2016-07-28 13:04:41 -04:00
|
|
|
// Copyright 2016 The Go Authors. All rights reserved.
|
|
|
|
|
// Use of this source code is governed by a BSD-style
|
|
|
|
|
// license that can be found in the LICENSE file.
|
|
|
|
|
|
|
|
|
|
// Package dwarf generates DWARF debugging information.
|
|
|
|
|
// DWARF generation is split between the compiler and the linker,
|
|
|
|
|
// this package contains the shared code.
|
|
|
|
|
package dwarf
|
|
|
|
|
|
2017-03-26 15:16:11 -07:00
|
|
|
import (
|
2017-05-02 16:46:01 +02:00
|
|
|
"errors"
|
2017-03-26 15:16:11 -07:00
|
|
|
"fmt"
|
|
|
|
|
)
|
2016-07-28 13:04:41 -04:00
|
|
|
|
|
|
|
|
// InfoPrefix is the prefix for all the symbols containing DWARF info entries.
|
|
|
|
|
const InfoPrefix = "go.info."
|
|
|
|
|
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
// RangePrefix is the prefix for all the symbols containing DWARF location lists.
|
|
|
|
|
const LocPrefix = "go.loc."
|
|
|
|
|
|
2017-05-02 16:46:01 +02:00
|
|
|
// RangePrefix is the prefix for all the symbols containing DWARF range lists.
|
|
|
|
|
const RangePrefix = "go.range."
|
|
|
|
|
|
2017-10-17 17:09:54 -04:00
|
|
|
// ConstInfoPrefix is the prefix for all symbols containing DWARF info
|
2017-09-03 11:59:18 +02:00
|
|
|
// entries that contain constants.
|
|
|
|
|
const ConstInfoPrefix = "go.constinfo."
|
|
|
|
|
|
2017-10-17 17:09:54 -04:00
|
|
|
// CUInfoPrefix is the prefix for symbols containing information to
|
|
|
|
|
// populate the DWARF compilation unit info entries.
|
|
|
|
|
const CUInfoPrefix = "go.cuinfo."
|
|
|
|
|
|
2016-07-28 13:04:41 -04:00
|
|
|
// Sym represents a symbol.
|
|
|
|
|
type Sym interface {
|
2017-05-02 16:46:01 +02:00
|
|
|
Len() int64
|
2016-07-28 13:04:41 -04:00
|
|
|
}
|
|
|
|
|
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
// A Location represents a variable's location at a particular PC range.
|
|
|
|
|
// It becomes a location list entry in the DWARF.
|
|
|
|
|
type Location struct {
|
|
|
|
|
StartPC, EndPC int64
|
|
|
|
|
Pieces []Piece
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// A Piece represents the location of a particular part of a variable.
|
|
|
|
|
// It becomes part of a location list entry (a DW_OP_piece) in the DWARF.
|
|
|
|
|
type Piece struct {
|
|
|
|
|
Length int64
|
|
|
|
|
StackOffset int32
|
|
|
|
|
RegNum int16
|
|
|
|
|
Missing bool
|
|
|
|
|
OnStack bool // if true, RegNum is unset.
|
|
|
|
|
}
|
|
|
|
|
|
2016-07-28 13:04:41 -04:00
|
|
|
// A Var represents a local variable or a function parameter.
|
|
|
|
|
type Var struct {
|
2017-10-18 13:45:03 -04:00
|
|
|
Name string
|
|
|
|
|
Abbrev int // Either DW_ABRV_AUTO[_LOCLIST] or DW_ABRV_PARAM[_LOCLIST]
|
|
|
|
|
IsReturnValue bool
|
|
|
|
|
StackOffset int32
|
|
|
|
|
LocationList []Location
|
|
|
|
|
Scope int32
|
|
|
|
|
Type Sym
|
|
|
|
|
DeclLine uint
|
2016-07-28 13:04:41 -04:00
|
|
|
}
|
|
|
|
|
|
2017-05-02 16:46:01 +02:00
|
|
|
// A Scope represents a lexical scope. All variables declared within a
|
|
|
|
|
// scope will only be visible to instructions covered by the scope.
|
|
|
|
|
// Lexical scopes are contiguous in source files but can end up being
|
|
|
|
|
// compiled to discontiguous blocks of instructions in the executable.
|
|
|
|
|
// The Ranges field lists all the blocks of instructions that belong
|
|
|
|
|
// in this scope.
|
|
|
|
|
type Scope struct {
|
|
|
|
|
Parent int32
|
|
|
|
|
Ranges []Range
|
|
|
|
|
Vars []*Var
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// A Range represents a half-open interval [Start, End).
|
|
|
|
|
type Range struct {
|
|
|
|
|
Start, End int64
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// UnifyRanges merges the list of ranges of c into the list of ranges of s
|
|
|
|
|
func (s *Scope) UnifyRanges(c *Scope) {
|
|
|
|
|
out := make([]Range, 0, len(s.Ranges)+len(c.Ranges))
|
|
|
|
|
|
|
|
|
|
i, j := 0, 0
|
|
|
|
|
for {
|
|
|
|
|
var cur Range
|
|
|
|
|
if i < len(s.Ranges) && j < len(c.Ranges) {
|
|
|
|
|
if s.Ranges[i].Start < c.Ranges[j].Start {
|
|
|
|
|
cur = s.Ranges[i]
|
|
|
|
|
i++
|
|
|
|
|
} else {
|
|
|
|
|
cur = c.Ranges[j]
|
|
|
|
|
j++
|
|
|
|
|
}
|
|
|
|
|
} else if i < len(s.Ranges) {
|
|
|
|
|
cur = s.Ranges[i]
|
|
|
|
|
i++
|
|
|
|
|
} else if j < len(c.Ranges) {
|
|
|
|
|
cur = c.Ranges[j]
|
|
|
|
|
j++
|
|
|
|
|
} else {
|
|
|
|
|
break
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if n := len(out); n > 0 && cur.Start <= out[n-1].End {
|
|
|
|
|
out[n-1].End = cur.End
|
|
|
|
|
} else {
|
|
|
|
|
out = append(out, cur)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
s.Ranges = out
|
|
|
|
|
}
|
|
|
|
|
|
2016-07-28 13:04:41 -04:00
|
|
|
// A Context specifies how to add data to a Sym.
|
|
|
|
|
type Context interface {
|
|
|
|
|
PtrSize() int
|
|
|
|
|
AddInt(s Sym, size int, i int64)
|
|
|
|
|
AddBytes(s Sym, b []byte)
|
|
|
|
|
AddAddress(s Sym, t interface{}, ofs int64)
|
|
|
|
|
AddSectionOffset(s Sym, size int, t interface{}, ofs int64)
|
|
|
|
|
AddString(s Sym, v string)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// AppendUleb128 appends v to b using DWARF's unsigned LEB128 encoding.
