Merge branch 'sched/core' into locking/core

Required for the rtmutex/sched_deadline patches which depend on both
branches

Documentation/cgroup-v2.txt

···
 
   pids.max
 
- A read-write single value file which exists on non-root cgroups.  The
- default is "max".
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "max".
 
- Hard limit of number of processes.
+	Hard limit of number of processes.
 
   pids.current
 
- A read-only single value file which exists on all cgroups.
+	A read-only single value file which exists on all cgroups.
 
- The number of processes currently in the cgroup and its descendants.
+	The number of processes currently in the cgroup and its
+	descendants.
 
 Organisational operations are not blocked by cgroup policies, so it is
 possible to have pids.current > pids.max.  This can be done by either

Documentation/devicetree/bindings/powerpc/4xx/emac.txt

···
 			  For Axon it can be absent, though my current driver
 			  doesn't handle phy-address yet so for now, keep
 			  0x00ffffff in it.
+    - phy-handle	: Used to describe configurations where a external PHY
+			  is used. Please refer to:
+			  Documentation/devicetree/bindings/net/ethernet.txt
     - rx-fifo-size-gige : 1 cell, Rx fifo size in bytes for 1000 Mb/sec
 			  operations (if absent the value is the same as
 			  rx-fifo-size).  For Axon, either absent or 2048.
···
 			  offload, phandle of the TAH device node.
     - tah-channel       : 1 cell, optional. If appropriate, channel used on the
 			  TAH engine.
+    - fixed-link	: Fixed-link subnode describing a link to a non-MDIO
+			  managed entity. See
+			  Documentation/devicetree/bindings/net/fixed-link.txt
+			  for details.
+    - mdio subnode	: When the EMAC has a phy connected to its local
+			  mdio, which us supported by the kernel's network
+			  PHY library in drivers/net/phy, there must be device
+			  tree subnode with the following required properties:
+				- #address-cells: Must be <1>.
+				- #size-cells: Must be <0>.
 
-    Example:
+			  For PHY definitions: Please refer to
+			  Documentation/devicetree/bindings/net/phy.txt and
+			  Documentation/devicetree/bindings/net/ethernet.txt
+
+    Examples:
 
 	EMAC0: ethernet@40000800 {
 		device_type = "network";
···
 		zmii-device = <&ZMII0>;
 		zmii-channel = <0>;
 	};
+
+	EMAC1: ethernet@ef600c00 {
+		device_type = "network";
+		compatible = "ibm,emac-apm821xx", "ibm,emac4sync";
+		interrupt-parent = <&EMAC1>;
+		interrupts = <0 1>;
+		#interrupt-cells = <1>;
+		#address-cells = <0>;
+		#size-cells = <0>;
+		interrupt-map = <0 &UIC2 0x10 IRQ_TYPE_LEVEL_HIGH /* Status */
+				 1 &UIC2 0x14 IRQ_TYPE_LEVEL_HIGH /* Wake */>;
+		reg = <0xef600c00 0x000000c4>;
+		local-mac-address = [000000000000]; /* Filled in by U-Boot */
+		mal-device = <&MAL0>;
+		mal-tx-channel = <0>;
+		mal-rx-channel = <0>;
+		cell-index = <0>;
+		max-frame-size = <9000>;
+		rx-fifo-size = <16384>;
+		tx-fifo-size = <2048>;
+		fifo-entry-size = <10>;
+		phy-mode = "rgmii";
+		phy-handle = <&phy0>;
+		phy-map = <0x00000000>;
+		rgmii-device = <&RGMII0>;
+		rgmii-channel = <0>;
+		tah-device = <&TAH0>;
+		tah-channel = <0>;
+		has-inverted-stacr-oc;
+		has-new-stacr-staopc;
+
+	        mdio {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			phy0: ethernet-phy@0 {
+				compatible = "ethernet-phy-ieee802.3-c22";
+				reg = <0>;
+			};
+		};
+	};
+
 
       ii) McMAL node
 
···
     - revision           : as provided by the RGMII new version register if
 			   available.
 			   For Axon: 0x0000012a
-

Documentation/networking/ip-sysctl.txt

···
 		FALSE (router)
 
 forwarding - BOOLEAN
-	Enable IP forwarding on this interface.
+	Enable IP forwarding on this interface.  This controls whether packets
+	received _on_ this interface can be forwarded.
 
 mc_forwarding - BOOLEAN
 	Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE

arch/powerpc/boot/zImage.lds.S

···
   }
 
 #ifdef CONFIG_PPC64_BOOT_WRAPPER
+  . = ALIGN(256);
   .got :
   {
     __toc_start = .;

arch/powerpc/crypto/crc32c-vpmsum_glue.c

···
 {
 	u32 *key = crypto_tfm_ctx(tfm);
 
-	*key = 0;
+	*key = ~0;
 
 	return 0;
 }

arch/powerpc/include/asm/bitops.h

···
 #define PPC_BIT(bit)		(1UL << PPC_BITLSHIFT(bit))
 #define PPC_BITMASK(bs, be)	((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs))
 
+/* Put a PPC bit into a "normal" bit position */
+#define PPC_BITEXTRACT(bits, ppc_bit, dst_bit)			\
+	((((bits) >> PPC_BITLSHIFT(ppc_bit)) & 1) << (dst_bit))
+
 #include <asm/barrier.h>
 
 /* Macro for generating the ***_bits() functions */

arch/powerpc/include/asm/mce.h

···
 
 #define P8_DSISR_MC_SLB_ERRORS		(P7_DSISR_MC_SLB_ERRORS | \
 					 P8_DSISR_MC_ERAT_MULTIHIT_SEC)
+
+/*
+ * Machine Check bits on power9
+ */
+#define P9_SRR1_MC_LOADSTORE(srr1)	(((srr1) >> PPC_BITLSHIFT(42)) & 1)
+
+#define P9_SRR1_MC_IFETCH(srr1)	(	\
+	PPC_BITEXTRACT(srr1, 45, 0) |	\
+	PPC_BITEXTRACT(srr1, 44, 1) |	\
+	PPC_BITEXTRACT(srr1, 43, 2) |	\
+	PPC_BITEXTRACT(srr1, 36, 3) )
+
+/* 0 is reserved */
+#define P9_SRR1_MC_IFETCH_UE				1
+#define P9_SRR1_MC_IFETCH_SLB_PARITY			2
+#define P9_SRR1_MC_IFETCH_SLB_MULTIHIT			3
+#define P9_SRR1_MC_IFETCH_ERAT_MULTIHIT			4
+#define P9_SRR1_MC_IFETCH_TLB_MULTIHIT			5
+#define P9_SRR1_MC_IFETCH_UE_TLB_RELOAD			6
+/* 7 is reserved */
+#define P9_SRR1_MC_IFETCH_LINK_TIMEOUT			8
+#define P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT	9
+/* 10 ? */
+#define P9_SRR1_MC_IFETCH_RA			11
+#define P9_SRR1_MC_IFETCH_RA_TABLEWALK		12
+#define P9_SRR1_MC_IFETCH_RA_ASYNC_STORE		13
+#define P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT	14
+#define P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN	15
+
+/* DSISR bits for machine check (On Power9) */
+#define P9_DSISR_MC_UE					(PPC_BIT(48))
+#define P9_DSISR_MC_UE_TABLEWALK			(PPC_BIT(49))
+#define P9_DSISR_MC_LINK_LOAD_TIMEOUT			(PPC_BIT(50))
+#define P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT		(PPC_BIT(51))
+#define P9_DSISR_MC_ERAT_MULTIHIT			(PPC_BIT(52))
+#define P9_DSISR_MC_TLB_MULTIHIT_MFTLB			(PPC_BIT(53))
+#define P9_DSISR_MC_USER_TLBIE				(PPC_BIT(54))
+#define P9_DSISR_MC_SLB_PARITY_MFSLB			(PPC_BIT(55))
+#define P9_DSISR_MC_SLB_MULTIHIT_MFSLB			(PPC_BIT(56))
+#define P9_DSISR_MC_RA_LOAD				(PPC_BIT(57))
+#define P9_DSISR_MC_RA_TABLEWALK			(PPC_BIT(58))
+#define P9_DSISR_MC_RA_TABLEWALK_FOREIGN		(PPC_BIT(59))
+#define P9_DSISR_MC_RA_FOREIGN				(PPC_BIT(60))
+
+/* SLB error bits */
+#define P9_DSISR_MC_SLB_ERRORS		(P9_DSISR_MC_ERAT_MULTIHIT | \
+					 P9_DSISR_MC_SLB_PARITY_MFSLB | \
+					 P9_DSISR_MC_SLB_MULTIHIT_MFSLB)
+
 enum MCE_Version {
 	MCE_V1 = 1,
 };
···
 	MCE_ERROR_TYPE_SLB = 2,
 	MCE_ERROR_TYPE_ERAT = 3,
 	MCE_ERROR_TYPE_TLB = 4,
+	MCE_ERROR_TYPE_USER = 5,
+	MCE_ERROR_TYPE_RA = 6,
+	MCE_ERROR_TYPE_LINK = 7,
 };
 
 enum MCE_UeErrorType {
···
 	MCE_TLB_ERROR_INDETERMINATE = 0,
 	MCE_TLB_ERROR_PARITY = 1,
 	MCE_TLB_ERROR_MULTIHIT = 2,
+};
+
+enum MCE_UserErrorType {
+	MCE_USER_ERROR_INDETERMINATE = 0,
+	MCE_USER_ERROR_TLBIE = 1,
+};
+
+enum MCE_RaErrorType {
+	MCE_RA_ERROR_INDETERMINATE = 0,
+	MCE_RA_ERROR_IFETCH = 1,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH = 2,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN = 3,
+	MCE_RA_ERROR_LOAD = 4,
+	MCE_RA_ERROR_STORE = 5,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 6,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN = 7,
+	MCE_RA_ERROR_LOAD_STORE_FOREIGN = 8,
+};
+
+enum MCE_LinkErrorType {
+	MCE_LINK_ERROR_INDETERMINATE = 0,
+	MCE_LINK_ERROR_IFETCH_TIMEOUT = 1,
+	MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT = 2,
+	MCE_LINK_ERROR_LOAD_TIMEOUT = 3,
+	MCE_LINK_ERROR_STORE_TIMEOUT = 4,
+	MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT = 5,
 };
 
 struct machine_check_event {
···
 			uint64_t	effective_address;
 			uint8_t		reserved_2[16];
 		} tlb_error;
+
+		struct {
+			enum MCE_UserErrorType user_error_type:8;
+			uint8_t		effective_address_provided;
+			uint8_t		reserved_1[6];
+			uint64_t	effective_address;
+			uint8_t		reserved_2[16];
+		} user_error;
+
+		struct {
+			enum MCE_RaErrorType ra_error_type:8;
+			uint8_t		effective_address_provided;
+			uint8_t		reserved_1[6];
+			uint64_t	effective_address;
+			uint8_t		reserved_2[16];
+		} ra_error;
+
+		struct {
+			enum MCE_LinkErrorType link_error_type:8;
+			uint8_t		effective_address_provided;
+			uint8_t		reserved_1[6];
+			uint64_t	effective_address;
+			uint8_t		reserved_2[16];
+		} link_error;
 	} u;
 };
 
···
 		enum MCE_SlbErrorType slb_error_type:8;
 		enum MCE_EratErrorType erat_error_type:8;
 		enum MCE_TlbErrorType tlb_error_type:8;
+		enum MCE_UserErrorType user_error_type:8;
+		enum MCE_RaErrorType ra_error_type:8;
+		enum MCE_LinkErrorType link_error_type:8;
 	} u;
-	uint8_t		reserved[2];
+	enum MCE_Severity	severity:8;
+	enum MCE_Initiator	initiator:8;
 };
 
 #define MAX_MC_EVT	100

arch/powerpc/kernel/cputable.c

···
 extern void __flush_tlb_power9(unsigned int action);
 extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
 extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
+extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
 #endif /* CONFIG_PPC64 */
 #if defined(CONFIG_E500)
 extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
···
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
 		.flush_tlb		= __flush_tlb_power9,
+		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
 	{	/* Power9 */
···
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
 		.flush_tlb		= __flush_tlb_power9,
+		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
 	{	/* Cell Broadband Engine */

arch/powerpc/kernel/mce.c

···
 	case MCE_ERROR_TYPE_TLB:
 		mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type;
 		break;
+	case MCE_ERROR_TYPE_USER:
+		mce->u.user_error.user_error_type = mce_err->u.user_error_type;
+		break;
+	case MCE_ERROR_TYPE_RA:
+		mce->u.ra_error.ra_error_type = mce_err->u.ra_error_type;
+		break;
+	case MCE_ERROR_TYPE_LINK:
+		mce->u.link_error.link_error_type = mce_err->u.link_error_type;
+		break;
 	case MCE_ERROR_TYPE_UNKNOWN:
 	default:
 		break;
···
 	mce->gpr3 = regs->gpr[3];
 	mce->in_use = 1;
 
-	mce->initiator = MCE_INITIATOR_CPU;
 	/* Mark it recovered if we have handled it and MSR(RI=1). */
 	if (handled && (regs->msr & MSR_RI))
 		mce->disposition = MCE_DISPOSITION_RECOVERED;
 	else
 		mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
-	mce->severity = MCE_SEV_ERROR_SYNC;
+
+	mce->initiator = mce_err->initiator;
+	mce->severity = mce_err->severity;
 
 	/*
 	 * Populate the mce error_type and type-specific error_type.
···
 	} else if (mce->error_type == MCE_ERROR_TYPE_ERAT) {
 		mce->u.erat_error.effective_address_provided = true;
 		mce->u.erat_error.effective_address = addr;
+	} else if (mce->error_type == MCE_ERROR_TYPE_USER) {
+		mce->u.user_error.effective_address_provided = true;
+		mce->u.user_error.effective_address = addr;
+	} else if (mce->error_type == MCE_ERROR_TYPE_RA) {
+		mce->u.ra_error.effective_address_provided = true;
+		mce->u.ra_error.effective_address = addr;
+	} else if (mce->error_type == MCE_ERROR_TYPE_LINK) {
+		mce->u.link_error.effective_address_provided = true;
+		mce->u.link_error.effective_address = addr;
 	} else if (mce->error_type == MCE_ERROR_TYPE_UE) {
 		mce->u.ue_error.effective_address_provided = true;
 		mce->u.ue_error.effective_address = addr;
···
 		"Parity",
 		"Multihit",
 	};
+	static const char *mc_user_types[] = {
+		"Indeterminate",
+		"tlbie(l) invalid",
+	};
+	static const char *mc_ra_types[] = {
+		"Indeterminate",
+		"Instruction fetch (bad)",
+		"Page table walk ifetch (bad)",
+		"Page table walk ifetch (foreign)",
+		"Load (bad)",
+		"Store (bad)",
+		"Page table walk Load/Store (bad)",
+		"Page table walk Load/Store (foreign)",
+		"Load/Store (foreign)",
+	};
+	static const char *mc_link_types[] = {
+		"Indeterminate",
+		"Instruction fetch (timeout)",
+		"Page table walk ifetch (timeout)",
+		"Load (timeout)",
+		"Store (timeout)",
+		"Page table walk Load/Store (timeout)",
+	};
 
 	/* Print things out */
 	if (evt->version != MCE_V1) {
···
 			printk("%s    Effective address: %016llx\n",
 			       level, evt->u.tlb_error.effective_address);
 		break;
+	case MCE_ERROR_TYPE_USER:
+		subtype = evt->u.user_error.user_error_type <
+			ARRAY_SIZE(mc_user_types) ?
+			mc_user_types[evt->u.user_error.user_error_type]
+			: "Unknown";
+		printk("%s  Error type: User [%s]\n", level, subtype);
+		if (evt->u.user_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt->u.user_error.effective_address);
+		break;
+	case MCE_ERROR_TYPE_RA:
+		subtype = evt->u.ra_error.ra_error_type <
+			ARRAY_SIZE(mc_ra_types) ?
+			mc_ra_types[evt->u.ra_error.ra_error_type]
+			: "Unknown";
+		printk("%s  Error type: Real address [%s]\n", level, subtype);
+		if (evt->u.ra_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt->u.ra_error.effective_address);
+		break;
+	case MCE_ERROR_TYPE_LINK:
+		subtype = evt->u.link_error.link_error_type <
+			ARRAY_SIZE(mc_link_types) ?
+			mc_link_types[evt->u.link_error.link_error_type]
+			: "Unknown";
+		printk("%s  Error type: Link [%s]\n", level, subtype);
+		if (evt->u.link_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt->u.link_error.effective_address);
+		break;
 	default:
 	case MCE_ERROR_TYPE_UNKNOWN:
 		printk("%s  Error type: Unknown\n", level);
···
 	case MCE_ERROR_TYPE_TLB:
 		if (evt->u.tlb_error.effective_address_provided)
 			return evt->u.tlb_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_USER:
+		if (evt->u.user_error.effective_address_provided)
+			return evt->u.user_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_RA:
+		if (evt->u.ra_error.effective_address_provided)
+			return evt->u.ra_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_LINK:
+		if (evt->u.link_error.effective_address_provided)
+			return evt->u.link_error.effective_address;
 		break;
 	default:
 	case MCE_ERROR_TYPE_UNKNOWN:

arch/powerpc/kernel/mce_power.c

···
 }
 #endif
 
+static void flush_erat(void)
+{
+	asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
+}
+
+#define MCE_FLUSH_SLB 1
+#define MCE_FLUSH_TLB 2
+#define MCE_FLUSH_ERAT 3
+
+static int mce_flush(int what)
+{
+#ifdef CONFIG_PPC_STD_MMU_64
+	if (what == MCE_FLUSH_SLB) {
+		flush_and_reload_slb();
+		return 1;
+	}
+#endif
+	if (what == MCE_FLUSH_ERAT) {
+		flush_erat();
+		return 1;
+	}
+	if (what == MCE_FLUSH_TLB) {
+		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
+			cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static int mce_handle_flush_derrors(uint64_t dsisr, uint64_t slb, uint64_t tlb, uint64_t erat)
+{
+	if ((dsisr & slb) && mce_flush(MCE_FLUSH_SLB))
+		dsisr &= ~slb;
+	if ((dsisr & erat) && mce_flush(MCE_FLUSH_ERAT))
+		dsisr &= ~erat;
+	if ((dsisr & tlb) && mce_flush(MCE_FLUSH_TLB))
+		dsisr &= ~tlb;
+	/* Any other errors we don't understand? */
+	if (dsisr)
+		return 0;
+	return 1;
+}
+
 static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
 {
 	long handled = 1;
···
 	long handled = 1;
 	struct mce_error_info mce_error_info = { 0 };
 
+	mce_error_info.severity = MCE_SEV_ERROR_SYNC;
+	mce_error_info.initiator = MCE_INITIATOR_CPU;
+
 	srr1 = regs->msr;
 	nip = regs->nip;
 
···
 	long handled = 1;
 	struct mce_error_info mce_error_info = { 0 };
 
+	mce_error_info.severity = MCE_SEV_ERROR_SYNC;
+	mce_error_info.initiator = MCE_INITIATOR_CPU;
+
 	srr1 = regs->msr;
 	nip = regs->nip;
 
···
 		handled = mce_handle_ierror_p8(srr1);
 		mce_get_ierror_p8(&mce_error_info, srr1);
 		addr = regs->nip;
+	}
+
+	/* Handle UE error. */
+	if (mce_error_info.error_type == MCE_ERROR_TYPE_UE)
+		handled = mce_handle_ue_error(regs);
+
+	save_mce_event(regs, handled, &mce_error_info, nip, addr);
+	return handled;
+}
+
+static int mce_handle_derror_p9(struct pt_regs *regs)
+{
+	uint64_t dsisr = regs->dsisr;
+
+	return mce_handle_flush_derrors(dsisr,
+			P9_DSISR_MC_SLB_PARITY_MFSLB |
+			P9_DSISR_MC_SLB_MULTIHIT_MFSLB,
+
+			P9_DSISR_MC_TLB_MULTIHIT_MFTLB,
+
+			P9_DSISR_MC_ERAT_MULTIHIT);
+}
+
+static int mce_handle_ierror_p9(struct pt_regs *regs)
+{
+	uint64_t srr1 = regs->msr;
+
+	switch (P9_SRR1_MC_IFETCH(srr1)) {
+	case P9_SRR1_MC_IFETCH_SLB_PARITY:
+	case P9_SRR1_MC_IFETCH_SLB_MULTIHIT:
+		return mce_flush(MCE_FLUSH_SLB);
+	case P9_SRR1_MC_IFETCH_TLB_MULTIHIT:
+		return mce_flush(MCE_FLUSH_TLB);
+	case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT:
+		return mce_flush(MCE_FLUSH_ERAT);
+	default:
+		return 0;
+	}
+}
+
+static void mce_get_derror_p9(struct pt_regs *regs,
+		struct mce_error_info *mce_err, uint64_t *addr)
+{
+	uint64_t dsisr = regs->dsisr;
+
+	mce_err->severity = MCE_SEV_ERROR_SYNC;
+	mce_err->initiator = MCE_INITIATOR_CPU;
+
+	if (dsisr & P9_DSISR_MC_USER_TLBIE)
+		*addr = regs->nip;
+	else
+		*addr = regs->dar;
+
+	if (dsisr & P9_DSISR_MC_UE) {
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
+	} else if (dsisr & P9_DSISR_MC_UE_TABLEWALK) {
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+	} else if (dsisr & P9_DSISR_MC_LINK_LOAD_TIMEOUT) {
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_LOAD_TIMEOUT;
+	} else if (dsisr & P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT) {
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT;
+	} else if (dsisr & P9_DSISR_MC_ERAT_MULTIHIT) {
+		mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+		mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+	} else if (dsisr & P9_DSISR_MC_TLB_MULTIHIT_MFTLB) {
+		mce_err->error_type = MCE_ERROR_TYPE_TLB;
+		mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+	} else if (dsisr & P9_DSISR_MC_USER_TLBIE) {
+		mce_err->error_type = MCE_ERROR_TYPE_USER;
+		mce_err->u.user_error_type = MCE_USER_ERROR_TLBIE;
+	} else if (dsisr & P9_DSISR_MC_SLB_PARITY_MFSLB) {
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+	} else if (dsisr & P9_DSISR_MC_SLB_MULTIHIT_MFSLB) {
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+	} else if (dsisr & P9_DSISR_MC_RA_LOAD) {
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD;
+	} else if (dsisr & P9_DSISR_MC_RA_TABLEWALK) {
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+	} else if (dsisr & P9_DSISR_MC_RA_TABLEWALK_FOREIGN) {
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN;
+	} else if (dsisr & P9_DSISR_MC_RA_FOREIGN) {
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD_STORE_FOREIGN;
+	}
+}
+
+static void mce_get_ierror_p9(struct pt_regs *regs,
+		struct mce_error_info *mce_err, uint64_t *addr)
+{
+	uint64_t srr1 = regs->msr;
+
+	switch (P9_SRR1_MC_IFETCH(srr1)) {
+	case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE:
+	case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT:
+		mce_err->severity = MCE_SEV_FATAL;
+		break;
+	default:
+		mce_err->severity = MCE_SEV_ERROR_SYNC;
+		break;
+	}
+
+	mce_err->initiator = MCE_INITIATOR_CPU;
+
+	*addr = regs->nip;
+
+	switch (P9_SRR1_MC_IFETCH(srr1)) {
+	case P9_SRR1_MC_IFETCH_UE:
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH;
+		break;
+	case P9_SRR1_MC_IFETCH_SLB_PARITY:
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+		break;
+	case P9_SRR1_MC_IFETCH_SLB_MULTIHIT:
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+		break;
+	case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT:
+		mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+		mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+		break;
+	case P9_SRR1_MC_IFETCH_TLB_MULTIHIT:
+		mce_err->error_type = MCE_ERROR_TYPE_TLB;
+		mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+		break;
+	case P9_SRR1_MC_IFETCH_UE_TLB_RELOAD:
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
+		break;
+	case P9_SRR1_MC_IFETCH_LINK_TIMEOUT:
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_IFETCH_TIMEOUT;
+		break;
+	case P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT:
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT;
+		break;
+	case P9_SRR1_MC_IFETCH_RA:
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_IFETCH;
+		break;
+	case P9_SRR1_MC_IFETCH_RA_TABLEWALK:
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH;
+		break;
+	case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE:
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_STORE;
+		break;
+	case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT:
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_STORE_TIMEOUT;
+		break;
+	case P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN:
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN;
+		break;
+	default:
+		break;
+	}
+}
+
+long __machine_check_early_realmode_p9(struct pt_regs *regs)
+{
+	uint64_t nip, addr;
+	long handled;
+	struct mce_error_info mce_error_info = { 0 };
+
+	nip = regs->nip;
+
+	if (P9_SRR1_MC_LOADSTORE(regs->msr)) {
+		handled = mce_handle_derror_p9(regs);
+		mce_get_derror_p9(regs, &mce_error_info, &addr);
+	} else {
+		handled = mce_handle_ierror_p9(regs);
+		mce_get_ierror_p9(regs, &mce_error_info, &addr);
 	}
 
 	/* Handle UE error. */

arch/powerpc/perf/core-book3s.c

···
 			sdsync = POWER7P_MMCRA_SDAR_VALID;
 		else if (ppmu->flags & PPMU_ALT_SIPR)
 			sdsync = POWER6_MMCRA_SDSYNC;
+		else if (ppmu->flags & PPMU_NO_SIAR)
+			sdsync = MMCRA_SAMPLE_ENABLE;
 		else
 			sdsync = MMCRA_SDSYNC;
 

arch/powerpc/perf/isa207-common.c

···
 	return !(event & ~valid_mask);
 }
 
-static u64 mmcra_sdar_mode(u64 event)
+static inline bool is_event_marked(u64 event)
 {
-	if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
-		return p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
+	if (event & EVENT_IS_MARKED)
+		return true;
 
-	return MMCRA_SDAR_MODE_TLB;
+	return false;
+}
+
+static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
+{
+	/*
+	 * MMCRA[SDAR_MODE] specifices how the SDAR should be updated in
+	 * continous sampling mode.
+	 *
+	 * Incase of Power8:
+	 * MMCRA[SDAR_MODE] will be programmed as "0b01" for continous sampling
+	 * mode and will be un-changed when setting MMCRA[63] (Marked events).
+	 *
+	 * Incase of Power9:
+	 * Marked event: MMCRA[SDAR_MODE] will be set to 0b00 ('No Updates'),
+	 *               or if group already have any marked events.
+	 * Non-Marked events (for DD1):
+	 *	MMCRA[SDAR_MODE] will be set to 0b01
+	 * For rest
+	 *	MMCRA[SDAR_MODE] will be set from event code.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (is_event_marked(event) || (*mmcra & MMCRA_SAMPLE_ENABLE))
+			*mmcra &= MMCRA_SDAR_MODE_NO_UPDATES;
+		else if (!cpu_has_feature(CPU_FTR_POWER9_DD1))
+			*mmcra |=  p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
+		else if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+			*mmcra |= MMCRA_SDAR_MODE_TLB;
+	} else
+		*mmcra |= MMCRA_SDAR_MODE_TLB;
 }
 
 static u64 thresh_cmp_val(u64 value)
···
 		value |= CNST_L1_QUAL_VAL(cache);
 	}
 
-	if (event & EVENT_IS_MARKED) {
+	if (is_event_marked(event)) {
 		mask  |= CNST_SAMPLE_MASK;
 		value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT);
 	}
···
 		}
 
 		/* In continuous sampling mode, update SDAR on TLB miss */
-		mmcra |= mmcra_sdar_mode(event[i]);
+		mmcra_sdar_mode(event[i], &mmcra);
 
 		if (event[i] & EVENT_IS_L1) {
 			cache = event[i] >> EVENT_CACHE_SEL_SHIFT;
···
 			mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT;
 		}
 
-		if (event[i] & EVENT_IS_MARKED) {
+		if (is_event_marked(event[i])) {
 			mmcra |= MMCRA_SAMPLE_ENABLE;
 
 			val = (event[i] >> EVENT_SAMPLE_SHIFT) & EVENT_SAMPLE_MASK;

arch/powerpc/perf/isa207-common.h

···
 #define MMCRA_THR_CMP_SHIFT		32
 #define MMCRA_SDAR_MODE_SHIFT		42
 #define MMCRA_SDAR_MODE_TLB		(1ull << MMCRA_SDAR_MODE_SHIFT)
+#define MMCRA_SDAR_MODE_NO_UPDATES	~(0x3ull << MMCRA_SDAR_MODE_SHIFT)
 #define MMCRA_IFM_SHIFT			30
 
 /* MMCR1 Threshold Compare bit constant for power9 */

arch/powerpc/platforms/powernv/opal.c

···
 					struct machine_check_event *evt)
 {
 	int recovered = 0;
-	uint64_t ea = get_mce_fault_addr(evt);
 
 	if (!(regs->msr & MSR_RI)) {
 		/* If MSR_RI isn't set, we cannot recover */
···
 	} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
 		/* Platform corrected itself */
 		recovered = 1;
-	} else if (ea && !is_kernel_addr(ea)) {
+	} else if (evt->severity == MCE_SEV_FATAL) {
+		/* Fatal machine check */
+		pr_err("Machine check interrupt is fatal\n");
+		recovered = 0;
+	} else if ((evt->severity == MCE_SEV_ERROR_SYNC) &&
+			(user_mode(regs) && !is_global_init(current))) {
 		/*
-		 * Faulting address is not in kernel text. We should be fine.
-		 * We need to find which process uses this address.
 		 * For now, kill the task if we have received exception when
 		 * in userspace.
 		 *
 		 * TODO: Queue up this address for hwpoisioning later.
-		 */
-		if (user_mode(regs) && !is_global_init(current)) {
-			_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
-			recovered = 1;
-		} else
-			recovered = 0;
-	} else if (user_mode(regs) && !is_global_init(current) &&
-		evt->severity == MCE_SEV_ERROR_SYNC) {
-		/*
-		 * If we have received a synchronous error when in userspace
-		 * kill the task.
 		 */
 		_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
 		recovered = 1;

arch/powerpc/platforms/powernv/pci-ioda.c

···
 }
 
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
-				   struct pci_bus *bus)
+				   struct pci_bus *bus,
+				   bool add_to_group)
 {
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
 		set_dma_offset(&dev->dev, pe->tce_bypass_base);
-		iommu_add_device(&dev->dev);
+		if (add_to_group)
+			iommu_add_device(&dev->dev);
 
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
-			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
+			pnv_ioda_setup_bus_dma(pe, dev->subordinate,
+					add_to_group);
 	}
 }
 
···
 		set_iommu_table_base(&pe->pdev->dev, tbl);
 		iommu_add_device(&pe->pdev->dev);
 	} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
-		pnv_ioda_setup_bus_dma(pe, pe->pbus);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
 
 	return;
  fail:
···
 
 	pnv_pci_ioda2_set_bypass(pe, false);
 	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
+	if (pe->pbus)
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
 	pnv_ioda2_table_free(tbl);
 }
 
···
 						table_group);
 
 	pnv_pci_ioda2_setup_default_config(pe);
+	if (pe->pbus)
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
 }
 
 static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
···
 	level_shift = entries_shift + 3;
 	level_shift = max_t(unsigned, level_shift, PAGE_SHIFT);
 
+	if ((level_shift - 3) * levels + page_shift >= 60)
+		return -EINVAL;
+
 	/* Allocate TCE table */
 	addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
 			levels, tce_table_size, &offset, &total_allocated);
···
 	if (pe->flags & PNV_IODA_PE_DEV)
 		iommu_add_device(&pe->pdev->dev);
 	else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
-		pnv_ioda_setup_bus_dma(pe, pe->pbus);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
 }
 
 #ifdef CONFIG_PCI_MSI

block/bio.c

···
 	bio_list_init(&punt);
 	bio_list_init(&nopunt);
 
-	while ((bio = bio_list_pop(current->bio_list)))
+	while ((bio = bio_list_pop(&current->bio_list[0])))
 		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+	current->bio_list[0] = nopunt;
 
-	*current->bio_list = nopunt;
+	bio_list_init(&nopunt);
+	while ((bio = bio_list_pop(&current->bio_list[1])))
+		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+	current->bio_list[1] = nopunt;
 
 	spin_lock(&bs->rescue_lock);
 	bio_list_merge(&bs->rescue_list, &punt);
···
 		 * we retry with the original gfp_flags.
 		 */
 
-		if (current->bio_list && !bio_list_empty(current->bio_list))
+		if (current->bio_list &&
+		    (!bio_list_empty(&current->bio_list[0]) ||
+		     !bio_list_empty(&current->bio_list[1])))
 			gfp_mask &= ~__GFP_DIRECT_RECLAIM;
 
 		p = mempool_alloc(bs->bio_pool, gfp_mask);

block/blk-core.c

···
  */
 blk_qc_t generic_make_request(struct bio *bio)
 {
-	struct bio_list bio_list_on_stack;
+	/*
+	 * bio_list_on_stack[0] contains bios submitted by the current
+	 * make_request_fn.
+	 * bio_list_on_stack[1] contains bios that were submitted before
+	 * the current make_request_fn, but that haven't been processed
+	 * yet.
+	 */
+	struct bio_list bio_list_on_stack[2];
 	blk_qc_t ret = BLK_QC_T_NONE;
 
 	if (!generic_make_request_checks(bio))
···
 	 * should be added at the tail
 	 */
 	if (current->bio_list) {
-		bio_list_add(current->bio_list, bio);
+		bio_list_add(&current->bio_list[0], bio);
 		goto out;
 	}
 
···
 	 * bio_list, and call into ->make_request() again.
 	 */
 	BUG_ON(bio->bi_next);
-	bio_list_init(&bio_list_on_stack);
-	current->bio_list = &bio_list_on_stack;
+	bio_list_init(&bio_list_on_stack[0]);
+	current->bio_list = bio_list_on_stack;
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 
 		if (likely(blk_queue_enter(q, false) == 0)) {
-			struct bio_list hold;
 			struct bio_list lower, same;
 
 			/* Create a fresh bio_list for all subordinate requests */
-			hold = bio_list_on_stack;
-			bio_list_init(&bio_list_on_stack);
+			bio_list_on_stack[1] = bio_list_on_stack[0];
+			bio_list_init(&bio_list_on_stack[0]);
 			ret = q->make_request_fn(q, bio);
 
 			blk_queue_exit(q);
···
 			 */
 			bio_list_init(&lower);
 			bio_list_init(&same);
-			while ((bio = bio_list_pop(&bio_list_on_stack)) != NULL)
+			while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
 				if (q == bdev_get_queue(bio->bi_bdev))
 					bio_list_add(&same, bio);
 				else
 					bio_list_add(&lower, bio);
 			/* now assemble so we handle the lowest level first */
-			bio_list_merge(&bio_list_on_stack, &lower);
-			bio_list_merge(&bio_list_on_stack, &same);
-			bio_list_merge(&bio_list_on_stack, &hold);
+			bio_list_merge(&bio_list_on_stack[0], &lower);
+			bio_list_merge(&bio_list_on_stack[0], &same);
+			bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
 		} else {
 			bio_io_error(bio);
 		}
-		bio = bio_list_pop(current->bio_list);
+		bio = bio_list_pop(&bio_list_on_stack[0]);
 	} while (bio);
 	current->bio_list = NULL; /* deactivate */
 

block/blk-mq-tag.c

···
 	for (i = 0; i < set->nr_hw_queues; i++) {
 		struct blk_mq_tags *tags = set->tags[i];
 
+		if (!tags)
+			continue;
+
 		for (j = 0; j < tags->nr_tags; j++) {
 			if (!tags->static_rqs[j])
 				continue;

block/blk-mq.c

···
 	return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
 }
 
-static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
+static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
+				      bool may_sleep)
 {
 	struct request_queue *q = rq->q;
 	struct blk_mq_queue_data bd = {
···
 	}
 
 insert:
-	blk_mq_sched_insert_request(rq, false, true, true, false);
+	blk_mq_sched_insert_request(rq, false, true, false, may_sleep);
 }
 
 /*
···
 
 		if (!(data.hctx->flags & BLK_MQ_F_BLOCKING)) {
 			rcu_read_lock();
-			blk_mq_try_issue_directly(old_rq, &cookie);
+			blk_mq_try_issue_directly(old_rq, &cookie, false);
 			rcu_read_unlock();
 		} else {
 			srcu_idx = srcu_read_lock(&data.hctx->queue_rq_srcu);
-			blk_mq_try_issue_directly(old_rq, &cookie);
+			blk_mq_try_issue_directly(old_rq, &cookie, true);
 			srcu_read_unlock(&data.hctx->queue_rq_srcu, srcu_idx);
 		}
 		goto done;

crypto/af_alg.c

···
 	return err;
 }
 
-int af_alg_accept(struct sock *sk, struct socket *newsock)
+int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern)
 {
 	struct alg_sock *ask = alg_sk(sk);
 	const struct af_alg_type *type;
···
 	if (!type)
 		goto unlock;
 
-	sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, 0);
+	sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, kern);
 	err = -ENOMEM;
 	if (!sk2)
 		goto unlock;
···
 }
 EXPORT_SYMBOL_GPL(af_alg_accept);
 
-static int alg_accept(struct socket *sock, struct socket *newsock, int flags)
+static int alg_accept(struct socket *sock, struct socket *newsock, int flags,
+		      bool kern)
 {
-	return af_alg_accept(sock->sk, newsock);
+	return af_alg_accept(sock->sk, newsock, kern);
 }
 
 static const struct proto_ops alg_proto_ops = {

crypto/algif_hash.c

···
 	return err ?: len;
 }
 
-static int hash_accept(struct socket *sock, struct socket *newsock, int flags)
+static int hash_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
···
 	if (err)
 		return err;
 
-	err = af_alg_accept(ask->parent, newsock);
+	err = af_alg_accept(ask->parent, newsock, kern);
 	if (err)
 		return err;
 
···
 }
 
 static int hash_accept_nokey(struct socket *sock, struct socket *newsock,
-			     int flags)
+			     int flags, bool kern)
 {
 	int err;
 
···
 	if (err)
 		return err;
 
-	return hash_accept(sock, newsock, flags);
+	return hash_accept(sock, newsock, flags, kern);
 }
 
 static struct proto_ops algif_hash_ops_nokey = {

drivers/ata/ahci_qoriq.c

···
 	case AHCI_LS1043A:
 		if (!qpriv->ecc_addr)
 			return -EINVAL;
-		writel(ECC_DIS_ARMV8_CH2, qpriv->ecc_addr);
+		writel(readl(qpriv->ecc_addr) | ECC_DIS_ARMV8_CH2,
+				qpriv->ecc_addr);
 		writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
 		writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
 		if (qpriv->is_dmacoherent)
···
 	case AHCI_LS1046A:
 		if (!qpriv->ecc_addr)
 			return -EINVAL;
-		writel(ECC_DIS_ARMV8_CH2, qpriv->ecc_addr);
+		writel(readl(qpriv->ecc_addr) | ECC_DIS_ARMV8_CH2,
+				qpriv->ecc_addr);
 		writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
 		writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
 		if (qpriv->is_dmacoherent)

drivers/ata/libata-sff.c

···
 		break;
 
 	default:
-		WARN_ON_ONCE(1);
 		return AC_ERR_SYSTEM;
 	}
 

drivers/ata/libata-transport.c

···
 
 static void ata_tport_release(struct device *dev)
 {
-	put_device(dev->parent);
 }
 
 /**
···
 	device_initialize(dev);
 	dev->type = &ata_port_type;
 
-	dev->parent = get_device(parent);
+	dev->parent = parent;
 	dev->release = ata_tport_release;
 	dev_set_name(dev, "ata%d", ap->print_id);
 	transport_setup_device(dev);
···
 
 static void ata_tlink_release(struct device *dev)
 {
-	put_device(dev->parent);
 }
 
 /**
···
 	int error;
 
 	device_initialize(dev);
-	dev->parent = get_device(&ap->tdev);
+	dev->parent = &ap->tdev;
 	dev->release = ata_tlink_release;
 	if (ata_is_host_link(link))
 		dev_set_name(dev, "link%d", ap->print_id);
···
 
 static void ata_tdev_release(struct device *dev)
 {
-	put_device(dev->parent);
 }
 
 /**
···
 	int error;
 
 	device_initialize(dev);
-	dev->parent = get_device(&link->tdev);
+	dev->parent = &link->tdev;
 	dev->release = ata_tdev_release;
 	if (ata_is_host_link(link))
 		dev_set_name(dev, "dev%d.%d", ap->print_id,ata_dev->devno);

drivers/char/hw_random/omap-rng.c

···
 				irq, err);
 			return err;
 		}
-		omap_rng_write(priv, RNG_INTMASK_REG, RNG_SHUTDOWN_OFLO_MASK);
 
-		priv->clk = of_clk_get(pdev->dev.of_node, 0);
+		priv->clk = devm_clk_get(&pdev->dev, NULL);
 		if (IS_ERR(priv->clk) && PTR_ERR(priv->clk) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
 		if (!IS_ERR(priv->clk)) {
···
 				dev_err(&pdev->dev, "unable to enable the clk, "
 						    "err = %d\n", err);
 		}
+
+		/*
+		 * On OMAP4, enabling the shutdown_oflo interrupt is
+		 * done in the interrupt mask register. There is no
+		 * such register on EIP76, and it's enabled by the
+		 * same bit in the control register
+		 */
+		if (priv->pdata->regs[RNG_INTMASK_REG])
+			omap_rng_write(priv, RNG_INTMASK_REG,
+				       RNG_SHUTDOWN_OFLO_MASK);
+		else
+			omap_rng_write(priv, RNG_CONTROL_REG,
+				       RNG_SHUTDOWN_OFLO_MASK);
 	}
 	return 0;
 }

drivers/crypto/s5p-sss.c

···
 	scatterwalk_done(&walk, out, 0);
 }
 
-static void s5p_aes_complete(struct s5p_aes_dev *dev, int err)
+static void s5p_sg_done(struct s5p_aes_dev *dev)
 {
 	if (dev->sg_dst_cpy) {
 		dev_dbg(dev->dev,
···
 	}
 	s5p_free_sg_cpy(dev, &dev->sg_src_cpy);
 	s5p_free_sg_cpy(dev, &dev->sg_dst_cpy);
+}
 
-	/* holding a lock outside */
+/* Calls the completion. Cannot be called with dev->lock hold. */
+static void s5p_aes_complete(struct s5p_aes_dev *dev, int err)
+{
 	dev->req->base.complete(&dev->req->base, err);
 	dev->busy = false;
 }
···
 }
 
 /*
- * Returns true if new transmitting (output) data is ready and its
- * address+length have to be written to device (by calling
- * s5p_set_dma_outdata()). False otherwise.
+ * Returns -ERRNO on error (mapping of new data failed).
+ * On success returns:
+ *  - 0 if there is no more data,
+ *  - 1 if new transmitting (output) data is ready and its address+length
+ *     have to be written to device (by calling s5p_set_dma_outdata()).
  */
-static bool s5p_aes_tx(struct s5p_aes_dev *dev)
+static int s5p_aes_tx(struct s5p_aes_dev *dev)
 {
-	int err = 0;
-	bool ret = false;
+	int ret = 0;
 
 	s5p_unset_outdata(dev);
 
 	if (!sg_is_last(dev->sg_dst)) {
-		err = s5p_set_outdata(dev, sg_next(dev->sg_dst));
-		if (err)
-			s5p_aes_complete(dev, err);
-		else
-			ret = true;
-	} else {
-		s5p_aes_complete(dev, err);
-
-		dev->busy = true;
-		tasklet_schedule(&dev->tasklet);
+		ret = s5p_set_outdata(dev, sg_next(dev->sg_dst));
+		if (!ret)
+			ret = 1;
 	}
 
 	return ret;
 }
 
 /*
- * Returns true if new receiving (input) data is ready and its
- * address+length have to be written to device (by calling
- * s5p_set_dma_indata()). False otherwise.
+ * Returns -ERRNO on error (mapping of new data failed).
+ * On success returns:
+ *  - 0 if there is no more data,
+ *  - 1 if new receiving (input) data is ready and its address+length
+ *     have to be written to device (by calling s5p_set_dma_indata()).
  */
-static bool s5p_aes_rx(struct s5p_aes_dev *dev)
+static int s5p_aes_rx(struct s5p_aes_dev *dev/*, bool *set_dma*/)
 {
-	int err;
-	bool ret = false;
+	int ret = 0;
 
 	s5p_unset_indata(dev);
 
 	if (!sg_is_last(dev->sg_src)) {
-		err = s5p_set_indata(dev, sg_next(dev->sg_src));
-		if (err)
-			s5p_aes_complete(dev, err);
-		else
-			ret = true;
+		ret = s5p_set_indata(dev, sg_next(dev->sg_src));
+		if (!ret)
+			ret = 1;
 	}
 
 	return ret;
···
 {
 	struct platform_device *pdev = dev_id;
 	struct s5p_aes_dev *dev = platform_get_drvdata(pdev);
-	bool set_dma_tx = false;
-	bool set_dma_rx = false;
+	int err_dma_tx = 0;
+	int err_dma_rx = 0;
+	bool tx_end = false;
 	unsigned long flags;
 	uint32_t status;
+	int err;
 
 	spin_lock_irqsave(&dev->lock, flags);
 
+	/*
+	 * Handle rx or tx interrupt. If there is still data (scatterlist did not
+	 * reach end), then map next scatterlist entry.
+	 * In case of such mapping error, s5p_aes_complete() should be called.
+	 *
+	 * If there is no more data in tx scatter list, call s5p_aes_complete()
+	 * and schedule new tasklet.
+	 */
 	status = SSS_READ(dev, FCINTSTAT);
 	if (status & SSS_FCINTSTAT_BRDMAINT)
-		set_dma_rx = s5p_aes_rx(dev);
-	if (status & SSS_FCINTSTAT_BTDMAINT)
-		set_dma_tx = s5p_aes_tx(dev);
+		err_dma_rx = s5p_aes_rx(dev);
+
+	if (status & SSS_FCINTSTAT_BTDMAINT) {
+		if (sg_is_last(dev->sg_dst))
+			tx_end = true;
+		err_dma_tx = s5p_aes_tx(dev);
+	}
 
 	SSS_WRITE(dev, FCINTPEND, status);
 
-	/*
-	 * Writing length of DMA block (either receiving or transmitting)
-	 * will start the operation immediately, so this should be done
-	 * at the end (even after clearing pending interrupts to not miss the
-	 * interrupt).
-	 */
-	if (set_dma_tx)
-		s5p_set_dma_outdata(dev, dev->sg_dst);
-	if (set_dma_rx)
-		s5p_set_dma_indata(dev, dev->sg_src);
+	if (err_dma_rx < 0) {
+		err = err_dma_rx;
+		goto error;
+	}
+	if (err_dma_tx < 0) {
+		err = err_dma_tx;
+		goto error;
+	}
 
+	if (tx_end) {
+		s5p_sg_done(dev);
+
+		spin_unlock_irqrestore(&dev->lock, flags);
+
+		s5p_aes_complete(dev, 0);
+		dev->busy = true;
+		tasklet_schedule(&dev->tasklet);
+	} else {
+		/*
+		 * Writing length of DMA block (either receiving or
+		 * transmitting) will start the operation immediately, so this
+		 * should be done at the end (even after clearing pending
+		 * interrupts to not miss the interrupt).
+		 */
+		if (err_dma_tx == 1)
+			s5p_set_dma_outdata(dev, dev->sg_dst);
+		if (err_dma_rx == 1)
+			s5p_set_dma_indata(dev, dev->sg_src);
+
+		spin_unlock_irqrestore(&dev->lock, flags);
+	}
+
+	return IRQ_HANDLED;
+
+error:
+	s5p_sg_done(dev);
 	spin_unlock_irqrestore(&dev->lock, flags);
+	s5p_aes_complete(dev, err);
 
 	return IRQ_HANDLED;
 }
···
 	s5p_unset_indata(dev);
 
 indata_error:
-	s5p_aes_complete(dev, err);
+	s5p_sg_done(dev);
 	spin_unlock_irqrestore(&dev->lock, flags);
+	s5p_aes_complete(dev, err);
 }
 
 static void s5p_tasklet_cb(unsigned long data)
···
 		dev_warn(dev, "feed control interrupt is not available.\n");
 		goto err_irq;
 	}
-	err = devm_request_irq(dev, pdata->irq_fc, s5p_aes_interrupt,
-			       IRQF_SHARED, pdev->name, pdev);
+	err = devm_request_threaded_irq(dev, pdata->irq_fc, NULL,
+					s5p_aes_interrupt, IRQF_ONESHOT,
+					pdev->name, pdev);
 	if (err < 0) {
 		dev_warn(dev, "feed control interrupt is not available.\n");
 		goto err_irq;

drivers/isdn/gigaset/bas-gigaset.c

···
 		return -ENODEV;
 	}
 
+	if (hostif->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	dev_info(&udev->dev,
 		 "%s: Device matched (Vendor: 0x%x, Product: 0x%x)\n",
 		 __func__, le16_to_cpu(udev->descriptor.idVendor),

drivers/macintosh/macio_asic.c

···
 	 * To get all the fields, copy all archdata
 	 */
 	dev->ofdev.dev.archdata = chip->lbus.pdev->dev.archdata;
+	dev->ofdev.dev.dma_ops = chip->lbus.pdev->dev.dma_ops;
 #endif /* CONFIG_PCI */
 
 #ifdef DEBUG

drivers/md/dm.c

···
 	struct dm_offload *o = container_of(cb, struct dm_offload, cb);
 	struct bio_list list;
 	struct bio *bio;
+	int i;
 
 	INIT_LIST_HEAD(&o->cb.list);
 
 	if (unlikely(!current->bio_list))
 		return;
 
-	list = *current->bio_list;
-	bio_list_init(current->bio_list);
+	for (i = 0; i < 2; i++) {
+		list = current->bio_list[i];
+		bio_list_init(&current->bio_list[i]);
 
-	while ((bio = bio_list_pop(&list))) {
-		struct bio_set *bs = bio->bi_pool;
-		if (unlikely(!bs) || bs == fs_bio_set) {
-			bio_list_add(current->bio_list, bio);
-			continue;
+		while ((bio = bio_list_pop(&list))) {
+			struct bio_set *bs = bio->bi_pool;
+			if (unlikely(!bs) || bs == fs_bio_set) {
+				bio_list_add(&current->bio_list[i], bio);
+				continue;
+			}
+
+			spin_lock(&bs->rescue_lock);
+			bio_list_add(&bs->rescue_list, bio);
+			queue_work(bs->rescue_workqueue, &bs->rescue_work);
+			spin_unlock(&bs->rescue_lock);
 		}
-
-		spin_lock(&bs->rescue_lock);
-		bio_list_add(&bs->rescue_list, bio);
-		queue_work(bs->rescue_workqueue, &bs->rescue_work);
-		spin_unlock(&bs->rescue_lock);
 	}
 }
 

drivers/md/raid10.c

···
 				    !conf->barrier ||
 				    (atomic_read(&conf->nr_pending) &&
 				     current->bio_list &&
-				     !bio_list_empty(current->bio_list)),
+				     (!bio_list_empty(&current->bio_list[0]) ||
+				      !bio_list_empty(&current->bio_list[1]))),
 				    conf->resync_lock);
 		conf->nr_waiting--;
 		if (!conf->nr_waiting)

drivers/net/ethernet/amd/xgbe/xgbe-drv.c

···
 	processed = xgbe_rx_poll(channel, budget);
 
 	/* If we processed everything, we are done */
-	if (processed < budget) {
-		/* Turn off polling */
-		napi_complete_done(napi, processed);
-
+	if ((processed < budget) && napi_complete_done(napi, processed)) {
 		/* Enable Tx and Rx interrupts */
 		if (pdata->channel_irq_mode)
 			xgbe_enable_rx_tx_int(pdata, channel);
···
 	} while ((processed < budget) && (processed != last_processed));
 
 	/* If we processed everything, we are done */
-	if (processed < budget) {
-		/* Turn off polling */
-		napi_complete_done(napi, processed);
-
+	if ((processed < budget) && napi_complete_done(napi, processed)) {
 		/* Enable Tx and Rx interrupts */
 		xgbe_enable_rx_tx_ints(pdata);
 	}

drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c

···
 		if (!((1U << i) & self->msix_entry_mask))
 			continue;
 
