diff options
author | Jakub Kicinski <kuba@kernel.org> | 2024-11-16 01:09:20 +0300 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2024-11-16 01:09:21 +0300 |
commit | 26a3beee2435cd712f7bc94664ec0550fb2da24d (patch) | |
tree | 3898675ad8edcefdd5d8c3ba2881d796538d40f9 | |
parent | dfc14664794a4706e0c2186a0c082386e6b14c4d (diff) | |
parent | b0ccf4f53d968e794a4ea579d5135cc1aaf1a53f (diff) | |
download | linux-26a3beee2435cd712f7bc94664ec0550fb2da24d.tar.xz |
Merge tag 'nf-next-24-11-15' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next
Pablo Neira Ayuso says:
====================
Netfilter updates for net-next
The following patchset contains Netfilter updates for net-next:
1) Extended netlink error reporting if nfnetlink attribute parser fails,
from Donald Hunter.
2) Incorrect request_module() module, from Simon Horman.
3) A series of patches to reduce memory consumption for set element
transactions.
Florian Westphal says:
"When doing a flush on a set or mass adding/removing elements from a
set, each element needs to allocate 96 bytes to hold the transactional
state.
In such cases, virtually all the information in struct nft_trans_elem
is the same.
Change nft_trans_elem to a flex-array, i.e. a single nft_trans_elem
can hold multiple set element pointers.
The number of elements that can be stored in one nft_trans_elem is limited
by the slab allocator, this series limits the compaction to at most 62
elements as it caps the reallocation to 2048 bytes of memory."
4) A series of patches to prepare the transition to dscp_t in .flowi_tos.
From Guillaume Nault.
5) Support for bitwise operations with two source registers,
from Jeremy Sowden.
* tag 'nf-next-24-11-15' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next:
netfilter: bitwise: add support for doing AND, OR and XOR directly
netfilter: bitwise: rename some boolean operation functions
netfilter: nf_dup4: Convert nf_dup_ipv4_route() to dscp_t.
netfilter: nft_fib: Convert nft_fib4_eval() to dscp_t.
netfilter: rpfilter: Convert rpfilter_mt() to dscp_t.
netfilter: flow_offload: Convert nft_flow_route() to dscp_t.
netfilter: ipv4: Convert ip_route_me_harder() to dscp_t.
netfilter: nf_tables: allocate element update information dynamically
netfilter: nf_tables: switch trans_elem to real flex array
netfilter: nf_tables: prepare nft audit for set element compaction
netfilter: nf_tables: prepare for multiple elements in nft_trans_elem structure
netfilter: nf_tables: add nft_trans_commit_list_add_elem helper
netfilter: bpf: Pass string literal as format argument of request_module()
netfilter: nfnetlink: Report extack policy errors for batched ops
====================
Link: https://patch.msgid.link/20241115133207.8907-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-rw-r--r-- | include/net/netfilter/nf_tables.h | 25 | ||||
-rw-r--r-- | include/uapi/linux/netfilter/nf_tables.h | 18 | ||||
-rw-r--r-- | net/ipv4/netfilter.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_rpfilter.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_dup_ipv4.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/nft_fib_ipv4.c | 3 | ||||
-rw-r--r-- | net/netfilter/nf_bpf_link.c | 2 | ||||
-rw-r--r-- | net/netfilter/nf_tables_api.c | 385 | ||||
-rw-r--r-- | net/netfilter/nfnetlink.c | 2 | ||||
-rw-r--r-- | net/netfilter/nft_bitwise.c | 166 | ||||
-rw-r--r-- | net/netfilter/nft_flow_offload.c | 4 |
11 files changed, 484 insertions, 127 deletions
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f24278767bfd..80a537ac26cd 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1759,28 +1759,29 @@ enum nft_trans_elem_flags { NFT_TRANS_UPD_EXPIRATION = (1 << 1), }; +struct nft_elem_update { + u64 timeout; + u64 expiration; + u8 flags; +}; + +struct nft_trans_one_elem { + struct nft_elem_priv *priv; + struct nft_elem_update *update; +}; + struct nft_trans_elem { struct nft_trans nft_trans; struct nft_set *set; - struct nft_elem_priv *elem_priv; - u64 timeout; - u64 expiration; - u8 update_flags; bool bound; + unsigned int nelems; + struct nft_trans_one_elem elems[] __counted_by(nelems); }; #define nft_trans_container_elem(t) \ container_of(t, struct nft_trans_elem, nft_trans) #define nft_trans_elem_set(trans) \ nft_trans_container_elem(trans)->set -#define nft_trans_elem_priv(trans) \ - nft_trans_container_elem(trans)->elem_priv -#define nft_trans_elem_update_flags(trans) \ - nft_trans_container_elem(trans)->update_flags -#define