From 22098763a10d9c1340827fcf6edab66f153b27f0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Sep 2026 12:27:00 -0700 Subject: Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Don't destroy user event fields when removal fails User event fields are destroyed before the event is removed from visibility. But that can fail leaving the still visible event with no fields. Move the destroying of the fields to after the event is successfully removed from visibility. - Initialize function graph state is fork before calling copy_exec_state() For non-CLONE_VM forks, copy_exec_state() allocates a new task_exec_state. If that allocation fails, ftrace_graph_exit_task() will free the tasks ret_stack pointer. Since that pointer is still using the parent's ret_stack, it mistakenly frees the parent's pointer too. Call ftrace_graph_init() on the task first which will NULL out the new tasks's ret_stack and if the copy fails, it will not free anything. - Remove FGRAPH_MAX_INDEX The macro FGRAPH_MAX_INDEX was added but never used. Remove it. - Save ent_size in function graph printing of nested functions The function graph tracer needs to look at the next event to see if the next event is the return of the current function entry. If it is, it prints a single line: ktime_get(); Otherwise it prints it like a nested function: tick_nohz_irq_exit() { ktime_get(); kcpustat_irq_exit(); } In order to look at the next event, it must save the current event so that it has the information to print from it. It saves the event in the iterator descriptor called "ent". What it doesn't save is the ent_size of the event which is now used to know if the function graph arguments are to be printed. The peek doesn't save the size so the size used happens to be that of the size of the last event that was seen. Save the entry event size in the iterator descriptor so that the correct size is used. - Fix several errors with freeing data in the histogram code The histogram code had a lot of leaked or or incorrect accounting when failures happen. Correct them. - Fix histogram regression of .percent and .graph modifiers Up until 6.3 histogram values could have "percent" or "graph" modifiers that changed how they were printed. But a change that added restricting histograms values from being strings, stack traces and other modifiers inadvertently prevented them from using the percent and graph modifiers, which were legal use cases for values. Put back the percent and graph modifiers. - Fix various typos in the comments - Set the trace_clock before initializing a histogram with clock argument The histogram API allows the user to specific which trace clock to use via a "clock=" string. The histogram is set up first before the clock is checked. If the passed in clock is not valid, it exits without fully fixing up the histogram leaving it on the list and a use-after-free can trigger. Update the clock argument first and if it fails then exit gracefully before the histogram trigger is placed on any lists. - Restore :mod: trailer after parsing in ftrace_set_clr_event The function ftrace_set_clr_event() modifies the parse string and needs to put it back to what was passed in. It searches for ":mod:" via a strsep() but fails to put back the first ':' in the string. Add back the ':' in the passed in string. - Take trace_array reference when opening a tracer options file The options files are dynamically created and some tracers add their own options. When a tracer adds their own list of options, the trace_array holding them has an array to hold the list of options for each tracer. This array increases in size via a krealloc(), and the new entry gets a newly allocated array to hold the options of the new tracer being added. The element in each entry of the tracer's option array holds a pointer back to the trace_array, a pointer to the tracer it is associated to, a pointer to the flags of the option. The issue is that these arrays are freed when the trace_array is freed when its instance it represents is removed from the instances directory. There's a race that an open of one of these options files can happen when the instance is being removed. Add a new helper function to be called by the open function of the options file to iterate all existing trace_arrays under a lock and find the one that has the given option element in one of it's tracer arrays. If found, then update the associated trace_array's reference counter to keep it from being freed. If not found, have the open call return -ENODEV. - Disable interrupts when acquiring the lock in rb_wake_up_waiters() The function rb_wake_up_waiters() assumes it will be called in interrupt context and does not disable irqs when taking cpu_buffer->reader_lock, which can be called in hard interrupt context. The issue is in PREEMPT_RT, this function is called in thread context leaving this lock open to a deadlock. Take the lock with interrupts disabled. - Use rcu_assign_pointer() for tmp_ops filter hash The tmp_ops used in update_ftrace_direct_mod() assigns its filter_hash field directly, but that field is annotated as __rcu and sparse complains. Assign it with rcu_assign_pointer() - Fix use-after-free in enable_trigger_private_data_free() The trace_event_call is accessed through the event_trigger_data's trace_event_file pointer to put the trace_event_call on freeing. The issue is that the trace_event_file data may have been freed already causing a use-after-free. Add a field to the event_trigger_data that points directly to the trace_event_call so that it can decrement its reference directly without needing to go through the trace_event_file. - Fix accounting of buffer data remote headers trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount the number of pages is needed for the asked for size as it doesn't take into account the meta data on each page. Add a helper function to do the calculation properly and use that in these functions. - Catch nr_page_va overflow in ring_buffer_desc sizing The number of pages per remote ring buffer is capped by ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to overflow that field would silently allocate a descriptor smaller than what was asked for. - Do not resize the subbuf order if any per_cpu buffer is disabled The mmapping of ring buffers disables resizing the subbuffers, but it is done per-cpu whereas the subbuf size change is done for all the per_cpu buffers under the buffer->mutex. It could change the size of some while the mapping is happening on others. Have the resize of the subbuf order check all the per_cpu buffers under the lock to see if any of them is disabled before starting and causing an inconsistency between buffers that are being mapped. * tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits) ring-buffer: Check resize_disabled before publishing the new subbuf order tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing tracing/remotes: Account for ring buffer page header in size calculation tracing: Don't dereference trace_event_file in deferred trigger free ftrace: Use rcu_assign_pointer() for tmp_ops filter hash ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters() tracing: Take trace_array reference when opening a tracer options file tracing: Fix ring_buffer_read_page_size() kernel-doc tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event() tracing: Fix memory corruption from a "STACKTRACE" histogram key tracing: Fix memory corruption from the histogram stacktrace modifier tracing: Undo the registration when enabling the histogram trigger fails tracing: Take the reference before publishing the named histogram trigger tracing: Set the trace clock before registering the histogram trigger tracing: Fix typo "preceeded" in comment tracing: Fix typo "availabe" in comment tracing: Let histogram values keep the percent and graph modifiers tracing: Keep the entry count when the histogram stats allocation fails tracing: Free histogram the field rejected for a bad modifier tracing: Free histogram the var ref when its initialization fails ... --- net/openvswitch/flow.c | 1119 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1119 insertions(+) create mode 100644 net/openvswitch/flow.c (limited to 'net/openvswitch/flow.c') diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c new file mode 100644 index 000000000..868d9fdf3 --- /dev/null +++ b/net/openvswitch/flow.c @@ -0,0 +1,1119 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2007-2014 Nicira, Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "conntrack.h" +#include "datapath.h" +#include "flow.h" +#include "flow_netlink.h" +#include "vport.h" + +u64 ovs_flow_used_time(unsigned long flow_jiffies) +{ + struct timespec64 cur_ts; + u64 cur_ms, idle_ms; + + ktime_get_ts64(&cur_ts); + idle_ms = jiffies_to_msecs(jiffies - flow_jiffies); + cur_ms = (u64)(u32)cur_ts.tv_sec * MSEC_PER_SEC + + cur_ts.tv_nsec / NSEC_PER_MSEC; + + return cur_ms - idle_ms; +} + +#define TCP_FLAGS_BE16(tp) (*(__be16 *)&tcp_flag_word(tp) & htons(0x0FFF)) + +void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, + const struct sk_buff *skb) +{ + struct sw_flow_stats *stats; + unsigned int cpu = smp_processor_id(); + int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); + + stats = rcu_dereference(flow->stats[cpu]); + + /* Check if already have CPU-specific stats. */ + if (likely(stats)) { + spin_lock(&stats->lock); + /* Mark if we write on the pre-allocated stats. */ + if (cpu == 0 && unlikely(flow->stats_last_writer != cpu)) + flow->stats_last_writer = cpu; + } else { + stats = rcu_dereference(flow->stats[0]); /* Pre-allocated. */ + spin_lock(&stats->lock); + + /* If the current CPU is the only writer on the + * pre-allocated stats keep using them. + */ + if (unlikely(flow->stats_last_writer != cpu)) { + /* A previous locker may have already allocated the + * stats, so we need to check again. If CPU-specific + * stats were already allocated, we update the pre- + * allocated stats as we have already locked them. + */ + if (likely(flow->stats_last_writer != -1) && + likely(!rcu_access_pointer(flow->stats[cpu]))) { + /* Try to allocate CPU-specific stats. */ + struct sw_flow_stats *new_stats; + + new_stats = + kmem_cache_alloc_node(flow_stats_cache, + GFP_NOWAIT | + __GFP_THISNODE | + __GFP_NOWARN | + __GFP_NOMEMALLOC, + numa_node_id()); + if (likely(new_stats)) { + new_stats->used = jiffies; + new_stats->packet_count = 1; + new_stats->byte_count = len; + new_stats->tcp_flags = tcp_flags; + spin_lock_init(&new_stats->lock); + + rcu_assign_pointer(flow->stats[cpu], + new_stats); + cpumask_set_cpu(cpu, + flow->cpu_used_mask); + goto unlock; + } + } + flow->stats_last_writer = cpu; + } + } + + stats->used = jiffies; + stats->packet_count++; + stats->byte_count += len; + stats->tcp_flags |= tcp_flags; +unlock: + spin_unlock(&stats->lock); +} + +/* Must be called with rcu_read_lock or ovs_mutex. */ +void ovs_flow_stats_get(const struct sw_flow *flow, + struct ovs_flow_stats *ovs_stats, + unsigned long *used, __be16 *tcp_flags) +{ + unsigned int cpu; + + *used = 0; + *tcp_flags = 0; + memset(ovs_stats, 0, sizeof(*ovs_stats)); + + for_each_cpu(cpu, flow->cpu_used_mask) { + struct sw_flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]); + + if (stats) { + /* Local CPU may write on non-local stats, so we must + * block bottom-halves here. + */ + spin_lock_bh(&stats->lock); + if (!*used || time_after(stats->used, *used)) + *used = stats->used; + *tcp_flags |= stats->tcp_flags; + ovs_stats->n_packets += stats->packet_count; + ovs_stats->n_bytes += stats->byte_count; + spin_unlock_bh(&stats->lock); + } + } +} + +/* Called with ovs_mutex. */ +void ovs_flow_stats_clear(struct sw_flow *flow) +{ + unsigned int cpu; + + for_each_cpu(cpu, flow->cpu_used_mask) { + struct sw_flow_stats *stats = ovsl_dereference(flow->stats[cpu]); + + if (stats) { + spin_lock_bh(&stats->lock); + stats->used = 0; + stats->packet_count = 0; + stats->byte_count = 0; + stats->tcp_flags = 0; + spin_unlock_bh(&stats->lock); + } + } +} + +static int check_header(struct sk_buff *skb, int len) +{ + if (unlikely(skb->len < len)) + return -EINVAL; + if (unlikely(!pskb_may_pull(skb, len))) + return -ENOMEM; + return 0; +} + +static bool arphdr_ok(struct sk_buff *skb) +{ + return pskb_may_pull(skb, skb_network_offset(skb) + + sizeof(struct arp_eth_header)); +} + +static int check_iphdr(struct sk_buff *skb) +{ + unsigned int nh_ofs = skb_network_offset(skb); + unsigned int ip_len; + int err; + + err = check_header(skb, nh_ofs + sizeof(struct iphdr)); + if (unlikely(err)) + return err; + + ip_len = ip_hdrlen(skb); + if (unlikely(ip_len < sizeof(struct iphdr) || + skb->len < nh_ofs + ip_len)) + return -EINVAL; + + skb_set_transport_header(skb, nh_ofs + ip_len); + return 0; +} + +static bool tcphdr_ok(struct sk_buff *skb) +{ + int th_ofs = skb_transport_offset(skb); + int tcp_len; + + if (unlikely(!pskb_may_pull(skb, th_ofs + sizeof(struct tcphdr)))) + return false; + + tcp_len = tcp_hdrlen(skb); + if (unlikely(tcp_len < sizeof(struct tcphdr) || + skb->len < th_ofs + tcp_len)) + return false; + + return true; +} + +static bool udphdr_ok(struct sk_buff *skb) +{ + return pskb_may_pull(skb, skb_transport_offset(skb) + + sizeof(struct udphdr)); +} + +static bool sctphdr_ok(struct sk_buff *skb) +{ + return pskb_may_pull(skb, skb_transport_offset(skb) + + sizeof(struct sctphdr)); +} + +static bool icmphdr_ok(struct sk_buff *skb) +{ + return pskb_may_pull(skb, skb_transport_offset(skb) + + sizeof(struct icmphdr)); +} + +/** + * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags. + * + * @skb: buffer where extension header data starts in packet + * @nh: ipv6 header + * @ext_hdrs: flags are stored here + * + * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header + * is unexpectedly encountered. (Two destination options headers may be + * expected and would not cause this bit to be set.) + * + * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order + * preferred (but not required) by RFC 2460: + * + * When more than one extension header is used in the same packet, it is + * recommended that those headers appear in the following order: + * IPv6 header + * Hop-by-Hop Options header + * Destination Options header + * Routing header + * Fragment header + * Authentication header + * Encapsulating Security Payload header + * Destination Options header + * upper-layer header + */ +static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh, + u16 *ext_hdrs) +{ + u8 next_type = nh->nexthdr; + unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr); + int dest_options_header_count = 0; + + *ext_hdrs = 0; + + while (ipv6_ext_hdr(next_type)) { + struct ipv6_opt_hdr _hdr, *hp; + + switch (next_type) { + case IPPROTO_NONE: + *ext_hdrs |= OFPIEH12_NONEXT; + /* stop parsing */ + return; + + case IPPROTO_ESP: + if (*ext_hdrs & OFPIEH12_ESP) + *ext_hdrs |= OFPIEH12_UNREP; + if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST | + OFPIEH12_ROUTER | OFPIEH12_FRAG | + OFPIEH12_AUTH | OFPIEH12_UNREP)) || + dest_options_header_count >= 2) { + *ext_hdrs |= OFPIEH12_UNSEQ; + } + *ext_hdrs |= OFPIEH12_ESP; + break; + + case IPPROTO_AH: + if (*ext_hdrs & OFPIEH12_AUTH) + *ext_hdrs |= OFPIEH12_UNREP; + if ((*ext_hdrs & + ~(OFPIEH12_HOP | OFPIEH12_DEST | OFPIEH12_ROUTER | + OFPIEH12_FRAG | OFPIEH12_UNREP)) || + dest_options_header_count >= 2) { + *ext_hdrs |= OFPIEH12_UNSEQ; + } + *ext_hdrs |= OFPIEH12_AUTH; + break; + + case IPPROTO_DSTOPTS: + if (dest_options_header_count == 0) { + if (*ext_hdrs & + ~(OFPIEH12_HOP | OFPIEH12_UNREP)) + *ext_hdrs |= OFPIEH12_UNSEQ; + *ext_hdrs |= OFPIEH12_DEST; + } else if (dest_options_header_count == 1) { + if (*ext_hdrs & + ~(OFPIEH12_HOP | OFPIEH12_DEST | + OFPIEH12_ROUTER | OFPIEH12_FRAG | + OFPIEH12_AUTH | OFPIEH12_ESP | + OFPIEH12_UNREP)) { + *ext_hdrs |= OFPIEH12_UNSEQ; + } + } else { + *ext_hdrs |= OFPIEH12_UNREP; + } + dest_options_header_count++; + break; + + case IPPROTO_FRAGMENT: + if (*ext_hdrs & OFPIEH12_FRAG) + *ext_hdrs |= OFPIEH12_UNREP; + if ((*ext_hdrs & ~(OFPIEH12_HOP | + OFPIEH12_DEST | + OFPIEH12_ROUTER | + OFPIEH12_UNREP)) || + dest_options_header_count >= 2) { + *ext_hdrs |= OFPIEH12_UNSEQ; + } + *ext_hdrs |= OFPIEH12_FRAG; + break; + + case IPPROTO_ROUTING: + if (*ext_hdrs & OFPIEH12_ROUTER) + *ext_hdrs |= OFPIEH12_UNREP; + if ((*ext_hdrs & ~(OFPIEH12_HOP | + OFPIEH12_DEST | + OFPIEH12_UNREP)) || + dest_options_header_count >= 2) { + *ext_hdrs |= OFPIEH12_UNSEQ; + } + *ext_hdrs |= OFPIEH12_ROUTER; + break; + + case IPPROTO_HOPOPTS: + if (*ext_hdrs & OFPIEH12_HOP) + *ext_hdrs |= OFPIEH12_UNREP; + /* OFPIEH12_HOP is set to 1 if a hop-by-hop IPv6 + * extension header is present as the first + * extension header in the packet. + */ + if (*ext_hdrs == 0) + *ext_hdrs |= OFPIEH12_HOP; + else + *ext_hdrs |= OFPIEH12_UNSEQ; + break; + + default: + return; + } + + hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); + if (!hp) + break; + next_type = hp->nexthdr; + start += ipv6_optlen(hp); + } +} + +static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) +{ + unsigned short frag_off; + unsigned int payload_ofs = 0; + unsigned int nh_ofs = skb_network_offset(skb); + unsigned int nh_len; + struct ipv6hdr *nh; + int err, nexthdr, flags = 0; + + err = check_header(skb, nh_ofs + sizeof(*nh)); + if (unlikely(err)) + return err; + + nh = ipv6_hdr(skb); + + get_ipv6_ext_hdrs(skb, nh, &key->ipv6.exthdrs); + + key->ip.proto = NEXTHDR_NONE; + key->ip.tos = ipv6_get_dsfield(nh); + key->ip.ttl = nh->hop_limit; + key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL); + key->ipv6.addr.src = nh->saddr; + key->ipv6.addr.dst = nh->daddr; + + nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags); + if (flags & IP6_FH_F_FRAG) { + if (frag_off) { + key->ip.frag = OVS_FRAG_TYPE_LATER; + key->ip.proto = NEXTHDR_FRAGMENT; + return 0; + } + key->ip.frag = OVS_FRAG_TYPE_FIRST; + } else { + key->ip.frag = OVS_FRAG_TYPE_NONE; + } + + /* Delayed handling of error in ipv6_find_hdr() as it + * always sets flags and frag_off to a valid value which