From patchwork Fri Sep 27 17:33:56 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Matthew Auld X-Patchwork-Id: 11164899 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 7DD5F1747 for ; Fri, 27 Sep 2019 17:34:30 +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 5F848207FF for ; Fri, 27 Sep 2019 17:34:30 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 5F848207FF Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=intel-gfx-bounces@lists.freedesktop.org Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 803F46E17F; Fri, 27 Sep 2019 17:34:28 +0000 (UTC) X-Original-To: intel-gfx@lists.freedesktop.org Delivered-To: intel-gfx@lists.freedesktop.org Received: from mga09.intel.com (mga09.intel.com [134.134.136.24]) by gabe.freedesktop.org (Postfix) with ESMTPS id D58A36E174 for ; Fri, 27 Sep 2019 17:34:26 +0000 (UTC) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga008.fm.intel.com ([10.253.24.58]) by orsmga102.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 27 Sep 2019 10:34:25 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,556,1559545200"; d="scan'208";a="189508383" Received: from rgdowlin-mobl.ger.corp.intel.com (HELO mwahaha-bdw.ger.corp.intel.com) ([10.252.7.171]) by fmsmga008.fm.intel.com with ESMTP; 27 Sep 2019 10:34:24 -0700 From: Matthew Auld To: intel-gfx@lists.freedesktop.org Date: Fri, 27 Sep 2019 18:33:56 +0100 Message-Id: <20190927173409.31175-10-matthew.auld@intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190927173409.31175-1-matthew.auld@intel.com> References: <20190927173409.31175-1-matthew.auld@intel.com> MIME-Version: 1.0 Subject: [Intel-gfx] [PATCH 09/22] drm/i915/lmem: support kernel mapping X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: daniel.vetter@ffwll.ch Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" From: Abdiel Janulgue We can create LMEM objects, but we also need to support mapping them into kernel space for internal use. Signed-off-by: Abdiel Janulgue Signed-off-by: Matthew Auld Signed-off-by: Steve Hampson Cc: Joonas Lahtinen --- drivers/gpu/drm/i915/gem/i915_gem_internal.c | 4 +- drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 36 +++++++++ drivers/gpu/drm/i915/gem/i915_gem_lmem.h | 8 ++ drivers/gpu/drm/i915/gem/i915_gem_object.h | 6 ++ .../gpu/drm/i915/gem/i915_gem_object_types.h | 3 +- drivers/gpu/drm/i915/gem/i915_gem_pages.c | 20 ++++- drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 3 +- .../drm/i915/gem/selftests/huge_gem_object.c | 4 +- .../drm/i915/selftests/intel_memory_region.c | 76 +++++++++++++++++++ 9 files changed, 152 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c index 5e72cb1cc2d3..c2e237702e8c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c @@ -140,7 +140,9 @@ static void i915_gem_object_put_pages_internal(struct drm_i915_gem_object *obj, static const struct drm_i915_gem_object_ops i915_gem_object_internal_ops = { .flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE | - I915_GEM_OBJECT_IS_SHRINKABLE, + I915_GEM_OBJECT_IS_SHRINKABLE | + I915_GEM_OBJECT_IS_MAPPABLE, + .get_pages = i915_gem_object_get_pages_internal, .put_pages = i915_gem_object_put_pages_internal, }; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c index 26a23304df32..d7ec74ed5b88 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c @@ -9,11 +9,47 @@ #include "i915_drv.h" const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = { + .flags = I915_GEM_OBJECT_IS_MAPPABLE, + .get_pages = i915_gem_object_get_pages_buddy, .put_pages = i915_gem_object_put_pages_buddy, .release = i915_gem_object_release_memory_region, }; +/* XXX: Time to vfunc your life up? */ +void __iomem *i915_gem_object_lmem_io_map_page(struct drm_i915_gem_object *obj, + unsigned long n) +{ + resource_size_t offset; + + offset = i915_gem_object_get_dma_address(obj, n); + + return io_mapping_map_wc(&obj->mm.region->iomap, offset, PAGE_SIZE); +} + +void __iomem *i915_gem_object_lmem_io_map_page_atomic(struct drm_i915_gem_object *obj, + unsigned long n) +{ + resource_size_t offset; + + offset = i915_gem_object_get_dma_address(obj, n); + + return io_mapping_map_atomic_wc(&obj->mm.region->iomap, offset); +} + +void __iomem *i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj, + unsigned long n, + unsigned long size) +{ + resource_size_t offset; + + GEM_BUG_ON(!