From a39e17b2d842938e19997d2fdc0443fdd4cd8d10 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 27 Nov 2017 12:10:23 -0800 Subject: bpf: offload: add a license header I forgot to add a license on kernel/bpf/offload.c. Luckily I'm still the only author so make it explicitly GPLv2. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: Daniel Borkmann --- kernel/bpf/offload.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 68ec884440b7..8455b89d1bbf 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -1,3 +1,18 @@ +/* + * Copyright (C) 2017 Netronome Systems, Inc. + * + * This software is licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree. + * + * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" + * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, + * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE + * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME + * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + */ + #include #include #include -- cgit v1.2.3 From 3d7682af228fd78dc46bc6bf40e0268ad04521ec Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 29 Nov 2017 14:25:50 +0000 Subject: rxrpc: Clean up whitespace Clean up some whitespace from rxrpc. Signed-off-by: David Howells --- net/rxrpc/call_event.c | 2 +- net/rxrpc/conn_object.c | 2 +- net/rxrpc/input.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index bda952ffe6a6..555274ddc514 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -426,7 +426,7 @@ recheck_state: next = call->expect_rx_by; #define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; } - + set(call->expect_req_by); set(call->expect_term_by); set(call->ack_at); diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 1aad04a32d5e..c628351eb900 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -424,7 +424,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) if (earliest != now + MAX_JIFFY_OFFSET) { _debug("reschedule reaper %ld", (long)earliest - (long)now); ASSERT(time_after(earliest, now)); - rxrpc_set_service_reap_timer(rxnet, earliest); + rxrpc_set_service_reap_timer(rxnet, earliest); } while (!list_empty(&graveyard)) { diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 23a5e61d8f79..6fc61400337f 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -976,7 +976,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, rxrpc_reduce_call_timer(call, expect_rx_by, now, rxrpc_timer_set_for_normal); } - + switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_DATA: rxrpc_input_data(call, skb, skew); @@ -1213,7 +1213,7 @@ void rxrpc_data_ready(struct sock *udp_sk) goto reupgrade; conn->service_id = sp->hdr.serviceId; } - + if (sp->hdr.callNumber == 0) { /* Connection-level packet */ _debug("CONN %p {%d}", conn, conn->debug_id); -- cgit v1.2.3 From 5fc62f6a139a7b06b027bf442cd4205619506f59 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 29 Nov 2017 14:40:41 +0000 Subject: rxrpc: Fix ACK generation from the connection event processor Repeat terminal ACKs and now terminal ACKs are now generated from the connection event processor rather from call handling as this allows us to discard client call structures as soon as possible and free up the channel for a follow on call. However, in ACKs so generated, the additional information trailer is malformed because the padding that's meant to be in the middle isn't included in what's transmitted. Fix it so that the 3 bytes of padding are included in the transmission. Further, the trailer is misaligned because of the padding, so assigment to the u16 and u32 fields inside it might cause problems on some arches, so fix this by breaking the padding and the trailer out of the packed struct. (This also deals with potential compiler weirdies where some of the nested structs are packed and some aren't). The symptoms can be seen in wireshark as terminal DUPLICATE or IDLE ACK packets in which the Max MTU, Interface MTU and rwind fields have weird values and the Max Packets field is apparently missing. Reported-by: Jeffrey Altman Signed-off-by: David Howells --- net/rxrpc/conn_event.c | 50 +++++++++++++++++++++++++++++--------------------- 1 file changed, 29 insertions(+), 21 deletions(-) diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 9e9a8db1bc9c..4ca11be6be3c 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -30,22 +30,18 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct rxrpc_skb_priv *sp = skb ? rxrpc_skb(skb) : NULL; struct rxrpc_channel *chan; struct msghdr msg; - struct kvec iov; + struct kvec iov[3]; struct { struct rxrpc_wire_header whdr; union { - struct { - __be32 code; - } abort; - struct { - struct rxrpc_ackpacket ack; - u8 padding[3]; - struct rxrpc_ackinfo info; - }; + __be32 abort_code; + struct rxrpc_ackpacket ack; }; } __attribute__((packed)) pkt; + struct rxrpc_ackinfo ack_info; size_t len; - u32 serial, mtu, call_id; + int ioc; + u32 serial, mtu, call_id, padding; _enter("%d", conn->debug_id); @@ -66,6 +62,13 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, msg.msg_controllen = 0; msg.msg_flags = 0; + iov[0].iov_base = &pkt; + iov[0].iov_len = sizeof(pkt.whdr); + iov[1].iov_base = &padding; + iov[1].iov_len = 3; + iov[2].iov_base = &ack_info; + iov[2].iov_len = sizeof(ack_info); + pkt.whdr.epoch = htonl(conn->proto.epoch); pkt.whdr.cid = htonl(conn->proto.cid); pkt.whdr.callNumber = htonl(call_id); @@ -80,8 +83,10 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, len = sizeof(pkt.whdr); switch (chan->last_type) { case RXRPC_PACKET_TYPE_ABORT: - pkt.abort.code = htonl(chan->last_abort); - len += sizeof(pkt.abort); + pkt.abort_code = htonl(chan->last_abort); + iov[0].iov_len += sizeof(pkt.abort_code); + len += sizeof(pkt.abort_code); + ioc = 1; break; case RXRPC_PACKET_TYPE_ACK: @@ -94,13 +99,19 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, pkt.ack.serial = htonl(skb ? sp->hdr.serial : 0); pkt.ack.reason = skb ? RXRPC_ACK_DUPLICATE : RXRPC_ACK_IDLE; pkt.ack.nAcks = 0; - pkt.info.rxMTU = htonl(rxrpc_rx_mtu); - pkt.info.maxMTU = htonl(mtu); - pkt.info.rwind = htonl(rxrpc_rx_window_size); - pkt.info.jumbo_max = htonl(rxrpc_rx_jumbo_max); + ack_info.rxMTU = htonl(rxrpc_rx_mtu); + ack_info.maxMTU = htonl(mtu); + ack_info.rwind = htonl(rxrpc_rx_window_size); + ack_info.jumbo_max = htonl(rxrpc_rx_jumbo_max); pkt.whdr.flags |= RXRPC_SLOW_START_OK; - len += sizeof(pkt.ack) + sizeof(pkt.info); + padding = 0; + iov[0].iov_len += sizeof(pkt.ack); + len += sizeof(pkt.ack) + 3 + sizeof(ack_info); + ioc = 3; break; + + default: + return; } /* Resync with __rxrpc_disconnect_call() and check that the last call @@ -110,9 +121,6 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, if (READ_ONCE(chan->last_call) != call_id) return; - iov.iov_base = &pkt; - iov.iov_len = len; - serial = atomic_inc_return(&conn->serial); pkt.whdr.serial = htonl(serial); @@ -127,7 +135,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, break; } - kernel_sendmsg(conn->params.local->socket, &msg, &iov, 1, len); + kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len); _leave(""); return; } -- cgit v1.2.3 From 282ef4729195c8503f7101d574acfb5e7c8a8209 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 28 Nov 2017 11:28:52 -0600 Subject: rxrpc: Fix variable overwrite Values assigned to both variable resend_at and ack_at are overwritten before they can be used. The correct fix here is to add 'now' to the previously computed value in resend_at and ack_at. Addresses-Coverity-ID: 1462262 Addresses-Coverity-ID: 1462263 Addresses-Coverity-ID: 1462264 Fixes: beb8e5e4f38c ("rxrpc: Express protocol timeouts in terms of RTT") Link: https://marc.info/?i=17004.1511808959%40warthog.procyon.org.uk Signed-off-by: Gustavo A. R. Silva Signed-off-by: David Howells --- net/rxrpc/call_event.c | 2 +- net/rxrpc/sendmsg.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 555274ddc514..ad2ab1103189 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -123,7 +123,7 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, else ack_at = expiry; - ack_at = jiffies + expiry; + ack_at += now; if (time_before(ack_at, call->ack_at)) { WRITE_ONCE(call->ack_at, ack_at); rxrpc_reduce_call_timer(call, ack_at, now, diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index a1c53ac066a1..09f2a3e05221 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -233,7 +233,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, if (resend_at < 1) resend_at = 1; - resend_at = now + rxrpc_resend_timeout; + resend_at += now; WRITE_ONCE(call->resend_at, resend_at); rxrpc_reduce_call_timer(call, resend_at, now, rxrpc_timer_set_for_send); -- cgit v1.2.3 From 9b85c2d4508563f4bb1de0d971ed02fea0d0d757 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Tue, 28 Nov 2017 17:44:28 -0800 Subject: tools: bpftool: fix crash on bad parameters with JSON If bad or unrecognised parameters are specified after JSON output is requested, `usage()` will try to output null JSON object before the writer is created. To prevent this, create the writer as soon as the `--json` option is parsed. Fixes: 004b45c0e51a ("tools: bpftool: provide JSON output for all possible commands") Reported-by: Jakub Kicinski Signed-off-by: Quentin Monnet Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/main.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index d6e4762170a4..14ad54a1c404 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -291,7 +291,15 @@ int main(int argc, char **argv) pretty_output = true; /* fall through */ case 'j': - json_output = true; + if (!json_output) { + json_wtr = jsonw_new(stdout); + if (!json_wtr) { + p_err("failed to create JSON writer"); + return -1; + } + json_output = true; + } + jsonw_pretty(json_wtr, pretty_output); break; case 'f': show_pinned = true; @@ -306,15 +314,6 @@ int main(int argc, char **argv) if (argc < 0) usage(); - if (json_output) { - json_wtr = jsonw_new(stdout); - if (!json_wtr) { - p_err("failed to create JSON writer"); - return -1; - } - jsonw_pretty(json_wtr, pretty_output); - } - bfd_init(); ret = cmd_select(cmds, argc, argv, do_help); -- cgit v1.2.3 From 7868620a3c15dbc661fb5d849de403ac04624c50 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Tue, 28 Nov 2017 17:44:29 -0800 Subject: tools: bpftool: clean up the JSON writer before exiting in usage() The writer is cleaned at the end of the main function, but not if the program exits sooner in usage(). Let's keep it clean and destroy the writer before exiting. Destruction and actual call to exit() are moved to another function so that clean exit can also be performed without printing usage() hints. Fixes: d35efba99d92 ("tools: bpftool: introduce --json and --pretty options") Signed-off-by: Quentin Monnet Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/main.c | 10 +++++++++- tools/bpf/bpftool/main.h | 3 ++- 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 14ad54a1c404..d72dd73a4016 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -58,11 +58,19 @@ bool show_pinned; struct pinned_obj_table prog_table; struct pinned_obj_table map_table; +static void __noreturn clean_and_exit(int i) +{ + if (json_output) + jsonw_destroy(&json_wtr); + + exit(i); +} + void usage(void) { last_do_help(last_argc - 1, last_argv + 1); - exit(-1); + clean_and_exit(-1); } static int do_help(int argc, char **argv) diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 9c191e222d6f..0b60ddfb2b93 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -80,7 +81,7 @@ void p_info(const char *fmt, ...); bool is_prefix(const char *pfx, const char *str); void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep); -void usage(void) __attribute__((noreturn)); +void usage(void) __noreturn; struct pinned_obj_table { DECLARE_HASHTABLE(table, 16); -- cgit v1.2.3 From 146882a37da7aa566c7ec088b42c6495d769f2ba Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Tue, 28 Nov 2017 17:44:30 -0800 Subject: tools: bpftool: make error message from getopt_long() JSON-friendly If `getopt_long()` meets an unknown option, it prints its own error message to standard error output. While this does not strictly break JSON output, it is the only case bpftool prints something to standard error output if JSON output is required. All other errors are printed on standard output as JSON objects, so that an external program does not have to parse stderr. This is changed by setting the global variable `opterr` to 0. Furthermore, p_err() is used to reproduce the error message in a more JSON-friendly way, so that users still get to know what the erroneous option is. Signed-off-by: Quentin Monnet Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/main.