may be + * used to set key->ip.frag above. + */ + if (unlikely(nexthdr < 0)) + return -EPROTO; + + nh_len = payload_ofs - nh_ofs; + skb_set_transport_header(skb, nh_ofs + nh_len); + key->ip.proto = nexthdr; + return nh_len; +} + +static bool icmp6hdr_ok(struct sk_buff *skb) +{ + return pskb_may_pull(skb, skb_transport_offset(skb) + + sizeof(struct icmp6hdr)); +} + +/** + * parse_vlan_tag - Parse vlan tag from vlan header. + * @skb: skb containing frame to parse + * @key_vh: pointer to parsed vlan tag + * @untag_vlan: should the vlan header be removed from the frame + * + * Return: ERROR on memory error. + * %0 if it encounters a non-vlan or incomplete packet. + * %1 after successfully parsing vlan tag. + */ +static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh, + bool untag_vlan) +{ + struct vlan_head *vh = (struct vlan_head *)skb->data; + + if (likely(!eth_type_vlan(vh->tpid))) + return 0; + + if (unlikely(skb->len < sizeof(struct vlan_head) + sizeof(__be16))) + return 0; + + if (unlikely(!pskb_may_pull(skb, sizeof(struct vlan_head) + + sizeof(__be16)))) + return -ENOMEM; + + vh = (struct vlan_head *)skb->data; + key_vh->tci = vh->tci | htons(VLAN_CFI_MASK); + key_vh->tpid = vh->tpid; + + if (unlikely(untag_vlan)) { + int offset = skb->data - skb_mac_header(skb); + u16 tci; + int err; + + __skb_push(skb, offset); + err = __skb_vlan_pop(skb, &tci); + __skb_pull(skb, offset); + if (err) + return err; + __vlan_hwaccel_put_tag(skb, key_vh->tpid, tci); + } else { + __skb_pull(skb, sizeof(struct vlan_head)); + } + return 1; +} + +static void clear_vlan(struct sw_flow_key *key) +{ + key->eth.vlan.tci = 0; + key->eth.vlan.tpid = 0; + key->eth.cvlan.tci = 0; + key->eth.cvlan.tpid = 0; +} + +static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key) +{ + int res; + + if (skb_vlan_tag_present(skb)) { + key->eth.vlan.tci = htons(skb->vlan_tci) | htons(VLAN_CFI_MASK); + key->eth.vlan.tpid = skb->vlan_proto; + } else { + /* Parse outer vlan tag in the non-accelerated case. */ + res = parse_vlan_tag(skb, &key->eth.vlan, true); + if (res <= 0) + return res; + } + + /* Parse inner vlan tag. */ + res = parse_vlan_tag(skb, &key->eth.cvlan, false); + if (res <= 0) + return res; + + return 0; +} + +static __be16 parse_ethertype(struct sk_buff *skb) +{ + struct llc_snap_hdr { + u8 dsap; /* Always 0xAA */ + u8 ssap; /* Always 0xAA */ + u8 ctrl; + u8 oui[3]; + __be16 ethertype; + }; + struct llc_snap_hdr *llc; + __be16 proto; + + proto = *(__be16 *) skb->data; + __skb_pull(skb, sizeof(__be16)); + + if (eth_proto_is_802_3(proto)) + return proto; + + if (skb->len < sizeof(struct llc_snap_hdr)) + return htons(ETH_P_802_2); + + if (unlikely(!pskb_may_pull(skb, sizeof(struct llc_snap_hdr)))) + return htons(0); + + llc = (struct llc_snap_hdr *) skb->data; + if (llc->dsap != LLC_SAP_SNAP || + llc->ssap != LLC_SAP_SNAP || + (llc->oui[0] | llc->oui[1] | llc->oui[2]) != 0) + return htons(ETH_P_802_2); + + __skb_pull(skb, sizeof(struct llc_snap_hdr)); + + if (eth_proto_is_802_3(llc->ethertype)) + return llc->ethertype; + + return htons(ETH_P_802_2); +} + +static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key, + int nh_len) +{ + struct icmp6hdr *icmp = icmp6_hdr(skb); + + /* The ICMPv6 type and code fields use the 16-bit transport port + * fields, so we need to store them in 16-bit network byte order. + */ + key->tp.src = htons(icmp->icmp6_type); + key->tp.dst = htons(icmp->icmp6_code); + + if (icmp->icmp6_code == 0 && + (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION || + icmp->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT)) { + int icmp_len = skb->len - skb_transport_offset(skb); + struct nd_msg *nd; + int offset; + + memset(&key->ipv6.nd, 0, sizeof(key->ipv6.nd)); + + /* In order to process neighbor discovery options, we need the + * entire packet. + */ + if (unlikely(icmp_len < sizeof(*nd))) + return 0; + + if (unlikely(skb_linearize(skb))) + return -ENOMEM; + + nd = (struct nd_msg *)skb_transport_header(skb); + key->ipv6.nd.target = nd->target; + + icmp_len -= sizeof(*nd); + offset = 0; + while (icmp_len >= 8) { + struct nd_opt_hdr *nd_opt = + (struct nd_opt_hdr *)(nd->opt + offset); + int opt_len = nd_opt->nd_opt_len * 8; + + if (unlikely(!opt_len || opt_len > icmp_len)) + return 0; + + /* Store the link layer address if the appropriate + * option is provided. It is considered an error if + * the same link layer option is specified twice. + */ + if (nd_opt->nd_opt_type == ND_OPT_SOURCE_LL_ADDR + && opt_len == 8) { + if (unlikely(!is_zero_ether_addr(key->ipv6.nd.sll))) + goto invalid; + ether_addr_copy(key->ipv6.nd.sll, + &nd->opt[offset+sizeof(*nd_opt)]); + } else if (nd_opt->nd_opt_type == ND_OPT_TARGET_LL_ADDR + && opt_len == 8) { + if (unlikely(!is_zero_ether_addr(key->ipv6.nd.tll))) + goto invalid; + ether_addr_copy(key->ipv6.nd.tll, + &nd->opt[offset+sizeof(*nd_opt)]); + } + + icmp_len -= opt_len; + offset += opt_len; + } + } + + return 0; + +invalid: + memset(&key->ipv6.nd.target, 0, sizeof(key->ipv6.nd.target)); + memset(key->ipv6.nd.sll, 0, sizeof(key->ipv6.nd.sll)); + memset(key->ipv6.nd.tll, 0, sizeof(key->ipv6.nd.tll)); + + return 0; +} + +static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key) +{ + struct nshhdr *nh; + unsigned int nh_ofs = skb_network_offset(skb); + u8 version, length; + int err; + + err = check_header(skb, nh_ofs + NSH_BASE_HDR_LEN); + if (unlikely(err)) + return err; + + nh = nsh_hdr(skb); + version = nsh_get_ver(nh); + length = nsh_hdr_len(nh); + + if (version != 0) + return -EINVAL; + + err = check_header(skb, nh_ofs + length); + if (unlikely(err)) + return err; + + nh = nsh_hdr(skb); + key->nsh.base.flags = nsh_get_flags(nh); + key->nsh.base.ttl = nsh_get_ttl(nh); + key->nsh.base.mdtype = nh->mdtype; + key->nsh.base.np = nh->np; + key->nsh.base.path_hdr = nh->path_hdr; + switch (key->nsh.base.mdtype) { + case NSH_M_TYPE1: + if (length != NSH_M_TYPE1_LEN) + return -EINVAL; + memcpy(key->nsh.context, nh->md1.context, + sizeof(nh->md1)); + break; + case NSH_M_TYPE2: + memset(key->nsh.context, 0, + sizeof(nh->md1)); + break; + default: + return -EINVAL; + } + + return 0; +} + +/** + * key_extract_l3l4 - extracts L3/L4 header information. + * @skb: sk_buff that contains the frame, with skb->data pointing to the + * L3 header + * @key: output flow key + * + * Return: %0 if successful, otherwise a negative errno value. + */ +static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) +{ + int error; + + /* Network layer. */ + if (key->eth.type == htons(ETH_P_IP)) { + struct iphdr *nh; + __be16 offset; + + error = check_iphdr(skb); + if (unlikely(error)) { + memset(&key->ip, 0, sizeof(key->ip)); + memset(&key->ipv4, 0, sizeof(key->ipv4)); + if (error == -EINVAL) { + skb->transport_header = skb->network_header; + error = 0; + } + return error; + } + + nh = ip_hdr(skb); + key->ipv4.addr.src = nh->saddr; + key->ipv4.addr.dst = nh->daddr; + + key->ip.proto = nh->protocol; + key->ip.tos = nh->tos; + key->ip.ttl = nh->ttl; + + offset = nh->frag_off & htons(IP_OFFSET); + if (offset) { + key->ip.frag = OVS_FRAG_TYPE_LATER; + memset(&key->tp, 0, sizeof(key->tp)); + return 0; + } + if (nh->frag_off & htons(IP_MF) || + skb_shinfo(skb)->gso_type & SKB_GSO_UDP) + key->ip.frag = OVS_FRAG_TYPE_FIRST; + else + key->ip.frag = OVS_FRAG_TYPE_NONE; + + /* Transport layer. */ + if (key->ip.proto == IPPROTO_TCP) { + if (tcphdr_ok(skb)) { + struct tcphdr *tcp = tcp_hdr(skb); + key->tp.src = tcp->source; + key->tp.dst = tcp->dest; + key->tp.flags = TCP_FLAGS_BE16(tcp); + } else { + memset(&key->tp, 0, sizeof(key->tp)); + } + + } else if (key->ip.proto == IPPROTO_UDP) { + if (udphdr_ok(skb)) { + struct udphdr *udp = udp_hdr(skb); + key->tp.src = udp->source; + key->tp.dst = udp->dest; + } else { + memset(&key->tp, 0, sizeof(key->tp)); + } + } else if (key->ip.proto == IPPROTO_SCTP) { + if (sctphdr_ok(skb)) { + struct sctphdr *sctp = sctp_hdr(skb); + key->tp.src = sctp->source; + key->tp.dst = sctp->dest; + } else { + memset(&key->tp, 0, sizeof(key->tp)); + } + } else if (key->ip.proto == IPPROTO_ICMP) { + if (icmphdr_ok(skb)) { + struct icmphdr *icmp = icmp_hdr(skb); + /* The ICMP type and code fields use the 16-bit + * transport port fields, so we need to store + * them in 16-bit network byte order. */ + key->tp.src = htons(icmp->type); + key->tp.dst = htons(icmp->code); + } else { + memset(&key->tp, 0, sizeof(key->tp)); + } + } + + } else if (key->eth.type == htons(ETH_P_ARP) || + key->eth.type == htons(ETH_P_RARP)) { + struct arp_eth_header *arp; + bool arp_available = arphdr_ok(skb); + + arp = (struct arp_eth_header *)skb_network_header(skb); + + if (arp_available && + arp->ar_hrd == htons(ARPHRD_ETHER) && + arp->ar_pro == htons(ETH_P_IP) && + arp->ar_hln == ETH_ALEN && + arp->ar_pln == 4) { + + /* We only match on the lower 8 bits of the opcode. */ + if (ntohs(arp->ar_op) <= 0xff) + key->ip.proto = ntohs(arp->ar_op); + else + key->ip.proto = 0; + + memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src)); + memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst)); + ether_addr_copy(key->ipv4.arp.sha, arp->ar_sha); + ether_addr_copy(key->ipv4.arp.tha, arp->ar_tha); + } else { + memset(&key->ip, 0, sizeof(key->ip)); + memset(&key->ipv4, 0, sizeof(key->ipv4)); + } + } else if (eth_p_mpls(key->eth.type)) { + size_t label_count = 1; + + memset(&key->mpls, 0, sizeof(key->mpls)); + skb_set_inner_network_header(skb, skb->mac_len); + while (1) { + __be32 lse; + + error = check_header(skb, skb->mac_len + + label_count * MPLS_HLEN); + if (unlikely(error)) + return 0; + + memcpy(&lse, skb_inner_network_header(skb), MPLS_HLEN); + + if (label_count <= MPLS_LABEL_DEPTH) + memcpy(&key->mpls.lse[label_count - 1], &lse, + MPLS_HLEN); + + skb_set_inner_network_header(skb, skb->mac_len + + label_count * MPLS_HLEN); + if (lse & htonl(MPLS_LS_S_MASK)) + break; + + label_count++; + } + if (label_count > MPLS_LABEL_DEPTH) + label_count = MPLS_LABEL_DEPTH; + + key->mpls.num_labels_mask = GENMASK(label_count - 1, 0); + } else if (key->eth.type == htons(ETH_P_IPV6)) { + int nh_len; /* IPv6 Header + Extensions */ + + nh_len = parse_ipv6hdr(skb, key); + if (unlikely(nh_len < 0)) { + switch (nh_len) { + case -EINVAL: + memset(&key->ip, 0, sizeof(key->ip)); + memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr)); + fallthrough; + case -EPROTO: + skb->transport_header = skb->network_header; + error = 0; + break; + default: + error = nh_len; + } + return error; + } + + if (key->ip.frag == OVS_FRAG_TYPE_LATER) { + memset(&key->tp, 0, sizeof(key->tp)); + return 0; + } + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP) + key->ip.frag = OVS_FRAG_TYPE_FIRST; + + /* Transport layer. */ + if (key->ip.proto == NEXTHDR_TCP) { + if (tcphdr_ok(skb)) { + struct tcphdr *tcp = tcp_hdr(skb); + key->tp.src = tcp->source; + key->tp.dst = tcp->dest; + key->tp.flags = TCP_FLAGS_BE16(tcp); + } else { + memset(&key->tp, 0, sizeof(key->tp)); + } + } else if (key->ip.proto == NEXTHDR_UDP) { + if (udphdr_ok(skb)) { + struct udphdr *udp = udp_hdr(skb); + key->tp.src = udp->source; + key->tp.dst = udp->dest; + } else { + memset(&key->tp, 0, sizeof(key->tp)); + } + } else if (key->ip.proto == NEXTHDR_SCTP) { + if (sctphdr_ok(skb)) { + struct sctphdr *sctp = sctp_hdr(skb); + key->tp.src = sctp->source; + key->tp.dst = sctp->dest; + } else { + memset(&key->tp, 0, sizeof(key->tp)); + } + } else if (key->ip.proto == NEXTHDR_ICMP) { + if (icmp6hdr_ok(skb)) { + error = parse_icmpv6(skb, key, nh_len); + if (error) + return error; + } else { + memset(&key->tp, 0, sizeof(key->tp)); + } + } + } else if (key->eth.type == htons(ETH_P_NSH)) { + error = parse_nsh(skb, key); + if (error) + return error; + } + return 0; +} + +/** + * key_extract - extracts a flow key from an Ethernet frame. + * @skb: sk_buff that contains the frame, with skb->data pointing to the + * Ethernet header + * @key: output flow key + * + * Initializes @skb header fields as follows: + * + * - skb->mac_header: the L2 header. + * + * - skb->network_header: just past the L2 header, or just past the + * VLAN header, to the first byte of the L2 payload. + * + * - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6 + * on output, then just past the IP header, if one is present and + * of a correct length, otherwise the same as skb->network_header. + * For other key->eth.type values it is left untouched. + * + * - skb->protocol: the type of the data starting at skb->network_header. + * Equals to key->eth.type. + * + * Return: %0 if successful, otherwise a negative errno value. + */ +static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) +{ + /* Flags are always used as part of stats */ + key->tp.flags = 0; + + skb_reset_mac_header(skb); + + /* Link layer. */ + clear_vlan(key); + if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) { + if (unlikely(eth_type_vlan(skb->protocol))) + return -EINVAL; + + skb_reset_network_header(skb); + key->eth.type = skb->protocol; + } else { + struct ethhdr *eth; + int err; + + err = check_header(skb, ETH_HLEN); + if (unlikely(err)) + return err; + + eth = eth_hdr(skb); + ether_addr_copy(key->eth.src, eth->h_source); + ether_addr_copy(key->eth.dst, eth->h_dest); + + __skb_pull(skb, 2 * ETH_ALEN); + /* We are going to push all headers that we pull, so no need to + * update skb->csum here. + */ + + if (unlikely(parse_vlan(skb, key))) + return -ENOMEM; + + key->eth.type = parse_ethertype(skb); + if (unlikely(key->eth.type == htons(0))) + return -ENOMEM; + + /* Multiple tagged packets need to retain TPID to satisfy + * skb_vlan_pop(), which will later shift the ethertype into + * skb->protocol. + */ + if (key->eth.cvlan.tci & htons(VLAN_CFI_MASK)) + skb->protocol = key->eth.cvlan.tpid; + else + skb->protocol = key->eth.type; + + skb_reset_network_header(skb); + __skb_push(skb, skb->data - skb_mac_header(skb)); + } + + skb_reset_mac_len(skb); + + /* Fill out L3/L4 key info, if any */ + return key_extract_l3l4(skb, key); +} + +/* In the case of conntrack fragment handling it expects L3 headers, + * add a helper. + */ +int ovs_flow_key_update_l3l4(struct sk_buff *skb, struct sw_flow_key *key) +{ + return key_extract_l3l4(skb, key); +} + +int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key) +{ + int res; + + res = key_extract(skb, key); + if (!res) + key->mac_proto &= ~SW_FLOW_KEY_INVALID; + + return res; +} + +static int key_extract_mac_proto(struct sk_buff *skb) +{ + switch (skb->dev->type) { + case ARPHRD_ETHER: + return MAC_PROTO_ETHERNET; + case ARPHRD_NONE: + if (skb->protocol == htons(ETH_P_TEB)) + return MAC_PROTO_ETHERNET; + return MAC_PROTO_NONE; + } + WARN_ON_ONCE(1); + return -EINVAL; +} + +int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, + struct sk_buff *skb, struct sw_flow_key *key) +{ +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + struct tc_skb_ext *tc_ext; +#endif + bool post_ct = false, post_ct_snat = false, post_ct_dnat = false; + int res, err; + u16 zone = 0; + + /* Extract metadata from packet. */ + if (tun_info) { + key->tun_proto = ip_tunnel_info_af(tun_info); + memcpy(&key->tun_key, &tun_info->key, sizeof(key->tun_key)); + + if (tun_info->options_len) { + BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) * + 8)) - 1 + > sizeof(key->tun_opts)); + + ip_tunnel_info_opts_get(TUN_METADATA_OPTS(key, tun_info->options_len), + tun_info); + key->tun_opts_len = tun_info->options_len; + } else { + key->tun_opts_len = 0; + } + } else { + key->tun_proto = 0; + key->tun_opts_len = 0; + memset(&key->tun_key, 0, sizeof(key->tun_key)); + } + + key->phy.priority = skb->priority; + key->phy.in_port = OVS_CB(skb)->input_vport->port_no; + key->phy.skb_mark = skb->mark; + key->ovs_flow_hash = 0; + res = key_extract_mac_proto(skb); + if (res < 0) + return res; + key->mac_proto = res; + +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + if (tc_skb_ext_tc_enabled()) { + tc_ext = skb_ext_find(skb, TC_SKB_EXT); + key->recirc_id = tc_ext && !tc_ext->act_miss ? + tc_ext->chain : 0; + OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0; + post_ct = tc_ext ? tc_ext->post_ct : false; + post_ct_snat = post_ct ? tc_ext->post_ct_snat : false; + post_ct_dnat = post_ct ? tc_ext->post_ct_dnat : false; + zone = post_ct ? tc_ext->zone : 0; + } else { + key->recirc_id = 0; + } +#else + key->recirc_id = 0; +#endif + + err = key_extract(skb, key); + if (!err) { + ovs_ct_fill_key(skb, key, post_ct); /* Must be after key_extract(). */ + if (post_ct) { + if (!skb_get_nfct(skb)) { + key->ct_zone = zone; + } else { + if (!post_ct_dnat) + key->ct_state &= ~OVS_CS_F_DST_NAT; + if (!post_ct_snat) + key->ct_state &= ~OVS_CS_F_SRC_NAT; + } + } + } + return err; +} + +int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr, + struct sk_buff *skb, + struct sw_flow_key *key, bool log) +{ + const struct nlattr *a[OVS_KEY_ATTR_MAX + 1]; + u64 attrs = 0; + int err; + + err = parse_flow_nlattrs(attr, a, &attrs, log); + if (err) + return -EINVAL; + + /* Extract metadata from netlink attributes. */ + err = ovs_nla_get_flow_metadata(net, a, attrs, key, log); + if (err) + return err; + + /* key_extract assumes that skb->protocol is set-up for + * layer 3 packets which is the case for other callers, + * in particular packets received from the network stack. + * Here the correct value can be set from the metadata + * extracted above. + * For L2 packet key eth type would be zero. skb protocol + * would be set to correct value later during key-extact. + */ + + skb->protocol = key->eth.type; + err = key_extract(skb, key); + if (err) + return err; + + /* Check that we have conntrack original direction tuple metadata only + * for packets for which it makes sense. Otherwise the key may be + * corrupted due to overlapping key fields. + */ + if (attrs & (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4) && + key->eth.type != htons(ETH_P_IP)) + return -EINVAL; + if (attrs & (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6) && + (key->eth.type != htons(ETH_P_IPV6) || + sw_flow_key_is_nd(key))) + return -EINVAL; + + return 0; +} -- cgit v1.3.1