x86: Remap GDT tables in the fixmap section

Each processor holds a GDT in its per-cpu structure. The sgdt
instruction gives the base address of the current GDT. This address can
be used to bypass KASLR memory randomization. With another bug, an
attacker could target other per-cpu structures or deduce the base of
the main memory section (PAGE_OFFSET).

This patch relocates the GDT table for each processor inside the
fixmap section. The space is reserved based on number of supported
processors.

For consistency, the remapping is done by default on 32 and 64-bit.

Each processor switches to its remapped GDT at the end of
initialization. For hibernation, the main processor returns with the
original GDT and switches back to the remapping at completion.

This patch was tested on both architectures. Hibernation and KVM were
both tested specially for their usage of the GDT.

Thanks to Boris Ostrovsky <boris.ostrovsky@oracle.com> for testing and
recommending changes for Xen support.

Signed-off-by: Thomas Garnier <thgarnie@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Len Brown <len.brown@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Luis R . Rodriguez <mcgrof@kernel.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Rafael J . Wysocki <rjw@rjwysocki.net>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: kasan-dev@googlegroups.com
Cc: kernel-hardening@lists.openwall.com
Cc: kvm@vger.kernel.org
Cc: lguest@lists.ozlabs.org
Cc: linux-doc@vger.kernel.org
Cc: linux-efi@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: linux-pm@vger.kernel.org
Cc: xen-devel@lists.xenproject.org
Cc: zijun_hu <zijun_hu@htc.com>
Link: http://lkml.kernel.org/r/20170314170508.100882-2-thgarnie@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/entry/vdso/vma.c

@@ -354,7 +354,7 @@ static void vgetcpu_cpu_init(void *arg)
 	d.p = 1;		/* Present */
 	d.d = 1;		/* 32-bit */
 
-	write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
+	write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
 }
 
 static int vgetcpu_online(unsigned int cpu)

arch/x86/include/asm/desc.h

@@ -4,6 +4,7 @@
 #include <asm/desc_defs.h>
 #include <asm/ldt.h>
 #include <asm/mmu.h>
+#include <asm/fixmap.h>
 
 #include <linux/smp.h>
 #include <linux/percpu.h>
@@ -38,6 +39,7 @@ extern struct desc_ptr idt_descr;
 extern gate_desc idt_table[];
 extern const struct desc_ptr debug_idt_descr;
 extern gate_desc debug_idt_table[];
+extern pgprot_t pg_fixmap_gdt_flags;
 
 struct gdt_page {
 	struct desc_struct gdt[GDT_ENTRIES];
@@ -45,11 +47,57 @@ struct gdt_page {
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
 
-static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
+/* Provide the original GDT */
+static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu)
 {
 	return per_cpu(gdt_page, cpu).gdt;
 }
 
+static inline unsigned long get_cpu_gdt_rw_vaddr(unsigned int cpu)
+{
+	return (unsigned long)get_cpu_gdt_rw(cpu);
+}
+
+/* Provide the current original GDT */
+static inline struct desc_struct *get_current_gdt_rw(void)
+{
+	return this_cpu_ptr(&gdt_page)->gdt;
+}
+
+static inline unsigned long get_current_gdt_rw_vaddr(void)
+{
+	return (unsigned long)get_current_gdt_rw();
+}
+
+/* Get the fixmap index for a specific processor */
+static inline unsigned int get_cpu_gdt_ro_index(int cpu)
+{
+	return FIX_GDT_REMAP_BEGIN + cpu;
+}
+
+/* Provide the fixmap address of the remapped GDT */
+static inline struct desc_struct *get_cpu_gdt_ro(int cpu)
+{
+	unsigned int idx = get_cpu_gdt_ro_index(cpu);
+	return (struct desc_struct *)__fix_to_virt(idx);
+}
+
+static inline unsigned long get_cpu_gdt_ro_vaddr(int cpu)
+{
+	return (unsigned long)get_cpu_gdt_ro(cpu);
+}
+
+/* Provide the current read-only GDT */
+static inline struct desc_struct *get_current_gdt_ro(void)
+{
+	return get_cpu_gdt_ro(smp_processor_id());
+}
+
+static inline unsigned long get_current_gdt_ro_vaddr(void)
+{
+	return (unsigned long)get_current_gdt_ro();
+}
+
 #ifdef CONFIG_X86_64
 
 static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func,
@@ -174,7 +222,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned t
 
 static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr)
 {
-	struct desc_struct *d = get_cpu_gdt_table(cpu);
+	struct desc_struct *d = get_cpu_gdt_rw(cpu);
 	tss_desc tss;
 
 	set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS,
@@ -194,7 +242,7 @@ static inline void native_set_ldt(const void *addr, unsigned int entries)
 
