diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 1300c66abc15..9a4eea1f9abd 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -111,7 +111,14 @@ static struct arm64_cpu_capabilities const __ro_after_init *cpucap_ptrs[ARM64_NC
 
 DECLARE_BITMAP(boot_cpucaps, ARM64_NCAPS);
 
-bool arm64_use_ng_mappings = false;
+/*
+ * arm64_use_ng_mappings must be placed in the .data section, otherwise it
+ * ends up in the .bss section where it is initialized in early_map_kernel()
+ * after the MMU (with the idmap) was enabled. create_init_idmap() - which
+ * runs before early_map_kernel() and reads the variable via PTE_MAYBE_NG -
+ * may end up generating an incorrect idmap page table attributes.
+ */
+bool arm64_use_ng_mappings __read_mostly = false;
 EXPORT_SYMBOL(arm64_use_ng_mappings);
 
 DEFINE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector) = vectors;
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 695e569159c1..be7cddc414e4 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -17,10 +17,12 @@ struct ucode_cpu_info {
 void load_ucode_bsp(void);
 void load_ucode_ap(void);
 void microcode_bsp_resume(void);
+bool __init microcode_loader_disabled(void);
 #else
 static inline void load_ucode_bsp(void)	{ }
 static inline void load_ucode_ap(void) { }
 static inline void microcode_bsp_resume(void) { }
+static inline bool __init microcode_loader_disabled(void) { return false; }
 #endif
 
 extern unsigned long initrd_start_early;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 093d3ca43c46..2f84164b20e0 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -1099,15 +1099,17 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
 
 static int __init save_microcode_in_initrd(void)
 {
-	unsigned int cpuid_1_eax = native_cpuid_eax(1);
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 	struct cont_desc desc = { 0 };
+	unsigned int cpuid_1_eax;
 	enum ucode_state ret;
 	struct cpio_data cp;
 
-	if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
+	if (microcode_loader_disabled() || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
 		return 0;
 
+	cpuid_1_eax = native_cpuid_eax(1);
+
 	if (!find_blobs_in_containers(&cp))
 		return -EINVAL;
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index b3658d11e7b6..079f046ee26d 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -41,8 +41,8 @@
 
 #include "internal.h"
 
-static struct microcode_ops	*microcode_ops;
-bool dis_ucode_ldr = true;
+static struct microcode_ops *microcode_ops;
+static bool dis_ucode_ldr = false;
 
 bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV);
 module_param(force_minrev, bool, S_IRUSR | S_IWUSR);
@@ -84,6 +84,9 @@ static bool amd_check_current_patch_level(void)
 	u32 lvl, dummy, i;
 	u32 *levels;
 
+	if (x86_cpuid_vendor() != X86_VENDOR_AMD)
+		return false;
+
 	native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
 
 	levels = final_levels;
@@ -95,27 +98,29 @@ static bool amd_check_current_patch_level(void)
 	return false;
 }
 
-static bool __init check_loader_disabled_bsp(void)
+bool __init microcode_loader_disabled(void)
 {
-	static const char *__dis_opt_str = "dis_ucode_ldr";
-	const char *cmdline = boot_command_line;
-	const char *option  = __dis_opt_str;
-
-	/*
-	 * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
-	 * completely accurate as xen pv guests don't see that CPUID bit set but
-	 * that's good enough as they don't land on the BSP path anyway.
-	 */
-	if (native_cpuid_ecx(1) & BIT(31))
+	if (dis_ucode_ldr)
 		return true;
 
-	if (x86_cpuid_vendor() == X86_VENDOR_AMD) {
-		if (amd_check_current_patch_level())
-			return true;
-	}
-
-	if (cmdline_find_option_bool(cmdline, option) <= 0)
-		dis_ucode_ldr = false;
+	/*
+	 * Disable when:
+	 *
+	 * 1) The CPU does not support CPUID.
+	 *
+	 * 2) Bit 31 in CPUID[1]:ECX is clear
+	 *    The bit is reserved for hypervisor use. This is still not
+	 *    completely accurate as XEN PV guests don't see that CPUID bit
+	 *    set, but that's good enough as they don't land on the BSP
+	 *    path anyway.
+	 *
+	 * 3) Certain AMD patch levels are not allowed to be
+	 *    overwritten.
+	 */
+	if (!have_cpuid_p() ||
+	    native_cpuid_ecx(1) & BIT(31) ||
+	    amd_check_current_patch_level())
+		dis_ucode_ldr = true;
 
 	return dis_ucode_ldr;
 }
@@ -125,7 +130,10 @@ void __init load_ucode_bsp(void)
 	unsigned int cpuid_1_eax;
 	bool intel = true;
 
-	if (!have_cpuid_p())
+	if (cmdline_find_option_bool(boot_command_line, "dis_ucode_ldr") > 0)
+		dis_ucode_ldr = true;
+
+	if (microcode_loader_disabled())
 		return;
 
 	cpuid_1_eax = native_cpuid_eax(1);
@@ -146,9 +154,6 @@ void __init load_ucode_bsp(void)
 		return;
 	}
 
-	if (check_loader_disabled_bsp())
-		return;
-
 	if (intel)
 		load_ucode_intel_bsp(&early_data);
 	else
@@ -159,6 +164,11 @@ void load_ucode_ap(void)
 {
 	unsigned int cpuid_1_eax;
 
+	/*
+	 * Can't use microcode_loader_disabled() here - .init section
+	 * hell. It doesn't have to either - the BSP variant must've
+	 * parsed cmdline already anyway.
+	 */
 	if (dis_ucode_ldr)
 		return;
 
@@ -810,7 +820,7 @@ static int __init microcode_init(void)
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 	int error;
 
-	if (dis_ucode_ldr)
+	if (microcode_loader_disabled())
 		return -EINVAL;
 
 	if (c->x86_vendor == X86_VENDOR_INTEL)
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 815fa67356a2..df5650eb3f08 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -395,7 +395,7 @@ static int __init save_builtin_microcode(void)
 	if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED)
 		return 0;
 
-	if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	if (microcode_loader_disabled() || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return 0;
 
 	uci.mc = get_microcode_blob(&uci, true);
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index 5df621752fef..50a9702ae4e2 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -94,7 +94,6 @@ static inline unsigned int x86_cpuid_family(void)
 	return x86_family(eax);
 }
 
-extern bool dis_ucode_ldr;
 extern bool force_minrev;
 
 #ifdef CONFIG_CPU_SUP_AMD
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index de001b2146ab..375f2d7f1762 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -145,10 +145,6 @@ void __init __no_stack_protector mk_early_pgtbl_32(void)
 	*ptr = (unsigned long)ptep + PAGE_OFFSET;
 
