From 92f724130fac801b97aef580ae5e185a699661c4 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 20 Jul 2018 13:58:21 +0200 Subject: [PATCH 01/34] 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 d071a3a0f876..fc97a11c41c5 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 650321fe96150898c69c58c6684b33edbe689de1 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Thu, 12 Jul 2018 09:33:04 -0700 Subject: [PATCH 02/34] MIPS: Fix off-by-one in pci_resource_to_user() commit 38c0a74fe06da3be133cae3fb7bde6a9438e698b upstream. The MIPS implementation of pci_resource_to_user() introduced in v3.12 by commit 4c2924b725fb ("MIPS: PCI: Use pci_resource_to_user to map pci memory space properly") incorrectly sets *end to the address of the byte after the resource, rather than the last byte of the resource. This results in userland seeing resources as a byte larger than they actually are, for example a 32 byte BAR will be reported by a tool such as lspci as being 33 bytes in size: Region 2: I/O ports at 1000 [disabled] [size=33] Correct this by subtracting one from the calculated end address, reporting the correct address to userland. Signed-off-by: Paul Burton Reported-by: Rui Wang Fixes: 4c2924b725fb ("MIPS: PCI: Use pci_resource_to_user to map pci memory space properly") Cc: James Hogan Cc: Ralf Baechle Cc: Wolfgang Grandegger Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # v3.12+ Patchwork: https://patchwork.linux-mips.org/patch/19829/ Signed-off-by: Greg Kroah-Hartman --- arch/mips/pci/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index f6325fa657fb..64ae8c094a54 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -55,7 +55,7 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, phys_addr_t size = resource_size(rsrc); *start = fixup_bigphys_addr(rsrc->start, size); - *end = rsrc->start + size; + *end = rsrc->start + size - 1; } int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, From 93d94fec94c7df51c7f36f45fdc18994073f47ee Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 23 Jul 2018 16:50:48 +0200 Subject: [PATCH 03/34] 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 3b1f3bc8becb..100c86f1f547 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -497,6 +497,8 @@ 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 eb9046eae581..ea14466cdca8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -576,6 +576,8 @@ 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 03fbf2b8237a3f1689848cf9f2d9bc7c1869e834 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 23 Jul 2018 19:36:48 -0400 Subject: [PATCH 04/34] 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 dd80276a8205..b21e435f428c 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 > (int)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 38062f403ceb..2d3c8fe27583 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -694,13 +694,16 @@ 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 <= (int)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 444987d535bf65b109b60f45406abe1d7f11f1f7 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Tue, 24 Jul 2018 14:27:55 +0300 Subject: [PATCH 05/34] 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 d6b06bef1b69..9d1a7d5ae835 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2916,7 +2916,7 @@ 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 e2ffdd646cf61ae1444d376d1ea1e756a495eff8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 19 Jul 2018 16:04:38 -0700 Subject: [PATCH 06/34] net: skb_segment() should not return NULL [ Upstream commit ff907a11a0d68a749ce1a321f4505c03bf72190c ] syzbot caught a NULL deref [1], caused by skb_segment() skb_segment() has many "goto err;" that assume the @err variable contains -ENOMEM. A successful call to __skb_linearize() should not clear @err, otherwise a subsequent memory allocation error could return NULL. While we are at it, we might use -EINVAL instead of -ENOMEM when MAX_SKB_FRAGS limit is reached. [1] kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN CPU: 0 PID: 13285 Comm: syz-executor3 Not tainted 4.18.0-rc4+ #146 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:tcp_gso_segment+0x3dc/0x1780 net/ipv4/tcp_offload.c:106 Code: f0 ff ff 0f 87 1c fd ff ff e8 00 88 0b fb 48 8b 75 d0 48 b9 00 00 00 00 00 fc ff df 48 8d be 90 00 00 00 48 89 f8 48 c1 e8 03 <0f> b6 14 08 48 8d 86 94 00 00 00 48 89 c6 83 e0 07 48 c1 ee 03 0f RSP: 0018:ffff88019b7fd060 EFLAGS: 00010206 RAX: 0000000000000012 RBX: 0000000000000020 RCX: dffffc0000000000 RDX: 0000000000040000 RSI: 0000000000000000 RDI: 0000000000000090 RBP: ffff88019b7fd0f0 R08: ffff88019510e0c0 R09: ffffed003b5c46d6 R10: ffffed003b5c46d6 R11: ffff8801dae236b3 R12: 0000000000000001 R13: ffff8801d6c581f4 R14: 0000000000000000 R15: ffff8801d6c58128 FS: 00007fcae64d6700(0000) GS:ffff8801dae00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004e8664 CR3: 00000001b669b000 CR4: 