summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm64/include/asm/cpu.h1
-rw-r--r--arch/arm64/include/asm/cpufeature.h1
-rw-r--r--arch/arm64/include/asm/kvm_arm.h4
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h3
-rw-r--r--arch/arm64/include/asm/kvm_host.h99
-rw-r--r--arch/arm64/include/asm/kvm_hyp.h2
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h46
-rw-r--r--arch/arm64/include/asm/kvm_nested.h1
-rw-r--r--arch/arm64/include/asm/kvm_pgtable.h2
-rw-r--r--arch/arm64/include/asm/memory.h2
-rw-r--r--arch/arm64/include/asm/sysreg.h5
-rw-r--r--arch/arm64/kernel/cpufeature.c105
-rw-r--r--arch/arm64/kernel/cpuinfo.c1
-rw-r--r--arch/arm64/kernel/head.S23
-rw-r--r--arch/arm64/kvm/Kconfig12
-rw-r--r--arch/arm64/kvm/arch_timer.c2
-rw-r--r--arch/arm64/kvm/arm.c14
-rw-r--r--arch/arm64/kvm/check-res-bits.h125
-rw-r--r--arch/arm64/kvm/debug.c3
-rw-r--r--arch/arm64/kvm/emulate-nested.c231
-rw-r--r--arch/arm64/kvm/fpsimd.c2
-rw-r--r--arch/arm64/kvm/guest.c7
-rw-r--r--arch/arm64/kvm/hyp/aarch32.c4
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/switch.h130
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h24
-rw-r--r--arch/arm64/kvm/hyp/nvhe/debug-sr.c12
-rw-r--r--arch/arm64/kvm/hyp/nvhe/host.S2
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mm.c4
-rw-r--r--arch/arm64/kvm/hyp/pgtable.c24
-rw-r--r--arch/arm64/kvm/hyp/vhe/sysreg-sr.c2
-rw-r--r--arch/arm64/kvm/inject_fault.c2
-rw-r--r--arch/arm64/kvm/mmu.c16
-rw-r--r--arch/arm64/kvm/nested.c274
-rw-r--r--arch/arm64/kvm/pmu-emul.c15
-rw-r--r--arch/arm64/kvm/sys_regs.c266
-rw-r--r--arch/arm64/kvm/sys_regs.h2
-rw-r--r--arch/arm64/kvm/vgic/vgic-debug.c2
-rw-r--r--arch/arm64/kvm/vgic/vgic-init.c10
-rw-r--r--arch/arm64/kvm/vgic/vgic-its.c63
-rw-r--r--arch/arm64/kvm/vgic/vgic-v3.c3
-rw-r--r--arch/arm64/kvm/vgic/vgic.c62
-rw-r--r--arch/arm64/kvm/vgic/vgic.h15
-rw-r--r--arch/arm64/tools/cpucaps1
-rw-r--r--arch/arm64/tools/sysreg45
-rw-r--r--arch/powerpc/kvm/powerpc.c3
-rw-r--r--arch/x86/kvm/debugfs.c3
46 files changed, 1346 insertions, 329 deletions
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index b1e43f56ee46..6c13fd47e170 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -56,6 +56,7 @@ struct cpuinfo_arm64 {
u64 reg_id_aa64mmfr1;
u64 reg_id_aa64mmfr2;
u64 reg_id_aa64mmfr3;
+ u64 reg_id_aa64mmfr4;
u64 reg_id_aa64pfr0;
u64 reg_id_aa64pfr1;
u64 reg_id_aa64zfr0;
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index bd8d4ca81a48..d7c6988188d9 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -363,6 +363,7 @@ struct arm64_cpu_capabilities {
u8 field_pos;
u8 field_width;
u8 min_field_value;
+ u8 max_field_value;
u8 hwcap_type;
bool sign;
unsigned long hwcap;
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 3c6f8ba1e479..a1769e415d72 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -102,9 +102,7 @@
#define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
-#define HCRX_GUEST_FLAGS \
- (HCRX_EL2_SMPME | HCRX_EL2_TCR2En | \
- (cpus_have_final_cap(ARM64_HAS_MOPS) ? (HCRX_EL2_MSCEn | HCRX_EL2_MCE2) : 0))
+#define HCRX_GUEST_FLAGS (HCRX_EL2_SMPME | HCRX_EL2_TCR2En)
#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En)
/* TCR_EL2 Registers bits */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index b804fe832184..debc3753d2ef 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -209,7 +209,8 @@ static inline bool vcpu_is_el2(const struct kvm_vcpu *vcpu)
static inline bool __vcpu_el2_e2h_is_set(const struct kvm_cpu_context *ctxt)
{
- return ctxt_sys_reg(ctxt, HCR_EL2) & HCR_E2H;
+ return (!cpus_have_final_cap(ARM64_HAS_HCR_NV1) ||
+ (ctxt_sys_reg(ctxt, HCR_EL2) & HCR_E2H));
}
static inline bool vcpu_el2_e2h_is_set(const struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 21c57b812569..6883963bbc3a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -238,9 +238,32 @@ static inline u16 kvm_mpidr_index(struct kvm_mpidr_data *data, u64 mpidr)
return index;
}
+struct kvm_sysreg_masks;
+
+enum fgt_group_id {
+ __NO_FGT_GROUP__,
+ HFGxTR_GROUP,
+ HDFGRTR_GROUP,
+ HDFGWTR_GROUP = HDFGRTR_GROUP,
+ HFGITR_GROUP,
+ HAFGRTR_GROUP,
+
+ /* Must be last */
+ __NR_FGT_GROUP_IDS__
+};
+
struct kvm_arch {
struct kvm_s2_mmu mmu;
+ /*
+ * Fine-Grained UNDEF, mimicking the FGT layout defined by the
+ * architecture. We track them globally, as we present the
+ * same feature-set to all vcpus.
+ *
+ * Index 0 is currently spare.
+ */
+ u64 fgu[__NR_FGT_GROUP_IDS__];
+
/* Interrupt controller */
struct vgic_dist vgic;
@@ -274,6 +297,8 @@ struct kvm_arch {
#define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE 6
/* Initial ID reg values loaded */
#define KVM_ARCH_FLAG_ID_REGS_INITIALIZED 7
+ /* Fine-Grained UNDEF initialised */
+#define KVM_ARCH_FLAG_FGU_INITIALIZED 8
unsigned long flags;
/* VM-wide vCPU feature set */
@@ -294,6 +319,9 @@ struct kvm_arch {
/* PMCR_EL0.N value for the guest */
u8 pmcr_n;
+ /* Iterator for idreg debugfs */
+ u8 idreg_debugfs_iter;
+
/* Hypercall features firmware registers' descriptor */
struct kvm_smccc_features smccc_feat;
struct maple_tree smccc_filter;
@@ -312,6 +340,9 @@ struct kvm_arch {
#define KVM_ARM_ID_REG_NUM (IDREG_IDX(sys_reg(3, 0, 0, 7, 7)) + 1)
u64 id_regs[KVM_ARM_ID_REG_NUM];
+ /* Masks for VNCR-baked sysregs */
+ struct kvm_sysreg_masks *sysreg_masks;
+
/*
* For an untrusted host VM, 'pkvm.handle' is used to lookup
* the associated pKVM instance in the hypervisor.
@@ -474,6 +505,13 @@ enum vcpu_sysreg {
NR_SYS_REGS /* Nothing after this line! */
};
+struct kvm_sysreg_masks {
+ struct {
+ u64 res0;
+ u64 res1;
+ } mask[NR_SYS_REGS - __VNCR_START__];
+};
+
struct kvm_cpu_context {
struct user_pt_regs regs; /* sp = sp_el0 */
@@ -549,6 +587,7 @@ struct kvm_vcpu_arch {
/* Values of trap registers for the guest. */
u64 hcr_el2;
+ u64 hcrx_el2;
u64 mdcr_el2;
u64 cptr_el2;
@@ -868,7 +907,15 @@ static inline u64 *__ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
#define ctxt_sys_reg(c,r) (*__ctxt_sys_reg(c,r))
-#define __vcpu_sys_reg(v,r) (ctxt_sys_reg(&(v)->arch.ctxt, (r)))
+u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *, enum vcpu_sysreg);
+#define __vcpu_sys_reg(v,r) \
+ (*({ \
+ const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt; \
+ u64 *__r = __ctxt_sys_reg(ctxt, (r)); \
+ if (vcpu_has_nv((v)) && (r) >= __VNCR_START__) \
+ *__r = kvm_vcpu_sanitise_vncr_reg((v), (r)); \
+ __r; \
+ }))
u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
@@ -1055,14 +1102,20 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu);
int kvm_handle_sys_reg(struct kvm_vcpu *vcpu);
int kvm_handle_cp10_id(struct kvm_vcpu *vcpu);
+void kvm_sys_regs_create_debugfs(struct kvm *kvm);
void kvm_reset_sys_regs(struct kvm_vcpu *vcpu);
int __init kvm_sys_reg_table_init(void);
+struct sys_reg_desc;
+int __init populate_sysreg_config(const struct sys_reg_desc *sr,
+ unsigned int idx);
int __init populate_nv_trap_config(void);
bool lock_all_vcpus(struct kvm *kvm);
void unlock_all_vcpus(struct kvm *kvm);
+void kvm_init_sysreg(struct kvm_vcpu *);
+
/* MMIO helpers */
void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
@@ -1233,4 +1286,48 @@ static inline void kvm_hyp_reserve(void) { }
void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu);
bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu);
+#define __expand_field_sign_unsigned(id, fld, val) \
+ ((u64)SYS_FIELD_VALUE(id, fld, val))
+
+#define __expand_field_sign_signed(id, fld, val) \
+ ({ \
+ u64 __val = SYS_FIELD_VALUE(id, fld, val); \
+ sign_extend64(__val, id##_##fld##_WIDTH - 1); \
+ })
+
+#define expand_field_sign(id, fld, val) \
+ (id##_##fld##_SIGNED ? \
+ __expand_field_sign_signed(id, fld, val) : \
+ __expand_field_sign_unsigned(id, fld, val))
+
+#define get_idreg_field_unsigned(kvm, id, fld) \
+ ({ \
+ u64 __val = IDREG((kvm), SYS_##id); \
+ FIELD_GET(id##_##fld##_MASK, __val); \
+ })
+
+#define get_idreg_field_signed(kvm, id, fld) \
+ ({ \
+ u64 __val = get_idreg_field_unsigned(kvm, id, fld); \
+ sign_extend64(__val, id##_##fld##_WIDTH - 1); \
+ })
+
+#define get_idreg_field_enum(kvm, id, fld) \
+ get_idreg_field_unsigned(kvm, id, fld)
+
+#define get_idreg_field(kvm, id, fld) \
+ (id##_##fld##_SIGNED ? \
+ get_idreg_field_signed(kvm, id, fld) : \
+ get_idreg_field_unsigned(kvm, id, fld))
+
+#define kvm_has_feat(kvm, id, fld, limit) \
+ (get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, limit))
+
+#define kvm_has_feat_enum(kvm, id, fld, val) \
+ (get_idreg_field_unsigned((kvm), id, fld) == __expand_field_sign_unsigned(id, fld, val))
+
+#define kvm_has_feat_range(kvm, id, fld, min, max) \
+ (get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, min) && \
+ get_idreg_field((kvm), id, fld) <= expand_field_sign(id, fld, max))
+
#endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 145ce73fc16c..3e2a1ac0c9bb 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -70,7 +70,7 @@ DECLARE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
/*
* Without an __arch_swab32(), we fall back to ___constant_swab32(), but the
* static inline can allow the compiler to out-of-line this. KVM always wants
- * the macro version as its always inlined.
+ * the macro version as it's always inlined.
*/
#define __kvm_swab32(x) ___constant_swab32(x)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index e3e793d0ec30..d5e48d870461 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -54,27 +54,6 @@
#include <asm/alternative.h>
/*
- * Convert a kernel VA into a HYP VA.
- * reg: VA to be converted.
- *
- * The actual code generation takes place in kvm_update_va_mask, and
- * the instructions below are only there to reserve the space and
- * perform the register allocation (kvm_update_va_mask uses the
- * specific registers encoded in the instructions).
- */
-.macro kern_hyp_va reg
-#ifndef __KVM_VHE_HYPERVISOR__
-alternative_cb ARM64_ALWAYS_SYSTEM, kvm_update_va_mask
- and \reg, \reg, #1 /* mask with va_mask */
- ror \reg, \reg, #1 /* rotate to the first tag bit */
- add \reg, \reg, #0 /* insert the low 12 bits of the tag */
- add \reg, \reg, #0, lsl 12 /* insert the top 12 bits of the tag */
- ror \reg, \reg, #63 /* rotate back */
-alternative_cb_end
-#endif
-.endm
-
-/*
* Convert a hypervisor VA to a PA
* reg: hypervisor address to be converted in place
* tmp: temporary register
@@ -127,14 +106,29 @@ void kvm_apply_hyp_relocations(void);
#define __hyp_pa(x) (((phys_addr_t)(x)) + hyp_physvirt_offset)
+/*
+ * Convert a kernel VA into a HYP VA.
+ *
+ * Can be called from hyp or non-hyp context.
+ *
+ * The actual code generation takes place in kvm_update_va_mask(), and
+ * the instructions below are only there to reserve the space and
+ * perform the register allocation (kvm_update_va_mask() uses the
+ * specific registers encoded in the instructions).
+ */
static __always_inline unsigned long __kern_hyp_va(unsigned long v)
{
+/*
+ * This #ifndef is an optimisation for when this is called from VHE hyp
+ * context. When called from a VHE non-hyp context, kvm_update_va_mask() will
+ * replace the instructions with `nop`s.
+ */
#ifndef __KVM_VHE_HYPERVISOR__
- asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n"
- "ror %0, %0, #1\n"
- "add %0, %0, #0\n"
- "add %0, %0, #0, lsl 12\n"
- "ror %0, %0, #63\n",
+ asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n" /* mask with va_mask */
+ "ror %0, %0, #1\n" /* rotate to the first tag bit */
+ "add %0, %0, #0\n" /* insert the low 12 bits of the tag */
+ "add %0, %0, #0, lsl 12\n" /* insert the top 12 bits of the tag */
+ "ror %0, %0, #63\n", /* rotate back */
ARM64_ALWAYS_SYSTEM,
kvm_update_va_mask)
: "+r" (v));
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 4882905357f4..c77d795556e1 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -60,7 +60,6 @@ static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0)
return ttbr0 & ~GENMASK_ULL(63, 48);
}
-extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
int kvm_init_nv_sysregs(struct kvm *kvm);
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index cfdf40f734b1..19278dfe7978 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -197,6 +197,7 @@ enum kvm_pgtable_stage2_flags {
* @KVM_PGTABLE_PROT_W: Write permission.
* @KVM_PGTABLE_PROT_R: Read permission.
* @KVM_PGTABLE_PROT_DEVICE: Device attributes.
+ * @KVM_PGTABLE_PROT_NORMAL_NC: Normal noncacheable attributes.
* @KVM_PGTABLE_PROT_SW0: Software bit 0.
* @KVM_PGTABLE_PROT_SW1: Software bit 1.
* @KVM_PGTABLE_PROT_SW2: Software bit 2.
