[PATCH] dma-buf: system_heap: use larger contiguous mappings instead of per-page mmap

[Barry Song <21cnbao@gmail.com>]

From: Barry Song <v-songbaohua@oppo.com>

We can allocate high-order pages, but mapping them one by
one is inefficient. This patch changes the code to map
as large a chunk as possible. The code looks somewhat
complicated mainly because supporting mmap with a
non-zero offset is a bit tricky.

Using the micro-benchmark below, we see that mmap becomes
3.5X faster:

  #include <stdio.h>
  #include <fcntl.h>
  #include <linux/dma-heap.h>
  #include <sys/ioctl.h>
  #include <sys/mman.h>
  #include <time.h>
  #include <unistd.h>
  #include <stdlib.h>

  #define SIZE   (512UL * 1024 * 1024)
  #define PAGE   4096
  #define STRIDE (PAGE/sizeof(int))
  #define PAGES  (SIZE/PAGE)

  int main(void) {
      int heap = open("/dev/dma_heap/system", O_RDONLY);
      struct dma_heap_allocation_data d = { .len = SIZE, .fd_flags = O_RDWR|O_CLOEXEC };
      ioctl(heap, DMA_HEAP_IOCTL_ALLOC, &d);

      struct timespec t0, t1;
      clock_gettime(CLOCK_MONOTONIC, &t0);
      int *p = mmap(NULL, SIZE, PROT_READ|PROT_WRITE, MAP_SHARED, d.fd, 0);
      clock_gettime(CLOCK_MONOTONIC, &t1);

      for (int i = 0; i < PAGES; i++) p[i*STRIDE] = i;
      for (int i = 0; i < PAGES; i++)
          if (p[i*STRIDE] != i) {
              fprintf(stderr, "mismatch at page %d\n", i);
              exit(1);
          }

      long ns = (t1.tv_sec-t0.tv_sec)*1000000000L + (t1.tv_nsec-t0.tv_nsec);
      printf("mmap 512MB took %.3f us, verify OK\n", ns/1000.0);
      return 0;
  }

W/ patch:

~ # ./a.out
mmap 512MB took 200266.000 us, verify OK
~ # ./a.out
mmap 512MB took 198151.000 us, verify OK
~ # ./a.out
mmap 512MB took 197069.000 us, verify OK
~ # ./a.out
mmap 512MB took 196781.000 us, verify OK
~ # ./a.out
mmap 512MB took 198102.000 us, verify OK
~ # ./a.out
mmap 512MB took 195552.000 us, verify OK

W/o patch:

~ # ./a.out
mmap 512MB took 6987470.000 us, verify OK
~ # ./a.out
mmap 512MB took 6970739.000 us, verify OK
~ # ./a.out
mmap 512MB took 6984383.000 us, verify OK
~ # ./a.out
mmap 512MB took 6971311.000 us, verify OK
~ # ./a.out
mmap 512MB took 6991680.000 us, verify OK

Signed-off-by: Barry Song <v-songbaohua@oppo.com>
---
 drivers/dma-buf/heaps/system_heap.c | 33 +++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 9 deletions(-)

diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c
index bbe7881f1360..4c782fe33fd4 100644
--- a/drivers/dma-buf/heaps/system_heap.c
+++ b/drivers/dma-buf/heaps/system_heap.c
@@ -186,20 +186,35 @@ static int system_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
 	struct system_heap_buffer *buffer = dmabuf->priv;
 	struct sg_table *table = &buffer->sg_table;
 	unsigned long addr = vma->vm_start;
-	struct sg_page_iter piter;
-	int ret;
+	unsigned long pgoff = vma->vm_pgoff;
+	struct scatterlist *sg;
+	int i, ret;
+
+	for_each_sgtable_sg(table, sg, i) {
+		unsigned long n = sg->length >> PAGE_SHIFT;
 
-	for_each_sgtable_page(table, &piter, vma->vm_pgoff) {
-		struct page *page = sg_page_iter_page(&piter);
+		if (pgoff < n)
+			break;
+		pgoff -= n;
+	}
+
+	for (; sg && addr < vma->vm_end; sg = sg_next(sg)) {
+		unsigned long n = (sg->length >> PAGE_SHIFT) - pgoff;
+		struct page *page = sg_page(sg) + pgoff;
+		unsigned long size = n << PAGE_SHIFT;
+
+		if (addr + size > vma->vm_end)
+			size = vma->vm_end - addr;
 
-		ret = remap_pfn_range(vma, addr, page_to_pfn(page), PAGE_SIZE,
-				      vma->vm_page_prot);
+		ret = remap_pfn_range(vma, addr, page_to_pfn(page),
+				size, vma->vm_page_prot);
 		if (ret)
 			return ret;
-		addr += PAGE_SIZE;
-		if (addr >= vma->vm_end)
-			return 0;
+
+		addr += size;
+		pgoff = 0;
 	}
+
 	return 0;
 }
 
-- 
2.39.3 (Apple Git-146)