diff --git a/core/platform/src/lib.rs b/core/platform/src/lib.rs
index d474f2b..e189975 100644
--- a/core/platform/src/lib.rs
+++ b/core/platform/src/lib.rs
@@ -8,13 +8,15 @@
 pub mod return_variant;
 mod syscalls;
 mod syscalls_impl;
+mod yield_types;
 
 pub use async_traits::{CallbackContext, FreeCallback, Locator, MethodCallback};
 pub use command_return::CommandReturn;
 pub use error_code::ErrorCode;
-pub use raw_syscalls::{OneArgMemop, RawSyscalls, YieldType, ZeroArgMemop};
+pub use raw_syscalls::RawSyscalls;
 pub use return_variant::ReturnVariant;
 pub use syscalls::Syscalls;
+pub use yield_types::YieldNoWaitReturn;
 
 #[cfg(test)]
 mod command_return_tests;
diff --git a/core/platform/src/raw_syscalls.rs b/core/platform/src/raw_syscalls.rs
index f4e37b8..5bea527 100644
--- a/core/platform/src/raw_syscalls.rs
+++ b/core/platform/src/raw_syscalls.rs
@@ -3,98 +3,77 @@
 
 /// `RawSyscalls` allows a fake Tock kernel to be injected into components for
 /// unit testing. It is implemented by `libtock_runtime::TockSyscalls` and
-/// `libtock_unittest::FakeSyscalls`. **Components should not use `RawSyscalls`
+/// `libtock_unittest::fake::Kernel`. **Components should not use `RawSyscalls`
 /// directly; instead, use the `Syscalls` trait, which provides higher-level
 /// interfaces to the system calls.**
 
