Merge tag 'riscv-for-linus-7.0-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Paul Walmsley:

 - Add support for control flow integrity for userspace processes.

   This is based on the standard RISC-V ISA extensions Zicfiss and
   Zicfilp

 - Improve ptrace behavior regarding vector registers, and add some
   selftests

 - Optimize our strlen() assembly

 - Enable the ISO-8859-1 code page as built-in, similar to ARM64, for
   EFI volume mounting

 - Clean up some code slightly, including defining copy_user_page() as
   copy_page() rather than memcpy(), aligning us with other
   architectures; and using max3() to slightly simplify an expression
   in riscv_iommu_init_check()

* tag 'riscv-for-linus-7.0-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (42 commits)
  riscv: lib: optimize strlen loop efficiency
  selftests: riscv: vstate_exec_nolibc: Use the regular prctl() function
  selftests: riscv: verify ptrace accepts valid vector csr values
  selftests: riscv: verify ptrace rejects invalid vector csr inputs
  selftests: riscv: verify syscalls discard vector context
  selftests: riscv: verify initial vector state with ptrace
  selftests: riscv: test ptrace vector interface
  riscv: ptrace: validate input vector csr registers
  riscv: csr: define vtype register elements
  riscv: vector: init vector context with proper vlenb
  riscv: ptrace: return ENODATA for inactive vector extension
  kselftest/riscv: add kselftest for user mode CFI
  riscv: add documentation for shadow stack
  riscv: add documentation for landing pad / indirect branch tracking
  riscv: create a Kconfig fragment for shadow stack and landing pad support
  arch/riscv: add dual vdso creation logic and select vdso based on hw
  arch/riscv: compile vdso with landing pad and shadow stack note
  riscv: enable kernel access to shadow stack memory via the FWFT SBI call
  riscv: add kernel command line option to opt out of user CFI
  riscv/hwprobe: add zicfilp / zicfiss enumeration in hwprobe
  ...

24 files changed, 1217 insertions, 90 deletions

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index a01f6439d62b..cabb99cadfb6 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -73,6 +73,7 @@ obj-y	+= vendor_extensions/
 obj-y	+= probes/
 obj-y	+= tests/
 obj-$(CONFIG_MMU) += vdso.o vdso/
+obj-$(CONFIG_RISCV_USER_CFI) += vdso_cfi/
 
 obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
 obj-$(CONFIG_RISCV_MISALIGNED)	+= unaligned_access_speed.o
@@ -126,3 +127,4 @@ obj-$(CONFIG_ACPI)		+= acpi.o
 obj-$(CONFIG_ACPI_NUMA)	+= acpi_numa.o
 
 obj-$(CONFIG_GENERIC_CPU_VULNERABILITIES) += bugs.o
+obj-$(CONFIG_RISCV_USER_CFI) += usercfi.o
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index 7d42d3b8a32a..af827448a609 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -51,6 +51,10 @@ void asm_offsets(void)
 #endif
 
 	OFFSET(TASK_TI_CPU_NUM, task_struct, thread_info.cpu);
+#ifdef CONFIG_RISCV_USER_CFI
+	OFFSET(TASK_TI_CFI_STATE, task_struct, thread_info.user_cfi_state);
+	OFFSET(TASK_TI_USER_SSP, task_struct, thread_info.user_cfi_state.user_shdw_stk);
+#endif
 	OFFSET(TASK_THREAD_F0,  task_struct, thread.fstate.f[0]);
 	OFFSET(TASK_THREAD_F1,  task_struct, thread.fstate.f[1]);
 	OFFSET(TASK_THREAD_F2,  task_struct, thread.fstate.f[2]);
@@ -529,4 +533,10 @@ void asm_offsets(void)
 	DEFINE(FREGS_A6,	    offsetof(struct __arch_ftrace_regs, a6));
 	DEFINE(FREGS_A7,	    offsetof(struct __arch_ftrace_regs, a7));
 #endif
+#ifdef CONFIG_RISCV_SBI
+	DEFINE(SBI_EXT_FWFT, SBI_EXT_FWFT);
+	DEFINE(SBI_EXT_FWFT_SET, SBI_EXT_FWFT_SET);
+	DEFINE(SBI_FWFT_SHADOW_STACK, SBI_FWFT_SHADOW_STACK);
+	DEFINE(SBI_FWFT_SET_FLAG_LOCK, SBI_FWFT_SET_FLAG_LOCK);
+#endif
 }
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index fa591aff9d33..1734f9a4c2fd 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -28,6 +28,7 @@
 #include <asm/vector.h>
 #include <asm/vendor_extensions.h>
 #include <asm/vendor_extensions/thead.h>
+#include <asm/usercfi.h>
 
 #define NUM_ALPHA_EXTS ('z' - 'a' + 1)
 
@@ -296,6 +297,26 @@ static int riscv_ext_svadu_validate(const struct riscv_isa_ext_data *data,
 	return 0;
 }
 
+static int riscv_cfilp_validate(const struct riscv_isa_ext_data *data,
+				const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_USER_CFI) ||
+	    (riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_FCFI))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int riscv_cfiss_validate(const struct riscv_isa_ext_data *data,
+				const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_USER_CFI) ||
+	    (riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_BCFI))
+		return -EINVAL;
+
+	return 0;
+}
+
 static const unsigned int riscv_a_exts[] = {
 	RISCV_ISA_EXT_ZAAMO,
 	RISCV_ISA_EXT_ZALRSC,
@@ -482,6 +503,10 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA_VALIDATE(zicbop, RISCV_ISA_EXT_ZICBOP, riscv_ext_zicbop_validate),
 	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts, riscv_ext_zicboz_validate),
 	__RISCV_ISA_EXT_DATA(ziccrse, RISCV_ISA_EXT_ZICCRSE),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicfilp, RISCV_ISA_EXT_ZICFILP, riscv_xlinuxenvcfg_exts,
+					  riscv_cfilp_validate),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicfiss, RISCV_ISA_EXT_ZICFISS, riscv_xlinuxenvcfg_exts,
+					  riscv_cfiss_validate),
 	__RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR),
 	__RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND),
 	__RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR),
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 9b9dec6893b8..60eb221296a6 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -92,6 +92,35 @@
 	REG_L	a0, TASK_TI_A0(tp)
 .endm
 
+/*
+ * If previous mode was U, capture shadow stack pointer and save it away
+ * Zero CSR_SSP at the same time for sanitization.
+ */
+.macro save_userssp tmp, status
+	ALTERNATIVE("nops(4)",
+		__stringify(				\
+		andi \tmp, \status, SR_SPP;		\
+		bnez \tmp, skip_ssp_save;		\
+		csrrw \tmp, CSR_SSP, x0;		\
+		REG_S \tmp, TASK_TI_USER_SSP(tp);	\
+		skip_ssp_save:),
+		0,
+		RISCV_ISA_EXT_ZICFISS,
+		CONFIG_RISCV_USER_CFI)
+.endm
+
+.macro restore_userssp tmp, status
+	ALTERNATIVE("nops(4)",
+		__stringify(				\
+		andi \tmp, \status, SR_SPP;		\
+		bnez \tmp, skip_ssp_restore;		\
+		REG_L \tmp, TASK_TI_USER_SSP(tp);	\
+		csrw CSR_SSP, \tmp;			\
+		skip_ssp_restore:),
+		0,
+		RISCV_ISA_EXT_ZICFISS,
+		CONFIG_RISCV_USER_CFI)
+.endm
 
 SYM_CODE_START(handle_exception)
 	/*
@@ -145,9 +174,14 @@ SYM_CODE_START(handle_exception)
 	 * or vector in kernel space.
 	 */
 	li t0, SR_SUM | SR_FS_VS
+#ifdef CONFIG_64BIT
+	li t1, SR_ELP
+	or t0, t0, t1
+#endif
 
 	REG_L s0, TASK_TI_USER_SP(tp)
 	csrrc s1, CSR_STATUS, t0
+	save_userssp s2, s1
 	csrr s2, CSR_EPC
 	csrr s3, CSR_TVAL
 	csrr s4, CSR_CAUSE
@@ -243,6 +277,7 @@ SYM_CODE_START_NOALIGN(ret_from_exception)
 	call riscv_v_context_nesting_end
 #endif
 	REG_L a0, PT_STATUS(sp)
+	restore_userssp s3, a0
 	/*
 	 * The current load reservation is effectively part of the processor's
 	 * state, in the sense that load reservations cannot be shared between
@@ -460,6 +495,9 @@ SYM_DATA_START_LOCAL(excp_vect_table)
 	RISCV_PTR do_page_fault   /* load page fault */
 	RISCV_PTR do_trap_unknown
 	RISCV_PTR do_page_fault   /* store page fault */
+	RISCV_PTR do_trap_unknown /* cause=16 */
+	RISCV_PTR do_trap_unknown /* cause=17 */
+	RISCV_PTR do_trap_software_check /* cause=18 is sw check exception */
 SYM_DATA_END_LABEL(excp_vect_table, SYM_L_LOCAL, excp_vect_table_end)
 
 #ifndef CONFIG_MMU
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index bdf3352acf4c..9c99c5ad6fe8 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -15,6 +15,7 @@
 #include <asm/image.h>
 #include <asm/scs.h>
 #include <asm/xip_fixup.h>
+#include <asm/usercfi.h>
 #include "efi-header.S"
 
