Source update

Lot of goodies there.

arch/arm/boot/dts/imx6dl-yapp4-common.dtsi

@@ -105,9 +105,13 @@ &fec {
 	phy-reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>;
 	phy-reset-duration = <20>;
 	phy-supply = <&sw2_reg>;
-	phy-handle = <&ethphy0>;
 	status = "okay";
 
+	fixed-link {
+		speed = <1000>;
+		full-duplex;
+	};
+
 	mdio {
 		#address-cells = <1>;
 		#size-cells = <0>;

arch/arm/boot/dts/imx6q-dhcom-som.dtsi

@@ -406,6 +406,18 @@ &reg_soc {
 	vin-supply = <&sw1_reg>;
 };
 
+&reg_pu {
+	vin-supply = <&sw1_reg>;
+};
+
+&reg_vdd1p1 {
+	vin-supply = <&sw2_reg>;
+};
+
+&reg_vdd2p5 {
+	vin-supply = <&sw2_reg>;
+};
+
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;

arch/arm/boot/dts/imx7d-meerkat96.dts

@@ -193,7 +193,7 @@ &usdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc1>;
 	keep-power-in-suspend;
-	tuning-step = <2>;
+	fsl,tuning-step = <2>;
 	vmmc-supply = <&reg_3p3v>;
 	no-1-8-v;
 	broken-cd;

arch/arm/boot/dts/imx7d-pico.dtsi

@@ -351,7 +351,7 @@ &usdhc1 {
 	pinctrl-2 = <&pinctrl_usdhc1_200mhz>;
 	cd-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>;
 	bus-width = <4>;
-	tuning-step = <2>;
+	fsl,tuning-step = <2>;
 	vmmc-supply = <&reg_3p3v>;
 	wakeup-source;
 	no-1-8-v;

arch/arm/boot/dts/overlays/ghost-amp-overlay.dts

@@ -82,14 +82,20 @@ amp_off {
 
 				amp_on_1 {
 					set = <RELAY1 1>;
-					amp_on = <GF_DELAY 1000>;
+					amp_on_2 = <GF_DELAY 1000>;
-					amp_off = <ENABLE 0>;
+					amp_off = <GF_SHUTDOWN 0>;
+					fault = <FAULT 1>;
+				};
+
+				amp_on_2 {
+					set = <RELAY2 1>;
+					amp_on_wait = <ENABLE 0>;
+					amp_on = <GF_DELAY 1>;
 					fault = <FAULT 1>;
 				};
 
 				amp_on {
-					set = <RELAY2 1>,
+					set = <RELAYSSR 1>;
-					      <RELAYSSR 1>;
 					amp_on_wait = <ENABLE 0>;
 					fault = <FAULT 1>;
 				};

arch/arm/mach-omap1/board-h2.c

@@ -320,7 +320,7 @@ static int tps_setup(struct i2c_client *client, void *context)
 {
 	if (!IS_BUILTIN(CONFIG_TPS65010))
 		return -ENOSYS;
-	
+
 	tps65010_config_vregs1(TPS_LDO2_ENABLE | TPS_VLDO2_3_0V |
 				TPS_LDO1_ENABLE | TPS_VLDO1_3_0V);
 
@@ -394,6 +394,8 @@ static void __init h2_init(void)
 	BUG_ON(gpio_request(H2_NAND_RB_GPIO_PIN, "NAND ready") < 0);
 	gpio_direction_input(H2_NAND_RB_GPIO_PIN);
 
+	gpiod_add_lookup_table(&isp1301_gpiod_table);
+
 	omap_cfg_reg(L3_1610_FLASH_CS2B_OE);
 	omap_cfg_reg(M8_1610_FLASH_CS2B_WE);
 

arch/arm64/Kconfig.platforms

@@ -168,6 +168,7 @@ config ARCH_MEDIATEK
 
 config ARCH_MESON
 	bool "Amlogic Platforms"
+	select COMMON_CLK
 	select MESON_IRQ_GPIO
 	help
 	  This enables support for the arm64 based Amlogic SoCs

arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var1.dts

@@ -46,7 +46,8 @@ phy0: ethernet-phy@4 {
 			eee-broken-100tx;
 			qca,clk-out-frequency = <125000000>;
 			qca,clk-out-strength = <AR803X_STRENGTH_FULL>;
-			vddio-supply = <&vddh>;
+			qca,keep-pll-enabled;
+			vddio-supply = <&vddio>;
 
 			vddio: vddio-regulator {
 				regulator-name = "VDDIO";

arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var4.dts

@@ -31,11 +31,10 @@ phy1: ethernet-phy@4 {
 			reg = <0x4>;
 			eee-broken-1000t;
 			eee-broken-100tx;
-
 			qca,clk-out-frequency = <125000000>;
 			qca,clk-out-strength = <AR803X_STRENGTH_FULL>;
-
+			qca,keep-pll-enabled;
-			vddio-supply = <&vddh>;
+			vddio-supply = <&vddio>;
 
 			vddio: vddio-regulator {
 				regulator-name = "VDDIO";

arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi

@@ -201,8 +201,8 @@ soc: soc {
 		ddr: memory-controller@1080000 {
 			compatible = "fsl,qoriq-memory-controller";
 			reg = <0x0 0x1080000 0x0 0x1000>;
-			interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
-			big-endian;
+			little-endian;
 		};
 
 		dcfg: syscon@1e00000 {

arch/arm64/boot/dts/freescale/imx8mq-zii-ultra-rmb3.dts

@@ -88,11 +88,11 @@ codec2: codec@18 {
 		pinctrl-0 = <&pinctrl_codec2>;
 		reg = <0x18>;
 		#sound-dai-cells = <0>;
-		HPVDD-supply = <&reg_3p3v>;
+		HPVDD-supply = <&reg_gen_3p3>;
-		SPRVDD-supply = <&reg_3p3v>;
+		SPRVDD-supply = <&reg_gen_3p3>;
-		SPLVDD-supply = <&reg_3p3v>;
+		SPLVDD-supply = <&reg_gen_3p3>;
-		AVDD-supply = <&reg_3p3v>;
+		AVDD-supply = <&reg_gen_3p3>;
-		IOVDD-supply = <&reg_3p3v>;
+		IOVDD-supply = <&reg_gen_3p3>;
 		DVDD-supply = <&vgen4_reg>;
 		reset-gpios = <&gpio3 4 GPIO_ACTIVE_HIGH>;
 	};

arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi

@@ -45,8 +45,8 @@ pcie1_refclk: clock-pcie1-refclk {
 	reg_12p0_main: regulator-12p0-main {
 		compatible = "regulator-fixed";
 		regulator-name = "12V_MAIN";
-		regulator-min-microvolt = <5000000>;
+		regulator-min-microvolt = <12000000>;
-		regulator-max-microvolt = <5000000>;
+		regulator-max-microvolt = <12000000>;
 		regulator-always-on;
 	};
 
@@ -77,15 +77,6 @@ reg_gen_3p3: regulator-gen-3p3 {
 		regulator-always-on;
 	};
 
-	reg_3p3v: regulator-3p3v {
-		compatible = "regulator-fixed";
-		vin-supply = <&reg_3p3_main>;
-		regulator-name = "GEN_3V3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		regulator-always-on;
-	};
-
 	reg_usdhc2_vmmc: regulator-vsd-3v3 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_reg_usdhc2>;
@@ -415,11 +406,11 @@ codec1: codec@18 {
 		pinctrl-0 = <&pinctrl_codec1>;
 		reg = <0x18>;
 		#sound-dai-cells = <0>;
-		HPVDD-supply = <&reg_3p3v>;
+		HPVDD-supply = <&reg_gen_3p3>;
-		SPRVDD-supply = <&reg_3p3v>;
+		SPRVDD-supply = <&reg_gen_3p3>;
-		SPLVDD-supply = <&reg_3p3v>;
+		SPLVDD-supply = <&reg_gen_3p3>;
-		AVDD-supply = <&reg_3p3v>;
+		AVDD-supply = <&reg_gen_3p3>;
-		IOVDD-supply = <&reg_3p3v>;
+		IOVDD-supply = <&reg_gen_3p3>;
 		DVDD-supply = <&vgen4_reg>;
 		reset-gpios = <&gpio3 3 GPIO_ACTIVE_LOW>;
 	};

arch/arm64/boot/dts/ti/k3-j7200-main.dtsi

@@ -85,6 +85,8 @@ main_navss: bus@30000000 {
 		#size-cells = <2>;
 		ranges = <0x00 0x30000000 0x00 0x30000000 0x00 0x0c400000>;
 		ti,sci-dev-id = <199>;
+		dma-coherent;
+		dma-ranges;
 
 		main_navss_intr: interrupt-controller1 {
 			compatible = "ti,sci-intr";

arch/arm64/include/asm/kvm_asm.h

@@ -57,6 +57,7 @@
 #define __KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2		12
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs		13
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs		14
+#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc			15
 
 #ifndef __ASSEMBLY__
 

arch/arm64/kvm/arm.c

@@ -715,11 +715,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			return ret;
 	}
 
-	if (run->immediate_exit)
-		return -EINTR;
-
 	vcpu_load(vcpu);
 
+	if (run->immediate_exit) {
+		ret = -EINTR;
+		goto out;
+	}
+
 	kvm_sigset_activate(vcpu);
 
 	ret = 1;
@@ -892,6 +894,18 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 	kvm_sigset_deactivate(vcpu);
 
+out:
+	/*
+	 * In the unlikely event that we are returning to userspace
+	 * with pending exceptions or PC adjustment, commit these
+	 * adjustments in order to give userspace a consistent view of
+	 * the vcpu state. Note that this relies on __kvm_adjust_pc()
+	 * being preempt-safe on VHE.
+	 */
+	if (unlikely(vcpu->arch.flags & (KVM_ARM64_PENDING_EXCEPTION |
+					 KVM_ARM64_INCREMENT_PC)))
+		kvm_call_hyp(__kvm_adjust_pc, vcpu);
+
 	vcpu_put(vcpu);
 	return ret;
 }

arch/arm64/kvm/hyp/exception.c

@@ -331,8 +331,8 @@ static void kvm_inject_exception(struct kvm_vcpu *vcpu)
 }
 
 /*
- * Adjust the guest PC on entry, depending on flags provided by EL1
+ * Adjust the guest PC (and potentially exception state) depending on
- * for the purpose of emulation (MMIO, sysreg) or exception injection.
+ * flags provided by the emulation code.
  */
 void __kvm_adjust_pc(struct kvm_vcpu *vcpu)
 {

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -25,6 +25,13 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) =  __kvm_vcpu_run(kern_hyp_va(vcpu));
 }
 
+static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
+
+	__kvm_adjust_pc(kern_hyp_va(vcpu));
+}
+
 static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt)
 {
 	__kvm_flush_vm_context();
@@ -112,6 +119,7 @@ typedef void (*hcall_t)(struct kvm_cpu_context *);
 
 static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_vcpu_run),
+	HANDLE_FUNC(__kvm_adjust_pc),
 	HANDLE_FUNC(__kvm_flush_vm_context),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid),

arch/mips/mm/cache.c

@@ -157,31 +157,29 @@ unsigned long _page_cachable_default;
 EXPORT_SYMBOL(_page_cachable_default);
 
 #define PM(p)	__pgprot(_page_cachable_default | (p))
-#define PVA(p)	PM(_PAGE_VALID | _PAGE_ACCESSED | (p))
 
 static inline void setup_protection_map(void)
 {
 	protection_map[0]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
-	protection_map[1]  = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC);
+	protection_map[1]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC);
-	protection_map[2]  = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
+	protection_map[2]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
-	protection_map[3]  = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC);
+	protection_map[3]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC);
-	protection_map[4]  = PVA(_PAGE_PRESENT);
+	protection_map[4]  = PM(_PAGE_PRESENT);
-	protection_map[5]  = PVA(_PAGE_PRESENT);
+	protection_map[5]  = PM(_PAGE_PRESENT);
-	protection_map[6]  = PVA(_PAGE_PRESENT);
+	protection_map[6]  = PM(_PAGE_PRESENT);
-	protection_map[7]  = PVA(_PAGE_PRESENT);
+	protection_map[7]  = PM(_PAGE_PRESENT);
 
 	protection_map[8]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
-	protection_map[9]  = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC);
+	protection_map[9]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC);
-	protection_map[10] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE |
+	protection_map[10] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE |
 				_PAGE_NO_READ);
-	protection_map[11] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE);
+	protection_map[11] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE);
-	protection_map[12] = PVA(_PAGE_PRESENT);
+	protection_map[12] = PM(_PAGE_PRESENT);
-	protection_map[13] = PVA(_PAGE_PRESENT);
+	protection_map[13] = PM(_PAGE_PRESENT);
-	protection_map[14] = PVA(_PAGE_PRESENT);
+	protection_map[14] = PM(_PAGE_PRESENT | _PAGE_WRITE);
-	protection_map[15] = PVA(_PAGE_PRESENT);
+	protection_map[15] = PM(_PAGE_PRESENT | _PAGE_WRITE);
 }
 
-#undef _PVA
 #undef PM
 
 void cpu_cache_init(void)

arch/powerpc/kernel/kprobes.c

@@ -108,7 +108,6 @@ int arch_prepare_kprobe(struct kprobe *p)
 	int ret = 0;
 	struct kprobe *prev;
 	struct ppc_inst insn = ppc_inst_read((struct ppc_inst *)p->addr);
-	struct ppc_inst prefix = ppc_inst_read((struct ppc_inst *)(p->addr - 1));
 
 	if ((unsigned long)p->addr & 0x03) {
 		printk("Attempt to register kprobe at an unaligned address\n");
@@ -116,7 +115,8 @@ int arch_prepare_kprobe(struct kprobe *p)
 	} else if (IS_MTMSRD(insn) || IS_RFID(insn) || IS_RFI(insn)) {
 		printk("Cannot register a kprobe on rfi/rfid or mtmsr[d]\n");
 		ret = -EINVAL;
-	} else if (ppc_inst_prefixed(prefix)) {
+	} else if ((unsigned long)p->addr & ~PAGE_MASK &&
+		   ppc_inst_prefixed(ppc_inst_read((struct ppc_inst *)(p->addr - 1)))) {
 		printk("Cannot register a kprobe on the second word of prefixed instruction\n");
 		ret = -EINVAL;
 	}

arch/powerpc/kvm/book3s_hv.c

@@ -4418,7 +4418,6 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 		mtspr(SPRN_EBBRR, ebb_regs[1]);
 		mtspr(SPRN_BESCR, ebb_regs[2]);
 		mtspr(SPRN_TAR, user_tar);
-		mtspr(SPRN_FSCR, current->thread.fscr);
 	}
 	mtspr(SPRN_VRSAVE, user_vrsave);
 

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -59,6 +59,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 #define STACK_SLOT_UAMOR	(SFS-88)
 #define STACK_SLOT_DAWR1	(SFS-96)
 #define STACK_SLOT_DAWRX1	(SFS-104)
+#define STACK_SLOT_FSCR		(SFS-112)
 /* the following is used by the P9 short path */
 #define STACK_SLOT_NVGPRS	(SFS-152)	/* 18 gprs */
 