nft_trans_elem_timeout(trans) \ - nft_trans_container_elem(trans)->timeout -#define nft_trans_elem_expiration(trans) \ - nft_trans_container_elem(trans)->expiration #define nft_trans_elem_set_bound(trans) \ nft_trans_container_elem(trans)->bound diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 9e9079321380..49c944e78463 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -564,16 +564,26 @@ enum nft_immediate_attributes { /** * enum nft_bitwise_ops - nf_tables bitwise operations * - * @NFT_BITWISE_BOOL: mask-and-xor operation used to implement NOT, AND, OR and - * XOR boolean operations + * @NFT_BITWISE_MASK_XOR: mask-and-xor operation used to implement NOT, AND, OR + * and XOR boolean operations * @NFT_BITWISE_LSHIFT: left-shift operation * @NFT_BITWISE_RSHIFT: right-shift operation + * @NFT_BITWISE_AND: and operation + * @NFT_BITWISE_OR: or operation + * @NFT_BITWISE_XOR: xor operation */ enum nft_bitwise_ops { - NFT_BITWISE_BOOL, + NFT_BITWISE_MASK_XOR, NFT_BITWISE_LSHIFT, NFT_BITWISE_RSHIFT, + NFT_BITWISE_AND, + NFT_BITWISE_OR, + NFT_BITWISE_XOR, }; +/* + * Old name for NFT_BITWISE_MASK_XOR. Retained for backwards-compatibility. + */ +#define NFT_BITWISE_BOOL NFT_BITWISE_MASK_XOR /** * enum nft_bitwise_attributes - nf_tables bitwise expression netlink attributes @@ -586,6 +596,7 @@ enum nft_bitwise_ops { * @NFTA_BITWISE_OP: type of operation (NLA_U32: nft_bitwise_ops) * @NFTA_BITWISE_DATA: argument for non-boolean operations * (NLA_NESTED: nft_data_attributes) + * @NFTA_BITWISE_SREG2: second source register (NLA_U32: nft_registers) * * The bitwise expression supports boolean and shift operations. It implements * the boolean operations by performing the following operation: @@ -609,6 +620,7 @@ enum nft_bitwise_attributes { NFTA_BITWISE_XOR, NFTA_BITWISE_OP, NFTA_BITWISE_DATA, + NFTA_BITWISE_SREG2, __NFTA_BITWISE_MAX }; #define NFTA_BITWISE_MAX (__NFTA_BITWISE_MAX - 1) diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index e0aab66cd925..08bc3f2c0078 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -44,7 +44,7 @@ int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, un */ fl4.daddr = iph->daddr; fl4.saddr = saddr; - fl4.flowi4_tos = iph->tos & INET_DSCP_MASK; + fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)); fl4.flowi4_oif = sk ? sk->sk_bound_dev_if : 0; fl4.flowi4_l3mdev = l3mdev_master_ifindex(dev); fl4.flowi4_mark = skb->mark; diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 1ce7a1655b97..a27782d7653e 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -76,7 +76,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.daddr = iph->saddr; flow.saddr = rpfilter_get_saddr(iph->daddr); flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; - flow.flowi4_tos = iph->tos & INET_DSCP_MASK; + flow.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)); flow.flowi4_scope = RT_SCOPE_UNIVERSE; flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par)); flow.flowi4_uid = sock_net_uid(xt_net(par), NULL); diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c index ec94ee1051c7..25e1e8eb18dd 100644 --- a/net/ipv4/netfilter/nf_dup_ipv4.c +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -33,7 +33,7 @@ static bool nf_dup_ipv4_route(struct net *net, struct sk_buff *skb, fl4.flowi4_oif = oif; fl4.daddr = gw->s_addr; - fl4.flowi4_tos = iph->tos & INET_DSCP_MASK; + fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)); fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = FLOWI_FLAG_KNOWN_NH; rt = ip_route_output_key(net, &fl4); diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index 09fff5d424ef..625adbc42037 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -11,6 +11,7 @@ #include <net/netfilter/nft_fib.h> #include <net/inet_dscp.h> +#include <net/ip.h> #include <net/ip_fib.h> #include <net/route.h> @@ -107,7 +108,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, if (priv->flags & NFTA_FIB_F_MARK) fl4.flowi4_mark = pkt->skb->mark; - fl4.flowi4_tos = iph->tos & INET_DSCP_MASK; + fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)); if (priv->flags & NFTA_FIB_F_DADDR) { fl4.daddr = iph->daddr; diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c index 3d64a4511fcf..06b084844700 100644 --- a/net/netfilter/nf_bpf_link.c +++ b/net/netfilter/nf_bpf_link.c @@ -43,7 +43,7 @@ get_proto_defrag_hook(struct bpf_nf_link *link, hook = rcu_dereference(*ptr_global_hook); if (!hook) { rcu_read_unlock(); - err = request_module(mod); + err = request_module("%s", mod); if (err) return ERR_PTR(err < 0 ? err : -EINVAL); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 6090ba9f1bb2..21b6f7410a1f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -26,6 +26,9 @@ #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) #define NFT_SET_MAX_ANONLEN 16 +/* limit compaction to avoid huge kmalloc/krealloc sizes. */ +#define NFT_MAX_SET_NELEMS ((2048 - sizeof(struct nft_trans_elem)) / sizeof(struct nft_trans_one_elem)) + unsigned int nf_tables_net_id __read_mostly; static LIST_HEAD(nf_tables_expressions); @@ -391,6 +394,86 @@ static void nf_tables_unregister_hook(struct net *net, return __nf_tables_unregister_hook(net, table, chain, false); } +static bool nft_trans_collapse_set_elem_allowed(const struct nft_trans_elem *a, const struct nft_trans_elem *b) +{ + /* NB: the ->bound equality check is defensive, at this time we only merge + * a new nft_trans_elem transaction request with the transaction tail + * element, but a->bound != b->bound would imply a NEWRULE transaction + * is queued in-between. + * + * The set check is mandatory, the NFT_MAX_SET_NELEMS check prevents + * huge krealloc() requests. + */ + return a->set == b->set && a->bound == b->bound && a->nelems < NFT_MAX_SET_NELEMS; +} + +static bool nft_trans_collapse_set_elem(struct nftables_pernet *nft_net, + struct nft_trans_elem *tail, + struct nft_trans_elem *trans, + gfp_t gfp) +{ + unsigned int nelems, old_nelems = tail->nelems; + struct nft_trans_elem *new_trans; + + if (!nft_trans_collapse_set_elem_allowed(tail, trans)) + return false; + + /* "cannot happen", at this time userspace element add + * requests always allocate a new transaction element. + * + * This serves as a reminder to adjust the list_add_tail + * logic below in case this ever changes. + */ + if (WARN_ON_ONCE(trans->nelems != 1)) + return false; + + if (check_add_overflow(old_nelems, trans->nelems, &nelems)) + return false; + + /* krealloc might free tail which invalidates list pointers */ + list_del_init(&tail->nft_trans.list); + + new_trans = krealloc(tail, struct_size(tail, elems, nelems), gfp); + if (!new_trans) { + list_add_tail(&tail->nft_trans.list, &nft_net->commit_list); + return false; + } + + /* + * new_trans->nft_trans.list contains garbage, but + * list_add_tail() doesn't care. + */ + new_trans->nelems = nelems; + new_trans->elems[old_nelems] = trans->elems[0]; + list_add_tail(&new_trans->nft_trans.list, &nft_net->commit_list); + + return true; +} + +static bool nft_trans_try_collapse(struct nftables_pernet *nft_net, + struct nft_trans *trans, gfp_t gfp) +{ + struct nft_trans *tail; + + if (list_empty(&nft_net->commit_list)) + return false; + + tail = list_last_entry(&nft_net->commit_list, struct nft_trans, list); + + if (tail->msg_type != trans->msg_type) + return false; + + switch (trans->msg_type) { + case NFT_MSG_NEWSETELEM: + case NFT_MSG_DELSETELEM: + return nft_trans_collapse_set_elem(nft_net, + nft_trans_container_elem(tail), + nft_trans_container_elem(trans), gfp); + } + + return false; +} + static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *trans) { struct nftables_pernet *nft_net = nft_pernet(net); @@ -421,6 +504,24 @@ static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *tr } } +static void nft_trans_commit_list_add_elem(struct net *net, struct nft_trans *trans, + gfp_t gfp) +{ + struct nftables_pernet *nft_net = nft_pernet(net); + + WARN_ON_ONCE(trans->msg_type != NFT_MSG_NEWSETELEM && + trans->msg_type != NFT_MSG_DELSETELEM); + + might_alloc(gfp); + + if (nft_trans_try_collapse(nft_net, trans, gfp)) { + kfree(trans); + return; + } + + nft_trans_commit_list_add_tail(net, trans); +} + static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) { struct nft_trans *trans; @@ -6435,13 +6536,17 @@ static struct nft_trans *nft_trans_elem_alloc(const struct nft_ctx *ctx, int msg_type, struct nft_set *set) { + struct nft_trans_elem *te; struct nft_trans *trans; - trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_elem)); + trans = nft_trans_alloc(ctx, msg_type, struct_size(te, elems, 1)); if (trans == NULL) return NULL; - nft_trans_elem_set(trans) = set; + te = nft_trans_container_elem(trans); + te->nelems = 1; + te->set = set; + return trans; } @@ -6563,28 +6668,52 @@ static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx, } /* Drop references and destroy. Called from gc, dynset and abort path. */ -void nft_set_elem_destroy(const struct nft_set *set, - const struct