Files
wasmtime/tests/all/memory.rs
Alex Crichton 3f3afb455e Remove support for userfaultfd (#4040)
This commit removes support for the `userfaultfd` or "uffd" syscall on
Linux. This support was originally added for users migrating from Lucet
to Wasmtime, but the recent developments of kernel-supported
copy-on-write support for memory initialization wound up being more
appropriate for these use cases than usefaultfd. The main reason for
moving to copy-on-write initialization are:

* The `userfaultfd` feature was never necessarily intended for this
  style of use case with wasm and was susceptible to subtle and rare
  bugs that were extremely difficult to track down. We were never 100%
  certain that there were kernel bugs related to userfaultfd but the
  suspicion never went away.

* Handling faults with userfaultfd was always slow and single-threaded.
  Only one thread could handle faults and traveling to user-space to
  handle faults is inherently slower than handling them all in the
  kernel. The single-threaded aspect in particular presented a
  significant scaling bottleneck for embeddings that want to run many
  wasm instances in parallel.

* One of the major benefits of userfaultfd was lazy initialization of
  wasm linear memory which is also achieved with the copy-on-write
  initialization support we have right now.

* One of the suspected benefits of userfaultfd was less frobbing of the
  kernel vma structures when wasm modules are instantiated. Currently
  the copy-on-write support has a mitigation where we attempt to reuse
  the memory images where possible to avoid changing vma structures.
  When comparing this to userfaultfd's performance it was found that
  kernel modifications of vmas aren't a worrisome bottleneck so
  copy-on-write is suitable for this as well.

Overall there are no remaining benefits that userfaultfd gives that
copy-on-write doesn't, and copy-on-write solves a major downsides of
userfaultfd, the scaling issue with a single faulting thread.
Additionally copy-on-write support seems much more robust in terms of
kernel implementation since it's only using standard memory-management
syscalls which are heavily exercised. Finally copy-on-write support
provides a new bonus where read-only memory in WebAssembly can be mapped
directly to the same kernel cache page, even amongst many wasm instances
of the same module, which was never possible with userfaultfd.

In light of all this it's expected that all users of userfaultfd should
migrate to the copy-on-write initialization of Wasmtime (which is
enabled by default).
2022-04-18 12:42:26 -05:00

