diff --git a/Makefile b/Makefile
index e848c6ea248b..b73dbc51a03b 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc7
+EXTRAVERSION = -rc8
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 4745bb9998bd..6d8492b6e2b8 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -602,6 +602,7 @@ ____##func(struct pt_regs *regs)
 /* kernel/traps.c */
 DECLARE_INTERRUPT_HANDLER_NMI(system_reset_exception);
 #ifdef CONFIG_PPC_BOOK3S_64
+DECLARE_INTERRUPT_HANDLER_RAW(machine_check_early_boot);
 DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async);
 #endif
 DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception);
diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
index 43f1c76d48ce..a379b0ce19ff 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -113,23 +113,19 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 {
 	int i;
 
+	/* Initialize tail_call_cnt, to be skipped if we do tail calls. */
+	EMIT(PPC_RAW_LI(_R4, 0));
+
+#define BPF_TAILCALL_PROLOGUE_SIZE	4
+
+	EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx)));
+
+	if (ctx->seen & SEEN_TAILCALL)
+		EMIT(PPC_RAW_STW(_R4, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
+
 	/* First arg comes in as a 32 bits pointer. */
 	EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_1), _R3));
 	EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0));
-	EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx)));
-
-	/*
-	 * Initialize tail_call_cnt in stack frame if we do tail calls.
-	 * Otherwise, put in NOPs so that it can be skipped when we are
-	 * invoked through a tail call.
-	 */
-	if (ctx->seen & SEEN_TAILCALL)
-		EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_1) - 1, _R1,
-				 bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
-	else
-		EMIT(PPC_RAW_NOP());
-
-#define BPF_TAILCALL_PROLOGUE_SIZE	16
 
 	/*
 	 * We need a stack frame, but we don't necessarily need to
@@ -170,6 +166,16 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx
 	for (i = BPF_PPC_NVR_MIN; i <= 31; i++)
 		if (bpf_is_seen_register(ctx, i))
 			EMIT(PPC_RAW_LWZ(i, _R1, bpf_jit_stack_offsetof(ctx, i)));
+
+	if (ctx->seen & SEEN_FUNC)
+		EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF));
+
+	/* Tear down our stack frame */
+	EMIT(PPC_RAW_ADDI(_R1, _R1, BPF_PPC_STACKFRAME(ctx)));
+
+	if (ctx->seen & SEEN_FUNC)
+		EMIT(PPC_RAW_MTLR(_R0));
+
 }
 
 void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
@@ -178,16 +184,6 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 
 	bpf_jit_emit_common_epilogue(image, ctx);
 
-	/* Tear down our stack frame */
-
-	if (ctx->seen & SEEN_FUNC)
-		EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF));
-
-	EMIT(PPC_RAW_ADDI(_R1, _R1, BPF_PPC_STACKFRAME(ctx)));
-
-	if (ctx->seen & SEEN_FUNC)
-		EMIT(PPC_RAW_MTLR(_R0));
-
 	EMIT(PPC_RAW_BLR());
 }
 
@@ -244,7 +240,6 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	EMIT(PPC_RAW_RLWINM(_R3, b2p_index, 2, 0, 29));
 	EMIT(PPC_RAW_ADD(_R3, _R3, b2p_bpf_array));
 	EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_array, ptrs)));
-	EMIT(PPC_RAW_STW(_R0, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
 
 	/*
 	 * if (prog == NULL)
@@ -255,19 +250,14 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 
 	/* goto *(prog->bpf_func + prologue_size); */
 	EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_prog, bpf_func)));
-
-	if (ctx->seen & SEEN_FUNC)
-		EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF));
-
 	EMIT(PPC_RAW_ADDIC(_R3, _R3, BPF_TAILCALL_PROLOGUE_SIZE));
-
-	if (ctx->seen & SEEN_FUNC)
-		EMIT(PPC_RAW_MTLR(_R0));
-
 	EMIT(PPC_RAW_MTCTR(_R3));
 
 	EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_1)));
 
