Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Include fixes for netrom and dsa (Fabian Frederick and Florian
    Fainelli)

 2) Fix FIXED_PHY support in stmmac, from Giuseppe CAVALLARO.

 3) Several SKB use after free fixes (vxlan, openvswitch, vxlan,
    ip_tunnel, fou), from Li ROngQing.

 4) fec driver PTP support fixes from Luwei Zhou and Nimrod Andy.

 5) Use after free in virtio_net, from Michael S Tsirkin.

 6) Fix flow mask handling for megaflows in openvswitch, from Pravin B
    Shelar.

 7) ISDN gigaset and capi bug fixes from Tilman Schmidt.

 8) Fix route leak in ip_send_unicast_reply(), from Vasily Averin.

 9) Fix two eBPF JIT bugs on x86, from Alexei Starovoitov.

10) TCP_SKB_CB() reorganization caused a few regressions, fixed by Cong
    Wang and Eric Dumazet.

11) Don't overwrite end of SKB when parsing malformed sctp ASCONF
    chunks, from Daniel Borkmann.

12) Don't call sock_kfree_s() with NULL pointers, this function also has
    the side effect of adjusting the socket memory usage.  From Cong Wang.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (90 commits)
  bna: fix skb->truesize underestimation
  net: dsa: add includes for ethtool and phy_fixed definitions
  openvswitch: Set flow-key members.
  netrom: use linux/uaccess.h
  dsa: Fix conversion from host device to mii bus
  tipc: fix bug in bundled buffer reception
  ipv6: introduce tcp_v6_iif()
  sfc: add support for skb->xmit_more
  r8152: return -EBUSY for runtime suspend
  ipv4: fix a potential use after free in fou.c
  ipv4: fix a potential use after free in ip_tunnel_core.c
  hyperv: Add handling of IP header with option field in netvsc_set_hash()
  openvswitch: Create right mask with disabled megaflows
  vxlan: fix a free after use
  openvswitch: fix a use after free
  ipv4: dst_entry leak in ip_send_unicast_reply()
  ipv4: clean up cookie_v4_check()
  ipv4: share tcp_v4_save_options() with cookie_v4_check()
  ipv4: call __ip_options_echo() in cookie_v4_check()
  atm: simplify lanai.c by using module_pci_driver
  ...

Documentation/devicetree/bindings/net/sti-dwmac.txt

@@ -1,58 +1,65 @@
 STMicroelectronics SoC DWMAC glue layer controller
 
+This file documents differences between the core properties in
+Documentation/devicetree/bindings/net/stmmac.txt
+and what is needed on STi platforms to program the stmmac glue logic.
+
 The device node has following properties.
 
 Required properties:
- - compatible	: Can be "st,stih415-dwmac", "st,stih416-dwmac" or
-   "st,stid127-dwmac".
- - reg		: Offset of the glue configuration register map in system
+ - compatible	: Can be "st,stih415-dwmac", "st,stih416-dwmac",
+   "st,stih407-dwmac", "st,stid127-dwmac".
+ - reg : Offset of the glue configuration register map in system
    configuration regmap pointed by st,syscon property and size.
-
- - reg-names	: Should be "sti-ethconf".
-
- - st,syscon	: Should be phandle to system configuration node which
+ - st,syscon : Should be phandle to system configuration node which
    encompases this glue registers.
+ - st,gmac_en: this is to enable the gmac into a dedicated sysctl control
+   register available on STiH407 SoC.
+ - sti-ethconf: this is the gmac glue logic register to enable the GMAC,
+   select among the different modes and program the clk retiming.
+ - pinctrl-0: pin-control for all the MII mode supported.
 
- - st,tx-retime-src: On STi Parts for Giga bit speeds, 125Mhz clocks can be
-   wired up in from different sources. One via TXCLK pin and other via CLK_125
-   pin. This wiring is totally board dependent. However the retiming glue
-   logic should be configured accordingly. Possible values for this property
-
-	   "txclk" - if 125Mhz clock is wired up via txclk line.
-	   "clk_125" - if 125Mhz clock is wired up via clk_125 line.
-
-   This property is only valid for Giga bit setup( GMII, RGMII), and it is
-   un-used for non-giga bit (MII and RMII) setups. Also note that internal
-   clockgen can not generate stable 125Mhz clock.
-
- - st,ext-phyclk: This boolean property indicates who is generating the clock
-  for tx and rx. This property is only valid for RMII case where the clock can
-  be generated from the MAC or PHY.
-
- - clock-names: should be "sti-ethclk".
- - clocks: Should point to ethernet clockgen which can generate phyclk.
-
+Optional properties:
+ - resets : phandle pointing to the system reset controller with correct
+   reset line index for ethernet reset.
+ - st,ext-phyclk: valid only for RMII where PHY can generate 50MHz clock or
+   MAC can generate it.
+ - st,tx-retime-src: This specifies which clk is wired up to the mac for
+   retimeing tx lines. This is totally board dependent and can take one of the
+   posssible values from "txclk", "clk_125" or "clkgen".
+   If not passed, the internal clock will be used by default.
+ - sti-ethclk: this is the phy clock.
+ - sti-clkconf: this is an extra sysconfig register, available in new SoCs,
+   to program the clk retiming.
+ - st,gmac_en: to enable the GMAC, this only is present in some SoCs; e.g.
+   STiH407.
 
 Example:
 
-ethernet0: dwmac@fe810000 {
-	device_type 	= "network";
-	compatible	= "st,stih416-dwmac", "snps,dwmac", "snps,dwmac-3.710";
-	reg 		= <0xfe810000 0x8000>, <0x8bc 0x4>;
-	reg-names	= "stmmaceth", "sti-ethconf";
-	interrupts	= <0 133 0>, <0 134 0>, <0 135 0>;
-	interrupt-names	= "macirq", "eth_wake_irq", "eth_lpi";
-	phy-mode	= "mii";
+ethernet0: dwmac@9630000 {
+	device_type = "network";
+	status = "disabled";
+	compatible = "st,stih407-dwmac", "snps,dwmac", "snps,dwmac-3.710";
+	reg = <0x9630000 0x8000>, <0x80 0x4>;
+	reg-names = "stmmaceth", "sti-ethconf";
 
-	st,syscon	= <&syscfg_rear>;
+	st,syscon = <&syscfg_sbc_reg>;
+	st,gmac_en;
+	resets = <&softreset STIH407_ETH1_SOFTRESET>;
+	reset-names = "stmmaceth";
 
-	snps,pbl 	= <32>;
+	interrupts = <GIC_SPI 98 IRQ_TYPE_NONE>,
+		     <GIC_SPI 99 IRQ_TYPE_NONE>,
+		     <GIC_SPI 100 IRQ_TYPE_NONE>;
+	interrupt-names = "macirq", "eth_wake_irq", "eth_lpi";
+
+	snps,pbl = <32>;
 	snps,mixed-burst;
 
-	resets		= <&softreset STIH416_ETH0_SOFTRESET>;
-	reset-names	= "stmmaceth";
-	pinctrl-0	= <&pinctrl_mii0>;
-	pinctrl-names 	= "default";
-	clocks		= <&CLK_S_GMAC0_PHY>;
-	clock-names	= "stmmaceth";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_rgmii1>;
+
+	clock-names = "stmmaceth", "sti-ethclk";
+	clocks = <&CLK_S_C0_FLEXGEN CLK_EXT2F_A9>,
+		 <&CLK_S_C0_FLEXGEN CLK_ETH_PHY>;
 };

MAINTAINERS

@@ -564,7 +564,7 @@ L:	linux-alpha@vger.kernel.org
 F:	arch/alpha/
 
 ALTERA TRIPLE SPEED ETHERNET DRIVER
-M:	Vince Bridgers <vbridgers2013@gmail.com>
+M:	Vince Bridgers <vbridger@opensource.altera.com>
 L:	netdev@vger.kernel.org
 L:	nios2-dev@lists.rocketboards.org (moderated for non-subscribers)
 S:	Maintained

arch/arm64/boot/dts/apm-mustang.dts

@@ -41,6 +41,10 @@
 	status = "ok";
 };
 
+&sgenet0 {
+	status = "ok";
+};
+
 &xgenet {
 	status = "ok";
 };

arch/arm64/boot/dts/apm-storm.dtsi

@@ -176,6 +176,16 @@
 				clock-output-names = "menetclk";
 			};
 
+			sge0clk: sge0clk@1f21c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f21c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				csr-mask = <0x3>;
+				clock-output-names = "sge0clk";
+			};
+
 			xge0clk: xge0clk@1f61c000 {
 				compatible = "apm,xgene-device-clock";
 				#clock-cells = <1>;
@@ -611,6 +621,20 @@
 			};
 		};
 
+		sgenet0: ethernet@1f210000 {
+			compatible = "apm,xgene-enet";
+			status = "disabled";
+			reg = <0x0 0x1f210000 0x0 0x10000>,
+			      <0x0 0x1f200000 0x0 0X10000>,
+			      <0x0 0x1B000000 0x0 0X20000>;
+			reg-names = "enet_csr", "ring_csr", "ring_cmd";
+			interrupts = <0x0 0xA0 0x4>;
+			dma-coherent;
+			clocks = <&sge0clk 0>;
+			local-mac-address = [00 00 00 00 00 00];
+			phy-connection-type = "sgmii";
+		};
+
 		xgenet: ethernet@1f610000 {
 			compatible = "apm,xgene-enet";
 			status = "disabled";

arch/x86/net/bpf_jit_comp.c

@@ -182,12 +182,17 @@ struct jit_context {
 	bool seen_ld_abs;
 };
 
+/* maximum number of bytes emitted while JITing one eBPF insn */
+#define BPF_MAX_INSN_SIZE	128
+#define BPF_INSN_SAFETY		64
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		  int oldproglen, struct jit_context *ctx)
 {
 	struct bpf_insn *insn = bpf_prog->insnsi;
 	int insn_cnt = bpf_prog->len;
-	u8 temp[64];
+	bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0);
+	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
 	int i;
 	int proglen = 0;
 	u8 *prog = temp;
@@ -225,7 +230,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 	EMIT2(0x31, 0xc0); /* xor eax, eax */
 	EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */
 
-	if (ctx->seen_ld_abs) {
+	if (seen_ld_abs) {
 		/* r9d : skb->len - skb->data_len (headlen)
 		 * r10 : skb->data
 		 */
@@ -685,7 +690,7 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP | BPF_CALL:
 			func = (u8 *) __bpf_call_base + imm32;
 			jmp_offset = func - (image + addrs[i]);
-			if (ctx->seen_ld_abs) {
+			if (seen_ld_abs) {
 				EMIT2(0x41, 0x52); /* push %r10 */
 				EMIT2(0x41, 0x51); /* push %r9 */
 				/* need to adjust jmp offset, since
@@ -699,7 +704,7 @@ xadd:			if (is_imm8(insn->off))
 				return -EINVAL;
 			}
 			EMIT1_off32(0xE8, jmp_offset);
-			if (ctx->seen_ld_abs) {
+			if (seen_ld_abs) {
 				EMIT2(0x41, 0x59); /* pop %r9 */
 				EMIT2(0x41, 0x5A); /* pop %r10 */
 			}
@@ -804,7 +809,8 @@ emit_jmp:
 			goto common_load;
 		case BPF_LD | BPF_ABS | BPF_W:
 			func = CHOOSE_LOAD_FUNC(imm32, sk_load_word);
-common_load:		ctx->seen_ld_abs = true;
+common_load:
+			ctx->seen_ld_abs = seen_ld_abs = true;
 			jmp_offset = func - (image + addrs[i]);
 			if (!func || !is_simm32(jmp_offset)) {
 				pr_err("unsupported bpf func %d addr %p image %p\n",
@@ -878,6 +884,11 @@ common_load:		ctx->seen_ld_abs = true;
 		}
 
 		ilen = prog - temp;
+		if (ilen > BPF_MAX_INSN_SIZE) {
+			pr_err("bpf_jit_compile fatal insn size error\n");
+			return -EFAULT;
+		}
+
 		if (image) {
 			if (unlikely(proglen + ilen > oldproglen)) {
 				pr_err("bpf_jit_compile fatal error\n");
@@ -934,9 +945,11 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 			goto out;
 		}
 		if (image) {
-			if (proglen != oldproglen)
+			if (proglen != oldproglen) {
 				pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
 				       proglen, oldproglen);
+				goto out;
+			}
 			break;
 		}
 		if (proglen == oldproglen) {

drivers/atm/lanai.c

@@ -2614,27 +2614,7 @@ static struct pci_driver lanai_driver = {
 	.probe    = lanai_init_one,
 };
 
-static int __init lanai_module_init(void)
-{
-	int x;
-
-	x = pci_register_driver(&lanai_driver);
-	if (x != 0)
-		printk(KERN_ERR DEV_LABEL ": no adapter found\n");
-	return x;
-}
-
-static void __exit lanai_module_exit(void)
-{
-	/* We'll only get called when all the interfaces are already
-	 * gone, so there isn't much to do
-	 */
-	DPRINTK("cleanup_module()\n");
-	pci_unregister_driver(&lanai_driver);
-}
-
-module_init(lanai_module_init);
-module_exit(lanai_module_exit);
+module_pci_driver(lanai_driver);
 
 MODULE_AUTHOR("Mitchell Blank Jr <mitch@sfgoth.com>");
 MODULE_DESCRIPTION("Efficient Networks Speedstream 3010 driver");

drivers/isdn/capi/capidrv.c

@@ -506,7 +506,10 @@ static void send_message(capidrv_contr *card, _cmsg *cmsg)
 	struct sk_buff *skb;
 	size_t len;
 
-	capi_cmsg2message(cmsg, cmsg->buf);
+	if (capi_cmsg2message(cmsg, cmsg->buf)) {
+		printk(KERN_ERR "capidrv::send_message: parser failure\n");
+		return;
+	}
 	len = CAPIMSG_LEN(cmsg->buf);
 	skb = alloc_skb(len, GFP_ATOMIC);
 	if (!skb) {
@@ -1578,7 +1581,12 @@ static _cmsg s_cmsg;
 
 static void capidrv_recv_message(struct capi20_appl *ap, struct sk_buff *skb)
 {
-	capi_message2cmsg(&s_cmsg, skb->data);
+	if (capi_message2cmsg(&s_cmsg, skb->data)) {
+		printk(KERN_ERR "capidrv: applid=%d: received invalid message\n",
+		       ap->applid);
+		kfree_skb(skb);
+		return;
+	}
 	if (debugmode > 3) {
 		_cdebbuf *cdb = capi_cmsg2str(&s_cmsg);
 
@@ -1903,7 +1911,11 @@ static int capidrv_command(isdn_ctrl *c, capidrv_contr *card)
 				       NULL,	/* Useruserdata */
 				       NULL	/* Facilitydataarray */
 			);
-		capi_cmsg2message(&cmdcmsg, cmdcmsg.buf);
+		if (capi_cmsg2message(&cmdcmsg, cmdcmsg.buf)) {
+			printk(KERN_ERR "capidrv-%d: capidrv_command: parser failure\n",
+			       card->contrnr);
+			return -EINVAL;
+		}
 		plci_change_state(card, bchan->plcip, EV_PLCI_CONNECT_RESP);
 		send_message(card, &cmdcmsg);
 		return 0;
@@ -2090,7 +2102,11 @@ static int if_sendbuf(int id, int channel, int doack, struct sk_buff *skb)
 	if (capidrv_add_ack(nccip, datahandle, doack ? (int)skb->len : -1) < 0)
 		return 0;
 
-	capi_cmsg2message(&sendcmsg, sendcmsg.buf);
+	if (capi_cmsg2message(&sendcmsg, sendcmsg.buf)) {
+		printk(KERN_ERR "capidrv-%d: if_sendbuf: parser failure\n",
+		       card->contrnr);
+		return -EINVAL;
+	}
 	msglen = CAPIMSG_LEN(sendcmsg.buf);
 	if (skb_headroom(skb) < msglen) {
 		struct sk_buff *nskb = skb_realloc_headroom(skb, msglen);

drivers/isdn/capi/capiutil.c

@@ -207,9 +207,24 @@ static unsigned command_2_index(unsigned c, unsigned sc)
 		c = 0x9 + (c & 0x0f);
 	else if (c == 0x41)
 		c = 0x9 + 0x1;
+	if (c > 0x18)
+		c = 0x00;
 	return (sc & 3) * (0x9 + 0x9) + c;
 }
 
+/**
+ * capi_cmd2par() - find parameter string for CAPI 2.0 command/subcommand
+ * @cmd:	command number
+ * @subcmd:	subcommand number
+ *
+ * Return value: static string, NULL if command/subcommand unknown
+ */
+
+static unsigned char *capi_cmd2par(u8 cmd, u8 subcmd)
+{
+	return cpars[command_2_index(cmd, subcmd)];
+}
+
 /*-------------------------------------------------------*/
 #define TYP (cdef[cmsg->par[cmsg->p]].typ)
 #define OFF (((u8 *)cmsg) + cdef[cmsg->par[cmsg->p]].off)
@@ -302,7 +317,9 @@ unsigned capi_cmsg2message(_cmsg *cmsg, u8 *msg)
 	cmsg->m = msg;
 	cmsg->l = 8;
 	cmsg->p = 0;
-	cmsg->par = cpars[command_2_index(cmsg->Command, cmsg->Subcommand)];
+	cmsg->par = capi_cmd2par(cmsg->Command, cmsg->Subcommand);
+	if (!cmsg->par)
+		return 1;	/* invalid command/subcommand */
 
 	pars_2_message(cmsg);
 
@@ -375,7 +392,9 @@ unsigned capi_message2cmsg(_cmsg *cmsg, u8 *msg)
 	cmsg->p = 0;
 	byteTRcpy(cmsg->m + 4, &cmsg->Command);
 	byteTRcpy(cmsg->m + 5, &cmsg->Subcommand);
-	cmsg->par = cpars[command_2_index(cmsg->Command, cmsg->Subcommand)];
+	cmsg->par = capi_cmd2par(cmsg->Command, cmsg->Subcommand);
+	if (!cmsg->par)
+		return 1;	/* invalid command/subcommand */
 
 	message_2_pars(cmsg);
 
@@ -470,12 +489,17 @@ static char *mnames[] =
  * @cmd:	command number
  * @subcmd:	subcommand number
  *
- * Return value: static string, NULL if command/subcommand unknown
+ * Return value: static string
  */
 
 char *capi_cmd2str(u8 cmd, u8 subcmd)
 {
-	return mnames[command_2_index(cmd, subcmd)];
+	char *result;
+
+	result = mnames[command_2_index(cmd, subcmd)];
+	if (result == NULL)
+		result = "INVALID_COMMAND";
+	return result;
 }
 
 
@@ -625,6 +649,9 @@ static _cdebbuf *printstruct(_cdebbuf *cdb, u8 *m)
 
 static _cdebbuf *protocol_message_2_pars(_cdebbuf *cdb, _cmsg *cmsg, int level)
 {
+	if (!cmsg->par)
+		return NULL;	/* invalid command/subcommand */
+
 	for (; TYP != _CEND; cmsg->p++) {
 		int slen = 29 + 3 - level;
 		int i;
@@ -759,10 +786,10 @@ _cdebbuf *capi_message2str(u8 *msg)
 	cmsg->p = 0;
 	byteTRcpy(cmsg->m + 4, &cmsg->Command);
 	byteTRcpy(cmsg->m + 5, &cmsg->Subcommand);
-	cmsg->par = cpars[command_2_index(cmsg->Command, cmsg->Subcommand)];
+	cmsg->par = capi_cmd2par(cmsg->Command, cmsg->Subcommand);
 
 	cdb = bufprint(cdb, "%-26s ID=%03d #0x%04x LEN=%04d\n",
-		       mnames[command_2_index(cmsg->Command, cmsg->Subcommand)],
+		       capi_cmd2str(cmsg->Command, cmsg->Subcommand),
 		       ((unsigned short *) msg)[1],
 		       ((unsigned short *) msg)[3],
 		       ((unsigned short *) msg)[0]);
@@ -796,7 +823,7 @@ _cdebbuf *capi_cmsg2str(_cmsg *cmsg)
 	cmsg->l = 8;
 	cmsg->p = 0;
 	cdb = bufprint(cdb, "%s ID=%03d #0x%04x LEN=%04d\n",
-		       mnames[command_2_index(cmsg->Command, cmsg->Subcommand)],
+		       capi_cmd2str(cmsg->Command, cmsg->Subcommand),
 		       ((u16 *) cmsg->m)[1],
 		       ((u16 *) cmsg->m)[3],
 		       ((u16 *) cmsg->m)[0]);

drivers/isdn/capi/kcapi.c

@@ -1184,7 +1184,7 @@ static int old_capi_manufacturer(unsigned int cmd, void __user *data)
  * Return value: CAPI result code
  */
 
-int capi20_manufacturer(unsigned int cmd, void __user *data)
+int capi20_manufacturer(unsigned long cmd, void __user *data)
 {
 	struct capi_ctr *ctr;
 	int retval;
@@ -1259,7 +1259,7 @@ int capi20_manufacturer(unsigned int cmd, void __user *data)
 	}
 
 	default:
-		printk(KERN_ERR "kcapi: manufacturer command %d unknown.\n",
+		printk(KERN_ERR "kcapi: manufacturer command %lu unknown.\n",
 		       cmd);
 		break;
 

drivers/isdn/gigaset/capi.c

@@ -250,6 +250,8 @@ static inline void dump_rawmsg(enum debuglevel level, const char *tag,
 	l -= 12;
 	if (l <= 0)
 		return;
+	if (l > 64)
+		l = 64; /* arbitrary limit */
 	dbgline = kmalloc(3 * l, GFP_ATOMIC);
 	if (!dbgline)
 		return;
@@ -645,7 +647,13 @@ int gigaset_isdn_icall(struct at_state_t *at_state)
 					__func__);
 				break;
 			}
-			capi_cmsg2message(&iif->hcmsg, __skb_put(skb, msgsize));
+			if (capi_cmsg2message(&iif->hcmsg,
+					      __skb_put(skb, msgsize))) {
+				dev_err(cs->dev, "%s: message parser failure\n",
+					__func__);
+				dev_kfree_skb_any(skb);
+				break;
+			}
 			dump_cmsg(DEBUG_CMD, __func__, &iif->hcmsg);
 
 			/* add to listeners on this B channel, update state */
@@ -691,7 +699,12 @@ static void send_disconnect_ind(struct bc_state *bcs,
 		dev_err(cs->dev, "%s: out of memory\n", __func__);
 		return;
 	}
-	capi_cmsg2message(&iif->hcmsg, __skb_put(skb, CAPI_DISCONNECT_IND_LEN));
+	if (capi_cmsg2message(&iif->hcmsg,
+			      __skb_put(skb, CAPI_DISCONNECT_IND_LEN))) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, &iif->hcmsg);
 	capi_ctr_handle_message(&iif->ctr, ap->id, skb);
 }
@@ -721,8 +734,12 @@ static void send_disconnect_b3_ind(struct bc_state *bcs,
 		dev_err(cs->dev, "%s: out of memory\n", __func__);
 		return;
 	}
-	capi_cmsg2message(&iif->hcmsg,
-			  __skb_put(skb, CAPI_DISCONNECT_B3_IND_BASELEN));
+	if (capi_cmsg2message(&iif->hcmsg,
+			  __skb_put(skb, CAPI_DISCONNECT_B3_IND_BASELEN))) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, &iif->hcmsg);
 	capi_ctr_handle_message(&iif->ctr, ap->id, skb);
 }
@@ -787,7 +804,11 @@ void gigaset_isdn_connD(struct bc_state *bcs)
 		dev_err(cs->dev, "%s: out of memory\n", __func__);
 		return;
 	}
-	capi_cmsg2message(&iif->hcmsg, __skb_put(skb, msgsize));
+	if (capi_cmsg2message(&iif->hcmsg, __skb_put(skb, msgsize))) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, &iif->hcmsg);
 	capi_ctr_handle_message(&iif->ctr, ap->id, skb);
 }
@@ -887,7 +908,11 @@ void gigaset_isdn_connB(struct bc_state *bcs)
 		dev_err(cs->dev, "%s: out of memory\n", __func__);
 		return;
 	}
-	capi_cmsg2message(&iif->hcmsg, __skb_put(skb, msgsize));
+	if (capi_cmsg2message(&iif->hcmsg, __skb_put(skb, msgsize))) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, &iif->hcmsg);
 	capi_ctr_handle_message(&iif->ctr, ap->id, skb);
 }
@@ -1094,13 +1119,19 @@ static void send_conf(struct gigaset_capi_ctr *iif,
 		      struct sk_buff *skb,
 		      u16 info)
 {
+	struct cardstate *cs = iif->ctr.driverdata;
+
 	/*
 	 * _CONF replies always only have NCCI and Info parameters
 	 * so they'll fit into the _REQ message skb
 	 */
 	capi_cmsg_answer(&iif->acmsg);
 	iif->acmsg.Info = info;
-	capi_cmsg2message(&iif->acmsg, skb->data);
+	if (capi_cmsg2message(&iif->acmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	__skb_trim(skb, CAPI_STDCONF_LEN);
 	dump_cmsg(DEBUG_CMD, __func__, &iif->acmsg);
 	capi_ctr_handle_message(&iif->ctr, ap->id, skb);
@@ -1122,7 +1153,11 @@ static void do_facility_req(struct gigaset_capi_ctr *iif,
 	static u8 confparam[10];	/* max. 9 octets + length byte */
 
 	/* decode message */
-	capi_message2cmsg(cmsg, skb->data);
+	if (capi_message2cmsg(cmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, cmsg);
 
 	/*
@@ -1180,6 +1215,7 @@ static void do_facility_req(struct gigaset_capi_ctr *iif,
 				confparam[3] = 2;	/* length */
 				capimsg_setu16(confparam, 4,
 					       CapiSupplementaryServiceNotSupported);
+				break;
 			}
 			info = CapiSuccess;
 			confparam[3] = 2;	/* length */
@@ -1220,6 +1256,7 @@ static void do_facility_req(struct gigaset_capi_ctr *iif,
 	}
 