00000000001406f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tcp4_gso_segment+0x1c3/0x440 net/ipv4/tcp_offload.c:54 inet_gso_segment+0x64e/0x12d0 net/ipv4/af_inet.c:1342 inet_gso_segment+0x64e/0x12d0 net/ipv4/af_inet.c:1342 skb_mac_gso_segment+0x3b5/0x740 net/core/dev.c:2792 __skb_gso_segment+0x3c3/0x880 net/core/dev.c:2865 skb_gso_segment include/linux/netdevice.h:4099 [inline] validate_xmit_skb+0x640/0xf30 net/core/dev.c:3104 __dev_queue_xmit+0xc14/0x3910 net/core/dev.c:3561 dev_queue_xmit+0x17/0x20 net/core/dev.c:3602 neigh_hh_output include/net/neighbour.h:473 [inline] neigh_output include/net/neighbour.h:481 [inline] ip_finish_output2+0x1063/0x1860 net/ipv4/ip_output.c:229 ip_finish_output+0x841/0xfa0 net/ipv4/ip_output.c:317 NF_HOOK_COND include/linux/netfilter.h:276 [inline] ip_output+0x223/0x880 net/ipv4/ip_output.c:405 dst_output include/net/dst.h:444 [inline] ip_local_out+0xc5/0x1b0 net/ipv4/ip_output.c:124 iptunnel_xmit+0x567/0x850 net/ipv4/ip_tunnel_core.c:91 ip_tunnel_xmit+0x1598/0x3af1 net/ipv4/ip_tunnel.c:778 ipip_tunnel_xmit+0x264/0x2c0 net/ipv4/ipip.c:308 __netdev_start_xmit include/linux/netdevice.h:4148 [inline] netdev_start_xmit include/linux/netdevice.h:4157 [inline] xmit_one net/core/dev.c:3034 [inline] dev_hard_start_xmit+0x26c/0xc30 net/core/dev.c:3050 __dev_queue_xmit+0x29ef/0x3910 net/core/dev.c:3569 dev_queue_xmit+0x17/0x20 net/core/dev.c:3602 neigh_direct_output+0x15/0x20 net/core/neighbour.c:1403 neigh_output include/net/neighbour.h:483 [inline] ip_finish_output2+0xa67/0x1860 net/ipv4/ip_output.c:229 ip_finish_output+0x841/0xfa0 net/ipv4/ip_output.c:317 NF_HOOK_COND include/linux/netfilter.h:276 [inline] ip_output+0x223/0x880 net/ipv4/ip_output.c:405 dst_output include/net/dst.h:444 [inline] ip_local_out+0xc5/0x1b0 net/ipv4/ip_output.c:124 ip_queue_xmit+0x9df/0x1f80 net/ipv4/ip_output.c:504 tcp_transmit_skb+0x1bf9/0x3f10 net/ipv4/tcp_output.c:1168 tcp_write_xmit+0x1641/0x5c20 net/ipv4/tcp_output.c:2363 __tcp_push_pending_frames+0xb2/0x290 net/ipv4/tcp_output.c:2536 tcp_push+0x638/0x8c0 net/ipv4/tcp.c:735 tcp_sendmsg_locked+0x2ec5/0x3f00 net/ipv4/tcp.c:1410 tcp_sendmsg+0x2f/0x50 net/ipv4/tcp.c:1447 inet_sendmsg+0x1a1/0x690 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:641 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:651 __sys_sendto+0x3d7/0x670 net/socket.c:1797 __do_sys_sendto net/socket.c:1809 [inline] __se_sys_sendto net/socket.c:1805 [inline] __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1805 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x455ab9 Code: 1d ba fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb b9 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fcae64d5c68 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007fcae64d66d4 RCX: 0000000000455ab9 RDX: 0000000000000001 RSI: 0000000020000200 RDI: 0000000000000013 RBP: 000000000072bea0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000014 R13: 00000000004c1145 R14: 00000000004d1818 R15: 0000000000000006 Modules linked in: Dumping ftrace buffer: (ftrace buffer empty) Fixes: ddff00d42043 ("net: Move skb_has_shared_frag check out of GRE code and into segmentation") Signed-off-by: Eric Dumazet Cc: Alexander Duyck Reported-by: syzbot Acked-by: Alexander Duyck Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/skbuff.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8cae7aa4a4ec..84c731aef0d8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3253,6 +3253,7 @@ normal: net_warn_ratelimited( "skb_segment: too many frags: %u %u\n", pos, mss); + err = -EINVAL; goto err; } @@ -3289,11 +3290,10 @@ skip_fraglist: perform_csum_check: if (!csum) { - if (skb_has_shared_frag(nskb)) { - err = __skb_linearize(nskb); - if (err) - goto err; - } + if (skb_has_shared_frag(nskb) && + __skb_linearize(nskb)) + goto err; + if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = From adcecd4ab150f4e2dfdb2fcbf3f1394de6f9dd7a Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Mon, 25 Jun 2018 19:12:02 +0300 Subject: [PATCH 07/34] net/mlx5: Adjust clock overflow work period [ Upstream commit 33180bee86a8940a84950edca46315cd9dd6deb5 ] When driver converts HW timestamp to wall clock time it subtracts the last saved cycle counter from the HW timestamp and converts the difference to nanoseconds. The conversion is done by multiplying the cycles difference with the clock multiplier value as a first step and therefore the cycles difference should be small enough so that the multiplication product doesn't exceed 64bit. The overflow handling routine is in charge of updating the last saved cycle counter in driver and it is called periodically using kernel delayed workqueue. The delay period for this work is calculated using the max HW cycle counter value (a 41 bit mask) as a base which doesn't take the 64bit limit into account so the delay period may be incorrect and too long to prevent a large difference between the HW counter and the last saved counter in SW. This change adjusts the work period for the HW clock overflow work by taking the minimum between the previous value and the quotient of max u64 value and the clock multiplier value. Fixes: ef9814deafd0 ("net/mlx5e: Add HW timestamping (TS) support") Signed-off-by: Ariel Levkovich Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/en_clock.