path: root/1152_linux-4.14.153.patch

diff --git a/Makefile b/Makefile
index 1d7f47334ca2..2819ed540ce2 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 14
-SUBLEVEL = 152
+SUBLEVEL = 153
 EXTRAVERSION =
 NAME = Petit Gorille
 
@@ -840,6 +840,15 @@ KBUILD_CFLAGS   += $(call cc-option,-Werror=incompatible-pointer-types)
 # Require designated initializers for all marked structures
 KBUILD_CFLAGS   += $(call cc-option,-Werror=designated-init)
 
+# change __FILE__ to the relative path from the srctree
+KBUILD_CFLAGS	+= $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
+
+# ensure -fcf-protection is disabled when using retpoline as it is
+# incompatible with -mindirect-branch=thunk-extern
+ifdef CONFIG_RETPOLINE
+KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none)
+endif
+
 # use the deterministic mode of AR if available
 KBUILD_ARFLAGS := $(call ar-option,D)
 
diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi
index bf15efbe8a71..836550f2297a 100644
--- a/arch/arm/boot/dts/imx7s.dtsi
+++ b/arch/arm/boot/dts/imx7s.dtsi
@@ -450,7 +450,7 @@
 				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
 				reg = <0x302d0000 0x10000>;
 				interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
+				clocks = <&clks IMX7D_GPT1_ROOT_CLK>,
 					 <&clks IMX7D_GPT1_ROOT_CLK>;
 				clock-names = "ipg", "per";
 			};
@@ -459,7 +459,7 @@
 				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
 				reg = <0x302e0000 0x10000>;
 				interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
+				clocks = <&clks IMX7D_GPT2_ROOT_CLK>,
 					 <&clks IMX7D_GPT2_ROOT_CLK>;
 				clock-names = "ipg", "per";
 				status = "disabled";
@@ -469,7 +469,7 @@
 				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
 				reg = <0x302f0000 0x10000>;
 				interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
+				clocks = <&clks IMX7D_GPT3_ROOT_CLK>,
 					 <&clks IMX7D_GPT3_ROOT_CLK>;
 				clock-names = "ipg", "per";
 				status = "disabled";
@@ -479,7 +479,7 @@
 				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
 				reg = <0x30300000 0x10000>;
 				interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
+				clocks = <&clks IMX7D_GPT4_ROOT_CLK>,
 					 <&clks IMX7D_GPT4_ROOT_CLK>;
 				clock-names = "ipg", "per";
 				status = "disabled";
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index fe4cbdc72359..7265d7072b5c 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -270,3 +270,7 @@
 &twl_gpio {
 	ti,use-leds;
 };
+
+&twl_keypad {
+	status = "disabled";
+};
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index 8be04ec95adf..d80b2290ac2e 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -856,8 +856,8 @@ static s8 dm365_queue_priority_mapping[][2] = {
 };
 
 static const struct dma_slave_map dm365_edma_map[] = {
-	{ "davinci-mcbsp.0", "tx", EDMA_FILTER_PARAM(0, 2) },
-	{ "davinci-mcbsp.0", "rx", EDMA_FILTER_PARAM(0, 3) },
+	{ "davinci-mcbsp", "tx", EDMA_FILTER_PARAM(0, 2) },
+	{ "davinci-mcbsp", "rx", EDMA_FILTER_PARAM(0, 3) },
 	{ "davinci_voicecodec", "tx", EDMA_FILTER_PARAM(0, 2) },
 	{ "davinci_voicecodec", "rx", EDMA_FILTER_PARAM(0, 3) },
 	{ "spi_davinci.2", "tx", EDMA_FILTER_PARAM(0, 10) },
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 2c96190e018b..96b17a870b91 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -768,6 +768,36 @@ do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
 	return NULL;
 }
 
+static int alignment_get_arm(struct pt_regs *regs, u32 *ip, unsigned long *inst)
+{
+	u32 instr = 0;
+	int fault;
+
+	if (user_mode(regs))
+		fault = get_user(instr, ip);
+	else
+		fault = probe_kernel_address(ip, instr);
+
+	*inst = __mem_to_opcode_arm(instr);
+
+	return fault;
+}
+
+static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst)
+{
+	u16 instr = 0;
+	int fault;
+
+	if (user_mode(regs))
+		fault = get_user(instr, ip);
+	else
+		fault = probe_kernel_address(ip, instr);
+
+	*inst = __mem_to_opcode_thumb16(instr);
+
+	return fault;
+}
+
 static int
 do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
@@ -775,10 +805,10 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	unsigned long instr = 0, instrptr;
 	int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs);
 	unsigned int type;
-	unsigned int fault;
 	u16 tinstr = 0;
 	int isize = 4;
 	int thumb2_32b = 0;
+	int fault;
 
 	if (interrupts_enabled(regs))
 		local_irq_enable();
@@ -787,15 +817,14 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	if (thumb_mode(regs)) {
 		u16 *ptr = (u16 *)(instrptr & ~1);
-		fault = probe_kernel_address(ptr, tinstr);
-		tinstr = __mem_to_opcode_thumb16(tinstr);
+
+		fault = alignment_get_thumb(regs, ptr, &tinstr);
 		if (!fault) {
 			if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
 			    IS_T32(tinstr)) {
 				/* Thumb-2 32-bit */
-				u16 tinst2 = 0;
-				fault = probe_kernel_address(ptr + 1, tinst2);
-				tinst2 = __mem_to_opcode_thumb16(tinst2);
+				u16 tinst2;
+				fault = alignment_get_thumb(regs, ptr + 1, &tinst2);
 				instr = __opcode_thumb32_compose(tinstr, tinst2);
 				thumb2_32b = 1;
 			} else {
@@ -804,8 +833,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 			}
 		}
 	} else {
-		fault = probe_kernel_address((void *)instrptr, instr);
-		instr = __mem_to_opcode_arm(instr);
+		fault = alignment_get_arm(regs, (void *)instrptr, &instr);
 	}
 
 	if (fault) {
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 92e84181933a..c68408d51c4b 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -135,7 +135,6 @@ __v7m_setup_cont:
 	dsb
 	mov	r6, lr			@ save LR
 	ldr	sp, =init_thread_union + THREAD_START_SP
-	stmia	sp, {r0-r3, r12}
 	cpsie	i
 	svc	#0
 1:	cpsid	i
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi
index 15214d05fec1..8c20d4a0cb4e 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi
@@ -42,13 +42,14 @@
 
 		pinmux: pinmux@0014029c {
 			compatible = "pinctrl-single";
-			reg = <0x0014029c 0x250>;
+			reg = <0x0014029c 0x26c>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			pinctrl-single,register-width = <32>;
 			pinctrl-single,function-mask = <0xf>;
 			pinctrl-single,gpio-range = <
-				&range 0 154 MODE_GPIO
+				&range 0  91 MODE_GPIO
+				&range 95 60 MODE_GPIO
 				>;
 			range: gpio-range {
 				#pinctrl-single,gpio-range-cells = <3>;
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
index 2b76293b51c8..3d2921ef2935 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
@@ -444,8 +444,7 @@
 					<&pinmux 108 16 27>,
 					<&pinmux 135 77 6>,
 					<&pinmux 141 67 4>,
-					<&pinmux 145 149 6>,
-					<&pinmux 151 91 4>;
+					<&pinmux 145 149 6>;
 		};
 
 		i2c1: i2c@000e0000 {
diff --git a/arch/mips/bcm63xx/prom.c b/arch/mips/bcm63xx/prom.c
index 7019e2967009..bbbf8057565b 100644
--- a/arch/mips/bcm63xx/prom.c
+++ b/arch/mips/bcm63xx/prom.c
@@ -84,7 +84,7 @@ void __init prom_init(void)
 		 * Here we will start up CPU1 in the background and ask it to
 		 * reconfigure itself then go back to sleep.
 		 */
-		memcpy((void *)0xa0000200, &bmips_smp_movevec, 0x20);
+		memcpy((void *)0xa0000200, bmips_smp_movevec, 0x20);
 		__sync();
 		set_c0_cause(C_SW0);
 		cpumask_set_cpu(1, &bmips_booted_mask);
diff --git a/arch/mips/include/asm/bmips.h b/arch/mips/include/asm/bmips.h
index b3e2975f83d3..a564915fddc4 100644
--- a/arch/mips/include/asm/bmips.h
+++ b/arch/mips/include/asm/bmips.h
@@ -75,11 +75,11 @@ static inline int register_bmips_smp_ops(void)
 #endif
 }
 
-extern char bmips_reset_nmi_vec;
-extern char bmips_reset_nmi_vec_end;
-extern char bmips_smp_movevec;
-extern char bmips_smp_int_vec;
-extern char bmips_smp_int_vec_end;
+extern char bmips_reset_nmi_vec[];
+extern char bmips_reset_nmi_vec_end[];
+extern char bmips_smp_movevec[];
+extern char bmips_smp_int_vec[];
+extern char bmips_smp_int_vec_end[];
 
 extern int bmips_smp_enabled;
 extern int bmips_cpu_offset;
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 382d12eb88f0..45fbcbbf2504 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -457,10 +457,10 @@ static void bmips_wr_vec(unsigned long dst, char *start, char *end)
 
 static inline void bmips_nmi_handler_setup(void)
 {
-	bmips_wr_vec(BMIPS_NMI_RESET_VEC, &bmips_reset_nmi_vec,
-		&bmips_reset_nmi_vec_end);
-	bmips_wr_vec(BMIPS_WARM_RESTART_VEC, &bmips_smp_int_vec,
-		&bmips_smp_int_vec_end);
+	bmips_wr_vec(BMIPS_NMI_RESET_VEC, bmips_reset_nmi_vec,
+		bmips_reset_nmi_vec_end);
+	bmips_wr_vec(BMIPS_WARM_RESTART_VEC, bmips_smp_int_vec,
+		bmips_smp_int_vec_end);
 }
 
 struct reset_vec_info {
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 53b31c2bcdf4..7e3ccf21830e 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -215,7 +215,9 @@ enum {
 #define CPU_FTR_DAWR			LONG_ASM_CONST(0x0400000000000000)
 #define CPU_FTR_DABRX			LONG_ASM_CONST(0x0800000000000000)
 #define CPU_FTR_PMAO_BUG		LONG_ASM_CONST(0x1000000000000000)
+#define CPU_FTR_P9_TLBIE_STQ_BUG	LONG_ASM_CONST(0x0000400000000000)
 #define CPU_FTR_POWER9_DD1		LONG_ASM_CONST(0x4000000000000000)
+#define CPU_FTR_P9_TLBIE_ERAT_BUG	LONG_ASM_CONST(0x0001000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -475,7 +477,8 @@ enum {
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
-	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300)
+	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | \
+	    CPU_FTR_P9_TLBIE_STQ_BUG | CPU_FTR_P9_TLBIE_ERAT_BUG)
 #define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \
 			     (~CPU_FTR_SAO))
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 2dba206b065a..2357df60de95 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -733,15 +733,45 @@ static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f)
 	return true;
 }
 
+/*
+ * Handle POWER9 broadcast tlbie invalidation issue using
+ * cpu feature flag.
+ */
+static __init void update_tlbie_feature_flag(unsigned long pvr)
+{
+	if (PVR_VER(pvr) == PVR_POWER9) {
+		/*
+		 * Set the tlbie feature flag for anything below
+		 * Nimbus DD 2.3 and Cumulus DD 1.3
+		 */
+		if ((pvr & 0xe000) == 0) {
+			/* Nimbus */
+			if ((pvr & 0xfff) < 0x203)
+				cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG;
+		} else if ((pvr & 0xc000) == 0) {
+			/* Cumulus */
+			if ((pvr & 0xfff) < 0x103)
+				cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG;
+		} else {
+			WARN_ONCE(1, "Unknown PVR");
+			cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG;
+		}
+
+		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_ERAT_BUG;
+	}
+}
+
 static __init void cpufeatures_cpu_quirks(void)
 {
-	int version = mfspr(SPRN_PVR);
+	unsigned long version = mfspr(SPRN_PVR);
 
 	/*
 	 * Not all quirks can be derived from the cpufeatures device tree.
 	 */
 	if ((version & 0xffffff00) == 0x004e0100)
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1;
+
+	update_tlbie_feature_flag(version);
 }
 
 static void __init cpufeatures_setup_finished(void)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 27a41695fcfd..7f8f2a0189df 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -160,6 +160,9 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
 	asm volatile("ptesync": : :"memory");
 	asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
 		     : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG))
+		asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
+			     : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
 	asm volatile("ptesync": : :"memory");
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 4962d537c186..669b547385f3 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -429,6 +429,37 @@ static inline int try_lock_tlbie(unsigned int *lock)
 	return old == 0;
 }
 
+static inline void fixup_tlbie_lpid(unsigned long rb_value, unsigned long lpid)
+{
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		/* Radix flush for a hash guest */
+
+		unsigned long rb,rs,prs,r,ric;
+
+		rb = PPC_BIT(52); /* IS = 2 */
+		rs = 0;  /* lpid = 0 */
+		prs = 0; /* partition scoped */
+		r = 1;   /* radix format */
+		ric = 0; /* RIC_FLSUH_TLB */
+
+		/*
+		 * Need the extra ptesync to make sure we don't
+		 * re-order the tlbie
+		 */
+		asm volatile("ptesync": : :"memory");
+		asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+			     : : "r"(rb), "i"(r), "i"(prs),
+			       "i"(ric), "r"(rs) : "memory");
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
+			     "r" (rb_value), "r" (lpid));
+	}
+}
+
 static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
 		      long npages, int global, bool need_sync)
 {
@@ -448,6 +479,8 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
 			asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
 				     "r" (rbvalues[i]), "r" (kvm->arch.lpid));
 		}
+
+		fixup_tlbie_lpid(rbvalues[i - 1], kvm->arch.lpid);
 		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 		kvm->arch.tlbie_lock = 0;
 	} else {
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 640cf566e986..a4b6efbf667b 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -104,6 +104,37 @@ static inline unsigned long  ___tlbie(unsigned long vpn, int psize,
 	return va;
 }
 
+static inline void fixup_tlbie_vpn(unsigned long vpn, int psize,
+				   int apsize, int ssize)
+{
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		/* Radix flush for a hash guest */
+
+		unsigned long rb,rs,prs,r,ric;
+
+		rb = PPC_BIT(52); /* IS = 2 */
+		rs = 0;  /* lpid = 0 */
+		prs = 0; /* partition scoped */
+		r = 1;   /* radix format */
+		ric = 0; /* RIC_FLSUH_TLB */
+
+		/*
+		 * Need the extra ptesync to make sure we don't
+		 * re-order the tlbie
+		 */
+		asm volatile("ptesync": : :"memory");
+		asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+			     : : "r"(rb), "i"(r), "i"(prs),
+			       "i"(ric), "r"(rs) : "memory");
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		/* Need the extra ptesync to ensure we don't reorder tlbie*/
+		asm volatile("ptesync": : :"memory");
+		___tlbie(vpn, psize, apsize, ssize);
+	}
+}
+
 static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 {
 	unsigned long rb;
@@ -181,6 +212,7 @@ static inline void tlbie(unsigned long vpn, int psize, int apsize,
 		asm volatile("ptesync": : :"memory");
 	} else {
 		__tlbie(vpn, psize, apsize, ssize);
+		fixup_tlbie_vpn(vpn, psize, apsize, ssize);
 		asm volatile("eieio; tlbsync; ptesync": : :"memory");
 	}
 	if (lock_tlbie && !use_local)
@@ -674,7 +706,7 @@ static void native_hpte_clear(void)
  */
 static void native_flush_hash_range(unsigned long number, int local)
 {
-	unsigned long vpn;
+	unsigned long vpn = 0;
 	unsigned long hash, index, hidx, shift, slot;
 	struct hash_pte *hptep;
 	unsigned long hpte_v;
@@ -746,6 +778,10 @@ static void native_flush_hash_range(unsigned long number, int local)
 				__tlbie(vpn, psize, psize, ssize);
 			} pte_iterate_hashed_end();
 		}
+		/*
+		 * Just do one more with the last used values.
+		 */
+		fixup_tlbie_vpn(vpn, psize, psize, ssize);
 		asm volatile("eieio; tlbsync; ptesync":::"memory");
 
 		if (lock_tlbie)
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 12f95b1f7d07..48ed34d52ffd 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -491,6 +491,7 @@ void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
 			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
 		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0);
 	}
+	/* do we need fixup here ?*/
 	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 }
 EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 4b295cfd5f7e..41e782f126d6 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -23,6 +23,37 @@
 #define RIC_FLUSH_PWC 1
 #define RIC_FLUSH_ALL 2
 
