Patch "x86/entry: Remap the TSS into the CPU entry area" has been added to the 4.14-stable tree

Patch "x86/entry: Remap the TSS into the CPU entry area" has been added to the 4.14-stable tree

[gregkh]

This is a note to let you know that I've just added the patch titled

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

to the 4.14-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     x86-entry-remap-the-tss-into-the-cpu-entry-area.patch
and it can be found in the queue-4.14 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@vger.kernel.org> know about it.


>From 72f5e08dbba2d01aa90b592cf76c378ea233b00b Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@kernel.org>
Date: Mon, 4 Dec 2017 15:07:20 +0100
Subject: x86/entry: Remap the TSS into the CPU entry area

From: Andy Lutomirski <luto@kernel.org>

commit 72f5e08dbba2d01aa90b592cf76c378ea233b00b upstream.

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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 arch/x86/entry/entry_32.S     |    6 ++++--
 arch/x86/include/asm/fixmap.h |    7 +++++++
 arch/x86/kernel/asm-offsets.c |    3 +++
 arch/x86/kernel/cpu/common.c  |   41 +++++++++++++++++++++++++++++++++++------
 arch/x86/kernel/dumpstack.c   |    3 ++-
 arch/x86/kvm/vmx.c            |    2 +-
 arch/x86/power/cpu.c          |   11 ++++++-----
 7 files changed, 58 insertions(+), 15 deletions(-)

--- a/arch/x86/entry/entry_32.S
+++ b/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
--- a/arch/x86/include/asm/fixmap.h
+++ b/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)
--- a/arch/x86/kernel/asm-offsets.c
+++ b/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);
 }
--- a/arch/x86/kernel/cpu/common.c
+++ b/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(
 	 */
 	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,
 /* 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
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -45,7 +45,8 @@ bool in_task_stack(unsigned long *stack,
 
 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;
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2295,7 +2295,7 @@ static void vmx_vcpu_load(struct kvm_vcp
 		 * 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 */
 
 		/*
--- a/arch/x86/power/cpu.c
+++ b/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
-	 * necessary, because 386 hardware has concept of busy TSS or some
-	 * similar stupidity.
+	 * We need to reload TR, which requires that we change the
+	 * GDT entry to indicate "available" first.
+	 *
+	 * 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));


Patches currently in stable-queue which might be from luto@kernel.org are

queue-4.14/x86-entry-64-simplify-reg-restore-code-in-the-standard-iret-paths.patch
queue-4.14/x86-cpufeatures-fix-various-details-in-the-feature-definitions.patch
queue-4.14/x86-entry-64-move-the-ist-stacks-into-struct-cpu_entry_area.patch
queue-4.14/x86-dumpstack-add-get_stack_info-support-for-the-sysenter-stack.patch
queue-4.14/x86-asm-don-t-use-the-confusing-.ifeq-directive.patch
queue-4.14/selftests-x86-ldt_gdt-add-infrastructure-to-test-set_thread_area.patch
queue-4.14/x86-entry-remap-the-tss-into-the-cpu-entry-area.patch
queue-4.14/x86-entry-64-paravirt-use-paravirt-safe-macro-to-access-eflags.patch
queue-4.14/x86-mm-fixmap-generalize-the-gdt-fixmap-mechanism-introduce-struct-cpu_entry_area.patch
queue-4.14/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.14/x86-dumpstack-handle-stack-overflow-on-all-stacks.patch
queue-4.14/x86-entry-64-use-pop-instead-of-movq-in-syscall_return_via_sysret.patch
queue-4.14/x86-entry-64-return-to-userspace-from-the-trampoline-stack.patch
queue-4.14/x86-paravirt-provide-a-way-to-check-for-hypervisors.patch
queue-4.14/xen-x86-entry-64-add-xen-nmi-trap-entry.patch
queue-4.14/x86-entry-64-remove-the-restore_c_regs_and_iret-label.patch
queue-4.14/x86-entry-64-create-a-per-cpu-syscall-entry-trampoline.patch
queue-4.14/x86-entry-64-remove-the-restore_..._regs-infrastructure.patch
queue-4.14/x86-xen-64-x86-entry-64-clean-up-sp-code-in-cpu_initialize_context.patch
queue-4.14/x86-entry-add-task_top_of_stack-to-find-the-top-of-a-task-s-stack.patch
queue-4.14/x86-entry-64-remove-all-remaining-direct-thread_struct-sp0-reads.patch
queue-4.14/x86-boot-relocate-definition-of-the-initial-state-of-cr0.patch
queue-4.14/x86-entry-64-stop-initializing-tss.sp0-at-boot.patch
queue-4.14/x86-entry-64-de-xen-ify-our-nmi-code.patch
queue-4.14/objtool-don-t-report-end-of-section-error-after-an-empty-unwind-hint.patch
queue-4.14/x86-entry-64-pass-sp0-directly-to-load_sp0.patch
queue-4.14/x86-entry-64-use-a-per-cpu-trampoline-stack-for-idt-entries.patch
queue-4.14/x86-entry-64-move-swapgs-into-the-common-iret-to-usermode-path.patch
queue-4.14/x86-entry-64-shorten-test-instructions.patch
queue-4.14/x86-cpufeature-add-user-mode-instruction-prevention-definitions.patch
queue-4.14/x86-cpufeatures-make-cpu-bugs-sticky.patch
queue-4.14/x86-espfix-64-stop-assuming-that-pt_regs-is-on-the-entry-stack.patch
queue-4.14/x86-traps-use-a-new-on_thread_stack-helper-to-clean-up-an-assertion.patch
queue-4.14/x86-xen-fix-xen-head-elf-annotations.patch
queue-4.14/x86-entry-64-remove-thread_struct-sp0.patch
queue-4.14/x86-entry-move-sysenter_stack-to-the-beginning-of-struct-tss_struct.patch
queue-4.14/x86-entry-64-allocate-and-enable-the-sysenter-stack.patch
queue-4.14/x86-unwinder-orc-dont-bail-on-stack-overflow.patch
queue-4.14/x86-head-fix-head-elf-function-annotations.patch
queue-4.14/selftests-x86-ldt_gdt-run-most-existing-ldt-test-cases-against-the-gdt-as-well.patch
queue-4.14/x86-entry-32-pull-the-msr_ia32_sysenter_cs-update-code-out-of-native_load_sp0.patch
queue-4.14/x86-entry-64-split-the-iret-to-user-and-iret-to-kernel-paths.patch
queue-4.14/x86-entry-64-shrink-paranoid_exit_restore-and-make-labels-local.patch
queue-4.14/x86-head-add-unwind-hint-annotations.patch
queue-4.14/x86-head-remove-unused-bad_address-code.patch
queue-4.14/x86-xen-add-unwind-hint-annotations.patch
queue-4.14/x86-kasan-64-teach-kasan-about-the-cpu_entry_area.patch
queue-4.14/x86-head-remove-confusing-comment.patch
queue-4.14/x86-entry-64-remove-the-sysenter-stack-canary.patch
queue-4.14/x86-mm-kasan-don-t-use-vmemmap_populate-to-initialize-shadow.patch
queue-4.14/x86-entry-gdt-put-per-cpu-gdt-remaps-in-ascending-order.patch
queue-4.14/x86-entry-fix-assumptions-that-the-hw-tss-is-at-the-beginning-of-cpu_tss.patch
queue-4.14/x86-cpufeatures-re-tabulate-the-x86_feature-definitions.patch
queue-4.14/x86-entry-32-fix-cpu_current_top_of_stack-initialization-at-boot.patch
queue-4.14/ptrace-x86-make-user_64bit_mode-available-to-32-bit-builds.patch
queue-4.14/x86-entry-64-make-cpu_entry_area.tss-read-only.patch
queue-4.14/x86-mm-relocate-page-fault-error-codes-to-traps.h.patch
queue-4.14/x86-unwinder-handle-stack-overflows-more-gracefully.patch
queue-4.14/x86-entry-64-use-pop-instead-of-mov-to-restore-regs-on-nmi-return.patch
queue-4.14/x86-irq-64-print-the-offending-ip-in-the-stack-overflow-warning.patch
queue-4.14/x86-entry-clean-up-the-sysenter_stack-code.patch
queue-4.14/x86-entry-64-merge-the-fast-and-slow-sysret-paths.patch
queue-4.14/x86-entry-64-separate-cpu_current_top_of_stack-from-tss.sp0.patch
queue-4.14/x86-boot-annotate-verify_cpu-as-a-callable-function.patch
queue-4.14/x86-irq-remove-an-old-outdated-comment-about-context-tracking-races.patch