@@ -686,6 +687,8 @@ BEGIN_FTR_SECTION
 	std	r6, STACK_SLOT_DAWR0(r1)
 	std	r7, STACK_SLOT_DAWRX0(r1)
 	std	r8, STACK_SLOT_IAMR(r1)
+	mfspr	r5, SPRN_FSCR
+	std	r5, STACK_SLOT_FSCR(r1)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 BEGIN_FTR_SECTION
 	mfspr	r6, SPRN_DAWR1
@@ -1663,6 +1666,10 @@ FTR_SECTION_ELSE
 	ld	r7, STACK_SLOT_HFSCR(r1)
 	mtspr	SPRN_HFSCR, r7
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
+BEGIN_FTR_SECTION
+	ld	r5, STACK_SLOT_FSCR(r1)
+	mtspr	SPRN_FSCR, r5
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	/*
 	 * Restore various registers to 0, where non-zero values
 	 * set by the guest could disrupt the host.

arch/riscv/kernel/vdso/Makefile

@@ -23,7 +23,7 @@ ifneq ($(c-gettimeofday-y),)
 endif
 
 # Build rules
-targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-dummy.o
+targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-syms.S
 obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
 
 obj-y += vdso.o vdso-syms.o
@@ -41,7 +41,7 @@ KASAN_SANITIZE := n
 $(obj)/vdso.o: $(obj)/vdso.so
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE
+$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
 	$(call if_changed,vdsold)
 LDFLAGS_vdso.so.dbg = -shared -s -soname=linux-vdso.so.1 \
 	--build-id=sha1 --hash-style=both --eh-frame-hdr

arch/x86/include/asm/apic.h

@@ -174,6 +174,7 @@ static inline int apic_is_clustered_box(void)
 extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
 extern void lapic_assign_system_vectors(void);
 extern void lapic_assign_legacy_vector(unsigned int isairq, bool replace);
+extern void lapic_update_legacy_vectors(void);
 extern void lapic_online(void);
 extern void lapic_offline(void);
 extern bool apic_needs_pit(void);

arch/x86/include/asm/disabled-features.h

@@ -56,11 +56,8 @@
 # define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
 #endif
 
-#ifdef CONFIG_IOMMU_SUPPORT
+/* Force disable because it's broken beyond repair */
-# define DISABLE_ENQCMD	0
+#define DISABLE_ENQCMD		(1 << (X86_FEATURE_ENQCMD & 31))
-#else
-# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))
-#endif
 
 #ifdef CONFIG_X86_SGX
 # define DISABLE_SGX	0

arch/x86/include/asm/fpu/api.h

@@ -106,10 +106,6 @@ extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
  */
 #define PASID_DISABLED	0
 
-#ifdef CONFIG_IOMMU_SUPPORT
-/* Update current's PASID MSR/state by mm's PASID. */
-void update_pasid(void);
-#else
 static inline void update_pasid(void) { }
-#endif
+
 #endif /* _ASM_X86_FPU_API_H */

arch/x86/include/asm/fpu/internal.h

@@ -584,13 +584,6 @@ static inline void switch_fpu_finish(struct fpu *new_fpu)
 			pkru_val = pk->pkru;
 	}
 	__write_pkru(pkru_val);
-
-	/*
-	 * Expensive PASID MSR write will be avoided in update_pasid() because
-	 * TIF_NEED_FPU_LOAD was set. And the PASID state won't be updated
-	 * unless it's different from mm->pasid to reduce overhead.
-	 */
-	update_pasid();
 }
 
 #endif /* _ASM_X86_FPU_INTERNAL_H */

arch/x86/include/asm/kvm_para.h

@@ -7,8 +7,6 @@
 #include <linux/interrupt.h>
 #include <uapi/asm/kvm_para.h>
 
-extern void kvmclock_init(void);
-
 #ifdef CONFIG_KVM_GUEST
 bool kvm_check_and_clear_guest_paused(void);
 #else
@@ -86,13 +84,14 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 }
 
 #ifdef CONFIG_KVM_GUEST
+void kvmclock_init(void);
+void kvmclock_disable(void);
 bool kvm_para_available(void);
 unsigned int kvm_arch_para_features(void);
 unsigned int kvm_arch_para_hints(void);
 void kvm_async_pf_task_wait_schedule(u32 token);
 void kvm_async_pf_task_wake(u32 token);
 u32 kvm_read_and_reset_apf_flags(void);
-void kvm_disable_steal_time(void);
 bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token);
 
 DECLARE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
@@ -137,11 +136,6 @@ static inline u32 kvm_read_and_reset_apf_flags(void)
 	return 0;
 }
 
-static inline void kvm_disable_steal_time(void)
-{
-	return;
-}
-
 static __always_inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 {
 	return false;

arch/x86/include/asm/thermal.h

@@ -3,11 +3,13 @@
 #define _ASM_X86_THERMAL_H
 
 #ifdef CONFIG_X86_THERMAL_VECTOR
+void therm_lvt_init(void);
 void intel_init_thermal(struct cpuinfo_x86 *c);
 bool x86_thermal_enabled(void);
 void intel_thermal_interrupt(void);
 #else
-static inline void intel_init_thermal(struct cpuinfo_x86 *c) { }
+static inline void therm_lvt_init(void)				{ }
+static inline void intel_init_thermal(struct cpuinfo_x86 *c)	{ }
 #endif
 
 #endif /* _ASM_X86_THERMAL_H */

arch/x86/kernel/apic/apic.c

@@ -2604,6 +2604,7 @@ static void __init apic_bsp_setup(bool upmode)
 	end_local_APIC_setup();
 	irq_remap_enable_fault_handling();
 	setup_IO_APIC();
+	lapic_update_legacy_vectors();
 }
 
 #ifdef CONFIG_UP_LATE_INIT

arch/x86/kernel/apic/vector.c

@@ -730,6 +730,26 @@ void lapic_assign_legacy_vector(unsigned int irq, bool replace)
 	irq_matrix_assign_system(vector_matrix, ISA_IRQ_VECTOR(irq), replace);
 }
 
+void __init lapic_update_legacy_vectors(void)
+{
+	unsigned int i;
+
+	if (IS_ENABLED(CONFIG_X86_IO_APIC) && nr_ioapics > 0)
+		return;
+
+	/*
+	 * If the IO/APIC is disabled via config, kernel command line or
+	 * lack of enumeration then all legacy interrupts are routed
+	 * through the PIC. Make sure that they are marked as legacy
+	 * vectors. PIC_CASCADE_IRQ has already been marked in
+	 * lapic_assign_system_vectors().
+	 */
+	for (i = 0; i < nr_legacy_irqs(); i++) {
+		if (i != PIC_CASCADE_IR)
+			lapic_assign_legacy_vector(i, true);
+	}
+}
+
 void __init lapic_assign_system_vectors(void)
 {
 	unsigned int i, vector = 0;

arch/x86/kernel/fpu/xstate.c

@@ -1402,60 +1402,3 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns,
 	return 0;
 }
 #endif /* CONFIG_PROC_PID_ARCH_STATUS */
-
-#ifdef CONFIG_IOMMU_SUPPORT
-void update_pasid(void)
-{
-	u64 pasid_state;
-	u32 pasid;
-
-	if (!cpu_feature_enabled(X86_FEATURE_ENQCMD))
-		return;
-
-	if (!current->mm)
-		return;
-
-	pasid = READ_ONCE(current->mm->pasid);
-	/* Set the valid bit in the PASID MSR/state only for valid pasid. */
-	pasid_state = pasid == PASID_DISABLED ?
-		      pasid : pasid | MSR_IA32_PASID_VALID;
-
-	/*
-	 * No need to hold fregs_lock() since the task's fpstate won't
-	 * be changed by others (e.g. ptrace) while the task is being
-	 * switched to or is in IPI.
-	 */
-	if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
-		/* The MSR is active and can be directly updated. */
-		wrmsrl(MSR_IA32_PASID, pasid_state);
-	} else {
-		struct fpu *fpu = &current->thread.fpu;
-		struct ia32_pasid_state *ppasid_state;
-		struct xregs_state *xsave;
-
-		/*
-		 * The CPU's xstate registers are not currently active. Just
-		 * update the PASID state in the memory buffer here. The
-		 * PASID MSR will be loaded when returning to user mode.
-		 */
-		xsave = &fpu->state.xsave;
-		xsave->header.xfeatures |= XFEATURE_MASK_PASID;
-		ppasid_state = get_xsave_addr(xsave, XFEATURE_PASID);
-		/*
-		 * Since XFEATURE_MASK_PASID is set in xfeatures, ppasid_state
-		 * won't be NULL and no need to check its value.
-		 *
-		 * Only update the task's PASID state when it's different
-		 * from the mm's pasid.
-		 */
-		if (ppasid_state->pasid != pasid_state) {
-			/*
-			 * Invalid fpregs so that state restoring will pick up
-			 * the PASID state.
-			 */
-			__fpu_invalidate_fpregs_state(fpu);
-			ppasid_state->pasid = pasid_state;
-		}
-	}
-}
-#endif /* CONFIG_IOMMU_SUPPORT */

arch/x86/kernel/kvm.c

@@ -26,6 +26,7 @@
 #include <linux/kprobes.h>
 #include <linux/nmi.h>
 #include <linux/swait.h>
+#include <linux/syscore_ops.h>
 #include <asm/timer.h>
 #include <asm/cpu.h>
 #include <asm/traps.h>
@@ -37,6 +38,7 @@
 #include <asm/tlb.h>
 #include <asm/cpuidle_haltpoll.h>
 #include <asm/ptrace.h>
+#include <asm/reboot.h>
 #include <asm/svm.h>
 
 DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
@@ -374,6 +376,14 @@ static void kvm_pv_disable_apf(void)
 	pr_info("Unregister pv shared memory for cpu %d\n", smp_processor_id());
 }
 
+static void kvm_disable_steal_time(void)
+{
+	if (!has_steal_clock)
+		return;
+
+	wrmsr(MSR_KVM_STEAL_TIME, 0, 0);
+}
+
 static void kvm_pv_guest_cpu_reboot(void *unused)
 {
 	/*
@@ -416,14 +426,6 @@ static u64 kvm_steal_clock(int cpu)
 	return steal;
 }
 
-void kvm_disable_steal_time(void)
-{
-	if (!has_steal_clock)
-		return;
-
-	wrmsr(MSR_KVM_STEAL_TIME, 0, 0);
-}
-
 static inline void __set_percpu_decrypted(void *ptr, unsigned long size)
 {
 	early_set_memory_decrypted((unsigned long) ptr, size);
@@ -460,6 +462,27 @@ static bool pv_tlb_flush_supported(void)
 
 static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask);
 
+static void kvm_guest_cpu_offline(bool shutdown)
+{
+	kvm_disable_steal_time();
+	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
+		wrmsrl(MSR_KVM_PV_EOI_EN, 0);
+	kvm_pv_disable_apf();
+	if (!shutdown)
+		apf_task_wake_all();
+	kvmclock_disable();
+}
+
+static int kvm_cpu_online(unsigned int cpu)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	kvm_guest_cpu_init();
+	local_irq_restore(flags);
+	return 0;
+}
+
 #ifdef CONFIG_SMP
 
 static bool pv_ipi_supported(void)
@@ -587,30 +610,47 @@ static void __init kvm_smp_prepare_boot_cpu(void)
 	kvm_spinlock_init();
 }
 
-static void kvm_guest_cpu_offline(void)
-{
-	kvm_disable_steal_time();
-	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
-		wrmsrl(MSR_KVM_PV_EOI_EN, 0);
-	kvm_pv_disable_apf();
-	apf_task_wake_all();
-}
-
-static int kvm_cpu_online(unsigned int cpu)
-{
-	local_irq_disable();
-	kvm_guest_cpu_init();
-	local_irq_enable();
-	return 0;
-}
-
 static int kvm_cpu_down_prepare(unsigned int cpu)
 {
-	local_irq_disable();
+	unsigned long flags;
-	kvm_guest_cpu_offline();
+
-	local_irq_enable();
+	local_irq_save(flags);
+	kvm_guest_cpu_offline(false);
+	local_irq_restore(flags);
 	return 0;
 }
+
+#endif
+
+static int kvm_suspend(void)
+{
+	kvm_guest_cpu_offline(false);
+
+	return 0;
+}
+
+static void kvm_resume(void)
+{
+	kvm_cpu_online(raw_smp_processor_id());
+}
+
+static struct syscore_ops kvm_syscore_ops = {
+	.suspend	= kvm_suspend,
+	.resume		= kvm_resume,
+};
+
+/*
+ * After a PV feature is registered, the host will keep writing to the
+ * registered memory location. If the guest happens to shutdown, this memory
+ * won't be valid. In cases like kexec, in which you install a new kernel, this
+ * means a random memory location will be kept being written.
+ */
+#ifdef CONFIG_KEXEC_CORE
+static void kvm_crash_shutdown(struct pt_regs *regs)
+{
+	kvm_guest_cpu_offline(true);
+	native_machine_crash_shutdown(regs);
+}
 #endif
 
 static void kvm_flush_tlb_others(const struct cpumask *cpumask,
@@ -681,6 +721,12 @@ static void __init kvm_guest_init(void)
 	kvm_guest_cpu_init();
 #endif
 
+#ifdef CONFIG_KEXEC_CORE
+	machine_ops.crash_shutdown = kvm_crash_shutdown;
+#endif
+
+	register_syscore_ops(&kvm_syscore_ops);
+
 	/*
 	 * Hard lockup detection is enabled by default. Disable it, as guests
 	 * can get false positives too easily, for example if the host is

arch/x86/kernel/kvmclock.c

@@ -20,7 +20,6 @@
 #include <asm/hypervisor.h>
 #include <asm/mem_encrypt.h>
 #include <asm/x86_init.h>
-#include <asm/reboot.h>
 #include <asm/kvmclock.h>
 
 static int kvmclock __initdata = 1;
@@ -203,28 +202,9 @@ static void kvm_setup_secondary_clock(void)
 }
 #endif
 
-/*
+void kvmclock_disable(void)
- * After the clock is registered, the host will keep writing to the
- * registered memory location. If the guest happens to shutdown, this memory
- * won't be valid. In cases like kexec, in which you install a new kernel, this
- * means a random memory location will be kept being written. So before any
- * kind of shutdown from our side, we unregister the clock by writing anything
- * that does not have the 'enable' bit set in the msr
- */
-#ifdef CONFIG_KEXEC_CORE
-static void kvm_crash_shutdown(struct pt_regs *regs)
 {
 	native_write_msr(msr_kvm_system_time, 0, 0);
-	kvm_disable_steal_time();
-	native_machine_crash_shutdown(regs);
-}
-#endif
-
-static void kvm_shutdown(void)
-{
-	native_write_msr(msr_kvm_system_time, 0, 0);
-	kvm_disable_steal_time();
-	native_machine_shutdown();
 }
 
 static void __init kvmclock_init_mem(void)
@@ -351,10 +331,6 @@ void __init kvmclock_init(void)
 #endif
 	x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
 	x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
-	machine_ops.shutdown  = kvm_shutdown;
-#ifdef CONFIG_KEXEC_CORE
-	machine_ops.crash_shutdown  = kvm_crash_shutdown;
-#endif
 	kvm_get_preset_lpj();
 
 	/*

arch/x86/kernel/setup.c

@@ -44,6 +44,7 @@
 #include <asm/pci-direct.h>
 #include <asm/prom.h>
 #include <asm/proto.h>
+#include <asm/thermal.h>
 #include <asm/unwind.h>
 #include <asm/vsyscall.h>
 #include <linux/vmalloc.h>
@@ -1220,6 +1221,14 @@ void __init setup_arch(char **cmdline_p)
 
 	x86_init.timers.wallclock_init();
 