471 lines
14 KiB
Rust

use anyhow::Result;
use rayon::prelude::*;
use wasmtime::*;
fn module(engine: &Engine) -> Result<Module> {
let mut wat = format!("(module\n");
wat.push_str("(import \"\" \"\" (memory 0))\n");
for i in 0..=33 {
let offset = if i == 0 {
0
} else if i == 33 {
!0
} else {
1u32 << (i - 1)
};
for (width, instr) in [
(1, &["i32.load8_s"][..]),
(2, &["i32.load16_s"]),
(4, &["i32.load" /*, "f32.load"*/]),
(8, &["i64.load" /*, "f64.load"*/]),
#[cfg(not(target_arch = "s390x"))]
(16, &["v128.load"]),
]
.iter()
{
for (j, instr) in instr.iter().enumerate() {
wat.push_str(&format!(
"(func (export \"{} {} v{}\") (param i32)\n",
width, offset, j
));
wat.push_str("local.get 0\n");
wat.push_str(instr);
wat.push_str(&format!(" offset={}\n", offset));
wat.push_str("drop\n)");
}
}
}
wat.push_str(")");
Module::new(engine, &wat)
}
struct TestFunc {
width: u32,
offset: u32,
func: TypedFunc<u32, ()>,
}
fn find_funcs(store: &mut Store<()>, instance: &Instance) -> Vec<TestFunc> {
let list = instance
.exports(&mut *store)
.map(|export| {
let name = export.name();
let mut parts = name.split_whitespace();
(
parts.next().unwrap().parse().unwrap(),
parts.next().unwrap().parse().unwrap(),
export.into_func().unwrap(),
)
})
.collect::<Vec<_>>();
list.into_iter()
.map(|(width, offset, func)| TestFunc {
width,
offset,
func: func.typed(&store).unwrap(),
})
.collect()
}
fn test_traps(store: &mut Store<()>, funcs: &[TestFunc], addr: u32, mem: &Memory) {
let mem_size = mem.data_size(&store) as u64;
for func in funcs {
let result = func.func.call(&mut *store, addr);
let base = u64::from(func.offset) + u64::from(addr);
let range = base..base + u64::from(func.width);
if range.start >= mem_size || range.end >= mem_size {
assert!(
result.is_err(),
"access at {}+{}+{} succeeded but should have failed when memory has {} bytes",
addr,
func.offset,
func.width,
mem_size
);
} else {
assert!(result.is_ok());
}
}
}
#[test]
fn offsets_static_dynamic_oh_my() -> Result<()> {
const GB: u64 = 1 << 30;
let mut engines = Vec::new();
let sizes = [0, 1 * GB, 4 * GB];
for &static_memory_maximum_size in sizes.iter() {
for &guard_size in sizes.iter() {
for &guard_before_linear_memory in [true, false].iter() {
let mut config = Config::new();
config.wasm_simd(true);
config.static_memory_maximum_size(static_memory_maximum_size);
config.dynamic_memory_guard_size(guard_size);
config.static_memory_guard_size(guard_size);
config.guard_before_linear_memory(guard_before_linear_memory);
config.cranelift_debug_verifier(true);
engines.push(Engine::new(&config)?);
}
}
}
engines.par_iter().for_each(|engine| {
let module = module(&engine).unwrap();
for (min, max) in [(1, Some(2)), (1, None)].iter() {
let mut store = Store::new(&engine, ());
let mem = Memory::new(&mut store, MemoryType::new(*min, *max)).unwrap();
let instance = Instance::new(&mut store, &module, &[mem.into()]).unwrap();
let funcs = find_funcs(&mut store, &instance);
test_traps(&mut store, &funcs, 0, &mem);
test_traps(&mut store, &funcs, 65536, &mem);
test_traps(&mut store, &funcs, u32::MAX, &mem);
mem.grow(&mut store, 1).unwrap();
test_traps(&mut store, &funcs, 0, &mem);
test_traps(&mut store, &funcs, 65536, &mem);
test_traps(&mut store, &funcs, u32::MAX, &mem);
}
});
Ok(())
}
#[test]
fn guards_present() -> Result<()> {
const GUARD_SIZE: u64 = 65536;
let mut config = Config::new();
config.static_memory_maximum_size(1 << 20);
config.dynamic_memory_guard_size(GUARD_SIZE);
config.static_memory_guard_size(GUARD_SIZE);
config.guard_before_linear_memory(true);
let engine = Engine::new(&config)?;
let mut store = Store::new(&engine, ());
let static_mem = Memory::new(&mut store, MemoryType::new(1, Some(2)))?;
let dynamic_mem = Memory::new(&mut store, MemoryType::new(1, None))?;
let assert_guards = |store: &Store<()>| unsafe {
// guards before
