15 files changed, 113 insertions, 73 deletions

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index fa42f895fdde..169c2feda14a 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -106,9 +106,13 @@ define cmd_check_data_rel
 	done
 endef
 
+# We need to run two commands under "if_changed", so merge them into a
+# single invocation.
+quiet_cmd_check-and-link-vmlinux = LD      $@
+      cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld)
+
 $(obj)/vmlinux: $(vmlinux-objs-y) FORCE
-	$(call if_changed,check_data_rel)
-	$(call if_changed,ld)
+	$(call if_changed,check-and-link-vmlinux)
 
 OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
 $(obj)/vmlinux.bin: vmlinux FORCE
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index 8c5107545251..9e2157371491 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -1,3 +1,4 @@
+#include <asm/e820/types.h>
 #include <asm/processor.h>
 #include "pgtable.h"
 #include "../string.h"
@@ -34,10 +35,62 @@ unsigned long *trampoline_32bit __section(.data);
 extern struct boot_params *boot_params;
 int cmdline_find_option_bool(const char *option);
 
+static unsigned long find_trampoline_placement(void)
+{
+	unsigned long bios_start, ebda_start;
+	unsigned long trampoline_start;
+	struct boot_e820_entry *entry;
+	int i;
+
+	/*
+	 * Find a suitable spot for the trampoline.
+	 * This code is based on reserve_bios_regions().
+	 */
+
+	ebda_start = *(unsigned short *)0x40e << 4;
+	bios_start = *(unsigned short *)0x413 << 10;
+
+	if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX)
+		bios_start = BIOS_START_MAX;
+
+	if (ebda_start > BIOS_START_MIN && ebda_start < bios_start)
+		bios_start = ebda_start;
+
+	bios_start = round_down(bios_start, PAGE_SIZE);
+
+	/* Find the first usable memory region under bios_start. */
+	for (i = boot_params->e820_entries - 1; i >= 0; i--) {
+		entry = &boot_params->e820_table[i];
+
+		/* Skip all entries above bios_start. */
+		if (bios_start <= entry->addr)
+			continue;
+
+		/* Skip non-RAM entries. */
+		if (entry->type != E820_TYPE_RAM)
+			continue;
+
+		/* Adjust bios_start to the end of the entry if needed. */
+		if (bios_start > entry->addr + entry->size)
+			bios_start = entry->addr + entry->size;
+
+		/* Keep bios_start page-aligned. */
+		bios_start = round_down(bios_start, PAGE_SIZE);
+
+		/* Skip the entry if it's too small. */
+		if (bios_start - TRAMPOLINE_32BIT_SIZE < entry->addr)
+			continue;
+
+		break;
+	}
+
+	/* Place the trampoline just below the end of low memory */
+	return bios_start - TRAMPOLINE_32BIT_SIZE;
+}
+
 struct paging_config paging_prepare(void *rmode)
 {
 	struct paging_config paging_config = {};
-	unsigned long bios_start, ebda_start;
 
 	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
 	boot_params = rmode;
@@ -61,23 +114,7 @@ struct paging_config paging_prepare(void *rmode)
 		paging_config.l5_required = 1;
 	}
 
-	/*
-	 * Find a suitable spot for the trampoline.
-	 * This code is based on reserve_bios_regions().
-	 */
-
-	ebda_start = *(unsigned short *)0x40e << 4;
-	bios_start = *(unsigned short *)0x413 << 10;
-
-	if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX)
-		bios_start = BIOS_START_MAX;
-
-	if (ebda_start > BIOS_START_MIN && ebda_start < bios_start)
-		bios_start = ebda_start;
-
-	/* Place the trampoline just below the end of low memory, aligned to 4k */
-	paging_config.trampoline_start = bios_start - TRAMPOLINE_32BIT_SIZE;
-	paging_config.trampoline_start = round_down(paging_config.trampoline_start, PAGE_SIZE);
+	paging_config.trampoline_start = find_trampoline_placement();
 
 	trampoline_32bit = (unsigned long *)paging_config.trampoline_start;
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 73a522d53b53..8ae7ffda8f98 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -981,7 +981,7 @@ ENTRY(\sym)
 
 	call	\do_sym
 
-	jmp	error_exit			/* %ebx: no swapgs flag */
+	jmp	error_exit
 	.endif
 END(\sym)
 .endm
@@ -1222,7 +1222,6 @@ END(paranoid_exit)
 
 /*
  * Save all registers in pt_regs, and switch GS if needed.
- * Return: EBX=0: came from user mode; EBX=1: otherwise
  */
 ENTRY(error_entry)
 	UNWIND_HINT_FUNC
@@ -1269,7 +1268,6 @@ ENTRY(error_entry)
 	 * for these here too.
 	 */
 .Lerror_kernelspace:
-	incl	%ebx
 	leaq	native_irq_return_iret(%rip), %rcx
 	cmpq	%rcx, RIP+8(%rsp)
 	je	.Lerror_bad_iret
@@ -1303,28 +1301,20 @@ ENTRY(error_entry)
 
 	/*
 	 * Pretend that the exception came from user mode: set up pt_regs
-	 * as if we faulted immediately after IRET and clear EBX so that
-	 * error_exit knows that we will be returning to user mode.
+	 * as if we faulted immediately after IRET.
 	 */
 	mov	%rsp, %rdi
 	call	fixup_bad_iret
 	mov	%rax, %rsp
-	decl	%ebx
 	jmp	.Lerror_entry_from_usermode_after_swapgs
 END(error_entry)
 
-
-/*
- * On entry, EBX is a "return to kernel mode" flag:
- *   1: already in kernel mode, don't need SWAPGS
- *   0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
- */
 ENTRY(error_exit)
 	UNWIND_HINT_REGS
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
-	testl	%ebx, %ebx
-	jnz	retint_kernel
+	testb	$3, CS(%rsp)
+	jz	retint_kernel
 	jmp	retint_user
 END(error_exit)
 
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 4b98101209a1..d50bb4dc0650 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -579,7 +579,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 {
 	struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
 	struct perf_event *event = pcpu->event;
-	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event *hwc;
 	struct perf_sample_data data;
 	struct perf_raw_record raw;
 	struct pt_regs regs;
@@ -602,6 +602,10 @@ fail:
 		return 0;
 	}
 
+	if (WARN_ON_ONCE(!event))
+		goto fail;
+
+	hwc = &event->hw;
 	msr = hwc->config_base;
 	buf = ibs_data.regs;
 	rdmsrl(msr, *buf);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 707b2a96e516..86f0c15dcc2d 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2997,6 +2997,9 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		}
 		if (x86_pmu.pebs_aliases)
 			x86_pmu.pebs_aliases(event);
+
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+			event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY;
 	}
 
 	if (needs_branch_stack(event)) {
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8cf03f101938..8dbba77e0518 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1186,16 +1186,20 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	}
 
 	/*
+	 * We must however always use iregs for the unwinder to stay sane; the
+	 * record BP,SP,IP can point into thin air when the record is from a
+	 * previous PMI context or an (I)RET happend between the record and
+	 * PMI.
+	 */
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+		data->callchain = perf_callchain(event, iregs);
+
+	/*
 	 * We use the interrupt regs as a base because the PEBS record does not
 	 * contain a full regs set, specifically it seems to lack segment
 	 * descriptors, which get used by things like user_mode().
 	 *
 	 * In the simple case fix up only the IP for PERF_SAMPLE_IP.
-	 *
-	 * We must however always use BP,SP from iregs for the unwinder to stay
-	 * sane; the record BP,SP can point into thin air when the record is
-	 * from a previous PMI context or an (I)RET happend between the record
-	 * and PMI.
 	 */
 	*regs = *iregs;
 
@@ -1214,15 +1218,8 @@ static void setup_pebs_sample_data(struct perf_event *event,
 		regs->si = pebs->si;
 		regs->di = pebs->di;
 
-		/*
-		 * Per the above; only set BP,SP if we don't need callchains.
-		 *
-		 * XXX: does this make sense?
-		 */
-		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
-			regs->bp = pebs->bp;
-			regs->sp = pebs->sp;
-		}
+		regs->bp = pebs->bp;
+		regs->sp = pebs->sp;
 
 #ifndef CONFIG_X86_32
 		regs->r8 = pebs->r8;
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index c9e1e0bef3c3..e17ab885b1e9 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -28,7 +28,7 @@
 #define UNCORE_PCI_DEV_TYPE(data)	((data >> 8) & 0xff)
 #define UNCORE_PCI_DEV_IDX(data)	(data & 0xff)
 #define UNCORE_EXTRA_PCI_DEV		0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX	3
+#define UNCORE_EXTRA_PCI_DEV_MAX	4
 
 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 87dc0263a2e1..51d7c117e3c7 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1029,6 +1029,7 @@ void snbep_uncore_cpu_init(void)
 enum {
 	SNBEP_PCI_QPI_PORT0_FILTER,
 	SNBEP_PCI_QPI_PORT1_FILTER,
+	BDX_PCI_QPI_PORT2_FILTER,
 	HSWEP_PCI_PCU_3,
 };
 
@@ -3286,15 +3287,18 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = {
 	},
 	{ /* QPI Port 0 filter  */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT0_FILTER),
 	},
 	{ /* QPI Port 1 filter  */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT1_FILTER),
 	},
 	{ /* QPI Port 2 filter  */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   BDX_PCI_QPI_PORT2_FILTER),
 	},
 	{ /* PCU.3 (for Capability registers) */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0),
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 9ef5ee03d2d7..159622ee0674 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -43,7 +43,7 @@ asm    (".pushsection .text;"
 	"push  %rdx;"
 	"mov   $0x1,%eax;"
 	"xor   %edx,%edx;"
-	"lock cmpxchg %dl,(%rdi);"
+	LOCK_PREFIX "cmpxchg %dl,(%rdi);"
 	"cmp   $0x1,%al;"
 	"jne   .slowpath;"
 	"pop   %rdx;"
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2aabd4cb0e3f..adbda5847b14 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -573,6 +573,9 @@ static u32 skx_deadline_rev(void)
 	case 0x04: return 0x02000014;
 	}
 
+	if (boot_cpu_data.x86_stepping > 4)
+		return 0;
+
 	return ~0U;
 }
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d594690d8b95..6b8f11521c41 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -890,7 +890,7 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache,
 	if (cache->nobjs >= min)
 		return 0;
 	while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
-		page = (void *)__get_free_page(GFP_KERNEL);
+		page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
 		if (!page)
 			return -ENOMEM;
 		cache->objects[cache->nobjs++] = page;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e30da9a2430c..5d8e317c2b04 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7893,6 +7893,8 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 		     HRTIMER_MODE_REL_PINNED);
 	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
 
+	vmx->nested.vpid02 = allocate_vpid();
+
 	vmx->nested.vmxon = true;
 	return 0;
 
@@ -8480,21 +8482,20 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 /* Emulate the VMPTRST instruction */
 static int handle_vmptrst(struct kvm_vcpu *vcpu)
 {
-	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	gva_t vmcs_gva;
+	unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION);
+	u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr;
 	struct x86_exception e;
+	gva_t gva;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (get_vmx_mem_address(vcpu, exit_qualification,
-			vmx_instruction_info, true, &vmcs_gva))
+	if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva))
 		return 1;
 	/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
-	if (kvm_write_guest_virt_system(vcpu, vmcs_gva,
-					(void *)&to_vmx(vcpu)->nested.current_vmptr,
-					sizeof(u64), &e)) {
+	if (kvm_write_guest_virt_system(vcpu, gva, (void *)&current_vmptr,
+					sizeof(gpa_t), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
@@ -10370,11 +10371,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 			goto free_vmcs;
 	}
 
-	if (nested) {
+	if (nested)
 		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
 					   kvm_vcpu_apicv_active(&vmx->vcpu));
-		vmx->nested.vpid02 = allocate_vpid();
-	}
 
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
@@ -10391,7 +10390,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	return &vmx->vcpu;
 
 free_vmcs:
-	free_vpid(vmx->nested.vpid02);
 	free_loaded_vmcs(vmx->loaded_vmcs);
 free_msrs:
 	kfree(vmx->guest_msrs);
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 55799873ebe5..8f6cc71e0848 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -1441,8 +1441,8 @@ static void emit_prologue(u8 **pprog, u32 stack_depth)
 
 	/* sub esp,STACK_SIZE */
 	EMIT2_off32(0x81, 0xEC, STACK_SIZE);
-	/* sub ebp,SCRATCH_SIZE+4+12*/
-	EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 16);
+	/* sub ebp,SCRATCH_SIZE+12*/
+	EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 12);
 	/* xor ebx,ebx */
 	EMIT2(0x31, add_2reg(0xC0, IA32_EBX, IA32_EBX));
 
@@ -1475,8 +1475,8 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth)
 	/* mov edx,dword ptr [ebp+off]*/
 	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r0[1]));
 
-	/* add ebp,SCRATCH_SIZE+4+12*/
-	EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 16);
+	/* add ebp,SCRATCH_SIZE+12*/
+	EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 12);
 
 	/* mov ebx,dword ptr [ebp-12]*/
 	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), -12);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 77873ce700ae..5f2eb3231607 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -417,7 +417,7 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va)
 	if (!(md->attribute & EFI_MEMORY_WB))
 		flags |= _PAGE_PCD;
 
-	if (sev_active())
+	if (sev_active() && md->type != EFI_MEMORY_MAPPED_IO)
 		flags |= _PAGE_ENC;
 
 	pfn = md->phys_addr >> PAGE_SHIFT;
diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c
index 744afdc18cf3..56c44d865f7b 100644
--- a/arch/x86/um/mem_32.c
+++ b/arch/x86/um/mem_32.c
@@ -16,7 +16,7 @@ static int __init gate_vma_init(void)
 	if (!FIXADDR_USER_START)
 		return 0;
 
-	gate_vma.vm_mm = NULL;
+	vma_init(&gate_vma, NULL);
 	gate_vma.vm_start = FIXADDR_USER_START;
 	gate_vma.vm_end = FIXADDR_USER_END;
 	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;