FAILED: patch "[PATCH] can: isotp: fix timer drain order, wakeup handling and tx_gen" failed to apply to 6.12-stable tree
Subsystems (2)
[email protected]
maintainerThe patch below does not apply to the 6.12-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y
git checkout FETCH_HEAD
git cherry-pick -x 050f010f920da17c1044a4f174766ad553e770b6
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026080551-puma-venture-46d7@gregkh' --subject-prefix 'PATCH 6.12.y' 'HEAD^..'
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 050f010f920da17c1044a4f174766ad553e770b6 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <[email protected]>
Date: Fri, 24 Jul 2026 20:15:25 +0200
Subject: [PATCH] can: isotp: fix timer drain order, wakeup handling and tx_gen
ordering
This patch is a follow-up to commit cf070fe33bfb ("can: isotp: serialize TX state transitions under so->rx_lock") which addresses following sashiko-bot findings:
- isotp_sendmsg(): drain so->txfrtimer first so a stale callback can't re-arm echotimer after the claim
- isotp_release(): wake so->wait after forcing ISOTP_SHUTDOWN so a sleeping sendmsg() claim isn't stranded
- isotp_sendmsg(): have both wait_event_interruptible() calls in isotp_sendmsg() also wake on ISOTP_SHUTDOWN and do not return claim to IDLE to avoid corrupting a concurrent isotp_release() process.
- isotp_sendmsg(): handle potential claim of a new transfer when the wait_event_interruptible() call returns in CAN_ISOTP_WAIT_TX_DONE mode. Don't touch timers and states of the new transfer if a new thread incremented so->tx_gen before getting the lock at err_event_drop.
- isotp_sendmsg(): handle a stuck can_send() and omit timer and state changes if a new transfer was claimed. wait_tx_done() returns the error recorded in so->tx_result[], tagged with the caller's own generation.
- isotp_tx_timeout(): on a claimed timeout, record the ECOMM error for the timed-out transfer's own generation in so->tx_result[]; sk->sk_err is raised unconditionally, same as every other error path here.
- isotp_tx_gen_done()/isotp_tx_timeout(): always read tx.state (acquire) before tx_gen - the reverse order let a weakly ordered CPU pair a fresh tx.state with a stale tx_gen/tx_result slot.
- isotp_sendmsg(): wait_tx_done: drain sk_err via sock_error() once we have read the result from so->tx_result[], so an already-reported error doesn't stay latched for a later poll()/SO_ERROR.
Also align the remaining lock-free so->tx.state/rx.state/cfecho accesses and use skb->hash as unique loopback echo frame indicator.
net/can/isotp.c +230 -87
@@ -127,6 +127,15 @@ MODULE_PARM_DESC(max_pdu_size, "maximum isotp pdu size (default "#define ISOTP_FC_TIMEOUT 1/* 1 sec */ #define ISOTP_ECHO_TIMEOUT 2/* 2 secs */ +/* so->tx_result[so->tx_gen % ISOTP_TX_RESULT_SLOTS] holds the packed value +* (err << ISOTP_TX_RESULT_GEN_BITS | gen) for each tx generation slot, so it +* can be handled with a single READ_ONCE()/WRITE_ONCE() access. +*/ +#define ISOTP_TX_RESULT_SLOTS 4 +#define ISOTP_TX_RESULT_GEN_BITS 24 +#define ISOTP_TX_RESULT_GEN_MASK ((1U << ISOTP_TX_RESULT_GEN_BITS) - 1) +#define ISOTP_TX_RESULT_ERR_MASK 0xFF +enum {ISOTP_IDLE =0 ,ISOTP_WAIT_FIRST_FC ,
@@ -166,7 +175,8 @@ struct isotp_sock {u32 force_tx_stmin;u32 force_rx_stmin;u32 cfecho;/* consecutive frame echo tag */ -u32 tx_gen;/* generation, bumped per new tx transfer */ +u32 tx_gen;/* transfer generation, increased per new tx transfer */ +u32 tx_result[ISOTP_TX_RESULT_SLOTS ];/* per-generation result slots */ struct tpcon rx, tx;struct list_head notifier;wait_queue_head_t wait;
@@ -177,6 +187,65 @@ static LIST_HEAD(isotp_notifier_list);static DEFINE_SPINLOCK (isotp_notifier_lock);static struct isotp_sock *isotp_busy_notifier; +/* increase (24 bit) tx generation value */ +static u32 isotp_inc_tx_gen (u32 gen) +{ +return (gen +1 ) &ISOTP_TX_RESULT_GEN_MASK ; +} + +/* store 8 bit error and 24 bit tx generation values in packed u32 element */ +static u32 isotp_pack_tx_result (u32 gen,int err) +{ +return gen | ((u32 )err <<ISOTP_TX_RESULT_GEN_BITS ); +} + +/* get the 24 bit tx generation value from the tx result */ +static u32 isotp_get_tx_gen (u32 gen_err) +{ +return gen_err &ISOTP_TX_RESULT_GEN_MASK ; +} + +/* get the 8 bit error value from the tx result */ +static u32 isotp_get_tx_err (u32 gen_err) +{ +return (gen_err >>ISOTP_TX_RESULT_GEN_BITS ) &ISOTP_TX_RESULT_ERR_MASK ; +} + +/* store transfer result in per-generation%4 so->tx_result[] slot */ +static void isotp_set_tx_result (struct isotp_sock *so,u32 gen,int err) +{ +WRITE_ONCE (so->tx_result[gen %ISOTP_TX_RESULT_SLOTS ], +isotp_pack_tx_result (gen, err)); +} + +/* fetch the result recorded for 'gen', as a (negative) errno (0 for success) */ +static int isotp_get_tx_result (struct isotp_sock *so,u32 gen) +{ +u32 result =READ_ONCE (so->tx_result[gen %ISOTP_TX_RESULT_SLOTS ]); + +if (isotp_get_tx_gen (result) != gen) { +pr_notice_once ("can-isotp: tx_result[] slot reused before read\n" ); + +/* report failure rather than risk a false success */ +return -ECOMM ; + } + +return -(isotp_get_tx_err (result)); +} + +/* true if done, shut down or superseded ('gen' is no longer the active +* transfer). Reads tx.state first (acquire) so tx_gen/tx_result reads +* below see at least what that state write published (common sequence). +*/ +static bool isotp_tx_gen_done (struct isotp_sock *so,u32 gen) +{ +/* read tx.state first for the common sequence */ +u32 state =smp_load_acquire (&so->tx.state); + +return state ==ISOTP_IDLE || state ==ISOTP_SHUTDOWN || +READ_ONCE (so->tx_gen) != gen; +} +static inline struct isotp_sock *isotp_sk (const struct sock *sk) {return (struct isotp_sock *)sk;
@@ -199,7 +268,7 @@ static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) rxtimer);struct sock *sk = &so->sk; -if (so->rx.state ==ISOTP_WAIT_DATA ) { +if (READ_ONCE (so->rx.state) ==ISOTP_WAIT_DATA ) {/* we did not get new data frames in time */ /* report 'connection timed out' */
@@ -208,7 +277,7 @@ static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer)sk_error_report (sk);/* reset rx state */ - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE ); }return HRTIMER_NORESTART ;
@@ -372,20 +441,19 @@ static void isotp_send_cframe(struct isotp_sock *so);static int isotp_rcv_fc (struct isotp_sock *so,struct canfd_frame *cf,int ae) {struct sock *sk = &so->sk; +int tx_err =EBADMSG ;/* default for unknown FC status */ -if (so->tx.state !=ISOTP_WAIT_FC && - so->tx.state !=ISOTP_WAIT_FIRST_FC ) +if (READ_ONCE (so->tx.state) !=ISOTP_WAIT_FC && +READ_ONCE (so->tx.state) !=ISOTP_WAIT_FIRST_FC )return 0 ;hrtimer_cancel (&so->txtimer);/* isotp_tx_timeout() may have given up on this job while -* hrtimer_cancel() above waited for it to finish; so->rx_lock -* (held by our caller isotp_rcv()) rules out a concurrent claim, -* so a plain recheck is enough here. +* hrtimer_cancel() above waited for it to finish => recheck */ -if (so->tx.state !=ISOTP_WAIT_FC && - so->tx.state !=ISOTP_WAIT_FIRST_FC ) +if (READ_ONCE (so->tx.state) !=ISOTP_WAIT_FC && +READ_ONCE (so->tx.state) !=ISOTP_WAIT_FIRST_FC )return 1 ; if ((cf->len < ae + FC_CONTENT_SZ) ||
@@ -396,13 +464,15 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae)if (!sock_flag (sk,SOCK_DEAD ))sk_error_report (sk); - so->tx.state =ISOTP_IDLE ; +isotp_set_tx_result (so, so->tx_gen,EBADMSG ); +/* set to IDLE after publishing tx_result */ +smp_store_release (&so->tx.state,ISOTP_IDLE );wake_up_interruptible (&so->wait);return 1 ; }/* get static/dynamic communication params from first/every FC frame */ -if (so->tx.state ==ISOTP_WAIT_FIRST_FC || +if (READ_ONCE (so->tx.state) ==ISOTP_WAIT_FIRST_FC || so->opt.flags &CAN_ISOTP_DYN_FC_PARMS ) { so->txfc.bs = cf->data[ae +1 ]; so->txfc.stmin = cf->data[ae +2 ];
@@ -426,13 +496,13 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) so->tx_gap =ktime_add_ns (so->tx_gap, (so->txfc.stmin -0xF0 ) *100000 ); - so->tx.state =ISOTP_WAIT_FC ; +WRITE_ONCE (so->tx.state,ISOTP_WAIT_FC ); }switch (cf->data[ae] &0x0F ) {case ISOTP_FC_CTS : so->tx.bs =0 ; - so->tx.state =ISOTP_SENDING ; +WRITE_ONCE (so->tx.state,ISOTP_SENDING );/* send CF frame and enable echo timeout handling */ hrtimer_start (&so->echotimer,ktime_set (ISOTP_ECHO_TIMEOUT ,0 ),HRTIMER_MODE_REL_SOFT );
@@ -447,14 +517,19 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae)case ISOTP_FC_OVFLW :/* overflow on receiver side - report 'message too long' */ - sk->sk_err =EMSGSIZE ; -if (!sock_flag (sk,SOCK_DEAD )) -sk_error_report (sk); + tx_err =EMSGSIZE ; fallthrough;default : -/* stop this tx job */ - so->tx.state =ISOTP_IDLE ; +/* reserved/unknown flow status (tx_err defaults to EBADMSG) */ + + sk->sk_err = tx_err; +if (!sock_flag (sk,SOCK_DEAD )) +sk_error_report (sk); + +isotp_set_tx_result (so, so->tx_gen, tx_err); +/* set to IDLE after publishing tx_result */ +smp_store_release (&so->tx.state,ISOTP_IDLE );wake_up_interruptible (&so->wait); }return 0 ;
@@ -467,7 +542,7 @@ static int isotp_rcv_sf(struct sock *sk, struct canfd_frame *cf, int pcilen,struct sk_buff *nskb;hrtimer_cancel (&so->rxtimer); - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE );if (!len || len > cf->len - pcilen)return 1 ;
@@ -501,7 +576,7 @@ static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae)int ff_pci_sz;hrtimer_cancel (&so->rxtimer); - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE );/* get the used sender LL_DL from the (first) CAN frame data length */ so->rx.ll_dl =padlen (cf->len);
@@ -555,7 +630,7 @@ static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae)/* initial setup for this pdu reception */ so->rx.sn =1 ; - so->rx.state =ISOTP_WAIT_DATA ; +WRITE_ONCE (so->rx.state,ISOTP_WAIT_DATA );/* no creation of flow control frames */ if (so->opt.flags &CAN_ISOTP_LISTEN_MODE )
@@ -573,7 +648,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae,struct sk_buff *nskb;int i; -if (so->rx.state !=ISOTP_WAIT_DATA ) +if (READ_ONCE (so->rx.state) !=ISOTP_WAIT_DATA )return 0 ;/* drop if timestamp gap is less than force_rx_stmin nano secs */
@@ -588,11 +663,9 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae,hrtimer_cancel (&so->rxtimer);/* isotp_rx_timer_handler() may have raced us for so->rx.state -* while hrtimer_cancel() above waited for it to finish, already -* reporting ETIMEDOUT and resetting the reception; don't process -* this CF into a reassembly that has already been given up on. +* while hrtimer_cancel() above waited for it to finish => recheck */ -if (so->rx.state !=ISOTP_WAIT_DATA ) +if (READ_ONCE (so->rx.state) !=ISOTP_WAIT_DATA )return 1 ;/* CFs are never longer than the FF */
