Merge tag 'ceph-for-7.2-rc5' of https://github.com/ceph/ceph-client

Pull ceph fixes from Ilya Dryomov:
 "A bunch of assorted fixes with the majority being hardening against
  malformed input and invalid data scenarios that don't happen in real
  deployments but can be utilized to trigger use-after-free and similar
  issues, some error path leak fixups and two patches from Max to avoid
  a potential hang in __ceph_get_caps() and unintended nesting of
  current->journal_info while handling replies from the MDS.

  All marked for stable"

* tag 'ceph-for-7.2-rc5' of https://github.com/ceph/ceph-client:
  ceph: avoid fs reclaim while using current->journal_info
  ceph: add owner/capability checks for CEPH_IOC_SET_LAYOUT*
  ceph: fix hanging __ceph_get_caps() with stale mds_wanted
  rbd: Reset positive result codes to zero in object map update path
  libceph: bound pg_{temp,upmap,upmap_items} length to CEPH_PG_MAX_SIZE
  libceph: refresh auth->authorizer_buf{,_len} after authorizer update
  ceph: fix refcount leak in ceph_readdir()
  libceph: guard missing CRUSH type name lookup
  libceph: remove debugfs files before client teardown
  libceph: bound get_version reply decode to front len
  ceph: fix writeback_count leak in write_folio_nounlock()
  libceph: fix two unsafe bare decodes in decode_lockers()
  ceph: fix pre-auth out-of-bounds read on snaptrace in ceph_handle_caps()
  libceph: Reject monmaps advertising zero monitors
  libceph: reject zero bucket types in crush_decode
  libceph: Fix multiplication overflow in decode_new_up_state_weight()

13 files changed, 90 insertions, 19 deletions

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index ac90d81aa294..1f1c2810f6ee 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1950,10 +1950,15 @@ static int rbd_object_map_update_finish(struct rbd_obj_request *obj_req,
 	bool has_current_state;
 	void *p;
 
-	if (osd_req->r_result)
+	if (osd_req->r_result < 0)
 		return osd_req->r_result;
 
 	/*
+	 * Writes aren't allowed to return a data payload.
+	 */
+	WARN_ON_ONCE(osd_req->r_result > 0);
+
+	/*
 	 * Nothing to do for a snapshot object map.
 	 */
 	if (osd_req->r_num_ops == 1)
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 61bd6d92ff25..ecf33b66610c 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -790,6 +790,9 @@ static int write_folio_nounlock(struct folio *folio,
 				    ceph_wbc.truncate_size, true);
 	if (IS_ERR(req)) {
 		folio_redirty_for_writepage(wbc, folio);
+		if (atomic_long_dec_return(&fsc->writeback_count) <
+				CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
+			fsc->write_congested = false;
 		return PTR_ERR(req);
 	}
 
@@ -809,6 +812,9 @@ static int write_folio_nounlock(struct folio *folio,
 			folio_redirty_for_writepage(wbc, folio);
 			folio_end_writeback(folio);
 			ceph_osdc_put_request(req);
+			if (atomic_long_dec_return(&fsc->writeback_count) <
+					CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
+				fsc->write_congested = false;
 			return PTR_ERR(bounce_page);
 		}
 	}
@@ -847,6 +853,9 @@ static int write_folio_nounlock(struct folio *folio,
 			      ceph_vinop(inode), folio);
 			folio_redirty_for_writepage(wbc, folio);
 			folio_end_writeback(folio);
+			if (atomic_long_dec_return(&fsc->writeback_count) <
+					CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
+				fsc->write_congested = false;
 			return err;
 		}
 		if (err == -EBLOCKLISTED)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 4b37d9ffdf7f..d7283fb54cec 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3094,7 +3094,19 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
 					ret = -ERESTARTSYS;
 					break;
 				}
-				wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+
+				/*
+				 * If a cap update is lost after
+				 * mds_wanted was raised, waiting
+				 * forever will never make progress.
+				 * Retry the renew path periodically
+				 * so we can resend synchronously.
+				 */
+				if (!wait_woken(&wait, TASK_INTERRUPTIBLE,
+						CEPH_GET_CAPS_WAIT_TIMEOUT)) {
+					ret = -EUCLEAN;
+					break;
+				}
 			}
 
