Merge tag 'net-6.5-rc2' of git://git.kernel.org/pub/scm/linux/kernel/…

…git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from netfilter, wireless and ebpf.

  Current release - regressions:

   - netfilter: conntrack: gre: don't set assured flag for clash entries

   - wifi: iwlwifi: remove 'use_tfh' config to fix crash

  Previous releases - regressions:

   - ipv6: fix a potential refcount underflow for idev

   - icmp6: ifix null-ptr-deref of ip6_null_entry->rt6i_idev in
     icmp6_dev()

   - bpf: fix max stack depth check for async callbacks

   - eth: mlx5e:
      - check for NOT_READY flag state after locking
      - fix page_pool page fragment tracking for XDP

   - eth: igc:
      - fix tx hang issue when QBV gate is closed
      - fix corner cases for TSN offload

   - eth: octeontx2-af: Move validation of ptp pointer before its usage

   - eth: ena: fix shift-out-of-bounds in exponential backoff

  Previous releases - always broken:

   - core: prevent skb corruption on frag list segmentation

   - sched:
      - cls_fw: fix improper refcount update leads to use-after-free
      - sch_qfq: account for stab overhead in qfq_enqueue

   - netfilter:
      - report use refcount overflow
      - prevent OOB access in nft_byteorder_eval

   - wifi: mt7921e: fix init command fail with enabled device

   - eth: ocelot: fix oversize frame dropping for preemptible TCs

   - eth: fec: recycle pages for transmitted XDP frames"

* tag 'net-6.5-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (79 commits)
  selftests: tc-testing: add test for qfq with stab overhead
  net/sched: sch_qfq: account for stab overhead in qfq_enqueue
  selftests: tc-testing: add tests for qfq mtu sanity check
  net/sched: sch_qfq: reintroduce lmax bound check for MTU
  wifi: cfg80211: fix receiving mesh packets without RFC1042 header
  wifi: rtw89: debug: fix error code in rtw89_debug_priv_send_h2c_set()
  net: txgbe: fix eeprom calculation error
  net/sched: make psched_mtu() RTNL-less safe
  net: ena: fix shift-out-of-bounds in exponential backoff
  netdevsim: fix uninitialized data in nsim_dev_trap_fa_cookie_write()
  net/sched: flower: Ensure both minimum and maximum ports are specified
  MAINTAINERS: Add another mailing list for QUALCOMM ETHQOS ETHERNET DRIVER
  docs: netdev: update the URL of the status page
  wifi: iwlwifi: remove 'use_tfh' config to fix crash
  xdp: use trusted arguments in XDP hints kfuncs
  bpf: cpumap: Fix memory leak in cpu_map_update_elem
  wifi: airo: avoid uninitialized warning in airo_get_rate()
  octeontx2-pf: Add additional check for MCAM rules
  net: dsa: Removed unneeded of_node_put in felix_parse_ports_node
  net: fec: use netdev_err_once() instead of netdev_err()
  ...

Documentation/process/maintainer-netdev.rst

@@ -98,7 +98,7 @@ If you aren't subscribed to netdev and/or are simply unsure if
 repository link above for any new networking-related commits.  You may
 also check the following website for the current status:
 
-  http://vger.kernel.org/~davem/net-next.html
+  https://patchwork.hopto.org/net-next.html
 
 The ``net`` tree continues to collect fixes for the vX.Y content, and is
 fed back to Linus at regular (~weekly) intervals.  Meaning that the

MAINTAINERS

@@ -17543,6 +17543,7 @@ QUALCOMM ETHQOS ETHERNET DRIVER
 M:	Vinod Koul <[email protected]>
 R:	Bhupesh Sharma <[email protected]>
 L:	[email protected]
+L:	[email protected]
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/qcom,ethqos.yaml
 F:	drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c

arch/riscv/net/bpf_jit.h

@@ -69,7 +69,7 @@ struct rv_jit_context {
 	struct bpf_prog *prog;
 	u16 *insns;		/* RV insns */
 	int ninsns;
-	int body_len;
+	int prologue_len;
 	int epilogue_offset;
 	int *offset;		/* BPF to RV */
 	int nexentries;
@@ -216,8 +216,8 @@ static inline int rv_offset(int insn, int off, struct rv_jit_context *ctx)
 	int from, to;
 