-		free_irq(pci_irq_vector(pdev, i), self->aq_vec[i]);
 		if (pdev->msix_enabled)
 			irq_set_affinity_hint(pci_irq_vector(pdev, i), NULL);
+		free_irq(pci_irq_vector(pdev, i), self->aq_vec[i]);
 		self->msix_entry_mask &= ~(1U << i);
 	}
 }

drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c

···
 	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 		NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_HIGHDMA;
 
-	/* VF with OLD Hypervisor or old PF do not support filtering */
 	if (IS_PF(bp)) {
 		if (chip_is_e1x)
 			bp->accept_any_vlan = true;
 		else
 			dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
-#ifdef CONFIG_BNX2X_SRIOV
-	} else if (bp->acquire_resp.pfdev_info.pf_cap & PFVF_CAP_VLAN_FILTER) {
-		dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
-#endif
 	}
+	/* For VF we'll know whether to enable VLAN filtering after
+	 * getting a response to CHANNEL_TLV_ACQUIRE from PF.
+	 */
 
 	dev->features |= dev->hw_features | NETIF_F_HW_VLAN_CTAG_RX;
 	dev->features |= NETIF_F_HIGHDMA;
···
 	if (!netif_running(bp->dev)) {
 		DP(BNX2X_MSG_PTP,
 		   "PTP adjfreq called while the interface is down\n");
-		return -EFAULT;
+		return -ENETDOWN;
 	}
 
 	if (ppb < 0) {
···
 {
 	struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info);
 
+	if (!netif_running(bp->dev)) {
+		DP(BNX2X_MSG_PTP,
+		   "PTP adjtime called while the interface is down\n");
+		return -ENETDOWN;
+	}
+
 	DP(BNX2X_MSG_PTP, "PTP adjtime called, delta = %llx\n", delta);
 
 	timecounter_adjtime(&bp->timecounter, delta);
···
 {
 	struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info);
 	u64 ns;
+
+	if (!netif_running(bp->dev)) {
+		DP(BNX2X_MSG_PTP,
+		   "PTP gettime called while the interface is down\n");
+		return -ENETDOWN;
+	}
 
 	ns = timecounter_read(&bp->timecounter);
 
···
 {
 	struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info);
 	u64 ns;
+
+	if (!netif_running(bp->dev)) {
+		DP(BNX2X_MSG_PTP,
+		   "PTP settime called while the interface is down\n");
+		return -ENETDOWN;
+	}
 
 	ns = timespec64_to_ns(ts);
 
···
 		rc = bnx2x_vfpf_acquire(bp, tx_count, rx_count);
 		if (rc)
 			goto init_one_freemem;
+
+#ifdef CONFIG_BNX2X_SRIOV
+		/* VF with OLD Hypervisor or old PF do not support filtering */
+		if (bp->acquire_resp.pfdev_info.pf_cap & PFVF_CAP_VLAN_FILTER) {
+			dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+			dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+		}
+#endif
 	}
 
 	/* Enable SRIOV if capability found in configuration space */

drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c

···
 
 	/* Add/Remove the filter */
 	rc = bnx2x_config_vlan_mac(bp, &ramrod);
-	if (rc && rc != -EEXIST) {
+	if (rc == -EEXIST)
+		return 0;
+	if (rc) {
 		BNX2X_ERR("Failed to %s %s\n",
 			  filter->add ? "add" : "delete",
 			  (filter->type == BNX2X_VF_FILTER_VLAN_MAC) ?
···
 				"MAC" : "VLAN");
 		return rc;
 	}
+
+	filter->applied = true;
 
 	return 0;
 }
···
 	/* Rollback if needed */
 	if (i != filters->count) {
 		BNX2X_ERR("Managed only %d/%d filters - rolling back\n",
-			  i, filters->count + 1);
+			  i, filters->count);
 		while (--i >= 0) {
+			if (!filters->filters[i].applied)
+				continue;
 			filters->filters[i].add = !filters->filters[i].add;
 			bnx2x_vf_mac_vlan_config(bp, vf, qid,
 						 &filters->filters[i],
···
 			continue;
 		}
 
-		DP(BNX2X_MSG_IOV, "add addresses for vf %d\n", vf->abs_vfid);
+		DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS),
+		       "add addresses for vf %d\n", vf->abs_vfid);
 		for_each_vfq(vf, j) {
 			struct bnx2x_vf_queue *rxq = vfq_get(vf, j);
 
···
 				cpu_to_le32(U64_HI(q_stats_addr));
 			cur_query_entry->address.lo =
 				cpu_to_le32(U64_LO(q_stats_addr));
-			DP(BNX2X_MSG_IOV,
-			   "added address %x %x for vf %d queue %d client %d\n",
-			   cur_query_entry->address.hi,
-			   cur_query_entry->address.lo, cur_query_entry->funcID,
-			   j, cur_query_entry->index);
+			DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS),
+			       "added address %x %x for vf %d queue %d client %d\n",
+			       cur_query_entry->address.hi,
+			       cur_query_entry->address.lo,
+			       cur_query_entry->funcID,
+			       j, cur_query_entry->index);
 			cur_query_entry++;
 			cur_data_offset += sizeof(struct per_queue_stats);
 			stats_count++;

drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h

···
 	(BNX2X_VF_FILTER_MAC | BNX2X_VF_FILTER_VLAN) /*shortcut*/
 
 	bool add;
+	bool applied;
 	u8 *mac;
 	u16 vid;
 };

drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c

···
 	struct bnx2x *bp = netdev_priv(dev);
 	struct vfpf_set_q_filters_tlv *req = &bp->vf2pf_mbox->req.set_q_filters;
 	struct pfvf_general_resp_tlv *resp = &bp->vf2pf_mbox->resp.general_resp;
-	int rc, i = 0;
+	int rc = 0, i = 0;
 	struct netdev_hw_addr *ha;
 
 	if (bp->state != BNX2X_STATE_OPEN) {
···
 	/* Get Rx mode requested */
 	DP(NETIF_MSG_IFUP, "dev->flags = %x\n", dev->flags);
 
+	/* We support PFVF_MAX_MULTICAST_PER_VF mcast addresses tops */
+	if (netdev_mc_count(dev) > PFVF_MAX_MULTICAST_PER_VF) {
+		DP(NETIF_MSG_IFUP,
+		   "VF supports not more than %d multicast MAC addresses\n",
+		   PFVF_MAX_MULTICAST_PER_VF);
+		rc = -EINVAL;
+		goto out;
+	}
+
 	netdev_for_each_mc_addr(ha, dev) {
 		DP(NETIF_MSG_IFUP, "Adding mcast MAC: %pM\n",
 		   bnx2x_mc_addr(ha));
 		memcpy(req->multicast[i], bnx2x_mc_addr(ha), ETH_ALEN);
 		i++;
-	}
-
-	/* We support four PFVF_MAX_MULTICAST_PER_VF mcast
-	  * addresses tops
-	  */
-	if (i >= PFVF_MAX_MULTICAST_PER_VF) {
-		DP(NETIF_MSG_IFUP,
-		   "VF supports not more than %d multicast MAC addresses\n",
-		   PFVF_MAX_MULTICAST_PER_VF);
-		return -EINVAL;
 	}
 
 	req->n_multicast = i;
···
 out:
 	bnx2x_vfpf_finalize(bp, &req->first_tlv);
 
-	return 0;
+	return rc;
 }
 
 /* request pf to add a vlan for the vf */
···
 
 		if (fl) {
 			/* set mac list */
+			rc = bnx2x_vf_mac_vlan_config_list(bp, vf, fl,
+							   msg->vf_qid,
+							   false);
+			if (rc)
+				goto op_err;
+		}
+
+		/* build vlan list */
+		fl = NULL;
+
+		rc = bnx2x_vf_mbx_macvlan_list(bp, vf, msg, &fl,
+					       VFPF_VLAN_FILTER);
+		if (rc)
+			goto op_err;
+
+		if (fl) {
+			/* set vlan list */
 			rc = bnx2x_vf_mac_vlan_config_list(bp, vf, fl,
 							   msg->vf_qid,
 							   false);

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

···
 		vf->vlan = le16_to_cpu(resp->vlan) & VLAN_VID_MASK;
 	}
 #endif
+	if (BNXT_PF(bp) && (le16_to_cpu(resp->flags) &
+			    FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED))
+		bp->flags |= BNXT_FLAG_FW_LLDP_AGENT;
+
 	switch (resp->port_partition_type) {
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0:
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5:
···
 		bp->lpi_tmr_hi = le32_to_cpu(resp->valid_tx_lpi_timer_high) &
 				 PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK;
 	}
-	link_info->support_auto_speeds =
-		le16_to_cpu(resp->supported_speeds_auto_mode);
+	if (resp->supported_speeds_auto_mode)
+		link_info->support_auto_speeds =
+			le16_to_cpu(resp->supported_speeds_auto_mode);
 
 hwrm_phy_qcaps_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
···
 	if (!silent)
 		bnxt_dbg_dump_states(bp);
 	if (netif_running(bp->dev)) {
+		int rc;
+
+		if (!silent)
+			bnxt_ulp_stop(bp);
 		bnxt_close_nic(bp, false, false);
-		bnxt_open_nic(bp, false, false);
+		rc = bnxt_open_nic(bp, false, false);
+		if (!silent && !rc)
+			bnxt_ulp_start(bp);
 	}
 }
 
···
 	if (rc)
 		goto init_err_pci_clean;
 
+	rc = bnxt_hwrm_func_reset(bp);
+	if (rc)
+		goto init_err_pci_clean;
+
 	bnxt_hwrm_fw_set_time(bp);
 
 	dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG |
···
 		bp->flags |= BNXT_FLAG_STRIP_VLAN;
 
 	rc = bnxt_probe_phy(bp);
-	if (rc)
-		goto init_err_pci_clean;
-
-	rc = bnxt_hwrm_func_reset(bp);
 	if (rc)
 		goto init_err_pci_clean;
 

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

···
 					 BNXT_FLAG_ROCEV2_CAP)
 	#define BNXT_FLAG_NO_AGG_RINGS	0x20000
 	#define BNXT_FLAG_RX_PAGE_MODE	0x40000
+	#define BNXT_FLAG_FW_LLDP_AGENT	0x80000
 	#define BNXT_FLAG_CHIP_NITRO_A0	0x1000000
 
 	#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA |		\

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

···
 		return;
 
 	bp->dcbx_cap = DCB_CAP_DCBX_VER_IEEE;
-	if (BNXT_PF(bp))
+	if (BNXT_PF(bp) && !(bp->flags & BNXT_FLAG_FW_LLDP_AGENT))
 		bp->dcbx_cap |= DCB_CAP_DCBX_HOST;
 	else
 		bp->dcbx_cap |= DCB_CAP_DCBX_LLD_MANAGED;

drivers/net/ethernet/broadcom/genet/bcmgenet.c

···
 /*
  * Broadcom GENET (Gigabit Ethernet) controller driver
  *
- * Copyright (c) 2014 Broadcom Corporation
+ * Copyright (c) 2014-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
···
 			genet_dma_ring_regs[r]);
 }
 
+static int bcmgenet_begin(struct net_device *dev)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+
+	/* Turn on the clock */
+	return clk_prepare_enable(priv->clk);
+}
+
+static void bcmgenet_complete(struct net_device *dev)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+
+	/* Turn off the clock */
+	clk_disable_unprepare(priv->clk);
+}
+
 static int bcmgenet_get_link_ksettings(struct net_device *dev,
 				       struct ethtool_link_ksettings *cmd)
 {
···
 	STAT_GENET_RUNT("rx_runt_bytes", mib.rx_runt_bytes),
 	/* Misc UniMAC counters */
 	STAT_GENET_MISC("rbuf_ovflow_cnt", mib.rbuf_ovflow_cnt,
-			UMAC_RBUF_OVFL_CNT),
-	STAT_GENET_MISC("rbuf_err_cnt", mib.rbuf_err_cnt, UMAC_RBUF_ERR_CNT),
+			UMAC_RBUF_OVFL_CNT_V1),
+	STAT_GENET_MISC("rbuf_err_cnt", mib.rbuf_err_cnt,
+			UMAC_RBUF_ERR_CNT_V1),
 	STAT_GENET_MISC("mdf_err_cnt", mib.mdf_err_cnt, UMAC_MDF_ERR_CNT),
 	STAT_GENET_SOFT_MIB("alloc_rx_buff_failed", mib.alloc_rx_buff_failed),
 	STAT_GENET_SOFT_MIB("rx_dma_failed", mib.rx_dma_failed),
···
 	}
 }
 
+static u32 bcmgenet_update_stat_misc(struct bcmgenet_priv *priv, u16 offset)
+{
+	u16 new_offset;
+	u32 val;
+
+	switch (offset) {
+	case UMAC_RBUF_OVFL_CNT_V1:
+		if (GENET_IS_V2(priv))
+			new_offset = RBUF_OVFL_CNT_V2;
+		else
+			new_offset = RBUF_OVFL_CNT_V3PLUS;
+
+		val = bcmgenet_rbuf_readl(priv,	new_offset);
+		/* clear if overflowed */
+		if (val == ~0)
+			bcmgenet_rbuf_writel(priv, 0, new_offset);
+		break;
+	case UMAC_RBUF_ERR_CNT_V1:
+		if (GENET_IS_V2(priv))
+			new_offset = RBUF_ERR_CNT_V2;
+		else
+			new_offset = RBUF_ERR_CNT_V3PLUS;
+
+		val = bcmgenet_rbuf_readl(priv,	new_offset);
+		/* clear if overflowed */
+		if (val == ~0)
+			bcmgenet_rbuf_writel(priv, 0, new_offset);
+		break;
+	default:
+		val = bcmgenet_umac_readl(priv, offset);
+		/* clear if overflowed */
+		if (val == ~0)
+			bcmgenet_umac_writel(priv, 0, offset);
+		break;
+	}
+
+	return val;
+}
+
 static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv)
 {
 	int i, j = 0;
···
 		case BCMGENET_STAT_NETDEV:
 		case BCMGENET_STAT_SOFT:
 			continue;
-		case BCMGENET_STAT_MIB_RX:
-		case BCMGENET_STAT_MIB_TX:
 		case BCMGENET_STAT_RUNT:
-			if (s->type != BCMGENET_STAT_MIB_RX)
-				offset = BCMGENET_STAT_OFFSET;
+			offset += BCMGENET_STAT_OFFSET;
+			/* fall through */
+		case BCMGENET_STAT_MIB_TX:
+			offset += BCMGENET_STAT_OFFSET;
+			/* fall through */
+		case BCMGENET_STAT_MIB_RX:
 			val = bcmgenet_umac_readl(priv,
 						  UMAC_MIB_START + j + offset);
+			offset = 0;	/* Reset Offset */
 			break;
 		case BCMGENET_STAT_MISC:
-			val = bcmgenet_umac_readl(priv, s->reg_offset);
-			/* clear if overflowed */
-			if (val == ~0)
-				bcmgenet_umac_writel(priv, 0, s->reg_offset);
+			if (GENET_IS_V1(priv)) {
+				val = bcmgenet_umac_readl(priv, s->reg_offset);
+				/* clear if overflowed */
+				if (val == ~0)
+					bcmgenet_umac_writel(priv, 0,
+							     s->reg_offset);
+			} else {
+				val = bcmgenet_update_stat_misc(priv,
+								s->reg_offset);
+			}
 			break;
 		}
 
···
 
 /* standard ethtool support functions. */
 static const struct ethtool_ops bcmgenet_ethtool_ops = {
+	.begin			= bcmgenet_begin,
+	.complete		= bcmgenet_complete,
 	.get_strings		= bcmgenet_get_strings,
 	.get_sset_count		= bcmgenet_get_sset_count,
 	.get_ethtool_stats	= bcmgenet_get_ethtool_stats,
···
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct device *kdev = &priv->pdev->dev;
 	struct enet_cb *tx_cb_ptr;
-	struct netdev_queue *txq;
 	unsigned int pkts_compl = 0;
 	unsigned int bytes_compl = 0;
 	unsigned int c_index;
···
 	dev->stats.tx_packets += pkts_compl;
 	dev->stats.tx_bytes += bytes_compl;
 
-	txq = netdev_get_tx_queue(dev, ring->queue);
-	netdev_tx_completed_queue(txq, pkts_compl, bytes_compl);
-
-	if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
-		if (netif_tx_queue_stopped(txq))
-			netif_tx_wake_queue(txq);
-	}
+	netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->queue),
+				  pkts_compl, bytes_compl);
 
 	return pkts_compl;
 }
···
 	struct bcmgenet_tx_ring *ring =
 		container_of(napi, struct bcmgenet_tx_ring, napi);
 	unsigned int work_done = 0;
+	struct netdev_queue *txq;
+	unsigned long flags;
 
-	work_done = bcmgenet_tx_reclaim(ring->priv->dev, ring);
+	spin_lock_irqsave(&ring->lock, flags);
+	work_done = __bcmgenet_tx_reclaim(ring->priv->dev, ring);
+	if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
+		txq = netdev_get_tx_queue(ring->priv->dev, ring->queue);
+		netif_tx_wake_queue(txq);
+	}
+	spin_unlock_irqrestore(&ring->lock, flags);
 
 	if (work_done == 0) {
 		napi_complete(napi);
···
 /* Interrupt bottom half */
 static void bcmgenet_irq_task(struct work_struct *work)
 {
+	unsigned long flags;
+	unsigned int status;
 	struct bcmgenet_priv *priv = container_of(
 			work, struct bcmgenet_priv, bcmgenet_irq_work);
 
 	netif_dbg(priv, intr, priv->dev, "%s\n", __func__);
 
-	if (priv->irq0_stat & UMAC_IRQ_MPD_R) {
-		priv->irq0_stat &= ~UMAC_IRQ_MPD_R;
+	spin_lock_irqsave(&priv->lock, flags);
+	status = priv->irq0_stat;
+	priv->irq0_stat = 0;
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	if (status & UMAC_IRQ_MPD_R) {
 		netif_dbg(priv, wol, priv->dev,
 			  "magic packet detected, waking up\n");
 		bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
 	}
 
 	/* Link UP/DOWN event */
-	if (priv->irq0_stat & UMAC_IRQ_LINK_EVENT) {
+	if (status & UMAC_IRQ_LINK_EVENT)
 		phy_mac_interrupt(priv->phydev,
-				  !!(priv->irq0_stat & UMAC_IRQ_LINK_UP));
-		priv->irq0_stat &= ~UMAC_IRQ_LINK_EVENT;
-	}
+				  !!(status & UMAC_IRQ_LINK_UP));
 }
 
 /* bcmgenet_isr1: handle Rx and Tx priority queues */
···
 	struct bcmgenet_priv *priv = dev_id;
 	struct bcmgenet_rx_ring *rx_ring;
 	struct bcmgenet_tx_ring *tx_ring;
-	unsigned int index;
+	unsigned int index, status;
 
-	/* Save irq status for bottom-half processing. */
-	priv->irq1_stat =
-		bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_STAT) &
+	/* Read irq status */
+	status = bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_STAT) &
 		~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS);
 
 	/* clear interrupts */
-	bcmgenet_intrl2_1_writel(priv, priv->irq1_stat, INTRL2_CPU_CLEAR);
+	bcmgenet_intrl2_1_writel(priv, status, INTRL2_CPU_CLEAR);
 
 	netif_dbg(priv, intr, priv->dev,
-		  "%s: IRQ=0x%x\n", __func__, priv->irq1_stat);
+		  "%s: IRQ=0x%x\n", __func__, status);
 
 	/* Check Rx priority queue interrupts */
 	for (index = 0; index < priv->hw_params->rx_queues; index++) {
-		if (!(priv->irq1_stat & BIT(UMAC_IRQ1_RX_INTR_SHIFT + index)))
+		if (!(status & BIT(UMAC_IRQ1_RX_INTR_SHIFT + index)))
 			continue;
 
 		rx_ring = &priv->rx_rings[index];
···
 
 	/* Check Tx priority queue interrupts */
 	for (index = 0; index < priv->hw_params->tx_queues; index++) {
-		if (!(priv->irq1_stat & BIT(index)))
+		if (!(status & BIT(index)))
 			continue;
 
 		tx_ring = &priv->tx_rings[index];
···
 	struct bcmgenet_priv *priv = dev_id;
 	struct bcmgenet_rx_ring *rx_ring;
 	struct bcmgenet_tx_ring *tx_ring;
+	unsigned int status;
+	unsigned long flags;
 
-	/* Save irq status for bottom-half processing. */
-	priv->irq0_stat =
-		bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT) &
+	/* Read irq status */
+	status = bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT) &
 		~bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
 
 	/* clear interrupts */
-	bcmgenet_intrl2_0_writel(priv, priv->irq0_stat, INTRL2_CPU_CLEAR);
+	bcmgenet_intrl2_0_writel(priv, status, INTRL2_CPU_CLEAR);
 
 	netif_dbg(priv, intr, priv->dev,
-		  "IRQ=0x%x\n", priv->irq0_stat);
+		  "IRQ=0x%x\n", status);
 
-	if (priv->irq0_stat & UMAC_IRQ_RXDMA_DONE) {
+	if (status & UMAC_IRQ_RXDMA_DONE) {
 		rx_ring = &priv->rx_rings[DESC_INDEX];
 
 		if (likely(napi_schedule_prep(&rx_ring->napi))) {
···
 		}
 	}
 
-	if (priv->irq0_stat & UMAC_IRQ_TXDMA_DONE) {
+	if (status & UMAC_IRQ_TXDMA_DONE) {
 		tx_ring = &priv->tx_rings[DESC_INDEX];
 
 		if (likely(napi_schedule_prep(&tx_ring->napi))) {
···
 		}
 	}
 
-	if (priv->irq0_stat & (UMAC_IRQ_PHY_DET_R |
-				UMAC_IRQ_PHY_DET_F |
-				UMAC_IRQ_LINK_EVENT |
-				UMAC_IRQ_HFB_SM |
-				UMAC_IRQ_HFB_MM |
-				UMAC_IRQ_MPD_R)) {
-		/* all other interested interrupts handled in bottom half */
-		schedule_work(&priv->bcmgenet_irq_work);
+	if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
+		status & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
+		wake_up(&priv->wq);
 	}
 
-	if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
-	    priv->irq0_stat & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
-		priv->irq0_stat &= ~(UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR);
-		wake_up(&priv->wq);
+	/* all other interested interrupts handled in bottom half */
+	status &= (UMAC_IRQ_LINK_EVENT |
+		   UMAC_IRQ_MPD_R);
+	if (status) {
+		/* Save irq status for bottom-half processing. */
+		spin_lock_irqsave(&priv->lock, flags);
+		priv->irq0_stat |= status;
+		spin_unlock_irqrestore(&priv->lock, flags);
+
+		schedule_work(&priv->bcmgenet_irq_work);
 	}
 
 	return IRQ_HANDLED;
···
 err_fini_dma:
 	bcmgenet_fini_dma(priv);
 err_clk_disable:
+	if (priv->internal_phy)
+		bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
 	clk_disable_unprepare(priv->clk);
 	return ret;
 }
···
 	 */
 	gphy_rev = reg & 0xffff;
 
+	/* This is reserved so should require special treatment */
+	if (gphy_rev == 0 || gphy_rev == 0x01ff) {
+		pr_warn("Invalid GPHY revision detected: 0x%04x\n", gphy_rev);
+		return;
+	}
+
 	/* This is the good old scheme, just GPHY major, no minor nor patch */
 	if ((gphy_rev & 0xf0) != 0)
 		priv->gphy_rev = gphy_rev << 8;
···
 	/* This is the new scheme, GPHY major rolls over with 0x10 = rev G0 */
 	else if ((gphy_rev & 0xff00) != 0)
 		priv->gphy_rev = gphy_rev;
-
-	/* This is reserved so should require special treatment */
-	else if (gphy_rev == 0 || gphy_rev == 0x01ff) {
-		pr_warn("Invalid GPHY revision detected: 0x%04x\n", gphy_rev);
-		return;
-	}
 
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
 	if (!(params->flags & GENET_HAS_40BITS))
···
 	const void *macaddr;
 	struct resource *r;
 	int err = -EIO;
+	const char *phy_mode_str;
 
 	/* Up to GENET_MAX_MQ_CNT + 1 TX queues and RX queues */
 	dev = alloc_etherdev_mqs(sizeof(*priv), GENET_MAX_MQ_CNT + 1,
···
 		err = PTR_ERR(priv->base);
 		goto err;
 	}
+
+	spin_lock_init(&priv->lock);
 
 	SET_NETDEV_DEV(dev, &pdev->dev);
 	dev_set_drvdata(&pdev->dev, dev);
···
 		dev_warn(&priv->pdev->dev, "failed to get enet-eee clock\n");
 		priv->clk_eee = NULL;
 	}
+
+	/* If this is an internal GPHY, power it on now, before UniMAC is
+	 * brought out of reset as absolutely no UniMAC activity is allowed
+	 */
+	if (dn && !of_property_read_string(dn, "phy-mode", &phy_mode_str) &&
+	    !strcasecmp(phy_mode_str, "internal"))
+		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
 
 	err = reset_umac(priv);
 	if (err)
···
 	return 0;
 
 out_clk_disable:
+	if (priv->internal_phy)
+		bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
 	clk_disable_unprepare(priv->clk);
 	return ret;
 }

drivers/net/ethernet/broadcom/genet/bcmgenet.h

···
 /*
- * Copyright (c) 2014 Broadcom Corporation
+ * Copyright (c) 2014-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
···
 #define  MDIO_REG_SHIFT			16
 #define  MDIO_REG_MASK			0x1F
 
-#define UMAC_RBUF_OVFL_CNT		0x61C
+#define UMAC_RBUF_OVFL_CNT_V1		0x61C
+#define RBUF_OVFL_CNT_V2		0x80
+#define RBUF_OVFL_CNT_V3PLUS		0x94
 
 #define UMAC_MPD_CTRL			0x620
 #define  MPD_EN				(1 << 0)
···
 
 #define UMAC_MPD_PW_MS			0x624
 #define UMAC_MPD_PW_LS			0x628
-#define UMAC_RBUF_ERR_CNT		0x634
+#define UMAC_RBUF_ERR_CNT_V1		0x634
+#define RBUF_ERR_CNT_V2			0x84
+#define RBUF_ERR_CNT_V3PLUS		0x98
 #define UMAC_MDF_ERR_CNT		0x638
 #define UMAC_MDF_CTRL			0x650
 #define UMAC_MDF_ADDR			0x654
···
 	struct work_struct bcmgenet_irq_work;
 	int irq0;
 	int irq1;
-	unsigned int irq0_stat;
-	unsigned int irq1_stat;
 	int wol_irq;
 	bool wol_irq_disabled;
+
+	/* shared status */
+	spinlock_t lock;
+	unsigned int irq0_stat;
 
 	/* HW descriptors/checksum variables */
 	bool desc_64b_en;

drivers/net/ethernet/cavium/liquidio/lio_main.c

···
 	 */
 	struct octeon_sg_entry *sg;
 
-	u64 sg_dma_ptr;
+	dma_addr_t sg_dma_ptr;
 };
 
 struct handshake {
···
 	struct octnic_gather *g;
 	int i;
 
+	kfree(lio->glist_lock);
+	lio->glist_lock = NULL;
+
 	if (!lio->glist)
 		return;
 
···
 		do {
 			g = (struct octnic_gather *)
 				list_delete_head(&lio->glist[i]);
-			if (g) {
-				if (g->sg) {
-					dma_unmap_single(&lio->oct_dev->
-							 pci_dev->dev,
-							 g->sg_dma_ptr,
-							 g->sg_size,
-							 DMA_TO_DEVICE);
-					kfree((void *)((unsigned long)g->sg -
-						       g->adjust));
-				}
+			if (g)
 				kfree(g);
-			}
 		} while (g);
+
+		if (lio->glists_virt_base && lio->glists_virt_base[i]) {
+			lio_dma_free(lio->oct_dev,
+				     lio->glist_entry_size * lio->tx_qsize,
+				     lio->glists_virt_base[i],
+				     lio->glists_dma_base[i]);
+		}
 	}
 
-	kfree((void *)lio->glist);
-	kfree((void *)lio->glist_lock);
+	kfree(lio->glists_virt_base);
+	lio->glists_virt_base = NULL;
+
+	kfree(lio->glists_dma_base);
+	lio->glists_dma_base = NULL;
+
+	kfree(lio->glist);
+	lio->glist = NULL;
 }
 
 /**
···
 	lio->glist_lock = kcalloc(num_iqs, sizeof(*lio->glist_lock),
 				  GFP_KERNEL);
 	if (!lio->glist_lock)
-		return 1;
+		return -ENOMEM;
 
 	lio->glist = kcalloc(num_iqs, sizeof(*lio->glist),
 			     GFP_KERNEL);
 	if (!lio->glist) {
-		kfree((void *)lio->glist_lock);
-		return 1;
+		kfree(lio->glist_lock);
+		lio->glist_lock = NULL;
+		return -ENOMEM;
+	}
+
+	lio->glist_entry_size =
+		ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE);
+
+	/* allocate memory to store virtual and dma base address of
+	 * per glist consistent memory
+	 */
+	lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base),
+					GFP_KERNEL);
+	lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base),
+				       GFP_KERNEL);
+
+	if (!lio->glists_virt_base || !lio->glists_dma_base) {
+		delete_glists(lio);
+		return -ENOMEM;
 	}
 
 	for (i = 0; i < num_iqs; i++) {
···
 
 		INIT_LIST_HEAD(&lio->glist[i]);
 
+		lio->glists_virt_base[i] =
+			lio_dma_alloc(oct,
+				      lio->glist_entry_size * lio->tx_qsize,
+				      &lio->glists_dma_base[i]);
+
+		if (!lio->glists_virt_base[i]) {
+			delete_glists(lio);
+			return -ENOMEM;
+		}
+
 		for (j = 0; j < lio->tx_qsize; j++) {
 			g = kzalloc_node(sizeof(*g), GFP_KERNEL,
 					 numa_node);
···
 			if (!g)
 				break;
 
-			g->sg_size = ((ROUNDUP4(OCTNIC_MAX_SG) >> 2) *
-				      OCT_SG_ENTRY_SIZE);
+			g->sg = lio->glists_virt_base[i] +
+				(j * lio->glist_entry_size);
 
-			g->sg = kmalloc_node(g->sg_size + 8,
-					     GFP_KERNEL, numa_node);
-			if (!g->sg)
-				g->sg = kmalloc(g->sg_size + 8, GFP_KERNEL);
-			if (!g->sg) {
-				kfree(g);
-				break;
-			}
-
-			/* The gather component should be aligned on 64-bit
-			 * boundary
-			 */
-			if (((unsigned long)g->sg) & 7) {
-				g->adjust = 8 - (((unsigned long)g->sg) & 7);
-				g->sg = (struct octeon_sg_entry *)
-					((unsigned long)g->sg + g->adjust);
-			}
-			g->sg_dma_ptr = dma_map_single(&oct->pci_dev->dev,
-						       g->sg, g->sg_size,
-						       DMA_TO_DEVICE);
-			if (dma_mapping_error(&oct->pci_dev->dev,
-					      g->sg_dma_ptr)) {
-				kfree((void *)((unsigned long)g->sg -
-					       g->adjust));
-				kfree(g);
-				break;
-			}
+			g->sg_dma_ptr = lio->glists_dma_base[i] +
+					(j * lio->glist_entry_size);
 
 			list_add_tail(&g->list, &lio->glist[i]);
 		}
 
 		if (j != lio->tx_qsize) {
 			delete_glists(lio);
-			return 1;
+			return -ENOMEM;
 		}
 	}
 
···
 		i++;
 	}
 
-	dma_sync_single_for_cpu(&lio->oct_dev->pci_dev->dev,
-				g->sg_dma_ptr, g->sg_size, DMA_TO_DEVICE);
-
 	iq = skb_iq(lio, skb);
 	spin_lock(&lio->glist_lock[iq]);
 	list_add_tail(&g->list, &lio->glist[iq]);
···
 			       frag->size, DMA_TO_DEVICE);
 		i++;
 	}
-
-	dma_sync_single_for_cpu(&lio->oct_dev->pci_dev->dev,
-				g->sg_dma_ptr, g->sg_size, DMA_TO_DEVICE);
 
 	iq = skb_iq(lio, skb);
 
···
 			i++;
 		}
 
-		dma_sync_single_for_device(&oct->pci_dev->dev, g->sg_dma_ptr,
-					   g->sg_size, DMA_TO_DEVICE);
 		dptr = g->sg_dma_ptr;
 
 		if (OCTEON_CN23XX_PF(oct))

drivers/net/ethernet/cavium/liquidio/lio_vf_main.c

···
 	 * received from the IP layer.
 	 */
 	struct octeon_sg_entry *sg;
+
+	dma_addr_t sg_dma_ptr;
 };
 
 struct octeon_device_priv {
···
 	struct octnic_gather *g;
 	int i;
 
+	kfree(lio->glist_lock);
+	lio->glist_lock = NULL;
+
 	if (!lio->glist)
 		return;
 
···
 		do {
 			g = (struct octnic_gather *)
 			    list_delete_head(&lio->glist[i]);
-			if (g) {
-				if (g->sg)
-					kfree((void *)((unsigned long)g->sg -
-							g->adjust));
+			if (g)
 				kfree(g);
-			}
 		} while (g);
+
+		if (lio->glists_virt_base && lio->glists_virt_base[i]) {
+			lio_dma_free(lio->oct_dev,
+				     lio->glist_entry_size * lio->tx_qsize,
+				     lio->glists_virt_base[i],
+				     lio->glists_dma_base[i]);
+		}
 	}
 
+	kfree(lio->glists_virt_base);
+	lio->glists_virt_base = NULL;
+
+	kfree(lio->glists_dma_base);
+	lio->glists_dma_base = NULL;
+
 	kfree(lio->glist);
-	kfree(lio->glist_lock);
+	lio->glist = NULL;
 }
 
 /**
···
 	lio->glist_lock =
 	    kzalloc(sizeof(*lio->glist_lock) * num_iqs, GFP_KERNEL);
 	if (!lio->glist_lock)
-		return 1;
+		return -ENOMEM;
 
 	lio->glist =
 	    kzalloc(sizeof(*lio->glist) * num_iqs, GFP_KERNEL);
 	if (!lio->glist) {
 		kfree(lio->glist_lock);
-		return 1;
+		lio->glist_lock = NULL;
+		return -ENOMEM;
+	}
+
+	lio->glist_entry_size =
+		ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE);
+
+	/* allocate memory to store virtual and dma base address of
+	 * per glist consistent memory
+	 */
+	lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base),
+					GFP_KERNEL);
+	lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base),
+				       GFP_KERNEL);
+
+	if (!lio->glists_virt_base || !lio->glists_dma_base) {
+		delete_glists(lio);
+		return -ENOMEM;
 	}
 
 	for (i = 0; i < num_iqs; i++) {
···
 
 		INIT_LIST_HEAD(&lio->glist[i]);
 
+		lio->glists_virt_base[i] =
+			lio_dma_alloc(lio->oct_dev,
+				      lio->glist_entry_size * lio->tx_qsize,
+				      &lio->glists_dma_base[i]);
+
+		if (!lio->glists_virt_base[i]) {
+			delete_glists(lio);
+			return -ENOMEM;
+		}
+
 		for (j = 0; j < lio->tx_qsize; j++) {
 			g = kzalloc(sizeof(*g), GFP_KERNEL);
 			if (!g)
 				break;
 
-			g->sg_size = ((ROUNDUP4(OCTNIC_MAX_SG) >> 2) *
-				      OCT_SG_ENTRY_SIZE);
+			g->sg = lio->glists_virt_base[i] +
+				(j * lio->glist_entry_size);
 
-			g->sg = kmalloc(g->sg_size + 8, GFP_KERNEL);
-			if (!g->sg) {
-				kfree(g);
-				break;
-			}
+			g->sg_dma_ptr = lio->glists_dma_base[i] +
+					(j * lio->glist_entry_size);
 
-			/* The gather component should be aligned on 64-bit
-			 * boundary
-			 */
-			if (((unsigned long)g->sg) & 7) {
-				g->adjust = 8 - (((unsigned long)g->sg) & 7);
-				g->sg = (struct octeon_sg_entry *)
-					((unsigned long)g->sg + g->adjust);
-			}
 			list_add_tail(&g->list, &lio->glist[i]);
 		}
 
 		if (j != lio->tx_qsize) {
 			delete_glists(lio);
-			return 1;
+			return -ENOMEM;
 		}
 	}
 
···
 		i++;
 	}
 
-	dma_unmap_single(&lio->oct_dev->pci_dev->dev,
-			 finfo->dptr, g->sg_size,
-			 DMA_TO_DEVICE);
-
 	iq = skb_iq(lio, skb);
 
 	spin_lock(&lio->glist_lock[iq]);
···
 			       frag->size, DMA_TO_DEVICE);
 		i++;
 	}
-
-	dma_unmap_single(&lio->oct_dev->pci_dev->dev,
-			 finfo->dptr, g->sg_size,
-			 DMA_TO_DEVICE);
 
 	iq = skb_iq(lio, skb);
 
···
 			i++;
 		}
 
-		dptr = dma_map_single(&oct->pci_dev->dev,
-				      g->sg, g->sg_size,
-				      DMA_TO_DEVICE);
-		if (dma_mapping_error(&oct->pci_dev->dev, dptr)) {
-			dev_err(&oct->pci_dev->dev, "%s DMA mapping error 4\n",
-				__func__);
-			dma_unmap_single(&oct->pci_dev->dev, g->sg[0].ptr[0],
-					 skb->len - skb->data_len,
-					 DMA_TO_DEVICE);
-			for (j = 1; j <= frags; j++) {
-				frag = &skb_shinfo(skb)->frags[j - 1];
-				dma_unmap_page(&oct->pci_dev->dev,
-					       g->sg[j >> 2].ptr[j & 3],
-					       frag->size, DMA_TO_DEVICE);
-			}
-			return NETDEV_TX_BUSY;
-		}
+		dptr = g->sg_dma_ptr;
 
 		ndata.cmd.cmd3.dptr = dptr;
 		finfo->dptr = dptr;

drivers/net/ethernet/cavium/liquidio/octeon_config.h

···
 #define   CN23XX_MAX_RINGS_PER_VF          8
 
 #define   CN23XX_MAX_INPUT_QUEUES	CN23XX_MAX_RINGS_PER_PF
-#define   CN23XX_MAX_IQ_DESCRIPTORS	2048
+#define   CN23XX_MAX_IQ_DESCRIPTORS	512
 #define   CN23XX_DB_MIN                 1
 #define   CN23XX_DB_MAX                 8
 #define   CN23XX_DB_TIMEOUT             1
 
 #define   CN23XX_MAX_OUTPUT_QUEUES	CN23XX_MAX_RINGS_PER_PF
-#define   CN23XX_MAX_OQ_DESCRIPTORS	2048
+#define   CN23XX_MAX_OQ_DESCRIPTORS	512
 #define   CN23XX_OQ_BUF_SIZE		1536
 #define   CN23XX_OQ_PKTSPER_INTR	128
 /*#define CAVIUM_ONLY_CN23XX_RX_PERF*/
-#define   CN23XX_OQ_REFIL_THRESHOLD	128
+#define   CN23XX_OQ_REFIL_THRESHOLD	16
 
 #define   CN23XX_OQ_INTR_PKT		64
 #define   CN23XX_OQ_INTR_TIME		100

drivers/net/ethernet/cavium/liquidio/octeon_droq.c

···
 			recv_buffer_destroy(droq->recv_buf_list[i].buffer,
 					    pg_info);
 
-		if (droq->desc_ring && droq->desc_ring[i].info_ptr)
-			lio_unmap_ring_info(oct->pci_dev,
-					    (u64)droq->
-					    desc_ring[i].info_ptr,
-					    OCT_DROQ_INFO_SIZE);
 		droq->recv_buf_list[i].buffer = NULL;
 	}
 
···
 	vfree(droq->recv_buf_list);
 
 	if (droq->info_base_addr)
-		cnnic_free_aligned_dma(oct->pci_dev, droq->info_list,
-				       droq->info_alloc_size,
-				       droq->info_base_addr,
-				       droq->info_list_dma);
+		lio_free_info_buffer(oct, droq);
 
 	if (droq->desc_ring)
 		lio_dma_free(oct, (droq->max_count * OCT_DROQ_DESC_SIZE),
···
 	dev_dbg(&oct->pci_dev->dev, "droq[%d]: num_desc: %d\n", q_no,
 		droq->max_count);
 
-	droq->info_list =
-		cnnic_numa_alloc_aligned_dma((droq->max_count *
-					      OCT_DROQ_INFO_SIZE),
-					     &droq->info_alloc_size,
-					     &droq->info_base_addr,
-					     numa_node);
+	droq->info_list = lio_alloc_info_buffer(oct, droq);
 	if (!droq->info_list) {
 		dev_err(&oct->pci_dev->dev, "Cannot allocate memory for info list.\n");
 		lio_dma_free(oct, (droq->max_count * OCT_DROQ_DESC_SIZE),

drivers/net/ethernet/cavium/liquidio/octeon_droq.h

···
 	size_t desc_ring_dma;
 
 	/** Info ptr list are allocated at this virtual address. */
-	size_t info_base_addr;
+	void *info_base_addr;
 
 	/** DMA mapped address of the info list */
-	size_t info_list_dma;
+	dma_addr_t info_list_dma;
 
 	/** Allocated size of info list. */
 	u32 info_alloc_size;

drivers/net/ethernet/cavium/liquidio/octeon_main.h

···
 	return 1;
 }
 
-static inline void *
-cnnic_numa_alloc_aligned_dma(u32 size,
-			     u32 *alloc_size,
-			     size_t *orig_ptr,
-			     int numa_node)
-{
-	int retries = 0;
-	void *ptr = NULL;
-
-#define OCTEON_MAX_ALLOC_RETRIES     1
-	do {
-		struct page *page = NULL;
-
-		page = alloc_pages_node(numa_node,
-					GFP_KERNEL,
-					get_order(size));
-		if (!page)
-			page = alloc_pages(GFP_KERNEL,
-					   get_order(size));
-		ptr = (void *)page_address(page);
-		if ((unsigned long)ptr & 0x07) {
-			__free_pages(page, get_order(size));
-			ptr = NULL;
-			/* Increment the size required if the first
-			 * attempt failed.
-			 */
-			if (!retries)
-				size += 7;
-		}
-		retries++;
-	} while ((retries <= OCTEON_MAX_ALLOC_RETRIES) && !ptr);
-
-	*alloc_size = size;
-	*orig_ptr = (unsigned long)ptr;
-	if ((unsigned long)ptr & 0x07)
-		ptr = (void *)(((unsigned long)ptr + 7) & ~(7UL));
-	return ptr;
-}
-
-#define cnnic_free_aligned_dma(pci_dev, ptr, size, orig_ptr, dma_addr) \
-		free_pages(orig_ptr, get_order(size))
-
 static inline int
 sleep_cond(wait_queue_head_t *wait_queue, int *condition)
 {

drivers/net/ethernet/cavium/liquidio/octeon_network.h

···
 
 	/** Array of gather component linked lists */
 	struct list_head *glist;
+	void **glists_virt_base;
+	dma_addr_t *glists_dma_base;
+	u32 glist_entry_size;
 
 	/** Pointer to the NIC properties for the Octeon device this network
 	 *  interface is associated with.
···
 #define lio_dma_free(oct, size, virt_addr, dma_addr) \
 	dma_free_coherent(&(oct)->pci_dev->dev, size, virt_addr, dma_addr)
 
+static inline void *
+lio_alloc_info_buffer(struct octeon_device *oct,
+		      struct octeon_droq *droq)
+{
+	void *virt_ptr;
+
+	virt_ptr = lio_dma_alloc(oct, (droq->max_count * OCT_DROQ_INFO_SIZE),
+				 &droq->info_list_dma);
+	if (virt_ptr) {
+		droq->info_alloc_size = droq->max_count * OCT_DROQ_INFO_SIZE;
+		droq->info_base_addr = virt_ptr;
+	}
+
+	return virt_ptr;
+}
+
+static inline void lio_free_info_buffer(struct octeon_device *oct,
+					struct octeon_droq *droq)
+{
+	lio_dma_free(oct, droq->info_alloc_size, droq->info_base_addr,
+		     droq->info_list_dma);
+}
+
 static inline
 void *get_rbd(struct sk_buff *skb)
 {
···
 static inline u64
 lio_map_ring_info(struct octeon_droq *droq, u32 i)
 {
-	dma_addr_t dma_addr;
-	struct octeon_device *oct = droq->oct_dev;
-
-	dma_addr = dma_map_single(&oct->pci_dev->dev, &droq->info_list[i],
-				  OCT_DROQ_INFO_SIZE, DMA_FROM_DEVICE);
-
-	WARN_ON(dma_mapping_error(&oct->pci_dev->dev, dma_addr));
-
-	return (u64)dma_addr;
-}
-
-static inline void
-lio_unmap_ring_info(struct pci_dev *pci_dev,
-		    u64 info_ptr, u32 size)
-{
-	dma_unmap_single(&pci_dev->dev, info_ptr, size, DMA_FROM_DEVICE);
+	return droq->info_list_dma + (i * sizeof(struct octeon_droq_info));
 }
 
 static inline u64

drivers/net/ethernet/cavium/thunder/nic.h

···
 #define	MAX_QUEUES_PER_QSET			8
 	struct queue_set	*qs;
 	struct nicvf_cq_poll	*napi[8];
+	void			*iommu_domain;
 	u8			vf_id;
 	u8			sqs_id;
 	bool                    sqs_mode;

drivers/net/ethernet/cavium/thunder/nicvf_main.c

···
 #include <linux/log2.h>
 #include <linux/prefetch.h>
 #include <linux/irq.h>
+#include <linux/iommu.h>
 
 #include "nic_reg.h"
 #include "nic.h"
···
 			/* Get actual TSO descriptors and free them */
 			tso_sqe =
 			 (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, hdr->rsvd2);
+			nicvf_unmap_sndq_buffers(nic, sq, hdr->rsvd2,
+						 tso_sqe->subdesc_cnt);
 			nicvf_put_sq_desc(sq, tso_sqe->subdesc_cnt + 1);
+		} else {
+			nicvf_unmap_sndq_buffers(nic, sq, cqe_tx->sqe_ptr,
+						 hdr->subdesc_cnt);
 		}
 		nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
 		prefetch(skb);
···
 {
 	struct sk_buff *skb;
 	struct nicvf *nic = netdev_priv(netdev);
+	struct nicvf *snic = nic;
 	int err = 0;
 	int rq_idx;
 
···
 	if (err && !cqe_rx->rb_cnt)
 		return;
 
-	skb = nicvf_get_rcv_skb(nic, cqe_rx);
+	skb = nicvf_get_rcv_skb(snic, cqe_rx);
 	if (!skb) {
 		netdev_dbg(nic->netdev, "Packet not received\n");
 		return;
···
 
 	if (!pass1_silicon(nic->pdev))
 		nic->hw_tso = true;
+
+	/* Get iommu domain for iova to physical addr conversion */
+	nic->iommu_domain = iommu_get_domain_for_dev(dev);
 
 	pci_read_config_word(nic->pdev, PCI_SUBSYSTEM_ID, &sdevid);
 	if (sdevid == 0xA134)

drivers/net/ethernet/cavium/thunder/nicvf_queues.c

···
 #include <linux/netdevice.h>
 #include <linux/ip.h>
 #include <linux/etherdevice.h>
+#include <linux/iommu.h>
 #include <net/ip.h>
 #include <net/tso.h>
 
···
 #include "nic.h"
 #include "q_struct.h"
 #include "nicvf_queues.h"
+
+#define NICVF_PAGE_ORDER ((PAGE_SIZE <= 4096) ?  PAGE_ALLOC_COSTLY_ORDER : 0)
+
+static inline u64 nicvf_iova_to_phys(struct nicvf *nic, dma_addr_t dma_addr)
+{
+	/* Translation is installed only when IOMMU is present */
+	if (nic->iommu_domain)
+		return iommu_iova_to_phys(nic->iommu_domain, dma_addr);
+	return dma_addr;
+}
 
 static void nicvf_get_page(struct nicvf *nic)
 {
···
 static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp,
 					 u32 buf_len, u64 **rbuf)
 {
-	int order = (PAGE_SIZE <= 4096) ?  PAGE_ALLOC_COSTLY_ORDER : 0;
+	int order = NICVF_PAGE_ORDER;
 
 	/* Check if request can be accomodated in previous allocated page */
 	if (nic->rb_page &&
···
 	}
 
 	nicvf_get_page(nic);
-	nic->rb_page = NULL;
 
 	/* Allocate a new page */
+	nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
+				   order);
 	if (!nic->rb_page) {
-		nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
-					   order);
-		if (!nic->rb_page) {
-			this_cpu_inc(nic->pnicvf->drv_stats->
-				     rcv_buffer_alloc_failures);
-			return -ENOMEM;
-		}
-		nic->rb_page_offset = 0;
+		this_cpu_inc(nic->pnicvf->drv_stats->rcv_buffer_alloc_failures);
+		return -ENOMEM;
 	}
-
+	nic->rb_page_offset = 0;
 ret:
-	*rbuf = (u64 *)((u64)page_address(nic->rb_page) + nic->rb_page_offset);
+	/* HW will ensure data coherency, CPU sync not required */
+	*rbuf = (u64 *)((u64)dma_map_page_attrs(&nic->pdev->dev, nic->rb_page,
+						nic->rb_page_offset, buf_len,
+						DMA_FROM_DEVICE,
+						DMA_ATTR_SKIP_CPU_SYNC));
+	if (dma_mapping_error(&nic->pdev->dev, (dma_addr_t)*rbuf)) {
+		if (!nic->rb_page_offset)
+			__free_pages(nic->rb_page, order);
+		nic->rb_page = NULL;
+		return -ENOMEM;
+	}
 	nic->rb_page_offset += buf_len;
 
 	return 0;
···
 	rbdr->dma_size = buf_size;
 	rbdr->enable = true;
 	rbdr->thresh = RBDR_THRESH;
+	rbdr->head = 0;
+	rbdr->tail = 0;
 
 	nic->rb_page = NULL;
 	for (idx = 0; idx < ring_len; idx++) {
 		err = nicvf_alloc_rcv_buffer(nic, GFP_KERNEL, RCV_FRAG_LEN,
 					     &rbuf);
-		if (err)
+		if (err) {
+			/* To free already allocated and mapped ones */
+			rbdr->tail = idx - 1;
 			return err;
+		}
 
 		desc = GET_RBDR_DESC(rbdr, idx);
-		desc->buf_addr = virt_to_phys(rbuf) >> NICVF_RCV_BUF_ALIGN;
+		desc->buf_addr = (u64)rbuf >> NICVF_RCV_BUF_ALIGN;
 	}
 
 	nicvf_get_page(nic);
···
 static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
 {
 	int head, tail;
-	u64 buf_addr;
+	u64 buf_addr, phys_addr;
 	struct rbdr_entry_t *desc;
 
 	if (!rbdr)
···
 	head = rbdr->head;
 	tail = rbdr->tail;
 
-	/* Free SKBs */
+	/* Release page references */
 	while (head != tail) {
 		desc = GET_RBDR_DESC(rbdr, head);
-		buf_addr = desc->buf_addr << NICVF_RCV_BUF_ALIGN;
-		put_page(virt_to_page(phys_to_virt(buf_addr)));
+		buf_addr = ((u64)desc->buf_addr) << NICVF_RCV_BUF_ALIGN;
+		phys_addr = nicvf_iova_to_phys(nic, buf_addr);
+		dma_unmap_page_attrs(&nic->pdev->dev, buf_addr, RCV_FRAG_LEN,
+				     DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+		if (phys_addr)
+			put_page(virt_to_page(phys_to_virt(phys_addr)));
 		head++;
 		head &= (rbdr->dmem.q_len - 1);
 	}
-	/* Free SKB of tail desc */
+	/* Release buffer of tail desc */
 	desc = GET_RBDR_DESC(rbdr, tail);
-	buf_addr = desc->buf_addr << NICVF_RCV_BUF_ALIGN;
-	put_page(virt_to_page(phys_to_virt(buf_addr)));
+	buf_addr = ((u64)desc->buf_addr) << NICVF_RCV_BUF_ALIGN;
+	phys_addr = nicvf_iova_to_phys(nic, buf_addr);
+	dma_unmap_page_attrs(&nic->pdev->dev, buf_addr, RCV_FRAG_LEN,
+			     DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+	if (phys_addr)
+		put_page(virt_to_page(phys_to_virt(phys_addr)));
 
