From: David Gibson Although fwd_rule_add() performs some sanity checks on the rule it is given, there are invalid rules we don't check for, assuming that its callers will do that. That won't be enough when we can get rules inserted by a dynamic update client without going through the existing parsing code. So, add stricter checks to fwd_rule_add(), which is now possible thanks to the capabilities bits in the struct fwd_table. Where those duplicate existing checks in the callers, remove the old copies. Signed-off-by: David Gibson Reviewed-by: Laurent Vivier Signed-off-by: Stefano Brivio --- conf.c | 21 --------------------- fwd.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 47 insertions(+), 26 deletions(-) diff --git a/conf.c b/conf.c index 6e884e5..b470b0d 100644 --- a/conf.c +++ b/conf.c @@ -176,8 +176,6 @@ static void conf_ports_range_except(struct fwd_table *fwd, uint8_t proto, die("Invalid interface name: %s", ifname); } - assert(first != 0); - for (base = first; base <= last; base++) { if (exclude && bitmap_isset(exclude, base)) continue; @@ -310,10 +308,6 @@ static void conf_ports_spec(struct fwd_table *fwd, uint8_t proto, if (p != ep) /* Garbage after the ranges */ goto bad; - if (orig_range.first == 0) { - die("Can't forward port 0 included in '%s'", spec); - } - conf_ports_range_except(fwd, proto, addr, ifname, orig_range.first, orig_range.last, exclude, @@ -356,11 +350,6 @@ static void conf_ports(char optname, const char *optarg, struct fwd_table *fwd) return; } - if (proto == IPPROTO_TCP && !(fwd->caps & FWD_CAP_TCP)) - die("TCP port forwarding requested but TCP is disabled"); - if (proto == IPPROTO_UDP && !(fwd->caps & FWD_CAP_UDP)) - die("UDP port forwarding requested but UDP is disabled"); - strncpy(buf, optarg, sizeof(buf) - 1); if ((spec = strchr(buf, '/'))) { @@ -405,16 +394,6 @@ static void conf_ports(char optname, const char *optarg, struct fwd_table *fwd) addr = NULL; } - if (addr) { - if (!(fwd->caps & FWD_CAP_IPV4) && inany_v4(addr)) { - die("IPv4 is disabled, can't use -%c %s", - optname, optarg); - } else if (!(fwd->caps & FWD_CAP_IPV6) && !inany_v4(addr)) { - die("IPv6 is disabled, can't use -%c %s", - optname, optarg); - } - } - if (optname == 'T' || optname == 'U') { assert(!addr && !ifname); diff --git a/fwd.c b/fwd.c index c7fd1a9..979c149 100644 --- a/fwd.c +++ b/fwd.c @@ -367,17 +367,59 @@ int fwd_rule_add(struct fwd_table *fwd, const struct fwd_rule *new) new->first, new->last); return -EINVAL; } + if (!new->first) { + warn("Forwarding rule attempts to map from port 0"); + return -EINVAL; + } + if (!new->to || + (in_port_t)(new->to + new->last - new->first) < new->to) { + warn("Forwarding rule attempts to map to port 0"); + return -EINVAL; + } if (new->flags & ~allowed_flags) { warn("Rule has invalid flags 0x%hhx", new->flags & ~allowed_flags); return -EINVAL; } - if (new->flags & FWD_DUAL_STACK_ANY && - !inany_equals(&new->addr, &inany_any6)) { - char astr[INANY_ADDRSTRLEN]; + if (new->flags & FWD_DUAL_STACK_ANY) { + if (!inany_equals(&new->addr, &inany_any6)) { + char astr[INANY_ADDRSTRLEN]; - warn("Dual stack rule has non-wildcard address %s", - inany_ntop(&new->addr, astr, sizeof(astr))); + warn("Dual stack rule has non-wildcard address %s", + inany_ntop(&new->addr, astr, sizeof(astr))); + return -EINVAL; + } + if (!(fwd->caps & FWD_CAP_IPV4)) { + warn("Dual stack forward, but IPv4 not enabled"); + return -EINVAL; + } + if (!(fwd->caps & FWD_CAP_IPV6)) { + warn("Dual stack forward, but IPv6 not enabled"); + return -EINVAL; + } + } else { + if (inany_v4(&new->addr) && !(fwd->caps & FWD_CAP_IPV4)) { + warn("IPv4 forward, but IPv4 not enabled"); + return -EINVAL; + } + if (!inany_v4(&new->addr) && !(fwd->caps & FWD_CAP_IPV6)) { + warn("IPv6 forward, but IPv6 not enabled"); + return -EINVAL; + } + } + if (new->proto == IPPROTO_TCP) { + if (!(fwd->caps & FWD_CAP_TCP)) { + warn("Can't add TCP forwarding rule, TCP not enabled"); + return -EINVAL; + } + } else if (new->proto == IPPROTO_UDP) { + if (!(fwd->caps & FWD_CAP_UDP)) { + warn("Can't add UDP forwarding rule, UDP not enabled"); + return -EINVAL; + } + } else { + warn("Unsupported protocol 0x%hhx (%s) for forwarding rule", + new->proto, ipproto_name(new->proto)); return -EINVAL; } -- 2.43.0

