x86: Make the GDT remapping read-only on 64-bit

This patch makes the GDT remapped pages read-only, to prevent accidental
(or intentional) corruption of this key data structure.

This change is done only on 64-bit, because 32-bit needs it to be writable
for TSS switches.

The native_load_tr_desc function was adapted to correctly handle a
read-only GDT. The LTR instruction always writes to the GDT TSS entry.
This generates a page fault if the GDT is read-only. This change checks
if the current GDT is a remap and swap GDTs as needed. This function was
tested by booting multiple machines and checking hibernation works
properly.

KVM SVM and VMX were adapted to use the writeable GDT. On VMX, the
per-cpu variable was removed for functions to fetch the original GDT.
Instead of reloading the previous GDT, VMX will reload the fixmap GDT as
expected. For testing, VMs were started and restored on multiple
configurations.

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/20170314170508.100882-3-thgarnie@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 68 insertions, 38 deletions

diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 4b5ef0c64291..ec05f9c1a62c 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -248,9 +248,77 @@ static inline void native_set_ldt(const void *addr, unsigned int entries)
 	}
 }
 
+static inline void native_load_gdt(const struct desc_ptr *dtr)
+{
+	asm volatile("lgdt %0"::"m" (*dtr));
+}
+
+static inline void native_load_idt(const struct desc_ptr *dtr)
+{
+	asm volatile("lidt %0"::"m" (*dtr));
+}
+
+static inline void native_store_gdt(struct desc_ptr *dtr)
+{
+	asm volatile("sgdt %0":"=m" (*dtr));
+}
+
+static inline void native_store_idt(struct desc_ptr *dtr)
+{
+	asm volatile("sidt %0":"=m" (*dtr));
+}
+
+/*
+ * The LTR instruction marks the TSS GDT entry as busy. On 64-bit, the GDT is
+ * a read-only remapping. To prevent a page fault, the GDT is switched to the
+ * original writeable version when needed.
+ */
+#ifdef CONFIG_X86_64
 static inline void native_load_tr_desc(void)
 {
+	struct desc_ptr gdt;
+	int cpu = raw_smp_processor_id();
+	bool restore = 0;
+	struct desc_struct *fixmap_gdt;
+
+	native_store_gdt(&gdt);
+	fixmap_gdt = get_cpu_gdt_ro(cpu);
+
+	/*
+	 * If the current GDT is the read-only fixmap, swap to the original
+	 * writeable version. Swap back at the end.
+	 */
+	if (gdt.address == (unsigned long)fixmap_gdt) {
+		load_direct_gdt(cpu);
+		restore = 1;
+	}
 	asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8));
+	if (restore)
+		load_fixmap_gdt(cpu);
+}
+#else
+static inline void native_load_tr_desc(void)
+{
+	asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8));
+}
+#endif
+
+static inline unsigned long native_store_tr(void)
+{
+	unsigned long tr;
+
+	asm volatile("str %0":"=r" (tr));
+
+	return tr;
+}
+
+static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
+{
+	struct desc_struct *gdt = get_cpu_gdt_rw(cpu);
+	unsigned int i;
+
+	for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
+		gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
 }
 
 DECLARE_PER_CPU(bool, __tss_limit_invalid);
@@ -305,44 +373,6 @@ static inline void invalidate_tss_limit(void)
 		this_cpu_write(__tss_limit_invalid, true);
 }
 
-static inline void native_load_gdt(const struct desc_ptr *dtr)
-{
-	asm volatile("lgdt %0"::"m" (*dtr));
-}
-
-static inline void native_load_idt(const struct desc_ptr *dtr)
-{
-	asm volatile("lidt %0"::"m" (*dtr));
-}
-
-static inline void native_store_gdt(struct desc_ptr *dtr)
-{
-	asm volatile("sgdt %0":"=m" (*dtr));
-}
-
-static inline void native_store_idt(struct desc_ptr *dtr)
-{
-	asm volatile("sidt %0":"=m" (*dtr));
-}
-
-static inline unsigned long native_store_tr(void)
-{
-	unsigned long tr;
-
-	asm volatile("str %0":"=r" (tr));
-
-	return tr;
-}
-
-static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
-{
-	struct desc_struct *gdt = get_cpu_gdt_rw(cpu);
-	unsigned int i;
-
-	for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
-		gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
-}
-
 /* This intentionally ignores lm, since 32-bit apps don't have that field. */
 #define LDT_empty(info)					\
 	((info)->base_addr		== 0	&&	\