ath11k: allocate dst ring descriptors from cacheable memory

tcl_data and reo_dst rings are currently being allocated using
dma_allocate_coherent() which is non cacheable.

Allocating ring memory from cacheable memory area allows cached descriptor
access and prefetch next descriptors to optimize CPU usage during
descriptor processing on NAPI. Based on the hardware param we can enable
or disable this feature for the corresponding platform.

Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.4.0.1.r2-00012-QCAHKSWPL_SILICONZ-1
Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.4.0.1-01695-QCAHKSWPL_SILICONZ-1

Co-developed-by: Pradeep Kumar Chitrapu <pradeepc@codeaurora.org>
Signed-off-by: Pradeep Kumar Chitrapu <pradeepc@codeaurora.org>
Co-developed-by: Sriram R <srirrama@codeaurora.org>
Signed-off-by: Sriram R <srirrama@codeaurora.org>
Signed-off-by: Jouni Malinen <jouni@codeaurora.org>
Signed-off-by: P Praneesh <ppranees@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/1630560820-21905-3-git-send-email-ppranees@codeaurora.org

1 files changed, 33 insertions, 5 deletions

diff --git a/drivers/net/wireless/ath/ath11k/dp.c b/drivers/net/wireless/ath/ath11k/dp.c
index 8baaeeb8cf82..8058b56028de 100644
--- a/drivers/net/wireless/ath/ath11k/dp.c
+++ b/drivers/net/wireless/ath/ath11k/dp.c
@@ -101,8 +101,11 @@ void ath11k_dp_srng_cleanup(struct ath11k_base *ab, struct dp_srng *ring)
 	if (!ring->vaddr_unaligned)
 		return;
 
-	dma_free_coherent(ab->dev, ring->size, ring->vaddr_unaligned,
-			  ring->paddr_unaligned);
+	if (ring->cached)
+		kfree(ring->vaddr_unaligned);
+	else
+		dma_free_coherent(ab->dev, ring->size, ring->vaddr_unaligned,
+				  ring->paddr_unaligned);
 
 	ring->vaddr_unaligned = NULL;
 }
@@ -222,6 +225,7 @@ int ath11k_dp_srng_setup(struct ath11k_base *ab, struct dp_srng *ring,
 	int entry_sz = ath11k_hal_srng_get_entrysize(ab, type);
 	int max_entries = ath11k_hal_srng_get_max_entries(ab, type);
 	int ret;
+	bool cached = false;
 
 	if (max_entries < 0 || entry_sz < 0)
 		return -EINVAL;
@@ -230,9 +234,28 @@ int ath11k_dp_srng_setup(struct ath11k_base *ab, struct dp_srng *ring,
 		num_entries = max_entries;
 
 	ring->size = (num_entries * entry_sz) + HAL_RING_BASE_ALIGN - 1;
-	ring->vaddr_unaligned = dma_alloc_coherent(ab->dev, ring->size,
-						   &ring->paddr_unaligned,
-						   GFP_KERNEL);
+
+	if (ab->hw_params.alloc_cacheable_memory) {
+		/* Allocate the reo dst and tx completion rings from cacheable memory */
+		switch (type) {
+		case HAL_REO_DST:
+			cached = true;
+			break;
+		default:
+			cached = false;
+		}
+
+		if (cached) {
+			ring->vaddr_unaligned = kzalloc(ring->size, GFP_KERNEL);
+			ring->paddr_unaligned = virt_to_phys(ring->vaddr_unaligned);
+		}
+	}
+
+	if (!cached)
+		ring->vaddr_unaligned = dma_alloc_coherent(ab->dev, ring->size,
+							   &ring->paddr_unaligned,
+							   GFP_KERNEL);
+
 	if (!ring->vaddr_unaligned)
 		return -ENOMEM;
 
@@ -292,6 +315,11 @@ int ath11k_dp_srng_setup(struct ath11k_base *ab, struct dp_srng *ring,
 		return -EINVAL;
 	}
 
+	if (cached) {
+		params.flags |= HAL_SRNG_FLAGS_CACHED;
+		ring->cached = 1;
+	}
+
 	ret = ath11k_hal_srng_setup(ab, type, ring_num, mac_id, &params);
 	if (ret < 0) {
 		ath11k_warn(ab, "failed to setup srng: %d ring_id %d\n",