@@ -613,7 +686,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae,sk_error_report (sk);/* reset rx state */ - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE );return 1 ; } so->rx.sn++;
@@ -627,7 +700,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae,if (so->rx.idx >= so->rx.len) {/* we are done */ - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE );if ((so->opt.flags &ISOTP_CHECK_PADDING ) &&check_pad (so, cf, i +1 , so->opt.rxpad_content)) {
@@ -698,8 +771,10 @@ static void isotp_rcv(struct sk_buff *skb, void *data)if (so->opt.flags &CAN_ISOTP_HALF_DUPLEX ) {/* check rx/tx path half duplex expectations */ -if ((so->tx.state !=ISOTP_IDLE && n_pci_type !=N_PCI_FC ) || - (so->rx.state !=ISOTP_IDLE && n_pci_type ==N_PCI_FC )) +if ((READ_ONCE (so->tx.state) !=ISOTP_IDLE && + n_pci_type !=N_PCI_FC ) || + (READ_ONCE (so->rx.state) !=ISOTP_IDLE && + n_pci_type ==N_PCI_FC )) goto out_unlock; }
@@ -794,6 +869,7 @@ static void isotp_send_cframe(struct isotp_sock *so)struct canfd_frame *cf;int can_send_ret;int ae = (so->opt.flags &CAN_ISOTP_EXTEND_ADDR ) ?1 :0 ; +u32 old_cfecho; dev =dev_get_by_index (sock_net (sk), so->ifindex);if (!dev)
@@ -814,6 +890,9 @@ static void isotp_send_cframe(struct isotp_sock *so) csx->can_iif = dev->ifindex; +/* set uid in tx skb to identify CF echo frames */ +can_set_skb_uid (skb); + cf = (struct canfd_frame *)skb->data;skb_put_zero (skb, so->ll.mtu);
@@ -830,12 +909,15 @@ static void isotp_send_cframe(struct isotp_sock *so) skb->dev = dev;can_skb_set_owner (skb, sk); -/* cfecho should have been zero'ed by init/isotp_rcv_echo() */ -if (so->cfecho) -pr_notice_once ("can-isotp: cfecho is %08X != 0\n" , so->cfecho); +/* zero'ed by init/isotp_rcv_echo(); reached lock-free via +* isotp_txfr_timer_handler() too, so use READ_ONCE()/WRITE_ONCE() +*/ + old_cfecho =READ_ONCE (so->cfecho); +if (old_cfecho) +pr_notice_once ("can-isotp: cfecho is %08X != 0\n" , old_cfecho);/* set consecutive frame echo tag */ - so->cfecho = *(u32 *)cf->data; +WRITE_ONCE (so->cfecho, skb->hash);/* send frame with local echo enabled */ can_send_ret =can_send (skb,1 );
@@ -887,7 +969,6 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) {struct sock *sk = (struct sock *)data;struct isotp_sock *so =isotp_sk (sk); -struct canfd_frame *cf = (struct canfd_frame *)skb->data;/* only handle my own local echo CF/SF skb's (no FF!) */ if (skb->sk != sk)
@@ -899,32 +980,35 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data)spin_lock (&so->rx_lock);/* so->cfecho may since belong to a new transfer; recheck under lock */ -if (so->cfecho != *(u32 *)cf->data) +if (READ_ONCE (so->cfecho) != skb->hash) goto out_unlock;/* cancel local echo timeout */ hrtimer_cancel (&so->echotimer);/* local echo skb with consecutive frame has been consumed */ - so->cfecho =0 ; +WRITE_ONCE (so->cfecho,0 );/* claiming a transfer also takes so->rx_lock, so a plain recheck * is enough: so->tx.state can't have flipped to ISOTP_SENDING for * a new claim while we're still in here */ -if (so->tx.state !=ISOTP_SENDING ) +if (READ_ONCE (so->tx.state) !=ISOTP_SENDING ) goto out_unlock;if (so->tx.idx >= so->tx.len) {/* we are done */ - so->tx.state =ISOTP_IDLE ; + +isotp_set_tx_result (so, so->tx_gen,0 ); +/* set to IDLE after publishing tx_result */ +smp_store_release (&so->tx.state,ISOTP_IDLE );wake_up_interruptible (&so->wait); goto out_unlock; }if (so->txfc.bs && so->tx.bs >= so->txfc.bs) {/* stop and wait for FC with timeout */ - so->tx.state =ISOTP_WAIT_FC ; +WRITE_ONCE (so->tx.state,ISOTP_WAIT_FC );hrtimer_start (&so->txtimer,ktime_set (ISOTP_FC_TIMEOUT ,0 ),HRTIMER_MODE_REL_SOFT ); goto out_unlock;
@@ -946,16 +1030,20 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data)spin_unlock (&so->rx_lock); } -/* shared by so->txtimer's and so->echotimer's callbacks. Both timers get -* cancelled under so->rx_lock elsewhere, so this must stay lock-free to -* avoid deadlocking with that; uses so->tx_gen instead to avoid tainting -* a new transfer with an error from the one that just timed out. +/* isotp_tx_timeout: we did not get any flow control or echo frame in time +* +* Shared by so->txtimer's and so->echotimer's callbacks. Both timers get +* cancelled under so->rx_lock elsewhere, so this must stay lock-free. +* +* tx.state is acquired before tx_gen. Common sequence in isotp_tx_gen_done(). +* cmpxchg() only orders itself, not the two preceding loads. */ static enum hrtimer_restart isotp_tx_timeout (struct isotp_sock *so) {struct sock *sk = &so->sk; +/* read tx.state first for the common sequence */ +u32 old_state =smp_load_acquire (&so->tx.state);u32 gen =READ_ONCE (so->tx_gen); -u32 old_state =READ_ONCE (so->tx.state);/* don't handle timeouts in IDLE or SHUTDOWN state */ if (old_state ==ISOTP_IDLE || old_state ==ISOTP_SHUTDOWN )
@@ -965,14 +1053,14 @@ static enum hrtimer_restart isotp_tx_timeout(struct isotp_sock *so)if (cmpxchg (&so->tx.state, old_state,ISOTP_IDLE ) != old_state)return HRTIMER_NORESTART ; -/* we did not get any flow control or echo frame in time */ +/* detected timeout: report 'communication error on send' */ -if (READ_ONCE (so->tx_gen) == gen) { -/* report 'communication error on send' */ - sk->sk_err =ECOMM ; -if (!sock_flag (sk,SOCK_DEAD )) -sk_error_report (sk); - } +/* a stale read of this slot by a waiter still falls back to ECOMM */ +isotp_set_tx_result (so, gen,ECOMM ); + + sk->sk_err =ECOMM ; +if (!sock_flag (sk,SOCK_DEAD )) +sk_error_report (sk);wake_up_interruptible (&so->wait);
@@ -1007,7 +1095,7 @@ static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer) HRTIMER_MODE_REL_SOFT);/* cfecho should be consumed by isotp_rcv_echo() here */ -if (so->tx.state ==ISOTP_SENDING && !so->cfecho) +if (READ_ONCE (so->tx.state) ==ISOTP_SENDING && !READ_ONCE (so->cfecho))isotp_send_cframe (so);return HRTIMER_NORESTART ;
@@ -1026,10 +1114,12 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)s64 hrtimer_sec =ISOTP_ECHO_TIMEOUT ;struct hrtimer *tx_hrt = &so->echotimer;u32 new_state =ISOTP_SENDING ; +u32 my_gen; +u32 old_cfecho;int off;int err; -if (!so->bound || so->tx.state ==ISOTP_SHUTDOWN ) +if (!so->bound ||READ_ONCE (so->tx.state) ==ISOTP_SHUTDOWN )return -EADDRNOTAVAIL ;/* claim the socket under so->rx_lock: this serializes the claim
@@ -1046,29 +1136,33 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)if (msg->msg_flags &MSG_DONTWAIT )return -EAGAIN ; -if (so->tx.state ==ISOTP_SHUTDOWN ) +if (READ_ONCE (so->tx.state) ==ISOTP_SHUTDOWN )return -EADDRNOTAVAIL ;/* wait for complete transmission of current pdu */ err =wait_event_interruptible (so->wait, - so->tx.state ==ISOTP_IDLE ); +READ_ONCE (so->tx.state) ==ISOTP_IDLE || +READ_ONCE (so->tx.state) ==ISOTP_SHUTDOWN );if (err)return err; } -/* new transfer: bump so->tx_gen and drain the old one's timers, -* still under the so->rx_lock we just claimed the socket with -*/ -WRITE_ONCE (so->tx.state,ISOTP_SENDING ); -WRITE_ONCE (so->tx_gen,READ_ONCE (so->tx_gen) +1 ); +/* txfrtimer's callback re-arms echotimer lock-free: drain it first */ +hrtimer_cancel (&so->txfrtimer);hrtimer_cancel (&so->txtimer);hrtimer_cancel (&so->echotimer); -hrtimer_cancel (&so->txfrtimer); - so->cfecho =0 ; + +/* new transfer: increment so->tx_gen and set tx.state after barrier */ + my_gen =isotp_inc_tx_gen (READ_ONCE (so->tx_gen)); +isotp_set_tx_result (so, my_gen,ECOMM );/* prevent stale slot matching */ +WRITE_ONCE (so->tx_gen, my_gen); +smp_wmb ();/* see smp_load_acquire() in isotp_tx_[timeout|gen_done] */ +WRITE_ONCE (so->tx.state,ISOTP_SENDING ); +WRITE_ONCE (so->cfecho,0 );spin_unlock_bh (&so->rx_lock);/* so->bound is only checked once above - a wakeup may have -* unbound/rebound the socket meanwhile, so re-validate it +* unbound/rebound the socket meanwhile => recheck */ if (!so->bound) { err = -EADDRNOTAVAIL ;
@@ -1127,6 +1221,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) csx->can_iif = dev->ifindex; +/* set uid in tx skb to identify CF echo frames */ +can_set_skb_uid (skb); + so->tx.len = size; so->tx.idx =0 ;
@@ -1134,8 +1231,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)skb_put_zero (skb, so->ll.mtu);/* cfecho should have been zero'ed by init / former isotp_rcv_echo() */ -if (so->cfecho) -pr_notice_once ("can-isotp: uninit cfecho %08X\n" , so->cfecho); + old_cfecho =READ_ONCE (so->cfecho); +if (old_cfecho) +pr_notice_once ("can-isotp: uninit cfecho %08X\n" , old_cfecho);/* check for single frame transmission depending on TX_DL */ if (size <= so->tx.ll_dl -SF_PCI_SZ4 - ae - off) {
@@ -1163,7 +1261,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) cf->data[ae] |= size;/* set CF echo tag for isotp_rcv_echo() (SF-mode) */ - so->cfecho = *(u32 *)cf->data; +WRITE_ONCE (so->cfecho, skb->hash); }else {/* send first frame */
@@ -1180,7 +1278,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) so->txfc.bs =0 ;/* set CF echo tag for isotp_rcv_echo() (CF-mode) */ - so->cfecho = *(u32 *)cf->data; +WRITE_ONCE (so->cfecho, skb->hash); }else {/* standard flow control check */ new_state =ISOTP_WAIT_FIRST_FC ;
@@ -1190,12 +1288,12 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) tx_hrt = &so->txtimer;/* no CF echo tag for isotp_rcv_echo() (FF-mode) */ - so->cfecho =0 ; +WRITE_ONCE (so->cfecho,0 ); } }spin_lock_bh (&so->rx_lock); -if (so->tx.state ==ISOTP_SHUTDOWN ) { +if (READ_ONCE (so->tx.state) ==ISOTP_SHUTDOWN ) {/* isotp_release() has since taken over and already drained * our timers - don't send into a socket that's going away */
@@ -1206,7 +1304,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)return -EADDRNOTAVAIL ; }/* WAIT_FIRST_FC for standard FF, else stays ISOTP_SENDING */ - so->tx.state = new_state; +WRITE_ONCE (so->tx.state, new_state);hrtimer_start (tx_hrt,ktime_set (hrtimer_sec,0 ),HRTIMER_MODE_REL_SOFT );spin_unlock_bh (&so->rx_lock);
@@ -1223,20 +1321,49 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) __func__, ERR_PTR(err));spin_lock_bh (&so->rx_lock); + +/* new transfer already claimed by a concurrent completion, +* timeout or sendmsg() while we were stuck in can_send()? +*/ +if (READ_ONCE (so->tx_gen) != my_gen) { +/* don't touch timers and state of the new transfer */ +spin_unlock_bh (&so->rx_lock); +return err; + } +/* no transmission -> no timeout monitoring */ hrtimer_cancel (tx_hrt); goto err_out_drop_locked; }if (wait_tx_done) { -/* wait for complete transmission of current pdu */ - err =wait_event_interruptible (so->wait, so->tx.state ==ISOTP_IDLE ); +/* wake up for: +* - concurrent sendmsg() claiming a new transfer +* - complete transmission of current PDU +* - shutdown state change in isotp_release() +* isotp_tx_gen_done() uses common tx.state/tx_gen read sequence +*/ + err =wait_event_interruptible (so->wait, +isotp_tx_gen_done (so, my_gen));if (err) goto err_event_drop; - err =sock_error (sk); -if (err) -return err; +/* still our claim, but isotp_release() force-shut it down */ +if (smp_load_acquire (&so->tx.state) ==ISOTP_SHUTDOWN && +READ_ONCE (so->tx_gen) == my_gen) { + err = -EADDRNOTAVAIL ; + goto err_event_drop; + } + +/* own completion, or tx_gen moved on - either way this is +* what isotp_get_tx_result() recorded for my_gen +*/ + err =isotp_get_tx_result (so, my_gen); + +/* drain to avoid stale error for a later poll()/SO_ERROR */ +sock_error (sk); + +return err ? err : size; }return size;
