x86_64: add KASan support

This patch adds arch specific code for kernel address sanitizer.

16TB of virtual addressed used for shadow memory.  It's located in range
[ffffec0000000000 - fffffc0000000000] between vmemmap and %esp fixup
stacks.

At early stage we map whole shadow region with zero page.  Latter, after
pages mapped to direct mapping address range we unmap zero pages from
corresponding shadow (see kasan_map_shadow()) and allocate and map a real
shadow memory reusing vmemmap_populate() function.

Also replace __pa with __pa_nodebug before shadow initialized.  __pa with
CONFIG_DEBUG_VIRTUAL=y make external function call (__phys_addr)
__phys_addr is instrumented, so __asan_load could be called before shadow
area initialized.

Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: Andrey Konovalov <adech.fo@gmail.com>
Cc: Yuri Gribov <tetra2005@gmail.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Jim Davis <jim.epost@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 46 insertions, 3 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 732223496968..b13b70634124 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -16,6 +16,8 @@ CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
 
+KASAN_SANITIZE_head$(BITS).o := n
+
 CFLAGS_irq.o := -I$(src)/../include/asm/trace
 
 obj-y                   := process_$(BITS).o signal.o entry_$(BITS).o
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index b74ebc7c4402..cf3df1d8d039 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -265,7 +265,10 @@ int __die(const char *str, struct pt_regs *regs, long err)
         printk("SMP ");
 #endif
 #ifdef CONFIG_DEBUG_PAGEALLOC
-        printk("DEBUG_PAGEALLOC");
+        printk("DEBUG_PAGEALLOC ");
+#endif
+#ifdef CONFIG_KASAN
+        printk("KASAN");
 #endif
         printk("\n");
         if (notify_die(DIE_OOPS, str, regs, err,
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index eda1a865641e..efcddfaf05f9 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -27,6 +27,7 @@
 #include <asm/bios_ebda.h>
 #include <asm/bootparam_utils.h>
 #include <asm/microcode.h>
+#include <asm/kasan.h>
 
 /*
  * Manage page tables very early on.
@@ -46,7 +47,7 @@ static void __init reset_early_page_tables(void)
 
         next_early_pgt = 0;
 
-        write_cr3(__pa(early_level4_pgt));
+        write_cr3(__pa_nodebug(early_level4_pgt));
 }
 
 /* Create a new PMD entry */
@@ -59,7 +60,7 @@ int __init early_make_pgtable(unsigned long address)
         pmdval_t pmd, *pmd_p;
 
         /* Invalid address or early pgt is done ?  */
-        if (physaddr >= MAXMEM || read_cr3() != __pa(early_level4_pgt))
+        if (physaddr >= MAXMEM || read_cr3() != __pa_nodebug(early_level4_pgt))
                 return -1;
 
 again:
@@ -158,6 +159,8 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
         /* Kill off the identity-map trampoline */
         reset_early_page_tables();
 
+        kasan_map_early_shadow(early_level4_pgt);
+
         /* clear bss before set_intr_gate with early_idt_handler */
         clear_bss();
 
@@ -179,6 +182,8 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
         /* set init_level4_pgt kernel high mapping*/
         init_level4_pgt[511] = early_level4_pgt[511];
 
+        kasan_map_early_shadow(init_level4_pgt);
+
         x86_64_start_reservations(real_mode_data);
 }
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index a468c0a65c42..6fd514d9f69a 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -514,8 +514,38 @@ ENTRY(phys_base)
         /* This must match the first entry in level2_kernel_pgt */
         .quad   0x0000000000000000
 
+#ifdef CONFIG_KASAN
+#define FILL(VAL, COUNT)                                \
+        .rept (COUNT) ;                                 \
+        .quad   (VAL) ;                                 \
+        .endr
+
+NEXT_PAGE(kasan_zero_pte)
+        FILL(kasan_zero_page - __START_KERNEL_map + _KERNPG_TABLE, 512)
+NEXT_PAGE(kasan_zero_pmd)
+        FILL(kasan_zero_pte - __START_KERNEL_map + _KERNPG_TABLE, 512)
+NEXT_PAGE(kasan_zero_pud)
+        FILL(kasan_zero_pmd - __START_KERNEL_map + _KERNPG_TABLE, 512)
+
+#undef FILL
+#endif
+
+
 #include "../../x86/xen/xen-head.S"
         
         __PAGE_ALIGNED_BSS
 NEXT_PAGE(empty_zero_page)
         .skip PAGE_SIZE
+
+#ifdef CONFIG_KASAN
+/*
+ * This page used as early shadow. We don't use empty_zero_page
+ * at early stages, stack instrumentation could write some garbage
+ * to this page.
+ * Latter we reuse it as zero shadow for large ranges of memory
+ * that allowed to access, but not instrumented by kasan
+ * (vmalloc/vmemmap ...).
+ */
+NEXT_PAGE(kasan_zero_page)
+        .skip PAGE_SIZE
+#endif
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c4648adadd7d..27d200929864 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -89,6 +89,7 @@
 #include <asm/cacheflush.h>
 #include <asm/processor.h>
 #include <asm/bugs.h>
+#include <asm/kasan.h>
 
 #include <asm/vsyscall.h>
 #include <asm/cpu.h>
@@ -1174,6 +1175,8 @@ void __init setup_arch(char **cmdline_p)
 
         x86_init.paging.pagetable_init();
 
+        kasan_init();
+
         if (boot_cpu_data.cpuid_level >= 0) {
                 /* A CPU has %cr4 if and only if it has CPUID */
                 mmu_cr4_features = read_cr4();