+	/* Put tail_call_cnt in r4 */
+	EMIT(PPC_RAW_MR(_R4, _R0));
+
 	/* tear restore NVRs, ... */
 	bpf_jit_emit_common_epilogue(image, ctx);
 
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 23f49a2f4d14..6cceca64a6bc 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -562,17 +562,26 @@ static int initiator_cmp(void *priv, const struct list_head *a,
 {
 	struct memory_initiator *ia;
 	struct memory_initiator *ib;
-	unsigned long *p_nodes = priv;
 
 	ia = list_entry(a, struct memory_initiator, node);
 	ib = list_entry(b, struct memory_initiator, node);
 
-	set_bit(ia->processor_pxm, p_nodes);
-	set_bit(ib->processor_pxm, p_nodes);
-
 	return ia->processor_pxm - ib->processor_pxm;
 }
 
+static int initiators_to_nodemask(unsigned long *p_nodes)
+{
+	struct memory_initiator *initiator;
+
+	if (list_empty(&initiators))
+		return -ENXIO;
+
+	list_for_each_entry(initiator, &initiators, node)
+		set_bit(initiator->processor_pxm, p_nodes);
+
+	return 0;
+}
+
 static void hmat_register_target_initiators(struct memory_target *target)
 {
 	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
@@ -609,7 +618,10 @@ static void hmat_register_target_initiators(struct memory_target *target)
 	 * initiators.
 	 */
 	bitmap_zero(p_nodes, MAX_NUMNODES);
-	list_sort(p_nodes, &initiators, initiator_cmp);
+	list_sort(NULL, &initiators, initiator_cmp);
+	if (initiators_to_nodemask(p_nodes) < 0)
+		return;
+
 	if (!access0done) {
 		for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) {
 			loc = localities_types[i];
@@ -643,8 +655,9 @@ static void hmat_register_target_initiators(struct memory_target *target)
 
 	/* Access 1 ignores Generic Initiators */
 	bitmap_zero(p_nodes, MAX_NUMNODES);
-	list_sort(p_nodes, &initiators, initiator_cmp);
-	best = 0;
+	if (initiators_to_nodemask(p_nodes) < 0)
+		return;
+
 	for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) {
 		loc = localities_types[i];
 		if (!loc)
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 1621ce818705..d69905233aff 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -401,13 +401,14 @@ int tpm_pm_suspend(struct device *dev)
 	    !pm_suspend_via_firmware())
 		goto suspended;
 
-	if (!tpm_chip_start(chip)) {
+	rc = tpm_try_get_ops(chip);
+	if (!rc) {
 		if (chip->flags & TPM_CHIP_FLAG_TPM2)
 			tpm2_shutdown(chip, TPM2_SU_STATE);
 		else
 			rc = tpm1_pm_suspend(chip, tpm_suspend_pcr);
 
-		tpm_chip_stop(chip);
+		tpm_put_ops(chip);
 	}
 
 suspended:
diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c
index 969a552da8d2..a0d66fabf073 100644
--- a/drivers/clocksource/timer-riscv.c
+++ b/drivers/clocksource/timer-riscv.c
@@ -51,7 +51,7 @@ static int riscv_clock_next_event(unsigned long delta,
 static unsigned int riscv_clock_event_irq;
 static DEFINE_PER_CPU(struct clock_event_device, riscv_clock_event) = {
 	.name			= "riscv_timer_clockevent",
-	.features		= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP,
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
 	.rating			= 100,
 	.set_next_event		= riscv_clock_next_event,
 };
diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c
index 97086fab698e..903325aac991 100644
--- a/drivers/dax/hmem/device.c
+++ b/drivers/dax/hmem/device.c
@@ -8,6 +8,13 @@
 static bool nohmem;
 module_param_named(disable, nohmem, bool, 0444);
 
+static struct resource hmem_active = {
+	.name = "HMEM devices",
+	.start = 0,
+	.end = -1,
+	.flags = IORESOURCE_MEM,
+};
+
 void hmem_register_device(int target_nid, struct resource *r)
 {
 	/* define a clean / non-busy resource for the platform device */
@@ -41,6 +48,12 @@ void hmem_register_device(int target_nid, struct resource *r)
 		goto out_pdev;
 	}
 
+	if (!__request_region(&hmem_active, res.start, resource_size(&res),
+			      dev_name(&pdev->dev), 0)) {
+		dev_dbg(&pdev->dev, "hmem range %pr already active\n", &res);
+		goto out_active;
+	}
+
 	pdev->dev.numa_node = numa_map_to_online_node(target_nid);
 	info = (struct memregion_info) {
 		.target_node = target_nid,
@@ -66,6 +79,8 @@ void hmem_register_device(int target_nid, struct resource *r)
 	return;
 
 out_resource:
+	__release_region(&hmem_active, res.start, resource_size(&res));
+out_active:
 	platform_device_put(pdev);
 out_pdev:
 	memregion_free(id);
@@ -73,15 +88,6 @@ out_pdev:
 
 static __init int hmem_register_one(struct resource *res, void *data)
 {
-	/*
-	 * If the resource is not a top-level resource it was already
-	 * assigned to a device by the HMAT parsing.
-	 */
-	if (res->parent != &iomem_resource) {
-		pr_info("HMEM: skip %pr, already claimed\n", res);
-		return 0;
-	}
-
 	hmem_register_device(phys_to_target_node(res->start), res);
 
 	return 0;
diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c
index fe0cd205502d..f58943cb1341 100644
--- a/drivers/i2c/busses/i2c-cadence.c
+++ b/drivers/i2c/busses/i2c-cadence.c
@@ -852,7 +852,8 @@ static int cdns_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs,
 					 CDNS_I2C_POLL_US, CDNS_I2C_TIMEOUT_US);
 	if (ret) {
 		ret = -EAGAIN;
-		i2c_recover_bus(adap);
+		if (id->adap.bus_recovery_info)
+			i2c_recover_bus(adap);
 		goto out;
 	}
 
@@ -1263,8 +1264,13 @@ static int cdns_i2c_probe(struct platform_device *pdev)
 
 	id->rinfo.pinctrl = devm_pinctrl_get(&pdev->dev);
 	if (IS_ERR(id->rinfo.pinctrl)) {
+		int err = PTR_ERR(id->rinfo.pinctrl);
+
 		dev_info(&pdev->dev, "can't get pinctrl, bus recovery not supported\n");
-		return PTR_ERR(id->rinfo.pinctrl);
+		if (err != -ENODEV)
+			return err;
+	} else {
+		id->adap.bus_recovery_info = &id->rinfo;
 	}
 
 	id->membase = devm_platform_get_and_ioremap_resource(pdev, 0, &r_mem);
@@ -1283,7 +1289,6 @@ static int cdns_i2c_probe(struct platform_device *pdev)
 	id->adap.retries = 3;		/* Default retry value. */
 	id->adap.algo_data = id;
 	id->adap.dev.parent = &pdev->dev;
-	id->adap.bus_recovery_info = &id->rinfo;
 	init_completion(&id->xfer_done);
 	snprintf(id->adap.name, sizeof(id->adap.name),
 		 "Cadence I2C at %08lx", (unsigned long)r_mem->start);
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 3082183bd66a..fc70920c4dda 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1132,7 +1132,8 @@ static int i2c_imx_read(struct imx_i2c_struct *i2c_imx, struct i2c_msg *msgs,
 	int i, result;
 	unsigned int temp;
 	int block_data = msgs->flags & I2C_M_RECV_LEN;
-	int use_dma = i2c_imx->dma && msgs->len >= DMA_THRESHOLD && !block_data;
+	int use_dma = i2c_imx->dma && msgs->flags & I2C_M_DMA_SAFE &&
+		msgs->len >= DMA_THRESHOLD && !block_data;
 
