aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-06-23 09:01:01 -0500
committerLinus Torvalds <torvalds@linux-foundation.org>2022-06-23 09:01:01 -0500
commit399bd66e219e331976fe6fa6ab81a023c0c97870 (patch)
tree3c25997e22ba28bb55f6d6c2aa69276458dd7c7c
parentMerge tag 'mmc-v5.19-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc (diff)
parentnet: openvswitch: fix parsing of nw_proto for IPv6 fragments (diff)
downloadlinux-dev-399bd66e219e331976fe6fa6ab81a023c0c97870.tar.xz
linux-dev-399bd66e219e331976fe6fa6ab81a023c0c97870.zip
Merge tag 'net-5.19-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni: "Including fixes from bpf and netfilter. Current release - regressions: - netfilter: cttimeout: fix slab-out-of-bounds read in cttimeout_net_exit Current release - new code bugs: - bpf: ftrace: keep address offset in ftrace_lookup_symbols - bpf: force cookies array to follow symbols sorting Previous releases - regressions: - ipv4: ping: fix bind address validity check - tipc: fix use-after-free read in tipc_named_reinit - eth: veth: add updating of trans_start Previous releases - always broken: - sock: redo the psock vs ULP protection check - netfilter: nf_dup_netdev: fix skb_under_panic - bpf: fix request_sock leak in sk lookup helpers - eth: igb: fix a use-after-free issue in igb_clean_tx_ring - eth: ice: prohibit improper channel config for DCB - eth: at803x: fix null pointer dereference on AR9331 phy - eth: virtio_net: fix xdp_rxq_info bug after suspend/resume Misc: - eth: hinic: replace memcpy() with direct assignment" * tag 'net-5.19-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (47 commits) net: openvswitch: fix parsing of nw_proto for IPv6 fragments sock: redo the psock vs ULP protection check Revert "net/tls: fix tls_sk_proto_close executed repeatedly" virtio_net: fix xdp_rxq_info bug after suspend/resume igb: Make DMA faster when CPU is active on the PCIe link net: dsa: qca8k: reduce mgmt ethernet timeout net: dsa: qca8k: reset cpu port on MTU change MAINTAINERS: Add a maintainer for OCP Time Card hinic: Replace memcpy() with direct assignment Revert "drivers/net/ethernet/neterion/vxge: Fix a use-after-free bug in vxge-main.c" net: phy: smsc: Disable Energy Detect Power-Down in interrupt mode ice: ethtool: Prohibit improper channel config for DCB ice: ethtool: advertise 1000M speeds properly ice: Fix switchdev rules book keeping ice: ignore protocol field in GTP offload netfilter: nf_dup_netdev: add and use recursion counter netfilter: nf_dup_netdev: do not push mac header a second time selftests: netfilter: correct PKTGEN_SCRIPT_PATHS in nft_concat_range.sh net/tls: fix tls_sk_proto_close executed repeatedly erspan: do not assume transport header is always set ...
-rw-r--r--MAINTAINERS42
-rw-r--r--arch/x86/net/bpf_jit_comp.c3
-rw-r--r--drivers/net/bonding/bond_main.c4
-rw-r--r--drivers/net/dsa/qca8k.c22
-rw-r--r--drivers/net/dsa/qca8k.h2
-rw-r--r--drivers/net/ethernet/huawei/hinic/hinic_devlink.c4
-rw-r--r--drivers/net/ethernet/intel/ice/ice_ethtool.c49
-rw-r--r--drivers/net/ethernet/intel/ice/ice_lib.c42
-rw-r--r--drivers/net/ethernet/intel/ice/ice_tc_lib.c5
-rw-r--r--drivers/net/ethernet/intel/igb/igb_main.c19
-rw-r--r--drivers/net/hamradio/6pack.c9
-rw-r--r--drivers/net/phy/aquantia_main.c15
-rw-r--r--drivers/net/phy/at803x.c6
-rw-r--r--drivers/net/phy/smsc.c6
-rw-r--r--drivers/net/veth.c4
-rw-r--r--drivers/net/virtio_net.c25
-rw-r--r--include/net/inet_sock.h5
-rw-r--r--kernel/bpf/btf.c5
-rw-r--r--kernel/trace/bpf_trace.c60
-rw-r--r--kernel/trace/ftrace.c13
-rw-r--r--kernel/trace/rethook.c9
-rw-r--r--net/core/dev.c25
-rw-r--r--net/core/filter.c34
-rw-r--r--net/core/net-sysfs.c1
-rw-r--r--net/core/skmsg.c5
-rw-r--r--net/ethtool/eeprom.c2
-rw-r--r--net/ipv4/ip_gre.c15
-rw-r--r--net/ipv4/ping.c10
-rw-r--r--net/ipv4/tcp_bpf.c3
-rw-r--r--net/ipv6/ip6_gre.c15
-rw-r--r--net/netfilter/nf_dup_netdev.c25
-rw-r--r--net/netfilter/nfnetlink_cttimeout.c2
-rw-r--r--net/netfilter/nft_meta.c13
-rw-r--r--net/netfilter/nft_numgen.c12
-rw-r--r--net/openvswitch/flow.c2
-rw-r--r--net/sched/sch_netem.c4
-rw-r--r--net/tipc/core.c3
-rw-r--r--net/tls/tls_main.c2
-rw-r--r--net/xdp/xsk.c16
-rw-r--r--samples/fprobe/fprobe_example.c29
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_cookie.c78
-rw-r--r--tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c3
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tailcalls.c55
-rw-r--r--tools/testing/selftests/bpf/progs/kprobe_multi.c24
-rw-r--r--tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c42
-rwxr-xr-xtools/testing/selftests/net/fcnal-test.sh61
-rwxr-xr-xtools/testing/selftests/netfilter/nft_concat_range.sh2
47 files changed, 617 insertions, 215 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index 3cf9842d9233..6cc825857722 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3662,7 +3662,7 @@ BPF JIT for ARM
M: Shubham Bansal <illusionist.neo@gmail.com>
L: netdev@vger.kernel.org
L: bpf@vger.kernel.org
-S: Maintained
+S: Odd Fixes
F: arch/arm/net/
BPF JIT for ARM64
@@ -3686,14 +3686,15 @@ BPF JIT for NFP NICs
M: Jakub Kicinski <kuba@kernel.org>
L: netdev@vger.kernel.org
L: bpf@vger.kernel.org
-S: Supported
+S: Odd Fixes
F: drivers/net/ethernet/netronome/nfp/bpf/
BPF JIT for POWERPC (32-BIT AND 64-BIT)
M: Naveen N. Rao <naveen.n.rao@linux.ibm.com>
+M: Michael Ellerman <mpe@ellerman.id.au>
L: netdev@vger.kernel.org
L: bpf@vger.kernel.org
-S: Maintained
+S: Supported
F: arch/powerpc/net/
BPF JIT for RISC-V (32-bit)
@@ -3719,7 +3720,7 @@ M: Heiko Carstens <hca@linux.ibm.com>
M: Vasily Gorbik <gor@linux.ibm.com>
L: netdev@vger.kernel.org
L: bpf@vger.kernel.org
-S: Maintained
+S: Supported
F: arch/s390/net/
X: arch/s390/net/pnet.c
@@ -3727,14 +3728,14 @@ BPF JIT for SPARC (32-BIT AND 64-BIT)
M: David S. Miller <davem@davemloft.net>
L: netdev@vger.kernel.org
L: bpf@vger.kernel.org
-S: Maintained
+S: Odd Fixes
F: arch/sparc/net/
BPF JIT for X86 32-BIT
M: Wang YanQing <udknight@gmail.com>
L: netdev@vger.kernel.org
L: bpf@vger.kernel.org
-S: Maintained
+S: Odd Fixes
F: arch/x86/net/bpf_jit_comp32.c
BPF JIT for X86 64-BIT
@@ -3757,6 +3758,19 @@ F: include/linux/bpf_lsm.h
F: kernel/bpf/bpf_lsm.c
F: security/bpf/
+BPF L7 FRAMEWORK
+M: John Fastabend <john.fastabend@gmail.com>
+M: Jakub Sitnicki <jakub@cloudflare.com>
+L: netdev@vger.kernel.org
+L: bpf@vger.kernel.org
+S: Maintained
+F: include/linux/skmsg.h
+F: net/core/skmsg.c
+F: net/core/sock_map.c
+F: net/ipv4/tcp_bpf.c
+F: net/ipv4/udp_bpf.c
+F: net/unix/unix_bpf.c
+
BPFTOOL
M: Quentin Monnet <quentin@isovalent.com>
L: bpf@vger.kernel.org
@@ -11098,20 +11112,6 @@ S: Maintained
F: include/net/l3mdev.h
F: net/l3mdev
-L7 BPF FRAMEWORK
-M: John Fastabend <john.fastabend@gmail.com>
-M: Daniel Borkmann <daniel@iogearbox.net>
-M: Jakub Sitnicki <jakub@cloudflare.com>
-L: netdev@vger.kernel.org
-L: bpf@vger.kernel.org
-S: Maintained
-F: include/linux/skmsg.h
-F: net/core/skmsg.c
-F: net/core/sock_map.c
-F: net/ipv4/tcp_bpf.c
-F: net/ipv4/udp_bpf.c
-F: net/unix/unix_bpf.c
-
LANDLOCK SECURITY MODULE
M: Mickaël Salaün <mic@digikod.net>
L: linux-security-module@vger.kernel.org
@@ -13954,7 +13954,6 @@ F: net/ipv6/tcp*.c
NETWORKING [TLS]
M: Boris Pismenny <borisp@nvidia.com>
M: John Fastabend <john.fastabend@gmail.com>
-M: Daniel Borkmann <daniel@iogearbox.net>
M: Jakub Kicinski <kuba@kernel.org>
L: netdev@vger.kernel.org
S: Maintained
@@ -14871,6 +14870,7 @@ F: include/dt-bindings/
OPENCOMPUTE PTP CLOCK DRIVER
M: Jonathan Lemon <jonathan.lemon@gmail.com>
+M: Vadim Fedorenko <vadfed@fb.com>
L: netdev@vger.kernel.org
S: Maintained
F: drivers/ptp/ptp_ocp.c
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index f298b18a9a3d..c98b8c0ed3b8 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1420,8 +1420,9 @@ st: if (is_imm8(insn->off))
case BPF_JMP | BPF_CALL:
func = (u8 *) __bpf_call_base + imm32;
if (tail_call_reachable) {
+ /* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */
EMIT3_off32(0x48, 0x8B, 0x85,
- -(bpf_prog->aux->stack_depth + 8));
+ -round_up(bpf_prog->aux->stack_depth, 8) - 8);
if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7))
return -EINVAL;
} else {
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f85372adf042..6ba4c83fe5fc 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3684,9 +3684,11 @@ re_arm:
if (!rtnl_trylock())
return;
- if (should_notify_peers)
+ if (should_notify_peers) {
+ bond->send_peer_notif--;
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
bond->dev);
+ }
if (should_notify_rtnl) {
bond_slave_state_notify(bond);
bond_slave_link_notify(bond);
diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index 2727d3169c25..1cbb05b0323f 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -2334,6 +2334,7 @@ static int
qca8k_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
{
struct qca8k_priv *priv = ds->priv;
+ int ret;
/* We have only have a general MTU setting.