From: David Gibson The code parsing command line options into forwarding rules has now been decoupled from most of passt/pasta's internals. This is good, because we'll soon want to share it with a configuration update client. Make the next step by moving this code into fwd_rule.[ch]. Signed-off-by: David Gibson Reviewed-by: Laurent Vivier Signed-off-by: Stefano Brivio --- conf.c | 376 +------------------------------------------ fwd.c | 94 ----------- fwd.h | 33 ---- fwd_rule.c | 464 ++++++++++++++++++++++++++++++++++++++++++++++++++++- fwd_rule.h | 36 ++++- 5 files changed, 502 insertions(+), 501 deletions(-) diff --git a/conf.c b/conf.c index b470b0d..5aacfe0 100644 --- a/conf.c +++ b/conf.c @@ -13,7 +13,6 @@ */ #include -#include #include #include #include @@ -66,365 +65,6 @@ const char *pasta_default_ifn = "tap0"; -/** - * port_range() - Represents a non-empty range of ports - * @first: First port number in the range - * @last: Last port number in the range (inclusive) - * - * Invariant: @last >= @first - */ -struct port_range { - in_port_t first, last; -}; - -/** - * parse_port_range() - Parse a range of port numbers '<first>[-<last>]' - * @s: String to parse - * @endptr: Update to the character after the parsed range (similar to - * strtol() etc.) - * @range: Update with the parsed values on success - * - * Return: -EINVAL on parsing error, -ERANGE on out of range port - * numbers, 0 on success - */ -static int parse_port_range(const char *s, const char **endptr, - struct port_range *range) -{ - unsigned long first, last; - char *ep; - - last = first = strtoul(s, &ep, 10); - if (ep == s) /* Parsed nothing */ - return -EINVAL; - if (*ep == '-') { /* we have a last value too */ - const char *lasts = ep + 1; - last = strtoul(lasts, &ep, 10); - if (ep == lasts) /* Parsed nothing */ - return -EINVAL; - } - - if ((last < first) || (last >= NUM_PORTS)) - return -ERANGE; - - range->first = first; - range->last = last; - *endptr = ep; - - return 0; -} - -/** - * parse_keyword() - Parse a literal keyword - * @s: String to parse - * @endptr: Update to the character after the keyword - * @kw: Keyword to accept - * - * Return: 0, if @s starts with @kw, -EINVAL if it does not - */ -static int parse_keyword(const char *s, const char **endptr, const char *kw) -{ - size_t len = strlen(kw); - - if (strlen(s) < len) - return -EINVAL; - - if (memcmp(s, kw, len)) - return -EINVAL; - - *endptr = s + len; - return 0; -} - -/** - * conf_ports_range_except() - Set up forwarding for a range of ports minus a - * bitmap of exclusions - * @fwd: Forwarding table to be updated - * @proto: Protocol to forward - * @addr: Listening address - * @ifname: Listening interface - * @first: First port to forward - * @last: Last port to forward - * @exclude: Bitmap of ports to exclude (may be NULL) - * @to: Port to translate @first to when forwarding - * @flags: Flags for forwarding entries - */ -static void conf_ports_range_except(struct fwd_table *fwd, uint8_t proto, - const union inany_addr *addr, - const char *ifname, - uint16_t first, uint16_t last, - const uint8_t *exclude, uint16_t to, - uint8_t flags) -{ - struct fwd_rule rule = { - .addr = addr ? *addr : inany_any6, - .ifname = { 0 }, - .proto = proto, - .flags = flags, - }; - char rulestr[FWD_RULE_STRLEN]; - unsigned delta = to - first; - unsigned base, i; - - if (!addr) - rule.flags |= FWD_DUAL_STACK_ANY; - if (ifname) { - int ret; - - ret = snprintf(rule.ifname, sizeof(rule.ifname), - "%s", ifname); - if (ret <= 0 || (size_t)ret >= sizeof(rule.ifname)) - die("Invalid interface name: %s", ifname); - } - - for (base = first; base <= last; base++) { - if (exclude && bitmap_isset(exclude, base)) - continue; - - for (i = base; i <= last; i++) { - if (exclude && bitmap_isset(exclude, i)) - break; - } - - rule.first = base; - rule.last = i - 1; - rule.to = base + delta; - - fwd_rule_conflict_check(&rule, fwd->rules, fwd->count); - if (fwd_rule_add(fwd, &rule) < 0) - goto fail; - - base = i - 1; - } - return; - -fail: - die("Unable to add rule %s", - fwd_rule_fmt(&rule, rulestr, sizeof(rulestr))); -} - -/* - * for_each_chunk - Step through delimited chunks of a string - * @p_: Pointer to start of each chunk (updated) - * @ep_: Pointer to end of each chunk (updated) - * @s_: String to step through - * @sep_: String of all allowed delimiters - */ -#define for_each_chunk(p_, ep_, s_, sep_) \ - for ((p_) = (s_); \ - (ep_) = (p_) + strcspn((p_), (sep_)), *(p_); \ - (p_) = *(ep_) ? (ep_) + 1 : (ep_)) - -/** - * conf_ports_spec() - Parse port range(s) specifier - * @fwd: Forwarding table to be updated - * @proto: Protocol to forward - * @addr: Listening address for forwarding - * @ifname: Interface name for listening - * @spec: Port range(s) specifier - */ -static void conf_ports_spec(struct fwd_table *fwd, uint8_t proto, - const union inany_addr *addr, const char *ifname, - const char *spec) -{ - uint8_t exclude[PORT_BITMAP_SIZE] = { 0 }; - bool exclude_only = true; - const char *p, *ep; - uint8_t flags = 0; - unsigned i; - - if (!strcmp(spec, "all")) { - /* Treat "all" as equivalent to "": all non-ephemeral ports */ - spec = ""; - } - - /* Parse excluded ranges and "auto" in the first pass */ - for_each_chunk(p, ep, spec, ",") { - struct port_range xrange; - - if (isdigit(*p)) { - /* Include range, parse later */ - exclude_only = false; - continue; - } - - if (parse_keyword(p, &p, "auto") == 0) { - if (p != ep) /* Garbage after the keyword */ - goto bad; - - if (!(fwd->caps & FWD_CAP_SCAN)) { - die( -"'auto' port forwarding is only allowed for pasta"); - } - - flags |= FWD_SCAN; - continue; - } - - /* Should be an exclude range */ - if (*p != '~') - goto bad; - p++; - - if (parse_port_range(p, &p, &xrange)) - goto bad; - if (p != ep) /* Garbage after the range */ - goto bad; - - for (i = xrange.first; i <= xrange.last; i++) - bitmap_set(exclude, i); - } - - if (exclude_only) { - /* Exclude ephemeral ports */ - fwd_port_map_ephemeral(exclude); - - conf_ports_range_except(fwd, proto, addr, ifname, - 1, NUM_PORTS - 1, exclude, - 1, flags | FWD_WEAK); - return; - } - - /* Now process base ranges, skipping exclusions */ - for_each_chunk(p, ep, spec, ",") { - struct port_range orig_range, mapped_range; - - if (!isdigit(*p)) - /* Already parsed */ - continue; - - if (parse_port_range(p, &p, &orig_range)) - goto bad; - - if (*p == ':') { /* There's a range to map to as well */ - if (parse_port_range(p + 1, &p, &mapped_range)) - goto bad; - if ((mapped_range.last - mapped_range.first) != - (orig_range.last - orig_range.first)) - goto bad; - } else { - mapped_range = orig_range; - } - - if (p != ep) /* Garbage after the ranges */ - goto bad; - - conf_ports_range_except(fwd, proto, addr, ifname, - orig_range.first, orig_range.last, - exclude, - mapped_range.first, flags); - } - - return; -bad: - die("Invalid port specifier '%s'", spec); -} - -/** - * conf_ports() - Parse port configuration options, initialise UDP/TCP sockets - * @optname: Short option name, t, T, u, or U - * @optarg: Option argument (port specification) - * @fwd: Forwarding table to be updated - */ -static void conf_ports(char optname, const char *optarg, struct fwd_table *fwd) -{ - union inany_addr addr_buf = inany_any6, *addr = &addr_buf; - char buf[BUFSIZ], *spec, *ifname = NULL; - uint8_t proto; - - if (optname == 't' || optname == 'T') - proto = IPPROTO_TCP; - else if (optname == 'u' || optname == 'U') - proto = IPPROTO_UDP; - else - assert(0); - - if (!strcmp(optarg, "none")) { - unsigned i; - - for (i = 0; i < fwd->count; i++) { - if (fwd->rules[i].proto == proto) { - die("-%c none conflicts with previous options", - optname); - } - } - return; - } - - strncpy(buf, optarg, sizeof(buf) - 1); - - if ((spec = strchr(buf, '/'))) { - *spec = 0; - spec++; - - if (optname != 't' && optname != 'u') - die("Listening address not allowed for -%c %s", - optname, optarg); - - if ((ifname = strchr(buf, '%'))) { - *ifname = 0; - ifname++; - - /* spec is already advanced one past the '/', - * so the length of the given ifname is: - * (spec - ifname - 1) - */ - if (spec - ifname - 1 >= IFNAMSIZ) { - die("Interface name '%s' is too long (max %u)", - ifname, IFNAMSIZ - 1); - } - } - - if (ifname == buf + 1) { /* Interface without address */ - addr = NULL; - } else { - char *p = buf; - - /* Allow square brackets for IPv4 too for convenience */ - if (*p == '[' && p[strlen(p) - 1] == ']') { - p[strlen(p) - 1] = '\0'; - p++; - } - - if (!inany_pton(p, addr)) - die("Bad forwarding address '%s'", p); - } - } else { - spec = buf; - - addr = NULL; - } - - if (optname == 'T' || optname == 'U') { - assert(!addr && !ifname); - - if (!(fwd->caps & FWD_CAP_IFNAME)) { - warn( -"SO_BINDTODEVICE unavailable, forwarding only 127.0.0.1 and ::1 for '-%c %s'", - optname, optarg); - - if (fwd->caps & FWD_CAP_IPV4) { - conf_ports_spec(fwd, proto, - &inany_loopback4, NULL, spec); - } - if (fwd->caps & FWD_CAP_IPV6) { - conf_ports_spec(fwd, proto, - &inany_loopback6, NULL, spec); - } - return; - } - - ifname = "lo"; - } - - if (ifname && !(fwd->caps & FWD_CAP_IFNAME)) { - die( -"Device binding for '-%c %s' unsupported (requires kernel 5.7+)", - optname, optarg); - } - - conf_ports_spec(fwd, proto, addr, ifname, spec); -} - /** * add_dns4() - Possibly add the IPv4 address of a DNS resolver to configuration * @c: Execution context @@ -2160,16 +1800,16 @@ void conf(struct ctx *c, int argc, char **argv) if (name == 't') { opt_t = true; - conf_ports(name, optarg, c->fwd[PIF_HOST]); + fwd_rule_parse(name, optarg, c->fwd[PIF_HOST]); } else if (name == 'u') { opt_u = true; - conf_ports(name, optarg, c->fwd[PIF_HOST]); + fwd_rule_parse(name, optarg, c->fwd[PIF_HOST]); } else if (name == 'T') { opt_T = true; - conf_ports(name, optarg, c->fwd[PIF_SPLICE]); + fwd_rule_parse(name, optarg, c->fwd[PIF_SPLICE]); } else if (name == 'U') { opt_U = true; - conf_ports(name, optarg, c->fwd[PIF_SPLICE]); + fwd_rule_parse(name, optarg, c->fwd[PIF_SPLICE]); } } while (name != -1); @@ -2221,13 +1861,13 @@ void conf(struct ctx *c, int argc, char **argv) if (c->mode == MODE_PASTA) { if (!opt_t) - conf_ports('t', "auto", c->fwd[PIF_HOST]); + fwd_rule_parse('t', "auto", c->fwd[PIF_HOST]); if (!opt_T) - conf_ports('T', "auto", c->fwd[PIF_SPLICE]); + fwd_rule_parse('T', "auto", c->fwd[PIF_SPLICE]); if (!opt_u) - conf_ports('u', "auto", c->fwd[PIF_HOST]); + fwd_rule_parse('u', "auto", c->fwd[PIF_HOST]); if (!opt_U) - conf_ports('U', "auto", c->fwd[PIF_SPLICE]); + fwd_rule_parse('U', "auto", c->fwd[PIF_SPLICE]); } if (!c->quiet) diff --git a/fwd.c b/fwd.c index a6d75b7..728a783 100644 --- a/fwd.c +++ b/fwd.c @@ -275,100 +275,6 @@ void fwd_rule_init(struct ctx *c) c->fwd[PIF_SPLICE] = &fwd_out; } -/** - * fwd_rule_add() - Validate and add a rule to a forwarding table - * @fwd: Table to add to - * @new: Rule to add - * - * Return: 0 on success, negative error code on failure - */ -int fwd_rule_add(struct fwd_table *fwd, const struct fwd_rule *new) -{ - /* Flags which can be set from the caller */ - const uint8_t allowed_flags = FWD_WEAK | FWD_SCAN | FWD_DUAL_STACK_ANY; - unsigned num = (unsigned)new->last - new->first + 1; - unsigned port; - - if (new->first > new->last) { - warn("Rule has invalid port range %u-%u", - new->first, new->last); - return -EINVAL; - } - if (!new->first) { - warn("Forwarding rule attempts to map from port 0"); - return -EINVAL; - } - if (!new->to || - (in_port_t)(new->to + new->last - new->first) < new->to) { - warn("Forwarding rule attempts to map to port 0"); - return -EINVAL; - } - if (new->flags & ~allowed_flags) { - warn("Rule has invalid flags 0x%hhx", - new->flags & ~allowed_flags); - return -EINVAL; - } - if (new->flags & FWD_DUAL_STACK_ANY) { - if (!inany_equals(&new->addr, &inany_any6)) { - char astr[INANY_ADDRSTRLEN]; - - warn("Dual stack rule has non-wildcard address %s", - inany_ntop(&new->addr, astr, sizeof(astr))); - return -EINVAL; - } - if (!(fwd->caps & FWD_CAP_IPV4)) { - warn("Dual stack forward, but IPv4 not enabled"); - return -EINVAL; - } - if (!(fwd->caps & FWD_CAP_IPV6)) { - warn("Dual stack forward, but IPv6 not enabled"); - return -EINVAL; - } - } else { - if (inany_v4(&new->addr) && !(fwd->caps & FWD_CAP_IPV4)) { - warn("IPv4 forward, but IPv4 not enabled"); - return -EINVAL; - } - if (!inany_v4(&new->addr) && !(fwd->caps & FWD_CAP_IPV6)) { - warn("IPv6 forward, but IPv6 not enabled"); - return -EINVAL; - } - } - if (new->proto == IPPROTO_TCP) { - if (!(fwd->caps & FWD_CAP_TCP)) { - warn("Can't add TCP forwarding rule, TCP not enabled"); - return -EINVAL; - } - } else if (new->proto == IPPROTO_UDP) { - if (!(fwd->caps & FWD_CAP_UDP)) { - warn("Can't add UDP forwarding rule, UDP not enabled"); - return -EINVAL; - } - } else { - warn("Unsupported protocol 0x%hhx (%s) for forwarding rule", - new->proto, ipproto_name(new->proto)); - return -EINVAL; - } - - if (fwd->count >= ARRAY_SIZE(fwd->rules)) { - warn("Too many rules (maximum %u)", ARRAY_SIZE(fwd->rules)); - return -ENOSPC; - } - if ((fwd->sock_count + num) > ARRAY_SIZE(fwd->socks)) { - warn("Rules require too many listening sockets (maximum %u)", - ARRAY_SIZE(fwd->socks)); - return -ENOSPC; - } - - fwd->rulesocks[fwd->count] = &fwd->socks[fwd->sock_count]; - for (port = new->first; port <= new->last; port++) - fwd->rulesocks[fwd->count][port - new->first] = -1; - - fwd->rules[fwd->count++] = *new; - fwd->sock_count += num; - return 0; -} - /** * fwd_rule_match() - Does a prospective flow match a given forwarding rule? * @rule: Forwarding rule diff --git a/fwd.h b/fwd.h index e664d1d..8f845d0 100644 --- a/fwd.h +++ b/fwd.h @@ -20,8 +20,6 @@ struct flowside; -#define FWD_RULE_BITS 8 -#define MAX_FWD_RULES MAX_FROM_BITS(FWD_RULE_BITS) #define FWD_NO_HINT (-1) /** @@ -36,36 +34,6 @@ struct fwd_listen_ref { unsigned rule :FWD_RULE_BITS; }; -/* Maximum number of listening sockets (per pif) - * - * Rationale: This lets us listen on every port for two addresses and two - * protocols (which we need for -T auto -U auto without SO_BINDTODEVICE), plus a - * comfortable number of extras. - */ -#define MAX_LISTEN_SOCKS (NUM_PORTS * 5) - -/** - * struct fwd_table - Forwarding state (per initiating pif) - * @caps: Forwarding capabilities for this initiating pif - * @count: Number of forwarding rules - * @rules: Array of forwarding rules - * @rulesocks: Parallel array of @rules (@count valid entries) of pointers to - * @socks entries giving the start of the corresponding rule's - * sockets within the larger array - * @sock_count: Number of entries used in @socks (for all rules combined) - * @socks: Listening sockets for forwarding - */ -struct fwd_table { - uint32_t caps; - unsigned count; - struct fwd_rule rules[MAX_FWD_RULES]; - int *rulesocks[MAX_FWD_RULES]; - unsigned sock_count; - int socks[MAX_LISTEN_SOCKS]; -}; - -#define PORT_BITMAP_SIZE DIV_ROUND_UP(NUM_PORTS, 8) - /** * struct fwd_scan - Port scanning state for a protocol+direction * @scan4: /proc/net fd to scan for IPv4 ports when in AUTO mode @@ -81,7 +49,6 @@ struct fwd_scan { #define FWD_PORT_SCAN_INTERVAL 1000 /* ms */ void fwd_rule_init(struct ctx *c); -int fwd_rule_add(struct fwd_table *fwd, const struct fwd_rule *new); const struct fwd_rule *fwd_rule_search(const struct fwd_table *fwd, const struct flowside *ini, uint8_t proto, int hint); diff --git a/fwd_rule.c b/fwd_rule.c index 9d48982..cd3dec0 100644 --- a/fwd_rule.c +++ b/fwd_rule.c @@ -15,6 +15,7 @@ * Author: David Gibson */ +#include #include #include #include @@ -89,7 +90,7 @@ parse_err: * fwd_port_map_ephemeral() - Mark ephemeral ports in a bitmap * @map: Bitmap to update */ -void fwd_port_map_ephemeral(uint8_t *map) +static void fwd_port_map_ephemeral(uint8_t *map) { unsigned port; @@ -123,6 +124,7 @@ const union inany_addr *fwd_rule_addr(const struct fwd_rule *rule) */ __attribute__((noinline)) #endif +/* cppcheck-suppress staticFunction */ const char *fwd_rule_fmt(const struct fwd_rule *rule, char *dst, size_t size) { const char *percent = *rule->ifname ? "%" : ""; @@ -199,8 +201,8 @@ static bool fwd_rule_conflicts(const struct fwd_rule *a, const struct fwd_rule * * @rules: Existing rules against which to test * @count: Number of rules in @rules */ -void fwd_rule_conflict_check(const struct fwd_rule *new, - const struct fwd_rule *rules, size_t count) +static void fwd_rule_conflict_check(const struct fwd_rule *new, + const struct fwd_rule *rules, size_t count) { unsigned i; @@ -215,3 +217,459 @@ void fwd_rule_conflict_check(const struct fwd_rule *new, fwd_rule_fmt(&rules[i], rulestr, sizeof(rulestr))); } } + +/** + * fwd_rule_add() - Validate and add a rule to a forwarding table + * @fwd: Table to add to + * @new: Rule to add + * + * Return: 0 on success, negative error code on failure + */ +static int fwd_rule_add(struct fwd_table *fwd, const struct fwd_rule *new) +{ + /* Flags which can be set from the caller */ + const uint8_t allowed_flags = FWD_WEAK | FWD_SCAN | FWD_DUAL_STACK_ANY; + unsigned num = (unsigned)new->last - new->first + 1; + unsigned port; + + if (new->first > new->last) { + warn("Rule has invalid port range %u-%u", + new->first, new->last); + return -EINVAL; + } + if (!new->first) { + warn("Forwarding rule attempts to map from port 0"); + return -EINVAL; + } + if (!new->to || + (in_port_t)(new->to + new->last - new->first) < new->to) { + warn("Forwarding rule attempts to map to port 0"); + return -EINVAL; + } + if (new->flags & ~allowed_flags) { + warn("Rule has invalid flags 0x%hhx", + new->flags & ~allowed_flags); + return -EINVAL; + } + if (new->flags & FWD_DUAL_STACK_ANY) { + if (!inany_equals(&new->addr, &inany_any6)) { + char astr[INANY_ADDRSTRLEN]; + + warn("Dual stack rule has non-wildcard address %s", + inany_ntop(&new->addr, astr, sizeof(astr))); + return -EINVAL; + } + if (!(fwd->caps & FWD_CAP_IPV4)) { + warn("Dual stack forward, but IPv4 not enabled"); + return -EINVAL; + } + if (!(fwd->caps & FWD_CAP_IPV6)) { + warn("Dual stack forward, but IPv6 not enabled"); + return -EINVAL; + } + } else { + if (inany_v4(&new->addr) && !(fwd->caps & FWD_CAP_IPV4)) { + warn("IPv4 forward, but IPv4 not enabled"); + return -EINVAL; + } + if (!inany_v4(&new->addr) && !(fwd->caps & FWD_CAP_IPV6)) { + warn("IPv6 forward, but IPv6 not enabled"); + return -EINVAL; + } + } + if (new->proto == IPPROTO_TCP) { + if (!(fwd->caps & FWD_CAP_TCP)) { + warn("Can't add TCP forwarding rule, TCP not enabled"); + return -EINVAL; + } + } else if (new->proto == IPPROTO_UDP) { + if (!(fwd->caps & FWD_CAP_UDP)) { + warn("Can't add UDP forwarding rule, UDP not enabled"); + return -EINVAL; + } + } else { + warn("Unsupported protocol 0x%hhx (%s) for forwarding rule", + new->proto, ipproto_name(new->proto)); + return -EINVAL; + } + + if (fwd->count >= ARRAY_SIZE(fwd->rules)) { + warn("Too many rules (maximum %u)", ARRAY_SIZE(fwd->rules)); + return -ENOSPC; + } + if ((fwd->sock_count + num) > ARRAY_SIZE(fwd->socks)) { + warn("Rules require too many listening sockets (maximum %u)", + ARRAY_SIZE(fwd->socks)); + return -ENOSPC; + } + + fwd->rulesocks[fwd->count] = &fwd->socks[fwd->sock_count]; + for (port = new->first; port <= new->last; port++) + fwd->rulesocks[fwd->count][port - new->first] = -1; + + fwd->rules[fwd->count++] = *new; + fwd->sock_count += num; + return 0; +} + +/** + * port_range() - Represents a non-empty range of ports + * @first: First port number in the range + * @last: Last port number in the range (inclusive) + * + * Invariant: @last >= @first + */ +struct port_range { + in_port_t first, last; +}; + +/** + * parse_port_range() - Parse a range of port numbers '<first>[-<last>]' + * @s: String to parse + * @endptr: Update to the character after the parsed range (similar to + * strtol() etc.) + * @range: Update with the parsed values on success + * + * Return: -EINVAL on parsing error, -ERANGE on out of range port + * numbers, 0 on success + */ +static int parse_port_range(const char *s, const char **endptr, + struct port_range *range) +{ + unsigned long first, last; + char *ep; + + last = first = strtoul(s, &ep, 10); + if (ep == s) /* Parsed nothing */ + return -EINVAL; + if (*ep == '-') { /* we have a last value too */ + const char *lasts = ep + 1; + last = strtoul(lasts, &ep, 10); + if (ep == lasts) /* Parsed nothing */ + return -EINVAL; + } + + if ((last < first) || (last >= NUM_PORTS)) + return -ERANGE; + + range->first = first; + range->last = last; + *endptr = ep; + + return 0; +} + +/** + * parse_keyword() - Parse a literal keyword + * @s: String to parse + * @endptr: Update to the character after the keyword + * @kw: Keyword to accept + * + * Return: 0, if @s starts with @kw, -EINVAL if it does not + */ +static int parse_keyword(const char *s, const char **endptr, const char *kw) +{ + size_t len = strlen(kw); + + if (strlen(s) < len) + return -EINVAL; + + if (memcmp(s, kw, len)) + return -EINVAL; + + *endptr = s + len; + return 0; +} + +/** + * fwd_rule_range_except() - Set up forwarding for a range of ports minus a + * bitmap of exclusions + * @fwd: Forwarding table to be updated + * @proto: Protocol to forward + * @addr: Listening address + * @ifname: Listening interface + * @first: First port to forward + * @last: Last port to forward + * @exclude: Bitmap of ports to exclude (may be NULL) + * @to: Port to translate @first to when forwarding + * @flags: Flags for forwarding entries + */ +static void fwd_rule_range_except(struct fwd_table *fwd, uint8_t proto, + const union inany_addr *addr, + const char *ifname, + uint16_t first, uint16_t last, + const uint8_t *exclude, uint16_t to, + uint8_t flags) +{ + struct fwd_rule rule = { + .addr = addr ? *addr : inany_any6, + .ifname = { 0 }, + .proto = proto, + .flags = flags, + }; + char rulestr[FWD_RULE_STRLEN]; + unsigned delta = to - first; + unsigned base, i; + + if (!addr) + rule.flags |= FWD_DUAL_STACK_ANY; + if (ifname) { + int ret; + + ret = snprintf(rule.ifname, sizeof(rule.ifname), + "%s", ifname); + if (ret <= 0 || (size_t)ret >= sizeof(rule.ifname)) + die("Invalid interface name: %s", ifname); + } + + for (base = first; base <= last; base++) { + if (exclude && bitmap_isset(exclude, base)) + continue; + + for (i = base; i <= last; i++) { + if (exclude && bitmap_isset(exclude, i)) + break; + } + + rule.first = base; + rule.last = i - 1; + rule.to = base + delta; + + fwd_rule_conflict_check(&rule, fwd->rules, fwd->count); + if (fwd_rule_add(fwd, &rule) < 0) + goto fail; + + base = i - 1; + } + return; + +fail: + die("Unable to add rule %s", + fwd_rule_fmt(&rule, rulestr, sizeof(rulestr))); +} + +/* + * for_each_chunk - Step through delimited chunks of a string + * @p_: Pointer to start of each chunk (updated) + * @ep_: Pointer to end of each chunk (updated) + * @s_: String to step through + * @sep_: String of all allowed delimiters + */ +#define for_each_chunk(p_, ep_, s_, sep_) \ + for ((p_) = (s_); \ + (ep_) = (p_) + strcspn((p_), (sep_)), *(p_); \ + (p_) = *(ep_) ? (ep_) + 1 : (ep_)) + +/** + * fwd_rule_parse_ports() - Parse port range(s) specifier + * @fwd: Forwarding table to be updated + * @proto: Protocol to forward + * @addr: Listening address for forwarding + * @ifname: Interface name for listening + * @spec: Port range(s) specifier + */ +static void fwd_rule_parse_ports(struct fwd_table *fwd, uint8_t proto, + const union inany_addr *addr, + const char *ifname, + const char *spec) +{ + uint8_t exclude[PORT_BITMAP_SIZE] = { 0 }; + bool exclude_only = true; + const char *p, *ep; + uint8_t flags = 0; + unsigned i; + + if (!strcmp(spec, "all")) { + /* Treat "all" as equivalent to "": all non-ephemeral ports */ + spec = ""; + } + + /* Parse excluded ranges and "auto" in the first pass */ + for_each_chunk(p, ep, spec, ",") { + struct port_range xrange; + + if (isdigit(*p)) { + /* Include range, parse later */ + exclude_only = false; + continue; + } + + if (parse_keyword(p, &p, "auto") == 0) { + if (p != ep) /* Garbage after the keyword */ + goto bad; + + if (!(fwd->caps & FWD_CAP_SCAN)) { + die( +"'auto' port forwarding is only allowed for pasta"); + } + + flags |= FWD_SCAN; + continue; + } + + /* Should be an exclude range */ + if (*p != '~') + goto bad; + p++; + + if (parse_port_range(p, &p, &xrange)) + goto bad; + if (p != ep) /* Garbage after the range */ + goto bad; + + for (i = xrange.first; i <= xrange.last; i++) + bitmap_set(exclude, i); + } + + if (exclude_only) { + /* Exclude ephemeral ports */ + fwd_port_map_ephemeral(exclude); + + fwd_rule_range_except(fwd, proto, addr, ifname, + 1, NUM_PORTS - 1, exclude, + 1, flags | FWD_WEAK); + return; + } + + /* Now process base ranges, skipping exclusions */ + for_each_chunk(p, ep, spec, ",") { + struct port_range orig_range, mapped_range; + + if (!isdigit(*p)) + /* Already parsed */ + continue; + + if (parse_port_range(p, &p, &orig_range)) + goto bad; + + if (*p == ':') { /* There's a range to map to as well */ + if (parse_port_range(p + 1, &p, &mapped_range)) + goto bad; + if ((mapped_range.last - mapped_range.first) != + (orig_range.last - orig_range.first)) + goto bad; + } else { + mapped_range = orig_range; + } + + if (p != ep) /* Garbage after the ranges */ + goto bad; + + fwd_rule_range_except(fwd, proto, addr, ifname, + orig_range.first, orig_range.last, + exclude, + mapped_range.first, flags); + } + + return; +bad: + die("Invalid port specifier '%s'", spec); +} + +/** + * fwd_rule_parse() - Parse port configuration option + * @optname: Short option name, t, T, u, or U + * @optarg: Option argument (port specification) + * @fwd: Forwarding table to be updated + */ +void fwd_rule_parse(char optname, const char *optarg, struct fwd_table *fwd) +{ + union inany_addr addr_buf = inany_any6, *addr = &addr_buf; + char buf[BUFSIZ], *spec, *ifname = NULL; + uint8_t proto; + + if (optname == 't' || optname == 'T') + proto = IPPROTO_TCP; + else if (optname == 'u' || optname == 'U') + proto = IPPROTO_UDP; + else + assert(0); + + if (!strcmp(optarg, "none")) { + unsigned i; + + for (i = 0; i < fwd->count; i++) { + if (fwd->rules[i].proto == proto) { + die("-%c none conflicts with previous options", + optname); + } + } + return; + } + + strncpy(buf, optarg, sizeof(buf) - 1); + + if ((spec = strchr(buf, '/'))) { + *spec = 0; + spec++; + + if (optname != 't' && optname != 'u') + die("Listening address not allowed for -%c %s", + optname, optarg); + + if ((ifname = strchr(buf, '%'))) { + *ifname = 0; + ifname++; + + /* spec is already advanced one past the '/', + * so the length of the given ifname is: + * (spec - ifname - 1) + */ + if (spec - ifname - 1 >= IFNAMSIZ) { + die("Interface name '%s' is too long (max %u)", + ifname, IFNAMSIZ - 1); + } + } + + if (ifname == buf + 1) { /* Interface without address */ + addr = NULL; + } else { + char *p = buf; + + /* Allow square brackets for IPv4 too for convenience */ + if (*p == '[' && p[strlen(p) - 1] == ']') { + p[strlen(p) - 1] = '\0'; + p++; + } + + if (!inany_pton(p, addr)) + die("Bad forwarding address '%s'", p); + } + } else { + spec = buf; + + addr = NULL; + } + + if (optname == 'T' || optname == 'U') { + assert(!addr && !ifname); + + if (!(fwd->caps & FWD_CAP_IFNAME)) { + warn( +"SO_BINDTODEVICE unavailable, forwarding only 127.0.0.1 and ::1 for '-%c %s'", + optname, optarg); + + if (fwd->caps & FWD_CAP_IPV4) { + fwd_rule_parse_ports(fwd, proto, + &inany_loopback4, NULL, + spec); + } + if (fwd->caps & FWD_CAP_IPV6) { + fwd_rule_parse_ports(fwd, proto, + &inany_loopback6, NULL, + spec); + } + return; + } + + ifname = "lo"; + } + + if (ifname && !(fwd->caps & FWD_CAP_IFNAME)) { + die( +"Device binding for '-%c %s' unsupported (requires kernel 5.7+)", + optname, optarg); + } + + fwd_rule_parse_ports(fwd, proto, addr, ifname, spec); +} diff --git a/fwd_rule.h b/fwd_rule.h index 5c7b67a..f0f4efd 100644 --- a/fwd_rule.h +++ b/fwd_rule.h @@ -19,6 +19,7 @@ /* Number of ports for both TCP and UDP */ #define NUM_PORTS (1U << 16) +#define PORT_BITMAP_SIZE DIV_ROUND_UP(NUM_PORTS, 8) /* Forwarding capability bits */ #define FWD_CAP_IPV4 BIT(0) @@ -54,8 +55,38 @@ struct fwd_rule { uint8_t flags; }; +#define FWD_RULE_BITS 8 +#define MAX_FWD_RULES MAX_FROM_BITS(FWD_RULE_BITS) + +/* Maximum number of listening sockets (per pif) + * + * Rationale: This lets us listen on every port for two addresses and two + * protocols (which we need for -T auto -U auto without SO_BINDTODEVICE), plus a + * comfortable number of extras. + */ +#define MAX_LISTEN_SOCKS (NUM_PORTS * 5) + +/** + * struct fwd_table - Forwarding state (per initiating pif) + * @caps: Forwarding capabilities for this initiating pif + * @count: Number of forwarding rules + * @rules: Array of forwarding rules + * @rulesocks: Parallel array of @rules (@count valid entries) of pointers to + * @socks entries giving the start of the corresponding rule's + * sockets within the larger array + * @sock_count: Number of entries used in @socks (for all rules combined) + * @socks: Listening sockets for forwarding + */ +struct fwd_table { + uint32_t caps; + unsigned count; + struct fwd_rule rules[MAX_FWD_RULES]; + int *rulesocks[MAX_FWD_RULES]; + unsigned sock_count; + int socks[MAX_LISTEN_SOCKS]; +}; + void fwd_probe_ephemeral(void); -void fwd_port_map_ephemeral(uint8_t *map); #define FWD_RULE_STRLEN \ (IPPROTO_STRLEN - 1 \ @@ -67,7 +98,6 @@ void fwd_port_map_ephemeral(uint8_t *map); const union inany_addr *fwd_rule_addr(const struct fwd_rule *rule); const char *fwd_rule_fmt(const struct fwd_rule *rule, char *dst, size_t size); void fwd_rules_info(const struct fwd_rule *rules, size_t count); -void fwd_rule_conflict_check(const struct fwd_rule *new, - const struct fwd_rule *rules, size_t count); +void fwd_rule_parse(char optname, const char *optarg, struct fwd_table *fwd); #endif /* FWD_RULE_H */ -- 2.43.0

From: David Gibson fwd_rules_info() is used to print a full table of forwarding rules for debugging or the like. Currently it has one caller, and uses info() to dump the messages. However for the upcoming configuration client, we're going to want to dump the rules in some similar, but not quite identical ways. For example, at different severity levels, or to stdout instead of stderr / system log / logfile. So, generalise fwd_rules_info() to fwd_rules_dump() which takes a printing function as a parameter. Because we want this to work with "functions" like info, which is actually a macro, we have to convert fwd_rules_dump() to a macro as well. We also allow the prefix and suffix for each rule / line to be provided as a parameter. Signed-off-by: David Gibson Reviewed-by: Laurent Vivier Signed-off-by: Stefano Brivio --- conf.c | 3 ++- fwd_rule.c | 16 ---------------- fwd_rule.h | 20 +++++++++++++++++++- 3 files changed, 21 insertions(+), 18 deletions(-) diff --git a/conf.c b/conf.c index 5aacfe0..0586107 100644 --- a/conf.c +++ b/conf.c @@ -902,7 +902,8 @@ dns6: dir = "Inbound"; info("%s forwarding rules (%s):", dir, pif_name(i)); - fwd_rules_info(c->fwd[i]->rules, c->fwd[i]->count); + fwd_rules_dump(info, c->fwd[i]->rules, c->fwd[i]->count, + " ", ""); } } diff --git a/fwd_rule.c b/fwd_rule.c index 1413584..777282d 100644 --- a/fwd_rule.c +++ b/fwd_rule.c @@ -124,7 +124,6 @@ const union inany_addr *fwd_rule_addr(const struct fwd_rule *rule) */ __attribute__((noinline)) #endif -/* cppcheck-suppress staticFunction */ const char *fwd_rule_fmt(const struct fwd_rule *rule, char *dst, size_t size) { const char *percent = *rule->ifname ? "%" : ""; @@ -158,21 +157,6 @@ const char *fwd_rule_fmt(const struct fwd_rule *rule, char *dst, size_t size) return dst; } -/** - * fwd_rules_info() - Print forwarding rules for debugging - * @fwd: Table to print - */ -void fwd_rules_info(const struct fwd_rule *rules, size_t count) -{ - unsigned i; - - for (i = 0; i < count; i++) { - char buf[FWD_RULE_STRLEN]; - - info(" %s", fwd_rule_fmt(&rules[i], buf, sizeof(buf))); - } -} - /** * fwd_rule_conflicts() - Test if two rules conflict with each other * @a, @b: Rules to test diff --git a/fwd_rule.h b/fwd_rule.h index f0f4efd..5855138 100644 --- a/fwd_rule.h +++ b/fwd_rule.h @@ -97,7 +97,25 @@ void fwd_probe_ephemeral(void); const union inany_addr *fwd_rule_addr(const struct fwd_rule *rule); const char *fwd_rule_fmt(const struct fwd_rule *rule, char *dst, size_t size); -void fwd_rules_info(const struct fwd_rule *rules, size_t count); void fwd_rule_parse(char optname, const char *optarg, struct fwd_table *fwd); +/** + * fwd_rules_dump() - Dump forwarding rules + * @fn: Printing/logging function to call + * @rules: Array of rules to dump + * @count: Number of rules to dump + * @prefix: String to print at the start of each rule + * @suffix: String to print at the end of each rule + */ +#define fwd_rules_dump(fn, rules, count, prefix, suffix) \ + do { \ + unsigned i_; \ + for (i_ = 0; i_ < (count); i_++) { \ + char buf_[FWD_RULE_STRLEN]; \ + fn("%s%s%s", prefix, \ + fwd_rule_fmt(&(rules)[i_], buf_, sizeof(buf_)), \ + suffix); \ + } \ + } while (0) + #endif /* FWD_RULE_H */ -- 2.43.0

From: David Gibson The new warnings in fwd_rule_add() have some not quite technically correct format specifiers. For some weird reason these don't trip warnings on passt itself, but do when we re-use this code in the upcoming configuration client. Fix them. Signed-off-by: David Gibson Reviewed-by: Laurent Vivier Signed-off-by: Stefano Brivio --- fwd_rule.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fwd_rule.c b/fwd_rule.c index 777282d..7fd20dd 100644 --- a/fwd_rule.c +++ b/fwd_rule.c @@ -208,7 +208,7 @@ static int fwd_rule_add(struct fwd_table *fwd, const struct fwd_rule *new) return -EINVAL; } if (new->flags & ~allowed_flags) { - warn("Rule has invalid flags 0x%hhx", + warn("Rule has invalid flags 0x%x", new->flags & ~allowed_flags); return -EINVAL; } @@ -267,11 +267,11 @@ static int fwd_rule_add(struct fwd_table *fwd, const struct fwd_rule *new) } if (fwd->count >= ARRAY_SIZE(fwd->rules)) { - warn("Too many rules (maximum %u)", ARRAY_SIZE(fwd->rules)); + warn("Too many rules (maximum %d)", ARRAY_SIZE(fwd->rules)); return -ENOSPC; } if ((fwd->sock_count + num) > ARRAY_SIZE(fwd->socks)) { - warn("Rules require too many listening sockets (maximum %u)", + warn("Rules require too many listening sockets (maximum %d)", ARRAY_SIZE(fwd->socks)); return -ENOSPC; } -- 2.43.0

