summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-10-15 18:42:13 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-10-15 18:42:13 -0700
commit9ff9b0d392ea08090cd1780fb196f36dbb586529 (patch)
tree276a3a5c4525b84dee64eda30b423fc31bf94850 /lib
parent840e5bb326bbcb16ce82dd2416d2769de4839aea (diff)
parent105faa8742437c28815b2a3eb8314ebc5fd9288c (diff)
downloadlwn-9ff9b0d392ea08090cd1780fb196f36dbb586529.tar.gz
lwn-9ff9b0d392ea08090cd1780fb196f36dbb586529.zip
Merge tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: - Add redirect_neigh() BPF packet redirect helper, allowing to limit stack traversal in common container configs and improving TCP back-pressure. Daniel reports ~10Gbps => ~15Gbps single stream TCP performance gain. - Expand netlink policy support and improve policy export to user space. (Ge)netlink core performs request validation according to declared policies. Expand the expressiveness of those policies (min/max length and bitmasks). Allow dumping policies for particular commands. This is used for feature discovery by user space (instead of kernel version parsing or trial and error). - Support IGMPv3/MLDv2 multicast listener discovery protocols in bridge. - Allow more than 255 IPv4 multicast interfaces. - Add support for Type of Service (ToS) reflection in SYN/SYN-ACK packets of TCPv6. - In Multi-patch TCP (MPTCP) support concurrent transmission of data on multiple subflows in a load balancing scenario. Enhance advertising addresses via the RM_ADDR/ADD_ADDR options. - Support SMC-Dv2 version of SMC, which enables multi-subnet deployments. - Allow more calls to same peer in RxRPC. - Support two new Controller Area Network (CAN) protocols - CAN-FD and ISO 15765-2:2016. - Add xfrm/IPsec compat layer, solving the 32bit user space on 64bit kernel problem. - Add TC actions for implementing MPLS L2 VPNs. - Improve nexthop code - e.g. handle various corner cases when nexthop objects are removed from groups better, skip unnecessary notifications and make it easier to offload nexthops into HW by converting to a blocking notifier. - Support adding and consuming TCP header options by BPF programs, opening the doors for easy experimental and deployment-specific TCP option use. - Reorganize TCP congestion control (CC) initialization to simplify life of TCP CC implemented in BPF. - Add support for shipping BPF programs with the kernel and loading them early on boot via the User Mode Driver mechanism, hence reusing all the user space infra we have. - Support sleepable BPF programs, initially targeting LSM and tracing. - Add bpf_d_path() helper for returning full path for given 'struct path'. - Make bpf_tail_call compatible with bpf-to-bpf calls. - Allow BPF programs to call map_update_elem on sockmaps. - Add BPF Type Format (BTF) support for type and enum discovery, as well as support for using BTF within the kernel itself (current use is for pretty printing structures). - Support listing and getting information about bpf_links via the bpf syscall. - Enhance kernel interfaces around NIC firmware update. Allow specifying overwrite mask to control if settings etc. are reset during update; report expected max time operation may take to users; support firmware activation without machine reboot incl. limits of how much impact reset may have (e.g. dropping link or not). - Extend ethtool configuration interface to report IEEE-standard counters, to limit the need for per-vendor logic in user space. - Adopt or extend devlink use for debug, monitoring, fw update in many drivers (dsa loop, ice, ionic, sja1105, qed, mlxsw, mv88e6xxx, dpaa2-eth). - In mlxsw expose critical and emergency SFP module temperature alarms. Refactor port buffer handling to make the defaults more suitable and support setting these values explicitly via the DCBNL interface. - Add XDP support for Intel's igb driver. - Support offloading TC flower classification and filtering rules to mscc_ocelot switches. - Add PTP support for Marvell Octeontx2 and PP2.2 hardware, as well as fixed interval period pulse generator and one-step timestamping in dpaa-eth. - Add support for various auth offloads in WiFi APs, e.g. SAE (WPA3) offload. - Add Lynx PHY/PCS MDIO module, and convert various drivers which have this HW to use it. Convert mvpp2 to split PCS. - Support Marvell Prestera 98DX3255 24-port switch ASICs, as well as 7-port Mediatek MT7531 IP. - Add initial support for QCA6390 and IPQ6018 in ath11k WiFi driver, and wcn3680 support in wcn36xx. - Improve performance for packets which don't require much offloads on recent Mellanox NICs by 20% by making multiple packets share a descriptor entry. - Move chelsio inline crypto drivers (for TLS and IPsec) from the crypto subtree to drivers/net. Move MDIO drivers out of the phy directory. - Clean up a lot of W=1 warnings, reportedly the actively developed subsections of networking drivers should now build W=1 warning free. - Make sure drivers don't use in_interrupt() to dynamically adapt their code. Convert tasklets to use new tasklet_setup API (sadly this conversion is not yet complete). * tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2583 commits) Revert "bpfilter: Fix build error with CONFIG_BPFILTER_UMH" net, sockmap: Don't call bpf_prog_put() on NULL pointer bpf, selftest: Fix flaky tcp_hdr_options test when adding addr to lo bpf, sockmap: Add locking annotations to iterator netfilter: nftables: allow re-computing sctp CRC-32C in 'payload' statements net: fix pos incrementment in ipv6_route_seq_next net/smc: fix invalid return code in smcd_new_buf_create() net/smc: fix valid DMBE buffer sizes net/smc: fix use-after-free of delayed events bpfilter: Fix build error with CONFIG_BPFILTER_UMH cxgb4/ch_ipsec: Replace the module name to ch_ipsec from chcr net: sched: Fix suspicious RCU usage while accessing tcf_tunnel_info bpf: Fix register equivalence tracking. rxrpc: Fix loss of final ack on shutdown rxrpc: Fix bundle counting for exclusive connections netfilter: restore NF_INET_NUMHOOKS ibmveth: Identify ingress large send packets. ibmveth: Switch order of ibmveth_helper calls. cxgb4: handle 4-tuple PEDIT to NAT mode translation selftests: Add VRF route leaking tests ...
