summaryrefslogtreecommitdiff
path: root/package/kernel/mac80211/patches/303-ath10k-do-not-use-coherent-memory-for-allocated-devi.patch
blob: 20bece68eca6a4f62b0050734fe4374b7db1f163 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
From: Felix Fietkau <nbd@openwrt.org>
Date: Sun, 22 Nov 2015 14:03:40 +0100
Subject: [PATCH] ath10k: do not use coherent memory for allocated device
 memory chunks

Coherent memory is more expensive to allocate (and constrained on some
architectures where it has to be pre-allocated). It is also completely
unnecessary, since the host has no reason to even access these allocated
memory spaces

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
---

--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -4312,34 +4312,58 @@ void ath10k_wmi_event_vdev_resume_req(st
 	ath10k_dbg(ar, ATH10K_DBG_WMI, "WMI_VDEV_RESUME_REQ_EVENTID\n");
 }
 
-static int ath10k_wmi_alloc_host_mem(struct ath10k *ar, u32 req_id,
-				     u32 num_units, u32 unit_len)
+static int ath10k_wmi_alloc_chunk(struct ath10k *ar, u32 req_id,
+				  u32 num_units, u32 unit_len)
 {
 	dma_addr_t paddr;
-	u32 pool_size;
+	u32 pool_size = 0;
 	int idx = ar->wmi.num_mem_chunks;
+	void *vaddr = NULL;
 
-	pool_size = num_units * round_up(unit_len, 4);
+	if (ar->wmi.num_mem_chunks == ARRAY_SIZE(ar->wmi.mem_chunks))
+		return -ENOMEM;
 
-	if (!pool_size)
-		return -EINVAL;
+	while (!vaddr && num_units) {
+		pool_size = num_units * round_up(unit_len, 4);
+		if (!pool_size)
+			return -EINVAL;
 
-	ar->wmi.mem_chunks[idx].vaddr = dma_alloc_coherent(ar->dev,
-							   pool_size,
-							   &paddr,
-							   GFP_KERNEL);
-	if (!ar->wmi.mem_chunks[idx].vaddr) {
-		ath10k_warn(ar, "failed to allocate memory chunk\n");
-		return -ENOMEM;
+		vaddr = kzalloc(pool_size, GFP_KERNEL | __GFP_NOWARN);
+		if (!vaddr)
+			num_units /= 2;
 	}
 
-	memset(ar->wmi.mem_chunks[idx].vaddr, 0, pool_size);
+	if (!num_units)
+		return -ENOMEM;
+
+	paddr = dma_map_single(ar->dev, vaddr, pool_size, DMA_TO_DEVICE);
+	if (dma_mapping_error(ar->dev, paddr)) {
+		kfree(vaddr);
+		return -ENOMEM;
+	}
 
+	ar->wmi.mem_chunks[idx].vaddr = vaddr;
 	ar->wmi.mem_chunks[idx].paddr = paddr;
 	ar->wmi.mem_chunks[idx].len = pool_size;
 	ar->wmi.mem_chunks[idx].req_id = req_id;
 	ar->wmi.num_mem_chunks++;
 
+	return num_units;
+}
+
+static int ath10k_wmi_alloc_host_mem(struct ath10k *ar, u32 req_id,
+				     u32 num_units, u32 unit_len)
+{
+	int ret;
+
+	while (num_units) {
+		ret = ath10k_wmi_alloc_chunk(ar, req_id, num_units, unit_len);
+		if (ret < 0)
+			return ret;
+
+		num_units -= ret;
+	}
+
 	return 0;
 }
 
@@ -7717,10 +7741,11 @@ void ath10k_wmi_free_host_mem(struct ath
 
 	/* free the host memory chunks requested by firmware */
 	for (i = 0; i < ar->wmi.num_mem_chunks; i++) {
-		dma_free_coherent(ar->dev,
-				  ar->wmi.mem_chunks[i].len,
-				  ar->wmi.mem_chunks[i].vaddr,
-				  ar->wmi.mem_chunks[i].paddr);
+		dma_unmap_single(ar->dev,
+				 ar->wmi.mem_chunks[i].paddr,
+				 ar->wmi.mem_chunks[i].len,
+				 DMA_TO_DEVICE);
+		kfree(ar->wmi.mem_chunks[i].vaddr);
 	}
 
 	ar->wmi.num_mem_chunks = 0;