 			remove_wait_queue(&ci->i_cap_wq, &wait);
@@ -3128,7 +3140,8 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
 				continue;
 			}
 			if (ret == -EUCLEAN) {
-				/* session was killed, try renew caps */
+				/* session was killed or a waited cap
+				 * request needs a retry */
 				ret = ceph_renew_caps(inode, flags);
 				if (ret == 0)
 					continue;
@@ -4375,6 +4388,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 
 	snaptrace = h + 1;
 	snaptrace_len = le32_to_cpu(h->snap_trace_len);
+	ceph_decode_need(&snaptrace, end, snaptrace_len, bad);
 	p = snaptrace + snaptrace_len;
 
 	if (msg_version >= 2) {
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 27ce9e55e947..ef9e92e362d3 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -546,11 +546,16 @@ more:
 			pr_warn_client(cl,
 				"%p %llx.%llx rde->offset 0x%llx ctx->pos 0x%llx\n",
 				inode, ceph_vinop(inode), rde->offset, ctx->pos);
+			ceph_mdsc_put_request(dfi->last_readdir);
+			dfi->last_readdir = NULL;
 			return -EIO;
 		}
 
-		if (WARN_ON_ONCE(!rde->inode.in))
+		if (WARN_ON_ONCE(!rde->inode.in)) {
+			ceph_mdsc_put_request(dfi->last_readdir);
+			dfi->last_readdir = NULL;
 			return -EIO;
+		}
 
 		ctx->pos = rde->offset;
 		doutc(cl, "%p %llx.%llx (%d/%d) -> %llx '%.*s' %p\n", inode,
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 71161f2b2151..a4a2a4b6a027 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -314,7 +314,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
 }
 
 /*
- * try renew caps after session gets killed.
+ * Retry cap acquisition after a stale session or a lost cap update.
  */
 int ceph_renew_caps(struct inode *inode, int fmode)
 {
@@ -322,14 +322,15 @@ int ceph_renew_caps(struct inode *inode, int fmode)
 	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_request *req;
-	int err, flags, wanted;
+	int err, flags, wanted, issued;
 
 	spin_lock(&ci->i_ceph_lock);
 	__ceph_touch_fmode(ci, mdsc, fmode);
 	wanted = __ceph_caps_file_wanted(ci);
+	issued = __ceph_caps_issued(ci, NULL);
 	if (__ceph_is_any_real_caps(ci) &&
-	    (!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap)) {
-		int issued = __ceph_caps_issued(ci, NULL);
+	    (!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap) &&
+	    (issued & wanted) == wanted) {
 		spin_unlock(&ci->i_ceph_lock);
 		doutc(cl, "%p %llx.%llx want %s issued %s updating mds_wanted\n",
 		      inode, ceph_vinop(inode), ceph_cap_string(wanted),
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 15cde055f3da..de07f19b0caa 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -72,6 +72,9 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 	struct ceph_ioctl_layout nl;
 	int err;
 
+	if (!inode_owner_or_capable(&nop_mnt_idmap, inode))
+		return -EACCES;
+
 	if (copy_from_user(&l, arg, sizeof(l)))
 		return -EFAULT;
 
@@ -142,6 +145,9 @@ static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
 	int err;
 	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc;
 