@@ -1246,15 +1373,26 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)spin_lock_bh (&so->rx_lock); goto err_out_drop_locked; err_event_drop: -/* interrupted waiting on our own transfer - drain its timers */ +/* interrupted or shut down while waiting on our own transfer */ spin_lock_bh (&so->rx_lock); + +/* new transfer already started by concurrent sendmsg()? */ +if (READ_ONCE (so->tx_gen) != my_gen) { +/* don't touch timers and states of the new transfer */ +spin_unlock_bh (&so->rx_lock); +return err; + } +hrtimer_cancel (&so->txfrtimer);hrtimer_cancel (&so->txtimer);hrtimer_cancel (&so->echotimer); err_out_drop_locked:/* release the claim; so->rx_lock still held from above */ - so->cfecho =0 ; - so->tx.state =ISOTP_IDLE ; +WRITE_ONCE (so->cfecho,0 ); + +/* only claim to IDLE if isotp_release() has not taken over */ +if (READ_ONCE (so->tx.state) !=ISOTP_SHUTDOWN ) +WRITE_ONCE (so->tx.state,ISOTP_IDLE );spin_unlock_bh (&so->rx_lock);wake_up_interruptible (&so->wait);
@@ -1320,8 +1458,9 @@ static int isotp_release(struct socket *sock)/* best-effort: wait for a running pdu to finish, but don't block on * it forever - give up after the first signal */ -while (so->tx.state !=ISOTP_IDLE && -wait_event_interruptible (so->wait, so->tx.state ==ISOTP_IDLE ) ==0 ) +while (READ_ONCE (so->tx.state) !=ISOTP_IDLE && +wait_event_interruptible (so->wait, +READ_ONCE (so->tx.state) ==ISOTP_IDLE ) ==0 ) ;/* claim the socket under so->rx_lock like sendmsg() does, so its
@@ -1329,9 +1468,12 @@ static int isotp_release(struct socket *sock)* unconditionally, even when a signal cut the wait above short */ spin_lock_bh (&so->rx_lock); - so->tx.state =ISOTP_SHUTDOWN ; +WRITE_ONCE (so->tx.state,ISOTP_SHUTDOWN );spin_unlock_bh (&so->rx_lock); - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE ); + +/* forced SHUTDOWN may have skipped IDLE (gave up on a signal) */ +wake_up_interruptible (&so->wait);spin_lock (&isotp_notifier_lock);while (isotp_busy_notifier == so) {
@@ -1447,7 +1589,8 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l* with so->bound in the same lock_sock() section above, so there is * no window in which a concurrent isotp_notify() could be missed. */ -if (so->tx.state !=ISOTP_IDLE || so->rx.state !=ISOTP_IDLE ) { +if (READ_ONCE (so->tx.state) !=ISOTP_IDLE || +READ_ONCE (so->rx.state) !=ISOTP_IDLE ) { err = -EAGAIN ; goto out; }
@@ -1481,7 +1624,7 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l isotp_rcv, sk, "isotp", sk);/* no consecutive frame echo skb in flight */ - so->cfecho =0 ; +WRITE_ONCE (so->cfecho,0 );/* register for echo skb's */ can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id),
@@ -1847,7 +1990,7 @@ static __poll_t isotp_poll(struct file *file, struct socket *sock, poll_table *wpoll_wait (file, &so->wait, wait);/* Check for false positives due to TX state */ -if ((mask &EPOLLWRNORM ) && (so->tx.state !=ISOTP_IDLE )) +if ((mask &EPOLLWRNORM ) && (READ_ONCE (so->tx.state) !=ISOTP_IDLE )) mask &= ~(EPOLLOUT |EPOLLWRNORM );return mask;
Oliver Hartkopp
maintainerPATCH 1/1 can: isotp: fix timer drain order, wakeup handling and tx_gen ordering
commit 050f010f920da17c1044a4f174766ad553e770b6 upstream.
This patch is a follow-up to commit cf070fe33bfb ("can: isotp: serialize TX state transitions under so->rx_lock") which addresses following sashiko-bot findings:
- isotp_sendmsg(): drain so->txfrtimer first so a stale callback can't re-arm echotimer after the claim
- isotp_release(): wake so->wait after forcing ISOTP_SHUTDOWN so a sleeping sendmsg() claim isn't stranded
- isotp_sendmsg(): have both wait_event_interruptible() calls in isotp_sendmsg() also wake on ISOTP_SHUTDOWN and do not return claim to IDLE to avoid corrupting a concurrent isotp_release() process.
- isotp_sendmsg(): handle potential claim of a new transfer when the wait_event_interruptible() call returns in CAN_ISOTP_WAIT_TX_DONE mode. Don't touch timers and states of the new transfer if a new thread incremented so->tx_gen before getting the lock at err_event_drop.
- isotp_sendmsg(): handle a stuck can_send() and omit timer and state changes if a new transfer was claimed. wait_tx_done() returns the error recorded in so->tx_result[], tagged with the caller's own generation.
- isotp_tx_timeout(): on a claimed timeout, record the ECOMM error for the timed-out transfer's own generation in so->tx_result[]; sk->sk_err is raised unconditionally, same as every other error path here.
- isotp_tx_gen_done()/isotp_tx_timeout(): always read tx.state (acquire) before tx_gen - the reverse order let a weakly ordered CPU pair a fresh tx.state with a stale tx_gen/tx_result slot.
- isotp_sendmsg(): wait_tx_done: drain sk_err via sock_error() once we have read the result from so->tx_result[], so an already-reported error doesn't stay latched for a later poll()/SO_ERROR.
Also align the remaining lock-free so->tx.state/rx.state/cfecho accesses and use skb->hash as unique loopback echo frame indicator.
--- net/can/isotp.c | 333 +++++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 246 insertions(+), 87 deletions(-)
net/can/isotp.c +246 -87
@@ -126,6 +126,15 @@ MODULE_PARM_DESC(max_pdu_size, "maximum isotp pdu size (default "#define ISOTP_FC_TIMEOUT 1/* 1 sec */ #define ISOTP_ECHO_TIMEOUT 2/* 2 secs */ +/* so->tx_result[so->tx_gen % ISOTP_TX_RESULT_SLOTS] holds the packed value +* (err << ISOTP_TX_RESULT_GEN_BITS | gen) for each tx generation slot, so it +* can be handled with a single READ_ONCE()/WRITE_ONCE() access. +*/ +#define ISOTP_TX_RESULT_SLOTS 4 +#define ISOTP_TX_RESULT_GEN_BITS 24 +#define ISOTP_TX_RESULT_GEN_MASK ((1U << ISOTP_TX_RESULT_GEN_BITS) - 1) +#define ISOTP_TX_RESULT_ERR_MASK 0xFF +enum {ISOTP_IDLE =0 ,ISOTP_WAIT_FIRST_FC ,
@@ -164,7 +173,8 @@ struct isotp_sock {u32 force_tx_stmin;u32 force_rx_stmin;u32 cfecho;/* consecutive frame echo tag */ -u32 tx_gen;/* generation, bumped per new tx transfer */ +u32 tx_gen;/* transfer generation, increased per new tx transfer */ +u32 tx_result[ISOTP_TX_RESULT_SLOTS ];/* per-generation result slots */ struct tpcon rx, tx;struct list_head notifier;wait_queue_head_t wait;
@@ -175,6 +185,81 @@ static LIST_HEAD(isotp_notifier_list);static DEFINE_SPINLOCK (isotp_notifier_lock);static struct isotp_sock *isotp_busy_notifier; +/* increase (24 bit) tx generation value */ +static u32 isotp_inc_tx_gen (u32 gen) +{ +return (gen +1 ) &ISOTP_TX_RESULT_GEN_MASK ; +} + +/* store 8 bit error and 24 bit tx generation values in packed u32 element */ +static u32 isotp_pack_tx_result (u32 gen,int err) +{ +return gen | ((u32 )err <<ISOTP_TX_RESULT_GEN_BITS ); +} + +/* get the 24 bit tx generation value from the tx result */ +static u32 isotp_get_tx_gen (u32 gen_err) +{ +return gen_err &ISOTP_TX_RESULT_GEN_MASK ; +} + +/* get the 8 bit error value from the tx result */ +static u32 isotp_get_tx_err (u32 gen_err) +{ +return (gen_err >>ISOTP_TX_RESULT_GEN_BITS ) &ISOTP_TX_RESULT_ERR_MASK ; +} + +/* store transfer result in per-generation%4 so->tx_result[] slot */ +static void isotp_set_tx_result (struct isotp_sock *so,u32 gen,int err) +{ +WRITE_ONCE (so->tx_result[gen %ISOTP_TX_RESULT_SLOTS ], +isotp_pack_tx_result (gen, err)); +} + +/* fetch the result recorded for 'gen', as a (negative) errno (0 for success) */ +static int isotp_get_tx_result (struct isotp_sock *so,u32 gen) +{ +u32 result =READ_ONCE (so->tx_result[gen %ISOTP_TX_RESULT_SLOTS ]); + +if (isotp_get_tx_gen (result) != gen) { +pr_notice_once ("can-isotp: tx_result[] slot reused before read\n" ); + +/* report failure rather than risk a false success */ +return -ECOMM ; + } + +return -(isotp_get_tx_err (result)); +} + +/* true if done, shut down or superseded ('gen' is no longer the active +* transfer). Reads tx.state first (acquire) so tx_gen/tx_result reads +* below see at least what that state write published (common sequence). +*/ +static bool isotp_tx_gen_done (struct isotp_sock *so,u32 gen) +{ +/* read tx.state first for the common sequence */ +u32 state =smp_load_acquire (&so->tx.state); + +return state ==ISOTP_IDLE || state ==ISOTP_SHUTDOWN || +READ_ONCE (so->tx_gen) != gen; +} + +/* can_set_skb_uid() (from commit d4fb6514ff8ed6912a71294e6b66a5d59ee88007, +* "can: use skb hash instead of private variable in headroom") is not +* available before mainline v7.0 - provide the same non-zero unique +* loopback echo identifier locally instead. +*/ +static atomic_t isotp_skb_uid_seq =ATOMIC_INIT (0 ); + +static void isotp_set_skb_uid (struct sk_buff *skb) +{ +/* create non-zero unique skb identifier together with *skb */ +while (!(skb->hash)) + skb->hash =atomic_inc_return (&isotp_skb_uid_seq); + + skb->sw_hash =1 ; +} +static inline struct isotp_sock *isotp_sk (const struct sock *sk) {return (struct isotp_sock *)sk;
@@ -197,7 +282,7 @@ static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) rxtimer);struct sock *sk = &so->sk; -if (so->rx.state ==ISOTP_WAIT_DATA ) { +if (READ_ONCE (so->rx.state) ==ISOTP_WAIT_DATA ) {/* we did not get new data frames in time */ /* report 'connection timed out' */
@@ -206,7 +291,7 @@ static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer)sk_error_report (sk);/* reset rx state */ - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE ); }return HRTIMER_NORESTART ;
@@ -364,20 +449,19 @@ static void isotp_send_cframe(struct isotp_sock *so);static int isotp_rcv_fc (struct isotp_sock *so,struct canfd_frame *cf,int ae) {struct sock *sk = &so->sk; +int tx_err =EBADMSG ;/* default for unknown FC status */ -if (so->tx.state !=ISOTP_WAIT_FC && - so->tx.state !=ISOTP_WAIT_FIRST_FC ) +if (READ_ONCE (so->tx.state) !=ISOTP_WAIT_FC && +READ_ONCE (so->tx.state) !=ISOTP_WAIT_FIRST_FC )return 0 ;hrtimer_cancel (&so->txtimer);/* isotp_tx_timeout() may have given up on this job while -* hrtimer_cancel() above waited for it to finish; so->rx_lock -* (held by our caller isotp_rcv()) rules out a concurrent claim, -* so a plain recheck is enough here. +* hrtimer_cancel() above waited for it to finish => recheck */ -if (so->tx.state !=ISOTP_WAIT_FC && - so->tx.state !=ISOTP_WAIT_FIRST_FC ) +if (READ_ONCE (so->tx.state) !=ISOTP_WAIT_FC && +READ_ONCE (so->tx.state) !=ISOTP_WAIT_FIRST_FC )return 1 ; if ((cf->len < ae + FC_CONTENT_SZ) ||
