summaryrefslogtreecommitdiff
path: root/arch/riscv
diff options
context:
space:
mode:
Diffstat (limited to 'arch/riscv')
-rw-r--r--arch/riscv/include/asm/kvm_host.h10
-rw-r--r--arch/riscv/include/asm/kvm_nacl.h245
-rw-r--r--arch/riscv/include/asm/perf_event.h3
-rw-r--r--arch/riscv/include/asm/sbi.h120
-rw-r--r--arch/riscv/kernel/perf_callchain.c10
-rw-r--r--arch/riscv/kvm/Kconfig1
-rw-r--r--arch/riscv/kvm/Makefile27
-rw-r--r--arch/riscv/kvm/aia.c114
-rw-r--r--arch/riscv/kvm/aia_aplic.c3
-rw-r--r--arch/riscv/kvm/main.c63
-rw-r--r--arch/riscv/kvm/mmu.c13
-rw-r--r--arch/riscv/kvm/nacl.c152
-rw-r--r--arch/riscv/kvm/tlb.c57
-rw-r--r--arch/riscv/kvm/vcpu.c191
-rw-r--r--arch/riscv/kvm/vcpu_sbi.c11
-rw-r--r--arch/riscv/kvm/vcpu_switch.S137
-rw-r--r--arch/riscv/kvm/vcpu_timer.c28
17 files changed, 995 insertions, 190 deletions
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 2e2254fd2a2a..35eab6e0f4ae 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -286,6 +286,16 @@ struct kvm_vcpu_arch {
} sta;
};
+/*
+ * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event,
+ * arrived in guest context. For riscv, any event that arrives while a vCPU is
+ * loaded is considered to be "in guest".
+ */
+static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu)
+{
+ return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu;
+}
+
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
#define KVM_RISCV_GSTAGE_TLB_MIN_ORDER 12
diff --git a/arch/riscv/include/asm/kvm_nacl.h b/arch/riscv/include/asm/kvm_nacl.h
new file mode 100644
index 000000000000..4124d5e06a0f
--- /dev/null
+++ b/arch/riscv/include/asm/kvm_nacl.h
@@ -0,0 +1,245 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024 Ventana Micro Systems Inc.
+ */
+
+#ifndef __KVM_NACL_H
+#define __KVM_NACL_H
+
+#include <linux/jump_label.h>
+#include <linux/percpu.h>
+#include <asm/byteorder.h>
+#include <asm/csr.h>
+#include <asm/sbi.h>
+
+struct kvm_vcpu_arch;
+
+DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_available);
+#define kvm_riscv_nacl_available() \
+ static_branch_unlikely(&kvm_riscv_nacl_available)
+
+DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_csr_available);
+#define kvm_riscv_nacl_sync_csr_available() \
+ static_branch_unlikely(&kvm_riscv_nacl_sync_csr_available)
+
+DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_hfence_available);
+#define kvm_riscv_nacl_sync_hfence_available() \
+ static_branch_unlikely(&kvm_riscv_nacl_sync_hfence_available)
+
+DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_sret_available);
+#define kvm_riscv_nacl_sync_sret_available() \
+ static_branch_unlikely(&kvm_riscv_nacl_sync_sret_available)
+
+DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_autoswap_csr_available);
+#define kvm_riscv_nacl_autoswap_csr_available() \
+ static_branch_unlikely(&kvm_riscv_nacl_autoswap_csr_available)
+
+struct kvm_riscv_nacl {
+ void *shmem;
+ phys_addr_t shmem_phys;
+};
+DECLARE_PER_CPU(struct kvm_riscv_nacl, kvm_riscv_nacl);
+
+void __kvm_riscv_nacl_hfence(void *shmem,
+ unsigned long control,
+ unsigned long page_num,
+ unsigned long page_count);
+
+void __kvm_riscv_nacl_switch_to(struct kvm_vcpu_arch *vcpu_arch,
+ unsigned long sbi_ext_id,
+ unsigned long sbi_func_id);
+
+int kvm_riscv_nacl_enable(void);
+
+void kvm_riscv_nacl_disable(void);
+
+void kvm_riscv_nacl_exit(void);
+
+int kvm_riscv_nacl_init(void);
+
+#ifdef CONFIG_32BIT
+#define lelong_to_cpu(__x) le32_to_cpu(__x)
+#define cpu_to_lelong(__x) cpu_to_le32(__x)
+#else
+#define lelong_to_cpu(__x) le64_to_cpu(__x)
+#define cpu_to_lelong(__x) cpu_to_le64(__x)
+#endif
+
+#define nacl_shmem() \
+ this_cpu_ptr(&kvm_riscv_nacl)->shmem
+
+#define nacl_scratch_read_long(__shmem, __offset) \
+({ \
+ unsigned long *__p = (__shmem) + \
+ SBI_NACL_SHMEM_SCRATCH_OFFSET + \
+ (__offset); \
+ lelong_to_cpu(*__p); \
+})
+
+#define nacl_scratch_write_long(__shmem, __offset, __val) \
+do { \
+ unsigned long *__p = (__shmem) + \
+ SBI_NACL_SHMEM_SCRATCH_OFFSET + \
+ (__offset); \
+ *__p = cpu_to_lelong(__val); \
+} while (0)
+
+#define nacl_scratch_write_longs(__shmem, __offset, __array, __count) \
+do { \
+ unsigned int __i; \
+ unsigned long *__p = (__shmem) + \
+ SBI_NACL_SHMEM_SCRATCH_OFFSET + \
+ (__offset); \
+ for (__i = 0; __i < (__count); __i++) \
+ __p[__i] = cpu_to_lelong((__array)[__i]); \
+} while (0)
+
+#define nacl_sync_hfence(__e) \
+ sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SYNC_HFENCE, \
+ (__e), 0, 0, 0, 0, 0)
+
+#define nacl_hfence_mkconfig(__type, __order, __vmid, __asid) \
+({ \
+ unsigned long __c = SBI_NACL_SHMEM_HFENCE_CONFIG_PEND; \
+ __c |= ((__type) & SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_MASK) \
+ << SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_SHIFT; \
+ __c |= (((__order) - SBI_NACL_SHMEM_HFENCE_ORDER_BASE) & \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_MASK) \
+ << SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_SHIFT; \
+ __c |= ((__vmid) & SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_MASK) \
+ << SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_SHIFT; \
+ __c |= ((__asid) & SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_MASK); \
+ __c; \
+})
+
+#define nacl_hfence_mkpnum(__order, __addr) \
+ ((__addr) >> (__order))
+
+#define nacl_hfence_mkpcount(__order, __size) \
+ ((__size) >> (__order))
+
+#define nacl_hfence_gvma(__shmem, __gpa, __gpsz, __order) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA, \
+ __order, 0, 0), \
+ nacl_hfence_mkpnum(__order, __gpa), \
+ nacl_hfence_mkpcount(__order, __gpsz))
+
+#define nacl_hfence_gvma_all(__shmem) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_ALL, \
+ 0, 0, 0), 0, 0)
+
+#define nacl_hfence_gvma_vmid(__shmem, __vmid, __gpa, __gpsz, __order) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID, \
+ __order, __vmid, 0), \
+ nacl_hfence_mkpnum(__order, __gpa), \
+ nacl_hfence_mkpcount(__order, __gpsz))
+
+#define nacl_hfence_gvma_vmid_all(__shmem, __vmid) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID_ALL, \
+ 0, __vmid, 0), 0, 0)
+
+#define nacl_hfence_vvma(__shmem, __vmid, __gva, __gvsz, __order) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA, \
+ __order, __vmid, 0), \
+ nacl_hfence_mkpnum(__order, __gva), \
+ nacl_hfence_mkpcount(__order, __gvsz))
+
+#define nacl_hfence_vvma_all(__shmem, __vmid) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ALL, \
+ 0, __vmid, 0), 0, 0)
+
+#define nacl_hfence_vvma_asid(__shmem, __vmid, __asid, __gva, __gvsz, __order)\
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID, \
+ __order, __vmid, __asid), \
+ nacl_hfence_mkpnum(__order, __gva), \
+ nacl_hfence_mkpcount(__order, __gvsz))
+
+#define nacl_hfence_vvma_asid_all(__shmem, __vmid, __asid) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID_ALL, \
+ 0, __vmid, __asid), 0, 0)
+
+#define nacl_csr_read(__shmem, __csr) \
+({ \
+ unsigned long *__a = (__shmem) + SBI_NACL_SHMEM_CSR_OFFSET; \
+ lelong_to_cpu(__a[SBI_NACL_SHMEM_CSR_INDEX(__csr)]); \
+})
+
+#define nacl_csr_write(__shmem, __csr, __val) \
+do { \
+ void *__s = (__shmem); \
+ unsigned int __i = SBI_NACL_SHMEM_CSR_INDEX(__csr); \
+ unsigned long *__a = (__s) + SBI_NACL_SHMEM_CSR_OFFSET; \
+ u8 *__b = (__s) + SBI_NACL_SHMEM_DBITMAP_OFFSET; \
+ __a[__i] = cpu_to_lelong(__val); \
+ __b[__i >> 3] |= 1U << (__i & 0x7); \
+} while (0)
+
+#define nacl_csr_swap(__shmem, __csr, __val) \
+({ \
+ void *__s = (__shmem); \
+ unsigned int __i = SBI_NACL_SHMEM_CSR_INDEX(__csr); \
+ unsigned long *__a = (__s) + SBI_NACL_SHMEM_CSR_OFFSET; \
+ u8 *__b = (__s) + SBI_NACL_SHMEM_DBITMAP_OFFSET; \
+ unsigned long __r = lelong_to_cpu(__a[__i]); \
+ __a[__i] = cpu_to_lelong(__val); \
+ __b[__i >> 3] |= 1U << (__i & 0x7); \
+ __r; \
+})
+
+#define nacl_sync_csr(__csr) \
+ sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SYNC_CSR, \
+ (__csr), 0, 0, 0, 0, 0)
+
+/*
+ * Each ncsr_xyz() macro defined below has it's own static-branch so every
+ * use of ncsr_xyz() macro emits a patchable direct jump. This means multiple
+ * back-to-back ncsr_xyz() macro usage will emit multiple patchable direct
+ * jumps which is sub-optimal.