 	off++; /* BPF branch is from PC+1, RV is from PC */
-	from = (insn > 0) ? ctx->offset[insn - 1] : 0;
-	to = (insn + off > 0) ? ctx->offset[insn + off - 1] : 0;
+	from = (insn > 0) ? ctx->offset[insn - 1] : ctx->prologue_len;
+	to = (insn + off > 0) ? ctx->offset[insn + off - 1] : ctx->prologue_len;
 	return ninsns_rvoff(to - from);
 }
 

arch/riscv/net/bpf_jit_core.c

@@ -44,7 +44,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	unsigned int prog_size = 0, extable_size = 0;
 	bool tmp_blinded = false, extra_pass = false;
 	struct bpf_prog *tmp, *orig_prog = prog;
-	int pass = 0, prev_ninsns = 0, prologue_len, i;
+	int pass = 0, prev_ninsns = 0, i;
 	struct rv_jit_data *jit_data;
 	struct rv_jit_context *ctx;
 
@@ -83,6 +83,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = orig_prog;
 		goto out_offset;
 	}
+
+	if (build_body(ctx, extra_pass, NULL)) {
+		prog = orig_prog;
+		goto out_offset;
+	}
+
 	for (i = 0; i < prog->len; i++) {
 		prev_ninsns += 32;
 		ctx->offset[i] = prev_ninsns;
@@ -91,12 +97,15 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	for (i = 0; i < NR_JIT_ITERATIONS; i++) {
 		pass++;
 		ctx->ninsns = 0;
+
+		bpf_jit_build_prologue(ctx);
+		ctx->prologue_len = ctx->ninsns;
+
 		if (build_body(ctx, extra_pass, ctx->offset)) {
 			prog = orig_prog;
 			goto out_offset;
 		}
-		ctx->body_len = ctx->ninsns;
-		bpf_jit_build_prologue(ctx);
+
 		ctx->epilogue_offset = ctx->ninsns;
 		bpf_jit_build_epilogue(ctx);
 
@@ -162,10 +171,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	if (!prog->is_func || extra_pass) {
 		bpf_jit_binary_lock_ro(jit_data->header);
-		prologue_len = ctx->epilogue_offset - ctx->body_len;
 		for (i = 0; i < prog->len; i++)
-			ctx->offset[i] = ninsns_rvoff(prologue_len +
-						      ctx->offset[i]);
+			ctx->offset[i] = ninsns_rvoff(ctx->offset[i]);
 		bpf_prog_fill_jited_linfo(prog, ctx->offset);
 out_offset:
 		kfree(ctx->offset);

drivers/net/dsa/ocelot/felix.c

@@ -1286,7 +1286,6 @@ static int felix_parse_ports_node(struct felix *felix,
 		if (err < 0) {
 			dev_info(dev, "Unsupported PHY mode %s on port %d\n",
 				 phy_modes(phy_mode), port);
-			of_node_put(child);
 
 			/* Leave port_phy_modes[port] = 0, which is also
 			 * PHY_INTERFACE_MODE_NA. This will perform a
@@ -1786,16 +1785,15 @@ static int felix_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
 {
 	struct ocelot *ocelot = ds->priv;
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	struct felix *felix = ocelot_to_felix(ocelot);
 
 	ocelot_port_set_maxlen(ocelot, port, new_mtu);
 
-	mutex_lock(&ocelot->tas_lock);
+	mutex_lock(&ocelot->fwd_domain_lock);
 
-	if (ocelot_port->taprio && felix->info->tas_guard_bands_update)
-		felix->info->tas_guard_bands_update(ocelot, port);
+	if (ocelot_port->taprio && ocelot->ops->tas_guard_bands_update)
+		ocelot->ops->tas_guard_bands_update(ocelot, port);
 
