6.18.40-rc1 review
Subsystems (13)
Greg Kroah-Hartman
maintainerPATCH 542/1611 net: remove addr_len argument of recvmsg() handlers
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <[email protected]>
[ Upstream commit 8341c989ac77d712c7d6e2bce29e8a4bcb2eeae4 ]
Use msg->msg_namelen as a place holder instead of a temporary variable, notably in inet[6]_recvmsg().
This removes stack canaries and allows tail-calls.
$ scripts/bloat-o-meter -t vmlinux.old vmlinux add/remove: 0/0 grow/shrink: 2/19 up/down: 26/-532 (-506) Function old new delta rawv6_recvmsg 744 767 +23 vsock_dgram_recvmsg 55 58 +3 vsock_connectible_recvmsg 50 47 -3 unix_stream_recvmsg 161 158 -3 unix_seqpacket_recvmsg 62 59 -3 unix_dgram_recvmsg 42 39 -3 tcp_recvmsg 546 543 -3 mptcp_recvmsg 1568 1565 -3 ping_recvmsg 806 800 -6 tcp_bpf_recvmsg_parser 983 974 -9 ip_recv_error 588 576 -12 ipv6_recv_rxpmtu 442 428 -14 udp_recvmsg 1243 1224 -19 ipv6_recv_error 1046 1024 -22 udpv6_recvmsg 1487 1461 -26 raw_recvmsg 465 437 -28 udp_bpf_recvmsg 1027 984 -43 sock_common_recvmsg 103 27 -76 inet_recvmsg 257 175 -82 inet6_recvmsg 257 175 -82 tcp_bpf_recvmsg 663 568 -95 Total: Before=25143834, After=25143328, chg -0.00%
Stable-dep-of: c010995b29c8 ("sockmap: Fix use-after-free in udp_bpf_recvmsg()")
--- .../chelsio/inline_crypto/chtls/chtls.h | 2 +- .../chelsio/inline_crypto/chtls/chtls_io.c | 8 ++++---- drivers/net/ovpn/tcp.c | 2 +- include/net/inet_common.h | 3 +-- include/net/ip.h | 2 +- include/net/ipv6.h | 6 ++---- include/net/ping.h | 5 ++--- include/net/sock.h | 2 +- include/net/tcp.h | 2 +- net/core/sock.c | 7 +------ net/ieee802154/socket.c | 6 +++--- net/ipv4/af_inet.c | 17 ++++++----------- net/ipv4/ip_sockglue.c | 4 ++-- net/ipv4/ping.c | 9 ++++----- net/ipv4/raw.c | 6 +++--- net/ipv4/tcp.c | 5 ++--- net/ipv4/tcp_bpf.c | 17 ++++++++--------- net/ipv4/udp.c | 9 ++++----- net/ipv4/udp_bpf.c | 16 ++++++++-------- net/ipv4/udp_impl.h | 3 +-- net/ipv6/af_inet6.c | 11 +++-------- net/ipv6/datagram.c | 9 ++++----- net/ipv6/ping.c | 3 +-- net/ipv6/raw.c | 8 ++++---- net/ipv6/udp.c | 10 +++++----- net/ipv6/udp_impl.h | 3 +-- net/l2tp/l2tp_ip.c | 4 ++-- net/l2tp/l2tp_ip6.c | 6 +++--- net/mptcp/protocol.c | 4 ++-- net/phonet/datagram.c | 4 ++-- net/phonet/pep.c | 2 +- net/sctp/socket.c | 12 ++++++------ net/tls/tls.h | 2 +- net/tls/tls_sw.c | 3 +-- net/unix/af_unix.c | 4 ++-- net/unix/unix_bpf.c | 2 +- net/vmw_vsock/af_vsock.c | 4 ++-- net/vmw_vsock/vsock_bpf.c | 2 +- net/xfrm/espintcp.c | 2 +- 39 files changed, 99 insertions(+), 127 deletions(-)
drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h +1 -1
@@ -567,7 +567,7 @@ void chtls_shutdown(struct sock *sk, int how);void chtls_destroy_sock (struct sock *sk);int chtls_sendmsg (struct sock *sk,struct msghdr *msg,size_t size);int chtls_recvmsg (struct sock *sk,struct msghdr *msg, -size_t len,int flags,int *addr_len); +size_t len,int flags);void chtls_splice_eof (struct socket *sock);int send_tx_flowc_wr (struct sock *sk,int compl,u32 snd_nxt,u32 rcv_nxt);
drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c +4 -4
@@ -1338,7 +1338,7 @@ static void chtls_cleanup_rbuf(struct sock *sk, int copied) }static int chtls_pt_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {struct chtls_sock *csk =rcu_dereference_sk_user_data (sk);struct chtls_hws *hws = &csk->tlshws;
@@ -1662,7 +1662,7 @@ static int peekmsg(struct sock *sk, struct msghdr *msg, }int chtls_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {struct tcp_sock *tp =tcp_sk (sk);struct chtls_sock *csk;
@@ -1676,7 +1676,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, buffers_freed =0 ;if (unlikely (flags &MSG_OOB )) -return tcp_prot.recvmsg (sk, msg, len, flags, addr_len); +return tcp_prot.recvmsg (sk, msg, len, flags);if (unlikely (flags &MSG_PEEK ))return peekmsg (sk, msg, len, flags);
@@ -1690,7 +1690,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, csk =rcu_dereference_sk_user_data (sk);if (is_tls_rx (csk)) -return chtls_pt_recvmsg (sk, msg, len, flags, addr_len); +return chtls_pt_recvmsg (sk, msg, len, flags); timeo =sock_rcvtimeo (sk, flags &MSG_DONTWAIT ); target =sock_rcvlowat (sk, flags &MSG_WAITALL , len);
drivers/net/ovpn/tcp.c +1 -1
@@ -158,7 +158,7 @@ static void ovpn_tcp_rcv(struct strparser *strp, struct sk_buff *skb) }static int ovpn_tcp_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {int err =0 , off, copied =0 , ret;struct ovpn_socket *sock;
include/net/inet_common.h +1 -2
@@ -60,8 +60,7 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);int inet_ctl_sock_create (struct sock **sk,unsigned short family,unsigned short type,unsigned char protocol,struct net *net); -int inet_recv_error (struct sock *sk,struct msghdr *msg,int len, -int *addr_len); +int inet_recv_error (struct sock *sk,struct msghdr *msg,int len);struct sk_buff *inet_gro_receive (struct list_head *head,struct sk_buff *skb);int inet_gro_complete (struct sk_buff *skb,int nhoff);
include/net/ip.h +1 -1
@@ -812,7 +812,7 @@ int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval,int ip_ra_control (struct sock *sk,unsigned char on,void (*destructor)(struct sock *)); -int ip_recv_error (struct sock *sk,struct msghdr *msg,int len,int *addr_len); +int ip_recv_error (struct sock *sk,struct msghdr *msg,int len);void ip_icmp_error (struct sock *sk,struct sk_buff *skb,int err,__be16 port,u32 info,u8 *payload); void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
include/net/ipv6.h +2 -4
@@ -1196,10 +1196,8 @@ int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr,int ip6_datagram_dst_update (struct sock *sk,bool fix_sk_saddr);void ip6_datagram_release_cb (struct sock *sk); -int ipv6_recv_error (struct sock *sk,struct msghdr *msg,int len, -int *addr_len); -int ipv6_recv_rxpmtu (struct sock *sk,struct msghdr *msg,int len, -int *addr_len); +int ipv6_recv_error (struct sock *sk,struct msghdr *msg,int len); +int ipv6_recv_rxpmtu (struct sock *sk,struct msghdr *msg,int len);void ipv6_icmp_error (struct sock *sk,struct sk_buff *skb,int err,__be16 port,u32 info,u8 *payload);void ipv6_local_error (struct sock *sk,int err,struct flowi6 *fl6,u32 info);
include/net/ping.h +2 -3
@@ -20,8 +20,7 @@/* Compatibility glue so we can support IPv6 when it's compiled as a module */ struct pingv6_ops { -int (*ipv6_recv_error)(struct sock *sk,struct msghdr *msg,int len, -int *addr_len); +int (*ipv6_recv_error)(struct sock *sk,struct msghdr *msg,int len);void (*ip6_datagram_recv_common_ctl)(struct sock *sk,struct msghdr *msg,struct sk_buff *skb);
@@ -64,7 +63,7 @@ int ping_getfrag(void *from, char *to, int offset, int fraglen, int odd, struct sk_buff *);int ping_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len); +int flags);int ping_common_sendmsg (int family,struct msghdr *msg,size_t len,void *user_icmph,size_t icmph_len);int ping_queue_rcv_skb (struct sock *sk,struct sk_buff *skb);
include/net/sock.h +1 -1
@@ -1289,7 +1289,7 @@ struct proto {int (*sendmsg)(struct sock *sk,struct msghdr *msg,size_t len);int (*recvmsg)(struct sock *sk,struct msghdr *msg, -size_t len,int flags,int *addr_len); +size_t len,int flags);void (*splice_eof)(struct socket *sock);int (*bind)(struct sock *sk,struct sockaddr *addr,int addr_len);
include/net/tcp.h +1 -1
@@ -485,7 +485,7 @@ void tcp_reset_keepalive_timer(struct sock *sk, unsigned long timeout);void tcp_set_keepalive (struct sock *sk,int val);void tcp_syn_ack_timeout (const struct request_sock *req);int tcp_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len); +int flags);int tcp_set_rcvlowat (struct sock *sk,int val);int tcp_set_window_clamp (struct sock *sk,int val); void tcp_update_recv_tstamps(struct sk_buff *skb,
net/core/sock.c +1 -6
@@ -3900,13 +3900,8 @@ int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) {struct sock *sk = sock->sk; -int addr_len =0 ; -int err; - err = sk->sk_prot->recvmsg (sk, msg, size, flags, &addr_len); -if (err >=0 ) - msg->msg_namelen = addr_len; -return err; +return sk->sk_prot->recvmsg (sk, msg, size, flags); }EXPORT_SYMBOL (sock_common_recvmsg);
net/ieee802154/socket.c +3 -3
@@ -313,7 +313,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) }static int raw_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {size_t copied =0 ;int err = -EOPNOTSUPP ;
@@ -703,7 +703,7 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) }static int dgram_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {size_t copied =0 ;int err = -EOPNOTSUPP ;
@@ -737,7 +737,7 @@ static int dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, saddr->family =AF_IEEE802154 ;ieee802154_addr_to_sa (&saddr->addr, &mac_cb (skb)->source); - *addr_len =sizeof (*saddr); + msg->msg_namelen =sizeof (*saddr); }if (ro->want_lqi) {
net/ipv4/af_inet.c +6 -11
@@ -871,22 +871,17 @@ void inet_splice_eof(struct socket *sock)EXPORT_SYMBOL_GPL (inet_splice_eof); INDIRECT_CALLABLE_DECLARE(int udp_recvmsg(struct sock *, struct msghdr *, -size_t ,int ,int *)); +size_t ,int ));int inet_recvmsg (struct socket *sock,struct msghdr *msg,size_t size,int flags) {struct sock *sk = sock->sk; -int addr_len =0 ; -int err;if (likely (!(flags &MSG_ERRQUEUE )))sock_rps_record_flow (sk); - err =INDIRECT_CALL_2 (sk->sk_prot->recvmsg, tcp_recvmsg, udp_recvmsg, - sk, msg, size, flags, &addr_len); -if (err >=0 ) - msg->msg_namelen = addr_len; -return err; +return INDIRECT_CALL_2 (sk->sk_prot->recvmsg, tcp_recvmsg, udp_recvmsg, + sk, msg, size, flags); }EXPORT_SYMBOL (inet_recvmsg);
@@ -1571,15 +1566,15 @@ __be32 inet_current_timestamp(void) }EXPORT_SYMBOL (inet_current_timestamp); -int inet_recv_error (struct sock *sk,struct msghdr *msg,int len,int *addr_len) +int inet_recv_error (struct sock *sk,struct msghdr *msg,int len) {unsigned int family =READ_ONCE (sk->sk_family);if (family ==AF_INET ) -return ip_recv_error (sk, msg, len, addr_len); +return ip_recv_error (sk, msg, len);#if IS_ENABLED (CONFIG_IPV6 )if (family ==AF_INET6 ) -return pingv6_ops.ipv6_recv_error (sk, msg, len, addr_len); +return pingv6_ops.ipv6_recv_error (sk, msg, len);#endif return -EINVAL ; }
net/ipv4/ip_sockglue.c +2 -2
@@ -520,7 +520,7 @@ static bool ipv4_datagram_support_cmsg(const struct sock *sk,/* * Handle MSG_ERRQUEUE */ -int ip_recv_error (struct sock *sk,struct msghdr *msg,int len,int *addr_len) +int ip_recv_error (struct sock *sk,struct msghdr *msg,int len) {struct sock_exterr_skb *serr;struct sk_buff *skb;
@@ -557,7 +557,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) serr->addr_offset); sin->sin_port = serr->port;memset (&sin->sin_zero,0 ,sizeof (sin->sin_zero)); - *addr_len =sizeof (*sin); + msg->msg_namelen =sizeof (*sin); }memcpy (&errhdr.ee, &serr->ee,sizeof (struct sock_extended_err ));
net/ipv4/ping.c +4 -5
@@ -847,8 +847,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto out; } -int ping_recvmsg (struct sock *sk,struct msghdr *msg,size_t len,int flags, -int *addr_len) +int ping_recvmsg (struct sock *sk,struct msghdr *msg,size_t len,int flags) {struct inet_sock *isk =inet_sk (sk);int family = sk->sk_family;
@@ -863,7 +862,7 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, goto out;if (flags &MSG_ERRQUEUE ) -return inet_recv_error (sk, msg, len, addr_len); +return inet_recv_error (sk, msg, len); skb =skb_recv_datagram (sk, flags, &err);if (!skb)
@@ -891,7 +890,7 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, sin->sin_port =0 /* skb->h.uh->source */ ; sin->sin_addr.s_addr =ip_hdr (skb)->saddr;memset (sin->sin_zero,0 ,sizeof (sin->sin_zero)); - *addr_len =sizeof (*sin); + msg->msg_namelen =sizeof (*sin); }if (inet_cmsg_flags (isk))
@@ -912,7 +911,7 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, sin6->sin6_scope_id =ipv6_iface_scope_id (&sin6->sin6_addr,inet6_iif (skb)); - *addr_len =sizeof (*sin6); + msg->msg_namelen =sizeof (*sin6); }if (inet6_sk (sk)->rxopt.all)
net/ipv4/raw.c +3 -3
@@ -737,7 +737,7 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)*/ static int raw_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {struct inet_sock *inet =inet_sk (sk);size_t copied =0 ;
@@ -749,7 +749,7 @@ static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, goto out;if (flags &MSG_ERRQUEUE ) { - err =ip_recv_error (sk, msg, len, addr_len); + err =ip_recv_error (sk, msg, len); goto out; }
@@ -775,7 +775,7 @@ static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, sin->sin_addr.s_addr =ip_hdr (skb)->saddr; sin->sin_port =0 ;memset (&sin->sin_zero,0 ,sizeof (sin->sin_zero)); - *addr_len =sizeof (*sin); + msg->msg_namelen =sizeof (*sin); }if (inet_cmsg_flags (inet))ip_cmsg_recv (msg, skb);
net/ipv4/tcp.c +2 -3
@@ -2909,14 +2909,13 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, goto out; } -int tcp_recvmsg (struct sock *sk,struct msghdr *msg,size_t len,int flags, -int *addr_len) +int tcp_recvmsg (struct sock *sk,struct msghdr *msg,size_t len,int flags) {int cmsg_flags =0 , ret;struct scm_timestamping_internal tss;if (unlikely (flags &MSG_ERRQUEUE )) -return inet_recv_error (sk, msg, len, addr_len); +return inet_recv_error (sk, msg, len); if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) &&
net/ipv4/tcp_bpf.c +8 -9
@@ -221,8 +221,7 @@ static bool is_next_msg_fin(struct sk_psock *psock)static int tcp_bpf_recvmsg_parser (struct sock *sk,struct msghdr *msg,size_t len, -int flags, -int *addr_len) +int flags) {int peek = flags &MSG_PEEK ;struct sk_psock *psock;
@@ -232,14 +231,14 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,u32 seq;if (unlikely (flags &MSG_ERRQUEUE )) -return inet_recv_error (sk, msg, len, addr_len); +return inet_recv_error (sk, msg, len);if (!len)return 0 ; psock =sk_psock_get (sk);if (unlikely (!psock)) -return tcp_recvmsg (sk, msg, len, flags, addr_len); +return tcp_recvmsg (sk, msg, len, flags);lock_sock (sk); tcp =tcp_sk (sk);
@@ -352,24 +351,24 @@ static int tcp_bpf_ioctl(struct sock *sk, int cmd, int *karg) }static int tcp_bpf_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {struct sk_psock *psock;int copied, ret;if (unlikely (flags &MSG_ERRQUEUE )) -return inet_recv_error (sk, msg, len, addr_len); +return inet_recv_error (sk, msg, len);if (!len)return 0 ; psock =sk_psock_get (sk);if (unlikely (!psock)) -return tcp_recvmsg (sk, msg, len, flags, addr_len); +return tcp_recvmsg (sk, msg, len, flags);if (!skb_queue_empty (&sk->sk_receive_queue) &&sk_psock_queue_empty (psock)) {sk_psock_put (sk, psock); -return tcp_recvmsg (sk, msg, len, flags, addr_len); +return tcp_recvmsg (sk, msg, len, flags); }lock_sock (sk); msg_bytes_ready:
@@ -389,7 +388,7 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, goto msg_bytes_ready;release_sock (sk);sk_psock_put (sk, psock); -return tcp_recvmsg (sk, msg, len, flags, addr_len); +return tcp_recvmsg (sk, msg, len, flags); } copied = -EAGAIN ; }
net/ipv4/udp.c +4 -5
@@ -2059,8 +2059,7 @@ EXPORT_IPV6_MOD(udp_read_skb);* return it, otherwise we block. */ -int udp_recvmsg (struct sock *sk,struct msghdr *msg,size_t len,int flags, -int *addr_len) +int udp_recvmsg (struct sock *sk,struct msghdr *msg,size_t len,int flags) {struct inet_sock *inet =inet_sk (sk); DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
@@ -2071,7 +2070,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,bool checksum_valid = false;if (flags &MSG_ERRQUEUE ) -return ip_recv_error (sk, msg, len, addr_len); +return ip_recv_error (sk, msg, len); try_again: off =sk_peek_offset (sk, flags);
@@ -2134,11 +2133,11 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, sin->sin_port =udp_hdr (skb)->source; sin->sin_addr.s_addr =ip_hdr (skb)->saddr;memset (sin->sin_zero,0 ,sizeof (sin->sin_zero)); - *addr_len =sizeof (*sin); + msg->msg_namelen =sizeof (*sin);BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK (sk, (struct sockaddr *)sin, - addr_len); + &msg->msg_namelen); }if (udp_test_bit (GRO_ENABLED , sk))
net/ipv4/udp_bpf.c +8 -8
@@ -12,13 +12,13 @@static struct proto *udpv6_prot_saved__read_mostly ;static int sk_udp_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {#if IS_ENABLED (CONFIG_IPV6 )if (sk->sk_family ==AF_INET6 ) -return udpv6_prot_saved->recvmsg (sk, msg, len, flags, addr_len); +return udpv6_prot_saved->recvmsg (sk, msg, len, flags);#endif -return udp_prot.recvmsg (sk, msg, len, flags, addr_len); +return udp_prot.recvmsg (sk, msg, len, flags); }static bool udp_sk_has_data (struct sock *sk)
@@ -61,23 +61,23 @@ static int udp_msg_wait_data(struct sock *sk, struct sk_psock *psock, }static int udp_bpf_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {struct sk_psock *psock;int copied, ret;if (unlikely (flags &MSG_ERRQUEUE )) -return inet_recv_error (sk, msg, len, addr_len); +return inet_recv_error (sk, msg, len);if (!len)return 0 ; psock =sk_psock_get (sk);if (unlikely (!psock)) -return sk_udp_recvmsg (sk, msg, len, flags, addr_len); +return sk_udp_recvmsg (sk, msg, len, flags);if (!psock_has_data (psock)) { - ret =sk_udp_recvmsg (sk, msg, len, flags, addr_len); + ret =sk_udp_recvmsg (sk, msg, len, flags); goto out; }
@@ -92,7 +92,7 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,if (data) {if (psock_has_data (psock)) goto msg_bytes_ready; - ret =sk_udp_recvmsg (sk, msg, len, flags, addr_len); + ret =sk_udp_recvmsg (sk, msg, len, flags); goto out; } copied = -EAGAIN ;
net/ipv4/udp_impl.h +1 -2
@@ -18,8 +18,7 @@ int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,int udp_getsockopt (struct sock *sk,int level,int optname,char __user *optval,int __user *optlen); -int udp_recvmsg (struct sock *sk,struct msghdr *msg,size_t len,int flags, -int *addr_len); +int udp_recvmsg (struct sock *sk,struct msghdr *msg,size_t len,int flags);void udp_destroy_sock (struct sock *sk);#ifdef CONFIG_PROC_FS
net/ipv6/af_inet6.c +3 -8
@@ -661,25 +661,20 @@ int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) } INDIRECT_CALLABLE_DECLARE(int udpv6_recvmsg(struct sock *, struct msghdr *, -size_t ,int ,int *)); +size_t ,int ));int inet6_recvmsg (struct socket *sock,struct msghdr *msg,size_t size,int flags) {struct sock *sk = sock->sk;const struct proto *prot; -int addr_len =0 ; -int err;if (likely (!(flags &MSG_ERRQUEUE )))sock_rps_record_flow (sk);/* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot =READ_ONCE (sk->sk_prot); - err =INDIRECT_CALL_2 (prot->recvmsg, tcp_recvmsg, udpv6_recvmsg, - sk, msg, size, flags, &addr_len); -if (err >=0 ) - msg->msg_namelen = addr_len; -return err; +return INDIRECT_CALL_2 (prot->recvmsg, tcp_recvmsg, udpv6_recvmsg, + sk, msg, size, flags); }const struct proto_ops inet6_stream_ops = {
net/ipv6/datagram.c +4 -5
@@ -451,7 +451,7 @@ static bool ip6_datagram_support_cmsg(struct sk_buff *skb,/* * Handle MSG_ERRQUEUE */ -int ipv6_recv_error (struct sock *sk,struct msghdr *msg,int len,int *addr_len) +int ipv6_recv_error (struct sock *sk,struct msghdr *msg,int len) {struct ipv6_pinfo *np =inet6_sk (sk);struct sock_exterr_skb *serr;
@@ -502,7 +502,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) &sin->sin6_addr); sin->sin6_scope_id =0 ; } - *addr_len =sizeof (*sin); + msg->msg_namelen =sizeof (*sin); }memcpy (&errhdr.ee, &serr->ee,sizeof (struct sock_extended_err ));
@@ -544,8 +544,7 @@ EXPORT_SYMBOL_GPL(ipv6_recv_error);/* * Handle IPV6_RECVPATHMTU */ -int ipv6_recv_rxpmtu (struct sock *sk,struct msghdr *msg,int len, -int *addr_len) +int ipv6_recv_rxpmtu (struct sock *sk,struct msghdr *msg,int len) {struct ipv6_pinfo *np =inet6_sk (sk);struct sk_buff *skb;
@@ -578,7 +577,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, sin->sin6_port =0 ; sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr; - *addr_len =sizeof (*sin); + msg->msg_namelen =sizeof (*sin); }put_cmsg (msg,SOL_IPV6 ,IPV6_PATHMTU ,sizeof (mtu_info), &mtu_info);
net/ipv6/ping.c +1 -2
@@ -24,8 +24,7 @@#include <net/ping.h> /* Compatibility glue so we can support IPv6 when it's compiled as a module */ -static int dummy_ipv6_recv_error (struct sock *sk,struct msghdr *msg,int len, -int *addr_len) +static int dummy_ipv6_recv_error (struct sock *sk,struct msghdr *msg,int len) {return -EAFNOSUPPORT ; }
net/ipv6/raw.c +4 -4
@@ -431,7 +431,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb)*/ static int rawv6_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {struct ipv6_pinfo *np =inet6_sk (sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
@@ -443,10 +443,10 @@ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,return -EOPNOTSUPP ;if (flags &MSG_ERRQUEUE ) -return ipv6_recv_error (sk, msg, len, addr_len); +return ipv6_recv_error (sk, msg, len);if (np->rxopt.bits.rxpmtu &&READ_ONCE (np->rxpmtu)) -return ipv6_recv_rxpmtu (sk, msg, len, addr_len); +return ipv6_recv_rxpmtu (sk, msg, len); skb =skb_recv_datagram (sk, flags, &err);if (!skb)
@@ -480,7 +480,7 @@ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, sin6->sin6_flowinfo =0 ; sin6->sin6_scope_id =ipv6_iface_scope_id (&sin6->sin6_addr,inet6_iif (skb)); - *addr_len =sizeof (*sin6); + msg->msg_namelen =sizeof (*sin6); }sock_recv_cmsgs (msg, sk, skb);
net/ipv6/udp.c +5 -5
@@ -466,7 +466,7 @@ static int udp6_skb_len(struct sk_buff *skb)*/ int udpv6_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {struct ipv6_pinfo *np =inet6_sk (sk);struct inet_sock *inet =inet_sk (sk);
@@ -479,10 +479,10 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,int is_udp4;if (flags &MSG_ERRQUEUE ) -return ipv6_recv_error (sk, msg, len, addr_len); +return ipv6_recv_error (sk, msg, len);if (np->rxopt.bits.rxpmtu &&READ_ONCE (np->rxpmtu)) -return ipv6_recv_rxpmtu (sk, msg, len, addr_len); +return ipv6_recv_rxpmtu (sk, msg, len); try_again: off =sk_peek_offset (sk, flags);
@@ -554,11 +554,11 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,ipv6_iface_scope_id (&sin6->sin6_addr,inet6_iif (skb)); } - *addr_len =sizeof (*sin6); + msg->msg_namelen =sizeof (*sin6);BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK (sk, (struct sockaddr *)sin6, - addr_len); + &msg->msg_namelen); }if (udp_test_bit (GRO_ENABLED , sk))
net/ipv6/udp_impl.h +1 -2
@@ -22,8 +22,7 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname,int udpv6_setsockopt (struct sock *sk,int level,int optname,sockptr_t optval,unsigned int optlen);int udpv6_sendmsg (struct sock *sk,struct msghdr *msg,size_t len); -int udpv6_recvmsg (struct sock *sk,struct msghdr *msg,size_t len,int flags, -int *addr_len); +int udpv6_recvmsg (struct sock *sk,struct msghdr *msg,size_t len,int flags);void udpv6_destroy_sock (struct sock *sk);#ifdef CONFIG_PROC_FS
net/l2tp/l2tp_ip.c +2 -2
@@ -535,7 +535,7 @@ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) }static int l2tp_ip_recvmsg (struct sock *sk,struct msghdr *msg, -size_t len,int flags,int *addr_len) +size_t len,int flags) {struct inet_sock *inet =inet_sk (sk);size_t copied =0 ;
@@ -568,7 +568,7 @@ static int l2tp_ip_recvmsg(struct sock *sk, struct msghdr *msg, sin->sin_addr.s_addr =ip_hdr (skb)->saddr; sin->sin_port =0 ;memset (&sin->sin_zero,0 ,sizeof (sin->sin_zero)); - *addr_len =sizeof (*sin); + msg->msg_namelen =sizeof (*sin); }if (inet_cmsg_flags (inet))ip_cmsg_recv (msg, skb);
net/l2tp/l2tp_ip6.c +3 -3
@@ -678,7 +678,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) }static int l2tp_ip6_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {struct ipv6_pinfo *np =inet6_sk (sk); DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
@@ -690,7 +690,7 @@ static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, goto out;if (flags &MSG_ERRQUEUE ) -return ipv6_recv_error (sk, msg, len, addr_len); +return ipv6_recv_error (sk, msg, len); skb =skb_recv_datagram (sk, flags, &err);if (!skb)
@@ -718,7 +718,7 @@ static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, lsa->l2tp_conn_id =0 ;if (ipv6_addr_type (&lsa->l2tp_addr) &IPV6_ADDR_LINKLOCAL ) lsa->l2tp_scope_id =inet6_iif (skb); - *addr_len =sizeof (*lsa); + msg->msg_namelen =sizeof (*lsa); }if (np->rxopt.all)
net/mptcp/protocol.c +2 -2
@@ -2206,7 +2206,7 @@ static unsigned int mptcp_inq_hint(const struct sock *sk) }static int mptcp_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {struct mptcp_sock *msk =mptcp_sk (sk);struct scm_timestamping_internal tss;
@@ -2216,7 +2216,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,/* MSG_ERRQUEUE is really a no-op till we support IP_RECVERR */ if (unlikely (flags &MSG_ERRQUEUE )) -return inet_recv_error (sk, msg, len, addr_len); +return inet_recv_error (sk, msg, len);lock_sock (sk);if (unlikely (sk->sk_state ==TCP_LISTEN )) {
net/phonet/datagram.c +2 -2
@@ -109,7 +109,7 @@ static int pn_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) }static int pn_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {struct sk_buff *skb =NULL ;struct sockaddr_pn sa;
@@ -143,7 +143,7 @@ static int pn_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,if (msg->msg_name !=NULL ) {__sockaddr_check_size (sizeof (sa));memcpy (msg->msg_name, &sa,sizeof (sa)); - *addr_len =sizeof (sa); + msg->msg_namelen =sizeof (sa); } out:
net/phonet/pep.c +1 -1
@@ -1276,7 +1276,7 @@ struct sk_buff *pep_read(struct sock *sk) }static int pep_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {struct sk_buff *skb;int err;
net/sctp/socket.c +6 -6
@@ -2095,7 +2095,7 @@ static int sctp_skb_pull(struct sk_buff *skb, int len)* 5 for complete description of the flags. */ static int sctp_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {struct sctp_ulpevent *event =NULL ;struct sctp_sock *sp =sctp_sk (sk);
@@ -2104,11 +2104,11 @@ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,int err =0 ;int skb_len; -pr_debug ("%s: sk:%p, msghdr:%p, len:%zd, flags:0x%x, addr_len:%p)\n" , - __func__, sk, msg, len, flags, addr_len); +pr_debug ("%s: sk:%p, msghdr:%p, len:%zd, flags:0x%x)\n" , + __func__, sk, msg, len, flags);if (unlikely (flags &MSG_ERRQUEUE )) -return inet_recv_error (sk, msg, len, addr_len); +return inet_recv_error (sk, msg, len);if (sk_can_busy_loop (sk) &&skb_queue_empty_lockless (&sk->sk_receive_queue))
@@ -2149,9 +2149,9 @@ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,sock_recv_cmsgs (msg, sk, head_skb);if (sctp_ulpevent_is_notification (event)) { msg->msg_flags |=MSG_NOTIFICATION ; - sp->pf->event_msgname (event, msg->msg_name, addr_len); + sp->pf->event_msgname (event, msg->msg_name, &msg->msg_namelen); }else { - sp->pf->skb_msgname (head_skb, msg->msg_name, addr_len); + sp->pf->skb_msgname (head_skb, msg->msg_name, &msg->msg_namelen); }/* Check if we allow SCTP_NXTINFO. */
net/tls/tls.h +1 -1
@@ -161,7 +161,7 @@ void tls_sw_free_resources_rx(struct sock *sk);void tls_sw_release_resources_rx (struct sock *sk);void tls_sw_free_ctx_rx (struct tls_context *tls_ctx);int tls_sw_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len); +int flags);bool tls_sw_sock_is_readable (struct sock *sk); ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe,
net/tls/tls_sw.c +1 -2
@@ -2064,8 +2064,7 @@ static void tls_rx_reader_unlock(struct sock *sk, struct tls_sw_context_rx *ctx)int tls_sw_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags, -int *addr_len) +int flags) {struct tls_context *tls_ctx =tls_get_ctx (sk);struct tls_sw_context_rx *ctx =tls_sw_ctx_rx (tls_ctx);
net/unix/af_unix.c +2 -2
@@ -2702,7 +2702,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t siconst struct proto *prot =READ_ONCE (sk->sk_prot);if (prot != &unix_dgram_proto) -return prot->recvmsg (sk, msg, size, flags,NULL ); +return prot->recvmsg (sk, msg, size, flags);#endif return __unix_dgram_recvmsg (sk, msg, size, flags); }
@@ -3179,7 +3179,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,const struct proto *prot =READ_ONCE (sk->sk_prot);if (prot != &unix_stream_proto) -return prot->recvmsg (sk, msg, size, flags,NULL ); +return prot->recvmsg (sk, msg, size, flags);#endif return unix_stream_read_generic (&state, true); }
net/unix/unix_bpf.c +1 -1
@@ -49,7 +49,7 @@ static int __unix_recvmsg(struct sock *sk, struct msghdr *msg, }static int unix_bpf_recvmsg (struct sock *sk,struct msghdr *msg, -size_t len,int flags,int *addr_len) +size_t len,int flags) {struct unix_sock *u =unix_sk (sk);struct sk_psock *psock;
net/vmw_vsock/af_vsock.c +2 -2
@@ -1412,7 +1412,7 @@ int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, prot =READ_ONCE (sk->sk_prot);if (prot != &vsock_proto) -return prot->recvmsg (sk, msg, len, flags,NULL ); +return prot->recvmsg (sk, msg, len, flags);#endif return __vsock_dgram_recvmsg (sock, msg, len, flags);
@@ -2485,7 +2485,7 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, prot =READ_ONCE (sk->sk_prot);if (prot != &vsock_proto) -return prot->recvmsg (sk, msg, len, flags,NULL ); +return prot->recvmsg (sk, msg, len, flags);#endif return __vsock_connectible_recvmsg (sock, msg, len, flags);
net/vmw_vsock/vsock_bpf.c +1 -1
@@ -74,7 +74,7 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int }static int vsock_bpf_recvmsg (struct sock *sk,struct msghdr *msg, -size_t len,int flags,int *addr_len) +size_t len,int flags) {struct sk_psock *psock;struct vsock_sock *vsk;
net/xfrm/espintcp.c +1 -1
@@ -133,7 +133,7 @@ static int espintcp_parse(struct strparser *strp, struct sk_buff *skb) }static int espintcp_recvmsg (struct sock *sk,struct msghdr *msg,size_t len, -int flags,int *addr_len) +int flags) {struct espintcp_ctx *ctx =espintcp_getctx (sk);struct sk_buff *skb;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 543/1611 sockmap: Fix use-after-free in udp_bpf_recvmsg()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit c010995b29c8939c6aa69e3cb26f8dbee163d156 ]
syzbot reported use-after-free of struct sk_msg in sk_msg_recvmsg(). [0]
sk_msg_recvmsg() peeks sk_msg from psock->ingress_msg under a lock, but its processing is lockless.
Thus, sk_msg_recvmsg() must be serialised by callers, otherwise multiple threads could touch the same sk_msg.
For example, TCP uses lock_sock(), and AF_UNIX uses unix_sk(sk)->iolock.
Initially, udp_bpf_recvmsg() had used lock_sock(), but the cited commit removed it.
Let's serialise sk_msg_recvmsg() with lock_sock() in udp_bpf_recvmsg().
Note that holding spin_lock_bh(&sk->sk_receive_queue.lock) is not an option due to copy_page_to_iter() in sk_msg_recvmsg().
[0]:
BUG: KASAN: slab-use-after-free in sk_msg_recvmsg+0xb54/0xc30 net/core/skmsg.c:428 Read of size 4 at addr ffff88814cdcf000 by task syz.0.24/6020 CPU: 1 UID: 0 PID: 6020 Comm: syz.0.24 Not tainted syzkaller #0 PREEMPT(full) Hardware name: Google Compute Engine/Google Compute Engine, BIOS Google 01/13/2026 Call Trace: <TASK> dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xba/0x230 mm/kasan/report.c:482 kasan_report+0x117/0x150 mm/kasan/report.c:595 sk_msg_recvmsg+0xb54/0xc30 net/core/skmsg.c:428 udp_bpf_recvmsg+0x4bd/0xe00 net/ipv4/udp_bpf.c:84 inet_recvmsg+0x260/0x270 net/ipv4/af_inet.c:891 sock_recvmsg_nosec net/socket.c:1078 [inline] sock_recvmsg+0x1a8/0x270 net/socket.c:1100 ____sys_recvmsg+0x1e6/0x4a0 net/socket.c:2812 ___sys_recvmsg+0x215/0x590 net/socket.c:2854 do_recvmmsg+0x334/0x800 net/socket.c:2949 __sys_recvmmsg net/socket.c:3023 [inline] __do_sys_recvmmsg net/socket.c:3046 [inline] __se_sys_recvmmsg net/socket.c:3039 [inline] __x64_sys_recvmmsg+0x198/0x250 net/socket.c:3039 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xe2/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fb319f9aeb9 Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fb31ad97028 EFLAGS: 00000246 ORIG_RAX: 000000000000012b RAX: ffffffffffffffda RBX: 00007fb31a216090 RCX: 00007fb319f9aeb9 RDX: 0000000000000001 RSI: 0000200000000400 RDI: 0000000000000004 RBP: 00007fb31a008c1f R08: 0000000000000000 R09: 0000000000000000 R10: 0000000040000021 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fb31a216128 R14: 00007fb31a216090 R15: 00007ffe21dd0a98 </TASK> Allocated by task 6019: kasan_save_stack mm/kasan/common.c:57 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:78 poison_kmalloc_redzone mm/kasan/common.c:398 [inline] __kasan_kmalloc+0x93/0xb0 mm/kasan/common.c:415 kasan_kmalloc include/linux/kasan.h:263 [inline] __kmalloc_cache_noprof+0x3d1/0x6e0 mm/slub.c:5780 kmalloc_noprof include/linux/slab.h:957 [inline] kzalloc_noprof include/linux/slab.h:1094 [inline] alloc_sk_msg net/core/skmsg.c:510 [inline] sk_psock_skb_ingress_self+0x60/0x350 net/core/skmsg.c:612 sk_psock_verdict_apply net/core/skmsg.c:1038 [inline] sk_psock_verdict_recv+0x7d9/0x8d0 net/core/skmsg.c:1236 udp_read_skb+0x73e/0x7e0 net/ipv4/udp.c:2045 sk_psock_verdict_data_ready+0x12d/0x550 net/core/skmsg.c:1257 __udp_enqueue_schedule_skb+0xc54/0x10b0 net/ipv4/udp.c:1789 __udp_queue_rcv_skb net/ipv4/udp.c:2346 [inline] udp_queue_rcv_one_skb+0xac5/0x19c0 net/ipv4/udp.c:2475 __udp4_lib_mcast_deliver+0xc06/0xcf0 net/ipv4/udp.c:2585 __udp4_lib_rcv+0x10f6/0x2620 net/ipv4/udp.c:2724 ip_protocol_deliver_rcu+0x282/0x440 net/ipv4/ip_input.c:207 ip_local_deliver_finish+0x3bb/0x6f0 net/ipv4/ip_input.c:241 NF_HOOK+0x336/0x3c0 include/linux/netfilter.h:318 dst_input include/net/dst.h:474 [inline] ip_sublist_rcv_finish+0x221/0x2a0 net/ipv4/ip_input.c:584 ip_list_rcv_finish net/ipv4/ip_input.c:628 [inline] ip_sublist_rcv+0x5c6/0xa70 net/ipv4/ip_input.c:644 ip_list_rcv+0x3f1/0x450 net/ipv4/ip_input.c:678 __netif_receive_skb_list_ptype net/core/dev.c:6195 [inline] __netif_receive_skb_list_core+0x7e5/0x810 net/core/dev.c:6242 __netif_receive_skb_list net/core/dev.c:6294 [inline] netif_receive_skb_list_internal+0x995/0xcf0 net/core/dev.c:6385 netif_receive_skb_list+0x54/0x410 net/core/dev.c:6437 xdp_recv_frames net/bpf/test_run.c:269 [inline] xdp_test_run_batch net/bpf/test_run.c:350 [inline] bpf_test_run_xdp_live+0x1946/0x1cf0 net/bpf/test_run.c:379 bpf_prog_test_run_xdp+0x81c/0x1160 net/bpf/test_run.c:1396 bpf_prog_test_run+0x2c7/0x340 kernel/bpf/syscall.c:4703 __sys_bpf+0x5cb/0x920 kernel/bpf/syscall.c:6182 __do_sys_bpf kernel/bpf/syscall.c:6274 [inline] __se_sys_bpf kernel/bpf/syscall.c:6272 [inline] __x64_sys_bpf+0x7c/0x90 kernel/bpf/syscall.c:6272 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xe2/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f Freed by task 6021: kasan_save_stack mm/kasan/common.c:57 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:78 kasan_save_free_info+0x46/0x50 mm/kasan/generic.c:584 poison_slab_object mm/kasan/common.c:253 [inline] __kasan_slab_free+0x5c/0x80 mm/kasan/common.c:285 kasan_slab_free include/linux/kasan.h:235 [inline] slab_free_hook mm/slub.c:2540 [inline] slab_free mm/slub.c:6674 [inline] kfree+0x1be/0x650 mm/slub.c:6882 kfree_sk_msg include/linux/skmsg.h:385 [inline] sk_msg_recvmsg+0xaa8/0xc30 net/core/skmsg.c:483 udp_bpf_recvmsg+0x4bd/0xe00 net/ipv4/udp_bpf.c:84 inet_recvmsg+0x260/0x270 net/ipv4/af_inet.c:891 sock_recvmsg_nosec net/socket.c:1078 [inline] sock_recvmsg+0x1a8/0x270 net/socket.c:1100 ____sys_recvmsg+0x1e6/0x4a0 net/socket.c:2812 ___sys_recvmsg+0x215/0x590 net/socket.c:2854 do_recvmmsg+0x334/0x800 net/socket.c:2949 __sys_recvmmsg net/socket.c:3023 [inline] __do_sys_recvmmsg net/socket.c:3046 [inline] __se_sys_recvmmsg net/socket.c:3039 [inline] __x64_sys_recvmmsg+0x198/0x250 net/socket.c:3039 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xe2/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f
--- net/ipv4/udp_bpf.c | 9 +++++++++ 1 file changed, 9 insertions(+)
net/ipv4/udp_bpf.c +9 -0
@@ -52,7 +52,9 @@ static int udp_msg_wait_data(struct sock *sk, struct sk_psock *psock,sk_set_bit (SOCKWQ_ASYNC_WAITDATA , sk); ret =udp_msg_has_data (sk, psock);if (!ret) { +release_sock (sk);wait_woken (&wait,TASK_INTERRUPTIBLE , timeo); +lock_sock (sk); ret =udp_msg_has_data (sk, psock); }sk_clear_bit (SOCKWQ_ASYNC_WAITDATA , sk);
@@ -81,6 +83,7 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, goto out; } +lock_sock (sk); msg_bytes_ready: copied =sk_msg_recvmsg (sk, psock, msg, len, flags);if (!copied) {
@@ -92,11 +95,17 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,if (data) {if (psock_has_data (psock)) goto msg_bytes_ready; + +release_sock (sk); + ret =sk_udp_recvmsg (sk, msg, len, flags); goto out; } copied = -EAGAIN ; } + +release_sock (sk); + ret = copied; out:sk_psock_put (sk, psock);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 544/1611 bpf, sockmap: fix integer overflow in bpf_msg_pop_data() bounds check
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sechang Lim <[email protected]>
[ Upstream commit a48802fb2cd2d1e23651989f8ff4d15e9d5dad54 ]
start and len are u32, so
u64 last = start + len;
evaluates start + len in 32-bit and wraps before storing it in last. The bounds check
if (start >= offset + l || last > msg->sg.size) return -EINVAL;
can then be passed with an out-of-range start/len, after which the pop loop runs off the end of the scatterlist and sk_msg_shift_left() calls put_page() on the empty msg->sg.end slot:
Oops: general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] RIP: 0010:sk_msg_shift_left net/core/filter.c:2957 [inline] RIP: 0010:____bpf_msg_pop_data net/core/filter.c:3103 [inline] RIP: 0010:bpf_msg_pop_data+0x753/0x1a10 net/core/filter.c:2984 Call Trace: <TASK> bpf_prog_4cc92c278f4d5d56+0x1b1/0x1e8 bpf_prog_run_pin_on_cpu+0x107/0x320 include/linux/filter.h:746 sk_psock_msg_verdict+0x357/0x7f0 net/core/skmsg.c:934 tcp_bpf_send_verdict net/ipv4/tcp_bpf.c:420 [inline] tcp_bpf_sendmsg+0x766/0x1ae0 net/ipv4/tcp_bpf.c:583 __sock_sendmsg+0x153/0x1c0 net/socket.c:802 __sys_sendto+0x326/0x430 net/socket.c:2265 __x64_sys_sendto+0xe3/0x100 net/socket.c:2268 do_syscall_64+0x14c/0x480 entry_SYSCALL_64_after_hwframe+0x77/0x7f </TASK>
Widen the addition with a (u64) cast so the bound is evaluated in 64-bit and a len near U32_MAX no longer wraps below msg->sg.size.