nft_elem_priv *elem_priv, - bool destroy_expr) +static void __nft_set_elem_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, + const struct nft_elem_priv *elem_priv, + bool destroy_expr) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); - struct nft_ctx ctx = { - .net = read_pnet(&set->net), - .family = set->table->family, - }; nft_data_release(nft_set_ext_key(ext), NFT_DATA_VALUE); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) - nft_set_elem_expr_destroy(&ctx, nft_set_ext_expr(ext)); + nft_set_elem_expr_destroy(ctx, nft_set_ext_expr(ext)); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) nft_use_dec(&(*nft_set_ext_obj(ext))->use); kfree(elem_priv); } + +/* Drop references and destroy. Called from gc and dynset. */ +void nft_set_elem_destroy(const struct nft_set *set, + const struct nft_elem_priv *elem_priv, + bool destroy_expr) +{ + struct nft_ctx ctx = { + .net = read_pnet(&set->net), + .family = set->table->family, + }; + + __nft_set_elem_destroy(&ctx, set, elem_priv, destroy_expr); +} EXPORT_SYMBOL_GPL(nft_set_elem_destroy); +/* Drop references and destroy. Called from abort path. */ +static void nft_trans_set_elem_destroy(const struct nft_ctx *ctx, struct nft_trans_elem *te) +{ + int i; + + for (i = 0; i < te->nelems; i++) { + /* skip update request, see nft_trans_elems_new_abort() */ + if (!te->elems[i].priv) + continue; + + __nft_set_elem_destroy(ctx, te->set, te->elems[i].priv, true); + } +} + /* Destroy element. References have been already dropped in the preparation * path via nft_setelem_data_deactivate(). */ @@ -6600,6 +6729,15 @@ void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, kfree(elem_priv); } +static void nft_trans_elems_destroy(const struct nft_ctx *ctx, + const struct nft_trans_elem *te) +{ + int i; + + for (i = 0; i < te->nelems; i++) + nf_tables_set_elem_destroy(ctx, te->set, te->elems[i].priv); +} + int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, struct nft_expr *expr_array[]) { @@ -6756,6 +6894,38 @@ static void nft_setelem_activate(struct net *net, struct nft_set *set, } } +static void nft_trans_elem_update(const struct nft_set *set, + const struct nft_trans_one_elem *elem) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_elem_update *update = elem->update; + + if (update->flags & NFT_TRANS_UPD_TIMEOUT) + WRITE_ONCE(nft_set_ext_timeout(ext)->timeout, update->timeout); + + if (update->flags & NFT_TRANS_UPD_EXPIRATION) + WRITE_ONCE(nft_set_ext_timeout(ext)->expiration, get_jiffies_64() + update->expiration); +} + +static void nft_trans_elems_add(const struct nft_ctx *ctx, + struct nft_trans_elem *te) +{ + int i; + + for (i = 0; i < te->nelems; i++) { + struct nft_trans_one_elem *elem = &te->elems[i]; + + if (elem->update) + nft_trans_elem_update(te->set, elem); + else + nft_setelem_activate(ctx->net, te->set, elem->priv); + + nf_tables_setelem_notify(ctx, te->set, elem->priv, + NFT_MSG_NEWSETELEM); + kfree(elem->update); + } +} + static int nft_setelem_catchall_deactivate(const struct net *net, struct nft_set *set, struct nft_set_elem *elem) @@ -6838,6 +7008,26 @@ static void nft_setelem_remove(const struct net *net, set->ops->remove(net, set, elem_priv); } +static void nft_trans_elems_remove(const struct nft_ctx *ctx, + const struct nft_trans_elem *te) +{ + int i; + + for (i = 0; i < te->nelems; i++) { + WARN_ON_ONCE(te->elems[i].update); + + nf_tables_setelem_notify(ctx, te->set, + te->elems[i].priv, + te->nft_trans.msg_type); + + nft_setelem_remove(ctx->net, te->set, te->elems[i].priv); + if (!nft_setelem_is_catchall(te->set, te->elems[i].priv)) { + atomic_dec(&te->set->nelems); + te->set->ndeact--; + } + } +} + static bool nft_setelem_valid_key_end(const struct nft_set *set, struct nlattr **nla, u32 flags) { @@ -6874,7 +7064,6 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, struct nft_data_desc desc; enum nft_registers dreg; struct nft_trans *trans; - u8 update_flags; u64 expiration; u64 timeout; int err, i; @@ -7189,23 +7378,33 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, else if (!