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 
 	return 0;
 }

drivers/net/dsa/ocelot/felix.h

@@ -57,7 +57,6 @@ struct felix_info {
 	void	(*mdio_bus_free)(struct ocelot *ocelot);
 	int	(*port_setup_tc)(struct dsa_switch *ds, int port,
 				 enum tc_setup_type type, void *type_data);
-	void	(*tas_guard_bands_update)(struct ocelot *ocelot, int port);
 	void	(*port_sched_speed_set)(struct ocelot *ocelot, int port,
 					u32 speed);
 	void	(*phylink_mac_config)(struct ocelot *ocelot, int port,

drivers/net/dsa/ocelot/felix_vsc9959.c

@@ -1209,15 +1209,17 @@ static u32 vsc9959_tas_tc_max_sdu(struct tc_taprio_qopt_offload *taprio, int tc)
 static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	struct ocelot_mm_state *mm = &ocelot->mm[port];
 	struct tc_taprio_qopt_offload *taprio;
 	u64 min_gate_len[OCELOT_NUM_TC];
+	u32 val, maxlen, add_frag_size;
+	u64 needed_min_frag_time_ps;
 	int speed, picos_per_byte;
 	u64 needed_bit_time_ps;
-	u32 val, maxlen;
 	u8 tas_speed;
 	int tc;
 
-	lockdep_assert_held(&ocelot->tas_lock);
+	lockdep_assert_held(&ocelot->fwd_domain_lock);
 
 	taprio = ocelot_port->taprio;
 
@@ -1253,14 +1255,21 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 	 */
 	needed_bit_time_ps = (u64)(maxlen + 24) * picos_per_byte;
 
+	/* Preemptible TCs don't need to pass a full MTU, the port will
+	 * automatically emit a HOLD request when a preemptible TC gate closes
+	 */
+	val = ocelot_read_rix(ocelot, QSYS_PREEMPTION_CFG, port);
+	add_frag_size = QSYS_PREEMPTION_CFG_MM_ADD_FRAG_SIZE_X(val);
+	needed_min_frag_time_ps = picos_per_byte *
+		(u64)(24 + 2 * ethtool_mm_frag_size_add_to_min(add_frag_size));
+
 	dev_dbg(ocelot->dev,
-		"port %d: max frame size %d needs %llu ps at speed %d\n",
-		port, maxlen, needed_bit_time_ps, speed);
+		"port %d: max frame size %d needs %llu ps, %llu ps for mPackets at speed %d\n",
+		port, maxlen, needed_bit_time_ps, needed_min_frag_time_ps,
+		speed);
 
 	vsc9959_tas_min_gate_lengths(taprio, min_gate_len);
 
-	mutex_lock(&ocelot->fwd_domain_lock);
-
 	for (tc = 0; tc < OCELOT_NUM_TC; tc++) {
 		u32 requested_max_sdu = vsc9959_tas_tc_max_sdu(taprio, tc);
 		u64 remaining_gate_len_ps;
@@ -1269,7 +1278,9 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 		remaining_gate_len_ps =
 			vsc9959_tas_remaining_gate_len_ps(min_gate_len[tc]);
 
-		if (remaining_gate_len_ps > needed_bit_time_ps) {
+		if ((mm->active_preemptible_tcs & BIT(tc)) ?
+		    remaining_gate_len_ps > needed_min_frag_time_ps :
+		    remaining_gate_len_ps > needed_bit_time_ps) {
 			/* Setting QMAXSDU_CFG to 0 disables oversized frame
 			 * dropping.
 			 */
@@ -1323,8 +1334,6 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 	ocelot_write_rix(ocelot, maxlen, QSYS_PORT_MAX_SDU, port);
 
 	ocelot->ops->cut_through_fwd(ocelot);
-
-	mutex_unlock(&ocelot->fwd_domain_lock);
 }
 
 static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port,
@@ -1351,7 +1360,7 @@ static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port,
 		break;
 	}
 
-	mutex_lock(&ocelot->tas_lock);
+	mutex_lock(&ocelot->fwd_domain_lock);
 
 	ocelot_rmw_rix(ocelot,
 		       QSYS_TAG_CONFIG_LINK_SPEED(tas_speed),
@@ -1361,7 +1370,7 @@ static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port,
 	if (ocelot_port->taprio)
 		vsc9959_tas_guard_bands_update(ocelot, port);
 
