Re: [RFC PATCH] drm: disable WC optimization for cache coherent devices on non-x86

From: Christoph Hellwig <hch@infradead.org>
To: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: "Maxime Ripard" <maxime.ripard@bootlin.com>,
	"Michael Ellerman" <mpe@ellerman.id.au>,
	"Michel Dänzer" <michel@daenzer.net>,
	"Will Deacon" <will.deacon@arm.com>,
	"Linux Kernel Mailing List" <linux-kernel@vger.kernel.org>,
	"amd-gfx list" <amd-gfx@lists.freedesktop.org>,
	"Junwei Zhang" <Jerry.Zhang@amd.com>,
	"Christoph Hellwig" <hch@infradead.org>,
	"David Airlie" <airlied@linux.ie>,
	"Huang Rui" <ray.huang@amd.com>,
	dri-devel <dri-devel@lists.freedesktop.org>,
	"Alex Deucher" <alexdeucher@gmail.com>,
	"Alex Deucher" <alexander.deucher@amd.com>,
	"Sean Paul" <sean@poorly.run>,
	"Christian Koenig" <christian.koenig@amd.com>,
	linux-arm-kernel <linux-arm-kernel@lists.infradead.org>
Subject: Re: [RFC PATCH] drm: disable WC optimization for cache coherent devices on non-x86
Date: Wed, 23 Jan 2019 08:44:28 -0800	[thread overview]
Message-ID: <20190123164428.GA9367@infradead.org> (raw)
In-Reply-To: <CAKv+Gu8+77uZHJ6ZYjGNcKQL8C3cT5Ree+TcTVmkQXAHV-ADyg@mail.gmail.com>

I think we just want a driver-local check for those combinations
where we know this hack actually works, which really just seems
to be x86-64 with PAT. Something like the patch below, but maybe with
even more strong warnings to not do something like this elsewhere:

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 728e15e5d68a..5fe657f20232 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -456,33 +456,16 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 
 	bo->flags = bp->flags;
 
-#ifdef CONFIG_X86_32
-	/* XXX: Write-combined CPU mappings of GTT seem broken on 32-bit
-	 * See https://bugs.freedesktop.org/show_bug.cgi?id=84627
-	 */
-	bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
-#elif defined(CONFIG_X86) && !defined(CONFIG_X86_PAT)
-	/* Don't try to enable write-combining when it can't work, or things
-	 * may be slow
-	 * See https://bugs.freedesktop.org/show_bug.cgi?id=88758
-	 */
-
-#ifndef CONFIG_COMPILE_TEST
-#warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \
-	 thanks to write-combining
-#endif
-
-	if (bo->flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC)
-		DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
-			      "better performance thanks to write-combining\n");
-	bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
-#else
-	/* For architectures that don't support WC memory,
-	 * mask out the WC flag from the BO
+	/*
+	 * Don't try to enable write-combined CPU mappings unless we 100%
+	 * positively know it works, otherwise there may be dragons.
+	 *
+	 * See:
+	 *  - https://bugs.freedesktop.org/show_bug.cgi?id=88758
+	 *  - https://bugs.freedesktop.org/show_bug.cgi?id=84627
 	 */
-	if (!drm_arch_can_wc_memory())
+	if (!(IS_ENABLED(CONFIG_X86_64) && IS_ENABLED(CONFIG_X86_PAT)))
 		bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
-#endif
 
 	bo->tbo.bdev = &adev->mman.bdev;
 	amdgpu_bo_placement_from_domain(bo, bp->domain);
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 833e909706a9..c1fb5ad4ab9a 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -226,32 +226,17 @@ int radeon_bo_create(struct radeon_device *rdev,
 	if (rdev->family >= CHIP_RV610 && rdev->family <= CHIP_RV635)
 		bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
 
-#ifdef CONFIG_X86_32
-	/* XXX: Write-combined CPU mappings of GTT seem broken on 32-bit
-	 * See https://bugs.freedesktop.org/show_bug.cgi?id=84627
-	 */
-	bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
-#elif defined(CONFIG_X86) && !defined(CONFIG_X86_PAT)
-	/* Don't try to enable write-combining when it can't work, or things
-	 * may be slow
-	 * See https://bugs.freedesktop.org/show_bug.cgi?id=88758
-	 */
-#ifndef CONFIG_COMPILE_TEST
-#warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \
-	 thanks to write-combining
-#endif
 
-	if (bo->flags & RADEON_GEM_GTT_WC)
-		DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
-			      "better performance thanks to write-combining\n");
-	bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
-#else
-	/* For architectures that don't support WC memory,
-	 * mask out the WC flag from the BO
+	/*
+	 * Don't try to enable write-combined CPU mappings unless we 100%
+	 * positively know it works, otherwise there may be dragons.
+	 *
+	 * See:
+	 *  - https://bugs.freedesktop.org/show_bug.cgi?id=88758
+	 *  - https://bugs.freedesktop.org/show_bug.cgi?id=84627
 	 */
-	if (!drm_arch_can_wc_memory())
-		bo->flags &= ~RADEON_GEM_GTT_WC;
-#endif
+	if (!(IS_ENABLED(CONFIG_X86_64) && IS_ENABLED(CONFIG_X86_PAT)))
+		bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
 
 	radeon_ttm_placement_from_domain(bo, domain);
 	/* Kernel allocation are uninterruptible */
diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h
index bfe1639df02d..6c3960f4c477 100644
--- a/include/drm/drm_cache.h
+++ b/include/drm/drm_cache.h
@@ -40,16 +40,4 @@ void drm_clflush_sg(struct sg_table *st);
 void drm_clflush_virt_range(void *addr, unsigned long length);
 u64 drm_get_max_iomem(void);
 
-
-static inline bool drm_arch_can_wc_memory(void)
-{
-#if defined(CONFIG_PPC) && !defined(CONFIG_NOT_COHERENT_CACHE)
-	return false;
-#elif defined(CONFIG_MIPS) && defined(CONFIG_CPU_LOONGSON3)
-	return false;
-#else
-	return true;
-#endif
-}
-
 #endif
