From patchwork Wed Mar 19 14:52:29 2025 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Rob Clark X-Patchwork-Id: 14022744 Received: from mail-pl1-f177.google.com (mail-pl1-f177.google.com [209.85.214.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A331E214801; Wed, 19 Mar 2025 14:55:40 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.214.177 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742396143; cv=none; b=BwFG/Oiu9C3JOLW+5nAGB1fNPpAeJQnzmPzHP7bbKJ40zof3aekM7M7jDt+Rgd34WuP47BQM4t2jQV3ccJWTwLIoY5ryK6KbLp5JoD4Z7yno3MsMcepe+w2rXLc8xymDlQF+/H11paiiO13bkceenypXpgQvD8aL+nqrL/qSVwc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742396143; c=relaxed/simple; bh=vmY7C8OGUYpxgzPjTwyBIYcrLqKNd4GK17l+1xwvqb0=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=hFIReTTgHCwbvkFP2abCCwEd1+Jby+QnlBKRlYQ6e0PgWCp7JYynol/CoNeexWDPXHUlOckXXxeq9jxVFIGSYKNtwEnCbqdWwGrJxmSY8uJVLVAWOQBPtWO7JnwLBhseB4dDtxrV+s/4hTLYlsx9g///dQLc+VXHupnUWcX0DdA= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=aHP56ftc; arc=none smtp.client-ip=209.85.214.177 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="aHP56ftc" Received: by mail-pl1-f177.google.com with SMTP id d9443c01a7336-2243803b776so27779615ad.0; Wed, 19 Mar 2025 07:55:40 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1742396140; x=1743000940; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=rFp5gYDsJKKjusUsNUKNLygAl2cHqL42U7ejjcZcvPI=; b=aHP56ftcjtNP8PZMZXXg+Du1RjuqKmDiuqeueNb0D19iUuClcdu0rguLYwQ0BIwZnC LXToPI19H7LOGo/NdZ83lFF8WyYxCJlzpiHWgz32AfzfDD7joHOcI7ogFNOeZyqoHuYL YlMD18gaJ+Uztjbu71iaSCdW9Xn3F/dr5aBixTkC194O8896Ek/qdpWyFd5EctKhYMUi vKOUeS+nOWLAvPBp6N8D9bBul49ErSsZt69iq5sgu+7whUlVlP4Bb1wNn2ZMKP9BNPJV 5T0sVoytOoEp3VNNLOeZERSMBxDAURYmDRFsQe7Isfo3BG4DB1QVuTyVUhZjUx/Ilb33 RLgA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1742396140; x=1743000940; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=rFp5gYDsJKKjusUsNUKNLygAl2cHqL42U7ejjcZcvPI=; b=isIfXiv2xf21fovWGGupQKm2scHmpwtlLXcG/cUQWU9SIQpt6GwbeT+Fe84CzUzprr QbuGQpD6eqkjihS6p+uceUSnShh5WPL16wUfVfAmO1NXx8nr81qYnuYY+uo9NB9clFwk kKcWTo8SPHIZSyB51BZwBGsLhenXnsd7C59kTT2bsfWc1DPqiAlOe7+Rhy0ZbJoDbeRC fzTWGDKm8Cc2G/28V7/ukAmc5WJX1rzsjM1dYok4LoDvAlzV8MPhdcjxrmDC3t+DFioe k7L4Bz3NFzdrVcBrgdT2mbScsZQhbYTqzgRG56+2i4m1W3TEq99MJ6c7cpKr8ElLqPDw pGJw== X-Forwarded-Encrypted: i=1; AJvYcCU/4M972t5HgrBfeF+9lc6SIyDOhigin/MiS2QbfZUNPZgNJOImjhho11VR0VG17TRvlWtjkNo8jqaElPPi@vger.kernel.org, AJvYcCWtFT+KKDPHdfu0v8p264yh06uxMz36H+IeRfhVthHtcpie8IExlDQ5mntzIQfZ3XNZZHm2MVrE7sP3IBY=@vger.kernel.org, AJvYcCXTXJvrgSHPED8uzn7W5enf6hghgYkvh69W9GsUqIaXPQMmvCD9K6ggz5jAAyT4d06AH4NpmvXUo/H44QYR@vger.kernel.org X-Gm-Message-State: AOJu0Yz2dqiszt++4dH9/xiXmMSoyStDT0Lu2DG9aHHsE3Okke34BKge Id5RzCT9MwiNqt+/S7fA02dBUzQHnTmgBI6u/zJBFxfRviAiDGJ+rZYCrA== X-Gm-Gg: ASbGncv7OE48vlUK5lzVyN3vkWd6rBx5GA+ESrYBIM9ZyrQSr3I0twtdt1DCfxLkY/D R1O4tml08YrTCVv+L+VmyDACFklXul9wtu4Jue3eXSyV6plk8BaxTSaRRQ8PlKYIsdbI04WGB9Q vPfJvxSGBYlbfeJf6dAlRDgigm9844noIGvegmuw87IK9ZcsLrOZiIP2ovbzF9iJNgjM3RCi6k4 /K3MXNX5uv5LWLAABeOxWTfXlEw4hpXtjIJZeUieB4LScWK2P/Lm/4F6V+XonkYN/Hn06XkSSCN dfmGfXExn0Ixqa4W6zrnebNFFH7umT3YeiR1/pyORh0JaVcfyD+rsbd140x3a8cJfs7+uJmmMRx V563TaOd6VCKDjG1bDqs= X-Google-Smtp-Source: AGHT+IEqIieP8fKBMjMJOk9V0T6bFwZVD5WXsDeLdLV0AxJjABCMvE+1HFXmwXd0HLstQOzQ1r9vkA== X-Received: by 2002:a17:903:41d0:b0:224:24d3:6103 with SMTP id d9443c01a7336-22649a80c3fmr53570765ad.35.1742396139817; Wed, 19 Mar 2025 07:55:39 -0700 (PDT) Received: from localhost ([2a00:79e0:3e00:2601:3afc:446b:f0df:eadc]) by smtp.gmail.com with ESMTPSA id d9443c01a7336-225c68a8796sm114893425ad.99.2025.03.19.07.55.38 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 19 Mar 2025 07:55:39 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: freedreno@lists.freedesktop.org, linux-arm-msm@vger.kernel.org, Rob Clark , Rob Clark , Abhinav Kumar , Dmitry Baryshkov , Sean Paul , Marijn Suijten , David Airlie , Simona Vetter , Konrad Dybcio , Maarten Lankhorst , Maxime Ripard , Thomas Zimmermann , Sumit Semwal , =?utf-8?q?Christian_K=C3=B6nig?= , linux-kernel@vger.kernel.org (open list), linux-media@vger.kernel.org (open list:DMA BUFFER SHARING FRAMEWORK:Keyword:\bdma_(?:buf|fence|resv)\b), linaro-mm-sig@lists.linaro.org (moderated list:DMA BUFFER SHARING FRAMEWORK:Keyword:\bdma_(?:buf|fence|resv)\b) Subject: [PATCH v2 17/34] drm/msm: Extend SUBMIT ioctl for VM_BIND Date: Wed, 19 Mar 2025 07:52:29 -0700 Message-ID: <20250319145425.51935-18-robdclark@gmail.com> X-Mailer: git-send-email 2.48.1 In-Reply-To: <20250319145425.51935-1-robdclark@gmail.com> References: <20250319145425.51935-1-robdclark@gmail.com> Precedence: bulk X-Mailing-List: linux-media@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 From: Rob Clark This is a bit different than the path taken by other clean-slate drivers. But there is a lot in similar with BO pinning in the legacy "EXEC" path and "VM_BIND" MAP path. Also, we want the same fence and syncobj handling. (Why bother with fence fd's? Because for virtgpu nctx for, guest syncobj's exist only as dma_fence's between the guest kernel and host.) Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_gem.h | 10 ++--- drivers/gpu/drm/msm/msm_gem_submit.c | 65 ++++++++++++++++++++++++---- include/uapi/drm/msm_drm.h | 49 ++++++++++++++++++--- 3 files changed, 103 insertions(+), 21 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index 7cb720137548..8e29e36ca9c5 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -345,13 +345,13 @@ struct msm_gem_submit { uint32_t nr_relocs; struct drm_msm_gem_submit_reloc *relocs; } *cmd; /* array of size nr_cmds */ - struct { + struct msm_gem_submit_bo { uint32_t flags; - union { - struct drm_gem_object *obj; - uint32_t handle; - }; + uint32_t handle; + struct drm_gem_object *obj; uint64_t iova; + uint64_t bo_offset; + uint64_t range; } bos[]; }; diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 9cef308a0ad1..bb61231ab8ba 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -115,23 +115,37 @@ void __msm_gem_submit_destroy(struct kref *kref) kfree(submit); } +static bool invalid_alignment(uint64_t addr) +{ + /* + * Technically this is about GPU alignment, not CPU alignment. But + * I've not seen any qcom SoC where the SMMU does not support the + * CPU's smallest page size. + */ + return !PAGE_ALIGNED(addr); +} + static int submit_lookup_objects(struct msm_gem_submit *submit, struct drm_msm_gem_submit *args, struct drm_file *file) { - unsigned i; + unsigned i, bo_stride = args->bos_stride; int ret = 0; + if (!bo_stride) + bo_stride = sizeof(struct drm_msm_gem_submit_bo); + for (i = 0; i < args->nr_bos; i++) { - struct drm_msm_gem_submit_bo submit_bo; + struct drm_msm_gem_submit_bo_v2 submit_bo = {0}; void __user *userptr = - u64_to_user_ptr(args->bos + (i * sizeof(submit_bo))); + u64_to_user_ptr(args->bos + (i * bo_stride)); + unsigned copy_sz = min(bo_stride, sizeof(submit_bo)); /* make sure we don't have garbage flags, in case we hit * error path before flags is initialized: */ submit->bos[i].flags = 0; - if (copy_from_user(&submit_bo, userptr, sizeof(submit_bo))) { + if (copy_from_user(&submit_bo, userptr, copy_sz)) { ret = -EFAULT; i = 0; goto out; @@ -141,14 +155,27 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, #define MANDATORY_FLAGS (MSM_SUBMIT_BO_READ | MSM_SUBMIT_BO_WRITE) if ((submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) || - !(submit_bo.flags & MANDATORY_FLAGS)) { + !(submit_bo.flags & MANDATORY_FLAGS)) ret = SUBMIT_ERROR(EINVAL, submit, "invalid flags: %x\n", submit_bo.flags); + + if (invalid_alignment(submit_bo.address)) + ret = SUBMIT_ERROR(EINVAL, submit, "invalid address: %016llx\n", submit_bo.address); + + if (invalid_alignment(submit_bo.bo_offset)) + ret = SUBMIT_ERROR(EINVAL, submit, "invalid bo_offset: %016llx\n", submit_bo.bo_offset); + + if (invalid_alignment(submit_bo.range)) + ret = SUBMIT_ERROR(EINVAL, submit, "invalid range: %016llx\n", submit_bo.range); + + if (ret) { i = 0; goto out; } submit->bos[i].handle = submit_bo.handle; submit->bos[i].flags = submit_bo.flags; + submit->bos[i].bo_offset = submit_bo.bo_offset; + submit->bos[i].range = submit_bo.range; } spin_lock(&file->table_lock); @@ -167,6 +194,15 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, drm_gem_object_get(obj); + if (submit->bos[i].bo_offset > obj->size) + ret = SUBMIT_ERROR(EINVAL, submit, "bo_offset to large: %016llx\n", submit->bos[i].bo_offset); + + if ((submit->bos[i].bo_offset + submit->bos[i].range) > obj->size) + ret = SUBMIT_ERROR(EINVAL, submit, "range to large: %016llx\n", submit->bos[i].range); + + if (ret) + goto out_unlock; + submit->bos[i].obj = obj; } @@ -182,6 +218,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, static int submit_lookup_cmds(struct msm_gem_submit *submit, struct drm_msm_gem_submit *args, struct drm_file *file) { + struct msm_context *ctx = file->driver_priv; unsigned i; size_t sz; int ret = 0; @@ -213,6 +250,19 @@ static int submit_lookup_cmds(struct msm_gem_submit *submit, goto out; } + if (msm_context_is_vmbind(ctx)) { + if (submit_cmd.nr_relocs) { + ret = SUBMIT_ERROR(EINVAL, submit, "nr_relocs must be zero"); + goto out; + } + if (submit_cmd.submit_idx || submit_cmd.submit_offset) { + ret = SUBMIT_ERROR(EINVAL, submit, "submit_idx/offset must be zero"); + goto out; + } + + submit->cmd[i].iova = submit_cmd.iova; + } + submit->cmd[i].type = submit_cmd.type; submit->cmd[i].size = submit_cmd.size / 4; submit->cmd[i].offset = submit_cmd.submit_offset / 4; @@ -665,9 +715,6 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (!gpu) return -ENXIO; - if (args->pad) - return -EINVAL; - if (to_msm_vm(ctx->vm)->unusable) return UERR(EPIPE, dev, "context is unusable"); @@ -677,7 +724,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (MSM_PIPE_ID(args->flags) != MSM_PIPE_3D0) return UERR(EINVAL, dev, "invalid pipe"); - if (MSM_PIPE_FLAGS(args->flags) & ~MSM_SUBMIT_FLAGS) + if (MSM_PIPE_FLAGS(args->flags) & ~MSM_SUBMIT_EXEC_FLAGS) return UERR(EINVAL, dev, "invalid flags"); if (args->flags & MSM_SUBMIT_SUDO) { diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 072e82a80607..1a948d49c610 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -245,7 +245,10 @@ struct drm_msm_gem_submit_cmd { __u32 size; /* in, cmdstream size */ __u32 pad; __u32 nr_relocs; /* in, number of submit_reloc's */ - __u64 relocs; /* in, ptr to array of submit_reloc's */ + union { + __u64 relocs; /* in, ptr to array of submit_reloc's */ + __u64 iova; /* cmdstream address (for VM_BIND contexts) */ + }; }; /* Each buffer referenced elsewhere in the cmdstream submit (ie. the @@ -264,6 +267,19 @@ struct drm_msm_gem_submit_cmd { #define MSM_SUBMIT_BO_DUMP 0x0004 #define MSM_SUBMIT_BO_NO_IMPLICIT 0x0008 +/* Map OP for for submits to a VM_BIND submitqueue: + * - MAP: map a specified range of the BO into the VM + * - MAP_NULL: map a NULL page into the specified range of the VM, handle + * and bo_offset MBZ. A NULL range will return zero on reads + * and discard writes + * see: VkPhysicalDeviceSparseProperties::residencyNonResidentStrict + * - UNMAP: unmap a specified VM range, handle and bo_offset MBZ + */ +#define MSM_SUBMIT_BO_OP_MASK 0xf000 +#define MSM_SUBMIT_BO_OP_MAP 0x0000 +#define MSM_SUBMIT_BO_OP_MAP_NULL 0x1000 +#define MSM_SUBMIT_BO_OP_UNMAP 0x2000 + #define MSM_SUBMIT_BO_FLAGS (MSM_SUBMIT_BO_READ | \ MSM_SUBMIT_BO_WRITE | \ MSM_SUBMIT_BO_DUMP | \ @@ -272,7 +288,16 @@ struct drm_msm_gem_submit_cmd { struct drm_msm_gem_submit_bo { __u32 flags; /* in, mask of MSM_SUBMIT_BO_x */ __u32 handle; /* in, GEM handle */ - __u64 presumed; /* in/out, presumed buffer address */ + __u64 address; /* in/out, presumed buffer address */ +}; + +struct drm_msm_gem_submit_bo_v2 { + __u32 flags; /* in, mask of MSM_SUBMIT_BO_x */ + __u32 handle; /* in, GEM handle */ + __u64 address; /* in/out, presumed buffer address */ + /* Remaining fields are only used with MSM_SUBMIT_OP_VM_BIND/_ASYNC: */ + __u64 bo_offset; + __u64 range; }; /* Valid submit ioctl flags: */ @@ -283,7 +308,8 @@ struct drm_msm_gem_submit_bo { #define MSM_SUBMIT_SYNCOBJ_IN 0x08000000 /* enable input syncobj */ #define MSM_SUBMIT_SYNCOBJ_OUT 0x04000000 /* enable output syncobj */ #define MSM_SUBMIT_FENCE_SN_IN 0x02000000 /* userspace passes in seqno fence */ -#define MSM_SUBMIT_FLAGS ( \ + +#define MSM_SUBMIT_EXEC_FLAGS ( \ MSM_SUBMIT_NO_IMPLICIT | \ MSM_SUBMIT_FENCE_FD_IN | \ MSM_SUBMIT_FENCE_FD_OUT | \ @@ -293,6 +319,13 @@ struct drm_msm_gem_submit_bo { MSM_SUBMIT_FENCE_SN_IN | \ 0) +#define MSM_SUBMIT_VM_BIND_FLAGS ( \ + MSM_SUBMIT_FENCE_FD_IN | \ + MSM_SUBMIT_FENCE_FD_OUT | \ + MSM_SUBMIT_SYNCOBJ_IN | \ + MSM_SUBMIT_SYNCOBJ_OUT | \ + 0) + #define MSM_SUBMIT_SYNCOBJ_RESET 0x00000001 /* Reset syncobj after wait. */ #define MSM_SUBMIT_SYNCOBJ_FLAGS ( \ MSM_SUBMIT_SYNCOBJ_RESET | \ @@ -307,14 +340,17 @@ struct drm_msm_gem_submit_syncobj { /* Each cmdstream submit consists of a table of buffers involved, and * one or more cmdstream buffers. This allows for conditional execution * (context-restore), and IB buffers needed for per tile/bin draw cmds. + * + * For MSM_SUBMIT_VM_BIND/_ASYNC operations, the queue must have been + * created with the MSM_SUBMITQUEUE_VM_BIND flag. */ struct drm_msm_gem_submit { __u32 flags; /* MSM_PIPE_x | MSM_SUBMIT_x */ __u32 fence; /* out (or in with MSM_SUBMIT_FENCE_SN_IN flag) */ __u32 nr_bos; /* in, number of submit_bo's */ - __u32 nr_cmds; /* in, number of submit_cmd's */ + __u32 nr_cmds; /* in, number of submit_cmd's, MBZ for VM_BIND queue */ __u64 bos; /* in, ptr to array of submit_bo's */ - __u64 cmds; /* in, ptr to array of submit_cmd's */ + __u64 cmds; /* in, ptr to array of submit_cmd's, MBZ for VM_BIND queue */ __s32 fence_fd; /* in/out fence fd (see MSM_SUBMIT_FENCE_FD_IN/OUT) */ __u32 queueid; /* in, submitqueue id */ __u64 in_syncobjs; /* in, ptr to array of drm_msm_gem_submit_syncobj */ @@ -322,8 +358,7 @@ struct drm_msm_gem_submit { __u32 nr_in_syncobjs; /* in, number of entries in in_syncobj */ __u32 nr_out_syncobjs; /* in, number of entries in out_syncobj. */ __u32 syncobj_stride; /* in, stride of syncobj arrays. */ - __u32 pad; /*in, reserved for future use, always 0. */ - + __u32 bos_stride; /* in, stride of bos array, if zero 16bytes used. */ }; #define MSM_WAIT_FENCE_BOOST 0x00000001 From patchwork Wed Mar 19 14:52:30 2025 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Rob Clark X-Patchwork-Id: 14022745 Received: from mail-pl1-f177.google.com (mail-pl1-f177.google.com [209.85.214.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A7204214A60; Wed, 19 Mar 2025 14:55:42 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.214.177 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742396144; cv=none; b=uDbhKTn2YP89DKRrUyAN1wYk8x2iToqrWrMXpDw9VXXVaL4/En0Lgg2SqlF72WzIJnevfWjtKPCdEI7CMkIt1WU9zQ+rhxN/jc3NsuHcl9HZiHgtFdHMThP8knPBPqigOoYW58hcUou8LOq7ywRBljcMr4gmtERw+sgr37F2KUw= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742396144; c=relaxed/simple; bh=Pk8qrg8XbQ3vqlzNp8run9pseTLdpNaZRm01OhGQn4s=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=CjChv/71P9bEuT6CKyc3bYJt+c0GneUmYDJPLnj3vtt3eYPEIIeiifop92T30sQKdbHLhxEa4r09uTqpWYnic/GrLJmq3fCrw6l91etOD1nZd7r1hsmRfi0jnGheBWh5W47zo614xk3n9EBGEHfEkAhstuH+6x4YoL5swGAu/CI= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=iFvJppNQ; arc=none smtp.client-ip=209.85.214.177 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="iFvJppNQ" Received: by mail-pl1-f177.google.com with SMTP id d9443c01a7336-223f4c06e9fso14544065ad.1; Wed, 19 Mar 2025 07:55:42 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1742396142; x=1743000942; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=8XT8DN3ZleGCofMlQ1mMQjy7k/r/T2YXHUe97y9PZGo=; b=iFvJppNQA0rW5yrdsrzz+mHhNfRbnJ86UPYU/SG4/Le4ZzzibGBFVCpW7UV7ZwFHO8 yVk+N2WwTL2XwFg6UjDbo0rZl7xn7R0kIiLS+fLb6VkK8IckcChvilFwIXdQVzbRrqDW UusBxmzn5Z7ESCEL6H3Qqopfq5wzeAayqy1XWJmaVKAclBENNO4l81688/khaEkrCK7i OeN5mtQ0kD+HXLNLp+7uram/8nJkGYMyMZcGcLqLJNZZxxHfM5M2lsZfa2hc4ossBpHE W28fcX+AMn05uFo8CYBfF5osl6SbqGFsTOF8FALfGkOmTaEHsKb/OSk7DMfXNkdgb4Eu yzuA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1742396142; x=1743000942; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=8XT8DN3ZleGCofMlQ1mMQjy7k/r/T2YXHUe97y9PZGo=; b=L71R1eOM89l2DKV0ZSt99l/UrryLkWY6GvRPDxJra/14tuCBYfIsclAFzSMwsJ8lxT OhuR59fIKPypxDTPqFB1HNbg4tq8tJr7ZvcmR9hRRyIObyccVZbZpj43V/FtFm6SwWBk qKVW4OImsP3vWE/WEEv/ANKEtZBnSdeIs+k4GGSl90yHozwmVDbhxnEiclzD5d1MU3EL ZcV51mWasH9X1mTNmnaCW3AJYQJosgSMykyks5FzMFs6eGnviYZ6RsTcWoB6229WhpHP WourFbFcJUZg/JVjA2ohD43ttqZL8iX2mo9eV37mEi92HCkzgFFFqTqVgdxAvHZzJHGG I5pA== X-Forwarded-Encrypted: i=1; AJvYcCUL6Zxtigd9HQvagMeE1Gd4xyJOrmUHME1FRMq5/yRjZ9I/PPhjBVgHKIBkeKOq+25/g0d/Lll1XPuDc5Y=@vger.kernel.org, AJvYcCWuZXIWajfhz+Foj85D8A7z+AwXHgJk2HryYA9J1EJsBOX6pkl0AZJux+wCcjt48reDL1ct1Wj4+mJMFY4Z@vger.kernel.org, AJvYcCXY6XQUo4izBMWyOHZjlgm9dRKML2HAv21+rOYhrhBFFGMQIlt6lPj25uR+KtaPgIg/u/4ThB0IYzivJla4@vger.kernel.org X-Gm-Message-State: AOJu0Yzvx9wNnNtBfRRrdv9lkXzmBwJCKPGBBO+YcX9fMJ+vWHeq5IBX ga08+HElZFJGKrl+mz4Tm8LyXkILbXHmX2Kjx+CJxsQOplPhWxjj X-Gm-Gg: ASbGncsUk2rA5kaCZEwzo5daOJgFw4gQGxRPSStSJP0MqFh6U8mi9AQJKLKt8pC2aFD hg58G9zpNQCbsH5wdbdPyb8Qhm3RGak/OH8WyNLEYAI5+zr8hLR55evu0rG6qLbzH+6V1psrC4m /U0d7pMqIEvgSbDxiY019PyxuAx9zOm96EFJ9f4GzKDBJJLtLaxfFqNzvYyLXY0E0SKf8ECegcQ Z55nR0vJ6qO5b3bVAldwfsxlDkLbMK8CLXR/7xwK6pEEfhAGreOtw/4iWEjUIqHVoENsN55CMYh gFOGzKUif4MFV71Qb4TfzycnV6edm7amIK1QBDXiEg9epXajIIt2N3pFvY0qk5UtzjnOgD7b2kJ kjvEoS8/nT5xW68HKoZk= X-Google-Smtp-Source: AGHT+IGKKoZeugIMzJo9Kl0W+rcTmXvkdvQFEcCdjrL7jzz+9e7IC2DNU5xrIm+Wn0RuPWMuOADobQ== X-Received: by 2002:a17:902:e803:b0:21f:6f33:f96 with SMTP id d9443c01a7336-2262c99c631mr107794785ad.6.1742396141855; Wed, 19 Mar 2025 07:55:41 -0700 (PDT) Received: from localhost ([2a00:79e0:3e00:2601:3afc:446b:f0df:eadc]) by smtp.gmail.com with ESMTPSA id d9443c01a7336-225c6ba7260sm114891055ad.110.2025.03.19.07.55.40 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 19 Mar 2025 07:55:40 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: freedreno@lists.freedesktop.org, linux-arm-msm@vger.kernel.org, Rob Clark , Rob Clark , Abhinav Kumar , Dmitry Baryshkov , Sean Paul , Marijn Suijten , David Airlie , Simona Vetter , Konrad Dybcio , Maarten Lankhorst , Maxime Ripard , Thomas Zimmermann , Sumit Semwal , =?utf-8?q?Christian_K=C3=B6nig?= , linux-kernel@vger.kernel.org (open list), linux-media@vger.kernel.org (open list:DMA BUFFER SHARING FRAMEWORK:Keyword:\bdma_(?:buf|fence|resv)\b), linaro-mm-sig@lists.linaro.org (moderated list:DMA BUFFER SHARING FRAMEWORK:Keyword:\bdma_(?:buf|fence|resv)\b) Subject: [PATCH v2 18/34] drm/msm: Add VM_BIND submitqueue Date: Wed, 19 Mar 2025 07:52:30 -0700 Message-ID: <20250319145425.51935-19-robdclark@gmail.com> X-Mailer: git-send-email 2.48.1 In-Reply-To: <20250319145425.51935-1-robdclark@gmail.com> References: <20250319145425.51935-1-robdclark@gmail.com> Precedence: bulk X-Mailing-List: linux-media@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 From: Rob Clark This submitqueue type isn't tied to a hw ringbuffer, but instead executes on the CPU for performing async VM_BIND ops. Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_gem.c | 3 +- drivers/gpu/drm/msm/msm_gem.h | 10 ++ drivers/gpu/drm/msm/msm_gem_submit.c | 128 +++++++++++++++++++++++--- drivers/gpu/drm/msm/msm_gem_vma.c | 107 +++++++++++++++++++++ drivers/gpu/drm/msm/msm_gpu.h | 3 + drivers/gpu/drm/msm/msm_submitqueue.c | 57 +++++++++--- include/uapi/drm/msm_drm.h | 9 +- 7 files changed, 287 insertions(+), 30 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 5a5220b6f21d..4c68a3dd3fed 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -232,8 +232,7 @@ static void put_pages(struct drm_gem_object *obj) } } -static struct page **msm_gem_get_pages_locked(struct drm_gem_object *obj, - unsigned madv) +struct page **msm_gem_get_pages_locked(struct drm_gem_object *obj, unsigned madv) { struct msm_gem_object *msm_obj = to_msm_bo(obj); diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index 8e29e36ca9c5..d427ead2dce0 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -53,6 +53,13 @@ struct msm_gem_vm { /** @base: Inherit from drm_gpuvm. */ struct drm_gpuvm base; + /** + * @sched: Scheduler used for asynchronous VM_BIND request. + * + * Unused for kernel managed VMs (where all operations are synchronous). + */ + struct drm_gpu_scheduler sched; + /** * @mm: Memory management for kernel managed VA allocations * @@ -106,6 +113,8 @@ struct drm_gpuvm * msm_gem_vm_create(struct drm_device *drm, struct msm_mmu *mmu, const char *name, u64 va_start, u64 va_size, bool managed); +void msm_gem_vm_close(struct drm_gpuvm *gpuvm); + struct msm_fence_context; /** @@ -195,6 +204,7 @@ int msm_gem_get_and_pin_iova(struct drm_gem_object *obj, struct drm_gpuvm *vm, uint64_t *iova); void msm_gem_unpin_iova(struct drm_gem_object *obj, struct drm_gpuvm *vm); void msm_gem_pin_obj_locked(struct drm_gem_object *obj); +struct page **msm_gem_get_pages_locked(struct drm_gem_object *obj, unsigned madv); struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj); void msm_gem_unpin_pages_locked(struct drm_gem_object *obj); int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev, diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index bb61231ab8ba..39a6e0418bdf 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -23,6 +23,11 @@ #define SUBMIT_ERROR(err, submit, fmt, ...) \ UERR(err, (submit)->dev, fmt, ##__VA_ARGS__) +static bool submit_is_vmbind(struct msm_gem_submit *submit) +{ + return !!(submit->queue->flags & MSM_SUBMITQUEUE_VM_BIND); +} + /* * Cmdstream submission: */ @@ -115,6 +120,17 @@ void __msm_gem_submit_destroy(struct kref *kref) kfree(submit); } +static bool invalid_bo_flags(bool vm_bind, uint32_t flags) +{ + if (vm_bind) { + return flags & ~(MSM_SUBMIT_BO_DUMP | MSM_SUBMIT_BO_OP_MASK); + } else { + /* at least one of READ and/or WRITE flags should be set: */ + return (flags & ~MSM_SUBMIT_BO_FLAGS) || + !(flags & (MSM_SUBMIT_BO_READ | MSM_SUBMIT_BO_WRITE)); + } +} + static bool invalid_alignment(uint64_t addr) { /* @@ -129,9 +145,10 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, struct drm_msm_gem_submit *args, struct drm_file *file) { unsigned i, bo_stride = args->bos_stride; + bool vm_bind = submit_is_vmbind(submit); int ret = 0; - if (!bo_stride) + if (!bo_stride || !vm_bind) bo_stride = sizeof(struct drm_msm_gem_submit_bo); for (i = 0; i < args->nr_bos; i++) { @@ -151,11 +168,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, goto out; } -/* at least one of READ and/or WRITE flags should be set: */ -#define MANDATORY_FLAGS (MSM_SUBMIT_BO_READ | MSM_SUBMIT_BO_WRITE) - - if ((submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) || - !