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 }
 
 static void vsc9959_new_base_time(struct ocelot *ocelot, ktime_t base_time,
@@ -1409,7 +1418,7 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port,
 	int ret, i;
 	u32 val;
 
-	mutex_lock(&ocelot->tas_lock);
+	mutex_lock(&ocelot->fwd_domain_lock);
 
 	if (taprio->cmd == TAPRIO_CMD_DESTROY) {
 		ocelot_port_mqprio(ocelot, port, &taprio->mqprio);
@@ -1421,7 +1430,7 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port,
 
 		vsc9959_tas_guard_bands_update(ocelot, port);
 
-		mutex_unlock(&ocelot->tas_lock);
+		mutex_unlock(&ocelot->fwd_domain_lock);
 		return 0;
 	} else if (taprio->cmd != TAPRIO_CMD_REPLACE) {
 		ret = -EOPNOTSUPP;
@@ -1504,15 +1513,15 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port,
 	ocelot_port->taprio = taprio_offload_get(taprio);
 	vsc9959_tas_guard_bands_update(ocelot, port);
 
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 
 	return 0;
 
 err_reset_tc:
 	taprio->mqprio.qopt.num_tc = 0;
 	ocelot_port_mqprio(ocelot, port, &taprio->mqprio);
 err_unlock:
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 
 	return ret;
 }
@@ -1525,7 +1534,7 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
 	int port;
 	u32 val;
 
-	mutex_lock(&ocelot->tas_lock);
+	mutex_lock(&ocelot->fwd_domain_lock);
 
 	for (port = 0; port < ocelot->num_phys_ports; port++) {
 		ocelot_port = ocelot->ports[port];
@@ -1563,7 +1572,7 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
 			       QSYS_TAG_CONFIG_ENABLE,
 			       QSYS_TAG_CONFIG, port);
 	}
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 }
 
 static int vsc9959_qos_port_cbs_set(struct dsa_switch *ds, int port,
@@ -1634,6 +1643,18 @@ static int vsc9959_qos_query_caps(struct tc_query_caps_base *base)
 	}
 }
 
+static int vsc9959_qos_port_mqprio(struct ocelot *ocelot, int port,
+				   struct tc_mqprio_qopt_offload *mqprio)
+{
+	int ret;
+
+	mutex_lock(&ocelot->fwd_domain_lock);
+	ret = ocelot_port_mqprio(ocelot, port, mqprio);
+	mutex_unlock(&ocelot->fwd_domain_lock);
+
+	return ret;
+}
+
 static int vsc9959_port_setup_tc(struct dsa_switch *ds, int port,
 				 enum tc_setup_type type,
 				 void *type_data)
@@ -1646,7 +1667,7 @@ static int vsc9959_port_setup_tc(struct dsa_switch *ds, int port,
 	case TC_SETUP_QDISC_TAPRIO:
 		return vsc9959_qos_port_tas_set(ocelot, port, type_data);
 	case TC_SETUP_QDISC_MQPRIO:
-		return ocelot_port_mqprio(ocelot, port, type_data);
+		return vsc9959_qos_port_mqprio(ocelot, port, type_data);
 	case TC_SETUP_QDISC_CBS:
 		return vsc9959_qos_port_cbs_set(ds, port, type_data);
 	default:
@@ -2591,6 +2612,7 @@ static const struct ocelot_ops vsc9959_ops = {
 	.cut_through_fwd	= vsc9959_cut_through_fwd,
 	.tas_clock_adjust	= vsc9959_tas_clock_adjust,
 	.update_stats		= vsc9959_update_stats,
+	.tas_guard_bands_update	= vsc9959_tas_guard_bands_update,
 };
 
 static const struct felix_info felix_info_vsc9959 = {
@@ -2616,7 +2638,6 @@ static const struct felix_info felix_info_vsc9959 = {
 	.port_modes		= vsc9959_port_modes,
 	.port_setup_tc		= vsc9959_port_setup_tc,
 	.port_sched_speed_set	= vsc9959_sched_speed_set,
-	.tas_guard_bands_update	= vsc9959_tas_guard_bands_update,
 };
 