* DSA always set the CPU port's MTU to the largest MTU of the slave
@@ -2344,8 +2345,27 @@ qca8k_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
if (!dsa_is_cpu_port(ds, port))
return 0;
+ /* To change the MAX_FRAME_SIZE the cpu ports must be off or
+ * the switch panics.
+ * Turn off both cpu ports before applying the new value to prevent
+ * this.
+ */
+ if (priv->port_enabled_map & BIT(0))
+ qca8k_port_set_status(priv, 0, 0);
+
+ if (priv->port_enabled_map & BIT(6))
+ qca8k_port_set_status(priv, 6, 0);
+
/* Include L2 header / FCS length */
- return qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, new_mtu + ETH_HLEN + ETH_FCS_LEN);
+ ret = qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, new_mtu + ETH_HLEN + ETH_FCS_LEN);
+
+ if (priv->port_enabled_map & BIT(0))
+ qca8k_port_set_status(priv, 0, 1);
+
+ if (priv->port_enabled_map & BIT(6))
+ qca8k_port_set_status(priv, 6, 1);
+
+ return ret;
}
static int
diff --git a/drivers/net/dsa/qca8k.h b/drivers/net/dsa/qca8k.h
index 04408e11402a..ec58d0e80a70 100644
--- a/drivers/net/dsa/qca8k.h
+++ b/drivers/net/dsa/qca8k.h
@@ -15,7 +15,7 @@
#define QCA8K_ETHERNET_MDIO_PRIORITY 7
#define QCA8K_ETHERNET_PHY_PRIORITY 6
-#define QCA8K_ETHERNET_TIMEOUT 100
+#define QCA8K_ETHERNET_TIMEOUT 5
#define QCA8K_NUM_PORTS 7
#define QCA8K_NUM_CPU_PORTS 2
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
index 60ae8bfc5f69..1749d26f4bef 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
@@ -43,9 +43,7 @@ static bool check_image_valid(struct hinic_devlink_priv *priv, const u8 *buf,
for (i = 0; i < fw_image->fw_info.fw_section_cnt; i++) {
len += fw_image->fw_section_info[i].fw_section_len;
- memcpy(&host_image->image_section_info[i],
- &fw_image->fw_section_info[i],
- sizeof(struct fw_section_info_st));
+ host_image->image_section_info[i] = fw_image->fw_section_info[i];
}
if (len != fw_image->fw_len ||
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 1e71b70f0e52..70335f6e8524 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -2190,6 +2190,42 @@ ice_setup_autoneg(struct ice_port_info *p, struct ethtool_link_ksettings *ks,
}
/**
+ * ice_set_phy_type_from_speed - set phy_types based on speeds
+ * and advertised modes
+ * @ks: ethtool link ksettings struct
+ * @phy_type_low: pointer to the lower part of phy_type
+ * @phy_type_high: pointer to the higher part of phy_type
+ * @adv_link_speed: targeted link speeds bitmap
+ */
+static void
+ice_set_phy_type_from_speed(const struct ethtool_link_ksettings *ks,
+ u64 *phy_type_low, u64 *phy_type_high,
+ u16 adv_link_speed)
+{
+ /* Handle 1000M speed in a special way because ice_update_phy_type
+ * enables all link modes, but having mixed copper and optical
+ * standards is not supported.
+ */
+ adv_link_speed &= ~ICE_AQ_LINK_SPEED_1000MB;
+
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 1000baseT_Full))
+ *phy_type_low |= ICE_PHY_TYPE_LOW_1000BASE_T |
+ ICE_PHY_TYPE_LOW_1G_SGMII;
+
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 1000baseKX_Full))
+ *phy_type_low |= ICE_PHY_TYPE_LOW_1000BASE_KX;
+
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 1000baseX_Full))
+ *phy_type_low |= ICE_PHY_TYPE_LOW_1000BASE_SX |
+ ICE_PHY_TYPE_LOW_1000BASE_LX;
+
+ ice_update_phy_type(phy_type_low, phy_type_high, adv_link_speed);
+}
+
+/**
* ice_set_link_ksettings - Set Speed and Duplex
* @netdev: network interface device structure
* @ks: ethtool ksettings
@@ -2320,7 +2356,8 @@ ice_set_link_ksettings(struct net_device *netdev,
adv_link_speed = curr_link_speed;
/* Convert the advertise link speeds to their corresponded PHY_TYPE */
- ice_update_phy_type(&phy_type_low, &phy_type_high, adv_link_speed);
+ ice_set_phy_type_from_speed(ks, &phy_type_low, &phy_type_high,
+ adv_link_speed);
if (!autoneg_changed && adv_link_speed == curr_link_speed) {
netdev_info(netdev, "Nothing changed, exiting without setting anything.\n");
@@ -3470,6 +3507,16 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch)
new_rx = ch->combined_count + ch->rx_count;
new_tx = ch->combined_count + ch->tx_count;
+ if (new_rx < vsi->tc_cfg.numtc) {
+ netdev_err(dev, "Cannot set less Rx channels, than Traffic Classes you have (%u)\n",
+ vsi->tc_cfg.numtc);
+ return -EINVAL;
+ }
+ if (new_tx < vsi->tc_cfg.numtc) {
+ netdev_err(dev, "Cannot set less Tx channels, than Traffic Classes you have (%u)\n",
+ vsi->tc_cfg.numtc);
+ return -EINVAL;
+ }
if (new_rx > ice_get_max_rxq(pf)) {
netdev_err(dev, "Maximum allowed Rx channels is %d\n",
ice_get_max_rxq(pf));
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 454e01ae09b9..f7f9c973ec54 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -909,7 +909,7 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt)
* @vsi: the VSI being configured
* @ctxt: VSI context structure
*/
-static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
+static int ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
{
u16 offset = 0, qmap = 0, tx_count = 0, pow = 0;
u16 num_txq_per_tc, num_rxq_per_tc;
@@ -982,7 +982,18 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
else
vsi->num_rxq = num_rxq_per_tc;
+ if (vsi->num_rxq > vsi->alloc_rxq) {
+ dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Rx queues (%u), than were allocated (%u)!\n",
+ vsi->num_rxq, vsi->alloc_rxq);
+ return -EINVAL;
+ }
+
vsi->num_txq = tx_count;
+ if (vsi->num_txq > vsi->alloc_txq) {
+ dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Tx queues (%u), than were allocated (%u)!\n",
+ vsi->num_txq, vsi->alloc_txq);
+ return -EINVAL;
+ }
if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) {
dev_dbg(ice_pf_to_dev(vsi->back), "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n");
@@ -1000,6 +1011,8 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
*/
ctxt->info.q_mapping[0] = cpu_to_le16(vsi->rxq_map[0]);
ctxt->info.q_mapping[1] = cpu_to_le16(vsi->num_rxq);
+
+ return 0;
}
/**
@@ -1187,7 +1200,10 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi)
if (vsi->type == ICE_VSI_CHNL) {
ice_chnl_vsi_setup_q_map(vsi, ctxt);
} else {
- ice_vsi_setup_q_map(vsi, ctxt);
+ ret = ice_vsi_setup_q_map(vsi, ctxt);
+ if (ret)
+ goto out;
+
if (!init_vsi) /* means VSI being updated */
/* must to indicate which section of VSI context are
* being modified
@@ -3464,7 +3480,7 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc)
*
* Prepares VSI tc_config to have queue configurations based on MQPRIO options.
