x86/entry: Remap the TSS into the CPU entry area

This has a secondary purpose: it puts the entry stack into a region
with a well-controlled layout.  A subsequent patch will take
advantage of this to streamline the SYSCALL entry code to be able to
find it more easily.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bpetkov@suse.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Link: https://lkml.kernel.org/r/20171204150605.962042855@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/entry/entry_32.S

@@ -941,7 +941,8 @@ ENTRY(debug)
 	movl	%esp, %eax			# pt_regs pointer
 
 	/* Are we currently on the SYSENTER stack? */
-	PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
+	movl	PER_CPU_VAR(cpu_entry_area), %ecx
+	addl	$CPU_ENTRY_AREA_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx
 	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
 	cmpl	$SIZEOF_SYSENTER_stack, %ecx
 	jb	.Ldebug_from_sysenter_stack
@@ -984,7 +985,8 @@ ENTRY(nmi)
 	movl	%esp, %eax			# pt_regs pointer
 
 	/* Are we currently on the SYSENTER stack? */
-	PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
+	movl	PER_CPU_VAR(cpu_entry_area), %ecx
+	addl	$CPU_ENTRY_AREA_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx
 	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
 	cmpl	$SIZEOF_SYSENTER_stack, %ecx
 	jb	.Lnmi_from_sysenter_stack

arch/x86/include/asm/fixmap.h

@@ -54,6 +54,13 @@ extern unsigned long __FIXADDR_TOP;
  */
 struct cpu_entry_area {
 	char gdt[PAGE_SIZE];
+
+	/*
+	 * The GDT is just below cpu_tss and thus serves (on x86_64) as a
+	 * a read-only guard page for the SYSENTER stack at the bottom
+	 * of the TSS region.
+	 */
+	struct tss_struct tss;
 };
 
 #define CPU_ENTRY_AREA_PAGES (sizeof(struct cpu_entry_area) / PAGE_SIZE)

arch/x86/kernel/asm-offsets.c

@@ -98,4 +98,7 @@ void common(void) {
 	OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack);
 	/* Size of SYSENTER_stack */
 	DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack));
+
+	/* Layout info for cpu_entry_area */
+	OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss);
 }

arch/x86/kernel/cpu/common.c

@@ -466,6 +466,22 @@ void load_percpu_segment(int cpu)
 	load_stack_canary_segment();
 }
 
+static void set_percpu_fixmap_pages(int fixmap_index, void *ptr,
+				    int pages, pgprot_t prot)
+{
+	int i;
+
+	for (i = 0; i < pages; i++) {
+		__set_fixmap(fixmap_index - i,
+			     per_cpu_ptr_to_phys(ptr + i * PAGE_SIZE), prot);
+	}
+}
+
+#ifdef CONFIG_X86_32
+/* The 32-bit entry code needs to find cpu_entry_area. */
+DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
+#endif
+
 /* Setup the fixmap mappings only once per-processor */
 static inline void setup_cpu_entry_area(int cpu)
 {
@@ -507,7 +523,15 @@ static inline void setup_cpu_entry_area(int cpu)
 	 */
 	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
 		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
+	BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0);
+	set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, tss),
+				&per_cpu(cpu_tss, cpu),
+				sizeof(struct tss_struct) / PAGE_SIZE,
+				PAGE_KERNEL);
 
+#ifdef CONFIG_X86_32
+	this_cpu_write(cpu_entry_area, get_cpu_entry_area(cpu));
+#endif
 }
 
 /* Load the original GDT from the per-cpu structure */
@@ -1257,7 +1281,8 @@ void enable_sep_cpu(void)
 	wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
 
 	wrmsr(MSR_IA32_SYSENTER_ESP,
-	      (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
+	      (unsigned long)&get_cpu_entry_area(cpu)->tss +
+	      offsetofend(struct tss_struct, SYSENTER_stack),
 	      0);
 
 	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
@@ -1370,6 +1395,8 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
 /* May not be marked __init: used by software suspend */
 void syscall_init(void)
 {
+	int cpu = smp_processor_id();
+
 	wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
 	wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
 
@@ -1383,7 +1410,7 @@ void syscall_init(void)
 	 */
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
 	wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
-		    (unsigned long)this_cpu_ptr(&cpu_tss) +
+		    (unsigned long)&get_cpu_entry_area(cpu)->tss +
 		    offsetofend(struct tss_struct, SYSENTER_stack));
 	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 #else
@@ -1593,11 +1620,13 @@ void cpu_init(void)
 	initialize_tlbstate_and_flush();
 	enter_lazy_tlb(&init_mm, me);
 
+	setup_cpu_entry_area(cpu);
+
 	/*
 	 * Initialize the TSS.  Don't bother initializing sp0, as the initial
 	 * task never enters user mode.
 	 */
-	set_tss_desc(cpu, &t->x86_tss);
+	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 	load_TR_desc();
 
 	load_mm_ldt(&init_mm);
@@ -1610,7 +1639,6 @@ void cpu_init(void)
 	if (is_uv_system())
 		uv_cpu_init();
 
-	setup_cpu_entry_area(cpu);
 	load_fixmap_gdt(cpu);
 }
 
@@ -1651,11 +1679,13 @@ void cpu_init(void)
 	initialize_tlbstate_and_flush();
 	enter_lazy_tlb(&init_mm, curr);
 
+	setup_cpu_entry_area(cpu);
+
 	/*
 	 * Initialize the TSS.  Don't bother initializing sp0, as the initial
 	 * task never enters user mode.
 	 */
-	set_tss_desc(cpu, &t->x86_tss);
+	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 	load_TR_desc();
 
 	load_mm_ldt(&init_mm);
@@ -1672,7 +1702,6 @@ void cpu_init(void)
 
 	fpu__init_cpu();
 
-	setup_cpu_entry_area(cpu);
 	load_fixmap_gdt(cpu);
 }
 #endif

arch/x86/kernel/dumpstack.c

@@ -45,7 +45,8 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task,
 
 bool in_sysenter_stack(unsigned long *stack, struct stack_info *info)
 {
-	struct tss_struct *tss = this_cpu_ptr(&cpu_tss);
+	int cpu = smp_processor_id();
+	struct tss_struct *tss = &get_cpu_entry_area(cpu)->tss;
 
 	/* Treat the canary as part of the stack for unwinding purposes. */
 	void *begin = &tss->SYSENTER_stack_canary;

arch/x86/kvm/vmx.c

@@ -2291,7 +2291,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		 * processors.  See 22.2.4.
 		 */
 		vmcs_writel(HOST_TR_BASE,
-			    (unsigned long)this_cpu_ptr(&cpu_tss.x86_tss));
+			    (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss);
 		vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt);   /* 22.2.4 */
 
 		/*

arch/x86/power/cpu.c

@@ -160,18 +160,19 @@ static void do_fpu_end(void)
 static void fix_processor_context(void)
 {
 	int cpu = smp_processor_id();
-	struct tss_struct *t = &per_cpu(cpu_tss, cpu);
 #ifdef CONFIG_X86_64
 	struct desc_struct *desc = get_cpu_gdt_rw(cpu);
 	tss_desc tss;
 #endif
 
 	/*
-	 * This just modifies memory; should not be necessary. But... This is
+	 * We need to reload TR, which requires that we change the
-	 * necessary, because 386 hardware has concept of busy TSS or some
+	 * GDT entry to indicate "available" first.
-	 * similar stupidity.
+	 *
+	 * XXX: This could probably all be replaced by a call to
+	 * force_reload_TR().
 	 */
-	set_tss_desc(cpu, &t->x86_tss);
+	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 
 #ifdef CONFIG_X86_64
 	memcpy(&tss, &desc[GDT_ENTRY_TSS], sizeof(tss_desc));