While here, change pop from int to u32. It counts bytes against the unsigned scatterlist lengths and can never be negative, so the signed type only invites sign-confusion in the pop loop.
--- net/core/filter.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
net/core/filter.c +2 -2
@@ -2999,8 +2999,8 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, u32, len, u64, flags) {u32 i =0 , l =0 , space, offset =0 ; -u64 last = start + len; -int pop; +u64 last = (u64 )start + len; +u32 pop;if (unlikely (flags))return -EINVAL ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 545/1611 MIPS: mm: Fix out-of-bounds write in maar_res_walk()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yadan Fan <[email protected]>
[ Upstream commit 1b001b16bc88f3f7817e228acfd91ee01bdcfcce ]
maar_res_walk() uses wi->num_cfg as the index into the fixed-size wi->cfg array, but checks whether the array is full only after it has filled the selected entry. If walk_system_ram_range() reports more than 16 memory ranges, the overflow call writes one struct maar_config past the end of the array before WARN_ON() prevents num_cfg from advancing.
Move the full-array check before taking the array slot and return non-zero when the scratch array is full, so walk_system_ram_range() terminates the walk instead of invoking the callback for further ranges.
--- arch/mips/mm/init.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)
arch/mips/mm/init.c +8 -4
@@ -275,9 +275,15 @@ static int maar_res_walk(unsigned long start_pfn, unsigned long nr_pages, void *data) {struct maar_walk_info *wi = data; -struct maar_config *cfg = &wi->cfg[wi->num_cfg]; +struct maar_config *cfg;unsigned int maar_align; +/* Ensure we don't overflow the cfg array */ +if (WARN_ON (wi->num_cfg >=ARRAY_SIZE (wi->cfg))) +return -1 ; + + cfg = &wi->cfg[wi->num_cfg]; +/* MAAR registers hold physical addresses right shifted by 4 bits */ maar_align =BIT (MIPS_MAAR_ADDR_SHIFT +4 );
@@ -286,9 +292,7 @@ static int maar_res_walk(unsigned long start_pfn, unsigned long nr_pages, cfg->upper =ALIGN_DOWN (PFN_PHYS (start_pfn + nr_pages), maar_align) -1 ; cfg->attrs =MIPS_MAAR_S ; -/* Ensure we don't overflow the cfg array */ -if (!WARN_ON (wi->num_cfg >=ARRAY_SIZE (wi->cfg))) - wi->num_cfg++; + wi->num_cfg++;return 0 ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 546/1611 powerpc/perf: fix preempt count underflow in fsl_emb_pmu_del
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Aboorva Devarajan <[email protected]>
[ Upstream commit 81e3a86030462824a67d697739cf3f387f4ba350 ]
fsl_emb_pmu_del() unconditionally calls put_cpu_var(cpu_hw_events) at the 'out:' label, but only calls the matching get_cpu_var() after the 'i < 0' early-return check. When event->hw.idx is negative the function jumps to 'out:' without having taken get_cpu_var(), and the trailing put_cpu_var() then issues an unmatched preempt_enable(), underflowing preempt_count.
On a CONFIG_PREEMPT=y kernel preempt_count would underflow and eventually present as a 'scheduling while atomic' BUG.
Move put_cpu_var() to pair with get_cpu_var() so the percpu access is correctly bracketed and the 'out:' label only handles perf_pmu_enable.
--- arch/powerpc/perf/core-fsl-emb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
arch/powerpc/perf/core-fsl-emb.c +2 -1
@@ -366,9 +366,10 @@ static void fsl_emb_pmu_del(struct perf_event *event, int flags) cpuhw->n_events--; +put_cpu_var (cpu_hw_events); + out:perf_pmu_enable (event->pmu); -put_cpu_var (cpu_hw_events); }static void fsl_emb_pmu_start (struct perf_event *event,int ef_flags)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 547/1611 powerpc/powernv: fix preempt count leak in pnv_kexec_wait_secondaries_down
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Aboorva Devarajan <[email protected]>
[ Upstream commit 0ecd26e93e698c8327521910fc6296f5b84a4b92 ]
pnv_kexec_wait_secondaries_down() calls get_cpu() to obtain the current CPU id but never calls the matching put_cpu(), leaking one preempt_disable() nesting level on every invocation.
In practice the imbalance does not trigger a visible splat because the kexec teardown path is a one-way trip: IRQs are already disabled, no schedule() occurs after the leak, and default_machine_kexec() overwrites preempt_count with HARDIRQ_OFFSET before jumping into kexec_sequence() which never returns. However the bookkeeping is still wrong.
The function only needs the current CPU id, and this path runs with interrupts disabled and the CPU pinned, so the preempt_disable() side-effect of get_cpu() is unnecessary. Replace it with raw_smp_processor_id().
--- arch/powerpc/platforms/powernv/setup.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
arch/powerpc/platforms/powernv/setup.c +2 -1
@@ -396,7 +396,8 @@ static void pnv_kexec_wait_secondaries_down(void) {int my_cpu, i, notified =-1 ; - my_cpu =get_cpu (); +/* Called with interrupts disabled, so the CPU is pinned. */ + my_cpu =raw_smp_processor_id ();for_each_online_cpu (i) {uint8_t status;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 548/1611 powerpc/kexec: fix double get_cpu() imbalance in kexec_prepare_cpus
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Aboorva Devarajan <[email protected]>
[ Upstream commit 5c86f1c1f972761a04bf22f4c0618d1aa714185b ]
kexec_prepare_cpus_wait() calls get_cpu() internally to obtain the current CPU id. kexec_prepare_cpus() calls kexec_prepare_cpus_wait() twice -- once for KEXEC_STATE_IRQS_OFF and once for KEXEC_STATE_REAL_MODE -- but only issues a single put_cpu() at the end, leaving preempt_count elevated by one extra nesting level.
In practice the imbalance does not trigger a 'scheduling while atomic' splat because the kexec path is a one-way trip: IRQs are already disabled, no schedule() occurs after the leak, and default_machine_kexec() overwrites preempt_count with HARDIRQ_OFFSET before jumping into kexec_sequence() which never returns. However the bookkeeping is still wrong.
kexec_prepare_cpus() calls local_irq_disable()/hard_irq_disable() before invoking kexec_prepare_cpus_wait(), so the CPU is already pinned and the get_cpu()/put_cpu() preempt_disable() bracketing is unnecessary. Only the current CPU id is needed, so replace get_cpu() with raw_smp_processor_id() and drop the now-unneeded put_cpu().
--- arch/powerpc/kexec/core_64.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)
arch/powerpc/kexec/core_64.c +1 -3
@@ -169,7 +169,7 @@ static void kexec_prepare_cpus_wait(int wait_state)int my_cpu, i, notified=-1 ;hw_breakpoint_disable (); - my_cpu =get_cpu (); + my_cpu =raw_smp_processor_id ();/* Make sure each CPU has at least made it to the state we need. * * FIXME: There is a (slim) chance of a problem if not all of the CPUs
@@ -267,8 +267,6 @@ static void kexec_prepare_cpus(void)/* after we tell the others to go down */ if (ppc_md.kexec_cpu_down) ppc_md.kexec_cpu_down(0, 0); - - put_cpu(); }#else /* ! SMP */
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 549/1611 KEYS: Use acquire when reading state in keyring search
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Gui-Dong Han <[email protected]>
[ Upstream commit c1201b37f666f6466ab1fd3a381c2b7a4b7e9fee ]
The negative-key race fix added release/acquire ordering for key use.
Publish payload before state; read state before payload.
keyring_search_iterator() still uses READ_ONCE() before match callbacks. An asymmetric match callback calls asymmetric_key_ids(), which reads key->payload.data[asym_key_ids].
Use key_read_state() there to complete that ordering.
--- security/keys/keyring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
security/keys/keyring.c +1 -1
@@ -576,7 +576,7 @@ static int keyring_search_iterator(const void *object, void *iterator_data)struct keyring_search_context *ctx = iterator_data;const struct key *key =keyring_ptr_to_key (object);unsigned long kflags =READ_ONCE (key->flags); -short state =READ_ONCE (key->state); +short state =key_read_state (key);kenter ("{%d}" , key->serial);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 550/1611 tipc: fix UAF in tipc_l2_send_msg()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <[email protected]>
[ Upstream commit f4c3d89fc986b0da196ddfc6cfe0ea5d5d08bec6 ]
Syzbot reported a slab-use-after-free in ipvlan_hard_header() when called from tipc_l2_send_msg().
The root cause is that tipc_disable_l2_media() calls synchronize_net() while b->media_ptr is still valid. This allows concurrent RCU readers to obtain the device pointer after synchronize_net() has finished. The pointer is cleared later in bearer_disable(), but without any subsequent synchronization, allowing the device to be freed while still in use by readers.
Fix this by clearing b->media_ptr in tipc_disable_l2_media() before calling synchronize_net().
This is safe to do now because the call order in bearer_disable() was reversed in 0d051bf93c06 ("tipc: make bearer packet filtering generic") to call tipc_node_delete_links() (which needs the pointer) before disable_media().
https: //lore.kernel.org/netdev/[email protected]/T/#u
--- net/tipc/bearer.c | 1 + 1 file changed, 1 insertion(+)
net/tipc/bearer.c +1 -0
@@ -482,6 +482,7 @@ void tipc_disable_l2_media(struct tipc_bearer *b) dev = (struct net_device *)rtnl_dereference (b->media_ptr);dev_remove_pack (&b->pt);RCU_INIT_POINTER (dev->tipc_ptr,NULL ); +RCU_INIT_POINTER (b->media_ptr,NULL );synchronize_net ();dev_put (dev); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 551/1611 tcp: ipv6: clamp default adverting MSS to avoid GSO_BY_FRAGS (0xFFFF)
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <[email protected]>
[ Upstream commit 2bf43d0e2e6a27d52a7d624e2d6b9116972e8a22 ]
When MTU is large, ip6_default_advmss() can return IPV6_MAXPLEN (65535). This is interpreted by TCP as mss_clamp, allowing the MSS to reach 65535.
However, 0xFFFF is also used as a magic value GSO_BY_FRAGS in the kernel. If a TCP packet with gso_size=0xFFFF is passed to skb_segment(), it will be mistakenly treated as GSO_BY_FRAGS, leading to a NULL pointer dereference because local TCP packets do not use frag_list.
Fix this by returning min(IPV6_MAXPLEN, GSO_BY_FRAGS - 1) (65534) from ip6_default_advmss() when MTU is large.
Also update the stale comment in ip6_default_advmss() which suggested that IPV6_MAXPLEN is returned to mean "any MSS".
--- net/ipv6/route.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
net/ipv6/route.c +3 -3
@@ -3268,11 +3268,11 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst)/* * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and * corresponding MSS is IPV6_MAXPLEN - tcp_header_size. -* IPV6_MAXPLEN is also valid and means: "any MSS, -* rely only on pmtu discovery" +* Limit the default MSS to GSO_BY_FRAGS - 1 to avoid +* collision with the GSO_BY_FRAGS magic value (0xFFFF). */ if (mtu >IPV6_MAXPLEN -sizeof (struct tcphdr )) - mtu =IPV6_MAXPLEN ; + mtu = min_t(unsigned int, IPV6_MAXPLEN, GSO_BY_FRAGS - 1);return mtu; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 552/1611 net: airoha: Fix always-true condition in PPE1 queue reservation loop
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Wayen.Yan <[email protected]>
[ Upstream commit c66f8511a8109fa50767941b26d3623e316fde02 ]
In airoha_fe_pse_ports_init(), the inner condition for PPE1 queue reservation is identical to the for-loop bound, making it always true and the else branch dead code:
for (q = 0; q < pse_port_num_queues[FE_PSE_PORT_PPE1]; q++) {
if (q < pse_port_num_queues[FE_PSE_PORT_PPE1]) /* always true */
set RSV_PAGES;
else
set 0; /* unreachable */
}The intended behavior is to reserve pages only for the first half of the queues, matching the PPE2 implementation on line 334 which correctly uses the /2 divisor. Fix the PPE1 condition accordingly.
--- drivers/net/ethernet/airoha/airoha_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/airoha/airoha_eth.c +1 -1
@@ -311,7 +311,7 @@ static void airoha_fe_pse_ports_init(struct airoha_eth *eth) PSE_QUEUE_RSV_PAGES);/* PPE1 */ for (q =0 ; q < pse_port_num_queues[FE_PSE_PORT_PPE1 ]; q++) { -if (q < pse_port_num_queues[FE_PSE_PORT_PPE1 ]) +if (q < pse_port_num_queues[FE_PSE_PORT_PPE1 ] /2 )airoha_fe_set_pse_oq_rsv (eth,FE_PSE_PORT_PPE1 , q,PSE_QUEUE_RSV_PAGES );else
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 553/1611 net: ethernet: oa_tc6: mdiobus->parent initialized with NULL
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Selvamani Rajagopal <[email protected]>
[ Upstream commit a221d3f7e3f3ea6a3b4bc511cf2a59242daa06e1 ]
As "dev" pointer in oa_tc6 structure is never initialized, mbiobus->parent was initialized with NULL. This change fixes it by initializing it with device pointer of spi.
--- drivers/net/ethernet/oa_tc6.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/net/ethernet/oa_tc6.c +1 -2
@@ -107,7 +107,6 @@/* Internal structure for MAC-PHY drivers */ struct oa_tc6 { -struct device *dev;struct net_device *netdev;struct phy_device *phydev;struct mii_bus *mdiobus;
@@ -518,7 +517,7 @@ static int oa_tc6_mdiobus_register(struc tc6->mdiobus->read_c45 = oa_tc6_mdiobus_read_c45; tc6->mdiobus->write_c45 = oa_tc6_mdiobus_write_c45; tc6->mdiobus->name ="oa-tc6-mdiobus" ; - tc6->mdiobus->parent = tc6->dev; + tc6->mdiobus->parent = &tc6->spi->dev;snprintf (tc6->mdiobus->id,ARRAY_SIZE (tc6->mdiobus->id),"%s" ,dev_name (&tc6->spi->dev));
Greg Kroah-Hartman
maintainerPATCH 554/1611 net: ethernet: oa_tc6: Remove FCS size in RX frame
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Selvamani Rajagopal <[email protected]>
[ Upstream commit a5a1d11dd3729146abe7420b874bab15870a42b4 ]
OA TC6 MAC-PHY appends FCS to the incoming frame. It must be removed from the frame before being passed to the stack.
With FCS in the frame, many applications, like ping or any application that uses IP layer may work as they may carry the packet size information in the protocol.
Application like ptp4l, particularly if it uses layer 2 for its communication, it will fail with "bad message" due to the extra 4 bytes added by the presence of FCS.
--- drivers/net/ethernet/oa_tc6.c | 11 +++++++++++ 1 file changed, 11 insertions(+)
drivers/net/ethernet/oa_tc6.c +11 -0
@@ -751,6 +751,17 @@ static int oa_tc6_process_rx_chunk_footestatic void oa_tc6_submit_rx_skb (struct oa_tc6 *tc6) { +/* MAC-PHY delivers each frame with its Ethernet FCS attached. +* Strip it before handing over to the stack, unless the user +* has asked to keep it via NETIF_F_RXFCS. Keeping the FCS +* in the frame is harmless for IP traffic, but is parsed as +* a (malformed) suffix TLV by PTP, which makes ptp4l reject +* every message with "bad message" error. +*/ +if (!(tc6->netdev->features &NETIF_F_RXFCS ) && + tc6->rx_skb->len >ETH_FCS_LEN ) +skb_trim (tc6->rx_skb, tc6->rx_skb->len -ETH_FCS_LEN ); + tc6->rx_skb->protocol =eth_type_trans (tc6->rx_skb, tc6->netdev); tc6->netdev->stats.rx_packets++; tc6->netdev->stats.rx_bytes += tc6->rx_skb->len;
Greg Kroah-Hartman
maintainerPATCH 555/1611 dt-bindings: net: updated interrupt type to be active low, level triggered
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Selvamani Rajagopal <[email protected]>
[ Upstream commit 31e56112e6544afba0a50d60251175585ee62943 ]
According to OPEN Alliance 10BASE-T1x MACPHY Serial Interface (TC6) specification, interrupt type is active low, level triggered interrupt.
Specification calls for when interrupt level will be asserted and what condition it is de-asserted. By using edge triggered interrupt, there is a potential chance to miss it, particularly if it is asserted when interrupt is disabled.
Level triggered interrupt can't be missed as it gets de-asserted only on interrupt handler taking actions on interrupting conditions.
--- Documentation/devicetree/bindings/net/microchip,lan8650.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
Documentation/devicetree/bindings/net/microchip,lan8650.yaml +1 -1
@@ -67,7 +67,7 @@ examples: pinctrl-names = "default"; pinctrl-0 = <ð0_pins>; interrupt-parent = <&gpio>; - interrupts = <6 IRQ_TYPE_EDGE_FALLING>; + interrupts = <6 IRQ_TYPE_LEVEL_LOW>; local-mac-address = [04 05 06 01 02 03]; spi-max-frequency = <15000000>; };
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 556/1611 ionic: Fix check in ionic_get_link_ext_stats
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Brett Creeley <[email protected]>
[ Upstream commit 7678e69079c10b2fb10977f28f44ddb22971ea5b ]
The current check will fail if SR-IOV is not initialized for the physical function; this is because is_physfn is 0 if sriov_init() isn't run or fails. Change the check that prevents getting the link down count to use is_virtfn instead so that VFs don't get this functionality, which was the original intent.
--- drivers/net/ethernet/pensando/ionic/ionic_ethtool.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)
drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +9 -2
@@ -116,8 +116,15 @@ static void ionic_get_link_ext_stats(struct net_device *netdev, {struct ionic_lif *lif =netdev_priv (netdev); -if (lif->ionic->pdev->is_physfn) - stats->link_down_events = lif->link_down_count; +if (lif->ionic->pdev->is_virtfn) +return ; + +if (!lif->ionic->idev.port_info) { +netdev_err_once (netdev,"port_info not initialized\n" ); +return ; + } + + stats->link_down_events = lif->link_down_count; } static int ionic_get_link_ksettings(struct net_device *netdev,
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 557/1611 RDMA/bnxt_re: Free SRQ toggle page after firmware teardown
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Selvin Xavier <[email protected]>
[ Upstream commit 131e2918b9b0529687e67e2e58047304027f095a ]
Free the toggle page only after firmware teardown completes so that an NQ interrupt arriving during bnxt_qplib_destroy_srq() won't write the toggle values to an already-freed page. Move free_page() after bnxt_qplib_destroy_srq().
--- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/infiniband/hw/bnxt_re/ib_verbs.c +3 -3
@@ -1826,11 +1826,11 @@ int bnxt_re_destroy_srq(struct ib_srq *ib_srq, struct ib_udata *udata)struct bnxt_re_dev *rdev = srq->rdev;struct bnxt_qplib_srq *qplib_srq = &srq->qplib_srq; -if (rdev->chip_ctx->modes.toggle_bits &BNXT_QPLIB_SRQ_TOGGLE_BIT ) { -free_page ((unsigned long )srq->uctx_srq_page); +if (rdev->chip_ctx->modes.toggle_bits &BNXT_QPLIB_SRQ_TOGGLE_BIT )hash_del (&srq->hash_entry); - }bnxt_qplib_destroy_srq (&rdev->qplib_res, qplib_srq); +if (rdev->chip_ctx->modes.toggle_bits &BNXT_QPLIB_SRQ_TOGGLE_BIT ) +free_page ((unsigned long )srq->uctx_srq_page);ib_umem_release (srq->umem);atomic_dec (&rdev->stats.res.srq_count);return 0 ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 558/1611 RDMA/bnxt_re: Avoid displaying the kernel pointer
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Selvin Xavier <[email protected]>
[ Upstream commit 7d70c704a06f620d5d421ab76bac5e225bfb4308 ]
While dumping the info on MR using the rdma tool, we dump the mr_hwq which is a kernel pointer. There is no need to expose this value for end user. So avoid it.
--- drivers/infiniband/hw/bnxt_re/main.c | 2 -- 1 file changed, 2 deletions(-)
drivers/infiniband/hw/bnxt_re/main.c +0 -2
@@ -1093,8 +1093,6 @@ static int bnxt_re_fill_res_mr_entry(struct sk_buff *msg, struct ib_mr *ib_mr) goto err;if (rdma_nl_put_driver_u32 (msg,"element_size" , mr_hwq->element_size)) goto err; -if (rdma_nl_put_driver_u64_hex (msg,"hwq" , (unsigned long )mr_hwq)) - goto err;if (rdma_nl_put_driver_u64_hex (msg,"va" , mr->qplib_mr.va)) goto err;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 559/1611 RDMA/bnxt_re: Move the UAPI methods to a dedicated file
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kalesh AP <[email protected]>
[ Upstream commit eee6268421a2ccc6d47d8e175a1f4bfcd78a83ca ]
This is in preparation for upcoming patches in the series. Driver has to support additional UAPIs for some applications. Moving current UAPI implementation to a new file, uapi.c.
Stable-dep-of: a57592c6392a ("RDMA/bnxt_re: Fail DBR related page allocation UAPIs if the feature is disabled")
--- drivers/infiniband/hw/bnxt_re/Makefile | 2 +- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 305 +------------------- drivers/infiniband/hw/bnxt_re/ib_verbs.h | 3 + drivers/infiniband/hw/bnxt_re/uapi.c | 339 +++++++++++++++++++++++ 4 files changed, 344 insertions(+), 305 deletions(-) create mode 100644 drivers/infiniband/hw/bnxt_re/uapi.c
drivers/infiniband/hw/bnxt_re/Makefile +1 -1
@@ -5,4 +5,4 @@ obj-$(CONFIG_INFINIBAND_BNXT_RE) += bnxt_re.o bnxt_re-y := main.o ib_verbs.o \ qplib_res.o qplib_rcfw.o \ qplib_sp.o qplib_fp.o hw_counters.o \ - debugfs.o + debugfs.o uapi.o
drivers/infiniband/hw/bnxt_re/ib_verbs.c +1 -304
320 lines not on this page · raw message
drivers/infiniband/hw/bnxt_re/ib_verbs.h +3 -0
@@ -293,4 +293,7 @@ static inline u32 __to_ib_port_num(u16 port_id)unsigned long bnxt_re_lock_cqs (struct bnxt_re_qp *qp);void bnxt_re_unlock_cqs (struct bnxt_re_qp *qp,unsigned long flags); +struct bnxt_re_user_mmap_entry * +bnxt_re_mmap_entry_insert (struct bnxt_re_ucontext *uctx,u64 mem_offset, +enum bnxt_re_mmap_flag mmap_flag,u64 *offset);#endif /* __BNXT_RE_IB_VERBS_H__ */
drivers/infiniband/hw/bnxt_re/uapi.c new file +339 -0
339 lines not on this page · raw message
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 560/1611 RDMA/bnxt_re: Fail DBR related page allocation UAPIs if the feature is disabled
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Selvin Xavier <[email protected]>
[ Upstream commit a57592c6392a8e333c9c2731701297a5a279313a ]
No need to support the DBR related page allocations if the pacing feature is disabled. Fail the request if pacing is disabled.
--- drivers/infiniband/hw/bnxt_re/uapi.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/infiniband/hw/bnxt_re/uapi.c +4 -0
@@ -112,12 +112,16 @@ static int UVERBS_HANDLER(BNXT_RE_METHOD_ALLOC_PAGE)(struct uverbs_attr_bundle *break ;case BNXT_RE_ALLOC_DBR_BAR_PAGE : +if (!rdev->pacing.dbr_pacing) +return -EOPNOTSUPP ; length =PAGE_SIZE ; addr = (u64 )rdev->pacing.dbr_bar_addr; mmap_flag =BNXT_RE_MMAP_DBR_BAR ;break ;case BNXT_RE_ALLOC_DBR_PAGE : +if (!rdev->pacing.dbr_pacing) +return -EOPNOTSUPP ; length =PAGE_SIZE ; addr = (u64 )rdev->pacing.dbr_page; mmap_flag =BNXT_RE_MMAP_DBR_PAGE ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 561/1611 ksmbd: fix use-after-free in same_client_has_lease()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Guangshuo Li <[email protected]>
[ Upstream commit 65b655f65c3ca1ab5d598d3832bb0ff531725858 ]
same_client_has_lease() returns an opinfo pointer from ci->m_op_list after dropping ci->m_lock without taking a reference.
smb_grant_oplock() then dereferences that pointer in copy_lease() and when checking breaking_cnt. A concurrent close can remove the old lease from ci->m_op_list and drop the last reference before the caller uses the returned pointer, leading to a use-after-free.
Take a reference when same_client_has_lease() selects an existing lease, drop any previous match while scanning, and release the returned reference in smb_grant_oplock() after copying the lease state.
--- fs/smb/server/oplock.c | 6 ++++++ 1 file changed, 6 insertions(+)
fs/smb/server/oplock.c +6 -0
@@ -531,7 +531,12 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, ret =compare_guid_key (opinfo, client_guid, lctx->lease_key);if (ret) { +if (!atomic_inc_not_zero (&opinfo->refcount)) +continue ; +if (m_opinfo) +opinfo_put (m_opinfo); m_opinfo = opinfo; +/* skip upgrading lease about breaking lease */ if (atomic_read (&opinfo->breaking_cnt))continue ;
@@ -1249,6 +1254,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid,if (atomic_read (&m_opinfo->breaking_cnt)) opinfo->o_lease->flags =SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE ; +opinfo_put (m_opinfo); goto out; } }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 562/1611 mfd: rsmu: Fix page register setup
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthew Bystrin <[email protected]>
[ Upstream commit 6bc38f26ed07197b11a2b588edf1f43bfbc81d76 ]
Fix writes to page register in 8A3400x family (Clock Matrix).
All calls to rsmu_write_page_register() (both in i2c and spi) have resulted in early return, because all addresses in include/linux/mfd/idt8a340_reg.h are less than RSMU_CM_SCSR_BASE.
There were 2 separate patch series which have to be merged in one time:
mfd and ptp. The latter have been merged, the former[1] have not.
--- drivers/mfd/rsmu_i2c.c | 6 +----- drivers/mfd/rsmu_spi.c | 5 +---- 2 files changed, 2 insertions(+), 9 deletions(-)
drivers/mfd/rsmu_i2c.c +1 -5
@@ -134,14 +134,10 @@ static int rsmu_i2c_write_device(struct rsmu_ddata *rsmu, u8 reg, u8 *buf, u8 bystatic int rsmu_write_page_register (struct rsmu_ddata *rsmu,u32 reg,rsmu_rw_device rsmu_write_device) { -u32 page = reg &RSMU_CM_PAGE_MASK ; +u32 page = (reg |RSMU_CM_SCSR_BASE ) &RSMU_CM_PAGE_MASK ;u8 buf[4 ];int err; -/* Do not modify offset register for none-scsr registers */ -if (reg <RSMU_CM_SCSR_BASE ) -return 0 ; -/* Simply return if we are on the same page */ if (rsmu->page == page)return 0 ;
drivers/mfd/rsmu_spi.c +1 -4
@@ -101,11 +101,8 @@ static int rsmu_write_page_register(struct rsmu_ddata *rsmu, u32 reg)switch (rsmu->type) {case RSMU_CM : -/* Do not modify page register for none-scsr registers */ -if (reg <RSMU_CM_SCSR_BASE ) -return 0 ; page_reg =RSMU_CM_PAGE_ADDR ; - page = reg &RSMU_PAGE_MASK ; + page = (reg |RSMU_CM_SCSR_BASE ) &RSMU_PAGE_MASK ; buf[0 ] = (u8)(page &0xFF ); buf[1 ] = (u8)((page >>8 ) &0xFF ); buf[2 ] = (u8)((page >>16 ) &0xFF );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 563/1611 mfd: cs42l43: Sanity check firmware size
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Charles Keepax <[email protected]>
[ Upstream commit b6ef1a74b3ec254f87a6a3c554fe8f8083ebd37c ]
Currently the code checks if a firmware was received, however it does not verify that the firmware size is larger than the firmware header. As the firmware pointer is dereferenced as a pointer to the header structure this could lead to an out of bounds memory access. Add the missing check.
--- drivers/mfd/cs42l43.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/mfd/cs42l43.c +1 -1
@@ -676,7 +676,7 @@ static void cs42l43_mcu_load_firmware(const struct firmware *firmware, void *conunsigned int loadaddr, val;int ret; -if (!firmware) { +if (!firmware || firmware->size <sizeof (*hdr)) {dev_err (cs42l43->dev,"Failed to load firmware\n" ); cs42l43->firmware_error = -ENODEV ; goto err;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 564/1611 ocfs2: fix circular locking dependency in ocfs2_dio_end_io_write
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Aleksandr Nogikh <[email protected]>
[ Upstream commit ff6f26c58421614b02694ac9d219ac61d924bc68 ]
A circular locking dependency involves INODE_ALLOC_SYSTEM_INODE, EXTENT_ALLOC_SYSTEM_INODE, and ORPHAN_DIR_SYSTEM_INODE.
1. ocfs2_mknod() acquires INODE_ALLOC then EXTENT_ALLOC.
2. ocfs2_dio_end_io_write() acquires EXTENT_ALLOC for unwritten extents, then ORPHAN_DIR via ocfs2_del_inode_from_orphan() while still holding EXTENT_ALLOC.
3. ocfs2_wipe_inode() acquires ORPHAN_DIR then INODE_ALLOC via ocfs2_remove_inode.
Break the cycle in ocfs2_dio_end_io_write() by freeing the allocation contexts (releasing EXTENT_ALLOC) before acquiring ORPHAN_DIR.
WARNING: possible circular locking dependency detected
------------------------------------------------------
is trying to acquire lock:ffff8881e78b33a0 (&ocfs2_sysfile_lock_key[INODE_ALLOC_SYSTEM_INODE]){+.+.}-{4:4}, at:ocfs2_evict_inode+0x1539/0x43b0 fs/ocfs2/inode.c:1299
but task is already holding lock:ffff8881e78b4fa0 (&ocfs2_sysfile_lock_key[ORPHAN_DIR_SYSTEM_INODE]){+.+.}-{4:4}, at:ocfs2_evict_inode+0xe97/0x43b0 fs/ocfs2/inode.c:1299
the existing dependency chain (in reverse order) is:
-> #2 (&ocfs2_sysfile_lock_key[ORPHAN_DIR_SYSTEM_INODE]){+.+.}-{4:4}:
inode_lock include/linux/fs.h:1029 [inline]
ocfs2_del_inode_from_orphan+0x12e/0x7a0 fs/ocfs2/namei.c:2728
ocfs2_dio_end_io+0xf9c/0x1370 fs/ocfs2/aops.c:2418
dio_complete+0x25b/0x790 fs/direct-io.c:281-> #1 (&ocfs2_sysfile_lock_key[EXTENT_ALLOC_SYSTEM_INODE]){+.+.}-{4:4}:
inode_lock include/linux/fs.h:1029 [inline]
ocfs2_reserve_suballoc_bits+0x16d/0x4840 fs/ocfs2/suballoc.c:882
ocfs2_reserve_new_metadata_blocks+0x415/0x9a0
fs/ocfs2/suballoc.c:1078
ocfs2_mknod+0x10f3/0x2260 fs/ocfs2/namei.c:351-> #0 (&ocfs2_sysfile_lock_key[INODE_ALLOC_SYSTEM_INODE]){+.+.}-{4:4}:
__lock_acquire+0x15a5/0x2cf0 kernel/locking/lockdep.c:5237
lock_acquire+0x106/0x350 kernel/locking/lockdep.c:5868
down_write+0x96/0x200 kernel/locking/rwsem.c:1625
inode_lock include/linux/fs.h:1029 [inline]
ocfs2_remove_inode fs/ocfs2/inode.c:733 [inline]
ocfs2_wipe_inode fs/ocfs2/inode.c:896 [inline]
ocfs2_delete_inode fs/ocfs2/inode.c:1157 [inline]
ocfs2_evict_inode+0x1539/0x43b0 fs/ocfs2/inode.c:1299
Chain exists of:
&ocfs2_sysfile_lock_key[INODE_ALLOC_SYSTEM_INODE] -->
&ocfs2_sysfile_lock_key[EXTENT_ALLOC_SYSTEM_INODE] -->
&ocfs2_sysfile_lock_key[ORPHAN_DIR_SYSTEM_INODE]
Possible unsafe locking scenario: CPU0 CPU1
---- ----
lock(&ocfs2_sysfile_lock_key[ORPHAN_DIR_SYSTEM_INODE]);
lock(&ocfs2_sysfile_lock_key[EXTENT_ALLOC_SYSTEM_INODE]);
lock(&ocfs2_sysfile_lock_key[ORPHAN_DIR_SYSTEM_INODE]); lock(&ocfs2_sysfile_lock_key[INODE_ALLOC_SYSTEM_INODE]);
*** DEADLOCK ***
--- fs/ocfs2/aops.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-)
fs/ocfs2/aops.c +9 -4
@@ -2373,6 +2373,15 @@ static int ocfs2_dio_end_io_write(struct inode *inode, unlock:up_write (&oi->ip_alloc_sem); +if (data_ac) { +ocfs2_free_alloc_context (data_ac); + data_ac =NULL ; + } +if (meta_ac) { +ocfs2_free_alloc_context (meta_ac); + meta_ac =NULL ; + } +/* everything looks good, let's start the cleanup */ if (!ret && dwc->dw_orphaned) {BUG_ON (dwc->dw_writer_pid !=task_pid_nr (current));
@@ -2384,10 +2393,6 @@ static int ocfs2_dio_end_io_write(struct inode *inode,ocfs2_inode_unlock (inode,1 );brelse (di_bh); out: -if (data_ac) -ocfs2_free_alloc_context (data_ac); -if (meta_ac) -ocfs2_free_alloc_context (meta_ac);ocfs2_run_deallocs (osb, &dealloc);ocfs2_dio_free_write_ctx (inode, dwc);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 565/1611 9p: avoid returning ERR_PTR(0) from mkdir operations
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hongling Zeng <[email protected]>
[ Upstream commit 314b58c01a9047567fd19446ca5fd46c473b89ff ]
When mkdir succeeds, v9fs_vfs_mkdir_dotl() and v9fs_vfs_mkdir() return ERR_PTR(0) which is incorrect. They should return NULL instead for success and ERR_PTR() only with negative error codes for failure.
Return NULL instead of passing to ERR_PTR while err is zero
Fixes smatch warnings:
fs/9p/vfs_inode_dotl.c:420 v9fs_vfs_mkdir_dotl() warn: passing zero to 'ERR_PTR' fs/9p/vfs_inode.c:695 v9fs_vfs_mkdir() warn: passing zero to 'ERR_PTR'
The v9fs_vfs_mkdir() code was further simplified because v9fs_create() can never return NULL, so we do not need to check for fid being set separately, and the error path can be a simple return immediately after v9fs_create() failure.
There is no intended functional change.
Message-ID: <[email protected]>
--- fs/9p/vfs_inode.c | 19 ++++++------------- fs/9p/vfs_inode_dotl.c | 4 ++-- 2 files changed, 8 insertions(+), 15 deletions(-)
fs/9p/vfs_inode.c +6 -13
@@ -672,27 +672,20 @@ v9fs_vfs_create(struct mnt_idmap *idmap, struct inode *dir,static struct dentry *v9fs_vfs_mkdir (struct mnt_idmap *idmap,struct inode *dir,struct dentry *dentry,umode_t mode) { -int err;u32 perm;struct p9_fid *fid;struct v9fs_session_info *v9ses;p9_debug (P9_DEBUG_VFS ,"name %pd\n" , dentry); - err =0 ; v9ses =v9fs_inode2v9ses (dir); perm =unixmode2p9mode (v9ses, mode |S_IFDIR ); fid =v9fs_create (v9ses, dir, dentry,NULL , perm,P9_OREAD ); -if (IS_ERR (fid)) { - err =PTR_ERR (fid); - fid =NULL ; - }else { -inc_nlink (dir); -v9fs_invalidate_inode_attr (dir); - } - -if (fid) -p9_fid_put (fid); -return ERR_PTR (err); +if (IS_ERR (fid)) +return ERR_CAST (fid); +inc_nlink (dir); +v9fs_invalidate_inode_attr (dir); +p9_fid_put (fid); +return NULL ; }/**
fs/9p/vfs_inode_dotl.c +2 -2
@@ -349,7 +349,7 @@ static struct dentry *v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t omode) { - int err; + int err = 0;struct v9fs_session_info *v9ses;struct p9_fid *fid =NULL , *dfid =NULL ;kgid_t gid;
@@ -412,7 +412,7 @@ static struct dentry *v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap,p9_fid_put (fid);v9fs_put_acl (dacl, pacl);p9_fid_put (dfid); -return ERR_PTR (err); +return err ?ERR_PTR (err) :NULL ; } static int
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 566/1611 net/9p: fix race condition on rdma->state in trans_rdma.c
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yizhou Zhao <[email protected]>
[ Upstream commit 7d54894a1ee265a72d70f7cae1da6cc774cccc71 ]
The rdma->state field is modified without holding req_lock in both recv_done() and p9_cm_event_handler(), while rdma_request() accesses the same field under the req_lock spinlock. This inconsistent locking creates a race condition:
- recv_done() running in softirq completion context sets rdma->state = P9_RDMA_FLUSHING without acquiring req_lock
- p9_cm_event_handler() modifies rdma->state at multiple points (ADDR_RESOLVED, ROUTE_RESOLVED, ESTABLISHED, CLOSED) without req_lock
- rdma_request() uses spin_lock_irqsave(&rdma->req_lock, flags) to protect the read-modify-write of rdma->state
The race can cause lost state transitions: recv_done() or the CM event handler could set state to FLUSHING/CLOSED while rdma_request() is concurrently checking or modifying state under the lock, leading to the FLUSHING transition being silently overwritten by CLOSING. This corrupts the connection state machine and can cause use-after-free on RDMA request objects during teardown.
Fix by adding req_lock protection to all rdma->state modifications in recv_done() and p9_cm_event_handler(), matching the pattern already used in rdma_request(). Use spin_lock_irqsave/spin_unlock_irqrestore in the CM event handler since it can race with recv_done() which runs in softirq context.
Tested with a kernel module that races two threads (simulating rdma_request and recv_done/CM handler) on rdma->state with proper
locking: 5.5M+ FLUSHING writes over 27M iterations with 0 lost transitions.
Message-ID: <[email protected]>
--- net/9p/trans_rdma.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-)
net/9p/trans_rdma.c +17 -2
@@ -240,25 +240,36 @@ p9_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) {struct p9_client *c = id->context;struct p9_trans_rdma *rdma = c->trans; +unsigned long flags; +switch (event->event) {case RDMA_CM_EVENT_ADDR_RESOLVED : +spin_lock_irqsave (&rdma->req_lock, flags);BUG_ON (rdma->state !=P9_RDMA_INIT ); rdma->state =P9_RDMA_ADDR_RESOLVED ; +spin_unlock_irqrestore (&rdma->req_lock, flags);break ;case RDMA_CM_EVENT_ROUTE_RESOLVED : +spin_lock_irqsave (&rdma->req_lock, flags);BUG_ON (rdma->state !=P9_RDMA_ADDR_RESOLVED ); rdma->state =P9_RDMA_ROUTE_RESOLVED ; +spin_unlock_irqrestore (&rdma->req_lock, flags);break ;case RDMA_CM_EVENT_ESTABLISHED : +spin_lock_irqsave (&rdma->req_lock, flags);BUG_ON (rdma->state !=P9_RDMA_ROUTE_RESOLVED ); rdma->state =P9_RDMA_CONNECTED ; +spin_unlock_irqrestore (&rdma->req_lock, flags);break ;case RDMA_CM_EVENT_DISCONNECTED : -if (rdma) +if (rdma) { +spin_lock_irqsave (&rdma->req_lock, flags); rdma->state =P9_RDMA_CLOSED ; +spin_unlock_irqrestore (&rdma->req_lock, flags); + } c->status = Disconnected;break ;
@@ -296,6 +307,7 @@ recv_done(struct ib_cq *cq, struct ib_wc *wc)struct p9_req_t *req;int err =0 ;int16_t tag; +unsigned long flags; req =NULL ; ib_dma_unmap_single(rdma->cm_id->device, c->busa, client->msize,
@@ -332,7 +344,10 @@ recv_done(struct ib_cq *cq, struct ib_wc *wc) err_out:p9_debug (P9_DEBUG_ERROR ,"req %p err %d status %d\n" , req, err, wc->status); - rdma->state =P9_RDMA_FLUSHING ; +spin_lock_irqsave (&rdma->req_lock, flags); +if (rdma->state <P9_RDMA_FLUSHING ) + rdma->state =P9_RDMA_FLUSHING ; +spin_unlock_irqrestore (&rdma->req_lock, flags); client->status = Disconnected; goto out; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 567/1611 eventpoll: rename ep_remove_safe() back to ep_remove()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Christian Brauner <[email protected]>
[ Upstream commit 0bade234723e40e4937be912e105785d6a51464e ]
The current name is just confusing and doesn't clarify anything.
Stable-dep-of: 0c4aefe3c2d0 ("eventpoll: Fix epoll_wait() report false negative")
--- fs/eventpoll.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)
fs/eventpoll.c +8 -8
@@ -910,7 +910,7 @@ static bool ep_remove_epi(struct eventpoll *ep, struct epitem *epi)/* * ep_remove variant for callers owing an additional reference to the ep */ -static void ep_remove_safe (struct eventpoll *ep,struct epitem *epi) +static void ep_remove (struct eventpoll *ep,struct epitem *epi) { struct file *file __free(fput) = NULL;
@@ -961,7 +961,7 @@ static void ep_clear_and_put(struct eventpoll *ep)/* * Walks through the whole tree and try to free each "struct epitem". -* Note that ep_remove_safe() will not remove the epitem in case of a +* Note that ep_remove() will not remove the epitem in case of a * racing eventpoll_release_file(); the latter will do the removal. * At this point we are sure no poll callbacks will be lingering around. * Since we still own a reference to the eventpoll struct, the loop can't
@@ -970,7 +970,7 @@ static void ep_clear_and_put(struct eventpoll *ep)for (rbp =rb_first_cached (&ep->rbr); rbp; rbp = next) { next =rb_next (rbp); epi = rb_entry(rbp, struct epitem, rbn); -ep_remove_safe (ep, epi); +ep_remove (ep, epi);cond_resched (); }
@@ -1635,21 +1635,21 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,mutex_unlock (&tep->mtx);/* -* ep_remove_safe() calls in the later error paths can't lead to +* ep_remove() calls in the later error paths can't lead to * ep_free() as the ep file itself still holds an ep reference. */ ep_get (ep);/* now check if we've created too many backpaths */ if (unlikely (full_check &&reverse_path_check ())) { -ep_remove_safe (ep, epi); +ep_remove (ep, epi);return -EINVAL ; }if (epi->event.events &EPOLLWAKEUP ) { error =ep_create_wakeup_source (epi);if (error) { -ep_remove_safe (ep, epi); +ep_remove (ep, epi);return error; } }
@@ -1673,7 +1673,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,* high memory pressure. */ if (unlikely (!epq.epi)) { -ep_remove_safe (ep, epi); +ep_remove (ep, epi);return -ENOMEM ; }
@@ -2380,7 +2380,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,* The eventpoll itself is still alive: the refcount * can't go to zero here. */ -ep_remove_safe (ep, epi); +ep_remove (ep, epi); error =0 ; }else { error = -ENOENT ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 568/1611 eventpoll: expand top-of-file overview / locking doc
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Christian Brauner <[email protected]>
[ Upstream commit 7c25a0bd4bf7139944c5893ff61211f4b5a3455e ]
The existing ~40-line "LOCKING:" banner covered the three-level lock hierarchy (epnested_mutex > ep->mtx > ep->lock) but nothing else. Lifetime rules, the ready-list state machine, the three removal paths, and the POLLFREE contract are implicit in the code. The recent UAF series (a6dc643c6931, 07712db80857, 8c2e52ebbe88, f2e467a48287) rode on invariants that were only implicit.
Codify them at the top of the file: the subsystem overview, the lock hierarchy and its mutex_lock_nested() subclass convention (reworded from the old banner), a field-protection table for struct eventpoll and struct epitem that names the two faces of the rbn/rcu union (rbn under ep->mtx while linked into ep->rbr; rcu touched only by kfree_rcu(epi) on the free path), the ovflist sentinel encoding and scan-flip invariants, the three removal paths (A ep_remove, B ep_clear_and_put, C eventpoll_release_file) and the epi_fget() pin that orchestrates A vs C, and the POLLFREE store-release / load-acquire handshake.
No functional change.
Stable-dep-of: 0c4aefe3c2d0 ("eventpoll: Fix epoll_wait() report false negative")
--- fs/eventpoll.c | 199 ++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 162 insertions(+), 37 deletions(-)
fs/eventpoll.c +162 -37
@@ -41,45 +41,170 @@#include <net/busy_poll.h> /* -* LOCKING: -* There are three level of locking required by epoll : +* fs/eventpoll.c - Efficient event polling ("epoll") kernel implementation. * -* 1) epnested_mutex (mutex) -* 2) ep->mtx (mutex) -* 3) ep->lock (spinlock) * -* The acquire order is the one listed above, from 1 to 3. -* We need a spinlock (ep->lock) because we manipulate objects -* from inside the poll callback, that might be triggered from -* a wake_up() that in turn might be called from IRQ context. -* So we can't sleep inside the poll callback and hence we need -* a spinlock. During the event transfer loop (from kernel to -* user space) we could end up sleeping due a copy_to_user(), so -* we need a lock that will allow us to sleep. This lock is a -* mutex (ep->mtx). It is acquired during the event transfer loop, -* during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file(). -* The epnested_mutex is acquired when inserting an epoll fd onto another -* epoll fd. We do this so that we walk the epoll tree and ensure that this -* insertion does not create a cycle of epoll file descriptors, which -* could lead to deadlock. We need a global mutex to prevent two -* simultaneous inserts (A into B and B into A) from racing and -* constructing a cycle without either insert observing that it is -* going to. -* It is necessary to acquire multiple "ep->mtx"es at once in the -* case when one epoll fd is added to another. In this case, we -* always acquire the locks in the order of nesting (i.e. after -* epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired -* before e2->mtx). Since we disallow cycles of epoll file -* descriptors, this ensures that the mutexes are well-ordered. In -* order to communicate this nesting to lockdep, when walking a tree -* of epoll file descriptors, we use the current recursion depth as -* the lockdep subkey. -* It is possible to drop the "ep->mtx" and to use the global -* mutex "epnested_mutex" (together with "ep->lock") to have it working, -* but having "ep->mtx" will make the interface more scalable. -* Events that require holding "epnested_mutex" are very rare, while for -* normal operations the epoll private "ep->mtx" will guarantee -* a better scalability. +* Overview +* -------- +* +* Each epoll_create(2) returns an anonymous [eventpoll] file whose +* ->private_data is a struct eventpoll. Each EPOLL_CTL_ADD installs +* a struct epitem linking one (watched file, fd) pair back to that +* eventpoll via the watched file's f_op->poll() wait queue(s). When +* the watched file signals readiness, ep_poll_callback() fires and +* marks the epitem ready. epoll_wait(2) drains the ready list under +* ep->mtx, re-queueing items in level-triggered mode. +* +* epoll instances can watch other epoll instances up to EP_MAX_NESTS +* deep; cycles are forbidden and detected at EPOLL_CTL_ADD time. +* +* +* Locking +* ------- +* +* Three levels, acquired from outer to inner: +* +* epnested_mutex (global; rare; taken only for EPOLL_CTL_ADD +* loop / path checks) +* > ep->mtx (per-eventpoll; sleepable; serializes most ops) +* > ep->lock (per-eventpoll; IRQ-safe spinlock) +* +* file->f_lock (per-file; NOT IRQ-safe; guards f_ep hlist ops; +* nested inside ep->mtx, outside ep->lock) +* +* Rationale: +* - ep->lock is a spinlock because ep_poll_callback() is called from +* wake_up() which may run in hard-IRQ context. All ep->lock +* critical sections use spin_lock_irqsave(). +* - ep->mtx is a sleepable mutex because the event delivery loop +* calls copy_to_user(), and ep_insert() may sleep in +* kmem_cache_alloc() and f_op->poll(). +* - epnested_mutex is global because cycle detection needs a global +* view of the epoll topology; a per-object scheme would let two +* concurrent inserts (A into B, B into A) construct a cycle +* without either observer seeing it. +* - Per-ep ep->mtx is preferred for scalability elsewhere. Events +* that require epnested_mutex are rare. +* +* When EPOLL_CTL_ADD nests one eventpoll inside another we acquire +* ep->mtx on both: outer first, target second. Since cycles are +* forbidden the set of live ep->mtx holds is always a strict chain, +* communicated to lockdep via mutex_lock_nested() subclasses derived +* from the current recursion depth. +* +* +* Field protection +* ---------------- +* +* struct eventpoll: +* mtx - self +* rbr - ep->mtx +* ovflist, rdllist - ep->lock (IRQ-safe) +* wq - ep->lock for queue mutation +* poll_wait - internal waitqueue spinlock +* refs - file->f_lock for adds; ep->mtx for removes; +* RCU for readers (hlist_del_rcu + kfree_rcu(ep)) +* ws - ep->mtx +* gen, loop_check_depth - epnested_mutex +* file, user - immutable after setup +* refcount - atomic (refcount_t) +* napi_* - READ_ONCE / WRITE_ONCE +* +* struct epitem: +* rbn / rcu union - rbn: ep->mtx (while epi is linked in ep->rbr). +* rcu: written only by kfree_rcu(epi) on the free +* path; otherwise untouched by epoll code. +* rdllink, next - ep->lock +* ffd, ep - immutable after ep_insert() +* pwqlist - ep->mtx for writes; POLLFREE clears pwq->whead +* via smp_store_release(), see below +* fllink - file->f_lock for mutation; hlist_del_rcu + +* kfree_rcu(epi) for safe RCU readers +* ws - RCU (rcu_assign_pointer / +* rcu_dereference_check(mtx)) +* event - ep->mtx for writes; lockless read in +* ep_poll_callback pairs with smp_mb() in +* ep_modify() +* +* +* Ready-list state machine +* ------------------------ +* +* Readiness is tracked in two lists under ep->lock: +* +* rdllist - doubly-linked FIFO; the "current" ready list. +* ovflist - singly-linked LIFO; used during a scan to catch +* events that arrive while rdllist is being iterated +* without ep->lock. +* +* Encoded in ep->ovflist: +* EP_UNACTIVE_PTR - no scan active; callback appends to rdllist. +* NULL - scan active, no spill yet. +* pointer to epi - scan active with spilled items (LIFO). +* +* Encoded in epi->next: +* EP_UNACTIVE_PTR - epi is not on ovflist. +* otherwise - next epi on ovflist (NULL at tail). +* +* ep_start_scan() flips "not scanning" to "scanning" and splices +* rdllist into a caller-local txlist. ep_done_scan() drains ovflist +* back to rdllist (list_add head-insert reverses LIFO to FIFO), +* flips back to "not scanning", and re-splices any items the caller +* left in txlist (e.g., level-triggered re-queues). +* +* +* Removal paths +* ------------- +* +* Three paths dispose of epitems and/or eventpolls: +* +* A. ep_remove() - EPOLL_CTL_DEL and ep_insert() +* rollback. Caller holds ep->mtx. +* B. ep_clear_and_put() - close of the epoll fd itself +* (ep_eventpoll_release). +* C. eventpoll_release_file() - close of a watched file, invoked +* from __fput(). +* +* Coordination: +* A and C exclude each other via the watched file's refcount. +* A pins the file with epi_fget() before touching file->f_ep or +* file->f_lock; if the pin fails, __fput() is in flight and C +* will clean this epi up. See the epi_fget() block comment. +* A and B both hold ep->mtx serially. B walks the rbtree with +* rb_next() captured before ep_remove() erases the current node. +* B and C both take ep->mtx; the loser sees fewer entries or an +* empty file->f_ep. +* +* Within every path the internal order is strict: +* ep_unregister_pollwait() - drain pwqlist; synchronizes with any +* in-flight ep_poll_callback via the +* watched wait-queue head's lock. +* ep_remove_file() - hlist_del_rcu of epi->fllink and, +* if last watcher, clear file->f_ep, +* under file->f_lock. +* ep_remove_epi() - rb_erase, rdllist unlink (ep->lock), +* wakeup_source_unregister, +* kfree_rcu(epi). +* +* kfree_rcu(epi) defers the free past RCU readers in +* reverse_path_check_proc(); kfree_rcu(ep) defers past readers in +* ep_get_upwards_depth_proc(). +* +* +* POLLFREE handshake +* ------------------ +* +* When a subsystem tears down a wait-queue head that an epitem is +* registered on (binder, signalfd, ...), it wakes the callback with +* POLLFREE and must RCU-defer the head's free. The store/load pair: +* +* ep_poll_callback() POLLFREE branch: +* smp_store_release(&pwq->whead, NULL) +* +* ep_remove_wait_queue(): +* smp_load_acquire(&pwq->whead) +* +* See those sites for the full argument. */ /* Epoll private bits inside the event mask */
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 569/1611 eventpoll: rename attach_epitem() to ep_attach_file()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Christian Brauner <[email protected]>
[ Upstream commit 6a3f1a494bc91d7976cf0d2b200bb3f1a22eef64 ]
ep_remove_file() tears down the f_ep linkage that attach_epitem() establishes, so the pair should look like one. Rename to ep_attach_file() for the "ep_*" + subject symmetry and to match the naming used elsewhere in the file (ep_insert, ep_modify, ep_remove, ep_remove_file, ep_remove_epi, ep_unregister_pollwait).
Pure rename; no functional change.
Stable-dep-of: 0c4aefe3c2d0 ("eventpoll: Fix epoll_wait() report false negative")
--- fs/eventpoll.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
fs/eventpoll.c +2 -2
@@ -1669,7 +1669,7 @@ static noinline void ep_destroy_wakeup_source(struct epitem *epi)wakeup_source_unregister (ws); } -static int attach_epitem (struct file *file,struct epitem *epi) +static int ep_attach_file (struct file *file,struct epitem *epi) {struct epitems_head *to_free =NULL ;struct hlist_head *head =NULL ;
@@ -1740,7 +1740,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,if (tep)mutex_lock_nested (&tep->mtx,1 );/* Add the current item to the list of active epoll hook for this file */ -if (unlikely (attach_epitem (tfile, epi) <0 )) { +if (unlikely (ep_attach_file (tfile, epi) <0 )) {if (tep)mutex_unlock (&tep->mtx);kmem_cache_free (epi_cache, epi);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 570/1611 eventpoll: split ep_insert() into alloc + register stages
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Christian Brauner <[email protected]>
[ Upstream commit e0e35f4cb983a55a36e79e9b2a20ca0e0688fae6 ]
ep_insert() was 130 lines and mixed four concerns in one body: user quota charge and epitem allocation, attach-into-file-hlist plus rbtree insert plus target-ep locking, reverse-path + EPOLLWAKEUP + poll-queue install with rollback, and ready-list publication. Factor the first two concerns into named helpers so the body reduces to orchestration.
ep_alloc_epitem() charges the user's epoll_watches quota, allocates a fresh epitem, and initializes its fields. On failure it returns ERR_PTR(-ENOSPC) or ERR_PTR(-ENOMEM); on success the epi is not yet linked into anything.
ep_register_epitem() installs @epi into @tfile's f_ep hlist and @ep's rbtree, optionally chains @tfile onto tfile_check_list for the path check, takes the tep->mtx nested lock for the epoll-watches- epoll case, and finally takes the ep_get() reference that pairs with ep_remove()'s ep_put() in ep_insert()'s error paths. On failure it frees the epi and decrements epoll_watches to match ep_alloc_epitem().
ep_insert()'s remaining body is the rollback-via-ep_remove() chain (reverse_path_check, EPOLLWAKEUP source creation, ep_ptable_queue_proc allocation) and the ready-list / wake publication. Remove a few stale comments that duplicated function-level documentation or described obvious code.
No functional change; rollback boundaries unchanged -- every error path after ep_register_epitem() still calls ep_remove(), preserving the ep->refcount invariant that keeps ep_remove()'s WARN_ON_ONCE safe.
Stable-dep-of: 0c4aefe3c2d0 ("eventpoll: Fix epoll_wait() report false negative")
--- fs/eventpoll.c | 111 ++++++++++++++++++++++++++++++++----------------- 1 file changed, 74 insertions(+), 37 deletions(-)
fs/eventpoll.c +74 -37
@@ -1704,68 +1704,112 @@ static int ep_attach_file(struct file *file, struct epitem *epi) }/* -* Must be called with "mtx" held. +* Charge the user's epoll_watches quota, allocate a fresh epitem for +* @tfile/@fd, and initialize its fields. The returned item is not yet +* linked into any data structure; the caller must install it via +* ep_register_epitem() (which takes over on success) or kmem_cache_free() +* it and decrement epoll_watches on its own. +* +* Returns ERR_PTR(-ENOSPC) if the quota is exceeded, ERR_PTR(-ENOMEM) +* if the slab allocation fails. */ -static int ep_insert (struct eventpoll *ep,const struct epoll_event *event, -struct file *tfile,int fd,int full_check) +static struct epitem *ep_alloc_epitem (struct eventpoll *ep, +const struct epoll_event *event, +struct file *tfile,int fd) { -int error, pwake =0 ; -__poll_t revents;struct epitem *epi; -struct ep_pqueue epq; -struct eventpoll *tep =NULL ; - -if (is_file_epoll (tfile)) - tep = tfile->private_data; - -lockdep_assert_irqs_enabled ();if (unlikely (percpu_counter_compare (&ep->user->epoll_watches, max_user_watches) >=0 )) -return -ENOSPC ; +return ERR_PTR (-ENOSPC );percpu_counter_inc (&ep->user->epoll_watches); -if (!(epi =kmem_cache_zalloc (epi_cache,GFP_KERNEL ))) { + epi =kmem_cache_zalloc (epi_cache,GFP_KERNEL ); +if (unlikely (!epi)) {percpu_counter_dec (&ep->user->epoll_watches); -return -ENOMEM ; +return ERR_PTR (-ENOMEM ); } -/* Item initialization follow here ... */ INIT_LIST_HEAD (&epi->rdllink); epi->ep = ep;ep_set_ffd (&epi->ffd, tfile, fd); epi->event = *event; epi->next =EP_UNACTIVE_PTR ; +return epi; +} + +/* +* Install @epi into its target file's f_ep hlist and into @ep's rbtree, +* taking one additional reference on @ep for the lifetime of the item. +* +* If @tep is non-NULL, the target file is itself an eventpoll; we hold +* tep->mtx at subclass 1 across the attach + rbtree insert to serialize +* with the target side. RB tree ops are protected by @ep->mtx, which +* the caller already holds. +* +* On failure the epi is freed and the epoll_watches counter decremented, +* matching ep_alloc_epitem()'s allocation. After this returns +* successfully, ep_insert()'s later error paths use ep_remove() for +* unwind; that cannot drop @ep's refcount to zero because the ep file +* itself still holds the original reference. +*/ +static int ep_register_epitem (struct eventpoll *ep,struct epitem *epi, +struct eventpoll *tep,int full_check) +{ +struct file *tfile = epi->ffd.file; +int error; +if (tep)mutex_lock_nested (&tep->mtx,1 ); -/* Add the current item to the list of active epoll hook for this file */ -if (unlikely (ep_attach_file (tfile, epi) <0 )) { + + error =ep_attach_file (tfile, epi); +if (unlikely (error)) {if (tep)mutex_unlock (&tep->mtx);kmem_cache_free (epi_cache, epi);percpu_counter_dec (&ep->user->epoll_watches); -return -ENOMEM ; +return error; }if (full_check && !tep)list_file (tfile); -/* -* Add the current item to the RB tree. All RB tree operations are -* protected by "mtx", and ep_insert() is called with "mtx" held. -*/ ep_rbtree_insert (ep, epi); +if (tep)mutex_unlock (&tep->mtx); -/* -* ep_remove() calls in the later error paths can't lead to -* ep_free() as the ep file itself still holds an ep reference. -*/ ep_get (ep); +return 0 ; +} + +/* +* Must be called with "mtx" held. +*/ +static int ep_insert (struct eventpoll *ep,const struct epoll_event *event, +struct file *tfile,int fd,int full_check) +{ +int error, pwake =0 ; +__poll_t revents; +struct epitem *epi; +struct ep_pqueue epq; +struct eventpoll *tep =NULL ; + +if (is_file_epoll (tfile)) + tep = tfile->private_data; + +lockdep_assert_irqs_enabled (); + + epi =ep_alloc_epitem (ep, event, tfile, fd); +if (IS_ERR (epi)) +return PTR_ERR (epi); -/* now check if we've created too many backpaths */ + error =ep_register_epitem (ep, epi, tep, full_check); +if (error) +return error; + +/* Reject the insert if the new link would create too many back-paths. */ if (unlikely (full_check &&reverse_path_check ())) {ep_remove (ep, epi);return -EINVAL ;
@@ -1792,28 +1836,21 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,*/ revents =ep_item_poll (epi, &epq.pt,1 ); -/* -* We have to check if something went wrong during the poll wait queue -* install process. Namely an allocation for a wait queue failed due -* high memory pressure. -*/ +/* ep_ptable_queue_proc() signals allocation failure by clearing epq.epi. */ if (unlikely (!epq.epi)) {ep_remove (ep, epi);return -ENOMEM ; } -/* We have to drop the new item inside our item list to keep track of it */ +/* Drop the new item onto the ready list if it is already ready. */ spin_lock_irq (&ep->lock); -/* record NAPI ID of new item if present */ ep_set_busy_poll_napi_id (epi); -/* If the file is already "ready" we drop it inside the ready list */ if (revents && !ep_is_linked (epi)) {list_add_tail (&epi->rdllink, &ep->rdllist);ep_pm_stay_awake (epi); -/* Notify waiting tasks that events are available */ if (waitqueue_active (&ep->wq))wake_up (&ep->wq);if (waitqueue_active (&ep->poll_wait))
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 571/1611 eventpoll: extract ep_deliver_event() from ep_send_events()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Christian Brauner <[email protected]>
[ Upstream commit 499a5e7f4a57fa08a297c627d007a55069acac9a ]
ep_send_events()'s body covered two concerns: per-item work (PM wakeup-source bookkeeping, re-poll, copy_to_user, level-trigger re-queue, EPOLLONESHOT mask clear) and the scan-level accumulator (maxevents cap, EFAULT preservation, txlist/rdllist splice).
Extract the per-item work as ep_deliver_event(), which returns a tri-state int:
1 one event was delivered; caller advances the counter,
0 re-poll produced no caller-requested events (item drops
out of the ready list; a future callback will re-queue),
-EFAULT copy_to_user() faulted; item is already re-inserted at
the head of the txlist so ep_done_scan() splices it back to rdllist.
The per-item comments (PM ordering, the "sole writer to rdllist" invariant for the LT re-queue, the EFAULT semantics) move into ep_deliver_event(). ep_send_events() reduces to the fatal-signal short-circuit, scan bracket, and a short txlist walk that accumulates the deliveries and preserves the "first error wins" EFAULT contract (res = delivered only if no event was previously delivered; otherwise the success count is returned and -EFAULT is reported on the next call).
No functional change.
Stable-dep-of: 0c4aefe3c2d0 ("eventpoll: Fix epoll_wait() report false negative")
--- fs/eventpoll.c | 138 ++++++++++++++++++++++++++++++------------------- 1 file changed, 84 insertions(+), 54 deletions(-)
fs/eventpoll.c +84 -54
@@ -1942,6 +1942,82 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi,return 0 ; } +/* +* Attempt to deliver one event for @epi into @*uevents. +* +* Returns 1 if an event was delivered (with *uevents advanced to the +* next slot), 0 if the re-poll reported no caller-requested events +* (@epi drops out of the ready list; a future callback will re-add +* it), or -EFAULT if copy_to_user() faulted (in which case @epi is +* re-inserted at the head of @txlist so ep_done_scan() merges it +* back to rdllist for the next attempt). +* +* PM bookkeeping and level-triggered re-queue are handled here. +* Caller holds ep->mtx and the scan is active. +*/ +static int ep_deliver_event (struct eventpoll *ep,struct epitem *epi, +poll_table *pt, +struct epoll_event __user **uevents, +struct list_head *txlist) +{ +struct epoll_event __user *next; +struct wakeup_source *ws; +__poll_t revents; + +/* +* Activate ep->ws before deactivating epi->ws to prevent +* triggering auto-suspend here (in case we reactivate epi->ws +* below). Rearranging to delay the deactivation would let +* epi->ws drift out of sync with ep_is_linked(). +*/ + ws =ep_wakeup_source (epi); +if (ws) { +if (ws->active) +__pm_stay_awake (ep->ws); +__pm_relax (ws); + } + +list_del_init (&epi->rdllink); + +/* +* Re-poll under ep->mtx so userspace cannot change the item +* out from under us. If no caller-requested events remain, +* @epi stays off the ready list; the poll callback will +* re-queue it when events next appear. +*/ + revents =ep_item_poll (epi, pt,1 ); +if (!revents) +return 0 ; + + next =epoll_put_uevent (revents, epi->event.data, *uevents); +if (!next) { +/* +* copy_to_user() faulted: put the item back so +* ep_done_scan() splices it onto rdllist for the next +* attempt. +*/ +list_add (&epi->rdllink, txlist); +ep_pm_stay_awake (epi); +return -EFAULT ; + } + *uevents = next; + +if (epi->event.events &EPOLLONESHOT ) { + epi->event.events &=EP_PRIVATE_BITS ; + }else if (!(epi->event.events &EPOLLET )) { +/* +* Level-triggered: re-queue so the next epoll_wait() +* rechecks availability. We are the sole writer to +* rdllist here -- epoll_ctl() callers are locked out +* by ep->mtx, and the poll callback queues to ovflist +* during scans. +*/ +list_add_tail (&epi->rdllink, &ep->rdllist); +ep_pm_stay_awake (epi); + } +return 1 ; +} +static int ep_send_events (struct eventpoll *ep,struct epoll_event __user *events,int maxevents) {
@@ -1964,70 +2040,24 @@ static int ep_send_events(struct eventpoll *ep,ep_start_scan (ep, &txlist);/* -* We can loop without lock because we are passed a task private list. -* Items cannot vanish during the loop we are holding ep->mtx. +* We can loop without lock because we are passed a task-private +* txlist; items cannot vanish while we hold ep->mtx. */ list_for_each_entry_safe (epi, tmp, &txlist, rdllink) { -struct wakeup_source *ws; -__poll_t revents; +int delivered;if (res >= maxevents)break ; -/* -* Activate ep->ws before deactivating epi->ws to prevent -* triggering auto-suspend here (in case we reactive epi->ws -* below). -* -* This could be rearranged to delay the deactivation of epi->ws -* instead, but then epi->ws would temporarily be out of sync -* with ep_is_linked(). -*/ - ws =ep_wakeup_source (epi); -if (ws) { -if (ws->active) -__pm_stay_awake (ep->ws); -__pm_relax (ws); - } - -list_del_init (&epi->rdllink); - -/* -* If the event mask intersect the caller-requested one, -* deliver the event to userspace. Again, we are holding ep->mtx, -* so no operations coming from userspace can change the item. -*/ - revents =ep_item_poll (epi, &pt,1 ); -if (!revents) -continue ; - - events =epoll_put_uevent (revents, epi->event.data, events); -if (!events) { -list_add (&epi->rdllink, &txlist); -ep_pm_stay_awake (epi); + delivered =ep_deliver_event (ep, epi, &pt, &events, &txlist); +if (delivered <0 ) {if (!res) - res = -EFAULT ; + res = delivered;break ; } - res++; -if (epi->event.events &EPOLLONESHOT ) - epi->event.events &=EP_PRIVATE_BITS ; -else if (!(epi->event.events &EPOLLET )) { -/* -* If this file has been added with Level -* Trigger mode, we need to insert back inside -* the ready list, so that the next call to -* epoll_wait() will check again the events -* availability. At this point, no one can insert -* into ep->rdllist besides us. The epoll_ctl() -* callers are locked out by -* ep_send_events() holding "mtx" and the -* poll callback will queue them in ep->ovflist. -*/ -list_add_tail (&epi->rdllink, &ep->rdllist); -ep_pm_stay_awake (epi); - } + res += delivered; } +ep_done_scan (ep, &txlist);mutex_unlock (&ep->mtx);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 572/1611 eventpoll: wrap EP_UNACTIVE_PTR in typed sentinel helpers
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Christian Brauner <[email protected]>
[ Upstream commit 0dcb726466a556f273beaadfb76f12d1b0087dd7 ]
ep->ovflist and epi->next both use EP_UNACTIVE_PTR (a cast to (void *)-1) as a sentinel, with distinct meanings at each site:
ep->ovflist == EP_UNACTIVE_PTR no scan in progress
epi->next == EP_UNACTIVE_PTR epi not on ovflist
Call sites had to know the sentinel's value and, by convention, what it meant in each context. Hide both behind inline helpers:
ep_is_scanning(ep) predicate for "scan in progress" ep_enter_scan(ep) WRITE_ONCE flip to NULL (scan start) ep_exit_scan(ep) WRITE_ONCE flip to sentinel (scan end) epi_on_ovflist(epi) predicate for "epi is on ovflist" epi_clear_ovflist(epi) clear epi's ovflist link slot
Convert ep_events_available(), ep_start_scan(), ep_done_scan(), ep_poll_callback(), and ep_alloc_epitem() to use the wrappers. The ovflist state-machine transitions are now named, not encoded in sentinel comparisons, and the top-of-file "Ready-list state machine" section is the single place that spells out the sentinel's meaning.
ep_alloc() keeps the raw "ep->ovflist = EP_UNACTIVE_PTR" init (no concurrent access at that point) with an inline "not scanning" comment, and the tfile_check_list sentinel is left alone -- it will disappear entirely when the loop-check globals move into a stack-allocated ep_ctl_ctx in a later commit.
Also rework ep_done_scan()'s for-loop: the combined initializer + update clause that advanced nepi AND cleared epi->next in one step was clever but hard to read; splitting the update into two statements inside the body makes the epi_clear_ovflist() call visible.
No functional change.
Stable-dep-of: 0c4aefe3c2d0 ("eventpoll: Fix epoll_wait() report false negative")
--- fs/eventpoll.c | 73 +++++++++++++++++++++++++++++++++++--------------- 1 file changed, 52 insertions(+), 21 deletions(-)
fs/eventpoll.c +52 -21
@@ -507,6 +507,43 @@ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p) return container_of(p, struct eppoll_entry, wait)->base; } +/* +* Ready-list / ovflist state (see "Ready-list state machine" in the +* top-of-file banner for the full state machine). EP_UNACTIVE_PTR is +* the sentinel; these wrappers name each transition and each test so +* call sites do not need to know the sentinel's value. +*/ + +/* True iff @ep is between ep_enter_scan() and ep_exit_scan(). */ +static inline bool ep_is_scanning (struct eventpoll *ep) +{ +return READ_ONCE (ep->ovflist) !=EP_UNACTIVE_PTR ; +} + +/* Called by ep_start_scan(): divert ep_poll_callback() to ovflist. */ +static inline void ep_enter_scan (struct eventpoll *ep) +{ +WRITE_ONCE (ep->ovflist,NULL ); +} + +/* Called by ep_done_scan(): redirect ep_poll_callback() back to rdllist. */ +static inline void ep_exit_scan (struct eventpoll *ep) +{ +WRITE_ONCE (ep->ovflist,EP_UNACTIVE_PTR ); +} + +/* True iff @epi is currently linked on its ep's ovflist. */ +static inline bool epi_on_ovflist (const struct epitem *epi) +{ +return epi->next !=EP_UNACTIVE_PTR ; +} + +/* Mark @epi as not on any ovflist (init and post-drain). */ +static inline void epi_clear_ovflist (struct epitem *epi) +{ + epi->next =EP_UNACTIVE_PTR ; +} +/** * ep_events_available - Checks if ready events might be available. *
@@ -517,8 +554,7 @@ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p)*/ static inline int ep_events_available (struct eventpoll *ep) { -return !list_empty_careful (&ep->rdllist) || -READ_ONCE (ep->ovflist) !=EP_UNACTIVE_PTR ; +return !list_empty_careful (&ep->rdllist) ||ep_is_scanning (ep); }#ifdef CONFIG_NET_RX_BUSY_POLL
@@ -871,7 +907,7 @@ static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist)lockdep_assert_irqs_enabled ();spin_lock_irq (&ep->lock);list_splice_init (&ep->rdllist, txlist); -WRITE_ONCE (ep->ovflist,NULL ); +ep_enter_scan (ep);spin_unlock_irq (&ep->lock); }
@@ -886,29 +922,24 @@ static void ep_done_scan(struct eventpoll *ep,* other events might have been queued by the poll callback. * We re-insert them inside the main ready-list here. */ -for (nepi =READ_ONCE (ep->ovflist); (epi = nepi) !=NULL ; - nepi = epi->next, epi->next =EP_UNACTIVE_PTR ) { +for (nepi =READ_ONCE (ep->ovflist); (epi = nepi) !=NULL ; ) { + nepi = epi->next; +epi_clear_ovflist (epi);/* -* We need to check if the item is already in the list. -* During the "sproc" callback execution time, items are -* queued into ->ovflist but the "txlist" might already -* contain them, and the list_splice() below takes care of them. +* Skip items that the caller already returned via @txlist +* -- the list_splice() below takes care of those. */ if (!ep_is_linked (epi)) {/* -* ->ovflist is LIFO, so we have to reverse it in order -* to keep in FIFO. +* ovflist is LIFO; list_add() head-insert here +* reverses the iteration order into FIFO. */ list_add (&epi->rdllink, &ep->rdllist);ep_pm_stay_awake (epi); } } -/* -* We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after -* releasing the lock, events will be queued in the normal way inside -* ep->rdllist. -*/ -WRITE_ONCE (ep->ovflist,EP_UNACTIVE_PTR ); +/* Back out of scan mode; callbacks target ep->rdllist again. */ +ep_exit_scan (ep);/* * Quickly re-inject items left on "txlist".
@@ -1302,7 +1333,7 @@ static int ep_alloc(struct eventpoll **pep)init_waitqueue_head (&ep->poll_wait);INIT_LIST_HEAD (&ep->rdllist); ep->rbr =RB_ROOT_CACHED ; - ep->ovflist =EP_UNACTIVE_PTR ; + ep->ovflist =EP_UNACTIVE_PTR ;/* not scanning */ ep->user =get_current_user ();refcount_set (&ep->refcount,1 );
@@ -1426,8 +1457,8 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v* semantics). All the events that happen during that period of time are * chained in ep->ovflist and requeued later on. */ -if (READ_ONCE (ep->ovflist) !=EP_UNACTIVE_PTR ) { -if (epi->next ==EP_UNACTIVE_PTR ) { +if (ep_is_scanning (ep)) { +if (!epi_on_ovflist (epi)) { epi->next =READ_ONCE (ep->ovflist);WRITE_ONCE (ep->ovflist, epi);ep_pm_stay_awake_rcu (epi);
@@ -1734,7 +1765,7 @@ static struct epitem *ep_alloc_epitem(struct eventpoll *ep, epi->ep = ep;ep_set_ffd (&epi->ffd, tfile, fd); epi->event = *event; - epi->next =EP_UNACTIVE_PTR ; +epi_clear_ovflist (epi);return epi; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 573/1611 eventpoll: rename epi->next and txlist for clarity
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Christian Brauner <[email protected]>
[ Upstream commit f38567bb63ae029e3b63fcb99b6a2dcc6f421e69 ]
Two list-related names were confusing in isolation:
struct epitem::next
A singly-linked link slot used only when an epi is queued on ep->ovflist during an ep_start_scan/ep_done_scan window. The bare name "next" suggests a generic list link and doesn't say which list it belongs to.
txlist
The caller-local list_head used by ep_send_events() and __ep_eventpoll_poll() to hold the batch of items stolen from ep->rdllist for the current scan. "txlist" ("transmission list") is abbreviated and overloaded: it doesn't distinguish itself from ep->rdllist or ep->ovflist at a glance.
Rename for what each actually is:
struct epitem::next -> struct epitem::ovflist_next
local txlist -> scan_batch
With these in place:
- epi->ovflist_next reads as "this is the ep->ovflist link slot", matching the rdllink pattern above it.
- scan_batch reads as "the batch currently being scanned", clearly distinct from rdllist (canonical ready list) and ovflist (scan-window overflow).
ep->rdllist and ep->ovflist struct field names are preserved -- they are long-standing interface-facing identifiers, and the new inline helpers (ep_is_scanning, epi_on_ovflist, ...) already hide the sentinel semantics at call sites.
No functional change.
Stable-dep-of: 0c4aefe3c2d0 ("eventpoll: Fix epoll_wait() report false negative")
--- fs/eventpoll.c | 62 ++++++++++++++++++++++++++------------------------ 1 file changed, 32 insertions(+), 30 deletions(-)
fs/eventpoll.c +32 -30
@@ -142,15 +142,15 @@* NULL - scan active, no spill yet. * pointer to epi - scan active with spilled items (LIFO). * -* Encoded in epi->next: +* Encoded in epi->ovflist_next: * EP_UNACTIVE_PTR - epi is not on ovflist. * otherwise - next epi on ovflist (NULL at tail). * * ep_start_scan() flips "not scanning" to "scanning" and splices -* rdllist into a caller-local txlist. ep_done_scan() drains ovflist +* rdllist into a caller-local scan_batch. ep_done_scan() drains ovflist * back to rdllist (list_add head-insert reverses LIFO to FIFO), * flips back to "not scanning", and re-splices any items the caller -* left in txlist (e.g., level-triggered re-queues). +* left in scan_batch (e.g., level-triggered re-queues). * * * Removal paths
@@ -261,14 +261,16 @@ struct epitem {struct rcu_head rcu; }; -/* List header used to link this structure to the eventpoll ready list */ +/* Link on the owning eventpoll's ready list (ep->rdllist). */ struct list_head rdllink;/* -* Works together "struct eventpoll"->ovflist in keeping the -* single linked chain of items. +* Link on the owning eventpoll's scan-overflow list (ep->ovflist), +* EP_UNACTIVE_PTR when not linked. See epi_on_ovflist() / +* epi_clear_ovflist() and the "Ready-list state machine" section +* in the top-of-file banner. */ -struct epitem *next; +struct epitem *ovflist_next;/* The file descriptor information this item refers to */ struct epoll_filefd ffd;
@@ -535,13 +537,13 @@ static inline void ep_exit_scan(struct eventpoll *ep)/* True iff @epi is currently linked on its ep's ovflist. */ static inline bool epi_on_ovflist (const struct epitem *epi) { -return epi->next !=EP_UNACTIVE_PTR ; +return epi->ovflist_next !=EP_UNACTIVE_PTR ; }/* Mark @epi as not on any ovflist (init and post-drain). */ static inline void epi_clear_ovflist (struct epitem *epi) { - epi->next =EP_UNACTIVE_PTR ; + epi->ovflist_next =EP_UNACTIVE_PTR ; }/**
@@ -894,7 +896,7 @@ static inline void ep_pm_stay_awake_rcu(struct epitem *epi)* ep->mutex needs to be held because we could be hit by * eventpoll_release_file() and epoll_ctl(). */ -static void ep_start_scan (struct eventpoll *ep,struct list_head *txlist) +static void ep_start_scan (struct eventpoll *ep,struct list_head *scan_batch) {/* * Steal the ready list, and re-init the original one to the
@@ -906,13 +908,13 @@ static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist)*/ lockdep_assert_irqs_enabled ();spin_lock_irq (&ep->lock); -list_splice_init (&ep->rdllist, txlist); +list_splice_init (&ep->rdllist, scan_batch);ep_enter_scan (ep);spin_unlock_irq (&ep->lock); }static void ep_done_scan (struct eventpoll *ep, -struct list_head *txlist) +struct list_head *scan_batch) {struct epitem *epi, *nepi;
@@ -923,10 +925,10 @@ static void ep_done_scan(struct eventpoll *ep,* We re-insert them inside the main ready-list here. */ for (nepi =READ_ONCE (ep->ovflist); (epi = nepi) !=NULL ; ) { - nepi = epi->next; + nepi = epi->ovflist_next;epi_clear_ovflist (epi);/* -* Skip items that the caller already returned via @txlist +* Skip items that the caller already returned via @scan_batch * -- the list_splice() below takes care of those. */ if (!ep_is_linked (epi)) {
@@ -942,9 +944,9 @@ static void ep_done_scan(struct eventpoll *ep,ep_exit_scan (ep);/* -* Quickly re-inject items left on "txlist". +* Quickly re-inject items left on "scan_batch". */ -list_splice (txlist, &ep->rdllist); +list_splice (scan_batch, &ep->rdllist);__pm_relax (ep->ws);if (!list_empty (&ep->rdllist)) {
@@ -1171,7 +1173,7 @@ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depthstatic __poll_t __ep_eventpoll_poll (struct file *file,poll_table *wait,int depth) {struct eventpoll *ep = file->private_data; -LIST_HEAD (txlist); +LIST_HEAD (scan_batch);struct epitem *epi, *tmp;poll_table pt;__poll_t res =0 ;
@@ -1186,8 +1188,8 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep* the ready list. */ mutex_lock_nested (&ep->mtx, depth); -ep_start_scan (ep, &txlist); -list_for_each_entry_safe (epi, tmp, &txlist, rdllink) { +ep_start_scan (ep, &scan_batch); +list_for_each_entry_safe (epi, tmp, &scan_batch, rdllink) {if (ep_item_poll (epi, &pt, depth +1 )) { res =EPOLLIN |EPOLLRDNORM ;break ;
@@ -1201,7 +1203,7 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int deplist_del_init (&epi->rdllink); } } -ep_done_scan (ep, &txlist); +ep_done_scan (ep, &scan_batch);mutex_unlock (&ep->mtx);return res; }
@@ -1459,7 +1461,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v*/ if (ep_is_scanning (ep)) {if (!epi_on_ovflist (epi)) { - epi->next =READ_ONCE (ep->ovflist); + epi->ovflist_next =READ_ONCE (ep->ovflist);WRITE_ONCE (ep->ovflist, epi);ep_pm_stay_awake_rcu (epi); }
@@ -1980,7 +1982,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi,* next slot), 0 if the re-poll reported no caller-requested events * (@epi drops out of the ready list; a future callback will re-add * it), or -EFAULT if copy_to_user() faulted (in which case @epi is -* re-inserted at the head of @txlist so ep_done_scan() merges it +* re-inserted at the head of @scan_batch so ep_done_scan() merges it * back to rdllist for the next attempt). * * PM bookkeeping and level-triggered re-queue are handled here.
@@ -1989,7 +1991,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi,static int ep_deliver_event (struct eventpoll *ep,struct epitem *epi,poll_table *pt,struct epoll_event __user **uevents, -struct list_head *txlist) +struct list_head *scan_batch) {struct epoll_event __user *next;struct wakeup_source *ws;
@@ -2027,7 +2029,7 @@ static int ep_deliver_event(struct eventpoll *ep, struct epitem *epi,* ep_done_scan() splices it onto rdllist for the next * attempt. */ -list_add (&epi->rdllink, txlist); +list_add (&epi->rdllink, scan_batch);ep_pm_stay_awake (epi);return -EFAULT ; }
@@ -2053,7 +2055,7 @@ static int ep_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) {struct epitem *epi, *tmp; -LIST_HEAD (txlist); +LIST_HEAD (scan_batch);poll_table pt;int res =0 ;
@@ -2068,19 +2070,19 @@ static int ep_send_events(struct eventpoll *ep,init_poll_funcptr (&pt,NULL );mutex_lock (&ep->mtx); -ep_start_scan (ep, &txlist); +ep_start_scan (ep, &scan_batch);/* * We can loop without lock because we are passed a task-private -* txlist; items cannot vanish while we hold ep->mtx. +* scan_batch; items cannot vanish while we hold ep->mtx. */ -list_for_each_entry_safe (epi, tmp, &txlist, rdllink) { +list_for_each_entry_safe (epi, tmp, &scan_batch, rdllink) {int delivered;if (res >= maxevents)break ; - delivered =ep_deliver_event (ep, epi, &pt, &events, &txlist); + delivered =ep_deliver_event (ep, epi, &pt, &events, &scan_batch);if (delivered <0 ) {if (!res) res = delivered;
@@ -2089,7 +2091,7 @@ static int ep_send_events(struct eventpoll *ep, res += delivered; } -ep_done_scan (ep, &txlist); +ep_done_scan (ep, &scan_batch);mutex_unlock (&ep->mtx);return res;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 574/1611 eventpoll: Fix epoll_wait() report false negative
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nam Cao <[email protected]>
[ Upstream commit 0c4aefe3c2d0f272a2ad73699a12d4446ffdbe7b ]
ep_events_available() checks for available events by looking at ep->rdllist and ep_is_scanning(). However, this is done without a lock and can report false negative if ep_start_scan() or ep_done_scan() are executed by another task concurrently. For example:
_________________________________________________________________________
|ep_start_scan()
| list_splice_init(&ep->rdllist, ...)
ep_events_available() |
!list_empty_careful(&ep->rdllist)|
|| ep_is_scanning(ep) | | ep_enter_scan(ep)
___________________________________|_____________________________________
Another example:
_________________________________________________________________________
ep_events_available() |
|ep_start_scan()
| list_splice_init(&ep->rdllist, ...)
| ep_enter_scan(ep)
!list_empty_careful(&ep->rdllist)|
|ep_done_scan()
| ep_exit_scan(ep)
| list_splice(..., &ep->rdllist)
|| ep_is_scanning(ep) |
___________________________________|_____________________________________In the above examples, ep_events_available() sees no event despite events being available. In case epoll_wait() is called with timeout=0, epoll_wait() will wrongly return "no event" to user.
Introduce a sequence lock to resolve this issue.
Measuring the time consumption of 10 million loop iterations doing epoll_wait(), the following performance drop is observed:
timeout #event before after diff
0ms 0 3727ms 3974ms +6.6%
0ms 1 8099ms 9134ms +13%
1ms 1 13525ms 13586ms +0.45%Considering the use case of epoll_wait() (wait for events, do something with the events, repeat), it should only contribute to a small portion of user's CPU consumption. Therefore this performance drop is not alarming.
--- fs/eventpoll.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-)
fs/eventpoll.c +19 -1
@@ -38,6 +38,7 @@#include <linux/compat.h> #include <linux/rculist.h> #include <linux/capability.h> +#include <linux/seqlock.h> #include <net/busy_poll.h> /*
@@ -324,6 +325,9 @@ struct eventpoll {/* Lock which protects rdllist and ovflist */ spinlock_t lock; +/* Protect switching between rdllist and ovflist */ +seqcount_spinlock_t seq; +/* RB tree root used to store monitored fd structs */ struct rb_root_cached rbr;
@@ -556,7 +560,10 @@ static inline void epi_clear_ovflist(struct epitem *epi)*/ static inline int ep_events_available (struct eventpoll *ep) { -return !list_empty_careful (&ep->rdllist) ||ep_is_scanning (ep); +unsigned int seq =read_seqcount_begin (&ep->seq); + +return !list_empty_careful (&ep->rdllist) ||ep_is_scanning (ep) || +read_seqcount_retry (&ep->seq, seq); }#ifdef CONFIG_NET_RX_BUSY_POLL
@@ -908,8 +915,12 @@ static void ep_start_scan(struct eventpoll *ep, struct list_head *scan_batch)*/ lockdep_assert_irqs_enabled ();spin_lock_irq (&ep->lock); +write_seqcount_begin (&ep->seq); +list_splice_init (&ep->rdllist, scan_batch);ep_enter_scan (ep); + +write_seqcount_end (&ep->seq);spin_unlock_irq (&ep->lock); }
@@ -940,6 +951,9 @@ static void ep_done_scan(struct eventpoll *ep,ep_pm_stay_awake (epi); } } + +write_seqcount_begin (&ep->seq); +/* Back out of scan mode; callbacks target ep->rdllist again. */ ep_exit_scan (ep);
@@ -947,6 +961,9 @@ static void ep_done_scan(struct eventpoll *ep,* Quickly re-inject items left on "scan_batch". */ list_splice (scan_batch, &ep->rdllist); + +write_seqcount_end (&ep->seq); +__pm_relax (ep->ws);if (!list_empty (&ep->rdllist)) {
@@ -1331,6 +1348,7 @@ static int ep_alloc(struct eventpoll **pep)mutex_init (&ep->mtx);spin_lock_init (&ep->lock); +seqcount_spinlock_init (&ep->seq, &ep->lock);init_waitqueue_head (&ep->wq);init_waitqueue_head (&ep->poll_wait);INIT_LIST_HEAD (&ep->rdllist);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 575/1611 gpiolib: acpi: Only trigger ActiveBoth interrupts on boot
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mario Limonciello <[email protected]>
[ Upstream commit 3bb62e3f99a557d257e5f5a803200051b7de3afa ]
Commit ca876c7483b6 ("gpiolib-acpi: make sure we trigger edge events at least once on boot") introduced logic to trigger edge-based GPIO interrupts during initialization to ensure proper initial state setup when firmware doesn't initialize it.
However, according to the Microsoft GPIO documentation, triggering GPIO interrupts during initialization should only happen for interrupts marked as ActiveBoth (both IRQF_TRIGGER_RISING and IRQF_TRIGGER_FALLING) and only when the associated GPIO line is already asserted (logic level low).
The current implementation incorrectly triggers:
1. Any edge-triggered interrupt (RISING-only or FALLING-only)
2. RISING interrupts when value is high and FALLING when value is low
This causes problems at bootup for single-edge interrupts that don't follow the ActiveBoth pattern.
Fix this by:
- Only triggering when BOTH rising and falling edges are configured
- Only triggering when the GPIO line is asserted (value == 0)
--- drivers/gpio/gpiolib-acpi-core.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-)
drivers/gpio/gpiolib-acpi-core.c +15 -4
@@ -233,12 +233,23 @@ static void acpi_gpiochip_request_irq(struct acpi_gpio_chip *acpi_gpio, event->irq_requested = true; -/* Make sure we trigger the initial state of edge-triggered IRQs */ +/* +* Make sure we trigger the initial state of ActiveBoth IRQs. +* +* According to the Microsoft GPIO documentation, triggering GPIO +* interrupts marked as ActiveBoth during initialization is correct +* as long as the associated GPIO line is already "asserted" +* (logic level low). We should not trigger edge-based GPIO +* interrupts not marked as ActiveBoth. +* +* See: https://learn.microsoft.com/en-us/windows-hardware/drivers/bringup/general-purpose-i-o--gpio- +* Section: "GPIO controllers and ActiveBoth interrupts" +*/ if (acpi_gpio_need_run_edge_events_on_boot () && - (event->irqflags & (IRQF_TRIGGER_RISING |IRQF_TRIGGER_FALLING ))) { + ((event->irqflags & (IRQF_TRIGGER_RISING |IRQF_TRIGGER_FALLING )) == + (IRQF_TRIGGER_RISING |IRQF_TRIGGER_FALLING ))) { value =gpiod_get_raw_value_cansleep (event->desc); -if (((event->irqflags &IRQF_TRIGGER_RISING ) && value ==1 ) || - ((event->irqflags &IRQF_TRIGGER_FALLING ) && value ==0 )) +if (value ==0 ) event->handler (event->irq, event); } }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 576/1611 i3c: master: svc: Fix missed IBI after false SLVSTART on NPCM845
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Stanley Chu <[email protected]>
[ Upstream commit fa1d4fa118f4229168e9ca88cea260c5e5a94652 ]
The NPCM845 I3C controller may raise a false SLVSTART interrupt. The handler first latches MSTATUS and then clears SLVSTART. If a real IBI request arrives after the handler latches MSTATUS but before it clears the SLVSTART interrupt status, HW sets the SLVREQ state. However, the handler still relies on the stale MSTATUS snapshot, returns early, and misses the real IBI. No further interrupt is generated for this pending IBI.
Re-read MSTATUS to obtain the latest state and avoid missing a real IBI due to this race condition.
--- drivers/i3c/master/svc-i3c-master.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-)
drivers/i3c/master/svc-i3c-master.c +12 -4
@@ -635,10 +635,18 @@ static irqreturn_t svc_i3c_master_irq_handler(int irq, void *dev_id)/* Clear the interrupt status */ writel (SVC_I3C_MINT_SLVSTART , master->regs +SVC_I3C_MSTATUS ); -/* Ignore the false event */ -if (svc_has_quirk (master,SVC_I3C_QUIRK_FALSE_SLVSTART ) && - !SVC_I3C_MSTATUS_STATE_SLVREQ (active)) -return IRQ_HANDLED ; +if (svc_has_quirk (master,SVC_I3C_QUIRK_FALSE_SLVSTART )) { +/* +* Re-read MSTATUS to obtain the latest state and avoid +* missing an IBI that arrives after MSTATUS is latched +* but before SLVSTART is cleared. +*/ + active =readl (master->regs +SVC_I3C_MSTATUS ); + +/* Ignore the false event */ +if (!SVC_I3C_MSTATUS_STATE_SLVREQ (active)) +return IRQ_HANDLED ; + }/* * The SDA line remains low until the request is processed.
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 577/1611 staging: nvec: fix use-after-free in nvec_rx_completed()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alexandru Hossu <[email protected]>
[ Upstream commit 26813881181deb3a32fbb59eadb2599cbe8423f6 ]
In nvec_rx_completed(), when an incomplete RX transfer is detected, nvec_msg_free() is called to return the message back to the pool by clearing its 'used' atomic flag. Immediately after this, the code accesses nvec->rx->data[0] to check the message type.
Since nvec_msg_free() marks the pool slot as available via atomic_set(), any concurrent or subsequent call to nvec_msg_alloc() could claim that same slot and overwrite its data[] array. Reading nvec->rx->data[0] after freeing the message is therefore a use-after-free.
Fix this by saving the message type byte before calling nvec_msg_free(), then using the saved value for the battery quirk check.
--- drivers/staging/nvec/nvec.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/staging/nvec/nvec.c +3 -1
@@ -494,6 +494,8 @@ static void nvec_tx_completed(struct nvec_chip *nvec)static void nvec_rx_completed (struct nvec_chip *nvec) {if (nvec->rx->pos !=nvec_msg_size (nvec->rx)) { +unsigned char msg_type = nvec->rx->data[0 ]; +dev_err (nvec->dev,"RX incomplete: Expected %u bytes, got %u\n" , (uint )nvec_msg_size (nvec->rx), (uint )nvec->rx->pos);
@@ -502,7 +504,7 @@ static void nvec_rx_completed(struct nvec_chip *nvec) nvec->state =0 ;/* Battery quirk - Often incomplete, and likes to crash */ -if (nvec->rx->data[0 ] ==NVEC_BAT ) +if (msg_type ==NVEC_BAT )complete (&nvec->ec_transfer);return ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 578/1611 perf debuginfo: Fix libdw API contract violations
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ian Rogers <[email protected]>
[ Upstream commit 31088ccf0312b1a547046f1f69890ede07834a30 ]
Check return value of dwfl_report_end during offline initialization. Validate dwfl_module_relocation_info result before passing to strcmp to avoid potential segmentation faults.
Additionally:
- Fix a file descriptor leak in debuginfo__init_offline_dwarf() when dwfl_report_offline() or subsequent setup calls fail.
--- tools/perf/util/debuginfo.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
tools/perf/util/debuginfo.c +6 -3
@@ -42,6 +42,7 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *dbg, {GElf_Addr dummy;int fd; +bool fd_consumed = false; fd =open (path,O_RDONLY );if (fd <0 )
@@ -55,6 +56,7 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *dbg, dbg->mod =dwfl_report_offline (dbg->dwfl,"" ,"" , fd);if (!dbg->mod) goto error; + fd_consumed = true; dbg->dbg =dwfl_module_getdwarf (dbg->mod, &dbg->bias);if (!dbg->dbg)
@@ -62,13 +64,14 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,dwfl_module_build_id (dbg->mod, &dbg->build_id, &dummy); -dwfl_report_end (dbg->dwfl,NULL ,NULL ); +if (dwfl_report_end (dbg->dwfl,NULL ,NULL ) !=0 ) + goto error;return 0 ; error:if (dbg->dwfl)dwfl_end (dbg->dwfl); -else +if (!fd_consumed)close (fd);memset (dbg,0 ,sizeof (*dbg));
@@ -168,7 +171,7 @@ int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,/* Search the relocation related .text section */ for (i =0 ; i < n; i++) { p =dwfl_module_relocation_info (dbg->mod, i, &shndx); -if (strcmp (p,".text" ) ==0 ) { +if (p &&strcmp (p,".text" ) ==0 ) {/* OK, get the section header */ scn =elf_getscn (elf, shndx);if (!scn)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 579/1611 coresight: cti: Fix DT filter signals silently ignored
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yingchao Deng <[email protected]>
[ Upstream commit 551bb2fd5e4ed63d33aa11f07102cce5179b7595 ]
In cti_plat_process_filter_sigs(), after allocating a temporary cti_trig_grp struct via kzalloc_obj(), the code never assigns tg->nr_sigs = nr_filter_sigs. Since kzalloc zero-initialises the struct, tg->nr_sigs remains 0. cti_plat_read_trig_group() guards with:
if (!tgrp->nr_sigs)
return 0;so it returns immediately without reading any signal indices from DT.
Fix by assigning tg->nr_sigs before calling cti_plat_read_trig_group().
--- drivers/hwtracing/coresight/coresight-cti-platform.c | 1 + 1 file changed, 1 insertion(+)
drivers/hwtracing/coresight/coresight-cti-platform.c +1 -0
@@ -329,6 +329,7 @@ static int cti_plat_process_filter_sigs(struct cti_drvdata *drvdata,if (!tg)return -ENOMEM ; + tg->nr_sigs = nr_filter_sigs; err =cti_plat_read_trig_group (tg, fwnode,CTI_DT_FILTER_OUT_SIGS );if (!err) drvdata->config.trig_out_filter |= tg->used_mask;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 580/1611 soundwire: dont program SDW_SCP_BUSCLOCK_SCALE on a unattached Peripheral
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Bard Liao <[email protected]>
[ Upstream commit c368dd5cbd61ffab2b6f8a89b0d5775e2e16cde6 ]
The SDW_SCP_BUSCLOCK_SCALE register will be programmed when the Peripheral is attached. We can and should skip programming the SDW_SCP_BUSCLOCK_SCALE register when the Peripheral is unattached.
--- drivers/soundwire/stream.c | 7 +++++++ 1 file changed, 7 insertions(+)
drivers/soundwire/stream.c +7 -0
@@ -691,6 +691,13 @@ static int sdw_program_params(struct sdw_bus *bus, bool prepare)if (scale_index <0 )return scale_index; +/* Skip the unattached Peripherals */ +if (!completion_done (&slave->enumeration_complete)) { +dev_warn (&slave->dev, +"Not enumerated, skip programming BUSCLOCK_SCALE\n" ); +continue ; + } + ret =sdw_write_no_pm (slave, addr1, scale_index);if (ret <0 ) {dev_err (&slave->dev,"SDW_SCP_BUSCLOCK_SCALE register write failed\n" );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 581/1611 soundwire: fix bug in sdw_add_element_group_count found by syzkaller
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Baoli.Zhang <[email protected]>
[ Upstream commit f772ff5a0e6758fd412803c09e03ba3bca5f5878 ]
The original implementation caused an out-of-bounds memory access in the sdw_add_element_group_count for-loop when i == num.
for (i = 0; i <= num; i++) {
if (rate == group->rates[i] && lane == group->lanes[i])
...To fix this error, the function now checks for existing rate/lane entries in the group(a function parameter) using a for-loop before adding them.
No functional changes apart from this fix.
--- .../soundwire/generic_bandwidth_allocation.c | 47 +++++++++---------- 1 file changed, 22 insertions(+), 25 deletions(-)
drivers/soundwire/generic_bandwidth_allocation.c +22 -25
@@ -296,39 +296,36 @@ static int sdw_add_element_group_count(struct sdw_group *group,int num = group->count;int i; -for (i =0 ; i <= num; i++) { +for (i =0 ; i < num; i++) {if (rate == group->rates[i] && lane == group->lanes[i]) -break ; - -if (i != num) -continue ; - -if (group->count >= group->max_size) { -unsigned int *rates; -unsigned int *lanes; +return 0 ; + } - group->max_size +=1 ; - rates =krealloc (group->rates, - (sizeof (int ) * group->max_size), -GFP_KERNEL ); -if (!rates) -return -ENOMEM ; +if (group->count >= group->max_size) { +unsigned int *rates; +unsigned int *lanes; - group->rates = rates; + group->max_size +=1 ; + rates =krealloc (group->rates, + (sizeof (int ) * group->max_size), +GFP_KERNEL ); +if (!rates) +return -ENOMEM ; - lanes =krealloc (group->lanes, - (sizeof (int ) * group->max_size), -GFP_KERNEL ); -if (!lanes) -return -ENOMEM ; + group->rates = rates; - group->lanes = lanes; - } + lanes =krealloc (group->lanes, + (sizeof (int ) * group->max_size), +GFP_KERNEL ); +if (!lanes) +return -ENOMEM ; - group->rates[group->count] = rate; - group->lanes[group->count++] = lane; + group->lanes = lanes; } + group->rates[group->count] = rate; + group->lanes[group->count++] = lane; +return 0 ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 582/1611 coresight: etm4x: Remove the state_needs_restore flag
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Leo Yan <[email protected]>
[ Upstream commit 9e9182cab5ebc3ee7544e60ef08ba19fdf216920 ]
When the restore flow is invoked, it means no error occurred during the save phase. Otherwise, if any errors happened while saving the context, the function would return an error and abort the suspend sequence.
Therefore, the state_needs_restore flag is unnecessary. The save and restore functions are changed to check two conditions:
1) The global flag pm_save_enable is SELF_HOSTED mode;
2) The device is in active mode (non DISABLED).
Stable-dep-of: 2ab4645fe420 ("coresight: ete: Always save state on power down")
--- drivers/hwtracing/coresight/coresight-etm4x-core.c | 14 ++++++++------ drivers/hwtracing/coresight/coresight-etm4x.h | 2 -- 2 files changed, 8 insertions(+), 8 deletions(-)
drivers/hwtracing/coresight/coresight-etm4x-core.c +8 -6
@@ -1953,8 +1953,6 @@ static int __etm4_cpu_save(struct etmv4_drvdata *drvdata) goto out; } - drvdata->state_needs_restore = true; -/* * Power can be removed from the trace unit now. We do this to * potentially save power on systems that respect the TRCPDCR_PU
@@ -1972,11 +1970,14 @@ static int etm4_cpu_save(struct etmv4_drvdata *drvdata) {int ret =0 ; +if (pm_save_enable !=PARAM_PM_SAVE_SELF_HOSTED ) +return 0 ; +/* * Save and restore the ETM Trace registers only if * the ETM is active. */ -if (coresight_get_mode (drvdata->csdev) && drvdata->save_state) +if (coresight_get_mode (drvdata->csdev)) ret =__etm4_cpu_save (drvdata);return ret; }
@@ -2066,8 +2067,6 @@ static void __etm4_cpu_restore(struct etmv4_drvdata *drvdata)if (!drvdata->skip_power_up)etm4x_relaxed_write32 (csa, state->trcpdcr,TRCPDCR ); - drvdata->state_needs_restore = false; -/* * As recommended by section 4.3.7 ("Synchronization when using the * memory-mapped interface") of ARM IHI 0064D
@@ -2086,7 +2085,10 @@ static void __etm4_cpu_restore(struct etmv4_drvdata *drvdata)static void etm4_cpu_restore (struct etmv4_drvdata *drvdata) { -if (drvdata->state_needs_restore) +if (pm_save_enable !=PARAM_PM_SAVE_SELF_HOSTED ) +return ; + +if (coresight_get_mode (drvdata->csdev))__etm4_cpu_restore (drvdata); }
drivers/hwtracing/coresight/coresight-etm4x.h +0 -2
@@ -980,7 +980,6 @@ struct etmv4_save_state {* in EL2. Otherwise, 0. * @config: structure holding configuration parameters. * @save_state: State to be preserved across power loss -* @state_needs_restore: True when there is context to restore after PM exit * @skip_power_up: Indicates if an implementation can skip powering up * the trace unit. * @paused: Indicates if the trace unit is paused.
@@ -1036,7 +1035,6 @@ struct etmv4_drvdata {u64 trfcr;struct etmv4_config config;struct etmv4_save_state *save_state; -bool state_needs_restore;bool skip_power_up;bool paused;DECLARE_BITMAP (arch_features,ETM4_IMPDEF_FEATURE_MAX );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 583/1611 coresight: ete: Always save state on power down
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: James Clark <[email protected]>
[ Upstream commit 2ab4645fe4206c142a5f1491e191c906279686cf ]
System register ETMs and ETE are unlikely to be preserved on CPU power down. The ETE DT binding also never documented "arm,coresight-loses-context-with-cpu" so nobody would have legitimately been able to use that binding to fix it and ACPI has no such binding at all.
Fix it by hard coding the setting for sysreg ETMs (ETE is always sysreg) or ACPI boots. Use a local variable when setting up save_state so that it's immune to concurrent probing when devices have different configurations which is an issue with modifying the global.
This fixes the following error when using Coresight with ACPI on the FVP which supports CPU PM:
coresight ete0: External agent took claim tag
WARNING: drivers/hwtracing/coresight/coresight-core.c:248 at coresight_disclaim_device_unlocked+0xe0/0xe8, CPU#0: perf/117
--- .../coresight/coresight-etm4x-core.c | 48 +++++++++++++------ 1 file changed, 34 insertions(+), 14 deletions(-)
drivers/hwtracing/coresight/coresight-etm4x-core.c +34 -14
@@ -55,10 +55,14 @@ MODULE_PARM_DESC(boot_enable, "Enable tracing on boot");#define PARAM_PM_SAVE_NEVER 1/* never save any state */ #define PARAM_PM_SAVE_SELF_HOSTED 2/* save self-hosted state only */ +/* +* Save option for ETM4. ETE, sysreg ETM4s and ACPI boots ignore this option and +* will always save. +*/ static int pm_save_enable =PARAM_PM_SAVE_FIRMWARE ;module_param (pm_save_enable, int,0444 );MODULE_PARM_DESC (pm_save_enable, -"Save/restore state on power down: 1 = never, 2 = self-hosted" ); +"Save/restore state on power down: 1 = never, 2 = self-hosted. MMIO and DT only." );static struct etmv4_drvdata *etmdrvdata[NR_CPUS ];static void etm4_set_default_config (struct etmv4_config *config);
@@ -1970,7 +1974,7 @@ static int etm4_cpu_save(struct etmv4_drvdata *drvdata) {int ret =0 ; -if (pm_save_enable !=PARAM_PM_SAVE_SELF_HOSTED ) +if (!drvdata->save_state)return 0 ;/*
@@ -2085,7 +2089,7 @@ static void __etm4_cpu_restore(struct etmv4_drvdata *drvdata)static void etm4_cpu_restore (struct etmv4_drvdata *drvdata) { -if (pm_save_enable !=PARAM_PM_SAVE_SELF_HOSTED ) +if (!drvdata->save_state)return ;if (coresight_get_mode (drvdata->csdev))
@@ -2170,6 +2174,17 @@ static void etm4_pm_clear(void) } } +static bool etm4x_always_pm_save (struct device *dev,struct csdev_access *csa) +{ +/* +* Only IO mem ETM devices will benefit from skipping PM save and only +* DT has the option to control it, not ACPI. Otherwise system register +* based ETMs and ETEs will always lose context on CPU power down, so +* always save. +*/ +return !csa->io_mem ||is_acpi_device_node (dev_fwnode (dev)); +} +static int etm4_add_coresight_dev (struct etm4_init_arg *init_arg) {int ret;
@@ -2179,6 +2194,7 @@ static int etm4_add_coresight_dev(struct etm4_init_arg *init_arg)struct coresight_desc desc = {0 };u8 major, minor;char *type_name; +bool pm_save;if (!drvdata)return -EINVAL ;
@@ -2206,6 +2222,21 @@ static int etm4_add_coresight_dev(struct etm4_init_arg *init_arg)etm4_set_default (&drvdata->config); +if (etm4x_always_pm_save (dev, init_arg->csa)) + pm_save = true; +else if (pm_save_enable ==PARAM_PM_SAVE_FIRMWARE ) + pm_save =coresight_loses_context_with_cpu (dev); +else + pm_save = pm_save_enable !=PARAM_PM_SAVE_NEVER ; + +if (pm_save) { + drvdata->save_state =devm_kmalloc (dev, +sizeof (struct etmv4_save_state ), +GFP_KERNEL ); +if (!drvdata->save_state) +return -ENOMEM ; + } + pdata =coresight_get_platform_data (dev);if (IS_ERR (pdata))return PTR_ERR (pdata);
@@ -2263,17 +2294,6 @@ static int etm4_probe(struct device *dev)if (ret)return ret; -if (pm_save_enable ==PARAM_PM_SAVE_FIRMWARE ) - pm_save_enable =coresight_loses_context_with_cpu (dev) ? -PARAM_PM_SAVE_SELF_HOSTED :PARAM_PM_SAVE_NEVER ; - -if (pm_save_enable !=PARAM_PM_SAVE_NEVER ) { - drvdata->save_state =devm_kmalloc (dev, -sizeof (struct etmv4_save_state ),GFP_KERNEL ); -if (!drvdata->save_state) -return -ENOMEM ; - } -raw_spin_lock_init (&drvdata->spinlock); drvdata->cpu =coresight_get_cpu (dev);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 584/1611 coresight: etm4x: Correct TRCVMIDCCTLR1 save and restore
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Leo Yan <[email protected]>
[ Upstream commit 0ec0a8785d21f63db520bd9d2a67c55e855d36a8 ]
It is a typo to use trcvmidcctlr0 to save and restore TRCVMIDCCTLR1. Use trcvmidcctlr1 instead.
--- drivers/hwtracing/coresight/coresight-etm4x-core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/hwtracing/coresight/coresight-etm4x-core.c +2 -2
@@ -1941,7 +1941,7 @@ static int __etm4_cpu_save(struct etmv4_drvdata *drvdata) state->trcvmidcctlr0 =etm4x_read32 (csa,TRCVMIDCCTLR0 );if (drvdata->numvmidc >4 ) - state->trcvmidcctlr0 =etm4x_read32 (csa,TRCVMIDCCTLR1 ); + state->trcvmidcctlr1 =etm4x_read32 (csa,TRCVMIDCCTLR1 ); state->trcclaimset =etm4x_read32 (csa,TRCCLAIMCLR );
@@ -2064,7 +2064,7 @@ static void __etm4_cpu_restore(struct etmv4_drvdata *drvdata)etm4x_relaxed_write32 (csa, state->trcvmidcctlr0,TRCVMIDCCTLR0 );if (drvdata->numvmidc >4 ) -etm4x_relaxed_write32 (csa, state->trcvmidcctlr0,TRCVMIDCCTLR1 ); +etm4x_relaxed_write32 (csa, state->trcvmidcctlr1,TRCVMIDCCTLR1 );etm4x_relaxed_write32 (csa, state->trcclaimset,TRCCLAIMSET );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 585/1611 PCI/ASPM: Dont reconfigure ASPM entering low-power state
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Carlos Bilbao <[email protected]>
[ Upstream commit c855c9921da72e535c24737c748f603a52d03f7e ]
Reconfiguring ASPM when a device transitions to low-power state can enable L1.1/L1.2 substates on the PCIe link at a time when the device is sleeping and may be unable to exit them. ASPM should be reconfigured on D0 entry (resume), not on the way down.
pci_set_low_power_state() calls pcie_aspm_pm_state_change() after writing D3hot to PCI_PM_CTRL. pcie_aspm_pm_state_change() resets link->aspm_capable to link->aspm_support and then calls pcie_config_aspm_path(), which can enable ASPM L1.1/L1.2 substates on the PCIe link. If the device cannot recover the link from L1.2 while in D3hot, subsequent config space reads return 0xFFFF ("device inaccessible") and pci_power_up() fails with messages like:
vfio-pci 0000:5d:00.0: Unable to change power state from D3hot to D0, device inaccessible
This was observed on NVIDIA H100 SXM5 GPUs bound to vfio-pci when Linux runtime PM suspends them to D3hot: the GPU becomes permanently inaccessible and disappears from the PCIe bus.
The call to pcie_aspm_pm_state_change() in pci_set_low_power_state() was restored by f93e71aea6c6 ("Revert "PCI/ASPM: Remove pcie_aspm_pm_state_change()""), which reverted 08d0cc5f3426 ("PCI/ASPM:
Remove pcie_aspm_pm_state_change()"). The revert was necessary because the removal broke suspend/resume on certain platforms that required ASPM to be reconfigured on D0 entry. However, the revert restored the call in both pci_set_full_power_state() (D0 entry) and pci_set_low_power_state() (low-power entry).
Only the D0-entry call is needed to fix the suspend/resume regression. The low-power-entry call is harmful: reconfiguring ASPM immediately after putting a device into D3hot can enable link substates that the device or platform cannot exit while the device is sleeping.
Remove the pcie_aspm_pm_state_change() call from pci_set_low_power_state(). ASPM will still be reconfigured correctly when the device returns to D0 via pci_set_full_power_state().
--- drivers/pci/pci.c | 3 --- 1 file changed, 3 deletions(-)
drivers/pci/pci.c +0 -3
@@ -1519,9 +1519,6 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state, boolpci_power_name (dev->current_state), pci_power_name(state)); -if (dev->bus->self) -pcie_aspm_pm_state_change (dev->bus->self, locked); -return 0 ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 586/1611 PCI: Introduce named defines for PCI ROM
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Guixin Liu <[email protected]>
[ Upstream commit 113e86bc58a918f85d250723436a4d541a873358 ]
Convert the magic numbers associated with PCI ROM into named definitions. Some of these definitions will be used in the second fix patch.
Stable-dep-of: 538796b807fc ("PCI: Check ROM header and data structure addr before accessing")
--- drivers/pci/rom.c | 40 ++++++++++++++++++++++++++++------------ 1 file changed, 28 insertions(+), 12 deletions(-)
drivers/pci/rom.c +28 -12
@@ -5,13 +5,28 @@* (C) Copyright 2004 Jon Smirl <[email protected]> * (C) Copyright 2004 Silicon Graphics, Inc. Jesse Barnes <[email protected]> */ + +#include <linux/bits.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/pci.h> +#include <linux/sizes.h> #include <linux/slab.h> #include "pci.h" +#define PCI_ROM_HEADER_SIZE 0x1A +#define PCI_ROM_POINTER_TO_DATA_STRUCT 0x18 +#define PCI_ROM_LAST_IMAGE_INDICATOR 0x15 +#define PCI_ROM_LAST_IMAGE_INDICATOR_BIT BIT(7) +#define PCI_ROM_IMAGE_LEN 0x10 +#define PCI_ROM_IMAGE_SECTOR_SIZE SZ_512 +#define PCI_ROM_IMAGE_SIGNATURE 0xAA55 + +/* Data structure signature is "PCIR" in ASCII representation */ +#define PCI_ROM_DATA_STRUCT_SIGNATURE 0x52494350 +#define PCI_ROM_DATA_STRUCT_LEN 0x0A +/** * pci_enable_rom - enable ROM decoding for a PCI device * @pdev: PCI device to enable
@@ -91,26 +106,27 @@ static size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, do { void __iomem *pds; /* Standard PCI ROMs start out with these bytes 55 AA */ - if (readw(image) != 0xAA55) { - pci_info(pdev, "Invalid PCI ROM header signature: expecting 0xaa55, got %#06x\n", - readw(image)); + if (readw(image) != PCI_ROM_IMAGE_SIGNATURE) { + pci_info(pdev, "Invalid PCI ROM header signature: expecting %#06x, got %#06x\n", + PCI_ROM_IMAGE_SIGNATURE, readw(image)); break; } - /* get the PCI data structure and check its "PCIR" signature */ - pds = image + readw(image + 24); - if (readl(pds) != 0x52494350) { - pci_info(pdev, "Invalid PCI ROM data signature: expecting 0x52494350, got %#010x\n", - readl(pds)); + /* Get the PCI data structure and check its "PCIR" signature */ + pds = image + readw(image + PCI_ROM_POINTER_TO_DATA_STRUCT); + if (readl(pds) != PCI_ROM_DATA_STRUCT_SIGNATURE) { + pci_info(pdev, "Invalid PCI ROM data signature: expecting %#010x, got %#010x\n", + PCI_ROM_DATA_STRUCT_SIGNATURE, readl(pds)); break; } - last_image = readb(pds + 21) & 0x80; - length = readw(pds + 16); - image += length * 512; + last_image = readb(pds + PCI_ROM_LAST_IMAGE_INDICATOR) & + PCI_ROM_LAST_IMAGE_INDICATOR_BIT; + length = readw(pds + PCI_ROM_IMAGE_LEN); + image += length * PCI_ROM_IMAGE_SECTOR_SIZE; /* Avoid iterating through memory outside the resource window */ if (image >= rom + size) break; if (!last_image) { - if (readw(image) != 0xAA55) { + if (readw(image) != PCI_ROM_IMAGE_SIGNATURE) { pci_info(pdev, "No more image in the PCI ROM\n"); break; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 587/1611 PCI: Check ROM header and data structure addr before accessing
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Guixin Liu <[email protected]>
[ Upstream commit 538796b807fcfb81b2ce40cc97a614fd8588feb5 ]
We meet a crash when running stress-ng on x86_64 machine:
BUG: unable to handle page fault for address: ffa0000007f40000
RIP: 0010:pci_get_rom_size+0x52/0x220
Call Trace:
<TASK>
pci_map_rom+0x80/0x130
pci_read_rom+0x4b/0xe0
kernfs_file_read_iter+0x96/0x180
vfs_read+0x1b1/0x300Our analysis reveals that the ROM space's start address is 0xffa0000007f30000, and size is 0x10000. Because of broken ROM space, before calling readl(pds), the pds's value is 0xffa0000007f3ffff, which is already pointed to the ROM space end, invoking readl() would read 4 bytes therefore cause an out-of-bounds access and trigger a crash. Fix this by adding image header and data structure checking.
We also found another crash on arm64 machine:
Unable to handle kernel paging request at virtual address ffff8000dd1393ff Mem abort info: ESR = 0x0000000096000021 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x21: alignment fault
The call trace is the same with x86_64, but the crash reason is that the data structure addr is not aligned with 4, and arm64 machine report "alignment fault". Fix this by adding alignment checking.
--- drivers/pci/rom.c | 123 +++++++++++++++++++++++++++++++++++++++------- 1 file changed, 105 insertions(+), 18 deletions(-)
drivers/pci/rom.c +105 -18
@@ -6,9 +6,12 @@* (C) Copyright 2004 Silicon Graphics, Inc. Jesse Barnes <[email protected]> */ +#include <linux/align.h> #include <linux/bits.h> #include <linux/kernel.h> #include <linux/export.h> +#include <linux/io.h> +#include <linux/overflow.h> #include <linux/pci.h> #include <linux/sizes.h> #include <linux/slab.h>
@@ -27,6 +30,15 @@#define PCI_ROM_DATA_STRUCT_SIGNATURE 0x52494350#define PCI_ROM_DATA_STRUCT_LEN 0x0A +/* +* Per PCI Firmware r3.3, sec 5.1.3, a conformant PCI Data Structure is at +* least 24 bytes (0x18), large enough to cover every fixed field this +* driver reads (up to the Indicator byte at offset 0x15). Reject smaller +* device-claimed lengths so the follow-up readers in pci_get_rom_size() +* cannot escape the mapped ROM window. +*/ +#define PCI_ROM_DATA_STRUCT_MIN_LEN 0x18 +/** * pci_enable_rom - enable ROM decoding for a PCI device * @pdev: PCI device to enable
@@ -84,6 +96,91 @@ void pci_disable_rom(struct pci_dev *pdev) }EXPORT_SYMBOL_GPL (pci_disable_rom); +static bool pci_rom_header_valid (struct pci_dev *pdev,void __iomem *image, +void __iomem *rom,size_t size, +bool expect_valid) +{ +unsigned long rom_end = (unsigned long )rom + size -1 ; +unsigned long header_end; +u16 signature; + +/* +* Per PCI Firmware r3.3, sec 5.1, each image must start on a +* 512-byte boundary and must contain the PCI Expansion ROM header. +* Because @rom is page-aligned (returned by ioremap()), checking +* 512-byte alignment of @image is equivalent to enforcing the +* spec's sector-aligned layout within the ROM. This also +* satisfies the natural-alignment requirement of readw() on archs +* such as arm64 that disallow unaligned IOMEM access. +*/ +if (!IS_ALIGNED ((unsigned long )image,PCI_ROM_IMAGE_SECTOR_SIZE )) +return false; + +if (check_add_overflow ((unsigned long )image,PCI_ROM_HEADER_SIZE -1 , + &header_end)) +return false; + +if (image < rom || header_end > rom_end) +return false; + +/* Standard PCI ROMs start out with these bytes 55 AA */ + signature =readw (image); +if (signature !=PCI_ROM_IMAGE_SIGNATURE ) { +if (expect_valid) { +pci_info (pdev,"Invalid PCI ROM header signature: expecting %#06x, got %#06x\n" , +PCI_ROM_IMAGE_SIGNATURE , signature); + }else { +pci_info (pdev,"No more images in PCI ROM\n" ); + } +return false; + } + +return true; +} + +static bool pci_rom_data_struct_valid (struct pci_dev *pdev,void __iomem *pds, +void __iomem *rom,size_t size) +{ +unsigned long rom_end = (unsigned long )rom + size -1 ; +unsigned long end; +u32 signature; +u16 data_len; + +/* +* Some CPU architectures require IOMEM access addresses to be +* aligned, for example arm64, so since we're about to call +* readl(), check here for 4-byte alignment. +*/ +if (!IS_ALIGNED ((unsigned long )pds,4 )) +return false; + +if (check_add_overflow ((unsigned long )pds,PCI_ROM_DATA_STRUCT_LEN +1 , + &end)) +return false; + +if (pds < rom || end > rom_end) +return false; + + signature =readl (pds); +if (signature !=PCI_ROM_DATA_STRUCT_SIGNATURE ) { +pci_info (pdev,"Invalid PCI ROM data signature: expecting %#010x, got %#010x\n" , +PCI_ROM_DATA_STRUCT_SIGNATURE , signature); +return false; + } + + data_len =readw (pds +PCI_ROM_DATA_STRUCT_LEN ); +if (data_len <PCI_ROM_DATA_STRUCT_MIN_LEN || data_len ==U16_MAX ) +return false; + +if (check_add_overflow ((unsigned long )pds, data_len -1 , &end)) +return false; + +if (end > rom_end) +return false; + +return true; +} +/** * pci_get_rom_size - obtain the actual size of the ROM image * @pdev: target PCI device
@@ -99,38 +196,28 @@ static size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size) {void __iomem *image; -int last_image;unsigned int length; +bool last_image; image = rom;do {void __iomem *pds; -/* Standard PCI ROMs start out with these bytes 55 AA */ -if (readw (image) !=PCI_ROM_IMAGE_SIGNATURE ) { -pci_info (pdev,"Invalid PCI ROM header signature: expecting %#06x, got %#06x\n" , -PCI_ROM_IMAGE_SIGNATURE ,readw (image)); +if (!pci_rom_header_valid (pdev, image, rom, size, true))break ; - } +/* Get the PCI data structure and check its "PCIR" signature */ pds = image +readw (image +PCI_ROM_POINTER_TO_DATA_STRUCT ); -if (readl (pds) !=PCI_ROM_DATA_STRUCT_SIGNATURE ) { -pci_info (pdev,"Invalid PCI ROM data signature: expecting %#010x, got %#010x\n" , -PCI_ROM_DATA_STRUCT_SIGNATURE ,readl (pds)); +if (!pci_rom_data_struct_valid (pdev, pds, rom, size))break ; - } + last_image =readb (pds +PCI_ROM_LAST_IMAGE_INDICATOR ) &PCI_ROM_LAST_IMAGE_INDICATOR_BIT ; length =readw (pds +PCI_ROM_IMAGE_LEN ); image += length *PCI_ROM_IMAGE_SECTOR_SIZE ; -/* Avoid iterating through memory outside the resource window */ -if (image >= rom + size) + +if (!last_image && + !pci_rom_header_valid (pdev, image, rom, size, false))break ; -if (!last_image) { -if (readw (image) !=PCI_ROM_IMAGE_SIGNATURE ) { -pci_info (pdev,"No more image in the PCI ROM\n" ); -break ; - } - } }while (length && !last_image);/* never return a size larger than the PCI resource window */
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 588/1611 x86/platform/olpc: xo15: Drop wakeup source on driver removal
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Rafael J. Wysocki <[email protected]>
[ Upstream commit cc966553e6ff0849978b5754531b768b0ff54985 ]
Prevent leaking a wakeup source object after removing the driver by adding appropriate cleanup code to its remove callback function.
--- arch/x86/platform/olpc/olpc-xo15-sci.c | 1 + 1 file changed, 1 insertion(+)
arch/x86/platform/olpc/olpc-xo15-sci.c +1 -0
@@ -185,6 +185,7 @@ static int xo15_sci_add(struct acpi_device *device)static void xo15_sci_remove (struct acpi_device *device) { +device_init_wakeup (&device->dev, false);acpi_disable_gpe (NULL , xo15_sci_gpe);acpi_remove_gpe_handler (NULL , xo15_sci_gpe, xo15_sci_gpe_handler);cancel_work_sync (&sci_work);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 589/1611 platform/x86: xo15-ebook: Fix wakeup source and GPE handling
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Rafael J. Wysocki <[email protected]>
[ Upstream commit b2fc2c6ebbd2d49935c8960755d8170faead2159 ]
The device_set_wakeup_enable() call in ebook_switch_add() doesn't actually do anything because power.can_wakeup is not set for ACPI device objects. Moreover, had it done anything, it would have registered a wakeup source object that wouldn't have been used going forward and that wakeup source would have been leaked after driver removal because ebook_switch_remove() doesn't clean it up. Accordingly, remove that call from ebook_switch_add().
Also prevent leaking an enabled ACPI GPE after removing the driver by adding appropriate cleanup code to ebook_switch_remove().
--- drivers/platform/x86/xo15-ebook.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/platform/x86/xo15-ebook.c +6 -1
@@ -38,6 +38,7 @@ MODULE_DEVICE_TABLE(acpi, ebook_device_ids);struct ebook_switch {struct input_dev *input;char phys[32 ];/* for input device */ +bool gpe_enabled; };static int ebook_send_state (struct acpi_device *device)
@@ -128,7 +129,7 @@ static int ebook_switch_add(struct acpi_device *device)/* Button's GPE is run-wake GPE */ acpi_enable_gpe (device->wakeup.gpe_device, device->wakeup.gpe_number); -device_set_wakeup_enable (&device->dev, true); + button->gpe_enabled = true; }return 0 ;
@@ -144,6 +145,10 @@ static void ebook_switch_remove(struct acpi_device *device) {struct ebook_switch *button =acpi_driver_data (device); +if (button->gpe_enabled) +acpi_disable_gpe (device->wakeup.gpe_device, + device->wakeup.gpe_number); +input_unregister_device (button->input);kfree (button); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 590/1611 perf sched: Add missing mmap2 handler in timehist
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ian Rogers <[email protected]>
[ Upstream commit 91182741369b261c441e63e6678893032a6d7e4c ]
perf_sched__timehist() registers event handlers for options using the sched->tool struct. It registers handlers for MMAP, COMM, EXIT, FORK, etc. but completely omits registering a handler for MMAP2 events.
Failing to register both MMAP and MMAP2 handlers causes modern systems (which primarily output MMAP2 records) to silently drop VMA map mappings. This results in uninitialized machine/thread mapping structures, making it impossible to resolve shared library instruction pointers (IPs) to dynamic symbols/DSOs during timehist callchain analysis.
Fix this by correctly registering perf_event__process_mmap2 in sched->tool inside perf_sched__timehist().
--- tools/perf/builtin-sched.c | 1 + 1 file changed, 1 insertion(+)
tools/perf/builtin-sched.c +1 -0
@@ -3292,6 +3292,7 @@ static int perf_sched__timehist(struct perf_sched *sched)*/ sched->tool.sample = perf_timehist__process_sample; sched->tool.mmap = perf_event__process_mmap; + sched->tool.mmap2 = perf_event__process_mmap2; sched->tool.comm = perf_event__process_comm; sched->tool.exit = perf_event__process_exit; sched->tool.fork = perf_event__process_fork;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 591/1611 PCI: loongson: Do not ignore downstream devices on external bridges
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Rong Zhang <[email protected]>
[ Upstream commit 1389ab9bf9f627d4daed86f492091b00f110aa86 ]
Loongson PCI host controllers have a hardware quirk that requires software to ignore downstream devices with device number > 0 on the internal bridges. The current implementation applies the workaround to all non-root buses, which breaks external bridges (e.g., PCIe switches) with multiple downstream devices.
Fix it by only applying the workaround to internal bridges.
Tested on Loongson-LS3A4000-7A1000-NUC-SE, using AMD Promontory 21 chipset add-in card [1].
$ lspci -tnnnvvv
-[0000:00]-+-00.0 Loongson Technology LLC 7A1000 Chipset Hyper Transport Bridge Controller [0014:7a00]
+-00.1 Loongson Technology LLC 7A2000 Chipset Hyper Transport Bridge Controller [0014:7a10]
+-03.0 Loongson Technology LLC 2K1000/2000 / 7A1000 Chipset Gigabit Ethernet Controller [0014:7a03]
+-04.0 Loongson Technology LLC 2K1000 / 7A1000/2000 Chipset USB OHCI Controller [0014:7a24]
+-04.1 Loongson Technology LLC 2K1000 / 7A1000/2000 Chipset USB EHCI Controller [0014:7a14]
+-05.0 Loongson Technology LLC 2K1000 / 7A1000/2000 Chipset USB OHCI Controller [0014:7a24]
+-05.1 Loongson Technology LLC 2K1000 / 7A1000/2000 Chipset USB EHCI Controller [0014:7a14]
+-06.0 Loongson Technology LLC 7A1000 Chipset Vivante GC1000 GPU [0014:7a15]
+-06.1 Loongson Technology LLC 2K1000 / 7A1000 Chipset Display Controller [0014:7a06]
+-07.0 Loongson Technology LLC 2K1000/2000/3000 / 3B6000M / 7A1000/2000 Chipset HD Audio Controller [0014:7a07]
+-08.0 Loongson Technology LLC 2K1000 / 7A1000 Chipset 3Gb/s SATA AHCI Controller [0014:7a08]
+-08.1 Loongson Technology LLC 2K1000 / 7A1000 Chipset 3Gb/s SATA AHCI Controller [0014:7a08]
+-08.2 Loongson Technology LLC 2K1000 / 7A1000 Chipset 3Gb/s SATA AHCI Controller [0014:7a08]
+-09.0-[01]----00.0 Qualcomm Technologies, Inc QCNFA765 Wireless Network Adapter [17cb:1103]
+-0a.0-[02]----00.0 Etron Technology, Inc. EJ188/EJ198 USB 3.0 Host Controller [1b6f:7052]
+-0f.0-[03-08]----00.0-[04-08]--+-00.0-[05]----00.0 Shenzhen Longsys Electronics Co., Ltd. FORESEE XP1000 / Lexar Professional CFexpress Type B Gold series, NM620 PCIe NVME SSD (DRAM-less) [1d97:5216]
| +-08.0-[06]----00.0 MAXIO Technology (Hangzhou) Ltd. NVMe SSD Controller MAP1202 (DRAM-less) [1e4b:1202]
| +-0c.0-[07]----00.0 Advanced Micro Devices, Inc. [AMD] 600 Series Chipset USB 3.2 Controller [1022:43f7]
| \-0d.0-[08]----00.0 Advanced Micro Devices, Inc. [AMD] 600 Series Chipset SATA Controller [1022:43f6]
\-16.0 Loongson Technology LLC 7A1000 Chipset SPI Controller [0014:7a0b]--- drivers/pci/controller/pci-loongson.c | 31 ++++++++++++++------------- 1 file changed, 16 insertions(+), 15 deletions(-)
drivers/pci/controller/pci-loongson.c +16 -15
@@ -80,6 +80,18 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON,DECLARE_PCI_FIXUP_EARLY (PCI_VENDOR_ID_LOONGSON ,DEV_LS7A_LPC , system_bus_quirk); +static const struct pci_device_id loongson_internal_bridge_devids[] = { + {PCI_VDEVICE (LOONGSON ,DEV_LS2K_PCIE_PORT0 ) }, + {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT0 ) }, + {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT1 ) }, + {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT2 ) }, + {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT3 ) }, + {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT4 ) }, + {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT5 ) }, + {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT6 ) }, + {0 , }, +}; +/* * Some Loongson PCIe ports have hardware limitations on their Maximum Read * Request Size. They can't handle anything larger than this. Sane
@@ -92,24 +104,13 @@ static void loongson_set_min_mrrs_quirk(struct pci_dev *pdev) {struct pci_bus *bus = pdev->bus;struct pci_dev *bridge; -static const struct pci_device_id bridge_devids[] = { - {PCI_VDEVICE (LOONGSON ,DEV_LS2K_PCIE_PORT0 ) }, - {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT0 ) }, - {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT1 ) }, - {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT2 ) }, - {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT3 ) }, - {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT4 ) }, - {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT5 ) }, - {PCI_VDEVICE (LOONGSON ,DEV_LS7A_PCIE_PORT6 ) }, - {0 , }, - };/* look for the matching bridge */ while (!pci_is_root_bus (bus)) { bridge = bus->self; bus = bus->parent; -if (pci_match_id (bridge_devids, bridge)) { +if (pci_match_id (loongson_internal_bridge_devids, bridge)) {if (pcie_get_readrq (pdev) >256 ) {pci_info (pdev,"limiting MRRS to 256\n" );pcie_set_readrq (pdev,256 );
@@ -266,11 +267,11 @@ static void __iomem *pci_loongson_map_bus(struct pci_bus *bus,struct loongson_pci *priv =pci_bus_to_loongson_pci (bus);/* -* Do not read more than one device on the bus other than -* the host bus. +* Do not read more than one device on the internal bridges. */ if ((priv->data->flags &FLAG_DEV_FIX ) && bus->self) { -if (!pci_is_root_bus (bus) && (device >0 )) +if (!pci_is_root_bus (bus) && (device >0 ) && +pci_match_id (loongson_internal_bridge_devids, bus->self))return NULL ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 592/1611 rust: alloc: fix assert in `Vec::reserve` doc test
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hsiu Che Yu <[email protected]>
[ Upstream commit 75619f2df7a5da6ffb61eedc2a73fdf70c65471c ]
The assert in the doctest used >= 10, which only checks that the capacity can hold additional elements, ignoring the existing length of v. The correct check should ensure there is room for additional *extra* elements on top of what is already in the vector.
