Merge tag 'rxrpc-fixes-20230107' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs

David Howells says:

====================
rxrpc: Fix race between call connection, data transmit and call disconnect

Here are patches to fix an oops[1] caused by a race between call
connection, initial packet transmission and call disconnection which
results in something like:

        kernel BUG at net/rxrpc/peer_object.c:413!

when the syzbot test is run.  The problem is that the connection procedure
is effectively split across two threads and can get expanded by taking an
interrupt, thereby adding the call to the peer error distribution list
*after* it has been disconnected (say by the rxrpc socket shutting down).

The easiest solution is to look at the fourth set of I/O thread
conversion/SACK table expansion patches that didn't get applied[2] and take
from it those patches that move call connection and disconnection into the
I/O thread.  Moving these things into the I/O thread means that the
sequencing is managed by all being done in the same thread - and the race
can no longer happen.

This is preferable to introducing an extra lock as adding an extra lock
would make the I/O thread have to wait for the app thread in yet another
place.

The changes can be considered as a number of logical parts:

 (1) Move all of the call state changes into the I/O thread.

 (2) Make client connection ID space per-local endpoint so that the I/O
     thread doesn't need locks to access it.

 (3) Move actual abort generation into the I/O thread and clean it up.  If
     sendmsg or recvmsg want to cause an abort, they have to delegate it.

 (4) Offload the setting up of the security context on a connection to the
     thread of one of the apps that's starting a call.  We don't want to be
     doing any sort of crypto in the I/O thread.

 (5) Connect calls (ie. assign them to channel slots on connections) in the
     I/O thread.  Calls are set up by sendmsg/kafs and passed to the I/O
     thread to connect.  Connections are allocated in the I/O thread after
     this.

 (6) Disconnect calls in the I/O thread.

I've also added a patch for an unrelated bug that cropped up during
testing, whereby a race can occur between an incoming call and socket
shutdown.

Note that whilst this fixes the original syzbot bug, another bug may get
triggered if this one is fixed:

        INFO: rcu detected stall in corrupted
        rcu: INFO: rcu_preempt detected expedited stalls on CPUs/tasks: { P5792 } 2657 jiffies s: 2825 root: 0x0/T
        rcu: blocking rcu_node structures (internal RCU debug):

It doesn't look this should be anything to do with rxrpc, though, as I've
tested an additional patch[3] that removes practically all the RCU usage
from rxrpc and it still occurs.  It seems likely that it is being caused by
something in the tunnelling setup that the syzbot test does, but there's
not enough info to go on.  It also seems unlikely to be anything to do with
the afs driver as the test doesn't use that.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 126 insertions, 37 deletions

diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index d5a5ae926380..ba717eac0229 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -15,6 +15,7 @@ struct key;
 struct sock;
 struct socket;
 struct rxrpc_call;
+enum rxrpc_abort_reason;
 