@@ -208,6 +209,7 @@ enum kvm_pgtable_prot {
KVM_PGTABLE_PROT_R = BIT(2),
KVM_PGTABLE_PROT_DEVICE = BIT(3),
+ KVM_PGTABLE_PROT_NORMAL_NC = BIT(4),
KVM_PGTABLE_PROT_SW0 = BIT(55),
KVM_PGTABLE_PROT_SW1 = BIT(56),
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index d82305ab420f..449ca2ff1df6 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -173,6 +173,7 @@
* Memory types for Stage-2 translation
*/
#define MT_S2_NORMAL 0xf
+#define MT_S2_NORMAL_NC 0x5
#define MT_S2_DEVICE_nGnRE 0x1
/*
@@ -180,6 +181,7 @@
* Stage-2 enforces Normal-WB and Device-nGnRE
*/
#define MT_S2_FWB_NORMAL 6
+#define MT_S2_FWB_NORMAL_NC 5
#define MT_S2_FWB_DEVICE_nGnRE 1
#ifdef CONFIG_ARM64_4K_PAGES
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index c3b19b376c86..9e8999592f3a 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1181,6 +1181,8 @@
par; \
})
+#define SYS_FIELD_VALUE(reg, field, val) reg##_##field##_##val
+
#define SYS_FIELD_GET(reg, field, val) \
FIELD_GET(reg##_##field##_MASK, val)
@@ -1188,7 +1190,8 @@
FIELD_PREP(reg##_##field##_MASK, val)
#define SYS_FIELD_PREP_ENUM(reg, field, val) \
- FIELD_PREP(reg##_##field##_MASK, reg##_##field##_##val)
+ FIELD_PREP(reg##_##field##_MASK, \
+ SYS_FIELD_VALUE(reg, field, val))
#endif
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 8d1a634a403e..f309fd542c20 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -140,12 +140,42 @@ void dump_cpu_features(void)
pr_emerg("0x%*pb\n", ARM64_NCAPS, &system_cpucaps);
}
+#define __ARM64_MAX_POSITIVE(reg, field) \
+ ((reg##_##field##_SIGNED ? \
+ BIT(reg##_##field##_WIDTH - 1) : \
+ BIT(reg##_##field##_WIDTH)) - 1)
+
+#define __ARM64_MIN_NEGATIVE(reg, field) BIT(reg##_##field##_WIDTH - 1)
+
+#define __ARM64_CPUID_FIELDS(reg, field, min_value, max_value) \
+ .sys_reg = SYS_##reg, \
+ .field_pos = reg##_##field##_SHIFT, \
+ .field_width = reg##_##field##_WIDTH, \
+ .sign = reg##_##field##_SIGNED, \
+ .min_field_value = min_value, \
+ .max_field_value = max_value,
+
+/*
+ * ARM64_CPUID_FIELDS() encodes a field with a range from min_value to
+ * an implicit maximum that depends on the sign-ess of the field.
+ *
+ * An unsigned field will be capped at all ones, while a signed field
+ * will be limited to the positive half only.
+ */
#define ARM64_CPUID_FIELDS(reg, field, min_value) \
- .sys_reg = SYS_##reg, \
- .field_pos = reg##_##field##_SHIFT, \
- .field_width = reg##_##field##_WIDTH, \
- .sign = reg##_##field##_SIGNED, \
- .min_field_value = reg##_##field##_##min_value,
+ __ARM64_CPUID_FIELDS(reg, field, \
+ SYS_FIELD_VALUE(reg, field, min_value), \
+ __ARM64_MAX_POSITIVE(reg, field))
+
+/*
+ * ARM64_CPUID_FIELDS_NEG() encodes a field with a range from an
+ * implicit minimal value to max_value. This should be used when
+ * matching a non-implemented property.
+ */
+#define ARM64_CPUID_FIELDS_NEG(reg, field, max_value) \
+ __ARM64_CPUID_FIELDS(reg, field, \
+ __ARM64_MIN_NEGATIVE(reg, field), \
+ SYS_FIELD_VALUE(reg, field, max_value))
#define __ARM64_FTR_BITS(SIGNED, VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
{ \
@@ -407,6 +437,11 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr3[] = {
ARM64_FTR_END,
};
+static const struct arm64_ftr_bits ftr_id_aa64mmfr4[] = {
+ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR4_EL1_E2H0_SHIFT, 4, 0),
+ ARM64_FTR_END,
+};
+
static const struct arm64_ftr_bits ftr_ctr[] = {
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_EL0_DIC_SHIFT, 1, 1),
@@ -724,6 +759,7 @@ static const struct __ftr_reg_entry {
&id_aa64mmfr1_override),
ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2),
ARM64_FTR_REG(SYS_ID_AA64MMFR3_EL1, ftr_id_aa64mmfr3),
+ ARM64_FTR_REG(SYS_ID_AA64MMFR4_EL1, ftr_id_aa64mmfr4),
/* Op1 = 1, CRn = 0, CRm = 0 */
ARM64_FTR_REG(SYS_GMID_EL1, ftr_gmid),
@@ -919,7 +955,8 @@ static void init_cpu_ftr_reg(u32 sys_reg, u64 new)
pr_warn("%s[%d:%d]: %s to %llx\n",
reg->name,
ftrp->shift + ftrp->width - 1,
- ftrp->shift, str, tmp);
+ ftrp->shift, str,
+ tmp & (BIT(ftrp->width) - 1));
} else if ((ftr_mask & reg->override->val) == ftr_mask) {
reg->override->val &= ~ftr_mask;
pr_warn("%s[%d:%d]: impossible override, ignored\n",
@@ -1047,6 +1084,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
init_cpu_ftr_reg(SYS_ID_AA64MMFR1_EL1, info->reg_id_aa64mmfr1);
init_cpu_ftr_reg(SYS_ID_AA64MMFR2_EL1, info->reg_id_aa64mmfr2);
init_cpu_ftr_reg(SYS_ID_AA64MMFR3_EL1, info->reg_id_aa64mmfr3);
+ init_cpu_ftr_reg(SYS_ID_AA64MMFR4_EL1, info->reg_id_aa64mmfr4);
init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0);
init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1);
init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0);
@@ -1418,6 +1456,7 @@ u64 __read_sysreg_by_encoding(u32 sys_id)
read_sysreg_case(SYS_ID_AA64MMFR1_EL1);
read_sysreg_case(SYS_ID_AA64MMFR2_EL1);
read_sysreg_case(SYS_ID_AA64MMFR3_EL1);
+ read_sysreg_case(SYS_ID_AA64MMFR4_EL1);
read_sysreg_case(SYS_ID_AA64ISAR0_EL1);
read_sysreg_case(SYS_ID_AA64ISAR1_EL1);
read_sysreg_case(SYS_ID_AA64ISAR2_EL1);
@@ -1451,11 +1490,28 @@ has_always(const struct arm64_cpu_capabilities *entry, int scope)
static bool
feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry)
{
- int val = cpuid_feature_extract_field_width(reg, entry->field_pos,
- entry->field_width,
- entry->sign);
+ int val, min, max;
+ u64 tmp;
+
+ val = cpuid_feature_extract_field_width(reg, entry->field_pos,
+ entry->field_width,
+ entry->sign);
+
+ tmp = entry->min_field_value;
+ tmp <<= entry->field_pos;
- return val >= entry->min_field_value;
+ min = cpuid_feature_extract_field_width(tmp, entry->field_pos,
+ entry->field_width,
+ entry->sign);
+
+ tmp = entry->max_field_value;
+ tmp <<= entry->field_pos;
+
+ max = cpuid_feature_extract_field_width(tmp, entry->field_pos,
+ entry->field_width,
+ entry->sign);
+
+ return val >= min && val <= max;
}
static u64
@@ -1739,6 +1795,28 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
return !meltdown_safe;
}
+static bool has_nv1(const struct arm64_cpu_capabilities *entry, int scope)
+{
+ /*
+ * Although the Apple M2 family appears to support NV1, the
+ * PTW barfs on the nVHE EL2 S1 page table format. Pretend
+ * that it doesn't support NV1 at all.
+ */
+ static const struct midr_range nv1_ni_list[] = {
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD),
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE),
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO),
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO),
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX),
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX),
+ {}
+ };
+
+ return (__system_matches_cap(ARM64_HAS_NESTED_VIRT) &&
+ !(has_cpuid_feature(entry, scope) ||
+ is_midr_in_range_list(read_cpuid_id(), nv1_ni_list)));
+}
+
#if defined(ID_AA64MMFR0_EL1_TGRAN_LPA2) && defined(ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2)
static bool has_lpa2_at_stage1(u64 mmfr0)
{
@@ -2739,6 +2817,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.type = ARM64_CPUCAP_SYSTEM_FEATURE,
.matches = has_lpa2,
},
+ {
+ .desc = "NV1",
+ .capability = ARM64_HAS_HCR_NV1,
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .matches = has_nv1,
+ ARM64_CPUID_FIELDS_NEG(ID_AA64MMFR4_EL1, E2H0, NI_NV1)
+ },
{},
};
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 47043c0d95ec..7ca3fbd200f0 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -447,6 +447,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
info->reg_id_aa64mmfr1 = read_cpuid(ID_AA64MMFR1_EL1);
info->reg_id_aa64mmfr2 = read_cpuid(ID_AA64MMFR2_EL1);
info->reg_id_aa64mmfr3 = read_cpuid(ID_AA64MMFR3_EL1);
+ info->reg_id_aa64mmfr4 = read_cpuid(ID_AA64MMFR4_EL1);
info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1);
info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1);
info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1);
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index cab7f91949d8..5bdafbcff009 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -584,25 +584,32 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
mov_q x1, INIT_SCTLR_EL1_MMU_OFF
/*
- * Fruity CPUs seem to have HCR_EL2.E2H set to RES1,
- * making it impossible to start in nVHE mode. Is that
- * compliant with the architecture? Absolutely not!
+ * Compliant CPUs advertise their VHE-onlyness with
+ * ID_AA64MMFR4_EL1.E2H0 < 0. HCR_EL2.E2H can be
+ * RES1 in that case.
+ *
+ * Fruity CPUs seem to have HCR_EL2.E2H set to RES1, but
+ * don't advertise it (they predate this relaxation).
*/
+ mrs_s x0, SYS_ID_AA64MMFR4_EL1
+ ubfx x0, x0, #ID_AA64MMFR4_EL1_E2H0_SHIFT, #ID_AA64MMFR4_EL1_E2H0_WIDTH
+ tbnz x0, #(ID_AA64MMFR4_EL1_E2H0_SHIFT + ID_AA64MMFR4_EL1_E2H0_WIDTH - 1), 1f
+
mrs x0, hcr_el2
and x0, x0, #HCR_E2H
- cbz x0, 1f
-
+ cbz x0, 2f
+1:
/* Set a sane SCTLR_EL1, the VHE way */
pre_disable_mmu_workaround
msr_s SYS_SCTLR_EL12, x1
mov x2, #BOOT_CPU_FLAG_E2H
- b 2f
+ b 3f
-1:
+2:
pre_disable_mmu_workaround
msr sctlr_el1, x1
mov x2, xzr
-2:
+3:
__init_el2_nvhe_prepare_eret
mov w0, #BOOT_CPU_MODE_EL2
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 4b25fa4b167c..937f15b7d8c3 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -37,7 +37,6 @@ menuconfig KVM
select HAVE_KVM_VCPU_RUN_PID_CHANGE
select SCHED_INFO
select GUEST_PERF_EVENTS if PERF_EVENTS
- select XARRAY_MULTI
help
Support hosting virtualized guest machines.
@@ -66,4 +65,15 @@ config PROTECTED_NVHE_STACKTRACE
If unsure, or not using protected nVHE (pKVM), say N.
+config KVM_ARM64_RES_BITS_PARANOIA
+ bool "Build-time check of RES0/RES1 bits"
+ depends on KVM
+ default n
+ help
+ Say Y here to validate that KVM's knowledge of most system
+ registers' RES0/RES1 bits matches when the rest of the kernel
+ defines. Expect the build to fail badly if you enable this.
+
+ Just say N.
+
endif # VIRTUALIZATION
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 9dec8c419bf4..879982b1cc73 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -745,7 +745,7 @@ static void kvm_timer_vcpu_load_nested_switch(struct kvm_vcpu *vcpu,
WARN_ON_ONCE(ret);
/*
- * The virtual offset behaviour is "interresting", as it
+ * The virtual offset behaviour is "interesting", as it
* always applies when HCR_EL2.E2H==0, but only when
* accessed from EL1 when HCR_EL2.E2H==1. So make sure we
* track E2H when putting the HV timer in "direct" mode.
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index a25265aca432..3dee5490eea9 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -190,6 +190,10 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
}
+void kvm_arch_create_vm_debugfs(struct kvm *kvm)
+{
+ kvm_sys_regs_create_debugfs(kvm);
+}
/**
* kvm_arch_destroy_vm - destroy the VM data structure
@@ -206,6 +210,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
pkvm_destroy_hyp_vm(kvm);
kfree(kvm->arch.mpidr_data);
+ kfree(kvm->arch.sysreg_masks);
kvm_destroy_vcpus(kvm);
kvm_unshare_hyp(kvm, kvm + 1);
@@ -674,6 +679,12 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
return ret;
}
+ /*
+ * This needs to happen after NV has imposed its own restrictions on
+ * the feature set
+ */
+ kvm_init_sysreg(vcpu);
+
ret = kvm_timer_enable(vcpu);
if (ret)
return ret;
@@ -2591,7 +2602,8 @@ static __init int kvm_arm_init(void)
} else if (in_hyp_mode) {
kvm_info("VHE mode initialized successfully\n");
} else {
- kvm_info("Hyp mode initialized successfully\n");
+ char mode = cpus_have_final_cap(ARM64_KVM_HVHE) ? 'h' : 'n';
+ kvm_info("Hyp mode (%cVHE) initialized successfully\n", mode);
}
/*
diff --git a/arch/arm64/kvm/check-res-bits.h b/arch/arm64/kvm/check-res-bits.h
new file mode 100644
index 000000000000..2d98e60efc3c
--- /dev/null
+++ b/arch/arm64/kvm/check-res-bits.h
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024 - Google LLC
+ * Author: Marc Zyngier <maz@kernel.org>
+ */
+
+#include <asm/sysreg-defs.h>
+
+/*
+ * WARNING WARNING WARNING WARNING WARNING WARNING WARNING WARNING
+ *
+ * If any of these BUILD_BUG_ON() fails, that's because some bits that
+ * were reserved have gained some other meaning, and KVM needs to know
+ * about those.
+ *
+ * In such case, do *NOT* blindly change the assertion so that it
+ * passes, but also teach the rest of the code about the actual
+ * change.
