From e757f741e9fa528d2ed72cc0ec369e402a5fdc9c Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 17 Mar 2021 13:54:31 +0100 Subject: [PATCH 1/5] json_print: Add print_tv() Add a helper to dump a timeval. Print by first converting to double and then dispatching to print_color_float(). Signed-off-by: Petr Machata Signed-off-by: David Ahern --- include/json_print.h | 1 + lib/json_print.c | 13 +++++++++++++ 2 files changed, 14 insertions(+) diff --git a/include/json_print.h b/include/json_print.h index 6fcf9fd9..91b34571 100644 --- a/include/json_print.h +++ b/include/json_print.h @@ -81,6 +81,7 @@ _PRINT_FUNC(0xhex, unsigned long long) _PRINT_FUNC(luint, unsigned long) _PRINT_FUNC(lluint, unsigned long long) _PRINT_FUNC(float, double) +_PRINT_FUNC(tv, const struct timeval *) #undef _PRINT_FUNC #define _PRINT_NAME_VALUE_FUNC(type_name, type, format_char) \ diff --git a/lib/json_print.c b/lib/json_print.c index 994a2f8d..e3a88375 100644 --- a/lib/json_print.c +++ b/lib/json_print.c @@ -299,6 +299,19 @@ int print_color_null(enum output_type type, return ret; } +int print_color_tv(enum output_type type, + enum color_attr color, + const char *key, + const char *fmt, + const struct timeval *tv) +{ + double usecs = tv->tv_usec; + double secs = tv->tv_sec; + double time = secs + usecs / 1000000; + + return print_color_float(type, color, key, fmt, time); +} + /* Print line separator (if not in JSON mode) */ void print_nl(void) { From 28fb925d8bf2578552f53598e7d7f29050a967b4 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 17 Mar 2021 13:54:32 +0100 Subject: [PATCH 2/5] nexthop: Extract a helper to parse a NH ID NH ID extraction is a common operation, and will become more common still with the resilient NH groups support. Add a helper that does what it usually done and returns the parsed NH ID. Signed-off-by: Petr Machata Signed-off-by: David Ahern --- ip/ipnexthop.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/ip/ipnexthop.c b/ip/ipnexthop.c index 20cde586..126b0b17 100644 --- a/ip/ipnexthop.c +++ b/ip/ipnexthop.c @@ -327,6 +327,15 @@ static int add_nh_group_attr(struct nlmsghdr *n, int maxlen, char *argv) return addattr_l(n, maxlen, NHA_GROUP, grps, count * sizeof(*grps)); } +static int ipnh_parse_id(const char *argv) +{ + __u32 id; + + if (get_unsigned(&id, argv, 0)) + invarg("invalid id value", argv); + return id; +} + static int ipnh_modify(int cmd, unsigned int flags, int argc, char **argv) { struct { @@ -343,12 +352,9 @@ static int ipnh_modify(int cmd, unsigned int flags, int argc, char **argv) while (argc > 0) { if (!strcmp(*argv, "id")) { - __u32 id; - NEXT_ARG(); - if (get_unsigned(&id, *argv, 0)) - invarg("invalid id value", *argv); - addattr32(&req.n, sizeof(req), NHA_ID, id); + addattr32(&req.n, sizeof(req), NHA_ID, + ipnh_parse_id(*argv)); } else if (!strcmp(*argv, "dev")) { int ifindex; @@ -485,12 +491,8 @@ static int ipnh_list_flush(int argc, char **argv, int action) if (!filter.master) invarg("VRF does not exist\n", *argv); } else if (!strcmp(*argv, "id")) { - __u32 id; - NEXT_ARG(); - if (get_unsigned(&id, *argv, 0)) - invarg("invalid id value", *argv); - return ipnh_get_id(id); + return ipnh_get_id(ipnh_parse_id(*argv)); } else if (!matches(*argv, "protocol")) { __u32 proto; @@ -536,8 +538,7 @@ static int ipnh_get(int argc, char **argv) while (argc > 0) { if (!strcmp(*argv, "id")) { NEXT_ARG(); - if (get_unsigned(&id, *argv, 0)) - invarg("invalid id value", *argv); + id = ipnh_parse_id(*argv); } else { usage(); } From