+static inline void __tlbie_va(unsigned long va, unsigned long pid,
+			      unsigned long ap, unsigned long ric)
+{
+	unsigned long rb,rs,prs,r;
+
+	rb = va & ~(PPC_BITMASK(52, 63));
+	rb |= ap << PPC_BITLSHIFT(58);
+	rs = pid << PPC_BITLSHIFT(31);
+	prs = 1; /* process scoped */
+	r = 1;   /* raidx format */
+
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 0, rb, rs, ric, prs, r);
+}
+
+
+static inline void fixup_tlbie_va(unsigned long va, unsigned long pid,
+				  unsigned long ap)
+{
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_va(va, 0, ap, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_va(va, pid, ap, RIC_FLUSH_TLB);
+	}
+}
+
 static inline void __tlbiel_pid(unsigned long pid, int set,
 				unsigned long ric)
 {
@@ -68,22 +99,64 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
 }
 
-static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
+static inline void __tlbie_pid(unsigned long pid, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
 
 	rb = PPC_BIT(53); /* IS = 1 */
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
+	r = 1;   /* radix format */
 
-	asm volatile("ptesync": : :"memory");
 	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
+static inline void fixup_tlbie_pid(unsigned long pid)
+{
+	/*
+	 * We can use any address for the invalidation, pick one which is
+	 * probably unused as an optimisation.
+	 */
+	unsigned long va = ((1UL << 52) - 1);
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_pid(0, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_va(va, pid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
+	}
+}
+
+static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
+{
+	asm volatile("ptesync": : :"memory");
+
+	/*
+	 * Workaround the fact that the "ric" argument to __tlbie_pid
+	 * must be a compile-time contraint to match the "i" constraint
+	 * in the asm statement.
+	 */
+	switch (ric) {
+	case RIC_FLUSH_TLB:
+		__tlbie_pid(pid, RIC_FLUSH_TLB);
+		fixup_tlbie_pid(pid);
+		break;
+	case RIC_FLUSH_PWC:
+		__tlbie_pid(pid, RIC_FLUSH_PWC);
+		break;
+	case RIC_FLUSH_ALL:
+	default:
+		__tlbie_pid(pid, RIC_FLUSH_ALL);
+		fixup_tlbie_pid(pid);
+	}
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
+}
+
 static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 			      unsigned long ap, unsigned long ric)
 {
@@ -105,19 +178,10 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 static inline void _tlbie_va(unsigned long va, unsigned long pid,
 			     unsigned long ap, unsigned long ric)
 {
-	unsigned long rb,rs,prs,r;
-
-	rb = va & ~(PPC_BITMASK(52, 63));
-	rb |= ap << PPC_BITLSHIFT(58);
-	rs = pid << PPC_BITLSHIFT(31);
-	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
-
 	asm volatile("ptesync": : :"memory");
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	__tlbie_va(va, pid, ap, ric);
+	fixup_tlbie_va(va, pid, ap);
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
-	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
 /*
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index f3d0bc9a9905..34dfadd4dcd4 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -648,6 +648,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		ret = -ENOENT;
 		goto out;
 	}
+	if (cmd->status != BLK_STS_OK) {
+		dev_err(disk_to_dev(nbd->disk), "Command already handled %p\n",
+			req);
+		ret = -ENOENT;
+		goto out;
+	}
 	if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) {
 		dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n",
 			req);
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index 8fbf175fdcc7..57c5cc51f862 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -690,7 +690,21 @@ static int bam_dma_terminate_all(struct dma_chan *chan)
 
 	/* remove all transactions, including active transaction */
 	spin_lock_irqsave(&bchan->vc.lock, flag);
+	/*
+	 * If we have transactions queued, then some might be committed to the
+	 * hardware in the desc fifo.  The only way to reset the desc fifo is
+	 * to do a hardware reset (either by pipe or the entire block).
+	 * bam_chan_init_hw() will trigger a pipe reset, and also reinit the
+	 * pipe.  If the pipe is left disabled (default state after pipe reset)
+	 * and is accessed by a connected hardware engine, a fatal error in
+	 * the BAM will occur.  There is a small window where this could happen
+	 * with bam_chan_init_hw(), but it is assumed that the caller has
+	 * stopped activity on any attached hardware engine.  Make sure to do
+	 * this first so that the BAM hardware doesn't cause memory corruption
+	 * by accessing freed resources.
+	 */
 	if (bchan->curr_txd) {
+		bam_chan_init_hw(bchan, bchan->curr_txd->dir);
 		list_add(&bchan->curr_txd->vd.node, &bchan->vc.desc_issued);
 		bchan->curr_txd = NULL;
 	}
diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index d8cbe149925b..14f60751729e 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -219,7 +219,7 @@ struct stm32f7_i2c_dev {
 	struct stm32f7_i2c_timings timing;
 };
 
-/**
+/*
  * All these values are coming from I2C Specification, Version 6.0, 4th of
  * April 2014.
  *
diff --git a/drivers/iio/adc/stm32-adc-core.c b/drivers/iio/adc/stm32-adc-core.c
index 804198eb0eef..bc9ebcc6508a 100644
--- a/drivers/iio/adc/stm32-adc-core.c
+++ b/drivers/iio/adc/stm32-adc-core.c
@@ -33,36 +33,9 @@
 
 #include "stm32-adc-core.h"
 
-/* STM32F4 - common registers for all ADC instances: 1, 2 & 3 */
-#define STM32F4_ADC_CSR			(STM32_ADCX_COMN_OFFSET + 0x00)
-#define STM32F4_ADC_CCR			(STM32_ADCX_COMN_OFFSET + 0x04)
-
-/* STM32F4_ADC_CSR - bit fields */
-#define STM32F4_EOC3			BIT(17)
-#define STM32F4_EOC2			BIT(9)
-#define STM32F4_EOC1			BIT(1)
-
-/* STM32F4_ADC_CCR - bit fields */
-#define STM32F4_ADC_ADCPRE_SHIFT	16
-#define STM32F4_ADC_ADCPRE_MASK		GENMASK(17, 16)
-
 /* STM32 F4 maximum analog clock rate (from datasheet) */
 #define STM32F4_ADC_MAX_CLK_RATE	36000000
 
-/* STM32H7 - common registers for all ADC instances */
-#define STM32H7_ADC_CSR			(STM32_ADCX_COMN_OFFSET + 0x00)
-#define STM32H7_ADC_CCR			(STM32_ADCX_COMN_OFFSET + 0x08)
-
-/* STM32H7_ADC_CSR - bit fields */
-#define STM32H7_EOC_SLV			BIT(18)
-#define STM32H7_EOC_MST			BIT(2)
-
-/* STM32H7_ADC_CCR - bit fields */
-#define STM32H7_PRESC_SHIFT		18
-#define STM32H7_PRESC_MASK		GENMASK(21, 18)
-#define STM32H7_CKMODE_SHIFT		16
-#define STM32H7_CKMODE_MASK		GENMASK(17, 16)
-
 /* STM32 H7 maximum analog clock rate (from datasheet) */
 #define STM32H7_ADC_MAX_CLK_RATE	36000000
 
@@ -72,12 +45,16 @@
  * @eoc1:	adc1 end of conversion flag in @csr
  * @eoc2:	adc2 end of conversion flag in @csr
  * @eoc3:	adc3 end of conversion flag in @csr
+ * @ier:	interrupt enable register offset for each adc
+ * @eocie_msk:	end of conversion interrupt enable mask in @ier
  */
 struct stm32_adc_common_regs {
 	u32 csr;
 	u32 eoc1_msk;
 	u32 eoc2_msk;
 	u32 eoc3_msk;
+	u32 ier;
+	u32 eocie_msk;
 };
 
 struct stm32_adc_priv;
@@ -271,6 +248,8 @@ static const struct stm32_adc_common_regs stm32f4_adc_common_regs = {
 	.eoc1_msk = STM32F4_EOC1,
 	.eoc2_msk = STM32F4_EOC2,
 	.eoc3_msk = STM32F4_EOC3,
+	.ier = STM32F4_ADC_CR1,
+	.eocie_msk = STM32F4_EOCIE,
 };
 
 /* STM32H7 common registers definitions */
@@ -278,8 +257,24 @@ static const struct stm32_adc_common_regs stm32h7_adc_common_regs = {
 	.csr = STM32H7_ADC_CSR,
 	.eoc1_msk = STM32H7_EOC_MST,
 	.eoc2_msk = STM32H7_EOC_SLV,
+	.ier = STM32H7_ADC_IER,
+	.eocie_msk = STM32H7_EOCIE,
+};
+
+static const unsigned int stm32_adc_offset[STM32_ADC_MAX_ADCS] = {
+	0, STM32_ADC_OFFSET, STM32_ADC_OFFSET * 2,
 };
 
+static unsigned int stm32_adc_eoc_enabled(struct stm32_adc_priv *priv,
+					  unsigned int adc)
+{
+	u32 ier, offset = stm32_adc_offset[adc];
+
+	ier = readl_relaxed(priv->common.base + offset + priv->cfg->regs->ier);
+
+	return ier & priv->cfg->regs->eocie_msk;
+}
+
 /* ADC common interrupt for all instances */
 static void stm32_adc_irq_handler(struct irq_desc *desc)
 {
@@ -290,13 +285,28 @@ static void stm32_adc_irq_handler(struct irq_desc *desc)
 	chained_irq_enter(chip, desc);
 	status = readl_relaxed(priv->common.base + priv->cfg->regs->csr);
 
-	if (status & priv->cfg->regs->eoc1_msk)
+	/*
+	 * End of conversion may be handled by using IRQ or DMA. There may be a
+	 * race here when two conversions complete at the same time on several
+	 * ADCs. EOC may be read 'set' for several ADCs, with:
+	 * - an ADC configured to use DMA (EOC triggers the DMA request, and
+	 *   is then automatically cleared by DR read in hardware)
+	 * - an ADC configured to use IRQs (EOCIE bit is set. The handler must
+	 *   be called in this case)
+	 * So both EOC status bit in CSR and EOCIE control bit must be checked
+	 * before invoking the interrupt handler (e.g. call ISR only for
+	 * IRQ-enabled ADCs).
+	 */
+	if (status & priv->cfg->regs->eoc1_msk &&
+	    stm32_adc_eoc_enabled(priv, 0))
 		generic_handle_irq(irq_find_mapping(priv->domain, 0));
 
-	if (status & priv->cfg->regs->eoc2_msk)
+	if (status & priv->cfg->regs->eoc2_msk &&
+	    stm32_adc_eoc_enabled(priv, 1))
 		generic_handle_irq(irq_find_mapping(priv->domain, 1));
 
-	if (status & priv->cfg->regs->eoc3_msk)
+	if (status & priv->cfg->regs->eoc3_msk &&
+	    stm32_adc_eoc_enabled(priv, 2))
 		generic_handle_irq(irq_find_mapping(priv->domain, 2));
 
 	chained_irq_exit(chip, desc);
diff --git a/drivers/iio/adc/stm32-adc-core.h b/drivers/iio/adc/stm32-adc-core.h
index 250ee958a669..9f8559cf86c4 100644
--- a/drivers/iio/adc/stm32-adc-core.h
+++ b/drivers/iio/adc/stm32-adc-core.h
@@ -37,8 +37,143 @@
  * --------------------------------------------------------
  */
 #define STM32_ADC_MAX_ADCS		3
+#define STM32_ADC_OFFSET		0x100
 #define STM32_ADCX_COMN_OFFSET		0x300
 
+/* STM32F4 - Registers for each ADC instance */
+#define STM32F4_ADC_SR			0x00
+#define STM32F4_ADC_CR1			0x04
+#define STM32F4_ADC_CR2			0x08
+#define STM32F4_ADC_SMPR1		0x0C
+#define STM32F4_ADC_SMPR2		0x10
+#define STM32F4_ADC_HTR			0x24
+#define STM32F4_ADC_LTR			0x28
+#define STM32F4_ADC_SQR1		0x2C
+#define STM32F4_ADC_SQR2		0x30
+#define STM32F4_ADC_SQR3		0x34
+#define STM32F4_ADC_JSQR		0x38
+#define STM32F4_ADC_JDR1		0x3C
+#define STM32F4_ADC_JDR2		0x40
+#define STM32F4_ADC_JDR3		0x44
+#define STM32F4_ADC_JDR4		0x48
+#define STM32F4_ADC_DR			0x4C
+
+/* STM32F4 - common registers for all ADC instances: 1, 2 & 3 */
+#define STM32F4_ADC_CSR			(STM32_ADCX_COMN_OFFSET + 0x00)
+#define STM32F4_ADC_CCR			(STM32_ADCX_COMN_OFFSET + 0x04)
+
+/* STM32F4_ADC_SR - bit fields */
+#define STM32F4_STRT			BIT(4)
+#define STM32F4_EOC			BIT(1)
+
+/* STM32F4_ADC_CR1 - bit fields */
+#define STM32F4_RES_SHIFT		24
+#define STM32F4_RES_MASK		GENMASK(25, 24)
+#define STM32F4_SCAN			BIT(8)
+#define STM32F4_EOCIE			BIT(5)
+
+/* STM32F4_ADC_CR2 - bit fields */
+#define STM32F4_SWSTART			BIT(30)
+#define STM32F4_EXTEN_SHIFT		28
+#define STM32F4_EXTEN_MASK		GENMASK(29, 28)
+#define STM32F4_EXTSEL_SHIFT		24
+#define STM32F4_EXTSEL_MASK		GENMASK(27, 24)
+#define STM32F4_EOCS			BIT(10)
+#define STM32F4_DDS			BIT(9)
+#define STM32F4_DMA			BIT(8)
+#define STM32F4_ADON			BIT(0)
+
+/* STM32F4_ADC_CSR - bit fields */
+#define STM32F4_EOC3			BIT(17)
+#define STM32F4_EOC2			BIT(9)
+#define STM32F4_EOC1			BIT(1)
+
+/* STM32F4_ADC_CCR - bit fields */
+#define STM32F4_ADC_ADCPRE_SHIFT	16
+#define STM32F4_ADC_ADCPRE_MASK		GENMASK(17, 16)
+
+/* STM32H7 - Registers for each ADC instance */
+#define STM32H7_ADC_ISR			0x00
+#define STM32H7_ADC_IER			0x04
+#define STM32H7_ADC_CR			0x08
+#define STM32H7_ADC_CFGR		0x0C
+#define STM32H7_ADC_SMPR1		0x14
+#define STM32H7_ADC_SMPR2		0x18
+#define STM32H7_ADC_PCSEL		0x1C
+#define STM32H7_ADC_SQR1		0x30
+#define STM32H7_ADC_SQR2		0x34
+#define STM32H7_ADC_SQR3		0x38
+#define STM32H7_ADC_SQR4		0x3C
+#define STM32H7_ADC_DR			0x40
+#define STM32H7_ADC_CALFACT		0xC4
+#define STM32H7_ADC_CALFACT2		0xC8
+
+/* STM32H7 - common registers for all ADC instances */
+#define STM32H7_ADC_CSR			(STM32_ADCX_COMN_OFFSET + 0x00)
+#define STM32H7_ADC_CCR			(STM32_ADCX_COMN_OFFSET + 0x08)
+
+/* STM32H7_ADC_ISR - bit fields */
+#define STM32H7_EOC			BIT(2)
+#define STM32H7_ADRDY			BIT(0)
+
+/* STM32H7_ADC_IER - bit fields */
+#define STM32H7_EOCIE			STM32H7_EOC
+
+/* STM32H7_ADC_CR - bit fields */
+#define STM32H7_ADCAL			BIT(31)
+#define STM32H7_ADCALDIF		BIT(30)
+#define STM32H7_DEEPPWD			BIT(29)
+#define STM32H7_ADVREGEN		BIT(28)
+#define STM32H7_LINCALRDYW6		BIT(27)
+#define STM32H7_LINCALRDYW5		BIT(26)
+#define STM32H7_LINCALRDYW4		BIT(25)
+#define STM32H7_LINCALRDYW3		BIT(24)
+#define STM32H7_LINCALRDYW2		BIT(23)
+#define STM32H7_LINCALRDYW1		BIT(22)
+#define STM32H7_ADCALLIN		BIT(16)
+#define STM32H7_BOOST			BIT(8)
+#define STM32H7_ADSTP			BIT(4)
+#define STM32H7_ADSTART			BIT(2)
+#define STM32H7_ADDIS			BIT(1)
+#define STM32H7_ADEN			BIT(0)
+
+/* STM32H7_ADC_CFGR bit fields */
+#define STM32H7_EXTEN_SHIFT		10
+#define STM32H7_EXTEN_MASK		GENMASK(11, 10)
+#define STM32H7_EXTSEL_SHIFT		5
+#define STM32H7_EXTSEL_MASK		GENMASK(9, 5)
+#define STM32H7_RES_SHIFT		2
+#define STM32H7_RES_MASK		GENMASK(4, 2)
+#define STM32H7_DMNGT_SHIFT		0
+#define STM32H7_DMNGT_MASK		GENMASK(1, 0)
+
+enum stm32h7_adc_dmngt {
+	STM32H7_DMNGT_DR_ONLY,		/* Regular data in DR only */
+	STM32H7_DMNGT_DMA_ONESHOT,	/* DMA one shot mode */
+	STM32H7_DMNGT_DFSDM,		/* DFSDM mode */
+	STM32H7_DMNGT_DMA_CIRC,		/* DMA circular mode */
+};
+
+/* STM32H7_ADC_CALFACT - bit fields */
+#define STM32H7_CALFACT_D_SHIFT		16
+#define STM32H7_CALFACT_D_MASK		GENMASK(26, 16)
+#define STM32H7_CALFACT_S_SHIFT		0
+#define STM32H7_CALFACT_S_MASK		GENMASK(10, 0)
+
+/* STM32H7_ADC_CALFACT2 - bit fields */
+#define STM32H7_LINCALFACT_SHIFT	0
+#define STM32H7_LINCALFACT_MASK		GENMASK(29, 0)
+
+/* STM32H7_ADC_CSR - bit fields */
+#define STM32H7_EOC_SLV			BIT(18)
+#define STM32H7_EOC_MST			BIT(2)
+
+/* STM32H7_ADC_CCR - bit fields */
+#define STM32H7_PRESC_SHIFT		18
+#define STM32H7_PRESC_MASK		GENMASK(21, 18)
+#define STM32H7_CKMODE_SHIFT		16
+#define STM32H7_CKMODE_MASK		GENMASK(17, 16)
+
 /**
  * struct stm32_adc_common - stm32 ADC driver common data (for all instances)
  * @base:		control registers base cpu addr
diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c
index 04be8bd951be..e59cbc9ad4f6 100644
--- a/drivers/iio/adc/stm32-adc.c
+++ b/drivers/iio/adc/stm32-adc.c
@@ -40,113 +40,6 @@
 