(obj->flags & I915_BO_ALLOC_CONTIGUOUS)); + + offset = i915_gem_object_get_dma_address(obj, n); + + return io_mapping_map_wc(&obj->mm.region->iomap, offset, size); +} + bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj) { struct intel_memory_region *region = obj->mm.region; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h index ebc15fe24f58..31a6462bdbb6 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h @@ -13,6 +13,14 @@ struct drm_i915_gem_object; extern const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops; +void __iomem *i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj, + unsigned long n, unsigned long size); +void __iomem *i915_gem_object_lmem_io_map_page(struct drm_i915_gem_object *obj, + unsigned long n); +void __iomem * +i915_gem_object_lmem_io_map_page_atomic(struct drm_i915_gem_object *obj, + unsigned long n); + bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj); struct drm_i915_gem_object * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index d5839cbd82c0..e8cc776581d0 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -158,6 +158,12 @@ i915_gem_object_is_proxy(const struct drm_i915_gem_object *obj) return obj->ops->flags & I915_GEM_OBJECT_IS_PROXY; } +static inline bool +i915_gem_object_is_mappable(const struct drm_i915_gem_object *obj) +{ + return obj->ops->flags & I915_GEM_OBJECT_IS_MAPPABLE; +} + static inline bool i915_gem_object_needs_async_cancel(const 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 0d934b67e547..743898944760 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -32,7 +32,8 @@ struct drm_i915_gem_object_ops { #define I915_GEM_OBJECT_HAS_STRUCT_PAGE BIT(0) #define I915_GEM_OBJECT_IS_SHRINKABLE BIT(1) #define I915_GEM_OBJECT_IS_PROXY BIT(2) -#define I915_GEM_OBJECT_ASYNC_CANCEL BIT(3) +#define I915_GEM_OBJECT_IS_MAPPABLE BIT(3) +#define I915_GEM_OBJECT_ASYNC_CANCEL BIT(4) /* Interface between the GEM object and its backing storage. * get_pages() is called once prior to the use of the associated set diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index b0ec0959c13f..fc4ad29ce881 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -7,6 +7,7 @@ #include "i915_drv.h" #include "i915_gem_object.h" #include "i915_scatterlist.h" +#include "i915_gem_lmem.h" void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, struct sg_table *pages, @@ -172,7 +173,9 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj) void *ptr; ptr = page_mask_bits(obj->mm.mapping); - if (is_vmalloc_addr(ptr)) + if (i915_gem_object_is_lmem(obj)) + io_mapping_unmap(ptr); + else if (is_vmalloc_addr(ptr)) vunmap(ptr); else kunmap(kmap_to_page(ptr)); @@ -231,7 +234,7 @@ int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj, } /* The 'mapping' part of i915_gem_object_pin_map() below */ -static void *i915_gem_object_map(const struct drm_i915_gem_object *obj, +static void *i915_gem_object_map(struct drm_i915_gem_object *obj, enum i915_map_type type) { unsigned long n_pages = obj->base.size >> PAGE_SHIFT; @@ -244,6 +247,13 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj, pgprot_t pgprot; void *addr; + if (i915_gem_object_is_lmem(obj)) { + if (type != I915_MAP_WC) + return NULL; + + return i915_gem_object_lmem_io_map(obj, 0, obj->base.size); + } + /* A single page can always be kmapped */ if (n_pages == 1 && type == I915_MAP_WB) return kmap(sg_page(sgt->sgl)); @@ -289,7 +299,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, void *ptr; int err; - if (unlikely(!i915_gem_object_has_struct_page(obj))) + if (unlikely(!i915_gem_object_is_mappable(obj))) return ERR_PTR(-ENXIO); err = mutex_lock_interruptible(&obj->mm.lock); @@ -321,7 +331,9 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, goto err_unpin; } - if (is_vmalloc_addr(ptr)) + if (i915_gem_object_is_lmem(obj)) + io_mapping_unmap(ptr); + else if (is_vmalloc_addr(ptr)) vunmap(ptr); else kunmap(kmap_to_page(ptr)); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 4c4954e8ce0a..9f5d903f7793 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -422,7 +422,8 @@ static void shmem_release(struct drm_i915_gem_object *obj) const struct drm_i915_gem_object_ops i915_gem_shmem_ops = { .flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE | - I915_GEM_OBJECT_IS_SHRINKABLE, + I915_GEM_OBJECT_IS_SHRINKABLE | + I915_GEM_OBJECT_IS_MAPPABLE, .get_pages = shmem_get_pages, .put_pages = shmem_put_pages, diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c index 3c5d17b2b670..686e0e909280 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c @@ -86,7 +86,9 @@ static void huge_put_pages(struct drm_i915_gem_object *obj, static const struct drm_i915_gem_object_ops huge_ops = { .flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE | - I915_GEM_OBJECT_IS_SHRINKABLE, + I915_GEM_OBJECT_IS_SHRINKABLE | + I915_GEM_OBJECT_IS_MAPPABLE, + .get_pages = huge_get_pages, .put_pages = huge_put_pages, }; diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c index 1e9a0eef17fc..ba98e8254b80 100644 --- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c +++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c @@ -13,8 +13,10 @@ #include "gem/i915_gem_lmem.h" #include "gem/i915_gem_region.h" +#include "gem/i915_gem_object_blt.h" #include "gem/selftests/mock_context.h" #include "gt/intel_gt.h" +#include "selftests/igt_flush_test.h" #include "selftests/i915_random.h" static void close_objects(struct list_head *objects) @@ -274,6 +276,79 @@ static int igt_lmem_create(void *arg) return err; } +static int igt_lmem_write_cpu(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct intel_context *ce = i915->engine[BCS0]->kernel_context; + struct drm_i915_gem_object *obj; + struct rnd_state prng; + u32 *vaddr; + u32 dword; + u32 val; + u32 sz; + int err; + + if (!HAS_ENGINE(i915, BCS0)) + return 0; + + sz = round_up(prandom_u32_state(&prng) % SZ_32M, PAGE_SIZE); + + obj = i915_gem_object_create_lmem(i915, sz, I915_BO_ALLOC_CONTIGUOUS); + if (IS_ERR(obj)) + return PTR_ERR(obj); + + vaddr = i915_gem_object_pin_map(obj, I915_MAP_WC); + if (IS_ERR(vaddr)) { + pr_err("Failed to iomap lmembar; err=%d\n", (int)PTR_ERR(vaddr)); + err = PTR_ERR(vaddr); + goto out_put; + } + + val = prandom_u32_state(&prng); + + /* Write from gpu and then read from cpu */ + err = i915_gem_object_fill_blt(obj, ce, val); + if (err) + goto out_unpin; + + i915_gem_object_lock(obj); + err = i915_gem_object_set_to_wc_domain(obj, true); + i915_gem_object_unlock(obj); + if (err) + goto out_unpin; + + for (dword = 0; dword < sz / sizeof(u32); ++dword) { + if (vaddr[dword] != val) { + pr_err("vaddr[%u]=%u, val=%u\n", dword, vaddr[dword], + val); + err = -EINVAL; + break; + } + } + + /* Write from the cpu and read again from the cpu */ + memset32(vaddr, val ^ 0xdeadbeaf, sz / sizeof(u32)); + + for (dword = 0; dword < sz / sizeof(u32); ++dword) { + if (vaddr[dword] != (val ^ 0xdeadbeaf)) { + pr_err("vaddr[%u]=%u, val=%u\n", dword, vaddr[dword], + val ^ 0xdeadbeaf); + err = -EINVAL; + break; + } + } + +out_unpin: + i915_gem_object_unpin_map(obj); +out_put: + i915_gem_object_put(obj); + + if (igt_flush_test(i915, I915_WAIT_LOCKED)) + err = -EIO; + + return err; +} + int intel_memory_region_mock_selftests(void) { static const struct i915_subtest tests[] = { @@ -313,6 +388,7 @@ int intel_memory_region_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { SUBTEST(igt_lmem_create), + SUBTEST(igt_lmem_write_cpu), }; int err;