 	/* Free RBDR ring */
 	nicvf_free_q_desc_mem(nic, &rbdr->dmem);
···
 			break;
 
 		desc = GET_RBDR_DESC(rbdr, tail);
-		desc->buf_addr = virt_to_phys(rbuf) >> NICVF_RCV_BUF_ALIGN;
+		desc->buf_addr = (u64)rbuf >> NICVF_RCV_BUF_ALIGN;
 		refill_rb_cnt--;
 		new_rb++;
 	}
···
 	return 0;
 }
 
+void nicvf_unmap_sndq_buffers(struct nicvf *nic, struct snd_queue *sq,
+			      int hdr_sqe, u8 subdesc_cnt)
+{
+	u8 idx;
+	struct sq_gather_subdesc *gather;
+
+	/* Unmap DMA mapped skb data buffers */
+	for (idx = 0; idx < subdesc_cnt; idx++) {
+		hdr_sqe++;
+		hdr_sqe &= (sq->dmem.q_len - 1);
+		gather = (struct sq_gather_subdesc *)GET_SQ_DESC(sq, hdr_sqe);
+		/* HW will ensure data coherency, CPU sync not required */
+		dma_unmap_page_attrs(&nic->pdev->dev, gather->addr,
+				     gather->size, DMA_TO_DEVICE,
+				     DMA_ATTR_SKIP_CPU_SYNC);
+	}
+}
+
 static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 {
 	struct sk_buff *skb;
+	struct sq_hdr_subdesc *hdr;
+	struct sq_hdr_subdesc *tso_sqe;
 
 	if (!sq)
 		return;
···
 	smp_rmb();
 	while (sq->head != sq->tail) {
 		skb = (struct sk_buff *)sq->skbuff[sq->head];
-		if (skb)
-			dev_kfree_skb_any(skb);
+		if (!skb)
+			goto next;
+		hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, sq->head);
+		/* Check for dummy descriptor used for HW TSO offload on 88xx */
+		if (hdr->dont_send) {
+			/* Get actual TSO descriptors and unmap them */
+			tso_sqe =
+			 (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, hdr->rsvd2);
+			nicvf_unmap_sndq_buffers(nic, sq, hdr->rsvd2,
+						 tso_sqe->subdesc_cnt);
+		} else {
+			nicvf_unmap_sndq_buffers(nic, sq, sq->head,
+						 hdr->subdesc_cnt);
+		}
+		dev_kfree_skb_any(skb);
+next:
 		sq->head++;
 		sq->head &= (sq->dmem.q_len - 1);
 	}
···
 	nicvf_send_msg_to_pf(nic, &mbx);
 
 	if (!nic->sqs_mode && (qidx == 0)) {
-		/* Enable checking L3/L4 length and TCP/UDP checksums */
+		/* Enable checking L3/L4 length and TCP/UDP checksums
+		 * Also allow IPv6 pkts with zero UDP checksum.
+		 */
 		nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0,
-				      (BIT(24) | BIT(23) | BIT(21)));
+				      (BIT(24) | BIT(23) | BIT(21) | BIT(20)));
 		nicvf_config_vlan_stripping(nic, nic->netdev->features);
 	}
 
···
 	sq->tail &= (sq->dmem.q_len - 1);
 
 	return qentry;
+}
+
+/* Rollback to previous tail pointer when descriptors not used */
+static inline void nicvf_rollback_sq_desc(struct snd_queue *sq,
+					  int qentry, int desc_cnt)
+{
+	sq->tail = qentry;
+	atomic_add(desc_cnt, &sq->free_cnt);
 }
 
 /* Free descriptor back to SQ for future use */
···
 			struct sk_buff *skb, u8 sq_num)
 {
 	int i, size;
-	int subdesc_cnt, tso_sqe = 0;
+	int subdesc_cnt, hdr_sqe = 0;
 	int qentry;
+	u64 dma_addr;
 
 	subdesc_cnt = nicvf_sq_subdesc_required(nic, skb);
 	if (subdesc_cnt > atomic_read(&sq->free_cnt))
···
 	/* Add SQ header subdesc */
 	nicvf_sq_add_hdr_subdesc(nic, sq, qentry, subdesc_cnt - 1,
 				 skb, skb->len);
-	tso_sqe = qentry;
+	hdr_sqe = qentry;
 
 	/* Add SQ gather subdescs */
 	qentry = nicvf_get_nxt_sqentry(sq, qentry);
 	size = skb_is_nonlinear(skb) ? skb_headlen(skb) : skb->len;
-	nicvf_sq_add_gather_subdesc(sq, qentry, size, virt_to_phys(skb->data));
+	/* HW will ensure data coherency, CPU sync not required */
+	dma_addr = dma_map_page_attrs(&nic->pdev->dev, virt_to_page(skb->data),
+				      offset_in_page(skb->data), size,
+				      DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+	if (dma_mapping_error(&nic->pdev->dev, dma_addr)) {
+		nicvf_rollback_sq_desc(sq, qentry, subdesc_cnt);
+		return 0;
+	}
+
+	nicvf_sq_add_gather_subdesc(sq, qentry, size, dma_addr);
 
 	/* Check for scattered buffer */
 	if (!skb_is_nonlinear(skb))
···
 
 		qentry = nicvf_get_nxt_sqentry(sq, qentry);
 		size = skb_frag_size(frag);
-		nicvf_sq_add_gather_subdesc(sq, qentry, size,
-					    virt_to_phys(
-					    skb_frag_address(frag)));
+		dma_addr = dma_map_page_attrs(&nic->pdev->dev,
+					      skb_frag_page(frag),
+					      frag->page_offset, size,
+					      DMA_TO_DEVICE,
+					      DMA_ATTR_SKIP_CPU_SYNC);
+		if (dma_mapping_error(&nic->pdev->dev, dma_addr)) {
+			/* Free entire chain of mapped buffers
+			 * here 'i' = frags mapped + above mapped skb->data
+			 */
+			nicvf_unmap_sndq_buffers(nic, sq, hdr_sqe, i);
+			nicvf_rollback_sq_desc(sq, qentry, subdesc_cnt);
+			return 0;
+		}
+		nicvf_sq_add_gather_subdesc(sq, qentry, size, dma_addr);
 	}
 
 doorbell:
 	if (nic->t88 && skb_shinfo(skb)->gso_size) {
 		qentry = nicvf_get_nxt_sqentry(sq, qentry);
-		nicvf_sq_add_cqe_subdesc(sq, qentry, tso_sqe, skb);
+		nicvf_sq_add_cqe_subdesc(sq, qentry, hdr_sqe, skb);
 	}
 
 	nicvf_sq_doorbell(nic, skb, sq_num, subdesc_cnt);
···
 	int offset;
 	u16 *rb_lens = NULL;
 	u64 *rb_ptrs = NULL;
+	u64 phys_addr;
 
 	rb_lens = (void *)cqe_rx + (3 * sizeof(u64));
 	/* Except 88xx pass1 on all other chips CQE_RX2_S is added to
···
 	else
 		rb_ptrs = (void *)cqe_rx + (7 * sizeof(u64));
 
-	netdev_dbg(nic->netdev, "%s rb_cnt %d rb0_ptr %llx rb0_sz %d\n",
-		   __func__, cqe_rx->rb_cnt, cqe_rx->rb0_ptr, cqe_rx->rb0_sz);
-
 	for (frag = 0; frag < cqe_rx->rb_cnt; frag++) {
 		payload_len = rb_lens[frag_num(frag)];
+		phys_addr = nicvf_iova_to_phys(nic, *rb_ptrs);
+		if (!phys_addr) {
+			if (skb)
+				dev_kfree_skb_any(skb);
+			return NULL;
+		}
+
 		if (!frag) {
 			/* First fragment */
+			dma_unmap_page_attrs(&nic->pdev->dev,
+					     *rb_ptrs - cqe_rx->align_pad,
+					     RCV_FRAG_LEN, DMA_FROM_DEVICE,
+					     DMA_ATTR_SKIP_CPU_SYNC);
 			skb = nicvf_rb_ptr_to_skb(nic,
-						  *rb_ptrs - cqe_rx->align_pad,
+						  phys_addr - cqe_rx->align_pad,
 						  payload_len);
 			if (!skb)
 				return NULL;
···
 			skb_put(skb, payload_len);
 		} else {
 			/* Add fragments */
-			page = virt_to_page(phys_to_virt(*rb_ptrs));
-			offset = phys_to_virt(*rb_ptrs) - page_address(page);
+			dma_unmap_page_attrs(&nic->pdev->dev, *rb_ptrs,
+					     RCV_FRAG_LEN, DMA_FROM_DEVICE,
+					     DMA_ATTR_SKIP_CPU_SYNC);
+			page = virt_to_page(phys_to_virt(phys_addr));
+			offset = phys_to_virt(phys_addr) - page_address(page);
 			skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
 					offset, payload_len, RCV_FRAG_LEN);
 		}

drivers/net/ethernet/cavium/thunder/nicvf_queues.h

···
 #define RCV_BUF_COUNT		(1ULL << (RBDR_SIZE + 13))
 #define MAX_RCV_BUF_COUNT	(1ULL << (RBDR_SIZE6 + 13))
 #define RBDR_THRESH		(RCV_BUF_COUNT / 2)
-#define DMA_BUFFER_LEN		2048 /* In multiples of 128bytes */
+#define DMA_BUFFER_LEN		1536 /* In multiples of 128bytes */
 #define RCV_FRAG_LEN	 (SKB_DATA_ALIGN(DMA_BUFFER_LEN + NET_SKB_PAD) + \
 			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 
···
 
 #define	CQ_ERR_MASK	(CQ_WR_FULL | CQ_WR_DISABLE | CQ_WR_FAULT)
 
+void nicvf_unmap_sndq_buffers(struct nicvf *nic, struct snd_queue *sq,
+			      int hdr_sqe, u8 subdesc_cnt);
 void nicvf_config_vlan_stripping(struct nicvf *nic,
 				 netdev_features_t features);
 int nicvf_set_qset_resources(struct nicvf *nic);

drivers/net/ethernet/cavium/thunder/thunder_bgx.c

···
 	return 1;
 }
 
+static int max_bgx_per_node;
+static void set_max_bgx_per_node(struct pci_dev *pdev)
+{
+	u16 sdevid;
+
+	if (max_bgx_per_node)
+		return;
+
+	pci_read_config_word(pdev, PCI_SUBSYSTEM_ID, &sdevid);
+	switch (sdevid) {
+	case PCI_SUBSYS_DEVID_81XX_BGX:
+		max_bgx_per_node = MAX_BGX_PER_CN81XX;
+		break;
+	case PCI_SUBSYS_DEVID_83XX_BGX:
+		max_bgx_per_node = MAX_BGX_PER_CN83XX;
+		break;
+	case PCI_SUBSYS_DEVID_88XX_BGX:
+	default:
+		max_bgx_per_node = MAX_BGX_PER_CN88XX;
+		break;
+	}
+}
+
+static struct bgx *get_bgx(int node, int bgx_idx)
+{
+	int idx = (node * max_bgx_per_node) + bgx_idx;
+
+	return bgx_vnic[idx];
+}
+
 /* Return number of BGX present in HW */
 unsigned bgx_get_map(int node)
 {
 	int i;
 	unsigned map = 0;
 
-	for (i = 0; i < MAX_BGX_PER_NODE; i++) {
-		if (bgx_vnic[(node * MAX_BGX_PER_NODE) + i])
+	for (i = 0; i < max_bgx_per_node; i++) {
+		if (bgx_vnic[(node * max_bgx_per_node) + i])
 			map |= (1 << i);
 	}
 
···
 {
 	struct bgx *bgx;
 
-	bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	bgx = get_bgx(node, bgx_idx);
 	if (bgx)
 		return bgx->lmac_count;
 
···
 	struct bgx *bgx;
 	struct lmac *lmac;
 
-	bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	bgx = get_bgx(node, bgx_idx);
 	if (!bgx)
 		return;
 
···
 
 const u8 *bgx_get_lmac_mac(int node, int bgx_idx, int lmacid)
 {
-	struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	struct bgx *bgx = get_bgx(node, bgx_idx);
 
 	if (bgx)
 		return bgx->lmac[lmacid].mac;
···
 
 void bgx_set_lmac_mac(int node, int bgx_idx, int lmacid, const u8 *mac)
 {
-	struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	struct bgx *bgx = get_bgx(node, bgx_idx);
 
 	if (!bgx)
 		return;
···
 
 void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable)
 {
-	struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	struct bgx *bgx = get_bgx(node, bgx_idx);
 	struct lmac *lmac;
 	u64 cfg;
 
···
 void bgx_lmac_get_pfc(int node, int bgx_idx, int lmacid, void *pause)
 {
 	struct pfc *pfc = (struct pfc *)pause;
-	struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+	struct bgx *bgx = get_bgx(node, bgx_idx);
 	struct lmac *lmac;
 	u64 cfg;
 
···
 void bgx_lmac_set_pfc(int node, int bgx_idx, int lmacid, void *pause)
 {
 	struct pfc *pfc = (struct pfc *)pause;
-	struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+	struct bgx *bgx = get_bgx(node, bgx_idx);
 	struct lmac *lmac;
 	u64 cfg;
 
···
 {
 	struct bgx *bgx;
 
-	bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	bgx = get_bgx(node, bgx_idx);
 	if (!bgx)
 		return 0;
 
···
 {
 	struct bgx *bgx;
 
-	bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	bgx = get_bgx(node, bgx_idx);
 	if (!bgx)
 		return 0;
 
···
 	struct lmac *lmac;
 	u64    cfg;
 
-	bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+	bgx = get_bgx(node, bgx_idx);
 	if (!bgx)
 		return;
 
···
 			dev_info(dev, "%s: 40G_KR4\n", (char *)str);
 		break;
 	case BGX_MODE_QSGMII:
-		if ((lmacid == 0) &&
-		    (bgx_get_lane2sds_cfg(bgx, lmac) != lmacid))
-			return;
-		if ((lmacid == 2) &&
-		    (bgx_get_lane2sds_cfg(bgx, lmac) == lmacid))
-			return;
 		dev_info(dev, "%s: QSGMII\n", (char *)str);
 		break;
 	case BGX_MODE_RGMII:
···
 		goto err_release_regions;
 	}
 
+	set_max_bgx_per_node(pdev);
+
 	pci_read_config_word(pdev, PCI_DEVICE_ID, &sdevid);
 	if (sdevid != PCI_DEVICE_ID_THUNDER_RGX) {
 		bgx->bgx_id = (pci_resource_start(pdev,
 			PCI_CFG_REG_BAR_NUM) >> 24) & BGX_ID_MASK;
-		bgx->bgx_id += nic_get_node_id(pdev) * MAX_BGX_PER_NODE;
+		bgx->bgx_id += nic_get_node_id(pdev) * max_bgx_per_node;
 		bgx->max_lmac = MAX_LMAC_PER_BGX;
 		bgx_vnic[bgx->bgx_id] = bgx;
 	} else {

drivers/net/ethernet/cavium/thunder/thunder_bgx.h

···
 #define    MAX_BGX_PER_CN88XX			2
 #define    MAX_BGX_PER_CN81XX			3 /* 2 BGXs + 1 RGX */
 #define    MAX_BGX_PER_CN83XX			4
-#define    MAX_BGX_PER_NODE			4
 #define    MAX_LMAC_PER_BGX			4
 #define    MAX_BGX_CHANS_PER_LMAC		16
 #define    MAX_DMAC_PER_LMAC			8

drivers/net/ethernet/ibm/emac/core.c

···
 static int emac_dt_phy_connect(struct emac_instance *dev,
 			       struct device_node *phy_handle)
 {
-	int res;
-
 	dev->phy.def = devm_kzalloc(&dev->ofdev->dev, sizeof(*dev->phy.def),
 				    GFP_KERNEL);
 	if (!dev->phy.def)
···
 {
 	struct device_node *np = dev->ofdev->dev.of_node;
 	struct device_node *phy_handle;
-	int res = 0;
+	int res = 1;
 
 	phy_handle = of_parse_phandle(np, "phy-handle", 0);
 
···
 	if (emac_has_feature(dev, EMAC_FTR_HAS_RGMII)) {
 		int res = emac_dt_phy_probe(dev);
 
-		mutex_unlock(&emac_phy_map_lock);
-		if (!res)
+		switch (res) {
+		case 1:
+			/* No phy-handle property configured.
+			 * Continue with the existing phy probe
+			 * and setup code.
+			 */
+			break;
+
+		case 0:
+			mutex_unlock(&emac_phy_map_lock);
 			goto init_phy;
 
-		dev_err(&dev->ofdev->dev, "failed to attach dt phy (%d).\n",
-			res);
-		return res;
+		default:
+			mutex_unlock(&emac_phy_map_lock);
+			dev_err(&dev->ofdev->dev, "failed to attach dt phy (%d).\n",
+				res);
+			return res;
+		}
 	}
 
 	if (dev->phy_address != 0xffffffff)

drivers/net/ethernet/ibm/ibmvnic.c

···
 	send_map_query(adapter);
 	for (i = 0; i < rxadd_subcrqs; i++) {
 		init_rx_pool(adapter, &adapter->rx_pool[i],
-			     IBMVNIC_BUFFS_PER_POOL, i,
+			     adapter->req_rx_add_entries_per_subcrq, i,
 			     be64_to_cpu(size_array[i]), 1);
 		if (alloc_rx_pool(adapter, &adapter->rx_pool[i])) {
 			dev_err(dev, "Couldn't alloc rx pool\n");
···
 	for (i = 0; i < tx_subcrqs; i++) {
 		tx_pool = &adapter->tx_pool[i];
 		tx_pool->tx_buff =
-		    kcalloc(adapter->max_tx_entries_per_subcrq,
+		    kcalloc(adapter->req_tx_entries_per_subcrq,
 			    sizeof(struct ibmvnic_tx_buff), GFP_KERNEL);
 		if (!tx_pool->tx_buff)
 			goto tx_pool_alloc_failed;
 
 		if (alloc_long_term_buff(adapter, &tx_pool->long_term_buff,
-					 adapter->max_tx_entries_per_subcrq *
+					 adapter->req_tx_entries_per_subcrq *
 					 adapter->req_mtu))
 			goto tx_ltb_alloc_failed;
 
 		tx_pool->free_map =
-		    kcalloc(adapter->max_tx_entries_per_subcrq,
+		    kcalloc(adapter->req_tx_entries_per_subcrq,
 			    sizeof(int), GFP_KERNEL);
 		if (!tx_pool->free_map)
 			goto tx_fm_alloc_failed;
 
-		for (j = 0; j < adapter->max_tx_entries_per_subcrq; j++)
+		for (j = 0; j < adapter->req_tx_entries_per_subcrq; j++)
 			tx_pool->free_map[j] = j;
 
 		tx_pool->consumer_index = 0;
···
 	u8 *hdrs = (u8 *)&adapter->tx_rx_desc_req;
 	struct device *dev = &adapter->vdev->dev;
 	struct ibmvnic_tx_buff *tx_buff = NULL;
+	struct ibmvnic_sub_crq_queue *tx_scrq;
 	struct ibmvnic_tx_pool *tx_pool;
 	unsigned int tx_send_failed = 0;
 	unsigned int tx_map_failed = 0;
···
 	int ret = 0;
 
 	tx_pool = &adapter->tx_pool[queue_num];
+	tx_scrq = adapter->tx_scrq[queue_num];
 	txq = netdev_get_tx_queue(netdev, skb_get_queue_mapping(skb));
 	handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
 				   be32_to_cpu(adapter->login_rsp_buf->
···
 
 	tx_pool->consumer_index =
 	    (tx_pool->consumer_index + 1) %
-		adapter->max_tx_entries_per_subcrq;
+		adapter->req_tx_entries_per_subcrq;
 
 	tx_buff = &tx_pool->tx_buff[index];
 	tx_buff->skb = skb;
···
 
 		if (tx_pool->consumer_index == 0)
 			tx_pool->consumer_index =
-				adapter->max_tx_entries_per_subcrq - 1;
+				adapter->req_tx_entries_per_subcrq - 1;
 		else
 			tx_pool->consumer_index--;
 
···
 		ret = NETDEV_TX_BUSY;
 		goto out;
 	}
+
+	atomic_inc(&tx_scrq->used);
+
+	if (atomic_read(&tx_scrq->used) >= adapter->req_tx_entries_per_subcrq) {
+		netdev_info(netdev, "Stopping queue %d\n", queue_num);
+		netif_stop_subqueue(netdev, queue_num);
+	}
+
 	tx_packets++;
 	tx_bytes += skb->len;
 	txq->trans_start = jiffies;
···
 	scrq->adapter = adapter;
 	scrq->size = 4 * PAGE_SIZE / sizeof(*scrq->msgs);
 	scrq->cur = 0;
+	atomic_set(&scrq->used, 0);
 	scrq->rx_skb_top = NULL;
 	spin_lock_init(&scrq->lock);
 
···
 						 DMA_TO_DEVICE);
 			}
 
-			if (txbuff->last_frag)
+			if (txbuff->last_frag) {
+				atomic_dec(&scrq->used);
+
+				if (atomic_read(&scrq->used) <=
+				    (adapter->req_tx_entries_per_subcrq / 2) &&
+				    netif_subqueue_stopped(adapter->netdev,
+							   txbuff->skb)) {
+					netif_wake_subqueue(adapter->netdev,
+							    scrq->pool_index);
+					netdev_dbg(adapter->netdev,
+						   "Started queue %d\n",
+						   scrq->pool_index);
+				}
+
 				dev_kfree_skb_any(txbuff->skb);
+			}
 
 			adapter->tx_pool[pool].free_map[adapter->tx_pool[pool].
 						     producer_index] = index;
 			adapter->tx_pool[pool].producer_index =
 			    (adapter->tx_pool[pool].producer_index + 1) %
-			    adapter->max_tx_entries_per_subcrq;
+			    adapter->req_tx_entries_per_subcrq;
 		}
 		/* remove tx_comp scrq*/
 		next->tx_comp.first = 0;

drivers/net/ethernet/ibm/ibmvnic.h

···
 	spinlock_t lock;
 	struct sk_buff *rx_skb_top;
 	struct ibmvnic_adapter *adapter;
+	atomic_t used;
 };
 
 struct ibmvnic_long_term_buff {

drivers/net/ethernet/mellanox/mlx5/core/Kconfig

···
 config MLX5_CORE_EN
 	bool "Mellanox Technologies ConnectX-4 Ethernet support"
 	depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE
+	depends on IPV6=y || IPV6=n || MLX5_CORE=m
 	imply PTP_1588_CLOCK
 	default n
 	---help---

drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c

···
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_dcbx *dcbx = &priv->dcbx;
 
+	if (mode & DCB_CAP_DCBX_LLD_MANAGED)
+		return 1;
+
 	if ((!mode) && MLX5_CAP_GEN(priv->mdev, dcbx)) {
 		if (dcbx->mode == MLX5E_DCBX_PARAM_VER_OPER_AUTO)
 			return 0;
···
 		return 1;
 	}
 
-	if (mlx5e_dcbnl_switch_to_host_mode(netdev_priv(dev)))
+	if (!(mode & DCB_CAP_DCBX_HOST))
 		return 1;
 
-	if ((mode & DCB_CAP_DCBX_LLD_MANAGED) ||
-	    !(mode & DCB_CAP_DCBX_VER_CEE) ||
-	    !(mode & DCB_CAP_DCBX_VER_IEEE) ||
-	    !(mode & DCB_CAP_DCBX_HOST))
+	if (mlx5e_dcbnl_switch_to_host_mode(netdev_priv(dev)))
 		return 1;
 
 	return 0;

drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c

···
 	struct iphdr *iph;
 
 	/* We are only going to peek, no need to clone the SKB */
-	if (skb->protocol != htons(ETH_P_IP))
-		goto out;
-
 	if (MLX5E_TEST_PKT_SIZE - ETH_HLEN > skb_headlen(skb))
 		goto out;
 
···
 	lbtp->loopback_ok = false;
 	init_completion(&lbtp->comp);
 
-	lbtp->pt.type = htons(ETH_P_ALL);
+	lbtp->pt.type = htons(ETH_P_IP);
 	lbtp->pt.func = mlx5e_test_loopback_validate;
 	lbtp->pt.dev = priv->netdev;
 	lbtp->pt.af_packet_priv = lbtp;

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

···
 #include "eswitch.h"
 #include "vxlan.h"
 
+enum {
+	MLX5E_TC_FLOW_ESWITCH	= BIT(0),
+};
+
 struct mlx5e_tc_flow {
 	struct rhash_head	node;
 	u64			cookie;
+	u8			flags;
 	struct mlx5_flow_handle *rule;
 	struct list_head	encap; /* flows sharing the same encap */
 	struct mlx5_esw_flow_attr *attr;
···
 		mlx5_fc_destroy(priv->mdev, counter);
 	}
 
-	if (esw && esw->mode == SRIOV_OFFLOADS) {
+	if (flow->flags & MLX5E_TC_FLOW_ESWITCH) {
 		mlx5_eswitch_del_vlan_action(esw, flow->attr);
 		if (flow->attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
 			mlx5e_detach_encap(priv, flow);
···
 }
 
 static int parse_cls_flower(struct mlx5e_priv *priv,
+			    struct mlx5e_tc_flow *flow,
 			    struct mlx5_flow_spec *spec,
 			    struct tc_cls_flower_offload *f)
 {
···
 
 	err = __parse_cls_flower(priv, spec, f, &min_inline);
 
-	if (!err && esw->mode == SRIOV_OFFLOADS &&
+	if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH) &&
 	    rep->vport != FDB_UPLINK_VPORT) {
 		if (min_inline > esw->offloads.inline_mode) {
 			netdev_warn(priv->netdev,
···
 			   struct tc_cls_flower_offload *f)
 {
 	struct mlx5e_tc_table *tc = &priv->fs.tc;
-	int err = 0;
-	bool fdb_flow = false;
+	int err, attr_size = 0;
 	u32 flow_tag, action;
 	struct mlx5e_tc_flow *flow;
 	struct mlx5_flow_spec *spec;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	u8 flow_flags = 0;
 
-	if (esw && esw->mode == SRIOV_OFFLOADS)
-		fdb_flow = true;
+	if (esw && esw->mode == SRIOV_OFFLOADS) {
+		flow_flags = MLX5E_TC_FLOW_ESWITCH;
+		attr_size  = sizeof(struct mlx5_esw_flow_attr);
+	}
 
-	if (fdb_flow)
-		flow = kzalloc(sizeof(*flow) +
-			       sizeof(struct mlx5_esw_flow_attr),
-			       GFP_KERNEL);
-	else
-		flow = kzalloc(sizeof(*flow), GFP_KERNEL);
-
+	flow = kzalloc(sizeof(*flow) + attr_size, GFP_KERNEL);
 	spec = mlx5_vzalloc(sizeof(*spec));
 	if (!spec || !flow) {
 		err = -ENOMEM;
···
 	}
 
 	flow->cookie = f->cookie;
+	flow->flags = flow_flags;
 
-	err = parse_cls_flower(priv, spec, f);
+	err = parse_cls_flower(priv, flow, spec, f);
 	if (err < 0)
 		goto err_free;
 
-	if (fdb_flow) {
+	if (flow->flags & MLX5E_TC_FLOW_ESWITCH) {
 		flow->attr  = (struct mlx5_esw_flow_attr *)(flow + 1);
 		err = parse_tc_fdb_actions(priv, f->exts, flow);
 		if (err < 0)

drivers/net/ethernet/mellanox/mlx5/core/fs_core.c

···
 						u32 *match_criteria)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct list_head *prev = ft->node.children.prev;
+	struct list_head *prev = &ft->node.children;
 	unsigned int candidate_index = 0;
 	struct mlx5_flow_group *fg;
 	void *match_criteria_addr;

drivers/net/ethernet/mellanox/mlx5/core/main.c

···
 	if (err)
 		goto clean_load;
 
+	pci_save_state(pdev);
 	return 0;
 
 clean_load:
···
 
 	mlx5_enter_error_state(dev);
 	mlx5_unload_one(dev, priv, false);
-	/* In case of kernel call save the pci state and drain the health wq */
+	/* In case of kernel call drain the health wq */
 	if (state) {
-		pci_save_state(pdev);
 		mlx5_drain_health_wq(dev);
 		mlx5_pci_disable_device(dev);
 	}
···
 
 	pci_set_master(pdev);
 	pci_restore_state(pdev);
+	pci_save_state(pdev);
 
 	if (wait_vital(pdev)) {
 		dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);

drivers/net/ethernet/mellanox/mlxsw/reg.h

···
 #define MLXSW_REG_SPVM_ID 0x200F
 #define MLXSW_REG_SPVM_BASE_LEN 0x04 /* base length, without records */
 #define MLXSW_REG_SPVM_REC_LEN 0x04 /* record length */
-#define MLXSW_REG_SPVM_REC_MAX_COUNT 256
+#define MLXSW_REG_SPVM_REC_MAX_COUNT 255
 #define MLXSW_REG_SPVM_LEN (MLXSW_REG_SPVM_BASE_LEN +	\
 		    MLXSW_REG_SPVM_REC_LEN * MLXSW_REG_SPVM_REC_MAX_COUNT)
 
···
 #define MLXSW_REG_SPVMLR_ID 0x2020
 #define MLXSW_REG_SPVMLR_BASE_LEN 0x04 /* base length, without records */
 #define MLXSW_REG_SPVMLR_REC_LEN 0x04 /* record length */
-#define MLXSW_REG_SPVMLR_REC_MAX_COUNT 256
+#define MLXSW_REG_SPVMLR_REC_MAX_COUNT 255
 #define MLXSW_REG_SPVMLR_LEN (MLXSW_REG_SPVMLR_BASE_LEN + \
 			      MLXSW_REG_SPVMLR_REC_LEN * \
 			      MLXSW_REG_SPVMLR_REC_MAX_COUNT)

drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c

···
 	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, mlxsw_sp_port->dev,
 					   ingress,
 					   MLXSW_SP_ACL_PROFILE_FLOWER);
-	if (WARN_ON(IS_ERR(ruleset)))
+	if (IS_ERR(ruleset))
 		return;
 
 	rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie);
-	if (!WARN_ON(!rule)) {
+	if (rule) {
 		mlxsw_sp_acl_rule_del(mlxsw_sp, rule);
 		mlxsw_sp_acl_rule_destroy(mlxsw_sp, rule);
 	}

drivers/net/ethernet/qlogic/qed/qed_cxt.c

···
 		u32 page_sz = p_mgr->clients[ILT_CLI_CDUC].p_size.val;
 		u32 cxt_size = CONN_CXT_SIZE(p_hwfn);
 		u32 elems_per_page = ILT_PAGE_IN_BYTES(page_sz) / cxt_size;
+		u32 align = elems_per_page * DQ_RANGE_ALIGN;
 
-		p_conn->cid_count = roundup(p_conn->cid_count, elems_per_page);
+		p_conn->cid_count = roundup(p_conn->cid_count, align);
 	}
 }
 

drivers/net/ethernet/qlogic/qed/qed_dev.c

···
 	 * size/capacity fields are of a u32 type.
 	 */
 	if ((cnt_type == QED_CHAIN_CNT_TYPE_U16 &&
-	     chain_size > 0x10000) ||
-	    (cnt_type == QED_CHAIN_CNT_TYPE_U32 &&
-	     chain_size > 0x100000000ULL)) {
+	     chain_size > ((u32)U16_MAX + 1)) ||
+	    (cnt_type == QED_CHAIN_CNT_TYPE_U32 && chain_size > U32_MAX)) {
 		DP_NOTICE(cdev,
 			  "The actual chain size (0x%llx) is larger than the maximal possible value\n",
 			  chain_size);

drivers/net/ethernet/qlogic/qed/qed_iscsi.c

···
 	p_init->num_sq_pages_in_ring = p_params->num_sq_pages_in_ring;
 	p_init->num_r2tq_pages_in_ring = p_params->num_r2tq_pages_in_ring;
 	p_init->num_uhq_pages_in_ring = p_params->num_uhq_pages_in_ring;
+	p_init->ooo_enable = p_params->ooo_enable;
+	p_init->ll2_rx_queue_id = p_hwfn->hw_info.resc_start[QED_LL2_QUEUE] +
+				  p_params->ll2_ooo_queue_id;
 	p_init->func_params.log_page_size = p_params->log_page_size;
 	val = p_params->num_tasks;
 	p_init->func_params.num_tasks = cpu_to_le16(val);
···
 	spin_unlock_bh(&p_hwfn->p_iscsi_info->lock);
 }
 
+void qed_iscsi_free_connection(struct qed_hwfn *p_hwfn,
+			       struct qed_iscsi_conn *p_conn)
+{
+	qed_chain_free(p_hwfn->cdev, &p_conn->xhq);
+	qed_chain_free(p_hwfn->cdev, &p_conn->uhq);
+	qed_chain_free(p_hwfn->cdev, &p_conn->r2tq);
+	dma_free_coherent(&p_hwfn->cdev->pdev->dev,
+			  sizeof(struct tcp_upload_params),
+			  p_conn->tcp_upload_params_virt_addr,
+			  p_conn->tcp_upload_params_phys_addr);
+	dma_free_coherent(&p_hwfn->cdev->pdev->dev,
+			  sizeof(struct scsi_terminate_extra_params),
+			  p_conn->queue_cnts_virt_addr,
+			  p_conn->queue_cnts_phys_addr);
+	kfree(p_conn);
+}
+
 struct qed_iscsi_info *qed_iscsi_alloc(struct qed_hwfn *p_hwfn)
 {
 	struct qed_iscsi_info *p_iscsi_info;
···
 void qed_iscsi_free(struct qed_hwfn *p_hwfn,
 		    struct qed_iscsi_info *p_iscsi_info)
 {
+	struct qed_iscsi_conn *p_conn = NULL;
+
+	while (!list_empty(&p_hwfn->p_iscsi_info->free_list)) {
+		p_conn = list_first_entry(&p_hwfn->p_iscsi_info->free_list,
+					  struct qed_iscsi_conn, list_entry);
+		if (p_conn) {
+			list_del(&p_conn->list_entry);
+			qed_iscsi_free_connection(p_hwfn, p_conn);
+		}
+	}
+
 	kfree(p_iscsi_info);
 }
 

drivers/net/ethernet/qlogic/qed/qed_ll2.c

···
 	/* If need to reuse or there's no replacement buffer, repost this */
 	if (rc)
 		goto out_post;
+	dma_unmap_single(&cdev->pdev->dev, buffer->phys_addr,
+			 cdev->ll2->rx_size, DMA_FROM_DEVICE);
 
 	skb = build_skb(buffer->data, 0);
 	if (!skb) {
···
 static int qed_ll2_rxq_completion_reg(struct qed_hwfn *p_hwfn,
 				      struct qed_ll2_info *p_ll2_conn,
 				      union core_rx_cqe_union *p_cqe,
-				      unsigned long lock_flags,
+				      unsigned long *p_lock_flags,
 				      bool b_last_cqe)
 {
 	struct qed_ll2_rx_queue *p_rx = &p_ll2_conn->rx_queue;
···
 			  "Mismatch between active_descq and the LL2 Rx chain\n");
 	list_add_tail(&p_pkt->list_entry, &p_rx->free_descq);
 
-	spin_unlock_irqrestore(&p_rx->lock, lock_flags);
+	spin_unlock_irqrestore(&p_rx->lock, *p_lock_flags);
 	qed_ll2b_complete_rx_packet(p_hwfn, p_ll2_conn->my_id,
 				    p_pkt, &p_cqe->rx_cqe_fp, b_last_cqe);
-	spin_lock_irqsave(&p_rx->lock, lock_flags);
+	spin_lock_irqsave(&p_rx->lock, *p_lock_flags);
 
 	return 0;
 }
···
 			break;
 		case CORE_RX_CQE_TYPE_REGULAR:
 			rc = qed_ll2_rxq_completion_reg(p_hwfn, p_ll2_conn,
-							cqe, flags, b_last_cqe);
+							cqe, &flags,
+							b_last_cqe);
 			break;
 		default:
 			rc = -EIO;
···
 {
 	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
 	u8 *handle = &hwfn->pf_params.iscsi_pf_params.ll2_ooo_queue_id;
-	struct qed_ll2_conn ll2_info;
+	struct qed_ll2_conn ll2_info = { 0 };
 	int rc;
 
 	ll2_info.conn_type = QED_LL2_TYPE_ISCSI_OOO;

drivers/net/ethernet/qlogic/qed/qed_ooo.c

···
 	if (!p_ooo_info->ooo_history.p_cqes)
 		goto no_history_mem;
 
+	p_ooo_info->ooo_history.num_of_cqes = QED_MAX_NUM_OOO_HISTORY_ENTRIES;
+
 	return p_ooo_info;
 
 no_history_mem:

drivers/net/ethernet/smsc/smc91x.c

···
  * Ethtool support
  */
 static int
-smc_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd)
+smc_ethtool_get_link_ksettings(struct net_device *dev,
+			       struct ethtool_link_ksettings *cmd)
 {
 	struct smc_local *lp = netdev_priv(dev);
 	int ret;
 
-	cmd->maxtxpkt = 1;
-	cmd->maxrxpkt = 1;
-
 	if (lp->phy_type != 0) {
 		spin_lock_irq(&lp->lock);
-		ret = mii_ethtool_gset(&lp->mii, cmd);
+		ret = mii_ethtool_get_link_ksettings(&lp->mii, cmd);
 		spin_unlock_irq(&lp->lock);
 	} else {
-		cmd->supported = SUPPORTED_10baseT_Half |
+		u32 supported = SUPPORTED_10baseT_Half |
 				 SUPPORTED_10baseT_Full |
 				 SUPPORTED_TP | SUPPORTED_AUI;
 
 		if (lp->ctl_rspeed == 10)
-			ethtool_cmd_speed_set(cmd, SPEED_10);
+			cmd->base.speed = SPEED_10;
 		else if (lp->ctl_rspeed == 100)
-			ethtool_cmd_speed_set(cmd, SPEED_100);
+			cmd->base.speed = SPEED_100;
 
-		cmd->autoneg = AUTONEG_DISABLE;
-		cmd->transceiver = XCVR_INTERNAL;
-		cmd->port = 0;
-		cmd->duplex = lp->tcr_cur_mode & TCR_SWFDUP ? DUPLEX_FULL : DUPLEX_HALF;
+		cmd->base.autoneg = AUTONEG_DISABLE;
+		cmd->base.port = 0;
+		cmd->base.duplex = lp->tcr_cur_mode & TCR_SWFDUP ?
+			DUPLEX_FULL : DUPLEX_HALF;
+
+		ethtool_convert_legacy_u32_to_link_mode(
+			cmd->link_modes.supported, supported);
 
 		ret = 0;
 	}
···
 }
 
 static int
-smc_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd)
+smc_ethtool_set_link_ksettings(struct net_device *dev,
+			       const struct ethtool_link_ksettings *cmd)
 {
 	struct smc_local *lp = netdev_priv(dev);
 	int ret;
 
 	if (lp->phy_type != 0) {
 		spin_lock_irq(&lp->lock);
-		ret = mii_ethtool_sset(&lp->mii, cmd);
+		ret = mii_ethtool_set_link_ksettings(&lp->mii, cmd);
 		spin_unlock_irq(&lp->lock);
 	} else {
-		if (cmd->autoneg != AUTONEG_DISABLE ||
-		    cmd->speed != SPEED_10 ||
-		    (cmd->duplex != DUPLEX_HALF && cmd->duplex != DUPLEX_FULL) ||
-		    (cmd->port != PORT_TP && cmd->port != PORT_AUI))
+		if (cmd->base.autoneg != AUTONEG_DISABLE ||
+		    cmd->base.speed != SPEED_10 ||
+		    (cmd->base.duplex != DUPLEX_HALF &&
+		     cmd->base.duplex != DUPLEX_FULL) ||
+		    (cmd->base.port != PORT_TP && cmd->base.port != PORT_AUI))
 			return -EINVAL;
 
-//		lp->port = cmd->port;
-		lp->ctl_rfduplx = cmd->duplex == DUPLEX_FULL;
+//		lp->port = cmd->base.port;
+		lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL;
 
 //		if (netif_running(dev))
 //			smc_set_port(dev);
···
 
 
 static const struct ethtool_ops smc_ethtool_ops = {
-	.get_settings	= smc_ethtool_getsettings,
-	.set_settings	= smc_ethtool_setsettings,
 	.get_drvinfo	= smc_ethtool_getdrvinfo,
 
 	.get_msglevel	= smc_ethtool_getmsglevel,
···
 	.get_eeprom_len = smc_ethtool_geteeprom_len,
 	.get_eeprom	= smc_ethtool_geteeprom,
 	.set_eeprom	= smc_ethtool_seteeprom,
+	.get_link_ksettings	= smc_ethtool_get_link_ksettings,
+	.set_link_ksettings	= smc_ethtool_set_link_ksettings,
 };
 
 static const struct net_device_ops smc_netdev_ops = {

drivers/net/hyperv/hyperv_net.h

···
 
 	u32 tx_checksum_mask;
 
+	u32 tx_send_table[VRSS_SEND_TAB_SIZE];
+
 	/* Ethtool settings */
 	u8 duplex;
 	u32 speed;
···
 
 	struct nvsp_message revoke_packet;
 
-	u32 send_table[VRSS_SEND_TAB_SIZE];
 	u32 max_chn;
 	u32 num_chn;
 	spinlock_t sc_lock; /* Protects num_sc_offered variable */

drivers/net/hyperv/netvsc.c

···
 static void netvsc_send_table(struct hv_device *hdev,
 			      struct nvsp_message *nvmsg)
 {
-	struct netvsc_device *nvscdev;
 	struct net_device *ndev = hv_get_drvdata(hdev);
+	struct net_device_context *net_device_ctx = netdev_priv(ndev);
 	int i;
 	u32 count, *tab;
-
-	nvscdev = get_outbound_net_device(hdev);
-	if (!nvscdev)
-		return;
 
 	count = nvmsg->msg.v5_msg.send_table.count;
 	if (count != VRSS_SEND_TAB_SIZE) {
···
 		      nvmsg->msg.v5_msg.send_table.offset);
 
 	for (i = 0; i < count; i++)
-		nvscdev->send_table[i] = tab[i];
+		net_device_ctx->tx_send_table[i] = tab[i];
 }
 
 static void netvsc_send_vf(struct net_device_context *net_device_ctx,

drivers/net/hyperv/netvsc_drv.c

···
 			void *accel_priv, select_queue_fallback_t fallback)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct netvsc_device *nvsc_dev = net_device_ctx->nvdev;
+	unsigned int num_tx_queues = ndev->real_num_tx_queues;
 	struct sock *sk = skb->sk;
 	int q_idx = sk_tx_queue_get(sk);
 
-	if (q_idx < 0 || skb->ooo_okay ||
-	    q_idx >= ndev->real_num_tx_queues) {
+	if (q_idx < 0 || skb->ooo_okay || q_idx >= num_tx_queues) {
 		u16 hash = __skb_tx_hash(ndev, skb, VRSS_SEND_TAB_SIZE);
 		int new_idx;
 
-		new_idx = nvsc_dev->send_table[hash]
-			% nvsc_dev->num_chn;
+		new_idx = net_device_ctx->tx_send_table[hash] % num_tx_queues;
 
 		if (q_idx != new_idx && sk &&
 		    sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache))
···
 
 		q_idx = new_idx;
 	}
-
-	if (unlikely(!nvsc_dev->chan_table[q_idx].channel))
-		q_idx = 0;
 
 	return q_idx;
 }

drivers/net/phy/marvell.c

···
 	return m88e1510_hwmon_probe(phydev);
 }
 
-static void marvell_remove(struct phy_device *phydev)
-{
-#ifdef CONFIG_HWMON
-
-	struct marvell_priv *priv = phydev->priv;
-
-	if (priv && priv->hwmon_dev)
-		hwmon_device_unregister(priv->hwmon_dev);
-#endif
-}
-
 static struct phy_driver marvell_drivers[] = {
 	{
 		.phy_id = MARVELL_PHY_ID_88E1101,
···
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = &m88e1121_probe,
-		.remove = &marvell_remove,
 		.config_init = &m88e1121_config_init,
 		.config_aneg = &m88e1121_config_aneg,
 		.read_status = &marvell_read_status,
···
 		.features = PHY_GBIT_FEATURES | SUPPORTED_FIBRE,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = &m88e1510_probe,
-		.remove = &marvell_remove,
 		.config_init = &m88e1510_config_init,
 		.config_aneg = &m88e1510_config_aneg,
 		.read_status = &marvell_read_status,
···
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = m88e1510_probe,
-		.remove = &marvell_remove,
 		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1510_config_aneg,
 		.read_status = &marvell_read_status,
···
 		.phy_id_mask = MARVELL_PHY_ID_MASK,
 		.name = "Marvell 88E1545",
 		.probe = m88e1510_probe,
-		.remove = &marvell_remove,
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.config_init = &marvell_config_init,

drivers/net/phy/phy_device.c

···
 	.phy_id		= 0xffffffff,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Generic PHY",
-	.soft_reset	= genphy_soft_reset,
+	.soft_reset	= genphy_no_soft_reset,
 	.config_init	= genphy_config_init,
 	.features	= PHY_GBIT_FEATURES | SUPPORTED_MII |
 			  SUPPORTED_AUI | SUPPORTED_FIBRE |

drivers/net/phy/spi_ks8995.c

···
 	if (err)
 		return err;
 
-	ks->regs_attr.size = ks->chip->regs_size;
 	memcpy(&ks->regs_attr, &ks8995_registers_attr, sizeof(ks->regs_attr));
+	ks->regs_attr.size = ks->chip->regs_size;
 
 	err = ks8995_reset(ks);
 	if (err)
 		return err;
 
+	sysfs_attr_init(&ks->regs_attr.attr);
 	err = sysfs_create_bin_file(&spi->dev.kobj, &ks->regs_attr);
 	if (err) {
 		dev_err(&spi->dev, "unable to create sysfs file, err=%d\n",

drivers/net/team/team.c

···
 static void team_setup(struct net_device *dev)
 {
 	ether_setup(dev);
+	dev->max_mtu = ETH_MAX_MTU;
 
 	dev->netdev_ops = &team_netdev_ops;
 	dev->ethtool_ops = &team_ethtool_ops;

drivers/net/tun.c

···
 /* Net device open. */
 static int tun_net_open(struct net_device *dev)
 {
+	struct tun_struct *tun = netdev_priv(dev);
+	int i;
+
 	netif_tx_start_all_queues(dev);
+
+	for (i = 0; i < tun->numqueues; i++) {
+		struct tun_file *tfile;
+
+		tfile = rtnl_dereference(tun->tfiles[i]);
+		tfile->socket.sk->sk_write_space(tfile->socket.sk);
+	}
+
 	return 0;
 }
 
···
 	if (!skb_array_empty(&tfile->tx_array))
 		mask |= POLLIN | POLLRDNORM;
 
-	if (sock_writeable(sk) ||
-	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
-	     sock_writeable(sk)))
+	if (tun->dev->flags & IFF_UP &&
+	    (sock_writeable(sk) ||
+	     (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+	      sock_writeable(sk))))
 		mask |= POLLOUT | POLLWRNORM;
 
 	if (tun->dev->reg_state != NETREG_REGISTERED)
···
 	int ret = 0;
 
 	pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
-	pr_info("%s\n", DRV_COPYRIGHT);
 
 	ret = rtnl_link_register(&tun_link_ops);
 	if (ret) {

drivers/net/vrf.c

···
 
 static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	int len = skb->len;
 	netdev_tx_t ret = is_ip_tx_frame(skb, dev);
 
 	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
···
 
 		u64_stats_update_begin(&dstats->syncp);
 		dstats->tx_pkts++;
-		dstats->tx_bytes += skb->len;
+		dstats->tx_bytes += len;
 		u64_stats_update_end(&dstats->syncp);
 	} else {
 		this_cpu_inc(dev->dstats->tx_drps);

drivers/net/vxlan.c

···
 	return 0;
 }
 
+static int __vxlan_dev_create(struct net *net, struct net_device *dev,
+			      struct vxlan_config *conf)
+{
+	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	int err;
+
+	err = vxlan_dev_configure(net, dev, conf, false);
+	if (err)
+		return err;
+
+	dev->ethtool_ops = &vxlan_ethtool_ops;
+
+	/* create an fdb entry for a valid default destination */
+	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
+		err = vxlan_fdb_create(vxlan, all_zeros_mac,
+				       &vxlan->default_dst.remote_ip,
+				       NUD_REACHABLE | NUD_PERMANENT,
+				       NLM_F_EXCL | NLM_F_CREATE,
+				       vxlan->cfg.dst_port,
+				       vxlan->default_dst.remote_vni,
+				       vxlan->default_dst.remote_vni,
+				       vxlan->default_dst.remote_ifindex,
+				       NTF_SELF);
+		if (err)
+			return err;
+	}
+
+	err = register_netdevice(dev);
+	if (err) {
+		vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni);
+		return err;
+	}
+
+	list_add(&vxlan->next, &vn->vxlan_list);
+	return 0;
+}
+
 static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
 			 struct net_device *dev, struct vxlan_config *conf,
 			 bool changelink)
···
 static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 			 struct nlattr *tb[], struct nlattr *data[])
 {
-	struct vxlan_net *vn = net_generic(src_net, vxlan_net_id);
-	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_config conf;
 	int err;
 
···
 	if (err)
 		return err;
 
-	err = vxlan_dev_configure(src_net, dev, &conf, false);
-	if (err)
-		return err;
-
-	dev->ethtool_ops = &vxlan_ethtool_ops;
-
-	/* create an fdb entry for a valid default destination */
-	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
-		err = vxlan_fdb_create(vxlan, all_zeros_mac,
-				       &vxlan->default_dst.remote_ip,
-				       NUD_REACHABLE | NUD_PERMANENT,
-				       NLM_F_EXCL | NLM_F_CREATE,
-				       vxlan->cfg.dst_port,
-				       vxlan->default_dst.remote_vni,
-				       vxlan->default_dst.remote_vni,
-				       vxlan->default_dst.remote_ifindex,
-				       NTF_SELF);
-		if (err)
-			return err;
-	}
-
-	err = register_netdevice(dev);
-	if (err) {
-		vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni);
-		return err;
-	}
-
-	list_add(&vxlan->next, &vn->vxlan_list);
-
-	return 0;
+	return __vxlan_dev_create(src_net, dev, &conf);
 }
 
 static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
···
 	if (IS_ERR(dev))
 		return dev;
 
-	err = vxlan_dev_configure(net, dev, conf, false);
+	err = __vxlan_dev_create(net, dev, conf);
 	if (err < 0) {
 		free_netdev(dev);
 		return ERR_PTR(err);

drivers/net/wan/fsl_ucc_hdlc.c

···
 	/* set bd status and length */
 	bd_status = (bd_status & T_W_S) | T_R_S | T_I_S | T_L_S | T_TC_S;
 
-	iowrite16be(bd_status, &bd->status);
 	iowrite16be(skb->len, &bd->length);
+	iowrite16be(bd_status, &bd->status);
 
 	/* Move to next BD in the ring */
 	if (!(bd_status & T_W_S))
···
 	struct sk_buff *skb;
 	hdlc_device *hdlc = dev_to_hdlc(dev);
 	struct qe_bd *bd;
-	u32 bd_status;
+	u16 bd_status;
 	u16 length, howmany = 0;
 	u8 *bdbuffer;
 	int i;

drivers/net/wimax/i2400m/usb.c

···
 	struct i2400mu *i2400mu;
 	struct usb_device *usb_dev = interface_to_usbdev(iface);
 
+	if (iface->cur_altsetting->desc.bNumEndpoints < 4)
+		return -ENODEV;
+
 	if (usb_dev->speed != USB_SPEED_HIGH)
 		dev_err(dev, "device not connected as high speed\n");
 

drivers/net/xen-netback/interface.c

···
 {
 	struct xenvif *vif = netdev_priv(dev);
 	struct xenvif_queue *queue = NULL;
-	unsigned int num_queues = vif->num_queues;
+	unsigned int num_queues;
 	u16 index;
 	struct xenvif_rx_cb *cb;
 
 	BUG_ON(skb->dev != dev);
 
-	/* Drop the packet if queues are not set up */
+	/* Drop the packet if queues are not set up.
+	 * This handler should be called inside an RCU read section
+	 * so we don't need to enter it here explicitly.
+	 */
+	num_queues = READ_ONCE(vif->num_queues);
 	if (num_queues < 1)
 		goto drop;
 