 #include "stm32-adc-core.h"
 
-/* STM32F4 - Registers for each ADC instance */
-#define STM32F4_ADC_SR			0x00
-#define STM32F4_ADC_CR1			0x04
-#define STM32F4_ADC_CR2			0x08
-#define STM32F4_ADC_SMPR1		0x0C
-#define STM32F4_ADC_SMPR2		0x10
-#define STM32F4_ADC_HTR			0x24
-#define STM32F4_ADC_LTR			0x28
-#define STM32F4_ADC_SQR1		0x2C
-#define STM32F4_ADC_SQR2		0x30
-#define STM32F4_ADC_SQR3		0x34
-#define STM32F4_ADC_JSQR		0x38
-#define STM32F4_ADC_JDR1		0x3C
-#define STM32F4_ADC_JDR2		0x40
-#define STM32F4_ADC_JDR3		0x44
-#define STM32F4_ADC_JDR4		0x48
-#define STM32F4_ADC_DR			0x4C
-
-/* STM32F4_ADC_SR - bit fields */
-#define STM32F4_STRT			BIT(4)
-#define STM32F4_EOC			BIT(1)
-
-/* STM32F4_ADC_CR1 - bit fields */
-#define STM32F4_RES_SHIFT		24
-#define STM32F4_RES_MASK		GENMASK(25, 24)
-#define STM32F4_SCAN			BIT(8)
-#define STM32F4_EOCIE			BIT(5)
-
-/* STM32F4_ADC_CR2 - bit fields */
-#define STM32F4_SWSTART			BIT(30)
-#define STM32F4_EXTEN_SHIFT		28
-#define STM32F4_EXTEN_MASK		GENMASK(29, 28)
-#define STM32F4_EXTSEL_SHIFT		24
-#define STM32F4_EXTSEL_MASK		GENMASK(27, 24)
-#define STM32F4_EOCS			BIT(10)
-#define STM32F4_DDS			BIT(9)
-#define STM32F4_DMA			BIT(8)
-#define STM32F4_ADON			BIT(0)
-
-/* STM32H7 - Registers for each ADC instance */
-#define STM32H7_ADC_ISR			0x00
-#define STM32H7_ADC_IER			0x04
-#define STM32H7_ADC_CR			0x08
-#define STM32H7_ADC_CFGR		0x0C
-#define STM32H7_ADC_SMPR1		0x14
-#define STM32H7_ADC_SMPR2		0x18
-#define STM32H7_ADC_PCSEL		0x1C
-#define STM32H7_ADC_SQR1		0x30
-#define STM32H7_ADC_SQR2		0x34
-#define STM32H7_ADC_SQR3		0x38
-#define STM32H7_ADC_SQR4		0x3C
-#define STM32H7_ADC_DR			0x40
-#define STM32H7_ADC_CALFACT		0xC4
-#define STM32H7_ADC_CALFACT2		0xC8
-
-/* STM32H7_ADC_ISR - bit fields */
-#define STM32H7_EOC			BIT(2)
-#define STM32H7_ADRDY			BIT(0)
-
-/* STM32H7_ADC_IER - bit fields */
-#define STM32H7_EOCIE			STM32H7_EOC
-
-/* STM32H7_ADC_CR - bit fields */
-#define STM32H7_ADCAL			BIT(31)
-#define STM32H7_ADCALDIF		BIT(30)
-#define STM32H7_DEEPPWD			BIT(29)
-#define STM32H7_ADVREGEN		BIT(28)
-#define STM32H7_LINCALRDYW6		BIT(27)
-#define STM32H7_LINCALRDYW5		BIT(26)
-#define STM32H7_LINCALRDYW4		BIT(25)
-#define STM32H7_LINCALRDYW3		BIT(24)
-#define STM32H7_LINCALRDYW2		BIT(23)
-#define STM32H7_LINCALRDYW1		BIT(22)
-#define STM32H7_ADCALLIN		BIT(16)
-#define STM32H7_BOOST			BIT(8)
-#define STM32H7_ADSTP			BIT(4)
-#define STM32H7_ADSTART			BIT(2)
-#define STM32H7_ADDIS			BIT(1)
-#define STM32H7_ADEN			BIT(0)
-
-/* STM32H7_ADC_CFGR bit fields */
-#define STM32H7_EXTEN_SHIFT		10
-#define STM32H7_EXTEN_MASK		GENMASK(11, 10)
-#define STM32H7_EXTSEL_SHIFT		5
-#define STM32H7_EXTSEL_MASK		GENMASK(9, 5)
-#define STM32H7_RES_SHIFT		2
-#define STM32H7_RES_MASK		GENMASK(4, 2)
-#define STM32H7_DMNGT_SHIFT		0
-#define STM32H7_DMNGT_MASK		GENMASK(1, 0)
-
-enum stm32h7_adc_dmngt {
-	STM32H7_DMNGT_DR_ONLY,		/* Regular data in DR only */
-	STM32H7_DMNGT_DMA_ONESHOT,	/* DMA one shot mode */
-	STM32H7_DMNGT_DFSDM,		/* DFSDM mode */
-	STM32H7_DMNGT_DMA_CIRC,		/* DMA circular mode */
-};
-
-/* STM32H7_ADC_CALFACT - bit fields */
-#define STM32H7_CALFACT_D_SHIFT		16
-#define STM32H7_CALFACT_D_MASK		GENMASK(26, 16)
-#define STM32H7_CALFACT_S_SHIFT		0
-#define STM32H7_CALFACT_S_MASK		GENMASK(10, 0)
-
-/* STM32H7_ADC_CALFACT2 - bit fields */
-#define STM32H7_LINCALFACT_SHIFT	0
-#define STM32H7_LINCALFACT_MASK		GENMASK(29, 0)
-
 /* Number of linear calibration shadow registers / LINCALRDYW control bits */
 #define STM32H7_LINCALFACT_NUM		6
 
diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index 91efbf0f19f9..da45049de97e 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -743,7 +743,7 @@ capi_poll(struct file *file, poll_table *wait)
 
 	poll_wait(file, &(cdev->recvwait), wait);
 	mask = POLLOUT | POLLWRNORM;
-	if (!skb_queue_empty(&cdev->recvqueue))
+	if (!skb_queue_empty_lockless(&cdev->recvqueue))
 		mask |= POLLIN | POLLRDNORM;
 	return mask;
 }
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index acf64d4cd94c..434e6dced6b7 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1431,7 +1431,6 @@ int b53_mirror_add(struct dsa_switch *ds, int port,
 		loc = B53_EG_MIR_CTL;
 
 	b53_read16(dev, B53_MGMT_PAGE, loc, &reg);
-	reg &= ~MIRROR_MASK;
 	reg |= BIT(port);
 	b53_write16(dev, B53_MGMT_PAGE, loc, reg);
 
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 0132921f408a..604c5abc08eb 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -106,22 +106,11 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 	unsigned int i;
 	u32 reg, offset;
 
-	if (priv->type == BCM7445_DEVICE_ID)
-		offset = CORE_STS_OVERRIDE_IMP;
-	else
-		offset = CORE_STS_OVERRIDE_IMP2;
-
 	/* Enable the port memories */
 	reg = core_readl(priv, CORE_MEM_PSM_VDD_CTRL);
 	reg &= ~P_TXQ_PSM_VDD(port);
 	core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL);
 
-	/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
-	reg = core_readl(priv, CORE_IMP_CTL);
-	reg |= (RX_BCST_EN | RX_MCST_EN | RX_UCST_EN);
-	reg &= ~(RX_DIS | TX_DIS);
-	core_writel(priv, reg, CORE_IMP_CTL);
-
 	/* Enable forwarding */
 	core_writel(priv, SW_FWDG_EN, CORE_SWMODE);
 
@@ -140,10 +129,27 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 
 	bcm_sf2_brcm_hdr_setup(priv, port);
 
-	/* Force link status for IMP port */
-	reg = core_readl(priv, offset);
-	reg |= (MII_SW_OR | LINK_STS);
-	core_writel(priv, reg, offset);
+	if (port == 8) {
+		if (priv->type == BCM7445_DEVICE_ID)
+			offset = CORE_STS_OVERRIDE_IMP;
+		else
+			offset = CORE_STS_OVERRIDE_IMP2;
+
+		/* Force link status for IMP port */
+		reg = core_readl(priv, offset);
+		reg |= (MII_SW_OR | LINK_STS);
+		core_writel(priv, reg, offset);
+
+		/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
+		reg = core_readl(priv, CORE_IMP_CTL);
+		reg |= (RX_BCST_EN | RX_MCST_EN | RX_UCST_EN);
+		reg &= ~(RX_DIS | TX_DIS);
+		core_writel(priv, reg, CORE_IMP_CTL);
+	} else {
+		reg = core_readl(priv, CORE_G_PCTL_PORT(port));
+		reg &= ~(RX_DIS | TX_DIS);
+		core_writel(priv, reg, CORE_G_PCTL_PORT(port));
+	}
 }
 
 static void bcm_sf2_eee_enable_set(struct dsa_switch *ds, int port, bool enable)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index d857df8ebdb4..1cc4fb27c13b 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1985,6 +1985,8 @@ static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv)
 	 */
 	if (priv->internal_phy) {
 		int0_enable |= UMAC_IRQ_LINK_EVENT;
+		if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv))
+			int0_enable |= UMAC_IRQ_PHY_DET_R;
 	} else if (priv->ext_phy) {
 		int0_enable |= UMAC_IRQ_LINK_EVENT;
 	} else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
@@ -2608,6 +2610,10 @@ static void bcmgenet_irq_task(struct work_struct *work)
 		bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
 	}
 
+	if (status & UMAC_IRQ_PHY_DET_R &&
+	    priv->dev->phydev->autoneg != AUTONEG_ENABLE)
+		phy_init_hw(priv->dev->phydev);
+
 	/* Link UP/DOWN event */
 	if (status & UMAC_IRQ_LINK_EVENT)
 		phy_mac_interrupt(priv->phydev,
@@ -2713,8 +2719,7 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 	}
 
 	/* all other interested interrupts handled in bottom half */
-	status &= (UMAC_IRQ_LINK_EVENT |
-		   UMAC_IRQ_MPD_R);
+	status &= (UMAC_IRQ_LINK_EVENT | UMAC_IRQ_MPD_R | UMAC_IRQ_PHY_DET_R);
 	if (status) {
 		/* Save irq status for bottom-half processing. */
 		spin_lock_irqsave(&priv->lock, flags);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index 8441ce3541af..ad4c9f17d77c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -670,10 +670,10 @@ static void uld_init(struct adapter *adap, struct cxgb4_lld_info *lld)
 	lld->fr_nsmr_tpte_wr_support = adap->params.fr_nsmr_tpte_wr_support;
 }
 
-static void uld_attach(struct adapter *adap, unsigned int uld)
+static int uld_attach(struct adapter *adap, unsigned int uld)
 {
-	void *handle;
 	struct cxgb4_lld_info lli;
+	void *handle;
 
 	uld_init(adap, &lli);
 	uld_queue_init(adap, uld, &lli);
@@ -683,7 +683,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 		dev_warn(adap->pdev_dev,
 			 "could not attach to the %s driver, error %ld\n",
 			 adap->uld[uld].name, PTR_ERR(handle));
-		return;
+		return PTR_ERR(handle);
 	}
 
 	adap->uld[uld].handle = handle;
@@ -691,23 +691,24 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 
 	if (adap->flags & FULL_INIT_DONE)
 		adap->uld[uld].state_change(handle, CXGB4_STATE_UP);
+
+	return 0;
 }
 
-/**
- *	cxgb4_register_uld - register an upper-layer driver
- *	@type: the ULD type
- *	@p: the ULD methods
+/* cxgb4_register_uld - register an upper-layer driver
+ * @type: the ULD type
+ * @p: the ULD methods
  *
- *	Registers an upper-layer driver with this driver and notifies the ULD
- *	about any presently available devices that support its type.  Returns
- *	%-EBUSY if a ULD of the same type is already registered.
+ * Registers an upper-layer driver with this driver and notifies the ULD
+ * about any presently available devices that support its type.  Returns
+ * %-EBUSY if a ULD of the same type is already registered.
  */
 int cxgb4_register_uld(enum cxgb4_uld type,
 		       const struct cxgb4_uld_info *p)
 {
-	int ret = 0;
 	unsigned int adap_idx = 0;
 	struct adapter *adap;
+	int ret = 0;
 
 	if (type >= CXGB4_ULD_MAX)
 		return -EINVAL;
@@ -741,12 +742,16 @@ int cxgb4_register_uld(enum cxgb4_uld type,
 		if (ret)
 			goto free_irq;
 		adap->uld[type] = *p;
-		uld_attach(adap, type);
+		ret = uld_attach(adap, type);
+		if (ret)
+			goto free_txq;
 		adap_idx++;
 	}
 	mutex_unlock(&uld_mutex);
 	return 0;
 
+free_txq:
+	release_sge_txq_uld(adap, type);
 free_irq:
 	if (adap->flags & FULL_INIT_DONE)
 		quiesce_rx_uld(adap, type);
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 9ed8e4b81530..bfda315a3f1b 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -734,6 +734,18 @@ static int ftgmac100_hard_start_xmit(struct sk_buff *skb,
 	 */
 	nfrags = skb_shinfo(skb)->nr_frags;
 
+	/* Setup HW checksumming */
+	csum_vlan = 0;
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    !ftgmac100_prep_tx_csum(skb, &csum_vlan))
+		goto drop;
+
+	/* Add VLAN tag */
+	if (skb_vlan_tag_present(skb)) {
+		csum_vlan |= FTGMAC100_TXDES1_INS_VLANTAG;
+		csum_vlan |= skb_vlan_tag_get(skb) & 0xffff;
+	}
+
 	/* Get header len */
 	len = skb_headlen(skb);
 