|
|
|
|
|
func AppendUleb128(b []byte, v uint64) []byte {
|
|
|
|
|
for {
|
|
|
|
|
c := uint8(v & 0x7f)
|
|
|
|
|
v >>= 7
|
|
|
|
|
if v != 0 {
|
|
|
|
|
c |= 0x80
|
|
|
|
|
}
|
|
|
|
|
b = append(b, c)
|
|
|
|
|
if c&0x80 == 0 {
|
|
|
|
|
break
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
return b
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// AppendSleb128 appends v to b using DWARF's signed LEB128 encoding.
|
|
|
|
|
func AppendSleb128(b []byte, v int64) []byte {
|
|
|
|
|
for {
|
|
|
|
|
c := uint8(v & 0x7f)
|
|
|
|
|
s := uint8(v & 0x40)
|
|
|
|
|
v >>= 7
|
|
|
|
|
if (v != -1 || s == 0) && (v != 0 || s != 0) {
|
|
|
|
|
c |= 0x80
|
|
|
|
|
}
|
|
|
|
|
b = append(b, c)
|
|
|
|
|
if c&0x80 == 0 {
|
|
|
|
|
break
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
return b
|
|
|
|
|
}
|
|
|
|
|
|
2017-03-26 15:16:11 -07:00
|
|
|
// sevenbits contains all unsigned seven bit numbers, indexed by their value.
|
|
|
|
|
var sevenbits = [...]byte{
|
|
|
|
|
0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
|
|
|
|
|
0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
|
|
|
|
|
0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f,
|
|
|
|
|
0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
|
|
|
|
|
0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f,
|
|
|
|
|
0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f,
|
|
|
|
|
0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f,
|
|
|
|
|
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f,
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// sevenBitU returns the unsigned LEB128 encoding of v if v is seven bits and nil otherwise.
|
|
|
|
|
// The contents of the returned slice must not be modified.
|
|
|
|
|
func sevenBitU(v int64) []byte {
|
|
|
|
|
if uint64(v) < uint64(len(sevenbits)) {
|
|
|
|
|
return sevenbits[v : v+1]
|
|
|
|
|
}
|
|
|
|
|
return nil
|
|
|
|
|
}
|
2016-07-28 13:04:41 -04:00
|
|
|
|
2017-03-26 15:16:11 -07:00
|
|
|
// sevenBitS returns the signed LEB128 encoding of v if v is seven bits and nil otherwise.
|
|
|
|
|
// The contents of the returned slice must not be modified.
|
|
|
|
|
func sevenBitS(v int64) []byte {
|
|
|
|
|
if uint64(v) <= 63 {
|
|
|
|
|
return sevenbits[v : v+1]
|
|
|
|
|
}
|
|
|
|
|
if uint64(-v) <= 64 {
|
|
|
|
|
return sevenbits[128+v : 128+v+1]
|
|
|
|
|
}
|
|
|
|
|
return nil
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Uleb128put appends v to s using DWARF's unsigned LEB128 encoding.
|
2016-07-28 13:04:41 -04:00
|
|
|
func Uleb128put(ctxt Context, s Sym, v int64) {
|
2017-03-26 15:16:11 -07:00
|
|
|
b := sevenBitU(v)
|
|
|
|
|
if b == nil {
|
|
|
|
|
var encbuf [20]byte
|
|
|
|
|
b = AppendUleb128(encbuf[:0], uint64(v))
|
|
|
|
|
}
|
2016-07-28 13:04:41 -04:00
|
|
|
ctxt.AddBytes(s, b)
|
|
|
|
|
}
|
|
|
|
|
|
2017-03-26 15:16:11 -07:00
|
|
|
// Sleb128put appends v to s using DWARF's signed LEB128 encoding.
|
2016-07-28 13:04:41 -04:00
|
|
|
func Sleb128put(ctxt Context, s Sym, v int64) {
|
2017-03-26 15:16:11 -07:00
|
|
|
b := sevenBitS(v)
|
|
|
|
|
if b == nil {
|
|
|
|
|
var encbuf [20]byte
|
|
|
|
|
b = AppendSleb128(encbuf[:0], v)
|
|
|
|
|
}
|
2016-07-28 13:04:41 -04:00
|
|
|
ctxt.AddBytes(s, b)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Defining Abbrevs. This is hardcoded, and there will be
|
|
|
|
|
* only a handful of them. The DWARF spec places no restriction on
|
|
|
|
|
* the ordering of attributes in the Abbrevs and DIEs, and we will
|
|
|
|
|
* always write them out in the order of declaration in the abbrev.
|
|
|
|
|
*/
|
|
|
|
|
type dwAttrForm struct {
|
|
|
|
|
attr uint16
|
|
|
|
|
form uint8
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Go-specific type attributes.
|
|
|
|
|
const (
|
|
|
|
|
DW_AT_go_kind = 0x2900
|
|
|
|
|
DW_AT_go_key = 0x2901
|
|
|
|
|
DW_AT_go_elem = 0x2902
|
2017-04-26 17:58:31 -04:00
|
|
|
// Attribute for DW_TAG_member of a struct type.
|
|
|
|
|
// Nonzero value indicates the struct field is an embedded field.
|
|
|
|
|
DW_AT_go_embedded_field = 0x2903
|
2016-07-28 13:04:41 -04:00
|
|
|
|
|
|
|
|
DW_AT_internal_location = 253 // params and locals; not emitted
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
// Index into the abbrevs table below.
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
// Keep in sync with ispubname() and ispubtype() in ld/dwarf.go.
|
2016-07-28 13:04:41 -04:00
|
|
|
// ispubtype considers >= NULLTYPE public
|
|
|
|
|
const (
|
|
|
|
|
DW_ABRV_NULL = iota
|
|
|
|
|
DW_ABRV_COMPUNIT
|
|
|
|
|
DW_ABRV_FUNCTION
|
|
|
|
|
DW_ABRV_VARIABLE
|
2017-09-03 11:59:18 +02:00
|
|
|
DW_ABRV_INT_CONSTANT
|
2016-07-28 13:04:41 -04:00
|
|
|
DW_ABRV_AUTO
|
2017-07-24 13:37:04 -04:00
|
|
|
DW_ABRV_AUTO_LOCLIST
|
2016-07-28 13:04:41 -04:00
|
|
|
DW_ABRV_PARAM
|
2017-07-24 13:37:04 -04:00
|
|
|
DW_ABRV_PARAM_LOCLIST
|
2017-05-02 16:46:01 +02:00
|
|
|
DW_ABRV_LEXICAL_BLOCK_RANGES
|
|
|
|
|
DW_ABRV_LEXICAL_BLOCK_SIMPLE
|
2016-07-28 13:04:41 -04:00
|
|
|
DW_ABRV_STRUCTFIELD
|
|
|
|
|
DW_ABRV_FUNCTYPEPARAM
|
|
|
|
|
DW_ABRV_DOTDOTDOT
|
|
|
|
|
DW_ABRV_ARRAYRANGE
|
|
|
|
|
DW_ABRV_NULLTYPE
|
|
|
|
|
DW_ABRV_BASETYPE
|
|
|
|
|
DW_ABRV_ARRAYTYPE
|
|
|
|
|
DW_ABRV_CHANTYPE
|
|
|
|
|
DW_ABRV_FUNCTYPE
|
|
|
|
|
DW_ABRV_IFACETYPE
|
|
|
|
|
DW_ABRV_MAPTYPE
|
|
|
|
|
DW_ABRV_PTRTYPE
|
|
|
|
|
DW_ABRV_BARE_PTRTYPE // only for void*, no DW_AT_type attr to please gdb 6.