*/
-static void
+static int
ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt,
u8 ena_tc)
{
@@ -3513,7 +3529,18 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt,
/* Set actual Tx/Rx queue pairs */
vsi->num_txq = offset + qcount_tx;
+ if (vsi->num_txq > vsi->alloc_txq) {
+ dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Tx queues (%u), than were allocated (%u)!\n",
+ vsi->num_txq, vsi->alloc_txq);
+ return -EINVAL;
+ }
+
vsi->num_rxq = offset + qcount_rx;
+ if (vsi->num_rxq > vsi->alloc_rxq) {
+ dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Rx queues (%u), than were allocated (%u)!\n",
+ vsi->num_rxq, vsi->alloc_rxq);
+ return -EINVAL;
+ }
/* Setup queue TC[0].qmap for given VSI context */
ctxt->info.tc_mapping[0] = cpu_to_le16(qmap);
@@ -3531,6 +3558,8 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt,
dev_dbg(ice_pf_to_dev(vsi->back), "vsi->num_rxq = %d\n", vsi->num_rxq);
dev_dbg(ice_pf_to_dev(vsi->back), "all_numtc %u, all_enatc: 0x%04x, tc_cfg.numtc %u\n",
vsi->all_numtc, vsi->all_enatc, vsi->tc_cfg.numtc);
+
+ return 0;
}
/**
@@ -3580,9 +3609,12 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc)
if (vsi->type == ICE_VSI_PF &&
test_bit(ICE_FLAG_TC_MQPRIO, pf->flags))
- ice_vsi_setup_q_map_mqprio(vsi, ctx, ena_tc);
+ ret = ice_vsi_setup_q_map_mqprio(vsi, ctx, ena_tc);
else
- ice_vsi_setup_q_map(vsi, ctx);
+ ret = ice_vsi_setup_q_map(vsi, ctx);
+
+ if (ret)
+ goto out;
/* must to indicate which section of VSI context are being modified */
ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID);
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index 0a0c55fb8699..b803f2ab3cc7 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -524,6 +524,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
*/
fltr->rid = rule_added.rid;
fltr->rule_id = rule_added.rule_id;
+ fltr->dest_id = rule_added.vsi_handle;
exit:
kfree(list);
@@ -993,7 +994,9 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
n_proto_key = ntohs(match.key->n_proto);
n_proto_mask = ntohs(match.mask->n_proto);
- if (n_proto_key == ETH_P_ALL || n_proto_key == 0) {
+ if (n_proto_key == ETH_P_ALL || n_proto_key == 0 ||
+ fltr->tunnel_type == TNL_GTPU ||
+ fltr->tunnel_type == TNL_GTPC) {
n_proto_key = 0;
n_proto_mask = 0;
} else {
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 68be2976f539..c5f04c40284b 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -4819,8 +4819,11 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring)
while (i != tx_ring->next_to_use) {
union e1000_adv_tx_desc *eop_desc, *tx_desc;
- /* Free all the Tx ring sk_buffs */
- dev_kfree_skb_any(tx_buffer->skb);
+ /* Free all the Tx ring sk_buffs or xdp frames */
+ if (tx_buffer->type == IGB_TYPE_SKB)
+ dev_kfree_skb_any(tx_buffer->skb);
+ else
+ xdp_return_frame(tx_buffer->xdpf);
/* unmap skb header data */
dma_unmap_single(tx_ring->dev,
@@ -9898,11 +9901,10 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba)
struct e1000_hw *hw = &adapter->hw;
u32 dmac_thr;
u16 hwm;
+ u32 reg;
if (hw->mac.type > e1000_82580) {
if (adapter->flags & IGB_FLAG_DMAC) {
- u32 reg;
-
/* force threshold to 0. */
wr32(E1000_DMCTXTH, 0);
@@ -9935,7 +9937,6 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba)
/* Disable BMC-to-OS Watchdog Enable */
if (hw->mac.type != e1000_i354)
reg &= ~E1000_DMACR_DC_BMC2OSW_EN;
-
wr32(E1000_DMACR, reg);
/* no lower threshold to disable
@@ -9952,12 +9953,12 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba)
*/
wr32(E1000_DMCTXTH, (IGB_MIN_TXPBSIZE -
(IGB_TX_BUF_4096 + adapter->max_frame_size)) >> 6);
+ }
- /* make low power state decision controlled
- * by DMA coal
- */
+ if (hw->mac.type >= e1000_i210 ||
+ (adapter->flags & IGB_FLAG_DMAC)) {
reg = rd32(E1000_PCIEMISC);
- reg &= ~E1000_PCIEMISC_LX_DECISION;
+ reg |= E1000_PCIEMISC_LX_DECISION;
wr32(E1000_PCIEMISC, reg);
} /* endif adapter->dmac is not disabled */
} else if (hw->mac.type == e1000_82580) {
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 45c3c4a1101b..9fb567524220 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -99,6 +99,7 @@ struct sixpack {
unsigned int rx_count;
unsigned int rx_count_cooked;
+ spinlock_t rxlock;
int mtu; /* Our mtu (to spot changes!) */
int buffsize; /* Max buffers sizes */
@@ -565,6 +566,7 @@ static int sixpack_open(struct tty_struct *tty)
sp->dev = dev;
spin_lock_init(&sp->lock);
+ spin_lock_init(&sp->rxlock);
refcount_set(&sp->refcnt, 1);
init_completion(&sp->dead);
@@ -913,6 +915,7 @@ static void decode_std_command(struct sixpack *sp, unsigned char cmd)
sp->led_state = 0x60;
/* fill trailing bytes with zeroes */
sp->tty->ops->write(sp->tty, &sp->led_state, 1);
+ spin_lock_bh(&sp->rxlock);
rest = sp->rx_count;
if (rest != 0)
for (i = rest; i <= 3; i++)
@@ -930,6 +933,7 @@ static void decode_std_command(struct sixpack *sp, unsigned char cmd)
sp_bump(sp, 0);
}
sp->rx_count_cooked = 0;
+ spin_unlock_bh(&sp->rxlock);
}
break;
case SIXP_TX_URUN: printk(KERN_DEBUG "6pack: TX underrun\n");
@@ -959,8 +963,11 @@ sixpack_decode(struct sixpack *sp, const unsigned char *pre_rbuff, int count)
decode_prio_command(sp, inbyte);
else if ((inbyte & SIXP_STD_CMD_MASK) != 0)
decode_std_command(sp, inbyte);
- else if ((sp->status & SIXP_RX_DCD_MASK) == SIXP_RX_DCD_MASK)
+ else if ((sp->status & SIXP_RX_DCD_MASK) == SIXP_RX_DCD_MASK) {
+ spin_lock_bh(&sp->rxlock);
decode_data(sp, inbyte);
+ spin_unlock_bh(&sp->rxlock);
+ }
}
}
diff --git a/drivers/net/phy/aquantia_main.c b/drivers/net/phy/aquantia_main.c
index a8db1a19011b..c7047f5d7a9b 100644
--- a/drivers/net/phy/aquantia_main.c
+++ b/drivers/net/phy/aquantia_main.c
@@ -34,6 +34,8 @@
#define MDIO_AN_VEND_PROV 0xc400
#define MDIO_AN_VEND_PROV_1000BASET_FULL BIT(15)
#define MDIO_AN_VEND_PROV_1000BASET_HALF BIT(14)
+#define MDIO_AN_VEND_PROV_5000BASET_FULL BIT(11)
+#define MDIO_AN_VEND_PROV_2500BASET_FULL BIT(10)
#define MDIO_AN_VEND_PROV_DOWNSHIFT_EN BIT(4)
#define MDIO_AN_VEND_PROV_DOWNSHIFT_MASK GENMASK(3, 0)
#define MDIO_AN_VEND_PROV_DOWNSHIFT_DFLT 4
@@ -231,9 +233,20 @@ static int aqr_config_aneg(struct phy_device *phydev)
phydev->advertising))
reg |= MDIO_AN_VEND_PROV_1000BASET_HALF;
+ /* Handle the case when the 2.5G and 5G speeds are not advertised */
+ if (linkmode_test_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
+ phydev->advertising))
+ reg |= MDIO_AN_VEND_PROV_2500BASET_FULL;
+
+ if (linkmode_test_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
+ phydev->advertising))
+ reg |= MDIO_AN_VEND_PROV_5000BASET_FULL;
+
ret = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MDIO_AN_VEND_PROV,
MDIO_AN_VEND_PROV_1000BASET_HALF |
- MDIO_AN_VEND_PROV_1000BASET_FULL, reg);
+ MDIO_AN_VEND_PROV_1000BASET_FULL |
+ MDIO_AN_VEND_PROV_2500BASET_FULL |
+ MDIO_AN_VEND_PROV_5000BASET_FULL, reg);
if (ret < 0)
return ret;
if (ret > 0)
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 6a467e7817a6..59fe356942b5 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -2072,6 +2072,8 @@ static struct phy_driver at803x_driver[] = {
/* ATHEROS AR9331 */
PHY_ID_MATCH_EXACT(ATH9331_PHY_ID),
.name = "Qualcomm Atheros AR9331 built-in PHY",
+ .probe = at803x_probe,
+ .remove = at803x_remove,
.suspend = at803x_suspend,
.resume = at803x_resume,
.flags = PHY_POLL_CABLE_TEST,
@@ -2087,6 +2089,8 @@ static struct phy_driver at803x_driver[] = {
/* Qualcomm Atheros QCA9561 */
PHY_ID_MATCH_EXACT(QCA9561_PHY_ID),
.name = "Qualcomm Atheros QCA9561 built-in PHY",
+ .probe = at803x_probe,
+ .remove = at803x_remove,
.suspend = at803x_suspend,
.resume = at803x_resume,
.flags = PHY_POLL_CABLE_TEST,
@@ -2151,6 +2155,8 @@ static struct phy_driver at803x_driver[] = {
PHY_ID_MATCH_EXACT(QCA8081_PHY_ID),
.name = "Qualcomm QCA8081",
.flags = PHY_POLL_CABLE_TEST,
+ .probe = at803x_probe,
+ .remove = at803x_remove,
.config_intr = at803x_config_intr,
.handle_interrupt = at803x_handle_interrupt,
.get_tunable = at803x_get_tunable,
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 1b54684b68a0..96d3c40932d8 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -110,7 +110,7 @@ static int smsc_phy_config_init(struct phy_device *phydev)
struct smsc_phy_priv *priv = phydev->priv;
int rc;
- if (!priv->energy_enable)
+ if (!priv->energy_enable || phydev->irq != PHY_POLL)
return 0;
rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS);
@@ -210,6 +210,8 @@ static int lan95xx_config_aneg_ext(struct phy_device *phydev)
* response on link pulses to detect presence of plugged Ethernet cable.