Fix the assert to use >= v.len() + 10 so the example accurately reflects the actual semantics of the function.
--- rust/kernel/alloc/kvec.rs | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
rust/kernel/alloc/kvec.rs +1 -1
@@ -611,7 +611,7 @@ where/// /// v.reserve(10, GFP_KERNEL)?; /// let cap = v.capacity(); -/// assert!(cap >= 10); +/// assert!(cap >= v.len() + 10); /// /// v.reserve(10, GFP_KERNEL)?; /// let new_cap = v.capacity();
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 593/1611 bus: mhi: ep: Fix potential deadlock in mhi_ep_reset_worker()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sumit Kumar <[email protected]>
[ Upstream commit 9dece4435d396e9877e27483552b910ba8654169 ]
There is a potential deadlock scenario in mhi_ep_reset_worker() where the state_lock mutex is acquired twice in the same call chain:
mhi_ep_reset_worker()
mutex_lock(&mhi_cntrl->state_lock)
mhi_ep_power_up()
mhi_ep_set_ready_state()
mutex_lock(&mhi_cntrl->state_lock) <- DeadlockFix this by releasing the state_lock before calling mhi_ep_power_up(). The lock is only needed to protect current MHI state read operation. The lock can be safely released before proceeding with the power up sequence.
--- drivers/bus/mhi/ep/main.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)
drivers/bus/mhi/ep/main.c +3 -4
@@ -1087,11 +1087,12 @@ static void mhi_ep_reset_worker(struct work_struct *work)mhi_ep_power_down (mhi_cntrl); -mutex_lock (&mhi_cntrl->state_lock); -/* Reset MMIO to signal host that the MHI_RESET is completed in endpoint */ mhi_ep_mmio_reset (mhi_cntrl); + +mutex_lock (&mhi_cntrl->state_lock); cur_state = mhi_cntrl->mhi_state; +mutex_unlock (&mhi_cntrl->state_lock);/* * Only proceed further if the reset is due to SYS_ERR. The host will
@@ -1100,8 +1101,6 @@ static void mhi_ep_reset_worker(struct work_struct *work)*/ if (cur_state ==MHI_STATE_SYS_ERR )mhi_ep_power_up (mhi_cntrl); - -mutex_unlock (&mhi_cntrl->state_lock); }/*
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 594/1611 coresight: fix missing error code when trace ID is invalid
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jie Gan <[email protected]>
[ Upstream commit f4526ffee6ff9f5845b430957417149eded74bf3 ]
When coresight_path_assign_trace_id() cannot assign a valid trace ID, coresight_enable_sysfs() takes the err_path goto with ret still 0, returning success to the caller despite no trace session being started.
Change coresight_path_assign_trace_id() to return int, moving the IS_VALID_CS_TRACE_ID() check inside it so it returns -EINVAL on failure and 0 on success. Update both callers to propagate this return value directly instead of inspecting path->trace_id after the call.
--- drivers/hwtracing/coresight/coresight-core.c | 23 +++++++++++-------- .../hwtracing/coresight/coresight-etm-perf.c | 5 ++-- drivers/hwtracing/coresight/coresight-priv.h | 2 +- drivers/hwtracing/coresight/coresight-sysfs.c | 4 ++-- 4 files changed, 19 insertions(+), 15 deletions(-)
drivers/hwtracing/coresight/coresight-core.c +13 -10
@@ -732,8 +732,8 @@ static int coresight_get_trace_id(struct coresight_device *csdev,* Call this after creating the path and before enabling it. This leaves * the trace ID set on the path, or it remains 0 if it couldn't be assigned. */ -void coresight_path_assign_trace_id (struct coresight_path *path, -enum cs_mode mode) +int coresight_path_assign_trace_id (struct coresight_path *path, +enum cs_mode mode) {struct coresight_device *sink =coresight_get_sink (path);struct coresight_node *nd;
@@ -743,15 +743,18 @@ void coresight_path_assign_trace_id(struct coresight_path *path,/* Assign a trace ID to the path for the first device that wants to do it */ trace_id =coresight_get_trace_id (nd->csdev, mode, sink); -/* -* 0 in this context is that it didn't want to assign so keep searching. -* Non 0 is either success or fail. -*/ -if (trace_id !=0 ) { - path->trace_id = trace_id; -return ; - } +/* 0 means the device has no ID assignment, so keep searching */ +if (trace_id ==0 ) +continue ; + +if (!IS_VALID_CS_TRACE_ID (trace_id)) +return -EINVAL ; + + path->trace_id = trace_id; +return 0 ; } + +return -EINVAL ; }/**
drivers/hwtracing/coresight/coresight-etm-perf.c +3 -2
@@ -321,6 +321,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages,struct coresight_device *sink =NULL ;struct coresight_device *user_sink =NULL , *last_sink =NULL ;struct etm_event_data *event_data =NULL ; +int ret; event_data =alloc_event_data (cpu);if (!event_data)
@@ -418,8 +419,8 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, }/* ensure we can allocate a trace ID for this CPU */ -coresight_path_assign_trace_id (path,CS_MODE_PERF ); -if (!IS_VALID_CS_TRACE_ID (path->trace_id)) { + ret =coresight_path_assign_trace_id (path,CS_MODE_PERF ); +if (ret) {cpumask_clear_cpu (cpu, mask);coresight_release_path (path);continue ;
drivers/hwtracing/coresight/coresight-priv.h +1 -1
@@ -154,7 +154,7 @@ int coresight_make_links(struct coresight_device *orig,void coresight_remove_links (struct coresight_device *orig,struct coresight_connection *conn);u32 coresight_get_sink_id (struct coresight_device *csdev); -void coresight_path_assign_trace_id (struct coresight_path *path, +int coresight_path_assign_trace_id (struct coresight_path *path,enum cs_mode mode);#if IS_ENABLED (CONFIG_CORESIGHT_SOURCE_ETM3X )
drivers/hwtracing/coresight/coresight-sysfs.c +2 -2
@@ -211,8 +211,8 @@ int coresight_enable_sysfs(struct coresight_device *csdev) goto out; } -coresight_path_assign_trace_id (path,CS_MODE_SYSFS ); -if (!IS_VALID_CS_TRACE_ID (path->trace_id)) + ret =coresight_path_assign_trace_id (path,CS_MODE_SYSFS ); +if (ret) goto err_path; ret =coresight_enable_path (path,CS_MODE_SYSFS ,NULL );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 595/1611 clk: qcom: cmnpll: Account for reference clock divider
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Luo Jie <[email protected]>
[ Upstream commit 88c543fff756450bcd04ec4560c4440be36c9e75 ]
The clk_cmn_pll_recalc_rate() function must account for the reference clock divider programmed in CMN_PLL_REFCLK_CONFIG. Without this fix, platforms with a reference divider other than 1 calculate incorrect CMN PLL rates. For example, on IPQ5332 where the reference divider is 2, the computed rate becomes twice the actual output.
Read CMN_PLL_REFCLK_DIV and divide the parent rate by this value before applying the 2 * FACTOR scaling. This yields the correct rate calculation:
rate = (parent_rate / ref_div) * 2 * factor.
Maintain backward compatibility with earlier platforms (e.g. IPQ9574, IPQ5424, IPQ5018) that use ref_div = 1.
--- drivers/clk/qcom/ipq-cmn-pll.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)
drivers/clk/qcom/ipq-cmn-pll.c +9 -2
@@ -185,7 +185,7 @@ static unsigned long clk_cmn_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) {struct clk_cmn_pll *cmn_pll =to_clk_cmn_pll (hw); -u32 val, factor; +u32 val, factor, ref_div;/* * The value of CMN_PLL_DIVIDER_CTRL_FACTOR is automatically adjusted
@@ -193,8 +193,15 @@ static unsigned long clk_cmn_pll_recalc_rate(struct clk_hw *hw,*/ regmap_read (cmn_pll->regmap,CMN_PLL_DIVIDER_CTRL , &val); factor =FIELD_GET (CMN_PLL_DIVIDER_CTRL_FACTOR , val); +if (WARN_ON (factor ==0 )) + factor =1 ; -return parent_rate *2 * factor; +regmap_read (cmn_pll->regmap,CMN_PLL_REFCLK_CONFIG , &val); + ref_div =FIELD_GET (CMN_PLL_REFCLK_DIV , val); +if (WARN_ON (ref_div ==0 )) + ref_div =1 ; + +return div_u64 ((u64 )parent_rate *2 * factor, ref_div); } static int clk_cmn_pll_determine_rate(struct clk_hw *hw,
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 596/1611 phy: phy-can-transceiver: Check driver match and driver data against NULL
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Andy Shevchenko <[email protected]>
[ Upstream commit ebee9004cc0200b2b708ebf7ac625d35c71c049f ]
Every platform driver can be forced to match a device that doesn't match its list of device IDs because of device_match_driver_override() so platform drivers that rely on the existence of a device's driver data need to verify its presence.
Accordingly, add requisite match and driver data checks against NULL to the driver where they are missing.
--- drivers/phy/phy-can-transceiver.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/phy/phy-can-transceiver.c +3 -0
@@ -122,6 +122,9 @@ static int can_transceiver_phy_probe(struct platform_device *pdev)return -ENOMEM ; match =of_match_node (can_transceiver_phy_ids, pdev->dev.of_node); +if (!match || !match->data) +return -ENODEV ; + drvdata = match->data; mux_state =devm_mux_state_get_optional (dev,NULL );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 597/1611 perf pmu: Skip test on Arm64 when #slots is zero
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Leo Yan <[email protected]>
[ Upstream commit 2e2ba7d1ea554ee6e9e751a53eebf3e9270b0670 ]
Some Arm64 PMUs expose 'caps/slots' as 0 when the slot count is not implemented, tool_pmu__read_event() currently returns false for this, so metrics that reference #slots are reported as syntax error.
Since the commit 3a61fd866ef9 ("perf expr: Return -EINVAL for syntax error in expr__find_ids()"), these syntax errors are populated as failures and make the PMU metric test fail:
9.3: Parsing of PMU event table metrics:
--- start ---
...
Found metric 'backend_bound'
metric expr 100 * (stall_slot_backend / (#slots * cpu_cycles)) for backend_bound parsing metric: 100 * (stall_slot_backend / (#slots * cpu_cycles)) Failure to read '#slots'
literal: #slots = nan
syntax error
Fail to parse metric or group `backend_bound'
...
---- end(-1) ----
9.3: Parsing of PMU event table metrics : FAILED!
This commit introduces a new function is_expected_broken_metric() to identify broken metrics, and treats metrics containing "#slots" as expected broken when #slots == 0 on Arm64 platforms.
--- tools/perf/tests/pmu-events.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-)
tools/perf/tests/pmu-events.c +22 -2
@@ -15,6 +15,7 @@#include "util/expr.h" #include "util/hashmap.h" #include "util/parse-events.h" +#include "util/tool_pmu.h" #include "metricgroup.h" #include "stat.h"
@@ -837,6 +838,26 @@ struct metric {struct metric_ref metric_ref; }; +static bool is_expected_broken_metric (const struct pmu_metric *pm) +{ +if (!strcmp (pm->metric_name,"M1" ) || !strcmp (pm->metric_name,"M2" ) || + !strcmp (pm->metric_name,"M3" )) +return true; + +#if defined(__aarch64__) +/* +* Arm64 platforms may return "#slots == 0", which is treated as a +* syntax error by the parser. Don't test these metrics when running +* on such platforms. +*/ +if (strstr (pm->metric_expr,"#slots" ) && + !tool_pmu__cpu_slots_per_cycle ()) +return true; +#endif + +return false; +} +static int test__parsing_callback (const struct pmu_metric *pm,const struct pmu_metrics_table *table,void *data)
@@ -872,8 +893,7 @@ static int test__parsing_callback(const struct pmu_metric *pm, err =metricgroup__parse_groups_test (evlist, table, pm->metric_name);if (err) { -if (!strcmp (pm->metric_name,"M1" ) || !strcmp (pm->metric_name,"M2" ) || - !strcmp (pm->metric_name,"M3" )) { +if (is_expected_broken_metric (pm)) { (*failures)--;pr_debug ("Expected broken metric %s skipping\n" , pm->metric_name); err =0 ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 598/1611 clk: at91: sam9x7: Fix gmac_gclk clock definition
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mihai Sain <[email protected]>
[ Upstream commit b6f6ebb0fb57ae6da622fb8fd4ebdc9ba1ae5756 ]
According to the datasheet (see link section), table 12.1, instance ID 24 is used for the GMAC generic clock, while instance ID 67 is reserved. Add the correct gmac_gclk entry at ID 24, aligned with the SoC clock layout, and remove the old misplaced entry at ID 67.
--- drivers/clk/at91/sam9x7.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-)
drivers/clk/at91/sam9x7.c +9 -9
@@ -569,6 +569,15 @@ static const struct { .pp_chg_id = INT_MIN, }, + { + .n = "gmac_gclk", + .id = 24, + .pp = { "audiopll_divpmcck", "plla_div2pmcck", }, + .pp_mux_table = { 6, 8, }, + .pp_count =2 , + .pp_chg_id = INT_MIN, + }, + { .n ="lcd_gclk" , .id = 25,
@@ -702,15 +711,6 @@ static const struct { .pp_count = 1, .pp_chg_id = INT_MIN, }, - - { - .n = "gmac_gclk", - .id = 67, - .pp = { "audiopll_divpmcck", "plla_div2pmcck", }, - .pp_mux_table = { 6, 8, }, - .pp_count = 2, - .pp_chg_id = INT_MIN, - }, };static void __init sam9x7_pmc_setup (struct device_node *np)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 599/1611 soundwire: intel_ace2x: release bpt_stream when close it
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Bard Liao <[email protected]>
[ Upstream commit 8a7fe10eec64bfb7cf4091bca540de4c55d56bfa ]
The BPT stream was allocated in intel_ace2x_bpt_open_stream(), we need to free it in intel_ace2x_bpt_close_stream().
--- drivers/soundwire/intel_ace2x.c | 1 + 1 file changed, 1 insertion(+)
drivers/soundwire/intel_ace2x.c +1 -0
@@ -248,6 +248,7 @@ static void intel_ace2x_bpt_close_stream(struct sdw_intel *sdw, struct sdw_slavedev_err (cdns->dev,"%s: remove slave failed: %d\n" , __func__, ret); +sdw_release_stream (cdns->bus.bpt_stream); cdns->bus.bpt_stream =NULL ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 600/1611 coresight: Fix source not disabled on idr_alloc_u32 failure
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jie Gan <[email protected]>
[ Upstream commit ea2c2b9e2a66e2b4aa0455b2d70058e2f0ea4d23 ]
In coresight_enable_sysfs(), for non-CPU sources (SOFTWARE, TPDM, OTHERS), the source device is enabled via coresight_enable_source_sysfs() before idr_alloc_u32() maps the path. If idr_alloc_u32() fails, the original code jumped directly to err_source, which only calls coresight_disable_path() and coresight_release_path(). The source device was left enabled with an incremented refcnt but no path tracked for it, leaving the device in an inconsistent state.
Disable the source before jumping to err_source so the enable and path operations are fully unwound.
--- drivers/hwtracing/coresight/coresight-sysfs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/hwtracing/coresight/coresight-sysfs.c +3 -1
@@ -244,8 +244,10 @@ int coresight_enable_sysfs(struct coresight_device *csdev)*/ hash =hashlen_hash (hashlen_string (NULL ,dev_name (&csdev->dev))); ret =idr_alloc_u32 (&path_idr, path, &hash, hash,GFP_KERNEL ); -if (ret) +if (ret) { +coresight_disable_source_sysfs (csdev,NULL ); goto err_source; + }break ;default :/* We can't be here */
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 601/1611 mailbox: mpfs: fix check for syscon presence in mpfs_mbox_inbox_isr()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Conor Dooley <[email protected]>
[ Upstream commit e30d8b2730a33e5e8789371e947c3529789a6070 ]
mpfs_mbox_inbox_isr() writes to the sysreg scb syscon, not the control scb syscon, but checks for the presence of the latter. Ultimately this makes little difference because if one syscon is present, both will be.
--- drivers/mailbox/mailbox-mpfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/mailbox/mailbox-mpfs.c +1 -1
@@ -201,7 +201,7 @@ static irqreturn_t mpfs_mbox_inbox_isr(int irq, void *data)struct mbox_chan *chan = data;struct mpfs_mbox *mbox = (struct mpfs_mbox *)chan->con_priv; -if (mbox->control_scb) +if (mbox->sysreg_scb)regmap_write (mbox->sysreg_scb,MESSAGE_INT_OFFSET ,0 );else writel_relaxed (0 , mbox->int_reg);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 602/1611 mailbox: mtk-adsp: fix UAF during device teardown
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sergey Senozhatsky <[email protected]>
[ Upstream commit b57d1a40bc43258372fa1f4d39305e093947a262 ]
When the SOF audio driver fails to initialize (e.g. firmware boot timeout), its devres unwind frees the snd_sof_dev object that the mailbox client (mtk-adsp-ipc) reaches via chan->cl->rx_callback. The mtk-adsp-mailbox shutdown clears the mailbox command registers but leaves the IRQ line unmasked, so a late interrupt can still queue a threaded handler after mbox_free_channel() had cleared chan->cl, and mbox_chan_received_data() would then trigger UAF:
BUG: KASAN: slab-use-after-free in sof_ipc3_validate_fw_version sof_ipc3_validate_fw_version sof_ipc3_do_rx_work sof_ipc3_rx_msg mt8196_dsp_handle_request mtk_adsp_ipc_recv mbox_chan_received_data mtk_adsp_mbox_isr irq_thread_fn Freed by task ...: kfree devres_release_all really_probe ... (sof-audio-of-mt8196 probe failure)
The crash was observed roughly three seconds after the failed probe.
disable_irq() in shutdown and enable_irq() in startup. disable_irq() also waits for any in-flight interrupts, so by the time mbox_free_channel() proceeds to clear chan->cl no rx_callback can run.
In addition, request the IRQ with IRQF_NO_AUTOEN so it stays masked between probe and the first client bind — otherwise an early interrupt can crash on chan->cl == NULL in mbox_chan_received_data().
--- drivers/mailbox/mtk-adsp-mailbox.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
drivers/mailbox/mtk-adsp-mailbox.c +8 -1
@@ -19,6 +19,7 @@ struct mtk_adsp_mbox_priv {struct mbox_controller mbox;void __iomem *va_mboxreg;const struct mtk_adsp_mbox_cfg *cfg; +int irq; };struct mtk_adsp_mbox_cfg {
@@ -67,6 +68,8 @@ static int mtk_adsp_mbox_startup(struct mbox_chan *chan)writel (0xFFFFFFFF , priv->va_mboxreg + priv->cfg->clr_in);writel (0xFFFFFFFF , priv->va_mboxreg + priv->cfg->clr_out); +enable_irq (priv->irq); +return 0 ; }
@@ -74,6 +77,8 @@ static void mtk_adsp_mbox_shutdown(struct mbox_chan *chan) {struct mtk_adsp_mbox_priv *priv =get_mtk_adsp_mbox_priv (chan->mbox); +disable_irq (priv->irq); +/* Clear ADSP mbox command */ writel (0xFFFFFFFF , priv->va_mboxreg + priv->cfg->clr_in);writel (0xFFFFFFFF , priv->va_mboxreg + priv->cfg->clr_out);
@@ -139,8 +144,10 @@ static int mtk_adsp_mbox_probe(struct platform_device *pdev)if (irq <0 )return irq; + priv->irq = irq; ret =devm_request_threaded_irq (dev, irq, mtk_adsp_mbox_irq, - mtk_adsp_mbox_isr,IRQF_TRIGGER_NONE , + mtk_adsp_mbox_isr, +IRQF_TRIGGER_NONE |IRQF_NO_AUTOEN ,dev_name (dev), mbox->chans);if (ret <0 )return ret;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 603/1611 PCI: dwc: Fix signedness bug in fault injection test code
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dan Carpenter <[email protected]>
[ Upstream commit 94ac934d2c054fba4a22d8dc84749094c5fa0ec0 ]
The kstrtou32() function returns negative error code or zero on success. However, in this case "val" is a u32 and the function returns signed long, so negative error codes from kstrtou32() are returned as high positive values.
Store the error code in an int instead.
--- drivers/pci/controller/dwc/pcie-designware-debugfs.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
drivers/pci/controller/dwc/pcie-designware-debugfs.c +4 -3
@@ -256,6 +256,7 @@ static ssize_t err_inj_write(struct file *file, const char __user *buf,u32 val, counter, vc_num, err_group, type_mask;int val_diff =0 ;char *kern_buf; +int ret; err_group = err_inj_list[pdata->idx].err_inj_group; type_mask = err_inj_type_mask[err_group];
@@ -277,10 +278,10 @@ static ssize_t err_inj_write(struct file *file, const char __user *buf,return -EINVAL ; } }else { - val =kstrtou32 (kern_buf,0 , &counter); -if (val) { + ret =kstrtou32 (kern_buf,0 , &counter); +if (ret) {kfree (kern_buf); -return val; +return ret; } }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 604/1611 perf build-id: Fix off-by-one bug when printing kernel/module build-id
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Michael Petlan <[email protected]>
[ Upstream commit 017bca78e4d72b1ff027d368c20a1b2c654edaf7 ]
When changing sprintf functions to snprintf, one byte got lost. Since snprintf ones do not handle the '\0' terminating character, the number of printed characters is 40, while sizeof(sbuild_id) is 41, including the terminating '\0' character.
This makes the later check fail so that nothing is printed.
Fix that.
Before:
[Michael@Carbon ~]$ perf buildid-list -k
[Michael@Carbon ~]$
After:
[Michael@Carbon ~]$ perf buildid-list -k
a527806324d543c4bc3ff2f9c9519d494fed5f68
[Michael@Carbon ~]$--- tools/perf/builtin-buildid-list.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
tools/perf/builtin-buildid-list.c +2 -2
@@ -61,7 +61,7 @@ static int sysfs__fprintf_build_id(FILE *fp)int ret; ret =sysfs__snprintf_build_id ("/" , sbuild_id,sizeof (sbuild_id)); -if (ret !=sizeof (sbuild_id)) +if (ret +1 !=sizeof (sbuild_id))return ret <0 ? ret : -EINVAL ;return fprintf (fp,"%s\n" , sbuild_id);
@@ -73,7 +73,7 @@ static int filename__fprintf_build_id(const char *name, FILE *fp)int ret; ret =filename__snprintf_build_id (name, sbuild_id,sizeof (sbuild_id)); -if (ret !=sizeof (sbuild_id)) +if (ret +1 !=sizeof (sbuild_id))return ret <0 ? ret : -EINVAL ;return fprintf (fp,"%s\n" , sbuild_id);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 605/1611 perf inject: Add --convert-callchain option
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Namhyung Kim <[email protected]>
[ Upstream commit 92ea788d2af4e65ad7a144ccfff50667e9a0d227 ]
There are applications not built with frame pointers, so DWARF is needed to get the stack traces.
perf record --call-graph dwarf saves the stack and register data for each sample to get the stacktrace offline. But sometimes this data may have sensitive information and we don't want to keep them in the file.
This new 'perf inject --convert-callchain' option creates the callchains and discards the stack and register after that.
This saves storage space and processing time for the new data file.
Of course, users should remove the original data file to not keep sensitive data around. :)
The down side is that it cannot handle inlined callchain entries as they all have the same IPs.
Maybe we can add an option to 'perf report' to look up inlined functions using DWARF - IIUC it doesn't require stack and register data.
This is an example.
$ perf record --call-graph dwarf -- perf test -w noploop
$ perf report --stdio --no-children --percent-limit=0 > output-prev
$ perf inject -i perf.data --convert-callchain -o perf.data.out
$ perf report --stdio --no-children --percent-limit=0 -i perf.data.out > output-next
$ diff -u output-prev output-next
...
0.23% perf ld-linux-x86-64.so.2 [.] _dl_relocate_object_no_relro
|
- ---elf_dynamic_do_Rela (inlined)
- _dl_relocate_object_no_relro
+ ---_dl_relocate_object_no_relro
_dl_relocate_object
dl_main
_dl_sysdep_start
- _dl_start_final (inlined)
_dl_start
_startStable-dep-of: 059e9100d82a ("perf event: Fix size of synthesized sample with branch stacks")
--- tools/perf/Documentation/perf-inject.txt | 5 + tools/perf/builtin-inject.c | 152 +++++++++++++++++++++++ 2 files changed, 157 insertions(+)
tools/perf/Documentation/perf-inject.txt +5 -0
@@ -109,6 +109,11 @@ include::itrace.txt[] should be used, and also --buildid-all and --switch-events may be useful. +--convert-callchain:: + Parse DWARF callchains and convert them to usual callchains. This also + discards stack and register data from the samples. This will lose + inlined callchain entries. + :GMEXAMPLECMD: inject :GMEXAMPLESUBCMD: include::guestmount.txt[]
tools/perf/builtin-inject.c +152 -0
211 lines not on this page · raw message
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 606/1611 perf event: Fix size of synthesized sample with branch stacks
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ian Rogers <[email protected]>
[ Upstream commit 059e9100d82aae2254f1b06835a55755936b1417 ]
Synthesizing branch stacks for Intel-PT highlighted an issue where PERF_SAMPLE_BRANCH_HW_INDEX was assumed to always be set in the perf_event_attr branch_sample_type. This caused an incorrect size calculation.
Fix the writing of the nr and hw_idx values during sample event synthesis by passing the branch_sample_type into the sample size and synthesis functions. Also update hardware tracers (Intel PT, ARM SPE, CS-ETM) to retrieve and pass their branch_sample_type dynamically to prevent payload misalignment.
--- tools/perf/bench/inject-buildid.c | 9 ++++++--- tools/perf/builtin-inject.c | 12 +++++++++--- tools/perf/tests/dlfilter-test.c | 8 ++++++-- tools/perf/tests/sample-parsing.c | 5 +++-- tools/perf/util/arm-spe.c | 28 ++++++++++++++++++++++++---- tools/perf/util/cs-etm.c | 28 +++++++++++++++++++++++----- tools/perf/util/intel-bts.c | 3 ++- tools/perf/util/intel-pt.c | 27 +++++++++++++++++++++++---- tools/perf/util/synthetic-events.c | 25 ++++++++++++++++++------- tools/perf/util/synthetic-events.h | 6 ++++-- 10 files changed, 118 insertions(+), 33 deletions(-)
tools/perf/bench/inject-buildid.c +6 -3
@@ -228,9 +228,12 @@ static ssize_t synthesize_sample(struct bench_data *data, struct bench_dso *dso, event.header.type =PERF_RECORD_SAMPLE ; event.header.misc =PERF_RECORD_MISC_USER ; - event.header.size =perf_event__sample_event_size (&sample, bench_sample_type,0 ); - -perf_event__synthesize_sample (&event, bench_sample_type,0 , &sample); + event.header.size =perf_event__sample_event_size (&sample, bench_sample_type, +/*read_format=*/ 0 , +/*branch_sample_type=*/ 0 ); +perf_event__synthesize_sample (&event, bench_sample_type, +/*read_format=*/ 0 , +/*branch_sample_type=*/ 0 , &sample);return writen (data->input_pipe[1 ], &event, event.header.size); }
tools/perf/builtin-inject.c +9 -3
@@ -477,8 +477,13 @@ static int perf_event__convert_sample_callchain(const struct perf_tool *tool,/* remove sample_type {STACK,REGS}_USER for synthesize */ sample_type &= ~(PERF_SAMPLE_STACK_USER |PERF_SAMPLE_REGS_USER ); -perf_event__synthesize_sample (event_copy, sample_type, - evsel->core.attr.read_format, sample); + ret =perf_event__synthesize_sample (event_copy, sample_type, + evsel->core.attr.read_format, + evsel->core.attr.branch_sample_type, sample); +if (ret) { +pr_err ("Failed to synthesize sample\n" ); +return ret; + }return perf_event__repipe_synth (tool, event_copy); }
@@ -1113,7 +1118,8 @@ static int perf_inject__sched_stat(const struct perf_tool *tool, sample_sw.period = sample->period; sample_sw.time = sample->time;perf_event__synthesize_sample (event_sw, evsel->core.attr.sample_type, - evsel->core.attr.read_format, &sample_sw); + evsel->core.attr.read_format, + evsel->core.attr.branch_sample_type, &sample_sw);build_id__mark_dso_hit (tool, event_sw, &sample_sw, evsel, machine);return perf_event__repipe (tool, event_sw, &sample_sw, machine); }
tools/perf/tests/dlfilter-test.c +6 -2
@@ -189,8 +189,12 @@ static int write_sample(struct test_data *td, u64 sample_type, u64 id, pid_t pid event->header.type =PERF_RECORD_SAMPLE ; event->header.misc =PERF_RECORD_MISC_USER ; - event->header.size =perf_event__sample_event_size (&sample, sample_type,0 ); - err =perf_event__synthesize_sample (event, sample_type,0 , &sample); + event->header.size =perf_event__sample_event_size (&sample, sample_type, +/*read_format=*/ 0 , +/*branch_sample_type=*/ 0 ); + err =perf_event__synthesize_sample (event, sample_type, +/*read_format=*/ 0 , +/*branch_sample_type=*/ 0 , &sample);if (err)return test_result ("perf_event__synthesize_sample() failed" ,TEST_FAIL );
tools/perf/tests/sample-parsing.c +3 -2
@@ -310,7 +310,8 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) sample.read.one.lost =1 ; } - sz =perf_event__sample_event_size (&sample, sample_type, read_format); + sz =perf_event__sample_event_size (&sample, sample_type, read_format, + evsel.core.attr.branch_sample_type); bufsz = sz +4096 ;/* Add a bit for overrun checking */ event =malloc (bufsz);if (!event) {
@@ -324,7 +325,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) event->header.size = sz; err =perf_event__synthesize_sample (event, sample_type, read_format, - &sample); + evsel.core.attr.branch_sample_type, &sample);if (err) {pr_debug ("%s failed for sample_type %#" PRIx64", error %d\n" ,"perf_event__synthesize_sample" , sample_type, err);
tools/perf/util/arm-spe.c +24 -4
@@ -466,10 +466,30 @@ static void arm_spe__prep_branch_stack(struct arm_spe_queue *speq) bstack->hw_idx =-1ULL ; } -static int arm_spe__inject_event (union perf_event *event,struct perf_sample *sample,u64 type) +static int arm_spe__inject_event (struct arm_spe *spe,union perf_event *event, +struct perf_sample *sample,u64 type) { - event->header.size =perf_event__sample_event_size (sample, type,0 ); -return perf_event__synthesize_sample (event, type,0 , sample); +struct evsel *evsel = sample->evsel; +u64 branch_sample_type =0 ; +size_t sz; + +if (!evsel && spe->session && spe->session->evlist) + evsel =evlist__id2evsel (spe->session->evlist, sample->id); + +if (evsel) + branch_sample_type = evsel->core.attr.branch_sample_type; + + event->header.type =PERF_RECORD_SAMPLE ; + sz =perf_event__sample_event_size (sample, type,/*read_format=*/ 0 , + branch_sample_type); +if (sz >=PERF_SAMPLE_MAX_SIZE ) { +pr_err ("Sample size %zu exceeds max size %d\n" , sz,PERF_SAMPLE_MAX_SIZE ); +return -EFAULT ; + } + event->header.size = sz; + +return perf_event__synthesize_sample (event, type,/*read_format=*/ 0 , + branch_sample_type, sample); } static inline int
@@ -481,7 +501,7 @@ arm_spe_deliver_synth_event(struct arm_spe *spe,int ret;if (spe->synth_opts.inject) { - ret =arm_spe__inject_event (event, sample, spe->sample_type); + ret =arm_spe__inject_event (spe, event, sample, spe->sample_type);if (ret)return ret; }
tools/perf/util/cs-etm.c +23 -5
@@ -1423,11 +1423,29 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq, bs->nr +=1 ; } -static int cs_etm__inject_event (union perf_event *event, +static int cs_etm__inject_event (struct cs_etm_auxtrace *etm,union perf_event *event,struct perf_sample *sample,u64 type) { - event->header.size =perf_event__sample_event_size (sample, type,0 ); -return perf_event__synthesize_sample (event, type,0 , sample); +struct evsel *evsel = sample->evsel; +u64 branch_sample_type =0 ; +size_t sz; + +if (!evsel && etm->session && etm->session->evlist) + evsel =evlist__id2evsel (etm->session->evlist, sample->id); + +if (evsel) + branch_sample_type = evsel->core.attr.branch_sample_type; + + sz =perf_event__sample_event_size (sample, type,/*read_format=*/ 0 , + branch_sample_type); +if (sz >=PERF_SAMPLE_MAX_SIZE ) { +pr_err ("Sample size %zu exceeds max size %d\n" , sz,PERF_SAMPLE_MAX_SIZE ); +return -EFAULT ; + } + event->header.size = sz; + +return perf_event__synthesize_sample (event, type,/*read_format=*/ 0 , + branch_sample_type, sample); }
@@ -1593,7 +1611,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, sample.branch_stack = tidq->last_branch;if (etm->synth_opts.inject) { - ret =cs_etm__inject_event (event, &sample, + ret =cs_etm__inject_event (etm, event, &sample, etm->instructions_sample_type);if (ret)return ret;
@@ -1668,7 +1686,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq, }if (etm->synth_opts.inject) { - ret =cs_etm__inject_event (event, &sample, + ret =cs_etm__inject_event (etm, event, &sample, etm->branches_sample_type);if (ret)return ret;
tools/perf/util/intel-bts.c +2 -1
@@ -303,7 +303,8 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq, event.sample.header.size = bts->branches_event_size; ret =perf_event__synthesize_sample (&event, bts->branches_sample_type, -0 , &sample); +/*read_format=*/ 0 ,/*branch_sample_type=*/ 0 , + &sample);if (ret)return ret; }
tools/perf/util/intel-pt.c +23 -4
@@ -1728,11 +1728,30 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt, event->sample.header.misc = sample->cpumode; } -static int intel_pt_inject_event (union perf_event *event, +static int intel_pt_inject_event (struct intel_pt *pt,union perf_event *event,struct perf_sample *sample,u64 type) { - event->header.size =perf_event__sample_event_size (sample, type,0 ); -return perf_event__synthesize_sample (event, type,0 , sample); +struct evsel *evsel = sample->evsel; +u64 branch_sample_type =0 ; +size_t sz; + +if (!evsel && pt->session && pt->session->evlist) + evsel =evlist__id2evsel (pt->session->evlist, sample->id); + +if (evsel) + branch_sample_type = evsel->core.attr.branch_sample_type; + + event->header.type =PERF_RECORD_SAMPLE ; + sz =perf_event__sample_event_size (sample, type,/*read_format=*/ 0 , + branch_sample_type); +if (sz >=PERF_SAMPLE_MAX_SIZE ) { +pr_err ("Sample size %zu exceeds max size %d\n" , sz,PERF_SAMPLE_MAX_SIZE ); +return -EFAULT ; + } + event->header.size = sz; + +return perf_event__synthesize_sample (event, type,/*read_format=*/ 0 , + branch_sample_type, sample); } static inline int intel_pt_opt_inject(struct intel_pt *pt,
@@ -1742,7 +1761,7 @@ static inline int intel_pt_opt_inject(struct intel_pt *pt,if (!pt->synth_opts.inject)return 0 ; -return intel_pt_inject_event (event, sample, type); +return intel_pt_inject_event (pt, event, sample, type); } static int intel_pt_deliver_synth_event(struct intel_pt *pt,
tools/perf/util/synthetic-events.c +18 -7
@@ -1455,7 +1455,8 @@ int perf_event__synthesize_stat_round(const struct perf_tool *tool,return process (tool, (union perf_event *) &event,NULL , machine); } -size_t perf_event__sample_event_size (const struct perf_sample *sample,u64 type,u64 read_format) +size_t perf_event__sample_event_size (const struct perf_sample *sample,u64 type,u64 read_format, +u64 branch_sample_type) {size_t sz, result =sizeof (struct perf_record_sample );
@@ -1515,8 +1516,10 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,if (type &PERF_SAMPLE_BRANCH_STACK ) { sz = sample->branch_stack->nr *sizeof (struct branch_entry ); -/* nr, hw_idx */ - sz +=2 *sizeof (u64); +/* nr */ + sz +=sizeof (u64); +if (branch_sample_type &PERF_SAMPLE_BRANCH_HW_INDEX ) + sz +=sizeof (u64); result += sz; }
@@ -1605,7 +1608,7 @@ static __u64 *copy_read_group_values(__u64 *array, __u64 read_format, }int perf_event__synthesize_sample (union perf_event *event,u64 type,u64 read_format, -const struct perf_sample *sample) +u64 branch_sample_type,const struct perf_sample *sample) {__u64 *array;size_t sz;
@@ -1719,9 +1722,17 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_foif (type &PERF_SAMPLE_BRANCH_STACK ) { sz = sample->branch_stack->nr *sizeof (struct branch_entry ); -/* nr, hw_idx */ - sz +=2 *sizeof (u64); -memcpy (array, sample->branch_stack, sz); + + *array++ = sample->branch_stack->nr; + +if (branch_sample_type &PERF_SAMPLE_BRANCH_HW_INDEX ) { +if (sample->no_hw_idx) + *array++ =0 ; +else + *array++ = sample->branch_stack->hw_idx; + } + +memcpy (array,perf_sample__branch_entries ((struct perf_sample *)sample), sz); array = (void *)array + sz; }
tools/perf/util/synthetic-events.h +4 -2
@@ -81,7 +81,8 @@ int perf_event__synthesize_mmap_events(const struct perf_tool *tool, union perf_int perf_event__synthesize_modules (const struct perf_tool *tool,perf_event__handler_t process,struct machine *machine);int perf_event__synthesize_namespaces (const struct perf_tool *tool,union perf_event *event,pid_t pid,pid_t tgid,perf_event__handler_t process,struct machine *machine);int perf_event__synthesize_cgroups (const struct perf_tool *tool,perf_event__handler_t process,struct machine *machine); -int perf_event__synthesize_sample (union perf_event *event,u64 type,u64 read_format,const struct perf_sample *sample); +int perf_event__synthesize_sample (union perf_event *event,u64 type,u64 read_format, +u64 branch_sample_type,const struct perf_sample *sample);int perf_event__synthesize_stat_config (const struct perf_tool *tool,struct perf_stat_config *config,perf_event__handler_t process,struct machine *machine);int perf_event__synthesize_stat_events (struct perf_stat_config *config,const struct perf_tool *tool,struct evlist *evlist,perf_event__handler_t process,bool attrs);int perf_event__synthesize_stat_round (const struct perf_tool *tool,u64 time,u64 type,perf_event__handler_t process,struct machine *machine);
@@ -97,7 +98,8 @@ void perf_event__synthesize_final_bpf_metadata(struct perf_session *session,int perf_tool__process_synth_event (const struct perf_tool *tool,union perf_event *event,struct machine *machine,perf_event__handler_t process); -size_t perf_event__sample_event_size (const struct perf_sample *sample,u64 type,u64 read_format); +size_t perf_event__sample_event_size (const struct perf_sample *sample,u64 type, +u64 read_format,u64 branch_sample_type); int __machine__synthesize_threads(struct machine *machine, const struct perf_tool *tool, struct target *target, struct perf_thread_map *threads,
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 607/1611 perf inject: Fix itrace branch stack synthesis
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ian Rogers <[email protected]>
[ Upstream commit daac18e7c42c012e289bfd310503f9417e4a9481 ]
When using "perf inject --itrace=L" to synthesize branch stacks from AUX data, several issues caused failures with the generated file:
1. The synthesized samples were delivered without the PERF_SAMPLE_BRANCH_STACK flag if it was not in the original event's sample_type. Fixed by using sample_type | evsel->synth_sample_type in intel_pt_do_synth_pebs_sample.
2. Modifying evsel->core.attr.sample_type early in __cmd_inject caused parse failures for subsequent records in the input file. Fixed by moving this modification to just before writing the header.
3. perf_event__repipe_sample was narrowed to only synthesize samples when branch stack injection was requested, and restored the use of perf_inject__cut_auxtrace_sample as a fallback to preserve functionality.
4. Potential Heap Overflow in perf_event__repipe_sample: Addressed by adding a check that prints an error and returns -EFAULT if the calculated event size exceeds PERF_SAMPLE_MAX_SIZE.
5. Header vs Payload Mismatch in __cmd_inject: Addressed by narrowing the condition so that HEADER_BRANCH_STACK is only set in the file header if add_last_branch was true.
6. NULL Pointer Dereference in intel-pt.c: When branch stack injection is requested (add_last_branch is true) but last_branch is false (e.g., perf inject --itrace=L), ptq->last_branch was not allocated. However, PEBS branch stack synthesis (via synth_sample_type) still forced LBR handling in do_synth_pebs_sample(), dereferencing the NULL ptq->last_branch pointer. Guarding the dereference is not sufficient because downstream sample size calculation and synthesis strictly require a non-NULL branch_stack when the bit is set. Fixed by ensuring ptq->last_branch is allocated in intel_pt_alloc_queue() when add_last_branch is requested.
7. Modifying event attributes in perf_event__repipe_attr in-place caused SIGSEGV on read-only mmap buffers in file mode and downstream parser breakage in pipe mode. Fixed by processing the unmodified attribute first, returning immediately in non-pipe mode, and correctly synthesizing a new attribute event for pipe output using perf_event__synthesize_attr. Also:
- Added a size validation check and integer underflow protection when parsing n_ids.
- Prevented Trailing ID memory corruption by zero-initializing the local attr copy and safely copying using min_t(size_t, sizeof(attr), event->attr.attr.size).
- Resolved ID array parsing mismatch downstream by expanding attr.size to sizeof(struct perf_event_attr) before synthesis to guarantee perfect header/attribute size alignment.
8. Potential dangling pointer vulnerability in perf_event__repipe_sample:
Addressed by restoring the original sample->branch_stack pointer before returning, including on early error return paths.
9. Off-by-one error in sample size check in perf_event__repipe_sample:
Fixed by checking if sz >= PERF_SAMPLE_MAX_SIZE instead of >.