 enum rxrpc_interruptibility {
 	RXRPC_INTERRUPTIBLE,	/* Call is interruptible */
@@ -55,7 +56,7 @@ int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *,
 int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *,
 			   struct iov_iter *, size_t *, bool, u32 *, u16 *);
 bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
-			     u32, int, const char *);
+			     u32, int, enum rxrpc_abort_reason);
 void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
 void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
 			   struct sockaddr_rxrpc *);
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 5f9dd7389536..283db0ea3db4 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -16,7 +16,107 @@
 /*
  * Declare tracing information enums and their string mappings for display.
  */
+#define rxrpc_abort_reasons \
+	/* AFS errors */						\
+	EM(afs_abort_general_error,		"afs-error")		\
+	EM(afs_abort_interrupted,		"afs-intr")		\
+	EM(afs_abort_oom,			"afs-oom")		\
+	EM(afs_abort_op_not_supported,		"afs-op-notsupp")	\
+	EM(afs_abort_probeuuid_negative,	"afs-probeuuid-neg")	\
+	EM(afs_abort_send_data_error,		"afs-send-data")	\
+	EM(afs_abort_unmarshal_error,		"afs-unmarshal")	\
+	/* rxperf errors */						\
+	EM(rxperf_abort_general_error,		"rxperf-error")		\
+	EM(rxperf_abort_oom,			"rxperf-oom")		\
+	EM(rxperf_abort_op_not_supported,	"rxperf-op-notsupp")	\
+	EM(rxperf_abort_unmarshal_error,	"rxperf-unmarshal")	\
+	/* RxKAD security errors */					\
+	EM(rxkad_abort_1_short_check,		"rxkad1-short-check")	\
+	EM(rxkad_abort_1_short_data,		"rxkad1-short-data")	\
+	EM(rxkad_abort_1_short_encdata,		"rxkad1-short-encdata")	\
+	EM(rxkad_abort_1_short_header,		"rxkad1-short-hdr")	\
+	EM(rxkad_abort_2_short_check,		"rxkad2-short-check")	\
+	EM(rxkad_abort_2_short_data,		"rxkad2-short-data")	\
+	EM(rxkad_abort_2_short_header,		"rxkad2-short-hdr")	\
+	EM(rxkad_abort_2_short_len,		"rxkad2-short-len")	\
+	EM(rxkad_abort_bad_checksum,		"rxkad2-bad-cksum")	\
+	EM(rxkad_abort_chall_key_expired,	"rxkad-chall-key-exp")	\
+	EM(rxkad_abort_chall_level,		"rxkad-chall-level")	\
+	EM(rxkad_abort_chall_no_key,		"rxkad-chall-nokey")	\
+	EM(rxkad_abort_chall_short,		"rxkad-chall-short")	\
+	EM(rxkad_abort_chall_version,		"rxkad-chall-version")	\
+	EM(rxkad_abort_resp_bad_callid,		"rxkad-resp-bad-callid") \
+	EM(rxkad_abort_resp_bad_checksum,	"rxkad-resp-bad-cksum")	\
+	EM(rxkad_abort_resp_bad_param,		"rxkad-resp-bad-param")	\
+	EM(rxkad_abort_resp_call_ctr,		"rxkad-resp-call-ctr") \
+	EM(rxkad_abort_resp_call_state,		"rxkad-resp-call-state") \
+	EM(rxkad_abort_resp_key_expired,	"rxkad-resp-key-exp")	\
+	EM(rxkad_abort_resp_key_rejected,	"rxkad-resp-key-rej")	\
+	EM(rxkad_abort_resp_level,		"rxkad-resp-level")	\
+	EM(rxkad_abort_resp_nokey,		"rxkad-resp-nokey")	\
+	EM(rxkad_abort_resp_ooseq,		"rxkad-resp-ooseq")	\
+	EM(rxkad_abort_resp_short,		"rxkad-resp-short")	\
+	EM(rxkad_abort_resp_short_tkt,		"rxkad-resp-short-tkt")	\
+	EM(rxkad_abort_resp_tkt_aname,		"rxkad-resp-tk-aname")	\
+	EM(rxkad_abort_resp_tkt_expired,	"rxkad-resp-tk-exp")	\
+	EM(rxkad_abort_resp_tkt_future,		"rxkad-resp-tk-future")	\
+	EM(rxkad_abort_resp_tkt_inst,		"rxkad-resp-tk-inst")	\
+	EM(rxkad_abort_resp_tkt_len,		"rxkad-resp-tk-len")	\
+	EM(rxkad_abort_resp_tkt_realm,		"rxkad-resp-tk-realm")	\
