Merge tag 'net-6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from bluetooth.

  Current release - regressions:

   - rtnetlink: fix rtnl_dump_ifinfo() error path

   - bluetooth: remove the redundant sco_conn_put

  Previous releases - regressions:

   - netlink: fix false positive warning in extack during dumps

   - sched: sch_fq: don't follow the fast path if Tx is behind now

   - ipv6: delete temporary address if mngtmpaddr is removed or
     unmanaged

   - tcp: fix use-after-free of nreq in reqsk_timer_handler().

   - bluetooth: fix slab-use-after-free Read in set_powered_sync

   - l2tp: fix warning in l2tp_exit_net found

   - eth:
       - bnxt_en: fix receive ring space parameters when XDP is active
       - lan78xx: fix double free issue with interrupt buffer allocation
       - tg3: set coherent DMA mask bits to 31 for BCM57766 chipsets

  Previous releases - always broken:

   - ipmr: fix tables suspicious RCU usage

   - iucv: MSG_PEEK causes memory leak in iucv_sock_destruct()

   - eth:
       - octeontx2-af: fix low network performance
       - stmmac: dwmac-socfpga: set RX watchdog interrupt as broken
       - rtase: correct the speed for RTL907XD-V1

  Misc:

   - some documentation fixup"

* tag 'net-6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (49 commits)
  ipmr: fix build with clang and DEBUG_NET disabled.
  Documentation: tls_offload: fix typos and grammar
  Fix spelling mistake
  ipmr: fix tables suspicious RCU usage
  ip6mr: fix tables suspicious RCU usage
  ipmr: add debug check for mr table cleanup
  selftests: rds: move test.py to TEST_FILES
  net_sched: sch_fq: don't follow the fast path if Tx is behind now
  tcp: Fix use-after-free of nreq in reqsk_timer_handler().
  net: phy: fix phy_ethtool_set_eee() incorrectly enabling LPI
  net: Comment copy_from_sockptr() explaining its behaviour
  rxrpc: Improve setsockopt() handling of malformed user input
  llc: Improve setsockopt() handling of malformed user input
  Bluetooth: SCO: remove the redundant sco_conn_put
  Bluetooth: MGMT: Fix possible deadlocks
  Bluetooth: MGMT: Fix slab-use-after-free Read in set_powered_sync
  bnxt_en: Unregister PTP during PCI shutdown and suspend
  bnxt_en: Refactor bnxt_ptp_init()
  bnxt_en: Fix receive ring space parameters when XDP is active
  bnxt_en: Fix queue start to update vnic RSS table
  ...

Author: torvalds

Documentation/networking/cdc_mbim.rst

@@ -51,7 +51,7 @@ Such userspace applications includes, but are not limited to:
  - mbimcli (included with the libmbim [3] library), and
  - ModemManager [4]
 
-Establishing a MBIM IP session reequires at least these actions by the
+Establishing a MBIM IP session requires at least these actions by the
 management application:
 
  - open the control channel

Documentation/networking/tls-offload.rst

@@ -51,7 +51,7 @@ and send them to the device for encryption and transmission.
 RX
 --
 
-On the receive side if the device handled decryption and authentication
+On the receive side, if the device handled decryption and authentication
 successfully, the driver will set the decrypted bit in the associated
 :c:type:`struct sk_buff <sk_buff>`. The packets reach the TCP stack and
 are handled normally. ``ktls`` is informed when data is queued to the socket
@@ -120,8 +120,9 @@ before installing the connection state in the kernel.
 RX
 --
 
-In RX direction local networking stack has little control over the segmentation,
-so the initial records' TCP sequence number may be anywhere inside the segment.
+In the RX direction, the local networking stack has little control over
+segmentation, so the initial records' TCP sequence number may be anywhere
+inside the segment.
 
