From 54a634c43ae75031c03126957edf667dba1439ec Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 20 Jul 2018 13:58:21 +0200 Subject: [PATCH 01/24] MIPS: ath79: fix register address in ath79_ddr_wb_flush() commit bc88ad2efd11f29e00a4fd60fcd1887abfe76833 upstream. ath79_ddr_wb_flush_base has the type void __iomem *, so register offsets need to be a multiple of 4 in order to access the intended register. Signed-off-by: Felix Fietkau Signed-off-by: John Crispin Signed-off-by: Paul Burton Fixes: 24b0e3e84fbf ("MIPS: ath79: Improve the DDR controller interface") Patchwork: https://patchwork.linux-mips.org/patch/19912/ Cc: Alban Bedel Cc: James Hogan Cc: Ralf Baechle Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # 4.2+ Signed-off-by: Greg Kroah-Hartman --- arch/mips/ath79/common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c index 8ae4067a5eda..40ecb6e700cd 100644 --- a/arch/mips/ath79/common.c +++ b/arch/mips/ath79/common.c @@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init); void ath79_ddr_wb_flush(u32 reg) { - void __iomem *flush_reg = ath79_ddr_wb_flush_base + reg; + void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4); /* Flush the DDR write buffer. */ __raw_writel(0x1, flush_reg); From 48f41c0c5781e3450830f8ec68513bfa18a5451b Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 23 Jul 2018 16:50:48 +0200 Subject: [PATCH 02/24] ip: hash fragments consistently [ Upstream commit 3dd1c9a1270736029ffca670e9bd0265f4120600 ] The skb hash for locally generated ip[v6] fragments belonging to the same datagram can vary in several circumstances: * for connected UDP[v6] sockets, the first fragment get its hash via set_owner_w()/skb_set_hash_from_sk() * for unconnected IPv6 UDPv6 sockets, the first fragment can get its hash via ip6_make_flowlabel()/skb_get_hash_flowi6(), if auto_flowlabel is enabled For the following frags the hash is usually computed via skb_get_hash(). The above can cause OoO for unconnected IPv6 UDPv6 socket: in that scenario the egress tx queue can be selected on a per packet basis via the skb hash. It may also fool flow-oriented schedulers to place fragments belonging to the same datagram in different flows. Fix the issue by copying the skb hash from the head frag into the others at fragmentation time. Before this commit: perf probe -a "dev_queue_xmit skb skb->hash skb->l4_hash:b1@0/8 skb->sw_hash:b1@1/8" netperf -H $IPV4 -t UDP_STREAM -l 5 -- -m 2000 -n & perf record -e probe:dev_queue_xmit -e probe:skb_set_owner_w -a sleep 0.1 perf script probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=3713014309 l4_hash=1 sw_hash=0 probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=0 l4_hash=0 sw_hash=0 After this commit: probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=2171763177 l4_hash=1 sw_hash=0 probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=2171763177 l4_hash=1 sw_hash=0 Fixes: b73c3d0e4f0e ("net: Save TX flow hash in sock and set in skbuf on xmit") Fixes: 67800f9b1f4e ("ipv6: Call skb_get_hash_flowi6 to get skb->hash in ip6_make_flowlabel") Signed-off-by: Paolo Abeni Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ip_output.c | 2 ++ net/ipv6/ip6_output.c | 2 ++ 2 files changed, 4 insertions(+) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 10286432f684..c11bb6d2d00a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -480,6 +480,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->dev = from->dev; to->mark = from->mark; + skb_copy_hash(to, from); + /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 74786783834b..0feede45bd28 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -559,6 +559,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->dev = from->dev; to->mark = from->mark; + skb_copy_hash(to, from); + #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif From 73dad08709fee646875f5a81c07b05fb54582732 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Tue, 24 Jul 2018 14:27:55 +0300 Subject: [PATCH 03/24] net/mlx4_core: Save the qpn from the input modifier in RST2INIT wrapper [ Upstream commit 958c696f5a7274d9447a458ad7aa70719b29a50a ] Function mlx4_RST2INIT_QP_wrapper saved the qp number passed in the qp context, rather than the one passed in the input modifier. However, the qp number in the qp context is not defined as a required parameter by the FW. Therefore, drivers may choose to not specify the qp number in the qp context for the reset-to-init transition. Thus, we must save the qp number passed in the command input modifier -- which is always present. (This saved qp number is used as the input modifier for command 2RST_QP when a slave's qp's are destroyed). Fixes: c82e9aa0a8bc ("mlx4_core: resource tracking for HCA resources used by guests") Signed-off-by: Jack Morgenstein Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index e3080fbd9d00..7911dc3da98e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2891,7 +2891,7 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, u32 srqn = qp_get_srqn(qpc) & 0xffffff; int use_srq = (qp_get_srqn(qpc) >> 24) & 1; struct res_srq *srq; - int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff; + int local_qpn = vhcr->in_modifier & 0xffffff; err = adjust_qp_sched_queue(dev, slave, qpc, inbox); if (err) From b04c9a08710606e2fa0a16f24541a270c00ef58c Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Fri, 20 Jul 2018 13:21:01 -0700 Subject: [PATCH 04/24] rtnetlink: add rtnl_link_state check in rtnl_configure_link [ Upstream commit 5025f7f7d506fba9b39e7fe8ca10f6f34cb9bc2d ] rtnl_configure_link sets dev->rtnl_link_state to RTNL_LINK_INITIALIZED and unconditionally calls __dev_notify_flags to notify user-space of dev flags. current call sequence for rtnl_configure_link rtnetlink_newlink rtnl_link_ops->newlink rtnl_configure_link (unconditionally notifies userspace of default and new dev flags) If a newlink handler wants to call rtnl_configure_link early, we will end up with duplicate notifications to user-space. This patch fixes rtnl_configure_link to check rtnl_link_state and call __dev_notify_flags with gchanges = 0 if already RTNL_LINK_INITIALIZED. Later in the series, this patch will help the following sequence where a driver implementing newlink can call rtnl_configure_link to initialize the link early. makes the following call sequence work: rtnetlink_newlink rtnl_link_ops->newlink (vxlan) -> rtnl_configure_link (initializes link and notifies user-space of default dev flags) rtnl_configure_link (updates dev flags if requested by user ifm and notifies user-space of new dev flags) Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/rtnetlink.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2017ffa5197a..96c9c0f0905a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2087,9 +2087,12 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) return err; } - dev->rtnl_link_state = RTNL_LINK_INITIALIZED; - - __dev_notify_flags(dev, old_flags, ~0U); + if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) { + __dev_notify_flags(dev, old_flags, 0U); + } else { + dev->rtnl_link_state = RTNL_LINK_INITIALIZED; + __dev_notify_flags(dev, old_flags, ~0U); + } return 0; } EXPORT_SYMBOL(rtnl_configure_link); From 500e03f463835e74c75890d56d9a7ab63755aa2d Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 12 Jul 2018 06:04:52 -0700 Subject: [PATCH 05/24] tcp: fix dctcp delayed ACK schedule [ Upstream commit b0c05d0e99d98d7f0cd41efc1eeec94efdc3325d ] Previously, when a data segment was sent an ACK was piggybacked on the data segment without generating a CA_EVENT_NON_DELAYED_ACK event to notify congestion control modules. So the DCTCP ca->delayed_ack_reserved flag could incorrectly stay set when in fact there were no delayed ACKs being reserved. This could result in sending a special ECN notification ACK that carries an older ACK sequence, when in fact there was no need for such an ACK. DCTCP keeps track of the delayed ACK status with its own separate state ca->delayed_ack_reserved. Previously it may accidentally cancel the delayed ACK without updating this field upon sending a special ACK that carries a older ACK sequence. This inconsistency would lead to DCTCP receiver never acknowledging the latest data until the sender times out and retry in some cases. Packetdrill script (provided by Larry Brakmo) 0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0 0.000 bind(3, ..., ...) = 0 0.000 listen(3, 1) = 0 0.100 < [ect0] SEW 0:0(0) win 32792 0.100 > SE. 0:0(0) ack 1 0.110 < [ect0] . 