b82d6b81fa84c85dc45e738c45fdb6ab09041b7d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 17 Mar 2021 13:54:33 +0100 Subject: [PATCH 3/5] nexthop: Add ability to specify group type Next patches are going to add a 'resilient' nexthop group type, so allow users to specify the type using the 'type' argument. Currently, only 'mpath' type is supported. These two commands are equivalent: # ip nexthop add id 10 group 1/2/3 # ip nexthop add id 10 group 1/2/3 type mpath Signed-off-by: Ido Schimmel Signed-off-by: Petr Machata Signed-off-by: David Ahern --- ip/ipnexthop.c | 32 +++++++++++++++++++++++++++++++- man/man8/ip-nexthop.8 | 19 +++++++++++++++++-- 2 files changed, 48 insertions(+), 3 deletions(-) diff --git a/ip/ipnexthop.c b/ip/ipnexthop.c index 126b0b17..5aae3262 100644 --- a/ip/ipnexthop.c +++ b/ip/ipnexthop.c @@ -42,8 +42,10 @@ static void usage(void) "SELECTOR := [ id ID ] [ dev DEV ] [ vrf NAME ] [ master DEV ]\n" " [ groups ] [ fdb ]\n" "NH := { blackhole | [ via ADDRESS ] [ dev DEV ] [ onlink ]\n" - " [ encap ENCAPTYPE ENCAPHDR ] | group GROUP [ fdb ] }\n" + " [ encap ENCAPTYPE ENCAPHDR ] |\n" + " group GROUP [ fdb ] [ type TYPE ] }\n" "GROUP := [ //... ]\n" + "TYPE := { mpath }\n" "ENCAPTYPE := [ mpls ]\n" "ENCAPHDR := [ MPLSLABEL ]\n"); exit(-1); @@ -327,6 +329,32 @@ static int add_nh_group_attr(struct nlmsghdr *n, int maxlen, char *argv) return addattr_l(n, maxlen, NHA_GROUP, grps, count * sizeof(*grps)); } +static int read_nh_group_type(const char *name) +{ + if (strcmp(name, "mpath") == 0) + return NEXTHOP_GRP_TYPE_MPATH; + + return __NEXTHOP_GRP_TYPE_MAX; +} + +static void parse_nh_group_type(struct nlmsghdr *n, int maxlen, int *argcp, + char ***argvp) +{ + char **argv = *argvp; + int argc = *argcp; + __u16 type; + + NEXT_ARG(); + type = read_nh_group_type(*argv); + if (type > NEXTHOP_GRP_TYPE_MAX) + invarg("\"type\" value is invalid\n", *argv); + + *argcp = argc; + *argvp = argv; + + addattr16(n, maxlen, NHA_GROUP_TYPE, type); +} + static int ipnh_parse_id(const char *argv) { __u32 id; @@ -409,6 +437,8 @@ static int ipnh_modify(int cmd, unsigned int flags, int argc, char **argv) if (add_nh_group_attr(&req.n, sizeof(req), *argv)) invarg("\"group\" value is invalid\n", *argv); + } else if (!strcmp(*argv, "type")) { + parse_nh_group_type(&req.n, sizeof(req), &argc, &argv); } else if (matches(*argv, "protocol") == 0) { __u32 prot; diff --git a/man/man8/ip-nexthop.8 b/man/man8/ip-nexthop.8 index 4d55f4db..b86f307f 100644 --- a/man/man8/ip-nexthop.8 +++ b/man/man8/ip-nexthop.8 @@ -54,7 +54,9 @@ ip-nexthop \- nexthop object management .BR fdb " ] | " .B group .IR GROUP " [ " -.BR fdb " ] } " +.BR fdb " ] [ " +.B type +.IR TYPE " ] } " .ti -8 .IR ENCAP " := [ " @@ -71,6 +73,10 @@ ip-nexthop \- nexthop object management .IR GROUP " := " .BR id "[," weight "[/...]" +.ti -8 +.IR TYPE " := { " +.BR mpath " }" + .SH DESCRIPTION .B ip nexthop is used to manipulate entries in the kernel's nexthop tables. @@ -122,9 +128,18 @@ is a set of encapsulation attributes specific to the .in -2 .TP -.BI group " GROUP" +.BI group " GROUP [ " type " TYPE ]" create a nexthop group. Group specification is id with an optional weight (id,weight) and a '/' as a separator between entries. +.sp +.I TYPE +is a string specifying the nexthop group type. Namely: + +.in +8 +.BI mpath +- Multipath nexthop group backed by the hash-threshold algorithm. The +default when the type is unspecified. + .TP .B blackhole create a blackhole nexthop From 