[v2,3/3] vhost: optimize vhost virtqueue struct
Checks
Commit Message
This patch moves vhost_virtuqueue struct fields in order
to both optimize packing and move hot fields on the first
cachelines.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
lib/librte_vhost/vhost.h | 52 +++++++++++++++++++++-------------------
1 file changed, 27 insertions(+), 25 deletions(-)
Comments
On Tue, Mar 16, 2021 at 1:42 PM Maxime Coquelin
<maxime.coquelin@redhat.com> wrote:
>
> This patch moves vhost_virtuqueue struct fields in order
virtqueue
You might want to add something in your local dictionary :-p.
> to both optimize packing and move hot fields on the first
> cachelines.
>
> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> ---
> lib/librte_vhost/vhost.h | 52 +++++++++++++++++++++-------------------
> 1 file changed, 27 insertions(+), 25 deletions(-)
>
> diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
> index 3a71dfeed9..ae45b05dd1 100644
> --- a/lib/librte_vhost/vhost.h
> +++ b/lib/librte_vhost/vhost.h
> @@ -133,7 +133,7 @@ struct vhost_virtqueue {
> struct vring_used *used;
> struct vring_packed_desc_event *device_event;
> };
> - uint32_t size;
> + uint16_t size;
There is one site in the code that could be problematic:
vhost_user_set_vring_num()
...
vq->size = msg->payload.state.num;
...
if (vq->size > 32768) {
payload.state.num is an unsigned int, so we'd better check its value
as an unsigned int, before storing to vq->size.
>
> uint16_t last_avail_idx;
> uint16_t last_used_idx;
> @@ -143,29 +143,12 @@ struct vhost_virtqueue {
> #define VIRTIO_INVALID_EVENTFD (-1)
> #define VIRTIO_UNINITIALIZED_EVENTFD (-2)
>
> - int enabled;
> - int access_ok;
> - int ready;
> - int notif_enable;
> -#define VIRTIO_UNINITIALIZED_NOTIF (-1)
> + bool enabled;
> + bool access_ok;
> + bool ready;
Changing those types is fine, but it is a bit odd to still see
boolean_var = 0 or boolean_var = 1 in the rest of the code.
>
> rte_spinlock_t access_lock;
>
> - /* Used to notify the guest (trigger interrupt) */
> - int callfd;
> - /* Currently unused as polling mode is enabled */
> - int kickfd;
> -
> - /* Physical address of used ring, for logging */
> - uint64_t log_guest_addr;
> -
> - /* inflight share memory info */
> - union {
> - struct rte_vhost_inflight_info_split *inflight_split;
> - struct rte_vhost_inflight_info_packed *inflight_packed;
> - };
> - struct rte_vhost_resubmit_info *resubmit_inflight;
> - uint64_t global_counter;
>
> union {
> struct vring_used_elem *shadow_used_split;
> @@ -176,22 +159,36 @@ struct vhost_virtqueue {
> uint16_t shadow_aligned_idx;
> /* Record packed ring first dequeue desc index */
> uint16_t shadow_last_used_idx;
> - struct vhost_vring_addr ring_addrs;
>
> - struct batch_copy_elem *batch_copy_elems;
> uint16_t batch_copy_nb_elems;
> + struct batch_copy_elem *batch_copy_elems;
> bool used_wrap_counter;
> bool avail_wrap_counter;
>
> - struct log_cache_entry *log_cache;
> + /* Physical address of used ring, for logging */
> uint16_t log_cache_nb_elem;
Indent is broken / not consistent, probably because you cut/pasted lines.