 __HEAD
@@ -170,6 +171,19 @@ secondary_start_sbi:
 	call relocate_enable_mmu
 #endif
 	call .Lsetup_trap_vector
+#if defined(CONFIG_RISCV_SBI) && defined(CONFIG_RISCV_USER_CFI)
+	li a7, SBI_EXT_FWFT
+	li a6, SBI_EXT_FWFT_SET
+	li a0, SBI_FWFT_SHADOW_STACK
+	li a1, 1 /* enable supervisor to access shadow stack access */
+	li a2, SBI_FWFT_SET_FLAG_LOCK
+	ecall
+	beqz a0, 1f
+	la a1, riscv_nousercfi
+	li a0, CMDLINE_DISABLE_RISCV_USERCFI_BCFI
+	REG_S a0, (a1)
+1:
+#endif
 	scs_load_current
 	call smp_callin
 #endif /* CONFIG_SMP */
@@ -330,6 +344,19 @@ SYM_CODE_START(_start_kernel)
 	la tp, init_task
 	la sp, init_thread_union + THREAD_SIZE
 	addi sp, sp, -PT_SIZE_ON_STACK
+#if defined(CONFIG_RISCV_SBI) && defined(CONFIG_RISCV_USER_CFI)
+	li a7, SBI_EXT_FWFT
+	li a6, SBI_EXT_FWFT_SET
+	li a0, SBI_FWFT_SHADOW_STACK
+	li a1, 1 /* enable supervisor to access shadow stack access */
+	li a2, SBI_FWFT_SET_FLAG_LOCK
+	ecall
+	beqz a0, 1f
+	la a1, riscv_nousercfi
+	li a0, CMDLINE_DISABLE_RISCV_USERCFI_BCFI
+	REG_S a0, (a1)
+1:
+#endif
 	scs_load_current
 
 #ifdef CONFIG_KASAN
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 31a392993cb4..aacb23978f93 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -31,6 +31,7 @@
 #include <asm/vector.h>
 #include <asm/cpufeature.h>
 #include <asm/exec.h>
+#include <asm/usercfi.h>
 
 #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
 #include <linux/stackprotector.h>
@@ -92,8 +93,8 @@ void __show_regs(struct pt_regs *regs)
 		regs->s8, regs->s9, regs->s10);
 	pr_cont(" s11: " REG_FMT " t3 : " REG_FMT " t4 : " REG_FMT "\n",
 		regs->s11, regs->t3, regs->t4);
-	pr_cont(" t5 : " REG_FMT " t6 : " REG_FMT "\n",
-		regs->t5, regs->t6);
+	pr_cont(" t5 : " REG_FMT " t6 : " REG_FMT " ssp : " REG_FMT "\n",
+		regs->t5, regs->t6, get_active_shstk(current));
 
 	pr_cont("status: " REG_FMT " badaddr: " REG_FMT " cause: " REG_FMT "\n",
 		regs->status, regs->badaddr, regs->cause);
@@ -155,6 +156,19 @@ void start_thread(struct pt_regs *regs, unsigned long pc,
 	regs->epc = pc;
 	regs->sp = sp;
 
+	/*
+	 * clear shadow stack state on exec.
+	 * libc will set it later via prctl.
+	 */
+	set_shstk_status(current, false);
+	set_shstk_base(current, 0, 0);
+	set_active_shstk(current, 0);
+	/*
+	 * disable indirect branch tracking on exec.
+	 * libc will enable it later via prctl.
+	 */
+	set_indir_lp_status(current, false);
+
 #ifdef CONFIG_64BIT
 	regs->status &= ~SR_UXL;
 
@@ -226,6 +240,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	u64 clone_flags = args->flags;
 	unsigned long usp = args->stack;
 	unsigned long tls = args->tls;
+	unsigned long ssp = 0;
 	struct pt_regs *childregs = task_pt_regs(p);
 
 	/* Ensure all threads in this mm have the same pointer masking mode. */
@@ -245,11 +260,19 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		p->thread.s[1] = (unsigned long)args->fn_arg;
 		p->thread.ra = (unsigned long)ret_from_fork_kernel_asm;
 	} else {
+		/* allocate new shadow stack if needed. In case of CLONE_VM we have to */
+		ssp = shstk_alloc_thread_stack(p, args);
+		if (IS_ERR_VALUE(ssp))
+			return PTR_ERR((void *)ssp);
+
 		*childregs = *(current_pt_regs());
 		/* Turn off status.VS */
 		riscv_v_vstate_off(childregs);
 		if (usp) /* User fork */
 			childregs->sp = usp;
+		/* if needed, set new ssp */
+		if (ssp)
+			set_active_shstk(p, ssp);
 		if (clone_flags & CLONE_SETTLS)
 			childregs->tp = tls;
 		childregs->a0 = 0; /* Return value of fork() */
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index e6272d74572f..e592bd6b7665 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -19,6 +19,7 @@
 #include <linux/regset.h>
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
+#include <asm/usercfi.h>
 
 enum riscv_regset {
 	REGSET_X,
@@ -31,6 +32,9 @@ enum riscv_regset {
 #ifdef CONFIG_RISCV_ISA_SUPM
 	REGSET_TAGGED_ADDR_CTRL,
 #endif
+#ifdef CONFIG_RISCV_USER_CFI
+	REGSET_CFI,
+#endif
 };
 
 static int riscv_gpr_get(struct task_struct *target,
@@ -95,9 +99,12 @@ static int riscv_vr_get(struct task_struct *target,
 	struct __riscv_v_ext_state *vstate = &target->thread.vstate;
 	struct __riscv_v_regset_state ptrace_vstate;
 
-	if (!riscv_v_vstate_query(task_pt_regs(target)))
+	if (!(has_vector() || has_xtheadvector()))
 		return -EINVAL;
 
+	if (!riscv_v_vstate_query(task_pt_regs(target)))
+		return -ENODATA;
+
 	/*
 	 * Ensure the vector registers have been saved to the memory before
 	 * copying them to membuf.
@@ -121,6 +128,92 @@ static int riscv_vr_get(struct task_struct *target,
 	return membuf_write(&to, vstate->datap, riscv_v_vsize);
 }
 
+static int invalid_ptrace_v_csr(struct __riscv_v_ext_state *vstate,
+				struct __riscv_v_regset_state *ptrace)
+{
+	unsigned long vsew, vlmul, vfrac, vl;
+	unsigned long elen, vlen;
+	unsigned long sew, lmul;
+	unsigned long reserved;
+
+	vlen = vstate->vlenb * 8;
+	if (vstate->vlenb != ptrace->vlenb)
+		return 1;
+
+	/* do not allow to set vcsr/vxrm/vxsat reserved bits */
+	reserved = ~(CSR_VXSAT_MASK | (CSR_VXRM_MASK << CSR_VXRM_SHIFT));
+	if (ptrace->vcsr & reserved)
+		return 1;
+
+	if (has_vector()) {
+		/* do not allow to set vtype reserved bits and vill bit */
+		reserved = ~(VTYPE_VSEW | VTYPE_VLMUL | VTYPE_VMA | VTYPE_VTA);
+		if (ptrace->vtype & reserved)
+			return 1;
+
+		elen = riscv_has_extension_unlikely(RISCV_ISA_EXT_ZVE64X) ? 64 : 32;
+		vsew = (ptrace->vtype & VTYPE_VSEW) >> VTYPE_VSEW_SHIFT;
+		sew = 8 << vsew;
+
+		if (sew > elen)
+			return 1;
+
+		vfrac = (ptrace->vtype & VTYPE_VLMUL_FRAC);
+		vlmul = (ptrace->vtype & VTYPE_VLMUL);
+
+		/* RVV 1.0 spec 3.4.2: VLMUL(0x4) reserved */
+		if (vlmul == 4)
+			return 1;
+
+		/* RVV 1.0 spec 3.4.2: (LMUL < SEW_min / ELEN) reserved */
+		if (vlmul == 5 && elen == 32)
+			return 1;
+
+		/* for zero vl verify that at least one element is possible */
+		vl = ptrace->vl ? ptrace->vl : 1;
+
+		if (vfrac) {
+			/* integer 1/LMUL: VL =< VLMAX = VLEN / SEW / LMUL */
+			lmul = 2 << (3 - (vlmul - vfrac));
+			if (vlen < vl * sew * lmul)
+				return 1;
+		} else {
+			/* integer LMUL: VL =< VLMAX = LMUL * VLEN / SEW */
+			lmul = 1 << vlmul;
+			if (vl * sew > lmul * vlen)
+				return 1;
+		}
+	}
+
+	if (has_xtheadvector()) {
+		/* do not allow to set vtype reserved bits and vill bit */
+		reserved = ~(VTYPE_VSEW_THEAD | VTYPE_VLMUL_THEAD | VTYPE_VEDIV_THEAD);
+		if (ptrace->vtype & reserved)
+			return 1;
+
+		/*
+		 * THead ISA Extension spec chapter 16:
+		 * divided element extension ('Zvediv') is not part of XTheadVector
+		 */
+		if (ptrace->vtype & VTYPE_VEDIV_THEAD)
+			return 1;
+
+		vsew = (ptrace->vtype & VTYPE_VSEW_THEAD) >> VTYPE_VSEW_THEAD_SHIFT;
+		sew = 8 << vsew;
+
+		vlmul = (ptrace->vtype & VTYPE_VLMUL_THEAD);
+		lmul = 1 << vlmul;
+
+		/* for zero vl verify that at least one element is possible */
+		vl = ptrace->vl ? ptrace->vl : 1;
+
+		if (vl * sew > lmul * vlen)
+			return 1;
+	}
+
+	return 0;
+}
+
 static int riscv_vr_set(struct task_struct *target,
 			const struct user_regset *regset,
 			unsigned int pos, unsigned int count,
@@ -130,16 +223,19 @@ static int riscv_vr_set(struct task_struct *target,
 	struct __riscv_v_ext_state *vstate = &target->thread.vstate;
 	struct __riscv_v_regset_state ptrace_vstate;
 
-	if (!riscv_v_vstate_query(task_pt_regs(target)))
+	if (!(has_vector() || has_xtheadvector()))
 		return -EINVAL;
 
+	if (!riscv_v_vstate_query(task_pt_regs(target)))
+		return -ENODATA;
+
 	/* Copy rest of the vstate except datap */
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ptrace_vstate, 0,
 				 sizeof(struct __riscv_v_regset_state));
 	if (unlikely(ret))
 		return ret;
 
-	if (vstate->vlenb != ptrace_vstate.vlenb)
+	if (invalid_ptrace_v_csr(vstate, &ptrace_vstate))
 		return -EINVAL;
 
 	vstate->vstart = ptrace_vstate.vstart;
@@ -195,6 +291,87 @@ static int tagged_addr_ctrl_set(struct task_struct *target,
 }
 #endif
 
+#ifdef CONFIG_RISCV_USER_CFI
+static int riscv_cfi_get(struct task_struct *target,
+			 const struct user_regset *regset,
+			 struct membuf to)
+{
+	struct user_cfi_state user_cfi;
+	struct pt_regs *regs;
+
+	memset(&user_cfi, 0, sizeof(user_cfi));
+	regs = task_pt_regs(target);
+
+	if (is_indir_lp_enabled(target)) {
+		user_cfi.cfi_status.cfi_state |= PTRACE_CFI_LP_EN_STATE;
+		user_cfi.cfi_status.cfi_state |= is_indir_lp_locked(target) ?
+						 PTRACE_CFI_LP_LOCK_STATE : 0;
+		user_cfi.cfi_status.cfi_state |= (regs->status & SR_ELP) ?
+						PTRACE_CFI_ELP_STATE : 0;
+	}
+
+	if (is_shstk_enabled(target)) {
+		user_cfi.cfi_status.cfi_state |= (PTRACE_CFI_SS_EN_STATE |
+						  PTRACE_CFI_SS_PTR_STATE);
+		user_cfi.cfi_status.cfi_state |= is_shstk_locked(target) ?
+						 PTRACE_CFI_SS_LOCK_STATE : 0;
+		user_cfi.shstk_ptr = get_active_shstk(target);
+	}
+
+	return membuf_write(&to, &user_cfi, sizeof(user_cfi));
+}
+
+/*
+ * Does it make sense to allow enable / disable of cfi via ptrace?
+ * We don't allow enable / disable / locking control via ptrace for now.
+ * Setting the shadow stack pointer is allowed. GDB might use it to unwind or
+ * some other fixup. Similarly gdb might want to suppress elp and may want
+ * to reset elp state.
+ */
+static int riscv_cfi_set(struct task_struct *target,
+			 const struct user_regset *regset,
+			 unsigned int pos, unsigned int count,
+			 const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+	struct user_cfi_state user_cfi;
+	struct pt_regs *regs;
+
+	regs = task_pt_regs(target);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_cfi, 0, -1);
+	if (ret)
+		return ret;
+
+	/*
+	 * Not allowing enabling or locking shadow stack or landing pad
+	 * There is no disabling of shadow stack or landing pad via ptrace
+	 * rsvd field should be set to zero so that if those fields are needed in future
+	 */
+	if ((user_cfi.cfi_status.cfi_state &
+	     (PTRACE_CFI_LP_EN_STATE | PTRACE_CFI_LP_LOCK_STATE |
+	      PTRACE_CFI_SS_EN_STATE | PTRACE_CFI_SS_LOCK_STATE)) ||
+	     (user_cfi.cfi_status.cfi_state & PRACE_CFI_STATE_INVALID_MASK))
+		return -EINVAL;
+
+	/* If lpad is enabled on target and ptrace requests to set / clear elp, do that */
+	if (is_indir_lp_enabled(target)) {
+		if (user_cfi.cfi_status.cfi_state &
+		    PTRACE_CFI_ELP_STATE) /* set elp state */
+			regs->status |= SR_ELP;
+		else
+			regs->status &= ~SR_ELP; /* clear elp state */
+	}
+
+	/* If shadow stack enabled on target, set new shadow stack pointer */
+	if (is_shstk_enabled(target) &&
+	    (user_cfi.cfi_status.cfi_state & PTRACE_CFI_SS_PTR_STATE))
+		set_active_shstk(target, user_cfi.shstk_ptr);
+
+	return 0;
+}
+#endif
+
 static struct user_regset riscv_user_regset[] __ro_after_init = {
 	[REGSET_X] = {
 		USER_REGSET_NOTE_TYPE(PRSTATUS),
@@ -234,6 +411,16 @@ static struct user_regset riscv_user_regset[] __ro_after_init = {
 		.set = tagged_addr_ctrl_set,
 	},
 #endif
+#ifdef CONFIG_RISCV_USER_CFI
+	[REGSET_CFI] = {
+		.core_note_type = NT_RISCV_USER_CFI,
+		.align = sizeof(__u64),
+		.n = sizeof(struct user_cfi_state) / sizeof(__u64),
+		.size = sizeof(__u64),
+		.regset_get = riscv_cfi_get,
+		.set = riscv_cfi_set,
+	},
+#endif
 };
 
 static const struct user_regset_view riscv_user_native_view = {
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index dbb067e345f0..59784dc117e4 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -22,11 +22,13 @@
 #include <asm/vector.h>
 #include <asm/csr.h>
 #include <asm/cacheflush.h>
+#include <asm/usercfi.h>
 
 unsigned long signal_minsigstksz __ro_after_init;
 
 extern u32 __user_rt_sigreturn[2];
 static size_t riscv_v_sc_size __ro_after_init;
+static size_t riscv_zicfiss_sc_size __ro_after_init;
 
 #define DEBUG_SIG 0
 
@@ -140,6 +142,62 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
 	return copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize);
 }
 
+static long save_cfiss_state(struct pt_regs *regs, void __user *sc_cfi)
+{
+	struct __sc_riscv_cfi_state __user *state = sc_cfi;
+	unsigned long ss_ptr = 0;
+	long err = 0;
+
+	if (!is_shstk_enabled(current))
+		return 0;
+
+	/*
+	 * Save a pointer to the shadow stack itself on shadow stack as a form of token.
+	 * A token on the shadow stack gives the following properties:
+	 * - Safe save and restore for shadow stack switching. Any save of a shadow stack
+	 *   must have saved a token on the shadow stack. Similarly any restore of shadow
+	 *   stack must check the token before restore. Since writing to the shadow stack with
+	 *   address of the shadow stack itself is not easily allowed, a restore without a save
+	 *   is quite difficult for an attacker to perform.
+	 * - A natural break. A token in shadow stack provides a natural break in shadow stack
+	 *   So a single linear range can be bucketed into different shadow stack segments. Any
+	 *   sspopchk will detect the condition and fault to kernel as a sw check exception.
+	 */
+	err |= save_user_shstk(current, &ss_ptr);
+	err |= __put_user(ss_ptr, &state->ss_ptr);
+	if (unlikely(err))
+		return -EFAULT;
+
+	return riscv_zicfiss_sc_size;
+}
+
+static long __restore_cfiss_state(struct pt_regs *regs, void __user *sc_cfi)
+{
+	struct __sc_riscv_cfi_state __user *state = sc_cfi;
+	unsigned long ss_ptr = 0;
+	long err;
+
+	/*
+	 * Restore shadow stack as a form of token stored on the shadow stack itself as a safe
+	 * way to restore.
+	 * A token on the shadow stack gives the following properties:
+	 * - Safe save and restore for shadow stack switching. Any save of shadow stack
+	 *   must have saved a token on shadow stack. Similarly any restore of shadow
+	 *   stack must check the token before restore. Since writing to a shadow stack with
+	 *   the address of shadow stack itself is not easily allowed, a restore without a save
+	 *   is quite difficult for an attacker to perform.
+	 * - A natural break. A token in the shadow stack provides a natural break in shadow stack
+	 *   So a single linear range can be bucketed into different shadow stack segments.
+	 *   sspopchk will detect the condition and fault to kernel as a sw check exception.
+	 */
+	err = __copy_from_user(&ss_ptr, &state->ss_ptr, sizeof(unsigned long));
+
+	if (unlikely(err))
+		return err;
+
+	return restore_user_shstk(current, ss_ptr);
+}
+
 struct arch_ext_priv {
 	__u32 magic;
 	long (*save)(struct pt_regs *regs, void __user *sc_vec);
@@ -150,6 +208,10 @@ static struct arch_ext_priv arch_ext_list[] = {
 		.magic = RISCV_V_MAGIC,
 		.save = &save_v_state,
 	},
+	{
+		.magic = RISCV_ZICFISS_MAGIC,
+		.save = &save_cfiss_state,
+	},
 };
 
 static const size_t nr_arch_exts = ARRAY_SIZE(arch_ext_list);
@@ -202,6 +264,12 @@ static long restore_sigcontext(struct pt_regs *regs,
 
 			err = __restore_v_state(regs, sc_ext_ptr);
 			break;
+		case RISCV_ZICFISS_MAGIC:
+			if (!is_shstk_enabled(current) || size != riscv_zicfiss_sc_size)
+				return -EINVAL;
+
+			err = __restore_cfiss_state(regs, sc_ext_ptr);
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -223,6 +291,16 @@ static size_t get_rt_frame_size(bool cal_all)
 			total_context_size += riscv_v_sc_size;
 	}
 
+	if (is_shstk_enabled(current))
+		total_context_size += riscv_zicfiss_sc_size;
+
+	/*
+	 * Preserved a __riscv_ctx_hdr for END signal context header if an
+	 * extension uses __riscv_extra_ext_header
+	 */
+	if (total_context_size)
+		total_context_size += sizeof(struct __riscv_ctx_hdr);
+
 	frame_size += total_context_size;
 
 	frame_size = round_up(frame_size, 16);
@@ -359,6 +437,11 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 #ifdef CONFIG_MMU
 	regs->ra = (unsigned long)VDSO_SYMBOL(
 		current->mm->context.vdso, rt_sigreturn);
+
+	/* if bcfi is enabled x1 (ra) and x5 (t0) must match. not sure if we need this? */
+	if (is_shstk_enabled(current))
+		regs->t0 = regs->ra;
+
 #else
 	/*
 	 * For the nommu case we don't have a VDSO.  Instead we push two
@@ -487,6 +570,9 @@ void __init init_rt_signal_env(void)
 {
 	riscv_v_sc_size = sizeof(struct __riscv_ctx_hdr) +
 			  sizeof(struct __sc_riscv_v_state) + riscv_v_vsize;
+
+	riscv_zicfiss_sc_size = sizeof(struct __riscv_ctx_hdr) +
+			  sizeof(struct __sc_riscv_cfi_state);
 	/*
 	 * Determine the stack space required for guaranteed signal delivery.
 	 * The signal_minsigstksz will be populated into the AT_MINSIGSTKSZ entry
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index e6787ba7f2fc..1659d31fd288 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -24,6 +24,14 @@
 #include <vdso/vsyscall.h>
 
 
+#define EXT_KEY(isa_arg, ext, pv, missing)					\
+	do {										\
+		if (__riscv_isa_extension_available(isa_arg, RISCV_ISA_EXT_##ext))	\
+			pv |= RISCV_HWPROBE_EXT_##ext;				\
+		else									\
+			missing |= RISCV_HWPROBE_EXT_##ext;				\
+	} while (false)
+
 static void hwprobe_arch_id(struct riscv_hwprobe *pair,
 			    const struct cpumask *cpus)
 {
@@ -93,90 +101,110 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 	for_each_cpu(cpu, cpus) {
 		struct riscv_isainfo *isainfo = &hart_isa[cpu];
 
-#define EXT_KEY(ext)									\
-	do {										\
-		if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_EXT_##ext))	\
-			pair->value |= RISCV_HWPROBE_EXT_##ext;				\
-		else									\
-			missing |= RISCV_HWPROBE_EXT_##ext;				\
-	} while (false)
-
 		/*
 		 * Only use EXT_KEY() for extensions which can be exposed to userspace,
 		 * regardless of the kernel's configuration, as no other checks, besides
 		 * presence in the hart_isa bitmap, are made.
 		 */
-		EXT_KEY(ZAAMO);
-		EXT_KEY(ZABHA);
-		EXT_KEY(ZACAS);
-		EXT_KEY(ZALASR);
-		EXT_KEY(ZALRSC);
-		EXT_KEY(ZAWRS);
-		EXT_KEY(ZBA);
-		EXT_KEY(ZBB);
-		EXT_KEY(ZBC);
-		EXT_KEY(ZBKB);
-		EXT_KEY(ZBKC);
-		EXT_KEY(ZBKX);
-		EXT_KEY(ZBS);
-		EXT_KEY(ZCA);
-		EXT_KEY(ZCB);
-		EXT_KEY(ZCLSD);
-		EXT_KEY(ZCMOP);
-		EXT_KEY(ZICBOM);
-		EXT_KEY(ZICBOP);
-		EXT_KEY(ZICBOZ);
-		EXT_KEY(ZICNTR);
-		EXT_KEY(ZICOND);
-		EXT_KEY(ZIHINTNTL);
-		EXT_KEY(ZIHINTPAUSE);
-		EXT_KEY(ZIHPM);
-		EXT_KEY(ZILSD);
-		EXT_KEY(ZIMOP);
-		EXT_KEY(ZKND);
-		EXT_KEY(ZKNE);
-		EXT_KEY(ZKNH);
-		EXT_KEY(ZKSED);
-		EXT_KEY(ZKSH);
-		EXT_KEY(ZKT);
-		EXT_KEY(ZTSO);
+		EXT_KEY(isainfo->isa, ZAAMO, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZABHA, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZACAS, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZALASR, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZALRSC, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZAWRS, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZBA, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZBB, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZBC, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZBKB, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZBKC, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZBKX, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZBS, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZCA, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZCB, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZCLSD, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZCMOP, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZICBOM, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZICBOP, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZICBOZ, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZICFILP, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZICNTR, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZICOND, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZIHINTNTL, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZIHINTPAUSE, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZIHPM, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZILSD, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZIMOP, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZKND, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZKNE, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZKNH, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZKSED, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZKSH, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZKT, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZTSO, pair->value, missing);
 
 		/*
 		 * All the following extensions must depend on the kernel
 		 * support of V.
 		 */
 		if (has_vector()) {
-			EXT_KEY(ZVBB);
-			EXT_KEY(ZVBC);
-			EXT_KEY(ZVE32F);
-			EXT_KEY(ZVE32X);
-			EXT_KEY(ZVE64D);
-			EXT_KEY(ZVE64F);
-			EXT_KEY(ZVE64X);
-			EXT_KEY(ZVFBFMIN);
-			EXT_KEY(ZVFBFWMA);
-			EXT_KEY(ZVFH);
-			EXT_KEY(ZVFHMIN);
-			EXT_KEY(ZVKB);
-			EXT_KEY(ZVKG);
-			EXT_KEY(ZVKNED);
-			EXT_KEY(ZVKNHA);
-			EXT_KEY(ZVKNHB);
-			EXT_KEY(ZVKSED);
-			EXT_KEY(ZVKSH);
-			EXT_KEY(ZVKT);
+			EXT_KEY(isainfo->isa, ZVBB, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVBC, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVE32F, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVE32X, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVE64D, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVE64F, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVE64X, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVFBFMIN, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVFBFWMA, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVFH, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVFHMIN, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVKB, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVKG, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVKNED, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVKNHA, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVKNHB, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVKSED, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVKSH, pair->value, missing);
+			EXT_KEY(isainfo->isa, ZVKT, pair->value, missing);
 		}
 
-		EXT_KEY(ZCD);
-		EXT_KEY(ZCF);
-		EXT_KEY(ZFA);
-		EXT_KEY(ZFBFMIN);
-		EXT_KEY(ZFH);
-		EXT_KEY(ZFHMIN);
+		EXT_KEY(isainfo->isa, ZCD, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZCF, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZFA, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZFBFMIN, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZFH, pair->value, missing);
+		EXT_KEY(isainfo->isa, ZFHMIN, pair->value, missing);
 
 		if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM))
-			EXT_KEY(SUPM);
-#undef EXT_KEY
+			EXT_KEY(isainfo->isa, SUPM, pair->value, missing);
+	}
+
+	/* Now turn off reporting features if any CPU is missing it. */
+	pair->value &= ~missing;
+}
+
+static void hwprobe_isa_ext1(struct riscv_hwprobe *pair,
+			     const struct cpumask *cpus)
+{
+	int cpu;
+	u64 missing = 0;
+
+	pair->value = 0;
+
+	/*
+	 * Loop through and record extensions that 1) anyone has, and 2) anyone
+	 * doesn't have.
+	 */
+	for_each_cpu(cpu, cpus) {
+		struct riscv_isainfo *isainfo = &hart_isa[cpu];
+
+		/*
+		 * Only use EXT_KEY() for extensions which can be
+		 * exposed to userspace, regardless of the kernel's
+		 * configuration, as no other checks, besides presence
+		 * in the hart_isa bitmap, are made.
+		 */
+		EXT_KEY(isainfo->isa, ZICFISS, pair->value, missing);
 	}
 
 	/* Now turn off reporting features if any CPU is missing it. */
@@ -287,6 +315,10 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 		hwprobe_isa_ext0(pair, cpus);
 		break;
 