+ *
+ * WARNING WARNING WARNING WARNING WARNING WARNING WARNING WARNING
+ */
+static inline void check_res_bits(void)
+{
+#ifdef CONFIG_KVM_ARM64_RES_BITS_PARANOIA
+
+ BUILD_BUG_ON(OSDTRRX_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(MDCCINT_EL1_RES0 != (GENMASK_ULL(63, 31) | GENMASK_ULL(28, 0)));
+ BUILD_BUG_ON(MDSCR_EL1_RES0 != (GENMASK_ULL(63, 36) | GENMASK_ULL(28, 28) | GENMASK_ULL(25, 24) | GENMASK_ULL(20, 20) | GENMASK_ULL(18, 16) | GENMASK_ULL(11, 7) | GENMASK_ULL(5, 1)));
+ BUILD_BUG_ON(OSDTRTX_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(OSECCR_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(OSLAR_EL1_RES0 != (GENMASK_ULL(63, 1)));
+ BUILD_BUG_ON(ID_PFR0_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(ID_PFR1_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(ID_DFR0_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(ID_AFR0_EL1_RES0 != (GENMASK_ULL(63, 16)));
+ BUILD_BUG_ON(ID_MMFR0_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(ID_MMFR1_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(ID_MMFR2_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(ID_MMFR3_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(ID_ISAR0_EL1_RES0 != (GENMASK_ULL(63, 28)));
+ BUILD_BUG_ON(ID_ISAR1_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(ID_ISAR2_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(ID_ISAR3_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(ID_ISAR4_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(ID_ISAR5_EL1_RES0 != (GENMASK_ULL(63, 32) | GENMASK_ULL(23, 20)));
+ BUILD_BUG_ON(ID_ISAR6_EL1_RES0 != (GENMASK_ULL(63, 28)));
+ BUILD_BUG_ON(ID_MMFR4_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(MVFR0_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(MVFR1_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(MVFR2_EL1_RES0 != (GENMASK_ULL(63, 8)));
+ BUILD_BUG_ON(ID_PFR2_EL1_RES0 != (GENMASK_ULL(63, 12)));
+ BUILD_BUG_ON(ID_DFR1_EL1_RES0 != (GENMASK_ULL(63, 8)));
+ BUILD_BUG_ON(ID_MMFR5_EL1_RES0 != (GENMASK_ULL(63, 8)));
+ BUILD_BUG_ON(ID_AA64PFR1_EL1_RES0 != (GENMASK_ULL(23, 20)));
+ BUILD_BUG_ON(ID_AA64PFR2_EL1_RES0 != (GENMASK_ULL(63, 36) | GENMASK_ULL(31, 12)));
+ BUILD_BUG_ON(ID_AA64ZFR0_EL1_RES0 != (GENMASK_ULL(63, 60) | GENMASK_ULL(51, 48) | GENMASK_ULL(39, 36) | GENMASK_ULL(31, 28) | GENMASK_ULL(15, 8)));
+ BUILD_BUG_ON(ID_AA64SMFR0_EL1_RES0 != (GENMASK_ULL(62, 61) | GENMASK_ULL(51, 49) | GENMASK_ULL(31, 31) | GENMASK_ULL(27, 0)));
+ BUILD_BUG_ON(ID_AA64FPFR0_EL1_RES0 != (GENMASK_ULL(63, 32) | GENMASK_ULL(27, 2)));
+ BUILD_BUG_ON(ID_AA64DFR0_EL1_RES0 != (GENMASK_ULL(27, 24) | GENMASK_ULL(19, 16)));
+ BUILD_BUG_ON(ID_AA64DFR1_EL1_RES0 != (GENMASK_ULL(63, 0)));
+ BUILD_BUG_ON(ID_AA64AFR0_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(ID_AA64AFR1_EL1_RES0 != (GENMASK_ULL(63, 0)));
+ BUILD_BUG_ON(ID_AA64ISAR0_EL1_RES0 != (GENMASK_ULL(3, 0)));
+ BUILD_BUG_ON(ID_AA64ISAR2_EL1_RES0 != (GENMASK_ULL(47, 44)));
+ BUILD_BUG_ON(ID_AA64ISAR3_EL1_RES0 != (GENMASK_ULL(63, 16)));
+ BUILD_BUG_ON(ID_AA64MMFR0_EL1_RES0 != (GENMASK_ULL(55, 48)));
+ BUILD_BUG_ON(ID_AA64MMFR2_EL1_RES0 != (GENMASK_ULL(47, 44)));
+ BUILD_BUG_ON(ID_AA64MMFR3_EL1_RES0 != (GENMASK_ULL(51, 48)));
+ BUILD_BUG_ON(ID_AA64MMFR4_EL1_RES0 != (GENMASK_ULL(63, 40) | GENMASK_ULL(35, 28) | GENMASK_ULL(3, 0)));
+ BUILD_BUG_ON(SCTLR_EL1_RES0 != (GENMASK_ULL(17, 17)));
+ BUILD_BUG_ON(CPACR_ELx_RES0 != (GENMASK_ULL(63, 30) | GENMASK_ULL(27, 26) | GENMASK_ULL(23, 22) | GENMASK_ULL(19, 18) | GENMASK_ULL(15, 0)));
+ BUILD_BUG_ON(SMPRI_EL1_RES0 != (GENMASK_ULL(63, 4)));
+ BUILD_BUG_ON(ZCR_ELx_RES0 != (GENMASK_ULL(63, 9)));
+ BUILD_BUG_ON(SMCR_ELx_RES0 != (GENMASK_ULL(63, 32) | GENMASK_ULL(29, 9)));
+ BUILD_BUG_ON(GCSCR_ELx_RES0 != (GENMASK_ULL(63, 10) | GENMASK_ULL(7, 7) | GENMASK_ULL(4, 1)));
+ BUILD_BUG_ON(GCSPR_ELx_RES0 != (GENMASK_ULL(2, 0)));
+ BUILD_BUG_ON(GCSCRE0_EL1_RES0 != (GENMASK_ULL(63, 11) | GENMASK_ULL(7, 6) | GENMASK_ULL(4, 1)));
+ BUILD_BUG_ON(ALLINT_RES0 != (GENMASK_ULL(63, 14) | GENMASK_ULL(12, 0)));
+ BUILD_BUG_ON(PMSCR_EL1_RES0 != (GENMASK_ULL(63, 8) | GENMASK_ULL(2, 2)));
+ BUILD_BUG_ON(PMSICR_EL1_RES0 != (GENMASK_ULL(55, 32)));
+ BUILD_BUG_ON(PMSIRR_EL1_RES0 != (GENMASK_ULL(63, 32) | GENMASK_ULL(7, 1)));
+ BUILD_BUG_ON(PMSFCR_EL1_RES0 != (GENMASK_ULL(63, 19) | GENMASK_ULL(15, 4)));
+ BUILD_BUG_ON(PMSLATFR_EL1_RES0 != (GENMASK_ULL(63, 16)));
+ BUILD_BUG_ON(PMSIDR_EL1_RES0 != (GENMASK_ULL(63, 25) | GENMASK_ULL(7, 7)));
+ BUILD_BUG_ON(PMBLIMITR_EL1_RES0 != (GENMASK_ULL(11, 6) | GENMASK_ULL(4, 3)));
+ BUILD_BUG_ON(PMBSR_EL1_RES0 != (GENMASK_ULL(63, 32) | GENMASK_ULL(25, 20)));
+ BUILD_BUG_ON(PMBIDR_EL1_RES0 != (GENMASK_ULL(63, 12) | GENMASK_ULL(7, 6)));
+ BUILD_BUG_ON(CONTEXTIDR_ELx_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(CCSIDR_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(CLIDR_EL1_RES0 != (GENMASK_ULL(63, 47)));
+ BUILD_BUG_ON(CCSIDR2_EL1_RES0 != (GENMASK_ULL(63, 24)));
+ BUILD_BUG_ON(GMID_EL1_RES0 != (GENMASK_ULL(63, 4)));
+ BUILD_BUG_ON(SMIDR_EL1_RES0 != (GENMASK_ULL(63, 32) | GENMASK_ULL(14, 12)));
+ BUILD_BUG_ON(CSSELR_EL1_RES0 != (GENMASK_ULL(63, 5)));
+ BUILD_BUG_ON(CTR_EL0_RES0 != (GENMASK_ULL(63, 38) | GENMASK_ULL(30, 30) | GENMASK_ULL(13, 4)));
+ BUILD_BUG_ON(CTR_EL0_RES1 != (GENMASK_ULL(31, 31)));
+ BUILD_BUG_ON(DCZID_EL0_RES0 != (GENMASK_ULL(63, 5)));
+ BUILD_BUG_ON(SVCR_RES0 != (GENMASK_ULL(63, 2)));
+ BUILD_BUG_ON(FPMR_RES0 != (GENMASK_ULL(63, 38) | GENMASK_ULL(23, 23) | GENMASK_ULL(13, 9)));
+ BUILD_BUG_ON(HFGxTR_EL2_RES0 != (GENMASK_ULL(51, 51)));
+ BUILD_BUG_ON(HFGITR_EL2_RES0 != (GENMASK_ULL(63, 63) | GENMASK_ULL(61, 61)));
+ BUILD_BUG_ON(HDFGRTR_EL2_RES0 != (GENMASK_ULL(49, 49) | GENMASK_ULL(42, 42) | GENMASK_ULL(39, 38) | GENMASK_ULL(21, 20) | GENMASK_ULL(8, 8)));
+ BUILD_BUG_ON(HDFGWTR_EL2_RES0 != (GENMASK_ULL(63, 63) | GENMASK_ULL(59, 58) | GENMASK_ULL(51, 51) | GENMASK_ULL(47, 47) | GENMASK_ULL(43, 43) | GENMASK_ULL(40, 38) | GENMASK_ULL(34, 34) | GENMASK_ULL(30, 30) | GENMASK_ULL(22, 22) | GENMASK_ULL(9, 9) | GENMASK_ULL(6, 6)));
+ BUILD_BUG_ON(HAFGRTR_EL2_RES0 != (GENMASK_ULL(63, 50) | GENMASK_ULL(16, 5)));
+ BUILD_BUG_ON(HCRX_EL2_RES0 != (GENMASK_ULL(63, 25) | GENMASK_ULL(13, 12)));
+ BUILD_BUG_ON(DACR32_EL2_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(PMSCR_EL2_RES0 != (GENMASK_ULL(63, 8) | GENMASK_ULL(2, 2)));
+ BUILD_BUG_ON(TCR2_EL1x_RES0 != (GENMASK_ULL(63, 16) | GENMASK_ULL(13, 12) | GENMASK_ULL(9, 6)));
+ BUILD_BUG_ON(TCR2_EL2_RES0 != (GENMASK_ULL(63, 16)));
+ BUILD_BUG_ON(LORSA_EL1_RES0 != (GENMASK_ULL(63, 52) | GENMASK_ULL(15, 1)));
+ BUILD_BUG_ON(LOREA_EL1_RES0 != (GENMASK_ULL(63, 52) | GENMASK_ULL(15, 0)));
+ BUILD_BUG_ON(LORN_EL1_RES0 != (GENMASK_ULL(63, 8)));
+ BUILD_BUG_ON(LORC_EL1_RES0 != (GENMASK_ULL(63, 10) | GENMASK_ULL(1, 1)));
+ BUILD_BUG_ON(LORID_EL1_RES0 != (GENMASK_ULL(63, 24) | GENMASK_ULL(15, 8)));
+ BUILD_BUG_ON(ISR_EL1_RES0 != (GENMASK_ULL(63, 11) | GENMASK_ULL(5, 0)));
+ BUILD_BUG_ON(ICC_NMIAR1_EL1_RES0 != (GENMASK_ULL(63, 24)));
+ BUILD_BUG_ON(TRBLIMITR_EL1_RES0 != (GENMASK_ULL(11, 7)));
+ BUILD_BUG_ON(TRBBASER_EL1_RES0 != (GENMASK_ULL(11, 0)));
+ BUILD_BUG_ON(TRBSR_EL1_RES0 != (GENMASK_ULL(63, 56) | GENMASK_ULL(25, 24) | GENMASK_ULL(19, 19) | GENMASK_ULL(16, 16)));
+ BUILD_BUG_ON(TRBMAR_EL1_RES0 != (GENMASK_ULL(63, 12)));
+ BUILD_BUG_ON(TRBTRG_EL1_RES0 != (GENMASK_ULL(63, 32)));
+ BUILD_BUG_ON(TRBIDR_EL1_RES0 != (GENMASK_ULL(63, 12) | GENMASK_ULL(7, 6)));
+
+#endif
+}
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index 8725291cb00a..ce8886122ed3 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -23,7 +23,7 @@
static DEFINE_PER_CPU(u64, mdcr_el2);
-/**
+/*
* save/restore_guest_debug_regs
*
* For some debug operations we need to tweak some guest registers. As
@@ -143,6 +143,7 @@ void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu)
/**
* kvm_arm_reset_debug_ptr - reset the debug ptr to point to the vcpu state
+ * @vcpu: the vcpu pointer
*/
void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 431fd429932d..4697ba41b3a9 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -427,12 +427,14 @@ static const complex_condition_check ccc[] = {
* [19:14] bit number in the FGT register (6 bits)
* [20] trap polarity (1 bit)
* [25:21] FG filter (5 bits)
- * [62:26] Unused (37 bits)
+ * [35:26] Main SysReg table index (10 bits)
+ * [62:36] Unused (27 bits)
* [63] RES0 - Must be zero, as lost on insertion in the xarray
*/
#define TC_CGT_BITS 10
#define TC_FGT_BITS 4
#define TC_FGF_BITS 5
+#define TC_SRI_BITS 10
union trap_config {
u64 val;
@@ -442,7 +444,8 @@ union trap_config {
unsigned long bit:6; /* Bit number */
unsigned long pol:1; /* Polarity */
unsigned long fgf:TC_FGF_BITS; /* Fine Grained Filter */
- unsigned long unused:37; /* Unused, should be zero */
+ unsigned long sri:TC_SRI_BITS; /* SysReg Index */
+ unsigned long unused:27; /* Unused, should be zero */
unsigned long mbz:1; /* Must Be Zero */
};
};
@@ -1006,18 +1009,6 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
static DEFINE_XARRAY(sr_forward_xa);
-enum fgt_group_id {
- __NO_FGT_GROUP__,
- HFGxTR_GROUP,
- HDFGRTR_GROUP,
- HDFGWTR_GROUP,
- HFGITR_GROUP,
- HAFGRTR_GROUP,
-
- /* Must be last */
- __NR_FGT_GROUP_IDS__
-};
-
enum fg_filter_id {
__NO_FGF__,
HCRX_FGTnXS,
@@ -1757,6 +1748,28 @@ static __init void print_nv_trap_error(const struct encoding_to_trap_config *tc,
err);
}
+static u32 encoding_next(u32 encoding)
+{
+ u8 op0, op1, crn, crm, op2;
+
+ op0 = sys_reg_Op0(encoding);
+ op1 = sys_reg_Op1(encoding);
+ crn = sys_reg_CRn(encoding);
+ crm = sys_reg_CRm(encoding);
+ op2 = sys_reg_Op2(encoding);
+
+ if (op2 < Op2_mask)
+ return sys_reg(op0, op1, crn, crm, op2 + 1);
+ if (crm < CRm_mask)
+ return sys_reg(op0, op1, crn, crm + 1, 0);
+ if (crn < CRn_mask)
+ return sys_reg(op0, op1, crn + 1, 0, 0);
+ if (op1 < Op1_mask)
+ return sys_reg(op0, op1 + 1, 0, 0, 0);
+
+ return sys_reg(op0 + 1, 0, 0, 0, 0);
+}
+
int __init populate_nv_trap_config(void)
{
int ret = 0;
@@ -1775,23 +1788,18 @@ int __init populate_nv_trap_config(void)
ret = -EINVAL;
}
- if (cgt->encoding != cgt->end) {
- prev = xa_store_range(&sr_forward_xa,
- cgt->encoding, cgt->end,
- xa_mk_value(cgt->tc.val),
- GFP_KERNEL);
- } else {
- prev = xa_store(&sr_forward_xa, cgt->encoding,
+ for (u32 enc = cgt->encoding; enc <= cgt->end; enc = encoding_next(enc)) {
+ prev = xa_store(&sr_forward_xa, enc,
xa_mk_value(cgt->tc.val), GFP_KERNEL);
if (prev && !xa_is_err(prev)) {
ret = -EINVAL;
print_nv_trap_error(cgt, "Duplicate CGT", ret);
}
- }
- if (xa_is_err(prev)) {
- ret = xa_err(prev);
- print_nv_trap_error(cgt, "Failed CGT insertion", ret);
+ if (xa_is_err(prev)) {
+ ret = xa_err(prev);
+ print_nv_trap_error(cgt, "Failed CGT insertion", ret);
+ }
}
}
@@ -1804,6 +1812,7 @@ int __init populate_nv_trap_config(void)
for (int i = 0; i < ARRAY_SIZE(encoding_to_fgt); i++) {
const struct encoding_to_trap_config *fgt = &encoding_to_fgt[i];
union trap_config tc;
+ void *prev;
if (fgt->tc.fgt >= __NR_FGT_GROUP_IDS__) {
ret = -EINVAL;
@@ -1818,8 +1827,13 @@ int __init populate_nv_trap_config(void)
}
tc.val |= fgt->tc.val;
- xa_store(&sr_forward_xa, fgt->encoding,
- xa_mk_value(tc.val), GFP_KERNEL);
+ prev = xa_store(&sr_forward_xa, fgt->encoding,
+ xa_mk_value(tc.val), GFP_KERNEL);
+
+ if (xa_is_err(prev)) {
+ ret = xa_err(prev);
+ print_nv_trap_error(fgt, "Failed FGT insertion", ret);
+ }
}
kvm_info("nv: %ld fine grained trap handlers\n",
@@ -1845,6 +1859,38 @@ check_mcb:
return ret;
}
+int __init populate_sysreg_config(const struct sys_reg_desc *sr,
+ unsigned int idx)
+{
+ union trap_config tc;
+ u32 encoding;
+ void *ret;
+
+ /*
+ * 0 is a valid value for the index, but not for the storage.
+ * We'll store (idx+1), so check against an offset'd limit.
+ */
+ if (idx >= (BIT(TC_SRI_BITS) - 1)) {
+ kvm_err("sysreg %s (%d) out of range\n", sr->name, idx);
+ return -EINVAL;
+ }
+
+ encoding = sys_reg(sr->Op0, sr->Op1, sr->CRn, sr->CRm, sr->Op2);
+ tc = get_trap_config(encoding);
+
+ if (tc.sri) {
+ kvm_err("sysreg %s (%d) duplicate entry (%d)\n",
+ sr->name, idx - 1, tc.sri);
+ return -EINVAL;
+ }
+
+ tc.sri = idx + 1;
+ ret = xa_store(&sr_forward_xa, encoding,
+ xa_mk_value(tc.val), GFP_KERNEL);
+
+ return xa_err(ret);
+}
+
static enum trap_behaviour get_behaviour(struct kvm_vcpu *vcpu,
const struct trap_bits *tb)
{
@@ -1892,20 +1938,64 @@ static enum trap_behaviour compute_trap_behaviour(struct kvm_vcpu *vcpu,
return __compute_trap_behaviour(vcpu, tc.cgt, b);
}
-static bool check_fgt_bit(u64 val, const union trap_config tc)
+static u64 kvm_get_sysreg_res0(struct kvm *kvm, enum vcpu_sysreg sr)
{
- return ((val >> tc.bit) & 1) == tc.pol;
+ struct kvm_sysreg_masks *masks;
+
+ /* Only handle the VNCR-backed regs for now */
+ if (sr < __VNCR_START__)
+ return 0;
+
+ masks = kvm->arch.sysreg_masks;
+
+ return masks->mask[sr - __VNCR_START__].res0;
}
-#define sanitised_sys_reg(vcpu, reg) \
- ({ \
- u64 __val; \
- __val = __vcpu_sys_reg(vcpu, reg); \
- __val &= ~__ ## reg ## _RES0; \
- (__val); \
- })
+static bool check_fgt_bit(struct kvm *kvm, bool is_read,
+ u64 val, const union trap_config tc)
+{
+ enum vcpu_sysreg sr;
+
+ if (tc.pol)
+ return (val & BIT(tc.bit));
+
+ /*
+ * FGTs with negative polarities are an absolute nightmare, as
+ * we need to evaluate the bit in the light of the feature
+ * that defines it. WTF were they thinking?
+ *
+ * So let's check if the bit has been earmarked as RES0, as
+ * this indicates an unimplemented feature.
+ */
+ if (val & BIT(tc.bit))
+ return false;
+
+ switch ((enum fgt_group_id)tc.fgt) {
+ case HFGxTR_GROUP:
+ sr = is_read ? HFGRTR_EL2 : HFGWTR_EL2;
+ break;
+
+ case HDFGRTR_GROUP:
+ sr = is_read ? HDFGRTR_EL2 : HDFGWTR_EL2;
+ break;
+
+ case HAFGRTR_GROUP:
+ sr = HAFGRTR_EL2;
+ break;
+
+ case HFGITR_GROUP:
+ sr = HFGITR_EL2;
+ break;
+
+ default:
+ WARN_ONCE(1, "Unhandled FGT group");
+ return false;
+ }
+
+ return !(kvm_get_sysreg_res0(kvm, sr) & BIT(tc.bit));
+}
-bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
+bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index)
{
union trap_config tc;
enum trap_behaviour b;
@@ -1913,9 +2003,6 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
u32 sysreg;
u64 esr, val;
- if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
- return false;
-
esr = kvm_vcpu_get_esr(vcpu);
sysreg = esr_sys64_to_sysreg(esr);
is_read = (esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ;
@@ -1926,13 +2013,27 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
* A value of 0 for the whole entry means that we know nothing
* for this sysreg, and that it cannot be re-injected into the
* nested hypervisor. In this situation, let's cut it short.
- *
- * Note that ultimately, we could also make use of the xarray
- * to store the index of the sysreg in the local descriptor
- * array, avoiding another search... Hint, hint...
*/
if (!tc.val)
- return false;
+ goto local;
+
+ /*
+ * If a sysreg can be trapped using a FGT, first check whether we
+ * trap for the purpose of forbidding the feature. In that case,
+ * inject an UNDEF.
+ */
+ if (tc.fgt != __NO_FGT_GROUP__ &&
+ (vcpu->kvm->arch.fgu[tc.fgt] & BIT(tc.bit))) {
+ kvm_inject_undefined(vcpu);
+ return true;
+ }
+
+ /*
+ * If we're not nesting, immediately return to the caller, with the
+ * sysreg index, should we have it.
+ */
+ if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
+ goto local;
switch ((enum fgt_group_id)tc.fgt) {
case __NO_FGT_GROUP__:
@@ -1940,25 +2041,24 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
case HFGxTR_GROUP:
if (is_read)
- val = sanitised_sys_reg(vcpu, HFGRTR_EL2);
+ val = __vcpu_sys_reg(vcpu, HFGRTR_EL2);
else
- val = sanitised_sys_reg(vcpu, HFGWTR_EL2);
+ val = __vcpu_sys_reg(vcpu, HFGWTR_EL2);
break;
case HDFGRTR_GROUP:
- case HDFGWTR_GROUP:
if (is_read)
- val = sanitised_sys_reg(vcpu, HDFGRTR_EL2);
+ val = __vcpu_sys_reg(vcpu, HDFGRTR_EL2);
else
- val = sanitised_sys_reg(vcpu, HDFGWTR_EL2);
+ val = __vcpu_sys_reg(vcpu, HDFGWTR_EL2);
break;
case HAFGRTR_GROUP:
- val = sanitised_sys_reg(vcpu, HAFGRTR_EL2);
+ val = __vcpu_sys_reg(vcpu, HAFGRTR_EL2);
break;
case HFGITR_GROUP:
- val = sanitised_sys_reg(vcpu, HFGITR_EL2);
+ val = __vcpu_sys_reg(vcpu, HFGITR_EL2);
switch (tc.fgf) {
u64 tmp;
@@ -1966,7 +2066,7 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
break;
case HCRX_FGTnXS:
- tmp = sanitised_sys_reg(vcpu, HCRX_EL2);
+ tmp = __vcpu_sys_reg(vcpu, HCRX_EL2);
if (tmp & HCRX_EL2_FGTnXS)
tc.fgt = __NO_FGT_GROUP__;
}
@@ -1975,10 +2075,11 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
case __NR_FGT_GROUP_IDS__:
/* Something is really wrong, bail out */
WARN_ONCE(1, "__NR_FGT_GROUP_IDS__");
- return false;
+ goto local;
}
- if (tc.fgt != __NO_FGT_GROUP__ && check_fgt_bit(val, tc))
+ if (tc.fgt != __NO_FGT_GROUP__ && check_fgt_bit(vcpu->kvm, is_read,
+ val, tc))
goto inject;
b = compute_trap_behaviour(vcpu, tc);
@@ -1987,6 +2088,26 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
((b & BEHAVE_FORWARD_WRITE) && !is_read))
goto inject;
+local:
+ if (!tc.sri) {
+ struct sys_reg_params params;
+
+ params = esr_sys64_to_params(esr);
+
+ /*
+ * Check for the IMPDEF range, as per DDI0487 J.a,
+ * D18.3.2 Reserved encodings for IMPLEMENTATION
+ * DEFINED registers.
+ */
+ if (!(params.Op0 == 3 && (params.CRn & 0b1011) == 0b1011))
+ print_sys_reg_msg(&params,
+ "Unsupported guest access at: %lx\n",
+ *vcpu_pc(vcpu));
+ kvm_inject_undefined(vcpu);
+ return true;
+ }
+
+ *sr_index = tc.sri - 1;
return false;
inject:
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 8c1d0d4853df..571cf6eef1e1 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -117,7 +117,7 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
}
/*
- * Called just before entering the guest once we are no longer preemptable
+ * Called just before entering the guest once we are no longer preemptible
* and interrupts are disabled. If we have managed to run anything using
* FP while we were preemptible (such as off the back of an interrupt),
* then neither the host nor the guest own the FP hardware (and it was the
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index aaf1d4939739..6e22e658795a 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -711,6 +711,7 @@ static int copy_sve_reg_indices(const struct kvm_vcpu *vcpu,
/**
* kvm_arm_num_regs - how many registers do we present via KVM_GET_ONE_REG
+ * @vcpu: the vCPU pointer
*
* This is for all registers.
*/
@@ -729,6 +730,8 @@ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
/**
* kvm_arm_copy_reg_indices - get indices of all registers.
+ * @vcpu: the vCPU pointer
+ * @uindices: register list to copy
*
* We do core registers right here, then we append system regs.
*/
@@ -902,8 +905,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
/**
* kvm_arch_vcpu_ioctl_set_guest_debug - set up guest debugging
- * @kvm: pointer to the KVM struct
- * @kvm_guest_debug: the ioctl data buffer
+ * @vcpu: the vCPU pointer
+ * @dbg: the ioctl data buffer
*
* This sets up and enables the VM for guest debugging. Userspace
* passes in a control flag to enable different debug types and
diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c
index f98cbe2626a1..8d9670e6615d 100644
--- a/arch/arm64/kvm/hyp/aarch32.c
+++ b/arch/arm64/kvm/hyp/aarch32.c
@@ -84,7 +84,7 @@ bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
}
/**
- * adjust_itstate - adjust ITSTATE when emulating instructions in IT-block
+ * kvm_adjust_itstate - adjust ITSTATE when emulating instructions in IT-block
* @vcpu: The VCPU pointer
*
* When exceptions occur while instructions are executed in Thumb IF-THEN
@@ -120,7 +120,7 @@ static void kvm_adjust_itstate(struct kvm_vcpu *vcpu)
}
/**
- * kvm_skip_instr - skip a trapped instruction and proceed to the next
+ * kvm_skip_instr32 - skip a trapped instruction and proceed to the next
* @vcpu: The vcpu pointer
*/
void kvm_skip_instr32(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index a038320cdb08..e3fcf8c4d5b4 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -79,14 +79,48 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
clr |= ~hfg & __ ## reg ## _nMASK; \
} while(0)
-#define update_fgt_traps_cs(vcpu, reg, clr, set) \
+#define reg_to_fgt_group_id(reg) \
+ ({ \
+ enum fgt_group_id id; \
+ switch(reg) { \
+ case HFGRTR_EL2: \
+ case HFGWTR_EL2: \
+ id = HFGxTR_GROUP; \
+ break; \
+ case HFGITR_EL2: \
+ id = HFGITR_GROUP; \
+ break; \
+ case HDFGRTR_EL2: \
+ case HDFGWTR_EL2: \
+ id = HDFGRTR_GROUP; \
+ break; \
+ case HAFGRTR_EL2: \
+ id = HAFGRTR_GROUP; \
+ break; \
+ default: \
+ BUILD_BUG_ON(1); \
+ } \
+ \
+ id; \
+ })
+
+#define compute_undef_clr_set(vcpu, kvm, reg, clr, set) \
+ do { \
+ u64 hfg = kvm->arch.fgu[reg_to_fgt_group_id(reg)]; \
+ set |= hfg & __ ## reg ## _MASK; \
+ clr |= hfg & __ ## reg ## _nMASK; \
+ } while(0)
+
+#define update_fgt_traps_cs(hctxt, vcpu, kvm, reg, clr, set) \
do { \
- struct kvm_cpu_context *hctxt = \
- &this_cpu_ptr(&kvm_host_data)->host_ctxt; \
u64 c = 0, s = 0; \
\
ctxt_sys_reg(hctxt, reg) = read_sysreg_s(SYS_ ## reg); \
- compute_clr_set(vcpu, reg, c, s); \
+ if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) \
+ compute_clr_set(vcpu, reg, c, s); \
+ \
+ compute_undef_clr_set(vcpu, kvm, reg, c, s); \
+ \
s |= set; \
c |= clr; \
if (c || s) { \
@@ -97,8 +131,8 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
} \
} while(0)
-#define update_fgt_traps(vcpu, reg) \
- update_fgt_traps_cs(vcpu, reg, 0, 0)
+#define update_fgt_traps(hctxt, vcpu, kvm, reg) \
+ update_fgt_traps_cs(hctxt, vcpu, kvm, reg, 0, 0)
/*
* Validate the fine grain trap masks.
@@ -122,8 +156,7 @@ static inline bool cpu_has_amu(void)
static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
- u64 r_clr = 0, w_clr = 0, r_set = 0, w_set = 0, tmp;
- u64 r_val, w_val;
+ struct kvm *kvm = kern_hyp_va(vcpu->kvm);
CHECK_FGT_MASKS(HFGRTR_EL2);
CHECK_FGT_MASKS(HFGWTR_EL2);
@@ -136,72 +169,45 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
if (!cpus_have_final_cap(ARM64_HAS_FGT))
return;
- ctxt_sys_reg(hctxt, HFGRTR_EL2) = read_sysreg_s(SYS_HFGRTR_EL2);
- ctxt_sys_reg(hctxt, HFGWTR_EL2) = read_sysreg_s(SYS_HFGWTR_EL2);
-
- if (cpus_have_final_cap(ARM64_SME)) {
- tmp = HFGxTR_EL2_nSMPRI_EL1_MASK | HFGxTR_EL2_nTPIDR2_EL0_MASK;
-
- r_clr |= tmp;
- w_clr |= tmp;
- }
-
- /*
- * Trap guest writes to TCR_EL1 to prevent it from enabling HA or HD.
- */
- if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38))
- w_set |= HFGxTR_EL2_TCR_EL1_MASK;
-
- if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
- compute_clr_set(vcpu, HFGRTR_EL2, r_clr, r_set);
- compute_clr_set(vcpu, HFGWTR_EL2, w_clr, w_set);
- }
-
- /* The default to trap everything not handled or supported in KVM. */
- tmp = HFGxTR_EL2_nAMAIR2_EL1 | HFGxTR_EL2_nMAIR2_EL1 | HFGxTR_EL2_nS2POR_EL1 |
- HFGxTR_EL2_nPOR_EL1 | HFGxTR_EL2_nPOR_EL0 | HFGxTR_EL2_nACCDATA_EL1;
-
- r_val = __HFGRTR_EL2_nMASK & ~tmp;
- r_val |= r_set;
- r_val &= ~r_clr;
-
- w_val = __HFGWTR_EL2_nMASK & ~tmp;
- w_val |= w_set;
- w_val &= ~w_clr;
-
- write_sysreg_s(r_val, SYS_HFGRTR_EL2);
- write_sysreg_s(w_val, SYS_HFGWTR_EL2);
-
- if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
- return;
-
- update_fgt_traps(vcpu, HFGITR_EL2);
- update_fgt_traps(vcpu, HDFGRTR_EL2);
- update_fgt_traps(vcpu, HDFGWTR_EL2);
+ update_fgt_traps(hctxt, vcpu, kvm, HFGRTR_EL2);
+ update_fgt_traps_cs(hctxt, vcpu, kvm, HFGWTR_EL2, 0,
+ cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38) ?
+ HFGxTR_EL2_TCR_EL1_MASK : 0);
+ update_fgt_traps(hctxt, vcpu, kvm, HFGITR_EL2);
+ update_fgt_traps(hctxt, vcpu, kvm, HDFGRTR_EL2);
+ update_fgt_traps(hctxt, vcpu, kvm, HDFGWTR_EL2);
if (cpu_has_amu())
- update_fgt_traps(vcpu, HAFGRTR_EL2);
+ update_fgt_traps(hctxt, vcpu, kvm, HAFGRTR_EL2);
}
+#define __deactivate_fgt(htcxt, vcpu, kvm, reg) \
+ do { \
+ if ((vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) || \
+ kvm->arch.fgu[reg_to_fgt_group_id(reg)]) \
+ write_sysreg_s(ctxt_sys_reg(hctxt, reg), \
+ SYS_ ## reg); \
+ } while(0)
+
static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+ struct kvm *kvm = kern_hyp_va(vcpu->kvm);
if (!cpus_have_final_cap(ARM64_HAS_FGT))
return;
- write_sysreg_s(ctxt_sys_reg(hctxt, HFGRTR_EL2), SYS_HFGRTR_EL2);
- write_sysreg_s(ctxt_sys_reg(hctxt, HFGWTR_EL2), SYS_HFGWTR_EL2);
-
- if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
- return;
-
- write_sysreg_s(ctxt_sys_reg(hctxt, HFGITR_EL2), SYS_HFGITR_EL2);
- write_sysreg_s(ctxt_sys_reg(hctxt, HDFGRTR_EL2), SYS_HDFGRTR_EL2);
- write_sysreg_s(ctxt_sys_reg(hctxt, HDFGWTR_EL2), SYS_HDFGWTR_EL2);
+ __deactivate_fgt(hctxt, vcpu, kvm, HFGRTR_EL2);
+ if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38))
+ write_sysreg_s(ctxt_sys_reg(hctxt, HFGWTR_EL2), SYS_HFGWTR_EL2);
+ else
+ __deactivate_fgt(hctxt, vcpu, kvm, HFGWTR_EL2);
+ __deactivate_fgt(hctxt, vcpu, kvm, HFGITR_EL2);
+ __deactivate_fgt(hctxt, vcpu, kvm, HDFGRTR_EL2);
+ __deactivate_fgt(hctxt, vcpu, kvm, HDFGWTR_EL2);
if (cpu_has_amu())
- write_sysreg_s(ctxt_sys_reg(hctxt, HAFGRTR_EL2), SYS_HAFGRTR_EL2);
+ __deactivate_fgt(hctxt, vcpu, kvm, HAFGRTR_EL2);
}
static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
@@ -230,7 +236,7 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
if (cpus_have_final_cap(ARM64_HAS_HCX)) {
- u64 hcrx = HCRX_GUEST_FLAGS;
+ u64 hcrx = vcpu->arch.hcrx_el2;
if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
u64 clr = 0, set = 0;
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index bb6b571ec627..4be6a7fa0070 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -27,16 +27,34 @@ static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
ctxt_sys_reg(ctxt, TPIDRRO_EL0) = read_sysreg(tpidrro_el0);
}
-static inline bool ctxt_has_mte(struct kvm_cpu_context *ctxt)
+static inline struct kvm_vcpu *ctxt_to_vcpu(struct kvm_cpu_context *ctxt)
{
struct kvm_vcpu *vcpu = ctxt->__hyp_running_vcpu;
if (!vcpu)
vcpu = container_of(ctxt, struct kvm_vcpu, arch.ctxt);
+ return vcpu;
+}
+
+static inline bool ctxt_has_mte(struct kvm_cpu_context *ctxt)
+{
+ struct kvm_vcpu *vcpu = ctxt_to_vcpu(ctxt);
+
return kvm_has_mte(kern_hyp_va(vcpu->kvm));
}
+static inline bool ctxt_has_s1pie(struct kvm_cpu_context *ctxt)
+{
+ struct kvm_vcpu *vcpu;
+
+ if (!cpus_have_final_cap(ARM64_HAS_S1PIE))
+ return false;
+
+ vcpu = ctxt_to_vcpu(ctxt);
+ return kvm_has_feat(kern_hyp_va(vcpu->kvm), ID_AA64MMFR3_EL1, S1PIE, IMP);
+}
+
static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
{
ctxt_sys_reg(ctxt, SCTLR_EL1) = read_sysreg_el1(SYS_SCTLR);
@@ -55,7 +73,7 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
ctxt_sys_reg(ctxt, CONTEXTIDR_EL1) = read_sysreg_el1(SYS_CONTEXTIDR);
ctxt_sys_reg(ctxt, AMAIR_EL1) = read_sysreg_el1(SYS_AMAIR);
ctxt_sys_reg(ctxt, CNTKCTL_EL1) = read_sysreg_el1(SYS_CNTKCTL);
- if (cpus_have_final_cap(ARM64_HAS_S1PIE)) {
+ if (ctxt_has_s1pie(ctxt)) {
ctxt_sys_reg(ctxt, PIR_EL1) = read_sysreg_el1(SYS_PIR);
ctxt_sys_reg(ctxt, PIRE0_EL1) = read_sysreg_el1(SYS_PIRE0);
}
@@ -131,7 +149,7 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
write_sysreg_el1(ctxt_sys_reg(ctxt, CONTEXTIDR_EL1), SYS_CONTEXTIDR);
write_sysreg_el1(ctxt_sys_reg(ctxt, AMAIR_EL1), SYS_AMAIR);
write_sysreg_el1(ctxt_sys_reg(ctxt, CNTKCTL_EL1), SYS_CNTKCTL);
- if (cpus_have_final_cap(ARM64_HAS_S1PIE)) {
+ if (ctxt_has_s1pie(ctxt)) {
write_sysreg_el1(ctxt_sys_reg(ctxt, PIR_EL1), SYS_PIR);
write_sysreg_el1(ctxt_sys_reg(ctxt, PIRE0_EL1), SYS_PIRE0);
}
diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
index 4558c02eb352..7746ea507b6f 100644
--- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
@@ -31,8 +31,8 @@ static void __debug_save_spe(u64 *pmscr_el1)
return;
/* Yes; save the control register and disable data generation */
- *pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1);
- write_sysreg_s(0, SYS_PMSCR_EL1);
+ *pmscr_el1 = read_sysreg_el1(SYS_PMSCR);
+ write_sysreg_el1(0, SYS_PMSCR);
isb();
/* Now drain all buffered data to memory */
@@ -48,7 +48,7 @@ static void __debug_restore_spe(u64 pmscr_el1)
isb();
/* Re-enable data generation */
- write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
+ write_sysreg_el1(pmscr_el1, SYS_PMSCR);
}
static void __debug_save_trace(u64 *trfcr_el1)
@@ -63,8 +63,8 @@ static void __debug_save_trace(u64 *trfcr_el1)
* Since access to TRFCR_EL1 is trapped, the guest can't
* modify the filtering set by the host.
*/
- *trfcr_el1 = read_sysreg_s(SYS_TRFCR_EL1);
- write_sysreg_s(0, SYS_TRFCR_EL1);
+ *trfcr_el1 = read_sysreg_el1(SYS_TRFCR);
+ write_sysreg_el1(0, SYS_TRFCR);
isb();
/* Drain the trace buffer to memory */
tsb_csync();
@@ -76,7 +76,7 @@ static void __debug_restore_trace(u64 trfcr_el1)
return;
/* Restore trace filter controls */
- write_sysreg_s(trfcr_el1, SYS_TRFCR_EL1);
+ write_sysreg_el1(trfcr_el1, SYS_TRFCR);
}
void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 7693a6757cd7..135cfb294ee5 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -110,7 +110,7 @@ SYM_FUNC_END(__host_enter)
* u64 elr, u64 par);
*/
SYM_FUNC_START(__hyp_do_panic)
- /* Prepare and exit to the host's panic funciton. */
+ /* Prepare and exit to the host's panic function. */
mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
PSR_MODE_EL1h)
msr spsr_el2, lr
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index b01a3d1078a8..8850b591d775 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -155,7 +155,7 @@ int hyp_back_vmemmap(phys_addr_t back)
start = hyp_memory[i].base;
start = ALIGN_DOWN((u64)hyp_phys_to_page(start), PAGE_SIZE);
/*
- * The begining of the hyp_vmemmap region for the current
+ * The beginning of the hyp_vmemmap region for the current
* memblock may already be backed by the page backing the end
* the previous region, so avoid mapping it twice.
*/
@@ -408,7 +408,7 @@ static void *admit_host_page(void *arg)
return pop_hyp_memcache(host_mc, hyp_phys_to_virt);
}
-/* Refill our local memcache by poping pages from the one provided by the host. */
+/* Refill our local memcache by popping pages from the one provided by the host. */
int refill_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages,
struct kvm_hyp_memcache *host_mc)
{
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index ab9d05fcf98b..3fae5830f8d2 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -717,15 +717,29 @@ void kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot prot,
kvm_pte_t *ptep)
{
- bool device = prot & KVM_PGTABLE_PROT_DEVICE;
- kvm_pte_t attr = device ? KVM_S2_MEMATTR(pgt, DEVICE_nGnRE) :
- KVM_S2_MEMATTR(pgt, NORMAL);
+ kvm_pte_t attr;
u32 sh = KVM_PTE_LEAF_ATTR_LO_S2_SH_IS;
+ switch (prot & (KVM_PGTABLE_PROT_DEVICE |
+ KVM_PGTABLE_PROT_NORMAL_NC)) {
+ case KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_NORMAL_NC:
+ return -EINVAL;
+ case KVM_PGTABLE_PROT_DEVICE:
+ if (prot & KVM_PGTABLE_PROT_X)
+ return -EINVAL;
+ attr = KVM_S2_MEMATTR(pgt, DEVICE_nGnRE);
+ break;
+ case KVM_PGTABLE_PROT_NORMAL_NC:
+ if (prot & KVM_PGTABLE_PROT_X)
+ return -EINVAL;
+ attr = KVM_S2_MEMATTR(pgt, NORMAL_NC);
+ break;
+ default:
+ attr = KVM_S2_MEMATTR(pgt, NORMAL);
+ }
+
if (!(prot & KVM_PGTABLE_PROT_X))
attr |= KVM_PTE_LEAF_ATTR_HI_S2_XN;
- else if (device)
- return -EINVAL;
if (prot & KVM_PGTABLE_PROT_R)
attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R;
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
index 8e1e0d5033b6..a8b9ea496706 100644
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -95,7 +95,7 @@ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
}
/**
- * __vcpu_put_switch_syregs - Restore host system registers to the physical CPU
+ * __vcpu_put_switch_sysregs - Restore host system registers to the physical CPU
*
* @vcpu: The VCPU pointer
*
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 0bd93a5f21ce..a640e839848e 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -134,7 +134,7 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, u32 addr)
if (vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE) {
fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE;
} else {
- /* no need to shuffle FS[4] into DFSR[10] as its 0 */
+ /* no need to shuffle FS[4] into DFSR[10] as it's 0 */
fsr = DFSR_FSC_EXTABT_nLPAE;
}
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index d14504821b79..2902f3ffca3c 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -305,7 +305,7 @@ static void invalidate_icache_guest_page(void *va, size_t size)
* does.
*/
/**
- * unmap_stage2_range -- Clear stage2 page table entries to unmap a range
+ * __unmap_stage2_range -- Clear stage2 page table entries to unmap a range
* @mmu: The KVM stage-2 MMU pointer
* @start: The intermediate physical base address of the range to unmap
* @size: The size of the area to unmap
@@ -1381,7 +1381,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
int ret = 0;
bool write_fault, writable, force_pte = false;
bool exec_fault, mte_allowed;
- bool device = false;
+ bool device = false, vfio_allow_any_uc = false;
unsigned long mmu_seq;
struct kvm *kvm = vcpu->kvm;
struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
@@ -1472,6 +1472,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
gfn = fault_ipa >> PAGE_SHIFT;
mte_allowed = kvm_vma_mte_allowed(vma);
+ vfio_allow_any_uc = vma->vm_flags & VM_ALLOW_ANY_UNCACHED;
+
/* Don't use the VMA after the unlock -- it may have vanished */
vma = NULL;
@@ -1557,10 +1559,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
if (exec_fault)
prot |= KVM_PGTABLE_PROT_X;
- if (device)
- prot |= KVM_PGTABLE_PROT_DEVICE;
- else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC))
+ if (device) {
+ if (vfio_allow_any_uc)
+ prot |= KVM_PGTABLE_PROT_NORMAL_NC;
+ else
+ prot |= KVM_PGTABLE_PROT_DEVICE;
+ } else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC)) {
prot |= KVM_PGTABLE_PROT_X;
+ }
/*
* Under the premise of getting a FSC_PERM fault, we just need to relax
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index ba95d044bc98..ced30c90521a 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -133,6 +133,13 @@ static u64 limit_nv_id_reg(u32 id, u64 val)
val |= FIELD_PREP(NV_FTR(MMFR2, TTL), 0b0001);
break;
+ case SYS_ID_AA64MMFR4_EL1:
+ val = 0;
+ if (!cpus_have_final_cap(ARM64_HAS_HCR_NV1))
+ val |= FIELD_PREP(NV_FTR(MMFR4, E2H0),
+ ID_AA64MMFR4_EL1_E2H0_NI_NV1);
+ break;
+
case SYS_ID_AA64DFR0_EL1:
/* Only limited support for PMU, Debug, BPs and WPs */
val &= (NV_FTR(DFR0, PMUVer) |
@@ -156,15 +163,280 @@ static u64 limit_nv_id_reg(u32 id, u64 val)
return val;
}
+
+u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *vcpu, enum vcpu_sysreg sr)
+{
+ u64 v = ctxt_sys_reg(&vcpu->arch.ctxt, sr);
+ struct kvm_sysreg_masks *masks;
+
+ masks = vcpu->kvm->arch.sysreg_masks;
+
+ if (masks) {
+ sr -= __VNCR_START__;
+
+ v &= ~masks->mask[sr].res0;
+ v |= masks->mask[sr].res1;
+ }
+
+ return v;
+}
+
+static void set_sysreg_masks(struct kvm *kvm, int sr, u64 res0, u64 res1)
+{
+ int i = sr - __VNCR_START__;
+
+ kvm->arch.sysreg_masks->mask[i].res0 = res0;
+ kvm->arch.sysreg_masks->mask[i].res1 = res1;
+}
+
int kvm_init_nv_sysregs(struct kvm *kvm)
{
+ u64 res0, res1;
+ int ret = 0;
+
mutex_lock(&kvm->arch.config_lock);
+ if (kvm->arch.sysreg_masks)
+ goto out;
+
+ kvm->arch.sysreg_masks = kzalloc(sizeof(*(kvm->arch.sysreg_masks)),
+ GFP_KERNEL);
+ if (!kvm->arch.sysreg_masks) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
for (int i = 0; i < KVM_ARM_ID_REG_NUM; i++)
kvm->arch.id_regs[i] = limit_nv_id_reg(IDX_IDREG(i),
kvm->arch.id_regs[i]);
+ /* VTTBR_EL2 */
+ res0 = res1 = 0;
+ if (!kvm_has_feat_enum(kvm, ID_AA64MMFR1_EL1, VMIDBits, 16))
+ res0 |= GENMASK(63, 56);
+ if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, CnP, IMP))
+ res0 |= VTTBR_CNP_BIT;
+ set_sysreg_masks(kvm, VTTBR_EL2, res0, res1);
+
+ /* VTCR_EL2 */
+ res0 = GENMASK(63, 32) | GENMASK(30, 20);
+ res1 = BIT(31);
+ set_sysreg_masks(kvm, VTCR_EL2, res0, res1);
+
+ /* VMPIDR_EL2 */
+ res0 = GENMASK(63, 40) | GENMASK(30, 24);
+ res1 = BIT(31);
+ set_sysreg_masks(kvm, VMPIDR_EL2, res0, res1);
+
+ /* HCR_EL2 */
+ res0 = BIT(48);
+ res1 = HCR_RW;
+ if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, TWED, IMP))
+ res0 |= GENMASK(63, 59);
+ if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, MTE, MTE2))
+ res0 |= (HCR_TID5 | HCR_DCT | HCR_ATA);
+ if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, EVT, TTLBxS))
+ res0 |= (HCR_TTLBIS | HCR_TTLBOS);
+ if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, CSV2, CSV2_2) &&
+ !kvm_has_feat(kvm, ID_AA64PFR1_EL1, CSV2_frac, CSV2_1p2))
