_snap_context(capsnap->context);
+	} else {
+		BUG_ON(!ci->i_head_snapc);
+		snapc = ceph_get_snap_context(ci->i_head_snapc);
+	}
+	spin_unlock(&ci->i_ceph_lock);
+
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 					ceph_vino(inode),
 					offset, length,
 					0, 1, op,
 					CEPH_OSD_FLAG_WRITE,
-					NULL, 0, 0, false);
+					snapc, 0, 0, false);
 	if (IS_ERR(req)) {
 		ret = PTR_ERR(req);
 		goto out;
@@ -2601,6 +2615,7 @@ static int ceph_zero_partial_object(struct inode *inode,
 	ceph_osdc_put_request(req);
 
 out:
+	ceph_put_snap_context(snapc);
 	return ret;
 }