1:1(0) ack 1 win 257 0.200 accept(3, ..., ...) = 4 0.200 < [ect0] . 1:1001(1000) ack 1 win 257 0.200 > [ect01] . 1:1(0) ack 1001 0.200 write(4, ..., 1) = 1 0.200 > [ect01] P. 1:2(1) ack 1001 0.200 < [ect0] . 1001:2001(1000) ack 2 win 257 0.200 write(4, ..., 1) = 1 0.200 > [ect01] P. 2:3(1) ack 2001 0.200 < [ect0] . 2001:3001(1000) ack 3 win 257 0.200 < [ect0] . 3001:4001(1000) ack 3 win 257 0.200 > [ect01] . 3:3(0) ack 4001 0.210 < [ce] P. 4001:4501(500) ack 3 win 257 +0.001 read(4, ..., 4500) = 4500 +0 write(4, ..., 1) = 1 +0 > [ect01] PE. 3:4(1) ack 4501 +0.010 < [ect0] W. 4501:5501(1000) ack 4 win 257 // Previously the ACK sequence below would be 4501, causing a long RTO +0.040~+0.045 > [ect01] . 4:4(0) ack 5501 // delayed ack +0.311 < [ect0] . 5501:6501(1000) ack 4 win 257 // More data +0 > [ect01] . 4:4(0) ack 6501 // now acks everything +0.500 < F. 9501:9501(0) ack 4 win 257 Reported-by: Larry Brakmo Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Lawrence Brakmo Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_dctcp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 55d7da1d2ce9..e772679a5ded 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -134,7 +134,8 @@ static void dctcp_ce_state_0_to_1(struct sock *sk) /* State has changed from CE=0 to CE=1 and delayed * ACK has not sent yet. */ - if (!ca->ce_state && ca->delayed_ack_reserved) { + if (!ca->ce_state && + inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { u32 tmp_rcv_nxt; /* Save current rcv_nxt. */ @@ -164,7 +165,8 @@ static void dctcp_ce_state_1_to_0(struct sock *sk) /* State has changed from CE=1 to CE=0 and delayed * ACK has not sent yet. */ - if (ca->ce_state && ca->delayed_ack_reserved) { + if (ca->ce_state && + inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { u32 tmp_rcv_nxt; /* Save current rcv_nxt. */ From 17fea38e74ab24afb06970bbd9dc52db11a8034b Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 18 Jul 2018 13:56:34 -0700 Subject: [PATCH 06/24] tcp: helpers to send special DCTCP ack [ Upstream commit 2987babb6982306509380fc11b450227a844493b ] Refactor and create helpers to send the special ACK in DCTCP. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_output.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2854db094864..cbba484d4f5e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -901,8 +901,8 @@ out: * We are working here with either a clone of the original * SKB, or a fresh unique copy made by the retransmit engine. */ -static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, - gfp_t gfp_mask) +static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, + int clone_it, gfp_t gfp_mask, u32 rcv_nxt) { const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet; @@ -962,7 +962,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, th->source = inet->inet_sport; th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); - th->ack_seq = htonl(tp->rcv_nxt); + th->ack_seq = htonl(rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | tcb->tcp_flags); @@ -1036,6 +1036,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, return net_xmit_eval(err); } +static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, + gfp_t gfp_mask) +{ + return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask, + tcp_sk(sk)->rcv_nxt); +} + /* This routine just queues the buffer for sending. * * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, @@ -3354,7 +3361,7 @@ void tcp_send_delayed_ack(struct sock *sk) } /* This routine sends an ack and also updates the window. */ -void tcp_send_ack(struct sock *sk) +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) { struct sk_buff *buff; @@ -3391,7 +3398,12 @@ void tcp_send_ack(struct sock *sk) /* Send it off, this clears delayed acks for us. */ skb_mstamp_get(&buff->skb_mstamp); - tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC)); + __tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC), rcv_nxt); +} + +void tcp_send_ack(struct sock *sk) +{ + __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); } EXPORT_SYMBOL_GPL(tcp_send_ack); From 0b1d40e9e7738e3396ce414b1c62b911c285dfa3 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 18 Jul 2018 13:56:35 -0700 Subject: [PATCH 07/24] tcp: do not cancel delay-AcK on DCTCP special ACK [ Upstream commit 27cde44a259c380a3c09066fc4b42de7dde9b1ad ] Currently when a DCTCP receiver delays an ACK and receive a data packet with a different CE mark from the previous one's, it sends two immediate ACKs acking previous and latest sequences respectly (for ECN accounting). Previously sending the first ACK may mark off the delayed ACK timer (tcp_event_ack_sent). This may subsequently prevent sending the second ACK to acknowledge the latest sequence (tcp_ack_snd_check). The culprit is that tcp_send_ack() assumes it always acknowleges the latest sequence, which is not true for the first special ACK. The fix is to not make the assumption in tcp_send_ack and check the actual ack sequence before cancelling the delayed ACK. Further it's safer to pass the ack sequence number as a local variable into tcp_send_ack routine, instead of intercepting tp->rcv_nxt to avoid future bugs like this. Reported-by: Neal Cardwell Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/tcp.h | 1 + net/ipv4/tcp_dctcp.c | 34 ++++------------------------------ net/ipv4/tcp_output.c | 11 ++++++++--- 3 files changed, 13 insertions(+), 33 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index a3696b778757..24ba8f005f01 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -559,6 +559,7 @@ void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index e772679a5ded..c48badee1cfa 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -135,21 +135,8 @@ static void dctcp_ce_state_0_to_1(struct sock *sk) * ACK has not sent yet. */ if (!ca->ce_state && - inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=0. */ - tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; - } + inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); ca->prior_rcv_nxt = tp->rcv_nxt; ca->ce_state = 1; @@ -166,21 +153,8 @@ static void dctcp_ce_state_1_to_0(struct sock *sk) * ACK has not sent yet. */ if (ca->ce_state && - inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=1. */ - tp->ecn_flags |= TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; - } + inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); ca->prior_rcv_nxt = tp->rcv_nxt; ca->ce_state = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index cbba484d4f5e..6fa749ce231f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -177,8 +177,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp, } /* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) +static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, + u32 rcv_nxt) { + struct tcp_sock *tp = tcp_sk(sk); + + if (unlikely(rcv_nxt != tp->rcv_nxt)) + return; /* Special ACK sent by DCTCP to reflect ECN */ tcp_dec_quickack_mode(sk, pkts); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -1005,7 +1010,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, icsk->icsk_af_ops->send_check(sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); + tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); if (skb->len != tcp_header_size) tcp_event_data_sent(tp, sk); @@ -3400,12 +3405,12 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) skb_mstamp_get(&buff->skb_mstamp); __tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC), rcv_nxt); } +EXPORT_SYMBOL_GPL(__tcp_send_ack); void tcp_send_ack(struct sock *sk) { __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); } -EXPORT_SYMBOL_GPL(tcp_send_ack); /* This