summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-06-27 19:05:35 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2024-06-27 19:05:35 +0200
commitfd19d4a492af77b1e8fb0439781a3048d1d1f554 (patch)
treec293c1a1218fe87c4b6712938352dbc349d0b68e
parentMerge tag 'sound-6.10-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/t... (diff)
parentMerge tag 'nf-24-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/netf... (diff)
downloadlinux-fd19d4a492af77b1e8fb0439781a3048d1d1f554.tar.xz
linux-fd19d4a492af77b1e8fb0439781a3048d1d1f554.zip
Merge tag 'net-6.10-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni: "Including fixes from can, bpf and netfilter. There are a bunch of regressions addressed here, but hopefully nothing spectacular. We are still waiting the driver fix from Intel, mentioned by Jakub in the previous networking pull. Current release - regressions: - core: add softirq safety to netdev_rename_lock - tcp: fix tcp_rcv_fastopen_synack() to enter TCP_CA_Loss for failed TFO - batman-adv: fix RCU race at module unload time Previous releases - regressions: - openvswitch: get related ct labels from its master if it is not confirmed - eth: bonding: fix incorrect software timestamping report - eth: mlxsw: fix memory corruptions on spectrum-4 systems - eth: ionic: use dev_consume_skb_any outside of napi Previous releases - always broken: - netfilter: fully validate NFT_DATA_VALUE on store to data registers - unix: several fixes for OoB data - tcp: fix race for duplicate reqsk on identical SYN - bpf: - fix may_goto with negative offset - fix the corner case with may_goto and jump to the 1st insn - fix overrunning reservations in ringbuf - can: - j1939: recover socket queue on CAN bus error during BAM transmission - mcp251xfd: fix infinite loop when xmit fails - dsa: microchip: monitor potential faults in half-duplex mode - eth: vxlan: pull inner IP header in vxlan_xmit_one() - eth: ionic: fix kernel panic due to multi-buffer handling Misc: - selftest: unix tests refactor and a lot of new cases added" * tag 'net-6.10-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (61 commits) net: mana: Fix possible double free in error handling path selftest: af_unix: Check SIOCATMARK after every send()/recv() in msg_oob.c. af_unix: Fix wrong ioctl(SIOCATMARK) when consumed OOB skb is at the head. selftest: af_unix: Check EPOLLPRI after every send()/recv() in msg_oob.c selftest: af_unix: Check SIGURG after every send() in msg_oob.c selftest: af_unix: Add SO_OOBINLINE test cases in msg_oob.c af_unix: Don't stop recv() at consumed ex-OOB skb. selftest: af_unix: Add non-TCP-compliant test cases in msg_oob.c. af_unix: Don't stop recv(MSG_DONTWAIT) if consumed OOB skb is at the head. af_unix: Stop recv(MSG_PEEK) at consumed OOB skb. selftest: af_unix: Add msg_oob.c. selftest: af_unix: Remove test_unix_oob.c. tracing/net_sched: NULL pointer dereference in perf_trace_qdisc_reset() netfilter: nf_tables: fully validate NFT_DATA_VALUE on store to data registers net: usb: qmi_wwan: add Telit FN912 compositions tcp: fix tcp_rcv_fastopen_synack() to enter TCP_CA_Loss for failed TFO ionic: use dev_consume_skb_any outside of napi net: dsa: microchip: fix wrong register write when masking interrupt Fix race for duplicate reqsk on identical SYN ibmvnic: Add tx check to prevent skb leak ...
-rw-r--r--Documentation/devicetree/bindings/net/fsl,fman-dtsec.yaml1
-rw-r--r--Documentation/netlink/specs/ethtool.yaml7
-rw-r--r--MAINTAINERS4
-rw-r--r--drivers/net/bonding/bond_main.c3
-rw-r--r--drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c14
-rw-r--r--drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c55
-rw-r--r--drivers/net/can/spi/mcp251xfd/mcp251xfd.h5
-rw-r--r--drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c2
-rw-r--r--drivers/net/dsa/microchip/ksz9477.c61
-rw-r--r--drivers/net/dsa/microchip/ksz9477.h2
-rw-r--r--drivers/net/dsa/microchip/ksz9477_reg.h11
-rw-r--r--drivers/net/dsa/microchip/ksz_common.c13
-rw-r--r--drivers/net/dsa/microchip/ksz_common.h1
-rw-r--r--drivers/net/ethernet/ibm/ibmvnic.c18
-rw-r--r--drivers/net/ethernet/intel/ice/ice_main.c10
-rw-r--r--drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c1
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c10
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h55
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c2
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/nic/qos.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/pci.c18
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/reg.h2
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c20
-rw-r--r--drivers/net/ethernet/microsoft/mana/mana_en.c2
-rw-r--r--drivers/net/ethernet/pensando/ionic/ionic_dev.h4
-rw-r--r--drivers/net/ethernet/pensando/ionic/ionic_lif.c2
-rw-r--r--drivers/net/ethernet/pensando/ionic/ionic_txrx.c55
-rw-r--r--drivers/net/phy/micrel.c1
-rw-r--r--drivers/net/pse-pd/Kconfig1
-rw-r--r--drivers/net/usb/ax88179_178a.c6
-rw-r--r--drivers/net/usb/qmi_wwan.c2
-rw-r--r--drivers/net/vxlan/vxlan_core.c9
-rw-r--r--include/net/inet_connection_sock.h2
-rw-r--r--include/net/netfilter/nf_tables.h5
-rw-r--r--include/trace/events/qdisc.h2
-rw-r--r--kernel/bpf/arena.c16
-rw-r--r--kernel/bpf/ringbuf.c31
-rw-r--r--kernel/bpf/verifier.c61
-rw-r--r--net/batman-adv/originator.c27
-rw-r--r--net/batman-adv/translation-table.c47
-rw-r--r--net/can/j1939/main.c6
-rw-r--r--net/can/j1939/transport.c21
-rw-r--r--net/core/dev.c12
-rw-r--r--net/core/xdp.c4
-rw-r--r--net/dccp/ipv4.c7
-rw-r--r--net/dccp/ipv6.c7
-rw-r--r--net/ipv4/inet_connection_sock.c17
-rw-r--r--net/ipv4/tcp_input.c45
-rw-r--r--net/netfilter/nf_hooks_lwtunnel.c3
-rw-r--r--net/netfilter/nf_tables_api.c8
-rw-r--r--net/netfilter/nft_lookup.c3
-rw-r--r--net/openvswitch/conntrack.c7
-rw-r--r--net/unix/af_unix.c37
-rw-r--r--tools/testing/selftests/bpf/Makefile2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/ringbuf.c56
-rw-r--r--tools/testing/selftests/bpf/progs/test_ringbuf_write.c46
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c146
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_movsx.c63
-rw-r--r--tools/testing/selftests/net/.gitignore1
-rw-r--r--tools/testing/selftests/net/af_unix/Makefile2
-rw-r--r--tools/testing/selftests/net/af_unix/config3
-rw-r--r--tools/testing/selftests/net/af_unix/msg_oob.c734
-rw-r--r--tools/testing/selftests/net/af_unix/test_unix_oob.c436
63 files changed, 1663 insertions, 594 deletions
diff --git a/Documentation/devicetree/bindings/net/fsl,fman-dtsec.yaml b/Documentation/devicetree/bindings/net/fsl,fman-dtsec.yaml
index c80c880a9dab..60aaf30d68ed 100644
--- a/Documentation/devicetree/bindings/net/fsl,fman-dtsec.yaml
+++ b/Documentation/devicetree/bindings/net/fsl,fman-dtsec.yaml
@@ -128,7 +128,6 @@ required:
- cell-index
- reg
- fsl,fman-ports
- - ptp-timer
dependencies:
pcs-handle-names:
diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 00dc61358be8..4510e8d1adcb 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -1603,7 +1603,7 @@ operations:
attributes:
- header
reply:
- attributes: &pse
+ attributes:
- header
- podl-pse-admin-state
- podl-pse-admin-control
@@ -1620,7 +1620,10 @@ operations:
do:
request:
- attributes: *pse
+ attributes:
+ - header
+ - podl-pse-admin-control
+ - c33-pse-admin-control
-
name: rss-get
doc: Get RSS params.
diff --git a/MAINTAINERS b/MAINTAINERS
index db9bb0ce3043..0748d6bd0c4f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4083,12 +4083,13 @@ F: kernel/bpf/ringbuf.c
BPF [SECURITY & LSM] (Security Audit and Enforcement using BPF)
M: KP Singh <kpsingh@kernel.org>
-R: Matt Bobrowski <mattbobrowski@google.com>
+M: Matt Bobrowski <mattbobrowski@google.com>
L: bpf@vger.kernel.org
S: Maintained
F: Documentation/bpf/prog_lsm.rst
F: include/linux/bpf_lsm.h
F: kernel/bpf/bpf_lsm.c
+F: kernel/trace/bpf_trace.c
F: security/bpf/
BPF [SELFTESTS] (Test Runners & Infrastructure)
@@ -17531,7 +17532,6 @@ F: include/linux/peci.h
PENSANDO ETHERNET DRIVERS
M: Shannon Nelson <shannon.nelson@amd.com>
M: Brett Creeley <brett.creeley@amd.com>
-M: drivers@pensando.io
L: netdev@vger.kernel.org
S: Supported
F: Documentation/networking/device_drivers/ethernet/pensando/ionic.rst
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 3c3fcce4acd4..d19aabf5d4fb 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -5773,6 +5773,9 @@ static int bond_ethtool_get_ts_info(struct net_device *bond_dev,
if (real_dev) {
ret = ethtool_get_ts_info_by_layer(real_dev, info);
} else {
+ info->phc_index = -1;
+ info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_SOFTWARE;
/* Check if all slaves support software tx timestamping */
rcu_read_lock();
bond_for_each_slave_rcu(bond, slave, iter) {
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 1d9057dc44f2..bf1589aef1fc 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -1618,11 +1618,20 @@ static int mcp251xfd_open(struct net_device *ndev)
clear_bit(MCP251XFD_FLAGS_DOWN, priv->flags);
can_rx_offload_enable(&priv->offload);
+ priv->wq = alloc_ordered_workqueue("%s-mcp251xfd_wq",
+ WQ_FREEZABLE | WQ_MEM_RECLAIM,
+ dev_name(&spi->dev));
+ if (!priv->wq) {
+ err = -ENOMEM;
+ goto out_can_rx_offload_disable;
+ }
+ INIT_WORK(&priv->tx_work, mcp251xfd_tx_obj_write_sync);
+
err = request_threaded_irq(spi->irq, NULL, mcp251xfd_irq,
IRQF_SHARED | IRQF_ONESHOT,
dev_name(&spi->dev), priv);
if (err)
- goto out_can_rx_offload_disable;
+ goto out_destroy_workqueue;
err = mcp251xfd_chip_interrupts_enable(priv);
if (err)
@@ -1634,6 +1643,8 @@ static int mcp251xfd_open(struct net_device *ndev)
out_free_irq:
free_irq(spi->irq, priv);
+ out_destroy_workqueue:
+ destroy_workqueue(priv->wq);
out_can_rx_offload_disable:
can_rx_offload_disable(&priv->offload);
set_bit(MCP251XFD_FLAGS_DOWN, priv->flags);
@@ -1661,6 +1672,7 @@ static int mcp251xfd_stop(struct net_device *ndev)
hrtimer_cancel(&priv->tx_irq_timer);
mcp251xfd_chip_interrupts_disable(priv);
free_irq(ndev->irq, priv);
+ destroy_workqueue(priv->wq);
can_rx_offload_disable(&priv->offload);
mcp251xfd_timestamp_stop(priv);
mcp251xfd_chip_stop(priv, CAN_STATE_STOPPED);
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c
index 160528d3cc26..b1de8052a45c 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c
@@ -131,6 +131,39 @@ mcp251xfd_tx_obj_from_skb(const struct mcp251xfd_priv *priv,
tx_obj->xfer[0].len = len;
}
+static void mcp251xfd_tx_failure_drop(const struct mcp251xfd_priv *priv,
+ struct mcp251xfd_tx_ring *tx_ring,
+ int err)
+{
+ struct net_device *ndev = priv->ndev;
+ struct net_device_stats *stats = &ndev->stats;
+ unsigned int frame_len = 0;
+ u8 tx_head;
+
+ tx_ring->head--;
+ stats->tx_dropped++;
+ tx_head = mcp251xfd_get_tx_head(tx_ring);
+ can_free_echo_skb(ndev, tx_head, &frame_len);
+ netdev_completed_queue(ndev, 1, frame_len);
+ netif_wake_queue(ndev);
+
+ if (net_ratelimit())
+ netdev_err(priv->ndev, "ERROR in %s: %d\n", __func__, err);
+}
+
+void mcp251xfd_tx_obj_write_sync(struct work_struct *work)
+{
+ struct mcp251xfd_priv *priv = container_of(work, struct mcp251xfd_priv,
+ tx_work);
+ struct mcp251xfd_tx_obj *tx_obj = priv->tx_work_obj;
+ struct mcp251xfd_tx_ring *tx_ring = priv->tx;
+ int err;
+
+ err = spi_sync(priv->spi, &tx_obj->msg);
+ if (err)
+ mcp251xfd_tx_failure_drop(priv, tx_ring, err);
+}
+
static int mcp251xfd_tx_obj_write(const struct mcp251xfd_priv *priv,
struct mcp251xfd_tx_obj *tx_obj)
{
@@ -162,6 +195,11 @@ static bool mcp251xfd_tx_busy(const struct mcp251xfd_priv *priv,
return false;
}
+static bool mcp251xfd_work_busy(struct work_struct *work)
+{
+ return work_busy(work);
+}
+
netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb,
struct net_device *ndev)
{
@@ -175,7 +213,8 @@ netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb,
if (can_dev_dropped_skb(ndev, skb))
return NETDEV_TX_OK;
- if (mcp251xfd_tx_busy(priv, tx_ring))
+ if (mcp251xfd_tx_busy(priv, tx_ring) ||
+ mcp251xfd_work_busy(&priv->tx_work))
return NETDEV_TX_BUSY;
tx_obj = mcp251xfd_get_tx_obj_next(tx_ring);
@@ -193,13 +232,13 @@ netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb,
netdev_sent_queue(priv->ndev, frame_len);
err = mcp251xfd_tx_obj_write(priv, tx_obj);
- if (err)
- goto out_err;
-
- return NETDEV_TX_OK;
-
- out_err:
- netdev_err(priv->ndev, "ERROR in %s: %d\n", __func__, err);
+ if (err == -EBUSY) {
+ netif_stop_queue(ndev);
+ priv->tx_work_obj = tx_obj;
+ queue_work(priv->wq, &priv->tx_work);
+ } else if (err) {
+ mcp251xfd_tx_failure_drop(priv, tx_ring, err);
+ }
return NETDEV_TX_OK;
}
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
index 24510b3b8020..b35bfebd23f2 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
@@ -633,6 +633,10 @@ struct mcp251xfd_priv {
struct mcp251xfd_rx_ring *rx[MCP251XFD_FIFO_RX_NUM];
struct mcp251xfd_tx_ring tx[MCP251XFD_FIFO_TX_NUM];
+ struct workqueue_struct *wq;
+ struct work_struct tx_work;
+ struct mcp251xfd_tx_obj *tx_work_obj;
+
DECLARE_BITMAP(flags, __MCP251XFD_FLAGS_SIZE__);
u8 rx_ring_num;
@@ -952,6 +956,7 @@ void mcp251xfd_skb_set_timestamp(const struct mcp251xfd_priv *priv,
void mcp251xfd_timestamp_init(struct mcp251xfd_priv *priv);
void mcp251xfd_timestamp_stop(struct mcp251xfd_priv *priv);
+void mcp251xfd_tx_obj_write_sync(struct work_struct *work);
netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb,
struct net_device *ndev);
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index 8faf8a462c05..7292c81fc0cd 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -294,7 +294,7 @@ int kvaser_usb_send_cmd_async(struct kvaser_usb_net_priv *priv, void *cmd,
}
usb_free_urb(urb);
- return 0;
+ return err;
}
int kvaser_usb_can_rx_over_error(struct net_device *netdev)
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index f8ad7833f5d9..425e20daf1e9 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -355,10 +355,8 @@ int ksz9477_reset_switch(struct ksz_device *dev)
SPI_AUTO_EDGE_DETECTION, 0);
/* default configuration */
- ksz_read8(dev, REG_SW_LUE_CTRL_1, &data8);
- data8 = SW_AGING_ENABLE | SW_LINK_AUTO_AGING |
- SW_SRC_ADDR_FILTER | SW_FLUSH_STP_TABLE | SW_FLUSH_MSTP_TABLE;
- ksz_write8(dev, REG_SW_LUE_CTRL_1, data8);
+ ksz_write8(dev, REG_SW_LUE_CTRL_1,
+ SW_AGING_ENABLE | SW_LINK_AUTO_AGING | SW_SRC_ADDR_FILTER);
/* disable interrupts */
ksz_write32(dev, REG_SW_INT_MASK__4, SWITCH_INT_MASK);
@@ -429,6 +427,57 @@ void ksz9477_freeze_mib(struct ksz_device *dev, int port, bool freeze)
mutex_unlock(&p->mib.cnt_mutex);
}
+int ksz9477_errata_monitor(struct ksz_device *dev, int port,
+ u64 tx_late_col)
+{
+ u32 pmavbc;
+ u8 status;
+ u16 pqm;
+ int ret;
+
+ ret = ksz_pread8(dev, port, REG_PORT_STATUS_0, &status);
+ if (ret)
+ return ret;
+ if (!(FIELD_GET(PORT_INTF_SPEED_MASK, status) == PORT_INTF_SPEED_NONE) &&
+ !(status & PORT_INTF_FULL_DUPLEX)) {
+ /* Errata DS80000754 recommends monitoring potential faults in
+ * half-duplex mode. The switch might not be able to communicate anymore
+ * in these states.
+ * If you see this message, please read the errata-sheet for more information:
+ * https://ww1.microchip.com/downloads/aemDocuments/documents/UNG/ProductDocuments/Errata/KSZ9477S-Errata-DS80000754.pdf
+ * To workaround this issue, half-duplex mode should be avoided.
+ * A software reset could be implemented to recover from this state.
+ */
+ dev_warn_once(dev->dev,
+ "Half-duplex detected on port %d, transmission halt may occur\n",
+ port);
+ if (tx_late_col != 0) {
+ /* Transmission halt with late collisions */
+ dev_crit_once(dev->dev,
+ "TX late collisions detected, transmission may be halted on port %d\n",
+ port);
+ }
+ ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &status);
+ if (ret)
+ return ret;
+ if (status & SW_VLAN_ENABLE) {
+ ret = ksz_pread16(dev, port, REG_PORT_QM_TX_CNT_0__4, &pqm);
+ if (ret)
+ return ret;
+ ret = ksz_read32(dev, REG_PMAVBC, &pmavbc);
+ if (ret)
+ return ret;
+ if ((FIELD_GET(PMAVBC_MASK, pmavbc) <= PMAVBC_MIN) ||
+ (FIELD_GET(PORT_QM_TX_CNT_M, pqm) >= PORT_QM_TX_CNT_MAX)) {
+ /* Transmission halt with Half-Duplex and VLAN */
+ dev_crit_once(dev->dev,
+ "resources out of limits, transmission may be halted\n");
+ }
+ }
+ }
+ return ret;
+}
+
void ksz9477_port_init_cnt(struct ksz_device *dev, int port)
{
struct ksz_port_mib *mib = &dev->ports[port].mib;
@@ -1299,6 +1348,10 @@ int ksz9477_setup(struct dsa_switch *ds)
/* Enable REG_SW_MTU__2 reg by setting SW_JUMBO_PACKET */
ksz_cfg(dev, REG_SW_MAC_CTRL_1, SW_JUMBO_PACKET, true);
+ /* Use collision based back pressure mode. */
+ ksz_cfg(dev, REG_SW_MAC_CTRL_1, SW_BACK_PRESSURE,
+ SW_BACK_PRESSURE_COLLISION);
+
/* Now we can configure default MTU value */
ret = regmap_update_bits(ksz_regmap_16(dev), REG_SW_MTU__2, REG_SW_MTU_MASK,
VLAN_ETH_FRAME_LEN + ETH_FCS_LEN);
diff --git a/drivers/net/dsa/microchip/ksz9477.h b/drivers/net/dsa/microchip/ksz9477.h
index ce1e656b800b..239a281da10b 100644
--- a/drivers/net/dsa/microchip/ksz9477.h
+++ b/drivers/net/dsa/microchip/ksz9477.h
@@ -36,6 +36,8 @@ int ksz9477_port_mirror_add(struct ksz_device *dev, int port,
bool ingress, struct netlink_ext_ack *extack);
void ksz9477_port_mirror_del(struct ksz_device *dev, int port,
struct dsa_mall_mirror_tc_entry *mirror);
+int ksz9477_errata_monitor(struct ksz_device *dev, int port,
+ u64 tx_late_col);
void ksz9477_get_caps(struct ksz_device *dev, int port,
struct phylink_config *config);
int ksz9477_fdb_dump(struct ksz_device *dev, int port,
diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h
index f3a205ee483f..d5354c600ea1 100644
--- a/drivers/net/dsa/microchip/ksz9477_reg.h
+++ b/drivers/net/dsa/microchip/ksz9477_reg.h
@@ -247,6 +247,7 @@
#define REG_SW_MAC_CTRL_1 0x0331
#define SW_BACK_PRESSURE BIT(5)
+#define SW_BACK_PRESSURE_COLLISION 0
#define FAIR_FLOW_CTRL BIT(4)
#define NO_EXC_COLLISION_DROP BIT(3)
#define SW_JUMBO_PACKET BIT(2)
@@ -842,8 +843,8 @@
#define REG_PORT_STATUS_0 0x0030
-#define PORT_INTF_SPEED_M 0x3
-#define PORT_INTF_SPEED_S 3
+#define PORT_INTF_SPEED_MASK GENMASK(4, 3)
+#define PORT_INTF_SPEED_NONE GENMASK(1, 0)
#define PORT_INTF_FULL_DUPLEX BIT(2)
#define PORT_TX_FLOW_CTRL BIT(1)
#define PORT_RX_FLOW_CTRL BIT(0)
@@ -1167,6 +1168,11 @@
#define PORT_RMII_CLK_SEL BIT(7)
#define PORT_MII_SEL_EDGE BIT(5)
+#define REG_PMAVBC 0x03AC
+
+#define PMAVBC_MASK GENMASK(26, 16)
+#define PMAVBC_MIN 0x580
+
/* 4 - MAC */
#define REG_PORT_MAC_CTRL_0 0x0400
@@ -1494,6 +1500,7 @@
#define PORT_QM_TX_CNT_USED_S 0
#define PORT_QM_TX_CNT_M (BIT(11) - 1)
+#define PORT_QM_TX_CNT_MAX 0x200
#define REG_PORT_QM_TX_CNT_1__4 0x0A14
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 2818e24e2a51..0580b2fee21c 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -1382,6 +1382,7 @@ const struct ksz_chip_data ksz_switch_chips[] = {
.tc_cbs_supported = true,
.ops = &ksz9477_dev_ops,
.phylink_mac_ops = &ksz9477_phylink_mac_ops,
+ .phy_errata_9477 = true,
.mib_names = ksz9477_mib_names,
.mib_cnt = ARRAY_SIZE(ksz9477_mib_names),
.reg_mib_cnt = MIB_COUNTER_NUM,
@@ -1416,6 +1417,7 @@ const struct ksz_chip_data ksz_switch_chips[] = {
.num_ipms = 8,
.ops = &ksz9477_dev_ops,
.phylink_mac_ops = &ksz9477_phylink_mac_ops,
+ .phy_errata_9477 = true,
.mib_names = ksz9477_mib_names,
.mib_cnt = ARRAY_SIZE(ksz9477_mib_names),
.reg_mib_cnt = MIB_COUNTER_NUM,
@@ -1450,6 +1452,7 @@ const struct ksz_chip_data ksz_switch_chips[] = {
.num_ipms = 8,
.ops = &ksz9477_dev_ops,
.phylink_mac_ops = &ksz9477_phylink_mac_ops,
+ .phy_errata_9477 = true,
.mib_names = ksz9477_mib_names,
.mib_cnt = ARRAY_SIZE(ksz9477_mib_names),
.reg_mib_cnt = MIB_COUNTER_NUM,
@@ -1540,6 +1543,7 @@ const struct ksz_chip_data ksz_switch_chips[] = {
.tc_cbs_supported = true,
.ops = &ksz9477_dev_ops,
.phylink_mac_ops = &ksz9477_phylink_mac_ops,
+ .phy_errata_9477 = true,
.mib_names = ksz9477_mib_names,
.mib_cnt = ARRAY_SIZE(ksz9477_mib_names),
.reg_mib_cnt = MIB_COUNTER_NUM,
@@ -1820,6 +1824,7 @@ void ksz_r_mib_stats64(struct ksz_device *dev, int port)
struct rtnl_link_stats64 *stats;
struct ksz_stats_raw *raw;
struct ksz_port_mib *mib;
+ int ret;
mib = &dev->ports[port].mib;
stats = &mib->stats64;
@@ -1861,6 +1866,12 @@ void ksz_r_mib_stats64(struct ksz_device *dev, int port)
pstats->rx_pause_frames = raw->rx_pause;
spin_unlock(&mib->stats64_lock);
+
+ if (dev->info->phy_errata_9477) {
+ ret = ksz9477_errata_monitor(dev, port, raw->tx_late_col);
+ if (ret)
+ dev_err(dev->dev, "Failed to monitor transmission halt\n");
+ }
}
void ksz88xx_r_mib_stats64(struct ksz_device *dev, int port)
@@ -2185,7 +2196,7 @@ static void ksz_irq_bus_sync_unlock(struct irq_data *d)
struct ksz_device *dev = kirq->dev;
int ret;
- ret = ksz_write32(dev, kirq->reg_mask, kirq->masked);
+ ret = ksz_write8(dev, kirq->reg_mask, kirq->masked);
if (ret)
dev_err(dev->dev, "failed to change IRQ mask\n");
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index c784fd23a993..ee7db46e469d 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -66,6 +66,7 @@ struct ksz_chip_data {
bool tc_cbs_supported;
const struct ksz_dev_ops *ops;
const struct phylink_mac_ops *phylink_mac_ops;
+ bool phy_errata_9477;
bool ksz87xx_eee_link_erratum;
const struct ksz_mib_names *mib_names;
int mib_cnt;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 5e9a93bdb518..23ebeb143987 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2482,6 +2482,18 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
(tx_pool->consumer_index + 1) % tx_pool->num_buffers;
tx_buff = &tx_pool->tx_buff[bufidx];
+
+ /* Sanity checks on our free map to make sure it points to an index
+ * that is not being occupied by another skb. If skb memory is
+ * not freed then we see congestion control kick in and halt tx.
+ */
+ if (unlikely(tx_buff->skb)) {
+ dev_warn_ratelimited(dev, "TX free map points to untracked skb (%s %d idx=%d)\n",
+ skb_is_gso(skb) ? "tso_pool" : "tx_pool",
+ queue_num, bufidx);
+ dev_kfree_skb_any(tx_buff->skb);
+ }
+
tx_buff->skb = skb;
tx_buff->index = bufidx;
tx_buff->pool_index = queue_num;
@@ -4061,6 +4073,12 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter, bool do_h_free)
adapter->num_active_tx_scrqs = 0;
}
+ /* Clean any remaining outstanding SKBs
+ * we freed the irq so we won't be hearing
+ * from them
+ */
+ clean_tx_pools(adapter);
+
if (adapter->rx_scrq) {
for (i = 0; i < adapter->num_active_rx_scrqs; i++) {
if (!adapter->rx_scrq[i])
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 1766230abfff..55a42aad92a5 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4139,7 +4139,7 @@ bool ice_is_wol_supported(struct ice_hw *hw)
int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked)
{
struct ice_pf *pf = vsi->back;
- int err = 0, timeout = 50;
+ int i, err = 0, timeout = 50;
if (!new_rx && !new_tx)
return -EINVAL;
@@ -4165,6 +4165,14 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked)
ice_vsi_close(vsi);
ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
+
+ ice_for_each_traffic_class(i) {
+ if (vsi->tc_cfg.ena_tc & BIT(i))
+ netdev_set_tc_queue(vsi->netdev,
+ vsi->tc_cfg.tc_info[i].netdev_tc,
+ vsi->tc_cfg.tc_info[i].qcount_tx,
+ vsi->tc_cfg.tc_info[i].qoffset);
+ }
ice_pf_dcb_recfg(pf, locked);
ice_vsi_open(vsi);
done:
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 671368d2c77e..9adf4301c9b1 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -6907,6 +6907,7 @@ static int mvpp2_port_probe(struct platform_device *pdev,
/* 9704 == 9728 - 20 and rounding to 8 */
dev->max_mtu = MVPP2_BM_JUMBO_PKT_SIZE;
device_set_node(&dev->dev, port_fwnode);
+ dev->dev_port = port->id;
port->pcs_gmac.ops = &mvpp2_phylink_gmac_pcs_ops;
port->pcs_gmac.neg_mode = true;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index a85ac039d779..87d5776e3b88 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -648,14 +648,14 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool txschq_for
} else if (lvl == NIX_TXSCH_LVL_TL4) {
parent = schq_list[NIX_TXSCH_LVL_TL3][prio];
req->reg[0] = NIX_AF_TL4X_PARENT(schq);
- req->regval[0] = parent << 16;
+ req->regval[0] = (u64)parent << 16;
req->num_regs++;
req->reg[1] = NIX_AF_TL4X_SCHEDULE(schq);
req->regval[1] = dwrr_val;
} else if (lvl == NIX_TXSCH_LVL_TL3) {
parent = schq_list[NIX_TXSCH_LVL_TL2][prio];
req->reg[0] = NIX_AF_TL3X_PARENT(schq);
- req->regval[0] = parent << 16;
+ req->regval[0] = (u64)parent << 16;
req->num_regs++;
req->reg[1] = NIX_AF_TL3X_SCHEDULE(schq);
req->regval[1] = dwrr_val;
@@ -670,11 +670,11 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool txschq_for
} else if (lvl == NIX_TXSCH_LVL_TL2) {
parent = schq_list[NIX_TXSCH_LVL_TL1][prio];
req->reg[0] = NIX_AF_TL2X_PARENT(schq);
- req->regval[0] = parent << 16;
+ req->regval[0] = (u64)parent << 16;
req->num_regs++;
req->reg[1] = NIX_AF_TL2X_SCHEDULE(schq);
- req->regval[1] = TXSCH_TL1_DFLT_RR_PRIO << 24 | dwrr_val;
+ req->regval[1] = (u64)hw->txschq_aggr_lvl_rr_prio << 24 | dwrr_val;
if (lvl == hw->txschq_link_cfg_lvl) {
req->num_regs++;
@@ -698,7 +698,7 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool txschq_for
req->num_regs++;
req->reg[1] = NIX_AF_TL1X_TOPOLOGY(schq);
- req->regval[1] = (TXSCH_TL1_DFLT_RR_PRIO << 1);
+ req->regval[1] = hw->txschq_aggr_lvl_rr_prio << 1;
req->num_regs++;
req->reg[2] = NIX_AF_TL1X_CIR(schq);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h
index 45a32e4b49d1..e3aee6e36215 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h
@@ -139,33 +139,34 @@
#define NIX_LF_CINTX_ENA_W1C(a) (NIX_LFBASE | 0xD50 | (a) << 12)
/* NIX AF transmit scheduler registers */
-#define NIX_AF_SMQX_CFG(a) (0x700 | (a) << 16)
-#define NIX_AF_TL1X_SCHEDULE(a) (0xC00 | (a) << 16)
-#define NIX_AF_TL1X_CIR(a) (0xC20 | (a) << 16)
-#define NIX_AF_TL1X_TOPOLOGY(a) (0xC80 | (a) << 16)
-#define NIX_AF_TL2X_PARENT(a) (0xE88 | (a) << 16)
-#define NIX_AF_TL2X_SCHEDULE(a) (0xE00 | (a) << 16)
-#define NIX_AF_TL2X_TOPOLOGY(a) (0xE80 | (a) << 16)
-#define NIX_AF_TL2X_CIR(a) (0xE20 | (a) << 16)
-#define NIX_AF_TL2X_PIR(a) (0xE30 | (a) << 16)
-#define NIX_AF_TL3X_PARENT(a) (0x1088 | (a) << 16)
-#define NIX_AF_TL3X_SCHEDULE(a) (0x1000 | (a) << 16)
-#define NIX_AF_TL3X_SHAPE(a) (0x1010 | (a) << 16)
-#define NIX_AF_TL3X_CIR(a) (0x1020 | (a) << 16)
-#define NIX_AF_TL3X_PIR(a) (0x1030 | (a) << 16)
-#define NIX_AF_TL3X_TOPOLOGY(a) (0x1080 | (a) << 16)
-#define NIX_AF_TL4X_PARENT(a) (0x1288 | (a) << 16)
-#define NIX_AF_TL4X_SCHEDULE(a) (0x1200 | (a) << 16)
-#define NIX_AF_TL4X_SHAPE(a) (0x1210 | (a) << 16)
-#define NIX_AF_TL4X_CIR(a) (0x1220 | (a) << 16)
-#define NIX_AF_TL4X_PIR(a) (0x1230 | (a) << 16)
-#define NIX_AF_TL4X_TOPOLOGY(a) (0x1280 | (a) << 16)
-#define NIX_AF_MDQX_SCHEDULE(a) (0x1400 | (a) << 16)
-#define NIX_AF_MDQX_SHAPE(a) (0x1410 | (a) << 16)
-#define NIX_AF_MDQX_CIR(a) (0x1420 | (a) << 16)
-#define NIX_AF_MDQX_PIR(a) (0x1430 | (a) << 16)
-#define NIX_AF_MDQX_PARENT(a) (0x1480 | (a) << 16)
-#define NIX_AF_TL3_TL2X_LINKX_CFG(a, b) (0x1700 | (a) << 16 | (b) << 3)
+#define NIX_AF_SMQX_CFG(a) (0x700 | (u64)(a) << 16)
+#define NIX_AF_TL4X_SDP_LINK_CFG(a) (0xB10 | (u64)(a) << 16)
+#define NIX_AF_TL1X_SCHEDULE(a) (0xC00 | (u64)(a) << 16)
+#define NIX_AF_TL1X_CIR(a) (0xC20 | (u64)(a) << 16)
+#define NIX_AF_TL1X_TOPOLOGY(a) (0xC80 | (u64)(a) << 16)
+#define NIX_AF_TL2X_PARENT(a) (0xE88 | (u64)(a) << 16)
+#define NIX_AF_TL2X_SCHEDULE(a) (0xE00 | (u64)(a) << 16)
+#define NIX_AF_TL2X_TOPOLOGY(a) (0xE80 | (u64)(a) << 16)
+#define NIX_AF_TL2X_CIR(a) (0xE20 | (u64)(a) << 16)