+	/*
+	 * This needs to run before setup_local_APIC() which soft-disables the
+	 * local APIC temporarily and that masks the thermal LVT interrupt,
+	 * leading to softlockups on machines which have configured SMI
+	 * interrupt delivery.
+	 */
+	therm_lvt_init();
+
 	mcheck_init();
 
 	register_refined_jiffies(CLOCK_TICK_RATE);

arch/x86/kvm/svm/svm.c

@@ -2532,7 +2532,7 @@ static int cr_interception(struct vcpu_svm *svm)
 	err = 0;
 	if (cr >= 16) { /* mov to cr */
 		cr -= 16;
-		val = kvm_register_read(&svm->vcpu, reg);
+		val = kvm_register_readl(&svm->vcpu, reg);
 		trace_kvm_cr_write(cr, val);
 		switch (cr) {
 		case 0:
@@ -2578,7 +2578,7 @@ static int cr_interception(struct vcpu_svm *svm)
 			kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 			return 1;
 		}
-		kvm_register_write(&svm->vcpu, reg, val);
+		kvm_register_writel(&svm->vcpu, reg, val);
 		trace_kvm_cr_read(cr, val);
 	}
 	return kvm_complete_insn_gp(&svm->vcpu, err);
@@ -2643,11 +2643,11 @@ static int dr_interception(struct vcpu_svm *svm)
 	dr = svm->vmcb->control.exit_code - SVM_EXIT_READ_DR0;
 	if (dr >= 16) { /* mov to DRn  */
 		dr -= 16;
-		val = kvm_register_read(&svm->vcpu, reg);
+		val = kvm_register_readl(&svm->vcpu, reg);
 		err = kvm_set_dr(&svm->vcpu, dr, val);
 	} else {
 		kvm_get_dr(&svm->vcpu, dr, &val);
-		kvm_register_write(&svm->vcpu, reg, val);
+		kvm_register_writel(&svm->vcpu, reg, val);
 	}
 
 	return kvm_complete_insn_gp(&svm->vcpu, err);

arch/x86/mm/fault.c

@@ -836,8 +836,8 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 
 	if (si_code == SEGV_PKUERR)
 		force_sig_pkuerr((void __user *)address, pkey);
-
+	else
-	force_sig_fault(SIGSEGV, si_code, (void __user *)address);
+		force_sig_fault(SIGSEGV, si_code, (void __user *)address);
 
 	local_irq_disable();
 }

arch/x86/mm/mem_encrypt_identity.c

@@ -504,10 +504,6 @@ void __init sme_enable(struct boot_params *bp)
 #define AMD_SME_BIT	BIT(0)
 #define AMD_SEV_BIT	BIT(1)
 
-	/* Check the SEV MSR whether SEV or SME is enabled */
-	sev_status   = __rdmsr(MSR_AMD64_SEV);
-	feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT;
-
 	/*
 	 * Check for the SME/SEV feature:
 	 *   CPUID Fn8000_001F[EAX]
@@ -519,11 +515,16 @@ void __init sme_enable(struct boot_params *bp)
 	eax = 0x8000001f;
 	ecx = 0;
 	native_cpuid(&eax, &ebx, &ecx, &edx);
-	if (!(eax & feature_mask))
+	/* Check whether SEV or SME is supported */
+	if (!(eax & (AMD_SEV_BIT | AMD_SME_BIT)))
 		return;
 
 	me_mask = 1UL << (ebx & 0x3f);
 
+	/* Check the SEV MSR whether SEV or SME is enabled */
+	sev_status   = __rdmsr(MSR_AMD64_SEV);
+	feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT;
+
 	/* Check if memory encryption is enabled */
 	if (feature_mask == AMD_SME_BIT) {
 		/*

drivers/acpi/acpica/utdelete.c

@@ -285,6 +285,14 @@ static void acpi_ut_delete_internal_obj(union acpi_operand_object *object)
 		}
 		break;
 
+	case ACPI_TYPE_LOCAL_ADDRESS_HANDLER:
+
+		ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS,
+				  "***** Address handler %p\n", object));
+
+		acpi_os_delete_mutex(object->address_space.context_mutex);
+		break;
+
 	default:
 
 		break;

drivers/bus/ti-sysc.c

@@ -1334,6 +1334,34 @@ static int __maybe_unused sysc_runtime_resume(struct device *dev)
 	return error;
 }
 
+static int sysc_reinit_module(struct sysc *ddata, bool leave_enabled)
+{
+	struct device *dev = ddata->dev;
+	int error;
+
+	/* Disable target module if it is enabled */
+	if (ddata->enabled) {
+		error = sysc_runtime_suspend(dev);
+		if (error)
+			dev_warn(dev, "reinit suspend failed: %i\n", error);
+	}
+
+	/* Enable target module */
+	error = sysc_runtime_resume(dev);
+	if (error)
+		dev_warn(dev, "reinit resume failed: %i\n", error);
+
+	if (leave_enabled)
+		return error;
+
+	/* Disable target module if no leave_enabled was set */
+	error = sysc_runtime_suspend(dev);
+	if (error)
+		dev_warn(dev, "reinit suspend failed: %i\n", error);
+
+	return error;
+}
+
 static int __maybe_unused sysc_noirq_suspend(struct device *dev)
 {
 	struct sysc *ddata;
@@ -1344,12 +1372,18 @@ static int __maybe_unused sysc_noirq_suspend(struct device *dev)
 	    (SYSC_QUIRK_LEGACY_IDLE | SYSC_QUIRK_NO_IDLE))
 		return 0;
 
-	return pm_runtime_force_suspend(dev);
+	if (!ddata->enabled)
+		return 0;
+
+	ddata->needs_resume = 1;
+
+	return sysc_runtime_suspend(dev);
 }
 
 static int __maybe_unused sysc_noirq_resume(struct device *dev)
 {
 	struct sysc *ddata;
+	int error = 0;
 
 	ddata = dev_get_drvdata(dev);
 
@@ -1357,7 +1391,19 @@ static int __maybe_unused sysc_noirq_resume(struct device *dev)
 	    (SYSC_QUIRK_LEGACY_IDLE | SYSC_QUIRK_NO_IDLE))
 		return 0;
 
-	return pm_runtime_force_resume(dev);
+	if (ddata->cfg.quirks & SYSC_QUIRK_REINIT_ON_RESUME) {
+		error = sysc_reinit_module(ddata, ddata->needs_resume);
+		if (error)
+			dev_warn(dev, "noirq_resume failed: %i\n", error);
+	} else if (ddata->needs_resume) {
+		error = sysc_runtime_resume(dev);
+		if (error)
+			dev_warn(dev, "noirq_resume failed: %i\n", error);
+	}
+
+	ddata->needs_resume = 0;
+
+	return error;
 }
 
 static const struct dev_pm_ops sysc_pm_ops = {
@@ -1408,9 +1454,9 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = {
 		   SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE),
 	/* Uarts on omap4 and later */
 	SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x50411e03, 0xffff00ff,
-		   SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE),
+		   SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE),
 	SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x47422e03, 0xffffffff,
-		   SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE),
+		   SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE),
 
 	/* Quirks that need to be set based on the module address */
 	SYSC_QUIRK("mcpdm", 0x40132000, 0, 0x10, -ENODEV, 0x50000800, 0xffffffff,
@@ -1466,7 +1512,8 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = {
 	SYSC_QUIRK("usb_otg_hs", 0, 0x400, 0x404, 0x408, 0x00000050,
 		   0xffffffff, SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY),
 	SYSC_QUIRK("usb_otg_hs", 0, 0, 0x10, -ENODEV, 0x4ea2080d, 0xffffffff,
-		   SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY),
+		   SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY |
+		   SYSC_QUIRK_REINIT_ON_RESUME),
 	SYSC_QUIRK("wdt", 0, 0, 0x10, 0x14, 0x502a0500, 0xfffff0f0,
 		   SYSC_MODULE_QUIRK_WDT),
 	/* PRUSS on am3, am4 and am5 */

drivers/dma/idxd/init.c

@@ -675,12 +675,12 @@ static int __init idxd_init_module(void)
 	 * If the CPU does not support MOVDIR64B or ENQCMDS, there's no point in
 	 * enumerating the device. We can not utilize it.
 	 */
-	if (!boot_cpu_has(X86_FEATURE_MOVDIR64B)) {
+	if (!cpu_feature_enabled(X86_FEATURE_MOVDIR64B)) {
 		pr_warn("idxd driver failed to load without MOVDIR64B.\n");
 		return -ENODEV;
 	}
 
-	if (!boot_cpu_has(X86_FEATURE_ENQCMD))
+	if (!cpu_feature_enabled(X86_FEATURE_ENQCMD))
 		pr_warn("Platform does not have ENQCMD(S) support.\n");
 	else
 		support_enqcmd = true;

drivers/firmware/efi/cper.c

@@ -276,8 +276,7 @@ static int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg)
 	if (!msg || !(mem->validation_bits & CPER_MEM_VALID_MODULE_HANDLE))
 		return 0;
 
-	n = 0;
+	len = CPER_REC_LEN;
-	len = CPER_REC_LEN - 1;
 	dmi_memdev_name(mem->mem_dev_handle, &bank, &device);
 	if (bank && device)
 		n = snprintf(msg, len, "DIMM location: %s %s ", bank, device);
@@ -286,7 +285,6 @@ static int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg)
 			     "DIMM location: not present. DMI handle: 0x%.4x ",
 			     mem->mem_dev_handle);
 
-	msg[n] = '\0';
 	return n;
 }
 

drivers/firmware/efi/fdtparams.c

@@ -98,6 +98,9 @@ u64 __init efi_get_fdt_params(struct efi_memory_map_data *mm)
 	BUILD_BUG_ON(ARRAY_SIZE(target) != ARRAY_SIZE(name));
 	BUILD_BUG_ON(ARRAY_SIZE(target) != ARRAY_SIZE(dt_params[0].params));
 
+	if (!fdt)
+		return 0;
+
 	for (i = 0; i < ARRAY_SIZE(dt_params); i++) {
 		node = fdt_path_offset(fdt, dt_params[i].path);
 		if (node < 0)

drivers/firmware/efi/libstub/file.c

@@ -103,7 +103,7 @@ static int find_file_option(const efi_char16_t *cmdline, int cmdline_len,
 		return 0;
 
 	/* Skip any leading slashes */
-	while (cmdline[i] == L'/' || cmdline[i] == L'\\')
+	while (i < cmdline_len && (cmdline[i] == L'/' || cmdline[i] == L'\\'))
 		i++;
 
 	while (--result_len > 0 && i < cmdline_len) {

drivers/firmware/efi/memattr.c

@@ -67,11 +67,6 @@ static bool entry_is_valid(const efi_memory_desc_t *in, efi_memory_desc_t *out)
 		return false;
 	}
 
-	if (!(in->attribute & (EFI_MEMORY_RO | EFI_MEMORY_XP))) {
-		pr_warn("Entry attributes invalid: RO and XP bits both cleared\n");
-		return false;
-	}
-
 	if (PAGE_SIZE > EFI_PAGE_SIZE &&
 	    (!PAGE_ALIGNED(in->phys_addr) ||
 	     !PAGE_ALIGNED(in->num_pages << EFI_PAGE_SHIFT))) {

drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c

@@ -337,7 +337,6 @@ static int amdgpu_ctx_query2(struct amdgpu_device *adev,
 {
 	struct amdgpu_ctx *ctx;
 	struct amdgpu_ctx_mgr *mgr;
-	unsigned long ras_counter;
 
 	if (!fpriv)
 		return -EINVAL;
@@ -362,21 +361,6 @@ static int amdgpu_ctx_query2(struct amdgpu_device *adev,
 	if (atomic_read(&ctx->guilty))
 		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_GUILTY;
 
-	/*query ue count*/
-	ras_counter = amdgpu_ras_query_error_count(adev, false);
-	/*ras counter is monotonic increasing*/
-	if (ras_counter != ctx->ras_counter_ue) {
-		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RAS_UE;
-		ctx->ras_counter_ue = ras_counter;
-	}
-
-	/*query ce count*/
-	ras_counter = amdgpu_ras_query_error_count(adev, true);
-	if (ras_counter != ctx->ras_counter_ce) {
-		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RAS_CE;
-		ctx->ras_counter_ce = ras_counter;
-	}
-
 	mutex_unlock(&mgr->lock);
 	return 0;
 }

drivers/gpu/drm/amd/amdgpu/amdgpu_display.c

@@ -944,6 +944,7 @@ amdgpu_display_user_framebuffer_create(struct drm_device *dev,
 	domains = amdgpu_display_supported_domains(drm_to_adev(dev), bo->flags);
 	if (obj->import_attach && !(domains & AMDGPU_GEM_DOMAIN_GTT)) {
 		drm_dbg_kms(dev, "Cannot create framebuffer from imported dma_buf\n");
+		drm_gem_object_put(obj);
 		return ERR_PTR(-EINVAL);
 	}
 

drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c

@@ -187,14 +187,14 @@ static int jpeg_v2_5_hw_init(void *handle)
 static int jpeg_v2_5_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring;
 	int i;
 
+	cancel_delayed_work_sync(&adev->vcn.idle_work);
+
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
 		if (adev->jpeg.harvest_config & (1 << i))
 			continue;
 
-		ring = &adev->jpeg.inst[i].ring_dec;
 		if (adev->jpeg.cur_state != AMD_PG_STATE_GATE &&
 		      RREG32_SOC15(JPEG, i, mmUVD_JRBC_STATUS))
 			jpeg_v2_5_set_powergating_state(adev, AMD_PG_STATE_GATE);

drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c

@@ -159,9 +159,9 @@ static int jpeg_v3_0_hw_init(void *handle)
 static int jpeg_v3_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring;
 
-	ring = &adev->jpeg.inst->ring_dec;
+	cancel_delayed_work_sync(&adev->vcn.idle_work);
+
 	if (adev->jpeg.cur_state != AMD_PG_STATE_GATE &&
 	      RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS))
 		jpeg_v3_0_set_powergating_state(adev, AMD_PG_STATE_GATE);

drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c

@@ -357,6 +357,7 @@ static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unpin(bo);
 	amdgpu_bo_unreserve(bo);
 	amdgpu_bo_unref(&bo);
 	return r;

drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c

@@ -367,15 +367,14 @@ static int vcn_v3_0_hw_init(void *handle)
 static int vcn_v3_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring;
 	int i;
 
+	cancel_delayed_work_sync(&adev->vcn.idle_work);
+
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
-		ring = &adev->vcn.inst[i].ring_dec;
-
 		if (!amdgpu_sriov_vf(adev)) {
 			if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
 					(adev->vcn.cur_state != AMD_PG_STATE_GATE &&

drivers/gpu/drm/i915/selftests/i915_request.c

@@ -1392,8 +1392,8 @@ static int live_breadcrumbs_smoketest(void *arg)
 
 	for (n = 0; n < smoke[0].ncontexts; n++) {
 		smoke[0].contexts[n] = live_context(i915, file);
-		if (!smoke[0].contexts[n]) {
+		if (IS_ERR(smoke[0].contexts[n])) {
-			ret = -ENOMEM;
+			ret = PTR_ERR(smoke[0].contexts[n]);
 			goto out_contexts;
 		}
 	}

drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c

@@ -933,8 +933,7 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 		DPU_DEBUG("REG_DMA is not defined");
 	}
 