+	case RISCV_HWPROBE_KEY_IMA_EXT_1:
+		hwprobe_isa_ext1(pair, cpus);
+		break;
+
 	case RISCV_HWPROBE_KEY_CPUPERF_0:
 	case RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF:
 		pair->value = hwprobe_misaligned(cpus);
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 795b2e815ac9..22fc9b3268be 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -7,6 +7,7 @@
 
 #include <linux/syscalls.h>
 #include <asm/cacheflush.h>
+#include <asm-generic/mman-common.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 			   unsigned long prot, unsigned long flags,
@@ -16,6 +17,15 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 	if (unlikely(offset & (~PAGE_MASK >> page_shift_offset)))
 		return -EINVAL;
 
+	/*
+	 * If PROT_WRITE is specified then extend that to PROT_READ
+	 * protection_map[VM_WRITE] is now going to select shadow stack encodings.
+	 * So specifying PROT_WRITE actually should select protection_map [VM_WRITE | VM_READ]
+	 * If user wants to create shadow stack then they should use `map_shadow_stack` syscall.
+	 */
+	if (unlikely((prot & PROT_WRITE) && !(prot & PROT_READ)))
+		prot |= PROT_READ;
+
 	return ksys_mmap_pgoff(addr, len, prot, flags, fd,
 			       offset >> (PAGE_SHIFT - page_shift_offset));
 }
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 47afea4ff1a8..5fb57fad188a 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -368,6 +368,60 @@ void do_trap_ecall_u(struct pt_regs *regs)
 