@@ -760,19 +772,6 @@ static int ftgmac100_hard_start_xmit(struct sk_buff *skb,
 	if (nfrags == 0)
 		f_ctl_stat |= FTGMAC100_TXDES0_LTS;
 	txdes->txdes3 = cpu_to_le32(map);
-
-	/* Setup HW checksumming */
-	csum_vlan = 0;
-	if (skb->ip_summed == CHECKSUM_PARTIAL &&
-	    !ftgmac100_prep_tx_csum(skb, &csum_vlan))
-		goto drop;
-
-	/* Add VLAN tag */
-	if (skb_vlan_tag_present(skb)) {
-		csum_vlan |= FTGMAC100_TXDES1_INS_VLANTAG;
-		csum_vlan |= skb_vlan_tag_get(skb) & 0xffff;
-	}
-
 	txdes->txdes1 = cpu_to_le32(csum_vlan);
 
 	/* Next descriptor */
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index 1bfe9544b3c1..17cbe8145dcd 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -174,6 +174,7 @@ struct hip04_priv {
 	dma_addr_t rx_phys[RX_DESC_NUM];
 	unsigned int rx_head;
 	unsigned int rx_buf_size;
+	unsigned int rx_cnt_remaining;
 
 	struct device_node *phy_node;
 	struct phy_device *phy;
@@ -487,7 +488,6 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget)
 	struct hip04_priv *priv = container_of(napi, struct hip04_priv, napi);
 	struct net_device *ndev = priv->ndev;
 	struct net_device_stats *stats = &ndev->stats;
-	unsigned int cnt = hip04_recv_cnt(priv);
 	struct rx_desc *desc;
 	struct sk_buff *skb;
 	unsigned char *buf;
@@ -500,8 +500,8 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget)
 
 	/* clean up tx descriptors */
 	tx_remaining = hip04_tx_reclaim(ndev, false);
-
-	while (cnt && !last) {
+	priv->rx_cnt_remaining += hip04_recv_cnt(priv);
+	while (priv->rx_cnt_remaining && !last) {
 		buf = priv->rx_buf[priv->rx_head];
 		skb = build_skb(buf, priv->rx_buf_size);
 		if (unlikely(!skb)) {
@@ -547,11 +547,13 @@ refill:
 		hip04_set_recv_desc(priv, phys);
 
 		priv->rx_head = RX_NEXT(priv->rx_head);
-		if (rx >= budget)
+		if (rx >= budget) {
+			--priv->rx_cnt_remaining;
 			goto done;
+		}
 
-		if (--cnt == 0)
-			cnt = hip04_recv_cnt(priv);
+		if (--priv->rx_cnt_remaining == 0)
+			priv->rx_cnt_remaining += hip04_recv_cnt(priv);
 	}
 
 	if (!(priv->reg_inten & RCV_INT)) {
@@ -636,6 +638,7 @@ static int hip04_mac_open(struct net_device *ndev)
 	int i;
 
 	priv->rx_head = 0;
+	priv->rx_cnt_remaining = 0;
 	priv->tx_head = 0;
 	priv->tx_tail = 0;
 	hip04_reset_ppe(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 53ca6cf316dc..66e8054a8966 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -471,12 +471,31 @@ void mlx4_init_quotas(struct mlx4_dev *dev)
 		priv->mfunc.master.res_tracker.res_alloc[RES_MPT].quota[pf];
 }
 
-static int get_max_gauranteed_vfs_counter(struct mlx4_dev *dev)
+static int
+mlx4_calc_res_counter_guaranteed(struct mlx4_dev *dev,
+				 struct resource_allocator *res_alloc,
+				 int vf)
 {
-	/* reduce the sink counter */
-	return (dev->caps.max_counters - 1 -
-		(MLX4_PF_COUNTERS_PER_PORT * MLX4_MAX_PORTS))
-		/ MLX4_MAX_PORTS;
+	struct mlx4_active_ports actv_ports;
+	int ports, counters_guaranteed;
+
+	/* For master, only allocate according to the number of phys ports */
+	if (vf == mlx4_master_func_num(dev))
+		return MLX4_PF_COUNTERS_PER_PORT * dev->caps.num_ports;
+
+	/* calculate real number of ports for the VF */
+	actv_ports = mlx4_get_active_ports(dev, vf);
+	ports = bitmap_weight(actv_ports.ports, dev->caps.num_ports);
+	counters_guaranteed = ports * MLX4_VF_COUNTERS_PER_PORT;
+
+	/* If we do not have enough counters for this VF, do not
+	 * allocate any for it. '-1' to reduce the sink counter.
+	 */
+	if ((res_alloc->res_reserved + counters_guaranteed) >
+	    (dev->caps.max_counters - 1))
+		return 0;
+
+	return counters_guaranteed;
 }
 
 int mlx4_init_resource_tracker(struct mlx4_dev *dev)
@@ -484,7 +503,6 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i, j;
 	int t;
-	int max_vfs_guarantee_counter = get_max_gauranteed_vfs_counter(dev);
 
 	priv->mfunc.master.res_tracker.slave_list =
 		kzalloc(dev->num_slaves * sizeof(struct slave_list),
@@ -601,16 +619,8 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 				break;
 			case RES_COUNTER:
 				res_alloc->quota[t] = dev->caps.max_counters;
-				if (t == mlx4_master_func_num(dev))
-					res_alloc->guaranteed[t] =
-						MLX4_PF_COUNTERS_PER_PORT *
-						MLX4_MAX_PORTS;
-				else if (t <= max_vfs_guarantee_counter)
-					res_alloc->guaranteed[t] =
-						MLX4_VF_COUNTERS_PER_PORT *
-						MLX4_MAX_PORTS;
-				else
-					res_alloc->guaranteed[t] = 0;
+				res_alloc->guaranteed[t] =
+					mlx4_calc_res_counter_guaranteed(dev, res_alloc, t);
 				break;
 			default:
 				break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index eec7c2ef067a..bf311a3c3e02 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1093,8 +1093,11 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_ENABLED)))
 		return 0;
 
-	if (cq->decmprs_left)
+	if (cq->decmprs_left) {
 		work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget);
+		if (cq->decmprs_left || work_done >= budget)
+			goto out;
+	}
 
 	cqe = mlx5_cqwq_get_cqe(&cq->wq);
 	if (!cqe) {
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index ffd15f5f836f..6c7a169d906a 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -800,6 +800,13 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+/* ThinkPad USB-C Dock Gen 2 (based on Realtek RTL8153) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0xa387, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* NVIDIA Tegra USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(NVIDIA_VENDOR_ID, 0x09ff, USB_CLASS_COMM,
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 24b994c68bcc..78a12d7b96e8 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -3642,10 +3642,14 @@ static int lan78xx_probe(struct usb_interface *intf,
 	/* driver requires remote-wakeup capability during autosuspend. */
 	intf->needs_remote_wakeup = 1;
 
+	ret = lan78xx_phy_init(dev);
+	if (ret < 0)
+		goto out4;
+
 	ret = register_netdev(netdev);
 	if (ret != 0) {
 		netif_err(dev, probe, netdev, "couldn't register the device\n");
-		goto out4;
+		goto out5;
 	}
 
 	usb_set_intfdata(intf, dev);
@@ -3658,14 +3662,10 @@ static int lan78xx_probe(struct usb_interface *intf,
 	pm_runtime_set_autosuspend_delay(&udev->dev,
 					 DEFAULT_AUTOSUSPEND_DELAY);
 
-	ret = lan78xx_phy_init(dev);
-	if (ret < 0)
-		goto out5;
-
 	return 0;
 
 out5:
-	unregister_netdev(netdev);
+	phy_disconnect(netdev->phydev);
 out4:
 	usb_free_urb(dev->urb_intr);
 out3:
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index c0964281ab98..6a86a03c5e95 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -5324,6 +5324,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x7205)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x720c)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x7214)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0xa387)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_TPLINK,  0x0601)},
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 2fbaa279988e..6d26bbd190dd 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2169,8 +2169,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		vni = tunnel_id_to_key32(info->key.tun_id);
 		ifindex = 0;
 		dst_cache = &info->dst_cache;
-		if (info->options_len)
+		if (info->options_len) {
+			if (info->options_len < sizeof(*md))
+				goto drop;
 			md = ip_tunnel_info_opts(info);
+		}
 		ttl = info->key.ttl;
 		tos = info->key.tos;
 		label = info->key.label;
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 7c6aff761800..87650d42682f 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -1002,6 +1002,7 @@ static int __init unittest_data_add(void)
 	of_fdt_unflatten_tree(unittest_data, NULL, &unittest_data_node);
 	if (!unittest_data_node) {
 		pr_warn("%s: No tree to attach; not running tests\n", __func__);
+		kfree(unittest_data);
 		return -ENODATA;
 	}
 	of_node_set_flag(unittest_data_node, OF_DETACHED);
diff --git a/drivers/pinctrl/bcm/pinctrl-ns2-mux.c b/drivers/pinctrl/bcm/pinctrl-ns2-mux.c
index 4b5cf0e0f16e..951090faa6a9 100644
--- a/drivers/pinctrl/bcm/pinctrl-ns2-mux.c
+++ b/drivers/pinctrl/bcm/pinctrl-ns2-mux.c
@@ -640,8 +640,8 @@ static int ns2_pinmux_enable(struct pinctrl_dev *pctrl_dev,
 	const struct ns2_pin_function *func;
 	const struct ns2_pin_group *grp;
 
-	if (grp_select > pinctrl->num_groups ||
-		func_select > pinctrl->num_functions)
+	if (grp_select >= pinctrl->num_groups ||
+		func_select >= pinctrl->num_functions)
 		return -EINVAL;
 
 	func = &pinctrl->functions[func_select];
diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c
index 63a6881c7078..971ae892c611 100644
--- a/drivers/platform/x86/pmc_atom.c
+++ b/drivers/platform/x86/pmc_atom.c
@@ -475,6 +475,13 @@ static const struct dmi_system_id critclk_systems[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "CB6363"),
 		},
 	},
+	{
+		.ident = "SIMATIC IPC227E",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "SIEMENS AG"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "6ES7647-8B"),
+		},
+	},
 	{ /*sentinel*/ }
 };
 
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 659e516455be..4f205366d8ae 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -632,7 +632,13 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 
 		/* SW2~SW4 high bit check and modify the voltage value table */
 		if (i >= sw_check_start && i <= sw_check_end) {
-			regmap_read(pfuze_chip->regmap, desc->vsel_reg, &val);
+			ret = regmap_read(pfuze_chip->regmap,
+						desc->vsel_reg, &val);
+			if (ret) {
+				dev_err(&client->dev, "Fails to read from the register.\n");
+				return ret;
+			}
+
 			if (val & sw_hi) {
 				if (pfuze_chip->chip_id == PFUZE3000) {
 					desc->volt_table = pfuze3000_sw2hi;
diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c
index d2f994298753..6d17357b3a24 100644
--- a/drivers/regulator/ti-abb-regulator.c
+++ b/drivers/regulator/ti-abb-regulator.c
@@ -173,19 +173,14 @@ static int ti_abb_wait_txdone(struct device *dev, struct ti_abb *abb)
 	while (timeout++ <= abb->settling_time) {
 		status = ti_abb_check_txdone(abb);
 		if (status)
-			break;
+			return 0;
 
 		udelay(1);
 	}
 
-	if (timeout > abb->settling_time) {
-		dev_warn_ratelimited(dev,
-				     "%s:TRANXDONE timeout(%duS) int=0x%08x\n",
-				     __func__, timeout, readl(abb->int_base));
-		return -ETIMEDOUT;
-	}
-
-	return 0;
+	dev_warn_ratelimited(dev, "%s:TRANXDONE timeout(%duS) int=0x%08x\n",
+			     __func__, timeout, readl(abb->int_base));
+	return -ETIMEDOUT;
 }
 
 /**
@@ -205,19 +200,14 @@ static int ti_abb_clear_all_txdone(struct device *dev, const struct ti_abb *abb)
 
 		status = ti_abb_check_txdone(abb);
 		if (!status)
-			break;
+			return 0;
 
 		udelay(1);
 	}
 
-	if (timeout > abb->settling_time) {
-		dev_warn_ratelimited(dev,
-				     "%s:TRANXDONE timeout(%duS) int=0x%08x\n",
-				     __func__, timeout, readl(abb->int_base));
-		return -ETIMEDOUT;
-	}
-
-	return 0;
+	dev_warn_ratelimited(dev, "%s:TRANXDONE timeout(%duS) int=0x%08x\n",
+			     __func__, timeout, readl(abb->int_base));
+	return -ETIMEDOUT;
 }
 
 /**
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 41366339b950..881906dc33b8 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -966,7 +966,7 @@ config SCSI_SNI_53C710
 
 config 53C700_LE_ON_BE
 	bool
-	depends on SCSI_LASI700
+	depends on SCSI_LASI700 || SCSI_SNI_53C710
 	default y
 
 config SCSI_STEX
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 41f5f6410163..135376ee2cbf 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -523,6 +523,7 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg)
 	unsigned int tpg_desc_tbl_off;
 	unsigned char orig_transition_tmo;
 	unsigned long flags;
+	bool transitioning_sense = false;
 
 	if (!pg->expiry) {
 		unsigned long transition_tmo = ALUA_FAILOVER_TIMEOUT * HZ;
@@ -567,13 +568,19 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg)
 			goto retry;
 		}
 		/*
-		 * Retry on ALUA state transition or if any
-		 * UNIT ATTENTION occurred.
+		 * If the array returns with 'ALUA state transition'
+		 * sense code here it cannot return RTPG data during
+		 * transition. So set the state to 'transitioning' directly.
 		 */
 		if (sense_hdr.sense_key == NOT_READY &&
-		    sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x0a)
-			err = SCSI_DH_RETRY;
-		else if (sense_hdr.sense_key == UNIT_ATTENTION)
+		    sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x0a) {
+			transitioning_sense = true;
+			goto skip_rtpg;
+		}
+		/*
+		 * Retry on any other UNIT ATTENTION occurred.
+		 */
+		if (sense_hdr.sense_key == UNIT_ATTENTION)
 			err = SCSI_DH_RETRY;
 		if (err == SCSI_DH_RETRY &&
 		    pg->expiry != 0 && time_before(jiffies, pg->expiry)) {
@@ -661,7 +668,11 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg)
 		off = 8 + (desc[7] * 4);
 	}
 
+ skip_rtpg:
 	spin_lock_irqsave(&pg->lock, flags);
+	if (transitioning_sense)
+		pg->state = SCSI_ACCESS_STATE_TRANSITIONING;
+
 	sdev_printk(KERN_INFO, sdev,
 		    "%s: port group %02x state %c %s supports %c%c%c%c%c%c%c\n",
 		    ALUA_DH_NAME, pg->group_id, print_alua_state(pg->state),
diff --git a/drivers/scsi/sni_53c710.c b/drivers/scsi/sni_53c710.c
index 1f9a087daf69..3102a75984d3 100644
--- a/drivers/scsi/sni_53c710.c
+++ b/drivers/scsi/sni_53c710.c
@@ -78,10 +78,8 @@ static int snirm710_probe(struct platform_device *dev)
 
 	base = res->start;
 	hostdata = kzalloc(sizeof(*hostdata), GFP_KERNEL);
-	if (!hostdata) {
-		dev_printk(KERN_ERR, dev, "Failed to allocate host data\n");
+	if (!hostdata)
 		return -ENOMEM;
-	}
 
 	hostdata->dev = &dev->dev;
 	dma_set_mask(&dev->dev, DMA_BIT_MASK(32));
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 84742125f773..92b52d2314b5 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -1151,27 +1151,6 @@ passthrough_parse_cdb(struct se_cmd *cmd,
 	struct se_device *dev = cmd->se_dev;
 	unsigned int size;
 
-	/*
-	 * Clear a lun set in the cdb if the initiator talking to use spoke
-	 * and old standards version, as we can't assume the underlying device
-	 * won't choke up on it.
-	 */
-	switch (cdb[0]) {
-	case READ_10: /* SBC - RDProtect */
-	case READ_12: /* SBC - RDProtect */
-	case READ_16: /* SBC - RDProtect */
-	case SEND_DIAGNOSTIC: /* SPC - SELF-TEST Code */
-	case VERIFY: /* SBC - VRProtect */
-	case VERIFY_16: /* SBC - VRProtect */
-	case WRITE_VERIFY: /* SBC - VRProtect */
-	case WRITE_VERIFY_12: /* SBC - VRProtect */
-	case MAINTENANCE_IN: /* SPC - Parameter Data Format for SA RTPG */
-		break;
-	default:
-		cdb[1] &= 0x1f; /* clear logical unit number */
-		break;
-	}
-
 	/*
 	 * For REPORT LUNS we always need to emulate the response, for everything
 	 * else, pass it up.
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 7b7ab10a9db1..600bb838c15b 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1210,6 +1210,11 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file);
 struct cifsInodeInfo {
 	bool can_cache_brlcks;
 	struct list_head llist;	/* locks helb by this inode */
+	/*
+	 * NOTE: Some code paths call down_read(lock_sem) twice, so
+	 * we must always use use cifs_down_write() instead of down_write()
+	 * for this semaphore to avoid deadlocks.
+	 */
 	struct rw_semaphore lock_sem;	/* protect the fields above */
 	/* BB add in lists for dirty pages i.e. write caching info for oplock */
 	struct list_head openFileList;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index ccdb42f71b2e..3a7fb8e750e9 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -149,6 +149,7 @@ extern int cifs_unlock_range(struct cifsFileInfo *cfile,
 			     struct file_lock *flock, const unsigned int xid);
 extern int cifs_push_mandatory_locks(struct cifsFileInfo *cfile);
 
