[PATCH v6 0/8] RISC-V: KVM: Add Svadu/Zicfiss/Zicfilp FWFT support

[PATCH v6 0/8] RISC-V: KVM: Add Svadu/Zicfiss/Zicfilp FWFT support

[Inochi Amaoto]

This patchset based on the patchset "RISC-V: KVM: Add Zicfiss/Zicfilp
support".

The patch includes all the function of original patchset from Quan:
adding the Svadu/Zicfiss/Zicfilp FWFT for the RISC-V KVM. And this
patchset already passes the KVM unit test.

Test with the patch applied
https://lore.kernel.org/all/20260618064406.14508-1-cuiyunhui@bytedance.com/

Changed from v5:
- https://lore.kernel.org/kvm/20260706022046.214956-1-inochiama@gmail.com/
patch 1, 5:
1. Switch to csr_read()/csr_write() to update csr
patch 8:
1. Fix the macro name.

Changed from v4:
- https://lore.kernel.org/kvm/20260701020746.170157-1-inochiama@gmail.com/
patch 1:
1. Use NACL for csr update
2. Check ISA mapping before cleaning the ADUE bit
patch 4:
1. Clear the zicfiss csr during a VCPU reset
2. Add zicfiss csr to num_csr_regs()
patch 6:
1. Cleanup SPELP after redirecting the trap
patch 7:
1. Use interrupt bit instead of number for masking/unmasking
patch 8:
1. Add missing entry for the test
2. Fix the wrong comment.

Changed from v3:
- https://lore.kernel.org/kvm/20260607081105.993908-1-inochiama@gmail.com/
1. rebase to the v7.2-rc1
2. Tested with the updated Svadu patch
3. Remove the dependency as it is already merged.

Changed from v2:
- https://lore.kernel.org/kvm/20260601084336.2601675-1-inochiama@gmail.com/
1. rebase with Yong-Xuan's patch set
2. Add SSP CSR context switch/set/get
3. Move the software-check exception set/unset into FWFT
4. Only delegate software-check exception when Zicfiss/Zicfilp is enabled.
5. Make KVM SBI_FWFT_PTE_AD_HW_UPDATING depends on both Svadu and Svade
   enabled.

Changed from Quan's v1:
- https://lore.kernel.org/kvm/cover.1764509485.git.zhouquan@iscas.ac.cn/
1. rebase to the latest master.
2. Split Svadu change as separate patch
3. Fix all build error from the original series
4. Remove the Svadu check in kvm_riscv_vcpu_config_ran_once() and in
   favor of the FWFT.
5. Remove the LPE/SSE setting bit in kvm_riscv_vcpu_config_ran_once()
   (kvm_riscv_vcpu_setup_config() in original patchset)

Inochi Amaoto (8):
  RISC-V: KVM: Add support for Svadu FWFT features
  KVM: riscv: selftests: add Svadu FWFT extension to get-reg-list test
  RISC-V: KVM: Allow Zicfiss/Zicfilp extensions for Guest/VM
  RISC-V: KVM: Add ssp context save/restore
  RISC-V: KVM: Handle software-check exits for VCPU
  RISC-V: KVM: Delegate SPELP bit to VS/VU mode if landing pad is
    enabled.
  RISC-V: KVM: Add support for control-flow integrity FWFT features
  KVM: riscv: selftests: add Zicfiss/Zicfilp extension to get-reg-list
    test

 arch/riscv/include/asm/csr.h                  |   1 +
 arch/riscv/include/asm/kvm_host.h             |   7 +
 arch/riscv/include/uapi/asm/kvm.h             |  13 ++
 arch/riscv/kvm/isa.c                          |   2 +
 arch/riscv/kvm/vcpu.c                         |   7 +
 arch/riscv/kvm/vcpu_exit.c                    |  11 ++
 arch/riscv/kvm/vcpu_onereg.c                  |  68 ++++++-
 arch/riscv/kvm/vcpu_sbi_fwft.c                | 183 ++++++++++++++++++
 .../selftests/kvm/riscv/get-reg-list.c        |  90 +++++++++
 9 files changed, 380 insertions(+), 2 deletions(-)

--
2.55.0

[PATCH v6 1/8] RISC-V: KVM: Add support for Svadu FWFT features

[Inochi Amaoto]

Hardware updating of PTE A/D bits is controlled through ADUE bit in
henvcfg Expose the feature only if both Svadu and Svade are supported
for VS-mode.

Allow the VMM to enable/disable this feature by change the ISA
extension state in the guest.

Assisted-by: YuanSheng:claude-4.7-opus
Co-developed-by: Quan Zhou <zhouquan@iscas.ac.cn>
Signed-off-by: Quan Zhou <zhouquan@iscas.ac.cn>
Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
---
 arch/riscv/include/uapi/asm/kvm.h |  1 +
 arch/riscv/kvm/vcpu_sbi_fwft.c    | 76 +++++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 504e73305343..7bbea8812d92 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -240,6 +240,7 @@ struct kvm_riscv_sbi_fwft_feature {
 struct kvm_riscv_sbi_fwft {
 	struct kvm_riscv_sbi_fwft_feature misaligned_deleg;
 	struct kvm_riscv_sbi_fwft_feature pointer_masking;
+	struct kvm_riscv_sbi_fwft_feature pte_ad_hw_updating;
 };
 
 /* If you need to interpret the index values, here is the key: */
diff --git a/arch/riscv/kvm/vcpu_sbi_fwft.c b/arch/riscv/kvm/vcpu_sbi_fwft.c
index ab39ac464ffd..4d474a439b29 100644
--- a/arch/riscv/kvm/vcpu_sbi_fwft.c
+++ b/arch/riscv/kvm/vcpu_sbi_fwft.c
@@ -94,6 +94,45 @@ static bool kvm_fwft_is_defined_feature(enum sbi_fwft_feature_t feature)
 	return false;
 }
 
+static void kvm_sbi_fwft_env_flag_reset_helper(struct kvm_vcpu *vcpu,
+					       u64 flag)
+{
+	vcpu->arch.cfg.henvcfg &= ~flag;
+}
+
+static long kvm_sbi_fwft_env_flag_set_helper(struct kvm_vcpu *vcpu,
+					     struct kvm_sbi_fwft_config *conf,
+					     bool one_reg_access,
+					     unsigned long value, u64 flag)
+{
+	struct kvm_vcpu_config *cfg = &vcpu->arch.cfg;
+
+	if (value == 0)
+		cfg->henvcfg &= ~flag;
+	else if (value == 1)
+		cfg->henvcfg |= flag;
+	else
+		return SBI_ERR_INVALID_PARAM;
+
+	if (!one_reg_access) {
+		csr_write(CSR_HENVCFG, vcpu->arch.cfg.henvcfg);
+		if (IS_ENABLED(CONFIG_32BIT))
+			csr_write(CSR_HENVCFGH, vcpu->arch.cfg.henvcfg >> 32);
+	}
+
+	return SBI_SUCCESS;
+}
+
+static long kvm_sbi_fwft_env_flag_get_helper(struct kvm_vcpu *vcpu,
+					     struct kvm_sbi_fwft_config *conf,
+					     bool one_reg_access,
+					     unsigned long *value, u64 flag)
+{
+	*value = (vcpu->arch.cfg.henvcfg & flag) == flag;
+
+	return SBI_SUCCESS;
+}
+
 static bool kvm_sbi_fwft_misaligned_delegation_supported(struct kvm_vcpu *vcpu)
 {
 	return misaligned_traps_can_delegate();
@@ -137,6 +176,34 @@ static long kvm_sbi_fwft_get_misaligned_delegation(struct kvm_vcpu *vcpu,
 	return SBI_SUCCESS;
 }
 