-	if (of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss"))
+	dpu_kms_parse_data_bus_icc_path(dpu_kms);
-		dpu_kms_parse_data_bus_icc_path(dpu_kms);
 
 	pm_runtime_get_sync(&dpu_kms->pdev->dev);
 

drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c

@@ -31,40 +31,8 @@ struct dpu_mdss {
 	void __iomem *mmio;
 	struct dss_module_power mp;
 	struct dpu_irq_controller irq_controller;
-	struct icc_path *path[2];
-	u32 num_paths;
 };
 
-static int dpu_mdss_parse_data_bus_icc_path(struct drm_device *dev,
-						struct dpu_mdss *dpu_mdss)
-{
-	struct icc_path *path0 = of_icc_get(dev->dev, "mdp0-mem");
-	struct icc_path *path1 = of_icc_get(dev->dev, "mdp1-mem");
-
-	if (IS_ERR_OR_NULL(path0))
-		return PTR_ERR_OR_ZERO(path0);
-
-	dpu_mdss->path[0] = path0;
-	dpu_mdss->num_paths = 1;
-
-	if (!IS_ERR_OR_NULL(path1)) {
-		dpu_mdss->path[1] = path1;
-		dpu_mdss->num_paths++;
-	}
-
-	return 0;
-}
-
-static void dpu_mdss_icc_request_bw(struct msm_mdss *mdss)
-{
-	struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss);
-	int i;
-	u64 avg_bw = dpu_mdss->num_paths ? MAX_BW / dpu_mdss->num_paths : 0;
-
-	for (i = 0; i < dpu_mdss->num_paths; i++)
-		icc_set_bw(dpu_mdss->path[i], avg_bw, kBps_to_icc(MAX_BW));
-}
-
 static void dpu_mdss_irq(struct irq_desc *desc)
 {
 	struct dpu_mdss *dpu_mdss = irq_desc_get_handler_data(desc);
@@ -178,8 +146,6 @@ static int dpu_mdss_enable(struct msm_mdss *mdss)
 	struct dss_module_power *mp = &dpu_mdss->mp;
 	int ret;
 
-	dpu_mdss_icc_request_bw(mdss);
-
 	ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
 	if (ret) {
 		DPU_ERROR("clock enable failed, ret:%d\n", ret);
@@ -213,15 +179,12 @@ static int dpu_mdss_disable(struct msm_mdss *mdss)
 {
 	struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss);
 	struct dss_module_power *mp = &dpu_mdss->mp;
-	int ret, i;
+	int ret;
 
 	ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false);
 	if (ret)
 		DPU_ERROR("clock disable failed, ret:%d\n", ret);
 
-	for (i = 0; i < dpu_mdss->num_paths; i++)
-		icc_set_bw(dpu_mdss->path[i], 0, 0);
-
 	return ret;
 }
 
@@ -232,7 +195,6 @@ static void dpu_mdss_destroy(struct drm_device *dev)
 	struct dpu_mdss *dpu_mdss = to_dpu_mdss(priv->mdss);
 	struct dss_module_power *mp = &dpu_mdss->mp;
 	int irq;
-	int i;
 
 	pm_runtime_suspend(dev->dev);
 	pm_runtime_disable(dev->dev);
@@ -242,9 +204,6 @@ static void dpu_mdss_destroy(struct drm_device *dev)
 	msm_dss_put_clk(mp->clk_config, mp->num_clk);
 	devm_kfree(&pdev->dev, mp->clk_config);
 
-	for (i = 0; i < dpu_mdss->num_paths; i++)
-		icc_put(dpu_mdss->path[i]);
-
 	if (dpu_mdss->mmio)
 		devm_iounmap(&pdev->dev, dpu_mdss->mmio);
 	dpu_mdss->mmio = NULL;
@@ -276,12 +235,6 @@ int dpu_mdss_init(struct drm_device *dev)
 
 	DRM_DEBUG("mapped mdss address space @%pK\n", dpu_mdss->mmio);
 
-	if (!of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss")) {
-		ret = dpu_mdss_parse_data_bus_icc_path(dev, dpu_mdss);
-		if (ret)
-			return ret;
-	}
-
 	mp = &dpu_mdss->mp;
 	ret = msm_dss_parse_clock(pdev, mp);
 	if (ret) {
@@ -307,8 +260,6 @@ int dpu_mdss_init(struct drm_device *dev)
 
 	pm_runtime_enable(dev->dev);
 
-	dpu_mdss_icc_request_bw(priv->mdss);
-
 	return ret;
 
 irq_error:

drivers/hid/amd-sfh-hid/amd_sfh_client.c

@@ -88,6 +88,7 @@ static void amd_sfh_work(struct work_struct *work)
 	sensor_index = req_node->sensor_idx;
 	report_id = req_node->report_id;
 	node_type = req_node->report_type;
+	kfree(req_node);
 
 	if (node_type == HID_FEATURE_REPORT) {
 		report_size = get_feature_report(sensor_index, report_id,

drivers/hid/hid-logitech-hidpp.c

@@ -1262,6 +1262,7 @@ static int hidpp20_battery_map_status_voltage(u8 data[3], int *voltage,
 	int status;
 
 	long flags = (long) data[2];
+	*level = POWER_SUPPLY_CAPACITY_LEVEL_UNKNOWN;
 
 	if (flags & 0x80)
 		switch (flags & 0x07) {

drivers/hid/hid-magicmouse.c

@@ -597,7 +597,7 @@ static int magicmouse_probe(struct hid_device *hdev,
 	if (id->vendor == USB_VENDOR_ID_APPLE &&
 	    id->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2 &&
 	    hdev->type != HID_TYPE_USBMOUSE)
-		return 0;
+		return -ENODEV;
 
 	msc = devm_kzalloc(&hdev->dev, sizeof(*msc), GFP_KERNEL);
 	if (msc == NULL) {

drivers/hid/hid-multitouch.c

@@ -604,9 +604,13 @@ static struct mt_report_data *mt_allocate_report_data(struct mt_device *td,
 		if (!(HID_MAIN_ITEM_VARIABLE & field->flags))
 			continue;
 
-		for (n = 0; n < field->report_count; n++) {
+		if (field->logical == HID_DG_FINGER || td->hdev->group != HID_GROUP_MULTITOUCH_WIN_8) {
-			if (field->usage[n].hid == HID_DG_CONTACTID)
+			for (n = 0; n < field->report_count; n++) {
-				rdata->is_mt_collection = true;
+				if (field->usage[n].hid == HID_DG_CONTACTID) {
+					rdata->is_mt_collection = true;
+					break;
+				}
+			}
 		}
 	}
 

drivers/hid/i2c-hid/i2c-hid-core.c

@@ -45,6 +45,7 @@
 #define I2C_HID_QUIRK_BOGUS_IRQ			BIT(4)
 #define I2C_HID_QUIRK_RESET_ON_RESUME		BIT(5)
 #define I2C_HID_QUIRK_BAD_INPUT_SIZE		BIT(6)
+#define I2C_HID_QUIRK_NO_WAKEUP_AFTER_RESET	BIT(7)
 
 
 /* flags */
@@ -178,6 +179,11 @@ static const struct i2c_hid_quirks {
 		 I2C_HID_QUIRK_RESET_ON_RESUME },
 	{ USB_VENDOR_ID_ITE, I2C_DEVICE_ID_ITE_LENOVO_LEGION_Y720,
 		I2C_HID_QUIRK_BAD_INPUT_SIZE },
+	/*
+	 * Sending the wakeup after reset actually break ELAN touchscreen controller
+	 */
+	{ USB_VENDOR_ID_ELAN, HID_ANY_ID,
+		 I2C_HID_QUIRK_NO_WAKEUP_AFTER_RESET },
 	{ 0, 0 }
 };
 
@@ -461,7 +467,8 @@ static int i2c_hid_hwreset(struct i2c_client *client)
 	}
 
 	/* At least some SIS devices need this after reset */
-	ret = i2c_hid_set_power(client, I2C_HID_PWR_ON);
+	if (!(ihid->quirks & I2C_HID_QUIRK_NO_WAKEUP_AFTER_RESET))
+		ret = i2c_hid_set_power(client, I2C_HID_PWR_ON);
 
 out_unlock:
 	mutex_unlock(&ihid->reset_lock);
@@ -990,8 +997,8 @@ int i2c_hid_core_probe(struct i2c_client *client, struct i2chid_ops *ops,
 	hid->vendor = le16_to_cpu(ihid->hdesc.wVendorID);
 	hid->product = le16_to_cpu(ihid->hdesc.wProductID);
 
-	snprintf(hid->name, sizeof(hid->name), "%s %04hX:%04hX",
+	snprintf(hid->name, sizeof(hid->name), "%s %04X:%04X",
-		 client->name, hid->vendor, hid->product);
+		 client->name, (u16)hid->vendor, (u16)hid->product);
 	strlcpy(hid->phys, dev_name(&client->dev), sizeof(hid->phys));
 
 	ihid->quirks = i2c_hid_lookup_quirk(hid->vendor, hid->product);

drivers/hid/usbhid/hid-pidff.c

@@ -1292,6 +1292,7 @@ int hid_pidff_init(struct hid_device *hid)
 
 	if (pidff->pool[PID_DEVICE_MANAGED_POOL].value &&
 	    pidff->pool[PID_DEVICE_MANAGED_POOL].value[0] == 0) {
+		error = -EPERM;
 		hid_notice(hid,
 			   "device does not support device managed pool\n");
 		goto fail;

drivers/hwmon/dell-smm-hwmon.c

@@ -838,10 +838,10 @@ static struct attribute *i8k_attrs[] = {
 static umode_t i8k_is_visible(struct kobject *kobj, struct attribute *attr,
 			      int index)
 {
-	if (disallow_fan_support && index >= 8)
+	if (disallow_fan_support && index >= 20)
 		return 0;
 	if (disallow_fan_type_call &&
-	    (index == 9 || index == 12 || index == 15))
+	    (index == 21 || index == 25 || index == 28))
 		return 0;
 	if (index >= 0 && index <= 1 &&
 	    !(i8k_hwmon_flags & I8K_HWMON_HAVE_TEMP1))

drivers/hwmon/pmbus/isl68137.c

@@ -244,8 +244,8 @@ static int isl68137_probe(struct i2c_client *client)
 		info->read_word_data = raa_dmpvr2_read_word_data;
 		break;
 	case raa_dmpvr2_2rail_nontc:
-		info->func[0] &= ~PMBUS_HAVE_TEMP;
+		info->func[0] &= ~PMBUS_HAVE_TEMP3;
-		info->func[1] &= ~PMBUS_HAVE_TEMP;
+		info->func[1] &= ~PMBUS_HAVE_TEMP3;
 		fallthrough;
 	case raa_dmpvr2_2rail:
 		info->pages = 2;

drivers/i2c/busses/i2c-qcom-geni.c

@@ -650,6 +650,14 @@ static int geni_i2c_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static void geni_i2c_shutdown(struct platform_device *pdev)
+{
+	struct geni_i2c_dev *gi2c = platform_get_drvdata(pdev);
+
+	/* Make client i2c transfers start failing */
+	i2c_mark_adapter_suspended(&gi2c->adap);
+}
+
 static int __maybe_unused geni_i2c_runtime_suspend(struct device *dev)
 {
 	int ret;
@@ -690,6 +698,8 @@ static int __maybe_unused geni_i2c_suspend_noirq(struct device *dev)
 {
 	struct geni_i2c_dev *gi2c = dev_get_drvdata(dev);
 
+	i2c_mark_adapter_suspended(&gi2c->adap);
+
 	if (!gi2c->suspended) {
 		geni_i2c_runtime_suspend(dev);
 		pm_runtime_disable(dev);
@@ -699,8 +709,16 @@ static int __maybe_unused geni_i2c_suspend_noirq(struct device *dev)
 	return 0;
 }
 
+static int __maybe_unused geni_i2c_resume_noirq(struct device *dev)
+{
+	struct geni_i2c_dev *gi2c = dev_get_drvdata(dev);
+
+	i2c_mark_adapter_resumed(&gi2c->adap);
+	return 0;
+}
+
 static const struct dev_pm_ops geni_i2c_pm_ops = {
-	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(geni_i2c_suspend_noirq, NULL)
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(geni_i2c_suspend_noirq, geni_i2c_resume_noirq)
 	SET_RUNTIME_PM_OPS(geni_i2c_runtime_suspend, geni_i2c_runtime_resume,
 									NULL)
 };
@@ -714,6 +732,7 @@ MODULE_DEVICE_TABLE(of, geni_i2c_dt_match);
 static struct platform_driver geni_i2c_driver = {
 	.probe  = geni_i2c_probe,
 	.remove = geni_i2c_remove,
+	.shutdown = geni_i2c_shutdown,
 	.driver = {
 		.name = "geni_i2c",
 		.pm = &geni_i2c_pm_ops,

drivers/media/i2c/imx477.c

@@ -1282,7 +1282,7 @@ static void imx477_adjust_exposure_range(struct imx477 *imx477)
 
 	/* Honour the VBLANK limits when setting exposure. */
 	exposure_max = imx477->mode->height + imx477->vblank->val -
-		       (IMX477_EXPOSURE_OFFSET << imx477->long_exp_shift);
+		       IMX477_EXPOSURE_OFFSET;
 	exposure_def = min(exposure_max, imx477->exposure->val);
 	__v4l2_ctrl_modify_range(imx477->exposure, imx477->exposure->minimum,
 				 exposure_max, imx477->exposure->step,

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

@@ -2177,8 +2177,6 @@ int cxgb4_update_mac_filt(struct port_info *pi, unsigned int viid,
 			  bool persistent, u8 *smt_idx);
 int cxgb4_get_msix_idx_from_bmap(struct adapter *adap);
 void cxgb4_free_msix_idx_in_bmap(struct adapter *adap, u32 msix_idx);
-int cxgb_open(struct net_device *dev);
-int cxgb_close(struct net_device *dev);
 void cxgb4_enable_rx(struct adapter *adap, struct sge_rspq *q);
 void cxgb4_quiesce_rx(struct sge_rspq *q);
 int cxgb4_port_mirror_alloc(struct net_device *dev);

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

@@ -2834,7 +2834,7 @@ static void cxgb_down(struct adapter *adapter)
 /*
  * net_device operations
  */
-int cxgb_open(struct net_device *dev)
+static int cxgb_open(struct net_device *dev)
 {
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
@@ -2882,7 +2882,7 @@ int cxgb_open(struct net_device *dev)
 	return err;
 }
 
-int cxgb_close(struct net_device *dev)
+static int cxgb_close(struct net_device *dev)
 {
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;

drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c

@@ -997,20 +997,16 @@ int cxgb4_tc_flower_destroy(struct net_device *dev,
 	if (!ch_flower)
 		return -ENOENT;
 
+	rhashtable_remove_fast(&adap->flower_tbl, &ch_flower->node,
+			       adap->flower_ht_params);
+
 	ret = cxgb4_flow_rule_destroy(dev, ch_flower->fs.tc_prio,
 				      &ch_flower->fs, ch_flower->filter_id);
 	if (ret)
-		goto err;
+		netdev_err(dev, "Flow rule destroy failed for tid: %u, ret: %d",
+			   ch_flower->filter_id, ret);
 
-	ret = rhashtable_remove_fast(&adap->flower_tbl, &ch_flower->node,
-				     adap->flower_ht_params);
-	if (ret) {
-		netdev_err(dev, "Flow remove from rhashtable failed");
-		goto err;
-	}
 	kfree_rcu(ch_flower, rcu);
-
-err:
 	return ret;
 }
 

drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c

@@ -589,7 +589,8 @@ int cxgb4_setup_tc_mqprio(struct net_device *dev,
 	 * down before configuring tc params.
 	 */
 	if (netif_running(dev)) {
-		cxgb_close(dev);
+		netif_tx_stop_all_queues(dev);
+		netif_carrier_off(dev);
 		needs_bring_up = true;
 	}
 
@@ -615,8 +616,10 @@ int cxgb4_setup_tc_mqprio(struct net_device *dev,
 	}
 
 out:
-	if (needs_bring_up)
+	if (needs_bring_up) {
-		cxgb_open(dev);
+		netif_tx_start_all_queues(dev);
+		netif_carrier_on(dev);
+	}
 
 	mutex_unlock(&adap->tc_mqprio->mqprio_mutex);
 	return ret;

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

@@ -2556,6 +2556,12 @@ int cxgb4_ethofld_send_flowc(struct net_device *dev, u32 eotid, u32 tc)
 	if (!eosw_txq)
 		return -ENOMEM;
 
+	if (!(adap->flags & CXGB4_FW_OK)) {
+		/* Don't stall caller when access to FW is lost */
+		complete(&eosw_txq->completion);
+		return -EIO;
+	}
+
 	skb = alloc_skb(len, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -2313,15 +2313,20 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 	case XDP_TX:
 		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
 		result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring);
+		if (result == I40E_XDP_CONSUMED)
+			goto out_failure;
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
+		if (err)
+			goto out_failure;
+		result = I40E_XDP_REDIR;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough; /* handle aborts by dropping packet */
 	case XDP_DROP:

drivers/net/ethernet/intel/i40e/i40e_xsk.c

@@ -160,21 +160,28 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 
+	if (likely(act == XDP_REDIRECT)) {
+		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
+		if (err)
+			goto out_failure;
+		rcu_read_unlock();
+		return I40E_XDP_REDIR;
+	}
+
 	switch (act) {
 	case XDP_PASS:
 		break;
 	case XDP_TX:
 		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
 		result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring);
-		break;
+		if (result == I40E_XDP_CONSUMED)
-	case XDP_REDIRECT:
+			goto out_failure;
-		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough; /* handle aborts by dropping packet */
 	case XDP_DROP:

drivers/net/ethernet/intel/ice/ice.h

@@ -325,6 +325,7 @@ struct ice_vsi {
 	struct ice_tc_cfg tc_cfg;
 	struct bpf_prog *xdp_prog;
 	struct ice_ring **xdp_rings;	 /* XDP ring array */
+	unsigned long *af_xdp_zc_qps;	 /* tracks AF_XDP ZC enabled qps */
 	u16 num_xdp_txq;		 /* Used XDP queues */
 	u8 xdp_mapping_mode;		 /* ICE_MAP_MODE_[CONTIG|SCATTER] */
 
@@ -534,15 +535,16 @@ static inline void ice_set_ring_xdp(struct ice_ring *ring)
  */
 static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_ring *ring)
 {
+	struct ice_vsi *vsi = ring->vsi;
 	u16 qid = ring->q_index;
 
 	if (ice_ring_is_xdp(ring))
-		qid -= ring->vsi->num_xdp_txq;
+		qid -= vsi->num_xdp_txq;
 
-	if (!ice_is_xdp_ena_vsi(ring->vsi))
+	if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps))
 		return NULL;
 
-	return xsk_get_pool_from_qid(ring->vsi->netdev, qid);
+	return xsk_get_pool_from_qid(vsi->netdev, qid);
 }
 
 /**

drivers/net/ethernet/intel/ice/ice_ethtool.c

@@ -1797,49 +1797,6 @@ ice_phy_type_to_ethtool(struct net_device *netdev,
 		ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB,
 						100000baseKR4_Full);
 	}
-
-	/* Autoneg PHY types */
-	if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_T ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_T ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_T ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_T ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR_S ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR1 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR_S ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_CR4 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) {
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     Autoneg);
-	}
-	if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CR2 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR2 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CP ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4) {
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     Autoneg);
-	}
-	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR4 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR4 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4 ||
-	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2) {
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     Autoneg);
-	}
 }
 
 #define TEST_SET_BITS_TIMEOUT	50
@@ -1996,9 +1953,7 @@ ice_get_link_ksettings(struct net_device *netdev,
 		ks->base.port = PORT_TP;
 		break;
 	case ICE_MEDIA_BACKPLANE:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
 		ethtool_link_ksettings_add_link_mode(ks, supported, Backplane);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     Backplane);
 		ks->base.port = PORT_NONE;
@@ -2073,6 +2028,12 @@ ice_get_link_ksettings(struct net_device *netdev,
 	if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN)
 		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
 
+	/* Set supported and advertised autoneg */
+	if (ice_is_phy_caps_an_enabled(caps)) {
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+	}
+
 done:
 	kfree(caps);
 	return err;

drivers/net/ethernet/intel/ice/ice_hw_autogen.h

@@ -31,6 +31,7 @@
 #define PF_FW_ATQLEN_ATQOVFL_M			BIT(29)
 #define PF_FW_ATQLEN_ATQCRIT_M			BIT(30)
 #define VF_MBX_ARQLEN(_VF)			(0x0022BC00 + ((_VF) * 4))
+#define VF_MBX_ATQLEN(_VF)			(0x0022A800 + ((_VF) * 4))
 #define PF_FW_ATQLEN_ATQENABLE_M		BIT(31)
 #define PF_FW_ATQT				0x00080400
 #define PF_MBX_ARQBAH				0x0022E400

drivers/net/ethernet/intel/ice/ice_lib.c

@@ -105,8 +105,14 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi)
 	if (!vsi->q_vectors)
 		goto err_vectors;
 
+	vsi->af_xdp_zc_qps = bitmap_zalloc(max_t(int, vsi->alloc_txq, vsi->alloc_rxq), GFP_KERNEL);
+	if (!vsi->af_xdp_zc_qps)
+		goto err_zc_qps;
+
 	return 0;
 
+err_zc_qps:
+	devm_kfree(dev, vsi->q_vectors);
 err_vectors:
 	devm_kfree(dev, vsi->rxq_map);
 err_rxq_map:
@@ -192,6 +198,8 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id)
 		break;
 	case ICE_VSI_VF:
 		vf = &pf->vf[vsi->vf_id];
+		if (vf->num_req_qs)
+			vf->num_vf_qs = vf->num_req_qs;
 		vsi->alloc_txq = vf->num_vf_qs;
 		vsi->alloc_rxq = vf->num_vf_qs;
 		/* pf->num_msix_per_vf includes (VF miscellaneous vector +
@@ -286,6 +294,10 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi)
 
 	dev = ice_pf_to_dev(pf);
 
+	if (vsi->af_xdp_zc_qps) {
+		bitmap_free(vsi->af_xdp_zc_qps);
+		vsi->af_xdp_zc_qps = NULL;
+	}
 	/* free the ring and vector containers */
 	if (vsi->q_vectors) {
 		devm_kfree(dev, vsi->q_vectors);

drivers/net/ethernet/intel/ice/ice_txrx.c

@@ -523,7 +523,7 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp,
 	    struct bpf_prog *xdp_prog)
 {
 	struct ice_ring *xdp_ring;
-	int err;
+	int err, result;
 	u32 act;
 
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
@@ -532,14 +532,20 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp,
 		return ICE_XDP_PASS;
 	case XDP_TX:
 		xdp_ring = rx_ring->vsi->xdp_rings[smp_processor_id()];
-		return ice_xmit_xdp_buff(xdp, xdp_ring);
+		result = ice_xmit_xdp_buff(xdp, xdp_ring);
+		if (result == ICE_XDP_CONSUMED)
+			goto out_failure;
+		return result;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		return !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED;
+		if (err)
+			goto out_failure;
+		return ICE_XDP_REDIR;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
 	case XDP_DROP:
@@ -2331,6 +2337,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
 	struct ice_tx_offload_params offload = { 0 };
 	struct ice_vsi *vsi = tx_ring->vsi;
 	struct ice_tx_buf *first;
+	struct ethhdr *eth;
 	unsigned int count;
 	int tso, csum;
 
@@ -2377,7 +2384,9 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
 		goto out_drop;
 
 	/* allow CONTROL frames egress from main VSI if FW LLDP disabled */
-	if (unlikely(skb->priority == TC_PRIO_CONTROL &&
+	eth = (struct ethhdr *)skb_mac_header(skb);
+	if (unlikely((skb->priority == TC_PRIO_CONTROL ||
+		      eth->h_proto == htons(ETH_P_LLDP)) &&
 		     vsi->type == ICE_VSI_PF &&
 		     vsi->port_info->qos_cfg.is_sw_lldp))
 		offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |

drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c

@@ -435,13 +435,15 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr)
 	 */
 	clear_bit(ICE_VF_STATE_INIT, vf->vf_states);
 
-	/* VF_MBX_ARQLEN is cleared by PFR, so the driver needs to clear it
+	/* VF_MBX_ARQLEN and VF_MBX_ATQLEN are cleared by PFR, so the driver
-	 * in the case of VFR. If this is done for PFR, it can mess up VF
+	 * needs to clear them in the case of VFR/VFLR. If this is done for
-	 * resets because the VF driver may already have started cleanup
+	 * PFR, it can mess up VF resets because the VF driver may already
-	 * by the time we get here.
+	 * have started cleanup by the time we get here.
 	 */
-	if (!is_pfr)
+	if (!is_pfr) {
 		wr32(hw, VF_MBX_ARQLEN(vf->vf_id), 0);
+		wr32(hw, VF_MBX_ATQLEN(vf->vf_id), 0);
+	}
 
 	/* In the case of a VFLR, the HW has already reset the VF and we
 	 * just need to clean up, so don't hit the VFRTRIG register.
@@ -1375,7 +1377,12 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 	}
 
 	ice_vf_pre_vsi_rebuild(vf);
-	ice_vf_rebuild_vsi_with_release(vf);
+
+	if (ice_vf_rebuild_vsi_with_release(vf)) {
+		dev_err(dev, "Failed to release and setup the VF%u's VSI\n", vf->vf_id);
+		return false;
+	}
+
 	ice_vf_post_vsi_rebuild(vf);
 
 	return true;

drivers/net/ethernet/intel/ice/ice_xsk.c

@@ -273,6 +273,7 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid)
 	if (!pool)
 		return -EINVAL;
 
+	clear_bit(qid, vsi->af_xdp_zc_qps);
 	xsk_pool_dma_unmap(pool, ICE_RX_DMA_ATTR);
 
 	return 0;
@@ -303,6 +304,8 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 	if (err)
 		return err;
 
+	set_bit(qid, vsi->af_xdp_zc_qps);
+
 	return 0;
 }
 
@@ -473,21 +476,29 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
+
+	if (likely(act == XDP_REDIRECT)) {
+		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
+		if (err)
+			goto out_failure;
+		rcu_read_unlock();
+		return ICE_XDP_REDIR;
+	}
+
 	switch (act) {
 	case XDP_PASS:
 		break;
 	case XDP_TX:
 		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->q_index];
 		result = ice_xmit_xdp_buff(xdp, xdp_ring);
-		break;
+		if (result == ICE_XDP_CONSUMED)
-	case XDP_REDIRECT:
+			goto out_failure;
-		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
 	case XDP_DROP:

drivers/net/ethernet/intel/igb/igb.h

@@ -749,7 +749,7 @@ void igb_ptp_rx_hang(struct igb_adapter *adapter);
 void igb_ptp_tx_hang(struct igb_adapter *adapter);
 void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb);
 int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
-			struct sk_buff *skb);
+			ktime_t *timestamp);
 int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
 int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
 void igb_set_flag_queue_pairs(struct igb_adapter *, const u32);

drivers/net/ethernet/intel/igb/igb_main.c

@@ -8281,7 +8281,7 @@ static void igb_add_rx_frag(struct igb_ring *rx_ring,
 static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 					 struct igb_rx_buffer *rx_buffer,
 					 struct xdp_buff *xdp,
-					 union e1000_adv_rx_desc *rx_desc)
+					 ktime_t timestamp)
 {
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
@@ -8301,12 +8301,8 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 	if (unlikely(!skb))
 		return NULL;
 
-	if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) {
+	if (timestamp)
-		if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb)) {
+		skb_hwtstamps(skb)->hwtstamp = timestamp;
-			xdp->data += IGB_TS_HDR_LEN;
-			size -= IGB_TS_HDR_LEN;
-		}
-	}
 
 	/* Determine available headroom for copy */
 	headlen = size;
@@ -8337,7 +8333,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
 				     struct igb_rx_buffer *rx_buffer,
 				     struct xdp_buff *xdp,
-				     union e1000_adv_rx_desc *rx_desc)
+				     ktime_t timestamp)
 {
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
@@ -8364,11 +8360,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
 	if (metasize)
 		skb_metadata_set(skb, metasize);
 
-	/* pull timestamp out of packet data */
+	if (timestamp)
-	if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
+		skb_hwtstamps(skb)->hwtstamp = timestamp;
-		if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb))
-			__skb_pull(skb, IGB_TS_HDR_LEN);
-	}
 
 	/* update buffer offset */
 #if (PAGE_SIZE < 8192)
@@ -8402,18 +8395,20 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter,
 		break;
 	case XDP_TX:
 		result = igb_xdp_xmit_back(adapter, xdp);
+		if (result == IGB_XDP_CONSUMED)
+			goto out_failure;
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
-		if (!err)
+		if (err)
-			result = IGB_XDP_REDIR;
+			goto out_failure;
-		else
+		result = IGB_XDP_REDIR;
-			result = IGB_XDP_CONSUMED;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
 	case XDP_DROP:
@@ -8683,7 +8678,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	while (likely(total_packets < budget)) {
 		union e1000_adv_rx_desc *rx_desc;
 		struct igb_rx_buffer *rx_buffer;
+		ktime_t timestamp = 0;
+		int pkt_offset = 0;
 		unsigned int size;
+		void *pktbuf;
 
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IGB_RX_BUFFER_WRITE) {
@@ -8703,14 +8701,24 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 		dma_rmb();
 
 		rx_buffer = igb_get_rx_buffer(rx_ring, size, &rx_buf_pgcnt);
+		pktbuf = page_address(rx_buffer->page) + rx_buffer->page_offset;
+
+		/* pull rx packet timestamp if available and valid */
+		if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
+			int ts_hdr_len;
+
+			ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector,
+							 pktbuf, &timestamp);
+
+			pkt_offset += ts_hdr_len;
+			size -= ts_hdr_len;
+		}
 
 		/* retrieve a buffer from the ring */
 		if (!skb) {
-			unsigned int offset = igb_rx_offset(rx_ring);
+			unsigned char *hard_start = pktbuf - igb_rx_offset(rx_ring);
-			unsigned char *hard_start;
+			unsigned int offset = pkt_offset + igb_rx_offset(rx_ring);
 
-			hard_start = page_address(rx_buffer->page) +
-				     rx_buffer->page_offset - offset;
 			xdp_prepare_buff(&xdp, hard_start, offset, size, true);
 #if (PAGE_SIZE > 4096)
 			/* At larger PAGE_SIZE, frame_sz depend on len size */
@@ -8733,10 +8741,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 		} else if (skb)
 			igb_add_rx_frag(rx_ring, rx_buffer, skb, size);
 		else if (ring_uses_build_skb(rx_ring))
-			skb = igb_build_skb(rx_ring, rx_buffer, &xdp, rx_desc);
+			skb = igb_build_skb(rx_ring, rx_buffer, &xdp,
+					    timestamp);
 		else
 			skb = igb_construct_skb(rx_ring, rx_buffer,
-						&xdp, rx_desc);
+						&xdp, timestamp);
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {

drivers/net/ethernet/intel/igb/igb_ptp.c

@@ -856,30 +856,28 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
 	dev_kfree_skb_any(skb);
 }
 