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index d72dd73a4016..d294bc8168be 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -288,6 +288,7 @@ int main(int argc, char **argv) hash_init(prog_table.table); hash_init(map_table.table); + opterr = 0; while ((opt = getopt_long(argc, argv, "Vhpjf", options, NULL)) >= 0) { switch (opt) { @@ -313,7 +314,11 @@ int main(int argc, char **argv) show_pinned = true; break; default: - usage(); + p_err("unrecognized option '%s'", argv[optind - 1]); + if (json_output) + clean_and_exit(-1); + else + usage(); } } -- cgit v1.2.3 From 0d954eeb99eee63964a07a68fcac61e1df8488e7 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Tue, 28 Nov 2017 17:44:31 -0800 Subject: tools: bpftool: remove spurious line break from error message The end-of-line character inside the string would break JSON compliance. Remove it, `p_err()` already adds a '\n' character for plain output anyway. Fixes: 9a5ab8bf1d6d ("tools: bpftool: turn err() and info() macros into functions") Reported-by: Jakub Kicinski Signed-off-by: Quentin Monnet Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/main.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 0b60ddfb2b93..bff330b49791 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -51,7 +51,7 @@ #define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) #define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) -#define BAD_ARG() ({ p_err("what is '%s'?\n", *argv); -1; }) +#define BAD_ARG() ({ p_err("what is '%s'?", *argv); -1; }) #define ERR_MAX_LEN 1024 -- cgit v1.2.3 From 507e590da398a0e3438d563b5e736c3f2a7749d7 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Tue, 28 Nov 2017 17:44:32 -0800 Subject: tools: bpftool: unify installation directories Programs and documentation not managed by package manager are generally installed under /usr/local/, instead of the user's home directory. In particular, `man` is generally able to find manual pages under `/usr/local/share/man`. bpftool generally follows perf's example, and perf installs to home directory. However bpftool requires root credentials, so it seems sensible to follow the more common convention of installing files under /usr/local instead. So, make /usr/local the default prefix for installing the binary with `make install`, and the documentation with `make doc-install`. Also, create /usr/local/sbin if it does not exist. Note that the bash-completion file, however, is still installed under /usr/share/bash-completion/completions, as the default setup for bash does not attempt to load completion files under /usr/local/. Reported-by: David Beckett Signed-off-by: Quentin Monnet Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/Documentation/Makefile | 2 +- tools/bpf/bpftool/Makefile | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile index bde77d7c4390..37292bb5ce60 100644 --- a/tools/bpf/bpftool/Documentation/Makefile +++ b/tools/bpf/bpftool/Documentation/Makefile @@ -6,7 +6,7 @@ RM ?= rm -f # Make the path relative to DESTDIR, not prefix ifndef DESTDIR -prefix?=$(HOME) +prefix ?= /usr/local endif mandir ?= $(prefix)/share/man man8dir = $(mandir)/man8 diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 813826c50936..c5b21f2cbca5 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -45,8 +45,8 @@ $(LIBBPF)-clean: $(call QUIET_CLEAN, libbpf) $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) clean >/dev/null -prefix = /usr -bash_compdir ?= $(prefix)/share/bash-completion/completions +prefix = /usr/local +bash_compdir ?= /usr/share/bash-completion/completions CC = gcc @@ -76,6 +76,7 @@ clean: $(LIBBPF)-clean $(Q)rm -rf $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d install: + install -m 0755 -d $(prefix)/sbin install $(OUTPUT)bpftool $(prefix)/sbin/bpftool install -m 0755 -d $(bash_compdir) install -m 0644 bash-completion/bpftool $(bash_compdir) -- cgit v1.2.3 From ad3cda064402b69148faf5f7cd1ac8c2eee52645 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Tue, 28 Nov 2017 17:44:33 -0800 Subject: tools: bpftool: declare phony targets as such In the Makefile, targets install, doc and doc-install should be added to .PHONY. Let's fix this. Fixes: 71bb428fe2c1 ("tools: bpf: add bpftool") Signed-off-by: Quentin Monnet Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index c5b21f2cbca5..ec3052c0b004 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -89,5 +89,5 @@ doc-install: FORCE: -.PHONY: all clean FORCE +.PHONY: all clean FORCE install doc doc-install .DEFAULT_GOAL := all -- cgit v1.2.3 From 23721a755f98ac846897a013c92cccb281c1bcc8 Mon Sep 17 00:00:00 2001 From: Xie XiuQi Date: Thu, 30 Nov 2017 09:41:29 +0800 Subject: trace/xdp: fix compile warning: 'struct bpf_map' declared inside parameter list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We meet this compile warning, which caused by missing bpf.h in xdp.h. In file included from ./include/trace/events/xdp.h:10:0, from ./include/linux/bpf_trace.h:6, from drivers/net/ethernet/intel/i40e/i40e_txrx.c:29: ./include/trace/events/xdp.h:93:17: warning: ‘struct bpf_map’ declared inside parameter list will not be visible outside of this definition or declaration const struct bpf_map *map, u32 map_index), ^ ./include/linux/tracepoint.h:187:34: note: in definition of macro ‘__DECLARE_TRACE’ static inline void trace_##name(proto) \ ^~~~~ ./include/linux/tracepoint.h:352:24: note: in expansion of macro ‘PARAMS’ __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ ^~~~~~ ./include/linux/tracepoint.h:477:2: note: in expansion of macro ‘DECLARE_TRACE’ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) ^~~~~~~~~~~~~ ./include/linux/tracepoint.h:477:22: note: in expansion of macro ‘PARAMS’ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) ^~~~~~ ./include/trace/events/xdp.h:89:1: note: in expansion of macro ‘DEFINE_EVENT’ DEFINE_EVENT(xdp_redirect_template, xdp_redirect, ^~~~~~~~~~~~ ./include/trace/events/xdp.h:90:2: note: in expansion of macro ‘TP_PROTO’ TP_PROTO(const struct net_device *dev, ^~~~~~~~ ./include/trace/events/xdp.h:93:17: warning: ‘struct bpf_map’ declared inside parameter list will not be visible outside of this definition or declaration const struct bpf_map *map, u32 map_index), ^ ./include/linux/tracepoint.h:203:38: note: in definition of macro ‘__DECLARE_TRACE’ register_trace_##name(void (*probe)(data_proto), void *data) \ ^~~~~~~~~~ ./include/linux/tracepoint.h:354:4: note: in expansion of macro ‘PARAMS’ PARAMS(void *__data, proto), \ ^~~~~~ Reported-by: Huang Daode Cc: Hanjun Guo Fixes: 8d3b778ff544 ("xdp: tracepoint xdp_redirect also need a map argument") Signed-off-by: Xie XiuQi Acked-by: Jesper Dangaard Brouer Acked-by: Steven Rostedt (VMware) Signed-off-by: Daniel Borkmann --- include/trace/events/xdp.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index 4cd0f05d0113..8989a92c571a 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -8,6 +8,7 @@ #include #include #include +#include #define __XDP_ACT_MAP(FN) \ FN(ABORTED) \ -- cgit v1.2.3 From a154f8e399a063137fc42b961f437248d55ece29 Mon Sep 17 00:00:00 2001 From: Yan Markman Date: Thu, 30 Nov 2017 10:49:46 +0100 Subject: net: mvpp2: allocate zeroed tx descriptors Reserved and unused fields in the Tx descriptors should be 0. The PPv2 driver doesn't clear them at run-time (for performance reasons) but these descriptors aren't zeroed when allocated, which can lead to unpredictable behaviors. This patch fixes this by using dma_zalloc_coherent instead of dma_alloc_coherent. Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit") Signed-off-by: Yan Markman [Antoine: commit message] Signed-off-by: Antoine Tenart Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index d83a78be98a2..fed2b2f909fc 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -5598,7 +5598,7 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev, u32 txq_dma; /* Allocate memory for TX descriptors */ - aggr_txq->descs = dma_alloc_coherent(&pdev->dev, + aggr_txq->descs = dma_zalloc_coherent(&pdev->dev, MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE, &aggr_txq->descs_dma, GFP_KERNEL); if (!aggr_txq->descs) -- cgit v1.2.3 From f8821f96ae97260d68228fe53f81848b2ede44d7 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 30 Nov 2017 14:33:56 +0100 Subject: skbuff: Grammar s/are can/can/, s/change/changes/ Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bc486ef23f20..a38c80e9f91e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1406,8 +1406,7 @@ static inline struct sk_buff *skb_get(struct sk_buff *skb) } /* - * If users == 1, we are the only owner and are can avoid redundant - * atomic change. + * If users == 1, we are the only owner and can avoid redundant atomic changes. */ /** -- cgit v1.2.3 From 1c08ac0c4bd8e9d66c4dde29bc496c3b430dd028 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Tue, 28 Nov 2017 17:48:22 +0100 Subject: net: stmmac: dwmac-sun8i: fix allwinner,leds-active-low handling The driver expect "allwinner,leds-active-low" to be in PHY node, but the binding doc expect it to be in MAC node. Since all board DT use it also in MAC node, the driver need to search allwinner,leds-active-low in MAC node. Signed-off-by: Corentin Labbe Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index e5ff734d4f9b..9eb7f65d8000 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -808,8 +808,7 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv) val, reg); if (gmac->variant->soc_has_internal_phy) { - if (of_property_read_bool(priv->plat->phy_node, - "allwinner,leds-active-low")) + if (of_property_read_bool(node, "allwinner,leds-active-low")) reg |= H3_EPHY_LED_POL; else reg &= ~H3_EPHY_LED_POL; -- cgit v1.2.3 From 90a6ec85351b31449c2c6b5406b5396ac96f191d Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Wed, 29 Nov 2017 16:07:51 -0800 Subject: act_sample: get rid of tcf_sample_cleanup_rcu() Similar to commit d7fb60b9cafb ("net_sched: get rid of tcfa_rcu"), TC actions don't need to respect RCU grace period, because it is either just detached from tc filter (standalone case) or it is removed together with tc filter (bound case) in which case RCU grace period is already respected at filter layer. Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action") Reported-by: Eric Dumazet Cc: Jamal Hadi Salim Cc: Jiri Pirko Cc: Yotam Gigi Signed-off-by: Cong Wang Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tc_act/tc_sample.h | 1 - net/sched/act_sample.c | 14 +++----------- 2 files changed, 3 insertions(+), 12 deletions(-) diff --git a/include/net/tc_act/tc_sample.h b/include/net/tc_act/tc_sample.h index 524cee4f4c81..01dbfea32672 100644 --- a/include/net/tc_act/tc_sample.h +++ b/include/net/tc_act/tc_sample.h @@ -14,7 +14,6 @@ struct tcf_sample { struct psample_group __rcu *psample_group; u32 psample_group_num; struct list_head tcfm_list; - struct rcu_head rcu; }; #define to_sample(a) ((struct tcf_sample *)a) diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 8b5abcd2f32f..9438969290a6 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -96,23 +96,16 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return ret; } -static void tcf_sample_cleanup_rcu(struct rcu_head *rcu) +static void tcf_sample_cleanup(struct tc_action *a, int bind) { - struct tcf_sample *s = container_of(rcu, struct tcf_sample, rcu); + struct tcf_sample *s = to_sample(a); struct psample_group *psample_group; - psample_group = rcu_dereference_protected(s->psample_group, 1); + psample_group = rtnl_dereference(s->psample_group); RCU_INIT_POINTER(s->psample_group, NULL); psample_group_put(psample_group); } -static void tcf_sample_cleanup(struct tc_action *a, int bind) -{ - struct tcf_sample *s = to_sample(a); - - call_rcu(&s->rcu, tcf_sample_cleanup_rcu); -} - static bool tcf_sample_dev_ok_push(struct net_device *dev) { switch (dev->type) { @@ -264,7 +257,6 @@ static int __init sample_init_module(void) static void __exit sample_cleanup_module(void) { - rcu_barrier(); tcf_unregister_action(&act_sample_ops, &sample_net_ops); } -- cgit v1.2.3 From 3016dad75b48279e579117ee3ed566ba90a3b023 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 29 Nov 2017 17:43:57 -0800 Subject: tcp: remove buggy call to tcp_v6_restore_cb() tcp_v6_send_reset() expects to receive an skb with skb->cb[] layout as used in TCP stack. MD5 lookup uses tcp_v6_iif() and tcp_v6_sdif() and thus TCP_SKB_CB(skb)->header.h6 This patch probably fixes RST packets sent on behalf of a timewait md5 ipv6 socket. Before Florian patch, tcp_v6_restore_cb() was needed before jumping to no_tcp_socket label. Fixes: 271c3b9b7bda ("tcp: honour SO_BINDTODEVICE for TW_RST case too") Signed-off-by: Eric Dumazet Cc: Florian Westphal Acked-by: Florian Westphal Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6bb98c93edfe..be11dc13aa70 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1590,7 +1590,6 @@ do_time_wait: tcp_v6_timewait_ack(sk, skb); break; case TCP_TW_RST: - tcp_v6_restore_cb(skb); tcp_v6_send_reset(sk, skb); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it; -- cgit v1.2.3 From f859b4af1c52493ec21173ccc73d0b60029b5b88 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 30 Nov 2017 10:41:14 +0800 Subject: sit: update frag_off info After parsing the sit netlink change info, we forget to update frag_off in ipip6_tunnel_update(). Fix it by assigning frag_off with new value. Reported-by: Jianlin Shi Signed-off-by: Hangbin Liu Acked-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv6/sit.