+static bool kvm_sbi_fwft_pte_ad_hw_updating_supported(struct kvm_vcpu *vcpu)
+{
+	return riscv_isa_extension_available(vcpu->arch.isa, SVADU) &&
+		riscv_isa_extension_available(vcpu->arch.isa, SVADE);
+}
+
+static void kvm_sbi_fwft_reset_pte_ad_hw_updating(struct kvm_vcpu *vcpu)
+{
+	if (kvm_sbi_fwft_pte_ad_hw_updating_supported(vcpu))
+		kvm_sbi_fwft_env_flag_reset_helper(vcpu, ENVCFG_ADUE);
+}
+
+static long kvm_sbi_fwft_set_pte_ad_hw_updating(struct kvm_vcpu *vcpu,
+						struct kvm_sbi_fwft_config *conf,
+						bool one_reg_access, unsigned long value)
+{
+	return kvm_sbi_fwft_env_flag_set_helper(vcpu, conf, one_reg_access,
+						value, ENVCFG_ADUE);
+}
+
+static long kvm_sbi_fwft_get_pte_ad_hw_updating(struct kvm_vcpu *vcpu,
+						struct kvm_sbi_fwft_config *conf,
+						bool one_reg_access, unsigned long *value)
+{
+	return kvm_sbi_fwft_env_flag_get_helper(vcpu, conf, one_reg_access,
+						value, ENVCFG_ADUE);
+}
+
 #ifndef CONFIG_32BIT
 
 static bool try_to_set_pmm(unsigned long value)
@@ -246,6 +313,15 @@ static const struct kvm_sbi_fwft_feature features[] = {
 		.set = kvm_sbi_fwft_set_misaligned_delegation,
 		.get = kvm_sbi_fwft_get_misaligned_delegation,
 	},
+	{
+		.id = SBI_FWFT_PTE_AD_HW_UPDATING,
+		.first_reg_num = offsetof(struct kvm_riscv_sbi_fwft, pte_ad_hw_updating.enable) /
+				 sizeof(unsigned long),
+		.supported = kvm_sbi_fwft_pte_ad_hw_updating_supported,
+		.reset = kvm_sbi_fwft_reset_pte_ad_hw_updating,
+		.set = kvm_sbi_fwft_set_pte_ad_hw_updating,
+		.get = kvm_sbi_fwft_get_pte_ad_hw_updating,
+	},
 #ifndef CONFIG_32BIT
 	{
 		.id = SBI_FWFT_POINTER_MASKING_PMLEN,
-- 
2.55.0

[PATCH v6 2/8] KVM: riscv: selftests: add Svadu FWFT extension to get-reg-list test

[Inochi Amaoto]

The KVM RISC-V allows Svadu FWFT for Guest/VM so add this extension
to get-reg-list test.

Assisted-by: YuanSheng:claude-4.7-opus
Co-developed-by: Quan Zhou <zhouquan@iscas.ac.cn>
Signed-off-by: Quan Zhou <zhouquan@iscas.ac.cn>
Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
---
 .../selftests/kvm/riscv/get-reg-list.c        | 21 +++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index cb86cb6b3635..94e33b2ee796 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -745,6 +745,9 @@ static const char *sbi_fwft_id_to_str(__u64 reg_off)
 	case 3: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.enable)";
 	case 4: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.flags)";
 	case 5: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.value)";
+	case 6: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pte_ad_hw_updating.enable)";
+	case 7: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pte_ad_hw_updating.flags)";
+	case 8: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pte_ad_hw_updating.value)";
 	}
 	return strdup_printf("KVM_REG_RISCV_SBI_FWFT | %lld /* UNKNOWN */", reg_off);
 }
@@ -944,6 +947,13 @@ static __u64 sbi_fwft_pointer_masking_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.value),
 };
 
+static __u64 sbi_fwft_pte_ad_hw_updating_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_FWFT,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pte_ad_hw_updating.enable),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pte_ad_hw_updating.flags),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pte_ad_hw_updating.value),
+};
+
 static __u64 zicbom_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size),
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM,
@@ -1259,6 +1269,16 @@ static struct vcpu_reg_list config_sbi_fwft_pointer_masking = {
 	},
 };
 
+static struct vcpu_reg_list config_sbi_fwft_pte_ad_hw_updating = {
+	.sublists = {
+		SUBLIST_BASE,
+		SUBLIST_ISA(svade, SVADE),
+		SUBLIST_ISA(svadu, SVADU),
+		SUBLIST_SBI(fwft_pte_ad_hw_updating, FWFT),
+		{0},
+	},
+};
+
 struct vcpu_reg_list *vcpu_configs[] = {
 	&config_sbi_base,
 	&config_sbi_sta,
@@ -1268,6 +1288,7 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_sbi_mpxy,
 	&config_sbi_fwft_misaligned_deleg,
 	&config_sbi_fwft_pointer_masking,
+	&config_sbi_fwft_pte_ad_hw_updating,
 	&config_aia,
 	&config_fp_f,
 	&config_fp_d,
-- 
2.55.0

[PATCH v6 3/8] RISC-V: KVM: Allow Zicfiss/Zicfilp extensions for Guest/VM

[Inochi Amaoto]

Extend the KVM ISA extension array to allow KVM userspace to
detect and enable Zicfiss/Zicfilp extensions for Guest/VM.

Assisted-by: YuanSheng:claude-4.7-opus
Co-developed-by: Quan Zhou <zhouquan@iscas.ac.cn>
Signed-off-by: Quan Zhou <zhouquan@iscas.ac.cn>
Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
---
 arch/riscv/include/uapi/asm/kvm.h | 2 ++
 arch/riscv/kvm/isa.c              | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 7bbea8812d92..a27de850fa4c 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -199,6 +199,8 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZCLSD,
 	KVM_RISCV_ISA_EXT_ZILSD,
 	KVM_RISCV_ISA_EXT_ZALASR,
+	KVM_RISCV_ISA_EXT_ZICFILP,
+	KVM_RISCV_ISA_EXT_ZICFISS,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/isa.c b/arch/riscv/kvm/isa.c
index 1132d909cc25..9852a91fdecc 100644
--- a/arch/riscv/kvm/isa.c
+++ b/arch/riscv/kvm/isa.c
@@ -65,6 +65,8 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(ZICBOP),
 	KVM_ISA_EXT_ARR(ZICBOZ),
 	KVM_ISA_EXT_ARR(ZICCRSE),
+	KVM_ISA_EXT_ARR(ZICFILP),
+	KVM_ISA_EXT_ARR(ZICFISS),
 	KVM_ISA_EXT_ARR(ZICNTR),
 	KVM_ISA_EXT_ARR(ZICOND),
 	KVM_ISA_EXT_ARR(ZICSR),
-- 
2.55.0

[PATCH v6 4/8] RISC-V: KVM: Add ssp context save/restore

[Inochi Amaoto]

Add ssp context save/restore for guest VCPUs and also add it to the
ONE_REG interface to allow its access from user space.

Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
---
 arch/riscv/include/asm/kvm_host.h |  7 ++++
 arch/riscv/include/uapi/asm/kvm.h |  8 ++++
 arch/riscv/kvm/vcpu.c             |  7 ++++
 arch/riscv/kvm/vcpu_onereg.c      | 68 ++++++++++++++++++++++++++++++-
 4 files changed, 88 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 60017ceec9d2..e5ed3b0e5a55 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -163,6 +163,10 @@ struct kvm_vcpu_smstateen_csr {
 	unsigned long sstateen0;
 };
 
+struct kvm_vcpu_zicfiss_csr {
+	unsigned long ssp;
+};
+
 struct kvm_vcpu_reset_state {
 	spinlock_t lock;
 	unsigned long pc;
@@ -203,6 +207,9 @@ struct kvm_vcpu_arch {
 	/* CPU Smstateen CSR context of Guest VCPU */
 	struct kvm_vcpu_smstateen_csr smstateen_csr;
 
+	/* CPU Zicfiss CSR context of Guest VCPU */
+	struct kvm_vcpu_zicfiss_csr zicfiss_csr;
+
 	/* CPU reset state of Guest VCPU */
 	struct kvm_vcpu_reset_state reset_state;
 
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index a27de850fa4c..fd4c81697617 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -102,6 +102,11 @@ struct kvm_riscv_smstateen_csr {
 	unsigned long sstateen0;
 };
 
+/* Zicfiss CSR for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_zicfiss_csr {
+	unsigned long ssp;
+};
+
 /* TIMER registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
 struct kvm_riscv_timer {
 	__u64 frequency;
@@ -266,12 +271,15 @@ struct kvm_riscv_sbi_fwft {
 #define KVM_REG_RISCV_CSR_GENERAL	(0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT)
 #define KVM_REG_RISCV_CSR_AIA		(0x1 << KVM_REG_RISCV_SUBTYPE_SHIFT)
 #define KVM_REG_RISCV_CSR_SMSTATEEN	(0x2 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_CSR_ZICFISS	(0x3 << KVM_REG_RISCV_SUBTYPE_SHIFT)
 #define KVM_REG_RISCV_CSR_REG(name)	\
 		(offsetof(struct kvm_riscv_csr, name) / sizeof(unsigned long))
 #define KVM_REG_RISCV_CSR_AIA_REG(name)	\
 	(offsetof(struct kvm_riscv_aia_csr, name) / sizeof(unsigned long))
 #define KVM_REG_RISCV_CSR_SMSTATEEN_REG(name)  \
 	(offsetof(struct kvm_riscv_smstateen_csr, name) / sizeof(unsigned long))
+#define KVM_REG_RISCV_CSR_ZICFISS_REG(name)  \
+	(offsetof(struct kvm_riscv_zicfiss_csr, name) / sizeof(unsigned long))
 
 /* Timer registers are mapped as type 4 */
 #define KVM_REG_RISCV_TIMER		(0x04 << KVM_REG_RISCV_TYPE_SHIFT)
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index cf6e231e76e2..acdb12fcdb69 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -63,6 +63,7 @@ static void kvm_riscv_vcpu_context_reset(struct kvm_vcpu *vcpu,
 	memset(cntx, 0, sizeof(*cntx));
 	memset(csr, 0, sizeof(*csr));
 	memset(&vcpu->arch.smstateen_csr, 0, sizeof(vcpu->arch.smstateen_csr));
+	memset(&vcpu->arch.zicfiss_csr, 0, sizeof(vcpu->arch.zicfiss_csr));
 
 	/* Restore datap as it's not a part of the guest context. */
 	cntx->vector.datap = vector_datap;
@@ -720,6 +721,7 @@ static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu)
 
 static __always_inline void kvm_riscv_vcpu_swap_in_guest_state(struct kvm_vcpu *vcpu)
 {
+	struct kvm_vcpu_zicfiss_csr *zicficsr = &vcpu->arch.zicfiss_csr;
 	struct kvm_vcpu_smstateen_csr *smcsr = &vcpu->arch.smstateen_csr;
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
 
@@ -727,10 +729,13 @@ static __always_inline void kvm_riscv_vcpu_swap_in_guest_state(struct kvm_vcpu *
 	vcpu->arch.host_senvcfg = csr_swap(CSR_SENVCFG, csr->senvcfg);
 	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN))
 		vcpu->arch.host_sstateen0 = csr_swap(CSR_SSTATEEN0, smcsr->sstateen0);
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICFISS))
+		csr_write(CSR_SSP, zicficsr->ssp);
 }
 
 static __always_inline void kvm_riscv_vcpu_swap_in_host_state(struct kvm_vcpu *vcpu)
 {
+	struct kvm_vcpu_zicfiss_csr *zicficsr = &vcpu->arch.zicfiss_csr;
 	struct kvm_vcpu_smstateen_csr *smcsr = &vcpu->arch.smstateen_csr;
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
 
@@ -738,6 +743,8 @@ static __always_inline void kvm_riscv_vcpu_swap_in_host_state(struct kvm_vcpu *v
 	csr->senvcfg = csr_swap(CSR_SENVCFG, vcpu->arch.host_senvcfg);
 	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN))
 		smcsr->sstateen0 = csr_swap(CSR_SSTATEEN0, vcpu->arch.host_sstateen0);
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICFISS))
+		zicficsr->ssp = csr_swap(CSR_SSP, 0);
 }
 