|
|
|
|
|
DW_ABRV_SLICETYPE
|
|
|
|
|
DW_ABRV_STRINGTYPE
|
|
|
|
|
DW_ABRV_STRUCTTYPE
|
|
|
|
|
DW_ABRV_TYPEDECL
|
|
|
|
|
DW_NABRV
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
type dwAbbrev struct {
|
|
|
|
|
tag uint8
|
|
|
|
|
children uint8
|
|
|
|
|
attr []dwAttrForm
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
var abbrevs = [DW_NABRV]dwAbbrev{
|
|
|
|
|
/* The mandatory DW_ABRV_NULL entry. */
|
|
|
|
|
{0, 0, []dwAttrForm{}},
|
|
|
|
|
|
|
|
|
|
/* COMPUNIT */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_compile_unit,
|
|
|
|
|
DW_CHILDREN_yes,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_language, DW_FORM_data1},
|
2017-05-24 17:43:08 -04:00
|
|
|
{DW_AT_stmt_list, DW_FORM_sec_offset},
|
2017-10-10 16:19:49 -04:00
|
|
|
{DW_AT_low_pc, DW_FORM_addr},
|
|
|
|
|
{DW_AT_ranges, DW_FORM_sec_offset},
|
2016-07-28 13:04:41 -04:00
|
|
|
{DW_AT_comp_dir, DW_FORM_string},
|
2017-05-08 14:37:02 -04:00
|
|
|
{DW_AT_producer, DW_FORM_string},
|
2016-07-28 13:04:41 -04:00
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* FUNCTION */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_subprogram,
|
|
|
|
|
DW_CHILDREN_yes,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_low_pc, DW_FORM_addr},
|
2017-09-06 22:05:24 -04:00
|
|
|
{DW_AT_high_pc, DW_FORM_addr},
|
2017-05-24 17:43:08 -04:00
|
|
|
{DW_AT_frame_base, DW_FORM_block1},
|
2016-07-28 13:04:41 -04:00
|
|
|
{DW_AT_external, DW_FORM_flag},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* VARIABLE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_variable,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_location, DW_FORM_block1},
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
{DW_AT_external, DW_FORM_flag},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
2017-09-03 11:59:18 +02:00
|
|
|
/* INT CONSTANT */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_constant,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
{DW_AT_const_value, DW_FORM_sdata},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
2016-07-28 13:04:41 -04:00
|
|
|
/* AUTO */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_variable,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
2017-05-26 15:34:56 -04:00
|
|
|
{DW_AT_decl_line, DW_FORM_udata},
|
2016-07-28 13:04:41 -04:00
|
|
|
{DW_AT_location, DW_FORM_block1},
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
2017-07-24 13:37:04 -04:00
|
|
|
/* AUTO_LOCLIST */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_variable,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
2017-08-25 12:27:15 -04:00
|
|
|
{DW_AT_decl_line, DW_FORM_udata},
|
2017-07-24 13:37:04 -04:00
|
|
|
{DW_AT_location, DW_FORM_sec_offset},
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
2016-07-28 13:04:41 -04:00
|
|
|
/* PARAM */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_formal_parameter,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
2017-10-18 13:45:03 -04:00
|
|
|
{DW_AT_variable_parameter, DW_FORM_flag},
|
2017-05-26 15:34:56 -04:00
|
|
|
{DW_AT_decl_line, DW_FORM_udata},
|
2016-07-28 13:04:41 -04:00
|
|
|
{DW_AT_location, DW_FORM_block1},
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
},
|
|
|
|
|
},
|
2017-07-24 13:37:04 -04:00
|
|
|
|
|
|
|
|
/* PARAM_LOCLIST */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_formal_parameter,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
2017-10-18 13:45:03 -04:00
|
|
|
{DW_AT_variable_parameter, DW_FORM_flag},
|
2017-08-25 12:27:15 -04:00
|
|
|
{DW_AT_decl_line, DW_FORM_udata},
|
2017-07-24 13:37:04 -04:00
|
|
|
{DW_AT_location, DW_FORM_sec_offset},
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
2017-05-02 16:46:01 +02:00
|
|
|
/* LEXICAL_BLOCK_RANGES */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_lexical_block,
|
|
|
|
|
DW_CHILDREN_yes,
|
|
|
|
|
[]dwAttrForm{
|
2017-05-24 17:43:08 -04:00
|
|
|
{DW_AT_ranges, DW_FORM_sec_offset},
|
2017-05-02 16:46:01 +02:00
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* LEXICAL_BLOCK_SIMPLE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_lexical_block,
|
|
|
|
|
DW_CHILDREN_yes,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_low_pc, DW_FORM_addr},
|
2017-09-06 22:05:24 -04:00
|
|
|
{DW_AT_high_pc, DW_FORM_addr},
|
2017-05-02 16:46:01 +02:00
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
2016-07-28 13:04:41 -04:00
|
|
|
/* STRUCTFIELD */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_member,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
2017-07-26 15:58:25 -04:00
|
|
|
{DW_AT_data_member_location, DW_FORM_udata},
|
2016-07-28 13:04:41 -04:00
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
2017-04-26 17:58:31 -04:00
|
|
|
{DW_AT_go_embedded_field, DW_FORM_flag},
|
2016-07-28 13:04:41 -04:00
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* FUNCTYPEPARAM */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_formal_parameter,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
|
|
|
|
|
// No name!
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* DOTDOTDOT */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_unspecified_parameters,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* ARRAYRANGE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_subrange_type,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
|
|
|
|
|
// No name!
