Patch "x86/entry/64: Pass SP0 directly to load_sp0()" has been added to the 4.14-stable tree

[<gregkh@linuxfoundation.org>]

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

    x86/entry/64: Pass SP0 directly to load_sp0()

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-64-pass-sp0-directly-to-load_sp0.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 da51da189a24bb9b7e2d5a123be096e51a4695a5 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@kernel.org>
Date: Thu, 2 Nov 2017 00:59:10 -0700
Subject: x86/entry/64: Pass SP0 directly to load_sp0()

From: Andy Lutomirski <luto@kernel.org>

commit da51da189a24bb9b7e2d5a123be096e51a4695a5 upstream.

load_sp0() had an odd signature:

  void load_sp0(struct tss_struct *tss, struct thread_struct *thread);

Simplify it to:

  void load_sp0(unsigned long sp0);

Also simplify a few get_cpu()/put_cpu() sequences to
preempt_disable()/preempt_enable().

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: Borislav Petkov <bpetkov@suse.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/2655d8b42ed940aa384fe18ee1129bbbcf730a08.1509609304.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 arch/x86/include/asm/paravirt.h       |    5 ++---
 arch/x86/include/asm/paravirt_types.h |    2 +-
 arch/x86/include/asm/processor.h      |    9 ++++-----
 arch/x86/kernel/cpu/common.c          |    4 ++--
 arch/x86/kernel/process_32.c          |    2 +-
 arch/x86/kernel/process_64.c          |    2 +-
 arch/x86/kernel/vm86_32.c             |   14 ++++++--------
 arch/x86/xen/enlighten_pv.c           |    7 +++----
 8 files changed, 20 insertions(+), 25 deletions(-)

--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -16,10 +16,9 @@
 #include <linux/cpumask.h>
 #include <asm/frame.h>
 
-static inline void load_sp0(struct tss_struct *tss,
-			     struct thread_struct *thread)
+static inline void load_sp0(unsigned long sp0)
 {
-	PVOP_VCALL2(pv_cpu_ops.load_sp0, tss, thread);
+	PVOP_VCALL1(pv_cpu_ops.load_sp0, sp0);
 }
 
 /* The paravirtualized CPUID instruction. */
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -134,7 +134,7 @@ struct pv_cpu_ops {
 	void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries);
 	void (*free_ldt)(struct desc_struct *ldt, unsigned entries);
 
-	void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t);
+	void (*load_sp0)(unsigned long sp0);
 
 	void (*set_iopl_mask)(unsigned mask);
 
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -518,9 +518,9 @@ static inline void native_set_iopl_mask(
 }
 
 static inline void
-native_load_sp0(struct tss_struct *tss, struct thread_struct *thread)
+native_load_sp0(unsigned long sp0)
 {
-	tss->x86_tss.sp0 = thread->sp0;
+	this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
 }
 
 static inline void native_swapgs(void)
@@ -545,10 +545,9 @@ static inline unsigned long current_top_
 #else
 #define __cpuid			native_cpuid
 
-static inline void load_sp0(struct tss_struct *tss,
-			    struct thread_struct *thread)
+static inline void load_sp0(unsigned long sp0)
 {
-	native_load_sp0(tss, thread);
+	native_load_sp0(sp0);
 }
 
 #define set_iopl_mask native_set_iopl_mask
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1570,7 +1570,7 @@ void cpu_init(void)
 	initialize_tlbstate_and_flush();
 	enter_lazy_tlb(&init_mm, me);
 
-	load_sp0(t, &current->thread);
+	load_sp0(current->thread.sp0);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
 	load_mm_ldt(&init_mm);
@@ -1625,7 +1625,7 @@ void cpu_init(void)
 	initialize_tlbstate_and_flush();
 	enter_lazy_tlb(&init_mm, curr);
 
-	load_sp0(t, thread);
+	load_sp0(thread->sp0);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
 	load_mm_ldt(&init_mm);
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -287,7 +287,7 @@ __switch_to(struct task_struct *prev_p,
 	 * current_thread_info().  Refresh the SYSENTER configuration in
 	 * case prev or next is vm86.
 	 */
-	load_sp0(tss, next);
+	load_sp0(next->sp0);
 	refresh_sysenter_cs(next);
 	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -465,7 +465,7 @@ __switch_to(struct task_struct *prev_p,
 	this_cpu_write(current_task, next_p);
 
 	/* Reload sp0. */
-	load_sp0(tss, next);
+	load_sp0(next->sp0);
 
 	/*
 	 * Now maybe reload the debug registers and handle I/O bitmaps
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -95,7 +95,6 @@
 
 void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 {
-	struct tss_struct *tss;
 	struct task_struct *tsk = current;
 	struct vm86plus_struct __user *user;
 	struct vm86 *vm86 = current->thread.vm86;
@@ -147,13 +146,13 @@ void save_v86_state(struct kernel_vm86_r
 		do_exit(SIGSEGV);
 	}
 
-	tss = &per_cpu(cpu_tss, get_cpu());
+	preempt_disable();
 	tsk->thread.sp0 = vm86->saved_sp0;
 	tsk->thread.sysenter_cs = __KERNEL_CS;
-	load_sp0(tss, &tsk->thread);
+	load_sp0(tsk->thread.sp0);
 	refresh_sysenter_cs(&tsk->thread);
 	vm86->saved_sp0 = 0;
-	put_cpu();
+	preempt_enable();
 
 	memcpy(&regs->pt, &vm86->regs32, sizeof(struct pt_regs));
 
@@ -239,7 +238,6 @@ SYSCALL_DEFINE2(vm86, unsigned long, cmd
 
 static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 {
-	struct tss_struct *tss;
 	struct task_struct *tsk = current;
 	struct vm86 *vm86 = tsk->thread.vm86;
 	struct kernel_vm86_regs vm86regs;
@@ -367,8 +365,8 @@ static long do_sys_vm86(struct vm86plus_
 	vm86->saved_sp0 = tsk->thread.sp0;
 	lazy_save_gs(vm86->regs32.gs);
 
-	tss = &per_cpu(cpu_tss, get_cpu());
 	/* make room for real-mode segments */
+	preempt_disable();
 	tsk->thread.sp0 += 16;
 
 	if (static_cpu_has(X86_FEATURE_SEP)) {
@@ -376,8 +374,8 @@ static long do_sys_vm86(struct vm86plus_
 		refresh_sysenter_cs(&tsk->thread);
 	}
 
-	load_sp0(tss, &tsk->thread);
-	put_cpu();
+	load_sp0(tsk->thread.sp0);
+	preempt_enable();
 
 	if (vm86->flags & VM86_SCREEN_BITMAP)
 		mark_screen_rdonly(tsk->mm);
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -811,15 +811,14 @@ static void __init xen_write_gdt_entry_b
 	}
 }
 
-static void xen_load_sp0(struct tss_struct *tss,
-			 struct thread_struct *thread)
+static void xen_load_sp0(unsigned long sp0)
 {
 	struct multicall_space mcs;
 
 	mcs = xen_mc_entry(0);
-	MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->sp0);
+	MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0);
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
-	tss->x86_tss.sp0 = thread->sp0;
+	this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
 }
 
 void xen_set_iopl_mask(unsigned mask)


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