 	/* send FACILITY_CONF with given Info and confirmation parameter */
+	dev_kfree_skb_any(skb);
 	capi_cmsg_answer(cmsg);
 	cmsg->Info = info;
 	cmsg->FacilityConfirmationParameter = confparam;
@@ -1229,7 +1266,11 @@ static void do_facility_req(struct gigaset_capi_ctr *iif,
 		dev_err(cs->dev, "%s: out of memory\n", __func__);
 		return;
 	}
-	capi_cmsg2message(cmsg, __skb_put(cskb, msgsize));
+	if (capi_cmsg2message(cmsg, __skb_put(cskb, msgsize))) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(cskb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, cmsg);
 	capi_ctr_handle_message(&iif->ctr, ap->id, cskb);
 }
@@ -1243,8 +1284,14 @@ static void do_listen_req(struct gigaset_capi_ctr *iif,
 			  struct gigaset_capi_appl *ap,
 			  struct sk_buff *skb)
 {
+	struct cardstate *cs = iif->ctr.driverdata;
+
 	/* decode message */
-	capi_message2cmsg(&iif->acmsg, skb->data);
+	if (capi_message2cmsg(&iif->acmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, &iif->acmsg);
 
 	/* store listening parameters */
@@ -1261,8 +1308,14 @@ static void do_alert_req(struct gigaset_capi_ctr *iif,
 			 struct gigaset_capi_appl *ap,
 			 struct sk_buff *skb)
 {
+	struct cardstate *cs = iif->ctr.driverdata;
+
 	/* decode message */
-	capi_message2cmsg(&iif->acmsg, skb->data);
+	if (capi_message2cmsg(&iif->acmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, &iif->acmsg);
 	send_conf(iif, ap, skb, CapiAlertAlreadySent);
 }
@@ -1287,7 +1340,11 @@ static void do_connect_req(struct gigaset_capi_ctr *iif,
 	u16 info;
 
 	/* decode message */
-	capi_message2cmsg(cmsg, skb->data);
+	if (capi_message2cmsg(cmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, cmsg);
 
 	/* get free B channel & construct PLCI */
@@ -1574,7 +1631,11 @@ static void do_connect_resp(struct gigaset_capi_ctr *iif,
 	int channel;
 
 	/* decode message */
-	capi_message2cmsg(cmsg, skb->data);
+	if (capi_message2cmsg(cmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, cmsg);
 	dev_kfree_skb_any(skb);
 
@@ -1740,7 +1801,11 @@ static void do_connect_b3_req(struct gigaset_capi_ctr *iif,
 	int channel;
 
 	/* decode message */
-	capi_message2cmsg(cmsg, skb->data);
+	if (capi_message2cmsg(cmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, cmsg);
 
 	/* extract and check channel number from PLCI */
@@ -1785,7 +1850,11 @@ static void do_connect_b3_resp(struct gigaset_capi_ctr *iif,
 	u8 command;
 
 	/* decode message */
-	capi_message2cmsg(cmsg, skb->data);
+	if (capi_message2cmsg(cmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, cmsg);
 
 	/* extract and check channel number and NCCI */
@@ -1825,7 +1894,11 @@ static void do_connect_b3_resp(struct gigaset_capi_ctr *iif,
 	capi_cmsg_header(cmsg, ap->id, command, CAPI_IND,
 			 ap->nextMessageNumber++, cmsg->adr.adrNCCI);
 	__skb_trim(skb, msgsize);
-	capi_cmsg2message(cmsg, skb->data);
+	if (capi_cmsg2message(cmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, cmsg);
 	capi_ctr_handle_message(&iif->ctr, ap->id, skb);
 }
@@ -1847,7 +1920,11 @@ static void do_disconnect_req(struct gigaset_capi_ctr *iif,
 	int channel;
 
 	/* decode message */
-	capi_message2cmsg(cmsg, skb->data);
+	if (capi_message2cmsg(cmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, cmsg);
 
 	/* extract and check channel number from PLCI */
@@ -1903,8 +1980,14 @@ static void do_disconnect_req(struct gigaset_capi_ctr *iif,
 			kfree(b3cmsg);
 			return;
 		}
-		capi_cmsg2message(b3cmsg,
-				  __skb_put(b3skb, CAPI_DISCONNECT_B3_IND_BASELEN));
+		if (capi_cmsg2message(b3cmsg,
+				      __skb_put(b3skb, CAPI_DISCONNECT_B3_IND_BASELEN))) {
+			dev_err(cs->dev, "%s: message parser failure\n",
+				__func__);
+			kfree(b3cmsg);
+			dev_kfree_skb_any(b3skb);
+			return;
+		}
 		dump_cmsg(DEBUG_CMD, __func__, b3cmsg);
 		kfree(b3cmsg);
 		capi_ctr_handle_message(&iif->ctr, ap->id, b3skb);
@@ -1935,7 +2018,11 @@ static void do_disconnect_b3_req(struct gigaset_capi_ctr *iif,
 	int channel;
 
 	/* decode message */
-	capi_message2cmsg(cmsg, skb->data);
+	if (capi_message2cmsg(cmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, cmsg);
 
 	/* extract and check channel number and NCCI */
@@ -2052,8 +2139,14 @@ static void do_reset_b3_req(struct gigaset_capi_ctr *iif,
 			    struct gigaset_capi_appl *ap,
 			    struct sk_buff *skb)
 {
+	struct cardstate *cs = iif->ctr.driverdata;
+
 	/* decode message */
-	capi_message2cmsg(&iif->acmsg, skb->data);
+	if (capi_message2cmsg(&iif->acmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, &iif->acmsg);
 	send_conf(iif, ap, skb,
 		  CapiResetProcedureNotSupportedByCurrentProtocol);
@@ -2066,8 +2159,14 @@ static void do_unsupported(struct gigaset_capi_ctr *iif,
 			   struct gigaset_capi_appl *ap,
 			   struct sk_buff *skb)
 {
+	struct cardstate *cs = iif->ctr.driverdata;
+
 	/* decode message */
-	capi_message2cmsg(&iif->acmsg, skb->data);
+	if (capi_message2cmsg(&iif->acmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, &iif->acmsg);
 	send_conf(iif, ap, skb, CapiMessageNotSupportedInCurrentState);
 }
@@ -2079,8 +2178,14 @@ static void do_nothing(struct gigaset_capi_ctr *iif,
 		       struct gigaset_capi_appl *ap,
 		       struct sk_buff *skb)
 {
+	struct cardstate *cs = iif->ctr.driverdata;
+
 	/* decode message */
-	capi_message2cmsg(&iif->acmsg, skb->data);
+	if (capi_message2cmsg(&iif->acmsg, skb->data)) {
+		dev_err(cs->dev, "%s: message parser failure\n", __func__);
+		dev_kfree_skb_any(skb);
+		return;
+	}
 	dump_cmsg(DEBUG_CMD, __func__, &iif->acmsg);
 	dev_kfree_skb_any(skb);
 }
@@ -2357,7 +2462,7 @@ int gigaset_isdn_regdev(struct cardstate *cs, const char *isdnid)
 	struct gigaset_capi_ctr *iif;
 	int rc;
 
-	iif = kmalloc(sizeof(*iif), GFP_KERNEL);
+	iif = kzalloc(sizeof(*iif), GFP_KERNEL);
 	if (!iif) {
 		pr_err("%s: out of memory\n", __func__);
 		return -ENOMEM;
@@ -2366,7 +2471,7 @@ int gigaset_isdn_regdev(struct cardstate *cs, const char *isdnid)
 	/* prepare controller structure */
 	iif->ctr.owner         = THIS_MODULE;
 	iif->ctr.driverdata    = cs;
-	strncpy(iif->ctr.name, isdnid, sizeof(iif->ctr.name));
+	strncpy(iif->ctr.name, isdnid, sizeof(iif->ctr.name) - 1);
 	iif->ctr.driver_name   = "gigaset";
 	iif->ctr.load_firmware = NULL;
 	iif->ctr.reset_ctr     = NULL;

drivers/isdn/gigaset/ev-layer.c

@@ -604,14 +604,14 @@ void gigaset_handle_modem_response(struct cardstate *cs)
 }
 EXPORT_SYMBOL_GPL(gigaset_handle_modem_response);
 
-/* disconnect
+/* disconnect_nobc
  * process closing of connection associated with given AT state structure
+ * without B channel
  */
-static void disconnect(struct at_state_t **at_state_p)
+static void disconnect_nobc(struct at_state_t **at_state_p,
+			    struct cardstate *cs)
 {
 	unsigned long flags;
-	struct bc_state *bcs = (*at_state_p)->bcs;
-	struct cardstate *cs = (*at_state_p)->cs;
 
 	spin_lock_irqsave(&cs->lock, flags);
 	++(*at_state_p)->seq_index;
@@ -622,23 +622,44 @@ static void disconnect(struct at_state_t **at_state_p)
 		gig_dbg(DEBUG_EVENT, "Scheduling PC_UMMODE");
 		cs->commands_pending = 1;
 	}
-	spin_unlock_irqrestore(&cs->lock, flags);
 
-	if (bcs) {
-		/* B channel assigned: invoke hardware specific handler */
-		cs->ops->close_bchannel(bcs);
-		/* notify LL */
-		if (bcs->chstate & (CHS_D_UP | CHS_NOTIFY_LL)) {
-			bcs->chstate &= ~(CHS_D_UP | CHS_NOTIFY_LL);
-			gigaset_isdn_hupD(bcs);
-		}
-	} else {
-		/* no B channel assigned: just deallocate */
-		spin_lock_irqsave(&cs->lock, flags);
+	/* check for and deallocate temporary AT state */
+	if (!list_empty(&(*at_state_p)->list)) {
 		list_del(&(*at_state_p)->list);
 		kfree(*at_state_p);
 		*at_state_p = NULL;
-		spin_unlock_irqrestore(&cs->lock, flags);
+	}
+
+	spin_unlock_irqrestore(&cs->lock, flags);
+}
+
+/* disconnect_bc
+ * process closing of connection associated with given AT state structure
+ * and B channel
+ */
+static void disconnect_bc(struct at_state_t *at_state,
+			  struct cardstate *cs, struct bc_state *bcs)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cs->lock, flags);
+	++at_state->seq_index;
+
+	/* revert to selected idle mode */
+	if (!cs->cidmode) {
+		cs->at_state.pending_commands |= PC_UMMODE;
+		gig_dbg(DEBUG_EVENT, "Scheduling PC_UMMODE");
+		cs->commands_pending = 1;
+	}
+	spin_unlock_irqrestore(&cs->lock, flags);
+
+	/* invoke hardware specific handler */
+	cs->ops->close_bchannel(bcs);
+
+	/* notify LL */
+	if (bcs->chstate & (CHS_D_UP | CHS_NOTIFY_LL)) {
+		bcs->chstate &= ~(CHS_D_UP | CHS_NOTIFY_LL);
+		gigaset_isdn_hupD(bcs);
 	}
 }
 
@@ -646,7 +667,7 @@ static void disconnect(struct at_state_t **at_state_p)
  * get a free AT state structure: either one of those associated with the
  * B channels of the Gigaset device, or if none of those is available,
  * a newly allocated one with bcs=NULL
- * The structure should be freed by calling disconnect() after use.
+ * The structure should be freed by calling disconnect_nobc() after use.
  */
 static inline struct at_state_t *get_free_channel(struct cardstate *cs,
 						  int cid)
@@ -1057,7 +1078,7 @@ static void do_action(int action, struct cardstate *cs,
 		      struct event_t *ev)
 {
 	struct at_state_t *at_state = *p_at_state;
-	struct at_state_t *at_state2;
+	struct bc_state *bcs2;
 	unsigned long flags;
 
 	int channel;
@@ -1156,8 +1177,8 @@ static void do_action(int action, struct cardstate *cs,
 		break;
 	case ACT_RING:
 		/* get fresh AT state structure for new CID */
-		at_state2 = get_free_channel(cs, ev->parameter);
-		if (!at_state2) {
+		at_state = get_free_channel(cs, ev->parameter);
+		if (!at_state) {
 			dev_warn(cs->dev,
 				 "RING ignored: could not allocate channel structure\n");
 			break;
@@ -1166,16 +1187,16 @@ static void do_action(int action, struct cardstate *cs,
 		/* initialize AT state structure
 		 * note that bcs may be NULL if no B channel is free
 		 */
-		at_state2->ConState = 700;
+		at_state->ConState = 700;
 		for (i = 0; i < STR_NUM; ++i) {
-			kfree(at_state2->str_var[i]);
-			at_state2->str_var[i] = NULL;
+			kfree(at_state->str_var[i]);
+			at_state->str_var[i] = NULL;
 		}
-		at_state2->int_var[VAR_ZCTP] = -1;
+		at_state->int_var[VAR_ZCTP] = -1;
 
 		spin_lock_irqsave(&cs->lock, flags);
-		at_state2->timer_expires = RING_TIMEOUT;
-		at_state2->timer_active = 1;
+		at_state->timer_expires = RING_TIMEOUT;
+		at_state->timer_active = 1;
 		spin_unlock_irqrestore(&cs->lock, flags);
 		break;
 	case ACT_ICALL:
@@ -1213,14 +1234,17 @@ static void do_action(int action, struct cardstate *cs,
 	case ACT_DISCONNECT:
 		cs->cur_at_seq = SEQ_NONE;
 		at_state->cid = -1;
-		if (bcs && cs->onechannel && cs->dle) {
+		if (!bcs) {
+			disconnect_nobc(p_at_state, cs);
+		} else if (cs->onechannel && cs->dle) {
 			/* Check for other open channels not needed:
 			 * DLE only used for M10x with one B channel.
 			 */
 			at_state->pending_commands |= PC_DLE0;
 			cs->commands_pending = 1;
-		} else
-			disconnect(p_at_state);
+		} else {
+			disconnect_bc(at_state, cs, bcs);
+		}
 		break;
 	case ACT_FAKEDLE0:
 		at_state->int_var[VAR_ZDLE] = 0;
@@ -1228,25 +1252,27 @@ static void do_action(int action, struct cardstate *cs,
 		/* fall through */
 	case ACT_DLE0:
 		cs->cur_at_seq = SEQ_NONE;
-		at_state2 = &cs->bcs[cs->curchannel].at_state;
-		disconnect(&at_state2);
+		bcs2 = cs->bcs + cs->curchannel;
+		disconnect_bc(&bcs2->at_state, cs, bcs2);
 		break;
 	case ACT_ABORTHUP:
 		cs->cur_at_seq = SEQ_NONE;
 		dev_warn(cs->dev, "Could not hang up.\n");
 		at_state->cid = -1;
-		if (bcs && cs->onechannel)
+		if (!bcs)
+			disconnect_nobc(p_at_state, cs);
+		else if (cs->onechannel)
 			at_state->pending_commands |= PC_DLE0;
 		else
-			disconnect(p_at_state);
+			disconnect_bc(at_state, cs, bcs);
 		schedule_init(cs, MS_RECOVER);
 		break;
 	case ACT_FAILDLE0:
 		cs->cur_at_seq = SEQ_NONE;
 		dev_warn(cs->dev, "Error leaving DLE mode.\n");
 		cs->dle = 0;
-		at_state2 = &cs->bcs[cs->curchannel].at_state;
-		disconnect(&at_state2);
+		bcs2 = cs->bcs + cs->curchannel;
+		disconnect_bc(&bcs2->at_state, cs, bcs2);
 		schedule_init(cs, MS_RECOVER);
 		break;
 	case ACT_FAILDLE1:
@@ -1275,14 +1301,14 @@ static void do_action(int action, struct cardstate *cs,
 		if (reinit_and_retry(cs, channel) < 0) {
 			dev_warn(cs->dev,
 				 "Could not get a call ID. Cannot dial.\n");
-			at_state2 = &cs->bcs[channel].at_state;
-			disconnect(&at_state2);
+			bcs2 = cs->bcs + channel;
+			disconnect_bc(&bcs2->at_state, cs, bcs2);
 		}
 		break;
 	case ACT_ABORTCID:
 		cs->cur_at_seq = SEQ_NONE;
-		at_state2 = &cs->bcs[cs->curchannel].at_state;
-		disconnect(&at_state2);
+		bcs2 = cs->bcs + cs->curchannel;
+		disconnect_bc(&bcs2->at_state, cs, bcs2);
 		break;
 
 	case ACT_DIALING:
@@ -1291,7 +1317,10 @@ static void do_action(int action, struct cardstate *cs,
 		break;
 
 	case ACT_ABORTACCEPT:	/* hangup/error/timeout during ICALL procssng */
-		disconnect(p_at_state);
+		if (bcs)
+			disconnect_bc(at_state, cs, bcs);
+		else
+			disconnect_nobc(p_at_state, cs);
 		break;
 
 	case ACT_ABORTDIAL:	/* error/timeout during dial preparation */
@@ -1380,6 +1409,11 @@ static void do_action(int action, struct cardstate *cs,
 	/* events from the LL */
 
 	case ACT_DIAL:
+		if (!ev->ptr) {
+			*p_genresp = 1;
+			*p_resp_code = RSP_ERROR;
+			break;
+		}
 		start_dial(at_state, ev->ptr, ev->parameter);
 		break;
 	case ACT_ACCEPT:

drivers/isdn/gigaset/usb-gigaset.c

@@ -497,6 +497,7 @@ static int send_cb(struct cardstate *cs, struct cmdbuf_t *cb)
 static int gigaset_write_cmd(struct cardstate *cs, struct cmdbuf_t *cb)
 {
 	unsigned long flags;
+	int len;
 
 	gigaset_dbg_buffer(cs->mstate != MS_LOCKED ?
 			   DEBUG_TRANSCMD : DEBUG_LOCKCMD,
@@ -515,10 +516,11 @@ static int gigaset_write_cmd(struct cardstate *cs, struct cmdbuf_t *cb)
 	spin_unlock_irqrestore(&cs->cmdlock, flags);
 
 	spin_lock_irqsave(&cs->lock, flags);
+	len = cb->len;
 	if (cs->connected)
 		tasklet_schedule(&cs->write_tasklet);
 	spin_unlock_irqrestore(&cs->lock, flags);
-	return cb->len;
+	return len;
 }
 
 static int gigaset_write_room(struct cardstate *cs)

drivers/net/dsa/mv88e6060.c

@@ -21,8 +21,12 @@
 
 static int reg_read(struct dsa_switch *ds, int addr, int reg)
 {
-	return mdiobus_read(to_mii_bus(ds->master_dev),
-			    ds->pd->sw_addr + addr, reg);
+	struct mii_bus *bus = dsa_host_dev_to_mii_bus(ds->master_dev);
+
+	if (bus == NULL)
+		return -EINVAL;
+
+	return mdiobus_read(bus, ds->pd->sw_addr + addr, reg);
 }
 
 #define REG_READ(addr, reg)					\
@@ -38,8 +42,12 @@ static int reg_read(struct dsa_switch *ds, int addr, int reg)
 
 static int reg_write(struct dsa_switch *ds, int addr, int reg, u16 val)
 {
-	return mdiobus_write(to_mii_bus(ds->master_dev),
-			     ds->pd->sw_addr + addr, reg, val);
+	struct mii_bus *bus = dsa_host_dev_to_mii_bus(ds->master_dev);
+
+	if (bus == NULL)
+		return -EINVAL;
+
+	return mdiobus_write(bus, ds->pd->sw_addr + addr, reg, val);
 }
 
 #define REG_WRITE(addr, reg, val)				\

drivers/net/dsa/mv88e6171.c

@@ -206,7 +206,7 @@ static int mv88e6171_setup_port(struct dsa_switch *ds, int p)
 	 */
 	val = 0x0433;
 	if (dsa_is_cpu_port(ds, p)) {
-		if (ds->dst->tag_protocol == htons(ETH_P_EDSA))
+		if (ds->dst->tag_protocol == DSA_TAG_PROTO_EDSA)
 			val |= 0x3300;
 		else
 			val |= 0x0100;

drivers/net/dsa/mv88e6xxx.c

@@ -75,11 +75,14 @@ int __mv88e6xxx_reg_read(struct mii_bus *bus, int sw_addr, int addr, int reg)
 int mv88e6xxx_reg_read(struct dsa_switch *ds, int addr, int reg)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mii_bus *bus = dsa_host_dev_to_mii_bus(ds->master_dev);
 	int ret;
 
+	if (bus == NULL)
+		return -EINVAL;
+
 	mutex_lock(&ps->smi_mutex);
-	ret = __mv88e6xxx_reg_read(to_mii_bus(ds->master_dev),
-				   ds->pd->sw_addr, addr, reg);
+	ret = __mv88e6xxx_reg_read(bus, ds->pd->sw_addr, addr, reg);
 	mutex_unlock(&ps->smi_mutex);
 
 	return ret;
@@ -119,11 +122,14 @@ int __mv88e6xxx_reg_write(struct mii_bus *bus, int sw_addr, int addr,
 int mv88e6xxx_reg_write(struct dsa_switch *ds, int addr, int reg, u16 val)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mii_bus *bus = dsa_host_dev_to_mii_bus(ds->master_dev);
 	int ret;
 
+	if (bus == NULL)
+		return -EINVAL;
+
 	mutex_lock(&ps->smi_mutex);
-	ret = __mv88e6xxx_reg_write(to_mii_bus(ds->master_dev),
-				    ds->pd->sw_addr, addr, reg, val);
+	ret = __mv88e6xxx_reg_write(bus, ds->pd->sw_addr, addr, reg, val);
 	mutex_unlock(&ps->smi_mutex);
 
 	return ret;

drivers/net/ethernet/apm/xgene/Makefile

@@ -2,6 +2,6 @@
 # Makefile for APM X-Gene Ethernet Driver.
 #
 
-xgene-enet-objs := xgene_enet_hw.o xgene_enet_xgmac.o \
+xgene-enet-objs := xgene_enet_hw.o xgene_enet_sgmac.o xgene_enet_xgmac.o \
 		   xgene_enet_main.o xgene_enet_ethtool.o
 obj-$(CONFIG_NET_XGENE) += xgene-enet.o

drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c

@@ -64,16 +64,25 @@ static int xgene_get_settings(struct net_device *ndev, struct ethtool_cmd *cmd)
 			return -ENODEV;
 
 		return phy_ethtool_gset(phydev, cmd);
+	} else if (pdata->phy_mode == PHY_INTERFACE_MODE_SGMII) {
+		cmd->supported = SUPPORTED_1000baseT_Full |
+				 SUPPORTED_Autoneg | SUPPORTED_MII;
+		cmd->advertising = cmd->supported;
+		ethtool_cmd_speed_set(cmd, SPEED_1000);
+		cmd->duplex = DUPLEX_FULL;
+		cmd->port = PORT_MII;
+		cmd->transceiver = XCVR_INTERNAL;
+		cmd->autoneg = AUTONEG_ENABLE;
+	} else {
+		cmd->supported = SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE;
+		cmd->advertising = cmd->supported;
+		ethtool_cmd_speed_set(cmd, SPEED_10000);
+		cmd->duplex = DUPLEX_FULL;
+		cmd->port = PORT_FIBRE;
+		cmd->transceiver = XCVR_INTERNAL;
+		cmd->autoneg = AUTONEG_DISABLE;
 	}
 
-	cmd->supported = SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE;
-	cmd->advertising = cmd->supported;
-	ethtool_cmd_speed_set(cmd, SPEED_10000);
-	cmd->duplex = DUPLEX_FULL;
-	cmd->port = PORT_FIBRE;
-	cmd->transceiver = XCVR_EXTERNAL;
-	cmd->autoneg = AUTONEG_DISABLE;
-
 	return 0;
 }
 

drivers/net/ethernet/apm/xgene/xgene_enet_hw.c

@@ -410,7 +410,6 @@ static void xgene_gmac_set_mac_addr(struct xgene_enet_pdata *pdata)
 	addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) |
 		(dev_addr[1] << 8) | dev_addr[0];
 	addr1 = (dev_addr[5] << 24) | (dev_addr[4] << 16);
-	addr1 |= pdata->phy_addr & 0xFFFF;
 
 	xgene_enet_wr_mcx_mac(pdata, STATION_ADDR0_ADDR, addr0);
 	xgene_enet_wr_mcx_mac(pdata, STATION_ADDR1_ADDR, addr1);

drivers/net/ethernet/apm/xgene/xgene_enet_hw.h

@@ -44,6 +44,7 @@ static inline u32 xgene_get_bits(u32 val, u32 start, u32 end)
 
 enum xgene_enet_rm {
 	RM0,
+	RM1,
 	RM3 = 3
 };
 
@@ -143,6 +144,8 @@ enum xgene_enet_rm {
 #define CFG_CLE_FPSEL0_SET(dst, val)		xgene_set_bits(dst, val, 16, 4)
 #define CFG_MACMODE_SET(dst, val)		xgene_set_bits(dst, val, 18, 2)
 #define CFG_WAITASYNCRD_SET(dst, val)		xgene_set_bits(dst, val, 0, 16)
+#define CFG_CLE_DSTQID0(val)		(val & GENMASK(11, 0))
+#define CFG_CLE_FPSEL0(val)		((val << 16) & GENMASK(19, 16))
 #define ICM_CONFIG0_REG_0_ADDR		0x0400
 #define ICM_CONFIG2_REG_0_ADDR		0x0410
 #define RX_DV_GATE_REG_0_ADDR		0x05fc
@@ -179,7 +182,6 @@ enum xgene_enet_rm {
 #define TUND_ADDR			0x4a
 
