This change reduces the binary size on macOS x64 by around 50KB.
Here's a diff of the impact on the code generated for Attr_Binding::get_specified
in the Mac build. It's a bit hard to read because %r12 and %rbx swap their
function, but what happens in this method is that "movq %r12, %rcx" goes
away, and the two instructions "leal 0x1(%r12) %eax" and
"movl %eax, 0x10(%rbx)" turn into an "incl 0x10(%r12)".
So the old code was preserving the original value of profilingStack->stackPointer
in a register, and then using it later to compute the incremented stackPointer.
The new code uses an "incl" instruction for the stackPointer increment and
doesn't worry that the stackPointer value might have changed since the stack
size check at the start of the function. (It can't have changed.)
before: %rbx has the ProfilingStack*, %r12 has profilingStack->stackPointer
after: %r12 has the ProfilingStack*, %rbx has profilingStack->stackPointer
@@ -3,37 +3,35 @@
movq %rsp, %rbp
pushq %r15
pushq %r14
pushq %r12
pushq %rbx
subq $0x10, %rsp
movq %rcx, %r14
movq %rdx, %r15
- movq 0x80(%rdi), %rbx
- movq %rbx, -40(%rbp)
- testq %rbx, %rbx
+ movq 0x80(%rdi), %r12
+ movq %r12, -40(%rbp)
+ testq %r12, %r12
je loc_xxxxx
- movl 0x10(%rbx), %r12d
- cmpl (%rbx), %r12d
+ movl 0x10(%r12), %ebx
+ cmpl (%r12), %ebx
jae loc_xxxxx
- movq 0x8(%rbx), %rax
- movq %r12, %rcx
- shlq $0x5, %rcx
- leaq aAttr, %rdx ; "Attr"
- movq %rdx, (%rax,%rcx)
- leaq aSpecified, %rdx ; "specified"
- movq %rdx, 0x8(%rax,%rcx)
- leaq -40(%rbp), %rdx
- movq %rdx, 0x10(%rax,%rcx)
- movl $0x3a1, 0x1c(%rax,%rcx)
- leal 0x1(%r12), %eax
- movl %eax, 0x10(%rbx)
+ movq 0x8(%r12), %rax
+ shlq $0x5, %rbx
+ leaq aAttr, %rcx ; "Attr"
+ movq %rcx, (%rax,%rbx)
+ leaq aSpecified, %rcx ; "specified"
+ movq %rcx, 0x8(%rax,%rbx)
+ leaq -40(%rbp), %rcx
+ movq %rcx, 0x10(%rax,%rbx)
+ movl $0x3a1, 0x1c(%rax,%rbx)
+ incl 0x10(%r12)
movq %r15, %rdi
call __ZNK7mozilla3dom4Attr9SpecifiedEv ; mozilla::dom::Attr::Specified() const
movzxl %al, %eax
movabsq $0xfff9000000000000, %rcx
orq %rax, %rcx
movq %rcx, (%r14)
movq -40(%rbp), %rax
@@ -47,11 +45,11 @@
popq %rbx
popq %r12
popq %r14
popq %r15
popq %rbp
ret
; endp
- movq %rbx, %rdi
+ movq %r12, %rdi
call __ZN14ProfilingStack18ensureCapacitySlowEv ; ProfilingStack::ensureCapacitySlow()
jmp loc_xxxxx
Depends on D9205
Differential Revision: https://phabricator.services.mozilla.com/D9206
--HG--
extra : moz-landing-system : lando
These flags will be used by WebIDL APIs in an upcoming patch.
Depends on D9199
Differential Revision: https://phabricator.services.mozilla.com/D9203
--HG--
extra : moz-landing-system : lando
They were not displayed in the UI, and the instructions to initialize the line
field of a stack frame increased code size unnecessarily.
This change reduces the binary size on Linux x64 by around 100KB.
Here's a diff of the impact on the code generated for Attr_Binding::get_specified
in the Mac build:
@@ -20,17 +20,16 @@
movq 0x8(%rbx), %rax
movq %r12, %rcx
shlq $0x5, %rcx
leaq aGetAttrspecifi, %rdx ; "get Attr.specified"
movq %rdx, (%rax,%rcx)
movq $0x0, 0x8(%rax,%rcx)
leaq -40(%rbp), %rdx
movq %rdx, 0x10(%rax,%rcx)
- movl $0x106, 0x18(%rax,%rcx)
movl $0x1c, 0x1c(%rax,%rcx)
leal 0x1(%r12), %eax
movl %eax, 0x10(%rbx)
movq %r15, %rdi
call __ZNK7mozilla3dom4Attr9SpecifiedEv ; mozilla::dom::Attr::Specified() const
movzxl %al, %eax
movabsq $0xfff9000000000000, %rcx
Depends on D9193
Differential Revision: https://phabricator.services.mozilla.com/D9195
--HG--
extra : moz-landing-system : lando
This eliminates a few instructions from each inlined instance of
AutoProfilerLabel because we no longer need to handle allocation failure in the
inlined code.
I think this allocation should be fine to make infallible: The allocation size
is limited by the thread's stack depth, and we only hit this code path when the
stack is the deepest it's ever been during the thread's life time.
