riscv: Implement arch-agnostic shadow stack prctls

Implement an architecture-agnostic prctl() interface for setting and
getting shadow stack status.  The prctls implemented are
PR_GET_SHADOW_STACK_STATUS, PR_SET_SHADOW_STACK_STATUS and
PR_LOCK_SHADOW_STACK_STATUS.

As part of PR_SET_SHADOW_STACK_STATUS/PR_GET_SHADOW_STACK_STATUS, only
PR_SHADOW_STACK_ENABLE is implemented because RISCV allows each mode to
write to their own shadow stack using 'sspush' or 'ssamoswap'.

PR_LOCK_SHADOW_STACK_STATUS locks the current shadow stack enablement
configuration.

Reviewed-by: Zong Li <zong.li@sifive.com>
Signed-off-by: Deepak Gupta <debug@rivosinc.com>
Tested-by: Andreas Korb <andreas.korb@aisec.fraunhofer.de> # QEMU, custom CVA6
Tested-by: Valentin Haudiquet <valentin.haudiquet@canonical.com>
Link: https://patch.msgid.link/20251112-v5_user_cfi_series-v23-12-b55691eacf4f@rivosinc.com
[pjw@kernel.org: cleaned up patch description]
Signed-off-by: Paul Walmsley <pjw@kernel.org>

arch/riscv/include/asm/usercfi.h

@@ -7,6 +7,7 @@
 
 #ifndef __ASSEMBLER__
 #include <linux/types.h>
+#include <linux/prctl.h>
 
 struct task_struct;
 struct kernel_clone_args;
@@ -14,6 +15,7 @@ struct kernel_clone_args;
 #ifdef CONFIG_RISCV_USER_CFI
 struct cfi_state {
 	unsigned long ubcfi_en : 1; /* Enable for backward cfi. */
+	unsigned long ubcfi_locked : 1;
 	unsigned long user_shdw_stk; /* Current user shadow stack pointer */
 	unsigned long shdw_stk_base; /* Base address of shadow stack */
 	unsigned long shdw_stk_size; /* size of shadow stack */
@@ -26,6 +28,12 @@ void set_shstk_base(struct task_struct *task, unsigned long shstk_addr, unsigned
 unsigned long get_shstk_base(struct task_struct *task, unsigned long *size);
 void set_active_shstk(struct task_struct *task, unsigned long shstk_addr);
 bool is_shstk_enabled(struct task_struct *task);
+bool is_shstk_locked(struct task_struct *task);
+bool is_shstk_allocated(struct task_struct *task);
+void set_shstk_lock(struct task_struct *task);
+void set_shstk_status(struct task_struct *task, bool enable);
+
+#define PR_SHADOW_STACK_SUPPORTED_STATUS_MASK (PR_SHADOW_STACK_ENABLE)
 
 #else
 
@@ -41,6 +49,14 @@ bool is_shstk_enabled(struct task_struct *task);
 
 #define is_shstk_enabled(task) false
 
+#define is_shstk_locked(task) false
+
+#define is_shstk_allocated(task) false
+
+#define set_shstk_lock(task) do {} while (0)
+
+#define set_shstk_status(task, enable) do {} while (0)
+
 #endif /* CONFIG_RISCV_USER_CFI */
 
 #endif /* __ASSEMBLER__ */

arch/riscv/kernel/process.c

@@ -156,6 +156,14 @@ 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);
+
 #ifdef CONFIG_64BIT
 	regs->status &= ~SR_UXL;
 

arch/riscv/kernel/usercfi.c

@@ -24,6 +24,16 @@ 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;
@@ -42,6 +52,26 @@ void set_active_shstk(struct task_struct *task, unsigned long shstk_addr)
 	task->thread_info.user_cfi_state.user_shdw_stk = shstk_addr;
 }
 
+void set_shstk_status(struct task_struct *task, bool enable)
+{
+	if (!cpu_supports_shadow_stack())
+		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;
+}
+
 /*
  * 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
@@ -258,3 +288,83 @@ void shstk_release(struct task_struct *tsk)
 	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 (!cpu_supports_shadow_stack())
+		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 (!cpu_supports_shadow_stack())
+		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 (!cpu_supports_shadow_stack() ||
+	    !is_shstk_enabled(task) || arg != 0)
+		return -EINVAL;
+
+	set_shstk_lock(task);
+
+	return 0;
+}