+	EM(rxkad_abort_resp_tkt_short,		"rxkad-resp-tk-short")	\
+	EM(rxkad_abort_resp_tkt_sinst,		"rxkad-resp-tk-sinst")	\
+	EM(rxkad_abort_resp_tkt_sname,		"rxkad-resp-tk-sname")	\
+	EM(rxkad_abort_resp_unknown_tkt,	"rxkad-resp-unknown-tkt") \
+	EM(rxkad_abort_resp_version,		"rxkad-resp-version")	\
+	/* rxrpc errors */						\
+	EM(rxrpc_abort_call_improper_term,	"call-improper-term")	\
+	EM(rxrpc_abort_call_reset,		"call-reset")		\
+	EM(rxrpc_abort_call_sendmsg,		"call-sendmsg")		\
+	EM(rxrpc_abort_call_sock_release,	"call-sock-rel")	\
+	EM(rxrpc_abort_call_sock_release_tba,	"call-sock-rel-tba")	\
+	EM(rxrpc_abort_call_timeout,		"call-timeout")		\
+	EM(rxrpc_abort_no_service_key,		"no-serv-key")		\
+	EM(rxrpc_abort_nomem,			"nomem")		\
+	EM(rxrpc_abort_service_not_offered,	"serv-not-offered")	\
+	EM(rxrpc_abort_shut_down,		"shut-down")		\
+	EM(rxrpc_abort_unsupported_security,	"unsup-sec")		\
+	EM(rxrpc_badmsg_bad_abort,		"bad-abort")		\
+	EM(rxrpc_badmsg_bad_jumbo,		"bad-jumbo")		\
+	EM(rxrpc_badmsg_short_ack,		"short-ack")		\
+	EM(rxrpc_badmsg_short_ack_info,		"short-ack-info")	\
+	EM(rxrpc_badmsg_short_hdr,		"short-hdr")		\
+	EM(rxrpc_badmsg_unsupported_packet,	"unsup-pkt")		\
+	EM(rxrpc_badmsg_zero_call,		"zero-call")		\
+	EM(rxrpc_badmsg_zero_seq,		"zero-seq")		\
+	EM(rxrpc_badmsg_zero_service,		"zero-service")		\
+	EM(rxrpc_eproto_ackr_outside_window,	"ackr-out-win")		\
+	EM(rxrpc_eproto_ackr_sack_overflow,	"ackr-sack-over")	\
+	EM(rxrpc_eproto_ackr_short_sack,	"ackr-short-sack")	\
+	EM(rxrpc_eproto_ackr_zero,		"ackr-zero")		\
+	EM(rxrpc_eproto_bad_upgrade,		"bad-upgrade")		\
+	EM(rxrpc_eproto_data_after_last,	"data-after-last")	\
+	EM(rxrpc_eproto_different_last,		"diff-last")		\
+	EM(rxrpc_eproto_early_reply,		"early-reply")		\
+	EM(rxrpc_eproto_improper_term,		"improper-term")	\
+	EM(rxrpc_eproto_no_client_call,		"no-cl-call")		\
+	EM(rxrpc_eproto_no_client_conn,		"no-cl-conn")		\
+	EM(rxrpc_eproto_no_service_call,	"no-sv-call")		\
+	EM(rxrpc_eproto_reupgrade,		"re-upgrade")		\
+	EM(rxrpc_eproto_rxnull_challenge,	"rxnull-chall")		\
+	EM(rxrpc_eproto_rxnull_response,	"rxnull-resp")		\
+	EM(rxrpc_eproto_tx_rot_last,		"tx-rot-last")		\
+	EM(rxrpc_eproto_unexpected_ack,		"unex-ack")		\
+	EM(rxrpc_eproto_unexpected_ackall,	"unex-ackall")		\
+	EM(rxrpc_eproto_unexpected_implicit_end, "unex-impl-end")	\
+	EM(rxrpc_eproto_unexpected_reply,	"unex-reply")		\
+	EM(rxrpc_eproto_wrong_security,		"wrong-sec")		\
+	EM(rxrpc_recvmsg_excess_data,		"recvmsg-excess")	\
+	EM(rxrpc_recvmsg_short_data,		"recvmsg-short")	\
+	E_(rxrpc_sendmsg_late_send,		"sendmsg-late")
+
 #define rxrpc_call_poke_traces \
+	EM(rxrpc_call_poke_abort,		"Abort")	\
+	EM(rxrpc_call_poke_complete,		"Compl")	\
 	EM(rxrpc_call_poke_error,		"Error")	\
 	EM(rxrpc_call_poke_idle,		"Idle")		\
 	EM(rxrpc_call_poke_start,		"Start")	\
@@ -26,6 +126,7 @@
 #define rxrpc_skb_traces \
 	EM(rxrpc_skb_eaten_by_unshare,		"ETN unshare  ") \
 	EM(rxrpc_skb_eaten_by_unshare_nomem,	"ETN unshar-nm") \
+	EM(rxrpc_skb_get_conn_secured,		"GET conn-secd") \
 	EM(rxrpc_skb_get_conn_work,		"GET conn-work") \
 	EM(rxrpc_skb_get_local_work,		"GET locl-work") \
 	EM(rxrpc_skb_get_reject_work,		"GET rej-work ") \
@@ -35,6 +136,7 @@
 	EM(rxrpc_skb_new_error_report,		"NEW error-rpt") \