 #ifdef CONFIG_MICROCODE_INITRD32
-	/* Running on a hypervisor? */
-	if (native_cpuid_ecx(1) & BIT(31))
-		return;
-
 	params = (struct boot_params *)__pa_nodebug(&boot_params);
 	if (!params->hdr.ramdisk_size || !params->hdr.ramdisk_image)
 		return;
diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c
index 85241c0c7f56..b0cab215b08f 100644
--- a/arch/x86/kvm/smm.c
+++ b/arch/x86/kvm/smm.c
@@ -131,6 +131,7 @@ void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
 
 	kvm_mmu_reset_context(vcpu);
 }
+EXPORT_SYMBOL_GPL(kvm_smm_changed);
 
 void process_smi(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index e39ab7c0be4e..7cbacd043921 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2222,6 +2222,10 @@ static int shutdown_interception(struct kvm_vcpu *vcpu)
 	 */
 	if (!sev_es_guest(vcpu->kvm)) {
 		clear_page(svm->vmcb);
+#ifdef CONFIG_KVM_SMM
+		if (is_smm(vcpu))
+			kvm_smm_changed(vcpu, false);
+#endif
 		kvm_vcpu_reset(vcpu, true);
 	}
 
diff --git a/drivers/accel/ivpu/ivpu_hw.c b/drivers/accel/ivpu/ivpu_hw.c
index 08b3cef58fd2..1214f155afa1 100644
--- a/drivers/accel/ivpu/ivpu_hw.c
+++ b/drivers/accel/ivpu/ivpu_hw.c
@@ -106,7 +106,7 @@ static void timeouts_init(struct ivpu_device *vdev)
 		else
 			vdev->timeout.autosuspend = 100;
 		vdev->timeout.d0i3_entry_msg = 5;
-		vdev->timeout.state_dump_msg = 10;
+		vdev->timeout.state_dump_msg = 100;
 	}
 }
 
diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c
index 39f7c2d736d1..b603c25f3dfa 100644
--- a/drivers/clocksource/i8253.c
+++ b/drivers/clocksource/i8253.c
@@ -103,7 +103,7 @@ int __init clocksource_i8253_init(void)
 #ifdef CONFIG_CLKEVT_I8253
 void clockevent_i8253_disable(void)
 {
-	raw_spin_lock(&i8253_lock);
+	guard(raw_spinlock_irqsave)(&i8253_lock);
 
 	/*
 	 * Writing the MODE register should stop the counter, according to
@@ -132,8 +132,6 @@ void clockevent_i8253_disable(void)
 	outb_p(0, PIT_CH0);
 
 	outb_p(0x30, PIT_MODE);
-
-	raw_spin_unlock(&i8253_lock);
 }
 
 static int pit_shutdown(struct clock_event_device *evt)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 2a1f3dbb14d3..3b6254de2c0e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -66,7 +66,6 @@
 #define VCN_ENC_CMD_REG_WAIT		0x0000000c
 
 #define VCN_AON_SOC_ADDRESS_2_0 	0x1f800
-#define VCN1_AON_SOC_ADDRESS_3_0 	0x48000
 #define VCN_VID_IP_ADDRESS_2_0		0x0
 #define VCN_AON_IP_ADDRESS_2_0		0x30000
 
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
index 194026e9be33..1ca1bbe7784e 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
@@ -42,7 +42,12 @@ static void hdp_v4_0_flush_hdp(struct amdgpu_device *adev,
 {
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
-		RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		/* We just need to read back a register to post the write.
+		 * Reading back the remapped register causes problems on
+		 * some platforms so just read back the memory size register.
+		 */
+		if (adev->nbio.funcs->get_memsize)
+			adev->nbio.funcs->get_memsize(adev);
 	} else {
 		amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
index d3962d469088..40705e13ca56 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
@@ -33,7 +33,12 @@ static void hdp_v5_0_flush_hdp(struct amdgpu_device *adev,
 {
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
-		RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		/* We just need to read back a register to post the write.
+		 * Reading back the remapped register causes problems on
+		 * some platforms so just read back the memory size register.
+		 */
+		if (adev->nbio.funcs->get_memsize)
+			adev->nbio.funcs->get_memsize(adev);
 	} else {
 		amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
index f52552c5fa27..6b9f2e1d9d69 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
@@ -34,7 +34,17 @@ static void hdp_v5_2_flush_hdp(struct amdgpu_device *adev,
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2,
 			0);
-		RREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		if (amdgpu_sriov_vf(adev)) {
+			/* this is fine because SR_IOV doesn't remap the register */
+			RREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		} else {
+			/* We just need to read back a register to post the write.
+			 * Reading back the remapped register causes problems on
+			 * some platforms so just read back the memory size register.
+			 */
+			if (adev->nbio.funcs->get_memsize)
+				adev->nbio.funcs->get_memsize(adev);
+		}
 	} else {
 		amdgpu_ring_emit_wreg(ring,
 			(adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2,
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
index 6948fe9956ce..20da813299f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
@@ -36,7 +36,12 @@ static void hdp_v6_0_flush_hdp(struct amdgpu_device *adev,
 {
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
-		RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		/* We just need to read back a register to post the write.
+		 * Reading back the remapped register causes problems on
+		 * some platforms so just read back the memory size register.
+		 */
+		if (adev->nbio.funcs->get_memsize)
+			adev->nbio.funcs->get_memsize(adev);
 	} else {
 		amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
index 63820329f67e..f7ecdd15d528 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
@@ -33,7 +33,12 @@ static void hdp_v7_0_flush_hdp(struct amdgpu_device *adev,
 {
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
-		RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		/* We just need to read back a register to post the write.
+		 * Reading back the remapped register causes problems on
+		 * some platforms so just read back the memory size register.
+		 */
+		if (adev->nbio.funcs->get_memsize)
+			adev->nbio.funcs->get_memsize(adev);
 	} else {
 		amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index bfd067e2d2f1..f0edaabdcde5 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -39,6 +39,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0					0x1fa00
 #define VCN1_VID_SOC_ADDRESS_3_0				0x48200
+#define VCN1_AON_SOC_ADDRESS_3_0				0x48000
 
 #define mmUVD_CONTEXT_ID_INTERNAL_OFFSET			0x1fd
 #define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET			0x503
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 04e9e806e318..e4d0c0310e76 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -39,6 +39,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0					0x1fa00
 #define VCN1_VID_SOC_ADDRESS_3_0				0x48200
+#define VCN1_AON_SOC_ADDRESS_3_0				0x48000
 
 #define mmUVD_CONTEXT_ID_INTERNAL_OFFSET			0x27
 #define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET			0x0f
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 65dd68b32280..be86f86b49e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -40,6 +40,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0					0x1fa00
 #define VCN1_VID_SOC_ADDRESS_3_0				0x48200
+#define VCN1_AON_SOC_ADDRESS_3_0				0x48000
 
 #define mmUVD_CONTEXT_ID_INTERNAL_OFFSET			0x27
 #define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET			0x0f
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 26c6f10a8c8f..f391f0c54043 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -46,6 +46,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0							0x1fb00
 #define VCN1_VID_SOC_ADDRESS_3_0						0x48300
+#define VCN1_AON_SOC_ADDRESS_3_0						0x48000
 
