Introduce a new concept in the IR that allows a producer to create
dynamic vector types. An IR function can now contain global value(s)
that represent a dynamic scaling factor, for a given fixed-width
vector type. A dynamic type is then created by 'multiplying' the
corresponding global value with a fixed-width type. These new types
can be used just like the existing types and the type system has a
set of hard-coded dynamic types, such as I32X4XN, which the user
defined types map onto. The dynamic types are also used explicitly
to create dynamic stack slots, which have no set size like their
existing counterparts. New IR instructions are added to access these
new stack entities.
Currently, during codegen, the dynamic scaling factor has to be
lowered to a constant so the dynamic slots do eventually have a
compile-time known size, as do spill slots.
The current lowering for aarch64 just targets Neon, using a dynamic
scale of 1.
Copyright (c) 2022, Arm Limited.
* Bump versions of wasm-tools crates
Note that this leaves new features in the component model, outer type
aliases for core wasm types, unimplemented for now.
* Move to crates.io-based versions of tools
* Implement `canon lower` of a `canon lift` function in the same component
This commit implements the "degenerate" logic for implementing a
function within a component that is lifted and then immediately lowered
again. In this situation the lowered function will immediately generate
a trap and doesn't need to implement anything else.
The implementation in this commit is somewhat heavyweight but I think is
probably justified moreso in future additions to the component model
rather than what exactly is here right now. It's not expected that this
"always trap" functionality will really be used all that often since it
would generally mean a buggy component, but the functionality plumbed
through here is hopefully going to be useful for implementing
component-to-component adapter trampolines.
Specifically this commit implements a strategy where the `canon.lower`'d
function is generated by Cranelift and simply has a single trap
instruction when called, doing nothing else. The main complexity comes
from juggling around all the data associated with these functions,
primarily plumbing through the traps into the `ModuleRegistry` to
ensure that the global `is_wasm_trap_pc` function returns `true` and at
runtime when we lookup information about the trap it's all readily
available (e.g. translating the trapping pc to a `TrapCode`).
* Fix non-component build
* Fix some offset calculations
* Only create one "always trap" per signature
Use an internal map to deduplicate during compilation.
* Implement lowered-then-lifted functions
This commit is a few features bundled into one, culminating in the
implementation of lowered-then-lifted functions for the component model.
It's probably not going to be used all that often but this is possible
within a valid component so Wasmtime needs to do something relatively
reasonable. The main things implemented in this commit are:
* Component instances are now assigned a `RuntimeComponentInstanceIndex`
to differentiate each one. This will be used in the future to detect
fusion (one instance lowering a function from another instance). For
now it's used to allocate separate `VMComponentFlags` for each
internal component instance.
* The `CoreExport<FuncIndex>` of lowered functions was changed to a
`CoreDef` since technically a lowered function can use another lowered
function as the callee. This ended up being not too difficult to plumb
through as everything else was already in place.
* A need arose to compile host-to-wasm trampolines which weren't already
present. Currently wasm in a component is always entered through a
host-to-wasm trampoline but core wasm modules are the source of all
the trampolines. In the case of a lowered-then-lifted function there
may not actually be any core wasm modules, so component objects now
contain necessary trampolines not otherwise provided by the core wasm
objects. This feature required splitting a new function into the
`Compiler` trait for creating a host-to-wasm trampoline. After doing
this core wasm compilation was also updated to leverage this which
further enabled compiling trampolines in parallel as opposed to the
previous synchronous compilation.
* Review comments
* Change how unwind information is stored on Windows
Unwind information on Windows is stored in two separate locations. The
first location is the unwind information itself which corresponds to
`UNWIND_INFO`. The second location is a list of `RUNTIME_INFO`
structures which point to function bodes and `UNWIND_INFO` structures.
Currently in Wasmtime the `UNWIND_INFO` structures are stored just after
functions themselves with a somewhat cryptic comment indicating that
Windows prefers this (I'm unsure as to the provenance of this comment).
The `RUNTIME_INFO` data is then stored in a separate section which has
the custom name of `_wasmtime_winx64_unwind`.
After my recent foray into trying to debug windows-2022 bad unwind
information again I realized though that Windows actually has official
sections for these two unwind information items. The `.xdata` section is
used to store the `UNWIND_INFO` structures and the `.pdata` section
stores the `RUNTIME_INFO` list. To try to be somewhat idiomatic and
perhaps one day even hook into standard Windows debugging tools I went
ahead and refactored how our unwind information is stored to match this.
Perhaps the main benefit of this is that it reduces the size of the
read/execute section of the binary. Previously the unwind information
was executable since it was stored in the `.text` section, but
unnecessarily so. Now it's in a read-only section which is in theory a
small amount of hardening.
Otherwise though I don't think this will really help all that much to
hook up in to standard debugging tools like `objdump` because it's all
still stored in an ELF file rather than a COFF file.
* Review comments
This commit implements the `post-return` feature of the canonical ABI in
the component model. This attribute is an optionally-specified function
which is to be executed after the return value has been processed by the
caller to optionally clean-up the return value. This enables, for
example, returning an allocated string and the host then knows how to
clean it up to prevent memory leaks in the original module.
The API exposed in this PR changes the prior `TypedFunc::call` API in
behavior but not in its signature. Previously the `TypedFunc::call`
method would set the `may_enter` flag on the way out, but now that
operation is deferred until a new `TypedFunc::post_return` method is
called. This means that once a method on an instance is invoked then
nothing else can be done on the instance until the `post_return` method
is called. Note that the method must be called irrespective of whether
the `post-return` canonical ABI option was specified or not. Internally
wasm will be invoked if necessary.
