* cranelift: Use JIT in runtests
Using `cranelift-jit` in run tests allows us to preform relocations and
libcalls. This is important since some instruction lowerings fallback
to libcall's when an extension is missing, or when it's too complicated
to implement manually.
This is also a first step to being able to test `call`'s between functions
in the runtest suite. It should also make it easier to eventually test
TLS relocations, symbol resolution and ABI's.
Another benefit of this is that we also get to test the JIT more, since
it now runs the runtests, and gets some fuzzing via `fuzzgen` (which
uses the `SingleFunctionCompiler`).
This change causes regressions in terms of runtime for the filetests.
I haven't done any serious benchmarking but what I've been seeing is
that it now takes about ~3 seconds to run the testsuite while it
previously took around 2 seconds.
* Add FMA tests for X86
* Improve the `component_api` fuzzer on a few dimensions
* Update the generated component to use an adapter module. This involves
two core wasm instances communicating with each other to test that
data flows through everything correctly. The intention here is to fuzz
the fused adapter compiler. String encoding options have been plumbed
here to exercise differences in string encodings.
* Use `Cow<'static, ...>` and `static` declarations for each static test
case to try to cut down on rustc codegen time.
* Add `Copy` to derivation of fuzzed enums to make `derive(Clone)`
smaller.
* Use `Store<Box<dyn Any>>` to try to cut down on codegen by
monomorphizing fewer `Store<T>` implementation.
* Add debug logging to print out what's flowing in and what's flowing
out for debugging failures.
* Improve `Debug` representation of dynamic value types to more closely
match their Rust counterparts.
* Fix a variant issue with adapter trampolines
Previously the offset of the payload was calculated as the discriminant
aligned up to the alignment of a singular case, but instead this needs
to be aligned up to the alignment of all cases to ensure all cases start
at the same location.
* Fix a copy/paste error when copying masked integers
A 32-bit load was actually doing a 16-bit load by accident since it was
copied from the 16-bit load-and-mask case.
* Fix f32/i64 conversions in adapter modules
The adapter previously erroneously converted the f32 to f64 and then to
i64, where instead it should go from f32 to i32 to i64.
* Fix zero-sized flags in adapter modules
This commit corrects the size calculation for zero-sized flags in
adapter modules.
cc #4592
* Fix a variant size calculation bug in adapters
This fixes the same issue found with variants during normal host-side
fuzzing earlier where the size of a variant needs to align up the
summation of the discriminant and the maximum case size.
* Implement memory growth in libc bump realloc
Some fuzz-generated test cases are copying lists large enough to exceed
one page of memory so bake in a `memory.grow` to the bump allocator as
well.
* Avoid adapters of exponential size
This commit is an attempt to avoid adapters being exponentially sized
with respect to the type hierarchy of the input. Previously all
adaptation was done inline within each adapter which meant that if
something was structured as `tuple<T, T, T, T, ...>` the translation of
`T` would be inlined N times. For very deeply nested types this can
quickly create an exponentially sized adapter with types of the form:
(type $t0 (list u8))
(type $t1 (tuple $t0 $t0))
(type $t2 (tuple $t1 $t1))
(type $t3 (tuple $t2 $t2))
;; ...
where the translation of `t4` has 8 different copies of translating
`t0`.
This commit changes the translation of types through memory to almost
always go through a helper function. The hope here is that it doesn't
lose too much performance because types already reside in memory.
This can still lead to exponentially sized adapter modules to a lesser
degree where if the translation all happens on the "stack", e.g. via
`variant`s and their flat representation then many copies of one
translation could still be made. For now this commit at least gets the
problem under control for fuzzing where fuzzing doesn't trivially find
type hierarchies that take over a minute to codegen the adapter module.
One of the main tricky parts of this implementation is that when a
function is generated the index that it will be placed at in the final
module is not known at that time. To solve this the encoded form of the
`Call` instruction is saved in a relocation-style format where the
`Call` isn't encoded but instead saved into a different area for
encoding later. When the entire adapter module is encoded to wasm these
pseudo-`Call` instructions are encoded as real instructions at that
time.
* Fix some memory64 issues with string encodings
Introduced just before #4623 I had a few mistakes related to 64-bit
memories and mixing 32/64-bit memories.
* Actually insert into the `translate_mem_funcs` map
This... was the whole point of having the map!
* Assert memory growth succeeds in bump allocator
This addresses #4307.
For the static API we generate 100 arbitrary test cases at build time, each of
which includes 0-5 parameter types, a result type, and a WAT fragment containing
an imported function and an exported function. The exported function calls the
imported function, which is implemented by the host. At runtime, the fuzz test
selects a test case at random and feeds it zero or more sets of arbitrary
parameters and results, checking that values which flow host-to-guest and
guest-to-host make the transition unchanged.
The fuzz test for the dynamic API follows a similar pattern, the only difference
being that test cases are generated at runtime.
Signed-off-by: Joel Dice <joel.dice@fermyon.com>
* Always preserve frame pointers in Wasmtime
This allows us to efficiently and simply capture Wasm stacks without maintaining
and synchronizing any safety-critical side tables between the compiler and the
runtime.
* wasmtime: Implement fast Wasm stack walking
Why do we want Wasm stack walking to be fast? Because we capture stacks whenever
there is a trap and traps actually happen fairly frequently with short-lived
programs and WASI's `exit`.
Previously, we would rely on generating the system unwind info (e.g.
`.eh_frame`) and using the system unwinder (via the `backtrace`crate) to walk
the full stack and filter out any non-Wasm stack frames. This can,
unfortunately, be slow for two primary reasons:
1. The system unwinder is doing `O(all-kinds-of-frames)` work rather than
`O(wasm-frames)` work.
2. System unwind info and the system unwinder need to be much more general than
a purpose-built stack walker for Wasm needs to be. It has to handle any kind of
stack frame that any compiler might emit where as our Wasm frames are emitted by
Cranelift and always have frame pointers. This translates into implementation
complexity and general overhead. There can also be unnecessary-for-our-use-cases
global synchronization and locks involved, further slowing down stack walking in
the presence of multiple threads trying to capture stacks in parallel.
This commit introduces a purpose-built stack walker for traversing just our Wasm
frames. To find all the sequences of Wasm-to-Wasm stack frames, and ignore
non-Wasm stack frames, we keep a linked list of `(entry stack pointer, exit
frame pointer)` pairs. This linked list is maintained via Wasm-to-host and
host-to-Wasm trampolines. Within a sequence of Wasm-to-Wasm calls, we can use
frame pointers (which Cranelift preserves) to find the next older Wasm frame on
the stack, and we keep doing this until we reach the entry stack pointer,
meaning that the next older frame will be a host frame.
The trampolines need to avoid a couple stumbling blocks. First, they need to be
compiled ahead of time, since we may not have access to a compiler at
runtime (e.g. if the `cranelift` feature is disabled) but still want to be able
to call functions that have already been compiled and get stack traces for those
functions. Usually this means we would compile the appropriate trampolines
inside `Module::new` and the compiled module object would hold the
trampolines. However, we *also* need to support calling host functions that are
wrapped into `wasmtime::Func`s and there doesn't exist *any* ahead-of-time
compiled module object to hold the appropriate trampolines:
```rust
// Define a host function.
let func_type = wasmtime::FuncType::new(
vec![wasmtime::ValType::I32],
vec![wasmtime::ValType::I32],
);
let func = Func::new(&mut store, func_type, |_, params, results| {
// ...
Ok(())
});
// Call that host function.
let mut results = vec![wasmtime::Val::I32(0)];
func.call(&[wasmtime::Val::I32(0)], &mut results)?;
```
Therefore, we define one host-to-Wasm trampoline and one Wasm-to-host trampoline
in assembly that work for all Wasm and host function signatures. These
trampolines are careful to only use volatile registers, avoid touching any
register that is an argument in the calling convention ABI, and tail call to the
target callee function. This allows forwarding any set of arguments and any
returns to and from the callee, while also allowing us to maintain our linked
list of Wasm stack and frame pointers before transferring control to the
callee. These trampolines are not used in Wasm-to-Wasm calls, only when crossing
the host-Wasm boundary, so they do not impose overhead on regular calls. (And if
using one trampoline for all host-Wasm boundary crossing ever breaks branch
prediction enough in the CPU to become any kind of bottleneck, we can do fun
things like have multiple copies of the same trampoline and choose a random copy
for each function, sharding the functions across branch predictor entries.)
Finally, this commit also ends the use of a synthetic `Module` and allocating a
stubbed out `VMContext` for host functions. Instead, we define a
`VMHostFuncContext` with its own magic value, similar to `VMComponentContext`,
specifically for host functions.
<h2>Benchmarks</h2>
<h3>Traps and Stack Traces</h3>
Large improvements to taking stack traces on traps, ranging from shaving off 64%
to 99.95% of the time it used to take.
