Merge tag 'v5.10-rc6' into rdma.git for-next

For dependencies in following patches

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

13 files changed, 91 insertions, 117 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 324ddd7fd0aa..7e5f33a0d0e2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1656,6 +1656,7 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
+int kvm_cpu_has_extint(struct kvm_vcpu *v);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index e039a933aca3..29dd27b5a339 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -88,8 +88,6 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx,
 
 static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
-	trace_hardirqs_on();
-
 	mds_idle_clear_cpu_buffers();
 	/* "mwait %eax, %ecx;" */
 	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 581fb7223ad0..d41b70fe4918 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -739,11 +739,13 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
 
+		spectre_v2_user_ibpb = mode;
 		switch (cmd) {
 		case SPECTRE_V2_USER_CMD_FORCE:
 		case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
 		case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
 			static_branch_enable(&switch_mm_always_ibpb);
+			spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT;
 			break;
 		case SPECTRE_V2_USER_CMD_PRCTL:
 		case SPECTRE_V2_USER_CMD_AUTO:
@@ -757,8 +759,6 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 		pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
 			static_key_enabled(&switch_mm_always_ibpb) ?
 			"always-on" : "conditional");
-
-		spectre_v2_user_ibpb = mode;
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4102b866e7c0..32b7099e3511 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1384,8 +1384,10 @@ noinstr void do_machine_check(struct pt_regs *regs)
 	 * When there's any problem use only local no_way_out state.
 	 */
 	if (!lmce) {
-		if (mce_end(order) < 0)
-			no_way_out = worst >= MCE_PANIC_SEVERITY;
+		if (mce_end(order) < 0) {
+			if (!no_way_out)
+				no_way_out = worst >= MCE_PANIC_SEVERITY;
+		}
 	} else {
 		/*
 		 * If there was a fatal machine check we should have
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index af323e2e3100..6f4ca4bea625 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -507,6 +507,24 @@ unlock:
 	return ret ?: nbytes;
 }
 
+/**
+ * rdtgroup_remove - the helper to remove resource group safely
+ * @rdtgrp: resource group to remove
+ *
+ * On resource group creation via a mkdir, an extra kernfs_node reference is
+ * taken to ensure that the rdtgroup structure remains accessible for the
+ * rdtgroup_kn_unlock() calls where it is removed.
+ *
+ * Drop the extra reference here, then free the rdtgroup structure.
+ *
+ * Return: void
+ */
+static void rdtgroup_remove(struct rdtgroup *rdtgrp)
+{
+	kernfs_put(rdtgrp->kn);
+	kfree(rdtgrp);
+}
+
 struct task_move_callback {
 	struct callback_head	work;
 	struct rdtgroup		*rdtgrp;
@@ -529,7 +547,7 @@ static void move_myself(struct callback_head *head)
 	    (rdtgrp->flags & RDT_DELETED)) {
 		current->closid = 0;
 		current->rmid = 0;
-		kfree(rdtgrp);
+		rdtgroup_remove(rdtgrp);
 	}
 
 	if (unlikely(current->flags & PF_EXITING))
@@ -1769,7 +1787,6 @@ static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name,
 	if (IS_ERR(kn_subdir))
 		return PTR_ERR(kn_subdir);
 
-	kernfs_get(kn_subdir);
 	ret = rdtgroup_kn_set_ugid(kn_subdir);
 	if (ret)
 		return ret;
@@ -1792,7 +1809,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 	kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
 	if (IS_ERR(kn_info))
 		return PTR_ERR(kn_info);
-	kernfs_get(kn_info);
 
 	ret = rdtgroup_add_files(kn_info, RF_TOP_INFO);
 	if (ret)
@@ -1813,12 +1829,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 			goto out_destroy;
 	}
 
-	/*
-	 * This extra ref will be put in kernfs_remove() and guarantees
-	 * that @rdtgrp->kn is always accessible.
-	 */
-	kernfs_get(kn_info);
-
 	ret = rdtgroup_kn_set_ugid(kn_info);
 	if (ret)
 		goto out_destroy;
@@ -1847,12 +1857,6 @@ mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp,
 	if (dest_kn)
 		*dest_kn = kn;
 