@@ -388,13 +472,15 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae)if (!sock_flag (sk,SOCK_DEAD ))sk_error_report (sk); - so->tx.state =ISOTP_IDLE ; +isotp_set_tx_result (so, so->tx_gen,EBADMSG ); +/* set to IDLE after publishing tx_result */ +smp_store_release (&so->tx.state,ISOTP_IDLE );wake_up_interruptible (&so->wait);return 1 ; }/* get static/dynamic communication params from first/every FC frame */ -if (so->tx.state ==ISOTP_WAIT_FIRST_FC || +if (READ_ONCE (so->tx.state) ==ISOTP_WAIT_FIRST_FC || so->opt.flags &CAN_ISOTP_DYN_FC_PARMS ) { so->txfc.bs = cf->data[ae +1 ]; so->txfc.stmin = cf->data[ae +2 ];
@@ -418,13 +504,13 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) so->tx_gap =ktime_add_ns (so->tx_gap, (so->txfc.stmin -0xF0 ) *100000 ); - so->tx.state =ISOTP_WAIT_FC ; +WRITE_ONCE (so->tx.state,ISOTP_WAIT_FC ); }switch (cf->data[ae] &0x0F ) {case ISOTP_FC_CTS : so->tx.bs =0 ; - so->tx.state =ISOTP_SENDING ; +WRITE_ONCE (so->tx.state,ISOTP_SENDING );/* send CF frame and enable echo timeout handling */ hrtimer_start (&so->echotimer,ktime_set (ISOTP_ECHO_TIMEOUT ,0 ),HRTIMER_MODE_REL_SOFT );
@@ -439,14 +525,19 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae)case ISOTP_FC_OVFLW :/* overflow on receiver side - report 'message too long' */ - sk->sk_err =EMSGSIZE ; -if (!sock_flag (sk,SOCK_DEAD )) -sk_error_report (sk); + tx_err =EMSGSIZE ; fallthrough;default : -/* stop this tx job */ - so->tx.state =ISOTP_IDLE ; +/* reserved/unknown flow status (tx_err defaults to EBADMSG) */ + + sk->sk_err = tx_err; +if (!sock_flag (sk,SOCK_DEAD )) +sk_error_report (sk); + +isotp_set_tx_result (so, so->tx_gen, tx_err); +/* set to IDLE after publishing tx_result */ +smp_store_release (&so->tx.state,ISOTP_IDLE );wake_up_interruptible (&so->wait); }return 0 ;
@@ -459,7 +550,7 @@ static int isotp_rcv_sf(struct sock *sk, struct canfd_frame *cf, int pcilen,struct sk_buff *nskb;hrtimer_cancel (&so->rxtimer); - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE );if (!len || len > cf->len - pcilen)return 1 ;
@@ -493,7 +584,7 @@ static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae)int ff_pci_sz;hrtimer_cancel (&so->rxtimer); - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE );/* get the used sender LL_DL from the (first) CAN frame data length */ so->rx.ll_dl =padlen (cf->len);
@@ -547,7 +638,7 @@ static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae)/* initial setup for this pdu reception */ so->rx.sn =1 ; - so->rx.state =ISOTP_WAIT_DATA ; +WRITE_ONCE (so->rx.state,ISOTP_WAIT_DATA );/* no creation of flow control frames */ if (so->opt.flags &CAN_ISOTP_LISTEN_MODE )
@@ -565,7 +656,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae,struct sk_buff *nskb;int i; -if (so->rx.state !=ISOTP_WAIT_DATA ) +if (READ_ONCE (so->rx.state) !=ISOTP_WAIT_DATA )return 0 ;/* drop if timestamp gap is less than force_rx_stmin nano secs */
@@ -580,11 +671,9 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae,hrtimer_cancel (&so->rxtimer);/* isotp_rx_timer_handler() may have raced us for so->rx.state -* while hrtimer_cancel() above waited for it to finish, already -* reporting ETIMEDOUT and resetting the reception; don't process -* this CF into a reassembly that has already been given up on. +* while hrtimer_cancel() above waited for it to finish => recheck */ -if (so->rx.state !=ISOTP_WAIT_DATA ) +if (READ_ONCE (so->rx.state) !=ISOTP_WAIT_DATA )return 1 ;/* CFs are never longer than the FF */
@@ -605,7 +694,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae,sk_error_report (sk);/* reset rx state */ - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE );return 1 ; } so->rx.sn++;
@@ -619,7 +708,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae,if (so->rx.idx >= so->rx.len) {/* we are done */ - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE );if ((so->opt.flags &ISOTP_CHECK_PADDING ) &&check_pad (so, cf, i +1 , so->opt.rxpad_content)) {
@@ -690,8 +779,10 @@ static void isotp_rcv(struct sk_buff *skb, void *data)if (so->opt.flags &CAN_ISOTP_HALF_DUPLEX ) {/* check rx/tx path half duplex expectations */ -if ((so->tx.state !=ISOTP_IDLE && n_pci_type !=N_PCI_FC ) || - (so->rx.state !=ISOTP_IDLE && n_pci_type ==N_PCI_FC )) +if ((READ_ONCE (so->tx.state) !=ISOTP_IDLE && + n_pci_type !=N_PCI_FC ) || + (READ_ONCE (so->rx.state) !=ISOTP_IDLE && + n_pci_type ==N_PCI_FC )) goto out_unlock; }
@@ -785,6 +876,7 @@ static void isotp_send_cframe(struct isotp_sock *so)struct canfd_frame *cf;int can_send_ret;int ae = (so->opt.flags &CAN_ISOTP_EXTEND_ADDR ) ?1 :0 ; +u32 old_cfecho; dev =dev_get_by_index (sock_net (sk), so->ifindex);if (!dev)
@@ -800,6 +892,9 @@ static void isotp_send_cframe(struct isotp_sock *so)can_skb_prv (skb)->ifindex = dev->ifindex;can_skb_prv (skb)->skbcnt =0 ; +/* set uid in tx skb to identify CF echo frames */ +isotp_set_skb_uid (skb); + cf = (struct canfd_frame *)skb->data;skb_put_zero (skb, so->ll.mtu);
@@ -816,12 +911,15 @@ static void isotp_send_cframe(struct isotp_sock *so) skb->dev = dev;can_skb_set_owner (skb, sk); -/* cfecho should have been zero'ed by init/isotp_rcv_echo() */ -if (so->cfecho) -pr_notice_once ("can-isotp: cfecho is %08X != 0\n" , so->cfecho); +/* zero'ed by init/isotp_rcv_echo(); reached lock-free via +* isotp_txfr_timer_handler() too, so use READ_ONCE()/WRITE_ONCE() +*/ + old_cfecho =READ_ONCE (so->cfecho); +if (old_cfecho) +pr_notice_once ("can-isotp: cfecho is %08X != 0\n" , old_cfecho);/* set consecutive frame echo tag */ - so->cfecho = *(u32 *)cf->data; +WRITE_ONCE (so->cfecho, skb->hash);/* send frame with local echo enabled */ can_send_ret =can_send (skb,1 );
@@ -873,7 +971,6 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) {struct sock *sk = (struct sock *)data;struct isotp_sock *so =isotp_sk (sk); -struct canfd_frame *cf = (struct canfd_frame *)skb->data;/* only handle my own local echo CF/SF skb's (no FF!) */ if (skb->sk != sk)
@@ -885,32 +982,35 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data)spin_lock (&so->rx_lock);/* so->cfecho may since belong to a new transfer; recheck under lock */ -if (so->cfecho != *(u32 *)cf->data) +if (READ_ONCE (so->cfecho) != skb->hash) goto out_unlock;/* cancel local echo timeout */ hrtimer_cancel (&so->echotimer);/* local echo skb with consecutive frame has been consumed */ - so->cfecho =0 ; +WRITE_ONCE (so->cfecho,0 );/* claiming a transfer also takes so->rx_lock, so a plain recheck * is enough: so->tx.state can't have flipped to ISOTP_SENDING for * a new claim while we're still in here */ -if (so->tx.state !=ISOTP_SENDING ) +if (READ_ONCE (so->tx.state) !=ISOTP_SENDING ) goto out_unlock;if (so->tx.idx >= so->tx.len) {/* we are done */ - so->tx.state =ISOTP_IDLE ; + +isotp_set_tx_result (so, so->tx_gen,0 ); +/* set to IDLE after publishing tx_result */ +smp_store_release (&so->tx.state,ISOTP_IDLE );wake_up_interruptible (&so->wait); goto out_unlock; }if (so->txfc.bs && so->tx.bs >= so->txfc.bs) {/* stop and wait for FC with timeout */ - so->tx.state =ISOTP_WAIT_FC ; +WRITE_ONCE (so->tx.state,ISOTP_WAIT_FC );hrtimer_start (&so->txtimer,ktime_set (ISOTP_FC_TIMEOUT ,0 ),HRTIMER_MODE_REL_SOFT ); goto out_unlock;
@@ -932,16 +1032,20 @@ out_unlock:spin_unlock (&so->rx_lock); } -/* shared by so->txtimer's and so->echotimer's callbacks. Both timers get -* cancelled under so->rx_lock elsewhere, so this must stay lock-free to -* avoid deadlocking with that; uses so->tx_gen instead to avoid tainting -* a new transfer with an error from the one that just timed out. +/* isotp_tx_timeout: we did not get any flow control or echo frame in time +* +* Shared by so->txtimer's and so->echotimer's callbacks. Both timers get +* cancelled under so->rx_lock elsewhere, so this must stay lock-free. +* +* tx.state is acquired before tx_gen. Common sequence in isotp_tx_gen_done(). +* cmpxchg() only orders itself, not the two preceding loads. */ static enum hrtimer_restart isotp_tx_timeout (struct isotp_sock *so) {struct sock *sk = &so->sk; +/* read tx.state first for the common sequence */ +u32 old_state =smp_load_acquire (&so->tx.state);u32 gen =READ_ONCE (so->tx_gen); -u32 old_state =READ_ONCE (so->tx.state);/* don't handle timeouts in IDLE or SHUTDOWN state */ if (old_state ==ISOTP_IDLE || old_state ==ISOTP_SHUTDOWN )
@@ -951,14 +1055,14 @@ static enum hrtimer_restart isotp_tx_timeout(struct isotp_sock *so)if (cmpxchg (&so->tx.state, old_state,ISOTP_IDLE ) != old_state)return HRTIMER_NORESTART ; -/* we did not get any flow control or echo frame in time */ +/* detected timeout: report 'communication error on send' */ -if (READ_ONCE (so->tx_gen) == gen) { -/* report 'communication error on send' */ - sk->sk_err =ECOMM ; -if (!sock_flag (sk,SOCK_DEAD )) -sk_error_report (sk); - } +/* a stale read of this slot by a waiter still falls back to ECOMM */ +isotp_set_tx_result (so, gen,ECOMM ); + + sk->sk_err =ECOMM ; +if (!sock_flag (sk,SOCK_DEAD )) +sk_error_report (sk);wake_up_interruptible (&so->wait);
@@ -993,7 +1097,7 @@ static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer) HRTIMER_MODE_REL_SOFT);/* cfecho should be consumed by isotp_rcv_echo() here */ -if (so->tx.state ==ISOTP_SENDING && !so->cfecho) +if (READ_ONCE (so->tx.state) ==ISOTP_SENDING && !READ_ONCE (so->cfecho))isotp_send_cframe (so);return HRTIMER_NORESTART ;
@@ -1011,10 +1115,12 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)s64 hrtimer_sec =ISOTP_ECHO_TIMEOUT ;struct hrtimer *tx_hrt = &so->echotimer;u32 new_state =ISOTP_SENDING ; +u32 my_gen; +u32 old_cfecho;int off;int err; -if (!so->bound || so->tx.state ==ISOTP_SHUTDOWN ) +if (!so->bound ||READ_ONCE (so->tx.state) ==ISOTP_SHUTDOWN )return -EADDRNOTAVAIL ;/* claim the socket under so->rx_lock: this serializes the claim
