drm/ttm: Add a generic TTM memcpy move for page-based iomem

The internal ttm_bo_util memcpy uses ioremap functionality, and while it
probably might be possible to use it for copying in- and out of
sglist represented io memory, using io_mem_reserve() / io_mem_free()
callbacks, that would cause problems with fault().
Instead, implement a method mapping page-by-page using kmap_local()
semantics. As an additional benefit we then avoid the occasional global
TLB flushes of ioremap() and consuming ioremap space, elimination of a
critical point of failure and with a slight change of semantics we could
also push the memcpy out async for testing and async driver development
purposes.

A special linear iomem iterator is introduced internally to mimic the
old ioremap behaviour for code-paths that can't immediately be ported
over. This adds to the code size and should be considered a temporary
solution.

Looking at the code we have a lot of checks for iomap tagged pointers.
Ideally we should extend the core memremap functions to also accept
uncached memory and kmap_local functionality. Then we could strip a
lot of code.

Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/r/20210602083818.241793-4-thomas.hellstrom@linux.intel.com

1 files changed, 193 insertions, 0 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
index 2a68145572cc..2431717376e7 100644
--- a/drivers/gpu/drm/ttm/ttm_resource.c
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -22,6 +22,10 @@
  * Authors: Christian König
  */
 
+#include <linux/dma-buf-map.h>
+#include <linux/io-mapping.h>
+#include <linux/scatterlist.h>
+
 #include <drm/ttm/ttm_resource.h>
 #include <drm/ttm/ttm_bo_driver.h>
 
@@ -154,3 +158,192 @@ void ttm_resource_manager_debug(struct ttm_resource_manager *man,
 		man->func->debug(man, p);
 }
 EXPORT_SYMBOL(ttm_resource_manager_debug);
+
+static void ttm_kmap_iter_iomap_map_local(struct ttm_kmap_iter *iter,
+					  struct dma_buf_map *dmap,
+					  pgoff_t i)
+{
+	struct ttm_kmap_iter_iomap *iter_io =
+		container_of(iter, typeof(*iter_io), base);
+	void __iomem *addr;
+
+retry:
+	while (i >= iter_io->cache.end) {
+		iter_io->cache.sg = iter_io->cache.sg ?
+			sg_next(iter_io->cache.sg) : iter_io->st->sgl;
+		iter_io->cache.i = iter_io->cache.end;
+		iter_io->cache.end += sg_dma_len(iter_io->cache.sg) >>
+			PAGE_SHIFT;
+		iter_io->cache.offs = sg_dma_address(iter_io->cache.sg) -
+			iter_io->start;
+	}
+
+	if (i < iter_io->cache.i) {
+		iter_io->cache.end = 0;
+		iter_io->cache.sg = NULL;
+		goto retry;
+	}
+
+	addr = io_mapping_map_local_wc(iter_io->iomap, iter_io->cache.offs +
+				       (((resource_size_t)i - iter_io->cache.i)
+					<< PAGE_SHIFT));
+	dma_buf_map_set_vaddr_iomem(dmap, addr);
+}
+
+static void ttm_kmap_iter_iomap_unmap_local(struct ttm_kmap_iter *iter,
+					    struct dma_buf_map *map)
+{
+	io_mapping_unmap_local(map->vaddr_iomem);
+}
+
+static const struct ttm_kmap_iter_ops ttm_kmap_iter_io_ops = {
+	.map_local =  ttm_kmap_iter_iomap_map_local,
+	.unmap_local = ttm_kmap_iter_iomap_unmap_local,
+	.maps_tt = false,
+};
+
+/**
+ * ttm_kmap_iter_iomap_init - Initialize a struct ttm_kmap_iter_iomap
+ * @iter_io: The struct ttm_kmap_iter_iomap to initialize.
+ * @iomap: The struct io_mapping representing the underlying linear io_memory.
+ * @st: sg_table into @iomap, representing the memory of the struct
+ * ttm_resource.
+ * @start: Offset that needs to be subtracted from @st to make
+ * sg_dma_address(st->sgl) - @start == 0 for @iomap start.
+ *
+ * Return: Pointer to the embedded struct ttm_kmap_iter.
+ */
+struct ttm_kmap_iter *
+ttm_kmap_iter_iomap_init(struct ttm_kmap_iter_iomap *iter_io,
+			 struct io_mapping *iomap,
+			 struct sg_table *st,
+			 resource_size_t start)
+{
+	iter_io->base.ops = &ttm_kmap_iter_io_ops;
+	iter_io->iomap = iomap;
+	iter_io->st = st;
+	iter_io->start = start;
+	memset(&iter_io->cache, 0, sizeof(iter_io->cache));
+
+	return &iter_io->base;
+}
+EXPORT_SYMBOL(ttm_kmap_iter_iomap_init);
+
+/**
+ * DOC: Linear io iterator
+ *
+ * This code should die in the not too near future. Best would be if we could
+ * make io-mapping use memremap for all io memory, and have memremap
+ * implement a kmap_local functionality. We could then strip a huge amount of
+ * code. These linear io iterators are implemented to mimic old functionality,
+ * and they don't use kmap_local semantics at all internally. Rather ioremap or
+ * friends, and at least on 32-bit they add global TLB flushes and points
+ * of failure.
+ */
+
+static void ttm_kmap_iter_linear_io_map_local(struct ttm_kmap_iter *iter,
+					      struct dma_buf_map *dmap,
+					      pgoff_t i)
+{
+	struct ttm_kmap_iter_linear_io *iter_io =
+		container_of(iter, typeof(*iter_io), base);
+
+	*dmap = iter_io->dmap;
+	dma_buf_map_incr(dmap, i * PAGE_SIZE);
+}
+
+static const struct ttm_kmap_iter_ops ttm_kmap_iter_linear_io_ops = {
+	.map_local =  ttm_kmap_iter_linear_io_map_local,
+	.maps_tt = false,
+};
+
+/**
+ * ttm_kmap_iter_linear_io_init - Initialize an iterator for linear io memory
+ * @iter_io: The iterator to initialize
+ * @bdev: The TTM device
+ * @mem: The ttm resource representing the iomap.
+ *
+ * This function is for internal TTM use only. It sets up a memcpy kmap iterator
+ * pointing at a linear chunk of io memory.
+ *
+ * Return: A pointer to the embedded struct ttm_kmap_iter or error pointer on
+ * failure.
+ */
+struct ttm_kmap_iter *
+ttm_kmap_iter_linear_io_init(struct ttm_kmap_iter_linear_io *iter_io,
+			     struct ttm_device *bdev,
+			     struct ttm_resource *mem)
+{
+	int ret;
+
+	ret = ttm_mem_io_reserve(bdev, mem);
+	if (ret)
+		goto out_err;
+	if (!mem->bus.is_iomem) {
+		ret = -EINVAL;
+		goto out_io_free;
+	}
+
+	if (mem->bus.addr) {
+		dma_buf_map_set_vaddr(&iter_io->dmap, mem->bus.addr);
+		iter_io->needs_unmap = false;
+	} else {
+		size_t bus_size = (size_t)mem->num_pages << PAGE_SHIFT;
+
+		iter_io->needs_unmap = true;
+		memset(&iter_io->dmap, 0, sizeof(iter_io->dmap));
+		if (mem->bus.caching == ttm_write_combined)
+			dma_buf_map_set_vaddr_iomem(&iter_io->dmap,
+						    ioremap_wc(mem->bus.offset,
+							       bus_size));
+		else if (mem->bus.caching == ttm_cached)
+			dma_buf_map_set_vaddr(&iter_io->dmap,
+					      memremap(mem->bus.offset, bus_size,
+						       MEMREMAP_WB |
+						       MEMREMAP_WT |
+						       MEMREMAP_WC));
+
+		/* If uncached requested or if mapping cached or wc failed */
+		if (dma_buf_map_is_null(&iter_io->dmap))
+			dma_buf_map_set_vaddr_iomem(&iter_io->dmap,
+						    ioremap(mem->bus.offset,
+							    bus_size));
+
+		if (dma_buf_map_is_null(&iter_io->dmap)) {
+			ret = -ENOMEM;
+			goto out_io_free;
+		}
+	}
+
+	iter_io->base.ops = &ttm_kmap_iter_linear_io_ops;
+	return &iter_io->base;
+
+out_io_free:
+	ttm_mem_io_free(bdev, mem);
+out_err:
+	return ERR_PTR(ret);
+}
+
+/**
+ * ttm_kmap_iter_linear_io_fini - Clean up an iterator for linear io memory
+ * @iter_io: The iterator to initialize
+ * @bdev: The TTM device
+ * @mem: The ttm resource representing the iomap.
+ *
+ * This function is for internal TTM use only. It cleans up a memcpy kmap
+ * iterator initialized by ttm_kmap_iter_linear_io_init.
+ */
+void
+ttm_kmap_iter_linear_io_fini(struct ttm_kmap_iter_linear_io *iter_io,
+			     struct ttm_device *bdev,
+			     struct ttm_resource *mem)
+{
+	if (iter_io->needs_unmap && dma_buf_map_is_set(&iter_io->dmap)) {
+		if (iter_io->dmap.is_iomem)
+			iounmap(iter_io->dmap.vaddr_iomem);
+		else
+			memunmap(iter_io->dmap.vaddr);
+	}
+
+	ttm_mem_io_free(bdev, mem);
+}