From patchwork Tue Jun 4 13:11:37 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Lionel Landwerlin X-Patchwork-Id: 10974959 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 309F614B6 for ; Tue, 4 Jun 2019 13:11:55 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 1FD8E285FD for ; Tue, 4 Jun 2019 13:11:55 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 1499328847; Tue, 4 Jun 2019 13:11:55 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-5.2 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_MED autolearn=ham version=3.3.1 Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.wl.linuxfoundation.org (Postfix) with ESMTPS id 26C02287F2 for ; Tue, 4 Jun 2019 13:11:54 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 8EF0C89842; Tue, 4 Jun 2019 13:11:53 +0000 (UTC) X-Original-To: intel-gfx@lists.freedesktop.org Delivered-To: intel-gfx@lists.freedesktop.org Received: from mga17.intel.com (mga17.intel.com [192.55.52.151]) by gabe.freedesktop.org (Postfix) with ESMTPS id 4C15389830 for ; Tue, 4 Jun 2019 13:11:52 +0000 (UTC) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga003.fm.intel.com ([10.253.24.29]) by fmsmga107.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 04 Jun 2019 06:11:52 -0700 X-ExtLoop1: 1 Received: from bblokx-mobl.ger.corp.intel.com (HELO delly.ger.corp.intel.com) ([10.249.139.199]) by FMSMGA003.fm.intel.com with ESMTP; 04 Jun 2019 06:11:50 -0700 From: Lionel Landwerlin To: intel-gfx@lists.freedesktop.org Date: Tue, 4 Jun 2019 16:11:37 +0300 Message-Id: <20190604131140.12647-5-lionel.g.landwerlin@intel.com> X-Mailer: git-send-email 2.21.0.392.gf8f6787159e In-Reply-To: <20190604131140.12647-1-lionel.g.landwerlin@intel.com> References: <20190604131140.12647-1-lionel.g.landwerlin@intel.com> MIME-Version: 1.0 Subject: [Intel-gfx] [PATCH v3 4/7] drm/i915: add syncobj timeline support 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: , Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" X-Virus-Scanned: ClamAV using ClamSMTP Introduces a new parameters to execbuf so that we can specify syncobj handles as well as timeline points. Signed-off-by: Lionel Landwerlin --- .../gpu/drm/i915/gem/i915_gem_execbuffer.c | 270 ++++++++++++++---- drivers/gpu/drm/i915/i915_drv.c | 4 +- include/uapi/drm/i915_drm.h | 37 +++ 3 files changed, 255 insertions(+), 56 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 480e20043d80..02dc5480e8fe 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -210,6 +210,13 @@ enum { * the batchbuffer in trusted mode, otherwise the ioctl is rejected. */ +struct i915_drm_dma_fences { + struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */ + struct dma_fence *dma_fence; + u64 value; + struct dma_fence_chain *chain_fence; +}; + struct i915_execbuffer { struct drm_i915_private *i915; /** i915 backpointer */ struct drm_file *file; /** per-file lookup tables and limits */ @@ -272,6 +279,7 @@ struct i915_execbuffer { struct { u64 flags; /** Available extensions parameters */ + struct drm_i915_gem_exec_timeline_fences timeline_fences; } extensions; }; @@ -2212,67 +2220,203 @@ eb_select_engine(struct i915_execbuffer *eb, } static void -__free_fence_array(struct drm_syncobj **fences, unsigned int n) +__free_fence_array(struct i915_drm_dma_fences *fences, unsigned int n) { - while (n--) - drm_syncobj_put(ptr_mask_bits(fences[n], 2)); + while (n--) { + drm_syncobj_put(ptr_mask_bits(fences[n].syncobj, 2)); + dma_fence_put(fences[n].dma_fence); + kfree(fences[n].chain_fence); + } kvfree(fences); } -static struct drm_syncobj ** +static struct i915_drm_dma_fences * +get_timeline_fence_array(struct drm_i915_gem_execbuffer2 *args, + struct drm_i915_gem_exec_timeline_fences *timeline_fences, + struct drm_file *file, + int *out_n_fences) +{ + struct drm_i915_gem_exec_fence __user *user_fences; + struct i915_drm_dma_fences *fences; + u64 __user *user_values; + unsigned long n; + int err; + + *out_n_fences = timeline_fences->handle_count; + + /* Incompatible with I915_EXEC_FENCE_ARRAY. */ + if (args->flags & I915_EXEC_FENCE_ARRAY) + return ERR_PTR(-EINVAL); + + /* Check multiplication overflow for access_ok() and kvmalloc_array() */ + BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long)); + if (*out_n_fences > min_t(unsigned long, + ULONG_MAX / sizeof(*user_fences), + SIZE_MAX / sizeof(*fences))) + return ERR_PTR(-EINVAL); + + user_fences = u64_to_user_ptr(timeline_fences->handles_ptr); + if (!access_ok(user_fences, *out_n_fences * sizeof(*user_fences))) + return ERR_PTR(-EFAULT); + + user_values = u64_to_user_ptr(timeline_fences->values_ptr); + if (!access_ok(user_values, *out_n_fences * sizeof(*user_values))) + return ERR_PTR(-EFAULT); + + fences = kvmalloc_array(*out_n_fences, sizeof(*fences), + __GFP_NOWARN | GFP_KERNEL); + if (!fences) + return ERR_PTR(-ENOMEM); + + BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) & + ~__I915_EXEC_FENCE_UNKNOWN_FLAGS); + + for (n = 0; n < *out_n_fences; n++) { + struct drm_i915_gem_exec_fence user_fence; + struct drm_syncobj *syncobj; + struct dma_fence *fence = NULL; + u64 point; + + if (__copy_from_user(&user_fence, user_fences++, sizeof(user_fence))) { + err = -EFAULT; + goto err; + } + + if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS) { + err = -EINVAL; + goto err; + } + + if (__get_user(point, user_values++)) { + err = -EFAULT; + goto err; + } + + syncobj = drm_syncobj_find(file, user_fence.handle); + if (!syncobj) { + DRM_DEBUG("Invalid syncobj handle provided\n"); + err = -EINVAL; + goto err; + } + + if (user_fence.flags & I915_EXEC_FENCE_WAIT) { + fence = drm_syncobj_fence_get(syncobj); + if (!fence) { + DRM_DEBUG("Syncobj handle has no fence\n"); + drm_syncobj_put(syncobj); + err = -EINVAL; + goto err; + } + + err = dma_fence_chain_find_seqno(&fence, point); + if (err) { + DRM_DEBUG("Syncobj handle missing requested point\n"); + goto err; + } + } + + /* + * For timeline syncobjs we need to create a chain. + */ + if (point != 0 && user_fence.flags & I915_EXEC_FENCE_SIGNAL) { + fences[n].chain_fence = + kmalloc(sizeof(*fences[n].chain_fence), + GFP_KERNEL); + if (!fences[n].chain_fence) { + dma_fence_put(fence); + drm_syncobj_put(syncobj); + err = -ENOMEM; + DRM_DEBUG("Unable to alloc chain_fence\n"); + goto err; + } + } else { + fences[n].chain_fence = NULL; + } + + fences[n].syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2); + fences[n].dma_fence = fence; + fences[n].value = point; + } + + return fences; + +err: + __free_fence_array(fences, n); + return ERR_PTR(err); +} + +static struct i915_drm_dma_fences * get_fence_array(struct drm_i915_gem_execbuffer2 *args, - struct drm_file *file) + struct i915_execbuffer *eb, + struct drm_file *file, + int *out_n_fences) { - const unsigned long nfences = args->num_cliprects; struct drm_i915_gem_exec_fence __user *user; - struct drm_syncobj **fences; + struct i915_drm_dma_fences *fences; unsigned long n; int err; - if (!