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
{DW_AT_count, DW_FORM_udata},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
// Below here are the types considered public by ispubtype
|
|
|
|
|
/* NULLTYPE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_unspecified_type,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* BASETYPE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_base_type,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_encoding, DW_FORM_data1},
|
|
|
|
|
{DW_AT_byte_size, DW_FORM_data1},
|
|
|
|
|
{DW_AT_go_kind, DW_FORM_data1},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* ARRAYTYPE */
|
|
|
|
|
// child is subrange with upper bound
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_array_type,
|
|
|
|
|
DW_CHILDREN_yes,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
{DW_AT_byte_size, DW_FORM_udata},
|
|
|
|
|
{DW_AT_go_kind, DW_FORM_data1},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* CHANTYPE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_typedef,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
{DW_AT_go_kind, DW_FORM_data1},
|
|
|
|
|
{DW_AT_go_elem, DW_FORM_ref_addr},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* FUNCTYPE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_subroutine_type,
|
|
|
|
|
DW_CHILDREN_yes,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
2017-08-14 15:07:57 -07:00
|
|
|
{DW_AT_byte_size, DW_FORM_udata},
|
2016-07-28 13:04:41 -04:00
|
|
|
// {DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
{DW_AT_go_kind, DW_FORM_data1},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* IFACETYPE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_typedef,
|
|
|
|
|
DW_CHILDREN_yes,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
{DW_AT_go_kind, DW_FORM_data1},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* MAPTYPE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_typedef,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
{DW_AT_go_kind, DW_FORM_data1},
|
|
|
|
|
{DW_AT_go_key, DW_FORM_ref_addr},
|
|
|
|
|
{DW_AT_go_elem, DW_FORM_ref_addr},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* PTRTYPE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_pointer_type,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
{DW_AT_go_kind, DW_FORM_data1},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* BARE_PTRTYPE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_pointer_type,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* SLICETYPE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_structure_type,
|
|
|
|
|
DW_CHILDREN_yes,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_byte_size, DW_FORM_udata},
|
|
|
|
|
{DW_AT_go_kind, DW_FORM_data1},
|
|
|
|
|
{DW_AT_go_elem, DW_FORM_ref_addr},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* STRINGTYPE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_structure_type,
|
|
|
|
|
DW_CHILDREN_yes,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_byte_size, DW_FORM_udata},
|
|
|
|
|
{DW_AT_go_kind, DW_FORM_data1},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* STRUCTTYPE */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_structure_type,
|
|
|
|
|
DW_CHILDREN_yes,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_byte_size, DW_FORM_udata},
|
|
|
|
|
{DW_AT_go_kind, DW_FORM_data1},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
/* TYPEDECL */
|
|
|
|
|
{
|
|
|
|
|
DW_TAG_typedef,
|
|
|
|
|
DW_CHILDREN_no,
|
|
|
|
|
[]dwAttrForm{
|
|
|
|
|
{DW_AT_name, DW_FORM_string},
|
|
|
|
|
{DW_AT_type, DW_FORM_ref_addr},
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// GetAbbrev returns the contents of the .debug_abbrev section.
|
|
|
|
|
func GetAbbrev() []byte {
|
|
|
|
|
var buf []byte
|
|
|
|
|
for i := 1; i < DW_NABRV; i++ {
|
|
|
|
|
// See section 7.5.3
|
|
|
|
|
buf = AppendUleb128(buf, uint64(i))
|
|
|
|
|
buf = AppendUleb128(buf, uint64(abbrevs[i].tag))
|
|
|
|
|
buf = append(buf, byte(abbrevs[i].children))
|
|
|
|
|
for _, f := range abbrevs[i].attr {
|
|
|
|
|
buf = AppendUleb128(buf, uint64(f.attr))
|
|
|
|
|
buf = AppendUleb128(buf, uint64(f.form))
|
|
|
|
|
}
|
|
|
|
|
buf = append(buf, 0, 0)
|
|
|
|
|
}
|
|
|
|
|
return append(buf, 0)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Debugging Information Entries and their attributes.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
// DWAttr represents an attribute of a DWDie.
|
|
|
|
|
//
|
|
|
|
|
// For DW_CLS_string and _block, value should contain the length, and
|
|
|
|
|
// data the data, for _reference, value is 0 and data is a DWDie* to
|
|
|
|
|
// the referenced instance, for all others, value is the whole thing
|
|
|
|
|
// and data is null.
|
|
|
|
|
type DWAttr struct {
|
|
|
|
|
Link *DWAttr
|
|
|
|
|
Atr uint16 // DW_AT_
|
|
|
|
|
Cls uint8 // DW_CLS_
|
|
|
|
|
Value int64
|
|
|
|
|
Data interface{}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// DWDie represents a DWARF debug info entry.
|
|
|
|
|
type DWDie struct {
|
|
|
|
|
Abbrev int
|
|
|
|
|
Link *DWDie
|
|
|
|
|
Child *DWDie
|
|
|
|
|
Attr *DWAttr
|
|
|
|
|
Sym Sym
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func putattr(ctxt Context, s Sym, abbrev int, form int, cls int, value int64, data interface{}) error {
|
|
|
|
|
switch form {
|
|
|
|
|
case DW_FORM_addr: // address
|
|
|
|
|
ctxt.AddAddress(s, data, value)
|
|
|
|
|
|
|
|
|
|
case DW_FORM_block1: // block
|
|
|
|
|
if cls == DW_CLS_ADDRESS {
|
|
|
|
|
ctxt.AddInt(s, 1, int64(1+ctxt.PtrSize()))
|
|
|
|
|
ctxt.AddInt(s, 1, DW_OP_addr)
|
|
|
|
|
ctxt.AddAddress(s, data, 0)
|
|
|
|
|
break
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
value &= 0xff
|
|
|
|
|
ctxt.AddInt(s, 1, value)
|
|
|
|
|
p := data.([]byte)[:value]
|
|
|
|
|
ctxt.AddBytes(s, p)
|
|
|
|
|
|
|
|
|
|
case DW_FORM_block2: // block
|
|
|
|
|
value &= 0xffff
|
|
|
|
|
|
|
|
|
|
ctxt.AddInt(s, 2, value)
|
|
|
|
|
p := data.([]byte)[:value]
|
|
|
|
|
ctxt.AddBytes(s, p)
|
|
|
|
|
|
|
|
|
|
case DW_FORM_block4: // block
|
|
|
|
|
value &= 0xffffffff
|
|
|
|
|
|
|
|
|
|
ctxt.AddInt(s, 4, value)
|
|
|
|
|
p := data.([]byte)[:value]
|
|
|
|
|
ctxt.AddBytes(s, p)
|
|
|
|
|
|
|
|
|
|
case DW_FORM_block: // block
|
|
|
|
|
Uleb128put(ctxt, s, value)
|
|
|
|
|
|
|
|
|
|
p := data.([]byte)[:value]
|
|
|
|
|
ctxt.AddBytes(s, p)
|
|
|
|
|
|
|
|
|
|
case DW_FORM_data1: // constant
|
|
|
|
|
ctxt.AddInt(s, 1, value)
|
|
|
|
|
|
|
|
|
|
case DW_FORM_data2: // constant
|
|
|
|
|
ctxt.AddInt(s, 2, value)
|
|
|
|
|
|
|
|
|
|
case DW_FORM_data4: // constant, {line,loclist,mac,rangelist}ptr
|
2017-05-02 16:46:01 +02:00
|
|
|
if cls == DW_CLS_PTR { // DW_AT_stmt_list and DW_AT_ranges
|
|
|
|
|
ctxt.AddSectionOffset(s, 4, data, value)
|
2016-07-28 13:04:41 -04:00
|
|
|
break
|
|
|
|
|
}
|
|
|
|
|
ctxt.AddInt(s, 4, value)
|
|
|
|
|
|
|
|
|
|
case DW_FORM_data8: // constant, {line,loclist,mac,rangelist}ptr
|
|
|
|
|
ctxt.AddInt(s, 8, value)
|
|
|
|
|
|
|
|
|
|
case DW_FORM_sdata: // constant
|
|
|
|
|
Sleb128put(ctxt, s, value)
|
|
|
|
|
|
|
|
|
|
case DW_FORM_udata: // constant
|
|
|
|
|
Uleb128put(ctxt, s, value)
|
|
|
|
|
|
|
|
|
|
case DW_FORM_string: // string
|
|
|
|
|
str := data.(string)
|
|
|
|
|
ctxt.AddString(s, str)
|
|
|
|
|
// TODO(ribrdb): verify padded strings are never used and remove this
|
|
|
|
|
for i := int64(len(str)); i < value; i++ {
|
|
|
|
|
ctxt.AddInt(s, 1, 0)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
case DW_FORM_flag: // flag
|
|
|
|
|
if value != 0 {
|
|
|
|
|
ctxt.AddInt(s, 1, 1)
|
|
|
|
|
} else {
|
|
|
|
|
ctxt.AddInt(s, 1, 0)
|
|
|
|
|
}
|
|
|
|
|
|
2017-05-24 17:43:08 -04:00
|
|
|
// As of DWARF 3 the ref_addr is always 32 bits, unless emitting a large
|
2016-07-28 13:04:41 -04:00
|
|
|
// (> 4 GB of debug info aka "64-bit") unit, which we don't implement.