 }
 
+#define CFI_TVAL_FCFI_CODE	2
+#define CFI_TVAL_BCFI_CODE	3
+/* handle cfi violations */
+bool handle_user_cfi_violation(struct pt_regs *regs)
+{
+	unsigned long tval = csr_read(CSR_TVAL);
+	bool is_fcfi = (tval == CFI_TVAL_FCFI_CODE && cpu_supports_indirect_br_lp_instr());
+	bool is_bcfi = (tval == CFI_TVAL_BCFI_CODE && cpu_supports_shadow_stack());
+
+	/*
+	 * Handle uprobe event first. The probe point can be a valid target
+	 * of indirect jumps or calls, in this case, forward cfi violation
+	 * will be triggered instead of breakpoint exception. Clear ELP flag
+	 * on sstatus image as well to avoid recurring fault.
+	 */
+	if (is_fcfi && probe_breakpoint_handler(regs)) {
+		regs->status &= ~SR_ELP;
+		return true;
+	}
+
+	if (is_fcfi || is_bcfi) {
+		do_trap_error(regs, SIGSEGV, SEGV_CPERR, regs->epc,
+			      "Oops - control flow violation");
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * software check exception is defined with risc-v cfi spec. Software check
+ * exception is raised when:
+ * a) An indirect branch doesn't land on 4 byte aligned PC or `lpad`
+ *    instruction or `label` value programmed in `lpad` instr doesn't
+ *    match with value setup in `x7`. reported code in `xtval` is 2.
+ * b) `sspopchk` instruction finds a mismatch between top of shadow stack (ssp)
+ *    and x1/x5. reported code in `xtval` is 3.
+ */
+asmlinkage __visible __trap_section void do_trap_software_check(struct pt_regs *regs)
+{
+	if (user_mode(regs)) {
+		irqentry_enter_from_user_mode(regs);
+
+		/* not a cfi violation, then merge into flow of unknown trap handler */
+		if (!handle_user_cfi_violation(regs))
+			do_trap_unknown(regs);
+
+		irqentry_exit_to_user_mode(regs);
+	} else {
+		/* sw check exception coming from kernel is a bug in kernel */
+		die(regs, "Kernel BUG");
+	}
+}
+
 #ifdef CONFIG_MMU
 asmlinkage __visible noinstr void do_page_fault(struct pt_regs *regs)
 {
diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c
new file mode 100644
index 000000000000..1adba746f164
--- /dev/null
+++ b/arch/riscv/kernel/usercfi.c
@@ -0,0 +1,542 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Rivos, Inc.
+ * Deepak Gupta <debug@rivosinc.com>
+ */
+
+#include <linux/sched.h>
+#include <linux/bitops.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/uaccess.h>
+#include <linux/sizes.h>
+#include <linux/user.h>
+#include <linux/syscalls.h>
+#include <linux/prctl.h>
+#include <asm/csr.h>
+#include <asm/usercfi.h>
+
+unsigned long riscv_nousercfi __read_mostly;
+
+#define SHSTK_ENTRY_SIZE sizeof(void *)
+
+bool is_shstk_enabled(struct task_struct *task)
+{
+	return task->thread_info.user_cfi_state.ubcfi_en;
+}
+
+bool is_shstk_allocated(struct task_struct *task)
+{
+	return task->thread_info.user_cfi_state.shdw_stk_base;
+}
+
+bool is_shstk_locked(struct task_struct *task)
+{
+	return task->thread_info.user_cfi_state.ubcfi_locked;
+}
+
+void set_shstk_base(struct task_struct *task, unsigned long shstk_addr, unsigned long size)
+{
+	task->thread_info.user_cfi_state.shdw_stk_base = shstk_addr;
+	task->thread_info.user_cfi_state.shdw_stk_size = size;
+}
+
+unsigned long get_shstk_base(struct task_struct *task, unsigned long *size)
+{
+	if (size)
+		*size = task->thread_info.user_cfi_state.shdw_stk_size;
+	return task->thread_info.user_cfi_state.shdw_stk_base;
+}
+
+void set_active_shstk(struct task_struct *task, unsigned long shstk_addr)
+{
+	task->thread_info.user_cfi_state.user_shdw_stk = shstk_addr;
+}
+
+unsigned long get_active_shstk(struct task_struct *task)
+{
+	return task->thread_info.user_cfi_state.user_shdw_stk;
+}
+
+void set_shstk_status(struct task_struct *task, bool enable)
+{
+	if (!is_user_shstk_enabled())
+		return;
+
+	task->thread_info.user_cfi_state.ubcfi_en = enable ? 1 : 0;
+
+	if (enable)
+		task->thread.envcfg |= ENVCFG_SSE;
+	else
+		task->thread.envcfg &= ~ENVCFG_SSE;
+
+	csr_write(CSR_ENVCFG, task->thread.envcfg);
+}
+
+void set_shstk_lock(struct task_struct *task)
+{
+	task->thread_info.user_cfi_state.ubcfi_locked = 1;
+}
+
+bool is_indir_lp_enabled(struct task_struct *task)
+{
+	return task->thread_info.user_cfi_state.ufcfi_en;
+}
+
+bool is_indir_lp_locked(struct task_struct *task)
+{
+	return task->thread_info.user_cfi_state.ufcfi_locked;
+}
+
+void set_indir_lp_status(struct task_struct *task, bool enable)
+{
+	if (!is_user_lpad_enabled())
+		return;
+
+	task->thread_info.user_cfi_state.ufcfi_en = enable ? 1 : 0;
+
+	if (enable)
+		task->thread.envcfg |= ENVCFG_LPE;
+	else
+		task->thread.envcfg &= ~ENVCFG_LPE;
+
+	csr_write(CSR_ENVCFG, task->thread.envcfg);
+}
+
+void set_indir_lp_lock(struct task_struct *task)
+{
+	task->thread_info.user_cfi_state.ufcfi_locked = 1;
+}
+/*
+ * If size is 0, then to be compatible with regular stack we want it to be as big as
+ * regular stack. Else PAGE_ALIGN it and return back
+ */
+static unsigned long calc_shstk_size(unsigned long size)
+{
+	if (size)
+		return PAGE_ALIGN(size);
+
+	return PAGE_ALIGN(min_t(unsigned long long, rlimit(RLIMIT_STACK), SZ_4G));
+}
+
+/*
+ * Writes on shadow stack can either be `sspush` or `ssamoswap`. `sspush` can happen
+ * implicitly on current shadow stack pointed to by CSR_SSP. `ssamoswap` takes pointer to
+ * shadow stack. To keep it simple, we plan to use `ssamoswap` to perform writes on shadow
+ * stack.
+ */
+static noinline unsigned long amo_user_shstk(unsigned long __user *addr, unsigned long val)
+{
+	/*
+	 * Never expect -1 on shadow stack. Expect return addresses and zero
+	 */
+	unsigned long swap = -1;
+
+	__enable_user_access();
+	asm goto(".option push\n"
+		".option arch, +zicfiss\n"
+		"1: ssamoswap.d %[swap], %[val], %[addr]\n"
+		_ASM_EXTABLE(1b, %l[fault])
+		".option pop\n"
+		 : [swap] "=r" (swap), [addr] "+A" (*(__force unsigned long *)addr)
+		: [val] "r" (val)
+		: "memory"
+		: fault
+		);
+	__disable_user_access();
+	return swap;
+fault:
+	__disable_user_access();
+	return -1;
+}
+
+/*
+ * Create a restore token on the shadow stack.  A token is always XLEN wide
+ * and aligned to XLEN.
+ */
+static int create_rstor_token(unsigned long ssp, unsigned long *token_addr)
+{
+	unsigned long addr;
+
+	/* Token must be aligned */
+	if (!IS_ALIGNED(ssp, SHSTK_ENTRY_SIZE))
+		return -EINVAL;
+
+	/* On RISC-V we're constructing token to be function of address itself */
+	addr = ssp - SHSTK_ENTRY_SIZE;
+
+	if (amo_user_shstk((unsigned long __user *)addr, (unsigned long)ssp) == -1)
+		return -EFAULT;
+
+	if (token_addr)
+		*token_addr = addr;
+
+	return 0;
+}
+
+/*
+ * Save user shadow stack pointer on the shadow stack itself and return a pointer to saved location.
+ * Returns -EFAULT if unsuccessful.
+ */
+int save_user_shstk(struct task_struct *tsk, unsigned long *saved_shstk_ptr)
+{
+	unsigned long ss_ptr = 0;
+	unsigned long token_loc = 0;
+	int ret = 0;
+
+	if (!saved_shstk_ptr)
+		return -EINVAL;
+
+	ss_ptr = get_active_shstk(tsk);
+	ret = create_rstor_token(ss_ptr, &token_loc);
+
+	if (!ret) {
+		*saved_shstk_ptr = token_loc;
+		set_active_shstk(tsk, token_loc);
+	}
+
+	return ret;
+}
+
+/*
+ * Restores the user shadow stack pointer from the token on the shadow stack for task 'tsk'.
+ * Returns -EFAULT if unsuccessful.
+ */
+int restore_user_shstk(struct task_struct *tsk, unsigned long shstk_ptr)
+{
+	unsigned long token = 0;
+
+	token = amo_user_shstk((unsigned long __user *)shstk_ptr, 0);
+
+	if (token == -1)
+		return -EFAULT;
+
+	/* invalid token, return EINVAL */
+	if ((token - shstk_ptr) != SHSTK_ENTRY_SIZE) {
+		pr_info_ratelimited("%s[%d]: bad restore token in %s: pc=%p sp=%p, token=%p, shstk_ptr=%p\n",
+				    tsk->comm, task_pid_nr(tsk), __func__,
+				    (void *)(task_pt_regs(tsk)->epc),
+				    (void *)(task_pt_regs(tsk)->sp),
+				    (void *)token, (void *)shstk_ptr);
+		return -EINVAL;
+	}
+
+	/* all checks passed, set active shstk and return success */
+	set_active_shstk(tsk, token);
+	return 0;
+}
+
+static unsigned long allocate_shadow_stack(unsigned long addr, unsigned long size,
+					   unsigned long token_offset, bool set_tok)
+{
+	int flags = MAP_ANONYMOUS | MAP_PRIVATE;
+	struct mm_struct *mm = current->mm;
+	unsigned long populate;
+
+	if (addr)
+		flags |= MAP_FIXED_NOREPLACE;
+
+	mmap_write_lock(mm);
+	addr = do_mmap(NULL, addr, size, PROT_READ, flags,
+		       VM_SHADOW_STACK | VM_WRITE, 0, &populate, NULL);
+	mmap_write_unlock(mm);
+
+	if (!set_tok || IS_ERR_VALUE(addr))
+		goto out;
+
+	if (create_rstor_token(addr + token_offset, NULL)) {
+		vm_munmap(addr, size);
+		return -EINVAL;
+	}
+
+out:
+	return addr;
+}
+
+SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsigned int, flags)
+{
+	bool set_tok = flags & SHADOW_STACK_SET_TOKEN;
+	unsigned long aligned_size = 0;
+
+	if (!is_user_shstk_enabled())
+		return -EOPNOTSUPP;
+
+	/* Anything other than set token should result in invalid param */
+	if (flags & ~SHADOW_STACK_SET_TOKEN)
+		return -EINVAL;
+
+	/*
+	 * Unlike other architectures, on RISC-V, SSP pointer is held in CSR_SSP and is an available
+	 * CSR in all modes. CSR accesses are performed using 12bit index programmed in instruction
+	 * itself. This provides static property on register programming and writes to CSR can't
+	 * be unintentional from programmer's perspective. As long as programmer has guarded areas
+	 * which perform writes to CSR_SSP properly, shadow stack pivoting is not possible. Since
+	 * CSR_SSP is writable by user mode, it itself can setup a shadow stack token subsequent
+	 * to allocation. Although in order to provide portablity with other architectures (because
+	 * `map_shadow_stack` is arch agnostic syscall), RISC-V will follow expectation of a token
+	 * flag in flags and if provided in flags, will setup a token at the base.
+	 */
+
+	/* If there isn't space for a token */
+	if (set_tok && size < SHSTK_ENTRY_SIZE)
+		return -ENOSPC;
+
+	if (addr && (addr & (PAGE_SIZE - 1)))
+		return -EINVAL;
+
+	aligned_size = PAGE_ALIGN(size);
+	if (aligned_size < size)
+		return -EOVERFLOW;
+
+	return allocate_shadow_stack(addr, aligned_size, size, set_tok);
+}
+
+/*
+ * This gets called during clone/clone3/fork. And is needed to allocate a shadow stack for
+ * cases where CLONE_VM is specified and thus a different stack is specified by user. We
+ * thus need a separate shadow stack too. How a separate shadow stack is specified by
+ * user is still being debated. Once that's settled, remove this part of the comment.
+ * This function simply returns 0 if shadow stacks are not supported or if separate shadow
+ * stack allocation is not needed (like in case of !CLONE_VM)
+ */
+unsigned long shstk_alloc_thread_stack(struct task_struct *tsk,
+				       const struct kernel_clone_args *args)
+{
+	unsigned long addr, size;
+
+	/* If shadow stack is not supported, return 0 */
+	if (!is_user_shstk_enabled())
+		return 0;
+
+	/*
+	 * If shadow stack is not enabled on the new thread, skip any
+	 * switch to a new shadow stack.
+	 */
+	if (!is_shstk_enabled(tsk))
+		return 0;
+
+	/*
+	 * For CLONE_VFORK the child will share the parents shadow stack.
+	 * Set base = 0 and size = 0, this is special means to track this state
+	 * so the freeing logic run for child knows to leave it alone.
+	 */
+	if (args->flags & CLONE_VFORK) {
+		set_shstk_base(tsk, 0, 0);
+		return 0;
+	}
+
+	/*
+	 * For !CLONE_VM the child will use a copy of the parents shadow
+	 * stack.
+	 */
+	if (!(args->flags & CLONE_VM))
+		return 0;
+
+	/*
+	 * reaching here means, CLONE_VM was specified and thus a separate shadow
+	 * stack is needed for new cloned thread. Note: below allocation is happening
+	 * using current mm.
+	 */
+	size = calc_shstk_size(args->stack_size);
+	addr = allocate_shadow_stack(0, size, 0, false);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
+	set_shstk_base(tsk, addr, size);
+
+	return addr + size;
+}
+
+void shstk_release(struct task_struct *tsk)
+{
+	unsigned long base = 0, size = 0;
+	/* If shadow stack is not supported or not enabled, nothing to release */
+	if (!is_user_shstk_enabled() || !is_shstk_enabled(tsk))
+		return;
+
+	/*
+	 * When fork() with CLONE_VM fails, the child (tsk) already has a
+	 * shadow stack allocated, and exit_thread() calls this function to
+	 * free it.  In this case the parent (current) and the child share
+	 * the same mm struct. Move forward only when they're same.
+	 */
+	if (!tsk->mm || tsk->mm != current->mm)
+		return;
+
+	/*
+	 * We know shadow stack is enabled but if base is NULL, then
+	 * this task is not managing its own shadow stack (CLONE_VFORK). So
+	 * skip freeing it.
+	 */
+	base = get_shstk_base(tsk, &size);
+	if (!base)
+		return;
+
+	vm_munmap(base, size);
+	set_shstk_base(tsk, 0, 0);
+}
+
+int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status)
+{
+	unsigned long bcfi_status = 0;
+
+	if (!is_user_shstk_enabled())
+		return -EINVAL;
+
+	/* this means shadow stack is enabled on the task */
+	bcfi_status |= (is_shstk_enabled(t) ? PR_SHADOW_STACK_ENABLE : 0);
+
+	return copy_to_user(status, &bcfi_status, sizeof(bcfi_status)) ? -EFAULT : 0;
+}
+
+int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status)
+{
+	unsigned long size = 0, addr = 0;
+	bool enable_shstk = false;
+
+	if (!is_user_shstk_enabled())
+		return -EINVAL;
+
+	/* Reject unknown flags */
+	if (status & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK)
+		return -EINVAL;
+
+	/* bcfi status is locked and further can't be modified by user */
+	if (is_shstk_locked(t))
+		return -EINVAL;
+
+	enable_shstk = status & PR_SHADOW_STACK_ENABLE;
+	/* Request is to enable shadow stack and shadow stack is not enabled already */
+	if (enable_shstk && !is_shstk_enabled(t)) {
+		/* shadow stack was allocated and enable request again
+		 * no need to support such usecase and return EINVAL.
+		 */
+		if (is_shstk_allocated(t))
+			return -EINVAL;
+
+		size = calc_shstk_size(0);
+		addr = allocate_shadow_stack(0, size, 0, false);
+		if (IS_ERR_VALUE(addr))
+			return -ENOMEM;
+		set_shstk_base(t, addr, size);
+		set_active_shstk(t, addr + size);
+	}
+
+	/*
+	 * If a request to disable shadow stack happens, let's go ahead and release it
+	 * Although, if CLONE_VFORKed child did this, then in that case we will end up
+	 * not releasing the shadow stack (because it might be needed in parent). Although
+	 * we will disable it for VFORKed child. And if VFORKed child tries to enable again
+	 * then in that case, it'll get entirely new shadow stack because following condition
+	 * are true
+	 *  - shadow stack was not enabled for vforked child
+	 *  - shadow stack base was anyways pointing to 0
+	 * This shouldn't be a big issue because we want parent to have availability of shadow
+	 * stack whenever VFORKed child releases resources via exit or exec but at the same
+	 * time we want VFORKed child to break away and establish new shadow stack if it desires
+	 *
+	 */
+	if (!enable_shstk)
+		shstk_release(t);
+
+	set_shstk_status(t, enable_shstk);
+	return 0;
+}
+
+int arch_lock_shadow_stack_status(struct task_struct *task,
+				  unsigned long arg)
+{
+	/* If shtstk not supported or not enabled on task, nothing to lock here */
+	if (!is_user_shstk_enabled() ||
+	    !is_shstk_enabled(task) || arg != 0)
+		return -EINVAL;
+
+	set_shstk_lock(task);
+
+	return 0;
+}
+
+int arch_get_indir_br_lp_status(struct task_struct *t, unsigned long __user *status)
+{
+	unsigned long fcfi_status = 0;
+
+	if (!is_user_lpad_enabled())
+		return -EINVAL;
+
+	/* indirect branch tracking is enabled on the task or not */
+	fcfi_status |= (is_indir_lp_enabled(t) ? PR_INDIR_BR_LP_ENABLE : 0);
+
+	return copy_to_user(status, &fcfi_status, sizeof(fcfi_status)) ? -EFAULT : 0;
+}
+
+int arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status)
+{
+	bool enable_indir_lp = false;
+
+	if (!is_user_lpad_enabled())
+		return -EINVAL;
+
+	/* indirect branch tracking is locked and further can't be modified by user */
+	if (is_indir_lp_locked(t))
+		return -EINVAL;
+
+	/* Reject unknown flags */
+	if (status & ~PR_INDIR_BR_LP_ENABLE)
+		return -EINVAL;
+
+	enable_indir_lp = (status & PR_INDIR_BR_LP_ENABLE);
+	set_indir_lp_status(t, enable_indir_lp);
+
+	return 0;
+}
+
+int arch_lock_indir_br_lp_status(struct task_struct *task,
+				 unsigned long arg)
+{
+	/*
+	 * If indirect branch tracking is not supported or not enabled on task,
+	 * nothing to lock here
+	 */
+	if (!is_user_lpad_enabled() ||
+	    !is_indir_lp_enabled(task) || arg != 0)
+		return -EINVAL;
+
+	set_indir_lp_lock(task);
+
+	return 0;
+}
+
+bool is_user_shstk_enabled(void)
+{
+	return (cpu_supports_shadow_stack() &&
+		!(riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_BCFI));
+}
+
+bool is_user_lpad_enabled(void)
+{
+	return (cpu_supports_indirect_br_lp_instr() &&
+		!(riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_FCFI));
+}
+
+static int __init setup_global_riscv_enable(char *str)
+{
+	if (strcmp(str, "all") == 0)
+		riscv_nousercfi = CMDLINE_DISABLE_RISCV_USERCFI;
+
+	if (strcmp(str, "fcfi") == 0)
+		riscv_nousercfi |= CMDLINE_DISABLE_RISCV_USERCFI_FCFI;
+
+	if (strcmp(str, "bcfi") == 0)
+		riscv_nousercfi |= CMDLINE_DISABLE_RISCV_USERCFI_BCFI;
+
+	if (riscv_nousercfi)
+		pr_info("RISC-V user CFI disabled via cmdline - shadow stack status : %s, landing pad status : %s\n",
+			(riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_BCFI) ? "disabled" :
+			"enabled", (riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_FCFI) ?
+			"disabled" : "enabled");
+
+	return 1;
+}
+
+__setup("riscv_nousercfi=", setup_global_riscv_enable);
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index 3a8e038b10a2..43f70198ac3c 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -98,6 +98,13 @@ static struct __vdso_info compat_vdso_info __ro_after_init = {
 
