[DTrace-devel] [PATCH] sparc: remove architecture support

[Eugene Loh]

In test/unittest/usdt/tst.enabled2.sh and 
test/unittest/aggs/tst.neglquant.d, there are SPARC comments that read 
funny in the absence of any SPARC support.

Should libdtrace/sparc/regs.d and include/sparc/platform.h be removed?

On 3/4/26 13:50, Kris Van Hees via DTrace-devel wrote:

> diff --git a/COMMANDLINE-OPTIONS b/COMMANDLINE-OPTIONS

Okay, but this file also has the line "All options are believed to work 
equally well on all supported architectures (x86 and SPARC)." How about 
s/SPARC/ARM/?

> diff --git a/GNUmakefile b/GNUmakefile
> @@ -20,8 +20,8 @@ VERSION := $(shell ./libdtrace/mkvers -vcurrent=t libdtrace/versions.list)
>   
>   ARCH := $(shell uname -m)
>   
> -$(if $(subst sparc64,,$(subst aarch64,,$(subst x86_64,,$(ARCH)))), \
> -    $(error "Error: DTrace for Linux only supports x86_64, ARM64 and sparc64"),)
> +$(if $(subst aarch64,,$(subst x86_64,,$(ARCH))), \
> +    $(error "Error: DTrace for Linux currently only supports x86_64, ARM64"),)

Okay, but how about s/x86_64, ARM64/x86_64 and ARM64/?

>   $(if $(subst Linux,,$(shell uname -s)), \
>       $(error "Error: DTrace only supports Linux"),)
>   
> diff --git a/libdtrace/procfs.d.in b/libdtrace/procfs.d.in
> index 23454d63..6a0e0122 100644
> --- a/libdtrace/procfs.d.in
> +++ b/libdtrace/procfs.d.in
> @@ -286,8 +286,7 @@ define_for_kernel([[on_cpu]], [[(m4_kver(5,16,0), m4_dnl
>     [[((struct thread_info *)T->stack)->cpu]]), m4_dnl
>   (m4_kver(4,9,0), m4_dnl
>     [[if_arch([[x86]],[[T->cpu]])]] m4_dnl
> -  [[if_arch([[arm64]],[[T->cpu]])]] m4_dnl
> -  [[if_arch([[sparc]],[[((struct thread_info *)T->stack)->cpu]])]])]], m4_dnl
> +  [[if_arch([[arm64]],[[T->cpu]])]]l)]], m4_dnl
>   [[((struct thread_info *)T->stack)->cpu]])m4_dnl
>   	pr_onpro = on_cpu;
>   };

I can't read M4, but maybe that diff is suspicious?  This is what gpt 
5.2 says:

### USER
Does the following diff in an m4 file make sense?  Are brackets still 
balanced?
@@ -286,8 +286,7 @@ define_for_kernel([[on_cpu]], [[(m4_kver(5,16,0), m4_dnl
    [[((struct thread_info *)T->stack)->cpu]]), m4_dnl
(m4_kver(4,9,0), m4_dnl
    [[if_arch([[x86]],[[T->cpu]])]] m4_dnl
-  [[if_arch([[arm64]],[[T->cpu]])]] m4_dnl
-  [[if_arch([[sparc]],[[((struct thread_info *)T->stack)->cpu]])]])]], 
m4_dnl
+  [[if_arch([[arm64]],[[T->cpu]])]]l)]], m4_dnl
[[((struct thread_info *)T->stack)->cpu]])m4_dnl
         pr_onpro = on_cpu;
};

### ASSISTANT
No — as shown, that diff does **not** make sense, and the 
brackets/parentheses are very likely **not balanced** anymore (and 
there’s also an obvious stray character).

### What looks wrong

1. **Stray `l` and unmatched delimiters**
    ```
    [[if_arch([[arm64]],[[T->cpu]])]]l)]], m4_dnl
                               ^^^
    ```
    That `l)` sequence is almost certainly accidental. It also strongly 
suggests you now have an extra `)` and/or `]` compared to what was intended.

2. **You removed the `sparc` branch and spliced the “default” expression 
oddly**
    Originally you had:
    ```
    ... [[if_arch([[arm64]],[[T->cpu]])]] m4_dnl
        [[if_arch([[sparc]],[[((struct thread_info 
*)T->stack)->cpu]])]])]], m4_dnl
    ```
    That last line clearly closes a number of nested `[[ ... ]]` / 
`(...)` constructs.

    In the new version, you have:
    ```
    [[if_arch([[arm64]],[[T->cpu]])]]l)]], m4_dnl
    [[((struct thread_info *)T->stack)->cpu]])m4_dnl
    ```
    The “default” `[[((struct thread_info *)T->stack)->cpu]]` expression 
now appears outside of the previous nesting, and the closers that used 
to be on the `sparc` line are now partially (and incorrectly) attached 
to the `arm64` line.

3. **`m4_dnl` placement**
    `m4_dnl` comments out the rest of the line. Moving delimiters to a 
new line while also changing where `m4_dnl` lands can easily break 
balanced delimiters, because closers might end up being “commented away” 
or no longer part of the intended argument.

### Practical conclusion
- **Brackets are almost certainly unbalanced** after this edit.
- The diff as shown looks like a broken manual edit (typo + moved closers).

### What to do next
- If your intent was only to remove the `sparc` case, the safe approach 
is: remove just that `if_arch([[sparc]]...)` fragment but keep the 
closing `]])]],` structure intact (i.e., don’t move closers onto other 
lines).
- Run `m4` on the file (or whatever build step consumes it) and expect 
it to fail with a quoting/argument/parenthesis error if this is truly 
the current state.

If you paste ~10–20 lines around this macro (before/after), I can tell 
you exactly where the missing/extra `[[` / `]]` / `(` / `)` are and 
suggest a corrected minimal diff.