 Normal operation
 ================
@@ -138,8 +139,8 @@ There are no guarantees on record length or record segmentation. In particular
 segments may start at any point of a record and contain any number of records.
 Assuming segments are received in order, the device should be able to perform
 crypto operations and authentication regardless of segmentation. For this
-to be possible device has to keep small amount of segment-to-segment state.
-This includes at least:
+to be possible, the device has to keep a small amount of segment-to-segment
+state. This includes at least:
 
  * partial headers (if a segment carried only a part of the TLS header)
  * partial data block
@@ -175,12 +176,12 @@ and packet transformation functions) the device validates the Layer 4
 checksum and performs a 5-tuple lookup to find any TLS connection the packet
 may belong to (technically a 4-tuple
 lookup is sufficient - IP addresses and TCP port numbers, as the protocol
-is always TCP). If connection is matched device confirms if the TCP sequence
-number is the expected one and proceeds to TLS handling (record delineation,
-decryption, authentication for each record in the packet). The device leaves
-the record framing unmodified, the stack takes care of record decapsulation.
-Device indicates successful handling of TLS offload in the per-packet context
-(descriptor) passed to the host.
+is always TCP). If the packet is matched to a connection, the device confirms
+if the TCP sequence number is the expected one and proceeds to TLS handling
+(record delineation, decryption, authentication for each record in the packet).
+The device leaves the record framing unmodified, the stack takes care of record
+decapsulation. Device indicates successful handling of TLS offload in the
+per-packet context (descriptor) passed to the host.
 
 Upon reception of a TLS offloaded packet, the driver sets
 the :c:member:`decrypted` mark in :c:type:`struct sk_buff <sk_buff>`
@@ -439,7 +440,7 @@ by the driver:
  * ``rx_tls_resync_req_end`` - number of times the TLS async resync request
     properly ended with providing the HW tracked tcp-seq.
  * ``rx_tls_resync_req_skip`` - number of times the TLS async resync request
-    procedure was started by not properly ended.
+    procedure was started but not properly ended.
  * ``rx_tls_resync_res_ok`` - number of times the TLS resync response call to
     the driver was successfully handled.
  * ``rx_tls_resync_res_skip`` - number of times the TLS resync response call to
@@ -507,8 +508,8 @@ in packets as seen on the wire.
 Transport layer transparency
 ----------------------------
 
-The device should not modify any packet headers for the purpose
-of the simplifying TLS offload.
+For the purpose of simplifying TLS offload, the device should not modify any
+packet headers.
 
 The device should not depend on any packet headers beyond what is strictly
 necessary for TLS offload.

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -4661,7 +4661,7 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
 	struct net_device *dev = bp->dev;
 
 	if (page_mode) {
-		bp->flags &= ~BNXT_FLAG_AGG_RINGS;
+		bp->flags &= ~(BNXT_FLAG_AGG_RINGS | BNXT_FLAG_NO_AGG_RINGS);
 		bp->flags |= BNXT_FLAG_RX_PAGE_MODE;
 
 		if (bp->xdp_prog->aux->xdp_has_frags)
@@ -9299,7 +9299,6 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp)
 	struct hwrm_port_mac_ptp_qcfg_output *resp;
 	struct hwrm_port_mac_ptp_qcfg_input *req;
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
-	bool phc_cfg;
 	u8 flags;
 	int rc;
 
@@ -9346,8 +9345,9 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp)
 		rc = -ENODEV;
 		goto exit;
 	}
-	phc_cfg = (flags & PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED) != 0;
-	rc = bnxt_ptp_init(bp, phc_cfg);
+	ptp->rtc_configured =
+		(flags & PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED) != 0;
+	rc = bnxt_ptp_init(bp);
 	if (rc)
 		netdev_warn(bp->dev, "PTP initialization failed.\n");
 exit:
@@ -14746,6 +14746,14 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu)
 		bnxt_close_nic(bp, true, false);
 
