From nobody Wed Oct 8 12:40:46 2025 Received: from mx0b-0031df01.pphosted.com (mx0b-0031df01.pphosted.com [205.220.180.131]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 7E74224467D for ; Sun, 29 Jun 2025 14:08:11 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=205.220.180.131 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1751206093; cv=none; b=AcsJ00WkhTdLoeIhBJPBjA7xli0dzs8co2kANP9kE6oWuRMcDlf4bG3w/XJ2O//AZU7Vypz9UK23+kZbmVKesj8BEagLg9noQUbg0RoLrl47ent8T9IRgL/7IH7jiuoI/cWlcXr4dZxmiJV3B5fB98jCP6BQBrtXvaVAh2gBhjk= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1751206093; c=relaxed/simple; bh=JsILLt2+b+xZrxxAbVvwrl1hB4+WAdrIOnzh9EnzXdU=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=KseKnHe1QJBqyFL7XYir0BWrnxedjTxmqDXeVV7WVCEPSUhEr2fodt0/DGRixkJmbinddcUKWgSAVpj/nV1GUm9sBYKzu8heF1e92uqA6XMFh++cm4Fzy4fpPeov55yxUqMAZn+G3j916zysxRJP1wSXxY7/mjvKYk83GT2i5cQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=oss.qualcomm.com; spf=pass smtp.mailfrom=oss.qualcomm.com; dkim=pass (2048-bit key) header.d=qualcomm.com header.i=@qualcomm.com header.b=fiI+gJT2; arc=none smtp.client-ip=205.220.180.131 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=oss.qualcomm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=oss.qualcomm.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=qualcomm.com header.i=@qualcomm.com header.b="fiI+gJT2" Received: from pps.filterd (m0279869.ppops.net [127.0.0.1]) by mx0a-0031df01.pphosted.com (8.18.1.2/8.18.1.2) with ESMTP id 55TADXsQ028542 for ; Sun, 29 Jun 2025 14:08:10 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=qualcomm.com; h= cc:content-transfer-encoding:date:from:in-reply-to:message-id :mime-version:references:subject:to; s=qcppdkim1; bh=iVk8CflO5KH TgfTqgOrc0graSmlaqzNMFTNHNE1Irm0=; b=fiI+gJT29jd5drbJ4nOPSM6hCPW DJpwqCUOXjIhbElg8gjmDz+c0bxMGhKwd8fwK4o/LwnURG4ZloHqioMH3bfxM1Ie unzPEa5pIadQDdTpx0lUJ0Ey0ems8wd9APThFn5RniqZNBRj/L8jQs+OFlff9M2r QTN9GxmZaQpbWRl0s13OZPHA/G+rgsQjLxDFWZU8TnbjcVzXmTEw28U0a0hKUo7+ ODl3LPEfUBsQM4euqZQQpVZbBoBly6uzh8DN2SC9lm1uW7wODgu/56qqfPsymCIL XPnDF5x9mqEUXBveEcZpcwMK29AQt7ZsGbLIbHdy3/Fk2RCgDX5fozuhnCA== Received: from mail-pf1-f199.google.com (mail-pf1-f199.google.com [209.85.210.199]) by mx0a-0031df01.pphosted.com (PPS) with ESMTPS id 47j7d9t9et-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128 verify=NOT) for ; Sun, 29 Jun 2025 14:08:10 +0000 (GMT) Received: by mail-pf1-f199.google.com with SMTP id d2e1a72fcca58-7492da755a1so976557b3a.1 for ; Sun, 29 Jun 2025 07:08:10 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1751206089; x=1751810889; 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=iVk8CflO5KHTgfTqgOrc0graSmlaqzNMFTNHNE1Irm0=; b=MSKB/SwZEKjemO/Y1506kr92dUGtE6Ov/+YpFTYvw71y4uoR135jojbJ42diP4sPID KWXMQAeDLHIY4VcApMq/pzrvjXICxLBxMkUXf3kYxusyzq/l1AKYbdEZx16Iy4u+NfGn 6a/pcReGK90K+6VC0KTmKATp2ZCSTpJ2zQexI5IYVRRW+Cuuskuk0zst/ur4lx43opak HB2ENzVUq3isyXgfvVGquXC9e3gu75n13ru9MGb8skDrILRNqvnOjdZByOIOxOx+X1wi slJO9hQbKSWdqVRpeztE5MAksGrwdphJt+gjuWkrHpzjtTiw+vwfRiBS6KoO/WjHD6qa YMpg== X-Forwarded-Encrypted: i=1; AJvYcCXqOwuU0kr0STtrJMe7xXWfz5V0ZIsr1hIK0R5vqGtNYTpprvwIz8Rt0h2pqut2dPwIU4e0zFTntofGpcs=@vger.kernel.org X-Gm-Message-State: AOJu0YxACuoncpJO80etKASCiRHsIeSZBwbDh0ueNvfYZ5QEmcEkz+ii