|
|
|
|
|
case DW_FORM_ref_addr: // reference to a DIE in the .info section
|
2017-05-24 17:43:08 -04:00
|
|
|
fallthrough
|
|
|
|
|
case DW_FORM_sec_offset: // offset into a DWARF section other than .info
|
2016-07-28 13:04:41 -04:00
|
|
|
if data == nil {
|
|
|
|
|
return fmt.Errorf("dwarf: null reference in %d", abbrev)
|
|
|
|
|
}
|
2017-05-24 17:43:08 -04:00
|
|
|
ctxt.AddSectionOffset(s, 4, data, value)
|
2016-07-28 13:04:41 -04:00
|
|
|
|
|
|
|
|
case DW_FORM_ref1, // reference within the compilation unit
|
|
|
|
|
DW_FORM_ref2, // reference
|
|
|
|
|
DW_FORM_ref4, // reference
|
|
|
|
|
DW_FORM_ref8, // reference
|
|
|
|
|
DW_FORM_ref_udata, // reference
|
|
|
|
|
|
|
|
|
|
DW_FORM_strp, // string
|
|
|
|
|
DW_FORM_indirect: // (see Section 7.5.3)
|
|
|
|
|
fallthrough
|
|
|
|
|
default:
|
|
|
|
|
return fmt.Errorf("dwarf: unsupported attribute form %d / class %d", form, cls)
|
|
|
|
|
}
|
|
|
|
|
return nil
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// PutAttrs writes the attributes for a DIE to symbol 's'.
|
|
|
|
|
//
|
|
|
|
|
// Note that we can (and do) add arbitrary attributes to a DIE, but
|
|
|
|
|
// only the ones actually listed in the Abbrev will be written out.
|
|
|
|
|
func PutAttrs(ctxt Context, s Sym, abbrev int, attr *DWAttr) {
|
|
|
|
|
Outer:
|
|
|
|
|
for _, f := range abbrevs[abbrev].attr {
|
|
|
|
|
for ap := attr; ap != nil; ap = ap.Link {
|
|
|
|
|
if ap.Atr == f.attr {
|
|
|
|
|
putattr(ctxt, s, abbrev, int(f.form), int(ap.Cls), ap.Value, ap.Data)
|
|
|
|
|
continue Outer
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
putattr(ctxt, s, abbrev, int(f.form), 0, 0, nil)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// HasChildren returns true if 'die' uses an abbrev that supports children.
|
|
|
|
|
func HasChildren(die *DWDie) bool {
|
|
|
|
|
return abbrevs[die.Abbrev].children != 0
|
|
|
|
|
}
|
|
|
|
|
|
2017-09-03 11:59:18 +02:00
|
|
|
// PutIntConst writes a DIE for an integer constant
|
|
|
|
|
func PutIntConst(ctxt Context, info, typ Sym, name string, val int64) {
|
|
|
|
|
Uleb128put(ctxt, info, DW_ABRV_INT_CONSTANT)
|
|
|
|
|
putattr(ctxt, info, DW_ABRV_INT_CONSTANT, DW_FORM_string, DW_CLS_STRING, int64(len(name)), name)
|
|
|
|
|
putattr(ctxt, info, DW_ABRV_INT_CONSTANT, DW_FORM_ref_addr, DW_CLS_REFERENCE, 0, typ)
|
|
|
|
|
putattr(ctxt, info, DW_ABRV_INT_CONSTANT, DW_FORM_sdata, DW_CLS_CONSTANT, val, nil)
|
|
|
|
|
}
|
|
|
|
|
|
2017-10-10 16:19:49 -04:00
|
|
|
// PutRanges writes a range table to sym. All addresses in ranges are
|
|
|
|
|
// relative to some base address. If base is not nil, then they're
|
|
|
|
|
// relative to the start of base. If base is nil, then the caller must
|
|
|
|
|
// arrange a base address some other way (such as a DW_AT_low_pc
|
|
|
|
|
// attribute).
|
|
|
|
|
func PutRanges(ctxt Context, sym Sym, base Sym, ranges []Range) {
|
|
|
|
|
ps := ctxt.PtrSize()
|
|
|
|
|
// Write base address entry.
|
|
|
|
|
if base != nil {
|
|
|
|
|
ctxt.AddInt(sym, ps, -1)
|
|
|
|
|
ctxt.AddAddress(sym, base, 0)
|
|
|
|
|
}
|
|
|
|
|
// Write ranges.
|
|
|
|
|
for _, r := range ranges {
|
|
|
|
|
ctxt.AddInt(sym, ps, r.Start)
|
|
|
|
|
ctxt.AddInt(sym, ps, r.End)
|
|
|
|
|
}
|
|
|
|
|
// Write trailer.
|
|
|
|
|
ctxt.AddInt(sym, ps, 0)
|
|
|
|
|
ctxt.AddInt(sym, ps, 0)
|
|
|
|
|
}
|
|
|
|
|
|
2016-07-28 13:04:41 -04:00
|
|
|
// PutFunc writes a DIE for a function to s.
|
|
|
|
|
// It also writes child DIEs for each variable in vars.