<details>
```
multi-threaded-traps/0 time: [2.5686 us 2.5808 us 2.5934 us]
thrpt: [0.0000 elem/s 0.0000 elem/s 0.0000 elem/s]
change:
time: [-85.419% -85.153% -84.869%] (p = 0.00 < 0.05)
thrpt: [+560.90% +573.56% +585.84%]
Performance has improved.
Found 8 outliers among 100 measurements (8.00%)
4 (4.00%) high mild
4 (4.00%) high severe
multi-threaded-traps/1 time: [2.9021 us 2.9167 us 2.9322 us]
thrpt: [341.04 Kelem/s 342.86 Kelem/s 344.58 Kelem/s]
change:
time: [-91.455% -91.294% -91.096%] (p = 0.00 < 0.05)
thrpt: [+1023.1% +1048.6% +1070.3%]
Performance has improved.
Found 6 outliers among 100 measurements (6.00%)
1 (1.00%) high mild
5 (5.00%) high severe
multi-threaded-traps/2 time: [2.9996 us 3.0145 us 3.0295 us]
thrpt: [660.18 Kelem/s 663.47 Kelem/s 666.76 Kelem/s]
change:
time: [-94.040% -93.910% -93.762%] (p = 0.00 < 0.05)
thrpt: [+1503.1% +1542.0% +1578.0%]
Performance has improved.
Found 5 outliers among 100 measurements (5.00%)
5 (5.00%) high severe
multi-threaded-traps/4 time: [5.5768 us 5.6052 us 5.6364 us]
thrpt: [709.68 Kelem/s 713.63 Kelem/s 717.25 Kelem/s]
change:
time: [-93.193% -93.121% -93.052%] (p = 0.00 < 0.05)
thrpt: [+1339.2% +1353.6% +1369.1%]
Performance has improved.
multi-threaded-traps/8 time: [8.6408 us 9.1212 us 9.5438 us]
thrpt: [838.24 Kelem/s 877.08 Kelem/s 925.84 Kelem/s]
change:
time: [-94.754% -94.473% -94.202%] (p = 0.00 < 0.05)
thrpt: [+1624.7% +1709.2% +1806.1%]
Performance has improved.
multi-threaded-traps/16 time: [10.152 us 10.840 us 11.545 us]
thrpt: [1.3858 Melem/s 1.4760 Melem/s 1.5761 Melem/s]
change:
time: [-97.042% -96.823% -96.577%] (p = 0.00 < 0.05)
thrpt: [+2821.5% +3048.1% +3281.1%]
Performance has improved.
Found 1 outliers among 100 measurements (1.00%)
1 (1.00%) high mild
many-modules-registered-traps/1
time: [2.6278 us 2.6361 us 2.6447 us]
thrpt: [378.11 Kelem/s 379.35 Kelem/s 380.55 Kelem/s]
change:
time: [-85.311% -85.108% -84.909%] (p = 0.00 < 0.05)
thrpt: [+562.65% +571.51% +580.76%]
Performance has improved.
Found 9 outliers among 100 measurements (9.00%)
3 (3.00%) high mild
6 (6.00%) high severe
many-modules-registered-traps/8
time: [2.6294 us 2.6460 us 2.6623 us]
thrpt: [3.0049 Melem/s 3.0235 Melem/s 3.0425 Melem/s]
change:
time: [-85.895% -85.485% -85.022%] (p = 0.00 < 0.05)
thrpt: [+567.63% +588.95% +608.95%]
Performance has improved.
Found 8 outliers among 100 measurements (8.00%)
3 (3.00%) high mild
5 (5.00%) high severe
many-modules-registered-traps/64
time: [2.6218 us 2.6329 us 2.6452 us]
thrpt: [24.195 Melem/s 24.308 Melem/s 24.411 Melem/s]
change:
time: [-93.629% -93.551% -93.470%] (p = 0.00 < 0.05)
thrpt: [+1431.4% +1450.6% +1469.5%]
Performance has improved.
Found 3 outliers among 100 measurements (3.00%)
3 (3.00%) high mild
many-modules-registered-traps/512
time: [2.6569 us 2.6737 us 2.6923 us]
thrpt: [190.17 Melem/s 191.50 Melem/s 192.71 Melem/s]
change:
time: [-99.277% -99.268% -99.260%] (p = 0.00 < 0.05)
thrpt: [+13417% +13566% +13731%]
Performance has improved.
Found 4 outliers among 100 measurements (4.00%)
4 (4.00%) high mild
many-modules-registered-traps/4096
time: [2.7258 us 2.7390 us 2.7535 us]
thrpt: [1.4876 Gelem/s 1.4955 Gelem/s 1.5027 Gelem/s]
change:
time: [-99.956% -99.955% -99.955%] (p = 0.00 < 0.05)
thrpt: [+221417% +223380% +224881%]
Performance has improved.
Found 2 outliers among 100 measurements (2.00%)
1 (1.00%) high mild
1 (1.00%) high severe
many-stack-frames-traps/1
time: [1.4658 us 1.4719 us 1.4784 us]
thrpt: [676.39 Kelem/s 679.38 Kelem/s 682.21 Kelem/s]
change:
time: [-90.368% -89.947% -89.586%] (p = 0.00 < 0.05)
thrpt: [+860.23% +894.72% +938.21%]
Performance has improved.
Found 8 outliers among 100 measurements (8.00%)
5 (5.00%) high mild
3 (3.00%) high severe
many-stack-frames-traps/8
time: [2.4772 us 2.4870 us 2.4973 us]
thrpt: [3.2034 Melem/s 3.2167 Melem/s 3.2294 Melem/s]
change:
time: [-85.550% -85.370% -85.199%] (p = 0.00 < 0.05)
thrpt: [+575.65% +583.51% +592.03%]
Performance has improved.
Found 8 outliers among 100 measurements (8.00%)
4 (4.00%) high mild
4 (4.00%) high severe
many-stack-frames-traps/64
time: [10.109 us 10.171 us 10.236 us]
thrpt: [6.2525 Melem/s 6.2925 Melem/s 6.3309 Melem/s]
change:
time: [-78.144% -77.797% -77.336%] (p = 0.00 < 0.05)
thrpt: [+341.22% +350.38% +357.55%]
Performance has improved.
Found 7 outliers among 100 measurements (7.00%)
5 (5.00%) high mild
2 (2.00%) high severe
many-stack-frames-traps/512
time: [126.16 us 126.54 us 126.96 us]
thrpt: [4.0329 Melem/s 4.0461 Melem/s 4.0583 Melem/s]
change:
time: [-65.364% -64.933% -64.453%] (p = 0.00 < 0.05)
thrpt: [+181.32% +185.17% +188.71%]
Performance has improved.
Found 4 outliers among 100 measurements (4.00%)
4 (4.00%) high severe
```
</details>
<h3>Calls</h3>
There is, however, a small regression in raw Wasm-to-host and host-to-Wasm call
performance due the new trampolines. It seems to be on the order of about 2-10
nanoseconds per call, depending on the benchmark.
I believe this regression is ultimately acceptable because
1. this overhead will be vastly dominated by whatever work a non-nop callee
actually does,
2. we will need these trampolines, or something like them, when implementing the
Wasm exceptions proposal to do things like translate Wasm's exceptions into
Rust's `Result`s,
3. and because the performance improvements to trapping and capturing stack
traces are of such a larger magnitude than this call regressions.
<details>
```
sync/no-hook/host-to-wasm - typed - nop
time: [28.683 ns 28.757 ns 28.844 ns]
change: [+16.472% +17.183% +17.904%] (p = 0.00 < 0.05)
Performance has regressed.
Found 10 outliers among 100 measurements (10.00%)
1 (1.00%) low mild
4 (4.00%) high mild
5 (5.00%) high severe
sync/no-hook/host-to-wasm - untyped - nop
time: [42.515 ns 42.652 ns 42.841 ns]
change: [+12.371% +14.614% +17.462%] (p = 0.00 < 0.05)
Performance has regressed.
Found 11 outliers among 100 measurements (11.00%)
1 (1.00%) high mild
10 (10.00%) high severe
sync/no-hook/host-to-wasm - unchecked - nop
time: [33.936 ns 34.052 ns 34.179 ns]
change: [+25.478% +26.938% +28.369%] (p = 0.00 < 0.05)
Performance has regressed.
Found 9 outliers among 100 measurements (9.00%)
7 (7.00%) high mild
2 (2.00%) high severe
sync/no-hook/host-to-wasm - typed - nop-params-and-results
time: [34.290 ns 34.388 ns 34.502 ns]
change: [+40.802% +42.706% +44.526%] (p = 0.00 < 0.05)
Performance has regressed.
Found 13 outliers among 100 measurements (13.00%)
5 (5.00%) high mild
8 (8.00%) high severe
sync/no-hook/host-to-wasm - untyped - nop-params-and-results
time: [62.546 ns 62.721 ns 62.919 ns]
change: [+2.5014% +3.6319% +4.8078%] (p = 0.00 < 0.05)
Performance has regressed.