@@ -1031,29 +1137,33 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)if (msg->msg_flags &MSG_DONTWAIT )return -EAGAIN ; -if (so->tx.state ==ISOTP_SHUTDOWN ) +if (READ_ONCE (so->tx.state) ==ISOTP_SHUTDOWN )return -EADDRNOTAVAIL ;/* wait for complete transmission of current pdu */ err =wait_event_interruptible (so->wait, - so->tx.state ==ISOTP_IDLE ); +READ_ONCE (so->tx.state) ==ISOTP_IDLE || +READ_ONCE (so->tx.state) ==ISOTP_SHUTDOWN );if (err)return err; } -/* new transfer: bump so->tx_gen and drain the old one's timers, -* still under the so->rx_lock we just claimed the socket with -*/ -WRITE_ONCE (so->tx.state,ISOTP_SENDING ); -WRITE_ONCE (so->tx_gen,READ_ONCE (so->tx_gen) +1 ); +/* txfrtimer's callback re-arms echotimer lock-free: drain it first */ +hrtimer_cancel (&so->txfrtimer);hrtimer_cancel (&so->txtimer);hrtimer_cancel (&so->echotimer); -hrtimer_cancel (&so->txfrtimer); - so->cfecho =0 ; + +/* new transfer: increment so->tx_gen and set tx.state after barrier */ + my_gen =isotp_inc_tx_gen (READ_ONCE (so->tx_gen)); +isotp_set_tx_result (so, my_gen,ECOMM );/* prevent stale slot matching */ +WRITE_ONCE (so->tx_gen, my_gen); +smp_wmb ();/* see smp_load_acquire() in isotp_tx_[timeout|gen_done] */ +WRITE_ONCE (so->tx.state,ISOTP_SENDING ); +WRITE_ONCE (so->cfecho,0 );spin_unlock_bh (&so->rx_lock);/* so->bound is only checked once above - a wakeup may have -* unbound/rebound the socket meanwhile, so re-validate it +* unbound/rebound the socket meanwhile => recheck */ if (!so->bound) { err = -EADDRNOTAVAIL ;
@@ -1106,6 +1216,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)can_skb_prv (skb)->ifindex = dev->ifindex;can_skb_prv (skb)->skbcnt =0 ; +/* set uid in tx skb to identify CF echo frames */ +isotp_set_skb_uid (skb); + so->tx.len = size; so->tx.idx =0 ;
@@ -1113,8 +1226,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)skb_put_zero (skb, so->ll.mtu);/* cfecho should have been zero'ed by init / former isotp_rcv_echo() */ -if (so->cfecho) -pr_notice_once ("can-isotp: uninit cfecho %08X\n" , so->cfecho); + old_cfecho =READ_ONCE (so->cfecho); +if (old_cfecho) +pr_notice_once ("can-isotp: uninit cfecho %08X\n" , old_cfecho);/* check for single frame transmission depending on TX_DL */ if (size <= so->tx.ll_dl -SF_PCI_SZ4 - ae - off) {
@@ -1142,7 +1256,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) cf->data[ae] |= size;/* set CF echo tag for isotp_rcv_echo() (SF-mode) */ - so->cfecho = *(u32 *)cf->data; +WRITE_ONCE (so->cfecho, skb->hash); }else {/* send first frame */
@@ -1159,7 +1273,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) so->txfc.bs =0 ;/* set CF echo tag for isotp_rcv_echo() (CF-mode) */ - so->cfecho = *(u32 *)cf->data; +WRITE_ONCE (so->cfecho, skb->hash); }else {/* standard flow control check */ new_state =ISOTP_WAIT_FIRST_FC ;
@@ -1169,12 +1283,12 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) tx_hrt = &so->txtimer;/* no CF echo tag for isotp_rcv_echo() (FF-mode) */ - so->cfecho =0 ; +WRITE_ONCE (so->cfecho,0 ); } }spin_lock_bh (&so->rx_lock); -if (so->tx.state ==ISOTP_SHUTDOWN ) { +if (READ_ONCE (so->tx.state) ==ISOTP_SHUTDOWN ) {/* isotp_release() has since taken over and already drained * our timers - don't send into a socket that's going away */
@@ -1185,7 +1299,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)return -EADDRNOTAVAIL ; }/* WAIT_FIRST_FC for standard FF, else stays ISOTP_SENDING */ - so->tx.state = new_state; +WRITE_ONCE (so->tx.state, new_state);hrtimer_start (tx_hrt,ktime_set (hrtimer_sec,0 ),HRTIMER_MODE_REL_SOFT );spin_unlock_bh (&so->rx_lock);
@@ -1202,20 +1316,49 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) __func__, ERR_PTR(err));spin_lock_bh (&so->rx_lock); + +/* new transfer already claimed by a concurrent completion, +* timeout or sendmsg() while we were stuck in can_send()? +*/ +if (READ_ONCE (so->tx_gen) != my_gen) { +/* don't touch timers and state of the new transfer */ +spin_unlock_bh (&so->rx_lock); +return err; + } +/* no transmission -> no timeout monitoring */ hrtimer_cancel (tx_hrt); goto err_out_drop_locked; }if (wait_tx_done) { -/* wait for complete transmission of current pdu */ - err =wait_event_interruptible (so->wait, so->tx.state ==ISOTP_IDLE ); +/* wake up for: +* - concurrent sendmsg() claiming a new transfer +* - complete transmission of current PDU +* - shutdown state change in isotp_release() +* isotp_tx_gen_done() uses common tx.state/tx_gen read sequence +*/ + err =wait_event_interruptible (so->wait, +isotp_tx_gen_done (so, my_gen));if (err) goto err_event_drop; - err =sock_error (sk); -if (err) -return err; +/* still our claim, but isotp_release() force-shut it down */ +if (smp_load_acquire (&so->tx.state) ==ISOTP_SHUTDOWN && +READ_ONCE (so->tx_gen) == my_gen) { + err = -EADDRNOTAVAIL ; + goto err_event_drop; + } + +/* own completion, or tx_gen moved on - either way this is +* what isotp_get_tx_result() recorded for my_gen +*/ + err =isotp_get_tx_result (so, my_gen); + +/* drain to avoid stale error for a later poll()/SO_ERROR */ +sock_error (sk); + +return err ? err : size; }return size;
@@ -1225,15 +1368,26 @@ err_out_drop:spin_lock_bh (&so->rx_lock); goto err_out_drop_locked; err_event_drop: -/* interrupted waiting on our own transfer - drain its timers */ +/* interrupted or shut down while waiting on our own transfer */ spin_lock_bh (&so->rx_lock); + +/* new transfer already started by concurrent sendmsg()? */ +if (READ_ONCE (so->tx_gen) != my_gen) { +/* don't touch timers and states of the new transfer */ +spin_unlock_bh (&so->rx_lock); +return err; + } +hrtimer_cancel (&so->txfrtimer);hrtimer_cancel (&so->txtimer);hrtimer_cancel (&so->echotimer); err_out_drop_locked:/* release the claim; so->rx_lock still held from above */ - so->cfecho =0 ; - so->tx.state =ISOTP_IDLE ; +WRITE_ONCE (so->cfecho,0 ); + +/* only claim to IDLE if isotp_release() has not taken over */ +if (READ_ONCE (so->tx.state) !=ISOTP_SHUTDOWN ) +WRITE_ONCE (so->tx.state,ISOTP_IDLE );spin_unlock_bh (&so->rx_lock);wake_up_interruptible (&so->wait);
@@ -1299,8 +1453,9 @@ static int isotp_release(struct socket *sock)/* best-effort: wait for a running pdu to finish, but don't block on * it forever - give up after the first signal */ -while (so->tx.state !=ISOTP_IDLE && -wait_event_interruptible (so->wait, so->tx.state ==ISOTP_IDLE ) ==0 ) +while (READ_ONCE (so->tx.state) !=ISOTP_IDLE && +wait_event_interruptible (so->wait, +READ_ONCE (so->tx.state) ==ISOTP_IDLE ) ==0 ) ;/* claim the socket under so->rx_lock like sendmsg() does, so its
@@ -1308,9 +1463,12 @@ static int isotp_release(struct socket *sock)* unconditionally, even when a signal cut the wait above short */ spin_lock_bh (&so->rx_lock); - so->tx.state =ISOTP_SHUTDOWN ; +WRITE_ONCE (so->tx.state,ISOTP_SHUTDOWN );spin_unlock_bh (&so->rx_lock); - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE ); + +/* forced SHUTDOWN may have skipped IDLE (gave up on a signal) */ +wake_up_interruptible (&so->wait);spin_lock (&isotp_notifier_lock);while (isotp_busy_notifier == so) {
@@ -1425,7 +1583,8 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)* with so->bound in the same lock_sock() section above, so there is * no window in which a concurrent isotp_notify() could be missed. */ -if (so->tx.state !=ISOTP_IDLE || so->rx.state !=ISOTP_IDLE ) { +if (READ_ONCE (so->tx.state) !=ISOTP_IDLE || +READ_ONCE (so->rx.state) !=ISOTP_IDLE ) { err = -EAGAIN ; goto out; }
@@ -1459,7 +1618,7 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) isotp_rcv, sk, "isotp", sk);/* no consecutive frame echo skb in flight */ - so->cfecho =0 ; +WRITE_ONCE (so->cfecho,0 );/* register for echo skb's */ can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id),
@@ -1825,7 +1984,7 @@ static __poll_t isotp_poll(struct file *file, struct socket *sock, poll_table *wpoll_wait (file, &so->wait, wait);/* Check for false positives due to TX state */ -if ((mask &EPOLLWRNORM ) && (so->tx.state !=ISOTP_IDLE )) +if ((mask &EPOLLWRNORM ) && (READ_ONCE (so->tx.state) !=ISOTP_IDLE )) mask &= ~(EPOLLOUT |EPOLLWRNORM );return mask;
Signature · 1 line
2.43.0
Oliver Hartkopp
maintainerPATCH v2 1/2 can: use skb hash instead of private variable in headroom
In reply to [email protected]commit d4fb6514ff8ed6912a71294e6b66a5d59ee88007 upstream.
The can_skb_priv::skbcnt variable is used to identify CAN skbs in the RX path analogue to the skb->hash.
As the skb hash is not filled in CAN skbs move the private skbcnt value to skb->hash and set skb->sw_hash accordingly. The skb->hash is a value used for RPS to identify skbs. Use it as intended.
--- drivers/net/can/dev/skb.c | 2 -- include/linux/can/core.h | 1 + include/linux/can/skb.h | 2 -- net/can/af_can.c | 14 +++++++++++--- net/can/bcm.c | 2 -- net/can/isotp.c | 3 --- net/can/j1939/socket.c | 1 - net/can/j1939/transport.c | 2 -- net/can/raw.c | 7 +++---- 9 files changed, 15 insertions(+), 19 deletions(-)
drivers/net/can/dev/skb.c +0 -2
@@ -200,11 +200,10 @@ static void init_can_skb_reserve(struct sk_buff *skb)skb_reset_mac_header (skb);skb_reset_network_header (skb);skb_reset_transport_header (skb);can_skb_reserve (skb); -can_skb_prv (skb)->skbcnt =0 ; }struct sk_buff *alloc_can_skb (struct net_device *dev,struct can_frame **cf) {struct sk_buff *skb;
@@ -310,11 +309,10 @@ static bool can_skb_headroom_valid(struct net_device *dev, struct sk_buff *skb)/* af_packet does not apply CAN skb specific settings */ if (skb->ip_summed ==CHECKSUM_NONE ) {/* init headroom */ can_skb_prv (skb)->ifindex = dev->ifindex; -can_skb_prv (skb)->skbcnt =0 ; skb->ip_summed =CHECKSUM_UNNECESSARY ;/* perform proper loopback on capable devices */ if (dev->flags &IFF_ECHO )
include/linux/can/core.h +1 -0
@@ -56,8 +56,9 @@ extern void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id, canid_t mask, void (*func)(struct sk_buff *, void *), void *data);extern int can_send (struct sk_buff *skb,int loop); +void can_set_skb_uid (struct sk_buff *skb);void can_sock_destruct (struct sock *sk);#endif /* !_CAN_CORE_H */
include/linux/can/skb.h +0 -2
@@ -47,17 +47,15 @@ bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb);*/ /** * struct can_skb_priv - private additional data inside CAN sk_buffs * @ifindex: ifindex of the first interface the CAN frame appeared on -* @skbcnt: atomic counter to have an unique id together with skb pointer * @frame_len: length of CAN frame in data link layer * @cf: align to the following CAN frame at skb->data */ struct can_skb_priv {int ifindex; -int skbcnt;unsigned int frame_len;struct can_frame cf[]; };static inline struct can_skb_priv *can_skb_prv (struct sk_buff *skb)
net/can/af_can.c +11 -3
@@ -637,10 +637,20 @@ static int can_rcv_filter(struct can_dev_rcv_lists *dev_rcv_lists, struct sk_buf }return matches; } +void can_set_skb_uid (struct sk_buff *skb) +{ +/* create non-zero unique skb identifier together with *skb */ +while (!(skb->hash)) + skb->hash =atomic_inc_return (&skbcounter); + + skb->sw_hash =1 ; +} +EXPORT_SYMBOL (can_set_skb_uid); +static void can_receive (struct sk_buff *skb,struct net_device *dev) {struct can_dev_rcv_lists *dev_rcv_lists;struct net *net =dev_net (dev);struct can_pkg_stats *pkg_stats = net->can.pkg_stats;