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
func PutFunc(ctxt Context, info, loc, ranges Sym, name string, external bool, startPC Sym, size int64, scopes []Scope) error {
|
|
|
|
|
Uleb128put(ctxt, info, DW_ABRV_FUNCTION)
|
|
|
|
|
putattr(ctxt, info, DW_ABRV_FUNCTION, DW_FORM_string, DW_CLS_STRING, int64(len(name)), name)
|
|
|
|
|
putattr(ctxt, info, DW_ABRV_FUNCTION, DW_FORM_addr, DW_CLS_ADDRESS, 0, startPC)
|
2017-09-06 22:05:24 -04:00
|
|
|
putattr(ctxt, info, DW_ABRV_FUNCTION, DW_FORM_addr, DW_CLS_ADDRESS, size, startPC)
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
putattr(ctxt, info, DW_ABRV_FUNCTION, DW_FORM_block1, DW_CLS_BLOCK, 1, []byte{DW_OP_call_frame_cfa})
|
2016-07-28 13:04:41 -04:00
|
|
|
var ev int64
|
|
|
|
|
if external {
|
|
|
|
|
ev = 1
|
|
|
|
|
}
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
putattr(ctxt, info, DW_ABRV_FUNCTION, DW_FORM_flag, DW_CLS_FLAG, ev, 0)
|
2017-05-02 16:46:01 +02:00
|
|
|
if len(scopes) > 0 {
|
|
|
|
|
var encbuf [20]byte
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
if putscope(ctxt, info, loc, ranges, startPC, 0, scopes, encbuf[:0]) < int32(len(scopes)) {
|
2017-05-02 16:46:01 +02:00
|
|
|
return errors.New("multiple toplevel scopes")
|
2017-03-07 18:59:14 +01:00
|
|
|
}
|
|
|
|
|
}
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
Uleb128put(ctxt, info, 0)
|
2017-05-02 16:46:01 +02:00
|
|
|
return nil
|
|
|
|
|
}
|
|
|
|
|
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
func putscope(ctxt Context, info, loc, ranges, startPC Sym, curscope int32, scopes []Scope, encbuf []byte) int32 {
|
2017-05-02 16:46:01 +02:00
|
|
|
for _, v := range scopes[curscope].Vars {
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
putvar(ctxt, info, loc, v, startPC, encbuf)
|
2017-05-02 16:46:01 +02:00
|
|
|
}
|
|
|
|
|
this := curscope
|
|
|
|
|
curscope++
|
|
|
|
|
for curscope < int32(len(scopes)) {
|
|
|
|
|
scope := scopes[curscope]
|
|
|
|
|
if scope.Parent != this {
|
|
|
|
|
return curscope
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if len(scope.Ranges) == 1 {
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
Uleb128put(ctxt, info, DW_ABRV_LEXICAL_BLOCK_SIMPLE)
|
|
|
|
|
putattr(ctxt, info, DW_ABRV_LEXICAL_BLOCK_SIMPLE, DW_FORM_addr, DW_CLS_ADDRESS, scope.Ranges[0].Start, startPC)
|
2017-09-06 22:05:24 -04:00
|
|
|
putattr(ctxt, info, DW_ABRV_LEXICAL_BLOCK_SIMPLE, DW_FORM_addr, DW_CLS_ADDRESS, scope.Ranges[0].End, startPC)
|
2017-05-02 16:46:01 +02:00
|
|
|
} else {
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
Uleb128put(ctxt, info, DW_ABRV_LEXICAL_BLOCK_RANGES)
|
|
|
|
|
putattr(ctxt, info, DW_ABRV_LEXICAL_BLOCK_RANGES, DW_FORM_sec_offset, DW_CLS_PTR, ranges.Len(), ranges)
|
2017-05-02 16:46:01 +02:00
|
|
|
|
2017-10-10 16:19:49 -04:00
|
|
|
PutRanges(ctxt, ranges, startPC, scope.Ranges)
|
2017-05-02 16:46:01 +02:00
|
|
|
}
|
|
|
|
|
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
curscope = putscope(ctxt, info, loc, ranges, startPC, curscope, scopes, encbuf)
|
2017-05-02 16:46:01 +02:00
|
|
|
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
Uleb128put(ctxt, info, 0)
|
2017-05-02 16:46:01 +02:00
|
|
|
}
|
|
|
|
|
return curscope
|
|
|
|
|
}
|
|
|
|
|
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
func putvar(ctxt Context, info, loc Sym, v *Var, startPC Sym, encbuf []byte) {
|
cmd/compile: cover control flow insns in location lists
The information that's used to generate DWARF location lists is very
ssa.Value centric; it uses Values as start and end coordinates to define
ranges. That mostly works fine, but control flow instructions don't come
from Values, so the ranges couldn't cover them.
Control flow instructions are generated when the SSA representation is
converted to assembly, so that's the best place to extend the ranges
to cover them. (Before that, there's nothing to refer to, and afterward
the boundaries between blocks have been lost.) That requires block
information in the debugInfo type, which then flows down to make
everything else awkward. On the plus side, there's a little less copying
slices around than there used to be, so it should be a little faster.
Previously, the ranges for empty blocks were not very meaningful. That
was fine, because they had no Values to cover, so no debug information
was generated for them. But they do have control flow instructions
(that's why they exist) and so now it's important that the information
be correct. Introduce two sentinel values, BlockStart and BlockEnd, that
denote the boundary of a block, even if the block is empty. BlockEnd
replaces the previous SurvivedBlock flag.
There's one more problem: the last instruction in the function will be a
control flow instruction, so any live ranges need to be extended past
it. But there's no instruction after it to use as the end of the range.
Instead, leave the EndProg field of those ranges as nil and fix it up to
point to past the end of the assembled text at the very last moment.
Change-Id: I81f884020ff36fd6fe8d7888fc57c99412c4245b
Reviewed-on: https://go-review.googlesource.com/63010
Reviewed-by: Alessandro Arzilli <alessandro.arzilli@gmail.com>
Reviewed-by: David Chase <drchase@google.com>
Run-TryBot: Heschi Kreinick <heschi@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
2017-09-11 14:28:34 -04:00
|
|
|
// If the variable was entirely optimized out, don't emit a location list;
|
|
|
|
|
// convert to an inline abbreviation and emit an empty location.
|
|
|
|
|
missing := false
|
|
|
|
|
switch {
|
|
|
|
|
case v.Abbrev == DW_ABRV_AUTO_LOCLIST && len(v.LocationList) == 0:
|
|
|
|
|
missing = true
|
|
|
|
|
v.Abbrev = DW_ABRV_AUTO
|
|
|
|
|
case v.Abbrev == DW_ABRV_PARAM_LOCLIST && len(v.LocationList) == 0:
|
|
|
|
|
missing = true
|
|
|
|
|
v.Abbrev = DW_ABRV_PARAM
|
|
|
|
|
}
|
|
|
|
|
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
Uleb128put(ctxt, info, int64(v.Abbrev))
|
2017-10-18 13:45:03 -04:00
|
|
|
putattr(ctxt, info, v.Abbrev, DW_FORM_string, DW_CLS_STRING, int64(len(v.Name)), v.Name)
|
|
|
|
|
if v.Abbrev == DW_ABRV_PARAM || v.Abbrev == DW_ABRV_PARAM_LOCLIST {
|
|
|
|
|
var isReturn int64
|
|
|
|
|
if v.IsReturnValue {
|
|
|
|
|
isReturn = 1
|
|
|
|
|
}
|
|
|
|
|
putattr(ctxt, info, v.Abbrev, DW_FORM_flag, DW_CLS_FLAG, isReturn, nil)
|
|
|
|
|
}
|
2017-05-26 15:34:56 -04:00
|
|
|
putattr(ctxt, info, v.Abbrev, DW_FORM_udata, DW_CLS_CONSTANT, int64(v.DeclLine), nil)
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
if v.Abbrev == DW_ABRV_AUTO_LOCLIST || v.Abbrev == DW_ABRV_PARAM_LOCLIST {
|
|
|
|
|
putattr(ctxt, info, v.Abbrev, DW_FORM_sec_offset, DW_CLS_PTR, int64(loc.Len()), loc)
|
|
|
|
|
addLocList(ctxt, loc, startPC, v, encbuf)
|
|
|
|
|
} else {
|
2017-07-04 08:32:02 +02:00
|
|
|
loc := encbuf[:0]
|
cmd/compile: cover control flow insns in location lists
The information that's used to generate DWARF location lists is very
ssa.Value centric; it uses Values as start and end coordinates to define
ranges. That mostly works fine, but control flow instructions don't come
from Values, so the ranges couldn't cover them.
