summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-08-01 18:42:09 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2024-08-01 18:42:09 +0200
commit183d46ff422ef9f3d755b6808ef3faa6d009ba3a (patch)
tree8405b88ef447994f3eafd40e8e3aa5f47d3fa33f
parentminmax: fix up min3() and max3() too (diff)
parentMerge branch 'mptcp-fix-duplicate-data-handling' (diff)
downloadlinux-183d46ff422ef9f3d755b6808ef3faa6d009ba3a.tar.xz
linux-183d46ff422ef9f3d755b6808ef3faa6d009ba3a.zip
Merge tag 'net-6.11-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni: "Including fixes from wireless, bleutooth, BPF and netfilter. Current release - regressions: - core: drop bad gso csum_start and offset in virtio_net_hdr - wifi: mt76: fix null pointer access in mt792x_mac_link_bss_remove - eth: tun: add missing bpf_net_ctx_clear() in do_xdp_generic() - phy: aquantia: only poll GLOBAL_CFG regs on aqr113, aqr113c and aqr115c Current release - new code bugs: - smc: prevent UAF in inet_create() - bluetooth: btmtk: fix kernel crash when entering btmtk_usb_suspend - eth: bnxt: reject unsupported hash functions Previous releases - regressions: - sched: act_ct: take care of padding in struct zones_ht_key - netfilter: fix null-ptr-deref in iptable_nat_table_init(). - tcp: adjust clamping window for applications specifying SO_RCVBUF Previous releases - always broken: - ethtool: rss: small fixes to spec and GET - mptcp: - fix signal endpoint re-add - pm: fix backup support in signal endpoints - wifi: ath12k: fix soft lockup on suspend - eth: bnxt_en: fix RSS logic in __bnxt_reserve_rings() - eth: ice: fix AF_XDP ZC timeout and concurrency issues - eth: mlx5: - fix missing lock on sync reset reload - fix error handling in irq_pool_request_irq" * tag 'net-6.11-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (76 commits) mptcp: fix duplicate data handling mptcp: fix bad RCVPRUNED mib accounting ipv6: fix ndisc_is_useropt() handling for PIO igc: Fix double reset adapter triggered from a single taprio cmd net: MAINTAINERS: Demote Qualcomm IPA to "maintained" net: wan: fsl_qmc_hdlc: Discard received CRC net: wan: fsl_qmc_hdlc: Convert carrier_lock spinlock to a mutex net/mlx5e: Add a check for the return value from mlx5_port_set_eth_ptys net/mlx5e: Fix CT entry update leaks of modify header context net/mlx5e: Require mlx5 tc classifier action support for IPsec prio capability net/mlx5: Fix missing lock on sync reset reload net/mlx5: Lag, don't use the hardcoded value of the first port net/mlx5: DR, Fix 'stack guard page was hit' error in dr_rule net/mlx5: Fix error handling in irq_pool_request_irq net/mlx5: Always drain health in shutdown callback net: Add skbuff.h to MAINTAINERS r8169: don't increment tx_dropped in case of NETDEV_TX_BUSY netfilter: iptables: Fix potential null-ptr-deref in ip6table_nat_table_init(). netfilter: iptables: Fix null-ptr-deref in iptable_nat_table_init(). net: drop bad gso csum_start and offset in virtio_net_hdr ...
-rw-r--r--Documentation/netlink/specs/ethtool.yaml2
-rw-r--r--Documentation/networking/ethtool-netlink.rst1
-rw-r--r--MAINTAINERS3
-rw-r--r--drivers/bluetooth/Kconfig2
-rw-r--r--drivers/bluetooth/btintel.c3
-rw-r--r--drivers/bluetooth/btmtk.c5
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt.c6
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c14
-rw-r--r--drivers/net/ethernet/intel/ice/ice.h11
-rw-r--r--drivers/net/ethernet/intel/ice/ice_base.c4
-rw-r--r--drivers/net/ethernet/intel/ice/ice_main.c2
-rw-r--r--drivers/net/ethernet/intel/ice/ice_txrx.c10
-rw-r--r--drivers/net/ethernet/intel/ice/ice_xsk.c184
-rw-r--r--drivers/net/ethernet/intel/ice/ice_xsk.h14
-rw-r--r--drivers/net/ethernet/intel/igc/igc_main.c33
-rw-r--r--drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c6
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c7
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c7
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c5
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c10
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/main.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c2
-rw-r--r--drivers/net/ethernet/meta/Kconfig2
-rw-r--r--drivers/net/ethernet/realtek/r8169_main.c8
-rw-r--r--drivers/net/ethernet/xilinx/xilinx_axienet_main.c2
-rw-r--r--drivers/net/phy/aquantia/aquantia_main.c29
-rw-r--r--drivers/net/phy/micrel.c34
-rw-r--r--drivers/net/phy/realtek.c7
-rw-r--r--drivers/net/usb/sr9700.c11
-rw-r--r--drivers/net/wan/fsl_qmc_hdlc.c31
-rw-r--r--drivers/net/wireless/ath/ath12k/pci.c3
-rw-r--r--drivers/net/wireless/ath/ath12k/wow.c8
-rw-r--r--drivers/net/wireless/mediatek/mt76/mt7921/main.c1
-rw-r--r--include/linux/virtio_net.h16
-rw-r--r--include/trace/events/mptcp.h2
-rw-r--r--net/bluetooth/hci_core.c7
-rw-r--r--net/bluetooth/hci_event.c5
-rw-r--r--net/bluetooth/hci_sync.c21
-rw-r--r--net/core/dev.c1
-rw-r--r--net/core/rtnetlink.c2
-rw-r--r--net/ethtool/ioctl.c43
-rw-r--r--net/ethtool/rss.c8
-rw-r--r--net/ipv4/netfilter/iptable_nat.c18
-rw-r--r--net/ipv4/tcp_input.c23
-rw-r--r--net/ipv4/tcp_offload.c3
-rw-r--r--net/ipv4/udp_offload.c4
-rw-r--r--net/ipv6/ndisc.c34
-rw-r--r--net/ipv6/netfilter/ip6table_nat.c14
-rw-r--r--net/iucv/af_iucv.c4
-rw-r--r--net/mac80211/cfg.c7
-rw-r--r--net/mac80211/tx.c5
-rw-r--r--net/mac80211/util.c2
-rw-r--r--net/mptcp/mib.c2
-rw-r--r--net/mptcp/mib.h2
-rw-r--r--net/mptcp/options.c2
-rw-r--r--net/mptcp/pm.c12
-rw-r--r--net/mptcp/pm_netlink.c46
-rw-r--r--net/mptcp/pm_userspace.c18
-rw-r--r--net/mptcp/protocol.c18
-rw-r--r--net/mptcp/protocol.h4
-rw-r--r--net/mptcp/subflow.c26
-rw-r--r--net/sched/act_ct.c4
-rw-r--r--net/smc/af_smc.c7
-rw-r--r--net/wireless/scan.c11
-rw-r--r--net/wireless/sme.c1
-rw-r--r--tools/testing/selftests/bpf/Makefile2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c2
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/rss_ctx.py37
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_connect.c8
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh103
73 files changed, 694 insertions, 303 deletions
diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 495e35fcfb21..ea21fe135b97 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -1753,6 +1753,7 @@ operations:
request:
attributes:
- header
+ - context
reply:
attributes:
- header
@@ -1761,7 +1762,6 @@ operations:
- indir
- hkey
- input_xfrm
- dump: *rss-get-op
-
name: plca-get-cfg
doc: Get PLCA params.
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 3ab423b80e91..d5f246aceb9f 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -1875,6 +1875,7 @@ Kernel response contents:
===================================== ====== ==========================
``ETHTOOL_A_RSS_HEADER`` nested reply header
+ ``ETHTOOL_A_RSS_CONTEXT`` u32 context number
``ETHTOOL_A_RSS_HFUNC`` u32 RSS hash func
``ETHTOOL_A_RSS_INDIR`` binary Indir table bytes
``ETHTOOL_A_RSS_HKEY`` binary Hash key bytes
diff --git a/MAINTAINERS b/MAINTAINERS
index 42decde38320..8766f3e5e87e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15936,6 +15936,7 @@ F: include/linux/in.h
F: include/linux/indirect_call_wrapper.h
F: include/linux/net.h
F: include/linux/netdevice.h
+F: include/linux/skbuff.h
F: include/net/
F: include/uapi/linux/in.h
F: include/uapi/linux/net.h
@@ -18556,7 +18557,7 @@ F: drivers/usb/misc/qcom_eud.c
QCOM IPA DRIVER
M: Alex Elder <elder@kernel.org>
L: netdev@vger.kernel.org
-S: Supported
+S: Maintained
F: drivers/net/ipa/
QEMU MACHINE EMULATOR AND VIRTUALIZER SUPPORT
diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index 90a94a111e67..769fa288179d 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -413,6 +413,7 @@ config BT_ATH3K
config BT_MTKSDIO
tristate "MediaTek HCI SDIO driver"
depends on MMC
+ depends on USB || !BT_HCIBTUSB_MTK
select BT_MTK
help
MediaTek Bluetooth HCI SDIO driver.
@@ -425,6 +426,7 @@ config BT_MTKSDIO
config BT_MTKUART
tristate "MediaTek HCI UART driver"
depends on SERIAL_DEV_BUS
+ depends on USB || !BT_HCIBTUSB_MTK
select BT_MTK
help
MediaTek Bluetooth HCI UART driver.
diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index e7a612504ab1..2ebc970e6573 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -3085,6 +3085,9 @@ static int btintel_setup_combined(struct hci_dev *hdev)
btintel_set_dsm_reset_method(hdev, &ver_tlv);
err = btintel_bootloader_setup_tlv(hdev, &ver_tlv);
+ if (err)
+ goto exit_error;
+
btintel_register_devcoredump_support(hdev);
btintel_print_fseq_info(hdev);
break;
diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c
index b7c348687a77..2b7c80043aa2 100644
--- a/drivers/bluetooth/btmtk.c
+++ b/drivers/bluetooth/btmtk.c
@@ -437,6 +437,7 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(btmtk_process_coredump);
+#if IS_ENABLED(CONFIG_BT_HCIBTUSB_MTK)
static void btmtk_usb_wmt_recv(struct urb *urb)
{
struct hci_dev *hdev = urb->context;
@@ -1262,7 +1263,8 @@ int btmtk_usb_suspend(struct hci_dev *hdev)
struct btmtk_data *btmtk_data = hci_get_priv(hdev);
/* Stop urb anchor for iso data transmission */
- usb_kill_anchored_urbs(&btmtk_data->isopkt_anchor);
+ if (test_bit(BTMTK_ISOPKT_RUNNING, &btmtk_data->flags))
+ usb_kill_anchored_urbs(&btmtk_data->isopkt_anchor);
return 0;
}
@@ -1487,6 +1489,7 @@ int btmtk_usb_shutdown(struct hci_dev *hdev)
return 0;
}
EXPORT_SYMBOL_GPL(btmtk_usb_shutdown);
+#endif
MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
MODULE_AUTHOR("Mark Chen <mark-yw.chen@mediatek.com>");
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ffa74c26ee53..23f74c6c88b9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7649,8 +7649,8 @@ static int bnxt_get_avail_msix(struct bnxt *bp, int num);
static int __bnxt_reserve_rings(struct bnxt *bp)
{
struct bnxt_hw_rings hwr = {0};
+ int rx_rings, old_rx_rings, rc;
int cp = bp->cp_nr_rings;
- int rx_rings, rc;
int ulp_msix = 0;
bool sh = false;
int tx_cp;
@@ -7684,6 +7684,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
hwr.grp = bp->rx_nr_rings;
hwr.rss_ctx = bnxt_get_total_rss_ctxs(bp, &hwr);
hwr.stat = bnxt_get_func_stat_ctxs(bp);
+ old_rx_rings = bp->hw_resc.resv_rx_rings;
rc = bnxt_hwrm_reserve_rings(bp, &hwr);
if (rc)
@@ -7738,7 +7739,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
if (!bnxt_rings_ok(bp, &hwr))
return -ENOMEM;
- if (!netif_is_rxfh_configured(bp->dev))
+ if (old_rx_rings != bp->hw_resc.resv_rx_rings &&
+ !netif_is_rxfh_configured(bp->dev))
bnxt_set_dflt_rss_indir_tbl(bp, NULL);
if (!bnxt_ulp_registered(bp->edev) && BNXT_NEW_RM(bp)) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index d00ef0063820..ab8e3f197e7b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1863,8 +1863,14 @@ static void bnxt_modify_rss(struct bnxt *bp, struct ethtool_rxfh_context *ctx,
}
static int bnxt_rxfh_context_check(struct bnxt *bp,
+ const struct ethtool_rxfh_param *rxfh,
struct netlink_ext_ack *extack)
{
+ if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP) {
+ NL_SET_ERR_MSG_MOD(extack, "RSS hash function not supported");
+ return -EOPNOTSUPP;
+ }
+
if (!BNXT_SUPPORTS_MULTI_RSS_CTX(bp)) {
NL_SET_ERR_MSG_MOD(extack, "RSS contexts not supported");
return -EOPNOTSUPP;
@@ -1888,7 +1894,7 @@ static int bnxt_create_rxfh_context(struct net_device *dev,
struct bnxt_vnic_info *vnic;
int rc;
- rc = bnxt_rxfh_context_check(bp, extack);
+ rc = bnxt_rxfh_context_check(bp, rxfh, extack);
if (rc)
return rc;
@@ -1915,8 +1921,12 @@ static int bnxt_create_rxfh_context(struct net_device *dev,
if (rc)
goto out;
+ /* Populate defaults in the context */
bnxt_set_dflt_rss_indir_tbl(bp, ctx);
+ ctx->hfunc = ETH_RSS_HASH_TOP;
memcpy(vnic->rss_hash_key, bp->rss_hash_key, HW_HASH_KEY_SIZE);
+ memcpy(ethtool_rxfh_context_key(ctx),
+ bp->rss_hash_key, HW_HASH_KEY_SIZE);
rc = bnxt_hwrm_vnic_alloc(bp, vnic, 0, bp->rx_nr_rings);
if (rc) {
@@ -1953,7 +1963,7 @@ static int bnxt_modify_rxfh_context(struct net_device *dev,
struct bnxt_rss_ctx *rss_ctx;
int rc;
- rc = bnxt_rxfh_context_check(bp, extack);
+ rc = bnxt_rxfh_context_check(bp, rxfh, extack);
if (rc)
return rc;
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 99a75a59078e..caaa10157909 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -765,18 +765,17 @@ static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi,
}
/**
- * ice_xsk_pool - get XSK buffer pool bound to a ring
+ * ice_rx_xsk_pool - assign XSK buff pool to Rx ring
* @ring: Rx ring to use
*
- * Returns a pointer to xsk_buff_pool structure if there is a buffer pool
- * present, NULL otherwise.
+ * Sets XSK buff pool pointer on Rx ring.
*/
-static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
+static inline void ice_rx_xsk_pool(struct ice_rx_ring *ring)
{
struct ice_vsi *vsi = ring->vsi;
u16 qid = ring->q_index;
- return ice_get_xp_from_qid(vsi, qid);
+ WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
}
/**
@@ -801,7 +800,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid)
if (!ring)
return;
- ring->xsk_pool = ice_get_xp_from_qid(vsi, qid);
+ WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
}
/**
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 5d396c1a7731..1facf179a96f 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -536,7 +536,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
return err;
}
- ring->xsk_pool = ice_xsk_pool(ring);
+ ice_rx_xsk_pool(ring);
if (ring->xsk_pool) {
xdp_rxq_info_unreg(&ring->xdp_rxq);
@@ -597,7 +597,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
return 0;
}
- ok = ice_alloc_rx_bufs_zc(ring, num_bufs);
+ ok = ice_alloc_rx_bufs_zc(ring, ring->xsk_pool, num_bufs);
if (!ok) {
u16 pf_q = ring->vsi->rxq_map[ring->q_index];
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index ec636be4d17d..3de020020bc4 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2948,7 +2948,7 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi)
ice_for_each_rxq(vsi, i) {
struct ice_rx_ring *rx_ring = vsi->rx_rings[i];
- if (rx_ring->xsk_pool)
+ if (READ_ONCE(rx_ring->xsk_pool))
napi_schedule(&rx_ring->q_vector->napi);
}
}
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 8bb743f78fcb..8d25b6981269 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -456,7 +456,7 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring)
if (rx_ring->vsi->type == ICE_VSI_PF)
if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
- rx_ring->xdp_prog = NULL;
+ WRITE_ONCE(rx_ring->xdp_prog, NULL);
if (rx_ring->xsk_pool) {
kfree(rx_ring->xdp_buf);
rx_ring->xdp_buf = NULL;
@@ -1521,10 +1521,11 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
* budget and be more aggressive about cleaning up the Tx descriptors.
*/
ice_for_each_tx_ring(tx_ring, q_vector->tx) {
+ struct xsk_buff_pool *xsk_pool = READ_ONCE(tx_ring->xsk_pool);
bool wd;
- if (tx_ring->xsk_pool)
- wd = ice_xmit_zc(tx_ring);
+ if (xsk_pool)
+ wd = ice_xmit_zc(tx_ring, xsk_pool);
else if (ice_ring_is_xdp(tx_ring))
wd = true;
else
@@ -1550,6 +1551,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
budget_per_ring = budget;
ice_for_each_rx_ring(rx_ring, q_vector->rx) {
+ struct xsk_buff_pool *xsk_pool = READ_ONCE(rx_ring->xsk_pool);
int cleaned;
/* A dedicated path for zero-copy allows making a single
@@ -1557,7 +1559,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
* ice_clean_rx_irq function and makes the codebase cleaner.
*/
cleaned = rx_ring->xsk_pool ?
- ice_clean_rx_irq_zc(rx_ring, budget_per_ring) :
+ ice_clean_rx_irq_zc(rx_ring, xsk_pool, budget_per_ring) :
ice_clean_rx_irq(rx_ring, budget_per_ring);
work_done += cleaned;
/* if we clean as many as budgeted, we must not be done */
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index a65955eb23c0..240a7bec242b 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -52,10 +52,8 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
{
ice_clean_tx_ring(vsi->tx_rings[q_idx]);
- if (ice_is_xdp_ena_vsi(vsi)) {
- synchronize_rcu();
+ if (ice_is_xdp_ena_vsi(vsi))
ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
- }
ice_clean_rx_ring(vsi->rx_rings[q_idx]);
}
@@ -112,25 +110,29 @@ ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring,
* ice_qvec_cfg_msix - Enable IRQ for given queue vector
* @vsi: the VSI that contains queue vector
* @q_vector: queue vector
+ * @qid: queue index
*/
static void
-ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector, u16 qid)
{
u16 reg_idx = q_vector->reg_idx;
struct ice_pf *pf = vsi->back;
struct ice_hw *hw = &pf->hw;
- struct ice_tx_ring *tx_ring;
- struct ice_rx_ring *rx_ring;
+ int q, _qid = qid;
ice_cfg_itr(hw, q_vector);
- ice_for_each_tx_ring(tx_ring, q_vector->tx)
- ice_cfg_txq_interrupt(vsi, tx_ring->reg_idx, reg_idx,
- q_vector->tx.itr_idx);
+ for (q = 0; q < q_vector->num_ring_tx; q++) {
+ ice_cfg_txq_interrupt(vsi, _qid, reg_idx, q_vector->tx.itr_idx);
+ _qid++;
+ }
+
+ _qid = qid;
- ice_for_each_rx_ring(rx_ring, q_vector->rx)
- ice_cfg_rxq_interrupt(vsi, rx_ring->reg_idx, reg_idx,
- q_vector->rx.itr_idx);
+ for (q = 0; q < q_vector->num_ring_rx; q++) {
+ ice_cfg_rxq_interrupt(vsi, _qid, reg_idx, q_vector->rx.itr_idx);
+ _qid++;
+ }
ice_flush(hw);
}
@@ -164,6 +166,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
struct ice_tx_ring *tx_ring;
struct ice_rx_ring *rx_ring;
int timeout = 50;
+ int fail = 0;
int err;
if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq)
@@ -180,15 +183,17 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
usleep_range(1000, 2000);
}
+ synchronize_net();
+ netif_carrier_off(vsi->netdev);
+ netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+
ice_qvec_dis_irq(vsi, rx_ring, q_vector);
ice_qvec_toggle_napi(vsi, q_vector, false);
- netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
-
ice_fill_txq_meta(vsi, tx_ring, &txq_meta);
err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta);
- if (err)
- return err;
+ if (!fail)
+ fail = err;
if (ice_is_xdp_ena_vsi(vsi)) {
struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
@@ -196,17 +201,15 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
ice_fill_txq_meta(vsi, xdp_ring, &txq_meta);
err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, xdp_ring,
&txq_meta);
- if (err)
- return err;
+ if (!fail)
+ fail = err;
}
- err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true);
- if (err)
- return err;
+ ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, false);
ice_qp_clean_rings(vsi, q_idx);
ice_qp_reset_stats(vsi, q_idx);
- return 0;
+ return fail;
}
/**
@@ -219,40 +222,48 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
{
struct ice_q_vector *q_vector;
+ int fail = 0;
+ bool link_up;
int err;
err = ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx);
- if (err)
- return err;
+ if (!fail)
+ fail = err;
if (ice_is_xdp_ena_vsi(vsi)) {
struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
err = ice_vsi_cfg_single_txq(vsi, vsi->xdp_rings, q_idx);
- if (err)
- return err;
+ if (!fail)
+ fail = err;
ice_set_ring_xdp(xdp_ring);
ice_tx_xsk_pool(vsi, q_idx);
}
err = ice_vsi_cfg_single_rxq(vsi, q_idx);
- if (err)
- return err;
+ if (!fail)
+ fail = err;
q_vector = vsi->rx_rings[q_idx]->q_vector;
- ice_qvec_cfg_msix(vsi, q_vector);
+ ice_qvec_cfg_msix(vsi, q_vector, q_idx);
err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true);
- if (err)
- return err;
+ if (!fail)
+ fail = err;
ice_qvec_toggle_napi(vsi, q_vector, true);
ice_qvec_ena_irq(vsi, q_vector);
- netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+ /* make sure NAPI sees updated ice_{t,x}_ring::xsk_pool */
+ synchronize_net();
+ ice_get_link_status(vsi->port_info, &link_up);
+ if (link_up) {
+ netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+ netif_carrier_on(vsi->netdev);
+ }
clear_bit(ICE_CFG_BUSY, vsi->state);
- return 0;
+ return fail;
}
/**
@@ -459,6 +470,7 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
/**
* __ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
* @rx_ring: Rx ring
+ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
* @count: The number of buffers to allocate
*
* Place the @count of descriptors onto Rx ring. Handle the ring wrap
@@ -467,7 +479,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
*
* Returns true if all allocations were successful, false if any fail.