10. Unadvertised size field left in payload by cut_auxtrace_sample:
Addressed by excluding the 8-byte size field from the copied payload to correctly match the cleared PERF_SAMPLE_AUX bit. Cut the AUX sample payload even if size is 0.
11. Inaccurate sample size calculation and uninitialized memory leaks in
convert_sample_callchain: Fixed by replacing manual arithmetic with perf_event__sample_event_size and adding a bounds check against PERF_SAMPLE_MAX_SIZE.
12. Omission of branch_sample_type in file headers: Addressed by expanding older, smaller attributes to PERF_ATTR_SIZE_VER2 in __cmd_inject to ensure branch_sample_type is not silently omitted.
--- tools/perf/builtin-inject.c | 153 ++++++++++++++++++++++++++++++++---- tools/perf/util/intel-pt.c | 8 +- 2 files changed, 142 insertions(+), 19 deletions(-)
tools/perf/builtin-inject.c +137 -16
@@ -213,12 +213,23 @@ static int perf_event__repipe_op4_synth(struct perf_session *session,return perf_event__repipe_synth (session->tool, event); } +static int perf_event__repipe_synth_cb (const struct perf_tool *tool, +union perf_event *event, +struct perf_sample *sample__maybe_unused , +struct machine *machine__maybe_unused ) +{ +return perf_event__repipe_synth (tool, event); +} +static int perf_event__repipe_attr (const struct perf_tool *tool,union perf_event *event,struct evlist **pevlist) { struct perf_inject *inject = container_of(tool, struct perf_inject, tool); +struct perf_event_attr attr; +size_t n_ids; +u64 *ids;int ret; ret =perf_event__process_attr (tool, event, pevlist);
@@ -229,7 +240,37 @@ static int perf_event__repipe_attr(const struct perf_tool *tool,if (!inject->output.is_pipe)return 0 ; -return perf_event__repipe_synth (tool, event); +if (!inject->itrace_synth_opts.set) +return perf_event__repipe_synth (tool, event); + +if (event->header.size <sizeof (struct perf_event_header ) +sizeof (u64)) { +pr_err ("Attribute event size %u is too small\n" , event->header.size); +return -EINVAL ; + } + +if (event->header.size -sizeof (event->header) < event->attr.attr.size) { +pr_err ("Attribute event size %u is too small for attr.size %u\n" , + event->header.size, event->attr.attr.size); +return -EINVAL ; + } + +memset (&attr,0 ,sizeof (attr)); +memcpy (&attr, &event->attr.attr, +min_t (size_t,sizeof (attr), (size_t )event->attr.attr.size)); + + n_ids = event->header.size -sizeof (event->header) - event->attr.attr.size; + n_ids /=sizeof (u64); + ids =perf_record_header_attr_id (event); + + attr.size =sizeof (struct perf_event_attr ); + attr.sample_type &= ~PERF_SAMPLE_AUX ; + +if (inject->itrace_synth_opts.add_last_branch) { + attr.sample_type |=PERF_SAMPLE_BRANCH_STACK ; + attr.branch_sample_type |=PERF_SAMPLE_BRANCH_HW_INDEX ; + } +return perf_event__synthesize_attr (tool, &attr, (u32 )n_ids, ids, + perf_event__repipe_synth_cb); } static int perf_event__repipe_event_update(const struct perf_tool *tool,
@@ -344,8 +385,8 @@ perf_inject__cut_auxtrace_sample(struct perf_inject *inject,union perf_event *event, struct perf_sample *sample) { - size_t sz1 = sample->aux_sample.data - (void *)event; -size_t sz2 = event->header.size - sample->aux_sample.size - sz1; + size_t sz1 = sample->aux_sample.data - (void *)event - sizeof(u64); +size_t sz2 = event->header.size - sample->aux_sample.size - (sz1 +sizeof (u64));union perf_event *ev;if (inject->event_copy ==NULL ) {
@@ -356,13 +397,12 @@ perf_inject__cut_auxtrace_sample(struct perf_inject *inject, ev = (union perf_event *)inject->event_copy;if (sz1 > event->header.size || sz2 > event->header.size || sz1 + sz2 > event->header.size || - sz1 <sizeof (struct perf_event_header ) +sizeof (u64)) + sz1 <sizeof (struct perf_event_header ))return event;memcpy (ev, event, sz1);memcpy ((void *)ev + sz1, (void *)event + event->header.size - sz2, sz2); ev->header.size = sz1 + sz2; - ((u64 *)((void *)ev + sz1))[-1 ] =0 ;return ev; }
@@ -382,14 +422,77 @@ static int perf_event__repipe_sample(const struct perf_tool *tool, struct perf_inject *inject = container_of(tool, struct perf_inject, tool); -if (evsel && evsel->handler) { +if (evsel ==NULL ) +return perf_event__repipe_synth (tool, event); + +if (evsel->handler) {inject_handler f = evsel->handler;return f (tool, event, sample, evsel, machine); }build_id__mark_dso_hit (tool, event, sample, evsel, machine); -if (inject->itrace_synth_opts.set && sample->aux_sample.size) { +if (inject->itrace_synth_opts.set && + (inject->itrace_synth_opts.last_branch || + inject->itrace_synth_opts.add_last_branch)) { +union perf_event *event_copy = (void *)inject->event_copy; +struct branch_stack dummy_bs = { .nr =0 , .hw_idx =0 }; +int err; +size_t sz; +u64 orig_type = evsel->core.attr.sample_type; +u64 orig_branch_type = evsel->core.attr.branch_sample_type; + +struct branch_stack *orig_bs = sample->branch_stack; + +if (event_copy ==NULL ) { + inject->event_copy =malloc (PERF_SAMPLE_MAX_SIZE ); +if (!inject->event_copy) +return -ENOMEM ; + + event_copy = (void *)inject->event_copy; + } + +if (!sample->branch_stack) + sample->branch_stack = &dummy_bs; + +if (inject->itrace_synth_opts.add_last_branch) { +/* Temporarily add in type bits for synthesis. */ + evsel->core.attr.sample_type |=PERF_SAMPLE_BRANCH_STACK ; + evsel->core.attr.branch_sample_type |=PERF_SAMPLE_BRANCH_HW_INDEX ; + } + evsel->core.attr.sample_type &= ~PERF_SAMPLE_AUX ; + + sz =perf_event__sample_event_size (sample, evsel->core.attr.sample_type, + evsel->core.attr.read_format, + evsel->core.attr.branch_sample_type); + +if (sz >=PERF_SAMPLE_MAX_SIZE ) { +pr_err ("Sample size %zu exceeds max size %d\n" , sz,PERF_SAMPLE_MAX_SIZE ); + evsel->core.attr.sample_type = orig_type; + evsel->core.attr.branch_sample_type = orig_branch_type; + sample->branch_stack = orig_bs; +return -EFAULT ; + } + + event_copy->header.type =PERF_RECORD_SAMPLE ; + event_copy->header.misc = event->header.misc; + event_copy->header.size = sz; + + err =perf_event__synthesize_sample (event_copy, evsel->core.attr.sample_type, + evsel->core.attr.read_format, + evsel->core.attr.branch_sample_type, sample); + + evsel->core.attr.sample_type = orig_type; + evsel->core.attr.branch_sample_type = orig_branch_type; + sample->branch_stack = orig_bs; + +if (err) { +pr_err ("Failed to synthesize sample\n" ); +return err; + } + event = event_copy; + }else if (inject->itrace_synth_opts.set && + (evsel->core.attr.sample_type &PERF_SAMPLE_AUX )) { event =perf_inject__cut_auxtrace_sample (inject, event, sample);if (IS_ERR (event))return PTR_ERR (event);
@@ -410,7 +513,7 @@ static int perf_event__convert_sample_callchain(const struct perf_tool *tool,struct callchain_cursor_node *node;struct thread *thread;u64 sample_type = evsel->core.attr.sample_type; -u32 sample_size = event->header.size; +size_t sz;u64 i, k;int ret;
@@ -468,15 +571,18 @@ static int perf_event__convert_sample_callchain(const struct perf_tool *tool, out:memcpy (event_copy, event,sizeof (event->header)); -/* adjust sample size for stack and regs */ - sample_size -= sample->user_stack.size; - sample_size -= (hweight64 (evsel->core.attr.sample_regs_user) +1 ) *sizeof (u64); - sample_size += (sample->callchain->nr +1 ) *sizeof (u64); - event_copy->header.size = sample_size; -/* remove sample_type {STACK,REGS}_USER for synthesize */ sample_type &= ~(PERF_SAMPLE_STACK_USER |PERF_SAMPLE_REGS_USER ); + sz =perf_event__sample_event_size (sample, sample_type, + evsel->core.attr.read_format, + evsel->core.attr.branch_sample_type); +if (sz >=PERF_SAMPLE_MAX_SIZE ) { +pr_err ("Sample size %zu exceeds max size %d\n" , sz,PERF_SAMPLE_MAX_SIZE ); +return -EFAULT ; + } + event_copy->header.size = sz; + ret =perf_event__synthesize_sample (event_copy, sample_type, evsel->core.attr.read_format, evsel->core.attr.branch_sample_type, sample);
@@ -2426,12 +2532,27 @@ static int __cmd_inject(struct perf_inject *inject)* synthesized hardware events, so clear the feature flag. */ if (inject->itrace_synth_opts.set) { +struct evsel *evsel; +perf_header__clear_feat (&session->header,HEADER_AUXTRACE ); -if (inject->itrace_synth_opts.last_branch || - inject->itrace_synth_opts.add_last_branch) + +evlist__for_each_entry (session->evlist, evsel) { + evsel->core.attr.sample_type &= ~PERF_SAMPLE_AUX ; + } + +if (inject->itrace_synth_opts.add_last_branch) {perf_header__set_feat (&session->header,HEADER_BRANCH_STACK ); + +evlist__for_each_entry (session->evlist, evsel) { + evsel->core.attr.sample_type |=PERF_SAMPLE_BRANCH_STACK ; +if (evsel->core.attr.size <PERF_ATTR_SIZE_VER2 ) + evsel->core.attr.size =PERF_ATTR_SIZE_VER2 ; + evsel->core.attr.branch_sample_type |= +PERF_SAMPLE_BRANCH_HW_INDEX ; + } + } }/*
tools/perf/util/intel-pt.c +5 -3
@@ -1307,7 +1307,8 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, goto out_free; } -if (pt->synth_opts.last_branch || pt->synth_opts.other_events) { +if (pt->synth_opts.last_branch || pt->synth_opts.add_last_branch || + pt->synth_opts.other_events) {unsigned int entry_cnt =max (LBRS_MAX , pt->br_stack_sz); ptq->last_branch =intel_pt_alloc_br_stack (entry_cnt);
@@ -2505,7 +2506,7 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evseintel_pt_add_xmm (intr_regs, pos, items, regs_mask); } -if (sample_type &PERF_SAMPLE_BRANCH_STACK ) { +if ((sample_type | evsel->synth_sample_type) &PERF_SAMPLE_BRANCH_STACK ) {if (items->mask[INTEL_PT_LBR_0_POS ] || items->mask[INTEL_PT_LBR_1_POS ] || items->mask[INTEL_PT_LBR_2_POS ]) {
@@ -2576,7 +2577,8 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse sample.transaction = txn; } - ret =intel_pt_deliver_synth_event (pt, event, &sample, sample_type); + ret =intel_pt_deliver_synth_event (pt, event, &sample, + sample_type | evsel->synth_sample_type);perf_sample__exit (&sample);return ret; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 608/1611 staging: most: video: avoid double free on video register failure
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Guangshuo Li <[email protected]>
[ Upstream commit 7cb1c5b32a2bfde961fff8d5204526b609bcb30a ]
comp_register_videodev() allocates a video_device with video_device_alloc() and releases it if video_register_device() fails.
This can double free the video_device when __video_register_device() reaches device_register() and that call fails:
video_register_device()
-> __video_register_device()
-> device_register() fails
-> put_device(&vdev->dev)
-> v4l2_device_release()
-> vdev->release(vdev)
-> video_device_release(vdev) comp_register_videodev()
-> video_device_release(mdev->vdev)
Use video_device_release_empty() while registering the device so that registration failure paths do not free mdev->vdev through vdev->release(). comp_register_videodev() then releases mdev->vdev exactly once on failure. Restore video_device_release() after successful registration so the registered device keeps its normal lifetime handling.
This issue was found by a static analysis tool I am developing.
--- drivers/staging/most/video/video.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/staging/most/video/video.c +6 -1
@@ -418,6 +418,7 @@ static int comp_register_videodev(struct most_video_dev *mdev)/* Fill the video capture device struct */ *mdev->vdev = comp_videodev_template; + mdev->vdev->release = video_device_release_empty; mdev->vdev->v4l2_dev = &mdev->v4l2_dev; mdev->vdev->lock = &mdev->lock; snprintf(mdev->vdev->name, sizeof(mdev->vdev->name), "MOST: %s",
@@ -430,9 +431,13 @@ static int comp_register_videodev(struct most_video_dev *mdev)v4l2_err (&mdev->v4l2_dev,"video_register_device failed (%d)\n" , ret);video_device_release (mdev->vdev); +return ret; } -return ret; + mdev->vdev->release = video_device_release; + +return 0 ; + }static void comp_unregister_videodev (struct most_video_dev *mdev)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 609/1611 usb: host: max3421: Fix shift-out-of-bounds in max3421_hub_control()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Seungjin Bae <[email protected]>
[ Upstream commit cff06b03b530ae1fe8a13e93a7848f2130e00fb4 ]
The max3421_hub_control() function handles USB hub class requests to the virtual root hub. In the default branches of both the ClearPortFeature and SetPortFeature switch statements, it modifies max3421_hcd->port_status by left shifting 1 by the request's value parameter. However, it does not validate whether this shift will exceed the width of port_status.
So if a malicious userspace task with access to the root hub via /dev/bus/usb/.../001 issues a USBDEVFS_CONTROL ioctl with wValue greater than or equal to 32, the left shift operation invokes shift-out-of-bounds undefined behavior. This results in arbitrary bit corruption of port_status, including the normally-immutable change bits, which can bypass internal state checks and confuse the hub status.
Fix this by rejecting requests whose value exceeds the shift width before performing the shift.
This issue was found using a KLEE-based symbolic execution tool for kernel drivers that I'm currently developing.
--- drivers/usb/host/max3421-hcd.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/usb/host/max3421-hcd.c +4 -0
@@ -1694,6 +1694,8 @@ max3421_hub_control(struct usb_hcd *hcd, u16 type_req, u16 value, u16 index, !pdata->vbus_active_level); fallthrough;default : +if (value >=32 ) + goto error; max3421_hcd->port_status &= ~(1 << value); }break ;
@@ -1747,6 +1749,8 @@ max3421_hub_control(struct usb_hcd *hcd, u16 type_req, u16 value, u16 index,max3421_reset_port (hcd); fallthrough;default : +if (value >=32 ) + goto error;if ((max3421_hcd->port_status &USB_PORT_STAT_POWER ) !=0 ) max3421_hcd->port_status |= (1 << value);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 610/1611 usb: host: max3421: Reject hub port requests for non-existent ports
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Seungjin Bae <[email protected]>
[ Upstream commit 11b5c101e2fd206104b05bc92554d356989423a8 ]
The max3421_hub_control() function handles USB hub class requests to the virtual root hub. The GetPortStatus case correctly rejects requests with index != 1, since the virtual root hub has only a single port. However, the ClearPortFeature and SetPortFeature cases lack the same check.
Fix this by extending the index != 1 rejection to both cases, matching the existing behavior of GetPortStatus.
--- drivers/usb/host/max3421-hcd.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/usb/host/max3421-hcd.c +4 -0
@@ -1685,6 +1685,8 @@ max3421_hub_control(struct usb_hcd *hcd, u16 type_req, u16 value, u16 index,case ClearHubFeature:break ;case ClearPortFeature: +if (index !=1 ) + goto error;switch (value) {case USB_PORT_FEAT_SUSPEND :break ;
@@ -1728,6 +1730,8 @@ max3421_hub_control(struct usb_hcd *hcd, u16 type_req, u16 value, u16 index,break ;case SetPortFeature: +if (index !=1 ) + goto error;switch (value) {case USB_PORT_FEAT_LINK_STATE :case USB_PORT_FEAT_U1_TIMEOUT :
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 611/1611 perf test amd ibs: Fix incorrect kernel version check
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ravi Bangoria <[email protected]>
[ Upstream commit 0b97e92393a178765ee1ea01fe5087efece2c425 ]
"AMD IBS sample period" unit test is getting skipped on kernel v7.x. Fix the kernel version >= v6.15 check.
--- tools/perf/arch/x86/tests/amd-ibs-period.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/arch/x86/tests/amd-ibs-period.c +1 -1
@@ -933,7 +933,7 @@ static bool kernel_v6_15_or_newer(void) endptr++; minor =strtol (endptr,NULL ,10 ); -return major >=6 && minor >=15 ; +return major >6 || (major ==6 && minor >=15 ); } int test__amd_ibs_period(struct test_suite *test __maybe_unused,
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 612/1611 gpib: Fix inappropriate ioctl error return
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dave Penkler <[email protected]>
[ Upstream commit 70ea440324e8c1a10837f721352f5bd469c85007 ]
The driver was returning -ENOTTY in the case the ioctl command was not recognised. Change it to -EBADRQC.
--- drivers/staging/gpib/common/gpib_os.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/staging/gpib/common/gpib_os.c +1 -2
@@ -613,7 +613,7 @@ long ibioctl(struct file *filep, unsigned int cmd, unsigned long arg)unsigned int minor =iminor (file_inode (filep));struct gpib_board *board;struct gpib_file_private *file_priv = filep->private_data; -long retval = -ENOTTY ; +long retval = -EBADRQC ;if (minor >=GPIB_MAX_NUM_BOARDS ) {pr_err ("gpib: invalid minor number of device file\n" );
@@ -806,7 +806,6 @@ long ibioctl(struct file *filep, unsigned int cmd, unsigned long arg)mutex_unlock (&board->big_gpib_mutex);return write_ioctl (file_priv, board, arg);default : - retval = -ENOTTY ; goto done; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 613/1611 char: tlclk: fix use-after-free in tlclk_cleanup()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: James Kim <[email protected]>
[ Upstream commit bbf003b7794d6ad6f939fdd29f1f1bde8ac554c1 ]
This patch improves the module cleanup process in the tlclk driver to prevent potential use-after-free and race conditions.
Currently, the file_operations structure does not specify the .owner field, which could allow the module to be unloaded while user-space processes are still interacting with the device. Additionally, the tlclk_cleanup() function frees the alarm_events memory before ensuring that blocked processes in the waitqueue are fully awakened and that the switchover_timer has completed.
To address these cases, this patch:
- Sets '.owner = THIS_MODULE' in tlclk_fops to safely defer module unloading while the device is in use.
- Updates tlclk_cleanup() to explicitly wake up all blocked readers (wake_up_all), properly release hardware I/O regions, and safely delete the timer (timer_delete_sync) prior to freeing memory.
--- drivers/char/tlclk.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/char/tlclk.c +4 -0
@@ -264,6 +264,7 @@ static ssize_t tlclk_read(struct file *filp, char __user *buf, size_t count, }static const struct file_operations tlclk_fops = { + .owner =THIS_MODULE , .read = tlclk_read, .open = tlclk_open, .release = tlclk_release,
@@ -837,6 +838,9 @@ static void __exit tlclk_cleanup(void)misc_deregister (&tlclk_miscdev);unregister_chrdev (tlclk_major,"telco_clock" ); + got_event =1 ; +wake_up_all (&wq); +release_region (TLCLK_BASE ,8 );timer_delete_sync (&switchover_timer);kfree (alarm_events);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 614/1611 gpib: fix double decrement of descriptor_busy in command_ioctl()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Adam Crosser <[email protected]>
[ Upstream commit c4faab452b3c1ada003d49c477609dd80523b9bf ]
commit d1857f8296dc ("gpib: fix use-after-free in IO ioctl handlers") introduced a descriptor_busy reference counter to pin struct gpib_descriptor across IO ioctl operations. In command_ioctl(), the error path inside the loop decrements descriptor_busy and breaks, but execution then falls through to the unconditional decrement after the loop, underflowing the counter to -1.
This re-enables the use-after-free that the original fix was meant to
prevent: a concurrent close_dev_ioctl() sees descriptor_busy == 0 on an actively-used descriptor and frees it.
Remove the early decrement from the error path. The post-loop decrement already handles all exit paths, matching the correct pattern used in read_ioctl() and write_ioctl().
--- drivers/staging/gpib/common/gpib_os.c | 1 - 1 file changed, 1 deletion(-)
drivers/staging/gpib/common/gpib_os.c +0 -1
@@ -1017,7 +1017,6 @@ static int command_ioctl(struct gpib_file_private *file_priv, userbuf += bytes_written;if (retval <0 ) {atomic_set (&desc->io_in_progress,0 ); -atomic_dec (&desc->descriptor_busy);wake_up_interruptible (&board->wait);break ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 615/1611 gpib: cb7210: Fix region leak when request_irq fails
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hongling Zeng <[email protected]>
[ Upstream commit 2eae90a457baa0048a96ed38ad93090ee38c8b2f ]
When request_irq() fails, the region allocated by request_region() is not released. Fix this by adding an error handling path with proper goto labels to release the region.
Stable-dep-of: 5ad284960558 ("gpib: cb7210: Fix region leak when request_irq fails")
--- drivers/staging/gpib/cb7210/cb7210.c | 1 + 1 file changed, 1 insertion(+)
drivers/staging/gpib/cb7210/cb7210.c +1 -0
@@ -1061,6 +1061,7 @@ static int cb_isa_attach(struct gpib_board *board, const struct gpib_board_confi// install interrupt handler if (request_irq (config->ibirq, cb7210_interrupt, isr_flags,DRV_NAME , board)) {dev_err (board->gpib_dev,"failed to obtain IRQ %d\n" , config->ibirq); +release_region (nec7210_iobase (cb_priv), cb7210_iosize);return -EBUSY ; } cb_priv->irq = config->ibirq;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 616/1611 clk: renesas: rzg2l: Rename iterator in for_each_mod_clock() to avoid shadowing
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lad Prabhakar <[email protected]>
[ Upstream commit 1f10c4509649e7c5f6d5d3acccf3ef6fbb5cdd46 ]
Rename the internal loop iterator variable in the for_each_mod_clock() macro from 'i' to '__i'.
The current naming conflicts with local loop variables named 'i' inside code blocks that utilize the macro, triggering compiler warnings due to variable shadowing:
drivers/clk/renesas/rzg2l-cpg.c:1494:36: warning: declaration of i shadows a previous local [-Wshadow]
1494 | for (unsigned int i = 0; i < clk->num_shared_mstop_clks; i++)
Using a unique identifier for the macro-internal iterator resolves the shadowing warnings globally across all macro expansions.
--- drivers/clk/renesas/rzg2l-cpg.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/clk/renesas/rzg2l-cpg.c +3 -3
@@ -1228,10 +1228,10 @@ struct mod_clock {#define to_mod_clock (_hw) container_of(_hw, struct mod_clock, hw)#define for_each_mod_clock (mod_clock, hw, priv) \ - for (unsigned int i = 0; (priv) && i < (priv)->num_mod_clks; i++) \ - if ((priv)->clks[(priv)->num_core_clks + i] == ERR_PTR(-ENOENT)) \ + for (unsigned int __i = 0; (priv) && __i < (priv)->num_mod_clks; __i++) \ + if ((priv)->clks[(priv)->num_core_clks + __i] == ERR_PTR(-ENOENT)) \ continue; \ - else if (((hw) = __clk_get_hw((priv)->clks[(priv)->num_core_clks + i])) && \ + else if (((hw) = __clk_get_hw((priv)->clks[(priv)->num_core_clks + __i])) && \ ((mod_clock) = to_mod_clock(hw)))/* Need to be called with a lock held to avoid concurrent access to mstop->usecnt. */
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 617/1611 powerpc tools perf: Initialize error code in auxtrace_record_init function
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Athira Rajeev <[email protected]>
[ Upstream commit 789d22d77879eabb042627f6627cdb62787bc142 ]
perf trace record fails some cases in powerpc
# perf test "perf trace record and replay" 128: perf trace record and replay : FAILED!
# perf trace record sleep 1
# echo $?
32This is happening because of non-zero err value from auxtrace_record__init() function.
static int record__auxtrace_init(struct record *rec)
{
int err;
if ((rec->opts.auxtrace_snapshot_opts || rec->opts.auxtrace_sample_opts)
&& record__threads_enabled(rec)) {
pr_err("AUX area tracing options are not available in parallel streaming mode.\n");
return -EINVAL;
}
if (!rec->itr) {
rec->itr = auxtrace_record__init(rec->evlist, &err);
if (err)
return err;
}Here "int err" is not initialised. The code expects "err" to be set from auxtrace_record__init() function.
Update auxtrace_record__init() in arch/powerpc/util/auxtrace.c to clear err value in the beginning.
- Clear err value in beginning of function. Any fail later will set appropriate return code to err.
- Even if we haven't found any event for auxtrace, perf record should continue for other events. NULL return
will indicate that there is no auxtrace record initialized.
- Not having "err" set here will affect monitoring of other events also because perf record will fail seeing random value in err.
Set err to -EINVAL before invoking auxtrace_record__init() in builtin-record.c
With the fix,
# perf trace record sleep 1 [ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.033 MB perf.data (228 samples) ]
--- tools/perf/arch/powerpc/util/auxtrace.c | 6 ++++++ tools/perf/builtin-record.c | 1 + 2 files changed, 7 insertions(+)
tools/perf/arch/powerpc/util/auxtrace.c +6 -0
@@ -70,6 +70,12 @@ struct auxtrace_record *auxtrace_record__init(struct evlist *evlist,struct evsel *pos;int found =0 ; +/* +* Set err value to zero here. Any fail later +* will set appropriate return code to err. +*/ + *err =0 ; +evlist__for_each_entry (evlist, pos) {if (strstarts (pos->name,"vpa_dtl" )) { found =1 ;
tools/perf/builtin-record.c +1 -0
@@ -867,6 +867,7 @@ static int record__auxtrace_init(struct record *rec) }if (!rec->itr) { + err = -EINVAL ; rec->itr =auxtrace_record__init (rec->evlist, &err);if (err)return err;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 618/1611 PCI: qcom: Disable ASPM L0s for SA8775P
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Shawn Guo <[email protected]>
[ Upstream commit 29f692985819f4089f02a86e151a72f6d4cdd90d ]
Due to a hardware issue, L0s is not properly supported by the PCIe controller on the SA8775p SoC. If enabled, the L0s to L0 transition triggers below correctable AER errors and may also affect link stability:
pcieport 0000:00:00.0: PME: Signaling with IRQ 332
pcieport 0000:00:00.0: AER: enabled with IRQ 332
pcieport 0000:00:00.0: AER: Correctable error message received from 0000:01:00.0 pci 0000:01:00.0: PCIe Bus Error: severity=Correctable, type=Data Link Layer, (Transmitter ID)
pci 0000:01:00.0: device [17cb:1103] error status/mask=00001000/0000e000
pci 0000:01:00.0: [12] Timeout
pcieport 0000:00:00.0: AER: Multiple Correctable error message received from 0000:01:00.0 pcieport 0000:00:00.0: PCIe Bus Error: severity=Correctable, type=Data Link Layer, (Transmitter ID)
pcieport 0000:00:00.0: device [17cb:0115] error status/mask=00001000/0000e000
pcieport 0000:00:00.0: [12] Timeout
Hence, disable L0s for the SA8775p SoC to allow it to properly function by sacrificing a little bit of power saving.
--- drivers/pci/controller/dwc/pcie-qcom.c | 1 + 1 file changed, 1 insertion(+)
drivers/pci/controller/dwc/pcie-qcom.c +1 -0
@@ -1438,6 +1438,7 @@ static const struct qcom_pcie_cfg cfg_1_9_0 = {static const struct qcom_pcie_cfg cfg_1_34_0 = { .ops = &ops_1_9_0, .override_no_snoop = true, + .no_l0s = true, };static const struct qcom_pcie_cfg cfg_2_1_0 = {
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 619/1611 perf header: Sanity check HEADER_EVENT_DESC attr.size before swap
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 944f65c8b8231d26d4db6be67bcb641142603cb4 ]
read_event_desc() reads nre (event count), sz (attr size), and nr (IDs per event) from the file and uses them to control allocations and loops without validating them against the section size.
A crafted perf.data could trigger large allocations or many loop iterations before __do_read() eventually rejects the reads.
Add bounds checks in read_event_desc():
- Reject sz smaller than PERF_ATTR_SIZE_VER0.
- Require at least one event (nre > 0).
- Check that nre events fit in the remaining section, using the minimum per-event footprint of sz + sizeof(u32).
- Pre-swap attr->size to native byte order, then reject values below PERF_ATTR_SIZE_VER0 or above sz before calling perf_event__attr_swap() to prevent heap out-of-bounds access.
- Handle ABI0 (attr.size == 0): substitute PERF_ATTR_SIZE_VER0, and on native-endian files write the value back so free_event_desc() does not treat the zero as its end-of-array sentinel (it iterates while attr.size != 0). The swap path skips the write-back — perf_event__attr_swap() has its own ABI0 fallback that sets VER0 after swapping.
- Check that nr IDs fit in the remaining section before allocating.
--- tools/perf/util/header.c | 54 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+)
tools/perf/util/header.c +54 -0
@@ -1919,9 +1919,28 @@ static struct evsel *read_event_desc(struct feat_fd *ff)if (do_read_u32 (ff, &nre)) goto error; +/* Size of each of the nre attributes. */ if (do_read_u32 (ff, &sz)) goto error; +/* +* Require at least one event with an attr no smaller than the +* first published struct, and reject sz values where +* sz + sizeof(u32) would overflow size_t (possible on 32-bit) +* or nre == UINT32_MAX where nre + 1 wraps to 0 in the calloc. +* +* The minimum section footprint per event is sz bytes for the +* attr plus a u32 for the id count, check that nre events fit. +*/ +if (!nre || sz <PERF_ATTR_SIZE_VER0 || + sz > ff->size || (size_t )sz >SIZE_MAX -sizeof (u32) || + nre ==UINT32_MAX || + nre > (ff->size - ff->offset) / (sz +sizeof (u32))) { +pr_err ("Invalid HEADER_EVENT_DESC: nre=%u sz=%u (min %d)\n" , + nre, sz,PERF_ATTR_SIZE_VER0 ); + goto error; + } +/* buffer to hold on file attr struct */ buf =malloc (sz);if (!buf)
@@ -1937,6 +1956,9 @@ static struct evsel *read_event_desc(struct feat_fd *ff) msz = sz;for (i =0 , evsel = events; i < nre; evsel++, i++) { +struct perf_event_attr *attr = buf; +u32 attr_size; + evsel->core.idx = i;/*
@@ -1946,6 +1968,32 @@ static struct evsel *read_event_desc(struct feat_fd *ff)if (__do_read (ff, buf, sz)) goto error; +/* Reject before attr_swap to prevent OOB via bswap_safe() */ + attr_size = ff->ph->needs_swap ?bswap_32 (attr->size) : attr->size; +/* ABI0: size == 0 means the producer didn't set it */ +if (!attr_size) { + attr_size =PERF_ATTR_SIZE_VER0 ; +/* +* Write back so free_event_desc() doesn't +* treat this event as the end-of-array sentinel +* (it iterates while attr.size != 0). +* +* Only for native — the swap path must NOT +* write native-endian VER0 here because +* perf_event__attr_swap() would re-swap it +* to 0x40000000, defeating bswap_safe() bounds. +* perf_event__attr_swap() has its own ABI0 +* fallback that sets VER0 after swapping. +*/ +if (!ff->ph->needs_swap) + attr->size = attr_size; + } +if (attr_size <PERF_ATTR_SIZE_VER0 || attr_size > sz) { +pr_err ("Event %d attr.size (%u) invalid (min: %d, max: %u)\n" , + i, attr_size,PERF_ATTR_SIZE_VER0 , sz); + goto error; + } +if (ff->ph->needs_swap)perf_event__attr_swap (buf);
@@ -1967,6 +2015,12 @@ static struct evsel *read_event_desc(struct feat_fd *ff)if (!nr)continue ; +/* Prevent oversized allocation from crafted nr */ +if (nr > (ff->size - ff->offset) /sizeof (*id)) { +pr_err ("Event %d: id count %u exceeds remaining section\n" , i, nr); + goto error; + } + id =calloc (nr,sizeof (*id));if (!id) goto error;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 620/1611 iio: light: si1133: reset counter to prevent race condition
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Joshua Crofts <[email protected]>
[ Upstream commit 0a5f45ed2342aabae1e32c72558d15be28940a95 ]
Sashiko reported a potential race condition happening when the driver returns an errno after a timeout in the si1133_command() function. The premature exit causes the hardware and software counters to become out of sync by not updating data->rsp_seq, therefore the internal hardware counter keeps incrementing.
Fix this by adding a call to si1133_cmd_reset_counter() before returning from timeout.
--- drivers/iio/light/si1133.c | 5 +++++ 1 file changed, 5 insertions(+)
drivers/iio/light/si1133.c +5 -0
@@ -427,6 +427,11 @@ static int si1133_command(struct si1133_data *data, u8 cmd)dev_warn (dev,"Failed to read command 0x%02x, ret=%d\n" , cmd, err); +/* +* Reset counter on err to prevent software and hardware +* counters being out of sync. +*/ +si1133_cmd_reset_counter (data); goto out; } }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 621/1611 iio: light: si1133: prevent race condition on timeout
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Joshua Crofts <[email protected]>
[ Upstream commit 8c50a95ceb230d17801758a9e41ffbbbe46f8b4d ]
Sashiko reported a bug where the si1133_command exits on timeout without halting the sensor or masking the interrupt. If the sensor completes the command later, any subsequent command to the sensor will cause the IRQ handler to complete immediately, returning stale data to the driver all while the command hasn't finished yet, shifting all potential reads in the future.
Fix this by masking the IRQ if wait_for_completion_timeout() fails. When initiating a new command, do a dummy read of the IRQ_STATUS register and turn the IRQ back on.
--- drivers/iio/light/si1133.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
drivers/iio/light/si1133.c +8 -1
@@ -395,8 +395,14 @@ static int si1133_command(struct si1133_data *data, u8 cmd) expected_seq = (data->rsp_seq +1 ) &SI1133_MAX_CMD_CTR ; -if (cmd ==SI1133_CMD_FORCE ) +if (cmd ==SI1133_CMD_FORCE ) { +/* Flush pending IRQs from a previous timeout. */ +regmap_read (data->regmap,SI1133_REG_IRQ_STATUS , &resp); +regmap_write (data->regmap,SI1133_REG_IRQ_ENABLE , +SI1133_IRQ_CHANNEL_ENABLE ); +reinit_completion (&data->completion); + } err =regmap_write (data->regmap,SI1133_REG_COMMAND , cmd);if (err) {
@@ -409,6 +415,7 @@ static int si1133_command(struct si1133_data *data, u8 cmd)/* wait for irq */ if (!wait_for_completion_timeout (&data->completion,msecs_to_jiffies (SI1133_COMPLETION_TIMEOUT_MS ))) { +regmap_write (data->regmap,SI1133_REG_IRQ_ENABLE ,0 ); err = -ETIMEDOUT ; goto out; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 622/1611 iio: magnetometer: ak8975: fix potential kernel stack memory leak
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Joshua Crofts <[email protected]>
[ Upstream commit a9a00d727b7bbc5e913a919530a9dd468935bf95 ]
Currently in the AK8975 driver there are four instances where potential uninitialized kernel stack memory leaks can occur. If i2c_smbus_read_i2c_block_data_or_emulated() returns a value less than the size of the buffer, uninitialized bytes are retained in the buffer and later the buffer is passed on to IIO buffers, potentially leaking memory to userspace.
Fix this by adding checks whether the return value of the function is equal to the size of the buffer and subsequently if the value is lesser than zero to distinguish from a returned error code.
--- drivers/iio/magnetometer/ak8975.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)
drivers/iio/magnetometer/ak8975.c +14 -0
@@ -495,6 +495,10 @@ static int ak8975_who_i_am(struct i2c_client *client,dev_err (&client->dev,"Error reading WIA\n" );return ret; } +if (ret !=sizeof (wia_val)) { +dev_err (&client->dev,"Error reading WIA\n" ); +return -EIO ; + }if (wia_val[0 ] !=AK8975_DEVICE_ID )return -ENODEV ;
@@ -619,6 +623,10 @@ static int ak8975_setup(struct i2c_client *client)dev_err (&client->dev,"Not able to read asa data\n" );return ret; } +if (ret !=sizeof (data->asa)) { +dev_err (&client->dev,"Error reading asa data\n" ); +return -EIO ; + }/* After reading fuse ROM data set power-down mode */ ret =ak8975_set_mode (data,POWER_DOWN );
@@ -758,6 +766,10 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val) sizeof(rval), (u8*)&rval);if (ret <0 ) goto exit; +if (ret !=sizeof (rval)) { + ret = -EIO ; + goto exit; + }/* Read out ST2 for release lock on measurment data. */ ret =i2c_smbus_read_byte_data (client, data->def->ctrl_regs[ST2 ]);
@@ -874,6 +886,8 @@ static void ak8975_fill_buffer(struct iio_dev *indio_dev) (u8 *)fval);if (ret <0 ) goto unlock; +if (ret !=sizeof (fval)) + goto unlock;mutex_unlock (&data->lock);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 623/1611 iio: adc: xilinx-ams: fix out-of-bounds channel lookup in event handling
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Guilherme Ivo Bozi <[email protected]>
[ Upstream commit 947eb6f0a274f8b15a0248051a65b069effd5057 ]
ams_event_to_channel() may return a pointer past the end of dev->channels when no matching scan_index is found. This can lead to invalid memory access in ams_handle_event().
Add a bounds check in ams_event_to_channel() and return NULL when no channel is found. Also guard the caller to safely handle this case.
--- drivers/iio/adc/xilinx-ams.c | 5 +++++ 1 file changed, 5 insertions(+)
drivers/iio/adc/xilinx-ams.c +5 -0
@@ -871,6 +871,9 @@ static const struct iio_chan_spec *ams_event_to_channel(struct iio_dev *dev,if (dev->channels[i].scan_index == scan_index)break ; +if (i == dev->num_channels) +return NULL ; +return &dev->channels[i]; }
@@ -1012,6 +1015,8 @@ static void ams_handle_event(struct iio_dev *indio_dev, u32 event)const struct iio_chan_spec *chan; chan =ams_event_to_channel (indio_dev, event); +if (!chan) +return ;if (chan->type ==IIO_TEMP ) {/*
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 624/1611 iio: accel: mma8452: handle I2C read error(s) in mma8452_read()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sanjay Chitroda <[email protected]>
[ Upstream commit 5bdff291d20c31b365d9ddfe9c426fbfb41da5bb ]
Currently, If i2c_smbus_read_i2c_block_data() fails but mma8452_set_runtime_pm_state() succeeds, mma8452_read() returns 0.
As a result, the caller mma8452_read_raw() assumes the read was successful and proceeds to use a buffer containing uninitialized stack memory.
Add proper checking of the I2C read return value and propagate errors to the caller.
--- drivers/iio/accel/mma8452.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/iio/accel/mma8452.c +2 -0
@@ -252,6 +252,8 @@ static int mma8452_read(struct mma8452_data *data, __be16 buf[3]) ret =i2c_smbus_read_i2c_block_data (data->client,MMA8452_OUT_X ,3 *sizeof (__be16), (u8 *)buf); +if (ret <0 ) +return ret; ret =mma8452_set_runtime_pm_state (data->client, false);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 625/1611 iio: tcs3472: power down chip on probe failure
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Aldo Conte <[email protected]>
[ Upstream commit b39f3bb9f5580d19bc0c10dea9224d75fed45f1d ]
If tcs3472_probe() fails after enabling the chip (by writing PON | AEN to the ENABLE register), the error paths return without powering down the device.
Add an 'error_powerdown' label at the end of the cleanup chain that calls tcs3472_powerdown() to power down the chip. The existing label cascade is rerouted to fall through to the new label.
Move tcs3472_powerdown() above tcs3472_probe() so the probe can call it without a forward declaration.
Found by code inspection while reviewing the probe error paths in preparation for the devm_ conversion.
--- drivers/iio/light/tcs3472.c | 38 +++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-)
drivers/iio/light/tcs3472.c +20 -18
@@ -440,6 +440,23 @@ static const struct iio_info tcs3472_info = { .attrs = &tcs3472_attribute_group, }; +static int tcs3472_powerdown (struct tcs3472_data *data) +{ +int ret; +u8 enable_mask =TCS3472_ENABLE_AEN |TCS3472_ENABLE_PON ; + +mutex_lock (&data->lock); + + ret =i2c_smbus_write_byte_data (data->client,TCS3472_ENABLE , + data->enable & ~enable_mask); +if (!ret) + data->enable &= ~enable_mask; + +mutex_unlock (&data->lock); + +return ret; +} +static int tcs3472_probe (struct i2c_client *client) {struct tcs3472_data *data;
@@ -513,7 +530,7 @@ static int tcs3472_probe(struct i2c_client *client) ret =iio_triggered_buffer_setup (indio_dev,NULL , tcs3472_trigger_handler,NULL );if (ret <0 ) -return ret; + goto error_powerdown;if (client->irq) { ret = request_threaded_irq(client->irq, NULL,
@@ -536,23 +553,8 @@ static int tcs3472_probe(struct i2c_client *client)free_irq (client->irq, indio_dev); buffer_cleanup:iio_triggered_buffer_cleanup (indio_dev); -return ret; -} - -static int tcs3472_powerdown (struct tcs3472_data *data) -{ -int ret; -u8 enable_mask =TCS3472_ENABLE_AEN |TCS3472_ENABLE_PON ; - -mutex_lock (&data->lock); - - ret =i2c_smbus_write_byte_data (data->client,TCS3472_ENABLE , - data->enable & ~enable_mask); -if (!ret) - data->enable &= ~enable_mask; - -mutex_unlock (&data->lock); - +error_powerdown: +tcs3472_powerdown (data);return ret; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 626/1611 clk: at91: keep securam node alive while mapping it
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yuho Choi <[email protected]>
[ Upstream commit 22fa1c39ba6fe726b547c877c924379b7fee260a ]
pmc_register_ops() gets an owned reference to the "atmel,sama5d2-securam" node with of_find_compatible_node(). The success path dropped that reference before passing the node to of_iomap(), leaving of_iomap() to consume a node pointer after the caller had released its reference.
Move of_node_put() after of_iomap() so the node remains referenced for the mapping operation. The unavailable-node error path already releases the reference.
--- drivers/clk/at91/pmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/clk/at91/pmc.c +1 -1
@@ -177,9 +177,9 @@ static int __init pmc_register_ops(void)of_node_put (np);return -ENODEV ; } -of_node_put (np); at91_pmc_backup_suspend =of_iomap (np,0 ); +of_node_put (np);if (!at91_pmc_backup_suspend) {pr_warn ("%s(): unable to map securam\n" , __func__);return -ENOMEM ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 627/1611 HID: logitech-hidpp: remove excess kernel-doc member in hidpp_scroll_counter
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Rosen Penev <[email protected]>
[ Upstream commit f22a5db8a7d38152556f230d6d68e59dbc27971b ]
The @dev member described in the kernel-doc does not exist in the struct. Remove the stale entry.
--- drivers/hid/hid-logitech-hidpp.c | 1 - 1 file changed, 1 deletion(-)
drivers/hid/hid-logitech-hidpp.c +0 -1
@@ -164,7 +164,6 @@ struct hidpp_battery {/** * struct hidpp_scroll_counter - Utility class for processing high-resolution * scroll events. -* @dev: the input device for which events should be reported. * @wheel_multiplier: the scalar multiplier to be applied to each wheel event * @remainder: counts the number of high-resolution units moved since the last * low-resolution event (REL_WHEEL or REL_HWHEEL) was sent. Should
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 628/1611 fs/ntfs3: add bounds check to run_get_highest_vcn()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Konstantin Komarov <[email protected]>
[ Upstream commit bb11485a87fbb2254b62cfed630b699d50e57da8 ]
run_get_highest_vcn() parses a packed NTFS mapping-pairs buffer without any length bound, relying solely on a 0x00 terminator to stop. A crafted $LogFile UpdateMappingPairs record whose embedded attribute contains mapping-pairs runs without a terminator causes the function to read past the slab allocation, triggering a KASAN slab-out-of-bounds read on mount.
