[RFC v3 19/27] x86: Support global stack cookie

[Thomas Garnier via Virtualization <virtualization@lists.linux-foundation.org>]

Add an off-by-default configuration option to use a global stack cookie
instead of the default TLS. This configuration option will only be used
with PIE binaries.

For kernel stack cookie, the compiler uses the mcmodel=kernel to switch
between the fs segment to gs segment. A PIE binary does not use
mcmodel=kernel because it can be relocated anywhere, therefore the
compiler will default to the fs segment register. This is going to be
fixed with a compiler change allowing to pick the segment register as
done on PowerPC. In the meantime, this configuration can be used to
support older compilers.

Signed-off-by: Thomas Garnier <thgarnie@google.com>
---
 arch/x86/Kconfig                      |  4 ++++
 arch/x86/Makefile                     |  9 +++++++++
 arch/x86/entry/entry_32.S             |  3 ++-
 arch/x86/entry/entry_64.S             |  3 ++-
 arch/x86/include/asm/processor.h      |  3 ++-
 arch/x86/include/asm/stackprotector.h | 19 ++++++++++++++-----
 arch/x86/kernel/asm-offsets.c         |  3 ++-
 arch/x86/kernel/asm-offsets_32.c      |  3 ++-
 arch/x86/kernel/asm-offsets_64.c      |  3 ++-
 arch/x86/kernel/cpu/common.c          |  3 ++-
 arch/x86/kernel/head_32.S             |  3 ++-
 arch/x86/kernel/process.c             |  5 +++++
 12 files changed, 48 insertions(+), 13 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 063f1e0d51aa..777197fab6dd 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2133,6 +2133,10 @@ config RANDOMIZE_MEMORY_PHYSICAL_PADDING
 
 	   If unsure, leave at the default value.
 
+config X86_GLOBAL_STACKPROTECTOR
+	bool
+	depends on CC_STACKPROTECTOR
+
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs"
 	depends on SMP
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 6276572259c8..4cb4f0495ddc 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -60,6 +60,15 @@ endif
 KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow
 KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
 
+ifdef CONFIG_X86_GLOBAL_STACKPROTECTOR
+        ifeq ($(call cc-option, -mstack-protector-guard=global),)
+                $(error Cannot use CONFIG_X86_GLOBAL_STACKPROTECTOR: \
+                        -mstack-protector-guard=global not supported \
+                        by compiler)
+        endif
+        KBUILD_CFLAGS += -mstack-protector-guard=global
+endif
+
 ifeq ($(CONFIG_X86_32),y)
         BITS := 32
         UTS_MACHINE := i386
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 8a13d468635a..ab3e5056722f 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -237,7 +237,8 @@ ENTRY(__switch_to_asm)
 	movl	%esp, TASK_threadsp(%eax)
 	movl	TASK_threadsp(%edx), %esp
 
-#ifdef CONFIG_CC_STACKPROTECTOR
+#if defined(CONFIG_CC_STACKPROTECTOR) && \
+	!defined(CONFIG_X86_GLOBAL_STACKPROTECTOR)
 	movl	TASK_stack_canary(%edx), %ebx
 	movl	%ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
 #endif
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d3a52d2342af..01be62c1b436 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -390,7 +390,8 @@ ENTRY(__switch_to_asm)
 	movq	%rsp, TASK_threadsp(%rdi)
 	movq	TASK_threadsp(%rsi), %rsp
 
-#ifdef CONFIG_CC_STACKPROTECTOR
+#if defined(CONFIG_CC_STACKPROTECTOR) && \
+	!defined(CONFIG_X86_GLOBAL_STACKPROTECTOR)
 	movq	TASK_stack_canary(%rsi), %rbx
 	movq	%rbx, PER_CPU_VAR(irq_stack_union + stack_canary_offset)
 #endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index b09bd50b06c7..e3a7ef8d5fb8 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -394,7 +394,8 @@ DECLARE_PER_CPU(char *, irq_stack_ptr);
 DECLARE_PER_CPU(unsigned int, irq_count);
 extern asmlinkage void ignore_sysret(void);
 #else	/* X86_64 */
-#ifdef CONFIG_CC_STACKPROTECTOR
+#if defined(CONFIG_CC_STACKPROTECTOR) && \
+	defined(CONFIG_X86_GLOBAL_STACKPROTECTOR)
 /*
  * Make sure stack canary segment base is cached-aligned:
  *   "For Intel Atom processors, avoid non zero segment base address
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 8abedf1d650e..66462d778dc5 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -51,6 +51,10 @@
 #define GDT_STACK_CANARY_INIT						\
 	[GDT_ENTRY_STACK_CANARY] = GDT_ENTRY_INIT(0x4090, 0, 0x18),
 
+#ifdef CONFIG_X86_GLOBAL_STACKPROTECTOR
+extern unsigned long __stack_chk_guard;
+#endif
+
 /*
  * Initialize the stackprotector canary value.
  *
@@ -62,7 +66,7 @@ static __always_inline void boot_init_stack_canary(void)
 	u64 canary;
 	u64 tsc;
 
