x86/irq/64: Adjust the per CPU irq stack pointer by 8

The per CPU hardirq_stack_ptr contains the pointer to the irq stack in the
form that it is ready to be assigned to [ER]SP so that the first push ends
up on the top entry of the stack.

But the stack switching on 64 bit has the following rules:

    1) Store the current stack pointer (RSP) in the top most stack entry
       to allow the unwinder to link back to the previous stack

    2) Set RSP to the top most stack entry

    3) Invoke functions on the irq stack

    4) Pop RSP from the top most stack entry (stored in #1) so it's back
       to the original stack.

That requires all stack switching code to decrement the stored pointer by 8
in order to be able to store the current RSP and then set RSP to that
location. That's a pointless exercise.

Do the -8 adjustment right when storing the pointer and make the data type
a void pointer to avoid confusion vs. the struct irq_stack data type which
is on 64bit only used to declare the backing store. Move the definition
next to the inuse flag so they likely end up in the same cache
line. Sticking them into a struct to enforce it is a seperate change.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20210210002512.354260928@linutronix.de

3 files changed, 21 insertions, 9 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 845c8a46cf7b..c5e23f351f67 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1739,7 +1739,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
 	&init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 
-DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
+DEFINE_PER_CPU(void *, hardirq_stack_ptr);
 DEFINE_PER_CPU(bool, hardirq_stack_inuse);
 
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 1dd851397bd9..5601b95944fa 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -128,12 +128,21 @@ static __always_inline bool in_exception_stack(unsigned long *stack, struct stac
 
 static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *end   = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
-	unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long));
+	unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
+	unsigned long *begin;
 
 	/*
-	 * This is a software stack, so 'end' can be a valid stack pointer.
-	 * It just means the stack is empty.
+	 * @end points directly to the top most stack entry to avoid a -8
+	 * adjustment in the stack switch hotpath. Adjust it back before
+	 * calculating @begin.
+	 */
+	end++;
+	begin = end - (IRQ_STACK_SIZE / sizeof(long));
+
+	/*
+	 * Due to the switching logic RSP can never be == @end because the
+	 * final operation is 'popq %rsp' which means after that RSP points
+	 * to the original stack and not to @end.
 	 */
 	if (stack < begin || stack >= end)
 		return false;
@@ -143,8 +152,9 @@ static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info
 	info->end	= end;
 
 	/*
-	 * The next stack pointer is the first thing pushed by the entry code
-	 * after switching to the irq stack.
+	 * The next stack pointer is stored at the top of the irq stack
+	 * before switching to the irq stack. Actual stack entries are all
+	 * below that.
 	 */
 	info->next_sp = (unsigned long *)*(end - 1);
 
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 440eed558558..7103f9889930 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -48,7 +48,8 @@ static int map_irq_stack(unsigned int cpu)
 	if (!va)
 		return -ENOMEM;
 
-	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
+	/* Store actual TOS to avoid adjustment in the hotpath */
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #else
@@ -60,7 +61,8 @@ static int map_irq_stack(unsigned int cpu)
 {
 	void *va = per_cpu_ptr(&irq_stack_backing_store, cpu);
 
-	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
+	/* Store actual TOS to avoid adjustment in the hotpath */
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #endif