+extern void cifs_down_write(struct rw_semaphore *sem);
 extern struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid,
 					      struct file *file,
 					      struct tcon_link *tlink,
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 71a960da7cce..40f22932343c 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -280,6 +280,13 @@ cifs_has_mand_locks(struct cifsInodeInfo *cinode)
 	return has_locks;
 }
 
+void
+cifs_down_write(struct rw_semaphore *sem)
+{
+	while (!down_write_trylock(sem))
+		msleep(10);
+}
+
 struct cifsFileInfo *
 cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 		  struct tcon_link *tlink, __u32 oplock)
@@ -305,7 +312,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 	INIT_LIST_HEAD(&fdlocks->locks);
 	fdlocks->cfile = cfile;
 	cfile->llist = fdlocks;
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 	list_add(&fdlocks->llist, &cinode->llist);
 	up_write(&cinode->lock_sem);
 
@@ -457,7 +464,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
 	 * Delete any outstanding lock records. We'll lose them when the file
 	 * is closed anyway.
 	 */
-	down_write(&cifsi->lock_sem);
+	cifs_down_write(&cifsi->lock_sem);
 	list_for_each_entry_safe(li, tmp, &cifs_file->llist->locks, llist) {
 		list_del(&li->llist);
 		cifs_del_lock_waiters(li);
@@ -1011,7 +1018,7 @@ static void
 cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock)
 {
 	struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 	list_add_tail(&lock->llist, &cfile->llist->locks);
 	up_write(&cinode->lock_sem);
 }
@@ -1033,7 +1040,7 @@ cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock,
 
 try_again:
 	exist = false;
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 
 	exist = cifs_find_lock_conflict(cfile, lock->offset, lock->length,
 					lock->type, &conf_lock, CIFS_LOCK_OP);
@@ -1055,7 +1062,7 @@ try_again:
 					(lock->blist.next == &lock->blist));
 		if (!rc)
 			goto try_again;
-		down_write(&cinode->lock_sem);
+		cifs_down_write(&cinode->lock_sem);
 		list_del_init(&lock->blist);
 	}
 
@@ -1108,7 +1115,7 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock)
 		return rc;
 
 try_again:
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 	if (!cinode->can_cache_brlcks) {
 		up_write(&cinode->lock_sem);
 		return rc;
@@ -1314,7 +1321,7 @@ cifs_push_locks(struct cifsFileInfo *cfile)
 	int rc = 0;
 
 	/* we are going to update can_cache_brlcks here - need a write access */
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 	if (!cinode->can_cache_brlcks) {
 		up_write(&cinode->lock_sem);
 		return rc;
@@ -1505,7 +1512,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 	if (!buf)
 		return -ENOMEM;
 
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 	for (i = 0; i < 2; i++) {
 		cur = buf;
 		num = 0;
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 1add404618f0..2c809233084b 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -139,7 +139,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 
 	cur = buf;
 
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 	list_for_each_entry_safe(li, tmp, &cfile->llist->locks, llist) {
 		if (flock->fl_start > li->offset ||
 		    (flock->fl_start + length) <
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index b041f94678de..79d3dab45ceb 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -313,6 +313,29 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
 	return !!(gfp_flags & __GFP_DIRECT_RECLAIM);
 }
 
+/**
+ * gfpflags_normal_context - is gfp_flags a normal sleepable context?
+ * @gfp_flags: gfp_flags to test
+ *
+ * Test whether @gfp_flags indicates that the allocation is from the
+ * %current context and allowed to sleep.
+ *
+ * An allocation being allowed to block doesn't mean it owns the %current
+ * context.  When direct reclaim path tries to allocate memory, the
+ * allocation context is nested inside whatever %current was doing at the
+ * time of the original allocation.  The nested allocation may be allowed
+ * to block but modifying anything %current owns can corrupt the outer
+ * context's expectations.
+ *
+ * %true result from this function indicates that the allocation context
+ * can sleep and use anything that's associated with %current.
+ */
+static inline bool gfpflags_normal_context(const gfp_t gfp_flags)
+{
+	return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) ==
+		__GFP_DIRECT_RECLAIM;
+}
+
 #ifdef CONFIG_HIGHMEM
 #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM
 #else
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index fdb0cd0699b6..ec00d9264e5c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1228,7 +1228,8 @@ static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6
 	return skb->hash;
 }
 
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb);
+__u32 skb_get_hash_perturb(const struct sk_buff *skb,
+			   const siphash_key_t *perturb);
 
 static inline __u32 skb_get_hash_raw(const struct sk_buff *skb)
 {
@@ -1345,6 +1346,19 @@ static inline int skb_queue_empty(const struct sk_buff_head *list)
 	return list->next == (const struct sk_buff *) list;
 }
 
+/**
+ *	skb_queue_empty_lockless - check if a queue is empty
+ *	@list: queue head
+ *
+ *	Returns true if the queue is empty, false otherwise.
+ *	This variant can be used in lockless contexts.
+ */
+static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list)
+{
+	return READ_ONCE(list->next) == (const struct sk_buff *) list;
+}
+
+
 /**
  *	skb_queue_is_last - check if skb is the last entry in the queue
  *	@list: queue head
@@ -1709,9 +1723,11 @@ static inline void __skb_insert(struct sk_buff *newsk,
 				struct sk_buff *prev, struct sk_buff *next,
 				struct sk_buff_head *list)
 {
-	newsk->next = next;
-	newsk->prev = prev;
-	next->prev  = prev->next = newsk;
+	/* see skb_queue_empty_lockless() for the opposite READ_ONCE() */
+	WRITE_ONCE(newsk->next, next);
+	WRITE_ONCE(newsk->prev, prev);
+	WRITE_ONCE(next->prev, newsk);
+	WRITE_ONCE(prev->next, newsk);
 	list->qlen++;
 }
 
@@ -1722,11 +1738,11 @@ static inline void __skb_queue_splice(const struct sk_buff_head *list,
 	struct sk_buff *first = list->next;
 	struct sk_buff *last = list->prev;
 
-	first->prev = prev;
-	prev->next = first;
+	WRITE_ONCE(first->prev, prev);
+	WRITE_ONCE(prev->next, first);
 
-	last->next = next;
-	next->prev = last;
+	WRITE_ONCE(last->next, next);
+	WRITE_ONCE(next->prev, last);
 }
 
 /**
@@ -1867,8 +1883,8 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
 	next	   = skb->next;
 	prev	   = skb->prev;
 	skb->next  = skb->prev = NULL;
-	next->prev = prev;
-	prev->next = next;
+	WRITE_ONCE(next->prev, prev);
+	WRITE_ONCE(prev->next, next);
 }
 
 /**
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 71c72a939bf8..c86fcadccbd7 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -134,7 +134,7 @@ static inline void skb_mark_napi_id(struct sk_buff *skb,
 static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
-	sk->sk_napi_id = skb->napi_id;
+	WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
 #endif
 }
 
@@ -143,8 +143,8 @@ static inline void sk_mark_napi_id_once(struct sock *sk,
 					const struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
-	if (!sk->sk_napi_id)
-		sk->sk_napi_id = skb->napi_id;
+	if (!READ_ONCE(sk->sk_napi_id))
+		WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
 #endif
 }
 
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 22aba321282d..227dc0a84172 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 #include <linux/in6.h>
+#include <linux/siphash.h>
 #include <uapi/linux/if_ether.h>
 
 /**
@@ -229,7 +230,7 @@ struct flow_dissector {
 struct flow_keys {
 	struct flow_dissector_key_control control;
 #define FLOW_KEYS_HASH_START_FIELD basic
-	struct flow_dissector_key_basic basic;
+	struct flow_dissector_key_basic basic __aligned(SIPHASH_ALIGNMENT);
 	struct flow_dissector_key_tags tags;
 	struct flow_dissector_key_vlan vlan;
 	struct flow_dissector_key_keyid keyid;
diff --git a/include/net/fq.h b/include/net/fq.h
index 6d8521a30c5c..2c7687902789 100644
--- a/include/net/fq.h
+++ b/include/net/fq.h
@@ -70,7 +70,7 @@ struct fq {
 	struct list_head backlogs;
 	spinlock_t lock;
 	u32 flows_cnt;
-	u32 perturbation;
+	siphash_key_t	perturbation;
 	u32 limit;
 	u32 memory_limit;
 	u32 memory_usage;
diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h
index ac1a2317941e..46903e23eab9 100644
--- a/include/net/fq_impl.h
+++ b/include/net/fq_impl.h
@@ -105,7 +105,7 @@ static struct fq_flow *fq_flow_classify(struct fq *fq,
 
 	lockdep_assert_held(&fq->lock);
 
-	hash = skb_get_hash_perturb(skb, fq->perturbation);
+	hash = skb_get_hash_perturb(skb, &fq->perturbation);
 	idx = reciprocal_scale(hash, fq->flows_cnt);
 	flow = &fq->flows[idx];
 
@@ -255,7 +255,7 @@ static int fq_init(struct fq *fq, int flows_cnt)
 	INIT_LIST_HEAD(&fq->backlogs);
 	spin_lock_init(&fq->lock);
 	fq->flows_cnt = max_t(u32, flows_cnt, 1);
-	fq->perturbation = prandom_u32();
+	get_random_bytes(&fq->perturbation, sizeof(fq->perturbation));
 	fq->quantum = 300;
 	fq->limit = 8192;
 	fq->memory_limit = 16 << 20; /* 16 MBytes */
diff --git a/include/net/sock.h b/include/net/sock.h
index 60eef7f1ac05..7ec4d0bd8d12 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -916,8 +916,8 @@ static inline void sk_incoming_cpu_update(struct sock *sk)
 {
 	int cpu = raw_smp_processor_id();
 
-	if (unlikely(sk->sk_incoming_cpu != cpu))
-		sk->sk_incoming_cpu = cpu;
+	if (unlikely(READ_ONCE(sk->sk_incoming_cpu) != cpu))
+		WRITE_ONCE(sk->sk_incoming_cpu, cpu);
 }
 
 static inline void sock_rps_record_flow_hash(__u32 hash)
@@ -2131,12 +2131,17 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
  * sk_page_frag - return an appropriate page_frag
  * @sk: socket
  *
- * If socket allocation mode allows current thread to sleep, it means its
- * safe to use the per task page_frag instead of the per socket one.
+ * Use the per task page_frag instead of the per socket one for
+ * optimization when we know that we're in the normal context and owns
+ * everything that's associated with %current.
+ *
+ * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest
+ * inside other socket operations and end up recursing into sk_page_frag()
+ * while it's already in use.
  */
 static inline struct page_frag *sk_page_frag(struct sock *sk)
 {
-	if (gfpflags_allow_blocking(sk->sk_allocation))
+	if (gfpflags_normal_context(sk->sk_allocation))
 		return &current->task_frag;
 
 	return &sk->sk_frag;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 32ba789c544c..bbf8b32fc69e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -432,10 +432,11 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 	 * its already queued (either by us or someone else) and will get the
 	 * wakeup due to that.
 	 *
-	 * This cmpxchg() implies a full barrier, which pairs with the write
-	 * barrier implied by the wakeup in wake_up_q().
+	 * In order to ensure that a pending wakeup will observe our pending
+	 * state, even in the failed case, an explicit smp_mb() must be used.
 	 */
-	if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
+	smp_mb__before_atomic();
+	if (cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL))
 		return;
 
 	get_task_struct(task);
diff --git a/net/atm/common.c b/net/atm/common.c
index 9e812c782a37..0fd2d26d4c6e 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -667,7 +667,7 @@ unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
 		mask |= POLLHUP;
 
 	/* readable? */
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= POLLIN | POLLRDNORM;
 
 	/* writable? */
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index b216e697deac..b48d54783e5d 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -460,7 +460,7 @@ unsigned int bt_sock_poll(struct file *file, struct socket *sock,
 	if (sk->sk_state == BT_LISTEN)
 		return bt_accept_poll(sk);
 
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= POLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
 
@@ -470,7 +470,7 @@ unsigned int bt_sock_poll(struct file *file, struct socket *sock,
 	if (sk->sk_shutdown == SHUTDOWN_MASK)
 		mask |= POLLHUP;
 
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= POLLIN | POLLRDNORM;
 
 	if (sk->sk_state == BT_CLOSED)
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 632d5a416d97..df936d2f58bd 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -953,7 +953,7 @@ static unsigned int caif_poll(struct file *file,
 		mask |= POLLRDHUP;
 
 	/* readable? */
-	if (!skb_queue_empty(&sk->sk_receive_queue) ||
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue) ||
 		(sk->sk_shutdown & RCV_SHUTDOWN))
 		mask |= POLLIN | POLLRDNORM;
 
diff --git a/net/core/datagram.c b/net/core/datagram.c
index dcb333e95702..85fcca395fad 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -97,7 +97,7 @@ int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
 	if (error)
 		goto out_err;
 
-	if (sk->sk_receive_queue.prev != skb)
+	if (READ_ONCE(sk->sk_receive_queue.prev) != skb)
 		goto out;
 
 	/* Socket shut down? */
@@ -281,7 +281,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 			break;
 
 		sk_busy_loop(sk, flags & MSG_DONTWAIT);
-	} while (sk->sk_receive_queue.prev != *last);
+	} while (READ_ONCE(sk->sk_receive_queue.prev) != *last);
 
 	error = -EAGAIN;
 
@@ -844,7 +844,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
 	mask = 0;
 
 	/* exceptional events? */
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= POLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
 
@@ -854,7 +854,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
 		mask |= POLLHUP;
 
 	/* readable? */
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= POLLIN | POLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 97569d3e1937..7822defa5a5d 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1450,11 +1450,13 @@ static int ethtool_reset(struct net_device *dev, char __user *useraddr)
 
 static int ethtool_get_wol(struct net_device *dev, char __user *useraddr)
 {
-	struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
+	struct ethtool_wolinfo wol;
 
 	if (!dev->ethtool_ops->get_wol)
 		return -EOPNOTSUPP;
 
+	memset(&wol, 0, sizeof(struct ethtool_wolinfo));
+	wol.cmd = ETHTOOL_GWOL;
 	dev->ethtool_ops->get_wol(dev, &wol);
 
 	if (copy_to_user(useraddr, &wol, sizeof(wol)))
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index e2e716003ede..7be5c20a93a5 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -889,45 +889,34 @@ out_bad:
 }
 EXPORT_SYMBOL(__skb_flow_dissect);
 
-static u32 hashrnd __read_mostly;
+static siphash_key_t hashrnd __read_mostly;
 static __always_inline void __flow_hash_secret_init(void)
 {
 	net_get_random_once(&hashrnd, sizeof(hashrnd));
 }
 
-static __always_inline u32 __flow_hash_words(const u32 *words, u32 length,
-					     u32 keyval)
+static const void *flow_keys_hash_start(const struct flow_keys *flow)
 {
-	return jhash2(words, length, keyval);
-}
-
-static inline const u32 *flow_keys_hash_start(const struct flow_keys *flow)
-{
-	const void *p = flow;
-
-	BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32));
-	return (const u32 *)(p + FLOW_KEYS_HASH_OFFSET);
+	BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % SIPHASH_ALIGNMENT);
+	return &flow->FLOW_KEYS_HASH_START_FIELD;
 }
 
 static inline size_t flow_keys_hash_length(const struct flow_keys *flow)
 {
-	size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs);
-	BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32));
-	BUILD_BUG_ON(offsetof(typeof(*flow), addrs) !=
-		     sizeof(*flow) - sizeof(flow->addrs));
+	size_t len = offsetof(typeof(*flow), addrs) - FLOW_KEYS_HASH_OFFSET;
 
 	switch (flow->control.addr_type) {
 	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
-		diff -= sizeof(flow->addrs.v4addrs);
+		len += sizeof(flow->addrs.v4addrs);
 		break;
 	case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
-		diff -= sizeof(flow->addrs.v6addrs);
+		len += sizeof(flow->addrs.v6addrs);
 		break;
 	case FLOW_DISSECTOR_KEY_TIPC_ADDRS:
-		diff -= sizeof(flow->addrs.tipcaddrs);
+		len += sizeof(flow->addrs.tipcaddrs);
 		break;
 	}
-	return (sizeof(*flow) - diff) / sizeof(u32);
+	return len;
 }
 