 #define VCN_HARVEST_MMSCH								0
 
@@ -575,7 +576,8 @@ static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx
 
 	/* VCN global tiling registers */
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
-		VCN, 0, regUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+			VCN, inst_idx, regUVD_GFX10_ADDR_CONFIG),
+			adev->gfx.config.gb_addr_config, 0, indirect);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index 84c6b0f5c4c0..77542dabec59 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -44,6 +44,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0		0x1fb00
 #define VCN1_VID_SOC_ADDRESS_3_0	0x48300
+#define VCN1_AON_SOC_ADDRESS_3_0	0x48000
 
 static const struct amdgpu_hwip_reg_entry vcn_reg_list_4_0_3[] = {
 	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_POWER_STATUS),
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index 9d4f5352a62c..e0b02bf1c563 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -46,6 +46,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0						0x1fb00
 #define VCN1_VID_SOC_ADDRESS_3_0					(0x48300 + 0x38000)
+#define VCN1_AON_SOC_ADDRESS_3_0					(0x48000 + 0x38000)
 
 #define VCN_HARVEST_MMSCH							0
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index c305386358b4..d19eec4d4790 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -488,7 +488,8 @@ static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i
 
 	/* VCN global tiling registers */
 	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
-		VCN, 0, regUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+		VCN, inst_idx, regUVD_GFX10_ADDR_CONFIG),
+		adev->gfx.config.gb_addr_config, 0, indirect);
 
 	return;
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 115fb3bc4564..66c50a09d2df 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -666,15 +666,21 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 
 	if (acrtc->dm_irq_params.stream &&
-	    acrtc->dm_irq_params.vrr_params.supported &&
-	    acrtc->dm_irq_params.freesync_config.state ==
-		    VRR_STATE_ACTIVE_VARIABLE) {
+		acrtc->dm_irq_params.vrr_params.supported) {
+		bool replay_en = acrtc->dm_irq_params.stream->link->replay_settings.replay_feature_enabled;
+		bool psr_en = acrtc->dm_irq_params.stream->link->psr_settings.psr_feature_enabled;
+		bool fs_active_var_en = acrtc->dm_irq_params.freesync_config.state == VRR_STATE_ACTIVE_VARIABLE;
+
 		mod_freesync_handle_v_update(adev->dm.freesync_module,
 					     acrtc->dm_irq_params.stream,
 					     &acrtc->dm_irq_params.vrr_params);
 
-		dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc->dm_irq_params.stream,
-					   &acrtc->dm_irq_params.vrr_params.adjust);
+		/* update vmin_vmax only if freesync is enabled, or only if PSR and REPLAY are disabled */
+		if (fs_active_var_en || (!fs_active_var_en && !replay_en && !psr_en)) {
+			dc_stream_adjust_vmin_vmax(adev->dm.dc,
+					acrtc->dm_irq_params.stream,
+					&acrtc->dm_irq_params.vrr_params.adjust);
+		}
 	}
 
 	/*
@@ -12526,7 +12532,7 @@ int amdgpu_dm_process_dmub_aux_transfer_sync(
 		 * Transient states before tunneling is enabled could
 		 * lead to this error. We can ignore this for now.
 		 */
-		if (p_notify->result != AUX_RET_ERROR_PROTOCOL_ERROR) {
+		if (p_notify->result == AUX_RET_ERROR_PROTOCOL_ERROR) {
 			DRM_WARN("DPIA AUX failed on 0x%x(%d), error %d\n",
 					payload->address, payload->length,
 					p_notify->result);
@@ -12535,22 +12541,14 @@ int amdgpu_dm_process_dmub_aux_transfer_sync(
 		goto out;
 	}
 
+	payload->reply[0] = adev->dm.dmub_notify->aux_reply.command & 0xF;
+	if (adev->dm.dmub_notify->aux_reply.command & 0xF0)
+		/* The reply is stored in the top nibble of the command. */
+		payload->reply[0] = (adev->dm.dmub_notify->aux_reply.command >> 4) & 0xF;
 
-	payload->reply[0] = adev->dm.dmub_notify->aux_reply.command;
-	if (!payload->write && p_notify->aux_reply.length &&
-			(payload->reply[0] == AUX_TRANSACTION_REPLY_AUX_ACK)) {
-
-		if (payload->length != p_notify->aux_reply.length) {
-			DRM_WARN("invalid read length %d from DPIA AUX 0x%x(%d)!\n",
-				p_notify->aux_reply.length,
-					payload->address, payload->length);
-			*operation_result = AUX_RET_ERROR_INVALID_REPLY;
-			goto out;
-		}
-
+	if (!payload->write && p_notify->aux_reply.length)
 		memcpy(payload->data, p_notify->aux_reply.data,
 				p_notify->aux_reply.length);
-	}
 
 	/* success */
 	ret = p_notify->aux_reply.length;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 5bdf44c69218..dca8384af95d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -51,6 +51,9 @@
 
 #define PEAK_FACTOR_X1000 1006
 
+/*
+ * This function handles both native AUX and I2C-Over-AUX transactions.
+ */
 static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 				  struct drm_dp_aux_msg *msg)
 {
@@ -87,15 +90,25 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	if (adev->dm.aux_hpd_discon_quirk) {
 		if (msg->address == DP_SIDEBAND_MSG_DOWN_REQ_BASE &&
 			operation_result == AUX_RET_ERROR_HPD_DISCON) {
-			result = 0;
+			result = msg->size;
 			operation_result = AUX_RET_SUCCESS;
 		}
 	}
 
-	if (payload.write && result >= 0)
-		result = msg->size;
+	/*
+	 * result equals to 0 includes the cases of AUX_DEFER/I2C_DEFER
+	 */
+	if (payload.write && result >= 0) {
+		if (result) {
+			/*one byte indicating partially written bytes. Force 0 to retry*/
+			drm_info(adev_to_drm(adev), "amdgpu: AUX partially written\n");
+			result = 0;
+		} else if (!payload.reply[0])
+			/*I2C_ACK|AUX_ACK*/
+			result = msg->size;
+	}
 
-	if (result < 0)
+	if (result < 0) {
 		switch (operation_result) {
 		case AUX_RET_SUCCESS:
 			break;
@@ -114,6 +127,13 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 			break;
 		}
 
+		drm_info(adev_to_drm(adev), "amdgpu: DP AUX transfer fail:%d\n", operation_result);
+	}
+
+	if (payload.reply[0])
+		drm_info(adev_to_drm(adev), "amdgpu: AUX reply command not ACK: 0x%02x.",
+			payload.reply[0]);
+
 	return result;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 81ba8809a3b4..92a3fff1e261 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -929,7 +929,9 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p
 	}
 }
 
-static void get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc_state *context, struct scaler_data *out)
+static struct scaler_data *get_scaler_data_for_plane(
+		const struct dc_plane_state *in,
+		struct dc_state *context)
 {
 	int i;
 	struct pipe_ctx *temp_pipe = &context->res_ctx.temp_pipe;
@@ -950,7 +952,7 @@ static void get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc
 	}
 