 #define TSO_IPPROTO_TCP			1
-#define	FULL_DUPLEX			2
 
 #define USERINFO_POS			0
 #define USERINFO_LEN			32

drivers/net/ethernet/apm/xgene/xgene_enet_main.c

@@ -21,6 +21,7 @@
 
 #include "xgene_enet_main.h"
 #include "xgene_enet_hw.h"
+#include "xgene_enet_sgmac.h"
 #include "xgene_enet_xgmac.h"
 
 static void xgene_enet_init_bufpool(struct xgene_enet_desc_ring *buf_pool)
@@ -813,6 +814,7 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata)
 		return pdata->phy_mode;
 	}
 	if (pdata->phy_mode != PHY_INTERFACE_MODE_RGMII &&
+	    pdata->phy_mode != PHY_INTERFACE_MODE_SGMII &&
 	    pdata->phy_mode != PHY_INTERFACE_MODE_XGMII) {
 		dev_err(dev, "Incorrect phy-connection-type specified\n");
 		return -ENODEV;
@@ -830,14 +832,13 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata)
 	pdata->eth_csr_addr = base_addr + BLOCK_ETH_CSR_OFFSET;
 	pdata->eth_ring_if_addr = base_addr + BLOCK_ETH_RING_IF_OFFSET;
 	pdata->eth_diag_csr_addr = base_addr + BLOCK_ETH_DIAG_CSR_OFFSET;
-	if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII) {
+	if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII ||
+	    pdata->phy_mode == PHY_INTERFACE_MODE_SGMII) {
 		pdata->mcx_mac_addr = base_addr + BLOCK_ETH_MAC_OFFSET;
 		pdata->mcx_mac_csr_addr = base_addr + BLOCK_ETH_MAC_CSR_OFFSET;
-		pdata->rm = RM3;
 	} else {
 		pdata->mcx_mac_addr = base_addr + BLOCK_AXG_MAC_OFFSET;
 		pdata->mcx_mac_csr_addr = base_addr + BLOCK_AXG_MAC_CSR_OFFSET;
-		pdata->rm = RM0;
 	}
 	pdata->rx_buff_cnt = NUM_PKT_BUF;
 
@@ -881,10 +882,17 @@ static void xgene_enet_setup_ops(struct xgene_enet_pdata *pdata)
 	case PHY_INTERFACE_MODE_RGMII:
 		pdata->mac_ops = &xgene_gmac_ops;
 		pdata->port_ops = &xgene_gport_ops;
+		pdata->rm = RM3;
+		break;
+	case PHY_INTERFACE_MODE_SGMII:
+		pdata->mac_ops = &xgene_sgmac_ops;
+		pdata->port_ops = &xgene_sgport_ops;
+		pdata->rm = RM1;
 		break;
 	default:
 		pdata->mac_ops = &xgene_xgmac_ops;
 		pdata->port_ops = &xgene_xgport_ops;
+		pdata->rm = RM0;
 		break;
 	}
 }
@@ -895,6 +903,7 @@ static int xgene_enet_probe(struct platform_device *pdev)
 	struct xgene_enet_pdata *pdata;
 	struct device *dev = &pdev->dev;
 	struct napi_struct *napi;
+	struct xgene_mac_ops *mac_ops;
 	int ret;
 
 	ndev = alloc_etherdev(sizeof(struct xgene_enet_pdata));
@@ -937,10 +946,11 @@ static int xgene_enet_probe(struct platform_device *pdev)
 
 	napi = &pdata->rx_ring->napi;
 	netif_napi_add(ndev, napi, xgene_enet_napi, NAPI_POLL_WEIGHT);
+	mac_ops = pdata->mac_ops;
 	if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII)
 		ret = xgene_enet_mdio_config(pdata);
 	else
-		INIT_DELAYED_WORK(&pdata->link_work, xgene_enet_link_state);
+		INIT_DELAYED_WORK(&pdata->link_work, mac_ops->link_state);
 
 	return ret;
 err:

drivers/net/ethernet/apm/xgene/xgene_enet_main.h

@@ -39,6 +39,9 @@
 #define NUM_PKT_BUF	64
 #define NUM_BUFPOOL	32
 
+#define PHY_POLL_LINK_ON	(10 * HZ)
+#define PHY_POLL_LINK_OFF	(PHY_POLL_LINK_ON / 5)
+
 /* software context of a descriptor ring */
 struct xgene_enet_desc_ring {
 	struct net_device *ndev;
@@ -76,6 +79,7 @@ struct xgene_mac_ops {
 	void (*tx_disable)(struct xgene_enet_pdata *pdata);
 	void (*rx_disable)(struct xgene_enet_pdata *pdata);
 	void (*set_mac_addr)(struct xgene_enet_pdata *pdata);
+	void (*link_state)(struct work_struct *work);
 };
 
 struct xgene_port_ops {
@@ -109,7 +113,6 @@ struct xgene_enet_pdata {
 	void __iomem *base_addr;
 	void __iomem *ring_csr_addr;
 	void __iomem *ring_cmd_addr;
-	u32 phy_addr;
 	int phy_mode;
 	enum xgene_enet_rm rm;
 	struct rtnl_link_stats64 stats;
@@ -118,6 +121,13 @@ struct xgene_enet_pdata {
 	struct delayed_work link_work;
 };
 
+struct xgene_indirect_ctl {
+	void __iomem *addr;
+	void __iomem *ctl;
+	void __iomem *cmd;
+	void __iomem *cmd_done;
+};
+
 /* Set the specified value into a bit-field defined by its starting position
  * and length within a single u64.
  */

drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c

@@ -0,0 +1,389 @@
+/* Applied Micro X-Gene SoC Ethernet Driver
+ *
+ * Copyright (c) 2014, Applied Micro Circuits Corporation
+ * Authors: Iyappan Subramanian <isubramanian@apm.com>
+ *	    Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "xgene_enet_main.h"
+#include "xgene_enet_hw.h"
+#include "xgene_enet_sgmac.h"
+
+static void xgene_enet_wr_csr(struct xgene_enet_pdata *p, u32 offset, u32 val)
+{
+	iowrite32(val, p->eth_csr_addr + offset);
+}
+
+static void xgene_enet_wr_ring_if(struct xgene_enet_pdata *p,
+				  u32 offset, u32 val)
+{
+	iowrite32(val, p->eth_ring_if_addr + offset);
+}
+
+static void xgene_enet_wr_diag_csr(struct xgene_enet_pdata *p,
+				   u32 offset, u32 val)
+{
+	iowrite32(val, p->eth_diag_csr_addr + offset);
+}
+
+static bool xgene_enet_wr_indirect(struct xgene_indirect_ctl *ctl,
+				   u32 wr_addr, u32 wr_data)
+{
+	int i;
+
+	iowrite32(wr_addr, ctl->addr);
+	iowrite32(wr_data, ctl->ctl);
+	iowrite32(XGENE_ENET_WR_CMD, ctl->cmd);
+
+	/* wait for write command to complete */
+	for (i = 0; i < 10; i++) {
+		if (ioread32(ctl->cmd_done)) {
+			iowrite32(0, ctl->cmd);
+			return true;
+		}
+		udelay(1);
+	}
+
+	return false;
+}
+
+static void xgene_enet_wr_mac(struct xgene_enet_pdata *p,
+			      u32 wr_addr, u32 wr_data)
+{
+	struct xgene_indirect_ctl ctl = {
+		.addr = p->mcx_mac_addr + MAC_ADDR_REG_OFFSET,
+		.ctl = p->mcx_mac_addr + MAC_WRITE_REG_OFFSET,
+		.cmd = p->mcx_mac_addr + MAC_COMMAND_REG_OFFSET,
+		.cmd_done = p->mcx_mac_addr + MAC_COMMAND_DONE_REG_OFFSET
+	};
+
+	if (!xgene_enet_wr_indirect(&ctl, wr_addr, wr_data))
+		netdev_err(p->ndev, "mac write failed, addr: %04x\n", wr_addr);
+}
+
+static u32 xgene_enet_rd_csr(struct xgene_enet_pdata *p, u32 offset)
+{
+	return ioread32(p->eth_csr_addr + offset);
+}
+
+static u32 xgene_enet_rd_diag_csr(struct xgene_enet_pdata *p, u32 offset)
+{
+	return ioread32(p->eth_diag_csr_addr + offset);
+}
+
+static u32 xgene_enet_rd_indirect(struct xgene_indirect_ctl *ctl, u32 rd_addr)
+{
+	u32 rd_data;
+	int i;
+
+	iowrite32(rd_addr, ctl->addr);
+	iowrite32(XGENE_ENET_RD_CMD, ctl->cmd);
+
+	/* wait for read command to complete */
+	for (i = 0; i < 10; i++) {
+		if (ioread32(ctl->cmd_done)) {
+			rd_data = ioread32(ctl->ctl);
+			iowrite32(0, ctl->cmd);
+
+			return rd_data;
+		}
+		udelay(1);
+	}
+
+	pr_err("%s: mac read failed, addr: %04x\n", __func__, rd_addr);
+
+	return 0;
+}
+
+static u32 xgene_enet_rd_mac(struct xgene_enet_pdata *p, u32 rd_addr)
+{
+	struct xgene_indirect_ctl ctl = {
+		.addr = p->mcx_mac_addr + MAC_ADDR_REG_OFFSET,
+		.ctl = p->mcx_mac_addr + MAC_READ_REG_OFFSET,
+		.cmd = p->mcx_mac_addr + MAC_COMMAND_REG_OFFSET,
+		.cmd_done = p->mcx_mac_addr + MAC_COMMAND_DONE_REG_OFFSET
+	};
+
+	return xgene_enet_rd_indirect(&ctl, rd_addr);
+}
+
+static int xgene_enet_ecc_init(struct xgene_enet_pdata *p)
+{
+	struct net_device *ndev = p->ndev;
+	u32 data;
+	int i;
+
+	xgene_enet_wr_diag_csr(p, ENET_CFG_MEM_RAM_SHUTDOWN_ADDR, 0);
+	for (i = 0; i < 10 && data != ~0U ; i++) {
+		usleep_range(100, 110);
+		data = xgene_enet_rd_diag_csr(p, ENET_BLOCK_MEM_RDY_ADDR);
+	}
+
+	if (data != ~0U) {
+		netdev_err(ndev, "Failed to release memory from shutdown\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static void xgene_enet_config_ring_if_assoc(struct xgene_enet_pdata *p)
+{
+	u32 val = 0xffffffff;
+
+	xgene_enet_wr_ring_if(p, ENET_CFGSSQMIWQASSOC_ADDR, val);
+	xgene_enet_wr_ring_if(p, ENET_CFGSSQMIFPQASSOC_ADDR, val);
+}
+
+static void xgene_mii_phy_write(struct xgene_enet_pdata *p, u8 phy_id,
+				u32 reg, u16 data)
+{
+	u32 addr, wr_data, done;
+	int i;
+
+	addr = PHY_ADDR(phy_id) | REG_ADDR(reg);
+	xgene_enet_wr_mac(p, MII_MGMT_ADDRESS_ADDR, addr);
+
+	wr_data = PHY_CONTROL(data);
+	xgene_enet_wr_mac(p, MII_MGMT_CONTROL_ADDR, wr_data);
+
+	for (i = 0; i < 10; i++) {
+		done = xgene_enet_rd_mac(p, MII_MGMT_INDICATORS_ADDR);
+		if (!(done & BUSY_MASK))
+			return;
+		usleep_range(10, 20);
+	}
+
+	netdev_err(p->ndev, "MII_MGMT write failed\n");
+}
+
+static u32 xgene_mii_phy_read(struct xgene_enet_pdata *p, u8 phy_id, u32 reg)
+{
+	u32 addr, data, done;
+	int i;
+
+	addr = PHY_ADDR(phy_id) | REG_ADDR(reg);
+	xgene_enet_wr_mac(p, MII_MGMT_ADDRESS_ADDR, addr);
+	xgene_enet_wr_mac(p, MII_MGMT_COMMAND_ADDR, READ_CYCLE_MASK);
+
+	for (i = 0; i < 10; i++) {
+		done = xgene_enet_rd_mac(p, MII_MGMT_INDICATORS_ADDR);
+		if (!(done & BUSY_MASK)) {
+			data = xgene_enet_rd_mac(p, MII_MGMT_STATUS_ADDR);
+			xgene_enet_wr_mac(p, MII_MGMT_COMMAND_ADDR, 0);
+
+			return data;
+		}
+		usleep_range(10, 20);
+	}
+
+	netdev_err(p->ndev, "MII_MGMT read failed\n");
+
+	return 0;
+}
+
+static void xgene_sgmac_reset(struct xgene_enet_pdata *p)
+{
+	xgene_enet_wr_mac(p, MAC_CONFIG_1_ADDR, SOFT_RESET1);
+	xgene_enet_wr_mac(p, MAC_CONFIG_1_ADDR, 0);
+}
+
+static void xgene_sgmac_set_mac_addr(struct xgene_enet_pdata *p)
+{
+	u32 addr0, addr1;
+	u8 *dev_addr = p->ndev->dev_addr;
+
+	addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) |
+		(dev_addr[1] << 8) | dev_addr[0];
+	xgene_enet_wr_mac(p, STATION_ADDR0_ADDR, addr0);
+
+	addr1 = xgene_enet_rd_mac(p, STATION_ADDR1_ADDR);
+	addr1 |= (dev_addr[5] << 24) | (dev_addr[4] << 16);
+	xgene_enet_wr_mac(p, STATION_ADDR1_ADDR, addr1);
+}
+
+static u32 xgene_enet_link_status(struct xgene_enet_pdata *p)
+{
+	u32 data;
+
+	data = xgene_mii_phy_read(p, INT_PHY_ADDR,
+				  SGMII_BASE_PAGE_ABILITY_ADDR >> 2);
+
+	return data & LINK_UP;
+}
+
+static void xgene_sgmac_init(struct xgene_enet_pdata *p)
+{
+	u32 data, loop = 10;
+
+	xgene_sgmac_reset(p);
+
+	/* Enable auto-negotiation */
+	xgene_mii_phy_write(p, INT_PHY_ADDR, SGMII_CONTROL_ADDR >> 2, 0x1000);
+	xgene_mii_phy_write(p, INT_PHY_ADDR, SGMII_TBI_CONTROL_ADDR >> 2, 0);
+
+	while (loop--) {
+		data = xgene_mii_phy_read(p, INT_PHY_ADDR,
+					  SGMII_STATUS_ADDR >> 2);
+		if ((data & AUTO_NEG_COMPLETE) && (data & LINK_STATUS))
+			break;
+		usleep_range(10, 20);
+	}
+	if (!(data & AUTO_NEG_COMPLETE) || !(data & LINK_STATUS))
+		netdev_err(p->ndev, "Auto-negotiation failed\n");
+
+	data = xgene_enet_rd_mac(p, MAC_CONFIG_2_ADDR);
+	ENET_INTERFACE_MODE2_SET(&data, 2);
+	xgene_enet_wr_mac(p, MAC_CONFIG_2_ADDR, data | FULL_DUPLEX2);
+	xgene_enet_wr_mac(p, INTERFACE_CONTROL_ADDR, ENET_GHD_MODE);
+
+	data = xgene_enet_rd_csr(p, ENET_SPARE_CFG_REG_ADDR);
+	data |= MPA_IDLE_WITH_QMI_EMPTY;
+	xgene_enet_wr_csr(p, ENET_SPARE_CFG_REG_ADDR, data);
+
+	xgene_sgmac_set_mac_addr(p);
+
+	data = xgene_enet_rd_csr(p, DEBUG_REG_ADDR);
+	data |= CFG_BYPASS_UNISEC_TX | CFG_BYPASS_UNISEC_RX;
+	xgene_enet_wr_csr(p, DEBUG_REG_ADDR, data);
+
+	/* Adjust MDC clock frequency */
+	data = xgene_enet_rd_mac(p, MII_MGMT_CONFIG_ADDR);
+	MGMT_CLOCK_SEL_SET(&data, 7);
+	xgene_enet_wr_mac(p, MII_MGMT_CONFIG_ADDR, data);
+
+	/* Enable drop if bufpool not available */
+	data = xgene_enet_rd_csr(p, RSIF_CONFIG_REG_ADDR);
+	data |= CFG_RSIF_FPBUFF_TIMEOUT_EN;
+	xgene_enet_wr_csr(p, RSIF_CONFIG_REG_ADDR, data);
+
+	/* Rtype should be copied from FP */
+	xgene_enet_wr_csr(p, RSIF_RAM_DBG_REG0_ADDR, 0);
+
+	/* Bypass traffic gating */
+	xgene_enet_wr_csr(p, CFG_LINK_AGGR_RESUME_0_ADDR, TX_PORT0);
+	xgene_enet_wr_csr(p, CFG_BYPASS_ADDR, RESUME_TX);
+	xgene_enet_wr_csr(p, SG_RX_DV_GATE_REG_0_ADDR, RESUME_RX0);
+}
+
+static void xgene_sgmac_rxtx(struct xgene_enet_pdata *p, u32 bits, bool set)
+{
+	u32 data;
+
+	data = xgene_enet_rd_mac(p, MAC_CONFIG_1_ADDR);
+
+	if (set)
+		data |= bits;
+	else
+		data &= ~bits;
+
+	xgene_enet_wr_mac(p, MAC_CONFIG_1_ADDR, data);
+}
+
+static void xgene_sgmac_rx_enable(struct xgene_enet_pdata *p)
+{
+	xgene_sgmac_rxtx(p, RX_EN, true);
+}
+
+static void xgene_sgmac_tx_enable(struct xgene_enet_pdata *p)
+{
+	xgene_sgmac_rxtx(p, TX_EN, true);
+}
+
+static void xgene_sgmac_rx_disable(struct xgene_enet_pdata *p)
+{
+	xgene_sgmac_rxtx(p, RX_EN, false);
+}
+
+static void xgene_sgmac_tx_disable(struct xgene_enet_pdata *p)
+{
+	xgene_sgmac_rxtx(p, TX_EN, false);
+}
+
+static void xgene_enet_reset(struct xgene_enet_pdata *p)
+{
+	clk_prepare_enable(p->clk);
+	clk_disable_unprepare(p->clk);
+	clk_prepare_enable(p->clk);
+
+	xgene_enet_ecc_init(p);
+	xgene_enet_config_ring_if_assoc(p);
+}
+
+static void xgene_enet_cle_bypass(struct xgene_enet_pdata *p,
+				  u32 dst_ring_num, u16 bufpool_id)
+{
+	u32 data, fpsel;
+
+	data = CFG_CLE_BYPASS_EN0;
+	xgene_enet_wr_csr(p, CLE_BYPASS_REG0_0_ADDR, data);
+
+	fpsel = xgene_enet_ring_bufnum(bufpool_id) - 0x20;
+	data = CFG_CLE_DSTQID0(dst_ring_num) | CFG_CLE_FPSEL0(fpsel);
+	xgene_enet_wr_csr(p, CLE_BYPASS_REG1_0_ADDR, data);
+}
+
+static void xgene_enet_shutdown(struct xgene_enet_pdata *p)
+{
+	clk_disable_unprepare(p->clk);
+}
+
+static void xgene_enet_link_state(struct work_struct *work)
+{
+	struct xgene_enet_pdata *p = container_of(to_delayed_work(work),
+				     struct xgene_enet_pdata, link_work);
+	struct net_device *ndev = p->ndev;
+	u32 link, poll_interval;
+
+	link = xgene_enet_link_status(p);
+	if (link) {
+		if (!netif_carrier_ok(ndev)) {
+			netif_carrier_on(ndev);
+			xgene_sgmac_init(p);
+			xgene_sgmac_rx_enable(p);
+			xgene_sgmac_tx_enable(p);
+			netdev_info(ndev, "Link is Up - 1Gbps\n");
+		}
+		poll_interval = PHY_POLL_LINK_ON;
+	} else {
+		if (netif_carrier_ok(ndev)) {
+			xgene_sgmac_rx_disable(p);
+			xgene_sgmac_tx_disable(p);
+			netif_carrier_off(ndev);
+			netdev_info(ndev, "Link is Down\n");
+		}
+		poll_interval = PHY_POLL_LINK_OFF;
+	}
+
+	schedule_delayed_work(&p->link_work, poll_interval);
+}
+
+struct xgene_mac_ops xgene_sgmac_ops = {
+	.init		= xgene_sgmac_init,
+	.reset		= xgene_sgmac_reset,
+	.rx_enable	= xgene_sgmac_rx_enable,
+	.tx_enable	= xgene_sgmac_tx_enable,
+	.rx_disable	= xgene_sgmac_rx_disable,
+	.tx_disable	= xgene_sgmac_tx_disable,
+	.set_mac_addr	= xgene_sgmac_set_mac_addr,
+	.link_state	= xgene_enet_link_state
+};
+
+struct xgene_port_ops xgene_sgport_ops = {
+	.reset		= xgene_enet_reset,
+	.cle_bypass	= xgene_enet_cle_bypass,
+	.shutdown	= xgene_enet_shutdown
+};

drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.h

@@ -0,0 +1,41 @@
+/* Applied Micro X-Gene SoC Ethernet Driver
+ *
+ * Copyright (c) 2014, Applied Micro Circuits Corporation
+ * Authors: Iyappan Subramanian <isubramanian@apm.com>
+ *	    Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_SGMAC_H__
+#define __XGENE_ENET_SGMAC_H__
+
+#define PHY_ADDR(src)		(((src)<<8) & GENMASK(12, 8))
+#define REG_ADDR(src)		((src) & GENMASK(4, 0))
+#define PHY_CONTROL(src)	((src) & GENMASK(15, 0))
+#define INT_PHY_ADDR			0x1e
+#define SGMII_TBI_CONTROL_ADDR		0x44
+#define SGMII_CONTROL_ADDR		0x00
+#define SGMII_STATUS_ADDR		0x04
+#define SGMII_BASE_PAGE_ABILITY_ADDR	0x14
+#define AUTO_NEG_COMPLETE		BIT(5)
+#define LINK_STATUS			BIT(2)
+#define LINK_UP				BIT(15)
+#define MPA_IDLE_WITH_QMI_EMPTY		BIT(12)
+#define SG_RX_DV_GATE_REG_0_ADDR	0x0dfc
+
+extern struct xgene_mac_ops xgene_sgmac_ops;
+extern struct xgene_port_ops xgene_sgport_ops;
+
+#endif  /* __XGENE_ENET_SGMAC_H__ */

drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c

@@ -284,7 +284,7 @@ static void xgene_enet_shutdown(struct xgene_enet_pdata *pdata)
 	clk_disable_unprepare(pdata->clk);
 }
 
-void xgene_enet_link_state(struct work_struct *work)
+static void xgene_enet_link_state(struct work_struct *work)
 {
 	struct xgene_enet_pdata *pdata = container_of(to_delayed_work(work),
 					 struct xgene_enet_pdata, link_work);
@@ -322,6 +322,7 @@ struct xgene_mac_ops xgene_xgmac_ops = {
 	.rx_disable = xgene_xgmac_rx_disable,
 	.tx_disable = xgene_xgmac_tx_disable,
 	.set_mac_addr = xgene_xgmac_set_mac_addr,
+	.link_state = xgene_enet_link_state
 };
 
 struct xgene_port_ops xgene_xgport_ops = {

drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h

@@ -47,10 +47,6 @@
 #define XG_ENET_SPARE_CFG_REG_1_ADDR	0x0410
 #define XGENET_RX_DV_GATE_REG_0_ADDR	0x0804
 
-#define PHY_POLL_LINK_ON	(10 * HZ)
-#define PHY_POLL_LINK_OFF	(PHY_POLL_LINK_ON / 5)
-
-void xgene_enet_link_state(struct work_struct *work);
 extern struct xgene_mac_ops xgene_xgmac_ops;
 extern struct xgene_port_ops xgene_xgport_ops;
 

drivers/net/ethernet/broadcom/tg3.c

@@ -8099,9 +8099,6 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Sync BD data before updating mailbox */
 	wmb();
 
-	/* Packets are ready, update Tx producer idx local and on card. */
-	tw32_tx_mbox(tnapi->prodmbox, entry);
-
 	tnapi->tx_prod = entry;
 	if (unlikely(tg3_tx_avail(tnapi) <= (MAX_SKB_FRAGS + 1))) {
 		netif_tx_stop_queue(txq);
@@ -8116,7 +8113,12 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			netif_tx_wake_queue(txq);
 	}
 
-	mmiowb();
+	if (!skb->xmit_more || netif_xmit_stopped(txq)) {
+		/* Packets are ready, update Tx producer idx on card. */
+		tw32_tx_mbox(tnapi->prodmbox, entry);
+		mmiowb();
+	}
+
 	return NETDEV_TX_OK;
 
 dma_error:

drivers/net/ethernet/brocade/bna/bnad.c

@@ -552,6 +552,7 @@ bnad_cq_setup_skb_frags(struct bna_rcb *rcb, struct sk_buff *skb,
 
 		len = (vec == nvecs) ?
 			last_fraglen : unmap->vector.len;
+		skb->truesize += unmap->vector.len;
 		totlen += len;
 
 		skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
@@ -563,7 +564,6 @@ bnad_cq_setup_skb_frags(struct bna_rcb *rcb, struct sk_buff *skb,
 
 	skb->len += totlen;
 	skb->data_len += totlen;
-	skb->truesize += totlen;
 }
 
 static inline void

drivers/net/ethernet/chelsio/Kconfig

@@ -68,7 +68,7 @@ config CHELSIO_T3
 
 config CHELSIO_T4
 	tristate "Chelsio Communications T4/T5 Ethernet support"
-	depends on PCI
+	depends on PCI && (IPV6 || IPV6=n)
 	select FW_LOADER
 	select MDIO
 	---help---

drivers/net/ethernet/chelsio/cxgb4/cxgb4.h

@@ -986,6 +986,8 @@ static inline int t4_memory_write(struct adapter *adap, int mtype, u32 addr,
 int t4_seeprom_wp(struct adapter *adapter, bool enable);
 int get_vpd_params(struct adapter *adapter, struct vpd_params *p);
 int t4_load_fw(struct adapter *adapter, const u8 *fw_data, unsigned int size);
+int t4_fw_upgrade(struct adapter *adap, unsigned int mbox,
+		  const u8 *fw_data, unsigned int size, int force);
 unsigned int t4_flash_cfg_addr(struct adapter *adapter);
 int t4_get_fw_version(struct adapter *adapter, u32 *vers);
 int t4_get_tp_version(struct adapter *adapter, u32 *vers);

drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c

@@ -2929,16 +2929,26 @@ static int set_flash(struct net_device *netdev, struct ethtool_flash *ef)
 	int ret;
 	const struct firmware *fw;
 	struct adapter *adap = netdev2adap(netdev);
+	unsigned int mbox = FW_PCIE_FW_MASTER_MASK + 1;
 
 	ef->data[sizeof(ef->data) - 1] = '\0';
 	ret = request_firmware(&fw, ef->data, adap->pdev_dev);
 	if (ret < 0)
 		return ret;
 
-	ret = t4_load_fw(adap, fw->data, fw->size);
+	/* If the adapter has been fully initialized then we'll go ahead and
+	 * try to get the firmware's cooperation in upgrading to the new
+	 * firmware image otherwise we'll try to do the entire job from the
+	 * host ... and we always "force" the operation in this path.
+	 */
+	if (adap->flags & FULL_INIT_DONE)
+		mbox = adap->mbox;
+
+	ret = t4_fw_upgrade(adap, mbox, fw->data, fw->size, 1);
 	release_firmware(fw);
 	if (!ret)
-		dev_info(adap->pdev_dev, "loaded firmware %s\n", ef->data);
+		dev_info(adap->pdev_dev, "loaded firmware %s,"
+			 " reload cxgb4 driver\n", ef->data);
 	return ret;
 }
 
@@ -4359,6 +4369,7 @@ EXPORT_SYMBOL(cxgb4_unregister_uld);
  * success (true) if it belongs otherwise failure (false).
  * Called with rcu_read_lock() held.
  */
+#if IS_ENABLED(CONFIG_IPV6)
 static bool cxgb4_netdev(const struct net_device *netdev)
 {
 	struct adapter *adap;
@@ -4480,6 +4491,13 @@ static int update_root_dev_clip(struct net_device *dev)
 		return ret;
 
 	/* Parse all bond and vlan devices layered on top of the physical dev */
+	root_dev = netdev_master_upper_dev_get_rcu(dev);
+	if (root_dev) {
+		ret = update_dev_clip(root_dev, dev);
+		if (ret)
+			return ret;
+	}
+
 	for (i = 0; i < VLAN_N_VID; i++) {
 		root_dev = __vlan_find_dev_deep_rcu(dev, htons(ETH_P_8021Q), i);
 		if (!root_dev)
@@ -4512,6 +4530,7 @@ static void update_clip(const struct adapter *adap)
 	}
 	rcu_read_unlock();
 }
+#endif /* IS_ENABLED(CONFIG_IPV6) */
 
 /**
  *	cxgb_up - enable the adapter
@@ -4558,7 +4577,9 @@ static int cxgb_up(struct adapter *adap)
 	t4_intr_enable(adap);
 	adap->flags |= FULL_INIT_DONE;
 	notify_ulds(adap, CXGB4_STATE_UP);
+#if IS_ENABLED(CONFIG_IPV6)
 	update_clip(adap);
+#endif
  out:
 	return err;
  irq_err:
@@ -6852,14 +6873,18 @@ static int __init cxgb4_init_module(void)
 	if (ret < 0)
 		debugfs_remove(cxgb4_debugfs_root);
 
+#if IS_ENABLED(CONFIG_IPV6)
 	register_inet6addr_notifier(&cxgb4_inet6addr_notifier);
+#endif
 
 	return ret;
 }
 
 static void __exit cxgb4_cleanup_module(void)
 {
+#if IS_ENABLED(CONFIG_IPV6)
 	unregister_inet6addr_notifier(&cxgb4_inet6addr_notifier);
+#endif
 	pci_unregister_driver(&cxgb4_driver);
 	debugfs_remove(cxgb4_debugfs_root);  /* NULL ok */
 }

drivers/net/ethernet/chelsio/cxgb4/t4_hw.c

@@ -37,8 +37,6 @@
 #include "t4_regs.h"
 #include "t4fw_api.h"
 
-static int t4_fw_upgrade(struct adapter *adap, unsigned int mbox,
-			 const u8 *fw_data, unsigned int size, int force);
 /**
  *	t4_wait_op_done_val - wait until an operation is completed
  *	@adapter: the adapter performing the operation
@@ -3076,8 +3074,8 @@ static int t4_fw_restart(struct adapter *adap, unsigned int mbox, int reset)
  *	positive errno indicates that the adapter is ~probably~ intact, a
  *	negative errno indicates that things are looking bad ...
  */
-static int t4_fw_upgrade(struct adapter *adap, unsigned int mbox,
-			 const u8 *fw_data, unsigned int size, int force)
+int t4_fw_upgrade(struct adapter *adap, unsigned int mbox,
+		  const u8 *fw_data, unsigned int size, int force)
 {
 	const struct fw_hdr *fw_hdr = (const struct fw_hdr *)fw_data;
 	int reset, ret;

drivers/net/ethernet/freescale/fec.h

@@ -367,6 +367,56 @@ struct bufdesc_ex {
 #define FEC_VLAN_TAG_LEN       0x04
 #define FEC_ETHTYPE_LEN                0x02
 
+/* Controller is ENET-MAC */
+#define FEC_QUIRK_ENET_MAC		(1 << 0)
+/* Controller needs driver to swap frame */
+#define FEC_QUIRK_SWAP_FRAME		(1 << 1)
+/* Controller uses gasket */
+#define FEC_QUIRK_USE_GASKET		(1 << 2)
+/* Controller has GBIT support */
+#define FEC_QUIRK_HAS_GBIT		(1 << 3)
+/* Controller has extend desc buffer */
+#define FEC_QUIRK_HAS_BUFDESC_EX	(1 << 4)
+/* Controller has hardware checksum support */
+#define FEC_QUIRK_HAS_CSUM		(1 << 5)
+/* Controller has hardware vlan support */
+#define FEC_QUIRK_HAS_VLAN		(1 << 6)
+/* ENET IP errata ERR006358
+ *
+ * If the ready bit in the transmit buffer descriptor (TxBD[R]) is previously
+ * detected as not set during a prior frame transmission, then the
+ * ENET_TDAR[TDAR] bit is cleared at a later time, even if additional TxBDs
+ * were added to the ring and the ENET_TDAR[TDAR] bit is set. This results in
+ * frames not being transmitted until there is a 0-to-1 transition on
+ * ENET_TDAR[TDAR].
+ */
+#define FEC_QUIRK_ERR006358            (1 << 7)
+/* ENET IP hw AVB
+ *
+ * i.MX6SX ENET IP add Audio Video Bridging (AVB) feature support.
+ * - Two class indicators on receive with configurable priority
+ * - Two class indicators and line speed timer on transmit allowing
+ *   implementation class credit based shapers externally
+ * - Additional DMA registers provisioned to allow managing up to 3
+ *   independent rings
+ */
+#define FEC_QUIRK_HAS_AVB		(1 << 8)
+/* There is a TDAR race condition for mutliQ when the software sets TDAR
+ * and the UDMA clears TDAR simultaneously or in a small window (2-4 cycles).
+ * This will cause the udma_tx and udma_tx_arbiter state machines to hang.
+ * The issue exist at i.MX6SX enet IP.
+ */
+#define FEC_QUIRK_ERR007885		(1 << 9)
+/* ENET Block Guide/ Chapter for the iMX6SX (PELE) address one issue:
+ * After set ENET_ATCR[Capture], there need some time cycles before the counter
+ * value is capture in the register clock domain.
+ * The wait-time-cycles is at least 6 clock cycles of the slower clock between
+ * the register clock and the 1588 clock. The 1588 ts_clk is fixed to 25Mhz,
+ * register clock is 66Mhz, so the wait-time-cycles must be greater than 240ns
+ * (40ns * 6).
+ */
+#define FEC_QUIRK_BUG_CAPTURE		(1 << 10)
+
 struct fec_enet_priv_tx_q {
 	int index;
 	unsigned char *tx_bounce[TX_RING_SIZE];
@@ -484,12 +534,22 @@ struct fec_enet_private {
 	unsigned int itr_clk_rate;
 
 	u32 rx_copybreak;
+
+	/* ptp clock period in ns*/
+	unsigned int ptp_inc;
+
+	/* pps  */
+	int pps_channel;
+	unsigned int reload_period;
+	int pps_enable;
+	unsigned int next_counter;
 };
 
 void fec_ptp_init(struct platform_device *pdev);
 void fec_ptp_start_cyclecounter(struct net_device *ndev);
 int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr);
 int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr);
+uint fec_ptp_check_pps_event(struct fec_enet_private *fep);
 
 /****************************************************************************/
 #endif /* FEC_H */

drivers/net/ethernet/freescale/fec_main.c

@@ -78,47 +78,6 @@ static void fec_enet_itr_coal_init(struct net_device *ndev);
 #define FEC_ENET_RAFL_V	0x8
 #define FEC_ENET_OPD_V	0xFFF0
 
-/* Controller is ENET-MAC */
-#define FEC_QUIRK_ENET_MAC		(1 << 0)
-/* Controller needs driver to swap frame */
-#define FEC_QUIRK_SWAP_FRAME		(1 << 1)
-/* Controller uses gasket */
-#define FEC_QUIRK_USE_GASKET		(1 << 2)
-/* Controller has GBIT support */
-#define FEC_QUIRK_HAS_GBIT		(1 << 3)
-/* Controller has extend desc buffer */
-#define FEC_QUIRK_HAS_BUFDESC_EX	(1 << 4)
-/* Controller has hardware checksum support */
-#define FEC_QUIRK_HAS_CSUM		(1 << 5)
-/* Controller has hardware vlan support */
-#define FEC_QUIRK_HAS_VLAN		(1 << 6)
-/* ENET IP errata ERR006358
- *
- * If the ready bit in the transmit buffer descriptor (TxBD[R]) is previously
- * detected as not set during a prior frame transmission, then the
- * ENET_TDAR[TDAR] bit is cleared at a later time, even if additional TxBDs
- * were added to the ring and the ENET_TDAR[TDAR] bit is set. This results in
- * frames not being transmitted until there is a 0-to-1 transition on
- * ENET_TDAR[TDAR].
- */
-#define FEC_QUIRK_ERR006358            (1 << 7)
-/* ENET IP hw AVB
- *
- * i.MX6SX ENET IP add Audio Video Bridging (AVB) feature support.
- * - Two class indicators on receive with configurable priority
- * - Two class indicators and line speed timer on transmit allowing
- *   implementation class credit based shapers externally
- * - Additional DMA registers provisioned to allow managing up to 3
- *   independent rings
- */
-#define FEC_QUIRK_HAS_AVB		(1 << 8)
-/* There is a TDAR race condition for mutliQ when the software sets TDAR
- * and the UDMA clears TDAR simultaneously or in a small window (2-4 cycles).
- * This will cause the udma_tx and udma_tx_arbiter state machines to hang.
- * The issue exist at i.MX6SX enet IP.
- */
-#define FEC_QUIRK_ERR007885		(1 << 9)
-
 static struct platform_device_id fec_devtype[] = {
 	{
 		/* keep it for coldfire */
@@ -146,7 +105,7 @@ static struct platform_device_id fec_devtype[] = {
 		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
 				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
 				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
-				FEC_QUIRK_ERR007885,
+				FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE,
 	}, {
 		/* sentinel */
 	}
@@ -1622,6 +1581,8 @@ fec_enet_interrupt(int irq, void *dev_id)
 		complete(&fep->mdio_done);
 	}
 
+	fec_ptp_check_pps_event(fep);
+
 	return ret;
 }
 
@@ -2912,20 +2873,12 @@ static void fec_poll_controller(struct net_device *dev)
 #endif
 
 #define FEATURES_NEED_QUIESCE NETIF_F_RXCSUM
-
-static int fec_set_features(struct net_device *netdev,
+static inline void fec_enet_set_netdev_features(struct net_device *netdev,
 	netdev_features_t features)
 {
 	struct fec_enet_private *fep = netdev_priv(netdev);
 	netdev_features_t changed = features ^ netdev->features;
 
-	/* Quiesce the device if necessary */
-	if (netif_running(netdev) && changed & FEATURES_NEED_QUIESCE) {
-		napi_disable(&fep->napi);
-		netif_tx_lock_bh(netdev);
-		fec_stop(netdev);
-	}
-
 	netdev->features = features;
 
 	/* Receive checksum has been changed */
@@ -2935,13 +2888,25 @@ static int fec_set_features(struct net_device *netdev,
 		else
 			fep->csum_flags &= ~FLAG_RX_CSUM_ENABLED;
 	}
+}
+
+static int fec_set_features(struct net_device *netdev,
+	netdev_features_t features)
+{
+	struct fec_enet_private *fep = netdev_priv(netdev);
+	netdev_features_t changed = features ^ netdev->features;
 
-	/* Resume the device after updates */
 	if (netif_running(netdev) && changed & FEATURES_NEED_QUIESCE) {
+		napi_disable(&fep->napi);
+		netif_tx_lock_bh(netdev);
+		fec_stop(netdev);
+		fec_enet_set_netdev_features(netdev, features);
 		fec_restart(netdev);
 		netif_tx_wake_all_queues(netdev);
 		netif_tx_unlock_bh(netdev);
 		napi_enable(&fep->napi);
+	} else {
+		fec_enet_set_netdev_features(netdev, features);
 	}
 
 	return 0;

drivers/net/ethernet/freescale/fec_ptp.c

@@ -61,6 +61,24 @@
 #define FEC_T_INC_CORR_MASK             0x00007f00
 #define FEC_T_INC_CORR_OFFSET           8
 
+#define FEC_T_CTRL_PINPER		0x00000080
+#define FEC_T_TF0_MASK			0x00000001
+#define FEC_T_TF0_OFFSET		0
+#define FEC_T_TF1_MASK			0x00000002
+#define FEC_T_TF1_OFFSET		1
+#define FEC_T_TF2_MASK			0x00000004
+#define FEC_T_TF2_OFFSET		2
+#define FEC_T_TF3_MASK			0x00000008
+#define FEC_T_TF3_OFFSET		3
+#define FEC_T_TDRE_MASK			0x00000001
+#define FEC_T_TDRE_OFFSET		0
+#define FEC_T_TMODE_MASK		0x0000003C
+#define FEC_T_TMODE_OFFSET		2
+#define FEC_T_TIE_MASK			0x00000040
+#define FEC_T_TIE_OFFSET		6
+#define FEC_T_TF_MASK			0x00000080
+#define FEC_T_TF_OFFSET			7
+
 #define FEC_ATIME_CTRL		0x400
 #define FEC_ATIME		0x404
 #define FEC_ATIME_EVT_OFFSET	0x408
@@ -69,7 +87,143 @@
 #define FEC_ATIME_INC		0x414
 #define FEC_TS_TIMESTAMP	0x418
 
+#define FEC_TGSR		0x604
+#define FEC_TCSR(n)		(0x608 + n * 0x08)
+#define FEC_TCCR(n)		(0x60C + n * 0x08)
+#define MAX_TIMER_CHANNEL	3
+#define FEC_TMODE_TOGGLE	0x05
+#define FEC_HIGH_PULSE		0x0F
+
 #define FEC_CC_MULT	(1 << 31)
+#define FEC_COUNTER_PERIOD	(1 << 31)
+#define PPS_OUPUT_RELOAD_PERIOD	NSEC_PER_SEC
+#define FEC_CHANNLE_0		0
+#define DEFAULT_PPS_CHANNEL	FEC_CHANNLE_0
+
+/**
+ * fec_ptp_enable_pps
+ * @fep: the fec_enet_private structure handle
+ * @enable: enable the channel pps output
+ *
+ * This function enble the PPS ouput on the timer channel.
+ */
+static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
+{
+	unsigned long flags;
+	u32 val, tempval;
+	int inc;
+	struct timespec ts;
+	u64 ns;
+	u32 remainder;
+	val = 0;
+
+	if (!(fep->hwts_tx_en || fep->hwts_rx_en)) {
+		dev_err(&fep->pdev->dev, "No ptp stack is running\n");
+		return -EINVAL;
+	}
+
+	if (fep->pps_enable == enable)
+		return 0;
+
+	fep->pps_channel = DEFAULT_PPS_CHANNEL;
+	fep->reload_period = PPS_OUPUT_RELOAD_PERIOD;
+	inc = fep->ptp_inc;
+
+	spin_lock_irqsave(&fep->tmreg_lock, flags);
+
+	if (enable) {
+		/* clear capture or output compare interrupt status if have.
+		 */
+		writel(FEC_T_TF_MASK, fep->hwp + FEC_TCSR(fep->pps_channel));
+
+		/* It is recommended to doulbe check the TMODE field in the
+		 * TCSR register to be cleared before the first compare counter
+		 * is written into TCCR register. Just add a double check.
+		 */
+		val = readl(fep->hwp + FEC_TCSR(fep->pps_channel));
+		do {
+			val &= ~(FEC_T_TMODE_MASK);
+			writel(val, fep->hwp + FEC_TCSR(fep->pps_channel));
+			val = readl(fep->hwp + FEC_TCSR(fep->pps_channel));
+		} while (val & FEC_T_TMODE_MASK);
+
+		/* Dummy read counter to update the counter */
+		timecounter_read(&fep->tc);
+		/* We want to find the first compare event in the next
+		 * second point. So we need to know what the ptp time
+		 * is now and how many nanoseconds is ahead to get next second.
+		 * The remaining nanosecond ahead before the next second would be
+		 * NSEC_PER_SEC - ts.tv_nsec. Add the remaining nanoseconds
+		 * to current timer would be next second.
+		 */
+		tempval = readl(fep->hwp + FEC_ATIME_CTRL);
+		tempval |= FEC_T_CTRL_CAPTURE;
+		writel(tempval, fep->hwp + FEC_ATIME_CTRL);
+
+		tempval = readl(fep->hwp + FEC_ATIME);
+		/* Convert the ptp local counter to 1588 timestamp */
+		ns = timecounter_cyc2time(&fep->tc, tempval);
+		ts.tv_sec = div_u64_rem(ns, 1000000000ULL, &remainder);
+		ts.tv_nsec = remainder;
+
+		/* The tempval is  less than 3 seconds, and  so val is less than
+		 * 4 seconds. No overflow for 32bit calculation.
+		 */
+		val = NSEC_PER_SEC - (u32)ts.tv_nsec + tempval;
+
+		/* Need to consider the situation that the current time is
+		 * very close to the second point, which means NSEC_PER_SEC
+		 * - ts.tv_nsec is close to be zero(For example 20ns); Since the timer
+		 * is still running when we calculate the first compare event, it is
+		 * possible that the remaining nanoseonds run out before the compare
+		 * counter is calculated and written into TCCR register. To avoid
+		 * this possibility, we will set the compare event to be the next
+		 * of next second. The current setting is 31-bit timer and wrap
+		 * around over 2 seconds. So it is okay to set the next of next
+		 * seond for the timer.
+		 */
+		val += NSEC_PER_SEC;
+
+		/* We add (2 * NSEC_PER_SEC - (u32)ts.tv_nsec) to current
+		 * ptp counter, which maybe cause 32-bit wrap. Since the
+		 * (NSEC_PER_SEC - (u32)ts.tv_nsec) is less than 2 second.
+		 * We can ensure the wrap will not cause issue. If the offset
+		 * is bigger than fep->cc.mask would be a error.
+		 */
+		val &= fep->cc.mask;
+		writel(val, fep->hwp + FEC_TCCR(fep->pps_channel));
+
+		/* Calculate the second the compare event timestamp */
+		fep->next_counter = (val + fep->reload_period) & fep->cc.mask;
+
+		/* * Enable compare event when overflow */
+		val = readl(fep->hwp + FEC_ATIME_CTRL);
+		val |= FEC_T_CTRL_PINPER;
+		writel(val, fep->hwp + FEC_ATIME_CTRL);
+
+		/* Compare channel setting. */
+		val = readl(fep->hwp + FEC_TCSR(fep->pps_channel));
+		val |= (1 << FEC_T_TF_OFFSET | 1 << FEC_T_TIE_OFFSET);
+		val &= ~(1 << FEC_T_TDRE_OFFSET);
+		val &= ~(FEC_T_TMODE_MASK);
+		val |= (FEC_HIGH_PULSE << FEC_T_TMODE_OFFSET);
+		writel(val, fep->hwp + FEC_TCSR(fep->pps_channel));
+
+		/* Write the second compare event timestamp and calculate
+		 * the third timestamp. Refer the TCCR register detail in the spec.
+		 */
+		writel(fep->next_counter, fep->hwp + FEC_TCCR(fep->pps_channel));
+		fep->next_counter = (fep->next_counter + fep->reload_period) & fep->cc.mask;
+	} else {
+		writel(0, fep->hwp + FEC_TCSR(fep->pps_channel));
+	}
+
+	fep->pps_enable = enable;
+	spin_unlock_irqrestore(&fep->tmreg_lock, flags);
+
+	return 0;
+}
+
 /**
  * fec_ptp_read - read raw cycle counter (to be used by time counter)
  * @cc: the cyclecounter structure
@@ -82,12 +236,17 @@ static cycle_t fec_ptp_read(const struct cyclecounter *cc)
 {
 	struct fec_enet_private *fep =
 		container_of(cc, struct fec_enet_private, cc);
+	const struct platform_device_id *id_entry =
+		platform_get_device_id(fep->pdev);
 	u32 tempval;
 
 	tempval = readl(fep->hwp + FEC_ATIME_CTRL);
 	tempval |= FEC_T_CTRL_CAPTURE;
 	writel(tempval, fep->hwp + FEC_ATIME_CTRL);
 
+	if (id_entry->driver_data & FEC_QUIRK_BUG_CAPTURE)
+		udelay(1);
+
 	return readl(fep->hwp + FEC_ATIME);
 }
 
@@ -113,14 +272,15 @@ void fec_ptp_start_cyclecounter(struct net_device *ndev)
 	/* 1ns counter */
 	writel(inc << FEC_T_INC_OFFSET, fep->hwp + FEC_ATIME_INC);
 
-	/* use free running count */
-	writel(0, fep->hwp + FEC_ATIME_EVT_PERIOD);
+	/* use 31-bit timer counter */
+	writel(FEC_COUNTER_PERIOD, fep->hwp + FEC_ATIME_EVT_PERIOD);
 
-	writel(FEC_T_CTRL_ENABLE, fep->hwp + FEC_ATIME_CTRL);
+	writel(FEC_T_CTRL_ENABLE | FEC_T_CTRL_PERIOD_RST,
+		fep->hwp + FEC_ATIME_CTRL);
 
 	memset(&fep->cc, 0, sizeof(fep->cc));
 	fep->cc.read = fec_ptp_read;
-	fep->cc.mask = CLOCKSOURCE_MASK(32);
+	fep->cc.mask = CLOCKSOURCE_MASK(31);
 	fep->cc.shift = 31;
 	fep->cc.mult = FEC_CC_MULT;
 
@@ -143,32 +303,59 @@ void fec_ptp_start_cyclecounter(struct net_device *ndev)
  */
 static int fec_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 {
-	u64 diff;
 	unsigned long flags;
 	int neg_adj = 0;
-	u32 mult = FEC_CC_MULT;
+	u32 i, tmp;
+	u32 corr_inc, corr_period;
+	u32 corr_ns;
+	u64 lhs, rhs;
 
 	struct fec_enet_private *fep =
 	    container_of(ptp, struct fec_enet_private, ptp_caps);
 
+	if (ppb == 0)
+		return 0;
+
 	if (ppb < 0) {
 		ppb = -ppb;
 		neg_adj = 1;
 	}
 
-	diff = mult;
-	diff *= ppb;
-	diff = div_u64(diff, 1000000000ULL);
+	/* In theory, corr_inc/corr_period = ppb/NSEC_PER_SEC;
+	 * Try to find the corr_inc  between 1 to fep->ptp_inc to
+	 * meet adjustment requirement.
+	 */
+	lhs = NSEC_PER_SEC;
+	rhs = (u64)ppb * (u64)fep->ptp_inc;
+	for (i = 1; i <= fep->ptp_inc; i++) {
+		if (lhs >= rhs) {
+			corr_inc = i;
+			corr_period = div_u64(lhs, rhs);
+			break;
+		}
+		lhs += NSEC_PER_SEC;
+	}
+	/* Not found? Set it to high value - double speed
+	 * correct in every clock step.
+	 */
+	if (i > fep->ptp_inc) {
+		corr_inc = fep->ptp_inc;
+		corr_period = 1;
+	}
+
+	if (neg_adj)
+		corr_ns = fep->ptp_inc - corr_inc;
+	else
+		corr_ns = fep->ptp_inc + corr_inc;
 
 	spin_lock_irqsave(&fep->tmreg_lock, flags);
-	/*
-	 * dummy read to set cycle_last in tc to now.
-	 * So use adjusted mult to calculate when next call
-	 * timercounter_read.
-	 */
-	timecounter_read(&fep->tc);
 
-	fep->cc.mult = neg_adj ? mult - diff : mult + diff;
+	tmp = readl(fep->hwp + FEC_ATIME_INC) & FEC_T_INC_MASK;
+	tmp |= corr_ns << FEC_T_INC_CORR_OFFSET;
+	writel(tmp, fep->hwp + FEC_ATIME_INC);
+	writel(corr_period, fep->hwp + FEC_ATIME_CORR);
+	/* dummy read to update the timer. */
+	timecounter_read(&fep->tc);
 
 	spin_unlock_irqrestore(&fep->tmreg_lock, flags);
 
@@ -188,12 +375,19 @@ static int fec_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	    container_of(ptp, struct fec_enet_private, ptp_caps);
 	unsigned long flags;
 	u64 now;
+	u32 counter;
 
 	spin_lock_irqsave(&fep->tmreg_lock, flags);
 
 	now = timecounter_read(&fep->tc);
 	now += delta;
 
+	/* Get the timer value based on adjusted timestamp.
+	 * Update the counter with the masked value.
+	 */
+	counter = now & fep->cc.mask;
+	writel(counter, fep->hwp + FEC_ATIME);
+
 	/* reset the timecounter */
 	timecounter_init(&fep->tc, &fep->cc, now);
 
@@ -244,6 +438,7 @@ static int fec_ptp_settime(struct ptp_clock_info *ptp,
 
 	u64 ns;
 	unsigned long flags;
+	u32 counter;
 
 	mutex_lock(&fep->ptp_clk_mutex);
 	/* Check the ptp clock */
@@ -254,8 +449,13 @@ static int fec_ptp_settime(struct ptp_clock_info *ptp,
 
 	ns = ts->tv_sec * 1000000000ULL;
 	ns += ts->tv_nsec;
+	/* Get the timer value based on timestamp.
+	 * Update the counter with the masked value.
+	 */
+	counter = ns & fep->cc.mask;
 
 	spin_lock_irqsave(&fep->tmreg_lock, flags);
+	writel(counter, fep->hwp + FEC_ATIME);
 	timecounter_init(&fep->tc, &fep->cc, ns);
 	spin_unlock_irqrestore(&fep->tmreg_lock, flags);
 	mutex_unlock(&fep->ptp_clk_mutex);
@@ -272,6 +472,15 @@ static int fec_ptp_settime(struct ptp_clock_info *ptp,
 static int fec_ptp_enable(struct ptp_clock_info *ptp,
 			  struct ptp_clock_request *rq, int on)
 {
+	struct fec_enet_private *fep =
+	    container_of(ptp, struct fec_enet_private, ptp_caps);
+	int ret = 0;
+
+	if (rq->type == PTP_CLK_REQ_PPS) {
+		ret = fec_ptp_enable_pps(fep, on);
+
+		return ret;
+	}
 	return -EOPNOTSUPP;
 }
 
@@ -386,7 +595,7 @@ void fec_ptp_init(struct platform_device *pdev)
 	fep->ptp_caps.n_ext_ts = 0;
 	fep->ptp_caps.n_per_out = 0;
 	fep->ptp_caps.n_pins = 0;
-	fep->ptp_caps.pps = 0;
+	fep->ptp_caps.pps = 1;
 	fep->ptp_caps.adjfreq = fec_ptp_adjfreq;
 	fep->ptp_caps.adjtime = fec_ptp_adjtime;
 	fep->ptp_caps.gettime = fec_ptp_gettime;
@@ -394,6 +603,7 @@ void fec_ptp_init(struct platform_device *pdev)
 	fep->ptp_caps.enable = fec_ptp_enable;
 
 	fep->cycle_speed = clk_get_rate(fep->clk_ptp);
+	fep->ptp_inc = NSEC_PER_SEC / fep->cycle_speed;
 
 	spin_lock_init(&fep->tmreg_lock);
 
@@ -409,3 +619,36 @@ void fec_ptp_init(struct platform_device *pdev)
 
 	schedule_delayed_work(&fep->time_keep, HZ);
 }
+
+/**
+ * fec_ptp_check_pps_event
+ * @fep: the fec_enet_private structure handle
+ *
+ * This function check the pps event and reload the timer compare counter.
+ */
+uint fec_ptp_check_pps_event(struct fec_enet_private *fep)
+{
+	u32 val;
+	u8 channel = fep->pps_channel;
+	struct ptp_clock_event event;
+
+	val = readl(fep->hwp + FEC_TCSR(channel));
+	if (val & FEC_T_TF_MASK) {
+		/* Write the next next compare(not the next according the spec)
+		 * value to the register
+		 */
+		writel(fep->next_counter, fep->hwp + FEC_TCCR(channel));
+		do {
+			writel(val, fep->hwp + FEC_TCSR(channel));
+		} while (readl(fep->hwp + FEC_TCSR(channel)) & FEC_T_TF_MASK);
+
+		/* Update the counter; */
+		fep->next_counter = (fep->next_counter + fep->reload_period) & fep->cc.mask;
+
+		event.type = PTP_CLOCK_PPS;
+		ptp_clock_event(fep->ptp_clock, &event);
+		return 1;
+	}
+
+	return 0;
+}

drivers/net/ethernet/freescale/gianfar.c

@@ -338,7 +338,7 @@ static void gfar_init_tx_rx_base(struct gfar_private *priv)
 
 static void gfar_rx_buff_size_config(struct gfar_private *priv)
 {
-	int frame_size = priv->ndev->mtu + ETH_HLEN;
+	int frame_size = priv->ndev->mtu + ETH_HLEN + ETH_FCS_LEN;
 
 	/* set this when rx hw offload (TOE) functions are being used */
 	priv->uses_rxfcb = 0;

drivers/net/ethernet/intel/Kconfig

@@ -320,4 +320,15 @@ config FM10K
 	  To compile this driver as a module, choose M here. The module
 	  will be called fm10k.  MSI-X interrupt support is required
 
+config FM10K_VXLAN
+	bool "Virtual eXtensible Local Area Network Support"
+	default n
+	depends on FM10K && VXLAN && !(FM10K=y && VXLAN=m)
+	---help---
+	  This allows one to create VXLAN virtual interfaces that provide
+	  Layer 2 Networks over Layer 3 Networks. VXLAN is often used
+	  to tunnel virtual network infrastructure in virtualized environments.
+	  Say Y here if you want to use Virtual eXtensible Local Area Network
+	  (VXLAN) in the driver.
+
 endif # NET_VENDOR_INTEL

drivers/net/ethernet/intel/fm10k/fm10k_main.c

@@ -929,6 +929,30 @@ static bool fm10k_tx_desc_push(struct fm10k_ring *tx_ring,
 	return i == tx_ring->count;
 }
 
+static int __fm10k_maybe_stop_tx(struct fm10k_ring *tx_ring, u16 size)
+{
+	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
+
+	smp_mb();
+
+	/* We need to check again in a case another CPU has just
+	 * made room available. */
+	if (likely(fm10k_desc_unused(tx_ring) < size))
+		return -EBUSY;
+
+	/* A reprieve! - use start_queue because it doesn't call schedule */
+	netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
+	++tx_ring->tx_stats.restart_queue;
+	return 0;
+}
+
+static inline int fm10k_maybe_stop_tx(struct fm10k_ring *tx_ring, u16 size)
+{
+	if (likely(fm10k_desc_unused(tx_ring) >= size))
+		return 0;
+	return __fm10k_maybe_stop_tx(tx_ring, size);
+}
+
 static void fm10k_tx_map(struct fm10k_ring *tx_ring,
 			 struct fm10k_tx_buffer *first)
 {
@@ -1022,13 +1046,18 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring,
 
 	tx_ring->next_to_use = i;
 
+	/* Make sure there is space in the ring for the next send. */
+	fm10k_maybe_stop_tx(tx_ring, DESC_NEEDED);
+
 	/* notify HW of packet */
-	writel(i, tx_ring->tail);
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+		writel(i, tx_ring->tail);
 
-	/* we need this if more than one processor can write to our tail
-	 * at a time, it synchronizes IO on IA64/Altix systems
-	 */
-	mmiowb();
+		/* we need this if more than one processor can write to our tail
+		 * at a time, it synchronizes IO on IA64/Altix systems
+		 */
+		mmiowb();
+	}
 
 	return;
 dma_error:
@@ -1048,30 +1077,6 @@ dma_error:
 	tx_ring->next_to_use = i;
 }
 
-static int __fm10k_maybe_stop_tx(struct fm10k_ring *tx_ring, u16 size)
-{
-	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
-
-	smp_mb();
-
-	/* We need to check again in a case another CPU has just
-	 * made room available. */
-	if (likely(fm10k_desc_unused(tx_ring) < size))
-		return -EBUSY;
-
-	/* A reprieve! - use start_queue because it doesn't call schedule */
-	netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
-	++tx_ring->tx_stats.restart_queue;
-	return 0;
-}
-
-static inline int fm10k_maybe_stop_tx(struct fm10k_ring *tx_ring, u16 size)
-{
-	if (likely(fm10k_desc_unused(tx_ring) >= size))
-		return 0;
-	return __fm10k_maybe_stop_tx(tx_ring, size);
-}
-
 netdev_tx_t fm10k_xmit_frame_ring(struct sk_buff *skb,
 				  struct fm10k_ring *tx_ring)
 {
@@ -1116,8 +1121,6 @@ netdev_tx_t fm10k_xmit_frame_ring(struct sk_buff *skb,
 
 	fm10k_tx_map(tx_ring, first);
 
-	fm10k_maybe_stop_tx(tx_ring, DESC_NEEDED);
-
 	return NETDEV_TX_OK;
 
 out_drop:

drivers/net/ethernet/intel/fm10k/fm10k_netdev.c

@@ -20,9 +20,9 @@
 
 #include "fm10k.h"
 #include <linux/vmalloc.h>
-#if IS_ENABLED(CONFIG_VXLAN)
+#if IS_ENABLED(CONFIG_FM10K_VXLAN)
 #include <net/vxlan.h>
-#endif /* CONFIG_VXLAN */
+#endif /* CONFIG_FM10K_VXLAN */
 
 /**
  * fm10k_setup_tx_resources - allocate Tx resources (Descriptors)
@@ -556,7 +556,7 @@ int fm10k_open(struct net_device *netdev)
 	if (err)
 		goto err_set_queues;
 
-#if IS_ENABLED(CONFIG_VXLAN)
+#if IS_ENABLED(CONFIG_FM10K_VXLAN)
 	/* update VXLAN port configuration */
 	vxlan_get_rx_port(netdev);
 
@@ -785,14 +785,14 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set)
 	if (!(netdev->flags & IFF_PROMISC)) {
 		err = hw->mac.ops.update_vlan(hw, vid, 0, set);
 		if (err)
-			return err;
+			goto err_out;
 	}
 
 	/* update our base MAC address */
 	err = hw->mac.ops.update_uc_addr(hw, interface->glort, hw->mac.addr,
 					 vid, set, 0);
 	if (err)
-		return err;
+		goto err_out;
 
 	/* set vid prior to syncing/unsyncing the VLAN */
 	interface->vid = vid + (set ? VLAN_N_VID : 0);
@@ -801,9 +801,10 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set)
 	__dev_uc_unsync(netdev, fm10k_uc_vlan_unsync);
 	__dev_mc_unsync(netdev, fm10k_mc_vlan_unsync);
 
+err_out:
 	fm10k_mbx_unlock(interface);
 
-	return 0;
+	return err;
 }
 
 static int fm10k_vlan_rx_add_vid(struct net_device *netdev,

drivers/net/ethernet/intel/fm10k/fm10k_pci.c

@@ -1489,6 +1489,7 @@ void fm10k_up(struct fm10k_intfc *interface)
 	netif_tx_start_all_queues(interface->netdev);
 
 	/* kick off the service timer */
+	hw->mac.get_host_state = 1;
 	mod_timer(&interface->service_timer, jiffies);
 }
 

drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c

@@ -1261,6 +1261,9 @@ int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting)
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 regval;
 
+	if (vf >= adapter->num_vfs)
+		return -EINVAL;
+
 	adapter->vfinfo[vf].spoofchk_enabled = setting;
 
 	regval = IXGBE_READ_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg));

drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c

@@ -11,7 +11,7 @@ static const struct qlcnic_mailbox_metadata qlcnic_mbx_tbl[] = {
 	{QLCNIC_CMD_CREATE_RX_CTX, 4, 1},
 	{QLCNIC_CMD_DESTROY_RX_CTX, 2, 1},
 	{QLCNIC_CMD_CREATE_TX_CTX, 4, 1},
-	{QLCNIC_CMD_DESTROY_TX_CTX, 2, 1},
+	{QLCNIC_CMD_DESTROY_TX_CTX, 3, 1},
 	{QLCNIC_CMD_INTRPT_TEST, 4, 1},
 	{QLCNIC_CMD_SET_MTU, 4, 1},
 	{QLCNIC_CMD_READ_PHY, 4, 2},
@@ -32,7 +32,7 @@ static const struct qlcnic_mailbox_metadata qlcnic_mbx_tbl[] = {
 	{QLCNIC_CMD_CONFIGURE_ESWITCH, 4, 1},
 	{QLCNIC_CMD_GET_MAC_STATS, 4, 1},
 	{QLCNIC_CMD_GET_ESWITCH_PORT_CONFIG, 4, 3},
-	{QLCNIC_CMD_GET_ESWITCH_STATS, 5, 1},
+	{QLCNIC_CMD_GET_ESWITCH_STATS, 4, 1},
 	{QLCNIC_CMD_CONFIG_PORT, 4, 1},
 	{QLCNIC_CMD_TEMP_SIZE, 4, 4},
 	{QLCNIC_CMD_GET_TEMP_HDR, 4, 1},
@@ -129,7 +129,7 @@ int qlcnic_82xx_issue_cmd(struct qlcnic_adapter *adapter,
 	}
 
 	QLCWR32(adapter, QLCNIC_SIGN_CRB_OFFSET, signature);
-	for (i = 1; i < QLCNIC_CDRP_MAX_ARGS; i++)
+	for (i = 1; i < cmd->req.num; i++)
 		QLCWR32(adapter, QLCNIC_CDRP_ARG(i), cmd->req.arg[i]);
 	QLCWR32(adapter, QLCNIC_CDRP_CRB_OFFSET,
 		QLCNIC_CDRP_FORM_CMD(cmd->req.arg[0]));

drivers/net/ethernet/sfc/nic.h

@@ -71,9 +71,17 @@ efx_tx_desc(struct efx_tx_queue *tx_queue, unsigned int index)
 	return ((efx_qword_t *) (tx_queue->txd.buf.addr)) + index;
 }
 
-/* Report whether the NIC considers this TX queue empty, given the
- * write_count used for the last doorbell push.  May return false
- * negative.
+/* Get partner of a TX queue, seen as part of the same net core queue */
+static struct efx_tx_queue *efx_tx_queue_partner(struct efx_tx_queue *tx_queue)
+{
+	if (tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD)
+		return tx_queue - EFX_TXQ_TYPE_OFFLOAD;
+	else
+		return tx_queue + EFX_TXQ_TYPE_OFFLOAD;
+}
+
+/* Report whether this TX queue would be empty for the given write_count.
+ * May return false negative.
  */
 static inline bool __efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue,
 					 unsigned int write_count)
@@ -86,9 +94,18 @@ static inline bool __efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue,
 	return ((empty_read_count ^ write_count) & ~EFX_EMPTY_COUNT_VALID) == 0;
 }
 
-static inline bool efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue)
+/* Decide whether we can use TX PIO, ie. write packet data directly into
+ * a buffer on the device.  This can reduce latency at the expense of
+ * throughput, so we only do this if both hardware and software TX rings
+ * are empty.  This also ensures that only one packet at a time can be
+ * using the PIO buffer.
+ */
+static inline bool efx_nic_may_tx_pio(struct efx_tx_queue *tx_queue)
 {
-	return __efx_nic_tx_is_empty(tx_queue, tx_queue->write_count);
+	struct efx_tx_queue *partner = efx_tx_queue_partner(tx_queue);
+	return tx_queue->piobuf &&
+	       __efx_nic_tx_is_empty(tx_queue, tx_queue->insert_count) &&
+	       __efx_nic_tx_is_empty(partner, partner->insert_count);
 }
 
 /* Decide whether to push a TX descriptor to the NIC vs merely writing
@@ -96,6 +113,8 @@ static inline bool efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue)
  * descriptor to an empty queue, but is otherwise pointless.  Further,
  * Falcon and Siena have hardware bugs (SF bug 33851) that may be
  * triggered if we don't check this.
+ * We use the write_count used for the last doorbell push, to get the
+ * NIC's view of the tx queue.
  */
 static inline bool efx_nic_may_push_tx_desc(struct efx_tx_queue *tx_queue,
 					    unsigned int write_count)

drivers/net/ethernet/sfc/tx.c

@@ -132,15 +132,6 @@ unsigned int efx_tx_max_skb_descs(struct efx_nic *efx)
 	return max_descs;
 }
 
-/* Get partner of a TX queue, seen as part of the same net core queue */
-static struct efx_tx_queue *efx_tx_queue_partner(struct efx_tx_queue *tx_queue)
-{
-	if (tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD)
-		return tx_queue - EFX_TXQ_TYPE_OFFLOAD;
-	else
-		return tx_queue + EFX_TXQ_TYPE_OFFLOAD;
-}
-
 static void efx_tx_maybe_stop_queue(struct efx_tx_queue *txq1)
 {
 	/* We need to consider both queues that the net core sees as one */
@@ -344,6 +335,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 	struct efx_nic *efx = tx_queue->efx;
 	struct device *dma_dev = &efx->pci_dev->dev;
 	struct efx_tx_buffer *buffer;
+	unsigned int old_insert_count = tx_queue->insert_count;
 	skb_frag_t *fragment;
 	unsigned int len, unmap_len = 0;
 	dma_addr_t dma_addr, unmap_addr = 0;
@@ -351,7 +343,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 	unsigned short dma_flags;
 	int i = 0;
 
-	EFX_BUG_ON_PARANOID(tx_queue->write_count != tx_queue->insert_count);
+	EFX_BUG_ON_PARANOID(tx_queue->write_count > tx_queue->insert_count);
 
 	if (skb_shinfo(skb)->gso_size)
 		return efx_enqueue_skb_tso(tx_queue, skb);
@@ -369,9 +361,8 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 
 	/* Consider using PIO for short packets */
 #ifdef EFX_USE_PIO
-	if (skb->len <= efx_piobuf_size && tx_queue->piobuf &&
-	    efx_nic_tx_is_empty(tx_queue) &&
-	    efx_nic_tx_is_empty(efx_tx_queue_partner(tx_queue))) {
+	if (skb->len <= efx_piobuf_size && !skb->xmit_more &&
+	    efx_nic_may_tx_pio(tx_queue)) {
 		buffer = efx_enqueue_skb_pio(tx_queue, skb);
 		dma_flags = EFX_TX_BUF_OPTION;
 		goto finish_packet;
@@ -439,13 +430,14 @@ finish_packet:
 
 	netdev_tx_sent_queue(tx_queue->core_txq, skb->len);
 
+	efx_tx_maybe_stop_queue(tx_queue);
+
 	/* Pass off to hardware */
-	efx_nic_push_buffers(tx_queue);
+	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+		efx_nic_push_buffers(tx_queue);
 
 	tx_queue->tx_packets++;
 
-	efx_tx_maybe_stop_queue(tx_queue);
-
 	return NETDEV_TX_OK;
 
  dma_err:
@@ -458,7 +450,7 @@ finish_packet:
 	dev_kfree_skb_any(skb);
 
 	/* Work backwards until we hit the original insert pointer value */
-	while (tx_queue->insert_count != tx_queue->write_count) {
+	while (tx_queue->insert_count != old_insert_count) {
 		unsigned int pkts_compl = 0, bytes_compl = 0;
 		--tx_queue->insert_count;
 		buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
@@ -989,12 +981,13 @@ static int efx_tso_put_header(struct efx_tx_queue *tx_queue,
 /* Remove buffers put into a tx_queue.  None of the buffers must have
  * an skb attached.
  */
-static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue)
+static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue,
+			       unsigned int insert_count)
 {
 	struct efx_tx_buffer *buffer;
 
 	/* Work backwards until we hit the original insert pointer value */
-	while (tx_queue->insert_count != tx_queue->write_count) {
+	while (tx_queue->insert_count != insert_count) {
 		--tx_queue->insert_count;
 		buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
 		efx_dequeue_buffer(tx_queue, buffer, NULL, NULL);
@@ -1258,13 +1251,14 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 			       struct sk_buff *skb)
 {
 	struct efx_nic *efx = tx_queue->efx;
+	unsigned int old_insert_count = tx_queue->insert_count;
 	int frag_i, rc;
 	struct tso_state state;
 
 	/* Find the packet protocol and sanity-check it */
 	state.protocol = efx_tso_check_protocol(skb);
 
-	EFX_BUG_ON_PARANOID(tx_queue->write_count != tx_queue->insert_count);
+	EFX_BUG_ON_PARANOID(tx_queue->write_count > tx_queue->insert_count);
 
 	rc = tso_start(&state, efx, skb);
 	if (rc)
@@ -1308,11 +1302,12 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 
 	netdev_tx_sent_queue(tx_queue->core_txq, skb->len);
 
-	/* Pass off to hardware */
-	efx_nic_push_buffers(tx_queue);
-
 	efx_tx_maybe_stop_queue(tx_queue);
 
+	/* Pass off to hardware */
+	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+		efx_nic_push_buffers(tx_queue);
+
 	tx_queue->tso_bursts++;
 	return NETDEV_TX_OK;
 
@@ -1336,6 +1331,6 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 		dma_unmap_single(&efx->pci_dev->dev, state.header_dma_addr,
 				 state.header_unmap_len, DMA_TO_DEVICE);
 
-	efx_enqueue_unwind(tx_queue);
+	efx_enqueue_unwind(tx_queue, old_insert_count);
 	return NETDEV_TX_OK;
 }

drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c

@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2003-2014 STMicroelectronics (R&D) Limited
  * Author: Srinivas Kandagatla <srinivas.kandagatla@st.com>
- *
+ * Contributors: Giuseppe Cavallaro <peppe.cavallaro@st.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -22,45 +22,22 @@
 #include <linux/of.h>
 #include <linux/of_net.h>
 
+#define DWMAC_125MHZ	125000000
+#define DWMAC_50MHZ	50000000
+#define DWMAC_25MHZ	25000000
+#define DWMAC_2_5MHZ	2500000
+
+#define IS_PHY_IF_MODE_RGMII(iface)	(iface == PHY_INTERFACE_MODE_RGMII || \
+			iface == PHY_INTERFACE_MODE_RGMII_ID || \
+			iface == PHY_INTERFACE_MODE_RGMII_RXID || \
+			iface == PHY_INTERFACE_MODE_RGMII_TXID)
+
+#define IS_PHY_IF_MODE_GBIT(iface)	(IS_PHY_IF_MODE_RGMII(iface) || \
+					 iface == PHY_INTERFACE_MODE_GMII)
+
+/* STiH4xx register definitions (STiH415/STiH416/STiH407/STiH410 families) */
+
 /**
- *			STi GMAC glue logic.
- *			--------------------
- *
- *		 _
- *		|  \
- *	--------|0  \ ETH_SEL_INTERNAL_NOTEXT_PHYCLK
- * phyclk	|    |___________________________________________
- *		|    |	|			(phyclk-in)
- *	--------|1  /	|
- * int-clk	|_ /	|
- *			|	 _
- *			|	|  \
- *			|_______|1  \ ETH_SEL_TX_RETIME_CLK
- *				|    |___________________________
- *				|    |		(tx-retime-clk)
- *			 _______|0  /
- *			|	|_ /
- *		 _	|
- *		|  \	|
- *	--------|0  \	|
- * clk_125	|    |__|
- *		|    |	ETH_SEL_TXCLK_NOT_CLK125
- *	--------|1  /
- * txclk	|_ /
- *
- *
- * ETH_SEL_INTERNAL_NOTEXT_PHYCLK is valid only for RMII where PHY can
- * generate 50MHz clock or MAC can generate it.
- * This bit is configured by "st,ext-phyclk" property.
- *
- * ETH_SEL_TXCLK_NOT_CLK125 is only valid for gigabit modes, where the 125Mhz
- * clock either comes from clk-125 pin or txclk pin. This configuration is
- * totally driven by the board wiring. This bit is configured by
- * "st,tx-retime-src" property.
- *
- * TXCLK configuration is different for different phy interface modes
- * and changes according to link speed in modes like RGMII.
- *
  * Below table summarizes the clock requirement and clock sources for
  * supported phy interface modes with link speeds.
  * ________________________________________________
@@ -74,44 +51,58 @@
  * ------------------------------------------------
  *|	RGMII	|     125Mhz	 |	25Mhz	   |
  *|		|  clk-125/txclk |	clkgen     |
+ *|		|    clkgen	 |		   |
  * ------------------------------------------------
  *|	RMII	|	n/a	 |	25Mhz	   |
  *|		|		 |clkgen/phyclk-in |
  * ------------------------------------------------
  *
- * TX lines are always retimed with a clk, which can vary depending
- * on the board configuration. Below is the table of these bits
- * in eth configuration register depending on source of retime clk.
- *
- *---------------------------------------------------------------
- * src	 | tx_rt_clk	| int_not_ext_phyclk	| txclk_n_clk125|
- *---------------------------------------------------------------
- * txclk |	0	|	n/a		|	1	|
- *---------------------------------------------------------------
- * ck_125|	0	|	n/a		|	0	|
- *---------------------------------------------------------------
- * phyclk|	1	|	0		|	n/a	|
- *---------------------------------------------------------------
- * clkgen|	1	|	1		|	n/a	|
- *---------------------------------------------------------------
+ *	  Register Configuration
+ *-------------------------------
+ * src	 |BIT(8)| BIT(7)| BIT(6)|
+ *-------------------------------
+ * txclk |   0	|  n/a	|   1	|
+ *-------------------------------
+ * ck_125|   0	|  n/a	|   0	|
+ *-------------------------------
+ * phyclk|   1	|   0	|  n/a	|
+ *-------------------------------
+ * clkgen|   1	|   1	|  n/a	|
+ *-------------------------------
  */
 
- /* Register definition */
+#define STIH4XX_RETIME_SRC_MASK			GENMASK(8, 6)
+#define STIH4XX_ETH_SEL_TX_RETIME_CLK		BIT(8)
+#define STIH4XX_ETH_SEL_INTERNAL_NOTEXT_PHYCLK	BIT(7)
+#define STIH4XX_ETH_SEL_TXCLK_NOT_CLK125	BIT(6)
+
+/* STiD127 register definitions */
 
- /* 3 bits [8:6]
-  *  [6:6]      ETH_SEL_TXCLK_NOT_CLK125
-  *  [7:7]      ETH_SEL_INTERNAL_NOTEXT_PHYCLK
-  *  [8:8]      ETH_SEL_TX_RETIME_CLK
-  *
-  */
+/**
+ *-----------------------
+ * src	 |BIT(6)| BIT(7)|
+ *-----------------------
+ * MII   |  1	|   n/a	|
+ *-----------------------
+ * RMII  |  n/a	|   1	|
+ * clkgen|	|	|
+ *-----------------------
+ * RMII  |  n/a	|   0	|
+ * phyclk|	|	|
+ *-----------------------
+ * RGMII |  1	|  n/a	|
+ * clkgen|	|	|
+ *-----------------------
+ */
 
-#define TX_RETIME_SRC_MASK		GENMASK(8, 6)
-#define ETH_SEL_TX_RETIME_CLK		BIT(8)
-#define ETH_SEL_INTERNAL_NOTEXT_PHYCLK	BIT(7)
-#define ETH_SEL_TXCLK_NOT_CLK125	BIT(6)
+#define STID127_RETIME_SRC_MASK			GENMASK(7, 6)
+#define STID127_ETH_SEL_INTERNAL_NOTEXT_PHYCLK	BIT(7)
+#define STID127_ETH_SEL_INTERNAL_NOTEXT_TXCLK	BIT(6)
 
-#define ENMII_MASK			GENMASK(5, 5)
-#define ENMII				BIT(5)
+#define ENMII_MASK	GENMASK(5, 5)
+#define ENMII		BIT(5)
+#define EN_MASK		GENMASK(1, 1)
+#define EN		BIT(1)
 
 /**
  * 3 bits [4:2]
@@ -120,29 +111,23 @@
  *	010-SGMII
  *	100-RMII
 */
-#define MII_PHY_SEL_MASK		GENMASK(4, 2)
-#define ETH_PHY_SEL_RMII		BIT(4)
-#define ETH_PHY_SEL_SGMII		BIT(3)
-#define ETH_PHY_SEL_RGMII		BIT(2)
-#define ETH_PHY_SEL_GMII		0x0
-#define ETH_PHY_SEL_MII			0x0
-
-#define IS_PHY_IF_MODE_RGMII(iface)	(iface == PHY_INTERFACE_MODE_RGMII || \
-			iface == PHY_INTERFACE_MODE_RGMII_ID || \
-			iface == PHY_INTERFACE_MODE_RGMII_RXID || \
-			iface == PHY_INTERFACE_MODE_RGMII_TXID)
-
-#define IS_PHY_IF_MODE_GBIT(iface)	(IS_PHY_IF_MODE_RGMII(iface) || \
-			iface == PHY_INTERFACE_MODE_GMII)
+#define MII_PHY_SEL_MASK	GENMASK(4, 2)
+#define ETH_PHY_SEL_RMII	BIT(4)
+#define ETH_PHY_SEL_SGMII	BIT(3)
+#define ETH_PHY_SEL_RGMII	BIT(2)
+#define ETH_PHY_SEL_GMII	0x0
+#define ETH_PHY_SEL_MII		0x0
 
 struct sti_dwmac {
-	int interface;
-	bool ext_phyclk;
-	bool is_tx_retime_src_clk_125;
-	struct clk *clk;
-	int reg;
+	int interface;		/* MII interface */
+	bool ext_phyclk;	/* Clock from external PHY */
+	u32 tx_retime_src;	/* TXCLK Retiming*/
+	struct clk *clk;	/* PHY clock */
+	int ctrl_reg;		/* GMAC glue-logic control register */
+	int clk_sel_reg;	/* GMAC ext clk selection register */
 	struct device *dev;
 	struct regmap *regmap;
+	u32 speed;
 };
 
 static u32 phy_intf_sels[] = {
@@ -162,74 +147,133 @@ enum {
 	TX_RETIME_SRC_CLKGEN,
 };
 
-static const char *const tx_retime_srcs[] = {
-	[TX_RETIME_SRC_NA] = "",
-	[TX_RETIME_SRC_TXCLK] = "txclk",
-	[TX_RETIME_SRC_CLK_125] = "clk_125",
-	[TX_RETIME_SRC_PHYCLK] = "phyclk",
-	[TX_RETIME_SRC_CLKGEN] = "clkgen",
-};
-
-static u32 tx_retime_val[] = {
-	[TX_RETIME_SRC_TXCLK] = ETH_SEL_TXCLK_NOT_CLK125,
+static u32 stih4xx_tx_retime_val[] = {
+	[TX_RETIME_SRC_TXCLK] = STIH4XX_ETH_SEL_TXCLK_NOT_CLK125,
 	[TX_RETIME_SRC_CLK_125] = 0x0,
-	[TX_RETIME_SRC_PHYCLK] = ETH_SEL_TX_RETIME_CLK,
-	[TX_RETIME_SRC_CLKGEN] = ETH_SEL_TX_RETIME_CLK |
-	    ETH_SEL_INTERNAL_NOTEXT_PHYCLK,
+	[TX_RETIME_SRC_PHYCLK] = STIH4XX_ETH_SEL_TX_RETIME_CLK,
+	[TX_RETIME_SRC_CLKGEN] = STIH4XX_ETH_SEL_TX_RETIME_CLK
+				 | STIH4XX_ETH_SEL_INTERNAL_NOTEXT_PHYCLK,
 };
 
-static void setup_retime_src(struct sti_dwmac *dwmac, u32 spd)
+static void stih4xx_fix_retime_src(void *priv, u32 spd)
 {
-	u32 src = 0, freq = 0;
-
-	if (spd == SPEED_100) {
-		if (dwmac->interface == PHY_INTERFACE_MODE_MII ||
-		    dwmac->interface == PHY_INTERFACE_MODE_GMII) {
-			src = TX_RETIME_SRC_TXCLK;
-		} else if (dwmac->interface == PHY_INTERFACE_MODE_RMII) {
-			if (dwmac->ext_phyclk) {
-				src = TX_RETIME_SRC_PHYCLK;
-			} else {
-				src = TX_RETIME_SRC_CLKGEN;
-				freq = 50000000;
-			}
-
-		} else if (IS_PHY_IF_MODE_RGMII(dwmac->interface)) {
+	struct sti_dwmac *dwmac = priv;
+	u32 src = dwmac->tx_retime_src;
+	u32 reg = dwmac->ctrl_reg;
+	u32 freq = 0;
+
+	if (dwmac->interface == PHY_INTERFACE_MODE_MII) {
+		src = TX_RETIME_SRC_TXCLK;
+	} else if (dwmac->interface == PHY_INTERFACE_MODE_RMII) {
+		if (dwmac->ext_phyclk) {
+			src = TX_RETIME_SRC_PHYCLK;
+		} else {
 			src = TX_RETIME_SRC_CLKGEN;
-			freq = 25000000;
+			freq = DWMAC_50MHZ;
 		}
+	} else if (IS_PHY_IF_MODE_RGMII(dwmac->interface)) {
+		/* On GiGa clk source can be either ext or from clkgen */
+		if (spd == SPEED_1000) {
+			freq = DWMAC_125MHZ;
+		} else {
+			/* Switch to clkgen for these speeds */
+			src = TX_RETIME_SRC_CLKGEN;
+			if (spd == SPEED_100)
+				freq = DWMAC_25MHZ;
+			else if (spd == SPEED_10)
+				freq = DWMAC_2_5MHZ;
+		}
+	}
 
-		if (src == TX_RETIME_SRC_CLKGEN && dwmac->clk)
-			clk_set_rate(dwmac->clk, freq);
+	if (src == TX_RETIME_SRC_CLKGEN && dwmac->clk && freq)
+		clk_set_rate(dwmac->clk, freq);
 
-	} else if (spd == SPEED_1000) {
-		if (dwmac->is_tx_retime_src_clk_125)
-			src = TX_RETIME_SRC_CLK_125;
-		else
-			src = TX_RETIME_SRC_TXCLK;
+	regmap_update_bits(dwmac->regmap, reg, STIH4XX_RETIME_SRC_MASK,
+			   stih4xx_tx_retime_val[src]);
+}
+
+static void stid127_fix_retime_src(void *priv, u32 spd)
+{
+	struct sti_dwmac *dwmac = priv;
+	u32 reg = dwmac->ctrl_reg;
+	u32 freq = 0;
+	u32 val = 0;
+
+	if (dwmac->interface == PHY_INTERFACE_MODE_MII) {
+		val = STID127_ETH_SEL_INTERNAL_NOTEXT_TXCLK;
+	} else if (dwmac->interface == PHY_INTERFACE_MODE_RMII) {
+		if (!dwmac->ext_phyclk) {
+			val = STID127_ETH_SEL_INTERNAL_NOTEXT_PHYCLK;
+			freq = DWMAC_50MHZ;
+		}
+	} else if (IS_PHY_IF_MODE_RGMII(dwmac->interface)) {
+		val = STID127_ETH_SEL_INTERNAL_NOTEXT_TXCLK;
+		if (spd == SPEED_1000)
+			freq = DWMAC_125MHZ;
+		else if (spd == SPEED_100)
+			freq = DWMAC_25MHZ;
+		else if (spd == SPEED_10)
+			freq = DWMAC_2_5MHZ;
 	}
 
-	regmap_update_bits(dwmac->regmap, dwmac->reg,
-			   TX_RETIME_SRC_MASK, tx_retime_val[src]);
+	if (dwmac->clk && freq)
+		clk_set_rate(dwmac->clk, freq);
+
+	regmap_update_bits(dwmac->regmap, reg, STID127_RETIME_SRC_MASK, val);
 }
 
-static void sti_dwmac_exit(struct platform_device *pdev, void *priv)
+static void sti_dwmac_ctrl_init(struct sti_dwmac *dwmac)
 {
-	struct sti_dwmac *dwmac = priv;
+	struct regmap *regmap = dwmac->regmap;
+	int iface = dwmac->interface;
+	struct device *dev = dwmac->dev;
+	struct device_node *np = dev->of_node;
+	u32 reg = dwmac->ctrl_reg;
+	u32 val;
 
 	if (dwmac->clk)
-		clk_disable_unprepare(dwmac->clk);
+		clk_prepare_enable(dwmac->clk);
+
+	if (of_property_read_bool(np, "st,gmac_en"))
+		regmap_update_bits(regmap, reg, EN_MASK, EN);
+
+	regmap_update_bits(regmap, reg, MII_PHY_SEL_MASK, phy_intf_sels[iface]);
+
+	val = (iface == PHY_INTERFACE_MODE_REVMII) ? 0 : ENMII;
+	regmap_update_bits(regmap, reg, ENMII_MASK, val);
+}
+
+static int stix4xx_init(struct platform_device *pdev, void *priv)
+{
+	struct sti_dwmac *dwmac = priv;
+	u32 spd = dwmac->speed;
+
+	sti_dwmac_ctrl_init(dwmac);
+
+	stih4xx_fix_retime_src(priv, spd);
+
+	return 0;
 }
 
-static void sti_fix_mac_speed(void *priv, unsigned int spd)
+static int stid127_init(struct platform_device *pdev, void *priv)
 {
 	struct sti_dwmac *dwmac = priv;
+	u32 spd = dwmac->speed;
 
-	setup_retime_src(dwmac, spd);
+	sti_dwmac_ctrl_init(dwmac);
 
-	return;
+	stid127_fix_retime_src(priv, spd);
+
+	return 0;
 }
 
+static void sti_dwmac_exit(struct platform_device *pdev, void *priv)
+{
+	struct sti_dwmac *dwmac = priv;
+
+	if (dwmac->clk)
+		clk_disable_unprepare(dwmac->clk);
+}
 static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
 				struct platform_device *pdev)
 {
@@ -245,6 +289,13 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sti-ethconf");
 	if (!res)
 		return -ENODATA;
+	dwmac->ctrl_reg = res->start;
+
+	/* clk selection from extra syscfg register */
+	dwmac->clk_sel_reg = -ENXIO;
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sti-clkconf");
+	if (res)
+		dwmac->clk_sel_reg = res->start;
 
 	regmap = syscon_regmap_lookup_by_phandle(np, "st,syscon");
 	if (IS_ERR(regmap))
@@ -253,53 +304,31 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
 	dwmac->dev = dev;
 	dwmac->interface = of_get_phy_mode(np);
 	dwmac->regmap = regmap;
-	dwmac->reg = res->start;
 	dwmac->ext_phyclk = of_property_read_bool(np, "st,ext-phyclk");
-	dwmac->is_tx_retime_src_clk_125 = false;
+	dwmac->tx_retime_src = TX_RETIME_SRC_NA;
+	dwmac->speed = SPEED_100;
 
 	if (IS_PHY_IF_MODE_GBIT(dwmac->interface)) {
 		const char *rs;
+		dwmac->tx_retime_src = TX_RETIME_SRC_CLKGEN;
 
 		err = of_property_read_string(np, "st,tx-retime-src", &rs);
-		if (err < 0) {
-			dev_err(dev, "st,tx-retime-src not specified\n");
-			return err;
-		}
+		if (err < 0)
+			dev_warn(dev, "Use internal clock source\n");
 
 		if (!strcasecmp(rs, "clk_125"))
-			dwmac->is_tx_retime_src_clk_125 = true;
+			dwmac->tx_retime_src = TX_RETIME_SRC_CLK_125;
+		else if (!strcasecmp(rs, "txclk"))
+			dwmac->tx_retime_src = TX_RETIME_SRC_TXCLK;
+
+		dwmac->speed = SPEED_1000;
 	}
 
 	dwmac->clk = devm_clk_get(dev, "sti-ethclk");
-
-	if (IS_ERR(dwmac->clk))
+	if (IS_ERR(dwmac->clk)) {
+		dev_warn(dev, "No phy clock provided...\n");
 		dwmac->clk = NULL;
-
-	return 0;
-}
-
-static int sti_dwmac_init(struct platform_device *pdev, void *priv)
-{
-	struct sti_dwmac *dwmac = priv;
-	struct regmap *regmap = dwmac->regmap;
-	int iface = dwmac->interface;
-	u32 reg = dwmac->reg;
-	u32 val, spd;
-
-	if (dwmac->clk)
-		clk_prepare_enable(dwmac->clk);
-
-	regmap_update_bits(regmap, reg, MII_PHY_SEL_MASK, phy_intf_sels[iface]);
-
-	val = (iface == PHY_INTERFACE_MODE_REVMII) ? 0 : ENMII;
-	regmap_update_bits(regmap, reg, ENMII_MASK, val);
-
-	if (IS_PHY_IF_MODE_GBIT(iface))
-		spd = SPEED_1000;
-	else
-		spd = SPEED_100;
-
-	setup_retime_src(dwmac, spd);
+	}
 
 	return 0;
 }
@@ -322,9 +351,16 @@ static void *sti_dwmac_setup(struct platform_device *pdev)
 	return dwmac;
 }
 
-const struct stmmac_of_data sti_gmac_data = {
-	.fix_mac_speed = sti_fix_mac_speed,
+const struct stmmac_of_data stih4xx_dwmac_data = {
+	.fix_mac_speed = stih4xx_fix_retime_src,
+	.setup = sti_dwmac_setup,
+	.init = stix4xx_init,
+	.exit = sti_dwmac_exit,
+};
+
+const struct stmmac_of_data stid127_dwmac_data = {
+	.fix_mac_speed = stid127_fix_retime_src,
 	.setup = sti_dwmac_setup,
-	.init = sti_dwmac_init,
+	.init = stid127_init,
 	.exit = sti_dwmac_exit,
 };

drivers/net/ethernet/stmicro/stmmac/stmmac.h

@@ -144,7 +144,8 @@ extern const struct stmmac_of_data meson6_dwmac_data;
 extern const struct stmmac_of_data sun7i_gmac_data;
 #endif
 #ifdef CONFIG_DWMAC_STI
-extern const struct stmmac_of_data sti_gmac_data;
+extern const struct stmmac_of_data stih4xx_dwmac_data;
+extern const struct stmmac_of_data stid127_dwmac_data;
 #endif
 #ifdef CONFIG_DWMAC_SOCFPGA
 extern const struct stmmac_of_data socfpga_gmac_data;

drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c

@@ -37,9 +37,10 @@ static const struct of_device_id stmmac_dt_ids[] = {
 	{ .compatible = "allwinner,sun7i-a20-gmac", .data = &sun7i_gmac_data},
 #endif
 #ifdef CONFIG_DWMAC_STI
-	{ .compatible = "st,stih415-dwmac", .data = &sti_gmac_data},
-	{ .compatible = "st,stih416-dwmac", .data = &sti_gmac_data},
-	{ .compatible = "st,stid127-dwmac", .data = &sti_gmac_data},
+	{ .compatible = "st,stih415-dwmac", .data = &stih4xx_dwmac_data},
+	{ .compatible = "st,stih416-dwmac", .data = &stih4xx_dwmac_data},
+	{ .compatible = "st,stid127-dwmac", .data = &stid127_dwmac_data},
+	{ .compatible = "st,stih407-dwmac", .data = &stih4xx_dwmac_data},
 #endif
 #ifdef CONFIG_DWMAC_SOCFPGA
 	{ .compatible = "altr,socfpga-stmmac", .data = &socfpga_gmac_data },
@@ -160,11 +161,16 @@ static int stmmac_probe_config_dt(struct platform_device *pdev,
 	if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0)
 		dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n");
 
-	plat->mdio_bus_data = devm_kzalloc(&pdev->dev,
-					   sizeof(struct stmmac_mdio_bus_data),
-					   GFP_KERNEL);
+	if (plat->phy_bus_name)
+		plat->mdio_bus_data = NULL;
+	else
+		plat->mdio_bus_data =
+			devm_kzalloc(&pdev->dev,
+				     sizeof(struct stmmac_mdio_bus_data),
+				     GFP_KERNEL);
 
-	plat->force_sf_dma_mode = of_property_read_bool(np, "snps,force_sf_dma_mode");
+	plat->force_sf_dma_mode =
+		of_property_read_bool(np, "snps,force_sf_dma_mode");
 
 	/* Set the maxmtu to a default of JUMBO_LEN in case the
 	 * parameter is not present in the device tree.

drivers/net/ethernet/ti/cpsw.c

@@ -2392,6 +2392,15 @@ clean_ndev_ret:
 	return ret;
 }
 
+static int cpsw_remove_child_device(struct device *dev, void *c)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+
+	of_device_unregister(pdev);
+
+	return 0;
+}
+
 static int cpsw_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
@@ -2406,6 +2415,7 @@ static int cpsw_remove(struct platform_device *pdev)
 	cpdma_chan_destroy(priv->rxch);
 	cpdma_ctlr_destroy(priv->dma);
 	pm_runtime_disable(&pdev->dev);
+	device_for_each_child(&pdev->dev, NULL, cpsw_remove_child_device);
 	if (priv->data.dual_emac)
 		free_netdev(cpsw_get_slave_ndev(priv, 1));
 	free_netdev(ndev);

drivers/net/ethernet/ti/davinci_cpdma.c

@@ -193,12 +193,9 @@ fail:
 
 static void cpdma_desc_pool_destroy(struct cpdma_desc_pool *pool)
 {
-	unsigned long flags;
-
 	if (!pool)
 		return;
 
-	spin_lock_irqsave(&pool->lock, flags);
 	WARN_ON(pool->used_desc);
 	if (pool->cpumap) {
 		dma_free_coherent(pool->dev, pool->mem_size, pool->cpumap,
@@ -206,7 +203,6 @@ static void cpdma_desc_pool_destroy(struct cpdma_desc_pool *pool)
 	} else {
 		iounmap(pool->iomap);
 	}
-	spin_unlock_irqrestore(&pool->lock, flags);
 }
 
 static inline dma_addr_t desc_phys(struct cpdma_desc_pool *pool,
@@ -561,7 +557,6 @@ int cpdma_chan_destroy(struct cpdma_chan *chan)
 		cpdma_chan_stop(chan);
 	ctlr->channels[chan->chan_num] = NULL;
 	spin_unlock_irqrestore(&ctlr->lock, flags);
-	kfree(chan);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(cpdma_chan_destroy);

drivers/net/hyperv/netvsc_drv.c

@@ -162,7 +162,7 @@ union sub_key {
  * data: network byte order
  * return: host byte order
  */
-static u32 comp_hash(u8 *key, int klen, u8 *data, int dlen)
+static u32 comp_hash(u8 *key, int klen, void *data, int dlen)
 {
 	union sub_key subk;
 	int k_next = 4;
@@ -176,7 +176,7 @@ static u32 comp_hash(u8 *key, int klen, u8 *data, int dlen)
 	for (i = 0; i < dlen; i++) {
 		subk.kb = key[k_next];
 		k_next = (k_next + 1) % klen;
-		dt = data[i];
+		dt = ((u8 *)data)[i];
 		for (j = 0; j < 8; j++) {
 			if (dt & 0x80)
 				ret ^= subk.ka;
@@ -190,26 +190,20 @@ static u32 comp_hash(u8 *key, int klen, u8 *data, int dlen)
 
 static bool netvsc_set_hash(u32 *hash, struct sk_buff *skb)
 {
-	struct iphdr *iphdr;
+	struct flow_keys flow;
 	int data_len;
-	bool ret = false;
 
-	if (eth_hdr(skb)->h_proto != htons(ETH_P_IP))
+	if (!skb_flow_dissect(skb, &flow) || flow.n_proto != htons(ETH_P_IP))
 		return false;
 
-	iphdr = ip_hdr(skb);
+	if (flow.ip_proto == IPPROTO_TCP)
+		data_len = 12;
+	else
+		data_len = 8;
 
-	if (iphdr->version == 4) {
-		if (iphdr->protocol == IPPROTO_TCP)
-			data_len = 12;
-		else
-			data_len = 8;
-		*hash = comp_hash(netvsc_hash_key, HASH_KEYLEN,
-				  (u8 *)&iphdr->saddr, data_len);
-		ret = true;
-	}
+	*hash = comp_hash(netvsc_hash_key, HASH_KEYLEN, &flow, data_len);
 
-	return ret;
+	return true;
 }
 
 static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,

drivers/net/macvtap.c

@@ -298,7 +298,7 @@ static rx_handler_result_t macvtap_handle_frame(struct sk_buff **pskb)
 	 */
 	if (q->flags & IFF_VNET_HDR)
 		features |= vlan->tap_features;
-	if (netif_needs_gso(skb, features)) {
+	if (netif_needs_gso(dev, skb, features)) {
 		struct sk_buff *segs = __skb_gso_segment(skb, features, false);
 
 		if (IS_ERR(segs))

drivers/net/phy/micrel.c

@@ -198,8 +198,10 @@ static int ksz8021_config_init(struct phy_device *phydev)
 	if (rc)
 		dev_err(&phydev->dev, "failed to set led mode\n");
 
-	phy_write(phydev, MII_KSZPHY_OMSO, val);
 	rc = ksz_config_flags(phydev);
+	if (rc < 0)
+		return rc;
+	rc = phy_write(phydev, MII_KSZPHY_OMSO, val);
 	return rc < 0 ? rc : 0;
 }
 

drivers/net/usb/r8152.c

@@ -3189,31 +3189,39 @@ static void r8153_init(struct r8152 *tp)
 static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
 {
 	struct r8152 *tp = usb_get_intfdata(intf);
+	struct net_device *netdev = tp->netdev;
+	int ret = 0;
 
 	mutex_lock(&tp->control);
 
-	if (PMSG_IS_AUTO(message))
+	if (PMSG_IS_AUTO(message)) {
+		if (netif_running(netdev) && work_busy(&tp->schedule.work)) {
+			ret = -EBUSY;
+			goto out1;
+		}
+
 		set_bit(SELECTIVE_SUSPEND, &tp->flags);
-	else
-		netif_device_detach(tp->netdev);
+	} else {
+		netif_device_detach(netdev);
+	}
 
-	if (netif_running(tp->netdev)) {
+	if (netif_running(netdev)) {
 		clear_bit(WORK_ENABLE, &tp->flags);
 		usb_kill_urb(tp->intr_urb);
-		cancel_delayed_work_sync(&tp->schedule);
 		tasklet_disable(&tp->tl);
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 			rtl_stop_rx(tp);
 			rtl_runtime_suspend_enable(tp, true);
 		} else {
+			cancel_delayed_work_sync(&tp->schedule);
 			tp->rtl_ops.down(tp);
 		}
 		tasklet_enable(&tp->tl);
 	}
-
+out1:
 	mutex_unlock(&tp->control);
 
-	return 0;
+	return ret;
 }
 
 static int rtl8152_resume(struct usb_interface *intf)

drivers/net/virtio_net.c

@@ -920,6 +920,8 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	int qnum = skb_get_queue_mapping(skb);
 	struct send_queue *sq = &vi->sq[qnum];
 	int err;
+	struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
+	bool kick = !skb->xmit_more;
 
 	/* Free up any pending old buffers before queueing new ones. */
 	free_old_xmit_skbs(sq);
@@ -956,7 +958,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
-	if (__netif_subqueue_stopped(dev, qnum) || !skb->xmit_more)
+	if (kick || netif_xmit_stopped(txq))
 		virtqueue_kick(sq->vq);
 
 	return NETDEV_TX_OK;

drivers/net/vxlan.c

@@ -1437,9 +1437,6 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb)
 	if (!in6_dev)
 		goto out;
 
