crypto: hisilicon/zip - Optimize performance by replacing rw_lock with spinlock

The req_lock is currently implemented as a rw_lock, but there are no
instances where read_lock() is called. This means that the lock is
effectively only used by writers, making it functionally equivalent to
a simple spinlock.

As stated in Documentation/locking/spinlocks.rst:
"Reader-writer locks require more atomic memory operations than simple
spinlocks. Unless the reader critical section is long, you are better
off just using spinlocks."

Since the rw_lock in this case incurs additional atomic memory
operations without any benefit from reader-writer locking, it is more
efficient to replace it with a spinlock. This patch implements that
replacement to optimize the driver's performance.

Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This commit is contained in:
Kuan-Wei Chiu 2024-08-24 02:38:56 +08:00 committed by Herbert Xu
parent 407f8cf8e6
commit be9c336852

View File

@ -54,7 +54,7 @@ struct hisi_zip_req {
struct hisi_zip_req_q { struct hisi_zip_req_q {
struct hisi_zip_req *q; struct hisi_zip_req *q;
unsigned long *req_bitmap; unsigned long *req_bitmap;
rwlock_t req_lock; spinlock_t req_lock;
u16 size; u16 size;
}; };
@ -116,17 +116,17 @@ static struct hisi_zip_req *hisi_zip_create_req(struct hisi_zip_qp_ctx *qp_ctx,
struct hisi_zip_req *req_cache; struct hisi_zip_req *req_cache;
int req_id; int req_id;
write_lock(&req_q->req_lock); spin_lock(&req_q->req_lock);
req_id = find_first_zero_bit(req_q->req_bitmap, req_q->size); req_id = find_first_zero_bit(req_q->req_bitmap, req_q->size);
if (req_id >= req_q->size) { if (req_id >= req_q->size) {
write_unlock(&req_q->req_lock); spin_unlock(&req_q->req_lock);
dev_dbg(&qp_ctx->qp->qm->pdev->dev, "req cache is full!\n"); dev_dbg(&qp_ctx->qp->qm->pdev->dev, "req cache is full!\n");
return ERR_PTR(-EAGAIN); return ERR_PTR(-EAGAIN);
} }
set_bit(req_id, req_q->req_bitmap); set_bit(req_id, req_q->req_bitmap);
write_unlock(&req_q->req_lock); spin_unlock(&req_q->req_lock);
req_cache = q + req_id; req_cache = q + req_id;
req_cache->req_id = req_id; req_cache->req_id = req_id;
@ -140,9 +140,9 @@ static void hisi_zip_remove_req(struct hisi_zip_qp_ctx *qp_ctx,
{ {
struct hisi_zip_req_q *req_q = &qp_ctx->req_q; struct hisi_zip_req_q *req_q = &qp_ctx->req_q;
write_lock(&req_q->req_lock); spin_lock(&req_q->req_lock);
clear_bit(req->req_id, req_q->req_bitmap); clear_bit(req->req_id, req_q->req_bitmap);
write_unlock(&req_q->req_lock); spin_unlock(&req_q->req_lock);
} }
static void hisi_zip_fill_addr(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req) static void hisi_zip_fill_addr(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req)
@ -456,7 +456,7 @@ static int hisi_zip_create_req_q(struct hisi_zip_ctx *ctx)
goto err_free_comp_q; goto err_free_comp_q;
} }
rwlock_init(&req_q->req_lock); spin_lock_init(&req_q->req_lock);
req_q->q = kcalloc(req_q->size, sizeof(struct hisi_zip_req), req_q->q = kcalloc(req_q->size, sizeof(struct hisi_zip_req),
GFP_KERNEL); GFP_KERNEL);