-#define IGB_RET_PTP_DISABLED 1
-#define IGB_RET_PTP_INVALID 2
-
 /**
  * igb_ptp_rx_pktstamp - retrieve Rx per packet timestamp
  * @q_vector: Pointer to interrupt specific structure
  * @va: Pointer to address containing Rx buffer
- * @skb: Buffer containing timestamp and packet
+ * @timestamp: Pointer where timestamp will be stored
  *
  * This function is meant to retrieve a timestamp from the first buffer of an
  * incoming frame.  The value is stored in little endian format starting on
  * byte 8
  *
- * Returns: 0 if success, nonzero if failure
+ * Returns: The timestamp header length or 0 if not available
  **/
 int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
-			struct sk_buff *skb)
+			ktime_t *timestamp)
 {
 	struct igb_adapter *adapter = q_vector->adapter;
+	struct skb_shared_hwtstamps ts;
 	__le64 *regval = (__le64 *)va;
 	int adjust = 0;
 
 	if (!(adapter->ptp_flags & IGB_PTP_ENABLED))
-		return IGB_RET_PTP_DISABLED;
+		return 0;
 
 	/* The timestamp is recorded in little endian format.
 	 * DWORD: 0        1        2        3
@@ -888,10 +886,9 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 
 	/* check reserved dwords are zero, be/le doesn't matter for zero */
 	if (regval[0])
-		return IGB_RET_PTP_INVALID;
+		return 0;
 
-	igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb),
+	igb_ptp_systim_to_hwtstamp(adapter, &ts, le64_to_cpu(regval[1]));
-				   le64_to_cpu(regval[1]));
 
 	/* adjust timestamp for the RX latency based on link speed */
 	if (adapter->hw.mac.type == e1000_i210) {
@@ -907,10 +904,10 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 			break;
 		}
 	}
-	skb_hwtstamps(skb)->hwtstamp =
-		ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust);
 
-	return 0;
+	*timestamp = ktime_sub_ns(ts.hwtstamp, adjust);
+
+	return IGB_TS_HDR_LEN;
 }
 
 /**

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

@@ -2213,23 +2213,23 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 		break;
 	case XDP_TX:
 		xdpf = xdp_convert_buff_to_frame(xdp);
-		if (unlikely(!xdpf)) {
+		if (unlikely(!xdpf))
-			result = IXGBE_XDP_CONSUMED;
+			goto out_failure;
-			break;
-		}
 		result = ixgbe_xmit_xdp_ring(adapter, xdpf);
+		if (result == IXGBE_XDP_CONSUMED)
+			goto out_failure;
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
-		if (!err)
+		if (err)
-			result = IXGBE_XDP_REDIR;
+			goto out_failure;
-		else
+		result = IXGBE_XDP_REDIR;
-			result = IXGBE_XDP_CONSUMED;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough; /* handle aborts by dropping packet */
 	case XDP_DROP:

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

@@ -104,25 +104,30 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 
+	if (likely(act == XDP_REDIRECT)) {
+		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
+		if (err)
+			goto out_failure;
+		rcu_read_unlock();
+		return IXGBE_XDP_REDIR;
+	}
+
 	switch (act) {
 	case XDP_PASS:
 		break;
 	case XDP_TX:
 		xdpf = xdp_convert_buff_to_frame(xdp);
-		if (unlikely(!xdpf)) {
+		if (unlikely(!xdpf))
-			result = IXGBE_XDP_CONSUMED;
+			goto out_failure;
-			break;
-		}
 		result = ixgbe_xmit_xdp_ring(adapter, xdpf);
-		break;
+		if (result == IXGBE_XDP_CONSUMED)
-	case XDP_REDIRECT:
+			goto out_failure;
-		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough; /* handle aborts by dropping packet */
 	case XDP_DROP:

drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c

@@ -1067,11 +1067,14 @@ static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter,
 	case XDP_TX:
 		xdp_ring = adapter->xdp_ring[rx_ring->queue_index];
 		result = ixgbevf_xmit_xdp_ring(xdp_ring, xdp);
+		if (result == IXGBEVF_XDP_CONSUMED)
+			goto out_failure;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
 	case XDP_ABORTED:
+out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough; /* handle aborts by dropping packet */
 	case XDP_DROP:

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

@@ -1632,12 +1632,13 @@ static int mlx5e_set_fecparam(struct net_device *netdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
+	unsigned long fec_bitmap;
 	u16 fec_policy = 0;
 	int mode;
 	int err;
 
-	if (bitmap_weight((unsigned long *)&fecparam->fec,
+	bitmap_from_arr32(&fec_bitmap, &fecparam->fec, sizeof(fecparam->fec) * BITS_PER_BYTE);
-			  ETHTOOL_FEC_LLRS_BIT + 1) > 1)
+	if (bitmap_weight(&fec_bitmap, ETHTOOL_FEC_LLRS_BIT + 1) > 1)
 		return -EOPNOTSUPP;
 
 	for (mode = 0; mode < ARRAY_SIZE(pplm_fec_2_ethtool); mode++) {

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

@@ -1964,11 +1964,13 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 				    misc_parameters);
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_dissector *dissector = rule->match.dissector;
+	enum fs_flow_table_type fs_type;
 	u16 addr_type = 0;
 	u8 ip_proto = 0;
 	u8 *match_level;
 	int err;
 
+	fs_type = mlx5e_is_eswitch_flow(flow) ? FS_FT_FDB : FS_FT_NIC_RX;
 	match_level = outer_match_level;
 
 	if (dissector->used_keys &
@@ -2093,6 +2095,13 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		if (match.mask->vlan_id ||
 		    match.mask->vlan_priority ||
 		    match.mask->vlan_tpid) {
+			if (!MLX5_CAP_FLOWTABLE_TYPE(priv->mdev, ft_field_support.outer_second_vid,
+						     fs_type)) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Matching on CVLAN is not supported");
+				return -EOPNOTSUPP;
+			}
+
 			if (match.key->vlan_tpid == htons(ETH_P_8021AD)) {
 				MLX5_SET(fte_match_set_misc, misc_c,
 					 outer_second_svlan_tag, 1);

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

@@ -349,7 +349,8 @@ esw_setup_slow_path_dest(struct mlx5_flow_destination *dest,
 			 struct mlx5_fs_chains *chains,
 			 int i)
 {
-	flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
+	if (mlx5_chains_ignore_flow_level_supported(chains))
+		flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 	dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dest[i].ft = mlx5_chains_get_tc_end_ft(chains);
 }

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

@@ -354,6 +354,9 @@ static void mlx5_sync_reset_abort_event(struct work_struct *work)
 						      reset_abort_work);
 	struct mlx5_core_dev *dev = fw_reset->dev;
 
+	if (!test_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags))
+		return;
+
 	mlx5_sync_reset_clear_reset_requested(dev, true);
 	mlx5_core_warn(dev, "PCI Sync FW Update Reset Aborted.\n");
 }

drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c

@@ -111,7 +111,7 @@ bool mlx5_chains_prios_supported(struct mlx5_fs_chains *chains)
 	return chains->flags & MLX5_CHAINS_AND_PRIOS_SUPPORTED;
 }
 
-static bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains)
+bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains)
 {
 	return chains->flags & MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED;
 }

drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h

@@ -27,6 +27,7 @@ struct mlx5_chains_attr {
 
 bool
 mlx5_chains_prios_supported(struct mlx5_fs_chains *chains);
+bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains);
 bool
 mlx5_chains_backwards_supported(struct mlx5_fs_chains *chains);
 u32
@@ -72,6 +73,10 @@ mlx5_chains_set_end_ft(struct mlx5_fs_chains *chains,
 
 #else /* CONFIG_MLX5_CLS_ACT */
 
+static inline bool
+mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains)
+{ return false; }
+
 static inline struct mlx5_flow_table *
 mlx5_chains_get_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio,
 		      u32 level) { return ERR_PTR(-EOPNOTSUPP); }

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c

@@ -112,7 +112,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn,
 	int ret;
 
 	ft_attr.table_type = MLX5_FLOW_TABLE_TYPE_FDB;
-	ft_attr.level = dmn->info.caps.max_ft_level - 2;
+	ft_attr.level = min_t(int, dmn->info.caps.max_ft_level - 2,
+			      MLX5_FT_MAX_MULTIPATH_LEVEL);
 	ft_attr.reformat_en = reformat_req;
 	ft_attr.decap_en = reformat_req;
 

drivers/net/wireguard/Makefile

@@ -1,5 +1,4 @@
-ccflags-y := -O3
+ccflags-y := -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt'
-ccflags-y += -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt'
 ccflags-$(CONFIG_WIREGUARD_DEBUG) += -DDEBUG
 wireguard-y := main.o
 wireguard-y += noise.o

drivers/net/wireguard/allowedips.c

@@ -6,6 +6,8 @@
 #include "allowedips.h"
 #include "peer.h"
 
+static struct kmem_cache *node_cache;
+
 static void swap_endian(u8 *dst, const u8 *src, u8 bits)
 {
 	if (bits == 32) {
@@ -28,8 +30,11 @@ static void copy_and_assign_cidr(struct allowedips_node *node, const u8 *src,
 	node->bitlen = bits;
 	memcpy(node->bits, src, bits / 8U);
 }
-#define CHOOSE_NODE(parent, key) \
+
-	parent->bit[(key[parent->bit_at_a] >> parent->bit_at_b) & 1]
+static inline u8 choose(struct allowedips_node *node, const u8 *key)
+{
+	return (key[node->bit_at_a] >> node->bit_at_b) & 1;
+}
 
 static void push_rcu(struct allowedips_node **stack,
 		     struct allowedips_node __rcu *p, unsigned int *len)
@@ -40,6 +45,11 @@ static void push_rcu(struct allowedips_node **stack,
 	}
 }
 
+static void node_free_rcu(struct rcu_head *rcu)
+{
+	kmem_cache_free(node_cache, container_of(rcu, struct allowedips_node, rcu));
+}
+
 static void root_free_rcu(struct rcu_head *rcu)
 {
 	struct allowedips_node *node, *stack[128] = {
@@ -49,7 +59,7 @@ static void root_free_rcu(struct rcu_head *rcu)
 	while (len > 0 && (node = stack[--len])) {
 		push_rcu(stack, node->bit[0], &len);
 		push_rcu(stack, node->bit[1], &len);
-		kfree(node);
+		kmem_cache_free(node_cache, node);
 	}
 }
 
@@ -66,60 +76,6 @@ static void root_remove_peer_lists(struct allowedips_node *root)
 	}
 }
 
-static void walk_remove_by_peer(struct allowedips_node __rcu **top,
-				struct wg_peer *peer, struct mutex *lock)
-{
-#define REF(p) rcu_access_pointer(p)
-#define DEREF(p) rcu_dereference_protected(*(p), lockdep_is_held(lock))
-#define PUSH(p) ({                                                             \
-		WARN_ON(IS_ENABLED(DEBUG) && len >= 128);                      \
-		stack[len++] = p;                                              \
-	})
-
-	struct allowedips_node __rcu **stack[128], **nptr;
-	struct allowedips_node *node, *prev;
-	unsigned int len;
-
-	if (unlikely(!peer || !REF(*top)))
-		return;
-
-	for (prev = NULL, len = 0, PUSH(top); len > 0; prev = node) {
-		nptr = stack[len - 1];
-		node = DEREF(nptr);
-		if (!node) {
-			--len;
-			continue;
-		}
-		if (!prev || REF(prev->bit[0]) == node ||
-		    REF(prev->bit[1]) == node) {
-			if (REF(node->bit[0]))
-				PUSH(&node->bit[0]);
-			else if (REF(node->bit[1]))
-				PUSH(&node->bit[1]);
-		} else if (REF(node->bit[0]) == prev) {
-			if (REF(node->bit[1]))
-				PUSH(&node->bit[1]);
-		} else {
-			if (rcu_dereference_protected(node->peer,
-				lockdep_is_held(lock)) == peer) {
-				RCU_INIT_POINTER(node->peer, NULL);
-				list_del_init(&node->peer_list);
-				if (!node->bit[0] || !node->bit[1]) {
-					rcu_assign_pointer(*nptr, DEREF(
-					       &node->bit[!REF(node->bit[0])]));
-					kfree_rcu(node, rcu);
-					node = DEREF(nptr);
-				}
-			}
-			--len;
-		}
-	}
-
-#undef REF
-#undef DEREF
-#undef PUSH
-}
-
 static unsigned int fls128(u64 a, u64 b)
 {
 	return a ? fls64(a) + 64U : fls64(b);
@@ -159,7 +115,7 @@ static struct allowedips_node *find_node(struct allowedips_node *trie, u8 bits,
 			found = node;
 		if (node->cidr == bits)
 			break;
-		node = rcu_dereference_bh(CHOOSE_NODE(node, key));
+		node = rcu_dereference_bh(node->bit[choose(node, key)]);
 	}
 	return found;
 }
@@ -191,8 +147,7 @@ static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key,
 			   u8 cidr, u8 bits, struct allowedips_node **rnode,
 			   struct mutex *lock)
 {
-	struct allowedips_node *node = rcu_dereference_protected(trie,
+	struct allowedips_node *node = rcu_dereference_protected(trie, lockdep_is_held(lock));
-						lockdep_is_held(lock));
 	struct allowedips_node *parent = NULL;
 	bool exact = false;
 
@@ -202,13 +157,24 @@ static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key,
 			exact = true;
 			break;
 		}
-		node = rcu_dereference_protected(CHOOSE_NODE(parent, key),
+		node = rcu_dereference_protected(parent->bit[choose(parent, key)], lockdep_is_held(lock));
-						 lockdep_is_held(lock));
 	}
 	*rnode = parent;
 	return exact;
 }
 
+static inline void connect_node(struct allowedips_node **parent, u8 bit, struct allowedips_node *node)
+{
+	node->parent_bit_packed = (unsigned long)parent | bit;
+	rcu_assign_pointer(*parent, node);
+}
+
+static inline void choose_and_connect_node(struct allowedips_node *parent, struct allowedips_node *node)
+{
+	u8 bit = choose(parent, node->bits);
+	connect_node(&parent->bit[bit], bit, node);
+}
+
 static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
 	       u8 cidr, struct wg_peer *peer, struct mutex *lock)
 {
@@ -218,13 +184,13 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
 		return -EINVAL;
 
 	if (!rcu_access_pointer(*trie)) {
-		node = kzalloc(sizeof(*node), GFP_KERNEL);
+		node = kmem_cache_zalloc(node_cache, GFP_KERNEL);
 		if (unlikely(!node))
 			return -ENOMEM;
 		RCU_INIT_POINTER(node->peer, peer);
 		list_add_tail(&node->peer_list, &peer->allowedips_list);
 		copy_and_assign_cidr(node, key, cidr, bits);
-		rcu_assign_pointer(*trie, node);
+		connect_node(trie, 2, node);
 		return 0;
 	}
 	if (node_placement(*trie, key, cidr, bits, &node, lock)) {
@@ -233,7 +199,7 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
 		return 0;
 	}
 
