arm64: Avoid cpus_have_const_cap() for ARM64_HAS_BTI

In system_supports_bti() we use cpus_have_const_cap() to check for
ARM64_HAS_BTI, but this is not necessary and alternative_has_cap_*() or
cpus_have_final_*cap() would be preferable.

For historical reasons, cpus_have_const_cap() is more complicated than
it needs to be. Before cpucaps are finalized, it will perform a bitmap
test of the system_cpucaps bitmap, and once cpucaps are finalized it
will use an alternative branch. This used to be necessary to handle some
race conditions in the window between cpucap detection and the
subsequent patching of alternatives and static branches, where different
branches could be out-of-sync with one another (or w.r.t. alternative
sequences). Now that we use alternative branches instead of static
branches, these are all patched atomically w.r.t. one another, and there
are only a handful of cases that need special care in the window between
cpucap detection and alternative patching.

Due to the above, it would be nice to remove cpus_have_const_cap(), and
migrate callers over to alternative_has_cap_*(), cpus_have_final_cap(),
or cpus_have_cap() depending on when their requirements. This will
remove redundant instructions and improve code generation, and will make
it easier to determine how each callsite will behave before, during, and
after alternative patching.

When CONFIG_ARM64_BTI_KERNEL=y, the ARM64_HAS_BTI cpucap is a strict
boot cpu feature which is detected and patched early on the boot cpu.
All uses guarded by CONFIG_ARM64_BTI_KERNEL happen after the boot CPU
has detected ARM64_HAS_BTI and patched boot alternatives, and hence can
safely use alternative_has_cap_*() or cpus_have_final_boot_cap().

Regardless of CONFIG_ARM64_BTI_KERNEL, all other uses of ARM64_HAS_BTI
happen after system capabilities have been finalized and alternatives
have been patched. Hence these can safely use alternative_has_cap_*) or
cpus_have_final_cap().

This patch splits system_supports_bti() into system_supports_bti() and
system_supports_bti_kernel(), with the former handling where the cpucap
affects userspace functionality, and ther latter handling where the
cpucap affects kernel functionality. The use of cpus_have_const_cap() is
replaced by cpus_have_final_cap() in cpus_have_const_cap, and
cpus_have_final_boot_cap() in system_supports_bti_kernel(). This will
avoid generating code to test the system_cpucaps bitmap and should be
better for all subsequent calls at runtime. The use of
cpus_have_final_cap() and cpus_have_final_boot_cap() will make it easier
to spot if code is chaanged such that these run before the ARM64_HAS_BTI
cpucap is guaranteed to have been finalized.

Signed-off-by: Mark Rutland <[email protected]>
Reviewed-by: Mark Brown <[email protected]>
Cc: Ard Biesheuvel <[email protected]>
Cc: Suzuki K Poulose <[email protected]>
Cc: Will Deacon <[email protected]>
Signed-off-by: Catalin Marinas <[email protected]>

Author: mrutland-arm

arch/arm64/include/asm/cpufeature.h

@@ -837,7 +837,13 @@ static inline bool system_has_prio_mask_debugging(void)
 
 static inline bool system_supports_bti(void)
 {
-	return cpus_have_const_cap(ARM64_BTI);
+	return cpus_have_final_cap(ARM64_BTI);
+}
+
+static inline bool system_supports_bti_kernel(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) &&
+		cpus_have_final_boot_cap(ARM64_BTI);
 }
 
 static inline bool system_supports_tlb_range(void)

arch/arm64/include/asm/pgtable-prot.h

@@ -75,11 +75,7 @@ extern bool arm64_use_ng_mappings;
  * If we have userspace only BTI we don't want to mark kernel pages
  * guarded even if the system does support BTI.
  */
-#ifdef CONFIG_ARM64_BTI_KERNEL
-#define PTE_MAYBE_GP		(system_supports_bti() ? PTE_GP : 0)
-#else
-#define PTE_MAYBE_GP		0
-#endif
+#define PTE_MAYBE_GP		(system_supports_bti_kernel() ? PTE_GP : 0)
 
 #define PAGE_KERNEL		__pgprot(_PAGE_KERNEL)
 #define PAGE_KERNEL_RO		__pgprot(_PAGE_KERNEL_RO)

arch/arm64/kernel/efi.c

@@ -113,8 +113,7 @@ static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
 		pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
 	if (md->attribute & EFI_MEMORY_XP)
 		pte = set_pte_bit(pte, __pgprot(PTE_PXN));
-	else if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) &&
-		 system_supports_bti() && spd->has_bti)
+	else if (system_supports_bti_kernel() && spd->has_bti)
 		pte = set_pte_bit(pte, __pgprot(PTE_GP));
 	set_pte(ptep, pte);
 	return 0;

arch/arm64/kernel/vdso.c

@@ -212,7 +212,7 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	if (IS_ERR(ret))
 		goto up_fail;
 
-	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti())
+	if (system_supports_bti_kernel())
 		gp_flags = VM_ARM64_BTI;
 
 	vdso_base += VVAR_NR_PAGES * PAGE_SIZE;

arch/arm64/kvm/hyp/pgtable.c

@@ -401,7 +401,7 @@ static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep)
 		if (device)
 			return -EINVAL;
 
-		if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti())
+		if (system_supports_bti_kernel())
 			attr |= KVM_PTE_LEAF_ATTR_HI_S1_GP;
 	} else {
 		attr |= KVM_PTE_LEAF_ATTR_HI_S1_XN;