f9d9ecg7vOe6MerZR0Z019KUjVWY5Ldpn2vZk1vF4wR9GO4RK5mBFTrb6YYHutzhhBcu23i7Ptl 2lkP8ztipvpi7O9gUVjED1QLru3DG58wlKLcuBM6QonTypEtEHGhcNJhSvJkNPSEDXmY= X-Gm-Gg: ASbGncuU26DTFBTC3I3E/XlzdD0G+e5Cwb5DMe9AGYB3TVmMe/wRBFGGXs8I3on81Df i5XWz/nxKCNDiizxk62gh7GAvQSWjoTI4+/umlAylfBMbbVxJqRw1u2UJ/W+mioD1pSTV23qYM5 I3wLkLFI9FA12IJTtT52iBsk+/R9u57Yn8F86dA0fcg3wM+JTzqS0BzfkiTQRvXvwpmMkWQLksc HWregKzLkbdca04G11mxiI3fkP2CWHmDwMxSiCKtyUlYbzYxhrtBVi7XPSDpnwSpbiBe9vP5Yrh UeYs3Sbx68nsH/Wih+EgDQTncji/T6uB X-Received: by 2002:a05:6a00:3d0c:b0:740:a023:5d60 with SMTP id d2e1a72fcca58-74af70169c1mr13465930b3a.19.1751206088929; Sun, 29 Jun 2025 07:08:08 -0700 (PDT) X-Google-Smtp-Source: AGHT+IFbWJbIQvDHD8EycgQb7AXqLyixheO7u4K5OIPfMTfi/5S9NCTN+H8I/tsChT7qBZnIDgfDhg== X-Received: by 2002:a05:6a00:3d0c:b0:740:a023:5d60 with SMTP id d2e1a72fcca58-74af70169c1mr13465890b3a.19.1751206088402; Sun, 29 Jun 2025 07:08:08 -0700 (PDT) Received: from localhost ([2601:1c0:5000:d5c:5b3e:de60:4fda:e7b1]) by smtp.gmail.com with ESMTPSA id d2e1a72fcca58-74af56cffd8sm7212728b3a.137.2025.06.29.07.08.07 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sun, 29 Jun 2025 07:08:07 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: freedreno@lists.freedesktop.org, linux-arm-msm@vger.kernel.org, Connor Abbott , Antonino Maniscalco , Danilo Krummrich , Rob Clark , Rob Clark , Dmitry Baryshkov , Abhinav Kumar , Jessica Zhang , Sean Paul , Marijn Suijten , David Airlie , Simona Vetter , linux-kernel@vger.kernel.org (open list) Subject: [PATCH v8 33/42] drm/msm: Support pgtable preallocation Date: Sun, 29 Jun 2025 07:03:36 -0700 Message-ID: <20250629140537.30850-34-robin.clark@oss.qualcomm.com> X-Mailer: git-send-email 2.50.0 In-Reply-To: <20250629140537.30850-1-robin.clark@oss.qualcomm.com> References: <20250629140537.30850-1-robin.clark@oss.qualcomm.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Proofpoint-Spam-Details-Enc: AW1haW4tMjUwNjI5MDExOSBTYWx0ZWRfX4DBgoZzztDjy yncJOTcSBmCZ+ohMV5AZ/eA1AnlcaBBxhhEfCi3gANjxglHSrXHIgZvXtdBImGdoP3KZXdJVxCl 2hNMZ7QZ2qW0j1ojVdVdrgHYT1Bb+YK8FIuz1vwKSeInm0r7lbgCgLCG4G8+chq7bbn7l/oGvvm qWe1obQ2r6SJbVTyb7bCoo+/u3rL/bPEoLpx7wdtqdHrep+duHDLe71S3cSiXc45NoLNfpHanug AW2RH/b/kubleXcEGXS/+SU84pK7/GKutViVMEqxpmUd+5XD+yNn2pW2fM4JFSFfKS7ewoA6t0M MjPhLWRMoKnYUnspsHB9lpZRUgkvjYavVk+PvdHvHDNXlffprE2SeUlgsBVyXuthTCr+2VfuCYV JzISY/HejLJtsoQS5cLbhtGKNxe8gxxJLeBLU2DSN+Y+yfIcusT5mpR/dT8Nf2XD6L+1c45D X-Proofpoint-GUID: DBv_yZxKSG6nvFG6T79gQC8emLhSrHFm X-Authority-Analysis: v=2.4 cv=RrbFLDmK c=1 sm=1 tr=0 ts=686148ca cx=c_pps a=WW5sKcV1LcKqjgzy2JUPuA==:117 a=xqWC_Br6kY4A:10 a=6IFa9wvqVegA:10 a=7CQSdrXTAAAA:8 a=cm27Pg_UAAAA:8 a=EUspDBNiAAAA:8 a=pGLkceISAAAA:8 a=FDPAursefL7ktZtO0vwA:9 a=OpyuDcXvxspvyRM73sMx:22 a=a-qgeE7W1pNrGK8U0ZQC:22 X-Proofpoint-ORIG-GUID: DBv_yZxKSG6nvFG6T79gQC8emLhSrHFm X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.293,Aquarius:18.0.1099,Hydra:6.1.7,FMLib:17.12.80.40 definitions=2025-06-27_05,2025-06-27_01,2025-03-28_01 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 impostorscore=0 mlxlogscore=999 adultscore=0 clxscore=1015 suspectscore=0 phishscore=0 bulkscore=0 malwarescore=0 spamscore=0 mlxscore=0 priorityscore=1501 lowpriorityscore=0 classifier=spam authscore=0 authtc=n/a authcc= route=outbound adjust=0 reason=mlx scancount=1 engine=8.19.0-2505280000 