+	if (!inode_owner_or_capable(&nop_mnt_idmap, inode))
+		return -EACCES;
+
 	/* copy and validate */
 	if (copy_from_user(&l, arg, sizeof(l)))
 		return -EFAULT;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 853bf698b356..3c692ad02c85 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <linux/gfp.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/delay.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -4015,6 +4016,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	struct ceph_mds_reply_head *head = msg->front.iov_base;
 	struct ceph_mds_reply_info_parsed *rinfo;  /* parsed reply info */
 	struct ceph_snap_realm *realm;
+	unsigned int nofs_flags;
 	u64 tid;
 	int err, result;
 	int mds = session->s_mds;
@@ -4158,6 +4160,14 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
 	/* insert trace into our cache */
 	mutex_lock(&req->r_fill_mutex);
+
+	/* disable fs reclaim while we are using current->journal_info
+	 * for our own purposes, or else shrinkers of other
+	 * filesystems might dereference this pointer as a different
+	 * type
+	 */
+	nofs_flags = memalloc_nofs_save();
+
 	current->journal_info = req;
 	err = ceph_fill_trace(mdsc->fsc->sb, req);
 	if (err == 0) {
@@ -4166,6 +4176,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 			err = ceph_readdir_prepopulate(req, req->r_session);
 	}
 	current->journal_info = NULL;
+	memalloc_nofs_restore(nofs_flags);
 	mutex_unlock(&req->r_fill_mutex);
 
 	up_read(&mdsc->snap_rwsem);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 731d6ad04956..0ece4c9e3529 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -77,6 +77,7 @@ struct ceph_fs_client;
 struct ceph_cap;
 
 #define MDS_AUTH_UID_ANY -1
+#define CEPH_GET_CAPS_WAIT_TIMEOUT (5 * HZ)
 #define CEPH_CAP_FLUSH_WAIT_TIMEOUT_SEC 60
 #define CEPH_CAP_FLUSH_MAX_DUMP_ENTRIES 5
 #define CEPH_CAP_FLUSH_MAX_DUMP_ITERS 5
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index 9e64e82d0b63..50a79e8aa656 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -849,9 +849,16 @@ static int ceph_x_update_authorizer(
 
 	au = (struct ceph_x_authorizer *)auth->authorizer;
 	if (au->secret_id < th->secret_id) {
+		int ret;
+
 		dout("ceph_x_update_authorizer service %u secret %llu < %llu\n",
 		     au->service, au->secret_id, th->secret_id);
-		return ceph_x_build_authorizer(ac, th, au);
+		ret = ceph_x_build_authorizer(ac, th, au);
+		if (ret)
+			return ret;
+
+		auth->authorizer_buf = au->buf->vec.iov_base;
+		auth->authorizer_buf_len = au->buf->vec.iov_len;
 	}
 	return 0;
 }
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 952121849180..a797c7360e3c 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -762,13 +762,13 @@ void ceph_destroy_client(struct ceph_client *client)
 
 	atomic_set(&client->msgr.stopping, 1);
 
+	ceph_debugfs_client_cleanup(client);
+
 	/* unmount */
 	ceph_osdc_stop(&client->osdc);
 	ceph_monc_stop(&client->monc);
 	ceph_messenger_fini(&client->msgr);
 
-	ceph_debugfs_client_cleanup(client);
-
 	ceph_destroy_options(client->options);
 
 	kfree(client);
diff --git a/net/ceph/cls_lock_client.c b/net/ceph/cls_lock_client.c
index c6956f1df333..377336982f7d 100644
--- a/net/ceph/cls_lock_client.c
+++ b/net/ceph/cls_lock_client.c
@@ -299,7 +299,7 @@ static int decode_lockers(void **p, void *end, u8 *type, char **tag,
 	if (ret)
 		return ret;
 
-	*num_lockers = ceph_decode_32(p);
+	ceph_decode_32_safe(p, end, *num_lockers, err_inval);
 	*lockers = kzalloc_objs(**lockers, *num_lockers, GFP_NOIO);
 	if (!*lockers)
 		return -ENOMEM;
@@ -310,7 +310,8 @@ static int decode_lockers(void **p, void *end, u8 *type, char **tag,
 			goto err_free_lockers;
 	}
 
-	*type = ceph_decode_8(p);
+	ret = -EINVAL;
+	ceph_decode_8_safe(p, end, *type, err_free_lockers);
 	s = ceph_extract_encoded_string(p, end, NULL, GFP_NOIO);
 	if (IS_ERR(s)) {
 		ret = PTR_ERR(s);
@@ -320,6 +321,9 @@ static int decode_lockers(void **p, void *end, u8 *type, char **tag,
 	*tag = s;
 	return 0;
 