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index d60ddcb0bfe2..d7dc23c1b2ca 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1098,6 +1098,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p, ipip6_tunnel_link(sitn, t); t->parms.iph.ttl = p->iph.ttl; t->parms.iph.tos = p->iph.tos; + t->parms.iph.frag_off = p->iph.frag_off; if (t->parms.link != p->link || t->fwmark != fwmark) { t->parms.link = p->link; t->fwmark = fwmark; -- cgit v1.2.3 From 2b279419567105d63f1e524bb1ac34ae8f918e5d Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 30 Nov 2017 08:52:42 -0800 Subject: tools/bpf: adjust rlimit RLIMIT_MEMLOCK for test_verifier_log The default rlimit RLIMIT_MEMLOCK is 64KB. In certain cases, e.g. in a test machine mimicking our production system, this test may fail due to unable to charge the required memory for prog load: # ./test_verifier_log Test log_level 0... ERROR: Program load returned: ret:-1/errno:1, expected ret:-1/errno:22 Changing the default rlimit RLIMIT_MEMLOCK to unlimited makes the test always pass. Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/test_verifier_log.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/testing/selftests/bpf/test_verifier_log.c b/tools/testing/selftests/bpf/test_verifier_log.c index 3cc0b561489e..e9626cf5607a 100644 --- a/tools/testing/selftests/bpf/test_verifier_log.c +++ b/tools/testing/selftests/bpf/test_verifier_log.c @@ -3,6 +3,8 @@ #include #include #include +#include +#include #include #include @@ -131,11 +133,16 @@ static void test_log_bad(char *log, size_t log_len, int log_level) int main(int argc, char **argv) { + struct rlimit limit = { RLIM_INFINITY, RLIM_INFINITY }; char full_log[LOG_SIZE]; char log[LOG_SIZE]; size_t want_len; int i; + /* allow unlimited locked memory to have more consistent error code */ + if (setrlimit(RLIMIT_MEMLOCK, &limit) < 0) + perror("Unable to lift memlock rlimit"); + memset(log, 1, LOG_SIZE); /* Test incorrect attr */ -- cgit v1.2.3 From 6fef90c6b3f6a2b52018e66c0886944ea0c03fcc Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 30 Nov 2017 10:45:26 -0800 Subject: net: dsa: bcm_sf2: Set correct CHAIN_ID and slice number mask When configuring an IPv6 address mask, we should use SLICE_NUM_MASK as the mask in order to make sure all bits are masked by the hardware. Also, we want matching entries to have a CHAIN_ID value set to the same value as the rule index we return to user-space for convenience, so fix that too. Fixes: ba0696c22e7c ("net: dsa: bcm_sf2: Add support for IPv6 CFP rules") Fixes: dd8eff68343d ("net: dsa: bcm_sf2: Allow matching arbitrary IPv6 masks/lengths") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/bcm_sf2_cfp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index b721a2009b50..23b45da784cb 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -625,7 +625,7 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, bcm_sf2_cfp_slice_ipv6(priv, v6_spec->ip6src, v6_spec->psrc, slice_num, false); bcm_sf2_cfp_slice_ipv6(priv, v6_m_spec->ip6src, v6_m_spec->psrc, - slice_num, true); + SLICE_NUM_MASK, true); /* Insert into TCAM now because we need to insert a second rule */ bcm_sf2_cfp_rule_addr_set(priv, rule_index[0]); @@ -699,7 +699,7 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, /* Insert into Action and policer RAMs now, set chain ID to * the one we are chained to */ - ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[0], port_num, + ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[1], port_num, queue_num, true); if (ret) goto out_err; -- cgit v1.2.3 From c8c088ba0edf65044c254b96fc438c91914aaab0 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 30 Nov 2017 13:47:54 -0800 Subject: bpf: set maximum number of attached progs to 64 for a single perf tp cgropu+bpf prog array has a maximum number of 64 programs. Let us apply the same limit here. Fixes: e87c6bc3852b ("bpf: permit multiple bpf attachments for a single perf event") Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- kernel/bpf/core.c | 3 ++- kernel/trace/bpf_trace.c | 8 ++++++++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index b9f8686a84cf..86b50aa26ee8 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1447,7 +1447,8 @@ int bpf_prog_array_length(struct bpf_prog_array __rcu *progs) rcu_read_lock(); prog = rcu_dereference(progs)->progs; for (; *prog; prog++) - cnt++; + if (*prog != &dummy_bpf_prog.prog) + cnt++; rcu_read_unlock(); return cnt; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 27d1f4ffa3de..0ce99c379c30 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -759,6 +759,8 @@ const struct bpf_prog_ops perf_event_prog_ops = { static DEFINE_MUTEX(bpf_event_mutex); +#define BPF_TRACE_MAX_PROGS 64 + int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog) { @@ -772,6 +774,12 @@ int perf_event_attach_bpf_prog(struct perf_event *event, goto unlock; old_array = event->tp_event->prog_array; + if (old_array && + bpf_prog_array_length(old_array) >= BPF_TRACE_MAX_PROGS) { + ret = -E2BIG; + goto unlock; + } + ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array); if (ret < 0) goto unlock; -- cgit v1.2.3 From 0ec9552b43b98deb882bf48efd347be4bd7afc9f Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 30 Nov 2017 13:47:55 -0800 Subject: samples/bpf: add error checking for perf ioctl calls in bpf loader load_bpf_file() should fail if ioctl with command PERF_EVENT_IOC_ENABLE and PERF_EVENT_IOC_SET_BPF fails. When they do fail, proper error messages are printed. With this change, the below "syscall_tp" run shows that the maximum number of bpf progs attaching to the same perf tracepoint is indeed enforced. $ ./syscall_tp -i 64 prog #0: map ids 4 5 ... prog #63: map ids 382 383 $ ./syscall_tp -i 65 prog #0: map ids 4 5 ... prog #64: map ids 388 389 ioctl PERF_EVENT_IOC_SET_BPF failed err Argument list too long Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- samples/bpf/bpf_load.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index 522ca9252d6c..242631aa4ea2 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -193,8 +193,18 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) return -1; } event_fd[prog_cnt - 1] = efd; - ioctl(efd, PERF_EVENT_IOC_ENABLE, 0); - ioctl(efd, PERF_EVENT_IOC_SET_BPF, fd); + err = ioctl(efd, PERF_EVENT_IOC_ENABLE, 0); + if (err < 0) { + printf("ioctl PERF_EVENT_IOC_ENABLE failed err %s\n", + strerror(errno)); + return -1; + } + err = ioctl(efd, PERF_EVENT_IOC_SET_BPF, fd); + if (err < 0) { + printf("ioctl PERF_EVENT_IOC_SET_BPF failed err %s\n", + strerror(errno)); + return -1; + } return 0; } -- cgit v1.2.3 From 435019b48033138581a6171093b181fc6b4d3d30 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 21 Nov 2017 08:22:26 +0100 Subject: can: kvaser_usb: free buf in error paths The allocated buffer was not freed if usb_submit_urb() failed. Signed-off-by: Jimmy Assarsson Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/kvaser_usb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index 9b18d96ef526..075644591498 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -813,6 +813,7 @@ static int kvaser_usb_simple_msg_async(struct kvaser_usb_net_priv *priv, if (err) { netdev_err(netdev, "Error transmitting URB\n"); usb_unanchor_urb(urb); + kfree(buf); usb_free_urb(urb); return err; } @@ -1768,6 +1769,7 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, spin_unlock_irqrestore(&priv->tx_contexts_lock, flags); usb_unanchor_urb(urb); + kfree(buf); stats->tx_dropped++; -- cgit v1.2.3 From e84f44eb5523401faeb9cc1c97895b68e3cfb78d Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 21 Nov 2017 08:22:27 +0100 Subject: can: kvaser_usb: Fix comparison bug in kvaser_usb_read_bulk_callback() The conditon in the while-loop becomes true when actual_length is less than 2 (MSG_HEADER_LEN). In best case we end up with a former, already dispatched msg, that got msg->len greater than actual_length. This will result in a "Format error" error printout. Problem seen when unplugging a Kvaser USB device connected to a vbox guest. warning: comparison between signed and unsigned integer expressions [-Wsign-compare] Signed-off-by: Jimmy Assarsson Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/kvaser_usb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index 075644591498..d87e330a20b3 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -1334,7 +1334,7 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb) goto resubmit_urb; } - while (pos <= urb->actual_length - MSG_HEADER_LEN) { + while (pos <= (int)(urb->actual_length - MSG_HEADER_LEN)) { msg = urb->transfer_buffer + pos; /* The Kvaser firmware can only read and write messages that -- cgit v1.2.3 From 8bd13bd522ff7dfa0eb371921aeb417155f7a3be Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 21 Nov 2017 08:22:28 +0100 Subject: can: kvaser_usb: ratelimit errors if incomplete messages are received Avoid flooding the kernel log with "Formate error", if incomplete message are received. Signed-off-by: Jimmy Assarsson Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/kvaser_usb.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index d87e330a20b3..f95945915d20 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -609,8 +609,8 @@ static int kvaser_usb_wait_msg(const struct kvaser_usb *dev, u8 id, } if (pos + tmp->len > actual_len) { - dev_err(dev->udev->dev.parent, - "Format error\n"); + dev_err_ratelimited(dev->udev->dev.parent, + "Format error\n"); break; } @@ -1353,7 +1353,8 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb) } if (pos + msg->len > urb->actual_length) { - dev_err(dev->udev->dev.parent, "Format error\n"); + dev_err_ratelimited(dev->udev->dev.parent, + "Format error\n"); break; } -- cgit v1.2.3 From f6c23b174c3c96616514827407769cbcfc8005cf Mon Sep 17 00:00:00 2001 From: Oliver Stäbler Date: Mon, 20 Nov 2017 14:45:15 +0100 Subject: can: ti_hecc: Fix napi poll return value for repoll MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After commit d75b1ade567f ("net: less interrupt masking in NAPI") napi repoll is done only when work_done == budget. So we need to return budget if there are still packets to receive. Signed-off-by: Oliver Stäbler Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/ti_hecc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index 4d4941469cfc..db6ea936dc3f 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -637,6 +637,9 @@ static int ti_hecc_rx_poll(struct napi_struct *napi, int quota) mbx_mask = hecc_read(priv, HECC_CANMIM); mbx_mask |= HECC_TX_MBOX_MASK; hecc_write(priv, HECC_CANMIM, mbx_mask); + } else { + /* repoll is done only if whole budget is used */ + num_pkts = quota; } return num_pkts; -- cgit v1.2.3 From 5c2cb02edf79ad79d9b8d07c6d52243a948c4c9f Mon Sep 17 00:00:00 2001 From: Stephane Grosjean Date: Thu, 23 Nov 2017 15:44:35 +0100 Subject: can: peak/pci: fix potential bug when probe() fails PCI/PCIe drivers for PEAK-System CAN/CAN-FD interfaces do some access to the PCI config during probing. In case one of these accesses fails, a POSITIVE PCIBIOS_xxx error code is returned back. This POSITIVE error code MUST be converted into a NEGATIVE errno for the probe() function to indicate it failed. Using the pcibios_err_to_errno() function, we make sure that the return code will always be negative. Signed-off-by: Stephane Grosjean Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/peak_canfd/peak_pciefd_main.c | 5 ++++- drivers/net/can/sja1000/peak_pci.c | 5 ++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c index b4efd711f824..788c3464a3b0 100644 --- a/drivers/net/can/peak_canfd/peak_pciefd_main.c +++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c @@ -825,7 +825,10 @@ err_release_regions: err_disable_pci: pci_disable_device(pdev); - return err; + /* pci_xxx_config_word() return positive PCIBIOS_xxx error codes while + * the probe() function must return a negative errno in case of failure + * (err is unchanged if negative) */ + return pcibios_err_to_errno(err); } /* free the board structure object, as well as its resources: */ diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c index 131026fbc2d7..5adc95c922ee 100644 --- a/drivers/net/can/sja1000/peak_pci.c +++ b/drivers/net/can/sja1000/peak_pci.c @@ -717,7 +717,10 @@ failure_release_regions: failure_disable_pci: pci_disable_device(pdev); - return err; + /* pci_xxx_config_word() return positive PCIBIOS_xxx error codes while + * the probe() function must return a negative errno in case of failure + * (err is unchanged if negative) */ + return pcibios_err_to_errno(err); } static void peak_pci_remove(struct pci_dev *pdev) -- cgit v1.2.3 From 658f534c036352a06584c8b2e71a547915173ba9 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 22 Nov 2017 13:01:08 +0100 Subject: can: flexcan: Update IRQ Err Passive information The flexcan IP cores used on MX25 and MX35 do not generate Error Passive IRQs. Update the IP core overview table in the driver accordingly. Suggested-by: ZHU Yi (ST-FIR/ENG1-Zhu) Signed-off-by: Marc Kleine-Budde --- drivers/net/can/flexcan.