diff options
Diffstat (limited to 'net/can')
| -rw-r--r-- | net/can/af_can.c | 4 | ||||
| -rw-r--r-- | net/can/af_can.h | 2 | ||||
| -rw-r--r-- | net/can/bcm.c | 653 | ||||
| -rw-r--r-- | net/can/gw.c | 6 | ||||
| -rw-r--r-- | net/can/isotp.c | 567 | ||||
| -rw-r--r-- | net/can/j1939/bus.c | 2 | ||||
| -rw-r--r-- | net/can/j1939/j1939-priv.h | 3 | ||||
| -rw-r--r-- | net/can/j1939/main.c | 8 | ||||
| -rw-r--r-- | net/can/j1939/socket.c | 3 | ||||
| -rw-r--r-- | net/can/j1939/transport.c | 22 | ||||
| -rw-r--r-- | net/can/proc.c | 3 | ||||
| -rw-r--r-- | net/can/raw.c | 108 |
12 files changed, 1029 insertions, 352 deletions
diff --git a/net/can/af_can.c b/net/can/af_can.c index f70e2ba0aadc..7bc86b176b4d 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -469,7 +469,7 @@ int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id, rcv->can_id = can_id; rcv->mask = mask; - rcv->matches = 0; + atomic_long_set(&rcv->matches, 0); rcv->func = func; rcv->data = data; rcv->ident = ident; @@ -573,7 +573,7 @@ EXPORT_SYMBOL(can_rx_unregister); static inline void deliver(struct sk_buff *skb, struct receiver *rcv) { rcv->func(skb, rcv->data); - rcv->matches++; + atomic_long_inc(&rcv->matches); } static int can_rcv_filter(struct can_dev_rcv_lists *dev_rcv_lists, struct sk_buff *skb) diff --git a/net/can/af_can.h b/net/can/af_can.h index 22f3352c77fe..87887014f562 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -52,7 +52,7 @@ struct receiver { struct hlist_node list; canid_t can_id; canid_t mask; - unsigned long matches; + atomic_long_t matches; void (*func)(struct sk_buff *skb, void *data); void *data; char *ident; diff --git a/net/can/bcm.c b/net/can/bcm.c index fd9fa072881e..3d637a1e0ac1 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -58,6 +58,7 @@ #include <linux/can/skb.h> #include <linux/can/bcm.h> #include <linux/slab.h> +#include <linux/workqueue.h> #include <linux/spinlock.h> #include <net/can.h> #include <net/sock.h> @@ -92,6 +93,8 @@ MODULE_ALIAS("can-proto-2"); #define BCM_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex) +static struct workqueue_struct *bcm_wq; + /* * easy access to the first 64 bit of can(fd)_frame payload. cp->data is * 64 bit aligned so the offset has to be multiples of 8 which is ensured @@ -105,14 +108,16 @@ static inline u64 get_u64(const struct canfd_frame *cp, int offset) struct bcm_op { struct list_head list; struct rcu_head rcu; + struct work_struct work; int ifindex; canid_t can_id; u32 flags; - unsigned long frames_abs, frames_filtered; + atomic_long_t frames_abs, frames_filtered; struct bcm_timeval ival1, ival2; struct hrtimer timer, thrtimer; ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg; int rx_ifindex; + int if_detected; /* first received ifindex in ANYDEV rx_op mode */ int cfsiz; u32 count; u32 nframes; @@ -124,7 +129,9 @@ struct bcm_op { struct canfd_frame last_sframe; struct sock *sk; struct net_device *rx_reg_dev; - spinlock_t bcm_tx_lock; /* protect currframe/count in runtime updates */ + netdevice_tracker rx_reg_dev_tracker; + spinlock_t bcm_tx_lock; /* protect tx data and timer updates */ + spinlock_t bcm_rx_update_lock; /* protect filter/timer data updates */ }; struct bcm_sock { @@ -224,10 +231,13 @@ static int bcm_proc_show(struct seq_file *m, void *v) list_for_each_entry_rcu(op, &bo->rx_ops, list) { - unsigned long reduction; + long reduction, frames_filtered, frames_abs; + + frames_filtered = atomic_long_read(&op->frames_filtered); + frames_abs = atomic_long_read(&op->frames_abs); /* print only active entries & prevent division by zero */ - if (!op->frames_abs) + if (!frames_abs) continue; seq_printf(m, "rx_op: %03X %-5s ", op->can_id, @@ -249,15 +259,15 @@ static int bcm_proc_show(struct seq_file *m, void *v) (long long)ktime_to_us(op->kt_ival2)); seq_printf(m, "# recv %ld (%ld) => reduction: ", - op->frames_filtered, op->frames_abs); + frames_filtered, frames_abs); - reduction = 100 - (op->frames_filtered * 100) / op->frames_abs; + reduction = 100 - (frames_filtered * 100) / frames_abs; seq_printf(m, "%s%ld%%\n", (reduction == 100) ? "near " : "", reduction); } - list_for_each_entry(op, &bo->tx_ops, list) { + list_for_each_entry_rcu(op, &bo->tx_ops, list) { seq_printf(m, "tx_op: %03X %s ", op->can_id, bcm_proc_getifname(net, ifname, op->ifindex)); @@ -275,7 +285,8 @@ static int bcm_proc_show(struct seq_file *m, void *v) seq_printf(m, "t2=%lld ", (long long)ktime_to_us(op->kt_ival2)); - seq_printf(m, "# sent %ld\n", op->frames_abs); + seq_printf(m, "# sent %ld\n", + atomic_long_read(&op->frames_abs)); } seq_putc(m, '\n'); @@ -285,26 +296,50 @@ static int bcm_proc_show(struct seq_file *m, void *v) } #endif /* CONFIG_PROC_FS */ +static void bcm_update_rx_stats(struct bcm_op *op) +{ + /* prevent overflow of the reduction% calculation in bcm_proc_show() */ + if (atomic_long_inc_return(&op->frames_abs) > LONG_MAX / 100) { + atomic_long_set(&op->frames_filtered, 0); + atomic_long_set(&op->frames_abs, 0); + } +} + +static void bcm_update_tx_stats(struct bcm_op *op) +{ + /* tx_op has no reduction% calculation - use the full range and + * just keep the displayed counter non-negative on overflow + */ + if (atomic_long_inc_return(&op->frames_abs) == LONG_MAX) + atomic_long_set(&op->frames_abs, 0); +} + /* * bcm_can_tx - send the (next) CAN frame to the appropriate CAN interface * of the given bcm tx op */ -static void bcm_can_tx(struct bcm_op *op) +static void bcm_can_tx(struct bcm_op *op, struct canfd_frame *cf) { struct sk_buff *skb; struct can_skb_ext *csx; struct net_device *dev; - struct canfd_frame *cf; + struct canfd_frame cframe; + bool cyclic = !cf; + unsigned int idx = 0; int err; /* no target device? => exit */ if (!op->ifindex) return; - /* read currframe under lock protection */ - spin_lock_bh(&op->bcm_tx_lock); - cf = op->frames + op->cfsiz * op->currframe; - spin_unlock_bh(&op->bcm_tx_lock); + if (cyclic) { + /* read currframe under lock protection */ + spin_lock_bh(&op->bcm_tx_lock); + idx = op->currframe; + memcpy(&cframe, op->frames + op->cfsiz * idx, op->cfsiz); + cf = &cframe; + spin_unlock_bh(&op->bcm_tx_lock); + } dev = dev_get_by_index(sock_net(op->sk), op->ifindex); if (!dev) { @@ -335,16 +370,22 @@ static void bcm_can_tx(struct bcm_op *op) spin_lock_bh(&op->bcm_tx_lock); if (!err) - op->frames_abs++; + bcm_update_tx_stats(op); - op->currframe++; + /* only advance the cyclic sequence if nothing reset currframe while + * we were sending - a concurrent TX_RESET_MULTI_IDX means this + * frame's bookkeeping belongs to a sequence that no longer exists + */ + if (!cyclic || op->currframe == idx) { + op->currframe++; - /* reached last frame? */ - if (op->currframe >= op->nframes) - op->currframe = 0; + /* reached last frame? */ + if (op->currframe >= op->nframes) + op->currframe = 0; - if (op->count > 0) - op->count--; + if (op->count > 0) + op->count--; + } spin_unlock_bh(&op->bcm_tx_lock); out: @@ -363,7 +404,6 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, struct sockaddr_can *addr; struct sock *sk = op->sk; unsigned int datalen = head->nframes * op->cfsiz; - int err; unsigned int *pflags; enum skb_drop_reason reason; @@ -420,8 +460,8 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, addr->can_family = AF_CAN; addr->can_ifindex = op->rx_ifindex; - err = sock_queue_rcv_skb_reason(sk, skb, &reason); - if (err < 0) { + reason = sock_queue_rcv_skb_reason(sk, skb); + if (reason) { struct bcm_sock *bo = bcm_sk(sk); sk_skb_reason_drop(sk, skb, reason); @@ -434,12 +474,18 @@ static bool bcm_tx_set_expiry(struct bcm_op *op, struct hrtimer *hrt) { ktime_t ival; + spin_lock_bh(&op->bcm_tx_lock); + if (op->kt_ival1 && op->count) ival = op->kt_ival1; - else if (op->kt_ival2) + else if (op->kt_ival2) { ival = op->kt_ival2; - else + } else { + spin_unlock_bh(&op->bcm_tx_lock); return false; + } + + spin_unlock_bh(&op->bcm_tx_lock); hrtimer_set_expires(hrt, ktime_add(ktime_get(), ival)); return true; @@ -456,26 +502,48 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; + bool tx_ival1, tx_ival2; + + /* snapshot kt_ival1/kt_ival2/count under lock to avoid torn + * ktime_t reads racing with concurrent bcm_tx_setup() updates + */ + spin_lock_bh(&op->bcm_tx_lock); + tx_ival1 = op->kt_ival1 && (op->count > 0); + tx_ival2 = !!op->kt_ival2; + spin_unlock_bh(&op->bcm_tx_lock); - if (op->kt_ival1 && (op->count > 0)) { - bcm_can_tx(op); - if (!op->count && (op->flags & TX_COUNTEVT)) { + if (tx_ival1) { + u32 flags, count; + struct bcm_timeval ival1, ival2; + bcm_can_tx(op, NULL); + + /* snapshot variables under lock to avoid torn reads racing + * with concurrent bcm_tx_setup() updates + */ + spin_lock_bh(&op->bcm_tx_lock); + flags = op->flags; + count = op->count; + ival1 = op->ival1; + ival2 = op->ival2; + spin_unlock_bh(&op->bcm_tx_lock); + + if (!count && (flags & TX_COUNTEVT)) { /* create notification to user */ memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = TX_EXPIRED; - msg_head.flags = op->flags; - msg_head.count = op->count; - msg_head.ival1 = op->ival1; - msg_head.ival2 = op->ival2; + msg_head.flags = flags; + msg_head.count = count; + msg_head.ival1 = ival1; + msg_head.ival2 = ival2; msg_head.can_id = op->can_id; msg_head.nframes = 0; bcm_send_to_user(op, &msg_head, NULL, 0); } - } else if (op->kt_ival2) { - bcm_can_tx(op); + } else if (tx_ival2) { + bcm_can_tx(op, NULL); } return bcm_tx_set_expiry(op, &op->timer) ? @@ -489,12 +557,9 @@ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data) { struct bcm_msg_head head; - /* update statistics */ - op->frames_filtered++; - - /* prevent statistics overflow */ - if (op->frames_filtered > ULONG_MAX/100) - op->frames_filtered = op->frames_abs = 0; + /* update statistics (frames_filtered <= frames_abs) */ + if (atomic_long_read(&op->frames_abs)) + atomic_long_inc(&op->frames_filtered); /* this element is not throttled anymore */ data->flags &= ~RX_THR; @@ -619,6 +684,8 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; + spin_lock_bh(&op->bcm_rx_update_lock); + /* if user wants to be informed, when cyclic CAN-Messages come back */ if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) { /* clear received CAN frames to indicate 'nothing received' */ @@ -635,6 +702,8 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) msg_head.can_id = op->can_id; msg_head.nframes = 0; + spin_unlock_bh(&op->bcm_rx_update_lock); + bcm_send_to_user(op, &msg_head, NULL, 0); return HRTIMER_NORESTART; @@ -683,15 +752,26 @@ static int bcm_rx_thr_flush(struct bcm_op *op) static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, thrtimer); + enum hrtimer_restart ret; - if (bcm_rx_thr_flush(op)) { + spin_lock_bh(&op->bcm_rx_update_lock); + + /* kt_ival2 may have been concurrently cleared by bcm_rx_setup() + * before it cancels this timer - never forward with a zero + * interval in that case. + */ + if (bcm_rx_thr_flush(op) && op->kt_ival2) { hrtimer_forward_now(hrtimer, op->kt_ival2); - return HRTIMER_RESTART; + ret = HRTIMER_RESTART; } else { /* rearm throttle handling */ op->kt_lastmsg = 0; - return HRTIMER_NORESTART; + ret = HRTIMER_NORESTART; } + + spin_unlock_bh(&op->bcm_rx_update_lock); + + return ret; } /* @@ -701,8 +781,10 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data) { struct bcm_op *op = (struct bcm_op *)data; const struct canfd_frame *rxframe = (struct canfd_frame *)skb->data; + struct canfd_frame rtrframe; unsigned int i; unsigned char traffic_flags; + bool rtr_frame; if (op->can_id != rxframe->can_id) return; @@ -716,22 +798,59 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data) return; } + /* An ANYDEV op with an active RX timeout and/or throttle timer + * tracks a single source interface: claim the first interface that + * delivers a matching frame and reject frames from any other one, + * before hrtimer_cancel() below can touch op->timer - this avoids + * racing bcm_rx_timeout_handler() across concurrent interfaces. + * RX_RTR_FRAME ops are excluded, as kt_ival1/kt_ival2 may briefly + * hold a stale value from an earlier non-RTR configuration. + */ + if (!op->ifindex) { + spin_lock_bh(&op->bcm_rx_update_lock); + + if (!(op->flags & RX_RTR_FRAME) && + (op->kt_ival1 || op->kt_ival2)) { + /* don't claim to vanishing interface */ + if (!op->if_detected && + READ_ONCE(skb->dev->reg_state) == NETREG_REGISTERED) + op->if_detected = skb->dev->ifindex; + + if (op->if_detected != skb->dev->ifindex) { + spin_unlock_bh(&op->bcm_rx_update_lock); + return; + } + } + + spin_unlock_bh(&op->bcm_rx_update_lock); + } + /* disable timeout */ hrtimer_cancel(&op->timer); - /* save rx timestamp */ - op->rx_stamp = skb->tstamp; - /* save originator for recvfrom() */ - op->rx_ifindex = skb->dev->ifindex; - /* update statistics */ - op->frames_abs++; + /* op->flags/op->frames may be updated concurrently by bcm_rx_setup() */ + spin_lock_bh(&op->bcm_rx_update_lock); + + rtr_frame = op->flags & RX_RTR_FRAME; + if (rtr_frame) { + bcm_update_rx_stats(op); + /* snapshot RTR content under lock */ + memcpy(&rtrframe, op->frames, op->cfsiz); + spin_unlock_bh(&op->bcm_rx_update_lock); - if (op->flags & RX_RTR_FRAME) { /* send reply for RTR-request (placed in op->frames[0]) */ - bcm_can_tx(op); + bcm_can_tx(op, &rtrframe); return; } + /* update statistics in the same critical section as bcm_rx_changed() + * below: frames_filtered must never be checked/incremented against a + * frames_abs snapshot from a concurrent bcm_rx_handler() call on + * another CPU for the same (wildcard) op, or frames_filtered can end + * up larger than frames_abs. + */ + bcm_update_rx_stats(op); + /* compute flags to distinguish between own/local/remote CAN traffic */ traffic_flags = 0; if (skb->sk) { @@ -740,6 +859,13 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data) traffic_flags |= RX_OWN; } + /* save rx timestamp and originator for recvfrom() under lock: an + * ANYDEV op without an active timer can still run concurrently on + * different CPUs, so content and meta data must be bundled here. + */ + op->rx_stamp = skb->tstamp; + op->rx_ifindex = skb->dev->ifindex; + if (op->flags & RX_FILTER_ID) { /* the easiest case */ bcm_rx_update_and_send(op, op->last_frames, rxframe, @@ -775,6 +901,8 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data) rx_starttimer: bcm_rx_starttimer(op); + + spin_unlock_bh(&op->bcm_rx_update_lock); } /* @@ -794,9 +922,12 @@ static struct bcm_op *bcm_find_op(struct list_head *ops, return NULL; } -static void bcm_free_op_rcu(struct rcu_head *rcu_head) +static void bcm_free_op_work(struct work_struct *work) { - struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu); + struct bcm_op *op = container_of(work, struct bcm_op, work); + + hrtimer_cancel(&op->timer); + hrtimer_cancel(&op->thrtimer); if ((op->frames) && (op->frames != &op->sframe)) kfree(op->frames); @@ -804,9 +935,23 @@ static void bcm_free_op_rcu(struct rcu_head *rcu_head) if ((op->last_frames) && (op->last_frames != &op->last_sframe)) kfree(op->last_frames); + /* the last possible access to op->timer/op->thrtimer has now + * happened above via hrtimer_cancel() - op->sk is no longer + * needed by any pending timer callback, so drop our reference + */ + sock_put(op->sk); + kfree(op); } +static void bcm_free_op_rcu(struct rcu_head *rcu_head) +{ + struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu); + + INIT_WORK(&op->work, bcm_free_op_work); + queue_work(bcm_wq, &op->work); +} + static void bcm_remove_op(struct bcm_op *op) { hrtimer_cancel(&op->timer); @@ -823,6 +968,7 @@ static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op) /* mark as removed subscription */ op->rx_reg_dev = NULL; + netdev_put(dev, &op->rx_reg_dev_tracker); } else printk(KERN_ERR "can-bcm: bcm_rx_unreg: registered device " "mismatch %p %p\n", op->rx_reg_dev, dev); @@ -853,17 +999,14 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, * Only remove subscriptions that had not * been removed due to NETDEV_UNREGISTER * in bcm_notifier() + * + * op->rx_reg_dev is a tracked reference taken + * when the subscription was registered, so it + * stays valid here even if a concurrent + * NETDEV_UNREGISTER already unlisted the dev. */ - if (op->rx_reg_dev) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(op->sk), - op->ifindex); - if (dev) { - bcm_rx_unreg(dev, op); - dev_put(dev); - } - } + if (op->rx_reg_dev) + bcm_rx_unreg(op->rx_reg_dev, op); } else can_rx_unregister(sock_net(op->sk), NULL, op->can_id, @@ -931,6 +1074,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; struct canfd_frame *cf; + bool add_op_to_list = false; unsigned int i; int err; @@ -949,6 +1093,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, /* check the given can_id */ op = bcm_find_op(&bo->tx_ops, msg_head, ifindex); if (op) { + void *new_frames; + /* update existing BCM operation */ /* @@ -959,11 +1105,23 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (msg_head->nframes > op->nframes) return -E2BIG; - /* update CAN frames content */ + /* get new CAN frames content into a staging buffer before + * locking: validate and normalize the frames there so that + * bcm_can_tx() / bcm_tx_timeout_handler() never observe a + * partially updated or unvalidated frame in op->frames + */ + new_frames = kmalloc(msg_head->nframes * op->cfsiz, GFP_KERNEL); + if (!new_frames) + return -ENOMEM; + for (i = 0; i < msg_head->nframes; i++) { - cf = op->frames + op->cfsiz * i; + cf = new_frames + op->cfsiz * i; err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz); + if (err < 0) { + kfree(new_frames); + return err; + } if (op->flags & CAN_FD_FRAME) { if (cf->len > 64) @@ -973,36 +1131,38 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, err = -EINVAL; } - if (err < 0) + if (err < 0) { + kfree(new_frames); return err; + } if (msg_head->flags & TX_CP_CAN_ID) { /* copy can_id into frame */ cf->can_id = msg_head->can_id; } } + + spin_lock_bh(&op->bcm_tx_lock); + + /* update CAN frames content */ + memcpy(op->frames, new_frames, msg_head->nframes * op->cfsiz); + op->flags = msg_head->flags; - /* only lock for unlikely count/nframes/currframe changes */ if (op->nframes != msg_head->nframes || - op->flags & TX_RESET_MULTI_IDX || - op->flags & SETTIMER) { - - spin_lock_bh(&op->bcm_tx_lock); + op->flags & TX_RESET_MULTI_IDX) { + /* potentially update changed nframes */ + op->nframes = msg_head->nframes; + /* restart multiple frame transmission */ + op->currframe = 0; + } - if (op->nframes != msg_head->nframes || - op->flags & TX_RESET_MULTI_IDX) { - /* potentially update changed nframes */ - op->nframes = msg_head->nframes; - /* restart multiple frame transmission */ - op->currframe = 0; - } + if (op->flags & SETTIMER) + op->count = msg_head->count; - if (op->flags & SETTIMER) - op->count = msg_head->count; + spin_unlock_bh(&op->bcm_tx_lock); - spin_unlock_bh(&op->bcm_tx_lock); - } + kfree(new_frames); } else { /* insert new BCM operation for the given can_id */ @@ -1061,6 +1221,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, /* bcm_can_tx / bcm_tx_timeout_handler needs this */ op->sk = sk; + sock_hold(sk); op->ifindex = ifindex; /* initialize uninitialized (kzalloc) structure */ @@ -1071,17 +1232,18 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, hrtimer_setup(&op->thrtimer, hrtimer_dummy_timeout, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); - /* add this bcm_op to the list of the tx_ops */ - list_add(&op->list, &bo->tx_ops); + add_op_to_list = true; } /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */ if (op->flags & SETTIMER) { /* set timer values */ + spin_lock_bh(&op->bcm_tx_lock); op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); + spin_unlock_bh(&op->bcm_tx_lock); /* disable an active timer due to zero values? */ if (!op->kt_ival1 && !op->kt_ival2) @@ -1094,8 +1256,12 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->flags |= TX_ANNOUNCE; } + /* add this bcm_op to the list of the tx_ops? */ + if (add_op_to_list) + list_add_rcu(&op->list, &bo->tx_ops); + if (op->flags & TX_ANNOUNCE) - bcm_can_tx(op); + bcm_can_tx(op, NULL); if (op->flags & STARTTIMER) bcm_tx_start_timer(op); @@ -1109,6 +1275,39 @@ free_op: return err; } +static int bcm_rx_setup_rtr_check(struct bcm_msg_head *msg_head, + struct bcm_op *op, void *new_frames) +{ + struct canfd_frame *frame0 = new_frames; + + if (!(msg_head->flags & RX_RTR_FRAME)) + return 0; + + /* this frame is sent out as-is by bcm_can_tx() whenever a matching + * remote request is received, so validate its length the same way + * bcm_tx_setup() validates TX_SETUP frames before installing it + */ + if (msg_head->flags & CAN_FD_FRAME) { + if (frame0->len > 64) + return -EINVAL; + } else { + if (frame0->len > 8) + return -EINVAL; + } + + /* funny feature in RX(!)_SETUP only for RTR-mode: + * copy can_id into frame BUT without RTR-flag to + * prevent a full-load-loopback-test ... ;-] + * normalize this on the staged buffer, before it is + * ever installed into op->frames. + */ + if ((msg_head->flags & TX_CP_CAN_ID) || + frame0->can_id == op->can_id) + frame0->can_id = op->can_id & ~CAN_RTR_FLAG; + + return 0; +} + /* * bcm_rx_setup - create or update a bcm rx op (for bcm_sendmsg) */ @@ -1118,6 +1317,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; int do_rx_register; + int new_op = 0; int err = 0; if ((msg_head->flags & RX_FILTER_ID) || (!(msg_head->nframes))) { @@ -1143,6 +1343,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, /* check the given can_id */ op = bcm_find_op(&bo->rx_ops, msg_head, ifindex); if (op) { + void *new_frames = NULL; + /* update existing BCM operation */ /* @@ -1154,21 +1356,62 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, return -E2BIG; if (msg_head->nframes) { - /* update CAN frames content */ - err = memcpy_from_msg(op->frames, msg, + /* get new CAN frames content before locking */ + new_frames = kmalloc(msg_head->nframes * op->cfsiz, + GFP_KERNEL); + if (!new_frames) + return -ENOMEM; + + err = memcpy_from_msg(new_frames, msg, msg_head->nframes * op->cfsiz); - if (err < 0) + if (err < 0) { + kfree(new_frames); return err; + } - /* clear last_frames to indicate 'nothing received' */ - memset(op->last_frames, 0, msg_head->nframes * op->cfsiz); + err = bcm_rx_setup_rtr_check(msg_head, op, new_frames); + if (err < 0) { + kfree(new_frames); + return err; + } } + spin_lock_bh(&op->bcm_rx_update_lock); op->nframes = msg_head->nframes; op->flags = msg_head->flags; - /* Only an update -> do not call can_rx_register() */ - do_rx_register = 0; + if (msg_head->nframes) { + /* update CAN frames content */ + memcpy(op->frames, new_frames, + msg_head->nframes * op->cfsiz); + + /* clear last_frames to indicate 'nothing received' */ + memset(op->last_frames, 0, + msg_head->nframes * op->cfsiz); + } + + if (msg_head->flags & SETTIMER) { + op->ival1 = msg_head->ival1; + op->ival2 = msg_head->ival2; + op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); + op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); + op->kt_lastmsg = 0; + op->if_detected = 0; /* reclaim ifindex in ANYDEV mode */ + } + spin_unlock_bh(&op->bcm_rx_update_lock); + + /* free temporary frames / kfree(NULL) is safe */ + kfree(new_frames); + + /* Don't register a new CAN filter for the rx_op update unless + * a concurrent NETDEV_UNREGISTER notifier already tore down + * the previous registration. In this case the receiver needs + * to be re-registered here so that this update doesn't + * silently stop delivering frames for the given ifindex. + * Ops with ifindex = 0 (all CAN interfaces) never carry a + * tracked rx_reg_dev and stay registered as-is. + */ + do_rx_register = (ifindex && !op->rx_reg_dev) ? 