This is a pretty wonky and unergonomic API to work with. For now I
couldn't think of a better alternative that improved on the ergonomics.
In the theory that the raw Wasmtime bindings for a component may not be
used all that heavily (instead `wit-bindgen` would largely be used) I'm
hoping that this isn't too much of an issue in the future.
cc #4185
* Update comment on stack overflow checking
This commit moves the top-level comment in `crates/cranelift/src/lib.rs`
into the location where the global value for the stack limit is
generated. Stack overflow checking is pretty localized nowadays so
there's not much need to have it at the top of the crate and most of the
words there were just adapted to this new location.
Closes#4286
* Review comments
This commit refactored `Config` to use a seperate `CompilerConfig` field instead
of operating on `CompilerBuilder` directly to make all its methods idempotent.
Fixes#4189
This commit updates the wasm-tools family of crates, notably pulling in
the refactorings and updates from bytecodealliance/wasm-tools#621 for
the latest iteration of the component model. This commit additionally
updates all support for the component model for these changes, notably:
* Many bits and pieces of type information was refactored. Many
`FooTypeIndex` namings are now `TypeFooIndex`. Additionally there is
now `TypeIndex` as well as `ComponentTypeIndex` for the two type index
spaces in a component.
* A number of new sections are now processed to handle the core and
component variants.
* Internal maps were split such as the `funcs` map into
`component_funcs` and `funcs` (same for `instances`).
* Canonical options are now processed individually instead of one bulk
`into` definition.
Overall this was not a major update to the internals of handling the
component model in Wasmtime. Instead this was mostly a surface-level
refactoring to make sure that everything lines up with the new binary
format for components.
* All text syntax used in tests was updated to the new syntax.
Now the fiber implementation on AArch64 authenticates function
return addresses and includes the relevant BTI instructions, except
on macOS.
Also, change the locations of the saved FP and LR registers on the
fiber stack to make them compliant with the Procedure Call Standard
for the Arm 64-bit Architecture.
Copyright (c) 2022, Arm Limited.
* Add shared memories
This change adds the ability to use shared memories in Wasmtime when the
[threads proposal] is enabled. Shared memories are annotated as `shared`
in the WebAssembly syntax, e.g., `(memory 1 1 shared)`, and are
protected from concurrent access during `memory.size` and `memory.grow`.
[threads proposal]: https://github.com/WebAssembly/threads/blob/master/proposals/threads/Overview.md
In order to implement this in Wasmtime, there are two main cases to
cover:
- a program may simply create a shared memory and possibly export it;
this means that Wasmtime itself must be able to create shared
memories
- a user may create a shared memory externally and pass it in as an
import during instantiation; this is the case when the program
contains code like `(import "env" "memory" (memory 1 1
shared))`--this case is handled by a new Wasmtime API
type--`SharedMemory`
Because of the first case, this change allows any of the current
memory-creation mechanisms to work as-is. Wasmtime can still create
either static or dynamic memories in either on-demand or pooling modes,
and any of these memories can be considered shared. When shared, the
`Memory` runtime container will lock appropriately during `memory.size`
and `memory.grow` operations; since all memories use this container, it
is an ideal place for implementing the locking once and once only.
The second case is covered by the new `SharedMemory` structure. It uses
the same `Mmap` allocation under the hood as non-shared memories, but
allows the user to perform the allocation externally to Wasmtime and
share the memory across threads (via an `Arc`). The pointer address to
the actual memory is carefully wired through and owned by the
`SharedMemory` structure itself. This means that there are differing
views of where to access the pointer (i.e., `VMMemoryDefinition`): for
owned memories (the default), the `VMMemoryDefinition` is stored
directly by the `VMContext`; in the `SharedMemory` case, however, this
`VMContext` must point to this separate structure.
To ensure that the `VMContext` can always point to the correct
`VMMemoryDefinition`, this change alters the `VMContext` structure.
Since a `SharedMemory` owns its own `VMMemoryDefinition`, the
`defined_memories` table in the `VMContext` becomes a sequence of
pointers--in the shared memory case, they point to the
`VMMemoryDefinition` owned by the `SharedMemory` and in the owned memory
case (i.e., not shared) they point to `VMMemoryDefinition`s stored in a
new table, `owned_memories`.
This change adds an additional indirection (through the `*mut
VMMemoryDefinition` pointer) that could add overhead. Using an imported
memory as a proxy, we measured a 1-3% overhead of this approach on the
`pulldown-cmark` benchmark. To avoid this, Cranelift-generated code will
special-case the owned memory access (i.e., load a pointer directly to
the `owned_memories` entry) for `memory.size` so that only
shared memories (and imported memories, as before) incur the indirection
cost.