+#define NIX_AF_TL2X_PIR(a) (0xE30 | (u64)(a) << 16)
+#define NIX_AF_TL3X_PARENT(a) (0x1088 | (u64)(a) << 16)
+#define NIX_AF_TL3X_SCHEDULE(a) (0x1000 | (u64)(a) << 16)
+#define NIX_AF_TL3X_SHAPE(a) (0x1010 | (u64)(a) << 16)
+#define NIX_AF_TL3X_CIR(a) (0x1020 | (u64)(a) << 16)
+#define NIX_AF_TL3X_PIR(a) (0x1030 | (u64)(a) << 16)
+#define NIX_AF_TL3X_TOPOLOGY(a) (0x1080 | (u64)(a) << 16)
+#define NIX_AF_TL4X_PARENT(a) (0x1288 | (u64)(a) << 16)
+#define NIX_AF_TL4X_SCHEDULE(a) (0x1200 | (u64)(a) << 16)
+#define NIX_AF_TL4X_SHAPE(a) (0x1210 | (u64)(a) << 16)
+#define NIX_AF_TL4X_CIR(a) (0x1220 | (u64)(a) << 16)
+#define NIX_AF_TL4X_PIR(a) (0x1230 | (u64)(a) << 16)
+#define NIX_AF_TL4X_TOPOLOGY(a) (0x1280 | (u64)(a) << 16)
+#define NIX_AF_MDQX_SCHEDULE(a) (0x1400 | (u64)(a) << 16)
+#define NIX_AF_MDQX_SHAPE(a) (0x1410 | (u64)(a) << 16)
+#define NIX_AF_MDQX_CIR(a) (0x1420 | (u64)(a) << 16)
+#define NIX_AF_MDQX_PIR(a) (0x1430 | (u64)(a) << 16)
+#define NIX_AF_MDQX_PARENT(a) (0x1480 | (u64)(a) << 16)
+#define NIX_AF_TL3_TL2X_LINKX_CFG(a, b) (0x1700 | (u64)(a) << 16 | (b) << 3)
/* LMT LF registers */
#define LMT_LFBASE BIT_ULL(RVU_FUNC_BLKADDR_SHIFT)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 929b4eac25d9..3eb85949677a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -513,7 +513,7 @@ process_cqe:
static void otx2_adjust_adaptive_coalese(struct otx2_nic *pfvf, struct otx2_cq_poll *cq_poll)
{
- struct dim_sample dim_sample;
+ struct dim_sample dim_sample = { 0 };
u64 rx_frames, rx_bytes;
u64 tx_frames, tx_bytes;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
index edac008099c0..0f844c14485a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
@@ -153,7 +153,6 @@ static void __otx2_qos_txschq_cfg(struct otx2_nic *pfvf,
num_regs++;
otx2_config_sched_shaping(pfvf, node, cfg, &num_regs);
-
} else if (level == NIX_TXSCH_LVL_TL4) {
otx2_config_sched_shaping(pfvf, node, cfg, &num_regs);
} else if (level == NIX_TXSCH_LVL_TL3) {
@@ -176,7 +175,7 @@ static void __otx2_qos_txschq_cfg(struct otx2_nic *pfvf,
/* check if node is root */
if (node->qid == OTX2_QOS_QID_INNER && !node->parent) {
cfg->reg[num_regs] = NIX_AF_TL2X_SCHEDULE(node->schq);
- cfg->regval[num_regs] = TXSCH_TL1_DFLT_RR_PRIO << 24 |
+ cfg->regval[num_regs] = (u64)hw->txschq_aggr_lvl_rr_prio << 24 |
mtu_to_dwrr_weight(pfvf,
pfvf->tx_max_pktlen);
num_regs++;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index bf66d996e32e..c0ced4d315f3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1594,18 +1594,25 @@ static int mlxsw_pci_sys_ready_wait(struct mlxsw_pci *mlxsw_pci,
return -EBUSY;
}
-static int mlxsw_pci_reset_at_pci_disable(struct mlxsw_pci *mlxsw_pci)
+static int mlxsw_pci_reset_at_pci_disable(struct mlxsw_pci *mlxsw_pci,
+ bool pci_reset_sbr_supported)
{
struct pci_dev *pdev = mlxsw_pci->pdev;
char mrsr_pl[MLXSW_REG_MRSR_LEN];
int err;
+ if (!pci_reset_sbr_supported) {
+ pci_dbg(pdev, "Performing PCI hot reset instead of \"all reset\"\n");
+ goto sbr;
+ }
+
mlxsw_reg_mrsr_pack(mrsr_pl,
MLXSW_REG_MRSR_COMMAND_RESET_AT_PCI_DISABLE);
err = mlxsw_reg_write(mlxsw_pci->core, MLXSW_REG(mrsr), mrsr_pl);
if (err)
return err;
+sbr:
device_lock_assert(&pdev->dev);
pci_cfg_access_lock(pdev);
@@ -1633,6 +1640,7 @@ static int
mlxsw_pci_reset(struct mlxsw_pci *mlxsw_pci, const struct pci_device_id *id)
{
struct pci_dev *pdev = mlxsw_pci->pdev;
+ bool pci_reset_sbr_supported = false;
char mcam_pl[MLXSW_REG_MCAM_LEN];
bool pci_reset_supported = false;
u32 sys_status;
@@ -1652,13 +1660,17 @@ mlxsw_pci_reset(struct mlxsw_pci *mlxsw_pci, const struct pci_device_id *id)
mlxsw_reg_mcam_pack(mcam_pl,
MLXSW_REG_MCAM_FEATURE_GROUP_ENHANCED_FEATURES);
err = mlxsw_reg_query(mlxsw_pci->core, MLXSW_REG(mcam), mcam_pl);
- if (!err)
+ if (!err) {
mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_PCI_RESET,
&pci_reset_supported);
+ mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_PCI_RESET_SBR,
+ &pci_reset_sbr_supported);
+ }
if (pci_reset_supported) {
pci_dbg(pdev, "Starting PCI reset flow\n");
- err = mlxsw_pci_reset_at_pci_disable(mlxsw_pci);
+ err = mlxsw_pci_reset_at_pci_disable(mlxsw_pci,
+ pci_reset_sbr_supported);
} else {
pci_dbg(pdev, "Starting software reset flow\n");
err = mlxsw_pci_reset_sw(mlxsw_pci);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 8adf86a6f5cc..3bb89045eaf5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -10671,6 +10671,8 @@ enum mlxsw_reg_mcam_mng_feature_cap_mask_bits {
MLXSW_REG_MCAM_MCIA_128B = 34,
/* If set, MRSR.command=6 is supported. */
MLXSW_REG_MCAM_PCI_RESET = 48,
+ /* If set, MRSR.command=6 is supported with Secondary Bus Reset. */
+ MLXSW_REG_MCAM_PCI_RESET_SBR = 67,
};
#define MLXSW_REG_BYTES_PER_DWORD 0x4
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index c9f1c79f3f9d..ba090262e27e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -1607,8 +1607,8 @@ static void mlxsw_sp_sb_sr_occ_query_cb(struct mlxsw_core *mlxsw_core,
int mlxsw_sp_sb_occ_snapshot(struct mlxsw_core *mlxsw_core,
unsigned int sb_index)
{
+ u16 local_port, local_port_1, first_local_port, last_local_port;
struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
- u16 local_port, local_port_1, last_local_port;
struct mlxsw_sp_sb_sr_occ_query_cb_ctx cb_ctx;
u8 masked_count, current_page = 0;
unsigned long cb_priv = 0;
@@ -1628,6 +1628,7 @@ next_batch:
masked_count = 0;
mlxsw_reg_sbsr_pack(sbsr_pl, false);
mlxsw_reg_sbsr_port_page_set(sbsr_pl, current_page);
+ first_local_port = current_page * MLXSW_REG_SBSR_NUM_PORTS_IN_PAGE;
last_local_port = current_page * MLXSW_REG_SBSR_NUM_PORTS_IN_PAGE +
MLXSW_REG_SBSR_NUM_PORTS_IN_PAGE - 1;
@@ -1645,9 +1646,12 @@ next_batch:
if (local_port != MLXSW_PORT_CPU_PORT) {
/* Ingress quotas are not supported for the CPU port */
mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl,
- local_port, 1);
+ local_port - first_local_port,
+ 1);
}
- mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1);
+ mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl,
+ local_port - first_local_port,
+ 1);
for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) {
err = mlxsw_sp_sb_pm_occ_query(mlxsw_sp, local_port, i,
&bulk_list);
@@ -1684,7 +1688,7 @@ int mlxsw_sp_sb_occ_max_clear(struct mlxsw_core *mlxsw_core,
unsigned int sb_index)
{
struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
- u16 local_port, last_local_port;
+ u16 local_port, first_local_port, last_local_port;
LIST_HEAD(bulk_list);
unsigned int masked_count;
u8 current_page = 0;
@@ -1702,6 +1706,7 @@ next_batch:
masked_count = 0;
mlxsw_reg_sbsr_pack(sbsr_pl, true);
mlxsw_reg_sbsr_port_page_set(sbsr_pl, current_page);
+ first_local_port = current_page * MLXSW_REG_SBSR_NUM_PORTS_IN_PAGE;
last_local_port = current_page * MLXSW_REG_SBSR_NUM_PORTS_IN_PAGE +
MLXSW_REG_SBSR_NUM_PORTS_IN_PAGE - 1;
@@ -1719,9 +1724,12 @@ next_batch:
if (local_port != MLXSW_PORT_CPU_PORT) {
/* Ingress quotas are not supported for the CPU port */
mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl,
- local_port, 1);
+ local_port - first_local_port,
+ 1);
}
- mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1);
+ mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl,
+ local_port - first_local_port,
+ 1);
for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) {
err = mlxsw_sp_sb_pm_occ_clear(mlxsw_sp, local_port, i,
&bulk_list);
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index d087cf954f75..608ad31a9702 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -2798,6 +2798,8 @@ static int add_adev(struct gdma_dev *gd)
if (ret)
goto init_fail;
+ /* madev is owned by the auxiliary device */
+ madev = NULL;
ret = auxiliary_device_add(adev);
if (ret)
goto add_fail;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
index f30eee4a5a80..b6c01a88098d 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@@ -375,7 +375,9 @@ typedef void (*ionic_cq_done_cb)(void *done_arg);
unsigned int ionic_cq_service(struct ionic_cq *cq, unsigned int work_to_do,
ionic_cq_cb cb, ionic_cq_done_cb done_cb,
void *done_arg);
-unsigned int ionic_tx_cq_service(struct ionic_cq *cq, unsigned int work_to_do);
+unsigned int ionic_tx_cq_service(struct ionic_cq *cq,
+ unsigned int work_to_do,
+ bool in_napi);
int ionic_q_init(struct ionic_lif *lif, struct ionic_dev *idev,
struct ionic_queue *q, unsigned int index, const char *name,
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 1934e9d6d9e4..1837a30ba08a 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1189,7 +1189,7 @@ static int ionic_adminq_napi(struct napi_struct *napi, int budget)
ionic_rx_service, NULL, NULL);
if (lif->hwstamp_txq)
- tx_work = ionic_tx_cq_service(&lif->hwstamp_txq->cq, budget);
+ tx_work = ionic_tx_cq_service(&lif->hwstamp_txq->cq, budget, !!budget);
work_done = max(max(n_work, a_work), max(rx_work, tx_work));
if (work_done < budget && napi_complete_done(napi, work_done)) {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 2427610f4306..9fdd7cd3ef19 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -23,7 +23,8 @@ static void ionic_tx_desc_unmap_bufs(struct ionic_queue *q,
static void ionic_tx_clean(struct ionic_queue *q,
struct ionic_tx_desc_info *desc_info,
- struct ionic_txq_comp *comp);
+ struct ionic_txq_comp *comp,
+ bool in_napi);
static inline void ionic_txq_post(struct ionic_queue *q, bool ring_dbell)
{
@@ -480,6 +481,20 @@ int ionic_xdp_xmit(struct net_device *netdev, int n,
return nxmit;
}
+static void ionic_xdp_rx_put_bufs(struct ionic_queue *q,
+ struct ionic_buf_info *buf_info,
+ int nbufs)
+{
+ int i;
+
+ for (i = 0; i < nbufs; i++) {
+ dma_unmap_page(q->dev, buf_info->dma_addr,
+ IONIC_PAGE_SIZE, DMA_FROM_DEVICE);
+ buf_info->page = NULL;
+ buf_info++;
+ }
+}
+
static bool ionic_run_xdp(struct ionic_rx_stats *stats,
struct net_device *netdev,
struct bpf_prog *xdp_prog,
@@ -493,6 +508,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
struct netdev_queue *nq;
struct xdp_frame *xdpf;
int remain_len;
+ int nbufs = 1;
int frag_len;
int err = 0;
@@ -542,6 +558,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
if (page_is_pfmemalloc(bi->page))
xdp_buff_set_frag_pfmemalloc(&xdp_buf);
} while (remain_len > 0);
+ nbufs += sinfo->nr_frags;
}
xdp_action = bpf_prog_run_xdp(xdp_prog, &xdp_buf);
@@ -574,9 +591,6 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
goto out_xdp_abort;
}
- dma_unmap_page(rxq->dev, buf_info->dma_addr,
- IONIC_PAGE_SIZE, DMA_FROM_DEVICE);
-
err = ionic_xdp_post_frame(txq, xdpf, XDP_TX,
buf_info->page,
buf_info->page_offset,
@@ -586,23 +600,19 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
netdev_dbg(netdev, "tx ionic_xdp_post_frame err %d\n", err);
goto out_xdp_abort;
}
- buf_info->page = NULL;
+ ionic_xdp_rx_put_bufs(rxq, buf_info, nbufs);
stats->xdp_tx++;
/* the Tx completion will free the buffers */
break;
case XDP_REDIRECT:
- /* unmap the pages before handing them to a different device */
- dma_unmap_page(rxq->dev, buf_info->dma_addr,
- IONIC_PAGE_SIZE, DMA_FROM_DEVICE);
-
err = xdp_do_redirect(netdev, &xdp_buf, xdp_prog);
if (err) {
netdev_dbg(netdev, "xdp_do_redirect err %d\n", err);
goto out_xdp_abort;
}
- buf_info->page = NULL;
+ ionic_xdp_rx_put_bufs(rxq, buf_info, nbufs);
rxq->xdp_flush = true;
stats->xdp_redirect++;
break;
@@ -935,7 +945,7 @@ int ionic_tx_napi(struct napi_struct *napi, int budget)
u32 work_done = 0;
u32 flags = 0;
- work_done = ionic_tx_cq_service(cq, budget);
+ work_done = ionic_tx_cq_service(cq, budget, !!budget);
if (unlikely(!budget))
return budget;
@@ -1019,7 +1029,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget)
txqcq = lif->txqcqs[qi];
txcq = &lif->txqcqs[qi]->cq;
- tx_work_done = ionic_tx_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT);
+ tx_work_done = ionic_tx_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT, !!budget);
if (unlikely(!budget))
return budget;
@@ -1152,7 +1162,8 @@ static void ionic_tx_desc_unmap_bufs(struct ionic_queue *q,
static void ionic_tx_clean(struct ionic_queue *q,
struct ionic_tx_desc_info *desc_info,
- struct ionic_txq_comp *comp)
+ struct ionic_txq_comp *comp,
+ bool in_napi)
{
struct ionic_tx_stats *stats = q_to_tx_stats(q);
struct ionic_qcq *qcq = q_to_qcq(q);
@@ -1204,11 +1215,13 @@ static void ionic_tx_clean(struct ionic_queue *q,
desc_info->bytes = skb->len;
stats->clean++;
- napi_consume_skb(skb, 1);
+ napi_consume_skb(skb, likely(in_napi) ? 1 : 0);
}
static bool ionic_tx_service(struct ionic_cq *cq,
- unsigned int *total_pkts, unsigned int *total_bytes)
+ unsigned int *total_pkts,
+ unsigned int *total_bytes,
+ bool in_napi)
{
struct ionic_tx_desc_info *desc_info;
struct ionic_queue *q = cq->bound_q;
@@ -1230,7 +1243,7 @@ static bool ionic_tx_service(struct ionic_cq *cq,
desc_info->bytes = 0;
index = q->tail_idx;
q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1);
- ionic_tx_clean(q, desc_info, comp);
+ ionic_tx_clean(q, desc_info, comp, in_napi);
if (desc_info->skb) {
pkts++;
bytes += desc_info->bytes;
@@ -1244,7 +1257,9 @@ static bool ionic_tx_service(struct ionic_cq *cq,
return true;
}
-unsigned int ionic_tx_cq_service(struct ionic_cq *cq, unsigned int work_to_do)
+unsigned int ionic_tx_cq_service(struct ionic_cq *cq,
+ unsigned int work_to_do,
+ bool in_napi)
{
unsigned int work_done = 0;
unsigned int bytes = 0;
@@ -1253,7 +1268,7 @@ unsigned int ionic_tx_cq_service(struct ionic_cq *cq, unsigned int work_to_do)
if (work_to_do == 0)
return 0;
- while (ionic_tx_service(cq, &pkts, &bytes)) {
+ while (ionic_tx_service(cq, &pkts, &bytes, in_napi)) {
if (cq->tail_idx == cq->num_descs - 1)
cq->done_color = !cq->done_color;
cq->tail_idx = (cq->tail_idx + 1) & (cq->num_descs - 1);
@@ -1279,7 +1294,7 @@ void ionic_tx_flush(struct ionic_cq *cq)
{
u32 work_done;
- work_done = ionic_tx_cq_service(cq, cq->num_descs);
+ work_done = ionic_tx_cq_service(cq, cq->num_descs, false);
if (work_done)
ionic_intr_credits(cq->idev->intr_ctrl, cq->bound_intr->index,
work_done, IONIC_INTR_CRED_RESET_COALESCE);
@@ -1296,7 +1311,7 @@ void ionic_tx_empty(struct ionic_queue *q)
desc_info = &q->tx_info[q->tail_idx];
desc_info->bytes = 0;
q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1);
- ionic_tx_clean(q, desc_info, NULL);
+ ionic_tx_clean(q, desc_info, NULL, false);
if (desc_info->skb) {
pkts++;
bytes += desc_info->bytes;
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 5aada7cf3da7..ebafedde0ab7 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -5607,6 +5607,7 @@ static struct mdio_device_id __maybe_unused micrel_tbl[] = {
{ PHY_ID_KSZ8081, MICREL_PHY_ID_MASK },
{ PHY_ID_KSZ8873MLL, MICREL_PHY_ID_MASK },
{ PHY_ID_KSZ886X, MICREL_PHY_ID_MASK },
+ { PHY_ID_KSZ9477, MICREL_PHY_ID_MASK },
{ PHY_ID_LAN8814, MICREL_PHY_ID_MASK },
{ PHY_ID_LAN8804, MICREL_PHY_ID_MASK },
{ PHY_ID_LAN8841, MICREL_PHY_ID_MASK },
diff --git a/drivers/net/pse-pd/Kconfig b/drivers/net/pse-pd/Kconfig
index 577ea904b3d9..7fab916a7f46 100644
--- a/drivers/net/pse-pd/Kconfig
+++ b/drivers/net/pse-pd/Kconfig
@@ -23,6 +23,7 @@ config PSE_REGULATOR
config PSE_PD692X0
tristate "PD692X0 PSE controller"
depends on I2C
+ select FW_LOADER
select FW_UPLOAD
help
This module provides support for PD692x0 regulator based Ethernet
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index c2fb736f78b2..b034ef8a73ea 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -326,7 +326,8 @@ static void ax88179_status(struct usbnet *dev, struct urb *urb)
if (netif_carrier_ok(dev->net) != link) {
usbnet_link_change(dev, link, 1);
- netdev_info(dev->net, "ax88179 - Link status is: %d\n", link);
+ if (!link)
+ netdev_info(dev->net, "ax88179 - Link status is: 0\n");
}
}
@@ -1542,6 +1543,7 @@ static int ax88179_link_reset(struct usbnet *dev)
GMII_PHY_PHYSR, 2, &tmp16);
if (!(tmp16 & GMII_PHY_PHYSR_LINK)) {
+ netdev_info(dev->net, "ax88179 - Link status is: 0\n");
return 0;
} else if (GMII_PHY_PHYSR_GIGA == (tmp16 & GMII_PHY_PHYSR_SMASK)) {
mode |= AX_MEDIUM_GIGAMODE | AX_MEDIUM_EN_125MHZ;
@@ -1579,6 +1581,8 @@ static int ax88179_link_reset(struct usbnet *dev)
netif_carrier_on(dev->net);
+ netdev_info(dev->net, "ax88179 - Link status is: 1\n");
+
return 0;
}
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 663e46348ce3..386d62769ded 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1372,6 +1372,8 @@ static const struct usb_device_id products[] = {
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1260, 2)}, /* Telit LE910Cx */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1261, 2)}, /* Telit LE910Cx */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1900, 1)}, /* Telit LN940 series */
+ {QMI_QUIRK_SET_DTR(0x1bc7, 0x3000, 0)}, /* Telit FN912 series */
+ {QMI_QUIRK_SET_DTR(0x1bc7, 0x3001, 0)}, /* Telit FN912 series */
{QMI_FIXED_INTF(0x1c9e, 0x9801, 3)}, /* Telewell TW-3G HSPA+ */
{QMI_FIXED_INTF(0x1c9e, 0x9803, 4)}, /* Telewell TW-3G HSPA+ */
{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)}, /* XS Stick W100-2 from 4G Systems */
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 567cb3faab70..ba59e92ab941 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -2339,7 +2339,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct ip_tunnel_key *pkey;
struct ip_tunnel_key key;
struct vxlan_dev *vxlan = netdev_priv(dev);
- const struct iphdr *old_iph = ip_hdr(skb);
+ const struct iphdr *old_iph;
struct vxlan_metadata _md;
struct vxlan_metadata *md = &_md;
unsigned int pkt_len = skb->len;
@@ -2353,8 +2353,15 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
bool use_cache;
bool udp_sum = false;
bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev));
+ bool no_eth_encap;
__be32 vni = 0;
+ no_eth_encap = flags & VXLAN_F_GPE && skb->protocol != htons(ETH_P_TEB);
+ if (!skb_vlan_inet_prepare(skb, no_eth_encap))
+ goto drop;
+
+ old_iph = ip_hdr(skb);
+
info = skb_tunnel_info(skb);
use_cache = ip_tunnel_dst_cache_usable(skb, info);
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 7d6b1254c92d..c0deaafebfdc 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -263,7 +263,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
struct request_sock *req,
struct sock *child);
-void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
+bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
unsigned long timeout);
struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
struct request_sock *req,
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 2796153b03da..188d41da1a40 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -619,6 +619,11 @@ static inline void *nft_set_priv(const struct nft_set *set)
return (void *)set->data;
}
+static inline enum nft_data_types nft_set_datatype(const struct nft_set *set)
+{
+ return set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE;
+}
+
static inline bool nft_set_gc_is_pending(const struct nft_set *s)
{
return refcount_read(&s->refs) != 1;
diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h
index f1b5e816e7e5..ff33f41a9db7 100644
--- a/include/trace/events/qdisc.h
+++ b/include/trace/events/qdisc.h
@@ -81,7 +81,7 @@ TRACE_EVENT(qdisc_reset,
TP_ARGS(q),
TP_STRUCT__entry(
- __string( dev, qdisc_dev(q)->name )
+ __string( dev, qdisc_dev(q) ? qdisc_dev(q)->name : "(null)" )
__string( kind, q->ops->id )
__field( u32, parent )
__field( u32, handle )
diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index 583ee4fe48ef..e52b3ad231b9 100644
--- a/kernel/bpf/arena.c
+++ b/kernel/bpf/arena.c
@@ -212,6 +212,7 @@ static u64 arena_map_mem_usage(const struct bpf_map *map)
struct vma_list {
struct vm_area_struct *vma;
struct list_head head;
+ atomic_t mmap_count;
};
static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma)
@@ -221,20 +222,30 @@ static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma)
vml = kmalloc(sizeof(*vml), GFP_KERNEL);
if (!vml)
return -ENOMEM;
+ atomic_set(&vml->mmap_count, 1);
vma->vm_private_data = vml;
vml->vma = vma;
list_add(&vml->head, &arena->vma_list);
return 0;
}
+static void arena_vm_open(struct vm_area_struct *vma)
+{
+ struct vma_list *vml = vma->vm_private_data;
+
+ atomic_inc(&vml->mmap_count);
+}
+
static void arena_vm_close(struct vm_area_struct *vma)
{
struct bpf_map *map = vma->vm_file->private_data;
struct bpf_arena *arena = container_of(map, struct bpf_arena, map);
- struct vma_list *vml;
+ struct vma_list *vml = vma->vm_private_data;
+ if (!atomic_dec_and_test(&vml->mmap_count))
+ return;
guard(mutex)(&arena->lock);
- vml = vma->vm_private_data;
+ /* update link list under lock */
list_del(&vml->head);
vma->vm_private_data = NULL;
kfree(vml);
@@ -287,6 +298,7 @@ out:
}
static const struct vm_operations_struct arena_vm_ops = {
+ .open = arena_vm_open,
.close = arena_vm_close,
.fault = arena_vm_fault,
};
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 0ee653a936ea..e20b90c36131 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -51,7 +51,8 @@ struct bpf_ringbuf {
* This prevents a user-space application from modifying the
* position and ruining in-kernel tracking. The permissions of the
* pages depend on who is producing samples: user-space or the
- * kernel.
+ * kernel. Note that the pending counter is placed in the same
+ * page as the producer, so that it shares the same cache line.
*
* Kernel-producer
* ---------------
@@ -70,6 +71,7 @@ struct bpf_ringbuf {
*/
unsigned long consumer_pos __aligned(PAGE_SIZE);
unsigned long producer_pos __aligned(PAGE_SIZE);
+ unsigned long pending_pos;
char data[] __aligned(PAGE_SIZE);
};
@@ -179,6 +181,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
rb->mask = data_sz - 1;
rb->consumer_pos = 0;
rb->producer_pos = 0;
+ rb->pending_pos = 0;
return rb;
}
@@ -404,9 +407,9 @@ bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr)
static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
{
- unsigned long cons_pos, prod_pos, new_prod_pos, flags;
- u32 len, pg_off;
+ unsigned long cons_pos, prod_pos, new_prod_pos, pend_pos, flags;
struct bpf_ringbuf_hdr *hdr;
+ u32 len, pg_off, tmp_size, hdr_len;
if (unlikely(size > RINGBUF_MAX_RECORD_SZ))
return NULL;
@@ -424,13 +427,29 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
spin_lock_irqsave(&rb->spinlock, flags);
}
+ pend_pos = rb->pending_pos;
prod_pos = rb->producer_pos;
new_prod_pos = prod_pos + len;
- /* check for out of ringbuf space by ensuring producer position
- * doesn't advance more than (ringbuf_size - 1) ahead
+ while (pend_pos < prod_pos) {
+ hdr = (void *)rb->data + (pend_pos & rb->mask);
+ hdr_len = READ_ONCE(hdr->len);
+ if (hdr_len & BPF_RINGBUF_BUSY_BIT)
+ break;
+ tmp_size = hdr_len & ~BPF_RINGBUF_DISCARD_BIT;
+ tmp_size = round_up(tmp_size + BPF_RINGBUF_HDR_SZ, 8);
+ pend_pos += tmp_size;
+ }
+ rb->pending_pos = pend_pos;
+
+ /* check for out of ringbuf space:
+ * - by ensuring producer position doesn't advance more than
+ * (ringbuf_size - 1) ahead
+ * - by ensuring oldest not yet committed record until newest
+ * record does not span more than (ringbuf_size - 1)
*/
- if (new_prod_pos - cons_pos > rb->mask) {
+ if (new_prod_pos - cons_pos > rb->mask ||
+ new_prod_pos - pend_pos > rb->mask) {
spin_unlock_irqrestore(&rb->spinlock, flags);
return NULL;
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 010cfee7ffe9..214a9fa8c6fb 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6236,6 +6236,7 @@ static void set_sext32_default_val(struct bpf_reg_state *reg, int size)
}
reg->u32_min_value = 0;
reg->u32_max_value = U32_MAX;
+ reg->var_off = tnum_subreg(tnum_unknown);
}
static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size)
@@ -6280,6 +6281,7 @@ static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size)
reg->s32_max_value = s32_max;
reg->u32_min_value = (u32)s32_min;
reg->u32_max_value = (u32)s32_max;
+ reg->var_off = tnum_subreg(tnum_range(s32_min, s32_max));
return;
}
@@ -12719,6 +12721,16 @@ static bool signed_add32_overflows(s32 a, s32 b)
return res < a;
}
+static bool signed_add16_overflows(s16 a, s16 b)
+{
+ /* Do the add in u16, where overflow is well-defined */
+ s16 res = (s16)((u16)a + (u16)b);
+
+ if (b < 0)
+ return res > a;
+ return res < a;
+}
+
static bool signed_sub_overflows(s64 a, s64 b)
{
/* Do the sub in u64, where overflow is well-defined */
@@ -17448,11 +17460,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
goto skip_inf_loop_check;
}
if (is_may_goto_insn_at(env, insn_idx)) {
- if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) {
+ if (sl->state.may_goto_depth != cur->may_goto_depth &&
+ states_equal(env, &sl->state, cur, RANGE_WITHIN)) {
update_loop_entry(cur, &sl->state);
goto hit;
}
- goto skip_inf_loop_check;
}
if (calls_callback(env, insn_idx)) {
if (states_equal(env, &sl->state, cur, RANGE_WITHIN))
@@ -18730,6 +18742,39 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
return new_prog;
}
+/*
+ * For all jmp insns in a given 'prog' that point to 'tgt_idx' insn adjust the
+ * jump offset by 'delta'.