 		set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT,
 				      entries * LDT_ENTRY_SIZE - 1);
-		write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT,
+		write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_LDT,
 				&ldt, DESC_LDT);
 		asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8));
 	}
@@ -209,7 +257,7 @@ DECLARE_PER_CPU(bool, __tss_limit_invalid);
 
 static inline void force_reload_TR(void)
 {
-	struct desc_struct *d = get_cpu_gdt_table(smp_processor_id());
+	struct desc_struct *d = get_current_gdt_rw();
 	tss_desc tss;
 
 	memcpy(&tss, &d[GDT_ENTRY_TSS], sizeof(tss_desc));
@@ -288,7 +336,7 @@ static inline unsigned long native_store_tr(void)
 
 static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
 {
-	struct desc_struct *gdt = get_cpu_gdt_table(cpu);
+	struct desc_struct *gdt = get_cpu_gdt_rw(cpu);
 	unsigned int i;
 
 	for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)

arch/x86/include/asm/fixmap.h

@@ -100,6 +100,10 @@ enum fixed_addresses {
 #ifdef	CONFIG_X86_INTEL_MID
 	FIX_LNW_VRTC,
 #endif
+	/* Fixmap entries to remap the GDTs, one per processor. */
+	FIX_GDT_REMAP_BEGIN,
+	FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1,
+
 	__end_of_permanent_fixed_addresses,
 
 	/*

arch/x86/include/asm/processor.h

@@ -716,6 +716,7 @@ extern struct desc_ptr		early_gdt_descr;
 
 extern void cpu_set_gdt(int);
 extern void switch_to_new_gdt(int);
+extern void load_fixmap_gdt(int);
 extern void load_percpu_segment(int);
 extern void cpu_init(void);
 

arch/x86/include/asm/stackprotector.h

@@ -87,7 +87,7 @@ static inline void setup_stack_canary_segment(int cpu)
 {
 #ifdef CONFIG_X86_32
 	unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu);
-	struct desc_struct *gdt_table = get_cpu_gdt_table(cpu);
+	struct desc_struct *gdt_table = get_cpu_gdt_rw(cpu);
 	struct desc_struct desc;
 
 	desc = gdt_table[GDT_ENTRY_STACK_CANARY];

arch/x86/kernel/acpi/sleep.c

@@ -101,7 +101,7 @@ int x86_acpi_suspend_lowlevel(void)
 #ifdef CONFIG_SMP
 	initial_stack = (unsigned long)temp_stack + sizeof(temp_stack);
 	early_gdt_descr.address =
-			(unsigned long)get_cpu_gdt_table(smp_processor_id());
+			(unsigned long)get_cpu_gdt_rw(smp_processor_id());
 	initial_gs = per_cpu_offset(smp_processor_id());
 #endif
 	initial_code = (unsigned long)wakeup_long64;

arch/x86/kernel/apm_32.c

@@ -609,7 +609,7 @@ static long __apm_bios_call(void *_call)
 
 	cpu = get_cpu();
 	BUG_ON(cpu != 0);
-	gdt = get_cpu_gdt_table(cpu);
+	gdt = get_cpu_gdt_rw(cpu);
 	save_desc_40 = gdt[0x40 / 8];
 	gdt[0x40 / 8] = bad_bios_desc;
 
@@ -685,7 +685,7 @@ static long __apm_bios_call_simple(void *_call)
 
 	cpu = get_cpu();
 	BUG_ON(cpu != 0);
-	gdt = get_cpu_gdt_table(cpu);
+	gdt = get_cpu_gdt_rw(cpu);
 	save_desc_40 = gdt[0x40 / 8];
 	gdt[0x40 / 8] = bad_bios_desc;
 
@@ -2352,7 +2352,7 @@ static int __init apm_init(void)
 	 * Note we only set APM segments on CPU zero, since we pin the APM
 	 * code to that CPU.
 	 */
-	gdt = get_cpu_gdt_table(0);
+	gdt = get_cpu_gdt_rw(0);
 	set_desc_base(&gdt[APM_CS >> 3],
 		 (unsigned long)__va((unsigned long)apm_info.bios.cseg << 4));
 	set_desc_base(&gdt[APM_CS_16 >> 3],

arch/x86/kernel/cpu/common.c

@@ -448,6 +448,26 @@ void load_percpu_segment(int cpu)
 	load_stack_canary_segment();
 }
 