 /*
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index bb920e8923c9..dd9519438546 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -355,6 +355,44 @@ static int kvm_riscv_vcpu_smstateen_get_csr(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static inline int kvm_riscv_vcpu_zicfiss_set_csr(struct kvm_vcpu *vcpu,
+						 unsigned long reg_num,
+						 unsigned long reg_val)
+{
+	struct kvm_vcpu_zicfiss_csr *csr = &vcpu->arch.zicfiss_csr;
+	unsigned long regs_max = sizeof(struct kvm_vcpu_zicfiss_csr) /
+		sizeof(unsigned long);
+
+	if (!riscv_isa_extension_available(vcpu->arch.isa, ZICFISS))
+		return -ENOENT;
+	if (reg_num >= regs_max)
+		return -ENOENT;
+
+	reg_num = array_index_nospec(reg_num, regs_max);
+
+	((unsigned long *)csr)[reg_num] = reg_val;
+	return 0;
+}
+
+static int kvm_riscv_vcpu_zicfiss_get_csr(struct kvm_vcpu *vcpu,
+					  unsigned long reg_num,
+					  unsigned long *out_val)
+{
+	struct kvm_vcpu_zicfiss_csr *csr = &vcpu->arch.zicfiss_csr;
+	unsigned long regs_max = sizeof(struct kvm_vcpu_zicfiss_csr) /
+		sizeof(unsigned long);
+
+	if (!riscv_isa_extension_available(vcpu->arch.isa, ZICFISS))
+		return -ENOENT;
+	if (reg_num >= regs_max)
+		return -ENOENT;
+
+	reg_num = array_index_nospec(reg_num, regs_max);
+
+	*out_val = ((unsigned long *)csr)[reg_num];
+	return 0;
+}
+
 static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu,
 				      const struct kvm_one_reg *reg)
 {
@@ -381,6 +419,9 @@ static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu,
 	case KVM_REG_RISCV_CSR_SMSTATEEN:
 		rc = kvm_riscv_vcpu_smstateen_get_csr(vcpu, reg_num, &reg_val);
 		break;
+	case KVM_REG_RISCV_CSR_ZICFISS:
+		rc = kvm_riscv_vcpu_zicfiss_get_csr(vcpu, reg_num, &reg_val);
+		break;
 	default:
 		rc = -ENOENT;
 		break;
@@ -423,6 +464,9 @@ static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu,
 	case KVM_REG_RISCV_CSR_SMSTATEEN:
 		rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num, reg_val);
 		break;
+	case KVM_REG_RISCV_CSR_ZICFISS:
+		rc = kvm_riscv_vcpu_zicfiss_set_csr(vcpu, reg_num, reg_val);
+		break;
 	default:
 		rc = -ENOENT;
 		break;
@@ -680,6 +724,8 @@ static inline unsigned long num_csr_regs(const struct kvm_vcpu *vcpu)
 		n += sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long);
 	if (riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN))
 		n += sizeof(struct kvm_riscv_smstateen_csr) / sizeof(unsigned long);
+	if (riscv_isa_extension_available(vcpu->arch.isa, ZICFISS))
+		n += sizeof(struct kvm_riscv_zicfiss_csr) / sizeof(unsigned long);
 
 	return n;
 }
@@ -688,7 +734,7 @@ static int copy_csr_reg_indices(const struct kvm_vcpu *vcpu,
 				u64 __user *uindices)
 {
 	int n1 = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long);
-	int n2 = 0, n3 = 0;
+	int n2 = 0, n3 = 0, n4 = 0;
 
 	/* copy general csr regs */
 	for (int i = 0; i < n1; i++) {
@@ -740,7 +786,25 @@ static int copy_csr_reg_indices(const struct kvm_vcpu *vcpu,
 		}
 	}
 
-	return n1 + n2 + n3;
+	/* copy Zicfiss csr regs */
+	if (riscv_isa_extension_available(vcpu->arch.isa, ZICFISS)) {
+		n4 = sizeof(struct kvm_riscv_zicfiss_csr) / sizeof(unsigned long);
+
+		for (int i = 0; i < n4; i++) {
+			u64 size = IS_ENABLED(CONFIG_32BIT) ?
+				   KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64;
+			u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_CSR |
+					  KVM_REG_RISCV_CSR_ZICFISS | i;
+
+			if (uindices) {
+				if (put_user(reg, uindices))
+					return -EFAULT;
+				uindices++;
+			}
+		}
+	}
+
+	return n1 + n2 + n3 + n4;
 }
 
 static inline unsigned long num_timer_regs(void)
-- 
2.55.0

[PATCH v6 5/8] RISC-V: KVM: Handle software-check exits for VCPU

[Inochi Amaoto]

The extension Zicfiss/Zicfilp introduces a software-check exception
to the privilege architecture. Delegate this exception to VS mode
when vCPU enable Zicfiss/Zicfilp so the CFI violations in VU/VS could
be reported.

Assisted-by: YuanSheng:claude-4.7-opus
Co-developed-by: Quan Zhou <zhouquan@iscas.ac.cn>
Signed-off-by: Quan Zhou <zhouquan@iscas.ac.cn>
Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
---
 arch/riscv/include/asm/csr.h | 1 +
 arch/riscv/kvm/vcpu_exit.c   | 4 ++++
 2 files changed, 5 insertions(+)

diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 31b8988f4488..224af9facf1f 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -117,6 +117,7 @@
 #define EXC_INST_PAGE_FAULT	12
 #define EXC_LOAD_PAGE_FAULT	13
 #define EXC_STORE_PAGE_FAULT	15
+#define EXC_SOFTWARE_CHECK		18
 #define EXC_INST_GUEST_PAGE_FAULT	20
 #define EXC_LOAD_GUEST_PAGE_FAULT	21
 #define EXC_VIRTUAL_INST_FAULT		22
diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c
index 0bb0c51e3c89..12eebeabdf14 100644
--- a/arch/riscv/kvm/vcpu_exit.c
+++ b/arch/riscv/kvm/vcpu_exit.c
@@ -243,6 +243,10 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		run->exit_reason = KVM_EXIT_DEBUG;
 		ret = 0;
 		break;
+	case EXC_SOFTWARE_CHECK:
+		if (vcpu->arch.cfg.henvcfg & (ENVCFG_LPE | ENVCFG_SSE))
+			ret = vcpu_redirect(vcpu, trap);
+		break;
 	default:
 		break;
 	}
-- 
2.55.0

[PATCH v6 6/8] RISC-V: KVM: Delegate SPELP bit to VS/VU mode if landing pad is enabled.

[Inochi Amaoto]

Delegate the newly added SPELP bit from Zicfilp extension to VS/VU mode
if it enables landing pad support.

Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
---
 arch/riscv/kvm/vcpu_exit.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c
index 12eebeabdf14..92a3ea7c7ffb 100644
--- a/arch/riscv/kvm/vcpu_exit.c
+++ b/arch/riscv/kvm/vcpu_exit.c
@@ -154,6 +154,13 @@ void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu,
 	/* Clear Guest SSTATUS.SIE bit */
 	vsstatus &= ~SR_SIE;
 
+	/* Change Guest SSTATUS.SPELP bit */
+	if (vcpu->arch.cfg.henvcfg & ENVCFG_LPE) {
+		vsstatus &= ~SR_SPELP;
+		vsstatus |= vcpu->arch.guest_context.sstatus & SR_SPELP;
+		vcpu->arch.guest_context.sstatus &= ~SR_SPELP;
+	}
+
 	/* Update Guest SSTATUS */
 	ncsr_write(CSR_VSSTATUS, vsstatus);
 
-- 
2.55.0

[PATCH v6 7/8] RISC-V: KVM: Add support for control-flow integrity FWFT features

[Inochi Amaoto]

Control-flow integrity is controlled through a WARL field in henvcfg.
Expose the feature only if the Zicfilp/Zicfiss is supported for VS-mode.
Allow the VMM to block access to the feature by disabling the ISA
extension in the guest.

Assisted-by: YuanSheng:claude-4.7-opus
Co-developed-by: Quan Zhou <zhouquan@iscas.ac.cn>
Signed-off-by: Quan Zhou <zhouquan@iscas.ac.cn>
Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
---
 arch/riscv/include/uapi/asm/kvm.h |   2 +
 arch/riscv/kvm/vcpu_sbi_fwft.c    | 107 ++++++++++++++++++++++++++++++
 2 files changed, 109 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index fd4c81697617..20d9959ca44f 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -248,6 +248,8 @@ struct kvm_riscv_sbi_fwft {
 	struct kvm_riscv_sbi_fwft_feature misaligned_deleg;
 	struct kvm_riscv_sbi_fwft_feature pointer_masking;
 	struct kvm_riscv_sbi_fwft_feature pte_ad_hw_updating;
+	struct kvm_riscv_sbi_fwft_feature landing_pad;
+	struct kvm_riscv_sbi_fwft_feature shadow_stack;
 };
 
 /* If you need to interpret the index values, here is the key: */
diff --git a/arch/riscv/kvm/vcpu_sbi_fwft.c b/arch/riscv/kvm/vcpu_sbi_fwft.c
index 4d474a439b29..03153fd8d15f 100644
--- a/arch/riscv/kvm/vcpu_sbi_fwft.c
+++ b/arch/riscv/kvm/vcpu_sbi_fwft.c
@@ -176,6 +176,95 @@ static long kvm_sbi_fwft_get_misaligned_delegation(struct kvm_vcpu *vcpu,
 	return SBI_SUCCESS;
 }
 
+static long kvm_sbi_fwft_set_cfi(struct kvm_vcpu *vcpu,
+				 struct kvm_sbi_fwft_config *conf,
+				 bool one_reg_access, unsigned long value,
+				 u64 flag)
+{
+	struct kvm_vcpu_config *cfg = &vcpu->arch.cfg;
+
+	if (value == 0)
+		cfg->henvcfg &= ~flag;
+	else if (value == 1)
+		cfg->henvcfg |= flag;
+	else
+		return SBI_ERR_INVALID_PARAM;
+
+	if (cfg->henvcfg & (ENVCFG_LPE | ENVCFG_SSE))
+		cfg->hedeleg |= BIT(EXC_SOFTWARE_CHECK);
+	else
+		cfg->hedeleg &= ~BIT(EXC_SOFTWARE_CHECK);
+
+	if (!one_reg_access) {
+		csr_write(CSR_HEDELEG, cfg->hedeleg);
+		/*
+		 * Both Bit LPE and SSE are in the lower part, so it is safe
+		 * to only write the henvcfg
+		 */
+		csr_write(CSR_HENVCFG, vcpu->arch.cfg.henvcfg);
+	}
+
+	return SBI_SUCCESS;
+}
+
+static bool kvm_sbi_fwft_landing_pad_supported(struct kvm_vcpu *vcpu)
+{
+	return riscv_isa_extension_available(vcpu->arch.isa, ZICFILP);
+}
+
+static void kvm_sbi_fwft_reset_landing_pad(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_config *cfg = &vcpu->arch.cfg;
+
+	kvm_sbi_fwft_env_flag_reset_helper(vcpu, ENVCFG_LPE);
+	if ((cfg->henvcfg & (ENVCFG_LPE | ENVCFG_SSE)) == 0)
+		cfg->hedeleg &= ~BIT(EXC_SOFTWARE_CHECK);
+}
+
+static long kvm_sbi_fwft_set_landing_pad(struct kvm_vcpu *vcpu,
+					 struct kvm_sbi_fwft_config *conf,
+					 bool one_reg_access, unsigned long value)
+{
+	return kvm_sbi_fwft_set_cfi(vcpu, conf, one_reg_access, value, ENVCFG_LPE);
+}
+
+static long kvm_sbi_fwft_get_landing_pad(struct kvm_vcpu *vcpu,
+					 struct kvm_sbi_fwft_config *conf,
+					 bool one_reg_access, unsigned long *value)
+{
+	return kvm_sbi_fwft_env_flag_get_helper(vcpu, conf, one_reg_access,
+						value, ENVCFG_LPE);
+}
+
+static bool kvm_sbi_fwft_shadow_stack_supported(struct kvm_vcpu *vcpu)
+{
+	return riscv_isa_extension_available(vcpu->arch.isa, ZICFISS);
+}
+
+static void kvm_sbi_fwft_reset_shadow_stack(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_config *cfg = &vcpu->arch.cfg;
+
+	kvm_sbi_fwft_env_flag_reset_helper(vcpu, ENVCFG_SSE);
+	if ((cfg->henvcfg & (ENVCFG_LPE | ENVCFG_SSE)) == 0)
+		cfg->hedeleg &= ~BIT(EXC_SOFTWARE_CHECK);
+}
+
+static long kvm_sbi_fwft_set_shadow_stack(struct kvm_vcpu *vcpu,
+					  struct kvm_sbi_fwft_config *conf,
+					  bool one_reg_access, unsigned long value)
+{
+	return kvm_sbi_fwft_set_cfi(vcpu, conf, one_reg_access, value, ENVCFG_SSE);
+}
+
+static long kvm_sbi_fwft_get_shadow_stack(struct kvm_vcpu *vcpu,
+					  struct kvm_sbi_fwft_config *conf,
+					  bool one_reg_access, unsigned long *value)
+{
+	return kvm_sbi_fwft_env_flag_get_helper(vcpu, conf, one_reg_access,
+						value, ENVCFG_SSE);
+}
+
 static bool kvm_sbi_fwft_pte_ad_hw_updating_supported(struct kvm_vcpu *vcpu)
 {
 	return riscv_isa_extension_available(vcpu->arch.isa, SVADU) &&
@@ -313,6 +402,24 @@ static const struct kvm_sbi_fwft_feature features[] = {
 		.set = kvm_sbi_fwft_set_misaligned_delegation,
 		.get = kvm_sbi_fwft_get_misaligned_delegation,
 	},
+	{
+		.id = SBI_FWFT_LANDING_PAD,
+		.first_reg_num = offsetof(struct kvm_riscv_sbi_fwft, landing_pad.enable) /
+				 sizeof(unsigned long),
+		.supported = kvm_sbi_fwft_landing_pad_supported,
+		.reset = kvm_sbi_fwft_reset_landing_pad,
+		.set = kvm_sbi_fwft_set_landing_pad,
+		.get = kvm_sbi_fwft_get_landing_pad,
+	},
+	{
+		.id = SBI_FWFT_SHADOW_STACK,
+		.first_reg_num = offsetof(struct kvm_riscv_sbi_fwft, shadow_stack.enable) /
+				 sizeof(unsigned long),
+		.supported = kvm_sbi_fwft_shadow_stack_supported,
+		.reset = kvm_sbi_fwft_reset_shadow_stack,
+		.set = kvm_sbi_fwft_set_shadow_stack,
+		.get = kvm_sbi_fwft_get_shadow_stack,
+	},
 	{
 		.id = SBI_FWFT_PTE_AD_HW_UPDATING,
 		.first_reg_num = offsetof(struct kvm_riscv_sbi_fwft, pte_ad_hw_updating.enable) /
-- 
2.55.0

[PATCH v6 8/8] KVM: riscv: selftests: add Zicfiss/Zicfilp extension to get-reg-list test

[Inochi Amaoto]

The KVM RISC-V allows Zicfiss/Zicfilp extensions for Guest/VM so
add these extensions to get-reg-list test.

Assisted-by: YuanSheng:claude-4.7-opus
Co-developed-by: Quan Zhou <zhouquan@iscas.ac.cn>
Signed-off-by: Quan Zhou <zhouquan@iscas.ac.cn>
Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
---
 .../selftests/kvm/riscv/get-reg-list.c        | 69 +++++++++++++++++++
 1 file changed, 69 insertions(+)

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 94e33b2ee796..bf3980e9db12 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -90,6 +90,8 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOP:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICCRSE:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICFILP:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICFISS:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICNTR:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICOND:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICSR:
@@ -358,6 +360,8 @@ static const char *core_id_to_str(const char *prefix, __u64 id)
 	"KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_REG(" #csr ")"
 #define RISCV_CSR_SMSTATEEN(csr) \
 	"KVM_REG_RISCV_CSR_SMSTATEEN | KVM_REG_RISCV_CSR_REG(" #csr ")"
+#define RISCV_CSR_ZICFISS(csr) \
+	"KVM_REG_RISCV_CSR_ZICFISS | KVM_REG_RISCV_CSR_ZICFISS_REG(" #csr ")"
 
 static const char *general_csr_id_to_str(__u64 reg_off)
 {
@@ -425,6 +429,18 @@ static const char *smstateen_csr_id_to_str(__u64 reg_off)
 	return NULL;
 }
 
+static const char *zicfiss_csr_id_to_str(__u64 reg_off)
+{
+	/* reg_off is the offset into struct kvm_riscv_zicfiss_csr */
+	switch (reg_off) {
+	case KVM_REG_RISCV_CSR_ZICFISS_REG(ssp):
+		return RISCV_CSR_ZICFISS(ssp);
+	}
+
+	TEST_FAIL("Unknown zicfiss csr reg: 0x%llx", reg_off);
+	return NULL;
+}
+
 static const char *csr_id_to_str(const char *prefix, __u64 id)
 {
 	__u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_CSR);
@@ -441,6 +457,8 @@ static const char *csr_id_to_str(const char *prefix, __u64 id)
 		return aia_csr_id_to_str(reg_off);
 	case KVM_REG_RISCV_CSR_SMSTATEEN:
 		return smstateen_csr_id_to_str(reg_off);
+	case KVM_REG_RISCV_CSR_ZICFISS:
+		return zicfiss_csr_id_to_str(reg_off);
 	}
 
 	return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off);
@@ -585,6 +603,8 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
 		KVM_ISA_EXT_ARR(ZICBOP),
 		KVM_ISA_EXT_ARR(ZICBOZ),
 		KVM_ISA_EXT_ARR(ZICCRSE),
+		KVM_ISA_EXT_ARR(ZICFILP),
+		KVM_ISA_EXT_ARR(ZICFISS),
 		KVM_ISA_EXT_ARR(ZICNTR),
 		KVM_ISA_EXT_ARR(ZICOND),
 		KVM_ISA_EXT_ARR(ZICSR),
@@ -748,6 +768,12 @@ static const char *sbi_fwft_id_to_str(__u64 reg_off)
 	case 6: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pte_ad_hw_updating.enable)";
 	case 7: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pte_ad_hw_updating.flags)";
 	case 8: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pte_ad_hw_updating.value)";
+	case 9: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(landing_pad.enable)";
+	case 10: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(landing_pad.flags)";
+	case 11: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(landing_pad.value)";
+	case 12: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(shadow_stack.enable)";
+	case 13: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(shadow_stack.flags)";
+	case 14: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(shadow_stack.value)";
 	}
 	return strdup_printf("KVM_REG_RISCV_SBI_FWFT | %lld /* UNKNOWN */", reg_off);
 }
@@ -954,6 +980,20 @@ static __u64 sbi_fwft_pte_ad_hw_updating_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pte_ad_hw_updating.value),
 };
 
+static __u64 sbi_fwft_landing_pad_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_FWFT,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(landing_pad.enable),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(landing_pad.flags),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(landing_pad.value),
+};
+
+static __u64 sbi_fwft_shadow_stack_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_FWFT,
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(shadow_stack.enable),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(shadow_stack.flags),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(shadow_stack.value),
+};
+
 static __u64 zicbom_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size),
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM,
@@ -969,6 +1009,11 @@ static __u64 zicboz_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ,
 };
 
+static __u64 zicfiss_regs[] = {
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_ZICFISS | KVM_REG_RISCV_CSR_ZICFISS_REG(ssp),
+	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICFISS,
+};
+
 static __u64 aia_regs[] = {
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siselect),
 	KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio1),
@@ -1220,6 +1265,8 @@ KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM);
 KVM_ISA_EXT_SUBLIST_CONFIG(zicbop, ZICBOP);
 KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ);
 KVM_ISA_EXT_SIMPLE_CONFIG(ziccrse, ZICCRSE);
+KVM_ISA_EXT_SIMPLE_CONFIG(zicfilp, ZICFILP);
+KVM_ISA_EXT_SUBLIST_CONFIG(zicfiss, ZICFISS);
 KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR);
 KVM_ISA_EXT_SIMPLE_CONFIG(zicond, ZICOND);
 KVM_ISA_EXT_SIMPLE_CONFIG(zicsr, ZICSR);
@@ -1279,6 +1326,24 @@ static struct vcpu_reg_list config_sbi_fwft_pte_ad_hw_updating = {
 	},
 };
 
+static struct vcpu_reg_list config_sbi_fwft_landing_pad = {
+	.sublists = {
+		SUBLIST_BASE,
+		SUBLIST_ISA(zicfilp, ZICFILP),
+		SUBLIST_SBI(fwft_landing_pad, FWFT),
+		{0},
+	},
+};
+
+static struct vcpu_reg_list config_sbi_fwft_shadow_stack = {
+	.sublists = {
+		SUBLIST_BASE,
+		SUBLIST_ISA(zicfiss, ZICFISS),
+		SUBLIST_SBI(fwft_shadow_stack, FWFT),
+		{0},
+	},
+};
+
 struct vcpu_reg_list *vcpu_configs[] = {
 	&config_sbi_base,
 	&config_sbi_sta,
@@ -1289,6 +1354,8 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_sbi_fwft_misaligned_deleg,
 	&config_sbi_fwft_pointer_masking,
 	&config_sbi_fwft_pte_ad_hw_updating,
+	&config_sbi_fwft_landing_pad,
+	&config_sbi_fwft_shadow_stack,
 	&config_aia,
 	&config_fp_f,
 	&config_fp_d,
@@ -1332,6 +1399,8 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_zicbop,
 	&config_zicboz,
 	&config_ziccrse,
+	&config_zicfilp,
+	&config_zicfiss,
 	&config_zicntr,
 	&config_zicond,
 	&config_zicsr,
-- 
2.55.0