1 : 0; } else { /* insert new BCM operation for the given can_id */ @@ -1177,6 +1420,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, return -ENOMEM; spin_lock_init(&op->bcm_tx_lock); + spin_lock_init(&op->bcm_rx_update_lock); op->can_id = msg_head->can_id; op->nframes = msg_head->nframes; op->cfsiz = CFSIZ(msg_head->flags); @@ -1210,18 +1454,17 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (msg_head->nframes) { err = memcpy_from_msg(op->frames, msg, msg_head->nframes * op->cfsiz); - if (err < 0) { - if (op->frames != &op->sframe) - kfree(op->frames); - if (op->last_frames != &op->last_sframe) - kfree(op->last_frames); - kfree(op); - return err; - } + if (err < 0) + goto free_op; + + err = bcm_rx_setup_rtr_check(msg_head, op, op->frames); + if (err < 0) + goto free_op; } /* bcm_can_tx / bcm_tx_timeout_handler needs this */ op->sk = sk; + sock_hold(sk); op->ifindex = ifindex; /* ifindex for timeout events w/o previous frame reception */ @@ -1233,40 +1476,31 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, hrtimer_setup(&op->thrtimer, bcm_rx_thr_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); - /* add this bcm_op to the list of the rx_ops */ - list_add(&op->list, &bo->rx_ops); - /* call can_rx_register() */ do_rx_register = 1; + new_op = 1; } /* if ((op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex))) */ /* check flags */ if (op->flags & RX_RTR_FRAME) { - struct canfd_frame *frame0 = op->frames; - /* no timers in RTR-mode */ hrtimer_cancel(&op->thrtimer); hrtimer_cancel(&op->timer); - - /* - * funny feature in RX(!)_SETUP only for RTR-mode: - * copy can_id into frame BUT without RTR-flag to - * prevent a full-load-loopback-test ... ;-] - */ - if ((op->flags & TX_CP_CAN_ID) || - (frame0->can_id == op->can_id)) - frame0->can_id = op->can_id & ~CAN_RTR_FLAG; - } else { if (op->flags & SETTIMER) { - /* set timer value */ - op->ival1 = msg_head->ival1; - op->ival2 = msg_head->ival2; - op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); - op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); + /* set timers (locked) for newly created op */ + if (new_op) { + spin_lock_bh(&op->bcm_rx_update_lock); + op->ival1 = msg_head->ival1; + op->ival2 = msg_head->ival2; + op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); + op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); + op->kt_lastmsg = 0; + spin_unlock_bh(&op->bcm_rx_update_lock); + } /* disable an active timer due to zero value? */ if (!op->kt_ival1) @@ -1276,9 +1510,11 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, * In any case cancel the throttle timer, flush * potentially blocked msgs and reset throttle handling */ - op->kt_lastmsg = 0; hrtimer_cancel(&op->thrtimer); + + spin_lock_bh(&op->bcm_rx_update_lock); bcm_rx_thr_flush(op); + spin_unlock_bh(&op->bcm_rx_update_lock); } if ((op->flags & STARTTIMER) && op->kt_ival1) @@ -1286,7 +1522,10 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, HRTIMER_MODE_REL_SOFT); } - /* now we can register for can_ids, if we added a new bcm_op */ + /* now we can register for can_ids, if we added a new bcm_op + * or need to re-register after a NETDEV_UNREGISTER tore down + * the previous registration of an existing op + */ if (do_rx_register) { if (ifindex) { struct net_device *dev; @@ -1299,23 +1538,62 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, bcm_rx_handler, op, "bcm", sk); - op->rx_reg_dev = dev; + /* keep a tracked reference so that a later + * unregister can safely reach the device even + * if a concurrent NETDEV_UNREGISTER has + * already unlisted it by ifindex + */ + if (!err) { + op->rx_reg_dev = dev; + netdev_hold(dev, + &op->rx_reg_dev_tracker, + GFP_KERNEL); + } dev_put(dev); + } else { + /* the requested device is gone - do not + * silently succeed without registering + */ + err = -ENODEV; } - } else + } else { err = can_rx_register(sock_net(sk), NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op, "bcm", sk); + } + if (err) { - /* this bcm rx op is broken -> remove it */ - list_del_rcu(&op->list); - bcm_remove_op(op); + /* newly created bcm rx op is broken -> remove it */ + if (new_op) { + bcm_remove_op(op); + return err; + } + + /* an existing op just stays unregistered. + * Cancel op->timer and (defensively) op->thrtimer. + * Other settings can't be reached until the next + * successful RX_SETUP. + */ + hrtimer_cancel(&op->timer); + hrtimer_cancel(&op->thrtimer); return err; } + + /* add a new bcm_op to the list of the rx_ops */ + if (new_op) + list_add_rcu(&op->list, &bo->rx_ops); } return msg_head->nframes * op->cfsiz + MHSIZ; + +free_op: + if (op->frames != &op->sframe) + kfree(op->frames); + if (op->last_frames != &op->last_sframe) + kfree(op->last_frames); + kfree(op); + return err; } /* @@ -1374,12 +1652,13 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct bcm_sock *bo = bcm_sk(sk); - int ifindex = bo->ifindex; /* default ifindex for this bcm_op */ + int ifindex; struct bcm_msg_head msg_head; int cfsiz; int ret; /* read bytes or error codes as return value */ - if (!bo->bound) + /* Lockless fast-path check for bound socket */ + if (!READ_ONCE(bo->bound)) return -ENOTCONN; /* check for valid message length from userspace */ @@ -1395,17 +1674,38 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if ((size - MHSIZ) % cfsiz) return -EINVAL; + lock_sock(sk); + + /* Re-validate under the socket lock: a concurrent bcm_notify() + * may have unbound this socket (device removal) after the + * lockless fast-path check above. bo->ifindex is only ever + * mutated under lock_sock(), so reading it here - instead of + * before taking the lock - guarantees it can't be observed + * torn against bo->bound. + */ + if (!bo->bound) { + ret = -ENOTCONN; + goto out_release; + } + + /* default ifindex for this bcm_op */ + ifindex = bo->ifindex; + /* check for alternative ifindex for this bcm_op */ if (!ifindex && msg->msg_name) { /* no bound device as default => check msg_name */ DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); - if (msg->msg_namelen < BCM_MIN_NAMELEN) - return -EINVAL; + if (msg->msg_namelen < BCM_MIN_NAMELEN) { + ret = -EINVAL; + goto out_release; + } - if (addr->can_family != AF_CAN) - return -EINVAL; + if (addr->can_family != AF_CAN) { + ret = -EINVAL; + goto out_release; + } /* ifindex from sendto() */ ifindex = addr->can_ifindex; @@ -1414,20 +1714,21 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) struct net_device *dev; dev = dev_get_by_index(sock_net(sk), ifindex); - if (!dev) - return -ENODEV; + if (!dev) { + ret = -ENODEV; + goto out_release; + } if (dev->type != ARPHRD_CAN) { dev_put(dev); - return -ENODEV; + ret = -ENODEV; + goto out_release; } dev_put(dev); } } - lock_sock(sk); - switch (msg_head.opcode) { case TX_SETUP: @@ -1477,6 +1778,7 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) break; } +out_release: release_sock(sk); return ret; @@ -1500,11 +1802,30 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, case NETDEV_UNREGISTER: lock_sock(sk); - /* remove device specific receive entries */ - list_for_each_entry(op, &bo->rx_ops, list) + /* rx_ops: remove device specific receive entries */ + list_for_each_entry(op, &bo->rx_ops, list) { if (op->rx_reg_dev == dev) bcm_rx_unreg(dev, op); + /* release an ANYDEV op's claim (see bcm_rx_handler()) + * on this now confirmed-gone interface. + */ + if (!op->ifindex) { + spin_lock_bh(&op->bcm_rx_update_lock); + if (op->if_detected == dev->ifindex) + op->if_detected = 0; + spin_unlock_bh(&op->bcm_rx_update_lock); + } + } + + /* tx_ops: stop device specific cyclic transmissions on the + * vanishing ifindex. Cancelling the timer is enough to stop + * cyclic bcm_can_tx() calls as there is no re-arming. + */ + list_for_each_entry(op, &bo->tx_ops, list) + if (op->ifindex == dev->ifindex) + hrtimer_cancel(&op->timer); + /* remove device reference, if this is our bound device */ if (bo->bound && bo->ifindex == dev->ifindex) { #if IS_ENABLED(CONFIG_PROC_FS) @@ -1513,7 +1834,12 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, bo->bcm_proc_read = NULL; } #endif - bo->bound = 0; + /* Paired with the lockless fast-path check in + * bcm_sendmsg(); bo->ifindex itself is only ever + * accessed under lock_sock() so it needs no + * annotation. + */ + WRITE_ONCE(bo->bound, 0); bo->ifindex = 0; notify_enodev = 1; } @@ -1617,8 +1943,10 @@ static int bcm_release(struct socket *sock) remove_proc_entry(bo->procname, net->can.bcmproc_dir); #endif /* CONFIG_PROC_FS */ - list_for_each_entry_safe(op, next, &bo->tx_ops, list) + list_for_each_entry_safe(op, next, &bo->tx_ops, list) { + list_del_rcu(&op->list); bcm_remove_op(op); + } list_for_each_entry_safe(op, next, &bo->rx_ops, list) { /* @@ -1630,16 +1958,14 @@ static int bcm_release(struct socket *sock) * Only remove subscriptions that had not * been removed due to NETDEV_UNREGISTER * in bcm_notifier() + * + * op->rx_reg_dev is a tracked reference taken + * when the subscription was registered, so it + * stays valid here even if a concurrent + * NETDEV_UNREGISTER already unlisted the device. */ - if (op->rx_reg_dev) { - struct net_device *dev; - - dev = dev_get_by_index(net, op->ifindex); - if (dev) { - bcm_rx_unreg(dev, op); - dev_put(dev); - } - } + if (op->rx_reg_dev) + bcm_rx_unreg(op->rx_reg_dev, op); } else can_rx_unregister(net, NULL, op->can_id, REGMASK(op->can_id), @@ -1649,12 +1975,14 @@ static int bcm_release(struct socket *sock) synchronize_rcu(); - list_for_each_entry_safe(op, next, &bo->rx_ops, list) + list_for_each_entry_safe(op, next, &bo->rx_ops, list) { + list_del_rcu(&op->list); bcm_remove_op(op); + } /* remove device reference */ if (bo->bound) { - bo->bound = 0; + WRITE_ONCE(bo->bound, 0); bo->ifindex = 0; } @@ -1713,7 +2041,7 @@ static int bcm_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int #if IS_ENABLED(CONFIG_PROC_FS) if (net->can.bcmproc_dir) { /* unique socket address as filename */ - sprintf(bo->procname, "%lu", sock_i_ino(sk)); + sprintf(bo->procname, "%llu", sock_i_ino(sk)); bo->bcm_proc_read = proc_create_net_single(bo->procname, 0644, net->can.bcmproc_dir, bcm_proc_show, sk); @@ -1724,7 +2052,10 @@ static int bcm_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int } #endif /* CONFIG_PROC_FS */ - bo->bound = 1; + /* bo->ifindex above is fully assigned before this point; pairs + * with the lockless fast-path check in bcm_sendmsg() + */ + WRITE_ONCE(bo->bound, 1); fail: release_sock(sk); @@ -1840,11 +2171,15 @@ static int __init bcm_module_init(void) { int err; + bcm_wq = alloc_workqueue("can-bcm-wq", WQ_UNBOUND, 0); + if (!bcm_wq) + return -ENOMEM; + pr_info("can: broadcast manager protocol\n"); err = register_pernet_subsys(&canbcm_pernet_ops); if (err) - return err; + goto register_pernet_failed; err = register_netdevice_notifier(&canbcm_notifier); if (err) @@ -1862,6 +2197,8 @@ register_proto_failed: unregister_netdevice_notifier(&canbcm_notifier); register_notifier_failed: unregister_pernet_subsys(&canbcm_pernet_ops); +register_pernet_failed: + destroy_workqueue(bcm_wq); return err; } @@ -1870,6 +2207,8 @@ static void __exit bcm_module_exit(void) can_proto_unregister(&bcm_can_proto); unregister_netdevice_notifier(&canbcm_notifier); unregister_pernet_subsys(&canbcm_pernet_ops); + rcu_barrier(); + destroy_workqueue(bcm_wq); } module_init(bcm_module_init); diff --git a/net/can/gw.c b/net/can/gw.c index 8ee4d67a07d3..0ec99f68aa45 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -375,10 +375,10 @@ static void cgw_csum_crc8_rel(struct canfd_frame *cf, return; if (from <= to) { - for (i = crc8->from_idx; i <= crc8->to_idx; i++) + for (i = from; i <= to; i++) crc = crc8->crctab[crc ^ cf->data[i]]; } else { - for (i = crc8->from_idx; i >= crc8->to_idx; i--) + for (i = from; i >= to; i--) crc = crc8->crctab[crc ^ cf->data[i]]; } @@ -397,7 +397,7 @@ static void cgw_csum_crc8_rel(struct canfd_frame *cf, break; } - cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; + cf->data[res] = crc ^ crc8->final_xor_val; } static void cgw_csum_crc8_pos(struct canfd_frame *cf, diff --git a/net/can/isotp.c b/net/can/isotp.c index da3b72e7afcc..155530aedce2 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -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, @@ -152,11 +161,13 @@ struct isotp_sock { struct sock sk; int bound; int ifindex; + struct net_device *dev; + netdevice_tracker dev_tracker; canid_t txid; canid_t rxid; ktime_t tx_gap; ktime_t lastrxcf_tstamp; - struct hrtimer rxtimer, txtimer, txfrtimer; + struct hrtimer rxtimer, txtimer, txfrtimer, echotimer; struct can_isotp_options opt; struct can_isotp_fc_options rxfc, txfc; struct can_isotp_ll_options ll; @@ -164,6 +175,8 @@ struct isotp_sock { u32 force_tx_stmin; u32 force_rx_stmin; u32 cfecho; /* consecutive frame echo tag */ + 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; @@ -174,6 +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; @@ -196,7 +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' */ @@ -205,7 +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; @@ -291,7 +363,8 @@ static void isotp_rcv_skb(struct sk_buff *skb, struct sock *sk) addr->can_family = AF_CAN; addr->can_ifindex = skb->dev->ifindex; - if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) + reason = sock_queue_rcv_skb_reason(sk, skb); + if (reason) sk_skb_reason_drop(sk, skb, reason); } @@ -368,13 +441,21 @@ 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 => recheck + */ + 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))) { @@ -383,13 +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]; @@ -413,15 +496,15 @@ 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->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), + hrtimer_start(&so->echotimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); isotp_send_cframe(so); break; @@ -434,14 +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; @@ -454,7 +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; @@ -488,7 +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); @@ -542,7 +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) @@ -560,7 +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 */ @@ -574,6 +662,12 @@ 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 => recheck + */ + 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; @@ -592,7 +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++; @@ -606,7 +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)) { @@ -677,8 +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; } @@ -773,6 +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) @@ -793,6 +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); @@ -809,12 +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); @@ -866,81 +969,133 @@ 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 || so->cfecho != *(u32 *)cf->data) + if (skb->sk != sk) return; + /* unlike isotp_rcv_fc()/isotp_rcv_cf(), not already under so->rx_lock + * (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 (READ_ONCE(so->cfecho) != skb->hash) + goto out_unlock; + /* cancel local echo timeout */ - hrtimer_cancel(&so->txtimer); + 