+/* Used by XEN to force the GDT read-only when required */
+pgprot_t pg_fixmap_gdt_flags = PAGE_KERNEL;
+
+/* Setup the fixmap mapping only once per-processor */
+static inline void setup_fixmap_gdt(int cpu)
+{
+	__set_fixmap(get_cpu_gdt_ro_index(cpu),
+		     __pa(get_cpu_gdt_rw(cpu)), pg_fixmap_gdt_flags);
+}
+
+/* Load a fixmap remapping of the per-cpu GDT */
+void load_fixmap_gdt(int cpu)
+{
+	struct desc_ptr gdt_descr;
+
+	gdt_descr.address = (long)get_cpu_gdt_ro(cpu);
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
+}
+
 /*
  * Current gdt points %fs at the "master" per-cpu area: after this,
  * it's on the real one.
@@ -456,11 +476,10 @@ void switch_to_new_gdt(int cpu)
 {
 	struct desc_ptr gdt_descr;
 
-	gdt_descr.address = (long)get_cpu_gdt_table(cpu);
+	gdt_descr.address = (long)get_cpu_gdt_rw(cpu);
 	gdt_descr.size = GDT_SIZE - 1;
 	load_gdt(&gdt_descr);
 	/* Reload the per-cpu base */
-
 	load_percpu_segment(cpu);
 }
 
@@ -1526,6 +1545,9 @@ void cpu_init(void)
 
 	if (is_uv_system())
 		uv_cpu_init();
+
+	setup_fixmap_gdt(cpu);
+	load_fixmap_gdt(cpu);
 }
 
 #else
@@ -1581,6 +1603,9 @@ void cpu_init(void)
 	dbg_restore_debug_regs();
 
 	fpu__init_cpu();
+
+	setup_fixmap_gdt(cpu);
+	load_fixmap_gdt(cpu);
 }
 #endif
 

arch/x86/kernel/setup_percpu.c

@@ -160,7 +160,7 @@ static inline void setup_percpu_segment(int cpu)
 	pack_descriptor(&gdt, per_cpu_offset(cpu), 0xFFFFF,
 			0x2 | DESCTYPE_S, 0x8);
 	gdt.s = 1;
-	write_gdt_entry(get_cpu_gdt_table(cpu),
+	write_gdt_entry(get_cpu_gdt_rw(cpu),
 			GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S);
 #endif
 }

arch/x86/kernel/smpboot.c

@@ -983,7 +983,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 	unsigned long timeout;
 
 	idle->thread.sp = (unsigned long)task_pt_regs(idle);
-	early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
+	early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu);
 	initial_code = (unsigned long)start_secondary;
 	initial_stack  = idle->thread.sp;
 

arch/x86/platform/efi/efi_32.c

@@ -68,7 +68,7 @@ pgd_t * __init efi_call_phys_prolog(void)
 	load_cr3(initial_page_table);
 	__flush_tlb_all();
 
-	gdt_descr.address = __pa(get_cpu_gdt_table(0));
+	gdt_descr.address = __pa(get_cpu_gdt_rw(0));
 	gdt_descr.size = GDT_SIZE - 1;
 	load_gdt(&gdt_descr);
 
@@ -79,7 +79,7 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 {
 	struct desc_ptr gdt_descr;
 
-	gdt_descr.address = (unsigned long)get_cpu_gdt_table(0);
+	gdt_descr.address = (unsigned long)get_cpu_gdt_rw(0);
 	gdt_descr.size = GDT_SIZE - 1;
 	load_gdt(&gdt_descr);
 

arch/x86/power/cpu.c

@@ -95,7 +95,7 @@ static void __save_processor_state(struct saved_context *ctxt)
 	 * 'pmode_gdt' in wakeup_start.
 	 */
 	ctxt->gdt_desc.size = GDT_SIZE - 1;
-	ctxt->gdt_desc.address = (unsigned long)get_cpu_gdt_table(smp_processor_id());
+	ctxt->gdt_desc.address = (unsigned long)get_cpu_gdt_rw(smp_processor_id());
 
 	store_tr(ctxt->tr);
 
@@ -162,7 +162,7 @@ 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_table(cpu);
+	struct desc_struct *desc = get_cpu_gdt_rw(cpu);
 	tss_desc tss;
 #endif
 	set_tss_desc(cpu, t);	/*
@@ -183,6 +183,9 @@ static void fix_processor_context(void)
 	load_mm_ldt(current->active_mm);	/* This does lldt */
 
 	fpu__resume_cpu();
+
+	/* The processor is back on the direct GDT, load back the fixmap */
+	load_fixmap_gdt(cpu);
 }
 
 /**

arch/x86/xen/enlighten.c

@@ -710,7 +710,7 @@ static void load_TLS_descriptor(struct thread_struct *t,
 
 	*shadow = t->tls_array[i];
 
-	gdt = get_cpu_gdt_table(cpu);
+	gdt = get_cpu_gdt_rw(cpu);
 	maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]);
 	mc = __xen_mc_entry(0);
 