-// RawSyscalls is designed to minimize the amount of handwritten assembly code
-// needed without generating unnecessary instructions. This comment describes
-// the thought process that led to the choice of methods for RawSyscalls. There
-// are a few major considerations affecting its design:
+// The RawSyscalls trait is designed to minimize the complexity and size of its
+// implementation, as its implementation is difficult to test (it cannot be used
+// in unit tests, with sanitizers, or in Miri). It is also designed to minimize
+// the number of unnecessary instructions it generates.
 //
-//     1. Most system calls only clobber r0-r4 (*), while yield has a far longer
-//        clobber list. As such, yield must have its own assembly
-//        implementation.
-//     2. The compiler is unable to optimize away unused arguments. For example,
-//        memop's "get process RAM start address" operation only needs r0 set,
-//        while memop's "break" operation needs both r0 and r1 set. If our
-//        inline assembly calls "get process RAM start address" but sets both r0
-//        and r1, the compiler doesn't know that r1 will be
-//        ignored so setting that register will not be optimized away. Therefore
-//        we want to set the minimum number of argument registers possible.
-//     3. The cost of specifying unused return registers is only that of
-//        unnecessarily marking a register as clobbered. Explanation: After
-//        inlining, an unused register is marked as "changed by the assembly"
-//        but can immediately be re-used by the compiler, which is the same as a
-//        clobbered register. System calls should generally be
-//        inlined -- and even if they aren't, the unused return values will
-//        probably be passed in caller-saved registers (this is true for the C
-//        ABI, so probably true for the Rust ABI), which are treated as
-//        clobbered regardless.
+// Convention: This file uses the same register naming conventions as the Tock
+// 2.0 syscall TRD. Registers r0-r4 correspond to ARM registers r0-r4 and RISC-V
+// registers a0-a4.
 //
-// (*) When this file refers to registers, it uses the same naming convention as
-// the Tock 2.0 syscalls TRD. Registers r0-r4 correspond to ARM registers r0-r4
-// and RISC-V registers a0-a4.
+// Theoretically, RawSyscalls could consist of a single raw system call. To
+// start, something like this should work:
 //
-// Currently, yield takes exactly one argument (to specify what yield type to
-// do). Therefore we only need one raw yield call.
+//   unsafe fn syscall<const CLASS: usize>([usize; 4]) -> [usize; 4];
 //
-// Based on these considerations, it would make sense to have the following
-// methods:
-//     yield
-//     zero_arg_syscall
-//     one_arg_syscall
-//     two_arg_syscall
-//     three_arg_syscall
-//     four_arg_syscall
+// However, this will not work with Miri's -Zmiri-track-raw-pointers flag, as it
+// causes pointers passed to the kernel via the Allow system calls to be
+// untagged. In order to work with -Zmiri-track-raw-pointers, we need to pass
+// pointers for the register values. Rust's closest analogue to C's void pointer
+// is *mut () or *const (); we use *mut () because it is shorter:
 //
-// However, there are no system calls that take 0 or 3 arguments, so we do not
-// need the corresponding methods. This leaves yield, 1-arg, 2-arg, and 4-arg
-// system calls.
+//   unsafe fn syscall<const CLASS: usize>([*mut (); 4]) -> [*mut (); 4];
 //
-// The 1-arg and 2-arg system calls are only used for memop. Memop currently has
-// the property that none of its operations can lead to undefined behavior.
-// Therefore, we can rename the 1-arg and 2-arg system calls to zero_arg_memop
-// and one_arg_memop and make them safe methods (the argument counts change
-// because the number of system call arguments is one greater than the number of
-// arguments passed to the specific op).
+// Using a single system call has a major inefficiency. The single raw system
+// call would need to clobber every register that any system call can clobber.
+// Yield has a far longer clobber list than most system calls, so this would be
+// inefficient for the majority of system calls. As a result, we can split yield
+// out into its own function, giving the following API:
 //
-// This only leaves four_arg_syscall, which is used to implement subscribe,
-// command, read-write allow, and read-only allow.
+//   unsafe fn yield([*mut (); 4]) -> [*mut (); 4];
+//   unsafe fn syscall<const CLASS: usize>([*mut (); 4]) -> [*mut (); 4];
 //
-// Therefore the final design has 4 methods:
-//     yield
-//     zero_arg_memop
-//     one_arg_memop
-//     four_arg_syscall
+// There is one significant inefficiency remaining. Many system calls, such as
+// memop's "get RAM start address" operation, do not need to set all four
+// arguments. The compiler cannot optimize away this inefficiency, so to remove
+// it we need to split the system calls up based on the number of arguments they
+// take:
 //
-// If a new system call class that uses fewer than four arguments is added, then
-// the above list will need to be revised.
+//   unsafe fn yield0([*mut (); 0]) -> [*mut (); 4];
+//   unsafe fn yield1([*mut (); 1]) -> [*mut (); 4];
+//   unsafe fn yield2([*mut (); 2]) -> [*mut (); 4];
+//   unsafe fn yield3([*mut (); 3]) -> [*mut (); 4];
+//   unsafe fn yield4([*mut (); 4]) -> [*mut (); 4];
+//   unsafe fn syscall0<const CLASS: usize>([*mut (); 0]) -> [*mut (); 4];
+//   unsafe fn syscall1<const CLASS: usize>([*mut (); 1]) -> [*mut (); 4];
+//   unsafe fn syscall2<const CLASS: usize>([*mut (); 2]) -> [*mut (); 4];