From: David Gibson In pesto we're going to want several levels of error/warning messages, much like passt itself. Particularly as we start to share mode code between passt and pesto, we want to use a similar interface to emit those. However we don't want to use the same implementation - logging to a file or syslog doesn't make sense for the command line tool. To accomplish this loosely share log.h, but not log.c between pesto and passt. In fact, an #ifdef means even most of log.h isn't actually shared, but we do provide similar warn(), die() etc. macros. This includes the *_perror() variants, which need strerror(). However, we want to avoid allocations for pesto as we do for passt, and strerror() allocates in some libc versions. Therefore, also move our workaround for this to be shared with pesto. Reviewed-by: Laurent Vivier [dwg: Based on changes part of a larger patch by Stefano] Signed-off-by: David Gibson [sbrivio: Dropped debug_perror_() as it's not used anyway, Laurent was asking about its name] [sbrivio: Fix conflicts in the Makefile caused by the fact that I'm not merging a previous series reworking it] [sbrivio: For some reason, this triggers some unrelated, but valid, cppcheck warnings in tap.c and conf.c: fix / suppress them] Signed-off-by: Stefano Brivio --- Makefile | 10 +++++----- common.h | 32 ++++++++++++++++++++++++++++++++ conf.c | 2 +- log.h | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++++- pasta.c | 4 ++-- pesto.c | 14 ++++---------- tap.c | 12 +++++++++++- util.h | 32 -------------------------------- 8 files changed, 107 insertions(+), 52 deletions(-) diff --git a/Makefile b/Makefile index 76b9b5c..2639472 100644 --- a/Makefile +++ b/Makefile @@ -50,10 +50,10 @@ SRCS = $(PASST_SRCS) $(QRAP_SRCS) $(PASST_REPAIR_SRCS) $(PESTO_SRCS) MANPAGES = passt.1 pasta.1 pesto.1 qrap.1 passt-repair.1 -PASST_HEADERS = arch.h arp.h bitmap.h checksum.h conf.h dhcp.h dhcpv6.h \ - epoll_ctl.h flow.h fwd.h fwd_rule.h flow_table.h icmp.h icmp_flow.h \ - inany.h iov.h ip.h isolation.h lineread.h log.h migrate.h ndp.h \ - netlink.h packet.h passt.h pasta.h pesto.h pcap.h pif.h repair.h \ +PASST_HEADERS = arch.h arp.h bitmap.h checksum.h common.h conf.h dhcp.h \ + dhcpv6.h epoll_ctl.h flow.h fwd.h fwd_rule.h flow_table.h icmp.h \ + icmp_flow.h inany.h iov.h ip.h isolation.h lineread.h log.h migrate.h \ + ndp.h netlink.h packet.h passt.h pasta.h pcap.h pesto.h pif.h repair.h \ serialise.h siphash.h tap.h tcp.h tcp_buf.h tcp_conn.h tcp_internal.h \ tcp_splice.h tcp_vu.h udp.h udp_flow.h udp_internal.h udp_vu.h util.h \ vhost_user.h virtio.h vu_common.h @@ -116,7 +116,7 @@ passt-repair: $(PASST_REPAIR_SRCS) seccomp_repair.h $(CC) $(FLAGS) $(CFLAGS) $(CPPFLAGS) $(PASST_REPAIR_SRCS) -o passt-repair $(LDFLAGS) pesto: $(PESTO_SRCS) $(PESTO_HEADERS) seccomp_pesto.h - $(CC) $(FLAGS) $(CFLAGS) $(CPPFLAGS) $(PESTO_SRCS) -o pesto $(LDFLAGS) + $(CC) $(FLAGS) $(CFLAGS) $(CPPFLAGS) -DPESTO $(PESTO_SRCS) -o pesto $(LDFLAGS) valgrind: EXTRA_SYSCALLS += rt_sigprocmask rt_sigtimedwait rt_sigaction \ rt_sigreturn getpid gettid kill clock_gettime \ diff --git a/common.h b/common.h index f3506b4..4251781 100644 --- a/common.h +++ b/common.h @@ -21,4 +21,36 @@ /* FPRINTF() intentionally silences cert-err33-c clang-tidy warnings */ #define FPRINTF(f, ...) (void)fprintf(f, __VA_ARGS__) +/* + * Starting from glibc 2.40.9000 and commit 25a5eb4010df ("string: strerror, + * strsignal cannot use buffer after dlmopen (bug 32026)"), strerror() needs + * getrandom(2) and brk(2) as it allocates memory for the locale-translated + * error description, but our seccomp profiles forbid both. + * + * Use the strerror_() wrapper instead, calling into strerrordesc_np() to get + * a static untranslated string. It's a GNU implementation, but also defined by + * bionic. + * + * If strerrordesc_np() is not defined (e.g. musl), call strerror(). C libraries + * not defining strerrordesc_np() are expected to provide strerror() + * implementations that are simple enough for us to call. + */ +__attribute__ ((weak)) const char *strerrordesc_np(int errnum); + +/** + * strerror_() - strerror() wrapper calling strerrordesc_np() if available + * @errnum: Error code + * + * Return: error description string + */ +static inline const char *strerror_(int errnum) +{ + if (strerrordesc_np) + return strerrordesc_np(errnum); + + return strerror(errnum); +} + +#define strerror(x) @ "Don't call strerror() directly, use strerror_() instead" + #endif /* COMMON_H */ diff --git a/conf.c b/conf.c index 0586107..27aded8 100644 --- a/conf.c +++ b/conf.c @@ -308,7 +308,7 @@ static void conf_netns_opt(char *netns, const char *arg) * @argv: Command line arguments */ static void conf_pasta_ns(int *netns_only, char *userns, char *netns, - int optind, int argc, char *argv[]) + int optind, int argc, const char *argv[]) { if (*netns && optind != argc) die("Both --netns and PID or command given"); diff --git a/log.h b/log.h index dbab006..c6befe3 100644 --- a/log.h +++ b/log.h @@ -6,8 +6,57 @@ #ifndef LOG_H #define LOG_H -#include #include +#include +#include + +#ifdef PESTO + +#include + +#include "common.h" + +extern bool debug_flag; + +#define msg(...) \ + do { \ + FPRINTF(stderr, __VA_ARGS__); \ + FPRINTF(stderr, "\n"); \ + } while (0) + +#define msg_perror(...) \ + do { \ + int errno_ = errno; \ + FPRINTF(stderr, __VA_ARGS__); \ + FPRINTF(stderr, ": %s\n", strerror_(errno_)); \ + } while (0) + +#define die(...) \ + do { \ + msg(__VA_ARGS__); \ + exit(EXIT_FAILURE); \ + } while (0) + +#define die_perror(...) \ + do { \ + msg_perror(__VA_ARGS__); \ + exit(EXIT_FAILURE); \ + } while (0) + +#define warn(...) msg(__VA_ARGS__) +#define warn_perror(...) msg_perror(__VA_ARGS__) +#define info(...) msg(__VA_ARGS__) +#define info_perror(...) msg_perror(__VA_ARGS__) + +#define debug(...) \ + do { \ + if (debug_flag) \ + msg(__VA_ARGS__); \ + } while (0) + +#else /* !PESTO */ + +#include #include #include @@ -109,4 +158,6 @@ void __openlog(const char *ident, int option, int facility); void logfile_init(const char *name, const char *path, size_t size); void __setlogmask(int mask); +#endif /* !PESTO */ + #endif /* LOG_H */ diff --git a/pasta.c b/pasta.c index bab945f..4e7ee54 100644 --- a/pasta.c +++ b/pasta.c @@ -521,7 +521,7 @@ void pasta_netns_quit_init(const struct ctx *c) * @c: Execution context * @inotify_fd: inotify file descriptor with watch on namespace directory */ -void pasta_netns_quit_inotify_handler(struct ctx *c, int inotify_fd) +void pasta_netns_quit_inotify_handler(const struct ctx *c, int inotify_fd) { char buf[sizeof(struct inotify_event) + NAME_MAX + 1] __attribute__ ((aligned(__alignof__(struct inotify_event)))); @@ -547,7 +547,7 @@ void pasta_netns_quit_inotify_handler(struct ctx *c, int inotify_fd) * @c: Execution context * @ref: epoll reference for timer descriptor */ -void pasta_netns_quit_timer_handler(struct ctx *c, union epoll_ref ref) +void pasta_netns_quit_timer_handler(const struct ctx *c, union epoll_ref ref) { uint64_t expirations; ssize_t n; diff --git a/pesto.c b/pesto.c index 9f2fa5d..f0916e8 100644 --- a/pesto.c +++ b/pesto.c @@ -34,18 +34,12 @@ #include "common.h" #include "seccomp_pesto.h" #include "pesto.h" +#include "log.h" -static bool debug_flag = false; +bool debug_flag = false; static char stdout_buf[BUFSIZ]; -#define die(...) \ - do { \ - FPRINTF(stderr, __VA_ARGS__); \ - FPRINTF(stderr, "\n"); \ - exit(EXIT_FAILURE); \ - } while (0) - /** * usage() - Print usage, exit with given status code * @name: Executable name @@ -99,7 +93,7 @@ int main(int argc, char **argv) * breaking our seccomp profile. */ if (setvbuf(stdout, stdout_buf, _IOFBF, sizeof(stdout_buf))) - die("Failed to set stdout buffer"); + die_perror("Failed to set stdout buffer"); do { optname = getopt_long(argc, argv, optstring, options, NULL); @@ -126,7 +120,7 @@ int main(int argc, char **argv) if (argc - optind != 1) usage(argv[0], stderr, EXIT_FAILURE); - printf("debug_flag=%d, path=\"%s\"\n", debug_flag, argv[optind]); + debug("debug_flag=%d, path=\"%s\"", debug_flag, argv[optind]); die("pesto is not implemented yet"); } diff --git a/tap.c b/tap.c index 7d06189..412f437 100644 --- a/tap.c +++ b/tap.c @@ -756,6 +756,11 @@ resume: if (IN4_IS_ADDR_LOOPBACK(&iph->saddr) || IN4_IS_ADDR_LOOPBACK(&iph->daddr)) { + /* The scope of sstr and dstr could be in theory reduced + * into the conditional block debug() expands to, but + * it's awkward and unreadable, so ignore this warning. + */ + /* cppcheck-suppress [variableScope,unmatchedSuppression] */ char sstr[INET_ADDRSTRLEN], dstr[INET_ADDRSTRLEN]; debug("Loopback address on tap interface: %s -> %s", @@ -929,6 +934,11 @@ resume: continue; if (IN6_IS_ADDR_LOOPBACK(saddr) || IN6_IS_ADDR_LOOPBACK(daddr)) { + /* The scope of sstr and dstr could be in theory reduced + * into the conditional block debug() expands to, but + * it's awkward and unreadable, so ignore this warning. + */ + /* cppcheck-suppress [variableScope,unmatchedSuppression] */ char sstr[INET6_ADDRSTRLEN], dstr[INET6_ADDRSTRLEN]; debug("Loopback address on tap interface: %s -> %s", @@ -1304,7 +1314,7 @@ void tap_handler_pasta(struct ctx *c, uint32_t events, * tap_backend_show_hints() - Give help information to start QEMU * @c: Execution context */ -static void tap_backend_show_hints(struct ctx *c) +static void tap_backend_show_hints(const struct ctx *c) { switch (c->mode) { case MODE_PASTA: diff --git a/util.h b/util.h index 770ff93..e90be47 100644 --- a/util.h +++ b/util.h @@ -302,38 +302,6 @@ static inline bool mod_between(unsigned x, unsigned i, unsigned j, unsigned m) void raw_random(void *buf, size_t buflen); -/* - * Starting from glibc 2.40.9000 and commit 25a5eb4010df ("string: strerror, - * strsignal cannot use buffer after dlmopen (bug 32026)"), strerror() needs - * getrandom(2) and brk(2) as it allocates memory for the locale-translated - * error description, but our seccomp profiles forbid both. - * - * Use the strerror_() wrapper instead, calling into strerrordesc_np() to get - * a static untranslated string. It's a GNU implementation, but also defined by - * bionic. - * - * If strerrordesc_np() is not defined (e.g. musl), call strerror(). C libraries - * not defining strerrordesc_np() are expected to provide strerror() - * implementations that are simple enough for us to call. - */ -__attribute__ ((weak)) const char *strerrordesc_np(int errnum); - -/** - * strerror_() - strerror() wrapper calling strerrordesc_np() if available - * @errnum: Error code - * - * Return: error description string - */ -static inline const char *strerror_(int errnum) -{ - if (strerrordesc_np) - return strerrordesc_np(errnum); - - return strerror(errnum); -} - -#define strerror(x) @ "Don't call strerror() directly, use strerror_() instead" - /* * Workarounds for https://github.com/llvm/llvm-project/issues/58992 * -- 2.43.0

From: David Gibson Extend the dynamic update protocol to expose the pif indices and names from a running passt/pasta to the pesto tool. pesto records that data and prints it out. Signed-off-by: David Gibson Reviewed-by: Laurent Vivier [sbrivio: In read_pif_conf(), force a redundant termination of the interface name, the existing check isn't obvious enough for static checkers] [sbrivio: Drop @resv_ left-over in description of struct pesto_pif_info, reported by Jon Maloy] [sbrivio: Fix minor nits reported by Laurent] [sbrivio: Initialise struct pesto_pif_info in conf_send_rules() with zeroes, otherwise the pif name might be seen as not terminated, and we'll expose memory from the back-end] [sbrivio: Fix conflicts in Makefile] Signed-off-by: Stefano Brivio --- common.h | 2 + conf.c | 41 ++++++++++++++++ pesto.c | 134 ++++++++++++++++++++++++++++++++++++++++++++++++++++ pesto.h | 18 ++++++- pif.h | 5 +- serialise.c | 4 ++ serialise.h | 1 + util.h | 2 - 8 files changed, 200 insertions(+), 7 deletions(-) diff --git a/common.h b/common.h index 4251781..68573b4 100644 --- a/common.h +++ b/common.h @@ -53,4 +53,6 @@ static inline const char *strerror_(int errnum) #define strerror(x) @ "Don't call strerror() directly, use strerror_() instead" +#define ARRAY_SIZE(a) ((int)(sizeof(a) / sizeof((a)[0]))) + #endif /* COMMON_H */ diff --git a/conf.c b/conf.c index 9eed1ec..70c5590 100644 --- a/conf.c +++ b/conf.c @@ -1927,6 +1927,43 @@ void conf(struct ctx *c, int argc, char **argv) static void conf_accept(struct ctx *c); +/** + * conf_send_rules() - Send current forwarding rules to config client (pesto) + * @c: Execution context + * @fd: Socket to the client + * + * Return: 0 on success, -1 on failure + * + * FIXME: So far only sends pif ids and names + */ +static int conf_send_rules(const struct ctx *c, int fd) +{ + unsigned pif; + + for (pif = 0; pif < PIF_NUM_TYPES; pif++) { + struct pesto_pif_info info = { 0 }; + int rc; + + if (!c->fwd[pif]) + continue; + + assert(pif != PIF_NONE); + + rc = snprintf(info.name, sizeof(info.name), "%s", pif_name(pif)); + assert(rc >= 0 && (size_t)rc < sizeof(info.name)); + + if (write_u8(fd, pif) < 0) + return -1; + if (write_all_buf(fd, &info, sizeof(info)) < 0) + return -1; + } + + if (write_u8(fd, PIF_NONE) < 0) + return -1; + + return 0; +} + /** * conf_close() - Close configuration / control socket and clean up * @c: Execution context @@ -1970,6 +2007,7 @@ static void conf_accept(struct ctx *c) struct pesto_hello hello = { .magic = PESTO_SERVER_MAGIC, .version = htonl(PESTO_PROTOCOL_VERSION), + .pif_name_size = htonl(PIF_NAME_SIZE), }; union epoll_ref ref = { .type = EPOLL_TYPE_CONF }; struct ucred uc = { 0 }; @@ -2010,6 +2048,9 @@ retry: "Warning: Using experimental unsupported configuration protocol"); } + if (conf_send_rules(c, fd) < 0) + goto fail; + return; fail: diff --git a/pesto.c b/pesto.c index ab476c5..b33492a 100644 --- a/pesto.c +++ b/pesto.c @@ -60,6 +60,127 @@ static void usage(const char *name, FILE *f, int status) exit(status); } +/* Maximum number of pifs with rule tables */ +#define MAX_PIFS 3 + +struct pif_configuration { + uint8_t pif; + char name[PIF_NAME_SIZE]; +}; + +struct configuration { + uint32_t npifs; + struct pif_configuration pif[MAX_PIFS]; +}; + +/** + * pif_conf_by_num() - Find a pif's configuration by pif id + * @conf: Configuration description + * @pif: pif id + * + * Return: pointer to the pif_configuration for @pif, or NULL if not found + */ +static struct pif_configuration *pif_conf_by_num(struct configuration *conf, + uint8_t pif) +{ + unsigned i; + + for (i = 0; i < conf->npifs; i++) { + if (conf->pif[i].pif == pif) + return &conf->pif[i]; + } + + return NULL; +} + +/** + * pif_conf_by_name() - Find a pif's configuration by name + * @conf: Configuration description + * @name: Interface name + * + * Return: pif_configuration for pif named @name, or NULL if not found + */ +static struct pif_configuration *pif_conf_by_name(struct configuration *conf, + const char *name) +{ + unsigned i; + + for (i = 0; i < conf->npifs; i++) { + if (strcmp(conf->pif[i].name, name) == 0) + return &conf->pif[i]; + } + + return NULL; +} + +/** + * pesto_read_rules() - Read rulestate from passt/pasta + * @fd: Control socket + * @conf: Configuration description to update + */ +static bool read_pif_conf(int fd, struct configuration *conf) +{ + struct pif_configuration *pc; + struct pesto_pif_info info; + uint8_t pif; + + if (read_u8(fd, &pif) < 0) + die("Error reading from control socket"); + + if (pif == PIF_NONE) + return false; + + debug("Receiving config for PIF %"PRIu8, pif); + + if (conf->npifs >= ARRAY_SIZE(conf->pif)) { + die("passt has more pifs than pesto can manage (max %d)", + ARRAY_SIZE(conf->pif)); + } + + pc = &conf->pif[conf->npifs]; + pc->pif = pif; + + if (read_all_buf(fd, &info, sizeof(info)) < 0) + die("Error reading from control socket"); + + if (info.name[sizeof(info.name)-1]) + die("Interface name was not NULL terminated"); + /* Redundant, to make static checkers happy */ + info.name[sizeof(info.name) - 1] = '\0'; + + static_assert(sizeof(info.name) == sizeof(pc->name), + "Mismatching pif name lengths"); + memcpy(pc->name, info.name, sizeof(pc->name)); + + debug("PIF %"PRIu8": %s", pc->pif, pc->name); + + /* O(n^2), but n is bounded by MAX_PIFS */ + if (pif_conf_by_num(conf, pc->pif)) + die("Received duplicate interface identifier"); + + /* O(n^2), but n is bounded by MAX_PIFS */ + if (pif_conf_by_name(conf, pc->name)) + die("Received duplicate interface name"); + + conf->npifs++; + return true; +} + +/** + * show_conf() - Show current configuration obtained from passt/pasta + * @conf: Configuration description + */ +static void show_conf(const struct configuration *conf) +{ + unsigned i; + + for (i = 0; i < conf->npifs; i++) { + const struct pif_configuration *pc = &conf->pif[i]; + printf(" %s\n", pc->name); + printf(" TBD\n"); + } +} + /** * main() - Dynamic reconfiguration client main program * @argc: Argument count @@ -80,6 +201,7 @@ int main(int argc, char **argv) { 0 }, }; struct sockaddr_un a = { AF_UNIX, "" }; + struct configuration conf = { 0 }; const char *optstring = "dh"; struct pesto_hello hello; struct sock_fprog prog; @@ -162,6 +284,18 @@ int main(int argc, char **argv) "Warning: Using experimental protocol version, client and server must match\n"); } + if (ntohl(hello.pif_name_size) != PIF_NAME_SIZE) { + die("Server has unexpected pif name size (%" + PRIu32" not %"PRIu32 ")", + ntohl(hello.pif_name_size), PIF_NAME_SIZE); + } + + while (read_pif_conf(s, &conf)) + ; + + printf("passt/pasta configuration (%s)\n", a.sun_path); + show_conf(&conf); + if (shutdown(s, SHUT_RDWR) < 0 || close(s) < 0) die_perror("Error shutting down control socket"); diff --git a/pesto.h b/pesto.h index 3c93d3e..fda0ef6 100644 --- a/pesto.h +++ b/pesto.h @@ -17,18 +17,32 @@ /* Version 0 is reserved for unreleased / unsupported experimental versions */ #define PESTO_PROTOCOL_VERSION 1 +/* Maximum size of a pif name, including \0 */ +#define PIF_NAME_SIZE (128) +#define PIF_NONE 0 + /** * struct pesto_hello - Server introduction message - * @magic: PESTO_SERVER_MAGIC - * @version: Version number + * @magic: PESTO_SERVER_MAGIC + * @version: Version number + * @pif_name_size: Server's value for PIF_NAME_SIZE */ struct pesto_hello { char magic[8]; uint32_t version; + uint32_t pif_name_size; } __attribute__ ((__packed__)); static_assert(sizeof(PESTO_SERVER_MAGIC) == sizeof(((struct pesto_hello *)0)->magic), "PESTO_SERVER_MAGIC has wrong size"); +/** + * struct pesto_pif_info - Message with basic metadata about a pif + * @name: Name (\0 terminated) + */ +struct pesto_pif_info { + char name[PIF_NAME_SIZE]; +} __attribute__ ((__packed__)); + #endif /* PESTO_H */ diff --git a/pif.h b/pif.h index 553c742..48d4919 100644 --- a/pif.h +++ b/pif.h @@ -11,6 +11,7 @@ #include +#include "pesto.h" #include "epoll_type.h" union inany_addr; @@ -24,7 +25,7 @@ union sockaddr_inany; */ enum pif_type { /* Invalid or not present pif */ - PIF_NONE = 0, + PIF_NONE_ = PIF_NONE, /* Host socket interface */ PIF_HOST, /* Qemu socket or namespace tuntap interface */ @@ -35,8 +36,6 @@ enum pif_type { PIF_NUM_TYPES, }; -/* Maximum size of a pif name, including \0 */ -#define PIF_NAME_SIZE (128) extern const char pif_type_str[][PIF_NAME_SIZE]; static inline const char *pif_type(enum pif_type pt) diff --git a/serialise.c b/serialise.c index 346df99..e083112 100644 --- a/serialise.c +++ b/serialise.c @@ -121,6 +121,10 @@ int write_all_buf(int fd, const void *buf, size_t len) return write_all_buf(fd, &beval, sizeof(beval)); \ } +#define be8toh(x) (x) +#define htobe8(x) (x) + +SERIALISE_UINT(8) SERIALISE_UINT(32) #undef SERIALISE_UINT diff --git a/serialise.h b/serialise.h index a88f3de..4714f4c 100644 --- a/serialise.h +++ b/serialise.h @@ -16,6 +16,7 @@ int write_all_buf(int fd, const void *buf, size_t len); int read_u##bits(int fd, uint##bits##_t *val); \ int write_u##bits(int fd, uint##bits##_t val); +SERIALISE_UINT_DECL(8) SERIALISE_UINT_DECL(32) #endif /* SERIALISE_H */ diff --git a/util.h b/util.h index e90be47..c788382 100644 --- a/util.h +++ b/util.h @@ -87,8 +87,6 @@ void abort_with_msg(const char *fmt, ...) #define V6 1 #define IP_VERSIONS 2 -#define ARRAY_SIZE(a) ((int)(sizeof(a) / sizeof((a)[0]))) - #define foreach(item, array) \ for ((item) = (array); (item) - (array) < ARRAY_SIZE(array); (item)++) -- 2.43.0