 	WRITE_ONCE(dev->mtu, new_mtu);
+
+	/* MTU change may change the AGG ring settings if an XDP multi-buffer
+	 * program is attached.  We need to set the AGG rings settings and
+	 * rx_skb_func accordingly.
+	 */
+	if (READ_ONCE(bp->xdp_prog))
+		bnxt_set_rx_skb_mode(bp, true);
+
 	bnxt_set_ring_params(bp);
 
 	if (netif_running(dev))
@@ -15483,6 +15491,13 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 
 	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
 		vnic = &bp->vnic_info[i];
+
+		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
+		if (rc) {
+			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
+				   vnic->vnic_id, rc);
+			return rc;
+		}
 		vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
 		bnxt_hwrm_vnic_update(bp, vnic,
 				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
@@ -16236,6 +16251,7 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 	if (netif_running(dev))
 		dev_close(dev);
 
+	bnxt_ptp_clear(bp);
 	bnxt_clear_int_mode(bp);
 	pci_disable_device(pdev);
 
@@ -16263,6 +16279,7 @@ static int bnxt_suspend(struct device *device)
 		rc = bnxt_close(dev);
 	}
 	bnxt_hwrm_func_drv_unrgtr(bp);
+	bnxt_ptp_clear(bp);
 	pci_disable_device(bp->pdev);
 	bnxt_free_ctx_mem(bp, false);
 	rtnl_unlock();
@@ -16306,6 +16323,10 @@ static int bnxt_resume(struct device *device)
 	if (bp->fw_crash_mem)
 		bnxt_hwrm_crash_dump_mem_cfg(bp);
 
+	if (bnxt_ptp_init(bp)) {
+		kfree(bp->ptp_cfg);
+		bp->ptp_cfg = NULL;
+	}
 	bnxt_get_wol_settings(bp);
 	if (netif_running(dev)) {
 		rc = bnxt_open(dev);
@@ -16484,8 +16505,12 @@ static void bnxt_io_resume(struct pci_dev *pdev)
 	rtnl_lock();
 
 	err = bnxt_hwrm_func_qcaps(bp);
-	if (!err && netif_running(netdev))
-		err = bnxt_open(netdev);
+	if (!err) {
+		if (netif_running(netdev))
+			err = bnxt_open(netdev);
+		else
+			err = bnxt_reserve_rings(bp, true);
+	}
 
 	if (!err)
 		netif_device_attach(netdev);

drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c

@@ -2837,19 +2837,24 @@ static int bnxt_get_link_ksettings(struct net_device *dev,
 	}
 
 	base->port = PORT_NONE;
-	if (link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP) {
+	if (media == BNXT_MEDIA_TP) {
 		base->port = PORT_TP;
 		linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT,
 				 lk_ksettings->link_modes.supported);
 		linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT,
 				 lk_ksettings->link_modes.advertising);
+	} else if (media == BNXT_MEDIA_KR) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Backplane_BIT,
+				 lk_ksettings->link_modes.supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Backplane_BIT,
+				 lk_ksettings->link_modes.advertising);
 	} else {
 		linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT,
 				 lk_ksettings->link_modes.supported);
 		linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT,
 				 lk_ksettings->link_modes.advertising);
 
-		if (link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_DAC)
+		if (media == BNXT_MEDIA_CR)
 			base->port = PORT_DA;
 		else
 			base->port = PORT_FIBRE;

drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c

@@ -1038,7 +1038,7 @@ static void bnxt_ptp_free(struct bnxt *bp)
 	}
 }
 
-int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg)
+int bnxt_ptp_init(struct bnxt *bp)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 	int rc;
@@ -1061,7 +1061,7 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg)
 
 	if (BNXT_PTP_USE_RTC(bp)) {
 		bnxt_ptp_timecounter_init(bp, false);
-		rc = bnxt_ptp_init_rtc(bp, phc_cfg);
+		rc = bnxt_ptp_init_rtc(bp, ptp->rtc_configured);
 		if (rc)
 			goto out;
 	} else {

drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h

@@ -135,6 +135,7 @@ struct bnxt_ptp_cfg {
 					 BNXT_PTP_MSG_PDELAY_REQ |	\
 					 BNXT_PTP_MSG_PDELAY_RESP)
 	u8			tx_tstamp_en:1;
+	u8			rtc_configured:1;
 	int			rx_filter;
 	u32			tstamp_filters;
 