91676718228b087b2742cd733cde43c5614b4c24 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 17 Mar 2021 13:54:34 +0100 Subject: [PATCH 4/5] nexthop: Add support for resilient nexthop groups Add ability to configure resilient nexthop groups and show their current configuration. Example: # ip nexthop add id 10 group 1/2 type resilient buckets 8 # ip nexthop show id 10 id 10 group 1/2 type resilient buckets 8 idle_timer 120 unbalanced_timer 0 # ip -j -p nexthop show id 10 [ { "id": 10, "group": [ { "id": 1 },{ "id": 2 } ], "type": "resilient", "resilient_args": { "buckets": 8, "idle_timer": 120, "unbalanced_timer": 0 }, "flags": [ ] } ] Signed-off-by: Ido Schimmel Signed-off-by: Petr Machata Signed-off-by: David Ahern --- ip/ipnexthop.c | 144 +++++++++++++++++++++++++++++++++++++++++- man/man8/ip-nexthop.8 | 55 +++++++++++++++- 2 files changed, 193 insertions(+), 6 deletions(-) diff --git a/ip/ipnexthop.c b/ip/ipnexthop.c index 5aae3262..1d50bf75 100644 --- a/ip/ipnexthop.c +++ b/ip/ipnexthop.c @@ -43,9 +43,12 @@ static void usage(void) " [ groups ] [ fdb ]\n" "NH := { blackhole | [ via ADDRESS ] [ dev DEV ] [ onlink ]\n" " [ encap ENCAPTYPE ENCAPHDR ] |\n" - " group GROUP [ fdb ] [ type TYPE ] }\n" + " group GROUP [ fdb ] [ type TYPE [ TYPE_ARGS ] ] }\n" "GROUP := [ //... ]\n" - "TYPE := { mpath }\n" + "TYPE := { mpath | resilient }\n" + "TYPE_ARGS := [ RESILIENT_ARGS ]\n" + "RESILIENT_ARGS := [ buckets BUCKETS ] [ idle_timer IDLE ]\n" + " [ unbalanced_timer UNBALANCED ]\n" "ENCAPTYPE := [ mpls ]\n" "ENCAPHDR := [ MPLSLABEL ]\n"); exit(-1); @@ -203,6 +206,66 @@ static void print_nh_group(FILE *fp, const struct rtattr *grps_attr) close_json_array(PRINT_JSON, NULL); } +static const char *nh_group_type_name(__u16 type) +{ + switch (type) { + case NEXTHOP_GRP_TYPE_MPATH: + return "mpath"; + case NEXTHOP_GRP_TYPE_RES: + return "resilient"; + default: + return ""; + } +} + +static void print_nh_group_type(FILE *fp, const struct rtattr *grp_type_attr) +{ + __u16 type = rta_getattr_u16(grp_type_attr); + + if (type == NEXTHOP_GRP_TYPE_MPATH) + /* Do not print type in order not to break existing output. */ + return; + + print_string(PRINT_ANY, "type", "type %s ", nh_group_type_name(type)); +} + +static void print_nh_res_group(FILE *fp, const struct rtattr *res_grp_attr) +{ + struct rtattr *tb[NHA_RES_GROUP_MAX + 1]; + struct rtattr *rta; + struct timeval tv; + + parse_rtattr_nested(tb, NHA_RES_GROUP_MAX, res_grp_attr); + + open_json_object("resilient_args"); + + if (tb[NHA_RES_GROUP_BUCKETS]) + print_uint(PRINT_ANY, "buckets", "buckets %u ", + rta_getattr_u16(tb[NHA_RES_GROUP_BUCKETS])); + + if (tb[NHA_RES_GROUP_IDLE_TIMER]) { + rta = tb[NHA_RES_GROUP_IDLE_TIMER]; + __jiffies_to_tv(&tv, rta_getattr_u32(rta)); + print_tv(PRINT_ANY, "idle_timer", "idle_timer %g ", &tv); + } + + if (tb[NHA_RES_GROUP_UNBALANCED_TIMER]) { + rta = tb[NHA_RES_GROUP_UNBALANCED_TIMER]; + __jiffies_to_tv(&tv, rta_getattr_u32(rta)); + print_tv(PRINT_ANY, "unbalanced_timer", "unbalanced_timer %g ", + &tv); + } + + if (tb[NHA_RES_GROUP_UNBALANCED_TIME]) { + rta = tb[NHA_RES_GROUP_UNBALANCED_TIME]; + __jiffies_to_tv(&tv, rta_getattr_u32(rta)); + print_tv(PRINT_ANY, "unbalanced_time", "unbalanced_time %g ", + &tv); + } + + close_json_object(); +} + int print_nexthop(struct nlmsghdr *n, void *arg) { struct nhmsg *nhm = NLMSG_DATA(n); @@ -229,7 +292,7 @@ int print_nexthop(struct nlmsghdr *n, void *arg) if (filter.proto && filter.proto != nhm->nh_protocol) return 