A SIMD register can "block" more than one FP register. In that case, no
virtual register will be assigned for one of the FP registers. This is
fine, we just need to detect and handle that case correctly.
R=thibaudm@chromium.org
CC=leszeks@chromium.org
Bug: chromium:1271538, v8:12330
Change-Id: I7ec19229445c5ace0782f63945acb89322816540
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3293082
Reviewed-by: Thibaud Michaud <thibaudm@chromium.org>
Reviewed-by: Maya Lekova <mslekova@chromium.org>
Commit-Queue: Clemens Backes <clemensb@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78400}
This bitset is used to quickly find the set of used / free registers,
and it should always be consistent with the information in the
{RegisterState}.
This CL adds a little validation after the register allocation of each
instruction.
This should help fuzzers to catch inconsistencies earlier.
R=thibaudm@chromium.org
Bug: v8:12330
Change-Id: Ia8da9708e982726d72d156f5bca04213a3f03b7f
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3341520
Reviewed-by: Thibaud Michaud <thibaudm@chromium.org>
Reviewed-by: Maya Lekova <mslekova@chromium.org>
Commit-Queue: Clemens Backes <clemensb@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78398}
This reverts commit 00a757fabd.
Reason for revert: Caused perf regressions, https://crbug.com/1280236
Original change's description:
> Shorten generated code for binary-search switches
>
> On some branches of the search tree for a binary-search switch, the
> input value is sufficiently constrained that we could unconditionally
> jump to the last possible case rather than checking for value equality.
> This shortens some builtins by a few instructions and might speed things
> up, though I expect the effect to be small.
>
> Change-Id: I2313f26976e6d3c182f03bd927b338c8175b3af3
> Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3335437
> Reviewed-by: Nico Hartmann <nicohartmann@chromium.org>
> Commit-Queue: Seth Brenith <seth.brenith@microsoft.com>
> Cr-Commit-Position: refs/heads/main@{#78376}
Bug: chromium:1280236
Change-Id: I88d9ff64641b85d48198b7012df2eeb9441913b5
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3343234
Bot-Commit: Rubber Stamper <rubber-stamper@appspot.gserviceaccount.com>
Reviewed-by: Nico Hartmann <nicohartmann@chromium.org>
Commit-Queue: Seth Brenith <seth.brenith@microsoft.com>
Cr-Commit-Position: refs/heads/main@{#78397}
We switch the order of inlining and loop unrolling optimizations. This
gives small improvements to wasm-gc benchmarks.
Changes:
- Change the loop analysis algorithm to accept loops directly connected
to the graph's end. This is required because some nodes in an inlined
function, such as tail calls, might be directly connected to the outer
function's end without an intervening LoopExit node.
- Based on the above, skip emitting loop exits for some Throw nodes in
WasmGraphBuildingInterface.
- Introduce WasmInliningPhase, add it before loop unrolling. Remove
inlining from WasmOptimizationPhase.
- Handle graph terminators in loop unrolling.
- Add loops in the inlined function to the callers loop_infos.
Drive-by:
- Allow more wasm builtins in unrolled loops.
- Reduce inlining parameters to reflect that functions are now slightly
smaller during inlining, as no unrolling has taken place yet.
Bug: v8:12166
Change-Id: Iadd6b2f75170aa153ca1efb47fbb0d185c2b8371
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3329783
Reviewed-by: Jakob Kummerow <jkummerow@chromium.org>
Reviewed-by: Nico Hartmann <nicohartmann@chromium.org>
Commit-Queue: Manos Koukoutos <manoskouk@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78394}
... in order to avoid Code <-> CodeT conversions in builtins.
This CL changes the meaning of RelocInfo::CODE_TARGET which now expects
CodeT objects as a code target.
In order to reduce code churn this CL makes BUILTIN_CODE and friends
return CodeT instead of Code. In the follow-up CLs BUILTIN_CODET and
friends will be removed.
Bug: v8:11880
Change-Id: Ib8f60973e55c60fc62ba84707471da388f8201b4
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3338483
Reviewed-by: Patrick Thier <pthier@chromium.org>
Reviewed-by: Nico Hartmann <nicohartmann@chromium.org>
Reviewed-by: Leszek Swirski <leszeks@chromium.org>
Commit-Queue: Igor Sheludko <ishell@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78393}
This is the first step towards moving away from sending `url` with every
call frame when emitting the `Debugger.paused` event.
Bug: chromium:1270316, chromium:1271078
Change-Id: I2f57f21e15bf908ffb53f5c7b5862d3efa329c86
Doc: https://bit.ly/devtools-debugger-callframe-url
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3344946
Reviewed-by: Yang Guo <yangguo@chromium.org>
Commit-Queue: Benedikt Meurer <bmeurer@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78392}
In the WebAssembly Turbofan pipeline, inlining should come before
unrolling. When we inline a function, we link unhandled throwing calls
in it to the handler of the caller node. If a throwing call is in a
loop, we need to generate loop exits between the call and the handler if
we want to unroll later.
This CL adds dangling IfException/LoopExit nodes following each throwing
call in an inlined function. These nodes are connected as required in
inlining.
Drive-by: Remove CheckForException from tail calls, which are kNoThrow.
Bug: v8:12166
Change-Id: Icb8371a0a27234f07d4880e5b3005fc90a91a4b6
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3322975
Reviewed-by: Jakob Kummerow <jkummerow@chromium.org>
Commit-Queue: Manos Koukoutos <manoskouk@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78391}
Since load elimination is only enabled for wasm-gc, we should use
LoadImmutable over LoadImmutableFromObject when possible. This is
possible for instance fields, which are always populated before the
start of function execution.
Bug: v8:11510, chromium:1279211
Change-Id: Ib11e8d19b91a16f509983378f74bdc4c3c2150ad
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3341522
Reviewed-by: Clemens Backes <clemensb@chromium.org>
Commit-Queue: Manos Koukoutos <manoskouk@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78390}
While there, make sure to exit on failures (e.g. missing tools).
Signed-off-by: Piotr Sikora <piotrsikora@google.com>
Change-Id: Ie84425bbedefc8c37cf12afbf0ad541caa125ac0
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3333634
Reviewed-by: Victor Gomes <victorgomes@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78388}
When compiled with gn argument 'is_debug=false' these tests fail on
Windows due to the fact that they're compiled with '/guard:cf'.
This CL changes the use of FUNCTION_CAST to GeneratedCode::Call which
contains DISABLE_CFI_ICALL attribute. This is analogous to how
assembled functions are called in Assembler tests for other
architectures.
Change-Id: I330e29a508ad1421cb98dea3d9761f05272ab763
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3341511
Auto-Submit: Dmitrii Tsykunov <dtsykunov1@yandex-team.ru>
Reviewed-by: Victor Gomes <victorgomes@chromium.org>
Commit-Queue: Victor Gomes <victorgomes@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78386}
This CL renames a number of things related to the V8 sandbox.
Mainly, what used to be under V8_HEAP_SANDBOX is now under
V8_SANDBOXED_EXTERNAL_POINTERS, while the previous V8 VirtualMemoryCage
is now simply the V8 Sandbox:
V8_VIRTUAL_MEMORY_CAGE => V8_SANDBOX
V8_HEAP_SANDBOX => V8_SANDBOXED_EXTERNAL_POINTERS
V8_CAGED_POINTERS => V8_SANDBOXED_POINTERS
V8VirtualMemoryCage => Sandbox
CagedPointer => SandboxedPointer
fake cage => partially reserved sandbox
src/security => src/sandbox
This naming scheme should simplify things: the sandbox is now the large
region of virtual address space inside which V8 mainly operates and
which should be considered untrusted. Mechanisms like sandboxed pointers
are then used to attempt to prevent escapes from the sandbox (i.e.
corruption of memory outside of it). Furthermore, the new naming scheme
avoids the confusion with the various other "cages" in V8, in
particular, the VirtualMemoryCage class, by dropping that name entirely.
Future sandbox features are developed under their own V8_SANDBOX_X flag,
and will, once final, be merged into V8_SANDBOX. Current future features
are sandboxed external pointers (using the external pointer table), and
sandboxed pointers (pointers guaranteed to point into the sandbox, e.g.
because they are encoded as offsets). This CL then also introduces a new
build flag, v8_enable_sandbox_future, which enables all future features.
Bug: v8:10391
Change-Id: I5174ea8f5ab40fb96a04af10853da735ad775c96
Cq-Include-Trybots: luci.v8.try:v8_linux64_heap_sandbox_dbg_ng,v8_linux_arm64_sim_heap_sandbox_dbg_ng
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3322981
Reviewed-by: Hannes Payer <hpayer@chromium.org>
Reviewed-by: Igor Sheludko <ishell@chromium.org>
Reviewed-by: Michael Achenbach <machenbach@chromium.org>
Reviewed-by: Toon Verwaest <verwaest@chromium.org>
Commit-Queue: Samuel Groß <saelo@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78384}
This is the final change list in the list of refactorings to split off
the implementations of v8::StackFrame and CallSite objects (as used by
the V8 JavaScript stack API). See https://bit.ly/v8-stack-frame for the
whole story.
This CL adds the v8::internal::StackFrameInfo class as new backing
implementation of v8::StackFrame, and puts it into debug-objects.tq
to indicate that it's used for the debugger API only. This new class
is lightweight and only holds on to static information about the
stack frame, and is thus usable for the V8 inspector to implement
async stack traces in a cheaper manner going forward.
Doc: https://bit.ly/v8-stack-frame
Bug: chromium:1258599, chromium:1278650
Fixed: chromium:1278647
Change-Id: I4dbf2d850f47797263af225895129499169aad02
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3302794
Commit-Queue: Benedikt Meurer <bmeurer@chromium.org>
Reviewed-by: Dominik Inführ <dinfuehr@chromium.org>
Reviewed-by: Jakob Kummerow <jkummerow@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78382}
On some branches of the search tree for a binary-search switch, the
input value is sufficiently constrained that we could unconditionally
jump to the last possible case rather than checking for value equality.
This shortens some builtins by a few instructions and might speed things
up, though I expect the effect to be small.
Change-Id: I2313f26976e6d3c182f03bd927b338c8175b3af3
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3335437
Reviewed-by: Nico Hartmann <nicohartmann@chromium.org>
Commit-Queue: Seth Brenith <seth.brenith@microsoft.com>
Cr-Commit-Position: refs/heads/main@{#78376}
Multiple threads can modify async_wraps_ in parallel, which is not ok.
Drive-by-fix:
- Use normal constructor/destructor for AsyncHooksWrap
- Use unique_ptr for storing AsyncHooksWrap
Bug: chromium:1278276
Change-Id: I667980151c775be29e603790e589b1de76fae05a
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3338257
Reviewed-by: Marja Hölttä <marja@chromium.org>
Commit-Queue: Camillo Bruni <cbruni@chromium.org>
Auto-Submit: Camillo Bruni <cbruni@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78375}
This decouples the stack trace visitation logic from the creation
of actual stack frame objects, in preparation to introduce a
second kind of stack frame object (`v8::internal::StackFrameInfo`
as part of http://crrev.com/c/3302794) in addition to the existing
`v8::internal::CallSiteInfo`.
Doc: https://bit.ly/v8-stack-frame
Bug: chromium:1258599, chromium:1278647, chromium:1278650
Change-Id: I398933653e29cc2fe5c222526d9dd686ef8239b4
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3334781
Commit-Queue: Benedikt Meurer <bmeurer@chromium.org>
Auto-Submit: Benedikt Meurer <bmeurer@chromium.org>
Reviewed-by: Jakob Kummerow <jkummerow@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78374}
- Mark uncommon timer-paths as V8_NOINLINE
- Add explicit LongTaskNestedTimedHistogramScope class
- Use explicit LongTaskRecordMode enum
- Mark a few more isolate methods as const
- Add more timer scopes:
- Accessors::ArrayLengthSetter
- v8::NewContext
Bug: v8:12498, chromium:1275056
Change-Id: I7896ee341c3c3a1fd5acf8f3f59347ff01dda9c0
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3338258
Reviewed-by: Marja Hölttä <marja@chromium.org>
Auto-Submit: Camillo Bruni <cbruni@chromium.org>
Reviewed-by: Jakob Kummerow <jkummerow@chromium.org>
Commit-Queue: Jakob Kummerow <jkummerow@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78372}
We probably expect a binary-search switch to take log(n) time in all
cases, but there is currently a possibility of that expectation being
broken. I'm not aware of any place where this actually happens, but if
the default handler immediately follows the switch dispatch block in
assembly order, then unconditional jump instructions for that handler
would be omitted. This omission could cause linear execution time, where
every case is checked before falling through to the default handler.
This change introduces a new function to emit an unconditional jump
instruction regardless of whether the target is the following block, and
uses that new function when generating a binary-search switch to ensure
consistently log(n) behavior.
Change-Id: I5cab86fd66386762519035410e3b532dc6fd764c
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3335222
Reviewed-by: Nico Hartmann <nicohartmann@chromium.org>
Commit-Queue: Seth Brenith <seth.brenith@microsoft.com>
Cr-Commit-Position: refs/heads/main@{#78370}
With dynamic tiering, the "serialize" function provided by the c-api
does not work anymore, and it is unclear how it should work.
R=jkummerow@chromium.org
Bug: v8:12281
Change-Id: Ib70bf118ba42b0752eb5dab5f43893da0404931e
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3338657
Reviewed-by: Jakob Kummerow <jkummerow@chromium.org>
Commit-Queue: Andreas Haas <ahaas@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78369}
An asm-js module has all wasm feature flags disabled, despite the global
flag configuration. Therefore, in WasmExportedFunction::New, we should
retrieve the enabled features from the NativeModule instead of the
flags.
Bug: chromium:1279151
Change-Id: Ic44fe535baa7cb851644457cce533c24d4c9824e
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3338256
Reviewed-by: Jakob Kummerow <jkummerow@chromium.org>
Commit-Queue: Manos Koukoutos <manoskouk@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78368}
This is a non-functional refactoring to make naming of stack traces more
consistent, and thus easier to reason about whether the "simple stack
trace" (stack trace API) or the "detailed stack trace" (inspector API)
is meant. Granted, these names aren't great by themselves, but at least
we should be consistent.
This also adds a new `Isolate::GetSimpleStackTrace()` and uses that
directly to implement the Wasm C-API, avoiding the roundtrip via the
`JSMessageObject`, which actually carries a detailed stack trace (which
by chance worked out so far).
Doc: https://bit.ly/v8-stack-frame
Bug: chromium:1258599, chromium:1278647, chromium:1278650
Change-Id: I29e1a956ed156d6eeceb50150a28afaa2f11b9c7
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3334780
Commit-Queue: Benedikt Meurer <bmeurer@chromium.org>
Reviewed-by: Thibaud Michaud <thibaudm@chromium.org>
Reviewed-by: Jakob Kummerow <jkummerow@chromium.org>
Reviewed-by: Maya Lekova <mslekova@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78366}
Use build_flags_ with @if/@ifnot in torque for the following flags:
- V8_ENABLE_JAVASCRIPT_PROMISE_HOOKS
- V8_ENABLE_SWISS_NAME_DICTIONARY
- Make sure Torque and CSA code actually respect
V8_ENABLE_JAVASCRIPT_PROMISE_HOOKS.
- Rename V8_ALLOW_JAVASCRIPT_IN_PROMISE_HOOKS to
V8_ENABLE_JAVASCRIPT_PROMISE_HOOKS
- Rename gn/bazel arg v8_allow_javascript_in_promise_hooks to
v8_enable_javascript_promise_hooks
- Unship context promise hooks in chrome and enable them only in d8
for testing purposes
- Make sure d8 and the API throw when using promise hooks without
the compile time feature enabled
Bug: chromium:1265186, v8:11025
Change-Id: I69834d44d683a36d0d7be3c3d68888321be0fd7f
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3301474
Reviewed-by: Nico Hartmann <nicohartmann@chromium.org>
Reviewed-by: Igor Sheludko <ishell@chromium.org>
Reviewed-by: Michael Achenbach <machenbach@chromium.org>
Commit-Queue: Camillo Bruni <cbruni@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78362}
This is the second step in the refactoring to make v8::StackFrame
more lightweight and usable for (long time storage) by the V8
inspector (see https://bit.ly/v8-stack-frame for an overview).
This is a purely mechanical change without any functional aspects.
The intention is to make the use case for the CallSiteInfo objects
clear, namely to serve as the backing store for the CallSite objects
exposed via the Error.prepareStackTrace() API and used under the
hood to implement the error.stack accessor.
Doc: https://bit.ly/v8-stack-frame
Bug: chromium:1258599, chromium:1278647, chromium:1278650
Change-Id: I39dffd1f1a8e5158ddc56f2a0a2b1b28321f487a
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3300138
Reviewed-by: Thibaud Michaud <thibaudm@chromium.org>
Reviewed-by: Jakob Kummerow <jkummerow@chromium.org>
Reviewed-by: Maya Lekova <mslekova@chromium.org>
Reviewed-by: Simon Zünd <szuend@chromium.org>
Reviewed-by: Dominik Inführ <dinfuehr@chromium.org>
Commit-Queue: Benedikt Meurer <bmeurer@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78361}
Some embedders might want to process console.info and console.log
differently. So inspector needs to return a different level for
these console log messages.
Change-Id: I936990a25f079a0d72f877a5095ed93819fc539a
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3331929
Reviewed-by: Benedikt Meurer <bmeurer@chromium.org>
Commit-Queue: Alexey Kozyatinskiy <kozyatinskiy@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78357}