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 (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); - return; + 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); - return; + goto out_unlock; } /* no gap between data frames needed => use burst mode */ if (!so->tx_gap) { /* enable echo timeout handling */ - hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), + hrtimer_start(&so->echotimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); isotp_send_cframe(so); - return; + goto out_unlock; } /* start timer to send next consecutive frame with correct delay */ hrtimer_start(&so->txfrtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT); + +out_unlock: + spin_unlock(&so->rx_lock); } -static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) +/* 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 isotp_sock *so = container_of(hrtimer, struct isotp_sock, - txtimer); 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); /* don't handle timeouts in IDLE or SHUTDOWN state */ - if (so->tx.state == ISOTP_IDLE || so->tx.state == ISOTP_SHUTDOWN) + 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' */ + + /* a stale read of this slot by a waiter still falls back to ECOMM */ + isotp_set_tx_result(so, gen, ECOMM); - /* report 'communication error on send' */ sk->sk_err = ECOMM; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); - /* reset tx state */ - so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return HRTIMER_NORESTART; } +/* so->txtimer: fires when a Flow Control frame does not arrive in time */ +static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) +{ + struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, + txtimer); + + return isotp_tx_timeout(so); +} + +/* so->echotimer: fires when a sent CF/SF's local echo does not arrive */ +static enum hrtimer_restart isotp_echo_timer_handler(struct hrtimer *hrtimer) +{ + struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, + echotimer); + + return isotp_tx_timeout(so); +} + static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, txfrtimer); /* start echo timeout handling and cover below protocol error */ - hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), + 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; @@ -957,24 +1112,61 @@ 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; - while (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE) { + /* 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 + */ + for (;;) { + spin_lock_bh(&so->rx_lock); + if (READ_ONCE(so->tx.state) == ISOTP_IDLE) + break; + spin_unlock_bh(&so->rx_lock); + /* 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); + err = wait_event_interruptible(so->wait, + READ_ONCE(so->tx.state) == ISOTP_IDLE || + READ_ONCE(so->tx.state) == ISOTP_SHUTDOWN); if (err) - goto err_event_drop; + return err; + } + + /* txfrtimer's callback re-arms echotimer lock-free: drain it first */ + hrtimer_cancel(&so->txfrtimer); + hrtimer_cancel(&so->txtimer); + hrtimer_cancel(&so->echotimer); + + /* 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 => recheck + */ + if (!so->bound) { + err = -EADDRNOTAVAIL; + goto err_out_drop; } /* PDU size > default => try max_pdu_size */ @@ -1029,6 +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; @@ -1036,8 +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) { @@ -1065,7 +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 */ @@ -1082,21 +1278,36 @@ 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 */ - so->tx.state = ISOTP_WAIT_FIRST_FC; + 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); } } - hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0), + spin_lock_bh(&so->rx_lock); + 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 */ + 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 */ cf->flags = so->ll.tx_flags; @@ -1109,36 +1320,80 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(err)); - /* no transmission -> no timeout monitoring */ - hrtimer_cancel(&so->txtimer); + spin_lock_bh(&so->rx_lock); - /* reset consecutive frame echo tag */ - so->cfecho = 0; + /* 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; + } - goto err_out_drop; + /* 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: - /* got signal: force tx state machine to be idle */ - so->tx.state = ISOTP_IDLE; + /* 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); -err_out_drop: - /* drop this PDU and unlock a potential wait queue */ - so->tx.state = ISOTP_IDLE; + hrtimer_cancel(&so->echotimer); +err_out_drop_locked: + /* release the claim; so->rx_lock still held from above */ + 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; @@ -1200,14 +1455,25 @@ static int isotp_release(struct socket *sock) so = isotp_sk(sk); net = sock_net(sk); - /* wait for complete transmission of current pdu */ - while (wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0 && - cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SHUTDOWN) != ISOTP_IDLE) + /* best-effort: wait for a running pdu to finish, but don't block on + * it forever - give up after the first signal + */ + while (READ_ONCE(so->tx.state) != ISOTP_IDLE && + wait_event_interruptible(so->wait, + READ_ONCE(so->tx.state) == ISOTP_IDLE) == 0) ; - /* force state machines to be idle also when a signal occurred */ - so->tx.state = ISOTP_SHUTDOWN; - so->rx.state = ISOTP_IDLE; + /* 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); + WRITE_ONCE(so->tx.state, ISOTP_SHUTDOWN); + spin_unlock_bh(&so->rx_lock); + 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) { @@ -1218,41 +1484,42 @@ static int isotp_release(struct socket *sock) list_del(&so->notifier); spin_unlock(&isotp_notifier_lock); + rtnl_lock(); lock_sock(sk); - /* remove current filters & unregister */ - if (so->bound) { - if (so->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(net, so->ifindex); - if (dev) { - if (isotp_register_rxid(so)) - can_rx_unregister(net, dev, so->rxid, - SINGLE_MASK(so->rxid), - isotp_rcv, sk); - - can_rx_unregister(net, dev, so->txid, - SINGLE_MASK(so->txid), - isotp_rcv_echo, sk); - dev_put(dev); - synchronize_rcu(); - } - } + /* remove current filters & unregister + * tracked reference so->dev is taken at bind() time with rtnl_lock + */ + if (so->bound && so->dev) { + if (isotp_register_rxid(so)) + can_rx_unregister(net, so->dev, so->rxid, + SINGLE_MASK(so->rxid), + isotp_rcv, sk); + + can_rx_unregister(net, so->dev, so->txid, + SINGLE_MASK(so->txid), + isotp_rcv_echo, sk); + netdev_put(so->dev, &so->dev_tracker); } - hrtimer_cancel(&so->txfrtimer); - hrtimer_cancel(&so->txtimer); - hrtimer_cancel(&so->rxtimer); - so->ifindex = 0; so->bound = 0; + so->dev = NULL; - if (so->rx.buf != so->rx.sbuf) - kfree(so->rx.buf); + rtnl_unlock(); - if (so->tx.buf != so->tx.sbuf) - kfree(so->tx.buf); + /* Always wait for a grace period before touching the timers below. + * A concurrent NETDEV_UNREGISTER may have already unregistered our + * filters and cleared so->bound in isotp_notify() without waiting + * for in-flight isotp_rcv() callers to finish, so this call must not + * be skipped just because so->bound is already 0 here. + */ + synchronize_rcu(); + + hrtimer_cancel(&so->txfrtimer); + hrtimer_cancel(&so->txtimer); + hrtimer_cancel(&so->echotimer); + hrtimer_cancel(&so->rxtimer); sock_orphan(sk); sock->sk = NULL; @@ -1308,6 +1575,7 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l if (!addr->can_ifindex) return -ENODEV; + rtnl_lock(); lock_sock(sk); if (so->bound) { @@ -1315,6 +1583,18 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l goto out; } + /* A transmission or reception that outlived a previous binding + * (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 (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 */ if (isotp_register_rxid(so) && rx_id == tx_id) { err = -EADDRNOTAVAIL; @@ -1327,14 +1607,12 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l goto out; } if (dev->type != ARPHRD_CAN) { - dev_put(dev); err = -ENODEV; - goto out; + goto out_put_dev; } if (READ_ONCE(dev->mtu) < so->ll.mtu) { - dev_put(dev); err = -EINVAL; - goto out; + goto out_put_dev; } if (!