 	dev_dbg(&i2c_imx->adapter.dev,
 		"<%s> write slave address: addr=0x%x\n",
@@ -1298,7 +1299,8 @@ static int i2c_imx_xfer_common(struct i2c_adapter *adapter,
 			result = i2c_imx_read(i2c_imx, &msgs[i], is_lastmsg, atomic);
 		} else {
 			if (!atomic &&
-			    i2c_imx->dma && msgs[i].len >= DMA_THRESHOLD)
+			    i2c_imx->dma && msgs[i].len >= DMA_THRESHOLD &&
+				msgs[i].flags & I2C_M_DMA_SAFE)
 				result = i2c_imx_dma_write(i2c_imx, &msgs[i]);
 			else
 				result = i2c_imx_write(i2c_imx, &msgs[i], atomic);
diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c
index 0c365b57d957..83457359ec45 100644
--- a/drivers/i2c/busses/i2c-npcm7xx.c
+++ b/drivers/i2c/busses/i2c-npcm7xx.c
@@ -2393,8 +2393,17 @@ static struct platform_driver npcm_i2c_bus_driver = {
 
 static int __init npcm_i2c_init(void)
 {
+	int ret;
+
 	npcm_i2c_debugfs_dir = debugfs_create_dir("npcm_i2c", NULL);
-	return platform_driver_register(&npcm_i2c_bus_driver);
+
+	ret = platform_driver_register(&npcm_i2c_bus_driver);
+	if (ret) {
+		debugfs_remove_recursive(npcm_i2c_debugfs_dir);
+		return ret;
+	}
+
+	return 0;
 }
 module_init(npcm_i2c_init);
 
diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
index 84a77512614d..8fce98bb77ff 100644
--- a/drivers/i2c/busses/i2c-qcom-geni.c
+++ b/drivers/i2c/busses/i2c-qcom-geni.c
@@ -626,7 +626,6 @@ static int geni_i2c_gpi_xfer(struct geni_i2c_dev *gi2c, struct i2c_msg msgs[], i
 			dev_err(gi2c->se.dev, "I2C timeout gpi flags:%d addr:0x%x\n",
 				gi2c->cur->flags, gi2c->cur->addr);
 			gi2c->err = -ETIMEDOUT;
-			goto err;
 		}
 
 		if (gi2c->err) {
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index b4edf10e8fd0..7539b0740351 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -467,6 +467,7 @@ static int i2c_device_probe(struct device *dev)
 {
 	struct i2c_client	*client = i2c_verify_client(dev);
 	struct i2c_driver	*driver;
+	bool do_power_on;
 	int status;
 
 	if (!client)
@@ -545,8 +546,8 @@ static int i2c_device_probe(struct device *dev)
 	if (status < 0)
 		goto err_clear_wakeup_irq;
 
-	status = dev_pm_domain_attach(&client->dev,
-				      !i2c_acpi_waive_d0_probe(dev));
+	do_power_on = !i2c_acpi_waive_d0_probe(dev);
+	status = dev_pm_domain_attach(&client->dev, do_power_on);
 	if (status)
 		goto err_clear_wakeup_irq;
 
@@ -585,7 +586,7 @@ static int i2c_device_probe(struct device *dev)
 err_release_driver_resources:
 	devres_release_group(&client->dev, client->devres_group_id);
 err_detach_pm_domain:
-	dev_pm_domain_detach(&client->dev, !i2c_acpi_waive_d0_probe(dev));
+	dev_pm_domain_detach(&client->dev, do_power_on);
 err_clear_wakeup_irq:
 	dev_pm_clear_wake_irq(&client->dev);
 	device_init_wakeup(&client->dev, false);
@@ -610,7 +611,7 @@ static void i2c_device_remove(struct device *dev)
 
 	devres_release_group(&client->dev, client->devres_group_id);
 
-	dev_pm_domain_detach(&client->dev, !i2c_acpi_waive_d0_probe(dev));
+	dev_pm_domain_detach(&client->dev, true);
 
 	dev_pm_clear_wake_irq(&client->dev);
 	device_init_wakeup(&client->dev, false);
diff --git a/drivers/input/touchscreen/raydium_i2c_ts.c b/drivers/input/touchscreen/raydium_i2c_ts.c
index 3a4952935366..3d9c5758d8a4 100644
--- a/drivers/input/touchscreen/raydium_i2c_ts.c
+++ b/drivers/input/touchscreen/raydium_i2c_ts.c
@@ -211,12 +211,14 @@ static int raydium_i2c_send(struct i2c_client *client,
 
 		error = raydium_i2c_xfer(client, addr, xfer, ARRAY_SIZE(xfer));
 		if (likely(!error))
-			return 0;
+			goto out;
 
 		msleep(RM_RETRY_DELAY_MS);
 	} while (++tries < RM_MAX_RETRIES);
 
 	dev_err(&client->dev, "%s failed: %d\n", __func__, error);
+out:
+	kfree(tx_buf);
 	return error;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0d72d74873cd..1b52cb1631c9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2291,6 +2291,7 @@ event_sched_out(struct perf_event *event,
 		    !event->pending_work) {
 			event->pending_work = 1;
 			dec = false;
+			WARN_ON_ONCE(!atomic_long_inc_not_zero(&event->refcount));
 			task_work_add(current, &event->pending_task, TWA_RESUME);
 		}
 		if (dec)
@@ -2336,6 +2337,7 @@ group_sched_out(struct perf_event *group_event,
 
 #define DETACH_GROUP	0x01UL
 #define DETACH_CHILD	0x02UL
+#define DETACH_DEAD	0x04UL
 
 /*
  * Cross CPU call to remove a performance event
@@ -2356,12 +2358,20 @@ __perf_remove_from_context(struct perf_event *event,
 		update_cgrp_time_from_cpuctx(cpuctx, false);
 	}
 
+	/*
+	 * Ensure event_sched_out() switches to OFF, at the very least
+	 * this avoids raising perf_pending_task() at this time.
+	 */
+	if (flags & DETACH_DEAD)
+		event->pending_disable = 1;
 	event_sched_out(event, cpuctx, ctx);
 	if (flags & DETACH_GROUP)
 		perf_group_detach(event);
 	if (flags & DETACH_CHILD)
 		perf_child_detach(event);
 	list_del_event(event, ctx);
+	if (flags & DETACH_DEAD)
+		event->state = PERF_EVENT_STATE_DEAD;
 
 	if (!ctx->nr_events && ctx->is_active) {
 		if (ctx == &cpuctx->ctx)
@@ -5122,9 +5132,7 @@ int perf_event_release_kernel(struct perf_event *event)
 
 	ctx = perf_event_ctx_lock(event);
 	WARN_ON_ONCE(ctx->parent_ctx);
-	perf_remove_from_context(event, DETACH_GROUP);
 
-	raw_spin_lock_irq(&ctx->lock);
 	/*
 	 * Mark this event as STATE_DEAD, there is no external reference to it
 	 * anymore.
@@ -5136,8 +5144,7 @@ int perf_event_release_kernel(struct perf_event *event)
 	 * Thus this guarantees that we will in fact observe and kill _ALL_
 	 * child events.
 	 */
-	event->state = PERF_EVENT_STATE_DEAD;
-	raw_spin_unlock_irq(&ctx->lock);
+	perf_remove_from_context(event, DETACH_GROUP|DETACH_DEAD);
 
 	perf_event_ctx_unlock(event, ctx);
 
@@ -6578,6 +6585,8 @@ static void perf_pending_task(struct callback_head *head)
 	if (rctx >= 0)
 		perf_swevent_put_recursion_context(rctx);
 	preempt_enable_notrace();
+
+	put_event(event);
 }
 
 #ifdef CONFIG_GUEST_PERF_EVENTS
diff --git a/mm/mmap.c b/mm/mmap.c
index e0c92b500df7..330226460741 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1780,9 +1780,6 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		 */
 		pgoff = 0;
 		get_area = shmem_get_unmapped_area;
-	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
-		/* Ensures that larger anonymous mappings are THP aligned. */
-		get_area = thp_get_unmapped_area;
 	}
 
 	addr = get_area(file, addr, len, pgoff, flags);