Issue #3548 describes a bug in the compiler which was fixed by commit
505e50b. But this case wasn't covered by our current tests (obviously)
and the fix in the compiler looks accidental so it's worth adding a
test for it.
Fixes#3548
This patch adds support for listing and setting breakpoints on inlined functions within stripped binaries. It uses a forked version of `debug/gosym` copied from golang.org/x/vuln/internal/vulncheck/internal/gosym which adds support for parsing the inline tree of the pclntab section. Parsing this section requires knowing the offset of the "go:func.*" symbol, which is not present in stripped binaries via the ``.symtab` section so instead, we search the `.noptrdata` section which contains `runtime.moduledatap` which contains the value of that missing symbol, which we then can use to find the inline tree for a given function.
Given all this we parse the inline tree for each function we find, and then add that information the the appropriate `Function` contained in `bi.Functions`, using a relatively empty `Function` struct as what would be the abstract origin.
- fix TestRefreshCurThreadSelGAfterContinueOnceError and TestBadAccess
to work when debugserver has --unmask-signals
- when a fatal signal is received while singlestepping delay its
delivery until the subsequent continue, otherwise debugserver will get
stuck completely (fixes TestNilPtrDerefInBreakInstr)
We have used a goroutine to keep track of some of the expression
evaluation status across target resumes during call injections.
Now that the expression interpreter has been rewritten to use a stack
machine we can move what little state is left into the stack machine
and get rid of the goroutine-and-channel mechanism.
* proc: use stack machine to evaluate expressions
This commit splits expression evaluation into two parts. The first part (in
pkg/proc/evalop/evalcompile.go) "compiles" as ast.Expr into a list of
instructions (defined in pkg/proc/evalop/ops.go) for a stack machine
(defined by `proc.(*evalStack)`).
The second part is a stack machine (implemented by `proc.(*EvalScope).eval`
and `proc.(*EvalScope).evalOne`) that has two modes of operation: in the
main mode it executes inteructions from the list (by calling `evalOne`), in
the second mode it executes the call injection protocol by calling
`funcCallStep` repeatedly until it either the protocol finishes, needs more
input from the stack machine (to set call arguments) or fails.
This approach has several benefits:
- it is now possible to remove the goroutine we use to evaluate expression
and the channel used to communicate with the Continue loop.
- every time we resume the target to execute the call injection protocol we
need to update several local variables to match the changed state of the
target, this is now done at the top level of the evaluation loop instead of
being hidden inside a recurisive evaluator
- using runtime.Pin to pin addresses returned by an injected call would
allow us to use a more natural evaluation order for function calls, which
would solve some bugs #3310, allow users to inspect values returned by a
call injection #1599 and allow implementing some other features #1465. Doing
this with the recursive evaluator, while keeping backwards compatibility
with versions of Go that do not have runtime.Pin is very hard. However after
this change we can simply conditionally change how compileFunctionCall works
and add some opcodes.
* review round 1
* review round 2
Use the trampoline attribute to detect auto-generated code. This fixes
a bug where stepping into a method of a generic type called through an
interface will take the debugger into an auto-generated wrapper that
does not have a dictionary and using next will step out of the wrapper.
Fixes a bug reported on the #delve channel of the gophers slack server.
There is no benefit to having a small part of the freebsd backend
implemented in C, rather than using cgo. While here, add a missing
call to procstat_close and check the return value of
procstat_getpathname.
Thank you to everyone who contributed to this release:
@alexsaezm, @pgavlin, @archanaravindar, @aarzilli, @hyangah, @thechampagne, @javierhonduco, @andreimatei, @gocurr, @alexandear, @stefanhaller.
* enable func call injection on delve for ppc64le
* Function call injection on Delve/ppc64le, modified DWARF encoding and decoding for floating point registers to make floatsum test work
* Function call injection on Delve/ppc64le cleanup
* skip PIE tests for function call injection on other packages
* Address review comments
* accounted for additional skipped PIE tests for function call injection
* Code cleanup and undoing revert of previous commit
* Enable function call injection only on 1.22 and above and some cleanup
* additional cleanup, go fmt run
* Debug function call tests fail on ppc64le/PIE mode adjusted the backup_test_health.md file accordingly
The current implementation assumes a specific command line interface
for opening an editor at a specific location within the source file.
This patch updates for different formats, namely the one used by the
editor 'hx'.
* proc: correctly update local variables after continue
At various point during the execution of the call injection protocol
the process is resumed and the call injection goroutine could migrate
to a different thread, we must make sure to update our local variables
correctly after every point where the target program is resumed.
'fncall122debug_clean' on 'f469a0a5'.
* go.mod: update golang.org/x/tools
Go 1.22 broke golang.org/x/tools/packages
* cmd/dlv: disable TestStaticcheck with go1.22
Go 1.22 is not yet supported by staticcheck.
This command lists the packages included in the debugee.
The implementation utilizes "ListPackagesBuildInfo" RPC.
In order to support server-side filtering like `sources` and other
commands, expanded the ListPackagesBuildInfo RPC to take an optional
filter field.
From the Go specification:
"1. For a nil slice, the number of iterations is 0." [1]
Therefore, an additional nil check for before the loop is unnecessary.
[1]: https://go.dev/ref/spec#For_range
Signed-off-by: Eng Zer Jun <engzerjun@gmail.com>
Miscellaneous non-functional changes to prepare for adding support for
follow-exec mode on Windows:
- removed (*nativeProcess).wait function from Windows backend (unused).
- move close of ptraceDoneChan from release to handlePtraceFuncs, this
makes postExit callable by a function executed by execPtraceFunc.
- change addTarget to detach before creating the target object if we
don't actually want to attach to the child process, also moved the
detach call to (*processGroup).add instead of having one in addTarget
and one in the code that calls (*processGroup).add.
- changed Detach to be a method of TargetGroup/ProcessGroup, the
Windows backend will need access to the process group to call
WaitForDebugEvent.
- moved resume method to processGroup. First all threads stopped at a
breakpoint need to be stepped, then all other threads can be resumed.
This is true also for linux even though it didn't cause the current
tests to fail.
Adds -chan option to the goroutines command to list only the goroutines
running on a specified channel.
Also when printing a variable if it is a channel also print the list of
goroutines that are waiting on it.
Implementing the `DW_CFA_remember_state` and `DW_CFA_restore_state`
according to the DWARF specification requires us to create a stack that
can store an arbitrary number of elements, that is, there could be
multiple "pushes" before "popping" them.
From the 5th revision of the spec [0]:
> 6.4.2.4 Row State Instructions
> DW_CFA_remember_state
> The DW_CFA_remember_state instruction takes no operands. The required
> action is to push the set of rules for every register onto an implicit stack.
> DW_CFA_restore_state
> DW_CFA_restore_state
> The DW_CFA_restore_state instruction takes no operands. The required action
> is to pop the set of rules off the implicit stack and place them in the
> current row.
- [0]: https://dwarfstd.org/doc/DWARF5.pdf
Signed-off-by: Francisco Javier Honduvilla Coto <javierhonduco@gmail.com>
- add architecture rule for ppc64le so that incompatible agents don't
pick up the build
- disable PIE tests on linux/ppc64le (the tests claim it doesn't work)
- enable PIE tests on darwin/amd64 now that the entry point calculation
has been fixed
- remove dependency on wget and curl in the test script for linux to
reduce test time
- only install git in the linux test script when we need it
- remove staticcheck from linux/ppc64le builds (it takes almost 5
minutes between installation and execution and makes the test timeout
sometimes)
- drop windows/arm64/tip build, the windows/arm64 build is broken
anyway and since there is only one agent it makes CI runs slow
- drop linux/ppc64le/tip build, there is only one agent, it's slow and
it will always timeout. CI runs in excess of 1h are too long.
If there is no current goroutine when 'next', 'step' or 'stepout' are
used set a condition that the thread ID should stay the same instead.
This makes stepping work for multithreaded C programs or Go programs
that have threads started by cgo code.
Fixes#3262
Add parsing for the new version format with toolchain (X.Y.Z-something)
and simplify internal representation of versions so that revision, beta
version and rc version are all represented on a single field with rc
and beta versions being negative numbers (this limits rc versions to a
maximum of 1000 which will not be a problem in practice).