*/
-static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+ struct xsk_buff_pool *xsk_pool, u16 count)
{
u32 nb_buffs_extra = 0, nb_buffs = 0;
union ice_32b_rx_flex_desc *rx_desc;
@@ -479,8 +492,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
xdp = ice_xdp_buf(rx_ring, ntu);
if (ntu + count >= rx_ring->count) {
- nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp,
- rx_desc,
+ nb_buffs_extra = ice_fill_rx_descs(xsk_pool, xdp, rx_desc,
rx_ring->count - ntu);
if (nb_buffs_extra != rx_ring->count - ntu) {
ntu += nb_buffs_extra;
@@ -493,7 +505,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
ice_release_rx_desc(rx_ring, 0);
}
- nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count);
+ nb_buffs = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, count);
ntu += nb_buffs;
if (ntu == rx_ring->count)
@@ -509,6 +521,7 @@ exit:
/**
* ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
* @rx_ring: Rx ring
+ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
* @count: The number of buffers to allocate
*
* Wrapper for internal allocation routine; figure out how many tail
@@ -516,7 +529,8 @@ exit:
*
* Returns true if all calls to internal alloc routine succeeded
*/
-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+ struct xsk_buff_pool *xsk_pool, u16 count)
{
u16 rx_thresh = ICE_RING_QUARTER(rx_ring);
u16 leftover, i, tail_bumps;
@@ -525,9 +539,9 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
leftover = count - (tail_bumps * rx_thresh);
for (i = 0; i < tail_bumps; i++)
- if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh))
+ if (!__ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, rx_thresh))
return false;
- return __ice_alloc_rx_bufs_zc(rx_ring, leftover);
+ return __ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, leftover);
}
/**
@@ -596,8 +610,10 @@ out:
/**
* ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
* @xdp_ring: XDP Tx ring
+ * @xsk_pool: AF_XDP buffer pool pointer
*/
-static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
+static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring,
+ struct xsk_buff_pool *xsk_pool)
{
u16 ntc = xdp_ring->next_to_clean;
struct ice_tx_desc *tx_desc;
@@ -648,7 +664,7 @@ skip:
if (xdp_ring->next_to_clean >= cnt)
xdp_ring->next_to_clean -= cnt;
if (xsk_frames)
- xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+ xsk_tx_completed(xsk_pool, xsk_frames);
return completed_frames;
}
@@ -657,6 +673,7 @@ skip:
* ice_xmit_xdp_tx_zc - AF_XDP ZC handler for XDP_TX
* @xdp: XDP buffer to xmit
* @xdp_ring: XDP ring to produce descriptor onto
+ * @xsk_pool: AF_XDP buffer pool pointer
*
* note that this function works directly on xdp_buff, no need to convert
* it to xdp_frame. xdp_buff pointer is stored to ice_tx_buf so that cleaning
@@ -666,7 +683,8 @@ skip:
* was not enough space on XDP ring
*/
static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
- struct ice_tx_ring *xdp_ring)
+ struct ice_tx_ring *xdp_ring,
+ struct xsk_buff_pool *xsk_pool)
{
struct skb_shared_info *sinfo = NULL;
u32 size = xdp->data_end - xdp->data;
@@ -680,7 +698,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
free_space = ICE_DESC_UNUSED(xdp_ring);
if (free_space < ICE_RING_QUARTER(xdp_ring))
- free_space += ice_clean_xdp_irq_zc(xdp_ring);
+ free_space += ice_clean_xdp_irq_zc(xdp_ring, xsk_pool);
if (unlikely(!free_space))
goto busy;
@@ -700,7 +718,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
dma_addr_t dma;
dma = xsk_buff_xdp_get_dma(xdp);
- xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
+ xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, size);
tx_buf->xdp = xdp;
tx_buf->type = ICE_TX_BUF_XSK_TX;
@@ -742,12 +760,14 @@ busy:
* @xdp: xdp_buff used as input to the XDP program
* @xdp_prog: XDP program to run
* @xdp_ring: ring to be used for XDP_TX action
+ * @xsk_pool: AF_XDP buffer pool pointer
*
* Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
*/
static int
ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
- struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring)
+ struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
+ struct xsk_buff_pool *xsk_pool)
{
int err, result = ICE_XDP_PASS;
u32 act;
@@ -758,7 +778,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
if (!err)
return ICE_XDP_REDIR;
- if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
+ if (xsk_uses_need_wakeup(xsk_pool) && err == -ENOBUFS)
result = ICE_XDP_EXIT;
else
result = ICE_XDP_CONSUMED;
@@ -769,7 +789,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
case XDP_PASS:
break;
case XDP_TX:
- result = ice_xmit_xdp_tx_zc(xdp, xdp_ring);
+ result = ice_xmit_xdp_tx_zc(xdp, xdp_ring, xsk_pool);
if (result == ICE_XDP_CONSUMED)
goto out_failure;
break;
@@ -821,14 +841,16 @@ ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first,
/**
* ice_clean_rx_irq_zc - consumes packets from the hardware ring
* @rx_ring: AF_XDP Rx ring
+ * @xsk_pool: AF_XDP buffer pool pointer
* @budget: NAPI budget
*
* Returns number of processed packets on success, remaining budget on failure.
*/
-int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
+int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
+ struct xsk_buff_pool *xsk_pool,
+ int budget)
{
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
- struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool;
u32 ntc = rx_ring->next_to_clean;
u32 ntu = rx_ring->next_to_use;
struct xdp_buff *first = NULL;
@@ -891,7 +913,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
if (ice_is_non_eop(rx_ring, rx_desc))
continue;
- xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring);
+ xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring,
+ xsk_pool);
if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) {
xdp_xmit |= xdp_res;
} else if (xdp_res == ICE_XDP_EXIT) {
@@ -940,7 +963,8 @@ construct_skb:
rx_ring->next_to_clean = ntc;
entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring);
if (entries_to_alloc > ICE_RING_QUARTER(rx_ring))
- failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc);
+ failure |= !ice_alloc_rx_bufs_zc(rx_ring, xsk_pool,
+ entries_to_alloc);
ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0);
ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
@@ -963,17 +987,19 @@ construct_skb:
/**
* ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor
* @xdp_ring: XDP ring to produce the HW Tx descriptor on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
* @desc: AF_XDP descriptor to pull the DMA address and length from
* @total_bytes: bytes accumulator that will be used for stats update
*/
-static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
+static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring,
+ struct xsk_buff_pool *xsk_pool, struct xdp_desc *desc,
unsigned int *total_bytes)
{
struct ice_tx_desc *tx_desc;
dma_addr_t dma;
- dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr);
- xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len);
+ dma = xsk_buff_raw_get_dma(xsk_pool, desc->addr);
+ xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, desc->len);
tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
tx_desc->buf_addr = cpu_to_le64(dma);
@@ -986,10 +1012,13 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
/**
* ice_xmit_pkt_batch - produce a batch of HW Tx descriptors out of AF_XDP descriptors
* @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
* @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
* @total_bytes: bytes accumulator that will be used for stats update
*/
-static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
+static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring,
+ struct xsk_buff_pool *xsk_pool,
+ struct xdp_desc *descs,
unsigned int *total_bytes)
{
u16 ntu = xdp_ring->next_to_use;
@@ -999,8 +1028,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
dma_addr_t dma;
- dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, descs[i].addr);
- xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, descs[i].len);
+ dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);
+ xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len);
tx_desc = ICE_TX_DESC(xdp_ring, ntu++);
tx_desc->buf_addr = cpu_to_le64(dma);
@@ -1016,60 +1045,69 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
/**
* ice_fill_tx_hw_ring - produce the number of Tx descriptors onto ring
* @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
* @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
* @nb_pkts: count of packets to be send
* @total_bytes: bytes accumulator that will be used for stats update
*/
-static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
- u32 nb_pkts, unsigned int *total_bytes)
+static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring,
+ struct xsk_buff_pool *xsk_pool,
+ struct xdp_desc *descs, u32 nb_pkts,
+ unsigned int *total_bytes)
{
u32 batched, leftover, i;
batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH);
leftover = nb_pkts & (PKTS_PER_BATCH - 1);
for (i = 0; i < batched; i += PKTS_PER_BATCH)
- ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes);
+ ice_xmit_pkt_batch(xdp_ring, xsk_pool, &descs[i], total_bytes);
for (; i < batched + leftover; i++)
- ice_xmit_pkt(xdp_ring, &descs[i], total_bytes);
+ ice_xmit_pkt(xdp_ring, xsk_pool, &descs[i], total_bytes);
}
/**
* ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring
* @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: AF_XDP buffer pool pointer
*
* Returns true if there is no more work that needs to be done, false otherwise
*/
-bool ice_xmit_zc(struct ice_tx_ring *xdp_ring)
+bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool)
{
- struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs;
+ struct xdp_desc *descs = xsk_pool->tx_descs;
u32 nb_pkts, nb_processed = 0;
unsigned int total_bytes = 0;
int budget;
- ice_clean_xdp_irq_zc(xdp_ring);
+ ice_clean_xdp_irq_zc(xdp_ring, xsk_pool);
+
+ if (!netif_carrier_ok(xdp_ring->vsi->netdev) ||
+ !netif_running(xdp_ring->vsi->netdev))
+ return true;
budget = ICE_DESC_UNUSED(xdp_ring);
budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring));
- nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget);
+ nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget);
if (!nb_pkts)
return true;
if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
nb_processed = xdp_ring->count - xdp_ring->next_to_use;
- ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes);
+ ice_fill_tx_hw_ring(xdp_ring, xsk_pool, descs, nb_processed,
+ &total_bytes);
xdp_ring->next_to_use = 0;
}
- ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed,
- &total_bytes);
+ ice_fill_tx_hw_ring(xdp_ring, xsk_pool, &descs[nb_processed],
+ nb_pkts - nb_processed, &total_bytes);
ice_set_rs_bit(xdp_ring);
ice_xdp_ring_update_tail(xdp_ring);
ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes);
- if (xsk_uses_need_wakeup(xdp_ring->xsk_pool))
- xsk_set_tx_need_wakeup(xdp_ring->xsk_pool);
+ if (xsk_uses_need_wakeup(xsk_pool))
+ xsk_set_tx_need_wakeup(xsk_pool);
return nb_pkts < budget;
}
@@ -1091,7 +1129,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
struct ice_vsi *vsi = np->vsi;
struct ice_tx_ring *ring;
- if (test_bit(ICE_VSI_DOWN, vsi->state))
+ if (test_bit(ICE_VSI_DOWN, vsi->state) || !netif_carrier_ok(netdev))
return -ENETDOWN;
if (!ice_is_xdp_ena_vsi(vsi))
@@ -1102,7 +1140,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
ring = vsi->rx_rings[queue_id]->xdp_ring;
- if (!ring->xsk_pool)
+ if (!READ_ONCE(ring->xsk_pool))
return -EINVAL;
/* The idea here is that if NAPI is running, mark a miss, so
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h
index 6fa181f080ef..45adeb513253 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.h