* review: remove thread feature check
* review: swap wasmtime-types dependency for existing wasmtime-environ use
* review: remove unused VMMemoryUnion
* review: reword cross-engine error message
* review: improve tests
* review: refactor to separate prevent Memory <-> SharedMemory conversion
* review: into_shared_memory -> as_shared_memory
* review: remove commented out code
* review: limit shared min/max to 32 bits
* review: skip imported memories
* review: imported memories are not owned
* review: remove TODO
* review: document unsafe send + sync
* review: add limiter assertion
* review: remove TODO
* review: improve tests
* review: fix doc test
* fix: fixes based on discussion with Alex
This changes several key parts:
- adds memory indexes to imports and exports
- makes `VMMemoryDefinition::current_length` an atomic usize
* review: add `Extern::SharedMemory`
* review: remove TODO
* review: atomically load from VMMemoryDescription in JIT-generated code
* review: add test probing the last available memory slot across threads
* fix: move assertion to new location due to rebase
* fix: doc link
* fix: add TODOs to c-api
* fix: broken doc link
* fix: modify pooling allocator messages in tests
* review: make owned_memory_index panic instead of returning an option
* review: clarify calculation of num_owned_memories
* review: move 'use' to top of file
* review: change '*const [u8]' to '*mut [u8]'
* review: remove TODO
* review: avoid hard-coding memory index
* review: remove 'preallocation' parameter from 'Memory::_new'
* fix: component model memory length
* review: check that shared memory plans are static
* review: ignore growth limits for shared memory
* review: improve atomic store comment
* review: add FIXME for memory growth failure
* review: add comment about absence of bounds-checked 'memory.size'
* review: make 'current_length()' doc comment more precise
* review: more comments related to memory.size non-determinism
* review: make 'vmmemory' unreachable for shared memory
* review: move code around
* review: thread plan through to 'wrap()'
* review: disallow shared memory allocation with the pooling allocator
* Add trampoline compilation support for lowered imports
This commit adds support to the component model implementation for
compiling trampolines suitable for calling host imports. Currently this
is purely just the compilation side of things, modifying the
wasmtime-cranelift crate and additionally filling out a new
`VMComponentOffsets` type (similar to `VMOffsets`). The actual creation
of a `VMComponentContext` is still not performed and will be a
subsequent PR.
Internally though some tests are actually possible with this where we at
least assert that compilation of a component and creation of everything
in-memory doesn't panic or trip any assertions, so some tests are added
here for that as well.
* Fix some test errors
* Split `wasm_to_host_trampoline` into pieces
In the upcoming component model supoprt for imports my plan is to reuse
some of these pieces but not the entirety of the current
`wasm_to_host_trampoline`. In an effort to make that diff smaller this
commit splits up the function preemptively into pieces to get reused
later.
* Delete unused `for_each_libcall` macros
Came across this when working in the object support for cranelift.
* Refactor some object creation details
This commit refactors some of the internals around creating an object
file in the wasmtime-cranelift integration. The old `ObjectBuilder` is
now named `ModuleTextBuilder` and is only used to create the text
section rather than other sections too. This helps maintain the
invariant that the unwind information section is placed directly after
the text section without having an odd API for doing this.
Additionally the unwind information creation is moved externally from
the `ModuleTextBuilder` to a standalone structure. This separate
structure is currently in use in the component model work I'm doing
although I may change that to using the `ModuleTextBuilder` instead. In
any case it seemed nice to encapsulate all of the unwinding information
into one standalone structure.
Finally, the insertion of native debug information has been refactored
to happen in a new `append_dwarf` method to keep all the dwarf-related
stuff together in one place as much as possible.
* Fix a doctest
* Fix a typo
* Change wasm-to-host trampolines to take the values_vec size
This commit changes the ABI of wasm-to-host trampolines, which are
only used right now for functions created with `Func::new`, to pass
along the size of the `values_vec` argument. Previously the trampoline
simply received `*mut ValRaw` and assumed that it was the appropriate
size. By receiving a size as well we can thread through `&mut [ValRaw]`
internally instead of `*mut ValRaw`.
The original motivation for this is that I'm planning to leverage these
trampolines for the component model for host-defined functions. Out of
an abundance of caution of making sure that everything lines up I wanted
to be able to write down asserts about the size received at runtime
compared to the size expected. This overall led me to the desire to
thread this size parameter through on the assumption that it would not
impact performance all that much.
I ran two benchmarks locally from the `call.rs` benchmark and got:
* `sync/no-hook/wasm-to-host - nop - unchecked` - no change
* `sync/no-hook/wasm-to-host - nop-params-and-results - unchecked` - 5%
slower
This is what I roughly expected in that if nothing actually reads the
new parameter (e.g. no arguments) then threading through the parameter
is effectively otherwise free. Otherwise though accesses to the `ValRaw`
storage is now bounds-checked internally in Wasmtime instead of assuming
it's valid, leading to the 5% slowdown (~9.6ns to ~10.3ns). If this
becomes a peformance bottleneck for a particular use case then we should
be fine to remove the bounds checking here or otherwise only bounds
check in debug mode, otherwise I plan on leaving this as-is.
Of particular note this also changes the C API for `*_unchecked`
functions where the C callback now receives the size of the array as
well.
* Add docs
* Remove unused srcloc in MachReloc
* Remove unused srcloc in MachTrap
* Use `into_iter` on array in bench code to suppress a warning
* Remove unused srcloc in MachCallSite
* Initial skeleton of some component model processing
This commit is the first of what will likely be many to implement the
component model proposal in Wasmtime. This will be structured as a
series of incremental commits, most of which haven't been written yet.
My hope is to make this incremental and over time to make this easier to
review and easier to test each step in isolation.
Here much of the skeleton of how components are going to work in
Wasmtime is sketched out. This is not a complete implementation of the
component model so it's not all that useful yet, but some things you can
do are:
* Process the type section into a representation amenable for working
with in Wasmtime.
* Process the module section and register core wasm modules.
* Process the instance section for core wasm modules.
* Process core wasm module imports.
* Process core wasm instance aliasing.
* Ability to compile a component with core wasm embedded.
* Ability to instantiate a component with no imports.
* Ability to get functions from this component.
This is already starting to diverge from the previous module linking
representation where a `Component` will try to avoid unnecessary
metadata about the component and instead internally only have the bare
minimum necessary to instantiate the module. My hope is we can avoid
constructing most of the index spaces during instantiation only for it
to all ge thrown away. Additionally I'm predicting that we'll need to
see through processing where possible to know how to generate adapters
and where they are fused.
At this time you can't actually call a component's functions, and that's
the next PR that I would like to make.
* Add tests for the component model support
This commit uses the recently updated wasm-tools crates to add tests for
the component model added in the previous commit. This involved updating
the `wasmtime-wast` crate for component-model changes. Currently the
component support there is quite primitive, but enough to at least
instantiate components and verify the internals of Wasmtime are all
working correctly. Additionally some simple tests for the embedding API
have also been added.
This PR adds a basic *alias analysis*, and optimizations that use it.
This is a "mid-end optimization": it operates on CLIF, the
machine-independent IR, before lowering occurs.
The alias analysis (or maybe more properly, a sort of memory-value
analysis) determines when it can prove a particular memory
location is equal to a given SSA value, and when it can, it replaces any
loads of that location.
This subsumes two common optimizations:
* Redundant load elimination: when the same memory address is loaded two
times, and it can be proven that no intervening operations will write
to that memory, then the second load is *redundant* and its result
must be the same as the first. We can use the first load's result and
remove the second load.
* Store-to-load forwarding: when a load can be proven to access exactly
the memory written by a preceding store, we can replace the load's
result with the store's data operand, and remove the load.
Both of these optimizations rely on a "last store" analysis that is a
sort of coloring mechanism, split across disjoint categories of abstract
state. The basic idea is that every memory-accessing operation is put
into one of N disjoint categories; it is disallowed for memory to ever
be accessed by an op in one category and later accessed by an op in
another category. (The frontend must ensure this.)
Then, given this, we scan the code and determine, for each
memory-accessing op, when a single prior instruction is a store to the
same category. This "colors" the instruction: it is, in a sense, a
static name for that version of memory.
This analysis provides an important invariant: if two operations access
memory with the same last-store, then *no other store can alias* in the
time between that last store and these operations. This must-not-alias
property, together with a check that the accessed address is *exactly
the same* (same SSA value and offset), and other attributes of the
access (type, extension mode) are the same, let us prove that the
results are the same.
Given last-store info, we scan the instructions and build a table from
"memory location" key (last store, address, offset, type, extension) to
known SSA value stored in that location. A store inserts a new mapping.
A load may also insert a new mapping, if we didn't already have one.
Then when a load occurs and an entry already exists for its "location",
we can reuse the value. This will be either RLE or St-to-Ld depending on
where the value came from.
Note that this *does* work across basic blocks: the last-store analysis
is a full iterative dataflow pass, and we are careful to check dominance
of a previously-defined value before aliasing to it at a potentially
redundant load. So we will do the right thing if we only have a
"partially redundant" load (loaded already but only in one predecessor
block), but we will also correctly reuse a value if there is a store or
load above a loop and a redundant load of that value within the loop, as
long as no potentially-aliasing stores happen within the loop.
* Update the wasm-tools family of crates
This commit updates these crates as used by Wasmtime for the recently
published versions to pull in changes necessary to support the component
model. I've split this out from #4005 to make it clear what's impacted
here and #4005 can simply rebase on top of this to pick up the necessary
changes.
* More test fixes
* Run a `cargo update` over our dependencies
This'll notably fix a `cargo audit` error where we have a pinned version
of the `regex` crate which has a CVE assigned to it.
* Update to `object` and `hashbrown` crates
Prune some duplicate versions showing up from the previous `cargo update`
* Store the `ValRaw` type in little-endian format
This commit changes the internal representation of the `ValRaw` type to
an unconditionally little-endian format instead of its current
native-endian format. The documentation and various accessors here have
been updated as well as the associated trampolines that read `ValRaw`
to always work with little-endian values, converting to the host
endianness as necessary.
The motivation for this change originally comes from the implementation
of the component model that I'm working on. One aspect of the component
model's canonical ABI is how variants are passed to functions as
immediate arguments. For example for a component model function:
```
foo: function(x: expected<i32, f64>)
```
This translates to a core wasm function:
```wasm
(module
(func (export "foo") (param i32 i64)
;; ...
)
)
```
The first `i32` parameter to the core wasm function is the discriminant
of whether the result is an "ok" or an "err". The second `i64`, however,
is the "join" operation on the `i32` and `f64` payloads. Essentially
these two types are unioned into one type to get passed into the function.
Currently in the implementation of the component model my plan is to
construct a `*mut [ValRaw]` to pass through to WebAssembly, always
invoking component exports through host trampolines. This means that the
implementation for `Result<T, E>` needs to do the correct "join"
operation here when encoding a particular case into the corresponding
`ValRaw`.
I personally found this particularly tricky to do structurally. The
solution that I settled on with fitzgen was that if `ValRaw` was always
stored in a little endian format then we could employ a trick where when
encoding a variant we first set all the `ValRaw` slots to zero, then the
associated case we have is encoding. Afterwards the `ValRaw` values are
already encoded into the correct format as if they'd been "join"ed.