+ *
+ * Based on the above, it is recommended to avoid multiple back-to-back
+ * ncsr_xyz() macro usage.
+ */
+
+#define ncsr_read(__csr) \
+({ \
+ unsigned long __r; \
+ if (kvm_riscv_nacl_available()) \
+ __r = nacl_csr_read(nacl_shmem(), __csr); \
+ else \
+ __r = csr_read(__csr); \
+ __r; \
+})
+
+#define ncsr_write(__csr, __val) \
+do { \
+ if (kvm_riscv_nacl_sync_csr_available()) \
+ nacl_csr_write(nacl_shmem(), __csr, __val); \
+ else \
+ csr_write(__csr, __val); \
+} while (0)
+
+#define ncsr_swap(__csr, __val) \
+({ \
+ unsigned long __r; \
+ if (kvm_riscv_nacl_sync_csr_available()) \
+ __r = nacl_csr_swap(nacl_shmem(), __csr, __val); \
+ else \
+ __r = csr_swap(__csr, __val); \
+ __r; \
+})
+
+#define nsync_csr(__csr) \
+do { \
+ if (kvm_riscv_nacl_sync_csr_available()) \
+ nacl_sync_csr(__csr); \
+} while (0)
+
+#endif
diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h
index 665bbc9b2f84..bcc928fd3785 100644
--- a/arch/riscv/include/asm/perf_event.h
+++ b/arch/riscv/include/asm/perf_event.h
@@ -8,6 +8,7 @@
#ifndef _ASM_RISCV_PERF_EVENT_H
#define _ASM_RISCV_PERF_EVENT_H
+#ifdef CONFIG_PERF_EVENTS
#include <linux/perf_event.h>
#define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs
@@ -17,4 +18,6 @@
(regs)->sp = current_stack_pointer; \
(regs)->status = SR_PP; \
}
+#endif
+
#endif /* _ASM_RISCV_PERF_EVENT_H */
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index 98f631b051db..6c82318065cf 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -34,6 +34,7 @@ enum sbi_ext_id {
SBI_EXT_PMU = 0x504D55,
SBI_EXT_DBCN = 0x4442434E,
SBI_EXT_STA = 0x535441,
+ SBI_EXT_NACL = 0x4E41434C,
/* Experimentals extensions must lie within this range */
SBI_EXT_EXPERIMENTAL_START = 0x08000000,
@@ -281,6 +282,125 @@ struct sbi_sta_struct {
#define SBI_SHMEM_DISABLE -1
+enum sbi_ext_nacl_fid {
+ SBI_EXT_NACL_PROBE_FEATURE = 0x0,
+ SBI_EXT_NACL_SET_SHMEM = 0x1,
+ SBI_EXT_NACL_SYNC_CSR = 0x2,
+ SBI_EXT_NACL_SYNC_HFENCE = 0x3,
+ SBI_EXT_NACL_SYNC_SRET = 0x4,
+};
+
+enum sbi_ext_nacl_feature {
+ SBI_NACL_FEAT_SYNC_CSR = 0x0,
+ SBI_NACL_FEAT_SYNC_HFENCE = 0x1,
+ SBI_NACL_FEAT_SYNC_SRET = 0x2,
+ SBI_NACL_FEAT_AUTOSWAP_CSR = 0x3,
+};
+
+#define SBI_NACL_SHMEM_ADDR_SHIFT 12
+#define SBI_NACL_SHMEM_SCRATCH_OFFSET 0x0000
+#define SBI_NACL_SHMEM_SCRATCH_SIZE 0x1000
+#define SBI_NACL_SHMEM_SRET_OFFSET 0x0000
+#define SBI_NACL_SHMEM_SRET_SIZE 0x0200
+#define SBI_NACL_SHMEM_AUTOSWAP_OFFSET (SBI_NACL_SHMEM_SRET_OFFSET + \
+ SBI_NACL_SHMEM_SRET_SIZE)
+#define SBI_NACL_SHMEM_AUTOSWAP_SIZE 0x0080
+#define SBI_NACL_SHMEM_UNUSED_OFFSET (SBI_NACL_SHMEM_AUTOSWAP_OFFSET + \
+ SBI_NACL_SHMEM_AUTOSWAP_SIZE)
+#define SBI_NACL_SHMEM_UNUSED_SIZE 0x0580
+#define SBI_NACL_SHMEM_HFENCE_OFFSET (SBI_NACL_SHMEM_UNUSED_OFFSET + \
+ SBI_NACL_SHMEM_UNUSED_SIZE)
+#define SBI_NACL_SHMEM_HFENCE_SIZE 0x0780
+#define SBI_NACL_SHMEM_DBITMAP_OFFSET (SBI_NACL_SHMEM_HFENCE_OFFSET + \
+ SBI_NACL_SHMEM_HFENCE_SIZE)
+#define SBI_NACL_SHMEM_DBITMAP_SIZE 0x0080
+#define SBI_NACL_SHMEM_CSR_OFFSET (SBI_NACL_SHMEM_DBITMAP_OFFSET + \
+ SBI_NACL_SHMEM_DBITMAP_SIZE)
+#define SBI_NACL_SHMEM_CSR_SIZE ((__riscv_xlen / 8) * 1024)
+#define SBI_NACL_SHMEM_SIZE (SBI_NACL_SHMEM_CSR_OFFSET + \
+ SBI_NACL_SHMEM_CSR_SIZE)
+
+#define SBI_NACL_SHMEM_CSR_INDEX(__csr_num) \
+ ((((__csr_num) & 0xc00) >> 2) | ((__csr_num) & 0xff))
+
+#define SBI_NACL_SHMEM_HFENCE_ENTRY_SZ ((__riscv_xlen / 8) * 4)
+#define SBI_NACL_SHMEM_HFENCE_ENTRY_MAX \
+ (SBI_NACL_SHMEM_HFENCE_SIZE / \
+ SBI_NACL_SHMEM_HFENCE_ENTRY_SZ)
+#define SBI_NACL_SHMEM_HFENCE_ENTRY(__num) \
+ (SBI_NACL_SHMEM_HFENCE_OFFSET + \
+ (__num) * SBI_NACL_SHMEM_HFENCE_ENTRY_SZ)
+#define SBI_NACL_SHMEM_HFENCE_ENTRY_CONFIG(__num) \
+ SBI_NACL_SHMEM_HFENCE_ENTRY(__num)
+#define SBI_NACL_SHMEM_HFENCE_ENTRY_PNUM(__num)\
+ (SBI_NACL_SHMEM_HFENCE_ENTRY(__num) + (__riscv_xlen / 8))
+#define SBI_NACL_SHMEM_HFENCE_ENTRY_PCOUNT(__num)\
+ (SBI_NACL_SHMEM_HFENCE_ENTRY(__num) + \
+ ((__riscv_xlen / 8) * 3))
+
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_BITS 1
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_SHIFT \
+ (__riscv_xlen - SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_BITS)
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_MASK \
+ ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_BITS) - 1)
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND \
+ (SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_MASK << \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_SHIFT)
+
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_BITS 3
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_SHIFT \
+ (SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_SHIFT - \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_BITS)
+
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_BITS 4
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_SHIFT \
+ (SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_SHIFT - \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_BITS)
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_MASK \
+ ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_BITS) - 1)
+
+#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA 0x0
+#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_ALL 0x1
+#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID 0x2
+#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID_ALL 0x3
+#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA 0x4
+#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ALL 0x5
+#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID 0x6
+#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID_ALL 0x7
+
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_BITS 1
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_SHIFT \
+ (SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_SHIFT - \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_BITS)
+
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_BITS 7
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_SHIFT \
+ (SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_SHIFT - \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_BITS)
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_MASK \
+ ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_BITS) - 1)
+#define SBI_NACL_SHMEM_HFENCE_ORDER_BASE 12
+
+#if __riscv_xlen == 32
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS 9
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_BITS 7
+#else
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS 16
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_BITS 14
+#endif
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_SHIFT \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_MASK \
+ ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS) - 1)
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_MASK \
+ ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_BITS) - 1)
+
+#define SBI_NACL_SHMEM_AUTOSWAP_FLAG_HSTATUS BIT(0)
+#define SBI_NACL_SHMEM_AUTOSWAP_HSTATUS ((__riscv_xlen / 8) * 1)
+
+#define SBI_NACL_SHMEM_SRET_X(__i) ((__riscv_xlen / 8) * (__i))
+#define SBI_NACL_SHMEM_SRET_X_LAST 31
+
/* SBI spec version fields */
#define SBI_SPEC_VERSION_DEFAULT 0x1
#define SBI_SPEC_VERSION_MAJOR_SHIFT 24
diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c
index c7468af77c66..b465bc9eb870 100644
--- a/arch/riscv/kernel/perf_callchain.c
+++ b/arch/riscv/kernel/perf_callchain.c
@@ -28,11 +28,21 @@ static bool fill_callchain(void *entry, unsigned long pc)
void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
+ if (perf_guest_state()) {
+ /* TODO: We don't support guest os callchain now */
+ return;
+ }
+
arch_stack_walk_user(fill_callchain, entry, regs);
}
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
+ if (perf_guest_state()) {
+ /* TODO: We don't support guest os callchain now */
+ return;
+ }
+
walk_stackframe(NULL, regs, fill_callchain, entry);
}
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index 26d1727f0550..0c3cbb0915ff 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -32,6 +32,7 @@ config KVM
select KVM_XFER_TO_GUEST_WORK
select KVM_GENERIC_MMU_NOTIFIER
select SCHED_INFO
+ select GUEST_PERF_EVENTS if PERF_EVENTS
help
Support hosting virtualized guest machines.
diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile
index c2cacfbc06a0..0fb1840c3e0a 100644
--- a/arch/riscv/kvm/Makefile
+++ b/arch/riscv/kvm/Makefile
@@ -9,27 +9,30 @@ include $(srctree)/virt/kvm/Makefile.kvm
obj-$(CONFIG_KVM) += kvm.o
+# Ordered alphabetically
+kvm-y += aia.o
+kvm-y += aia_aplic.o
+kvm-y += aia_device.o
+kvm-y += aia_imsic.o
kvm-y += main.o
-kvm-y += vm.o
-kvm-y += vmid.o
-kvm-y += tlb.o
kvm-y += mmu.o
+kvm-y += nacl.o
+kvm-y += tlb.o
kvm-y += vcpu.o
kvm-y += vcpu_exit.o
kvm-y += vcpu_fp.o
-kvm-y += vcpu_vector.o
kvm-y += vcpu_insn.o
kvm-y += vcpu_onereg.o
-kvm-y += vcpu_switch.o
+kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_pmu.o
kvm-y += vcpu_sbi.o
-kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o
kvm-y += vcpu_sbi_base.o
-kvm-y += vcpu_sbi_replace.o
kvm-y += vcpu_sbi_hsm.o
+kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_sbi_pmu.o
+kvm-y += vcpu_sbi_replace.o
kvm-y += vcpu_sbi_sta.o
+kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o
+kvm-y += vcpu_switch.o
kvm-y += vcpu_timer.o
-kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_pmu.o vcpu_sbi_pmu.o
-kvm-y += aia.o
-kvm-y += aia_device.o
-kvm-y += aia_aplic.o
-kvm-y += aia_imsic.o
+kvm-y += vcpu_vector.o
+kvm-y += vm.o
+kvm-y += vmid.o
diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c
index 2967d305c442..dcced4db7fe8 100644
--- a/arch/riscv/kvm/aia.c
+++ b/arch/riscv/kvm/aia.c
@@ -16,6 +16,7 @@
#include <linux/percpu.h>
#include <linux/spinlock.h>
#include <asm/cpufeature.h>
+#include <asm/kvm_nacl.h>
struct aia_hgei_control {
raw_spinlock_t lock;
@@ -51,7 +52,7 @@ static int aia_find_hgei(struct kvm_vcpu *owner)
return hgei;
}
-static void aia_set_hvictl(bool ext_irq_pending)
+static inline unsigned long aia_hvictl_value(bool ext_irq_pending)
{
unsigned long hvictl;
@@ -62,7 +63,7 @@ static void aia_set_hvictl(bool ext_irq_pending)
hvictl = (IRQ_S_EXT << HVICTL_IID_SHIFT) & HVICTL_IID;
hvictl |= ext_irq_pending;
- csr_write(CSR_HVICTL, hvictl);
+ return hvictl;
}
#ifdef CONFIG_32BIT
@@ -88,7 +89,7 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu)
struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
if (kvm_riscv_aia_available())
- csr->vsieh = csr_read(CSR_VSIEH);
+ csr->vsieh = ncsr_read(CSR_VSIEH);
}
#endif
@@ -115,7 +116,7 @@ bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask)
hgei = aia_find_hgei(vcpu);
if (hgei > 0)
- return !!(csr_read(CSR_HGEIP) & BIT(hgei));
+ return !!(ncsr_read(CSR_HGEIP) & BIT(hgei));
return false;
}
@@ -128,45 +129,73 @@ void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu)
return;
#ifdef CONFIG_32BIT
- csr_write(CSR_HVIPH, vcpu->arch.aia_context.guest_csr.hviph);
+ ncsr_write(CSR_HVIPH, vcpu->arch.aia_context.guest_csr.hviph);
#endif
- aia_set_hvictl(!!(csr->hvip & BIT(IRQ_VS_EXT)));
+ ncsr_write(CSR_HVICTL, aia_hvictl_value(!!(csr->hvip & BIT(IRQ_VS_EXT))));
}
void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu)
{
struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
+ void *nsh;
if (!kvm_riscv_aia_available())
return;
- csr_write(CSR_VSISELECT, csr->vsiselect);
- csr_write(CSR_HVIPRIO1, csr->hviprio1);
- csr_write(CSR_HVIPRIO2, csr->hviprio2);
+ if (kvm_riscv_nacl_sync_csr_available()) {
+ nsh = nacl_shmem();
+ nacl_csr_write(nsh, CSR_VSISELECT, csr->vsiselect);
+ nacl_csr_write(nsh, CSR_HVIPRIO1, csr->hviprio1);
+ nacl_csr_write(nsh, CSR_HVIPRIO2, csr->hviprio2);
+#ifdef CONFIG_32BIT
+ nacl_csr_write(nsh, CSR_VSIEH, csr->vsieh);
+ nacl_csr_write(nsh, CSR_HVIPH, csr->hviph);
+ nacl_csr_write(nsh, CSR_HVIPRIO1H, csr->hviprio1h);
+ nacl_csr_write(nsh, CSR_HVIPRIO2H, csr->hviprio2h);
+#endif
+ } else {
+ csr_write(CSR_VSISELECT, csr->vsiselect);
+ csr_write(CSR_HVIPRIO1, csr->hviprio1);
+ csr_write(CSR_HVIPRIO2, csr->hviprio2);
#ifdef CONFIG_32BIT
- csr_write(CSR_VSIEH, csr->vsieh);
- csr_write(CSR_HVIPH, csr->hviph);
- csr_write(CSR_HVIPRIO1H, csr->hviprio1h);
- csr_write(CSR_HVIPRIO2H, csr->hviprio2h);
+ csr_write(CSR_VSIEH, csr->vsieh);
+ csr_write(CSR_HVIPH, csr->hviph);
+ csr_write(CSR_HVIPRIO1H, csr->hviprio1h);
+ csr_write(CSR_HVIPRIO2H, csr->hviprio2h);
#endif
+ }
}
void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu)
{
struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
+ void *nsh;
if (!kvm_riscv_aia_available())
return;
- csr->vsiselect = csr_read(CSR_VSISELECT);
- csr->hviprio1 = csr_read(CSR_HVIPRIO1);
- csr->hviprio2 = csr_read(CSR_HVIPRIO2);
+ if (kvm_riscv_nacl_available()) {
+ nsh = nacl_shmem();
+ csr->vsiselect = nacl_csr_read(nsh, CSR_VSISELECT);
+ csr->hviprio1 = nacl_csr_read(nsh, CSR_HVIPRIO1);
+ csr->hviprio2 = nacl_csr_read(nsh, CSR_HVIPRIO2);
#ifdef CONFIG_32BIT
- csr->vsieh = csr_read(CSR_VSIEH);
- csr->hviph = csr_read(CSR_HVIPH);
- csr->hviprio1h = csr_read(CSR_HVIPRIO1H);
- csr->hviprio2h = csr_read(CSR_HVIPRIO2H);
+ csr->vsieh = nacl_csr_read(nsh, CSR_VSIEH);
+ csr->hviph = nacl_csr_read(nsh, CSR_HVIPH);
+ csr->hviprio1h = nacl_csr_read(nsh, CSR_HVIPRIO1H);
+ csr->hviprio2h = nacl_csr_read(nsh, CSR_HVIPRIO2H);
#endif
+ } else {
+ csr->vsiselect = csr_read(CSR_VSISELECT);
+ csr->hviprio1 = csr_read(CSR_HVIPRIO1);
+ csr->hviprio2 = csr_read(CSR_HVIPRIO2);
+#ifdef CONFIG_32BIT
+ csr->vsieh = csr_read(CSR_VSIEH);
+ csr->hviph = csr_read(CSR_HVIPH);
+ csr->hviprio1h = csr_read(CSR_HVIPRIO1H);
+ csr->hviprio2h = csr_read(CSR_HVIPRIO2H);
+#endif
+ }
}
int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu,
@@ -250,20 +279,20 @@ static u8 aia_get_iprio8(struct kvm_vcpu *vcpu, unsigned int irq)
switch (bitpos / BITS_PER_LONG) {
case 0:
- hviprio = csr_read(CSR_HVIPRIO1);
+ hviprio = ncsr_read(CSR_HVIPRIO1);
break;
case 1:
#ifndef CONFIG_32BIT
- hviprio = csr_read(CSR_HVIPRIO2);
+ hviprio = ncsr_read(CSR_HVIPRIO2);
break;
#else
- hviprio = csr_read(CSR_HVIPRIO1H);
+ hviprio = ncsr_read(CSR_HVIPRIO1H);
break;
case 2:
- hviprio = csr_read(CSR_HVIPRIO2);
+ hviprio = ncsr_read(CSR_HVIPRIO2);
break;
case 3:
- hviprio = csr_read(CSR_HVIPRIO2H);
+ hviprio = ncsr_read(CSR_HVIPRIO2H);
break;
#endif
default:
@@ -283,20 +312,20 @@ static void aia_set_iprio8(struct kvm_vcpu *vcpu, unsigned int irq, u8 prio)
switch (bitpos / BITS_PER_LONG) {
case 0:
- hviprio = csr_read(CSR_HVIPRIO1);
+ hviprio = ncsr_read(CSR_HVIPRIO1);
break;
case 1:
#ifndef CONFIG_32BIT
- hviprio = csr_read(CSR_HVIPRIO2);
+ hviprio = ncsr_read(CSR_HVIPRIO2);
break;
#else
- hviprio = csr_read(CSR_HVIPRIO1H);
+ hviprio = ncsr_read(CSR_HVIPRIO1H);
break;
case 2:
- hviprio = csr_read(CSR_HVIPRIO2);
+ hviprio = ncsr_read(CSR_HVIPRIO2);
break;
case 3:
- hviprio = csr_read(CSR_HVIPRIO2H);
