arm64: KVM: Add support for Stage-2 control of memory types and cacheability

Up to ARMv8.3, the combinaison of Stage-1 and Stage-2 attributes
results in the strongest attribute of the two stages.  This means
that the hypervisor has to perform quite a lot of cache maintenance
just in case the guest has some non-cacheable mappings around.

ARMv8.4 solves this problem by offering a different mode (FWB) where
Stage-2 has total control over the memory attribute (this is limited
to systems where both I/O and instruction fetches are coherent with
the dcache). This is achieved by having a different set of memory
attributes in the page tables, and a new bit set in HCR_EL2.

On such a system, we can then safely sidestep any form of dcache
management.

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>

1 files changed, 21 insertions, 6 deletions

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index fb9a7127bb75..bac9f016736b 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -267,6 +267,15 @@ static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
 {
 	void *va = page_address(pfn_to_page(pfn));
 
+	/*
+	 * With FWB, we ensure that the guest always accesses memory using
+	 * cacheable attributes, and we don't have to clean to PoC when
+	 * faulting in pages. Furthermore, FWB implies IDC, so cleaning to
+	 * PoU is not required either in this case.
+	 */
+	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
+		return;
+
 	kvm_flush_dcache_to_poc(va, size);
 }
 
@@ -287,20 +296,26 @@ static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn,
 
 static inline void __kvm_flush_dcache_pte(pte_t pte)
 {
-	struct page *page = pte_page(pte);
-	kvm_flush_dcache_to_poc(page_address(page), PAGE_SIZE);
+	if (!cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
+		struct page *page = pte_page(pte);
+		kvm_flush_dcache_to_poc(page_address(page), PAGE_SIZE);
+	}
 }
 
 static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
 {
-	struct page *page = pmd_page(pmd);
-	kvm_flush_dcache_to_poc(page_address(page), PMD_SIZE);
+	if (!cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
+		struct page *page = pmd_page(pmd);
+		kvm_flush_dcache_to_poc(page_address(page), PMD_SIZE);
+	}
 }
 
 static inline void __kvm_flush_dcache_pud(pud_t pud)
 {
-	struct page *page = pud_page(pud);
-	kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE);
+	if (!cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
+		struct page *page = pud_page(pud);
+		kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE);
+	}
 }
 
 #define kvm_virt_to_phys(x)		__pa_symbol(x)