[PATCH v2 3/3] drm/i915/gem: Replace kmap() with kmap_local_page()

[Fabio M. De Francesco]

kmap() s been deprecated in favor of kmap_local_page().

There are two main problems with kmap(): (1) It comes with an overhead as
mapping space is restricted and protected by a global lock for
synchronization and (2) it also requires global TLB invalidation when the
kmap’s pool wraps and it might block when the mapping space is fully
utilized until a slot becomes available.

With kmap_local_page() the mappings are per thread, CPU local, can take
page faults, and can be called from any context (including interrupts).
It is faster than kmap() in kernels with HIGHMEM enabled. Furthermore,
the tasks can be preempted and, when they are scheduled to run again, the
kernel virtual addresses are restored and are still valid.

Obviously, thread locality implies that the kernel virtual addresses are
only valid in the context of the callers. The kmap_local_page() use in
i915/gem doesn't break the above-mentioned constraint, so it should be
preferred to kmap().

Therefore, replace kmap() with kmap_local_page() in i915/gem and use
memcpy_to_page() where it is possible to avoid the open coding of
mapping + memcpy() + un-mapping.

Suggested-by: Ira Weiny <ira.weiny at intel.com>
Signed-off-by: Fabio M. De Francesco <fmdefrancesco at gmail.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c          | 6 ++----
 drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c | 8 ++++----
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 37d1efcd3ca6..8856a6409e83 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -657,16 +657,14 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *dev_priv,
 	do {
 		unsigned int len = min_t(typeof(size), size, PAGE_SIZE);
 		struct page *page;
-		void *pgdata, *vaddr;
+		void *pgdata;

 		err = aops->write_begin(file, file->f_mapping, offset, len,
 					&page, &pgdata);
 		if (err < 0)
 			goto fail;

-		vaddr = kmap(page);
-		memcpy(vaddr, data, len);
-		kunmap(page);
+		memcpy_to_page(page, 0, data, len);

 		err = aops->write_end(file, file->f_mapping, offset, len, len,
 				      page, pgdata);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 56279908ed30..5fd9e1ee2340 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -155,7 +155,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj,
 	intel_gt_flush_ggtt_writes(to_gt(i915));

 	p = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
-	cpu = kmap(p) + offset_in_page(offset);
+	cpu = kmap_local_page(p) + offset_in_page(offset);
 	drm_clflush_virt_range(cpu, sizeof(*cpu));
 	if (*cpu != (u32)page) {
 		pr_err("Partial view for %lu [%u] (offset=%llu, size=%u [%llu, row size %u], fence=%d, tiling=%d, stride=%d) misalignment, expected write to page (%lu + %u [0x%lx]) of 0x%x, found 0x%x\n",
@@ -173,7 +173,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj,
 	}
 	*cpu = 0;
 	drm_clflush_virt_range(cpu, sizeof(*cpu));
-	kunmap(p);
+	kunmap_local(cpu);

 out:
 	i915_gem_object_lock(obj, NULL);
@@ -251,7 +251,7 @@ static int check_partial_mappings(struct drm_i915_gem_object *obj,
 		intel_gt_flush_ggtt_writes(to_gt(i915));

 		p = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
-		cpu = kmap(p) + offset_in_page(offset);
+		cpu = kmap_local_page(p) + offset_in_page(offset);
 		drm_clflush_virt_range(cpu, sizeof(*cpu));
 		if (*cpu != (u32)page) {
 			pr_err("Partial view for %lu [%u] (offset=%llu, size=%u [%llu, row size %u], fence=%d, tiling=%d, stride=%d) misalignment, expected write to page (%lu + %u [0x%lx]) of 0x%x, found 0x%x\n",
@@ -269,7 +269,7 @@ static int check_partial_mappings(struct drm_i915_gem_object *obj,
 		}
 		*cpu = 0;
 		drm_clflush_virt_range(cpu, sizeof(*cpu));
-		kunmap(p);
+		kunmap_local(cpu);
 		if (err)
 			return err;

--
2.40.0