+ */
+static int adjust_jmp_off(struct bpf_prog *prog, u32 tgt_idx, u32 delta)
+{
+ struct bpf_insn *insn = prog->insnsi;
+ u32 insn_cnt = prog->len, i;
+
+ for (i = 0; i < insn_cnt; i++, insn++) {
+ u8 code = insn->code;
+
+ if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) ||
+ BPF_OP(code) == BPF_CALL || BPF_OP(code) == BPF_EXIT)
+ continue;
+
+ if (insn->code == (BPF_JMP32 | BPF_JA)) {
+ if (i + 1 + insn->imm != tgt_idx)
+ continue;
+ if (signed_add32_overflows(insn->imm, delta))
+ return -ERANGE;
+ insn->imm += delta;
+ } else {
+ if (i + 1 + insn->off != tgt_idx)
+ continue;
+ if (signed_add16_overflows(insn->imm, delta))
+ return -ERANGE;
+ insn->off += delta;
+ }
+ }
+ return 0;
+}
+
static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env,
u32 off, u32 cnt)
{
@@ -20004,7 +20049,10 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
stack_depth_extra = 8;
insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_AX, BPF_REG_10, stack_off);
- insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2);
+ if (insn->off >= 0)
+ insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2);
+ else
+ insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off - 1);
insn_buf[2] = BPF_ALU64_IMM(BPF_SUB, BPF_REG_AX, 1);
insn_buf[3] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_AX, stack_off);
cnt = 4;
@@ -20546,6 +20594,13 @@ next_insn:
if (!new_prog)
return -ENOMEM;
env->prog = prog = new_prog;
+ /*
+ * If may_goto is a first insn of a prog there could be a jmp
+ * insn that points to it, hence adjust all such jmps to point
+ * to insn after BPF_ST that inits may_goto count.
+ * Adjustment will succeed because bpf_patch_insn_data() didn't fail.
+ */
+ WARN_ON(adjust_jmp_off(env->prog, subprog_start, 1));
}
/* Since poke tab is now finalized, publish aux to tracker. */
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index ac74f6ead62d..8f6dd2c6ee41 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -12,6 +12,7 @@
#include <linux/errno.h>
#include <linux/etherdevice.h>
#include <linux/gfp.h>
+#include <linux/if_vlan.h>
#include <linux/jiffies.h>
#include <linux/kref.h>
#include <linux/list.h>
@@ -132,6 +133,29 @@ batadv_orig_node_vlan_get(struct batadv_orig_node *orig_node,
}
/**
+ * batadv_vlan_id_valid() - check if vlan id is in valid batman-adv encoding
+ * @vid: the VLAN identifier
+ *
+ * Return: true when either no vlan is set or if VLAN is in correct range,
+ * false otherwise
+ */
+static bool batadv_vlan_id_valid(unsigned short vid)
+{
+ unsigned short non_vlan = vid & ~(BATADV_VLAN_HAS_TAG | VLAN_VID_MASK);
+
+ if (vid == 0)
+ return true;
+
+ if (!(vid & BATADV_VLAN_HAS_TAG))
+ return false;
+
+ if (non_vlan)
+ return false;
+
+ return true;
+}
+
+/**
* batadv_orig_node_vlan_new() - search and possibly create an orig_node_vlan
* object
* @orig_node: the originator serving the VLAN
@@ -149,6 +173,9 @@ batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node,
{
struct batadv_orig_node_vlan *vlan;
+ if (!batadv_vlan_id_valid(vid))
+ return NULL;
+
spin_lock_bh(&orig_node->vlan_list_lock);
/* first look if an object for this vid already exists */
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index b21ff3c36b07..2243cec18ecc 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -209,6 +209,20 @@ batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const u8 *addr,
}
/**
+ * batadv_tt_local_entry_free_rcu() - free the tt_local_entry
+ * @rcu: rcu pointer of the tt_local_entry
+ */
+static void batadv_tt_local_entry_free_rcu(struct rcu_head *rcu)
+{
+ struct batadv_tt_local_entry *tt_local_entry;
+
+ tt_local_entry = container_of(rcu, struct batadv_tt_local_entry,
+ common.rcu);
+
+ kmem_cache_free(batadv_tl_cache, tt_local_entry);
+}
+
+/**
* batadv_tt_local_entry_release() - release tt_local_entry from lists and queue
* for free after rcu grace period
* @ref: kref pointer of the nc_node
@@ -222,7 +236,7 @@ static void batadv_tt_local_entry_release(struct kref *ref)
batadv_softif_vlan_put(tt_local_entry->vlan);
- kfree_rcu(tt_local_entry, common.rcu);
+ call_rcu(&tt_local_entry->common.rcu, batadv_tt_local_entry_free_rcu);
}
/**
@@ -241,6 +255,20 @@ batadv_tt_local_entry_put(struct batadv_tt_local_entry *tt_local_entry)
}
/**
+ * batadv_tt_global_entry_free_rcu() - free the tt_global_entry
+ * @rcu: rcu pointer of the tt_global_entry
+ */
+static void batadv_tt_global_entry_free_rcu(struct rcu_head *rcu)
+{
+ struct batadv_tt_global_entry *tt_global_entry;
+
+ tt_global_entry = container_of(rcu, struct batadv_tt_global_entry,
+ common.rcu);
+
+ kmem_cache_free(batadv_tg_cache, tt_global_entry);
+}
+
+/**
* batadv_tt_global_entry_release() - release tt_global_entry from lists and
* queue for free after rcu grace period
* @ref: kref pointer of the nc_node
@@ -254,7 +282,7 @@ void batadv_tt_global_entry_release(struct kref *ref)
batadv_tt_global_del_orig_list(tt_global_entry);
- kfree_rcu(tt_global_entry, common.rcu);
+ call_rcu(&tt_global_entry->common.rcu, batadv_tt_global_entry_free_rcu);
}
/**
@@ -380,6 +408,19 @@ static void batadv_tt_global_size_dec(struct batadv_orig_node *orig_node,
}
/**
+ * batadv_tt_orig_list_entry_free_rcu() - free the orig_entry
+ * @rcu: rcu pointer of the orig_entry
+ */
+static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu)
+{
+ struct batadv_tt_orig_list_entry *orig_entry;
+
+ orig_entry = container_of(rcu, struct batadv_tt_orig_list_entry, rcu);
+
+ kmem_cache_free(batadv_tt_orig_cache, orig_entry);
+}
+
+/**
* batadv_tt_orig_list_entry_release() - release tt orig entry from lists and
* queue for free after rcu grace period
* @ref: kref pointer of the tt orig entry
@@ -392,7 +433,7 @@ static void batadv_tt_orig_list_entry_release(struct kref *ref)
refcount);
batadv_orig_node_put(orig_entry->orig_node);
- kfree_rcu(orig_entry, rcu);
+ call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu);
}
/**
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index a6fb89fa6278..7e8a20f2fc42 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -30,10 +30,6 @@ MODULE_ALIAS("can-proto-" __stringify(CAN_J1939));
/* CAN_HDR: #bytes before can_frame data part */
#define J1939_CAN_HDR (offsetof(struct can_frame, data))
-/* CAN_FTR: #bytes beyond data part */
-#define J1939_CAN_FTR (sizeof(struct can_frame) - J1939_CAN_HDR - \
- sizeof(((struct can_frame *)0)->data))
-
/* lowest layer */
static void j1939_can_recv(struct sk_buff *iskb, void *data)
{
@@ -342,7 +338,7 @@ int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb)
memset(cf, 0, J1939_CAN_HDR);
/* make it a full can frame again */
- skb_put(skb, J1939_CAN_FTR + (8 - dlc));
+ skb_put_zero(skb, 8 - dlc);
canid = CAN_EFF_FLAG |
(skcb->priority << 26) |
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index fe3df23a2595..4be73de5033c 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1593,8 +1593,8 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv,
struct j1939_sk_buff_cb skcb = *j1939_skb_to_cb(skb);
struct j1939_session *session;
const u8 *dat;
+ int len, ret;
pgn_t pgn;
- int len;
netdev_dbg(priv->ndev, "%s\n", __func__);
@@ -1653,7 +1653,22 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv,
session->tskey = priv->rx_tskey++;
j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_RTS);
- WARN_ON_ONCE(j1939_session_activate(session));
+ ret = j1939_session_activate(session);
+ if (ret) {
+ /* Entering this scope indicates an issue with the J1939 bus.
+ * Possible scenarios include:
+ * - A time lapse occurred, and a new session was initiated
+ * due to another packet being sent correctly. This could
+ * have been caused by too long interrupt, debugger, or being
+ * out-scheduled by another task.
+ * - The bus is receiving numerous erroneous packets, either
+ * from a malfunctioning device or during a test scenario.
+ */
+ netdev_alert(priv->ndev, "%s: 0x%p: concurrent session with same addr (%02x %02x) is already active.\n",
+ __func__, session, skcb.addr.sa, skcb.addr.da);
+ j1939_session_put(session);
+ return NULL;
+ }
return session;
}
@@ -1681,6 +1696,8 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session,
j1939_session_timers_cancel(session);
j1939_session_cancel(session, J1939_XTP_ABORT_BUSY);
+ if (session->transmission)
+ j1939_session_deactivate_activate_next(session);
return -EBUSY;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 4d4de9008f6f..2b4819b610b8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1226,9 +1226,9 @@ int dev_change_name(struct net_device *dev, const char *newname)
memcpy(oldname, dev->name, IFNAMSIZ);
- write_seqlock(&netdev_rename_lock);
+ write_seqlock_bh(&netdev_rename_lock);
err = dev_get_valid_name(net, dev, newname);
- write_sequnlock(&netdev_rename_lock);
+ write_sequnlock_bh(&netdev_rename_lock);
if (err < 0) {
up_write(&devnet_rename_sem);
@@ -1269,9 +1269,9 @@ rollback:
if (err >= 0) {
err = ret;
down_write(&devnet_rename_sem);
- write_seqlock(&netdev_rename_lock);
+ write_seqlock_bh(&netdev_rename_lock);
memcpy(dev->name, oldname, IFNAMSIZ);
- write_sequnlock(&netdev_rename_lock);
+ write_sequnlock_bh(&netdev_rename_lock);
memcpy(oldname, newname, IFNAMSIZ);
WRITE_ONCE(dev->name_assign_type, old_assign_type);
old_assign_type = NET_NAME_RENAMED;
@@ -11419,9 +11419,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
if (new_name[0]) {
/* Rename the netdev to prepared name */
- write_seqlock(&netdev_rename_lock);
+ write_seqlock_bh(&netdev_rename_lock);
strscpy(dev->name, new_name, IFNAMSIZ);
- write_sequnlock(&netdev_rename_lock);
+ write_sequnlock_bh(&netdev_rename_lock);
}
/* Fixup kobjects */
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 41693154e426..022c12059cf2 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -295,10 +295,8 @@ static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem,
mutex_lock(&mem_id_lock);
ret = __mem_id_init_hash_table();
mutex_unlock(&mem_id_lock);
- if (ret < 0) {
- WARN_ON(1);
+ if (ret < 0)
return ERR_PTR(ret);
- }
}
xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index ff41bd6f99c3..5926159a6f20 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -657,8 +657,11 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
if (dccp_v4_send_response(sk, req))
goto drop_and_free;
- inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
- reqsk_put(req);
+ if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT)))
+ reqsk_free(req);
+ else
+ reqsk_put(req);
+
return 0;
drop_and_free:
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 85f4b8fdbe5e..da5dba120bc9 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -400,8 +400,11 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
if (dccp_v6_send_response(sk, req))
goto drop_and_free;
- inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
- reqsk_put(req);
+ if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT)))
+ reqsk_free(req);
+ else
+ reqsk_put(req);
+
return 0;
drop_and_free:
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d81f74ce0f02..d4f0eff8b20f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1122,25 +1122,34 @@ drop:
inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq);
}
-static void reqsk_queue_hash_req(struct request_sock *req,
+static bool reqsk_queue_hash_req(struct request_sock *req,
unsigned long timeout)
{
+ bool found_dup_sk = false;
+
+ if (!inet_ehash_insert(req_to_sk(req), NULL, &found_dup_sk))
+ return false;
+
+ /* The timer needs to be setup after a successful insertion. */
timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
mod_timer(&req->rsk_timer, jiffies + timeout);
- inet_ehash_insert(req_to_sk(req), NULL, NULL);
/* before letting lookups find us, make sure all req fields
* are committed to memory and refcnt initialized.
*/
smp_wmb();
refcount_set(&req->rsk_refcnt, 2 + 1);
+ return true;
}
-void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
+bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
unsigned long timeout)
{
- reqsk_queue_hash_req(req, timeout);
+ if (!reqsk_queue_hash_req(req, timeout))
+ return false;
+
inet_csk_reqsk_queue_added(sk);
+ return true;
}
EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 01d208e0eef3..2e39cb881e20 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2782,13 +2782,37 @@ static void tcp_mtup_probe_success(struct sock *sk)
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS);
}
+/* Sometimes we deduce that packets have been dropped due to reasons other than
+ * congestion, like path MTU reductions or failed client TFO attempts. In these
+ * cases we call this function to retransmit as many packets as cwnd allows,
+ * without reducing cwnd. Given that retransmits will set retrans_stamp to a
+ * non-zero value (and may do so in a later calling context due to TSQ), we
+ * also enter CA_Loss so that we track when all retransmitted packets are ACKed
+ * and clear retrans_stamp when that happens (to ensure later recurring RTOs
+ * are using the correct retrans_stamp and don't declare ETIMEDOUT
+ * prematurely).
+ */
+static void tcp_non_congestion_loss_retransmit(struct sock *sk)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (icsk->icsk_ca_state != TCP_CA_Loss) {
+ tp->high_seq = tp->snd_nxt;
+ tp->snd_ssthresh = tcp_current_ssthresh(sk);
+ tp->prior_ssthresh = 0;
+ tp->undo_marker = 0;
+ tcp_set_ca_state(sk, TCP_CA_Loss);
+ }
+ tcp_xmit_retransmit_queue(sk);
+}
+
/* Do a simple retransmit without using the backoff mechanisms in
* tcp_timer. This is used for path mtu discovery.
* The socket is already locked here.
*/
void tcp_simple_retransmit(struct sock *sk)
{
- const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int mss;
@@ -2828,14 +2852,7 @@ void tcp_simple_retransmit(struct sock *sk)
* in network, but units changed and effective
* cwnd/ssthresh really reduced now.