 	ASSERT(i < MAX_PIPES);
-	memcpy(out, &temp_pipe->plane_res.scl_data, sizeof(*out));
+	return &temp_pipe->plane_res.scl_data;
 }
 
 static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned int location,
@@ -1013,11 +1015,7 @@ static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out
 						    const struct dc_plane_state *in, struct dc_state *context,
 						    const struct soc_bounding_box_st *soc)
 {
-	struct scaler_data *scaler_data = kzalloc(sizeof(*scaler_data), GFP_KERNEL);
-	if (!scaler_data)
-		return;
-
-	get_scaler_data_for_plane(in, context, scaler_data);
+	struct scaler_data *scaler_data = get_scaler_data_for_plane(in, context);
 
 	out->CursorBPP[location] = dml_cur_32bit;
 	out->CursorWidth[location] = 256;
@@ -1082,8 +1080,6 @@ static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out
 	out->DynamicMetadataTransmittedBytes[location] = 0;
 
 	out->NumberOfCursors[location] = 1;
-
-	kfree(scaler_data);
 }
 
 static unsigned int map_stream_to_dml_display_cfg(const struct dml2_context *dml2,
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 4a6aa36619fe..ad32e584deee 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -728,11 +728,16 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job)
 	return DRM_GPU_SCHED_STAT_NOMINAL;
 }
 
-/* If the current address or return address have changed, then the GPU
- * has probably made progress and we should delay the reset.  This
- * could fail if the GPU got in an infinite loop in the CL, but that
- * is pretty unlikely outside of an i-g-t testcase.
- */
+static void
+v3d_sched_skip_reset(struct drm_sched_job *sched_job)
+{
+	struct drm_gpu_scheduler *sched = sched_job->sched;
+
+	spin_lock(&sched->job_list_lock);
+	list_add(&sched_job->list, &sched->pending_list);
+	spin_unlock(&sched->job_list_lock);
+}
+
 static enum drm_gpu_sched_stat
 v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q,
 		    u32 *timedout_ctca, u32 *timedout_ctra)
@@ -742,9 +747,16 @@ v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q,
 	u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(q));
 	u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(q));
 
+	/* If the current address or return address have changed, then the GPU
+	 * has probably made progress and we should delay the reset. This
+	 * could fail if the GPU got in an infinite loop in the CL, but that
+	 * is pretty unlikely outside of an i-g-t testcase.
+	 */
 	if (*timedout_ctca != ctca || *timedout_ctra != ctra) {
 		*timedout_ctca = ctca;
 		*timedout_ctra = ctra;
+
+		v3d_sched_skip_reset(sched_job);
 		return DRM_GPU_SCHED_STAT_NOMINAL;
 	}
 
@@ -784,11 +796,13 @@ v3d_csd_job_timedout(struct drm_sched_job *sched_job)
 	struct v3d_dev *v3d = job->base.v3d;
 	u32 batches = V3D_CORE_READ(0, V3D_CSD_CURRENT_CFG4(v3d->ver));
 
-	/* If we've made progress, skip reset and let the timer get
-	 * rearmed.
+	/* If we've made progress, skip reset, add the job to the pending
+	 * list, and let the timer get rearmed.
 	 */
 	if (job->timedout_batches != batches) {
 		job->timedout_batches = batches;
+
+		v3d_sched_skip_reset(sched_job);
 		return DRM_GPU_SCHED_STAT_NOMINAL;
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 79c426dc2505..db540c8be6c7 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -423,9 +423,16 @@ static int xe_alloc_pf_queue(struct xe_gt *gt, struct pf_queue *pf_queue)
 	num_eus = bitmap_weight(gt->fuse_topo.eu_mask_per_dss,
 				XE_MAX_EU_FUSE_BITS) * num_dss;
 
-	/* user can issue separate page faults per EU and per CS */
+	/*
+	 * user can issue separate page faults per EU and per CS
+	 *
+	 * XXX: Multiplier required as compute UMD are getting PF queue errors
+	 * without it. Follow on why this multiplier is required.
+	 */
+#define PF_MULTIPLIER	8
 	pf_queue->num_dw =
-		(num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW;
+		(num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW * PF_MULTIPLIER;
+#undef PF_MULTIPLIER
 
 	pf_queue->gt = gt;
 	pf_queue->data = devm_kcalloc(xe->drm.dev, pf_queue->num_dw,
diff --git a/drivers/iio/accel/adis16201.c b/drivers/iio/accel/adis16201.c
index d054721859b3..99b05548b7bd 100644
--- a/drivers/iio/accel/adis16201.c
+++ b/drivers/iio/accel/adis16201.c
@@ -211,9 +211,9 @@ static const struct iio_chan_spec adis16201_channels[] = {
 			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
 	ADIS_AUX_ADC_CHAN(ADIS16201_AUX_ADC_REG, ADIS16201_SCAN_AUX_ADC, 0, 12),
 	ADIS_INCLI_CHAN(X, ADIS16201_XINCL_OUT_REG, ADIS16201_SCAN_INCLI_X,
-			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
+			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12),
 	ADIS_INCLI_CHAN(Y, ADIS16201_YINCL_OUT_REG, ADIS16201_SCAN_INCLI_Y,
-			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
+			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12),
 	IIO_CHAN_SOFT_TIMESTAMP(7)
 };
 
diff --git a/drivers/iio/adc/ad7606_spi.c b/drivers/iio/adc/ad7606_spi.c
index 62ec12195307..32a5448116a1 100644
--- a/drivers/iio/adc/ad7606_spi.c
+++ b/drivers/iio/adc/ad7606_spi.c
@@ -127,7 +127,7 @@ static int ad7606_spi_reg_read(struct ad7606_state *st, unsigned int addr)
 		{
 			.tx_buf = &st->d16[0],
 			.len = 2,
-			.cs_change = 0,
+			.cs_change = 1,
 		}, {
 			.rx_buf = &st->d16[1],
 			.len = 2,
diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c
index dfd47a6e1f4a..e4dcd9e782af 100644
--- a/drivers/iio/adc/rockchip_saradc.c
+++ b/drivers/iio/adc/rockchip_saradc.c
@@ -480,15 +480,6 @@ static int rockchip_saradc_probe(struct platform_device *pdev)
 	if (info->reset)
 		rockchip_saradc_reset_controller(info->reset);
 
-	/*
-	 * Use a default value for the converter clock.
-	 * This may become user-configurable in the future.
-	 */
-	ret = clk_set_rate(info->clk, info->data->clk_rate);
-	if (ret < 0)
-		return dev_err_probe(&pdev->dev, ret,
-				     "failed to set adc clk rate\n");
-
 	ret = regulator_enable(info->vref);
 	if (ret < 0)
 		return dev_err_probe(&pdev->dev, ret,
@@ -515,6 +506,14 @@ static int rockchip_saradc_probe(struct platform_device *pdev)
 	if (IS_ERR(info->clk))
 		return dev_err_probe(&pdev->dev, PTR_ERR(info->clk),
 				     "failed to get adc clock\n");
+	/*
+	 * Use a default value for the converter clock.
+	 * This may become user-configurable in the future.
+	 */
+	ret = clk_set_rate(info->clk, info->data->clk_rate);
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "failed to set adc clk rate\n");
 
 	platform_set_drvdata(pdev, indio_dev);
 
