Merge tag 'ceph-for-6.19-rc1' of https://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov: "We have a patch that adds an initial set of tracepoints to the MDS client from Max, a fix that hardens osdmap parsing code from myself (marked for stable) and a few assorted fixups" * tag 'ceph-for-6.19-rc1' of https://github.com/ceph/ceph-client: rbd: stop selecting CRC32, CRYPTO, and CRYPTO_AES ceph: stop selecting CRC32, CRYPTO, and CRYPTO_AES libceph: make decode_pool() more resilient against corrupted osdmaps libceph: Amend checking to fix `make W=1` build breakage ceph: Amend checking to fix `make W=1` build breakage ceph: add trace points to the MDS client libceph: fix log output race condition in OSD client
2025-12-16 12:01:47 +01:00 · 2025-12-14 15:24:10 +12:00
parent 4cfc21494a 21c1466ea2
commit 0dfb36b2dc
9 changed files with 316 additions and 79 deletions
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -316,9 +316,6 @@ config BLK_DEV_RBD
 	tristate "Rados block device (RBD)"
 	depends on INET && BLOCK
 	select CEPH_LIB
-	select CRC32
-	select CRYPTO_AES
-	select CRYPTO
 	help
 	  Say Y here if you want include the Rados block device, which stripes
 	  a block device over objects stored in the Ceph distributed object
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -3,9 +3,6 @@ config CEPH_FS
 	tristate "Ceph distributed file system"
 	depends on INET
 	select CEPH_LIB
-	select CRC32
-	select CRYPTO_AES
-	select CRYPTO
 	select NETFS_SUPPORT
 	select FS_ENCRYPTION_ALGS if FS_ENCRYPTION
 	default n
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -18,6 +18,7 @@
 #include "crypto.h"
 #include <linux/ceph/decode.h>
 #include <linux/ceph/messenger.h>
+#include <trace/events/ceph.h>

 /*
 * Capability management
@@ -4452,6 +4453,9 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	      session->s_mds, ceph_cap_op_name(op), vino.ino, vino.snap, inode,
 	      seq, issue_seq, mseq);

+	trace_ceph_handle_caps(mdsc, session, op, &vino, ceph_inode(inode),
+			       seq, issue_seq, mseq);
+
 	mutex_lock(&session->s_mutex);

 	if (!inode) {
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -24,6 +24,7 @@
 #include <linux/ceph/pagelist.h>
 #include <linux/ceph/auth.h>
 #include <linux/ceph/debugfs.h>
+#include <trace/events/ceph.h>

 #define RECONNECT_MAX_SIZE (INT_MAX - PAGE_SIZE)

@@ -3288,6 +3289,8 @@ static void complete_request(struct ceph_mds_client *mdsc,
 {
 	req->r_end_latency = ktime_get();

+	trace_ceph_mdsc_complete_request(mdsc, req);
+
 	if (req->r_callback)
 		req->r_callback(mdsc, req);
 	complete_all(&req->r_completion);
@@ -3419,6 +3422,8 @@ static int __send_request(struct ceph_mds_session *session,
 {
 	int err;