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c index 1612ec0d9103..f8b99d0b54d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c @@ -233,6 +233,7 @@ static void mlx5e_timestamp_init_config(struct mlx5e_tstamp *tstamp) void mlx5e_timestamp_init(struct mlx5e_priv *priv) { struct mlx5e_tstamp *tstamp = &priv->tstamp; + u64 overflow_cycles; u64 ns; u64 frac = 0; u32 dev_freq; @@ -257,10 +258,17 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv) /* Calculate period in seconds to call the overflow watchdog - to make * sure counter is checked at least once every wrap around. + * The period is calculated as the minimum between max HW cycles count + * (The clock source mask) and max amount of cycles that can be + * multiplied by clock multiplier where the result doesn't exceed + * 64bits. */ - ns = cyclecounter_cyc2ns(&tstamp->cycles, tstamp->cycles.mask, + overflow_cycles = div64_u64(~0ULL >> 1, tstamp->cycles.mult); + overflow_cycles = min(overflow_cycles, tstamp->cycles.mask >> 1); + + ns = cyclecounter_cyc2ns(&tstamp->cycles, overflow_cycles, frac, &frac); - do_div(ns, NSEC_PER_SEC / 2 / HZ); + do_div(ns, NSEC_PER_SEC / HZ); tstamp->overflow_period = ns; INIT_DELAYED_WORK(&tstamp->overflow_work, mlx5e_timestamp_overflow); From d9d580121617d95aade9aa839d4e405521eafcb8 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Sun, 8 Jul 2018 14:52:12 +0300 Subject: [PATCH 08/34] net/mlx5e: Don't allow aRFS for encapsulated packets [ Upstream commit d2e1c57bcf9a07cbb67f30ecf238f298799bce1c ] Driver is yet to support aRFS for encapsulated packets, return early error in such case. Fixes: 18c908e477dc ("net/mlx5e: Add accelerated RFS support") Signed-off-by: Eran Ben Elisha Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index a8cb38789774..885f47e9ae93 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -715,6 +715,9 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, skb->protocol != htons(ETH_P_IPV6)) return -EPROTONOSUPPORT; + if (skb->encapsulation) + return -EPROTONOSUPPORT; + arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol); if (!arfs_t) return -EPROTONOSUPPORT; From b7e37add79bf1a2c9f4a7574b0d7f53f0f6df663 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Sun, 8 Jul 2018 13:08:55 +0300 Subject: [PATCH 09/34] net/mlx5e: Fix quota counting in aRFS expire flow [ Upstream commit 2630bae8018823c3b88788b69fb9f16ea3b4a11e ] Quota should follow the amount of rules which do expire, and not the number of rules that were examined, fixed that. Fixes: 18c908e477dc ("net/mlx5e: Add accelerated RFS support") Signed-off-by: Eran Ben Elisha Reviewed-by: Maor Gottlieb Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 885f47e9ae93..4a51fc6908ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -383,14 +383,14 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv) HLIST_HEAD(del_list); spin_lock_bh(&priv->fs.arfs.arfs_lock); mlx5e_for_each_arfs_rule(arfs_rule, htmp, priv->fs.arfs.arfs_tables, i, j) { - if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA) - break; if (!work_pending(&arfs_rule->arfs_work) && rps_may_expire_flow(priv->netdev, arfs_rule->rxq, arfs_rule->flow_id, arfs_rule->filter_id)) { hlist_del_init(&arfs_rule->hlist); hlist_add_head(&arfs_rule->hlist, &del_list); + if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA) + break; } } spin_unlock_bh(&priv->fs.arfs.arfs_lock); From cc403d5dc140ba74400335b84b91f97d07dbd569 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 20 Jul 2018 14:04:27 +0800 Subject: [PATCH 10/34] multicast: do not restore deleted record source filter mode to new one There are two scenarios that we will restore deleted records. The first is when device down and up(or unmap/remap). In this scenario the new filter mode is same with previous one. Because we get it from in_dev->mc_list and we do not touch it during device down and up. The other scenario is when a new socket join a group which was just delete and not finish sending status reports. In this scenario, we should use the current filter mode instead of restore old one. Here are 4 cases in total. old_socket new_socket before_fix after_fix IN(A) IN(A) ALLOW(A) ALLOW(A) IN(A) EX( ) TO_IN( ) TO_EX( ) EX( ) IN(A) TO_EX( ) ALLOW(A) EX( ) EX( ) TO_EX( ) TO_EX( ) Fixes: 24803f38a5c0b (igmp: do not remove igmp souce list info when set link down) Fixes: 1666d49e1d416 (mld: do not remove mld souce list info when set link down) Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/igmp.c | 3 +-- net/ipv6/mcast.c | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 7f5fe07d0b13..f2e6e874e4ec 