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index a13a4896a8bd..eefddae2e99a 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -184,9 +184,9 @@ * Below is some version info we got: * SOC Version IP-Version Glitch- [TR]WRN_INT IRQ Err Memory err RTR re- * Filter? connected? Passive detection ception in MB - * MX25 FlexCAN2 03.00.00.00 no no ? no no + * MX25 FlexCAN2 03.00.00.00 no no no no no * MX28 FlexCAN2 03.00.04.00 yes yes no no no - * MX35 FlexCAN2 03.00.00.00 no no ? no no + * MX35 FlexCAN2 03.00.00.00 no no no no no * MX53 FlexCAN2 03.00.00.00 yes no no no no * MX6s FlexCAN3 10.00.12.00 yes yes no no yes * VF610 FlexCAN3 ? no yes ? yes yes? -- cgit v1.2.3 From 29c64b17a0bc72232acc45e9533221d88a262efb Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 27 Nov 2017 09:18:21 +0100 Subject: can: flexcan: fix VF610 state transition issue Enable FLEXCAN_QUIRK_BROKEN_PERR_STATE for VF610 to report correct state transitions. Tested-by: Mirza Krak Cc: linux-stable # >= v4.11 Signed-off-by: Marc Kleine-Budde --- drivers/net/can/flexcan.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index eefddae2e99a..0626dcfd1f3d 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -189,7 +189,7 @@ * MX35 FlexCAN2 03.00.00.00 no no no no no * MX53 FlexCAN2 03.00.00.00 yes no no no no * MX6s FlexCAN3 10.00.12.00 yes yes no no yes - * VF610 FlexCAN3 ? no yes ? yes yes? + * VF610 FlexCAN3 ? no yes no yes yes? * * Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected. */ @@ -297,7 +297,8 @@ static const struct flexcan_devtype_data fsl_imx6q_devtype_data = { static const struct flexcan_devtype_data fsl_vf610_devtype_data = { .quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS | - FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP, + FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | + FLEXCAN_QUIRK_BROKEN_PERR_STATE, }; static const struct can_bittiming_const flexcan_bittiming_const = { -- cgit v1.2.3 From 3fed8dbbc42c0639ac03d2361ab5f0606dd49e28 Mon Sep 17 00:00:00 2001 From: Martin Kelly Date: Mon, 27 Nov 2017 15:49:15 -0800 Subject: can: mcba_usb: fix typo Fix typo "analizer" --> "Analyzer". Signed-off-by: Martin Kelly Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/mcba_usb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 7f0272558bef..c4355f0a20d5 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -862,7 +862,7 @@ static int mcba_usb_probe(struct usb_interface *intf, goto cleanup_unregister_candev; } - dev_info(&intf->dev, "Microchip CAN BUS analizer connected\n"); + dev_info(&intf->dev, "Microchip CAN BUS Analyzer connected\n"); return 0; -- cgit v1.2.3 From 1cb35a33a28394fd711bb26ddf3a564f4e9d9125 Mon Sep 17 00:00:00 2001 From: Martin Kelly Date: Mon, 27 Nov 2017 15:49:16 -0800 Subject: can: mcba_usb: fix device disconnect bug Currently, when you disconnect the device, the driver infinitely resubmits all URBs, so you see: Rx URB aborted (-32) in an infinite loop. Fix this by catching -EPIPE (what we get in urb->status when the device disconnects) and not resubmitting. With this patch, I can plug and unplug many times and the driver recovers correctly. Signed-off-by: Martin Kelly Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/mcba_usb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index c4355f0a20d5..ef417dcddbf7 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -592,6 +592,7 @@ static void mcba_usb_read_bulk_callback(struct urb *urb) break; case -ENOENT: + case -EPIPE: case -ESHUTDOWN: return; -- cgit v1.2.3 From d30fc5126efb0c33b7adf5966d3051db2c3d7721 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 25 Nov 2017 21:18:34 +0800 Subject: sctp: only update outstanding_bytes for transmitted queue when doing prsctp_prune Now outstanding_bytes is only increased when appending chunks into one packet and sending it at 1st time, while decreased when it is about to move into retransmit queue. It means outstanding_bytes value is already decreased for all chunks in retransmit queue. However sctp_prsctp_prune_sent is a common function to check the chunks in both transmitted and retransmit queue, it decrease outstanding_bytes when moving a chunk into abandoned queue from either of them. It could cause outstanding_bytes underflow, as it also decreases it's value for the chunks in retransmit queue. This patch fixes it by only updating outstanding_bytes for transmitted queue when pruning queues for prsctp prio policy, the same fix is also needed in sctp_check_transmitted. Fixes: 8dbdf1f5b09c ("sctp: implement prsctp PRIO policy") Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/outqueue.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 4db012aa25f7..7029f8b99063 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -377,7 +377,8 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; - if (!chk->tsn_gap_acked) { + if (queue != &asoc->outqueue.retransmit && + !chk->tsn_gap_acked) { if (chk->transport) chk->transport->flight_size -= sctp_data_size(chk); @@ -1434,7 +1435,8 @@ static void sctp_check_transmitted(struct sctp_outq *q, /* If this chunk has not been acked, stop * considering it as 'outstanding'. */ - if (!tchunk->tsn_gap_acked) { + if (transmitted_queue != &q->retransmit && + !tchunk->tsn_gap_acked) { if (tchunk->transport) tchunk->transport->flight_size -= sctp_data_size(tchunk); -- cgit v1.2.3 From e5f612969c6f965e3bd1158598e0a3b1c4f389b9 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 25 Nov 2017 21:18:35 +0800 Subject: sctp: abandon the whole msg if one part of a fragmented message is abandoned As rfc3758#section-3.1 demands: A3) When a TSN is "abandoned", if it is part of a fragmented message, all other TSN's within that fragmented message MUST be abandoned at the same time. Besides, if it couldn't handle this, the rest frags would never get assembled in peer side. This patch supports it by adding abandoned flag in sctp_datamsg, when one chunk is being abandoned, set chunk->msg->abandoned as well. Next time when checking for abandoned, go checking chunk->msg->abandoned first. Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 3 ++- net/sctp/chunk.c | 7 +++++++ net/sctp/outqueue.c | 12 ++++++++---- 3 files changed, 17 insertions(+), 5 deletions(-) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 16f949eef52f..2f8f93da5dc2 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -503,7 +503,8 @@ struct sctp_datamsg { /* Did the messenge fail to send? */ int send_error; u8 send_failed:1, - can_delay; /* should this message be Nagle delayed */ + can_delay:1, /* should this message be Nagle delayed */ + abandoned:1; /* should this message be abandoned */ }; struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *, diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 7b261afc47b9..9213805b558d 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -53,6 +53,7 @@ static void sctp_datamsg_init(struct sctp_datamsg *msg) msg->send_failed = 0; msg->send_error = 0; msg->can_delay = 1; + msg->abandoned = 0; msg->expires_at = 0; INIT_LIST_HEAD(&msg->chunks); } @@ -304,6 +305,9 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) if (!chunk->asoc->peer.prsctp_capable) return 0; + if (chunk->msg->abandoned) + return 1; + if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) && time_after(jiffies, chunk->msg->expires_at)) { struct sctp_stream_out *streamout = @@ -316,6 +320,7 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; streamout->ext->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; } + chunk->msg->abandoned = 1; return 1; } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && chunk->sent_count > chunk->sinfo.sinfo_timetolive) { @@ -324,10 +329,12 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++; + chunk->msg->abandoned = 1; return 1; } else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) && chunk->msg->expires_at && time_after(jiffies, chunk->msg->expires_at)) { + chunk->msg->abandoned = 1; return 1; } /* PRIO policy is processed by sendmsg, not here */ diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 7029f8b99063..4ab164b5aad0 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -364,10 +364,12 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, list_for_each_entry_safe(chk, temp, queue, transmitted_list) { struct sctp_stream_out *streamout; - if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || - chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive) + if (!chk->msg->abandoned && + (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || + chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)) continue; + chk->msg->abandoned = 1; list_del_init(&chk->transmitted_list); sctp_insert_list(&asoc->outqueue.abandoned, &chk->transmitted_list); @@ -404,10 +406,12 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, q->sched->unsched_all(&asoc->stream); list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) { - if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || - chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive) + if (!chk->msg->abandoned && + (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || + chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)) continue; + chk->msg->abandoned = 1; sctp_sched_dequeue_common(q, chk); asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; -- cgit v1.2.3 From 779edd7348878a7376c0e3d0f96485c30b5f1b7d Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 25 Nov 2017 21:18:36 +0800 Subject: sctp: do not abandon the other frags in unsent outq if one msg has outstanding frags Now for the abandoned chunks in unsent outq, it would just free the chunks. Because no tsn is assigned to them yet, there's no need to send fwd tsn to peer, unlike for the abandoned chunks in sent outq. The problem is when parts of the msg have been sent and the other frags are still in unsent outq, if they are abandoned/dropped, the peer would never get this msg reassembled. So these frags in unsent outq can't be dropped if this msg already has outstanding frags. This patch does the check in sctp_chunk_abandoned and sctp_prsctp_prune_unsent. Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/chunk.c | 4 ++++ net/sctp/outqueue.c | 3 ++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 9213805b558d..7f8baa48e7c2 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -308,6 +308,10 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) if (chunk->msg->abandoned) return 1; + if (!chunk->has_tsn && + !(chunk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG)) + return 0; + if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) && time_after(jiffies, chunk->msg->expires_at)) { struct sctp_stream_out *streamout = diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 4ab164b5aad0..7d67feeeffc1 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -407,7 +407,8 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) { if (!chk->msg->abandoned && - (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || + (!(chk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG) || + !SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)) continue; -- cgit v1.2.3 From cfac7f836a715b91f08c851df915d401a4d52783 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 1 Dec 2017 10:06:56 -0800 Subject: tcp/dccp: block bh before arming time_wait timer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Maciej Żenczykowski reported some panics in tcp_twsk_destructor() that might be caused by the following bug. timewait timer is pinned to the cpu, because we want to transition timwewait refcount from 0 to 4 in one go, once everything has been initialized. At the time commit ed2e92394589 ("tcp/dccp: fix timewait races in timer handling") was merged, TCP was always running from BH habdler. After commit 5413d1babe8f ("net: do not block BH while processing socket backlog") we definitely can run tcp_time_wait() from process context. We need to block BH in the critical section so that the pinned timer has still its purpose. This bug is more likely to happen under stress and when very small RTO are used in datacenter flows. Fixes: 5413d1babe8f ("net: do not block BH while processing socket backlog") Signed-off-by: Eric Dumazet Reported-by: Maciej Żenczykowski Acked-by: Maciej Żenczykowski Signed-off-by: David S. Miller --- net/dccp/minisocks.c | 6 ++++++ net/ipv4/tcp_minisocks.c | 6 ++++++ 2 files changed, 12 insertions(+) diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index abd07a443219..178bb9833311 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -57,10 +57,16 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) if (state == DCCP_TIME_WAIT) timeo = DCCP_TIMEWAIT_LEN; + /* tw_timer is pinned, so we need to make sure BH are disabled + * in following section, otherwise timer handler could run before + * we complete the initialization. + */ + local_bh_disable(); inet_twsk_schedule(tw, timeo); /* Linkage updates. */ __inet_twsk_hashdance(tw, sk, &dccp_hashinfo); inet_twsk_put(tw); + local_bh_enable(); } else { /* Sorry, if we're out of memory, just CLOSE this * socket up. We've got bigger problems than diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index e36eff0403f4..b079b619b60c 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -310,10 +310,16 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (state == TCP_TIME_WAIT) timeo = TCP_TIMEWAIT_LEN; + /* tw_timer is pinned, so we need to make sure BH are disabled + * in following section, otherwise timer handler could run before + * we complete the initialization. + */ + local_bh_disable(); inet_twsk_schedule(tw, timeo); /* Linkage updates. */ __inet_twsk_hashdance(tw, sk, &tcp_hashinfo); inet_twsk_put(tw); + local_bh_enable(); } else { /* Sorry, if we're out of memory, just CLOSE this * socket up. We've got bigger problems than -- cgit v1.2.3 From c7799c067c2ae33e348508c8afec354f3257ff25 Mon Sep 17 00:00:00 2001 From: Tommi Rantala Date: Wed, 29 Nov 2017 12:48:42 +0200 Subject: tipc: call tipc_rcv() only if bearer is up in tipc_udp_recv() Remove the second tipc_rcv() call in tipc_udp_recv(). We have just checked that the bearer is not up, and calling tipc_rcv() with a bearer that is not up leads to a TIPC div-by-zero crash in tipc_node_calculate_timer(). The crash is rare in practice, but can happen like this: We're enabling a bearer, but it's not yet up and fully initialized. At the same time we receive a discovery packet, and in tipc_udp_recv() we end up calling tipc_rcv() with the not-yet-initialized bearer, causing later the div-by-zero crash in tipc_node_calculate_timer(). Jon Maloy explains the impact of removing the second tipc_rcv() call: "link setup in the worst case will be delayed until the next arriving discovery messages, 1 sec later, and this is an acceptable delay." As the tipc_rcv() call is removed, just leave the function via the rcu_out label, so that we will kfree_skb(). [ 12.590450] Own node address <1.1.1>, network identity 1 [ 12.668088] divide error: 0000 [#1] SMP [ 12.676952] CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.14.2-dirty #1 [ 12.679225] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-2.fc27 04/01/2014 [ 12.682095] task: ffff8c2a761edb80 task.stack: ffffa41cc0cac000 [ 12.684087] RIP: 0010:tipc_node_calculate_timer.isra.12+0x45/0x60 [tipc] [ 12.686486] RSP: 0018:ffff8c2a7fc838a0 EFLAGS: 00010246 [ 12.688451] RAX: 0000000000000000 RBX: ffff8c2a5b382600 RCX: 0000000000000000 [ 12.691197] RDX: 0000000000000000 RSI: ffff8c2a5b382600 RDI: ffff8c2a5b382600 [ 12.693945] RBP: ffff8c2a7fc838b0 R08: 0000000000000001 R09: 0000000000000001 [ 12.696632] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8c2a5d8949d8 [ 12.699491] R13: ffffffff95ede400 R14: 0000000000000000 R15: ffff8c2a5d894800 [ 12.702338] FS: 0000000000000000(0000) GS:ffff8c2a7fc80000(0000) knlGS:0000000000000000 [ 12.705099] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 12.706776] CR2: 0000000001bb9440 CR3: 00000000bd009001 CR4: 00000000003606e0 [ 12.708847] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 12.711016] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 12.712627] Call Trace: [ 12.713390] [ 12.714011] tipc_node_check_dest+0x2e8/0x350 [tipc] [ 12.715286] tipc_disc_rcv+0x14d/0x1d0 [tipc] [ 12.716370] tipc_rcv+0x8b0/0xd40 [tipc] [ 12.717396] ? minmax_running_min+0x2f/0x60 [ 12.718248] ? dst_alloc+0x4c/0xa0 [ 12.718964] ? tcp_ack+0xaf1/0x10b0 [ 12.719658] ? tipc_udp_is_known_peer+0xa0/0xa0 [tipc] [ 12.720634] tipc_udp_recv+0x71/0x1d0 [tipc] [ 12.721459] ? dst_alloc+0x4c/0xa0 [ 12.722130] udp_queue_rcv_skb+0x264/0x490 [ 12.722924] __udp4_lib_rcv+0x21e/0x990 [ 12.723670] ? ip_route_input_rcu+0x2dd/0xbf0 [ 12.724442] ? tcp_v4_rcv+0x958/0xa40 [ 12.725039] udp_rcv+0x1a/0x20 [ 12.725587] ip_local_deliver_finish+0x97/0x1d0 [ 12.726323] ip_local_deliver+0xaf/0xc0 [ 12.726959] ? ip_route_input_noref+0x19/0x20 [ 12.727689] ip_rcv_finish+0xdd/0x3b0 [ 12.728307] ip_rcv+0x2ac/0x360 [ 12.728839] __netif_receive_skb_core+0x6fb/0xa90 [ 12.729580] ? udp4_gro_receive+0x1a7/0x2c0 [ 12.730274] __netif_receive_skb+0x1d/0x60 [ 12.730953] ? __netif_receive_skb+0x1d/0x60 [ 12.731637] netif_receive_skb_internal+0x37/0xd0 [ 12.732371] napi_gro_receive+0xc7/0xf0 [ 12.732920] receive_buf+0x3c3/0xd40 [ 12.733441] virtnet_poll+0xb1/0x250 [ 12.733944] net_rx_action+0x23e/0x370 [ 12.734476] __do_softirq+0xc5/0x2f8 [ 12.734922] irq_exit+0xfa/0x100 [ 12.735315] do_IRQ+0x4f/0xd0 [ 12.735680] common_interrupt+0xa2/0xa2 [ 12.736126] [ 12.736416] RIP: 0010:native_safe_halt+0x6/0x10 [ 12.736925] RSP: 0018:ffffa41cc0cafe90 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff4d [ 12.737756] RAX: 0000000000000000 RBX: ffff8c2a761edb80 RCX: 0000000000000000 [ 12.738504] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 [ 12.739258] RBP: ffffa41cc0cafe90 R08: 0000014b5b9795e5 R09: ffffa41cc12c7e88 [ 12.740118] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000002 [ 12.740964] R13: ffff8c2a761edb80 R14: 0000000000000000 R15: 0000000000000000 [ 12.741831] default_idle+0x2a/0x100 [ 12.742323] arch_cpu_idle+0xf/0x20 [ 12.742796] default_idle_call+0x28/0x40 [ 12.743312] do_idle+0x179/0x1f0 [ 12.743761] cpu_startup_entry+0x1d/0x20 [ 12.744291] start_secondary+0x112/0x120 [ 12.744816] secondary_startup_64+0xa5/0xa5 [ 12.745367] Code: b9 f4 01 00 00 48 89 c2 48 c1 ea 02 48 3d d3 07 00 00 48 0f 47 d1 49 8b 0c 24 48 39 d1 76 07 49 89 14 24 48 89 d1 31 d2 48 89 df <48> f7 f1 89 c6 e8 81 6e ff ff 5b 41 5c 5d c3 66 90 66 2e 0f 1f [ 12.747527] RIP: tipc_node_calculate_timer.isra.12+0x45/0x60 [tipc] RSP: ffff8c2a7fc838a0 [ 12.748555] ---[ end trace 1399ab83390650fd ]--- [ 12.749296] Kernel panic - not syncing: Fatal exception in interrupt [ 12.750123] Kernel Offset: 0x13200000 from 0xffffffff82000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 12.751215] Rebooting in 60 seconds.. Fixes: c9b64d492b1f ("tipc: add replicast peer discovery") Signed-off-by: Tommi Rantala Cc: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/udp_media.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index ecca64fc6a6f..3deabcab4882 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -371,10 +371,6 @@ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb) goto rcu_out; } - tipc_rcv(sock_net(sk), skb, b); - rcu_read_unlock(); - return 0; - rcu_out: rcu_read_unlock(); out: -- cgit v1.2.3 From a0da456bbf95d2a9294799bb05c61bfb24736bb7 Mon Sep 17 00:00:00 2001 From: Max Uvarov Date: Thu, 30 Nov 2017 13:08:29 +0300 Subject: net: phy-micrel: check return code in flp center function Fix obvious typo that first return value is set but not checked. Signed-off-by: Max Uvarov Signed-off-by: David S. Miller --- drivers/net/phy/micrel.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index fdb43dd9b5cd..ab4614113403 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -496,16 +496,18 @@ static int ksz9031_of_load_skew_values(struct phy_device *phydev, return ksz9031_extended_write(phydev, OP_DATA, 2, reg, newval); } +/* Center KSZ9031RNX FLP timing at 16ms. */ static int ksz9031_center_flp_timing(struct phy_device *phydev) { int result; - /* Center KSZ9031RNX FLP timing at 16ms. */ result = ksz9031_extended_write(phydev, OP_DATA, 0, MII_KSZ9031RN_FLP_BURST_TX_HI, 0x0006); + if (result) + return result; + result = ksz9031_extended_write(phydev, OP_DATA, 0, MII_KSZ9031RN_FLP_BURST_TX_LO, 0x1A80); - if (result) return result; -- cgit v1.2.3 From acf1c02f023926b8b04672a9e81b1711ae681619 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 30 Nov 2017 13:59:11 +0000 Subject: sfp: fix RX_LOS signal handling The options word is a be16 quantity, so we need to test the flags having converted the endian-ness. Convert the flag bits to be16, which can be optimised by the compiler, rather than converting a variable at runtime. Reported-by: Florian Fainelli Signed-off-by: Russell King Signed-off-by: David S. Miller --- drivers/net/phy/sfp.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index e381811e5f11..3355141688a6 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -355,7 +355,7 @@ static void sfp_sm_link_check_los(struct sfp *sfp) * SFP_OPTIONS_LOS_NORMAL are set? For now, we assume * the same as SFP_OPTIONS_LOS_NORMAL set. */ - if (sfp->id.ext.options & SFP_OPTIONS_LOS_INVERTED) + if (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_LOS_INVERTED)) los ^= SFP_F_LOS; if (los) @@ -582,7 +582,8 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) if (event == SFP_E_TX_FAULT) sfp_sm_fault(sfp, true); else if (event == - (sfp->id.ext.options & SFP_OPTIONS_LOS_INVERTED ? + (sfp->id.ext.options & + cpu_to_be16(SFP_OPTIONS_LOS_INVERTED) ? SFP_E_LOS_HIGH : SFP_E_LOS_LOW)) sfp_sm_link_up(sfp); break; @@ -592,7 +593,8 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) sfp_sm_link_down(sfp); sfp_sm_fault(sfp, true); } else if (event == - (sfp->id.ext.options & SFP_OPTIONS_LOS_INVERTED ? + (sfp->id.ext.options & + cpu_to_be16(SFP_OPTIONS_LOS_INVERTED) ? SFP_E_LOS_LOW : SFP_E_LOS_HIGH)) { sfp_sm_link_down(sfp); sfp_sm_next(sfp, SFP_S_WAIT_LOS, 0); -- cgit v1.2.3 From 710dfbb01a8ac0fc8d0cc191131bd84dc3796497 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 30 Nov 2017 13:59:16 +0000 Subject: sfp: improve RX_LOS handling There are two bits in the option word for the RX_LOS signal. One reports that the RX_LOS signal is active high, the other reports that it is active low. When both or neither are set, the result is not well defined in the specification. Rather than assuming that neither set means normal RX_LOS, take this as meaning no RX_LOS signal available, thereby ignoring the signal. Signed-off-by: Russell King Signed-off-by: David S. Miller --- drivers/net/phy/sfp.c | 33 ++++++++++++++++++++++----------- 1 file changed, 22 insertions(+), 11 deletions(-) diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 3355141688a6..c1aab6a81ce9 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -351,12 +351,13 @@ static void sfp_sm_link_check_los(struct sfp *sfp) { unsigned int los = sfp->state & SFP_F_LOS; - /* FIXME: what if neither SFP_OPTIONS_LOS_INVERTED nor - * SFP_OPTIONS_LOS_NORMAL are set? For now, we assume - * the same as SFP_OPTIONS_LOS_NORMAL set. + /* If neither SFP_OPTIONS_LOS_INVERTED nor SFP_OPTIONS_LOS_NORMAL + * are set, we assume that no LOS signal is available. */ if (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_LOS_INVERTED)) los ^= SFP_F_LOS; + else if (!(sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_LOS_NORMAL))) + los = 0; if (los) sfp_sm_next(sfp, SFP_S_WAIT_LOS, 0); @@ -364,6 +365,22 @@ static void sfp_sm_link_check_los(struct sfp *sfp) sfp_sm_link_up(sfp); } +static bool sfp_los_event_active(struct sfp *sfp, unsigned int event) +{ + return (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_LOS_INVERTED) && + event == SFP_E_LOS_LOW) || + (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_LOS_NORMAL) && + event == SFP_E_LOS_HIGH); +} + +static bool sfp_los_event_inactive(struct sfp *sfp, unsigned int event) +{ + return (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_LOS_INVERTED) && + event == SFP_E_LOS_HIGH) || + (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_LOS_NORMAL) && + event == SFP_E_LOS_LOW); +} + static void sfp_sm_fault(struct sfp *sfp, bool warn) { if (sfp->sm_retries && !--sfp->sm_retries) { @@ -581,10 +598,7 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) case SFP_S_WAIT_LOS: if (event == SFP_E_TX_FAULT) sfp_sm_fault(sfp, true); - else if (event == - (sfp->id.ext.options & - cpu_to_be16(SFP_OPTIONS_LOS_INVERTED) ? - SFP_E_LOS_HIGH : SFP_E_LOS_LOW)) + else if (sfp_los_event_inactive(sfp, event)) sfp_sm_link_up(sfp); break; @@ -592,10 +606,7 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) if (event == SFP_E_TX_FAULT) { sfp_sm_link_down(sfp); sfp_sm_fault(sfp, true); - } else if (event == - (sfp->id.ext.options & - cpu_to_be16(SFP_OPTIONS_LOS_INVERTED) ? - SFP_E_LOS_LOW : SFP_E_LOS_HIGH)) { + } else if (sfp_los_event_active(sfp, event)) { sfp_sm_link_down(sfp); sfp_sm_next(sfp, SFP_S_WAIT_LOS, 0); } -- cgit v1.2.3 From ec7681bde6d0e53ea5ef564477c8656fc318023a Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 30 Nov 2017 13:59:21 +0000 Subject: sfp: warn about modules requiring address change sequence We do not support SFP modules which require the address change sequence as detailed by SFF 8472 revision 1.22 section 8.9. Warn when these modules are inserted, and treat them as SFF8079 modules for ethtool. Signed-off-by: Russell King Signed-off-by: David S. Miller --- drivers/net/phy/sfp.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index c1aab6a81ce9..9dfc1c4c954f 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -487,6 +487,11 @@ static int sfp_sm_mod_probe(struct sfp *sfp) return -EINVAL; } + /* If the module requires address swap mode, warn about it */ + if (sfp->id.ext.diagmon & SFP_DIAGMON_ADDRMODE) + dev_warn(sfp->dev, + "module address swap to access page 0xA2 is not supported.