x86/i386: Make sure stack-protector segment base is cache aligned

The Intel Optimization Reference Guide says:

In Intel Atom microarchitecture, the address generation unit
assumes that the segment base will be 0 by default. Non-zero
segment base will cause load and store operations to experience
a delay.
- If the segment base isn't aligned to a cache line
boundary, the max throughput of memory operations is
reduced to one [e]very 9 cycles.
[...]
Assembly/Compiler Coding Rule 15. (H impact, ML generality)
For Intel Atom processors, use segments with base set to 0
whenever possible; avoid non-zero segment base address that is
not aligned to cache line boundary at all cost.

We can't avoid having a non-zero base for the stack-protector
segment, but we can make it cache-aligned.

Signed-off-by: Jeremy Fitzhardinge <[e-mail]>
Cc: <[e-mail]>
LKML-Reference: <[e-mail]>
Signed-off-by: Ingo Molnar <[e-mail]>

arch/x86/include/asm/processor.h

···
 extern asmlinkage void ignore_sysret(void);
 #else	/* X86_64 */
 #ifdef CONFIG_CC_STACKPROTECTOR
-DECLARE_PER_CPU(unsigned long, stack_canary);
+/*
+ * Make sure stack canary segment base is cached-aligned:
+ *   "For Intel Atom processors, avoid non zero segment base address
+ *    that is not aligned to cache line boundary at all cost."
+ * (Optim Ref Manual Assembly/Compiler Coding Rule 15.)
+ */
+struct stack_canary {
+	char __pad[20];		/* canary at %gs:20 */
+	unsigned long canary;
+};
+DECLARE_PER_CPU(struct stack_canary, stack_canary) ____cacheline_aligned;
 #endif
 #endif	/* X86_64 */
 

arch/x86/include/asm/stackprotector.h

···
 #ifdef CONFIG_X86_64
 	percpu_write(irq_stack_union.stack_canary, canary);
 #else
-	percpu_write(stack_canary, canary);
+	percpu_write(stack_canary.canary, canary);
 #endif
 }
 
 static inline void setup_stack_canary_segment(int cpu)
 {
 #ifdef CONFIG_X86_32
-	unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu) - 20;
+	unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu);
 	struct desc_struct *gdt_table = get_cpu_gdt_table(cpu);
 	struct desc_struct desc;
 

arch/x86/include/asm/system.h

···
 	"movl %P[task_canary](%[next]), %%ebx\n\t"			\
 	"movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
 #define __switch_canary_oparam						\
-	, [stack_canary] "=m" (per_cpu_var(stack_canary))
+	, [stack_canary] "=m" (per_cpu_var(stack_canary.canary))
 #define __switch_canary_iparam						\
 	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
 #else	/* CC_STACKPROTECTOR */

arch/x86/kernel/cpu/common.c

···
 #else	/* CONFIG_X86_64 */
 
 #ifdef CONFIG_CC_STACKPROTECTOR
-DEFINE_PER_CPU(unsigned long, stack_canary);
+DEFINE_PER_CPU(struct stack_canary, stack_canary) ____cacheline_aligned;
 #endif
 
 /* Make sure %fs and %gs are initialized properly in idle threads */

arch/x86/kernel/head_32.S

···
 	jne 1f
 	movl $per_cpu__gdt_page,%eax
 	movl $per_cpu__stack_canary,%ecx
-	subl $20, %ecx
 	movw %cx, 8 * GDT_ENTRY_STACK_CANARY + 2(%eax)
 	shrl $16, %ecx
 	movb %cl, 8 * GDT_ENTRY_STACK_CANARY + 4(%eax)