(nlmsg_flags & NLM_F_EXCL)) { err = 0; if (nft_set_ext_exists(ext2, NFT_SET_EXT_TIMEOUT)) { - update_flags = 0; + struct nft_elem_update update = { }; + if (timeout != nft_set_ext_timeout(ext2)->timeout) { - nft_trans_elem_timeout(trans) = timeout; + update.timeout = timeout; if (expiration == 0) expiration = timeout; - update_flags |= NFT_TRANS_UPD_TIMEOUT; + update.flags |= NFT_TRANS_UPD_TIMEOUT; } if (expiration) { - nft_trans_elem_expiration(trans) = expiration; - update_flags |= NFT_TRANS_UPD_EXPIRATION; + update.expiration = expiration; + update.flags |= NFT_TRANS_UPD_EXPIRATION; } - if (update_flags) { - nft_trans_elem_priv(trans) = elem_priv; - nft_trans_elem_update_flags(trans) = update_flags; - nft_trans_commit_list_add_tail(ctx->net, trans); + if (update.flags) { + struct nft_trans_one_elem *ue; + + ue = &nft_trans_container_elem(trans)->elems[0]; + + ue->update = kmemdup(&update, sizeof(update), GFP_KERNEL); + if (!ue->update) { + err = -ENOMEM; + goto err_element_clash; + } + + ue->priv = elem_priv; + nft_trans_commit_list_add_elem(ctx->net, trans, GFP_KERNEL); goto err_elem_free; } } @@ -7228,8 +7427,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, } } - nft_trans_elem_priv(trans) = elem.priv; - nft_trans_commit_list_add_tail(ctx->net, trans); + nft_trans_container_elem(trans)->elems[0].priv = elem.priv; + nft_trans_commit_list_add_elem(ctx->net, trans, GFP_KERNEL); return 0; err_set_full: @@ -7366,6 +7565,55 @@ void nft_setelem_data_deactivate(const struct net *net, nft_use_dec(&(*nft_set_ext_obj(ext))->use); } +/* similar to nft_trans_elems_remove, but called from abort path to undo newsetelem. + * No notifications and no ndeact changes. + * + * Returns true if set had been added to (i.e., elements need to be removed again). + */ +static bool nft_trans_elems_new_abort(const struct nft_ctx *ctx, + struct nft_trans_elem *te) +{ + bool removed = false; + int i; + + for (i = 0; i < te->nelems; i++) { + if (te->elems[i].update) { + kfree(te->elems[i].update); + te->elems[i].update = NULL; + /* Update request, so do not release this element */ + te->elems[i].priv = NULL; + continue; + } + + if (!te->set->ops->abort || nft_setelem_is_catchall(te->set, te->elems[i].priv)) + nft_setelem_remove(ctx->net, te->set, te->elems[i].priv); + + if (!nft_setelem_is_catchall(te->set, te->elems[i].priv)) + atomic_dec(&te->set->nelems); + + removed = true; + } + + return removed; +} + +/* Called from abort path to undo DELSETELEM/DESTROYSETELEM. */ +static void nft_trans_elems_destroy_abort(const struct nft_ctx *ctx, + const struct nft_trans_elem *te) +{ + int i; + + for (i = 0; i < te->nelems; i++) { + if (!nft_setelem_active_next(ctx->net, te->set, te->elems[i].priv)) { + nft_setelem_data_activate(ctx->net, te->set, te->elems[i].priv); + nft_setelem_activate(ctx->net, te->set, te->elems[i].priv); + } + + if (!nft_setelem_is_catchall(te->set, te->elems[i].priv)) + te->set->ndeact--; + } +} + static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) { @@ -7445,8 +7693,8 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, nft_setelem_data_deactivate(ctx->net, set, elem.priv); - nft_trans_elem_priv(trans) = elem.priv; - nft_trans_commit_list_add_tail(ctx->net, trans); + nft_trans_container_elem(trans)->elems[0].priv = elem.priv; + nft_trans_commit_list_add_elem(ctx->net, trans, GFP_KERNEL); return 0; fail_ops: @@ -7472,7 +7720,8 @@ static int nft_setelem_flush(const struct nft_ctx *ctx, return 0; trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM, - sizeof(struct nft_trans_elem), GFP_ATOMIC); + struct_size_t(struct nft_trans_elem, elems, 1), + GFP_ATOMIC); if (!trans) return -ENOMEM; @@ -7481,8 +7730,9 @@ static int nft_setelem_flush(const struct nft_ctx *ctx, nft_setelem_data_deactivate(ctx->net, set, elem_priv); nft_trans_elem_set(trans) = set; - nft_trans_elem_priv(trans) = elem_priv; - nft_trans_commit_list_add_tail(ctx->net, trans); + nft_trans_container_elem(trans)->nelems = 1; + nft_trans_container_elem(trans)->elems[0].priv = elem_priv; + nft_trans_commit_list_add_elem(ctx->net, trans, GFP_ATOMIC); return 0; } @@ -7498,8 +7748,8 @@ static int __nft_set_catchall_flush(const struct nft_ctx *ctx, return -ENOMEM; nft_setelem_data_deactivate(ctx->net, set, elem_priv); - nft_trans_elem_priv(trans) = elem_priv; - nft_trans_commit_list_add_tail(ctx->net, trans); + nft_trans_container_elem(trans)->elems[0].priv = elem_priv; + nft_trans_commit_list_add_elem(ctx->net, trans, GFP_KERNEL); return 0; } @@ -9680,9 +9930,7 @@ static void nft_commit_release(struct nft_trans *trans) break; case NFT_MSG_DELSETELEM: case NFT_MSG_DESTROYSETELEM: - nf_tables_set_elem_destroy(&ctx, - nft_trans_elem_set(trans), - nft_trans_elem_priv(trans)); + nft_trans_elems_destroy(&ctx, nft_trans_container_elem(trans)); break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: @@ -10255,9 +10503,24 @@ static void nf_tables_commit_audit_free(struct list_head *adl) } } +/* nft audit emits the number of elements that get added/removed/updated, + * so NEW/DELSETELEM needs to increment based on the total elem count. + */ +static unsigned int nf_tables_commit_audit_entrycount(const struct nft_trans *trans) +{ + switch (trans->msg_type) { + case NFT_MSG_NEWSETELEM: + case NFT_MSG_DELSETELEM: + return nft_trans_container_elem(trans)->nelems; + } + + return 1; +} + static void nf_tables_commit_audit_collect(struct list_head *adl, - struct nft_table *table, u32 op) + const struct nft_trans *trans, u32 op) { + const struct nft_table *table = trans->table; struct nft_audit_data *adp; list_for_each_entry(adp, adl, list) { @@ -10267,7 +10530,7 @@ static void nf_tables_commit_audit_collect(struct list_head *adl, WARN_ONCE(1, "table=%s not expected in commit list", table->name); return; found: - adp->entries++; + adp->entries += nf_tables_commit_audit_entrycount(trans); if (!adp->op || adp->op > op) adp->op = op; } @@ -10426,7 +10689,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_ctx_update(&ctx, trans); - nf_tables_commit_audit_collect(&adl, table, trans->msg_type); + nf_tables_commit_audit_collect(&adl, trans, trans->msg_type); switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { @@ -10535,25 +10798,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) case NFT_MSG_NEWSETELEM: te = nft_trans_container_elem(trans); - if (te->update_flags) { - const struct nft_set_ext *ext = - nft_set_elem_ext(te->set, te->elem_priv); - - if (te->update_flags & NFT_TRANS_UPD_TIMEOUT) { - WRITE_ONCE(nft_set_ext_timeout(ext)->timeout, - te->timeout); - } - if (te->update_flags & NFT_TRANS_UPD_EXPIRATION) { - WRITE_ONCE(nft_set_ext_timeout(ext)->expiration, - get_jiffies_64() + te->expiration); - } - } else { - nft_setelem_activate(net, te->set, te->elem_priv); - } + nft_trans_elems_add(&ctx, te); - nf_tables_setelem_notify(&ctx, te->set, - te->elem_priv, - NFT_MSG_NEWSETELEM); if (te->set->ops->commit && list_empty(&te->set->pending_update)) { list_add_tail(&te->set->pending_update, @@ -10565,14 +10811,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) case NFT_MSG_DESTROYSETELEM: te = nft_trans_container_elem(trans); - nf_tables_setelem_notify(&ctx, te->set, - te->elem_priv, - trans->msg_type); - nft_setelem_remove(net, te->set, te->elem_priv); - if (!nft_setelem_is_catchall(te->set, te->elem_priv)) { - atomic_dec(&te->set->nelems); - te->set->ndeact--; - } + nft_trans_elems_remove(&ctx, te); + if (te->set->ops->commit && list_empty(&te->set->pending_update)) { list_add_tail(&te->set->pending_update, @@ -10692,8 +10932,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) nft_set_destroy(&ctx, nft_trans_set(trans)); break; case NFT_MSG_NEWSETELEM: - nft_set_elem_destroy(nft_trans_elem_set(trans), - nft_trans_elem_priv(trans), true); + nft_trans_set_elem_destroy(&ctx, nft_trans_container_elem(trans)); break; case NFT_MSG_NEWOBJ: nft_obj_destroy(&ctx, nft_trans_obj(trans)); @@ -10850,18 +11089,15 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: - if (nft_trans_elem_update_flags(trans) || - nft_trans_elem_set_bound(trans)) { + if (nft_trans_elem_set_bound(trans)) { nft_trans_destroy(trans); break; } te = nft_trans_container_elem(trans); - if (!te->set->ops->abort || - nft_setelem_is_catchall(te->set, te->elem_priv)) - nft_setelem_remove(net, te->set, te->elem_priv); - - if (!nft_setelem_is_catchall(te->set, te->elem_priv)) - atomic_dec(&te->set->nelems); + if (!nft_trans_elems_new_abort(&ctx, te)) { + nft_trans_destroy(trans); + break; + } if (te->set->ops->abort && list_empty(&te->set->pending_update)) { @@ -10873,12 +11109,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DESTROYSETELEM: te = nft_trans_container_elem(trans); - if (!nft_setelem_active_next(net, te->set, te->elem_priv)) { - nft_setelem_data_activate(net, te->set, te->elem_priv); - nft_setelem_activate(net, te->set, te->elem_priv); - } - if (!nft_setelem_is_catchall(te->set, te->elem_priv)) - te->set->ndeact--; + nft_trans_elems_destroy_abort(&ctx, te); if (te->set->ops->abort && list_empty(&te->set->pending_update)) { diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 7784ec094097..e598a2a252b0 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -517,7 +517,7 @@ replay_abort: err = nla_parse_deprecated(cda, ss->cb[cb_id].attr_count, attr, attrlen, - ss->cb[cb_id].policy, NULL); + ss->cb[cb_id].policy, &extack); if (err < 0) goto ack; diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 7de95674fd8c..d550910aabec 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -17,6 +17,7 @@ struct nft_bitwise { u8 sreg; + u8 sreg2; u8 dreg; enum nft_bitwise_ops op:8; u8 len; @@ -25,8 +26,8 @@ struct nft_bitwise { struct nft_data data; }; -static void nft_bitwise_eval_bool(u32 *dst, const u32 *src, - const struct nft_bitwise *priv) +static void nft_bitwise_eval_mask_xor(u32 *dst, const u32 *src, + const struct nft_bitwise *priv) { unsigned int i; @@ -60,28 +61,72 @@ static void nft_bitwise_eval_rshift(u32 *dst, const u32 *src, } } +static void nft_bitwise_eval_and(u32 *dst, const u32 *src, const u32 *src2, + const struct nft_bitwise *priv) +{ + unsigned int i, n; + + for (i = 0, n = DIV_ROUND_UP(priv->len, sizeof(u32)); i < n; i++) + dst[i] = src[i] & src2[i]; +} + +static void nft_bitwise_eval_or(u32 *dst, const u32 *src, const u32 *src2, + const struct nft_bitwise *priv) +{ + unsigned int i, n; + + for (i = 0, n = DIV_ROUND_UP(priv->len, sizeof(u32)); i < n; i++) + dst[i] = src[i] | src2[i]; +} + +static void nft_bitwise_eval_xor(u32 *dst, const u32 *src, const u32 *src2, + const struct nft_bitwise *priv) +{ + unsigned int i, n; + + for (i = 0, n = DIV_ROUND_UP(priv->len, sizeof(u32)); i < n; i++) + dst[i] = src[i] ^ src2[i]; +} + void nft_bitwise_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_bitwise *priv = nft_expr_priv(expr); - const u32 *src = ®s->data[priv->sreg]; + const u32 *src = ®s->data[priv->sreg], *src2; u32 *dst = ®s->data[priv->dreg]; - switch (priv->op) { - case NFT_BITWISE_BOOL: - nft_bitwise_eval_bool(dst, src, priv); - break; - case NFT_BITWISE_LSHIFT: + if (priv->op == NFT_BITWISE_MASK_XOR) { + nft_bitwise_eval_mask_xor(dst, src, priv); + return; + } + if (priv->op == NFT_BITWISE_LSHIFT) { nft_bitwise_eval_lshift(dst, src, priv); - break; - case NFT_BITWISE_RSHIFT: + return; + } + if (priv->op == NFT_BITWISE_RSHIFT) { nft_bitwise_eval_rshift(dst, src, priv); - break; + return; + } + + src2 = priv->sreg2 ? ®s->data[priv->sreg2] : priv->data.data; + + if (priv->op == NFT_BITWISE_AND) { + nft_bitwise_eval_and(dst, src, src2, priv); + return; + } + if (priv->op == NFT_BITWISE_OR) { + nft_bitwise_eval_or(dst, src, src2, priv); + return; + } + if (priv->op == NFT_BITWISE_XOR) { + nft_bitwise_eval_xor(dst, src, src2, priv); + return; } } static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = { [NFTA_BITWISE_SREG] = { .type = NLA_U32 }, + [NFTA_BITWISE_SREG2] = { .type = NLA_U32 }, [NFTA_BITWISE_DREG] = { .type = NLA_U32 }, [NFTA_BITWISE_LEN] = { .type = NLA_U32 }, [NFTA_BITWISE_MASK] = { .type = NLA_NESTED }, @@ -90,8 +135,8 @@ static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = { [NFTA_BITWISE_DATA] = { .type = NLA_NESTED }, }; -static int nft_bitwise_init_bool(struct nft_bitwise *priv, - const struct nlattr *const tb[]) +static int nft_bitwise_init_mask_xor(struct nft_bitwise *priv, + const struct nlattr *const tb[]) { struct nft_data_desc mask = { .type = NFT_DATA_VALUE, @@ -105,7 +150,8 @@ static int nft_bitwise_init_bool(struct nft_bitwise *priv, }; int err; - if (tb[NFTA_BITWISE_DATA]) + if (tb[NFTA_BITWISE_DATA] || + tb[NFTA_BITWISE_SREG2]) return -EINVAL; if (!tb[NFTA_BITWISE_MASK] || @@ -139,7 +185,8 @@ static int nft_bitwise_init_shift(struct nft_bitwise *priv, int err; if (tb[NFTA_BITWISE_MASK] || - tb[NFTA_BITWISE_XOR]) + tb[NFTA_BITWISE_XOR] || + tb[NFTA_BITWISE_SREG2]) return -EINVAL; if (!tb[NFTA_BITWISE_DATA]) @@ -157,6 +204,41 @@ static int nft_bitwise_init_shift(struct nft_bitwise *priv, return 0; } +static int nft_bitwise_init_bool(const struct nft_ctx *ctx, + struct nft_bitwise *priv, + const struct nlattr *const tb[]) +{ + int err; + + if (tb[NFTA_BITWISE_MASK] || + tb[NFTA_BITWISE_XOR]) + return -EINVAL; + + if ((!tb[NFTA_BITWISE_DATA] && !tb[NFTA_BITWISE_SREG2]) || + (tb[NFTA_BITWISE_DATA] && tb[NFTA_BITWISE_SREG2])) + return -EINVAL; + + if (tb[NFTA_BITWISE_DATA]) { + struct nft_data_desc desc = { + .type = NFT_DATA_VALUE, + .size = sizeof(priv->data), + .len = priv->len, + }; + + err = nft_data_init(NULL, &priv->data, &desc, + tb[NFTA_BITWISE_DATA]); + if (err < 0) + return err; + } else { + err = nft_parse_register_load(ctx, tb[NFTA_BITWISE_SREG2], + &priv->sreg2, priv->len); + if (err < 0) + return err; + } + + return 0; +} + static int nft_bitwise_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -185,32 +267,40 