All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Subject: [Intel-gfx] [PATCH 1/8] drm/i915/selftests: Set cache status for huge_gem_object
Date: Mon, 25 Jan 2021 14:17:56 +0000	[thread overview]
Message-ID: <20210125141803.14378-1-chris@chris-wilson.co.uk> (raw)

Set the cache coherency and status using the set-coherency helper.
Otherwise, we forget to mark the new pages as cache dirty.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gem/selftests/huge_pages.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index aacf4856ccb4..f6329e462cfc 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -171,10 +171,8 @@ huge_pages_object(struct drm_i915_private *i915,
 	i915_gem_object_init(obj, &huge_page_ops, &lock_class);
 
 	i915_gem_object_set_volatile(obj);
-
-	obj->write_domain = I915_GEM_DOMAIN_CPU;
-	obj->read_domains = I915_GEM_DOMAIN_CPU;
-	obj->cache_level = I915_CACHE_NONE;
+	i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
+	__start_cpu_write(obj);
 
 	obj->mm.page_mask = page_mask;
 
@@ -324,10 +322,8 @@ fake_huge_pages_object(struct drm_i915_private *i915, u64 size, bool single)
 		i915_gem_object_init(obj, &fake_ops, &lock_class);
 
 	i915_gem_object_set_volatile(obj);
-
-	obj->write_domain = I915_GEM_DOMAIN_CPU;
-	obj->read_domains = I915_GEM_DOMAIN_CPU;
-	obj->cache_level = I915_CACHE_NONE;
+	i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
+	__start_cpu_write(obj);
 
 	return obj;
 }
@@ -994,7 +990,7 @@ __cpu_check_shmem(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 		u32 *ptr = kmap_atomic(i915_gem_object_get_page(obj, n));
 
 		if (needs_flush & CLFLUSH_BEFORE)
-			drm_clflush_virt_range(ptr, PAGE_SIZE);
+			drm_clflush_virt_range(&ptr[dword], sizeof(val));
 
 		if (ptr[dword] != val) {
 			pr_err("n=%lu ptr[%u]=%u, val=%u\n",
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

             reply	other threads:[~2021-01-25 14:18 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-25 14:17 Chris Wilson [this message]
2021-01-25 14:17 ` [Intel-gfx] [PATCH 2/8] drm/i915/selftests: Use a coherent map to setup scratch batch buffers Chris Wilson
2021-01-27 15:48   ` Matthew Auld
2021-01-25 14:17 ` [Intel-gfx] [PATCH 3/8] drm/i915/selftests: Replace the unbounded set-domain with an explicit wait Chris Wilson
2021-01-27 16:00   ` Matthew Auld
2021-01-25 14:17 ` [Intel-gfx] [PATCH 4/8] drm/i915/selftests: Remove redundant set-to-gtt-domain Chris Wilson
2021-01-27 16:03   ` Matthew Auld
2021-01-25 14:18 ` [Intel-gfx] [PATCH 5/8] drm/i915/selftests: Replace unbound set-domain waits with explicit timeouts Chris Wilson
2021-01-27 16:19   ` Matthew Auld
2021-01-25 14:18 ` [Intel-gfx] [PATCH 6/8] drm/i915/selftests: Replace an unbounded set-domain wait with a timeout Chris Wilson
2021-01-27 16:06   ` Matthew Auld
2021-01-25 14:18 ` [Intel-gfx] [PATCH 7/8] drm/i915/selftests: Remove redundant set-to-gtt-domain before batch submission Chris Wilson
2021-01-27 16:07   ` Matthew Auld
2021-01-25 14:18 ` [Intel-gfx] [PATCH 8/8] drm/i915/gem: Manage all set-domain waits explicitly Chris Wilson
2021-01-25 18:47 ` [Intel-gfx] ✓ Fi.CI.BAT: success for series starting with [1/8] drm/i915/selftests: Set cache status for huge_gem_object Patchwork
2021-01-26  0:06 ` [Intel-gfx] ✓ Fi.CI.IGT: " Patchwork
2021-01-27 15:44 ` [Intel-gfx] [PATCH 1/8] " Matthew Auld

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210125141803.14378-1-chris@chris-wilson.co.uk \
    --to=chris@chris-wilson.co.uk \
    --cc=intel-gfx@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.