Found 12 outliers among 100 measurements (12.00%)
2 (2.00%) high mild
10 (10.00%) high severe
sync/no-hook/host-to-wasm - unchecked - nop-params-and-results
time: [42.609 ns 42.710 ns 42.831 ns]
change: [+20.966% +22.282% +23.475%] (p = 0.00 < 0.05)
Performance has regressed.
Found 11 outliers among 100 measurements (11.00%)
4 (4.00%) high mild
7 (7.00%) high severe
sync/hook-sync/host-to-wasm - typed - nop
time: [29.546 ns 29.675 ns 29.818 ns]
change: [+20.693% +21.794% +22.836%] (p = 0.00 < 0.05)
Performance has regressed.
Found 5 outliers among 100 measurements (5.00%)
3 (3.00%) high mild
2 (2.00%) high severe
sync/hook-sync/host-to-wasm - untyped - nop
time: [45.448 ns 45.699 ns 45.961 ns]
change: [+17.204% +18.514% +19.590%] (p = 0.00 < 0.05)
Performance has regressed.
Found 14 outliers among 100 measurements (14.00%)
4 (4.00%) high mild
10 (10.00%) high severe
sync/hook-sync/host-to-wasm - unchecked - nop
time: [34.334 ns 34.437 ns 34.558 ns]
change: [+23.225% +24.477% +25.886%] (p = 0.00 < 0.05)
Performance has regressed.
Found 12 outliers among 100 measurements (12.00%)
5 (5.00%) high mild
7 (7.00%) high severe
sync/hook-sync/host-to-wasm - typed - nop-params-and-results
time: [36.594 ns 36.763 ns 36.974 ns]
change: [+41.967% +47.261% +52.086%] (p = 0.00 < 0.05)
Performance has regressed.
Found 12 outliers among 100 measurements (12.00%)
3 (3.00%) high mild
9 (9.00%) high severe
sync/hook-sync/host-to-wasm - untyped - nop-params-and-results
time: [63.541 ns 63.831 ns 64.194 ns]
change: [-4.4337% -0.6855% +2.7134%] (p = 0.73 > 0.05)
No change in performance detected.
Found 8 outliers among 100 measurements (8.00%)
6 (6.00%) high mild
2 (2.00%) high severe
sync/hook-sync/host-to-wasm - unchecked - nop-params-and-results
time: [43.968 ns 44.169 ns 44.437 ns]
change: [+18.772% +21.802% +24.623%] (p = 0.00 < 0.05)
Performance has regressed.
Found 15 outliers among 100 measurements (15.00%)
3 (3.00%) high mild
12 (12.00%) high severe
async/no-hook/host-to-wasm - typed - nop
time: [4.9612 us 4.9743 us 4.9889 us]
change: [+9.9493% +11.911% +13.502%] (p = 0.00 < 0.05)
Performance has regressed.
Found 10 outliers among 100 measurements (10.00%)
6 (6.00%) high mild
4 (4.00%) high severe
async/no-hook/host-to-wasm - untyped - nop
time: [5.0030 us 5.0211 us 5.0439 us]
change: [+10.841% +11.873% +12.977%] (p = 0.00 < 0.05)
Performance has regressed.
Found 10 outliers among 100 measurements (10.00%)
3 (3.00%) high mild
7 (7.00%) high severe
async/no-hook/host-to-wasm - typed - nop-params-and-results
time: [4.9273 us 4.9468 us 4.9700 us]
change: [+4.7381% +6.8445% +8.8238%] (p = 0.00 < 0.05)
Performance has regressed.
Found 14 outliers among 100 measurements (14.00%)
5 (5.00%) high mild
9 (9.00%) high severe
async/no-hook/host-to-wasm - untyped - nop-params-and-results
time: [5.1151 us 5.1338 us 5.1555 us]
change: [+9.5335% +11.290% +13.044%] (p = 0.00 < 0.05)
Performance has regressed.
Found 16 outliers among 100 measurements (16.00%)
3 (3.00%) high mild
13 (13.00%) high severe
async/hook-sync/host-to-wasm - typed - nop
time: [4.9330 us 4.9394 us 4.9467 us]
change: [+10.046% +11.038% +12.035%] (p = 0.00 < 0.05)
Performance has regressed.
Found 12 outliers among 100 measurements (12.00%)
5 (5.00%) high mild
7 (7.00%) high severe
async/hook-sync/host-to-wasm - untyped - nop
time: [5.0073 us 5.0183 us 5.0310 us]
change: [+9.3828% +10.565% +11.752%] (p = 0.00 < 0.05)
Performance has regressed.
Found 8 outliers among 100 measurements (8.00%)
3 (3.00%) high mild
5 (5.00%) high severe
async/hook-sync/host-to-wasm - typed - nop-params-and-results
time: [4.9610 us 4.9839 us 5.0097 us]
change: [+9.0857% +11.513% +14.359%] (p = 0.00 < 0.05)
Performance has regressed.
Found 13 outliers among 100 measurements (13.00%)
7 (7.00%) high mild
6 (6.00%) high severe
async/hook-sync/host-to-wasm - untyped - nop-params-and-results
time: [5.0995 us 5.1272 us 5.1617 us]
change: [+9.3600% +11.506% +13.809%] (p = 0.00 < 0.05)
Performance has regressed.
Found 10 outliers among 100 measurements (10.00%)
6 (6.00%) high mild
4 (4.00%) high severe
async-pool/no-hook/host-to-wasm - typed - nop
time: [2.4242 us 2.4316 us 2.4396 us]
change: [+7.8756% +8.8803% +9.8346%] (p = 0.00 < 0.05)
Performance has regressed.
Found 8 outliers among 100 measurements (8.00%)
5 (5.00%) high mild
3 (3.00%) high severe
async-pool/no-hook/host-to-wasm - untyped - nop
time: [2.5102 us 2.5155 us 2.5210 us]
change: [+12.130% +13.194% +14.270%] (p = 0.00 < 0.05)
Performance has regressed.
Found 12 outliers among 100 measurements (12.00%)
4 (4.00%) high mild
8 (8.00%) high severe
async-pool/no-hook/host-to-wasm - typed - nop-params-and-results
time: [2.4203 us 2.4310 us 2.4440 us]
change: [+4.0380% +6.3623% +8.7534%] (p = 0.00 < 0.05)
Performance has regressed.
Found 14 outliers among 100 measurements (14.00%)
5 (5.00%) high mild
9 (9.00%) high severe
async-pool/no-hook/host-to-wasm - untyped - nop-params-and-results
time: [2.5501 us 2.5593 us 2.5700 us]
change: [+8.8802% +10.976% +12.937%] (p = 0.00 < 0.05)
Performance has regressed.
Found 16 outliers among 100 measurements (16.00%)
5 (5.00%) high mild
11 (11.00%) high severe
async-pool/hook-sync/host-to-wasm - typed - nop
time: [2.4135 us 2.4190 us 2.4254 us]
change: [+8.3640% +9.3774% +10.435%] (p = 0.00 < 0.05)
Performance has regressed.
Found 11 outliers among 100 measurements (11.00%)
6 (6.00%) high mild
5 (5.00%) high severe
async-pool/hook-sync/host-to-wasm - untyped - nop
time: [2.5172 us 2.5248 us 2.5357 us]
change: [+11.543% +12.750% +13.982%] (p = 0.00 < 0.05)
Performance has regressed.
Found 8 outliers among 100 measurements (8.00%)
1 (1.00%) high mild
7 (7.00%) high severe
async-pool/hook-sync/host-to-wasm - typed - nop-params-and-results
time: [2.4214 us 2.4353 us 2.4532 us]
change: [+1.5158% +5.0872% +8.6765%] (p = 0.00 < 0.05)
Performance has regressed.
Found 15 outliers among 100 measurements (15.00%)
2 (2.00%) high mild
13 (13.00%) high severe
async-pool/hook-sync/host-to-wasm - untyped - nop-params-and-results
time: [2.5499 us 2.5607 us 2.5748 us]
change: [+10.146% +12.459% +14.919%] (p = 0.00 < 0.05)
Performance has regressed.
Found 18 outliers among 100 measurements (18.00%)
3 (3.00%) high mild
15 (15.00%) high severe
sync/no-hook/wasm-to-host - nop - typed
time: [6.6135 ns 6.6288 ns 6.6452 ns]
change: [+37.927% +38.837% +39.869%] (p = 0.00 < 0.05)
Performance has regressed.
Found 7 outliers among 100 measurements (7.00%)
2 (2.00%) high mild
5 (5.00%) high severe
sync/no-hook/wasm-to-host - nop-params-and-results - typed
time: [15.930 ns 15.993 ns 16.067 ns]
change: [+3.9583% +5.6286% +7.2430%] (p = 0.00 < 0.05)
Performance has regressed.