 __be32 flow_get_u32_src(const struct flow_keys *flow)
@@ -993,14 +982,15 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys)
 	}
 }
 
-static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
+static inline u32 __flow_hash_from_keys(struct flow_keys *keys,
+					const siphash_key_t *keyval)
 {
 	u32 hash;
 
 	__flow_hash_consistentify(keys);
 
-	hash = __flow_hash_words(flow_keys_hash_start(keys),
-				 flow_keys_hash_length(keys), keyval);
+	hash = siphash(flow_keys_hash_start(keys),
+		       flow_keys_hash_length(keys), keyval);
 	if (!hash)
 		hash = 1;
 
@@ -1010,12 +1000,13 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
 u32 flow_hash_from_keys(struct flow_keys *keys)
 {
 	__flow_hash_secret_init();
-	return __flow_hash_from_keys(keys, hashrnd);
+	return __flow_hash_from_keys(keys, &hashrnd);
 }
 EXPORT_SYMBOL(flow_hash_from_keys);
 
 static inline u32 ___skb_get_hash(const struct sk_buff *skb,
-				  struct flow_keys *keys, u32 keyval)
+				  struct flow_keys *keys,
+				  const siphash_key_t *keyval)
 {
 	skb_flow_dissect_flow_keys(skb, keys,
 				   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
@@ -1063,7 +1054,7 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb)
 			   NULL, 0, 0, 0,
 			   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
 
-	return __flow_hash_from_keys(&keys, hashrnd);
+	return __flow_hash_from_keys(&keys, &hashrnd);
 }
 EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric);
 
@@ -1083,13 +1074,14 @@ void __skb_get_hash(struct sk_buff *skb)
 
 	__flow_hash_secret_init();
 
-	hash = ___skb_get_hash(skb, &keys, hashrnd);
+	hash = ___skb_get_hash(skb, &keys, &hashrnd);
 
 	__skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys));
 }
 EXPORT_SYMBOL(__skb_get_hash);
 
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb)
+__u32 skb_get_hash_perturb(const struct sk_buff *skb,
+			   const siphash_key_t *perturb)
 {
 	struct flow_keys keys;
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 5f466db916ee..7ccbcd853cbc 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1039,7 +1039,7 @@ set_rcvbuf:
 		break;
 
 	case SO_INCOMING_CPU:
-		sk->sk_incoming_cpu = val;
+		WRITE_ONCE(sk->sk_incoming_cpu, val);
 		break;
 
 	case SO_CNX_ADVICE:
@@ -1351,7 +1351,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case SO_INCOMING_CPU:
-		v.val = sk->sk_incoming_cpu;
+		v.val = READ_ONCE(sk->sk_incoming_cpu);
 		break;
 
 	case SO_MEMINFO:
@@ -3381,7 +3381,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time)
 {
 	struct sock *sk = p;
 
-	return !skb_queue_empty(&sk->sk_receive_queue) ||
+	return !skb_queue_empty_lockless(&sk->sk_receive_queue) ||
 	       sk_busy_loop_timeout(sk, start_time);
 }
 EXPORT_SYMBOL(sk_busy_loop_end);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 8e08cea6f178..176bddacc16e 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -121,7 +121,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 						    inet->inet_daddr,
 						    inet->inet_sport,
 						    inet->inet_dport);
-	inet->inet_id = dp->dccps_iss ^ jiffies;
+	inet->inet_id = prandom_u32();
 
 	err = dccp_connect(sk);
 	rt = NULL;
@@ -417,7 +417,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
 	RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt));
 	newinet->mc_index  = inet_iif(skb);
 	newinet->mc_ttl	   = ip_hdr(skb)->ttl;
-	newinet->inet_id   = jiffies;
+	newinet->inet_id   = prandom_u32();
 
 	if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL)
 		goto put_and_exit;
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 045d8a176279..0796355e74c1 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -62,7 +62,7 @@ static struct dsa_switch_tree *dsa_add_dst(u32 tree)
 		return NULL;
 	dst->tree = tree;
 	INIT_LIST_HEAD(&dst->list);
-	list_add_tail(&dsa_switch_trees, &dst->list);
+	list_add_tail(&dst->list, &dsa_switch_trees);
 	kref_init(&dst->refcount);
 
 	return dst;
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index f915abff1350..d3eddfd13875 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -75,7 +75,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 	inet->inet_dport = usin->sin_port;
 	sk->sk_state = TCP_ESTABLISHED;
 	sk_set_txhash(sk);
-	inet->inet_id = jiffies;
+	inet->inet_id = prandom_u32();
 
 	sk_dst_set(sk, &rt->dst);
 	err = 0;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 24b066c32e06..1f26627c7fad 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -193,7 +193,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
 			if (sk->sk_bound_dev_if)
 				score += 4;
 		}
-		if (sk->sk_incoming_cpu == raw_smp_processor_id())
+		if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
 			score++;
 	}
 	return score;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 347be2ea78d4..71ff2531d973 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -592,6 +592,9 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
 		truncate = true;
 	}
 
+	if (tun_info->options_len < sizeof(*md))
+		goto err_free_rt;
+
 	md = ip_tunnel_info_opts(tun_info);
 	if (!md)
 		goto err_free_rt;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c1f59a53f68f..8f07655718f3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -574,7 +574,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	}
 	/* This barrier is coupled with smp_wmb() in tcp_reset() */
 	smp_rmb();
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= POLLERR;
 
 	return mask;
@@ -1787,7 +1787,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
 
-	if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) &&
+	if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) &&
 	    (sk->sk_state == TCP_ESTABLISHED))
 		sk_busy_loop(sk, nonblock);
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 0569718e3656..44a41ac2b0ca 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -245,7 +245,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 						 inet->inet_daddr);
 	}
 
-	inet->inet_id = tp->write_seq ^ jiffies;
+	inet->inet_id = prandom_u32();
 
 	if (tcp_fastopen_defer_connect(sk, &err))
 		return err;
@@ -1368,7 +1368,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
 	if (inet_opt)
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
-	newinet->inet_id = newtp->write_seq ^ jiffies;
+	newinet->inet_id = prandom_u32();
 
 	if (!dst) {
 		dst = inet_csk_route_child_sock(sk, newsk, req);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 54343dc29cb4..ab3f272a0884 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -419,7 +419,7 @@ static int compute_score(struct sock *sk, struct net *net,
 			score += 4;
 	}
 
-	if (sk->sk_incoming_cpu == raw_smp_processor_id())
+	if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
 		score++;
 	return score;
 }
@@ -1195,6 +1195,20 @@ static void udp_set_dev_scratch(struct sk_buff *skb)
 		scratch->_tsize_state |= UDP_SKB_IS_STATELESS;
 }
 
+static void udp_skb_csum_unnecessary_set(struct sk_buff *skb)
+{
+	/* We come here after udp_lib_checksum_complete() returned 0.
+	 * This means that __skb_checksum_complete() might have
+	 * set skb->csum_valid to 1.
+	 * On 64bit platforms, we can set csum_unnecessary
+	 * to true, but only if the skb is not shared.
+	 */
+#if BITS_PER_LONG == 64
+	if (!skb_shared(skb))
+		udp_skb_scratch(skb)->csum_unnecessary = true;
+#endif
+}
+
 static int udp_skb_truesize(struct sk_buff *skb)
 {
 	return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS;
@@ -1430,10 +1444,7 @@ static struct sk_buff *__first_packet_length(struct sock *sk,
 			*total += skb->truesize;
 			kfree_skb(skb);
 		} else {
-			/* the csum related bits could be changed, refresh
-			 * the scratch area
-			 */
-			udp_set_dev_scratch(skb);
+			udp_skb_csum_unnecessary_set(skb);
 			break;
 		}
 	}
@@ -1457,7 +1468,7 @@ static int first_packet_length(struct sock *sk)
 
 	spin_lock_bh(&rcvq->lock);
 	skb = __first_packet_length(sk, rcvq, &total);
-	if (!skb && !skb_queue_empty(sk_queue)) {
+	if (!skb && !skb_queue_empty_lockless(sk_queue)) {
 		spin_lock(&sk_queue->lock);
 		skb_queue_splice_tail_init(sk_queue, rcvq);
 		spin_unlock(&sk_queue->lock);
@@ -1532,7 +1543,7 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
 				return skb;
 			}
 
-			if (skb_queue_empty(sk_queue)) {
+			if (skb_queue_empty_lockless(sk_queue)) {
 				spin_unlock_bh(&queue->lock);
 				goto busy_check;
 			}
@@ -1559,7 +1570,7 @@ busy_check:
 				break;
 
 			sk_busy_loop(sk, flags & MSG_DONTWAIT);
-		} while (!skb_queue_empty(sk_queue));
+		} while (!skb_queue_empty_lockless(sk_queue));
 
 		/* sk_queue is empty, reader_queue may contain peeked packets */
 	} while (timeo &&
@@ -2539,7 +2550,7 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	unsigned int mask = datagram_poll(file, sock, wait);
 	struct sock *sk = sock->sk;
 
-	if (!skb_queue_empty(&udp_sk(sk)->reader_queue))
+	if (!skb_queue_empty_lockless(&udp_sk(sk)->reader_queue))
 		mask |= POLLIN | POLLRDNORM;
 
 	sock_rps_record_flow(sk);
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 6dc93ac28261..228983a5531b 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -118,7 +118,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
 			if (sk->sk_bound_dev_if)
 				score++;
 		}
-		if (sk->sk_incoming_cpu == raw_smp_processor_id())
+		if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
 			score++;
 	}
 	return score;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 9f7bfeb90fb0..a2ba7356fa65 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -170,7 +170,7 @@ static int compute_score(struct sock *sk, struct net *net,
 			score++;
 	}
 
-	if (sk->sk_incoming_cpu == raw_smp_processor_id())
+	if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
 		score++;
 
 	return score;
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index a51bfba19b9e..694a43c05eb9 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -567,11 +567,11 @@ static unsigned int llcp_sock_poll(struct file *file, struct socket *sock,
 	if (sk->sk_state == LLCP_LISTEN)
 		return llcp_accept_poll(sk);
 
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= POLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
 
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= POLLIN | POLLRDNORM;
 
 	if (sk->sk_state == LLCP_CLOSED)
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index 1b050dd17393..a1df36f3bb6e 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -352,9 +352,9 @@ static unsigned int pn_socket_poll(struct file *file, struct socket *sock,
 
 	if (sk->sk_state == TCP_CLOSE)
 		return POLLERR;
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= POLLIN | POLLRDNORM;
-	if (!skb_queue_empty(&pn->ctrlreq_queue))
+	if (!skb_queue_empty_lockless(&pn->ctrlreq_queue))
 		mask |= POLLPRI;
 	if (!mask && sk->sk_state == TCP_CLOSE_WAIT)
 		return POLLHUP;
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index fa256f8038af..c73475c3a464 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -4,11 +4,11 @@
  * Copyright (C) 2013 Nandita Dukkipati <nanditad@google.com>
  */
 
-#include <linux/jhash.h>
 #include <linux/jiffies.h>
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/vmalloc.h>
+#include <linux/siphash.h>
 #include <net/pkt_sched.h>
 #include <net/sock.h>
 
@@ -125,7 +125,7 @@ struct wdrr_bucket {
 
 struct hhf_sched_data {
 	struct wdrr_bucket buckets[WDRR_BUCKET_CNT];
-	u32		   perturbation;   /* hash perturbation */
+	siphash_key_t	   perturbation;   /* hash perturbation */
 	u32		   quantum;        /* psched_mtu(qdisc_dev(sch)); */
 	u32		   drop_overlimit; /* number of times max qdisc packet
 					    * limit was hit
@@ -263,7 +263,7 @@ static enum wdrr_bucket_idx hhf_classify(struct sk_buff *skb, struct Qdisc *sch)
 	}
 
 	/* Get hashed flow-id of the skb. */
-	hash = skb_get_hash_perturb(skb, q->perturbation);
+	hash = skb_get_hash_perturb(skb, &q->perturbation);
 
 	/* Check if this packet belongs to an already established HH flow. */
 	flow_pos = hash & HHF_BIT_MASK;
@@ -578,7 +578,7 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt)
 
 	sch->limit = 1000;
 	q->quantum = psched_mtu(qdisc_dev(sch));
-	q->perturbation = prandom_u32();
+	get_random_bytes(&q->perturbation, sizeof(q->perturbation));
 	INIT_LIST_HEAD(&q->new_buckets);
 	INIT_LIST_HEAD(&q->old_buckets);
 
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index cc39e170b4aa..04f15e0aeaa8 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -22,7 +22,7 @@
 #include <linux/errno.h>
 #include <linux/skbuff.h>
 #include <linux/random.h>
-#include <linux/jhash.h>
+#include <linux/siphash.h>
 #include <net/ip.h>
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
@@ -49,7 +49,7 @@ struct sfb_bucket {
  * (Section 4.4 of SFB reference : moving hash functions)
  */
 struct sfb_bins {
-	u32		  perturbation; /* jhash perturbation */
+	siphash_key_t	  perturbation; /* siphash key */
 	struct sfb_bucket bins[SFB_LEVELS][SFB_NUMBUCKETS];
 };
 
@@ -221,7 +221,8 @@ static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_da
 
 static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q)
 {
-	q->bins[slot].perturbation = prandom_u32();
+	get_random_bytes(&q->bins[slot].perturbation,
+			 sizeof(q->bins[slot].perturbation));
 }
 
 static void sfb_swap_slot(struct sfb_sched_data *q)
@@ -317,9 +318,9 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		/* If using external classifiers, get result and record it. */
 		if (!sfb_classify(skb, fl, &ret, &salt))
 			goto other_drop;
-		sfbhash = jhash_1word(salt, q->bins[slot].perturbation);
+		sfbhash = siphash_1u32(salt, &q->bins[slot].perturbation);
 	} else {
-		sfbhash = skb_get_hash_perturb(skb, q->bins[slot].perturbation);
+		sfbhash = skb_get_hash_perturb(skb, &q->bins[slot].perturbation);
 	}
 
 
@@ -355,7 +356,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		/* Inelastic flow */
 		if (q->double_buffering) {
 			sfbhash = skb_get_hash_perturb(skb,
-			    q->bins[slot].perturbation);
+			    &q->bins[slot].perturbation);
 			if (!sfbhash)
 				sfbhash = 1;
 			sfb_skb_cb(skb)->hashes[slot] = sfbhash;
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 3fbf20126045..cbc54ddfe076 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -18,7 +18,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/skbuff.h>
-#include <linux/jhash.h>
+#include <linux/siphash.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <net/netlink.h>
@@ -121,7 +121,7 @@ struct sfq_sched_data {
 	u8		headdrop;
 	u8		maxdepth;	/* limit of packets per flow */
 
-	u32		perturbation;
+	siphash_key_t 	perturbation;
 	u8		cur_depth;	/* depth of longest slot */
 	u8		flags;
 	unsigned short  scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */
@@ -160,7 +160,7 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index
 static unsigned int sfq_hash(const struct sfq_sched_data *q,
 			     const struct sk_buff *skb)
 {
-	return skb_get_hash_perturb(skb, q->perturbation) & (q->divisor - 1);
+	return skb_get_hash_perturb(skb, &q->perturbation) & (q->divisor - 1);
 }
 
 static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
@@ -609,9 +609,11 @@ static void sfq_perturbation(unsigned long arg)
 	struct Qdisc *sch = (struct Qdisc *)arg;
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
+	siphash_key_t nkey;
 
