Commit 71b38245 authored by Michael Kelley's avatar Michael Kelley Committed by Greg Kroah-Hartman

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: default avatarMichael Kelley <mikelley@microsoft.com>
Signed-off-by: default avatarK. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: default avatarGreg Kroah-Hartman <gregkh@linuxfoundation.org>
parent e9a7fda2
...@@ -431,7 +431,24 @@ static u32 hv_pkt_iter_bytes_read(const struct hv_ring_buffer_info *rbi, ...@@ -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) void hv_pkt_iter_close(struct vmbus_channel *channel)
{ {
...@@ -447,22 +464,30 @@ 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; start_read_index = rbi->ring_buffer->read_index;
rbi->ring_buffer->read_index = rbi->priv_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) if (!rbi->ring_buffer->feature_bits.feat_pending_send_sz)
return; return;
/* /*
* Issue a full memory barrier before making the signaling decision. * Issue a full memory barrier before making the signaling decision.
* Here is the reason for having this barrier: * If reading pending_send_sz were to be reordered and happen
* If the reading of the pend_sz (in this function) * before we commit the new read_index, a race could occur. If the
* were to be reordered and read before we commit the new read * host were to set the pending_send_sz after we have sampled
* index (in the calling function) we could * pending_send_sz, and the ring buffer blocks before we commit the
* 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
* read index, we could miss sending the interrupt. Issue a full * read index, we could miss sending the interrupt. Issue a full
* memory barrier to address this. * memory barrier to address this.
*/ */
virt_mb(); 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); pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz);
if (!pending_sz) if (!pending_sz)
return; return;
...@@ -476,14 +501,32 @@ void hv_pkt_iter_close(struct vmbus_channel *channel) ...@@ -476,14 +501,32 @@ void hv_pkt_iter_close(struct vmbus_channel *channel)
bytes_read = hv_pkt_iter_bytes_read(rbi, start_read_index); bytes_read = hv_pkt_iter_bytes_read(rbi, start_read_index);
/* /*
* If there was space before we began iteration, * We want to signal the host only if we're transitioning
* then host was not blocked. * 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) if (curr_write_sz - bytes_read > pending_sz)
return; 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) if (curr_write_sz <= pending_sz)
return; return;
......
...@@ -89,18 +89,33 @@ struct hv_ring_buffer { ...@@ -89,18 +89,33 @@ struct hv_ring_buffer {
u32 interrupt_mask; u32 interrupt_mask;
/* /*
* Win8 uses some of the reserved bits to implement * WS2012/Win8 and later versions of Hyper-V implement interrupt
* interrupt driven flow management. On the send side * driven flow management. The feature bit feat_pending_send_sz
* we can request that the receiver interrupt the sender * is set by the host on the host->guest ring buffer, and by the
* when the ring transitions from being full to being able * guest on the guest->host ring buffer.
* to handle a message of size "pending_send_sz".
* *
* Add necessary state for this enhancement. * The meaning of the feature bit is a bit complex in that it has
* semantics that apply to both ring buffers. If the guest sets
* the feature bit in the guest->host ring buffer, the guest is
* telling the host that:
* 1) It will set the pending_send_sz field in the guest->host ring
* buffer when it is waiting for space to become available, and
* 2) It will read the pending_send_sz field in the host->guest
* ring buffer and interrupt the host when it frees enough space
*
* Similarly, if the host sets the feature bit in the host->guest
* ring buffer, the host is telling the guest that:
* 1) It will set the pending_send_sz field in the host->guest ring
* buffer when it is waiting for space to become available, and
* 2) It will read the pending_send_sz field in the guest->host
* ring buffer and interrupt the guest when it frees enough space
*
* If either the guest or host does not set the feature bit that it
* owns, that guest or host must do polling if it encounters a full
* ring buffer, and not signal the other end with an interrupt.
*/ */
u32 pending_send_sz; u32 pending_send_sz;
u32 reserved1[12]; u32 reserved1[12];
union { union {
struct { struct {
u32 feat_pending_send_sz:1; u32 feat_pending_send_sz:1;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment