Update 5.10.x+fslc up to v5.10.60

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 10
-SUBLEVEL = 59
+SUBLEVEL = 60
 EXTRAVERSION =
 NAME = Dare mighty things
 

arch/arc/kernel/fpu.c

@@ -57,23 +57,26 @@ void fpu_save_restore(struct task_struct *prev, struct task_struct *next)
 
 void fpu_init_task(struct pt_regs *regs)
 {
+	const unsigned int fwe = 0x80000000;
+
 	/* default rounding mode */
 	write_aux_reg(ARC_REG_FPU_CTRL, 0x100);
 
-	/* set "Write enable" to allow explicit write to exception flags */
-	write_aux_reg(ARC_REG_FPU_STATUS, 0x80000000);
+	/* Initialize to zero: setting requires FWE be set */
+	write_aux_reg(ARC_REG_FPU_STATUS, fwe);
 }
 
 void fpu_save_restore(struct task_struct *prev, struct task_struct *next)
 {
 	struct arc_fpu *save = &prev->thread.fpu;
 	struct arc_fpu *restore = &next->thread.fpu;
+	const unsigned int fwe = 0x80000000;
 
 	save->ctrl = read_aux_reg(ARC_REG_FPU_CTRL);
 	save->status = read_aux_reg(ARC_REG_FPU_STATUS);
 
 	write_aux_reg(ARC_REG_FPU_CTRL, restore->ctrl);
-	write_aux_reg(ARC_REG_FPU_STATUS, restore->status);
+	write_aux_reg(ARC_REG_FPU_STATUS, (fwe | restore->status));
 }
 
 #endif

arch/powerpc/kernel/kprobes.c

@@ -276,7 +276,8 @@ int kprobe_handler(struct pt_regs *regs)
 	if (user_mode(regs))
 		return 0;
 
-	if (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR))
+	if (!IS_ENABLED(CONFIG_BOOKE) &&
+	    (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR)))
 		return 0;
 
 	/*

arch/powerpc/kernel/sysfs.c

@@ -1167,7 +1167,7 @@ static int __init topology_init(void)
 		 * CPU.  For instance, the boot cpu might never be valid
 		 * for hotplugging.
 		 */
-		if (smp_ops->cpu_offline_self)
+		if (smp_ops && smp_ops->cpu_offline_self)
 			c->hotpluggable = 1;
 #endif
 

arch/x86/include/asm/svm.h

@@ -166,6 +166,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 #define V_IGN_TPR_SHIFT 20
 #define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT)
 
+#define V_IRQ_INJECTION_BITS_MASK (V_IRQ_MASK | V_INTR_PRIO_MASK | V_IGN_TPR_MASK)
+
 #define V_INTR_MASKING_SHIFT 24
 #define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
 

arch/x86/kernel/apic/io_apic.c

@@ -1948,7 +1948,8 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.irq_set_affinity	= ioapic_set_affinity,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_get_irqchip_state	= ioapic_irq_get_chip_state,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
+	.flags			= IRQCHIP_SKIP_SET_WAKE |
+				  IRQCHIP_AFFINITY_PRE_STARTUP,
 };
 
 static struct irq_chip ioapic_ir_chip __read_mostly = {
@@ -1961,7 +1962,8 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
 	.irq_set_affinity	= ioapic_set_affinity,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_get_irqchip_state	= ioapic_irq_get_chip_state,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
+	.flags			= IRQCHIP_SKIP_SET_WAKE |
+				  IRQCHIP_AFFINITY_PRE_STARTUP,
 };
 
 static inline void init_IO_APIC_traps(void)

arch/x86/kernel/apic/msi.c

@@ -86,11 +86,13 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force)
 	 *   The quirk bit is not set in this case.
 	 * - The new vector is the same as the old vector
 	 * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up)
+	 * - The interrupt is not yet started up
 	 * - The new destination CPU is the same as the old destination CPU
 	 */
 	if (!irqd_msi_nomask_quirk(irqd) ||
 	    cfg->vector == old_cfg.vector ||
 	    old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR ||
+	    !irqd_is_started(irqd) ||
 	    cfg->dest_apicid == old_cfg.dest_apicid) {
 		irq_msi_update_msg(irqd, cfg);
 		return ret;
@@ -178,7 +180,8 @@ static struct irq_chip pci_msi_controller = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_set_affinity	= msi_set_affinity,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
+	.flags			= IRQCHIP_SKIP_SET_WAKE |
+				  IRQCHIP_AFFINITY_PRE_STARTUP,
 };
 
 int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
@@ -247,7 +250,8 @@ static struct irq_chip pci_msi_ir_controller = {
 	.irq_mask		= pci_msi_mask_irq,
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
+	.flags			= IRQCHIP_SKIP_SET_WAKE |
+				  IRQCHIP_AFFINITY_PRE_STARTUP,
 };
 