(submit_bo.flags & MANDATORY_FLAGS)) + if (invalid_bo_flags(vm_bind, submit_bo.flags)) ret = SUBMIT_ERROR(EINVAL, submit, "invalid flags: %x\n", submit_bo.flags); if (invalid_alignment(submit_bo.address)) @@ -174,6 +187,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, submit->bos[i].handle = submit_bo.handle; submit->bos[i].flags = submit_bo.flags; + submit->bos[i].iova = submit_bo.address; submit->bos[i].bo_offset = submit_bo.bo_offset; submit->bos[i].range = submit_bo.range; } @@ -183,6 +197,12 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, for (i = 0; i < args->nr_bos; i++) { struct drm_gem_object *obj; + if (vm_bind) { + unsigned op = submit->bos[i].flags & MSM_SUBMIT_BO_OP_MASK; + if (op != MSM_SUBMIT_BO_OP_MAP) + continue; + } + /* normally use drm_gem_object_lookup(), but for bulk lookup * all under single table_lock just hit object_idr directly: */ @@ -297,13 +317,22 @@ static int submit_lookup_cmds(struct msm_gem_submit *submit, /* This is where we make sure all the bo's are reserved and pin'd: */ static int submit_lock_objects(struct msm_gem_submit *submit) { + bool vm_bind = submit_is_vmbind(submit); + unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT; int ret; - drm_exec_init(&submit->exec, DRM_EXEC_INTERRUPTIBLE_WAIT, submit->nr_bos); + if (vm_bind) + flags |= DRM_EXEC_IGNORE_DUPLICATES; + + drm_exec_init(&submit->exec, flags, submit->nr_bos); drm_exec_until_all_locked (&submit->exec) { for (unsigned i = 0; i < submit->nr_bos; i++) { struct drm_gem_object *obj = submit->bos[i].obj; + + if (!obj) + continue; + ret = drm_exec_prepare_obj(&submit->exec, obj, 1); drm_exec_retry_on_contention(&submit->exec); if (ret) @@ -372,6 +401,28 @@ static int submit_pin_vmas(struct msm_gem_submit *submit) return ret; } +static int submit_get_pages(struct msm_gem_submit *submit) +{ + /* + * First loop, before holding the LRU lock, avoids holding the + * LRU lock while calling msm_gem_pin_vma_locked (which could + * trigger get_pages()) + */ + for (int i = 0; i < submit->nr_bos; i++) { + struct drm_gem_object *obj = submit->bos[i].obj; + struct page **pages; + + if (!obj) + continue; + + pages = msm_gem_get_pages_locked(obj, MSM_MADV_WILLNEED); + if (IS_ERR(pages)) + return PTR_ERR(pages); + } + + return 0; +} + static void submit_pin_objects(struct msm_gem_submit *submit) { struct msm_drm_private *priv = submit->dev->dev_private; @@ -385,7 +436,12 @@ static void submit_pin_objects(struct msm_gem_submit *submit) */ mutex_lock(&priv->lru.lock); for (int i = 0; i < submit->nr_bos; i++) { - msm_gem_pin_obj_locked(submit->bos[i].obj); + struct drm_gem_object *obj = submit->bos[i].obj; + + if (!obj) + continue; + + msm_gem_pin_obj_locked(obj); } mutex_unlock(&priv->lru.lock); @@ -400,6 +456,9 @@ static void submit_unpin_objects(struct msm_gem_submit *submit) for (int i = 0; i < submit->nr_bos; i++) { struct drm_gem_object *obj = submit->bos[i].obj; + if (!obj) + continue; + msm_gem_unpin_locked(obj); } @@ -413,6 +472,9 @@ static void submit_attach_object_fences(struct msm_gem_submit *submit) for (i = 0; i < submit->nr_bos; i++) { struct drm_gem_object *obj = submit->bos[i].obj; + if (!obj) + continue; + if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE) dma_resv_add_fence(obj->resv, submit->user_fence, DMA_RESV_USAGE_WRITE); @@ -708,6 +770,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, struct msm_ringbuffer *ring; struct msm_submit_post_dep *post_deps = NULL; struct drm_syncobj **syncobjs_to_reset = NULL; + unsigned cmds_to_parse; int out_fence_fd = -1; unsigned i; int ret; @@ -724,9 +787,6 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (MSM_PIPE_ID(args->flags) != MSM_PIPE_3D0) return UERR(EINVAL, dev, "invalid pipe"); - if (MSM_PIPE_FLAGS(args->flags) & ~MSM_SUBMIT_EXEC_FLAGS) - return UERR(EINVAL, dev, "invalid flags"); - if (args->flags & MSM_SUBMIT_SUDO) { if (!IS_ENABLED(CONFIG_DRM_MSM_GPU_SUDO) || !capable(CAP_SYS_RAWIO)) @@ -737,6 +797,26 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (!queue) return -ENOENT; + if (queue->flags & MSM_SUBMITQUEUE_VM_BIND) { + if (args->nr_cmds || args->cmds) { + ret = UERR(EINVAL, dev, "nr_cmds should be zero for VM_BIND queue"); + goto out_post_unlock; + } + if (MSM_PIPE_FLAGS(args->flags) & ~MSM_SUBMIT_VM_BIND_FLAGS) { + ret = UERR(EINVAL, dev, "invalid flags"); + goto out_post_unlock; + } + } else { + if (msm_context_is_vmbind(ctx) && (args->nr_bos || args->bos)) { + ret = UERR(EINVAL, dev, "nr_bos should be zero for VM_BIND contexts"); + goto out_post_unlock; + } + if (MSM_PIPE_FLAGS(args->flags) & ~MSM_SUBMIT_EXEC_FLAGS) { + ret = UERR(EINVAL, dev, "invalid flags"); + goto out_post_unlock; + } + } + ring = gpu->rb[queue->ring_nr]; if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) { @@ -813,19 +893,37 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (ret) goto out; - if (!(args->flags & MSM_SUBMIT_NO_IMPLICIT)) { + if (msm_context_is_vmbind(ctx) && !submit_is_vmbind(submit)) { + /* + * If we are not using VM_BIND, submit_pin_vmas() will validate + * just the BOs attached to the submit. In that case we don't + * need to validate the _entire_ vm, because userspace tracked + * what BOs are associated with the submit. + */ + ret = drm_gpuvm_validate(submit->vm, &submit->exec); + if (ret) + goto out; + } + + if (!(args->flags & MSM_SUBMIT_NO_IMPLICIT) && !submit_is_vmbind(submit)) { ret = submit_fence_sync(submit); if (ret) goto out; } - ret = submit_pin_vmas(submit); + if (submit_is_vmbind(submit)) { + ret = submit_get_pages(submit); + } else { + ret = submit_pin_vmas(submit); + } if (ret) goto out; submit_pin_objects(submit); - for (i = 0; i < args->nr_cmds; i++) { + cmds_to_parse = msm_context_is_vmbind(ctx) ? 