daptest has type assertion functions that panic
if the read response/event message is not
the expected type. This is not only against the
recommended style guideline (Don't Panic, Useful
Test Failures, ...), but also it prevents from
quickly diagnosing test failures occurred in remote
CIs.
This PR changes the type assertion to the two
return value type assertion, and t.Fatal with details
if the type is not expected.
service/dap/daptest/main.go is a program that auto
generates those assertion functions in resp.go.
Run `go generate` from the service/dap directory
to update resp.go.
The client can specify certain configurations in the initialize request.
For example, pathFormat determines the pathFormat. We do not currently
support configuring pathFormat, linesStartAt1, or columnsStartAt1, so
we report an error if the client attempts to set these to an
unsupported value.
Changes the expression evaluation code so that register names, when not
shadowed by local or global variables, will evaluate to the current
value of the corresponding CPU register.
This allows a greater flexibility with displaying CPU registers than is
possible with using the ListRegisters API call. Also it allows
debuggers users to view register values even if the frontend they are
using does not implement a register view.
* service/dap: add go build stderr to error response
* service/dap: add go build stderr to error response
* Skip message check for build errors
* test for flag provided message
* service/dap: annotate shadowed variable names in variables request
In order to distinguish variables that are shadowed, this change
updates the names from 'name' to '(name)'. This is the same syntax
used in the terminal package.
* remove unnecessary comment
* Add todo for evaluate name
* Check the evaluateName result is the unshadowed var
* service/rpcommon: resolve race between Detach and shutdown
Detach will close DisconnectChan causing the server to initiate
shutdown, there is a race between Detach writing its response to the
client and the shutdown terminating the server process.
If Detach loses the race the response to the Detach request is never
sent to the client and the client will report an EOF error instead.
This change delays the start of the shutdown process until after Detach
has written its response.
Fixes an occasional failure of TestContinue.
* service/rpccommon: ignore listener error when shutting down
Ignore the closed listener error when the server is being shut down in
response to a SIGINT signal.
Fixes#1633
* service/dap: add substitutePath configuration
Similar to substitute-path configuration in the dlv cli, substitutePath
in dap allows users to specify path mappings that are applied to the
source files in stacktrace and breakpoint requests.
Updates #2203
* service/dap: refactor the startup of the fixture for attach
Add a helper function for starting up a process to attach to.
* service/dap: update substitute path tests for windows
* service/dap: remove lines that should have been removed in merge
* respond to comments on pr
* move logging to helper functions
* make test comments more clear
* Add comments about absolute paths
* fix log messages
* clarify test comments
* remove comment about absolute paths
We have some places where we use proc.ErrProcessExited and some places
that use &proc.ErrProcessExited, resulting in checks for process exited
errors occasionally failing on some architectures.
Uniform use of ErrProcessExited to the non-pointer version.
Fixes intermittent failure of TestStepOutPreservesGoroutine.
When restarting we must take care of setting breakpoint IDs correctly
so that enabled breakpoints do not end up having the same ID as a
disabled breakpoint, also we must make sure that breakpoints created
after restart will not get an ID already used by a disabled breakpoint.
* dap: change how noDebug launch request is served
PR #2400 added support for noDebug launch requests - that was done
by directly starting the target program using os/exec.Cmd and blocking
the launch request indefinitely until the program terminates or
is stopped with a disconnect request (when dlv dap can support it).
Even though the approach seemed to work for user, that adds an extra
control flow and complexity to the codebase.
This change takes a different approach to implement the noDebug
launch feature. Instead of using os/exec.Cmd, this uses the existing
debug launch path, but avoids setting breakpoints. Finally, the program
will start upon receiving onConfigurationDoneRequest and blocks there
until the program terminates. This simplifies the code.
The DAP spec does not explicitly specify what to do about other
requests. It seems like VSCode can issue evaluate requests or other
requests after the configuration done request. Currently they are
blocked because the program is in running state. We can consider checking
s.noDebug and responding with an error in the future if we want/need to.