+//   unsafe fn syscall3<const CLASS: usize>([*mut (); 3]) -> [*mut (); 4];
+//   unsafe fn syscall4<const CLASS: usize>([*mut (); 4]) -> [*mut (); 4];
 //
-// Note that `command` always needs to use four_arg_syscall, even when calling a
-// command with fewer arguments, because we don't want to leak the
-// (possibly secret) values in the r2 and r3 registers to untrusted capsules.
-// Yield and memop do not have this concern and can leave arbitrary data in r2
-// and r3, because they are implemented by the core kernel, which is trusted.
+// However, not all of these are used! If we remove the system calls that are
+// unused, we are left with the following:
 //
-// The success type for Memop calls depends on the operation performed. However,
-// all *currently defined* memop operations return either Success or Success
-// with u32. Therefore, the memop implementations only need to mark r0 and r1 as
-// clobbered, not r2 and r3. This choice of clobbers will need to be revisited
-// if and when a memop operation that returns more data is added.
+//   unsafe fn yield1([*mut (); 1]) -> [*mut (); 4];
+//   unsafe fn yield2([*mut (); 2]) -> [*mut (); 4];
+//   unsafe fn syscall1<const CLASS: usize>([*mut (); 1]) -> [*mut (); 4];
+//   unsafe fn syscall2<const CLASS: usize>([*mut (); 2]) -> [*mut (); 4];
+//   unsafe fn syscall4<const CLASS: usize>([*mut (); 4]) -> [*mut (); 4];
 //
-// The decision of where to use u32 and usize can be a bit tricky. The Tock
-// syscall ABI is currently only specified for 32-bit systems, so on real Tock
-// systems both types match the size of a register, but the unit test
-// environment can be either 32 bit or 64 bit. This interface uses usize for
-// values that can contain pointers, so that pointers are not truncated in the
-// unit test environment. To keep types as consistent as possible, it uses u32
-// for all values that cannot be pointers.
-pub trait RawSyscalls {
-    // raw_yield should:
+// These system calls are refined further individually, which is documented on
+// a per-function basis.
+pub unsafe trait RawSyscalls {
+    // yield1 can only be used to call `yield-wait`, which does not have a
+    // return value. To simplify the assembly implementation, we remove its
+    // return value.
+    //
+    // yield1 should:
     //     1. Call syscall class 0
-    //     2. Use register r0 for input and output as an inlateout register,
-    //        passing in r0_in and returning its value.
+    //     2. Pass in r0 as an inlateout register.
     //     3. Mark all caller-saved registers as lateout clobbers.
     //     4. NOT provide any of the following options:
     //            pure             (yield has side effects)
@@ -103,142 +82,106 @@
     //            preserves_flags  (a callback can change flags)
     //            noreturn         (yield is expected to return)
     //            nostack          (a callback needs the stack)
-    //
-    // Design note: This is safe because the yield types that currently exist
-    // are safe. If an unsafe yield type is added, we will need to make
-    // raw_yield unsafe. Although raw_yield shouldn't be called by code outside
-    // this crate, it can be, so that is a backwards-incompatible change. We
-    // pass YieldType rather than a usize because if we used usize directly then
-    // this API becomes unsound if the kernel adds support for an unsafe yield
-    // type (or even one that takes one more argument).
-    /// `raw_yield` should only be called by `libtock_platform`.
-    fn raw_yield(r0_in: YieldType) -> u32;
-
-    // four_arg_syscall is used to invoke the subscribe, command, read-write
-    // allow, and read-only allow system calls.
-    //
-    // four_arg_syscall's inline assembly should have the following properties:
-    //     1. Calls the syscall class specified by class
-    //     2. Passes r0-r3 in the corresponding registers as inlateout
-    //        registers. Returns r0-r3 in order.
-    //     3. Does not mark any registers as clobbered.
-    //     4. Has all of the following options:
-    //            preserves_flags  (these system calls do not touch flags)
-    //            nostack          (these system calls do not touch the stack)
-    //     5. Does NOT have any of the following options:
-    //            pure      (these system calls have side effects)
-    //            nomem     (the compiler needs to write to globals before allow)
-    //            readonly  (rw allow can modify memory)
-    //            noreturn  (all these system calls are expected to return)
-    //
-    // Note that subscribe's application data argument can potentially contain a
-    // pointer, so r3 can contain a pointer (in addition to r1 and r2, which
-    // more obviously contain pointers for subscribe and memop).
-    //
-    // For subscribe(), the callback pointer should be either 0 (for the null
-    // callback) or an `unsafe extern fn(u32, u32, u32, usize)`.
-    /// `four_arg_syscall` should only be called by `libtock_platform`.
-    ///
+    /// `yield1` should only be called by `libtock_platform`.
     /// # Safety
-    /// `four_arg_syscall` must NOT be used to invoke yield. Otherwise, it has
-    /// the same safety invariants as the underlying system call, which varies
-    /// depending on the system call class.
-    unsafe fn four_arg_syscall(
-        r0: u32,
-        r1: u32,
-        r2: usize,
-        r3: usize,
-        class: u8,
-    ) -> (u32, usize, usize, usize);
+    /// yield1 may only be used for yield operations that do not return a value.
+    /// It is exactly as safe as the underlying system call.
+    unsafe fn yield1(_: [*mut (); 1]);
 
