diff options
71 files changed, 606 insertions, 342 deletions
diff --git a/Documentation/networking/device_drivers/ethernet/pensando/ionic.rst b/Documentation/networking/device_drivers/ethernet/pensando/ionic.rst index 6ec7d686efab..05fe2b11bb18 100644 --- a/Documentation/networking/device_drivers/ethernet/pensando/ionic.rst +++ b/Documentation/networking/device_drivers/ethernet/pensando/ionic.rst @@ -99,6 +99,12 @@ Minimal SR-IOV support is currently offered and can be enabled by setting the sysfs 'sriov_numvfs' value, if supported by your particular firmware configuration. +XDP +--- + +Support for XDP includes the basics, plus Jumbo frames, Redirect and +ndo_xmit. There is no current support for zero-copy sockets or HW offload. + Statistics ========== @@ -138,6 +144,12 @@ Driver port specific:: rx_csum_none: 0 rx_csum_complete: 3 rx_csum_error: 0 + xdp_drop: 0 + xdp_aborted: 0 + xdp_pass: 0 + xdp_tx: 0 + xdp_redirect: 0 + xdp_frames: 0 Driver queue specific:: @@ -149,9 +161,12 @@ Driver queue specific:: tx_0_frags: 0 tx_0_tso: 0 tx_0_tso_bytes: 0 + tx_0_hwstamp_valid: 0 + tx_0_hwstamp_invalid: 0 tx_0_csum_none: 3 tx_0_csum: 0 tx_0_vlan_inserted: 0 + tx_0_xdp_frames: 0 rx_0_pkts: 2 rx_0_bytes: 120 rx_0_dma_map_err: 0 @@ -159,8 +174,15 @@ Driver queue specific:: rx_0_csum_none: 0 rx_0_csum_complete: 0 rx_0_csum_error: 0 + rx_0_hwstamp_valid: 0 + rx_0_hwstamp_invalid: 0 rx_0_dropped: 0 rx_0_vlan_stripped: 0 + rx_0_xdp_drop: 0 + rx_0_xdp_aborted: 0 + rx_0_xdp_pass: 0 + rx_0_xdp_tx: 0 + rx_0_xdp_redirect: 0 Firmware port specific:: diff --git a/Documentation/networking/multi-pf-netdev.rst b/Documentation/networking/multi-pf-netdev.rst index be8e4bcadf11..268819225866 100644 --- a/Documentation/networking/multi-pf-netdev.rst +++ b/Documentation/networking/multi-pf-netdev.rst @@ -87,35 +87,35 @@ all using the same instance under "priv->mdev". Observability ============= -The relation between PF, irq, napi, and queue can be observed via netlink spec: +The relation between PF, irq, napi, and queue can be observed via netlink spec:: -$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump queue-get --json='{"ifindex": 13}' -[{'id': 0, 'ifindex': 13, 'napi-id': 539, 'type': 'rx'}, - {'id': 1, 'ifindex': 13, 'napi-id': 540, 'type': 'rx'}, - {'id': 2, 'ifindex': 13, 'napi-id': 541, 'type': 'rx'}, - {'id': 3, 'ifindex': 13, 'napi-id': 542, 'type': 'rx'}, - {'id': 4, 'ifindex': 13, 'napi-id': 543, 'type': 'rx'}, - {'id': 0, 'ifindex': 13, 'napi-id': 539, 'type': 'tx'}, - {'id': 1, 'ifindex': 13, 'napi-id': 540, 'type': 'tx'}, - {'id': 2, 'ifindex': 13, 'napi-id': 541, 'type': 'tx'}, - {'id': 3, 'ifindex': 13, 'napi-id': 542, 'type': 'tx'}, - {'id': 4, 'ifindex': 13, 'napi-id': 543, 'type': 'tx'}] + $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump queue-get --json='{"ifindex": 13}' + [{'id': 0, 'ifindex': 13, 'napi-id': 539, 'type': 'rx'}, + {'id': 1, 'ifindex': 13, 'napi-id': 540, 'type': 'rx'}, + {'id': 2, 'ifindex': 13, 'napi-id': 541, 'type': 'rx'}, + {'id': 3, 'ifindex': 13, 'napi-id': 542, 'type': 'rx'}, + {'id': 4, 'ifindex': 13, 'napi-id': 543, 'type': 'rx'}, + {'id': 0, 'ifindex': 13, 'napi-id': 539, 'type': 'tx'}, + {'id': 1, 'ifindex': 13, 'napi-id': 540, 'type': 'tx'}, + {'id': 2, 'ifindex': 13, 'napi-id': 541, 'type': 'tx'}, + {'id': 3, 'ifindex': 13, 'napi-id': 542, 'type': 'tx'}, + {'id': 4, 'ifindex': 13, 'napi-id': 543, 'type': 'tx'}] -$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump napi-get --json='{"ifindex": 13}' -[{'id': 543, 'ifindex': 13, 'irq': 42}, - {'id': 542, 'ifindex': 13, 'irq': 41}, - {'id': 541, 'ifindex': 13, 'irq': 40}, - {'id': 540, 'ifindex': 13, 'irq': 39}, - {'id': 539, 'ifindex': 13, 'irq': 36}] + $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump napi-get --json='{"ifindex": 13}' + [{'id': 543, 'ifindex': 13, 'irq': 42}, + {'id': 542, 'ifindex': 13, 'irq': 41}, + {'id': 541, 'ifindex': 13, 'irq': 40}, + {'id': 540, 'ifindex': 13, 'irq': 39}, + {'id': 539, 'ifindex': 13, 'irq': 36}] -Here you can clearly observe our channels distribution policy: +Here you can clearly observe our channels distribution policy:: -$ ls /proc/irq/{36,39,40,41,42}/mlx5* -d -1 -/proc/irq/36/mlx5_comp1@pci:0000:08:00.0 -/proc/irq/39/mlx5_comp1@pci:0000:09:00.0 -/proc/irq/40/mlx5_comp2@pci:0000:08:00.0 -/proc/irq/41/mlx5_comp2@pci:0000:09:00.0 -/proc/irq/42/mlx5_comp3@pci:0000:08:00.0 + $ ls /proc/irq/{36,39,40,41,42}/mlx5* -d -1 + /proc/irq/36/mlx5_comp1@pci:0000:08:00.0 + /proc/irq/39/mlx5_comp1@pci:0000:09:00.0 + /proc/irq/40/mlx5_comp2@pci:0000:08:00.0 + /proc/irq/41/mlx5_comp2@pci:0000:09:00.0 + /proc/irq/42/mlx5_comp3@pci:0000:08:00.0 Steering ======== diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst index dceb49d56a91..70c4fb9d4e5c 100644 --- a/Documentation/networking/net_cachelines/net_device.rst +++ b/Documentation/networking/net_cachelines/net_device.rst @@ -13,7 +13,7 @@ struct_dev_ifalias* ifalias unsigned_long mem_end unsigned_long mem_start unsigned_long base_addr -unsigned_long state +unsigned_long state read_mostly read_mostly netif_running(dev) struct_list_head dev_list struct_list_head napi_list struct_list_head unreg_list diff --git a/MAINTAINERS b/MAINTAINERS index 5b251bcc91f0..f736af98d7b5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15237,7 +15237,6 @@ F: drivers/net/ethernet/neterion/ NETFILTER M: Pablo Neira Ayuso <pablo@netfilter.org> M: Jozsef Kadlecsik <kadlec@netfilter.org> -M: Florian Westphal <fw@strlen.de> L: netfilter-devel@vger.kernel.org L: coreteam@netfilter.org S: Maintained diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index f81b598147b3..7b5028b67cd5 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -370,8 +370,8 @@ static const struct kvaser_pciefd_irq_mask kvaser_pciefd_sf2_irq_mask = { static const struct kvaser_pciefd_irq_mask kvaser_pciefd_xilinx_irq_mask = { .kcan_rx0 = BIT(4), - .kcan_tx = { BIT(16), BIT(17), BIT(18), BIT(19) }, - .all = GENMASK(19, 16) | BIT(4), + .kcan_tx = { BIT(16), BIT(17), BIT(18), BIT(19), BIT(20), BIT(21), BIT(22), BIT(23) }, + .all = GENMASK(23, 16) | BIT(4), }; static const struct kvaser_pciefd_dev_ops kvaser_pciefd_altera_dev_ops = { diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 678b51f9cea6..767f66c37f6b 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -950,20 +950,56 @@ static void mt7530_setup_port5(struct dsa_switch *ds, phy_interface_t interface) mutex_unlock(&priv->reg_mutex); } +/* On page 205, section "8.6.3 Frame filtering" of the active standard, IEEE Std + * 802.1Q™-2022, it is stated that frames with 01:80:C2:00:00:00-0F as MAC DA + * must only be propagated to C-VLAN and MAC Bridge components. That means + * VLAN-aware and VLAN-unaware bridges. On the switch designs with CPU ports, + * these frames are supposed to be processed by the CPU (software). So we make + * the switch only forward them to the CPU port. And if received from a CPU + * port, forward to a single port. The software is responsible of making the + * switch conform to the latter by setting a single port as destination port on + * the special tag. + * + * This switch intellectual property cannot conform to this part of the standard + * fully. Whilst the REV_UN frame tag covers the remaining :04-0D and :0F MAC + * DAs, it also includes :22-FF which the scope of propagation is not supposed + * to be restricted for these MAC DAs. + */ static void mt753x_trap_frames(struct mt7530_priv *priv) { - /* Trap BPDUs to the CPU port(s) */ - mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK, + /* Trap 802.1X PAE frames and BPDUs to the CPU port(s) and egress them + * VLAN-untagged. + */ + mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_EG_TAG_MASK | + MT753X_PAE_PORT_FW_MASK | MT753X_BPDU_EG_TAG_MASK | + MT753X_BPDU_PORT_FW_MASK, + MT753X_PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY) | + MT753X_BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | MT753X_BPDU_CPU_ONLY); - /* Trap 802.1X PAE frames to the CPU port(s) */ - mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_PORT_FW_MASK, - MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY)); + /* Trap frames with :01 and :02 MAC DAs to the CPU port(s) and egress + * them VLAN-untagged. + */ + mt7530_rmw(priv, MT753X_RGAC1, MT753X_R02_EG_TAG_MASK | + MT753X_R02_PORT_FW_MASK | MT753X_R01_EG_TAG_MASK | + MT753X_R01_PORT_FW_MASK, + MT753X_R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_R02_PORT_FW(MT753X_BPDU_CPU_ONLY) | + MT753X_R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_BPDU_CPU_ONLY); - /* Trap LLDP frames with :0E MAC DA to the CPU port(s) */ - mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_PORT_FW_MASK, - MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY)); + /* Trap frames with :03 and :0E MAC DAs to the CPU port(s) and egress + * them VLAN-untagged. + */ + mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_EG_TAG_MASK | + MT753X_R0E_PORT_FW_MASK | MT753X_R03_EG_TAG_MASK | + MT753X_R03_PORT_FW_MASK, + MT753X_R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY) | + MT753X_R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_BPDU_CPU_ONLY); } static void @@ -2192,22 +2228,16 @@ mt7530_setup(struct dsa_switch *ds) } } - /* Disable LEDs before reset to prevent the MT7530 sampling a - * potentially incorrect HT_XTAL_FSEL value. - */ - mt7530_write(priv, MT7530_LED_EN, 0); - usleep_range(1000, 1100); - /* Reset whole chip through gpio pin or memory-mapped registers for * different type of hardware */ if (priv->mcm) { reset_control_assert(priv->rstc); - usleep_range(1000, 1100); + usleep_range(5000, 5100); reset_control_deassert(priv->rstc); } else { gpiod_set_value_cansleep(priv->reset, 0); - usleep_range(1000, 1100); + usleep_range(5000, 5100); gpiod_set_value_cansleep(priv->reset, 1); } @@ -2420,11 +2450,11 @@ mt7531_setup(struct dsa_switch *ds) */ if (priv->mcm) { reset_control_assert(priv->rstc); - usleep_range(1000, 1100); + usleep_range(5000, 5100); reset_control_deassert(priv->rstc); } else { gpiod_set_value_cansleep(priv->reset, 0); - usleep_range(1000, 1100); + usleep_range(5000, 5100); gpiod_set_value_cansleep(priv->reset, 1); } diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index a71166e0a7fc..d17b318e6ee4 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -65,14 +65,33 @@ enum mt753x_id { /* Registers for BPDU and PAE frame control*/ #define MT753X_BPC 0x24 -#define MT753X_BPDU_PORT_FW_MASK GENMASK(2, 0) +#define MT753X_PAE_EG_TAG_MASK GENMASK(24, 22) +#define MT753X_PAE_EG_TAG(x) FIELD_PREP(MT753X_PAE_EG_TAG_MASK, x) #define MT753X_PAE_PORT_FW_MASK GENMASK(18, 16) #define MT753X_PAE_PORT_FW(x) FIELD_PREP(MT753X_PAE_PORT_FW_MASK, x) +#define MT753X_BPDU_EG_TAG_MASK GENMASK(8, 6) +#define MT753X_BPDU_EG_TAG(x) FIELD_PREP(MT753X_BPDU_EG_TAG_MASK, x) +#define MT753X_BPDU_PORT_FW_MASK GENMASK(2, 0) + +/* Register for :01 and :02 MAC DA frame control */ +#define MT753X_RGAC1 0x28 +#define MT753X_R02_EG_TAG_MASK GENMASK(24, 22) +#define MT753X_R02_EG_TAG(x) FIELD_PREP(MT753X_R02_EG_TAG_MASK, x) +#define MT753X_R02_PORT_FW_MASK GENMASK(18, 16) +#define MT753X_R02_PORT_FW(x) FIELD_PREP(MT753X_R02_PORT_FW_MASK, x) +#define MT753X_R01_EG_TAG_MASK GENMASK(8, 6) +#define MT753X_R01_EG_TAG(x) FIELD_PREP(MT753X_R01_EG_TAG_MASK, x) +#define MT753X_R01_PORT_FW_MASK GENMASK(2, 0) /* Register for :03 and :0E MAC DA frame control */ #define MT753X_RGAC2 0x2c +#define MT753X_R0E_EG_TAG_MASK GENMASK(24, 22) +#define MT753X_R0E_EG_TAG(x) FIELD_PREP(MT753X_R0E_EG_TAG_MASK, x) #define MT753X_R0E_PORT_FW_MASK GENMASK(18, 16) #define MT753X_R0E_PORT_FW(x) FIELD_PREP(MT753X_R0E_PORT_FW_MASK, x) +#define MT753X_R03_EG_TAG_MASK GENMASK(8, 6) +#define MT753X_R03_EG_TAG(x) FIELD_PREP(MT753X_R03_EG_TAG_MASK, x) +#define MT753X_R03_PORT_FW_MASK GENMASK(2, 0) enum mt753x_bpdu_port_fw { MT753X_BPDU_FOLLOW_MFC, @@ -253,6 +272,7 @@ enum mt7530_port_mode { enum mt7530_vlan_port_eg_tag { MT7530_VLAN_EG_DISABLED = 0, MT7530_VLAN_EG_CONSISTENT = 1, + MT7530_VLAN_EG_UNTAGGED = 4, }; enum mt7530_vlan_port_attr { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index d8b1824c334d..0bc1367fd649 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -1002,9 +1002,6 @@ static inline void bnx2x_set_fw_mac_addr(__le16 *fw_hi, __le16 *fw_mid, static inline void bnx2x_free_rx_mem_pool(struct bnx2x *bp, struct bnx2x_alloc_pool *pool) { - if (!pool->page) - return; - put_page(pool->page); pool->page = NULL; @@ -1015,6 +1012,9 @@ static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp, { int i; + if (!fp->page_pool.page) + return; + if (fp->mode == TPA_MODE_DISABLED) return; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 6c70c8498690..3c0f55b3e48e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -1338,7 +1338,7 @@ static irqreturn_t cgx_fwi_event_handler(int irq, void *data) /* Release thread waiting for completion */ lmac->cmd_pend = false; - wake_up_interruptible(&lmac->wq_cmd_cmplt); + wake_up(&lmac->wq_cmd_cmplt); break; case CGX_EVT_ASYNC: if (cgx_event_is_linkevent(event)) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c index b92264d0a77e..1e5aa5397504 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c @@ -214,11 +214,12 @@ int otx2_mbox_busy_poll_for_rsp(struct otx2_mbox *mbox, int devid) } EXPORT_SYMBOL(otx2_mbox_busy_poll_for_rsp); -void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid) +static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data) { struct otx2_mbox_dev *mdev = &mbox->dev[devid]; struct mbox_hdr *tx_hdr, *rx_hdr; void *hw_mbase = mdev->hwbase; + u64 intr_val; tx_hdr = hw_mbase + mbox->tx_start; rx_hdr = hw_mbase + mbox->rx_start; @@ -254,14 +255,52 @@ void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid) spin_unlock(&mdev->mbox_lock); + /* Check if interrupt pending */ + intr_val = readq((void __iomem *)mbox->reg_base + + (mbox->trigger | (devid << mbox->tr_shift))); + + intr_val |= data; /* The interrupt should be fired after num_msgs is written * to the shared memory */ - writeq(1, (void __iomem *)mbox->reg_base + + writeq(intr_val, (void __iomem *)mbox->reg_base + (mbox->trigger | (devid << mbox->tr_shift))); } + +void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid) +{ + otx2_mbox_msg_send_data(mbox, devid, MBOX_DOWN_MSG); +} EXPORT_SYMBOL(otx2_mbox_msg_send); +void otx2_mbox_msg_send_up(struct otx2_mbox *mbox, int devid) +{ + otx2_mbox_msg_send_data(mbox, devid, MBOX_UP_MSG); +} +EXPORT_SYMBOL(otx2_mbox_msg_send_up); + +bool otx2_mbox_wait_for_zero(struct otx2_mbox *mbox, int devid) +{ + u64 data; + + data = readq((void __iomem *)mbox->reg_base + + (mbox->trigger | (devid << mbox->tr_shift))); + + /* If data is non-zero wait for ~1ms and return to caller + * whether data has changed to zero or not after the wait. + */ + if (!data) + return true; + + usleep_range(950, 1000); + + data = readq((void __iomem *)mbox->reg_base + + (mbox->trigger | (devid << mbox->tr_shift))); + + return data == 0; +} +EXPORT_SYMBOL(otx2_mbox_wait_for_zero); + struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid, int size, int size_rsp) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 61ab7f66f053..eb2a20b5a0d0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -16,6 +16,9 @@ #define MBOX_SIZE SZ_64K +#define MBOX_DOWN_MSG 1 +#define MBOX_UP_MSG 2 + /* AF/PF: PF initiated, PF/VF VF initiated */ #define MBOX_DOWN_RX_START 0 #define MBOX_DOWN_RX_SIZE (46 * SZ_1K) @@ -101,6 +104,7 @@ int otx2_mbox_regions_init(struct otx2_mbox *mbox, void __force **hwbase, struct pci_dev *pdev, void __force *reg_base, int direction, int ndevs, unsigned long *bmap); void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid); +void otx2_mbox_msg_send_up(struct otx2_mbox *mbox, int devid); int otx2_mbox_wait_for_rsp(struct otx2_mbox *mbox, int devid); int otx2_mbox_busy_poll_for_rsp(struct otx2_mbox *mbox, int devid); struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid, @@ -118,6 +122,8 @@ static inline struct mbox_msghdr *otx2_mbox_alloc_msg(struct otx2_mbox *mbox, return otx2_mbox_alloc_msg_rsp(mbox, devid, size, 0); } +bool otx2_mbox_wait_for_zero(struct otx2_mbox *mbox, int devid); + /* Mailbox message types */ #define MBOX_MSG_MASK 0xFFFF #define MBOX_MSG_INVALID 0xFFFE diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c index dfd23580e3b8..d39d86e694cc 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c @@ -121,13 +121,17 @@ int mcs_add_intr_wq_entry(struct mcs *mcs, struct mcs_intr_event *event) static int mcs_notify_pfvf(struct mcs_intr_event *event, struct rvu *rvu) { struct mcs_intr_info *req; - int err, pf; + int pf; pf = rvu_get_pf(event->pcifunc); + mutex_lock(&rvu->mbox_lock); + req = otx2_mbox_alloc_msg_mcs_intr_notify(rvu, pf); - if (!req) + if (!req) { + mutex_unlock(&rvu->mbox_lock); return -ENOMEM; + } req->mcs_id = event->mcs_id; req->intr_mask = event->intr_mask; @@ -135,10 +139,11 @@ static int mcs_notify_pfvf(struct mcs_intr_event *event, struct rvu *rvu) req->hdr.pcifunc = event->pcifunc; req->lmac_id = event->lmac_id; - otx2_mbox_msg_send(&rvu->afpf_wq_info.mbox_up, pf); - err = otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pf); - if (err) - dev_warn(rvu->dev, "MCS notification to pf %d failed\n", pf); + otx2_mbox_wait_for_zero(&rvu->afpf_wq_info.mbox_up, pf); + + otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pf); + + mutex_unlock(&rvu->mbox_lock); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 07d4859de53a..ff78251f92d4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -2119,7 +2119,7 @@ bad_message: } } -static void __rvu_mbox_handler(struct rvu_work *mwork, int type) +static void __rvu_mbox_handler(struct rvu_work *mwork, int type, bool poll) { struct rvu *rvu = mwork->rvu; int offset, err, id, devid; @@ -2186,6 +2186,9 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type) } mw->mbox_wrk[devid].num_msgs = 0; + if (poll) + otx2_mbox_wait_for_zero(mbox, devid); + /* Send mbox responses to VF/PF */ otx2_mbox_msg_send(mbox, devid); } @@ -2193,15 +2196,18 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type) static inline void rvu_afpf_mbox_handler(struct work_struct *work) { struct rvu_work *mwork = container_of(work, struct rvu_work, work); + struct rvu *rvu = mwork->rvu; - __rvu_mbox_handler(mwork, TYPE_AFPF); + mutex_lock(&rvu->mbox_lock); + __rvu_mbox_handler(mwork, TYPE_AFPF, true); + mutex_unlock(&rvu->mbox_lock); } static inline void rvu_afvf_mbox_handler(struct work_struct *work) { struct rvu_work *mwork = container_of(work, struct rvu_work, work); - __rvu_mbox_handler(mwork, TYPE_AFVF); + __rvu_mbox_handler(mwork, TYPE_AFVF, false); } static void __rvu_mbox_up_handler(struct rvu_work *mwork, int type) @@ -2376,6 +2382,8 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, } } + mutex_init(&rvu->mbox_lock); + mbox_regions = kcalloc(num, sizeof(void *), GFP_KERNEL); if (!mbox_regions) { err = -ENOMEM; @@ -2525,10 +2533,9 @@ static void rvu_queue_work(struct mbox_wq_info *mw, int first, } } -static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq) +static irqreturn_t rvu_mbox_pf_intr_handler(int irq, void *rvu_irq) { struct rvu *rvu = (struct rvu *)rvu_irq; - int vfs = rvu->vfs; u64 intr; intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT); @@ -2542,6 +2549,18 @@ static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq) rvu_queue_work(&rvu->afpf_wq_info, 0, rvu->hw->total_pfs, intr); + return IRQ_HANDLED; +} + +static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq) +{ + struct rvu *rvu = (struct rvu *)rvu_irq; + int vfs = rvu->vfs; + u64 intr; + + /* Sync with mbox memory region */ + rmb(); + /* Handle VF interrupts */ if (vfs > 64) { intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(1)); @@ -2886,7 +2905,7 @@ static int rvu_register_interrupts(struct