+ hviprio = ncsr_read(CSR_HVIPRIO2H);
break;
#endif
default:
@@ -308,20 +337,20 @@ static void aia_set_iprio8(struct kvm_vcpu *vcpu, unsigned int irq, u8 prio)
switch (bitpos / BITS_PER_LONG) {
case 0:
- csr_write(CSR_HVIPRIO1, hviprio);
+ ncsr_write(CSR_HVIPRIO1, hviprio);
break;
case 1:
#ifndef CONFIG_32BIT
- csr_write(CSR_HVIPRIO2, hviprio);
+ ncsr_write(CSR_HVIPRIO2, hviprio);
break;
#else
- csr_write(CSR_HVIPRIO1H, hviprio);
+ ncsr_write(CSR_HVIPRIO1H, hviprio);
break;
case 2:
- csr_write(CSR_HVIPRIO2, hviprio);
+ ncsr_write(CSR_HVIPRIO2, hviprio);
break;
case 3:
- csr_write(CSR_HVIPRIO2H, hviprio);
+ ncsr_write(CSR_HVIPRIO2H, hviprio);
break;
#endif
default:
@@ -377,7 +406,7 @@ int kvm_riscv_vcpu_aia_rmw_ireg(struct kvm_vcpu *vcpu, unsigned int csr_num,
return KVM_INSN_ILLEGAL_TRAP;
/* First try to emulate in kernel space */
- isel = csr_read(CSR_VSISELECT) & ISELECT_MASK;
+ isel = ncsr_read(CSR_VSISELECT) & ISELECT_MASK;
if (isel >= ISELECT_IPRIO0 && isel <= ISELECT_IPRIO15)
return aia_rmw_iprio(vcpu, isel, val, new_val, wr_mask);
else if (isel >= IMSIC_FIRST && isel <= IMSIC_LAST &&
@@ -499,6 +528,10 @@ static int aia_hgei_init(void)
hgctrl->free_bitmap = 0;
}
+ /* Skip SGEI interrupt setup for zero guest external interrupts */
+ if (!kvm_riscv_aia_nr_hgei)
+ goto skip_sgei_interrupt;
+
/* Find INTC irq domain */
domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(),
DOMAIN_BUS_ANY);
@@ -522,11 +555,16 @@ static int aia_hgei_init(void)
return rc;
}
+skip_sgei_interrupt:
return 0;
}
static void aia_hgei_exit(void)
{
+ /* Do nothing for zero guest external interrupts */
+ if (!kvm_riscv_aia_nr_hgei)
+ return;
+
/* Free per-CPU SGEI interrupt */
free_percpu_irq(hgei_parent_irq, &aia_hgei);
}
@@ -536,7 +574,7 @@ void kvm_riscv_aia_enable(void)
if (!kvm_riscv_aia_available())
return;
- aia_set_hvictl(false);
+ csr_write(CSR_HVICTL, aia_hvictl_value(false));
csr_write(CSR_HVIPRIO1, 0x0);
csr_write(CSR_HVIPRIO2, 0x0);
#ifdef CONFIG_32BIT
@@ -572,7 +610,7 @@ void kvm_riscv_aia_disable(void)
csr_clear(CSR_HIE, BIT(IRQ_S_GEXT));
disable_percpu_irq(hgei_parent_irq);
- aia_set_hvictl(false);
+ csr_write(CSR_HVICTL, aia_hvictl_value(false));
raw_spin_lock_irqsave(&hgctrl->lock, flags);
diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c
index da6ff1bade0d..f59d1c0c8c43 100644
--- a/arch/riscv/kvm/aia_aplic.c
+++ b/arch/riscv/kvm/aia_aplic.c
@@ -143,7 +143,7 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending)
if (sm == APLIC_SOURCECFG_SM_LEVEL_HIGH ||
sm == APLIC_SOURCECFG_SM_LEVEL_LOW) {
if (!pending)
- goto skip_write_pending;
+ goto noskip_write_pending;
if ((irqd->state & APLIC_IRQ_STATE_INPUT) &&
sm == APLIC_SOURCECFG_SM_LEVEL_LOW)
goto skip_write_pending;
@@ -152,6 +152,7 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending)
goto skip_write_pending;
}
+noskip_write_pending:
if (pending)
irqd->state |= APLIC_IRQ_STATE_PENDING;
else
diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c
index f3427f6de608..1fa8be5ee509 100644
--- a/arch/riscv/kvm/main.c
+++ b/arch/riscv/kvm/main.c
@@ -10,8 +10,8 @@
#include <linux/err.h>
#include <linux/module.h>
#include <linux/kvm_host.h>
-#include <asm/csr.h>
#include <asm/cpufeature.h>
+#include <asm/kvm_nacl.h>
#include <asm/sbi.h>
long kvm_arch_dev_ioctl(struct file *filp,
@@ -22,6 +22,12 @@ long kvm_arch_dev_ioctl(struct file *filp,
int kvm_arch_enable_virtualization_cpu(void)
{
+ int rc;
+
+ rc = kvm_riscv_nacl_enable();
+ if (rc)
+ return rc;
+
csr_write(CSR_HEDELEG, KVM_HEDELEG_DEFAULT);
csr_write(CSR_HIDELEG, KVM_HIDELEG_DEFAULT);
@@ -49,11 +55,21 @@ void kvm_arch_disable_virtualization_cpu(void)
csr_write(CSR_HVIP, 0);
csr_write(CSR_HEDELEG, 0);
csr_write(CSR_HIDELEG, 0);
+
+ kvm_riscv_nacl_disable();
+}
+
+static void kvm_riscv_teardown(void)
+{
+ kvm_riscv_aia_exit();
+ kvm_riscv_nacl_exit();
+ kvm_unregister_perf_callbacks();
}
static int __init riscv_kvm_init(void)
{
int rc;
+ char slist[64];
const char *str;
if (!riscv_isa_extension_available(NULL, h)) {
@@ -71,16 +87,53 @@ static int __init riscv_kvm_init(void)
return -ENODEV;
}
+ rc = kvm_riscv_nacl_init();
+ if (rc && rc != -ENODEV)
+ return rc;
+
kvm_riscv_gstage_mode_detect();
kvm_riscv_gstage_vmid_detect();
rc = kvm_riscv_aia_init();
- if (rc && rc != -ENODEV)
+ if (rc && rc != -ENODEV) {
+ kvm_riscv_nacl_exit();
return rc;
+ }
kvm_info("hypervisor extension available\n");
+ if (kvm_riscv_nacl_available()) {
+ rc = 0;
+ slist[0] = '\0';
+ if (kvm_riscv_nacl_sync_csr_available()) {
+ if (rc)
+ strcat(slist, ", ");
+ strcat(slist, "sync_csr");
+ rc++;
+ }
+ if (kvm_riscv_nacl_sync_hfence_available()) {
+ if (rc)
+ strcat(slist, ", ");
+ strcat(slist, "sync_hfence");
+ rc++;
+ }
+ if (kvm_riscv_nacl_sync_sret_available()) {
+ if (rc)
+ strcat(slist, ", ");
+ strcat(slist, "sync_sret");
+ rc++;
+ }
+ if (kvm_riscv_nacl_autoswap_csr_available()) {
+ if (rc)
+ strcat(slist, ", ");
+ strcat(slist, "autoswap_csr");
+ rc++;
+ }
+ kvm_info("using SBI nested acceleration with %s\n",
+ (rc) ? slist : "no features");
+ }
+
switch (kvm_riscv_gstage_mode()) {
case HGATP_MODE_SV32X4:
str = "Sv32x4";
@@ -105,9 +158,11 @@ static int __init riscv_kvm_init(void)
kvm_info("AIA available with %d guest external interrupts\n",
kvm_riscv_aia_nr_hgei);
+ kvm_register_perf_callbacks(NULL);
+
rc = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE);
if (rc) {
- kvm_riscv_aia_exit();
+ kvm_riscv_teardown();
return rc;
}
@@ -117,7 +172,7 @@ module_init(riscv_kvm_init);
static void __exit riscv_kvm_exit(void)
{
- kvm_riscv_aia_exit();
+ kvm_riscv_teardown();
kvm_exit();
}
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index b63650f9b966..1087ea74567b 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -15,7 +15,7 @@
#include <linux/vmalloc.h>
#include <linux/kvm_host.h>
#include <linux/sched/signal.h>
-#include <asm/csr.h>
+#include <asm/kvm_nacl.h>
#include <asm/page.h>
#include <asm/pgtable.h>
@@ -601,6 +601,7 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
bool logging = (memslot->dirty_bitmap &&
!(memslot->flags & KVM_MEM_READONLY)) ? true : false;
unsigned long vma_pagesize, mmu_seq;
+ struct page *page;
/* We need minimum second+third level pages */
ret = kvm_mmu_topup_memory_cache(pcache, gstage_pgd_levels);
@@ -631,7 +632,7 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
/*
* Read mmu_invalidate_seq so that KVM can detect if the results of
- * vma_lookup() or gfn_to_pfn_prot() become stale priort to acquiring
+ * vma_lookup() or __kvm_faultin_pfn() become stale prior to acquiring
* kvm->mmu_lock.