routine sends a packet with an out of date sequence * number. It assumes the other end will try to ack it. From 255924ea891f647451af3acbc40a3730dcb3255e Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 18 Jul 2018 13:56:36 -0700 Subject: [PATCH 08/24] tcp: do not delay ACK in DCTCP upon CE status change [ Upstream commit a0496ef2c23b3b180902dd185d0d63ccbc624cf8 ] Per DCTCP RFC8257 (Section 3.2) the ACK reflecting the CE status change has to be sent immediately so the sender can respond quickly: """ When receiving packets, the CE codepoint MUST be processed as follows: 1. If the CE codepoint is set and DCTCP.CE is false, set DCTCP.CE to true and send an immediate ACK. 2. If the CE codepoint is not set and DCTCP.CE is true, set DCTCP.CE to false and send an immediate ACK. """ Previously DCTCP implementation may continue to delay the ACK. This patch fixes that to implement the RFC by forcing an immediate ACK. Tested with this packetdrill script provided by Larry Brakmo 0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0 0.000 bind(3, ..., ...) = 0 0.000 listen(3, 1) = 0 0.100 < [ect0] SEW 0:0(0) win 32792 0.100 > SE. 0:0(0) ack 1 0.110 < [ect0] . 1:1(0) ack 1 win 257 0.200 accept(3, ..., ...) = 4 +0 setsockopt(4, SOL_SOCKET, SO_DEBUG, [1], 4) = 0 0.200 < [ect0] . 1:1001(1000) ack 1 win 257 0.200 > [ect01] . 1:1(0) ack 1001 0.200 write(4, ..., 1) = 1 0.200 > [ect01] P. 1:2(1) ack 1001 0.200 < [ect0] . 1001:2001(1000) ack 2 win 257 +0.005 < [ce] . 2001:3001(1000) ack 2 win 257 +0.000 > [ect01] . 2:2(0) ack 2001 // Previously the ACK below would be delayed by 40ms +0.000 > [ect01] E. 2:2(0) ack 3001 +0.500 < F. 9501:9501(0) ack 4 win 257 Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/tcp.h | 1 + net/ipv4/tcp_dctcp.c | 30 ++++++++++++++++++------------ net/ipv4/tcp_input.c | 3 ++- 3 files changed, 21 insertions(+), 13 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 24ba8f005f01..65babd8a682d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -376,6 +376,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +void tcp_enter_quickack_mode(struct sock *sk); static inline void tcp_dec_quickack_mode(struct sock *sk, const unsigned int pkts) { diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index c48badee1cfa..e63b764e55ea 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -131,12 +131,15 @@ static void dctcp_ce_state_0_to_1(struct sock *sk) struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - /* State has changed from CE=0 to CE=1 and delayed - * ACK has not sent yet. - */ - if (!ca->ce_state && - inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) - __tcp_send_ack(sk, ca->prior_rcv_nxt); + if (!ca->ce_state) { + /* State has changed from CE=0 to CE=1, force an immediate + * ACK to reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); + tcp_enter_quickack_mode(sk); + } ca->prior_rcv_nxt = tp->rcv_nxt; ca->ce_state = 1; @@ -149,12 +152,15 @@ static void dctcp_ce_state_1_to_0(struct sock *sk) struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - /* State has changed from CE=1 to CE=0 and delayed - * ACK has not sent yet. - */ - if (ca->ce_state && - inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) - __tcp_send_ack(sk, ca->prior_rcv_nxt); + if (ca->ce_state) { + /* State has changed from CE=1 to CE=0, force an immediate + * ACK to reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); + tcp_enter_quickack_mode(sk); + } ca->prior_rcv_nxt = tp->rcv_nxt; ca->ce_state = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4350ee058441..782fb6dbf636 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -187,13 +187,14 @@ static void tcp_incr_quickack(struct sock *sk) icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS); } -static void tcp_enter_quickack_mode(struct sock *sk) +void tcp_enter_quickack_mode(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_incr_quickack(sk); icsk->icsk_ack.pingpong = 0; icsk->icsk_ack.ato = TCP_ATO_MIN; } +EXPORT_SYMBOL(tcp_enter_quickack_mode); /* Send ACKs quickly, if "quick" count is not exhausted * and the session is not interactive. From 5fbec4801264cb3279ef6ac9c70bcbe2aaef89d5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 23 Jul 2018 09:28:18 -0700 Subject: [PATCH 09/24] tcp: avoid collapses in tcp_prune_queue() if possible [ Upstream commit f4a3313d8e2ca9fd8d8f45e40a2903ba782607e7 ] Right after a TCP flow is created, receiving tiny out of order packets allways hit the condition : if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) tcp_clamp_window(sk); tcp_clamp_window() increases sk_rcvbuf to match sk_rmem_alloc (guarded by tcp_rmem[2]) Calling tcp_collapse_ofo_queue() in this case is not useful, and offers a O(N^2) surface attack to malicious peers. Better not attempt anything before full queue capacity is reached, forcing attacker to spend lots of resource and allow us to more easily detect the abuse. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 782fb6dbf636..8088e98696aa 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4875,6 +4875,9 @@ static int tcp_prune_queue(struct sock *sk) else if (tcp_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) + return 0; + tcp_collapse_ofo_queue(sk); if (!skb_queue_empty(&sk->sk_receive_queue)) tcp_collapse(sk, &sk->sk_receive_queue, From dc6ae4dffd656811dee7151b19545e4cd839d378 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 23 Jul 2018 09:28:19 -0700 Subject: [PATCH 10/24] tcp: detect malicious patterns in tcp_collapse_ofo_queue() [ Upstream commit 3d4bf93ac12003f9b8e1e2de37fe27983deebdcf ] In case an attacker feeds tiny packets completely out of order, tcp_collapse_ofo_queue() might scan the whole rb-tree, performing expensive copies, but not changing socket memory usage at all. 1) Do not attempt to collapse tiny skbs. 2) Add logic to exit early when too many tiny skbs are detected. We prefer not doing aggressive collapsing (which copies packets) for pathological flows, and revert to tcp_prune_ofo_queue() which will be less expensive. In the future, we might add the possibility of terminating flows that are proven to be malicious. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8088e98696aa..5c645069a09a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4789,6 +4789,7 @@ restart: static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 range_truesize, sum_tiny = 0; struct sk_buff *skb = skb_peek(&tp->out_of_order_queue); struct sk_buff *head; u32 start, end; @@ -4798,6 +4799,7 @@ static void tcp_collapse_ofo_queue(struct sock *sk) start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; + range_truesize = skb->truesize; head = skb; for (;;) { @@ -4812,14 +4814,24 @@ static void tcp_collapse_ofo_queue(struct sock *sk) if (!skb || after(TCP_SKB_CB(skb)->seq, end) || before(TCP_SKB_CB(skb)->end_seq, start)) { - tcp_collapse(sk, &tp->out_of_order_queue, - head, skb, start, end); + /* Do not attempt collapsing tiny skbs */ + if (range_truesize != head->truesize || + end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) { + tcp_collapse(sk, &tp->out_of_order_queue, + head, skb, start, end); + } else { + sum_tiny += range_truesize; + if (sum_tiny > sk->sk_rcvbuf >> 3) + return; + } + head = skb; if (!skb) break; /* Start new segment */ start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; + range_truesize = skb->truesize; } else { if (before(TCP_SKB_CB(skb)->seq, start)) start = TCP_SKB_CB(skb)->seq; From a77bf88daa402cb52729fe4e46e1b7ce58f1f8ad Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 23 Jul 2018 19:36:48 -0400 Subject: [PATCH 11/24] ip: in cmsg IP(V6)_ORIGDSTADDR call pskb_may_pull [ Upstream commit 2efd4fca703a6707cad16ab486eaab8fc7f0fd49 ] Syzbot reported a read beyond the end of the skb head when returning IPV6_ORIGDSTADDR: BUG: KMSAN: kernel-infoleak in put_cmsg+0x5ef/0x860 net/core/scm.c:242 CPU: 0 PID: 4501 Comm: syz-executor128 Not tainted 4.17.0+ #9 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:113 kmsan_report+0x188/0x2a0 mm/kmsan/kmsan.c:1125 kmsan_internal_check_memory+0x138/0x1f0 mm/kmsan/kmsan.c:1219 kmsan_copy_to_user+0x7a/0x160 mm/kmsan/kmsan.c:1261 copy_to_user include/linux/uaccess.h:184 [inline] put_cmsg+0x5ef/0x860 net/core/scm.c:242 ip6_datagram_recv_specific_ctl+0x1cf3/0x1eb0 net/ipv6/datagram.c:719 ip6_datagram_recv_ctl+0x41c/0x450 net/ipv6/datagram.c:733 rawv6_recvmsg+0x10fb/0x1460 net/ipv6/raw.c:521 [..] This logic and its ipv4 counterpart read the destination port from the packet at skb_transport_offset(skb) + 4. With MSG_MORE and a local SOCK_RAW sender, syzbot was able to cook a packet that stores headers exactly up to skb_transport_offset(skb) in the head and the remainder in a frag. Call pskb_may_pull before accessing the pointer to ensure that it lies in skb head. Link: http://lkml.kernel.org/r/CAF=yD-LEJwZj5a1-bAAj2Oy_hKmGygV6rsJ_WOrAYnv-fnayiQ@mail.gmail.com Reported-by: syzbot+9adb4b567003cac781f0@syzkaller.appspotmail.com Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ip_sockglue.c | 7 +++++-- net/ipv6/datagram.c | 7 +++++-- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ce9a7fbb7c5f..88426a6a7a85 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -135,15 +135,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { struct sockaddr_in sin; const struct iphdr *iph = ip_hdr(skb); - __be16 *ports = (__be16 *)skb_transport_header(skb); + __be16 *ports; + int end; - if (skb_transport_offset(skb) + 4 > skb->len) + end = skb_transport_offset(skb) + 4; + if (end > 0 && !pskb_may_pull(skb, end)) return; /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ + ports = (__be16 *)skb_transport_header(skb); sin.sin_family = AF_INET; sin.sin_addr.s_addr = iph->daddr; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index cae37bfd12ab..9f6e57ded338 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -657,13 +657,16 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, } if (np->rxopt.bits.rxorigdstaddr) { struct sockaddr_in6 sin6; - __be16 *ports = (__be16 *) skb_transport_header(skb); + __be16 *ports; + int end; - if (skb_transport_offset(skb) + 4 <= skb->len) { + end = skb_transport_offset(skb) + 4; + if (end <= 0 || pskb_may_pull(skb, end)) { /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ + ports = (__be16 *)skb_transport_header(skb); sin6.sin6_family = AF_INET6; sin6.sin6_addr = ipv6_hdr(skb)->daddr; From 92197cdb913a3f130b70550c856afc27cf710ea9 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Tue, 10 Jul 2018 08:28:49 +0200 Subject: [PATCH 12/24] usb: cdc_acm: Add quirk for Castles VEGA3000 commit 1445cbe476fc3dd09c0b380b206526a49403c071 upstream. The device (a POS terminal) implements CDC ACM, but has not union descriptor. Signed-off-by: Lubomir Rintel Acked-by: Oliver Neukum Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-acm.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 7ed30d0b5273..a501f3ba6a3f 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1771,6 +1771,9 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x09d8, 0x0320), /* Elatec GmbH TWN3 */ .driver_info = NO_UNION_NORMAL, /* has misplaced union descriptor */ }, + { USB_DEVICE(0x0ca6, 0xa050), /* Castles VEGA3000 */ + .driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */ + }, { USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */ .driver_info = CLEAR_HALT_CONDITIONS, From ff180bcc594676b355476237a382ea10c6492c34 Mon Sep 17 00:00:00 2001 From: Bin Liu Date: Thu, 19 Jul 2018 14:39:37 -0500 Subject: [PATCH 13/24] usb: core: handle hub C_PORT_OVER_CURRENT condition commit 249a32b7eeb3edb6897dd38f89651a62163ac4ed upstream. Based on USB2.0 Spec Section 11.12.5, "If a hub has per-port power switching and per-port current limiting, an over-current on one port may still cause the power on another port to fall below specific minimums. In this case, the affected port is placed in the Power-Off state and C_PORT_OVER_CURRENT is set for the port, but PORT_OVER_CURRENT is not set." so let's check C_PORT_OVER_CURRENT too for over current condition. Fixes: 08d1dec6f405 ("usb:hub set hub->change_bits when over-current happens") Cc: Tested-by: Alessandro Antenucci Signed-off-by: Bin Liu Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 4d86da0df131..93756664592a 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1123,10 +1123,14 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) if (!udev || udev->state == USB_STATE_NOTATTACHED) { /* Tell hub_wq to disconnect the device or - * check for a new connection + * check for a new connection or over current condition. + * Based on USB2.0 Spec Section 11.12.5, + * C_PORT_OVER_CURRENT could be set while + * PORT_OVER_CURRENT is not. So check for any of them. */ if (udev || (portstatus & USB_PORT_STAT_CONNECTION) || - (portstatus & USB_PORT_STAT_OVERCURRENT)) + (portstatus & USB_PORT_STAT_OVERCURRENT) || + (portchange & USB_PORT_STAT_C_OVERCURRENT)) set_bit(port1, hub->change_bits); } else if (portstatus & USB_PORT_STAT_ENABLE) { From c420866afc161203d17f1fcd965a27a61ef70dd4 Mon Sep 17 00:00:00 2001 From: Jerry Zhang Date: Mon, 2 Jul 2018 12:48:08 -0700 Subject: [PATCH 14/24] usb: gadget: f_fs: Only return delayed status when len is 0 commit 4d644abf25698362bd33d17c9ddc8f7122c30f17 upstream. Commit 1b9ba000 ("Allow function drivers to pause control transfers") states that USB_GADGET_DELAYED_STATUS is only supported if data phase is 0 bytes. It seems that when the length is not 0 bytes, there is no need to explicitly delay the data stage since the transfer is not completed until the user responds. However, when the length is 0, there is no data stage and the transfer is finished once setup() returns, hence there is a need to explicitly delay completion. This manifests as the following bugs: Prior to 946ef68ad4e4 ('Let setup() return USB_GADGET_DELAYED_STATUS'), when setup is 0 bytes, ffs would require user to queue a 0 byte request in order to clear setup state. However, that 0 byte request was actually not needed and would hang and cause errors in other setup requests. After the above commit, 0 byte setups work since the gadget now accepts empty queues to ep0 to clear the delay, but all other setups hang. Fixes: 946ef68ad4e4 ("Let setup() return USB_GADGET_DELAYED_STATUS") Signed-off-by: Jerry Zhang Cc: stable Acked-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_fs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 4191feb765b1..4800bb22cdd6 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3037,7 +3037,7 @@ static int ffs_func_setup(struct usb_function *f, __ffs_event_add(ffs, FUNCTIONFS_SETUP); spin_unlock_irqrestore(&ffs->ev.waitq.lock, flags); - return USB_GADGET_DELAYED_STATUS; + return creq->wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0; } static void ffs_func_suspend(struct usb_function *f) From 0b14de0538aaa6c9b8c5d90b29e0a8dd698ba918 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 10 Jul 2018 14:51:33 +0200 Subject: [PATCH 15/24] driver core: Partially revert "driver core: correct device's shutdown order" commit 722e5f2b1eec7de61117b7c0a7914761e3da2eda upstream. Commit 52cdbdd49853 (driver core: correct device's shutdown order) introduced a regression by breaking device shutdown on some systems. Namely, the devices_kset_move_last() call in really_probe() added by that commit is a mistake as it may cause parents to follow children in the devices_kset list which then causes shutdown to fail. For example, if a device has children before really_probe() is called for it (which is not uncommon), that call will cause it to be reordered after the children in the devices_kset list and the ordering of that list will not reflect the correct device shutdown order any more. Also it causes the devices_kset list to be constantly reordered until all drivers have been probed which is totally pointless overhead in the majority of cases and it only covered an issue with system shutdown, while system-wide suspend/resume potentially had the same issue on the affected platforms (which was not covered). Moreover, the shutdown issue originally addressed by the change in really_probe() made by commit 52cdbdd49853 is not present in 4.18-rc any more, since dra7 started to use the sdhci-omap driver which doesn't disable any regulators during shutdown, so the really_probe() part of commit 52cdbdd49853 can be safely reverted. [The original issue was related to the omap_hsmmc driver used by dra7 previously.] For the above reasons, revert the really_probe() modifications made by commit 52cdbdd49853. The other code changes made by commit 52cdbdd49853 are useful and they need not be reverted. Fixes: 52cdbdd49853 (driver core: correct device's shutdown order) Link: https://lore.kernel.org/lkml/CAFgQCTt7VfqM=UyCnvNFxrSw8Z6cUtAi3HUwR4_xPAc03SgHjQ@mail.gmail.com/ Reported-by: Pingfan Liu Tested-by: Pingfan Liu Reviewed-by: Kishon Vijay Abraham I Signed-off-by: Rafael J. Wysocki Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/base/dd.