*/
- if (icsk->icsk_ca_state != TCP_CA_Loss) {
- tp->high_seq = tp->snd_nxt;
- tp->snd_ssthresh = tcp_current_ssthresh(sk);
- tp->prior_ssthresh = 0;
- tp->undo_marker = 0;
- tcp_set_ca_state(sk, TCP_CA_Loss);
- }
- tcp_xmit_retransmit_queue(sk);
+ tcp_non_congestion_loss_retransmit(sk);
}
EXPORT_SYMBOL(tcp_simple_retransmit);
@@ -6295,8 +6312,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
tp->fastopen_client_fail = TFO_DATA_NOT_ACKED;
skb_rbtree_walk_from(data)
tcp_mark_skb_lost(sk, data);
- tcp_xmit_retransmit_queue(sk);
- tp->retrans_stamp = 0;
+ tcp_non_congestion_loss_retransmit(sk);
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPFASTOPENACTIVEFAIL);
return true;
@@ -7257,7 +7273,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
tcp_rsk(req)->tfo_listener = false;
if (!want_cookie) {
req->timeout = tcp_timeout_init((struct sock *)req);
- inet_csk_reqsk_queue_hash_add(sk, req, req->timeout);
+ if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req,
+ req->timeout))) {
+ reqsk_free(req);
+ return 0;
+ }
+
}
af_ops->send_synack(sk, dst, &fl, req, &foc,
!want_cookie ? TCP_SYNACK_NORMAL :
diff --git a/net/netfilter/nf_hooks_lwtunnel.c b/net/netfilter/nf_hooks_lwtunnel.c
index 7cdb59bb4459..d8ebebc9775d 100644
--- a/net/netfilter/nf_hooks_lwtunnel.c
+++ b/net/netfilter/nf_hooks_lwtunnel.c
@@ -117,4 +117,7 @@ void netfilter_lwtunnel_fini(void)
{
unregister_pernet_subsys(&nf_lwtunnel_net_ops);
}
+#else
+int __init netfilter_lwtunnel_init(void) { return 0; }
+void netfilter_lwtunnel_fini(void) {}
#endif /* CONFIG_SYSCTL */
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index be3b4c90d2ed..e8dcf41d360d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5740,8 +5740,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext),
- set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE,
- set->dlen) < 0)
+ nft_set_datatype(set), set->dlen) < 0)
goto nla_put_failure;
if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS) &&
@@ -11073,6 +11072,9 @@ static int nft_validate_register_store(const struct nft_ctx *ctx,
return 0;
default:
+ if (type != NFT_DATA_VALUE)
+ return -EINVAL;
+
if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE)
return -EINVAL;
if (len == 0)
@@ -11081,8 +11083,6 @@ static int nft_validate_register_store(const struct nft_ctx *ctx,
sizeof_field(struct nft_regs, data))
return -ERANGE;
- if (data != NULL && type != NFT_DATA_VALUE)
- return -EINVAL;
return 0;
}
}
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index b314ca728a29..f3080fa1b226 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -132,7 +132,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
return -EINVAL;
err = nft_parse_register_store(ctx, tb[NFTA_LOOKUP_DREG],
- &priv->dreg, NULL, set->dtype,
+ &priv->dreg, NULL,
+ nft_set_datatype(set),
set->dlen);
if (err < 0)
return err;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 2928c142a2dd..3b980bf2770b 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -168,8 +168,13 @@ static u32 ovs_ct_get_mark(const struct nf_conn *ct)
static void ovs_ct_get_labels(const struct nf_conn *ct,
struct ovs_key_ct_labels *labels)
{
- struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL;
+ struct nf_conn_labels *cl = NULL;
+ if (ct) {
+ if (ct->master && !nf_ct_is_confirmed(ct))
+ ct = ct->master;
+ cl = nf_ct_labels_find(ct);
+ }
if (cl)
memcpy(labels, cl->bits, OVS_CT_LABELS_LEN);
else
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5e695a9a609c..142f56770b77 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2613,10 +2613,24 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
{
struct unix_sock *u = unix_sk(sk);
- if (!unix_skb_len(skb) && !(flags & MSG_PEEK)) {
- skb_unlink(skb, &sk->sk_receive_queue);
- consume_skb(skb);
- skb = NULL;
+ if (!unix_skb_len(skb)) {
+ struct sk_buff *unlinked_skb = NULL;
+
+ spin_lock(&sk->sk_receive_queue.lock);
+
+ if (copied && (!u->oob_skb || skb == u->oob_skb)) {
+ skb = NULL;
+ } else if (flags & MSG_PEEK) {
+ skb = skb_peek_next(skb, &sk->sk_receive_queue);
+ } else {
+ unlinked_skb = skb;
+ skb = skb_peek_next(skb, &sk->sk_receive_queue);
+ __skb_unlink(unlinked_skb, &sk->sk_receive_queue);
+ }
+
+ spin_unlock(&sk->sk_receive_queue.lock);
+
+ consume_skb(unlinked_skb);
} else {
struct sk_buff *unlinked_skb = NULL;
@@ -3093,12 +3107,23 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
case SIOCATMARK:
{
+ struct unix_sock *u = unix_sk(sk);
struct sk_buff *skb;
int answ = 0;
+ mutex_lock(&u->iolock);
+
skb = skb_peek(&sk->sk_receive_queue);
- if (skb && skb == READ_ONCE(unix_sk(sk)->oob_skb))
- answ = 1;
+ if (skb) {
+ struct sk_buff *oob_skb = READ_ONCE(u->oob_skb);
+
+ if (skb == oob_skb ||
+ (!oob_skb && !unix_skb_len(skb)))
+ answ = 1;
+ }
+
+ mutex_unlock(&u->iolock);
+
err = put_user(answ, (int __user *)arg);
}
break;
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e0b3887b3d2d..dd49c1d23a60 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -457,7 +457,7 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \
LSKELS := fentry_test.c fexit_test.c fexit_sleep.c atomics.c \
trace_printk.c trace_vprintk.c map_ptr_kern.c \
core_kern.c core_kern_overflow.c test_ringbuf.c \
- test_ringbuf_n.c test_ringbuf_map_key.c
+ test_ringbuf_n.c test_ringbuf_map_key.c test_ringbuf_write.c
# Generate both light skeleton and libbpf skeleton for these
LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test.c \
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index 4c6f42dae409..da430df45aa4 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -12,9 +12,11 @@
#include <sys/sysinfo.h>
#include <linux/perf_event.h>
#include <linux/ring_buffer.h>
+
#include "test_ringbuf.lskel.h"
#include "test_ringbuf_n.lskel.h"
#include "test_ringbuf_map_key.lskel.h"
+#include "test_ringbuf_write.lskel.h"
#define EDONE 7777
@@ -84,6 +86,58 @@ static void *poll_thread(void *input)
return (void *)(long)ring_buffer__poll(ringbuf, timeout);
}
+static void ringbuf_write_subtest(void)
+{
+ struct test_ringbuf_write_lskel *skel;
+ int page_size = getpagesize();
+ size_t *mmap_ptr;
+ int err, rb_fd;
+
+ skel = test_ringbuf_write_lskel__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ skel->maps.ringbuf.max_entries = 0x4000;
+
+ err = test_ringbuf_write_lskel__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto cleanup;
+
+ rb_fd = skel->maps.ringbuf.map_fd;
+
+ mmap_ptr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rb_fd, 0);
+ if (!ASSERT_OK_PTR(mmap_ptr, "rw_cons_pos"))
+ goto cleanup;
+ *mmap_ptr = 0x3000;
+ ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_rw");
+
+ skel->bss->pid = getpid();
+
+ ringbuf = ring_buffer__new(rb_fd, process_sample, NULL, NULL);
+ if (!ASSERT_OK_PTR(ringbuf, "ringbuf_new"))
+ goto cleanup;
+
+ err = test_ringbuf_write_lskel__attach(skel);
+ if (!ASSERT_OK(err, "skel_attach"))
+ goto cleanup_ringbuf;
+
+ skel->bss->discarded = 0;
+ skel->bss->passed = 0;
+
+ /* trigger exactly two samples */
+ syscall(__NR_getpgid);
+ syscall(__NR_getpgid);
+
+ ASSERT_EQ(skel->bss->discarded, 2, "discarded");
+ ASSERT_EQ(skel->bss->passed, 0, "passed");
+
+ test_ringbuf_write_lskel__detach(skel);
+cleanup_ringbuf:
+ ring_buffer__free(ringbuf);
+cleanup:
+ test_ringbuf_write_lskel__destroy(skel);
+}
+
static void ringbuf_subtest(void)
{
const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample);
@@ -451,4 +505,6 @@ void test_ringbuf(void)
ringbuf_n_subtest();
if (test__start_subtest("ringbuf_map_key"))
ringbuf_map_key_subtest();
+ if (test__start_subtest("ringbuf_write"))
+ ringbuf_write_subtest();
}
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_write.c b/tools/testing/selftests/bpf/progs/test_ringbuf_write.c
new file mode 100644
index 000000000000..350513c0e4c9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf_write.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_RINGBUF);
+} ringbuf SEC(".maps");
+
+/* inputs */
+int pid = 0;
+
+/* outputs */
+long passed = 0;
+long discarded = 0;
+
+SEC("fentry/" SYS_PREFIX "sys_getpgid")
+int test_ringbuf_write(void *ctx)
+{
+ int *foo, cur_pid = bpf_get_current_pid_tgid() >> 32;
+ void *sample1, *sample2;
+
+ if (cur_pid != pid)
+ return 0;
+
+ sample1 = bpf_ringbuf_reserve(&ringbuf, 0x3000, 0);
+ if (!sample1)
+ return 0;
+ /* first one can pass */
+ sample2 = bpf_ringbuf_reserve(&ringbuf, 0x3000, 0);
+ if (!sample2) {
+ bpf_ringbuf_discard(sample1, 0);
+ __sync_fetch_and_add(&discarded, 1);
+ return 0;
+ }
+ /* second one must not */
+ __sync_fetch_and_add(&passed, 1);
+ foo = sample2 + 4084;
+ *foo = 256;
+ bpf_ringbuf_discard(sample1, 0);
+ bpf_ringbuf_discard(sample2, 0);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
index bd676d7e615f..80c737b6d340 100644
--- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
+++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
@@ -274,6 +274,58 @@ static __naked void iter_limit_bug_cb(void)
);
}
+int tmp_var;
+SEC("socket")
+__failure __msg("infinite loop detected at insn 2")
+__naked void jgt_imm64_and_may_goto(void)
+{
+ asm volatile (" \
+ r0 = %[tmp_var] ll; \
+l0_%=: .byte 0xe5; /* may_goto */ \
+ .byte 0; /* regs */ \
+ .short -3; /* off -3 */ \
+ .long 0; /* imm */ \
+ if r0 > 10 goto l0_%=; \
+ r0 = 0; \
+ exit; \
+" :: __imm_addr(tmp_var)
+ : __clobber_all);
+}
+
+SEC("socket")
+__failure __msg("infinite loop detected at insn 1")
+__naked void may_goto_self(void)
+{
+ asm volatile (" \
+ r0 = *(u32 *)(r10 - 4); \
+l0_%=: .byte 0xe5; /* may_goto */ \
+ .byte 0; /* regs */ \
+ .short -1; /* off -1 */ \
+ .long 0; /* imm */ \
+ if r0 > 10 goto l0_%=; \
+ r0 = 0; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__success __retval(0)
+__naked void may_goto_neg_off(void)
+{
+ asm volatile (" \
+ r0 = *(u32 *)(r10 - 4); \
+ goto l0_%=; \
+ goto l1_%=; \
+l0_%=: .byte 0xe5; /* may_goto */ \
+ .byte 0; /* regs */ \
+ .short -2; /* off -2 */ \
+ .long 0; /* imm */ \
+ if r0 > 10 goto l0_%=; \
+l1_%=: r0 = 0; \
+ exit; \
+" ::: __clobber_all);
+}
+
SEC("tc")
__failure
__flag(BPF_F_TEST_STATE_FREQ)
@@ -307,6 +359,100 @@ int iter_limit_bug(struct __sk_buff *skb)
return 0;
}
+SEC("socket")
+__success __retval(0)
+__naked void ja_and_may_goto(void)
+{
+ asm volatile (" \
+l0_%=: .byte 0xe5; /* may_goto */ \
+ .byte 0; /* regs */ \
+ .short 1; /* off 1 */ \
+ .long 0; /* imm */ \
+ goto l0_%=; \
+ r0 = 0; \
+ exit; \
+" ::: __clobber_common);
+}
+
+SEC("socket")
+__success __retval(0)
+__naked void ja_and_may_goto2(void)
+{
+ asm volatile (" \
+l0_%=: r0 = 0; \
+ .byte 0xe5; /* may_goto */ \
+ .byte 0; /* regs */ \
+ .short 1; /* off 1 */ \
+ .long 0; /* imm */ \
+ goto l0_%=; \
+ r0 = 0; \
+ exit; \
+" ::: __clobber_common);
+}
+
+SEC("socket")
+__success __retval(0)
+__naked void jlt_and_may_goto(void)
+{
+ asm volatile (" \
+l0_%=: call %[bpf_jiffies64]; \
+ .byte 0xe5; /* may_goto */ \
+ .byte 0; /* regs */ \
+ .short 1; /* off 1 */ \
+ .long 0; /* imm */ \
+ if r0 < 10 goto l0_%=; \
+ r0 = 0; \
+ exit; \
+" :: __imm(bpf_jiffies64)
+ : __clobber_all);
+}
+
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+ (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+ defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \
+ defined(__TARGET_ARCH_loongarch)) && \
+ __clang_major__ >= 18
+SEC("socket")
+__success __retval(0)
+__naked void gotol_and_may_goto(void)
+{
+ asm volatile (" \
+l0_%=: r0 = 0; \
+ .byte 0xe5; /* may_goto */ \
+ .byte 0; /* regs */ \
+ .short 1; /* off 1 */ \
+ .long 0; /* imm */ \
+ gotol l0_%=; \
+ r0 = 0; \
+ exit; \
+" ::: __clobber_common);
+}
+#endif
+
+SEC("socket")
+__success __retval(0)
+__naked void ja_and_may_goto_subprog(void)
+{
+ asm volatile (" \
+ call subprog_with_may_goto; \
+ exit; \
+" ::: __clobber_all);
+}
+
+static __naked __noinline __used
+void subprog_with_may_goto(void)
+{
+ asm volatile (" \
+l0_%=: .byte 0xe5; /* may_goto */ \
+ .byte 0; /* regs */ \
+ .short 1; /* off 1 */ \
+ .long 0; /* imm */ \
+ goto l0_%=; \
+ r0 = 0; \
+ exit; \
+" ::: __clobber_all);
+}
+
#define ARR_SZ 1000000
int zero;
char arr[ARR_SZ];
diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c
index cbb9d6714f53..028ec855587b 100644
--- a/tools/testing/selftests/bpf/progs/verifier_movsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c
@@ -224,6 +224,69 @@ l0_%=: \
: __clobber_all);
}
+SEC("socket")
+__description("MOV32SX, S8, var_off u32_max")
+__failure __msg("infinite loop detected")
+__failure_unpriv __msg_unpriv("back-edge from insn 2 to 0")
+__naked void mov64sx_s32_varoff_1(void)
+{
+ asm volatile (" \
+l0_%=: \
+ r3 = *(u8 *)(r10 -387); \
+ w7 = (s8)w3; \
+ if w7 >= 0x2533823b goto l0_%=; \
+ w0 = 0; \
+ exit; \
+" :
+ :
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S8, var_off not u32_max, positive after s8 extension")
+__success __retval(0)
+__failure_unpriv __msg_unpriv("frame pointer is read only")
+__naked void mov64sx_s32_varoff_2(void)
+{
+ asm volatile (" \
+ call %[bpf_get_prandom_u32]; \
+ r3 = r0; \
+ r3 &= 0xf; \
+ w7 = (s8)w3; \
+ if w7 s>= 16 goto l0_%=; \
+ w0 = 0; \
+ exit; \
+l0_%=: \
+ r10 = 1; \
+ exit; \