 /* The INTB interrupt is shared between for PTP TX timestamp availability

drivers/net/dsa/qca/qca8k-8xxx.c

@@ -588,6 +588,9 @@ qca8k_phy_eth_busy_wait(struct qca8k_mgmt_eth_data *mgmt_eth_data,
 	bool ack;
 	int ret;
 
+	if (!skb)
+		return -ENOMEM;
+
 	reinit_completion(&mgmt_eth_data->rw_done);
 
 	/* Increment seq_num and set it in the copy pkt */

drivers/net/ethernet/amazon/ena/ena_com.c

@@ -35,6 +35,8 @@
 
 #define ENA_REGS_ADMIN_INTR_MASK 1
 
+#define ENA_MAX_BACKOFF_DELAY_EXP 16U
+
 #define ENA_MIN_ADMIN_POLL_US 100
 
 #define ENA_MAX_ADMIN_POLL_US 5000
@@ -536,6 +538,7 @@ static int ena_com_comp_status_to_errno(struct ena_com_admin_queue *admin_queue,
 
 static void ena_delay_exponential_backoff_us(u32 exp, u32 delay_us)
 {
+	exp = min_t(u32, exp, ENA_MAX_BACKOFF_DELAY_EXP);
 	delay_us = max_t(u32, ENA_MIN_ADMIN_POLL_US, delay_us);
 	delay_us = min_t(u32, delay_us * (1U << exp), ENA_MAX_ADMIN_POLL_US);
 	usleep_range(delay_us, 2 * delay_us);

drivers/net/ethernet/broadcom/bgmac.c

@@ -1492,8 +1492,6 @@ int bgmac_enet_probe(struct bgmac *bgmac)
 
 	bgmac->in_init = true;
 
-	bgmac_chip_intrs_off(bgmac);
-
 	net_dev->irq = bgmac->irq;
 	SET_NETDEV_DEV(net_dev, bgmac->dev);
 	dev_set_drvdata(bgmac->dev, bgmac);
@@ -1511,6 +1509,8 @@ int bgmac_enet_probe(struct bgmac *bgmac)
 	 */
 	bgmac_clk_enable(bgmac, 0);
 
+	bgmac_chip_intrs_off(bgmac);
+
 	/* This seems to be fixing IRQ by assigning OOB #6 to the core */
 	if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) {
 		if (bgmac->feature_flags & BGMAC_FEAT_IRQ_ID_OOB_6)

drivers/net/ethernet/freescale/fec.h

@@ -355,7 +355,7 @@ struct bufdesc_ex {
 #define RX_RING_SIZE		(FEC_ENET_RX_FRPPG * FEC_ENET_RX_PAGES)
 #define FEC_ENET_TX_FRSIZE	2048
 #define FEC_ENET_TX_FRPPG	(PAGE_SIZE / FEC_ENET_TX_FRSIZE)
-#define TX_RING_SIZE		512	/* Must be power of two */
+#define TX_RING_SIZE		1024	/* Must be power of two */
 #define TX_RING_MOD_MASK	511	/*   for this to work */
 
 #define BD_ENET_RX_INT		0x00800000
@@ -544,10 +544,23 @@ enum {
 	XDP_STATS_TOTAL,
 };
 
+enum fec_txbuf_type {
+	FEC_TXBUF_T_SKB,
+	FEC_TXBUF_T_XDP_NDO,
+};
+
+struct fec_tx_buffer {
+	union {
+		struct sk_buff *skb;
+		struct xdp_frame *xdp;
+	};
+	enum fec_txbuf_type type;
+};
+
 struct fec_enet_priv_tx_q {
 	struct bufdesc_prop bd;
 	unsigned char *tx_bounce[TX_RING_SIZE];
-	struct  sk_buff *tx_skbuff[TX_RING_SIZE];
+	struct fec_tx_buffer tx_buf[TX_RING_SIZE];
 
 	unsigned short tx_stop_threshold;
 	unsigned short tx_wake_threshold;