The sibling function run_unpack() received an analogous bounds-check in commit b62567bca474 ("ntfs3: add buffer boundary checks to run_unpack()"), but run_get_highest_vcn() was missed.
Take a run_buf_size parameter and reject any run header whose payload would extend past the buffer end, mirroring the pattern used by run_unpack(). The caller in fslog.c passes the remaining attribute bytes after the mapping-pairs offset.
KASAN report (on mainline v7.1 merge window HEAD):
BUG: KASAN: slab-out-of-bounds in run_get_highest_vcn+0x3c0/0x410 Read of size 1 at addr ffff88800e2d5400 by task mount/72 Call Trace: run_get_highest_vcn+0x3c0/0x410 do_action.isra.0+0x3ba8/0x7b50 log_replay+0x9ddd/0x10200 ntfs_loadlog_and_replay+0x4ad/0x610 ntfs_fill_super+0x214a/0x4540
--- fs/ntfs3/fslog.c | 5 ++++- fs/ntfs3/ntfs_fs.h | 3 ++- fs/ntfs3/run.c | 9 +++++++-- 3 files changed, 13 insertions(+), 4 deletions(-)
fs/ntfs3/fslog.c +4 -1
@@ -3362,7 +3362,10 @@ static int do_action(struct ntfs_log *log, struct OPEN_ATTR_ENRTY *oe,memmove (Add2Ptr (attr, aoff), data, dlen);if (run_get_highest_vcn (le64_to_cpu (attr->nres.svcn), -attr_run (attr), &t64)) { +attr_run (attr), +le32_to_cpu (attr->size) - +le16_to_cpu (attr->nres.run_off), + &t64)) { goto dirty_vol; }
fs/ntfs3/ntfs_fs.h +2 -1
@@ -821,7 +821,8 @@ int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino,#else #define run_unpack_ex run_unpack#endif -int run_get_highest_vcn (CLST vcn,const u8 *run_buf,u64 *highest_vcn); +int run_get_highest_vcn (CLST vcn,const u8 *run_buf,size_t run_buf_size, +u64 *highest_vcn);int run_clone (const struct runs_tree *run,struct runs_tree *new_run);/* Globals from super.c */
fs/ntfs3/run.c +7 -2
@@ -1160,18 +1160,23 @@ int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino,* Return the highest vcn from a mapping pairs array * it used while replaying log file. */ -int run_get_highest_vcn (CLST vcn,const u8 *run_buf,u64 *highest_vcn) +int run_get_highest_vcn (CLST vcn,const u8 *run_buf,size_t run_buf_size, +u64 *highest_vcn) { +const u8 *run_last = run_buf + run_buf_size;u64 vcn64 = vcn;u8 size_size; -while ((size_size = *run_buf &0xF )) { +while (run_buf < run_last && (size_size = *run_buf &0xF )) {u8 offset_size = *run_buf++ >>4 ;u64 len;if (size_size >8 || offset_size >8 )return -EINVAL ; +if (run_buf + size_size + offset_size > run_last) +return -EINVAL ; + len =run_unpack_s64 (run_buf, size_size,0 );if (!len)return -EINVAL ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 629/1611 fs/ntfs3: fix mount failure on 64K page-size kernels
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jamie Nguyen <[email protected]>
[ Upstream commit b7a9125cac8645245d2473c6c0a50e338280ad23 ]
On 64K page-size kernels, mounting NTFS volumes smaller than ~650 MB fails with EINVAL. The issue is in log_replay(): the initial log page size probe uses PAGE_SIZE (65536) instead of DefaultLogPageSize (4096) when PAGE_SIZE exceeds DefaultLogPageSize * 2.
This makes norm_file_page() require the $LogFile to be at least 50 * 65536 = 3.2 MB, but mkfs.ntfs creates a $LogFile of only ~1.5 MB for a typical 300 MB volume. norm_file_page() returns 0 and the mount is rejected with EINVAL.
On 4K kernels the #if guard evaluates to true, so use_default=true is passed and DefaultLogPageSize (4096) is used, requiring only ~200 KB. This path works fine.
Fix this by always passing use_default=true, which forces the initial probe to use DefaultLogPageSize regardless of the kernel's PAGE_SIZE. This is safe because, after reading the on-disk restart area, log_replay() already re-adjusts log->page_size to match the volume's actual sys_page_size.
Also fix read_log_page() to pass log->page_size instead of PAGE_SIZE to ntfs_fix_post_read(), matching the actual buffer size.
--- fs/ntfs3/fslog.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)
fs/ntfs3/fslog.c +1 -5
@@ -1170,7 +1170,7 @@ static int read_log_page(struct ntfs_log *log, u32 vbo, goto out;if (page_buf->rhdr.sign !=NTFS_FFFF_SIGNATURE ) -ntfs_fix_post_read (&page_buf->rhdr,PAGE_SIZE , false); +ntfs_fix_post_read (&page_buf->rhdr, log->page_size, false);if (page_buf != *buffer)memcpy (*buffer,Add2Ptr (page_buf, page_off), bytes);
@@ -3798,11 +3798,7 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) log->l_size = log->orig_file_size = ni->vfs_inode.i_size;/* Get the size of page. NOTE: To replay we can use default page. */ -#if PAGE_SIZE >= DefaultLogPageSize &&PAGE_SIZE <= DefaultLogPageSize *2 log->page_size =norm_file_page (PAGE_SIZE , &log->l_size, true); -#else - log->page_size =norm_file_page (PAGE_SIZE , &log->l_size, false); -#endif if (!log->page_size) { err = -EINVAL ; goto out;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 630/1611 drm/amd/display: Add missing kdoc for ALLM parameters
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Srinivasan Shanmugam <[email protected]>
[ Upstream commit d4c6ec729fb7a8bf8a27b19bd70a1b945ad93dac ]
Add descriptions for the missing parameters for ALLMEnabled and ALLMValue to keep the function documentation synchronized with the function prototype mod_build_hf_vsif_infopacket().
Fixes the below with gcc W=1:../display/modules/info_packet/info_packet.c:507 function parameter 'ALLMEnabled' not described in 'mod_build_hf_vsif_infopacket' ../display/modules/info_packet/info_packet.c:507 function parameter 'ALLMValue' not described in 'mod_build_hf_vsif_infopacket'
--- drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c +2 -0
@@ -447,6 +447,8 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,* * @stream: contains data we may need to construct VSIF (i.e. timing_3d_format, etc.) * @info_packet: output structure where to store VSIF +* @ALLMEnabled: indicates whether ALLM HF-VSIF should be generated +* @ALLMValue: ALLM bit value to advertise in HF-VSIF */ void mod_build_hf_vsif_infopacket (const struct dc_stream_state *stream,struct dc_info_packet *info_packet)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 631/1611 thunderbolt: debugfs: Fix margining error counter buffer leak
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Xu Rao <[email protected]>
[ Upstream commit 503c5ae1e72aa9ed91925dafa3d82ee2e992747f ]
When USB4 lane margining debugfs write support is enabled, margining_error_counter_write() copies the user input with validate_and_copy_from_user(). This allocates a temporary page that is only needed while parsing the requested error counter mode.
The function currently returns without freeing that page. This leaks one page per write to the error_counter debugfs file, including successful writes and writes that later fail while taking the domain lock or because software margining is not enabled.
Free the temporary page once parsing has completed, and also before returning from the invalid-input path.
--- drivers/thunderbolt/debugfs.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
drivers/thunderbolt/debugfs.c +7 -1
@@ -956,7 +956,9 @@ margining_error_counter_write(struct file *file, const char __user *user_buf,else if (!strcmp (buf,"stop" )) error_counter =USB4_MARGIN_SW_ERROR_COUNTER_STOP ;else -return -EINVAL ; + goto err_free; + +free_page ((unsigned long )buf); scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &tb->lock) {if (!margining->software)
@@ -966,6 +968,10 @@ margining_error_counter_write(struct file *file, const char __user *user_buf, }return count; + +err_free: +free_page ((unsigned long )buf); +return -EINVAL ; }static int margining_error_counter_show (struct seq_file *s,void *not_used)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 632/1611 dmaengine: imx-sdma: Refine spba bus searching in probe
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Shengjiu Wang <[email protected]>
[ Upstream commit d52d42e2e5d9f13166e81ac837ebb023d1306e61 ]
There are multi spba-busses for i.MX8M* platforms, if only search for the first spba-bus in DT, the found spba-bus may not the real bus of audio devices, which cause issue for sdma p2p case, as the sdma p2p script presently does not deal with the transactions involving two devices connected to the AIPS bus.
Search the SDMA parent node first, which should be the AIPS bus, then search the child node whose compatible string is spba-bus under that AIPS bus for the above multi spba-busses case.
--- drivers/dma/imx-sdma.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/dma/imx-sdma.c +3 -1
@@ -2376,7 +2376,9 @@ static int sdma_probe(struct platform_device *pdev) goto err_register; } - spba_bus =of_find_compatible_node (NULL ,NULL ,"fsl,spba-bus" ); + struct device_node *sdma_parent_np __free(device_node) = of_get_parent(np); + + spba_bus =of_get_compatible_child (sdma_parent_np,"fsl,spba-bus" ); ret =of_address_to_resource (spba_bus,0 , &spba_res);if (!ret) { sdma->spba_start_addr = spba_res.start;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 633/1611 dt-bindings: dma: nvidia,tegra186-gpc-dma: Make reset optional
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Akhil R <[email protected]>
[ Upstream commit cc6049bd3fa8501ee27042df469a19ed69cf406d ]
On Tegra264, GPCDMA reset control is not exposed to Linux and is handled by the boot firmware.
Although reset was not exposed in Tegra234 as well, the firmware supported a dummy reset which just returns success on reset without doing an actual reset. This is also not supported in Tegra264 BPMP. Therefore mark 'reset' and 'reset-names' properties as required only for devices prior to Tegra264.
This also necessitates that the Tegra264 compatible be standalone and cannot have the fallback compatible of Tegra186. Since there is no functional impact, we keep reset as required for Tegra234 to avoid breaking the ABI.
--- .../bindings/dma/nvidia,tegra186-gpc-dma.yaml | 23 +++++++++++++------ 1 file changed, 16 insertions(+), 7 deletions(-)
Documentation/devicetree/bindings/dma/nvidia,tegra186-gpc-dma.yaml +16 -7
@@ -15,16 +15,14 @@ maintainers: - Jon Hunter <[email protected]> - Rajesh Gumasta <[email protected]> -allOf: - - $ref: dma-controller.yaml# - properties: compatible: oneOf: - - const: nvidia,tegra186-gpcdma + - enum: + - nvidia,tegra264-gpcdma + - nvidia,tegra186-gpcdma - items: - enum: - - nvidia,tegra264-gpcdma - nvidia,tegra234-gpcdma - nvidia,tegra194-gpcdma - const: nvidia,tegra186-gpcdma
@@ -60,12 +58,23 @@ required: - compatible - reg - interrupts - - resets - - reset-names - "#dma-cells" - iommus - dma-channel-mask +allOf: + - $ref: dma-controller.yaml# + - if: + properties: + compatible: + contains: + enum: + - nvidia,tegra186-gpcdma + then: + required: + - resets + - reset-names + additionalProperties: false examples:
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 634/1611 perf: Fix off-by-one stack buffer overflow in kallsyms__parse()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Rui Qi <[email protected]>
[ Upstream commit 68018df3f55eba96a20dd703f5f276a6518f4963 ]
In kallsyms__parse(), the loop reading symbol names iterates with i < sizeof(symbol_name), which allows i to reach sizeof(symbol_name) upon loop exit. The subsequent symbol_name[i] = '\0' then writes one byte past the end of the stack-allocated symbol_name[] array.
Fix this by changing the loop bound to KSYM_NAME_LEN, so the null terminator always lands within the array. The overflow is triggerable by a kallsyms entry with a symbol name of KSYM_NAME_LEN+1 or more characters (e.g., long Rust mangled names or a malicious /proc/kallsyms).
--- tools/lib/symbol/kallsyms.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
tools/lib/symbol/kallsyms.c +4 -1
@@ -60,7 +60,7 @@ int kallsyms__parse(const char *filename, void *arg,read_to_eol (&io);continue ; } -for (i =0 ; i <sizeof (symbol_name); i++) { +for (i =0 ; i <KSYM_NAME_LEN ; i++) { ch =io__get_char (&io);if (ch <0 || ch =='\n' )break ;
@@ -68,6 +68,9 @@ int kallsyms__parse(const char *filename, void *arg, } symbol_name[i] ='\0' ; +if (i ==KSYM_NAME_LEN ) +read_to_eol (&io); + err =process_symbol (arg, symbol_name, symbol_type, start);if (err)break ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 635/1611 perf annotate: Fix crashes on empty annotate windows
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: James Clark <[email protected]>
[ Upstream commit 74802634e4a7e556429417963a8cbda27dd8b4b3 ]
Annotate can open with an empty window if the disassembly tool fails. After the linked change, the TUI started assuming there was a current annotation line and could assert or segfault in the seek, refresh, and source-toggle paths.
Handle empty annotate windows explicitly: set the asm entry count before resetting the browser, return early when refreshing an empty list, and ignore source line toggle when there is no current annotation line.
Fixes the following when opening an annotation:
perf: ui/browser.c:125: ui_browser__list_head_seek: Assertion `pos != NULL' failed. Aborted
--- tools/perf/ui/browser.c | 3 +++ tools/perf/ui/browsers/annotate.c | 5 ++++- 2 files changed, 7 insertions(+), 1 deletion(-)
tools/perf/ui/browser.c +3 -0
@@ -513,6 +513,9 @@ unsigned int ui_browser__list_head_refresh(struct ui_browser *browser)struct list_head *head = browser->entries;int row =0 ; +if (browser->nr_entries ==0 ) +return 0 ; +if (browser->top ==NULL || browser->top == browser->entries) browser->top =ui_browser__list_head_filter_entries (browser, head->next);
tools/perf/ui/browsers/annotate.c +4 -1
@@ -449,6 +449,9 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser,struct annotation_line *al;off_t offset = browser->b.index - browser->b.top_idx; +if (browser->b.nr_entries ==0 ) +return false; + browser->b.seek (&browser->b, offset,SEEK_CUR ); al = list_entry(browser->b.top, struct annotation_line, node);
@@ -542,8 +545,8 @@ static void annotate_browser__show_full_location(struct ui_browser *browser)static void ui_browser__init_asm_mode (struct ui_browser *browser) {struct annotation *notes =browser__annotation (browser); -ui_browser__reset_index (browser); browser->nr_entries = notes->src->nr_asm_entries; +ui_browser__reset_index (browser); } static int sym_title(struct symbol *sym, struct map *map, char *title,
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 636/1611 perf tools: Guard test_bit from out-of-bounds sample CPU
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit a5498ccf8079fc91c938f122ff9697b0c526b2fd ]
When PERF_SAMPLE_CPU is absent from a perf.data file, sample->cpu is initialized to (u32)-1 by evsel__parse_sample(). Five call sites pass this value directly to test_bit(sample->cpu, cpu_bitmap), reading massively out of bounds past the DECLARE_BITMAP(..., MAX_NR_CPUS) allocation of 4096 bits.
Add a sample->cpu >= MAX_NR_CPUS guard before each test_bit() call, matching the existing safe pattern in builtin-kwork.c. This catches both the (u32)-1 sentinel and any corrupted CPU value exceeding the bitmap size.
--- tools/perf/builtin-annotate.c | 3 ++- tools/perf/builtin-diff.c | 3 ++- tools/perf/builtin-report.c | 3 ++- tools/perf/builtin-sched.c | 6 ++++-- 4 files changed, 10 insertions(+), 5 deletions(-)
tools/perf/builtin-annotate.c +2 -1
@@ -299,7 +299,8 @@ static int process_sample_event(const struct perf_tool *tool, goto out_put; } -if (ann->cpu_list && !test_bit (sample->cpu, ann->cpu_bitmap)) +if (ann->cpu_list && (sample->cpu >=MAX_NR_CPUS || + !test_bit (sample->cpu, ann->cpu_bitmap))) goto out_put; if (!al.filtered &&
tools/perf/builtin-diff.c +2 -1
@@ -418,7 +418,8 @@ static int diff__process_sample_event(const struct perf_tool *tool, goto out; } -if (cpu_list && !test_bit (sample->cpu, cpu_bitmap)) { +if (cpu_list && (sample->cpu >=MAX_NR_CPUS || + !test_bit (sample->cpu, cpu_bitmap))) { ret =0 ; goto out; }
tools/perf/builtin-report.c +2 -1
@@ -303,7 +303,8 @@ static int process_sample_event(const struct perf_tool *tool,if (symbol_conf.hide_unresolved && al.sym ==NULL ) goto out_put; -if (rep->cpu_list && !test_bit (sample->cpu, rep->cpu_bitmap)) +if (rep->cpu_list && (sample->cpu >=MAX_NR_CPUS || + !test_bit (sample->cpu, rep->cpu_bitmap))) goto out_put;if (sort__mode ==SORT_MODE__BRANCH ) {
tools/perf/builtin-sched.c +4 -2
@@ -2168,7 +2168,8 @@ static void timehist_print_sample(struct perf_sched *sched,char nstr[30 ];u64 wait_time; -if (cpu_list && !test_bit (sample->cpu, cpu_bitmap)) +if (cpu_list && (sample->cpu >=MAX_NR_CPUS || + !test_bit (sample->cpu, cpu_bitmap)))return ;timestamp__scnprintf_usec (t, tstr,sizeof (tstr));
@@ -2850,7 +2851,8 @@ static int timehist_sched_change_event(const struct perf_tool *tool, }if (!sched->idle_hist ||thread__tid (thread) ==0 ) { -if (!cpu_list ||test_bit (sample->cpu, cpu_bitmap)) +if (!cpu_list || (sample->cpu <MAX_NR_CPUS && +test_bit (sample->cpu, cpu_bitmap)))timehist_update_runtime_stats (tr, t, tprev);if (sched->idle_hist) {
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 637/1611 perf sched: Fix thread reference leak in latency_switch_event
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 66ea9de60396a4dea5276bc87025884691876c36 ]
In latency_switch_event(), after acquiring thread references for sched_out and sched_in via machine__findnew_thread(), the first add_sched_out_event() failure path does 'return -1', bypassing the out_put label that calls thread__put() on both references.
The second and third add_sched_out_event() failures correctly use 'goto out_put'. Fix the first one to match.
--- tools/perf/builtin-sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/builtin-sched.c +1 -1
@@ -1170,7 +1170,7 @@ static int latency_switch_event(struct perf_sched *sched, } }if (add_sched_out_event (out_events, prev_state, timestamp)) -return -1 ; + goto out_put; in_events =thread_atoms_search (&sched->atom_root, sched_in, &sched->cmp_pid);if (!in_events) {
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 638/1611 perf sched: Replace BUG_ON on invalid CPU with graceful skip
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 1e2c83f732deb329ebce23e26cbc482f4c4bf194 ]
latency_switch_event(), latency_runtime_event(), and map_switch_event() use BUG_ON(cpu >= MAX_CPUS || cpu < 0) to validate the sample CPU. When PERF_SAMPLE_CPU is absent from the sample type, evsel__parse_sample() initializes sample->cpu to (u32)-1. Casting this to int yields -1, which triggers the BUG_ON and aborts perf sched.
The central CPU validation in perf_session__deliver_event() intentionally preserves the (u32)-1 sentinel for downstream tools like perf script and perf inject, so leaf callbacks must handle it themselves.
Replace the three BUG_ON calls with graceful skips using pr_warning(), matching the existing pattern in process_sched_switch_event() and process_sched_runtime_event() earlier in the same file. Include the file offset for cross-referencing with perf report -D.
Stable-dep-of: 8cbca8a480e1 ("perf sched: Fix NULL dereference in latency_runtime_event")
--- tools/perf/builtin-sched.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-)
tools/perf/builtin-sched.c +19 -3
@@ -1140,7 +1140,12 @@ static int latency_switch_event(struct perf_sched *sched,int cpu = sample->cpu, err =-1 ;s64 delta; -BUG_ON (cpu >=MAX_CPUS || cpu <0 ); +/* perf.data is untrusted input — CPU may be absent or corrupted */ +if (cpu >=MAX_CPUS || cpu <0 ) { +pr_warning ("WARNING: at offset %#" PRIx64": out-of-bound sample CPU %d, skipping sample\n" , + sample->file_offset, cpu); +return 0 ; + } timestamp0 = sched->cpu_last_switched[cpu]; sched->cpu_last_switched[cpu] = timestamp;
@@ -1211,7 +1216,13 @@ static int latency_runtime_event(struct perf_sched *sched,if (thread ==NULL )return -1 ; -BUG_ON (cpu >=MAX_CPUS || cpu <0 ); +/* perf.data is untrusted input — CPU may be absent or corrupted */ +if (cpu >=MAX_CPUS || cpu <0 ) { +pr_warning ("WARNING: at offset %#" PRIx64": out-of-bound sample CPU %d, skipping sample\n" , + sample->file_offset, cpu); + err =0 ; + goto out_put; + }if (!atoms) {if (thread_atoms_insert (sched, thread)) goto out_put;
@@ -1640,7 +1651,12 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,const char *str;int ret =-1 ; -BUG_ON (this_cpu.cpu >=MAX_CPUS || this_cpu.cpu <0 ); +/* perf.data is untrusted input — CPU may be absent or corrupted */ +if (this_cpu.cpu >=MAX_CPUS || this_cpu.cpu <0 ) { +pr_warning ("WARNING: at offset %#" PRIx64": out-of-bound sample CPU %d, skipping sample\n" , + sample->file_offset, this_cpu.cpu); +return 0 ; + }if (this_cpu.cpu > sched->max_cpu.cpu) sched->max_cpu = this_cpu;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 639/1611 perf sched: Fix NULL dereference in latency_runtime_event
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 8cbca8a480e15f6326ce94287570993f27a4b2d5 ]
latency_runtime_event() passes the return value of machine__findnew_thread() directly to thread_atoms_search() at line 1216, before checking for NULL at line 1220. thread_atoms_search() calls pid_cmp() which dereferences the thread pointer via thread__tid(), causing a NULL pointer dereference if the allocation fails.
All other callers of thread_atoms_search() in this file (latency_switch_event, latency_wakeup_event, latency_migrate_task_event) correctly check for NULL first.
Move the atoms assignment after the NULL check to match the pattern used by the other callers.
--- tools/perf/builtin-sched.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
tools/perf/builtin-sched.c +3 -1
@@ -1209,13 +1209,15 @@ static int latency_runtime_event(struct perf_sched *sched,const u32 pid =evsel__intval (evsel, sample,"pid" );const u64 runtime =evsel__intval (evsel, sample,"runtime" );struct thread *thread =machine__findnew_thread (machine,-1 , pid); -struct work_atoms *atoms =thread_atoms_search (&sched->atom_root, thread, &sched->cmp_pid); +struct work_atoms *atoms;u64 timestamp = sample->time;int cpu = sample->cpu, err =-1 ;if (thread ==NULL )return -1 ; + atoms =thread_atoms_search (&sched->atom_root, thread, &sched->cmp_pid); +/* perf.data is untrusted input — CPU may be absent or corrupted */ if (cpu >=MAX_CPUS || cpu <0 ) { pr_warning("WARNING: at offset %#" PRIx64 ": out-of-bound sample CPU %d, skipping sample\n",
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 640/1611 perf tools: Add bounds check to cpu__get_node()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 1e7921d7227de5da0dfc167943092c823ec7e49b ]
cpu__get_node() accesses cpunode_map[cpu.cpu] without checking against max_cpu_num, the allocation size of cpunode_map. Callers such as builtin-kmem.c:evsel__process_alloc_event() pass sample->cpu from perf.data events, which may exceed the host's CPU count when analyzing cross-machine recordings.
Add a bounds check against max_cpu_num before indexing, returning -1 for out-of-range values. This is a central fix that protects all callers.
--- tools/perf/util/cpumap.c | 4 ++++ 1 file changed, 4 insertions(+)
tools/perf/util/cpumap.c +4 -0
@@ -548,6 +548,10 @@ int cpu__get_node(struct perf_cpu cpu)return -1 ; } +/* cpunode_map allocated for max_cpu_num entries; input may be untrusted */ +if (cpu.cpu <0 || cpu.cpu >= max_cpu_num.cpu) +return -1 ; +return cpunode_map[cpu.cpu]; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 641/1611 perf sched: Cap max_cpu at MAX_CPUS in timehist sample processing
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 06e7994427ab56e32699a5e45d048ff0826f3d53 ]
perf_timehist__process_sample() updates sched->max_cpu from the sample CPU without bounds checking. Later code uses max_cpu + 1 as an iteration count over arrays allocated with MAX_CPUS entries (curr_thread, cpu_last_switched). A recording with CPU IDs >= MAX_CPUS causes out-of-bounds array accesses.
Also cap the env->nr_cpus_online initialization of max_cpu in perf_sched__timehist(), which could exceed MAX_CPUS on very large systems.
Add bounds checks before both max_cpu updates, matching the pattern already used in map_switch_event().
--- tools/perf/builtin-sched.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
tools/perf/builtin-sched.c +5 -3
@@ -3206,7 +3206,9 @@ static int perf_timehist__process_sample(const struct perf_tool *tool, .cpu = sample->cpu, }; -if (this_cpu.cpu > sched->max_cpu.cpu) +/* max_cpu indexes arrays allocated with MAX_CPUS entries */ +if (this_cpu.cpu >=0 && this_cpu.cpu <MAX_CPUS && + this_cpu.cpu > sched->max_cpu.cpu) sched->max_cpu = this_cpu;if (evsel->handler !=NULL ) {
@@ -3376,8 +3378,8 @@ static int perf_sched__timehist(struct perf_sched *sched) perf_session__set_tracepoints_handlers(session, migrate_handlers)) goto out; -/* pre-allocate struct for per-CPU idle stats */ - sched->max_cpu.cpu = env->nr_cpus_online; +/* pre-allocate struct for per-CPU idle stats; cap to array bounds */ + sched->max_cpu.cpu =min (env->nr_cpus_online,MAX_CPUS );if (sched->max_cpu.cpu ==0 ) sched->max_cpu.cpu =4 ;if (init_idle_threads (sched->max_cpu.cpu))
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 642/1611 perf sched: Fix register_pid() overflow, strcpy, and BUG_ON
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 5949d339f5ec98752d56dcd4e36f619a59d513a5 ]
register_pid() has several issues when processing untrusted perf.data:
1. Integer overflow: (pid + 1) * sizeof(struct task_desc *) can wrap to a small value on 32-bit systems when pid is large (e.g. 0x40000000), causing realloc to return a tiny buffer followed by out-of-bounds writes in the initialization loop.
2. Heap buffer overflow: strcpy(task->comm, comm) copies the untrusted comm string into a fixed 20-byte COMM_LEN buffer with no length check.
3. BUG_ON on allocation failure: perf.data is untrusted input, so allocation failures should be handled gracefully rather than killing the process.
4. Realloc of sched->tasks assigned directly back, leaking the old pointer on failure; nr_tasks incremented before the realloc, leaving corrupted state on failure.
Cap pid at PID_MAX_LIMIT (4194304, matching the kernel's maximum on 64-bit), replace strcpy with strlcpy, guard against NULL comm, replace BUG_ON with NULL returns using safe realloc patterns, and add NULL checks in callers that dereference the result.
--- tools/perf/builtin-sched.c | 40 ++++++++++++++++++++++++++++---------- 1 file changed, 30 insertions(+), 10 deletions(-)
tools/perf/builtin-sched.c +30 -10
@@ -52,6 +52,7 @@#define COMM_LEN 20#define SYM_LEN 129#define MAX_PID 1024000 +#define PID_MAX_LIMIT 4194304/* kernel limit on 64-bit */ #define MAX_PRIO 140static const char *cpu_list;
@@ -441,17 +442,28 @@ static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *tastatic struct task_desc *register_pid (struct perf_sched *sched,unsigned long pid,const char *comm) { -struct task_desc *task; +struct task_desc *task, **tasks_p;static int pid_max; +/* perf.data is untrusted — cap pid to prevent overflow in size calculations */ +if (pid >=PID_MAX_LIMIT ) { +pr_err ("pid %lu exceeds limit %d, skipping\n" , pid,PID_MAX_LIMIT ); +return NULL ; + } +if (sched->pid_to_task ==NULL ) {if (sysctl__read_int ("kernel/pid_max" , &pid_max) <0 ) pid_max =MAX_PID ; -BUG_ON ((sched->pid_to_task =calloc (pid_max,sizeof (struct task_desc *))) ==NULL ); + sched->pid_to_task =calloc (pid_max,sizeof (struct task_desc *)); +if (sched->pid_to_task ==NULL ) +return NULL ; }if (pid >= (unsigned long )pid_max) { -BUG_ON ((sched->pid_to_task =realloc (sched->pid_to_task, (pid +1 ) * -sizeof (struct task_desc *))) ==NULL ); +void *p =realloc (sched->pid_to_task, (pid +1 ) *sizeof (struct task_desc *)); + +if (p ==NULL ) +return NULL ; + sched->pid_to_task = p;while (pid >= (unsigned long )pid_max) sched->pid_to_task[pid_max++] =NULL ; }
@@ -462,9 +474,11 @@ static struct task_desc *register_pid(struct perf_sched *sched,return task; task =zalloc (sizeof (*task)); +if (task ==NULL ) +return NULL ; task->pid = pid; - task->nr = sched->nr_tasks; -strcpy (task->comm, comm); +if (comm) +strlcpy (task->comm, comm,sizeof (task->comm));/* * every task starts in sleeping state - this gets ignored * if there's no wakeup pointing to this sleep state:
@@ -472,10 +486,12 @@ static struct task_desc *register_pid(struct perf_sched *sched,add_sched_event_sleep (sched, task,0 ); sched->pid_to_task[pid] = task; - sched->nr_tasks++; - sched->tasks =realloc (sched->tasks, sched->nr_tasks *sizeof (struct task_desc *)); -BUG_ON (!sched->tasks); - sched->tasks[task->nr] = task; + tasks_p =realloc (sched->tasks, (sched->nr_tasks +1 ) *sizeof (struct task_desc *)); +if (!tasks_p) +return NULL ; + sched->tasks = tasks_p; + sched->tasks[sched->nr_tasks] = task; + task->nr = sched->nr_tasks++;if (verbose >0 )printf ("registered task #%ld, PID %ld (%s)\n" , sched->nr_tasks, pid, comm);
@@ -834,6 +850,8 @@ replay_wakeup_event(struct perf_sched *sched, waker =register_pid (sched, sample->tid,"<unknown>" ); wakee =register_pid (sched, pid, comm); +if (waker ==NULL || wakee ==NULL ) +return -1 ;add_sched_event_wakeup (sched, waker, sample->time, wakee);return 0 ;
@@ -875,6 +893,8 @@ static int replay_switch_event(struct perf_sched *sched, prev =register_pid (sched, prev_pid, prev_comm); next =register_pid (sched, next_pid, next_comm); +if (prev ==NULL || next ==NULL ) +return -1 ; sched->cpu_last_switched[cpu] = timestamp;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 643/1611 perf mmap: Guard cpu__get_node() return in aio_bind()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit f32dc302a090f48893477ef297a888db109ec0bd ]
perf_mmap__aio_bind() passes the cpu__get_node() return value directly to an unsigned long variable (node_index). When cpu__get_node() returns -1 for an unknown CPU, the implicit int-to-unsigned-long conversion sign-extends it to ULONG_MAX.
This causes bitmap_zalloc(ULONG_MAX + 1) which wraps to bitmap_zalloc(0), returning a zero-sized allocation. The subsequent __set_bit(ULONG_MAX, node_mask) then writes massively out of bounds.
Check the return value in a signed temporary before assigning to node_index, and skip the NUMA binding when the node is unknown.
--- tools/perf/util/mmap.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
tools/perf/util/mmap.c +7 -1
@@ -103,9 +103,15 @@ static int perf_mmap__aio_bind(struct mmap *map, int idx, struct perf_cpu cpu, iint err =0 ;if (affinity !=PERF_AFFINITY_SYS &&cpu__max_node () >1 ) { +int node; + data = map->aio.data[idx]; mmap_len =mmap__mmap_len (map); - node_index =cpu__get_node (cpu); + node =cpu__get_node (cpu); +/* -1 sign-extends to ULONG_MAX, wrapping bitmap_zalloc(0) and OOB __set_bit */ +if (node <0 ) +return 0 ; + node_index = node; node_mask =bitmap_zalloc (node_index +1 );if (!node_mask) {pr_err ("Failed to allocate node mask for mbind: error %m\n" );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 644/1611 perf stat: Bounds-check CPU index in topology aggregation callbacks
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 52e69b1c5b606b513d403dd4addc784c27a0c8e2 ]
Six perf_env__get_*_aggr_by_cpu() functions access env->cpu[cpu.cpu] after only checking cpu.cpu != -1. env->cpu[] is allocated with env->nr_cpus_avail entries, so a CPU index from an untrusted perf.data file that exceeds that count causes an out-of-bounds heap read.
Replace the != -1 guard with >= 0 && < env->nr_cpus_avail in all six functions. The >= 0 check also catches -1 and any other negative values that could bypass the old check.
Affected functions:
- perf_env__get_socket_aggr_by_cpu()
- perf_env__get_die_aggr_by_cpu()
- perf_env__get_cache_aggr_by_cpu()
- perf_env__get_cluster_aggr_by_cpu()
- perf_env__get_core_aggr_by_cpu()
- perf_env__get_cpu_aggr_by_cpu()
--- tools/perf/builtin-stat.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)
tools/perf/builtin-stat.c +7 -6
@@ -1565,7 +1565,8 @@ static struct aggr_cpu_id perf_env__get_socket_aggr_by_cpu(struct perf_cpu cpu,struct perf_env *env = data;struct aggr_cpu_id id =aggr_cpu_id__empty (); -if (cpu.cpu !=-1 ) +/* env->cpu[] has env->nr_cpus_avail entries; reject untrusted indices */ +if (cpu.cpu >=0 && cpu.cpu < env->nr_cpus_avail) id.socket = env->cpu[cpu.cpu].socket_id;return id;
@@ -1576,7 +1577,7 @@ static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(struct perf_cpu cpu, voistruct perf_env *env = data;struct aggr_cpu_id id =aggr_cpu_id__empty (); -if (cpu.cpu !=-1 ) { +if (cpu.cpu >=0 && cpu.cpu < env->nr_cpus_avail) {/* * die_id is relative to socket, so start * with the socket ID and then add die to
@@ -1632,7 +1633,7 @@ static struct aggr_cpu_id perf_env__get_cache_aggr_by_cpu(struct perf_cpu cpu,struct perf_env *env = data;struct aggr_cpu_id id =aggr_cpu_id__empty (); -if (cpu.cpu !=-1 ) { +if (cpu.cpu >=0 && cpu.cpu < env->nr_cpus_avail) {u32 cache_level = (perf_stat.aggr_level) ?: stat_config.aggr_level; id.socket = env->cpu[cpu.cpu].socket_id;
@@ -1649,7 +1650,7 @@ static struct aggr_cpu_id perf_env__get_cluster_aggr_by_cpu(struct perf_cpu cpu,struct perf_env *env = data;struct aggr_cpu_id id =aggr_cpu_id__empty (); -if (cpu.cpu !=-1 ) { +if (cpu.cpu >=0 && cpu.cpu < env->nr_cpus_avail) { id.socket = env->cpu[cpu.cpu].socket_id; id.die = env->cpu[cpu.cpu].die_id; id.cluster = env->cpu[cpu.cpu].cluster_id;
@@ -1663,7 +1664,7 @@ static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(struct perf_cpu cpu, vostruct perf_env *env = data;struct aggr_cpu_id id =aggr_cpu_id__empty (); -if (cpu.cpu !=-1 ) { +if (cpu.cpu >=0 && cpu.cpu < env->nr_cpus_avail) {/* * core_id is relative to socket, die and cluster, we need a * global id. So we set socket, die id, cluster id and core id.
@@ -1682,7 +1683,7 @@ static struct aggr_cpu_id perf_env__get_cpu_aggr_by_cpu(struct perf_cpu cpu, voistruct perf_env *env = data;struct aggr_cpu_id id =aggr_cpu_id__empty (); -if (cpu.cpu !=-1 ) { +if (cpu.cpu >=0 && cpu.cpu < env->nr_cpus_avail) {/* * core_id is relative to socket and die, * we need a global id. So we set
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 645/1611 perf c2c: Bounds-check CPU and node IDs before bitmap and array access
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 65117c3da50f749f4c22eb7a7effc53453dff57f ]
c2c_he__set_cpu() passes sample->cpu directly to __set_bit(cpu, cpuset) after only checking for the (u32)-1 sentinel. The cpuset bitmap is allocated with c2c.cpus_cnt bits (from env->nr_cpus_avail), so a crafted perf.data with CPU IDs exceeding that count causes out-of-bounds heap writes.
c2c_he__set_node() similarly passes the node ID from mem2node__node() to __set_bit(node, nodeset) after only checking for negative values. The nodeset bitmap is sized to c2c.nodes_cnt (from env->nr_numa_nodes), so a node ID exceeding that causes OOB writes.
process_sample_event() indexes c2c.cpu2node[cpu] and c2c_he->node_stats[node] without bounds checking. Both arrays are sized to c2c.cpus_cnt and c2c.nodes_cnt respectively.
Add bounds checks in all three paths:
- c2c_he__set_cpu(): return if sample->cpu >= c2c.cpus_cnt
- c2c_he__set_node(): return if node >= c2c.nodes_cnt
- process_sample_event(): clamp cpu to 0 if >= cpus_cnt, guard node_stats access with bounds check
--- tools/perf/builtin-c2c.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-)
tools/perf/builtin-c2c.c +17 -2
@@ -232,6 +232,10 @@ static void c2c_he__set_cpu(struct c2c_hist_entry *c2c_he, "WARNING: no sample cpu value"))return ; +/* cpuset bitmap has c2c.cpus_cnt bits from env->nr_cpus_avail */ +if (sample->cpu >= (unsigned int )c2c.cpus_cnt) +return ; +__set_bit (sample->cpu, c2c_he->cpuset); }
@@ -249,6 +253,10 @@ static void c2c_he__set_node(struct c2c_hist_entry *c2c_he,if (WARN_ONCE (node <0 ,"WARNING: failed to find node\n" ))return ; +/* nodeset bitmap has c2c.nodes_cnt bits from env->nr_numa_nodes */ +if (node >= c2c.nodes_cnt) +return ; +__set_bit (node, c2c_he->nodeset);if (c2c_he->paddr != sample->phys_addr) {
@@ -348,7 +356,12 @@ static int process_sample_event(const struct perf_tool *tool __maybe_unused,* Doing node stats only for single callchain data. */ int cpu = sample->cpu == (unsigned int )-1 ?0 : sample->cpu; -int node = c2c.cpu2node[cpu]; +int node; + +/* cpu2node[] has c2c.cpus_cnt entries; large u32 wraps signed negative */ +if (cpu <0 || cpu >= c2c.cpus_cnt) + cpu =0 ; + node = c2c.cpu2node[cpu]; mi = mi_dup;
@@ -365,7 +378,9 @@ static int process_sample_event(const struct perf_tool *tool __maybe_unused, c2c_he = container_of(he, struct c2c_hist_entry, he);c2c_add_stats (&c2c_he->stats, &stats);c2c_add_stats (&c2c_hists->stats, &stats); -c2c_add_stats (&c2c_he->node_stats[node], &stats); +/* node_stats[] has c2c.nodes_cnt entries */ +if (node >=0 && node < c2c.nodes_cnt) +c2c_add_stats (&c2c_he->node_stats[node], &stats);compute_stats (c2c_he, &stats, sample->weight);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 646/1611 perf c2c: Bounds-check CPU IDs in setup_nodes() topology loop
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 5fb2e6ad8c5d6b3b380f94c7456595511f3731be ]
setup_nodes() iterates CPU maps from the perf.data topology header and uses cpu.cpu directly as an array index into cpu2node[] (allocated with c2c.cpus_cnt = env->nr_cpus_avail entries) and __set_bit(cpu.cpu, set) (bitmap also sized to c2c.cpus_cnt).
A crafted perf.data with topology CPU IDs exceeding nr_cpus_avail causes out-of-bounds heap writes into both the cpu2node array and the per-node bitmap.
Add a bounds check to skip CPU IDs that fall outside the valid range.
--- tools/perf/builtin-c2c.c | 4 ++++ 1 file changed, 4 insertions(+)
tools/perf/builtin-c2c.c +4 -0
@@ -2327,6 +2327,10 @@ static int setup_nodes(struct perf_session *session) nodes[node] = set;perf_cpu_map__for_each_cpu_skip_any (cpu, idx, map) { +/* topology CPU IDs from perf.data may exceed nr_cpus_avail */ +if (cpu.cpu <0 || cpu.cpu >= c2c.cpus_cnt) +continue ; +__set_bit (cpu.cpu, set);if (WARN_ONCE (cpu2node[cpu.cpu] !=-1 ,"node/cpu topology bug" ))
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 647/1611 perf sched: Clean up idle_threads entry on init failure
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit cda5a94ad9181cd60cbf04be11d524201bf489a2 ]
get_idle_thread() allocates a thread via thread__new() and stores it in idle_threads[cpu], then calls init_idle_thread() to set up the private data. If init_idle_thread() fails (e.g. OOM for the idle_thread_runtime struct), the function returns NULL but leaves the partially initialized thread in idle_threads[cpu].
On subsequent calls for the same CPU, get_idle_thread() finds a non-NULL idle_threads[cpu], skips allocation, and returns thread__get() on a thread that has no priv data. Callers then get a thread whose thread__priv() returns NULL, leading to unexpected behavior.
Release the thread and reset the slot to NULL on init failure so the entry doesn't persist in a corrupted state.
--- tools/perf/builtin-sched.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
tools/perf/builtin-sched.c +4 -1
@@ -2507,8 +2507,11 @@ static struct thread *get_idle_thread(int cpu) idle_threads[cpu] =thread__new (0 ,0 );if (idle_threads[cpu]) { -if (init_idle_thread (idle_threads[cpu]) <0 ) +if (init_idle_thread (idle_threads[cpu]) <0 ) { +/* clean up so next call doesn't find a half-initialized thread */ +thread__zput (idle_threads[cpu]);return NULL ; + } } }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 648/1611 perf sched: Use thread__put() in free_idle_threads()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit a99d6394cd48fed75b1d24733d5afe6837a61a3f ]
free_idle_threads() calls thread__delete() directly instead of thread__put(), bypassing the reference counting lifecycle. Under REFCNT_CHECKING builds, this leaks the pointer handle since thread__delete() frees the object without going through the refcount wrapper.
The idle threads are created via thread__new() (refcount=1) in get_idle_thread(). Callers get additional references via thread__get() which they release with thread__put(). free_idle_threads() drops the base reference — thread__put() is the correct call, matching the thread__new() acquisition.
--- tools/perf/builtin-sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/builtin-sched.c +1 -1
@@ -2474,7 +2474,7 @@ static void free_idle_threads(void)if (itr)thread__put (itr->last_thread); -thread__delete (idle); +thread__put (idle); } }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 649/1611 perf sched: Replace BUG_ON and add NULL checks in replay event helpers
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 75eafe4a3a93a0143a20c0cc286bfb9008ac1478 ]
get_new_event() has three issues:
1. The zalloc() result is dereferenced without a NULL check, crashing on allocation failure.
2. BUG_ON(!task->atoms) kills the process when realloc() fails. Since perf.data is untrusted input, this should be a graceful error.
3. The realloc pattern assigns directly to task->atoms, losing the old pointer on failure. task->nr_events is also incremented before the realloc, leaving corrupted state on failure.
Fix get_new_event() to:
- Check the zalloc() result before dereferencing
- Use a temporary for realloc() to avoid losing the old pointer
- Increment nr_events only after successful realloc
- Return NULL instead of calling BUG_ON on failure
Also fix add_sched_event_wakeup() where zalloc() for wait_sem is passed to sem_init() without a NULL check.
Update all callers (add_sched_event_run, add_sched_event_wakeup, add_sched_event_sleep) to handle NULL returns by returning early. The replay may produce incomplete output on OOM but will not crash.