0; - parse_rtattr(tb, NHA_MAX, RTM_NHA(nhm), len); + parse_rtattr_flags(tb, NHA_MAX, RTM_NHA(nhm), len, NLA_F_NESTED); open_json_object(NULL); @@ -243,6 +306,12 @@ int print_nexthop(struct nlmsghdr *n, void *arg) if (tb[NHA_GROUP]) print_nh_group(fp, tb[NHA_GROUP]); + if (tb[NHA_GROUP_TYPE]) + print_nh_group_type(fp, tb[NHA_GROUP_TYPE]); + + if (tb[NHA_RES_GROUP]) + print_nh_res_group(fp, tb[NHA_RES_GROUP]); + if (tb[NHA_ENCAP]) lwt_print_encap(fp, tb[NHA_ENCAP_TYPE], tb[NHA_ENCAP]); @@ -333,10 +402,70 @@ static int read_nh_group_type(const char *name) { if (strcmp(name, "mpath") == 0) return NEXTHOP_GRP_TYPE_MPATH; + else if (strcmp(name, "resilient") == 0) + return NEXTHOP_GRP_TYPE_RES; return __NEXTHOP_GRP_TYPE_MAX; } +static void parse_nh_group_type_res(struct nlmsghdr *n, int maxlen, int *argcp, + char ***argvp) +{ + char **argv = *argvp; + struct rtattr *nest; + int argc = *argcp; + + if (!NEXT_ARG_OK()) + return; + + nest = addattr_nest(n, maxlen, NHA_RES_GROUP); + nest->rta_type |= NLA_F_NESTED; + + NEXT_ARG_FWD(); + while (argc > 0) { + if (strcmp(*argv, "buckets") == 0) { + __u16 buckets; + + NEXT_ARG(); + if (get_u16(&buckets, *argv, 0)) + invarg("invalid buckets value", *argv); + + addattr16(n, maxlen, NHA_RES_GROUP_BUCKETS, buckets); + } else if (strcmp(*argv, "idle_timer") == 0) { + __u32 idle_timer; + + NEXT_ARG(); + if (get_unsigned(&idle_timer, *argv, 0) || + idle_timer >= ~0UL / 100) + invarg("invalid idle timer value", *argv); + + addattr32(n, maxlen, NHA_RES_GROUP_IDLE_TIMER, + idle_timer * 100); + } else if (strcmp(*argv, "unbalanced_timer") == 0) { + __u32 unbalanced_timer; + + NEXT_ARG(); + if (get_unsigned(&unbalanced_timer, *argv, 0) || + unbalanced_timer >= ~0UL / 100) + invarg("invalid unbalanced timer value", *argv); + + addattr32(n, maxlen, NHA_RES_GROUP_UNBALANCED_TIMER, + unbalanced_timer * 100); + } else { + break; + } + argc--; argv++; + } + + /* argv is currently the first unparsed argument, but ipnh_modify() + * will move to the next, so step back. + */ + *argcp = argc + 1; + *argvp = argv - 1; + + addattr_nest_end(n, nest); +} + static void parse_nh_group_type(struct nlmsghdr *n, int maxlen, int *argcp, char ***argvp) { @@ -349,6 +478,15 @@ static void parse_nh_group_type(struct nlmsghdr *n, int maxlen, int *argcp, if (type > NEXTHOP_GRP_TYPE_MAX) invarg("\"type\" value is invalid\n", *argv); + switch (type) { + case NEXTHOP_GRP_TYPE_MPATH: + /* No additional arguments */ + break; + case NEXTHOP_GRP_TYPE_RES: + parse_nh_group_type_res(n, maxlen, &argc, &argv); + break; + } + *argcp = argc; *argvp = argv; diff --git a/man/man8/ip-nexthop.8 b/man/man8/ip-nexthop.8 index b86f307f..c1ac130c 100644 --- a/man/man8/ip-nexthop.8 +++ b/man/man8/ip-nexthop.8 @@ -56,7 +56,7 @@ ip-nexthop \- nexthop object management .IR GROUP " [ " .BR fdb " ] [ " .B type -.IR TYPE " ] } " +.IR TYPE " [ " TYPE_ARGS " ] ] }" .ti -8 .IR ENCAP " := [ " @@ -75,7 +75,20 @@ ip-nexthop \- nexthop object management .ti -8 .IR TYPE " := { " -.BR mpath " }" +.BR mpath " | " resilient " }" + +.ti -8 +.IR TYPE_ARGS " := [ " +.IR RESILIENT_ARGS " ] " + +.ti -8 +.IR RESILIENT_ARGS " := " +.RB "[ " buckets +.IR BUCKETS " ] [ " +.B idle_timer +.IR IDLE " ] [ " +.B unbalanced_timer +.IR UNBALANCED " ]" .SH DESCRIPTION .B ip nexthop @@ -128,7 +141,7 @@ is a set of encapsulation attributes specific to the .in -2 .TP -.BI group " GROUP [ " type " TYPE ]" +.BI group " GROUP [ " type " TYPE [ TYPE_ARGS ] ]" create a nexthop group. Group specification is id with an optional weight (id,weight) and