-	/*
-	 * This extra ref will be put in kernfs_remove() and guarantees
-	 * that @rdtgrp->kn is always accessible.
-	 */
-	kernfs_get(kn);
-
 	ret = rdtgroup_kn_set_ugid(kn);
 	if (ret)
 		goto out_destroy;
@@ -2079,8 +2083,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn)
 		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
 			rdtgroup_pseudo_lock_remove(rdtgrp);
 		kernfs_unbreak_active_protection(kn);
-		kernfs_put(rdtgrp->kn);
-		kfree(rdtgrp);
+		rdtgroup_remove(rdtgrp);
 	} else {
 		kernfs_unbreak_active_protection(kn);
 	}
@@ -2139,13 +2142,11 @@ static int rdt_get_tree(struct fs_context *fc)
 					  &kn_mongrp);
 		if (ret < 0)
 			goto out_info;
-		kernfs_get(kn_mongrp);
 
 		ret = mkdir_mondata_all(rdtgroup_default.kn,
 					&rdtgroup_default, &kn_mondata);
 		if (ret < 0)
 			goto out_mongrp;
-		kernfs_get(kn_mondata);
 		rdtgroup_default.mon.mon_data_kn = kn_mondata;
 	}
 
@@ -2357,7 +2358,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
 		if (atomic_read(&sentry->waitcount) != 0)
 			sentry->flags = RDT_DELETED;
 		else
-			kfree(sentry);
+			rdtgroup_remove(sentry);
 	}
 }
 
@@ -2399,7 +2400,7 @@ static void rmdir_all_sub(void)
 		if (atomic_read(&rdtgrp->waitcount) != 0)
 			rdtgrp->flags = RDT_DELETED;
 		else
-			kfree(rdtgrp);
+			rdtgroup_remove(rdtgrp);
 	}
 	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
 	update_closid_rmid(cpu_online_mask, &rdtgroup_default);
@@ -2499,11 +2500,6 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 	if (IS_ERR(kn))
 		return PTR_ERR(kn);
 
-	/*
-	 * This extra ref will be put in kernfs_remove() and guarantees
-	 * that kn is always accessible.
-	 */
-	kernfs_get(kn);
 	ret = rdtgroup_kn_set_ugid(kn);
 	if (ret)
 		goto out_destroy;
@@ -2838,8 +2834,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	/*
 	 * kernfs_remove() will drop the reference count on "kn" which
 	 * will free it. But we still need it to stick around for the
-	 * rdtgroup_kn_unlock(kn} call below. Take one extra reference
-	 * here, which will be dropped inside rdtgroup_kn_unlock().
+	 * rdtgroup_kn_unlock(kn) call. Take one extra reference here,
+	 * which will be dropped by kernfs_put() in rdtgroup_remove().
 	 */
 	kernfs_get(kn);
 
@@ -2880,6 +2876,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 out_idfree:
 	free_rmid(rdtgrp->mon.rmid);
 out_destroy:
+	kernfs_put(rdtgrp->kn);
 	kernfs_remove(rdtgrp->kn);
 out_free_rgrp:
 	kfree(rdtgrp);
@@ -2892,7 +2889,7 @@ static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp)
 {
 	kernfs_remove(rgrp->kn);
 	free_rmid(rgrp->mon.rmid);
-	kfree(rgrp);
+	rdtgroup_remove(rgrp);
 }
 
 /*
@@ -3049,11 +3046,6 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
 	list_del(&rdtgrp->mon.crdtgrp_list);
 
-	/*
-	 * one extra hold on this, will drop when we kfree(rdtgrp)
-	 * in rdtgroup_kn_unlock()
-	 */
-	kernfs_get(kn);
 	kernfs_remove(rdtgrp->kn);
 
 	return 0;
@@ -3065,11 +3057,6 @@ static int rdtgroup_ctrl_remove(struct kernfs_node *kn,
 	rdtgrp->flags = RDT_DELETED;
 	list_del(&rdtgrp->rdtgroup_list);
 
-	/*
-	 * one extra hold on this, will drop when we kfree(rdtgrp)
-	 * in rdtgroup_kn_unlock()
-	 */
-	kernfs_get(kn);
 	kernfs_remove(rdtgrp->kn);
 	return 0;
 }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ba4593a913fa..145a7ac0c19a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -685,7 +685,7 @@ void arch_cpu_idle(void)
  */
 void __cpuidle default_idle(void)
 {
-	safe_halt();
+	raw_safe_halt();
 }
 #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)
 EXPORT_SYMBOL(default_idle);
@@ -736,6 +736,8 @@ void stop_this_cpu(void *dummy)
 /*
  * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power
  * states (local apic timer and TSC stop).
+ *
+ * XXX this function is completely buggered vs RCU and tracing.
  */
 static void amd_e400_idle(void)
 {
@@ -757,9 +759,9 @@ static void amd_e400_idle(void)
 	 * The switch back from broadcast mode needs to be called with
 	 * interrupts disabled.
 	 */
-	local_irq_disable();
+	raw_local_irq_disable();
 	tick_broadcast_exit();
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 /*
@@ -801,9 +803,9 @@ static __cpuidle void mwait_idle(void)
 		if (!need_resched())
 			__sti_mwait(0, 0);
 		else
-			local_irq_enable();
+			raw_local_irq_enable();
 	} else {
-		local_irq_enable();
+		raw_local_irq_enable();
 	}
 	__current_clr_polling();
 }
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 420be871d9d4..ae64f98ec2ab 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -514,13 +514,10 @@ int tboot_force_iommu(void)
 	if (!tboot_enabled())
 		return 0;
 
-	if (no_iommu || swiotlb || dmar_disabled)
+	if (no_iommu || dmar_disabled)
 		pr_warn("Forcing Intel-IOMMU to enabled\n");
 
 	dmar_disabled = 0;
-#ifdef CONFIG_SWIOTLB
-	swiotlb = 0;
-#endif
 	no_iommu = 0;
 
 	return 1;
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 99d118ffc67d..814698e5b152 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -40,29 +40,10 @@ static int pending_userspace_extint(struct kvm_vcpu *v)
  * check if there is pending interrupt from
  * non-APIC source without intack.
  */
-static int kvm_cpu_has_extint(struct kvm_vcpu *v)
-{
-	u8 accept = kvm_apic_accept_pic_intr(v);
-
-	if (accept) {
-		if (irqchip_split(v->kvm))
-			return pending_userspace_extint(v);
-		else
-			return v->kvm->arch.vpic->output;
-	} else
-		return 0;
-}
-
-/*
- * check if there is injectable interrupt:
- * when virtual interrupt delivery enabled,
- * interrupt from apic will handled by hardware,
- * we don't need to check it here.
- */
-int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+int kvm_cpu_has_extint(struct kvm_vcpu *v)
 {
 	/*
-	 * FIXME: interrupt.injected represents an interrupt that it's
+	 * FIXME: interrupt.injected represents an interrupt whose
 	 * side-effects have already been applied (e.g. bit from IRR
 	 * already moved to ISR). Therefore, it is incorrect to rely
 	 * on interrupt.injected to know if there is a pending
@@ -75,6 +56,23 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
 	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.injected;
 
+	if (!kvm_apic_accept_pic_intr(v))
+		return 0;
+
+	if (irqchip_split(v->kvm))
+		return pending_userspace_extint(v);
+	else
+		return v->kvm->arch.vpic->output;
+}
+
+/*
+ * check if there is injectable interrupt:
+ * when virtual interrupt delivery enabled,
+ * interrupt from apic will handled by hardware,
+ * we don't need to check it here.
+ */
+int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+{
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
@@ -91,20 +89,6 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_injectable_intr);
  */
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
 {
-	/*
-	 * FIXME: interrupt.injected represents an interrupt that it's
-	 * side-effects have already been applied (e.g. bit from IRR
-	 * already moved to ISR). Therefore, it is incorrect to rely
-	 * on interrupt.injected to know if there is a pending
-	 * interrupt in the user-mode LAPIC.
-	 * This leads to nVMX/nSVM not be able to distinguish
-	 * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on
-	 * pending interrupt or should re-inject an injected
-	 * interrupt.
-	 */
-	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.injected;
-
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
@@ -118,16 +102,21 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt);
  */
 static int kvm_cpu_get_extint(struct kvm_vcpu *v)
 {
-	if (kvm_cpu_has_extint(v)) {
-		if (irqchip_split(v->kvm)) {
-			int vector = v->arch.pending_external_vector;
-
-			v->arch.pending_external_vector = -1;
-			return vector;
-		} else
-			return kvm_pic_read_irq(v->kvm); /* PIC */
-	} else
+	if (!kvm_cpu_has_extint(v)) {
+		WARN_ON(!lapic_in_kernel(v));
 		return -1;
+	}
+
+	if (!lapic_in_kernel(v))
+		return v->arch.interrupt.nr;
+
+	if (irqchip_split(v->kvm)) {
+		int vector = v->arch.pending_external_vector;
+
+		v->arch.pending_external_vector = -1;
+		return vector;
+	} else
+		return kvm_pic_read_irq(v->kvm); /* PIC */
 }
 
 /*
@@ -135,13 +124,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v)
  */
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 {
-	int vector;
-
-	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.nr;
-
-	vector = kvm_cpu_get_extint(v);
-
+	int vector = kvm_cpu_get_extint(v);
 	if (vector != -1)
 		return vector;			/* PIC */
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 105e7859d1f2..86c33d53c90a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2465,7 +2465,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 ppr;
 
-	if (!kvm_apic_hw_enabled(apic))
+	if (!kvm_apic_present(vcpu))
 		return -1;
 
 	__apic_update_ppr(apic, &ppr);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 5bb1939b65d8..7a6ae9e90bd7 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3517,7 +3517,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 {
 	u64 sptes[PT64_ROOT_MAX_LEVEL];
 	struct rsvd_bits_validate *rsvd_check;
-	int root = vcpu->arch.mmu->root_level;
+	int root = vcpu->arch.mmu->shadow_root_level;
 	int leaf;
 	int level;
 	bool reserved = false;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index c0b14106258a..566f4d18185b 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -642,8 +642,8 @@ static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr,
 	 * Its safe to read more than we are asked, caller should ensure that
 	 * destination has enough space.
 	 */
-	src_paddr = round_down(src_paddr, 16);
 	offset = src_paddr & 15;
+	src_paddr = round_down(src_paddr, 16);
 	sz = round_up(sz + offset, 16);
 
 	return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 1e81cfebd491..79b3a564f1c9 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1309,8 +1309,10 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 		svm->avic_is_running = true;
 
 	svm->msrpm = svm_vcpu_alloc_msrpm();
-	if (!svm->msrpm)
+	if (!svm->msrpm) {
+		err = -ENOMEM;
 		goto error_free_vmcb_page;
+	}
 
 	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 078a39d489fe..e545a8a613b1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4051,21 +4051,23 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
 
 static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * We can accept userspace's request for interrupt injection
+	 * as long as we have a place to store the interrupt number.
+	 * The actual injection will happen when the CPU is able to
+	 * deliver the interrupt.
+	 */
+	if (kvm_cpu_has_extint(vcpu))
+		return false;
+
+	/* Acknowledging ExtINT does not happen if LINT0 is masked.  */
 	return (!lapic_in_kernel(vcpu) ||
 		kvm_apic_accept_pic_intr(vcpu));
 }
 
-/*
- * if userspace requested an interrupt window, check that the
- * interrupt window is open.
- *
- * No need to exit to userspace if we already have an interrupt queued.
- */
 static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
 {
 	return kvm_arch_interrupt_allowed(vcpu) &&
-		!kvm_cpu_has_interrupt(vcpu) &&
-		!kvm_event_needs_reinjection(vcpu) &&
 		kvm_cpu_accept_dm_intr(vcpu);
 }