(args->flags & I915_EXEC_FENCE_ARRAY)) - return NULL; + *out_n_fences = args->num_cliprects; + + /* Timeline fences are incompatible with the fence array. */ + if (eb->extensions.flags & BIT(DRM_I915_GEM_BASE_EXECBUFFER_TYPE_TIMELINE_FENCES)) + return ERR_PTR(-EINVAL); /* Check multiplication overflow for access_ok() and kvmalloc_array() */ BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long)); - if (nfences > min_t(unsigned long, - ULONG_MAX / sizeof(*user), - SIZE_MAX / sizeof(*fences))) + if (*out_n_fences > min_t(unsigned long, + ULONG_MAX / sizeof(*user), + SIZE_MAX / sizeof(*fences))) return ERR_PTR(-EINVAL); user = u64_to_user_ptr(args->cliprects_ptr); - if (!access_ok(user, nfences * sizeof(*user))) + if (!access_ok(user, *out_n_fences * sizeof(*user))) return ERR_PTR(-EFAULT); - fences = kvmalloc_array(nfences, sizeof(*fences), + fences = kvmalloc_array(*out_n_fences, sizeof(*fences), __GFP_NOWARN | GFP_KERNEL); if (!fences) return ERR_PTR(-ENOMEM); - for (n = 0; n < nfences; n++) { - struct drm_i915_gem_exec_fence fence; + for (n = 0; n < *out_n_fences; n++) { + struct drm_i915_gem_exec_fence user_fence; struct drm_syncobj *syncobj; + struct dma_fence *fence = NULL; - if (__copy_from_user(&fence, user++, sizeof(fence))) { + if (__copy_from_user(&user_fence, user++, sizeof(user_fence))) { err = -EFAULT; goto err; } - if (fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS) { + if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS) { err = -EINVAL; goto err; } - syncobj = drm_syncobj_find(file, fence.handle); + syncobj = drm_syncobj_find(file, user_fence.handle); if (!syncobj) { DRM_DEBUG("Invalid syncobj handle provided\n"); err = -ENOENT; goto err; } + if (user_fence.flags & I915_EXEC_FENCE_WAIT) { + fence = drm_syncobj_fence_get(syncobj); + if (!fence) { + DRM_DEBUG("Syncobj handle has no fence\n"); + drm_syncobj_put(syncobj); + err = -EINVAL; + goto err; + } + } + BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) & ~__I915_EXEC_FENCE_UNKNOWN_FLAGS); - fences[n] = ptr_pack_bits(syncobj, fence.flags, 2); + fences[n].syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2); + fences[n].dma_fence = fence; + fences[n].value = 0; + fences[n].chain_fence = NULL; } return fences; @@ -2283,36 +2427,30 @@ get_fence_array(struct drm_i915_gem_execbuffer2 *args, } static void -put_fence_array(struct drm_i915_gem_execbuffer2 *args, - struct drm_syncobj **fences) +put_fence_array(struct i915_drm_dma_fences *fences, int nfences) { if (fences) - __free_fence_array(fences, args->num_cliprects); + __free_fence_array(fences, nfences); } static int await_fence_array(struct i915_execbuffer *eb, - struct drm_syncobj **fences) + struct i915_drm_dma_fences *fences, + int nfences) { - const unsigned int nfences = eb->args->num_cliprects; unsigned int n; int err; for (n = 0; n < nfences; n++) { struct drm_syncobj *syncobj; - struct dma_fence *fence; unsigned int flags; - syncobj = ptr_unpack_bits(fences[n], &flags, 2); + syncobj = ptr_unpack_bits(fences[n].syncobj, &flags, 2); if (!