 	EM(rxrpc_skb_new_jumbo_subpacket,	"NEW jumbo-sub") \
 	EM(rxrpc_skb_new_unshared,		"NEW unshared ") \
+	EM(rxrpc_skb_put_conn_secured,		"PUT conn-secd") \
 	EM(rxrpc_skb_put_conn_work,		"PUT conn-work") \
 	EM(rxrpc_skb_put_error_report,		"PUT error-rep") \
 	EM(rxrpc_skb_put_input,			"PUT input    ") \
@@ -76,7 +178,6 @@
 #define rxrpc_peer_traces \
 	EM(rxrpc_peer_free,			"FREE        ") \
 	EM(rxrpc_peer_get_accept,		"GET accept  ") \
-	EM(rxrpc_peer_get_activate_call,	"GET act-call") \
 	EM(rxrpc_peer_get_bundle,		"GET bundle  ") \
 	EM(rxrpc_peer_get_client_conn,		"GET cln-conn") \
 	EM(rxrpc_peer_get_input,		"GET input   ") \
@@ -89,7 +190,6 @@
 	EM(rxrpc_peer_put_bundle,		"PUT bundle  ") \
 	EM(rxrpc_peer_put_call,			"PUT call    ") \
 	EM(rxrpc_peer_put_conn,			"PUT conn    ") \
-	EM(rxrpc_peer_put_discard_tmp,		"PUT disc-tmp") \
 	EM(rxrpc_peer_put_input,		"PUT input   ") \
 	EM(rxrpc_peer_put_input_error,		"PUT inpt-err") \
 	E_(rxrpc_peer_put_keepalive,		"PUT keepaliv")
@@ -99,6 +199,7 @@
 	EM(rxrpc_bundle_get_client_call,	"GET clt-call") \
 	EM(rxrpc_bundle_get_client_conn,	"GET clt-conn") \
 	EM(rxrpc_bundle_get_service_conn,	"GET svc-conn") \
+	EM(rxrpc_bundle_put_call,		"PUT call    ") \
 	EM(rxrpc_bundle_put_conn,		"PUT conn    ") \
 	EM(rxrpc_bundle_put_discard,		"PUT discard ") \
 	E_(rxrpc_bundle_new,			"NEW         ")
@@ -109,14 +210,14 @@
 	EM(rxrpc_conn_get_call_input,		"GET inp-call") \
 	EM(rxrpc_conn_get_conn_input,		"GET inp-conn") \
 	EM(rxrpc_conn_get_idle,			"GET idle    ") \
-	EM(rxrpc_conn_get_poke,			"GET poke    ") \
+	EM(rxrpc_conn_get_poke_abort,		"GET pk-abort") \
+	EM(rxrpc_conn_get_poke_timer,		"GET poke    ") \
 	EM(rxrpc_conn_get_service_conn,		"GET svc-conn") \
 	EM(rxrpc_conn_new_client,		"NEW client  ") \
 	EM(rxrpc_conn_new_service,		"NEW service ") \
 	EM(rxrpc_conn_put_call,			"PUT call    ") \
 	EM(rxrpc_conn_put_call_input,		"PUT inp-call") \
 	EM(rxrpc_conn_put_conn_input,		"PUT inp-conn") \
-	EM(rxrpc_conn_put_discard,		"PUT discard ") \
 	EM(rxrpc_conn_put_discard_idle,		"PUT disc-idl") \
 	EM(rxrpc_conn_put_local_dead,		"PUT loc-dead") \
 	EM(rxrpc_conn_put_noreuse,		"PUT noreuse ") \
@@ -124,10 +225,10 @@
 	EM(rxrpc_conn_put_service_reaped,	"PUT svc-reap") \
 	EM(rxrpc_conn_put_unbundle,		"PUT unbundle") \
 	EM(rxrpc_conn_put_unidle,		"PUT unidle  ") \
+	EM(rxrpc_conn_put_work,			"PUT work    ") \
 	EM(rxrpc_conn_queue_challenge,		"QUE chall   ") \
 	EM(rxrpc_conn_queue_retry_work,		"QUE retry-wk") \
 	EM(rxrpc_conn_queue_rx_work,		"QUE rx-work ") \
-	EM(rxrpc_conn_queue_timer,		"QUE timer   ") \
 	EM(rxrpc_conn_see_new_service_conn,	"SEE new-svc ") \
 	EM(rxrpc_conn_see_reap_service,		"SEE reap-svc") \
 	E_(rxrpc_conn_see_work,			"SEE work    ")
@@ -138,16 +239,16 @@
 	EM(rxrpc_client_chan_activate,		"ChActv") \
 	EM(rxrpc_client_chan_disconnect,	"ChDisc") \
 	EM(rxrpc_client_chan_pass,		"ChPass") \
-	EM(rxrpc_client_chan_wait_failed,	"ChWtFl") \
 	EM(rxrpc_client_cleanup,		"Clean ") \
 	EM(rxrpc_client_discard,		"Discar") \
-	EM(rxrpc_client_duplicate,		"Duplic") \
 	EM(rxrpc_client_exposed,		"Expose") \
 	EM(rxrpc_client_replace,		"Replac") \
+	EM(rxrpc_client_queue_new_call,		"Q-Call") \
 	EM(rxrpc_client_to_active,		"->Actv") \
 	E_(rxrpc_client_to_idle,		"->Idle")
 