-#ifdef CONFIG_X86_64
+#if defined(CONFIG_X86_64) && !defined(CONFIG_X86_GLOBAL_STACKPROTECTOR)
 	BUILD_BUG_ON(offsetof(union irq_stack_union, stack_canary) != 40);
 #endif
 	/*
@@ -76,17 +80,22 @@ static __always_inline void boot_init_stack_canary(void)
 	canary += tsc + (tsc << 32UL);
 	canary &= CANARY_MASK;
 
+#ifdef CONFIG_X86_GLOBAL_STACKPROTECTOR
+	if (__stack_chk_guard == 0)
+		__stack_chk_guard = canary ?: 1;
+#else /* !CONFIG_X86_GLOBAL_STACKPROTECTOR */
 	current->stack_canary = canary;
 #ifdef CONFIG_X86_64
 	this_cpu_write(irq_stack_union.stack_canary, canary);
-#else
+#else /* CONFIG_X86_32 */
 	this_cpu_write(stack_canary.canary, canary);
 #endif
+#endif
 }
 
 static inline void setup_stack_canary_segment(int cpu)
 {
-#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_GLOBAL_STACKPROTECTOR)
 	unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu);
 	struct desc_struct *gdt_table = get_cpu_gdt_rw(cpu);
 	struct desc_struct desc;
@@ -99,7 +108,7 @@ static inline void setup_stack_canary_segment(int cpu)
 
 static inline void load_stack_canary_segment(void)
 {
-#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_GLOBAL_STACKPROTECTOR)
 	asm("mov %0, %%gs" : : "r" (__KERNEL_STACK_CANARY) : "memory");
 #endif
 }
@@ -115,7 +124,7 @@ static inline void setup_stack_canary_segment(int cpu)
 
 static inline void load_stack_canary_segment(void)
 {
-#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_GLOBAL_STACKPROTECTOR)
 	asm volatile ("mov %0, %%gs" : : "r" (0));
 #endif
 }
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index de827d6ac8c2..b30a12cd021e 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -30,7 +30,8 @@
 void common(void) {
 	BLANK();
 	OFFSET(TASK_threadsp, task_struct, thread.sp);
-#ifdef CONFIG_CC_STACKPROTECTOR
+#if defined(CONFIG_CC_STACKPROTECTOR) && \
+	!defined(CONFIG_X86_GLOBAL_STACKPROTECTOR)
 	OFFSET(TASK_stack_canary, task_struct, stack_canary);
 #endif
 
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 710edab9e644..33584e7e486b 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -54,7 +54,8 @@ void foo(void)
 	/* Size of SYSENTER_stack */
 	DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack));
 
-#ifdef CONFIG_CC_STACKPROTECTOR
+#if defined(CONFIG_CC_STACKPROTECTOR) && \
+	!defined(CONFIG_X86_GLOBAL_STACKPROTECTOR)
 	BLANK();
 	OFFSET(stack_canary_offset, stack_canary, canary);
 #endif
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index cf42206926af..06feb31a09f5 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -64,7 +64,8 @@ int main(void)
 	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
 	BLANK();
 
-#ifdef CONFIG_CC_STACKPROTECTOR
+#if defined(CONFIG_CC_STACKPROTECTOR) && \
+	!defined(CONFIG_X86_GLOBAL_STACKPROTECTOR)
 	DEFINE(stack_canary_offset, offsetof(union irq_stack_union, stack_canary));
 	BLANK();
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8732c9e719d5..839f4da2ed76 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1431,7 +1431,8 @@ DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) =
 	(unsigned long)&init_thread_union + THREAD_SIZE;
 EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack);
 
-#ifdef CONFIG_CC_STACKPROTECTOR
+#if defined(CONFIG_CC_STACKPROTECTOR) && \
+	!defined(CONFIG_X86_GLOBAL_STACKPROTECTOR)
 DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
 #endif
 
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 9ed3074d0d27..a55a67b33934 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -377,7 +377,8 @@ ENDPROC(startup_32_smp)
  */
 __INIT
 setup_once:
-#ifdef CONFIG_CC_STACKPROTECTOR
+#if defined(CONFIG_CC_STACKPROTECTOR) && \
+	!defined(CONFIG_X86_GLOBAL_STACKPROTECTOR)
 	/*
 	 * Configure the stack canary. The linker can't handle this by
 	 * relocation.  Manually set base address in stack canary
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index bd6b85fac666..66ea1a35413e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -73,6 +73,11 @@ EXPORT_PER_CPU_SYMBOL(cpu_tss);
 DEFINE_PER_CPU(bool, __tss_limit_invalid);
 EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
 
+#ifdef CONFIG_X86_GLOBAL_STACKPROTECTOR
+unsigned long __stack_chk_guard __read_mostly;
+EXPORT_SYMBOL(__stack_chk_guard);
+#endif
+
 /*
  * this gets called so that we can store lazy state into memory and copy the
  * current task into the new thread.
-- 
2.14.2.920.gcf0c67979c-goog