-    // zero_arg_memop is used to invoke memop operations that do not accept an
-    // argument register. Because there are no memop commands that set r2 or r3,
-    // this only needs to return r0 and r1.
+    // yield2 can only be used to call `yield-no-wait`. `yield-no-wait` does not
+    // return any values, so to simplify the assembly we omit return arguments.
+    //
+    // yield2 should:
+    //     1. Call syscall class 0
+    //     2. Pass in r0 and r1 as inlateout registers.
+    //     3. Mark all caller-saved registers as lateout clobbers.
+    //     4. NOT provide any of the following options:
+    //            pure             (yield has side effects)
+    //            nomem            (a callback can read + write globals)
+    //            readonly         (a callback can write globals)
+    //            preserves_flags  (a callback can change flags)
+    //            noreturn         (yield is expected to return)
+    //            nostack          (a callback needs the stack)
+    /// `yield2` should only be called by `libtock_platform`.
+    /// # Safety
+    /// yield2 may only be used for yield operations that do not return a value.
+    /// It has the same safety invariants as the underlying system call.
+    unsafe fn yield2(_: [*mut (); 2]);
+
+    // syscall1 is only used to invoke Memop operations. Because there are no
+    // Memop commands that set r2 or r3, raw_syscall1 only needs to return r0
+    // and r1.
     //
     // Memop commands may panic in the unit test environment, as not all memop
     // calls can be sensibly implemented in that environment.
     //
-    // zero_arg_memop's inline assembly should have the following properties:
-    //     1. Calls syscall class 5
-    //     2. Specifies r0 as an inlateout register, and r1 as a lateout
-    //        register.
-    //     3. Does not mark any registers as clobbered.
-    //     4. Has all of the following options:
+    // syscall1 should:
+    //     1. Call the syscall class specified by CLASS.
+    //     2. Pass r0 as an inlateout register.
+    //     3. Specify r1 as a lateout register and return its value.
+    //     4. Not mark any registers as clobbered.
+    //     5. Have all of the following options:
     //            preserves_flags
     //            nostack
     //            nomem            (it is okay for the compiler to cache globals
     //                              across memop calls)
-    //     5. Does NOT have any of the following options:
+    //     6. NOT have any of the following options:
     //            pure      (two invocations of the same memop can return
     //                       different values)
     //            readonly  (incompatible with nomem)
     //            noreturn
-    //
-    // Design note: like raw_yield, this is safe because memops that currently
-    // exist are safe. zero_arg_memop takes a ZeroArgMemop rather than a u32 so
-    // that if the kernel adds an unsafe memop -- or one that can clobber r2/r3
-    // --  this API doesn't become unsound.
-    /// `four_arg_syscall` should only be called by `libtock_platform`.
-    fn zero_arg_memop(r0_in: ZeroArgMemop) -> (u32, usize);
+    /// `syscall1` should only be called by `libtock_platform`.
+    /// # Safety
+    /// This directly makes a system call. It can only be used for core kernel
+    /// system calls that accept 1 argument and only overwrite r0 and r1 on
+    /// return. It is unsafe any time the underlying system call is unsafe.
+    unsafe fn syscall1<const CLASS: usize>(_: [*mut (); 1]) -> [*mut (); 2];
 