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1193,8 +1193,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) if (pmc) { im->interface = pmc->interface; im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - im->sfmode = pmc->sfmode; - if (pmc->sfmode == MCAST_INCLUDE) { + if (im->sfmode == MCAST_INCLUDE) { im->tomb = pmc->tomb; im->sources = pmc->sources; for (psf = im->sources; psf; psf = psf->sf_next) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index ca8fac6e5a09..918c161e5b55 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -771,8 +771,7 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) if (pmc) { im->idev = pmc->idev; im->mca_crcount = idev->mc_qrv; - im->mca_sfmode = pmc->mca_sfmode; - if (pmc->mca_sfmode == MCAST_INCLUDE) { + if (im->mca_sfmode == MCAST_INCLUDE) { im->mca_tomb = pmc->mca_tomb; im->mca_sources = pmc->mca_sources; for (psf = im->mca_sources; psf; psf = psf->sf_next) From c6ac36be72e46082bedd4433ccba9925bbf6a322 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 19 Jul 2018 08:15:16 +0200 Subject: [PATCH 11/34] net: phy: consider PHY_IGNORE_INTERRUPT in phy_start_aneg_priv [ Upstream commit 215d08a85b9acf5e1fe9dbf50f1774cde333efef ] The situation described in the comment can occur also with PHY_IGNORE_INTERRUPT, therefore change the condition to include it. Fixes: f555f34fdc58 ("net: phy: fix auto-negotiation stall due to unavailable interrupt") Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/phy/phy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 4d217649c8b1..5fde8e335f13 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -598,7 +598,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync) * negotiation may already be done and aneg interrupt may not be * generated. */ - if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) { + if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) { err = phy_aneg_done(phydev); if (err > 0) { trigger = true; From 19b74799159ab6f780fedd568adf00cdee9edd5a Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Fri, 20 Jul 2018 13:21:01 -0700 Subject: [PATCH 12/34] 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 f3a0ad14b454..194e844e1021 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2339,9 +2339,12 @@ 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 841778018235f7328a8be29cbdaa36c7703d064c Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 12 Jul 2018 06:04:52 -0700 Subject: [PATCH 13/34] 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 ab37c6775630..e42f800b5dda 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 1fcccc57866bd5c31ec09df7accdfecb0d222a85 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 18 Jul 2018 13:56:34 -0700 Subject: [PATCH 14/34] 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 f07a0a1c98ff..ea78ef3195a4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -905,8 +905,8 @@ 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; @@ -969,7 +969,7 @@ 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); @@ -1046,6 +1046,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, return 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, @@ -3482,7 +3489,7 @@ 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; @@ -3520,7 +3527,12 @@ 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, (__force gfp_t)0); + __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, 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 57ec8824b14d76089d1fd0d963ccc2d084070e57 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 18 Jul 2018 13:56:35 -0700 Subject: [PATCH 15/34] 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 18f029bcb8c7..fd575bc80745 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -553,6 +553,7 @@ 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 e42f800b5dda..f87d2a61543b 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 ea78ef3195a4..5f916953b28e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -174,8 +174,13 @@ 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); } @@ -1010,7 +1015,7 @@ 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); @@ -3529,12 +3534,12 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) skb_mstamp_get(&buff->skb_mstamp); __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, 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 8736711f4e55a50e0ec89edd366256f8edb5f9c3 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 18 Jul 2018 13:56:36 -0700 Subject: [PATCH 16/34] 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 fd575bc80745..5d440bb0e409 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -363,6 +363,7 @@ 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 f87d2a61543b..dd52ccb812ea 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 be453aa8fce8..71f2b0958c4f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -209,13 +209,14 @@ 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 2d08921c8da26bdce3d8848ef6f32068f594d7d4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 