@@ -1545,6 +1545,9 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	 */
 	xen_initial_gdt = &per_cpu(gdt_page, 0);
 
+	/* GDT can only be remapped RO */
+	pg_fixmap_gdt_flags = PAGE_KERNEL_RO;
+
 	xen_smp_init();
 
 #ifdef CONFIG_ACPI_NUMA

arch/x86/xen/mmu.c

@@ -2326,6 +2326,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 	case FIX_TEXT_POKE0:
 	case FIX_TEXT_POKE1:
+	case FIX_GDT_REMAP_BEGIN ... FIX_GDT_REMAP_END:
 		/* All local page mappings */
 		pte = pfn_pte(phys, prot);
 		break;

arch/x86/xen/smp.c

@@ -392,7 +392,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 	if (ctxt == NULL)
 		return -ENOMEM;
 
-	gdt = get_cpu_gdt_table(cpu);
+	gdt = get_cpu_gdt_rw(cpu);
 
 #ifdef CONFIG_X86_32
 	ctxt->user_regs.fs = __KERNEL_PERCPU;

drivers/lguest/x86/core.c

@@ -504,7 +504,7 @@ void __init lguest_arch_host_init(void)
 		 * byte, not the size, hence the "-1").
 		 */
 		state->host_gdt_desc.size = GDT_SIZE-1;
-		state->host_gdt_desc.address = (long)get_cpu_gdt_table(i);
+		state->host_gdt_desc.address = (long)get_cpu_gdt_rw(i);
 
 		/*
 		 * All CPUs on the Host use the same Interrupt Descriptor
@@ -554,8 +554,8 @@ void __init lguest_arch_host_init(void)
 		 * The Host needs to be able to use the LGUEST segments on this
 		 * CPU, too, so put them in the Host GDT.
 		 */
-		get_cpu_gdt_table(i)[GDT_ENTRY_LGUEST_CS] = FULL_EXEC_SEGMENT;
-		get_cpu_gdt_table(i)[GDT_ENTRY_LGUEST_DS] = FULL_SEGMENT;
+		get_cpu_gdt_rw(i)[GDT_ENTRY_LGUEST_CS] = FULL_EXEC_SEGMENT;
+		get_cpu_gdt_rw(i)[GDT_ENTRY_LGUEST_DS] = FULL_SEGMENT;
 	}
 
 	/*

drivers/pnp/pnpbios/bioscalls.c

@@ -54,7 +54,7 @@ __asm__(".text			\n"
 
 #define Q2_SET_SEL(cpu, selname, address, size) \
 do { \
-	struct desc_struct *gdt = get_cpu_gdt_table((cpu)); \
+	struct desc_struct *gdt = get_cpu_gdt_rw((cpu)); \
 	set_desc_base(&gdt[(selname) >> 3], (u32)(address)); \
 	set_desc_limit(&gdt[(selname) >> 3], (size) - 1); \
 } while(0)
@@ -95,8 +95,8 @@ static inline u16 call_pnp_bios(u16 func, u16 arg1, u16 arg2, u16 arg3,
 		return PNP_FUNCTION_NOT_SUPPORTED;
 
 	cpu = get_cpu();
-	save_desc_40 = get_cpu_gdt_table(cpu)[0x40 / 8];
-	get_cpu_gdt_table(cpu)[0x40 / 8] = bad_bios_desc;
+	save_desc_40 = get_cpu_gdt_rw(cpu)[0x40 / 8];
+	get_cpu_gdt_rw(cpu)[0x40 / 8] = bad_bios_desc;
 
 	/* On some boxes IRQ's during PnP BIOS calls are deadly.  */
 	spin_lock_irqsave(&pnp_bios_lock, flags);
@@ -134,7 +134,7 @@ static inline u16 call_pnp_bios(u16 func, u16 arg1, u16 arg2, u16 arg3,
 			     :"memory");
 	spin_unlock_irqrestore(&pnp_bios_lock, flags);
 
-	get_cpu_gdt_table(cpu)[0x40 / 8] = save_desc_40;
+	get_cpu_gdt_rw(cpu)[0x40 / 8] = save_desc_40;
 	put_cpu();
 
 	/* If we get here and this is set then the PnP BIOS faulted on us. */
@@ -477,7 +477,7 @@ void pnpbios_calls_init(union pnp_bios_install_struct *header)
 	pnp_bios_callpoint.segment = PNP_CS16;
 
 	for_each_possible_cpu(i) {
-		struct desc_struct *gdt = get_cpu_gdt_table(i);
+		struct desc_struct *gdt = get_cpu_gdt_rw(i);
 		if (!gdt)
 			continue;
 		set_desc_base(&gdt[GDT_ENTRY_PNPBIOS_CS32],