Found 12 outliers among 100 measurements (12.00%)
11 (11.00%) high mild
1 (1.00%) high severe
sync/no-hook/wasm-to-host - nop - untyped
time: [20.596 ns 20.640 ns 20.690 ns]
change: [+4.3293% +5.2047% +6.0935%] (p = 0.00 < 0.05)
Performance has regressed.
Found 10 outliers among 100 measurements (10.00%)
5 (5.00%) high mild
5 (5.00%) high severe
sync/no-hook/wasm-to-host - nop-params-and-results - untyped
time: [42.659 ns 42.882 ns 43.159 ns]
change: [-2.1466% -0.5079% +1.2554%] (p = 0.58 > 0.05)
No change in performance detected.
Found 15 outliers among 100 measurements (15.00%)
1 (1.00%) high mild
14 (14.00%) high severe
sync/no-hook/wasm-to-host - nop - unchecked
time: [10.671 ns 10.691 ns 10.713 ns]
change: [+83.911% +87.620% +92.062%] (p = 0.00 < 0.05)
Performance has regressed.
Found 9 outliers among 100 measurements (9.00%)
2 (2.00%) high mild
7 (7.00%) high severe
sync/no-hook/wasm-to-host - nop-params-and-results - unchecked
time: [11.136 ns 11.190 ns 11.263 ns]
change: [-29.719% -28.446% -27.029%] (p = 0.00 < 0.05)
Performance has improved.
Found 14 outliers among 100 measurements (14.00%)
4 (4.00%) high mild
10 (10.00%) high severe
sync/hook-sync/wasm-to-host - nop - typed
time: [6.7964 ns 6.8087 ns 6.8226 ns]
change: [+21.531% +24.206% +27.331%] (p = 0.00 < 0.05)
Performance has regressed.
Found 14 outliers among 100 measurements (14.00%)
4 (4.00%) high mild
10 (10.00%) high severe
sync/hook-sync/wasm-to-host - nop-params-and-results - typed
time: [15.865 ns 15.921 ns 15.985 ns]
change: [+4.8466% +6.3330% +7.8317%] (p = 0.00 < 0.05)
Performance has regressed.
Found 16 outliers among 100 measurements (16.00%)
3 (3.00%) high mild
13 (13.00%) high severe
sync/hook-sync/wasm-to-host - nop - untyped
time: [21.505 ns 21.587 ns 21.677 ns]
change: [+8.0908% +9.1943% +10.254%] (p = 0.00 < 0.05)
Performance has regressed.
Found 8 outliers among 100 measurements (8.00%)
4 (4.00%) high mild
4 (4.00%) high severe
sync/hook-sync/wasm-to-host - nop-params-and-results - untyped
time: [44.018 ns 44.128 ns 44.261 ns]
change: [-1.4671% -0.0458% +1.2443%] (p = 0.94 > 0.05)
No change in performance detected.
Found 14 outliers among 100 measurements (14.00%)
5 (5.00%) high mild
9 (9.00%) high severe
sync/hook-sync/wasm-to-host - nop - unchecked
time: [11.264 ns 11.326 ns 11.387 ns]
change: [+80.225% +81.659% +83.068%] (p = 0.00 < 0.05)
Performance has regressed.
Found 6 outliers among 100 measurements (6.00%)
3 (3.00%) high mild
3 (3.00%) high severe
sync/hook-sync/wasm-to-host - nop-params-and-results - unchecked
time: [11.816 ns 11.865 ns 11.920 ns]
change: [-29.152% -28.040% -26.957%] (p = 0.00 < 0.05)
Performance has improved.
Found 14 outliers among 100 measurements (14.00%)
8 (8.00%) high mild
6 (6.00%) high severe
async/no-hook/wasm-to-host - nop - typed
time: [6.6221 ns 6.6385 ns 6.6569 ns]
change: [+43.618% +44.755% +45.965%] (p = 0.00 < 0.05)
Performance has regressed.
Found 13 outliers among 100 measurements (13.00%)
6 (6.00%) high mild
7 (7.00%) high severe
async/no-hook/wasm-to-host - nop-params-and-results - typed
time: [15.884 ns 15.929 ns 15.983 ns]
change: [+3.5987% +5.2053% +6.7846%] (p = 0.00 < 0.05)
Performance has regressed.
Found 16 outliers among 100 measurements (16.00%)
3 (3.00%) high mild
13 (13.00%) high severe
async/no-hook/wasm-to-host - nop - untyped
time: [20.615 ns 20.702 ns 20.821 ns]
change: [+6.9799% +8.1212% +9.2819%] (p = 0.00 < 0.05)
Performance has regressed.
Found 10 outliers among 100 measurements (10.00%)
2 (2.00%) high mild
8 (8.00%) high severe
async/no-hook/wasm-to-host - nop-params-and-results - untyped
time: [41.956 ns 42.207 ns 42.521 ns]
change: [-4.3057% -2.7730% -1.2428%] (p = 0.00 < 0.05)
Performance has improved.
Found 14 outliers among 100 measurements (14.00%)
3 (3.00%) high mild
11 (11.00%) high severe
async/no-hook/wasm-to-host - nop - unchecked
time: [10.440 ns 10.474 ns 10.513 ns]
change: [+83.959% +85.826% +87.541%] (p = 0.00 < 0.05)
Performance has regressed.
Found 11 outliers among 100 measurements (11.00%)
5 (5.00%) high mild
6 (6.00%) high severe
async/no-hook/wasm-to-host - nop-params-and-results - unchecked
time: [11.476 ns 11.512 ns 11.554 ns]
change: [-29.857% -28.383% -26.978%] (p = 0.00 < 0.05)
Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
1 (1.00%) low mild
6 (6.00%) high mild
5 (5.00%) high severe
async/no-hook/wasm-to-host - nop - async-typed
time: [26.427 ns 26.478 ns 26.532 ns]
change: [+6.5730% +7.4676% +8.3983%] (p = 0.00 < 0.05)
Performance has regressed.
Found 9 outliers among 100 measurements (9.00%)
2 (2.00%) high mild
7 (7.00%) high severe
async/no-hook/wasm-to-host - nop-params-and-results - async-typed
time: [28.557 ns 28.693 ns 28.880 ns]
change: [+1.9099% +3.7332% +5.9731%] (p = 0.00 < 0.05)
Performance has regressed.
Found 15 outliers among 100 measurements (15.00%)
1 (1.00%) high mild
14 (14.00%) high severe
async/hook-sync/wasm-to-host - nop - typed
time: [6.7488 ns 6.7630 ns 6.7784 ns]
change: [+19.935% +22.080% +23.683%] (p = 0.00 < 0.05)
Performance has regressed.
Found 9 outliers among 100 measurements (9.00%)
4 (4.00%) high mild
5 (5.00%) high severe
async/hook-sync/wasm-to-host - nop-params-and-results - typed
time: [15.928 ns 16.031 ns 16.149 ns]
change: [+5.5188% +6.9567% +8.3839%] (p = 0.00 < 0.05)
Performance has regressed.
Found 11 outliers among 100 measurements (11.00%)
9 (9.00%) high mild
2 (2.00%) high severe
async/hook-sync/wasm-to-host - nop - untyped
time: [21.930 ns 22.114 ns 22.296 ns]
change: [+4.6674% +7.7588% +10.375%] (p = 0.00 < 0.05)
Performance has regressed.
Found 4 outliers among 100 measurements (4.00%)
3 (3.00%) high mild
1 (1.00%) high severe
async/hook-sync/wasm-to-host - nop-params-and-results - untyped
time: [42.684 ns 42.858 ns 43.081 ns]
change: [-5.2957% -3.4693% -1.6217%] (p = 0.00 < 0.05)
Performance has improved.
Found 14 outliers among 100 measurements (14.00%)
2 (2.00%) high mild
12 (12.00%) high severe
async/hook-sync/wasm-to-host - nop - unchecked
time: [11.026 ns 11.053 ns 11.086 ns]
change: [+70.751% +72.378% +73.961%] (p = 0.00 < 0.05)
Performance has regressed.
Found 10 outliers among 100 measurements (10.00%)
5 (5.00%) high mild
5 (5.00%) high severe
async/hook-sync/wasm-to-host - nop-params-and-results - unchecked
time: [11.840 ns 11.900 ns 11.982 ns]
change: [-27.977% -26.584% -24.887%] (p = 0.00 < 0.05)
Performance has improved.
Found 18 outliers among 100 measurements (18.00%)
3 (3.00%) high mild
15 (15.00%) high severe
async/hook-sync/wasm-to-host - nop - async-typed
time: [27.601 ns 27.709 ns 27.882 ns]
change: [+8.1781% +9.1102% +10.030%] (p = 0.00 < 0.05)
Performance has regressed.
Found 11 outliers among 100 measurements (11.00%)
2 (2.00%) low mild
3 (3.00%) high mild
6 (6.00%) high severe
async/hook-sync/wasm-to-host - nop-params-and-results - async-typed
time: [28.955 ns 29.174 ns 29.413 ns]
change: [+1.1226% +3.0366% +5.1126%] (p = 0.00 < 0.05)
Performance has regressed.
Found 13 outliers among 100 measurements (13.00%)
7 (7.00%) high mild
6 (6.00%) high severe
async-pool/no-hook/wasm-to-host - nop - typed
time: [6.5626 ns 6.5733 ns 6.5851 ns]
change: [+40.561% +42.307% +44.514%] (p = 0.00 < 0.05)
Performance has regressed.
Found 9 outliers among 100 measurements (9.00%)
5 (5.00%) high mild
4 (4.00%) high severe
async-pool/no-hook/wasm-to-host - nop-params-and-results - typed
time: [15.820 ns 15.886 ns 15.969 ns]
change: [+4.1044% +5.7928% +7.7122%] (p = 0.00 < 0.05)
Performance has regressed.
Found 17 outliers among 100 measurements (17.00%)
4 (4.00%) high mild
13 (13.00%) high severe
async-pool/no-hook/wasm-to-host - nop - untyped
time: [20.481 ns 20.521 ns 20.566 ns]
change: [+6.7962% +7.6950% +8.7612%] (p = 0.00 < 0.05)
Performance has regressed.
Found 11 outliers among 100 measurements (11.00%)
6 (6.00%) high mild
5 (5.00%) high severe
async-pool/no-hook/wasm-to-host - nop-params-and-results - untyped
time: [41.834 ns 41.998 ns 42.189 ns]
change: [-3.8185% -2.2687% -0.7541%] (p = 0.01 < 0.05)
Change within noise threshold.
Found 13 outliers among 100 measurements (13.00%)
3 (3.00%) high mild
10 (10.00%) high severe
async-pool/no-hook/wasm-to-host - nop - unchecked
time: [10.353 ns 10.380 ns 10.414 ns]
change: [+82.042% +84.591% +87.205%] (p = 0.00 < 0.05)
Performance has regressed.
Found 7 outliers among 100 measurements (7.00%)
4 (4.00%) high mild
3 (3.00%) high severe
async-pool/no-hook/wasm-to-host - nop-params-and-results - unchecked
time: [11.123 ns 11.168 ns 11.228 ns]
change: [-30.813% -29.285% -27.874%] (p = 0.00 < 0.05)
Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
11 (11.00%) high mild
1 (1.00%) high severe
async-pool/no-hook/wasm-to-host - nop - async-typed
time: [27.442 ns 27.528 ns 27.638 ns]
change: [+7.5215% +9.9795% +12.266%] (p = 0.00 < 0.05)
Performance has regressed.
Found 18 outliers among 100 measurements (18.00%)
3 (3.00%) high mild
15 (15.00%) high severe
async-pool/no-hook/wasm-to-host - nop-params-and-results - async-typed
time: [29.014 ns 29.148 ns 29.312 ns]
change: [+2.0227% +3.4722% +4.9047%] (p = 0.00 < 0.05)
Performance has regressed.
Found 7 outliers among 100 measurements (7.00%)
6 (6.00%) high mild
1 (1.00%) high severe
async-pool/hook-sync/wasm-to-host - nop - typed
time: [6.7916 ns 6.8116 ns 6.8325 ns]
change: [+20.937% +22.050% +23.281%] (p = 0.00 < 0.05)
Performance has regressed.
Found 11 outliers among 100 measurements (11.00%)
5 (5.00%) high mild
6 (6.00%) high severe
async-pool/hook-sync/wasm-to-host - nop-params-and-results - typed
time: [15.917 ns 15.975 ns 16.051 ns]
change: [+4.6404% +6.4217% +8.3075%] (p = 0.00 < 0.05)
Performance has regressed.
Found 16 outliers among 100 measurements (16.00%)
5 (5.00%) high mild
11 (11.00%) high severe
async-pool/hook-sync/wasm-to-host - nop - untyped
time: [21.558 ns 21.612 ns 21.679 ns]
change: [+8.1158% +9.1409% +10.217%] (p = 0.00 < 0.05)
Performance has regressed.
Found 9 outliers among 100 measurements (9.00%)
2 (2.00%) high mild
7 (7.00%) high severe
async-pool/hook-sync/wasm-to-host - nop-params-and-results - untyped
time: [42.475 ns 42.614 ns 42.775 ns]
change: [-6.3613% -4.4709% -2.7647%] (p = 0.00 < 0.05)
Performance has improved.
Found 18 outliers among 100 measurements (18.00%)
3 (3.00%) high mild
15 (15.00%) high severe
async-pool/hook-sync/wasm-to-host - nop - unchecked
time: [11.150 ns 11.195 ns 11.247 ns]
change: [+74.424% +77.056% +79.811%] (p = 0.00 < 0.05)
Performance has regressed.
Found 14 outliers among 100 measurements (14.00%)
3 (3.00%) high mild
11 (11.00%) high severe
async-pool/hook-sync/wasm-to-host - nop-params-and-results - unchecked
time: [11.639 ns 11.695 ns 11.760 ns]
change: [-30.212% -29.023% -27.954%] (p = 0.00 < 0.05)
Performance has improved.
Found 15 outliers among 100 measurements (15.00%)
7 (7.00%) high mild
8 (8.00%) high severe
async-pool/hook-sync/wasm-to-host - nop - async-typed
time: [27.480 ns 27.712 ns 27.984 ns]
change: [+2.9764% +6.5061% +9.8914%] (p = 0.00 < 0.05)
Performance has regressed.
Found 8 outliers among 100 measurements (8.00%)
6 (6.00%) high mild
2 (2.00%) high severe
async-pool/hook-sync/wasm-to-host - nop-params-and-results - async-typed
time: [29.218 ns 29.380 ns 29.600 ns]
change: [+5.2283% +7.7247% +10.822%] (p = 0.00 < 0.05)
Performance has regressed.
Found 16 outliers among 100 measurements (16.00%)
2 (2.00%) high mild
14 (14.00%) high severe
```
</details>
* Add s390x support for frame pointer-based stack walking
* wasmtime: Allow `Caller::get_export` to get all exports
* fuzzing: Add a fuzz target to check that our stack traces are correct
We generate Wasm modules that keep track of their own stack as they call and
return between functions, and then we periodically check that if the host
captures a backtrace, it matches what the Wasm module has recorded.
* Remove VM offsets for `VMHostFuncContext` since it isn't used by JIT code
* Add doc comment with stack walking implementation notes
* Document the extra state that can be passed to `wasmtime_runtime::Backtrace` methods
* Add extensive comments for stack walking function
* Factor architecture-specific bits of stack walking out into modules
* Initialize store-related fields in a vmctx to null when there is no store yet
Rather than leaving them as uninitialized data.
* Use `set_callee` instead of manually setting the vmctx field
* Use a more informative compile error message for unsupported architectures
* Document unsafety of `prepare_host_to_wasm_trampoline`
* Use `bti c` instead of `hint #34` in inline aarch64 assembly
* Remove outdated TODO comment
* Remove setting of `last_wasm_exit_fp` in `set_jit_trap`
This is no longer needed as the value is plumbed through to the backtrace code
directly now.
* Only set the stack limit once, in the face of re-entrancy into Wasm
* Add comments for s390x-specific stack walking bits
* Use the helper macro for all libcalls
If we forget to use it, and then trigger a GC from the libcall, that means we
could miss stack frames when walking the stack, fail to find live GC refs, and
then get use after free bugs. Much less risky to always use the helper macro
that takes care of all of that for us.
* Use the `asm_sym!` macro in Wasm-to-libcall trampolines
This macro handles the macOS-specific underscore prefix stuff for us.
* wasmtime: add size and align to `externref` assertion error message
* Extend the `stacks` fuzzer to have host frames in between Wasm frames
This way we get one or more contiguous sequences of Wasm frames on the stack,
instead of exactly one.
* Add documentation for aarch64-specific backtrace helpers
* Clarify that we only support little-endian aarch64 in trampoline comment
* Use `.machine z13` in s390x assembly file
Since apparently our CI machines have pretty old assemblers that don't have
`.machine z14`. This should be fine though since these trampolines don't make
use of anything that is introduced in z14.
* Fix aarch64 build
* Fix macOS build
* Document the `asm_sym!` macro
* Add windows support to the `wasmtime-asm-macros` crate
* Add windows support to host<--->Wasm trampolines
* Fix trap handler build on windows
* Run `rustfmt` on s390x trampoline source file
* Temporarily disable some assertions about a trap's backtrace in the component model tests
Follow up to re-enable this and fix the associated issue:
https://github.com/bytecodealliance/wasmtime/issues/4535
* Refactor libcall definitions with less macros
This refactors the `libcall!` macro to use the
`foreach_builtin_function!` macro to define all of the trampolines.