@@ -648,13 +658,11 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev)/* update statistics */ atomic_long_inc (&pkg_stats->rx_frames);atomic_long_inc (&pkg_stats->rx_frames_delta); -/* create non-zero unique skb identifier together with *skb */ -while (!(can_skb_prv (skb)->skbcnt)) -can_skb_prv (skb)->skbcnt =atomic_inc_return (&skbcounter); +can_set_skb_uid (skb);rcu_read_lock ();/* deliver the packet to sockets listening on all devices */ matches =can_rcv_filter (net->can.rx_alldev_list, skb);
net/can/bcm.c +0 -2
@@ -348,11 +348,10 @@ static void bcm_can_tx(struct bcm_op *op, struct canfd_frame *cf)if (!skb) goto out;can_skb_reserve (skb);can_skb_prv (skb)->ifindex = dev->ifindex; -can_skb_prv (skb)->skbcnt =0 ;skb_put_data (skb, cf, op->cfsiz);/* send with loopback */ skb->dev = dev;
@@ -1622,11 +1621,10 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk,kfree_skb (skb);return -ENODEV ; }can_skb_prv (skb)->ifindex = dev->ifindex; -can_skb_prv (skb)->skbcnt =0 ; skb->dev = dev;can_skb_set_owner (skb, sk); err =can_send (skb,1 );/* send with loopback */ dev_put (dev);
net/can/isotp.c +0 -3
@@ -230,11 +230,10 @@ static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus)return 1 ; }can_skb_reserve (nskb);can_skb_prv (nskb)->ifindex = dev->ifindex; -can_skb_prv (nskb)->skbcnt =0 ; nskb->dev = dev;can_skb_set_owner (nskb, sk); ncf = (struct canfd_frame *)nskb->data;skb_put_zero (nskb, so->ll.mtu);
@@ -796,11 +795,10 @@ static void isotp_send_cframe(struct isotp_sock *so)return ; }can_skb_reserve (skb);can_skb_prv (skb)->ifindex = dev->ifindex; -can_skb_prv (skb)->skbcnt =0 ; cf = (struct canfd_frame *)skb->data;skb_put_zero (skb, so->ll.mtu);/* create consecutive frame */
@@ -1102,11 +1100,10 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) goto err_out_drop; }can_skb_reserve (skb);can_skb_prv (skb)->ifindex = dev->ifindex; -can_skb_prv (skb)->skbcnt =0 ; so->tx.len = size; so->tx.idx =0 ; cf = (struct canfd_frame *)skb->data;
net/can/j1939/socket.c +0 -1
@@ -887,11 +887,10 @@ static struct sk_buff *j1939_sk_alloc_skb(struct net_device *ndev,if (!skb) goto failure;can_skb_reserve (skb);can_skb_prv (skb)->ifindex = ndev->ifindex; -can_skb_prv (skb)->skbcnt =0 ;skb_reserve (skb, offsetof(struct can_frame , data)); ret =memcpy_from_msg (skb_put (skb, size), msg, size);if (ret <0 ) goto free_skb;
net/can/j1939/transport.c +0 -2
@@ -610,11 +610,10 @@ sk_buff *j1939_tp_tx_dat_new(struct j1939_priv *priv,return ERR_PTR (-ENOMEM ); skb->dev = priv->ndev;can_skb_reserve (skb);can_skb_prv (skb)->ifindex = priv->ndev->ifindex; -can_skb_prv (skb)->skbcnt =0 ;/* reserve CAN header */ skb_reserve (skb, offsetof(struct can_frame , data));/* skb->cb must be large enough to hold a j1939_sk_buff_cb structure */ BUILD_BUG_ON (sizeof (skb->cb) <sizeof (*re_skcb));
@@ -1549,11 +1548,10 @@ j1939_session *j1939_session_fresh_new(struct j1939_priv *priv,return NULL ; skb->dev = priv->ndev;can_skb_reserve (skb);can_skb_prv (skb)->ifindex = priv->ndev->ifindex; -can_skb_prv (skb)->skbcnt =0 ; skcb =j1939_skb_to_cb (skb);memcpy (skcb, rel_skcb,sizeof (*skcb)); session =j1939_session_new (priv, skb, size);if (!session) {
net/can/raw.c +3 -4
@@ -73,12 +73,12 @@ MODULE_ALIAS("can-proto-1");* list containing only one item. This common case is optimized by * storing the single filter in dfilter, to avoid using dynamic memory. */ struct uniqframe { -int skbcnt;const struct sk_buff *skb; +u32 hash;unsigned int join_rx_count; };struct raw_sock {struct sock sk;
@@ -161,21 +161,21 @@ static void raw_rcv(struct sk_buff *oskb, void *data) } }/* eliminate multiple filter matches for the same skb */ if (this_cpu_ptr (ro->uniq)->skb == oskb && -this_cpu_ptr (ro->uniq)->skbcnt ==can_skb_prv (oskb)->skbcnt) { +this_cpu_ptr (ro->uniq)->hash == oskb->hash) {if (!ro->join_filters)return ;this_cpu_inc (ro->uniq->join_rx_count);/* drop frame until all enabled filters matched */ if (this_cpu_ptr (ro->uniq)->join_rx_count < ro->count)return ; }else {this_cpu_ptr (ro->uniq)->skb = oskb; -this_cpu_ptr (ro->uniq)->skbcnt =can_skb_prv (oskb)->skbcnt; +this_cpu_ptr (ro->uniq)->hash = oskb->hash;this_cpu_ptr (ro->uniq)->join_rx_count =1 ;/* drop first frame to check all enabled filters? */ if (ro->join_filters && ro->count >1 )return ; }
@@ -943,11 +943,10 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)if (!skb) goto put_dev;can_skb_reserve (skb);can_skb_prv (skb)->ifindex = dev->ifindex; -can_skb_prv (skb)->skbcnt =0 ;/* fill the skb before testing for valid CAN frames */ err =memcpy_from_msg (skb_put (skb, size), msg, size);if (err <0 ) goto free_skb;
Signature · 1 line
2.53.0
Oliver Hartkopp
maintainerPATCH v2 2/2 can: isotp: fix timer drain order, wakeup handling and tx_gen ordering
commit 050f010f920da17c1044a4f174766ad553e770b6 upstream.
This patch is a follow-up to commit cf070fe33bfb ("can: isotp: serialize TX state transitions under so->rx_lock") which addresses following sashiko-bot findings:
- isotp_sendmsg(): drain so->txfrtimer first so a stale callback can't re-arm echotimer after the claim
- isotp_release(): wake so->wait after forcing ISOTP_SHUTDOWN so a sleeping sendmsg() claim isn't stranded
- isotp_sendmsg(): have both wait_event_interruptible() calls in isotp_sendmsg() also wake on ISOTP_SHUTDOWN and do not return claim to IDLE to avoid corrupting a concurrent isotp_release() process.
- isotp_sendmsg(): handle potential claim of a new transfer when the wait_event_interruptible() call returns in CAN_ISOTP_WAIT_TX_DONE mode. Don't touch timers and states of the new transfer if a new thread incremented so->tx_gen before getting the lock at err_event_drop.
- isotp_sendmsg(): handle a stuck can_send() and omit timer and state changes if a new transfer was claimed. wait_tx_done() returns the error recorded in so->tx_result[], tagged with the caller's own generation.
- isotp_tx_timeout(): on a claimed timeout, record the ECOMM error for the timed-out transfer's own generation in so->tx_result[]; sk->sk_err is raised unconditionally, same as every other error path here.
- isotp_tx_gen_done()/isotp_tx_timeout(): always read tx.state (acquire) before tx_gen - the reverse order let a weakly ordered CPU pair a fresh tx.state with a stale tx_gen/tx_result slot.
- isotp_sendmsg(): wait_tx_done: drain sk_err via sock_error() once we have read the result from so->tx_result[], so an already-reported error doesn't stay latched for a later poll()/SO_ERROR.
Also align the remaining lock-free so->tx.state/rx.state/cfecho accesses and use skb->hash as unique loopback echo frame indicator.
--- net/can/isotp.c | 317 +++++++++++++++++++++++++++++++++++------------- 1 file changed, 230 insertions(+), 87 deletions(-)
net/can/isotp.c +230 -87
@@ -124,10 +124,19 @@ MODULE_PARM_DESC(max_pdu_size, "maximum isotp pdu size (default "#define ISOTP_FC_OVFLW 2/* overflow */ #define ISOTP_FC_TIMEOUT 1/* 1 sec */ #define ISOTP_ECHO_TIMEOUT 2/* 2 secs */ +/* so->tx_result[so->tx_gen % ISOTP_TX_RESULT_SLOTS] holds the packed value +* (err << ISOTP_TX_RESULT_GEN_BITS | gen) for each tx generation slot, so it +* can be handled with a single READ_ONCE()/WRITE_ONCE() access. +*/ +#define ISOTP_TX_RESULT_SLOTS 4 +#define ISOTP_TX_RESULT_GEN_BITS 24 +#define ISOTP_TX_RESULT_GEN_MASK ((1U << ISOTP_TX_RESULT_GEN_BITS) - 1) +#define ISOTP_TX_RESULT_ERR_MASK 0xFF +enum {ISOTP_IDLE =0 ,ISOTP_WAIT_FIRST_FC ,ISOTP_WAIT_FC ,ISOTP_WAIT_DATA ,
@@ -162,21 +171,81 @@ struct isotp_sock {struct can_isotp_ll_options ll;u32 frame_txtime;u32 force_tx_stmin;u32 force_rx_stmin;u32 cfecho;/* consecutive frame echo tag */ -u32 tx_gen;/* generation, bumped per new tx transfer */ +u32 tx_gen;/* transfer generation, increased per new tx transfer */ +u32 tx_result[ISOTP_TX_RESULT_SLOTS ];/* per-generation result slots */ struct tpcon rx, tx;struct list_head notifier;wait_queue_head_t wait;spinlock_t rx_lock;/* protect single thread state machine */ };static LIST_HEAD (isotp_notifier_list);static DEFINE_SPINLOCK (isotp_notifier_lock);static struct isotp_sock *isotp_busy_notifier; +/* increase (24 bit) tx generation value */ +static u32 isotp_inc_tx_gen (u32 gen) +{ +return (gen +1 ) &ISOTP_TX_RESULT_GEN_MASK ; +} + +/* store 8 bit error and 24 bit tx generation values in packed u32 element */ +static u32 isotp_pack_tx_result (u32 gen,int err) +{ +return gen | ((u32 )err <<ISOTP_TX_RESULT_GEN_BITS ); +} + +/* get the 24 bit tx generation value from the tx result */ +static u32 isotp_get_tx_gen (u32 gen_err) +{ +return gen_err &ISOTP_TX_RESULT_GEN_MASK ; +} + +/* get the 8 bit error value from the tx result */ +static u32 isotp_get_tx_err (u32 gen_err) +{ +return (gen_err >>ISOTP_TX_RESULT_GEN_BITS ) &ISOTP_TX_RESULT_ERR_MASK ; +} + +/* store transfer result in per-generation%4 so->tx_result[] slot */ +static void isotp_set_tx_result (struct isotp_sock *so,u32 gen,int err) +{ +WRITE_ONCE (so->tx_result[gen %ISOTP_TX_RESULT_SLOTS ], +isotp_pack_tx_result (gen, err)); +} + +/* fetch the result recorded for 'gen', as a (negative) errno (0 for success) */ +static int isotp_get_tx_result (struct isotp_sock *so,u32 gen) +{ +u32 result =READ_ONCE (so->tx_result[gen %ISOTP_TX_RESULT_SLOTS ]); + +if (isotp_get_tx_gen (result) != gen) { +pr_notice_once ("can-isotp: tx_result[] slot reused before read\n" ); + +/* report failure rather than risk a false success */ +return -ECOMM ; + } + +return -(isotp_get_tx_err (result)); +} + +/* true if done, shut down or superseded ('gen' is no longer the active +* transfer). Reads tx.state first (acquire) so tx_gen/tx_result reads +* below see at least what that state write published (common sequence). +*/ +static bool isotp_tx_gen_done (struct isotp_sock *so,u32 gen) +{ +/* read tx.state first for the common sequence */ +u32 state =smp_load_acquire (&so->tx.state); + +return state ==ISOTP_IDLE || state ==ISOTP_SHUTDOWN || +READ_ONCE (so->tx_gen) != gen; +} +static inline struct isotp_sock *isotp_sk (const struct sock *sk) {return (struct isotp_sock *)sk; }
@@ -195,20 +264,20 @@ static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, rxtimer);struct sock *sk = &so->sk; -if (so->rx.state ==ISOTP_WAIT_DATA ) { +if (READ_ONCE (so->rx.state) ==ISOTP_WAIT_DATA ) {/* we did not get new data frames in time */ /* report 'connection timed out' */ sk->sk_err =ETIMEDOUT ;if (!sock_flag (sk,SOCK_DEAD ))sk_error_report (sk);/* reset rx state */ - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE ); }return HRTIMER_NORESTART ; }
