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>

5 files changed, 33 insertions, 8 deletions

diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 4858733..ed01481 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/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;
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 5a41454..446b0d3 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/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],
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 58094a1..3cf1590 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/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
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 9820d6d..11338b0 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/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
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index bd1f1ad..f04479a 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/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;