The -C argument must come first on the command line of 'go build' if
the flags specified by the user via build-flags start with -C pass it
first.
Replaces #3380
TestStacktraceGoroutine failed intermittently on freebsd/amd64/go1.20.
This happens because of two windows, in the scheduler (right after
parking a goroutine and just before resuming a parked goroutine) where
a thread is associated with a goroutine but running in the system stack
and there is no systemstack_switch frame to connect the two stacks.
Go1.22 switched to emitting PIE by default and also changed some
details of the PIE implementation. This breaks delve entirely on macOS.
Fix how relocations are handled on macOS.
Update test matrix to remove 1.18 and add 1.21, fix build scripts to
deal with the new format returned by:
https://golang.org/VERSION?m=text
which now has an extra second line with the time.
Adds a waitfor option to 'dlv attach' that waits for a process with a
name starting with a given prefix to appear before attaching to it.
Debugserver on macOS does not support follow-fork mode, but has this
feature instead which is not the same thing but still helps with
multiprocess debugging somewhat.
I searched the source code of Go, and found no usages of
"== (reflect.Value{})" and "!= (reflect.Value{})". I think
it's more idiomatic to use "IsValid" to check a zero Value.
Change FindLocation so it can return a substitute location expression
and propagate it to pkg/terminal/command.
When breakpoints are set using the syntax :<lineno> or +<lineno>
produce a substitute location expression that doesn't depend on having
a valid scope and can be used to restore the breakpoint.
Fixes#3423
Show the location expression that will be used to set a suspended
breakpoint in the breakpoints list.
Also change 'target' called without arguments to print a better error
message and 'target follow-exec' without the last argument to print the
state of follow-exec.
* logflags,proc: flag to log stacktrace execution
Add a log flag to write logs about what the stacktracer does.
* proc: read context from sigtrampgo, fixes TestCgoStacktrace2 on 1.21
Changes stacktrace code to read the signal context from the arguments
of sigtrampgo.
Also changes the automatic fatalthrow breakpoint for go 1.21.
In combination these two changes fix TestCgoStacktrace2 on Go 1.21 on
various platforms.
Only print the warning that gopclntab can not be read for the first
image (i.e. the executable file), also change the returned when neither
DWARF nor gopclntab are found to preserve the DWARF error.
Uprobes get automatically cleaned and removed when the reference to
the Link object is lost. Hold a reference to any active Uprobe Link
for duration of Delve execution and ensure they are cleaned up
at exit.
Fixes ebpf probes don't work after time.Sleep() #3227
We used to parse the .gopclntab section but removed support in favor of
simply using DWARF debug information, due to lack of C symbols among
other reasons. This makes it impossible to debug stripped binaries,
which some distrubutions ship by default.
Add back in basic support for .gopclntab which survives if the binary
is stripped, allowing for rudimentary debugging such as basic
program navigation, tracing, etc...
Adds a new starlark builtin 'help' that prints the list of available
builtins when called without arguments and help for the specified
builtin when passed an argument.
The help is autogenerated from godoc comments so it isn't always
exactly accurate for starlark (in particular we sometimes refer to the
In structs), but it's better than nothing.
dwarf/op gained the ability to execute DW_OP_deref opcodes a while ago
but because we didn't save the readMemory function in the context
structure it never worked.
This patch makes the time library available to Starlark scripts. This
library is one of the very few few that are built into starlark-go (the
others are json, math, proto).
I've played around with Starlark scripting today, and immediately I
wanted to measure how long certain computations take.
Using a fixed path as the default output binary means that executing
Delve twice in the same directory will cause the second invocation to
overwrite the output binary of the first instance of Delve, making the
restart command not work correctly.
Fixes#3345
* pkg/proc: pad variable mem in extractVarInfoFromEntry
On 64 bit system, the byte size of the following struct is 16:
type myStruct struct {
a int
b uint32
}
But extractVarInfoFromEntry only allocates a mem of 12 bytes for it.
When calling method of this struct with the "call" command, it will
result in this error:
write out of bounds
This patch extends the mem by adding padding bytes to the end of the
mem.
Fixes#3364.
* move the padding logic into newCompositeMemory
Go 1.21 renamed runtime._type to internal/abi.Type and changed the name
of its fields. Update Delve so that it uses the new names for loading
interfaces and generic type parameters.
Read the command line of the main target process as well as any other
process Delve attaches to in follow exec mode.
The command line can be viewed using the 'target list' command.
In follow exec mode this command line is used to match the follow exec
regex to decide whether or not to attach to a child process.
On macOS or when using rr the list of arguments is not available for
attached processes since there is no way to use the gdb serial protocol
to read it.
Fixes#2242
We can simplify the following code
dir, err := os.Open(dirname)
if err != nil {
return err
}
defer dir.Close()
dirs, err := dir.Readdir(-1)
with just `os.ReadDir(dirname)`.
Reference: https://pkg.go.dev/os#ReadDir
Signed-off-by: Eng Zer Jun <engzerjun@gmail.com>
A series of interconnected changes to both the terminal command
'config', DAP command 'dlv config', quality of life improvements to how
substitute-path works, and better documentation.
- Let 'config substitute-path' show the current substitute path rules
- Add a -clear command to 'config substitute-path'
- Support 'config-debug-info-directories'
- rewrite SubstitutePath to be platform independent (see below)
- document path substitution more
Regarding the rewrite of SubstitutePath: the previous version used
runtime.GOOS and filepath.IsAbs to determine which filepath separator to use
and if matching should be case insensitive. This is wrong in all situations
where the client and server run on different OSes, when examining core files
and when cross-compilation is involved.
The new version of SubstitutePath checks the rules and the input path to
determine if Windows is involved in the process, if it looks like it is it
switches to case-insensitive matching. It uses a lax version of
filepath.IsAbs to determine if a path is absolute and tries to avoid having
to select a path separator as much as possible
Fixes#2891, #2890, #2889, #3179, #3332, #3343
* Remove standard C headers since we have vmlinux.h already
* Simplify get_goroutine_id() implementation, this reduces a map
and thus reduces runtime memory comsumption.
While at it, unify all indention using 4 spaces.
Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
When using Step on a function that has a dynamic CALL instruction we
set a Step breakpoint on the call.
When it is hit we determine the destination of the CALL by looking at
registers, set a breakpoint there and continue.
If the Step breakpoint is hit simultaneously with a normal breakpoint
our Step logic will take precedence and the normal breakpoint hit will
be hidden from the user.
Move the Step logic to a breaklet callback so that it does not
interfere with the decision to stop.
deref'd
Fix infinite recursion if escapeCheck, at some point during its
recursion, creates an unreadable variable.
The deeper reason for this is that we evaluate function calls in a very
weird order so that we can always have stack space to store
intermediate evaluation results.
The variable 'value' happens to be stored in a register when we try to
make the call and because of our weird evaluation strategy registers
are no longer available to us when we evaluate 'value'.
This is not a complete fix for the issue, the real fix would be to
evaluate everything in its natural order, storing intermediate values
in Delve's memory instead of the target's stack. To do this we need a
mechanism to pin heap allocated objects, which at the moment does not
exist.
Updates #3310
The compiler produces ABI compatibility wrappers for some functions.
We have changed the support for breakpoints to allow a single logical
breakpoint to correspond to multiple physical breakpoints, take
advantage of that to set breakpoints on both the ABI wrapper and the
real function.
Fixes#3296
The loop adding maxAddSeconds to format a time.Time can take multiple
seconds to complete if the time is very far into the future. To avoid
this loop slowing down debugging too much limit it to an arbitrary
maximum.
The chosen maximum is 1000 times the maximum expressible time.Duration,
which is 262 years. This means that we will not format dates beyond
year 262000 AD.
Unrecovered-panic and fatal-throw were no longer part of the breakpoint
list because starting in 37e44bf they were created before the logical
breakpoints map was switched to the logical breakpoints map of the
target group.