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.h
@@ -20,16 +20,20 @@ struct ice_vsi;
#ifdef CONFIG_XDP_SOCKETS
int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool,
u16 qid);
-int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget);
+int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
+ struct xsk_buff_pool *xsk_pool,
+ int budget);
int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags);
-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count);
+bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+ struct xsk_buff_pool *xsk_pool, u16 count);
bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi);
void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring);
void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring);
-bool ice_xmit_zc(struct ice_tx_ring *xdp_ring);
+bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool);
int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc);
#else
-static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring)
+static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring,
+ struct xsk_buff_pool __always_unused *xsk_pool)
{
return false;
}
@@ -44,6 +48,7 @@ ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi,
static inline int
ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring,
+ struct xsk_buff_pool __always_unused *xsk_pool,
int __always_unused budget)
{
return 0;
@@ -51,6 +56,7 @@ ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring,
static inline bool
ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring,
+ struct xsk_buff_pool __always_unused *xsk_pool,
u16 __always_unused count)
{
return false;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index cb5c7b09e8a0..8daf938afc36 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6306,21 +6306,6 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
size_t n;
int i;
- switch (qopt->cmd) {
- case TAPRIO_CMD_REPLACE:
- break;
- case TAPRIO_CMD_DESTROY:
- return igc_tsn_clear_schedule(adapter);
- case TAPRIO_CMD_STATS:
- igc_taprio_stats(adapter->netdev, &qopt->stats);
- return 0;
- case TAPRIO_CMD_QUEUE_STATS:
- igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-
if (qopt->base_time < 0)
return -ERANGE;
@@ -6429,7 +6414,23 @@ static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter,
if (hw->mac.type != igc_i225)
return -EOPNOTSUPP;
- err = igc_save_qbv_schedule(adapter, qopt);
+ switch (qopt->cmd) {
+ case TAPRIO_CMD_REPLACE:
+ err = igc_save_qbv_schedule(adapter, qopt);
+ break;
+ case TAPRIO_CMD_DESTROY:
+ err = igc_tsn_clear_schedule(adapter);
+ break;
+ case TAPRIO_CMD_STATS:
+ igc_taprio_stats(adapter->netdev, &qopt->stats);
+ return 0;
+ case TAPRIO_CMD_QUEUE_STATS:
+ igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats);
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+
if (err)
return err;
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 8c45ad983abc..0d62a33afa80 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -953,13 +953,13 @@ static void mvpp2_bm_pool_update_fc(struct mvpp2_port *port,
static void mvpp2_bm_pool_update_priv_fc(struct mvpp2 *priv, bool en)
{
struct mvpp2_port *port;
- int i;
+ int i, j;
for (i = 0; i < priv->port_count; i++) {
port = priv->port_list[i];
if (port->priv->percpu_pools) {
- for (i = 0; i < port->nrxqs; i++)
- mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[i],
+ for (j = 0; j < port->nrxqs; j++)
+ mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[j],
port->tx_fc & en);
} else {
mvpp2_bm_pool_update_fc(port, port->pool_long, port->tx_fc & en);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index 8cf8ba2622f2..71a168746ebe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -932,6 +932,7 @@ err_rule:
mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, mh);
mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
err_mod_hdr:
+ *attr = *old_attr;
kfree(old_attr);
err_attr:
kvfree(spec);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 6e00afe4671b..797db853de36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -51,9 +51,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
MLX5_CAP_FLOWTABLE_NIC_RX(mdev, decap))
caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD;
- if ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
- MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) ||
- MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level))
+ if (IS_ENABLED(CONFIG_MLX5_CLS_ACT) &&
+ ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
+ MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) ||
+ MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level)))
caps |= MLX5_IPSEC_CAP_PRIO;
if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 00d5661dc62e..36845872ae94 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1409,7 +1409,12 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
if (!an_changes && link_modes == eproto.admin)
goto out;
- mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext);
+ err = mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext);
+ if (err) {
+ netdev_err(priv->netdev, "%s: failed to set ptys reg: %d\n", __func__, err);
+ goto out;
+ }
+
mlx5_toggle_port_link(mdev);
out:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 979c49ae6b5c..b43ca0b762c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -207,6 +207,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev)
static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unloaded)
{
struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+ struct devlink *devlink = priv_to_devlink(dev);
/* if this is the driver that initiated the fw reset, devlink completed the reload */
if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
@@ -218,9 +219,11 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unload
mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
else
mlx5_load_one(dev, true);
- devlink_remote_reload_actions_performed(priv_to_devlink(dev), 0,
+ devl_lock(devlink);
+ devlink_remote_reload_actions_performed(devlink, 0,
BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE));
+ devl_unlock(devlink);
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
index f7b01b3f0cba..1477db7f5307 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
@@ -48,6 +48,7 @@ static struct mlx5_irq *
irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_desc)
{
struct irq_affinity_desc auto_desc = {};
+ struct mlx5_irq *irq;
u32 irq_index;
int err;
@@ -64,9 +65,12 @@ irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_de
else
cpu_get(pool, cpumask_first(&af_desc->mask));
}
- return mlx5_irq_alloc(pool, irq_index,
- cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc,
- NULL);
+ irq = mlx5_irq_alloc(pool, irq_index,
+ cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc,
+ NULL);
+ if (IS_ERR(irq))
+ xa_erase(&pool->irqs, irq_index);
+ return irq;
}
/* Looking for the IRQ with the smallest refcount that fits req_mask.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index d0871c46b8c5..cf8045b92689 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1538,7 +1538,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
goto unlock;
for (i = 0; i < ldev->ports; i++) {
- if (ldev->pf[MLX5_LAG_P1].netdev == slave) {
+ if (ldev->pf[i].netdev == slave) {
port = i;
break;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 527da58c7953..5b7e6f4b5c7e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -2142,7 +2142,6 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev)
/* Panic tear down fw command will stop the PCI bus communication
* with the HCA, so the health poll is no longer needed.
*/
- mlx5_drain_health_wq(dev);
mlx5_stop_health_poll(dev, false);
ret = mlx5_cmd_fast_teardown_hca(dev);
@@ -2177,6 +2176,7 @@ static void shutdown(struct pci_dev *pdev)
mlx5_core_info(dev, "Shutdown was called\n");
set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
+ mlx5_drain_health_wq(dev);
err = mlx5_try_fast_unload(dev);
if (err)
mlx5_unload_one(dev, false);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
index b2986175d9af..b706f1486504 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
@@ -112,6 +112,7 @@ static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev)
struct mlx5_core_dev *mdev = sf_dev->mdev;
set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state);
+ mlx5_drain_health_wq(mdev);
mlx5_unload_one(mdev, false);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index 042ca0349124..d1db04baa1fa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -7,7 +7,7 @@
/* don't try to optimize STE allocation if the stack is too constaraining */
#define DR_RULE_MAX_STES_OPTIMIZED 0
#else
-#define DR_RULE_MAX_STES_OPTIMIZED 5
+#define DR_RULE_MAX_STES_OPTIMIZED 2
#endif
#define DR_RULE_MAX_STE_CHAIN_OPTIMIZED (DR_RULE_MAX_STES_OPTIMIZED + DR_ACTION_MAX_STES)
diff --git a/drivers/net/ethernet/meta/Kconfig b/drivers/net/ethernet/meta/Kconfig
index 86034ea4ba5b..c002ede36402 100644
--- a/drivers/net/ethernet/meta/Kconfig
+++ b/drivers/net/ethernet/meta/Kconfig
@@ -20,7 +20,7 @@ if NET_VENDOR_META
config FBNIC
tristate "Meta Platforms Host Network Interface"
depends on X86_64 || COMPILE_TEST
- depends on S390=n
+ depends on !S390
depends on MAX_SKB_FRAGS < 22
depends on PCI_MSI
select PHYLINK
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 714d2e804694..3507c2e28110 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4349,7 +4349,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
if (unlikely(!rtl_tx_slots_avail(tp))) {
if (net_ratelimit())
netdev_err(dev, "BUG! Tx Ring full when queue awake!\n");
- goto err_stop_0;
+ netif_stop_queue(dev);
+ return NETDEV_TX_BUSY;
}
opts[1] = rtl8169_tx_vlan_tag(skb);
@@ -4405,11 +4406,6 @@ err_dma_0:
dev_kfree_skb_any(skb);
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
-
-err_stop_0:
- netif_stop_queue(dev);
- dev->stats.tx_dropped++;
- return NETDEV_TX_BUSY;
}
static unsigned int rtl_last_frag_len(struct sk_buff *skb)
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index e342f387c3dd..02fdf66e07fa 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -2219,9 +2219,9 @@ static void axienet_dma_err_handler(struct work_struct *work)
~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
axienet_set_mac_address(ndev, NULL);
axienet_set_multicast_list(ndev);
- axienet_setoptions(ndev, lp->options);
napi_enable(&lp->napi_rx);
napi_enable(&lp->napi_tx);
+ axienet_setoptions(ndev, lp->options);
}
/**
diff --git a/drivers/net/phy/aquantia/aquantia_main.c b/drivers/net/phy/aquantia/aquantia_main.c
index d12e35374231..e982e9ce44a5 100644
--- a/drivers/net/phy/aquantia/aquantia_main.c
+++ b/drivers/net/phy/aquantia/aquantia_main.c
@@ -653,13 +653,7 @@ static int aqr107_fill_interface_modes(struct phy_device *phydev)
unsigned long *possible = phydev->possible_interfaces;
unsigned int serdes_mode, rate_adapt;
phy_interface_t interface;
- int i, val, ret;
-
- ret = phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1,
- VEND1_GLOBAL_CFG_10M, val, val != 0,
- 1000, 100000, false);
- if (ret)
- return ret;
+ int i, val;
/* Walk the media-speed configuration registers to determine which
* host-side serdes modes may be used by the PHY depending on the
@@ -708,6 +702,25 @@ static int aqr107_fill_interface_modes(struct phy_device *phydev)
return 0;
}
+static int aqr113c_fill_interface_modes(struct phy_device *phydev)
+{
+ int val, ret;
+
+ /* It's been observed on some models that - when coming out of suspend
+ * - the FW signals that the PHY is ready but the GLOBAL_CFG registers
+ * continue on returning zeroes for some time. Let's poll the 100M
+ * register until it returns a real value as both 113c and 115c support
+ * this mode.