For example if we were to encode `Ok(1i32)` then this would produce
`ValRaw { i32: 1 }`, which memory-wise is equivalent to `ValRaw { i64: 1 }`
if the other bytes in the `ValRaw` are guaranteed to be zero. Similarly
storing `ValRaw { f64 }` is equivalent to the storage required for
`ValRaw { i64 }` here in the join operation.
Note, though, that this equivalence relies on everything being
little-endian. Otherwise the in-memory representations of `ValRaw { i32: 1 }`
and `ValRaw { i64: 1 }` are different.
That motivation is what leads to this change. It's expected that this is
a low-to-zero cost change in the sense that little-endian platforms will
see no change and big-endian platforms are already required to
efficiently byte-swap loads/stores as WebAssembly requires that.
Additionally the `ValRaw` type is an esoteric niche use case primarily
used for accelerating the C API right now, so it's expected that not
many users will have to update for this change.
* Track down some more endianness conversions
* Update wasm-tools crates
This commit updates the wasm-tools family of crates as used in Wasmtime.
Notably this brings in the update which removes module linking support
as well as a number of internal refactorings around names and such
within wasmparser itself. This updates all of the wasm translation
support which binds to wasmparser as appropriate.
Other crates all had API-compatible changes for at least what Wasmtime
used so no further changes were necessary beyond updating version
requirements.
* Update a test expectation
* Bump to 0.36.0
* Add a two-week delay to Wasmtime's release process
This commit is a proposal to update Wasmtime's release process with a
two-week delay from branching a release until it's actually officially
released. We've had two issues lately that came up which led to this proposal:
* In #3915 it was realized that changes just before the 0.35.0 release
weren't enough for an embedding use case, but the PR didn't meet the
expectations for a full patch release.
* At Fastly we were about to start rolling out a new version of Wasmtime
when over the weekend the fuzz bug #3951 was found. This led to the
desire internally to have a "must have been fuzzed for this long"
period of time for Wasmtime changes which we felt were better
reflected in the release process itself rather than something about
Fastly's own integration with Wasmtime.
This commit updates the automation for releases to unconditionally
create a `release-X.Y.Z` branch on the 5th of every month. The actual
release from this branch is then performed on the 20th of every month,
roughly two weeks later. This should provide a period of time to ensure
that all changes in a release are fuzzed for at least two weeks and
avoid any further surprises. This should also help with any last-minute
changes made just before a release if they need tweaking since
backporting to a not-yet-released branch is much easier.
Overall there are some new properties about Wasmtime with this proposal
as well:
* The `main` branch will always have a section in `RELEASES.md` which is
listed as "Unreleased" for us to fill out.
* The `main` branch will always be a version ahead of the latest
release. For example it will be bump pre-emptively as part of the
release process on the 5th where if `release-2.0.0` was created then
the `main` branch will have 3.0.0 Wasmtime.
* Dates for major versions are automatically updated in the
`RELEASES.md` notes.
The associated documentation for our release process is updated and the
various scripts should all be updated now as well with this commit.
* Add notes on a security patch
* Clarify security fixes shouldn't be previewed early on CI
* Remove duplicate `TypeTables` type
This was once needed historically but it is no longer needed.
* Make the internals of `TypeTables` private
Instead of reaching internally for the `wasm_signatures` map an `Index`
implementation now exists to indirect accesses through the type of the
index being accessed. For the component model this table of types will
grow a number of other tables and this'll assist in consuming sites not
having to worry so much about which map they're reaching into.
* Support disabling backtraces at compile time
This commit adds support to Wasmtime to disable, at compile time, the
gathering of backtraces on traps. The `wasmtime` crate now sports a
`wasm-backtrace` feature which, when disabled, will mean that backtraces
are never collected at compile time nor are unwinding tables inserted
into compiled objects.
The motivation for this commit stems from the fact that generating a
backtrace is quite a slow operation. Currently backtrace generation is
done with libunwind and `_Unwind_Backtrace` typically found in glibc or
other system libraries. When thousands of modules are loaded into the
same process though this means that the initial backtrace can take
nearly half a second and all subsequent backtraces can take upwards of
hundreds of milliseconds. Relative to all other operations in Wasmtime
this is extremely expensive at this time. In the future we'd like to
implement a more performant backtrace scheme but such an implementation
would require coordination with Cranelift and is a big chunk of work
that may take some time, so in the meantime if embedders don't need a
backtrace they can still use this option to disable backtraces at
compile time and avoid the performance pitfalls of collecting
backtraces.
In general I tried to originally make this a runtime configuration
option but ended up opting for a compile-time option because `Trap::new`
otherwise has no arguments and always captures a backtrace. By making
this a compile-time option it was possible to configure, statically, the
behavior of `Trap::new`. Additionally I also tried to minimize the
amount of `#[cfg]` necessary by largely only having it at the producer
and consumer sites.
Also a noteworthy restriction of this implementation is that if
backtrace support is disabled at compile time then reference types
support will be unconditionally disabled at runtime. With backtrace
support disabled there's no way to trace the stack of wasm frames which
means that GC can't happen given our current implementation.
* Always enable backtraces for the C API
* Delete historical interruptable support in Wasmtime
This commit removes the `Config::interruptable` configuration along with
the `InterruptHandle` type from the `wasmtime` crate. The original
support for adding interruption to WebAssembly was added pretty early on
in the history of Wasmtime when there was no other method to prevent an
infinite loop from the host. Nowadays, however, there are alternative
methods for interruption such as fuel or epoch-based interruption.