+ res0 |= HCR_ENSCXT;
+ if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, EVT, IMP))
+ res0 |= (HCR_TOCU | HCR_TICAB | HCR_TID4);
+ if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, V1P1))
+ res0 |= HCR_AMVOFFEN;
+ if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, V1P1))
+ res0 |= HCR_FIEN;
+ if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, FWB, IMP))
+ res0 |= HCR_FWB;
+ if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, NV, NV2))
+ res0 |= HCR_NV2;
+ if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, NV, IMP))
+ res0 |= (HCR_AT | HCR_NV1 | HCR_NV);
+ if (!(__vcpu_has_feature(&kvm->arch, KVM_ARM_VCPU_PTRAUTH_ADDRESS) &&
+ __vcpu_has_feature(&kvm->arch, KVM_ARM_VCPU_PTRAUTH_GENERIC)))
+ res0 |= (HCR_API | HCR_APK);
+ if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TME, IMP))
+ res0 |= BIT(39);
+ if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP))
+ res0 |= (HCR_TEA | HCR_TERR);
+ if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP))
+ res0 |= HCR_TLOR;
+ if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, E2H0, IMP))
+ res1 |= HCR_E2H;
+ set_sysreg_masks(kvm, HCR_EL2, res0, res1);
+
+ /* HCRX_EL2 */
+ res0 = HCRX_EL2_RES0;
+ res1 = HCRX_EL2_RES1;
+ if (!kvm_has_feat(kvm, ID_AA64ISAR3_EL1, PACM, TRIVIAL_IMP))
+ res0 |= HCRX_EL2_PACMEn;
+ if (!kvm_has_feat(kvm, ID_AA64PFR2_EL1, FPMR, IMP))
+ res0 |= HCRX_EL2_EnFPM;
+ if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP))
+ res0 |= HCRX_EL2_GCSEn;
+ if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, SYSREG_128, IMP))
+ res0 |= HCRX_EL2_EnIDCP128;
+ if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, ADERR, DEV_ASYNC))
+ res0 |= (HCRX_EL2_EnSDERR | HCRX_EL2_EnSNERR);
+ if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, DF2, IMP))
+ res0 |= HCRX_EL2_TMEA;
+ if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, D128, IMP))
+ res0 |= HCRX_EL2_D128En;
+ if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP))
+ res0 |= HCRX_EL2_PTTWI;
+ if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, SCTLRX, IMP))
+ res0 |= HCRX_EL2_SCTLR2En;
+ if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, TCRX, IMP))
+ res0 |= HCRX_EL2_TCR2En;
+ if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, MOPS, IMP))
+ res0 |= (HCRX_EL2_MSCEn | HCRX_EL2_MCE2);
+ if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, CMOW, IMP))
+ res0 |= HCRX_EL2_CMOW;
+ if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, NMI, IMP))
+ res0 |= (HCRX_EL2_VFNMI | HCRX_EL2_VINMI | HCRX_EL2_TALLINT);
+ if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP) ||
+ !(read_sysreg_s(SYS_SMIDR_EL1) & SMIDR_EL1_SMPS))
+ res0 |= HCRX_EL2_SMPME;
+ if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP))
+ res0 |= (HCRX_EL2_FGTnXS | HCRX_EL2_FnXS);
+ if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_V))
+ res0 |= HCRX_EL2_EnASR;
+ if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64))
+ res0 |= HCRX_EL2_EnALS;
+ if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA))
+ res0 |= HCRX_EL2_EnAS0;
+ set_sysreg_masks(kvm, HCRX_EL2, res0, res1);
+
+ /* HFG[RW]TR_EL2 */
+ res0 = res1 = 0;
+ if (!(__vcpu_has_feature(&kvm->arch, KVM_ARM_VCPU_PTRAUTH_ADDRESS) &&
+ __vcpu_has_feature(&kvm->arch, KVM_ARM_VCPU_PTRAUTH_GENERIC)))
+ res0 |= (HFGxTR_EL2_APDAKey | HFGxTR_EL2_APDBKey |
+ HFGxTR_EL2_APGAKey | HFGxTR_EL2_APIAKey |
+ HFGxTR_EL2_APIBKey);
+ if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP))
+ res0 |= (HFGxTR_EL2_LORC_EL1 | HFGxTR_EL2_LOREA_EL1 |
+ HFGxTR_EL2_LORID_EL1 | HFGxTR_EL2_LORN_EL1 |
+ HFGxTR_EL2_LORSA_EL1);
+ if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, CSV2, CSV2_2) &&
+ !kvm_has_feat(kvm, ID_AA64PFR1_EL1, CSV2_frac, CSV2_1p2))
+ res0 |= (HFGxTR_EL2_SCXTNUM_EL1 | HFGxTR_EL2_SCXTNUM_EL0);
+ if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, GIC, IMP))
+ res0 |= HFGxTR_EL2_ICC_IGRPENn_EL1;
+ if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP))
+ res0 |= (HFGxTR_EL2_ERRIDR_EL1 | HFGxTR_EL2_ERRSELR_EL1 |
+ HFGxTR_EL2_ERXFR_EL1 | HFGxTR_EL2_ERXCTLR_EL1 |
+ HFGxTR_EL2_ERXSTATUS_EL1 | HFGxTR_EL2_ERXMISCn_EL1 |
+ HFGxTR_EL2_ERXPFGF_EL1 | HFGxTR_EL2_ERXPFGCTL_EL1 |
+ HFGxTR_EL2_ERXPFGCDN_EL1 | HFGxTR_EL2_ERXADDR_EL1);
+ if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA))
+ res0 |= HFGxTR_EL2_nACCDATA_EL1;
+ if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP))
+ res0 |= (HFGxTR_EL2_nGCS_EL0 | HFGxTR_EL2_nGCS_EL1);
+ if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP))
+ res0 |= (HFGxTR_EL2_nSMPRI_EL1 | HFGxTR_EL2_nTPIDR2_EL0);
+ if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP))
+ res0 |= HFGxTR_EL2_nRCWMASK_EL1;
+ if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S1PIE, IMP))
+ res0 |= (HFGxTR_EL2_nPIRE0_EL1 | HFGxTR_EL2_nPIR_EL1);
+ if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S1POE, IMP))
+ res0 |= (HFGxTR_EL2_nPOR_EL0 | HFGxTR_EL2_nPOR_EL1);
+ if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S2POE, IMP))
+ res0 |= HFGxTR_EL2_nS2POR_EL1;
+ if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, AIE, IMP))
+ res0 |= (HFGxTR_EL2_nMAIR2_EL1 | HFGxTR_EL2_nAMAIR2_EL1);
+ set_sysreg_masks(kvm, HFGRTR_EL2, res0 | __HFGRTR_EL2_RES0, res1);
+ set_sysreg_masks(kvm, HFGWTR_EL2, res0 | __HFGWTR_EL2_RES0, res1);
+
+ /* HDFG[RW]TR_EL2 */
+ res0 = res1 = 0;
+ if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DoubleLock, IMP))
+ res0 |= HDFGRTR_EL2_OSDLR_EL1;
+ if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP))
+ res0 |= (HDFGRTR_EL2_PMEVCNTRn_EL0 | HDFGRTR_EL2_PMEVTYPERn_EL0 |
+ HDFGRTR_EL2_PMCCFILTR_EL0 | HDFGRTR_EL2_PMCCNTR_EL0 |
+ HDFGRTR_EL2_PMCNTEN | HDFGRTR_EL2_PMINTEN |
+ HDFGRTR_EL2_PMOVS | HDFGRTR_EL2_PMSELR_EL0 |
+ HDFGRTR_EL2_PMMIR_EL1 | HDFGRTR_EL2_PMUSERENR_EL0 |
+ HDFGRTR_EL2_PMCEIDn_EL0);
+ if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, IMP))
+ res0 |= (HDFGRTR_EL2_PMBLIMITR_EL1 | HDFGRTR_EL2_PMBPTR_EL1 |
+ HDFGRTR_EL2_PMBSR_EL1 | HDFGRTR_EL2_PMSCR_EL1 |
+ HDFGRTR_EL2_PMSEVFR_EL1 | HDFGRTR_EL2_PMSFCR_EL1 |
+ HDFGRTR_EL2_PMSICR_EL1 | HDFGRTR_EL2_PMSIDR_EL1 |
+ HDFGRTR_EL2_PMSIRR_EL1 | HDFGRTR_EL2_PMSLATFR_EL1 |
+ HDFGRTR_EL2_PMBIDR_EL1);
+ if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceVer, IMP))
+ res0 |= (HDFGRTR_EL2_TRC | HDFGRTR_EL2_TRCAUTHSTATUS |
+ HDFGRTR_EL2_TRCAUXCTLR | HDFGRTR_EL2_TRCCLAIM |
+ HDFGRTR_EL2_TRCCNTVRn | HDFGRTR_EL2_TRCID |
+ HDFGRTR_EL2_TRCIMSPECn | HDFGRTR_EL2_TRCOSLSR |
+ HDFGRTR_EL2_TRCPRGCTLR | HDFGRTR_EL2_TRCSEQSTR |
+ HDFGRTR_EL2_TRCSSCSRn | HDFGRTR_EL2_TRCSTATR |
+ HDFGRTR_EL2_TRCVICTLR);
+ if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceBuffer, IMP))
+ res0 |= (HDFGRTR_EL2_TRBBASER_EL1 | HDFGRTR_EL2_TRBIDR_EL1 |
+ HDFGRTR_EL2_TRBLIMITR_EL1 | HDFGRTR_EL2_TRBMAR_EL1 |
+ HDFGRTR_EL2_TRBPTR_EL1 | HDFGRTR_EL2_TRBSR_EL1 |
+ HDFGRTR_EL2_TRBTRG_EL1);
+ if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP))
+ res0 |= (HDFGRTR_EL2_nBRBIDR | HDFGRTR_EL2_nBRBCTL |
+ HDFGRTR_EL2_nBRBDATA);
+ if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, V1P2))
+ res0 |= HDFGRTR_EL2_nPMSNEVFR_EL1;
+ set_sysreg_masks(kvm, HDFGRTR_EL2, res0 | HDFGRTR_EL2_RES0, res1);
+
+ /* Reuse the bits from the read-side and add the write-specific stuff */
+ if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP))
+ res0 |= (HDFGWTR_EL2_PMCR_EL0 | HDFGWTR_EL2_PMSWINC_EL0);
+ if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceVer, IMP))
+ res0 |= HDFGWTR_EL2_TRCOSLAR;
+ if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceFilt, IMP))
+ res0 |= HDFGWTR_EL2_TRFCR_EL1;
+ set_sysreg_masks(kvm, HFGWTR_EL2, res0 | HDFGWTR_EL2_RES0, res1);
+
+ /* HFGITR_EL2 */
+ res0 = HFGITR_EL2_RES0;
+ res1 = HFGITR_EL2_RES1;
+ if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, DPB, DPB2))
+ res0 |= HFGITR_EL2_DCCVADP;
+ if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, PAN, PAN2))
+ res0 |= (HFGITR_EL2_ATS1E1RP | HFGITR_EL2_ATS1E1WP);
+ if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
+ res0 |= (HFGITR_EL2_TLBIRVAALE1OS | HFGITR_EL2_TLBIRVALE1OS |
+ HFGITR_EL2_TLBIRVAAE1OS | HFGITR_EL2_TLBIRVAE1OS |
+ HFGITR_EL2_TLBIVAALE1OS | HFGITR_EL2_TLBIVALE1OS |
+ HFGITR_EL2_TLBIVAAE1OS | HFGITR_EL2_TLBIASIDE1OS |
+ HFGITR_EL2_TLBIVAE1OS | HFGITR_EL2_TLBIVMALLE1OS);
+ if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
+ res0 |= (HFGITR_EL2_TLBIRVAALE1 | HFGITR_EL2_TLBIRVALE1 |
+ HFGITR_EL2_TLBIRVAAE1 | HFGITR_EL2_TLBIRVAE1 |
+ HFGITR_EL2_TLBIRVAALE1IS | HFGITR_EL2_TLBIRVALE1IS |
+ HFGITR_EL2_TLBIRVAAE1IS | HFGITR_EL2_TLBIRVAE1IS |
+ HFGITR_EL2_TLBIRVAALE1OS | HFGITR_EL2_TLBIRVALE1OS |
+ HFGITR_EL2_TLBIRVAAE1OS | HFGITR_EL2_TLBIRVAE1OS);
+ if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, SPECRES, IMP))
+ res0 |= (HFGITR_EL2_CFPRCTX | HFGITR_EL2_DVPRCTX |
+ HFGITR_EL2_CPPRCTX);
+ if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP))
+ res0 |= (HFGITR_EL2_nBRBINJ | HFGITR_EL2_nBRBIALL);
+ if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP))
+ res0 |= (HFGITR_EL2_nGCSPUSHM_EL1 | HFGITR_EL2_nGCSSTR_EL1 |
+ HFGITR_EL2_nGCSEPP);
+ if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, SPECRES, COSP_RCTX))
+ res0 |= HFGITR_EL2_COSPRCTX;
+ if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, ATS1A, IMP))
+ res0 |= HFGITR_EL2_ATS1E1A;
+ set_sysreg_masks(kvm, HFGITR_EL2, res0, res1);
+
+ /* HAFGRTR_EL2 - not a lot to see here */
+ res0 = HAFGRTR_EL2_RES0;
+ res1 = HAFGRTR_EL2_RES1;
+ if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, V1P1))
+ res0 |= ~(res0 | res1);
+ set_sysreg_masks(kvm, HAFGRTR_EL2, res0, res1);
+out:
mutex_unlock(&kvm->arch.config_lock);
- return 0;
+ return ret;
}
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 3d9467ff73bc..a35ce10e0a9f 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -64,12 +64,11 @@ u64 kvm_pmu_evtyper_mask(struct kvm *kvm)
{
u64 mask = ARMV8_PMU_EXCLUDE_EL1 | ARMV8_PMU_EXCLUDE_EL0 |
kvm_pmu_event_mask(kvm);
- u64 pfr0 = IDREG(kvm, SYS_ID_AA64PFR0_EL1);
- if (SYS_FIELD_GET(ID_AA64PFR0_EL1, EL2, pfr0))
+ if (kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL2, IMP))
mask |= ARMV8_PMU_INCLUDE_EL2;
- if (SYS_FIELD_GET(ID_AA64PFR0_EL1, EL3, pfr0))
+ if (kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL3, IMP))
mask |= ARMV8_PMU_EXCLUDE_NS_EL0 |
ARMV8_PMU_EXCLUDE_NS_EL1 |
ARMV8_PMU_EXCLUDE_EL3;
@@ -83,8 +82,10 @@ u64 kvm_pmu_evtyper_mask(struct kvm *kvm)
*/
static bool kvm_pmc_is_64bit(struct kvm_pmc *pmc)
{
+ struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+
return (pmc->idx == ARMV8_PMU_CYCLE_IDX ||
- kvm_pmu_is_3p5(kvm_pmc_to_vcpu(pmc)));
+ kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5));
}
static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc)
@@ -419,7 +420,7 @@ void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu)
kvm_pmu_update_state(vcpu);
}
-/**
+/*
* When perf interrupt is an NMI, we cannot safely notify the vcpu corresponding
* to the event.
* This is why we need a callback to do it once outside of the NMI context.
@@ -490,7 +491,7 @@ static u64 compute_period(struct kvm_pmc *pmc, u64 counter)
return val;
}
-/**
+/*
* When the perf event overflows, set the overflow status and inform the vcpu.
*/
static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
@@ -556,7 +557,7 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
return;
/* Fixup PMCR_EL0 to reconcile the PMU version and the LP bit */
- if (!kvm_pmu_is_3p5(vcpu))
+ if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5))
val &= ~ARMV8_PMU_PMCR_LP;
/* The reset bits don't indicate any state, and shouldn't be saved. */
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 30253bd19917..8e60aa4a8dfb 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -12,6 +12,7 @@
#include <linux/bitfield.h>
#include <linux/bsearch.h>
#include <linux/cacheinfo.h>
+#include <linux/debugfs.h>
#include <linux/kvm_host.h>
#include <linux/mm.h>
#include <linux/printk.h>
@@ -31,6 +32,7 @@
#include <trace/events/kvm.h>
+#include "check-res-bits.h"
#include "sys_regs.h"
#include "trace.h"
@@ -505,10 +507,9 @@ static bool trap_loregion(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
- u64 val = IDREG(vcpu->kvm, SYS_ID_AA64MMFR1_EL1);
u32 sr = reg_to_encoding(r);
- if (!(val & (0xfUL << ID_AA64MMFR1_EL1_LO_SHIFT))) {
+ if (!kvm_has_feat(vcpu->kvm, ID_AA64MMFR1_EL1, LO, IMP)) {
kvm_inject_undefined(vcpu);
return false;
}
@@ -1685,7 +1686,8 @@ static u64 read_sanitised_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
u64 __f_val = FIELD_GET(reg##_##field##_MASK, val); \
(val) &= ~reg##_##field##_MASK; \
(val) |= FIELD_PREP(reg##_##field##_MASK, \
- min(__f_val, (u64)reg##_##field##_##limit)); \
+ min(__f_val, \
+ (u64)SYS_FIELD_VALUE(reg, field, limit))); \
(val); \
})
@@ -2174,6 +2176,16 @@ static bool access_spsr(struct kvm_vcpu *vcpu,
return true;
}
+static u64 reset_hcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+ u64 val = r->val;
+
+ if (!cpus_have_final_cap(ARM64_HAS_HCR_NV1))
+ val |= HCR_E2H;
+
+ return __vcpu_sys_reg(vcpu, r->reg) = val;
+}
+
/*
* Architected system registers.
* Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
@@ -2186,16 +2198,6 @@ static bool access_spsr(struct kvm_vcpu *vcpu,
* guest...
*/
static const struct sys_reg_desc sys_reg_descs[] = {
- { SYS_DESC(SYS_DC_ISW), access_dcsw },
- { SYS_DESC(SYS_DC_IGSW), access_dcgsw },
- { SYS_DESC(SYS_DC_IGDSW), access_dcgsw },
- { SYS_DESC(SYS_DC_CSW), access_dcsw },
- { SYS_DESC(SYS_DC_CGSW), access_dcgsw },
- { SYS_DESC(SYS_DC_CGDSW), access_dcgsw },
- { SYS_DESC(SYS_DC_CISW), access_dcsw },
- { SYS_DESC(SYS_DC_CIGSW), access_dcgsw },
- { SYS_DESC(SYS_DC_CIGDSW), access_dcgsw },
-
DBG_BCR_BVR_WCR_WVR_EL1(0),
DBG_BCR_BVR_WCR_WVR_EL1(1),
{ SYS_DESC(SYS_MDCCINT_EL1), trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
@@ -2349,7 +2351,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
ID_AA64MMFR2_EL1_NV |
ID_AA64MMFR2_EL1_CCIDX)),
ID_SANITISED(ID_AA64MMFR3_EL1),
- ID_UNALLOCATED(7,4),
+ ID_SANITISED(ID_AA64MMFR4_EL1),
ID_UNALLOCATED(7,5),
ID_UNALLOCATED(7,6),
ID_UNALLOCATED(7,7),
@@ -2665,7 +2667,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
EL2_REG_VNCR(VMPIDR_EL2, reset_unknown, 0),
EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1),
EL2_REG(ACTLR_EL2, access_rw, reset_val, 0),
- EL2_REG_VNCR(HCR_EL2, reset_val, 0),
+ EL2_REG_VNCR(HCR_EL2, reset_hcr, 0),
EL2_REG(MDCR_EL2, access_rw, reset_val, 0),
EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1),
EL2_REG_VNCR(HSTR_EL2, reset_val, 0),
@@ -2727,6 +2729,18 @@ static const struct sys_reg_desc sys_reg_descs[] = {
EL2_REG(SP_EL2, NULL, reset_unknown, 0),
};
+static struct sys_reg_desc sys_insn_descs[] = {
+ { SYS_DESC(SYS_DC_ISW), access_dcsw },
+ { SYS_DESC(SYS_DC_IGSW), access_dcgsw },
+ { SYS_DESC(SYS_DC_IGDSW), access_dcgsw },
+ { SYS_DESC(SYS_DC_CSW), access_dcsw },
+ { SYS_DESC(SYS_DC_CGSW), access_dcgsw },
+ { SYS_DESC(SYS_DC_CGDSW), access_dcgsw },
+ { SYS_DESC(SYS_DC_CISW), access_dcsw },
+ { SYS_DESC(SYS_DC_CIGSW), access_dcgsw },
+ { SYS_DESC(SYS_DC_CIGDSW), access_dcgsw },
+};
+
static const struct sys_reg_desc *first_idreg;
static bool trap_dbgdidr(struct kvm_vcpu *vcpu,
@@ -2737,8 +2751,7 @@ static bool trap_dbgdidr(struct kvm_vcpu *vcpu,
return ignore_write(vcpu, p);
} else {
u64 dfr = IDREG(vcpu->kvm, SYS_ID_AA64DFR0_EL1);
- u64 pfr = IDREG(vcpu->kvm, SYS_ID_AA64PFR0_EL1);
- u32 el3 = !!SYS_FIELD_GET(ID_AA64PFR0_EL1, EL3, pfr);
+ u32 el3 = kvm_has_feat(vcpu->kvm, ID_AA64PFR0_EL1, EL3, IMP);
p->regval = ((SYS_FIELD_GET(ID_AA64DFR0_EL1, WRPs, dfr) << 28) |
(SYS_FIELD_GET(ID_AA64DFR0_EL1, BRPs, dfr) << 24) |
@@ -3159,7 +3172,8 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
/**
* kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP14/CP15 access
* @vcpu: The VCPU pointer
- * @run: The kvm_run struct
+ * @global: &struct sys_reg_desc
+ * @nr_global: size of the @global array
*/
static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *global,
@@ -3326,7 +3340,9 @@ static int kvm_emulate_cp15_id_reg(struct kvm_vcpu *vcpu,
/**
* kvm_handle_cp_32 -- handles a mrc/mcr trap on a guest CP14/CP15 access
* @vcpu: The VCPU pointer
- * @run: The kvm_run struct
+ * @params: &struct sys_reg_params
+ * @global: &struct sys_reg_desc
+ * @nr_global: size of the @global array
*/
static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
struct sys_reg_params *params,
@@ -3384,12 +3400,6 @@ int kvm_handle_cp14_32(struct kvm_vcpu *vcpu)
return kvm_handle_cp_32(vcpu, &params, cp14_regs, ARRAY_SIZE(cp14_regs));
}
-static bool is_imp_def_sys_reg(struct sys_reg_params *params)
-{
- // See ARM DDI 0487E.a, section D12.3.2
- return params->Op0 == 3 && (params->CRn & 0b1011) == 0b1011;
-}
-
/**
* emulate_sys_reg - Emulate a guest access to an AArch64 system register
* @vcpu: The VCPU pointer
@@ -3398,26 +3408,106 @@ static bool is_imp_def_sys_reg(struct sys_reg_params *params)
* Return: true if the system register access was successful, false otherwise.
*/
static bool emulate_sys_reg(struct kvm_vcpu *vcpu,
- struct sys_reg_params *params)
+ struct sys_reg_params *params)
{
const struct sys_reg_desc *r;
r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
-
if (likely(r)) {
perform_access(vcpu, params, r);
return true;
}
- if (is_imp_def_sys_reg(params)) {
- kvm_inject_undefined(vcpu);
+ print_sys_reg_msg(params,
+ "Unsupported guest sys_reg access at: %lx [%08lx]\n",
+ *vcpu_pc(vcpu), *vcpu_cpsr(vcpu));
+ kvm_inject_undefined(vcpu);
+
+ return false;
+}
+
+static void *idregs_debug_start(struct seq_file *s, loff_t *pos)
+{
+ struct kvm *kvm = s->private;
+ u8 *iter;
+
+ mutex_lock(&kvm->arch.config_lock);
+
+ iter = &kvm->arch.idreg_debugfs_iter;
+ if (test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags) &&
+ *iter == (u8)~0) {
+ *iter = *pos;
+ if (*iter >= KVM_ARM_ID_REG_NUM)
+ iter = NULL;
} else {
- print_sys_reg_msg(params,
- "Unsupported guest sys_reg access at: %lx [%08lx]\n",
- *vcpu_pc(vcpu), *vcpu_cpsr(vcpu));
- kvm_inject_undefined(vcpu);
+ iter = ERR_PTR(-EBUSY);
}
- return false;
+
+ mutex_unlock(&kvm->arch.config_lock);
+
+ return iter;
+}
+
+static void *idregs_debug_next(struct seq_file *s, void *v, loff_t *pos)
+{
+ struct kvm *kvm = s->private;
+
+ (*pos)++;
+
+ if ((kvm->arch.idreg_debugfs_iter + 1) < KVM_ARM_ID_REG_NUM) {
+ kvm->arch.idreg_debugfs_iter++;
+
+ return &kvm->arch.idreg_debugfs_iter;
+ }
+
+ return NULL;
+}
+
+static void idregs_debug_stop(struct seq_file *s, void *v)
+{
+ struct kvm *kvm = s->private;
+
+ if (IS_ERR(v))
+ return;
+
+ mutex_lock(&kvm->arch.config_lock);
+
+ kvm->arch.idreg_debugfs_iter = ~0;
+
+ mutex_unlock(&kvm->arch.config_lock);
+}
+
+static int idregs_debug_show(struct seq_file *s, void *v)
+{
+ struct kvm *kvm = s->private;
+ const struct sys_reg_desc *desc;
+
+ desc = first_idreg + kvm->arch.idreg_debugfs_iter;
+
+ if (!desc->name)
+ return 0;
+
+ seq_printf(s, "%20s:\t%016llx\n",
+ desc->name, IDREG(kvm, IDX_IDREG(kvm->arch.idreg_debugfs_iter)));
+
+ return 0;
+}
+
+static const struct seq_operations idregs_debug_sops = {
+ .start = idregs_debug_start,
+ .next = idregs_debug_next,
+ .stop = idregs_debug_stop,
+ .show = idregs_debug_show,
+};
+
+DEFINE_SEQ_ATTRIBUTE(idregs_debug);
+
+void kvm_sys_regs_create_debugfs(struct kvm *kvm)
+{
+ kvm->arch.idreg_debugfs_iter = ~0;
+
+ debugfs_create_file("idregs", 0444, kvm->debugfs_dentry, kvm,
+ &idregs_debug_fops);
}
static void kvm_reset_id_regs(struct kvm_vcpu *vcpu)
@@ -3467,28 +3557,39 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
}
/**
- * kvm_handle_sys_reg -- handles a mrs/msr trap on a guest sys_reg access
+ * kvm_handle_sys_reg -- handles a system instruction or mrs/msr instruction
+ * trap on a guest execution
* @vcpu: The VCPU pointer
*/
int kvm_handle_sys_reg(struct kvm_vcpu *vcpu)
{
+ const struct sys_reg_desc *desc = NULL;
struct sys_reg_params params;
unsigned long esr = kvm_vcpu_get_esr(vcpu);
int Rt = kvm_vcpu_sys_get_rt(vcpu);
+ int sr_idx;
trace_kvm_handle_sys_reg(esr);
- if (__check_nv_sr_forward(vcpu))
+ if (triage_sysreg_trap(vcpu, &sr_idx))
return 1;
params = esr_sys64_to_params(esr);
params.regval = vcpu_get_reg(vcpu, Rt);
- if (!emulate_sys_reg(vcpu, &params))
- return 1;
+ /* System registers have Op0=={2,3}, as per DDI487 J.a C5.1.2 */
+ if (params.Op0 == 2 || params.Op0 == 3)
+ desc = &sys_reg_descs[sr_idx];
+ else
+ desc = &sys_insn_descs[sr_idx];
- if (!params.is_write)
+ perform_access(vcpu, &params, desc);
+
+ /* Read from system register? */
+ if (!params.is_write &&
+ (params.Op0 == 2 || params.Op0 == 3))
vcpu_set_reg(vcpu, Rt, params.regval);
+
return 1;
}
@@ -3930,11 +4031,86 @@ int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, struct reg_mask_range *
return 0;
}
+void kvm_init_sysreg(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+
+ mutex_lock(&kvm->arch.config_lock);
+
+ /*
+ * In the absence of FGT, we cannot independently trap TLBI
+ * Range instructions. This isn't great, but trapping all
+ * TLBIs would be far worse. Live with it...
+ */
+ if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
+ vcpu->arch.hcr_el2 |= HCR_TTLBOS;
+
+ if (cpus_have_final_cap(ARM64_HAS_HCX)) {
+ vcpu->arch.hcrx_el2 = HCRX_GUEST_FLAGS;
+
+ if (kvm_has_feat(kvm, ID_AA64ISAR2_EL1, MOPS, IMP))
+ vcpu->arch.hcrx_el2 |= (HCRX_EL2_MSCEn | HCRX_EL2_MCE2);
+ }
+
+ if (test_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags))
+ goto out;
+
+ kvm->arch.fgu[HFGxTR_GROUP] = (HFGxTR_EL2_nAMAIR2_EL1 |
+ HFGxTR_EL2_nMAIR2_EL1 |
+ HFGxTR_EL2_nS2POR_EL1 |
+ HFGxTR_EL2_nPOR_EL1 |
+ HFGxTR_EL2_nPOR_EL0 |
+ HFGxTR_EL2_nACCDATA_EL1 |
+ HFGxTR_EL2_nSMPRI_EL1_MASK |
+ HFGxTR_EL2_nTPIDR2_EL0_MASK);
+
+ if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
+ kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_TLBIRVAALE1OS|
+ HFGITR_EL2_TLBIRVALE1OS |
+ HFGITR_EL2_TLBIRVAAE1OS |
+ HFGITR_EL2_TLBIRVAE1OS |
+ HFGITR_EL2_TLBIVAALE1OS |
+ HFGITR_EL2_TLBIVALE1OS |
+ HFGITR_EL2_TLBIVAAE1OS |
+ HFGITR_EL2_TLBIASIDE1OS |
+ HFGITR_EL2_TLBIVAE1OS |
+ HFGITR_EL2_TLBIVMALLE1OS);
+
+ if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
+ kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_TLBIRVAALE1 |
+ HFGITR_EL2_TLBIRVALE1 |
+ HFGITR_EL2_TLBIRVAAE1 |
+ HFGITR_EL2_TLBIRVAE1 |
+ HFGITR_EL2_TLBIRVAALE1IS|
+ HFGITR_EL2_TLBIRVALE1IS |
+ HFGITR_EL2_TLBIRVAAE1IS |
+ HFGITR_EL2_TLBIRVAE1IS |
+ HFGITR_EL2_TLBIRVAALE1OS|
+ HFGITR_EL2_TLBIRVALE1OS |
+ HFGITR_EL2_TLBIRVAAE1OS |
+ HFGITR_EL2_TLBIRVAE1OS);
+
+ if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S1PIE, IMP))
+ kvm->arch.fgu[HFGxTR_GROUP] |= (HFGxTR_EL2_nPIRE0_EL1 |
+ HFGxTR_EL2_nPIR_EL1);
+
+ if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, IMP))
+ kvm->arch.fgu[HAFGRTR_GROUP] |= ~(HAFGRTR_EL2_RES0 |
+ HAFGRTR_EL2_RES1);
+
+ set_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags);
+out:
+ mutex_unlock(&kvm->arch.config_lock);
+}
+
int __init kvm_sys_reg_table_init(void)
{
struct sys_reg_params params;
bool valid = true;
unsigned int i;
+ int ret = 0;
+
+ check_res_bits();
/* Make sure tables are unique and in order. */
valid &= check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs), false);
@@ -3943,6 +4119,7 @@ int __init kvm_sys_reg_table_init(void)
valid &= check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs), true);
valid &= check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs), true);
valid &= check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs), false);
+ valid &= check_sysreg_table(sys_insn_descs, ARRAY_SIZE(sys_insn_descs), false);
if (!valid)
return -EINVAL;
@@ -3957,8 +4134,13 @@ int __init kvm_sys_reg_table_init(void)
if (!first_idreg)
return -EINVAL;
- if (kvm_get_mode() == KVM_MODE_NV)
- return populate_nv_trap_config();
+ ret = populate_nv_trap_config();
- return 0;
+ for (i = 0; !ret && i < ARRAY_SIZE(sys_reg_descs); i++)
+ ret = populate_sysreg_config(sys_reg_descs + i, i);
+
+ for (i = 0; !ret && i < ARRAY_SIZE(sys_insn_descs); i++)
+ ret = populate_sysreg_config(sys_insn_descs + i, i);
+
+ return ret;
}
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index c65c129b3500..997eea21ba2a 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -233,6 +233,8 @@ int kvm_sys_reg_get_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg,
int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg,
const struct sys_reg_desc table[], unsigned int num);
+bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index);
+
#define AA32(_x) .aarch32_map = AA32_##_x
#define Op0(_x) .Op0 = _x
#define Op1(_x) .Op1 = _x
diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c
index 85606a531dc3..389025ce7749 100644
--- a/arch/arm64/kvm/vgic/vgic-debug.c
+++ b/arch/arm64/kvm/vgic/vgic-debug.c
@@ -149,7 +149,7 @@ static void print_dist_state(struct seq_file *s, struct vgic_dist *dist)
seq_printf(s, "vgic_model:\t%s\n", v3 ? "GICv3" : "GICv2");
seq_printf(s, "nr_spis:\t%d\n", dist->nr_spis);
if (v3)
- seq_printf(s, "nr_lpis:\t%d\n", dist->lpi_list_count);
+ seq_printf(s, "nr_lpis:\t%d\n", atomic_read(&dist->lpi_count));
seq_printf(s, "enabled:\t%d\n", dist->enabled);
seq_printf(s, "\n");
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index e949e1d0fd9f..f20941f83a07 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -53,9 +53,9 @@ void kvm_vgic_early_init(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
- INIT_LIST_HEAD(&dist->lpi_list_head);
INIT_LIST_HEAD(&dist->lpi_translation_cache);
raw_spin_lock_init(&dist->lpi_list_lock);
+ xa_init_flags(&dist->lpi_xa, XA_FLAGS_LOCK_IRQ);
}
/* CREATION */
@@ -309,7 +309,7 @@ int vgic_init(struct kvm *kvm)
vgic_lpi_translation_cache_init(kvm);
/*
- * If we have GICv4.1 enabled, unconditionnaly request enable the
+ * If we have GICv4.1 enabled, unconditionally request enable the
* v4 support so that we get HW-accelerated vSGIs. Otherwise, only
* enable it if we present a virtual ITS to the guest.
*/
@@ -366,6 +366,8 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm)
if (vgic_supports_direct_msis(kvm))
vgic_v4_teardown(kvm);
+
+ xa_destroy(&dist->lpi_xa);
}
static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -445,13 +447,15 @@ int vgic_lazy_init(struct kvm *kvm)
/* RESOURCE MAPPING */
/**
+ * kvm_vgic_map_resources - map the MMIO regions
+ * @kvm: kvm struct pointer
+ *
* Map the MMIO regions depending on the VGIC model exposed to the guest
* called on the first VCPU run.
* Also map the virtual CPU interface into the VM.
* v2 calls vgic_init() if not already done.
* v3 and derivatives return an error if the VGIC is not initialized.
* vgic_ready() returns true if this function has succeeded.
- * @kvm: kvm struct pointer
*/
int kvm_vgic_map_resources(struct kvm *kvm)
{
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 28a93074eca1..e85a495ada9c 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -52,7 +52,12 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
if (!irq)
return ERR_PTR(-ENOMEM);
- INIT_LIST_HEAD(&irq->lpi_list);
+ ret = xa_reserve_irq(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT);
+ if (ret) {
+ kfree(irq);
+ return ERR_PTR(ret);
+ }
+
INIT_LIST_HEAD(&irq->ap_list);
raw_spin_lock_init(&irq->irq_lock);
@@ -68,30 +73,30 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
* There could be a race with another vgic_add_lpi(), so we need to
* check that we don't add a second list entry with the same LPI.
*/
- list_for_each_entry(oldirq, &dist->lpi_list_head, lpi_list) {
- if (oldirq->intid != intid)
- continue;
-
+ oldirq = xa_load(&dist->lpi_xa, intid);
+ if (vgic_try_get_irq_kref(oldirq)) {
/* Someone was faster with adding this LPI, lets use that. */
kfree(irq);
irq = oldirq;
- /*
- * This increases the refcount, the caller is expected to
- * call vgic_put_irq() on the returned pointer once it's
- * finished with the IRQ.
- */
- vgic_get_irq_kref(irq);
+ goto out_unlock;
+ }
+ ret = xa_err(xa_store(&dist->lpi_xa, intid, irq, 0));
+ if (ret) {
+ xa_release(&dist->lpi_xa, intid);
+ kfree(irq);
goto out_unlock;
}
- list_add_tail(&irq->lpi_list, &dist->lpi_list_head);
- dist->lpi_list_count++;
+ atomic_inc(&dist->lpi_count);
out_unlock:
raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
+ if (ret)
+ return ERR_PTR(ret);
+
/*
* We "cache" the configuration table entries in our struct vgic_irq's.
* However we only have those structs for mapped IRQs, so we read in
@@ -158,7 +163,7 @@ struct vgic_translation_cache_entry {
* @cte_esz: collection table entry size
* @dte_esz: device table entry size
* @ite_esz: interrupt translation table entry size
- * @save tables: save the ITS tables into guest RAM
+ * @save_tables: save the ITS tables into guest RAM
* @restore_tables: restore the ITS internal structs from tables
* stored in guest RAM
* @commit: initialize the registers which expose the ABI settings,
@@ -311,6 +316,8 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
return 0;
}
+#define GIC_LPI_MAX_INTID ((1 << INTERRUPT_ID_BITS_ITS) - 1)
+
/*
* Create a snapshot of the current LPIs targeting @vcpu, so that we can
* enumerate those LPIs without holding any lock.
@@ -319,6 +326,7 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr)
{
struct vgic_dist *dist = &kvm->arch.vgic;
+ XA_STATE(xas, &dist->lpi_xa, GIC_LPI_OFFSET);
struct vgic_irq *irq;
unsigned long flags;
u32 *intids;
@@ -331,13 +339,15 @@ int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr)
* command). If coming from another path (such as enabling LPIs),
* we must be careful not to overrun the array.
*/
- irq_count = READ_ONCE(dist->lpi_list_count);
+ irq_count = atomic_read(&dist->lpi_count);
intids = kmalloc_array(irq_count, sizeof(intids[0]), GFP_KERNEL_ACCOUNT);
if (!intids)
return -ENOMEM;
raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
- list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
+ rcu_read_lock();
+
+ xas_for_each(&xas, irq, GIC_LPI_MAX_INTID) {
if (i == irq_count)
break;
/* We don't need to "get" the IRQ, as we hold the list lock. */
@@ -345,6 +355,8 @@ int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr)
continue;
intids[i++] = irq->intid;
}
+
+ rcu_read_unlock();
raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
*intid_ptr = intids;
@@ -595,8 +607,8 @@ static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db,
raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
irq = __vgic_its_check_cache(dist, db, devid, eventid);
- if (irq)
- vgic_get_irq_kref(irq);
+ if (!vgic_try_get_irq_kref(irq))
+ irq = NULL;
raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
@@ -640,8 +652,13 @@ static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its,
* was in the cache, and increment it on the new interrupt.
*/
if (cte->irq)
- __vgic_put_lpi_locked(kvm, cte->irq);
+ vgic_put_irq(kvm, cte->irq);
+ /*
+ * The irq refcount is guaranteed to be nonzero while holding the
+ * its_lock, as the ITE (and the reference it holds) cannot be freed.
+ */
+ lockdep_assert_held(&its->its_lock);
vgic_get_irq_kref(irq);
cte->db = db;
@@ -672,7 +689,7 @@ void vgic_its_invalidate_cache(struct kvm *kvm)
if (!cte->irq)
break;
- __vgic_put_lpi_locked(kvm, cte->irq);
+ vgic_put_irq(kvm, cte->irq);
cte->irq = NULL;
}
@@ -1345,8 +1362,8 @@ static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its,
}
/**
- * vgic_its_invall - invalidate all LPIs targetting a given vcpu
- * @vcpu: the vcpu for which the RD is targetted by an invalidation
+ * vgic_its_invall - invalidate all LPIs targeting a given vcpu
+ * @vcpu: the vcpu for which the RD is targeted by an invalidation
*
* Contrary to the INVALL command, this targets a RD instead of a
* collection, and we don't need to hold the its_lock, since no ITS is
@@ -2144,7 +2161,7 @@ static u32 compute_next_eventid_offset(struct list_head *h, struct its_ite *ite)
}
/**
- * entry_fn_t - Callback called on a table entry restore path
+ * typedef entry_fn_t - Callback called on a table entry restore path
* @its: its handle
* @id: id of the entry
* @entry: pointer to the entry
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 9465d3706ab9..4ea3340786b9 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -380,6 +380,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
struct vgic_irq *irq;
gpa_t last_ptr = ~(gpa_t)0;
bool vlpi_avail = false;
+ unsigned long index;
int ret = 0;
u8 val;
@@ -396,7 +397,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
vlpi_avail = true;
}
- list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
+ xa_for_each(&dist->lpi_xa, index, irq) {
int byte_offset, bit_nr;
struct kvm_vcpu *vcpu;
gpa_t pendbase, ptr;
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index db2a95762b1b..4ec93587c8cd 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -30,7 +30,8 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
* its->its_lock (mutex)
* vgic_cpu->ap_list_lock must be taken with IRQs disabled
* kvm->lpi_list_lock must be taken with IRQs disabled
- * vgic_irq->irq_lock must be taken with IRQs disabled
+ * vgic_dist->lpi_xa.xa_lock must be taken with IRQs disabled
+ * vgic_irq->irq_lock must be taken with IRQs disabled
*
* As the ap_list_lock might be taken from the timer interrupt handler,
* we have to disable IRQs before taking this lock and everything lower
@@ -54,32 +55,22 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
*/
/*
- * Iterate over the VM's list of mapped LPIs to find the one with a
- * matching interrupt ID and return a reference to the IRQ structure.
+ * Index the VM's xarray of mapped LPIs and return a reference to the IRQ
+ * structure. The caller is expected to call vgic_put_irq() later once it's
+ * finished with the IRQ.
*/
static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct vgic_irq *irq = NULL;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
- list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
- if (irq->intid != intid)
- continue;
+ rcu_read_lock();
- /*
- * This increases the refcount, the caller is expected to
- * call vgic_put_irq() later once it's finished with the IRQ.
- */
- vgic_get_irq_kref(irq);
- goto out_unlock;
- }
- irq = NULL;
+ irq = xa_load(&dist->lpi_xa, intid);
+ if (!vgic_try_get_irq_kref(irq))
+ irq = NULL;
-out_unlock:
- raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
+ rcu_read_unlock();
return irq;
}
@@ -120,22 +111,6 @@ static void vgic_irq_release(struct kref *ref)
{
}
-/*
- * Drop the refcount on the LPI. Must be called with lpi_list_lock held.
- */
-void __vgic_put_lpi_locked(struct kvm *kvm, struct vgic_irq *irq)
-{
- struct vgic_dist *dist = &kvm->arch.vgic;
-
- if (!kref_put(&irq->refcount, vgic_irq_release))
- return;
-
- list_del(&irq->lpi_list);
- dist->lpi_list_count--;
-
- kfree(irq);
-}
-
void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
{
struct vgic_dist *dist = &kvm->arch.vgic;
@@ -144,9 +119,15 @@ void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
if (irq->intid < VGIC_MIN_LPI)
return;
- raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
- __vgic_put_lpi_locked(kvm, irq);
- raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
+ if (!kref_put(&irq->refcount, vgic_irq_release))
+ return;
+
+ xa_lock_irqsave(&dist->lpi_xa, flags);
+ __xa_erase(&dist->lpi_xa, irq->intid);
+ xa_unlock_irqrestore(&dist->lpi_xa, flags);
+
+ atomic_dec(&dist->lpi_count);
+ kfree_rcu(irq, rcu);
}
void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu)
@@ -203,7 +184,7 @@ void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active)
}
/**
- * kvm_vgic_target_oracle - compute the target vcpu for an irq
+ * vgic_target_oracle - compute the target vcpu for an irq
*
* @irq: The irq to route. Must be already locked.
*
@@ -404,7 +385,8 @@ retry:
/*
* Grab a reference to the irq to reflect the fact that it is
- * now in the ap_list.
+ * now in the ap_list. This is safe as the caller must already hold a
+ * reference on the irq.
*/
vgic_get_irq_kref(irq);
list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head);
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 8d134569d0a1..0c2b82de8fa3 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -180,7 +180,6 @@ vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev,
gpa_t addr, int len);
struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
u32 intid);
-void __vgic_put_lpi_locked(struct kvm *kvm, struct vgic_irq *irq);
void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq);
bool vgic_get_phys_line_level(struct vgic_irq *irq);
void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending);
@@ -220,12 +219,20 @@ void vgic_v2_vmcr_sync(struct kvm_vcpu *vcpu);
void vgic_v2_save_state(struct kvm_vcpu *vcpu);
void vgic_v2_restore_state(struct kvm_vcpu *vcpu);
-static inline void vgic_get_irq_kref(struct vgic_irq *irq)
+static inline bool vgic_try_get_irq_kref(struct vgic_irq *irq)
{
+ if (!irq)
+ return false;
+
if (irq->intid < VGIC_MIN_LPI)
- return;
+ return true;
- kref_get(&irq->refcount);
+ return kref_get_unless_zero(&irq->refcount);
+}
+
+static inline void vgic_get_irq_kref(struct vgic_irq *irq)
+{
+ WARN_ON_ONCE(!vgic_try_get_irq_kref(irq));
}
void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index b912b1409fc0..65090dd34641 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -35,6 +35,7 @@ HAS_GENERIC_AUTH_IMP_DEF
HAS_GIC_CPUIF_SYSREGS
HAS_GIC_PRIO_MASKING
HAS_GIC_PRIO_RELAXED_SYNC
+HAS_HCR_NV1
HAS_HCX
HAS_LDAPR
HAS_LPA2
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index 4c9b67934367..53daaaef46cb 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -1366,6 +1366,7 @@ EndEnum
UnsignedEnum 43:40 SPECRES
0b0000 NI
0b0001 IMP
+ 0b0010 COSP_RCTX
EndEnum
UnsignedEnum 39:36 SB
0b0000 NI
@@ -1492,7 +1493,12 @@ EndEnum
EndSysreg
Sysreg ID_AA64ISAR3_EL1 3 0 0 6 3
-Res0 63:12
+Res0 63:16
+UnsignedEnum 15:12 PACM
+ 0b0000 NI
+ 0b0001 TRIVIAL_IMP
+ 0b0010 FULL_IMP
+EndEnum
UnsignedEnum 11:8 TLBIW
0b0000 NI
0b0001 IMP
@@ -1791,6 +1797,43 @@ UnsignedEnum 3:0 TCRX
EndEnum
EndSysreg
+Sysreg ID_AA64MMFR4_EL1 3 0 0 7 4
+Res0 63:40
+UnsignedEnum 39:36 E3DSE
+ 0b0000 NI
+ 0b0001 IMP
+EndEnum
+Res0 35:28
+SignedEnum 27:24 E2H0
+ 0b0000 IMP
+ 0b1110 NI_NV1
+ 0b1111 NI
+EndEnum
+UnsignedEnum 23:20 NV_frac
+ 0b0000 NV_NV2
+ 0b0001 NV2_ONLY
+EndEnum
+UnsignedEnum 19:16 FGWTE3
+ 0b0000 NI
+ 0b0001 IMP
+EndEnum
+UnsignedEnum 15:12 HACDBS
+ 0b0000 NI
+ 0b0001 IMP
+EndEnum
+UnsignedEnum 11:8 ASID2
+ 0b0000 NI
+ 0b0001 IMP
+EndEnum
+SignedEnum 7:4 EIESB
+ 0b0000 NI
+ 0b0001 ToEL3
+ 0b0010 ToELx
+ 0b1111 ANY
+EndEnum
+Res0 3:0
+EndSysreg
+
Sysreg SCTLR_EL1 3 0 1 0 0
Field 63 TIDCP
Field 62 SPINTMASK
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 23407fbd73c9..d32abe7fe6ab 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -2538,9 +2538,8 @@ void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_
vcpu->kvm->arch.kvm_ops->create_vcpu_debugfs(vcpu, debugfs_dentry);
}
-int kvm_arch_create_vm_debugfs(struct kvm *kvm)
+void kvm_arch_create_vm_debugfs(struct kvm *kvm)
{
if (kvm->arch.kvm_ops->create_vm_debugfs)
kvm->arch.kvm_ops->create_vm_debugfs(kvm);
- return 0;
}
diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index 95ea1a1f7403..999227fc7c66 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -189,9 +189,8 @@ static const struct file_operations mmu_rmaps_stat_fops = {
.release = kvm_mmu_rmaps_stat_release,
};
-int kvm_arch_create_vm_debugfs(struct kvm *kvm)
+void kvm_arch_create_vm_debugfs(struct kvm *kvm)
{
debugfs_create_file("mmu_rmaps_stat", 0644, kvm->debugfs_dentry, kvm,
&mmu_rmaps_stat_fops);
- return 0;
}