Control flow instructions are generated when the SSA representation is
converted to assembly, so that's the best place to extend the ranges
to cover them. (Before that, there's nothing to refer to, and afterward
the boundaries between blocks have been lost.) That requires block
information in the debugInfo type, which then flows down to make
everything else awkward. On the plus side, there's a little less copying
slices around than there used to be, so it should be a little faster.
Previously, the ranges for empty blocks were not very meaningful. That
was fine, because they had no Values to cover, so no debug information
was generated for them. But they do have control flow instructions
(that's why they exist) and so now it's important that the information
be correct. Introduce two sentinel values, BlockStart and BlockEnd, that
denote the boundary of a block, even if the block is empty. BlockEnd
replaces the previous SurvivedBlock flag.
There's one more problem: the last instruction in the function will be a
control flow instruction, so any live ranges need to be extended past
it. But there's no instruction after it to use as the end of the range.
Instead, leave the EndProg field of those ranges as nil and fix it up to
point to past the end of the assembled text at the very last moment.
Change-Id: I81f884020ff36fd6fe8d7888fc57c99412c4245b
Reviewed-on: https://go-review.googlesource.com/63010
Reviewed-by: Alessandro Arzilli <alessandro.arzilli@gmail.com>
Reviewed-by: David Chase <drchase@google.com>
Run-TryBot: Heschi Kreinick <heschi@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
2017-09-11 14:28:34 -04:00
|
|
|
switch {
|
|
|
|
|
case missing:
|
|
|
|
|
break // no location
|
|
|
|
|
case v.StackOffset == 0:
|
2017-07-04 08:32:02 +02:00
|
|
|
loc = append(loc, DW_OP_call_frame_cfa)
|
cmd/compile: cover control flow insns in location lists
The information that's used to generate DWARF location lists is very
ssa.Value centric; it uses Values as start and end coordinates to define
ranges. That mostly works fine, but control flow instructions don't come
from Values, so the ranges couldn't cover them.
Control flow instructions are generated when the SSA representation is
converted to assembly, so that's the best place to extend the ranges
to cover them. (Before that, there's nothing to refer to, and afterward
the boundaries between blocks have been lost.) That requires block
information in the debugInfo type, which then flows down to make
everything else awkward. On the plus side, there's a little less copying
slices around than there used to be, so it should be a little faster.
Previously, the ranges for empty blocks were not very meaningful. That
was fine, because they had no Values to cover, so no debug information
was generated for them. But they do have control flow instructions
(that's why they exist) and so now it's important that the information
be correct. Introduce two sentinel values, BlockStart and BlockEnd, that
denote the boundary of a block, even if the block is empty. BlockEnd
replaces the previous SurvivedBlock flag.
There's one more problem: the last instruction in the function will be a
control flow instruction, so any live ranges need to be extended past
it. But there's no instruction after it to use as the end of the range.
Instead, leave the EndProg field of those ranges as nil and fix it up to
point to past the end of the assembled text at the very last moment.
Change-Id: I81f884020ff36fd6fe8d7888fc57c99412c4245b
Reviewed-on: https://go-review.googlesource.com/63010
Reviewed-by: Alessandro Arzilli <alessandro.arzilli@gmail.com>
Reviewed-by: David Chase <drchase@google.com>
Run-TryBot: Heschi Kreinick <heschi@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
2017-09-11 14:28:34 -04:00
|
|
|
default:
|
2017-07-04 08:32:02 +02:00
|
|
|
loc = append(loc, DW_OP_fbreg)
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
loc = AppendSleb128(loc, int64(v.StackOffset))
|
|
|
|
|
}
|
|
|
|
|
putattr(ctxt, info, v.Abbrev, DW_FORM_block1, DW_CLS_BLOCK, int64(len(loc)), loc)
|
|
|
|
|
}
|
|
|
|
|
putattr(ctxt, info, v.Abbrev, DW_FORM_ref_addr, DW_CLS_REFERENCE, 0, v.Type)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func addLocList(ctxt Context, listSym, startPC Sym, v *Var, encbuf []byte) {
|
|
|
|
|
// Base address entry: max ptr followed by the base address.
|
|
|
|
|
ctxt.AddInt(listSym, ctxt.PtrSize(), ^0)
|
|
|
|
|
ctxt.AddAddress(listSym, startPC, 0)
|
|
|
|
|
for _, entry := range v.LocationList {
|
|
|
|
|
ctxt.AddInt(listSym, ctxt.PtrSize(), entry.StartPC)
|
|
|
|
|
ctxt.AddInt(listSym, ctxt.PtrSize(), entry.EndPC)
|
|
|
|
|
locBuf := encbuf[:0]
|
|
|
|
|
for _, piece := range entry.Pieces {
|
|
|
|
|
if !piece.Missing {
|
|
|
|
|
if piece.OnStack {
|
2017-07-04 08:32:02 +02:00
|
|
|
if piece.StackOffset == 0 {
|
|
|
|
|
locBuf = append(locBuf, DW_OP_call_frame_cfa)
|
|
|
|
|
} else {
|
|
|
|
|
locBuf = append(locBuf, DW_OP_fbreg)
|
|
|
|
|
locBuf = AppendSleb128(locBuf, int64(piece.StackOffset))
|
|
|
|
|
}
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
} else {
|
|
|
|
|
if piece.RegNum < 32 {
|
|
|
|
|
locBuf = append(locBuf, DW_OP_reg0+byte(piece.RegNum))
|
|
|
|
|
} else {
|
|
|
|
|
locBuf = append(locBuf, DW_OP_regx)
|
|
|
|
|
locBuf = AppendUleb128(locBuf, uint64(piece.RegNum))
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
if len(entry.Pieces) > 1 {
|
|
|
|
|
locBuf = append(locBuf, DW_OP_piece)
|
|
|
|
|
locBuf = AppendUleb128(locBuf, uint64(piece.Length))
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
ctxt.AddInt(listSym, 2, int64(len(locBuf)))
|
|
|
|
|
ctxt.AddBytes(listSym, locBuf)
|
2017-05-02 16:46:01 +02:00
|
|
|
}
|
[dev.debug] cmd/compile: better DWARF with optimizations on
Debuggers use DWARF information to find local variables on the
stack and in registers. Prior to this CL, the DWARF information for
functions claimed that all variables were on the stack at all times.
That's incorrect when optimizations are enabled, and results in
debuggers showing data that is out of date or complete gibberish.