One of the major downsides of `Config::interruptable` is that even when
it's not enabled it forces an atomic swap to happen when entering
WebAssembly code. This technically could be a non-atomic swap if the
configuration option isn't enabled but that produces even more branch-y
code on entry into WebAssembly which is already something we try to
optimize. Calling into WebAssembly is on the order of a dozens of
nanoseconds at this time and an atomic swap, even uncontended, can add
up to 5ns on some platforms.
The main goal of this PR is to remove this atomic swap on entry into
WebAssembly. This is done by removing the `Config::interruptable` field
entirely, moving all existing consumers to epochs instead which are
suitable for the same purposes. This means that the stack overflow check
is no longer entangled with the interruption check and perhaps one day
we could continue to optimize that further as well.
Some consequences of this change are:
* Epochs are now the only method of remote-thread interruption.
* There are no more Wasmtime traps that produces the `Interrupted` trap
code, although we may wish to move future traps to this so I left it
in place.
* The C API support for interrupt handles was also removed and bindings
for epoch methods were added.
* Function-entry checks for interruption are a tiny bit less efficient
since one check is performed for the stack limit and a second is
performed for the epoch as opposed to the `Config::interruptable`
style of bundling the stack limit and the interrupt check in one. It's
expected though that this is likely to not really be measurable.
* The old `VMInterrupts` structure is renamed to `VMRuntimeLimits`.
Previously (as in an hour ago) #3905 landed a new ability for fuzzing to
arbitrarily insert padding between functions. Running some fuzzers
locally though this instantly hit a lot of problems on AArch64 because
the arbitrary padding isn't aligned to 4 bytes like all other functions
are. To fix this issue appending functions now correctly aligns the
output as appropriate for the platform. The alignment argument for
appending was switched to `None` where `None` means "use the platform
default" and otherwise and explicit alignment can be specified for
inserting other data (like arbitrary padding or Windows unwind tables).
* fuzz: Fuzz padding between compiled functions
This commit hooks up the custom
`wasmtime_linkopt_padding_between_functions` configuration option to the
cranelift compiler into the fuzz configuration, enabling us to ensure
that randomly inserting a moderate amount of padding between functions
shouldn't tamper with any results.
* fuzz: Fuzz the `Config::generate_address_map` option
This commit adds fuzz configuration where `generate_address_map` is
either enabled or disabled, unlike how it's always enabled for fuzzing
today.
* Remove unnecessary handling of relocations
This commit removes a number of bits and pieces all related to handling
relocations in JIT code generated by Wasmtime. None of this is necessary
nowadays that the "old backend" has been removed (quite some time ago)
and relocations are no longer expected to be in the JIT code at all.
Additionally with the minimum x86_64 features required to run wasm code
it should be expected that no libcalls are required either for
Wasmtime-based JIT code.
* Shrink the size of the anyfunc table in `VMContext`
This commit shrinks the size of the `VMCallerCheckedAnyfunc` table
allocated into a `VMContext` to be the size of the number of "escaped"
functions in a module rather than the number of functions in a module.
Escaped functions include exports, table elements, etc, and are
typically an order of magnitude smaller than the number of functions in
general. This should greatly shrink the `VMContext` for some modules
which while we aren't necessarily having any problems with that today
shouldn't cause any problems in the future.
The original motivation for this was that this came up during the recent
lazy-table-initialization work and while it no longer has a direct
performance benefit since tables aren't initialized at all on
instantiation it should still improve long-running instances
theoretically with smaller `VMContext` allocations as well as better
locality between anyfuncs.
* Fix some tests
* Remove redundant hash set
* Use a helper for pushing function type information
* Use a more descriptive `is_escaping` method
* Clarify a comment
* Fix condition
* 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
* Fix typo
* Move vmoffset field size and field name together
The previous code was quite confusing about what applied to which field.
The new code also makes it easier to move fields around and insert and
delete fields.
* Move builtin_functions before all variable sized fields
This allows the offset to be calculated at compile time
* Add cadd and cmul convenience functions
* Remove comment
* Change fields! syntax as per review
* Add implicit u32::from to fields!
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.
* Shrink the size of `FuncData`
Before this commit on a 64-bit system the `FuncData` type had a size of
88 bytes and after this commit it has a size of 32 bytes. A `FuncData`
is required for all host functions in a store, including those inserted
from a `Linker` into a store used during linking. This means that
instantiation ends up creating a nontrivial number of these types and
pushing them into the store. Looking at some profiles there were some
surprisingly expensive movements of `FuncData` from the stack to a
vector for moves-by-value generated by Rust. Shrinking this type enables
more efficient code to be generated and additionally means less storage
is needed in a store's function array.
For instantiating the spidermonkey and rustpython modules this improves
instantiation by 10% since they each import a fair number of host
functions and the speedup here is relative to the number of items
imported.
* Use `ptr::copy_nonoverlapping` during initialization
Prevoiusly `ptr::copy` was used for copying imports into place which
translates to `memmove`, but `ptr::copy_nonoverlapping` can be used here
since it's statically known these areas don't overlap. While this
doesn't end up having a performance difference it's something I kept
noticing while looking at the disassembly of `initialize_vmcontext` so I
figured I'd go ahead and implement.