 static int __init vdso_init(void)
 {
+	/* Hart implements zimop, expose cfi compiled vdso */
+	if (IS_ENABLED(CONFIG_RISCV_USER_CFI) &&
+	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZIMOP)) {
+		vdso_info.vdso_code_start = vdso_cfi_start;
+		vdso_info.vdso_code_end = vdso_cfi_end;
+	}
+
 	__vdso_init(&vdso_info);
 #ifdef CONFIG_COMPAT
 	__vdso_init(&compat_vdso_info);
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 9ebb5e590f93..a842dc034571 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -17,6 +17,15 @@ ifdef CONFIG_VDSO_GETRANDOM
 vdso-syms += getrandom
 endif
 
+ifdef VDSO_CFI_BUILD
+CFI_MARCH = _zicfilp_zicfiss
+CFI_FULL = -fcf-protection=full
+CFI_SUFFIX = -cfi
+OFFSET_SUFFIX = _cfi
+ccflags-y += -DVDSO_CFI=1
+asflags-y += -DVDSO_CFI=1
+endif
+
 # Files to link into the vdso
 obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
 
@@ -27,6 +36,10 @@ endif
 ccflags-y := -fno-stack-protector
 ccflags-y += -DDISABLE_BRANCH_PROFILING
 ccflags-y += -fno-builtin
+ccflags-y += $(KBUILD_BASE_ISA)$(CFI_MARCH)
+ccflags-y += $(CFI_FULL)
+asflags-y += $(KBUILD_BASE_ISA)$(CFI_MARCH)
+asflags-y += $(CFI_FULL)
 
 ifneq ($(c-gettimeofday-y),)
   CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y)
@@ -39,13 +52,20 @@ endif
 CFLAGS_hwprobe.o += -fPIC
 
 # Build rules
-targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds
+vdso_offsets := vdso$(if $(VDSO_CFI_BUILD),$(CFI_SUFFIX),)-offsets.h
+vdso_o := vdso$(if $(VDSO_CFI_BUILD),$(CFI_SUFFIX),).o
+vdso_so := vdso$(if $(VDSO_CFI_BUILD),$(CFI_SUFFIX),).so
+vdso_so_dbg := vdso$(if $(VDSO_CFI_BUILD),$(CFI_SUFFIX),).so.dbg
+vdso_lds := vdso.lds
+
+targets := $(obj-vdso) $(vdso_so) $(vdso_so_dbg) $(vdso_lds)
+
 obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
 
-obj-y += vdso.o
-CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
+obj-y += vdso$(if $(VDSO_CFI_BUILD),$(CFI_SUFFIX),).o
+CPPFLAGS_$(vdso_lds) += -P -C -U$(ARCH)
 ifneq ($(filter vgettimeofday, $(vdso-syms)),)
-CPPFLAGS_vdso.lds += -DHAS_VGETTIMEOFDAY
+CPPFLAGS_$(vdso_lds) += -DHAS_VGETTIMEOFDAY
 endif
 
 # Disable -pg to prevent insert call site
@@ -54,12 +74,12 @@ CFLAGS_REMOVE_getrandom.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
 CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
 
 # Force dependency
-$(obj)/vdso.o: $(obj)/vdso.so
+$(obj)/$(vdso_o): $(obj)/$(vdso_so)
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
+$(obj)/$(vdso_so_dbg): $(obj)/$(vdso_lds) $(obj-vdso) FORCE
 	$(call if_changed,vdsold_and_check)
-LDFLAGS_vdso.so.dbg = -shared -soname=linux-vdso.so.1 \
+LDFLAGS_$(vdso_so_dbg) = -shared -soname=linux-vdso.so.1 \
 	--build-id=sha1 --eh-frame-hdr
 
 # strip rule for the .so file
@@ -70,16 +90,16 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 # Generate VDSO offsets using helper script
 gen-vdsosym := $(src)/gen_vdso_offsets.sh
 quiet_cmd_vdsosym = VDSOSYM $@
-	cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
+	cmd_vdsosym = $(NM) $< | $(gen-vdsosym) $(OFFSET_SUFFIX) | LC_ALL=C sort > $@
 
-include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
+include/generated/$(vdso_offsets): $(obj)/$(vdso_so_dbg) FORCE
 	$(call if_changed,vdsosym)
 
 # actual build commands
 # The DSO images are built using a special linker script
 # Make sure only to export the intended __vdso_xxx symbol offsets.
 quiet_cmd_vdsold_and_check = VDSOLD  $@
-      cmd_vdsold_and_check = $(LD) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \
+      cmd_vdsold_and_check = $(LD) $(CFI_FULL) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \
                    $(OBJCOPY) $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
                    rm $@.tmp && \
                    $(cmd_vdso_check)
diff --git a/arch/riscv/kernel/vdso/flush_icache.S b/arch/riscv/kernel/vdso/flush_icache.S
index 8f884227e8bc..e4c56970905e 100644
--- a/arch/riscv/kernel/vdso/flush_icache.S
+++ b/arch/riscv/kernel/vdso/flush_icache.S
@@ -5,11 +5,13 @@
 