After this CL, the compiler is capable of representing variable
locations more accurately, and attempts to do so. Due to limitations of
the SSA backend, it's not possible to be completely correct.
There are a number of problems in the current design. One of the easier
to understand is that variable names currently must be attached to an
SSA value, but not all assignments in the source code actually result
in machine code. For example:
type myint int
var a int
b := myint(int)
and
b := (*uint64)(unsafe.Pointer(a))
don't generate machine code because the underlying representation is the
same, so the correct value of b will not be set when the user would
expect.
Generating the more precise debug information is behind a flag,
dwarflocationlists. Because of the issues described above, setting the
flag may not make the debugging experience much better, and may actually
make it worse in cases where the variable actually is on the stack and
the more complicated analysis doesn't realize it.
A number of changes are included:
- Add a new pseudo-instruction, RegKill, which indicates that the value
in the register has been clobbered.
- Adjust regalloc to emit RegKills in the right places. Significantly,
this means that phis are mixed with StoreReg and RegKills after
regalloc.
- Track variable decomposition in ssa.LocalSlots.
- After the SSA backend is done, analyze the result and build location
lists for each LocalSlot.
- After assembly is done, update the location lists with the assembled
PC offsets, recompose variables, and build DWARF location lists. Emit the
list as a new linker symbol, one per function.
- In the linker, aggregate the location lists into a .debug_loc section.
TODO:
- currently disabled for non-X86/AMD64 because there are no data tables.
go build -toolexec 'toolstash -cmp' -a std succeeds.
With -dwarflocationlists false:
before: f02812195637909ff675782c0b46836a8ff01976
after: 06f61e8112a42ac34fb80e0c818b3cdb84a5e7ec
benchstat -geomean /tmp/220352263 /tmp/621364410
completed 15 of 15, estimated time remaining 0s (eta 3:52PM)
name old time/op new time/op delta
Template 199ms ± 3% 198ms ± 2% ~ (p=0.400 n=15+14)
Unicode 96.6ms ± 5% 96.4ms ± 5% ~ (p=0.838 n=15+15)
GoTypes 653ms ± 2% 647ms ± 2% ~ (p=0.102 n=15+14)
Flate 133ms ± 6% 129ms ± 3% -2.62% (p=0.041 n=15+15)
GoParser 164ms ± 5% 159ms ± 3% -3.05% (p=0.000 n=15+15)
Reflect 428ms ± 4% 422ms ± 3% ~ (p=0.156 n=15+13)
Tar 123ms ±10% 124ms ± 8% ~ (p=0.461 n=15+15)
XML 228ms ± 3% 224ms ± 3% -1.57% (p=0.045 n=15+15)
[Geo mean] 206ms 377ms +82.86%
name old user-time/op new user-time/op delta
Template 292ms ±10% 301ms ±12% ~ (p=0.189 n=15+15)
Unicode 166ms ±37% 158ms ±14% ~ (p=0.418 n=15+14)
GoTypes 962ms ± 6% 963ms ± 7% ~ (p=0.976 n=15+15)
Flate 207ms ±19% 200ms ±14% ~ (p=0.345 n=14+15)
GoParser 246ms ±22% 240ms ±15% ~ (p=0.587 n=15+15)
Reflect 611ms ±13% 587ms ±14% ~ (p=0.085 n=15+13)
Tar 211ms ±12% 217ms ±14% ~ (p=0.355 n=14+15)
XML 335ms ±15% 320ms ±18% ~ (p=0.169 n=15+15)
[Geo mean] 317ms 583ms +83.72%
name old alloc/op new alloc/op delta
Template 40.2MB ± 0% 40.2MB ± 0% -0.15% (p=0.000 n=14+15)
Unicode 29.2MB ± 0% 29.3MB ± 0% ~ (p=0.624 n=15+15)
GoTypes 114MB ± 0% 114MB ± 0% -0.15% (p=0.000 n=15+14)
Flate 25.7MB ± 0% 25.6MB ± 0% -0.18% (p=0.000 n=13+15)
GoParser 32.2MB ± 0% 32.2MB ± 0% -0.14% (p=0.003 n=15+15)
Reflect 77.8MB ± 0% 77.9MB ± 0% ~ (p=0.061 n=15+15)
Tar 27.1MB ± 0% 27.0MB ± 0% -0.11% (p=0.029 n=15+15)
XML 42.7MB ± 0% 42.5MB ± 0% -0.29% (p=0.000 n=15+15)
[Geo mean] 42.1MB 75.0MB +78.05%
name old allocs/op new allocs/op delta
Template 402k ± 1% 398k ± 0% -0.91% (p=0.000 n=15+15)
Unicode 344k ± 1% 344k ± 0% ~ (p=0.715 n=15+14)
GoTypes 1.18M ± 0% 1.17M ± 0% -0.91% (p=0.000 n=15+14)
Flate 243k ± 0% 240k ± 1% -1.05% (p=0.000 n=13+15)
GoParser 327k ± 1% 324k ± 1% -0.96% (p=0.000 n=15+15)
Reflect 984k ± 1% 982k ± 0% ~ (p=0.050 n=15+15)
Tar 261k ± 1% 259k ± 1% -0.77% (p=0.000 n=15+15)
XML 411k ± 0% 404k ± 1% -1.55% (p=0.000 n=15+15)
[Geo mean] 439k 755k +72.01%
name old text-bytes new text-bytes delta
HelloSize 694kB ± 0% 694kB ± 0% -0.00% (p=0.000 n=15+15)
name old data-bytes new data-bytes delta
HelloSize 5.55kB ± 0% 5.55kB ± 0% ~ (all equal)
name old bss-bytes new bss-bytes delta
HelloSize 133kB ± 0% 133kB ± 0% ~ (all equal)
name old exe-bytes new exe-bytes delta
HelloSize 1.04MB ± 0% 1.04MB ± 0% ~ (all equal)
Change-Id: I991fc553ef175db46bb23b2128317bbd48de70d8
Reviewed-on: https://go-review.googlesource.com/41770
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-07-21 18:30:19 -04:00
|
|
|
// End list
|
|
|
|
|
ctxt.AddInt(listSym, ctxt.PtrSize(), 0)
|
|
|
|
|
ctxt.AddInt(listSym, ctxt.PtrSize(), 0)
|
2016-07-28 13:04:41 -04:00
|
|
|
}
|
2017-02-06 15:52:36 -08:00
|
|
|
|
|
|
|
|
// VarsByOffset attaches the methods of sort.Interface to []*Var,
|
2017-07-21 17:55:41 -04:00
|
|
|
// sorting in increasing StackOffset.
|
2017-02-06 15:52:36 -08:00
|
|
|
type VarsByOffset []*Var
|
|
|
|
|
|
|
|
|
|
func (s VarsByOffset) Len() int { return len(s) }
|
2017-07-21 17:55:41 -04:00
|
|
|
func (s VarsByOffset) Less(i, j int) bool { return s[i].StackOffset < s[j].StackOffset }
|
2017-02-06 15:52:36 -08:00
|
|
|
func (s VarsByOffset) Swap(i, j int) { s[i], s[j] = s[j], s[i] }
|