println!("check pre-static-mem");
assert_faults(static_mem.data_ptr(&store).offset(-(GUARD_SIZE as isize)));
println!("check pre-dynamic-mem");
assert_faults(dynamic_mem.data_ptr(&store).offset(-(GUARD_SIZE as isize)));
// guards after
println!("check post-static-mem");
assert_faults(
static_mem
.data_ptr(&store)
.add(static_mem.data_size(&store)),
);
println!("check post-dynamic-mem");
assert_faults(
dynamic_mem
.data_ptr(&store)
.add(dynamic_mem.data_size(&store)),
);
};
assert_guards(&store);
// static memory should start with the second page unmapped
unsafe {
assert_faults(static_mem.data_ptr(&store).add(65536));
}
println!("growing");
static_mem.grow(&mut store, 1).unwrap();
dynamic_mem.grow(&mut store, 1).unwrap();
assert_guards(&store);
Ok(())
}
#[test]
fn guards_present_pooling() -> Result<()> {
const GUARD_SIZE: u64 = 65536;
let mut config = Config::new();
config.static_memory_maximum_size(1 << 20);
config.dynamic_memory_guard_size(GUARD_SIZE);
config.static_memory_guard_size(GUARD_SIZE);
config.guard_before_linear_memory(true);
config.allocation_strategy(InstanceAllocationStrategy::Pooling {
strategy: PoolingAllocationStrategy::default(),
instance_limits: InstanceLimits {
count: 2,
memory_pages: 10,
..Default::default()
},
});
let engine = Engine::new(&config)?;
let mut store = Store::new(&engine, ());
let mem1 = {
let m = Module::new(&engine, "(module (memory (export \"\") 1 2))")?;
Instance::new(&mut store, &m, &[])?
.get_memory(&mut store, "")
.unwrap()
};
let mem2 = {
let m = Module::new(&engine, "(module (memory (export \"\") 1))")?;
Instance::new(&mut store, &m, &[])?
.get_memory(&mut store, "")
.unwrap()
};
unsafe fn assert_guards(store: &Store<()>, mem: &Memory) {
// guards before
println!("check pre-mem");
assert_faults(mem.data_ptr(&store).offset(-(GUARD_SIZE as isize)));
// unmapped just after memory
println!("check mem");
assert_faults(mem.data_ptr(&store).add(mem.data_size(&store)));
// guards after memory
println!("check post-mem");
assert_faults(mem.data_ptr(&store).add(1 << 20));
}
unsafe {
assert_guards(&store, &mem1);
assert_guards(&store, &mem2);
println!("growing");
mem1.grow(&mut store, 1).unwrap();
mem2.grow(&mut store, 1).unwrap();
assert_guards(&store, &mem1);
assert_guards(&store, &mem2);
}
Ok(())
}
unsafe fn assert_faults(ptr: *mut u8) {
use std::io::Error;
#[cfg(unix)]
{
// There's probably a faster way to do this here, but, uh, when in rome?
match libc::fork() {
0 => {
*ptr = 4;
std::process::exit(0);
}
-1 => panic!("failed to fork: {}", Error::last_os_error()),
n => {
let mut status = 0;
assert!(
libc::waitpid(n, &mut status, 0) == n,
"failed to wait: {}",
Error::last_os_error()
);
assert!(libc::WIFSIGNALED(status));
}
}
}
#[cfg(windows)]
{
use winapi::um::memoryapi::*;
use winapi::um::winnt::*;
let mut info = std::mem::MaybeUninit::uninit();
let r = VirtualQuery(
ptr as *const _,
info.as_mut_ptr(),
std::mem::size_of_val(&info),
);
if r == 0 {
panic!("failed to VirtualAlloc: {}", Error::last_os_error());
}
let info = info.assume_init();
assert_eq!(info.AllocationProtect, PAGE_NOACCESS);
}
}
#[test]
fn massive_64_bit_still_limited() -> Result<()> {
// Creating a 64-bit memory which exceeds the limits of the address space
// should still send a request to the `ResourceLimiter` to ensure that it
// gets at least some chance to see that oom was requested.
let mut config = Config::new();
config.wasm_memory64(true);
let engine = Engine::new(&config)?;
let mut store = Store::new(&engine, MyLimiter { hit: false });
store.limiter(|x| x);
let ty = MemoryType::new64(1 << 48, None);
assert!(Memory::new(&mut store, ty).is_err());
assert!(store.data().hit);
return Ok(());
struct MyLimiter {
hit: bool,
}
impl ResourceLimiter for MyLimiter {
fn memory_growing(
&mut self,
_current: usize,
_request: usize,
_max: Option<usize>,
) -> bool {