@@ -168,7 +169,7 @@ void bnxt_tx_ts_cmp(struct bnxt *bp, struct bnxt_napi *bnapi,
 		    struct tx_ts_cmp *tscmp);
 void bnxt_ptp_rtc_timecounter_init(struct bnxt_ptp_cfg *ptp, u64 ns);
 int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg);
-int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg);
+int bnxt_ptp_init(struct bnxt *bp);
 void bnxt_ptp_clear(struct bnxt *bp);
 static inline u64 bnxt_timecounter_cyc2time(struct bnxt_ptp_cfg *ptp, u64 ts)
 {

drivers/net/ethernet/broadcom/tg3.c

@@ -17839,6 +17839,9 @@ static int tg3_init_one(struct pci_dev *pdev,
 	} else
 		persist_dma_mask = dma_mask = DMA_BIT_MASK(64);
 
+	if (tg3_asic_rev(tp) == ASIC_REV_57766)
+		persist_dma_mask = DMA_BIT_MASK(31);
+
 	/* Configure DMA attributes. */
 	if (dma_mask > DMA_BIT_MASK(32)) {
 		err = dma_set_mask(&pdev->dev, dma_mask);

drivers/net/ethernet/marvell/octeontx2/af/cgx.c

@@ -112,6 +112,11 @@ struct mac_ops *get_mac_ops(void *cgxd)
 	return ((struct cgx *)cgxd)->mac_ops;
 }
 
+u32 cgx_get_fifo_len(void *cgxd)
+{
+	return ((struct cgx *)cgxd)->fifo_len;
+}
+
 void cgx_write(struct cgx *cgx, u64 lmac, u64 offset, u64 val)
 {
 	writeq(val, cgx->reg_base + (lmac << cgx->mac_ops->lmac_offset) +
@@ -209,6 +214,24 @@ u8 cgx_lmac_get_p2x(int cgx_id, int lmac_id)
 	return (cfg & CMR_P2X_SEL_MASK) >> CMR_P2X_SEL_SHIFT;
 }
 
+static u8 cgx_get_nix_resetbit(struct cgx *cgx)
+{
+	int first_lmac;
+	u8 p2x;
+
+	/* non 98XX silicons supports only NIX0 block */
+	if (cgx->pdev->subsystem_device != PCI_SUBSYS_DEVID_98XX)
+		return CGX_NIX0_RESET;
+
+	first_lmac = find_first_bit(&cgx->lmac_bmap, cgx->max_lmac_per_mac);
+	p2x = cgx_lmac_get_p2x(cgx->cgx_id, first_lmac);
+
+	if (p2x == CMR_P2X_SEL_NIX1)
+		return CGX_NIX1_RESET;
+	else
+		return CGX_NIX0_RESET;
+}
+
 /* Ensure the required lock for event queue(where asynchronous events are
  * posted) is acquired before calling this API. Else an asynchronous event(with
  * latest link status) can reach the destination before this function returns
@@ -501,7 +524,7 @@ static u32 cgx_get_lmac_fifo_len(void *cgxd, int lmac_id)
 	u8 num_lmacs;
 	u32 fifo_len;
 
-	fifo_len = cgx->mac_ops->fifo_len;
+	fifo_len = cgx->fifo_len;
 	num_lmacs = cgx->mac_ops->get_nr_lmacs(cgx);
 
 	switch (num_lmacs) {
@@ -1719,6 +1742,8 @@ static int cgx_lmac_init(struct cgx *cgx)
 		lmac->lmac_type = cgx->mac_ops->get_lmac_type(cgx, lmac->lmac_id);
 	}
 
+	/* Start X2P reset on given MAC block */
+	cgx->mac_ops->mac_x2p_reset(cgx, true);
 	return cgx_lmac_verify_fwi_version(cgx);
 
 err_bitmap_free:
@@ -1764,7 +1789,7 @@ static void cgx_populate_features(struct cgx *cgx)
 	u64 cfg;
 
 	cfg = cgx_read(cgx, 0, CGX_CONST);
-	cgx->mac_ops->fifo_len = FIELD_GET(CGX_CONST_RXFIFO_SIZE, cfg);
+	cgx->fifo_len = FIELD_GET(CGX_CONST_RXFIFO_SIZE, cfg);
 	cgx->max_lmac_per_mac = FIELD_GET(CGX_CONST_MAX_LMACS, cfg);
 
 	if (is_dev_rpm(cgx))
@@ -1784,6 +1809,45 @@ static u8 cgx_get_rxid_mapoffset(struct cgx *cgx)
 		return 0x60;
 }
 