···
 {
 	struct xenvif *vif = netdev_priv(dev);
 	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues;
 	u64 rx_bytes = 0;
 	u64 rx_packets = 0;
 	u64 tx_bytes = 0;
 	u64 tx_packets = 0;
 	unsigned int index;
 
-	spin_lock(&vif->lock);
-	if (vif->queues == NULL)
-		goto out;
+	rcu_read_lock();
+	num_queues = READ_ONCE(vif->num_queues);
 
 	/* Aggregate tx and rx stats from each queue */
-	for (index = 0; index < vif->num_queues; ++index) {
+	for (index = 0; index < num_queues; ++index) {
 		queue = &vif->queues[index];
 		rx_bytes += queue->stats.rx_bytes;
 		rx_packets += queue->stats.rx_packets;
···
 		tx_packets += queue->stats.tx_packets;
 	}
 
-out:
-	spin_unlock(&vif->lock);
+	rcu_read_unlock();
 
 	vif->dev->stats.rx_bytes = rx_bytes;
 	vif->dev->stats.rx_packets = rx_packets;
···
 				     struct ethtool_stats *stats, u64 * data)
 {
 	struct xenvif *vif = netdev_priv(dev);
-	unsigned int num_queues = vif->num_queues;
+	unsigned int num_queues;
 	int i;
 	unsigned int queue_index;
+
+	rcu_read_lock();
+	num_queues = READ_ONCE(vif->num_queues);
 
 	for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) {
 		unsigned long accum = 0;
···
 		}
 		data[i] = accum;
 	}
+
+	rcu_read_unlock();
 }
 
 static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data)

drivers/net/xen-netback/netback.c

···
 	netdev_err(vif->dev, "fatal error; disabling device\n");
 	vif->disabled = true;
 	/* Disable the vif from queue 0's kthread */
-	if (vif->queues)
+	if (vif->num_queues)
 		xenvif_kick_thread(&vif->queues[0]);
 }
 

drivers/net/xen-netback/xenbus.c

···
 	struct xenvif *vif = be->vif;
 
 	if (vif) {
+		unsigned int num_queues = vif->num_queues;
 		unsigned int queue_index;
-		struct xenvif_queue *queues;
 
 		xen_unregister_watchers(vif);
 #ifdef CONFIG_DEBUG_FS
 		xenvif_debugfs_delif(vif);
 #endif /* CONFIG_DEBUG_FS */
 		xenvif_disconnect_data(vif);
-		for (queue_index = 0;
-		     queue_index < vif->num_queues;
-		     ++queue_index)
+
+		/* At this point some of the handlers may still be active
+		 * so we need to have additional synchronization here.
+		 */
+		vif->num_queues = 0;
+		synchronize_net();
+
+		for (queue_index = 0; queue_index < num_queues; ++queue_index)
 			xenvif_deinit_queue(&vif->queues[queue_index]);
 
-		spin_lock(&vif->lock);
-		queues = vif->queues;
-		vif->num_queues = 0;
+		vfree(vif->queues);
 		vif->queues = NULL;
-		spin_unlock(&vif->lock);
-
-		vfree(queues);
 
 		xenvif_disconnect_ctrl(vif);
 	}

drivers/platform/x86/asus-nb-wmi.c

···
 	.wapf = 2,
 };
 
-static struct quirk_entry quirk_no_rfkill = {
-	.no_rfkill = true,
-};
-
-static struct quirk_entry quirk_no_rfkill_wapf4 = {
-	.wapf = 4,
-	.no_rfkill = true,
-};
-
 static struct quirk_entry quirk_asus_ux303ub = {
 	.wmi_backlight_native = true,
 };
···
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "X456UA"),
 		},
-		.driver_data = &quirk_no_rfkill_wapf4,
+		.driver_data = &quirk_asus_wapf4,
 	},
 	{
 		.callback = dmi_matched,
···
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "X456UF"),
 		},
-		.driver_data = &quirk_no_rfkill_wapf4,
+		.driver_data = &quirk_asus_wapf4,
 	},
 	{
 		.callback = dmi_matched,
···
 			DMI_MATCH(DMI_PRODUCT_NAME, "X200CA"),
 		},
 		.driver_data = &quirk_asus_x200ca,
-	},
-	{
-		.callback = dmi_matched,
-		.ident = "ASUSTeK COMPUTER INC. X555UB",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "X555UB"),
-		},
-		.driver_data = &quirk_no_rfkill,
-	},
-	{
-		.callback = dmi_matched,
-		.ident = "ASUSTeK COMPUTER INC. N552VW",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "N552VW"),
-		},
-		.driver_data = &quirk_no_rfkill,
-	},
-	{
-		.callback = dmi_matched,
-		.ident = "ASUSTeK COMPUTER INC. U303LB",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "U303LB"),
-		},
-		.driver_data = &quirk_no_rfkill,
-	},
-	{
-		.callback = dmi_matched,
-		.ident = "ASUSTeK COMPUTER INC. Z550MA",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Z550MA"),
-		},
-		.driver_data = &quirk_no_rfkill,
 	},
 	{
 		.callback = dmi_matched,

drivers/platform/x86/asus-wmi.c

···
 #define USB_INTEL_XUSB2PR		0xD0
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI	0x9c31
 
+static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL };
+
 struct bios_args {
 	u32 arg0;
 	u32 arg1;
···
 	return 0;
 }
 
+static bool ashs_present(void)
+{
+	int i = 0;
+	while (ashs_ids[i]) {
+		if (acpi_dev_found(ashs_ids[i++]))
+			return true;
+	}
+	return false;
+}
+
 /*
  * WMI Driver
  */
···
 	if (err)
 		goto fail_leds;
 
-	if (!asus->driver->quirks->no_rfkill) {
+	asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result);
+	if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT))
+		asus->driver->wlan_ctrl_by_user = 1;
+
+	if (!(asus->driver->wlan_ctrl_by_user && ashs_present())) {
 		err = asus_wmi_rfkill_init(asus);
 		if (err)
 			goto fail_rfkill;
···
 	err = asus_wmi_debugfs_init(asus);
 	if (err)
 		goto fail_debugfs;
-
-	asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result);
-	if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT))
-		asus->driver->wlan_ctrl_by_user = 1;
 
 	return 0;
 

drivers/platform/x86/asus-wmi.h

···
 struct asus_wmi;
 
 struct quirk_entry {
-	bool no_rfkill;
 	bool hotplug_wireless;
 	bool scalar_panel_brightness;
 	bool store_backlight_power;

drivers/platform/x86/fujitsu-laptop.c

···
 
 #define FUJITSU_LCD_N_LEVELS 8
 
-#define ACPI_FUJITSU_CLASS              "fujitsu"
-#define ACPI_FUJITSU_HID                "FUJ02B1"
-#define ACPI_FUJITSU_DRIVER_NAME	"Fujitsu laptop FUJ02B1 ACPI brightness driver"
-#define ACPI_FUJITSU_DEVICE_NAME        "Fujitsu FUJ02B1"
-#define ACPI_FUJITSU_HOTKEY_HID 	"FUJ02E3"
-#define ACPI_FUJITSU_HOTKEY_DRIVER_NAME "Fujitsu laptop FUJ02E3 ACPI hotkeys driver"
-#define ACPI_FUJITSU_HOTKEY_DEVICE_NAME "Fujitsu FUJ02E3"
+#define ACPI_FUJITSU_CLASS		"fujitsu"
+#define ACPI_FUJITSU_BL_HID		"FUJ02B1"
+#define ACPI_FUJITSU_BL_DRIVER_NAME	"Fujitsu laptop FUJ02B1 ACPI brightness driver"
+#define ACPI_FUJITSU_BL_DEVICE_NAME	"Fujitsu FUJ02B1"
+#define ACPI_FUJITSU_LAPTOP_HID		"FUJ02E3"
+#define ACPI_FUJITSU_LAPTOP_DRIVER_NAME	"Fujitsu laptop FUJ02E3 ACPI hotkeys driver"
+#define ACPI_FUJITSU_LAPTOP_DEVICE_NAME	"Fujitsu FUJ02E3"
 
 #define ACPI_FUJITSU_NOTIFY_CODE1     0x80
 
 /* FUNC interface - command values */
-#define FUNC_RFKILL	0x1000
+#define FUNC_FLAGS	0x1000
 #define FUNC_LEDS	0x1001
 #define FUNC_BUTTONS	0x1002
 #define FUNC_BACKLIGHT  0x1004
 
 /* FUNC interface - responses */
 #define UNSUPPORTED_CMD 0x80000000
+
+/* FUNC interface - status flags */
+#define FLAG_RFKILL	0x020
+#define FLAG_LID	0x100
+#define FLAG_DOCK	0x200
 
 #if IS_ENABLED(CONFIG_LEDS_CLASS)
 /* FUNC interface - LED control */
···
 #endif
 
 /* Device controlling the backlight and associated keys */
-struct fujitsu_t {
+struct fujitsu_bl {
 	acpi_handle acpi_handle;
 	struct acpi_device *dev;
 	struct input_dev *input;
···
 	unsigned int brightness_level;
 };
 
-static struct fujitsu_t *fujitsu;
+static struct fujitsu_bl *fujitsu_bl;
 static int use_alt_lcd_levels = -1;
 static int disable_brightness_adjust = -1;
 
-/* Device used to access other hotkeys on the laptop */
-struct fujitsu_hotkey_t {
+/* Device used to access hotkeys and other features on the laptop */
+struct fujitsu_laptop {
 	acpi_handle acpi_handle;
 	struct acpi_device *dev;
 	struct input_dev *input;
···
 	struct platform_device *pf_device;
 	struct kfifo fifo;
 	spinlock_t fifo_lock;
-	int rfkill_supported;
-	int rfkill_state;
+	int flags_supported;
+	int flags_state;
 	int logolamp_registered;
 	int kblamps_registered;
 	int radio_led_registered;
 	int eco_led_registered;
 };
 
-static struct fujitsu_hotkey_t *fujitsu_hotkey;
-
-static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event);
+static struct fujitsu_laptop *fujitsu_laptop;
 
 #if IS_ENABLED(CONFIG_LEDS_CLASS)
 static enum led_brightness logolamp_get(struct led_classdev *cdev);
···
 static u32 dbg_level = 0x03;
 #endif
 
-static void acpi_fujitsu_notify(struct acpi_device *device, u32 event);
-
 /* Fujitsu ACPI interface function */
 
 static int call_fext_func(int cmd, int arg0, int arg1, int arg2)
···
 	unsigned long long value;
 	acpi_handle handle = NULL;
 
-	status = acpi_get_handle(fujitsu_hotkey->acpi_handle, "FUNC", &handle);
+	status = acpi_get_handle(fujitsu_laptop->acpi_handle, "FUNC", &handle);
 	if (ACPI_FAILURE(status)) {
 		vdbg_printk(FUJLAPTOP_DBG_ERROR,
 				"FUNC interface is not present\n");
···
 				enum led_brightness brightness)
 {
 	if (brightness >= LED_FULL)
-		return call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, RADIO_LED_ON);
+		return call_fext_func(FUNC_FLAGS, 0x5, RADIO_LED_ON, RADIO_LED_ON);
 	else
-		return call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, 0x0);
+		return call_fext_func(FUNC_FLAGS, 0x5, RADIO_LED_ON, 0x0);
 }
 
 static int eco_led_set(struct led_classdev *cdev,
···
 {
 	enum led_brightness brightness = LED_OFF;
 
-	if (call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0) & RADIO_LED_ON)
+	if (call_fext_func(FUNC_FLAGS, 0x4, 0x0, 0x0) & RADIO_LED_ON)
 		brightness = LED_FULL;
 
 	return brightness;
···
 	vdbg_printk(FUJLAPTOP_DBG_TRACE, "set lcd level via SBLL [%d]\n",
 		    level);
 
-	if (level < 0 || level >= fujitsu->max_brightness)
+	if (level < 0 || level >= fujitsu_bl->max_brightness)
 		return -EINVAL;
 
-	status = acpi_get_handle(fujitsu->acpi_handle, "SBLL", &handle);
+	status = acpi_get_handle(fujitsu_bl->acpi_handle, "SBLL", &handle);
 	if (ACPI_FAILURE(status)) {
 		vdbg_printk(FUJLAPTOP_DBG_ERROR, "SBLL not present\n");
 		return -ENODEV;
···
 	vdbg_printk(FUJLAPTOP_DBG_TRACE, "set lcd level via SBL2 [%d]\n",
 		    level);
 
-	if (level < 0 || level >= fujitsu->max_brightness)
+	if (level < 0 || level >= fujitsu_bl->max_brightness)
 		return -EINVAL;
 
-	status = acpi_get_handle(fujitsu->acpi_handle, "SBL2", &handle);
+	status = acpi_get_handle(fujitsu_bl->acpi_handle, "SBL2", &handle);
 	if (ACPI_FAILURE(status)) {
 		vdbg_printk(FUJLAPTOP_DBG_ERROR, "SBL2 not present\n");
 		return -ENODEV;
···
 
 	vdbg_printk(FUJLAPTOP_DBG_TRACE, "get lcd level via GBLL\n");
 
-	status =
-	    acpi_evaluate_integer(fujitsu->acpi_handle, "GBLL", NULL, &state);
+	status = acpi_evaluate_integer(fujitsu_bl->acpi_handle, "GBLL", NULL,
+				       &state);
 	if (ACPI_FAILURE(status))
 		return 0;
 
-	fujitsu->brightness_level = state & 0x0fffffff;
+	fujitsu_bl->brightness_level = state & 0x0fffffff;
 
 	if (state & 0x80000000)
-		fujitsu->brightness_changed = 1;
+		fujitsu_bl->brightness_changed = 1;
 	else
-		fujitsu->brightness_changed = 0;
+		fujitsu_bl->brightness_changed = 0;
 
-	return fujitsu->brightness_level;
+	return fujitsu_bl->brightness_level;
 }
 
 static int get_max_brightness(void)
···
 
 	vdbg_printk(FUJLAPTOP_DBG_TRACE, "get max lcd level via RBLL\n");
 
-	status =
-	    acpi_evaluate_integer(fujitsu->acpi_handle, "RBLL", NULL, &state);
+	status = acpi_evaluate_integer(fujitsu_bl->acpi_handle, "RBLL", NULL,
+				       &state);
 	if (ACPI_FAILURE(status))
 		return -1;
 
-	fujitsu->max_brightness = state;
+	fujitsu_bl->max_brightness = state;
 
-	return fujitsu->max_brightness;
+	return fujitsu_bl->max_brightness;
 }
 
 /* Backlight device stuff */
···
 	return ret;
 }
 
-static const struct backlight_ops fujitsubl_ops = {
+static const struct backlight_ops fujitsu_bl_ops = {
 	.get_brightness = bl_get_brightness,
 	.update_status = bl_update_status,
 };
···
 
 	int ret;
 
-	ret = fujitsu->brightness_changed;
+	ret = fujitsu_bl->brightness_changed;
 	if (ret < 0)
 		return ret;
 
···
 	int level, ret;
 
 	if (sscanf(buf, "%i", &level) != 1
-	    || (level < 0 || level >= fujitsu->max_brightness))
+	    || (level < 0 || level >= fujitsu_bl->max_brightness))
 		return -EINVAL;
 
 	if (use_alt_lcd_levels)
···
 show_lid_state(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
-	if (!(fujitsu_hotkey->rfkill_supported & 0x100))
+	if (!(fujitsu_laptop->flags_supported & FLAG_LID))
 		return sprintf(buf, "unknown\n");
-	if (fujitsu_hotkey->rfkill_state & 0x100)
+	if (fujitsu_laptop->flags_state & FLAG_LID)
 		return sprintf(buf, "open\n");
 	else
 		return sprintf(buf, "closed\n");
···
 show_dock_state(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
-	if (!(fujitsu_hotkey->rfkill_supported & 0x200))
+	if (!(fujitsu_laptop->flags_supported & FLAG_DOCK))
 		return sprintf(buf, "unknown\n");
-	if (fujitsu_hotkey->rfkill_state & 0x200)
+	if (fujitsu_laptop->flags_state & FLAG_DOCK)
 		return sprintf(buf, "docked\n");
 	else
 		return sprintf(buf, "undocked\n");
···
 show_radios_state(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
-	if (!(fujitsu_hotkey->rfkill_supported & 0x20))
+	if (!(fujitsu_laptop->flags_supported & FLAG_RFKILL))
 		return sprintf(buf, "unknown\n");
-	if (fujitsu_hotkey->rfkill_state & 0x20)
+	if (fujitsu_laptop->flags_state & FLAG_RFKILL)
 		return sprintf(buf, "on\n");
 	else
 		return sprintf(buf, "killed\n");
···
 static DEVICE_ATTR(dock, 0444, show_dock_state, ignore_store);
 static DEVICE_ATTR(radios, 0444, show_radios_state, ignore_store);
 
-static struct attribute *fujitsupf_attributes[] = {
+static struct attribute *fujitsu_pf_attributes[] = {
 	&dev_attr_brightness_changed.attr,
 	&dev_attr_max_brightness.attr,
 	&dev_attr_lcd_level.attr,
···
 	NULL
 };
 
-static struct attribute_group fujitsupf_attribute_group = {
-	.attrs = fujitsupf_attributes
+static struct attribute_group fujitsu_pf_attribute_group = {
+	.attrs = fujitsu_pf_attributes
 };
 
-static struct platform_driver fujitsupf_driver = {
+static struct platform_driver fujitsu_pf_driver = {
 	.driver = {
 		   .name = "fujitsu-laptop",
 		   }
···
 static void __init dmi_check_cb_common(const struct dmi_system_id *id)
 {
 	pr_info("Identified laptop model '%s'\n", id->ident);
-	if (use_alt_lcd_levels == -1) {
-		if (acpi_has_method(NULL,
-				"\\_SB.PCI0.LPCB.FJEX.SBL2"))
-			use_alt_lcd_levels = 1;
-		else
-			use_alt_lcd_levels = 0;
-		vdbg_printk(FUJLAPTOP_DBG_TRACE, "auto-detected usealt as "
-			"%i\n", use_alt_lcd_levels);
-	}
 }
 
 static int __init dmi_check_cb_s6410(const struct dmi_system_id *id)
 {
 	dmi_check_cb_common(id);
-	fujitsu->keycode1 = KEY_SCREENLOCK;	/* "Lock" */
-	fujitsu->keycode2 = KEY_HELP;	/* "Mobility Center" */
+	fujitsu_bl->keycode1 = KEY_SCREENLOCK;	/* "Lock" */
+	fujitsu_bl->keycode2 = KEY_HELP;	/* "Mobility Center" */
 	return 1;
 }
 
 static int __init dmi_check_cb_s6420(const struct dmi_system_id *id)
 {
 	dmi_check_cb_common(id);
-	fujitsu->keycode1 = KEY_SCREENLOCK;	/* "Lock" */
-	fujitsu->keycode2 = KEY_HELP;	/* "Mobility Center" */
+	fujitsu_bl->keycode1 = KEY_SCREENLOCK;	/* "Lock" */
+	fujitsu_bl->keycode2 = KEY_HELP;	/* "Mobility Center" */
 	return 1;
 }
 
 static int __init dmi_check_cb_p8010(const struct dmi_system_id *id)
 {
 	dmi_check_cb_common(id);
-	fujitsu->keycode1 = KEY_HELP;	/* "Support" */
-	fujitsu->keycode3 = KEY_SWITCHVIDEOMODE;	/* "Presentation" */
-	fujitsu->keycode4 = KEY_WWW;	/* "Internet" */
+	fujitsu_bl->keycode1 = KEY_HELP;		/* "Support" */
+	fujitsu_bl->keycode3 = KEY_SWITCHVIDEOMODE;	/* "Presentation" */
+	fujitsu_bl->keycode4 = KEY_WWW;			/* "Internet" */
 	return 1;
 }
 
···
 
 /* ACPI device for LCD brightness control */
 
-static int acpi_fujitsu_add(struct acpi_device *device)
+static int acpi_fujitsu_bl_add(struct acpi_device *device)
 {
 	int state = 0;
 	struct input_dev *input;
···
 	if (!device)
 		return -EINVAL;
 
-	fujitsu->acpi_handle = device->handle;
-	sprintf(acpi_device_name(device), "%s", ACPI_FUJITSU_DEVICE_NAME);
+	fujitsu_bl->acpi_handle = device->handle;
+	sprintf(acpi_device_name(device), "%s", ACPI_FUJITSU_BL_DEVICE_NAME);
 	sprintf(acpi_device_class(device), "%s", ACPI_FUJITSU_CLASS);
-	device->driver_data = fujitsu;
+	device->driver_data = fujitsu_bl;
 
-	fujitsu->input = input = input_allocate_device();
+	fujitsu_bl->input = input = input_allocate_device();
 	if (!input) {
 		error = -ENOMEM;
 		goto err_stop;
 	}
 
-	snprintf(fujitsu->phys, sizeof(fujitsu->phys),
+	snprintf(fujitsu_bl->phys, sizeof(fujitsu_bl->phys),
 		 "%s/video/input0", acpi_device_hid(device));
 
 	input->name = acpi_device_name(device);
-	input->phys = fujitsu->phys;
+	input->phys = fujitsu_bl->phys;
 	input->id.bustype = BUS_HOST;
 	input->id.product = 0x06;
 	input->dev.parent = &device->dev;
···
 	if (error)
 		goto err_free_input_dev;
 
-	error = acpi_bus_update_power(fujitsu->acpi_handle, &state);
+	error = acpi_bus_update_power(fujitsu_bl->acpi_handle, &state);
 	if (error) {
 		pr_err("Error reading power state\n");
 		goto err_unregister_input_dev;
···
 	       acpi_device_name(device), acpi_device_bid(device),
 	       !device->power.state ? "on" : "off");
 
-	fujitsu->dev = device;
+	fujitsu_bl->dev = device;
 
 	if (acpi_has_method(device->handle, METHOD_NAME__INI)) {
 		vdbg_printk(FUJLAPTOP_DBG_INFO, "Invoking _INI\n");
···
 		    (acpi_evaluate_object
 		     (device->handle, METHOD_NAME__INI, NULL, NULL)))
 			pr_err("_INI Method failed\n");
+	}
+
+	if (use_alt_lcd_levels == -1) {
+		if (acpi_has_method(NULL, "\\_SB.PCI0.LPCB.FJEX.SBL2"))
+			use_alt_lcd_levels = 1;
+		else
+			use_alt_lcd_levels = 0;
+		vdbg_printk(FUJLAPTOP_DBG_TRACE, "auto-detected usealt as %i\n",
+			    use_alt_lcd_levels);
 	}
 
 	/* do config (detect defaults) */
···
 		    use_alt_lcd_levels, disable_brightness_adjust);
 
 	if (get_max_brightness() <= 0)
-		fujitsu->max_brightness = FUJITSU_LCD_N_LEVELS;
+		fujitsu_bl->max_brightness = FUJITSU_LCD_N_LEVELS;
 	get_lcd_level();
 
 	return 0;
···
 	return error;
 }
 
-static int acpi_fujitsu_remove(struct acpi_device *device)
+static int acpi_fujitsu_bl_remove(struct acpi_device *device)
 {
-	struct fujitsu_t *fujitsu = acpi_driver_data(device);
-	struct input_dev *input = fujitsu->input;
+	struct fujitsu_bl *fujitsu_bl = acpi_driver_data(device);
+	struct input_dev *input = fujitsu_bl->input;
 
 	input_unregister_device(input);
 
-	fujitsu->acpi_handle = NULL;
+	fujitsu_bl->acpi_handle = NULL;
 
 	return 0;
 }
 
 /* Brightness notify */
 
-static void acpi_fujitsu_notify(struct acpi_device *device, u32 event)
+static void acpi_fujitsu_bl_notify(struct acpi_device *device, u32 event)
 {
 	struct input_dev *input;
 	int keycode;
 	int oldb, newb;
 
-	input = fujitsu->input;
+	input = fujitsu_bl->input;
 
 	switch (event) {
 	case ACPI_FUJITSU_NOTIFY_CODE1:
 		keycode = 0;
-		oldb = fujitsu->brightness_level;
+		oldb = fujitsu_bl->brightness_level;
 		get_lcd_level();
-		newb = fujitsu->brightness_level;
+		newb = fujitsu_bl->brightness_level;
 
 		vdbg_printk(FUJLAPTOP_DBG_TRACE,
 			    "brightness button event [%i -> %i (%i)]\n",
-			    oldb, newb, fujitsu->brightness_changed);
+			    oldb, newb, fujitsu_bl->brightness_changed);
 
 		if (oldb < newb) {
 			if (disable_brightness_adjust != 1) {
···
 
 /* ACPI device for hotkey handling */
 
-static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
+static int acpi_fujitsu_laptop_add(struct acpi_device *device)
 {
 	int result = 0;
 	int state = 0;
···
 	if (!device)
 		return -EINVAL;
 
-	fujitsu_hotkey->acpi_handle = device->handle;
+	fujitsu_laptop->acpi_handle = device->handle;
 	sprintf(acpi_device_name(device), "%s",
-		ACPI_FUJITSU_HOTKEY_DEVICE_NAME);
+		ACPI_FUJITSU_LAPTOP_DEVICE_NAME);
 	sprintf(acpi_device_class(device), "%s", ACPI_FUJITSU_CLASS);
-	device->driver_data = fujitsu_hotkey;
+	device->driver_data = fujitsu_laptop;
 
 	/* kfifo */
-	spin_lock_init(&fujitsu_hotkey->fifo_lock);
-	error = kfifo_alloc(&fujitsu_hotkey->fifo, RINGBUFFERSIZE * sizeof(int),
+	spin_lock_init(&fujitsu_laptop->fifo_lock);
+	error = kfifo_alloc(&fujitsu_laptop->fifo, RINGBUFFERSIZE * sizeof(int),
 			GFP_KERNEL);
 	if (error) {
 		pr_err("kfifo_alloc failed\n");
 		goto err_stop;
 	}
 
-	fujitsu_hotkey->input = input = input_allocate_device();
+	fujitsu_laptop->input = input = input_allocate_device();
 	if (!input) {
 		error = -ENOMEM;
 		goto err_free_fifo;
 	}
 
-	snprintf(fujitsu_hotkey->phys, sizeof(fujitsu_hotkey->phys),
+	snprintf(fujitsu_laptop->phys, sizeof(fujitsu_laptop->phys),
 		 "%s/video/input0", acpi_device_hid(device));
 
 	input->name = acpi_device_name(device);
-	input->phys = fujitsu_hotkey->phys;
+	input->phys = fujitsu_laptop->phys;
 	input->id.bustype = BUS_HOST;
 	input->id.product = 0x06;
 	input->dev.parent = &device->dev;
 
 	set_bit(EV_KEY, input->evbit);
-	set_bit(fujitsu->keycode1, input->keybit);
-	set_bit(fujitsu->keycode2, input->keybit);
-	set_bit(fujitsu->keycode3, input->keybit);
-	set_bit(fujitsu->keycode4, input->keybit);
-	set_bit(fujitsu->keycode5, input->keybit);
+	set_bit(fujitsu_bl->keycode1, input->keybit);
+	set_bit(fujitsu_bl->keycode2, input->keybit);
+	set_bit(fujitsu_bl->keycode3, input->keybit);
+	set_bit(fujitsu_bl->keycode4, input->keybit);
+	set_bit(fujitsu_bl->keycode5, input->keybit);
 	set_bit(KEY_TOUCHPAD_TOGGLE, input->keybit);
 	set_bit(KEY_UNKNOWN, input->keybit);
 
···
 	if (error)
 		goto err_free_input_dev;
 
-	error = acpi_bus_update_power(fujitsu_hotkey->acpi_handle, &state);
+	error = acpi_bus_update_power(fujitsu_laptop->acpi_handle, &state);
 	if (error) {
 		pr_err("Error reading power state\n");
 		goto err_unregister_input_dev;
···
 		acpi_device_name(device), acpi_device_bid(device),
 		!device->power.state ? "on" : "off");
 
-	fujitsu_hotkey->dev = device;
+	fujitsu_laptop->dev = device;
 
 	if (acpi_has_method(device->handle, METHOD_NAME__INI)) {
 		vdbg_printk(FUJLAPTOP_DBG_INFO, "Invoking _INI\n");
···
 		; /* No action, result is discarded */
 	vdbg_printk(FUJLAPTOP_DBG_INFO, "Discarded %i ringbuffer entries\n", i);
 
-	fujitsu_hotkey->rfkill_supported =
-		call_fext_func(FUNC_RFKILL, 0x0, 0x0, 0x0);
+	fujitsu_laptop->flags_supported =
+		call_fext_func(FUNC_FLAGS, 0x0, 0x0, 0x0);
 
 	/* Make sure our bitmask of supported functions is cleared if the
 	   RFKILL function block is not implemented, like on the S7020. */
-	if (fujitsu_hotkey->rfkill_supported == UNSUPPORTED_CMD)
-		fujitsu_hotkey->rfkill_supported = 0;
+	if (fujitsu_laptop->flags_supported == UNSUPPORTED_CMD)
+		fujitsu_laptop->flags_supported = 0;
 
-	if (fujitsu_hotkey->rfkill_supported)
-		fujitsu_hotkey->rfkill_state =
-			call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0);
+	if (fujitsu_laptop->flags_supported)
+		fujitsu_laptop->flags_state =
+			call_fext_func(FUNC_FLAGS, 0x4, 0x0, 0x0);
 
 	/* Suspect this is a keymap of the application panel, print it */
 	pr_info("BTNI: [0x%x]\n", call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0));
 
 #if IS_ENABLED(CONFIG_LEDS_CLASS)
 	if (call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & LOGOLAMP_POWERON) {
-		result = led_classdev_register(&fujitsu->pf_device->dev,
+		result = led_classdev_register(&fujitsu_bl->pf_device->dev,
 						&logolamp_led);
 		if (result == 0) {
-			fujitsu_hotkey->logolamp_registered = 1;
+			fujitsu_laptop->logolamp_registered = 1;
 		} else {
 			pr_err("Could not register LED handler for logo lamp, error %i\n",
 			       result);
···
 
 	if ((call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & KEYBOARD_LAMPS) &&
 	   (call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0) == 0x0)) {
-		result = led_classdev_register(&fujitsu->pf_device->dev,
+		result = led_classdev_register(&fujitsu_bl->pf_device->dev,
 						&kblamps_led);
 		if (result == 0) {
-			fujitsu_hotkey->kblamps_registered = 1;
+			fujitsu_laptop->kblamps_registered = 1;
 		} else {
 			pr_err("Could not register LED handler for keyboard lamps, error %i\n",
 			       result);
···
 	 * that an RF LED is present.
 	 */
 	if (call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0) & BIT(24)) {
-		result = led_classdev_register(&fujitsu->pf_device->dev,
+		result = led_classdev_register(&fujitsu_bl->pf_device->dev,
 						&radio_led);
 		if (result == 0) {
-			fujitsu_hotkey->radio_led_registered = 1;
+			fujitsu_laptop->radio_led_registered = 1;
 		} else {
 			pr_err("Could not register LED handler for radio LED, error %i\n",
 			       result);
···
 	*/
 	if ((call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & BIT(14)) &&
 	   (call_fext_func(FUNC_LEDS, 0x2, ECO_LED, 0x0) != UNSUPPORTED_CMD)) {
-		result = led_classdev_register(&fujitsu->pf_device->dev,
+		result = led_classdev_register(&fujitsu_bl->pf_device->dev,
 						&eco_led);
 		if (result == 0) {
-			fujitsu_hotkey->eco_led_registered = 1;
+			fujitsu_laptop->eco_led_registered = 1;
 		} else {
 			pr_err("Could not register LED handler for eco LED, error %i\n",
 			       result);
···
 err_free_input_dev:
 	input_free_device(input);
 err_free_fifo:
-	kfifo_free(&fujitsu_hotkey->fifo);
+	kfifo_free(&fujitsu_laptop->fifo);
 err_stop:
 	return error;
 }
 
-static int acpi_fujitsu_hotkey_remove(struct acpi_device *device)
+static int acpi_fujitsu_laptop_remove(struct acpi_device *device)
 {
-	struct fujitsu_hotkey_t *fujitsu_hotkey = acpi_driver_data(device);
-	struct input_dev *input = fujitsu_hotkey->input;
+	struct fujitsu_laptop *fujitsu_laptop = acpi_driver_data(device);
+	struct input_dev *input = fujitsu_laptop->input;
 
 #if IS_ENABLED(CONFIG_LEDS_CLASS)
-	if (fujitsu_hotkey->logolamp_registered)
+	if (fujitsu_laptop->logolamp_registered)
 		led_classdev_unregister(&logolamp_led);
 
-	if (fujitsu_hotkey->kblamps_registered)
+	if (fujitsu_laptop->kblamps_registered)
 		led_classdev_unregister(&kblamps_led);
 
-	if (fujitsu_hotkey->radio_led_registered)
+	if (fujitsu_laptop->radio_led_registered)
 		led_classdev_unregister(&radio_led);
 
-	if (fujitsu_hotkey->eco_led_registered)
+	if (fujitsu_laptop->eco_led_registered)
 		led_classdev_unregister(&eco_led);
 #endif
 
 	input_unregister_device(input);
 
-	kfifo_free(&fujitsu_hotkey->fifo);
+	kfifo_free(&fujitsu_laptop->fifo);
 
-	fujitsu_hotkey->acpi_handle = NULL;
+	fujitsu_laptop->acpi_handle = NULL;
 
 	return 0;
 }
 
-static void acpi_fujitsu_hotkey_press(int keycode)
+static void acpi_fujitsu_laptop_press(int keycode)
 {
-	struct input_dev *input = fujitsu_hotkey->input;
+	struct input_dev *input = fujitsu_laptop->input;
 	int status;
 
-	status = kfifo_in_locked(&fujitsu_hotkey->fifo,
+	status = kfifo_in_locked(&fujitsu_laptop->fifo,
 				 (unsigned char *)&keycode, sizeof(keycode),
-				 &fujitsu_hotkey->fifo_lock);
+				 &fujitsu_laptop->fifo_lock);
 	if (status != sizeof(keycode)) {
 		vdbg_printk(FUJLAPTOP_DBG_WARN,
 			    "Could not push keycode [0x%x]\n", keycode);
···
 		    "Push keycode into ringbuffer [%d]\n", keycode);
 }
 
-static void acpi_fujitsu_hotkey_release(void)
+static void acpi_fujitsu_laptop_release(void)
 {
-	struct input_dev *input = fujitsu_hotkey->input;
+	struct input_dev *input = fujitsu_laptop->input;
 	int keycode, status;
 
 	while (true) {
-		status = kfifo_out_locked(&fujitsu_hotkey->fifo,
+		status = kfifo_out_locked(&fujitsu_laptop->fifo,
 					  (unsigned char *)&keycode,
 					  sizeof(keycode),
-					  &fujitsu_hotkey->fifo_lock);
+					  &fujitsu_laptop->fifo_lock);
 		if (status != sizeof(keycode))
 			return;
 		input_report_key(input, keycode, 0);
···
 	}
 }
 
-static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event)
+static void acpi_fujitsu_laptop_notify(struct acpi_device *device, u32 event)
 {
 	struct input_dev *input;
 	int keycode;
 	unsigned int irb = 1;
 	int i;
 
-	input = fujitsu_hotkey->input;
+	input = fujitsu_laptop->input;
 
 	if (event != ACPI_FUJITSU_NOTIFY_CODE1) {
 		keycode = KEY_UNKNOWN;
···
 		return;
 	}
 
-	if (fujitsu_hotkey->rfkill_supported)
-		fujitsu_hotkey->rfkill_state =
-			call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0);
+	if (fujitsu_laptop->flags_supported)
+		fujitsu_laptop->flags_state =
+			call_fext_func(FUNC_FLAGS, 0x4, 0x0, 0x0);
 
 	i = 0;
 	while ((irb =
···
 			&& (i++) < MAX_HOTKEY_RINGBUFFER_SIZE) {
 		switch (irb & 0x4ff) {
 		case KEY1_CODE:
-			keycode = fujitsu->keycode1;
+			keycode = fujitsu_bl->keycode1;
 			break;
 		case KEY2_CODE:
-			keycode = fujitsu->keycode2;
+			keycode = fujitsu_bl->keycode2;
 			break;
 		case KEY3_CODE:
-			keycode = fujitsu->keycode3;
+			keycode = fujitsu_bl->keycode3;
 			break;
 		case KEY4_CODE:
-			keycode = fujitsu->keycode4;
+			keycode = fujitsu_bl->keycode4;
 			break;
 		case KEY5_CODE:
-			keycode = fujitsu->keycode5;
+			keycode = fujitsu_bl->keycode5;
 			break;
 		case 0:
 			keycode = 0;
···
 		}
 
 		if (keycode > 0)
-			acpi_fujitsu_hotkey_press(keycode);
+			acpi_fujitsu_laptop_press(keycode);
 		else if (keycode == 0)
-			acpi_fujitsu_hotkey_release();
+			acpi_fujitsu_laptop_release();
 	}
 
 	/* On some models (first seen on the Skylake-based Lifebook
 	 * E736/E746/E756), the touchpad toggle hotkey (Fn+F4) is
-	 * handled in software; its state is queried using FUNC_RFKILL
+	 * handled in software; its state is queried using FUNC_FLAGS
 	 */
-	if ((fujitsu_hotkey->rfkill_supported & BIT(26)) &&
-	    (call_fext_func(FUNC_RFKILL, 0x1, 0x0, 0x0) & BIT(26))) {
+	if ((fujitsu_laptop->flags_supported & BIT(26)) &&
+	    (call_fext_func(FUNC_FLAGS, 0x1, 0x0, 0x0) & BIT(26))) {
 		keycode = KEY_TOUCHPAD_TOGGLE;
 		input_report_key(input, keycode, 1);
 		input_sync(input);
···
 
 /* Initialization */
 
-static const struct acpi_device_id fujitsu_device_ids[] = {
-	{ACPI_FUJITSU_HID, 0},
+static const struct acpi_device_id fujitsu_bl_device_ids[] = {
+	{ACPI_FUJITSU_BL_HID, 0},
 	{"", 0},
 };
 
-static struct acpi_driver acpi_fujitsu_driver = {
-	.name = ACPI_FUJITSU_DRIVER_NAME,
+static struct acpi_driver acpi_fujitsu_bl_driver = {
+	.name = ACPI_FUJITSU_BL_DRIVER_NAME,
 	.class = ACPI_FUJITSU_CLASS,
-	.ids = fujitsu_device_ids,
+	.ids = fujitsu_bl_device_ids,
 	.ops = {
-		.add = acpi_fujitsu_add,
-		.remove = acpi_fujitsu_remove,
-		.notify = acpi_fujitsu_notify,
+		.add = acpi_fujitsu_bl_add,
+		.remove = acpi_fujitsu_bl_remove,
+		.notify = acpi_fujitsu_bl_notify,
 		},
 };
 
-static const struct acpi_device_id fujitsu_hotkey_device_ids[] = {
-	{ACPI_FUJITSU_HOTKEY_HID, 0},
+static const struct acpi_device_id fujitsu_laptop_device_ids[] = {
+	{ACPI_FUJITSU_LAPTOP_HID, 0},
 	{"", 0},
 };
 
-static struct acpi_driver acpi_fujitsu_hotkey_driver = {
-	.name = ACPI_FUJITSU_HOTKEY_DRIVER_NAME,
+static struct acpi_driver acpi_fujitsu_laptop_driver = {
+	.name = ACPI_FUJITSU_LAPTOP_DRIVER_NAME,
 	.class = ACPI_FUJITSU_CLASS,
-	.ids = fujitsu_hotkey_device_ids,
+	.ids = fujitsu_laptop_device_ids,
 	.ops = {
-		.add = acpi_fujitsu_hotkey_add,
-		.remove = acpi_fujitsu_hotkey_remove,
-		.notify = acpi_fujitsu_hotkey_notify,
+		.add = acpi_fujitsu_laptop_add,
+		.remove = acpi_fujitsu_laptop_remove,
+		.notify = acpi_fujitsu_laptop_notify,
 		},
 };
 
 static const struct acpi_device_id fujitsu_ids[] __used = {
-	{ACPI_FUJITSU_HID, 0},
-	{ACPI_FUJITSU_HOTKEY_HID, 0},
+	{ACPI_FUJITSU_BL_HID, 0},
+	{ACPI_FUJITSU_LAPTOP_HID, 0},
 	{"", 0}
 };
 MODULE_DEVICE_TABLE(acpi, fujitsu_ids);
 
 static int __init fujitsu_init(void)
 {
-	int ret, result, max_brightness;
+	int ret, max_brightness;
 
 	if (acpi_disabled)
 		return -ENODEV;
 
-	fujitsu = kzalloc(sizeof(struct fujitsu_t), GFP_KERNEL);
-	if (!fujitsu)
+	fujitsu_bl = kzalloc(sizeof(struct fujitsu_bl), GFP_KERNEL);
+	if (!fujitsu_bl)
 		return -ENOMEM;
-	fujitsu->keycode1 = KEY_PROG1;
-	fujitsu->keycode2 = KEY_PROG2;
-	fujitsu->keycode3 = KEY_PROG3;
-	fujitsu->keycode4 = KEY_PROG4;
-	fujitsu->keycode5 = KEY_RFKILL;
+	fujitsu_bl->keycode1 = KEY_PROG1;
+	fujitsu_bl->keycode2 = KEY_PROG2;
+	fujitsu_bl->keycode3 = KEY_PROG3;
+	fujitsu_bl->keycode4 = KEY_PROG4;
+	fujitsu_bl->keycode5 = KEY_RFKILL;
 	dmi_check_system(fujitsu_dmi_table);
 
-	result = acpi_bus_register_driver(&acpi_fujitsu_driver);
-	if (result < 0) {
-		ret = -ENODEV;
+	ret = acpi_bus_register_driver(&acpi_fujitsu_bl_driver);
+	if (ret)
 		goto fail_acpi;
-	}
 
 	/* Register platform stuff */
 
-	fujitsu->pf_device = platform_device_alloc("fujitsu-laptop", -1);
-	if (!fujitsu->pf_device) {
+	fujitsu_bl->pf_device = platform_device_alloc("fujitsu-laptop", -1);
+	if (!fujitsu_bl->pf_device) {
 		ret = -ENOMEM;
 		goto fail_platform_driver;
 	}
 
-	ret = platform_device_add(fujitsu->pf_device);
+	ret = platform_device_add(fujitsu_bl->pf_device);
 	if (ret)
 		goto fail_platform_device1;
 
 	ret =
-	    sysfs_create_group(&fujitsu->pf_device->dev.kobj,
-			       &fujitsupf_attribute_group);
+	    sysfs_create_group(&fujitsu_bl->pf_device->dev.kobj,
+			       &fujitsu_pf_attribute_group);
 	if (ret)
 		goto fail_platform_device2;
 
···
 		struct backlight_properties props;
 
 		memset(&props, 0, sizeof(struct backlight_properties));
-		max_brightness = fujitsu->max_brightness;
+		max_brightness = fujitsu_bl->max_brightness;
 		props.type = BACKLIGHT_PLATFORM;
 		props.max_brightness = max_brightness - 1;
-		fujitsu->bl_device = backlight_device_register("fujitsu-laptop",
-							       NULL, NULL,
-							       &fujitsubl_ops,
-							       &props);
-		if (IS_ERR(fujitsu->bl_device)) {
-			ret = PTR_ERR(fujitsu->bl_device);
-			fujitsu->bl_device = NULL;
+		fujitsu_bl->bl_device = backlight_device_register("fujitsu-laptop",
+								  NULL, NULL,
+								  &fujitsu_bl_ops,
+								  &props);
+		if (IS_ERR(fujitsu_bl->bl_device)) {
+			ret = PTR_ERR(fujitsu_bl->bl_device);
+			fujitsu_bl->bl_device = NULL;
 			goto fail_sysfs_group;
 		}
-		fujitsu->bl_device->props.brightness = fujitsu->brightness_level;
+		fujitsu_bl->bl_device->props.brightness = fujitsu_bl->brightness_level;
 	}
 
-	ret = platform_driver_register(&fujitsupf_driver);
+	ret = platform_driver_register(&fujitsu_pf_driver);
 	if (ret)
 		goto fail_backlight;
 
-	/* Register hotkey driver */
+	/* Register laptop driver */
 
-	fujitsu_hotkey = kzalloc(sizeof(struct fujitsu_hotkey_t), GFP_KERNEL);
-	if (!fujitsu_hotkey) {
+	fujitsu_laptop = kzalloc(sizeof(struct fujitsu_laptop), GFP_KERNEL);
+	if (!fujitsu_laptop) {
 		ret = -ENOMEM;
-		goto fail_hotkey;
+		goto fail_laptop;
 	}
 
-	result = acpi_bus_register_driver(&acpi_fujitsu_hotkey_driver);
-	if (result < 0) {
-		ret = -ENODEV;
-		goto fail_hotkey1;
-	}
+	ret = acpi_bus_register_driver(&acpi_fujitsu_laptop_driver);
+	if (ret)
+		goto fail_laptop1;
 
 	/* Sync backlight power status (needs FUJ02E3 device, hence deferred) */
 	if (acpi_video_get_backlight_type() == acpi_backlight_vendor) {
 		if (call_fext_func(FUNC_BACKLIGHT, 0x2, 0x4, 0x0) == 3)
-			fujitsu->bl_device->props.power = FB_BLANK_POWERDOWN;
+			fujitsu_bl->bl_device->props.power = FB_BLANK_POWERDOWN;
 		else
-			fujitsu->bl_device->props.power = FB_BLANK_UNBLANK;
+			fujitsu_bl->bl_device->props.power = FB_BLANK_UNBLANK;
 	}
 
 	pr_info("driver " FUJITSU_DRIVER_VERSION " successfully loaded\n");
 
 	return 0;
 
-fail_hotkey1:
-	kfree(fujitsu_hotkey);
-fail_hotkey:
-	platform_driver_unregister(&fujitsupf_driver);
+fail_laptop1:
+	kfree(fujitsu_laptop);
+fail_laptop:
+	platform_driver_unregister(&fujitsu_pf_driver);
 fail_backlight:
-	backlight_device_unregister(fujitsu->bl_device);
+	backlight_device_unregister(fujitsu_bl->bl_device);
 fail_sysfs_group:
-	sysfs_remove_group(&fujitsu->pf_device->dev.kobj,
-			   &fujitsupf_attribute_group);
+	sysfs_remove_group(&fujitsu_bl->pf_device->dev.kobj,
+			   &fujitsu_pf_attribute_group);
 fail_platform_device2:
-	platform_device_del(fujitsu->pf_device);
+	platform_device_del(fujitsu_bl->pf_device);
 fail_platform_device1:
-	platform_device_put(fujitsu->pf_device);
+	platform_device_put(fujitsu_bl->pf_device);
 fail_platform_driver:
-	acpi_bus_unregister_driver(&acpi_fujitsu_driver);
+	acpi_bus_unregister_driver(&acpi_fujitsu_bl_driver);
 fail_acpi:
-	kfree(fujitsu);
+	kfree(fujitsu_bl);
 
 	return ret;
 }
 
 static void __exit fujitsu_cleanup(void)
 {
-	acpi_bus_unregister_driver(&acpi_fujitsu_hotkey_driver);
+	acpi_bus_unregister_driver(&acpi_fujitsu_laptop_driver);
 
-	kfree(fujitsu_hotkey);
+	kfree(fujitsu_laptop);
 
-	platform_driver_unregister(&fujitsupf_driver);
+	platform_driver_unregister(&fujitsu_pf_driver);
 
-	backlight_device_unregister(fujitsu->bl_device);
+	backlight_device_unregister(fujitsu_bl->bl_device);
 
-	sysfs_remove_group(&fujitsu->pf_device->dev.kobj,
-			   &fujitsupf_attribute_group);
+	sysfs_remove_group(&fujitsu_bl->pf_device->dev.kobj,
+			   &fujitsu_pf_attribute_group);
 
-	platform_device_unregister(fujitsu->pf_device);
+	platform_device_unregister(fujitsu_bl->pf_device);
 
-	acpi_bus_unregister_driver(&acpi_fujitsu_driver);
+	acpi_bus_unregister_driver(&acpi_fujitsu_bl_driver);
 
-	kfree(fujitsu);
+	kfree(fujitsu_bl);
 
 	pr_info("driver unloaded\n");
 }
···
 MODULE_DESCRIPTION("Fujitsu laptop extras support");
 MODULE_VERSION(FUJITSU_DRIVER_VERSION);
 MODULE_LICENSE("GPL");
-
-MODULE_ALIAS("dmi:*:svnFUJITSUSIEMENS:*:pvr:rvnFUJITSU:rnFJNB1D3:*:cvrS6410:*");
-MODULE_ALIAS("dmi:*:svnFUJITSUSIEMENS:*:pvr:rvnFUJITSU:rnFJNB1E6:*:cvrS6420:*");
-MODULE_ALIAS("dmi:*:svnFUJITSU:*:pvr:rvnFUJITSU:rnFJNB19C:*:cvrS7020:*");

drivers/scsi/Kconfig

···
 	tristate "Emulex LightPulse Fibre Channel Support"
 	depends on PCI && SCSI
 	depends on SCSI_FC_ATTRS
-	depends on NVME_FC && NVME_TARGET_FC
 	select CRC_T10DIF
-	help
+	---help---
           This lpfc driver supports the Emulex LightPulse
           Family of Fibre Channel PCI host adapters.
 
 config SCSI_LPFC_DEBUG_FS
 	bool "Emulex LightPulse Fibre Channel debugfs Support"
 	depends on SCSI_LPFC && DEBUG_FS
-	help
+	---help---
 	  This makes debugging information from the lpfc driver
 	  available via the debugfs filesystem.
+
+config LPFC_NVME_INITIATOR
+	bool "Emulex LightPulse Fibre Channel NVME Initiator Support"
+	depends on SCSI_LPFC && NVME_FC
+	---help---
+	  This enables NVME Initiator support in the Emulex lpfc driver.
+
+config LPFC_NVME_TARGET
+	bool "Emulex LightPulse Fibre Channel NVME Initiator Support"
+	depends on SCSI_LPFC && NVME_TARGET_FC
+	---help---
+	  This enables NVME Target support in the Emulex lpfc driver.
+	  Target enablement must still be enabled on a per adapter
+	  basis by module parameters.
 
 config SCSI_SIM710
 	tristate "Simple 53c710 SCSI support (Compaq, NCR machines)"

drivers/scsi/aacraid/src.c

···
 	return -1;
 
 err_blink:
-	return (status > 16) & 0xFF;
+	return (status >> 16) & 0xFF;
 }
 
 static inline u32 aac_get_vector(struct aac_dev *dev)

drivers/scsi/libiscsi.c

···
 	WARN_ON_ONCE(task->state == ISCSI_TASK_FREE);
 	task->state = state;
 
-	if (!list_empty(&task->running))
+	spin_lock_bh(&conn->taskqueuelock);
+	if (!list_empty(&task->running)) {
+		pr_debug_once("%s while task on list", __func__);
 		list_del_init(&task->running);
+	}
+	spin_unlock_bh(&conn->taskqueuelock);
 
 	if (conn->task == task)
 		conn->task = NULL;
···
 		if (session->tt->xmit_task(task))
 			goto free_task;
 	} else {
+		spin_lock_bh(&conn->taskqueuelock);
 		list_add_tail(&task->running, &conn->mgmtqueue);
+		spin_unlock_bh(&conn->taskqueuelock);
 		iscsi_conn_queue_work(conn);
 	}
 
···
 	 * this may be on the requeue list already if the xmit_task callout
 	 * is handling the r2ts while we are adding new ones
 	 */
+	spin_lock_bh(&conn->taskqueuelock);
 	if (list_empty(&task->running))
 		list_add_tail(&task->running, &conn->requeue);
+	spin_unlock_bh(&conn->taskqueuelock);
 	iscsi_conn_queue_work(conn);
 }
 EXPORT_SYMBOL_GPL(iscsi_requeue_task);
···
 	 * only have one nop-out as a ping from us and targets should not
 	 * overflow us with nop-ins
 	 */
+	spin_lock_bh(&conn->taskqueuelock);
 check_mgmt:
 	while (!list_empty(&conn->mgmtqueue)) {
 		conn->task = list_entry(conn->mgmtqueue.next,
 					 struct iscsi_task, running);
 		list_del_init(&conn->task->running);
+		spin_unlock_bh(&conn->taskqueuelock);
 		if (iscsi_prep_mgmt_task(conn, conn->task)) {
 			/* regular RX path uses back_lock */
 			spin_lock_bh(&conn->session->back_lock);
 			__iscsi_put_task(conn->task);
 			spin_unlock_bh(&conn->session->back_lock);
 			conn->task = NULL;
+			spin_lock_bh(&conn->taskqueuelock);
 			continue;
 		}
 		rc = iscsi_xmit_task(conn);
 		if (rc)
 			goto done;
+		spin_lock_bh(&conn->taskqueuelock);
 	}
 