*
* Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs
@@ -647,7 +648,7 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
return -EFAULT;
}
- hfn = gfn_to_pfn_prot(kvm, gfn, is_write, &writable);
+ hfn = kvm_faultin_pfn(vcpu, gfn, is_write, &writable, &page);
if (hfn == KVM_PFN_ERR_HWPOISON) {
send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva,
vma_pageshift, current);
@@ -669,7 +670,6 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
goto out_unlock;
if (writable) {
- kvm_set_pfn_dirty(hfn);
mark_page_dirty(kvm, gfn);
ret = gstage_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT,
vma_pagesize, false, true);
@@ -682,9 +682,8 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
kvm_err("Failed to map in G-stage\n");
out_unlock:
+ kvm_release_faultin_page(kvm, page, ret && ret != -EEXIST, writable);
spin_unlock(&kvm->mmu_lock);
- kvm_set_pfn_accessed(hfn);
- kvm_release_pfn_clean(hfn);
return ret;
}
@@ -732,7 +731,7 @@ void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu)
hgatp |= (READ_ONCE(k->vmid.vmid) << HGATP_VMID_SHIFT) & HGATP_VMID;
hgatp |= (k->pgd_phys >> PAGE_SHIFT) & HGATP_PPN;
- csr_write(CSR_HGATP, hgatp);
+ ncsr_write(CSR_HGATP, hgatp);
if (!kvm_riscv_gstage_vmid_bits())
kvm_riscv_local_hfence_gvma_all();
diff --git a/arch/riscv/kvm/nacl.c b/arch/riscv/kvm/nacl.c
new file mode 100644
index 000000000000..08a95ad9ada2
--- /dev/null
+++ b/arch/riscv/kvm/nacl.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2024 Ventana Micro Systems Inc.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/vmalloc.h>
+#include <asm/kvm_nacl.h>
+
+DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_available);
+DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_csr_available);
+DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_hfence_available);
+DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_sret_available);
+DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_autoswap_csr_available);
+DEFINE_PER_CPU(struct kvm_riscv_nacl, kvm_riscv_nacl);
+
+void __kvm_riscv_nacl_hfence(void *shmem,
+ unsigned long control,
+ unsigned long page_num,
+ unsigned long page_count)
+{
+ int i, ent = -1, try_count = 5;
+ unsigned long *entp;
+
+again:
+ for (i = 0; i < SBI_NACL_SHMEM_HFENCE_ENTRY_MAX; i++) {
+ entp = shmem + SBI_NACL_SHMEM_HFENCE_ENTRY_CONFIG(i);
+ if (lelong_to_cpu(*entp) & SBI_NACL_SHMEM_HFENCE_CONFIG_PEND)
+ continue;
+
+ ent = i;
+ break;
+ }
+
+ if (ent < 0) {
+ if (try_count) {
+ nacl_sync_hfence(-1UL);
+ goto again;
+ } else {
+ pr_warn("KVM: No free entry in NACL shared memory\n");
+ return;
+ }
+ }
+
+ entp = shmem + SBI_NACL_SHMEM_HFENCE_ENTRY_CONFIG(i);
+ *entp = cpu_to_lelong(control);
+ entp = shmem + SBI_NACL_SHMEM_HFENCE_ENTRY_PNUM(i);
+ *entp = cpu_to_lelong(page_num);
+ entp = shmem + SBI_NACL_SHMEM_HFENCE_ENTRY_PCOUNT(i);
+ *entp = cpu_to_lelong(page_count);
+}
+
+int kvm_riscv_nacl_enable(void)
+{
+ int rc;
+ struct sbiret ret;
+ struct kvm_riscv_nacl *nacl;
+
+ if (!kvm_riscv_nacl_available())
+ return 0;
+ nacl = this_cpu_ptr(&kvm_riscv_nacl);
+
+ ret = sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SET_SHMEM,
+ nacl->shmem_phys, 0, 0, 0, 0, 0);
+ rc = sbi_err_map_linux_errno(ret.error);
+ if (rc)
+ return rc;
+
+ return 0;
+}
+
+void kvm_riscv_nacl_disable(void)
+{
+ if (!kvm_riscv_nacl_available())
+ return;
+
+ sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SET_SHMEM,
+ SBI_SHMEM_DISABLE, SBI_SHMEM_DISABLE, 0, 0, 0, 0);
+}
+
+void kvm_riscv_nacl_exit(void)
+{
+ int cpu;
+ struct kvm_riscv_nacl *nacl;
+
+ if (!kvm_riscv_nacl_available())
+ return;
+
+ /* Allocate per-CPU shared memory */
+ for_each_possible_cpu(cpu) {
+ nacl = per_cpu_ptr(&kvm_riscv_nacl, cpu);
+ if (!nacl->shmem)
+ continue;
+
+ free_pages((unsigned long)nacl->shmem,
+ get_order(SBI_NACL_SHMEM_SIZE));
+ nacl->shmem = NULL;
+ nacl->shmem_phys = 0;
+ }
+}
+
+static long nacl_probe_feature(long feature_id)
+{
+ struct sbiret ret;
+
+ if (!kvm_riscv_nacl_available())
+ return 0;
+
+ ret = sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_PROBE_FEATURE,
+ feature_id, 0, 0, 0, 0, 0);
+ return ret.value;
+}
+
+int kvm_riscv_nacl_init(void)
+{
+ int cpu;
+ struct page *shmem_page;
+ struct kvm_riscv_nacl *nacl;
+
+ if (sbi_spec_version < sbi_mk_version(1, 0) ||
+ sbi_probe_extension(SBI_EXT_NACL) <= 0)
+ return -ENODEV;
+
+ /* Enable NACL support */
+ static_branch_enable(&kvm_riscv_nacl_available);
+
+ /* Probe NACL features */
+ if (nacl_probe_feature(SBI_NACL_FEAT_SYNC_CSR))
+ static_branch_enable(&kvm_riscv_nacl_sync_csr_available);
+ if (nacl_probe_feature(SBI_NACL_FEAT_SYNC_HFENCE))
+ static_branch_enable(&kvm_riscv_nacl_sync_hfence_available);
+ if (nacl_probe_feature(SBI_NACL_FEAT_SYNC_SRET))
+ static_branch_enable(&kvm_riscv_nacl_sync_sret_available);
+ if (nacl_probe_feature(SBI_NACL_FEAT_AUTOSWAP_CSR))
+ static_branch_enable(&kvm_riscv_nacl_autoswap_csr_available);
+
+ /* Allocate per-CPU shared memory */
+ for_each_possible_cpu(cpu) {
+ nacl = per_cpu_ptr(&kvm_riscv_nacl, cpu);
+
+ shmem_page = alloc_pages(GFP_KERNEL | __GFP_ZERO,
+ get_order(SBI_NACL_SHMEM_SIZE));
+ if (!shmem_page) {
+ kvm_riscv_nacl_exit();
+ return -ENOMEM;
+ }
+ nacl->shmem = page_to_virt(shmem_page);
+ nacl->shmem_phys = page_to_phys(shmem_page);
+ }
+
+ return 0;
+}
diff --git a/arch/riscv/kvm/tlb.c b/arch/riscv/kvm/tlb.c
index 23c0e82b5103..2f91ea5f8493 100644
--- a/arch/riscv/kvm/tlb.c
+++ b/arch/riscv/kvm/tlb.c
@@ -14,6 +14,7 @@
#include <asm/csr.h>
#include <asm/cpufeature.h>
#include <asm/insn-def.h>
+#include <asm/kvm_nacl.h>
#define has_svinval() riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL)
@@ -186,18 +187,24 @@ void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu)
void kvm_riscv_hfence_gvma_vmid_all_process(struct kvm_vcpu *vcpu)
{
- struct kvm_vmid *vmid;
+ struct kvm_vmid *v = &vcpu->kvm->arch.vmid;
+ unsigned long vmid = READ_ONCE(v->vmid);
- vmid = &vcpu->kvm->arch.vmid;
- kvm_riscv_local_hfence_gvma_vmid_all(READ_ONCE(vmid->vmid));
+ if (kvm_riscv_nacl_available())
+ nacl_hfence_gvma_vmid_all(nacl_shmem(), vmid);
+ else
+ kvm_riscv_local_hfence_gvma_vmid_all(vmid);
}
void kvm_riscv_hfence_vvma_all_process(struct kvm_vcpu *vcpu)
{
- struct kvm_vmid *vmid;
+ struct kvm_vmid *v = &vcpu->kvm->arch.vmid;
+ unsigned long vmid = READ_ONCE(v->vmid);
- vmid = &vcpu->kvm->arch.vmid;
- kvm_riscv_local_hfence_vvma_all(READ_ONCE(vmid->vmid));
+ if (kvm_riscv_nacl_available())
+ nacl_hfence_vvma_all(nacl_shmem(), vmid);
+ else
+ kvm_riscv_local_hfence_vvma_all(vmid);
}
static bool vcpu_hfence_dequeue(struct kvm_vcpu *vcpu,
@@ -251,6 +258,7 @@ static bool vcpu_hfence_enqueue(struct kvm_vcpu *vcpu,
void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu)
{
+ unsigned long vmid;
struct kvm_riscv_hfence d = { 0 };
struct kvm_vmid *v = &vcpu->kvm->arch.vmid;
@@ -259,26 +267,41 @@ void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu)
case KVM_RISCV_HFENCE_UNKNOWN:
break;
case KVM_RISCV_HFENCE_GVMA_VMID_GPA:
- kvm_riscv_local_hfence_gvma_vmid_gpa(
- READ_ONCE(v->vmid),
- d.addr, d.size, d.order);
+ vmid = READ_ONCE(v->vmid);
+ if (kvm_riscv_nacl_available())
+ nacl_hfence_gvma_vmid(nacl_shmem(), vmid,
+ d.addr, d.size, d.order);
+ else
+ kvm_riscv_local_hfence_gvma_vmid_gpa(vmid, d.addr,
+ d.size, d.order);
break;
case KVM_RISCV_HFENCE_VVMA_ASID_GVA:
kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD);
- kvm_riscv_local_hfence_vvma_asid_gva(
- READ_ONCE(v->vmid), d.asid,
- d.addr, d.size, d.order);
+ vmid = READ_ONCE(v->vmid);
+ if (kvm_riscv_nacl_available())
+ nacl_hfence_vvma_asid(nacl_shmem(), vmid, d.asid,
+ d.addr, d.size, d.order);
+ else
+ kvm_riscv_local_hfence_vvma_asid_gva(vmid, d.asid, d.addr,
+ d.size, d.order);
break;
case KVM_RISCV_HFENCE_VVMA_ASID_ALL:
kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD);
- kvm_riscv_local_hfence_vvma_asid_all(
- READ_ONCE(v->vmid), d.asid);
+ vmid = READ_ONCE(v->vmid);
+ if (kvm_riscv_nacl_available())
+ nacl_hfence_vvma_asid_all(nacl_shmem(), vmid, d.asid);
+ else
+ kvm_riscv_local_hfence_vvma_asid_all(vmid, d.asid);
break;
case KVM_RISCV_HFENCE_VVMA_GVA:
kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_RCVD);
- kvm_riscv_local_hfence_vvma_gva(
- READ_ONCE(v->vmid),
- d.addr, d.size, d.order);
+ vmid = READ_ONCE(v->vmid);
+ if (kvm_riscv_nacl_available())
+ nacl_hfence_vvma(nacl_shmem(), vmid,
+ d.addr, d.size, d.order);
+ else
+ kvm_riscv_local_hfence_vvma_gva(vmid, d.addr,
+ d.size, d.order);
break;
default:
break;
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 8d7d381737ee..dc3f76f6e46c 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -17,8 +17,8 @@
#include <linux/sched/signal.h>
#include <linux/fs.h>
#include <linux/kvm_host.h>
-#include <asm/csr.h>
#include <asm/cacheflush.h>
+#include <asm/kvm_nacl.h>
#include <asm/kvm_vcpu_vector.h>
#define CREATE_TRACE_POINTS
@@ -226,6 +226,13 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
return (vcpu->arch.guest_context.sstatus & SR_SPP) ? true : false;
}
+#ifdef CONFIG_GUEST_PERF_EVENTS
+unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.guest_context.sepc;
+}
+#endif
+
vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
{
return VM_FAULT_SIGBUS;
@@ -361,10 +368,10 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu)
struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
/* Read current HVIP and VSIE CSRs */
- csr->vsie = csr_read(CSR_VSIE);
+ csr->vsie = ncsr_read(CSR_VSIE);
/* Sync-up HVIP.VSSIP bit changes does by Guest */
- hvip = csr_read(CSR_HVIP);
+ hvip = ncsr_read(CSR_HVIP);
if ((csr->hvip ^ hvip) & (1UL << IRQ_VS_SOFT)) {
if (hvip & (1UL << IRQ_VS_SOFT)) {
if (!test_and_set_bit(IRQ_VS_SOFT,
@@ -561,26 +568,49 @@ static void kvm_riscv_vcpu_setup_config(struct kvm_vcpu *vcpu)
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
+ void *nsh;
struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
struct kvm_vcpu_config *cfg = &vcpu->arch.cfg;
- csr_write(CSR_VSSTATUS, csr->vsstatus);
- csr_write(CSR_VSIE, csr->vsie);
- csr_write(CSR_VSTVEC, csr->vstvec);
- csr_write(CSR_VSSCRATCH, csr->vsscratch);
- csr_write(CSR_VSEPC, csr->vsepc);
- csr_write(CSR_VSCAUSE, csr->vscause);
- csr_write(CSR_VSTVAL, csr->vstval);
- csr_write(CSR_HEDELEG, cfg->hedeleg);
- csr_write(CSR_HVIP, csr->hvip);
- csr_write(CSR_VSATP, csr->vsatp);
- csr_write(CSR_HENVCFG, cfg->henvcfg);
- if (IS_ENABLED(CONFIG_32BIT))
- csr_write(CSR_HENVCFGH, cfg->henvcfg >> 32);
- if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) {
- csr_write(CSR_HSTATEEN0, cfg->hstateen0);
+ if (kvm_riscv_nacl_sync_csr_available()) {
+ nsh = nacl_shmem();
+ nacl_csr_write(nsh, CSR_VSSTATUS, csr->vsstatus);
+ nacl_csr_write(nsh, CSR_VSIE, csr->vsie);
+ nacl_csr_write(nsh, CSR_VSTVEC, csr->vstvec);
+ nacl_csr_write(nsh, CSR_VSSCRATCH, csr->vsscratch);
+ nacl_csr_write(nsh, CSR_VSEPC, csr->vsepc);
+ nacl_csr_write(nsh, CSR_VSCAUSE, csr->vscause);
+ nacl_csr_write(nsh, CSR_VSTVAL, csr->vstval);
+ nacl_csr_write(nsh, CSR_HEDELEG, cfg->hedeleg);
+ nacl_csr_write(nsh, CSR_HVIP, csr->hvip);
+ nacl_csr_write(nsh, CSR_VSATP, csr->vsatp);
+ nacl_csr_write(nsh, CSR_HENVCFG, cfg->henvcfg);
if (IS_ENABLED(CONFIG_32BIT))
- csr_write(CSR_HSTATEEN0H, cfg->hstateen0 >> 32);
+ nacl_csr_write(nsh, CSR_HENVCFGH, cfg->henvcfg >> 32);
+ if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) {
+ nacl_csr_write(nsh, CSR_HSTATEEN0, cfg->hstateen0);
+ if (IS_ENABLED(CONFIG_32BIT))
+ nacl_csr_write(nsh, CSR_HSTATEEN0H, cfg->hstateen0 >> 32);
+ }
+ } else {
+ csr_write(CSR_VSSTATUS, csr->vsstatus);
+ csr_write(CSR_VSIE, csr->vsie);
+ csr_write(CSR_VSTVEC, csr->vstvec);
+ csr_write(CSR_VSSCRATCH, csr->vsscratch);
+ csr_write(CSR_VSEPC, csr->vsepc);
+ csr_write(CSR_VSCAUSE, csr->vscause);
+ csr_write(CSR_VSTVAL, csr->vstval);
+ csr_write(CSR_HEDELEG, cfg->hedeleg);
+ csr_write(CSR_HVIP, csr->hvip);
+ csr_write(CSR_VSATP, csr->vsatp);
+ csr_write(CSR_HENVCFG, cfg->henvcfg);
+ if (IS_ENABLED(CONFIG_32BIT))
+ csr_write(CSR_HENVCFGH, cfg->henvcfg >> 32);
+ if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) {
+ csr_write(CSR_HSTATEEN0, cfg->hstateen0);
+ if (IS_ENABLED(CONFIG_32BIT))
+ csr_write(CSR_HSTATEEN0H, cfg->hstateen0 >> 32);
+ }
}
kvm_riscv_gstage_update_hgatp(vcpu);
@@ -603,6 +633,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
+ void *nsh;
struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
vcpu->cpu = -1;
@@ -618,15 +649,28 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
vcpu->arch.isa);
kvm_riscv_vcpu_host_vector_restore(&vcpu->arch.host_context);
- csr->vsstatus = csr_read(CSR_VSSTATUS);
- csr->vsie = csr_read(CSR_VSIE);
- csr->vstvec = csr_read(CSR_VSTVEC);
- csr->vsscratch = csr_read(CSR_VSSCRATCH);
- csr->vsepc = csr_read(CSR_VSEPC);
- csr->vscause = csr_read(CSR_VSCAUSE);
- csr->vstval = csr_read(CSR_VSTVAL);
- csr->hvip = csr_read(CSR_HVIP);
- csr->vsatp = csr_read(CSR_VSATP);
+ if (kvm_riscv_nacl_available()) {
+ nsh = nacl_shmem();
+ csr->vsstatus = nacl_csr_read(nsh, CSR_VSSTATUS);
+ csr->vsie = nacl_csr_read(nsh, CSR_VSIE);
+ csr->vstvec = nacl_csr_read(nsh, CSR_VSTVEC);
+ csr->vsscratch = nacl_csr_read(nsh, CSR_VSSCRATCH);
+ csr->vsepc = nacl_csr_read(nsh, CSR_VSEPC);
+ csr->vscause = nacl_csr_read(nsh, CSR_VSCAUSE);
+ csr->vstval = nacl_csr_read(nsh, CSR_VSTVAL);
+ csr->hvip = nacl_csr_read(nsh, CSR_HVIP);
+ csr->vsatp = nacl_csr_read(nsh, CSR_VSATP);
+ } else {
+ csr->vsstatus = csr_read(CSR_VSSTATUS);
+ csr->vsie = csr_read(CSR_VSIE);
+ csr->vstvec = csr_read(CSR_VSTVEC);
+ csr->vsscratch = csr_read(CSR_VSSCRATCH);
+ csr->vsepc = csr_read(CSR_VSEPC);
+ csr->vscause = csr_read(CSR_VSCAUSE);
+ csr->vstval = csr_read(CSR_VSTVAL);
+ csr->hvip = csr_read(CSR_HVIP);
+ csr->vsatp = csr_read(CSR_VSATP);
+ }
}
static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
@@ -681,7 +725,7 @@ static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu)
{
struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
- csr_write(CSR_HVIP, csr->hvip);
+ ncsr_write(CSR_HVIP, csr->hvip);
kvm_riscv_vcpu_aia_update_hvip(vcpu);
}
@@ -691,6 +735,7 @@ static __always_inline void kvm_riscv_vcpu_swap_in_guest_state(struct kvm_vcpu *
struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
struct kvm_vcpu_config *cfg = &vcpu->arch.cfg;
+ vcpu->arch.host_scounteren = csr_swap(CSR_SCOUNTEREN, csr->scounteren);
vcpu->arch.host_senvcfg = csr_swap(CSR_SENVCFG, csr->senvcfg);
if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN) &&
(cfg->hstateen0 & SMSTATEEN0_SSTATEEN0))
@@ -704,6 +749,7 @@ static __always_inline void kvm_riscv_vcpu_swap_in_host_state(struct kvm_vcpu *v
struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
struct kvm_vcpu_config *cfg = &vcpu->arch.cfg;
+ csr->scounteren = csr_swap(CSR_SCOUNTEREN, vcpu->arch.host_scounteren);
csr->senvcfg = csr_swap(CSR_SENVCFG, vcpu->arch.host_senvcfg);
if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN) &&
(cfg->hstateen0 & SMSTATEEN0_SSTATEEN0))
@@ -718,11 +764,81 @@ static __always_inline void kvm_riscv_vcpu_swap_in_host_state(struct kvm_vcpu *v
* This must be noinstr as instrumentation may make use of RCU, and this is not
* safe during the EQS.