* The Energy Detect Power-Down mode is enabled again in the end of procedure to
* save approximately 220 mW of power if cable is unplugged.
+ * The workaround is only applicable to poll mode. Energy Detect Power-Down may
+ * not be used in interrupt mode lest link change detection becomes unreliable.
*/
static int lan87xx_read_status(struct phy_device *phydev)
{
@@ -217,7 +219,7 @@ static int lan87xx_read_status(struct phy_device *phydev)
int err = genphy_read_status(phydev);
- if (!phydev->link && priv->energy_enable) {
+ if (!phydev->link && priv->energy_enable && phydev->irq == PHY_POLL) {
/* Disable EDPD to wake up PHY */
int rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS);
if (rc < 0)
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 466da01ba2e3..2cb833b3006a 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -312,6 +312,7 @@ static bool veth_skb_is_eligible_for_gro(const struct net_device *dev,
static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
+ struct netdev_queue *queue = NULL;
struct veth_rq *rq = NULL;
struct net_device *rcv;
int length = skb->len;
@@ -329,6 +330,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
rxq = skb_get_queue_mapping(skb);
if (rxq < rcv->real_num_rx_queues) {
rq = &rcv_priv->rq[rxq];
+ queue = netdev_get_tx_queue(dev, rxq);
/* The napi pointer is available when an XDP program is
* attached or when GRO is enabled
@@ -340,6 +342,8 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
skb_tx_timestamp(skb);
if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) {
+ if (queue)
+ txq_trans_cond_update(queue);
if (!use_napi)
dev_lstats_add(dev, length);
} else {
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index db05b5e930be..969a67970e71 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2768,7 +2768,6 @@ static const struct ethtool_ops virtnet_ethtool_ops = {
static void virtnet_freeze_down(struct virtio_device *vdev)
{
struct virtnet_info *vi = vdev->priv;
- int i;
/* Make sure no work handler is accessing the device */
flush_work(&vi->config_work);
@@ -2776,14 +2775,8 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
netif_tx_lock_bh(vi->dev);
netif_device_detach(vi->dev);
netif_tx_unlock_bh(vi->dev);
- cancel_delayed_work_sync(&vi->refill);
-
- if (netif_running(vi->dev)) {
- for (i = 0; i < vi->max_queue_pairs; i++) {
- napi_disable(&vi->rq[i].napi);
- virtnet_napi_tx_disable(&vi->sq[i].napi);
- }
- }
+ if (netif_running(vi->dev))
+ virtnet_close(vi->dev);
}
static int init_vqs(struct virtnet_info *vi);
@@ -2791,7 +2784,7 @@ static int init_vqs(struct virtnet_info *vi);
static int virtnet_restore_up(struct virtio_device *vdev)
{
struct virtnet_info *vi = vdev->priv;
- int err, i;
+ int err;
err = init_vqs(vi);
if (err)
@@ -2800,15 +2793,9 @@ static int virtnet_restore_up(struct virtio_device *vdev)
virtio_device_ready(vdev);
if (netif_running(vi->dev)) {
- for (i = 0; i < vi->curr_queue_pairs; i++)
- if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
- schedule_delayed_work(&vi->refill, 0);
-
- for (i = 0; i < vi->max_queue_pairs; i++) {
- virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
- virtnet_napi_tx_enable(vi, vi->sq[i].vq,
- &vi->sq[i].napi);
- }
+ err = virtnet_open(vi->dev);
+ if (err)
+ return err;
}
netif_tx_lock_bh(vi->dev);
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index c1b5dcd6597c..daead5fb389a 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -253,6 +253,11 @@ struct inet_sock {
#define IP_CMSG_CHECKSUM BIT(7)
#define IP_CMSG_RECVFRAGSIZE BIT(8)
+static inline bool sk_is_inet(struct sock *sk)
+{
+ return sk->sk_family == AF_INET || sk->sk_family == AF_INET6;
+}
+
/**
* sk_to_full_sk - Access to a full socket
* @sk: pointer to a socket
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 63d0ac7dfe2f..eb12d4f705cc 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4815,6 +4815,7 @@ static int btf_check_type_tags(struct btf_verifier_env *env,
n = btf_nr_types(btf);
for (i = start_id; i < n; i++) {
const struct btf_type *t;
+ int chain_limit = 32;
u32 cur_id = i;
t = btf_type_by_id(btf, i);
@@ -4827,6 +4828,10 @@ static int btf_check_type_tags(struct btf_verifier_env *env,
in_tags = btf_type_is_type_tag(t);
while (btf_type_is_modifier(t)) {
+ if (!chain_limit--) {
+ btf_verifier_log(env, "Max chain length or cycle detected");
+ return -ELOOP;
+ }
if (btf_type_is_type_tag(t)) {
if (!in_tags) {
btf_verifier_log(env, "Type tags don't precede modifiers");
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7a13e6ac6327..88589d74a892 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2423,7 +2423,7 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip,
kprobe_multi_link_prog_run(link, entry_ip, regs);
}
-static int symbols_cmp(const void *a, const void *b)
+static int symbols_cmp_r(const void *a, const void *b, const void *priv)
{
const char **str_a = (const char **) a;
const char **str_b = (const char **) b;
@@ -2431,6 +2431,28 @@ static int symbols_cmp(const void *a, const void *b)
return strcmp(*str_a, *str_b);
}
+struct multi_symbols_sort {
+ const char **funcs;
+ u64 *cookies;
+};
+
+static void symbols_swap_r(void *a, void *b, int size, const void *priv)
+{
+ const struct multi_symbols_sort *data = priv;
+ const char **name_a = a, **name_b = b;
+
+ swap(*name_a, *name_b);
+
+ /* If defined, swap also related cookies. */
+ if (data->cookies) {
+ u64 *cookie_a, *cookie_b;
+
+ cookie_a = data->cookies + (name_a - data->funcs);
+ cookie_b = data->cookies + (name_b - data->funcs);
+ swap(*cookie_a, *cookie_b);
+ }
+}
+
int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
struct bpf_kprobe_multi_link *link = NULL;
@@ -2468,38 +2490,46 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
if (!addrs)
return -ENOMEM;
+ ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies);
+ if (ucookies) {
+ cookies = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
+ if (!cookies) {
+ err = -ENOMEM;
+ goto error;
+ }
+ if (copy_from_user(cookies, ucookies, size)) {
+ err = -EFAULT;
+ goto error;
+ }
+ }
+
if (uaddrs) {
if (copy_from_user(addrs, uaddrs, size)) {
err = -EFAULT;
goto error;
}
} else {
+ struct multi_symbols_sort data = {
+ .cookies = cookies,
+ };
struct user_syms us;
err = copy_user_syms(&us, usyms, cnt);
if (err)
goto error;
- sort(us.syms, cnt, sizeof(*us.syms), symbols_cmp, NULL);
+ if (cookies)
+ data.funcs = us.syms;
+
+ sort_r(us.syms, cnt, sizeof(*us.syms), symbols_cmp_r,
+ symbols_swap_r, &data);
+
err = ftrace_lookup_symbols(us.syms, cnt, addrs);
free_user_syms(&us);
if (err)
goto error;
}
- ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies);
- if (ucookies) {
- cookies = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
- if (!cookies) {
- err = -ENOMEM;
- goto error;
- }
- if (copy_from_user(cookies, ucookies, size)) {
- err = -EFAULT;
- goto error;
- }
- }
-
link = kzalloc(sizeof(*link), GFP_KERNEL);
if (!link) {
err = -ENOMEM;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index e750fe141a60..601ccf1b2f09 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -8029,15 +8029,23 @@ static int kallsyms_callback(void *data, const char *name,
struct module *mod, unsigned long addr)
{
struct kallsyms_data *args = data;
+ const char **sym;
+ int idx;
- if (!bsearch(&name, args->syms, args->cnt, sizeof(*args->syms), symbols_cmp))
+ sym = bsearch(&name, args->syms, args->cnt, sizeof(*args->syms), symbols_cmp);
+ if (!sym)
+ return 0;
+
+ idx = sym - args->syms;
+ if (args->addrs[idx])
return 0;
addr = ftrace_location(addr);
if (!addr)
return 0;
- args->addrs[args->found++] = addr;
+ args->addrs[idx] = addr;
+ args->found++;
return args->found == args->cnt ? 1 : 0;
}
@@ -8062,6 +8070,7 @@ int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *a
struct kallsyms_data args;
int err;
+ memset(addrs, 0, sizeof(*addrs) * cnt);
args.addrs = addrs;
args.syms = sorted_syms;
args.cnt = cnt;
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index b56833700d23..c69d82273ce7 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -154,6 +154,15 @@ struct rethook_node *rethook_try_get(struct rethook *rh)
if (unlikely(!handler))
return NULL;
+ /*
+ * This expects the caller will set up a rethook on a function entry.
+ * When the function returns, the rethook will eventually be reclaimed
+ * or released in the rethook_recycle() with call_rcu().
+ * This means the caller must be run in the RCU-availabe context.
+ */
+ if (unlikely(!rcu_is_watching()))
+ return NULL;
+
fn = freelist_try_get(&rh->pool);
if (!fn)
return NULL;
diff --git a/net/core/dev.c b/net/core/dev.c
index 08ce317fcec8..8e6f22961206 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -397,16 +397,18 @@ static void list_netdevice(struct net_device *dev)
/* Device list removal
* caller must respect a RCU grace period before freeing/reusing dev
*/
-static void unlist_netdevice(struct net_device *dev)
+static void unlist_netdevice(struct net_device *dev, bool lock)
{
ASSERT_RTNL();
/* Unlink dev from the device chain */
- write_lock(&dev_base_lock);
+ if (lock)
+ write_lock(&dev_base_lock);
list_del_rcu(&dev->dev_list);
netdev_name_node_del(dev->name_node);
hlist_del_rcu(&dev->index_hlist);
- write_unlock(&dev_base_lock);
+ if (lock)
+ write_unlock(&dev_base_lock);
dev_base_seq_inc(dev_net(dev));
}
@@ -10043,11 +10045,11 @@ int register_netdevice(struct net_device *dev)
goto err_uninit;
ret = netdev_register_kobject(dev);
- if (ret) {
- dev->reg_state = NETREG_UNREGISTERED;
+ write_lock(&dev_base_lock);
+ dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED;
+ write_unlock(&dev_base_lock);
+ if (ret)
goto err_uninit;
- }
- dev->reg_state = NETREG_REGISTERED;
__netdev_update_features(dev);
@@ -10329,7 +10331,9 @@ void netdev_run_todo(void)
continue;
}
+ write_lock(&dev_base_lock);
dev->reg_state = NETREG_UNREGISTERED;
+ write_unlock(&dev_base_lock);
linkwatch_forget_dev(dev);
}
@@ -10810,9 +10814,10 @@ void unregister_netdevice_many(struct list_head *head)
list_for_each_entry(dev, head, unreg_list) {
/* And unlink it from device chain. */
- unlist_netdevice(dev);
-
+ write_lock(&dev_base_lock);
+ unlist_netdevice(dev, false);
dev->reg_state = NETREG_UNREGISTERING;
+ write_unlock(&dev_base_lock);
}
flush_all_backlogs();
@@ -10959,7 +10964,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
dev_close(dev);
/* And unlink it from device chain */
- unlist_netdevice(dev);
+ unlist_netdevice(dev, true);
synchronize_net();
diff --git a/net/core/filter.c b/net/core/filter.c
index 5af58eb48587..5d16d66727fc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6516,10 +6516,21 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
ifindex, proto, netns_id, flags);
if (sk) {
- sk = sk_to_full_sk(sk);
- if (!sk_fullsock(sk)) {
+ struct sock *sk2 = sk_to_full_sk(sk);
+
+ /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk
+ * sock refcnt is decremented to prevent a request_sock leak.
+ */
+ if (!sk_fullsock(sk2))
+ sk2 = NULL;
+ if (sk2 != sk) {
sock_gen_put(sk);
- return NULL;
+ /* Ensure there is no need to bump sk2 refcnt */
+ if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) {
+ WARN_ONCE(1, "Found non-RCU, unreferenced socket!");
+ return NULL;
+ }
+ sk = sk2;
}
}
@@ -6553,10 +6564,21 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
flags);
if (sk) {
- sk = sk_to_full_sk(sk);
- if (!sk_fullsock(sk)) {
+ struct sock *sk2 = sk_to_full_sk(sk);
+
+ /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk
+ * sock refcnt is decremented to prevent a request_sock leak.
+ */
+ if (!sk_fullsock(sk2))
+ sk2 = NULL;
+ if (sk2 != sk) {
sock_gen_put(sk);
- return NULL;
+ /* Ensure there is no need to bump sk2 refcnt */
+ if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) {
+ WARN_ONCE(1, "Found non-RCU, unreferenced socket!");
+ return NULL;
+ }
+ sk = sk2;
}
}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index e319e242dddf..a3642569fe53 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -33,6 +33,7 @@ static const char fmt_dec[] = "%d\n";
static const char fmt_ulong[] = "%lu\n";
static const char fmt_u64[] = "%llu\n";
+/* Caller holds RTNL or dev_base_lock */
static inline int dev_isalive(const struct net_device *dev)
{
return dev->reg_state <= NETREG_REGISTERED;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 22b983ade0e7..b0fcd0200e84 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -699,6 +699,11 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
write_lock_bh(&sk->sk_callback_lock);
+ if (sk_is_inet(sk) && inet_csk_has_ulp(sk)) {
+ psock = ERR_PTR(-EINVAL);
+ goto out;
+ }
+
if (sk->sk_user_data) {
psock = ERR_PTR(-EBUSY);
goto out;
diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c
index 7e6b37a54add..1c94bb8ea03f 100644
--- a/net/ethtool/eeprom.c
+++ b/net/ethtool/eeprom.c
@@ -36,7 +36,7 @@ static int fallback_set_params(struct eeprom_req_info *request,
if (request->page)
offset = request->page * ETH_MODULE_EEPROM_PAGE_LEN + offset;
- if (modinfo->type == ETH_MODULE_SFF_8079 &&
+ if (modinfo->type == ETH_MODULE_SFF_8472 &&
request->i2c_address == 0x51)
offset += ETH_MODULE_EEPROM_PAGE_LEN * 2;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 3b9cd487075a..5c58e21f724e 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -524,7 +524,6 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
int tunnel_hlen;
int version;
int nhoff;
- int thoff;
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
@@ -558,10 +557,16 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
(ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff))
truncate = true;
- thoff = skb_transport_header(skb) - skb_mac_header(skb);
- if (skb->protocol == htons(ETH_P_IPV6) &&
- (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff))
- truncate = true;
+ if (skb->protocol == htons(ETH_P_IPV6)) {
+ int thoff;
+
+ if (skb_transport_header_was_set(skb))
+ thoff = skb_transport_header(skb) - skb_mac_header(skb);
+ else
+ thoff = nhoff + sizeof(struct ipv6hdr);
+ if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)
+ truncate = true;
+ }
if (version == 1) {
erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)),
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 1a43ca73f94d..3c6101def7d6 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -319,12 +319,16 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));
+ if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
+ return 0;
+
tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id;
chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);
- if (!inet_addr_valid_or_nonlocal(net, inet_sk(sk),
- addr->sin_addr.s_addr,
- chk_addr_ret))
+ if (chk_addr_ret == RTN_MULTICAST ||
+ chk_addr_ret == RTN_BROADCAST ||
+ (chk_addr_ret != RTN_LOCAL &&
+ !inet_can_nonlocal_bind(net, isk)))
return -EADDRNOTAVAIL;
#if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index be3947e70fec..0d3f68bb51c0 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -611,9 +611,6 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
return 0;
}
- if (inet_csk_has_ulp(sk))
- return -EINVAL;
-
if (sk->sk_family == AF_INET6) {
if (tcp_bpf_assert_proto_ops(psock->sk_proto))
return -EINVAL;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 4e37f7c29900..a9051df0625d 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -939,7 +939,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
__be16 proto;
__u32 mtu;
int nhoff;
- int thoff;
if (!pskb_inet_may_pull(skb))
goto tx_err;
@@ -960,10 +959,16 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
(ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff))
truncate = true;
- thoff = skb_transport_header(skb) - skb_mac_header(skb);
- if (skb->protocol == htons(ETH_P_IPV6) &&
- (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff))
- truncate = true;
+ if (skb->protocol == htons(ETH_P_IPV6)) {
+ int thoff;
+
+ if (skb_transport_header_was_set(skb))
+ thoff = skb_transport_header(skb) - skb_mac_header(skb);
+ else
+ thoff = nhoff + sizeof(struct ipv6hdr);
+ if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)
+ truncate = true;
+ }
if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen))
goto tx_err;
diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c
index 7873bd1389c3..a8e2425e43b0 100644
--- a/net/netfilter/nf_dup_netdev.c
+++ b/net/netfilter/nf_dup_netdev.c
@@ -13,14 +13,31 @@
#include <net/netfilter/nf_tables_offload.h>
#include <net/netfilter/nf_dup_netdev.h>
-static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev)