* Indirect shared signature ids in the VMContext
This commit is a small improvement for the instantiation time of modules
by avoiding copying a list of `VMSharedSignatureIndex` entries into each
`VMContext`, instead building one inside of a module and sharing that
amongst all instances. This involves less lookups at instantiation time
and less movement of data during instantiation. The downside is that
type-checks on `call_indirect` now involve an additionally load, but I'm
assuming that these are somewhat pessimized enough as-is that the
runtime impact won't be much there.
For instantiation performance this is a 5-10% win with
rustpyhon/spidermonky instantiation. This should also reduce the size of
each `VMContext` for an instantiation since signatures are no longer
stored inline but shared amongst all instances with one module.
Note that one subtle change here is that the array of
`VMSharedSignatureIndex` was previously indexed by `TypeIndex`, and now
it's indexed by `SignaturedIndex` which is a deduplicated form of
`TypeIndex`. This is done because we already had a list of those lying
around in `Module`, so it was easier to reuse that than to build a
separate array and store it somewhere.
* Reserve space in `Store<T>` with `InstancePre`
This commit updates the instantiation process to reserve space in a
`Store<T>` for the functions that an `InstancePre<T>`, as part of
instantiation, will insert into it. Using an `InstancePre<T>` to
instantiate allows pre-computing the number of host functions that will
be inserted into a store, and by pre-reserving space we can avoid costly
reallocations during instantiation by ensuring the function vector has
enough space to fit everything during the instantiation process.
Overall this makes instantiation of rustpython/spidermonkey about 8%
faster locally.
* Fix tests
* Use checked arithmetic
* Skip memfd creation with precompiled modules
This commit updates the memfd support internally to not actually use a
memfd if a compiled module originally came from disk via the
`wasmtime::Module::deserialize_file` API. In this situation we already
have a file descriptor open and there's no need to copy a module's heap
image to a new file descriptor.
To facilitate a new source of `mmap` the currently-memfd-specific-logic
of creating a heap image is generalized to a new form of
`MemoryInitialization` which is attempted for all modules at
module-compile-time. This means that the serialized artifact to disk
will have the memory image in its entirety waiting for us. Furthermore
the memory image is ensured to be padded and aligned carefully to the
target system's page size, notably meaning that the data section in the
final object file is page-aligned and the size of the data section is
also page aligned.
This means that when a precompiled module is mapped from disk we can
reuse the underlying `File` to mmap all initial memory images. This
means that the offset-within-the-memory-mapped-file can differ for
memfd-vs-not, but that's just another piece of state to track in the
memfd implementation.
In the limit this waters down the term "memfd" for this technique of
quickly initializing memory because we no longer use memfd
unconditionally (only when the backing file isn't available).
This does however open up an avenue in the future to porting this
support to other OSes because while `memfd_create` is Linux-specific
both macOS and Windows support mapping a file with copy-on-write. This
porting isn't done in this PR and is left for a future refactoring.
Closes#3758
* Enable "memfd" support on all unix systems
Cordon off the Linux-specific bits and enable the memfd support to
compile and run on platforms like macOS which have a Linux-like `mmap`.
This only works if a module is mapped from a precompiled module file on
disk, but that's better than not supporting it at all!
* Fix linux compile
* Use `Arc<File>` instead of `MmapVecFileBacking`
* Use a named struct instead of mysterious tuples
* Comment about unsafety in `Module::deserialize_file`
* Fix tests
* Fix uffd compile
* Always align data segments
No need to have conditional alignment since their sizes are all aligned
anyway
* Update comment in build.rs
* Use rustix, not `region`
* Fix some confusing logic/names around memory indexes
These functions all work with memory indexes, not specifically defined
memory indexes.
* Move function names out of `Module`
This commit moves function names in a module out of the
`wasmtime_environ::Module` type and into separate sections stored in the
final compiled artifact. Spurred on by #3787 to look at module load
times I noticed that a huge amount of time was spent in deserializing
this map. The `spidermonkey.wasm` file, for example, has a 3MB name
section which is a lot of unnecessary data to deserialize at module load
time.
The names of functions are now split out into their own dedicated
section of the compiled artifact and metadata about them is stored in a
more compact format at runtime by avoiding a `BTreeMap` and instead
using a sorted array. Overall this improves deserialize times by up to
80% for modules with large name sections since the name section is no
longer deserialized at load time and it's lazily paged in as names are
actually referenced.
* Fix a typo
* Fix compiled module determinism
Need to not only sort afterwards but also first to ensure the data of
the name section is consistent.
During instance initialization, we build two sorts of arrays eagerly:
- We create an "anyfunc" (a `VMCallerCheckedAnyfunc`) for every function
in an instance.
- We initialize every element of a funcref table with an initializer to
a pointer to one of these anyfuncs.
Most instances will not touch (via call_indirect or table.get) all
funcref table elements. And most anyfuncs will never be referenced,
because most functions are never placed in tables or used with
`ref.func`. Thus, both of these initialization tasks are quite wasteful.
Profiling shows that a significant fraction of the remaining
instance-initialization time after our other recent optimizations is
going into these two tasks.
This PR implements two basic ideas:
- The anyfunc array can be lazily initialized as long as we retain the
information needed to do so. For now, in this PR, we just recreate the
anyfunc whenever a pointer is taken to it, because doing so is fast
enough; in the future we could keep some state to know whether the
anyfunc has been written yet and skip this work if redundant.