 #include <linux/linkage.h>
 #include <asm/unistd.h>
+#include <asm/assembler.h>
 
 	.text
 /* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */
 SYM_FUNC_START(__vdso_flush_icache)
 	.cfi_startproc
+	vdso_lpad
 #ifdef CONFIG_SMP
 	li a7, __NR_riscv_flush_icache
 	ecall
@@ -20,3 +22,5 @@ SYM_FUNC_START(__vdso_flush_icache)
 	ret
 	.cfi_endproc
 SYM_FUNC_END(__vdso_flush_icache)
+
+emit_riscv_feature_1_and
diff --git a/arch/riscv/kernel/vdso/gen_vdso_offsets.sh b/arch/riscv/kernel/vdso/gen_vdso_offsets.sh
index c2e5613f3495..bd5d5afaaa14 100755
--- a/arch/riscv/kernel/vdso/gen_vdso_offsets.sh
+++ b/arch/riscv/kernel/vdso/gen_vdso_offsets.sh
@@ -2,4 +2,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
 LC_ALL=C
-sed -n -e 's/^[0]\+\(0[0-9a-fA-F]*\) . \(__vdso_[a-zA-Z0-9_]*\)$/\#define \2_offset\t0x\1/p'
+SUFFIX=${1:-""}
+sed -n -e \
+'s/^[0]\+\(0[0-9a-fA-F]*\) . \(__vdso_[a-zA-Z0-9_]*\)$/\#define \2'$SUFFIX'_offset\t0x\1/p'
diff --git a/arch/riscv/kernel/vdso/getcpu.S b/arch/riscv/kernel/vdso/getcpu.S
index 9c1bd531907f..5c1ecc4e1465 100644
--- a/arch/riscv/kernel/vdso/getcpu.S
+++ b/arch/riscv/kernel/vdso/getcpu.S
@@ -5,14 +5,18 @@
 
 #include <linux/linkage.h>
 #include <asm/unistd.h>
+#include <asm/assembler.h>
 
 	.text
 /* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */
 SYM_FUNC_START(__vdso_getcpu)
 	.cfi_startproc
+	vdso_lpad
 	/* For now, just do the syscall. */
 	li a7, __NR_getcpu
 	ecall
 	ret
 	.cfi_endproc
 SYM_FUNC_END(__vdso_getcpu)
+
+emit_riscv_feature_1_and
diff --git a/arch/riscv/kernel/vdso/note.S b/arch/riscv/kernel/vdso/note.S
index 2a956c942211..3d92cc956b95 100644
--- a/arch/riscv/kernel/vdso/note.S
+++ b/arch/riscv/kernel/vdso/note.S
@@ -6,7 +6,10 @@
 
 #include <linux/elfnote.h>
 #include <linux/version.h>
+#include <asm/assembler.h>
 
 ELFNOTE_START(Linux, 0, "a")
 	.long LINUX_VERSION_CODE
 ELFNOTE_END
+
+emit_riscv_feature_1_and
diff --git a/arch/riscv/kernel/vdso/rt_sigreturn.S b/arch/riscv/kernel/vdso/rt_sigreturn.S
index 3dc022aa8931..e82987dc3739 100644
--- a/arch/riscv/kernel/vdso/rt_sigreturn.S
+++ b/arch/riscv/kernel/vdso/rt_sigreturn.S
@@ -5,12 +5,16 @@
 
 #include <linux/linkage.h>
 #include <asm/unistd.h>
+#include <asm/assembler.h>
 
 	.text
 SYM_FUNC_START(__vdso_rt_sigreturn)
 	.cfi_startproc
 	.cfi_signal_frame
+	vdso_lpad
 	li a7, __NR_rt_sigreturn
 	ecall
 	.cfi_endproc
 SYM_FUNC_END(__vdso_rt_sigreturn)
+
+emit_riscv_feature_1_and
diff --git a/arch/riscv/kernel/vdso/sys_hwprobe.S b/arch/riscv/kernel/vdso/sys_hwprobe.S
index 77e57f830521..f1694451a60c 100644
--- a/arch/riscv/kernel/vdso/sys_hwprobe.S
+++ b/arch/riscv/kernel/vdso/sys_hwprobe.S
@@ -3,13 +3,17 @@
 
 #include <linux/linkage.h>
 #include <asm/unistd.h>
+#include <asm/assembler.h>
 
 .text
 SYM_FUNC_START(riscv_hwprobe)
 	.cfi_startproc
+	vdso_lpad
 	li a7, __NR_riscv_hwprobe
 	ecall
 	ret
 
 	.cfi_endproc
 SYM_FUNC_END(riscv_hwprobe)
+
+emit_riscv_feature_1_and
diff --git a/arch/riscv/kernel/vdso/vgetrandom-chacha.S b/arch/riscv/kernel/vdso/vgetrandom-chacha.S
index 5f0dad8f2373..916ab30a88f7 100644
--- a/arch/riscv/kernel/vdso/vgetrandom-chacha.S
+++ b/arch/riscv/kernel/vdso/vgetrandom-chacha.S
@@ -7,6 +7,7 @@
 
 #include <asm/asm.h>
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 .text
 
@@ -74,7 +75,7 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 #define _20		20, 20, 20, 20
 #define _24		24, 24, 24, 24
 #define _25		25, 25, 25, 25
-
+	vdso_lpad
 	/*
 	 * The ABI requires s0-s9 saved.
 	 * This does not violate the stack-less requirement: no sensitive data
@@ -247,3 +248,5 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 
 	ret
 SYM_FUNC_END(__arch_chacha20_blocks_nostack)
+
+emit_riscv_feature_1_and
diff --git a/arch/riscv/kernel/vdso_cfi/Makefile b/arch/riscv/kernel/vdso_cfi/Makefile
new file mode 100644
index 000000000000..8ebd190782b0
--- /dev/null
+++ b/arch/riscv/kernel/vdso_cfi/Makefile
@@ -0,0 +1,25 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# RISC-V VDSO CFI Makefile
+# This Makefile builds the VDSO with CFI support when CONFIG_RISCV_USER_CFI is enabled
+
+# setting VDSO_CFI_BUILD triggers build for vdso differently
+VDSO_CFI_BUILD := 1
+
+# Set the source directory to the main vdso directory
+src := $(srctree)/arch/riscv/kernel/vdso
+
+# Copy all .S and .c files from vdso directory to vdso_cfi object build directory
+vdso_c_sources := $(wildcard $(src)/*.c)
+vdso_S_sources := $(wildcard $(src)/*.S)
+vdso_c_objects := $(addprefix $(obj)/, $(notdir $(vdso_c_sources)))
+vdso_S_objects := $(addprefix $(obj)/, $(notdir $(vdso_S_sources)))
+
+$(vdso_S_objects): $(obj)/%.S: $(src)/%.S
+	$(Q)cp $< $@
+
+$(vdso_c_objects): $(obj)/%.c: $(src)/%.c
+	$(Q)cp $< $@
+
+# Include the main VDSO Makefile which contains all the build rules and sources
+# The VDSO_CFI_BUILD variable will be passed to it to enable CFI compilation
+include $(src)/Makefile
diff --git a/arch/riscv/kernel/vdso_cfi/vdso-cfi.S b/arch/riscv/kernel/vdso_cfi/vdso-cfi.S
new file mode 100644
index 000000000000..d426f6accb35
--- /dev/null
+++ b/arch/riscv/kernel/vdso_cfi/vdso-cfi.S
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2025 Rivos, Inc
+ */
+
+#define	vdso_start	vdso_cfi_start
+#define	vdso_end	vdso_cfi_end
+
+#define __VDSO_PATH "arch/riscv/kernel/vdso_cfi/vdso-cfi.so"
+
+#include "../vdso/vdso.S"
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 3ed071dab9d8..b112166d51e9 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -111,8 +111,8 @@ bool insn_is_vector(u32 insn_buf)
 	return false;
 }
 
-static int riscv_v_thread_zalloc(struct kmem_cache *cache,
-				 struct __riscv_v_ext_state *ctx)
+static int riscv_v_thread_ctx_alloc(struct kmem_cache *cache,
+				    struct __riscv_v_ext_state *ctx)
 {
 	void *datap;
 
@@ -122,13 +122,15 @@ static int riscv_v_thread_zalloc(struct kmem_cache *cache,
 
 	ctx->datap = datap;
 	memset(ctx, 0, offsetof(struct __riscv_v_ext_state, datap));
+	ctx->vlenb = riscv_v_vsize / 32;
+
 	return 0;
 }
 
 void riscv_v_thread_alloc(struct task_struct *tsk)
 {
 #ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
-	riscv_v_thread_zalloc(riscv_v_kernel_cachep, &tsk->thread.kernel_vstate);
+	riscv_v_thread_ctx_alloc(riscv_v_kernel_cachep, &tsk->thread.kernel_vstate);
 #endif
 }
 
@@ -214,12 +216,14 @@ bool riscv_v_first_use_handler(struct pt_regs *regs)
 	 * context where VS has been off. So, try to allocate the user's V
 	 * context and resume execution.
 	 */
-	if (riscv_v_thread_zalloc(riscv_v_user_cachep, &current->thread.vstate)) {
+	if (riscv_v_thread_ctx_alloc(riscv_v_user_cachep, &current->thread.vstate)) {
 		force_sig(SIGBUS);
 		return true;
 	}
+
 	riscv_v_vstate_on(regs);
 	riscv_v_vstate_set_restore(current, regs);
+
 	return true;
 }