[RISCV] Mark More Fatal Errors as Usage/Internal (#154876)
We have lots of uses of `report_fatal_error` in the backend, which will
result in a crash and a backtrace. This API has been replaced with
`reportFatalUsageError` and `reportFatalInternalError`, for which only
the latter emits a stack trace.
This tries to move the errors in RISCVISelLowering and RISCVRegisterInfo
to the new APIs, to prevent some stack traces where we specificially do
not support certain situations.
Updates #124132