+	get_random_bytes(&nkey, sizeof(nkey));
 	spin_lock(root_lock);
-	q->perturbation = prandom_u32();
+	q->perturbation = nkey;
 	if (!q->filter_list && q->tail)
 		sfq_rehash(sch);
 	spin_unlock(root_lock);
@@ -690,7 +692,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	del_timer(&q->perturb_timer);
 	if (q->perturb_period) {
 		mod_timer(&q->perturb_timer, jiffies + q->perturb_period);
-		q->perturbation = prandom_u32();
+		get_random_bytes(&q->perturbation, sizeof(q->perturbation));
 	}
 	sch_tree_unlock(sch);
 	kfree(p);
@@ -746,7 +748,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
 	q->quantum = psched_mtu(qdisc_dev(sch));
 	q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
 	q->perturb_period = 0;
-	q->perturbation = prandom_u32();
+	get_random_bytes(&q->perturbation, sizeof(q->perturbation));
 
 	if (opt) {
 		int err = sfq_change(sch, opt);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 4045d203b7d4..09cda66d0567 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7371,7 +7371,7 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	mask = 0;
 
 	/* Is there any exceptional events?  */
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= POLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
@@ -7380,7 +7380,7 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		mask |= POLLHUP;
 
 	/* Is it readable?  Reconsider this code with TCP-style support.  */
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= POLLIN | POLLRDNORM;
 
 	/* The association is either gone or not ready.  */
@@ -7716,7 +7716,7 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags,
 		if (sk_can_busy_loop(sk)) {
 			sk_busy_loop(sk, noblock);
 
-			if (!skb_queue_empty(&sk->sk_receive_queue))
+			if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 				continue;
 		}
 
@@ -8136,7 +8136,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newinet->inet_rcv_saddr = inet->inet_rcv_saddr;
 	newinet->inet_dport = htons(asoc->peer.port);
 	newinet->pmtudisc = inet->pmtudisc;
-	newinet->inet_id = asoc->next_tsn ^ jiffies;
+	newinet->inet_id = prandom_u32();
 
 	newinet->uc_ttl = inet->uc_ttl;
 	newinet->mc_loop = 1;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index f13fb607c563..21929ba196eb 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -714,14 +714,14 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
 		/* fall thru' */
 	case TIPC_LISTEN:
 	case TIPC_CONNECTING:
-		if (!skb_queue_empty(&sk->sk_receive_queue))
+		if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 			mask |= (POLLIN | POLLRDNORM);
 		break;
 	case TIPC_OPEN:
 		if (!tsk->cong_link_cnt)
 			mask |= POLLOUT;
 		if (tipc_sk_type_connectionless(sk) &&
-		    (!skb_queue_empty(&sk->sk_receive_queue)))
+		    (!skb_queue_empty_lockless(&sk->sk_receive_queue)))
 			mask |= (POLLIN | POLLRDNORM);
 		break;
 	case TIPC_DISCONNECTING:
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 2adfcc6dec5a..4de9dfd14d09 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2665,7 +2665,7 @@ static unsigned int unix_poll(struct file *file, struct socket *sock, poll_table
 		mask |= POLLRDHUP | POLLIN | POLLRDNORM;
 
 	/* readable? */
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= POLLIN | POLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */
@@ -2693,7 +2693,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
 	mask = 0;
 
 	/* exceptional events? */
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= POLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
 
@@ -2703,7 +2703,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
 		mask |= POLLHUP;
 
 	/* readable? */
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= POLLIN | POLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 148c949cdfe7..1939b77e98b7 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -880,7 +880,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
 		 * the queue and write as long as the socket isn't shutdown for
 		 * sending.
 		 */
-		if (!skb_queue_empty(&sk->sk_receive_queue) ||
+		if (!skb_queue_empty_lockless(&sk->sk_receive_queue) ||
 		    (sk->sk_shutdown & RCV_SHUTDOWN)) {
 			mask |= POLLIN | POLLRDNORM;
 		}
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index d632a0511d62..158ce68bc9bf 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1169,8 +1169,7 @@ static unsigned int wmfw_convert_flags(unsigned int in, unsigned int len)
 	}
 
 	if (in) {
-		if (in & WMFW_CTL_FLAG_READABLE)
-			out |= rd;
+		out |= rd;
 		if (in & WMFW_CTL_FLAG_WRITEABLE)
 			out |= wr;
 		if (in & WMFW_CTL_FLAG_VOLATILE)
diff --git a/sound/soc/rockchip/rockchip_i2s.c b/sound/soc/rockchip/rockchip_i2s.c
index 66fc13a2396a..0e07e3dea7de 100644
--- a/sound/soc/rockchip/rockchip_i2s.c
+++ b/sound/soc/rockchip/rockchip_i2s.c
@@ -676,7 +676,7 @@ static int rockchip_i2s_probe(struct platform_device *pdev)
 	ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
 	if (ret) {
 		dev_err(&pdev->dev, "Could not register PCM\n");
-		return ret;
+		goto err_suspend;
 	}
 
 	return 0;
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 32e64a8a6443..bec7a2f1fb4d 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2454,6 +2454,7 @@ static int build_cl_output(char *cl_sort, bool no_source)
 	bool add_sym   = false;
 	bool add_dso   = false;
 	bool add_src   = false;
+	int ret = 0;
 
 	if (!buf)
 		return -ENOMEM;
@@ -2472,7 +2473,8 @@ static int build_cl_output(char *cl_sort, bool no_source)
 			add_dso = true;
 		} else if (strcmp(tok, "offset")) {
 			pr_err("unrecognized sort token: %s\n", tok);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err;
 		}
 	}
 
@@ -2495,13 +2497,15 @@ static int build_cl_output(char *cl_sort, bool no_source)
 		add_sym ? "symbol," : "",
 		add_dso ? "dso," : "",
 		add_src ? "cl_srcline," : "",
-		"node") < 0)
-		return -ENOMEM;
+		"node") < 0) {
+		ret = -ENOMEM;
+		goto err;
+	}
 
 	c2c.show_src = add_src;
-
+err:
 	free(buf);
-	return 0;
+	return ret;
 }
 
 static int setup_coalesce(const char *coalesce, bool no_source)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 9e693ce4b73b..ce786f363476 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -687,6 +687,7 @@ static char *compact_gfp_flags(char *gfp_flags)
 			new = realloc(new_flags, len + strlen(cpt) + 2);
 			if (new == NULL) {
 				free(new_flags);
+				free(orig_flags);
 				return NULL;
 			}
 
diff --git a/tools/testing/selftests/net/reuseport_dualstack.c b/tools/testing/selftests/net/reuseport_dualstack.c
index fe3230c55986..fb7a59ed759e 100644
--- a/tools/testing/selftests/net/reuseport_dualstack.c
+++ b/tools/testing/selftests/net/reuseport_dualstack.c
@@ -129,7 +129,7 @@ static void test(int *rcv_fds, int count, int proto)
 {
 	struct epoll_event ev;
 	int epfd, i, test_fd;
-	uint16_t test_family;
+	int test_family;
 	socklen_t len;
 
 	epfd = epoll_create(1);
@@ -146,6 +146,7 @@ static void test(int *rcv_fds, int count, int proto)
 	send_from_v4(proto);
 
 	test_fd = receive_once(epfd, proto);
+	len = sizeof(test_family);
 	if (getsockopt(test_fd, SOL_SOCKET, SO_DOMAIN, &test_family, &len))
 		error(1, errno, "failed to read socket domain");
 	if (test_family != AF_INET)
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index bf315bcbe663..fae8c52cf8f0 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -3,6 +3,7 @@ noarg:
 	$(MAKE) -C ../
 
 TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao
+TEST_GEN_PROGS_EXTENDED := tlbie_test
 TEST_GEN_FILES := tempfile
 
 include ../../lib.mk
@@ -14,3 +15,4 @@ $(OUTPUT)/prot_sao: ../utils.c
 $(OUTPUT)/tempfile:
 	dd if=/dev/zero of=$@ bs=64k count=1
 