@@ -361,41 +430,42 @@ static int check_pad(struct isotp_sock *so, struct canfd_frame *cf,static void isotp_send_cframe (struct isotp_sock *so);static int isotp_rcv_fc (struct isotp_sock *so,struct canfd_frame *cf,int ae) {struct sock *sk = &so->sk; +int tx_err =EBADMSG ;/* default for unknown FC status */ -if (so->tx.state !=ISOTP_WAIT_FC && - so->tx.state !=ISOTP_WAIT_FIRST_FC ) +if (READ_ONCE (so->tx.state) !=ISOTP_WAIT_FC && +READ_ONCE (so->tx.state) !=ISOTP_WAIT_FIRST_FC )return 0 ;hrtimer_cancel (&so->txtimer);/* isotp_tx_timeout() may have given up on this job while -* hrtimer_cancel() above waited for it to finish; so->rx_lock -* (held by our caller isotp_rcv()) rules out a concurrent claim, -* so a plain recheck is enough here. +* hrtimer_cancel() above waited for it to finish => recheck */ -if (so->tx.state !=ISOTP_WAIT_FC && - so->tx.state !=ISOTP_WAIT_FIRST_FC ) +if (READ_ONCE (so->tx.state) !=ISOTP_WAIT_FC && +READ_ONCE (so->tx.state) !=ISOTP_WAIT_FIRST_FC )return 1 ;if ((cf->len < ae +FC_CONTENT_SZ ) || ((so->opt.flags &ISOTP_CHECK_PADDING ) &&check_pad (so, cf, ae +FC_CONTENT_SZ , so->opt.rxpad_content))) {/* malformed PDU - report 'not a data message' */ sk->sk_err =EBADMSG ;if (!sock_flag (sk,SOCK_DEAD ))sk_error_report (sk); - so->tx.state =ISOTP_IDLE ; +isotp_set_tx_result (so, so->tx_gen,EBADMSG ); +/* set to IDLE after publishing tx_result */ +smp_store_release (&so->tx.state,ISOTP_IDLE );wake_up_interruptible (&so->wait);return 1 ; }/* get static/dynamic communication params from first/every FC frame */ -if (so->tx.state ==ISOTP_WAIT_FIRST_FC || +if (READ_ONCE (so->tx.state) ==ISOTP_WAIT_FIRST_FC || so->opt.flags &CAN_ISOTP_DYN_FC_PARMS ) { so->txfc.bs = cf->data[ae +1 ]; so->txfc.stmin = cf->data[ae +2 ];/* fix wrong STmin values according spec */
@@ -415,17 +485,17 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) so->txfc.stmin * 1000000); else so->tx_gap = ktime_add_ns(so->tx_gap, (so->txfc.stmin -0xF0 ) *100000 ); - so->tx.state =ISOTP_WAIT_FC ; +WRITE_ONCE (so->tx.state,ISOTP_WAIT_FC ); }switch (cf->data[ae] &0x0F ) {case ISOTP_FC_CTS : so->tx.bs =0 ; - so->tx.state =ISOTP_SENDING ; +WRITE_ONCE (so->tx.state,ISOTP_SENDING );/* send CF frame and enable echo timeout handling */ hrtimer_start (&so->echotimer,ktime_set (ISOTP_ECHO_TIMEOUT ,0 ),HRTIMER_MODE_REL_SOFT );isotp_send_cframe (so);break ;
@@ -436,18 +506,23 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) HRTIMER_MODE_REL_SOFT);break ;case ISOTP_FC_OVFLW :/* overflow on receiver side - report 'message too long' */ - sk->sk_err =EMSGSIZE ; -if (!sock_flag (sk,SOCK_DEAD )) -sk_error_report (sk); + tx_err =EMSGSIZE ; fallthrough;default : -/* stop this tx job */ - so->tx.state =ISOTP_IDLE ; +/* reserved/unknown flow status (tx_err defaults to EBADMSG) */ + + sk->sk_err = tx_err; +if (!sock_flag (sk,SOCK_DEAD )) +sk_error_report (sk); + +isotp_set_tx_result (so, so->tx_gen, tx_err); +/* set to IDLE after publishing tx_result */ +smp_store_release (&so->tx.state,ISOTP_IDLE );wake_up_interruptible (&so->wait); }return 0 ; }
@@ -456,11 +531,11 @@ static int isotp_rcv_sf(struct sock *sk, struct canfd_frame *cf, int pcilen, {struct isotp_sock *so =isotp_sk (sk);struct sk_buff *nskb;hrtimer_cancel (&so->rxtimer); - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE );if (!len || len > cf->len - pcilen)return 1 ; if ((so->opt.flags & ISOTP_CHECK_PADDING) &&
@@ -490,11 +565,11 @@ static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae)int i;int off;int ff_pci_sz;hrtimer_cancel (&so->rxtimer); - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE );/* get the used sender LL_DL from the (first) CAN frame data length */ so->rx.ll_dl =padlen (cf->len);/* the first frame has to use the entire frame up to LL_DL length */
@@ -544,11 +619,11 @@ static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae)for (i = ae + ff_pci_sz; i < so->rx.ll_dl; i++) so->rx.buf[so->rx.idx++] = cf->data[i];/* initial setup for this pdu reception */ so->rx.sn =1 ; - so->rx.state =ISOTP_WAIT_DATA ; +WRITE_ONCE (so->rx.state,ISOTP_WAIT_DATA );/* no creation of flow control frames */ if (so->opt.flags &CAN_ISOTP_LISTEN_MODE )return 0 ;
@@ -562,11 +637,11 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, {struct isotp_sock *so =isotp_sk (sk);struct sk_buff *nskb;int i; -if (so->rx.state !=ISOTP_WAIT_DATA ) +if (READ_ONCE (so->rx.state) !=ISOTP_WAIT_DATA )return 0 ;/* drop if timestamp gap is less than force_rx_stmin nano secs */ if (so->opt.flags &CAN_ISOTP_FORCE_RXSTMIN ) { if (ktime_to_ns(ktime_sub(skb->tstamp, so->lastrxcf_tstamp)) <
@@ -577,15 +652,13 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, }hrtimer_cancel (&so->rxtimer);/* isotp_rx_timer_handler() may have raced us for so->rx.state -* while hrtimer_cancel() above waited for it to finish, already -* reporting ETIMEDOUT and resetting the reception; don't process -* this CF into a reassembly that has already been given up on. +* while hrtimer_cancel() above waited for it to finish => recheck */ -if (so->rx.state !=ISOTP_WAIT_DATA ) +if (READ_ONCE (so->rx.state) !=ISOTP_WAIT_DATA )return 1 ;/* CFs are never longer than the FF */ if (cf->len > so->rx.ll_dl)return 1 ;
@@ -602,11 +675,11 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, sk->sk_err =EILSEQ ;if (!sock_flag (sk,SOCK_DEAD ))sk_error_report (sk);/* reset rx state */ - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE );return 1 ; } so->rx.sn++; so->rx.sn %=16 ;
@@ -616,11 +689,11 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae,break ; }if (so->rx.idx >= so->rx.len) {/* we are done */ - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE );if ((so->opt.flags &ISOTP_CHECK_PADDING ) &&check_pad (so, cf, i +1 , so->opt.rxpad_content)) {/* malformed PDU - report 'not a data message' */ sk->sk_err =EBADMSG ;
@@ -687,12 +760,14 @@ static void isotp_rcv(struct sk_buff *skb, void *data)*/ spin_lock (&so->rx_lock);if (so->opt.flags &CAN_ISOTP_HALF_DUPLEX ) {/* check rx/tx path half duplex expectations */ -if ((so->tx.state !=ISOTP_IDLE && n_pci_type !=N_PCI_FC ) || - (so->rx.state !=ISOTP_IDLE && n_pci_type ==N_PCI_FC )) +if ((READ_ONCE (so->tx.state) !=ISOTP_IDLE && + n_pci_type !=N_PCI_FC ) || + (READ_ONCE (so->rx.state) !=ISOTP_IDLE && + n_pci_type ==N_PCI_FC )) goto out_unlock; }switch (n_pci_type) {case N_PCI_FC :
@@ -782,10 +857,11 @@ static void isotp_send_cframe(struct isotp_sock *so)struct sk_buff *skb;struct net_device *dev;struct canfd_frame *cf;int can_send_ret;int ae = (so->opt.flags &CAN_ISOTP_EXTEND_ADDR ) ?1 :0 ; +u32 old_cfecho; dev =dev_get_by_index (sock_net (sk), so->ifindex);if (!dev)return ;
@@ -796,10 +872,13 @@ static void isotp_send_cframe(struct isotp_sock *so) }can_skb_reserve (skb);can_skb_prv (skb)->ifindex = dev->ifindex; +/* set uid in tx skb to identify CF echo frames */ +can_set_skb_uid (skb); + cf = (struct canfd_frame *)skb->data;skb_put_zero (skb, so->ll.mtu);/* create consecutive frame */ isotp_fill_dataframe (cf, so, ae,0 );
@@ -812,16 +891,19 @@ static void isotp_send_cframe(struct isotp_sock *so) cf->flags = so->ll.tx_flags; skb->dev = dev;can_skb_set_owner (skb, sk); -/* cfecho should have been zero'ed by init/isotp_rcv_echo() */ -if (so->cfecho) -pr_notice_once ("can-isotp: cfecho is %08X != 0\n" , so->cfecho); +/* zero'ed by init/isotp_rcv_echo(); reached lock-free via +* isotp_txfr_timer_handler() too, so use READ_ONCE()/WRITE_ONCE() +*/ + old_cfecho =READ_ONCE (so->cfecho); +if (old_cfecho) +pr_notice_once ("can-isotp: cfecho is %08X != 0\n" , old_cfecho);/* set consecutive frame echo tag */ - so->cfecho = *(u32 *)cf->data; +WRITE_ONCE (so->cfecho, skb->hash);/* send frame with local echo enabled */ can_send_ret =can_send (skb,1 );if (can_send_ret) { pr_notice_once("can-isotp: %s: can_send_ret %pe\n",
@@ -869,11 +951,10 @@ static void isotp_create_fframe(struct canfd_frame *cf, struct isotp_sock *so,static void isotp_rcv_echo (struct sk_buff *skb,void *data) {struct sock *sk = (struct sock *)data;struct isotp_sock *so =isotp_sk (sk); -struct canfd_frame *cf = (struct canfd_frame *)skb->data;/* only handle my own local echo CF/SF skb's (no FF!) */ if (skb->sk != sk)return ;
@@ -881,36 +962,39 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data)* (no isotp_rcv() caller here), so take it ourselves */ spin_lock (&so->rx_lock);/* so->cfecho may since belong to a new transfer; recheck under lock */ -if (so->cfecho != *(u32 *)cf->data) +if (READ_ONCE (so->cfecho) != skb->hash) goto out_unlock;/* cancel local echo timeout */ hrtimer_cancel (&so->echotimer);/* local echo skb with consecutive frame has been consumed */ - so->cfecho =0 ; +WRITE_ONCE (so->cfecho,0 );/* claiming a transfer also takes so->rx_lock, so a plain recheck * is enough: so->tx.state can't have flipped to ISOTP_SENDING for * a new claim while we're still in here */ -if (so->tx.state !=ISOTP_SENDING ) +if (READ_ONCE (so->tx.state) !=ISOTP_SENDING ) goto out_unlock;if (so->tx.idx >= so->tx.len) {/* we are done */ - so->tx.state =ISOTP_IDLE ; + +isotp_set_tx_result (so, so->tx_gen,0 ); +/* set to IDLE after publishing tx_result */ +smp_store_release (&so->tx.state,ISOTP_IDLE );wake_up_interruptible (&so->wait); goto out_unlock; }if (so->txfc.bs && so->tx.bs >= so->txfc.bs) {/* stop and wait for FC with timeout */ - so->tx.state =ISOTP_WAIT_FC ; +WRITE_ONCE (so->tx.state,ISOTP_WAIT_FC );hrtimer_start (&so->txtimer,ktime_set (ISOTP_FC_TIMEOUT ,0 ),HRTIMER_MODE_REL_SOFT ); goto out_unlock; }
@@ -928,37 +1012,41 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) out_unlock:spin_unlock (&so->rx_lock); } -/* shared by so->txtimer's and so->echotimer's callbacks. Both timers get -* cancelled under so->rx_lock elsewhere, so this must stay lock-free to -* avoid deadlocking with that; uses so->tx_gen instead to avoid tainting -* a new transfer with an error from the one that just timed out. +/* isotp_tx_timeout: we did not get any flow control or echo frame in time +* +* Shared by so->txtimer's and so->echotimer's callbacks. Both timers get +* cancelled under so->rx_lock elsewhere, so this must stay lock-free. +* +* tx.state is acquired before tx_gen. Common sequence in isotp_tx_gen_done(). +* cmpxchg() only orders itself, not the two preceding loads. */ static enum hrtimer_restart isotp_tx_timeout (struct isotp_sock *so) {struct sock *sk = &so->sk; +/* read tx.state first for the common sequence */ +u32 old_state =smp_load_acquire (&so->tx.state);u32 gen =READ_ONCE (so->tx_gen); -u32 old_state =READ_ONCE (so->tx.state);/* don't handle timeouts in IDLE or SHUTDOWN state */ if (old_state ==ISOTP_IDLE || old_state ==ISOTP_SHUTDOWN )return HRTIMER_NORESTART ;/* only claim the timeout if the state is still unchanged */ if (cmpxchg (&so->tx.state, old_state,ISOTP_IDLE ) != old_state)return HRTIMER_NORESTART ; -/* we did not get any flow control or echo frame in time */ +/* detected timeout: report 'communication error on send' */ -if (READ_ONCE (so->tx_gen) == gen) { -/* report 'communication error on send' */ - sk->sk_err =ECOMM ; -if (!sock_flag (sk,SOCK_DEAD )) -sk_error_report (sk); - } +/* a stale read of this slot by a waiter still falls back to ECOMM */ +isotp_set_tx_result (so, gen,ECOMM ); + + sk->sk_err =ECOMM ; +if (!sock_flag (sk,SOCK_DEAD )) +sk_error_report (sk);wake_up_interruptible (&so->wait);return HRTIMER_NORESTART ; }
@@ -989,11 +1077,11 @@ static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer)/* start echo timeout handling and cover below protocol error */ hrtimer_start (&so->echotimer,ktime_set (ISOTP_ECHO_TIMEOUT ,0 ),HRTIMER_MODE_REL_SOFT );/* cfecho should be consumed by isotp_rcv_echo() here */ -if (so->tx.state ==ISOTP_SENDING && !so->cfecho) +if (READ_ONCE (so->tx.state) ==ISOTP_SENDING && !READ_ONCE (so->cfecho))isotp_send_cframe (so);return HRTIMER_NORESTART ; }
@@ -1007,14 +1095,16 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)int ae = (so->opt.flags &CAN_ISOTP_EXTEND_ADDR ) ?1 :0 ;int wait_tx_done = (so->opt.flags &CAN_ISOTP_WAIT_TX_DONE ) ?1 :0 ;s64 hrtimer_sec =ISOTP_ECHO_TIMEOUT ;struct hrtimer *tx_hrt = &so->echotimer;u32 new_state =ISOTP_SENDING ; +u32 my_gen; +u32 old_cfecho;int off;int err; -if (!so->bound || so->tx.state ==ISOTP_SHUTDOWN ) +if (!so->bound ||READ_ONCE (so->tx.state) ==ISOTP_SHUTDOWN )return -EADDRNOTAVAIL ;/* claim the socket under so->rx_lock: this serializes the claim * with the RX path and with sendmsg()'s own error paths below, so * none of them can ever see a transfer mid-claim
@@ -1027,33 +1117,37 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)/* we do not support multiple buffers - for now */ if (msg->msg_flags &MSG_DONTWAIT )return -EAGAIN ; -if (so->tx.state ==ISOTP_SHUTDOWN ) +if (READ_ONCE (so->tx.state) ==ISOTP_SHUTDOWN )return -EADDRNOTAVAIL ;/* wait for complete transmission of current pdu */ err =wait_event_interruptible (so->wait, - so->tx.state ==ISOTP_IDLE ); +READ_ONCE (so->tx.state) ==ISOTP_IDLE || +READ_ONCE (so->tx.state) ==ISOTP_SHUTDOWN );if (err)return err; } -/* new transfer: bump so->tx_gen and drain the old one's timers, -* still under the so->rx_lock we just claimed the socket with -*/ -WRITE_ONCE (so->tx.state,ISOTP_SENDING ); -WRITE_ONCE (so->tx_gen,READ_ONCE (so->tx_gen) +1 ); +/* txfrtimer's callback re-arms echotimer lock-free: drain it first */ +hrtimer_cancel (&so->txfrtimer);hrtimer_cancel (&so->txtimer);hrtimer_cancel (&so->echotimer); -hrtimer_cancel (&so->txfrtimer); - so->cfecho =0 ; + +/* new transfer: increment so->tx_gen and set tx.state after barrier */ + my_gen =isotp_inc_tx_gen (READ_ONCE (so->tx_gen)); +isotp_set_tx_result (so, my_gen,ECOMM );/* prevent stale slot matching */ +WRITE_ONCE (so->tx_gen, my_gen); +smp_wmb ();/* see smp_load_acquire() in isotp_tx_[timeout|gen_done] */ +WRITE_ONCE (so->tx.state,ISOTP_SENDING ); +WRITE_ONCE (so->cfecho,0 );spin_unlock_bh (&so->rx_lock);/* so->bound is only checked once above - a wakeup may have -* unbound/rebound the socket meanwhile, so re-validate it +* unbound/rebound the socket meanwhile => recheck */ if (!so->bound) { err = -EADDRNOTAVAIL ; goto err_out_drop; }
@@ -1101,19 +1195,23 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) }can_skb_reserve (skb);can_skb_prv (skb)->ifindex = dev->ifindex; +/* set uid in tx skb to identify CF echo frames */ +can_set_skb_uid (skb); + so->tx.len = size; so->tx.idx =0 ; cf = (struct canfd_frame *)skb->data;skb_put_zero (skb, so->ll.mtu);/* cfecho should have been zero'ed by init / former isotp_rcv_echo() */ -if (so->cfecho) -pr_notice_once ("can-isotp: uninit cfecho %08X\n" , so->cfecho); + old_cfecho =READ_ONCE (so->cfecho); +if (old_cfecho) +pr_notice_once ("can-isotp: uninit cfecho %08X\n" , old_cfecho);/* check for single frame transmission depending on TX_DL */ if (size <= so->tx.ll_dl -SF_PCI_SZ4 - ae - off) {/* The message size generally fits into a SingleFrame - good. *
@@ -1137,11 +1235,11 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) cf->data[SF_PCI_SZ4 + ae] = size; else cf->data[ae] |= size;/* set CF echo tag for isotp_rcv_echo() (SF-mode) */ - so->cfecho = *(u32 *)cf->data; +WRITE_ONCE (so->cfecho, skb->hash); }else {/* send first frame */ isotp_create_fframe (cf, so, ae);
@@ -1154,37 +1252,37 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)/* disable wait for FCs due to activated block size */ so->txfc.bs =0 ;/* set CF echo tag for isotp_rcv_echo() (CF-mode) */ - so->cfecho = *(u32 *)cf->data; +WRITE_ONCE (so->cfecho, skb->hash); }else {/* standard flow control check */ new_state =ISOTP_WAIT_FIRST_FC ;/* start timeout for FC */ hrtimer_sec =ISOTP_FC_TIMEOUT ; tx_hrt = &so->txtimer;/* no CF echo tag for isotp_rcv_echo() (FF-mode) */ - so->cfecho =0 ; +WRITE_ONCE (so->cfecho,0 ); } }spin_lock_bh (&so->rx_lock); -if (so->tx.state ==ISOTP_SHUTDOWN ) { +if (READ_ONCE (so->tx.state) ==ISOTP_SHUTDOWN ) {/* isotp_release() has since taken over and already drained * our timers - don't send into a socket that's going away */ spin_unlock_bh (&so->rx_lock);kfree_skb (skb);dev_put (dev);wake_up_interruptible (&so->wait);return -EADDRNOTAVAIL ; }/* WAIT_FIRST_FC for standard FF, else stays ISOTP_SENDING */ - so->tx.state = new_state; +WRITE_ONCE (so->tx.state, new_state);hrtimer_start (tx_hrt,ktime_set (hrtimer_sec,0 ),HRTIMER_MODE_REL_SOFT );spin_unlock_bh (&so->rx_lock);/* send the first or only CAN frame */
@@ -1197,42 +1295,82 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)if (err) {pr_notice_once ("can-isotp: %s: can_send_ret %pe\n" , __func__,ERR_PTR (err));spin_lock_bh (&so->rx_lock); + +/* new transfer already claimed by a concurrent completion, +* timeout or sendmsg() while we were stuck in can_send()? +*/ +if (READ_ONCE (so->tx_gen) != my_gen) { +/* don't touch timers and state of the new transfer */ +spin_unlock_bh (&so->rx_lock); +return err; + } +/* no transmission -> no timeout monitoring */ hrtimer_cancel (tx_hrt); goto err_out_drop_locked; }if (wait_tx_done) { -/* wait for complete transmission of current pdu */ - err =wait_event_interruptible (so->wait, so->tx.state ==ISOTP_IDLE ); +/* wake up for: +* - concurrent sendmsg() claiming a new transfer +* - complete transmission of current PDU +* - shutdown state change in isotp_release() +* isotp_tx_gen_done() uses common tx.state/tx_gen read sequence +*/ + err =wait_event_interruptible (so->wait, +isotp_tx_gen_done (so, my_gen));if (err) goto err_event_drop; - err =sock_error (sk); -if (err) -return err; +/* still our claim, but isotp_release() force-shut it down */ +if (smp_load_acquire (&so->tx.state) ==ISOTP_SHUTDOWN && +READ_ONCE (so->tx_gen) == my_gen) { + err = -EADDRNOTAVAIL ; + goto err_event_drop; + } + +/* own completion, or tx_gen moved on - either way this is +* what isotp_get_tx_result() recorded for my_gen +*/ + err =isotp_get_tx_result (so, my_gen); + +/* drain to avoid stale error for a later poll()/SO_ERROR */ +sock_error (sk); + +return err ? err : size; }return size; err_out_drop:/* claimed but nothing sent yet - no timer to cancel */ spin_lock_bh (&so->rx_lock); goto err_out_drop_locked; err_event_drop: -/* interrupted waiting on our own transfer - drain its timers */ +/* interrupted or shut down while waiting on our own transfer */ spin_lock_bh (&so->rx_lock); + +/* new transfer already started by concurrent sendmsg()? */ +if (READ_ONCE (so->tx_gen) != my_gen) { +/* don't touch timers and states of the new transfer */ +spin_unlock_bh (&so->rx_lock); +return err; + } +hrtimer_cancel (&so->txfrtimer);hrtimer_cancel (&so->txtimer);hrtimer_cancel (&so->echotimer); err_out_drop_locked:/* release the claim; so->rx_lock still held from above */ - so->cfecho =0 ; - so->tx.state =ISOTP_IDLE ; +WRITE_ONCE (so->cfecho,0 ); + +/* only claim to IDLE if isotp_release() has not taken over */ +if (READ_ONCE (so->tx.state) !=ISOTP_SHUTDOWN ) +WRITE_ONCE (so->tx.state,ISOTP_IDLE );spin_unlock_bh (&so->rx_lock);wake_up_interruptible (&so->wait);return err; }
@@ -1294,22 +1432,26 @@ static int isotp_release(struct socket *sock) net =sock_net (sk);/* best-effort: wait for a running pdu to finish, but don't block on * it forever - give up after the first signal */ -while (so->tx.state !=ISOTP_IDLE && -wait_event_interruptible (so->wait, so->tx.state ==ISOTP_IDLE ) ==0 ) +while (READ_ONCE (so->tx.state) !=ISOTP_IDLE && +wait_event_interruptible (so->wait, +READ_ONCE (so->tx.state) ==ISOTP_IDLE ) ==0 ) ;/* claim the socket under so->rx_lock like sendmsg() does, so its * claim can't race the forced ISOTP_SHUTDOWN below; force it * unconditionally, even when a signal cut the wait above short */ spin_lock_bh (&so->rx_lock); - so->tx.state =ISOTP_SHUTDOWN ; +WRITE_ONCE (so->tx.state,ISOTP_SHUTDOWN );spin_unlock_bh (&so->rx_lock); - so->rx.state =ISOTP_IDLE ; +WRITE_ONCE (so->rx.state,ISOTP_IDLE ); + +/* forced SHUTDOWN may have skipped IDLE (gave up on a signal) */ +wake_up_interruptible (&so->wait);spin_lock (&isotp_notifier_lock);while (isotp_busy_notifier == so) {spin_unlock (&isotp_notifier_lock);schedule_timeout_uninterruptible (1 );
@@ -1420,11 +1562,12 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)* (unbound by NETDEV_UNREGISTER) may still be draining; the FC/echo * and RX watchdog timers bound how long this takes. Checked together * with so->bound in the same lock_sock() section above, so there is * no window in which a concurrent isotp_notify() could be missed. */ -if (so->tx.state !=ISOTP_IDLE || so->rx.state !=ISOTP_IDLE ) { +if (READ_ONCE (so->tx.state) !=ISOTP_IDLE || +READ_ONCE (so->rx.state) !=ISOTP_IDLE ) { err = -EAGAIN ; goto out; }/* ensure different CAN IDs when the rx_id is to be registered */
@@ -1454,11 +1597,11 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)if (isotp_register_rxid (so))can_rx_register (net, dev, rx_id,SINGLE_MASK (rx_id), isotp_rcv, sk,"isotp" , sk);/* no consecutive frame echo skb in flight */ - so->cfecho =0 ; +WRITE_ONCE (so->cfecho,0 );/* register for echo skb's */ can_rx_register (net, dev, tx_id,SINGLE_MASK (tx_id), isotp_rcv_echo, sk,"isotpe" , sk);
@@ -1820,11 +1963,11 @@ static __poll_t isotp_poll(struct file *file, struct socket *sock, poll_table *w__poll_t mask =datagram_poll (file, sock, wait);poll_wait (file, &so->wait, wait);/* Check for false positives due to TX state */ -if ((mask &EPOLLWRNORM ) && (so->tx.state !=ISOTP_IDLE )) +if ((mask &EPOLLWRNORM ) && (READ_ONCE (so->tx.state) !=ISOTP_IDLE )) mask &= ~(EPOLLOUT |EPOLLWRNORM );return mask; }
Signature · 1 line
2.53.0