*/
-static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu,
+ struct kvm_cpu_trap *trap)
{
+ void *nsh;
+ struct kvm_cpu_context *gcntx = &vcpu->arch.guest_context;
+ struct kvm_cpu_context *hcntx = &vcpu->arch.host_context;
+
+ /*
+ * We save trap CSRs (such as SEPC, SCAUSE, STVAL, HTVAL, and
+ * HTINST) here because we do local_irq_enable() after this
+ * function in kvm_arch_vcpu_ioctl_run() which can result in
+ * an interrupt immediately after local_irq_enable() and can
+ * potentially change trap CSRs.
+ */
+
kvm_riscv_vcpu_swap_in_guest_state(vcpu);
guest_state_enter_irqoff();
- __kvm_riscv_switch_to(&vcpu->arch);
+
+ if (kvm_riscv_nacl_sync_sret_available()) {
+ nsh = nacl_shmem();
+
+ if (kvm_riscv_nacl_autoswap_csr_available()) {
+ hcntx->hstatus =
+ nacl_csr_read(nsh, CSR_HSTATUS);
+ nacl_scratch_write_long(nsh,
+ SBI_NACL_SHMEM_AUTOSWAP_OFFSET +
+ SBI_NACL_SHMEM_AUTOSWAP_HSTATUS,
+ gcntx->hstatus);
+ nacl_scratch_write_long(nsh,
+ SBI_NACL_SHMEM_AUTOSWAP_OFFSET,
+ SBI_NACL_SHMEM_AUTOSWAP_FLAG_HSTATUS);
+ } else if (kvm_riscv_nacl_sync_csr_available()) {
+ hcntx->hstatus = nacl_csr_swap(nsh,
+ CSR_HSTATUS, gcntx->hstatus);
+ } else {
+ hcntx->hstatus = csr_swap(CSR_HSTATUS, gcntx->hstatus);
+ }
+
+ nacl_scratch_write_longs(nsh,
+ SBI_NACL_SHMEM_SRET_OFFSET +
+ SBI_NACL_SHMEM_SRET_X(1),
+ &gcntx->ra,
+ SBI_NACL_SHMEM_SRET_X_LAST);
+
+ __kvm_riscv_nacl_switch_to(&vcpu->arch, SBI_EXT_NACL,
+ SBI_EXT_NACL_SYNC_SRET);
+
+ if (kvm_riscv_nacl_autoswap_csr_available()) {
+ nacl_scratch_write_long(nsh,
+ SBI_NACL_SHMEM_AUTOSWAP_OFFSET,
+ 0);
+ gcntx->hstatus = nacl_scratch_read_long(nsh,
+ SBI_NACL_SHMEM_AUTOSWAP_OFFSET +
+ SBI_NACL_SHMEM_AUTOSWAP_HSTATUS);
+ } else {
+ gcntx->hstatus = csr_swap(CSR_HSTATUS, hcntx->hstatus);
+ }
+
+ trap->htval = nacl_csr_read(nsh, CSR_HTVAL);
+ trap->htinst = nacl_csr_read(nsh, CSR_HTINST);
+ } else {
+ hcntx->hstatus = csr_swap(CSR_HSTATUS, gcntx->hstatus);
+
+ __kvm_riscv_switch_to(&vcpu->arch);
+
+ gcntx->hstatus = csr_swap(CSR_HSTATUS, hcntx->hstatus);
+
+ trap->htval = csr_read(CSR_HTVAL);
+ trap->htinst = csr_read(CSR_HTINST);
+ }
+
+ trap->sepc = gcntx->sepc;
+ trap->scause = csr_read(CSR_SCAUSE);
+ trap->stval = csr_read(CSR_STVAL);
+
vcpu->arch.last_exit_cpu = vcpu->cpu;
guest_state_exit_irqoff();
kvm_riscv_vcpu_swap_in_host_state(vcpu);
@@ -839,22 +955,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
guest_timing_enter_irqoff();
- kvm_riscv_vcpu_enter_exit(vcpu);
+ kvm_riscv_vcpu_enter_exit(vcpu, &trap);
vcpu->mode = OUTSIDE_GUEST_MODE;
vcpu->stat.exits++;
- /*
- * Save SCAUSE, STVAL, HTVAL, and HTINST because we might
- * get an interrupt between __kvm_riscv_switch_to() and
- * local_irq_enable() which can potentially change CSRs.
- */
- trap.sepc = vcpu->arch.guest_context.sepc;
- trap.scause = csr_read(CSR_SCAUSE);
- trap.stval = csr_read(CSR_STVAL);
- trap.htval = csr_read(CSR_HTVAL);
- trap.htinst = csr_read(CSR_HTINST);
-
/* Syncup interrupts state with HW */
kvm_riscv_vcpu_sync_interrupts(vcpu);
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index 7de128be8db9..6e704ed86a83 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -486,19 +486,22 @@ void kvm_riscv_vcpu_sbi_init(struct kvm_vcpu *vcpu)
struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context;
const struct kvm_riscv_sbi_extension_entry *entry;
const struct kvm_vcpu_sbi_extension *ext;
- int i;
+ int idx, i;
for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) {
entry = &sbi_ext[i];
ext = entry->ext_ptr;
+ idx = entry->ext_idx;
+
+ if (idx < 0 || idx >= ARRAY_SIZE(scontext->ext_status))
+ continue;
if (ext->probe && !ext->probe(vcpu)) {
- scontext->ext_status[entry->ext_idx] =
- KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE;
+ scontext->ext_status[idx] = KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE;
continue;
}
- scontext->ext_status[entry->ext_idx] = ext->default_disabled ?
+ scontext->ext_status[idx] = ext->default_disabled ?
KVM_RISCV_SBI_EXT_STATUS_DISABLED :
KVM_RISCV_SBI_EXT_STATUS_ENABLED;
}
diff --git a/arch/riscv/kvm/vcpu_switch.S b/arch/riscv/kvm/vcpu_switch.S
index 0c26189aa01c..47686bcb21e0 100644
--- a/arch/riscv/kvm/vcpu_switch.S
+++ b/arch/riscv/kvm/vcpu_switch.S
@@ -11,11 +11,7 @@
#include <asm/asm-offsets.h>
#include <asm/csr.h>
- .text
- .altmacro
- .option norelax
-
-SYM_FUNC_START(__kvm_riscv_switch_to)
+.macro SAVE_HOST_GPRS
/* Save Host GPRs (except A0 and T0-T6) */
REG_S ra, (KVM_ARCH_HOST_RA)(a0)
REG_S sp, (KVM_ARCH_HOST_SP)(a0)
@@ -40,39 +36,33 @@ SYM_FUNC_START(__kvm_riscv_switch_to)
REG_S s9, (KVM_ARCH_HOST_S9)(a0)
REG_S s10, (KVM_ARCH_HOST_S10)(a0)
REG_S s11, (KVM_ARCH_HOST_S11)(a0)
+.endm
+.macro SAVE_HOST_AND_RESTORE_GUEST_CSRS __resume_addr
/* Load Guest CSR values */
REG_L t0, (KVM_ARCH_GUEST_SSTATUS)(a0)
- REG_L t1, (KVM_ARCH_GUEST_HSTATUS)(a0)
- REG_L t2, (KVM_ARCH_GUEST_SCOUNTEREN)(a0)
- la t4, .Lkvm_switch_return
- REG_L t5, (KVM_ARCH_GUEST_SEPC)(a0)
+ la t1, \__resume_addr
+ REG_L t2, (KVM_ARCH_GUEST_SEPC)(a0)
/* Save Host and Restore Guest SSTATUS */
csrrw t0, CSR_SSTATUS, t0
- /* Save Host and Restore Guest HSTATUS */
- csrrw t1, CSR_HSTATUS, t1
-
- /* Save Host and Restore Guest SCOUNTEREN */
- csrrw t2, CSR_SCOUNTEREN, t2
-
/* Save Host STVEC and change it to return path */
- csrrw t4, CSR_STVEC, t4
+ csrrw t1, CSR_STVEC, t1
+
+ /* Restore Guest SEPC */
+ csrw CSR_SEPC, t2
/* Save Host SSCRATCH and change it to struct kvm_vcpu_arch pointer */
csrrw t3, CSR_SSCRATCH, a0
- /* Restore Guest SEPC */
- csrw CSR_SEPC, t5
-
/* Store Host CSR values */
REG_S t0, (KVM_ARCH_HOST_SSTATUS)(a0)
- REG_S t1, (KVM_ARCH_HOST_HSTATUS)(a0)
- REG_S t2, (KVM_ARCH_HOST_SCOUNTEREN)(a0)
+ REG_S t1, (KVM_ARCH_HOST_STVEC)(a0)
REG_S t3, (KVM_ARCH_HOST_SSCRATCH)(a0)
- REG_S t4, (KVM_ARCH_HOST_STVEC)(a0)
+.endm
+.macro RESTORE_GUEST_GPRS
/* Restore Guest GPRs (except A0) */
REG_L ra, (KVM_ARCH_GUEST_RA)(a0)
REG_L sp, (KVM_ARCH_GUEST_SP)(a0)
@@ -107,13 +97,9 @@ SYM_FUNC_START(__kvm_riscv_switch_to)
/* Restore Guest A0 */
REG_L a0, (KVM_ARCH_GUEST_A0)(a0)
+.endm
- /* Resume Guest */
- sret
-
- /* Back to Host */
- .align 2
-.Lkvm_switch_return:
+.macro SAVE_GUEST_GPRS
/* Swap Guest A0 with SSCRATCH */
csrrw a0, CSR_SSCRATCH, a0
@@ -148,39 +134,33 @@ SYM_FUNC_START(__kvm_riscv_switch_to)
REG_S t4, (KVM_ARCH_GUEST_T4)(a0)
REG_S t5, (KVM_ARCH_GUEST_T5)(a0)
REG_S t6, (KVM_ARCH_GUEST_T6)(a0)
+.endm
+.macro SAVE_GUEST_AND_RESTORE_HOST_CSRS
/* Load Host CSR values */
- REG_L t1, (KVM_ARCH_HOST_STVEC)(a0)
- REG_L t2, (KVM_ARCH_HOST_SSCRATCH)(a0)
- REG_L t3, (KVM_ARCH_HOST_SCOUNTEREN)(a0)
- REG_L t4, (KVM_ARCH_HOST_HSTATUS)(a0)
- REG_L t5, (KVM_ARCH_HOST_SSTATUS)(a0)
-
- /* Save Guest SEPC */
- csrr t0, CSR_SEPC
+ REG_L t0, (KVM_ARCH_HOST_STVEC)(a0)
+ REG_L t1, (KVM_ARCH_HOST_SSCRATCH)(a0)
+ REG_L t2, (KVM_ARCH_HOST_SSTATUS)(a0)
/* Save Guest A0 and Restore Host SSCRATCH */
- csrrw t2, CSR_SSCRATCH, t2
+ csrrw t1, CSR_SSCRATCH, t1
- /* Restore Host STVEC */
- csrw CSR_STVEC, t1
-
- /* Save Guest and Restore Host SCOUNTEREN */
- csrrw t3, CSR_SCOUNTEREN, t3
+ /* Save Guest SEPC */
+ csrr t3, CSR_SEPC
- /* Save Guest and Restore Host HSTATUS */
- csrrw t4, CSR_HSTATUS, t4
+ /* Restore Host STVEC */
+ csrw CSR_STVEC, t0
/* Save Guest and Restore Host SSTATUS */
- csrrw t5, CSR_SSTATUS, t5
+ csrrw t2, CSR_SSTATUS, t2
/* Store Guest CSR values */
- REG_S t0, (KVM_ARCH_GUEST_SEPC)(a0)
- REG_S t2, (KVM_ARCH_GUEST_A0)(a0)
- REG_S t3, (KVM_ARCH_GUEST_SCOUNTEREN)(a0)
- REG_S t4, (KVM_ARCH_GUEST_HSTATUS)(a0)
- REG_S t5, (KVM_ARCH_GUEST_SSTATUS)(a0)
+ REG_S t1, (KVM_ARCH_GUEST_A0)(a0)
+ REG_S t2, (KVM_ARCH_GUEST_SSTATUS)(a0)
+ REG_S t3, (KVM_ARCH_GUEST_SEPC)(a0)
+.endm
+.macro RESTORE_HOST_GPRS
/* Restore Host GPRs (except A0 and T0-T6) */
REG_L ra, (KVM_ARCH_HOST_RA)(a0)
REG_L sp, (KVM_ARCH_HOST_SP)(a0)
@@ -205,11 +185,68 @@ SYM_FUNC_START(__kvm_riscv_switch_to)
REG_L s9, (KVM_ARCH_HOST_S9)(a0)
REG_L s10, (KVM_ARCH_HOST_S10)(a0)
REG_L s11, (KVM_ARCH_HOST_S11)(a0)
+.endm
+
+ .text
+ .altmacro
+ .option norelax
+
+ /*
+ * Parameters:
+ * A0 <= Pointer to struct kvm_vcpu_arch
+ */
+SYM_FUNC_START(__kvm_riscv_switch_to)
+ SAVE_HOST_GPRS
+
+ SAVE_HOST_AND_RESTORE_GUEST_CSRS .Lkvm_switch_return
+
+ RESTORE_GUEST_GPRS
+
+ /* Resume Guest using SRET */
+ sret
+
+ /* Back to Host */
+ .align 2
+.Lkvm_switch_return:
+ SAVE_GUEST_GPRS
+
+ SAVE_GUEST_AND_RESTORE_HOST_CSRS
+
+ RESTORE_HOST_GPRS
/* Return to C code */
ret
SYM_FUNC_END(__kvm_riscv_switch_to)
+ /*
+ * Parameters:
+ * A0 <= Pointer to struct kvm_vcpu_arch
+ * A1 <= SBI extension ID
+ * A2 <= SBI function ID
+ */
+SYM_FUNC_START(__kvm_riscv_nacl_switch_to)
+ SAVE_HOST_GPRS
+
+ SAVE_HOST_AND_RESTORE_GUEST_CSRS .Lkvm_nacl_switch_return
+
+ /* Resume Guest using SBI nested acceleration */
+ add a6, a2, zero
+ add a7, a1, zero
+ ecall
+
+ /* Back to Host */
+ .align 2
+.Lkvm_nacl_switch_return:
+ SAVE_GUEST_GPRS
+
+ SAVE_GUEST_AND_RESTORE_HOST_CSRS
+
+ RESTORE_HOST_GPRS
+
+ /* Return to C code */
+ ret
+SYM_FUNC_END(__kvm_riscv_nacl_switch_to)
+
SYM_CODE_START(__kvm_riscv_unpriv_trap)
/*
* We assume that faulting unpriv load/store instruction is
diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c
index 75486b25ac45..96e7a4e463f7 100644
--- a/arch/riscv/kvm/vcpu_timer.c
+++ b/arch/riscv/kvm/vcpu_timer.c
@@ -11,8 +11,8 @@
#include <linux/kvm_host.h>
#include <linux/uaccess.h>
#include <clocksource/timer-riscv.h>
-#include <asm/csr.h>
#include <asm/delay.h>
+#include <asm/kvm_nacl.h>
#include <asm/kvm_vcpu_timer.h>
static u64 kvm_riscv_current_cycles(struct kvm_guest_timer *gt)
@@ -72,12 +72,12 @@ static int kvm_riscv_vcpu_timer_cancel(struct kvm_vcpu_timer *t)
static int kvm_riscv_vcpu_update_vstimecmp(struct kvm_vcpu *vcpu, u64 ncycles)
{
#if defined(CONFIG_32BIT)
- csr_write(CSR_VSTIMECMP, ncycles & 0xFFFFFFFF);
- csr_write(CSR_VSTIMECMPH, ncycles >> 32);
+ ncsr_write(CSR_VSTIMECMP, ncycles & 0xFFFFFFFF);
+ ncsr_write(CSR_VSTIMECMPH, ncycles >> 32);
#else
- csr_write(CSR_VSTIMECMP, ncycles);
+ ncsr_write(CSR_VSTIMECMP, ncycles);
#endif
- return 0;
+ return 0;
}
static int kvm_riscv_vcpu_update_hrtimer(struct kvm_vcpu *vcpu, u64 ncycles)
@@ -289,10 +289,10 @@ static void kvm_riscv_vcpu_update_timedelta(struct kvm_vcpu *vcpu)
struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
#if defined(CONFIG_32BIT)
- csr_write(CSR_HTIMEDELTA, (u32)(gt->time_delta));
- csr_write(CSR_HTIMEDELTAH, (u32)(gt->time_delta >> 32));
+ ncsr_write(CSR_HTIMEDELTA, (u32)(gt->time_delta));
+ ncsr_write(CSR_HTIMEDELTAH, (u32)(gt->time_delta >> 32));
#else
- csr_write(CSR_HTIMEDELTA, gt->time_delta);
+ ncsr_write(CSR_HTIMEDELTA, gt->time_delta);
#endif
}
@@ -306,10 +306,10 @@ void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu)
return;
#if defined(CONFIG_32BIT)
- csr_write(CSR_VSTIMECMP, (u32)t->next_cycles);
- csr_write(CSR_VSTIMECMPH, (u32)(t->next_cycles >> 32));
+ ncsr_write(CSR_VSTIMECMP, (u32)t->next_cycles);
+ ncsr_write(CSR_VSTIMECMPH, (u32)(t->next_cycles >> 32));
#else
- csr_write(CSR_VSTIMECMP, t->next_cycles);
+ ncsr_write(CSR_VSTIMECMP, t->next_cycles);
#endif
/* timer should be enabled for the remaining operations */
@@ -327,10 +327,10 @@ void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu)
return;
#if defined(CONFIG_32BIT)
- t->next_cycles = csr_read(CSR_VSTIMECMP);
- t->next_cycles |= (u64)csr_read(CSR_VSTIMECMPH) << 32;
+ t->next_cycles = ncsr_read(CSR_VSTIMECMP);
+ t->next_cycles |= (u64)ncsr_read(CSR_VSTIMECMPH) << 32;
#else
- t->next_cycles = csr_read(CSR_VSTIMECMP);
+ t->next_cycles = ncsr_read(CSR_VSTIMECMP);
#endif
}
generated by cgit v1.2.3 (git 2.25.1) at 2025-02-23 10:34:50 +0000