From: Marc Zyngier <marc.zyngier@arm.com>
To: kvm@vger.kernel.org, kvmarm@lists.cs.columbia.edu,
linux-arm-kernel@lists.infradead.org
Cc: Catalin Marinas <catalin.marinas@arm.com>
Subject: [PATCH v4 1/6] arm64: KVM: Add support for Stage-2 control of memory types and cacheability
Date: Mon, 2 Jul 2018 16:02:45 +0100 [thread overview]
Message-ID: <20180702150250.16550-2-marc.zyngier@arm.com> (raw)
In-Reply-To: <20180702150250.16550-1-marc.zyngier@arm.com>
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>
---
arch/arm64/include/asm/cpucaps.h | 3 ++-
arch/arm64/include/asm/kvm_arm.h | 1 +
arch/arm64/include/asm/kvm_emulate.h | 2 ++
arch/arm64/include/asm/kvm_mmu.h | 27 +++++++++++++++++++++------
arch/arm64/include/asm/memory.h | 7 +++++++
arch/arm64/include/asm/pgtable-prot.h | 14 ++++++++++++--
arch/arm64/include/asm/sysreg.h | 1 +
arch/arm64/kernel/cpufeature.c | 20 ++++++++++++++++++++
virt/kvm/arm/mmu.c | 4 ++++
9 files changed, 70 insertions(+), 9 deletions(-)
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 8a699c708fc9..ed84d6536830 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -49,7 +49,8 @@
#define ARM64_HAS_CACHE_DIC 28
#define ARM64_HW_DBM 29
#define ARM64_SSBD 30
+#define ARM64_HAS_STAGE2_FWB 31
-#define ARM64_NCAPS 31
+#define ARM64_NCAPS 32
#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 6dd285e979c9..aa45df752a16 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -23,6 +23,7 @@
#include <asm/types.h>
/* Hyp Configuration Register (HCR) bits */
+#define HCR_FWB (UL(1) << 46)
#define HCR_TEA (UL(1) << 37)
#define HCR_TERR (UL(1) << 36)
#define HCR_TLOR (UL(1) << 35)
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 1dab3a984608..dd98fdf33d99 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -63,6 +63,8 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
/* trap error record accesses */
vcpu->arch.hcr_el2 |= HCR_TERR;
}
+ if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
+ vcpu->arch.hcr_el2 |= HCR_FWB;
if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
vcpu->arch.hcr_el2 &= ~HCR_RW;
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)
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 49d99214f43c..b96442960aea 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -155,6 +155,13 @@
#define MT_S2_NORMAL 0xf
#define MT_S2_DEVICE_nGnRE 0x1
+/*
+ * Memory types for Stage-2 translation when ID_AA64MMFR2_EL1.FWB is 0001
+ * Stage-2 enforces Normal-WB and Device-nGnRE
+ */
+#define MT_S2_FWB_NORMAL 6
+#define MT_S2_FWB_DEVICE_nGnRE 1
+
#ifdef CONFIG_ARM64_4K_PAGES
#define IOREMAP_MAX_ORDER (PUD_SHIFT)
#else
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 108ecad7acc5..c66c3047400e 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -67,8 +67,18 @@
#define PAGE_HYP_RO __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
-#define PAGE_S2 __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY | PTE_S2_XN)
-#define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN)
+#define PAGE_S2_MEMATTR(attr) \
+ ({ \
+ u64 __val; \
+ if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) \
+ __val = PTE_S2_MEMATTR(MT_S2_FWB_ ## attr); \
+ else \
+ __val = PTE_S2_MEMATTR(MT_S2_ ## attr); \
+ __val; \
+ })
+
+#define PAGE_S2 __pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(NORMAL) | PTE_S2_RDONLY | PTE_S2_XN)
+#define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN)
#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index a8f84812c6e8..98af0b37fb31 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -576,6 +576,7 @@
#define ID_AA64MMFR1_VMIDBITS_16 2
/* id_aa64mmfr2 */
+#define ID_AA64MMFR2_FWB_SHIFT 40
#define ID_AA64MMFR2_AT_SHIFT 32
#define ID_AA64MMFR2_LVA_SHIFT 16
#define ID_AA64MMFR2_IESB_SHIFT 12
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index f24892a40d2c..d58d1f0abe16 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -192,6 +192,7 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
};
static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_FWB_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_AT_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
@@ -1026,6 +1027,14 @@ static void cpu_copy_el2regs(const struct arm64_cpu_capabilities *__unused)
}
#endif
+static void cpu_has_fwb(const struct arm64_cpu_capabilities *__unused)
+{
+ u64 val = read_sysreg_s(SYS_CLIDR_EL1);
+
+ /* Check that CLIDR_EL1.LOU{U,IS} are both 0 */
+ WARN_ON(val & (7 << 27 | 7 << 21));
+}
+
static const struct arm64_cpu_capabilities arm64_features[] = {
{
.desc = "GIC system register CPU interface",
@@ -1182,6 +1191,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.type = ARM64_CPUCAP_SYSTEM_FEATURE,
.matches = has_cache_dic,
},
+ {
+ .desc = "Stage-2 Force Write-Back",
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .capability = ARM64_HAS_STAGE2_FWB,
+ .sys_reg = SYS_ID_AA64MMFR2_EL1,
+ .sign = FTR_UNSIGNED,
+ .field_pos = ID_AA64MMFR2_FWB_SHIFT,
+ .min_field_value = 1,
+ .matches = has_cpuid_feature,
+ .cpu_enable = cpu_has_fwb,
+ },
#ifdef CONFIG_ARM64_HW_AFDBM
{
/*
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 1d90d79706bd..ea7314296ad1 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -196,6 +196,10 @@ static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr
* This is why right after unmapping a page/section and invalidating
* the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure
* the IO subsystem will never hit in the cache.
