Re: [PATCH] x86/sev: Fully map the #VC exception stacks

[Borislav Petkov]

It doesn't get any more straight-forward than this.

We can ifdef around the ESTACKS_MEMBERS VC and VC2 arrays so that those
things do get allocated only on a CONFIG_AMD_MEM_ENCRYPT kernel so that
we don't waste 4 pages per CPU on machines which don't do SEV but meh.

Thoughts?

---
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index 3d52b094850a..13a3e8510c33 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -21,9 +21,9 @@
 	char	MCE_stack_guard[guardsize];			\
 	char	MCE_stack[EXCEPTION_STKSZ];			\
 	char	VC_stack_guard[guardsize];			\
-	char	VC_stack[optional_stack_size];			\
+	char	VC_stack[EXCEPTION_STKSZ];			\
 	char	VC2_stack_guard[guardsize];			\
-	char	VC2_stack[optional_stack_size];			\
+	char	VC2_stack[EXCEPTION_STKSZ];			\
 	char	IST_top_guard[guardsize];			\
 
 /* The exception stacks' physical storage. No guard pages required */
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index a6895e440bc3..88401675dabb 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -46,16 +46,6 @@ static struct ghcb __initdata *boot_ghcb;
 struct sev_es_runtime_data {
 	struct ghcb ghcb_page;
 
-	/* Physical storage for the per-CPU IST stack of the #VC handler */
-	char ist_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE);
-
-	/*
-	 * Physical storage for the per-CPU fall-back stack of the #VC handler.
-	 * The fall-back stack is used when it is not safe to switch back to the
-	 * interrupted stack in the #VC entry code.
-	 */
-	char fallback_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE);
-
 	/*
 	 * Reserve one page per CPU as backup storage for the unencrypted GHCB.
 	 * It is needed when an NMI happens while the #VC handler uses the real
@@ -99,27 +89,6 @@ DEFINE_STATIC_KEY_FALSE(sev_es_enable_key);
 /* Needed in vc_early_forward_exception */
 void do_early_exception(struct pt_regs *regs, int trapnr);
 
-static void __init setup_vc_stacks(int cpu)
-{
-	struct sev_es_runtime_data *data;
-	struct cpu_entry_area *cea;
-	unsigned long vaddr;
-	phys_addr_t pa;
-
-	data = per_cpu(runtime_data, cpu);
-	cea  = get_cpu_entry_area(cpu);
-
-	/* Map #VC IST stack */
-	vaddr = CEA_ESTACK_BOT(&cea->estacks, VC);
-	pa    = __pa(data->ist_stack);
-	cea_set_pte((void *)vaddr, pa, PAGE_KERNEL);
-
-	/* Map VC fall-back stack */
-	vaddr = CEA_ESTACK_BOT(&cea->estacks, VC2);
-	pa    = __pa(data->fallback_stack);
-	cea_set_pte((void *)vaddr, pa, PAGE_KERNEL);
-}
-
 static __always_inline bool on_vc_stack(struct pt_regs *regs)
 {
 	unsigned long sp = regs->sp;
@@ -787,7 +756,6 @@ void __init sev_es_init_vc_handling(void)
 	for_each_possible_cpu(cpu) {
 		alloc_runtime_data(cpu);
 		init_ghcb(cpu);
-		setup_vc_stacks(cpu);
 	}
 
 	sev_es_setup_play_dead();
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index f5e1e60c9095..82d062414f19 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -110,6 +110,13 @@ static void __init percpu_setup_exception_stacks(unsigned int cpu)
 	cea_map_stack(NMI);
 	cea_map_stack(DB);
 	cea_map_stack(MCE);
+
+	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
+		if (sev_es_active()) {
+			cea_map_stack(VC);
+			cea_map_stack(VC2);
+		}
+	}
 }
 #else
 static inline void percpu_setup_exception_stacks(unsigned int cpu)

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette