gpu: nvgpu: nvgpu SGL implementation

The last major item preventing the core MM code in the nvgpu
driver from being platform agnostic is the usage of Linux
scattergather tables and scattergather lists. These data
structures are used throughout the mapping code to handle
discontiguous DMA allocations and also overloaded to represent
VIDMEM allocs.

The notion of a scatter gather table is crucial to a HW device
that can handle discontiguous DMA. The GPU has a MMU which
allows the GPU to do page gathering and present a virtually
contiguous buffer to the GPU HW. As a result it makes sense
for the GPU driver to use some sort of scatter gather concept
so maximize memory usage efficiency.

To that end this patch keeps the notion of a scatter gather
list but implements it in the nvgpu common code. It is based
heavily on the Linux SGL concept. It is a singly linked list
of blocks - each representing a chunk of memory. To map or
use a DMA allocation SW must iterate over each block in the
SGL.

This patch implements the most basic level of support for this
data structure. There are certainly easy optimizations that
could be done to speed up the current implementation. However,
this patches' goal is to simply divest the core MM code from
any last Linux'isms. Speed and efficiency come next.

Change-Id: Icf44641db22d87fa1d003debbd9f71b605258e42
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1530867
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 15 insertions, 12 deletions

diff --git a/drivers/gpu/nvgpu/common/pramin.c b/drivers/gpu/nvgpu/common/pramin.c
index 425bfdb4..bb7d930e 100644
--- a/drivers/gpu/nvgpu/common/pramin.c
+++ b/drivers/gpu/nvgpu/common/pramin.c
@@ -84,37 +84,40 @@ void nvgpu_pramin_access_batched(struct gk20a *g, struct nvgpu_mem *mem,
                 u32 offset, u32 size, pramin_access_batch_fn loop, u32 **arg)
 {
         struct nvgpu_page_alloc *alloc = NULL;
-        struct page_alloc_chunk *chunk = NULL;
+        struct nvgpu_mem_sgl *sgl;
         u32 byteoff, start_reg, until_end, n;
 
         alloc = get_vidmem_page_alloc(mem->priv.sgt->sgl);
-        nvgpu_list_for_each_entry(chunk, &alloc->alloc_chunks,
-                        page_alloc_chunk, list_entry) {
-                if (offset >= chunk->length)
-                        offset -= chunk->length;
-                else
+        sgl = alloc->sgl;
+        while (sgl) {
+                if (offset >= nvgpu_mem_sgl_length(sgl)) {
+                        offset -= nvgpu_mem_sgl_length(sgl);
+                        sgl = sgl->next;
+                } else {
                         break;
+                }
         }
 
         while (size) {
-                byteoff = g->ops.pramin.enter(g, mem, chunk,
+                u32 sgl_len = (u32)nvgpu_mem_sgl_length(sgl);
+
+                byteoff = g->ops.pramin.enter(g, mem, sgl,
                                               offset / sizeof(u32));
                 start_reg = g->ops.pramin.data032_r(byteoff / sizeof(u32));
                 until_end = SZ_1M - (byteoff & (SZ_1M - 1));
 
-                n = min3(size, until_end, (u32)(chunk->length - offset));
+                n = min3(size, until_end, (u32)(sgl_len - offset));
 
                 loop(g, start_reg, n / sizeof(u32), arg);
 
                 /* read back to synchronize accesses */
                 gk20a_readl(g, start_reg);
-                g->ops.pramin.exit(g, mem, chunk);
+                g->ops.pramin.exit(g, mem, sgl);
 
                 size -= n;
 
-                if (n == (chunk->length - offset)) {
-                        chunk = nvgpu_list_next_entry(chunk, page_alloc_chunk,
-                                        list_entry);
+                if (n == (sgl_len - offset)) {
+                        sgl = nvgpu_mem_sgl_next(sgl);
                         offset = 0;
                 } else {
                         offset += n;