(dev->flags & IFF_UP)) notify_enetdown = 1; @@ -1346,22 +1624,31 @@ 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), isotp_rcv_echo, sk, "isotpe", sk); - dev_put(dev); - /* switch to new settings */ so->ifindex = ifindex; so->rxid = rx_id; so->txid = tx_id; so->bound = 1; + /* bind() ok -> hold a reference for so->dev so that isotp_release() + * can safely reach the device later, even if a concurrent + * NETDEV_UNREGISTER has already unlisted it by ifindex. + */ + so->dev = dev; + netdev_hold(so->dev, &so->dev_tracker, GFP_KERNEL); + +out_put_dev: + /* remove potential reference from dev_get_by_index() */ + dev_put(dev); out: release_sock(sk); + rtnl_unlock(); if (notify_enetdown) { sk->sk_err = ENETDOWN; @@ -1564,7 +1851,7 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg, if (!net_eq(dev_net(dev), sock_net(sk))) return; - if (so->ifindex != dev->ifindex) + if (so->dev != dev) return; switch (msg) { @@ -1580,10 +1867,12 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg, can_rx_unregister(dev_net(dev), dev, so->txid, SINGLE_MASK(so->txid), isotp_rcv_echo, sk); + netdev_put(so->dev, &so->dev_tracker); } so->ifindex = 0; so->bound = 0; + so->dev = NULL; release_sock(sk); sk->sk_err = ENODEV; @@ -1622,12 +1911,28 @@ static int isotp_notifier(struct notifier_block *nb, unsigned long msg, return NOTIFY_DONE; } +static void isotp_sock_destruct(struct sock *sk) +{ + struct isotp_sock *so = isotp_sk(sk); + + /* do the standard CAN sock destruct work */ + can_sock_destruct(sk); + + /* free potential extended PDU buffers */ + if (so->rx.buf != so->rx.sbuf) + kfree(so->rx.buf); + + if (so->tx.buf != so->tx.sbuf) + kfree(so->tx.buf); +} + static int isotp_init(struct sock *sk) { struct isotp_sock *so = isotp_sk(sk); so->ifindex = 0; so->bound = 0; + so->dev = NULL; so->opt.flags = CAN_ISOTP_DEFAULT_FLAGS; so->opt.ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS; @@ -1654,10 +1959,14 @@ static int isotp_init(struct sock *sk) so->rx.buflen = ARRAY_SIZE(so->rx.sbuf); so->tx.buflen = ARRAY_SIZE(so->tx.sbuf); - hrtimer_setup(&so->rxtimer, isotp_rx_timer_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); - hrtimer_setup(&so->txtimer, isotp_tx_timer_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); - hrtimer_setup(&so->txfrtimer, isotp_txfr_timer_handler, CLOCK_MONOTONIC, - HRTIMER_MODE_REL_SOFT); + hrtimer_setup(&so->rxtimer, isotp_rx_timer_handler, + CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + hrtimer_setup(&so->txtimer, isotp_tx_timer_handler, + CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + hrtimer_setup(&so->echotimer, isotp_echo_timer_handler, + CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + hrtimer_setup(&so->txfrtimer, isotp_txfr_timer_handler, + CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); init_waitqueue_head(&so->wait); spin_lock_init(&so->rx_lock); @@ -1666,6 +1975,9 @@ static int isotp_init(struct sock *sk) list_add_tail(&so->notifier, &isotp_notifier_list); spin_unlock(&isotp_notifier_lock); + /* re-assign default can_sock_destruct() reference */ + sk->sk_destruct = isotp_sock_destruct; + return 0; } @@ -1678,7 +1990,7 @@ static __poll_t isotp_poll(struct file *file, struct socket *sock, poll_table *w 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; @@ -1738,13 +2050,18 @@ static __init int isotp_module_init(void) pr_info("can: isotp protocol (max_pdu_size %d)\n", max_pdu_size); + err = register_netdevice_notifier(&canisotp_notifier); + if (err) + return err; + err = can_proto_register(&isotp_can_proto); - if (err < 0) + if (err < 0) { pr_err("can: registration of isotp protocol failed %pe\n", ERR_PTR(err)); - else - register_netdevice_notifier(&canisotp_notifier); + unregister_netdevice_notifier(&canisotp_notifier); + return err; + } - return err; + return 0; } static __exit void isotp_module_exit(void) diff --git a/net/can/j1939/bus.c b/net/can/j1939/bus.c index dc374286eeb6..cdc3c0a71937 100644 --- a/net/can/j1939/bus.c +++ b/net/can/j1939/bus.c @@ -20,6 +20,7 @@ static void __j1939_ecu_release(struct kref *kref) struct j1939_priv *priv = ecu->priv; list_del(&ecu->list); + netdev_put(priv->ndev, &ecu->priv_dev_tracker); kfree(ecu); j1939_priv_put(priv); } @@ -155,6 +156,7 @@ struct j1939_ecu *j1939_ecu_create_locked(struct j1939_priv *priv, name_t name) if (!ecu) return ERR_PTR(-ENOMEM); kref_init(&ecu->kref); + netdev_hold(priv->ndev, &ecu->priv_dev_tracker, gfp_any()); ecu->addr = J1939_IDLE_ADDR; ecu->name = name; diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index 81f58924b4ac..cf26352d1d8c 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -38,6 +38,7 @@ struct j1939_ecu { struct hrtimer ac_timer; struct kref kref; struct j1939_priv *priv; + netdevice_tracker priv_dev_tracker; /* count users, to help transport protocol decide for interaction */ int nusers; @@ -60,6 +61,7 @@ struct j1939_priv { rwlock_t lock; struct net_device *ndev; + netdevice_tracker dev_tracker; /* list of 256 ecu ptrs, that cache the claimed addresses. * also protected by the above lock @@ -230,6 +232,7 @@ enum j1939_session_state { struct j1939_session { struct j1939_priv *priv; + netdevice_tracker priv_dev_tracker; struct list_head active_session_list_entry; struct list_head sk_session_queue_entry; struct kref kref; diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index 9937c04241bc..5e5e6c228f22 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -137,7 +137,7 @@ static struct j1939_priv *j1939_priv_create(struct net_device *ndev) priv->ndev = ndev; kref_init(&priv->kref); kref_init(&priv->rx_kref); - dev_hold(ndev); + netdev_hold(ndev, &priv->dev_tracker, GFP_KERNEL); netdev_dbg(priv->ndev, "%s : 0x%p\n", __func__, priv); @@ -163,7 +163,7 @@ static void __j1939_priv_release(struct kref *kref) WARN_ON_ONCE(!list_empty(&priv->ecus)); WARN_ON_ONCE(!list_empty(&priv->j1939_socks)); - dev_put(ndev); + netdev_put(ndev, &priv->dev_tracker); kfree(priv); } @@ -281,7 +281,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) */ kref_get(&priv_new->rx_kref); mutex_unlock(&j1939_netdev_lock); - dev_put(ndev); + netdev_put(ndev, &priv->dev_tracker); kfree(priv); return priv_new; } @@ -298,7 +298,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) j1939_priv_set(ndev, NULL); mutex_unlock(&j1939_netdev_lock); - dev_put(ndev); + netdev_put(ndev, &priv->dev_tracker); kfree(priv); return ERR_PTR(ret); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 0502b030d238..50a598ef5fd4 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -333,7 +333,8 @@ static void j1939_sk_recv_one(struct j1939_sock *jsk, struct sk_buff *oskb) if (skb->sk) skcb->msg_flags |= MSG_DONTROUTE; - if (sock_queue_rcv_skb_reason(&jsk->sk, skb, &reason) < 0) + reason = sock_queue_rcv_skb_reason(&jsk->sk, skb); + if (reason) sk_skb_reason_drop(&jsk->sk, skb, reason); } diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index df93d57907da..8fcfd13e5e6f 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -283,6 +283,7 @@ static void j1939_session_destroy(struct j1939_session *session) kfree_skb(skb); } __j1939_session_drop(session); + netdev_put(session->priv->ndev, &session->priv_dev_tracker); j1939_priv_put(session->priv); kfree(session); } @@ -351,6 +352,18 @@ static void j1939_session_skb_drop_old(struct j1939_session *session) } } +static bool j1939_address_is_local(struct j1939_priv *priv, u8 addr) +{ + bool local = false; + + read_lock_bh(&priv->lock); + if (j1939_address_is_unicast(addr) && priv->ents[addr].nusers) + local = true; + read_unlock_bh(&priv->lock); + + return local; +} + void j1939_session_skb_queue(struct j1939_session *session, struct sk_buff *skb) { @@ -359,8 +372,7 @@ void j1939_session_skb_queue(struct j1939_session *session, j1939_ac_fixup(priv, skb); - if (j1939_address_is_unicast(skcb->addr.da) && - priv->ents[skcb->addr.da].nusers) + if (j1939_address_is_local(priv, skcb->addr.da)) skcb->flags |= J1939_ECU_LOCAL_DST; skcb->flags |= J1939_ECU_LOCAL_SRC; @@ -1515,6 +1527,7 @@ static struct j1939_session *j1939_session_new(struct j1939_priv *priv, INIT_LIST_HEAD(&session->active_session_list_entry); INIT_LIST_HEAD(&session->sk_session_queue_entry); kref_init(&session->kref); + netdev_hold(priv->ndev, &session->priv_dev_tracker, gfp_any()); j1939_priv_get(priv); session->priv = priv; @@ -1568,7 +1581,7 @@ j1939_session *j1939_session_fresh_new(struct j1939_priv *priv, } /* alloc data area */ - skb_put(skb, size); + skb_put_zero(skb, size); /* skb is recounted in j1939_session_new() */ return session; } @@ -2038,8 +2051,7 @@ struct j1939_session *j1939_tp_send(struct j1939_priv *priv, return ERR_PTR(ret); /* fix DST flags, it may be used there soon */ - if (j1939_address_is_unicast(skcb->addr.da) && - priv->ents[skcb->addr.da].nusers) + if (j1939_address_is_local(priv, skcb->addr.da)) skcb->flags |= J1939_ECU_LOCAL_DST; /* src is always local, I'm sending ... */ diff --git a/net/can/proc.c b/net/can/proc.c index 0938bf7dd646..de4d05ae3459 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -196,7 +196,8 @@ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list, " %-5s %03x %08x %pK %pK %8ld %s\n"; seq_printf(m, fmt, DNAME(dev), r->can_id, r->mask, - r->func, r->data, r->matches, r->ident); + r->func, r->data, atomic_long_read(&r->matches), + r->ident); } } diff --git a/net/can/raw.c b/net/can/raw.c index eee244ffc31e..82d9c0499c95 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -207,7 +207,8 @@ static void raw_rcv(struct sk_buff *oskb, void *data) if (oskb->sk == sk) *pflags |= MSG_CONFIRM; - if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) + reason = sock_queue_rcv_skb_reason(sk, skb); + if (reason) sk_skb_reason_drop(sk, skb, reason); } @@ -361,6 +362,14 @@ static int raw_notifier(struct notifier_block *nb, unsigned long msg, return NOTIFY_DONE; } +static void raw_sock_destruct(struct sock *sk) +{ + struct raw_sock *ro = raw_sk(sk); + + free_percpu(ro->uniq); + can_sock_destruct(sk); +} + static int raw_init(struct sock *sk) { struct raw_sock *ro = raw_sk(sk); @@ -387,6 +396,8 @@ static int raw_init(struct sock *sk) if (unlikely(!ro->uniq)) return -ENOMEM; + sk->sk_destruct = raw_sock_destruct; + /* set notifier */ spin_lock(&raw_notifier_lock); list_add_tail(&ro->notifier, &raw_notifier_list); @@ -436,7 +447,6 @@ static int raw_release(struct socket *sock) ro->bound = 0; ro->dev = NULL; ro->count = 0; - free_percpu(ro->uniq); sock_orphan(sk); sock->sk = NULL; @@ -552,8 +562,8 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr, return RAW_MIN_NAMELEN; } -static int raw_setsockopt(struct socket *sock, int level, int optname, - sockptr_t optval, unsigned int optlen) +static int raw_setsockopt_locked(struct socket *sock, int optname, + sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); @@ -565,9 +575,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, int flag; int err = 0; - if (level != SOL_CAN_RAW) - return -EINVAL; - switch (optname) { case CAN_RAW_FILTER: if (optlen % sizeof(struct can_filter) != 0) @@ -588,17 +595,11 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; } - rtnl_lock(); - lock_sock(sk); - dev = ro->dev; - if (ro->bound && dev) { - if (dev->reg_state != NETREG_REGISTERED) { - if (count > 1) - kfree(filter); - err = -ENODEV; - goto out_fil; - } + if (ro->bound && dev && dev->reg_state != NETREG_REGISTERED) { + if (count > 1) + kfree(filter); + return -ENODEV; } if (ro->bound) { @@ -612,7 +613,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, if (err) { if (count > 1) kfree(filter); - goto out_fil; + return err; } /* remove old filter registrations */ @@ -632,11 +633,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, } ro->filter = filter; ro->count = count; - - out_fil: - release_sock(sk); - rtnl_unlock(); - break; case CAN_RAW_ERR_FILTER: @@ -648,16 +644,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, err_mask &= CAN_ERR_MASK; - rtnl_lock(); - lock_sock(sk); - dev = ro->dev; - if (ro->bound && dev) { - if (dev->reg_state != NETREG_REGISTERED) { - err = -ENODEV; - goto out_err; - } - } + if (ro->bound && dev && dev->reg_state != NETREG_REGISTERED) + return -ENODEV; /* remove current error mask */ if (ro->bound) { @@ -666,7 +655,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, err_mask); if (err) - goto out_err; + return err; /* remove old err_mask registration */ raw_disable_errfilter(sock_net(sk), dev, sk, @@ -675,11 +664,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, /* link new err_mask to the socket */ ro->err_mask = err_mask; - - out_err: - release_sock(sk); - rtnl_unlock(); - break; case CAN_RAW_LOOPBACK: @@ -759,8 +743,28 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, return err; } +static int raw_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) +{ + struct sock *sk = sock->sk; + int err; + + if (level != SOL_CAN_RAW) + return -EINVAL; + + rtnl_lock(); + lock_sock(sk); + + err = raw_setsockopt_locked(sock, optname, optval, optlen); + + release_sock(sk); + rtnl_unlock(); + + return err; +} + static int raw_getsockopt(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) + sockopt_t *opt) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); @@ -770,8 +774,7 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, if (level != SOL_CAN_RAW) return -EINVAL; - if (get_user(len, optlen)) - return -EFAULT; + len = opt->optlen; if (len < 0) return -EINVAL; @@ -787,12 +790,12 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, if (len < fsize) { /* return -ERANGE and needed space in optlen */ err = -ERANGE; - if (put_user(fsize, optlen)) - err = -EFAULT; + opt->optlen = fsize; } else { if (len > fsize) len = fsize; - if (copy_to_user(optval, ro->filter, len)) + if (copy_to_iter(ro->filter, len, + &opt->iter_out) != len) err = -EFAULT; } } else { @@ -801,7 +804,7 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, release_sock(sk); if (!err) - err = put_user(len, optlen); + opt->optlen = len; return err; } case CAN_RAW_ERR_FILTER: @@ -845,16 +848,16 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, if (len < sizeof(ro->raw_vcid_opts)) { /* return -ERANGE and needed space in optlen */ err = -ERANGE; - if (put_user(sizeof(ro->raw_vcid_opts), optlen)) - err = -EFAULT; + opt->optlen = sizeof(ro->raw_vcid_opts); } else { if (len > sizeof(ro->raw_vcid_opts)) len = sizeof(ro->raw_vcid_opts); - if (copy_to_user(optval, &ro->raw_vcid_opts, len)) + if (copy_to_iter(&ro->raw_vcid_opts, len, + &opt->iter_out) != len) err = -EFAULT; } if (!err) - err = put_user(len, optlen); + opt->optlen = len; return err; } case CAN_RAW_JOIN_FILTERS: @@ -868,9 +871,8 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, return -ENOPROTOOPT; } - if (put_user(len, optlen)) - return -EFAULT; - if (copy_to_user(optval, val, len)) + opt->optlen = len; + if (copy_to_iter(val, len, &opt->iter_out) != len) return -EFAULT; return 0; } @@ -1077,7 +1079,7 @@ static const struct proto_ops raw_ops = { .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = raw_setsockopt, - .getsockopt = raw_getsockopt, + .getsockopt_iter = raw_getsockopt, .sendmsg = raw_sendmsg, .recvmsg = raw_recvmsg, .mmap = sock_no_mmap, |