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/base/dd.c b/drivers/base/dd.c index a641cf3ccad6..1dffb018a7fe 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -304,14 +304,6 @@ static int really_probe(struct device *dev, struct device_driver *drv) goto probe_failed; } - /* - * Ensure devices are listed in devices_kset in correct order - * It's important to move Dev to the end of devices_kset before - * calling .probe, because it could be recursive and parent Dev - * should always go first - */ - devices_kset_move_last(dev); - if (dev->bus->probe) { ret = dev->bus->probe(dev); if (ret) From e4c557649fda285e512f28a771038180cdeff6cf Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Tue, 7 Feb 2017 17:01:14 +0200 Subject: [PATCH 16/24] can: xilinx_can: fix RX loop if RXNEMP is asserted without RXOK commit 32852c561bffd613d4ed7ec464b1e03e1b7b6c5c upstream. If the device gets into a state where RXNEMP (RX FIFO not empty) interrupt is asserted without RXOK (new frame received successfully) interrupt being asserted, xcan_rx_poll() will continue to try to clear RXNEMP without actually reading frames from RX FIFO. If the RX FIFO is not empty, the interrupt will not be cleared and napi_schedule() will just be called again. This situation can occur when: (a) xcan_rx() returns without reading RX FIFO due to an error condition. The code tries to clear both RXOK and RXNEMP but RXNEMP will not clear due to a frame still being in the FIFO. The frame will never be read from the FIFO as RXOK is no longer set. (b) A frame is received between xcan_rx_poll() reading interrupt status and clearing RXOK. RXOK will be cleared, but RXNEMP will again remain set as the new message is still in the FIFO. I'm able to trigger case (b) by flooding the bus with frames under load. There does not seem to be any benefit in using both RXNEMP and RXOK in the way the driver does, and the polling example in the reference manual (UG585 v1.10 18.3.7 Read Messages from RxFIFO) also says that either RXOK or RXNEMP can be used for detecting incoming messages. Fix the issue and simplify the RX processing by only using RXNEMP without RXOK. Tested with the integrated CAN on Zynq-7000 SoC. Fixes: b1201e44f50b ("can: xilinx CAN controller support") Signed-off-by: Anssi Hannula Cc: Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/xilinx_can.c | 18 +++++------------- 1 file changed, 5 insertions(+), 13 deletions(-) diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 51670b322409..727add0decdf 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -100,7 +100,7 @@ enum xcan_reg { #define XCAN_INTR_ALL (XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\ XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \ XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \ - XCAN_IXR_ARBLST_MASK | XCAN_IXR_RXOK_MASK) + XCAN_IXR_ARBLST_MASK) /* CAN register bit shift - XCAN___SHIFT */ #define XCAN_BTR_SJW_SHIFT 7 /* Synchronous jump width */ @@ -708,15 +708,7 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota) isr = priv->read_reg(priv, XCAN_ISR_OFFSET); while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) { - if (isr & XCAN_IXR_RXOK_MASK) { - priv->write_reg(priv, XCAN_ICR_OFFSET, - XCAN_IXR_RXOK_MASK); - work_done += xcan_rx(ndev); - } else { - priv->write_reg(priv, XCAN_ICR_OFFSET, - XCAN_IXR_RXNEMP_MASK); - break; - } + work_done += xcan_rx(ndev); priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK); isr = priv->read_reg(priv, XCAN_ISR_OFFSET); } @@ -727,7 +719,7 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota) if (work_done < quota) { napi_complete(napi); ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier |= (XCAN_IXR_RXOK_MASK | XCAN_IXR_RXNEMP_MASK); + ier |= XCAN_IXR_RXNEMP_MASK; priv->write_reg(priv, XCAN_IER_OFFSET, ier); } return work_done; @@ -799,9 +791,9 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) } /* Check for the type of receive interrupt and Processing it */ - if (isr & (XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK)) { + if (isr & XCAN_IXR_RXNEMP_MASK) { ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier &= ~(XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK); + ier &= ~XCAN_IXR_RXNEMP_MASK; priv->write_reg(priv, XCAN_IER_OFFSET, ier); napi_schedule(&priv->napi); } From 7e572a170fc30ce4e6bff79b2a54f445a88457ac Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Wed, 8 Feb 2017 13:13:40 +0200 Subject: [PATCH 17/24] can: xilinx_can: fix recovery from error states not being propagated commit 877e0b75947e2c7acf5624331bb17ceb093c98ae upstream. The xilinx_can driver contains no mechanism for propagating recovery from CAN_STATE_ERROR_WARNING and CAN_STATE_ERROR_PASSIVE. Add such a mechanism by factoring the handling of XCAN_STATE_ERROR_PASSIVE and XCAN_STATE_ERROR_WARNING out of xcan_err_interrupt and checking for recovery after RX and TX if the interface is in one of those states. Tested with the integrated CAN on Zynq-7000 SoC. Fixes: b1201e44f50b ("can: xilinx CAN controller support") Signed-off-by: Anssi Hannula Cc: Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/xilinx_can.c | 155 ++++++++++++++++++++++++++++------- 1 file changed, 127 insertions(+), 28 deletions(-) diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 727add0decdf..b0b52bf276b0 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -2,6 +2,7 @@ * * Copyright (C) 2012 - 2014 Xilinx, Inc. * Copyright (C) 2009 PetaLogix. All rights reserved. + * Copyright (C) 2017 Sandvik Mining and Construction Oy * * Description: * This driver is developed for Axi CAN IP and for Zynq CANPS Controller. @@ -528,6 +529,123 @@ static int xcan_rx(struct net_device *ndev) return 1; } +/** + * xcan_current_error_state - Get current error state from HW + * @ndev: Pointer to net_device structure + * + * Checks the current CAN error state from the HW. Note that this + * only checks for ERROR_PASSIVE and ERROR_WARNING. + * + * Return: + * ERROR_PASSIVE or ERROR_WARNING if either is active, ERROR_ACTIVE + * otherwise. + */ +static enum can_state xcan_current_error_state(struct net_device *ndev) +{ + struct xcan_priv *priv = netdev_priv(ndev); + u32 status = priv->read_reg(priv, XCAN_SR_OFFSET); + + if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) + return CAN_STATE_ERROR_PASSIVE; + else if (status & XCAN_SR_ERRWRN_MASK) + return CAN_STATE_ERROR_WARNING; + else + return CAN_STATE_ERROR_ACTIVE; +} + +/** + * xcan_set_error_state - Set new CAN error state + * @ndev: Pointer to net_device structure + * @new_state: The new CAN state to be set + * @cf: Error frame to be populated or NULL + * + * Set new CAN error state for the device, updating statistics and + * populating the error frame if given. + */ +static void xcan_set_error_state(struct net_device *ndev, + enum can_state new_state, + struct can_frame *cf) +{ + struct xcan_priv *priv = netdev_priv(ndev); + u32 ecr = priv->read_reg(priv, XCAN_ECR_OFFSET); + u32 txerr = ecr & XCAN_ECR_TEC_MASK; + u32 rxerr = (ecr & XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT; + + priv->can.state = new_state; + + if (cf) { + cf->can_id |= CAN_ERR_CRTL; + cf->data[6] = txerr; + cf->data[7] = rxerr; + } + + switch (new_state) { + case CAN_STATE_ERROR_PASSIVE: + priv->can.can_stats.error_passive++; + if (cf) + cf->data[1] = (rxerr > 127) ? + CAN_ERR_CRTL_RX_PASSIVE : + CAN_ERR_CRTL_TX_PASSIVE; + break; + case CAN_STATE_ERROR_WARNING: + priv->can.can_stats.error_warning++; + if (cf) + cf->data[1] |= (txerr > rxerr) ? + CAN_ERR_CRTL_TX_WARNING : + CAN_ERR_CRTL_RX_WARNING; + break; + case CAN_STATE_ERROR_ACTIVE: + if (cf) + cf->data[1] |= CAN_ERR_CRTL_ACTIVE; + break; + default: + /* non-ERROR states are handled elsewhere */ + WARN_ON(1); + break; + } +} + +/** + * xcan_update_error_state_after_rxtx - Update CAN error state after RX/TX + * @ndev: Pointer to net_device structure + * + * If the device is in a ERROR-WARNING or ERROR-PASSIVE state, check if + * the performed RX/TX has caused it to drop to a lesser state and set + * the interface state accordingly. + */ +static void xcan_update_error_state_after_rxtx(struct net_device *ndev) +{ + struct xcan_priv *priv = netdev_priv(ndev); + enum can_state old_state = priv->can.state; + enum can_state new_state; + + /* changing error state due to successful frame RX/TX can only + * occur from these states + */ + if (old_state != CAN_STATE_ERROR_WARNING && + old_state != CAN_STATE_ERROR_PASSIVE) + return; + + new_state = xcan_current_error_state(ndev); + + if (new_state != old_state) { + struct sk_buff *skb; + struct can_frame *cf; + + skb = alloc_can_err_skb(ndev, &cf); + + xcan_set_error_state(ndev, new_state, skb ? cf : NULL); + + if (skb) { + struct net_device_stats *stats = &ndev->stats; + + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); + } + } +} + /** * xcan_err_interrupt - error frame Isr * @ndev: net_device pointer @@ -543,16 +661,12 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) struct net_device_stats *stats = &ndev->stats; struct can_frame *cf; struct sk_buff *skb; - u32 err_status, status, txerr = 0, rxerr = 0; + u32 err_status; skb = alloc_can_err_skb(ndev, &cf); err_status = priv->read_reg(priv, XCAN_ESR_OFFSET); priv->write_reg(priv, XCAN_ESR_OFFSET, err_status); - txerr = priv->read_reg(priv, XCAN_ECR_OFFSET) & XCAN_ECR_TEC_MASK; - rxerr = ((priv->read_reg(priv, XCAN_ECR_OFFSET) & - XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT); - status = priv->read_reg(priv, XCAN_SR_OFFSET); if (isr & XCAN_IXR_BSOFF_MASK) { priv->can.state = CAN_STATE_BUS_OFF; @@ -562,28 +676,10 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) can_bus_off(ndev); if (skb) cf->can_id |= CAN_ERR_BUSOFF; - } else if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) { - priv->can.state = CAN_STATE_ERROR_PASSIVE; - priv->can.can_stats.error_passive++; - if (skb) { - cf->can_id |= CAN_ERR_CRTL; - cf->data[1] = (rxerr > 127) ? - CAN_ERR_CRTL_RX_PASSIVE : - CAN_ERR_CRTL_TX_PASSIVE; - cf->data[6] = txerr; - cf->data[7] = rxerr; - } - } else if (status & XCAN_SR_ERRWRN_MASK) { - priv->can.state = CAN_STATE_ERROR_WARNING; - priv->can.can_stats.error_warning++; - if (skb) { - cf->can_id |= CAN_ERR_CRTL; - cf->data[1] |= (txerr > rxerr) ? - CAN_ERR_CRTL_TX_WARNING : - CAN_ERR_CRTL_RX_WARNING; - cf->data[6] = txerr; - cf->data[7] = rxerr; - } + } else { + enum can_state new_state = xcan_current_error_state(ndev); + + xcan_set_error_state(ndev, new_state, skb ? cf : NULL); } /* Check for Arbitration lost interrupt */ @@ -713,8 +809,10 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota) isr = priv->read_reg(priv, XCAN_ISR_OFFSET); } - if (work_done) + if (work_done) { can_led_event(ndev, CAN_LED_EVENT_RX); + xcan_update_error_state_after_rxtx(ndev); + } if (work_done < quota) { napi_complete(napi); @@ -745,6 +843,7 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr) isr = priv->read_reg(priv, XCAN_ISR_OFFSET); } can_led_event(ndev, CAN_LED_EVENT_TX); + xcan_update_error_state_after_rxtx(ndev); netif_wake_queue(ndev); } From d7dec444472632fcba1d4b3be0aac8d279a37cc4 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Tue, 7 Feb 2017 13:23:04 +0200 Subject: [PATCH 18/24] can: xilinx_can: fix device dropping off bus on RX overrun commit 2574fe54515ed3487405de329e4e9f13d7098c10 upstream. The xilinx_can driver performs a software reset when an RX overrun is detected. This causes the device to enter Configuration mode where no messages are received or transmitted. The documentation does not mention any need to perform a reset on an RX overrun, and testing by inducing an RX overflow also indicated that the device continues to work just fine without a reset. Remove the software reset. Tested with the integrated CAN on Zynq-7000 SoC. Fixes: b1201e44f50b ("can: xilinx CAN controller support") Signed-off-by: Anssi Hannula Cc: Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/xilinx_can.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index b0b52bf276b0..e787116e9e82 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -695,7 +695,6 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) if (isr & XCAN_IXR_RXOFLW_MASK) { stats->rx_over_errors++; stats->rx_errors++; - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); if (skb) { cf->can_id |= CAN_ERR_CRTL; cf->data[1] |= CAN_ERR_CRTL_RX_OVERFLOW; From e5df9264649e13f0b6c2da9ce089a8ac41ef5121 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Thu, 23 Feb 2017 14:50:03 +0200 Subject: [PATCH 19/24] can: xilinx_can: keep only 1-2 frames in TX FIFO to fix TX accounting commit 620050d9c2be15c47017ba95efe59e0832e99a56 upstream. The xilinx_can driver assumes that the TXOK interrupt only clears after it has been acknowledged as many times as there have been successfully sent frames. However, the documentation does not mention such behavior, instead saying just that the interrupt is cleared when the clear bit is set. Similarly, testing seems to also suggest that it is immediately cleared regardless of the amount of frames having been sent. Performing some heavy TX load and then going back to idle has the tx_head drifting further away from tx_tail over time, steadily reducing the amount of frames the driver keeps in the TX FIFO (but not to zero, as the TXOK interrupt always frees up space for 1 frame from the driver's perspective, so frames continue to be sent) and delaying the local echo frames. The TX FIFO tracking is also otherwise buggy as it does not account for TX FIFO being cleared after software resets, causing BUG!, TX FIFO full when queue awake! messages to be output. There does not seem to be any way to accurately track the state of the TX FIFO for local echo support while using the full TX FIFO. The Zynq version of the HW (but not the soft-AXI version) has watermark programming support and with it an additional TX-FIFO-empty interrupt bit. Modify the driver to only put 1 frame into TX FIFO at a time on soft-AXI and 2 frames at a time on Zynq. On Zynq the TXFEMP interrupt bit is used to detect whether 1 or 2 frames have been sent at interrupt processing time. Tested with the integrated CAN on Zynq-7000 SoC. The 1-frame-FIFO mode was also tested. An alternative way to solve this would be to drop local echo support but keep using the full TX FIFO. v2: Add FIFO space check before TX queue wake with locking to synchronize with queue stop. This avoids waking the queue when xmit() had just filled it. v3: Keep local echo support and reduce the amount of frames in FIFO instead as suggested by Marc Kleine-Budde. Fixes: b1201e44f50b ("can: xilinx CAN controller support") Signed-off-by: Anssi Hannula Cc: Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/xilinx_can.c | 139 +++++++++++++++++++++++++++++++---- 1 file changed, 123 insertions(+), 16 deletions(-) diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index e787116e9e82..09c9950a03a5 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -26,8 +26,10 @@ #include #include #include +#include #include #include +#include #include #include #include @@ -118,6 +120,7 @@ enum xcan_reg { /** * struct xcan_priv - This definition define CAN driver instance * @can: CAN private