rvu *rvu) /* Register mailbox interrupt handler */ sprintf(&rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], "RVUAF Mbox"); ret = request_irq(pci_irq_vector(rvu->pdev, RVU_AF_INT_VEC_MBOX), - rvu_mbox_intr_handler, 0, + rvu_mbox_pf_intr_handler, 0, &rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], rvu); if (ret) { dev_err(rvu->dev, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index f390525a6217..35834687e40f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -591,6 +591,8 @@ struct rvu { spinlock_t mcs_intrq_lock; /* CPT interrupt lock */ spinlock_t cpt_intr_lock; + + struct mutex mbox_lock; /* Serialize mbox up and down msgs */ }; static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 38acdc7a73bb..72e060cf6b61 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -232,7 +232,7 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu) struct cgx_link_user_info *linfo; struct cgx_link_info_msg *msg; unsigned long pfmap; - int err, pfid; + int pfid; linfo = &event->link_uinfo; pfmap = cgxlmac_to_pfmap(rvu, event->cgx_id, event->lmac_id); @@ -255,16 +255,22 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu) continue; } + mutex_lock(&rvu->mbox_lock); + /* Send mbox message to PF */ msg = otx2_mbox_alloc_msg_cgx_link_event(rvu, pfid); - if (!msg) + if (!msg) { + mutex_unlock(&rvu->mbox_lock); continue; + } + msg->link_info = *linfo; - otx2_mbox_msg_send(&rvu->afpf_wq_info.mbox_up, pfid); - err = otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pfid); - if (err) - dev_warn(rvu->dev, "notification to pf %d failed\n", - pfid); + + otx2_mbox_wait_for_zero(&rvu->afpf_wq_info.mbox_up, pfid); + + otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pfid); + + mutex_unlock(&rvu->mbox_lock); } while (pfmap); } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 02d0b707aea5..a85ac039d779 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1592,7 +1592,7 @@ int otx2_detach_resources(struct mbox *mbox) detach->partial = false; /* Send detach request to AF */ - otx2_mbox_msg_send(&mbox->mbox, 0); + otx2_sync_mbox_msg(mbox); mutex_unlock(&mbox->lock); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 06910307085e..7e16a341ec58 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -815,7 +815,7 @@ static inline int otx2_sync_mbox_up_msg(struct mbox *mbox, int devid) if (!otx2_mbox_nonempty(&mbox->mbox_up, devid)) return 0; - otx2_mbox_msg_send(&mbox->mbox_up, devid); + otx2_mbox_msg_send_up(&mbox->mbox_up, devid); err = otx2_mbox_wait_for_rsp(&mbox->mbox_up, devid); if (err) return err; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index e5fe67e73865..b40bd0e46751 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -292,8 +292,8 @@ static int otx2_pf_flr_init(struct otx2_nic *pf, int num_vfs) return 0; } -static void otx2_queue_work(struct mbox *mw, struct workqueue_struct *mbox_wq, - int first, int mdevs, u64 intr, int type) +static void otx2_queue_vf_work(struct mbox *mw, struct workqueue_struct *mbox_wq, + int first, int mdevs, u64 intr) { struct otx2_mbox_dev *mdev; struct otx2_mbox *mbox; @@ -307,40 +307,26 @@ static void otx2_queue_work(struct mbox *mw, struct workqueue_struct *mbox_wq, mbox = &mw->mbox; mdev = &mbox->dev[i]; - if (type == TYPE_PFAF) - otx2_sync_mbox_bbuf(mbox, i); hdr = mdev->mbase + mbox->rx_start; /* The hdr->num_msgs is set to zero immediately in the interrupt - * handler to ensure that it holds a correct value next time - * when the interrupt handler is called. - * pf->mbox.num_msgs holds the data for use in pfaf_mbox_handler - * pf>mbox.up_num_msgs holds the data for use in - * pfaf_mbox_up_handler. + * handler to ensure that it holds a correct value next time + * when the interrupt handler is called. pf->mw[i].num_msgs + * holds the data for use in otx2_pfvf_mbox_handler and + * pf->mw[i].up_num_msgs holds the data for use in + * otx2_pfvf_mbox_up_handler. */ if (hdr->num_msgs) { mw[i].num_msgs = hdr->num_msgs; hdr->num_msgs = 0; - if (type == TYPE_PFAF) - memset(mbox->hwbase + mbox->rx_start, 0, - ALIGN(sizeof(struct mbox_hdr), - sizeof(u64))); - queue_work(mbox_wq, &mw[i].mbox_wrk); } mbox = &mw->mbox_up; mdev = &mbox->dev[i]; - if (type == TYPE_PFAF) - otx2_sync_mbox_bbuf(mbox, i); hdr = mdev->mbase + mbox->rx_start; if (hdr->num_msgs) { mw[i].up_num_msgs = hdr->num_msgs; hdr->num_msgs = 0; - if (type == TYPE_PFAF) - memset(mbox->hwbase + mbox->rx_start, 0, - ALIGN(sizeof(struct mbox_hdr), - sizeof(u64))); - queue_work(mbox_wq, &mw[i].mbox_up_wrk); } } @@ -356,8 +342,10 @@ static void otx2_forward_msg_pfvf(struct otx2_mbox_dev *mdev, /* Msgs are already copied, trigger VF's mbox irq */ smp_wmb(); + otx2_mbox_wait_for_zero(pfvf_mbox, devid); + offset = pfvf_mbox->trigger | (devid << pfvf_mbox->tr_shift); - writeq(1, (void __iomem *)pfvf_mbox->reg_base + offset); + writeq(MBOX_DOWN_MSG, (void __iomem *)pfvf_mbox->reg_base + offset); /* Restore VF's mbox bounce buffer region address */ src_mdev->mbase = bbuf_base; @@ -547,7 +535,7 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work) end: offset = mbox->rx_start + msg->next_msgoff; if (mdev->msgs_acked == (vf_mbox->up_num_msgs - 1)) - __otx2_mbox_reset(mbox, 0); + __otx2_mbox_reset(mbox, vf_idx); mdev->msgs_acked++; } } @@ -564,8 +552,7 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq) if (vfs > 64) { intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(1)); otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(1), intr); - otx2_queue_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr, - TYPE_PFVF); + otx2_queue_vf_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr); if (intr) trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr); vfs = 64; @@ -574,7 +561,7 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq) intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(0)); otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(0), intr); - otx2_queue_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr, TYPE_PFVF); + otx2_queue_vf_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr); if (intr) trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr); @@ -597,8 +584,9 @@ static int otx2_pfvf_mbox_init(struct otx2_nic *pf, int numvfs) if (!pf->mbox_pfvf) return -ENOMEM; - pf->mbox_pfvf_wq = alloc_ordered_workqueue("otx2_pfvf_mailbox", - WQ_HIGHPRI | WQ_MEM_RECLAIM); + pf->mbox_pfvf_wq = alloc_workqueue("otx2_pfvf_mailbox", + WQ_UNBOUND | WQ_HIGHPRI | + WQ_MEM_RECLAIM, 0); if (!pf->mbox_pfvf_wq) return -ENOMEM; @@ -821,20 +809,22 @@ static void otx2_pfaf_mbox_handler(struct work_struct *work) struct mbox *af_mbox; struct otx2_nic *pf; int offset, id; + u16 num_msgs; af_mbox = container_of(work, struct mbox, mbox_wrk); mbox = &af_mbox->mbox; mdev = &mbox->dev[0]; rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + num_msgs = rsp_hdr->num_msgs; offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN); pf = af_mbox->pfvf; - for (id = 0; id < af_mbox->num_msgs; id++) { + for (id = 0; id < num_msgs; id++) { msg = (struct mbox_msghdr *)(mdev->mbase + offset); otx2_process_pfaf_mbox_msg(pf, msg); offset = mbox->rx_start + msg->next_msgoff; - if (mdev->msgs_acked == (af_mbox->num_msgs - 1)) + if (mdev->msgs_acked == (num_msgs - 1)) __otx2_mbox_reset(mbox, 0); mdev->msgs_acked++; } @@ -945,12 +935,14 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work) int offset, id, devid = 0; struct mbox_hdr *rsp_hdr; struct mbox_msghdr *msg; + u16 num_msgs; rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + num_msgs = rsp_hdr->num_msgs; offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN); - for (id = 0; id < af_mbox->up_num_msgs; id++) { + for (id = 0; id < num_msgs; id++) { msg = (struct mbox_msghdr *)(mdev->mbase + offset); devid = msg->pcifunc & RVU_PFVF_FUNC_MASK; @@ -959,10 +951,11 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work) otx2_process_mbox_msg_up(pf, msg); offset = mbox->rx_start + msg->next_msgoff; } - if (devid) { + /* Forward to VF iff VFs are really present */ + if (devid && pci_num_vf(pf->pdev)) { otx2_forward_vf_mbox_msgs(pf, &pf->mbox.mbox_up, MBOX_DIR_PFVF_UP, devid - 1, - af_mbox->up_num_msgs); + num_msgs); return; } @@ -972,16 +965,49 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work) static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq) { struct otx2_nic *pf = (struct otx2_nic *)pf_irq; - struct mbox *mbox; + struct mbox *mw = &pf->mbox; + struct otx2_mbox_dev *mdev; + struct otx2_mbox *mbox; + struct mbox_hdr *hdr; + u64 mbox_data; /* Clear the IRQ */ otx2_write64(pf, RVU_PF_INT, BIT_ULL(0)); - mbox = &pf->mbox; - trace_otx2_msg_interrupt(mbox->mbox.pdev, "AF to PF", BIT_ULL(0)); + mbox_data = otx2_read64(pf, RVU_PF_PFAF_MBOX0); + + if (mbox_data & MBOX_UP_MSG) { + mbox_data &= ~MBOX_UP_MSG; + otx2_write64(pf, RVU_PF_PFAF_MBOX0, mbox_data); + + mbox = &mw->mbox_up; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); + + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(pf->mbox_wq, &mw->mbox_up_wrk); + + trace_otx2_msg_interrupt(pf->pdev, "UP message from AF to PF", + BIT_ULL(0)); + } + + if (mbox_data & MBOX_DOWN_MSG) { + mbox_data &= ~MBOX_DOWN_MSG; + otx2_write64(pf, RVU_PF_PFAF_MBOX0, mbox_data); + + mbox = &mw->mbox; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); + + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(pf->mbox_wq, &mw->mbox_wrk); - otx2_queue_work(mbox, pf->mbox_wq, 0, 1, 1, TYPE_PFAF); + trace_otx2_msg_interrupt(pf->pdev, "DOWN reply from AF to PF", + BIT_ULL(0)); + } return IRQ_HANDLED; } @@ -3087,6 +3113,7 @@ static void otx2_vf_link_event_task(struct work_struct *work) struct otx2_vf_config *config; struct cgx_link_info_msg *req; struct mbox_msghdr *msghdr; + struct delayed_work *dwork; struct otx2_nic *pf; int vf_idx; @@ -3095,10 +3122,24 @@ static void otx2_vf_link_event_task(struct work_struct *work) vf_idx = config - config->pf->vf_configs; pf = config->pf; + if (config->intf_down) + return; + + mutex_lock(&pf->mbox.lock); + + dwork = &config->link_event_work; + + if (!otx2_mbox_wait_for_zero(&pf->mbox_pfvf[0].mbox_up, vf_idx)) { + schedule_delayed_work(dwork, msecs_to_jiffies(100)); + mutex_unlock(&pf->mbox.lock); + return; + } + msghdr = otx2_mbox_alloc_msg_rsp(&pf->mbox_pfvf[0].mbox_up, vf_idx, sizeof(*req), sizeof(struct msg_rsp)); if (!msghdr) { dev_err(pf->dev, "Failed to create VF%d link event\n", vf_idx); + mutex_unlock(&pf->mbox.lock); return; } @@ -3107,7 +3148,11 @@ static void otx2_vf_link_event_task(struct work_struct *work) req->hdr.sig = OTX2_MBOX_REQ_SIG; memcpy(&req->link_info, &pf->linfo, sizeof(req->link_info)); + otx2_mbox_wait_for_zero(&pf->mbox_pfvf[0].mbox_up, vf_idx); + otx2_sync_mbox_up_msg(&pf->mbox_pfvf[0], vf_idx); + + mutex_unlock(&pf->mbox.lock); } static int otx2_sriov_enable(struct pci_dev *pdev, int numvfs) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 35e06048356f..cf0aa16d7540 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -89,16 +89,20 @@ static void otx2vf_vfaf_mbox_handler(struct work_struct *work) struct otx2_mbox *mbox; struct mbox *af_mbox; int offset, id; + u16 num_msgs; af_mbox = container_of(work, struct mbox, mbox_wrk); mbox = &af_mbox->mbox; mdev = &mbox->dev[0]; rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - if (af_mbox->num_msgs == 0) + num_msgs = rsp_hdr->num_msgs; + + if (num_msgs == 0) return; + offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN); - for (id = 0; id < af_mbox->num_msgs; id++) { + for (id = 0; id < num_msgs; id++) { msg = (struct mbox_msghdr *)(mdev->mbase + offset); otx2vf_process_vfaf_mbox_msg(af_mbox->pfvf, msg); offset = mbox->rx_start + msg->next_msgoff; @@ -151,6 +155,7 @@ static void otx2vf_vfaf_mbox_up_handler(struct work_struct *work) struct mbox *vf_mbox; struct otx2_nic *vf; int offset, id; + u16 num_msgs; vf_mbox = container_of(work, struct mbox, mbox_up_wrk); vf = vf_mbox->pfvf; @@ -158,12 +163,14 @@ static void otx2vf_vfaf_mbox_up_handler(struct work_struct *work) mdev = &mbox->dev[0]; rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - if (vf_mbox->up_num_msgs == 0) + num_msgs = rsp_hdr->num_msgs; + + if (num_msgs == 0) return; offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN); - for (id = 0; id < vf_mbox->up_num_msgs; id++) { + for (id = 0; id < num_msgs; id++) { msg = (struct mbox_msghdr *)(mdev->mbase + offset); otx2vf_process_mbox_msg_up(vf, msg); offset = mbox->rx_start + msg->next_msgoff; @@ -178,40 +185,48 @@ static irqreturn_t otx2vf_vfaf_mbox_intr_handler(int irq, void *vf_irq) struct otx2_mbox_dev *mdev; struct otx2_mbox *mbox; struct mbox_hdr *hdr; + u64 mbox_data; /* Clear the IRQ */ otx2_write64(vf, RVU_VF_INT, BIT_ULL(0)); + mbox_data = otx2_read64(vf, RVU_VF_VFPF_MBOX0); + /* Read latest mbox data */ smp_rmb(); - /* Check for PF => VF response messages */ - mbox = &vf->mbox.mbox; - mdev = &mbox->dev[0]; - otx2_sync_mbox_bbuf(mbox, 0); + if (mbox_data & MBOX_DOWN_MSG) { + mbox_data &= ~MBOX_DOWN_MSG; + otx2_write64(vf, RVU_VF_VFPF_MBOX0, mbox_data); + + /* Check for PF => VF response messages */ + mbox = &vf->mbox.mbox; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); - trace_otx2_msg_interrupt(mbox->pdev, "PF to VF", BIT_ULL(0)); + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(vf->mbox_wq, &vf->mbox.mbox_wrk); - hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - if (hdr->num_msgs) { - vf->mbox.num_msgs = hdr->num_msgs; - hdr->num_msgs = 0; - memset(mbox->hwbase + mbox->rx_start, 0, - ALIGN(sizeof(struct mbox_hdr), sizeof(u64))); - queue_work(vf->mbox_wq, &vf->mbox.mbox_wrk); + trace_otx2_msg_interrupt(mbox->pdev, "DOWN reply from PF to VF", + BIT_ULL(0)); } - /* Check for PF => VF notification messages */ - mbox = &vf->mbox.mbox_up; - mdev = &mbox->dev[0]; - otx2_sync_mbox_bbuf(mbox, 0); - hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - if (hdr->num_msgs) { - vf->mbox.up_num_msgs = hdr->num_msgs; - hdr->num_msgs = 0; - memset(mbox->hwbase + mbox->rx_start, 0, - ALIGN(sizeof(struct mbox_hdr), sizeof(u64))); - queue_work(vf->mbox_wq, &vf->mbox.mbox_up_wrk); + if (mbox_data & MBOX_UP_MSG) { + mbox_data &= ~MBOX_UP_MSG; + otx2_write64(vf, RVU_VF_VFPF_MBOX0, mbox_data); + + /* Check for PF => VF notification messages */ + mbox = &vf->mbox.mbox_up; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); + + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(vf->mbox_wq, &vf->mbox.mbox_up_wrk); + + trace_otx2_msg_interrupt(mbox->pdev, "UP message from PF to VF", + BIT_ULL(0)); } return IRQ_HANDLED; @@ -760,8 +775,8 @@ static void otx2vf_remove(struct pci_dev *pdev) otx2_mcam_flow_del(vf); otx2_shutdown_tc(vf); otx2_shutdown_qos(vf); - otx2vf_disable_mbox_intr(vf); otx2_detach_resources(&vf->mbox); + otx2vf_disable_mbox_intr(vf); free_percpu(vf->hw.lmt_info); if (test_bit(CN10K_LMTST, &vf->hw.cap_flag)) qmem_free(vf->dev, vf->dync_lmt); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index de123350bd46..caa13b9cedff 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -677,8 +677,7 @@ static int mtk_mac_finish(struct phylink_config *config, unsigned int mode, mcr_cur = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id)); mcr_new = mcr_cur; mcr_new |= MAC_MCR_IPG_CFG | MAC_MCR_FORCE_MODE | - MAC_MCR_BACKOFF_EN | MAC_MCR_BACKPR_EN | MAC_MCR_FORCE_LINK | - MAC_MCR_RX_FIFO_CLR_DIS; + MAC_MCR_BACKOFF_EN | MAC_MCR_BACKPR_EN | MAC_MCR_RX_FIFO_CLR_DIS; /* Only update control register when needed! */ if (mcr_new != mcr_cur) @@ -694,7 +693,7 @@ static void mtk_mac_link_down(struct phylink_config *config, unsigned int mode, phylink_config); u32 mcr = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id)); - mcr &= ~(MAC_MCR_TX_EN | MAC_MCR_RX_EN); + mcr &= ~(MAC_MCR_TX_EN | MAC_MCR_RX_EN | MAC_MCR_FORCE_LINK); mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); } @@ -803,7 +802,7 @@ static void mtk_mac_link_up(struct phylink_config *config, if (rx_pause) mcr |= MAC_MCR_FORCE_RX_FC; - mcr |= MAC_MCR_TX_EN | MAC_MCR_RX_EN; + mcr |= MAC_MCR_TX_EN | MAC_MCR_RX_EN | MAC_MCR_FORCE_LINK; mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); } diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index b2a5d9c3733d..6ce0db3a1a92 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -994,7 +994,7 @@ void mtk_ppe_start(struct mtk_ppe *ppe) MTK_PPE_KEEPALIVE_DISABLE) | FIELD_PREP(MTK_PPE_TB_CFG_HASH_MODE, 1) | FIELD_PREP(MTK_PPE_TB_CFG_SCAN_MODE, - MTK_PPE_SCAN_MODE_KEEPALIVE_AGE) | + MTK_PPE_SCAN_MODE_CHECK_AGE) | FIELD_PREP(MTK_PPE_TB_CFG_ENTRY_NUM, MTK_PPE_ENTRIES_SHIFT); if (mtk_is_netsys_v2_or_greater(ppe->eth)) @@ -1090,17 +1090,21 @@ int mtk_ppe_stop(struct mtk_ppe *ppe) mtk_ppe_cache_enable(ppe, false); - /* disable offload engine */ - ppe_clear(ppe, MTK_PPE_GLO_CFG, MTK_PPE_GLO_CFG_EN); - ppe_w32(ppe, MTK_PPE_FLOW_CFG, 0); - /* disable aging */ val = MTK_PPE_TB_CFG_AGE_NON_L4 | MTK_PPE_TB_CFG_AGE_UNBIND | MTK_PPE_TB_CFG_AGE_TCP | MTK_PPE_TB_CFG_AGE_UDP | - MTK_PPE_TB_CFG_AGE_TCP_FIN; + MTK_PPE_TB_CFG_AGE_TCP_FIN | + MTK_PPE_TB_CFG_SCAN_MODE; ppe_clear(ppe, MTK_PPE_TB_CFG, val); - return mtk_ppe_wait_busy(ppe); + if (mtk_ppe_wait_busy(ppe)) + return -ETIMEDOUT; + + /* disable offload engine */ + ppe_clear(ppe, MTK_PPE_GLO_CFG, MTK_PPE_GLO_CFG_EN); + ppe_w32(ppe, MTK_PPE_FLOW_CFG, 0); + + return 0; } diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c index 93295916b1d2..5b5d5e4310d1 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c @@ -571,7 +571,7 @@ static int txgbe_clock_register(struct txgbe *txgbe) char clk_name[32]; struct clk *clk; - snprintf(clk_name, sizeof(clk_name), "i2c_designware.%d", + snprintf(clk_name, sizeof(clk_name), "i2c_dw.%d", pci_dev_id(pdev)); clk = clk_register_fixed_rate(NULL, clk_name, NULL, 0, 156250000); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 8297ef681bf5..6c6ec9475709 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2831,8 +2831,8 @@ EXPORT_SYMBOL(genphy_resume); int genphy_loopback(struct phy_device *phydev, bool enable) { if (enable) { - u16 val, ctl = BMCR_LOOPBACK; - int ret; + u16 ctl = BMCR_LOOPBACK; + int ret, val; ctl |= mii_bmcr_encode_fixed(phydev->speed, phydev->duplex); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 13d902462d8e..bcdfbf61eb66 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1464,8 +1464,6 @@ static netdev_features_t veth_fix_features(struct net_device *dev, if (peer_priv->_xdp_prog) features &= ~NETIF_F_GSO_SOFTWARE; } - if (priv->_xdp_prog) - features |= NETIF_F_GRO; return features; } @@ -1569,14 +1567,6 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog, } if (!old_prog) { - if (!veth_gro_requested(dev)) { - /* user-space did not require GRO, but adding - * XDP is supposed to get GRO working - */ - dev->features |= NETIF_F_GRO; - netdev_features_change(dev); - } - peer->hw_features &= ~NETIF_F_GSO_SOFTWARE; peer->max_mtu = max_mtu; } @@ -1592,14 +1582,6 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog, if (dev->flags & IFF_UP) veth_disable_xdp(dev); - /* if user-space did not require GRO, since adding XDP - * enabled it, clear it now - */ - if (!veth_gro_requested(dev)) { - dev->features &= ~NETIF_F_GRO; - netdev_features_change(dev); - } - if (peer) { peer->hw_features |= NETIF_F_GSO_SOFTWARE; peer->max_mtu = ETH_MAX_MTU; diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c index 80ddaff759d4..a6c787454a1a 100644 --- a/drivers/net/vmxnet3/vmxnet3_xdp.c +++ b/drivers/net/vmxnet3/vmxnet3_xdp.c @@ -382,12 +382,12 @@ vmxnet3_process_xdp(struct vmxnet3_adapter *adapter, page = rbi->page; dma_sync_single_for_cpu(&adapter->pdev->dev, page_pool_get_dma_addr(page) + - rq->page_pool->p.offset, rcd->len, + rq->page_pool->p.offset, rbi->len, page_pool_get_dma_dir(rq->page_pool)); - xdp_init_buff(&xdp, rbi->len, &rq->xdp_rxq); + xdp_init_buff(&xdp, PAGE_SIZE, &rq->xdp_rxq); xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset, - rcd->len, false); + rbi->len, false); xdp_buff_clear_frags_flag(&xdp); xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog); diff --git a/drivers/net/wan/fsl_qmc_hdlc.c b/drivers/net/wan/fsl_qmc_hdlc.c index 960371df470a..f69b1f579a0c 100644 --- a/drivers/net/wan/fsl_qmc_hdlc.c +++ b/drivers/net/wan/fsl_qmc_hdlc.c @@ -780,7 +780,7 @@ static const struct of_device_id qmc_hdlc_id_table[] = { { .compatible = "fsl,qmc-hdlc" }, {} /* sentinel */ }; -MODULE_DEVICE_TABLE(of, qmc_hdlc_driver); +MODULE_DEVICE_TABLE(of, qmc_hdlc_id_table); static struct platform_driver qmc_hdlc_driver = { .driver = { diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index deb9636b0ecf..3feb36ee5bfb 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -237,7 +237,6 @@ static const struct net_device_ops netdev_ops = { .ndo_open = wg_open, .ndo_stop = wg_stop, .ndo_start_xmit = wg_xmit, - .ndo_get_stats64 = dev_get_tstats64 }; static void wg_destruct(struct net_device *dev) @@ -262,7 +261,6 @@ static void wg_destruct(struct net_device *dev) rcu_barrier(); /* Wait for all the peers to be actually freed. */ wg_ratelimiter_uninit(); memzero_explicit(&wg->static_identity, sizeof(wg->static_identity)); - free_percpu(dev->tstats); kvfree(wg->index_hashtable); kvfree(wg->peer_hashtable); mutex_unlock(&wg->device_update_lock); @@ -297,6 +295,7 @@ static void wg_setup(struct net_device *dev) dev->hw_enc_features |= WG_NETDEV_FEATURES; dev->mtu = ETH_DATA_LEN - overhead; dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; SET_NETDEV_DEVTYPE(dev, &device_type); @@ -331,14 +330,10 @@ static int wg_newlink(struct net *src_net, struct net_device *dev, if (!wg->index_hashtable) goto err_free_peer_hashtable; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - goto err_free_index_hashtable; - wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s", WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name); if (!wg->handshake_receive_wq) - goto err_free_tstats; + goto err_free_index_hashtable; wg->handshake_send_wq = alloc_workqueue("wg-kex-%s", WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name); @@ -397,8 +392,6 @@ err_destroy_handshake_send: destroy_workqueue(wg->handshake_send_wq); err_destroy_handshake_receive: destroy_workqueue(wg->handshake_receive_wq); -err_free_tstats: - free_percpu(dev->tstats); err_free_index_hashtable: kvfree(wg->index_hashtable); err_free_peer_hashtable: diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index e220d761b1f2..f7055180ba4a 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -164,8 +164,8 @@ get_peer(struct wg_peer *peer, struct sk_buff *skb, struct dump_ctx *ctx) if (!allowedips_node) goto no_allowedips; if (!ctx->allowedips_seq) - ctx->allowedips_seq = peer->device->peer_allowedips.seq; - else if (ctx->allowedips_seq != peer->device->peer_allowedips.seq) + ctx->allowedips_seq = ctx->wg->peer_allowedips.seq; + else if (ctx->allowedips_seq != ctx->wg->peer_allowedips.seq) goto no_allowedips; allowedips_nest = nla_nest_start(skb, WGPEER_A_ALLOWEDIPS); @@ -255,17 +255,17 @@ static int wg_get_device_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!peers_nest) goto out; ret = 0; - /* If the last cursor was removed via list_del_init in peer_remove, then + lockdep_assert_held(&wg->device_update_lock); + /* If the last cursor was removed in peer_remove or peer_remove_all, then * we just treat this the same as there being no more peers left. The * reason is that seq_nr should indicate to userspace that this isn't a * coherent dump anyway, so they'll try again. */ if (list_empty(&wg->peer_list) || - (ctx->next_peer && list_empty(&ctx->next_peer->peer_list))) { + (ctx->next_peer && ctx->next_peer->is_dead)) { nla_nest_cancel(skb, peers_nest); goto out; } - lockdep_assert_held(&wg->device_update_lock); peer = list_prepare_entry(ctx->next_peer, &wg->peer_list, peer_list); list_for_each_entry_continue(peer, &wg->peer_list, peer_list) { if (get_peer(peer, skb, ctx)) { diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index df275b4fccb6..eb8851113654 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -251,7 +251,7 @@ static bool decrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) if (unlikely(!READ_ONCE(keypair->receiving.is_valid) || wg_birthdate_has_expired(keypair->receiving.birthdate, REJECT_AFTER_TIME) || - keypair->receiving_counter.counter >= REJECT_AFTER_MESSAGES)) { + READ_ONCE(keypair->receiving_counter.counter) >= REJECT_AFTER_MESSAGES)) { WRITE_ONCE(keypair->receiving.is_valid, false); return false; } @@ -318,7 +318,7 @@ static bool counter_validate(struct noise_replay_counter *counter, u64 their_cou for (i = 1; i <= top; ++i) counter->backtrack[(i + index_current) & ((COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1)] = 0; - counter->counter = their_counter; + WRITE_ONCE(counter->counter, their_counter); } index &= (COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1; @@ -463,7 +463,7 @@ int wg_packet_rx_poll(struct napi_struct *napi, int budget) net_dbg_ratelimited("%s: Packet has invalid nonce %llu (max %llu)\n", peer->device->dev->name, PACKET_CB(skb)->nonce, - keypair->receiving_counter.counter); + READ_ONCE(keypair->receiving_counter.counter)); goto next; } diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index 739e4eee6b75..7e9074519ad2 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -991,7 +991,7 @@ struct qman_portal { /* linked-list of CSCN handlers. */ struct list_head cgr_cbs; /* list lock */ - spinlock_t cgr_lock; + raw_spinlock_t cgr_lock; struct work_struct congestion_work; struct work_struct mr_work; char irqname[MAX_IRQNAME]; @@ -1281,7 +1281,7 @@ static int qman_create_portal(struct qman_portal *portal, /* if the given mask is NULL, assume all CGRs can be seen */ qman_cgrs_fill(&portal->cgrs[0]); INIT_LIST_HEAD(&portal->cgr_cbs); - spin_lock_init(&portal->cgr_lock); + raw_spin_lock_init(&portal->cgr_lock); INIT_WORK(&portal->congestion_work, qm_congestion_task); INIT_WORK(&portal->mr_work, qm_mr_process_task); portal->bits = 0; @@ -1456,11 +1456,14 @@ static void qm_congestion_task(struct work_struct *work) union qm_mc_result *mcr; struct qman_cgr *cgr; - spin_lock(&p->cgr_lock); + /* + * FIXME: QM_MCR_TIMEOUT is 10ms, which is too long for a raw spinlock! + */ + raw_spin_lock_irq(&p->cgr_lock); qm_mc_start(&p->p); qm_mc_commit(&p->p, QM_MCC_VERB_QUERYCONGESTION); if (!qm_mc_result_timeout(&p->p, &mcr)) { - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); dev_crit(p->config->dev, "QUERYCONGESTION timeout\n"); qman_p_irqsource_add(p, QM_PIRQ_CSCI); return; @@ -1476,7 +1479,7 @@ static void qm_congestion_task(struct work_struct *work) list_for_each_entry(cgr, &p->cgr_cbs, node) if (cgr->cb && qman_cgrs_get(&c, cgr->cgrid)) cgr->cb(p, cgr, qman_cgrs_get(&rr, cgr->cgrid)); - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); qman_p_irqsource_add(p, QM_PIRQ_CSCI); } @@ -2440,7 +2443,7 @@ int qman_create_cgr(struct qman_cgr *cgr, u32 flags, preempt_enable(); cgr->chan = p->config->channel; - spin_lock(&p->cgr_lock); + raw_spin_lock_irq(&p->cgr_lock); if (opts) { struct qm_mcc_initcgr local_opts = *opts; @@ -2477,7 +2480,7 @@ int qman_create_cgr(struct qman_cgr *cgr, u32 flags, qman_cgrs_get(&p->cgrs[1], cgr->cgrid)) cgr->cb(p, cgr, 1); out: - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); put_affine_portal(); return ret; } @@ -2512,7 +2515,7 @@ int qman_delete_cgr(struct qman_cgr *cgr) return -EINVAL; memset(&local_opts, 0, sizeof(struct qm_mcc_initcgr)); - spin_lock_irqsave(&p->cgr_lock, irqflags); + raw_spin_lock_irqsave(&p->cgr_lock, irqflags); list_del(&cgr->node); /* * If there are no other CGR objects for this CGRID in the list, @@ -2537,7 +2540,7 @@ int qman_delete_cgr(struct qman_cgr *cgr) /* add back to the list */ list_add(&cgr->node, &p->cgr_cbs); release_lock: - spin_unlock_irqrestore(&p->cgr_lock, irqflags); + raw_spin_unlock_irqrestore(&p->cgr_lock, irqflags); put_affine_portal(); return ret; } @@ -2577,9 +2580,9 @@ static int qman_update_cgr(struct qman_cgr *cgr, struct qm_mcc_initcgr *opts) if (!p) return -EINVAL; - spin_lock_irqsave(&p->cgr_lock, irqflags); + raw_spin_lock_irqsave(&p->cgr_lock, irqflags); ret = qm_modify_cgr(cgr, 0, opts); - spin_unlock_irqrestore(&p->cgr_lock, irqflags); + raw_spin_unlock_irqrestore(&p->cgr_lock, irqflags); put_affine_portal(); return ret; } diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index fb3a9c93ac86..aa4096126553 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -522,17 +522,18 @@ static inline void bitmap_replace(unsigned long *dst, * * (Bits 0, 1, 2, 3, 4, 5 are copied to the bits 0, 1, 4, 8, 9, 12) * - * A more 'visual' description of the operation: - * src: 0000000001011010 - * |||||| - * +------+||||| - * | +----+|||| - * | |+----+||| - * | || +-+|| - * | || | || - * mask: ...v..vv...v..vv - * ...0..11...0..10 - * dst: 0000001100000010 + * A more 'visual' description of the operation:: + * + * src: 0000000001011010 + * |||||| + * +------+||||| + * | +----+|||| + * | |+----+||| + * | || +-+|| + * | || | || + * mask: ...v..vv...v..vv + * ...0..11...0..10 + * dst: 0000001100000010 * * A relationship exists between bitmap_scatter() and bitmap_gather(). * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation. @@ -568,16 +569,17 @@ static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, * * (Bits 0, 1, 4, 8, 9, 12 are copied to the bits 0, 1, 2, 3, 4, 5) * - * A more 'visual' description of the operation: - * mask: ...v..vv...v..vv - * src: 0000001100000010 - * ^ ^^ ^ 0 - * | || | 10 - * | || > 010 - * | |+--> 1010 - * | +--> 11010 - * +----> 011010 - * dst: 0000000000011010 + * A more 'visual' description of the operation:: + * + * mask: ...v..vv...v..vv + * src: 0000001100000010 + * ^ ^^ ^ 0 + * | || | 10 + * | || > 010 + * | |+--> 1010 + * | +--> 11010 + * +----> 011010 + * dst: 0000000000011010 * * A relationship exists between bitmap_gather() and bitmap_scatter(). See * bitmap_scatter() for the bitmap scatter detailed operations. diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c6f6ac779b34..cb37817d6382 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2072,6 +2072,7 @@ struct net_device { struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; }; + unsigned long state; unsigned int flags; unsigned short hard_header_len; netdev_features_t features; @@ -2117,7 +2118,6 @@ struct net_device { * part of the usual set specified in Space.c. */ - unsigned long state; struct list_head dev_list; struct list_head napi_list; diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 16f519914415..17d7ed5f3ae6 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -247,6 +247,37 @@ do { \ cond_resched(); \ } while (0) +/** + * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states + * @old_ts: jiffies at start of processing. + * + * This helper is for long-running softirq handlers, such as NAPI threads in + * networking. The caller should initialize the variable passed in as @old_ts + * at the beginning of the softirq handler. When invoked frequently, this macro + * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will + * provide both RCU and RCU-Tasks quiescent states. Note that this macro + * modifies its old_ts argument. + * + * Because regions of code that have disabled softirq act as RCU read-side + * critical sections, this macro should be invoked with softirq (and + * preemption) enabled. + * + * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would + * have more chance to invoke schedule() calls and provide necessary quiescent + * states. As a contrast, calling cond_resched() only won't achieve the same + * effect because cond_resched() does not provide RCU-Tasks quiescent states. + */ +#define rcu_softirq_qs_periodic(old_ts) \ +do { \ + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ + time_after(jiffies, (old_ts) + HZ / 10)) { \ + preempt_disable(); \ + rcu_softirq_qs(); \ + preempt_enable(); \ + (old_ts) = jiffies; \ + } \ +} while (0) + /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3023bc2be6a1..0c7c67b3a87b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -822,9 +822,9 @@ typedef unsigned char *sk_buff_data_t; * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required * @mono_delivery_time: When set, skb->tstamp has the - * delivery_time in mono clock base (i.e., EDT) or a clock base chosen - * by SO_TXTIME. If zero, skb->tstamp has the (rcv) timestamp at - * ingress. + * delivery_time in mono clock base (i.e. EDT). Otherwise, the + * skb->tstamp has the (rcv) timestamp at ingress and + * delivery_time at egress. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. @@ -3524,6 +3524,16 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, bool napi_pp_put_page(struct page *page, bool napi_safe); static inline void +skb_page_unref(const struct sk_buff *skb, struct page *page, bool napi_safe) +{ +#ifdef CONFIG_PAGE_POOL + if (skb->pp_recycle && napi_pp_put_page(page, napi_safe)) + return; +#endif + put_page(page); +} + +static inline void napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) { struct page *page = skb_frag_page(frag); diff --git a/include/linux/socket.h b/include/linux/socket.h index cfcb7e2c3813..139c330ccf2c 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -422,13 +422,6 @@ extern long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags); -extern int sendmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct iovec **iov); -extern int recvmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct sockaddr __user **uaddr, - struct iovec **iov); extern int __copy_msghdr(struct msghdr *kmsg, struct user_msghdr *umsg, struct sockaddr __user **save_addr); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 8839133d6f6b..004e651e6067 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -61,7 +61,11 @@ struct request_sock { struct request_sock *dl_next; u16 mss; u8 num_retrans; /* number of retransmits */ - u8 syncookie:1; /* syncookie: encode tcpopts in timestamp */ + u8 syncookie:1; /* True if + * 1) tcpopts needs to be encoded in + * TS of SYN+ACK + * 2) ACK is validated by BPF kfunc. + */ u8 num_timeout:7; /* number of timeouts */ u32 ts_recent; struct timer_list rsk_timer; @@ -144,6 +148,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, sk_node_init(&req_to_sk(req)->sk_node); sk_tx_queue_clear(req_to_sk(req)); req->saved_syn = NULL; + req->syncookie = 0; req->timeout = 0; req->num_timeout = 0; req->num_retrans = 0; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 9ee8da477465..a8e34416e960 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -263,6 +263,7 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; + unsigned long last_qs = jiffies; complete(&rcpu->kthread_running); set_current_state(TASK_INTERRUPTIBLE); @@ -288,10 +289,12 @@ static int cpu_map_kthread_run(void *data) if (__ptr_ring_empty(rcpu->queue)) { schedule(); sched = 1; + last_qs = jiffies; } else { __set_current_state(TASK_RUNNING); } } else { + rcu_softirq_qs_periodic(last_qs); sched = cond_resched(); } diff --git a/net/core/dev.c b/net/core/dev.c index 0766a245816b..9a67003e49db 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2245,7 +2245,7 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); again: list_for_each_entry_rcu(ptype, ptype_list, list) { - if (ptype->ignore_outgoing) + if (READ_ONCE(ptype->ignore_outgoing)) continue; /* Never send packets back to the socket @@ -6743,6 +6743,8 @@ static int napi_threaded_poll(void *data) void *have; while (!napi_thread_wait(napi)) { + unsigned long last_qs = jiffies; + for (;;) { bool repoll = false; @@ -6767,6 +6769,7 @@ static int napi_threaded_poll(void *data) if (!repoll) break; + rcu_softirq_qs_periodic(last_qs); cond_resched(); } } @@ -11665,11 +11668,12 @@ static void __init net_dev_struct_check(void) /* TXRX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, state); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr); - CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 38); + CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 46); /* RX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific); diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c index 499885c8b9ca..593605c1b1ef 100644 --- a/net/devlink/netlink.c +++ b/net/devlink/netlink.c @@ -193,12 +193,13 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs, devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); devlinks_xa_for_each_registered_get(net, index, devlink) { - devl_dev_lock(devlink, dev_lock); - if (devl_is_registered(devlink) && - strcmp(devlink->dev->bus->name, busname) == 0 && - strcmp(dev_name(devlink->dev), devname) == 0) - return devlink; - devl_dev_unlock(devlink, dev_lock); + if (strcmp(devlink->dev->bus->name, busname) == 0 && + strcmp(dev_name(devlink->dev), devname) == 0) { + devl_dev_lock(devlink, dev_lock); + if (devl_is_registered(devlink)) + return devlink; + devl_dev_unlock(devlink, dev_lock); + } devlink_put(devlink); } diff --git a/net/devlink/port.c b/net/devlink/port.c index 4b2d46ccfe48..118d130d2afd 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -889,7 +889,7 @@ int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info) err = -ENOMEM; goto err_out_port_del; } - err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW, + err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, info->snd_portid, info->snd_seq, 0, NULL); if (WARN_ON_ONCE(err)) goto err_out_msg_free; diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 6d14d935ee82..26329db09210 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -228,6 +228,10 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, */ if (ethhdr->h_proto == htons(ETH_P_PRP) || ethhdr->h_proto == htons(ETH_P_HSR)) { + /* Check if skb contains hsr_ethhdr */ + if (skb->mac_len < sizeof(struct hsr_ethhdr)) + return NULL; + /* Use the existing sequence_nr from the tag as starting point * for filtering duplicate frames. */ diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index cb83c8feb746..9756e657bab9 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -148,14 +148,21 @@ static struct notifier_block hsr_nb = { static int __init hsr_init(void) { - int res; + int err; BUILD_BUG_ON(sizeof(struct hsr_tag) != HSR_HLEN); - register_netdevice_notifier(&hsr_nb); - res = hsr_netlink_init(); + err = register_netdevice_notifier(&hsr_nb); + if (err) + return err; + + err = hsr_netlink_init(); + if (err) { + unregister_netdevice_notifier(&hsr_nb); + return err; + } - return res; + return 0; } static void __exit hsr_exit(void) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 4dd9e5040672..d33d12421814 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -95,7 +95,7 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, __alignof__(struct scatterlist)); } -static void esp_ssg_unref(struct xfrm_state *x, void *tmp) +static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) { struct crypto_aead *aead = x->data; int extralen = 0; @@ -114,7 +114,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - put_page(sg_page(sg)); + skb_page_unref(skb, sg_page(sg), false); } #ifdef CONFIG_INET_ESPINTCP @@ -260,7 +260,7 @@ static void esp_output_done(void *data, int err) } tmp = ESP_SKB_CB(skb)->tmp; - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); kfree(tmp); if (xo && (xo->flags & XFRM_DEV_RESUME)) { @@ -639,7 +639,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * } if (sg != dsg) - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) err = esp_output_tail_tcp(x, skb); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 7498af320164..cf88eca5f1b4 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1135,7 +1135,7 @@ error: sock_prot_inuse_add(net, sk->sk_prot, -1); spin_lock(lock); - sk_nulls_del_node_init_rcu(sk); + __sk_nulls_del_node_init_rcu(sk); spin_unlock(lock); sk->sk_hash = 0; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 5befa4de5b24..e8de45d34d56 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -263,12 +263,12 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) } EXPORT_SYMBOL_GPL(__inet_twsk_schedule); +/* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */ void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) { - struct inet_timewait_sock *tw; - struct sock *sk; struct hlist_nulls_node *node; unsigned int slot; + struct sock *sk; for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; @@ -277,38 +277,35 @@ restart_rcu: rcu_read_lock(); restart: sk_nulls_for_each_rcu(sk, node, &head->chain) { - if (sk->sk_state != TCP_TIME_WAIT) { - /* A kernel listener socket might not hold refcnt for net, - * so reqsk_timer_handler() could be fired after net is - * freed. Userspace listener and reqsk never exist here. - */ - if (unlikely(sk->sk_state == TCP_NEW_SYN_RECV && - hashinfo->pernet)) { - struct request_sock *req = inet_reqsk(sk); - - inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req); - } + int state = inet_sk_state_load(sk); + if ((1 << state) & ~(TCPF_TIME_WAIT | + TCPF_NEW_SYN_RECV)) continue; - } - tw = inet_twsk(sk); - if ((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->ns.count)) + if (sk->sk_family != family || + refcount_read(&sock_net(sk)->ns.count)) continue; - if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) continue; - if (unlikely((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->ns.count))) { - inet_twsk_put(tw); + if (unlikely(sk->sk_family != family || + refcount_read(&sock_net(sk)->ns.count))) { + sock_gen_put(sk); goto restart; } rcu_read_unlock(); local_bh_disable(); - inet_twsk_deschedule_put(tw); + if (state == TCP_TIME_WAIT) { + inet_twsk_deschedule_put(inet_twsk(sk)); + } else { + struct request_sock *req = inet_reqsk(sk); + + inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, + req); + } local_bh_enable(); goto restart_rcu; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 33f93dc730a3..1fe794967211 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1458,7 +1458,6 @@ struct sk_buff *__ip_make_skb(struct sock *sk, skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority); skb->mark = cork->mark; skb->tstamp = cork->transmit_time; - skb->mono_delivery_time = !!skb->tstamp; /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 42ac434cfcfa..dcb11f22cbf2 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -357,10 +357,10 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, goto error; skb_reserve(skb, hlen); + skb->protocol = htons(ETH_P_IP); skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; - skb->mono_delivery_time = !!skb->tstamp; skb_dst_set(skb, &rt->dst); *rtp = NULL; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 7972ad3d7c73..500f665f98cb 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -474,6 +474,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); + /* req->syncookie is set true only if ACK is validated + * by BPF kfunc, then, rcv_wscale is already configured. + */ if (!req->syncookie) ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 52040b0e2616..f0761f060a83 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -398,10 +398,6 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family) /* Even if tw_refcount == 1, we must clean up kernel reqsk */ inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family); } else if (!purged_once) { - /* The last refcount is decremented in tcp_sk_exit_batch() */ - if (refcount_read(&net->ipv4.tcp_death_row.tw_refcount) == 1) - continue; - inet_twsk_purge(&tcp_hashinfo, family); purged_once = true; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 6e6efe026cdc..7371886d4f9f 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -112,7 +112,7 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, __alignof__(struct scatterlist)); } -static void esp_ssg_unref(struct xfrm_state *x, void *tmp) +static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) { struct crypto_aead *aead = x->data; int extralen = 0; @@ -131,7 +131,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - put_page(sg_page(sg)); + skb_page_unref(skb, sg_page(sg), false); } #ifdef CONFIG_INET6_ESPINTCP @@ -294,7 +294,7 @@ static void esp_output_done(void *data, int err) } tmp = ESP_SKB_CB(skb)->tmp; - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); kfree(tmp); esp_output_encap_csum(skb); @@ -677,7 +677,7 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info } if (sg != dsg) - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) err = esp_output_tail_tcp(x, skb); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 02eeca5492cd..b9dd3a66e423 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1925,7 +1925,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = cork->base.mark; skb->tstamp = cork->base.transmit_time; - skb->mono_delivery_time = !!skb->tstamp; + ip6_cork_steal_dst(skb, cork); IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); if (proto == IPPROTO_ICMPV6) { diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ca49e6617afa..0d896ca7b589 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -622,7 +622,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; - skb->mono_delivery_time = !!skb->tstamp; + skb_put(skb, length); skb_reset_network_header(skb); iph = ipv6_hdr(skb); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 8bad0a44a0a6..6d8286c299c9 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -258,6 +258,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); + /* req->syncookie is set true only if ACK is validated + * by BPF kfunc, then, rcv_wscale is already configured. + */ if (!req->syncookie) ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok &= cookie_ecn_ok(net, dst); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e93f905e60b6..5fa3d3540c93 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1213,7 +1213,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if (flags & ~NFT_TABLE_F_MASK) return -EOPNOTSUPP; - if (flags == ctx->table->flags) + if (flags == (ctx->table->flags & NFT_TABLE_F_MASK)) return 0; if ((nft_table_has_owner(ctx->table) && @@ -2631,19 +2631,6 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, } } - if (nla[NFTA_CHAIN_COUNTERS]) { - if (!nft_is_base_chain(chain)) { - err = -EOPNOTSUPP; - goto err_hooks; - } - - stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); - if (IS_ERR(stats)) { - err = PTR_ERR(stats); - goto err_hooks; - } - } - if (!(table->flags & NFT_TABLE_F_DORMANT) && nft_is_base_chain(chain) && !list_empty(&hook.list)) { @@ -2658,6 +2645,20 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, } unregister = true; + + if (nla[NFTA_CHAIN_COUNTERS]) { + if (!nft_is_base_chain(chain)) { + err = -EOPNOTSUPP; + goto err_hooks; + } + + stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); + if (IS_ERR(stats)) { + err = PTR_ERR(stats); + goto err_hooks; + } + } + err = -ENOMEM; trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN, sizeof(struct nft_trans_chain)); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index c0ceea068936..df8de5090246 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -2329,8 +2329,6 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (m) { rcu_barrier(); - nft_set_pipapo_match_destroy(ctx, set, m); - for_each_possible_cpu(cpu) pipapo_free_scratch(m, cpu); free_percpu(m->scratch); @@ -2342,8 +2340,7 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (priv->clone) { m = priv->clone; - if (priv->dirty) - nft_set_pipapo_match_destroy(ctx, set, m); + nft_set_pipapo_match_destroy(ctx, set, m); for_each_possible_cpu(cpu) pipapo_free_scratch(priv->clone, cpu); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 61270826b9ac..18f616f487ea 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2057,7 +2057,7 @@ retry: skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; - skb->mono_delivery_time = !!skb->tstamp; + skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) @@ -2586,7 +2586,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->priority = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_mark); skb->tstamp = sockc->transmit_time; - skb->mono_delivery_time = !!skb->tstamp; skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); @@ -3065,7 +3064,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; - skb->mono_delivery_time = !!skb->tstamp; if (unlikely(extra_len == 4)) skb->no_fcs = 1; @@ -4000,7 +3998,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, if (val < 0 || val > 1) return -EINVAL; - po->prot_hook.ignore_outgoing = !!val; + WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val); return 0; } case PACKET_TX_HAS_OFF: @@ -4134,7 +4132,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, 0); break; case PACKET_IGNORE_OUTGOING: - val = po->prot_hook.ignore_outgoing; + val = READ_ONCE(po->prot_hook.ignore_outgoing); break; case PACKET_ROLLOVER_STATS: if (!po->rollover) diff --git a/net/rds/send.c b/net/rds/send.c index 2899def23865..09a280110654 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -103,13 +103,12 @@ EXPORT_SYMBOL_GPL(rds_send_path_reset); static int acquire_in_xmit(struct rds_conn_path *cp) { - return test_and_set_bit(RDS_IN_XMIT, &cp->cp_flags) == 0; + return test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags) == 0; } static void release_in_xmit(struct rds_conn_path *cp) { - clear_bit(RDS_IN_XMIT, &cp->cp_flags); - smp_mb__after_atomic(); + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); /* * We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 6f765768c49c..894b8fa68e5e 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -349,8 +349,8 @@ reload: */ remain = more ? INT_MAX : msg_data_left(msg); txb = call->conn->security->alloc_txbuf(call, remain, sk->sk_allocation); - if (IS_ERR(txb)) { - ret = PTR_ERR(txb); + if (!txb) { + ret = -ENOMEM; goto maybe_error; } } diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index b2a82ab756c2..e0679658d9de 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -33,8 +33,8 @@ struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_ total = hoff + sizeof(*whdr) + data_size; mutex_lock(&call->conn->tx_data_alloc_lock); - buf = page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp, - ~(data_align - 1) & ~(L1_CACHE_BYTES - 1)); + buf = __page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp, + ~(data_align - 1) & ~(L1_CACHE_BYTES - 1)); mutex_unlock(&call->conn->tx_data_alloc_lock); if (!buf) { kfree(txb); diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 5b595773e59b..358cf304f4c9 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -10,6 +10,7 @@ */ #include <linux/jhash.h> +#include <linux/module.h> #include <linux/sizes.h> #include <linux/vmalloc.h> #include <net/pkt_cls.h> @@ -563,6 +564,7 @@ static struct Qdisc_ops fq_pie_qdisc_ops __read_mostly = { .dump_stats = fq_pie_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("fq_pie"); static int __init fq_pie_module_init(void) { diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index c5de70efdc86..a0d54b422186 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -997,7 +997,8 @@ static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { - [TCA_TAPRIO_TC_ENTRY_INDEX] = { .type = NLA_U32 }, + [TCA_TAPRIO_TC_ENTRY_INDEX] = NLA_POLICY_MAX(NLA_U32, + TC_QOPT_MAX_QUEUE), [TCA_TAPRIO_TC_ENTRY_MAX_SDU] = { .type = NLA_U32 }, [TCA_TAPRIO_TC_ENTRY_FP] = NLA_POLICY_RANGE(NLA_U32, TC_FP_EXPRESS, diff --git a/net/socket.c b/net/socket.c index 7e9c8fc9a5b4..e5f3af49a8b6 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2600,9 +2600,9 @@ out: return err; } -int sendmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct iovec **iov) +static int sendmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct iovec **iov) { int err; @@ -2753,10 +2753,10 @@ SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, return __sys_sendmmsg(fd, mmsg, vlen, flags, true); } -int recvmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct sockaddr __user **uaddr, - struct iovec **iov) +static int recvmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct sockaddr __user **uaddr, + struct iovec **iov) { ssize_t err; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 653e51ae3964..6346690d5c69 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -407,7 +407,8 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct net_device *dev = x->xso.dev; - if (!x->type_offload) + if (!x->type_offload || + (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap)) return false; if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET || diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps index 07373c5a7afe..f4e8eb79c1b8 100644 --- a/tools/net/ynl/Makefile.deps +++ b/tools/net/ynl/Makefile.deps @@ -20,6 +20,7 @@ CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h) CFLAGS_mptcp_pm:=$(call get_hdr_inc,_LINUX_MPTCP_PM_H,mptcp_pm.h) CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h) +CFLAGS_nlctrl:=$(call get_hdr_inc,__LINUX_GENERIC_NETLINK_H,genetlink.h) CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_NETLINK_H,nfsd_netlink.h) CFLAGS_ovs_datapath:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h) CFLAGS_ovs_flow:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h) diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index cfcb7e2c3813..139c330ccf2c 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -422,13 +422,6 @@ extern long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags); -extern int sendmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct iovec **iov); -extern int recvmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct sockaddr __user **uaddr, - struct iovec **iov); extern int __copy_msghdr(struct msghdr *kmsg, struct user_msghdr *umsg, struct sockaddr __user **save_addr); diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh index a0bb4524e1e9..a603f7b0a08f 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh @@ -354,7 +354,7 @@ __ping_ipv4() # Send 100 packets and verify that at least 100 packets hit the rule, # to overcome ARP noise. - PING_COUNT=100 PING_TIMEOUT=11 ping_do $dev $dst_ip + PING_COUNT=100 PING_TIMEOUT=20 ping_do $dev $dst_ip check_err $? "Ping failed" tc_check_at_least_x_packets "dev $rp1 egress" 101 10 100 @@ -410,7 +410,7 @@ __ping_ipv6() # Send 100 packets and verify that at least 100 packets hit the rule, # to overcome neighbor discovery noise. - PING_COUNT=100 PING_TIMEOUT=11 ping6_do $dev $dst_ip + PING_COUNT=100 PING_TIMEOUT=20 ping6_do $dev $dst_ip check_err $? "Ping failed" tc_check_at_least_x_packets "dev $rp1 egress" 101 100 diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh index d880df89bc8b..e83fde79f40d 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh @@ -457,7 +457,7 @@ __ping_ipv4() # Send 100 packets and verify that at least 100 packets hit the rule, # to overcome ARP noise. - PING_COUNT=100 PING_TIMEOUT=11 ping_do $dev $dst_ip + PING_COUNT=100 PING_TIMEOUT=20 ping_do $dev $dst_ip check_err $? "Ping failed" tc_check_at_least_x_packets "dev $rp1 egress" 101 10 100 @@ -522,7 +522,7 @@ __ping_ipv6() # Send 100 packets and verify that at least 100 packets hit the rule, # to overcome neighbor discovery noise. - PING_COUNT=100 PING_TIMEOUT=11 ping6_do $dev $dst_ip + PING_COUNT=100 PING_TIMEOUT=20 ping6_do $dev $dst_ip check_err $? "Ping failed" tc_check_at_least_x_packets "dev $rp1 egress" 101 100 diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index 9cd5e885e91f..380cb15e942e 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -217,6 +217,7 @@ for family in 4 6; do cleanup create_ns + ip netns exec $NS_DST ethtool -K veth$DST generic-receive-offload on ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on run_test "GRO frag list" $BM_NET$DST 1 0 cleanup @@ -227,6 +228,7 @@ for family in 4 6; do # use NAT to circumvent GRO FWD check create_ns ip -n $NS_DST addr add dev veth$DST $BM_NET$DST_NAT/$SUFFIX + ip netns exec $NS_DST ethtool -K veth$DST generic-receive-offload on ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on ip netns exec $NS_DST $IPT -t nat -I PREROUTING -d $BM_NET$DST_NAT \ -j DNAT --to-destination $BM_NET$DST @@ -240,6 +242,7 @@ for family in 4 6; do cleanup create_vxlan_pair + ip netns exec $NS_DST ethtool -K veth$DST generic-receive-offload on ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on run_test "GRO frag list over UDP tunnel" $OL_NET$DST 1 1 cleanup @@ -247,6 +250,7 @@ for family in 4 6; do # use NAT to circumvent GRO FWD check create_vxlan_pair ip -n $NS_DST addr add dev $VXDEV$DST $OL_NET$DST_NAT/$SUFFIX + ip netns exec $NS_DST ethtool -K veth$DST generic-receive-offload on ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on ip netns exec $NS_DST $IPT -t nat -I PREROUTING -d $OL_NET$DST_NAT \ -j DNAT --to-destination $OL_NET$DST diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh index 5ae85def0739..3a394b43e274 100755 --- a/tools/testing/selftests/net/veth.sh +++ b/tools/testing/selftests/net/veth.sh @@ -249,9 +249,9 @@ cleanup create_ns ip -n $NS_DST link set dev veth$DST up ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} section xdp -chk_gro_flag "gro vs xdp while down - gro flag on" $DST on +chk_gro_flag "gro vs xdp while down - gro flag off" $DST off ip -n $NS_DST link set dev veth$DST down -chk_gro_flag " - after down" $DST on +chk_gro_flag " - after down" $DST off ip -n $NS_DST link set dev veth$DST xdp off chk_gro_flag " - after xdp off" $DST off ip -n $NS_DST link set dev veth$DST up @@ -261,6 +261,21 @@ chk_gro_flag " - after peer xdp" $DST off cleanup create_ns +ip -n $NS_DST link set dev veth$DST up +ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} section xdp +ip netns exec $NS_DST ethtool -K veth$DST generic-receive-offload on +chk_gro_flag "gro vs xdp while down - gro flag on" $DST on +ip -n $NS_DST link set dev veth$DST down +chk_gro_flag " - after down" $DST on +ip -n $NS_DST link set dev veth$DST xdp off +chk_gro_flag " - after xdp off" $DST on +ip -n $NS_DST link set dev veth$DST up +chk_gro_flag " - after up" $DST on +ip -n $NS_SRC link set dev veth$SRC xdp object ${BPF_FILE} section xdp +chk_gro_flag " - after peer xdp" $DST on +cleanup + +create_ns chk_channels "default channels" $DST 1 1 ip -n $NS_DST link set dev veth$DST down @@ -327,11 +342,14 @@ if [ $CPUS -gt 2 ]; then fi ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} section xdp 2>/dev/null -chk_gro_flag "with xdp attached - gro flag" $DST on +chk_gro_flag "with xdp attached - gro flag" $DST off chk_gro_flag " - peer gro flag" $SRC off chk_tso_flag " - tso flag" $SRC off chk_tso_flag " - peer tso flag" $DST on ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on +chk_gro " - no aggregation" 10 +ip netns exec $NS_DST ethtool -K veth$DST generic-receive-offload on +chk_gro_flag " - gro flag with GRO on" $DST on chk_gro " - aggregation" 1 diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv32.config b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config index 2fc36efb166d..a7f8e8a95625 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/riscv32.config +++ b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config @@ -3,6 +3,7 @@ CONFIG_ARCH_RV32I=y CONFIG_MMU=y CONFIG_FPU=y CONFIG_SOC_VIRT=y +CONFIG_RISCV_ISA_FALLBACK=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv64.config b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config index dc266f3b1915..daeb3e5e0965 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/riscv64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config @@ -2,6 +2,7 @@ CONFIG_ARCH_RV64I=y CONFIG_MMU=y CONFIG_FPU=y CONFIG_SOC_VIRT=y +CONFIG_RISCV_ISA_FALLBACK=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y |