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
index 3d3b27f28c9d..273196e647a2 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
@@ -50,7 +50,7 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p)
 	u16 fifo_count;
 	u32 fifo_period;
 	s64 timestamp;
-	u8 data[INV_MPU6050_OUTPUT_DATA_SIZE];
+	u8 data[INV_MPU6050_OUTPUT_DATA_SIZE] __aligned(8);
 	size_t i, nb;
 
 	mutex_lock(&st->lock);
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
index 0a7cd8c1aa33..8a9d2593576a 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
@@ -392,6 +392,9 @@ int st_lsm6dsx_read_fifo(struct st_lsm6dsx_hw *hw)
 	if (fifo_status & cpu_to_le16(ST_LSM6DSX_FIFO_EMPTY_MASK))
 		return 0;
 
+	if (!pattern_len)
+		pattern_len = ST_LSM6DSX_SAMPLE_SIZE;
+
 	fifo_len = (le16_to_cpu(fifo_status) & fifo_diff_mask) *
 		   ST_LSM6DSX_CHAN_SIZE;
 	fifo_len = (fifo_len / pattern_len) * pattern_len;
@@ -623,6 +626,9 @@ int st_lsm6dsx_read_tagged_fifo(struct st_lsm6dsx_hw *hw)
 	if (!fifo_len)
 		return 0;
 
+	if (!pattern_len)
+		pattern_len = ST_LSM6DSX_TAGGED_SAMPLE_SIZE;
+
 	for (read_len = 0; read_len < fifo_len; read_len += pattern_len) {
 		err = st_lsm6dsx_read_block(hw,
 					    ST_LSM6DSX_REG_FIFO_OUT_TAG_ADDR,
diff --git a/drivers/usb/host/uhci-platform.c b/drivers/usb/host/uhci-platform.c
index 3dec5dd3a0d5..712389599d46 100644
--- a/drivers/usb/host/uhci-platform.c
+++ b/drivers/usb/host/uhci-platform.c
@@ -121,7 +121,7 @@ static int uhci_hcd_platform_probe(struct platform_device *pdev)
 	}
 
 	/* Get and enable clock if any specified */
-	uhci->clk = devm_clk_get(&pdev->dev, NULL);
+	uhci->clk = devm_clk_get_optional(&pdev->dev, NULL);
 	if (IS_ERR(uhci->clk)) {
 		ret = PTR_ERR(uhci->clk);
 		goto err_rmr;
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 1f65795cf5d7..ef56a2500ed6 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -217,6 +217,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * buffering it.
 	 */
 	if (dma_capable(dev, dev_addr, size, true) &&
+	    !dma_kmalloc_needs_bounce(dev, size, dir) &&
 	    !range_straddles_page_boundary(phys, size) &&
 		!xen_arch_need_swiotlb(dev, phys, dev_addr) &&
 		!is_swiotlb_force_bounce(dev))
diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h
index 13821e7e825e..9ac0427724a3 100644
--- a/drivers/xen/xenbus/xenbus.h
+++ b/drivers/xen/xenbus/xenbus.h
@@ -77,6 +77,7 @@ enum xb_req_state {
 struct xb_req_data {
 	struct list_head list;
 	wait_queue_head_t wq;
+	struct kref kref;
 	struct xsd_sockmsg msg;
 	uint32_t caller_req_id;
 	enum xsd_sockmsg_type type;
@@ -103,6 +104,7 @@ int xb_init_comms(void);
 void xb_deinit_comms(void);
 int xs_watch_msg(struct xs_watch_event *event);
 void xs_request_exit(struct xb_req_data *req);
+void xs_free_req(struct kref *kref);
 
 int xenbus_match(struct device *_dev, const struct device_driver *_drv);
 int xenbus_dev_probe(struct device *_dev);
diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c
index e5fda0256feb..82df2da1b880 100644
--- a/drivers/xen/xenbus/xenbus_comms.c
+++ b/drivers/xen/xenbus/xenbus_comms.c
@@ -309,8 +309,8 @@ static int process_msg(void)
 			virt_wmb();
 			req->state = xb_req_state_got_reply;
 			req->cb(req);
-		} else
-			kfree(req);
+		}
+		kref_put(&req->kref, xs_free_req);
 	}
 
 	mutex_unlock(&xs_response_mutex);
@@ -386,14 +386,13 @@ static int process_writes(void)
 	state.req->msg.type = XS_ERROR;
 	state.req->err = err;
 	list_del(&state.req->list);
-	if (state.req->state == xb_req_state_aborted)
-		kfree(state.req);
-	else {
+	if (state.req->state != xb_req_state_aborted) {
 		/* write err, then update state */
 		virt_wmb();
 		state.req->state = xb_req_state_got_reply;
 		wake_up(&state.req->wq);
 	}
+	kref_put(&state.req->kref, xs_free_req);
 
 	mutex_unlock(&xb_write_mutex);
 
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 46f8916597e5..f5c21ba64df5 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -406,7 +406,7 @@ void xenbus_dev_queue_reply(struct xb_req_data *req)
 	mutex_unlock(&u->reply_mutex);
 
 	kfree(req->body);
-	kfree(req);
+	kref_put(&req->kref, xs_free_req);
 
 	kref_put(&u->kref, xenbus_file_free);
 
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index d32c726f7a12..dcf9182c8451 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -112,6 +112,12 @@ static void xs_suspend_exit(void)
 	wake_up_all(&xs_state_enter_wq);
 }
 
+void xs_free_req(struct kref *kref)
+{
+	struct xb_req_data *req = container_of(kref, struct xb_req_data, kref);
+	kfree(req);
+}
+
 static uint32_t xs_request_enter(struct xb_req_data *req)
 {
 	uint32_t rq_id;
@@ -237,6 +243,12 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg)
 	req->caller_req_id = req->msg.req_id;
 	req->msg.req_id = xs_request_enter(req);
 
+	/*
+	 * Take 2nd ref.  One for this thread, and the second for the
+	 * xenbus_thread.
+	 */
+	kref_get(&req->kref);
+
 	mutex_lock(&xb_write_mutex);
 	list_add_tail(&req->list, &xb_write_list);
 	notify = list_is_singular(&xb_write_list);
@@ -261,8 +273,8 @@ static void *xs_wait_for_reply(struct xb_req_data *req, struct xsd_sockmsg *msg)
 	if (req->state == xb_req_state_queued ||
 	    req->state == xb_req_state_wait_reply)
 		req->state = xb_req_state_aborted;
-	else
-		kfree(req);
+
+	kref_put(&req->kref, xs_free_req);
 	mutex_unlock(&xb_write_mutex);
 
 	return ret;
@@ -291,6 +303,7 @@ int xenbus_dev_request_and_reply(struct xsd_sockmsg *msg, void *par)
 	req->cb = xenbus_dev_queue_reply;
 	req->par = par;
 	req->user_req = true;
+	kref_init(&req->kref);
 
 	xs_send(req, msg);
 