+ *
+ * This is all avoided on systems that have ARM64_HAS_STAGE2_FWB, as
+ * we then fully enforce cacheability of RAM, no matter what the guest
+ * does.
*/
static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
phys_addr_t addr, phys_addr_t end)
--
2.17.1
WARNING: multiple messages have this Message-ID (diff)
From: marc.zyngier@arm.com (Marc Zyngier)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v4 1/6] arm64: KVM: Add support for Stage-2 control of memory types and cacheability
Date: Mon, 2 Jul 2018 16:02:45 +0100 [thread overview]
Message-ID: <20180702150250.16550-2-marc.zyngier@arm.com> (raw)
In-Reply-To: <20180702150250.16550-1-marc.zyngier@arm.com>
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>
---
arch/arm64/include/asm/cpucaps.h | 3 ++-
arch/arm64/include/asm/kvm_arm.h | 1 +
arch/arm64/include/asm/kvm_emulate.h | 2 ++
arch/arm64/include/asm/kvm_mmu.h | 27 +++++++++++++++++++++------
arch/arm64/include/asm/memory.h | 7 +++++++
arch/arm64/include/asm/pgtable-prot.h | 14 ++++++++++++--
arch/arm64/include/asm/sysreg.h | 1 +
arch/arm64/kernel/cpufeature.c | 20 ++++++++++++++++++++
virt/kvm/arm/mmu.c | 4 ++++
9 files changed, 70 insertions(+), 9 deletions(-)
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 8a699c708fc9..ed84d6536830 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -49,7 +49,8 @@
#define ARM64_HAS_CACHE_DIC 28
#define ARM64_HW_DBM 29
#define ARM64_SSBD 30
+#define ARM64_HAS_STAGE2_FWB 31
-#define ARM64_NCAPS 31
+#define ARM64_NCAPS 32
#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 6dd285e979c9..aa45df752a16 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -23,6 +23,7 @@
#include <asm/types.h>
/* Hyp Configuration Register (HCR) bits */
+#define HCR_FWB (UL(1) << 46)
#define HCR_TEA (UL(1) << 37)
#define HCR_TERR (UL(1) << 36)
#define HCR_TLOR (UL(1) << 35)
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 1dab3a984608..dd98fdf33d99 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -63,6 +63,8 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
/* trap error record accesses */
vcpu->arch.hcr_el2 |= HCR_TERR;
}
+ if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
+ vcpu->arch.hcr_el2 |= HCR_FWB;
if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
vcpu->arch.hcr_el2 &= ~HCR_RW;
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)
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 49d99214f43c..b96442960aea 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -155,6 +155,13 @@
#define MT_S2_NORMAL 0xf
#define MT_S2_DEVICE_nGnRE 0x1
+/*
+ * Memory types for Stage-2 translation when ID_AA64MMFR2_EL1.FWB is 0001
+ * Stage-2 enforces Normal-WB and Device-nGnRE
+ */
+#define MT_S2_FWB_NORMAL 6
+#define MT_S2_FWB_DEVICE_nGnRE 1
+
#ifdef CONFIG_ARM64_4K_PAGES
#define IOREMAP_MAX_ORDER (PUD_SHIFT)
#else
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 108ecad7acc5..c66c3047400e 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -67,8 +67,18 @@
#define PAGE_HYP_RO __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
-#define PAGE_S2 __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY | PTE_S2_XN)
-#define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN)
+#define PAGE_S2_MEMATTR(attr) \
+ ({ \
+ u64 __val; \
+ if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) \
+ __val = PTE_S2_MEMATTR(MT_S2_FWB_ ## attr); \
+ else \
+ __val = PTE_S2_MEMATTR(MT_S2_ ## attr); \
+ __val; \
+ })
+
+#define PAGE_S2 __pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(NORMAL) | PTE_S2_RDONLY | PTE_S2_XN)
+#define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN)
#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index a8f84812c6e8..98af0b37fb31 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -576,6 +576,7 @@