data structure. + * @tx_lock: Lock for synchronizing TX interrupt handling * @tx_head: Tx CAN packets ready to send on the queue * @tx_tail: Tx CAN packets successfully sended on the queue * @tx_max: Maximum number packets the driver can send @@ -132,6 +135,7 @@ enum xcan_reg { */ struct xcan_priv { struct can_priv can; + spinlock_t tx_lock; unsigned int tx_head; unsigned int tx_tail; unsigned int tx_max; @@ -159,6 +163,11 @@ static const struct can_bittiming_const xcan_bittiming_const = { .brp_inc = 1, }; +#define XCAN_CAP_WATERMARK 0x0001 +struct xcan_devtype_data { + unsigned int caps; +}; + /** * xcan_write_reg_le - Write a value to the device register little endian * @priv: Driver private data structure @@ -238,6 +247,10 @@ static int set_reset_mode(struct net_device *ndev) usleep_range(500, 10000); } + /* reset clears FIFOs */ + priv->tx_head = 0; + priv->tx_tail = 0; + return 0; } @@ -392,6 +405,7 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) struct net_device_stats *stats = &ndev->stats; struct can_frame *cf = (struct can_frame *)skb->data; u32 id, dlc, data[2] = {0, 0}; + unsigned long flags; if (can_dropped_invalid_skb(ndev, skb)) return NETDEV_TX_OK; @@ -439,6 +453,9 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) data[1] = be32_to_cpup((__be32 *)(cf->data + 4)); can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max); + + spin_lock_irqsave(&priv->tx_lock, flags); + priv->tx_head++; /* Write the Frame to Xilinx CAN TX FIFO */ @@ -454,10 +471,16 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) stats->tx_bytes += cf->can_dlc; } + /* Clear TX-FIFO-empty interrupt for xcan_tx_interrupt() */ + if (priv->tx_max > 1) + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXFEMP_MASK); + /* Check if the TX buffer is full */ if ((priv->tx_head - priv->tx_tail) == priv->tx_max) netif_stop_queue(ndev); + spin_unlock_irqrestore(&priv->tx_lock, flags); + return NETDEV_TX_OK; } @@ -831,19 +854,71 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr) { struct xcan_priv *priv = netdev_priv(ndev); struct net_device_stats *stats = &ndev->stats; + unsigned int frames_in_fifo; + int frames_sent = 1; /* TXOK => at least 1 frame was sent */ + unsigned long flags; + int retries = 0; - while ((priv->tx_head - priv->tx_tail > 0) && - (isr & XCAN_IXR_TXOK_MASK)) { + /* Synchronize with xmit as we need to know the exact number + * of frames in the FIFO to stay in sync due to the TXFEMP + * handling. + * This also prevents a race between netif_wake_queue() and + * netif_stop_queue(). + */ + spin_lock_irqsave(&priv->tx_lock, flags); + + frames_in_fifo = priv->tx_head - priv->tx_tail; + + if (WARN_ON_ONCE(frames_in_fifo == 0)) { + /* clear TXOK anyway to avoid getting back here */ priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + spin_unlock_irqrestore(&priv->tx_lock, flags); + return; + } + + /* Check if 2 frames were sent (TXOK only means that at least 1 + * frame was sent). + */ + if (frames_in_fifo > 1) { + WARN_ON(frames_in_fifo > priv->tx_max); + + /* Synchronize TXOK and isr so that after the loop: + * (1) isr variable is up-to-date at least up to TXOK clear + * time. This avoids us clearing a TXOK of a second frame + * but not noticing that the FIFO is now empty and thus + * marking only a single frame as sent. + * (2) No TXOK is left. Having one could mean leaving a + * stray TXOK as we might process the associated frame + * via TXFEMP handling as we read TXFEMP *after* TXOK + * clear to satisfy (1). + */ + while ((isr & XCAN_IXR_TXOK_MASK) && !WARN_ON(++retries == 100)) { + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + isr = priv->read_reg(priv, XCAN_ISR_OFFSET); + } + + if (isr & XCAN_IXR_TXFEMP_MASK) { + /* nothing in FIFO anymore */ + frames_sent = frames_in_fifo; + } + } else { + /* single frame in fifo, just clear TXOK */ + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + } + + while (frames_sent--) { can_get_echo_skb(ndev, priv->tx_tail % priv->tx_max); priv->tx_tail++; stats->tx_packets++; - isr = priv->read_reg(priv, XCAN_ISR_OFFSET); } + + netif_wake_queue(ndev); + + spin_unlock_irqrestore(&priv->tx_lock, flags); + can_led_event(ndev, CAN_LED_EVENT_TX); xcan_update_error_state_after_rxtx(ndev); - netif_wake_queue(ndev); } /** @@ -1120,6 +1195,18 @@ static int __maybe_unused xcan_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(xcan_dev_pm_ops, xcan_suspend, xcan_resume); +static const struct xcan_devtype_data xcan_zynq_data = { + .caps = XCAN_CAP_WATERMARK, +}; + +/* Match table for OF platform binding */ +static const struct of_device_id xcan_of_match[] = { + { .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data }, + { .compatible = "xlnx,axi-can-1.00.a", }, + { /* end of list */ }, +}; +MODULE_DEVICE_TABLE(of, xcan_of_match); + /** * xcan_probe - Platform registration call * @pdev: Handle to the platform device structure @@ -1134,8 +1221,10 @@ static int xcan_probe(struct platform_device *pdev) struct resource *res; /* IO mem resources */ struct net_device *ndev; struct xcan_priv *priv; + const struct of_device_id *of_id; + int caps = 0; void __iomem *addr; - int ret, rx_max, tx_max; + int ret, rx_max, tx_max, tx_fifo_depth; /* Get the virtual base address for the device */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -1145,7 +1234,8 @@ static int xcan_probe(struct platform_device *pdev) goto err; } - ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", &tx_max); + ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", + &tx_fifo_depth); if (ret < 0) goto err; @@ -1153,6 +1243,30 @@ static int xcan_probe(struct platform_device *pdev) if (ret < 0) goto err; + of_id = of_match_device(xcan_of_match, &pdev->dev); + if (of_id) { + const struct xcan_devtype_data *devtype_data = of_id->data; + + if (devtype_data) + caps = devtype_data->caps; + } + + /* There is no way to directly figure out how many frames have been + * sent when the TXOK interrupt is processed. If watermark programming + * is supported, we can have 2 frames in the FIFO and use TXFEMP + * to determine if 1 or 2 frames have been sent. + * Theoretically we should be able to use TXFWMEMP to determine up + * to 3 frames, but it seems that after putting a second frame in the + * FIFO, with watermark at 2 frames, it can happen that TXFWMEMP (less + * than 2 frames in FIFO) is set anyway with no TXOK (a frame was + * sent), which is not a sensible state - possibly TXFWMEMP is not + * completely synchronized with the rest of the bits? + */ + if (caps & XCAN_CAP_WATERMARK) + tx_max = min(tx_fifo_depth, 2); + else + tx_max = 1; + /* Create a CAN device instance */ ndev = alloc_candev(sizeof(struct xcan_priv), tx_max); if (!ndev) @@ -1167,6 +1281,7 @@ static int xcan_probe(struct platform_device *pdev) CAN_CTRLMODE_BERR_REPORTING; priv->reg_base = addr; priv->tx_max = tx_max; + spin_lock_init(&priv->tx_lock); /* Get IRQ for the device */ ndev->irq = platform_get_irq(pdev, 0); @@ -1234,9 +1349,9 @@ static int xcan_probe(struct platform_device *pdev) devm_can_led_init(ndev); clk_disable_unprepare(priv->bus_clk); clk_disable_unprepare(priv->can_clk); - netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth:%d\n", + netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth: actual %d, using %d\n", priv->reg_base, ndev->irq, priv->can.clock.freq, - priv->tx_max); + tx_fifo_depth, priv->tx_max); return 0; @@ -1272,14 +1387,6 @@ static int xcan_remove(struct platform_device *pdev) return 0; } -/* Match table for OF platform binding */ -static const struct of_device_id xcan_of_match[] = { - { .compatible = "xlnx,zynq-can-1.0", }, - { .compatible = "xlnx,axi-can-1.00.a", }, - { /* end of list */ }, -}; -MODULE_DEVICE_TABLE(of, xcan_of_match); - static struct platform_driver xcan_driver = { .probe = xcan_probe, .remove = xcan_remove, From f7efacee6f8aaa311726eed09470e970b59fd4e1 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Mon, 26 Feb 2018 14:39:59 +0200 Subject: [PATCH 20/24] can: xilinx_can: fix incorrect clear of non-processed interrupts commit 2f4f0f338cf453bfcdbcf089e177c16f35f023c8 upstream. xcan_interrupt() clears ERROR|RXOFLV|BSOFF|ARBLST interrupts if any of them is asserted. This does not take into account that some of them could have been asserted between interrupt status read and interrupt clear, therefore clearing them without handling them. Fix the code to only clear those interrupts that it knows are asserted and therefore going to be processed in xcan_err_interrupt(). Fixes: b1201e44f50b ("can: xilinx CAN controller support") Signed-off-by: Anssi Hannula Cc: Michal Simek Cc: Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/xilinx_can.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 09c9950a03a5..a7286d72ed7b 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -937,6 +937,7 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) struct net_device *ndev = (struct net_device *)dev_id; struct xcan_priv *priv = netdev_priv(ndev); u32 isr, ier; + u32 isr_errors; /* Get the interrupt status from Xilinx CAN */ isr = priv->read_reg(priv, XCAN_ISR_OFFSET); @@ -955,11 +956,10 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) xcan_tx_interrupt(ndev, isr); /* Check for the type of error interrupt and Processing it */ - if (isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK | - XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK)) { - priv->write_reg(priv, XCAN_ICR_OFFSET, (XCAN_IXR_ERROR_MASK | - XCAN_IXR_RXOFLW_MASK | XCAN_IXR_BSOFF_MASK | - XCAN_IXR_ARBLST_MASK)); + isr_errors = isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK | + XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK); + if (isr_errors) { + priv->write_reg(priv, XCAN_ICR_OFFSET, isr_errors); xcan_err_interrupt(ndev, isr); } From 264dc1588925388709eeddd51901042ca277c828 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Mon, 26 Feb 2018 14:27:13 +0200 Subject: [PATCH 21/24] can: xilinx_can: fix RX overflow interrupt not being enabled commit 83997997252f5d3fc7f04abc24a89600c2b504ab upstream. RX overflow interrupt (RXOFLW) is disabled even though xcan_interrupt() processes it. This means that an RX overflow interrupt will only be processed when another interrupt gets asserted (e.g. for RX/TX). Fix that by enabling the RXOFLW interrupt. Fixes: b1201e44f50b ("can: xilinx CAN controller support") Signed-off-by: Anssi Hannula Cc: Michal Simek Cc: Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/xilinx_can.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index a7286d72ed7b..700b98d9c250 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -103,7 +103,7 @@ enum xcan_reg { #define XCAN_INTR_ALL (XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\ XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \ XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \ - XCAN_IXR_ARBLST_MASK) + XCAN_IXR_RXOFLW_MASK | XCAN_IXR_ARBLST_MASK) /* CAN register bit shift - XCAN___SHIFT */ #define XCAN_BTR_SJW_SHIFT 7 /* Synchronous jump width */ From d41d0fe374d4fc358cfdae80fd39fd98174d3da3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 26 Jul 2018 10:13:22 +0200 Subject: [PATCH 22/24] turn off -Wattribute-alias Starting with gcc-8.1, we get a warning about all system call definitions, which use an alias between functions with incompatible prototypes, e.g.: In file included from ../mm/process_vm_access.c:19: ../include/linux/syscalls.h:211:18: warning: 'sys_process_vm_readv' alias between functions of incompatible types 'long int(pid_t, const struct iovec *, long unsigned int, const struct iovec *, long unsigned int, long unsigned int)' {aka 'long int(int, const struct iovec *, long unsigned int, const struct iovec *, long unsigned int, long unsigned int)'} and 'long int(long int, long int, long int, long int, long int, long int)' [-Wattribute-alias] asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ ^~~ ../include/linux/syscalls.h:207:2: note: in expansion of macro '__SYSCALL_DEFINEx' __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) ^~~~~~~~~~~~~~~~~ ../include/linux/syscalls.h:201:36: note: in expansion of macro 'SYSCALL_DEFINEx' #define SYSCALL_DEFINE6(name, ...) SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) ^~~~~~~~~~~~~~~ ../mm/process_vm_access.c:300:1: note: in expansion of macro 'SYSCALL_DEFINE6' SYSCALL_DEFINE6(process_vm_readv, pid_t, pid, const struct iovec __user *, lvec, ^~~~~~~~~~~~~~~ ../include/linux/syscalls.h:215:18: note: aliased declaration here asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ ^~~ ../include/linux/syscalls.h:207:2: note: in expansion of macro '__SYSCALL_DEFINEx' __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) ^~~~~~~~~~~~~~~~~ ../include/linux/syscalls.h:201:36: note: in expansion of macro 'SYSCALL_DEFINEx' #define SYSCALL_DEFINE6(name, ...) SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) ^~~~~~~~~~~~~~~ ../mm/process_vm_access.c:300:1: note: in expansion of macro 'SYSCALL_DEFINE6' SYSCALL_DEFINE6(process_vm_readv, pid_t, pid, const struct iovec __user *, lvec, This is really noisy and does not indicate a real problem. In the latest mainline kernel, this was addressed by commit bee20031772a ("disable -Wattribute-alias warning for SYSCALL_DEFINEx()"), which seems too invasive to backport. This takes a much simpler approach and just disables the warning across the kernel. Signed-off-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/Makefile b/Makefile index 63f3e2438a26..bee96eda883a 100644 --- a/Makefile +++ b/Makefile @@ -624,6 +624,7 @@ KBUILD_CFLAGS += $(call cc-disable-warning,frame-address,) KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation) KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow) KBUILD_CFLAGS += $(call cc-disable-warning, int-in-bool-context) +KBUILD_CFLAGS += $(call cc-disable-warning, attribute-alias) ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE KBUILD_CFLAGS += -Os From 0ca85fc310e8c24cba10ed241a0188795e177683 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 26 Jul 2018 10:13:23 +0200 Subject: [PATCH 23/24] ARM: fix put_user() for gcc-8 Building kernels before linux-4.7 with gcc-8 results in many build failures when gcc triggers a check that was meant to catch broken compilers: /tmp/ccCGMQmS.s:648: Error: .err encountered According to the discussion in the gcc bugzilla, a local "register asm()" variable is still supposed to be the correct way to force an inline assembly to use a particular register, but marking it 'const' lets the compiler do optimizations that break that, i.e the compiler is free to treat the variable as either 'const' or 'register' in that case. Upstream commit 9f73bd8bb445 ("ARM: uaccess: remove put_user() code duplication") fixed this problem in linux-4.8 as part of a larger change, but seems a little too big to be backported to 4.4. Let's take the simplest fix and change only the one broken line in the same way as newer kernels. Suggested-by: Bernd Edlinger Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=85745 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=86673 Signed-off-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- arch/arm/include/asm/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 35c9db857ebe..cd8b589111ba 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -251,7 +251,7 @@ extern int __put_user_8(void *, unsigned long long); ({ \ unsigned long __limit = current_thread_info()->addr_limit - 1; \ const typeof(*(p)) __user *__tmp_p = (p); \ - register const typeof(*(p)) __r2 asm("r2") = (x); \ + register typeof(*(p)) __r2 asm("r2") = (x); \ register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \ register unsigned long __l asm("r1") = __limit; \ register int __e asm("r0"); \ From ac15b2b23808ee2c3264329b035a8f0f7d7f50e6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 28 Jul 2018 07:45:05 +0200 Subject: [PATCH 24/24] Linux 4.4.145 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index bee96eda883a..be31491a2d67 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 144 +SUBLEVEL = 145 EXTRAVERSION = NAME = Blurry Fish Butt