@@ -319,6 +332,7 @@ static void *xs_talkv(struct xenbus_transaction t,
 	req->num_vecs = num_vecs;
 	req->cb = xs_wake_up;
 	req->user_req = false;
+	kref_init(&req->kref);
 
 	msg.req_id = 0;
 	msg.tx_id = t.id;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 1bf188b6866a..2ebee1dced1b 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -174,7 +174,7 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
 	struct ocfs2_recovery_map *rm;
 
 	mutex_init(&osb->recovery_lock);
-	osb->disable_recovery = 0;
+	osb->recovery_state = OCFS2_REC_ENABLED;
 	osb->recovery_thread_task = NULL;
 	init_waitqueue_head(&osb->recovery_event);
 
@@ -190,31 +190,53 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
 	return 0;
 }
 
-/* we can't grab the goofy sem lock from inside wait_event, so we use
- * memory barriers to make sure that we'll see the null task before
- * being woken up */
 static int ocfs2_recovery_thread_running(struct ocfs2_super *osb)
 {
-	mb();
 	return osb->recovery_thread_task != NULL;
 }
 
+static void ocfs2_recovery_disable(struct ocfs2_super *osb,
+				   enum ocfs2_recovery_state state)
+{
+	mutex_lock(&osb->recovery_lock);
+	/*
+	 * If recovery thread is not running, we can directly transition to
+	 * final state.
+	 */
+	if (!ocfs2_recovery_thread_running(osb)) {
+		osb->recovery_state = state + 1;
+		goto out_lock;
+	}
+	osb->recovery_state = state;
+	/* Wait for recovery thread to acknowledge state transition */
+	wait_event_cmd(osb->recovery_event,
+		       !ocfs2_recovery_thread_running(osb) ||
+				osb->recovery_state >= state + 1,
+		       mutex_unlock(&osb->recovery_lock),
+		       mutex_lock(&osb->recovery_lock));
+out_lock:
+	mutex_unlock(&osb->recovery_lock);
+
+	/*
+	 * At this point we know that no more recovery work can be queued so
+	 * wait for any recovery completion work to complete.
+	 */
+	if (osb->ocfs2_wq)
+		flush_workqueue(osb->ocfs2_wq);
+}
+
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb)
+{
+	ocfs2_recovery_disable(osb, OCFS2_REC_QUOTA_WANT_DISABLE);
+}
+
 void ocfs2_recovery_exit(struct ocfs2_super *osb)
 {
 	struct ocfs2_recovery_map *rm;
 
 	/* disable any new recovery threads and wait for any currently
 	 * running ones to exit. Do this before setting the vol_state. */
-	mutex_lock(&osb->recovery_lock);
-	osb->disable_recovery = 1;
-	mutex_unlock(&osb->recovery_lock);
-	wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb));
-
-	/* At this point, we know that no more recovery threads can be
-	 * launched, so wait for any recovery completion work to
-	 * complete. */
-	if (osb->ocfs2_wq)
-		flush_workqueue(osb->ocfs2_wq);
+	ocfs2_recovery_disable(osb, OCFS2_REC_WANT_DISABLE);
 
 	/*
 	 * Now that recovery is shut down, and the osb is about to be
@@ -1472,6 +1494,18 @@ static int __ocfs2_recovery_thread(void *arg)
 		}
 	}
 restart:
+	if (quota_enabled) {
+		mutex_lock(&osb->recovery_lock);
+		/* Confirm that recovery thread will no longer recover quotas */
+		if (osb->recovery_state == OCFS2_REC_QUOTA_WANT_DISABLE) {
+			osb->recovery_state = OCFS2_REC_QUOTA_DISABLED;
+			wake_up(&osb->recovery_event);
+		}
+		if (osb->recovery_state >= OCFS2_REC_QUOTA_DISABLED)
+			quota_enabled = 0;
+		mutex_unlock(&osb->recovery_lock);
+	}
+
 	status = ocfs2_super_lock(osb, 1);
 	if (status < 0) {
 		mlog_errno(status);
@@ -1569,27 +1603,29 @@ bail:
 
 	ocfs2_free_replay_slots(osb);
 	osb->recovery_thread_task = NULL;
-	mb(); /* sync with ocfs2_recovery_thread_running */
+	if (osb->recovery_state == OCFS2_REC_WANT_DISABLE)
+		osb->recovery_state = OCFS2_REC_DISABLED;
 	wake_up(&osb->recovery_event);
 
 	mutex_unlock(&osb->recovery_lock);
 
-	if (quota_enabled)
-		kfree(rm_quota);
+	kfree(rm_quota);
 
 	return status;
 }
 
 void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
 {
+	int was_set = -1;
+
 	mutex_lock(&osb->recovery_lock);
+	if (osb->recovery_state < OCFS2_REC_WANT_DISABLE)
+		was_set = ocfs2_recovery_map_set(osb, node_num);
 
 	trace_ocfs2_recovery_thread(node_num, osb->node_num,
-		osb->disable_recovery, osb->recovery_thread_task,
-		osb->disable_recovery ?
-		-1 : ocfs2_recovery_map_set(osb, node_num));
+		osb->recovery_state, osb->recovery_thread_task, was_set);
 
-	if (osb->disable_recovery)
+	if (osb->recovery_state >= OCFS2_REC_WANT_DISABLE)
 		goto out;
 
 	if (osb->recovery_thread_task)
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index e3c3a35dc5e0..6397170f302f 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -148,6 +148,7 @@ void ocfs2_wait_for_recovery(struct ocfs2_super *osb);
 
 int ocfs2_recovery_init(struct ocfs2_super *osb);
 void ocfs2_recovery_exit(struct ocfs2_super *osb);
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb);
 
 int ocfs2_compute_replay_slots(struct ocfs2_super *osb);
 void ocfs2_free_replay_slots(struct ocfs2_super *osb);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 51c52768132d..6aaa94c554c1 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -308,6 +308,21 @@ enum ocfs2_journal_trigger_type {
 void ocfs2_initialize_journal_triggers(struct super_block *sb,
 				       struct ocfs2_triggers triggers[]);
 
+enum ocfs2_recovery_state {
+	OCFS2_REC_ENABLED = 0,
+	OCFS2_REC_QUOTA_WANT_DISABLE,
+	/*
+	 * Must be OCFS2_REC_QUOTA_WANT_DISABLE + 1 for
+	 * ocfs2_recovery_disable_quota() to work.
+	 */
+	OCFS2_REC_QUOTA_DISABLED,
+	OCFS2_REC_WANT_DISABLE,
+	/*
+	 * Must be OCFS2_REC_WANT_DISABLE + 1 for ocfs2_recovery_exit() to work
+	 */
+	OCFS2_REC_DISABLED,
+};
+
 struct ocfs2_journal;
 struct ocfs2_slot_info;
 struct ocfs2_recovery_map;
@@ -370,7 +385,7 @@ struct ocfs2_super
 	struct ocfs2_recovery_map *recovery_map;
 	struct ocfs2_replay_map *replay_map;
 	struct task_struct *recovery_thread_task;
-	int disable_recovery;
+	enum ocfs2_recovery_state recovery_state;
 	wait_queue_head_t checkpoint_event;
 	struct ocfs2_journal *journal;
 	unsigned long osb_commit_interval;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2956d888c131..e272429da3db 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -453,8 +453,7 @@ out:
 