-	newnode = kzalloc(sizeof(*newnode), GFP_KERNEL);
+	newnode = kmem_cache_zalloc(node_cache, GFP_KERNEL);
 	if (unlikely(!newnode))
 		return -ENOMEM;
 	RCU_INIT_POINTER(newnode->peer, peer);
@@ -243,10 +209,10 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
 	if (!node) {
 		down = rcu_dereference_protected(*trie, lockdep_is_held(lock));
 	} else {
-		down = rcu_dereference_protected(CHOOSE_NODE(node, key),
+		const u8 bit = choose(node, key);
-						 lockdep_is_held(lock));
+		down = rcu_dereference_protected(node->bit[bit], lockdep_is_held(lock));
 		if (!down) {
-			rcu_assign_pointer(CHOOSE_NODE(node, key), newnode);
+			connect_node(&node->bit[bit], bit, newnode);
 			return 0;
 		}
 	}
@@ -254,30 +220,29 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
 	parent = node;
 
 	if (newnode->cidr == cidr) {
-		rcu_assign_pointer(CHOOSE_NODE(newnode, down->bits), down);
+		choose_and_connect_node(newnode, down);
 		if (!parent)
-			rcu_assign_pointer(*trie, newnode);
+			connect_node(trie, 2, newnode);
 		else
-			rcu_assign_pointer(CHOOSE_NODE(parent, newnode->bits),
+			choose_and_connect_node(parent, newnode);
-					   newnode);
+		return 0;
-	} else {
-		node = kzalloc(sizeof(*node), GFP_KERNEL);
-		if (unlikely(!node)) {
-			list_del(&newnode->peer_list);
-			kfree(newnode);
-			return -ENOMEM;
-		}
-		INIT_LIST_HEAD(&node->peer_list);
-		copy_and_assign_cidr(node, newnode->bits, cidr, bits);
-
-		rcu_assign_pointer(CHOOSE_NODE(node, down->bits), down);
-		rcu_assign_pointer(CHOOSE_NODE(node, newnode->bits), newnode);
-		if (!parent)
-			rcu_assign_pointer(*trie, node);
-		else
-			rcu_assign_pointer(CHOOSE_NODE(parent, node->bits),
-					   node);
 	}
+
+	node = kmem_cache_zalloc(node_cache, GFP_KERNEL);
+	if (unlikely(!node)) {
+		list_del(&newnode->peer_list);
+		kmem_cache_free(node_cache, newnode);
+		return -ENOMEM;
+	}
+	INIT_LIST_HEAD(&node->peer_list);
+	copy_and_assign_cidr(node, newnode->bits, cidr, bits);
+
+	choose_and_connect_node(node, down);
+	choose_and_connect_node(node, newnode);
+	if (!parent)
+		connect_node(trie, 2, node);
+	else
+		choose_and_connect_node(parent, node);
 	return 0;
 }
 
@@ -335,9 +300,41 @@ int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip,
 void wg_allowedips_remove_by_peer(struct allowedips *table,
 				  struct wg_peer *peer, struct mutex *lock)
 {
+	struct allowedips_node *node, *child, **parent_bit, *parent, *tmp;
+	bool free_parent;
+
+	if (list_empty(&peer->allowedips_list))
+		return;
 	++table->seq;
-	walk_remove_by_peer(&table->root4, peer, lock);
+	list_for_each_entry_safe(node, tmp, &peer->allowedips_list, peer_list) {
-	walk_remove_by_peer(&table->root6, peer, lock);
+		list_del_init(&node->peer_list);
+		RCU_INIT_POINTER(node->peer, NULL);
+		if (node->bit[0] && node->bit[1])
+			continue;
+		child = rcu_dereference_protected(node->bit[!rcu_access_pointer(node->bit[0])],
+						  lockdep_is_held(lock));
+		if (child)
+			child->parent_bit_packed = node->parent_bit_packed;
+		parent_bit = (struct allowedips_node **)(node->parent_bit_packed & ~3UL);
+		*parent_bit = child;
+		parent = (void *)parent_bit -
+			 offsetof(struct allowedips_node, bit[node->parent_bit_packed & 1]);
+		free_parent = !rcu_access_pointer(node->bit[0]) &&
+			      !rcu_access_pointer(node->bit[1]) &&
+			      (node->parent_bit_packed & 3) <= 1 &&
+			      !rcu_access_pointer(parent->peer);
+		if (free_parent)
+			child = rcu_dereference_protected(
+					parent->bit[!(node->parent_bit_packed & 1)],
+					lockdep_is_held(lock));
+		call_rcu(&node->rcu, node_free_rcu);
+		if (!free_parent)
+			continue;
+		if (child)
+			child->parent_bit_packed = parent->parent_bit_packed;
+		*(struct allowedips_node **)(parent->parent_bit_packed & ~3UL) = child;
+		call_rcu(&parent->rcu, node_free_rcu);
+	}
 }
 
 int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr)
@@ -374,4 +371,16 @@ struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table,
 	return NULL;
 }
 
+int __init wg_allowedips_slab_init(void)
+{
+	node_cache = KMEM_CACHE(allowedips_node, 0);
+	return node_cache ? 0 : -ENOMEM;
+}
+
+void wg_allowedips_slab_uninit(void)
+{
+	rcu_barrier();
+	kmem_cache_destroy(node_cache);
+}
+
 #include "selftest/allowedips.c"

drivers/net/wireguard/allowedips.h

@@ -15,14 +15,11 @@ struct wg_peer;
 struct allowedips_node {
 	struct wg_peer __rcu *peer;
 	struct allowedips_node __rcu *bit[2];
-	/* While it may seem scandalous that we waste space for v4,
-	 * we're alloc'ing to the nearest power of 2 anyway, so this
-	 * doesn't actually make a difference.
-	 */
-	u8 bits[16] __aligned(__alignof(u64));
 	u8 cidr, bit_at_a, bit_at_b, bitlen;
+	u8 bits[16] __aligned(__alignof(u64));
 
-	/* Keep rarely used list at bottom to be beyond cache line. */
+	/* Keep rarely used members at bottom to be beyond cache line. */
+	unsigned long parent_bit_packed;
 	union {
 		struct list_head peer_list;
 		struct rcu_head rcu;
@@ -33,7 +30,7 @@ struct allowedips {
 	struct allowedips_node __rcu *root4;
 	struct allowedips_node __rcu *root6;
 	u64 seq;
-};
+} __aligned(4); /* We pack the lower 2 bits of &root, but m68k only gives 16-bit alignment. */
 
 void wg_allowedips_init(struct allowedips *table);
 void wg_allowedips_free(struct allowedips *table, struct mutex *mutex);
@@ -56,4 +53,7 @@ struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table,
 bool wg_allowedips_selftest(void);
 #endif
 
+int wg_allowedips_slab_init(void);
+void wg_allowedips_slab_uninit(void);
+
 #endif /* _WG_ALLOWEDIPS_H */

drivers/net/wireguard/main.c

@@ -21,13 +21,22 @@ static int __init mod_init(void)
 {
 	int ret;
 
+	ret = wg_allowedips_slab_init();
+	if (ret < 0)
+		goto err_allowedips;
+
 #ifdef DEBUG
+	ret = -ENOTRECOVERABLE;
 	if (!wg_allowedips_selftest() || !wg_packet_counter_selftest() ||
 	    !wg_ratelimiter_selftest())
-		return -ENOTRECOVERABLE;
+		goto err_peer;
 #endif
 	wg_noise_init();
 
+	ret = wg_peer_init();
+	if (ret < 0)
+		goto err_peer;
+
 	ret = wg_device_init();
 	if (ret < 0)
 		goto err_device;
@@ -44,6 +53,10 @@ static int __init mod_init(void)
 err_netlink:
 	wg_device_uninit();
 err_device:
+	wg_peer_uninit();
+err_peer:
+	wg_allowedips_slab_uninit();
+err_allowedips:
 	return ret;
 }
 
@@ -51,6 +64,8 @@ static void __exit mod_exit(void)
 {
 	wg_genetlink_uninit();
 	wg_device_uninit();
+	wg_peer_uninit();
+	wg_allowedips_slab_uninit();
 }
 
 module_init(mod_init);

drivers/net/wireguard/peer.c

@@ -15,6 +15,7 @@
 #include <linux/rcupdate.h>
 #include <linux/list.h>
 
+static struct kmem_cache *peer_cache;
 static atomic64_t peer_counter = ATOMIC64_INIT(0);
 
 struct wg_peer *wg_peer_create(struct wg_device *wg,
@@ -29,10 +30,10 @@ struct wg_peer *wg_peer_create(struct wg_device *wg,
 	if (wg->num_peers >= MAX_PEERS_PER_DEVICE)
 		return ERR_PTR(ret);
 
-	peer = kzalloc(sizeof(*peer), GFP_KERNEL);
+	peer = kmem_cache_zalloc(peer_cache, GFP_KERNEL);
 	if (unlikely(!peer))
 		return ERR_PTR(ret);
-	if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))
+	if (unlikely(dst_cache_init(&peer->endpoint_cache, GFP_KERNEL)))
 		goto err;
 
 	peer->device = wg;
@@ -64,7 +65,7 @@ struct wg_peer *wg_peer_create(struct wg_device *wg,
 	return peer;
 
 err:
-	kfree(peer);
+	kmem_cache_free(peer_cache, peer);
 	return ERR_PTR(ret);
 }
 
@@ -88,7 +89,7 @@ static void peer_make_dead(struct wg_peer *peer)
 	/* Mark as dead, so that we don't allow jumping contexts after. */
 	WRITE_ONCE(peer->is_dead, true);
 
-	/* The caller must now synchronize_rcu() for this to take effect. */
+	/* The caller must now synchronize_net() for this to take effect. */
 }
 
 static void peer_remove_after_dead(struct wg_peer *peer)
@@ -160,7 +161,7 @@ void wg_peer_remove(struct wg_peer *peer)
 	lockdep_assert_held(&peer->device->device_update_lock);
 
 	peer_make_dead(peer);
-	synchronize_rcu();
+	synchronize_net();
 	peer_remove_after_dead(peer);
 }
 
@@ -178,7 +179,7 @@ void wg_peer_remove_all(struct wg_device *wg)
 		peer_make_dead(peer);
 		list_add_tail(&peer->peer_list, &dead_peers);
 	}
-	synchronize_rcu();
+	synchronize_net();
 	list_for_each_entry_safe(peer, temp, &dead_peers, peer_list)
 		peer_remove_after_dead(peer);
 }
@@ -193,7 +194,8 @@ static void rcu_release(struct rcu_head *rcu)
 	/* The final zeroing takes care of clearing any remaining handshake key
 	 * material and other potentially sensitive information.
 	 */
-	kfree_sensitive(peer);
+	memzero_explicit(peer, sizeof(*peer));
+	kmem_cache_free(peer_cache, peer);
 }
 
 static void kref_release(struct kref *refcount)
@@ -225,3 +227,14 @@ void wg_peer_put(struct wg_peer *peer)
 		return;
 	kref_put(&peer->refcount, kref_release);
 }
+
+int __init wg_peer_init(void)
+{
+	peer_cache = KMEM_CACHE(wg_peer, 0);
+	return peer_cache ? 0 : -ENOMEM;
+}
+
+void wg_peer_uninit(void)
+{
+	kmem_cache_destroy(peer_cache);
+}

drivers/net/wireguard/peer.h

@@ -80,4 +80,7 @@ void wg_peer_put(struct wg_peer *peer);
 void wg_peer_remove(struct wg_peer *peer);
 void wg_peer_remove_all(struct wg_device *wg);
 
+int wg_peer_init(void);
+void wg_peer_uninit(void);
+
 #endif /* _WG_PEER_H */

drivers/net/wireguard/selftest/allowedips.c

@@ -19,32 +19,22 @@
 
 #include <linux/siphash.h>
 
-static __init void swap_endian_and_apply_cidr(u8 *dst, const u8 *src, u8 bits,
-					      u8 cidr)
-{
-	swap_endian(dst, src, bits);
-	memset(dst + (cidr + 7) / 8, 0, bits / 8 - (cidr + 7) / 8);
-	if (cidr)
-		dst[(cidr + 7) / 8 - 1] &= ~0U << ((8 - (cidr % 8)) % 8);
-}
-
 static __init void print_node(struct allowedips_node *node, u8 bits)
 {
 	char *fmt_connection = KERN_DEBUG "\t\"%p/%d\" -> \"%p/%d\";\n";
-	char *fmt_declaration = KERN_DEBUG
+	char *fmt_declaration = KERN_DEBUG "\t\"%p/%d\"[style=%s, color=\"#%06x\"];\n";
-		"\t\"%p/%d\"[style=%s, color=\"#%06x\"];\n";
+	u8 ip1[16], ip2[16], cidr1, cidr2;
 	char *style = "dotted";
-	u8 ip1[16], ip2[16];
 	u32 color = 0;
 
+	if (node == NULL)
+		return;
 	if (bits == 32) {
 		fmt_connection = KERN_DEBUG "\t\"%pI4/%d\" -> \"%pI4/%d\";\n";
-		fmt_declaration = KERN_DEBUG
+		fmt_declaration = KERN_DEBUG "\t\"%pI4/%d\"[style=%s, color=\"#%06x\"];\n";
-			"\t\"%pI4/%d\"[style=%s, color=\"#%06x\"];\n";
 	} else if (bits == 128) {
 		fmt_connection = KERN_DEBUG "\t\"%pI6/%d\" -> \"%pI6/%d\";\n";
-		fmt_declaration = KERN_DEBUG
+		fmt_declaration = KERN_DEBUG "\t\"%pI6/%d\"[style=%s, color=\"#%06x\"];\n";
-			"\t\"%pI6/%d\"[style=%s, color=\"#%06x\"];\n";
 	}
 	if (node->peer) {
 		hsiphash_key_t key = { { 0 } };
@@ -55,24 +45,20 @@ static __init void print_node(struct allowedips_node *node, u8 bits)
 			hsiphash_1u32(0xabad1dea, &key) % 200;
 		style = "bold";
 	}
-	swap_endian_and_apply_cidr(ip1, node->bits, bits, node->cidr);
+	wg_allowedips_read_node(node, ip1, &cidr1);
-	printk(fmt_declaration, ip1, node->cidr, style, color);
+	printk(fmt_declaration, ip1, cidr1, style, color);
 	if (node->bit[0]) {
-		swap_endian_and_apply_cidr(ip2,
+		wg_allowedips_read_node(rcu_dereference_raw(node->bit[0]), ip2, &cidr2);
-				rcu_dereference_raw(node->bit[0])->bits, bits,
+		printk(fmt_connection, ip1, cidr1, ip2, cidr2);
-				node->cidr);
-		printk(fmt_connection, ip1, node->cidr, ip2,
-		       rcu_dereference_raw(node->bit[0])->cidr);
-		print_node(rcu_dereference_raw(node->bit[0]), bits);
 	}
 	if (node->bit[1]) {
-		swap_endian_and_apply_cidr(ip2,
+		wg_allowedips_read_node(rcu_dereference_raw(node->bit[1]), ip2, &cidr2);
-				rcu_dereference_raw(node->bit[1])->bits,
+		printk(fmt_connection, ip1, cidr1, ip2, cidr2);
-				bits, node->cidr);
-		printk(fmt_connection, ip1, node->cidr, ip2,
-		       rcu_dereference_raw(node->bit[1])->cidr);
-		print_node(rcu_dereference_raw(node->bit[1]), bits);
 	}
+	if (node->bit[0])
+		print_node(rcu_dereference_raw(node->bit[0]), bits);
+	if (node->bit[1])
+		print_node(rcu_dereference_raw(node->bit[1]), bits);
 }
 
 static __init void print_tree(struct allowedips_node __rcu *top, u8 bits)
@@ -121,8 +107,8 @@ static __init inline union nf_inet_addr horrible_cidr_to_mask(u8 cidr)
 {
 	union nf_inet_addr mask;
 
