From 71b38245acb05a38d2d861792bdd99cd9f6a0f78 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Tue, 5 Jun 2018 13:37:51 -0700 Subject: Drivers: hv: vmbus: Add comments on ring buffer signaling Add comments describing intricacies of Hyper-V ring buffer signaling code. This information is not in Hyper-V public documents, so include here to capture the knowledge for future coders. There are no code changes in this commit. Signed-off-by: Michael Kelley Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- drivers/hv/ring_buffer.c | 65 ++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 54 insertions(+), 11 deletions(-) (limited to 'drivers') diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index be3c8b10b84a..3e90eb91db45 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -431,7 +431,24 @@ static u32 hv_pkt_iter_bytes_read(const struct hv_ring_buffer_info *rbi, } /* - * Update host ring buffer after iterating over packets. + * Update host ring buffer after iterating over packets. If the host has + * stopped queuing new entries because it found the ring buffer full, and + * sufficient space is being freed up, signal the host. But be careful to + * only signal the host when necessary, both for performance reasons and + * because Hyper-V protects itself by throttling guests that signal + * inappropriately. + * + * Determining when to signal is tricky. There are three key data inputs + * that must be handled in this order to avoid race conditions: + * + * 1. Update the read_index + * 2. Read the pending_send_sz + * 3. Read the current write_index + * + * The interrupt_mask is not used to determine when to signal. The + * interrupt_mask is used only on the guest->host ring buffer when + * sending requests to the host. The host does not use it on the host-> + * guest ring buffer to indicate whether it should be signaled. */ void hv_pkt_iter_close(struct vmbus_channel *channel) { @@ -447,22 +464,30 @@ void hv_pkt_iter_close(struct vmbus_channel *channel) start_read_index = rbi->ring_buffer->read_index; rbi->ring_buffer->read_index = rbi->priv_read_index; + /* + * Older versions of Hyper-V (before WS2102 and Win8) do not + * implement pending_send_sz and simply poll if the host->guest + * ring buffer is full. No signaling is needed or expected. + */ if (!rbi->ring_buffer->feature_bits.feat_pending_send_sz) return; /* * Issue a full memory barrier before making the signaling decision. - * Here is the reason for having this barrier: - * If the reading of the pend_sz (in this function) - * were to be reordered and read before we commit the new read - * index (in the calling function) we could - * have a problem. If the host were to set the pending_sz after we - * have sampled pending_sz and go to sleep before we commit the + * If reading pending_send_sz were to be reordered and happen + * before we commit the new read_index, a race could occur. If the + * host were to set the pending_send_sz after we have sampled + * pending_send_sz, and the ring buffer blocks before we commit the * read index, we could miss sending the interrupt. Issue a full * memory barrier to address this. */ virt_mb(); + /* + * If the pending_send_sz is zero, then the ring buffer is not + * blocked and there is no need to signal. This is far by the + * most common case, so exit quickly for best performance. + */ pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz); if (!pending_sz) return; @@ -476,14 +501,32 @@ void hv_pkt_iter_close(struct vmbus_channel *channel) bytes_read = hv_pkt_iter_bytes_read(rbi, start_read_index); /* - * If there was space before we began iteration, - * then host was not blocked. + * We want to signal the host only if we're transitioning + * from a "not enough free space" state to a "enough free + * space" state. For example, it's possible that this function + * could run and free up enough space to signal the host, and then + * run again and free up additional space before the host has a + * chance to clear the pending_send_sz. The 2nd invocation would + * be a null transition from "enough free space" to "enough free + * space", which doesn't warrant a signal. + * + * Exactly filling the ring buffer is treated as "not enough + * space". The ring buffer always must have at least one byte + * empty so the empty and full conditions are distinguishable. + * hv_get_bytes_to_write() doesn't fully tell the truth in + * this regard. + * + * So first check if we were in the "enough free space" state + * before we began the iteration. If so, the host was not + * blocked, and there's no need to signal. */ - if (curr_write_sz - bytes_read > pending_sz) return; - /* If pending write will not fit, don't give false hope. */ + /* + * Similarly, if the new state is "not enough space", then + * there's no need to signal. + */ if (curr_write_sz <= pending_sz) return; -- cgit v1.2.3