Change generated comment header for opcodes.go to match Go regexp:
```
^// Code generated .* DO NOT EDIT\.$
```
Fix panic in gen-opcodes.go if no args provided.
Adds the ability to automatically debug child processes executed by the
target to the linux native backend.
This commit does not contain user interface or API to access this
functionality.
Updates #2551
This patch changes how we handle end_seq in the debug_line state machine
program. Instead of always considering the state machine invalid at the
end_seq instead simply consider the *current* address invalid. This
solves a number of issues such as incorrect disassemble output for the
last few instructions in certain functions, and creating an eval scope
at an address within the last few instructions of certain functions. It
also handles the case where the end_seq address is the same as the start
address of the next adjacent function, which would previously confuse
Delve which is why we initially marked end_seq as invalid for the entire
state machine. This approach is more nuanced and still solves that
initial problem while fixing some problems introduced by that patch.
* terminal/logflags: Added `SetLoggerFactory(LoggerFactory)`
This change will enable people who want to embed Delve into their applications to adjust the logging better to their needs.
* terminal/logflags: Added `SetLoggerFactory(LoggerFactory)`
Added changes from code review.
* terminal/logflags: Added `SetLoggerFactory(LoggerFactory)`
Reworked requested changes.
* terminal/logflags: Added `SetLoggerFactory(LoggerFactory)`
Reworked requested changes.
Delve no longer compiles on Go1.12 and earlier, we don't test it on
these versions and they are 4 years old and unsupported. Remove some
code related to Go 1.12 and earlier, mostly from tests.
Per https://pkg.go.dev/unsafe#Pointer conversions from unsafe.Pointer
to uintptr are only safe in limited circumstances. In particular only
conversions made in the syscall call are pinned.
Additionally add a call to runtime.KeepAlive to mitigate the bug
described in: https://github.com/golang/go/issues/58351
Previously it was only possible to extract a value of type `any` using
an attribute name. This poses challenges when fields are allowed to have
different classes, and it is ambiguous how to handle them.
Fixes a bug where we cannot get locals (including arguments and return
values) from a given scope because the line number state machine ends up
in an invalid state because of this parameter being set to false.
Instead of using a fixed 100x30 window size query the operating system
for the exact size, also fixes a bug where the last line before calling
the pager is repeated twice.
This patch allows users to set a breakpoint even when the process has
exited. It will be left in a pending state until the process is
restarted.
Fixes#3242
The typical convention with `[Y/n]` type command line questions
is that the capitalized letter represents the default if the user
simply hits "enter" instead of typing an actual response.
This patch fixes our implementation to use the implied default response.
New config "tab" allows user to set a string instead of literal tab
(e.g. "... ").
New config "source-list-tab-color" allows that string to be colored.
This builds on top of the `updateColorScheme` change
* proc: add a test for dangling unsafe pointers
This new tests checks the behavior when dereferencing dangling pointers.
The behavior does not fully make sense; the test checks the current
behavior for now, which will be improved in subsequent commits.
* proc: populate pointer values
This patch changes how Value and Unreadable are populated for pointer
Variables. Before this patch, variables of kind reflect.Ptr did not have
their Value field populated. This patch populates it in
Variable.loadValue(), which seems natural and consistent with other
types of variables. The Value is the address that the pointer points to.
The Unreadable field was populated inconsistently for pointer variables:
it was never populated for an outer pointer, but it could be populated
for an inner pointer in pointer-to-pointer types. Before this patch,
in pointer whose value could not be read was not easily distinguishable
from a pointer with a value that could be read, but that cannot be
dereferenced (i.e. a dangling pointer): neither of these would be marked
as Unreadable, and both would have a child marked as Unreadable. This
patch makes it so that a pointer variable whose pointer value cannot be
read is marked as Unreadable.
Using this new distinction, this patch fixes a bug around dereferencing
dangling pointers: before, attempting such a dereference produced a
"nil pointer dereference" error. This was bogus, since the pointer was
not nil. Now, we are more discerning and generate a different error.
Parsing the source list color when set during a Delve debug session
resulted in unexpected errors. Additionally the changes were not reflected
in the current session, forcing the user to save the config and start a
new session. This patch fixes those issues.