See the log below for a typical DAP request/response sequence:
2021-03-29T01:42:53-04:00 debug layer=dap building binary at /Users/hakim/projects/s/__debug_bin
2021-03-29T01:42:55-04:00 info layer=debugger launching process with args: [/Users/hakim/projects/s/__debug_bin]
2021-03-29T01:42:55-04:00 debug layer=dap [-> to client]{"seq":0,"type":"event","event":"initialized"}
2021-03-29T01:42:55-04:00 debug layer=dap [-> to client]{"seq":0,"type":"response","request_seq":2,"success":true,"command":"launch"}
2021-03-29T01:42:55-04:00 debug layer=dap [<- from client]{"seq":3,"type":"request","command":"setBreakpoints","arguments":{"source":{"name":"main.go","path":"/Users/hakim/projects/s/main.go"},"breakpoints":[{"line":9}],"lines":[9]}}
2021-03-29T01:42:55-04:00 error layer=dap Unable to set or clear breakpoints: running in noDebug mode
2021-03-29T01:42:55-04:00 debug layer=dap [-> to client]{"seq":0,"type":"response","request_seq":3,"success":false,"command":"setBreakpoints","message":"Unable to set or clear breakpoints","body":{"error":{"id":2002,"format":"Unable to set or clear breakpoints: running in noDebug mode"}}}
2021-03-29T01:42:55-04:00 debug layer=dap [<- from client]{"seq":4,"type":"request","command":"configurationDone","arguments":{}}
2021-03-29T01:42:55-04:00 debug layer=dap [-> to client]{"seq":0,"type":"response","request_seq":4,"success":true,"command":"configurationDone"}
2021-03-29T01:42:55-04:00 debug layer=debugger continuing
Hello
2021-03-29T01:43:00-04:00 debug layer=dap [-> to client]{"seq":0,"type":"event","event":"terminated","body":{}}
2021-03-29T01:43:00-04:00 debug layer=dap [<- from client]{"seq":5,"type":"request","command":"threads"}
2021-03-29T01:43:00-04:00 debug layer=dap [-> to client]{"seq":0,"type":"response","request_seq":5,"success":true,"command":"threads","body":{"threads":null}}
2021-03-29T01:43:00-04:00 debug layer=dap [<- from client]{"seq":6,"type":"request","command":"disconnect","arguments":{}}
2021-03-29T01:43:00-04:00 debug layer=dap [-> to client]{"seq":0,"type":"response","request_seq":6,"success":true,"command":"disconnect"}
2021-03-29T01:43:00-04:00 debug layer=debugger halting
2021-03-29T01:43:00-04:00 error layer=dap Process 27219 has exited with status 0
2021-03-29T01:43:00-04:00 debug layer=debugger detaching
Updates https://github.com/golang/vscode-go/issues/1111
* service/dap: address polina's comments for noDebug logic
Reworked so the noDebug launch request again blocks launch request
handler after responding with the launch response. By skipping
the initialized event, it should prevent well-behaving clients from
sending any further requests. Currently, doesn't matter because
the handler goroutine will be blocked until the program termination
anyway.
Placed mutex back, since I noticed that's the only way to prevent
racing between Stop and the handler goroutine. The synchronization
lotic (in particular, during teardown) should be revisited after
asynchronous request support work is done.
* dap: address more comments
* service/dap: switch goroutine before stepping
The correct goroutine needs to be selected when stepping in order
for the step to execute to the correct location.
* handle next in progress while stepping
* Add tests for steps when switching goroutine
* remove nextInProgress handling
* add new step out test and review debug state check
* update text of stopped event and set goroutine id
Error level logging shows up in the users' consoles/terminals
so be more conservative when logging. Move the followings to
Debug logging.
- DAP error reponses caused by invalid requests.
They are application level errors and DAP clients should handle them.
- Errors reported when debugee already exited.
Fixesgolang/vscode-go#1392
Changes print so a format argument can be specified by using '%' as
prefix. For example:
print %x d
will print variable 'd' in hexadecimal. The interpretarion of the
format argument is the same as that of fmt's package.
Fixes#1038Fixes#1800Fixes#2159
* Truncate long compound map keys and use address suffix only for those
* Remove test typo that causes failures
Co-authored-by: Polina Sokolova <polinasok@users.noreply.github.com>
* Add logging and comments to clarify relative output path treatement
* Use absolute output path in one of the unittests
Co-authored-by: Polina Sokolova <polinasok@users.noreply.github.com>
If the launch requests has noDebug attribute set, run the built
binary directly. The launch request handler will block until
the binary terminates, so the editor won't send additional requests
like breakpoint setting etc. Still disconnect or restart requests
can flow in though and they should trigger killing of the target
process if it's still running.