-    // one_arg_memop is used to invoke memop operations that take an argument.
-    // Because there are no memop operations that set r2 or r3, this only needs
-    // to return r0 and r1.
+    // syscall2 is used to invoke Exit as well as Memop operations that take an
+    // argument. Memop does not currently use more than 2 registers for its
+    // return value, and Exit does not return, so syscall2 only returns 2
+    // values.
     //
-    // one_arg_memop's inline assembly should:
-    //     1. Call syscall class 5
-    //     2. Specify r0 and r1 as inlateout registers, and return (r0, r1)
+    // syscall2 should:
+    //     1. Call the syscall class specified by CLASS.
+    //     2. Pass r0 and r1 as inlateout registers.
     //     3. Not mark any registers as clobbered.
     //     4. Have all of the following options:
     //            preserves_flags
     //            nostack
     //            nomem            (the compiler can cache globals across memop
     //                              calls)
-    //     5. Does NOT have any of the following options:
+    //     5. NOT have any of the following options:
     //            pure      Two invocations of sbrk can return different values
     //            readonly  Incompatible with nomem
     //            noreturn
+    /// `syscall2` should only be called by `libtock_platform`.
+    /// # Safety
+    /// `syscall2` directly makes a system call. It can only be used for core
+    /// kernel system calls that accept 2 arguments and only overwrite r0 and r1
+    /// on return. It is unsafe any time the underlying system call is unsafe.
+    unsafe fn syscall2<const CLASS: usize>(_: [*mut (); 2]) -> [*mut (); 2];
+
+    // syscall4 should:
+    //     1. Call the syscall class specified by CLASS.
+    //     2. Pass r0-r3 in the corresponding registers as inlateout registers.
+    //     3. Not mark any registers as clobbered.
+    //     4. Have all of the following options:
+    //            preserves_flags  (these system calls do not touch flags)
+    //            nostack          (these system calls do not touch the stack)
+    //     5. NOT have any of the following options:
+    //            pure      (these system calls have side effects)
+    //            nomem     (the compiler needs to write to globals before allow)
+    //            readonly  (rw allow can modify memory)
+    //            noreturn  (all these system calls are expected to return)
     //
-    // Design note: like raw_yield, this is safe because memops that currently
-    // exist are safe. zero_arg_memop takes a ZeroArgMemop rather than a u32 so
-    // that if the kernel adds an unsafe memop -- or one that can clobber r2/r3
-    // -- this API doesn't become unsound.
-    /// `four_arg_syscall` should only be called by `libtock_platform`.
-    fn one_arg_memop(r0_in: OneArgMemop, r1: usize) -> (u32, usize);
-}
-
-#[non_exhaustive]
-#[repr(u32)]
-pub enum OneArgMemop {
-    Brk = 0,
-    Sbrk = 1,
-    FlashRegionStart = 8,
-    FlashRegionEnd = 9,
-    SpecifyStackTop = 10,
-    SpecifyHeapStart = 11,
-    // Note: before adding new memop operations, make sure the assumptions in
-    // the design notes on `one_arg_memop` are valid for the new operation type.
-}
-
-// TODO: When the numeric values (0 and 1) are assigned to the yield types,
-// specify those values here.
-#[non_exhaustive]
-#[repr(u32)]
-pub enum YieldType {
-    Wait,
-    NoWait,
-}
-
-#[non_exhaustive]
-#[repr(u32)]
-pub enum ZeroArgMemop {
-    MemoryStart = 2,
-    MemoryEnd = 3,
-    FlashStart = 4,
-    FlashEnd = 5,
-    GrantStart = 6,
-    FlashRegions = 7,
-    // Note: before adding new memop operations, make sure the assumptions in
-    // the design notes on `zero_arg_memop` are valid for the new operation
-    // type.
+    // For subscribe(), the callback pointer should be either 0 (for the null
+    // callback) or an `unsafe extern fn(u32, u32, u32, Userdata)`.
+    /// `syscall4` should only be called by `libtock_platform`.
+    ///
+    /// # Safety
+    /// `syscall4` must NOT be used to invoke yield. Otherwise, it has the same
+    /// safety invariants as the underlying system call, which varies depending
+    /// on the system call class.
+    unsafe fn syscall4<const CLASS: usize>(_: [*mut (); 4]) -> [*mut (); 4];
 }
diff --git a/core/platform/src/syscalls.rs b/core/platform/src/syscalls.rs
index 8d85380..d5ff0bc 100644
--- a/core/platform/src/syscalls.rs
+++ b/core/platform/src/syscalls.rs
@@ -5,15 +5,15 @@
 /// implemented for `libtock_runtime::TockSyscalls` and
 /// `libtock_unittest::FakeSyscalls` (by way of `RawSyscalls`).
 pub trait Syscalls {
+    /// Runs the next pending callback, if a callback is pending. Unlike
+    /// `yield_wait`, `yield_no_wait` returns immediately if no callback is
+    /// pending.
+    fn yield_no_wait() -> crate::YieldNoWaitReturn;
+
     /// Puts the process to sleep until a callback becomes pending, invokes the
     /// callback, then returns.
     fn yield_wait();
 
