Regression in `MemoryError` displaying (`_PyErr_Display` fallback to C impl of `print_exception`)

[chgnrdv]

Bug report

Bug description:

After e733136:

>>> raise MemoryError()
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
object address  : 0x7fd3b6037540
object refcount : 3
object type     : 0x556d6e04cf40
object type name: MemoryError
object repr     : MemoryError()
lost sys.stderr

cc @pablogsal

CPython versions tested on:

CPython main branch

Operating systems tested on:

Linux

Linked PRs

• gh-110912: Correctly display tracebacks for MemoryError exceptions using the traceback module #110921

[serhiy-storchaka]

Seen this with real MemoryError, but I thought it was because the error handler couldn't run when out of memory. But if it produces this for an artificial MemoryError, something is very wrong.

[pablogsal]

Seen this with real MemoryError, but I thought it was because the error handler couldn't run when out of memory. But if it produces this for an artificial MemoryError, something is very wrong.

This was caused by an (incorrect) forceful fallback to the C implementation of the traceback machinery after we switched to use the Python traceback module as the main mechanism. Fixed in #110921