In order to run the binary using os/exec on windows, the target
binary has to have .exe as its extension. So, add .exe to the default
output name if it is on windows. I am not sure though yet we want
to modify the user-specified output or not yet. Considering how
go commands behave (not automatically append .exe for 'go build -o')
I think respecting what user specified is right, but the failure
(file not exist) may be mysterious.
* service/dap: use specified working directory for launch requests
If a user specifies a working directory in the launch request,
then the process should use that working directory. This may
affect how the program runs and the user should be able to have
control over this.
* service/dap: add tests for launch with working dir
Added tests to make sure the working directory is set correctly.
* service/dap: fix TestWorkingDir on windows
* service/dap: use %q to print quoted string
* cmd/dlv: update dap warning about working dir
* service/dap: change the launch argument to be wd`
* update warning to specify only launch request
* Adds toggle command
Also adds two rpc2 tests for testing the new functionality
* Removes Debuggers' ToggleBreakpoint method
rpc2's ToggleBreakpoint now calls AmendBreakpoint
Refactors the ClearBreakpoint to avoid a lock.
* Use (*api.Variable).SinglelinesString() for dap.Variable values
* Make DeepSource happy
* Adjust unreadable regex in tests
* Use regex for runtime.mutex variable test
Co-authored-by: Polina Sokolova <polinasok@users.noreply.github.com>
* service: serialize calls to Command API
Wait until the target process has resumed before accepting new calls to
Command. Before this if a 'continue' was immediately followed by a
'halt' the 'halt' could be processed before the 'continue'.
Fixes#1608Fixes#2216
* service/rpccommon: fix DeepSource issues
* service/dap: support auto-loading of unloaded interfaces
* Make DeepSource happy
* Don't set reference if data failed to auto-load
* Use frame-less expressions
* Refine interface recursion capping test case
Co-authored-by: Polina Sokolova <polinasok@users.noreply.github.com>
- remove github workflow for testing macOS/amd64 that is now covered by
TeamCity
- fix DeepSource glob patterns to actually match what they are intended
to match (did the interpretation change?)
- disable some cgo tests on darwin/arm64
* Avoid double removal of temp binary
* Add back accidentally removed empty line
* Simplify regex
* Use unique build output directories in test cases
* Recover TestLaunchDebugRequest hidden logging and refine error check
* Special case access-denied error on Windows
* Remove special case for access denied on Windows
* Increase remove delay on Win
Co-authored-by: Polina Sokolova <polinasok@users.noreply.github.com>
* TeamCity: add linux/arm64/tip configuration
So that it can be tested when we make the next-version-support-branch.
* tests: disable failing cgo tests on arm64
* DAP test for github.com/golang/vscode-go/issues/1056
* DAP test for github.com/golang/vscode-go/issues/884
* DAP test for github.com/golang/vscode-go/issues/851
* DAP test for github.com/golang/vscode-go/issues/1053
* DAP test for github.com/golang/vscode-go/issues/1054
* Make DeepSource happy
Co-authored-by: Polina Sokolova <polinasok@users.noreply.github.com>
* proc/core: off-by-one error reading ELF core files
core.(*splicedMemory).ReadMemory checked the entry interval
erroneously when dealing with contiguous entries.
* terminal,service,proc/*: adds dump command (gcore equivalent)
Adds the `dump` command that creates a core file from the target process.
Backends will need to implement a new, optional, method `MemoryMap` that
returns a list of mapped memory regions.
Additionally the method `DumpProcessNotes` can be implemented to write out
to the core file notes describing the target process and its threads. If
DumpProcessNotes is not implemented `proc.Dump` will write a description of
the process and its threads in a OS/arch-independent format (that only Delve
understands).
Currently only linux/amd64 implements `DumpProcessNotes`.
Core files are only written in ELF, there is no minidump or macho-o writers.
# Conflicts:
# pkg/proc/proc_test.go