-    /// Runs the next pending callback, if a callback is pending. Unlike
-    /// `yield_wait`, `yield_no_wait` returns immediately if no callback is
-    /// pending. Returns true if a callback was executed, false otherwise.
-    fn yield_no_wait() -> bool;
-
     // TODO: Add a subscribe interface.
 
     // TODO: Add a command interface.
diff --git a/core/platform/src/syscalls_impl.rs b/core/platform/src/syscalls_impl.rs
index 506ad64..ec4ab9a 100644
--- a/core/platform/src/syscalls_impl.rs
+++ b/core/platform/src/syscalls_impl.rs
@@ -1,17 +1,38 @@
 //! Implements `Syscalls` for all types that implement `RawSyscalls`.
 
-use crate::{return_variant, RawSyscalls, Syscalls, YieldType};
+use crate::{RawSyscalls, Syscalls, YieldNoWaitReturn};
+
+mod yield_op {
+    pub const NO_WAIT: u32 = 0;
+    pub const WAIT: u32 = 1;
+}
 
 impl<S: RawSyscalls> Syscalls for S {
     // -------------------------------------------------------------------------
     // Yield
     // -------------------------------------------------------------------------
 
-    fn yield_wait() {
-        Self::raw_yield(YieldType::Wait);
+    fn yield_no_wait() -> YieldNoWaitReturn {
+        let mut flag = core::mem::MaybeUninit::<YieldNoWaitReturn>::uninit();
+
+        unsafe {
+            // Flag can be uninitialized here because the kernel promises to
+            // only write to it, not read from it. MaybeUninit guarantees that
+            // it is safe to write a YieldNoWaitReturn into it.
+            Self::yield2([yield_op::NO_WAIT as *mut (), flag.as_mut_ptr() as *mut ()]);
+
+            // yield-no-wait guarantees it sets (initializes) flag before
+            // returning.
+            flag.assume_init()
+        }
     }
 
-    fn yield_no_wait() -> bool {
-        Self::raw_yield(YieldType::NoWait) != return_variant::FAILURE.into()
+    fn yield_wait() {
+        // Safety: yield-wait does not return a value, which satisfies yield1's
+        // requirement. The yield-wait system call cannot trigger undefined
+        // behavior on its own in any other way.
+        unsafe {
+            Self::yield1([yield_op::WAIT as *mut ()]);
+        }
     }
 }
diff --git a/core/platform/src/yield_types.rs b/core/platform/src/yield_types.rs
new file mode 100644
index 0000000..12dd961
--- /dev/null
+++ b/core/platform/src/yield_types.rs
@@ -0,0 +1,15 @@
+/// The return value from a yield_no_wait call.
+// Calling yield-no-wait passes a *mut YieldNoWaitReturn to the kernel, which
+// the kernel writes to. We cannot safely pass a `*mut bool` to the kernel,
+// because the representation of `bool` in Rust is undefined (although it is
+// likely false == 0, true == 1, based on `bool`'s conversions). Using *mut
+// YieldNoWaitReturn rather than a *mut u8 allows the compiler to assume the
+// kernel will never write a value other than 0 or 1 into the pointee. Assuming
+// the likely representation of `bool`, this makes the conversion into `bool`
+// free.
+#[derive(Clone, Copy, Debug, Eq, PartialEq)]
+#[repr(u8)]
+pub enum YieldNoWaitReturn {
+    NoCallback = 0,
+    Callback = 1,
+}
diff --git a/core/runtime/src/syscalls_impl_riscv.rs b/core/runtime/src/syscalls_impl_riscv.rs
index 0e5f58a..7b6427c 100644
--- a/core/runtime/src/syscalls_impl_riscv.rs
+++ b/core/runtime/src/syscalls_impl_riscv.rs
@@ -1,11 +1,12 @@
-use libtock_platform::{OneArgMemop, RawSyscalls, YieldType, ZeroArgMemop};
+use libtock_platform::RawSyscalls;
 
-impl RawSyscalls for crate::TockSyscalls {
-    // This yield implementation is currently limited RISC-V versions without
+unsafe impl RawSyscalls for crate::TockSyscalls {
+    // This yield implementation is currently limited to RISC-V versions without
     // floating-point registers, as it does not mark them clobbered.
     #[cfg(not(any(target_feature = "d", target_feature = "f")))]
-    fn raw_yield(r0_in: YieldType) -> u32 {
-        let mut r0 = r0_in as u32;
+    unsafe fn yield1([r0]: [*mut (); 1]) {
+        // Safety: This matches the invariants required by the documentation on
+        // RawSyscalls::yield1
         unsafe {
             asm!("ecall",
                  // x0 is the zero register.
@@ -16,14 +17,14 @@
                  lateout("x6") _, // t1
                  lateout("x7") _, // t2
                  // x8 and x9 are s0 and s1 and are callee-saved.
-                 inlateout("x10") r0,     // a0
-                 lateout("x11") _,        // a1
-                 lateout("x12") _,        // a2
-                 lateout("x13") _,        // a3
-                 inlateout("x14") 0 => _, // a4
-                 lateout("x15") _,        // a5
-                 lateout("x16") _,        // a6
-                 lateout("x17") _,        // a7
+                 inlateout("x10") r0 => _, // a0
+                 lateout("x11") _,         // a1
+                 lateout("x12") _,         // a2
+                 lateout("x13") _,         // a3
+                 inlateout("x14") 0 => _,  // a4
+                 lateout("x15") _,         // a5
+                 lateout("x16") _,         // a6
+                 lateout("x17") _,         // a7
                  // x18-27 are s2-s11 and are callee-saved
                  lateout("x28") _, // t3
                  lateout("x29") _, // t4
@@ -31,53 +32,85 @@
                  lateout("x31") _, // t6
             );
         }
-        r0
     }
 