Additionally the macro surrounding each libcall itself is no longer
necessary and helps avoid too many macros.
* Use `VMOpaqueContext::from_vm_host_func_context` in `VMHostFuncContext::new`
* Move `backtrace` module to be submodule of `traphandlers`
This avoids making some things `pub(crate)` in `traphandlers` that really
shouldn't be.
* Fix macOS aarch64 build
* Use "i64" instead of "word" in aarch64-specific file
* Save/restore entry SP and exit FP/return pointer in the face of panicking imported host functions
Also clean up assertions surrounding our saved entry/exit registers.
* Put "typed" vs "untyped" in the same position of call benchmark names
Regardless if we are doing wasm-to-host or host-to-wasm
* Fix stacks test case generator build for new `wasm-encoder`
* Fix build for s390x
* Expand libcalls in s390x asm
* Disable more parts of component tests now that backtrace assertions are a bit tighter
* Remove assertion that can maybe fail on s390x
Co-authored-by: Ulrich Weigand <ulrich.weigand@de.ibm.com>
Co-authored-by: Alex Crichton <alex@alexcrichton.com>
* Allow using jump-tables multiple times (fixes#3347)
If there are multiple `br_table` instructions using the same jump table,
then `append_jump_argument` must not modify the jump table in-place.
When this function is called, we don't know if more `br_table`
instructions might be added later. So this patch conservatively assumes
that all jump tables might be reused. If Cranelift needs to add a block
argument to a block that's the target of some jump table, then the jump
table will be unconditionally cloned.
I'm not sure if having duplicated and unused jump tables will turn out
to be a compile-time performance issue. If it is, there's discussion in
issue #3347 about ways to determine that there can't be any more uses of
a jump table, so that it's safe to modify in-place.
* Re-enable cranelift-fuzzgen fuzz target
I've been running this fuzz target for an hour without finding new bugs.
Let's see if oss-fuzz finds anything now.
The compile step that cranelift-fuzzgen does also triggers IR
verification. So all bugs that cranelift-fuzzgen-verify could catch are
also caught by cranelift-fuzzgen. Removing redundant fuzzers lets us
spend limited fuzz-testing CPU time budgets better.
Consulting oss-fuzz it looks like these fuzz targets are crashing 100%
of the time partly due to #3347 I believe. Until that's fixed this hopes
to reclaim the time used on oss-fuzz for other fuzzers to make progress.
OSS-fuzz long-ago discovered https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=45662
which we currently believe to be a bug in v8. I originally thought it
was going to be fixed with https://bugs.chromium.org/p/v8/issues/detail?id=12722
but that no longer appears to be the case now that the `v8` crate has
caught up and it still isn't fixed. Personally I've sort of lost an
appetite for continuing to debug these issues so I figure it's best to
just disable reference types with v8 for now and exercise the rest of
the engine, e.g. simd.
`wasm-smith` v0.11 has support for generating shared memories when the
`threads_enabled` configuration flag is set. This change turns on that
flag occasionally. This also upgrades `wasm-smith` to v0.11.1 to always
generate shared memory with a known maximum.
This commit refactored `Config` to use a seperate `CompilerConfig` field instead
of operating on `CompilerBuilder` directly to make all its methods idempotent.
Fixes#4189
We should still get the same amount of fuzzing using libfuzzer's mutators and
using `wasm-mutate` as a mutator now, but they can share the same corpus,
allowing mutations that one performed but the other didn't to reach new areas.
This tells Cranelift to run regalloc2's symbolic verifier on the results
of register allocation after compiling each function.
We already fuzz regalloc2 independently, but that provides coverage
using regalloc2's purpose-built (synthetic) `Function` implementation.
This fuzz target with this change, in contrast, exercises regalloc2 with
whatever particular details of generated code Cranelift generates.
Testing the whole pipeline together and ensuring that the register
allocation is still valid is at least as important as fuzzing regalloc2
independently, IMHO.
Fuzzed locally for a brief time (~10M inputs) to smoke-test; let's see
what oss-fuzz can find (hopefully it's boring)!
* Upgrade all crates to the Rust 2021 edition
I've personally started using the new format strings for things like
`panic!("some message {foo}")` or similar and have been upgrading crates
on a case-by-case basis, but I think it probably makes more sense to go
ahead and blanket upgrade everything so 2021 features are always
available.
* Fix compile of the C API
* Fix a warning
* Fix another warning
A fuzz bug was hit last night where the root of the fuzz bug appears to
be exhaustion of the virtual address space. The specific case in
question instantiated a module with ~100 memories ~100 times, and each
memory reserved ~8gb of the virtual address space. This takes around 47
bits of addressable memory which is mighty close to the limit of what
can be done on x86_64, so this commit reduces the number of memories
that an instance may have when coming out of `wasm-smith`.
* Move spec interpreter fuzzing behind a Cargo feature
Building the spec interpreter requires a local installation of Ocaml and
now libgmp which isn't always available, so this enables the ability to
disable building the spec interpreter by using `cargo +nightly fuzz
build --no-default-features`. The spec interpreter is still built by
default but if fuzzers are being built locally and the spec interpreter
isn't needed then this should enable it to be relatively easily
opted-out of.
* Tweak manifest directives
* fuzzing: Add a custom mutator based on `wasm-mutate`
* fuzz: Add a version of the `compile` fuzz target that uses `wasm-mutate`
* Update `wasmparser` dependencies
Addresses #3809: when we are asked to create a Cranelift backend with
shared flags that indicate support for SIMD, we should check that the
ISA level needed for our SIMD lowerings is present.
This commit improves the stability of the fuzz targets by ensuring the
generated configs and modules are congruent, especially when the pooling
allocator is being used.
For the `differential` target, this means both configurations must use the same
allocation strategy for now as one side generates the module that might not be
compatible with another arbitrary config now that we fuzz the pooling
allocator.
These changes also ensure that constraints put on the config are more
consistently applied, especially when using a fuel-based timeout.
* Add the instance allocation strategy to generated fuzzing configs.
This commit adds support for generating configs with arbitrary instance
allocation strategies.
With this, the pooling allocator will be fuzzed as part of the existing fuzz
targets.
* Refine maximum constants for arbitrary module limits.
* Add an `instantiate-many` fuzz target.
This commit adds a new `instantiate-many` fuzz target that will attempt to
instantiate and terminate modules in an arbitrary order.
It generates up to 5 modules, from which a random sequence of instances will be
created.
The primary benefactor of this fuzz target is the pooling instance allocator.
* Allow no aliasing in generated modules when using the pooling allocator.
This commit prevents aliases in the generated modules as they might count
against the configured import limits of the pooling allocator.
As the existing module linking proposal implementation will eventually be
deprecated in favor of the component model proposal, it isn't very important
that we test aliases in generated modules with the pooling allocator.
* Improve distribution of memory config in fuzzing.
The previous commit attempted to provide a 32-bit upper bound to 64-bit
arbitrary values, which skewed the distribution heavily in favor of the upper
bound.
This commit removes the constraint and instead uses arbitrary 32-bit values
that are converted to 64-bit values in the `Arbitrary` implementation.
* fuzz: Refactor Wasmtime's fuzz targets
A recent fuzz bug found is related to timing out when compiling a
module. This timeout, however, is predominately because Cranelift's
debug verifier is enabled and taking up over half the compilation time.
I wanted to fix this by disabling the verifier when input modules might
have a lot of functions, but this was pretty difficult to implement.
Over time we've grown a number of various fuzzers. Most are
`wasm-smith`-based at this point but there's various entry points for
configuring the wasm-smith module, the wasmtime configuration, etc. I've
historically gotten quite lost in trying to change defaults and feeling
like I have to touch a lot of different places. This is the motivation
for this commit, simplifying fuzzer default configuration.
This commit removes the ability to create a default `Config` for
fuzzing, instead only supporting generating a configuration via
`Arbitrary`. This then involved refactoring all targets and fuzzers to
ensure that configuration is generated through `Arbitrary`. This should
actually expand the coverage of some existing fuzz targets since
`Arbitrary for Config` will tweak options that don't affect runtime,
such as memory configuration or jump veneers.
All existing fuzz targets are refactored to use this new method of
configuration. Some fuzz targets were also shuffled around or
reimplemented:
* `compile` - this now directly calls `Module::new` to skip all the
fuzzing infrastructure. This is mostly done because this fuzz target
isn't too interesting and is largely just seeing what happens when
things are thrown at the wall for Wasmtime.
* `instantiate-maybe-invalid` - this fuzz target now skips instantiation
and instead simply goes into `Module::new` like the `compile` target.
The rationale behind this is that most modules won't instantiate
anyway and this fuzz target is primarily fuzzing the compiler. This
skips having to generate arbitrary configuration since
wasm-smith-generated-modules (or valid ones at least) aren't used
here.