\n"); + return sfp_module_insert(sfp->sfp_bus, &sfp->id); } @@ -652,7 +657,8 @@ static int sfp_module_info(struct sfp *sfp, struct ethtool_modinfo *modinfo) { /* locking... and check module is present */ - if (sfp->id.ext.sff8472_compliance) { + if (sfp->id.ext.sff8472_compliance && + !(sfp->id.ext.diagmon & SFP_DIAGMON_ADDRMODE)) { modinfo->type = ETH_MODULE_SFF_8472; modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; } else { -- cgit v1.2.3 From 2012b7d6b2868c532f22d9172c8b24611637eb48 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 30 Nov 2017 13:59:26 +0000 Subject: phylink: ensure we take the link down when phylink_stop() is called Ensure that we tell the MAC to take the link down when phylink_stop() is called, and that this completes prior to phylink_stop() returns. Reported-by: Florian Fainelli Tested-by: Florian Fainelli Signed-off-by: Russell King Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index e3bbc70372d3..5dc9668dde34 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -773,6 +773,7 @@ void phylink_stop(struct phylink *pl) sfp_upstream_stop(pl->sfp_bus); set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state); + queue_work(system_power_efficient_wq, &pl->resolve); flush_work(&pl->resolve); } EXPORT_SYMBOL_GPL(phylink_stop); -- cgit v1.2.3 From a7f3f939dd7d8398acebecd1ceb2e9e7ffbe91d2 Mon Sep 17 00:00:00 2001 From: Ray Jui Date: Fri, 1 Dec 2017 03:13:02 -0500 Subject: bnxt_en: Need to unconditionally shut down RoCE in bnxt_shutdown The current 'bnxt_shutdown' implementation only invokes 'bnxt_ulp_shutdown' to shut down RoCE in the case when the system is in the path of power off (SYSTEM_POWER_OFF). While this may work in most cases, it does not work in the smart NIC case, when Linux 'reboot' command is initiated from the Linux that runs on the ARM cores of the NIC card. In this particular case, Linux 'reboot' results in a system 'L3' level reset where the entire ARM and associated subsystems are being reset, but at the same time, Nitro core is being kept in sane state (to allow external PCIe connected servers to continue to work). Without properly shutting down RoCE and freeing all associated resources, it results in the ARM core to hang immediately after the 'reboot' By always invoking 'bnxt_ulp_shutdown' in 'bnxt_shutdown', it fixes the above issue Fixes: 0efd2fc65c92 ("bnxt_en: Add a callback to inform RDMA driver during PCI shutdown.") Signed-off-by: Ray Jui Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c5c38d4b7d1c..7f173eb42aa2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -8263,8 +8263,9 @@ static void bnxt_shutdown(struct pci_dev *pdev) if (netif_running(dev)) dev_close(dev); + bnxt_ulp_shutdown(bp); + if (system_state == SYSTEM_POWER_OFF) { - bnxt_ulp_shutdown(bp); bnxt_clear_int_mode(bp); pci_wake_from_d3(pdev, bp->wol); pci_set_power_state(pdev, PCI_D3hot); -- cgit v1.2.3 From c8fb7b8259c67b86cd93a71c85e78b34d2c96fdc Mon Sep 17 00:00:00 2001 From: Sunil Challa Date: Fri, 1 Dec 2017 03:13:03 -0500 Subject: bnxt_en: wildcard smac while creating tunnel decap filter While creating a decap filter the tunnel smac need not (and must not) be specified as we cannot ascertain the neighbor in the recv path. 'ttl' match is also not needed for the decap filter and must be wild-carded. Fixes: f484f6782e01 ("bnxt_en: add hwrm FW cmds for cfa_encap_record and decap_filter") Signed-off-by: Sunil Challa Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index d5031f436f83..96bff48af971 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -532,10 +532,8 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp, } if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_ETH_ADDRS) { - enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR | - CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR; + enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR; ether_addr_copy(req.dst_macaddr, l2_info->dmac); - ether_addr_copy(req.src_macaddr, l2_info->smac); } if (l2_info->num_vlans) { enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_IVLAN_VID; @@ -1012,10 +1010,9 @@ static int bnxt_tc_get_decap_handle(struct bnxt *bp, struct bnxt_tc_flow *flow, if (rc) goto put_decap; - decap_key->ttl = tun_key.ttl; decap_l2_info = &decap_node->l2_info; + /* decap smac is wildcarded */ ether_addr_copy(decap_l2_info->dmac, l2_info.smac); - ether_addr_copy(decap_l2_info->smac, l2_info.dmac); if (l2_info.num_vlans) { decap_l2_info->num_vlans = l2_info.num_vlans; decap_l2_info->inner_vlan_tpid = l2_info.inner_vlan_tpid; -- cgit v1.2.3 From e9ecc731a87912d209d6e9b4ed20ed70451c08cb Mon Sep 17 00:00:00 2001 From: Sathya Perla Date: Fri, 1 Dec 2017 03:13:04 -0500 Subject: bnxt_en: fix dst/src fid for vxlan encap/decap actions For flows that involve a vxlan encap action, the vxlan sock interface may be specified as the outgoing interface. The driver must resolve the outgoing PF interface used by this socket and use the dst_fid of the PF in the hwrm_cfa_encap_record_alloc cmd. Similarily for flows that have a vxlan decap action, the fid of the incoming PF interface must be used as the src_fid in the hwrm_cfa_decap_filter_alloc cmd. Fixes: 8c95f773b4a3 ("bnxt_en: add support for Flower based vxlan encap/decap offload") Signed-off-by: Sathya Perla Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 48 +++++++++++++++------------- 1 file changed, 26 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 96bff48af971..3d201d7324bd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -56,7 +56,6 @@ static int bnxt_tc_parse_redir(struct bnxt *bp, { int ifindex = tcf_mirred_ifindex(tc_act); struct net_device *dev; - u16 dst_fid; dev = __dev_get_by_index(dev_net(bp->dev), ifindex); if (!dev) { @@ -64,15 +63,7 @@ static int bnxt_tc_parse_redir(struct bnxt *bp, return -EINVAL; } - /* find the FID from dev */ - dst_fid = bnxt_flow_get_dst_fid(bp, dev); - if (dst_fid == BNXT_FID_INVALID) { - netdev_info(bp->dev, "can't get fid for ifindex=%d", ifindex); - return -EINVAL; - } - actions->flags |= BNXT_TC_ACTION_FLAG_FWD; - actions->dst_fid = dst_fid; actions->dst_dev = dev; return 0; } @@ -160,13 +151,17 @@ static int bnxt_tc_parse_actions(struct bnxt *bp, if (rc) return rc; - /* Tunnel encap/decap action must be accompanied by a redirect action */ - if ((actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP || - actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_DECAP) && - !(actions->flags & BNXT_TC_ACTION_FLAG_FWD)) { - netdev_info(bp->dev, - "error: no redir action along with encap/decap"); - return -EINVAL; + if (actions->flags & BNXT_TC_ACTION_FLAG_FWD) { + if (actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP) { + /* dst_fid is PF's fid */ + actions->dst_fid = bp->pf.fw_fid; + } else { + /* find the FID from dst_dev */ + actions->dst_fid = + bnxt_flow_get_dst_fid(bp, actions->dst_dev); + if (actions->dst_fid == BNXT_FID_INVALID) + return -EINVAL; + } } return rc; @@ -899,10 +894,10 @@ static void bnxt_tc_put_decap_handle(struct bnxt *bp, static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp, struct ip_tunnel_key *tun_key, - struct bnxt_tc_l2_key *l2_info, - struct net_device *real_dst_dev) + struct bnxt_tc_l2_key *l2_info) { #ifdef CONFIG_INET + struct net_device *real_dst_dev = bp->dev; struct flowi4 flow = { {0} }; struct net_device *dst_dev; struct neighbour *nbr; @@ -1006,7 +1001,7 @@ static int bnxt_tc_get_decap_handle(struct bnxt *bp, struct bnxt_tc_flow *flow, */ tun_key.u.ipv4.dst = flow->tun_key.u.ipv4.src; tun_key.tp_dst = flow->tun_key.tp_dst; - rc = bnxt_tc_resolve_tunnel_hdrs(bp, &tun_key, &l2_info, bp->dev); + rc = bnxt_tc_resolve_tunnel_hdrs(bp, &tun_key, &l2_info); if (rc) goto put_decap; @@ -1092,8 +1087,7 @@ static int bnxt_tc_get_encap_handle(struct bnxt *bp, struct bnxt_tc_flow *flow, if (encap_node->tunnel_handle != INVALID_TUNNEL_HANDLE) goto done; - rc = bnxt_tc_resolve_tunnel_hdrs(bp, encap_key, &encap_node->l2_info, - flow->actions.dst_dev); + rc = bnxt_tc_resolve_tunnel_hdrs(bp, encap_key, &encap_node->l2_info); if (rc) goto put_encap; @@ -1166,6 +1160,15 @@ static int __bnxt_tc_del_flow(struct bnxt *bp, return 0; } +static void bnxt_tc_set_src_fid(struct bnxt *bp, struct bnxt_tc_flow *flow, + u16 src_fid) +{ + if (flow->actions.flags & BNXT_TC_ACTION_FLAG_TUNNEL_DECAP) + flow->src_fid = bp->pf.fw_fid; + else + flow->src_fid = src_fid; +} + /* Add a new flow or replace an existing flow. * Notes on locking: * There are essentially two critical sections here. @@ -1201,7 +1204,8 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid, rc = bnxt_tc_parse_flow(bp, tc_flow_cmd, flow); if (rc) goto free_node; - flow->src_fid = src_fid; + + bnxt_tc_set_src_fid(bp, flow, src_fid); if (!bnxt_tc_can_offload(bp, flow)) { rc = -ENOSPC; -- cgit v1.2.3 From ebd5818cc5d4847897d7fe872e2d9799d7b7fcbb Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Fri, 1 Dec 2017 03:13:05 -0500 Subject: bnxt_en: Fix a variable scoping in bnxt_hwrm_do_send_msg() short_input variable is assigned to another data pointer which is referred out of its scope. Fix it by moving short_input definition to the beginning of bnxt_hwrm_do_send_msg() function. No failure has been reported so far due to this issue. Fixes: e605db801bde ("bnxt_en: Support for Short Firmware Message") Signed-off-by: Vasundhara Volam Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 7f173eb42aa2..28f5e94274ee 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3368,6 +3368,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, u16 cp_ring_id, len = 0; struct hwrm_err_output *resp = bp->hwrm_cmd_resp_addr; u16 max_req_len = BNXT_HWRM_MAX_REQ_LEN; + struct hwrm_short_input short_input = {0}; req->seq_id = cpu_to_le16(bp->hwrm_cmd_seq++); memset(resp, 0, PAGE_SIZE); @@ -3376,7 +3377,6 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, if (bp->flags & BNXT_FLAG_SHORT_CMD) { void *short_cmd_req = bp->hwrm_short_cmd_req_addr; - struct hwrm_short_input short_input = {0}; memcpy(short_cmd_req, req, msg_len); memset(short_cmd_req + msg_len, 0, BNXT_HWRM_MAX_REQ_LEN - -- cgit v1.2.3 From 6e474083f3daf3a3546737f5d7d502ad12eb257c Mon Sep 17 00:00:00 2001 From: Wei Xu Date: Fri, 1 Dec 2017 05:10:36 -0500 Subject: vhost: fix skb leak in handle_rx() Matthew found a roughly 40% tcp throughput regression with commit c67df11f(vhost_net: try batch dequing from skb array) as discussed in the following thread: https://www.mail-archive.com/netdev@vger.kernel.org/msg187936.html Eventually we figured out that it was a skb leak in handle_rx() when sending packets to the VM. This usually happens when a guest can not drain out vq as fast as vhost fills in, afterwards it sets off the traffic jam and leaks skb(s) which occurs as no headcount to send on the vq from vhost side. This can be avoided by making sure we have got enough headcount before actually consuming a skb from the batched rx array while transmitting, which is simply done by moving checking the zero headcount a bit ahead. Signed-off-by: Wei Xu Reported-by: Matthew Rosato Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/vhost/net.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 8d626d7c2e7e..c7bdeb655646 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -778,16 +778,6 @@ static void handle_rx(struct vhost_net *net) /* On error, stop handling until the next kick. */ if (unlikely(headcount < 0)) goto out; - if (nvq->rx_array) - msg.msg_control = vhost_net_buf_consume(&nvq->rxq); - /* On overrun, truncate and discard */ - if (unlikely(headcount > UIO_MAXIOV)) { - iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1); - err = sock->ops->recvmsg(sock, &msg, - 1, MSG_DONTWAIT | MSG_TRUNC); - pr_debug("Discarded rx packet: len %zd\n", sock_len); - continue; - } /* OK, now we need to know about added descriptors. */ if (!headcount) { if (unlikely(vhost_enable_notify(&net->dev, vq))) { @@ -800,6 +790,16 @@ static void handle_rx(struct vhost_net *net) * they refilled. */ goto out; } + if (nvq->rx_array) + msg.msg_control = vhost_net_buf_consume(&nvq->rxq); + /* On overrun, truncate and discard */ + if (unlikely(headcount > UIO_MAXIOV)) { + iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1); + err = sock->ops->recvmsg(sock, &msg, + 1, MSG_DONTWAIT | MSG_TRUNC); + pr_debug("Discarded rx packet: len %zd\n", sock_len); + continue; + } /* We don't need to be notified again. */ iov_iter_init(&msg.msg_iter, READ, vq->iov, in, vhost_len); fixup = msg.msg_iter; -- cgit v1.2.3 From c33ee15b3820a03cf8229ba9415084197b827f8c Mon Sep 17 00:00:00 2001 From: Wei Xu Date: Fri, 1 Dec 2017 05:10:37 -0500 Subject: tun: free skb in early errors tun_recvmsg() supports accepting skb by msg_control after commit ac77cfd4258f ("tun: support receiving skb through msg_control"), the skb if presented should be freed no matter how far it can go along, otherwise it would be leaked. This patch fixes several missed cases. Signed-off-by: Wei Xu Reported-by: Matthew Rosato Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/tun.