+#define NF_RECURSION_LIMIT 2
+
+static DEFINE_PER_CPU(u8, nf_dup_skb_recursion);
+
+static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev,
+ enum nf_dev_hooks hook)
{
- if (skb_mac_header_was_set(skb))
+ if (__this_cpu_read(nf_dup_skb_recursion) > NF_RECURSION_LIMIT)
+ goto err;
+
+ if (hook == NF_NETDEV_INGRESS && skb_mac_header_was_set(skb)) {
+ if (skb_cow_head(skb, skb->mac_len))
+ goto err;
+
skb_push(skb, skb->mac_len);
+ }
skb->dev = dev;
skb_clear_tstamp(skb);
+ __this_cpu_inc(nf_dup_skb_recursion);
dev_queue_xmit(skb);
+ __this_cpu_dec(nf_dup_skb_recursion);
+ return;
+err:
+ kfree_skb(skb);
}
void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif)
@@ -33,7 +50,7 @@ void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif)
return;
}
- nf_do_netdev_egress(pkt->skb, dev);
+ nf_do_netdev_egress(pkt->skb, dev, nft_hook(pkt));
}
EXPORT_SYMBOL_GPL(nf_fwd_netdev_egress);
@@ -48,7 +65,7 @@ void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif)
skb = skb_clone(pkt->skb, GFP_ATOMIC);
if (skb)
- nf_do_netdev_egress(skb, dev);
+ nf_do_netdev_egress(skb, dev, nft_hook(pkt));
}
EXPORT_SYMBOL_GPL(nf_dup_netdev_egress);
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index af15102bc696..f466af4f8531 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -614,7 +614,7 @@ static void __net_exit cttimeout_net_exit(struct net *net)
nf_ct_untimeout(net, NULL);
- list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_freelist, head) {
+ list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_freelist, free_head) {
list_del(&cur->free_head);
if (refcount_dec_and_test(&cur->refcnt))
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index ac4859241e17..55d2d49c3425 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -14,6 +14,7 @@
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
+#include <linux/random.h>
#include <linux/smp.h>
#include <linux/static_key.h>
#include <net/dst.h>
@@ -32,8 +33,6 @@
#define NFT_META_SECS_PER_DAY 86400
#define NFT_META_DAYS_PER_WEEK 7
-static DEFINE_PER_CPU(struct rnd_state, nft_prandom_state);
-
static u8 nft_meta_weekday(void)
{
time64_t secs = ktime_get_real_seconds();
@@ -271,13 +270,6 @@ static bool nft_meta_get_eval_ifname(enum nft_meta_keys key, u32 *dest,
return true;
}
-static noinline u32 nft_prandom_u32(void)
-{
- struct rnd_state *state = this_cpu_ptr(&nft_prandom_state);
-
- return prandom_u32_state(state);
-}
-
#ifdef CONFIG_IP_ROUTE_CLASSID
static noinline bool
nft_meta_get_eval_rtclassid(const struct sk_buff *skb, u32 *dest)
@@ -389,7 +381,7 @@ void nft_meta_get_eval(const struct nft_expr *expr,
break;
#endif
case NFT_META_PRANDOM:
- *dest = nft_prandom_u32();
+ *dest = get_random_u32();
break;
#ifdef CONFIG_XFRM
case NFT_META_SECPATH:
@@ -518,7 +510,6 @@ int nft_meta_get_init(const struct nft_ctx *ctx,
len = IFNAMSIZ;
break;
case NFT_META_PRANDOM:
- prandom_init_once(&nft_prandom_state);
len = sizeof(u32);
break;
#ifdef CONFIG_XFRM
diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c
index 81b40c663d86..45d3dc9e96f2 100644
--- a/net/netfilter/nft_numgen.c
+++ b/net/netfilter/nft_numgen.c
@@ -9,12 +9,11 @@
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
+#include <linux/random.h>
#include <linux/static_key.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables_core.h>
-static DEFINE_PER_CPU(struct rnd_state, nft_numgen_prandom_state);
-
struct nft_ng_inc {
u8 dreg;
u32 modulus;
@@ -135,12 +134,9 @@ struct nft_ng_random {
u32 offset;
};
-static u32 nft_ng_random_gen(struct nft_ng_random *priv)
+static u32 nft_ng_random_gen(const struct nft_ng_random *priv)
{
- struct rnd_state *state = this_cpu_ptr(&nft_numgen_prandom_state);
-
- return reciprocal_scale(prandom_u32_state(state), priv->modulus) +
- priv->offset;
+ return reciprocal_scale(get_random_u32(), priv->modulus) + priv->offset;
}
static void nft_ng_random_eval(const struct nft_expr *expr,
@@ -168,8 +164,6 @@ static int nft_ng_random_init(const struct nft_ctx *ctx,
if (priv->offset + priv->modulus - 1 < priv->offset)
return -EOVERFLOW;
- prandom_init_once(&nft_numgen_prandom_state);
-
return nft_parse_register_store(ctx, tb[NFTA_NG_DREG], &priv->dreg,
NULL, NFT_DATA_VALUE, sizeof(u32));
}
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 372bf54a0ca9..e20d1a973417 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -407,7 +407,7 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
if (flags & IP6_FH_F_FRAG) {
if (frag_off) {
key->ip.frag = OVS_FRAG_TYPE_LATER;
- key->ip.proto = nexthdr;
+ key->ip.proto = NEXTHDR_FRAGMENT;
return 0;
}
key->ip.frag = OVS_FRAG_TYPE_FIRST;
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index ed4ccef5d6a8..5449ed114e40 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -1146,9 +1146,9 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
struct tc_netem_rate rate;
struct tc_netem_slot slot;
- qopt.latency = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->latency),
+ qopt.latency = min_t(psched_time_t, PSCHED_NS2TICKS(q->latency),
UINT_MAX);
- qopt.jitter = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->jitter),
+ qopt.jitter = min_t(psched_time_t, PSCHED_NS2TICKS(q->jitter),
UINT_MAX);
qopt.limit = q->limit;
qopt.loss = q->loss;
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 3f4542e0f065..434e70eabe08 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -109,10 +109,9 @@ static void __net_exit tipc_exit_net(struct net *net)
struct tipc_net *tn = tipc_net(net);
tipc_detach_loopback(net);
+ tipc_net_stop(net);
/* Make sure the tipc_net_finalize_work() finished */
cancel_work_sync(&tn->work);
- tipc_net_stop(net);
-
tipc_bcast_stop(net);
tipc_nametbl_stop(net);
tipc_sk_rht_destroy(net);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index da176411c1b5..2ffede463e4a 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -921,6 +921,8 @@ static void tls_update(struct sock *sk, struct proto *p,
{
struct tls_context *ctx;
+ WARN_ON_ONCE(sk->sk_prot == p);
+
ctx = tls_get_ctx(sk);
if (likely(ctx)) {
ctx->sk_write_space = write_space;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 19ac872a6624..09002387987e 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -538,12 +538,6 @@ static int xsk_generic_xmit(struct sock *sk)
goto out;
}
- skb = xsk_build_skb(xs, &desc);
- if (IS_ERR(skb)) {
- err = PTR_ERR(skb);
- goto out;
- }
-
/* This is the backpressure mechanism for the Tx path.
* Reserve space in the completion queue and only proceed
* if there is space in it. This avoids having to implement
@@ -552,11 +546,19 @@ static int xsk_generic_xmit(struct sock *sk)
spin_lock_irqsave(&xs->pool->cq_lock, flags);
if (xskq_prod_reserve(xs->pool->cq)) {
spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
- kfree_skb(skb);
goto out;
}
spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
+ skb = xsk_build_skb(xs, &desc);
+ if (IS_ERR(skb)) {
+ err = PTR_ERR(skb);
+ spin_lock_irqsave(&xs->pool->cq_lock, flags);
+ xskq_prod_cancel(xs->pool->cq);
+ spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
+ goto out;
+ }
+
err = __dev_direct_xmit(skb, xs->queue_id);
if (err == NETDEV_TX_BUSY) {
/* Tell user-space to retry the send */
diff --git a/samples/fprobe/fprobe_example.c b/samples/fprobe/fprobe_example.c
index 24d3cf109140..01ee6c8c8382 100644
--- a/samples/fprobe/fprobe_example.c
+++ b/samples/fprobe/fprobe_example.c
@@ -21,6 +21,7 @@
#define BACKTRACE_DEPTH 16
#define MAX_SYMBOL_LEN 4096
struct fprobe sample_probe;
+static unsigned long nhit;
static char symbol[MAX_SYMBOL_LEN] = "kernel_clone";
module_param_string(symbol, symbol, sizeof(symbol), 0644);
@@ -28,6 +29,8 @@ static char nosymbol[MAX_SYMBOL_LEN] = "";
module_param_string(nosymbol, nosymbol, sizeof(nosymbol), 0644);
static bool stackdump = true;
module_param(stackdump, bool, 0644);
+static bool use_trace = false;
+module_param(use_trace, bool, 0644);
static void show_backtrace(void)
{
@@ -40,7 +43,15 @@ static void show_backtrace(void)
static void sample_entry_handler(struct fprobe *fp, unsigned long ip, struct pt_regs *regs)
{
- pr_info("Enter <%pS> ip = 0x%p\n", (void *)ip, (void *)ip);
+ if (use_trace)
+ /*
+ * This is just an example, no kernel code should call
+ * trace_printk() except when actively debugging.