 	/* process pending command queue */
···
 		conn->task = list_entry(conn->cmdqueue.next, struct iscsi_task,
 					running);
 		list_del_init(&conn->task->running);
+		spin_unlock_bh(&conn->taskqueuelock);
 		if (conn->session->state == ISCSI_STATE_LOGGING_OUT) {
 			fail_scsi_task(conn->task, DID_IMM_RETRY);
+			spin_lock_bh(&conn->taskqueuelock);
 			continue;
 		}
 		rc = iscsi_prep_scsi_cmd_pdu(conn->task);
 		if (rc) {
 			if (rc == -ENOMEM || rc == -EACCES) {
+				spin_lock_bh(&conn->taskqueuelock);
 				list_add_tail(&conn->task->running,
 					      &conn->cmdqueue);
 				conn->task = NULL;
+				spin_unlock_bh(&conn->taskqueuelock);
 				goto done;
 			} else
 				fail_scsi_task(conn->task, DID_ABORT);
+			spin_lock_bh(&conn->taskqueuelock);
 			continue;
 		}
 		rc = iscsi_xmit_task(conn);
···
 		 * we need to check the mgmt queue for nops that need to
 		 * be sent to aviod starvation
 		 */
+		spin_lock_bh(&conn->taskqueuelock);
 		if (!list_empty(&conn->mgmtqueue))
 			goto check_mgmt;
 	}
···
 		conn->task = task;
 		list_del_init(&conn->task->running);
 		conn->task->state = ISCSI_TASK_RUNNING;
+		spin_unlock_bh(&conn->taskqueuelock);
 		rc = iscsi_xmit_task(conn);
 		if (rc)
 			goto done;
+		spin_lock_bh(&conn->taskqueuelock);
 		if (!list_empty(&conn->mgmtqueue))
 			goto check_mgmt;
 	}
+	spin_unlock_bh(&conn->taskqueuelock);
 	spin_unlock_bh(&conn->session->frwd_lock);
 	return -ENODATA;
 
···
 			goto prepd_reject;
 		}
 	} else {
+		spin_lock_bh(&conn->taskqueuelock);
 		list_add_tail(&task->running, &conn->cmdqueue);
+		spin_unlock_bh(&conn->taskqueuelock);
 		iscsi_conn_queue_work(conn);
 	}
 
···
 	INIT_LIST_HEAD(&conn->mgmtqueue);
 	INIT_LIST_HEAD(&conn->cmdqueue);
 	INIT_LIST_HEAD(&conn->requeue);
+	spin_lock_init(&conn->taskqueuelock);
 	INIT_WORK(&conn->xmitwork, iscsi_xmitworker);
 
 	/* allocate login_task used for the login/text sequences */

drivers/scsi/lpfc/lpfc.h

···
 #define FC_MAX_ADPTMSG		64
 
 #define MAX_HBAEVT	32
+#define MAX_HBAS_NO_RESET 16
 
 /* Number of MSI-X vectors the driver uses */
 #define LPFC_MSIX_VECTORS	2
 
 /* lpfc wait event data ready flag */
-#define LPFC_DATA_READY		(1<<0)
+#define LPFC_DATA_READY		0	/* bit 0 */
 
 /* queue dump line buffer size */
 #define LPFC_LBUF_SZ		128
···
 					 * capability
 					 */
 #define HBA_NVME_IOQ_FLUSH      0x80000 /* NVME IO queues flushed. */
+#define NVME_XRI_ABORT_EVENT	0x100000
 
 	uint32_t fcp_ring_in_use; /* When polling test if intr-hndlr active*/
 	struct lpfc_dmabuf slim2p;

drivers/scsi/lpfc/lpfc_attr.c

···
 static DEVICE_ATTR(lpfc_poll, S_IRUGO | S_IWUSR,
 		   lpfc_poll_show, lpfc_poll_store);
 
+int lpfc_no_hba_reset_cnt;
+unsigned long lpfc_no_hba_reset[MAX_HBAS_NO_RESET] = {
+	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+module_param_array(lpfc_no_hba_reset, ulong, &lpfc_no_hba_reset_cnt, 0444);
+MODULE_PARM_DESC(lpfc_no_hba_reset, "WWPN of HBAs that should not be reset");
+
 LPFC_ATTR(sli_mode, 0, 0, 3,
 	"SLI mode selector:"
 	" 0 - auto (SLI-3 if supported),"
···
 		return -EINVAL;
 
 	phba->cfg_fcp_imax = (uint32_t)val;
-	for (i = 0; i < phba->io_channel_irqs; i++)
+
+	for (i = 0; i < phba->io_channel_irqs; i += LPFC_MAX_EQ_DELAY_EQID_CNT)
 		lpfc_modify_hba_eq_delay(phba, i);
 
 	return strlen(buf);

drivers/scsi/lpfc/lpfc_crtn.h

···
 extern struct device_attribute *lpfc_hba_attrs[];
 extern struct device_attribute *lpfc_vport_attrs[];
 extern struct scsi_host_template lpfc_template;
-extern struct scsi_host_template lpfc_template_s3;
+extern struct scsi_host_template lpfc_template_no_hr;
 extern struct scsi_host_template lpfc_template_nvme;
 extern struct scsi_host_template lpfc_vport_template;
 extern struct fc_function_template lpfc_transport_functions;
···
 				struct lpfc_wcqe_complete *abts_cmpl);
 extern int lpfc_enable_nvmet_cnt;
 extern unsigned long long lpfc_enable_nvmet[];
+extern int lpfc_no_hba_reset_cnt;
+extern unsigned long lpfc_no_hba_reset[];

drivers/scsi/lpfc/lpfc_ct.c

···
 					 "FC4 x%08x, Data: x%08x x%08x\n",
 					 ndlp, did, ndlp->nlp_fc4_type,
 					 FC_TYPE_FCP, FC_TYPE_NVME);
+			ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
 		}
-		ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE);
 		lpfc_issue_els_prli(vport, ndlp, 0);
 	} else

drivers/scsi/lpfc/lpfc_debugfs.c

···
 			idiag.ptr_private = phba->sli4_hba.nvmels_cq;
 			goto pass_check;
 		}
-		/* NVME LS complete queue */
-		if (phba->sli4_hba.nvmels_cq &&
-		    phba->sli4_hba.nvmels_cq->queue_id == queid) {
-			/* Sanity check */
-			rc = lpfc_idiag_que_param_check(
-					phba->sli4_hba.nvmels_cq, index, count);
-			if (rc)
-				goto error_out;
-			idiag.ptr_private = phba->sli4_hba.nvmels_cq;
-			goto pass_check;
-		}
 		/* FCP complete queue */
 		if (phba->sli4_hba.fcp_cq) {
 			for (qidx = 0; qidx < phba->cfg_fcp_io_channel;
···
 			if (rc)
 				goto error_out;
 			idiag.ptr_private = phba->sli4_hba.els_wq;
-			goto pass_check;
-		}
-		/* NVME LS work queue */
-		if (phba->sli4_hba.nvmels_wq &&
-		    phba->sli4_hba.nvmels_wq->queue_id == queid) {
-			/* Sanity check */
-			rc = lpfc_idiag_que_param_check(
-					phba->sli4_hba.nvmels_wq, index, count);
-			if (rc)
-				goto error_out;
-			idiag.ptr_private = phba->sli4_hba.nvmels_wq;
 			goto pass_check;
 		}
 		/* NVME LS work queue */

drivers/scsi/lpfc/lpfc_els.c

···
 
 static uint32_t
 lpfc_rdp_res_diag_port_names(struct fc_rdp_port_name_desc *desc,
-		struct lpfc_hba *phba)
+		struct lpfc_vport *vport)
 {
 
 	desc->tag = cpu_to_be32(RDP_PORT_NAMES_DESC_TAG);
 
-	memcpy(desc->port_names.wwnn, phba->wwnn,
+	memcpy(desc->port_names.wwnn, &vport->fc_nodename,
 			sizeof(desc->port_names.wwnn));
 
-	memcpy(desc->port_names.wwpn, phba->wwpn,
+	memcpy(desc->port_names.wwpn, &vport->fc_portname,
 			sizeof(desc->port_names.wwpn));
 
 	desc->length = cpu_to_be32(sizeof(desc->port_names));
···
 	len += lpfc_rdp_res_link_error((struct fc_rdp_link_error_status_desc *)
 				       (len + pcmd), &rdp_context->link_stat);
 	len += lpfc_rdp_res_diag_port_names((struct fc_rdp_port_name_desc *)
-					     (len + pcmd), phba);
+					     (len + pcmd), vport);
 	len += lpfc_rdp_res_attach_port_names((struct fc_rdp_port_name_desc *)
 					(len + pcmd), vport, ndlp);
 	len += lpfc_rdp_res_fec_desc((struct fc_fec_rdp_desc *)(len + pcmd),
···
 			spin_lock_irq(shost->host_lock);
 			vport->fc_flag |= FC_VPORT_NEEDS_REG_VPI;
 			spin_unlock_irq(shost->host_lock);
-			if (vport->port_type == LPFC_PHYSICAL_PORT
-				&& !(vport->fc_flag & FC_LOGO_RCVD_DID_CHNG))
-				lpfc_issue_init_vfi(vport);
-			else
+			if (mb->mbxStatus == MBX_NOT_FINISHED)
+				break;
+			if ((vport->port_type == LPFC_PHYSICAL_PORT) &&
+			    !(vport->fc_flag & FC_LOGO_RCVD_DID_CHNG)) {
+				if (phba->sli_rev == LPFC_SLI_REV4)
+					lpfc_issue_init_vfi(vport);
+				else
+					lpfc_initial_flogi(vport);
+			} else {
 				lpfc_initial_fdisc(vport);
+			}
 			break;
 		}
 	} else {

drivers/scsi/lpfc/lpfc_hbadisc.c

···
 				 ndlp->nlp_state, ndlp->nlp_rpi);
 	}
 
-	if (!(vport->load_flag & FC_UNLOADING) &&
-	    !(ndlp->nlp_flag & NLP_DELAY_TMO) &&
+	if (!(ndlp->nlp_flag & NLP_DELAY_TMO) &&
 	    !(ndlp->nlp_flag & NLP_NPR_2B_DISC) &&
 	    (ndlp->nlp_state != NLP_STE_UNMAPPED_NODE) &&
 	    (ndlp->nlp_state != NLP_STE_REG_LOGIN_ISSUE) &&
···
 			lpfc_handle_rrq_active(phba);
 		if (phba->hba_flag & FCP_XRI_ABORT_EVENT)
 			lpfc_sli4_fcp_xri_abort_event_proc(phba);
+		if (phba->hba_flag & NVME_XRI_ABORT_EVENT)
+			lpfc_sli4_nvme_xri_abort_event_proc(phba);
 		if (phba->hba_flag & ELS_XRI_ABORT_EVENT)
 			lpfc_sli4_els_xri_abort_event_proc(phba);
 		if (phba->hba_flag & ASYNC_EVENT)
···
 	uint32_t boot_flag, addr_mode;
 	uint16_t fcf_index, next_fcf_index;
 	struct lpfc_fcf_rec *fcf_rec = NULL;
-	uint16_t vlan_id;
+	uint16_t vlan_id = LPFC_FCOE_NULL_VID;
 	bool select_new_fcf;
 	int rc;
 
···
 		rdata = rport->dd_data;
 		/* break the link before dropping the ref */
 		ndlp->rport = NULL;
-		if (rdata && rdata->pnode == ndlp)
-			lpfc_nlp_put(ndlp);
-		rdata->pnode = NULL;
+		if (rdata) {
+			if (rdata->pnode == ndlp)
+				lpfc_nlp_put(ndlp);
+			rdata->pnode = NULL;
+		}
 		/* drop reference for earlier registeration */
 		put_device(&rport->dev);
 	}
···
 {
 	INIT_LIST_HEAD(&ndlp->els_retry_evt.evt_listp);
 	INIT_LIST_HEAD(&ndlp->dev_loss_evt.evt_listp);
-	init_timer(&ndlp->nlp_delayfunc);
-	ndlp->nlp_delayfunc.function = lpfc_els_retry_delay;
-	ndlp->nlp_delayfunc.data = (unsigned long)ndlp;
+	setup_timer(&ndlp->nlp_delayfunc, lpfc_els_retry_delay,
+			(unsigned long)ndlp);
 	ndlp->nlp_DID = did;
 	ndlp->vport = vport;
 	ndlp->phba = vport->phba;
···
 		pring = qp->pring;
 		if (!pring)
 			continue;
-		spin_lock_irq(&pring->ring_lock);
+		spin_lock(&pring->ring_lock);
 		__lpfc_dequeue_nport_iocbs(phba, ndlp, pring, dequeue_list);
-		spin_unlock_irq(&pring->ring_lock);
+		spin_unlock(&pring->ring_lock);
 	}
 	spin_unlock_irq(&phba->hbalock);
 }

drivers/scsi/lpfc/lpfc_hw4.h

···
 	uint32_t phase;
 	uint32_t delay_multi;
 };
-#define	LPFC_MAX_EQ_DELAY	8
+#define	LPFC_MAX_EQ_DELAY_EQID_CNT	8
 
 struct sgl_page_pairs {
 	uint32_t sgl_pg0_addr_lo;
···
 	union {
 		struct {
 			uint32_t num_eq;
-			struct eq_delay_info eq[LPFC_MAX_EQ_DELAY];
+			struct eq_delay_info eq[LPFC_MAX_EQ_DELAY_EQID_CNT];
 		} request;
 		struct {
 			uint32_t word0;

drivers/scsi/lpfc/lpfc_init.c

···
 	return rc;
 }
 
+static uint64_t
+lpfc_get_wwpn(struct lpfc_hba *phba)
+{
+	uint64_t wwn;
+	int rc;
+	LPFC_MBOXQ_t *mboxq;
+	MAILBOX_t *mb;
+
+
+	mboxq = (LPFC_MBOXQ_t *) mempool_alloc(phba->mbox_mem_pool,
+						GFP_KERNEL);
+	if (!mboxq)
+		return (uint64_t)-1;
+
+	/* First get WWN of HBA instance */
+	lpfc_read_nv(phba, mboxq);
+	rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
+	if (rc != MBX_SUCCESS) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+				"6019 Mailbox failed , mbxCmd x%x "
+				"READ_NV, mbxStatus x%x\n",
+				bf_get(lpfc_mqe_command, &mboxq->u.mqe),
+				bf_get(lpfc_mqe_status, &mboxq->u.mqe));
+		mempool_free(mboxq, phba->mbox_mem_pool);
+		return (uint64_t) -1;
+	}
+	mb = &mboxq->u.mb;
+	memcpy(&wwn, (char *)mb->un.varRDnvp.portname, sizeof(uint64_t));
+	/* wwn is WWPN of HBA instance */
+	mempool_free(mboxq, phba->mbox_mem_pool);
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		return be64_to_cpu(wwn);
+	else
+		return (((wwn & 0xffffffff00000000) >> 32) |
+			((wwn & 0x00000000ffffffff) << 32));
+
+}
+
 /**
  * lpfc_sli4_nvme_sgl_update - update xri-sgl sizing and mapping
  * @phba: pointer to lpfc hba data structure.
···
 	struct lpfc_vport *vport;
 	struct Scsi_Host  *shost = NULL;
 	int error = 0;
+	int i;
+	uint64_t wwn;
+	bool use_no_reset_hba = false;
+
+	wwn = lpfc_get_wwpn(phba);
+
+	for (i = 0; i < lpfc_no_hba_reset_cnt; i++) {
+		if (wwn == lpfc_no_hba_reset[i]) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+					"6020 Setting use_no_reset port=%llx\n",
+					wwn);
+			use_no_reset_hba = true;
+			break;
+		}
+	}
 
 	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) {
 		if (dev != &phba->pcidev->dev) {
 			shost = scsi_host_alloc(&lpfc_vport_template,
 						sizeof(struct lpfc_vport));
 		} else {
-			if (phba->sli_rev == LPFC_SLI_REV4)
+			if (!use_no_reset_hba)
 				shost = scsi_host_alloc(&lpfc_template,
 						sizeof(struct lpfc_vport));
 			else
-				shost = scsi_host_alloc(&lpfc_template_s3,
+				shost = scsi_host_alloc(&lpfc_template_no_hr,
 						sizeof(struct lpfc_vport));
 		}
 	} else if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
···
 	INIT_LIST_HEAD(&vport->rcv_buffer_list);
 	spin_lock_init(&vport->work_port_lock);
 
-	init_timer(&vport->fc_disctmo);
-	vport->fc_disctmo.function = lpfc_disc_timeout;
-	vport->fc_disctmo.data = (unsigned long)vport;
+	setup_timer(&vport->fc_disctmo, lpfc_disc_timeout,
+			(unsigned long)vport);
 
-	init_timer(&vport->els_tmofunc);
-	vport->els_tmofunc.function = lpfc_els_timeout;
-	vport->els_tmofunc.data = (unsigned long)vport;
+	setup_timer(&vport->els_tmofunc, lpfc_els_timeout,
+			(unsigned long)vport);
 
-	init_timer(&vport->delayed_disc_tmo);
-	vport->delayed_disc_tmo.function = lpfc_delayed_disc_tmo;
-	vport->delayed_disc_tmo.data = (unsigned long)vport;
+	setup_timer(&vport->delayed_disc_tmo, lpfc_delayed_disc_tmo,
+			(unsigned long)vport);
 
 	error = scsi_add_host_with_dma(shost, dev, &phba->pcidev->dev);
 	if (error)
···
 	INIT_LIST_HEAD(&phba->luns);
 
 	/* MBOX heartbeat timer */
-	init_timer(&psli->mbox_tmo);
-	psli->mbox_tmo.function = lpfc_mbox_timeout;
-	psli->mbox_tmo.data = (unsigned long) phba;
+	setup_timer(&psli->mbox_tmo, lpfc_mbox_timeout, (unsigned long)phba);
 	/* Fabric block timer */
-	init_timer(&phba->fabric_block_timer);
-	phba->fabric_block_timer.function = lpfc_fabric_block_timeout;
-	phba->fabric_block_timer.data = (unsigned long) phba;
+	setup_timer(&phba->fabric_block_timer, lpfc_fabric_block_timeout,
+			(unsigned long)phba);
 	/* EA polling mode timer */
-	init_timer(&phba->eratt_poll);
-	phba->eratt_poll.function = lpfc_poll_eratt;
-	phba->eratt_poll.data = (unsigned long) phba;
+	setup_timer(&phba->eratt_poll, lpfc_poll_eratt,
+			(unsigned long)phba);
 	/* Heartbeat timer */
-	init_timer(&phba->hb_tmofunc);
-	phba->hb_tmofunc.function = lpfc_hb_timeout;
-	phba->hb_tmofunc.data = (unsigned long)phba;
+	setup_timer(&phba->hb_tmofunc, lpfc_hb_timeout, (unsigned long)phba);
 
 	return 0;
 }
···
 	 */
 
 	/* FCP polling mode timer */
-	init_timer(&phba->fcp_poll_timer);
-	phba->fcp_poll_timer.function = lpfc_poll_timeout;
-	phba->fcp_poll_timer.data = (unsigned long) phba;
+	setup_timer(&phba->fcp_poll_timer, lpfc_poll_timeout,
+			(unsigned long)phba);
 
 	/* Host attention work mask setup */
 	phba->work_ha_mask = (HA_ERATT | HA_MBATT | HA_LATT);
···
 
 	/* Initialize the host templates the configured values. */
 	lpfc_vport_template.sg_tablesize = phba->cfg_sg_seg_cnt;
-	lpfc_template_s3.sg_tablesize = phba->cfg_sg_seg_cnt;
+	lpfc_template_no_hr.sg_tablesize = phba->cfg_sg_seg_cnt;
+	lpfc_template.sg_tablesize = phba->cfg_sg_seg_cnt;
 
 	/* There are going to be 2 reserved BDEs: 1 FCP cmnd + 1 FCP rsp */
 	if (phba->cfg_enable_bg) {
···
 	 * Initialize timers used by driver
 	 */
 
-	init_timer(&phba->rrq_tmr);
-	phba->rrq_tmr.function = lpfc_rrq_timeout;
-	phba->rrq_tmr.data = (unsigned long)phba;
+	setup_timer(&phba->rrq_tmr, lpfc_rrq_timeout, (unsigned long)phba);
 
 	/* FCF rediscover timer */
-	init_timer(&phba->fcf.redisc_wait);
-	phba->fcf.redisc_wait.function = lpfc_sli4_fcf_redisc_wait_tmo;
-	phba->fcf.redisc_wait.data = (unsigned long)phba;
+	setup_timer(&phba->fcf.redisc_wait, lpfc_sli4_fcf_redisc_wait_tmo,
+			(unsigned long)phba);
 
 	/*
 	 * Control structure for handling external multi-buffer mailbox
···
 	/* Initialize the host templates with the updated values. */
 	lpfc_vport_template.sg_tablesize = phba->cfg_sg_seg_cnt;
 	lpfc_template.sg_tablesize = phba->cfg_sg_seg_cnt;
+	lpfc_template_no_hr.sg_tablesize = phba->cfg_sg_seg_cnt;
 
 	if (phba->cfg_sg_dma_buf_size  <= LPFC_MIN_SG_SLI4_BUF_SZ)
 		phba->cfg_sg_dma_buf_size = LPFC_MIN_SG_SLI4_BUF_SZ;
···
 		/* Initialize the Abort nvme buffer list used by driver */
 		spin_lock_init(&phba->sli4_hba.abts_nvme_buf_list_lock);
 		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvme_buf_list);
+		/* Fast-path XRI aborted CQ Event work queue list */
+		INIT_LIST_HEAD(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue);
 	}
 
 	/* This abort list used by worker thread */
···
 		}
 	}
 
-	/*
-	 * Configure EQ delay multipier for interrupt coalescing using
-	 * MODIFY_EQ_DELAY for all EQs created, LPFC_MAX_EQ_DELAY at a time.
-	 */
-	for (qidx = 0; qidx < io_channel; qidx += LPFC_MAX_EQ_DELAY)
+	for (qidx = 0; qidx < io_channel; qidx += LPFC_MAX_EQ_DELAY_EQID_CNT)
 		lpfc_modify_hba_eq_delay(phba, qidx);
+
 	return 0;
 
 out_destroy:
···
 	/* Pending ELS XRI abort events */
 	list_splice_init(&phba->sli4_hba.sp_els_xri_aborted_work_queue,
 			 &cqelist);
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
+		/* Pending NVME XRI abort events */
+		list_splice_init(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue,
+				 &cqelist);
+	}
 	/* Pending asynnc events */
 	list_splice_init(&phba->sli4_hba.sp_asynce_work_queue,
 			 &cqelist);
···
 	fc_remove_host(shost);
 	scsi_remove_host(shost);
 
-	/* Perform ndlp cleanup on the physical port.  The nvme and nvmet
-	 * localports are destroyed after to cleanup all transport memory.
-	 */
 	lpfc_cleanup(vport);
-	lpfc_nvmet_destroy_targetport(phba);
-	lpfc_nvme_destroy_localport(vport);
 
 	/*
 	 * Bring down the SLI Layer. This step disable all interrupts,
···
 	.id_table	= lpfc_id_table,
 	.probe		= lpfc_pci_probe_one,
 	.remove		= lpfc_pci_remove_one,
+	.shutdown	= lpfc_pci_remove_one,
 	.suspend        = lpfc_pci_suspend_one,
 	.resume		= lpfc_pci_resume_one,
 	.err_handler    = &lpfc_err_handler,

drivers/scsi/lpfc/lpfc_mem.c

···
 	}
 
 	dma_buf->iocbq = lpfc_sli_get_iocbq(phba);
-	dma_buf->iocbq->iocb_flag = LPFC_IO_NVMET;
 	if (!dma_buf->iocbq) {
 		kfree(dma_buf->context);
 		pci_pool_free(phba->lpfc_drb_pool, dma_buf->dbuf.virt,
···
 				"2621 Ran out of nvmet iocb/WQEs\n");
 		return NULL;
 	}
+	dma_buf->iocbq->iocb_flag = LPFC_IO_NVMET;
 	nvmewqe = dma_buf->iocbq;
 	wqe = (union lpfc_wqe128 *)&nvmewqe->wqe;
 	/* Initialize WQE */

drivers/scsi/lpfc/lpfc_nvme.c

···
 	bf_set(wqe_dfctl, &wqe->gen_req.wge_ctl, 0);
 	bf_set(wqe_si, &wqe->gen_req.wge_ctl, 1);
 	bf_set(wqe_la, &wqe->gen_req.wge_ctl, 1);
-	bf_set(wqe_rctl, &wqe->gen_req.wge_ctl, FC_RCTL_DD_UNSOL_CTL);
+	bf_set(wqe_rctl, &wqe->gen_req.wge_ctl, FC_RCTL_ELS4_REQ);
 	bf_set(wqe_type, &wqe->gen_req.wge_ctl, FC_TYPE_NVME);
 
 	/* Word 6 */
···
 	 * Embed the payload in the last half of the WQE
 	 * WQE words 16-30 get the NVME CMD IU payload
 	 *
-	 * WQE Word 16 is already setup with flags
-	 * WQE words 17-19 get payload Words 2-4
+	 * WQE words 16-19 get payload Words 1-4
 	 * WQE words 20-21 get payload Words 6-7
 	 * WQE words 22-29 get payload Words 16-23
 	 */
-	wptr = &wqe->words[17];  /* WQE ptr */
+	wptr = &wqe->words[16];  /* WQE ptr */
 	dptr = (uint32_t *)nCmd->cmdaddr;  /* payload ptr */
-	dptr += 2;		/* Skip Words 0-1 in payload */
+	dptr++;			/* Skip Word 0 in payload */
 
+	*wptr++ = *dptr++;	/* Word 1 */
 	*wptr++ = *dptr++;	/* Word 2 */
 	*wptr++ = *dptr++;	/* Word 3 */
 	*wptr++ = *dptr++;	/* Word 4 */
···
 			bf_set(wqe_cmd_type, &wqe->generic.wqe_com,
 			       NVME_WRITE_CMD);
 
-			/* Word 16 */
-			wqe->words[16] = LPFC_NVME_EMBED_WRITE;
-
 			phba->fc4NvmeOutputRequests++;
 		} else {
 			/* Word 7 */
···
 			bf_set(wqe_cmd_type, &wqe->generic.wqe_com,
 			       NVME_READ_CMD);
 
-			/* Word 16 */
-			wqe->words[16] = LPFC_NVME_EMBED_READ;
-
 			phba->fc4NvmeInputRequests++;
 		}
 	} else {
···
 
 		/* Word 11 */
 		bf_set(wqe_cmd_type, &wqe->generic.wqe_com, NVME_READ_CMD);
-
-		/* Word 16 */
-		wqe->words[16] = LPFC_NVME_EMBED_CMD;
 
 		phba->fc4NvmeControlRequests++;
 	}
···
 	pnvme_fcreq->private = (void *)lpfc_ncmd;
 	lpfc_ncmd->nvmeCmd = pnvme_fcreq;
 	lpfc_ncmd->nrport = rport;
+	lpfc_ncmd->ndlp = ndlp;
 	lpfc_ncmd->start_time = jiffies;
 
 	lpfc_nvme_prep_io_cmd(vport, lpfc_ncmd, ndlp);
···
 				 "sid: x%x did: x%x oxid: x%x\n",
 				 ret, vport->fc_myDID, ndlp->nlp_DID,
 				 lpfc_ncmd->cur_iocbq.sli4_xritag);
-		ret = -EINVAL;
+		ret = -EBUSY;
 		goto out_free_nvme_buf;
 	}
 
···
 						pdma_phys_sgl1, cur_xritag);
 				if (status) {
 					/* failure, put on abort nvme list */
-					lpfc_ncmd->exch_busy = 1;
+					lpfc_ncmd->flags |= LPFC_SBUF_XBUSY;
 				} else {
 					/* success, put on NVME buffer list */
-					lpfc_ncmd->exch_busy = 0;
+					lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
 					lpfc_ncmd->status = IOSTAT_SUCCESS;
 					num_posted++;
 				}
···
 					 struct lpfc_nvme_buf, list);
 			if (status) {
 				/* failure, put on abort nvme list */
-				lpfc_ncmd->exch_busy = 1;
+				lpfc_ncmd->flags |= LPFC_SBUF_XBUSY;
 			} else {
 				/* success, put on NVME buffer list */
-				lpfc_ncmd->exch_busy = 0;
+				lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
 				lpfc_ncmd->status = IOSTAT_SUCCESS;
 				num_posted++;
 			}
···
 	unsigned long iflag = 0;
 
 	lpfc_ncmd->nonsg_phys = 0;
-	if (lpfc_ncmd->exch_busy) {
+	if (lpfc_ncmd->flags & LPFC_SBUF_XBUSY) {
 		spin_lock_irqsave(&phba->sli4_hba.abts_nvme_buf_list_lock,
 					iflag);
 		lpfc_ncmd->nvmeCmd = NULL;
···
 int
 lpfc_nvme_create_localport(struct lpfc_vport *vport)
 {
+	int ret = 0;
 	struct lpfc_hba  *phba = vport->phba;
 	struct nvme_fc_port_info nfcp_info;
 	struct nvme_fc_local_port *localport;
 	struct lpfc_nvme_lport *lport;
-	int len, ret = 0;
+	int len;
 
 	/* Initialize this localport instance.  The vport wwn usage ensures
 	 * that NPIV is accounted for.
···
 	/* localport is allocated from the stack, but the registration
 	 * call allocates heap memory as well as the private area.
 	 */
+#ifdef CONFIG_LPFC_NVME_INITIATOR
 	ret = nvme_fc_register_localport(&nfcp_info, &lpfc_nvme_template,
 					 &vport->phba->pcidev->dev, &localport);
+#else
+	ret = -ENOMEM;
+#endif
 	if (!ret) {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME | LOG_NVME_DISC,
 				 "6005 Successfully registered local "
···
 		lport->vport = vport;
 		INIT_LIST_HEAD(&lport->rport_list);
 		vport->nvmei_support = 1;
+		len  = lpfc_new_nvme_buf(vport, phba->sli4_hba.nvme_xri_max);
+		vport->phba->total_nvme_bufs += len;
 	}
 
-	len  = lpfc_new_nvme_buf(vport, phba->sli4_hba.nvme_xri_max);
-	vport->phba->total_nvme_bufs += len;
 	return ret;
 }
 
···
 void
 lpfc_nvme_destroy_localport(struct lpfc_vport *vport)
 {
+#ifdef CONFIG_LPFC_NVME_INITIATOR
 	struct nvme_fc_local_port *localport;
 	struct lpfc_nvme_lport *lport;
 	struct lpfc_nvme_rport *rport = NULL, *rport_next = NULL;
···
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME,
 			 "6011 Destroying NVME localport %p\n",
 			 localport);
-
 	list_for_each_entry_safe(rport, rport_next, &lport->rport_list, list) {
 		/* The last node ref has to get released now before the rport
 		 * private memory area is released by the transport.
···
 					 "6008 rport fail destroy %x\n", ret);
 		wait_for_completion_timeout(&rport->rport_unreg_done, 5);
 	}
+
 	/* lport's rport list is clear.  Unregister
 	 * lport and release resources.
 	 */
···
 				 "Failed, status x%x\n",
 				 ret);
 	}
+#endif
 }
 
 void
···
 int
 lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 {
+#ifdef CONFIG_LPFC_NVME_INITIATOR
 	int ret = 0;
 	struct nvme_fc_local_port *localport;
 	struct lpfc_nvme_lport *lport;
···
 			rpinfo.port_role |= FC_PORT_ROLE_NVME_INITIATOR;
 		rpinfo.port_name = wwn_to_u64(ndlp->nlp_portname.u.wwn);
 		rpinfo.node_name = wwn_to_u64(ndlp->nlp_nodename.u.wwn);
-
 		ret = nvme_fc_register_remoteport(localport, &rpinfo,
 						  &remote_port);
 		if (!ret) {
···
 				 ndlp->nlp_type, ndlp->nlp_DID, ndlp);
 	}
 	return ret;
+#else
+	return 0;
+#endif
 }
 
 /* lpfc_nvme_unregister_port - unbind the DID and port_role from this rport.
···
 void
 lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 {
+#ifdef CONFIG_LPFC_NVME_INITIATOR
 	int ret;
 	struct nvme_fc_local_port *localport;
 	struct lpfc_nvme_lport *lport;
···
 	return;
 
  input_err:
+#endif
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
 			 "6168: State error: lport %p, rport%p FCID x%06x\n",
 			 vport->localport, ndlp->rport, ndlp->nlp_DID);
+}
+
+/**
+ * lpfc_sli4_nvme_xri_aborted - Fast-path process of NVME xri abort
+ * @phba: pointer to lpfc hba data structure.
+ * @axri: pointer to the fcp xri abort wcqe structure.
+ *
+ * This routine is invoked by the worker thread to process a SLI4 fast-path
+ * FCP aborted xri.
+ **/
+void
+lpfc_sli4_nvme_xri_aborted(struct lpfc_hba *phba,
+			   struct sli4_wcqe_xri_aborted *axri)
+{
+	uint16_t xri = bf_get(lpfc_wcqe_xa_xri, axri);
+	uint16_t rxid = bf_get(lpfc_wcqe_xa_remote_xid, axri);
+	struct lpfc_nvme_buf *lpfc_ncmd, *next_lpfc_ncmd;
+	struct lpfc_nodelist *ndlp;
+	unsigned long iflag = 0;
+	int rrq_empty = 0;
+
+	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
+		return;
+	spin_lock_irqsave(&phba->hbalock, iflag);
+	spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+	list_for_each_entry_safe(lpfc_ncmd, next_lpfc_ncmd,
+				 &phba->sli4_hba.lpfc_abts_nvme_buf_list,
+				 list) {
+		if (lpfc_ncmd->cur_iocbq.sli4_xritag == xri) {
+			list_del(&lpfc_ncmd->list);
+			lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
+			lpfc_ncmd->status = IOSTAT_SUCCESS;
+			spin_unlock(
+				&phba->sli4_hba.abts_nvme_buf_list_lock);
+
+			rrq_empty = list_empty(&phba->active_rrq_list);
+			spin_unlock_irqrestore(&phba->hbalock, iflag);
+			ndlp = lpfc_ncmd->ndlp;
+			if (ndlp) {
+				lpfc_set_rrq_active(
+					phba, ndlp,
+					lpfc_ncmd->cur_iocbq.sli4_lxritag,
+					rxid, 1);
+				lpfc_sli4_abts_err_handler(phba, ndlp, axri);
+			}
+			lpfc_release_nvme_buf(phba, lpfc_ncmd);
+			if (rrq_empty)
+				lpfc_worker_wake_up(phba);
+			return;
+		}
+	}
+	spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+	spin_unlock_irqrestore(&phba->hbalock, iflag);
 }

drivers/scsi/lpfc/lpfc_nvme.h

···
 	struct list_head list;
 	struct nvmefc_fcp_req *nvmeCmd;
 	struct lpfc_nvme_rport *nrport;
+	struct lpfc_nodelist *ndlp;
 
 	uint32_t timeout;
 

drivers/scsi/lpfc/lpfc_nvmet.c

···
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
 				"6102 Bad state IO x%x aborted\n",
 				ctxp->oxid);
+		rc = -ENXIO;
 		goto aerr;
 	}
 
···
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
 				"6152 FCP Drop IO x%x: Prep\n",
 				ctxp->oxid);
+		rc = -ENXIO;
 		goto aerr;
 	}
 
···
 	ctxp->wqeq->hba_wqidx = 0;
 	nvmewqeq->context2 = NULL;
 	nvmewqeq->context3 = NULL;
+	rc = -EBUSY;
 aerr:
-	return -ENXIO;
+	return rc;
 }
 
 static void
···
 	lpfc_tgttemplate.target_features = NVMET_FCTGTFEAT_READDATA_RSP |
 					   NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED;
 
+#ifdef CONFIG_LPFC_NVME_TARGET
 	error = nvmet_fc_register_targetport(&pinfo, &lpfc_tgttemplate,
 					     &phba->pcidev->dev,
 					     &phba->targetport);
+#else
+	error = -ENOMEM;
+#endif
 	if (error) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
 				"6025 Cannot register NVME targetport "
···
 	return 0;
 }
 
+/**
+ * lpfc_sli4_nvmet_xri_aborted - Fast-path process of nvmet xri abort
+ * @phba: pointer to lpfc hba data structure.
+ * @axri: pointer to the nvmet xri abort wcqe structure.
+ *
+ * This routine is invoked by the worker thread to process a SLI4 fast-path
+ * NVMET aborted xri.
+ **/
+void
+lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba,
+			    struct sli4_wcqe_xri_aborted *axri)
+{
+	/* TODO: work in progress */
+}
+
 void
 lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba)
 {
+#ifdef CONFIG_LPFC_NVME_TARGET
 	struct lpfc_nvmet_tgtport *tgtp;
 
 	if (phba->nvmet_support == 0)
···
 		wait_for_completion_timeout(&tgtp->tport_unreg_done, 5);
 	}
 	phba->targetport = NULL;
+#endif
 }
 
 /**
···
 lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			   struct hbq_dmabuf *nvmebuf)
 {
+#ifdef CONFIG_LPFC_NVME_TARGET
 	struct lpfc_nvmet_tgtport *tgtp;
 	struct fc_frame_header *fc_hdr;
 	struct lpfc_nvmet_rcv_ctx *ctxp;
···
 
 	atomic_inc(&tgtp->xmt_ls_abort);
 	lpfc_nvmet_unsol_ls_issue_abort(phba, ctxp, sid, oxid);
+#endif
 }
 
 /**
···
 			    struct rqb_dmabuf *nvmebuf,
 			    uint64_t isr_timestamp)
 {
+#ifdef CONFIG_LPFC_NVME_TARGET
 	struct lpfc_nvmet_rcv_ctx *ctxp;
 	struct lpfc_nvmet_tgtport *tgtp;
 	struct fc_frame_header *fc_hdr;
···
 
 	atomic_inc(&tgtp->rcv_fcp_cmd_drop);
 	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-			"6159 FCP Drop IO x%x: nvmet_fc_rcv_fcp_req x%x\n",
+			"6159 FCP Drop IO x%x: err x%x\n",
 			ctxp->oxid, rc);
 dropit:
 	lpfc_nvmeio_data(phba, "NVMET FCP DROP: xri x%x sz %d from %06x\n",
···
 		/* We assume a rcv'ed cmd ALWAYs fits into 1 buffer */
 		lpfc_nvmet_rq_post(phba, NULL, &nvmebuf->hbuf);
 	}
+#endif
 }
 
 /**
···
 	bf_set(wqe_dfctl, &wqe->xmit_sequence.wge_ctl, 0);
 	bf_set(wqe_ls, &wqe->xmit_sequence.wge_ctl, 1);
 	bf_set(wqe_la, &wqe->xmit_sequence.wge_ctl, 0);
-	bf_set(wqe_rctl, &wqe->xmit_sequence.wge_ctl, FC_RCTL_DD_SOL_CTL);
+	bf_set(wqe_rctl, &wqe->xmit_sequence.wge_ctl, FC_RCTL_ELS4_REP);
 	bf_set(wqe_type, &wqe->xmit_sequence.wge_ctl, FC_TYPE_NVME);
 
 	/* Word 6 */
···
 
 	case NVMET_FCOP_RSP:
 		/* Words 0 - 2 */
-		sgel = &rsp->sg[0];
 		physaddr = rsp->rspdma;
 		wqe->fcp_trsp.bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
 		wqe->fcp_trsp.bde.tus.f.bdeSize = rsp->rsplen;
···
 	struct lpfc_nodelist *ndlp;
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
-			"6067 %s: Entrypoint: sid %x xri %x\n", __func__,
-			sid, xri);
+			"6067 Abort: sid %x xri x%x/x%x\n",
+			sid, xri, ctxp->wqeq->sli4_xritag);
 
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
 
···
 		atomic_inc(&tgtp->xmt_abort_rsp_error);
 		lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
 				"6134 Drop ABTS - wrong NDLP state x%x.\n",
-				ndlp->nlp_state);
+				(ndlp) ? ndlp->nlp_state : NLP_STE_MAX_STATE);
 
 		/* No failure to an ABTS request. */
 		return 0;
···
 		atomic_inc(&tgtp->xmt_abort_rsp_error);
 		lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
 				"6160 Drop ABTS - wrong NDLP state x%x.\n",
-				ndlp->nlp_state);
+				(ndlp) ? ndlp->nlp_state : NLP_STE_MAX_STATE);
 
 		/* No failure to an ABTS request. */
 		return 0;

drivers/scsi/lpfc/lpfc_scsi.c

···
 	.track_queue_depth	= 0,
 };
 
-struct scsi_host_template lpfc_template_s3 = {
+struct scsi_host_template lpfc_template_no_hr = {
 	.module			= THIS_MODULE,
 	.name			= LPFC_DRIVER_NAME,
 	.proc_name		= LPFC_DRIVER_NAME,
 	.info			= lpfc_info,
 	.queuecommand		= lpfc_queuecommand,
+	.eh_timed_out		= fc_eh_timed_out,
 	.eh_abort_handler	= lpfc_abort_handler,
 	.eh_device_reset_handler = lpfc_device_reset_handler,
 	.eh_target_reset_handler = lpfc_target_reset_handler,
···
 	.eh_abort_handler	= lpfc_abort_handler,
 	.eh_device_reset_handler = lpfc_device_reset_handler,
 	.eh_target_reset_handler = lpfc_target_reset_handler,
-	.eh_bus_reset_handler	= lpfc_bus_reset_handler,
 	.slave_alloc		= lpfc_slave_alloc,
 	.slave_configure	= lpfc_slave_configure,
 	.slave_destroy		= lpfc_slave_destroy,

drivers/scsi/lpfc/lpfc_sli.c

···
+
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
···
 	start_sglq = sglq;
 	while (!found) {
 		if (!sglq)
-			return NULL;
+			break;
 		if (ndlp && ndlp->active_rrqs_xri_bitmap &&
 		    test_bit(sglq->sli4_lxritag,
 		    ndlp->active_rrqs_xri_bitmap)) {
···
 }
 
 /**
+ * lpfc_sli4_nvme_xri_abort_event_proc - Process nvme xri abort event
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine is invoked by the worker thread to process all the pending
+ * SLI4 NVME abort XRI events.
+ **/
+void lpfc_sli4_nvme_xri_abort_event_proc(struct lpfc_hba *phba)
+{
+	struct lpfc_cq_event *cq_event;
+
+	/* First, declare the fcp xri abort event has been handled */
+	spin_lock_irq(&phba->hbalock);
+	phba->hba_flag &= ~NVME_XRI_ABORT_EVENT;
+	spin_unlock_irq(&phba->hbalock);
+	/* Now, handle all the fcp xri abort events */
+	while (!list_empty(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue)) {
+		/* Get the first event from the head of the event queue */
+		spin_lock_irq(&phba->hbalock);
+		list_remove_head(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue,
+				 cq_event, struct lpfc_cq_event, list);
+		spin_unlock_irq(&phba->hbalock);
+		/* Notify aborted XRI for NVME work queue */
+		if (phba->nvmet_support) {
+			lpfc_sli4_nvmet_xri_aborted(phba,
+						    &cq_event->cqe.wcqe_axri);
+		} else {
+			lpfc_sli4_nvme_xri_aborted(phba,
+						   &cq_event->cqe.wcqe_axri);
+		}
+		/* Free the event processed back to the free pool */
+		lpfc_sli4_cq_event_release(phba, cq_event);
+	}
+}
+
+/**
  * lpfc_sli4_els_xri_abort_event_proc - Process els xri abort event
  * @phba: pointer to lpfc hba data structure.
  *
···
 		spin_unlock_irqrestore(&phba->hbalock, iflags);
 		workposted = true;
 		break;
+	case LPFC_NVME:
+		spin_lock_irqsave(&phba->hbalock, iflags);
+		list_add_tail(&cq_event->list,
+			      &phba->sli4_hba.sp_nvme_xri_aborted_work_queue);
+		/* Set the nvme xri abort event flag */
+		phba->hba_flag |= NVME_XRI_ABORT_EVENT;
+		spin_unlock_irqrestore(&phba->hbalock, iflags);
+		workposted = true;
+		break;
 	default:
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
-				"0603 Invalid work queue CQE subtype (x%x)\n",
-				cq->subtype);
+				"0603 Invalid CQ subtype %d: "
+				"%08x %08x %08x %08x\n",
+				cq->subtype, wcqe->word0, wcqe->parameter,
+				wcqe->word2, wcqe->word3);
+		lpfc_sli4_cq_event_release(phba, cq_event);
 		workposted = false;
 		break;
 	}
···
  * @startq: The starting FCP EQ to modify
  *
  * This function sends an MODIFY_EQ_DELAY mailbox command to the HBA.
+ * The command allows up to LPFC_MAX_EQ_DELAY_EQID_CNT EQ ID's to be
+ * updated in one mailbox command.
  *
  * The @phba struct is used to send mailbox command to HBA. The @startq
  * is used to get the starting FCP EQ to change.
···
 		eq_delay->u.request.eq[cnt].phase = 0;
 		eq_delay->u.request.eq[cnt].delay_multi = dmult;
 		cnt++;
-		if (cnt >= LPFC_MAX_EQ_DELAY)
+		if (cnt >= LPFC_MAX_EQ_DELAY_EQID_CNT)
 			break;
 	}
 	eq_delay->u.request.num_eq = cnt;
···
 		drq = drqp[idx];
 		cq  = cqp[idx];
 
-		if (hrq->entry_count != drq->entry_count) {
-			status = -EINVAL;
-			goto out;
-		}
-
 		/* sanity check on queue memory */
 		if (!hrq || !drq || !cq) {
 			status = -ENODEV;
+			goto out;
+		}
+
+		if (hrq->entry_count != drq->entry_count) {
+			status = -EINVAL;
 			goto out;
 		}
 

drivers/scsi/lpfc/lpfc_sli4.h

···
 	struct list_head sp_asynce_work_queue;
 	struct list_head sp_fcp_xri_aborted_work_queue;
 	struct list_head sp_els_xri_aborted_work_queue;
+	struct list_head sp_nvme_xri_aborted_work_queue;
 	struct list_head sp_unsol_work_queue;
 	struct lpfc_sli4_link link_state;
 	struct lpfc_sli4_lnk_info lnk_info;
···
 int lpfc_sli4_resume_rpi(struct lpfc_nodelist *,
 			void (*)(struct lpfc_hba *, LPFC_MBOXQ_t *), void *);
 void lpfc_sli4_fcp_xri_abort_event_proc(struct lpfc_hba *);
+void lpfc_sli4_nvme_xri_abort_event_proc(struct lpfc_hba *phba);
 void lpfc_sli4_els_xri_abort_event_proc(struct lpfc_hba *);
 void lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *,
 			       struct sli4_wcqe_xri_aborted *);
+void lpfc_sli4_nvme_xri_aborted(struct lpfc_hba *phba,
+				struct sli4_wcqe_xri_aborted *axri);
+void lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba,
+				 struct sli4_wcqe_xri_aborted *axri);
 void lpfc_sli4_els_xri_aborted(struct lpfc_hba *,
 			       struct sli4_wcqe_xri_aborted *);
 void lpfc_sli4_vport_delete_els_xri_aborted(struct lpfc_vport *);

drivers/scsi/lpfc/lpfc_version.h

···
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "11.2.0.7"
+#define LPFC_DRIVER_VERSION "11.2.0.10"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */

drivers/scsi/mpt3sas/mpt3sas_base.h

···
 	u64 sas_address, u16 handle, u8 phy_number, u8 link_rate);
 extern struct sas_function_template mpt3sas_transport_functions;
 extern struct scsi_transport_template *mpt3sas_transport_template;
-extern int scsi_internal_device_block(struct scsi_device *sdev);
-extern int scsi_internal_device_unblock(struct scsi_device *sdev,
-				enum scsi_device_state new_state);
 /* trigger data externs */
 void mpt3sas_send_trigger_data_event(struct MPT3SAS_ADAPTER *ioc,
 	struct SL_WH_TRIGGERS_EVENT_DATA_T *event_data);

drivers/scsi/mpt3sas/mpt3sas_scsih.c

···
 	    sas_device_priv_data->sas_target->handle);
 	sas_device_priv_data->block = 1;
 
-	r = scsi_internal_device_block(sdev);
+	r = scsi_internal_device_block(sdev, false);
 	if (r == -EINVAL)
 		sdev_printk(KERN_WARNING, sdev,
 		    "device_block failed with return(%d) for handle(0x%04x)\n",
···
 		    "performing a block followed by an unblock\n",
 		    r, sas_device_priv_data->sas_target->handle);
 		sas_device_priv_data->block = 1;
-		r = scsi_internal_device_block(sdev);
+		r = scsi_internal_device_block(sdev, false);
 		if (r)
 			sdev_printk(KERN_WARNING, sdev, "retried device_block "
 			    "failed with return(%d) for handle(0x%04x)\n",
···
 	struct MPT3SAS_DEVICE *sas_device_priv_data;
 	u32 response_code = 0;
 	unsigned long flags;
-	unsigned int sector_sz;
 
 	mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply);
 
···
 	}
 
 	xfer_cnt = le32_to_cpu(mpi_reply->TransferCount);
-
-	/* In case of bogus fw or device, we could end up having
-	 * unaligned partial completion. We can force alignment here,
-	 * then scsi-ml does not need to handle this misbehavior.
-	 */
-	sector_sz = scmd->device->sector_size;
-	if (unlikely(!blk_rq_is_passthrough(scmd->request) && sector_sz &&
-		     xfer_cnt % sector_sz)) {
-		sdev_printk(KERN_INFO, scmd->device,
-		    "unaligned partial completion avoided (xfer_cnt=%u, sector_sz=%u)\n",
-			    xfer_cnt, sector_sz);
-		xfer_cnt = round_down(xfer_cnt, sector_sz);
-	}
-
 	scsi_set_resid(scmd, scsi_bufflen(scmd) - xfer_cnt);
 	if (ioc_status & MPI2_IOCSTATUS_FLAG_LOG_INFO_AVAILABLE)
 		log_info =  le32_to_cpu(mpi_reply->IOCLogInfo);

drivers/scsi/qedf/qedf_dbg.h

···
 #define QEDF_INFO(pdev, level, fmt, ...)	\
 		qedf_dbg_info(pdev, __func__, __LINE__, level, fmt,	\
 			      ## __VA_ARGS__)
-
-extern void qedf_dbg_err(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+__printf(4, 5)
+void qedf_dbg_err(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
 			  const char *fmt, ...);
-extern void qedf_dbg_warn(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+__printf(4, 5)
+void qedf_dbg_warn(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
 			   const char *, ...);
-extern void qedf_dbg_notice(struct qedf_dbg_ctx *qedf, const char *func,
+__printf(4, 5)
+void qedf_dbg_notice(struct qedf_dbg_ctx *qedf, const char *func,
 			    u32 line, const char *, ...);
-extern void qedf_dbg_info(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+__printf(5, 6)
+void qedf_dbg_info(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
 			  u32 info, const char *fmt, ...);
 
 /* GRC Dump related defines */

drivers/scsi/qedf/qedf_fip.c

···
 			case FIP_DT_MAC:
 				mp = (struct fip_mac_desc *)desc;
 				QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2,
-				    "fd_mac=%pM.\n", __func__, mp->fd_mac);
+				    "fd_mac=%pM\n", mp->fd_mac);
 				ether_addr_copy(cvl_mac, mp->fd_mac);
 				break;
 			case FIP_DT_NAME:

drivers/scsi/qedf/qedf_io.c

···
 		} else {
 			refcount = kref_read(&io_req->refcount);
 			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
-			    "%d:0:%d:%d xid=0x%0x op=0x%02x "
+			    "%d:0:%d:%lld xid=0x%0x op=0x%02x "
 			    "lba=%02x%02x%02x%02x cdb_status=%d "
 			    "fcp_resid=0x%x refcount=%d.\n",
 			    qedf->lport->host->host_no, sc_cmd->device->id,
···
 
 	sc_cmd->result = result << 16;
 	refcount = kref_read(&io_req->refcount);
-	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "%d:0:%d:%d: Completing "
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "%d:0:%d:%lld: Completing "
 	    "sc_cmd=%p result=0x%08x op=0x%02x lba=0x%02x%02x%02x%02x, "
 	    "allowed=%d retries=%d refcount=%d.\n",
 	    qedf->lport->host->host_no, sc_cmd->device->id,

drivers/scsi/qedf/qedf_main.c

···
 	}
 
 	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
-	    "BDQ PBL addr=0x%p dma=0x%llx.\n", qedf->bdq_pbl,
-	    qedf->bdq_pbl_dma);
+		  "BDQ PBL addr=0x%p dma=%pad\n",
+		  qedf->bdq_pbl, &qedf->bdq_pbl_dma);
 
