Hi Philipp,
The code might be taking advantage of the fact that on some architectures,
reads and writes to aligned words are atomic, meaning the spinlock might
not be required for the loop.
From the snippet, it looks like a mutual-exclusion mechanism—only one thread
of execution is allowed to
Hi Frank,
On 4/30/23 15:20, Frank Oltmanns wrote:
Hi Philipp,
I'm a kernel newbie myself (but a senior software developer) and I
haven't actually looked up the source, other then the part you cited, so
please take the following with a grain of salt.
On 2023-04-30 at 10:31:09 +0200, Philipp