+ */
+ ret = phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1,
+ VEND1_GLOBAL_CFG_100M, val, val != 0,
+ 1000, 100000, false);
+ if (ret)
+ return ret;
+
+ return aqr107_fill_interface_modes(phydev);
+}
+
static int aqr113c_config_init(struct phy_device *phydev)
{
int ret;
@@ -725,7 +738,7 @@ static int aqr113c_config_init(struct phy_device *phydev)
if (ret)
return ret;
- return aqr107_fill_interface_modes(phydev);
+ return aqr113c_fill_interface_modes(phydev);
}
static int aqr107_probe(struct phy_device *phydev)
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index dd519805deee..65b0a3115e14 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1389,6 +1389,8 @@ static int ksz9131_config_init(struct phy_device *phydev)
const struct device *dev_walker;
int ret;
+ phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
+
dev_walker = &phydev->mdio.dev;
do {
of_node = dev_walker->of_node;
@@ -1438,28 +1440,30 @@ static int ksz9131_config_init(struct phy_device *phydev)
#define MII_KSZ9131_AUTO_MDIX 0x1C
#define MII_KSZ9131_AUTO_MDI_SET BIT(7)
#define MII_KSZ9131_AUTO_MDIX_SWAP_OFF BIT(6)
+#define MII_KSZ9131_DIG_AXAN_STS 0x14
+#define MII_KSZ9131_DIG_AXAN_STS_LINK_DET BIT(14)
+#define MII_KSZ9131_DIG_AXAN_STS_A_SELECT BIT(12)
static int ksz9131_mdix_update(struct phy_device *phydev)
{
int ret;
- ret = phy_read(phydev, MII_KSZ9131_AUTO_MDIX);
- if (ret < 0)
- return ret;
-
- if (ret & MII_KSZ9131_AUTO_MDIX_SWAP_OFF) {
- if (ret & MII_KSZ9131_AUTO_MDI_SET)
- phydev->mdix_ctrl = ETH_TP_MDI;
- else
- phydev->mdix_ctrl = ETH_TP_MDI_X;
+ if (phydev->mdix_ctrl != ETH_TP_MDI_AUTO) {
+ phydev->mdix = phydev->mdix_ctrl;
} else {
- phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
- }
+ ret = phy_read(phydev, MII_KSZ9131_DIG_AXAN_STS);
+ if (ret < 0)
+ return ret;
- if (ret & MII_KSZ9131_AUTO_MDI_SET)
- phydev->mdix = ETH_TP_MDI;
- else
- phydev->mdix = ETH_TP_MDI_X;
+ if (ret & MII_KSZ9131_DIG_AXAN_STS_LINK_DET) {
+ if (ret & MII_KSZ9131_DIG_AXAN_STS_A_SELECT)
+ phydev->mdix = ETH_TP_MDI;
+ else
+ phydev->mdix = ETH_TP_MDI_X;
+ } else {
+ phydev->mdix = ETH_TP_MDI_INVALID;
+ }
+ }
return 0;
}
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index bed839237fb5..87865918dab6 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -1465,6 +1465,13 @@ static struct phy_driver realtek_drvs[] = {
.handle_interrupt = genphy_handle_interrupt_no_ack,
.suspend = genphy_suspend,
.resume = genphy_resume,
+ }, {
+ PHY_ID_MATCH_EXACT(0x001cc960),
+ .name = "RTL8366S Gigabit Ethernet",
+ .suspend = genphy_suspend,
+ .resume = genphy_resume,
+ .read_mmd = genphy_read_mmd_unsupported,
+ .write_mmd = genphy_write_mmd_unsupported,
},
};
diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
index 0a662e42ed96..cb7d2f798fb4 100644
--- a/drivers/net/usb/sr9700.c
+++ b/drivers/net/usb/sr9700.c
@@ -179,6 +179,7 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc)
struct usbnet *dev = netdev_priv(netdev);
__le16 res;
int rc = 0;
+ int err;
if (phy_id) {
netdev_dbg(netdev, "Only internal phy supported\n");
@@ -189,11 +190,17 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc)
if (loc == MII_BMSR) {
u8 value;
- sr_read_reg(dev, SR_NSR, &value);
+ err = sr_read_reg(dev, SR_NSR, &value);
+ if (err < 0)
+ return err;
+
if (value & NSR_LINKST)
rc = 1;
}
- sr_share_read_word(dev, 1, loc, &res);
+ err = sr_share_read_word(dev, 1, loc, &res);
+ if (err < 0)
+ return err;
+
if (rc == 1)
res = le16_to_cpu(res) | BMSR_LSTATUS;
else
diff --git a/drivers/net/wan/fsl_qmc_hdlc.c b/drivers/net/wan/fsl_qmc_hdlc.c
index c5e7ca793c43..8fcfbde31a1c 100644
--- a/drivers/net/wan/fsl_qmc_hdlc.c
+++ b/drivers/net/wan/fsl_qmc_hdlc.c
@@ -18,6 +18,7 @@
#include <linux/hdlc.h>
#include <linux/mod_devicetable.h>
#include <linux/module.h>
+#include <linux/mutex.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
@@ -37,7 +38,7 @@ struct qmc_hdlc {
struct qmc_chan *qmc_chan;
struct net_device *netdev;
struct framer *framer;
- spinlock_t carrier_lock; /* Protect carrier detection */
+ struct mutex carrier_lock; /* Protect carrier detection */
struct notifier_block nb;
bool is_crc32;
spinlock_t tx_lock; /* Protect tx descriptors */
@@ -60,7 +61,7 @@ static int qmc_hdlc_framer_set_carrier(struct qmc_hdlc *qmc_hdlc)
if (!qmc_hdlc->framer)
return 0;
- guard(spinlock_irqsave)(&qmc_hdlc->carrier_lock);
+ guard(mutex)(&qmc_hdlc->carrier_lock);
ret = framer_get_status(qmc_hdlc->framer, &framer_status);
if (ret) {
@@ -249,6 +250,7 @@ static void qmc_hcld_recv_complete(void *context, size_t length, unsigned int fl
struct qmc_hdlc_desc *desc = context;
struct net_device *netdev;
struct qmc_hdlc *qmc_hdlc;
+ size_t crc_size;
int ret;
netdev = desc->netdev;
@@ -267,15 +269,26 @@ static void qmc_hcld_recv_complete(void *context, size_t length, unsigned int fl
if (flags & QMC_RX_FLAG_HDLC_CRC) /* CRC error */
netdev->stats.rx_crc_errors++;
kfree_skb(desc->skb);
- } else {
- netdev->stats.rx_packets++;
- netdev->stats.rx_bytes += length;
+ goto re_queue;
+ }
- skb_put(desc->skb, length);
- desc->skb->protocol = hdlc_type_trans(desc->skb, netdev);
- netif_rx(desc->skb);
+ /* Discard the CRC */
+ crc_size = qmc_hdlc->is_crc32 ? 4 : 2;
+ if (length < crc_size) {
+ netdev->stats.rx_length_errors++;
+ kfree_skb(desc->skb);
+ goto re_queue;
}
+ length -= crc_size;
+
+ netdev->stats.rx_packets++;
+ netdev->stats.rx_bytes += length;
+
+ skb_put(desc->skb, length);
+ desc->skb->protocol = hdlc_type_trans(desc->skb, netdev);
+ netif_rx(desc->skb);
+re_queue:
/* Re-queue a transfer using the same descriptor */
ret = qmc_hdlc_recv_queue(qmc_hdlc, desc, desc->dma_size);
if (ret) {
@@ -706,7 +719,7 @@ static int qmc_hdlc_probe(struct platform_device *pdev)
qmc_hdlc->dev = dev;
spin_lock_init(&qmc_hdlc->tx_lock);
- spin_lock_init(&qmc_hdlc->carrier_lock);
+ mutex_init(&qmc_hdlc->carrier_lock);
qmc_hdlc->qmc_chan = devm_qmc_chan_get_bychild(dev, dev->of_node);
if (IS_ERR(qmc_hdlc->qmc_chan))
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 876c029f58f6..9e0b9e329bda 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -473,7 +473,8 @@ static void __ath12k_pci_ext_irq_disable(struct ath12k_base *ab)
{
int i;
- clear_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags);
+ if (!test_and_clear_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags))
+ return;
for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
diff --git a/drivers/net/wireless/ath/ath12k/wow.c b/drivers/net/wireless/ath/ath12k/wow.c
index bead19db2c9a..9b8684abbe40 100644
--- a/drivers/net/wireless/ath/ath12k/wow.c
+++ b/drivers/net/wireless/ath/ath12k/wow.c
@@ -361,7 +361,7 @@ static int ath12k_wow_vif_set_wakeups(struct ath12k_vif *arvif,
struct ath12k *ar = arvif->ar;
unsigned long wow_mask = 0;
int pattern_id = 0;
- int ret, i;
+ int ret, i, j;
/* Setup requested WOW features */
switch (arvif->vdev_type) {
@@ -431,9 +431,9 @@ static int ath12k_wow_vif_set_wakeups(struct ath12k_vif *arvif,
eth_pattern->pattern_len);
/* convert bitmask to bytemask */
- for (i = 0; i < eth_pattern->pattern_len; i++)
- if (eth_pattern->mask[i / 8] & BIT(i % 8))
- new_pattern.bytemask[i] = 0xff;
+ for (j = 0; j < eth_pattern->pattern_len; j++)
+ if (eth_pattern->mask[j / 8] & BIT(j % 8))
+ new_pattern.bytemask[j] = 0xff;
new_pattern.pattern_len = eth_pattern->pattern_len;
new_pattern.pkt_offset = eth_pattern->pkt_offset;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 2e6268cb06c0..1bab93d049df 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -303,6 +303,7 @@ mt7921_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
mvif->bss_conf.mt76.omac_idx = mvif->bss_conf.mt76.idx;
mvif->phy = phy;
+ mvif->bss_conf.vif = mvif;
mvif->bss_conf.mt76.band_idx = 0;
mvif->bss_conf.mt76.wmm_idx = mvif->bss_conf.mt76.idx % MT76_CONNAC_MAX_WMM_SETS;
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index d1d7825318c3..6c395a2600e8 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -56,7 +56,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
unsigned int thlen = 0;
unsigned int p_off = 0;
unsigned int ip_proto;
- u64 ret, remainder, gso_size;
if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
@@ -99,16 +98,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16));
- if (hdr->gso_size) {
- gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
- ret = div64_u64_rem(skb->len, gso_size, &remainder);
- if (!(ret && (hdr->gso_size > needed) &&
- ((remainder > needed) || (remainder == 0)))) {
- return -EINVAL;
- }
- skb_shinfo(skb)->tx_flags |= SKBFL_SHARED_FRAG;
- }
-
if (!pskb_may_pull(skb, needed))
return -EINVAL;
@@ -182,6 +171,11 @@ retry:
if (gso_type != SKB_GSO_UDP_L4)
return -EINVAL;
break;
+ case SKB_GSO_TCPV4:
+ case SKB_GSO_TCPV6:
+ if (skb->csum_offset != offsetof(struct tcphdr, check))
+ return -EINVAL;
+ break;
}
/* Kernel has a special handling for GSO_BY_FRAGS. */
diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h
index 09e72215b9f9..085b749cdd97 100644
--- a/include/trace/events/mptcp.h
+++ b/include/trace/events/mptcp.h
@@ -34,7 +34,7 @@ TRACE_EVENT(mptcp_subflow_get_send,
struct sock *ssk;
__entry->active = mptcp_subflow_active(subflow);
- __entry->backup = subflow->backup;
+ __entry->backup = subflow->backup || subflow->request_bkup;
if (subflow->tcp_sock && sk_fullsock(subflow->tcp_sock))
__entry->free = sk_stream_memory_free(subflow->tcp_sock);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 8a4ebd93adfc..06da8ac13dca 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -119,13 +119,6 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state)
case DISCOVERY_STARTING:
break;
case DISCOVERY_FINDING:
- /* If discovery was not started then it was initiated by the
- * MGMT interface so no MGMT event shall be generated either
- */
- if (old_state != DISCOVERY_STARTING) {
- hdev->discovery.state = old_state;
- return;
- }
mgmt_discovering(hdev, 1);
break;
case DISCOVERY_RESOLVING:
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index dce8035ca799..d0c118c47f6c 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1721,9 +1721,10 @@ static void le_set_scan_enable_complete(struct hci_dev *hdev, u8 enable)
switch (enable) {
case LE_SCAN_ENABLE:
hci_dev_set_flag(hdev, HCI_LE_SCAN);
- if (hdev->le_scan_type == LE_SCAN_ACTIVE)
+ if (hdev->le_scan_type == LE_SCAN_ACTIVE) {
clear_pending_adv_report(hdev);
- hci_discovery_set_state(hdev, DISCOVERY_FINDING);
+ hci_discovery_set_state(hdev, DISCOVERY_FINDING);
+ }
break;
case LE_SCAN_DISABLE:
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index cd2ed16da8a4..a31d39a821f4 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -2976,6 +2976,27 @@ static int hci_passive_scan_sync(struct hci_dev *hdev)
*/
filter_policy = hci_update_accept_list_sync(hdev);
+ /* If suspended and filter_policy set to 0x00 (no acceptlist) then
+ * passive scanning cannot be started since that would require the host
+ * to be woken up to process the reports.
+ */
+ if (hdev->suspended && !filter_policy) {
+ /* Check if accept list is empty then there is no need to scan
+ * while suspended.
+ */
+ if (list_empty(&hdev->le_accept_list))
+ return 0;
+
+ /* If there are devices is the accept_list that means some
+ * devices could not be programmed which in non-suspended case
+ * means filter_policy needs to be set to 0x00 so the host needs
+ * to filter, but since this is treating suspended case we
+ * can ignore device needing host to filter to allow devices in
+ * the acceptlist to be able to wakeup the system.
