From patchwork Mon Oct 11 14:56:12 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Matthew Auld X-Patchwork-Id: 12550267 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 810CEC433EF for ; Mon, 11 Oct 2021 15:01:35 +0000 (UTC) Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 47C8A60EE2 for ; Mon, 11 Oct 2021 15:01:35 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org 47C8A60EE2 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=lists.freedesktop.org Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 0726789FCC; Mon, 11 Oct 2021 15:01:20 +0000 (UTC) Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by gabe.freedesktop.org (Postfix) with ESMTPS id 2BAA06E4A2; Mon, 11 Oct 2021 15:01:18 +0000 (UTC) X-IronPort-AV: E=McAfee;i="6200,9189,10134"; a="227179407" X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="227179407" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:56:43 -0700 X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="569984412" Received: from phutoant-mobl3.ccr.corp.intel.com (HELO mwauld-desk1.intel.com) ([10.213.44.196]) by fmsmga002-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:56:41 -0700 From: Matthew Auld To: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org, =?utf-8?q?Thomas_Hellstr=C3=B6m?= Subject: [PATCH v8 1/8] drm/i915/gem: Break out some shmem backend utils Date: Mon, 11 Oct 2021 15:56:12 +0100 Message-Id: <20211011145619.1397733-1-matthew.auld@intel.com> X-Mailer: git-send-email 2.26.3 MIME-Version: 1.0 X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" From: Thomas Hellström Break out some shmem backend utils for future reuse by the TTM backend: shmem_alloc_st(), shmem_free_st() and __shmem_writeback() which we can use to provide a shmem-backed TTM page pool for cached-only TTM buffer objects. Main functional change here is that we now compute the page sizes using the dma segments rather than using the physical page address segments. v2(Reported-by: kernel test robot ) - Make sure we initialise the mapping on the error path in shmem_get_pages() Signed-off-by: Thomas Hellström Reviewed-by: Matthew Auld Signed-off-by: Matthew Auld --- drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 181 +++++++++++++--------- 1 file changed, 106 insertions(+), 75 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 11f072193f3b..36b711ae9e28 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -25,46 +25,61 @@ static void check_release_pagevec(struct pagevec *pvec) cond_resched(); } -static int shmem_get_pages(struct drm_i915_gem_object *obj) +static void shmem_free_st(struct sg_table *st, struct address_space *mapping, + bool dirty, bool backup) { - struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct intel_memory_region *mem = obj->mm.region; - const unsigned long page_count = obj->base.size / PAGE_SIZE; + struct sgt_iter sgt_iter; + struct pagevec pvec; + struct page *page; + + mapping_clear_unevictable(mapping); + + pagevec_init(&pvec); + for_each_sgt_page(page, sgt_iter, st) { + if (dirty) + set_page_dirty(page); + + if (backup) + mark_page_accessed(page); + + if (!pagevec_add(&pvec, page)) + check_release_pagevec(&pvec); + } + if (pagevec_count(&pvec)) + check_release_pagevec(&pvec); + + sg_free_table(st); + kfree(st); +} + +static struct sg_table *shmem_alloc_st(struct drm_i915_private *i915, + size_t size, struct intel_memory_region *mr, + struct address_space *mapping, + unsigned int max_segment) +{ + const unsigned long page_count = size / PAGE_SIZE; unsigned long i; - struct address_space *mapping; struct sg_table *st; struct scatterlist *sg; - struct sgt_iter sgt_iter; struct page *page; unsigned long last_pfn = 0; /* suppress gcc warning */ - unsigned int max_segment = i915_sg_segment_size(); - unsigned int sg_page_sizes; gfp_t noreclaim; int ret; - /* - * Assert that the object is not currently in any GPU domain. As it - * wasn't in the GTT, there shouldn't be any way it could have been in - * a GPU cache - */ - GEM_BUG_ON(obj->read_domains & I915_GEM_GPU_DOMAINS); - GEM_BUG_ON(obj->write_domain & I915_GEM_GPU_DOMAINS); - /* * If there's no chance of allocating enough pages for the whole * object, bail early. */ - if (obj->base.size > resource_size(&mem->region)) - return -ENOMEM; + if (size > resource_size(&mr->region)) + return ERR_PTR(-ENOMEM); st = kmalloc(sizeof(*st), GFP_KERNEL); if (!st) - return -ENOMEM; + return ERR_PTR(-ENOMEM); -rebuild_st: if (sg_alloc_table(st, page_count, GFP_KERNEL)) { kfree(st); - return -ENOMEM; + return ERR_PTR(-ENOMEM); } /* @@ -73,14 +88,12 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj) * * Fail silently without starting the shrinker */ - mapping = obj->base.filp->f_mapping; mapping_set_unevictable(mapping); noreclaim = mapping_gfp_constraint(mapping, ~__GFP_RECLAIM); noreclaim |= __GFP_NORETRY | __GFP_NOWARN; sg = st->sgl; st->nents = 0; - sg_page_sizes = 0; for (i = 0; i < page_count; i++) { const unsigned int shrink[] = { I915_SHRINK_BOUND | I915_SHRINK_UNBOUND, @@ -135,10 +148,9 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj) if (!i || sg->length >= max_segment || page_to_pfn(page) != last_pfn + 1) { - if (i) { - sg_page_sizes |= sg->length; + if (i) sg = sg_next(sg); - } + st->nents++; sg_set_page(sg, page, PAGE_SIZE, 0); } else { @@ -149,14 +161,65 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj) /* Check that the i965g/gm workaround works. */ GEM_BUG_ON(gfp & __GFP_DMA32 && last_pfn >= 0x00100000UL); } - if (sg) { /* loop terminated early; short sg table */ - sg_page_sizes |= sg->length; + if (sg) /* loop terminated early; short sg table */ sg_mark_end(sg); - } /* Trim unused sg entries to avoid wasting memory. */ i915_sg_trim(st); + return st; +err_sg: + sg_mark_end(sg); + if (sg != st->sgl) { + shmem_free_st(st, mapping, false, false); + } else { + mapping_clear_unevictable(mapping); + sg_free_table(st); + kfree(st); + } + + /* + * shmemfs first checks if there is enough memory to allocate the page + * and reports ENOSPC should there be insufficient, along with the usual + * ENOMEM for a genuine allocation failure. + * + * We use ENOSPC in our driver to mean that we have run out of aperture + * space and so want to translate the error from shmemfs back to our + * usual understanding of ENOMEM. + */ + if (ret == -ENOSPC) + ret = -ENOMEM; + + return ERR_PTR(ret); +} + +static int shmem_get_pages(struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *i915 = to_i915(obj->base.dev); + struct intel_memory_region *mem = obj->mm.region; + struct address_space *mapping = obj->base.filp->f_mapping; + const unsigned long page_count = obj->base.size / PAGE_SIZE; + unsigned int max_segment = i915_sg_segment_size(); + struct sg_table *st; + struct sgt_iter sgt_iter; + struct page *page; + int ret; + + /* + * Assert that the object is not currently in any GPU domain. As it + * wasn't in the GTT, there shouldn't be any way it could have been in + * a GPU cache + */ + GEM_BUG_ON(obj->read_domains & I915_GEM_GPU_DOMAINS); + GEM_BUG_ON(obj->write_domain & I915_GEM_GPU_DOMAINS); + +rebuild_st: + st = shmem_alloc_st(i915, obj->base.size, mem, mapping, max_segment); + if (IS_ERR(st)) { + ret = PTR_ERR(st); + goto err_st; + } + ret = i915_gem_gtt_prepare_pages(obj, st); if (ret) { /* @@ -168,6 +231,7 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj) for_each_sgt_page(page, sgt_iter, st) put_page(page); sg_free_table(st); + kfree(st); max_segment = PAGE_SIZE; goto rebuild_st; @@ -200,28 +264,12 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj) 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); + __i915_gem_object_set_pages(obj, st, i915_sg_dma_sizes(st->sgl)); return 