This change reduces the binary size on Linux x64 by around 100KB.
Here's a diff of the impact on the code generated for Attr_Binding::get_specified
in the Mac build, it really just eliminates one test and one jump at the very end
of the method:
@@ -9,30 +9,29 @@
movq %rcx, %r14
movq %rdx, %r15
movq 0x80(%rdi), %rbx
movq %rbx, -40(%rbp)
testq %rbx, %rbx
je loc_xxxxx
movl 0x10(%rbx), %r12d
- cmpl %r12d, (%rbx)
- jbe loc_xxxxx
+ cmpl (%rbx), %r12d
+ jae loc_xxxxx
movq 0x8(%rbx), %rax
movq %r12, %rcx
shlq $0x5, %rcx
leaq aGetAttrspecifi, %rdx ; "get Attr.specified"
movq %rdx, (%rax,%rcx)
movq $0x0, 0x8(%rax,%rcx)
leaq -40(%rbp), %rdx
movq %rdx, 0x10(%rax,%rcx)
movl $0x106, 0x18(%rax,%rcx)
movl $0x1c, 0x1c(%rax,%rcx)
-
leal 0x1(%r12), %eax
movl %eax, 0x10(%rbx)
movq %r15, %rdi
call __ZNK7mozilla3dom4Attr9SpecifiedEv ; mozilla::dom::Attr::Specified() const
movzxl %al, %eax
movabsq $0xfff9000000000000, %rcx
orq %rax, %rcx
@@ -50,12 +49,9 @@
popq %r14
popq %r15
popq %rbp
ret
; endp
movq %rbx, %rdi
call __ZN14ProfilingStack18ensureCapacitySlowEv ; ProfilingStack::ensureCapacitySlow()
- testb %al, %al
- jne loc_xxxxx
-
jmp loc_xxxxx
Depends on D9192
Differential Revision: https://phabricator.services.mozilla.com/D9193
--HG--
extra : moz-landing-system : lando
This eliminates a few instructions from every profiler label and saves code size.
We have around 9000 WebIDL constructors + methods + getters + setters which all
have an inlined instance of this code.
This change reduces the binary size on Linux x64 by around 160KB.
Here's a diff of the impact on the code generated for Attr_Binding::get_specified
in the Mac build:
movq %rsp, %rbp
pushq %r15
pushq %r14
pushq %r12
pushq %rbx
subq $0x10, %rsp
movq %rcx, %r14
movq %rdx, %r15
- movq __ZN7mozilla8profiler6detail12RacyFeatures18sActiveAndFeaturesE@GOT, %rax ; __ZN7mozilla8profiler6detail12RacyFeatures18sActiveAndFeaturesE@GOT
- movl (%rax), %eax
- testl %eax, %eax
- js loc_xxxxx
-
- movq $0x0, -40(%rbp)
- jmp loc_xxxxx
-
- movq 0x78(%rdi), %rbx
+ movq 0x80(%rdi), %rbx
movq %rbx, -40(%rbp)
testq %rbx, %rbx
je loc_xxxxx
movl 0x10(%rbx), %r12d
cmpl %r12d, (%rbx)
jbe loc_xxxxx
Differential Revision: https://phabricator.services.mozilla.com/D9192
--HG--
extra : moz-landing-system : lando
- Add JOF_ARGC, JOF_RESUMEINDEX instead of bare integer tags
- Fix some inconsistencies of JOF_ type and opcode size
- Reorganize JOF_ type list
Differential Revision: https://phabricator.services.mozilla.com/D10567
--HG--
extra : moz-landing-system : lando
This also reorders the remaining members of class ReadableStream a bit.
Depends on D10435
Differential Revision: https://phabricator.services.mozilla.com/D10436
--HG--
extra : moz-landing-system : lando
In passing, change ReadableStreamControllerPullSteps to use explicit downcasts,
so it's a little more obvious what's going on.
Depends on D10430
Differential Revision: https://phabricator.services.mozilla.com/D10431
--HG--
extra : moz-landing-system : lando
This commit changes ReadableStreamReaderGenericRelease to use
UnwrapInternalSlot when accessing reader.[[closedPromise]]. Before this commit,
the code assumed that there would be a promise in the slot, not a wrapper.
I think that was actually correct, because it's impossible for the stream to
still be readable and the reader to have a [[closedPromise]] that's a wrapper.
Still, it's a bit precarious (and I'm still not 100% sure about that), so I just
changed it to unwrap.
Depends on D10374
Differential Revision: https://phabricator.services.mozilla.com/D10428
--HG--
extra : moz-landing-system : lando
Note: JSOP_GOSUB has a use count of 2 even though it doesn't push/pop anything.
This isn't great but was done to match the old behavior (def count of 0, pushed
2 values).
Depends on D10571
Differential Revision: https://phabricator.services.mozilla.com/D10572
--HG--
extra : moz-landing-system : lando
This also reorders the remaining members of class ReadableStream a bit.
Depends on D10435
Differential Revision: https://phabricator.services.mozilla.com/D10436
--HG--
extra : moz-landing-system : lando
