From f8017fe7b73f60c72ba8312cceed6e13389c9f1e Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Fri, 23 Jul 2021 11:50:45 +0100 Subject: [PATCH] drm/i915/ehl: unconditionally flush the pages on acquire EHL and JSL add the 'Bypass LLC' MOCS entry, which should make it possible for userspace to bypass the GTT caching bits set by the kernel, as per the given object cache_level. This is troublesome since the heavy flush we apply when first acquiring the pages is skipped if the kernel thinks the object is coherent with the GPU. As a result it might be possible to bypass the cache and read the contents of the page directly, which could be stale data. If it's just a case of userspace shooting themselves in the foot then so be it, but since i915 takes the stance of always zeroing memory before handing it to userspace, we need to prevent this. v2: this time actually set cache_dirty in put_pages() v3: move to get_pages() which looks simpler BSpec: 34007 References: dbd3c2e04bef ("Revert "drm/i915/ehl: Update MOCS table for EHL"") Signed-off-by: Matthew Auld Cc: Tejas Upadhyay Cc: Francisco Jerez Cc: Lucas De Marchi Cc: Jon Bloomfield Cc: Chris Wilson Cc: Matt Roper Cc: Daniel Vetter Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210723105045.400841-2-matthew.auld@intel.com --- .../gpu/drm/i915/gem/i915_gem_object_types.h | 6 ++++++ drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 18 ++++++++++++++++++ 2 files changed, 24 insertions(+) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 79de925aecfdb..2471f36aaff38 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -415,6 +415,12 @@ struct drm_i915_gem_object { * Note that on shared LLC platforms we still apply the heavy flush for * I915_CACHE_NONE objects, under the assumption that this is going to * be used for scanout. + * + * Update: On some hardware there is now also the 'Bypass LLC' MOCS + * entry, which defeats our @cache_coherent tracking, since userspace + * can freely bypass the CPU cache when touching the pages with the GPU, + * where the kernel is completely unaware. On such platform we need + * apply the sledgehammer-on-acquire regardless of the @cache_coherent. */ unsigned int cache_dirty:1; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 6a04cce188fcc..11f072193f3b1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -182,6 +182,24 @@ rebuild_st: if (i915_gem_object_needs_bit17_swizzle(obj)) i915_gem_object_do_bit_17_swizzle(obj, st); + /* + * EHL and JSL add the 'Bypass LLC' MOCS entry, which should make it + * possible for userspace to bypass the GTT caching bits set by the + * kernel, as per the given object cache_level. This is troublesome + * since the heavy flush we apply when first gathering the pages is + * skipped if the kernel thinks the object is coherent with the GPU. As + * a result it might be possible to bypass the cache and read the + * contents of the page directly, which could be stale data. If it's + * just a case of userspace shooting themselves in the foot then so be + * it, but since i915 takes the stance of always zeroing memory before + * handing it to userspace, we need to prevent this. + * + * By setting cache_dirty here we make the clflush in set_pages + * unconditional on such platforms. + */ + if (IS_JSL_EHL(i915) && obj->flags & I915_BO_ALLOC_USER) + obj->cache_dirty = true; + __i915_gem_object_set_pages(obj, st, sg_page_sizes); return 0; -- 2.39.5