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, if (tb[NFTA_BITWISE_OP]) { priv->op = ntohl(nla_get_be32(tb[NFTA_BITWISE_OP])); switch (priv->op) { - case NFT_BITWISE_BOOL: + case NFT_BITWISE_MASK_XOR: case NFT_BITWISE_LSHIFT: case NFT_BITWISE_RSHIFT: + case NFT_BITWISE_AND: + case NFT_BITWISE_OR: + case NFT_BITWISE_XOR: break; default: return -EOPNOTSUPP; } } else { - priv->op = NFT_BITWISE_BOOL; + priv->op = NFT_BITWISE_MASK_XOR; } switch(priv->op) { - case NFT_BITWISE_BOOL: - err = nft_bitwise_init_bool(priv, tb); + case NFT_BITWISE_MASK_XOR: + err = nft_bitwise_init_mask_xor(priv, tb); break; case NFT_BITWISE_LSHIFT: case NFT_BITWISE_RSHIFT: err = nft_bitwise_init_shift(priv, tb); break; + case NFT_BITWISE_AND: + case NFT_BITWISE_OR: + case NFT_BITWISE_XOR: + err = nft_bitwise_init_bool(ctx, priv, tb); + break; } return err; } -static int nft_bitwise_dump_bool(struct sk_buff *skb, - const struct nft_bitwise *priv) +static int nft_bitwise_dump_mask_xor(struct sk_buff *skb, + const struct nft_bitwise *priv) { if (nft_data_dump(skb, NFTA_BITWISE_MASK, &priv->mask, NFT_DATA_VALUE, priv->len) < 0) @@ -232,6 +322,21 @@ static int nft_bitwise_dump_shift(struct sk_buff *skb, return 0; } +static int nft_bitwise_dump_bool(struct sk_buff *skb, + const struct nft_bitwise *priv) +{ + if (priv->sreg2) { + if (nft_dump_register(skb, NFTA_BITWISE_SREG2, priv->sreg2)) + return -1; + } else { + if (nft_data_dump(skb, NFTA_BITWISE_DATA, &priv->data, + NFT_DATA_VALUE, sizeof(u32)) < 0) + return -1; + } + + return 0; +} + static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { @@ -248,13 +353,18 @@ static int nft_bitwise_dump(struct sk_buff *skb, return -1; switch (priv->op) { - case NFT_BITWISE_BOOL: - err = nft_bitwise_dump_bool(skb, priv); + case NFT_BITWISE_MASK_XOR: + err = nft_bitwise_dump_mask_xor(skb, priv); break; case NFT_BITWISE_LSHIFT: case NFT_BITWISE_RSHIFT: err = nft_bitwise_dump_shift(skb, priv); break; + case NFT_BITWISE_AND: + case NFT_BITWISE_OR: + case NFT_BITWISE_XOR: + err = nft_bitwise_dump_bool(skb, priv); + break; } return err; @@ -269,7 +379,7 @@ static int nft_bitwise_offload(struct nft_offload_ctx *ctx, const struct nft_bitwise *priv = nft_expr_priv(expr); struct nft_offload_reg *reg = &ctx->regs[priv->dreg]; - if (priv->op != NFT_BITWISE_BOOL) + if (priv->op != NFT_BITWISE_MASK_XOR) return -EOPNOTSUPP; if (memcmp(&priv->xor, &zero, sizeof(priv->xor)) || @@ -299,6 +409,7 @@ static bool nft_bitwise_reduce(struct nft_regs_track *track, track->regs[priv->dreg].bitwise && track->regs[priv->dreg].bitwise->ops == expr->ops && priv->sreg == bitwise->sreg && + priv->sreg2 == bitwise->sreg2 && priv->dreg == bitwise->dreg && priv->op == bitwise->op && priv->len == bitwise->len && @@ -375,7 +486,8 @@ static int nft_bitwise_fast_init(const struct nft_ctx *ctx, if (err < 0) return err; - if (tb[NFTA_BITWISE_DATA]) + if (tb[NFTA_BITWISE_DATA] || + tb[NFTA_BITWISE_SREG2]) return -EINVAL; if (!tb[NFTA_BITWISE_MASK] || @@ -406,7 +518,7 @@ nft_bitwise_fast_dump(struct sk_buff *skb, return -1; if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(sizeof(u32)))) return -1; - if (nla_put_be32(skb, NFTA_BITWISE_OP, htonl(NFT_BITWISE_BOOL))) + if (nla_put_be32(skb, NFTA_BITWISE_OP, htonl(NFT_BITWISE_MASK_XOR))) return -1; data.data[0] = priv->mask; @@ -501,7 +613,7 @@ nft_bitwise_select_ops(const struct nft_ctx *ctx, return &nft_bitwise_ops; if (tb[NFTA_BITWISE_OP] && - ntohl(nla_get_be32(tb[NFTA_BITWISE_OP])) != NFT_BITWISE_BOOL) + ntohl(nla_get_be32(tb[NFTA_BITWISE_OP])) != NFT_BITWISE_MASK_XOR) return &nft_bitwise_ops; return &nft_bitwise_fast_ops; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 65199c23c75c..3b474d235663 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -8,7 +8,7 @@ #include <linux/spinlock.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/netfilter/nf_tables.h> -#include <net/ip.h> /* for ipv4 options. */ +#include <net/ip.h> #include <net/inet_dscp.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> @@ -236,7 +236,7 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, fl.u.ip4.saddr = ct->tuplehash[!dir].tuple.src.u3.ip; fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex; fl.u.ip4.flowi4_iif = this_dst->dev->ifindex; - fl.u.ip4.flowi4_tos = ip_hdr(pkt->skb)->tos & INET_DSCP_MASK; + fl.u.ip4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip_hdr(pkt->skb))); fl.u.ip4.flowi4_mark = pkt->skb->mark; fl.u.ip4.flowi4_flags = FLOWI_FLAG_ANYSRC; break; |