23 Jul 2018 09:28:17 -0700 Subject: [PATCH 17/34] tcp: free batches of packets in tcp_prune_ofo_queue() [ Upstream commit 72cd43ba64fc172a443410ce01645895850844c8 ] Juha-Matti Tilli reported that malicious peers could inject tiny packets in out_of_order_queue, forcing very expensive calls to tcp_collapse_ofo_queue() and tcp_prune_ofo_queue() for every incoming packet. out_of_order_queue rb-tree can contain thousands of nodes, iterating over all of them is not nice. Before linux-4.9, we would have pruned all packets in ofo_queue in one go, every XXXX packets. XXXX depends on sk_rcvbuf and skbs truesize, but is about 7000 packets with tcp_rmem[2] default of 6 MB. Since we plan to increase tcp_rmem[2] in the future to cope with modern BDP, can not revert to the old behavior, without great pain. Strategy taken in this patch is to purge ~12.5 % of the queue capacity. Fixes: 36a6503fedda ("tcp: refine tcp_prune_ofo_queue() to not drop all packets") Signed-off-by: Eric Dumazet Reported-by: Juha-Matti Tilli Acked-by: Yuchung Cheng Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/skbuff.h | 2 ++ net/ipv4/tcp_input.c | 15 +++++++++++---- 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b048d3d3b327..1f207dd22757 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2982,6 +2982,8 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) return __skb_grow(skb, len); } +#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) + #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 71f2b0958c4f..2eabf219b71d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4965,6 +4965,7 @@ new_range: * 2) not add too big latencies if thousands of packets sit there. * (But if application shrinks SO_RCVBUF, we could still end up * freeing whole queue here) + * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks. * * Return true if queue has shrunk. */ @@ -4972,20 +4973,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct rb_node *node, *prev; + int goal; if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) return false; NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); + goal = sk->sk_rcvbuf >> 3; node = &tp->ooo_last_skb->rbnode; do { prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); + goal -= rb_to_skb(node)->truesize; tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode)); - sk_mem_reclaim(sk); - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && - !tcp_under_memory_pressure(sk)) - break; + if (!prev || goal <= 0) { + sk_mem_reclaim(sk); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && + !tcp_under_memory_pressure(sk)) + break; + goal = sk->sk_rcvbuf >> 3; + } node = prev; } while (node); tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode); From fdf258ed5dd85b57cf0e0e66500be98d38d42d02 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 23 Jul 2018 09:28:18 -0700 Subject: [PATCH 18/34] 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 2eabf219b71d..0a1ab0522511 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5027,6 +5027,9 @@ 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, NULL, From a878681484a0992ee3dfbd7826439951f9f82a69 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 23 Jul 2018 09:28:19 -0700 Subject: [PATCH 19/34] 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 | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0a1ab0522511..d0c47c2fefd2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4918,6 +4918,7 @@ end: 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, *head; struct rb_node *p; u32 start, end; @@ -4936,6 +4937,7 @@ new_range: } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; + range_truesize = skb->truesize; for (head = skb;;) { skb = tcp_skb_next(skb, NULL); @@ -4946,11 +4948,20 @@ new_range: if (!skb || after(TCP_SKB_CB(skb)->seq, end) || before(TCP_SKB_CB(skb)->end_seq, start)) { - tcp_collapse(sk, NULL, &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, NULL, &tp->out_of_order_queue, + head, skb, start, end); + } else { + sum_tiny += range_truesize; + if (sum_tiny > sk->sk_rcvbuf >> 3) + return; + } goto new_range; } + range_truesize += skb->truesize; if (unlikely(before(TCP_SKB_CB(skb)->seq, start))) start = TCP_SKB_CB(skb)->seq; if (after(TCP_SKB_CB(skb)->end_seq, end)) From 94623c7463f3424776408df2733012c42b52395a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 23 Jul 2018 09:28:20 -0700 Subject: [PATCH 20/34] tcp: call tcp_drop() from tcp_data_queue_ofo() [ Upstream commit 8541b21e781a22dce52a74fef0b9bed00404a1cd ] In order to be able to give better diagnostics and detect malicious traffic, we need to have better sk->sk_drops tracking. Fixes: 9f5afeae5152 ("tcp: use an RB tree for ooo receive queue") 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 | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d0c47c2fefd2..44d136fd2af5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4517,7 +4517,7 @@ coalesce_done: /* All the bits are present. Drop. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb); + tcp_drop(sk, skb); skb = NULL; tcp_dsack_set(sk, seq, end_seq); goto add_sack; @@ -4536,7 +4536,7 @@ coalesce_done: TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb1); + tcp_drop(sk, skb1); goto merge_right; } } else if (tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { From b0bd06a4757e4356569c2a73bc535f090dec5fa8 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Tue, 10 Jul 2018 08:28:49 +0200 Subject: [PATCH 21/34] 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 08bef18372ea..a9c950d29ce2 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1785,6 +1785,9 @@ 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 e2996cf59ebf6564002f6bdf9ebb16336cae62e1 Mon Sep 17 00:00:00 2001 From: Bin Liu Date: Thu, 19 Jul 2018 14:39:37 -0500 Subject: [PATCH 22/34] 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 8bf0090218dd..bdb19db542a4 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1139,10 +1139,14 @@ 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 9e10043b6bdcc1a991a029de8a0bc745950345c6 Mon Sep 17 00:00:00 2001 From: Jerry Zhang Date: Mon, 2 Jul 2018 12:48:08 -0700 Subject: [PATCH 23/34] 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 af72224f8ba2..04eb64381d92 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3243,7 +3243,7 @@ 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 bool ffs_func_req_match(struct usb_function *f, From bf0070e2f56eb3da708978da5dab5d36bbed1bf6 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 10 Jul 2018 14:51:33 +0200 Subject: [PATCH 24/34] 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 d76cd97a98b6..ee25a69630c3 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -363,14 +363,6 @@ re_probe: 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 de2219a86c0ba1d07e16e81011b0749b867f76c5 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Tue, 7 Feb 2017 17:01:14 +0200 Subject: [PATCH 25/34] 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 c71a03593595..556ef6481117 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -101,7 +101,7 @@ 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 */ @@ -709,15 +709,7 @@ 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); } @@ -728,7 +720,7 @@ 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; @@ -800,9 +792,9 @@ 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 1fadfbd9f593903e84f66d4e6902193886c5de1c Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Thu, 17 May 2018 15:41:19 +0300 Subject: [PATCH 26/34] can: xilinx_can: fix power management handling commit 8ebd83bdb027f29870d96649dba18b91581ea829 upstream. There are several issues with the suspend/resume handling code of the driver: - The device is attached and detached in the runtime_suspend() and runtime_resume() callbacks if the interface is running. However, during xcan_chip_start() the interface is considered running, causing the resume handler to incorrectly call netif_start_queue() at the beginning of xcan_chip_start(), and on xcan_chip_start() error return the suspend handler detaches the device leaving the user unable to bring-up the device anymore. - The device is not brought properly up on system resume. A reset is done and the code tries to determine the bus state after that. However, after reset the device is always in Configuration mode (down), so the state checking code does not make sense and communication will also not work. - The suspend callback tries to set the device to sleep mode (low-power mode which monitors the bus and brings the device back to normal mode on activity), but then immediately disables the clocks (possibly before the device reaches the sleep mode), which does not make sense to me. If a clean shutdown is wanted before disabling clocks, we can just bring it down completely instead of only sleep mode. Reorganize the PM code so that only the clock logic remains in the runtime PM callbacks and the system PM callbacks contain the device bring-up/down logic. This makes calling the runtime PM callbacks during e.g. xcan_chip_start() safe. The system PM callbacks now simply call common code to start/stop the HW if the interface was running, replacing the broken code from before. xcan_chip_stop() is updated to use the common reset code so that it will wait for the reset to complete. Reset also disables all interrupts so do not do that separately. Also, the device_may_wakeup() checks are removed as the driver does not have wakeup support. Tested on Zynq-7000 integrated CAN. 