0; -err_sg: - sg_mark_end(sg); err_pages: - mapping_clear_unevictable(mapping); - if (sg != st->sgl) { - struct pagevec pvec; - - pagevec_init(&pvec); - for_each_sgt_page(page, sgt_iter, st) { - if (!pagevec_add(&pvec, page)) - check_release_pagevec(&pvec); - } - if (pagevec_count(&pvec)) - check_release_pagevec(&pvec); - } - sg_free_table(st); - kfree(st); - + shmem_free_st(st, mapping, false, false); /* * shmemfs first checks if there is enough memory to allocate the page * and reports ENOSPC should there be insufficient, along with the usual @@ -231,6 +279,7 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj) * space and so want to translate the error from shmemfs back to our * usual understanding of ENOMEM. */ +err_st: if (ret == -ENOSPC) ret = -ENOMEM; @@ -251,10 +300,8 @@ shmem_truncate(struct drm_i915_gem_object *obj) obj->mm.pages = ERR_PTR(-EFAULT); } -static void -shmem_writeback(struct drm_i915_gem_object *obj) +static void __shmem_writeback(size_t size, struct address_space *mapping) { - struct address_space *mapping; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = SWAP_CLUSTER_MAX, @@ -270,10 +317,9 @@ shmem_writeback(struct drm_i915_gem_object *obj) * instead of invoking writeback so they are aged and paged out * as normal. */ - mapping = obj->base.filp->f_mapping; /* Begin writeback on each dirty page */ - for (i = 0; i < obj->base.size >> PAGE_SHIFT; i++) { + for (i = 0; i < size >> PAGE_SHIFT; i++) { struct page *page; page = find_lock_page(mapping, i); @@ -296,6 +342,12 @@ shmem_writeback(struct drm_i915_gem_object *obj) } } +static void +shmem_writeback(struct drm_i915_gem_object *obj) +{ + __shmem_writeback(obj->base.size, obj->base.filp->f_mapping); +} + void __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj, struct sg_table *pages, @@ -316,11 +368,6 @@ __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj, void i915_gem_object_put_pages_shmem(struct drm_i915_gem_object *obj, struct sg_table *pages) { - struct sgt_iter sgt_iter; - struct pagevec pvec; - struct page *page; - - GEM_WARN_ON(IS_DGFX(to_i915(obj->base.dev))); __i915_gem_object_release_shmem(obj, pages, true); i915_gem_gtt_finish_pages(obj, pages); @@ -328,25 +375,9 @@ void i915_gem_object_put_pages_shmem(struct drm_i915_gem_object *obj, struct sg_ if (i915_gem_object_needs_bit17_swizzle(obj)) i915_gem_object_save_bit_17_swizzle(obj, pages); - mapping_clear_unevictable(file_inode(obj->base.filp)->i_mapping); - - pagevec_init(&pvec); - for_each_sgt_page(page, sgt_iter, pages) { - if (obj->mm.dirty) - set_page_dirty(page); - - if (obj->mm.madv == I915_MADV_WILLNEED) - mark_page_accessed(page); - - if (!pagevec_add(&pvec, page)) - check_release_pagevec(&pvec); - } - if (pagevec_count(&pvec)) - check_release_pagevec(&pvec); + shmem_free_st(pages, file_inode(obj->base.filp)->i_mapping, + obj->mm.dirty, obj->mm.madv == I915_MADV_WILLNEED); obj->mm.dirty = false; - - sg_free_table(pages); - kfree(pages); } static void From patchwork Mon Oct 11 14:56:13 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Matthew Auld X-Patchwork-Id: 12550271 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id AD384C433F5 for ; Mon, 11 Oct 2021 15:01:43 +0000 (UTC) Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 7B9DC60EE2 for ; Mon, 11 Oct 2021 15:01:43 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org 7B9DC60EE2 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=lists.freedesktop.org Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 7B8D96E506; Mon, 11 Oct 2021 15:01:22 +0000 (UTC) Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by gabe.freedesktop.org (Postfix) with ESMTPS id 1337E89FCC; Mon, 11 Oct 2021 15:01:19 +0000 (UTC) X-IronPort-AV: E=McAfee;i="6200,9189,10134"; a="227179418" X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="227179418" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:56:47 -0700 X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="569984432" Received: from phutoant-mobl3.ccr.corp.intel.com (HELO mwauld-desk1.intel.com) ([10.213.44.196]) by fmsmga002-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:56:44 -0700 From: Matthew Auld To: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org, =?utf-8?q?Thomas_Hellstr=C3=B6m?= , =?utf-8?q?Christian_K=C3=B6nig?= , Oak Zeng Subject: [PATCH v8 2/8] drm/i915/ttm: add tt shmem backend Date: Mon, 11 Oct 2021 15:56:13 +0100 Message-Id: <20211011145619.1397733-2-matthew.auld@intel.com> X-Mailer: git-send-email 2.26.3 In-Reply-To: <20211011145619.1397733-1-matthew.auld@intel.com> References: <20211011145619.1397733-1-matthew.auld@intel.com> MIME-Version: 1.0 X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" For cached objects we can allocate our pages directly in shmem. This should make it possible(in a later patch) to utilise the existing i915-gem shrinker code for such objects. For now this is still disabled. v2(Thomas): - Add optional try_to_writeback hook for objects. Importantly we need to check if the object is even still shrinkable; in between us dropping the shrinker LRU lock and acquiring the object lock it could for example have been moved. Also we need to differentiate between "lazy" shrinking and the immediate writeback mode. Also later we need to handle objects which don't even have mm.pages, so bundling this into put_pages() would require somehow handling that edge case, hence just letting the ttm backend handle everything in try_to_writeback doesn't seem too bad. v3(Thomas): - Likely a bad idea to touch the object from the unpopulate hook, since it's not possible to hold a reference, without also creating circular dependency, so likely this is too fragile. For now just ensure we at least mark the pages as dirty/accessed when called from the shrinker on WILLNEED objects. - s/try_to_writeback/shrinker_release_pages, since this can do more than just writeback. - Get rid of do_backup boolean and just set the SWAPPED flag prior to calling unpopulate. - Keep shmem_tt as lowest priority for the TTM LRU bo_swapout walk, since these just get skipped anyway. We can try to come up with something better later. v4(Thomas): - s/PCI_DMA/DMA/. Also drop NO_KERNEL_MAPPING and NO_WARN, which apparently doesn't do anything with streaming mappings. - Just pass along the error for ->truncate, and assume nothing. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Christian König Cc: Oak Zeng Reviewed-by: Thomas Hellström Acked-by: Oak Zeng --- drivers/gpu/drm/i915/gem/i915_gem_object.h | 11 +- .../gpu/drm/i915/gem/i915_gem_object_types.h | 4 +- drivers/gpu/drm/i915/gem/i915_gem_pages.c | 6 +- drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 18 +- drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 17 +- drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 233 ++++++++++++++++-- 6 files changed, 247 insertions(+), 42 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 9df3ee60604e..e641db297e0e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -93,7 +93,6 @@ void i915_gem_flush_free_objects(struct drm_i915_private *i915); struct sg_table * __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj); -void i915_gem_object_truncate(struct drm_i915_gem_object *obj); /** * i915_gem_object_lookup_rcu - look up a temporary GEM object from its handle @@ -449,7 +448,7 @@ i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj) } int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj); -void i915_gem_object_truncate(struct drm_i915_gem_object *obj); +int i915_gem_object_truncate(struct drm_i915_gem_object *obj); void i915_gem_object_writeback(struct drm_i915_gem_object *obj); /** @@ -612,6 +611,14 @@ int i915_gem_object_wait_migration(struct drm_i915_gem_object *obj, bool i915_gem_object_placement_possible(struct drm_i915_gem_object *obj, enum intel_memory_type type); +struct sg_table *shmem_alloc_st(struct drm_i915_private *i915, + size_t size, struct intel_memory_region *mr, + struct address_space *mapping, + unsigned int max_segment); +void shmem_free_st(struct sg_table *st, struct address_space *mapping, + bool dirty, bool backup); +void __shmem_writeback(size_t size, struct address_space *mapping); + #ifdef CONFIG_MMU_NOTIFIER static inline bool i915_gem_object_is_userptr(struct drm_i915_gem_object *obj) 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 7c3da4e3e737..7dd5f804aab3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -54,8 +54,10 @@ struct drm_i915_gem_object_ops { int (*get_pages)(struct drm_i915_gem_object *obj); void (*put_pages)(struct drm_i915_gem_object *obj, struct sg_table *pages); - void (*truncate)(struct drm_i915_gem_object *obj); + int (*truncate)(struct drm_i915_gem_object *obj); void (*writeback)(struct drm_i915_gem_object *obj); + int (*shrinker_release_pages)(struct drm_i915_gem_object *obj, + bool should_writeback); int (*pread)(struct drm_i915_gem_object *obj, const struct drm_i915_gem_pread *arg); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 8eb1c3a6fc9c..ea6d9b3d2d6b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -158,11 +158,13 @@ int i915_gem_object_pin_pages_unlocked(struct drm_i915_gem_object *obj) } /* Immediately discard the backing storage */ -void i915_gem_object_truncate(struct drm_i915_gem_object *obj) +int i915_gem_object_truncate(struct drm_i915_gem_object *obj) { drm_gem_free_mmap_offset(&obj->base); if (obj->ops->truncate) - obj->ops->truncate(obj); + return obj->ops->truncate(obj); + + return 0; } /* Try to discard unwanted pages */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 36b711ae9e28..8375dc23f233 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -25,8 +25,8 @@ static void check_release_pagevec(struct pagevec *pvec) cond_resched(); } -static void shmem_free_st(struct sg_table *st, struct address_space *mapping, - bool dirty, bool backup) +void shmem_free_st(struct sg_table *st, struct address_space *mapping, + bool dirty, bool backup) { struct sgt_iter sgt_iter; struct pagevec pvec; @@ -52,10 +52,10 @@ static void shmem_free_st(struct sg_table *st, struct address_space *mapping, kfree(st); } -static struct sg_table *shmem_alloc_st(struct drm_i915_private *i915, - size_t size, struct intel_memory_region *mr, - struct address_space *mapping, - unsigned int max_segment) +struct sg_table *shmem_alloc_st(struct drm_i915_private *i915, + size_t size, struct intel_memory_region *mr, + struct address_space *mapping, + unsigned int max_segment) { const unsigned long page_count = size / PAGE_SIZE; unsigned long i; @@ -286,7 +286,7 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj) return ret; } -static void +static int shmem_truncate(struct drm_i915_gem_object *obj) { /* @@ -298,9 +298,11 @@ shmem_truncate(struct drm_i915_gem_object *obj) shmem_truncate_range(file_inode(obj->base.filp), 0, (loff_t)-1); obj->mm.madv = __I915_MADV_PURGED; obj->mm.pages = ERR_PTR(-EFAULT); + + return 0; } -static void __shmem_writeback(size_t size, struct address_space *mapping) +void __shmem_writeback(size_t size, struct address_space *mapping) { struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index 5ab136ffdeb2..ae2a8d54b7a4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -56,19 +56,24 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj, return false; } -static void try_to_writeback(struct drm_i915_gem_object *obj, - unsigned int flags) +static int try_to_writeback(struct drm_i915_gem_object *obj, unsigned int flags) { + if (obj->ops->shrinker_release_pages) + return obj->ops->shrinker_release_pages(obj, + flags & I915_SHRINK_WRITEBACK); + switch (obj->mm.madv) { case I915_MADV_DONTNEED: i915_gem_object_truncate(obj); - return; + return 0; case __I915_MADV_PURGED: - return; + return 0; } if (flags & I915_SHRINK_WRITEBACK) i915_gem_object_writeback(obj); + + return 0; } /** @@ -222,8 +227,8 @@ i915_gem_shrink(struct i915_gem_ww_ctx *ww, } if (!__i915_gem_object_put_pages(obj)) { - try_to_writeback(obj, shrink); - count += obj->base.size >> PAGE_SHIFT; + if (!try_to_writeback(obj, shrink)) + count += obj->base.size >> PAGE_SHIFT; } if (!ww) i915_gem_object_unlock(obj); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 9914e8fadb2c..ff8bd4c6fd2e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -35,6 +35,8 @@ * @ttm: The base TTM page vector. * @dev: The struct device used for dma mapping and unmapping. * @cached_st: The cached scatter-gather table. + * @is_shmem: Set if using shmem. + * @filp: The shmem file, if using shmem backend. * * Note that DMA may be going on right up to the point where the page- * vector is unpopulated in delayed destroy. Hence keep the @@ -46,6 +48,9 @@ struct i915_ttm_tt { struct ttm_tt ttm; struct device *dev; struct sg_table *cached_st; + + bool is_shmem; + struct file *filp; }; static const struct ttm_place sys_placement_flags = { @@ -179,12 +184,88 @@ i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj, placement->busy_placement = busy; } +static int i915_ttm_tt_shmem_populate(struct ttm_device *bdev, + struct ttm_tt *ttm, + struct ttm_operation_ctx *ctx) +{ + struct drm_i915_private *i915 = container_of(bdev, typeof(*i915), bdev); + struct intel_memory_region *mr = i915->mm.regions[INTEL_MEMORY_SYSTEM]; + struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); + const unsigned int max_segment = i915_sg_segment_size(); + const size_t size = ttm->num_pages << PAGE_SHIFT; + struct file *filp = i915_tt->filp; + struct sgt_iter sgt_iter; + struct sg_table *st; + struct page *page; + unsigned long i; + int err; + + if (!filp) { + struct address_space *mapping; + gfp_t mask; + + filp = shmem_file_setup("i915-shmem-tt", size, VM_NORESERVE); + if (IS_ERR(filp)) + return PTR_ERR(filp); + + mask = GFP_HIGHUSER | __GFP_RECLAIMABLE; + + mapping = filp->f_mapping; + mapping_set_gfp_mask(mapping, mask); + GEM_BUG_ON(!(mapping_gfp_mask(mapping) & __GFP_RECLAIM)); + + i915_tt->filp = filp; + } + + st = shmem_alloc_st(i915, size, mr, filp->f_mapping, max_segment); + if (IS_ERR(st)) + return PTR_ERR(st); + + err = dma_map_sg_attrs(i915_tt->dev, + st->sgl, st->nents, + DMA_BIDIRECTIONAL, + DMA_ATTR_SKIP_CPU_SYNC); + if (err <= 0) { + err = -EINVAL; + goto err_free_st; + } + + i = 0; + for_each_sgt_page(page, sgt_iter, st) + ttm->pages[i++] = page; + + if (ttm->page_flags & TTM_TT_FLAG_SWAPPED) + ttm->page_flags &= ~TTM_TT_FLAG_SWAPPED; + + i915_tt->cached_st = st; + return 0; + +err_free_st: + shmem_free_st(st, filp->f_mapping, false, false); + return err; +} + +static void i915_ttm_tt_shmem_unpopulate(struct ttm_tt *ttm) +{ + struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); + bool backup = ttm->page_flags & TTM_TT_FLAG_SWAPPED; + + dma_unmap_sg(i915_tt->dev, i915_tt->cached_st->sgl, + i915_tt->cached_st->nents, + DMA_BIDIRECTIONAL); + + shmem_free_st(fetch_and_zero(&i915_tt->cached_st), + file_inode(i915_tt->filp)->i_mapping, + backup, backup); +} + static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, uint32_t page_flags) { struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, bo->resource->mem_type); struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + enum ttm_caching caching = i915_ttm_select_tt_caching(obj); struct i915_ttm_tt *i915_tt; int