This technique allows us to leave the anyfunc array as uninitialized
memory, which can be a significant savings. Filling it with
initialized anyfuncs is very expensive, but even zeroing it is
expensive: e.g. in a large module, it can be >500KB.
- A funcref table can be lazily initialized as long as we retain a link
to its corresponding instance and function index for each element. A
zero in a table element means "uninitialized", and a slowpath does the
initialization.
Funcref tables are a little tricky because funcrefs can be null. We need
to distinguish "element was initially non-null, but user stored explicit
null later" from "element never touched" (ie the lazy init should not
blow away an explicitly stored null). We solve this by stealing the LSB
from every funcref (anyfunc pointer): when the LSB is set, the funcref
is initialized and we don't hit the lazy-init slowpath. We insert the
bit on storing to the table and mask it off after loading.
We do have to set up a precomputed array of `FuncIndex`s for the table
in order for this to work. We do this as part of the module compilation.
This PR also refactors the way that the runtime crate gains access to
information computed during module compilation.
Performance effect measured with in-tree benches/instantiation.rs, using
SpiderMonkey built for WASI, and with memfd enabled:
```
BEFORE:
sequential/default/spidermonkey.wasm
time: [68.569 us 68.696 us 68.856 us]
sequential/pooling/spidermonkey.wasm
time: [69.406 us 69.435 us 69.465 us]
parallel/default/spidermonkey.wasm: with 1 background thread
time: [69.444 us 69.470 us 69.497 us]
parallel/default/spidermonkey.wasm: with 16 background threads
time: [183.72 us 184.31 us 184.89 us]
parallel/pooling/spidermonkey.wasm: with 1 background thread
time: [69.018 us 69.070 us 69.136 us]
parallel/pooling/spidermonkey.wasm: with 16 background threads
time: [326.81 us 337.32 us 347.01 us]
WITH THIS PR:
sequential/default/spidermonkey.wasm
time: [6.7821 us 6.8096 us 6.8397 us]
change: [-90.245% -90.193% -90.142%] (p = 0.00 < 0.05)
Performance has improved.
sequential/pooling/spidermonkey.wasm
time: [3.0410 us 3.0558 us 3.0724 us]
change: [-95.566% -95.552% -95.537%] (p = 0.00 < 0.05)
Performance has improved.
parallel/default/spidermonkey.wasm: with 1 background thread
time: [7.2643 us 7.2689 us 7.2735 us]
change: [-89.541% -89.533% -89.525%] (p = 0.00 < 0.05)
Performance has improved.
parallel/default/spidermonkey.wasm: with 16 background threads
time: [147.36 us 148.99 us 150.74 us]
change: [-18.997% -18.081% -17.285%] (p = 0.00 < 0.05)
Performance has improved.
parallel/pooling/spidermonkey.wasm: with 1 background thread
time: [3.1009 us 3.1021 us 3.1033 us]
change: [-95.517% -95.511% -95.506%] (p = 0.00 < 0.05)
Performance has improved.
parallel/pooling/spidermonkey.wasm: with 16 background threads
time: [49.449 us 50.475 us 51.540 us]
change: [-85.423% -84.964% -84.465%] (p = 0.00 < 0.05)
Performance has improved.
```
So an improvement of something like 80-95% for a very large module (7420
functions in its one funcref table, 31928 functions total).
* Don't copy `VMBuiltinFunctionsArray` into each `VMContext`
This is another PR along the lines of "let's squeeze all possible
performance we can out of instantiation". Before this PR we would copy,
by value, the contents of `VMBuiltinFunctionsArray` into each
`VMContext` allocated. This array of function pointers is modestly-sized
but growing over time as we add various intrinsics. Additionally it's
the exact same for all `VMContext` allocations.
This PR attempts to speed up instantiation slightly by instead storing
an indirection to the function array. This means that calling a builtin
intrinsic is a tad bit slower since it requires two loads instead of one
(one to get the base pointer, another to get the actual address).
Otherwise though `VMContext` initialization is now simply setting one
pointer instead of doing a `memcpy` from one location to another.
With some macro-magic this commit also replaces the previous
implementation with one that's more `const`-friendly which also gets us
compile-time type-checks of libcalls as well as compile-time
verification that all libcalls are defined.
Overall, as with #3739, the win is very modest here. Locally I measured
a speedup from 1.9us to 1.7us taken to instantiate an empty module with
one function. While small at these scales it's still a 10% improvement!
* Review comments
This PR introduces a new way of performing cooperative timeslicing that
is intended to replace the "fuel" mechanism. The tradeoff is that this
mechanism interrupts with less precision: not at deterministic points
where fuel runs out, but rather when the Engine enters a new epoch. The
generated code instrumentation is substantially faster, however, because
it does not need to do as much work as when tracking fuel; it only loads
the global "epoch counter" and does a compare-and-branch at backedges
and function prologues.
This change has been measured as ~twice as fast as fuel-based
timeslicing for some workloads, especially control-flow-intensive
workloads such as the SpiderMonkey JS interpreter on Wasm/WASI.
The intended interface is that the embedder of the `Engine` performs an
`engine.increment_epoch()` call periodically, e.g. once per millisecond.
An async invocation of a Wasm guest on a `Store` can specify a number of
epoch-ticks that are allowed before an async yield back to the
executor's event loop. (The initial amount and automatic "refills" are
configured on the `Store`, just as for fuel.) This call does only
signal-safe work (it increments an `AtomicU64`) so could be invoked from
a periodic signal, or from a thread that wakes up once per period.