#define ID_AA64MMFR1_VMIDBITS_16 2
/* id_aa64mmfr2 */
+#define ID_AA64MMFR2_FWB_SHIFT 40
#define ID_AA64MMFR2_AT_SHIFT 32
#define ID_AA64MMFR2_LVA_SHIFT 16
#define ID_AA64MMFR2_IESB_SHIFT 12
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index f24892a40d2c..d58d1f0abe16 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -192,6 +192,7 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
};
static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_FWB_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_AT_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
@@ -1026,6 +1027,14 @@ static void cpu_copy_el2regs(const struct arm64_cpu_capabilities *__unused)
}
#endif
+static void cpu_has_fwb(const struct arm64_cpu_capabilities *__unused)
+{
+ u64 val = read_sysreg_s(SYS_CLIDR_EL1);
+
+ /* Check that CLIDR_EL1.LOU{U,IS} are both 0 */
+ WARN_ON(val & (7 << 27 | 7 << 21));
+}
+
static const struct arm64_cpu_capabilities arm64_features[] = {
{
.desc = "GIC system register CPU interface",
@@ -1182,6 +1191,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.type = ARM64_CPUCAP_SYSTEM_FEATURE,
.matches = has_cache_dic,
},
+ {
+ .desc = "Stage-2 Force Write-Back",
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .capability = ARM64_HAS_STAGE2_FWB,
+ .sys_reg = SYS_ID_AA64MMFR2_EL1,
+ .sign = FTR_UNSIGNED,
+ .field_pos = ID_AA64MMFR2_FWB_SHIFT,
+ .min_field_value = 1,
+ .matches = has_cpuid_feature,
+ .cpu_enable = cpu_has_fwb,
+ },
#ifdef CONFIG_ARM64_HW_AFDBM
{
/*
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 1d90d79706bd..ea7314296ad1 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -196,6 +196,10 @@ static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr
* This is why right after unmapping a page/section and invalidating
* the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure
* the IO subsystem will never hit in the cache.
+ *
+ * This is all avoided on systems that have ARM64_HAS_STAGE2_FWB, as
+ * we then fully enforce cacheability of RAM, no matter what the guest
+ * does.
*/
static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
phys_addr_t addr, phys_addr_t end)
--
2.17.1
next prev parent reply other threads:[~2018-07-02 15:02 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-02 15:02 [PATCH v4 0/6] KVM/arm64: Cache maintenance relaxations Marc Zyngier
2018-07-02 15:02 ` Marc Zyngier
2018-07-02 15:02 ` Marc Zyngier [this message]
2018-07-02 15:02 ` [PATCH v4 1/6] arm64: KVM: Add support for Stage-2 control of memory types and cacheability Marc Zyngier
2018-07-02 15:02 ` [PATCH v4 2/6] arm64: KVM: Handle Set/Way CMOs as NOPs if FWB is present Marc Zyngier
2018-07-02 15:02 ` Marc Zyngier
2018-07-02 15:02 ` [PATCH v4 3/6] arm64: KVM: Avoid marking pages as XN in Stage-2 if CTR_EL0.DIC is set Marc Zyngier
2018-07-02 15:02 ` Marc Zyngier
2018-07-02 15:02 ` [PATCH v4 4/6] KVM: arm/arm64: Consolidate page-table accessors Marc Zyngier
2018-07-02 15:02 ` Marc Zyngier
2018-07-02 15:02 ` [PATCH v4 5/6] KVM: arm/arm64: Stop using the kernel's {pmd, pud, pgd}_populate helpers Marc Zyngier
2018-07-02 15:02 ` Marc Zyngier
2018-07-02 15:02 ` [PATCH v4 6/6] KVM: arm/arm64: Remove unnecessary CMOs when creating HYP page tables Marc Zyngier
2018-07-02 15:02 ` Marc Zyngier
2018-07-09 10:52 ` [PATCH v4 0/6] KVM/arm64: Cache maintenance relaxations Marc Zyngier
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180702150250.16550-2-marc.zyngier@arm.com \
--to=marc.zyngier@arm.com \
--cc=catalin.marinas@arm.com \
--cc=kvm@vger.kernel.org \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=linux-arm-kernel@lists.infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.