 static struct msi_domain_info pci_msi_ir_domain_info = {
@@ -289,7 +293,8 @@ static struct irq_chip dmar_msi_controller = {
 	.irq_set_affinity	= msi_domain_set_affinity,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_write_msi_msg	= dmar_msi_write_msg,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
+	.flags			= IRQCHIP_SKIP_SET_WAKE |
+				  IRQCHIP_AFFINITY_PRE_STARTUP,
 };
 
 static int dmar_msi_init(struct irq_domain *domain,
@@ -381,7 +386,7 @@ static struct irq_chip hpet_msi_controller __ro_after_init = {
 	.irq_set_affinity = msi_domain_set_affinity,
 	.irq_retrigger = irq_chip_retrigger_hierarchy,
 	.irq_write_msi_msg = hpet_msi_write_msg,
-	.flags = IRQCHIP_SKIP_SET_WAKE,
+	.flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_AFFINITY_PRE_STARTUP,
 };
 
 static int hpet_msi_init(struct irq_domain *domain,

arch/x86/kernel/cpu/resctrl/monitor.c

@@ -222,15 +222,14 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 	return chunks >>= shift;
 }
 
-static int __mon_event_count(u32 rmid, struct rmid_read *rr)
+static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
 {
 	struct mbm_state *m;
 	u64 chunks, tval;
 
 	tval = __rmid_read(rmid, rr->evtid);
 	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
-		rr->val = tval;
-		return -EINVAL;
+		return tval;
 	}
 	switch (rr->evtid) {
 	case QOS_L3_OCCUP_EVENT_ID:
@@ -242,12 +241,6 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 	case QOS_L3_MBM_LOCAL_EVENT_ID:
 		m = &rr->d->mbm_local[rmid];
 		break;
-	default:
-		/*
-		 * Code would never reach here because
-		 * an invalid event id would fail the __rmid_read.
-		 */
-		return -EINVAL;
 	}
 
 	if (rr->first) {
@@ -297,23 +290,29 @@ void mon_event_count(void *info)
 	struct rdtgroup *rdtgrp, *entry;
 	struct rmid_read *rr = info;
 	struct list_head *head;
+	u64 ret_val;
 
 	rdtgrp = rr->rgrp;
 
-	if (__mon_event_count(rdtgrp->mon.rmid, rr))
-		return;
+	ret_val = __mon_event_count(rdtgrp->mon.rmid, rr);
 
 	/*
-	 * For Ctrl groups read data from child monitor groups.
+	 * For Ctrl groups read data from child monitor groups and
+	 * add them together. Count events which are read successfully.
+	 * Discard the rmid_read's reporting errors.
 	 */
 	head = &rdtgrp->mon.crdtgrp_list;
 
 	if (rdtgrp->type == RDTCTRL_GROUP) {
 		list_for_each_entry(entry, head, mon.crdtgrp_list) {
-			if (__mon_event_count(entry->mon.rmid, rr))
-				return;
+			if (__mon_event_count(entry->mon.rmid, rr) == 0)
+				ret_val = 0;
 		}
 	}
+
+	/* Report error if none of rmid_reads are successful */
+	if (ret_val)
+		rr->val = ret_val;
 }
 
 /*

arch/x86/kvm/svm/nested.c

@@ -147,6 +147,9 @@ void recalc_intercepts(struct vcpu_svm *svm)
 
 	for (i = 0; i < MAX_INTERCEPT; i++)
 		c->intercepts[i] |= g->intercepts[i];
+
+	vmcb_set_intercept(c, INTERCEPT_VMLOAD);
+	vmcb_set_intercept(c, INTERCEPT_VMSAVE);
 }
 
 static void copy_vmcb_control_area(struct vmcb_control_area *dst,
@@ -429,17 +432,20 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 
 static void nested_prepare_vmcb_control(struct vcpu_svm *svm)
 {
-	const u32 mask = V_INTR_MASKING_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK;
+	const u32 int_ctl_vmcb01_bits =
+		V_INTR_MASKING_MASK | V_GIF_MASK | V_GIF_ENABLE_MASK;
+
+	const u32 int_ctl_vmcb12_bits = V_TPR_MASK | V_IRQ_INJECTION_BITS_MASK;
 
 	if (nested_npt_enabled(svm))
 		nested_svm_init_mmu_context(&svm->vcpu);
 
 	svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset =
 		svm->vcpu.arch.l1_tsc_offset + svm->nested.ctl.tsc_offset;
 
-	svm->vmcb->control.int_ctl             =
-		(svm->nested.ctl.int_ctl & ~mask) |
-		(svm->nested.hsave->control.int_ctl & mask);
+	svm->vmcb->control.int_ctl =
+		(svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) |
+		(svm->nested.hsave->control.int_ctl & int_ctl_vmcb01_bits);
 
 	svm->vmcb->control.virt_ext            = svm->nested.ctl.virt_ext;
 	svm->vmcb->control.int_vector          = svm->nested.ctl.int_vector;

arch/x86/kvm/svm/svm.c

@@ -1486,17 +1486,17 @@ static void svm_set_vintr(struct vcpu_svm *svm)
 
 static void svm_clear_vintr(struct vcpu_svm *svm)
 {
-	const u32 mask = V_TPR_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK | V_INTR_MASKING_MASK;
 	svm_clr_intercept(svm, INTERCEPT_VINTR);
 
 	/* Drop int_ctl fields related to VINTR injection.  */
-	svm->vmcb->control.int_ctl &= mask;
+	svm->vmcb->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK;
 	if (is_guest_mode(&svm->vcpu)) {
-		svm->nested.hsave->control.int_ctl &= mask;
+		svm->nested.hsave->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK;
 
 		WARN_ON((svm->vmcb->control.int_ctl & V_TPR_MASK) !=
 			(svm->nested.ctl.int_ctl & V_TPR_MASK));
-		svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & ~mask;
+		svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl &
+			V_IRQ_INJECTION_BITS_MASK;
 	}
 
 	vmcb_mark_dirty(svm->vmcb, VMCB_INTR);

arch/x86/kvm/vmx/nested.c

@@ -5779,7 +5779,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
 		if (is_nmi(intr_info))
 			return true;
 		else if (is_page_fault(intr_info))
-			return vcpu->arch.apf.host_apf_flags || !enable_ept;
+			return vcpu->arch.apf.host_apf_flags ||
+			       vmx_need_pf_intercept(vcpu);
 		else if (is_debug(intr_info) &&
 			 vcpu->guest_debug &
 			 (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))

arch/x86/kvm/vmx/vmx.h

@@ -488,7 +488,7 @@ static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx)
 
 static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
 {
-	return vmx->secondary_exec_control &
+	return secondary_exec_controls_get(vmx) &
 		SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
 }
 

arch/x86/tools/chkobjdump.awk

@@ -10,6 +10,7 @@ BEGIN {
 
 /^GNU objdump/ {
 	verstr = ""
+	gsub(/\(.*\)/, "");
 	for (i = 3; i <= NF; i++)
 		if (match($(i), "^[0-9]")) {
 			verstr = $(i);

drivers/acpi/nfit/core.c

@@ -3031,6 +3031,9 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 		struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev;
 		struct nd_mapping_desc *mapping;
 
+		/* range index 0 == unmapped in SPA or invalid-SPA */
+		if (memdev->range_index == 0 || spa->range_index == 0)
+			continue;
 		if (memdev->range_index != spa->range_index)
 			continue;
 		if (count >= ND_MAX_MAPPINGS) {

drivers/base/core.c

@@ -2452,6 +2452,7 @@ void device_initialize(struct device *dev)
 	device_pm_init(dev);
 	set_dev_node(dev, -1);
 #ifdef CONFIG_GENERIC_MSI_IRQ
+	raw_spin_lock_init(&dev->msi_lock);
 	INIT_LIST_HEAD(&dev->msi_list);
 #endif
 	INIT_LIST_HEAD(&dev->links.consumers);

drivers/block/nbd.c

@@ -812,6 +812,10 @@ static bool nbd_clear_req(struct request *req, void *data, bool reserved)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
 
+	/* don't abort one completed request */
+	if (blk_mq_request_completed(req))
+		return true;
+
 	mutex_lock(&cmd->lock);
 	cmd->status = BLK_STS_IOERR;
 	mutex_unlock(&cmd->lock);
@@ -2024,15 +2028,19 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd)
 {
 	mutex_lock(&nbd->config_lock);
 	nbd_disconnect(nbd);
-	nbd_clear_sock(nbd);
-	mutex_unlock(&nbd->config_lock);
+	sock_shutdown(nbd);
 	/*
 	 * Make sure recv thread has finished, so it does not drop the last
 	 * config ref and try to destroy the workqueue from inside the work
-	 * queue.
+	 * queue. And this also ensure that we can safely call nbd_clear_que()
+	 * to cancel the inflight I/Os.
 	 */
 	if (nbd->recv_workq)
 		flush_workqueue(nbd->recv_workq);
+	nbd_clear_que(nbd);
+	nbd->task_setup = NULL;
+	mutex_unlock(&nbd->config_lock);
+
 	if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF,
 			       &nbd->config->runtime_flags))
 		nbd_config_put(nbd);