Merge branch 'perf/urgent' into perf/core

Merge the latest fixes.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

11 files changed, 77 insertions, 30 deletions

diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 90a21f430117..4dbf967da50d 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -111,7 +111,7 @@ struct mem_vector {
 };
 
 #define MEM_AVOID_MAX 5
-struct mem_vector mem_avoid[MEM_AVOID_MAX];
+static struct mem_vector mem_avoid[MEM_AVOID_MAX];
 
 static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
 {
@@ -180,7 +180,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 }
 
 /* Does this memory vector overlap a known avoided area? */
-bool mem_avoid_overlap(struct mem_vector *img)
+static bool mem_avoid_overlap(struct mem_vector *img)
 {
 	int i;
 
@@ -192,8 +192,9 @@ bool mem_avoid_overlap(struct mem_vector *img)
 	return false;
 }
 
-unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / CONFIG_PHYSICAL_ALIGN];
-unsigned long slot_max = 0;
+static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+			   CONFIG_PHYSICAL_ALIGN];
+static unsigned long slot_max;
 
 static void slots_append(unsigned long addr)
 {
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 3d6b9f81cc68..acd86c850414 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -134,6 +134,7 @@ extern void efi_setup_page_tables(void);
 extern void __init old_map_region(efi_memory_desc_t *md);
 extern void __init runtime_code_page_mkexec(void);
 extern void __init efi_runtime_mkexec(void);
+extern void __init efi_apply_memmap_quirks(void);
 
 struct efi_setup_data {
 	u64 fw_vendor;
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 81ba27679f18..f36bd42d6f0c 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -544,6 +544,10 @@ ENDPROC(early_idt_handlers)
 	/* This is global to keep gas from relaxing the jumps */
 ENTRY(early_idt_handler)
 	cld
+
+	cmpl $2,(%esp)		# X86_TRAP_NMI
+	je is_nmi		# Ignore NMI
+
 	cmpl $2,%ss:early_recursion_flag
 	je hlt_loop
 	incl %ss:early_recursion_flag
@@ -594,8 +598,9 @@ ex_entry:
 	pop %edx
 	pop %ecx
 	pop %eax
-	addl $8,%esp		/* drop vector number and error code */
 	decl %ss:early_recursion_flag
+is_nmi:
+	addl $8,%esp		/* drop vector number and error code */
 	iret
 ENDPROC(early_idt_handler)
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index e1aabdb314c8..a468c0a65c42 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -343,6 +343,9 @@ early_idt_handlers:
 ENTRY(early_idt_handler)
 	cld
 
+	cmpl $2,(%rsp)		# X86_TRAP_NMI
+	je is_nmi		# Ignore NMI
+
 	cmpl $2,early_recursion_flag(%rip)
 	jz  1f
 	incl early_recursion_flag(%rip)
@@ -405,8 +408,9 @@ ENTRY(early_idt_handler)
 	popq %rdx
 	popq %rcx
 	popq %rax
-	addq $16,%rsp		# drop vector number and error code
 	decl early_recursion_flag(%rip)
+is_nmi:
+	addq $16,%rsp		# drop vector number and error code
 	INTERRUPT_RETURN
 ENDPROC(early_idt_handler)
 
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 4eabc160696f..679cef0791cd 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -279,5 +279,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(node_data);
 	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
 #endif
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
+			      (unsigned long)&_text - __START_KERNEL);
 }
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 06853e670354..ce72964b2f46 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1239,14 +1239,8 @@ void __init setup_arch(char **cmdline_p)
 	register_refined_jiffies(CLOCK_TICK_RATE);
 
 #ifdef CONFIG_EFI
-	/* Once setup is done above, unmap the EFI memory map on
-	 * mismatched firmware/kernel archtectures since there is no
-	 * support for runtime services.
-	 */
-	if (efi_enabled(EFI_BOOT) && !efi_is_native()) {
-		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
-		efi_unmap_memmap();
-	}
+	if (efi_enabled(EFI_BOOT))
+		efi_apply_memmap_quirks();
 #endif
 }
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e50425d0f5f7..9b531351a587 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2672,6 +2672,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 			break;
 		}
 
+		drop_large_spte(vcpu, iterator.sptep);
 		if (!is_shadow_present_pte(*iterator.sptep)) {
 			u64 base_addr = iterator.addr;
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a06f101ef64b..392752834751 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6688,7 +6688,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		else if (is_page_fault(intr_info))
 			return enable_ept;
 		else if (is_no_device(intr_info) &&
-			 !(nested_read_cr0(vmcs12) & X86_CR0_TS))
+			 !(vmcs12->guest_cr0 & X86_CR0_TS))
 			return 0;
 		return vmcs12->exception_bitmap &
 				(1u << (intr_info & INTR_INFO_VECTOR_MASK));
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 39c28f09dfd5..2b8578432d5b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6186,7 +6186,7 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 		frag->len -= len;
 	}
 
-	if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+	if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
 		vcpu->mmio_needed = 0;
 
 		/* FIXME: return into emulator if single-stepping.  */
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 6dea040cc3a1..a10c8c792161 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1020,13 +1020,17 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs)
  * This routine handles page faults.  It determines the address,
  * and the problem, and then passes it off to one of the appropriate
  * routines.
+ *
+ * This function must have noinline because both callers
+ * {,trace_}do_page_fault() have notrace on. Having this an actual function
+ * guarantees there's a function trace entry.
  */
-static void __kprobes
-__do_page_fault(struct pt_regs *regs, unsigned long error_code)
+static void __kprobes noinline
+__do_page_fault(struct pt_regs *regs, unsigned long error_code,
+		unsigned long address)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
-	unsigned long address;
 	struct mm_struct *mm;
 	int fault;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -1034,9 +1038,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	tsk = current;
 	mm = tsk->mm;
 
-	/* Get the faulting address: */
-	address = read_cr2();
-
 	/*
 	 * Detect and handle instructions that would cause a page fault for
 	 * both a tracked kernel page and a userspace page.
@@ -1248,32 +1249,50 @@ good_area:
 	up_read(&mm->mmap_sem);
 }
 
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
 do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
+	unsigned long address = read_cr2(); /* Get the faulting address */
 	enum ctx_state prev_state;
 
+	/*
+	 * We must have this function tagged with __kprobes, notrace and call
+	 * read_cr2() before calling anything else. To avoid calling any kind
+	 * of tracing machinery before we've observed the CR2 value.
+	 *
+	 * exception_{enter,exit}() contain all sorts of tracepoints.
+	 */
+
 	prev_state = exception_enter();
-	__do_page_fault(regs, error_code);
+	__do_page_fault(regs, error_code, address);
 	exception_exit(prev_state);
 }
 
-static void trace_page_fault_entries(struct pt_regs *regs,
+#ifdef CONFIG_TRACING
+static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs,
 				     unsigned long error_code)
 {
 	if (user_mode(regs))
-		trace_page_fault_user(read_cr2(), regs, error_code);
+		trace_page_fault_user(address, regs, error_code);
 	else
-		trace_page_fault_kernel(read_cr2(), regs, error_code);
+		trace_page_fault_kernel(address, regs, error_code);
 }
 
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
 trace_do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
+	/*
+	 * The exception_enter and tracepoint processing could
+	 * trigger another page faults (user space callchain
+	 * reading) and destroy the original cr2 value, so read
+	 * the faulting address now.
+	 */
+	unsigned long address = read_cr2();
 	enum ctx_state prev_state;
 
 	prev_state = exception_enter();
-	trace_page_fault_entries(regs, error_code);
-	__do_page_fault(regs, error_code);
+	trace_page_fault_entries(address, regs, error_code);
+	__do_page_fault(regs, error_code, address);
 	exception_exit(prev_state);
 }
+#endif /* CONFIG_TRACING */
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 1a201ac7cef8..b97acecf3fd9 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -52,6 +52,7 @@
 #include <asm/tlbflush.h>
 #include <asm/x86_init.h>
 #include <asm/rtc.h>
+#include <asm/uv/uv.h>
 
 #define EFI_DEBUG
 
@@ -1210,3 +1211,22 @@ static int __init parse_efi_cmdline(char *str)
 	return 0;
 }
 early_param("efi", parse_efi_cmdline);
+
+void __init efi_apply_memmap_quirks(void)
+{
+	/*
+	 * Once setup is done earlier, unmap the EFI memory map on mismatched
+	 * firmware/kernel architectures since there is no support for runtime
+	 * services.
+	 */
+	if (!efi_is_native()) {
+		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+		efi_unmap_memmap();
+	}
+
+	/*
+	 * UV doesn't support the new EFI pagetable mapping yet.
+	 */
+	if (is_uv_system())
+		set_bit(EFI_OLD_MEMMAP, &x86_efi_facility);
+}