(flags & I915_EXEC_FENCE_WAIT)) continue; - fence = drm_syncobj_fence_get(syncobj); - if (!fence) - return -EINVAL; - - err = i915_request_await_dma_fence(eb->request, fence); - dma_fence_put(fence); + err = i915_request_await_dma_fence(eb->request, + fences[n].dma_fence); if (err < 0) return err; } @@ -2322,9 +2460,9 @@ await_fence_array(struct i915_execbuffer *eb, static void signal_fence_array(struct i915_execbuffer *eb, - struct drm_syncobj **fences) + struct i915_drm_dma_fences *fences, + int nfences) { - const unsigned int nfences = eb->args->num_cliprects; struct dma_fence * const fence = &eb->request->fence; unsigned int n; @@ -2332,11 +2470,21 @@ signal_fence_array(struct i915_execbuffer *eb, struct drm_syncobj *syncobj; unsigned int flags; - syncobj = ptr_unpack_bits(fences[n], &flags, 2); + syncobj = ptr_unpack_bits(fences[n].syncobj, &flags, 2); if (!(flags & I915_EXEC_FENCE_SIGNAL)) continue; - drm_syncobj_replace_fence(syncobj, fence); + if (fences[n].chain_fence) { + drm_syncobj_add_point(syncobj, fences[n].chain_fence, + fence, fences[n].value); + /* + * The chain's ownership is transfered to the + * timeline. + */ + fences[n].chain_fence = NULL; + } else { + drm_syncobj_replace_fence(syncobj, fence); + } } } @@ -2364,6 +2512,13 @@ parse_execbuf2_extensions(struct drm_i915_gem_execbuffer2 *args, return -EINVAL; switch (iter.type) { + case DRM_I915_GEM_BASE_EXECBUFFER_TYPE_TIMELINE_FENCES: + if (copy_from_user(&eb->extensions.timeline_fences, + u64_to_user_ptr(iter_ptr), + sizeof(eb->extensions.timeline_fences))) + return -EFAULT; + break; + default: return -EINVAL; } @@ -2380,14 +2535,15 @@ static int i915_gem_do_execbuffer(struct drm_device *dev, struct drm_file *file, struct drm_i915_gem_execbuffer2 *args, - struct drm_i915_gem_exec_object2 *exec, - struct drm_syncobj **fences) + struct drm_i915_gem_exec_object2 *exec) { struct i915_execbuffer eb; struct dma_fence *in_fence = NULL; struct dma_fence *exec_fence = NULL; struct sync_file *out_fence = NULL; + struct i915_drm_dma_fences *fences = NULL; int out_fence_fd = -1; + int nfences = 0; int err; BUILD_BUG_ON(__EXEC_INTERNAL_FLAGS & ~__I915_EXEC_ILLEGAL_FLAGS); @@ -2429,10 +2585,22 @@ i915_gem_do_execbuffer(struct drm_device *dev, return err; } + if (args->flags & I915_EXEC_FENCE_ARRAY) { + fences = get_fence_array(args, &eb, file, &nfences); + } else if (eb.extensions.flags & BIT(DRM_I915_GEM_BASE_EXECBUFFER_TYPE_TIMELINE_FENCES)) { + fences = get_timeline_fence_array( + args, &eb.extensions.timeline_fences, file, &nfences); + } + + if (IS_ERR(fences)) + return PTR_ERR(fences); + if (args->flags & I915_EXEC_FENCE_IN) { in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2)); - if (!in_fence) - return -EINVAL; + if (!in_fence) { + err = -EINVAL; + goto err_fences; + } } if (args->flags & I915_EXEC_FENCE_SUBMIT) { @@ -2590,7 +2758,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, } if (fences) { - err = await_fence_array(&eb, fences); + err = await_fence_array(&eb, fences, nfences); if (err) goto err_request; } @@ -2619,7 +2787,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, i915_request_add(eb.request); if (fences) - signal_fence_array(&eb, fences); + signal_fence_array(&eb, fences, nfences); if (out_fence) { if (err == 0) { @@ -2654,6 +2822,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, dma_fence_put(exec_fence); err_in_fence: dma_fence_put(in_fence); +err_fences: + put_fence_array(fences, nfences); return err; } @@ -2747,7 +2917,7 @@ i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data, exec2_list[i].flags = 0; } - err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list, NULL); + err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list); if (exec2.flags & __EXEC_HAS_RELOC) { struct drm_i915_gem_exec_object __user *user_exec_list = u64_to_user_ptr(args->buffers_ptr); @@ -2778,7 +2948,6 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data, { struct drm_i915_gem_execbuffer2 *args = data; struct drm_i915_gem_exec_object2 *exec2_list; - struct drm_syncobj **fences = NULL; const size_t count = args->buffer_count; int err; @@ -2806,15 +2975,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data, return -EFAULT; } - if (args->flags & I915_EXEC_FENCE_ARRAY) { - fences = get_fence_array(args, file); - if (IS_ERR(fences)) { - kvfree(exec2_list); - return PTR_ERR(fences); - } - } - - err = i915_gem_do_execbuffer(dev, file, args, exec2_list, fences); + err = i915_gem_do_execbuffer(dev, file, args, exec2_list); /* * Now that we have begun execution of the batchbuffer, we ignore @@ -2854,7 +3015,6 @@ end:; } args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS; - put_fence_array(args, fences); kvfree(exec2_list); return err; } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 9ed4d0016ee1..a872791f98bd 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -448,6 +448,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data, case I915_PARAM_HAS_EXEC_BATCH_FIRST: case I915_PARAM_HAS_EXEC_FENCE_ARRAY: case I915_PARAM_HAS_EXEC_SUBMIT_FENCE: + case I915_PARAM_HAS_EXEC_TIMELINE_FENCES: /* For the time being all of these are always true; * if some supported hardware does not have one of these * features this value needs to be provided from @@ -3192,7 +3193,8 @@ static struct drm_driver driver = { */ .driver_features = DRIVER_GEM | DRIVER_PRIME | - DRIVER_RENDER | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_SYNCOBJ, + DRIVER_RENDER | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_SYNCOBJ | + DRIVER_SYNCOBJ_TIMELINE, .release = i915_driver_release, .open = i915_driver_open, .lastclose = i915_driver_lastclose, diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 2ef5ab0daae4..ba1b02859346 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -617,6 +617,12 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_PERF_REVISION 54 +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of + * timeline syncobj through drm_i915_gem_exec_timeline_fences. See + * I915_EXEC_EXT. + */ +#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55 + /* Must be kept compact -- no holes and well documented */ typedef struct drm_i915_getparam { @@ -1014,6 +1020,12 @@ struct drm_i915_gem_exec_fence { }; enum drm_i915_gem_base_execbuffer_type { + /** + * This identifier is associated with + * drm_i915_gem_exec_timeline_fences. + */ + DRM_I915_GEM_BASE_EXECBUFFER_TYPE_TIMELINE_FENCES, + DRM_I915_GEM_BASE_EXECBUFFER_TYPE_MAX /* non-ABI */ }; @@ -1036,6 +1048,31 @@ struct drm_i915_gem_base_execbuffer_ext { __u64 next_ptr; }; +/** + * This structure describes an array of drm_syncobj and associated points for + * timeline variants of drm_syncobj. It is invalid to append this structure to + * the execbuf if I915_EXEC_FENCE_ARRAY is set. + */ +struct drm_i915_gem_exec_timeline_fences { + struct drm_i915_gem_base_execbuffer_ext base; + + /** + * Number of element in the handles_ptr & value_ptr arrays. + */ + __u64 handle_count; + + /** + * Pointer to an array of struct drm_i915_gem_exec_fence of size handle_count. + */ + __u64 handles_ptr; + + /** + * Pointer to an array of u64 values of size handle_count. Values must + * be 0 for a binary drm_syncobj. + */ + __u64 values_ptr; +}; + struct drm_i915_gem_execbuffer2 { /** * List of gem_exec_object2 structs