From: David Gibson inany contains a number of helpful functions for dealing with addresses which might be IPv4 or IPv6. We're going to want to use that in pesto. For the most part inany doesn't depend on other passt/pasta internals, however it does depend on siphash.h, which pesto doesn't need. Move the single dependent function, inany_siphash_feed() to siphash.h, renaming to match. Use that include inany.[ch] into pesto as well as passt/pasta. While we're there reformat pesto.c's header comment to match the convention used in most other files. Signed-off-by: David Gibson Reviewed-by: Laurent Vivier Signed-off-by: Stefano Brivio --- common.h | 20 ++++++++++++++++++-- flow.c | 4 ++-- fwd.c | 2 +- fwd.h | 1 + fwd_rule.h | 1 + inany.c | 19 ++++++++++++++----- inany.h | 17 ++--------------- pif.h | 1 + siphash.h | 13 +++++++++++++ util.h | 16 ---------------- 10 files changed, 53 insertions(+), 41 deletions(-) diff --git a/common.h b/common.h index ae6908d..f2518f6 100644 --- a/common.h +++ b/common.h @@ -18,9 +18,27 @@ "This is free software: you are free to change and redistribute it.\n" \ "There is NO WARRANTY, to the extent permitted by law.\n\n" +#ifndef MIN +#define MIN(x, y) (((x) < (y)) ? (x) : (y)) +#endif +#ifndef MAX +#define MAX(x, y) (((x) > (y)) ? (x) : (y)) +#endif + +#define MAX_FROM_BITS(n) (((1U << (n)) - 1)) + /* FPRINTF() intentionally silences cert-err33-c clang-tidy warnings */ #define FPRINTF(f, ...) (void)fprintf(f, __VA_ARGS__) +#define ARRAY_SIZE(a) ((int)(sizeof(a) / sizeof((a)[0]))) + +#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) +#define DIV_ROUND_CLOSEST(n, d) (((n) + (d) / 2) / (d)) +#define ROUND_DOWN(x, y) ((x) & ~((y) - 1)) +#define ROUND_UP(x, y) (((x) + (y) - 1) & ~((y) - 1)) + +#define UINT16_STRLEN (sizeof("65535")) + /* * Starting from glibc 2.40.9000 and commit 25a5eb4010df ("string: strerror, * strsignal cannot use buffer after dlmopen (bug 32026)"), strerror() needs @@ -53,8 +71,6 @@ static inline const char *strerror_(int errnum) #define strerror(x) @ "Don't call strerror() directly, use strerror_() instead" -#define ARRAY_SIZE(a) ((int)(sizeof(a) / sizeof((a)[0]))) - #ifndef __bswap_constant_16 #define __bswap_constant_16(x) \ ((uint16_t) ((((x) >> 8) & 0xff) | (((x) & 0xff) << 8))) diff --git a/flow.c b/flow.c index 56a6c6d..91f2b81 100644 --- a/flow.c +++ b/flow.c @@ -680,8 +680,8 @@ static uint64_t flow_hash(const struct ctx *c, uint8_t proto, uint8_t pif, { struct siphash_state state = SIPHASH_INIT(c->hash_secret); - inany_siphash_feed(&state, &side->oaddr); - inany_siphash_feed(&state, &side->eaddr); + siphash_feed_inany(&state, &side->oaddr); + siphash_feed_inany(&state, &side->eaddr); return siphash_final(&state, 38, (uint64_t)proto << 40 | (uint64_t)pif << 32 | diff --git a/fwd.c b/fwd.c index 728a783..8849cfc 100644 --- a/fwd.c +++ b/fwd.c @@ -80,7 +80,7 @@ static size_t neigh_table_slot(const struct ctx *c, struct siphash_state st = SIPHASH_INIT(c->hash_secret); uint32_t i; - inany_siphash_feed(&st, key); + siphash_feed_inany(&st, key); i = siphash_final(&st, sizeof(*key), 0); return ((size_t)i) & (NEIGH_TABLE_SIZE - 1); diff --git a/fwd.h b/fwd.h index 8f845d0..ac24782 100644 --- a/fwd.h +++ b/fwd.h @@ -19,6 +19,7 @@ #include "fwd_rule.h" struct flowside; +struct ctx; #define FWD_NO_HINT (-1) diff --git a/fwd_rule.h b/fwd_rule.h index 5855138..f51f1b4 100644 --- a/fwd_rule.h +++ b/fwd_rule.h @@ -13,6 +13,7 @@ #include #include +#include "common.h" #include "ip.h" #include "inany.h" #include "bitmap.h" diff --git a/inany.c b/inany.c index 2a586ed..23faf3f 100644 --- a/inany.c +++ b/inany.c @@ -1,9 +1,19 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later - * Copyright Red Hat - * Author: David Gibson +// SPDX-License-Identifier: GPL-2.0-or-later + +/* PASST - Plug A Simple Socket Transport + * for qemu/UNIX domain socket mode + * + * PASTA - Pack A Subtle Tap Abstraction + * for network namespace/tap device mode + * + * PESTO - Programmable Extensible Socket Translation Orchestrator + * front-end for passt(1) and pasta(1) forwarding configuration * * inany.c - Types and helpers for handling addresses which could be * IPv6 or IPv4 (encoded as IPv4-mapped IPv6 addresses) + * + * Copyright Red Hat + * Author: David Gibson */ #include @@ -13,9 +23,8 @@ #include #include -#include "util.h" +#include "common.h" #include "ip.h" -#include "siphash.h" #include "inany.h" #include "fwd.h" diff --git a/inany.h b/inany.h index 1f7741d..73385b9 100644 --- a/inany.h +++ b/inany.h @@ -11,13 +11,11 @@ #include #include +#include #include -#include "util.h" +#include "common.h" #include "ip.h" -#include "siphash.h" - -struct siphash_state; /** union inany_addr - Represents either an IPv4 or IPv6 address * @a6: Address as an IPv6 address, may be IPv4-mapped @@ -301,17 +299,6 @@ static inline int inany_from_sockaddr(union inany_addr *dst, in_port_t *port, return -1; } -/** inany_siphash_feed- Fold IPv[46] address into an in-progress siphash - * @state: siphash state - * @aa: inany to hash - */ -static inline void inany_siphash_feed(struct siphash_state *state, - const union inany_addr *aa) -{ - siphash_feed(state, (uint64_t)aa->u32[0] << 32 | aa->u32[1]); - siphash_feed(state, (uint64_t)aa->u32[2] << 32 | aa->u32[3]); -} - #define INANY_ADDRSTRLEN MAX(INET_ADDRSTRLEN, INET6_ADDRSTRLEN) bool inany_matches(const union inany_addr *a, const union inany_addr *b); diff --git a/pif.h b/pif.h index 48d4919..62223d1 100644 --- a/pif.h +++ b/pif.h @@ -16,6 +16,7 @@ union inany_addr; union sockaddr_inany; +struct ctx; /** * enum pif_type - Type of passt/pasta interface ("pif") diff --git a/siphash.h b/siphash.h index bbddcac..313b894 100644 --- a/siphash.h +++ b/siphash.h @@ -47,6 +47,8 @@ #include #include +#include "inany.h" + /** * struct siphash_state - Internal state of siphash calculation */ @@ -101,6 +103,17 @@ static inline void siphash_feed(struct siphash_state *state, uint64_t in) state->v[0] ^= in; } +/** siphash_feed_inany() - Fold IPv[46] address into an in-progress siphash + * @state: siphash state + * @aa: inany to hash + */ +static inline void siphash_feed_inany(struct siphash_state *state, + const union inany_addr *aa) +{ + siphash_feed(state, (uint64_t)aa->u32[0] << 32 | aa->u32[1]); + siphash_feed(state, (uint64_t)aa->u32[2] << 32 | aa->u32[3]); +} + /** * siphash_final() - Finalize SipHash calculations * @v: siphash state (4 x 64-bit integers) diff --git a/util.h b/util.h index dc14c78..70aadeb 100644 --- a/util.h +++ b/util.h @@ -29,20 +29,6 @@ #define IP_MAX_MTU USHRT_MAX #endif -#ifndef MIN -#define MIN(x, y) (((x) < (y)) ? (x) : (y)) -#endif -#ifndef MAX -#define MAX(x, y) (((x) > (y)) ? (x) : (y)) -#endif - -#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) -#define DIV_ROUND_CLOSEST(n, d) (((n) + (d) / 2) / (d)) -#define ROUND_DOWN(x, y) ((x) & ~((y) - 1)) -#define ROUND_UP(x, y) (((x) + (y) - 1) & ~((y) - 1)) - -#define MAX_FROM_BITS(n) (((1U << (n)) - 1)) - #define SWAP(a, b) \ do { \ __typeof__(a) __x = (a); (a) = (b); (b) = __x; \ @@ -202,8 +188,6 @@ static inline const char *af_name(sa_family_t af) } } -#define UINT16_STRLEN (sizeof("65535")) - /* inet address (- '\0') + port (u16) (- '\0') + ':' + '\0' */ #define SOCKADDR_INET_STRLEN \ (INET_ADDRSTRLEN-1 + UINT16_STRLEN-1 + sizeof(":")) -- 2.43.0

From: David Gibson This adds parsing of options using fwd_rule_parse(), validates them and adds them to the existing rules. It doesn't yet send those rules back to passt or pasta. Message-ID: <20260322141843.4095972-3-sbrivio@redhat.com> [dwg: Based on an early draft by Stefano] Signed-off-by: David Gibson [sbrivio: Recycled usage messages for -T and -U from conf.c as suggested by Laurent, dropped unrelated whitespace change] [sbrivio: Add description of -t, -u, -T, -U to pesto.1] [sbrivio: Fix conflicts in Makefile] [sbrivio: Add description of -s to pesto.1 as well] Signed-off-by: Stefano Brivio Reviewed-by: Laurent Vivier --- fwd_rule.c | 2 +- fwd_rule.h | 1 + pesto.1 | 131 +++++++++++++++++++++++++++++++++++++++++++++++++++++ pesto.c | 111 +++++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 240 insertions(+), 5 deletions(-) diff --git a/fwd_rule.c b/fwd_rule.c index c2824d5..b55e4df 100644 --- a/fwd_rule.c +++ b/fwd_rule.c @@ -187,7 +187,7 @@ static bool fwd_rule_conflicts(const struct fwd_rule *a, const struct fwd_rule * * * Return: 0 on success, negative error code on failure */ -static int fwd_rule_add(struct fwd_table *fwd, const struct fwd_rule *new) +int fwd_rule_add(struct fwd_table *fwd, const struct fwd_rule *new) { /* Flags which can be set from the caller */ const uint8_t allowed_flags = FWD_WEAK | FWD_SCAN | FWD_DUAL_STACK_ANY; diff --git a/fwd_rule.h b/fwd_rule.h index 330d49e..f43b37d 100644 --- a/fwd_rule.h +++ b/fwd_rule.h @@ -103,6 +103,7 @@ const char *fwd_rule_fmt(const struct fwd_rule *rule, char *dst, size_t size); void fwd_rule_parse(char optname, const char *optarg, struct fwd_table *fwd); int fwd_rule_read(int fd, struct fwd_rule *rule); int fwd_rule_write(int fd, const struct fwd_rule *rule); +int fwd_rule_add(struct fwd_table *fwd, const struct fwd_rule *new); /** * fwd_rules_dump() - Dump forwarding rules diff --git a/pesto.1 b/pesto.1 index 9f54362..1e1c0f3 100644 --- a/pesto.1 +++ b/pesto.1 @@ -31,6 +31,137 @@ Be verbose. .BR \-h ", " \-\-help Display a help message and exit. +.TP +.BR \-s ", " \-\-show +Show the forwarding configuration before and after changes are applied. + +.TP +.BR \-t ", " \-\-tcp-ports " " \fIspec +Configure TCP port forwarding to guest or namespace. \fIspec\fR can be one of: +.RS + +.TP +.BR none +Don't forward any ports + +.TP +[\fIaddress\fR[\fB%\fR\fIinterface\fR]\fB/\fR]\fIports\fR ... +Specific ports to forward. Optionally, a specific listening address +and interface name (since Linux 5.7) can be specified. \fIports\fR +may be either: +.RS +.TP +\fBall\fR +Forward all unbound, non-ephemeral ports, as permitted by current capabilities. +No failures are reported for unavailable ports, unless no ports could be +forwarded at all. +.RE + +.RS +or a comma-separated list of entries which may be any of: +.TP +\fIfirst\fR[\fB-\fR\fIlast\fR][\fB:\fR\fItofirst\fR[\fB-\fR\fItolast\fR]] +Include range. Forward port numbers between \fIfirst\fR and \fIlast\fR +(inclusive) to ports between \fItofirst\fR and \fItolast\fR. If +\fItofirst\fR and \fItolast\fR are omitted, assume the same as +\fIfirst\fR and \fIlast\fR. If \fIlast\fR is omitted, assume the same +as \fIfirst\fR. + +.TP +\fB~\fR\fIfirst\fR[\fB-\fR\fIlast\fR] +Exclude range. Don't forward port numbers between \fIfirst\fR and +\fIlast\fR. This takes precedences over include ranges. + +.TP +.BR auto +\fBpasta\fR only. Only forward ports in the specified set if the +target ports are bound in the namespace. The list of ports is +periodically derived (every second) from listening sockets reported by +\fI/proc/net/tcp\fR and \fI/proc/net/tcp6\fR, see \fBproc\fR(5). +.RE + +Specifying excluded ranges only implies that all other non-ephemeral +ports are forwarded. Specifying no ranges at all implies forwarding +all non-ephemeral ports permitted by current capabilities. In this +case, no failures are reported for unavailable ports, unless no ports +could be forwarded at all. + +Examples: +.RS +.TP +-t all +Forward all unbound, non-ephemeral ports as permitted by current +capabilities to the corresponding port on the guest or namespace +.TP +-t ::1/all +For the local address ::1, forward all unbound, non-ephemeral ports as +permitted by current capabilities +.TP +-t 22 +Forward local port 22 to port 22 on the guest or namespace +.TP +-t 22:23 +Forward local port 22 to port 23 on the guest or namespace +.TP +-t 22,25 +Forward local ports 22 and 25 to ports 22 and 25 on the guest or namespace +.TP +-t 22-80 +Forward local ports between 22 and 80 to corresponding ports on the guest or +namespace +.TP +-t 22-80:32-90 +Forward local ports between 22 and 80 to ports between 32 and 90 on the guest or +namespace +.TP +-t 192.0.2.1/22 +Forward local port 22, bound to 192.0.2.1, to port 22 on the guest or namespace +.TP +-t 192.0.2.1%eth0/22 +Forward local port 22, bound to 192.0.2.1 and interface eth0, to port 22 +.TP +-t %eth0/22 +Forward local port 22, bound to any address on interface eth0, to port 22 +.TP +-t 2000-5000,~3000-3010 +Forward local ports between 2000 and 5000, except for those between 3000 and +3010 +.TP +-t 192.0.2.1/20-30,~25 +For the local address 192.0.2.1, forward ports between 20 and 24 and between 26 +and 30 +.TP +-t ~20000-20010 +Forward all ports to the guest, except for the range from 20000 to 20010 +.TP +-t auto +Automatically forward any ports which are bound in the namespace +.TP +-t ::1/auto +Automatically forward any ports which are bound in the namespace, +listening only on local port ::1 +.TP +-t 8000-8010,auto +Forward ports in the range 8000-8010 if and only if they are bound in +the namespace +.RE +.RE + +.TP +.BR \-u ", " \-\-udp-ports " " \fIspec +Configure UDP port forwarding to guest. \fIspec\fR is as described for TCP +above. + +.TP +.BR \-T ", " \-\-tcp-ns " " \fIspec +Configure TCP port forwarding from target namespace to init namespace. +\fIspec\fR is as described above. + +.TP +.BR \-U ", " \-\-udp-ns " " \fIspec +Configure UDP port forwarding from target namespace to init namespace. +\fIspec\fR is as described above. + .TP .BR \-\-version Show version and exit. diff --git a/pesto.c b/pesto.c index 92a8cb2..16b3a5a 100644 --- a/pesto.c +++ b/pesto.c @@ -55,6 +55,43 @@ static void usage(const char *name, FILE *f, int status) FPRINTF(f, "Usage: %s [OPTION]... PATH\n", name); FPRINTF(f, "\n" + " -t, --tcp-ports SPEC TCP inbound port forwarding\n" + " can be specified multiple times\n" + " SPEC can be:\n" + " 'none': don't forward any ports\n" + " [ADDR[%%IFACE]/]PORTS: forward specific ports\n" + " PORTS is either 'all' (forward all unbound, non-ephemeral\n" + " ports), or a comma-separated list of ports, optionally\n" + " ranged with '-' and optional target ports after ':'.\n" + " Ranges can be reduced by excluding ports or ranges\n" + " prefixed by '~'.\n" + " The 'auto' keyword may be given to only forward\n" + " ports which are bound in the target namespace\n" + " Examples:\n" + " -t all Forward all ports\n" + " -t 127.0.0.1/all Forward all ports from local address\n" + " 127.0.0.1\n" + " -t 22 Forward local port 22 to 22\n" + " -t 22:23 Forward local port 22 to 23\n" + " -t 22,25 Forward ports 22, 25 to ports 22, 25\n" + " -t 22-80 Forward ports 22 to 80\n" + " -t 22-80:32-90 Forward ports 22 to 80 to\n" + " corresponding port numbers plus 10\n" + " -t 192.0.2.1/5 Bind port 5 of 192.0.2.1\n" + " -t 5-25,~10-20 Forward ports 5 to 9, and 21 to 25\n" + " -t ~25 Forward all ports except for 25\n" + " -t auto Forward all ports bound in namespace\n" + " -t 192.0.2.2/auto Forward ports from 192.0.2.2 if\n" + " they are bound in the namespace\n" + " -t 8000-8010,auto Forward ports 8000-8010 if they\n" + " are bound in the namespace\n" + " -u, --udp-ports SPEC UDP inbound port forwarding\n" + " SPEC is as described for TCP above\n" + " -T, --tcp-ns SPEC TCP port forwarding to init namespace\n" + " SPEC is as described above\n" + " -U, --udp-ns SPEC UDP port forwarding to init namespace\n" + " SPEC is as described above\n" + " -s, --show Show configuration before and after\n" " -d, --debug Print debugging messages\n" " -h, --help Display this help message and exit\n" " --version Show version and exit\n"); @@ -207,6 +244,8 @@ static void show_conf(const struct configuration *conf) fwd_rules_dump(printf, pc->fwd.rules, pc->fwd.count, " ", "\n"); } + /* Flush stdout, so this doesn't get misordered with later debug()s */ + (void)fflush(stdout); } /** @@ -218,7 +257,7 @@ static void show_conf(const struct configuration *conf) * * #syscalls:pesto socket s390x:socketcall i686:socketcall * #syscalls:pesto connect shutdown close - * #syscalls:pesto exit_group fstat read write + * #syscalls:pesto exit_group fstat read write openat */ int main(int argc, char **argv) { @@ -226,11 +265,18 @@ int main(int argc, char **argv) {"debug", no_argument, NULL, 'd' }, {"help", no_argument, NULL, 'h' }, {"version", no_argument, NULL, 1 }, + {"tcp-ports", required_argument, NULL, 't' }, + {"udp-ports", required_argument, NULL, 'u' }, + {"tcp-ns", required_argument, NULL, 'T' }, + {"udp-ns", required_argument, NULL, 'U' }, + {"show", no_argument, NULL, 's' }, { 0 }, }; + struct pif_configuration *inbound, *outbound; struct sockaddr_un a = { AF_UNIX, "" }; + const char *optstring = "dht:u:T:U:s"; struct configuration conf = { 0 }; - const char *optstring = "dh"; + bool update = false, show = false; struct pesto_hello hello; struct sock_fprog prog; int optname, ret, s; @@ -251,6 +297,8 @@ int main(int argc, char **argv) if (setvbuf(stdout, stdout_buf, _IOFBF, sizeof(stdout_buf))) die_perror("Failed to set stdout buffer"); + fwd_probe_ephemeral(); + do { optname = getopt_long(argc, argv, optstring, options, NULL); @@ -258,6 +306,16 @@ int main(int argc, char **argv) case -1: case 0: break; + case 't': + case 'u': + case 'T': + case 'U': + /* Parse these options after we've read state from passt/pasta */ + update = true; + break; + case 's': + show = true; + break; case 'h': usage(argv[0], stdout, EXIT_SUCCESS); break; @@ -290,6 +348,8 @@ int main(int argc, char **argv) die_perror("Failed to connect to %s", a.sun_path); } + debug("Connected to passt/pasta control socket"); + ret = read_all_buf(s, &hello, sizeof(hello)); if (ret < 0) die_perror("Couldn't read server greeting"); @@ -327,9 +387,52 @@ int main(int argc, char **argv) while (read_pif_conf(s, &conf)) ; - printf("passt/pasta configuration (%s)\n", a.sun_path); - show_conf(&conf); + if (!update) { + printf("passt/pasta configuration (%s)\n", a.sun_path); + show_conf(&conf); + goto noupdate; + } + + if (show) { + printf("Previous configuration (%s)\n", a.sun_path); + show_conf(&conf); + } + + inbound = pif_conf_by_name(&conf, "HOST"); + outbound = pif_conf_by_name(&conf, "SPLICE"); + + optind = 0; + do { + optname = getopt_long(argc, argv, optstring, options, NULL); + + switch (optname) { + case 't': + case 'u': + if (!inbound) { + die("Can't use -%c, no inbound interface", + optname); + } + fwd_rule_parse(optname, optarg, &inbound->fwd); + break; + case 'T': + case 'U': + if (!outbound) { + die("Can't use -%c, no outbound interface", + optname); + } + fwd_rule_parse(optname, optarg, &outbound->fwd); + break; + default: + continue; + } + } while (optname != -1); + + if (show) { + printf("Updated configuration (%s)\n", a.sun_path); + show_conf(&conf); + } +noupdate: if (shutdown(s, SHUT_RDWR) < 0 || close(s) < 0) die_perror("Error shutting down control socket"); -- 2.43.0