ret; @@ -196,36 +277,62 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, man->use_tt) page_flags |= TTM_TT_FLAG_ZERO_ALLOC; - ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags, - i915_ttm_select_tt_caching(obj)); - if (ret) { - kfree(i915_tt); - return NULL; + if (i915_gem_object_is_shrinkable(obj) && caching == ttm_cached) { + page_flags |= TTM_TT_FLAG_EXTERNAL | + TTM_TT_FLAG_EXTERNAL_MAPPABLE; + i915_tt->is_shmem = true; } + ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags, caching); + if (ret) + goto err_free; + i915_tt->dev = obj->base.dev->dev; return &i915_tt->ttm; + +err_free: + kfree(i915_tt); + return NULL; +} + +static int i915_ttm_tt_populate(struct ttm_device *bdev, + struct ttm_tt *ttm, + struct ttm_operation_ctx *ctx) +{ + struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); + + if (i915_tt->is_shmem) + return i915_ttm_tt_shmem_populate(bdev, ttm, ctx); + + return ttm_pool_alloc(&bdev->pool, ttm, ctx); } static void i915_ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm) { struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); - if (i915_tt->cached_st) { - dma_unmap_sgtable(i915_tt->dev, i915_tt->cached_st, - DMA_BIDIRECTIONAL, 0); - sg_free_table(i915_tt->cached_st); - kfree(i915_tt->cached_st); - i915_tt->cached_st = NULL; + if (i915_tt->is_shmem) { + i915_ttm_tt_shmem_unpopulate(ttm); + } else { + if (i915_tt->cached_st) { + dma_unmap_sgtable(i915_tt->dev, i915_tt->cached_st, + DMA_BIDIRECTIONAL, 0); + sg_free_table(i915_tt->cached_st); + kfree(i915_tt->cached_st); + i915_tt->cached_st = NULL; + } + ttm_pool_free(&bdev->pool, ttm); } - ttm_pool_free(&bdev->pool, ttm); } static void i915_ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm) { struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); + if (i915_tt->filp) + fput(i915_tt->filp); + ttm_tt_fini(ttm); kfree(i915_tt); } @@ -235,6 +342,14 @@ static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo, { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + /* + * EXTERNAL objects should never be swapped out by TTM, instead we need + * to handle that ourselves. TTM will already skip such objects for us, + * but we would like to avoid grabbing locks for no good reason. + */ + if (bo->ttm && bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL) + return -EBUSY; + /* Will do for now. Our pinned objects are still on TTM's LRU lists */ return i915_gem_object_evictable(obj); } @@ -328,9 +443,11 @@ static void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj) i915_gem_object_set_cache_coherency(obj, cache_level); } -static void i915_ttm_purge(struct drm_i915_gem_object *obj) +static int i915_ttm_purge(struct drm_i915_gem_object *obj) { struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + struct i915_ttm_tt *i915_tt = + container_of(bo->ttm, typeof(*i915_tt), ttm); struct ttm_operation_ctx ctx = { .interruptible = true, .no_wait_gpu = false, @@ -339,17 +456,74 @@ static void i915_ttm_purge(struct drm_i915_gem_object *obj) int ret; if (obj->mm.madv == __I915_MADV_PURGED) - return; + return 0; - /* TTM's purge interface. Note that we might be reentering. */ ret = ttm_bo_validate(bo, &place, &ctx); - if (!ret) { - obj->write_domain = 0; - obj->read_domains = 0; - i915_ttm_adjust_gem_after_move(obj); - i915_ttm_free_cached_io_st(obj); - obj->mm.madv = __I915_MADV_PURGED; + if (ret) + return ret; + + if (bo->ttm && i915_tt->filp) { + /* + * The below fput(which eventually calls shmem_truncate) might + * be delayed by worker, so when directly called to purge the + * pages(like by the shrinker) we should try to be more + * aggressive and release the pages immediately. + */ + shmem_truncate_range(file_inode(i915_tt->filp), + 0, (loff_t)-1); + fput(fetch_and_zero(&i915_tt->filp)); } + + obj->write_domain = 0; + obj->read_domains = 0; + i915_ttm_adjust_gem_after_move(obj); + i915_ttm_free_cached_io_st(obj); + obj->mm.madv = __I915_MADV_PURGED; + return 0; +} + +static int i915_ttm_shrinker_release_pages(struct drm_i915_gem_object *obj, + bool should_writeback) +{ + struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + struct i915_ttm_tt *i915_tt = + container_of(bo->ttm, typeof(*i915_tt), ttm); + struct ttm_operation_ctx ctx = { + .interruptible = true, + .no_wait_gpu = false, + }; + struct ttm_placement place = {}; + int ret; + + if (!bo->ttm || bo->resource->mem_type != TTM_PL_SYSTEM) + return 0; + + GEM_BUG_ON(!i915_tt->is_shmem); + + if (!i915_tt->filp) + return 0; + + switch (obj->mm.madv) { + case I915_MADV_DONTNEED: + return i915_ttm_purge(obj); + case __I915_MADV_PURGED: + return 0; + } + + if (bo->ttm->page_flags & TTM_TT_FLAG_SWAPPED) + return 0; + + bo->ttm->page_flags |= TTM_TT_FLAG_SWAPPED; + ret = ttm_bo_validate(bo, &place, &ctx); + if (ret) { + bo->ttm->page_flags &= ~TTM_TT_FLAG_SWAPPED; + return ret; + } + + if (should_writeback) + __shmem_writeback(obj->base.size, i915_tt->filp->f_mapping); + + return 0; } static void i915_ttm_swap_notify(struct ttm_buffer_object *bo) @@ -620,6 +794,7 @@ static unsigned long i915_ttm_io_mem_pfn(struct ttm_buffer_object *bo, static struct ttm_device_funcs i915_ttm_bo_driver = { .ttm_tt_create = i915_ttm_tt_create, + .ttm_tt_populate = i915_ttm_tt_populate, .ttm_tt_unpopulate = i915_ttm_tt_unpopulate, .ttm_tt_destroy = i915_ttm_tt_destroy, .eviction_valuable = i915_ttm_eviction_valuable, @@ -687,12 +862,17 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj, } if (!i915_gem_object_has_pages(obj)) { + struct i915_ttm_tt *i915_tt = + container_of(bo->ttm, typeof(*i915_tt), ttm); + /* Object either has a page vector or is an iomem object */ st = bo->ttm ? i915_ttm_tt_get_st(bo->ttm) : obj->ttm.cached_io_st; if (IS_ERR(st)) return PTR_ERR(st); __i915_gem_object_set_pages(obj, st, i915_sg_dma_sizes(st->sgl)); + if (!bo->ttm || !i915_tt->is_shmem) + i915_gem_object_make_unshrinkable(obj); } return ret; @@ -772,6 +952,8 @@ static void i915_ttm_put_pages(struct drm_i915_gem_object *obj, static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj) { struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + struct i915_ttm_tt *i915_tt = + container_of(bo->ttm, typeof(*i915_tt), ttm); /* * Don't manipulate the TTM LRUs while in TTM bo destruction. @@ -784,7 +966,10 @@ static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj) * Put on the correct LRU list depending on the MADV status */ spin_lock(&bo->bdev->lru_lock); - if (obj->mm.madv != I915_MADV_WILLNEED) { + if (bo->ttm && i915_tt->filp) { + /* Try to keep shmem_tt from being considered for shrinking. */ + bo->priority = TTM_MAX_BO_PRIORITY - 1; + } else if (obj->mm.madv != I915_MADV_WILLNEED) { bo->priority = I915_TTM_PRIO_PURGE; } else if (!i915_gem_object_has_pages(obj)) { if (bo->priority < I915_TTM_PRIO_HAS_PAGES) @@ -886,9 +1071,12 @@ static const struct drm_i915_gem_object_ops i915_gem_ttm_obj_ops = { .get_pages = i915_ttm_get_pages, .put_pages = i915_ttm_put_pages, .truncate = i915_ttm_purge, + .shrinker_release_pages = i915_ttm_shrinker_release_pages, + .adjust_lru = i915_ttm_adjust_lru, .delayed_free = i915_ttm_delayed_free, .migrate = i915_ttm_migrate, + .mmap_offset = i915_ttm_mmap_offset, .mmap_ops = &vm_ops_ttm, }; @@ -946,7 +1134,6 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem, obj->mm.region = intel_memory_region_get(mem); INIT_LIST_HEAD(&obj->mm.region_link); - i915_gem_object_make_unshrinkable(obj); INIT_RADIX_TREE(&obj->ttm.get_io_page.radix, GFP_KERNEL | __GFP_NOWARN); mutex_init(&obj->ttm.get_io_page.lock); bo_type = (obj->flags & I915_BO_ALLOC_USER) ? ttm_bo_type_device : From patchwork Mon Oct 11 14:56:14 