0 : args->nr_cmds; + + for (i = 0; i < cmds_to_parse; i++) { struct drm_gem_object *obj; uint64_t iova; @@ -856,7 +954,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, goto out; } - submit->nr_cmds = i; + submit->nr_cmds = args->nr_cmds; idr_preload(GFP_KERNEL); diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c index 0bc22618e9f0..8c780dd6a936 100644 --- a/drivers/gpu/drm/msm/msm_gem_vma.c +++ b/drivers/gpu/drm/msm/msm_gem_vma.c @@ -162,6 +162,70 @@ static const struct drm_gpuvm_ops msm_gpuvm_ops = { .vm_free = msm_gem_vm_free, }; +static int +run_bo_op(struct msm_gem_submit *submit, const struct msm_gem_submit_bo *bo) +{ + unsigned op = bo->flags & MSM_SUBMIT_BO_OP_MASK; + + switch (op) { + case MSM_SUBMIT_BO_OP_MAP: + case MSM_SUBMIT_BO_OP_MAP_NULL: + return drm_gpuvm_sm_map(submit->vm, submit->vm, bo->iova, + bo->range, bo->obj, bo->bo_offset); + break; + case MSM_SUBMIT_BO_OP_UNMAP: + return drm_gpuvm_sm_unmap(submit->vm, submit->vm, bo->iova, + bo->bo_offset); + } + + return -EINVAL; +} + +static struct dma_fence * +msm_vma_job_run(struct drm_sched_job *job) +{ + struct msm_gem_submit *submit = to_msm_submit(job); + + for (unsigned i = 0; i < submit->nr_bos; i++) { + int ret = run_bo_op(submit, &submit->bos[i]); + if (ret) { + to_msm_vm(submit->vm)->unusable = true; + return ERR_PTR(ret); + } + } + + /* VM_BIND ops run on CPU, so we are done now: */ + msm_submit_retire(submit); + + for (int i = 0; i < submit->nr_bos; i++) { + struct drm_gem_object *obj = submit->bos[i].obj; + + if (!obj) + continue; + + msm_gem_lock(obj); + msm_gem_unpin_locked(obj); + msm_gem_unlock(obj); + } + + /* VM_BIND ops are synchronous, so no fence to wait on: */ + return NULL; +} + +static void +msm_vma_job_free(struct drm_sched_job *job) +{ + struct msm_gem_submit *submit = to_msm_submit(job); + + drm_sched_job_cleanup(job); + msm_gem_submit_put(submit); +} + +static const struct drm_sched_backend_ops msm_vm_bind_ops = { + .run_job = msm_vma_job_run, + .free_job = msm_vma_job_free +}; + /** * msm_gem_vm_create() - Create and initialize a &msm_gem_vm * @drm: the drm device @@ -198,6 +262,21 @@ msm_gem_vm_create(struct drm_device *drm, struct msm_mmu *mmu, const char *name, goto err_free_vm; } + if (!managed) { + struct drm_sched_init_args args = { + .ops = &msm_vm_bind_ops, + .num_rqs = 1, + .credit_limit = 1, + .timeout = MAX_SCHEDULE_TIMEOUT, + .name = "msm-vm-bind", + .dev = drm->dev, + }; + + ret = drm_sched_init(&vm->sched, &args); + if (ret) + goto err_free_dummy; + } + drm_gpuvm_init(&vm->base, name, flags, drm, dummy_gem, va_start, va_size, 0, 0, &msm_gpuvm_ops); drm_gem_object_put(dummy_gem); @@ -212,8 +291,36 @@ msm_gem_vm_create(struct drm_device *drm, struct msm_mmu *mmu, const char *name, return &vm->base; +err_free_dummy: + drm_gem_object_put(dummy_gem); + err_free_vm: kfree(vm); return ERR_PTR(ret); } + +/** + * msm_gem_vm_close() - Close a VM + * @gpuvm: The VM to close + * + * Called when the drm device file is closed, to tear down VM related resources + * (which will drop refcounts to GEM objects that were still mapped into the + * VM at the time). + */ +void +msm_gem_vm_close(struct drm_gpuvm *gpuvm) +{ + struct msm_gem_vm *vm = to_msm_vm(gpuvm); + + /* + * For kernel managed VMs, the VMAs are torn down when the handle is + * closed, so nothing more to do. + */ + if (vm->managed) + return; + + /* Kill the scheduler now, so we aren't racing with it for cleanup: */ + drm_sched_stop(&vm->sched, NULL); + drm_sched_fini(&vm->sched); +} diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 20f52d9636b0..49c8862ada13 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -562,6 +562,9 @@ struct msm_gpu_submitqueue { struct mutex lock; struct kref ref; struct drm_sched_entity *entity; + + /** @_vm_bind_entity: used for @entity pointer for VM_BIND queues */ + struct drm_sched_entity _vm_bind_entity[0]; }; struct msm_gpu_state_bo { diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index 8ced49c7557b..99ab780d5d7b 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -72,6 +72,9 @@ void msm_submitqueue_destroy(struct kref *kref) idr_destroy(&queue->fence_idr); + if (queue->entity == &queue->_vm_bind_entity[0]) + drm_sched_entity_destroy(queue->entity); + msm_context_put(queue->ctx); kfree(queue); @@ -115,6 +118,11 @@ void msm_submitqueue_close(struct msm_context *ctx) list_del(&entry->node); msm_submitqueue_put(entry); } + + if (!ctx->vm) + return; + + msm_gem_vm_close(ctx->vm); } static struct drm_sched_entity * @@ -160,8 +168,6 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_context *ctx, struct msm_drm_private *priv = drm->dev_private; struct msm_gpu_submitqueue *queue; enum drm_sched_priority sched_prio; - extern int enable_preemption; - bool preemption_supported; unsigned ring_nr; int ret; @@ -171,26 +177,53 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_context *ctx, if (!priv->gpu) return -ENODEV; - preemption_supported = priv->gpu->nr_rings == 1 && enable_preemption != 0; + if (flags & MSM_SUBMITQUEUE_VM_BIND) { + unsigned sz; - if (flags & MSM_SUBMITQUEUE_ALLOW_PREEMPT && preemption_supported) - return -EINVAL; + /* Not allowed for kernel managed VMs (ie. kernel allocs VA) */ + if (!msm_context_is_vmbind(ctx)) + return -EINVAL; - ret = msm_gpu_convert_priority(priv->gpu, prio, &ring_nr, &sched_prio); - if (ret) - return ret; + if (prio) + return -EINVAL; + + sz = struct_size(queue, _vm_bind_entity, 1); + queue = kzalloc(sz, GFP_KERNEL); + } else { + extern int enable_preemption; + bool preemption_supported = + priv->gpu->nr_rings == 1 && enable_preemption != 0; + + if (flags & MSM_SUBMITQUEUE_ALLOW_PREEMPT && preemption_supported) + return -EINVAL; - queue = kzalloc(sizeof(*queue), GFP_KERNEL); + ret = msm_gpu_convert_priority(priv->gpu, prio, &ring_nr, &sched_prio); + if (ret) + return ret; + + queue = kzalloc(sizeof(*queue), GFP_KERNEL); + } if (!queue) return -ENOMEM; kref_init(&queue->ref); queue->flags = flags; - queue->ring_nr = ring_nr; - queue->entity = get_sched_entity(ctx, priv->gpu->rb[ring_nr], - ring_nr, sched_prio); + if (flags & MSM_SUBMITQUEUE_VM_BIND) { + struct drm_gpu_scheduler *sched = &to_msm_vm(msm_context_vm(drm, ctx))->sched; + + queue->entity = &queue->_vm_bind_entity[0]; + + drm_sched_entity_init(queue->entity, DRM_SCHED_PRIORITY_KERNEL, + &sched, 1, NULL); + } else { + queue->ring_nr = ring_nr; + + queue->entity = get_sched_entity(ctx, priv->gpu->rb[ring_nr], + ring_nr, sched_prio); + } + if (IS_ERR(queue->entity)) { ret = PTR_ERR(queue->entity); kfree(queue); diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 1a948d49c610..39b55c8d7413 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -404,12 +404,19 @@ struct drm_msm_gem_madvise { /* * Draw queues allow the user to set specific submission parameter. Command * submissions specify a specific submitqueue to use. ID 0 is reserved for - * backwards compatibility as a "default" submitqueue + * backwards compatibility as a "default" submitqueue. + * + * Because VM_BIND async updates happen on the CPU, they must run on a + * virtual queue created with the flag MSM_SUBMITQUEUE_VM_BIND. If we had + * a way to do pgtable updates on the GPU, we could drop this restriction. */ #define MSM_SUBMITQUEUE_ALLOW_PREEMPT 0x00000001 +#define MSM_SUBMITQUEUE_VM_BIND 0x00000002 /* virtual queue for VM_BIND ops */ + #define MSM_SUBMITQUEUE_FLAGS ( \ MSM_SUBMITQUEUE_ALLOW_PREEMPT | \ + MSM_SUBMITQUEUE_VM_BIND | \ 0) /* From patchwork Wed Mar 19 14:52:31 2025 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Rob Clark X-Patchwork-Id: 14022746 Received: from mail-pj1-f48.google.com (mail-pj1-f48.google.com [209.85.216.48]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 994AD1DED6B; Wed, 19 Mar 2025 14:55:44 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.216.48 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742396146; cv=none; b=RBYI0q3eiThUeFWsFqOcljobhqQa3gc2aercpM+9/RCIboUV7hID8ZYCDAeJARfH6UUHVwwKm7aMnxf85MQFHxYhpxbAXqafuNjCxrB4zo2WCYXU8L9tkarf2b8Jo4KXZC6ZjQ5w18mUsN2WvgYLvgK8jZWz7BrKSjSSK2xA5xc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1742396146; c=relaxed/simple; bh=Wf8zd+5GgvnEbx72cIC0QKnNJVwGLKIpsyfv36Azr5Y=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=vC5q2hLDrd6nn56ES6LV3mohhaeTVMw9kUBcdJastBbOXjSOvA30p1QPdSfis6C50PPTFtT0x/EivTyUCQnB8I4vCST+dub0s2Uvui7SOFrwRaQvuHUwOaUVmk7nx6HeS65/1iDGJFPWKJcln57Z9rAHt0Rr4NpnevefxaiV/HA= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=jCsiCuT8; arc=none smtp.client-ip=209.85.216.48 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="jCsiCuT8" Received: by mail-pj1-f48.google.com with SMTP id 98e67ed59e1d1-2ff85fec403so1814206a91.1; Wed, 19 Mar 2025 07:55:44 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1742396144; x=1743000944; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=AwhScULefMfboLX0liFkQPUFffcIJe/d8pWVK3z+O00=; b=jCsiCuT8y/tqssH6KM8GdOGJyn6CnacElejkLiewckQ9bSJIrnV1tXI+2f6Yjkc56+ n2SyUCASg+tF/RfY/CebNTTvUs2dj3z4hqM3d57V0XonIvJJkFW5zWIXmmHecg/yHvNj qJzfiNgXBV0aIUHRDviudoTcNz5cuMgRRkr8asO6xoumvWQZKBxP0DtcTi2o3MqYwGk0 o948dIDy9UdwGfpF1D2uy9oBymuCfkIrCJ57fCcSqIrlzo0/E5YJ3QaCxSP+EDE/r1A6 njtKT29ReyhTIVSnW6MAsfpmqdRaIDE8HpoQrud3oD9K+mG8S0vQq4ZwzlDH5kP9SQC2 dwuA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1742396144; x=1743000944; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=AwhScULefMfboLX0liFkQPUFffcIJe/d8pWVK3z+O00=; b=o9QFqe1/56cwIrZppxaNWsFnfMtabozxqb3d4ghSmoluKk9m6bkXie9X6o1N+VZnZ6 2t39BwpMlvRIRv4E4yDHJ7dsiysCI7iT19cxrtO7RRHlq3awfBkdgp/bf2Mq2qDM897U SRgjr4DMh5wuCtoQg6feWs87Z1+rO6liYG0ve2LxIpSh8TYLLGbriBHp6TfTa2fN40I0 y7X8eJXws6rR/GebsulwsRPUNK70ptty4/ocSXMiX49co9bBu95Wp3olubkqTgiyvnnD aDfKoYHnre4f6NPLwpGm097n8mkyE4sJW8/vy+J1lB9edDG4uKR6b3hdqT+WwTP9mNY/ 7aHA== X-Forwarded-Encrypted: i=1; AJvYcCVJE1KPXIMNa8xTL+GvMhAc1GEaKwqcOr2+P0/25L/UwUX9TqC79VJyLhvbR+O2LTeKcOj2SMVRCRantfc=@vger.kernel.org, AJvYcCW/1ymqLHt7g15fMEV3JGL63bpkGkOlOu9M7d90foKENHb955RHIJtNgwokyhehdVDnAKVmq3tkxpxvdFyc@vger.kernel.org, AJvYcCWAq5m1FtT9K9K+ynITDxYX1vNWI2oV0+PROy+PswKInbwcfziFd0ecXjwQgzg/yPM1DSl7OHkxnszqVXrS@vger.kernel.org X-Gm-Message-State: AOJu0Yz+SVYr0xxZRD/CldYuV6iOM8oPBSLL77TRUhWdxhFXvcmTTbr6 ffxWMsFm1clUgDibpXX2skbxMQ8jBGR+Lu88bG+FjasPTFglJHyU X-Gm-Gg: ASbGncvpAaSVnlAgCO3WIvNYRipi8mAfVmrNVfXgPtP9CHMkgAqCxEj7XqJB3zwhJTT oe8VniAdimq9+iydKWYg9xVgQOUoFPgkafwrLQA50Q8qT/alBrhtHnhbU/43/1mFW0aMu9ZVwXT 8ZWB0PhrvbLRH23HYVM7cDCjbV1xFpSQcexXXq3kr32M+nh6uwcmd6WOWiBdW4vjL/0mRi+4sKm 9l5MzXkYFe9BrMEI+YNh0ooVqv2TjT7GDVZJnCEa14Dxx7PVNtTEk0gsWZYHReO/RmdAebK0tET tBrlERJFUcQMyZZy7BcT6POSDD1fUf2iapwcVv/TbvLGVV3BUWNDrOIa1ftaIBRLbegGuZYUFcG SaZCD0juCrX0+4PpqxQ5wnzAdMSSTlA== X-Google-Smtp-Source: AGHT+IHCA/GqCE/f2P5dI0HamwPMEXDfsvX/N0jLiLWDfWHv3zNa6XPbkeXex6uF1RGR2mrPoY2f+w== X-Received: by 2002:a05:6a00:8c4:b0:728:f21b:ce4c with SMTP id d2e1a72fcca58-7376d55d06emr5667798b3a.5.1742396143748; Wed, 19 Mar 2025 07:55:43 -0700 (PDT) Received: from localhost ([2a00:79e0:3e00:2601:3afc:446b:f0df:eadc]) by smtp.gmail.com with ESMTPSA id d2e1a72fcca58-73711695abbsm11691211b3a.150.2025.03.19.07.55.42 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 19 Mar 2025 07:55:42 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: freedreno@lists.freedesktop.org, linux-arm-msm@vger.kernel.org, Rob Clark , Rob Clark , Abhinav Kumar , Dmitry Baryshkov , Sean Paul , Marijn Suijten , David Airlie , Simona Vetter , Konrad Dybcio , Maarten Lankhorst , Maxime Ripard , Thomas Zimmermann , Sumit Semwal , =?utf-8?q?Christian_K=C3=B6nig?