-	if (!pskb_may_pull(skb, skb->len))
-		goto out;
-
 	iphdr = ipv6_hdr(skb);
 	saddr = &iphdr->saddr;
 	daddr = &iphdr->daddr;
@@ -1668,6 +1665,8 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 	struct pcpu_sw_netstats *tx_stats, *rx_stats;
 	union vxlan_addr loopback;
 	union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
+	struct net_device *dev = skb->dev;
+	int len = skb->len;
 
 	tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
 	rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats);
@@ -1691,16 +1690,16 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 
 	u64_stats_update_begin(&tx_stats->syncp);
 	tx_stats->tx_packets++;
-	tx_stats->tx_bytes += skb->len;
+	tx_stats->tx_bytes += len;
 	u64_stats_update_end(&tx_stats->syncp);
 
 	if (netif_rx(skb) == NET_RX_SUCCESS) {
 		u64_stats_update_begin(&rx_stats->syncp);
 		rx_stats->rx_packets++;
-		rx_stats->rx_bytes += skb->len;
+		rx_stats->rx_bytes += len;
 		u64_stats_update_end(&rx_stats->syncp);
 	} else {
-		skb->dev->stats.rx_dropped++;
+		dev->stats.rx_dropped++;
 	}
 }
 
@@ -1878,7 +1877,8 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 			return arp_reduce(dev, skb);
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (ntohs(eth->h_proto) == ETH_P_IPV6 &&
-			 skb->len >= sizeof(struct ipv6hdr) + sizeof(struct nd_msg) &&
+			 pskb_may_pull(skb, sizeof(struct ipv6hdr)
+				       + sizeof(struct nd_msg)) &&
 			 ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
 				struct nd_msg *msg;
 
@@ -1887,6 +1887,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 				    msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION)
 					return neigh_reduce(dev, skb);
 		}
+		eth = eth_hdr(skb);
 #endif
 	}
 

drivers/net/xen-netfront.c

@@ -638,7 +638,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (unlikely(!netif_carrier_ok(dev) ||
 		     (slots > 1 && !xennet_can_sg(dev)) ||
-		     netif_needs_gso(skb, netif_skb_features(skb)))) {
+		     netif_needs_gso(dev, skb, netif_skb_features(skb)))) {
 		spin_unlock_irqrestore(&queue->tx_lock, flags);
 		goto drop;
 	}

drivers/scsi/cxgbi/cxgb4i/cxgb4i.c

@@ -259,6 +259,7 @@ static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb,
 	cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 static void send_act_open_req6(struct cxgbi_sock *csk, struct sk_buff *skb,
 			       struct l2t_entry *e)
 {
@@ -344,6 +345,7 @@ static void send_act_open_req6(struct cxgbi_sock *csk, struct sk_buff *skb,
 
 	cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t);
 }
+#endif
 
 static void send_close_req(struct cxgbi_sock *csk)
 {
@@ -756,7 +758,7 @@ static int act_open_rpl_status_to_errno(int status)
 
 static void csk_act_open_retry_timer(unsigned long data)
 {
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	struct cxgbi_sock *csk = (struct cxgbi_sock *)data;
 	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(csk->cdev);
 	void (*send_act_open_func)(struct cxgbi_sock *, struct sk_buff *,
@@ -781,9 +783,11 @@ static void csk_act_open_retry_timer(unsigned long data)
 	if (csk->csk_family == AF_INET) {
 		send_act_open_func = send_act_open_req;
 		skb = alloc_wr(size, 0, GFP_ATOMIC);
+#if IS_ENABLED(CONFIG_IPV6)
 	} else {
 		send_act_open_func = send_act_open_req6;
 		skb = alloc_wr(size6, 0, GFP_ATOMIC);
+#endif
 	}
 
 	if (!skb)
@@ -1313,11 +1317,6 @@ static int init_act_open(struct cxgbi_sock *csk)
 	cxgbi_sock_set_flag(csk, CTPF_HAS_ATID);
 	cxgbi_sock_get(csk);
 
-	n = dst_neigh_lookup(csk->dst, &csk->daddr.sin_addr.s_addr);
-	if (!n) {
-		pr_err("%s, can't get neighbour of csk->dst.\n", ndev->name);
-		goto rel_resource;
-	}
 	csk->l2t = cxgb4_l2t_get(lldi->l2t, n, ndev, 0);
 	if (!csk->l2t) {
 		pr_err("%s, cannot alloc l2t.\n", ndev->name);
@@ -1335,8 +1334,10 @@ static int init_act_open(struct cxgbi_sock *csk)
 
 	if (csk->csk_family == AF_INET)
 		skb = alloc_wr(size, 0, GFP_NOIO);
+#if IS_ENABLED(CONFIG_IPV6)
 	else
 		skb = alloc_wr(size6, 0, GFP_NOIO);
+#endif
 
 	if (!skb)
 		goto rel_resource;
@@ -1370,8 +1371,10 @@ static int init_act_open(struct cxgbi_sock *csk)
 	cxgbi_sock_set_state(csk, CTP_ACTIVE_OPEN);
 	if (csk->csk_family == AF_INET)
 		send_act_open_req(csk, skb, csk->l2t);
+#if IS_ENABLED(CONFIG_IPV6)
 	else
 		send_act_open_req6(csk, skb, csk->l2t);
+#endif
 	neigh_release(n);
 
 	return 0;
@@ -1635,129 +1638,6 @@ static int cxgb4i_ddp_init(struct cxgbi_device *cdev)
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
-static int cxgbi_inet6addr_handler(struct notifier_block *this,
-				   unsigned long event, void *data)
-{
-	struct inet6_ifaddr *ifa = data;
-	struct net_device *event_dev = ifa->idev->dev;
-	struct cxgbi_device *cdev;
-	int ret = NOTIFY_DONE;
-
-	if (event_dev->priv_flags & IFF_802_1Q_VLAN)
-		event_dev = vlan_dev_real_dev(event_dev);
-
-	cdev = cxgbi_device_find_by_netdev_rcu(event_dev, NULL);
-
-	if (!cdev)
-		return ret;
-
-	switch (event) {
-	case NETDEV_UP:
-		ret = cxgb4_clip_get(event_dev,
-				     (const struct in6_addr *)
-				     ((ifa)->addr.s6_addr));
-		if (ret < 0)
-			return ret;
-
-		ret = NOTIFY_OK;
-		break;
-
-	case NETDEV_DOWN:
-		cxgb4_clip_release(event_dev,
-				   (const struct in6_addr *)
-				   ((ifa)->addr.s6_addr));
-		ret = NOTIFY_OK;
-		break;
-
-	default:
-		break;
-	}
-
-	return ret;
-}
-
-static struct notifier_block cxgbi_inet6addr_notifier = {
-	.notifier_call = cxgbi_inet6addr_handler
-};
-
-/* Retrieve IPv6 addresses from a root device (bond, vlan) associated with
- * a physical device.
- * The physical device reference is needed to send the actual CLIP command.
- */
-static int update_dev_clip(struct net_device *root_dev, struct net_device *dev)
-{
-	struct inet6_dev *idev = NULL;
-	struct inet6_ifaddr *ifa;
-	int ret = 0;
-
-	idev = __in6_dev_get(root_dev);
-	if (!idev)
-		return ret;
-
-	read_lock_bh(&idev->lock);
-	list_for_each_entry(ifa, &idev->addr_list, if_list) {
-		pr_info("updating the clip for addr %pI6\n",
-			ifa->addr.s6_addr);
-		ret = cxgb4_clip_get(dev, (const struct in6_addr *)
-				     ifa->addr.s6_addr);
-		if (ret < 0)
-			break;
-	}
-
-	read_unlock_bh(&idev->lock);
-	return ret;
-}
-
-static int update_root_dev_clip(struct net_device *dev)
-{
-	struct net_device *root_dev = NULL;
-	int i, ret = 0;
-
-	/* First populate the real net device's IPv6 address */
-	ret = update_dev_clip(dev, dev);
-	if (ret)
-		return ret;
-
-	/* Parse all bond and vlan devices layered on top of the physical dev */
-	root_dev = netdev_master_upper_dev_get(dev);
-	if (root_dev) {
-		ret = update_dev_clip(root_dev, dev);
-		if (ret)
-			return ret;
-	}
-
-	for (i = 0; i < VLAN_N_VID; i++) {
-		root_dev = __vlan_find_dev_deep_rcu(dev, htons(ETH_P_8021Q), i);
-		if (!root_dev)
-			continue;
-
-		ret = update_dev_clip(root_dev, dev);
-		if (ret)
-			break;
-	}
-	return ret;
-}
-
-static void cxgbi_update_clip(struct cxgbi_device *cdev)
-{
-	int i;
-
-	rcu_read_lock();
-
-	for (i = 0; i < cdev->nports; i++) {
-		struct net_device *dev = cdev->ports[i];
-		int ret = 0;
-
-		if (dev)
-			ret = update_root_dev_clip(dev);
-		if (ret < 0)
-			break;
-	}
-	rcu_read_unlock();
-}
-#endif /* IS_ENABLED(CONFIG_IPV6) */
-
 static void *t4_uld_add(const struct cxgb4_lld_info *lldi)
 {
 	struct cxgbi_device *cdev;
@@ -1876,10 +1756,6 @@ static int t4_uld_state_change(void *handle, enum cxgb4_state state)
 	switch (state) {
 	case CXGB4_STATE_UP:
 		pr_info("cdev 0x%p, UP.\n", cdev);
-#if IS_ENABLED(CONFIG_IPV6)
-		cxgbi_update_clip(cdev);
-#endif
-		/* re-initialize */
 		break;
 	case CXGB4_STATE_START_RECOVERY:
 		pr_info("cdev 0x%p, RECOVERY.\n", cdev);
@@ -1910,17 +1786,11 @@ static int __init cxgb4i_init_module(void)
 		return rc;
 	cxgb4_register_uld(CXGB4_ULD_ISCSI, &cxgb4i_uld_info);
 
-#if IS_ENABLED(CONFIG_IPV6)
-	register_inet6addr_notifier(&cxgbi_inet6addr_notifier);
-#endif
 	return 0;
 }
 
 static void __exit cxgb4i_exit_module(void)
 {
-#if IS_ENABLED(CONFIG_IPV6)
-	unregister_inet6addr_notifier(&cxgbi_inet6addr_notifier);
-#endif
 	cxgb4_unregister_uld(CXGB4_ULD_ISCSI);
 	cxgbi_device_unregister_all(CXGBI_FLAG_DEV_T4);
 	cxgbi_iscsi_cleanup(&cxgb4i_iscsi_transport, &cxgb4i_stt);

drivers/scsi/cxgbi/libcxgbi.c

@@ -275,6 +275,7 @@ struct cxgbi_device *cxgbi_device_find_by_netdev_rcu(struct net_device *ndev,
 }
 EXPORT_SYMBOL_GPL(cxgbi_device_find_by_netdev_rcu);
 
+#if IS_ENABLED(CONFIG_IPV6)
 static struct cxgbi_device *cxgbi_device_find_by_mac(struct net_device *ndev,
 						     int *port)
 {
@@ -307,6 +308,7 @@ static struct cxgbi_device *cxgbi_device_find_by_mac(struct net_device *ndev,
 		  ndev, ndev->name);
 	return NULL;
 }
+#endif
 
 void cxgbi_hbas_remove(struct cxgbi_device *cdev)
 {

include/linux/genl_magic_func.h

@@ -178,12 +178,12 @@ static int s_name ## _from_attrs_for_change(struct s_name *s,		\
 #define __assign(attr_nr, attr_flag, name, nla_type, type, assignment...)	\
 		nla = ntb[attr_nr];						\
 		if (nla) {						\
-			if (exclude_invariants && ((attr_flag) & DRBD_F_INVARIANT)) {		\
+			if (exclude_invariants && !!((attr_flag) & DRBD_F_INVARIANT)) {		\
 				pr_info("<< must not change invariant attr: %s\n", #name);	\
 				return -EEXIST;				\
 			}						\
 			assignment;					\
-		} else if (exclude_invariants && ((attr_flag) & DRBD_F_INVARIANT)) {		\
+		} else if (exclude_invariants && !!((attr_flag) & DRBD_F_INVARIANT)) {		\
 			/* attribute missing from payload, */		\
 			/* which was expected */			\
 		} else if ((attr_flag) & DRBD_F_REQUIRED) {		\

include/linux/kernelcapi.h

@@ -41,7 +41,7 @@ u16 capi20_get_manufacturer(u32 contr, u8 buf[CAPI_MANUFACTURER_LEN]);
 u16 capi20_get_version(u32 contr, struct capi_version *verp);
 u16 capi20_get_serial(u32 contr, u8 serial[CAPI_SERIAL_LEN]);
 u16 capi20_get_profile(u32 contr, struct capi_profile *profp);
-int capi20_manufacturer(unsigned int cmd, void __user *data);
+int capi20_manufacturer(unsigned long cmd, void __user *data);
 
 #define CAPICTR_UP			0
 #define CAPICTR_DOWN			1

include/linux/netdevice.h

@@ -998,6 +998,12 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *	Callback to use for xmit over the accelerated station. This
  *	is used in place of ndo_start_xmit on accelerated net
  *	devices.
+ * bool	(*ndo_gso_check) (struct sk_buff *skb,
+ *			  struct net_device *dev);
+ *	Called by core transmit path to determine if device is capable of
+ *	performing GSO on a packet. The device returns true if it is
+ *	able to GSO the packet, false otherwise. If the return value is
+ *	false the stack will do software GSO.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1147,6 +1153,8 @@ struct net_device_ops {
 							struct net_device *dev,
 							void *priv);
 	int			(*ndo_get_lock_subclass)(struct net_device *dev);
+	bool			(*ndo_gso_check) (struct sk_buff *skb,
+						  struct net_device *dev);
 };
 
 /**
@@ -3572,10 +3580,12 @@ static inline bool skb_gso_ok(struct sk_buff *skb, netdev_features_t features)
 	       (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST));
 }
 
-static inline bool netif_needs_gso(struct sk_buff *skb,
+static inline bool netif_needs_gso(struct net_device *dev, struct sk_buff *skb,
 				   netdev_features_t features)
 {
 	return skb_is_gso(skb) && (!skb_gso_ok(skb, features) ||
+		(dev->netdev_ops->ndo_gso_check &&
+		 !dev->netdev_ops->ndo_gso_check(skb, dev)) ||
 		unlikely((skb->ip_summed != CHECKSUM_PARTIAL) &&
 			 (skb->ip_summed != CHECKSUM_UNNECESSARY)));
 }

include/linux/skbuff.h

@@ -1203,7 +1203,12 @@ static inline struct sk_buff *skb_unshare(struct sk_buff *skb,
 	might_sleep_if(pri & __GFP_WAIT);
 	if (skb_cloned(skb)) {
 		struct sk_buff *nskb = skb_copy(skb, pri);
-		kfree_skb(skb);	/* Free our shared copy */
+
+		/* Free our shared copy */
+		if (likely(nskb))
+			consume_skb(skb);
+		else
+			kfree_skb(skb);
 		skb = nskb;
 	}
 	return skb;

include/net/dsa.h

@@ -18,6 +18,7 @@
 #include <linux/of.h>
 #include <linux/phy.h>
 #include <linux/phy_fixed.h>
+#include <linux/ethtool.h>
 
 enum dsa_tag_protocol {
 	DSA_TAG_PROTO_NONE = 0,

include/net/if_inet6.h

@@ -146,7 +146,6 @@ struct ifacaddr6 {
 	struct ifacaddr6	*aca_next;
 	int			aca_users;
 	atomic_t		aca_refcnt;
-	spinlock_t		aca_lock;
 	unsigned long		aca_cstamp;
 	unsigned long		aca_tstamp;
 };

include/net/inet6_hashtables.h

@@ -80,7 +80,8 @@ static inline struct sock *__inet6_lookup(struct net *net,
 static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 					      struct sk_buff *skb,
 					      const __be16 sport,
-					      const __be16 dport)
+					      const __be16 dport,
+					      int iif)
 {
 	struct sock *sk = skb_steal_sock(skb);
 
@@ -90,7 +91,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 	return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo,
 			      &ipv6_hdr(skb)->saddr, sport,
 			      &ipv6_hdr(skb)->daddr, ntohs(dport),
-			      inet6_iif(skb));
+			      iif);
 }
 
 struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,

include/net/netlink.h

@@ -431,7 +431,7 @@ static inline int nlmsg_report(const struct nlmsghdr *nlh)
 /**
  * nlmsg_put - Add a new netlink message to an skb
  * @skb: socket buffer to store message in
- * @portid: netlink process id
+ * @portid: netlink PORTID of requesting application
  * @seq: sequence number of message
  * @type: message type
  * @payload: length of message payload

include/net/sctp/sctp.h

@@ -426,6 +426,11 @@ static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_associat
 	asoc->pmtu_pending = 0;
 }
 
+static inline bool sctp_chunk_pending(const struct sctp_chunk *chunk)
+{
+	return !list_empty(&chunk->list);
+}
+
 /* Walk through a list of TLV parameters.  Don't trust the
  * individual parameter lengths and instead depend on
  * the chunk length to indicate when to stop.  Make sure

include/net/sctp/sm.h

@@ -248,9 +248,9 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *,
 					      int, __be16);
 struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc,
 					     union sctp_addr *addr);
-int sctp_verify_asconf(const struct sctp_association *asoc,
-		       struct sctp_paramhdr *param_hdr, void *chunk_end,
-		       struct sctp_paramhdr **errp);
+bool sctp_verify_asconf(const struct sctp_association *asoc,
+			struct sctp_chunk *chunk, bool addr_param_needed,
+			struct sctp_paramhdr **errp);
 struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
 				       struct sctp_chunk *asconf);
 int sctp_process_asconf_ack(struct sctp_association *asoc,

include/net/tcp.h

@@ -468,8 +468,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb);
 /* From syncookies.c */
 int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
 		      u32 cookie);
-struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
-			     struct ip_options *opt);
+struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
 #ifdef CONFIG_SYN_COOKIES
 
 /* Syncookies use a monotonic timer which increments every 60 seconds.
@@ -730,6 +729,15 @@ struct tcp_skb_cb {
 
 #define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))
 
+
+/* This is the variant of inet6_iif() that must be used by TCP,
+ * as TCP moves IP6CB into a different location in skb->cb[]
+ */
+static inline int tcp_v6_iif(const struct sk_buff *skb)
+{
+	return TCP_SKB_CB(skb)->header.h6.iif;
+}
+
 /* Due to TSO, an SKB can be composed of multiple actual
  * packets.  To keep these tracked properly, we use this.
  */
@@ -1666,4 +1674,24 @@ int tcpv4_offload_init(void);
 void tcp_v4_init(void);
 void tcp_init(void);
 
+/*
+ * Save and compile IPv4 options, return a pointer to it
+ */
+static inline struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
+{
+	const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
+	struct ip_options_rcu *dopt = NULL;
+
+	if (opt->optlen) {
+		int opt_size = sizeof(*dopt) + opt->optlen;
+
+		dopt = kmalloc(opt_size, GFP_ATOMIC);
+		if (dopt && __ip_options_echo(&dopt->opt, skb, opt)) {
+			kfree(dopt);
+			dopt = NULL;
+		}
+	}
+	return dopt;
+}
+
 #endif	/* _TCP_H */

include/uapi/linux/Kbuild

@@ -68,6 +68,7 @@ header-y += binfmts.h
 header-y += blkpg.h
 header-y += blktrace_api.h
 header-y += bpf.h
+header-y += bpf_common.h
 header-y += bpqether.h
 header-y += bsg.h
 header-y += btrfs.h

include/uapi/linux/bpf.h

@@ -8,6 +8,7 @@
 #define _UAPI__LINUX_BPF_H__
 
 #include <linux/types.h>
+#include <linux/bpf_common.h>
 
 /* Extended instruction set based on top of classic BPF */
 

include/uapi/linux/bpf_common.h

@@ -0,0 +1,55 @@
+#ifndef _UAPI__LINUX_BPF_COMMON_H__
+#define _UAPI__LINUX_BPF_COMMON_H__
+
+/* Instruction classes */
+#define BPF_CLASS(code) ((code) & 0x07)
+#define		BPF_LD		0x00
+#define		BPF_LDX		0x01
+#define		BPF_ST		0x02
+#define		BPF_STX		0x03
+#define		BPF_ALU		0x04
+#define		BPF_JMP		0x05
+#define		BPF_RET		0x06
+#define		BPF_MISC        0x07
+
+/* ld/ldx fields */
+#define BPF_SIZE(code)  ((code) & 0x18)
+#define		BPF_W		0x00
+#define		BPF_H		0x08
+#define		BPF_B		0x10
+#define BPF_MODE(code)  ((code) & 0xe0)
+#define		BPF_IMM		0x00
+#define		BPF_ABS		0x20
+#define		BPF_IND		0x40
+#define		BPF_MEM		0x60
+#define		BPF_LEN		0x80
+#define		BPF_MSH		0xa0
+
+/* alu/jmp fields */
+#define BPF_OP(code)    ((code) & 0xf0)
+#define		BPF_ADD		0x00
+#define		BPF_SUB		0x10
+#define		BPF_MUL		0x20
+#define		BPF_DIV		0x30
+#define		BPF_OR		0x40
+#define		BPF_AND		0x50
+#define		BPF_LSH		0x60
+#define		BPF_RSH		0x70
+#define		BPF_NEG		0x80
+#define		BPF_MOD		0x90
+#define		BPF_XOR		0xa0
+
+#define		BPF_JA		0x00
+#define		BPF_JEQ		0x10
+#define		BPF_JGT		0x20
+#define		BPF_JGE		0x30
+#define		BPF_JSET        0x40
+#define BPF_SRC(code)   ((code) & 0x08)
+#define		BPF_K		0x00
+#define		BPF_X		0x08
+
+#ifndef BPF_MAXINSNS
+#define BPF_MAXINSNS 4096
+#endif
+
+#endif /* _UAPI__LINUX_BPF_COMMON_H__ */

include/uapi/linux/filter.h

@@ -7,7 +7,7 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-
+#include <linux/bpf_common.h>
 
 /*
  * Current version of the filter code architecture.
@@ -32,56 +32,6 @@ struct sock_fprog {	/* Required for SO_ATTACH_FILTER. */
 	struct sock_filter __user *filter;
 };
 
-/*
- * Instruction classes
- */
-
-#define BPF_CLASS(code) ((code) & 0x07)
-#define         BPF_LD          0x00
-#define         BPF_LDX         0x01
-#define         BPF_ST          0x02
-#define         BPF_STX         0x03
-#define         BPF_ALU         0x04
-#define         BPF_JMP         0x05
-#define         BPF_RET         0x06
-#define         BPF_MISC        0x07
-
-/* ld/ldx fields */
-#define BPF_SIZE(code)  ((code) & 0x18)
-#define         BPF_W           0x00
-#define         BPF_H           0x08
-#define         BPF_B           0x10
-#define BPF_MODE(code)  ((code) & 0xe0)
-#define         BPF_IMM         0x00
-#define         BPF_ABS         0x20
-#define         BPF_IND         0x40
-#define         BPF_MEM         0x60
-#define         BPF_LEN         0x80
-#define         BPF_MSH         0xa0
-
-/* alu/jmp fields */
-#define BPF_OP(code)    ((code) & 0xf0)
-#define         BPF_ADD         0x00
-#define         BPF_SUB         0x10
-#define         BPF_MUL         0x20
-#define         BPF_DIV         0x30
-#define         BPF_OR          0x40
-#define         BPF_AND         0x50
-#define         BPF_LSH         0x60
-#define         BPF_RSH         0x70
-#define         BPF_NEG         0x80
-#define		BPF_MOD		0x90
-#define		BPF_XOR		0xa0
-
-#define         BPF_JA          0x00
-#define         BPF_JEQ         0x10
-#define         BPF_JGT         0x20
-#define         BPF_JGE         0x30
-#define         BPF_JSET        0x40
-#define BPF_SRC(code)   ((code) & 0x08)
-#define         BPF_K           0x00
-#define         BPF_X           0x08
-
 /* ret - BPF_K and BPF_X also apply */
 #define BPF_RVAL(code)  ((code) & 0x18)
 #define         BPF_A           0x10
@@ -91,10 +41,6 @@ struct sock_fprog {	/* Required for SO_ATTACH_FILTER. */
 #define         BPF_TAX         0x00
 #define         BPF_TXA         0x80
 
-#ifndef BPF_MAXINSNS
-#define BPF_MAXINSNS 4096
-#endif
-
 /*
  * Macros for filter block array initializers.
  */

net/caif/caif_usb.c

@@ -87,13 +87,12 @@ static struct cflayer *cfusbl_create(int phyid, u8 ethaddr[ETH_ALEN],
 {
 	struct cfusbl *this = kmalloc(sizeof(struct cfusbl), GFP_ATOMIC);
 
-	if (!this) {
-		pr_warn("Out of memory\n");
+	if (!this)
 		return NULL;
-	}
+
 	caif_assert(offsetof(struct cfusbl, layer) == 0);
 
-	memset(this, 0, sizeof(struct cflayer));
+	memset(&this->layer, 0, sizeof(this->layer));
 	this->layer.receive = cfusbl_receive;
 	this->layer.transmit = cfusbl_transmit;
 	this->layer.ctrlcmd = cfusbl_ctrlcmd;

net/caif/cfmuxl.c

@@ -47,10 +47,10 @@ static struct cflayer *get_up(struct cfmuxl *muxl, u16 id);
 
 struct cflayer *cfmuxl_create(void)
 {
-	struct cfmuxl *this = kmalloc(sizeof(struct cfmuxl), GFP_ATOMIC);
+	struct cfmuxl *this = kzalloc(sizeof(struct cfmuxl), GFP_ATOMIC);
+
 	if (!this)
 		return NULL;
-	memset(this, 0, sizeof(*this));
 	this->layer.receive = cfmuxl_receive;
 	this->layer.transmit = cfmuxl_transmit;
 	this->layer.ctrlcmd = cfmuxl_ctrlcmd;

net/core/dev.c

@@ -2675,7 +2675,7 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 	if (skb->encapsulation)
 		features &= dev->hw_enc_features;
 