Diffstat (limited to 'lib')
-rw-r--r--lib/nlattr.c122
1 files changed, 88 insertions, 34 deletions
diff --git a/lib/nlattr.c b/lib/nlattr.c
index bc5b5cf608c4..74019c8ebf6b 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -96,8 +96,8 @@ static int nla_validate_array(const struct nlattr *head, int len, int maxtype,
continue;
if (nla_len(entry) < NLA_HDRLEN) {
- NL_SET_ERR_MSG_ATTR(extack, entry,
- "Array element too short");
+ NL_SET_ERR_MSG_ATTR_POL(extack, entry, policy,
+ "Array element too short");
return -ERANGE;
}
@@ -124,6 +124,7 @@ void nla_get_range_unsigned(const struct nla_policy *pt,
range->max = U8_MAX;
break;
case NLA_U16:
+ case NLA_BINARY:
range->max = U16_MAX;
break;
case NLA_U32:
@@ -140,6 +141,7 @@ void nla_get_range_unsigned(const struct nla_policy *pt,
switch (pt->validation_type) {
case NLA_VALIDATE_RANGE:
+ case NLA_VALIDATE_RANGE_WARN_TOO_LONG:
range->min = pt->min;
range->max = pt->max;
break;
@@ -157,9 +159,10 @@ void nla_get_range_unsigned(const struct nla_policy *pt,
}
}
-static int nla_validate_int_range_unsigned(const struct nla_policy *pt,
- const struct nlattr *nla,
- struct netlink_ext_ack *extack)
+static int nla_validate_range_unsigned(const struct nla_policy *pt,
+ const struct nlattr *nla,
+ struct netlink_ext_ack *extack,
+ unsigned int validate)
{
struct netlink_range_validation range;
u64 value;
@@ -178,15 +181,39 @@ static int nla_validate_int_range_unsigned(const struct nla_policy *pt,
case NLA_MSECS:
value = nla_get_u64(nla);
break;
+ case NLA_BINARY:
+ value = nla_len(nla);
+ break;
default:
return -EINVAL;
}
nla_get_range_unsigned(pt, &range);
+ if (pt->validation_type == NLA_VALIDATE_RANGE_WARN_TOO_LONG &&
+ pt->type == NLA_BINARY && value > range.max) {
+ pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
+ current->comm, pt->type);
+ if (validate & NL_VALIDATE_STRICT_ATTRS) {
+ NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+ "invalid attribute length");
+ return -EINVAL;
+ }
+
+ /* this assumes min <= max (don't validate against min) */
+ return 0;
+ }
+
if (value < range.min || value > range.max) {
- NL_SET_ERR_MSG_ATTR(extack, nla,
- "integer out of range");
+ bool binary = pt->type == NLA_BINARY;
+
+ if (binary)
+ NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+ "binary attribute size out of range");
+ else
+ NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+ "integer out of range");
+
return -ERANGE;
}
@@ -264,8 +291,8 @@ static int nla_validate_int_range_signed(const struct nla_policy *pt,
nla_get_range_signed(pt, &range);
if (value < range.min || value > range.max) {
- NL_SET_ERR_MSG_ATTR(extack, nla,
- "integer out of range");
+ NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+ "integer out of range");
return -ERANGE;
}
@@ -274,7 +301,8 @@ static int nla_validate_int_range_signed(const struct nla_policy *pt,
static int nla_validate_int_range(const struct nla_policy *pt,
const struct nlattr *nla,
- struct netlink_ext_ack *extack)
+ struct netlink_ext_ack *extack,
+ unsigned int validate)
{
switch (pt->type) {
case NLA_U8:
@@ -282,7 +310,8 @@ static int nla_validate_int_range(const struct nla_policy *pt,
case NLA_U32:
case NLA_U64:
case NLA_MSECS:
- return nla_validate_int_range_unsigned(pt, nla, extack);
+ case NLA_BINARY:
+ return nla_validate_range_unsigned(pt, nla, extack, validate);
case NLA_S8:
case NLA_S16:
case NLA_S32:
@@ -294,6 +323,37 @@ static int nla_validate_int_range(const struct nla_policy *pt,