+	trace_ceph_mdsc_send_request(session, req);
+
 	err = __prepare_send_request(session, req, drop_cap_releases);
 	if (!err) {
 		ceph_msg_get(req->r_request);
@@ -3470,6 +3475,8 @@ static void __do_request(struct ceph_mds_client *mdsc,
 		}
 		if (mdsc->mdsmap->m_epoch == 0) {
 			doutc(cl, "no mdsmap, waiting for map\n");
+			trace_ceph_mdsc_suspend_request(mdsc, session, req,
+							ceph_mdsc_suspend_reason_no_mdsmap);
 			list_add(&req->r_wait, &mdsc->waiting_for_map);
 			return;
 		}
@@ -3491,6 +3498,8 @@ static void __do_request(struct ceph_mds_client *mdsc,
 			goto finish;
 		}
 		doutc(cl, "no mds or not active, waiting for map\n");
+		trace_ceph_mdsc_suspend_request(mdsc, session, req,
+						ceph_mdsc_suspend_reason_no_active_mds);
 		list_add(&req->r_wait, &mdsc->waiting_for_map);
 		return;
 	}
@@ -3536,9 +3545,11 @@ static void __do_request(struct ceph_mds_client *mdsc,
 		 * it to the mdsc queue.
 		 */
 		if (session->s_state == CEPH_MDS_SESSION_REJECTED) {
-			if (ceph_test_mount_opt(mdsc->fsc, CLEANRECOVER))
+			if (ceph_test_mount_opt(mdsc->fsc, CLEANRECOVER)) {
+				trace_ceph_mdsc_suspend_request(mdsc, session, req,
+								ceph_mdsc_suspend_reason_rejected);
 				list_add(&req->r_wait, &mdsc->waiting_for_map);
-			else
+			} else
 				err = -EACCES;
 			goto out_session;
 		}
@@ -3552,6 +3563,8 @@ static void __do_request(struct ceph_mds_client *mdsc,
 			if (random)
 				req->r_resend_mds = mds;
 		}
+		trace_ceph_mdsc_suspend_request(mdsc, session, req,
+						ceph_mdsc_suspend_reason_session);
 		list_add(&req->r_wait, &session->s_waiting);
 		goto out_session;
 	}
@@ -3652,6 +3665,7 @@ static void __wake_requests(struct ceph_mds_client *mdsc,
 		list_del_init(&req->r_wait);
 		doutc(cl, " wake request %p tid %llu\n", req,
 		      req->r_tid);
+		trace_ceph_mdsc_resume_request(mdsc, req);
 		__do_request(mdsc, req);
 	}
 }
@@ -3678,6 +3692,7 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds)
 		    req->r_session->s_mds == mds) {
 			doutc(cl, " kicking tid %llu\n", req->r_tid);
 			list_del_init(&req->r_wait);
+			trace_ceph_mdsc_resume_request(mdsc, req);
 			__do_request(mdsc, req);
 		}
 	}
@@ -3724,6 +3739,7 @@ int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir,
 	doutc(cl, "submit_request on %p for inode %p\n", req, dir);
 	mutex_lock(&mdsc->mutex);
 	__register_request(mdsc, req, dir);
+	trace_ceph_mdsc_submit_request(mdsc, req);
 	__do_request(mdsc, req);
 	err = req->r_err;
 	mutex_unlock(&mdsc->mutex);
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -374,7 +374,7 @@ static int build_snap_context(struct ceph_mds_client *mdsc,

 	/* alloc new snap context */
 	err = -ENOMEM;
-	if (num > (SIZE_MAX - sizeof(*snapc)) / sizeof(u64))
+	if ((size_t)num > (SIZE_MAX - sizeof(*snapc)) / sizeof(u64))
 		goto fail;
 	snapc = ceph_create_snap_context(num, GFP_NOFS);
 	if (!snapc)
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -30,6 +30,9 @@

 #include <uapi/linux/magic.h>

+#define CREATE_TRACE_POINTS
+#include <trace/events/ceph.h>
+
 static DEFINE_SPINLOCK(ceph_fsc_lock);
 static LIST_HEAD(ceph_fsc_list);