+ */
+ trace_printk("Enter <%pS> ip = 0x%p\n", (void *)ip, (void *)ip);
+ else
+ pr_info("Enter <%pS> ip = 0x%p\n", (void *)ip, (void *)ip);
+ nhit++;
if (stackdump)
show_backtrace();
}
@@ -49,8 +60,17 @@ static void sample_exit_handler(struct fprobe *fp, unsigned long ip, struct pt_r
{
unsigned long rip = instruction_pointer(regs);
- pr_info("Return from <%pS> ip = 0x%p to rip = 0x%p (%pS)\n",
- (void *)ip, (void *)ip, (void *)rip, (void *)rip);
+ if (use_trace)
+ /*
+ * This is just an example, no kernel code should call
+ * trace_printk() except when actively debugging.
+ */
+ trace_printk("Return from <%pS> ip = 0x%p to rip = 0x%p (%pS)\n",
+ (void *)ip, (void *)ip, (void *)rip, (void *)rip);
+ else
+ pr_info("Return from <%pS> ip = 0x%p to rip = 0x%p (%pS)\n",
+ (void *)ip, (void *)ip, (void *)rip, (void *)rip);
+ nhit++;
if (stackdump)
show_backtrace();
}
@@ -112,7 +132,8 @@ static void __exit fprobe_exit(void)
{
unregister_fprobe(&sample_probe);
- pr_info("fprobe at %s unregistered\n", symbol);
+ pr_info("fprobe at %s unregistered. %ld times hit, %ld times missed\n",
+ symbol, nhit, sample_probe.nmissed);
}
module_init(fprobe_init)
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
index 83ef55e3caa4..2974b44f80fa 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
@@ -121,24 +121,24 @@ static void kprobe_multi_link_api_subtest(void)
})
GET_ADDR("bpf_fentry_test1", addrs[0]);
- GET_ADDR("bpf_fentry_test2", addrs[1]);
- GET_ADDR("bpf_fentry_test3", addrs[2]);
- GET_ADDR("bpf_fentry_test4", addrs[3]);
- GET_ADDR("bpf_fentry_test5", addrs[4]);
- GET_ADDR("bpf_fentry_test6", addrs[5]);
- GET_ADDR("bpf_fentry_test7", addrs[6]);
+ GET_ADDR("bpf_fentry_test3", addrs[1]);
+ GET_ADDR("bpf_fentry_test4", addrs[2]);
+ GET_ADDR("bpf_fentry_test5", addrs[3]);
+ GET_ADDR("bpf_fentry_test6", addrs[4]);
+ GET_ADDR("bpf_fentry_test7", addrs[5]);
+ GET_ADDR("bpf_fentry_test2", addrs[6]);
GET_ADDR("bpf_fentry_test8", addrs[7]);
#undef GET_ADDR
- cookies[0] = 1;
- cookies[1] = 2;
- cookies[2] = 3;
- cookies[3] = 4;
- cookies[4] = 5;
- cookies[5] = 6;
- cookies[6] = 7;
- cookies[7] = 8;
+ cookies[0] = 1; /* bpf_fentry_test1 */
+ cookies[1] = 2; /* bpf_fentry_test3 */
+ cookies[2] = 3; /* bpf_fentry_test4 */
+ cookies[3] = 4; /* bpf_fentry_test5 */
+ cookies[4] = 5; /* bpf_fentry_test6 */
+ cookies[5] = 6; /* bpf_fentry_test7 */
+ cookies[6] = 7; /* bpf_fentry_test2 */
+ cookies[7] = 8; /* bpf_fentry_test8 */
opts.kprobe_multi.addrs = (const unsigned long *) &addrs;
opts.kprobe_multi.cnt = ARRAY_SIZE(addrs);
@@ -149,14 +149,14 @@ static void kprobe_multi_link_api_subtest(void)
if (!ASSERT_GE(link1_fd, 0, "link1_fd"))
goto cleanup;
- cookies[0] = 8;
- cookies[1] = 7;
- cookies[2] = 6;
- cookies[3] = 5;
- cookies[4] = 4;
- cookies[5] = 3;
- cookies[6] = 2;
- cookies[7] = 1;
+ cookies[0] = 8; /* bpf_fentry_test1 */
+ cookies[1] = 7; /* bpf_fentry_test3 */
+ cookies[2] = 6; /* bpf_fentry_test4 */
+ cookies[3] = 5; /* bpf_fentry_test5 */
+ cookies[4] = 4; /* bpf_fentry_test6 */
+ cookies[5] = 3; /* bpf_fentry_test7 */
+ cookies[6] = 2; /* bpf_fentry_test2 */
+ cookies[7] = 1; /* bpf_fentry_test8 */
opts.kprobe_multi.flags = BPF_F_KPROBE_MULTI_RETURN;
prog_fd = bpf_program__fd(skel->progs.test_kretprobe);
@@ -181,12 +181,12 @@ static void kprobe_multi_attach_api_subtest(void)
struct kprobe_multi *skel = NULL;
const char *syms[8] = {
"bpf_fentry_test1",
- "bpf_fentry_test2",
"bpf_fentry_test3",
"bpf_fentry_test4",
"bpf_fentry_test5",
"bpf_fentry_test6",
"bpf_fentry_test7",
+ "bpf_fentry_test2",
"bpf_fentry_test8",
};
__u64 cookies[8];
@@ -198,14 +198,14 @@ static void kprobe_multi_attach_api_subtest(void)
skel->bss->pid = getpid();
skel->bss->test_cookie = true;
- cookies[0] = 1;
- cookies[1] = 2;
- cookies[2] = 3;
- cookies[3] = 4;
- cookies[4] = 5;
- cookies[5] = 6;
- cookies[6] = 7;
- cookies[7] = 8;
+ cookies[0] = 1; /* bpf_fentry_test1 */
+ cookies[1] = 2; /* bpf_fentry_test3 */
+ cookies[2] = 3; /* bpf_fentry_test4 */
+ cookies[3] = 4; /* bpf_fentry_test5 */
+ cookies[4] = 5; /* bpf_fentry_test6 */
+ cookies[5] = 6; /* bpf_fentry_test7 */
+ cookies[6] = 7; /* bpf_fentry_test2 */
+ cookies[7] = 8; /* bpf_fentry_test8 */
opts.syms = syms;
opts.cnt = ARRAY_SIZE(syms);
@@ -216,14 +216,14 @@ static void kprobe_multi_attach_api_subtest(void)
if (!ASSERT_OK_PTR(link1, "bpf_program__attach_kprobe_multi_opts"))
goto cleanup;
- cookies[0] = 8;
- cookies[1] = 7;
- cookies[2] = 6;
- cookies[3] = 5;
- cookies[4] = 4;
- cookies[5] = 3;
- cookies[6] = 2;
- cookies[7] = 1;
+ cookies[0] = 8; /* bpf_fentry_test1 */
+ cookies[1] = 7; /* bpf_fentry_test3 */
+ cookies[2] = 6; /* bpf_fentry_test4 */
+ cookies[3] = 5; /* bpf_fentry_test5 */
+ cookies[4] = 4; /* bpf_fentry_test6 */
+ cookies[5] = 3; /* bpf_fentry_test7 */
+ cookies[6] = 2; /* bpf_fentry_test2 */
+ cookies[7] = 1; /* bpf_fentry_test8 */
opts.retprobe = true;
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 586dc52d6fb9..5b93d5d0bd93 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -364,6 +364,9 @@ static int get_syms(char ***symsp, size_t *cntp)
continue;
if (!strncmp(name, "rcu_", 4))
continue;
+ if (!strncmp(name, "__ftrace_invalid_address__",
+ sizeof("__ftrace_invalid_address__") - 1))
+ continue;
err = hashmap__add(map, name, NULL);
if (err) {
free(name);
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index c4da87ec3ba4..19c70880cfb3 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -831,6 +831,59 @@ out:
bpf_object__close(obj);
}
+#include "tailcall_bpf2bpf6.skel.h"
+
+/* Tail call counting works even when there is data on stack which is
+ * not aligned to 8 bytes.
+ */
+static void test_tailcall_bpf2bpf_6(void)
+{
+ struct tailcall_bpf2bpf6 *obj;
+ int err, map_fd, prog_fd, main_fd, data_fd, i, val;
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .repeat = 1,
+ );
+
+ obj = tailcall_bpf2bpf6__open_and_load();
+ if (!ASSERT_OK_PTR(obj, "open and load"))
+ return;
+
+ main_fd = bpf_program__fd(obj->progs.entry);
+ if (!ASSERT_GE(main_fd, 0, "entry prog fd"))
+ goto out;
+
+ map_fd = bpf_map__fd(obj->maps.jmp_table);
+ if (!ASSERT_GE(map_fd, 0, "jmp_table map fd"))
+ goto out;
+
+ prog_fd = bpf_program__fd(obj->progs.classifier_0);
+ if (!ASSERT_GE(prog_fd, 0, "classifier_0 prog fd"))
+ goto out;
+
+ i = 0;
+ err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+ if (!ASSERT_OK(err, "jmp_table map update"))
+ goto out;
+
+ err = bpf_prog_test_run_opts(main_fd, &topts);
+ ASSERT_OK(err, "entry prog test run");
+ ASSERT_EQ(topts.retval, 0, "tailcall retval");
+
+ data_fd = bpf_map__fd(obj->maps.bss);
+ if (!ASSERT_GE(map_fd, 0, "bss map fd"))
+ goto out;
+
+ i = 0;
+ err = bpf_map_lookup_elem(data_fd, &i, &val);
+ ASSERT_OK(err, "bss map lookup");
+ ASSERT_EQ(val, 1, "done flag is set");
+
+out:
+ tailcall_bpf2bpf6__destroy(obj);
+}
+
void test_tailcalls(void)
{
if (test__start_subtest("tailcall_1"))
@@ -855,4 +908,6 @@ void test_tailcalls(void)
test_tailcall_bpf2bpf_4(false);
if (test__start_subtest("tailcall_bpf2bpf_5"))
test_tailcall_bpf2bpf_4(true);
+ if (test__start_subtest("tailcall_bpf2bpf_6"))
+ test_tailcall_bpf2bpf_6();
}
diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi.c b/tools/testing/selftests/bpf/progs/kprobe_multi.c
index 93510f4f0f3a..08f95a8155d1 100644
--- a/tools/testing/selftests/bpf/progs/kprobe_multi.c
+++ b/tools/testing/selftests/bpf/progs/kprobe_multi.c
@@ -54,21 +54,21 @@ static void kprobe_multi_check(void *ctx, bool is_return)
if (is_return) {
SET(kretprobe_test1_result, &bpf_fentry_test1, 8);
- SET(kretprobe_test2_result, &bpf_fentry_test2, 7);
- SET(kretprobe_test3_result, &bpf_fentry_test3, 6);
- SET(kretprobe_test4_result, &bpf_fentry_test4, 5);
- SET(kretprobe_test5_result, &bpf_fentry_test5, 4);
- SET(kretprobe_test6_result, &bpf_fentry_test6, 3);
- SET(kretprobe_test7_result, &bpf_fentry_test7, 2);
+ SET(kretprobe_test2_result, &bpf_fentry_test2, 2);
+ SET(kretprobe_test3_result, &bpf_fentry_test3, 7);
+ SET(kretprobe_test4_result, &bpf_fentry_test4, 6);
+ SET(kretprobe_test5_result, &bpf_fentry_test5, 5);
+ SET(kretprobe_test6_result, &bpf_fentry_test6, 4);
+ SET(kretprobe_test7_result, &bpf_fentry_test7, 3);
SET(kretprobe_test8_result, &bpf_fentry_test8, 1);
} else {
SET(kprobe_test1_result, &bpf_fentry_test1, 1);
- SET(kprobe_test2_result, &bpf_fentry_test2, 2);
- SET(kprobe_test3_result, &bpf_fentry_test3, 3);
- SET(kprobe_test4_result, &bpf_fentry_test4, 4);
- SET(kprobe_test5_result, &bpf_fentry_test5, 5);
- SET(kprobe_test6_result, &bpf_fentry_test6, 6);
- SET(kprobe_test7_result, &bpf_fentry_test7, 7);
+ SET(kprobe_test2_result, &bpf_fentry_test2, 7);
+ SET(kprobe_test3_result, &bpf_fentry_test3, 2);
+ SET(kprobe_test4_result, &bpf_fentry_test4, 3);
+ SET(kprobe_test5_result, &bpf_fentry_test5, 4);
+ SET(kprobe_test6_result, &bpf_fentry_test6, 5);
+ SET(kprobe_test7_result, &bpf_fentry_test7, 6);
SET(kprobe_test8_result, &bpf_fentry_test8, 8);
}
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c
new file mode 100644
index 000000000000..41ce83da78e8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#define __unused __attribute__((unused))
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+ __uint(max_entries, 1);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+int done = 0;
+
+SEC("tc")
+int classifier_0(struct __sk_buff *skb __unused)
+{
+ done = 1;
+ return 0;
+}
+
+static __noinline
+int subprog_tail(struct __sk_buff *skb)
+{
+ /* Don't propagate the constant to the caller */
+ volatile int ret = 1;
+
+ bpf_tail_call_static(skb, &jmp_table, 0);
+ return ret;
+}
+
+SEC("tc")
+int entry(struct __sk_buff *skb)
+{
+ /* Have data on stack which size is not a multiple of 8 */
+ volatile char arr[1] = {};
+
+ return subprog_tail(skb);
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 54701c8b0cd7..03b586760164 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -70,6 +70,10 @@ NSB_LO_IP6=2001:db8:2::2
NL_IP=172.17.1.1
NL_IP6=2001:db8:4::1
+# multicast and broadcast addresses
+MCAST_IP=224.0.0.1
+BCAST_IP=255.255.255.255
+
MD5_PW=abc123
MD5_WRONG_PW=abc1234
@@ -308,6 +312,9 @@ addr2str()
127.0.0.1) echo "loopback";;
::1) echo "IPv6 loopback";;
+ ${BCAST_IP}) echo "broadcast";;
+ ${MCAST_IP}) echo "multicast";;
+
${NSA_IP}) echo "ns-A IP";;
${NSA_IP6}) echo "ns-A IPv6";;
${NSA_LO_IP}) echo "ns-A loopback IP";;
@@ -1793,12 +1800,33 @@ ipv4_addr_bind_novrf()
done
#
- # raw socket with nonlocal bind
+ # tests for nonlocal bind
#
a=${NL_IP}
log_start
- run_cmd nettest -s -R -P icmp -f -l ${a} -I ${NSA_DEV} -b
- log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after device bind"
+ run_cmd nettest -s -R -f -l ${a} -b
+ log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address"
+
+ log_start
+ run_cmd nettest -s -f -l ${a} -b
+ log_test_addr ${a} $? 0 "TCP socket bind to nonlocal address"
+
+ log_start
+ run_cmd nettest -s -D -P icmp -f -l ${a} -b
+ log_test_addr ${a} $? 0 "ICMP socket bind to nonlocal address"
+
+ #
+ # check that ICMP sockets cannot bind to broadcast and multicast addresses
+ #
+ a=${BCAST_IP}
+ log_start
+ run_cmd nettest -s -D -P icmp -l ${a} -b
+ log_test_addr ${a} $? 1 "ICMP socket bind to broadcast address"
+
+ a=${MCAST_IP}
+ log_start
+ run_cmd nettest -s -D -P icmp -l ${a} -b
+ log_test_addr ${a} $? 1 "ICMP socket bind to multicast address"
#
# tcp sockets
@@ -1850,13 +1878,34 @@ ipv4_addr_bind_vrf()
log_test_addr ${a} $? 1 "Raw socket bind to out of scope address after VRF bind"
#
- # raw socket with nonlocal bind
+ # tests for nonlocal bind
#
a=${NL_IP}
log_start
- run_cmd nettest -s -R -P icmp -f -l ${a} -I ${VRF} -b
+ run_cmd nettest -s -R -f -l ${a} -I ${VRF} -b
log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after VRF bind"
+ log_start
+ run_cmd nettest -s -f -l ${a} -I ${VRF} -b
+ log_test_addr ${a} $? 0 "TCP socket bind to nonlocal address after VRF bind"
+
+ log_start
+ run_cmd nettest -s -D -P icmp -f -l ${a} -I ${VRF} -b
+ log_test_addr ${a} $? 0 "ICMP socket bind to nonlocal address after VRF bind"
+
+ #
+ # check that ICMP sockets cannot bind to broadcast and multicast addresses
+ #
+ a=${BCAST_IP}
+ log_start
+ run_cmd nettest -s -D -P icmp -l ${a} -I ${VRF} -b
+ log_test_addr ${a} $? 1 "ICMP socket bind to broadcast address after VRF bind"
+
+ a=${MCAST_IP}
+ log_start
+ run_cmd nettest -s -D -P icmp -l ${a} -I ${VRF} -b
+ log_test_addr ${a} $? 1 "ICMP socket bind to multicast address after VRF bind"
+
#
# tcp sockets
#
@@ -1889,10 +1938,12 @@ ipv4_addr_bind()
log_subsection "No VRF"
setup
+ set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null
ipv4_addr_bind_novrf
log_subsection "With VRF"
setup "yes"
+ set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null
ipv4_addr_bind_vrf
}
diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
index b35010cc7f6a..a6991877e50c 100755
--- a/tools/testing/selftests/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -31,7 +31,7 @@ BUGS="flush_remove_add reload"
# List of possible paths to pktgen script from kernel tree for performance tests
PKTGEN_SCRIPT_PATHS="
- ../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh
+ ../../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh
pktgen/pktgen_bench_xmit_mode_netif_receive.sh"
# Definition of set types: