[RFC PATCH 06/13] staging: vchiq_arm: Usa a DMA pool for small bulks

[Maarten Vanraes <maarten@xxxxxxxx>]

From: detule <ogjoneski@xxxxxxxxx>

During a bulk transfer we request a DMA allocation to hold the
scatter-gather list.  Most of the time, this allocation is small
(<< PAGE_SIZE), however it can be requested at a high enough frequency
to cause fragmentation and/or stress the CMA allocator (think time
spent in compaction here, or during allocations elsewhere).

Implement a pool to serve up small DMA allocations, falling back
to a coherent allocation if the request is greater than
VCHIQ_DMA_POOL_SIZE.

Signed-off-by: Oliver Gjoneski <ogjoneski@xxxxxxxxx>
Signed-off-by: Maarten Vanraes <maarten@xxxxxxxx>
---
 .../interface/vchiq_arm/vchiq_arm.c           | 33 ++++++++++++++++---
 1 file changed, 29 insertions(+), 4 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index e306f420d767..eb15aa011a22 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -24,6 +24,7 @@
 #include <linux/platform_device.h>
 #include <linux/compat.h>
 #include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
 #include <linux/rcupdate.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
@@ -54,6 +55,8 @@
 
 #define ARM_DS_ACTIVE	BIT(2)
 
+#define VCHIQ_DMA_POOL_SIZE PAGE_SIZE
+
 /* Override the default prefix, which would be vchiq_arm (from the filename) */
 #undef MODULE_PARAM_PREFIX
 #define MODULE_PARAM_PREFIX DEVICE_NAME "."
@@ -136,6 +139,7 @@ struct vchiq_pagelist_info {
 	struct pagelist *pagelist;
 	size_t pagelist_buffer_size;
 	dma_addr_t dma_addr;
+	bool is_from_pool;
 	enum dma_data_direction dma_dir;
 	unsigned int num_pages;
 	unsigned int pages_need_release;
@@ -156,6 +160,7 @@ static void __iomem *g_regs;
  * of 32.
  */
 static unsigned int g_cache_line_size = 32;
+static struct dma_pool *g_dma_pool;
 static unsigned int g_use_36bit_addrs = 0;
 static unsigned int g_fragments_size;
 static char *g_fragments_base;
@@ -198,8 +203,13 @@ cleanup_pagelistinfo(struct vchiq_instance *instance, struct vchiq_pagelist_info
 	if (pagelistinfo->pages_need_release)
 		unpin_user_pages(pagelistinfo->pages, pagelistinfo->num_pages);
 
-	dma_free_coherent(instance->state->dev, pagelistinfo->pagelist_buffer_size,
-			  pagelistinfo->pagelist, pagelistinfo->dma_addr);
+	if (pagelistinfo->is_from_pool) {
+		dma_pool_free(g_dma_pool, pagelistinfo->pagelist,
+			      pagelistinfo->dma_addr);
+	} else {
+		dma_free_coherent(instance->state->dev, pagelistinfo->pagelist_buffer_size,
+				  pagelistinfo->pagelist, pagelistinfo->dma_addr);
+	}
 }
 
 static inline bool
@@ -234,6 +244,7 @@ create_pagelist(struct vchiq_instance *instance, char *buf, char __user *ubuf,
 	u32 *addrs;
 	unsigned int num_pages, offset, i, k;
 	int actual_pages;
+	bool is_from_pool;
 	size_t pagelist_size;
 	struct scatterlist *scatterlist, *sg;
 	int dma_buffers;
@@ -263,8 +274,14 @@ create_pagelist(struct vchiq_instance *instance, char *buf, char __user *ubuf,
 	/* Allocate enough storage to hold the page pointers and the page
 	 * list
 	 */
-	pagelist = dma_alloc_coherent(instance->state->dev, pagelist_size, &dma_addr,
-				      GFP_KERNEL);
+	if (pagelist_size > VCHIQ_DMA_POOL_SIZE) {
+		pagelist = dma_alloc_coherent(instance->state->dev, pagelist_size, &dma_addr,
+					      GFP_KERNEL);
+		is_from_pool = false;
+	} else {
+		pagelist = dma_pool_alloc(g_dma_pool, GFP_KERNEL, &dma_addr);
+		is_from_pool = true;
+	}
 
 	dev_dbg(instance->state->dev, "arm: %pK\n", pagelist);
 
@@ -285,6 +302,7 @@ create_pagelist(struct vchiq_instance *instance, char *buf, char __user *ubuf,
 	pagelistinfo->pagelist = pagelist;
 	pagelistinfo->pagelist_buffer_size = pagelist_size;
 	pagelistinfo->dma_addr = dma_addr;
+	pagelistinfo->is_from_pool = is_from_pool;
 	pagelistinfo->dma_dir =  (type == PAGELIST_WRITE) ?
 				  DMA_TO_DEVICE : DMA_FROM_DEVICE;
 	pagelistinfo->num_pages = num_pages;
@@ -625,6 +643,13 @@ static int vchiq_platform_init(struct platform_device *pdev, struct vchiq_state
 	dev_dbg(&pdev->dev, "arm: vchiq_init - done (slots %pK, phys %pad)\n",
 		vchiq_slot_zero, &slot_phys);
 	g_dma_dev = dma_dev ?: dev;
+	g_dma_pool = dmam_pool_create("vchiq_scatter_pool", dev,
+				      VCHIQ_DMA_POOL_SIZE, g_cache_line_size,
+				      0);
+	if (!g_dma_pool) {
+		dev_err(dev, "failed to create dma pool");
+		return -ENOMEM;
+	}
 
 	vchiq_call_connected_callbacks();
 
-- 
2.41.0