Well, for the READ_ONCE() actually I'm wrong, it's overloaded for Alpha and arm64 https://elixir.bootlin.com/linux/latest/C/ident/__READ_ONCE
On 13/09/2023 13:22, Andy Shevchenko wrote:
On Wed, Sep 13, 2023 at 11:04:00AM +0200, Yann Sionneau wrote:To my knowledge the READ_ONCE()/WRITE_ONCE() only imply the use of volatile to access memory thus preventing the compiler to do weird optimizations like merging store/loads, moving store/loads, removing them etc
On 13/09/2023 03:03, Jan Bottorff wrote:...
If this is the case, shouldn't we rather use READ_ONCE()/WRITE_ONCE() where+ /*Apart from the commit message it looks good to me.
+ * To guarantee data written by the current core is visible to
+ * all cores, a write barrier is required. This needs to be
+ * before an interrupt causes execution on another core.
+ * For ARM processors, this needs to be a DSB barrier.
+ */
+ wmb();
If I understand correctly without this wmb() it is possible that the writes
to dev->msg_write_idx , dev->msg_read_idx = 0 etc would not yet be visible
to another CPU running the ISR handler right after enabling those.
appropriate?
They don't imply a memory barrier.
Some systems need a memory barrier, to emit a "fence" like instruction, so that the pipeline stalls waiting for the store to "finish", for systems where the writes are posted.
Regards,