Patch "x86/entry/64: Move the IST stacks into struct cpu_entry_area" has been added to the 4.14-stable tree

Patch "x86/entry/64: Move the IST stacks into struct 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/64: Move the IST stacks into struct 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-64-move-the-ist-stacks-into-struct-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 40e7f949e0d9a33968ebde5d67f7e3a47c97742a Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@kernel.org>
Date: Mon, 4 Dec 2017 15:07:26 +0100
Subject: x86/entry/64: Move the IST stacks into struct cpu_entry_area

From: Andy Lutomirski <luto@kernel.org>

commit 40e7f949e0d9a33968ebde5d67f7e3a47c97742a upstream.

The IST stacks are needed when an IST exception occurs and are accessed
before any kernel code at all runs.  Move them into struct cpu_entry_area.

The IST stacks are unlike the rest of cpu_entry_area: they're used even for
entries from kernel mode.  This means that they should be set up before we
load the final IDT.  Move cpu_entry_area setup to trap_init() for the boot
CPU and set it up for all possible CPUs at once in native_smp_prepare_cpus().

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 <bp@suse.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bpetkov@suse.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/20171204150606.480598743@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 arch/x86/include/asm/fixmap.h |   12 ++++++
 arch/x86/kernel/cpu/common.c  |   74 +++++++++++++++++++++++-------------------
 arch/x86/kernel/traps.c       |    3 +
 3 files changed, 57 insertions(+), 32 deletions(-)

--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -63,10 +63,22 @@ struct cpu_entry_area {
 	struct tss_struct tss;
 
 	char entry_trampoline[PAGE_SIZE];
+
+#ifdef CONFIG_X86_64
+	/*
+	 * Exception stacks used for IST entries.
+	 *
+	 * In the future, this should have a separate slot for each stack
+	 * with guard pages between them.
+	 */
+	char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
+#endif
 };
 
 #define CPU_ENTRY_AREA_PAGES (sizeof(struct cpu_entry_area) / PAGE_SIZE)
 
+extern void setup_cpu_entry_areas(void);
+
 /*
  * Here we define all the compile-time 'special' virtual
  * addresses. The point is to have a constant address at
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -466,24 +466,36 @@ 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
 
+#ifdef CONFIG_X86_64
+/*
+ * Special IST stacks which the CPU switches to when it calls
+ * an IST-marked descriptor entry. Up to 7 stacks (hardware
+ * limit), all of them are 4K, except the debug stack which
+ * is 8K.
+ */
+static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
+	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
+	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
+};
+
+static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
+#endif
+
+static void __init
+set_percpu_fixmap_pages(int idx, void *ptr, int pages, pgprot_t prot)
+{
+	for ( ; pages; pages--, idx--, ptr += PAGE_SIZE)
+		__set_fixmap(idx, per_cpu_ptr_to_phys(ptr), prot);
+}
+
 /* Setup the fixmap mappings only once per-processor */
-static inline void setup_cpu_entry_area(int cpu)
+static void __init setup_cpu_entry_area(int cpu)
 {
 #ifdef CONFIG_X86_64
 	extern char _entry_trampoline[];
@@ -532,15 +544,31 @@ static inline void setup_cpu_entry_area(
 				PAGE_KERNEL);
 
 #ifdef CONFIG_X86_32
-	this_cpu_write(cpu_entry_area, get_cpu_entry_area(cpu));
+	per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu);
 #endif
 
 #ifdef CONFIG_X86_64
+	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
+	BUILD_BUG_ON(sizeof(exception_stacks) !=
+		     sizeof(((struct cpu_entry_area *)0)->exception_stacks));
+	set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, exception_stacks),
+				&per_cpu(exception_stacks, cpu),
+				sizeof(exception_stacks) / PAGE_SIZE,
+				PAGE_KERNEL);
+
 	__set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline),
 		     __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
 #endif
 }
 
+void __init setup_cpu_entry_areas(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		setup_cpu_entry_area(cpu);
+}
+
 /* Load the original GDT from the per-cpu structure */
 void load_direct_gdt(int cpu)
 {
@@ -1385,20 +1413,6 @@ DEFINE_PER_CPU(unsigned int, irq_count)
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 
-/*
- * Special IST stacks which the CPU switches to when it calls
- * an IST-marked descriptor entry. Up to 7 stacks (hardware
- * limit), all of them are 4K, except the debug stack which
- * is 8K.
- */
-static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
-	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
-	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
-};
-
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
-	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
-
 /* May not be marked __init: used by software suspend */
 void syscall_init(void)
 {
@@ -1607,7 +1621,7 @@ void cpu_init(void)
 	 * set up and load the per-CPU TSS
 	 */
 	if (!oist->ist[0]) {
-		char *estacks = per_cpu(exception_stacks, cpu);
+		char *estacks = get_cpu_entry_area(cpu)->exception_stacks;
 
 		for (v = 0; v < N_EXCEPTION_STACKS; v++) {
 			estacks += exception_stack_sizes[v];
@@ -1633,8 +1647,6 @@ void cpu_init(void)
 	initialize_tlbstate_and_flush();
 	enter_lazy_tlb(&init_mm, me);
 
-	setup_cpu_entry_area(cpu);
-
 	/*
 	 * Initialize the TSS.  sp0 points to the entry trampoline stack
 	 * regardless of what task is running.
@@ -1694,8 +1706,6 @@ 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.
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -947,6 +947,9 @@ dotraplinkage void do_iret_error(struct
 
 void __init trap_init(void)
 {
+	/* Init cpu_entry_area before IST entries are set up */
+	setup_cpu_entry_areas();
+
 	idt_setup_traps();
 
 	/*


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