--- a/include/trace/events/ceph.h
+++ b/include/trace/events/ceph.h
@@ -0,0 +1,234 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Ceph filesystem support module tracepoints
+ *
+ * Copyright (C) 2025 IONOS SE. All Rights Reserved.
+ * Written by Max Kellermann (max.kellermann@ionos.com)
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM ceph
+
+#if !defined(_TRACE_CEPH_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_CEPH_H
+
+#include <linux/tracepoint.h>
+
+#define ceph_mdsc_suspend_reasons						\
+	EM(ceph_mdsc_suspend_reason_no_mdsmap,		"no-mdsmap")		\
+	EM(ceph_mdsc_suspend_reason_no_active_mds,	"no-active-mds")	\
+	EM(ceph_mdsc_suspend_reason_rejected,		"rejected")		\
+	E_(ceph_mdsc_suspend_reason_session,		"session")
+
+#ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
+#define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
+
+#undef EM
+#undef E_
+#define EM(a, b) a,
+#define E_(a, b) a
+
+enum ceph_mdsc_suspend_reason { ceph_mdsc_suspend_reasons } __mode(byte);
+
+#endif
+
+/*
+ * Export enum symbols via userspace.
+ */
+#undef EM
+#undef E_
+#define EM(a, b) TRACE_DEFINE_ENUM(a);
+#define E_(a, b) TRACE_DEFINE_ENUM(a);
+
+ceph_mdsc_suspend_reasons;
+
+/*
+ * Now redefine the EM() and E_() macros to map the enums to the strings that
+ * will be printed in the output.
+ */
+#undef EM
+#undef E_
+#define EM(a, b)	{ a, b },
+#define E_(a, b)	{ a, b }
+
+TRACE_EVENT(ceph_mdsc_submit_request,
+	TP_PROTO(struct ceph_mds_client *mdsc,
+		 struct ceph_mds_request *req),
+
+	TP_ARGS(mdsc, req),
+
+	TP_STRUCT__entry(
+		__field(u64,	tid)
+		__field(int,	op)
+		__field(u64,	ino)
+		__field(u64,	snap)
+	),
+
+	TP_fast_assign(
+		struct inode *inode;
+
+		__entry->tid = req->r_tid;
+		__entry->op = req->r_op;
+
+		inode = req->r_inode;
+		if (inode == NULL && req->r_dentry)
+			inode = d_inode(req->r_dentry);
+
+		if (inode) {
+			__entry->ino = ceph_ino(inode);
+			__entry->snap = ceph_snap(inode);
+		} else {
+			__entry->ino = __entry->snap = 0;
+		}
+	),
+
+	TP_printk("R=%llu op=%s ino=%llx,%llx",
+		  __entry->tid,
+		  ceph_mds_op_name(__entry->op),
+		  __entry->ino, __entry->snap)
+);
+
+TRACE_EVENT(ceph_mdsc_suspend_request,
+	TP_PROTO(struct ceph_mds_client *mdsc,
+		     struct ceph_mds_session *session,
+		     struct ceph_mds_request *req,
+		     enum ceph_mdsc_suspend_reason reason),
+
+	TP_ARGS(mdsc, session, req, reason),
+
+	TP_STRUCT__entry(
+		__field(u64,				tid)
+		__field(int,				op)
+		__field(int,				mds)
+		__field(enum ceph_mdsc_suspend_reason,	reason)
+	),
+
+	TP_fast_assign(
+		__entry->tid = req->r_tid;
+		__entry->op = req->r_op;
+		__entry->mds = session ? session->s_mds : -1;
+		__entry->reason = reason;
+	),
+
+	TP_printk("R=%llu op=%s reason=%s",
+		  __entry->tid,
+		  ceph_mds_op_name(__entry->op),
+		  __print_symbolic(__entry->reason, ceph_mdsc_suspend_reasons))
+);
+
+TRACE_EVENT(ceph_mdsc_resume_request,