+$(OUTPUT)/tlbie_test: LDLIBS += -lpthread
diff --git a/tools/testing/selftests/powerpc/mm/tlbie_test.c b/tools/testing/selftests/powerpc/mm/tlbie_test.c
new file mode 100644
index 000000000000..f85a0938ab25
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/tlbie_test.c
@@ -0,0 +1,734 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2019, Nick Piggin, Gautham R. Shenoy, Aneesh Kumar K.V, IBM Corp.
+ */
+
+/*
+ *
+ * Test tlbie/mtpidr race. We have 4 threads doing flush/load/compare/store
+ * sequence in a loop. The same threads also rung a context switch task
+ * that does sched_yield() in loop.
+ *
+ * The snapshot thread mark the mmap area PROT_READ in between, make a copy
+ * and copy it back to the original area. This helps us to detect if any
+ * store continued to happen after we marked the memory PROT_READ.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/ipc.h>
+#include <sys/shm.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <linux/futex.h>
+#include <unistd.h>
+#include <asm/unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <time.h>
+#include <stdarg.h>
+#include <sched.h>
+#include <pthread.h>
+#include <signal.h>
+#include <sys/prctl.h>
+
+static inline void dcbf(volatile unsigned int *addr)
+{
+	__asm__ __volatile__ ("dcbf %y0; sync" : : "Z"(*(unsigned char *)addr) : "memory");
+}
+
+static void err_msg(char *msg)
+{
+
+	time_t now;
+	time(&now);
+	printf("=================================\n");
+	printf("    Error: %s\n", msg);
+	printf("    %s", ctime(&now));
+	printf("=================================\n");
+	exit(1);
+}
+
+static char *map1;
+static char *map2;
+static pid_t rim_process_pid;
+
+/*
+ * A "rim-sequence" is defined to be the sequence of the following
+ * operations performed on a memory word:
+ *	1) FLUSH the contents of that word.
+ *	2) LOAD the contents of that word.
+ *	3) COMPARE the contents of that word with the content that was
+ *	           previously stored at that word
+ *	4) STORE new content into that word.
+ *
+ * The threads in this test that perform the rim-sequence are termed
+ * as rim_threads.
+ */
+
+/*
+ * A "corruption" is defined to be the failed COMPARE operation in a
+ * rim-sequence.
+ *
+ * A rim_thread that detects a corruption informs about it to all the
+ * other rim_threads, and the mem_snapshot thread.
+ */
+static volatile unsigned int corruption_found;
+
+/*
+ * This defines the maximum number of rim_threads in this test.
+ *
+ * The THREAD_ID_BITS denote the number of bits required
+ * to represent the thread_ids [0..MAX_THREADS - 1].
+ * We are being a bit paranoid here and set it to 8 bits,
+ * though 6 bits suffice.
+ *
+ */
+#define MAX_THREADS 		64
+#define THREAD_ID_BITS		8
+#define THREAD_ID_MASK		((1 << THREAD_ID_BITS) - 1)
+static unsigned int rim_thread_ids[MAX_THREADS];
+static pthread_t rim_threads[MAX_THREADS];
+
+
+/*
+ * Each rim_thread works on an exclusive "chunk" of size
+ * RIM_CHUNK_SIZE.
+ *
+ * The ith rim_thread works on the ith chunk.
+ *
+ * The ith chunk begins at
+ * map1 + (i * RIM_CHUNK_SIZE)
+ */
+#define RIM_CHUNK_SIZE  	1024
+#define BITS_PER_BYTE 		8
+#define WORD_SIZE     		(sizeof(unsigned int))
+#define WORD_BITS		(WORD_SIZE * BITS_PER_BYTE)
+#define WORDS_PER_CHUNK		(RIM_CHUNK_SIZE/WORD_SIZE)
+
+static inline char *compute_chunk_start_addr(unsigned int thread_id)
+{
+	char *chunk_start;
+
+	chunk_start = (char *)((unsigned long)map1 +
+			       (thread_id * RIM_CHUNK_SIZE));
+
+	return chunk_start;
+}
+
+/*
+ * The "word-offset" of a word-aligned address inside a chunk, is
+ * defined to be the number of words that precede the address in that
+ * chunk.
+ *
+ * WORD_OFFSET_BITS denote the number of bits required to represent
+ * the word-offsets of all the word-aligned addresses of a chunk.
+ */
+#define WORD_OFFSET_BITS	(__builtin_ctz(WORDS_PER_CHUNK))
+#define WORD_OFFSET_MASK	((1 << WORD_OFFSET_BITS) - 1)
+
+static inline unsigned int compute_word_offset(char *start, unsigned int *addr)
+{
+	unsigned int delta_bytes, ret;
+	delta_bytes = (unsigned long)addr - (unsigned long)start;
+
+	ret = delta_bytes/WORD_SIZE;
+
+	return ret;
+}
+
+/*
+ * A "sweep" is defined to be the sequential execution of the
+ * rim-sequence by a rim_thread on its chunk one word at a time,
+ * starting from the first word of its chunk and ending with the last
+ * word of its chunk.
+ *
+ * Each sweep of a rim_thread is uniquely identified by a sweep_id.
+ * SWEEP_ID_BITS denote the number of bits required to represent
+ * the sweep_ids of rim_threads.
+ *
+ * As to why SWEEP_ID_BITS are computed as a function of THREAD_ID_BITS,
+ * WORD_OFFSET_BITS, and WORD_BITS, see the "store-pattern" below.
+ */
+#define SWEEP_ID_BITS		(WORD_BITS - (THREAD_ID_BITS + WORD_OFFSET_BITS))
+#define SWEEP_ID_MASK		((1 << SWEEP_ID_BITS) - 1)
+
+/*
+ * A "store-pattern" is the word-pattern that is stored into a word
+ * location in the 4)STORE step of the rim-sequence.
+ *
+ * In the store-pattern, we shall encode:
+ *
+ *      - The thread-id of the rim_thread performing the store
+ *        (The most significant THREAD_ID_BITS)
+ *
+ *      - The word-offset of the address into which the store is being
+ *        performed (The next WORD_OFFSET_BITS)
+ *
+ *      - The sweep_id of the current sweep in which the store is
+ *        being performed. (The lower SWEEP_ID_BITS)
+ *
+ * Store Pattern: 32 bits
+ * |------------------|--------------------|---------------------------------|
+ * |    Thread id     |  Word offset       |         sweep_id                |
+ * |------------------|--------------------|---------------------------------|
+ *    THREAD_ID_BITS     WORD_OFFSET_BITS          SWEEP_ID_BITS
+ *
+ * In the store pattern, the (Thread-id + Word-offset) uniquely identify the
+ * address to which the store is being performed i.e,
+ *    address == map1 +
+ *              (Thread-id * RIM_CHUNK_SIZE) + (Word-offset * WORD_SIZE)
+ *
+ * And the sweep_id in the store pattern identifies the time when the
+ * store was performed by the rim_thread.
+ *
+ * We shall use this property in the 3)COMPARE step of the
+ * rim-sequence.
+ */
+#define SWEEP_ID_SHIFT	0
+#define WORD_OFFSET_SHIFT	(SWEEP_ID_BITS)
+#define THREAD_ID_SHIFT		(WORD_OFFSET_BITS + SWEEP_ID_BITS)
+
+/*
+ * Compute the store pattern for a given thread with id @tid, at
+ * location @addr in the sweep identified by @sweep_id
+ */
+static inline unsigned int compute_store_pattern(unsigned int tid,
+						 unsigned int *addr,
+						 unsigned int sweep_id)
+{
+	unsigned int ret = 0;
+	char *start = compute_chunk_start_addr(tid);
+	unsigned int word_offset = compute_word_offset(start, addr);
+
+	ret += (tid & THREAD_ID_MASK) << THREAD_ID_SHIFT;
+	ret += (word_offset & WORD_OFFSET_MASK) << WORD_OFFSET_SHIFT;
+	ret += (sweep_id & SWEEP_ID_MASK) << SWEEP_ID_SHIFT;
+	return ret;
+}
+
+/* Extract the thread-id from the given store-pattern */
+static inline unsigned int extract_tid(unsigned int pattern)
+{
+	unsigned int ret;
+
+	ret = (pattern >> THREAD_ID_SHIFT) & THREAD_ID_MASK;
+	return ret;
+}
+
+/* Extract the word-offset from the given store-pattern */
+static inline unsigned int extract_word_offset(unsigned int pattern)
+{
+	unsigned int ret;
+
+	ret = (pattern >> WORD_OFFSET_SHIFT) & WORD_OFFSET_MASK;
+
+	return ret;
+}
+
+/* Extract the sweep-id from the given store-pattern */
+static inline unsigned int extract_sweep_id(unsigned int pattern)
+
+{
+	unsigned int ret;
+
+	ret = (pattern >> SWEEP_ID_SHIFT) & SWEEP_ID_MASK;
+
+	return ret;
+}
+
+/************************************************************
+ *                                                          *
+ *          Logging the output of the verification          *
+ *                                                          *
+ ************************************************************/
+#define LOGDIR_NAME_SIZE 100
+static char logdir[LOGDIR_NAME_SIZE];
+
+static FILE *fp[MAX_THREADS];
+static const char logfilename[] ="Thread-%02d-Chunk";
+
+static inline void start_verification_log(unsigned int tid,
+					  unsigned int *addr,
+					  unsigned int cur_sweep_id,
+					  unsigned int prev_sweep_id)
+{
+	FILE *f;
+	char logfile[30];
+	char path[LOGDIR_NAME_SIZE + 30];
+	char separator[2] = "/";
+	char *chunk_start = compute_chunk_start_addr(tid);
+	unsigned int size = RIM_CHUNK_SIZE;
+
+	sprintf(logfile, logfilename, tid);
+	strcpy(path, logdir);
+	strcat(path, separator);
+	strcat(path, logfile);
+	f = fopen(path, "w");
+
+	if (!f) {
+		err_msg("Unable to create logfile\n");
+	}
+
+	fp[tid] = f;
+
+	fprintf(f, "----------------------------------------------------------\n");
+	fprintf(f, "PID                = %d\n", rim_process_pid);
+	fprintf(f, "Thread id          = %02d\n", tid);
+	fprintf(f, "Chunk Start Addr   = 0x%016lx\n", (unsigned long)chunk_start);
+	fprintf(f, "Chunk Size         = %d\n", size);
+	fprintf(f, "Next Store Addr    = 0x%016lx\n", (unsigned long)addr);
+	fprintf(f, "Current sweep-id   = 0x%08x\n", cur_sweep_id);
+	fprintf(f, "Previous sweep-id  = 0x%08x\n", prev_sweep_id);
+	fprintf(f, "----------------------------------------------------------\n");
+}
+
+static inline void log_anamoly(unsigned int tid, unsigned int *addr,
+			       unsigned int expected, unsigned int observed)
+{
+	FILE *f = fp[tid];
+
+	fprintf(f, "Thread %02d: Addr 0x%lx: Expected 0x%x, Observed 0x%x\n",
+	        tid, (unsigned long)addr, expected, observed);
+	fprintf(f, "Thread %02d: Expected Thread id   = %02d\n", tid, extract_tid(expected));
+	fprintf(f, "Thread %02d: Observed Thread id   = %02d\n", tid, extract_tid(observed));
+	fprintf(f, "Thread %02d: Expected Word offset = %03d\n", tid, extract_word_offset(expected));
+	fprintf(f, "Thread %02d: Observed Word offset = %03d\n", tid, extract_word_offset(observed));
+	fprintf(f, "Thread %02d: Expected sweep-id    = 0x%x\n", tid, extract_sweep_id(expected));
+	fprintf(f, "Thread %02d: Observed sweep-id    = 0x%x\n", tid, extract_sweep_id(observed));
+	fprintf(f, "----------------------------------------------------------\n");
+}
+
+static inline void end_verification_log(unsigned int tid, unsigned nr_anamolies)
+{
+	FILE *f = fp[tid];
+	char logfile[30];
+	char path[LOGDIR_NAME_SIZE + 30];
+	char separator[] = "/";
+
+	fclose(f);
+
+	if (nr_anamolies == 0) {
+		remove(path);
+		return;
+	}
+
+	sprintf(logfile, logfilename, tid);
+	strcpy(path, logdir);
+	strcat(path, separator);
+	strcat(path, logfile);
+
+	printf("Thread %02d chunk has %d corrupted words. For details check %s\n",
+		tid, nr_anamolies, path);
+}
+
+/*
+ * When a COMPARE step of a rim-sequence fails, the rim_thread informs
+ * everyone else via the shared_memory pointed to by
+ * corruption_found variable. On seeing this, every thread verifies the
+ * content of its chunk as follows.
+ *
+ * Suppose a thread identified with @tid was about to store (but not
+ * yet stored) to @next_store_addr in its current sweep identified
+ * @cur_sweep_id. Let @prev_sweep_id indicate the previous sweep_id.
+ *
+ * This implies that for all the addresses @addr < @next_store_addr,
+ * Thread @tid has already performed a store as part of its current
+ * sweep. Hence we expect the content of such @addr to be:
+ *    |-------------------------------------------------|
+ *    | tid   | word_offset(addr) |    cur_sweep_id     |
+ *    |-------------------------------------------------|
+ *
+ * Since Thread @tid is yet to perform stores on address
+ * @next_store_addr and above, we expect the content of such an
+ * address @addr to be:
+ *    |-------------------------------------------------|
+ *    | tid   | word_offset(addr) |    prev_sweep_id    |
+ *    |-------------------------------------------------|
+ *
+ * The verifier function @verify_chunk does this verification and logs
+ * any anamolies that it finds.
+ */
+static void verify_chunk(unsigned int tid, unsigned int *next_store_addr,
+		  unsigned int cur_sweep_id,
+		  unsigned int prev_sweep_id)
+{
+	unsigned int *iter_ptr;
+	unsigned int size = RIM_CHUNK_SIZE;
+	unsigned int expected;
+	unsigned int observed;
+	char *chunk_start = compute_chunk_start_addr(tid);
+
+	int nr_anamolies = 0;
+
+	start_verification_log(tid, next_store_addr,
+			       cur_sweep_id, prev_sweep_id);
+
+	for (iter_ptr = (unsigned int *)chunk_start;
+	     (unsigned long)iter_ptr < (unsigned long)chunk_start + size;
+	     iter_ptr++) {
+		unsigned int expected_sweep_id;
+
+		if (iter_ptr < next_store_addr) {
+			expected_sweep_id = cur_sweep_id;
+		} else {
+			expected_sweep_id = prev_sweep_id;
+		}
+
+		expected = compute_store_pattern(tid, iter_ptr, expected_sweep_id);
+
+		dcbf((volatile unsigned int*)iter_ptr); //Flush before reading
+		observed = *iter_ptr;
+
+	        if (observed != expected) {
+			nr_anamolies++;
+			log_anamoly(tid, iter_ptr, expected, observed);
+		}
+	}
+
+	end_verification_log(tid, nr_anamolies);
+}
+
+static void set_pthread_cpu(pthread_t th, int cpu)
+{
+	cpu_set_t run_cpu_mask;
+	struct sched_param param;
+
+	CPU_ZERO(&run_cpu_mask);
+	CPU_SET(cpu, &run_cpu_mask);
+	pthread_setaffinity_np(th, sizeof(cpu_set_t), &run_cpu_mask);
+
+	param.sched_priority = 1;
+	if (0 && sched_setscheduler(0, SCHED_FIFO, &param) == -1) {
+		/* haven't reproduced with this setting, it kills random preemption which may be a factor */
+		fprintf(stderr, "could not set SCHED_FIFO, run as root?\n");
+	}
+}
+
+static void set_mycpu(int cpu)
+{
+	cpu_set_t run_cpu_mask;
+	struct sched_param param;
+
+	CPU_ZERO(&run_cpu_mask);
+	CPU_SET(cpu, &run_cpu_mask);
+	sched_setaffinity(0, sizeof(cpu_set_t), &run_cpu_mask);
+
+	param.sched_priority = 1;
+	if (0 && sched_setscheduler(0, SCHED_FIFO, &param) == -1) {
+		fprintf(stderr, "could not set SCHED_FIFO, run as root?\n");
+	}
+}
+
+static volatile int segv_wait;
+
+static void segv_handler(int signo, siginfo_t *info, void *extra)
+{
+	while (segv_wait) {
+		sched_yield();
+	}
+
+}
+
+static void set_segv_handler(void)
+{
+	struct sigaction sa;
+
+	sa.sa_flags = SA_SIGINFO;
+	sa.sa_sigaction = segv_handler;
+
+	if (sigaction(SIGSEGV, &sa, NULL) == -1) {
+		perror("sigaction");
+		exit(EXIT_FAILURE);
+	}
+}
+
+int timeout = 0;
+/*
+ * This function is executed by every rim_thread.
+ *
+ * This function performs sweeps over the exclusive chunks of the
+ * rim_threads executing the rim-sequence one word at a time.
+ */
+static void *rim_fn(void *arg)
+{
+	unsigned int tid = *((unsigned int *)arg);
+
+	int size = RIM_CHUNK_SIZE;
+	char *chunk_start = compute_chunk_start_addr(tid);
+
+	unsigned int prev_sweep_id;
+	unsigned int cur_sweep_id = 0;
+
+	/* word access */
+	unsigned int pattern = cur_sweep_id;
+	unsigned int *pattern_ptr = &pattern;
+	unsigned int *w_ptr, read_data;
+
+	set_segv_handler();
+
+	/*
+	 * Let us initialize the chunk:
+	 *
+	 * Each word-aligned address addr in the chunk,
+	 * is initialized to :
+	 *    |-------------------------------------------------|
+	 *    | tid   | word_offset(addr) |         0           |
+	 *    |-------------------------------------------------|
+	 */
+	for (w_ptr = (unsigned int *)chunk_start;
+	     (unsigned long)w_ptr < (unsigned long)(chunk_start) + size;
+	     w_ptr++) {
+
+		*pattern_ptr = compute_store_pattern(tid, w_ptr, cur_sweep_id);
+		*w_ptr = *pattern_ptr;
+	}
+
+	while (!corruption_found && !timeout) {
+		prev_sweep_id = cur_sweep_id;
+		cur_sweep_id = cur_sweep_id + 1;
+
+		for (w_ptr = (unsigned int *)chunk_start;
+		     (unsigned long)w_ptr < (unsigned long)(chunk_start) + size;
+		     w_ptr++)  {
+			unsigned int old_pattern;
+
+			/*
+			 * Compute the pattern that we would have
+			 * stored at this location in the previous
+			 * sweep.
+			 */
+			old_pattern = compute_store_pattern(tid, w_ptr, prev_sweep_id);
+
+			/*
+			 * FLUSH:Ensure that we flush the contents of
+			 *       the cache before loading
+			 */
+			dcbf((volatile unsigned int*)w_ptr); //Flush
+
+			/* LOAD: Read the value */
+			read_data = *w_ptr; //Load
+
+			/*
+			 * COMPARE: Is it the same as what we had stored
+			 *          in the previous sweep ? It better be!
+			 */
+			if (read_data != old_pattern) {
+				/* No it isn't! Tell everyone */
+				corruption_found = 1;
+			}
+
+			/*
+			 * Before performing a store, let us check if
+			 * any rim_thread has found a corruption.
+			 */
+			if (corruption_found || timeout) {
+				/*
+				 * Yes. Someone (including us!) has found
+				 * a corruption :(
+				 *
+				 * Let us verify that our chunk is
+				 * correct.
+				 */
+				/* But first, let us allow the dust to settle down! */
+				verify_chunk(tid, w_ptr, cur_sweep_id, prev_sweep_id);
+
+				return 0;
+			}
+
+			/*
+			 * Compute the new pattern that we are going
+			 * to write to this location
+			 */
+			*pattern_ptr = compute_store_pattern(tid, w_ptr, cur_sweep_id);
+
+			/*
+			 * STORE: Now let us write this pattern into
+			 *        the location
+			 */
+			*w_ptr = *pattern_ptr;
+		}
+	}
+
+	return NULL;
+}
+
+
+static unsigned long start_cpu = 0;
+static unsigned long nrthreads = 4;
+
+static pthread_t mem_snapshot_thread;
+
+static void *mem_snapshot_fn(void *arg)
+{
+	int page_size = getpagesize();
+	size_t size = page_size;
+	void *tmp = malloc(size);
+
+	while (!corruption_found && !timeout) {
+		/* Stop memory migration once corruption is found */
+		segv_wait = 1;
+
+		mprotect(map1, size, PROT_READ);
+
+		/*
+		 * Load from the working alias (map1). Loading from map2
+		 * also fails.
+		 */
+		memcpy(tmp, map1, size);
+
+		/*
+		 * Stores must go via map2 which has write permissions, but
+		 * the corrupted data tends to be seen in the snapshot buffer,
+		 * so corruption does not appear to be introduced at the
+		 * copy-back via map2 alias here.
+		 */
+		memcpy(map2, tmp, size);
+		/*
+		 * Before releasing other threads, must ensure the copy
+		 * back to
+		 */
+		asm volatile("sync" ::: "memory");
+		mprotect(map1, size, PROT_READ|PROT_WRITE);
+		asm volatile("sync" ::: "memory");
+		segv_wait = 0;
+
+		usleep(1); /* This value makes a big difference */
+	}
+
+	return 0;
+}
+
+void alrm_sighandler(int sig)
+{
+	timeout = 1;
+}
+
+int main(int argc, char *argv[])
+{
+	int c;
+	int page_size = getpagesize();
+	time_t now;
+	int i, dir_error;
+	pthread_attr_t attr;
+	key_t shm_key = (key_t) getpid();
+	int shmid, run_time = 20 * 60;
+	struct sigaction sa_alrm;
+
+	snprintf(logdir, LOGDIR_NAME_SIZE,
+		 "/tmp/logdir-%u", (unsigned int)getpid());
+	while ((c = getopt(argc, argv, "r:hn:l:t:")) != -1) {
+		switch(c) {
+		case 'r':
+			start_cpu = strtoul(optarg, NULL, 10);
+			break;
+		case 'h':
+			printf("%s [-r <start_cpu>] [-n <nrthreads>] [-l <logdir>] [-t <timeout>]\n", argv[0]);
+			exit(0);
+			break;
+		case 'n':
+			nrthreads = strtoul(optarg, NULL, 10);
+			break;
+		case 'l':
+			strncpy(logdir, optarg, LOGDIR_NAME_SIZE - 1);
+			break;
+		case 't':
+			run_time = strtoul(optarg, NULL, 10);
+			break;
+		default:
+			printf("invalid option\n");
+			exit(0);
+			break;
+		}
+	}
+
+	if (nrthreads > MAX_THREADS)
+		nrthreads = MAX_THREADS;
+
+	shmid = shmget(shm_key, page_size, IPC_CREAT|0666);
+	if (shmid < 0) {
+		err_msg("Failed shmget\n");
+	}
+
+	map1 = shmat(shmid, NULL, 0);
+	if (map1 == (void *) -1) {
+		err_msg("Failed shmat");
+	}
+
+	map2 = shmat(shmid, NULL, 0);
+	if (map2 == (void *) -1) {
+		err_msg("Failed shmat");
+	}
+
+	dir_error = mkdir(logdir, 0755);
+
+	if (dir_error) {
+		err_msg("Failed mkdir");
+	}
+
+	printf("start_cpu list:%lu\n", start_cpu);
+	printf("number of worker threads:%lu + 1 snapshot thread\n", nrthreads);
+	printf("Allocated address:0x%016lx + secondary map:0x%016lx\n", (unsigned long)map1, (unsigned long)map2);
+	printf("logdir at : %s\n", logdir);
+	printf("Timeout: %d seconds\n", run_time);
+
+	time(&now);
+	printf("=================================\n");
+	printf("     Starting Test\n");
+	printf("     %s", ctime(&now));
+	printf("=================================\n");
+
+	for (i = 0; i < nrthreads; i++) {
+		if (1 && !fork()) {
+			prctl(PR_SET_PDEATHSIG, SIGKILL);
+			set_mycpu(start_cpu + i);
+			for (;;)
+				sched_yield();
+			exit(0);
+		}
+	}
+
+
+	sa_alrm.sa_handler = &alrm_sighandler;
+	sigemptyset(&sa_alrm.sa_mask);
+	sa_alrm.sa_flags = 0;
+
+	if (sigaction(SIGALRM, &sa_alrm, 0) == -1) {
+		err_msg("Failed signal handler registration\n");
+	}
+
+	alarm(run_time);
+
+	pthread_attr_init(&attr);
+	for (i = 0; i < nrthreads; i++) {
+		rim_thread_ids[i] = i;
+		pthread_create(&rim_threads[i], &attr, rim_fn, &rim_thread_ids[i]);
+		set_pthread_cpu(rim_threads[i], start_cpu + i);
+	}
+
+	pthread_create(&mem_snapshot_thread, &attr, mem_snapshot_fn, map1);
+	set_pthread_cpu(mem_snapshot_thread, start_cpu + i);
+
+
+	pthread_join(mem_snapshot_thread, NULL);
+	for (i = 0; i < nrthreads; i++) {
+		pthread_join(rim_threads[i], NULL);
+	}
+
+	if (!timeout) {
+		time(&now);
+		printf("=================================\n");
+		printf("      Data Corruption Detected\n");
+		printf("      %s", ctime(&now));
+		printf("      See logfiles in %s\n", logdir);
+		printf("=================================\n");
+		return 1;
+	}
+	return 0;
+}