-	if (netif_needs_gso(skb, features)) {
+	if (netif_needs_gso(dev, skb, features)) {
 		struct sk_buff *segs;
 
 		segs = skb_gso_segment(skb, features);

net/core/sock.c

@@ -1718,6 +1718,8 @@ EXPORT_SYMBOL(sock_kmalloc);
  */
 void sock_kfree_s(struct sock *sk, void *mem, int size)
 {
+	if (WARN_ON_ONCE(!mem))
+		return;
 	kfree(mem);
 	atomic_sub(size, &sk->sk_omem_alloc);
 }

net/dccp/ipv6.c

@@ -757,7 +757,8 @@ static int dccp_v6_rcv(struct sk_buff *skb)
 	/* Step 2:
 	 *	Look up flow ID in table and get corresponding socket */
 	sk = __inet6_lookup_skb(&dccp_hashinfo, skb,
-			        dh->dccph_sport, dh->dccph_dport);
+			        dh->dccph_sport, dh->dccph_dport,
+				inet6_iif(skb));
 	/*
 	 * Step 2:
 	 *	If no socket ...

net/dsa/slave.c

@@ -11,6 +11,7 @@
 #include <linux/list.h>
 #include <linux/etherdevice.h>
 #include <linux/phy.h>
+#include <linux/phy_fixed.h>
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
 #include "dsa_priv.h"

net/ipv4/fib_semantics.c

@@ -537,7 +537,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
 			return 1;
 
 		attrlen = rtnh_attrlen(rtnh);
-		if (attrlen < 0) {
+		if (attrlen > 0) {
 			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);

net/ipv4/fou.c

@@ -87,6 +87,9 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	if (!pskb_may_pull(skb, len))
 		goto drop;
 
+	uh = udp_hdr(skb);
+	guehdr = (struct guehdr *)&uh[1];
+
 	if (guehdr->version != 0)
 		goto drop;
 

net/ipv4/ip_output.c

@@ -1535,6 +1535,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
 	struct sk_buff *nskb;
 	struct sock *sk;
 	struct inet_sock *inet;
+	int err;
 
 	if (__ip_options_echo(&replyopts.opt.opt, skb, sopt))
 		return;
@@ -1574,8 +1575,13 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
 	sock_net_set(sk, net);
 	__skb_queue_head_init(&sk->sk_write_queue);
 	sk->sk_sndbuf = sysctl_wmem_default;
-	ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0,
-		       &ipc, &rt, MSG_DONTWAIT);
+	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
+			     len, 0, &ipc, &rt, MSG_DONTWAIT);
+	if (unlikely(err)) {
+		ip_flush_pending_frames(sk);
+		goto out;
+	}
+
 	nskb = skb_peek(&sk->sk_write_queue);
 	if (nskb) {
 		if (arg->csumoffset >= 0)
@@ -1587,7 +1593,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
 		skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
 		ip_push_pending_frames(sk, &fl4);
 	}
-
+out:
 	put_cpu_var(unicast_sock);
 
 	ip_rt_put(rt);

net/ipv4/ip_tunnel_core.c

@@ -91,11 +91,12 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto)
 	skb_pull_rcsum(skb, hdr_len);
 
 	if (inner_proto == htons(ETH_P_TEB)) {
-		struct ethhdr *eh = (struct ethhdr *)skb->data;
+		struct ethhdr *eh;
 
 		if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
 			return -ENOMEM;
 
+		eh = (struct ethhdr *)skb->data;
 		if (likely(ntohs(eh->h_proto) >= ETH_P_802_3_MIN))
 			skb->protocol = eh->h_proto;
 		else

net/ipv4/syncookies.c

@@ -255,9 +255,9 @@ bool cookie_check_timestamp(struct tcp_options_received *tcp_opt,
 }
 EXPORT_SYMBOL(cookie_check_timestamp);
 
-struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
-			     struct ip_options *opt)
+struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 {
+	struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
 	struct tcp_options_received tcp_opt;
 	struct inet_request_sock *ireq;
 	struct tcp_request_sock *treq;
@@ -317,15 +317,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
 	 */
-	if (opt && opt->optlen) {
-		int opt_size = sizeof(struct ip_options_rcu) + opt->optlen;
-
-		ireq->opt = kmalloc(opt_size, GFP_ATOMIC);
-		if (ireq->opt != NULL && ip_options_echo(&ireq->opt->opt, skb)) {
-			kfree(ireq->opt);
-			ireq->opt = NULL;
-		}
-	}
+	ireq->opt = tcp_v4_save_options(skb);
 
 	if (security_inet_conn_request(sk, skb, req)) {
 		reqsk_free(req);
@@ -344,7 +336,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
 			   inet_sk_flowi_flags(sk),
-			   (opt && opt->srr) ? opt->faddr : ireq->ir_rmt_addr,
+			   opt->srr ? opt->faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, th->source, th->dest);
 	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_key(sock_net(sk), &fl4);

net/ipv4/tcp_input.c

@@ -68,6 +68,7 @@
 #include <linux/module.h>
 #include <linux/sysctl.h>
 #include <linux/kernel.h>
+#include <linux/prefetch.h>
 #include <net/dst.h>
 #include <net/tcp.h>
 #include <net/inet_common.h>
@@ -3029,6 +3030,21 @@ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb)
 	return packets_acked;
 }
 
+static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
+			   u32 prior_snd_una)
+{
+	const struct skb_shared_info *shinfo;
+
+	/* Avoid cache line misses to get skb_shinfo() and shinfo->tx_flags */
+	if (likely(!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)))
+		return;
+
+	shinfo = skb_shinfo(skb);
+	if ((shinfo->tx_flags & SKBTX_ACK_TSTAMP) &&
+	    between(shinfo->tskey, prior_snd_una, tcp_sk(sk)->snd_una - 1))
+		__skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
+}
+
 /* Remove acknowledged frames from the retransmission queue. If our packet
  * is before the ack sequence we can discard it as it's confirmed to have
  * arrived at the other end.
@@ -3052,14 +3068,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 	first_ackt.v64 = 0;
 
 	while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
-		struct skb_shared_info *shinfo = skb_shinfo(skb);
 		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
 		u8 sacked = scb->sacked;
 		u32 acked_pcount;
 
-		if (unlikely(shinfo->tx_flags & SKBTX_ACK_TSTAMP) &&
-		    between(shinfo->tskey, prior_snd_una, tp->snd_una - 1))
-			__skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
+		tcp_ack_tstamp(sk, skb, prior_snd_una);
 
 		/* Determine how many packets and what bytes were acked, tso and else */
 		if (after(scb->end_seq, tp->snd_una)) {
@@ -3073,10 +3086,12 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 
 			fully_acked = false;
 		} else {
+			/* Speedup tcp_unlink_write_queue() and next loop */
+			prefetchw(skb->next);
 			acked_pcount = tcp_skb_pcount(skb);
 		}
 
-		if (sacked & TCPCB_RETRANS) {
+		if (unlikely(sacked & TCPCB_RETRANS)) {
 			if (sacked & TCPCB_SACKED_RETRANS)
 				tp->retrans_out -= acked_pcount;
 			flag |= FLAG_RETRANS_DATA_ACKED;
@@ -3107,7 +3122,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 		 * connection startup slow start one packet too
 		 * quickly.  This is severely frowned upon behavior.
 		 */
-		if (!(scb->tcp_flags & TCPHDR_SYN)) {
+		if (likely(!(scb->tcp_flags & TCPHDR_SYN))) {
 			flag |= FLAG_DATA_ACKED;
 		} else {
 			flag |= FLAG_SYN_ACKED;
@@ -3119,9 +3134,9 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 
 		tcp_unlink_write_queue(skb, sk);
 		sk_wmem_free_skb(sk, skb);
-		if (skb == tp->retransmit_skb_hint)
+		if (unlikely(skb == tp->retransmit_skb_hint))
 			tp->retransmit_skb_hint = NULL;
-		if (skb == tp->lost_skb_hint)
+		if (unlikely(skb == tp->lost_skb_hint))
 			tp->lost_skb_hint = NULL;
 	}
 
@@ -3132,7 +3147,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 		flag |= FLAG_SACK_RENEGING;
 
 	skb_mstamp_get(&now);
-	if (first_ackt.v64) {
+	if (likely(first_ackt.v64)) {
 		seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt);
 		ca_seq_rtt_us = skb_mstamp_us_delta(&now, &last_ackt);
 	}
@@ -3394,6 +3409,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	int acked = 0; /* Number of packets newly acked */
 	long sack_rtt_us = -1L;
 
+	/* We very likely will need to access write queue head. */
+	prefetchw(sk->sk_write_queue.next);
+
 	/* If the ack is older than previous acks
 	 * then we can probably ignore it.
 	 */

net/ipv4/tcp_ipv4.c

@@ -880,26 +880,6 @@ bool tcp_syn_flood_action(struct sock *sk,
 }
 EXPORT_SYMBOL(tcp_syn_flood_action);
 
-/*
- * Save and compile IPv4 options into the request_sock if needed.
- */
-static struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
-{
-	const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
-	struct ip_options_rcu *dopt = NULL;
-
-	if (opt && opt->optlen) {
-		int opt_size = sizeof(*dopt) + opt->optlen;
-
-		dopt = kmalloc(opt_size, GFP_ATOMIC);
-		if (dopt && __ip_options_echo(&dopt->opt, skb, opt)) {
-			kfree(dopt);
-			dopt = NULL;
-		}
-	}
-	return dopt;
-}
-
 #ifdef CONFIG_TCP_MD5SIG
 /*
  * RFC2385 MD5 checksumming requires a mapping of
@@ -1428,7 +1408,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_SYN_COOKIES
 	if (!th->syn)
-		sk = cookie_v4_check(sk, skb, &TCP_SKB_CB(skb)->header.h4.opt);
+		sk = cookie_v4_check(sk, skb);
 #endif
 	return sk;
 }

net/ipv4/tcp_output.c

@@ -839,26 +839,38 @@ void tcp_wfree(struct sk_buff *skb)
 {
 	struct sock *sk = skb->sk;
 	struct tcp_sock *tp = tcp_sk(sk);
+	int wmem;
+
+	/* Keep one reference on sk_wmem_alloc.
+	 * Will be released by sk_free() from here or tcp_tasklet_func()
+	 */
+	wmem = atomic_sub_return(skb->truesize - 1, &sk->sk_wmem_alloc);
+
+	/* If this softirq is serviced by ksoftirqd, we are likely under stress.
+	 * Wait until our queues (qdisc + devices) are drained.
+	 * This gives :
+	 * - less callbacks to tcp_write_xmit(), reducing stress (batches)
+	 * - chance for incoming ACK (processed by another cpu maybe)
+	 *   to migrate this flow (skb->ooo_okay will be eventually set)
+	 */
+	if (wmem >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current)
+		goto out;
 
 	if (test_and_clear_bit(TSQ_THROTTLED, &tp->tsq_flags) &&
 	    !test_and_set_bit(TSQ_QUEUED, &tp->tsq_flags)) {
 		unsigned long flags;
 		struct tsq_tasklet *tsq;
 
-		/* Keep a ref on socket.
-		 * This last ref will be released in tcp_tasklet_func()
-		 */
-		atomic_sub(skb->truesize - 1, &sk->sk_wmem_alloc);
-
 		/* queue this socket to tasklet queue */
 		local_irq_save(flags);
 		tsq = this_cpu_ptr(&tsq_tasklet);
 		list_add(&tp->tsq_node, &tsq->head);
 		tasklet_schedule(&tsq->tasklet);
 		local_irq_restore(flags);
-	} else {
-		sock_wfree(skb);
+		return;
 	}
+out:
+	sk_free(sk);
 }
 
 /* This routine actually transmits TCP packets queued in by
@@ -914,9 +926,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		tcp_ca_event(sk, CA_EVENT_TX_START);
 
 	/* if no packet is in qdisc/device queue, then allow XPS to select
-	 * another queue.
+	 * another queue. We can be called from tcp_tsq_handler()
+	 * which holds one reference to sk_wmem_alloc.
+	 *
+	 * TODO: Ideally, in-flight pure ACK packets should not matter here.
+	 * One way to get this would be to set skb->truesize = 2 on them.
 	 */
-	skb->ooo_okay = sk_wmem_alloc_get(sk) == 0;
+	skb->ooo_okay = sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);

net/ipv6/anycast.c

@@ -235,7 +235,6 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt,
 	/* aca_tstamp should be updated upon changes */
 	aca->aca_cstamp = aca->aca_tstamp = jiffies;
 	atomic_set(&aca->aca_refcnt, 1);
-	spin_lock_init(&aca->aca_lock);
 
 	return aca;
 }

net/ipv6/syncookies.c

@@ -214,7 +214,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	/* So that link locals have meaning */
 	if (!sk->sk_bound_dev_if &&
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
-		ireq->ir_iif = inet6_iif(skb);
+		ireq->ir_iif = tcp_v6_iif(skb);
 
 	ireq->ir_mark = inet_request_mark(sk, skb);
 

net/ipv6/tcp_ipv6.c

@@ -424,6 +424,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (sock_owned_by_user(sk))
 			goto out;
 
+		/* Note : We use inet6_iif() here, not tcp_v6_iif() */
 		req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr,
 					   &hdr->saddr, inet6_iif(skb));
 		if (!req)
@@ -738,7 +739,7 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk,
 	/* So that link locals have meaning */
 	if (!sk->sk_bound_dev_if &&
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
-		ireq->ir_iif = inet6_iif(skb);
+		ireq->ir_iif = tcp_v6_iif(skb);
 
 	if (!TCP_SKB_CB(skb)->tcp_tw_isn &&
 	    (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) ||
@@ -860,7 +861,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 
 	fl6.flowi6_proto = IPPROTO_TCP;
 	if (rt6_need_strict(&fl6.daddr) && !oif)
-		fl6.flowi6_oif = inet6_iif(skb);
+		fl6.flowi6_oif = tcp_v6_iif(skb);
 	else
 		fl6.flowi6_oif = oif;
 	fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
@@ -918,7 +919,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 		sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev),
 					   &tcp_hashinfo, &ipv6h->saddr,
 					   th->source, &ipv6h->daddr,
-					   ntohs(th->source), inet6_iif(skb));
+					   ntohs(th->source), tcp_v6_iif(skb));
 		if (!sk1)
 			return;
 
@@ -1000,13 +1001,14 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb)
 	/* Find possible connection requests. */
 	req = inet6_csk_search_req(sk, &prev, th->source,
 				   &ipv6_hdr(skb)->saddr,
-				   &ipv6_hdr(skb)->daddr, inet6_iif(skb));
+				   &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb));
 	if (req)
 		return tcp_check_req(sk, skb, req, prev, false);
 
 	nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo,
-			&ipv6_hdr(skb)->saddr, th->source,
-			&ipv6_hdr(skb)->daddr, ntohs(th->dest), inet6_iif(skb));
+					 &ipv6_hdr(skb)->saddr, th->source,
+					 &ipv6_hdr(skb)->daddr, ntohs(th->dest),
+					 tcp_v6_iif(skb));
 
 	if (nsk) {
 		if (nsk->sk_state != TCP_TIME_WAIT) {
@@ -1090,7 +1092,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		newnp->ipv6_fl_list = NULL;
 		newnp->pktoptions  = NULL;
 		newnp->opt	   = NULL;
-		newnp->mcast_oif   = inet6_iif(skb);
+		newnp->mcast_oif   = tcp_v6_iif(skb);
 		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
 		newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
 		if (np->repflow)
@@ -1174,7 +1176,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 			skb_set_owner_r(newnp->pktoptions, newsk);
 	}
 	newnp->opt	  = NULL;
-	newnp->mcast_oif  = inet6_iif(skb);
+	newnp->mcast_oif  = tcp_v6_iif(skb);
 	newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
 	newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
 	if (np->repflow)
@@ -1360,7 +1362,7 @@ ipv6_pktoptions:
 	if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt &&
 	    !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) {
 		if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo)
-			np->mcast_oif = inet6_iif(opt_skb);
+			np->mcast_oif = tcp_v6_iif(opt_skb);
 		if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
 			np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
 		if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
@@ -1427,7 +1429,8 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
 	TCP_SKB_CB(skb)->sacked = 0;
 
-	sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest);
+	sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest,
+				tcp_v6_iif(skb));
 	if (!sk)
 		goto no_tcp_socket;
 
@@ -1514,7 +1517,7 @@ do_time_wait:
 		sk2 = inet6_lookup_listener(dev_net(skb->dev), &tcp_hashinfo,
 					    &ipv6_hdr(skb)->saddr, th->source,
 					    &ipv6_hdr(skb)->daddr,
-					    ntohs(th->dest), inet6_iif(skb));
+					    ntohs(th->dest), tcp_v6_iif(skb));
 		if (sk2 != NULL) {
 			struct inet_timewait_sock *tw = inet_twsk(sk);
 			inet_twsk_deschedule(tw, &tcp_death_row);
@@ -1553,6 +1556,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
 	if (th->doff < sizeof(struct tcphdr) / 4)
 		return;
 
+	/* Note : We use inet6_iif() here, not tcp_v6_iif() */
 	sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
 					&hdr->saddr, th->source,
 					&hdr->daddr, ntohs(th->dest),

net/netrom/af_netrom.c

@@ -30,7 +30,7 @@
 #include <linux/skbuff.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/termios.h>	/* For TIOCINQ/OUTQ */
 #include <linux/mm.h>

net/netrom/nr_dev.c

@@ -20,8 +20,8 @@
 #include <linux/in.h>
 #include <linux/if_ether.h>	/* For the statistics structure. */
 #include <linux/slab.h>
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/io.h>
 
 #include <linux/inet.h>

net/netrom/nr_in.c

@@ -23,7 +23,7 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>

net/netrom/nr_out.c

@@ -22,7 +22,7 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>

net/netrom/nr_route.c

@@ -25,7 +25,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/termios.h>	/* For TIOCINQ/OUTQ */
 #include <linux/mm.h>

net/netrom/nr_subr.c

@@ -22,7 +22,7 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>

net/netrom/nr_timer.c

@@ -23,7 +23,7 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>

net/openvswitch/flow.c

@@ -274,6 +274,8 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
 			key->ip.frag = OVS_FRAG_TYPE_LATER;
 		else
 			key->ip.frag = OVS_FRAG_TYPE_FIRST;
+	} else {
+		key->ip.frag = OVS_FRAG_TYPE_NONE;
 	}
 
 	nh_len = payload_ofs - nh_ofs;
@@ -358,6 +360,7 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
 	 */
 	key->tp.src = htons(icmp->icmp6_type);
 	key->tp.dst = htons(icmp->icmp6_code);
+	memset(&key->ipv6.nd, 0, sizeof(key->ipv6.nd));
 
 	if (icmp->icmp6_code == 0 &&
 	    (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION ||
@@ -557,10 +560,11 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 	} else if (key->eth.type == htons(ETH_P_ARP) ||
 		   key->eth.type == htons(ETH_P_RARP)) {
 		struct arp_eth_header *arp;
+		bool arp_available = arphdr_ok(skb);
 
 		arp = (struct arp_eth_header *)skb_network_header(skb);
 
-		if (arphdr_ok(skb) &&
+		if (arp_available &&
 		    arp->ar_hrd == htons(ARPHRD_ETHER) &&
 		    arp->ar_pro == htons(ETH_P_IP) &&
 		    arp->ar_hln == ETH_ALEN &&
@@ -673,9 +677,6 @@ int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
 	key->ovs_flow_hash = 0;
 	key->recirc_id = 0;
 
-	/* Flags are always used as part of stats */
-	key->tp.flags = 0;
-
 	return key_extract(skb, key);
 }
 

net/openvswitch/flow_netlink.c

@@ -103,10 +103,19 @@ static void update_range__(struct sw_flow_match *match,
 	SW_FLOW_KEY_MEMCPY_OFFSET(match, offsetof(struct sw_flow_key, field), \
 				  value_p, len, is_mask)
 
-static u16 range_n_bytes(const struct sw_flow_key_range *range)
-{
-	return range->end - range->start;
-}
+#define SW_FLOW_KEY_MEMSET_FIELD(match, field, value, is_mask) \
+	do { \
+		update_range__(match, offsetof(struct sw_flow_key, field),  \
+				     sizeof((match)->key->field), is_mask); \
+		if (is_mask) {						    \
+			if ((match)->mask)				    \
+				memset((u8 *)&(match)->mask->key.field, value,\
+				       sizeof((match)->mask->key.field));   \
+		} else {                                                    \
+			memset((u8 *)&(match)->key->field, value,           \
+			       sizeof((match)->key->field));                \
+		}                                                           \
+	} while (0)
 
 static bool match_validate(const struct sw_flow_match *match,
 			   u64 key_attrs, u64 mask_attrs)
@@ -809,13 +818,26 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 	return 0;
 }
 
-static void sw_flow_mask_set(struct sw_flow_mask *mask,
-			     struct sw_flow_key_range *range, u8 val)
+static void nlattr_set(struct nlattr *attr, u8 val, bool is_attr_mask_key)
 {
-	u8 *m = (u8 *)&mask->key + range->start;
+	struct nlattr *nla;
+	int rem;
+
+	/* The nlattr stream should already have been validated */
+	nla_for_each_nested(nla, attr, rem) {
+		/* We assume that ovs_key_lens[type] == -1 means that type is a
+		 * nested attribute
+		 */
+		if (is_attr_mask_key && ovs_key_lens[nla_type(nla)] == -1)
+			nlattr_set(nla, val, false);
+		else
+			memset(nla_data(nla), val, nla_len(nla));
+	}
+}
 
-	mask->range = *range;
-	memset(m, val, range_n_bytes(range));
+static void mask_set_nlattr(struct nlattr *attr, u8 val)
+{
+	nlattr_set(attr, val, true);
 }
 
 /**
@@ -836,6 +858,7 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 {
 	const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
 	const struct nlattr *encap;
+	struct nlattr *newmask = NULL;
 	u64 key_attrs = 0;
 	u64 mask_attrs = 0;
 	bool encap_valid = false;
@@ -882,18 +905,44 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 	if (err)
 		return err;
 
+	if (match->mask && !mask) {
+		/* Create an exact match mask. We need to set to 0xff all the
+		 * 'match->mask' fields that have been touched in 'match->key'.
+		 * We cannot simply memset 'match->mask', because padding bytes
+		 * and fields not specified in 'match->key' should be left to 0.
+		 * Instead, we use a stream of netlink attributes, copied from
+		 * 'key' and set to 0xff: ovs_key_from_nlattrs() will take care
+		 * of filling 'match->mask' appropriately.
+		 */
+		newmask = kmemdup(key, nla_total_size(nla_len(key)),
+				  GFP_KERNEL);
+		if (!newmask)
+			return -ENOMEM;
+
+		mask_set_nlattr(newmask, 0xff);
+
+		/* The userspace does not send tunnel attributes that are 0,
+		 * but we should not wildcard them nonetheless.
+		 */
+		if (match->key->tun_key.ipv4_dst)
+			SW_FLOW_KEY_MEMSET_FIELD(match, tun_key, 0xff, true);
+
+		mask = newmask;
+	}
+
 	if (mask) {
 		err = parse_flow_mask_nlattrs(mask, a, &mask_attrs);
 		if (err)
-			return err;
+			goto free_newmask;
 
-		if (mask_attrs & 1 << OVS_KEY_ATTR_ENCAP)  {
+		if (mask_attrs & 1 << OVS_KEY_ATTR_ENCAP) {
 			__be16 eth_type = 0;
 			__be16 tci = 0;
 
 			if (!encap_valid) {
 				OVS_NLERR("Encap mask attribute is set for non-VLAN frame.\n");
-				return  -EINVAL;
+				err = -EINVAL;
+				goto free_newmask;
 			}
 
 			mask_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP);
@@ -904,10 +953,13 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 				mask_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
 				encap = a[OVS_KEY_ATTR_ENCAP];
 				err = parse_flow_mask_nlattrs(encap, a, &mask_attrs);
+				if (err)
+					goto free_newmask;
 			} else {
 				OVS_NLERR("VLAN frames must have an exact match on the TPID (mask=%x).\n",
 						ntohs(eth_type));
-				return -EINVAL;
+				err = -EINVAL;
+				goto free_newmask;
 			}
 
 			if (a[OVS_KEY_ATTR_VLAN])
@@ -915,23 +967,22 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 
 			if (!(tci & htons(VLAN_TAG_PRESENT))) {
 				OVS_NLERR("VLAN tag present bit must have an exact match (tci_mask=%x).\n", ntohs(tci));
-				return -EINVAL;
+				err = -EINVAL;
+				goto free_newmask;
 			}
 		}
 
 		err = ovs_key_from_nlattrs(match, mask_attrs, a, true);
 		if (err)
-			return err;
-	} else {
-		/* Populate exact match flow's key mask. */
-		if (match->mask)
-			sw_flow_mask_set(match->mask, &match->range, 0xff);
+			goto free_newmask;
 	}
 
 	if (!match_validate(match, key_attrs, mask_attrs))
-		return -EINVAL;
+		err = -EINVAL;
 
-	return 0;
+free_newmask:
+	kfree(newmask);
+	return err;
 }
 
 /**

net/openvswitch/vport-geneve.c

@@ -30,7 +30,7 @@
 
 /**
  * struct geneve_port - Keeps track of open UDP ports
- * @sock: The socket created for this port number.
+ * @gs: The socket created for this port number.
  * @name: vport name.
  */
 struct geneve_port {

net/openvswitch/vport.c

@@ -408,13 +408,13 @@ int ovs_vport_get_upcall_portids(const struct vport *vport,
  *
  * Returns the portid of the target socket.  Must be called with rcu_read_lock.
  */
-u32 ovs_vport_find_upcall_portid(const struct vport *p, struct sk_buff *skb)
+u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb)
 {
 	struct vport_portids *ids;
 	u32 ids_index;
 	u32 hash;
 
-	ids = rcu_dereference(p->upcall_portids);
+	ids = rcu_dereference(vport->upcall_portids);
 
 	if (ids->n_ids == 1 && ids->ids[0] == 0)
 		return 0;