 /* Sync changes in local quota file into global quota file and
  * reinitialize local quota file.
- * The function expects local quota file to be already locked and
- * s_umount locked in shared mode. */
+ * The function expects local quota file to be already locked. */
 static int ocfs2_recover_local_quota_file(struct inode *lqinode,
 					  int type,
 					  struct ocfs2_quota_recovery *rec)
@@ -588,7 +587,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 {
 	unsigned int ino[OCFS2_MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE,
 					      LOCAL_GROUP_QUOTA_SYSTEM_INODE };
-	struct super_block *sb = osb->sb;
 	struct ocfs2_local_disk_dqinfo *ldinfo;
 	struct buffer_head *bh;
 	handle_t *handle;
@@ -600,7 +598,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 	printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for "
 	       "slot %u\n", osb->dev_str, slot_num);
 
-	down_read(&sb->s_umount);
 	for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
 		if (list_empty(&(rec->r_list[type])))
 			continue;
@@ -677,7 +674,6 @@ out_put:
 			break;
 	}
 out:
-	up_read(&sb->s_umount);
 	kfree(rec);
 	return status;
 }
@@ -843,8 +839,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type)
 	ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk);
 
 	/*
-	 * s_umount held in exclusive mode protects us against racing with
-	 * recovery thread...
+	 * ocfs2_dismount_volume() has already aborted quota recovery...
 	 */
 	if (oinfo->dqi_rec) {
 		ocfs2_free_quota_recovery(oinfo->dqi_rec);
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index f7b483f0de2a..6ac4dcd54588 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -698,10 +698,12 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 
 	bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode,
 					       ac, cl);
-	if (PTR_ERR(bg_bh) == -ENOSPC)
+	if (PTR_ERR(bg_bh) == -ENOSPC) {
+		ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
 		bg_bh = ocfs2_block_group_alloc_discontig(handle,
 							  alloc_inode,
 							  ac, cl);
+	}
 	if (IS_ERR(bg_bh)) {
 		status = PTR_ERR(bg_bh);
 		bg_bh = NULL;
@@ -1794,6 +1796,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
 {
 	int status;
 	u16 chain;
+	u32 contig_bits;
 	u64 next_group;
 	struct inode *alloc_inode = ac->ac_inode;
 	struct buffer_head *group_bh = NULL;
@@ -1819,10 +1822,21 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
 	status = -ENOSPC;
 	/* for now, the chain search is a bit simplistic. We just use
 	 * the 1st group with any empty bits. */
-	while ((status = ac->ac_group_search(alloc_inode, group_bh,
-					     bits_wanted, min_bits,
-					     ac->ac_max_block,
-					     res)) == -ENOSPC) {
+	while (1) {
+		if (ac->ac_which == OCFS2_AC_USE_MAIN_DISCONTIG) {
+			contig_bits = le16_to_cpu(bg->bg_contig_free_bits);
+			if (!contig_bits)
+				contig_bits = ocfs2_find_max_contig_free_bits(bg->bg_bitmap,
+						le16_to_cpu(bg->bg_bits), 0);
+			if (bits_wanted > contig_bits && contig_bits >= min_bits)
+				bits_wanted = contig_bits;
+		}
+
+		status = ac->ac_group_search(alloc_inode, group_bh,
+				bits_wanted, min_bits,
+				ac->ac_max_block, res);
+		if (status != -ENOSPC)
+			break;
 		if (!bg->bg_next_group)
 			break;
 
@@ -1982,6 +1996,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 	victim = ocfs2_find_victim_chain(cl);
 	ac->ac_chain = victim;
 
+search:
 	status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
 				    res, &bits_left);
 	if (!status) {
@@ -2022,6 +2037,16 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 		}
 	}
 
+	/* Chains can't supply the bits_wanted contiguous space.
+	 * We should switch to using every single bit when allocating
+	 * from the global bitmap. */
+	if (i == le16_to_cpu(cl->cl_next_free_rec) &&
+	    status == -ENOSPC && ac->ac_which == OCFS2_AC_USE_MAIN) {
+		ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
+		ac->ac_chain = victim;
+		goto search;
+	}
+
 set_hint:
 	if (status != -ENOSPC) {
 		/* If the next search of this group is not likely to
@@ -2365,7 +2390,8 @@ int __ocfs2_claim_clusters(handle_t *handle,
 	BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted);
 
 	BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL
-	       && ac->ac_which != OCFS2_AC_USE_MAIN);
+	       && ac->ac_which != OCFS2_AC_USE_MAIN
+	       && ac->ac_which != OCFS2_AC_USE_MAIN_DISCONTIG);
 
 	if (ac->ac_which == OCFS2_AC_USE_LOCAL) {
 		WARN_ON(min_clusters > 1);
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index b481b834857d..bcf2ed4a8631 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -29,6 +29,7 @@ struct ocfs2_alloc_context {
 #define OCFS2_AC_USE_MAIN  2
 #define OCFS2_AC_USE_INODE 3
 #define OCFS2_AC_USE_META  4
+#define OCFS2_AC_USE_MAIN_DISCONTIG  5
 	u32    ac_which;
 
 	/* these are used by the chain search */
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 4e6dcb638fd4..77a6b6a65044 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1868,6 +1868,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	/* Orphan scan should be stopped as early as possible */
 	ocfs2_orphan_scan_stop(osb);
 
+	/* Stop quota recovery so that we can disable quotas */
+	ocfs2_recovery_disable_quota(osb);
+
 	ocfs2_disable_quotas(osb);
 
 	/* All dquots should be freed by now */
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index 9c0ef4195b58..749794667295 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -29,7 +29,6 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
 {
 	struct cached_fid *cfid;
 
-	spin_lock(&cfids->cfid_list_lock);
 	list_for_each_entry(cfid, &cfids->entries, entry) {
 		if (!strcmp(cfid->path, path)) {
 			/*
@@ -38,25 +37,20 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
 			 * being deleted due to a lease break.
 			 */
 			if (!cfid->time || !cfid->has_lease) {
-				spin_unlock(&cfids->cfid_list_lock);
 				return NULL;
 			}
 			kref_get(&cfid->refcount);
-			spin_unlock(&cfids->cfid_list_lock);
 			return cfid;
 		}
 	}
 	if (lookup_only) {
-		spin_unlock(&cfids->cfid_list_lock);
 		return NULL;
 	}
 	if (cfids->num_entries >= max_cached_dirs) {
-		spin_unlock(&cfids->cfid_list_lock);
 		return NULL;
 	}
 	cfid = init_cached_dir(path);
 	if (cfid == NULL) {
-		spin_unlock(&cfids->cfid_list_lock);
 		return NULL;
 	}
 	cfid->cfids = cfids;
@@ -74,7 +68,6 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
 	 */
 	cfid->has_lease = true;
 