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S8, var_off not u32_max, negative after s8 extension")
+__success __retval(0)
+__failure_unpriv __msg_unpriv("frame pointer is read only")
+__naked void mov64sx_s32_varoff_3(void)
+{
+ asm volatile (" \
+ call %[bpf_get_prandom_u32]; \
+ r3 = r0; \
+ r3 &= 0xf; \
+ r3 |= 0x80; \
+ w7 = (s8)w3; \
+ if w7 s>= -5 goto l0_%=; \
+ w0 = 0; \
+ exit; \
+l0_%=: \
+ r10 = 1; \
+ exit; \
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
#else
SEC("socket")
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 49a56eb5d036..666ab7d9390b 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -43,7 +43,6 @@ tap
tcp_fastopen_backup_key
tcp_inq
tcp_mmap
-test_unix_oob
timestamping
tls
toeplitz
diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile
index 3b83c797650d..50584479540b 100644
--- a/tools/testing/selftests/net/af_unix/Makefile
+++ b/tools/testing/selftests/net/af_unix/Makefile
@@ -1,4 +1,4 @@
CFLAGS += $(KHDR_INCLUDES)
-TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect scm_pidfd scm_rights
+TEST_GEN_PROGS := diag_uid msg_oob scm_pidfd scm_rights unix_connect
include ../../lib.mk
diff --git a/tools/testing/selftests/net/af_unix/config b/tools/testing/selftests/net/af_unix/config
new file mode 100644
index 000000000000..37368567768c
--- /dev/null
+++ b/tools/testing/selftests/net/af_unix/config
@@ -0,0 +1,3 @@
+CONFIG_UNIX=y
+CONFIG_AF_UNIX_OOB=y
+CONFIG_UNIX_DIAG=m
diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c
new file mode 100644
index 000000000000..16d0c172eaeb
--- /dev/null
+++ b/tools/testing/selftests/net/af_unix/msg_oob.c
@@ -0,0 +1,734 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <netinet/in.h>
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <sys/signalfd.h>
+#include <sys/socket.h>
+
+#include "../../kselftest_harness.h"
+
+#define BUF_SZ 32
+
+FIXTURE(msg_oob)
+{
+ int fd[4]; /* 0: AF_UNIX sender
+ * 1: AF_UNIX receiver
+ * 2: TCP sender
+ * 3: TCP receiver
+ */
+ int signal_fd;
+ int epoll_fd[2]; /* 0: AF_UNIX receiver
+ * 1: TCP receiver
+ */
+ bool tcp_compliant;
+};
+
+FIXTURE_VARIANT(msg_oob)
+{
+ bool peek;
+};
+
+FIXTURE_VARIANT_ADD(msg_oob, no_peek)
+{
+ .peek = false,
+};
+
+FIXTURE_VARIANT_ADD(msg_oob, peek)
+{
+ .peek = true
+};
+
+static void create_unix_socketpair(struct __test_metadata *_metadata,
+ FIXTURE_DATA(msg_oob) *self)
+{
+ int ret;
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_NONBLOCK, 0, self->fd);
+ ASSERT_EQ(ret, 0);
+}
+
+static void create_tcp_socketpair(struct __test_metadata *_metadata,
+ FIXTURE_DATA(msg_oob) *self)
+{
+ struct sockaddr_in addr;
+ socklen_t addrlen;
+ int listen_fd;
+ int ret;
+
+ listen_fd = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GE(listen_fd, 0);
+
+ ret = listen(listen_fd, -1);
+ ASSERT_EQ(ret, 0);
+
+ addrlen = sizeof(addr);
+ ret = getsockname(listen_fd, (struct sockaddr *)&addr, &addrlen);
+ ASSERT_EQ(ret, 0);
+
+ self->fd[2] = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GE(self->fd[2], 0);
+
+ ret = connect(self->fd[2], (struct sockaddr *)&addr, addrlen);
+ ASSERT_EQ(ret, 0);
+
+ self->fd[3] = accept(listen_fd, (struct sockaddr *)&addr, &addrlen);
+ ASSERT_GE(self->fd[3], 0);
+
+ ret = fcntl(self->fd[3], F_SETFL, O_NONBLOCK);
+ ASSERT_EQ(ret, 0);
+}
+
+static void setup_sigurg(struct __test_metadata *_metadata,
+ FIXTURE_DATA(msg_oob) *self)
+{
+ struct signalfd_siginfo siginfo;
+ int pid = getpid();
+ sigset_t mask;
+ int i, ret;
+
+ for (i = 0; i < 2; i++) {
+ ret = ioctl(self->fd[i * 2 + 1], FIOSETOWN, &pid);
+ ASSERT_EQ(ret, 0);
+ }
+
+ ret = sigemptyset(&mask);
+ ASSERT_EQ(ret, 0);
+
+ ret = sigaddset(&mask, SIGURG);
+ ASSERT_EQ(ret, 0);
+
+ ret = sigprocmask(SIG_BLOCK, &mask, NULL);
+ ASSERT_EQ(ret, 0);
+
+ self->signal_fd = signalfd(-1, &mask, SFD_NONBLOCK);
+ ASSERT_GE(self->signal_fd, 0);
+
+ ret = read(self->signal_fd, &siginfo, sizeof(siginfo));
+ ASSERT_EQ(ret, -1);
+}
+
+static void setup_epollpri(struct __test_metadata *_metadata,
+ FIXTURE_DATA(msg_oob) *self)
+{
+ struct epoll_event event = {
+ .events = EPOLLPRI,
+ };
+ int i;
+
+ for (i = 0; i < 2; i++) {
+ int ret;
+
+ self->epoll_fd[i] = epoll_create1(0);
+ ASSERT_GE(self->epoll_fd[i], 0);
+
+ ret = epoll_ctl(self->epoll_fd[i], EPOLL_CTL_ADD, self->fd[i * 2 + 1], &event);
+ ASSERT_EQ(ret, 0);
+ }
+}
+
+static void close_sockets(FIXTURE_DATA(msg_oob) *self)
+{
+ int i;
+
+ for (i = 0; i < 4; i++)
+ close(self->fd[i]);
+}
+
+FIXTURE_SETUP(msg_oob)
+{
+ create_unix_socketpair(_metadata, self);
+ create_tcp_socketpair(_metadata, self);
+
+ setup_sigurg(_metadata, self);
+ setup_epollpri(_metadata, self);
+
+ self->tcp_compliant = true;
+}
+
+FIXTURE_TEARDOWN(msg_oob)
+{
+ close_sockets(self);
+}
+
+static void __epollpair(struct __test_metadata *_metadata,
+ FIXTURE_DATA(msg_oob) *self,
+ bool oob_remaining)
+{
+ struct epoll_event event[2] = {};
+ int i, ret[2];
+
+ for (i = 0; i < 2; i++)
+ ret[i] = epoll_wait(self->epoll_fd[i], &event[i], 1, 0);
+
+ ASSERT_EQ(ret[0], oob_remaining);
+
+ if (self->tcp_compliant)
+ ASSERT_EQ(ret[0], ret[1]);
+
+ if (oob_remaining) {
+ ASSERT_EQ(event[0].events, EPOLLPRI);
+
+ if (self->tcp_compliant)
+ ASSERT_EQ(event[0].events, event[1].events);
+ }
+}
+
+static void __sendpair(struct __test_metadata *_metadata,
+ FIXTURE_DATA(msg_oob) *self,
+ const void *buf, size_t len, int flags)
+{
+ int i, ret[2];
+
+ for (i = 0; i < 2; i++) {
+ struct signalfd_siginfo siginfo = {};
+ int bytes;
+
+ ret[i] = send(self->fd[i * 2], buf, len, flags);
+
+ bytes = read(self->signal_fd, &siginfo, sizeof(siginfo));
+
+ if (flags & MSG_OOB) {
+ ASSERT_EQ(bytes, sizeof(siginfo));
+ ASSERT_EQ(siginfo.ssi_signo, SIGURG);
+
+ bytes = read(self->signal_fd, &siginfo, sizeof(siginfo));
+ }
+
+ ASSERT_EQ(bytes, -1);
+ }
+
+ ASSERT_EQ(ret[0], len);
+ ASSERT_EQ(ret[0], ret[1]);
+}
+
+static void __recvpair(struct __test_metadata *_metadata,
+ FIXTURE_DATA(msg_oob) *self,
+ const void *expected_buf, int expected_len,
+ int buf_len, int flags)
+{
+ int i, ret[2], recv_errno[2], expected_errno = 0;
+ char recv_buf[2][BUF_SZ] = {};
+ bool printed = false;
+
+ ASSERT_GE(BUF_SZ, buf_len);
+
+ errno = 0;
+
+ for (i = 0; i < 2; i++) {
+ ret[i] = recv(self->fd[i * 2 + 1], recv_buf[i], buf_len, flags);
+ recv_errno[i] = errno;
+ }
+
+ if (expected_len < 0) {
+ expected_errno = -expected_len;
+ expected_len = -1;
+ }
+
+ if (ret[0] != expected_len || recv_errno[0] != expected_errno) {
+ TH_LOG("AF_UNIX :%s", ret[0] < 0 ? strerror(recv_errno[0]) : recv_buf[0]);
+ TH_LOG("Expected:%s", expected_errno ? strerror(expected_errno) : expected_buf);
+
+ ASSERT_EQ(ret[0], expected_len);
+ ASSERT_EQ(recv_errno[0], expected_errno);
+ }
+
+ if (ret[0] != ret[1] || recv_errno[0] != recv_errno[1]) {
+ TH_LOG("AF_UNIX :%s", ret[0] < 0 ? strerror(recv_errno[0]) : recv_buf[0]);
+ TH_LOG("TCP :%s", ret[1] < 0 ? strerror(recv_errno[1]) : recv_buf[1]);
+
+ printed = true;
+
+ if (self->tcp_compliant) {
+ ASSERT_EQ(ret[0], ret[1]);
+ ASSERT_EQ(recv_errno[0], recv_errno[1]);
+ }
+ }
+
+ if (expected_len >= 0) {
+ int cmp;
+
+ cmp = strncmp(expected_buf, recv_buf[0], expected_len);
+ if (cmp) {
+ TH_LOG("AF_UNIX :%s", ret[0] < 0 ? strerror(recv_errno[0]) : recv_buf[0]);
+ TH_LOG("Expected:%s", expected_errno ? strerror(expected_errno) : expected_buf);
+
+ ASSERT_EQ(cmp, 0);
+ }
+
+ cmp = strncmp(recv_buf[0], recv_buf[1], expected_len);
+ if (cmp) {
+ if (!printed) {
+ TH_LOG("AF_UNIX :%s", ret[0] < 0 ? strerror(recv_errno[0]) : recv_buf[0]);
+ TH_LOG("TCP :%s", ret[1] < 0 ? strerror(recv_errno[1]) : recv_buf[1]);
+ }
+
+ if (self->tcp_compliant)
+ ASSERT_EQ(cmp, 0);
+ }
+ }
+}
+
+static void __setinlinepair(struct __test_metadata *_metadata,
+ FIXTURE_DATA(msg_oob) *self)
+{
+ int i, oob_inline = 1;
+
+ for (i = 0; i < 2; i++) {
+ int ret;
+
+ ret = setsockopt(self->fd[i * 2 + 1], SOL_SOCKET, SO_OOBINLINE,
+ &oob_inline, sizeof(oob_inline));
+ ASSERT_EQ(ret, 0);
+ }
+}
+
+static void __siocatmarkpair(struct __test_metadata *_metadata,
+ FIXTURE_DATA(msg_oob) *self,
+ bool oob_head)
+{
+ int answ[2] = {};
+ int i;
+
+ for (i = 0; i < 2; i++) {
+ int ret;
+
+ ret = ioctl(self->fd[i * 2 + 1], SIOCATMARK, &answ[i]);
+ ASSERT_EQ(ret, 0);
+ }
+
+ ASSERT_EQ(answ[0], oob_head);
+
+ if (self->tcp_compliant)
+ ASSERT_EQ(answ[0], answ[1]);
+}
+
+#define sendpair(buf, len, flags) \
+ __sendpair(_metadata, self, buf, len, flags)
+
+#define recvpair(expected_buf, expected_len, buf_len, flags) \
+ do { \
+ if (variant->peek) \
+ __recvpair(_metadata, self, \
+ expected_buf, expected_len, \
+ buf_len, (flags) | MSG_PEEK); \
+ __recvpair(_metadata, self, \
+ expected_buf, expected_len, buf_len, flags); \
+ } while (0)
+
+#define epollpair(oob_remaining) \
+ __epollpair(_metadata, self, oob_remaining)
+
+#define siocatmarkpair(oob_head) \
+ __siocatmarkpair(_metadata, self, oob_head)
+
+#define setinlinepair() \
+ __setinlinepair(_metadata, self)
+
+#define tcp_incompliant \
+ for (self->tcp_compliant = false; \
+ self->tcp_compliant == false; \
+ self->tcp_compliant = true)
+
+TEST_F(msg_oob, non_oob)
+{
+ sendpair("x", 1, 0);
+ epollpair(false);
+ siocatmarkpair(false);
+
+ recvpair("", -EINVAL, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(false);
+}
+
+TEST_F(msg_oob, oob)
+{
+ sendpair("x", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("x", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(true);
+}
+
+TEST_F(msg_oob, oob_drop)
+{
+ sendpair("x", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("", -EAGAIN, 1, 0); /* Drop OOB. */
+ epollpair(false);
+ siocatmarkpair(false);
+
+ recvpair("", -EINVAL, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(false);
+}
+
+TEST_F(msg_oob, oob_ahead)
+{
+ sendpair("hello", 5, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("o", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(false);
+
+ recvpair("hell", 4, 4, 0);
+ epollpair(false);
+ siocatmarkpair(true);
+}
+
+TEST_F(msg_oob, oob_break)
+{
+ sendpair("hello", 5, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("hell", 4, 5, 0); /* Break at OOB even with enough buffer. */
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("o", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(true);
+
+ recvpair("", -EAGAIN, 1, 0);
+ siocatmarkpair(false);
+}
+
+TEST_F(msg_oob, oob_ahead_break)
+{
+ sendpair("hello", 5, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ sendpair("world", 5, 0);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("o", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(false);
+
+ recvpair("hell", 4, 9, 0); /* Break at OOB even after it's recv()ed. */
+ epollpair(false);
+ siocatmarkpair(true);
+
+ recvpair("world", 5, 5, 0);
+ epollpair(false);
+ siocatmarkpair(false);
+}
+
+TEST_F(msg_oob, oob_break_drop)
+{
+ sendpair("hello", 5, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ sendpair("world", 5, 0);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("hell", 4, 10, 0); /* Break at OOB even with enough buffer. */
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("world", 5, 10, 0); /* Drop OOB and recv() the next skb. */
+ epollpair(false);
+ siocatmarkpair(false);
+
+ recvpair("", -EINVAL, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(false);
+}
+
+TEST_F(msg_oob, ex_oob_break)
+{
+ sendpair("hello", 5, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ sendpair("wor", 3, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ sendpair("ld", 2, 0);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("hellowo", 7, 10, 0); /* Break at OOB but not at ex-OOB. */
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("r", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(true);
+
+ recvpair("ld", 2, 2, 0);
+ epollpair(false);
+ siocatmarkpair(false);
+}
+
+TEST_F(msg_oob, ex_oob_drop)
+{
+ sendpair("x", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ sendpair("y", 1, MSG_OOB); /* TCP drops "x" at this moment. */
+ epollpair(true);
+
+ tcp_incompliant {
+ siocatmarkpair(false);
+
+ recvpair("x", 1, 1, 0); /* TCP drops "y" by passing through it. */
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("y", 1, 1, MSG_OOB); /* TCP returns -EINVAL. */
+ epollpair(false);
+ siocatmarkpair(true);
+ }
+}
+
+TEST_F(msg_oob, ex_oob_drop_2)
+{
+ sendpair("x", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ sendpair("y", 1, MSG_OOB); /* TCP drops "x" at this moment. */
+ epollpair(true);
+
+ tcp_incompliant {
+ siocatmarkpair(false);
+ }
+
+ recvpair("y", 1, 1, MSG_OOB);
+ epollpair(false);
+
+ tcp_incompliant {
+ siocatmarkpair(false);
+
+ recvpair("x", 1, 1, 0); /* TCP returns -EAGAIN. */
+ epollpair(false);
+ siocatmarkpair(true);
+ }
+}
+
+TEST_F(msg_oob, ex_oob_ahead_break)
+{
+ sendpair("hello", 5, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ sendpair("wor", 3, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("r", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(false);
+
+ sendpair("ld", 2, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ tcp_incompliant {
+ recvpair("hellowol", 8, 10, 0); /* TCP recv()s "helloworl", why "r" ?? */
+ }
+