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Matthew Auld X-Patchwork-Id: 12550269 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 22A48C433FE for ; Mon, 11 Oct 2021 15:01:41 +0000 (UTC) Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id E8C3260EDF for ; Mon, 11 Oct 2021 15:01:40 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org E8C3260EDF Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=lists.freedesktop.org Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 92F1C6E508; Mon, 11 Oct 2021 15:01:21 +0000 (UTC) Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by gabe.freedesktop.org (Postfix) with ESMTPS id E22536E4A2; Mon, 11 Oct 2021 15:01:18 +0000 (UTC) X-IronPort-AV: E=McAfee;i="6200,9189,10134"; a="227179424" X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="227179424" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:56:50 -0700 X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="569984437" Received: from phutoant-mobl3.ccr.corp.intel.com (HELO mwauld-desk1.intel.com) ([10.213.44.196]) by fmsmga002-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:56:47 -0700 From: Matthew Auld To: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org, =?utf-8?q?Thomas_Hellstr=C3=B6m?= Subject: [PATCH v8 3/8] drm/i915/gtt: drop unneeded make_unshrinkable Date: Mon, 11 Oct 2021 15:56:14 +0100 Message-Id: <20211011145619.1397733-3-matthew.auld@intel.com> X-Mailer: git-send-email 2.26.3 In-Reply-To: <20211011145619.1397733-1-matthew.auld@intel.com> References: <20211011145619.1397733-1-matthew.auld@intel.com> MIME-Version: 1.0 X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" We already do this when mapping the pages. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Thomas Hellström --- drivers/gpu/drm/i915/gt/gen6_ppgtt.c | 1 - drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c index 890191f286e3..baea9770200a 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c @@ -185,7 +185,6 @@ static void gen6_alloc_va_range(struct i915_address_space *vm, pt = stash->pt[0]; __i915_gem_object_pin_pages(pt->base); - i915_gem_object_make_unshrinkable(pt->base); fill32_px(pt, vm->scratch[0]->encode); diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index 037a9a6e4889..8af2f709571c 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -301,7 +301,6 @@ static void __gen8_ppgtt_alloc(struct i915_address_space * const vm, pt = stash->pt[!!lvl]; __i915_gem_object_pin_pages(pt->base); - i915_gem_object_make_unshrinkable(pt->base); fill_px(pt, vm->scratch[lvl]->encode); From patchwork Mon Oct 11 14:56:15 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Matthew Auld X-Patchwork-Id: 12550265 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 4ACEDC433F5 for ; Mon, 11 Oct 2021 15:01:27 +0000 (UTC) Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 16C3A60EDF for ; Mon, 11 Oct 2021 15:01:27 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org 16C3A60EDF Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=lists.freedesktop.org Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 720286E4A2; Mon, 11 Oct 2021 15:01:19 +0000 (UTC) Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by gabe.freedesktop.org (Postfix) with ESMTPS id D0F2589FCC; Mon, 11 Oct 2021 15:01:17 +0000 (UTC) X-IronPort-AV: E=McAfee;i="6200,9189,10134"; a="227179432" X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="227179432" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:56:52 -0700 X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="569984453" Received: from phutoant-mobl3.ccr.corp.intel.com (HELO mwauld-desk1.intel.com) ([10.213.44.196]) by fmsmga002-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:56:50 -0700 From: Matthew Auld To: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org, =?utf-8?q?Thomas_Hellstr=C3=B6m?= Subject: [PATCH v8 4/8] drm/i915: drop unneeded make_unshrinkable in free_object Date: Mon, 11 Oct 2021 15:56:15 +0100 Message-Id: <20211011145619.1397733-4-matthew.auld@intel.com> X-Mailer: git-send-email 2.26.3 In-Reply-To: <20211011145619.1397733-1-matthew.auld@intel.com> References: <20211011145619.1397733-1-matthew.auld@intel.com> MIME-Version: 1.0 X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" The comment here is no longer accurate, since the current shrinker code requires a full ref before touching any objects. Also unset_pages() should already do the required make_unshrinkable() for us, if needed, which is also nicely balanced with set_pages(). Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Thomas Hellström --- drivers/gpu/drm/i915/gem/i915_gem_object.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 76ce6a1500bc..1dc3c1940c32 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -337,15 +337,6 @@ static void i915_gem_free_object(struct drm_gem_object *gem_obj) */ atomic_inc(&i915->mm.free_count); - /* - * This serializes freeing with the shrinker. Since the free - * is delayed, first by RCU then by the workqueue, we want the - * shrinker to be able to free pages of unreferenced objects, - * or else we may oom whilst there are plenty of deferred - * freed objects. - */ - i915_gem_object_make_unshrinkable(obj); - /* * Since we require blocking on struct_mutex to unbind the freed * object from the GPU before releasing resources back to the From patchwork Mon Oct 11 14:56:16 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Matthew Auld X-Patchwork-Id: 12550273 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id BDDE4C433FE for ; Mon, 11 Oct 2021 15:01:45 +0000 (UTC) Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 8D3AB60EE2 for ; Mon, 11 Oct 2021 15:01:45 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org 8D3AB60EE2 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=lists.freedesktop.org Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 628936E504; Mon, 11 Oct 2021 15:01:22 +0000 (UTC) Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by gabe.freedesktop.org (Postfix) with ESMTPS id BC57B89FCC; Mon, 11 Oct 2021 15:01:18 +0000 (UTC) X-IronPort-AV: E=McAfee;i="6200,9189,10134"; a="227179438" X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="227179438" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:56:56 -0700 X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="569984469" Received: from phutoant-mobl3.ccr.corp.intel.com (HELO mwauld-desk1.intel.com) ([10.213.44.196]) by fmsmga002-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:56:53 -0700 From: Matthew Auld To: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org, =?utf-8?q?Thomas_Hellstr=C3=B6m?= Subject: [PATCH v8 5/8] drm/i915: add some kernel-doc for shrink_pin and friends Date: Mon, 11 Oct 2021 15:56:16 +0100 Message-Id: <20211011145619.1397733-5-matthew.auld@intel.com> X-Mailer: git-send-email 2.26.3 In-Reply-To: <20211011145619.1397733-1-matthew.auld@intel.com> References: <20211011145619.1397733-1-matthew.auld@intel.com> MIME-Version: 1.0 X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" Attempt to document shrink_pin and the other relevant interfaces that interact with it, before we start messing with it. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Thomas Hellström --- .../gpu/drm/i915/gem/i915_gem_object_types.h | 24 +++++++++++++- drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 31 +++++++++++++++++++ 2 files changed, 54 insertions(+), 1 deletion(-) 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 7dd5f804aab3..f4233c4e8d2e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -461,6 +461,28 @@ struct drm_i915_gem_object { * instead go through the pin/unpin interfaces. */ atomic_t pages_pin_count; + + /** + * @shrink_pin: Prevents the pages from being made visible to + * the shrinker, while the shrink_pin is non-zero. Most users + * should pretty much never have to care about this, outside of + * some special use cases. + * + * By default most objects will start out as visible to the + * shrinker(if I915_GEM_OBJECT_IS_SHRINKABLE) as soon as the + * backing pages are attached to the object, like in + * __i915_gem_object_set_pages(). They will then be removed the + * shrinker list once the pages are released. + * + * The @shrink_pin is incremented by calling + * i915_gem_object_make_unshrinkable(), which will also remove + * the object from the shrinker list, if the pin count was zero. + * + * Callers will then typically call + * i915_gem_object_make_shrinkable() or + * i915_gem_object_make_purgeable() to decrement the pin count, + * and make the pages visible again. + */ atomic_t shrink_pin; /** @@ -522,7 +544,7 @@ struct drm_i915_gem_object { struct i915_gem_object_page_iter get_dma_page; /** - * Element within i915->mm.unbound_list or i915->mm.bound_list, + * Element within i915->mm.shrink_list or i915->mm.purge_list, * locked by i915->mm.obj_lock. */ struct list_head link; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index ae2a8d54b7a4..66121fedc655 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -463,6 +463,16 @@ void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915, #define obj_to_i915(obj__) to_i915((obj__)->base.dev) +/** + * i915_gem_object_make_unshrinkable - Hide the object from the shrinker. By + * default all object types that support shrinking(see IS_SHRINKABLE), will also + * make the object visible to the shrinker after allocating the system memory + * pages. + * @obj: The GEM object. + * + * This is typically used for special kernel internal objects that can't be + * easily processed by the shrinker, like if they are perma-pinned. + */ void i915_gem_object_make_unshrinkable(struct drm_i915_gem_object *obj) { struct drm_i915_private *i915 = obj_to_i915(obj); @@ -513,12 +523,33 @@ static void __i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj, spin_unlock_irqrestore(&i915->mm.obj_lock, flags); } +/** + * i915_gem_object_make_shrinkable - Move the object to the tail of the + * shrinkable list. Objects on this list might be swapped out. Used with + * WILLNEED objects. + * @obj: The GEM object. + * + * MUST only be called on objects which have backing pages. + * + * MUST be balanced with previous call to i915_gem_object_make_unshrinkable(). + */ void i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj) { __i915_gem_object_make_shrinkable(obj, &obj_to_i915(obj)->mm.shrink_list); } +/** + * i915_gem_object_make_purgeable - Move the object to the tail of the purgeable + * list. Used with DONTNEED objects. Unlike with shrinkable objects, the + * shrinker will attempt to discard the backing pages, instead of trying to swap + * them out. + * @obj: The GEM object. + * + * MUST only be called on objects which have backing pages. + * + * MUST be balanced with previous call to i915_gem_object_make_unshrinkable(). + */ void i915_gem_object_make_purgeable(struct drm_i915_gem_object *obj) { __i915_gem_object_make_shrinkable(obj, From patchwork Mon Oct 11 14:56:17 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Matthew Auld X-Patchwork-Id: 12550275 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8E6FAC433F5 for ; Mon, 11 Oct 2021 15:01:47 +0000 (UTC) Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 63C3B60EE5 for ; Mon, 11 Oct 2021 15:01:47 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org 63C3B60EE5 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=lists.freedesktop.org Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 9A3C76E50C; Mon, 11 Oct 2021 15:01:22 +0000 (UTC) Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by gabe.freedesktop.org (Postfix) with ESMTPS id 58C8D89FCC; Mon, 11 Oct 2021 15:01:19 +0000 (UTC) X-IronPort-AV: E=McAfee;i="6200,9189,10134"; a="227179448" X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="227179448" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:56:59 -0700 X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="569984479" Received: from phutoant-mobl3.ccr.corp.intel.com (HELO mwauld-desk1.intel.com) ([10.213.44.196]) by fmsmga002-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:56:56 -0700 From: Matthew Auld To: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org, =?utf-8?q?Thomas_Hellstr=C3=B6m?= Subject: [PATCH v8 6/8] drm/i915/ttm: move shrinker management into adjust_lru Date: Mon, 11 Oct 2021 15:56:17 +0100 Message-Id: <20211011145619.1397733-6-matthew.auld@intel.com> X-Mailer: git-send-email 2.26.3 In-Reply-To: <20211011145619.1397733-1-matthew.auld@intel.com> References: <20211011145619.1397733-1-matthew.auld@intel.com> MIME-Version: 1.0 X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" We currently just evict lmem objects to system memory when under memory pressure. For this case we might lack the usual object mm.pages, which effectively hides the pages from the i915-gem shrinker, until we actually "attach" the TT to the object, or in the case of lmem-only objects it just gets migrated back to lmem when touched again. For all cases we can just adjust the i915 shrinker LRU each time we also adjust the TTM LRU. The two cases we care about are: 1) When something is moved by TTM, including when initially populating an object. Importantly this covers the case where TTM moves something from lmem <-> smem, outside of the normal get_pages() interface, which should still ensure the shmem pages underneath are reclaimable. 2) When calling into i915_gem_object_unlock(). The unlock should ensure the object is removed from the shinker LRU, if it was indeed swapped out, or just purged, when the shrinker drops the object lock. v2(Thomas): - Handle managing the shrinker LRU in adjust_lru, where it is always safe to touch the object. v3(Thomas): - Pretty much a re-write. This time piggy back off the shrink_pin stuff, which actually seems to fit quite well for what we want here. v4(Thomas): - Just use a simple boolean for tracking ttm_shrinkable. v5: - Ensure we call adjust_lru when faulting the object, to ensure the pages are visible to the shrinker, if needed. - Add back the adjust_lru when in i915_ttm_move (Thomas) Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Thomas Hellström #v4 --- drivers/gpu/drm/i915/gem/i915_gem_object.h | 8 ++ .../gpu/drm/i915/gem/i915_gem_object_types.h | 14 +++- drivers/gpu/drm/i915/gem/i915_gem_pages.c | 5 +- drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 45 ++++++++-- drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 84 +++++++++++++++++-- 5 files changed, 137 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index e641db297e0e..3eac8cf2ae10 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -294,6 +294,12 @@ i915_gem_object_is_shrinkable(const struct drm_i915_gem_object *obj) return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE); } +static inline bool +i915_gem_object_has_self_managed_shrink_list(const struct drm_i915_gem_object *obj) +{ + return i915_gem_object_type_has(obj, I915_GEM_OBJECT_SELF_MANAGED_SHRINK_LIST); +} + static inline bool i915_gem_object_is_proxy(const struct drm_i915_gem_object *obj) { @@ -531,6 +537,8 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, void i915_gem_object_make_unshrinkable(struct drm_i915_gem_object *obj); void i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj); +void __i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj); +void __i915_gem_object_make_purgeable(struct drm_i915_gem_object *obj); void i915_gem_object_make_purgeable(struct drm_i915_gem_object *obj); static inline bool cpu_write_needs_clflush(struct drm_i915_gem_object *obj) 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 f4233c4e8d2e..5718a09f5533 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -34,9 +34,11 @@ struct i915_lut_handle { struct drm_i915_gem_object_ops { unsigned int flags; -#define I915_GEM_OBJECT_IS_SHRINKABLE BIT(1) -#define I915_GEM_OBJECT_IS_PROXY BIT(2) -#define I915_GEM_OBJECT_NO_MMAP BIT(3) +#define I915_GEM_OBJECT_IS_SHRINKABLE BIT(1) +/* Skip the shrinker management in set_pages/unset_pages */ +#define I915_GEM_OBJECT_SELF_MANAGED_SHRINK_LIST BIT(2) +#define I915_GEM_OBJECT_IS_PROXY BIT(3) +#define I915_GEM_OBJECT_NO_MMAP BIT(4) /* Interface between the GEM object and its backing storage. * get_pages() is called once prior to the use of the associated set @@ -485,6 +487,12 @@ struct drm_i915_gem_object { */ atomic_t shrink_pin; + /** + * @ttm_shrinkable: True when the object is using shmem pages + * underneath. Protected by the object lock. + */ + bool ttm_shrinkable; + /** * Priority list of potential placements for this object. */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index ea6d9b3d2d6b..308e22a80af4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -68,7 +68,7 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, shrinkable = false; } - if (shrinkable) { + if (shrinkable && !i915_gem_object_has_self_managed_shrink_list(obj)) { struct list_head *list; unsigned long flags; @@ -210,7 +210,8 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj) if (i915_gem_object_is_volatile(obj)) obj->mm.madv = I915_MADV_WILLNEED; - i915_gem_object_make_unshrinkable(obj); + if (!i915_gem_object_has_self_managed_shrink_list(obj)) + i915_gem_object_make_unshrinkable(obj); if (obj->mm.mapping) { unmap_object(obj, page_mask_bits(obj->mm.mapping)); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index 66121fedc655..dde0a5c232f8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -497,13 +497,12 @@ void i915_gem_object_make_unshrinkable(struct drm_i915_gem_object *obj) spin_unlock_irqrestore(&i915->mm.obj_lock, flags); } -static void __i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj, - struct list_head *head) +static void ___i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj, + struct list_head *head) { struct drm_i915_private *i915 = obj_to_i915(obj); unsigned long flags; - GEM_BUG_ON(!i915_gem_object_has_pages(obj)); if (!i915_gem_object_is_shrinkable(obj)) return; @@ -523,6 +522,38 @@ static void __i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj, spin_unlock_irqrestore(&i915->mm.obj_lock, flags); } +/** + * __i915_gem_object_make_shrinkable - Move the object to the tail of the + * shrinkable list. Objects on this list might be swapped out. Used with + * WILLNEED objects. + * @obj: The GEM object. + * + * DO NOT USE. This is intended to be called on very special objects that don't + * yet have mm.pages, but are guaranteed to have potentially reclaimable pages + * underneath. + */ +void __i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj) +{ + ___i915_gem_object_make_shrinkable(obj, + &obj_to_i915(obj)->mm.shrink_list); +} + +/** + * __i915_gem_object_make_purgeable - Move the object to the tail of the + * purgeable list. Objects on this list might be swapped out. Used with + * DONTNEED objects. + * @obj: The GEM object. + * + * DO NOT USE. This is intended to be called on very special objects that don't + * yet have mm.pages, but are guaranteed to have potentially reclaimable pages + * underneath. + */ +void __i915_gem_object_make_purgeable(struct drm_i915_gem_object *obj) +{ + ___i915_gem_object_make_shrinkable(obj, + &obj_to_i915(obj)->mm.purge_list); +} + /** * i915_gem_object_make_shrinkable - Move the object to the tail of the * shrinkable list. Objects on this list might be swapped out. Used with @@ -535,8 +566,8 @@ static void __i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj, */ void i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj) { - __i915_gem_object_make_shrinkable(obj, - &obj_to_i915(obj)->mm.shrink_list); + GEM_BUG_ON(!i915_gem_object_has_pages(obj)); + __i915_gem_object_make_shrinkable(obj); } /** @@ -552,6 +583,6 @@ void i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj) */ void i915_gem_object_make_purgeable(struct drm_i915_gem_object *obj) { - __i915_gem_object_make_shrinkable(obj, - &obj_to_i915(obj)->mm.purge_list); + GEM_BUG_ON(!i915_gem_object_has_pages(obj)); + __i915_gem_object_make_purgeable(obj); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index ff8bd4c6fd2e..21a2b37ae1e7 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -762,6 +762,7 @@ static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, obj->ttm.get_io_page.sg_idx = 0; } + i915_ttm_adjust_lru(obj); i915_ttm_adjust_gem_after_move(obj); return 0; } @@ -851,7 +852,6 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj, return i915_ttm_err_to_gem(ret); } - i915_ttm_adjust_lru(obj); if (bo->ttm && !ttm_tt_is_populated(bo->ttm)) { ret = ttm_tt_populate(bo->bdev, bo->ttm, &ctx); if (ret) @@ -871,10 +871,9 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj, return PTR_ERR(st); __i915_gem_object_set_pages(obj, st, i915_sg_dma_sizes(st->sgl)); - if (!bo->ttm || !i915_tt->is_shmem) - i915_gem_object_make_unshrinkable(obj); } + i915_ttm_adjust_lru(obj); return ret; } @@ -945,8 +944,6 @@ static void i915_ttm_put_pages(struct drm_i915_gem_object *obj, * If the object is not destroyed next, The TTM eviction logic * and shrinkers will move it out if needed. */ - - i915_ttm_adjust_lru(obj); } static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj) @@ -954,6 +951,8 @@ static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj) struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); struct i915_ttm_tt *i915_tt = container_of(bo->ttm, typeof(*i915_tt), ttm); + bool shrinkable = + bo->ttm && i915_tt->filp && ttm_tt_is_populated(bo->ttm); /* * Don't manipulate the TTM LRUs while in TTM bo destruction. @@ -962,11 +961,40 @@ static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj) if (!kref_read(&bo->kref)) return; + /* + * We skip managing the shrinker LRU in set_pages() and just manage + * everything here. This does at least solve the issue with having + * temporary shmem mappings(like with evicted lmem) not being visible to + * the shrinker. Only our shmem objects are shrinkable, everything else + * we keep as unshrinkable. + * + * To make sure everything plays nice we keep an extra shrink pin in TTM + * if the underlying pages are not currently shrinkable. Once we release + * our pin, like when the pages are moved to shmem, the pages will then + * be added to the shrinker LRU, assuming the caller isn't also holding + * a pin. + * + * TODO: consider maybe also bumping the shrinker list here when we have + * already unpinned it, which should give us something more like an LRU. + */ + if (shrinkable != obj->mm.ttm_shrinkable) { + if (shrinkable) { + if (obj->mm.madv == I915_MADV_WILLNEED) + __i915_gem_object_make_shrinkable(obj); + else + __i915_gem_object_make_purgeable(obj); + } else { + i915_gem_object_make_unshrinkable(obj); + } + + obj->mm.ttm_shrinkable = shrinkable; + } + /* * Put on the correct LRU list depending on the MADV status */ spin_lock(&bo->bdev->lru_lock); - if (bo->ttm && i915_tt->filp) { + if (shrinkable) { /* Try to keep shmem_tt from being considered for shrinking. */ bo->priority = TTM_MAX_BO_PRIORITY - 1; } else if (obj->mm.madv != I915_MADV_WILLNEED) { @@ -1010,13 +1038,34 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) struct vm_area_struct *area = vmf->vma; struct drm_i915_gem_object *obj = i915_ttm_to_gem(area->vm_private_data); + struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + struct drm_device *dev = bo->base.dev; + vm_fault_t ret; + int idx; /* Sanity check that we allow writing into this object */ if (unlikely(i915_gem_object_is_readonly(obj) && area->vm_flags & VM_WRITE)) return VM_FAULT_SIGBUS; - return ttm_bo_vm_fault(vmf); + ret = ttm_bo_vm_reserve(bo, vmf); + if (ret) + return ret; + + if (drm_dev_enter(dev, &idx)) { + ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot, + TTM_BO_VM_NUM_PREFAULT, 1); + drm_dev_exit(idx); + } else { + ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot); + } + if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) + return ret; + + i915_ttm_adjust_lru(obj); + + dma_resv_unlock(bo->base.resv); + return ret; } static int @@ -1067,6 +1116,7 @@ static u64 i915_ttm_mmap_offset(struct drm_i915_gem_object *obj) static const struct drm_i915_gem_object_ops i915_gem_ttm_obj_ops = { .name = "i915_gem_object_ttm", + .flags = I915_GEM_OBJECT_SELF_MANAGED_SHRINK_LIST, .get_pages = i915_ttm_get_pages, .put_pages = i915_ttm_put_pages, @@ -1092,6 +1142,18 @@ void i915_ttm_bo_destroy(struct ttm_buffer_object *bo) mutex_destroy(&obj->ttm.get_io_page.lock); if (obj->ttm.created) { + /* + * We freely manage the shrinker LRU outide of the mm.pages life + * cycle. As a result when destroying the object we should be + * extra paranoid and ensure we remove it from the LRU, before + * we free the object. + * + * Touching the ttm_shrinkable outside of the object lock here + * should be safe now that the last GEM object ref was dropped. + */ + if (obj->mm.ttm_shrinkable) + i915_gem_object_make_unshrinkable(obj); + i915_ttm_backup_free(obj); /* This releases all gem object bindings to the backend. */ @@ -1144,6 +1206,14 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem, /* Forcing the page size is kernel internal only */ GEM_BUG_ON(page_size && obj->mm.n_placements); + /* + * Keep an extra shrink pin to prevent the object from being made + * shrinkable too early. If the ttm_tt is ever allocated in shmem, we + * drop the pin. The TTM backend manages the shrinker LRU itself, + * outside of the normal mm.pages life cycle. + */ + i915_gem_object_make_unshrinkable(obj); + /* * If this function fails, it will call the destructor, but * our caller still owns the object. So no freeing in the From patchwork Mon Oct 11 14:56:18 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Matthew Auld X-Patchwork-Id: 12550277 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 4AB68C433FE for ; Mon, 11 Oct 2021 15:01:50 +0000 (UTC) Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id E7B5460EDF for ; Mon, 11 Oct 2021 15:01:49 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org E7B5460EDF Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=lists.freedesktop.org Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 9E8A96E50B; Mon, 11 Oct 2021 15:01:25 +0000 (UTC) Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by gabe.freedesktop.org (Postfix) with ESMTPS id 64A4C6E51D; Mon, 11 Oct 2021 15:01:24 +0000 (UTC) X-IronPort-AV: E=McAfee;i="6200,9189,10134"; a="227179459" X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="227179459" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:57:01 -0700 X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="569984481" Received: from phutoant-mobl3.ccr.corp.intel.com (HELO mwauld-desk1.intel.com) ([10.213.44.196]) by fmsmga002-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:56:59 -0700 From: Matthew Auld To: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org, =?utf-8?q?Thomas_Hellstr=C3=B6m?= Subject: [PATCH v8 7/8] drm/i915/ttm: use cached system pages when evicting lmem Date: Mon, 11 Oct 2021 15:56:18 +0100 Message-Id: <20211011145619.1397733-7-matthew.auld@intel.com> X-Mailer: git-send-email 2.26.3 In-Reply-To: <20211011145619.1397733-1-matthew.auld@intel.com> References: <20211011145619.1397733-1-matthew.auld@intel.com> MIME-Version: 1.0 X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" This should let us do an accelerated copy directly to the shmem pages when temporarily moving lmem-only objects, where the i915-gem shrinker can later kick in to swap out the pages, if needed. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Thomas Hellström --- drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 21a2b37ae1e7..dfbce5607ddc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -134,11 +134,11 @@ static enum ttm_caching i915_ttm_select_tt_caching(const struct drm_i915_gem_object *obj) { /* - * Objects only allowed in system get cached cpu-mappings. - * Other objects get WC mapping for now. Even if in system. + * Objects only allowed in system get cached cpu-mappings, or when + * evicting lmem-only buffers to system for swapping. Other objects get + * WC mapping for now. Even if in system. */ - if (obj->mm.region->type == INTEL_MEMORY_SYSTEM && - obj->mm.n_placements <= 1) + if (obj->mm.n_placements <= 1) return ttm_cached; return ttm_write_combined; From patchwork Mon Oct 11 14:56:19 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Matthew Auld X-Patchwork-Id: 12550279 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 10737C4332F for ; Mon, 11 Oct 2021 15:01:53 +0000 (UTC) Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id D632360EE5 for ; Mon, 11 Oct 2021 15:01:52 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org D632360EE5 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=lists.freedesktop.org Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id D9C2C6E524; Mon, 11 Oct 2021 15:01:32 +0000 (UTC) Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by gabe.freedesktop.org (Postfix) with ESMTPS id 567036E507; Mon, 11 Oct 2021 15:01:31 +0000 (UTC) X-IronPort-AV: E=McAfee;i="6200,9189,10134"; a="227179474" X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="227179474" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:57:04 -0700 X-IronPort-AV: E=Sophos;i="5.85,364,1624345200"; d="scan'208";a="569984486" Received: from phutoant-mobl3.ccr.corp.intel.com (HELO mwauld-desk1.intel.com) ([10.213.44.196]) by fmsmga002-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Oct 2021 07:57:02 -0700 From: Matthew Auld To: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org, =?utf-8?q?Thomas_Hellstr=C3=B6m?= Subject: [PATCH v8 8/8] drm/i915/ttm: enable shmem tt backend Date: Mon, 11 Oct 2021 15:56:19 +0100 Message-Id: <20211011145619.1397733-8-matthew.auld@intel.com> X-Mailer: git-send-email 2.26.3 In-Reply-To: <20211011145619.1397733-1-matthew.auld@intel.com> References: <20211011145619.1397733-1-matthew.auld@intel.com> MIME-Version: 1.0 X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" Turn on the shmem tt backend, and enable shrinking. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Thomas Hellström --- drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index dfbce5607ddc..99e993caa3d4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -1116,7 +1116,8 @@ static u64 i915_ttm_mmap_offset(struct drm_i915_gem_object *obj) static const struct drm_i915_gem_object_ops i915_gem_ttm_obj_ops = { .name = "i915_gem_object_ttm", - .flags = I915_GEM_OBJECT_SELF_MANAGED_SHRINK_LIST, + .flags = I915_GEM_OBJECT_IS_SHRINKABLE | + I915_GEM_OBJECT_SELF_MANAGED_SHRINK_LIST, .get_pages = i915_ttm_get_pages, .put_pages = i915_ttm_put_pages,