-    unsafe fn four_arg_syscall(
-        mut r0: u32,
-        mut r1: u32,
-        mut r2: usize,
-        mut r3: usize,
-        class: u8,
-    ) -> (u32, usize, usize, usize) {
+    // This yield implementation is currently limited to RISC-V versions without
+    // floating-point registers, as it does not mark them clobbered.
+    #[cfg(not(any(target_feature = "d", target_feature = "f")))]
+    unsafe fn yield2([r0, r1]: [*mut (); 2]) {
+        // Safety: This matches the invariants required by the documentation on
+        // RawSyscalls::yield2
+        unsafe {
+            asm!("ecall",
+                 // x0 is the zero register.
+                 lateout("x1") _, // Return address
+                 // x2-x4 are stack, global, and thread pointers. sp is
+                 // callee-saved.
+                 lateout("x5") _, // t0
+                 lateout("x6") _, // t1
+                 lateout("x7") _, // t2
+                 // x8 and x9 are s0 and s1 and are callee-saved.
+                 inlateout("x10") r0 => _, // a0
+                 inlateout("x11") r1 => _, // a1
+                 lateout("x12") _,         // a2
+                 lateout("x13") _,         // a3
+                 inlateout("x14") 0 => _,  // a4
+                 lateout("x15") _,         // a5
+                 lateout("x16") _,         // a6
+                 lateout("x17") _,         // a7
+                 // x18-27 are s2-s11 and are callee-saved
+                 lateout("x28") _, // t3
+                 lateout("x29") _, // t4
+                 lateout("x30") _, // t5
+                 lateout("x31") _, // t6
+            );
+        }
+    }
+
+    unsafe fn syscall1<const CLASS: usize>([mut r0]: [*mut (); 1]) -> [*mut (); 2] {
+        let r1;
+        // Safety: This matches the invariants required by the documentation on
+        // RawSyscalls::syscall1
+        unsafe {
+            asm!("ecall",
+                 inlateout("a0") r0,
+                 lateout("a1") r1,
+                 in("a4") CLASS,
+                 options(preserves_flags, nostack, nomem),
+            );
+        }
+        [r0, r1]
+    }
+
+    unsafe fn syscall2<const CLASS: usize>([mut r0, mut r1]: [*mut (); 2]) -> [*mut (); 2] {
+        // Safety: This matches the invariants required by the documentation on
+        // RawSyscalls::syscall2
+        unsafe {
+            asm!("ecall",
+                 inlateout("a0") r0,
+                 inlateout("a1") r1,
+                 in("a4") CLASS,
+                 options(preserves_flags, nostack, nomem)
+            );
+        }
+        [r0, r1]
+    }
+
+    unsafe fn syscall4<const CLASS: usize>(
+        [mut r0, mut r1, mut r2, mut r3]: [*mut (); 4],
+    ) -> [*mut (); 4] {
+        // Safety: This matches the invariants required by the documentation on
+        // RawSyscalls::syscall4
         unsafe {
             asm!("ecall",
                  inlateout("a0") r0,
                  inlateout("a1") r1,
                  inlateout("a2") r2,
                  inlateout("a3") r3,
-                 in("a4") class,
+                 in("a4") CLASS,
                  options(preserves_flags, nostack),
             );
         }
-        (r0, r1 as usize, r2, r3)
-    }
-
-    fn zero_arg_memop(r0_in: ZeroArgMemop) -> (u32, usize) {
-        let mut r0 = r0_in as u32;
-        let r1;
-        unsafe {
-            asm!("ecall",
-                 inlateout("a0") r0,
-                 lateout("a1") r1,
-                 in("a4") 5,
-                 options(preserves_flags, nostack, nomem),
-            );
-        }
-        (r0, r1)
-    }
-
-    fn one_arg_memop(r0_in: OneArgMemop, mut r1: usize) -> (u32, usize) {
-        let mut r0 = r0_in as u32;
-        unsafe {
-            asm!("ecall",
-                 inlateout("a0") r0,
-                 inlateout("a1") r1,
-                 in("a4") 5,
-                 options(preserves_flags, nostack, nomem)
-            );
-        }
-        (r0, r1)
+        [r0, r1, r2, r3]
     }
 }