= , linux-kernel@vger.kernel.org (open list), linux-media@vger.kernel.org (open list:DMA BUFFER SHARING FRAMEWORK:Keyword:\bdma_(?:buf|fence|resv)\b), linaro-mm-sig@lists.linaro.org (moderated list:DMA BUFFER SHARING FRAMEWORK:Keyword:\bdma_(?:buf|fence|resv)\b) Subject: [PATCH v2 19/34] drm/msm: Add _NO_SHARE flag Date: Wed, 19 Mar 2025 07:52:31 -0700 Message-ID: <20250319145425.51935-20-robdclark@gmail.com> X-Mailer: git-send-email 2.48.1 In-Reply-To: <20250319145425.51935-1-robdclark@gmail.com> References: <20250319145425.51935-1-robdclark@gmail.com> Precedence: bulk X-Mailing-List: linux-media@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 From: Rob Clark Buffers that are not shared between contexts can share a single resv object. This way drm_gpuvm will not track them as external objects, and submit-time validating overhead will be O(1) for all N non-shared BOs, instead of O(n). Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_drv.h | 1 + drivers/gpu/drm/msm/msm_gem.c | 23 +++++++++++++++++++++++ drivers/gpu/drm/msm/msm_gem_prime.c | 15 +++++++++++++++ include/uapi/drm/msm_drm.h | 14 ++++++++++++++ 4 files changed, 53 insertions(+) diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index b77fd2c531c3..b0add236cbb3 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -246,6 +246,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map); void msm_gem_prime_vunmap(struct drm_gem_object *obj, struct iosys_map *map); struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sg); +struct dma_buf *msm_gem_prime_export(struct drm_gem_object *obj, int flags); int msm_gem_prime_pin(struct drm_gem_object *obj); void msm_gem_prime_unpin(struct drm_gem_object *obj); diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 4c68a3dd3fed..9d4f7b76471f 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -522,6 +522,9 @@ static int get_and_pin_iova_range_locked(struct drm_gem_object *obj, msm_gem_assert_locked(obj); + if (to_msm_bo(obj)->flags & MSM_BO_NO_SHARE) + return -EINVAL; + vma = get_vma_locked(obj, vm, range_start, range_end); if (IS_ERR(vma)) return PTR_ERR(vma); @@ -1032,6 +1035,16 @@ static void msm_gem_free_object(struct drm_gem_object *obj) put_pages(obj); } + if (msm_obj->flags & MSM_BO_NO_SHARE) { + struct drm_gem_object *r_obj = + container_of(obj->resv, struct drm_gem_object, _resv); + + BUG_ON(obj->resv == &obj->_resv); + + /* Drop reference we hold to shared resv obj: */ + drm_gem_object_put(r_obj); + } + drm_gem_object_release(obj); kfree(msm_obj->metadata); @@ -1064,6 +1077,15 @@ int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file, if (name) msm_gem_object_set_name(obj, "%s", name); + if (flags & MSM_BO_NO_SHARE) { + struct msm_context *ctx = file->driver_priv; + struct drm_gem_object *r_obj = drm_gpuvm_resv_obj(ctx->vm); + + drm_gem_object_get(r_obj); + + obj->resv = r_obj->resv; + } + ret = drm_gem_handle_create(file, obj, handle); /* drop reference from allocate - handle holds it now */ @@ -1096,6 +1118,7 @@ static const struct drm_gem_object_funcs msm_gem_object_funcs = { .free = msm_gem_free_object, .open = msm_gem_open, .close = msm_gem_close, + .export = msm_gem_prime_export, .pin = msm_gem_prime_pin, .unpin = msm_gem_prime_unpin, .get_sg_table = msm_gem_prime_get_sg_table, diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c index ee267490c935..1a6d8099196a 100644 --- a/drivers/gpu/drm/msm/msm_gem_prime.c +++ b/drivers/gpu/drm/msm/msm_gem_prime.c @@ -16,6 +16,9 @@ struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj) struct msm_gem_object *msm_obj = to_msm_bo(obj); int npages = obj->size >> PAGE_SHIFT; + if (msm_obj->flags & MSM_BO_NO_SHARE) + return ERR_PTR(-EINVAL); + if (WARN_ON(!msm_obj->pages)) /* should have already pinned! */ return ERR_PTR(-ENOMEM); @@ -45,6 +48,15 @@ struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev, return msm_gem_import(dev, attach->dmabuf, sg); } + +struct dma_buf *msm_gem_prime_export(struct drm_gem_object *obj, int flags) +{ + if (to_msm_bo(obj)->flags & MSM_BO_NO_SHARE) + return ERR_PTR(-EPERM); + + return drm_gem_prime_export(obj, flags); +} + int msm_gem_prime_pin(struct drm_gem_object *obj) { struct page **pages; @@ -53,6 +65,9 @@ int msm_gem_prime_pin(struct drm_gem_object *obj) if (obj->import_attach) return 0; + if (to_msm_bo(obj)->flags & MSM_BO_NO_SHARE) + return -EINVAL; + pages = msm_gem_pin_pages_locked(obj); if (IS_ERR(pages)) ret = PTR_ERR(pages); diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 39b55c8d7413..a7e48ee1dd95 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -138,6 +138,19 @@ struct drm_msm_param { #define MSM_BO_SCANOUT 0x00000001 /* scanout capable */ #define MSM_BO_GPU_READONLY 0x00000002 +/* Private buffers do not need to be explicitly listed in the SUBMIT + * ioctl, unless referenced by a drm_msm_gem_submit_cmd. Private + * buffers may NOT be imported/exported or used for scanout (or any + * other situation where buffers can be indefinitely pinned, but + * cases other than scanout are all kernel owned BOs which are not + * visible to userspace). + * + * In exchange for those constraints, all private BOs associated with + * a single context (drm_file) share a single dma_resv, and if there + * has been no eviction since the last submit, there are no per-BO + * bookeeping to do, significantly cutting the SUBMIT overhead. + */ +#define MSM_BO_NO_SHARE 0x00000004 #define MSM_BO_CACHE_MASK 0x000f0000 /* cache modes */ #define MSM_BO_CACHED 0x00010000 @@ -147,6 +160,7 @@ struct drm_msm_param { #define MSM_BO_FLAGS (MSM_BO_SCANOUT | \ MSM_BO_GPU_READONLY | \ + MSM_BO_NO_SHARE | \ MSM_BO_CACHE_MASK) struct drm_msm_gem_new {