-	spin_unlock(&cfids->cfid_list_lock);
 	return cfid;
 }
 
@@ -185,8 +178,10 @@ replay_again:
 	if (!utf16_path)
 		return -ENOMEM;
 
+	spin_lock(&cfids->cfid_list_lock);
 	cfid = find_or_create_cached_dir(cfids, path, lookup_only, tcon->max_cached_dirs);
 	if (cfid == NULL) {
+		spin_unlock(&cfids->cfid_list_lock);
 		kfree(utf16_path);
 		return -ENOENT;
 	}
@@ -195,7 +190,6 @@ replay_again:
 	 * Otherwise, it is either a new entry or laundromat worker removed it
 	 * from @cfids->entries.  Caller will put last reference if the latter.
 	 */
-	spin_lock(&cfids->cfid_list_lock);
 	if (cfid->has_lease && cfid->time) {
 		spin_unlock(&cfids->cfid_list_lock);
 		*ret_cfid = cfid;
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index c83e4a10afcc..450c81abb494 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1586,8 +1586,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 	user_uffdio_copy = (struct uffdio_copy __user *) arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_copy, user_uffdio_copy,
@@ -1642,8 +1645,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 	user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
@@ -1745,8 +1751,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
 	user_uffdio_continue = (struct uffdio_continue __user *)arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_continue, user_uffdio_continue,
@@ -1802,8 +1811,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long
 	user_uffdio_poison = (struct uffdio_poison __user *)arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_poison->updated)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_poison, user_uffdio_poison,
@@ -1871,8 +1883,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
 
 	user_uffdio_move = (struct uffdio_move __user *) arg;
 
-	if (atomic_read(&ctx->mmap_changing))
-		return -EAGAIN;
+	ret = -EAGAIN;
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_move->move)))
+			return -EFAULT;
+		goto out;
+	}
 
 	if (copy_from_user(&uffdio_move, user_uffdio_move,
 			   /* don't copy "move" last field */
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index fef5c6e3b251..06f84108a063 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -884,6 +884,14 @@ bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags)
 	struct io_ring_ctx *ctx = req->ctx;
 	bool posted;
 
+	/*
+	 * If multishot has already posted deferred completions, ensure that
+	 * those are flushed first before posting this one. If not, CQEs
+	 * could get reordered.
+	 */
+	if (!wq_list_empty(&ctx->submit_state.compl_reqs))
+		__io_submit_flush_completions(ctx);
+
 	lockdep_assert(!io_wq_current_is_worker());
 	lockdep_assert_held(&ctx->uring_lock);
 
diff --git a/kernel/params.c b/kernel/params.c
index 33b2985b31c7..9935ff599356 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -949,7 +949,9 @@ struct kset *module_kset;
 static void module_kobj_release(struct kobject *kobj)
 {
 	struct module_kobject *mk = to_module_kobject(kobj);
-	complete(mk->kobj_completion);
+
+	if (mk->kobj_completion)
+		complete(mk->kobj_completion);
 }
 
 const struct kobj_type module_ktype = {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 3f6ef7f74207..04fd908a074c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2883,6 +2883,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
 			   pmd_t *pmd, bool freeze, struct folio *folio)
 {
+	bool pmd_migration = is_pmd_migration_entry(*pmd);
+
 	VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio));
 	VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE));
 	VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
@@ -2893,9 +2895,12 @@ void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
 	 * require a folio to check the PMD against. Otherwise, there
 	 * is a risk of replacing the wrong folio.
 	 */
-	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
-	    is_pmd_migration_entry(*pmd)) {
-		if (folio && folio != pmd_folio(*pmd))
+	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || pmd_migration) {
+		/*
+		 * Do not apply pmd_folio() to a migration entry; and folio lock
+		 * guarantees that it must be of the wrong folio anyway.
+		 */
+		if (folio && (pmd_migration || folio != pmd_folio(*pmd)))
 			return;
 		__split_huge_pmd_locked(vma, pmd, address, freeze);
 	}
diff --git a/mm/memblock.c b/mm/memblock.c
index 6a5ccb6dd48c..3331d6cf9605 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -461,7 +461,14 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 				min(new_area_start, memblock.current_limit),
 				new_alloc_size, PAGE_SIZE);
 
-		new_array = addr ? __va(addr) : NULL;
+		if (addr) {
+			/* The memory may not have been accepted, yet. */
+			accept_memory(addr, new_alloc_size);
+
+			new_array = __va(addr);
+		} else {
+			new_array = NULL;
+		}
 	}
 	if (!addr) {
 		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c
index 2c3a0eb6b22d..9bc4591c7b16 100644
--- a/tools/testing/selftests/mm/compaction_test.c
+++ b/tools/testing/selftests/mm/compaction_test.c
@@ -90,6 +90,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
 	int compaction_index = 0;
 	char nr_hugepages[20] = {0};
 	char init_nr_hugepages[24] = {0};
+	char target_nr_hugepages[24] = {0};
+	int slen;
 
 	snprintf(init_nr_hugepages, sizeof(init_nr_hugepages),
 		 "%lu", initial_nr_hugepages);
@@ -106,11 +108,18 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
 		goto out;
 	}
 
-	/* Request a large number of huge pages. The Kernel will allocate
-	   as much as it can */
-	if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) {
-		ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n",
-			       strerror(errno));
+	/*
+	 * Request huge pages for about half of the free memory. The Kernel
+	 * will allocate as much as it can, and we expect it will get at least 1/3
+	 */
+	nr_hugepages_ul = mem_free / hugepage_size / 2;
+	snprintf(target_nr_hugepages, sizeof(target_nr_hugepages),
+		 "%lu", nr_hugepages_ul);
+
+	slen = strlen(target_nr_hugepages);
+	if (write(fd, target_nr_hugepages, slen) != slen) {
+		ksft_print_msg("Failed to write %lu to /proc/sys/vm/nr_hugepages: %s\n",
+			       nr_hugepages_ul, strerror(errno));
 		goto close_fd;
 	}
 
diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h
index 3d0c0bdae5bc..e90af82f8688 100644
--- a/tools/testing/selftests/mm/pkey-powerpc.h
+++ b/tools/testing/selftests/mm/pkey-powerpc.h
@@ -102,8 +102,18 @@ void expect_fault_on_read_execonly_key(void *p1, int pkey)
 	return;
 }
 
+#define REPEAT_8(s) s s s s s s s s
+#define REPEAT_64(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) \
+		     REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s)
+#define REPEAT_512(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) \
+		      REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s)
+#define REPEAT_4096(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) \
+		       REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s)
+#define REPEAT_16384(s) REPEAT_4096(s) REPEAT_4096(s) \
+			REPEAT_4096(s) REPEAT_4096(s)
+
 /* 4-byte instructions * 16384 = 64K page */
-#define __page_o_noops() asm(".rept 16384 ; nop; .endr")
+#define __page_o_noops() asm(REPEAT_16384("nop\n"))
 
 void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
 {