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 | 69 +++++++++++++++--------------------- 1 file changed, 28 insertions(+), 41 deletions(-) diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 556ef6481117..363bc8b1bc03 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -811,13 +811,9 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) static void xcan_chip_stop(struct net_device *ndev) { struct xcan_priv *priv = netdev_priv(ndev); - u32 ier; /* Disable interrupts and leave the can in configuration mode */ - ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier &= ~XCAN_INTR_ALL; - priv->write_reg(priv, XCAN_IER_OFFSET, ier); - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); + set_reset_mode(ndev); priv->can.state = CAN_STATE_STOPPED; } @@ -950,10 +946,15 @@ static const struct net_device_ops xcan_netdev_ops = { */ static int __maybe_unused xcan_suspend(struct device *dev) { - if (!device_may_wakeup(dev)) - return pm_runtime_force_suspend(dev); + struct net_device *ndev = dev_get_drvdata(dev); - return 0; + if (netif_running(ndev)) { + netif_stop_queue(ndev); + netif_device_detach(ndev); + xcan_chip_stop(ndev); + } + + return pm_runtime_force_suspend(dev); } /** @@ -965,11 +966,27 @@ static int __maybe_unused xcan_suspend(struct device *dev) */ static int __maybe_unused xcan_resume(struct device *dev) { - if (!device_may_wakeup(dev)) - return pm_runtime_force_resume(dev); + struct net_device *ndev = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_force_resume(dev); + if (ret) { + dev_err(dev, "pm_runtime_force_resume failed on resume\n"); + return ret; + } + + if (netif_running(ndev)) { + ret = xcan_chip_start(ndev); + if (ret) { + dev_err(dev, "xcan_chip_start failed on resume\n"); + return ret; + } + + netif_device_attach(ndev); + netif_start_queue(ndev); + } return 0; - } /** @@ -984,14 +1001,6 @@ static int __maybe_unused xcan_runtime_suspend(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct xcan_priv *priv = netdev_priv(ndev); - if (netif_running(ndev)) { - netif_stop_queue(ndev); - netif_device_detach(ndev); - } - - priv->write_reg(priv, XCAN_MSR_OFFSET, XCAN_MSR_SLEEP_MASK); - priv->can.state = CAN_STATE_SLEEPING; - clk_disable_unprepare(priv->bus_clk); clk_disable_unprepare(priv->can_clk); @@ -1010,7 +1019,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct xcan_priv *priv = netdev_priv(ndev); int ret; - u32 isr, status; ret = clk_prepare_enable(priv->bus_clk); if (ret) { @@ -1024,27 +1032,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev) return ret; } - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); - isr = priv->read_reg(priv, XCAN_ISR_OFFSET); - status = priv->read_reg(priv, XCAN_SR_OFFSET); - - if (netif_running(ndev)) { - if (isr & XCAN_IXR_BSOFF_MASK) { - priv->can.state = CAN_STATE_BUS_OFF; - priv->write_reg(priv, XCAN_SRR_OFFSET, - XCAN_SRR_RESET_MASK); - } else if ((status & XCAN_SR_ESTAT_MASK) == - XCAN_SR_ESTAT_MASK) { - priv->can.state = CAN_STATE_ERROR_PASSIVE; - } else if (status & XCAN_SR_ERRWRN_MASK) { - priv->can.state = CAN_STATE_ERROR_WARNING; - } else { - priv->can.state = CAN_STATE_ERROR_ACTIVE; - } - netif_device_attach(ndev); - netif_start_queue(ndev); - } - return 0; } From c98f577204b4bdc46453c2f64fa760fa17721046 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Wed, 8 Feb 2017 13:13:40 +0200 Subject: [PATCH 27/34] 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 363bc8b1bc03..9e64929d1e9f 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. @@ -529,6 +530,123 @@ 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 @@ -544,16 +662,12 @@ 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; @@ -563,28 +677,10 @@ 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 */ @@ -714,8 +810,10 @@ 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); @@ -746,6 +844,7 @@ 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 1fd9fa57c1d97938b877018324809bafd59e15f5 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Tue, 7 Feb 2017 13:23:04 +0200 Subject: [PATCH 28/34] 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 9e64929d1e9f..88c7c2f5901e 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -696,7 +696,6 @@ 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 bee7ff7eaade2f51d0a4b485642e06b6d2b2d125 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Thu, 23 Feb 2017 14:50:03 +0200 Subject: [PATCH 29/34] 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 88c7c2f5901e..ad36c68e55e0 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 @@ -119,6 +121,7 @@ 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 @@ -133,6 +136,7 @@ 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; @@ -160,6 +164,11 @@ 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 @@ -239,6 +248,10 @@ 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; } @@ -393,6 +406,7 @@ 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; @@ -440,6 +454,9 @@ 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 */ @@ -455,10 +472,16 @@ 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; } @@ -832,19 +855,71 @@ 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); } /** @@ -1138,6 +1213,18 @@ static const struct dev_pm_ops xcan_dev_pm_ops = { SET_RUNTIME_PM_OPS(xcan_runtime_suspend, xcan_runtime_resume, NULL) }; +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 @@ -1152,8 +1239,10 @@ 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); @@ -1163,7 +1252,8 @@ 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; @@ -1171,6 +1261,30 @@ 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) @@ -1185,6 +1299,7 @@ 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); @@ -1249,9 +1364,9 @@ static int xcan_probe(struct platform_device *pdev) pm_runtime_put(&pdev->dev); - 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; @@ -1285,14 +1400,6 @@ 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 9f7308434ed6922545e00562a9a6ccd0aa3759da Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Mon, 26 Feb 2018 14:39:59 +0200 Subject: [PATCH 30/34] 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 ad36c68e55e0..8a6264c10777 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -938,6 +938,7 @@ 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); @@ -956,11 +957,10 @@ 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 b2019f0f7021b5ca9da3173ace7fcf97aa1d4923 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Mon, 26 Feb 2018 14:27:13 +0200 Subject: [PATCH 31/34] 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 8a6264c10777..e680bab27dd7 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -104,7 +104,7 @@ 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 b1a1d9bdb1b5123924956f069920bf4b9c4b11c4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 26 Jul 2018 10:13:22 +0200 Subject: [PATCH 32/34] 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 889c58e39928..db7f6eeeaa1a 100644 --- a/Makefile +++ b/Makefile @@ -635,6 +635,7 @@ 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_LD_DEAD_CODE_DATA_ELIMINATION KBUILD_CFLAGS += $(call cc-option,-ffunction-sections,) From b9dd13488acb680c5f141f5c077880317c9749cf Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 14 Dec 2017 15:32:41 -0800 Subject: [PATCH 33/34] exec: avoid gcc-8 warning for get_task_comm commit 3756f6401c302617c5e091081ca4d26ab604bec5 upstream. gcc-8 warns about using strncpy() with the source size as the limit: fs/exec.c:1223:32: error: argument to 'sizeof' in 'strncpy' call is the same expression as the source; did you mean to use the size of the destination? [-Werror=sizeof-pointer-memaccess] This is indeed slightly suspicious, as it protects us from source arguments without NUL-termination, but does not guarantee that the destination is terminated. This keeps the strncpy() to ensure we have properly padded target buffer, but ensures that we use the correct length, by passing the actual length of the destination buffer as well as adding a build-time check to ensure it is exactly TASK_COMM_LEN. There are only 23 callsites which I all reviewed to ensure this is currently the case. We could get away with doing only the check or passing the right length, but it doesn't hurt to do both. Link: http://lkml.kernel.org/r/20171205151724.1764896-1-arnd@arndb.de Signed-off-by: Arnd Bergmann Suggested-by: Kees Cook Acked-by: Kees Cook Acked-by: Ingo Molnar Cc: Alexander Viro Cc: Peter Zijlstra Cc: Serge Hallyn Cc: James Morris Cc: Aleksa Sarai Cc: "Eric W. Biederman" Cc: Frederic Weisbecker Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/exec.c | 7 +++---- include/linux/sched.h | 6 +++++- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/fs/exec.c b/fs/exec.c index b8c43be24751..fcd8642ef2d2 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1228,15 +1228,14 @@ killed: return -EAGAIN; } -char *get_task_comm(char *buf, struct task_struct *tsk) +char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk) { - /* buf must be at least sizeof(tsk->comm) in size */ task_lock(tsk); - strncpy(buf, tsk->comm, sizeof(tsk->comm)); + strncpy(buf, tsk->comm, buf_size); task_unlock(tsk); return buf; } -EXPORT_SYMBOL_GPL(get_task_comm); +EXPORT_SYMBOL_GPL(__get_task_comm); /* * These functions flushes out all traces of the currently running executable diff --git a/include/linux/sched.h b/include/linux/sched.h index 5ebef8c86c26..1cc5723a7821 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2999,7 +2999,11 @@ static inline void set_task_comm(struct task_struct *tsk, const char *from) { __set_task_comm(tsk, from, false); } -extern char *get_task_comm(char *to, struct task_struct *tsk); +extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk); +#define get_task_comm(buf, tsk) ({ \ + BUILD_BUG_ON(sizeof(buf) != TASK_COMM_LEN); \ + __get_task_comm(buf, sizeof(buf), tsk); \ +}) #ifdef CONFIG_SMP void scheduler_ipi(void); From 94c67449c7550597e86f15cce923055f7b2c8e09 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 28 Jul 2018 07:49:14 +0200 Subject: [PATCH 34/34] Linux 4.9.116 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index db7f6eeeaa1a..a6b011778960 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 9 -SUBLEVEL = 115 +SUBLEVEL = 116 EXTRAVERSION = NAME = Roaring Lionus