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("d", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(true);
+}
+
+TEST_F(msg_oob, ex_oob_siocatmark)
+{
+ sendpair("hello", 5, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("o", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(false);
+
+ sendpair("world", 5, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("hell", 4, 4, 0); /* Intentionally stop at ex-OOB. */
+ epollpair(true);
+ siocatmarkpair(false);
+}
+
+TEST_F(msg_oob, inline_oob)
+{
+ setinlinepair();
+
+ sendpair("x", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("", -EINVAL, 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("x", 1, 1, 0);
+ epollpair(false);
+ siocatmarkpair(false);
+}
+
+TEST_F(msg_oob, inline_oob_break)
+{
+ setinlinepair();
+
+ sendpair("hello", 5, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("", -EINVAL, 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("hell", 4, 5, 0); /* Break at OOB but not at ex-OOB. */
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("o", 1, 1, 0);
+ epollpair(false);
+ siocatmarkpair(false);
+}
+
+TEST_F(msg_oob, inline_oob_ahead_break)
+{
+ sendpair("hello", 5, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ sendpair("world", 5, 0);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("o", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(false);
+
+ setinlinepair();
+
+ recvpair("hell", 4, 9, 0); /* Break at OOB even with enough buffer. */
+ epollpair(false);
+ siocatmarkpair(true);
+
+ tcp_incompliant {
+ recvpair("world", 5, 6, 0); /* TCP recv()s "oworld", ... "o" ??? */
+ }
+
+ epollpair(false);
+ siocatmarkpair(false);
+}
+
+TEST_F(msg_oob, inline_ex_oob_break)
+{
+ sendpair("hello", 5, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ sendpair("wor", 3, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ sendpair("ld", 2, 0);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ setinlinepair();
+
+ recvpair("hellowo", 7, 10, 0); /* Break at OOB but not at ex-OOB. */
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("rld", 3, 3, 0);
+ epollpair(false);
+ siocatmarkpair(false);
+}
+
+TEST_F(msg_oob, inline_ex_oob_no_drop)
+{
+ sendpair("x", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ setinlinepair();
+
+ sendpair("y", 1, MSG_OOB); /* TCP does NOT drops "x" at this moment. */
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("x", 1, 1, 0);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("y", 1, 1, 0);
+ epollpair(false);
+ siocatmarkpair(false);
+}
+
+TEST_F(msg_oob, inline_ex_oob_drop)
+{
+ sendpair("x", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ sendpair("y", 1, MSG_OOB); /* TCP drops "x" at this moment. */
+ epollpair(true);
+
+ setinlinepair();
+
+ tcp_incompliant {
+ siocatmarkpair(false);
+
+ recvpair("x", 1, 1, 0); /* TCP recv()s "y". */
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("y", 1, 1, 0); /* TCP returns -EAGAIN. */
+ epollpair(false);
+ siocatmarkpair(false);
+ }
+}
+
+TEST_F(msg_oob, inline_ex_oob_siocatmark)
+{
+ sendpair("hello", 5, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("o", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(false);
+
+ setinlinepair();
+
+ sendpair("world", 5, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(false);
+
+ recvpair("hell", 4, 4, 0); /* Intentionally stop at ex-OOB. */
+ epollpair(true);
+ siocatmarkpair(false);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c
deleted file mode 100644
index a7c51889acd5..000000000000
--- a/tools/testing/selftests/net/af_unix/test_unix_oob.c
+++ /dev/null
@@ -1,436 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-#include <stdio.h>
-#include <stdlib.h>
-#include <sys/socket.h>
-#include <arpa/inet.h>
-#include <unistd.h>
-#include <string.h>
-#include <fcntl.h>
-#include <sys/ioctl.h>
-#include <errno.h>
-#include <netinet/tcp.h>
-#include <sys/un.h>
-#include <sys/signal.h>
-#include <sys/poll.h>
-
-static int pipefd[2];
-static int signal_recvd;
-static pid_t producer_id;
-static char sock_name[32];
-
-static void sig_hand(int sn, siginfo_t *si, void *p)
-{
- signal_recvd = sn;
-}
-
-static int set_sig_handler(int signal)
-{
- struct sigaction sa;
-
- sa.sa_sigaction = sig_hand;
- sigemptyset(&sa.sa_mask);
- sa.sa_flags = SA_SIGINFO | SA_RESTART;
-
- return sigaction(signal, &sa, NULL);
-}
-
-static void set_filemode(int fd, int set)
-{
- int flags = fcntl(fd, F_GETFL, 0);
-
- if (set)
- flags &= ~O_NONBLOCK;
- else
- flags |= O_NONBLOCK;
- fcntl(fd, F_SETFL, flags);
-}
-
-static void signal_producer(int fd)
-{
- char cmd;
-
- cmd = 'S';
- write(fd, &cmd, sizeof(cmd));
-}
-
-static void wait_for_signal(int fd)
-{
- char buf[5];
-
- read(fd, buf, 5);
-}
-
-static void die(int status)
-{
- fflush(NULL);
- unlink(sock_name);
- kill(producer_id, SIGTERM);
- exit(status);
-}
-
-int is_sioctatmark(int fd)
-{
- int ans = -1;
-
- if (ioctl(fd, SIOCATMARK, &ans, sizeof(ans)) < 0) {
-#ifdef DEBUG
- perror("SIOCATMARK Failed");
-#endif
- }
- return ans;
-}
-
-void read_oob(int fd, char *c)
-{
-
- *c = ' ';
- if (recv(fd, c, sizeof(*c), MSG_OOB) < 0) {
-#ifdef DEBUG
- perror("Reading MSG_OOB Failed");
-#endif
- }
-}
-
-int read_data(int pfd, char *buf, int size)
-{
- int len = 0;
-
- memset(buf, size, '0');
- len = read(pfd, buf, size);
-#ifdef DEBUG
- if (len < 0)
- perror("read failed");
-#endif
- return len;
-}
-
-static void wait_for_data(int pfd, int event)
-{
- struct pollfd pfds[1];
-
- pfds[0].fd = pfd;
- pfds[0].events = event;
- poll(pfds, 1, -1);
-}
-
-void producer(struct sockaddr_un *consumer_addr)
-{
- int cfd;
- char buf[64];
- int i;
-
- memset(buf, 'x', sizeof(buf));
- cfd = socket(AF_UNIX, SOCK_STREAM, 0);
-
- wait_for_signal(pipefd[0]);
- if (connect(cfd, (struct sockaddr *)consumer_addr,
- sizeof(*consumer_addr)) != 0) {
- perror("Connect failed");
- kill(0, SIGTERM);
- exit(1);
- }
-
- for (i = 0; i < 2; i++) {
- /* Test 1: Test for SIGURG and OOB */
- wait_for_signal(pipefd[0]);
- memset(buf, 'x', sizeof(buf));
- buf[63] = '@';
- send(cfd, buf, sizeof(buf), MSG_OOB);
-
- wait_for_signal(pipefd[0]);
-
- /* Test 2: Test for OOB being overwitten */
- memset(buf, 'x', sizeof(buf));
- buf[63] = '%';
- send(cfd, buf, sizeof(buf), MSG_OOB);
-
- memset(buf, 'x', sizeof(buf));
- buf[63] = '#';
- send(cfd, buf, sizeof(buf), MSG_OOB);
-
- wait_for_signal(pipefd[0]);
-
- /* Test 3: Test for SIOCATMARK */
- memset(buf, 'x', sizeof(buf));
- buf[63] = '@';
- send(cfd, buf, sizeof(buf), MSG_OOB);
-
- memset(buf, 'x', sizeof(buf));
- buf[63] = '%';
- send(cfd, buf, sizeof(buf), MSG_OOB);
-
- memset(buf, 'x', sizeof(buf));
- send(cfd, buf, sizeof(buf), 0);
-
- wait_for_signal(pipefd[0]);
-
- /* Test 4: Test for 1byte OOB msg */
- memset(buf, 'x', sizeof(buf));
- buf[0] = '@';
- send(cfd, buf, 1, MSG_OOB);
- }
-}
-
-int
-main(int argc, char **argv)
-{
- int lfd, pfd;
- struct sockaddr_un consumer_addr, paddr;
- socklen_t len = sizeof(consumer_addr);
- char buf[1024];
- int on = 0;
- char oob;
- int atmark;
-
- lfd = socket(AF_UNIX, SOCK_STREAM, 0);
- memset(&consumer_addr, 0, sizeof(consumer_addr));
- consumer_addr.sun_family = AF_UNIX;
- sprintf(sock_name, "unix_oob_%d", getpid());
- unlink(sock_name);
- strcpy(consumer_addr.sun_path, sock_name);
-
- if ((bind(lfd, (struct sockaddr *)&consumer_addr,
- sizeof(consumer_addr))) != 0) {
- perror("socket bind failed");
- exit(1);
- }
-
- pipe(pipefd);
-
- listen(lfd, 1);
-
- producer_id = fork();
- if (producer_id == 0) {
- producer(&consumer_addr);
- exit(0);
- }
-
- set_sig_handler(SIGURG);
- signal_producer(pipefd[1]);
-
- pfd = accept(lfd, (struct sockaddr *) &paddr, &len);
- fcntl(pfd, F_SETOWN, getpid());
-
- signal_recvd = 0;
- signal_producer(pipefd[1]);
-
- /* Test 1:
- * veriyf that SIGURG is
- * delivered, 63 bytes are
- * read, oob is '@', and POLLPRI works.
- */
- wait_for_data(pfd, POLLPRI);
- read_oob(pfd, &oob);
- len = read_data(pfd, buf, 1024);
- if (!signal_recvd || len != 63 || oob != '@') {
- fprintf(stderr, "Test 1 failed sigurg %d len %d %c\n",
- signal_recvd, len, oob);
- die(1);
- }
-
- signal_recvd = 0;
- signal_producer(pipefd[1]);
-
- /* Test 2:
- * Verify that the first OOB is over written by
- * the 2nd one and the first OOB is returned as
- * part of the read, and sigurg is received.
- */
- wait_for_data(pfd, POLLIN | POLLPRI);
- len = 0;
- while (len < 70)
- len = recv(pfd, buf, 1024, MSG_PEEK);
- len = read_data(pfd, buf, 1024);
- read_oob(pfd, &oob);
- if (!signal_recvd || len != 127 || oob != '#') {
- fprintf(stderr, "Test 2 failed, sigurg %d len %d OOB %c\n",
- signal_recvd, len, oob);
- die(1);
- }
-
- signal_recvd = 0;
- signal_producer(pipefd[1]);
-
- /* Test 3:
- * verify that 2nd oob over writes
- * the first one and read breaks at
- * oob boundary returning 127 bytes
- * and sigurg is received and atmark
- * is set.
- * oob is '%' and second read returns
- * 64 bytes.
- */
- len = 0;
- wait_for_data(pfd, POLLIN | POLLPRI);
- while (len < 150)
- len = recv(pfd, buf, 1024, MSG_PEEK);
- len = read_data(pfd, buf, 1024);
- atmark = is_sioctatmark(pfd);
- read_oob(pfd, &oob);
-
- if (!signal_recvd || len != 127 || oob != '%' || atmark != 1) {
- fprintf(stderr,
- "Test 3 failed, sigurg %d len %d OOB %c atmark %d\n",
- signal_recvd, len, oob, atmark);
- die(1);
- }
-
- signal_recvd = 0;
-
- len = read_data(pfd, buf, 1024);
- if (len != 64) {
- fprintf(stderr, "Test 3.1 failed, sigurg %d len %d OOB %c\n",
- signal_recvd, len, oob);
- die(1);
- }
-
- signal_recvd = 0;
- signal_producer(pipefd[1]);
-
- /* Test 4:
- * verify that a single byte
- * oob message is delivered.
- * set non blocking mode and
- * check proper error is
- * returned and sigurg is
- * received and correct
- * oob is read.
- */
-
- set_filemode(pfd, 0);
-
- wait_for_data(pfd, POLLIN | POLLPRI);
- len = read_data(pfd, buf, 1024);
- if ((len == -1) && (errno == 11))
- len = 0;
-
- read_oob(pfd, &oob);
-
- if (!signal_recvd || len != 0 || oob != '@') {
- fprintf(stderr, "Test 4 failed, sigurg %d len %d OOB %c\n",
- signal_recvd, len, oob);
- die(1);
- }
-
- set_filemode(pfd, 1);
-
- /* Inline Testing */
-
- on = 1;
- if (setsockopt(pfd, SOL_SOCKET, SO_OOBINLINE, &on, sizeof(on))) {
- perror("SO_OOBINLINE");
- die(1);
- }
-
- signal_recvd = 0;
- signal_producer(pipefd[1]);
-
- /* Test 1 -- Inline:
- * Check that SIGURG is
- * delivered and 63 bytes are
- * read and oob is '@'
- */
-
- wait_for_data(pfd, POLLIN | POLLPRI);
- len = read_data(pfd, buf, 1024);
-
- if (!signal_recvd || len != 63) {
- fprintf(stderr, "Test 1 Inline failed, sigurg %d len %d\n",
- signal_recvd, len);
- die(1);
- }
-
- len = read_data(pfd, buf, 1024);
-
- if (len != 1) {
- fprintf(stderr,
- "Test 1.1 Inline failed, sigurg %d len %d oob %c\n",
- signal_recvd, len, oob);
- die(1);
- }
-
- signal_recvd = 0;
- signal_producer(pipefd[1]);
-
- /* Test 2 -- Inline:
- * Verify that the first OOB is over written by
- * the 2nd one and read breaks correctly on
- * 2nd OOB boundary with the first OOB returned as
- * part of the read, and sigurg is delivered and
- * siocatmark returns true.
- * next read returns one byte, the oob byte
- * and siocatmark returns false.
- */
- len = 0;
- wait_for_data(pfd, POLLIN | POLLPRI);
- while (len < 70)
- len = recv(pfd, buf, 1024, MSG_PEEK);
- len = read_data(pfd, buf, 1024);
- atmark = is_sioctatmark(pfd);
- if (len != 127 || atmark != 1 || !signal_recvd) {
- fprintf(stderr, "Test 2 Inline failed, len %d atmark %d\n",
- len, atmark);
- die(1);
- }
-
- len = read_data(pfd, buf, 1024);
- atmark = is_sioctatmark(pfd);
- if (len != 1 || buf[0] != '#' || atmark == 1) {
- fprintf(stderr, "Test 2.1 Inline failed, len %d data %c atmark %d\n",
- len, buf[0], atmark);
- die(1);
- }
-
- signal_recvd = 0;
- signal_producer(pipefd[1]);
-
- /* Test 3 -- Inline:
- * verify that 2nd oob over writes
- * the first one and read breaks at
- * oob boundary returning 127 bytes
- * and sigurg is received and siocatmark
- * is true after the read.
- * subsequent read returns 65 bytes
- * because of oob which should be '%'.
- */
- len = 0;
- wait_for_data(pfd, POLLIN | POLLPRI);
- while (len < 126)
- len = recv(pfd, buf, 1024, MSG_PEEK);
- len = read_data(pfd, buf, 1024);
- atmark = is_sioctatmark(pfd);
- if (!signal_recvd || len != 127 || !atmark) {
- fprintf(stderr,
- "Test 3 Inline failed, sigurg %d len %d data %c\n",
- signal_recvd, len, buf[0]);
- die(1);
- }
-
- len = read_data(pfd, buf, 1024);
- atmark = is_sioctatmark(pfd);
- if (len != 65 || buf[0] != '%' || atmark != 0) {
- fprintf(stderr,
- "Test 3.1 Inline failed, len %d oob %c atmark %d\n",
- len, buf[0], atmark);
- die(1);
- }
-
- signal_recvd = 0;
- signal_producer(pipefd[1]);
-
- /* Test 4 -- Inline:
- * verify that a single
- * byte oob message is delivered
- * and read returns one byte, the oob
- * byte and sigurg is received
- */
- wait_for_data(pfd, POLLIN | POLLPRI);
- len = read_data(pfd, buf, 1024);
- if (!signal_recvd || len != 1 || buf[0] != '@') {
- fprintf(stderr,
- "Test 4 Inline failed, signal %d len %d data %c\n",
- signal_recvd, len, buf[0]);
- die(1);
- }
- die(0);
-}