Merge tag 'v3.14.18' into v3.14-rt

This is the 3.14.18 stable release

10 files changed, 65 insertions, 28 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5677140d7b82..4a69be4137ea 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1601,6 +1601,7 @@ config EFI
 config EFI_STUB
        bool "EFI stub support"
        depends on EFI
+       select RELOCATABLE
        ---help---
           This kernel feature allows a bzImage to be loaded directly
 	  by EFI firmware without the use of a bootloader.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3092300a07cd..d71d5ac78e42 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -99,7 +99,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
 #define KVM_REFILL_PAGES 25
 #define KVM_MAX_CPUID_ENTRIES 80
 #define KVM_NR_FIXED_MTRR_REGION 88
-#define KVM_NR_VAR_MTRR 10
+#define KVM_NR_VAR_MTRR 8
 
 #define ASYNC_PF_PER_VCPU 64
 
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
index 2a26819bb6a8..80eab01c1a68 100644
--- a/arch/x86/kernel/resource.c
+++ b/arch/x86/kernel/resource.c
@@ -37,10 +37,12 @@ static void remove_e820_regions(struct resource *avail)
 
 void arch_remove_reservations(struct resource *avail)
 {
-	/* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */
+	/*
+	 * Trim out BIOS area (high 2MB) and E820 regions. We do not remove
+	 * the low 1MB unconditionally, as this area is needed for some ISA
+	 * cards requiring a memory range, e.g. the i82365 PCMCIA controller.
+	 */
 	if (avail->flags & IORESOURCE_MEM) {
-		if (avail->start < BIOS_END)
-			avail->start = BIOS_END;
 		resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END);
 
 		remove_e820_regions(avail);
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 1f96f9347ed9..09ce23ae370c 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -125,10 +125,10 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
 	if (!show_unhandled_signals)
 		return;
 
-	pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
-			      level, current->comm, task_pid_nr(current),
-			      message, regs->ip, regs->cs,
-			      regs->sp, regs->ax, regs->si, regs->di);
+	printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+			   level, current->comm, task_pid_nr(current),
+			   message, regs->ip, regs->cs,
+			   regs->sp, regs->ax, regs->si, regs->di);
 }
 
 static int addr_to_vsyscall_nr(unsigned long addr)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 07ffca0a89e9..7bff3e2a7a11 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2006,6 +2006,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 	unsigned long cs;
+	int cpl = ctxt->ops->cpl(ctxt);
 
 	rc = emulate_pop(ctxt, &ctxt->_eip, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
@@ -2015,6 +2016,9 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 	rc = emulate_pop(ctxt, &cs, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
+	/* Outer-privilege level return is not implemented */
+	if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl)
+		return X86EMUL_UNHANDLEABLE;
 	rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS);
 	return rc;
 }
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 484bc874688b..3ec38cb56bd5 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -108,7 +108,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 
 	vector = kvm_cpu_get_extint(v);
 
-	if (kvm_apic_vid_enabled(v->kvm) || vector != -1)
+	if (vector != -1)
 		return vector;			/* PIC */
 
 	return kvm_get_apic_interrupt(v);	/* APIC */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 006911858174..453e5fbbb7ae 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -352,25 +352,46 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic)
 
 static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
 {
-	apic->irr_pending = false;
+	struct kvm_vcpu *vcpu;
+
+	vcpu = apic->vcpu;
+
 	apic_clear_vector(vec, apic->regs + APIC_IRR);
-	if (apic_search_irr(apic) != -1)
-		apic->irr_pending = true;
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		/* try to update RVI */
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+	else {
+		vec = apic_search_irr(apic);
+		apic->irr_pending = (vec != -1);
+	}
 }
 
 static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 {
-	/* Note that we never get here with APIC virtualization enabled.  */
+	struct kvm_vcpu *vcpu;
+
+	if (__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
+		return;
+
+	vcpu = apic->vcpu;
 
-	if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
-		++apic->isr_count;
-	BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
 	/*
-	 * ISR (in service register) bit is set when injecting an interrupt.
-	 * The highest vector is injected. Thus the latest bit set matches
-	 * the highest bit in ISR.
+	 * With APIC virtualization enabled, all caching is disabled
+	 * because the processor can modify ISR under the hood.  Instead
+	 * just set SVI.
 	 */
-	apic->highest_isr_cache = vec;
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec);
+	else {
+		++apic->isr_count;
+		BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
+		/*
+		 * ISR (in service register) bit is set when injecting an interrupt.
+		 * The highest vector is injected. Thus the latest bit set matches
+		 * the highest bit in ISR.
+		 */
+		apic->highest_isr_cache = vec;
+	}
 }
 
 static inline int apic_find_highest_isr(struct kvm_lapic *apic)
@@ -1627,11 +1648,16 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 	int vector = kvm_apic_has_interrupt(vcpu);
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	/* Note that we never get here with APIC virtualization enabled.  */
-
 	if (vector == -1)
 		return -1;
 
+	/*
+	 * We get here even with APIC virtualization enabled, if doing
+	 * nested virtualization and L1 runs with the "acknowledge interrupt
+	 * on exit" mode.  Then we cannot inject the interrupt via RVI,
+	 * because the process would deliver it through the IDT.
+	 */
+
 	apic_set_isr(vector, apic);
 	apic_update_ppr(apic);
 	apic_clear_irr(vector, apic);
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index db6b1ab43255..96a159afe3c6 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -162,6 +162,10 @@ pcibios_align_resource(void *data, const struct resource *res,
 			return start;
 		if (start & 0x300)
 			start = (start + 0x3ff) & ~0x3ff;
+	} else if (res->flags & IORESOURCE_MEM) {
+		/* The low 1MB range is reserved for ISA cards */
+		if (start < BIOS_END)
+			start = BIOS_END;
 	}
 	return start;
 }
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index c98583588580..5b406fc45674 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -134,6 +134,7 @@ static int __init xlated_setup_gnttab_pages(void)
 {
 	struct page **pages;
 	xen_pfn_t *pfns;
+	void *vaddr;
 	int rc;
 	unsigned int i;
 	unsigned long nr_grant_frames = gnttab_max_grant_frames();
@@ -159,21 +160,20 @@ static int __init xlated_setup_gnttab_pages(void)
 	for (i = 0; i < nr_grant_frames; i++)
 		pfns[i] = page_to_pfn(pages[i]);
 
-	rc = arch_gnttab_map_shared(pfns, nr_grant_frames, nr_grant_frames,
-				    &xen_auto_xlat_grant_frames.vaddr);
-
-	if (rc) {
+	vaddr = vmap(pages, nr_grant_frames, 0, PAGE_KERNEL);
+	if (!vaddr) {
 		pr_warn("%s Couldn't map %ld pfns rc:%d\n", __func__,
 			nr_grant_frames, rc);
 		free_xenballooned_pages(nr_grant_frames, pages);
 		kfree(pages);
 		kfree(pfns);
-		return rc;
+		return -ENOMEM;
 	}
 	kfree(pages);
 
 	xen_auto_xlat_grant_frames.pfn = pfns;
 	xen_auto_xlat_grant_frames.count = nr_grant_frames;
+	xen_auto_xlat_grant_frames.vaddr = vaddr;
 
 	return 0;
 }
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 7b78f88c1707..5718b0b58b60 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -444,7 +444,7 @@ void xen_setup_timer(int cpu)
 
 	irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt,
 				      IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER|
-				      IRQF_FORCE_RESUME,
+				      IRQF_FORCE_RESUME|IRQF_EARLY_RESUME,
 				      name, NULL);
 	(void)xen_set_irq_priority(irq, XEN_IRQ_PRIORITY_MAX);