+	TP_PROTO(struct ceph_mds_client *mdsc,
+		 struct ceph_mds_request *req),
+
+	TP_ARGS(mdsc, req),
+
+	TP_STRUCT__entry(
+		__field(u64,				tid)
+		__field(int,				op)
+	),
+
+	TP_fast_assign(
+		__entry->tid = req->r_tid;
+		__entry->op = req->r_op;
+	),
+
+	TP_printk("R=%llu op=%s",
+		  __entry->tid,
+		  ceph_mds_op_name(__entry->op))
+);
+
+TRACE_EVENT(ceph_mdsc_send_request,
+	TP_PROTO(struct ceph_mds_session *session,
+		 struct ceph_mds_request *req),
+
+	TP_ARGS(session, req),
+
+	TP_STRUCT__entry(
+		__field(u64,		tid)
+		__field(int,		op)
+		__field(int,		mds)
+	),
+
+	TP_fast_assign(
+		__entry->tid = req->r_tid;
+		__entry->op = req->r_op;
+		__entry->mds = session->s_mds;
+	),
+
+	TP_printk("R=%llu op=%s mds=%d",
+		  __entry->tid,
+		  ceph_mds_op_name(__entry->op),
+		  __entry->mds)
+);
+
+TRACE_EVENT(ceph_mdsc_complete_request,
+	TP_PROTO(struct ceph_mds_client *mdsc,
+		     struct ceph_mds_request *req),
+
+	TP_ARGS(mdsc, req),
+
+	TP_STRUCT__entry(
+		__field(u64,			tid)
+		__field(int,			op)
+		__field(int,			err)
+		__field(unsigned long,		latency_ns)
+	),
+
+	TP_fast_assign(
+		__entry->tid = req->r_tid;
+		__entry->op = req->r_op;
+		__entry->err = req->r_err;
+		__entry->latency_ns = req->r_end_latency - req->r_start_latency;
+	),
+
+	TP_printk("R=%llu op=%s err=%d latency_ns=%lu",
+		  __entry->tid,
+		  ceph_mds_op_name(__entry->op),
+		  __entry->err,
+		  __entry->latency_ns)
+);
+
+TRACE_EVENT(ceph_handle_caps,
+	TP_PROTO(struct ceph_mds_client *mdsc,
+		 struct ceph_mds_session *session,
+		 int op,
+		 const struct ceph_vino *vino,
+		 struct ceph_inode_info *inode,
+		 u32 seq, u32 mseq, u32 issue_seq),
+
+	TP_ARGS(mdsc, session, op, vino, inode, seq, mseq, issue_seq),
+
+	TP_STRUCT__entry(
+		__field(int,	mds)
+		__field(int,	op)
+		__field(u64,	ino)
+		__field(u64,	snap)
+		__field(u32,	seq)
+		__field(u32,	mseq)
+		__field(u32,	issue_seq)
+	),
+
+	TP_fast_assign(
+		__entry->mds = session->s_mds;
+		__entry->op = op;
+		__entry->ino = vino->ino;
+		__entry->snap = vino->snap;
+		__entry->seq = seq;
+		__entry->mseq = mseq;
+		__entry->issue_seq = issue_seq;
+	),
+
+	TP_printk("mds=%d op=%s vino=%llx.%llx seq=%u iseq=%u mseq=%u",
+		  __entry->mds,
+		  ceph_cap_op_name(__entry->op),
+		  __entry->ino,
+		  __entry->snap,
+		  __entry->seq,
+		  __entry->issue_seq,
+		  __entry->mseq)
+);
+
+#undef EM
+#undef E_
+#endif /* _TRACE_CEPH_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1280,8 +1280,7 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum)
 static struct ceph_osd *get_osd(struct ceph_osd *osd)
 {
 	if (refcount_inc_not_zero(&osd->o_ref)) {
-		dout("get_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref)-1,
-		     refcount_read(&osd->o_ref));
+		dout("get_osd %p -> %d\n", osd, refcount_read(&osd->o_ref));
 		return osd;
 	} else {
 		dout("get_osd %p FAIL\n", osd);
@@ -1291,8 +1290,7 @@ static struct ceph_osd *get_osd(struct ceph_osd *osd)

 static void put_osd(struct ceph_osd *osd)
 {
-	dout("put_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref),
-	     refcount_read(&osd->o_ref) - 1);
+	dout("put_osd %p -> %d\n", osd, refcount_read(&osd->o_ref) - 1);
 	if (refcount_dec_and_test(&osd->o_ref)) {
 		osd_cleanup(osd);
 		kfree(osd);
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -806,51 +806,49 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
 	ceph_decode_need(p, end, len, bad);
 	pool_end = *p + len;

+	ceph_decode_need(p, end, 4 + 4 + 4, bad);
 	pi->type = ceph_decode_8(p);
 	pi->size = ceph_decode_8(p);
 	pi->crush_ruleset = ceph_decode_8(p);
 	pi->object_hash = ceph_decode_8(p);
-
 	pi->pg_num = ceph_decode_32(p);
 	pi->pgp_num = ceph_decode_32(p);

-	*p += 4 + 4;  /* skip lpg* */
-	*p += 4;      /* skip last_change */
-	*p += 8 + 4;  /* skip snap_seq, snap_epoch */
+	/* lpg*, last_change, snap_seq, snap_epoch */
+	ceph_decode_skip_n(p, end, 8 + 4 + 8 + 4, bad);

 	/* skip snaps */
-	num = ceph_decode_32(p);
+	ceph_decode_32_safe(p, end, num, bad);
 	while (num--) {
-		*p += 8;  /* snapid key */
-		*p += 1 + 1; /* versions */
-		len = ceph_decode_32(p);
-		*p += len;
+		/* snapid key, pool snap (with versions) */
+		ceph_decode_skip_n(p, end, 8 + 2, bad);
+		ceph_decode_skip_string(p, end, bad);
 	}

-	/* skip removed_snaps */
-	num = ceph_decode_32(p);
-	*p += num * (8 + 8);
+	/* removed_snaps */
+	ceph_decode_skip_map(p, end, 64, 64, bad);

+	ceph_decode_need(p, end, 8 + 8 + 4, bad);
 	*p += 8;  /* skip auid */
 	pi->flags = ceph_decode_64(p);
 	*p += 4;  /* skip crash_replay_interval */

 	if (ev >= 7)
-		pi->min_size = ceph_decode_8(p);
+		ceph_decode_8_safe(p, end, pi->min_size, bad);
 	else
 		pi->min_size = pi->size - pi->size / 2;

 	if (ev >= 8)
-		*p += 8 + 8;  /* skip quota_max_* */
+		/* quota_max_* */
+		ceph_decode_skip_n(p, end, 8 + 8, bad);

 	if (ev >= 9) {
-		/* skip tiers */
-		num = ceph_decode_32(p);
-		*p += num * 8;
+		/* tiers */
+		ceph_decode_skip_set(p, end, 64, bad);

+		ceph_decode_need(p, end, 8 + 1 + 8 + 8, bad);
 		*p += 8;  /* skip tier_of */
 		*p += 1;  /* skip cache_mode */
-
 		pi->read_tier = ceph_decode_64(p);
 		pi->write_tier = ceph_decode_64(p);
 	} else {
@@ -858,86 +856,76 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
 		pi->write_tier = -1;
 	}

-	if (ev >= 10) {
-		/* skip properties */
-		num = ceph_decode_32(p);
-		while (num--) {
-			len = ceph_decode_32(p);
-			*p += len; /* key */
-			len = ceph_decode_32(p);
-			*p += len; /* val */
-		}
-	}
+	if (ev >= 10)
+		/* properties */
+		ceph_decode_skip_map(p, end, string, string, bad);

 	if (ev >= 11) {
-		/* skip hit_set_params */
-		*p += 1 + 1; /* versions */
-		len = ceph_decode_32(p);
-		*p += len;
+		/* hit_set_params (with versions) */
+		ceph_decode_skip_n(p, end, 2, bad);
+		ceph_decode_skip_string(p, end, bad);

-		*p += 4; /* skip hit_set_period */
-		*p += 4; /* skip hit_set_count */
+		/* hit_set_period, hit_set_count */
+		ceph_decode_skip_n(p, end, 4 + 4, bad);
 	}

 	if (ev >= 12)
-		*p += 4; /* skip stripe_width */
+		/* stripe_width */
+		ceph_decode_skip_32(p, end, bad);