a '/' as a separator between entries. .sp @@ -139,6 +152,37 @@ is a string specifying the nexthop group type. Namely: .BI mpath - Multipath nexthop group backed by the hash-threshold algorithm. The default when the type is unspecified. +.sp +.BI resilient +- Resilient nexthop group. Group is resilient to addition and deletion of +nexthops. + +.sp +.in -8 +.I TYPE_ARGS +is a set of attributes specific to the +.I TYPE. + +.in +8 +.B resilient +.in +2 +.B buckets +.I BUCKETS +- Number of nexthop buckets. Cannot be changed for an existing group +.sp + +.B idle_timer +.I IDLE +- Time in seconds in which a nexthop bucket does not see traffic and is +therefore considered idle. Default is 120 seconds + +.B unbalanced_timer +.I UNBALANCED +- Time in seconds in which a nexthop group is unbalanced and is therefore +considered unbalanced. The kernel will try to rebalance unbalanced groups, which +might result in some flows being reset. A value of 0 means that no +rebalancing will take place. Default is 0 seconds +.in -2 .TP .B blackhole @@ -225,6 +269,11 @@ ip nexthop add id 7 group 5/6 fdb Adds a fdb nexthop group with id 7. A fdb nexthop group can only have fdb nexthops. .RE +.PP +ip nexthop add id 10 group 1/2 type resilient buckets 32 +.RS 4 +Add a resilient nexthop group with id 10 and 32 nexthop buckets. +.RE .SH SEE ALSO .br .BR ip (8) From 2be6d18b309b7d2a41336f4fd1c201f20b3a50e4 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 17 Mar 2021 13:54:35 +0100 Subject: [PATCH 5/5] nexthop: Add support for nexthop buckets Add ability to dump multiple nexthop buckets and get a specific one. Example: # ip nexthop add id 10 group 1/2 type resilient buckets 8 # ip nexthop id 1 via 192.0.2.2 dev dummy10 scope link id 2 via 192.0.2.19 dev dummy20 scope link id 10 group 1/2 type resilient buckets 8 idle_timer 120 unbalanced_timer 0 unbalanced_time 0 # ip nexthop bucket id 10 index 0 idle_time 28.1 nhid 2 id 10 index 1 idle_time 28.1 nhid 2 id 10 index 2 idle_time 28.1 nhid 2 id 10 index 3 idle_time 28.1 nhid 2 id 10 index 4 idle_time 28.1 nhid 1 id 10 index 5 idle_time 28.1 nhid 1 id 10 index 6 idle_time 28.1 nhid 1 id 10 index 7 idle_time 28.1 nhid 1 # ip nexthop bucket show nhid 1 id 10 index 4 idle_time 53.59 nhid 1 id 10 index 5 idle_time 53.59 nhid 1 id 10 index 6 idle_time 53.59 nhid 1 id 10 index 7 idle_time 53.59 nhid 1 # ip nexthop bucket get id 10 index 5 id 10 index 5 idle_time 81 nhid 1 # ip -j -p nexthop bucket get id 10 index 5 [ { "id": 10, "bucket": { "index": 5, "idle_time": 104.89, "nhid": 1 }, "flags": [ ] } ] Signed-off-by: Ido Schimmel Signed-off-by: Petr Machata Signed-off-by: David Ahern --- include/libnetlink.h | 3 + ip/ip_common.h | 1 + ip/ipmonitor.c | 6 + ip/ipnexthop.c | 254 ++++++++++++++++++++++++++++++++++++++++++ lib/libnetlink.c | 26 +++++ man/man8/ip-nexthop.8 | 45 ++++++++ 6 files changed, 335 insertions(+) diff --git a/include/libnetlink.h b/include/libnetlink.h index b9073a6a..e8ed5d7f 100644 --- a/include/libnetlink.h +++ b/include/libnetlink.h @@ -97,6 +97,9 @@ int rtnl_dump_request_n(struct rtnl_handle *rth, struct nlmsghdr *n) int rtnl_nexthopdump_req(struct rtnl_handle *rth, int family, req_filter_fn_t filter_fn) __attribute__((warn_unused_result)); +int rtnl_nexthop_bucket_dump_req(struct rtnl_handle *rth, int family, + req_filter_fn_t filter_fn) + __attribute__((warn_unused_result)); struct rtnl_ctrl_data { int nsid; diff --git a/ip/ip_common.h b/ip/ip_common.h index 9a31e837..55a5521c 100644 --- a/ip/ip_common.h +++ b/ip/ip_common.h @@ -53,6 +53,7 @@ int print_rule(struct nlmsghdr *n, void *arg); int print_netconf(struct rtnl_ctrl_data *ctrl, struct nlmsghdr *n, void *arg); int print_nexthop(struct nlmsghdr *n, void *arg); +int print_nexthop_bucket(struct nlmsghdr *n, void *arg); void netns_map_init(void); void netns_nsid_socket_init(void); int print_nsid(struct nlmsghdr *n, void *arg); diff --git a/ip/ipmonitor.c b/ip/ipmonitor.c index 99f5fda8..d7f31cf5 100644 --- a/ip/ipmonitor.c +++ b/ip/ipmonitor.c @@ -90,6 +90,12 @@ static int accept_msg(struct rtnl_ctrl_data *ctrl, print_nexthop(n, arg); return 0; + case RTM_NEWNEXTHOPBUCKET: + case RTM_DELNEXTHOPBUCKET: + print_headers(fp, "[NEXTHOPBUCKET]", ctrl); + print_nexthop_bucket(n, arg); + return 0; + case RTM_NEWLINK: case RTM_DELLINK: ll_remember_index(n, NULL); diff --git a/ip/ipnexthop.c b/ip/ipnexthop.c index 1d50bf75..0263307c 100644 --- a/ip/ipnexthop.c +++ b/ip/ipnexthop.c @@ -21,6 +21,8 @@ static struct { unsigned int master; unsigned int proto; unsigned int fdb; + unsigned int id; + unsigned int nhid; } filter; enum { @@ -39,8 +41,11 @@ static void usage(void) "Usage: ip nexthop { list | flush } [ protocol ID ] SELECTOR\n" " ip nexthop { add | replace } id ID NH [ protocol ID ]\n" " ip nexthop { get | del } id ID\n" + " ip nexthop bucket list BUCKET_SELECTOR\n" + " ip nexthop bucket get id ID index INDEX\n" "SELECTOR := [ id ID ] [ dev DEV ] [ vrf NAME ] [ master DEV ]\n" " [ groups ] [ fdb ]\n" + "BUCKET_SELECTOR := SELECTOR | [ nhid ID ]\n" "NH := { blackhole | [ via ADDRESS ] [ dev DEV ] [ onlink ]\n" " [ encap ENCAPTYPE ENCAPHDR ] |\n" " group GROUP [ fdb ] [ type TYPE [ TYPE_ARGS ] ] }\n" @@ -85,6 +90,36 @@ static int nh_dump_filter(struct nlmsghdr *nlh, int reqlen) return 0; } +static int nh_dump_bucket_filter(struct nlmsghdr *nlh, int reqlen) +{ + struct rtattr *nest; + int err = 0; + + err = nh_dump_filter(nlh, reqlen); + if (err) + return err; + + if (filter.id) { + err = addattr32(nlh, reqlen, NHA_ID, filter.id); + if (err) + return err; + } + + if (filter.nhid) { + nest = addattr_nest(nlh, reqlen, NHA_RES_BUCKET); + nest->rta_type |= NLA_F_NESTED; + + err = addattr32(nlh, reqlen, NHA_RES_BUCKET_NH_ID, + filter.nhid); + if (err) + return err; + + addattr_nest_end(nlh, nest); + } + + return err; +} + static struct rtnl_handle rth_del = { .fd = -1 }; static int delete_nexthop(__u32 id) @@ -266,6 +301,33 @@ static void print_nh_res_group(FILE *fp, const struct rtattr *res_grp_attr) close_json_object(); } +static void print_nh_res_bucket(FILE *fp, const struct rtattr *res_bucket_attr) +{ + struct rtattr *tb[NHA_RES_BUCKET_MAX + 1]; + + parse_rtattr_nested(tb, NHA_RES_BUCKET_MAX, res_bucket_attr); + + open_json_object("bucket"); + + if (tb[NHA_RES_BUCKET_INDEX]) + print_uint(PRINT_ANY, "index", "index %u ", + rta_getattr_u16(tb[NHA_RES_BUCKET_INDEX])); + + if (tb[NHA_RES_BUCKET_IDLE_TIME]) { + struct rtattr *rta = tb[NHA_RES_BUCKET_IDLE_TIME]; + struct timeval tv; + + __jiffies_to_tv(&tv, rta_getattr_u64(rta)); + print_tv(PRINT_ANY, "idle_time", "idle_time %g ", &tv); + } + + if (tb[NHA_RES_BUCKET_NH_ID]) + print_uint(PRINT_ANY, "nhid", "nhid %u ", + rta_getattr_u32(tb[NHA_RES_BUCKET_NH_ID])); + + close_json_object(); +} + int print_nexthop(struct nlmsghdr *n, void *arg) { struct nhmsg *nhm = NLMSG_DATA(n); @@ -346,6 +408,50 @@ int print_nexthop(struct nlmsghdr *n, void *arg) return 0; } +int print_nexthop_bucket(struct nlmsghdr *n, void *arg) +{ + struct nhmsg *nhm = NLMSG_DATA(n); + struct rtattr *tb[NHA_MAX+1]; + FILE *fp = (FILE *)arg; + int len; + + if (n->nlmsg_type != RTM_DELNEXTHOPBUCKET && + n->nlmsg_type != RTM_NEWNEXTHOPBUCKET) { + fprintf(stderr, "Not a nexthop bucket: %08x %08x %08x\n", + n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags); + return -1; + } + + len = n->nlmsg_len - NLMSG_SPACE(sizeof(*nhm)); + if (len < 0) { + close_json_object(); + fprintf(stderr, "BUG: wrong nlmsg len %d\n", len); + return -1; + } + + parse_rtattr_flags(tb, NHA_MAX, RTM_NHA(nhm), len, NLA_F_NESTED); + + open_json_object(NULL); + + if (n->nlmsg_type == RTM_DELNEXTHOP) + print_bool(PRINT_ANY, "deleted", "Deleted ", true); + + if (tb[NHA_ID]) + print_uint(PRINT_ANY, "id", "id %u ", + rta_getattr_u32(tb[NHA_ID])); + + if (tb[NHA_RES_BUCKET]) + print_nh_res_bucket(fp, tb[NHA_RES_BUCKET]); + + print_rt_flags(fp, nhm->nh_flags); + + print_string(PRINT_FP, NULL, "%s", "\n"); + close_json_object(); + fflush(fp); + + return 0; +} + static int add_nh_group_attr(struct nlmsghdr *n, int maxlen, char *argv) { struct nexthop_grp *grps; @@ -721,6 +827,151 @@ static int ipnh_get(int argc, char **argv) return ipnh_get_id(id); } +static int ipnh_bucket_list(int argc, char **argv) +{ + while (argc > 0) { + if (!matches(*argv, "dev")) { + NEXT_ARG(); + filter.ifindex = ll_name_to_index(*argv); + if (!filter.ifindex) + invarg("Device does not exist\n", *argv); + } else if (!matches(*argv, "master")) { + NEXT_ARG(); + filter.master = ll_name_to_index(*argv); + if (!filter.master) + invarg("Device does not exist\n", *argv); + } else if (matches(*argv, "vrf") == 0) { + NEXT_ARG(); + if (!name_is_vrf(*argv)) + invarg("Invalid VRF\n", *argv); + filter.master = ll_name_to_index(*argv); + if (!filter.master) + invarg("VRF does not exist\n", *argv); + } else if (!strcmp(*argv, "id")) { + NEXT_ARG(); + filter.id = ipnh_parse_id(*argv); + } else if (!strcmp(*argv, "nhid")) { + NEXT_ARG(); + filter.nhid = ipnh_parse_id(*argv); + } else if (matches(*argv, "help") == 0) { + usage(); + } else { + invarg("", *argv); + } + argc--; argv++; + } + + if (rtnl_nexthop_bucket_dump_req(&rth, preferred_family, + nh_dump_bucket_filter) < 0) { + perror("Cannot send dump request"); + return -2; + } + + new_json_obj(json); + + if (rtnl_dump_filter(&rth, print_nexthop_bucket, stdout) < 0) { + fprintf(stderr, "Dump terminated\n"); + return -2; + } + + delete_json_obj(); + fflush(stdout); + + return 0; +} + +static int ipnh_bucket_get_id(__u32 id, __u16 bucket_index) +{ + struct { + struct nlmsghdr n; + struct nhmsg nhm; + char buf[1024]; + } req = { + .n.nlmsg_len = NLMSG_LENGTH(sizeof(struct nhmsg)), + .n.nlmsg_flags = NLM_F_REQUEST, + .n.nlmsg_type = RTM_GETNEXTHOPBUCKET, + .nhm.nh_family = preferred_family, + }; + struct nlmsghdr *answer; + struct rtattr *nest; + + addattr32(&req.n, sizeof(req), NHA_ID, id); + + nest = addattr_nest(&req.n, sizeof(req), NHA_RES_BUCKET); + nest->rta_type |= NLA_F_NESTED; + + addattr16(&req.n, sizeof(req), NHA_RES_BUCKET_INDEX, bucket_index); + + addattr_nest_end(&req.n, nest); + + if (rtnl_talk(&rth, &req.n, &answer) < 0) + return -2; + + new_json_obj(json); + + if (print_nexthop_bucket(answer, (void *)stdout) < 0) { + free(answer); + return -1; + } + + delete_json_obj(); + fflush(stdout); + + free(answer); + + return 0; +} + +static int ipnh_bucket_get(int argc, char **argv) +{ + bool bucket_valid = false; + __u16 bucket_index; + __u32 id = 0; + + while (argc > 0) { + if (!strcmp(*argv, "id")) { + NEXT_ARG(); + id = ipnh_parse_id(*argv); + } else if (!strcmp(*argv, "index")) { + NEXT_ARG(); + if (get_u16(&bucket_index, *argv, 0)) + invarg("invalid bucket index value", *argv); + bucket_valid = true; + } else { + usage(); + } + argc--; argv++; + } + + if (!id || !bucket_valid) { + usage(); + return -1; + } + + return ipnh_bucket_get_id(id, bucket_index); +} + +static int do_ipnh_bucket(int argc, char **argv) +{ + if (argc < 1) + return ipnh_bucket_list(0, NULL); + + if (!matches(*argv, "list") || + !matches(*argv, "show") || + !matches(*argv, "lst")) + return ipnh_bucket_list(argc-1, argv+1); + + if (!matches(*argv, "get")) + return ipnh_bucket_get(argc-1, argv+1); + + if (!matches(*argv, "help")) + usage(); + + fprintf(stderr, + "Command \"%s\" is unknown, try \"ip nexthop help\".\n", *argv); + exit(-1); +} + int do_ipnh(int argc, char **argv) { if (argc < 1) @@ -746,6 +997,9 @@ int do_ipnh(int argc, char **argv) if (!matches(*argv, "flush")) return ipnh_list_flush(argc-1, argv+1, IPNH_FLUSH); + if (!matches(*argv, "bucket")) + return do_ipnh_bucket(argc-1, argv+1); + if (!matches(*argv, "help")) usage(); diff --git a/lib/libnetlink.c b/lib/libnetlink.c index c958aa57..6885087b 100644 --- a/lib/libnetlink.c +++ b/lib/libnetlink.c @@ -282,6 +282,32 @@ int rtnl_nexthopdump_req(struct rtnl_handle *rth, int family, return send(rth->fd, &req, sizeof(req), 0); } +int rtnl_nexthop_bucket_dump_req(struct rtnl_handle *rth, int family, + req_filter_fn_t filter_fn) +{ + struct { + struct nlmsghdr nlh; + struct nhmsg nhm; + char buf[128]; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct nhmsg)), + .nlh.nlmsg_type = RTM_GETNEXTHOPBUCKET, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .nlh.nlmsg_seq = rth->dump = ++rth->seq, + .nhm.nh_family = family, + }; + + if (filter_fn) { + int err; + + err = filter_fn(&req.nlh, sizeof(req)); + if (err) + return err; + } + + return send(rth->fd, &req, sizeof(req), 0); +} + int rtnl_addrdump_req(struct rtnl_handle *rth, int family, req_filter_fn_t filter_fn) { diff --git a/man/man8/ip-nexthop.8 b/man/man8/ip-nexthop.8 index c1ac130c..f81a5910 100644 --- a/man/man8/ip-nexthop.8 +++ b/man/man8/ip-nexthop.8 @@ -28,6 +28,14 @@ ip-nexthop \- nexthop object management .BR "ip nexthop" " { " get " | " del " } id " .I ID +.ti -8 +.BI "ip nexthop bucket list " BUCKET_SELECTOR + +.ti -8 +.BR "ip nexthop bucket get " id +.I ID +.RI "index " INDEX + .ti -8 .IR SELECTOR " := " .RB "[ " id @@ -41,6 +49,12 @@ ip-nexthop \- nexthop object management .BR groups " ] [ " .BR fdb " ]" +.ti -8 +.IR BUCKET_SELECTOR " := " +.IR SELECTOR +.RB " | [ " nhid +.IR ID " ]" + .ti -8 .IR NH " := { " .BR blackhole " | [ " @@ -230,6 +244,37 @@ as show. ip nexthop get id ID get a single nexthop by id +.TP +ip nexthop bucket show +show the contents of the nexthop bucket table or the nexthop buckets +selected by some criteria. +.RS +.TP +.BI id " ID " +.in +0 +show the nexthop buckets that belong to a nexthop group with a given id +.TP +.BI nhid " ID " +.in +0 +show the nexthop buckets that hold a nexthop with a given id +.TP +.BI dev " DEV " +.in +0 +show the nexthop buckets using the given device +.TP +.BI vrf " NAME " +.in +0 +show the nexthop buckets using devices associated with the vrf name +.TP +.BI master " DEV " +.in +0 +show the nexthop buckets using devices enslaved to given master device +.RE + +.TP +ip nexthop bucket get id ID index INDEX +get a single nexthop bucket by nexthop group id and bucket index + .SH EXAMPLES .PP ip nexthop ls