+ */
+ filter_policy = 0x01;
+ }
+
/* When the controller is using random resolvable addresses and
* with that having LE privacy enabled, then controllers with
* Extended Scanner Filter Policies support can now enable support
diff --git a/net/core/dev.c b/net/core/dev.c
index 6ea1d20676fb..751d9b70e6ad 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5150,6 +5150,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb)
bpf_net_ctx_clear(bpf_net_ctx);
return XDP_DROP;
}
+ bpf_net_ctx_clear(bpf_net_ctx);
}
return XDP_PASS;
out_redir:
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 87e67194f240..73fd7f543fd0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3288,7 +3288,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
- dev = rtnl_dev_get(net, tb);
+ dev = rtnl_dev_get(tgt_net, tb);
else if (tb[IFLA_GROUP])
err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP]));
else
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 983fee76f5cf..8ca13208d240 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1331,13 +1331,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
const struct ethtool_ops *ops = dev->ethtool_ops;
u32 dev_indir_size = 0, dev_key_size = 0, i;
+ u32 user_indir_len = 0, indir_bytes = 0;
struct ethtool_rxfh_param rxfh_dev = {};
struct ethtool_rxfh_context *ctx = NULL;
struct netlink_ext_ack *extack = NULL;
struct ethtool_rxnfc rx_rings;
struct ethtool_rxfh rxfh;
bool locked = false; /* dev->ethtool->rss_lock taken */
- u32 indir_bytes = 0;
bool create = false;
u8 *rss_config;
int ret;
@@ -1382,10 +1382,9 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
rxfh.input_xfrm == RXH_XFRM_NO_CHANGE))
return -EINVAL;
- if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
- indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]);
+ indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]);
- rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER);
+ rss_config = kzalloc(indir_bytes + dev_key_size, GFP_USER);
if (!rss_config)
return -ENOMEM;
@@ -1400,6 +1399,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
*/
if (rxfh.indir_size &&
rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) {
+ user_indir_len = indir_bytes;
rxfh_dev.indir = (u32 *)rss_config;
rxfh_dev.indir_size = dev_indir_size;
ret = ethtool_copy_validate_indir(rxfh_dev.indir,
@@ -1426,7 +1426,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
rxfh_dev.key_size = dev_key_size;
rxfh_dev.key = rss_config + indir_bytes;
if (copy_from_user(rxfh_dev.key,
- useraddr + rss_cfg_offset + indir_bytes,
+ useraddr + rss_cfg_offset + user_indir_len,
rxfh.key_size)) {
ret = -EFAULT;
goto out;
@@ -1474,16 +1474,21 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
rxfh_dev.input_xfrm = rxfh.input_xfrm;
if (rxfh.rss_context && ops->create_rxfh_context) {
- if (create)
+ if (create) {
ret = ops->create_rxfh_context(dev, ctx, &rxfh_dev,
extack);
- else if (rxfh_dev.rss_delete)
+ /* Make sure driver populates defaults */
+ WARN_ON_ONCE(!ret && !rxfh_dev.key &&
+ !memchr_inv(ethtool_rxfh_context_key(ctx),
+ 0, ctx->key_size));
+ } else if (rxfh_dev.rss_delete) {
ret = ops->remove_rxfh_context(dev, ctx,
rxfh.rss_context,
extack);
- else
+ } else {
ret = ops->modify_rxfh_context(dev, ctx, &rxfh_dev,
extack);
+ }
} else {
ret = ops->set_rxfh(dev, &rxfh_dev, extack);
}
@@ -1522,6 +1527,22 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
kfree(ctx);
goto out;
}
+
+ /* Fetch the defaults for the old API, in the new API drivers
+ * should write defaults into ctx themselves.
+ */
+ rxfh_dev.indir = (u32 *)rss_config;
+ rxfh_dev.indir_size = dev_indir_size;
+
+ rxfh_dev.key = rss_config + indir_bytes;
+ rxfh_dev.key_size = dev_key_size;
+
+ ret = ops->get_rxfh(dev, &rxfh_dev);
+ if (WARN_ON(ret)) {
+ xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context);
+ kfree(ctx);
+ goto out;
+ }
}
if (rxfh_dev.rss_delete) {
WARN_ON(xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context) != ctx);
@@ -1530,12 +1551,14 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
if (rxfh_dev.indir) {
for (i = 0; i < dev_indir_size; i++)
ethtool_rxfh_context_indir(ctx)[i] = rxfh_dev.indir[i];
- ctx->indir_configured = 1;
+ ctx->indir_configured =
+ rxfh.indir_size &&
+ rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE;
}
if (rxfh_dev.key) {
memcpy(ethtool_rxfh_context_key(ctx), rxfh_dev.key,
dev_key_size);
- ctx->key_configured = 1;
+ ctx->key_configured = !!rxfh.key_size;
}
if (rxfh_dev.hfunc != ETH_RSS_HASH_NO_CHANGE)
ctx->hfunc = rxfh_dev.hfunc;
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 71679137eff2..5c4c4505ab9a 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -111,7 +111,8 @@ rss_reply_size(const struct ethnl_req_info *req_base,
const struct rss_reply_data *data = RSS_REPDATA(reply_base);
int len;
- len = nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */
+ len = nla_total_size(sizeof(u32)) + /* _RSS_CONTEXT */
+ nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */
nla_total_size(sizeof(u32)) + /* _RSS_INPUT_XFRM */
nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */
nla_total_size(data->hkey_size); /* _RSS_HKEY */
@@ -124,6 +125,11 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base,
const struct ethnl_reply_data *reply_base)
{
const struct rss_reply_data *data = RSS_REPDATA(reply_base);
+ struct rss_req_info *request = RSS_REQINFO(req_base);
+
+ if (request->rss_context &&
+ nla_put_u32(skb, ETHTOOL_A_RSS_CONTEXT, request->rss_context))
+ return -EMSGSIZE;
if ((data->hfunc &&
nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) ||
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index 4d42d0756fd7..a5db7c67d61b 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -145,25 +145,27 @@ static struct pernet_operations iptable_nat_net_ops = {
static int __init iptable_nat_init(void)
{
- int ret = xt_register_template(&nf_nat_ipv4_table,
- iptable_nat_table_init);
+ int ret;
+ /* net->gen->ptr[iptable_nat_net_id] must be allocated
+ * before calling iptable_nat_table_init().
+ */
+ ret = register_pernet_subsys(&iptable_nat_net_ops);
if (ret < 0)
return ret;
- ret = register_pernet_subsys(&iptable_nat_net_ops);
- if (ret < 0) {
- xt_unregister_template(&nf_nat_ipv4_table);
- return ret;
- }
+ ret = xt_register_template(&nf_nat_ipv4_table,
+ iptable_nat_table_init);
+ if (ret < 0)
+ unregister_pernet_subsys(&iptable_nat_net_ops);
return ret;
}
static void __exit iptable_nat_exit(void)
{
- unregister_pernet_subsys(&iptable_nat_net_ops);
xt_unregister_template(&nf_nat_ipv4_table);
+ unregister_pernet_subsys(&iptable_nat_net_ops);
}
module_init(iptable_nat_init);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 454362e359da..e2b9583ed96a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -754,8 +754,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
* <prev RTT . ><current RTT .. ><next RTT .... >
*/
- if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
- !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) {
u64 rcvwin, grow;
int rcvbuf;
@@ -771,12 +770,22 @@ void tcp_rcv_space_adjust(struct sock *sk)
rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin),
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
- if (rcvbuf > sk->sk_rcvbuf) {
- WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
+ if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+ if (rcvbuf > sk->sk_rcvbuf) {
+ WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
- /* Make the window clamp follow along. */
- WRITE_ONCE(tp->window_clamp,
- tcp_win_from_space(sk, rcvbuf));
+ /* Make the window clamp follow along. */
+ WRITE_ONCE(tp->window_clamp,
+ tcp_win_from_space(sk, rcvbuf));
+ }
+ } else {
+ /* Make the window clamp follow along while being bounded
+ * by SO_RCVBUF.
+ */
+ int clamp = tcp_win_from_space(sk, min(rcvbuf, sk->sk_rcvbuf));
+
+ if (clamp > tp->window_clamp)
+ WRITE_ONCE(tp->window_clamp, clamp);
}
}
tp->rcvq_space.space = copied;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 4b791e74529e..e4ad3311e148 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -140,6 +140,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
if (thlen < sizeof(*th))
goto out;
+ if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb)))
+ goto out;
+
if (!pskb_may_pull(skb, thlen))
goto out;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index aa2e0a28ca61..bc8a9da750fe 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -278,6 +278,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
if (gso_skb->len <= sizeof(*uh) + mss)
return ERR_PTR(-EINVAL);
+ if (unlikely(skb_checksum_start(gso_skb) !=
+ skb_transport_header(gso_skb)))
+ return ERR_PTR(-EINVAL);
+
if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) {
/* Packet is from an untrusted source, reset gso_segs. */
skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh),
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 70a0b2ad6bd7..b8eec1b6cc2c 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -227,6 +227,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
return NULL;
memset(ndopts, 0, sizeof(*ndopts));
while (opt_len) {
+ bool unknown = false;
int l;
if (opt_len < sizeof(struct nd_opt_hdr))
return NULL;
@@ -262,22 +263,23 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
break;
#endif
default:
- if (ndisc_is_useropt(dev, nd_opt)) {
- ndopts->nd_useropts_end = nd_opt;
- if (!ndopts->nd_useropts)
- ndopts->nd_useropts = nd_opt;
- } else {
- /*
- * Unknown options must be silently ignored,
- * to accommodate future extension to the
- * protocol.
- */
- ND_PRINTK(2, notice,
- "%s: ignored unsupported option; type=%d, len=%d\n",
- __func__,
- nd_opt->nd_opt_type,
- nd_opt->nd_opt_len);
- }
+ unknown = true;
+ }
+ if (ndisc_is_useropt(dev, nd_opt)) {
+ ndopts->nd_useropts_end = nd_opt;
+ if (!ndopts->nd_useropts)
+ ndopts->nd_useropts = nd_opt;
+ } else if (unknown) {
+ /*
+ * Unknown options must be silently ignored,
+ * to accommodate future extension to the
+ * protocol.
+ */
+ ND_PRINTK(2, notice,
+ "%s: ignored unsupported option; type=%d, len=%d\n",
+ __func__,
+ nd_opt->nd_opt_type,
+ nd_opt->nd_opt_len);
}
next_opt:
opt_len -= l;
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index 52cf104e3478..e119d4f090cc 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -147,23 +147,27 @@ static struct pernet_operations ip6table_nat_net_ops = {
static int __init ip6table_nat_init(void)
{
- int ret = xt_register_template(&nf_nat_ipv6_table,
- ip6table_nat_table_init);
+ int ret;
+ /* net->gen->ptr[ip6table_nat_net_id] must be allocated
+ * before calling ip6t_nat_register_lookups().
