> +static void gsi_trans_tre_fill(struct gsi_tre *dest_tre, dma_addr_t addr,
> + u32 len, bool last_tre, bool bei,
> + enum ipa_cmd_opcode opcode)
> +{
> + struct gsi_tre tre;
> +
> + tre.addr = cpu_to_le64(addr);
> + tre.len_opcode = gsi_tre_len_opcode(opcode, len);
> + tre.reserved = 0;
> + tre.flags = gsi_tre_flags(last_tre, bei, opcode);
> +
> + *dest_tre = tre; /* Write TRE as a single (16-byte) unit */
> +}
Have you checked that the atomic write is actually what happens here,
but looking at the compiler output? You might need to add a 'volatile'
qualifier to the dest_tre argument so the temporary structure doesn't
get optimized away here.
> +/* Cancel a channel's pending transactions */
> +void gsi_channel_trans_cancel_pending(struct gsi_channel *channel)
> +{
> + struct gsi_trans_info *trans_info = &channel->trans_info;
> + u32 evt_ring_id = channel->evt_ring_id;
> + struct gsi *gsi = channel->gsi;
> + struct gsi_evt_ring *evt_ring;
> + struct gsi_trans *trans;
> + unsigned long flags;
> +
> + evt_ring = &gsi->evt_ring[evt_ring_id];
> +
> + spin_lock_irqsave(&evt_ring->ring.spinlock, flags);
> +
> + list_for_each_entry(trans, &trans_info->pending, links)
> + trans->result = -ECANCELED;
> +
> + list_splice_tail_init(&trans_info->pending, &trans_info->complete);
> +
> + spin_unlock_irqrestore(&evt_ring->ring.spinlock, flags);
> +
> + spin_lock_irqsave(&gsi->spinlock, flags);
> +
> + if (gsi->event_enable_bitmap & BIT(evt_ring_id))
> + gsi_event_handle(gsi, evt_ring_id);
> +
> + spin_unlock_irqrestore(&gsi->spinlock, flags);
> +}
That is a lot of irqsave()/irqrestore() operations. Do you actually call
all of these functions from hardirq context?
Arnd