 #define rxrpc_call_traces \
+	EM(rxrpc_call_get_io_thread,		"GET iothread") \
 	EM(rxrpc_call_get_input,		"GET input   ") \
 	EM(rxrpc_call_get_kernel_service,	"GET krnl-srv") \
 	EM(rxrpc_call_get_notify_socket,	"GET notify  ") \
@@ -160,6 +261,7 @@
 	EM(rxrpc_call_new_prealloc_service,	"NEW prealloc") \
 	EM(rxrpc_call_put_discard_prealloc,	"PUT disc-pre") \
 	EM(rxrpc_call_put_discard_error,	"PUT disc-err") \
+	EM(rxrpc_call_put_io_thread,		"PUT iothread") \
 	EM(rxrpc_call_put_input,		"PUT input   ") \
 	EM(rxrpc_call_put_kernel,		"PUT kernel  ") \
 	EM(rxrpc_call_put_poke,			"PUT poke    ") \
@@ -169,10 +271,12 @@
 	EM(rxrpc_call_put_sendmsg,		"PUT sendmsg ") \
 	EM(rxrpc_call_put_unnotify,		"PUT unnotify") \
 	EM(rxrpc_call_put_userid_exists,	"PUT u-exists") \
+	EM(rxrpc_call_put_userid,		"PUT user-id ") \
 	EM(rxrpc_call_see_accept,		"SEE accept  ") \
 	EM(rxrpc_call_see_activate_client,	"SEE act-clnt") \
 	EM(rxrpc_call_see_connect_failed,	"SEE con-fail") \
 	EM(rxrpc_call_see_connected,		"SEE connect ") \
+	EM(rxrpc_call_see_disconnected,		"SEE disconn ") \
 	EM(rxrpc_call_see_distribute_error,	"SEE dist-err") \
 	EM(rxrpc_call_see_input,		"SEE input   ") \
 	EM(rxrpc_call_see_release,		"SEE release ") \
@@ -376,6 +480,7 @@
 #define EM(a, b) a,
 #define E_(a, b) a
 