}
}
+static int nla_validate_mask(const struct nla_policy *pt,
+ const struct nlattr *nla,
+ struct netlink_ext_ack *extack)
+{
+ u64 value;
+
+ switch (pt->type) {
+ case NLA_U8:
+ value = nla_get_u8(nla);
+ break;
+ case NLA_U16:
+ value = nla_get_u16(nla);
+ break;
+ case NLA_U32:
+ value = nla_get_u32(nla);
+ break;
+ case NLA_U64:
+ value = nla_get_u64(nla);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (value & ~(u64)pt->mask) {
+ NL_SET_ERR_MSG_ATTR(extack, nla, "reserved bit set");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int validate_nla(const struct nlattr *nla, int maxtype,
const struct nla_policy *policy, unsigned int validate,
struct netlink_ext_ack *extack, unsigned int depth)
@@ -313,15 +373,12 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
BUG_ON(pt->type > NLA_TYPE_MAX);
- if ((nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) ||
- (pt->type == NLA_EXACT_LEN &&
- pt->validation_type == NLA_VALIDATE_WARN_TOO_LONG &&
- attrlen != pt->len)) {
+ if (nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) {
pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
current->comm, type);
if (validate & NL_VALIDATE_STRICT_ATTRS) {
- NL_SET_ERR_MSG_ATTR(extack, nla,
- "invalid attribute length");
+ NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+ "invalid attribute length");
return -EINVAL;
}
}
@@ -329,14 +386,14 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
if (validate & NL_VALIDATE_NESTED) {
if ((pt->type == NLA_NESTED || pt->type == NLA_NESTED_ARRAY) &&
!(nla->nla_type & NLA_F_NESTED)) {
- NL_SET_ERR_MSG_ATTR(extack, nla,
- "NLA_F_NESTED is missing");
+ NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+ "NLA_F_NESTED is missing");
return -EINVAL;
}
if (pt->type != NLA_NESTED && pt->type != NLA_NESTED_ARRAY &&
pt->type != NLA_UNSPEC && (nla->nla_type & NLA_F_NESTED)) {
- NL_SET_ERR_MSG_ATTR(extack, nla,
- "NLA_F_NESTED not expected");
+ NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+ "NLA_F_NESTED not expected");
return -EINVAL;
}
}
@@ -449,19 +506,10 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
"Unsupported attribute");
return -EINVAL;
}
- /* fall through */
- case NLA_MIN_LEN:
if (attrlen < pt->len)
goto out_err;
break;
- case NLA_EXACT_LEN:
- if (pt->validation_type != NLA_VALIDATE_WARN_TOO_LONG) {
- if (attrlen != pt->len)
- goto out_err;
- break;
- }
- /* fall through */
default:
if (pt->len)
minlen = pt->len;
@@ -479,9 +527,15 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
break;
case NLA_VALIDATE_RANGE_PTR:
case NLA_VALIDATE_RANGE:
+ case NLA_VALIDATE_RANGE_WARN_TOO_LONG:
case NLA_VALIDATE_MIN:
case NLA_VALIDATE_MAX:
- err = nla_validate_int_range(pt, nla, extack);
+ err = nla_validate_int_range(pt, nla, extack, validate);
+ if (err)
+ return err;
+ break;
+ case NLA_VALIDATE_MASK:
+ err = nla_validate_mask(pt, nla, extack);
if (err)
return err;
break;
@@ -496,7 +550,8 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
return 0;
out_err:
- NL_SET_ERR_MSG_ATTR(extack, nla, "Attribute failed policy validation");
+ NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+ "Attribute failed policy validation");
return err;
}
@@ -816,8 +871,7 @@ EXPORT_SYMBOL(__nla_reserve);
struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype,
int attrlen, int padattr)
{
- if (nla_need_padding_for_64bit(skb))
- nla_align_64bit(skb, padattr);
+ nla_align_64bit(skb, padattr);
return __nla_reserve(skb, attrtype, attrlen);
}