--- tools/perf/builtin-sched.c | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-)
tools/perf/builtin-sched.c +25 -3
@@ -358,14 +358,25 @@ get_new_event(struct task_desc *task, u64 timestamp)struct sched_atom *event =zalloc (sizeof (*event));unsigned long idx = task->nr_events;size_t size; +struct sched_atom **atoms_p; + +if (event ==NULL ) { +pr_err ("ERROR: sched: failed to allocate event\n" ); +return NULL ; + } event->timestamp = timestamp; event->nr = idx; + size =sizeof (struct sched_atom *) * (task->nr_events +1 ); + atoms_p =realloc (task->atoms, size); +if (!atoms_p) { +pr_err ("ERROR: sched: failed to grow atoms array\n" ); +free (event); +return NULL ; + } + task->atoms = atoms_p; task->nr_events++; - size =sizeof (struct sched_atom *) * task->nr_events; - task->atoms =realloc (task->atoms, size); -BUG_ON (!task->atoms); task->atoms[idx] = event;
@@ -396,6 +407,8 @@ static void add_sched_event_run(struct perf_sched *sched, struct task_desc *task } event =get_new_event (task, timestamp); +if (event ==NULL ) +return ; event->type =SCHED_EVENT_RUN ; event->duration = duration;
@@ -409,6 +422,8 @@ static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *tstruct sched_atom *event, *wakee_event; event =get_new_event (task, timestamp); +if (event ==NULL ) +return ; event->type =SCHED_EVENT_WAKEUP ; event->wakee = wakee;
@@ -423,6 +438,10 @@ static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *t } wakee_event->wait_sem =zalloc (sizeof (*wakee_event->wait_sem)); +if (!wakee_event->wait_sem) { +pr_err ("ERROR: sched: failed to allocate semaphore\n" ); +return ; + }sem_init (wakee_event->wait_sem,0 ,0 ); event->wait_sem = wakee_event->wait_sem;
@@ -434,6 +453,9 @@ static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *ta {struct sched_atom *event =get_new_event (task, timestamp); +if (event ==NULL ) +return ; + event->type =SCHED_EVENT_SLEEP ; sched->nr_sleep_events++;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 650/1611 perf mmap: Fix NULL deref in aio cleanup on alloc failure
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 25627346b10e6a564610ea2c49dc6dd54812226d ]
perf_mmap__aio_mmap() sets map->aio.nr_cblocks before allocating the data array. If calloc() for aiocb or cblocks fails before the data array is allocated, the return -1 path leads to perf_mmap__aio_munmap() which loops nr_cblocks times calling perf_mmap__aio_free(). Both versions of perf_mmap__aio_free() (NUMA and non-NUMA) dereference map->aio.data[idx] without checking if data is NULL, causing a NULL pointer dereference.
Add NULL checks for map->aio.data at the top of both perf_mmap__aio_free() variants so the cleanup path is safe when allocation fails partway through perf_mmap__aio_mmap().
--- tools/perf/util/mmap.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
tools/perf/util/mmap.c +6 -4
@@ -88,10 +88,10 @@ static int perf_mmap__aio_alloc(struct mmap *map, int idx)static void perf_mmap__aio_free (struct mmap *map,int idx) { -if (map->aio.data[idx]) { -munmap (map->aio.data[idx],mmap__mmap_len (map)); - map->aio.data[idx] =NULL ; - } +if (!map->aio.data || !map->aio.data[idx]) +return ; +munmap (map->aio.data[idx],mmap__mmap_len (map)); + map->aio.data[idx] =NULL ; }static int perf_mmap__aio_bind (struct mmap *map,int idx,struct perf_cpu cpu,int affinity)
@@ -140,6 +140,8 @@ static int perf_mmap__aio_alloc(struct mmap *map, int idx)static void perf_mmap__aio_free (struct mmap *map,int idx) { +if (!map->aio.data) +return ;zfree (&(map->aio.data[idx])); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 651/1611 perf stat: Introduce perf_env__get_cpu_topology() to guard NULL env->cpu
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit afa4363a91a19dff65dceb7fbce7bba689bbc854 ]
process_cpu_topology() in header.c frees env->cpu on old-format perf.data files that predate topology information, but leaves nr_cpus_avail set. The six perf_env__get_*_aggr_by_cpu() functions in builtin-stat.c pass the bounds check but dereference a NULL env->cpu pointer, crashing on old recordings.
Introduce perf_env__get_cpu_topology() as a safe accessor that validates env->cpu, cpu.cpu >= 0, and cpu.cpu < nr_cpus_avail in one place, returning a struct cpu_topology_map pointer or NULL. Convert all six topology aggregation callbacks to use it.
--- tools/perf/builtin-stat.c | 51 +++++++++++++++++++++------------------ tools/perf/util/env.h | 14 +++++++++++ 2 files changed, 42 insertions(+), 23 deletions(-)
tools/perf/builtin-stat.c +28 -23
@@ -1564,10 +1564,10 @@ static struct aggr_cpu_id perf_env__get_socket_aggr_by_cpu(struct perf_cpu cpu, {struct perf_env *env = data;struct aggr_cpu_id id =aggr_cpu_id__empty (); +struct cpu_topology_map *topo =perf_env__get_cpu_topology (env, cpu); -/* env->cpu[] has env->nr_cpus_avail entries; reject untrusted indices */ -if (cpu.cpu >=0 && cpu.cpu < env->nr_cpus_avail) - id.socket = env->cpu[cpu.cpu].socket_id; +if (topo) + id.socket = topo->socket_id;return id; }
@@ -1576,15 +1576,16 @@ static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(struct perf_cpu cpu, voi {struct perf_env *env = data;struct aggr_cpu_id id =aggr_cpu_id__empty (); +struct cpu_topology_map *topo =perf_env__get_cpu_topology (env, cpu); -if (cpu.cpu >=0 && cpu.cpu < env->nr_cpus_avail) { +if (topo) {/* * die_id is relative to socket, so start * with the socket ID and then add die to * make a unique ID. */ - id.socket = env->cpu[cpu.cpu].socket_id; - id.die = env->cpu[cpu.cpu].die_id; + id.socket = topo->socket_id; + id.die = topo->die_id; }return id;
@@ -1632,12 +1633,13 @@ static struct aggr_cpu_id perf_env__get_cache_aggr_by_cpu(struct perf_cpu cpu, {struct perf_env *env = data;struct aggr_cpu_id id =aggr_cpu_id__empty (); +struct cpu_topology_map *topo =perf_env__get_cpu_topology (env, cpu); -if (cpu.cpu >=0 && cpu.cpu < env->nr_cpus_avail) { +if (topo) {u32 cache_level = (perf_stat.aggr_level) ?: stat_config.aggr_level; - id.socket = env->cpu[cpu.cpu].socket_id; - id.die = env->cpu[cpu.cpu].die_id; + id.socket = topo->socket_id; + id.die = topo->die_id;perf_env__get_cache_id_for_cpu (cpu, env, cache_level, &id); }
@@ -1649,11 +1651,12 @@ static struct aggr_cpu_id perf_env__get_cluster_aggr_by_cpu(struct perf_cpu cpu, {struct perf_env *env = data;struct aggr_cpu_id id =aggr_cpu_id__empty (); +struct cpu_topology_map *topo =perf_env__get_cpu_topology (env, cpu); -if (cpu.cpu >=0 && cpu.cpu < env->nr_cpus_avail) { - id.socket = env->cpu[cpu.cpu].socket_id; - id.die = env->cpu[cpu.cpu].die_id; - id.cluster = env->cpu[cpu.cpu].cluster_id; +if (topo) { + id.socket = topo->socket_id; + id.die = topo->die_id; + id.cluster = topo->cluster_id; }return id;
@@ -1663,16 +1666,17 @@ static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(struct perf_cpu cpu, vo {struct perf_env *env = data;struct aggr_cpu_id id =aggr_cpu_id__empty (); +struct cpu_topology_map *topo =perf_env__get_cpu_topology (env, cpu); -if (cpu.cpu >=0 && cpu.cpu < env->nr_cpus_avail) { +if (topo) {/* * core_id is relative to socket, die and cluster, we need a * global id. So we set socket, die id, cluster id and core id. */ - id.socket = env->cpu[cpu.cpu].socket_id; - id.die = env->cpu[cpu.cpu].die_id; - id.cluster = env->cpu[cpu.cpu].cluster_id; - id.core = env->cpu[cpu.cpu].core_id; + id.socket = topo->socket_id; + id.die = topo->die_id; + id.cluster = topo->cluster_id; + id.core = topo->core_id; }return id;
@@ -1682,18 +1686,19 @@ static struct aggr_cpu_id perf_env__get_cpu_aggr_by_cpu(struct perf_cpu cpu, voi {struct perf_env *env = data;struct aggr_cpu_id id =aggr_cpu_id__empty (); +struct cpu_topology_map *topo =perf_env__get_cpu_topology (env, cpu); -if (cpu.cpu >=0 && cpu.cpu < env->nr_cpus_avail) { +if (topo) {/* * core_id is relative to socket and die, * we need a global id. So we set * socket, die id and core id */ - id.socket = env->cpu[cpu.cpu].socket_id; - id.die = env->cpu[cpu.cpu].die_id; - id.core = env->cpu[cpu.cpu].core_id; - id.cpu = cpu; + id.socket = topo->socket_id; + id.die = topo->die_id; + id.core = topo->core_id; } + id.cpu = cpu;return id; }
tools/perf/util/env.h +14 -0
@@ -164,6 +164,20 @@ const char *perf_env__pmu_mappings(struct perf_env *env);int perf_env__read_cpu_topology_map (struct perf_env *env); +/* +* Safe accessor for env->cpu[] topology array. env->cpu can be NULL when +* reading old-format perf.data that predates topology information — +* process_cpu_topology() in header.c frees it while nr_cpus_avail remains +* set, so callers must not index env->cpu[] without this check. +*/ +static inline struct cpu_topology_map * +perf_env__get_cpu_topology (struct perf_env *env,struct perf_cpu cpu) +{ +if (env->cpu && cpu.cpu >=0 && cpu.cpu < env->nr_cpus_avail) +return &env->cpu[cpu.cpu]; +return NULL ; +} +void cpu_cache_level__free (struct cpu_cache_level *cache);const char *perf_env__arch (struct perf_env *env);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 652/1611 perf c2c: Fix use-after-free in he__get_c2c_hists() error path
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 5e5e6196d737c5be03d20647428316b36621608d ]
he__get_c2c_hists() assigns c2c_he->hists before calling c2c_hists__init(). If init fails, the error path calls free(hists) but leaves c2c_he->hists pointing to freed memory. On teardown, c2c_he_free() finds the non-NULL pointer and calls hists__delete_entries() on it, causing a use-after-free.
Set c2c_he->hists to NULL before freeing so teardown skips the already-freed allocation.
--- tools/perf/builtin-c2c.c | 1 + 1 file changed, 1 insertion(+)
tools/perf/builtin-c2c.c +1 -0
@@ -218,6 +218,7 @@ he__get_c2c_hists(struct hist_entry *he, ret =c2c_hists__init (hists, sort, nr_header_lines, env);if (ret) { + c2c_he->hists =NULL ;free (hists);return NULL ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 653/1611 perf timechart: Fix cpu2y() OOB read on untrusted CPU index
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit e2496db45bfd8dfb6154ec415798fee330f1cc0a ]
cpu2y() indexes topology_map[cpu] without bounds checking. The array is allocated with nr_cpus entries (from env->nr_cpus_online), but callers pass sample CPU values from perf.data which can exceed that size with cross-machine recordings.
Track the topology_map allocation size and bounds-check the CPU argument in cpu2y() before indexing. Out-of-bounds CPUs fall back to the identity mapping (cpu2slot(cpu)), which is the same behavior as when no topology is available.
--- tools/perf/util/svghelper.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
tools/perf/util/svghelper.c +6 -4
@@ -47,13 +47,13 @@ static double cpu2slot(int cpu) }static int *topology_map; +static int topology_map_size;static double cpu2y (int cpu) { -if (topology_map) +if (topology_map && cpu >=0 && cpu < topology_map_size)return cpu2slot (topology_map[cpu]) *SLOT_MULT ; -else -return cpu2slot (cpu) *SLOT_MULT ; +return cpu2slot (cpu) *SLOT_MULT ; }static double time2pixels (u64 __time)
@@ -735,7 +735,8 @@ static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus)return -1 ;perf_cpu_map__for_each_cpu (cpu, idx, map) { -if (cpu.cpu >= nr_cpus) { +/* perf_cpu_map__new("") returns cpu.cpu == -1 */ +if (cpu.cpu <0 || cpu.cpu >= nr_cpus) { ret =-1 ;break ; }
@@ -793,6 +794,7 @@ int svg_build_topology_map(struct perf_env *env)fprintf (stderr,"topology: no memory\n" ); goto exit; } + topology_map_size = nr_cpus;for (i =0 ; i < nr_cpus; i++) topology_map[i] =-1 ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 654/1611 perf tools: Fix int16_t truncation of max_cpu_num in set_max_cpu_num()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 33fa2bf5608fc36bc25231592145f4738f14f11b ]
set_max_cpu_num() assigns the sysfs "possible" CPU count to max_cpu_num.cpu which is int16_t (struct perf_cpu). On systems with >32767 possible CPUs the value silently truncates, potentially wrapping negative. This causes cpunode_map to be underallocated and subsequent cpu__get_node() calls to read out of bounds.
The matching check for max_present_cpu_num was added by commit c760174401f6 ("perf cpumap: Reduce cpu size from int to int16_t") but max_cpu_num was missed. Add the same INT16_MAX guard.
--- tools/perf/util/cpumap.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-)
tools/perf/util/cpumap.c +17 -4
@@ -466,6 +466,16 @@ static void set_max_cpu_num(void)if (ret) goto out; +/* +* struct perf_cpu.cpu is int16_t (libperf ABI) — clamp to avoid +* truncation to negative. See tools/lib/perf/TODO for the ABI +* widening plan. +*/ +if (max >INT16_MAX ) { +pr_warning ("WARNING: max possible cpus %d exceeds int16_t, clamping to %d\n" , + max,INT16_MAX ); + max =INT16_MAX ; + } max_cpu_num.cpu = max;/* get the highest present cpu number for a sparse allocation */
@@ -478,11 +488,12 @@ static void set_max_cpu_num(void) ret =get_max_num (path, &max);if (!ret && max >INT16_MAX ) { -pr_err ("Read out of bounds max cpus of %d\n" , max); - ret =-1 ; +pr_warning ("WARNING: max present cpus %d exceeds int16_t, clamping to %d\n" , + max,INT16_MAX ); + max =INT16_MAX ; }if (!ret) - max_present_cpu_num.cpu = (int16_t )max; + max_present_cpu_num.cpu = max; out:if (ret)pr_err ("Failed to read max cpus, using default of %d\n" , max_cpu_num.cpu);
@@ -619,7 +630,9 @@ int cpu__setup_cpunode_map(void)while ((dent2 =readdir (dir2)) !=NULL ) {if (dent2->d_type !=DT_LNK ||sscanf (dent2->d_name,"cpu%u" , &cpu) <1 )continue ; - cpunode_map[cpu] = mem; +/* cpunode_map allocated for max_cpu_num entries */ +if (cpu < (unsigned int )max_cpu_num.cpu) + cpunode_map[cpu] = mem; }closedir (dir2); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 655/1611 dt-bindings: clock: qcom: Add X1P42100 camera clock controller
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jagadeesh Kona <[email protected]>
[ Upstream commit 97a5e120be5d3d7cf7d221b8703921046b73f0d2 ]
Add X1P42100 camera clock controller support and clock bindings for camera QDSS debug clocks which are applicable for both X1E80100 and X1P42100 platforms.
Stable-dep-of: 1e6ae74ac6f2 ("clk: qcom: camcc-x1e80100: Add support for camera QDSS debug clocks")
--- .../devicetree/bindings/clock/qcom,x1e80100-camcc.yaml | 1 + include/dt-bindings/clock/qcom,x1e80100-camcc.h | 3 +++ 2 files changed, 4 insertions(+)
Documentation/devicetree/bindings/clock/qcom,x1e80100-camcc.yaml +1 -0
@@ -23,6 +23,7 @@ properties: compatible: enum: - qcom,x1e80100-camcc + - qcom,x1p42100-camcc reg: maxItems: 1
include/dt-bindings/clock/qcom,x1e80100-camcc.h +3 -0
@@ -115,6 +115,9 @@#define CAM_CC_SLEEP_CLK_SRC 105#define CAM_CC_SLOW_AHB_CLK_SRC 106#define CAM_CC_XO_CLK_SRC 107 +#define CAM_CC_QDSS_DEBUG_CLK 108 +#define CAM_CC_QDSS_DEBUG_CLK_SRC 109 +#define CAM_CC_QDSS_DEBUG_XO_CLK 110/* CAM_CC power domains */ #define CAM_CC_BPS_GDSC 0
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 656/1611 clk: qcom: camcc-x1e80100: Add support for camera QDSS debug clocks
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jagadeesh Kona <[email protected]>
[ Upstream commit 1e6ae74ac6f28ace7a0eb84897c6e17bb044e5de ]
Add support for camera QDSS debug clocks on X1E80100 platform which are required to be voted for camera icp and cpas usecases. This change aligns the camcc driver to the new ABI exposed from X1E80100 camcc bindings that supports these camcc QDSS debug clocks.
--- drivers/clk/qcom/camcc-x1e80100.c | 64 +++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+)
drivers/clk/qcom/camcc-x1e80100.c +64 -0
@@ -1052,6 +1052,31 @@ static struct clk_rcg2 cam_cc_mclk7_clk_src = { }, }; +static const struct freq_tbl ftbl_cam_cc_qdss_debug_clk_src[] = { +F (19200000 ,P_BI_TCXO ,1 ,0 ,0 ), +F (60000000 ,P_CAM_CC_PLL8_OUT_EVEN ,8 ,0 ,0 ), +F (75000000 ,P_CAM_CC_PLL0_OUT_EVEN ,8 ,0 ,0 ), +F (150000000 ,P_CAM_CC_PLL0_OUT_EVEN ,4 ,0 ,0 ), +F (300000000 ,P_CAM_CC_PLL0_OUT_MAIN ,4 ,0 ,0 ), + { } +}; + +static struct clk_rcg2 cam_cc_qdss_debug_clk_src = { + .cmd_rcgr =0x13938 , + .mnd_width =0 , + .hid_width =5 , + .parent_map = cam_cc_parent_map_0, + .freq_tbl = ftbl_cam_cc_qdss_debug_clk_src, + .hw_clk_ctrl = true, + .clkr.hw.init = &(const struct clk_init_data ) { + .name ="cam_cc_qdss_debug_clk_src" , + .parent_data = cam_cc_parent_data_0, + .num_parents =ARRAY_SIZE (cam_cc_parent_data_0), + .flags =CLK_SET_RATE_PARENT , + .ops = &clk_rcg2_shared_ops, + }, +}; +static const struct freq_tbl ftbl_cam_cc_sfe_0_clk_src[] = {F (345600000 ,P_CAM_CC_PLL6_OUT_EVEN ,1 ,0 ,0 ),F (432000000 ,P_CAM_CC_PLL6_OUT_EVEN ,1 ,0 ,0 ),
@@ -2182,6 +2207,42 @@ static struct clk_branch cam_cc_mclk7_clk = { }, }; +static struct clk_branch cam_cc_qdss_debug_clk = { + .halt_reg =0x13a64 , + .halt_check =BRANCH_HALT , + .clkr = { + .enable_reg =0x13a64 , + .enable_mask =BIT (0 ), + .hw.init = &(const struct clk_init_data ) { + .name ="cam_cc_qdss_debug_clk" , + .parent_hws = (const struct clk_hw *[]) { + &cam_cc_qdss_debug_clk_src.clkr.hw, + }, + .num_parents =1 , + .flags =CLK_SET_RATE_PARENT , + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch cam_cc_qdss_debug_xo_clk = { + .halt_reg =0x13a68 , + .halt_check =BRANCH_HALT , + .clkr = { + .enable_reg =0x13a68 , + .enable_mask =BIT (0 ), + .hw.init = &(const struct clk_init_data ) { + .name ="cam_cc_qdss_debug_xo_clk" , + .parent_hws = (const struct clk_hw *[]) { + &cam_cc_xo_clk_src.clkr.hw, + }, + .num_parents =1 , + .flags =CLK_SET_RATE_PARENT , + .ops = &clk_branch2_ops, + }, + }, +}; +static struct clk_branch cam_cc_sfe_0_clk = { .halt_reg =0x133c0 , .halt_check =BRANCH_HALT ,
@@ -2398,6 +2459,9 @@ static struct clk_regmap *cam_cc_x1e80100_clocks[] = { [CAM_CC_PLL6_OUT_EVEN] = &cam_cc_pll6_out_even.clkr, [CAM_CC_PLL8] = &cam_cc_pll8.clkr, [CAM_CC_PLL8_OUT_EVEN] = &cam_cc_pll8_out_even.clkr, + [CAM_CC_QDSS_DEBUG_CLK] = &cam_cc_qdss_debug_clk.clkr, + [CAM_CC_QDSS_DEBUG_CLK_SRC] = &cam_cc_qdss_debug_clk_src.clkr, + [CAM_CC_QDSS_DEBUG_XO_CLK] = &cam_cc_qdss_debug_xo_clk.clkr, [CAM_CC_SFE_0_CLK] = &cam_cc_sfe_0_clk.clkr, [CAM_CC_SFE_0_CLK_SRC] = &cam_cc_sfe_0_clk_src.clkr, [CAM_CC_SFE_0_FAST_AHB_CLK] = &cam_cc_sfe_0_fast_ahb_clk.clkr,
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 657/1611 mshv: add bounds check on vp_index in mshv_intercept_isr()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Junrui Luo <[email protected]>
[ Upstream commit a4ffc59238be84dd1c26bf1c001543e832674fc6 ]
mshv_intercept_isr() extracts vp_index from the hypervisor message payload and uses it directly to index into pt_vp_array without validation. handle_bitset_message() and handle_pair_message() already validate vp_index against MSHV_MAX_VPS before array access.
Add the same MSHV_MAX_VPS bounds check for consistency with the other message handlers.
--- drivers/hv/mshv_synic.c | 5 +++++ 1 file changed, 5 insertions(+)
drivers/hv/mshv_synic.c +5 -0
@@ -375,6 +375,11 @@ mshv_intercept_isr(struct hv_message *msg)*/ vp_index = ((struct hv_opaque_intercept_message *)msg->u.payload)->vp_index; +/* This shouldn't happen, but just in case. */ +if (unlikely (vp_index >=MSHV_MAX_VPS )) { +pr_debug ("VP index %u out of bounds\n" , vp_index); + goto unlock_out; + } vp = partition->pt_vp_array[vp_index];if (unlikely (!vp)) {pr_debug ("failed to find VP %u\n" , vp_index);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 658/1611 dmaengine: qcom: gpi: set DMA_PRIVATE capability
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Icenowy Zheng <[email protected]>
[ Upstream commit 4e351f408743354d54ee1af5193fc78234f2044e ]
The GPI DMA controller is only responsible for QUP peripherals, and cannot work as a general-purpose DMA accelerator.
Set DMA_PRIVATE capability for it.
This fixes error messages about GPI being shown when an async-tx consumer is loaded.
--- drivers/dma/qcom/gpi.c | 1 + 1 file changed, 1 insertion(+)
drivers/dma/qcom/gpi.c +1 -0
@@ -2253,6 +2253,7 @@ static int gpi_probe(struct platform_device *pdev)/* clear and Set capabilities */ dma_cap_zero (gpi_dev->dma_device.cap_mask);dma_cap_set (DMA_SLAVE , gpi_dev->dma_device.cap_mask); +dma_cap_set (DMA_PRIVATE , gpi_dev->dma_device.cap_mask);/* configure dmaengine apis */ gpi_dev->dma_device.directions =BIT (DMA_DEV_TO_MEM ) |BIT (DMA_MEM_TO_DEV );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 659/1611 dmaengine: Fix possible use after free
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nuno Sá <[email protected]>
[ Upstream commit 92f853f0645aebf1d05d333e97ab7c342ace1892 ]
In dma_release_channel(), check chan->device->privatecnt after call dma_chan_put(). However, dma_chan_put() call dma_device_put() which could release the last reference of the device if the DMA provider is already gone and hence free it.
Fixes it by moving dma_chan_put() after the check.
--- drivers/dma/dmaengine.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/dma/dmaengine.c +2 -1
@@ -905,11 +905,12 @@ void dma_release_channel(struct dma_chan *chan)mutex_lock (&dma_list_mutex);WARN_ONCE (chan->client_count !=1 ,"chan reference count %d != 1\n" , chan->client_count); -dma_chan_put (chan);/* drop PRIVATE cap enabled by __dma_request_channel() */ if (--chan->device->privatecnt ==0 )dma_cap_clear (DMA_PRIVATE , chan->device->cap_mask); +dma_chan_put (chan); +if (chan->slave) {sysfs_remove_link (&chan->dev->device.kobj,DMA_SLAVE_NAME );sysfs_remove_link (&chan->slave->kobj, chan->name);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 660/1611 dmaengine: dma-axi-dmac: Properly free struct axi_dmac_desc
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nuno Sá <[email protected]>
[ Upstream commit 4910ce1b3b35687bb2a5e742c4bfbea3c647c980 ]
Use axi_dmac_free_desc() to free fully the descriptor at fail path when call axi_dmac_alloc_desc() in axi_dmac_prep_peripheral_dma_vec().
--- drivers/dma/dma-axi-dmac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/dma/dma-axi-dmac.c +1 -1
@@ -643,7 +643,7 @@ axi_dmac_prep_peripheral_dma_vec(struct dma_chan *c, const struct dma_vec *vecs,for (i =0 ; i < nb; i++) {if (!axi_dmac_check_addr (chan, vecs[i].addr) || !axi_dmac_check_len (chan, vecs[i].len)) { -kfree (desc); +axi_dmac_free_desc (desc);return NULL ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 661/1611 dmaengine: dma-axi-dmac: use DMA pool to manange DMA descriptor
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nuno Sá <[email protected]>
[ Upstream commit 9e942c8579130e62734c14338e9f451780669164 ]
For architectures like Microblaze or arm64 (where this IP is used), DMA_DIRECT_REMAP is set which means that dma_alloc_coherent() might remap (and hence vmalloc()) some memory. This became visible in a design where dma_direct_use_pool() is not possible.
With the above, when calling dma_free_coherent(), vunmap() would be called from softirq context and thus leading to a BUG().
To fix it, use a dma pool that is allocated in .device_alloc_chan_resources() and allocate blocks from it. The key point is that now dma_pool_free() is used in axi_dmac_free_desc() to free the blocks and that just frees the blocks from the pool in the sense they can be used again. In other words, no actual call to dma_free_coherent() happens. That only happens when destroying the pool in axi_dmac_free_chan_resources() which does not happen in any interrupt context.
--- drivers/dma/dma-axi-dmac.c | 66 +++++++++++++++++++++++--------------- 1 file changed, 40 insertions(+), 26 deletions(-)
drivers/dma/dma-axi-dmac.c +40 -26
@@ -12,6 +12,7 @@#include <linux/device.h> #include <linux/dma-mapping.h> #include <linux/dmaengine.h> +#include <linux/dmapool.h> #include <linux/err.h> #include <linux/interrupt.h> #include <linux/io.h>
@@ -143,6 +144,7 @@ struct axi_dmac_chan {struct virt_dma_chan vchan;struct axi_dmac_desc *next_desc; +void *pool;struct list_head active_descs;enum dma_transfer_direction direction;
@@ -524,11 +526,17 @@ static void axi_dmac_issue_pending(struct dma_chan *c)spin_unlock_irqrestore (&chan->vchan.lock, flags); } +static void axi_dmac_free_desc (struct axi_dmac_desc *desc) +{ +for (unsigned int i =0 ; i < desc->num_sgs; i++) +dma_pool_free (desc->chan->pool, desc->sg[i].hw, desc->sg[i].hw_phys); + +kfree (desc); +} +static struct axi_dmac_desc *axi_dmac_alloc_desc (struct axi_dmac_chan *chan,unsigned int num_sgs) { -struct axi_dmac *dmac =chan_to_axi_dmac (chan); -struct device *dev = dmac->dma_dev.dev;struct axi_dmac_hw_desc *hws;struct axi_dmac_desc *desc;dma_addr_t hw_phys;
@@ -540,22 +548,22 @@ axi_dmac_alloc_desc(struct axi_dmac_chan *chan, unsigned int num_sgs) desc->num_sgs = num_sgs; desc->chan = chan; - hws =dma_alloc_coherent (dev,PAGE_ALIGN (num_sgs *sizeof (*hws)), - &hw_phys,GFP_ATOMIC ); -if (!hws) { -kfree (desc); -return NULL ; - } -for (i =0 ; i < num_sgs; i++) { - desc->sg[i].hw = &hws[i]; - desc->sg[i].hw_phys = hw_phys + i *sizeof (*hws); + hws =dma_pool_zalloc (chan->pool,GFP_NOWAIT , &hw_phys); +if (!hws) { + desc->num_sgs = i; +axi_dmac_free_desc (desc); +return NULL ; + } + + desc->sg[i].hw = hws; + desc->sg[i].hw_phys = hw_phys; - hws[i].id =AXI_DMAC_SG_UNUSED ; - hws[i].flags =0 ; + hws->id =AXI_DMAC_SG_UNUSED ;/* Link hardware descriptors */ - hws[i].next_sg_addr = hw_phys + (i +1 ) *sizeof (*hws); +if (i) + desc->sg[i -1 ].hw->next_sg_addr = hw_phys; }/* The last hardware descriptor will trigger an interrupt */
@@ -564,18 +572,6 @@ axi_dmac_alloc_desc(struct axi_dmac_chan *chan, unsigned int num_sgs)return desc; } -static void axi_dmac_free_desc (struct axi_dmac_desc *desc) -{ -struct axi_dmac *dmac =chan_to_axi_dmac (desc->chan); -struct device *dev = dmac->dma_dev.dev; -struct axi_dmac_hw_desc *hw = desc->sg[0 ].hw; -dma_addr_t hw_phys = desc->sg[0 ].hw_phys; - -dma_free_coherent (dev,PAGE_ALIGN (desc->num_sgs *sizeof (*hw)), - hw, hw_phys); -kfree (desc); -} - static struct axi_dmac_sg *axi_dmac_fill_linear_sg(struct axi_dmac_chan *chan, enum dma_transfer_direction direction, dma_addr_t addr, unsigned int num_periods, unsigned int period_len,
@@ -807,9 +803,26 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_interleaved(return vchan_tx_prep (&chan->vchan, &desc->vdesc, flags); } +static int axi_dmac_alloc_chan_resources (struct dma_chan *c) +{ +struct axi_dmac_chan *chan =to_axi_dmac_chan (c); +struct device *dev = c->device->dev; + + chan->pool =dma_pool_create (dev_name (dev), dev, +sizeof (struct axi_dmac_hw_desc ), + __alignof__(struct axi_dmac_hw_desc ),0 ); +if (!chan->pool) +return -ENOMEM ; + +return 0 ; +} +static void axi_dmac_free_chan_resources (struct dma_chan *c) { +struct axi_dmac_chan *chan =to_axi_dmac_chan (c); +vchan_free_chan_resources (to_virt_chan (c)); +dma_pool_destroy (chan->pool); }static void axi_dmac_desc_free (struct virt_dma_desc *vdesc)
@@ -1093,6 +1106,7 @@ static int axi_dmac_probe(struct platform_device *pdev)dma_cap_set (DMA_SLAVE , dma_dev->cap_mask);dma_cap_set (DMA_CYCLIC , dma_dev->cap_mask);dma_cap_set (DMA_INTERLEAVE , dma_dev->cap_mask); + dma_dev->device_alloc_chan_resources = axi_dmac_alloc_chan_resources; dma_dev->device_free_chan_resources = axi_dmac_free_chan_resources; dma_dev->device_tx_status = dma_cookie_status; dma_dev->device_issue_pending = axi_dmac_issue_pending;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 662/1611 clk: qcom: a53: Corrected frequency multiplier for 1152MHz
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Phillip Varney <[email protected]>
[ Upstream commit bb56147ea9fce98ebde1d367335ba006cba61fbd ]
The 1152MHz frequency entry for the a53 currently selects a multiplier of 62, giving 1190MHz. This changes the mulitiplier to 60 giving the intended 1152MHz.
--- drivers/clk/qcom/a53-pll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/clk/qcom/a53-pll.c +1 -1
@@ -20,7 +20,7 @@static const struct pll_freq_tbl a53pll_freq[] = { {998400000 ,52 ,0x0 ,0x1 ,0 }, {1094400000 ,57 ,0x0 ,0x1 ,0 }, - {1152000000 ,62 ,0x0 ,0x1 ,0 }, + {1152000000 ,60 ,0x0 ,0x1 ,0 }, {1209600000 ,63 ,0x0 ,0x1 ,0 }, {1248000000 ,65 ,0x0 ,0x1 ,0 }, {1363200000 ,71 ,0x0 ,0x1 ,0 },
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 663/1611 sunrpc: Fix error handling in rpc_sysfs_xprt_switch_add_xprt_store()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hongling Zeng <[email protected]>
[ Upstream commit 37957478be021b92981aa4c99b69f308d3b784d0 ]
xprt_create_transport() never returns NULL, only valid pointers or error pointers. Using IS_ERR_OR_NULL() is incorrect, and PTR_ERR(NULL) would return 0, which indicates EOF in a sysfs store function.
Fix this by using IS_ERR() instead of IS_ERR_OR_NULL().
--- net/sunrpc/sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/sunrpc/sysfs.c +1 -1
@@ -347,7 +347,7 @@ static ssize_t rpc_sysfs_xprt_switch_add_xprt_store(struct kobject *kobj, xprt_create_args.reconnect_timeout = xprt->max_reconnect_timeout; new =xprt_create_transport (&xprt_create_args); -if (IS_ERR_OR_NULL (new)) { +if (IS_ERR (new)) { count =PTR_ERR (new); goto out_put_xprt; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 664/1611 pNFS/filelayout: fix cheking if a layout is striped
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sagi Grimberg <[email protected]>
[ Upstream commit 91668417d4e925c98cae4a55b1b9860380ddbf16 ]
A layout can still be striped with num_fh = 1 as it is perfectly possible that both MDS and DSs can handle the same filehandle. Hence check according to stripe_count > 1, which is the correct check to begin with.
We should not be called with flseg->dsaddr = NULL, but if for some reason we do, return our best guess with is flseg->num_fh > 1.
--- fs/nfs/filelayout/filelayout.c | 2 ++ 1 file changed, 2 insertions(+)
fs/nfs/filelayout/filelayout.c +2 -0
@@ -778,6 +778,8 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,static bool filelayout_lseg_is_striped (const struct nfs4_filelayout_segment *flseg) { +if (flseg->dsaddr) +return flseg->dsaddr->stripe_count >1 ;return flseg->num_fh >1 ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 665/1611 xprtrdma: Avoid 250 ms delay on backlog wakeup
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Chuck Lever <[email protected]>
[ Upstream commit 100142093e22b3f7741ac88e94878bb3694e306f ]
Commit a721035477fb ("SUNRPC/xprt: async tasks mustn't block waiting for memory") changed xprt_rdma_alloc_slot() to set tk_status to -ENOMEM so that call_reserveresult() would sleep HZ/4 before retrying. That rationale applies to xprt_dynamic_alloc_slot(), where an immediate retry under memory pressure wastes CPU, but not to the RDMA backlog path: a task woken from the backlog has a slot waiting for it, so the 250 ms rpc_delay adds latency without benefit.
This also aligns the code with the existing kernel-doc for xprt_rdma_alloc_slot(), which already documented %-EAGAIN.
Stable-dep-of: e786233d2e0b ("xprtrdma: Decouple req recycling from RPC completion")
--- net/sunrpc/xprtrdma/transport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/sunrpc/xprtrdma/transport.c +1 -1
@@ -510,7 +510,7 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task)return ; out_sleep: - task->tk_status = -ENOMEM ; + task->tk_status = -EAGAIN ;xprt_add_backlog (xprt, task); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 666/1611 xprtrdma: Close lost-wakeup race in xprt_rdma_alloc_slot
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Chuck Lever <[email protected]>
[ Upstream commit 765bde47fe7f197dabeb12da76831f40d0b20377 ]
xprt_rdma_alloc_slot() and xprt_rdma_free_slot() lack serialization between the buffer pool and the backlog queue. A buffer freed after rpcrdma_buffer_get() finds the pool empty but before rpc_sleep_on() places the task on the backlog is returned to the pool with no waiter to wake, leaving the task stuck on the backlog indefinitely.
After joining the backlog, re-check the pool and route any recovered buffer through xprt_wake_up_backlog(), whose queue lock serializes with concurrent wakeups and avoids double-assignment of slots.
Because xprt_rdma_free_slot() does not hold reserve_lock, the XPRT_CONGESTED double-check in xprt_throttle_congested() is
ineffective: a task can join the backlog through that path after free_slot has already found it empty and cleared the bit. Avoid this by using xprt_add_backlog_noncongested(), which queues the task without setting XPRT_CONGESTED, so every allocation reaches xprt_rdma_alloc_slot() and its post-sleep re-check.
Stable-dep-of: e786233d2e0b ("xprtrdma: Decouple req recycling from RPC completion")
--- include/linux/sunrpc/xprt.h | 2 ++ net/sunrpc/xprt.c | 16 ++++++++++++++++ net/sunrpc/xprtrdma/transport.c | 15 ++++++++++++++- 3 files changed, 32 insertions(+), 1 deletion(-)
include/linux/sunrpc/xprt.h +2 -0
@@ -404,6 +404,8 @@ struct rpc_xprt * xprt_alloc(struct net *net, size_t size, unsigned int max_req);void xprt_free (struct rpc_xprt *);void xprt_add_backlog (struct rpc_xprt *xprt,struct rpc_task *task); +void xprt_add_backlog_noncongested (struct rpc_xprt *xprt, +struct rpc_task *task);bool xprt_wake_up_backlog (struct rpc_xprt *xprt,struct rpc_rqst *req);void xprt_cleanup_ids (void );
net/sunrpc/xprt.c +16 -0
@@ -1663,6 +1663,22 @@ void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) }EXPORT_SYMBOL_GPL (xprt_add_backlog); +/** +* xprt_add_backlog_noncongested - queue task on backlog +* @xprt: transport whose backlog queue receives the task +* @task: task to queue +* +* Like xprt_add_backlog, but does not set XPRT_CONGESTED. +* For transports whose free_slot path does not synchronize +* with xprt_throttle_congested via reserve_lock. +*/ +void xprt_add_backlog_noncongested (struct rpc_xprt *xprt, +struct rpc_task *task) +{ +rpc_sleep_on (&xprt->backlog, task, xprt_complete_request_init); +} +EXPORT_SYMBOL_GPL (xprt_add_backlog_noncongested); +static bool __xprt_set_rq (struct rpc_task *task,void *data) {struct rpc_rqst *req = data;
net/sunrpc/xprtrdma/transport.c +14 -1
@@ -511,7 +511,20 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) out_sleep: task->tk_status = -EAGAIN ; -xprt_add_backlog (xprt, task); +xprt_add_backlog_noncongested (xprt, task); +/* A buffer freed between buffer_get and rpc_sleep_on +* goes back to the pool with no waiter to wake. +* Re-check after joining the backlog to close that gap. +*/ + req =rpcrdma_buffer_get (&r_xprt->rx_buf); +if (req) { +struct rpc_rqst *rqst = &req->rl_slot; + +if (!xprt_wake_up_backlog (xprt, rqst)) { +memset (rqst,0 ,sizeof (*rqst)); +rpcrdma_buffer_put (&r_xprt->rx_buf, req); + } + } }/**
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 667/1611 xprtrdma: Post receive buffers after RPC completion
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Chuck Lever <[email protected]>
[ Upstream commit 704f3f640f72db4d44ec5ce3db8d4e150c974bc7 ]
rpcrdma_post_recvs() runs in CQ poll context and its cost falls on the latency-critical path between polling a Receive completion and waking the RPC consumer. Every cycle spent refilling the Receive Queue delays delivery of the reply to the NFS layer.
Move the rpcrdma_post_recvs() call in rpcrdma_reply_handler() to after the RPC has been decoded and completed. The larger batch size from the preceding patch provides sufficient Receive Queue headroom to absorb the brief delay before buffers are replenished.
Stable-dep-of: e786233d2e0b ("xprtrdma: Decouple req recycling from RPC completion")
--- net/sunrpc/xprtrdma/rpc_rdma.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-)
net/sunrpc/xprtrdma/rpc_rdma.c +9 -5
@@ -1471,7 +1471,6 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) credits =1 ;/* don't deadlock */ else if (credits > r_xprt->rx_ep->re_max_requests) credits = r_xprt->rx_ep->re_max_requests; -rpcrdma_post_recvs (r_xprt, credits + (buf->rb_bc_srv_max_requests <<1 ));if (buf->rb_credits != credits)rpcrdma_update_cwnd (r_xprt, credits);
@@ -1490,15 +1489,20 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)/* LocalInv completion will complete the RPC */ else kref_put(&req->rl_kref, rpcrdma_reply_done); -return ; -out_badversion: -trace_xprtrdma_reply_vers_err (rep); - goto out; +out_post: +rpcrdma_post_recvs (r_xprt, + credits + (buf->rb_bc_srv_max_requests <<1 )); +return ; out_norqst:spin_unlock (&xprt->queue_lock);trace_xprtrdma_reply_rqst_err (rep); +rpcrdma_rep_put (buf, rep); + goto out_post; + +out_badversion: +trace_xprtrdma_reply_vers_err (rep); goto out; out_shortreply:
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 668/1611 xprtrdma: Use sendctx DMA state for Send signaling
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Chuck Lever <[email protected]>
[ Upstream commit 2797ae7c929610fb2d2303a996a08173fa096730 ]
Send signaling matters only when the prepared Send has page mappings to unmap. Today that test is expressed indirectly with rl_kref, because the Send-side reference is taken only for Sends with mapped SGEs.
Split the SGE DMA unmap loop into its own helper and use sc_unmap_count directly for the signaling decision. This keeps the current behavior but removes one dependency on the old rl_kref semantics before the request lifetime rules are changed.
Stable-dep-of: e786233d2e0b ("xprtrdma: Decouple req recycling from RPC completion")
--- net/sunrpc/xprtrdma/frwr_ops.c | 2 +- net/sunrpc/xprtrdma/rpc_rdma.c | 22 +++++++++++++--------- 2 files changed, 14 insertions(+), 10 deletions(-)
net/sunrpc/xprtrdma/frwr_ops.c +1 -1
@@ -404,7 +404,7 @@ int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) ++num_wrs; } -if ((kref_read (&req->rl_kref) >1 ) || num_wrs > ep->re_send_count) { +if (req->rl_sendctx->sc_unmap_count || num_wrs > ep->re_send_count) { send_wr->send_flags |=IB_SEND_SIGNALED ; ep->re_send_count = min_t(unsigned int, ep->re_send_batch, num_wrs - ep->re_send_count);
net/sunrpc/xprtrdma/rpc_rdma.c +13 -9
@@ -526,19 +526,11 @@ static void rpcrdma_sendctx_done(struct kref *kref) rep->rr_rxprt->rx_stats.reply_waits_for_send++; } -/** -* rpcrdma_sendctx_unmap - DMA-unmap Send buffer -* @sc: sendctx containing SGEs to unmap -* -*/ -void rpcrdma_sendctx_unmap (struct rpcrdma_sendctx *sc) +static void rpcrdma_sendctx_dma_unmap (struct rpcrdma_sendctx *sc) {struct rpcrdma_regbuf *rb = sc->sc_req->rl_sendbuf;struct ib_sge *sge; -if (!sc->sc_unmap_count) -return ; -/* The first two SGEs contain the transport header and * the inline buffer. These are always left mapped so * they can be cheaply re-used.
@@ -547,7 +539,19 @@ void rpcrdma_sendctx_unmap(struct rpcrdma_sendctx *sc) ++sge, --sc->sc_unmap_count)ib_dma_unmap_page (rdmab_device (rb), sge->addr, sge->length,DMA_TO_DEVICE ); +} + +/** +* rpcrdma_sendctx_unmap - DMA-unmap Send buffer +* @sc: sendctx containing SGEs to unmap +* +*/ +void rpcrdma_sendctx_unmap (struct rpcrdma_sendctx *sc) +{ +if (!sc->sc_unmap_count) +return ; +rpcrdma_sendctx_dma_unmap (sc);kref_put (&sc->sc_req->rl_kref, rpcrdma_sendctx_done); }
Signature · 1 line
2.53.0