+ */
+ ret = register_pernet_subsys(&ip6table_nat_net_ops);
if (ret < 0)
return ret;
- ret = register_pernet_subsys(&ip6table_nat_net_ops);
+ ret = xt_register_template(&nf_nat_ipv6_table,
+ ip6table_nat_table_init);
if (ret)
- xt_unregister_template(&nf_nat_ipv6_table);
+ unregister_pernet_subsys(&ip6table_nat_net_ops);
return ret;
}
static void __exit ip6table_nat_exit(void)
{
- unregister_pernet_subsys(&ip6table_nat_net_ops);
xt_unregister_template(&nf_nat_ipv6_table);
+ unregister_pernet_subsys(&ip6table_nat_net_ops);
}
module_init(ip6table_nat_init);
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index c3b0b610b0aa..c00323fa9eb6 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -335,8 +335,8 @@ static void iucv_sever_path(struct sock *sk, int with_user_data)
struct iucv_sock *iucv = iucv_sk(sk);
struct iucv_path *path = iucv->path;
- if (iucv->path) {
- iucv->path = NULL;
+ /* Whoever resets the path pointer, must sever and free it. */
+ if (xchg(&iucv->path, NULL)) {
if (with_user_data) {
low_nmcpy(user_data, iucv->src_name);
high_nmcpy(user_data, iucv->dst_name);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 85cb71de370f..b02b84ce2130 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -114,7 +114,7 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata,
/* apply all changes now - no failures allowed */
- if (monitor_sdata)
+ if (monitor_sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
ieee80211_set_mu_mimo_follow(monitor_sdata, params);
if (params->flags) {
@@ -3053,6 +3053,9 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
+ if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
+ return -EOPNOTSUPP;
+
sdata = wiphy_dereference(local->hw.wiphy,
local->monitor_sdata);
if (!sdata)
@@ -3115,7 +3118,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
if (has_monitor) {
sdata = wiphy_dereference(local->hw.wiphy,
local->monitor_sdata);
- if (sdata) {
+ if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
sdata->deflink.user_power_level = local->user_power_level;
if (txp_type != sdata->vif.bss_conf.txpower_type)
update_txp_type = true;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 72a9ba8bc5fd..edba4a31844f 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1768,7 +1768,7 @@ static bool __ieee80211_tx(struct ieee80211_local *local,
break;
}
sdata = rcu_dereference(local->monitor_sdata);
- if (sdata) {
+ if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
vif = &sdata->vif;
info->hw_queue =
vif->hw_queue[skb_get_queue_mapping(skb)];
@@ -3957,7 +3957,8 @@ begin:
break;
}
tx.sdata = rcu_dereference(local->monitor_sdata);
- if (tx.sdata) {
+ if (tx.sdata &&
+ ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
vif = &tx.sdata->vif;
info->hw_queue =
vif->hw_queue[skb_get_queue_mapping(skb)];
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index ced19ce7c51a..c7ad9bc5973a 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -776,7 +776,7 @@ static void __iterate_interfaces(struct ieee80211_local *local,
sdata = rcu_dereference_check(local->monitor_sdata,
lockdep_is_held(&local->iflist_mtx) ||
lockdep_is_held(&local->hw.wiphy->mtx));
- if (sdata &&
+ if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) &&
(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only ||
sdata->flags & IEEE80211_SDATA_IN_DRIVER))
iterator(data, sdata->vif.addr, &sdata->vif);
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index c30405e76833..7884217f33eb 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -19,7 +19,9 @@ static const struct snmp_mib mptcp_snmp_list[] = {
SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS),
SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN),
SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX),
+ SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX),
SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX),
+ SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX),
SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC),
SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX),
SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 2704afd0dfe4..66aa67f49d03 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -14,7 +14,9 @@ enum linux_mptcp_mib_field {
MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */
MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */
MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */
+ MPTCP_MIB_JOINSYNBACKUPRX, /* Received a SYN + MP_JOIN + backup flag */
MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */
+ MPTCP_MIB_JOINSYNACKBACKUPRX, /* Received a SYN/ACK + MP_JOIN + backup flag */
MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */
MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */
MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 8e8dcfbc2993..8a68382a4fe9 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -909,7 +909,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
return true;
} else if (subflow_req->mp_join) {
opts->suboptions = OPTION_MPTCP_MPJ_SYNACK;
- opts->backup = subflow_req->backup;
+ opts->backup = subflow_req->request_bkup;
opts->join_id = subflow_req->local_id;
opts->thmac = subflow_req->thmac;
opts->nonce = subflow_req->local_nonce;
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 55406720c607..23bb89c94e90 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -426,6 +426,18 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
return mptcp_pm_nl_get_local_id(msk, &skc_local);
}
+bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
+{
+ struct mptcp_addr_info skc_local;
+
+ mptcp_local_address((struct sock_common *)skc, &skc_local);
+
+ if (mptcp_pm_is_userspace(msk))
+ return mptcp_userspace_pm_is_backup(msk, &skc_local);
+
+ return mptcp_pm_nl_is_backup(msk, &skc_local);
+}
+
int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
u8 *flags, int *ifindex)
{
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index ea9e5817b9e9..37954a0b087d 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -471,7 +471,6 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con
slow = lock_sock_fast(ssk);
if (prio) {
subflow->send_mp_prio = 1;
- subflow->backup = backup;
subflow->request_bkup = backup;
}
@@ -1102,6 +1101,24 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
return ret;
}
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
+{
+ struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+ struct mptcp_pm_addr_entry *entry;
+ bool backup = false;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+ if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) {
+ backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return backup;
+}
+
#define MPTCP_PM_CMD_GRP_OFFSET 0
#define MPTCP_PM_EV_GRP_OFFSET 1
@@ -1401,6 +1418,7 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
ret = remove_anno_list_by_saddr(msk, addr);
if (ret || force) {
spin_lock_bh(&msk->pm.lock);
+ msk->pm.add_addr_signaled -= ret;
mptcp_pm_remove_addr(msk, &list);
spin_unlock_bh(&msk->pm.lock);
}
@@ -1534,16 +1552,25 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
{
struct mptcp_rm_list alist = { .nr = 0 };
struct mptcp_pm_addr_entry *entry;
+ int anno_nr = 0;
list_for_each_entry(entry, rm_list, list) {
- if ((remove_anno_list_by_saddr(msk, &entry->addr) ||
- lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) &&
- alist.nr < MPTCP_RM_IDS_MAX)
- alist.ids[alist.nr++] = entry->addr.id;
+ if (alist.nr >= MPTCP_RM_IDS_MAX)
+ break;
+
+ /* only delete if either announced or matching a subflow */
+ if (remove_anno_list_by_saddr(msk, &entry->addr))
+ anno_nr++;
+ else if (!lookup_subflow_by_saddr(&msk->conn_list,
+ &entry->addr))
+ continue;
+
+ alist.ids[alist.nr++] = entry->addr.id;
}
if (alist.nr) {
spin_lock_bh(&msk->pm.lock);
+ msk->pm.add_addr_signaled -= anno_nr;
mptcp_pm_remove_addr(msk, &alist);
spin_unlock_bh(&msk->pm.lock);
}
@@ -1556,17 +1583,18 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
struct mptcp_pm_addr_entry *entry;
list_for_each_entry(entry, rm_list, list) {
- if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) &&
- slist.nr < MPTCP_RM_IDS_MAX)
+ if (slist.nr < MPTCP_RM_IDS_MAX &&
+ lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
slist.ids[slist.nr++] = entry->addr.id;
- if (remove_anno_list_by_saddr(msk, &entry->addr) &&
- alist.nr < MPTCP_RM_IDS_MAX)
+ if (alist.nr < MPTCP_RM_IDS_MAX &&
+ remove_anno_list_by_saddr(msk, &entry->addr))
alist.ids[alist.nr++] = entry->addr.id;
}
if (alist.nr) {
spin_lock_bh(&msk->pm.lock);
+ msk->pm.add_addr_signaled -= alist.nr;
mptcp_pm_remove_addr(msk, &alist);
spin_unlock_bh(&msk->pm.lock);
}
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index f0a4590506c6..8eaa9fbe3e34 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -165,6 +165,24 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true);
}
+bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
+ struct mptcp_addr_info *skc)
+{
+ struct mptcp_pm_addr_entry *entry;
+ bool backup = false;
+
+ spin_lock_bh(&msk->pm.lock);
+ list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
+ if (mptcp_addresses_equal(&entry->addr, skc, false)) {
+ backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+ break;
+ }
+ }
+ spin_unlock_bh(&msk->pm.lock);
+
+ return backup;
+}
+
int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
{
struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a26c2c840fd9..0d536b183a6c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -350,8 +350,10 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
skb_orphan(skb);
/* try to fetch required memory from subflow */
- if (!mptcp_rmem_schedule(sk, ssk, skb->truesize))
+ if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
goto drop;
+ }
has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
@@ -844,10 +846,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
sk_rbuf = ssk_rbuf;
/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
- if (__mptcp_rmem(sk) > sk_rbuf) {
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
+ if (__mptcp_rmem(sk) > sk_rbuf)
return;
- }
/* Wake-up the reader only for in-sequence data */
mptcp_data_lock(sk);
@@ -1422,13 +1422,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
}
mptcp_for_each_subflow(msk, subflow) {
+ bool backup = subflow->backup || subflow->request_bkup;
+
trace_mptcp_subflow_get_send(subflow);
ssk = mptcp_subflow_tcp_sock(subflow);
if (!mptcp_subflow_active(subflow))
continue;
tout = max(tout, mptcp_timeout_from_subflow(subflow));
- nr_active += !subflow->backup;
+ nr_active += !backup;
pace = subflow->avg_pacing_rate;
if (unlikely(!pace)) {
/* init pacing rate from socket */
@@ -1439,9 +1441,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
}
linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace);
- if (linger_time < send_info[subflow->backup].linger_time) {
- send_info[subflow->backup].ssk = ssk;
- send_info[subflow->backup].linger_time = linger_time;
+ if (linger_time < send_info[backup].linger_time) {
+ send_info[backup].ssk = ssk;
+ send_info[backup].linger_time = linger_time;
}
}
__mptcp_set_timeout(sk, tout);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index b11a4e50d52b..60c6b073d65f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -448,6 +448,7 @@ struct mptcp_subflow_request_sock {
u16 mp_capable : 1,
mp_join : 1,
backup : 1,
+ request_bkup : 1,
csum_reqd : 1,
allow_join_id0 : 1;
u8 local_id;
@@ -1108,6 +1109,9 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc);
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb);
int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
struct netlink_callback *cb);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 39e2cbdf3801..a21c712350c3 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -100,6 +100,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req)
return NULL;
}
subflow_req->local_id = local_id;
+ subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req);
return msk;
}
@@ -168,6 +169,9 @@ static int subflow_check_req(struct request_sock *req,
return 0;
} else if (opt_mp_join) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
+
+ if (mp_opt.backup)
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX);
}
if (opt_mp_capable && listener->request_mptcp) {
@@ -577,6 +581,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow->mp_join = 1;
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
+ if (subflow->backup)
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX);
+
if (subflow_use_different_dport(msk, sk)) {
pr_debug("synack inet_dport=%d %d",
ntohs(inet_sk(sk)->inet_dport),
@@ -614,6 +621,8 @@ static int subflow_chk_local_id(struct sock *sk)
return err;
subflow_set_local_id(subflow, err);
+ subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk);
+
return 0;
}
@@ -1221,14 +1230,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
- u32 incr;
+ struct tcp_sock *tp = tcp_sk(ssk);
+ u32 offset, incr, avail_len;
- incr = limit >= skb->len ? skb->len + fin : limit;
+ offset = tp->copied_seq - TCP_SKB_CB(skb)->seq;
+ if (WARN_ON_ONCE(offset > skb->len))
+ goto out;
- pr_debug("discarding=%d len=%d seq=%d", incr, skb->len,
- subflow->map_subflow_seq);
+ avail_len = skb->len - offset;
+ incr = limit >= avail_len ? avail_len + fin : limit;
+
+ pr_debug("discarding=%d len=%d offset=%d seq=%d", incr, skb->len,
+ offset, subflow->map_subflow_seq);
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
tcp_sk(ssk)->copied_seq += incr;
+
+out:
if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq))
sk_eat_skb(ssk, skb);
if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
@@ -2005,6 +2022,7 @@ static void subflow_ulp_clone(const struct request_sock *req,
new_ctx->fully_established = 1;
new_ctx->remote_key_valid = 1;
new_ctx->backup = subflow_req->backup;
+ new_ctx->request_bkup = subflow_req->request_bkup;
WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id);
new_ctx->token = subflow_req->token;
new_ctx->thmac = subflow_req->thmac;
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 113b907da0f7..3ba8e7e739b5 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -44,6 +44,8 @@ static DEFINE_MUTEX(zones_mutex);
struct zones_ht_key {
struct net *net;
u16 zone;
+ /* Note : pad[] must be the last field. */
+ u8 pad[];
};
struct tcf_ct_flow_table {
@@ -60,7 +62,7 @@ struct tcf_ct_flow_table {
static const struct rhashtable_params zones_params = {
.head_offset = offsetof(struct tcf_ct_flow_table, node),
.key_offset = offsetof(struct tcf_ct_flow_table, key),
- .key_len = sizeof_field(struct tcf_ct_flow_table, key),
+ .key_len = offsetof(struct zones_ht_key, pad),
.automatic_shrinking = true,
};
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 73a875573e7a..8e3093938cd2 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -3319,10 +3319,8 @@ int smc_create_clcsk(struct net *net, struct sock *sk, int family)
rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP,
&smc->clcsock);
- if (rc) {
- sk_common_release(sk);
+ if (rc)
return rc;
- }
/* smc_clcsock_release() does not wait smc->clcsock->sk's
* destruction; its sk_state might not be TCP_CLOSE after
@@ -3368,6 +3366,9 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol,
smc->clcsock = clcsock;
else
rc = smc_create_clcsk(net, sk, family);
+
+ if (rc)
+ sk_common_release(sk);
out:
return rc;
}
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index d99319d82205..64eeed82d43d 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -3178,8 +3178,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
struct ieee80211_mgmt *mgmt, size_t len,
gfp_t gfp)
{
- size_t min_hdr_len = offsetof(struct ieee80211_mgmt,
- u.probe_resp.variable);
+ size_t min_hdr_len;
struct ieee80211_ext *ext = NULL;
enum cfg80211_bss_frame_type ftype;
u16 beacon_interval;
@@ -3202,10 +3201,16 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
ext = (void *) mgmt;
- min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon);
if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
min_hdr_len = offsetof(struct ieee80211_ext,
u.s1g_short_beacon.variable);
+ else
+ min_hdr_len = offsetof(struct ieee80211_ext,
+ u.s1g_beacon.variable);
+ } else {
+ /* same for beacons */
+ min_hdr_len = offsetof(struct ieee80211_mgmt,
+ u.probe_resp.variable);
}
if (WARN_ON(len < min_hdr_len))
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index e419aa8c4a5a..d9d7bf8bb5c1 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -1045,6 +1045,7 @@ void cfg80211_connect_done(struct net_device *dev,
cfg80211_hold_bss(
bss_from_pub(params->links[link].bss));
ev->cr.links[link].bss = params->links[link].bss;
+ ev->cr.links[link].status = params->links[link].status;
if (params->links[link].addr) {
ev->cr.links[link].addr = next;
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index dd49c1d23a60..81d4757ecd4c 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -713,7 +713,7 @@ $(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp
# Make sure we are able to include and link libbpf against c++.
$(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
$(call msg,CXX,,$@)
- $(Q)$(CXX) $(CFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@
+ $(Q)$(CXX) $(subst -D_GNU_SOURCE=,,$(CFLAGS)) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@
# Benchmark runner
$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ)
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index bd8c75b620c2..797de47f8197 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -253,7 +253,7 @@ static void test_uretprobe_syscall_call(void)
struct uprobe_syscall_executed *skel;
int pid, status, err, go[2], c;
- if (ASSERT_OK(pipe(go), "pipe"))
+ if (!ASSERT_OK(pipe(go), "pipe"))
return;
skel = uprobe_syscall_executed__open_and_load();
diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index 931dbc36ca43..011508ca604b 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -19,6 +19,15 @@ def _rss_key_rand(length):
return [random.randint(0, 255) for _ in range(length)]
+def _rss_key_check(cfg, data=None, context=0):
+ if data is None:
+ data = get_rss(cfg, context=context)
+ if 'rss-hash-key' not in data:
+ return
+ non_zero = [x for x in data['rss-hash-key'] if x != 0]
+ ksft_eq(bool(non_zero), True, comment=f"RSS key is all zero {data['rss-hash-key']}")
+
+
def get_rss(cfg, context=0):
return ethtool(f"-x {cfg.ifname} context {context}", json=True)[0]
@@ -90,8 +99,9 @@ def _send_traffic_check(cfg, port, name, params):
def test_rss_key_indir(cfg):
"""Test basics like updating the main RSS key and indirection table."""
- if len(_get_rx_cnts(cfg)) < 2:
- KsftSkipEx("Device has only one queue (or doesn't support queue stats)")
+ qcnt = len(_get_rx_cnts(cfg))
+ if qcnt < 3:
+ KsftSkipEx("Device has fewer than 3 queues (or doesn't support queue stats)")
data = get_rss(cfg)
want_keys = ['rss-hash-key', 'rss-hash-function', 'rss-indirection-table']
@@ -101,6 +111,7 @@ def test_rss_key_indir(cfg):
if not data[k]:
raise KsftFailEx(f"ethtool results empty for '{k}': {data[k]}")
+ _rss_key_check(cfg, data=data)
key_len = len(data['rss-hash-key'])
# Set the key
@@ -110,9 +121,26 @@ def test_rss_key_indir(cfg):
data = get_rss(cfg)
ksft_eq(key, data['rss-hash-key'])
+ # Set the indirection table and the key together
+ key = _rss_key_rand(key_len)
+ ethtool(f"-X {cfg.ifname} equal 3 hkey " + _rss_key_str(key))
+ reset_indir = defer(ethtool, f"-X {cfg.ifname} default")
+
+ data = get_rss(cfg)
+ _rss_key_check(cfg, data=data)
+ ksft_eq(0, min(data['rss-indirection-table']))
+ ksft_eq(2, max(data['rss-indirection-table']))
+
+ # Reset indirection table and set the key
+ key = _rss_key_rand(key_len)
+ ethtool(f"-X {cfg.ifname} default hkey " + _rss_key_str(key))
+ data = get_rss(cfg)
+ _rss_key_check(cfg, data=data)
+ ksft_eq(0, min(data['rss-indirection-table']))
+ ksft_eq(qcnt - 1, max(data['rss-indirection-table']))
+
# Set the indirection table
ethtool(f"-X {cfg.ifname} equal 2")
- reset_indir = defer(ethtool, f"-X {cfg.ifname} default")
data = get_rss(cfg)
ksft_eq(0, min(data['rss-indirection-table']))
ksft_eq(1, max(data['rss-indirection-table']))
@@ -317,8 +345,11 @@ def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None):
ctx_cnt = i
break
+ _rss_key_check(cfg, context=ctx_id)
+
if not create_with_cfg:
ethtool(f"-X {cfg.ifname} context {ctx_id} {want_cfg}")
+ _rss_key_check(cfg, context=ctx_id)
# Sanity check the context we just created
data = get_rss(cfg, ctx_id)
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index d2043ec3bf6d..4209b9569039 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -1115,11 +1115,11 @@ again:
return 1;
}
- if (--cfg_repeat > 0) {
- if (cfg_input)
- close(fd);
+ if (cfg_input)
+ close(fd);
+
+ if (--cfg_repeat > 0)
goto again;
- }
return 0;
}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 108aeeb84ef1..4df48f1f14ab 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -661,7 +661,7 @@ pm_nl_check_endpoint()
done
if [ -z "${id}" ]; then
- test_fail "bad test - missing endpoint id"
+ fail_test "bad test - missing endpoint id"
return
fi
@@ -1634,6 +1634,8 @@ chk_prio_nr()
{
local mp_prio_nr_tx=$1
local mp_prio_nr_rx=$2
+ local mpj_syn=$3
+ local mpj_syn_ack=$4
local count
print_check "ptx"
@@ -1655,6 +1657,26 @@ chk_prio_nr()
else
print_ok
fi
+
+ print_check "syn backup"
+ count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinSynBackupRx")
+ if [ -z "$count" ]; then
+ print_skip
+ elif [ "$count" != "$mpj_syn" ]; then
+ fail_test "got $count JOIN[s] syn with Backup expected $mpj_syn"
+ else
+ print_ok
+ fi
+
+ print_check "synack backup"
+ count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckBackupRx")
+ if [ -z "$count" ]; then
+ print_skip
+ elif [ "$count" != "$mpj_syn_ack" ]; then
+ fail_test "got $count JOIN[s] synack with Backup expected $mpj_syn_ack"
+ else
+ print_ok
+ fi
}
chk_subflow_nr()
@@ -2612,33 +2634,46 @@ backup_tests()
sflags=nobackup speed=slow \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 1 1 1
- chk_prio_nr 0 1
+ chk_prio_nr 0 1 1 0
fi
# single address, backup
if reset "single address, backup" &&
continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
pm_nl_set_limits $ns1 0 1
+ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup
+ pm_nl_set_limits $ns2 1 1
+ sflags=nobackup speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 1 1 1
+ chk_add_nr 1 1
+ chk_prio_nr 1 0 0 1
+ fi
+
+ # single address, switch to backup
+ if reset "single address, switch to backup" &&
+ continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
+ pm_nl_set_limits $ns1 0 1
pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
pm_nl_set_limits $ns2 1 1
sflags=backup speed=slow \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 1 1 1
chk_add_nr 1 1
- chk_prio_nr 1 1
+ chk_prio_nr 1 1 0 0
fi
# single address with port, backup
if reset "single address with port, backup" &&
continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
pm_nl_set_limits $ns1 0 1
- pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100
+ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup port 10100
pm_nl_set_limits $ns2 1 1
- sflags=backup speed=slow \
+ sflags=nobackup speed=slow \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 1 1 1
chk_add_nr 1 1
- chk_prio_nr 1 1
+ chk_prio_nr 1 0 0 1
fi
if reset "mpc backup" &&
@@ -2647,17 +2682,26 @@ backup_tests()
speed=slow \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 0 0 0
- chk_prio_nr 0 1
+ chk_prio_nr 0 1 0 0
fi
if reset "mpc backup both sides" &&
continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then
- pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup
+ pm_nl_set_limits $ns1 0 2
+ pm_nl_set_limits $ns2 1 2
+ pm_nl_add_endpoint $ns1 10.0.1.1 flags signal,backup
pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup
+
+ # 10.0.2.2 (non-backup) -> 10.0.1.1 (backup)
+ pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
+ # 10.0.1.2 (backup) -> 10.0.2.1 (non-backup)
+ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+ ip -net "$ns2" route add 10.0.2.1 via 10.0.1.1 dev ns2eth1 # force this path
+
speed=slow \
run_tests $ns1 $ns2 10.0.1.1
- chk_join_nr 0 0 0
- chk_prio_nr 1 1
+ chk_join_nr 2 2 2
+ chk_prio_nr 1 1 1 1
fi
if reset "mpc switch to backup" &&
@@ -2666,7 +2710,7 @@ backup_tests()
sflags=backup speed=slow \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 0 0 0
- chk_prio_nr 0 1
+ chk_prio_nr 0 1 0 0
fi
if reset "mpc switch to backup both sides" &&
@@ -2676,7 +2720,7 @@ backup_tests()
sflags=backup speed=slow \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 0 0 0
- chk_prio_nr 1 1
+ chk_prio_nr 1 1 0 0
fi
}
@@ -3053,7 +3097,7 @@ fullmesh_tests()
addr_nr_ns2=1 sflags=backup,fullmesh speed=slow \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 2 2 2
- chk_prio_nr 0 1
+ chk_prio_nr 0 1 1 0
chk_rm_nr 0 1
fi
@@ -3066,7 +3110,7 @@ fullmesh_tests()
sflags=nobackup,nofullmesh speed=slow \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 2 2 2
- chk_prio_nr 0 1
+ chk_prio_nr 0 1 1 0
chk_rm_nr 0 1
fi
}
@@ -3318,7 +3362,7 @@ userspace_tests()
sflags=backup speed=slow \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 1 1 0
- chk_prio_nr 0 0
+ chk_prio_nr 0 0 0 0
fi
# userspace pm type prevents rm_addr
@@ -3526,6 +3570,35 @@ endpoint_tests()
chk_mptcp_info subflows 1 subflows 1
mptcp_lib_kill_wait $tests_pid
fi
+
+ # remove and re-add
+ if reset "delete re-add signal" &&
+ mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
+ pm_nl_set_limits $ns1 1 1
+ pm_nl_set_limits $ns2 1 1
+ pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal
+ test_linkfail=4 speed=20 \
+ run_tests $ns1 $ns2 10.0.1.1 &
+ local tests_pid=$!
+
+ wait_mpj $ns2
+ pm_nl_check_endpoint "creation" \
+ $ns1 10.0.2.1 id 1 flags signal
+ chk_subflow_nr "before delete" 2
+ chk_mptcp_info subflows 1 subflows 1
+
+ pm_nl_del_endpoint $ns1 1 10.0.2.1
+ sleep 0.5
+ chk_subflow_nr "after delete" 1
+ chk_mptcp_info subflows 0 subflows 0
+
+ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+ wait_mpj $ns2
+ chk_subflow_nr "after re-add" 2
+ chk_mptcp_info subflows 1 subflows 1
+ mptcp_lib_kill_wait $tests_pid
+ fi
+
}
# [$1: error message]