+err_inval:
+	return -EINVAL;
+
 err_free_lockers:
 	ceph_free_lockers(*lockers, *num_lockers);
 	return ret;
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index d2cdc8ee3155..c56457378d00 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -114,7 +114,7 @@ static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2)
 
 	dout("%s fsid %pU epoch %u num_mon %u\n", __func__, &fsid, epoch,
 	     num_mon);
-	if (num_mon > CEPH_MAX_MON)
+	if (num_mon == 0 || num_mon > CEPH_MAX_MON)
 		goto e_inval;
 
 	monmap = kmalloc_flex(*monmap, mon_inst, num_mon, GFP_NOIO);
@@ -821,7 +821,7 @@ static void handle_get_version_reply(struct ceph_mon_client *monc,
 	struct ceph_mon_generic_request *req;
 	u64 tid = le64_to_cpu(msg->hdr.tid);
 	void *p = msg->front.iov_base;
-	void *end = p + msg->front_alloc_len;
+	void *const end = p + msg->front.iov_len;
 	u64 handle;
 
 	dout("%s msg %p tid %llu\n", __func__, msg, tid);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 8b5b0587a0cf..a4b0dd8672ec 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -518,6 +518,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 		ceph_decode_need(p, end, 4*sizeof(u32), bad);
 		b->id = ceph_decode_32(p);
 		b->type = ceph_decode_16(p);
+		if (b->type == 0)
+			goto bad;
 		b->alg = ceph_decode_8(p);
 		if (b->alg != alg) {
 			b->alg = 0;
@@ -1436,7 +1438,7 @@ static struct ceph_pg_mapping *__decode_pg_temp(void **p, void *end,
 	ceph_decode_32_safe(p, end, len, e_inval);
 	if (len == 0 && incremental)
 		return NULL;	/* new_pg_temp: [] to remove */
-	if ((size_t)len > (SIZE_MAX - sizeof(*pg)) / sizeof(u32))
+	if (len > CEPH_PG_MAX_SIZE)
 		return ERR_PTR(-EINVAL);
 
 	ceph_decode_need(p, end, len * sizeof(u32), e_inval);
@@ -1617,7 +1619,7 @@ static struct ceph_pg_mapping *__decode_pg_upmap_items(void **p, void *end,
 	u32 len, i;
 
 	ceph_decode_32_safe(p, end, len, e_inval);
-	if ((size_t)len > (SIZE_MAX - sizeof(*pg)) / (2 * sizeof(u32)))
+	if (len > CEPH_PG_MAX_SIZE)
 		return ERR_PTR(-EINVAL);
 
 	ceph_decode_need(p, end, 2 * len * sizeof(u32), e_inval);
@@ -1842,6 +1844,8 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
 	void *new_up_client;
 	void *new_state;
 	void *new_weight_end;
+	const u32 new_state_item_size =
+	    sizeof(u32) + (struct_v >= 5 ? sizeof(u32) : sizeof(u8));
 	u32 len;
 	int ret;
 	int i;
@@ -1862,7 +1866,8 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
 
 	new_state = *p;
 	ceph_decode_32_safe(p, end, len, e_inval);
-	len *= sizeof(u32) + (struct_v >= 5 ? sizeof(u32) : sizeof(u8));
+	if (check_mul_overflow(len, new_state_item_size, &len))
+		goto e_inval;
 	ceph_decode_need(p, end, len, e_inval);
 	*p += len;
 
@@ -3055,8 +3060,11 @@ static int get_immediate_parent(struct crush_map *c, int id,
 			if (b->items[j] != id)
 				continue;
 
-			*parent_type_id = b->type;
 			type_cn = lookup_crush_name(&c->type_names, b->type);
+			if (WARN_ON_ONCE(!type_cn))
+				continue;
+
+			*parent_type_id = b->type;
 			parent_loc->cl_type_name = type_cn->cn_name;
 			parent_loc->cl_name = cn->cn_name;
 			return b->id;