diff options
| author |   zhenwei pi <pizhenwei@bytedance.com> | 2022-05-06 21:16:25 +0800 |
|---|---|---|
| committer |   Michael S. Tsirkin <mst@redhat.com> | 2022-05-31 12:45:09 -0400 |
| commit | 977231e8d45657871a86fe3c7bed94921d04e447 (patch) | |
| tree | aef2e17dcba635fcb0a324edc0b7ed6b922c9793 /drivers/crypto/virtio/virtio_crypto_common.h | |
| parent | virtio-crypto: use private buffer for control request (diff) | |
| download | linux-dev-977231e8d45657871a86fe3c7bed94921d04e447.tar.xz linux-dev-977231e8d45657871a86fe3c7bed94921d04e447.zip | |
virtio-crypto: wait ctrl queue instead of busy polling
Originally, after submitting request into virtio crypto control
queue, the guest side polls the result from the virt queue. This
works like following:
CPU0 CPU1 ... CPUx CPUy
| | | |
\ \ / /
\--------spin_lock(&vcrypto->ctrl_lock)-------/
|
virtqueue add & kick
|
busy poll virtqueue
|
spin_unlock(&vcrypto->ctrl_lock)
...
There are two problems:
1, The queue depth is always 1, the performance of a virtio crypto
device gets limited. Multi user processes share a single control
queue, and hit spin lock race from control queue. Test on Intel
Platinum 8260, a single worker gets ~35K/s create/close session
operations, and 8 workers get ~40K/s operations with 800% CPU
utilization.
2, The control request is supposed to get handled immediately, but
in the current implementation of QEMU(v6.2), the vCPU thread kicks
another thread to do this work, the latency also gets unstable.
Tracking latency of virtio_crypto_alg_akcipher_close_session in 5s:
usecs : count distribution
0 -> 1 : 0 | |
2 -> 3 : 7 | |
4 -> 7 : 72 | |
8 -> 15 : 186485 |************************|
16 -> 31 : 687 | |
32 -> 63 : 5 | |
64 -> 127 : 3 | |
128 -> 255 : 1 | |
256 -> 511 : 0 | |
512 -> 1023 : 0 | |
1024 -> 2047 : 0 | |
2048 -> 4095 : 0 | |
4096 -> 8191 : 0 | |
8192 -> 16383 : 2 | |
This means that a CPU may hold vcrypto->ctrl_lock as long as 8192~16383us.
To improve the performance of control queue, a request on control queue
waits completion instead of busy polling to reduce lock racing, and gets
completed by control queue callback.
CPU0 CPU1 ... CPUx CPUy
| | | |
\ \ / /
\--------spin_lock(&vcrypto->ctrl_lock)-------/
|
virtqueue add & kick
|
---------spin_unlock(&vcrypto->ctrl_lock)------
/ / \ \
| | | |
wait wait wait wait
Test this patch, the guest side get ~200K/s operations with 300% CPU
utilization.
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Gonglei <arei.gonglei@huawei.com>
Reviewed-by: Gonglei <arei.gonglei@huawei.com>
Signed-off-by: zhenwei pi <pizhenwei@bytedance.com>
Message-Id: <20220506131627.180784-4-pizhenwei@bytedance.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Diffstat (limited to 'drivers/crypto/virtio/virtio_crypto_common.h')
| -rw-r--r-- | drivers/crypto/virtio/virtio_crypto_common.h | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/drivers/crypto/virtio/virtio_crypto_common.h b/drivers/crypto/virtio/virtio_crypto_common.h index 2422237ec4e6..59a4c0259456 100644 --- a/drivers/crypto/virtio/virtio_crypto_common.h +++ b/drivers/crypto/virtio/virtio_crypto_common.h @@ -90,6 +90,7 @@ struct virtio_crypto_ctrl_request { struct virtio_crypto_op_ctrl_req ctrl; struct virtio_crypto_session_input input; struct virtio_crypto_inhdr ctrl_status; + struct completion compl; }; struct virtio_crypto_request; @@ -141,5 +142,8 @@ int virtio_crypto_skcipher_algs_register(struct virtio_crypto *vcrypto); void virtio_crypto_skcipher_algs_unregister(struct virtio_crypto *vcrypto); int virtio_crypto_akcipher_algs_register(struct virtio_crypto *vcrypto); void virtio_crypto_akcipher_algs_unregister(struct virtio_crypto *vcrypto); +int virtio_crypto_ctrl_vq_request(struct virtio_crypto *vcrypto, struct scatterlist *sgs[], + unsigned int out_sgs, unsigned int in_sgs, + struct virtio_crypto_ctrl_request *vc_ctrl_req); #endif /* _VIRTIO_CRYPTO_COMMON_H */ |