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 95749006d687..4f4a842a1c9c 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1952,8 +1952,11 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile, tun_debug(KERN_INFO, tun, "tun_do_read\n"); - if (!iov_iter_count(to)) + if (!iov_iter_count(to)) { + if (skb) + kfree_skb(skb); return 0; + } if (!skb) { /* Read frames from ring */ @@ -2069,22 +2072,24 @@ static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len, { struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); + struct sk_buff *skb = m->msg_control; int ret; - if (!tun) - return -EBADFD; + if (!tun) { + ret = -EBADFD; + goto out_free_skb; + } if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) { ret = -EINVAL; - goto out; + goto out_put_tun; } if (flags & MSG_ERRQUEUE) { ret = sock_recv_errqueue(sock->sk, m, total_len, SOL_PACKET, TUN_TX_TIMESTAMP); goto out; } - ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT, - m->msg_control); + ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT, skb); if (ret > (ssize_t)total_len) { m->msg_flags |= MSG_TRUNC; ret = flags & MSG_TRUNC ? ret : total_len; @@ -2092,6 +2097,13 @@ static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len, out: tun_put(tun); return ret; + +out_put_tun: + tun_put(tun); +out_free_skb: + if (skb) + kfree_skb(skb); + return ret; } static int tun_peek_len(struct socket *sock) -- cgit v1.2.3 From 61d78537843e676e7f56ac6db333db0c0529b892 Mon Sep 17 00:00:00 2001 From: Wei Xu Date: Fri, 1 Dec 2017 05:10:38 -0500 Subject: tap: free skb if flags error tap_recvmsg() supports accepting skb by msg_control after commit 3b4ba04acca8 ("tap: support receiving skb from msg_control"), the skb if presented should be freed within the function, otherwise it would be leaked. Signed-off-by: Wei Xu Reported-by: Matthew Rosato Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/tap.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index e9489b88407c..0a886fda0129 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -829,8 +829,11 @@ static ssize_t tap_do_read(struct tap_queue *q, DEFINE_WAIT(wait); ssize_t ret = 0; - if (!iov_iter_count(to)) + if (!iov_iter_count(to)) { + if (skb) + kfree_skb(skb); return 0; + } if (skb) goto put; @@ -1154,11 +1157,14 @@ static int tap_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len, int flags) { struct tap_queue *q = container_of(sock, struct tap_queue, sock); + struct sk_buff *skb = m->msg_control; int ret; - if (flags & ~(MSG_DONTWAIT|MSG_TRUNC)) + if (flags & ~(MSG_DONTWAIT|MSG_TRUNC)) { + if (skb) + kfree_skb(skb); return -EINVAL; - ret = tap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT, - m->msg_control); + } + ret = tap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT, skb); if (ret > total_len) { m->msg_flags |= MSG_TRUNC; ret = flags & MSG_TRUNC ? ret : total_len; -- cgit v1.2.3 From bc3ab70584696cb798b9e1e0ac8e6ced5fd4c3b8 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 1 Dec 2017 10:14:49 +0100 Subject: s390/qeth: fix thinko in IPv4 multicast address tracking Commit 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback") reworked how secondary addresses are managed for qeth devices. Instead of dropping & subsequently re-adding all addresses on every ndo_set_rx_mode() call, qeth now keeps track of the addresses that are currently registered with the HW. On a ndo_set_rx_mode(), we thus only need to do (de-)registration requests for the addresses that have actually changed. On L3 devices, the lookup for IPv4 Multicast addresses checks the wrong hashtable - and thus never finds a match. As a result, we first delete *all* such addresses, and then re-add them again. So each set_rx_mode() causes a short period where the IPv4 Multicast addresses are not registered, and the card stops forwarding inbound traffic for them. Fix this by setting the ->is_multicast flag on the lookup object, thus enabling qeth_l3_ip_from_hash() to search the correct hashtable and find a match there. Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback") Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_l3_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index aadd384316a3..e79936b50698 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1376,6 +1376,7 @@ qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev) tmp->u.a4.addr = be32_to_cpu(im4->multiaddr); memcpy(tmp->mac, buf, sizeof(tmp->mac)); + tmp->is_multicast = 1; ipm = qeth_l3_ip_from_hash(card, tmp); if (ipm) { -- cgit v1.2.3 From 6d69b1f1eb7a2edf8a3547f361c61f2538e054bb Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 1 Dec 2017 10:14:50 +0100 Subject: s390/qeth: fix GSO throughput regression Using GSO with small MTUs currently results in a substantial throughput regression - which is caused by how qeth needs to map non-linear skbs into its IO buffer elements: compared to a linear skb, each GSO-segmented skb effectively consumes twice as many buffer elements (ie two instead of one) due to the additional header-only part. This causes the Output Queue to be congested with low-utilized IO buffers. Fix this as follows: If the MSS is low enough so that a non-SG GSO segmentation produces order-0 skbs (currently ~3500 byte), opt out from NETIF_F_SG. This is where we anticipate the biggest savings, since an SG-enabled GSO segmentation produces skbs that always consume at least two buffer elements. Larger MSS values continue to get a SG-enabled GSO segmentation, since 1) the relative overhead of the additional header-only buffer element becomes less noticeable, and 2) the linearization overhead increases. With the throughput regression fixed, re-enable NETIF_F_SG by default to reap the significant CPU savings of GSO. Fixes: 5722963a8e83 ("qeth: do not turn on SG per default") Reported-by: Nils Hoppmann Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core.h | 3 +++ drivers/s390/net/qeth_core_main.c | 31 +++++++++++++++++++++++++++++++ drivers/s390/net/qeth_l2_main.c | 2 ++ drivers/s390/net/qeth_l3_main.c | 2 ++ 4 files changed, 38 insertions(+) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 9cd569ef43ec..15015a24f8ad 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -987,6 +987,9 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *, int qeth_set_features(struct net_device *, netdev_features_t); void qeth_recover_features(struct net_device *dev); netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t); +netdev_features_t qeth_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features); int qeth_vm_request_mac(struct qeth_card *card); int qeth_push_hdr(struct sk_buff *skb, struct qeth_hdr **hdr, unsigned int len); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 49b9efeba1bd..d9b0e07d4fa7 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -19,6 +19,11 @@ #include #include #include +#include +#include +#include +#include + #include #include @@ -6438,6 +6443,32 @@ netdev_features_t qeth_fix_features(struct net_device *dev, } EXPORT_SYMBOL_GPL(qeth_fix_features); +netdev_features_t qeth_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + /* GSO segmentation builds skbs with + * a (small) linear part for the headers, and + * page frags for the data. + * Compared to a linear skb, the header-only part consumes an + * additional buffer element. This reduces buffer utilization, and + * hurts throughput. So compress small segments into one element. + */ + if (netif_needs_gso(skb, features)) { + /* match skb_segment(): */ + unsigned int doffset = skb->data - skb_mac_header(skb); + unsigned int hsize = skb_shinfo(skb)->gso_size; + unsigned int hroom = skb_headroom(skb); + + /* linearize only if resulting skb allocations are order-0: */ + if (SKB_DATA_ALIGN(hroom + doffset + hsize) <= SKB_MAX_HEAD(0)) + features &= ~NETIF_F_SG; + } + + return vlan_features_check(skb, features); +} +EXPORT_SYMBOL_GPL(qeth_features_check); + static int __init qeth_core_init(void) { int rc; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index d2537c09126d..85162712d207 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -960,6 +960,7 @@ static const struct net_device_ops qeth_l2_netdev_ops = { .ndo_stop = qeth_l2_stop, .ndo_get_stats = qeth_get_stats, .ndo_start_xmit = qeth_l2_hard_start_xmit, + .ndo_features_check = qeth_features_check, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = qeth_l2_set_rx_mode, .ndo_do_ioctl = qeth_do_ioctl, @@ -1010,6 +1011,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) { card->dev->hw_features = NETIF_F_SG; card->dev->vlan_features = NETIF_F_SG; + card->dev->features |= NETIF_F_SG; /* OSA 3S and earlier has no RX/TX support */ if (qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) { card->dev->hw_features |= NETIF_F_IP_CSUM; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index e79936b50698..46a841258fc8 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2918,6 +2918,7 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = { .ndo_stop = qeth_l3_stop, .ndo_get_stats = qeth_get_stats, .ndo_start_xmit = qeth_l3_hard_start_xmit, + .ndo_features_check = qeth_features_check, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = qeth_l3_set_multicast_list, .ndo_do_ioctl = qeth_do_ioctl, @@ -2958,6 +2959,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) card->dev->vlan_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO; + card->dev->features |= NETIF_F_SG; } } } else if (card->info.type == QETH_CARD_TYPE_IQD) { -- cgit v1.2.3 From 0cbff6d4546613330a1c5f139f5c368e4ce33ca1 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 1 Dec 2017 10:14:51 +0100 Subject: s390/qeth: build max size GSO skbs on L2 devices The current GSO skb size limit was copy&pasted over from the L3 path, where it is needed due to a TSO limitation. As L2 devices don't offer TSO support (and thus all GSO skbs are segmented before they reach the driver), there's no reason to restrict the stack in how large it may build the GSO skbs. Fixes: d52aec97e5bc ("qeth: enable scatter/gather in layer 2 mode") Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_l2_main.c | 2 -- drivers/s390/net/qeth_l3_main.c | 4 ++-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 85162712d207..f21c94810373 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1030,8 +1030,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) card->info.broadcast_capable = 1; qeth_l2_request_initial_mac(card); - card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) * - PAGE_SIZE; SET_NETDEV_DEV(card->dev, &card->gdev->dev); netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT); netif_carrier_off(card->dev); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 46a841258fc8..2a25f20566d8 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2987,8 +2987,8 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; netif_keep_dst(card->dev); - card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) * - PAGE_SIZE; + netif_set_gso_max_size(card->dev, (QETH_MAX_BUFFER_ELEMENTS(card) - 1) * + PAGE_SIZE); SET_NETDEV_DEV(card->dev, &card->gdev->dev); netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT); -- cgit v1.2.3 From a98a4ebc8c61d20f0150d6be66e0e65223a347af Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Fri, 1 Dec 2017 09:58:42 +0800 Subject: ipvlan: Add the skb->mark as flow4's member to lookup route Current codes don't use skb->mark to assign flowi4_mark, it would make the policy route rule with fwmark doesn't work as expected. Signed-off-by: Gao Feng Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 11c1e7950fe5..77cc4fbaeace 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -393,6 +393,7 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb) .flowi4_oif = dev->ifindex, .flowi4_tos = RT_TOS(ip4h->tos), .flowi4_flags = FLOWI_FLAG_ANYSRC, + .flowi4_mark = skb->mark, .daddr = ip4h->daddr, .saddr = ip4h->saddr, }; -- cgit v1.2.3 From 45ab4b13e46325d00f4acdb365d406e941a15f81 Mon Sep 17 00:00:00 2001 From: Lars Persson Date: Fri, 1 Dec 2017 11:12:44 +0100 Subject: stmmac: reset last TSO segment size after device open The mss variable tracks the last max segment size sent to the TSO engine. We do not update the hardware as long as we receive skb:s with the same value in gso_size. During a network device down/up cycle (mapped to stmmac_release() and stmmac_open() callbacks) we issue a reset to the hardware and it forgets the setting for mss. However we did not zero out our mss variable so the next transmission of a gso packet happens with an undefined hardware setting. This triggers a hang in the TSO engine and eventuelly the netdev watchdog will bark. Fixes: f748be531d70 ("stmmac: support new GMAC4") Signed-off-by: Lars Persson Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f63c2ddced3c..d7250539d0bd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2588,6 +2588,7 @@ static int stmmac_open(struct net_device *dev) priv->dma_buf_sz = STMMAC_ALIGN(buf_sz); priv->rx_copybreak = STMMAC_RX_COPYBREAK; + priv->mss = 0; ret = alloc_dma_desc_resources(priv); if (ret < 0) { -- cgit v1.2.3 From 886afc1dc489436bf2c4fadf0f3aecacd7269234 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 1 Dec 2017 12:38:11 +0000 Subject: liquidio: fix incorrect indentation of assignment statement Remove one extraneous level of indentation on assignment statement. Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/liquidio/lio_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 6aa0eee88ea5..a5eecd895a82 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1113,7 +1113,7 @@ static int liquidio_watchdog(void *param) dev_err(&oct->pci_dev->dev, "ERROR: Octeon core %d crashed or got stuck! See oct-fwdump for details.\n", core); - err_msg_was_printed[core] = true; + err_msg_was_printed[core] = true; } } -- cgit v1.2.3 From c501256406fb19c306504ee1fe41a4ea208d4245 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 1 Dec 2017 11:09:53 +0000 Subject: rxrpc: Use correct netns source in rxrpc_release_sock() In rxrpc_release_sock() there may be no rx->local value to access, so we can't unconditionally follow it to the rxrpc network namespace information to poke the connection reapers. Instead, use the socket's namespace pointer to find the namespace. This unfixed code causes the following static checker warning: net/rxrpc/af_rxrpc.c:898 rxrpc_release_sock() error: we previously assumed 'rx->local' could be null (see line 887) Fixes: 3d18cbb7fd0c ("rxrpc: Fix conn expiry timers") Reported-by: Dan Carpenter Signed-off-by: David Howells Signed-off-by: David S. Miller --- net/rxrpc/af_rxrpc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 8f7cf4c042be..dcd818fa837e 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -860,6 +860,7 @@ static void rxrpc_sock_destructor(struct sock *sk) static int rxrpc_release_sock(struct sock *sk) { struct rxrpc_sock *rx = rxrpc_sk(sk); + struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); _enter("%p{%d,%d}", sk, sk->sk_state, refcount_read(&sk->sk_refcnt)); @@ -895,8 +896,8 @@ static int rxrpc_release_sock(struct sock *sk) rxrpc_release_calls_on_socket(rx); flush_workqueue(rxrpc_workqueue); rxrpc_purge_queue(&sk->sk_receive_queue); - rxrpc_queue_work(&rx->local->rxnet->service_conn_reaper); - rxrpc_queue_work(&rx->local->rxnet->client_conn_reaper); + rxrpc_queue_work(&rxnet->service_conn_reaper); + rxrpc_queue_work(&rxnet->client_conn_reaper); rxrpc_put_local(rx->local); rx->local = NULL; -- cgit v1.2.3 From bcd1d601e5cc760bf5743a59e4716603490e281c Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 1 Dec 2017 11:10:37 +0000 Subject: rxrpc: Fix the MAINTAINERS record Fix the MAINTAINERS record so that it's more obvious who the maintainer for AF_RXRPC is. Reported-by: Joe Perches Reported-by: David Miller Signed-off-by: David Howells Signed-off-by: David S. Miller --- MAINTAINERS | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 77d819b458a9..511b858405bc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -554,13 +554,13 @@ S: Orphan F: Documentation/filesystems/affs.txt F: fs/affs/ -AFS FILESYSTEM & AF_RXRPC SOCKET DOMAIN +AFS FILESYSTEM M: David Howells L: linux-afs@lists.infradead.org S: Supported F: fs/afs/ -F: include/net/af_rxrpc.h -F: net/rxrpc/af_rxrpc.c +F: include/trace/events/afs.h +F: Documentation/filesystems/afs.txt W: https://www.infradead.org/~dhowells/kafs/ AGPGART DRIVER @@ -11777,6 +11777,18 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jes/linux.git rtl8xxxu-deve S: Maintained F: drivers/net/wireless/realtek/rtl8xxxu/ +RXRPC SOCKETS (AF_RXRPC) +M: David Howells +L: linux-afs@lists.infradead.org +S: Supported +F: net/rxrpc/ +F: include/keys/rxrpc-type.h +F: include/net/af_rxrpc.h +F: include/trace/events/rxrpc.h +F: include/uapi/linux/rxrpc.h +F: Documentation/networking/rxrpc.txt +W: https://www.infradead.org/~dhowells/kafs/ + S3 SAVAGE FRAMEBUFFER DRIVER M: Antonino Daplas L: linux-fbdev@vger.kernel.org -- cgit v1.2.3 From eeea10b83a139451130df1594f26710c8fa390c8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 3 Dec 2017 09:32:59 -0800 Subject: tcp: add tcp_v4_fill_cb()/tcp_v4_restore_cb() James Morris reported kernel stack corruption bug [1] while running the SELinux testsuite, and bisected to a recent commit bffa72cf7f9d ("net: sk_buff rbnode reorg") We believe this commit is fine, but exposes an older bug. SELinux code runs from tcp_filter() and might send an ICMP, expecting IP options to be found in skb->cb[] using regular IPCB placement. We need to defer TCP mangling of skb->cb[] after tcp_filter() calls. This patch adds tcp_v4_fill_cb()/tcp_v4_restore_cb() in a very similar way we added them for IPv6. [1] [ 339.806024] SELinux: failure in selinux_parse_skb(), unable to parse packet [ 339.822505] Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: ffffffff81745af5 [ 339.822505] [ 339.852250] CPU: 4 PID: 3642 Comm: client Not tainted 4.15.0-rc1-test #15 [ 339.868498] Hardware name: LENOVO 10FGS0VA1L/30BC, BIOS FWKT68A 01/19/2017 [ 339.885060] Call Trace: [ 339.896875] [ 339.908103] dump_stack+0x63/0x87 [ 339.920645] panic+0xe8/0x248 [ 339.932668] ? ip_push_pending_frames+0x33/0x40 [ 339.946328] ? icmp_send+0x525/0x530 [ 339.958861] ? kfree_skbmem+0x60/0x70 [ 339.971431] __stack_chk_fail+0x1b/0x20 [ 339.984049] icmp_send+0x525/0x530 [ 339.996205] ? netlbl_skbuff_err+0x36/0x40 [ 340.008997] ? selinux_netlbl_err+0x11/0x20 [ 340.021816] ? selinux_socket_sock_rcv_skb+0x211/0x230 [ 340.035529] ? security_sock_rcv_skb+0x3b/0x50 [ 340.048471] ? sk_filter_trim_cap+0x44/0x1c0 [ 340.061246] ? tcp_v4_inbound_md5_hash+0x69/0x1b0 [ 340.074562] ? tcp_filter+0x2c/0x40 [ 340.086400] ? tcp_v4_rcv+0x820/0xa20 [ 340.098329] ? ip_local_deliver_finish+0x71/0x1a0 [ 340.111279] ? ip_local_deliver+0x6f/0xe0 [ 340.123535] ? ip_rcv_finish+0x3a0/0x3a0 [ 340.135523] ? ip_rcv_finish+0xdb/0x3a0 [ 340.147442] ? ip_rcv+0x27c/0x3c0 [ 340.158668] ? inet_del_offload+0x40/0x40 [ 340.170580] ? __netif_receive_skb_core+0x4ac/0x900 [ 340.183285] ? rcu_accelerate_cbs+0x5b/0x80 [ 340.195282] ? __netif_receive_skb+0x18/0x60 [ 340.207288] ? process_backlog+0x95/0x140 [ 340.218948] ? net_rx_action+0x26c/0x3b0 [ 340.230416] ? __do_softirq+0xc9/0x26a [ 340.241625] ? do_softirq_own_stack+0x2a/0x40 [ 340.253368] [ 340.262673] ? do_softirq+0x50/0x60 [ 340.273450] ? __local_bh_enable_ip+0x57/0x60 [ 340.285045] ? ip_finish_output2+0x175/0x350 [ 340.296403] ? ip_finish_output+0x127/0x1d0 [ 340.307665] ? nf_hook_slow+0x3c/0xb0 [ 340.318230] ? ip_output+0x72/0xe0 [ 340.328524] ? ip_fragment.constprop.54+0x80/0x80 [ 340.340070] ? ip_local_out+0x35/0x40 [ 340.350497] ? ip_queue_xmit+0x15c/0x3f0 [ 340.361060] ? __kmalloc_reserve.isra.40+0x31/0x90 [ 340.372484] ? __skb_clone+0x2e/0x130 [ 340.382633] ? tcp_transmit_skb+0x558/0xa10 [ 340.393262] ? tcp_connect+0x938/0xad0 [ 340.403370] ? ktime_get_with_offset+0x4c/0xb0 [ 340.414206] ? tcp_v4_connect+0x457/0x4e0 [ 340.424471] ? __inet_stream_connect+0xb3/0x300 [ 340.435195] ? inet_stream_connect+0x3b/0x60 [ 340.445607] ? SYSC_connect+0xd9/0x110 [ 340.455455] ? __audit_syscall_entry+0xaf/0x100 [ 340.466112] ? syscall_trace_enter+0x1d0/0x2b0 [ 340.476636] ? __audit_syscall_exit+0x209/0x290 [ 340.487151] ? SyS_connect+0xe/0x10 [ 340.496453] ? do_syscall_64+0x67/0x1b0 [ 340.506078] ? entry_SYSCALL64_slow_path+0x25/0x25 Fixes: 971f10eca186 ("tcp: better TCP_SKB_CB layout to reduce cache line misses") Signed-off-by: Eric Dumazet Reported-by: James Morris Tested-by: James Morris Tested-by: Casey Schaufler Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 59 ++++++++++++++++++++++++++++++++++++----------------- net/ipv6/tcp_ipv6.c | 10 +++++---- 2 files changed, 46 insertions(+), 23 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c6bc0c4d19c6..77ea45da0fe9 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1591,6 +1591,34 @@ int tcp_filter(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(tcp_filter); +static void tcp_v4_restore_cb(struct sk_buff *skb) +{ + memmove(IPCB(skb), &TCP_SKB_CB(skb)->header.h4, + sizeof(struct inet_skb_parm)); +} + +static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, + const struct tcphdr *th) +{ + /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB() + * barrier() makes sure compiler wont play fool^Waliasing games. + */ + memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb), + sizeof(struct inet_skb_parm)); + barrier(); + + TCP_SKB_CB(skb)->seq = ntohl(th->seq); + TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + + skb->len - th->doff * 4); + TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); + TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); + TCP_SKB_CB(skb)->tcp_tw_isn = 0; + TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); + TCP_SKB_CB(skb)->sacked = 0; + TCP_SKB_CB(skb)->has_rxtstamp = + skb->tstamp || skb_hwtstamps(skb)->hwtstamp; +} + /* * From tcp_input.c */ @@ -1631,24 +1659,6 @@ int tcp_v4_rcv(struct sk_buff *skb) th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); - /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB() - * barrier() makes sure compiler wont play fool^Waliasing games. - */ - memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb), - sizeof(struct inet_skb_parm)); - barrier(); - - TCP_SKB_CB(skb)->seq = ntohl(th->seq); - TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + - skb->len - th->doff * 4); - TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); - TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); - TCP_SKB_CB(skb)->tcp_tw_isn = 0; - TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); - TCP_SKB_CB(skb)->sacked = 0; - TCP_SKB_CB(skb)->has_rxtstamp = - skb->tstamp || skb_hwtstamps(skb)->hwtstamp; - lookup: sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source, th->dest, sdif, &refcounted); @@ -1679,14 +1689,19 @@ process: sock_hold(sk); refcounted = true; nsk = NULL; - if (!tcp_filter(sk, skb)) + if (!tcp_filter(sk, skb)) { + th = (const struct tcphdr *)skb->data; + iph = ip_hdr(skb); + tcp_v4_fill_cb(skb, iph, th); nsk = tcp_check_req(sk, skb, req, false); + } if (!nsk) { reqsk_put(req); goto discard_and_relse; } if (nsk == sk) { reqsk_put(req); + tcp_v4_restore_cb(skb); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); goto discard_and_relse; @@ -1712,6 +1727,7 @@ process: goto discard_and_relse; th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); + tcp_v4_fill_cb(skb, iph, th); skb->dev = NULL; @@ -1742,6 +1758,8 @@ no_tcp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; + tcp_v4_fill_cb(skb, iph, th); + if (tcp_checksum_complete(skb)) { csum_error: __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); @@ -1768,6 +1786,8 @@ do_time_wait: goto discard_it; } + tcp_v4_fill_cb(skb, iph, th); + if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; @@ -1784,6 +1804,7 @@ do_time_wait: if (sk2) { inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; + tcp_v4_restore_cb(skb); refcounted = false; goto process; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index be11dc13aa70..1f04ec0e4a7a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1454,7 +1454,6 @@ process: struct sock *nsk; sk = req->rsk_listener; - tcp_v6_fill_cb(skb, hdr, th); if (tcp_v6_inbound_md5_hash(sk, skb)) { sk_drops_add(sk, skb); reqsk_put(req); @@ -1467,8 +1466,12 @@ process: sock_hold(sk); refcounted = true; nsk = NULL; - if (!tcp_filter(sk, skb)) + if (!tcp_filter(sk, skb)) { + th = (const struct tcphdr *)skb->data; + hdr = ipv6_hdr(skb); + tcp_v6_fill_cb(skb, hdr, th); nsk = tcp_check_req(sk, skb, req, false); + } if (!nsk) { reqsk_put(req); goto discard_and_relse; @@ -1492,8 +1495,6 @@ process: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - tcp_v6_fill_cb(skb, hdr, th); - if (tcp_v6_inbound_md5_hash(sk, skb)) goto discard_and_relse; @@ -1501,6 +1502,7 @@ process: goto discard_and_relse; th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); + tcp_v6_fill_cb(skb, hdr, th); skb->dev = NULL; -- cgit v1.2.3 From b4d1605a8ea608fd7dc45b926a05d75d340bde4b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 3 Dec 2017 09:33:00 -0800 Subject: tcp: use IPCB instead of TCP_SKB_CB in inet_exact_dif_match() After this fix : ("tcp: add tcp_v4_fill_cb()/tcp_v4_restore_cb()"), socket lookups happen while skb->cb[] has not been mangled yet by TCP. Fixes: a04a480d4392 ("net: Require exact match for TCP socket lookups if dif is l3mdev") Signed-off-by: David Ahern Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 4e09398009c1..6998707e81f3 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -844,12 +844,11 @@ static inline int tcp_v6_sdif(const struct sk_buff *skb) } #endif -/* TCP_SKB_CB reference means this can not be used from early demux */ static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (!net->ipv4.sysctl_tcp_l3mdev_accept && - skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags)) + skb && ipv4_l3mdev_skb(IPCB(skb)->flags)) return true; #endif return false; -- cgit v1.2.3