From: David Gibson We can now receive updates to the forwarding rules from the pesto client and store them in a "pending" copy of the forwarding tables. Implement switching to using the new rules. The logic is in a new fwd_listen_switch(). For now this closes all listening sockets related to the old tables, swaps the active and pending tables, then listens based on the new tables. In future we look to improve this so that we don't temporarily stop listening on ports that both the old and new tables specify. Signed-off-by: David Gibson [sbrivio: In fwd_listen_switch(), use the destination size as argument to memcpy(), instead of sizeof(tmp), as suggested by Laurent] Signed-off-by: Stefano Brivio Reviewed-by: Laurent Vivier --- conf.c | 5 ++--- fwd.c | 34 ++++++++++++++++++++++++++++++++++ fwd.h | 1 + 3 files changed, 37 insertions(+), 3 deletions(-) diff --git a/conf.c b/conf.c index 25472bc..f4ab72a 100644 --- a/conf.c +++ b/conf.c @@ -2160,15 +2160,14 @@ void conf_handler(struct ctx *c, uint32_t events) fwd_rules_dump(info, fwd->rules, fwd->count, " ", ""); } + + fwd_listen_switch(c); } if (events & EPOLLHUP) { debug("Configuration client hangup"); - goto close; } - return; - close: conf_close(c); diff --git a/fwd.c b/fwd.c index d93d2e5..0697435 100644 --- a/fwd.c +++ b/fwd.c @@ -534,6 +534,40 @@ int fwd_listen_init(const struct ctx *c) return 0; } +/** + * fwd_listen_switch() - Switch from current to pending rules table + * @c: Execution context + */ +void fwd_listen_switch(struct ctx *c) +{ + struct fwd_table *tmp[PIF_NUM_TYPES]; + unsigned i; + + /* Stop listening on the old tables */ + for (i = 0; i < PIF_NUM_TYPES; i++) { + struct fwd_table *fwd = c->fwd[i]; + + if (!fwd) + continue; + + debug("Flushing %u old %s rules", fwd->count, pif_name(i)); + fwd_listen_close(fwd); + fwd->count = fwd->sock_count = 0; + } + + /* Swap active and pending tables */ + static_assert(sizeof(tmp) == sizeof(c->fwd) && + sizeof(tmp) == sizeof(c->fwd_pending), + "Temporary has wrong size"); + memcpy(&tmp, (void *)c->fwd, sizeof(tmp)); + memcpy((void *)c->fwd, (void *)c->fwd_pending, sizeof(c->fwd)); + memcpy((void *)c->fwd_pending, &tmp, sizeof(c->fwd_pending)); + + /* Start listening on the new tables */ + if (fwd_listen_init(c) < 0) + err("Error switching to new forwarding rules"); +} + /* See enum in kernel's include/net/tcp_states.h */ #define UDP_LISTEN 0x07 #define TCP_LISTEN 0x0a diff --git a/fwd.h b/fwd.h index ac24782..b60697d 100644 --- a/fwd.h +++ b/fwd.h @@ -61,6 +61,7 @@ int fwd_listen_sync(const struct ctx *c, uint8_t pif, const struct fwd_scan *tcp, const struct fwd_scan *udp); void fwd_listen_close(const struct fwd_table *fwd); int fwd_listen_init(const struct ctx *c); +void fwd_listen_switch(struct ctx *c); bool nat_inbound(const struct ctx *c, const union inany_addr *addr, union inany_addr *translated); -- 2.43.0

Instead of just being able to add to the existing tables, implement an explicit --clear option to replace them, which now becomes the default behaviour, and implement explicit --add and --delete options to maintain the table and add or delete specific ports. The option --clear PIF forces the clearing of a table, instead. These options can be combined arbitrarily and are handled as sequential commands, as now described in pesto(1). If no option is given before forwarding specifiers for a matching table, the command line is interpreted as a replacement of the existing rules. To this end: - there's no protocol change, as pesto is anyway sending updated copies of the table - the forwarding table functions now include a new fwd_rule_del(), which deletes existing rule only if a matching one is found - a trivial fwd_rule_clear() is factored out from the existing conf_handler() implementation, so that it can be directly used in pesto The entry points for parsing of port specifiers now take an additional 'del' parameter which is passed down all the way before reaching the fwd_rule_add() implementation. If a rule should be deleted, at that point, fwd_rule_del() is called instead. Signed-off-by: Stefano Brivio --- conf.c | 26 +++++------- fwd_rule.c | 116 +++++++++++++++++++++++++++++++++++++++++++++++------ fwd_rule.h | 4 +- pesto.1 | 85 +++++++++++++++++++++++++++++++++++++++ pesto.c | 55 +++++++++++++++++++++++-- 5 files changed, 253 insertions(+), 33 deletions(-) diff --git a/conf.c b/conf.c index f4ab72a..b5576f5 100644 --- a/conf.c +++ b/conf.c @@ -1849,16 +1849,16 @@ void conf(struct ctx *c, int argc, char **argv) if (name == 't') { opt_t = true; - fwd_rule_parse(name, optarg, c->fwd[PIF_HOST]); + fwd_rule_parse(name, false, optarg, c->fwd[PIF_HOST]); } else if (name == 'u') { opt_u = true; - fwd_rule_parse(name, optarg, c->fwd[PIF_HOST]); + fwd_rule_parse(name, false, optarg, c->fwd[PIF_HOST]); } else if (name == 'T') { opt_T = true; - fwd_rule_parse(name, optarg, c->fwd[PIF_SPLICE]); + fwd_rule_parse(name, false, optarg, c->fwd[PIF_SPLICE]); } else if (name == 'U') { opt_U = true; - fwd_rule_parse(name, optarg, c->fwd[PIF_SPLICE]); + fwd_rule_parse(name, false, optarg, c->fwd[PIF_SPLICE]); } } while (name != -1); @@ -1910,13 +1910,13 @@ void conf(struct ctx *c, int argc, char **argv) if (c->mode == MODE_PASTA) { if (!opt_t) - fwd_rule_parse('t', "auto", c->fwd[PIF_HOST]); + fwd_rule_parse('t', false, "auto", c->fwd[PIF_HOST]); if (!opt_T) - fwd_rule_parse('T', "auto", c->fwd[PIF_SPLICE]); + fwd_rule_parse('T', false, "auto", c->fwd[PIF_SPLICE]); if (!opt_u) - fwd_rule_parse('u', "auto", c->fwd[PIF_HOST]); + fwd_rule_parse('u', false, "auto", c->fwd[PIF_HOST]); if (!opt_U) - fwd_rule_parse('U', "auto", c->fwd[PIF_SPLICE]); + fwd_rule_parse('U', false, "auto", c->fwd[PIF_SPLICE]); } conf_sock_listen(c); @@ -2135,14 +2135,8 @@ void conf_handler(struct ctx *c, uint32_t events) unsigned pif; /* Clear pending tables */ - for (pif = 0; pif < PIF_NUM_TYPES; pif++) { - struct fwd_table *fwd = c->fwd_pending[pif]; - - if (!fwd) - continue; - fwd->count = 0; - fwd->sock_count = 0; - } + for (pif = 0; pif < PIF_NUM_TYPES; pif++) + fwd_rule_clear(c->fwd_pending[pif]); /* FIXME: this could block indefinitely if the client doesn't * write as much as it should diff --git a/fwd_rule.c b/fwd_rule.c index 200f4b5..5fc04d7 100644 --- a/fwd_rule.c +++ b/fwd_rule.c @@ -180,6 +180,89 @@ static bool fwd_rule_conflicts(const struct fwd_rule *a, const struct fwd_rule * return true; } +/** + * fwd_rule_match() - Test if two rules exactly match each other + * @a: Rule to check against @b + * @b: Rule to check against @a + * + * Return: true if rules match exactly, false otherwise + */ +static bool fwd_rule_match(const struct fwd_rule *a, const struct fwd_rule *b) +{ + return !memcmp(a, b, sizeof(*a)); +} + +/** + * fwd_rule_clear() - Clear a forwarding table + * @fwd: Table to clear (might be NULL) + */ +void fwd_rule_clear(struct fwd_table *fwd) +{ + if (!fwd) + return; + + /* TODO: check that there are no open sockets in the table before + * going on. See also a related item in fwd_rule_del(). + */ + + fwd->count = 0; + fwd->sock_count = 0; +} + +/** + * fwd_rule_del() - Partially validate and delete a rule from a forwarding table + * @fwd: Table to delete from + * @rule: Rule to delete (must conflict with an existing rule) + * + * Return: 0 on success, negative error code on failure (-ENOENT if not found) + * + * NOTE: This function can't be used for a forwarding table with any open socket + * stored in fwd->rulesocks. + */ +static int fwd_rule_del(struct fwd_table *fwd, const struct fwd_rule *rule) +{ + char rulestr[FWD_RULE_STRLEN], oldstr[FWD_RULE_STRLEN]; + unsigned num, i; + + for (i = 0; i < fwd->count; i++) { + if (fwd_rule_match(rule, &fwd->rules[i])) + break; + + if (fwd_rule_conflicts(rule, &fwd->rules[i])) { + warn( +"Specifier %s conflicts with rule %s, but doesn't match it, can't delete", + fwd_rule_fmt(rule, rulestr, sizeof(rulestr)), + fwd_rule_fmt(&fwd->rules[i], oldstr, sizeof(oldstr))); + return -EINVAL; + } + } + + if (i == fwd->count) { + warn("Couldn't find forwarding rule to delete: %s", + fwd_rule_fmt(rule, rulestr, sizeof(rulestr))); + return -ENOENT; + } + + /* Don't use anything else from 'rule' as passed, it's not validated */ + rule = &fwd->rules[i]; + num = (unsigned)rule->last - rule->first + 1; + + fwd->count--; + + memmove((void *)(fwd->rulesocks + i), (void *)(fwd->rulesocks + i + 1), + (fwd->count - i) * sizeof(*fwd->rulesocks)); + + /* TODO: move sockets stored starting from fwd->rulesocks[i + 1], should + * we ever need to delete rules from a table with open sockets. + */ + fwd->sock_count -= num; + + memmove(fwd->rules + i, fwd->rules + i + 1, + (fwd->count - i) * sizeof(*fwd->rules)); + + return 0; +} + /** * fwd_rule_add() - Validate and add a rule to a forwarding table * @fwd: Table to add to @@ -370,6 +453,7 @@ static int parse_keyword(const char *s, const char **endptr, const char *kw) * fwd_rule_range_except() - Set up forwarding for a range of ports minus a * bitmap of exclusions * @fwd: Forwarding table to be updated + * @del: Delete resulting rules from forwarding table, instead of adding * @proto: Protocol to forward * @addr: Listening address * @ifname: Listening interface @@ -379,8 +463,8 @@ static int parse_keyword(const char *s, const char **endptr, const char *kw) * @to: Port to translate @first to when forwarding * @flags: Flags for forwarding entries */ -static void fwd_rule_range_except(struct fwd_table *fwd, uint8_t proto, - const union inany_addr *addr, +static void fwd_rule_range_except(struct fwd_table *fwd, bool del, + uint8_t proto, const union inany_addr *addr, const char *ifname, uint16_t first, uint16_t last, const uint8_t *exclude, uint16_t to, @@ -420,15 +504,20 @@ static void fwd_rule_range_except(struct fwd_table *fwd, uint8_t proto, rule.last = i - 1; rule.to = base + delta; - if (fwd_rule_add(fwd, &rule) < 0) - goto fail; + if (del) { + if (fwd_rule_del(fwd, &rule) < 0) + goto fail; + } else { + if (fwd_rule_add(fwd, &rule) < 0) + goto fail; + } base = i - 1; } return; fail: - die("Unable to add rule %s", + die("Unable to %s rule %s", del ? "delete" : "add", fwd_rule_fmt(&rule, rulestr, sizeof(rulestr))); } @@ -447,12 +536,13 @@ fail: /** * fwd_rule_parse_ports() - Parse port range(s) specifier * @fwd: Forwarding table to be updated + * @del: Delete resulting rules from forwarding table, instead of adding * @proto: Protocol to forward * @addr: Listening address for forwarding * @ifname: Interface name for listening * @spec: Port range(s) specifier */ -static void fwd_rule_parse_ports(struct fwd_table *fwd, uint8_t proto, +static void fwd_rule_parse_ports(struct fwd_table *fwd, bool del, uint8_t proto, const union inany_addr *addr, const char *ifname, const char *spec) @@ -509,7 +599,7 @@ static void fwd_rule_parse_ports(struct fwd_table *fwd, uint8_t proto, /* Exclude ephemeral ports */ fwd_port_map_ephemeral(exclude); - fwd_rule_range_except(fwd, proto, addr, ifname, + fwd_rule_range_except(fwd, del, proto, addr, ifname, 1, NUM_PORTS - 1, exclude, 1, flags | FWD_WEAK); return; @@ -539,7 +629,7 @@ static void fwd_rule_parse_ports(struct fwd_table *fwd, uint8_t proto, if (p != ep) /* Garbage after the ranges */ goto bad; - fwd_rule_range_except(fwd, proto, addr, ifname, + fwd_rule_range_except(fwd, del, proto, addr, ifname, orig_range.first, orig_range.last, exclude, mapped_range.first, flags); @@ -553,10 +643,12 @@ bad: /** * fwd_rule_parse() - Parse port configuration option * @optname: Short option name, t, T, u, or U + * @del: Delete resulting rules from forwarding table, instead of adding * @optarg: Option argument (port specification) * @fwd: Forwarding table to be updated */ -void fwd_rule_parse(char optname, const char *optarg, struct fwd_table *fwd) +void fwd_rule_parse(char optname, bool del, const char *optarg, + struct fwd_table *fwd) { union inany_addr addr_buf = inany_any6, *addr = &addr_buf; char buf[BUFSIZ], *spec, *ifname = NULL; @@ -634,12 +726,12 @@ void fwd_rule_parse(char optname, const char *optarg, struct fwd_table *fwd) optname, optarg); if (fwd->caps & FWD_CAP_IPV4) { - fwd_rule_parse_ports(fwd, proto, + fwd_rule_parse_ports(fwd, del, proto, &inany_loopback4, NULL, spec); } if (fwd->caps & FWD_CAP_IPV6) { - fwd_rule_parse_ports(fwd, proto, + fwd_rule_parse_ports(fwd, del, proto, &inany_loopback6, NULL, spec); } @@ -655,7 +747,7 @@ void fwd_rule_parse(char optname, const char *optarg, struct fwd_table *fwd) optname, optarg); } - fwd_rule_parse_ports(fwd, proto, addr, ifname, spec); + fwd_rule_parse_ports(fwd, del, proto, addr, ifname, spec); } /** diff --git a/fwd_rule.h b/fwd_rule.h index f43b37d..ae9a3cb 100644 --- a/fwd_rule.h +++ b/fwd_rule.h @@ -100,9 +100,11 @@ void fwd_probe_ephemeral(void); const union inany_addr *fwd_rule_addr(const struct fwd_rule *rule); const char *fwd_rule_fmt(const struct fwd_rule *rule, char *dst, size_t size); -void fwd_rule_parse(char optname, const char *optarg, struct fwd_table *fwd); +void fwd_rule_parse(char optname, bool del, const char *optarg, + struct fwd_table *fwd); int fwd_rule_read(int fd, struct fwd_rule *rule); int fwd_rule_write(int fd, const struct fwd_rule *rule); +void fwd_rule_clear(struct fwd_table *fwd); int fwd_rule_add(struct fwd_table *fwd, const struct fwd_rule *new); /** diff --git a/pesto.1 b/pesto.1 index 1e1c0f3..c13a18e 100644 --- a/pesto.1 +++ b/pesto.1 @@ -35,6 +35,42 @@ Display a help message and exit. .BR \-s ", " \-\-show Show the forwarding configuration before and after changes are applied. +.TP +.BR \-A ", " \-\-add +Add the port forwarding specifiers following this option to the current +forwarding table, rather than replacing it. + +This option can be given multiple times, as it might follow previous deletions +(see \fB--delete\fR below), and implies that all the specifiers following it, +before a further \fB--delete\fR option occurs, will be handled as additions. + +See the section \fBAdding, deleting, clearing rules\fR in the \fBNOTES\fR for +more details. + +.TP +.BR \-D ", " \-\-delete +Delete the port forwarding specifiers following this option from the current +forwarding table, rather than adding them to it. + +This option can be given multiple times, as it might follow previous additions +(see \fB--add\fR above), and implies that all the specifiers following it, +before a further \fB--add\fR option occurs, will be handled as deletions. + +See the section \fBAdding, deleting, clearing rules\fR in the \fBNOTES\fR for +more details. + +.TP +.BR \-C ", " \-\-clear " " \fIpif +Clear the forwarding table associated to a given \fIpif\fR, that is, a +conceptual type of interface in \fBpasst\fR(1) or \fBpasta\fR(1) representing a +specific data path and direction. + +The available \fIpif\fR names can be obtained by querying the current forwarding +configuration, which can be done by calling \fBpesto\fR(1) without options. + +See the section \fBAdding, deleting, clearing rules\fR in the \fBNOTES\fR for +more details. + .TP .BR \-t ", " \-\-tcp-ports " " \fIspec Configure TCP port forwarding to guest or namespace. \fIspec\fR can be one of: @@ -166,6 +202,55 @@ Configure UDP port forwarding from target namespace to init namespace. .BR \-\-version Show version and exit. +.SH NOTES + +.SS Adding, deleting, clearing rules + +The options \fB--add\fR, \fB--delete\fR, and \fB--clear\fR are handled as +sequential commands to manipulate the current forwarding tables. If none of them +is given, forwarding specifiers for a given table are intended as replacement of +the corresponding table. That is: + +.nf + pesto -t 1024 -U 1025 +.fi + +will \fBreplace\fR the current TCP inbound port forwarding table with a single +rule, forwarding port 1024, and will similarly replace the UDP outbound +forwarding table with a single forwarding rule for port 1025. This usage is a +short-hand form for: + +.nf + pesto -C HOST -t 1024 -C SPLICE -U 1025 +.fi + +The options \fB--add\fR and \fB--delete\fR are used to \fBadd new specific +rules or delete existing ones\fR, instead of replacing tables. For example: + +.nf + pesto -A -t 2000 -D -t 3000 -U 5000 +.fi + +will add a forwarding rule for inbound TCP port 2000, and delete inbound TCP +port 3000 as well as outbound UDP port 5000 from the existing set of rules. + +All these options are interpreted as sequential commands and can be arbitrarily +combined. For example: + +.nf + pesto -A -t 2000 -C HOST -A -T 3000 -t 2001 -D -u 5000 +.fi + +will, in order: + +.RS +- add inbound TCP port 2000 +- clear inbound ports, reverting the addition above +- add outbound TCP port 3000 +- add inbound TCP port 2001 +- delete inbound UDP port 5000 +.RE + .SH AUTHORS Stefano Brivio , diff --git a/pesto.c b/pesto.c index 73fdc39..f4d752b 100644 --- a/pesto.c +++ b/pesto.c @@ -55,6 +55,9 @@ static void usage(const char *name, FILE *f, int status) FPRINTF(f, "Usage: %s [OPTION]... PATH\n", name); FPRINTF(f, "\n" + " -A, --add Add following specifiers to forwards\n" + " -D, --delete Delete following specifiers instead\n" + " -C, --clear PIF Clear forwarding table for given PIF\n" " -t, --tcp-ports SPEC TCP inbound port forwarding\n" " can be specified multiple times\n" " SPEC can be:\n" @@ -298,6 +301,9 @@ int main(int argc, char **argv) {"debug", no_argument, NULL, 'd' }, {"help", no_argument, NULL, 'h' }, {"version", no_argument, NULL, 1 }, + {"add", no_argument, NULL, 'A' }, + {"delete", no_argument, NULL, 'D' }, + {"clear", required_argument, NULL, 'C' }, {"tcp-ports", required_argument, NULL, 't' }, {"udp-ports", required_argument, NULL, 'u' }, {"tcp-ns", required_argument, NULL, 'T' }, @@ -305,9 +311,11 @@ int main(int argc, char **argv) {"show", no_argument, NULL, 's' }, { 0 }, }; + enum { MODE_CLEAR, MODE_ADD, MODE_DEL } mode = MODE_CLEAR; + bool inbound_cleared = false, outbound_cleared = false; struct pif_configuration *inbound, *outbound; + const char *optstring = "dhADC:t:u:T:U:s"; struct sockaddr_un a = { AF_UNIX, "" }; - const char *optstring = "dht:u:T:U:s"; struct configuration conf = { 0 }; bool update = false, show = false; struct pesto_hello hello; @@ -339,11 +347,16 @@ int main(int argc, char **argv) case -1: case 0: break; + case 'C': case 't': case 'u': case 'T': case 'U': - /* Parse these options after we've read state from passt/pasta */ + case 'A': + case 'D': + /* Parse these options after we've read state from + * passt/pasta + */ update = true; break; case 's': @@ -436,16 +449,43 @@ int main(int argc, char **argv) optind = 0; do { + struct pif_configuration *pif_to_clear; + optname = getopt_long(argc, argv, optstring, options, NULL); switch (optname) { + case 'A': + mode = MODE_ADD; + break; + case 'D': + mode = MODE_DEL; + break; + case 'C': + if (!(pif_to_clear = pif_conf_by_name(&conf, optarg))) + die("Unsupported pif name %s", optarg); + + fwd_rule_clear(&pif_to_clear->fwd); + + if (!strcmp(optarg, "HOST")) + inbound_cleared = true; + else if (!strcmp(optarg, "SPLICE")) + outbound_cleared = true; + + break; case 't': case 'u': if (!inbound) { die("Can't use -%c, no inbound interface", optname); } - fwd_rule_parse(optname, optarg, &inbound->fwd); + + if (mode == MODE_CLEAR && !inbound_cleared) { + fwd_rule_clear(&inbound->fwd); + inbound_cleared = true; + } + + fwd_rule_parse(optname, mode == MODE_DEL, optarg, + &inbound->fwd); break; case 'T': case 'U': @@ -453,7 +493,14 @@ int main(int argc, char **argv) die("Can't use -%c, no outbound interface", optname); } - fwd_rule_parse(optname, optarg, &outbound->fwd); + + if (mode == MODE_CLEAR && !outbound_cleared) { + fwd_rule_clear(&outbound->fwd); + outbound_cleared = true; + } + + fwd_rule_parse(optname, mode == MODE_DEL, optarg, + &outbound->fwd); break; default: continue; -- 2.43.0

Loosely inspired by passt-repair's policy: pesto needs to be able to run, check networking entries under /proc (for ip_local_port_range), talk to passt and pasta, wherever the control socket is. Signed-off-by: Stefano Brivio --- contrib/selinux/pesto.fc | 11 +++++ contrib/selinux/pesto.te | 95 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 106 insertions(+) create mode 100644 contrib/selinux/pesto.fc create mode 100644 contrib/selinux/pesto.te diff --git a/contrib/selinux/pesto.fc b/contrib/selinux/pesto.fc new file mode 100644 index 0000000..7ec4d87 --- /dev/null +++ b/contrib/selinux/pesto.fc @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0-or-later +# +# PESTO - Programmable Extensible Socket Translation Orchestrator +# front-end for passt(1) and pasta(1) forwarding configuration +# +# contrib/selinux/pesto.fc - SELinux: File Context for pesto +# +# Copyright (c) 2026 Red Hat GmbH +# Author: Stefano Brivio + +/usr/bin/pesto system_u:object_r:pesto_exec_t:s0 diff --git a/contrib/selinux/pesto.te b/contrib/selinux/pesto.te new file mode 100644 index 0000000..991833a --- /dev/null +++ b/contrib/selinux/pesto.te @@ -0,0 +1,95 @@ +# SPDX-License-Identifier: GPL-2.0-or-later +# +# PESTO - Programmable Extensible Socket Translation Orchestrator +# front-end for passt(1) and pasta(1) forwarding configuration +# +# contrib/selinux/pesto.te - SELinux: Type Enforcement for pesto +# +# Copyright (c) 2026 Red Hat GmbH +# Author: Stefano Brivio + +policy_module(pesto, 0.1) + +require { + type unconfined_t; + type passt_t; + type pasta_t; + role unconfined_r; + class process transition; + + class file { read execute execute_no_trans entrypoint open map }; + class capability { dac_override dac_read_search }; + class chr_file { append open getattr read write ioctl }; + + type net_conf_t; + type proc_net_t; + type sysctl_net_t; + + class unix_stream_socket { create connect sendto }; + class sock_file { read write }; + + type console_device_t; + type user_devpts_t; + type user_tmp_t; + type tmp_t; + + # Workaround: pesto needs to needs to access socket files + # that passt, started by libvirt, might create under different + # labels, depending on whether passt is started as root or not. + # + # However, libvirt doesn't maintain its own policy, which makes + # updates particularly complicated. To avoid breakage in the short + # term, deal with that in passt's own policy. + type qemu_var_run_t; + type virt_var_run_t; +} + +type pesto_t; +domain_type(pesto_t); +type pesto_exec_t; +corecmd_executable_file(pesto_exec_t); + +role unconfined_r types pesto_t; + +allow pesto_t pesto_exec_t:file { read execute execute_no_trans entrypoint open map }; +type_transition unconfined_t pesto_exec_t:process pesto_t; +allow unconfined_t pesto_t:process transition; + +allow pesto_t self:capability { dac_override dac_read_search }; + +allow pesto_t proc_net_t:file read; +kernel_search_network_sysctl(pesto_t) +allow pesto_t sysctl_net_t:dir search; +allow pesto_t sysctl_net_t:file { open read }; + +allow pesto_t console_device_t:chr_file { append open getattr read write ioctl }; +allow pesto_t user_devpts_t:chr_file { append open getattr read write ioctl }; + +allow pesto_t unconfined_t:unix_stream_socket { connectto read write }; +allow pesto_t passt_t:unix_stream_socket { connectto read write }; +allow pesto_t pasta_t:unix_stream_socket { connectto read write }; +allow pesto_t user_tmp_t:unix_stream_socket { connectto read write }; + +allow pesto_t user_tmp_t:dir { getattr read search watch }; + +allow pesto_t unconfined_t:sock_file { getattr read write }; +allow pesto_t passt_t:sock_file { getattr read write }; +allow pesto_t pasta_t:sock_file { getattr read write }; +allow pesto_t user_tmp_t:sock_file { getattr read write }; +allow pesto_t tmp_t:sock_file { getattr read write }; + +# Workaround: pesto needs to needs to access socket files +# that passt, started by libvirt, might create under different +# labels, depending on whether passt is started as root or not. +# +# However, libvirt doesn't maintain its own policy, which makes +# updates particularly complicated. To avoid breakage in the short +# term, deal with that in passt's own policy. +allow pesto_t qemu_var_run_t:unix_stream_socket { connectto read write }; +allow pesto_t virt_var_run_t:unix_stream_socket { connectto read write }; + +allow pesto_t qemu_var_run_t:dir { getattr read search watch }; +allow pesto_t virt_var_run_t:dir { getattr read search watch }; + +allow pesto_t qemu_var_run_t:sock_file { getattr read write }; +allow pesto_t virt_var_run_t:sock_file { getattr read write }; -- 2.43.0

Signed-off-by: Stefano Brivio Reviewed-by: Laurent Vivier --- hooks/pre-push | 1 + 1 file changed, 1 insertion(+) diff --git a/hooks/pre-push b/hooks/pre-push index 839b310..3e2d15f 100755 --- a/hooks/pre-push +++ b/hooks/pre-push @@ -57,6 +57,7 @@ make pkgs scp passt passt.avx2 passt.1 qrap qrap.1 "${USER_HOST}:${BIN}" scp pasta pasta.avx2 pasta.1 "${USER_HOST}:${BIN}" scp passt-repair passt-repair.1 "${USER_HOST}:${BIN}" +scp pesto pesto.1 "${USER_HOST}:${BIN}" ssh "${USER_HOST}" "rm -f ${BIN}/*.deb" ssh "${USER_HOST}" "rm -f ${BIN}/*.rpm" -- 2.43.0

Hi, so I was testing these patches and found one small "problem". On 06/05/2026 15:23, Stefano Brivio wrote:

From: David Gibson

Start implementing pesto in earnest. Create a control/configuration socket in passt. Have pesto connect to it and retrieve a server greeting Perform some basic version checking.

Signed-off-by: David Gibson [sbrivio: Avoid potential recursive calling between conf_accept() and conf_close(), reported by clang-tidy] [sbrivio: In conf(), check we're not exceeding sizeof(c->control_path) instead of sizeof(c->socket_path), and, in pesto's main(), print argv[optind] instead of argv[1] to indicate an invalid socket path, both reported by Jon Maloy] [sbrivio: In pesto's main(), drop unnecessary newline from error message, reported by Laurent] [sbrivio: Don't use SOCK_NONBLOCK on accept4(), as that only applies to the *new* file descriptor, which we don't want -- set O_NONBLOCK on the listening file descriptor using fcntl()] [sbrivio: Switch to protocol version 1, and reflect the true magic behind pesto, i.e. basil, into the magic string] [sbrivio: Fix conflicts in the Makefile caused by the fact that I'm not merging a previous series reworking it] Signed-off-by: Stefano Brivio Reviewed-by: Laurent Vivier --- Makefile | 2 +- conf.c | 184 ++++++++++++++++++++++++++++++++++++++++++++++++++- conf.h | 2 + epoll_type.h | 4 ++ passt.1 | 5 ++ passt.c | 8 +++ passt.h | 6 ++ pesto.c | 47 ++++++++++++- pesto.h | 22 ++++++ serialise.c | 3 + 10 files changed, 279 insertions(+), 4 deletions(-)

diff --git a/Makefile b/Makefile index 2639472..b1003d8 100644 --- a/Makefile +++ b/Makefile @@ -45,7 +45,7 @@ PASST_SRCS = arch.c arp.c bitmap.c checksum.c conf.c dhcp.c dhcpv6.c \ vhost_user.c virtio.c vu_common.c QRAP_SRCS = qrap.c PASST_REPAIR_SRCS = passt-repair.c -PESTO_SRCS = pesto.c +PESTO_SRCS = pesto.c serialise.c SRCS = $(PASST_SRCS) $(QRAP_SRCS) $(PASST_REPAIR_SRCS) $(PESTO_SRCS)

MANPAGES = passt.1 pasta.1 pesto.1 qrap.1 passt-repair.1 diff --git a/conf.c b/conf.c index 27aded8..9eed1ec 100644 --- a/conf.c +++ b/conf.c @@ -48,6 +48,10 @@ #include "isolation.h" #include "log.h" #include "vhost_user.h" +#include "epoll_ctl.h" +#include "conf.h" +#include "pesto.h" +#include "serialise.h"

#define NETNS_RUN_DIR "/run/netns"

@@ -541,6 +545,7 @@ static void usage(const char *name, FILE *f, int status) " --runas UID|UID:GID Run as given UID, GID, which can be\n" " numeric, or login and group names\n" " default: drop to user \"nobody\"\n" + " -c, --conf-path PATH Configuration socket path\n" " -h, --help Display this help message and exit\n" " --version Show version and exit\n");

@@ -779,6 +784,9 @@ static void conf_print(const struct ctx *c) char buf[INANY_ADDRSTRLEN]; int i;

+ if (c->fd_control_listen >= 0) + info("Configuration socket: %s", c->control_path); + if (c->ifi4 > 0 || c->ifi6 > 0) { char ifn[IFNAMSIZ];

@@ -1072,6 +1080,19 @@ static void conf_open_files(struct ctx *c) if (c->pidfile_fd < 0) die_perror("Couldn't open PID file %s", c->pidfile); } + + c->fd_control = -1; + if (*c->control_path) { + c->fd_control_listen = sock_unix(c->control_path); + if (c->fd_control_listen < 0) { + die_perror("Couldn't open control socket %s", + c->control_path); + } + if (fcntl(c->fd_control_listen, F_SETFL, O_NONBLOCK)) + die_perror("Couldn't set O_NONBLOCK on control socket"); + } else { + c->fd_control_listen = -1; + } }

/** @@ -1107,6 +1128,25 @@ fail: die("Invalid MAC address: %s", str); }

+/** + * conf_sock_listen() - Start listening for connections on configuration socket + * @c: Execution context + */ +static void conf_sock_listen(const struct ctx *c) +{ + union epoll_ref ref = { .type = EPOLL_TYPE_CONF_LISTEN }; + + if (c->fd_control_listen < 0) + return; + + if (listen(c->fd_control_listen, 0)) + die_perror("Couldn't listen on configuration socket"); + + ref.fd = c->fd_control_listen; + if (epoll_add(c->epollfd, EPOLLIN | EPOLLET, ref)) + die_perror("Couldn't add configuration socket to epoll"); +} + /** * conf() - Process command-line arguments and set configuration * @c: Execution context @@ -1189,9 +1229,10 @@ void conf(struct ctx *c, int argc, char **argv) {"migrate-exit", no_argument, NULL, 29 }, {"migrate-no-linger", no_argument, NULL, 30 }, {"stats", required_argument, NULL, 31 }, + {"conf-path", required_argument, NULL, 'c' }, { 0 }, }; - const char *optstring = "+dqfel:hs:F:I:p:P:m:a:n:M:g:i:o:D:S:H:461t:u:T:U:"; + const char *optstring = "+dqfel:hs:c:F:I:p:P:m:a:n:M:g:i:o:D:S:H:461t:u:T:U:"; const char *logname = (c->mode == MODE_PASTA) ? "pasta" : "passt"; bool opt_t = false, opt_T = false, opt_u = false, opt_U = false; char userns[PATH_MAX] = { 0 }, netns[PATH_MAX] = { 0 }; @@ -1449,6 +1490,13 @@ void conf(struct ctx *c, int argc, char **argv)

c->fd_tap = -1; break; + case 'c': + ret = snprintf(c->control_path, sizeof(c->control_path), + "%s", optarg); + if (ret <= 0 || ret >= (int)sizeof(c->control_path)) + die("Invalid configuration path: %s", optarg); + c->fd_control_listen = c->fd_control = -1; + break; case 'F': errno = 0; fd_tap_opt = strtol(optarg, NULL, 0); @@ -1871,6 +1919,140 @@ void conf(struct ctx *c, int argc, char **argv) fwd_rule_parse('U', "auto", c->fwd[PIF_SPLICE]); }

+ conf_sock_listen(c); + if (!c->quiet) conf_print(c); } + +static void conf_accept(struct ctx *c); + +/** + * conf_close() - Close configuration / control socket and clean up + * @c: Execution context + */ +static void conf_close(struct ctx *c) +{ + debug("Closing configuration socket"); + epoll_ctl(c->epollfd, EPOLL_CTL_DEL, c->fd_control, NULL); + close(c->fd_control); + c->fd_control = -1; +} + +/** + * conf_listen_handler() - Handle events on configuration listening socket + * @c: Execution context + * @events: epoll events + */ +void conf_listen_handler(struct ctx *c, uint32_t events) +{ + if (events != EPOLLIN) { + err("Unexpected event 0x%04x on configuration socket", events); + return; + } + + if (c->fd_control >= 0) { + /* Ignore the new connection for now, blocking it until the + * current one finishes. + */ + return; + } + + conf_accept(c); +} + +/** + * conf_accept() - Accept a new control connection + * @c: Execution context + */ +static void conf_accept(struct ctx *c) +{ + struct pesto_hello hello = { + .magic = PESTO_SERVER_MAGIC, + .version = htonl(PESTO_PROTOCOL_VERSION), + }; + union epoll_ref ref = { .type = EPOLL_TYPE_CONF }; + struct ucred uc = { 0 }; + socklen_t len = sizeof(uc); + int fd, rc; + +retry: + err("%s: %i", __func__, __LINE__); + fd = accept4(c->fd_control_listen, NULL, NULL, SOCK_CLOEXEC); + if (fd < 0) { + err("%s: %i", __func__, __LINE__); + if (errno != EAGAIN) + warn_perror("accept4() on configuration listening socket"); + return; + } + + err("%s: %i", __func__, __LINE__); I assume the three err() calls are debug leftovers? I was wondering why my journal was getting spammed with "conf_accept: XXX". + + if (getsockopt(fd, SOL_SOCKET, SO_PEERCRED, &uc, &len) < 0) + warn_perror("Can't get configuration client credentials"); + + c->fd_control = ref.fd = fd; + rc = epoll_add(c->epollfd, EPOLLIN | EPOLLET, ref); + if (rc < 0) { + warn_perror("epoll_ctl() on configuration socket"); + goto fail; + } + + rc = write_all_buf(fd, &hello, sizeof(hello)); + if (rc < 0) { + warn_perror("Error writing configuration protocol hello"); + goto fail; + } + + info("Accepted configuration client, PID %i", uc.pid); + if (!PESTO_PROTOCOL_VERSION) { + warn( +"Warning: Using experimental unsupported configuration protocol"); + } + + return; + +fail: + conf_close(c); + goto retry; +} + +/** + * conf_handler() - Handle events on configuration socket + * @c: Execution context + * @events: epoll events + */ +void conf_handler(struct ctx *c, uint32_t events) +{ + if (events & EPOLLIN) { + char discard[BUFSIZ]; + ssize_t n; + + do { + n = read(c->fd_control, discard, sizeof(discard)); + if (n > 0) + debug("Discarded %zd bytes of config data", n); + } while (n > 0); + if (n == 0) { + debug("Configuration client EOF"); + goto close; + } + if (errno != EAGAIN && errno != EWOULDBLOCK) { + err_perror("Error reading config data"); + goto close; + } + } + + if (events & EPOLLHUP) { + debug("Configuration client hangup"); + goto close; + } + + return; + +close: + conf_close(c); + + /* Check if any other clients are waiting to connect */ + conf_accept(c); +} diff --git a/conf.h b/conf.h index b45ad74..16f9718 100644 --- a/conf.h +++ b/conf.h @@ -8,5 +8,7 @@

enum passt_modes conf_mode(int argc, char *argv[]); void conf(struct ctx *c, int argc, char **argv); +void conf_listen_handler(struct ctx *c, uint32_t events); +void conf_handler(struct ctx *c, uint32_t events);

#endif /* CONF_H */ diff --git a/epoll_type.h b/epoll_type.h index a90ffb6..061325a 100644 --- a/epoll_type.h +++ b/epoll_type.h @@ -46,6 +46,10 @@ enum epoll_type { EPOLL_TYPE_REPAIR, /* Netlink neighbour subscription socket */ EPOLL_TYPE_NL_NEIGH, + /* Configuration listening socket */ + EPOLL_TYPE_CONF_LISTEN, + /* Configuration socket */ + EPOLL_TYPE_CONF,

EPOLL_NUM_TYPES, }; diff --git a/passt.1 b/passt.1 index 6303aeb..908fd4a 100644 --- a/passt.1 +++ b/passt.1 @@ -127,6 +127,11 @@ login name and group name can be passed. This requires privileges (either initial effective UID 0 or CAP_SETUID capability) to work. Default is to change to user \fInobody\fR if started as root.

+.TP +.BR \-c ", " \-\-conf-path " " \fIpath " " (EXPERIMENTAL) +Path for configuration and control socket used by \fBpesto\fR(1) to +dynamically update passt or pasta's configuration. + .TP .BR \-h ", " \-\-help Display a help message and exit. diff --git a/passt.c b/passt.c index f84419c..bc42ea3 100644 --- a/passt.c +++ b/passt.c @@ -80,6 +80,8 @@ char *epoll_type_str[] = { [EPOLL_TYPE_REPAIR_LISTEN] = "TCP_REPAIR helper listening socket", [EPOLL_TYPE_REPAIR] = "TCP_REPAIR helper socket", [EPOLL_TYPE_NL_NEIGH] = "netlink neighbour notifier socket", + [EPOLL_TYPE_CONF_LISTEN] = "configuration listening socket", + [EPOLL_TYPE_CONF] = "configuration socket", }; static_assert(ARRAY_SIZE(epoll_type_str) == EPOLL_NUM_TYPES, "epoll_type_str[] doesn't match enum epoll_type"); @@ -303,6 +305,12 @@ static void passt_worker(void *opaque, int nfds, struct epoll_event *events) case EPOLL_TYPE_NL_NEIGH: nl_neigh_notify_handler(c); break; + case EPOLL_TYPE_CONF_LISTEN: + conf_listen_handler(c, eventmask); + break; + case EPOLL_TYPE_CONF: + conf_handler(c, eventmask); + break; default: /* Can't happen */ assert(0); diff --git a/passt.h b/passt.h index 62b8dcd..b3f049d 100644 --- a/passt.h +++ b/passt.h @@ -158,6 +158,7 @@ struct ip6_ctx { * @foreground: Run in foreground, don't log to stderr by default * @nofile: Maximum number of open files (ulimit -n) * @sock_path: Path for UNIX domain socket + * @control_path: Path for control/configuration UNIX domain socket * @repair_path: TCP_REPAIR helper path, can be "none", empty for default * @pcap: Path for packet capture file * @pidfile: Path to PID file, empty string if not configured @@ -169,6 +170,8 @@ struct ip6_ctx { * @epollfd: File descriptor for epoll instance * @fd_tap_listen: File descriptor for listening AF_UNIX socket, if any * @fd_tap: AF_UNIX socket, tuntap device, or pre-opened socket + * @fd_control_listen: Listening control/configuration socket, if any + * @fd_control: Control/configuration socket, if any * @fd_repair_listen: File descriptor for listening TCP_REPAIR socket, if any * @fd_repair: Connected AF_UNIX socket for TCP_REPAIR helper * @our_tap_mac: Pasta/passt's MAC on the tap link @@ -223,6 +226,7 @@ struct ctx { int foreground; int nofile; char sock_path[UNIX_PATH_MAX]; + char control_path[UNIX_PATH_MAX]; char repair_path[UNIX_PATH_MAX]; char pcap[PATH_MAX];

@@ -240,6 +244,8 @@ struct ctx { int epollfd; int fd_tap_listen; int fd_tap; + int fd_control_listen; + int fd_control; int fd_repair_listen; int fd_repair; unsigned char our_tap_mac[ETH_ALEN]; diff --git a/pesto.c b/pesto.c index f0916e8..ab476c5 100644 --- a/pesto.c +++ b/pesto.c @@ -33,6 +33,7 @@

#include "common.h" #include "seccomp_pesto.h" +#include "serialise.h" #include "pesto.h" #include "log.h"

@@ -66,6 +67,8 @@ static void usage(const char *name, FILE *f, int status) * * Return: 0 on success, won't return on failure * + * #syscalls:pesto socket s390x:socketcall i686:socketcall + * #syscalls:pesto connect shutdown close * #syscalls:pesto exit_group fstat read write */ int main(int argc, char **argv) @@ -76,9 +79,12 @@ int main(int argc, char **argv) {"version", no_argument, NULL, 1 }, { 0 }, }; + struct sockaddr_un a = { AF_UNIX, "" }; const char *optstring = "dh"; + struct pesto_hello hello; struct sock_fprog prog; - int optname; + int optname, ret, s; + uint32_t s_version;

prctl(PR_SET_DUMPABLE, 0);

@@ -122,5 +128,42 @@ int main(int argc, char **argv)

debug("debug_flag=%d, path=\"%s\"", debug_flag, argv[optind]);

- die("pesto is not implemented yet"); + if ((s = socket(AF_UNIX, SOCK_STREAM, 0)) < 0) + die_perror("Failed to create AF_UNIX socket"); + + ret = snprintf(a.sun_path, sizeof(a.sun_path), "%s", argv[optind]); + if (ret <= 0 || ret >= (int)sizeof(a.sun_path)) + die("Invalid socket path \"%s\"", argv[optind]); + + ret = connect(s, (struct sockaddr *)&a, sizeof(a)); + if (ret < 0) { + die_perror("Failed to connect to %s", a.sun_path); + } + + ret = read_all_buf(s, &hello, sizeof(hello)); + if (ret < 0) + die_perror("Couldn't read server greeting"); + + if (memcmp(hello.magic, PESTO_SERVER_MAGIC, sizeof(hello.magic))) + die("Bad magic number from server"); + + s_version = ntohl(hello.version); + + if (s_version > PESTO_PROTOCOL_VERSION) { + die("Unknown server protocol version %"PRIu32" > %"PRIu32, + s_version, PESTO_PROTOCOL_VERSION); + } + + /* cppcheck-suppress knownConditionTrueFalse */ + if (!s_version) { + if (PESTO_PROTOCOL_VERSION) + die("Unsupported experimental server protocol"); + FPRINTF(stderr, +"Warning: Using experimental protocol version, client and server must match\n"); + } + + if (shutdown(s, SHUT_RDWR) < 0 || close(s) < 0) + die_perror("Error shutting down control socket"); + + exit(0); } diff --git a/pesto.h b/pesto.h index e9b329f..3c93d3e 100644 --- a/pesto.h +++ b/pesto.h @@ -9,4 +9,26 @@ #ifndef PESTO_H #define PESTO_H

+#include +#include + +#define PESTO_SERVER_MAGIC "basil:s" + +/* Version 0 is reserved for unreleased / unsupported experimental versions */ +#define PESTO_PROTOCOL_VERSION 1 + +/** + * struct pesto_hello - Server introduction message + * @magic: PESTO_SERVER_MAGIC + * @version: Version number + */ +struct pesto_hello { + char magic[8]; + uint32_t version; +} __attribute__ ((__packed__)); + +static_assert(sizeof(PESTO_SERVER_MAGIC) + == sizeof(((struct pesto_hello *)0)->magic), + "PESTO_SERVER_MAGIC has wrong size"); + #endif /* PESTO_H */ diff --git a/serialise.c b/serialise.c index 944e741..346df99 100644 --- a/serialise.c +++ b/serialise.c @@ -6,6 +6,9 @@ * PASTA - Pack A Subtle Tap Abstraction * for network namespace/tap device mode * + * PESTO - Programmable Extensible Socket Translation Orchestrator + * front-end for passt(1) and pasta(1) forwarding configuration + * * serialise.c - Serialisation of data structures over bytestreams * * Copyright Red Hat

-- Paul Holzinger