self.hit = true;
true
}
fn table_growing(&mut self, _current: u32, _request: u32, _max: Option<u32>) -> bool {
unreachable!()
}
}
}
#[test]
fn tiny_static_heap() -> Result<()> {
// The size of the memory in the module below is the exact same size as
// the static memory size limit in the configuration. This is intended to
// specifically test that a load of all the valid addresses of the memory
// all pass bounds-checks in cranelift to help weed out any off-by-one bugs.
let mut config = Config::new();
config.static_memory_maximum_size(65536);
let engine = Engine::new(&config)?;
let mut store = Store::new(&engine, ());
let module = Module::new(
&engine,
r#"
(module
(memory 1 1)
(func (export "run")
(local $i i32)
(loop
(if (i32.eq (local.get $i) (i32.const 65536))
(return))
(drop (i32.load8_u (local.get $i)))
(local.set $i (i32.add (local.get $i) (i32.const 1)))
br 0
)
)
)
"#,
)?;
let i = Instance::new(&mut store, &module, &[])?;
let f = i.get_typed_func::<(), (), _>(&mut store, "run")?;
f.call(&mut store, ())?;
Ok(())
}
#[test]
fn static_forced_max() -> Result<()> {
let mut config = Config::new();
config.static_memory_maximum_size(5 * 65536);
config.static_memory_forced(true);
let engine = Engine::new(&config)?;
let mut store = Store::new(&engine, ());
let mem = Memory::new(&mut store, MemoryType::new(0, None))?;
mem.grow(&mut store, 5).unwrap();
assert!(mem.grow(&mut store, 1).is_err());
Ok(())
}
#[test]
fn dynamic_extra_growth_unchanged_pointer() -> Result<()> {
const EXTRA_PAGES: u64 = 5;
let mut config = Config::new();
config.static_memory_maximum_size(0);
// 5 wasm pages extra
config.dynamic_memory_reserved_for_growth(EXTRA_PAGES * (1 << 16));
let engine = Engine::new(&config)?;
let mut store = Store::new(&engine, ());
fn assert_behaves_well(store: &mut Store<()>, mem: &Memory) -> Result<()> {
let ptr = mem.data_ptr(&store);
// Each growth here should retain the same linear pointer in memory and the
// memory shouldn't get moved.
for _ in 0..EXTRA_PAGES {
mem.grow(&mut *store, 1)?;
assert_eq!(ptr, mem.data_ptr(&store));
}
// Growth afterwards though will be forced to move the pointer
mem.grow(&mut *store, 1)?;
let new_ptr = mem.data_ptr(&store);
assert_ne!(ptr, new_ptr);
for _ in 0..EXTRA_PAGES - 1 {
mem.grow(&mut *store, 1)?;
assert_eq!(new_ptr, mem.data_ptr(&store));
}
Ok(())
}
let mem = Memory::new(&mut store, MemoryType::new(10, None))?;
assert_behaves_well(&mut store, &mem)?;
let module = Module::new(&engine, r#"(module (memory (export "mem") 10))"#)?;
let instance = Instance::new(&mut store, &module, &[])?;
let mem = instance.get_memory(&mut store, "mem").unwrap();
assert_behaves_well(&mut store, &mem)?;
let module = Module::new(
&engine,
r#"
(module
(memory (export "mem") 10)
(data (i32.const 0) ""))
"#,
)?;
let instance = Instance::new(&mut store, &module, &[])?;
let mem = instance.get_memory(&mut store, "mem").unwrap();
assert_behaves_well(&mut store, &mem)?;
Ok(())
}
// This test exercises trying to create memories of the maximum 64-bit memory
// size of `1 << 48` pages. This should always fail but in the process of
// determining this failure we shouldn't hit any overflows or anything like that
// (checked via debug-mode tests).
#[test]
fn memory64_maximum_minimum() -> Result<()> {
let mut config = Config::new();
config.wasm_memory64(true);
let engine = Engine::new(&config)?;
let mut store = Store::new(&engine, ());
assert!(Memory::new(&mut store, MemoryType::new64(1 << 48, None)).is_err());
let module = Module::new(
&engine,
&format!(
r#"
(module
(memory i64 {})
)
"#,
1u64 << 48,
),
)?;
assert!(Instance::new(&mut store, &module, &[]).is_err());
let module = Module::new(
&engine,
&format!(
r#"
(module
(memory i64 {})
(data (i64.const 0) "")
)
"#,
1u64 << 48,
),
)?;
assert!(Instance::new(&mut store, &module, &[]).is_err());
Ok(())
}