+static void cgx_x2p_reset(void *cgxd, bool enable)
+{
+	struct cgx *cgx = cgxd;
+	int lmac_id;
+	u64 cfg;
+
+	if (enable) {
+		for_each_set_bit(lmac_id, &cgx->lmac_bmap, cgx->max_lmac_per_mac)
+			cgx->mac_ops->mac_enadis_rx(cgx, lmac_id, false);
+
+		usleep_range(1000, 2000);
+
+		cfg = cgx_read(cgx, 0, CGXX_CMR_GLOBAL_CONFIG);
+		cfg |= cgx_get_nix_resetbit(cgx) | CGX_NSCI_DROP;
+		cgx_write(cgx, 0, CGXX_CMR_GLOBAL_CONFIG, cfg);
+	} else {
+		cfg = cgx_read(cgx, 0, CGXX_CMR_GLOBAL_CONFIG);
+		cfg &= ~(cgx_get_nix_resetbit(cgx) | CGX_NSCI_DROP);
+		cgx_write(cgx, 0, CGXX_CMR_GLOBAL_CONFIG, cfg);
+	}
+}
+
+static int cgx_enadis_rx(void *cgxd, int lmac_id, bool enable)
+{
+	struct cgx *cgx = cgxd;
+	u64 cfg;
+
+	if (!is_lmac_valid(cgx, lmac_id))
+		return -ENODEV;
+
+	cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_CFG);
+	if (enable)
+		cfg |= DATA_PKT_RX_EN;
+	else
+		cfg &= ~DATA_PKT_RX_EN;
+	cgx_write(cgx, lmac_id, CGXX_CMRX_CFG, cfg);
+	return 0;
+}
+
 static struct mac_ops	cgx_mac_ops    = {
 	.name		=       "cgx",
 	.csr_offset	=       0,
@@ -1815,6 +1879,8 @@ static struct mac_ops	cgx_mac_ops    = {
 	.mac_get_pfc_frm_cfg   =        cgx_lmac_get_pfc_frm_cfg,
 	.mac_reset   =			cgx_lmac_reset,
 	.mac_stats_reset       =	cgx_stats_reset,
+	.mac_x2p_reset                   =      cgx_x2p_reset,
+	.mac_enadis_rx			 =      cgx_enadis_rx,
 };
 
 static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)

drivers/net/ethernet/marvell/octeontx2/af/cgx.h

@@ -32,6 +32,10 @@
 #define CGX_LMAC_TYPE_MASK		0xF
 #define CGXX_CMRX_INT			0x040
 #define FW_CGX_INT			BIT_ULL(1)
+#define CGXX_CMR_GLOBAL_CONFIG          0x08
+#define CGX_NIX0_RESET			BIT_ULL(2)
+#define CGX_NIX1_RESET			BIT_ULL(3)
+#define CGX_NSCI_DROP			BIT_ULL(9)
 #define CGXX_CMRX_INT_ENA_W1S		0x058
 #define CGXX_CMRX_RX_ID_MAP		0x060
 #define CGXX_CMRX_RX_STAT0		0x070
@@ -185,4 +189,5 @@ int cgx_lmac_get_pfc_frm_cfg(void *cgxd, int lmac_id, u8 *tx_pause,
 int verify_lmac_fc_cfg(void *cgxd, int lmac_id, u8 tx_pause, u8 rx_pause,
 		       int pfvf_idx);
 int cgx_lmac_reset(void *cgxd, int lmac_id, u8 pf_req_flr);
+u32 cgx_get_fifo_len(void *cgxd);
 #endif /* CGX_H */