* `instantiate` - this fuzz target was removed. In general this fuzz
target isn't too interesting in isolation. Almost everything it deals
with likely won't pass compilation and is covered by the `compile`
fuzz target, and otherwise interesting modules being instantiated can
all theoretically be created by `wasm-smith` anyway.
* `instantiate-wasm-smith` and `instantiate-swarm` - these were both merged
into a new `instantiate` target (replacing the old one from above).
There wasn't really much need to keep these separate since they really
only differed at this point in methods of timeout. Otherwise we much
more heavily use `SwarmConfig` than wasm-smith's built-in options.
The intention is that we should still have basically the same coverage
of fuzzing as before, if not better because configuration is now
possible on some targets. Additionally there is one centralized point of
configuration for fuzzing for wasmtime, `Arbitrary for ModuleConfig`.
This internally creates an arbitrary `SwarmConfig` from `wasm-smith` and
then further tweaks it for Wasmtime's needs, such as enabling various
wasm proposals by default. In the future enabling a wasm proposal on
fuzzing should largely just be modifying this one trait implementation.
* fuzz: Sometimes disable the cranelift debug verifier
This commit disables the cranelift debug verifier if the input wasm
module might be "large" for the definition of "more than 10 functions".
While fuzzing we disable threads (set them to 1) and enable the
cranelift debug verifier. Coupled with a 20-30x slowdown this means that
a module with the maximum number of functions, 100, gives:
60x / 100 functions / 30x slowdown = 20ms
With only 20 milliseconds per function this is even further halved by
the `differential` fuzz target compiling a module twice, which means
that, when compiling with a normal release mode Wasmtime, if any
function takes more than 10ms to compile then it's a candidate for
timing out while fuzzing. Given that the cranelift debug verifier can
more than double compilation time in fuzzing mode this actually means
that the real time budget for function compilation is more like 4ms.
The `wasm-smith` crate can pretty easily generate a large function that
takes 4ms to compile, and then when that function is multiplied 100x in
the `differential` fuzz target we trivially time out the fuzz target.
The hope of this commit is to buy back half our budget by disabling the
debug verifier for modules that may have many functions. Further
refinements can be implemented in the future such as limiting functions
for just the differential target as well.
* Fix the single-function-module fuzz configuration
* Tweak how features work in differential fuzzing
* Disable everything for baseline differential fuzzing
* Enable selectively for each engine afterwards
* Also forcibly enable reference types and bulk memory for spec tests
* Log wasms when compiling
* Add reference types support to v8 fuzzer
* Fix timeouts via fuel
The default store has "infinite" fuel so that needs to be consumed
before fuel is added back in.
* Remove fuzzing-specific tests
These no longer compile and also haven't been added to in a long time.
Most of the time a reduced form of original the fuzz test case is added
when a fuzz bug is fixed.
Peepmatic was an early attempt at a DSL for peephole optimizations, with the
idea that maybe sometime in the future we could user it for instruction
selection as well. It didn't really pan out, however:
* Peepmatic wasn't quite flexible enough, and adding new operators or snippets
of code implemented externally in Rust was a bit of a pain.
* The performance was never competitive with the hand-written peephole
optimizers. It was *very* size efficient, but that came at the cost of
run-time efficiency. Everything was table-based and interpreted, rather than
generating any Rust code.
Ultimately, because of these reasons, we never turned Peepmatic on by default.
These days, we just landed the ISLE domain-specific language, and it is better
suited than Peepmatic for all the things that Peepmatic was originally designed
to do. It is more flexible and easy to integrate with external Rust code. It is
has better time efficiency, meeting or even beating hand-written code. I think a
small part of the reason why ISLE excels in these things is because its design
was informed by Peepmatic's failures. I still plan on continuing Peepmatic's
mission to make Cranelift's peephole optimizer passes generated from DSL rewrite
rules, but using ISLE instead of Peepmatic.
Thank you Peepmatic, rest in peace!
Alignment on all memory instructions in wasm is currently best-effort
and not actually required, meaning that whatever wasm actually uses as
an address should work regardless of whether the address is aligned or
not. This is theoretically tested in the fuzzers via
wasm-smith-generated code, but wasm-smith doesn't today have too too
high of a chance of generating an actual successful load/store.
This commit adds a new configuration option to the `Config` generator
for fuzzing which forces usage of a custom linear memory implementation
which is backed by Rust's `Vec<u8>` and forces the base address of
linear memory to be off-by-one relative to the base address of the
`Vec<u8>` itself. This should theoretically force host addresses to
almost always be unaligned, even if wasm addresses are otherwise
aligned.
The main interesting fuzz coverage here is likely to be in the existing
`differential` target which compares running the same module in wasmtime
with two different `Config` values to ensure the same results are
produced. This probably won't increase coverage all that much in the
near future due to wasm-smith rarely generating successful loads/stores,
but in the meantime by hooking this up into `Config` it also means that
we'll be running in comparison against v8 and also ensuring that all
spec tests succeed if misalignment is forced at the hardware level.
As a side effect this commit also cleans up the fuzzers slightly:
* The `DifferentialConfig` struct is removed and folded into `Config`
* The `init_hang_limit` processing is removed since we don't use
`-ttf`-generated modules from binaryen any more.
* Traps are now asserted to have the same trap code, otherwise
differential fuzzing fails.
* Some more debug logging was added to the differential fuzzer
This commit removes the `differential_spec` fuzz target for now,
although this removal is intended to be temporary. We have #3251 to
track re-enabling the spec interpreter in a way that it won't time out,
and additionally the spec interpreter is also failing to build with
ocaml on oss-fuzz so that will also need to be investigated when
re-enabling.
This commit removes the Lightbeam backend from Wasmtime as per [RFC 14].
This backend hasn't received maintenance in quite some time, and as [RFC
14] indicates this doesn't meet the threshold for keeping the code
in-tree, so this commit removes it.
A fast "baseline" compiler may still be added in the future. The
addition of such a backend should be in line with [RFC 14], though, with
the principles we now have for stable releases of Wasmtime. I'll close
out Lightbeam-related issues once this is merged.
[RFC 14]: https://github.com/bytecodealliance/rfcs/pull/14
We've got a large crop of fuzz-bugs from fuzzing with enabled-with-SIMD
on oss-fuzz but at this point the fuzz stats from oss-fuzz say that the
fuzzers like v8 are spending less than 50% of its time actually fuzzing
and presumably mostly hitting crashes and such. While we fix the other
issues this disables simd for fuzzing with v8 so we can try to see if we
can weed out other issues.
* Add differential fuzzing against V8
This commit adds a differential fuzzing target to Wasmtime along the
lines of the wasmi and spec interpreters we already have, but with V8
instead. The intention here is that wasmi is unlikely to receive updates
over time (e.g. for SIMD), and the spec interpreter is not suitable for
fuzzing against in general due to its performance characteristics. The
hope is that V8 is indeed appropriate to fuzz against because it's
naturally receiving updates and it also is expected to have good
performance.
Here the `rusty_v8` crate is used which provides bindings to V8 as well
as precompiled binaries by default. This matches exactly the use case we
need and at least for now I think the `rusty_v8` crate will be
maintained by the Deno folks as they continue to develop it. If it
becomes an issue though maintaining we can evaluate other options to
have differential fuzzing against.
For now this commit enables the SIMD and bulk-memory feature of
fuzz-target-generation which should enable them to get
differentially-fuzzed with V8 in addition to the compilation fuzzing
we're already getting.
* Use weak linkage for GDB jit helpers
This should help us deduplicate our symbol with other JIT runtimes, if
any. For now this leans on some C helpers to define the weak linkage
since Rust doesn't support that on stable yet.
* Don't use rusty_v8 on MinGW
They don't have precompiled libraries there.
* Fix msvc build
* Comment about execution
* Update wasm-smith to 0.7.0
* Canonicalize NaN with wasm-smith for differential fuzzing
This then also enables floating point executing in wasmi in addition to
the spec interpreter. With NaN canonicalization at the wasm level this
means that we should be producing deterministic results between Wasmtime
and these alternative implementations.
* Implement the memory64 proposal in Wasmtime
This commit implements the WebAssembly [memory64 proposal][proposal] in
both Wasmtime and Cranelift. In terms of work done Cranelift ended up
needing very little work here since most of it was already prepared for
64-bit memories at one point or another. Most of the work in Wasmtime is
largely refactoring, changing a bunch of `u32` values to something else.
A number of internal and public interfaces are changing as a result of
this commit, for example:
* Acessors on `wasmtime::Memory` that work with pages now all return
`u64` unconditionally rather than `u32`. This makes it possible to
accommodate 64-bit memories with this API, but we may also want to
consider `usize` here at some point since the host can't grow past
`usize`-limited pages anyway.
* The `wasmtime::Limits` structure is removed in favor of
minimum/maximum methods on table/memory types.
* Many libcall intrinsics called by jit code now unconditionally take
`u64` arguments instead of `u32`. Return values are `usize`, however,
since the return value, if successful, is always bounded by host
memory while arguments can come from any guest.
* The `heap_addr` clif instruction now takes a 64-bit offset argument
instead of a 32-bit one. It turns out that the legalization of
`heap_addr` already worked with 64-bit offsets, so this change was
fairly trivial to make.
* The runtime implementation of mmap-based linear memories has changed
to largely work in `usize` quantities in its API and in bytes instead
of pages. This simplifies various aspects and reflects that
mmap-memories are always bound by `usize` since that's what the host
is using to address things, and additionally most calculations care
about bytes rather than pages except for the very edge where we're
going to/from wasm.
Overall I've tried to minimize the amount of `as` casts as possible,
using checked `try_from` and checked arithemtic with either error
handling or explicit `unwrap()` calls to tell us about bugs in the
future. Most locations have relatively obvious things to do with various
implications on various hosts, and I think they should all be roughly of
the right shape but time will tell. I mostly relied on the compiler
complaining that various types weren't aligned to figure out
type-casting, and I manually audited some of the more obvious locations.
I suspect we have a number of hidden locations that will panic on 32-bit
hosts if 64-bit modules try to run there, but otherwise I think we
should be generally ok (famous last words). In any case I wouldn't want
to enable this by default naturally until we've fuzzed it for some time.
In terms of the actual underlying implementation, no one should expect
memory64 to be all that fast. Right now it's implemented with
"dynamic" heaps which have a few consequences:
* All memory accesses are bounds-checked. I'm not sure how aggressively
Cranelift tries to optimize out bounds checks, but I suspect not a ton
since we haven't stressed this much historically.
* Heaps are always precisely sized. This means that every call to
`memory.grow` will incur a `memcpy` of memory from the old heap to the
new. We probably want to at least look into `mremap` on Linux and
otherwise try to implement schemes where dynamic heaps have some
reserved pages to grow into to help amortize the cost of
`memory.grow`.
The memory64 spec test suite is scheduled to now run on CI, but as with
all the other spec test suites it's really not all that comprehensive.
I've tried adding more tests for basic things as I've had to implement
guards for them, but I wouldn't really consider the testing adequate
from just this PR itself. I did try to take care in one test to actually
allocate a 4gb+ heap and then avoid running that in the pooling
allocator or in emulation because otherwise that may fail or take
excessively long.
[proposal]: https://github.com/WebAssembly/memory64/blob/master/proposals/memory64/Overview.md
* Fix some tests
* More test fixes
* Fix wasmtime tests
* Fix doctests
* Revert to 32-bit immediate offsets in `heap_addr`
This commit updates the generation of addresses in wasm code to always
use 32-bit offsets for `heap_addr`, and if the calculated offset is
bigger than 32-bits we emit a manual add with an overflow check.
* Disable memory64 for spectest fuzzing
* Fix wrong offset being added to heap addr
* More comments!
* Clarify bytes/pages
This new target compares the outputs of executing the first exported
function of a Wasm module in Wasmtime and in the official Wasm spec
interpreter (using the `wasm-spec-interpreter` crate). This is an
initial step towards more fully-featured fuzzing (e.g. compare memories,
add `v128`, add references, add other proposals, etc.)
* Enable simd fuzzing on oss-fuzz
This commit generally enables the simd feature while fuzzing, which
should affect almost all fuzzers. For fuzzers that just throw random
data at the wall and see what sticks, this means that they'll now be
able to throw simd-shaped data at the wall and have it stick. For
wasm-smith-based fuzzers this commit also updates wasm-smith to 0.6.0
which allows further configuring the `SwarmConfig` after generation,
notably allowing `instantiate-swarm` to generate modules using simd
using `wasm-smith`. This should much more reliably feed simd-related
things into the fuzzers.
Finally, this commit updates wasmtime to avoid usage of the general
`wasm_smith::Module` generator to instead use a Wasmtime-specific custom
default configuration which enables various features we have
implemented.
* Allow dummy table creation to fail
Tables might creation for imports may exceed the memory limit on the
store, which we'll want to gracefully recover from and not fail the
fuzzers.
* cranelift: Initial fuzzer implementation
* cranelift: Generate multiple test cases in fuzzer
* cranelift: Separate function generator in fuzzer
* cranelift: Insert random instructions in fuzzer
* cranelift: Rename gen_testcase
* cranelift: Implement div for unsigned values in interpreter
* cranelift: Run all test cases in fuzzer
* cranelift: Comment options in function_runner
* cranelift: Improve fuzzgen README.md
* cranelift: Fuzzgen remove unused variable
* cranelift: Fuzzer code style fixes
Thanks! @bjorn3
* cranelift: Fix nits in CLIF fuzzer
Thanks @cfallin!
* cranelift: Implement Arbitrary for TestCase
* cranelift: Remove gen_testcase
* cranelift: Move fuzzers to wasmtime fuzz directory
* cranelift: CLIF-Fuzzer ignore tests that produce traps
* cranelift: CLIF-Fuzzer create new fuzz target to validate generated testcases
* cranelift: Store clif-fuzzer config in a separate struct
* cranelift: Generate variables upfront per function
* cranelift: Prevent publishing of fuzzgen crate
* Update wasm-tools crates
This brings in recent updates, notably including more improvements to
wasm-smith which will hopefully help exercise non-trapping wasm more.
* Fix some wat
This PR switches the default backend on x86, for both the
`cranelift-codegen` crate and for Wasmtime, to the new
(`MachInst`-style, `VCode`-based) backend that has been under
development and testing for some time now.
The old backend is still available by default in builds with the
`old-x86-backend` feature, or by requesting `BackendVariant::Legacy`
from the appropriate APIs.
As part of that switch, it adds some more runtime-configurable plumbing
to the testing infrastructure so that tests can be run using the
appropriate backend. `clif-util test` is now capable of parsing a
backend selector option from filetests and instantiating the correct
backend.
CI has been updated so that the old x86 backend continues to run its
tests, just as we used to run the new x64 backend separately.
At some point, we will remove the old x86 backend entirely, once we are
satisfied that the new backend has not caused any unforeseen issues and
we do not need to revert.
This bumps target-lexicon and adds support for the AppleAarch64 calling
convention. Specifically for WebAssembly support, we only have to worry
about the new stack slots convention. Stack slots don't need to be at
least 8-bytes, they can be as small as the data type's size. For
instance, if we need stack slots for (i32, i32), they can be located at
offsets (+0, +4). Note that they still need to be properly aligned on
the data type they're containing, though, so if we need stack slots for
(i32, i64), we can't start the i64 slot at the +4 offset (it must start
at the +8 offset).
Added one test that was failing on the Mac M1, as well as other tests
stressing different yet similar situations.
There are occasional timeouts in type checking where Z3 hangs. This is a known
issue[0] with the implementation of type checking in Peepmatic, and getting
these timeouts in the fuzzers is just annoying and adds noise to our fuzzing
results. When we fix [0] we can reintroduce these fuzz targets.
[0]: https://github.com/bytecodealliance/wasmtime/issues/2695
* Consume fuel during function execution
This commit adds codegen infrastructure necessary to instrument wasm
code to consume fuel as it executes. Currently nothing is really done
with the fuel, but that'll come in later commits.
The focus of this commit is to implement the codegen infrastructure
necessary to consume fuel and account for fuel consumed correctly.
* Periodically check remaining fuel in wasm JIT code
This commit enables wasm code to periodically check to see if fuel has
run out. When fuel runs out an intrinsic is called which can do what it
needs to do in the result of fuel running out. For now a trap is thrown
to have at least some semantics in synchronous stores, but another
planned use for this feature is for asynchronous stores to periodically
yield back to the host based on fuel running out.
Checks for remaining fuel happen in the same locations as interrupt
checks, which is to say the start of the function as well as loop
headers.
* Improve codegen by caching `*const VMInterrupts`
The location of the shared interrupt value and fuel value is through a
double-indirection on the vmctx (load through the vmctx and then load
through that pointer). The second pointer in this chain, however, never
changes, so we can alter codegen to account for this and remove some
extraneous load instructions and hopefully reduce some register
pressure even maybe.
* Add tests fuel can abort infinite loops
* More fuzzing with fuel
Use fuel to time out modules in addition to time, using fuzz input to
figure out which.
* Update docs on trapping instructions
* Fix doc links
* Fix a fuzz test
* Change setting fuel to adding fuel
* Fix a doc link
* Squelch some rustdoc warnings
This commit updates the various tooling used by wasmtime which has new
updates to the module linking proposal. This is done primarily to sync
with WebAssembly/module-linking#26. The main change implemented here is
that wasmtime now supports creating instances from a set of values, nott
just from instantiating a module. Additionally subtyping handling of
modules with respect to imports is now properly handled by desugaring
two-level imports to imports of instances.
A number of small refactorings are included here as well, but most of
them are in accordance with the changes to `wasmparser` and the updated
binary format for module linking.