> + uint64_t log_guest_addr;
> + struct log_cache_entry *log_cache;
>
> rte_rwlock_t iotlb_lock;
> rte_rwlock_t iotlb_pending_lock;
> struct rte_mempool *iotlb_pool;
> TAILQ_HEAD(, vhost_iotlb_entry) iotlb_list;
> - int iotlb_cache_nr;
> TAILQ_HEAD(, vhost_iotlb_entry) iotlb_pending_list;
> + int iotlb_cache_nr;
> +
> + /* Used to notify the guest (trigger interrupt) */
> + int callfd;
> + /* Currently unused as polling mode is enabled */
> + int kickfd;
> +
> + /* inflight share memory info */
> + union {
> + struct rte_vhost_inflight_info_split *inflight_split;
> + struct rte_vhost_inflight_info_packed *inflight_packed;
> + };
> + struct rte_vhost_resubmit_info *resubmit_inflight;
> + uint64_t global_counter;
>
> /* operation callbacks for async dma */
> struct rte_vhost_async_channel_ops async_ops;
> @@ -212,6 +209,11 @@ struct vhost_virtqueue {
> bool async_inorder;
> bool async_registered;
> uint16_t async_threshold;
> +
> + int notif_enable;
> +#define VIRTIO_UNINITIALIZED_NOTIF (-1)
> +
> + struct vhost_vring_addr ring_addrs;
> } __rte_cache_aligned;
>
> /* Virtio device status as per Virtio specification */
> --
> 2.29.2
>
On 3/16/21 2:38 PM, David Marchand wrote:
> On Tue, Mar 16, 2021 at 1:42 PM Maxime Coquelin
> <maxime.coquelin@redhat.com> wrote:
>>
>> This patch moves vhost_virtuqueue struct fields in order
>
> virtqueue
> You might want to add something in your local dictionary :-p.
>
>
>> to both optimize packing and move hot fields on the first
>> cachelines.
>>
>> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
>> ---
>> lib/librte_vhost/vhost.h | 52 +++++++++++++++++++++-------------------
>> 1 file changed, 27 insertions(+), 25 deletions(-)
>>
>> diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
>> index 3a71dfeed9..ae45b05dd1 100644
>> --- a/lib/librte_vhost/vhost.h
>> +++ b/lib/librte_vhost/vhost.h
>> @@ -133,7 +133,7 @@ struct vhost_virtqueue {
>> struct vring_used *used;
>> struct vring_packed_desc_event *device_event;
>> };
>> - uint32_t size;
>> + uint16_t size;
>
> There is one site in the code that could be problematic:
>
> vhost_user_set_vring_num()
> ...
> vq->size = msg->payload.state.num;
> ...
> if (vq->size > 32768) {
>
> payload.state.num is an unsigned int, so we'd better check its value
> as an unsigned int, before storing to vq->size.
Indeed, I will rework the function, so that it checks that
msg->payload.state.num is smaller than 32K to comply with the spec,
and so remove the later check on vq->size.
>
>>
>> uint16_t last_avail_idx;
>> uint16_t last_used_idx;
>> @@ -143,29 +143,12 @@ struct vhost_virtqueue {
>> #define VIRTIO_INVALID_EVENTFD (-1)
>> #define VIRTIO_UNINITIALIZED_EVENTFD (-2)
>>
>> - int enabled;
>> - int access_ok;
>> - int ready;
>> - int notif_enable;
>> -#define VIRTIO_UNINITIALIZED_NOTIF (-1)
>> + bool enabled;
>> + bool access_ok;
>> + bool ready;
>
> Changing those types is fine, but it is a bit odd to still see
> boolean_var = 0 or boolean_var = 1 in the rest of the code.
Yes, I fix all the places with assigning boolean values.
>
>>
>> rte_spinlock_t access_lock;
>>
>> - /* Used to notify the guest (trigger interrupt) */
>> - int callfd;
>> - /* Currently unused as polling mode is enabled */
>> - int kickfd;
>> -
>> - /* Physical address of used ring, for logging */
>> - uint64_t log_guest_addr;
>> -
>> - /* inflight share memory info */
>> - union {
>> - struct rte_vhost_inflight_info_split *inflight_split;
>> - struct rte_vhost_inflight_info_packed *inflight_packed;
>> - };
>> - struct rte_vhost_resubmit_info *resubmit_inflight;
>> - uint64_t global_counter;
>>
>> union {
>> struct vring_used_elem *shadow_used_split;
>> @@ -176,22 +159,36 @@ struct vhost_virtqueue {
>> uint16_t shadow_aligned_idx;
>> /* Record packed ring first dequeue desc index */
>> uint16_t shadow_last_used_idx;
>> - struct vhost_vring_addr ring_addrs;
>>
>> - struct batch_copy_elem *batch_copy_elems;
>> uint16_t batch_copy_nb_elems;
>> + struct batch_copy_elem *batch_copy_elems;
>> bool used_wrap_counter;
>> bool avail_wrap_counter;
>>
>> - struct log_cache_entry *log_cache;
>> + /* Physical address of used ring, for logging */
>> uint16_t log_cache_nb_elem;
>
> Indent is broken / not consistent, probably because you cut/pasted lines.