-	if (ev >= 13) {
-		*p += 8; /* skip target_max_bytes */
-		*p += 8; /* skip target_max_objects */
-		*p += 4; /* skip cache_target_dirty_ratio_micro */
-		*p += 4; /* skip cache_target_full_ratio_micro */
-		*p += 4; /* skip cache_min_flush_age */
-		*p += 4; /* skip cache_min_evict_age */
-	}
+	if (ev >= 13)
+		/* target_max_*, cache_target_*, cache_min_* */
+		ceph_decode_skip_n(p, end, 16 + 8 + 8, bad);

-	if (ev >=  14) {
-		/* skip erasure_code_profile */
-		len = ceph_decode_32(p);
-		*p += len;
-	}
+	if (ev >= 14)
+		/* erasure_code_profile */
+		ceph_decode_skip_string(p, end, bad);

 	/*
 	 * last_force_op_resend_preluminous, will be overridden if the
 	 * map was encoded with RESEND_ON_SPLIT
 	 */
 	if (ev >= 15)
-		pi->last_force_request_resend = ceph_decode_32(p);
+		ceph_decode_32_safe(p, end, pi->last_force_request_resend, bad);
 	else
 		pi->last_force_request_resend = 0;

 	if (ev >= 16)
-		*p += 4; /* skip min_read_recency_for_promote */
+		/* min_read_recency_for_promote */
+		ceph_decode_skip_32(p, end, bad);

 	if (ev >= 17)
-		*p += 8; /* skip expected_num_objects */
+		/* expected_num_objects */
+		ceph_decode_skip_64(p, end, bad);

 	if (ev >= 19)
-		*p += 4; /* skip cache_target_dirty_high_ratio_micro */
+		/* cache_target_dirty_high_ratio_micro */
+		ceph_decode_skip_32(p, end, bad);

 	if (ev >= 20)
-		*p += 4; /* skip min_write_recency_for_promote */
+		/* min_write_recency_for_promote */
+		ceph_decode_skip_32(p, end, bad);

 	if (ev >= 21)
-		*p += 1; /* skip use_gmt_hitset */
+		/* use_gmt_hitset */
+		ceph_decode_skip_8(p, end, bad);

 	if (ev >= 22)
-		*p += 1; /* skip fast_read */
+		/* fast_read */
+		ceph_decode_skip_8(p, end, bad);

-	if (ev >= 23) {
-		*p += 4; /* skip hit_set_grade_decay_rate */
-		*p += 4; /* skip hit_set_search_last_n */
-	}
+	if (ev >= 23)
+		/* hit_set_grade_decay_rate, hit_set_search_last_n */
+		ceph_decode_skip_n(p, end, 4 + 4, bad);

 	if (ev >= 24) {
-		/* skip opts */
-		*p += 1 + 1; /* versions */
-		len = ceph_decode_32(p);
-		*p += len;
+		/* opts (with versions) */
+		ceph_decode_skip_n(p, end, 2, bad);
+		ceph_decode_skip_string(p, end, bad);
 	}

 	if (ev >= 25)
-		pi->last_force_request_resend = ceph_decode_32(p);
+		ceph_decode_32_safe(p, end, pi->last_force_request_resend, bad);

 	/* ignore the rest */

@@ -1438,7 +1426,7 @@ 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 (len > (SIZE_MAX - sizeof(*pg)) / sizeof(u32))
+	if ((size_t)len > (SIZE_MAX - sizeof(*pg)) / sizeof(u32))
 		return ERR_PTR(-EINVAL);

 	ceph_decode_need(p, end, len * sizeof(u32), e_inval);
@@ -1619,7 +1607,7 @@ 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 (len > (SIZE_MAX - sizeof(*pg)) / (2 * sizeof(u32)))
+	if ((size_t)len > (SIZE_MAX - sizeof(*pg)) / (2 * sizeof(u32)))
 		return ERR_PTR(-EINVAL);

 	ceph_decode_need(p, end, 2 * len * sizeof(u32), e_inval);