 	/*
 	 * Populate BDQ PBL with physical and virtual address of individual

drivers/scsi/qedi/qedi_debugfs.c

···
 #include <linux/debugfs.h>
 #include <linux/module.h>
 
-int do_not_recover;
+int qedi_do_not_recover;
 static struct dentry *qedi_dbg_root;
 
 void
···
 static ssize_t
 qedi_dbg_do_not_recover_enable(struct qedi_dbg_ctx *qedi_dbg)
 {
-	if (!do_not_recover)
-		do_not_recover = 1;
+	if (!qedi_do_not_recover)
+		qedi_do_not_recover = 1;
 
 	QEDI_INFO(qedi_dbg, QEDI_LOG_DEBUGFS, "do_not_recover=%d\n",
-		  do_not_recover);
+		  qedi_do_not_recover);
 	return 0;
 }
 
 static ssize_t
 qedi_dbg_do_not_recover_disable(struct qedi_dbg_ctx *qedi_dbg)
 {
-	if (do_not_recover)
-		do_not_recover = 0;
+	if (qedi_do_not_recover)
+		qedi_do_not_recover = 0;
 
 	QEDI_INFO(qedi_dbg, QEDI_LOG_DEBUGFS, "do_not_recover=%d\n",
-		  do_not_recover);
+		  qedi_do_not_recover);
 	return 0;
 }
 
···
 	if (*ppos)
 		return 0;
 
-	cnt = sprintf(buffer, "do_not_recover=%d\n", do_not_recover);
+	cnt = sprintf(buffer, "do_not_recover=%d\n", qedi_do_not_recover);
 	cnt = min_t(int, count, cnt - *ppos);
 	*ppos += cnt;
 	return cnt;

drivers/scsi/qedi/qedi_fw.c

···
 		  get_itt(tmf_hdr->rtt), get_itt(ctask->itt), cmd->task_id,
 		  qedi_conn->iscsi_conn_id);
 
-	if (do_not_recover) {
+	if (qedi_do_not_recover) {
 		QEDI_ERR(&qedi->dbg_ctx, "DONT SEND CLEANUP/ABORT %d\n",
-			 do_not_recover);
+			 qedi_do_not_recover);
 		goto abort_ret;
 	}
 

drivers/scsi/qedi/qedi_gbl.h

···
 
 #include "qedi_iscsi.h"
 
+#ifdef CONFIG_DEBUG_FS
+extern int qedi_do_not_recover;
+#else
+#define qedi_do_not_recover (0)
+#endif
+
 extern uint qedi_io_tracing;
-extern int do_not_recover;
+
 extern struct scsi_host_template qedi_host_template;
 extern struct iscsi_transport qedi_iscsi_transport;
 extern const struct qed_iscsi_ops *qedi_ops;

drivers/scsi/qedi/qedi_iscsi.c

···
 		return ERR_PTR(ret);
 	}
 
-	if (do_not_recover) {
+	if (qedi_do_not_recover) {
 		ret = -ENOMEM;
 		return ERR_PTR(ret);
 	}
···
 	struct qedi_endpoint *qedi_ep;
 	int ret = 0;
 
-	if (do_not_recover)
+	if (qedi_do_not_recover)
 		return 1;
 
 	qedi_ep = ep->dd_data;
···
 		}
 
 		if (test_bit(QEDI_IN_RECOVERY, &qedi->flags)) {
-			if (do_not_recover) {
+			if (qedi_do_not_recover) {
 				QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
 					  "Do not recover cid=0x%x\n",
 					  qedi_ep->iscsi_cid);
···
 		}
 	}
 
-	if (do_not_recover)
+	if (qedi_do_not_recover)
 		goto ep_exit_recover;
 
 	switch (qedi_ep->state) {

drivers/scsi/qedi/qedi_main.c

···
 	 */
 	qedi_ops->common->update_pf_params(qedi->cdev, &qedi->pf_params);
 
-	qedi_setup_int(qedi);
+	rc = qedi_setup_int(qedi);
 	if (rc)
 		goto stop_iscsi_func;
 

drivers/scsi/qla2xxx/qla_dbg.c

···
 	    "%-+5d  0  1  2  3  4  5  6  7  8  9  A  B  C  D  E  F\n", size);
 	ql_dbg(level, vha, id,
 	    "----- -----------------------------------------------\n");
-	for (cnt = 0; cnt < size; cnt++, buf++) {
-		if (cnt % 16 == 0)
-			ql_dbg(level, vha, id, "%04x:", cnt & ~0xFU);
-		printk(" %02x", *buf);
-		if (cnt % 16 == 15)
-			printk("\n");
+	for (cnt = 0; cnt < size; cnt += 16) {
+		ql_dbg(level, vha, id, "%04x: ", cnt);
+		print_hex_dump(KERN_CONT, "", DUMP_PREFIX_NONE, 16, 1,
+			       buf + cnt, min(16U, size - cnt), false);
 	}
-	if (cnt % 16 != 0)
-		printk("\n");
 }

drivers/scsi/scsi_lib.c

···
 /**
  * scsi_internal_device_block - internal function to put a device temporarily into the SDEV_BLOCK state
  * @sdev:	device to block
+ * @wait:	Whether or not to wait until ongoing .queuecommand() /
+ *		.queue_rq() calls have finished.
  *
  * Block request made by scsi lld's to temporarily stop all
  * scsi commands on the specified device. May sleep.
···
  * remove the rport mutex lock and unlock calls from srp_queuecommand().
  */
 int
-scsi_internal_device_block(struct scsi_device *sdev)
+scsi_internal_device_block(struct scsi_device *sdev, bool wait)
 {
 	struct request_queue *q = sdev->request_queue;
 	unsigned long flags;
···
 	 * request queue. 
 	 */
 	if (q->mq_ops) {
-		blk_mq_quiesce_queue(q);
+		if (wait)
+			blk_mq_quiesce_queue(q);
+		else
+			blk_mq_stop_hw_queues(q);
 	} else {
 		spin_lock_irqsave(q->queue_lock, flags);
 		blk_stop_queue(q);
 		spin_unlock_irqrestore(q->queue_lock, flags);
-		scsi_wait_for_queuecommand(sdev);
+		if (wait)
+			scsi_wait_for_queuecommand(sdev);
 	}
 
 	return 0;
···
 static void
 device_block(struct scsi_device *sdev, void *data)
 {
-	scsi_internal_device_block(sdev);
+	scsi_internal_device_block(sdev, true);
 }
 
 static int

drivers/scsi/scsi_priv.h

···
  */
 
 #define SCSI_DEVICE_BLOCK_MAX_TIMEOUT	600	/* units in seconds */
-extern int scsi_internal_device_block(struct scsi_device *sdev);
-extern int scsi_internal_device_unblock(struct scsi_device *sdev,
-					enum scsi_device_state new_state);
 
 #endif /* _SCSI_PRIV_H */

drivers/scsi/sd.c

···
 {
 	int result = SCpnt->result;
 	unsigned int good_bytes = result ? 0 : scsi_bufflen(SCpnt);
+	unsigned int sector_size = SCpnt->device->sector_size;
+	unsigned int resid;
 	struct scsi_sense_hdr sshdr;
 	struct scsi_disk *sdkp = scsi_disk(SCpnt->request->rq_disk);
 	struct request *req = SCpnt->request;
···
 			scsi_set_resid(SCpnt, blk_rq_bytes(req));
 		}
 		break;
+	default:
+		/*
+		 * In case of bogus fw or device, we could end up having
+		 * an unaligned partial completion. Check this here and force
+		 * alignment.
+		 */
+		resid = scsi_get_resid(SCpnt);
+		if (resid & (sector_size - 1)) {
+			sd_printk(KERN_INFO, sdkp,
+				"Unaligned partial completion (resid=%u, sector_sz=%u)\n",
+				resid, sector_size);
+			resid = min(scsi_bufflen(SCpnt),
+				    round_up(resid, sector_size));
+			scsi_set_resid(SCpnt, resid);
+		}
 	}
 
 	if (result) {

drivers/scsi/storvsc_drv.c

···
  */
 static int storvsc_timeout = 180;
 
-static int msft_blist_flags = BLIST_TRY_VPD_PAGES;
-
 #if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
 static struct scsi_transport_template *fc_transport_template;
 #endif
···
 	return ret;
 }
 
+static int storvsc_device_alloc(struct scsi_device *sdevice)
+{
+	/*
+	 * Set blist flag to permit the reading of the VPD pages even when
+	 * the target may claim SPC-2 compliance. MSFT targets currently
+	 * claim SPC-2 compliance while they implement post SPC-2 features.
+	 * With this flag we can correctly handle WRITE_SAME_16 issues.
+	 *
+	 * Hypervisor reports SCSI_UNKNOWN type for DVD ROM device but
+	 * still supports REPORT LUN.
+	 */
+	sdevice->sdev_bflags = BLIST_REPORTLUN2 | BLIST_TRY_VPD_PAGES;
+
+	return 0;
+}
+
 static int storvsc_device_configure(struct scsi_device *sdevice)
 {
 
···
 	blk_queue_virt_boundary(sdevice->request_queue, PAGE_SIZE - 1);
 
 	sdevice->no_write_same = 1;
-
-	/*
-	 * Add blist flags to permit the reading of the VPD pages even when
-	 * the target may claim SPC-2 compliance. MSFT targets currently
-	 * claim SPC-2 compliance while they implement post SPC-2 features.
-	 * With this patch we can correctly handle WRITE_SAME_16 issues.
-	 */
-	sdevice->sdev_bflags |= msft_blist_flags;
 
 	/*
 	 * If the host is WIN8 or WIN8 R2, claim conformance to SPC-3
···
 	.eh_host_reset_handler =	storvsc_host_reset_handler,
 	.proc_name =		"storvsc_host",
 	.eh_timed_out =		storvsc_eh_timed_out,
+	.slave_alloc =		storvsc_device_alloc,
 	.slave_configure =	storvsc_device_configure,
 	.cmd_per_lun =		255,
 	.this_id =		-1,

drivers/scsi/ufs/ufs.h

···
 /* Descriptor idn for Query requests */
 enum desc_idn {
 	QUERY_DESC_IDN_DEVICE		= 0x0,
-	QUERY_DESC_IDN_CONFIGURAION	= 0x1,
+	QUERY_DESC_IDN_CONFIGURATION	= 0x1,
 	QUERY_DESC_IDN_UNIT		= 0x2,
 	QUERY_DESC_IDN_RFU_0		= 0x3,
 	QUERY_DESC_IDN_INTERCONNECT	= 0x4,
···
 	QUERY_DESC_DESC_TYPE_OFFSET	= 0x01,
 };
 
-enum ufs_desc_max_size {
-	QUERY_DESC_DEVICE_MAX_SIZE		= 0x40,
-	QUERY_DESC_CONFIGURAION_MAX_SIZE	= 0x90,
-	QUERY_DESC_UNIT_MAX_SIZE		= 0x23,
-	QUERY_DESC_INTERCONNECT_MAX_SIZE	= 0x06,
-	/*
-	 * Max. 126 UNICODE characters (2 bytes per character) plus 2 bytes
-	 * of descriptor header.
-	 */
-	QUERY_DESC_STRING_MAX_SIZE		= 0xFE,
-	QUERY_DESC_GEOMETRY_MAX_SIZE		= 0x44,
-	QUERY_DESC_POWER_MAX_SIZE		= 0x62,
-	QUERY_DESC_RFU_MAX_SIZE			= 0x00,
+enum ufs_desc_def_size {
+	QUERY_DESC_DEVICE_DEF_SIZE		= 0x40,
+	QUERY_DESC_CONFIGURATION_DEF_SIZE	= 0x90,
+	QUERY_DESC_UNIT_DEF_SIZE		= 0x23,
+	QUERY_DESC_INTERCONNECT_DEF_SIZE	= 0x06,
+	QUERY_DESC_GEOMETRY_DEF_SIZE		= 0x44,
+	QUERY_DESC_POWER_DEF_SIZE		= 0x62,
 };
 
 /* Unit descriptor parameters offsets in bytes*/

drivers/scsi/ufs/ufshcd.c

···
 #define ufshcd_hex_dump(prefix_str, buf, len) \
 print_hex_dump(KERN_ERR, prefix_str, DUMP_PREFIX_OFFSET, 16, 4, buf, len, false)
 
-static u32 ufs_query_desc_max_size[] = {
-	QUERY_DESC_DEVICE_MAX_SIZE,
-	QUERY_DESC_CONFIGURAION_MAX_SIZE,
-	QUERY_DESC_UNIT_MAX_SIZE,
-	QUERY_DESC_RFU_MAX_SIZE,
-	QUERY_DESC_INTERCONNECT_MAX_SIZE,
-	QUERY_DESC_STRING_MAX_SIZE,
-	QUERY_DESC_RFU_MAX_SIZE,
-	QUERY_DESC_GEOMETRY_MAX_SIZE,
-	QUERY_DESC_POWER_MAX_SIZE,
-	QUERY_DESC_RFU_MAX_SIZE,
-};
-
 enum {
 	UFSHCD_MAX_CHANNEL	= 0,
 	UFSHCD_MAX_ID		= 1,
···
 		goto out;
 	}
 
-	if (*buf_len <= QUERY_DESC_MIN_SIZE || *buf_len > QUERY_DESC_MAX_SIZE) {
+	if (*buf_len < QUERY_DESC_MIN_SIZE || *buf_len > QUERY_DESC_MAX_SIZE) {
 		dev_err(hba->dev, "%s: descriptor buffer size (%d) is out of range\n",
 				__func__, *buf_len);
 		err = -EINVAL;
···
 }
 
 /**
+ * ufshcd_read_desc_length - read the specified descriptor length from header
+ * @hba: Pointer to adapter instance
+ * @desc_id: descriptor idn value
+ * @desc_index: descriptor index
+ * @desc_length: pointer to variable to read the length of descriptor
+ *
+ * Return 0 in case of success, non-zero otherwise
+ */
+static int ufshcd_read_desc_length(struct ufs_hba *hba,
+	enum desc_idn desc_id,
+	int desc_index,
+	int *desc_length)
+{
+	int ret;
+	u8 header[QUERY_DESC_HDR_SIZE];
+	int header_len = QUERY_DESC_HDR_SIZE;
+
+	if (desc_id >= QUERY_DESC_IDN_MAX)
+		return -EINVAL;
+
+	ret = ufshcd_query_descriptor_retry(hba, UPIU_QUERY_OPCODE_READ_DESC,
+					desc_id, desc_index, 0, header,
+					&header_len);
+
+	if (ret) {
+		dev_err(hba->dev, "%s: Failed to get descriptor header id %d",
+			__func__, desc_id);
+		return ret;
+	} else if (desc_id != header[QUERY_DESC_DESC_TYPE_OFFSET]) {
+		dev_warn(hba->dev, "%s: descriptor header id %d and desc_id %d mismatch",
+			__func__, header[QUERY_DESC_DESC_TYPE_OFFSET],
+			desc_id);
+		ret = -EINVAL;
+	}
+
+	*desc_length = header[QUERY_DESC_LENGTH_OFFSET];
+	return ret;
+
+}
+
+/**
+ * ufshcd_map_desc_id_to_length - map descriptor IDN to its length
+ * @hba: Pointer to adapter instance
+ * @desc_id: descriptor idn value
+ * @desc_len: mapped desc length (out)
+ *
+ * Return 0 in case of success, non-zero otherwise
+ */
+int ufshcd_map_desc_id_to_length(struct ufs_hba *hba,
+	enum desc_idn desc_id, int *desc_len)
+{
+	switch (desc_id) {
+	case QUERY_DESC_IDN_DEVICE:
+		*desc_len = hba->desc_size.dev_desc;
+		break;
+	case QUERY_DESC_IDN_POWER:
+		*desc_len = hba->desc_size.pwr_desc;
+		break;
+	case QUERY_DESC_IDN_GEOMETRY:
+		*desc_len = hba->desc_size.geom_desc;
+		break;
+	case QUERY_DESC_IDN_CONFIGURATION:
+		*desc_len = hba->desc_size.conf_desc;
+		break;
+	case QUERY_DESC_IDN_UNIT:
+		*desc_len = hba->desc_size.unit_desc;
+		break;
+	case QUERY_DESC_IDN_INTERCONNECT:
+		*desc_len = hba->desc_size.interc_desc;
+		break;
+	case QUERY_DESC_IDN_STRING:
+		*desc_len = QUERY_DESC_MAX_SIZE;
+		break;
+	case QUERY_DESC_IDN_RFU_0:
+	case QUERY_DESC_IDN_RFU_1:
+		*desc_len = 0;
+		break;
+	default:
+		*desc_len = 0;
+		return -EINVAL;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ufshcd_map_desc_id_to_length);
+
+/**
  * ufshcd_read_desc_param - read the specified descriptor parameter
  * @hba: Pointer to adapter instance
  * @desc_id: descriptor idn value
···
 static int ufshcd_read_desc_param(struct ufs_hba *hba,
 				  enum desc_idn desc_id,
 				  int desc_index,
-				  u32 param_offset,
+				  u8 param_offset,
 				  u8 *param_read_buf,
-				  u32 param_size)
+				  u8 param_size)
 {
 	int ret;
 	u8 *desc_buf;
-	u32 buff_len;
+	int buff_len;
 	bool is_kmalloc = true;
 
-	/* safety checks */
-	if (desc_id >= QUERY_DESC_IDN_MAX)
+	/* Safety check */
+	if (desc_id >= QUERY_DESC_IDN_MAX || !param_size)
 		return -EINVAL;
 
-	buff_len = ufs_query_desc_max_size[desc_id];
-	if ((param_offset + param_size) > buff_len)
-		return -EINVAL;
+	/* Get the max length of descriptor from structure filled up at probe
+	 * time.
+	 */
+	ret = ufshcd_map_desc_id_to_length(hba, desc_id, &buff_len);
 
-	if (!param_offset && (param_size == buff_len)) {
-		/* memory space already available to hold full descriptor */
-		desc_buf = param_read_buf;
-		is_kmalloc = false;
-	} else {
-		/* allocate memory to hold full descriptor */
+	/* Sanity checks */
+	if (ret || !buff_len) {
+		dev_err(hba->dev, "%s: Failed to get full descriptor length",
+			__func__);
+		return ret;
+	}
+
+	/* Check whether we need temp memory */
+	if (param_offset != 0 || param_size < buff_len) {
 		desc_buf = kmalloc(buff_len, GFP_KERNEL);
 		if (!desc_buf)
 			return -ENOMEM;
+	} else {
+		desc_buf = param_read_buf;
+		is_kmalloc = false;
 	}
 
+	/* Request for full descriptor */
 	ret = ufshcd_query_descriptor_retry(hba, UPIU_QUERY_OPCODE_READ_DESC,
-					desc_id, desc_index, 0, desc_buf,
-					&buff_len);
+					desc_id, desc_index, 0,
+					desc_buf, &buff_len);
 
 	if (ret) {
 		dev_err(hba->dev, "%s: Failed reading descriptor. desc_id %d, desc_index %d, param_offset %d, ret %d",
 			__func__, desc_id, desc_index, param_offset, ret);
-
 		goto out;
 	}
 
···
 		goto out;
 	}
 
-	/*
-	 * While reading variable size descriptors (like string descriptor),
-	 * some UFS devices may report the "LENGTH" (field in "Transaction
-	 * Specific fields" of Query Response UPIU) same as what was requested
-	 * in Query Request UPIU instead of reporting the actual size of the
-	 * variable size descriptor.
-	 * Although it's safe to ignore the "LENGTH" field for variable size
-	 * descriptors as we can always derive the length of the descriptor from
-	 * the descriptor header fields. Hence this change impose the length
-	 * match check only for fixed size descriptors (for which we always
-	 * request the correct size as part of Query Request UPIU).
-	 */
-	if ((desc_id != QUERY_DESC_IDN_STRING) &&
-	    (buff_len != desc_buf[QUERY_DESC_LENGTH_OFFSET])) {
-		dev_err(hba->dev, "%s: desc_buf length mismatch: buff_len %d, buff_len(desc_header) %d",
-			__func__, buff_len, desc_buf[QUERY_DESC_LENGTH_OFFSET]);
-		ret = -EINVAL;
-		goto out;
-	}
+	/* Check wherher we will not copy more data, than available */
+	if (is_kmalloc && param_size > buff_len)
+		param_size = buff_len;
 
 	if (is_kmalloc)
 		memcpy(param_read_buf, &desc_buf[param_offset], param_size);
···
 static void ufshcd_init_icc_levels(struct ufs_hba *hba)
 {
 	int ret;
-	int buff_len = QUERY_DESC_POWER_MAX_SIZE;
-	u8 desc_buf[QUERY_DESC_POWER_MAX_SIZE];
+	int buff_len = hba->desc_size.pwr_desc;
+	u8 desc_buf[hba->desc_size.pwr_desc];
 
 	ret = ufshcd_read_power_desc(hba, desc_buf, buff_len);
 	if (ret) {
···
 {
 	int err;
 	u8 model_index;
-	u8 str_desc_buf[QUERY_DESC_STRING_MAX_SIZE + 1] = {0};
-	u8 desc_buf[QUERY_DESC_DEVICE_MAX_SIZE];
+	u8 str_desc_buf[QUERY_DESC_MAX_SIZE + 1] = {0};
+	u8 desc_buf[hba->desc_size.dev_desc];
 
-	err = ufshcd_read_device_desc(hba, desc_buf,
-					QUERY_DESC_DEVICE_MAX_SIZE);
+	err = ufshcd_read_device_desc(hba, desc_buf, hba->desc_size.dev_desc);
 	if (err) {
 		dev_err(hba->dev, "%s: Failed reading Device Desc. err = %d\n",
 			__func__, err);
···
 	model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME];
 
 	err = ufshcd_read_string_desc(hba, model_index, str_desc_buf,
-					QUERY_DESC_STRING_MAX_SIZE, ASCII_STD);
+				QUERY_DESC_MAX_SIZE, ASCII_STD);
 	if (err) {
 		dev_err(hba->dev, "%s: Failed reading Product Name. err = %d\n",
 			__func__, err);
 		goto out;
 	}
 
-	str_desc_buf[QUERY_DESC_STRING_MAX_SIZE] = '\0';
+	str_desc_buf[QUERY_DESC_MAX_SIZE] = '\0';
 	strlcpy(dev_desc->model, (str_desc_buf + QUERY_DESC_HDR_SIZE),
 		min_t(u8, str_desc_buf[QUERY_DESC_LENGTH_OFFSET],
 		      MAX_MODEL_LEN));
···
 	hba->req_abort_count = 0;
 }
 
+static void ufshcd_init_desc_sizes(struct ufs_hba *hba)
+{
+	int err;
+
+	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_DEVICE, 0,
+		&hba->desc_size.dev_desc);
+	if (err)
+		hba->desc_size.dev_desc = QUERY_DESC_DEVICE_DEF_SIZE;
+
+	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_POWER, 0,
+		&hba->desc_size.pwr_desc);
+	if (err)
+		hba->desc_size.pwr_desc = QUERY_DESC_POWER_DEF_SIZE;
+
+	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_INTERCONNECT, 0,
+		&hba->desc_size.interc_desc);
+	if (err)
+		hba->desc_size.interc_desc = QUERY_DESC_INTERCONNECT_DEF_SIZE;
+
+	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_CONFIGURATION, 0,
+		&hba->desc_size.conf_desc);
+	if (err)
+		hba->desc_size.conf_desc = QUERY_DESC_CONFIGURATION_DEF_SIZE;
+
+	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_UNIT, 0,
+		&hba->desc_size.unit_desc);
+	if (err)
+		hba->desc_size.unit_desc = QUERY_DESC_UNIT_DEF_SIZE;
+
+	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_GEOMETRY, 0,
+		&hba->desc_size.geom_desc);
+	if (err)
+		hba->desc_size.geom_desc = QUERY_DESC_GEOMETRY_DEF_SIZE;
+}
+
+static void ufshcd_def_desc_sizes(struct ufs_hba *hba)
+{
+	hba->desc_size.dev_desc = QUERY_DESC_DEVICE_DEF_SIZE;
+	hba->desc_size.pwr_desc = QUERY_DESC_POWER_DEF_SIZE;
+	hba->desc_size.interc_desc = QUERY_DESC_INTERCONNECT_DEF_SIZE;
+	hba->desc_size.conf_desc = QUERY_DESC_CONFIGURATION_DEF_SIZE;
+	hba->desc_size.unit_desc = QUERY_DESC_UNIT_DEF_SIZE;
+	hba->desc_size.geom_desc = QUERY_DESC_GEOMETRY_DEF_SIZE;
+}
+
 /**
  * ufshcd_probe_hba - probe hba to detect device and initialize
  * @hba: per-adapter instance
···
 	ret = ufshcd_complete_dev_init(hba);
 	if (ret)
 		goto out;
+
+	/* Init check for device descriptor sizes */
+	ufshcd_init_desc_sizes(hba);
 
 	ret = ufs_get_device_desc(hba, &card);
 	if (ret) {
···
 
 	/* set the state as operational after switching to desired gear */
 	hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
+
 	/*
 	 * If we are in error handling context or in power management callbacks
 	 * context, no need to scan the host
···
 
 	hba->mmio_base = mmio_base;
 	hba->irq = irq;
+
+	/* Set descriptor lengths to specification defaults */
+	ufshcd_def_desc_sizes(hba);
 
 	err = ufshcd_hba_init(hba);
 	if (err)

drivers/scsi/ufs/ufshcd.h

···
 	struct ufs_query query;
 };
 
+struct ufs_desc_size {
+	int dev_desc;
+	int pwr_desc;
+	int geom_desc;
+	int interc_desc;
+	int unit_desc;
+	int conf_desc;
+};
+
 /**
  * struct ufs_clk_info - UFS clock related info
  * @list: list headed by hba->clk_list_head
···
  * @clk_list_head: UFS host controller clocks list node head
  * @pwr_info: holds current power mode
  * @max_pwr_info: keeps the device max valid pwm
+ * @desc_size: descriptor sizes reported by device
  * @urgent_bkops_lvl: keeps track of urgent bkops level for device
  * @is_urgent_bkops_lvl_checked: keeps track if the urgent bkops level for
  *  device is known or not.
···
 	bool is_urgent_bkops_lvl_checked;
 
 	struct rw_semaphore clk_scaling_lock;
+	struct ufs_desc_size desc_size;
 };
 
 /* Returns true if clocks can be gated. Otherwise false */
···
 	enum flag_idn idn, bool *flag_res);
 int ufshcd_hold(struct ufs_hba *hba, bool async);
 void ufshcd_release(struct ufs_hba *hba);
+
+int ufshcd_map_desc_id_to_length(struct ufs_hba *hba, enum desc_idn desc_id,
+	int *desc_length);
+
 u32 ufshcd_get_local_unipro_ver(struct ufs_hba *hba);
 
 /* Wrapper functions for safely calling variant operations */

drivers/scsi/vmw_pvscsi.c

···
 		irq_flag &= ~PCI_IRQ_MSI;
 
 	error = pci_alloc_irq_vectors(adapter->dev, 1, 1, irq_flag);
-	if (error)
+	if (error < 0)
 		goto out_reset_adapter;
 
 	adapter->use_req_threshold = pvscsi_setup_req_threshold(adapter, true);

drivers/staging/lustre/lnet/lnet/lib-socket.c

···
 
 	newsock->ops = sock->ops;
 
-	rc = sock->ops->accept(sock, newsock, O_NONBLOCK);
+	rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false);
 	if (rc == -EAGAIN) {
 		/* Nothing ready, so wait for activity */
 		init_waitqueue_entry(&wait, current);
···
 		set_current_state(TASK_INTERRUPTIBLE);
 		schedule();
 		remove_wait_queue(sk_sleep(sock->sk), &wait);
-		rc = sock->ops->accept(sock, newsock, O_NONBLOCK);
+		rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false);
 	}
 
 	if (rc)

fs/dlm/lowcomms.c

···
 	newsock->type = con->sock->type;
 	newsock->ops = con->sock->ops;
 
-	result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK);
+	result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK, true);
 	if (result < 0)
 		goto accept_err;
 

fs/fs-writeback.c

···
 	spin_unlock_bh(&wb->work_lock);
 }
 
+static void finish_writeback_work(struct bdi_writeback *wb,
+				  struct wb_writeback_work *work)
+{
+	struct wb_completion *done = work->done;
+
+	if (work->auto_free)
+		kfree(work);
+	if (done && atomic_dec_and_test(&done->cnt))
+		wake_up_all(&wb->bdi->wb_waitq);
+}
+
 static void wb_queue_work(struct bdi_writeback *wb,
 			  struct wb_writeback_work *work)
 {
 	trace_writeback_queue(wb, work);
 
-	spin_lock_bh(&wb->work_lock);
-	if (!test_bit(WB_registered, &wb->state))
-		goto out_unlock;
 	if (work->done)
 		atomic_inc(&work->done->cnt);
-	list_add_tail(&work->list, &wb->work_list);
-	mod_delayed_work(bdi_wq, &wb->dwork, 0);
-out_unlock:
+
+	spin_lock_bh(&wb->work_lock);
+
+	if (test_bit(WB_registered, &wb->state)) {
+		list_add_tail(&work->list, &wb->work_list);
+		mod_delayed_work(bdi_wq, &wb->dwork, 0);
+	} else
+		finish_writeback_work(wb, work);
+
 	spin_unlock_bh(&wb->work_lock);
 }
 
···
 
 	set_bit(WB_writeback_running, &wb->state);
 	while ((work = get_next_work_item(wb)) != NULL) {
-		struct wb_completion *done = work->done;
-
 		trace_writeback_exec(wb, work);
-
 		wrote += wb_writeback(wb, work);
-
-		if (work->auto_free)
-			kfree(work);
-		if (done && atomic_dec_and_test(&done->cnt))
-			wake_up_all(&wb->bdi->wb_waitq);
+		finish_writeback_work(wb, work);
 	}
 
 	/*

fs/gfs2/incore.h

···
 	struct gfs2_sbd *ln_sbd;
 	u64 ln_number;
 	unsigned int ln_type;
-};
+} __packed __aligned(sizeof(int));
 
 #define lm_name_equal(name1, name2) \
         (((name1)->ln_number == (name2)->ln_number) &&	\

fs/ocfs2/cluster/tcp.c

···
 
 	new_sock->type = sock->type;
 	new_sock->ops = sock->ops;
-	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK);
+	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, false);
 	if (ret < 0)
 		goto out;
 

include/crypto/if_alg.h

···
 
 int af_alg_release(struct socket *sock);
 void af_alg_release_parent(struct sock *sk);
-int af_alg_accept(struct sock *sk, struct socket *newsock);
+int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern);
 
 int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len);
 void af_alg_free_sg(struct af_alg_sgl *sgl);

include/linux/dccp.h

···
 	__u64			 dreq_isr;
 	__u64			 dreq_gsr;
 	__be32			 dreq_service;
+	spinlock_t		 dreq_lock;
 	struct list_head	 dreq_featneg;
 	__u32			 dreq_timestamp_echo;
 	__u32			 dreq_timestamp_time;

include/linux/filter.h

···
 	u16			pages;		/* Number of allocated pages */
 	kmemcheck_bitfield_begin(meta);
 	u16			jited:1,	/* Is our filter JIT'ed? */
+				locked:1,	/* Program image locked? */
 				gpl_compatible:1, /* Is filter GPL compatible? */
 				cb_access:1,	/* Is control block accessed? */
 				dst_needed:1,	/* Do we need dst entry? */
···
 #ifdef CONFIG_ARCH_HAS_SET_MEMORY
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 {
-	set_memory_ro((unsigned long)fp, fp->pages);
+	fp->locked = 1;
+	WARN_ON_ONCE(set_memory_ro((unsigned long)fp, fp->pages));
 }
 
 static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 {
-	set_memory_rw((unsigned long)fp, fp->pages);
+	if (fp->locked) {
+		WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages));
+		/* In case set_memory_rw() fails, we want to be the first
+		 * to crash here instead of some random place later on.
+		 */
+		fp->locked = 0;
+	}
 }
 
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
-	set_memory_ro((unsigned long)hdr, hdr->pages);
+	WARN_ON_ONCE(set_memory_ro((unsigned long)hdr, hdr->pages));
 }
 
 static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
 {
-	set_memory_rw((unsigned long)hdr, hdr->pages);
+	WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages));
 }
 #else
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)

include/linux/list_nulls.h

···
 	((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls))
 
 #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member)
+
+#define hlist_nulls_entry_safe(ptr, type, member) \
+	({ typeof(ptr) ____ptr = (ptr); \
+	   !is_a_nulls(____ptr) ? hlist_nulls_entry(____ptr, type, member) : NULL; \
+	})
 /**
  * ptr_is_a_nulls - Test if a ptr is a nulls
  * @ptr: ptr to be tested

include/linux/net.h

···
 	int		(*socketpair)(struct socket *sock1,
 				      struct socket *sock2);
 	int		(*accept)    (struct socket *sock,
-				      struct socket *newsock, int flags);
+				      struct socket *newsock, int flags, bool kern);
 	int		(*getname)   (struct socket *sock,
 				      struct sockaddr *addr,
 				      int *sockaddr_len, int peer);

include/linux/phy.h

···
 int genphy_suspend(struct phy_device *phydev);
 int genphy_resume(struct phy_device *phydev);
 int genphy_soft_reset(struct phy_device *phydev);
+static inline int genphy_no_soft_reset(struct phy_device *phydev)
+{
+	return 0;
+}
 void phy_driver_unregister(struct phy_driver *drv);
 void phy_drivers_unregister(struct phy_driver *drv, int n);
 int phy_driver_register(struct phy_driver *new_driver, struct module *owner);

include/linux/rculist_nulls.h

···
 		({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \
 		pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)))
 
+/**
+ * hlist_nulls_for_each_entry_safe -
+ *   iterate over list of given type safe against removal of list entry
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_nulls_node to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_nulls_node within the struct.
+ */
+#define hlist_nulls_for_each_entry_safe(tpos, pos, head, member)		\
+	for (({barrier();}),							\
+	     pos = rcu_dereference_raw(hlist_nulls_first_rcu(head));		\
+		(!is_a_nulls(pos)) &&						\
+		({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member);	\
+		   pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)); 1; });)
 #endif
 #endif

include/net/inet_common.h

···
 			  int addr_len, int flags, int is_sendmsg);
 int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
 		       int addr_len, int flags);
-int inet_accept(struct socket *sock, struct socket *newsock, int flags);
+int inet_accept(struct socket *sock, struct socket *newsock, int flags,
+		bool kern);
 int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size);
 ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
 		      size_t size, int flags);

include/net/inet_connection_sock.h

···
         return (unsigned long)min_t(u64, when, max_when);
 }
 
-struct sock *inet_csk_accept(struct sock *sk, int flags, int *err);
+struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern);
 
 int inet_csk_get_port(struct sock *sk, unsigned short snum);
 

include/net/sctp/structs.h

···
 	int  (*send_verify) (struct sctp_sock *, union sctp_addr *);
 	int  (*supported_addrs)(const struct sctp_sock *, __be16 *);
 	struct sock *(*create_accept_sk) (struct sock *sk,
-					  struct sctp_association *asoc);
+					  struct sctp_association *asoc,
+					  bool kern);
 	int (*addr_to_user)(struct sctp_sock *sk, union sctp_addr *addr);
 	void (*to_sk_saddr)(union sctp_addr *, struct sock *sk);
 	void (*to_sk_daddr)(union sctp_addr *, struct sock *sk);

include/net/sock.h

···
   *	@sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
   *	@sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
   *	@sk_lock:	synchronizer
+  *	@sk_kern_sock: True if sock is using kernel lock classes
   *	@sk_rcvbuf: size of receive buffer in bytes
   *	@sk_wq: sock wait queue and async head
   *	@sk_rx_dst: receive input route used by early demux
···
 #endif
 
 	kmemcheck_bitfield_begin(flags);
-	unsigned int		sk_padding : 2,
+	unsigned int		sk_padding : 1,
+				sk_kern_sock : 1,
 				sk_no_check_tx : 1,
 				sk_no_check_rx : 1,
 				sk_userlocks : 4,
···
 					int addr_len);
 	int			(*disconnect)(struct sock *sk, int flags);
 
-	struct sock *		(*accept)(struct sock *sk, int flags, int *err);
+	struct sock *		(*accept)(struct sock *sk, int flags, int *err,
+					  bool kern);
 
 	int			(*ioctl)(struct sock *sk, int cmd,
 					 unsigned long arg);
···
 int sock_no_bind(struct socket *, struct sockaddr *, int);
 int sock_no_connect(struct socket *, struct sockaddr *, int, int);
 int sock_no_socketpair(struct socket *, struct socket *);
-int sock_no_accept(struct socket *, struct socket *, int);
+int sock_no_accept(struct socket *, struct socket *, int, bool);
 int sock_no_getname(struct socket *, struct sockaddr *, int *, int);
 unsigned int sock_no_poll(struct file *, struct socket *,
 			  struct poll_table_struct *);

include/scsi/libiscsi.h

···
 	struct iscsi_task	*task;		/* xmit task in progress */
 
 	/* xmit */
+	spinlock_t		taskqueuelock;  /* protects the next three lists */
 	struct list_head	mgmtqueue;	/* mgmt (control) xmit queue */
 	struct list_head	cmdqueue;	/* data-path cmd queue */
 	struct list_head	requeue;	/* tasks needing another run */

include/scsi/scsi_device.h

···
 		sdev->sdev_state == SDEV_CREATED_BLOCK;
 }
 
+int scsi_internal_device_block(struct scsi_device *sdev, bool wait);
+int scsi_internal_device_unblock(struct scsi_device *sdev,
+				 enum scsi_device_state new_state);
+
 /* accessor functions for the SCSI parameters */
 static inline int scsi_device_sync(struct scsi_device *sdev)
 {

include/uapi/linux/packet_diag.h

···
 	__u32	pdmc_count;
 	__u16	pdmc_type;
 	__u16	pdmc_alen;
-	__u8	pdmc_addr[MAX_ADDR_LEN];
+	__u8	pdmc_addr[32]; /* MAX_ADDR_LEN */
 };
 
 struct packet_diag_ring {

kernel/bpf/hashtab.c

···
 #include <linux/bpf.h>
 #include <linux/jhash.h>
 #include <linux/filter.h>
+#include <linux/rculist_nulls.h>
 #include "percpu_freelist.h"
 #include "bpf_lru_list.h"
 
 struct bucket {
-	struct hlist_head head;
+	struct hlist_nulls_head head;
 	raw_spinlock_t lock;
 };
 
···
 /* each htab element is struct htab_elem + key + value */
 struct htab_elem {
 	union {
-		struct hlist_node hash_node;
-		struct bpf_htab *htab;
-		struct pcpu_freelist_node fnode;
+		struct hlist_nulls_node hash_node;
+		struct {
+			void *padding;
+			union {
+				struct bpf_htab *htab;
+				struct pcpu_freelist_node fnode;
+			};
+		};
 	};
 	union {
 		struct rcu_head rcu;
···
 				 offsetof(struct htab_elem, lru_node),
 				 htab->elem_size, htab->map.max_entries);
 	else
-		pcpu_freelist_populate(&htab->freelist, htab->elems,
+		pcpu_freelist_populate(&htab->freelist,
+				       htab->elems + offsetof(struct htab_elem, fnode),
 				       htab->elem_size, htab->map.max_entries);
 
 	return 0;
···
 	struct bpf_htab *htab;
 	int err, i;
 	u64 cost;
+
+	BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
+		     offsetof(struct htab_elem, hash_node.pprev));
+	BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
+		     offsetof(struct htab_elem, hash_node.pprev));
 
 	if (lru && !capable(CAP_SYS_ADMIN))
 		/* LRU implementation is much complicated than other
···
 		goto free_htab;
 
 	for (i = 0; i < htab->n_buckets; i++) {
-		INIT_HLIST_HEAD(&htab->buckets[i].head);
+		INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
 		raw_spin_lock_init(&htab->buckets[i].lock);
 	}
 
···
 	return &htab->buckets[hash & (htab->n_buckets - 1)];
 }
 
-static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+static inline struct hlist_nulls_head *select_bucket(struct bpf_htab *htab, u32 hash)
 {
 	return &__select_bucket(htab, hash)->head;
 }
 
-static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash,
+/* this lookup function can only be called with bucket lock taken */
+static struct htab_elem *lookup_elem_raw(struct hlist_nulls_head *head, u32 hash,
 					 void *key, u32 key_size)
 {
+	struct hlist_nulls_node *n;
 	struct htab_elem *l;
 
-	hlist_for_each_entry_rcu(l, head, hash_node)
+	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
 		if (l->hash == hash && !memcmp(&l->key, key, key_size))
 			return l;
+
+	return NULL;
+}
+
+/* can be called without bucket lock. it will repeat the loop in
+ * the unlikely event when elements moved from one bucket into another
+ * while link list is being walked
+ */
+static struct htab_elem *lookup_nulls_elem_raw(struct hlist_nulls_head *head,
+					       u32 hash, void *key,
+					       u32 key_size, u32 n_buckets)
+{
+	struct hlist_nulls_node *n;
+	struct htab_elem *l;
+
+again:
+	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
+		if (l->hash == hash && !memcmp(&l->key, key, key_size))
+			return l;
+
+	if (unlikely(get_nulls_value(n) != (hash & (n_buckets - 1))))
+		goto again;
 
 	return NULL;
 }
···
 static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	struct htab_elem *l;
 	u32 hash, key_size;
 
···
 
 	head = select_bucket(htab, hash);
 
-	l = lookup_elem_raw(head, hash, key, key_size);
+	l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);
 
 	return l;
 }
···
 static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 {
 	struct bpf_htab *htab = (struct bpf_htab *)arg;
-	struct htab_elem *l, *tgt_l;
-	struct hlist_head *head;
+	struct htab_elem *l = NULL, *tgt_l;
+	struct hlist_nulls_head *head;
+	struct hlist_nulls_node *n;
 	unsigned long flags;
 	struct bucket *b;
 
···
 
 	raw_spin_lock_irqsave(&b->lock, flags);
 
-	hlist_for_each_entry_rcu(l, head, hash_node)
+	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
 		if (l == tgt_l) {
-			hlist_del_rcu(&l->hash_node);
+			hlist_nulls_del_rcu(&l->hash_node);
 			break;
 		}
 
···
 static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	struct htab_elem *l, *next_l;
 	u32 hash, key_size;
 	int i;
···
 	head = select_bucket(htab, hash);
 
 	/* lookup the key */
-	l = lookup_elem_raw(head, hash, key, key_size);
+	l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);
 
 	if (!l) {
 		i = 0;
···
 	}
 
 	/* key was found, get next key in the same bucket */
-	next_l = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&l->hash_node)),
+	next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_next_rcu(&l->hash_node)),
 				  struct htab_elem, hash_node);
 
 	if (next_l) {
···
 		head = select_bucket(htab, i);
 
 		/* pick first element in the bucket */
-		next_l = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),
+		next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_first_rcu(head)),
 					  struct htab_elem, hash_node);
 		if (next_l) {
 			/* if it's not empty, just return it */
···
 	int err = 0;
 
 	if (prealloc) {
-		l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist);
-		if (!l_new)
+		struct pcpu_freelist_node *l;
+
+		l = pcpu_freelist_pop(&htab->freelist);
+		if (!l)
 			err = -E2BIG;
+		else
+			l_new = container_of(l, struct htab_elem, fnode);
 	} else {
 		if (atomic_inc_return(&htab->count) > htab->map.max_entries) {
 			atomic_dec(&htab->count);
···
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct htab_elem *l_new = NULL, *l_old;
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
···
 	/* add new element to the head of the list, so that
 	 * concurrent search will find it before old elem
 	 */
-	hlist_add_head_rcu(&l_new->hash_node, head);
+	hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 	if (l_old) {
-		hlist_del_rcu(&l_old->hash_node);
+		hlist_nulls_del_rcu(&l_old->hash_node);
 		free_htab_elem(htab, l_old);
 	}
 	ret = 0;
···
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct htab_elem *l_new, *l_old = NULL;
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
···
 	/* add new element to the head of the list, so that
 	 * concurrent search will find it before old elem
 	 */
-	hlist_add_head_rcu(&l_new->hash_node, head);
+	hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 	if (l_old) {
 		bpf_lru_node_set_ref(&l_new->lru_node);
-		hlist_del_rcu(&l_old->hash_node);
+		hlist_nulls_del_rcu(&l_old->hash_node);
 	}
 	ret = 0;
 
···
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct htab_elem *l_new = NULL, *l_old;
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
···
 			ret = PTR_ERR(l_new);
 			goto err;
 		}
-		hlist_add_head_rcu(&l_new->hash_node, head);
+		hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 	}
 	ret = 0;
 err:
···
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct htab_elem *l_new = NULL, *l_old;
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
···
 	} else {
 		pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size),
 				value, onallcpus);
-		hlist_add_head_rcu(&l_new->hash_node, head);
+		hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 		l_new = NULL;
 	}
 	ret = 0;
···
 static int htab_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	struct bucket *b;
 	struct htab_elem *l;
 	unsigned long flags;
···
 	l = lookup_elem_raw(head, hash, key, key_size);
 
 	if (l) {
-		hlist_del_rcu(&l->hash_node);
+		hlist_nulls_del_rcu(&l->hash_node);
 		free_htab_elem(htab, l);
 		ret = 0;
 	}
···
 static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct hlist_head *head;
+	struct hlist_nulls_head *head;
 	struct bucket *b;
 	struct htab_elem *l;
 	unsigned long flags;
···
 	l = lookup_elem_raw(head, hash, key, key_size);
 
 	if (l) {
-		hlist_del_rcu(&l->hash_node);
+		hlist_nulls_del_rcu(&l->hash_node);
 		ret = 0;
 	}
 
···
 	int i;
 
 	for (i = 0; i < htab->n_buckets; i++) {
-		struct hlist_head *head = select_bucket(htab, i);
-		struct hlist_node *n;
+		struct hlist_nulls_head *head = select_bucket(htab, i);
+		struct hlist_nulls_node *n;
 		struct htab_elem *l;
 
-		hlist_for_each_entry_safe(l, n, head, hash_node) {
-			hlist_del_rcu(&l->hash_node);
+		hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
+			hlist_nulls_del_rcu(&l->hash_node);
 			if (l->state != HTAB_EXTRA_ELEM_USED)
 				htab_elem_free(htab, l);
 		}

kernel/bpf/lpm_trie.c

···
 	raw_spin_unlock(&trie->lock);
 }
 
+static int trie_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	return -ENOTSUPP;
+}
+
 static const struct bpf_map_ops trie_ops = {
 	.map_alloc = trie_alloc,
 	.map_free = trie_free,
+	.map_get_next_key = trie_get_next_key,
 	.map_lookup_elem = trie_lookup_elem,
 	.map_update_elem = trie_update_elem,
 	.map_delete_elem = trie_delete_elem,

kernel/cgroup/cgroup-v1.c

···
 		struct task_struct *task;
 		int count = 0;
 
-		seq_printf(seq, "css_set %p\n", cset);
+		seq_printf(seq, "css_set %pK\n", cset);
 
 		list_for_each_entry(task, &cset->tasks, cg_list) {
 			if (count++ > MAX_TASKS_SHOWN_PER_CSS)

kernel/cgroup/pids.c

···
 		/* Only log the first time events_limit is incremented. */
 		if (atomic64_inc_return(&pids->events_limit) == 1) {
 			pr_info("cgroup: fork rejected by pids controller in ");
-			pr_cont_cgroup_path(task_cgroup(current, pids_cgrp_id));
+			pr_cont_cgroup_path(css->cgroup);
 			pr_cont("\n");
 		}
 		cgroup_file_notify(&pids->events_file);

kernel/sched/core.c

···
 cpumask_var_t cpu_isolated_map;
 
 /*
- * this_rq_lock - lock this runqueue and disable interrupts.
- */
-static struct rq *this_rq_lock(void)
-	__acquires(rq->lock)
-{
-	struct rq *rq;
-
-	local_irq_disable();
-	rq = this_rq();
-	raw_spin_lock(&rq->lock);
-
-	return rq;
-}
-
-/*
  * __task_rq_lock - lock the rq @p resides on.
  */
 struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
···
 		return;
 
 #ifdef CONFIG_SCHED_DEBUG
+	if (sched_feat(WARN_DOUBLE_CLOCK))
+		SCHED_WARN_ON(rq->clock_update_flags & RQCF_UPDATED);
 	rq->clock_update_flags |= RQCF_UPDATED;
 #endif
+
 	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
 	if (delta < 0)
 		return;
···
 static enum hrtimer_restart hrtick(struct hrtimer *timer)
 {
 	struct rq *rq = container_of(timer, struct rq, hrtick_timer);
+	struct rq_flags rf;
 
 	WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
 
-	raw_spin_lock(&rq->lock);
+	rq_lock(rq, &rf);
 	update_rq_clock(rq);
 	rq->curr->sched_class->task_tick(rq, rq->curr, 1);
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, &rf);
 
 	return HRTIMER_NORESTART;
 }
···
 static void __hrtick_start(void *arg)
 {
 	struct rq *rq = arg;
+	struct rq_flags rf;
 
-	raw_spin_lock(&rq->lock);
+	rq_lock(rq, &rf);
 	__hrtick_restart(rq);
 	rq->hrtick_csd_pending = 0;
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, &rf);
 }
 
 /*
···
 
 static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	update_rq_clock(rq);
+	if (!(flags & ENQUEUE_NOCLOCK))
+		update_rq_clock(rq);
+
 	if (!(flags & ENQUEUE_RESTORE))
 		sched_info_queued(rq, p);
+
 	p->sched_class->enqueue_task(rq, p, flags);
 }
 
 static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	update_rq_clock(rq);
+	if (!(flags & DEQUEUE_NOCLOCK))
+		update_rq_clock(rq);
+
 	if (!(flags & DEQUEUE_SAVE))
 		sched_info_dequeued(rq, p);
+
 	p->sched_class->dequeue_task(rq, p, flags);
 }
 
···
  *
  * Returns (locked) new rq. Old rq's lock is released.
  */
-static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new_cpu)
+static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
+				   struct task_struct *p, int new_cpu)
 {
 	lockdep_assert_held(&rq->lock);
 
 	p->on_rq = TASK_ON_RQ_MIGRATING;
-	dequeue_task(rq, p, 0);
+	dequeue_task(rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, new_cpu);
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, rf);
 
 	rq = cpu_rq(new_cpu);
 
-	raw_spin_lock(&rq->lock);
+	rq_lock(rq, rf);
 	BUG_ON(task_cpu(p) != new_cpu);
 	enqueue_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_QUEUED;
···
  * So we race with normal scheduler movements, but that's OK, as long
  * as the task is no longer on this CPU.
  */
-static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int dest_cpu)
+static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
+				 struct task_struct *p, int dest_cpu)
 {
 	if (unlikely(!cpu_active(dest_cpu)))
 		return rq;
···
 	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
 		return rq;
 
-	rq = move_queued_task(rq, p, dest_cpu);
+	update_rq_clock(rq);
+	rq = move_queued_task(rq, rf, p, dest_cpu);
 
 	return rq;
 }
···
 	struct migration_arg *arg = data;
 	struct task_struct *p = arg->task;
 	struct rq *rq = this_rq();
+	struct rq_flags rf;
 