Will fix it.
Thanks,
Maxime
@@ -133,7 +133,7 @@ struct vhost_virtqueue {
struct vring_used *used;
struct vring_packed_desc_event *device_event;
};
- uint32_t size;
+ uint16_t size;
uint16_t last_avail_idx;
uint16_t last_used_idx;
@@ -143,29 +143,12 @@ struct vhost_virtqueue {
#define VIRTIO_INVALID_EVENTFD (-1)
#define VIRTIO_UNINITIALIZED_EVENTFD (-2)
- int enabled;
- int access_ok;
- int ready;
- int notif_enable;
-#define VIRTIO_UNINITIALIZED_NOTIF (-1)
+ bool enabled;
+ bool access_ok;
+ bool ready;
rte_spinlock_t access_lock;
- /* Used to notify the guest (trigger interrupt) */
- int callfd;
- /* Currently unused as polling mode is enabled */
- int kickfd;
-
- /* Physical address of used ring, for logging */
- uint64_t log_guest_addr;
-
- /* inflight share memory info */
- union {
- struct rte_vhost_inflight_info_split *inflight_split;
- struct rte_vhost_inflight_info_packed *inflight_packed;
- };
- struct rte_vhost_resubmit_info *resubmit_inflight;
- uint64_t global_counter;
union {
struct vring_used_elem *shadow_used_split;
@@ -176,22 +159,36 @@ struct vhost_virtqueue {
uint16_t shadow_aligned_idx;
/* Record packed ring first dequeue desc index */
uint16_t shadow_last_used_idx;
- struct vhost_vring_addr ring_addrs;
- struct batch_copy_elem *batch_copy_elems;
uint16_t batch_copy_nb_elems;
+ struct batch_copy_elem *batch_copy_elems;
bool used_wrap_counter;
bool avail_wrap_counter;
- struct log_cache_entry *log_cache;
+ /* Physical address of used ring, for logging */
uint16_t log_cache_nb_elem;
+ uint64_t log_guest_addr;
+ struct log_cache_entry *log_cache;
rte_rwlock_t iotlb_lock;
rte_rwlock_t iotlb_pending_lock;
struct rte_mempool *iotlb_pool;
TAILQ_HEAD(, vhost_iotlb_entry) iotlb_list;
- int iotlb_cache_nr;
TAILQ_HEAD(, vhost_iotlb_entry) iotlb_pending_list;
+ int iotlb_cache_nr;
+
+ /* Used to notify the guest (trigger interrupt) */
+ int callfd;
+ /* Currently unused as polling mode is enabled */
+ int kickfd;
+
+ /* inflight share memory info */
+ union {
+ struct rte_vhost_inflight_info_split *inflight_split;
+ struct rte_vhost_inflight_info_packed *inflight_packed;
+ };
+ struct rte_vhost_resubmit_info *resubmit_inflight;
+ uint64_t global_counter;
/* operation callbacks for async dma */
struct rte_vhost_async_channel_ops async_ops;
@@ -212,6 +209,11 @@ struct vhost_virtqueue {
bool async_inorder;
bool async_registered;
uint16_t async_threshold;
+
+ int notif_enable;
+#define VIRTIO_UNINITIALIZED_NOTIF (-1)
+
+ struct vhost_vring_addr ring_addrs;
} __rte_cache_aligned;
/* Virtio device status as per Virtio specification */