Re: [PATCH v6 3/8] RISC-V: KVM: Allow Zicfiss/Zicfilp extensions for Guest/VM

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] Missing context switch logic and ONE_REG state management for the unbanked `CSR_SSP` register (Zicfiss).
- [High] Missing hardware enablement for Zicfiss (`ENVCFG_SSE`) and Zicfilp (`ENVCFG_LPE`) in the hypervisor's `henvcfg` register.
--

--- Patch [3]: [PATCH v6 3/8] RISC-V: KVM: Allow Zicfiss/Zicfilp extensions for Guest/VM ---
commit e9ffdcbcaf04d693405f356426ae62f60a2aa04c
Author: Inochi Amaoto <inochiama@gmail.com>

RISC-V: KVM: Allow Zicfiss/Zicfilp extensions for Guest/VM

This commit extends the KVM ISA extension array to allow userspace to detect
and enable the Zicfiss and Zicfilp extensions for the guest VM.

> diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
> index 7bbea8812d927..a27de850fa4cc 100644
> --- a/arch/riscv/include/uapi/asm/kvm.h
> +++ b/arch/riscv/include/uapi/asm/kvm.h
[ ... ]
> @@ -199,6 +199,8 @@ enum KVM_RISCV_ISA_EXT_ID {
>  	KVM_RISCV_ISA_EXT_ZCLSD,
>  	KVM_RISCV_ISA_EXT_ZILSD,
>  	KVM_RISCV_ISA_EXT_ZALASR,
> +	KVM_RISCV_ISA_EXT_ZICFILP,
> +	KVM_RISCV_ISA_EXT_ZICFISS,
>  	KVM_RISCV_ISA_EXT_MAX,
>  };
>  
> diff --git a/arch/riscv/kvm/isa.c b/arch/riscv/kvm/isa.c
> index 1132d909cc25c..9852a91fdecc9 100644
> --- a/arch/riscv/kvm/isa.c
> +++ b/arch/riscv/kvm/isa.c
[ ... ]
> @@ -65,6 +65,8 @@ static const unsigned long kvm_isa_ext_arr[] = {
>  	KVM_ISA_EXT_ARR(ZICBOP),
>  	KVM_ISA_EXT_ARR(ZICBOZ),
>  	KVM_ISA_EXT_ARR(ZICCRSE),
> +	KVM_ISA_EXT_ARR(ZICFILP),

[Severity: High]
Is hardware enablement for Zicfiss and Zicfilp missing in the hypervisor's
henvcfg register?

KVM populates cfg->henvcfg based on enabled ISA extensions here:

arch/riscv/kvm/vcpu_config.c:kvm_riscv_vcpu_config_ran_once() {
    ...
    if (riscv_isa_extension_available(isa, ZICBOM))
        cfg->henvcfg |= (ENVCFG_CBIE | ENVCFG_CBCFE);
    ...
}

If ENVCFG_SSE and ENVCFG_LPE are not delegated to henvcfg, will the guest
kernel's attempts to set senvcfg.SSE and senvcfg.LPE silently fail?

This would leave the fields read-only zero in the guest, preventing the
advertised CFI extensions from being used.

> +	KVM_ISA_EXT_ARR(ZICFISS),

[Severity: High]
Will the guest's CSR_SSP register be corrupted when context switching?

When a guest with Zicfiss enabled sets a valid shadow stack pointer in
CSR_SSP, and a VM exit occurs, the host scheduler may preempt the KVM vCPU
thread.

The host's exception return path overwrites CSR_SSP for the new process, and
upon switching back, the host's exception entry path zeroes CSR_SSP.

Since the C-level CSR context switch logic in
kvm_riscv_vcpu_swap_in_guest_state() and the assembly path in
__kvm_riscv_switch_to() lack save/restore operations for CSR_SSP:

arch/riscv/kvm/vcpu_switch.S:__kvm_riscv_switch_to() {
    ...
    SAVE_HOST_AND_RESTORE_GUEST_CSRS .Lkvm_switch_return
    ...
    SAVE_GUEST_AND_RESTORE_HOST_CSRS
    ...
}

Does this cause the guest to resume with a zeroed CSR_SSP and crash on its
next CFI instruction? Should CSR_SSP also be exposed via the ONE_REG
interface for state management?

>  	KVM_ISA_EXT_ARR(ZICNTR),
>  	KVM_ISA_EXT_ARR(ZICOND),
>  	KVM_ISA_EXT_ARR(ZICSR),

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260713010302.303278-1-inochiama@gmail.com?part=3

Re: [PATCH v6 6/8] RISC-V: KVM: Delegate SPELP bit to VS/VU mode if landing pad is enabled.

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] The guest's Expected Landing Pad (ELP) state is not exposed to the KVM userspace API, causing silent loss of Forward-Edge CFI protection across live migrations.
- [High] KVM fails to initialize ENVCFG_LPE and ENVCFG_SSE in vcpu->arch.cfg.henvcfg when the Zicfilp/Zicfiss extensions are enabled, rendering the SPELP trap redirection dead code and silently disabling guest CFI protections.
--

--- Patch [6]: [PATCH v6 6/8] RISC-V: KVM: Delegate SPELP bit to VS/VU mode if landing pad is enabled. ---
commit bd73a6254729060ad92677fe490d23fc4aea31a6
Author: Inochi Amaoto <inochiama@gmail.com>

RISC-V: KVM: Delegate SPELP bit to VS/VU mode if landing pad is enabled.

This commit delegates the SPELP bit from the Zicfilp extension to VS/VU
mode when landing pad support is enabled. It clears and updates the guest
SSTATUS.SPELP bit during trap redirection based on the guest context.

> diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c
> --- a/arch/riscv/kvm/vcpu_exit.c
> +++ b/arch/riscv/kvm/vcpu_exit.c

[ ... ]

> @@ -154,6 +154,13 @@ void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu,
>  	/* Clear Guest SSTATUS.SIE bit */
>  	vsstatus &= ~SR_SIE;
>  
> +	/* Change Guest SSTATUS.SPELP bit */
> +	if (vcpu->arch.cfg.henvcfg & ENVCFG_LPE) {

[Severity: High]
Will this condition ever be true? Looking at the vCPU initialization
code in kvm_riscv_vcpu_config_ran_once(), it appears KVM does not currently
set ENVCFG_LPE or ENVCFG_SSE in henvcfg when the Zicfilp or Zicfiss
extensions are available.

If ENVCFG_LPE is never initialized, this block becomes dead code, and writes
to the guest's SENVCFG CSR for landing pads would be silently ignored by the
hardware. Should the HENVCFG setup be added to
kvm_riscv_vcpu_config_ran_once() so the guest can successfully enable
CFI protections?

> +		vsstatus &= ~SR_SPELP;
> +		vsstatus |= vcpu->arch.guest_context.sstatus & SR_SPELP;
> +		vcpu->arch.guest_context.sstatus &= ~SR_SPELP;

[Severity: High]
Does this new SPELP state need to be exposed to userspace to prevent
losing the landing pad state across live migrations?

When a guest traps to the hypervisor, the hardware saves the active ELP
state, which KVM now stores in vcpu->arch.guest_context.sstatus. However,
when userspace reads the core registers during migration:

arch/riscv/kvm/vcpu_onereg.c:kvm_riscv_vcpu_get_reg_core() {
        ...
        else if (reg_num == KVM_REG_RISCV_CORE_REG(mode))
                reg_val = (cntx->sstatus & SR_SPP) ?
                                KVM_RISCV_MODE_S : KVM_RISCV_MODE_U;
        ...
}

The SPELP bit is not extracted, meaning the VMM cannot save or restore
the guest's ELP state. If a migration occurs immediately after an indirect
branch in the guest, would resuming on the destination node with ELP=0
silently bypass the Zicfilp CFI hardware check?

> +	}
> +
>  	/* Update Guest SSTATUS */
>  	ncsr_write(CSR_VSSTATUS, vsstatus);
>

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260713010302.303278-1-inochiama@gmail.com?part=6

Re: [PATCH v6 4/8] RISC-V: KVM: Add ssp context save/restore

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] KVM exposes the Zicfiss extension (shadow stack) to the guest but fails to enable it in the hypervisor environment configuration, making it unusable.
- [Medium] The patch adds a new register to the ONE_REG UAPI but fails to update the KVM RISC-V `get-reg-list` selftest.
--

--- Patch [4]: [PATCH v6 4/8] RISC-V: KVM: Add ssp context save/restore ---
commit 1dccefe0c0e59cdb4b3a936e440649fc566ba10e
Author: Inochi Amaoto <inochiama@gmail.com>

RISC-V: KVM: Add ssp context save/restore
    
Add ssp context save/restore for guest VCPUs and also add it to the
ONE_REG interface to allow its access from user space.

> diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
> index a27de850fa4cc..fd4c816976177 100644
> --- a/arch/riscv/include/uapi/asm/kvm.h
> +++ b/arch/riscv/include/uapi/asm/kvm.h
[ ... ]
> @@ -266,12 +271,15 @@ struct kvm_riscv_sbi_fwft {
>  #define KVM_REG_RISCV_CSR_GENERAL	(0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT)
>  #define KVM_REG_RISCV_CSR_AIA		(0x1 << KVM_REG_RISCV_SUBTYPE_SHIFT)
>  #define KVM_REG_RISCV_CSR_SMSTATEEN	(0x2 << KVM_REG_RISCV_SUBTYPE_SHIFT)
> +#define KVM_REG_RISCV_CSR_ZICFISS	(0x3 << KVM_REG_RISCV_SUBTYPE_SHIFT)

[Severity: Medium]
Will this new CSR subtype cause the KVM get-reg-list selftest to fail?

The get-reg-list test uses a strict list of expected registers. It appears
the new KVM_REG_RISCV_CSR_ZICFISS register subtype is missing from the CSR
identification logic in tools/testing/selftests/kvm/riscv/get-reg-list.c:csr_id_to_str(),
and the new ISA extensions (KVM_RISCV_ISA_EXT_ZICFISS and KVM_RISCV_ISA_EXT_ZICFILP)
are missing from the filter_reg() whitelist.

Could this lead to an "Unknown csr reg" failure when the tests are run on a
Zicfiss-capable host?

>  #define KVM_REG_RISCV_CSR_REG(name)	\
>  		(offsetof(struct kvm_riscv_csr, name) / sizeof(unsigned long))
>  #define KVM_REG_RISCV_CSR_AIA_REG(name)	\
>  	(offsetof(struct kvm_riscv_aia_csr, name) / sizeof(unsigned long))
>  #define KVM_REG_RISCV_CSR_SMSTATEEN_REG(name)  \
>  	(offsetof(struct kvm_riscv_smstateen_csr, name) / sizeof(unsigned long))
> +#define KVM_REG_RISCV_CSR_ZICFISS_REG(name)  \
> +	(offsetof(struct kvm_riscv_zicfiss_csr, name) / sizeof(unsigned long))
>  
>  /* Timer registers are mapped as type 4 */
>  #define KVM_REG_RISCV_TIMER		(0x04 << KVM_REG_RISCV_TYPE_SHIFT)
> diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
> index cf6e231e76e25..acdb12fcdb69a 100644
> --- a/arch/riscv/kvm/vcpu.c
> +++ b/arch/riscv/kvm/vcpu.c
[ ... ]
> @@ -720,6 +721,7 @@ static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu)
>  
>  static __always_inline void kvm_riscv_vcpu_swap_in_guest_state(struct kvm_vcpu *vcpu)
>  {
> +	struct kvm_vcpu_zicfiss_csr *zicficsr = &vcpu->arch.zicfiss_csr;
>  	struct kvm_vcpu_smstateen_csr *smcsr = &vcpu->arch.smstateen_csr;
>  	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
>  
> @@ -727,10 +729,13 @@ static __always_inline void kvm_riscv_vcpu_swap_in_guest_state(struct kvm_vcpu *
>  	vcpu->arch.host_senvcfg = csr_swap(CSR_SENVCFG, csr->senvcfg);
>  	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN))
>  		vcpu->arch.host_sstateen0 = csr_swap(CSR_SSTATEEN0, smcsr->sstateen0);
> +	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICFISS))
> +		csr_write(CSR_SSP, zicficsr->ssp);

[Severity: High]
Does KVM need to enable the shadow stack feature in henvcfg to allow the guest
to use it?

It looks like the henvcfg register must be updated to include ENVCFG_SSE when
the Zicfiss ISA extension is available, similar to the ZICBOZ/ZICBOM
handling in arch/riscv/kvm/vcpu_config.c:kvm_riscv_vcpu_config_ran_once():

	if (riscv_isa_extension_available(isa, ZICBOZ))
		cfg->henvcfg |= ENVCFG_CBZE;

Without ENVCFG_SSE set in the hypervisor environment configuration, when a
guest attempts to use shadow stack instructions, won't the hardware inject an
illegal instruction exception and potentially crash the guest application or
kernel?

Additionally, it seems SBI_FWFT_SHADOW_STACK is missing from the features[]
array in arch/riscv/kvm/vcpu_sbi_fwft.c. Would this prevent the guest from
dynamically enabling it via the SBI FWFT interface, causing it to receive
SBI_ERR_NOT_SUPPORTED instead?

>  }
>  
>  static __always_inline void kvm_riscv_vcpu_swap_in_host_state(struct kvm_vcpu *vcpu)

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260713010302.303278-1-inochiama@gmail.com?part=4