 	/*
 	 * The original target CPU might have gone down and we might
···
 	sched_ttwu_pending();
 
 	raw_spin_lock(&p->pi_lock);
-	raw_spin_lock(&rq->lock);
+	rq_lock(rq, &rf);
 	/*
 	 * If task_rq(p) != rq, it cannot be migrated here, because we're
 	 * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
···
 	 */
 	if (task_rq(p) == rq) {
 		if (task_on_rq_queued(p))
-			rq = __migrate_task(rq, p, arg->dest_cpu);
+			rq = __migrate_task(rq, &rf, p, arg->dest_cpu);
 		else
 			p->wake_cpu = arg->dest_cpu;
 	}
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, &rf);
 	raw_spin_unlock(&p->pi_lock);
 
 	local_irq_enable();
···
 		 * holding rq->lock.
 		 */
 		lockdep_assert_held(&rq->lock);
-		dequeue_task(rq, p, DEQUEUE_SAVE);
+		dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
 	}
 	if (running)
 		put_prev_task(rq, p);
···
 	p->sched_class->set_cpus_allowed(p, new_mask);
 
 	if (queued)
-		enqueue_task(rq, p, ENQUEUE_RESTORE);
+		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
 	if (running)
 		set_curr_task(rq, p);
 }
···
 		 * OK, since we're going to drop the lock immediately
 		 * afterwards anyway.
 		 */
-		rq_unpin_lock(rq, &rf);
-		rq = move_queued_task(rq, p, dest_cpu);
-		rq_repin_lock(rq, &rf);
+		rq = move_queued_task(rq, &rf, p, dest_cpu);
 	}
 out:
 	task_rq_unlock(rq, p, &rf);
···
 {
 	if (task_on_rq_queued(p)) {
 		struct rq *src_rq, *dst_rq;
+		struct rq_flags srf, drf;
 
 		src_rq = task_rq(p);
 		dst_rq = cpu_rq(cpu);
+
+		rq_pin_lock(src_rq, &srf);
+		rq_pin_lock(dst_rq, &drf);
 
 		p->on_rq = TASK_ON_RQ_MIGRATING;
 		deactivate_task(src_rq, p, 0);
···
 		activate_task(dst_rq, p, 0);
 		p->on_rq = TASK_ON_RQ_QUEUED;
 		check_preempt_curr(dst_rq, p, 0);
+
+		rq_unpin_lock(dst_rq, &drf);
+		rq_unpin_lock(src_rq, &srf);
+
 	} else {
 		/*
 		 * Task isn't running anymore; make it appear like we migrated
···
 ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		 struct rq_flags *rf)
 {
-	int en_flags = ENQUEUE_WAKEUP;
+	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
 
 	lockdep_assert_held(&rq->lock);
 
···
 	struct rq *rq = this_rq();
 	struct llist_node *llist = llist_del_all(&rq->wake_list);
 	struct task_struct *p;
-	unsigned long flags;
 	struct rq_flags rf;
 
 	if (!llist)
 		return;
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
-	rq_pin_lock(rq, &rf);
+	rq_lock_irqsave(rq, &rf);
+	update_rq_clock(rq);
 
 	while (llist) {
 		int wake_flags = 0;
···
 		ttwu_do_activate(rq, p, wake_flags, &rf);
 	}
 
-	rq_unpin_lock(rq, &rf);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	rq_unlock_irqrestore(rq, &rf);
 }
 
 void scheduler_ipi(void)
···
 void wake_up_if_idle(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long flags;
+	struct rq_flags rf;
 
 	rcu_read_lock();
 
···
 	if (set_nr_if_polling(rq->idle)) {
 		trace_sched_wake_idle_without_ipi(cpu);
 	} else {
-		raw_spin_lock_irqsave(&rq->lock, flags);
+		rq_lock_irqsave(rq, &rf);
 		if (is_idle_task(rq->curr))
 			smp_send_reschedule(cpu);
 		/* Else CPU is not idle, do nothing here: */
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
+		rq_unlock_irqrestore(rq, &rf);
 	}
 
 out:
···
 	}
 #endif
 
-	raw_spin_lock(&rq->lock);
-	rq_pin_lock(rq, &rf);
+	rq_lock(rq, &rf);
+	update_rq_clock(rq);
 	ttwu_do_activate(rq, p, wake_flags, &rf);
-	rq_unpin_lock(rq, &rf);
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, &rf);
 }
 
 /*
···
 		 * disabled avoiding further scheduler activity on it and we've
 		 * not yet picked a replacement task.
 		 */
-		rq_unpin_lock(rq, rf);
-		raw_spin_unlock(&rq->lock);
+		rq_unlock(rq, rf);
 		raw_spin_lock(&p->pi_lock);
-		raw_spin_lock(&rq->lock);
-		rq_repin_lock(rq, rf);
+		rq_relock(rq, rf);
 	}
 
 	if (!(p->state & TASK_NORMAL))
···
 			delayacct_blkio_end();
 			atomic_dec(&rq->nr_iowait);
 		}
-		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+		ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
 	}
 
 	ttwu_do_wakeup(rq, p, 0, rf);
···
 	update_rq_clock(rq);
 	post_init_entity_util_avg(&p->se);
 
-	activate_task(rq, p, 0);
+	activate_task(rq, p, ENQUEUE_NOCLOCK);
 	p->on_rq = TASK_ON_RQ_QUEUED;
 	trace_sched_wakeup_new(p);
 	check_preempt_curr(rq, p, WF_FORK);
···
 	int cpu = smp_processor_id();
 	struct rq *rq = cpu_rq(cpu);
 	struct task_struct *curr = rq->curr;
+	struct rq_flags rf;
 
 	sched_clock_tick();
 
-	raw_spin_lock(&rq->lock);
+	rq_lock(rq, &rf);
+
 	update_rq_clock(rq);
 	curr->sched_class->task_tick(rq, curr, 0);
 	cpu_load_update_active(rq);
 	calc_global_load_tick(rq);
-	raw_spin_unlock(&rq->lock);
+
+	rq_unlock(rq, &rf);
 
 	perf_event_task_tick();
 
···
 	 * done by the caller to avoid the race with signal_wake_up().
 	 */
 	smp_mb__before_spinlock();
-	raw_spin_lock(&rq->lock);
-	rq_pin_lock(rq, &rf);
+	rq_lock(rq, &rf);
 
 	/* Promote REQ to ACT */
 	rq->clock_update_flags <<= 1;
+	update_rq_clock(rq);
 
 	switch_count = &prev->nivcsw;
 	if (!preempt && prev->state) {
 		if (unlikely(signal_pending_state(prev->state, prev))) {
 			prev->state = TASK_RUNNING;
 		} else {
-			deactivate_task(rq, prev, DEQUEUE_SLEEP);
+			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
 			prev->on_rq = 0;
 
 			if (prev->in_iowait) {
···
 		switch_count = &prev->nvcsw;
 	}
 
-	if (task_on_rq_queued(prev))
-		update_rq_clock(rq);
-
 	next = pick_next_task(rq, prev, &rf);
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
···
 		rq = context_switch(rq, prev, next, &rf);
 	} else {
 		rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
-		rq_unpin_lock(rq, &rf);
-		raw_spin_unlock_irq(&rq->lock);
+		rq_unlock_irq(rq, &rf);
 	}
 
 	balance_callback(rq);
···
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
-	int oldprio, queued, running, queue_flag = DEQUEUE_SAVE | DEQUEUE_MOVE;
+	int oldprio, queued, running, queue_flag =
+		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	const struct sched_class *prev_class;
 	struct rq_flags rf;
 	struct rq *rq;
···
 	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
 	if (queued)
-		dequeue_task(rq, p, DEQUEUE_SAVE);
+		dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
 	if (running)
 		put_prev_task(rq, p);
 
···
 	delta = p->prio - old_prio;
 
 	if (queued) {
-		enqueue_task(rq, p, ENQUEUE_RESTORE);
+		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
 		/*
 		 * If the task increased its priority or is running and
 		 * lowered its priority, then reschedule its CPU:
···
 	const struct sched_class *prev_class;
 	struct rq_flags rf;
 	int reset_on_fork;
-	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
+	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	struct rq *rq;
 
 	/* May grab non-irq protected spin_locks: */
···
  */
 SYSCALL_DEFINE0(sched_yield)
 {
-	struct rq *rq = this_rq_lock();
+	struct rq_flags rf;
+	struct rq *rq;
+
+	local_irq_disable();
+	rq = this_rq();
+	rq_lock(rq, &rf);
 
 	schedstat_inc(rq->yld_count);
 	current->sched_class->yield_task(rq);
···
 	 * Since we are going to call schedule() anyway, there's
 	 * no need to preempt or enable interrupts:
 	 */
-	__release(rq->lock);
-	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
-	do_raw_spin_unlock(&rq->lock);
+	preempt_disable();
+	rq_unlock(rq, &rf);
 	sched_preempt_enable_no_resched();
 
 	schedule();
···
 	p->numa_preferred_nid = nid;
 
 	if (queued)
-		enqueue_task(rq, p, ENQUEUE_RESTORE);
+		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
 	if (running)
 		set_curr_task(rq, p);
 	task_rq_unlock(rq, p, &rf);
···
  * there's no concurrency possible, we hold the required locks anyway
  * because of lock validation efforts.
  */
-static void migrate_tasks(struct rq *dead_rq)
+static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
 {
 	struct rq *rq = dead_rq;
 	struct task_struct *next, *stop = rq->stop;
-	struct rq_flags rf;
+	struct rq_flags orf = *rf;
 	int dest_cpu;
 
 	/*
···
 	 * class method both need to have an up-to-date
 	 * value of rq->clock[_task]
 	 */
-	rq_pin_lock(rq, &rf);
 	update_rq_clock(rq);
-	rq_unpin_lock(rq, &rf);
 
 	for (;;) {
 		/*
···
 		/*
 		 * pick_next_task() assumes pinned rq->lock:
 		 */
-		rq_repin_lock(rq, &rf);
-		next = pick_next_task(rq, &fake_task, &rf);
+		next = pick_next_task(rq, &fake_task, rf);
 		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
 
···
 		 * because !cpu_active at this point, which means load-balance
 		 * will not interfere. Also, stop-machine.
 		 */
-		rq_unpin_lock(rq, &rf);
-		raw_spin_unlock(&rq->lock);
+		rq_unlock(rq, rf);
 		raw_spin_lock(&next->pi_lock);
-		raw_spin_lock(&rq->lock);
+		rq_relock(rq, rf);
 
 		/*
 		 * Since we're inside stop-machine, _nothing_ should have
···
 
 		/* Find suitable destination for @next, with force if needed. */
 		dest_cpu = select_fallback_rq(dead_rq->cpu, next);
-
-		rq = __migrate_task(rq, next, dest_cpu);
+		rq = __migrate_task(rq, rf, next, dest_cpu);
 		if (rq != dead_rq) {
-			raw_spin_unlock(&rq->lock);
+			rq_unlock(rq, rf);
 			rq = dead_rq;
-			raw_spin_lock(&rq->lock);
+			*rf = orf;
+			rq_relock(rq, rf);
 		}
 		raw_spin_unlock(&next->pi_lock);
 	}
···
 int sched_cpu_activate(unsigned int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long flags;
+	struct rq_flags rf;
 
 	set_cpu_active(cpu, true);
 
···
 	 * 2) At runtime, if cpuset_cpu_active() fails to rebuild the
 	 *    domains.
 	 */
-	raw_spin_lock_irqsave(&rq->lock, flags);
+	rq_lock_irqsave(rq, &rf);
 	if (rq->rd) {
 		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 		set_rq_online(rq);
 	}
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	rq_unlock_irqrestore(rq, &rf);
 
 	update_max_interval();
 
···
 int sched_cpu_dying(unsigned int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long flags;
+	struct rq_flags rf;
 
 	/* Handle pending wakeups and then migrate everything off */
 	sched_ttwu_pending();
-	raw_spin_lock_irqsave(&rq->lock, flags);
+
+	rq_lock_irqsave(rq, &rf);
 	if (rq->rd) {
 		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 		set_rq_offline(rq);
 	}
-	migrate_tasks(rq);
+	migrate_tasks(rq, &rf);
 	BUG_ON(rq->nr_running != 1);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	rq_unlock_irqrestore(rq, &rf);
+
 	calc_load_migrate(rq);
 	update_max_interval();
 	nohz_balance_exit_idle(cpu);
···
  */
 void sched_move_task(struct task_struct *tsk)
 {
-	int queued, running;
+	int queued, running, queue_flags =
+		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	struct rq_flags rf;
 	struct rq *rq;
 
···
 	queued = task_on_rq_queued(tsk);
 
 	if (queued)
-		dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE);
+		dequeue_task(rq, tsk, queue_flags);
 	if (running)
 		put_prev_task(rq, tsk);
 
 	sched_change_group(tsk, TASK_MOVE_GROUP);
 
 	if (queued)
-		enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE);
+		enqueue_task(rq, tsk, queue_flags);
 	if (running)
 		set_curr_task(rq, tsk);
 
···
 	for_each_online_cpu(i) {
 		struct cfs_rq *cfs_rq = tg->cfs_rq[i];
 		struct rq *rq = cfs_rq->rq;
+		struct rq_flags rf;
 
-		raw_spin_lock_irq(&rq->lock);
+		rq_lock_irq(rq, &rf);
 		cfs_rq->runtime_enabled = runtime_enabled;
 		cfs_rq->runtime_remaining = 0;
 
 		if (cfs_rq->throttled)
 			unthrottle_cfs_rq(cfs_rq);
-		raw_spin_unlock_irq(&rq->lock);
+		rq_unlock_irq(rq, &rf);
 	}
 	if (runtime_was_enabled && !runtime_enabled)
 		cfs_bandwidth_usage_dec();

kernel/sched/deadline.c

···
  *
  * This function returns true if:
  *
- *   runtime / (deadline - t) > dl_runtime / dl_period ,
+ *   runtime / (deadline - t) > dl_runtime / dl_deadline ,
  *
  * IOW we can't recycle current parameters.
  *
- * Notice that the bandwidth check is done against the period. For
+ * Notice that the bandwidth check is done against the deadline. For
  * task with deadline equal to period this is the same of using
- * dl_deadline instead of dl_period in the equation above.
+ * dl_period instead of dl_deadline in the equation above.
  */
 static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
 			       struct sched_dl_entity *pi_se, u64 t)
···
 	 * of anything below microseconds resolution is actually fiction
 	 * (but still we want to give the user that illusion >;).
 	 */
-	left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+	left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
 	right = ((dl_se->deadline - t) >> DL_SCALE) *
 		(pi_se->dl_runtime >> DL_SCALE);
 
···
 	}
 }
 
+static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
+{
+	return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period;
+}
+
 /*
  * If the entity depleted all its runtime, and if we want it to sleep
  * while waiting for some new execution time to become available, we
- * set the bandwidth enforcement timer to the replenishment instant
+ * set the bandwidth replenishment timer to the replenishment instant
  * and try to activate it.
  *
  * Notice that it is important for the caller to know if the timer
···
 	 * that it is actually coming from rq->clock and not from
 	 * hrtimer's time base reading.
 	 */
-	act = ns_to_ktime(dl_se->deadline);
+	act = ns_to_ktime(dl_next_period(dl_se));
 	now = hrtimer_cb_get_time(timer);
 	delta = ktime_to_ns(now) - rq_clock(rq);
 	act = ktime_add_ns(act, delta);
···
 		lockdep_unpin_lock(&rq->lock, rf.cookie);
 		rq = dl_task_offline_migration(rq, p);
 		rf.cookie = lockdep_pin_lock(&rq->lock);
+		update_rq_clock(rq);
 
 		/*
 		 * Now that the task has been migrated to the new RQ and we
···
 
 	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	timer->function = dl_task_timer;
+}
+
+/*
+ * During the activation, CBS checks if it can reuse the current task's
+ * runtime and period. If the deadline of the task is in the past, CBS
+ * cannot use the runtime, and so it replenishes the task. This rule
+ * works fine for implicit deadline tasks (deadline == period), and the
+ * CBS was designed for implicit deadline tasks. However, a task with
+ * constrained deadline (deadine < period) might be awakened after the
+ * deadline, but before the next period. In this case, replenishing the
+ * task would allow it to run for runtime / deadline. As in this case
+ * deadline < period, CBS enables a task to run for more than the
+ * runtime / period. In a very loaded system, this can cause a domino
+ * effect, making other tasks miss their deadlines.
+ *
+ * To avoid this problem, in the activation of a constrained deadline
+ * task after the deadline but before the next period, throttle the
+ * task and set the replenishing timer to the begin of the next period,
+ * unless it is boosted.
+ */
+static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
+{
+	struct task_struct *p = dl_task_of(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
+
+	if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
+	    dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
+		if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
+			return;
+		dl_se->dl_throttled = 1;
+	}
 }
 
 static
···
 	__dequeue_dl_entity(dl_se);
 }
 
+static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
+{
+	return dl_se->dl_deadline < dl_se->dl_period;
+}
+
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct task_struct *pi_task = rt_mutex_get_top_task(p);
···
 		BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH);
 		return;
 	}
+
+	/*
+	 * Check if a constrained deadline task was activated
+	 * after the deadline but before the next period.
+	 * If that is the case, the task will be throttled and
+	 * the replenishment timer will be set to the next period.
+	 */
+	if (!p->dl.dl_throttled && dl_is_constrained(&p->dl))
+		dl_check_constrained_dl(&p->dl);
 
 	/*
 	 * If p is throttled, we do nothing. In fact, if it exhausted

kernel/sched/fair.c

···
  * Approximate:
  *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
  */
-static __always_inline u64 decay_load(u64 val, u64 n)
+static u64 decay_load(u64 val, u64 n)
 {
 	unsigned int local_n;
 
···
 	return val;
 }
 
-/*
- * For updates fully spanning n periods, the contribution to runnable
- * average will be: \Sum 1024*y^n
- *
- * We can compute this reasonably efficiently by combining:
- *   y^PERIOD = 1/2 with precomputed \Sum 1024*y^n {for  n <PERIOD}
- */
-static u32 __compute_runnable_contrib(u64 n)
+static u32 __accumulate_sum(u64 periods, u32 period_contrib, u32 remainder)
 {
-	u32 contrib = 0;
+	u32 c1, c2, c3 = remainder; /* y^0 == 1 */
 
-	if (likely(n <= LOAD_AVG_PERIOD))
-		return runnable_avg_yN_sum[n];
-	else if (unlikely(n >= LOAD_AVG_MAX_N))
+	if (!periods)
+		return remainder - period_contrib;
+
+	if (unlikely(periods >= LOAD_AVG_MAX_N))
 		return LOAD_AVG_MAX;
 
-	/* Since n < LOAD_AVG_MAX_N, n/LOAD_AVG_PERIOD < 11 */
-	contrib = __accumulated_sum_N32[n/LOAD_AVG_PERIOD];
-	n %= LOAD_AVG_PERIOD;
-	contrib = decay_load(contrib, n);
-	return contrib + runnable_avg_yN_sum[n];
+	/*
+	 * c1 = d1 y^(p+1)
+	 */
+	c1 = decay_load((u64)(1024 - period_contrib), periods);
+
+	periods -= 1;
+	/*
+	 * For updates fully spanning n periods, the contribution to runnable
+	 * average will be:
+	 *
+	 *   c2 = 1024 \Sum y^n
+	 *
+	 * We can compute this reasonably efficiently by combining:
+	 *
+	 *   y^PERIOD = 1/2 with precomputed 1024 \Sum y^n {for: n < PERIOD}
+	 */
+	if (likely(periods <= LOAD_AVG_PERIOD)) {
+		c2 = runnable_avg_yN_sum[periods];
+	} else {
+		c2 = __accumulated_sum_N32[periods/LOAD_AVG_PERIOD];
+		periods %= LOAD_AVG_PERIOD;
+		c2 = decay_load(c2, periods);
+		c2 += runnable_avg_yN_sum[periods];
+	}
+
+	return c1 + c2 + c3;
 }
 
 #define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+
+/*
+ * Accumulate the three separate parts of the sum; d1 the remainder
+ * of the last (incomplete) period, d2 the span of full periods and d3
+ * the remainder of the (incomplete) current period.
+ *
+ *           d1          d2           d3
+ *           ^           ^            ^
+ *           |           |            |
+ *         |<->|<----------------->|<--->|
+ * ... |---x---|------| ... |------|-----x (now)
+ *
+ *                                p
+ * u' = (u + d1) y^(p+1) + 1024 \Sum y^n + d3 y^0
+ *                               n=1
+ *
+ *    = u y^(p+1) +				(Step 1)
+ *
+ *                          p
+ *      d1 y^(p+1) + 1024 \Sum y^n + d3 y^0	(Step 2)
+ *                         n=1
+ */
+static __always_inline u32
+accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
+	       unsigned long weight, int running, struct cfs_rq *cfs_rq)
+{
+	unsigned long scale_freq, scale_cpu;
+	u64 periods;
+	u32 contrib;
+
+	scale_freq = arch_scale_freq_capacity(NULL, cpu);
+	scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+
+	delta += sa->period_contrib;
+	periods = delta / 1024; /* A period is 1024us (~1ms) */
+
+	/*
+	 * Step 1: decay old *_sum if we crossed period boundaries.
+	 */
+	if (periods) {
+		sa->load_sum = decay_load(sa->load_sum, periods);
+		if (cfs_rq) {
+			cfs_rq->runnable_load_sum =
+				decay_load(cfs_rq->runnable_load_sum, periods);
+		}
+		sa->util_sum = decay_load((u64)(sa->util_sum), periods);
+	}
+
+	/*
+	 * Step 2
+	 */
+	delta %= 1024;
+	contrib = __accumulate_sum(periods, sa->period_contrib, delta);
+	sa->period_contrib = delta;
+
+	contrib = cap_scale(contrib, scale_freq);
+	if (weight) {
+		sa->load_sum += weight * contrib;
+		if (cfs_rq)
+			cfs_rq->runnable_load_sum += weight * contrib;
+	}
+	if (running)
+		sa->util_sum += contrib * scale_cpu;
+
+	return periods;
+}
 
 /*
  * We can represent the historical contribution to runnable average as the
···
  *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
  */
 static __always_inline int
-__update_load_avg(u64 now, int cpu, struct sched_avg *sa,
+___update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 		  unsigned long weight, int running, struct cfs_rq *cfs_rq)
 {
-	u64 delta, scaled_delta, periods;
-	u32 contrib;
-	unsigned int delta_w, scaled_delta_w, decayed = 0;
-	unsigned long scale_freq, scale_cpu;
+	u64 delta;
 
 	delta = now - sa->last_update_time;
 	/*
···
 		return 0;
 	sa->last_update_time = now;
 
-	scale_freq = arch_scale_freq_capacity(NULL, cpu);
-	scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+	/*
+	 * Now we know we crossed measurement unit boundaries. The *_avg
+	 * accrues by two steps:
+	 *
+	 * Step 1: accumulate *_sum since last_update_time. If we haven't
+	 * crossed period boundaries, finish.
+	 */
+	if (!accumulate_sum(delta, cpu, sa, weight, running, cfs_rq))
+		return 0;
 
-	/* delta_w is the amount already accumulated against our next period */
-	delta_w = sa->period_contrib;
-	if (delta + delta_w >= 1024) {
-		decayed = 1;
-
-		/* how much left for next period will start over, we don't know yet */
-		sa->period_contrib = 0;
-
-		/*
-		 * Now that we know we're crossing a period boundary, figure
-		 * out how much from delta we need to complete the current
-		 * period and accrue it.
-		 */
-		delta_w = 1024 - delta_w;
-		scaled_delta_w = cap_scale(delta_w, scale_freq);
-		if (weight) {
-			sa->load_sum += weight * scaled_delta_w;
-			if (cfs_rq) {
-				cfs_rq->runnable_load_sum +=
-						weight * scaled_delta_w;
-			}
-		}
-		if (running)
-			sa->util_sum += scaled_delta_w * scale_cpu;
-
-		delta -= delta_w;
-
-		/* Figure out how many additional periods this update spans */
-		periods = delta / 1024;
-		delta %= 1024;
-
-		sa->load_sum = decay_load(sa->load_sum, periods + 1);
-		if (cfs_rq) {
-			cfs_rq->runnable_load_sum =
-				decay_load(cfs_rq->runnable_load_sum, periods + 1);
-		}
-		sa->util_sum = decay_load((u64)(sa->util_sum), periods + 1);
-
-		/* Efficiently calculate \sum (1..n_period) 1024*y^i */
-		contrib = __compute_runnable_contrib(periods);
-		contrib = cap_scale(contrib, scale_freq);
-		if (weight) {
-			sa->load_sum += weight * contrib;
-			if (cfs_rq)
-				cfs_rq->runnable_load_sum += weight * contrib;
-		}
-		if (running)
-			sa->util_sum += contrib * scale_cpu;
+	/*
+	 * Step 2: update *_avg.
+	 */
+	sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX);
+	if (cfs_rq) {
+		cfs_rq->runnable_load_avg =
+			div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
 	}
+	sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
 
-	/* Remainder of delta accrued against u_0` */
-	scaled_delta = cap_scale(delta, scale_freq);
-	if (weight) {
-		sa->load_sum += weight * scaled_delta;
-		if (cfs_rq)
-			cfs_rq->runnable_load_sum += weight * scaled_delta;
-	}
-	if (running)
-		sa->util_sum += scaled_delta * scale_cpu;
+	return 1;
+}
 
-	sa->period_contrib += delta;
+static int
+__update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
+{
+	return ___update_load_avg(now, cpu, &se->avg, 0, 0, NULL);
+}
 
-	if (decayed) {
-		sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX);
-		if (cfs_rq) {
-			cfs_rq->runnable_load_avg =
-				div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
-		}
-		sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
-	}
+static int
+__update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	return ___update_load_avg(now, cpu, &se->avg,
+				  se->on_rq * scale_load_down(se->load.weight),
+				  cfs_rq->curr == se, NULL);
+}
 
-	return decayed;
+static int
+__update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
+{
+	return ___update_load_avg(now, cpu, &cfs_rq->avg,
+			scale_load_down(cfs_rq->load.weight),
+			cfs_rq->curr != NULL, cfs_rq);
 }
 
 /*
···
 void set_task_rq_fair(struct sched_entity *se,
 		      struct cfs_rq *prev, struct cfs_rq *next)
 {
+	u64 p_last_update_time;
+	u64 n_last_update_time;
+
 	if (!sched_feat(ATTACH_AGE_LOAD))
 		return;
 
···
 	 * time. This will result in the wakee task is less decayed, but giving
 	 * the wakee more load sounds not bad.
 	 */
-	if (se->avg.last_update_time && prev) {
-		u64 p_last_update_time;
-		u64 n_last_update_time;
+	if (!(se->avg.last_update_time && prev))
+		return;
 
 #ifndef CONFIG_64BIT
+	{
 		u64 p_last_update_time_copy;
 		u64 n_last_update_time_copy;
 
···
 
 		} while (p_last_update_time != p_last_update_time_copy ||
 			 n_last_update_time != n_last_update_time_copy);
-#else
-		p_last_update_time = prev->avg.last_update_time;
-		n_last_update_time = next->avg.last_update_time;
-#endif
-		__update_load_avg(p_last_update_time, cpu_of(rq_of(prev)),
-				  &se->avg, 0, 0, NULL);
-		se->avg.last_update_time = n_last_update_time;
 	}
+#else
+	p_last_update_time = prev->avg.last_update_time;
+	n_last_update_time = next->avg.last_update_time;
+#endif
+	__update_load_avg_blocked_se(p_last_update_time, cpu_of(rq_of(prev)), se);
+	se->avg.last_update_time = n_last_update_time;
 }
 
 /* Take into account change of utilization of a child task group */
···
 	return 1;
 }
 
+/*
+ * Check if we need to update the load and the utilization of a blocked
+ * group_entity:
+ */
+static inline bool skip_blocked_update(struct sched_entity *se)
+{
+	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
+
+	/*
+	 * If sched_entity still have not zero load or utilization, we have to
+	 * decay it:
+	 */
+	if (se->avg.load_avg || se->avg.util_avg)
+		return false;
+
+	/*
+	 * If there is a pending propagation, we have to update the load and
+	 * the utilization of the sched_entity:
+	 */
+	if (gcfs_rq->propagate_avg)
+		return false;
+
+	/*
+	 * Otherwise, the load and the utilization of the sched_entity is
+	 * already zero and there is no pending propagation, so it will be a
+	 * waste of time to try to decay it:
+	 */
+	return true;
+}
+
 #else /* CONFIG_FAIR_GROUP_SCHED */
 
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
···
 		set_tg_cfs_propagate(cfs_rq);
 	}
 
-	decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
-		scale_load_down(cfs_rq->load.weight), cfs_rq->curr != NULL, cfs_rq);
+	decayed = __update_load_avg_cfs_rq(now, cpu_of(rq_of(cfs_rq)), cfs_rq);
 
 #ifndef CONFIG_64BIT
 	smp_wmb();
···
 	 * Track task load average for carrying it to new CPU after migrated, and
 	 * track group sched_entity load average for task_h_load calc in migration
 	 */
-	if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD)) {
-		__update_load_avg(now, cpu, &se->avg,
-			  se->on_rq * scale_load_down(se->load.weight),
-			  cfs_rq->curr == se, NULL);
-	}
+	if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD))
+		__update_load_avg_se(now, cpu, cfs_rq, se);
 
 	decayed  = update_cfs_rq_load_avg(now, cfs_rq, true);
 	decayed |= propagate_entity_load_avg(se);
···
 	u64 last_update_time;
 
 	last_update_time = cfs_rq_last_update_time(cfs_rq);
-	__update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
+	__update_load_avg_blocked_se(last_update_time, cpu_of(rq_of(cfs_rq)), se);
 }
 
 /*
···
 	list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
 				throttled_list) {
 		struct rq *rq = rq_of(cfs_rq);
+		struct rq_flags rf;
 
-		raw_spin_lock(&rq->lock);
+		rq_lock(rq, &rf);
 		if (!cfs_rq_throttled(cfs_rq))
 			goto next;
 
···
 			unthrottle_cfs_rq(cfs_rq);
 
 next:
-		raw_spin_unlock(&rq->lock);
+		rq_unlock(rq, &rf);
 
 		if (!remaining)
 			break;
···
 	unsigned long curr_jiffies = READ_ONCE(jiffies);
 	struct rq *this_rq = this_rq();
 	unsigned long load;
+	struct rq_flags rf;
 
 	if (curr_jiffies == this_rq->last_load_update_tick)
 		return;
 
 	load = weighted_cpuload(cpu_of(this_rq));
-	raw_spin_lock(&this_rq->lock);
+	rq_lock(this_rq, &rf);
 	update_rq_clock(this_rq);
 	cpu_load_update_nohz(this_rq, curr_jiffies, load);
-	raw_spin_unlock(&this_rq->lock);
+	rq_unlock(this_rq, &rf);
 }
 #else /* !CONFIG_NO_HZ_COMMON */
 static inline void cpu_load_update_nohz(struct rq *this_rq,
···
 	lockdep_assert_held(&env->src_rq->lock);
 
 	p->on_rq = TASK_ON_RQ_MIGRATING;
-	deactivate_task(env->src_rq, p, 0);
+	deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, env->dst_cpu);
 }
 
···
 	lockdep_assert_held(&rq->lock);
 
 	BUG_ON(task_rq(p) != rq);
-	activate_task(rq, p, 0);
+	activate_task(rq, p, ENQUEUE_NOCLOCK);
 	p->on_rq = TASK_ON_RQ_QUEUED;
 	check_preempt_curr(rq, p, 0);
 }
···
  */
 static void attach_one_task(struct rq *rq, struct task_struct *p)
 {
-	raw_spin_lock(&rq->lock);
+	struct rq_flags rf;
+
+	rq_lock(rq, &rf);
+	update_rq_clock(rq);
 	attach_task(rq, p);
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, &rf);
 }
 
 /*
···
 {
 	struct list_head *tasks = &env->tasks;
 	struct task_struct *p;
+	struct rq_flags rf;
 
-	raw_spin_lock(&env->dst_rq->lock);
+	rq_lock(env->dst_rq, &rf);
+	update_rq_clock(env->dst_rq);
 
 	while (!list_empty(tasks)) {
 		p = list_first_entry(tasks, struct task_struct, se.group_node);
···
 		attach_task(env->dst_rq, p);
 	}
 
-	raw_spin_unlock(&env->dst_rq->lock);
+	rq_unlock(env->dst_rq, &rf);
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
···
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq;
-	unsigned long flags;
+	struct rq_flags rf;
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
+	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
 	/*
···
 	 * list_add_leaf_cfs_rq() for details.
 	 */
 	for_each_leaf_cfs_rq(rq, cfs_rq) {
+		struct sched_entity *se;
+
 		/* throttled entities do not contribute to load */
 		if (throttled_hierarchy(cfs_rq))
 			continue;
···
 		if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true))
 			update_tg_load_avg(cfs_rq, 0);
 
-		/* Propagate pending load changes to the parent */
-		if (cfs_rq->tg->se[cpu])
-			update_load_avg(cfs_rq->tg->se[cpu], 0);
+		/* Propagate pending load changes to the parent, if any: */
+		se = cfs_rq->tg->se[cpu];
+		if (se && !skip_blocked_update(se))
+			update_load_avg(se, 0);
 	}
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	rq_unlock_irqrestore(rq, &rf);
 }
 
 /*
···
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq = &rq->cfs;
-	unsigned long flags;
+	struct rq_flags rf;
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
+	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 	update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	rq_unlock_irqrestore(rq, &rf);
 }
 
 static unsigned long task_h_load(struct task_struct *p)
···
 {
 	struct sched_domain *child = env->sd->child;
 	struct sched_group *sg = env->sd->groups;
+	struct sg_lb_stats *local = &sds->local_stat;
 	struct sg_lb_stats tmp_sgs;
 	int load_idx, prefer_sibling = 0;
 	bool overload = false;
···
 		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
 		if (local_group) {
 			sds->local = sg;
-			sgs = &sds->local_stat;
+			sgs = local;
 
 			if (env->idle != CPU_NEWLY_IDLE ||
 			    time_after_eq(jiffies, sg->sgc->next_update))
···
 		 * the tasks on the system).
 		 */
 		if (prefer_sibling && sds->local &&
-		    group_has_capacity(env, &sds->local_stat) &&
-		    (sgs->sum_nr_running > 1)) {
+		    group_has_capacity(env, local) &&
+		    (sgs->sum_nr_running > local->sum_nr_running + 1)) {
 			sgs->group_no_capacity = 1;
 			sgs->group_type = group_classify(sg, sgs);
 		}
···
 	struct sched_domain *sd_parent = sd->parent;
 	struct sched_group *group;
 	struct rq *busiest;
-	unsigned long flags;
+	struct rq_flags rf;
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask);
 
 	struct lb_env env = {
···
 		env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);
 
 more_balance:
-		raw_spin_lock_irqsave(&busiest->lock, flags);
+		rq_lock_irqsave(busiest, &rf);
 		update_rq_clock(busiest);
 
 		/*
···
 		 * See task_rq_lock() family for the details.
 		 */
 
-		raw_spin_unlock(&busiest->lock);
+		rq_unlock(busiest, &rf);
 
 		if (cur_ld_moved) {
 			attach_tasks(&env);
 			ld_moved += cur_ld_moved;
 		}
 
-		local_irq_restore(flags);
+		local_irq_restore(rf.flags);
 
 		if (env.flags & LBF_NEED_BREAK) {
 			env.flags &= ~LBF_NEED_BREAK;
···
 			sd->nr_balance_failed++;
 
 		if (need_active_balance(&env)) {
+			unsigned long flags;
+
 			raw_spin_lock_irqsave(&busiest->lock, flags);
 
 			/* don't kick the active_load_balance_cpu_stop,
···
 	struct rq *target_rq = cpu_rq(target_cpu);
 	struct sched_domain *sd;
 	struct task_struct *p = NULL;
+	struct rq_flags rf;
 
-	raw_spin_lock_irq(&busiest_rq->lock);
+	rq_lock_irq(busiest_rq, &rf);
 
 	/* make sure the requested cpu hasn't gone down in the meantime */
 	if (unlikely(busiest_cpu != smp_processor_id() ||
···
 	rcu_read_unlock();
 out_unlock:
 	busiest_rq->active_balance = 0;
-	raw_spin_unlock(&busiest_rq->lock);
+	rq_unlock(busiest_rq, &rf);
 
 	if (p)
 		attach_one_task(target_rq, p);
···
 		 * do the balance.
 		 */
 		if (time_after_eq(jiffies, rq->next_balance)) {
-			raw_spin_lock_irq(&rq->lock);
+			struct rq_flags rf;
+
+			rq_lock_irq(rq, &rf);
 			update_rq_clock(rq);
 			cpu_load_update_idle(rq);
-			raw_spin_unlock_irq(&rq->lock);
+			rq_unlock_irq(rq, &rf);
+
 			rebalance_domains(rq, CPU_IDLE);
 		}
 
···
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se, *curr;
 	struct rq *rq = this_rq();
+	struct rq_flags rf;
 
-	raw_spin_lock(&rq->lock);
+	rq_lock(rq, &rf);
 	update_rq_clock(rq);
 
 	cfs_rq = task_cfs_rq(current);
···
 	}
 
 	se->vruntime -= cfs_rq->min_vruntime;
-	raw_spin_unlock(&rq->lock);
+	rq_unlock(rq, &rf);
 }
 
 /*
···
 int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 {
 	int i;
-	unsigned long flags;
 
 	/*
 	 * We can't change the weight of the root cgroup.
···
 	tg->shares = shares;
 	for_each_possible_cpu(i) {
 		struct rq *rq = cpu_rq(i);
-		struct sched_entity *se;
+		struct sched_entity *se = tg->se[i];
+		struct rq_flags rf;
 
-		se = tg->se[i];
 		/* Propagate contribution to hierarchy */
-		raw_spin_lock_irqsave(&rq->lock, flags);
-
-		/* Possible calls to update_curr() need rq clock */
+		rq_lock_irqsave(rq, &rf);
 		update_rq_clock(rq);
 		for_each_sched_entity(se) {
 			update_load_avg(se, UPDATE_TG);
 			update_cfs_shares(se);
 		}
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
+		rq_unlock_irqrestore(rq, &rf);
 	}
 
 done:

kernel/sched/features.h

···
  */
 SCHED_FEAT(SIS_AVG_CPU, false)
 
+/*
+ * Issue a WARN when we do multiple update_rq_clock() calls
+ * in a single rq->lock section. Default disabled because the
+ * annotations are not complete.
+ */
+SCHED_FEAT(WARN_DOUBLE_CLOCK, false)
+
 #ifdef HAVE_RT_PUSH_IPI
 /*
  * In order to avoid a thundering herd attack of CPUs that are

kernel/sched/loadavg.c

···
 	 * If the folding window started, make sure we start writing in the
 	 * next idle-delta.
 	 */
-	if (!time_before(jiffies, calc_load_update))
+	if (!time_before(jiffies, READ_ONCE(calc_load_update)))
 		idx++;
 
 	return idx & 1;
···
 	struct rq *this_rq = this_rq();
 
 	/*
-	 * If we're still before the sample window, we're done.
+	 * If we're still before the pending sample window, we're done.
 	 */
+	this_rq->calc_load_update = READ_ONCE(calc_load_update);
 	if (time_before(jiffies, this_rq->calc_load_update))
 		return;
 
···
 	 * accounted through the nohz accounting, so skip the entire deal and
 	 * sync up for the next window.
 	 */
-	this_rq->calc_load_update = calc_load_update;
 	if (time_before(jiffies, this_rq->calc_load_update + 10))
 		this_rq->calc_load_update += LOAD_FREQ;
 }
···
  */
 static void calc_global_nohz(void)
 {
+	unsigned long sample_window;
 	long delta, active, n;
 
-	if (!time_before(jiffies, calc_load_update + 10)) {
+	sample_window = READ_ONCE(calc_load_update);
+	if (!time_before(jiffies, sample_window + 10)) {
 		/*
 		 * Catch-up, fold however many we are behind still
 		 */
-		delta = jiffies - calc_load_update - 10;
+		delta = jiffies - sample_window - 10;
 		n = 1 + (delta / LOAD_FREQ);
 
 		active = atomic_long_read(&calc_load_tasks);
···
 		avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
 		avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
 
-		calc_load_update += n * LOAD_FREQ;
+		WRITE_ONCE(calc_load_update, sample_window + n * LOAD_FREQ);
 	}
 
 	/*
···
  */
 void calc_global_load(unsigned long ticks)
 {
+	unsigned long sample_window;
 	long active, delta;
 
-	if (time_before(jiffies, calc_load_update + 10))
+	sample_window = READ_ONCE(calc_load_update);
+	if (time_before(jiffies, sample_window + 10))
 		return;
 
 	/*
···
 	avenrun[1] = calc_load(avenrun[1], EXP_5, active);
 	avenrun[2] = calc_load(avenrun[2], EXP_15, active);
 
-	calc_load_update += LOAD_FREQ;
+	WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ);
 
 	/*
 	 * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.

kernel/sched/rt.c

···
 #define RT_PUSH_IPI_EXECUTING		1
 #define RT_PUSH_IPI_RESTART		2
 
+/*
+ * When a high priority task schedules out from a CPU and a lower priority
+ * task is scheduled in, a check is made to see if there's any RT tasks
+ * on other CPUs that are waiting to run because a higher priority RT task
+ * is currently running on its CPU. In this case, the CPU with multiple RT
+ * tasks queued on it (overloaded) needs to be notified that a CPU has opened
+ * up that may be able to run one of its non-running queued RT tasks.
+ *
+ * On large CPU boxes, there's the case that several CPUs could schedule
+ * a lower priority task at the same time, in which case it will look for
+ * any overloaded CPUs that it could pull a task from. To do this, the runqueue
+ * lock must be taken from that overloaded CPU. Having 10s of CPUs all fighting
+ * for a single overloaded CPU's runqueue lock can produce a large latency.
+ * (This has actually been observed on large boxes running cyclictest).
+ * Instead of taking the runqueue lock of the overloaded CPU, each of the
+ * CPUs that scheduled a lower priority task simply sends an IPI to the
+ * overloaded CPU. An IPI is much cheaper than taking an runqueue lock with
+ * lots of contention. The overloaded CPU will look to push its non-running
+ * RT task off, and if it does, it can then ignore the other IPIs coming
+ * in, and just pass those IPIs off to any other overloaded CPU.
+ *
+ * When a CPU schedules a lower priority task, it only sends an IPI to
+ * the "next" CPU that has overloaded RT tasks. This prevents IPI storms,
+ * as having 10 CPUs scheduling lower priority tasks and 10 CPUs with
+ * RT overloaded tasks, would cause 100 IPIs to go out at once.
+ *
+ * The overloaded RT CPU, when receiving an IPI, will try to push off its
+ * overloaded RT tasks and then send an IPI to the next CPU that has
+ * overloaded RT tasks. This stops when all CPUs with overloaded RT tasks
+ * have completed. Just because a CPU may have pushed off its own overloaded
+ * RT task does not mean it should stop sending the IPI around to other
+ * overloaded CPUs. There may be another RT task waiting to run on one of
+ * those CPUs that are of higher priority than the one that was just
+ * pushed.
+ *
+ * An optimization that could possibly be made is to make a CPU array similar
+ * to the cpupri array mask of all running RT tasks, but for the overloaded
+ * case, then the IPI could be sent to only the CPU with the highest priority
+ * RT task waiting, and that CPU could send off further IPIs to the CPU with
+ * the next highest waiting task. Since the overloaded case is much less likely
+ * to happen, the complexity of this implementation may not be worth it.
+ * Instead, just send an IPI around to all overloaded CPUs.
+ *
+ * The rq->rt.push_flags holds the status of the IPI that is going around.
+ * A run queue can only send out a single IPI at a time. The possible flags
+ * for rq->rt.push_flags are:
+ *
+ *    (None or zero):		No IPI is going around for the current rq
+ *    RT_PUSH_IPI_EXECUTING:	An IPI for the rq is being passed around
+ *    RT_PUSH_IPI_RESTART:	The priority of the running task for the rq
+ *				has changed, and the IPI should restart
+ *				circulating the overloaded CPUs again.
+ *
+ * rq->rt.push_cpu contains the CPU that is being sent the IPI. It is updated
+ * before sending to the next CPU.
+ *
+ * Instead of having all CPUs that schedule a lower priority task send
+ * an IPI to the same "first" CPU in the RT overload mask, they send it
+ * to the next overloaded CPU after their own CPU. This helps distribute
+ * the work when there's more than one overloaded CPU and multiple CPUs
+ * scheduling in lower priority tasks.
+ *
+ * When a rq schedules a lower priority task than what was currently
+ * running, the next CPU with overloaded RT tasks is examined first.
+ * That is, if CPU 1 and 5 are overloaded, and CPU 3 schedules a lower
+ * priority task, it will send an IPI first to CPU 5, then CPU 5 will
+ * send to CPU 1 if it is still overloaded. CPU 1 will clear the
+ * rq->rt.push_flags if RT_PUSH_IPI_RESTART is not set.
+ *
+ * The first CPU to notice IPI_RESTART is set, will clear that flag and then
+ * send an IPI to the next overloaded CPU after the rq->cpu and not the next
+ * CPU after push_cpu. That is, if CPU 1, 4 and 5 are overloaded when CPU 3
+ * schedules a lower priority task, and the IPI_RESTART gets set while the
+ * handling is being done on CPU 5, it will clear the flag and send it back to
+ * CPU 4 instead of CPU 1.
+ *
+ * Note, the above logic can be disabled by turning off the sched_feature
+ * RT_PUSH_IPI. Then the rq lock of the overloaded CPU will simply be
+ * taken by the CPU requesting a pull and the waiting RT task will be pulled
+ * by that CPU. This may be fine for machines with few CPUs.
+ */
 static void tell_cpu_to_push(struct rq *rq)
 {
 	int cpu;

kernel/sched/sched.h

···
 #define DEQUEUE_SLEEP		0x01
 #define DEQUEUE_SAVE		0x02 /* matches ENQUEUE_RESTORE */
 #define DEQUEUE_MOVE		0x04 /* matches ENQUEUE_MOVE */
+#define DEQUEUE_NOCLOCK		0x08 /* matches ENQUEUE_NOCLOCK */
 
 #define ENQUEUE_WAKEUP		0x01
 #define ENQUEUE_RESTORE		0x02
 #define ENQUEUE_MOVE		0x04
+#define ENQUEUE_NOCLOCK		0x08
 
-#define ENQUEUE_HEAD		0x08
-#define ENQUEUE_REPLENISH	0x10
+#define ENQUEUE_HEAD		0x10
+#define ENQUEUE_REPLENISH	0x20
 #ifdef CONFIG_SMP
-#define ENQUEUE_MIGRATED	0x20
+#define ENQUEUE_MIGRATED	0x40
 #else
 #define ENQUEUE_MIGRATED	0x00
 #endif
···
 
 struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 	__acquires(rq->lock);
+
 struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 	__acquires(p->pi_lock)
 	__acquires(rq->lock);
···
 	rq_unpin_lock(rq, rf);
 	raw_spin_unlock(&rq->lock);
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
+}
+
+static inline void
+rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
+	__acquires(rq->lock)
+{
+	raw_spin_lock_irqsave(&rq->lock, rf->flags);
+	rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock_irq(struct rq *rq, struct rq_flags *rf)
+	__acquires(rq->lock)
+{
+	raw_spin_lock_irq(&rq->lock);
+	rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock(struct rq *rq, struct rq_flags *rf)
+	__acquires(rq->lock)
+{
+	raw_spin_lock(&rq->lock);
+	rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_relock(struct rq *rq, struct rq_flags *rf)
+	__acquires(rq->lock)
+{
+	raw_spin_lock(&rq->lock);
+	rq_repin_lock(rq, rf);
+}
+
+static inline void
+rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
+	__releases(rq->lock)
+{
+	rq_unpin_lock(rq, rf);
+	raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
+}
+
+static inline void
+rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
+	__releases(rq->lock)
+{
+	rq_unpin_lock(rq, rf);
+	raw_spin_unlock_irq(&rq->lock);
+}
+
+static inline void
+rq_unlock(struct rq *rq, struct rq_flags *rf)
+	__releases(rq->lock)
+{
+	rq_unpin_lock(rq, rf);
+	raw_spin_unlock(&rq->lock);
 }
 
 #ifdef CONFIG_SMP

kernel/workqueue.c

···
 	struct timer_list *timer = &dwork->timer;
 	struct work_struct *work = &dwork->work;
 
+	WARN_ON_ONCE(!wq);
 	WARN_ON_ONCE(timer->function != delayed_work_timer_fn ||
 		     timer->data != (unsigned long)dwork);
 	WARN_ON_ONCE(timer_pending(timer));

mm/gup.c

···
 			if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr,
 					 P4D_SHIFT, next, write, pages, nr))
 				return 0;
-		} else if (!gup_p4d_range(p4d, addr, next, write, pages, nr))
+		} else if (!gup_pud_range(p4d, addr, next, write, pages, nr))
 			return 0;
 	} while (p4dp++, addr = next, addr != end);
 

mm/percpu-vm.c

···
 
 /**
  * pcpu_get_pages - get temp pages array
- * @chunk: chunk of interest
  *
  * Returns pointer to array of pointers to struct page which can be indexed
  * with pcpu_page_idx().  Note that there is only one array and accesses
···
  * RETURNS:
  * Pointer to temp pages array on success.
  */
-static struct page **pcpu_get_pages(struct pcpu_chunk *chunk_alloc)
+static struct page **pcpu_get_pages(void)
 {
 	static struct page **pages;
 	size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]);
···
 {
 	struct page **pages;
 
-	pages = pcpu_get_pages(chunk);
+	pages = pcpu_get_pages();
 	if (!pages)
 		return -ENOMEM;
 
···
 	 * successful population attempt so the temp pages array must
 	 * be available now.
 	 */
-	pages = pcpu_get_pages(chunk);
+	pages = pcpu_get_pages();
 	BUG_ON(!pages);
 
 	/* unmap and free */

mm/percpu.c

···
 		mutex_unlock(&pcpu_alloc_mutex);
 	}
 
-	if (chunk != pcpu_reserved_chunk)
+	if (chunk != pcpu_reserved_chunk) {
+		spin_lock_irqsave(&pcpu_lock, flags);
 		pcpu_nr_empty_pop_pages -= occ_pages;
+		spin_unlock_irqrestore(&pcpu_lock, flags);
+	}
 
 	if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
 		pcpu_schedule_balance_work();

net/atm/svc.c

···
 	return error;
 }
 
-static int svc_accept(struct socket *sock, struct socket *newsock, int flags)
+static int svc_accept(struct socket *sock, struct socket *newsock, int flags,
+		      bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
···
 
 	lock_sock(sk);
 
-	error = svc_create(sock_net(sk), newsock, 0, 0);
+	error = svc_create(sock_net(sk), newsock, 0, kern);
 	if (error)
 		goto out;
 

net/ax25/af_ax25.c

···
 	return err;
 }
 
-static int ax25_accept(struct socket *sock, struct socket *newsock, int flags)
+static int ax25_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sk_buff *skb;
 	struct sock *newsk;

net/bluetooth/l2cap_sock.c

···
 }
 
 static int l2cap_sock_accept(struct socket *sock, struct socket *newsock,
-			     int flags)
+			     int flags, bool kern)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct sock *sk = sock->sk, *nsk;

net/bluetooth/rfcomm/sock.c

···
 	return err;
 }
 
-static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags)
+static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags,
+			      bool kern)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct sock *sk = sock->sk, *nsk;

net/bluetooth/sco.c

···
 }
 
 static int sco_sock_accept(struct socket *sock, struct socket *newsock,
-			   int flags)
+			   int flags, bool kern)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct sock *sk = sock->sk, *ch;

net/bridge/br_input.c

···
 static int
 br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	br_drop_fake_rtable(skb);
 	return netif_receive_skb(skb);
 }
 

net/bridge/br_netfilter_hooks.c

···
 }
 
 
-/* PF_BRIDGE/LOCAL_IN ************************************************/
-/* The packet is locally destined, which requires a real
- * dst_entry, so detach the fake one.  On the way up, the
- * packet would pass through PRE_ROUTING again (which already
- * took place when the packet entered the bridge), but we
- * register an IPv4 PRE_ROUTING 'sabotage' hook that will
- * prevent this from happening. */
-static unsigned int br_nf_local_in(void *priv,
-				   struct sk_buff *skb,
-				   const struct nf_hook_state *state)
-{
-	br_drop_fake_rtable(skb);
-	return NF_ACCEPT;
-}
-
 /* PF_BRIDGE/FORWARD *************************************************/
 static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
···
 		.hook = br_nf_pre_routing,
 		.pf = NFPROTO_BRIDGE,
 		.hooknum = NF_BR_PRE_ROUTING,
-		.priority = NF_BR_PRI_BRNF,
-	},
-	{
-		.hook = br_nf_local_in,
-		.pf = NFPROTO_BRIDGE,
-		.hooknum = NF_BR_LOCAL_IN,
 		.priority = NF_BR_PRI_BRNF,
 	},
 	{

net/core/dev.c

···
 {
 	rtnl_lock();
 	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
+	call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev);
 	rtnl_unlock();
 }
 EXPORT_SYMBOL(netdev_notify_peers);

net/core/net-sysfs.c

···
 	while (--i >= new_num) {
 		struct kobject *kobj = &dev->_rx[i].kobj;
 
-		if (!list_empty(&dev_net(dev)->exit_list))
+		if (!atomic_read(&dev_net(dev)->count))
 			kobj->uevent_suppress = 1;
 		if (dev->sysfs_rx_queue_group)
 			sysfs_remove_group(kobj, dev->sysfs_rx_queue_group);
···
 	while (--i >= new_num) {
 		struct netdev_queue *queue = dev->_tx + i;
 
-		if (!list_empty(&dev_net(dev)->exit_list))
+		if (!atomic_read(&dev_net(dev)->count))
 			queue->kobj.uevent_suppress = 1;
 #ifdef CONFIG_BQL
 		sysfs_remove_group(&queue->kobj, &dql_group);
···
 {
 	struct device *dev = &(ndev->dev);
 
-	if (!list_empty(&dev_net(ndev)->exit_list))
+	if (!atomic_read(&dev_net(ndev)->count))
 		dev_set_uevent_suppress(dev, 1);
 
 	kobject_get(&dev->kobj);

net/core/skbuff.c

···
 	if (!skb_may_tx_timestamp(sk, false))
 		return;
 
-	/* take a reference to prevent skb_orphan() from freeing the socket */
-	sock_hold(sk);
-
-	*skb_hwtstamps(skb) = *hwtstamps;
-	__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
-
-	sock_put(sk);
+	/* Take a reference to prevent skb_orphan() from freeing the socket,
+	 * but only if the socket refcount is not zero.
+	 */
+	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+		*skb_hwtstamps(skb) = *hwtstamps;
+		__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
+		sock_put(sk);
+	}
 }
 EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
 
···
 {
 	struct sock *sk = skb->sk;
 	struct sock_exterr_skb *serr;
-	int err;
+	int err = 1;
 
 	skb->wifi_acked_valid = 1;
 	skb->wifi_acked = acked;
···
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS;
 
-	/* take a reference to prevent skb_orphan() from freeing the socket */
-	sock_hold(sk);
-
-	err = sock_queue_err_skb(sk, skb);
+	/* Take a reference to prevent skb_orphan() from freeing the socket,
+	 * but only if the socket refcount is not zero.
+	 */
+	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+		err = sock_queue_err_skb(sk, skb);
+		sock_put(sk);
+	}
 	if (err)
 		kfree_skb(skb);
-
-	sock_put(sk);
 }
 EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
 

net/core/sock.c

···
 
 /*
  * Each address family might have different locking rules, so we have
- * one slock key per address family:
+ * one slock key per address family and separate keys for internal and
+ * userspace sockets.
  */
 static struct lock_class_key af_family_keys[AF_MAX];
+static struct lock_class_key af_family_kern_keys[AF_MAX];
 static struct lock_class_key af_family_slock_keys[AF_MAX];
+static struct lock_class_key af_family_kern_slock_keys[AF_MAX];
 
 /*
  * Make lock validator output more readable. (we pre-construct these
  * strings build-time, so that runtime initialization of socket
  * locks is fast):
  */
+
+#define _sock_locks(x)						  \
+  x "AF_UNSPEC",	x "AF_UNIX"     ,	x "AF_INET"     , \
+  x "AF_AX25"  ,	x "AF_IPX"      ,	x "AF_APPLETALK", \
+  x "AF_NETROM",	x "AF_BRIDGE"   ,	x "AF_ATMPVC"   , \
+  x "AF_X25"   ,	x "AF_INET6"    ,	x "AF_ROSE"     , \
+  x "AF_DECnet",	x "AF_NETBEUI"  ,	x "AF_SECURITY" , \
+  x "AF_KEY"   ,	x "AF_NETLINK"  ,	x "AF_PACKET"   , \
+  x "AF_ASH"   ,	x "AF_ECONET"   ,	x "AF_ATMSVC"   , \
+  x "AF_RDS"   ,	x "AF_SNA"      ,	x "AF_IRDA"     , \
+  x "AF_PPPOX" ,	x "AF_WANPIPE"  ,	x "AF_LLC"      , \
+  x "27"       ,	x "28"          ,	x "AF_CAN"      , \
+  x "AF_TIPC"  ,	x "AF_BLUETOOTH",	x "IUCV"        , \
+  x "AF_RXRPC" ,	x "AF_ISDN"     ,	x "AF_PHONET"   , \
+  x "AF_IEEE802154",	x "AF_CAIF"	,	x "AF_ALG"      , \
+  x "AF_NFC"   ,	x "AF_VSOCK"    ,	x "AF_KCM"      , \
+  x "AF_QIPCRTR",	x "AF_SMC"	,	x "AF_MAX"
+
 static const char *const af_family_key_strings[AF_MAX+1] = {
-  "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX"     , "sk_lock-AF_INET"     ,
-  "sk_lock-AF_AX25"  , "sk_lock-AF_IPX"      , "sk_lock-AF_APPLETALK",
-  "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE"   , "sk_lock-AF_ATMPVC"   ,
-  "sk_lock-AF_X25"   , "sk_lock-AF_INET6"    , "sk_lock-AF_ROSE"     ,
-  "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI"  , "sk_lock-AF_SECURITY" ,
-  "sk_lock-AF_KEY"   , "sk_lock-AF_NETLINK"  , "sk_lock-AF_PACKET"   ,
-  "sk_lock-AF_ASH"   , "sk_lock-AF_ECONET"   , "sk_lock-AF_ATMSVC"   ,
-  "sk_lock-AF_RDS"   , "sk_lock-AF_SNA"      , "sk_lock-AF_IRDA"     ,
-  "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE"  , "sk_lock-AF_LLC"      ,
-  "sk_lock-27"       , "sk_lock-28"          , "sk_lock-AF_CAN"      ,
-  "sk_lock-AF_TIPC"  , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV"        ,
-  "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN"     , "sk_lock-AF_PHONET"   ,
-  "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG"      ,
-  "sk_lock-AF_NFC"   , "sk_lock-AF_VSOCK"    , "sk_lock-AF_KCM"      ,
-  "sk_lock-AF_QIPCRTR", "sk_lock-AF_SMC"     , "sk_lock-AF_MAX"
+	_sock_locks("sk_lock-")
 };
 static const char *const af_family_slock_key_strings[AF_MAX+1] = {
-  "slock-AF_UNSPEC", "slock-AF_UNIX"     , "slock-AF_INET"     ,
-  "slock-AF_AX25"  , "slock-AF_IPX"      , "slock-AF_APPLETALK",
-  "slock-AF_NETROM", "slock-AF_BRIDGE"   , "slock-AF_ATMPVC"   ,
-  "slock-AF_X25"   , "slock-AF_INET6"    , "slock-AF_ROSE"     ,
-  "slock-AF_DECnet", "slock-AF_NETBEUI"  , "slock-AF_SECURITY" ,
-  "slock-AF_KEY"   , "slock-AF_NETLINK"  , "slock-AF_PACKET"   ,
-  "slock-AF_ASH"   , "slock-AF_ECONET"   , "slock-AF_ATMSVC"   ,
-  "slock-AF_RDS"   , "slock-AF_SNA"      , "slock-AF_IRDA"     ,
-  "slock-AF_PPPOX" , "slock-AF_WANPIPE"  , "slock-AF_LLC"      ,
-  "slock-27"       , "slock-28"          , "slock-AF_CAN"      ,
-  "slock-AF_TIPC"  , "slock-AF_BLUETOOTH", "slock-AF_IUCV"     ,
-  "slock-AF_RXRPC" , "slock-AF_ISDN"     , "slock-AF_PHONET"   ,
-  "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG"      ,
-  "slock-AF_NFC"   , "slock-AF_VSOCK"    ,"slock-AF_KCM"       ,
-  "slock-AF_QIPCRTR", "slock-AF_SMC"     , "slock-AF_MAX"
+	_sock_locks("slock-")
 };
 static const char *const af_family_clock_key_strings[AF_MAX+1] = {
-  "clock-AF_UNSPEC", "clock-AF_UNIX"     , "clock-AF_INET"     ,
-  "clock-AF_AX25"  , "clock-AF_IPX"      , "clock-AF_APPLETALK",
-  "clock-AF_NETROM", "clock-AF_BRIDGE"   , "clock-AF_ATMPVC"   ,
-  "clock-AF_X25"   , "clock-AF_INET6"    , "clock-AF_ROSE"     ,
-  "clock-AF_DECnet", "clock-AF_NETBEUI"  , "clock-AF_SECURITY" ,
-  "clock-AF_KEY"   , "clock-AF_NETLINK"  , "clock-AF_PACKET"   ,
-  "clock-AF_ASH"   , "clock-AF_ECONET"   , "clock-AF_ATMSVC"   ,
-  "clock-AF_RDS"   , "clock-AF_SNA"      , "clock-AF_IRDA"     ,
-  "clock-AF_PPPOX" , "clock-AF_WANPIPE"  , "clock-AF_LLC"      ,
-  "clock-27"       , "clock-28"          , "clock-AF_CAN"      ,
-  "clock-AF_TIPC"  , "clock-AF_BLUETOOTH", "clock-AF_IUCV"     ,
-  "clock-AF_RXRPC" , "clock-AF_ISDN"     , "clock-AF_PHONET"   ,
-  "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG"      ,
-  "clock-AF_NFC"   , "clock-AF_VSOCK"    , "clock-AF_KCM"      ,
-  "clock-AF_QIPCRTR", "clock-AF_SMC"     , "clock-AF_MAX"
+	_sock_locks("clock-")
+};
+
+static const char *const af_family_kern_key_strings[AF_MAX+1] = {
+	_sock_locks("k-sk_lock-")
+};
+static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = {
+	_sock_locks("k-slock-")
+};
+static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = {
+	_sock_locks("k-clock-")
 };
 
 /*
···
  * so split the lock classes by using a per-AF key:
  */
 static struct lock_class_key af_callback_keys[AF_MAX];
+static struct lock_class_key af_kern_callback_keys[AF_MAX];
 
 /* Take into consideration the size of the struct sk_buff overhead in the
  * determination of these values, since that is non-constant across
···
  */
 static inline void sock_lock_init(struct sock *sk)
 {
-	sock_lock_init_class_and_name(sk,
+	if (sk->sk_kern_sock)
+		sock_lock_init_class_and_name(
+			sk,
+			af_family_kern_slock_key_strings[sk->sk_family],
+			af_family_kern_slock_keys + sk->sk_family,
+			af_family_kern_key_strings[sk->sk_family],
+			af_family_kern_keys + sk->sk_family);
+	else
+		sock_lock_init_class_and_name(
+			sk,
 			af_family_slock_key_strings[sk->sk_family],
 			af_family_slock_keys + sk->sk_family,
 			af_family_key_strings[sk->sk_family],
···
 		 * why we need sk_prot_creator -acme
 		 */
 		sk->sk_prot = sk->sk_prot_creator = prot;
+		sk->sk_kern_sock = kern;
 		sock_lock_init(sk);
 		sk->sk_net_refcnt = kern ? 0 : 1;
 		if (likely(sk->sk_net_refcnt))
···
 }
 EXPORT_SYMBOL(sock_no_socketpair);
 
-int sock_no_accept(struct socket *sock, struct socket *newsock, int flags)
+int sock_no_accept(struct socket *sock, struct socket *newsock, int flags,
+		   bool kern)
 {
 	return -EOPNOTSUPP;
 }
···
 	}
 
 	rwlock_init(&sk->sk_callback_lock);
-	lockdep_set_class_and_name(&sk->sk_callback_lock,
+	if (sk->sk_kern_sock)
+		lockdep_set_class_and_name(
+			&sk->sk_callback_lock,
+			af_kern_callback_keys + sk->sk_family,
+			af_family_kern_clock_key_strings[sk->sk_family]);
+	else
+		lockdep_set_class_and_name(
+			&sk->sk_callback_lock,
 			af_callback_keys + sk->sk_family,
 			af_family_clock_key_strings[sk->sk_family]);
 

net/dccp/ccids/ccid2.c

···
 	for (i = 0; i < hc->tx_seqbufc; i++)
 		kfree(hc->tx_seqbuf[i]);
 	hc->tx_seqbufc = 0;
+	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
 }
 
 static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)

net/dccp/ipv4.c

···
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		dccp_do_redirect(skb, sk);
+		if (!sock_owned_by_user(sk))
+			dccp_do_redirect(skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */

net/dccp/ipv6.c

···
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 

net/dccp/minisocks.c

···
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 	bool own_req;
 
+	/* TCP/DCCP listeners became lockless.
+	 * DCCP stores complex state in its request_sock, so we need
+	 * a protection for them, now this code runs without being protected
+	 * by the parent (listener) lock.
+	 */
+	spin_lock_bh(&dreq->dreq_lock);
+
 	/* Check for retransmitted REQUEST */
 	if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) {
 
···
 			inet_rtx_syn_ack(sk, req);
 		}
 		/* Network Duplicate, discard packet */
-		return NULL;
+		goto out;
 	}
 
 	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
···
 
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
 							 req, &own_req);
-	if (!child)
-		goto listen_overflow;
+	if (child) {
+		child = inet_csk_complete_hashdance(sk, child, req, own_req);
+		goto out;
+	}
 
-	return inet_csk_complete_hashdance(sk, child, req, own_req);
-
-listen_overflow:
-	dccp_pr_debug("listen_overflow!\n");
 	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
 drop:
 	if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET)
 		req->rsk_ops->send_reset(sk, skb);
 
 	inet_csk_reqsk_queue_drop(sk, req);
-	return NULL;
+out:
+	spin_unlock_bh(&dreq->dreq_lock);
+	return child;
 }
 
 EXPORT_SYMBOL_GPL(dccp_check_req);
···
 {
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 
+	spin_lock_init(&dreq->dreq_lock);
 	inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport;
 	inet_rsk(req)->ir_num	   = ntohs(dccp_hdr(skb)->dccph_dport);
 	inet_rsk(req)->acked	   = 0;

net/decnet/af_decnet.c

···
 	return skb == NULL ? ERR_PTR(err) : skb;
 }
 
-static int dn_accept(struct socket *sock, struct socket *newsock, int flags)
+static int dn_accept(struct socket *sock, struct socket *newsock, int flags,
+		     bool kern)
 {
 	struct sock *sk = sock->sk, *newsk;
 	struct sk_buff *skb = NULL;
···
 
 	cb = DN_SKB_CB(skb);
 	sk->sk_ack_backlog--;
-	newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, 0);
+	newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, kern);
 	if (newsk == NULL) {
 		release_sock(sk);
 		kfree_skb(skb);

net/ipv4/af_inet.c

···
  *	Accept a pending connection. The TCP layer now gives BSD semantics.
  */
 
-int inet_accept(struct socket *sock, struct socket *newsock, int flags)
+int inet_accept(struct socket *sock, struct socket *newsock, int flags,
+		bool kern)
 {
 	struct sock *sk1 = sock->sk;
 	int err = -EINVAL;
-	struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err);
+	struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err, kern);
 
 	if (!sk2)
 		goto do_err;
···
 	int proto = iph->protocol;
 	int err = -ENOSYS;
 
-	if (skb->encapsulation)
+	if (skb->encapsulation) {
+		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP));
 		skb_set_inner_network_header(skb, nhoff);
+	}
 
 	csum_replace2(&iph->check, iph->tot_len, newlen);
 	iph->tot_len = newlen;

net/ipv4/inet_connection_sock.c

···
 /*
  * This will accept the next outstanding connection.
  */
-struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
+struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct request_sock_queue *queue = &icsk->icsk_accept_queue;

net/ipv4/ip_output.c

···
 	cork->length += length;
 	if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+	    (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
 	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,

net/ipv4/tcp_ipv4.c

···
  */
 void tcp_v4_mtu_reduced(struct sock *sk)
 {
-	struct dst_entry *dst;
 	struct inet_sock *inet = inet_sk(sk);
-	u32 mtu = tcp_sk(sk)->mtu_info;
+	struct dst_entry *dst;
+	u32 mtu;
 
+	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+		return;
+	mtu = tcp_sk(sk)->mtu_info;
 	dst = inet_csk_update_pmtu(sk, mtu);
 	if (!dst)
 		return;
···
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		do_redirect(icmp_skb, sk);
+		if (!sock_owned_by_user(sk))
+			do_redirect(icmp_skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */

net/ipv4/tcp_timer.c

···
 
 	sk_mem_reclaim_partial(sk);
 
-	if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
 		goto out;
 
 	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
···
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int event;
 
-	if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending)
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !icsk->icsk_pending)
 		goto out;
 
 	if (time_after(icsk->icsk_timeout, jiffies)) {

net/ipv6/af_inet6.c

···
 	err = register_pernet_subsys(&inet6_net_ops);
 	if (err)
 		goto register_pernet_fail;
-	err = icmpv6_init();
-	if (err)
-		goto icmp_fail;
 	err = ip6_mr_init();
 	if (err)
 		goto ipmr_fail;
+	err = icmpv6_init();
+	if (err)
+		goto icmp_fail;
 	err = ndisc_init();
 	if (err)
 		goto ndisc_fail;
···
 	ndisc_cleanup();
 ndisc_fail:
 	ip6_mr_cleanup();
-ipmr_fail:
-	icmpv6_cleanup();
 icmp_fail:
 	unregister_pernet_subsys(&inet6_net_ops);
+ipmr_fail:
+	icmpv6_cleanup();
 register_pernet_fail:
 	sock_unregister(PF_INET6);
 	rtnl_unregister_all(PF_INET6);

net/ipv6/ip6_fib.c

···
 			ins = &rt->dst.rt6_next;
 			iter = *ins;
 			while (iter) {
+				if (iter->rt6i_metric > rt->rt6i_metric)
+					break;
 				if (rt6_qualify_for_ecmp(iter)) {
 					*ins = iter->dst.rt6_next;
 					fib6_purge_rt(iter, fn, info->nl_net);

net/ipv6/ip6_offload.c

···
 	struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
 	int err = -ENOSYS;
 
-	if (skb->encapsulation)
+	if (skb->encapsulation) {
+		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
 		skb_set_inner_network_header(skb, nhoff);
+	}
 
 	iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
 

net/ipv6/ip6_output.c

···
 	 *	Fragment the datagram.
 	 */
 
-	*prevhdr = NEXTHDR_FRAGMENT;
 	troom = rt->dst.dev->needed_tailroom;
 
 	/*
 	 *	Keep copying data until we run out.
 	 */
 	while (left > 0)	{
+		u8 *fragnexthdr_offset;
+
 		len = left;
 		/* IF: it doesn't fit, use 'mtu' - the data space left */
 		if (len > mtu)
···
 		 *	Copy the packet header into the new buffer.
 		 */
 		skb_copy_from_linear_data(skb, skb_network_header(frag), hlen);
+
+		fragnexthdr_offset = skb_network_header(frag);
+		fragnexthdr_offset += prevhdr - skb_network_header(skb);
+		*fragnexthdr_offset = NEXTHDR_FRAGMENT;
 
 		/*
 		 *	Build fragment header.
···
 	if ((((length + fragheaderlen) > mtu) ||
 	     (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+	    (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
 	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
 		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
 					  hh_len, fragheaderlen, exthdrlen,

net/ipv6/ip6_vti.c

···
 	if (!skb->ignore_df && skb->len > mtu) {
 		skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu);
 
-		if (skb->protocol == htons(ETH_P_IPV6))
+		if (skb->protocol == htons(ETH_P_IPV6)) {
+			if (mtu < IPV6_MIN_MTU)
+				mtu = IPV6_MIN_MTU;
+
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
-		else
+		} else {
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 				  htonl(mtu));
+		}
 
 		return -EMSGSIZE;
 	}

net/ipv6/route.c

···
 		nexthop_len = nla_total_size(0)	 /* RTA_MULTIPATH */
 			    + NLA_ALIGN(sizeof(struct rtnexthop))
 			    + nla_total_size(16) /* RTA_GATEWAY */
-			    + nla_total_size(4)  /* RTA_OIF */
 			    + lwtunnel_get_encap_size(rt->dst.lwtstate);
 
 		nexthop_len *= rt->rt6i_nsiblings;
···
 }
 
 static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
-			    unsigned int *flags)
+			    unsigned int *flags, bool skip_oif)
 {
 	if (!netif_running(rt->dst.dev) || !netif_carrier_ok(rt->dst.dev)) {
 		*flags |= RTNH_F_LINKDOWN;
···
 			goto nla_put_failure;
 	}
 
-	if (rt->dst.dev &&
+	/* not needed for multipath encoding b/c it has a rtnexthop struct */
+	if (!skip_oif && rt->dst.dev &&
 	    nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
 		goto nla_put_failure;
 
···
 	return -EMSGSIZE;
 }
 
+/* add multipath next hop */
 static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
 {
 	struct rtnexthop *rtnh;
···
 	rtnh->rtnh_hops = 0;
 	rtnh->rtnh_ifindex = rt->dst.dev ? rt->dst.dev->ifindex : 0;
 
-	if (rt6_nexthop_info(skb, rt, &flags) < 0)
+	if (rt6_nexthop_info(skb, rt, &flags, true) < 0)
 		goto nla_put_failure;
 
 	rtnh->rtnh_flags = flags;
···
 
 		nla_nest_end(skb, mp);
 	} else {
-		if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags) < 0)
+		if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags, false) < 0)
 			goto nla_put_failure;
 	}
 

net/ipv6/tcp_ipv6.c

···
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 

net/irda/af_irda.c

···
  *    Wait for incoming connection
  *
  */
-static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
+static int irda_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct irda_sock *new, *self = irda_sk(sk);
···
 	struct sk_buff *skb = NULL;
 	int err;
 
-	err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0);
+	err = irda_create(sock_net(sk), newsock, sk->sk_protocol, kern);
 	if (err)
 		return err;
 

net/iucv/af_iucv.c

···
 
 /* Accept a pending connection */
 static int iucv_sock_accept(struct socket *sock, struct socket *newsock,
-			    int flags)
+			    int flags, bool kern)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	struct sock *sk = sock->sk, *nsk;

net/llc/af_llc.c

···
  *	@sock: Socket which connections arrive on.
  *	@newsock: Socket to move incoming connection to.
  *	@flags: User specified operational flags.
+ *	@kern: If the socket is kernel internal
  *
  *	Accept a new incoming connection.
  *	Returns 0 upon success, negative otherwise.
  */
-static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags)
+static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags,
+			 bool kern)
 {
 	struct sock *sk = sock->sk, *newsk;
 	struct llc_sock *llc, *newllc;

net/mpls/af_mpls.c

···
 				/* fall through */
 			case NETDEV_CHANGE:
 				nh->nh_flags |= RTNH_F_LINKDOWN;
-				ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
+				if (event != NETDEV_UNREGISTER)
+					ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
 				break;
 			}
 			if (event == NETDEV_UNREGISTER)
···
 	for (index = 0; index < platform_labels; index++) {
 		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
 		RCU_INIT_POINTER(platform_label[index], NULL);
+		mpls_notify_route(net, index, rt, NULL, NULL);
 		mpls_rt_free(rt);
 	}
 	rtnl_unlock();

net/netrom/af_netrom.c

···
 	return err;
 }
 
-static int nr_accept(struct socket *sock, struct socket *newsock, int flags)
+static int nr_accept(struct socket *sock, struct socket *newsock, int flags,
+		     bool kern)
 {
 	struct sk_buff *skb;
 	struct sock *newsk;

net/nfc/llcp_sock.c

···
 }
 
 static int llcp_sock_accept(struct socket *sock, struct socket *newsock,
-			    int flags)
+			    int flags, bool kern)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	struct sock *sk = sock->sk, *new_sk;

net/phonet/pep.c

···
 	sock_put(sk);
 }
 
-static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp)
+static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp,
+				    bool kern)
 {
 	struct pep_sock *pn = pep_sk(sk), *newpn;
 	struct sock *newsk = NULL;
···
 	}
 
 	/* Create a new to-be-accepted sock */
-	newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, 0);
+	newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot,
+			 kern);
 	if (!newsk) {
 		pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL);
 		err = -ENOBUFS;

net/phonet/socket.c

···
 }
 
 static int pn_socket_accept(struct socket *sock, struct socket *newsock,
-				int flags)
+			    int flags, bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct sock *newsk;
···
 	if (unlikely(sk->sk_state != TCP_LISTEN))
 		return -EINVAL;
 
-	newsk = sk->sk_prot->accept(sk, flags, &err);
+	newsk = sk->sk_prot->accept(sk, flags, &err, kern);
 	if (!newsk)
 		return err;
 

net/rds/connection.c

···
 	 */
 	rds_cong_remove_conn(conn);
 
+	put_net(conn->c_net);
 	kmem_cache_free(rds_conn_slab, conn);
 
 	spin_lock_irqsave(&rds_conn_lock, flags);

net/rds/ib_cm.c

···
 		ic->i_send_cq = NULL;
 		ibdev_put_vector(rds_ibdev, ic->i_scq_vector);
 		rdsdebug("ib_create_cq send failed: %d\n", ret);
-		goto out;
+		goto rds_ibdev_out;
 	}
 
 	ic->i_rcq_vector = ibdev_get_unused_vector(rds_ibdev);
···
 		ic->i_recv_cq = NULL;
 		ibdev_put_vector(rds_ibdev, ic->i_rcq_vector);
 		rdsdebug("ib_create_cq recv failed: %d\n", ret);
-		goto out;
+		goto send_cq_out;
 	}
 
 	ret = ib_req_notify_cq(ic->i_send_cq, IB_CQ_NEXT_COMP);
 	if (ret) {
 		rdsdebug("ib_req_notify_cq send failed: %d\n", ret);
-		goto out;
+		goto recv_cq_out;
 	}
 
 	ret = ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
 	if (ret) {
 		rdsdebug("ib_req_notify_cq recv failed: %d\n", ret);
-		goto out;
+		goto recv_cq_out;
 	}
 
 	/* XXX negotiate max send/recv with remote? */
···
 	ret = rdma_create_qp(ic->i_cm_id, ic->i_pd, &attr);
 	if (ret) {
 		rdsdebug("rdma_create_qp failed: %d\n", ret);
-		goto out;
+		goto recv_cq_out;
 	}
 
 	ic->i_send_hdrs = ib_dma_alloc_coherent(dev,
···
 	if (!ic->i_send_hdrs) {
 		ret = -ENOMEM;
 		rdsdebug("ib_dma_alloc_coherent send failed\n");
-		goto out;
+		goto qp_out;
 	}
 
 	ic->i_recv_hdrs = ib_dma_alloc_coherent(dev,
···
 	if (!ic->i_recv_hdrs) {
 		ret = -ENOMEM;
 		rdsdebug("ib_dma_alloc_coherent recv failed\n");
-		goto out;
+		goto send_hdrs_dma_out;
 	}
 
 	ic->i_ack = ib_dma_alloc_coherent(dev, sizeof(struct rds_header),
···
 	if (!ic->i_ack) {
 		ret = -ENOMEM;
 		rdsdebug("ib_dma_alloc_coherent ack failed\n");
-		goto out;
+		goto recv_hdrs_dma_out;
 	}
 
 	ic->i_sends = vzalloc_node(ic->i_send_ring.w_nr * sizeof(struct rds_ib_send_work),
···
 	if (!ic->i_sends) {
 		ret = -ENOMEM;
 		rdsdebug("send allocation failed\n");
-		goto out;
+		goto ack_dma_out;
 	}
 
 	ic->i_recvs = vzalloc_node(ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work),
···
 	if (!ic->i_recvs) {
 		ret = -ENOMEM;
 		rdsdebug("recv allocation failed\n");
-		goto out;
+		goto sends_out;
 	}
 
 	rds_ib_recv_init_ack(ic);
···
 	rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd,
 		 ic->i_send_cq, ic->i_recv_cq);
 
-out:
+	return ret;
+
+sends_out:
+	vfree(ic->i_sends);
+ack_dma_out:
+	ib_dma_free_coherent(dev, sizeof(struct rds_header),
+			     ic->i_ack, ic->i_ack_dma);
+recv_hdrs_dma_out:
+	ib_dma_free_coherent(dev, ic->i_recv_ring.w_nr *
+					sizeof(struct rds_header),
+					ic->i_recv_hdrs, ic->i_recv_hdrs_dma);
+send_hdrs_dma_out:
+	ib_dma_free_coherent(dev, ic->i_send_ring.w_nr *
+					sizeof(struct rds_header),
+					ic->i_send_hdrs, ic->i_send_hdrs_dma);
+qp_out:
+	rdma_destroy_qp(ic->i_cm_id);
+recv_cq_out:
+	if (!ib_destroy_cq(ic->i_recv_cq))
+		ic->i_recv_cq = NULL;
+send_cq_out:
+	if (!ib_destroy_cq(ic->i_send_cq))
+		ic->i_send_cq = NULL;
+rds_ibdev_out:
+	rds_ib_remove_conn(rds_ibdev, conn);
 	rds_ib_dev_put(rds_ibdev);
+
 	return ret;
 }
 

net/rds/rds.h

···
 
 	/* Protocol version */
 	unsigned int		c_version;
-	possible_net_t		c_net;
+	struct net		*c_net;
 
 	struct list_head	c_map_item;
 	unsigned long		c_map_queued;
···
 static inline
 struct net *rds_conn_net(struct rds_connection *conn)
 {
-	return read_pnet(&conn->c_net);
+	return conn->c_net;
 }
 
 static inline
 void rds_conn_net_set(struct rds_connection *conn, struct net *net)
 {
-	write_pnet(&conn->c_net, net);
+	conn->c_net = get_net(net);
 }
 
 #define RDS_FLAG_CONG_BITMAP	0x01

net/rds/tcp.c

···
 	 * we do need to clean up the listen socket here.
 	 */
 	if (rtn->rds_tcp_listen_sock) {
-		rds_tcp_listen_stop(rtn->rds_tcp_listen_sock);
+		struct socket *lsock = rtn->rds_tcp_listen_sock;
+
 		rtn->rds_tcp_listen_sock = NULL;
-		flush_work(&rtn->rds_tcp_accept_w);
+		rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w);
 	}
 }
 
···
 	struct rds_tcp_connection *tc, *_tc;
 	LIST_HEAD(tmp_list);
 	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+	struct socket *lsock = rtn->rds_tcp_listen_sock;
 
-	rds_tcp_listen_stop(rtn->rds_tcp_listen_sock);
 	rtn->rds_tcp_listen_sock = NULL;
-	flush_work(&rtn->rds_tcp_accept_w);
+	rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w);
 	spin_lock_irq(&rds_tcp_conn_lock);
 	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
-		struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
+		struct net *c_net = tc->t_cpath->cp_conn->c_net;
 
 		if (net != c_net || !tc->t_sock)
 			continue;
···
 void *rds_tcp_listen_sock_def_readable(struct net *net)
 {
 	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+	struct socket *lsock = rtn->rds_tcp_listen_sock;
 
-	return rtn->rds_tcp_listen_sock->sk->sk_user_data;
+	if (!lsock)
+		return NULL;
+
+	return lsock->sk->sk_user_data;
 }
 
 static int rds_tcp_dev_event(struct notifier_block *this,
···
 
 	spin_lock_irq(&rds_tcp_conn_lock);
 	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
-		struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
+		struct net *c_net = tc->t_cpath->cp_conn->c_net;
 
 		if (net != c_net || !tc->t_sock)
 			continue;
···
 		goto out;
 	}
 
-	ret = register_netdevice_notifier(&rds_tcp_dev_notifier);
-	if (ret) {
-		pr_warn("could not register rds_tcp_dev_notifier\n");
+	ret = rds_tcp_recv_init();
+	if (ret)
 		goto out_slab;
-	}
 
 	ret = register_pernet_subsys(&rds_tcp_net_ops);
 	if (ret)
-		goto out_notifier;
+		goto out_recv;
 
-	ret = rds_tcp_recv_init();
-	if (ret)
+	ret = register_netdevice_notifier(&rds_tcp_dev_notifier);
+	if (ret) {
+		pr_warn("could not register rds_tcp_dev_notifier\n");
 		goto out_pernet;
+	}
 
 	rds_trans_register(&rds_tcp_transport);
 
···
 
 out_pernet:
 	unregister_pernet_subsys(&rds_tcp_net_ops);
-out_notifier:
-	if (unregister_netdevice_notifier(&rds_tcp_dev_notifier))
-		pr_warn("could not unregister rds_tcp_dev_notifier\n");
+out_recv:
+	rds_tcp_recv_exit();
 out_slab:
 	kmem_cache_destroy(rds_tcp_conn_slab);
 out:

net/rds/tcp.h

···
 
 /* tcp_listen.c */
 struct socket *rds_tcp_listen_init(struct net *);
-void rds_tcp_listen_stop(struct socket *);
+void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor);
 void rds_tcp_listen_data_ready(struct sock *sk);
 int rds_tcp_accept_one(struct socket *sock);
 int rds_tcp_keepalive(struct socket *sock);

net/rds/tcp_listen.c

···
 
 	new_sock->type = sock->type;
 	new_sock->ops = sock->ops;
-	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK);
+	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true);
 	if (ret < 0)
 		goto out;
 
···
 	 * before it has been accepted and the accepter has set up their
 	 * data_ready.. we only want to queue listen work for our listening
 	 * socket
+	 *
+	 * (*ready)() may be null if we are racing with netns delete, and
+	 * the listen socket is being torn down.
 	 */
 	if (sk->sk_state == TCP_LISTEN)
 		rds_tcp_accept_work(sk);
···
 
 out:
 	read_unlock_bh(&sk->sk_callback_lock);
-	ready(sk);
+	if (ready)
+		ready(sk);
 }
 
 struct socket *rds_tcp_listen_init(struct net *net)
···
 	return NULL;
 }
 
-void rds_tcp_listen_stop(struct socket *sock)
+void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor)
 {
 	struct sock *sk;
 
···
 
 	/* wait for accepts to stop and close the socket */
 	flush_workqueue(rds_wq);
+	flush_work(acceptor);
 	sock_release(sock);
 }

net/rose/af_rose.c

···
 	return err;
 }
 
-static int rose_accept(struct socket *sock, struct socket *newsock, int flags)
+static int rose_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sk_buff *skb;
 	struct sock *newsk;

net/rxrpc/input.c

···
 			     u16 skew)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	enum rxrpc_call_state state;
 	unsigned int offset = sizeof(struct rxrpc_wire_header);
 	unsigned int ix;
 	rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0;
···
 	_proto("Rx DATA %%%u { #%u f=%02x }",
 	       sp->hdr.serial, seq, sp->hdr.flags);
 
-	if (call->state >= RXRPC_CALL_COMPLETE)
+	state = READ_ONCE(call->state);
+	if (state >= RXRPC_CALL_COMPLETE)
 		return;
 
 	/* Received data implicitly ACKs all of the request packets we sent
 	 * when we're acting as a client.
 	 */
-	if ((call->state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
-	     call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
+	if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
+	     state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
 	    !rxrpc_receiving_reply(call))
 		return;
 
···
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxrpc_peer *peer;
 	unsigned int mtu;
+	bool wake = false;
 	u32 rwind = ntohl(ackinfo->rwind);
 
 	_proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }",
···
 	       ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU),
 	       rwind, ntohl(ackinfo->jumbo_max));
 
-	if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
-		rwind = RXRPC_RXTX_BUFF_SIZE - 1;
-	call->tx_winsize = rwind;
+	if (call->tx_winsize != rwind) {
+		if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
+			rwind = RXRPC_RXTX_BUFF_SIZE - 1;
+		if (rwind > call->tx_winsize)
+			wake = true;
+		call->tx_winsize = rwind;
+	}
+
 	if (call->cong_ssthresh > rwind)
 		call->cong_ssthresh = rwind;
 
···
 		spin_unlock_bh(&peer->lock);
 		_net("Net MTU %u (maxdata %u)", peer->mtu, peer->maxdata);
 	}
+
+	if (wake)
+		wake_up(&call->waitq);
 }
 
 /*
···
 		return rxrpc_proto_abort("AK0", call, 0);
 
 	/* Ignore ACKs unless we are or have just been transmitting. */
-	switch (call->state) {
+	switch (READ_ONCE(call->state)) {
 	case RXRPC_CALL_CLIENT_SEND_REQUEST:
 	case RXRPC_CALL_CLIENT_AWAIT_REPLY:
 	case RXRPC_CALL_SERVER_SEND_REPLY:
···
 static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn,
 					  struct rxrpc_call *call)
 {
-	switch (call->state) {
+	switch (READ_ONCE(call->state)) {
 	case RXRPC_CALL_SERVER_AWAIT_ACK:
 		rxrpc_call_completed(call);
 		break;

net/rxrpc/recvmsg.c

···
 		msg->msg_namelen = len;
 	}
 
-	switch (call->state) {
+	switch (READ_ONCE(call->state)) {
 	case RXRPC_CALL_SERVER_ACCEPTING:
 		ret = rxrpc_recvmsg_new_call(rx, call, msg, flags);
 		break;
···
 
 	mutex_lock(&call->user_mutex);
 
-	switch (call->state) {
+	switch (READ_ONCE(call->state)) {
 	case RXRPC_CALL_CLIENT_RECV_REPLY:
 	case RXRPC_CALL_SERVER_RECV_REQUEST:
 	case RXRPC_CALL_SERVER_ACK_REQUEST:

net/rxrpc/sendmsg.c

···
 int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 	__releases(&rx->sk.sk_lock.slock)
 {
+	enum rxrpc_call_state state;
 	enum rxrpc_command cmd;
 	struct rxrpc_call *call;
 	unsigned long user_call_ID = 0;
···
 			return PTR_ERR(call);
 		/* ... and we have the call lock. */
 	} else {
-		ret = -EBUSY;
-		if (call->state == RXRPC_CALL_UNINITIALISED ||
-		    call->state == RXRPC_CALL_CLIENT_AWAIT_CONN ||
-		    call->state == RXRPC_CALL_SERVER_PREALLOC ||
-		    call->state == RXRPC_CALL_SERVER_SECURING ||
-		    call->state == RXRPC_CALL_SERVER_ACCEPTING)
+		switch (READ_ONCE(call->state)) {
+		case RXRPC_CALL_UNINITIALISED:
+		case RXRPC_CALL_CLIENT_AWAIT_CONN:
+		case RXRPC_CALL_SERVER_PREALLOC:
+		case RXRPC_CALL_SERVER_SECURING:
+		case RXRPC_CALL_SERVER_ACCEPTING:
+			ret = -EBUSY;
 			goto error_release_sock;
+		default:
+			break;
+		}
 
 		ret = mutex_lock_interruptible(&call->user_mutex);
 		release_sock(&rx->sk);
···
 		}
 	}
 
+	state = READ_ONCE(call->state);
 	_debug("CALL %d USR %lx ST %d on CONN %p",
-	       call->debug_id, call->user_call_ID, call->state, call->conn);
+	       call->debug_id, call->user_call_ID, state, call->conn);
 
-	if (call->state >= RXRPC_CALL_COMPLETE) {
+	if (state >= RXRPC_CALL_COMPLETE) {
 		/* it's too late for this call */
 		ret = -ESHUTDOWN;
 	} else if (cmd == RXRPC_CMD_SEND_ABORT) {
···
 	} else if (cmd != RXRPC_CMD_SEND_DATA) {
 		ret = -EINVAL;
 	} else if (rxrpc_is_client_call(call) &&
-		   call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
+		   state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
 		/* request phase complete for this client call */
 		ret = -EPROTO;
 	} else if (rxrpc_is_service_call(call) &&
-		   call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
-		   call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
+		   state != RXRPC_CALL_SERVER_ACK_REQUEST &&
+		   state != RXRPC_CALL_SERVER_SEND_REPLY) {
 		/* Reply phase not begun or not complete for service call. */
 		ret = -EPROTO;
 	} else {
···
 	_debug("CALL %d USR %lx ST %d on CONN %p",
 	       call->debug_id, call->user_call_ID, call->state, call->conn);
 
-	if (call->state >= RXRPC_CALL_COMPLETE) {
-		ret = -ESHUTDOWN; /* it's too late for this call */
-	} else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
-		   call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
-		   call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
-		ret = -EPROTO; /* request phase complete for this client call */
-	} else {
+	switch (READ_ONCE(call->state)) {
+	case RXRPC_CALL_CLIENT_SEND_REQUEST:
+	case RXRPC_CALL_SERVER_ACK_REQUEST:
+	case RXRPC_CALL_SERVER_SEND_REPLY:
 		ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len);
+		break;
+	case RXRPC_CALL_COMPLETE:
+		read_lock_bh(&call->state_lock);
+		ret = -call->error;
+		read_unlock_bh(&call->state_lock);
+		break;
+	default:
+		 /* Request phase complete for this client call */
+		ret = -EPROTO;
+		break;
 	}
 
 	mutex_unlock(&call->user_mutex);

net/sched/act_connmark.c

···
 	if (ret < 0)
 		return ret;
 
+	if (!tb[TCA_CONNMARK_PARMS])
+		return -EINVAL;
+
 	parm = nla_data(tb[TCA_CONNMARK_PARMS]);
 
 	if (!tcf_hash_check(tn, parm->index, a, bind)) {

net/sched/act_skbmod.c

···
 
 	return skb->len;
 nla_put_failure:
-	rcu_read_unlock();
 	nlmsg_trim(skb, b);
 	return -1;
 }

net/sctp/ipv6.c

···
 
 /* Create and initialize a new sk for the socket to be returned by accept(). */
 static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
-					     struct sctp_association *asoc)
+					     struct sctp_association *asoc,
+					     bool kern)
 {
 	struct sock *newsk;
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
 	struct sctp6_sock *newsctp6sk;
 	struct ipv6_txoptions *opt;
 
-	newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0);
+	newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern);
 	if (!newsk)
 		goto out;
 

net/sctp/protocol.c

···
 
 /* Create and initialize a new sk for the socket returned by accept(). */
 static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
-					     struct sctp_association *asoc)
+					     struct sctp_association *asoc,
+					     bool kern)
 {
 	struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL,
-			sk->sk_prot, 0);
+			sk->sk_prot, kern);
 	struct inet_sock *newinet;
 
 	if (!newsk)

net/sctp/socket.c

···
  * descriptor will be returned from accept() to represent the newly
  * formed association.
  */
-static struct sock *sctp_accept(struct sock *sk, int flags, int *err)
+static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern)
 {
 	struct sctp_sock *sp;
 	struct sctp_endpoint *ep;
···
 	 */
 	asoc = list_entry(ep->asocs.next, struct sctp_association, asocs);
 
-	newsk = sp->pf->create_accept_sk(sk, asoc);
+	newsk = sp->pf->create_accept_sk(sk, asoc, kern);
 	if (!newsk) {
 		error = -ENOMEM;
 		goto out;

net/smc/af_smc.c

···
 }
 
 static int smc_accept(struct socket *sock, struct socket *new_sock,
-		      int flags)
+		      int flags, bool kern)
 {
 	struct sock *sk = sock->sk, *nsk;
 	DECLARE_WAITQUEUE(wait, current);

net/socket.c

···
 	if (err)
 		goto out_fd;
 
-	err = sock->ops->accept(sock, newsock, sock->file->f_flags);
+	err = sock->ops->accept(sock, newsock, sock->file->f_flags, false);
 	if (err < 0)
 		goto out_fd;
 
···
 	/* We assume all kernel code knows the size of sockaddr_storage */
 	msg.msg_namelen = 0;
 	msg.msg_iocb = NULL;
+	msg.msg_flags = 0;
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	err = sock_recvmsg(sock, &msg, flags);
···
 	if (err < 0)
 		goto done;
 
-	err = sock->ops->accept(sock, *newsock, flags);
+	err = sock->ops->accept(sock, *newsock, flags, true);
 	if (err < 0) {
 		sock_release(*newsock);
 		*newsock = NULL;

net/tipc/socket.c

···
 static void tipc_write_space(struct sock *sk);
 static void tipc_sock_destruct(struct sock *sk);
 static int tipc_release(struct socket *sock);
-static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
+		       bool kern);
 static void tipc_sk_timeout(unsigned long data);
 static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
 			   struct tipc_name_seq const *seq);
···
  *
  * Returns 0 on success, errno otherwise
  */
-static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
+		       bool kern)
 {
 	struct sock *new_sk, *sk = sock->sk;
 	struct sk_buff *buf;
···
 
 	buf = skb_peek(&sk->sk_receive_queue);
 
-	res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 0);
+	res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, kern);
 	if (res)
 		goto exit;
 	security_sk_clone(sock->sk, new_sock->sk);

net/unix/af_unix.c

···
 static int unix_stream_connect(struct socket *, struct sockaddr *,
 			       int addr_len, int flags);
 static int unix_socketpair(struct socket *, struct socket *);
-static int unix_accept(struct socket *, struct socket *, int);
+static int unix_accept(struct socket *, struct socket *, int, bool);
 static int unix_getname(struct socket *, struct sockaddr *, int *, int);
 static unsigned int unix_poll(struct file *, struct socket *, poll_table *);
 static unsigned int unix_dgram_poll(struct file *, struct socket *,
···
 		set_bit(SOCK_PASSSEC, &new->flags);
 }
 
-static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
+static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct sock *tsk;

net/vmw_vsock/af_vsock.c

···
 	return err;
 }
 
-static int vsock_accept(struct socket *sock, struct socket *newsock, int flags)
+static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
+			bool kern)
 {
 	struct sock *listener;
 	int err;

net/x25/af_x25.c

···
 	return rc;
 }
 
-static int x25_accept(struct socket *sock, struct socket *newsock, int flags)
+static int x25_accept(struct socket *sock, struct socket *newsock, int flags,
+		      bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct sock *newsk;

net/xfrm/xfrm_policy.c

···
 }
 
 static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
-						 const struct flowi *fl)
+						 const struct flowi *fl, u16 family)
 {
 	struct xfrm_policy *pol;
 
···
  again:
 	pol = rcu_dereference(sk->sk_policy[dir]);
 	if (pol != NULL) {
-		bool match = xfrm_selector_match(&pol->selector, fl,
-						 sk->sk_family);
+		bool match = xfrm_selector_match(&pol->selector, fl, family);
 		int err = 0;
 
 		if (match) {
···
 	sk = sk_const_to_full_sk(sk);
 	if (sk && sk->sk_policy[XFRM_POLICY_OUT]) {
 		num_pols = 1;
-		pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl);
+		pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family);
 		err = xfrm_expand_policies(fl, family, pols,
 					   &num_pols, &num_xfrms);
 		if (err < 0)
···
 	pol = NULL;
 	sk = sk_to_full_sk(sk);
 	if (sk && sk->sk_policy[dir]) {
-		pol = xfrm_sk_policy_lookup(sk, dir, &fl);
+		pol = xfrm_sk_policy_lookup(sk, dir, &fl, family);
 		if (IS_ERR(pol)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
 			return 0;
···
 {
 	int rv;
 
+	/* Initialize the per-net locks here */
+	spin_lock_init(&net->xfrm.xfrm_state_lock);
+	spin_lock_init(&net->xfrm.xfrm_policy_lock);
+	mutex_init(&net->xfrm.xfrm_cfg_mutex);
+
 	rv = xfrm_statistics_init(net);
 	if (rv < 0)
 		goto out_statistics;
···
 	rv = flow_cache_init(net);
 	if (rv < 0)
 		goto out;
-
-	/* Initialize the per-net locks here */
-	spin_lock_init(&net->xfrm.xfrm_state_lock);
-	spin_lock_init(&net->xfrm.xfrm_policy_lock);
-	mutex_init(&net->xfrm.xfrm_cfg_mutex);
 
 	return 0;
 

tools/include/uapi/linux/bpf_perf_event.h

···
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__
+#define _UAPI__LINUX_BPF_PERF_EVENT_H__
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+
+struct bpf_perf_event_data {
+	struct pt_regs regs;
+	__u64 sample_period;
+};
+
+#endif /* _UAPI__LINUX_BPF_PERF_EVENT_H__ */

tools/testing/selftests/bpf/Makefile

···
 LIBDIR := ../../../lib
 BPFOBJ := $(LIBDIR)/bpf/bpf.o
 
-CFLAGS += -Wall -O2 -lcap -I../../../include/uapi -I$(LIBDIR)
+CFLAGS += -Wall -O2 -lcap -I../../../include/uapi -I$(LIBDIR) $(BPFOBJ)
 
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map
 
 TEST_PROGS := test_kmod.sh
+
+all: $(TEST_GEN_PROGS)
 
 .PHONY: all clean force
 

tools/testing/selftests/bpf/test_verifier.c

···
  * License as published by the Free Software Foundation.
  */
 
+#include <asm/types.h>
+#include <linux/types.h>
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
···
 	cap_flag_value_t sysadmin = CAP_CLEAR;
 	const cap_value_t cap_val = CAP_SYS_ADMIN;
 
+#ifdef CAP_IS_SUPPORTED
 	if (!CAP_IS_SUPPORTED(CAP_SETFCAP)) {
 		perror("cap_get_flag");
 		return false;
 	}
+#endif
 	caps = cap_get_proc();
 	if (!caps) {
 		perror("cap_get_proc");

tools/testing/selftests/powerpc/include/vsx_asm.h

···
  */
 FUNC_START(load_vsx)
 	li	r5,0
-	lxvx	vs20,r5,r3
+	lxvd2x	vs20,r5,r3
 	addi	r5,r5,16
-	lxvx	vs21,r5,r3
+	lxvd2x	vs21,r5,r3
 	addi	r5,r5,16
-	lxvx	vs22,r5,r3
+	lxvd2x	vs22,r5,r3
 	addi	r5,r5,16
-	lxvx	vs23,r5,r3
+	lxvd2x	vs23,r5,r3
 	addi	r5,r5,16
-	lxvx	vs24,r5,r3
+	lxvd2x	vs24,r5,r3
 	addi	r5,r5,16
-	lxvx	vs25,r5,r3
+	lxvd2x	vs25,r5,r3
 	addi	r5,r5,16
-	lxvx	vs26,r5,r3
+	lxvd2x	vs26,r5,r3
 	addi	r5,r5,16
-	lxvx	vs27,r5,r3
+	lxvd2x	vs27,r5,r3
 	addi	r5,r5,16
-	lxvx	vs28,r5,r3
+	lxvd2x	vs28,r5,r3
 	addi	r5,r5,16
-	lxvx	vs29,r5,r3
+	lxvd2x	vs29,r5,r3
 	addi	r5,r5,16
-	lxvx	vs30,r5,r3
+	lxvd2x	vs30,r5,r3
 	addi	r5,r5,16
-	lxvx	vs31,r5,r3
+	lxvd2x	vs31,r5,r3
 	blr
 FUNC_END(load_vsx)
 
 FUNC_START(store_vsx)
 	li	r5,0
-	stxvx	vs20,r5,r3
+	stxvd2x	vs20,r5,r3
 	addi	r5,r5,16
-	stxvx	vs21,r5,r3
+	stxvd2x	vs21,r5,r3
 	addi	r5,r5,16
-	stxvx	vs22,r5,r3
+	stxvd2x	vs22,r5,r3
 	addi	r5,r5,16
-	stxvx	vs23,r5,r3
+	stxvd2x	vs23,r5,r3
 	addi	r5,r5,16
-	stxvx	vs24,r5,r3
+	stxvd2x	vs24,r5,r3
 	addi	r5,r5,16
-	stxvx	vs25,r5,r3
+	stxvd2x	vs25,r5,r3
 	addi	r5,r5,16
-	stxvx	vs26,r5,r3
+	stxvd2x	vs26,r5,r3
 	addi	r5,r5,16
-	stxvx	vs27,r5,r3
+	stxvd2x	vs27,r5,r3
 	addi	r5,r5,16
-	stxvx	vs28,r5,r3
+	stxvd2x	vs28,r5,r3
 	addi	r5,r5,16
-	stxvx	vs29,r5,r3
+	stxvd2x	vs29,r5,r3
 	addi	r5,r5,16
-	stxvx	vs30,r5,r3
+	stxvd2x	vs30,r5,r3
 	addi	r5,r5,16
-	stxvx	vs31,r5,r3
+	stxvd2x	vs31,r5,r3
 	blr
 FUNC_END(store_vsx)