-	memset(&mask, 0x00, 128 / 8);
+	memset(&mask, 0, sizeof(mask));
-	memset(&mask, 0xff, cidr / 8);
+	memset(&mask.all, 0xff, cidr / 8);
 	if (cidr % 32)
 		mask.all[cidr / 32] = (__force u32)htonl(
 			(0xFFFFFFFFUL << (32 - (cidr % 32))) & 0xFFFFFFFFUL);
@@ -149,42 +135,36 @@ horrible_mask_self(struct horrible_allowedips_node *node)
 }
 
 static __init inline bool
-horrible_match_v4(const struct horrible_allowedips_node *node,
+horrible_match_v4(const struct horrible_allowedips_node *node, struct in_addr *ip)
-		  struct in_addr *ip)
 {
 	return (ip->s_addr & node->mask.ip) == node->ip.ip;
 }
 
 static __init inline bool
-horrible_match_v6(const struct horrible_allowedips_node *node,
+horrible_match_v6(const struct horrible_allowedips_node *node, struct in6_addr *ip)
-		  struct in6_addr *ip)
 {
-	return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) ==
+	return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) == node->ip.ip6[0] &&
-		       node->ip.ip6[0] &&
+	       (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) == node->ip.ip6[1] &&
-	       (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) ==
+	       (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) == node->ip.ip6[2] &&
-		       node->ip.ip6[1] &&
-	       (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) ==
-		       node->ip.ip6[2] &&
 	       (ip->in6_u.u6_addr32[3] & node->mask.ip6[3]) == node->ip.ip6[3];
 }
 
 static __init void
-horrible_insert_ordered(struct horrible_allowedips *table,
+horrible_insert_ordered(struct horrible_allowedips *table, struct horrible_allowedips_node *node)
-			struct horrible_allowedips_node *node)
 {
 	struct horrible_allowedips_node *other = NULL, *where = NULL;
 	u8 my_cidr = horrible_mask_to_cidr(node->mask);
 
 	hlist_for_each_entry(other, &table->head, table) {
-		if (!memcmp(&other->mask, &node->mask,
+		if (other->ip_version == node->ip_version &&
-			    sizeof(union nf_inet_addr)) &&
+		    !memcmp(&other->mask, &node->mask, sizeof(union nf_inet_addr)) &&
-		    !memcmp(&other->ip, &node->ip,
+		    !memcmp(&other->ip, &node->ip, sizeof(union nf_inet_addr))) {
-			    sizeof(union nf_inet_addr)) &&
-		    other->ip_version == node->ip_version) {
 			other->value = node->value;
 			kfree(node);
 			return;
 		}
+	}
+	hlist_for_each_entry(other, &table->head, table) {
 		where = other;
 		if (horrible_mask_to_cidr(other->mask) <= my_cidr)
 			break;
@@ -201,8 +181,7 @@ static __init int
 horrible_allowedips_insert_v4(struct horrible_allowedips *table,
 			      struct in_addr *ip, u8 cidr, void *value)
 {
-	struct horrible_allowedips_node *node = kzalloc(sizeof(*node),
+	struct horrible_allowedips_node *node = kzalloc(sizeof(*node), GFP_KERNEL);
-							GFP_KERNEL);
 
 	if (unlikely(!node))
 		return -ENOMEM;
@@ -219,8 +198,7 @@ static __init int
 horrible_allowedips_insert_v6(struct horrible_allowedips *table,
 			      struct in6_addr *ip, u8 cidr, void *value)
 {
-	struct horrible_allowedips_node *node = kzalloc(sizeof(*node),
+	struct horrible_allowedips_node *node = kzalloc(sizeof(*node), GFP_KERNEL);
-							GFP_KERNEL);
 
 	if (unlikely(!node))
 		return -ENOMEM;
@@ -234,39 +212,43 @@ horrible_allowedips_insert_v6(struct horrible_allowedips *table,
 }
 
 static __init void *
-horrible_allowedips_lookup_v4(struct horrible_allowedips *table,
+horrible_allowedips_lookup_v4(struct horrible_allowedips *table, struct in_addr *ip)
-			      struct in_addr *ip)
 {
 	struct horrible_allowedips_node *node;
-	void *ret = NULL;
 
 	hlist_for_each_entry(node, &table->head, table) {
-		if (node->ip_version != 4)
+		if (node->ip_version == 4 && horrible_match_v4(node, ip))
-			continue;
+			return node->value;
-		if (horrible_match_v4(node, ip)) {
-			ret = node->value;
-			break;
-		}
 	}
-	return ret;
+	return NULL;
 }
 
 static __init void *
-horrible_allowedips_lookup_v6(struct horrible_allowedips *table,
+horrible_allowedips_lookup_v6(struct horrible_allowedips *table, struct in6_addr *ip)
-			      struct in6_addr *ip)
 {
 	struct horrible_allowedips_node *node;
-	void *ret = NULL;
 
 	hlist_for_each_entry(node, &table->head, table) {
-		if (node->ip_version != 6)
+		if (node->ip_version == 6 && horrible_match_v6(node, ip))
-			continue;
+			return node->value;
-		if (horrible_match_v6(node, ip)) {
-			ret = node->value;
-			break;
-		}
 	}
-	return ret;
+	return NULL;
+}
+
+
+static __init void
+horrible_allowedips_remove_by_value(struct horrible_allowedips *table, void *value)
+{
+	struct horrible_allowedips_node *node;
+	struct hlist_node *h;
+
+	hlist_for_each_entry_safe(node, h, &table->head, table) {
+		if (node->value != value)
+			continue;
+		hlist_del(&node->table);
+		kfree(node);
+	}
+
 }
 
 static __init bool randomized_test(void)
@@ -296,6 +278,7 @@ static __init bool randomized_test(void)
 			goto free;
 		}
 		kref_init(&peers[i]->refcount);
+		INIT_LIST_HEAD(&peers[i]->allowedips_list);
 	}
 
 	mutex_lock(&mutex);
@@ -333,7 +316,7 @@ static __init bool randomized_test(void)
 			if (wg_allowedips_insert_v4(&t,
 						    (struct in_addr *)mutated,
 						    cidr, peer, &mutex) < 0) {
-				pr_err("allowedips random malloc: FAIL\n");
+				pr_err("allowedips random self-test malloc: FAIL\n");
 				goto free_locked;
 			}
 			if (horrible_allowedips_insert_v4(&h,
@@ -396,23 +379,33 @@ static __init bool randomized_test(void)
 		print_tree(t.root6, 128);
 	}
 
-	for (i = 0; i < NUM_QUERIES; ++i) {
+	for (j = 0;; ++j) {
-		prandom_bytes(ip, 4);
+		for (i = 0; i < NUM_QUERIES; ++i) {
-		if (lookup(t.root4, 32, ip) !=
+			prandom_bytes(ip, 4);
-		    horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) {
+			if (lookup(t.root4, 32, ip) != horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) {
-			pr_err("allowedips random self-test: FAIL\n");
+				horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip);
-			goto free;
+				pr_err("allowedips random v4 self-test: FAIL\n");
+				goto free;
+			}
+			prandom_bytes(ip, 16);
+			if (lookup(t.root6, 128, ip) != horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) {
+				pr_err("allowedips random v6 self-test: FAIL\n");
+				goto free;
+			}
 		}
+		if (j >= NUM_PEERS)
+			break;
+		mutex_lock(&mutex);
+		wg_allowedips_remove_by_peer(&t, peers[j], &mutex);
+		mutex_unlock(&mutex);
+		horrible_allowedips_remove_by_value(&h, peers[j]);
 	}
 
-	for (i = 0; i < NUM_QUERIES; ++i) {
+	if (t.root4 || t.root6) {
-		prandom_bytes(ip, 16);
+		pr_err("allowedips random self-test removal: FAIL\n");
-		if (lookup(t.root6, 128, ip) !=
+		goto free;
-		    horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) {
-			pr_err("allowedips random self-test: FAIL\n");
-			goto free;
-		}
 	}
+
 	ret = true;
 
 free:

drivers/net/wireless/mediatek/mt76/mt76x0/pci.c

@@ -87,7 +87,7 @@ static const struct ieee80211_ops mt76x0e_ops = {
 	.reconfig_complete = mt76x02_reconfig_complete,
 };
 
-static int mt76x0e_register_device(struct mt76x02_dev *dev)
+static int mt76x0e_init_hardware(struct mt76x02_dev *dev, bool resume)
 {
 	int err;
 
@@ -100,9 +100,11 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev)
 	if (err < 0)
 		return err;
 
-	err = mt76x02_dma_init(dev);
+	if (!resume) {
-	if (err < 0)
+		err = mt76x02_dma_init(dev);
-		return err;
+		if (err < 0)
+			return err;
+	}
 
 	err = mt76x0_init_hardware(dev);
 	if (err < 0)
@@ -123,6 +125,17 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev)
 	mt76_clear(dev, 0x110, BIT(9));
 	mt76_set(dev, MT_MAX_LEN_CFG, BIT(13));
 
+	return 0;
+}
+
+static int mt76x0e_register_device(struct mt76x02_dev *dev)
+{
+	int err;
+
+	err = mt76x0e_init_hardware(dev, false);
+	if (err < 0)
+		return err;
+
 	err = mt76x0_register_device(dev);
 	if (err < 0)
 		return err;
@@ -167,6 +180,8 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		return ret;
 
+	mt76_pci_disable_aspm(pdev);
+
 	mdev = mt76_alloc_device(&pdev->dev, sizeof(*dev), &mt76x0e_ops,
 				 &drv_ops);
 	if (!mdev)
@@ -220,6 +235,60 @@ mt76x0e_remove(struct pci_dev *pdev)
 	mt76_free_device(mdev);
 }
 
+#ifdef CONFIG_PM
+static int mt76x0e_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	struct mt76_dev *mdev = pci_get_drvdata(pdev);
+	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
+	int i;
+
+	mt76_worker_disable(&mdev->tx_worker);
+	for (i = 0; i < ARRAY_SIZE(mdev->phy.q_tx); i++)
+		mt76_queue_tx_cleanup(dev, mdev->phy.q_tx[i], true);
+	for (i = 0; i < ARRAY_SIZE(mdev->q_mcu); i++)
+		mt76_queue_tx_cleanup(dev, mdev->q_mcu[i], true);
+	napi_disable(&mdev->tx_napi);
+
+	mt76_for_each_q_rx(mdev, i)
+		napi_disable(&mdev->napi[i]);
+
+	mt76x02_dma_disable(dev);
+	mt76x02_mcu_cleanup(dev);
+	mt76x0_chip_onoff(dev, false, false);
+
+	pci_enable_wake(pdev, pci_choose_state(pdev, state), true);
+	pci_save_state(pdev);
+
+	return pci_set_power_state(pdev, pci_choose_state(pdev, state));
+}
+
+static int mt76x0e_resume(struct pci_dev *pdev)
+{
+	struct mt76_dev *mdev = pci_get_drvdata(pdev);
+	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
+	int err, i;
+
+	err = pci_set_power_state(pdev, PCI_D0);
+	if (err)
+		return err;
+
+	pci_restore_state(pdev);
+
+	mt76_worker_enable(&mdev->tx_worker);
+
+	mt76_for_each_q_rx(mdev, i) {
+		mt76_queue_rx_reset(dev, i);
+		napi_enable(&mdev->napi[i]);
+		napi_schedule(&mdev->napi[i]);
+	}
+
+	napi_enable(&mdev->tx_napi);
+	napi_schedule(&mdev->tx_napi);
+
+	return mt76x0e_init_hardware(dev, true);
+}
+#endif /* CONFIG_PM */
+
 static const struct pci_device_id mt76x0e_device_table[] = {
 	{ PCI_DEVICE(0x14c3, 0x7610) },
 	{ PCI_DEVICE(0x14c3, 0x7630) },
@@ -237,6 +306,10 @@ static struct pci_driver mt76x0e_driver = {
 	.id_table	= mt76x0e_device_table,
 	.probe		= mt76x0e_probe,
 	.remove		= mt76x0e_remove,
+#ifdef CONFIG_PM
+	.suspend	= mt76x0e_suspend,
+	.resume		= mt76x0e_resume,
+#endif /* CONFIG_PM */
 };
 
 module_pci_driver(mt76x0e_driver);

drivers/net/wireless/mediatek/mt76/mt7921/mcu.c

@@ -391,29 +391,37 @@ static void
 mt7921_mcu_tx_rate_report(struct mt7921_dev *dev, struct sk_buff *skb,
 			  u16 wlan_idx)
 {
-	struct mt7921_mcu_wlan_info_event *wtbl_info =
+	struct mt7921_mcu_wlan_info_event *wtbl_info;
-		(struct mt7921_mcu_wlan_info_event *)(skb->data);
-	struct rate_info rate = {};
-	u8 curr_idx = wtbl_info->rate_info.rate_idx;
-	u16 curr = le16_to_cpu(wtbl_info->rate_info.rate[curr_idx]);
-	struct mt7921_mcu_peer_cap peer = wtbl_info->peer_cap;
 	struct mt76_phy *mphy = &dev->mphy;
 	struct mt7921_sta_stats *stats;
+	struct rate_info rate = {};
 	struct mt7921_sta *msta;
 	struct mt76_wcid *wcid;
+	u8 idx;
 
 	if (wlan_idx >= MT76_N_WCIDS)
 		return;
+
+	wtbl_info = (struct mt7921_mcu_wlan_info_event *)skb->data;
+	idx = wtbl_info->rate_info.rate_idx;
+	if (idx >= ARRAY_SIZE(wtbl_info->rate_info.rate))
+		return;
+
+	rcu_read_lock();
+
 	wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]);
 	if (!wcid)
-		return;
+		goto out;
 
 	msta = container_of(wcid, struct mt7921_sta, wcid);
 	stats = &msta->stats;
 
 	/* current rate */
-	mt7921_mcu_tx_rate_parse(mphy, &peer, &rate, curr);
+	mt7921_mcu_tx_rate_parse(mphy, &wtbl_info->peer_cap, &rate,
+				 le16_to_cpu(wtbl_info->rate_info.rate[idx]));
 	stats->tx_rate = rate;
+out:
+	rcu_read_unlock();
 }
 
 static void

drivers/net/xen-netback/interface.c

@@ -684,6 +684,7 @@ static void xenvif_disconnect_queue(struct xenvif_queue *queue)
 {
 	if (queue->task) {
 		kthread_stop(queue->task);
+		put_task_struct(queue->task);
 		queue->task = NULL;
 	}
 
@@ -745,6 +746,11 @@ int xenvif_connect_data(struct xenvif_queue *queue,
 	if (IS_ERR(task))
 		goto kthread_err;
 	queue->task = task;
+	/*
+	 * Take a reference to the task in order to prevent it from being freed
+	 * if the thread function returns before kthread_stop is called.
+	 */
+	get_task_struct(task);
 
 	task = kthread_run(xenvif_dealloc_kthread, queue,
 			   "%s-dealloc", queue->name);