+enum rxrpc_abort_reason		{ rxrpc_abort_reasons } __mode(byte);
 enum rxrpc_bundle_trace		{ rxrpc_bundle_traces } __mode(byte);
 enum rxrpc_call_poke_trace	{ rxrpc_call_poke_traces } __mode(byte);
 enum rxrpc_call_trace		{ rxrpc_call_traces } __mode(byte);
@@ -404,9 +509,13 @@ enum rxrpc_txqueue_trace	{ rxrpc_txqueue_traces } __mode(byte);
  */
 #undef EM
 #undef E_
+
+#ifndef RXRPC_TRACE_ONLY_DEFINE_ENUMS
+
 #define EM(a, b) TRACE_DEFINE_ENUM(a);
 #define E_(a, b) TRACE_DEFINE_ENUM(a);
 
+rxrpc_abort_reasons;
 rxrpc_bundle_traces;
 rxrpc_call_poke_traces;
 rxrpc_call_traces;
@@ -657,14 +766,14 @@ TRACE_EVENT(rxrpc_rx_done,
 	    );
 
 TRACE_EVENT(rxrpc_abort,
-	    TP_PROTO(unsigned int call_nr, const char *why, u32 cid, u32 call_id,
-		     rxrpc_seq_t seq, int abort_code, int error),
+	    TP_PROTO(unsigned int call_nr, enum rxrpc_abort_reason why,
+		     u32 cid, u32 call_id, rxrpc_seq_t seq, int abort_code, int error),
 
 	    TP_ARGS(call_nr, why, cid, call_id, seq, abort_code, error),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,		call_nr		)
-		    __array(char,			why, 4		)
+		    __field(enum rxrpc_abort_reason,	why		)
 		    __field(u32,			cid		)
 		    __field(u32,			call_id		)
 		    __field(rxrpc_seq_t,		seq		)
@@ -673,8 +782,8 @@ TRACE_EVENT(rxrpc_abort,
 			     ),
 
 	    TP_fast_assign(
-		    memcpy(__entry->why, why, 4);
 		    __entry->call_nr = call_nr;
+		    __entry->why = why;
 		    __entry->cid = cid;
 		    __entry->call_id = call_id;
 		    __entry->abort_code = abort_code;
@@ -685,7 +794,8 @@ TRACE_EVENT(rxrpc_abort,
 	    TP_printk("c=%08x %08x:%08x s=%u a=%d e=%d %s",
 		      __entry->call_nr,
 		      __entry->cid, __entry->call_id, __entry->seq,
-		      __entry->abort_code, __entry->error, __entry->why)
+		      __entry->abort_code, __entry->error,
+		      __print_symbolic(__entry->why, rxrpc_abort_reasons))
 	    );
 
 TRACE_EVENT(rxrpc_call_complete,
@@ -1521,30 +1631,6 @@ TRACE_EVENT(rxrpc_improper_term,
 		      __entry->abort_code)
 	    );
 
-TRACE_EVENT(rxrpc_rx_eproto,
-	    TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial,
-		     const char *why),
-
-	    TP_ARGS(call, serial, why),
-
-	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(rxrpc_serial_t,		serial		)
-		    __field(const char *,		why		)
-			     ),
-
-	    TP_fast_assign(
-		    __entry->call = call ? call->debug_id : 0;
-		    __entry->serial = serial;
-		    __entry->why = why;
-			   ),
-
-	    TP_printk("c=%08x EPROTO %08x %s",
-		      __entry->call,
-		      __entry->serial,
-		      __entry->why)
-	    );
-
 TRACE_EVENT(rxrpc_connect_call,
 	    TP_PROTO(struct rxrpc_call *call),
 
@@ -1842,6 +1928,8 @@ TRACE_EVENT(rxrpc_call_poked,
 
 #undef EM
 #undef E_
+
+#endif /* RXRPC_TRACE_ONLY_DEFINE_ENUMS */
 #endif /* _TRACE_RXRPC_H */
 
 /* This part must be outside protection */