definitions=main-2506290119 Content-Type: text/plain; charset="utf-8" From: Rob Clark Introduce a mechanism to count the worst case # of pages required in a VM_BIND op. Note that previously we would have had to somehow account for allocations in unmap, when splitting a block. This behavior was removed in commit 33729a5fc0ca ("iommu/io-pgtable-arm: Remove split on unmap behavior)" Signed-off-by: Rob Clark Signed-off-by: Rob Clark Tested-by: Antonino Maniscalco Reviewed-by: Antonino Maniscalco --- drivers/gpu/drm/msm/msm_gem.h | 1 + drivers/gpu/drm/msm/msm_iommu.c | 191 +++++++++++++++++++++++++++++++- drivers/gpu/drm/msm/msm_mmu.h | 34 ++++++ 3 files changed, 225 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index af637409be39..f369a30a247c 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -7,6 +7,7 @@ #ifndef __MSM_GEM_H__ #define __MSM_GEM_H__ =20 +#include "msm_mmu.h" #include #include #include "drm/drm_exec.h" diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iomm= u.c index bd67431cb25f..887c9023f8a2 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -6,6 +6,7 @@ =20 #include #include +#include #include "msm_drv.h" #include "msm_mmu.h" =20 @@ -14,6 +15,8 @@ struct msm_iommu { struct iommu_domain *domain; atomic_t pagetables; struct page *prr_page; + + struct kmem_cache *pt_cache; }; =20 #define to_msm_iommu(x) container_of(x, struct msm_iommu, base) @@ -27,6 +30,9 @@ struct msm_iommu_pagetable { unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ phys_addr_t ttbr; u32 asid; + + /** @root_page_table: Stores the root page table pointer. */ + void *root_page_table; }; static struct msm_iommu_pagetable *to_pagetable(struct msm_mmu *mmu) { @@ -282,7 +288,145 @@ msm_iommu_pagetable_walk(struct msm_mmu *mmu, unsigne= d long iova, uint64_t ptes[ return 0; } =20 +static void +msm_iommu_pagetable_prealloc_count(struct msm_mmu *mmu, struct msm_mmu_pre= alloc *p, + uint64_t iova, size_t len) +{ + u64 pt_count; + + /* + * L1, L2 and L3 page tables. + * + * We could optimize L3 allocation by iterating over the sgt and merging + * 2M contiguous blocks, but it's simpler to over-provision and return + * the pages if they're not used. + * + * The first level descriptor (v8 / v7-lpae page table format) encodes + * 30 bits of address. The second level encodes 29. For the 3rd it is + * 39. + * + * https://developer.arm.com/documentation/ddi0406/c/System-Level-Archite= cture/Virtual-Memory-System-Architecture--VMSA-/Long-descriptor-translation= -table-format/Long-descriptor-translation-table-format-descriptors?lang=3De= n#BEIHEFFB + */ + pt_count =3D ((ALIGN(iova + len, 1ull << 39) - ALIGN_DOWN(iova, 1ull << 3= 9)) >> 39) + + ((ALIGN(iova + len, 1ull << 30) - ALIGN_DOWN(iova, 1ull << 30)) >> 30= ) + + ((ALIGN(iova + len, 1ull << 21) - ALIGN_DOWN(iova, 1ull << 21)) >> 21= ); + + p->count +=3D pt_count; +} + +static struct kmem_cache * +get_pt_cache(struct msm_mmu *mmu) +{ + struct msm_iommu_pagetable *pagetable =3D to_pagetable(mmu); + return to_msm_iommu(pagetable->parent)->pt_cache; +} + +static int +msm_iommu_pagetable_prealloc_allocate(struct msm_mmu *mmu, struct msm_mmu_= prealloc *p) +{ + struct kmem_cache *pt_cache =3D get_pt_cache(mmu); + int ret; + + p->pages =3D kvmalloc_array(p->count, sizeof(p->pages), GFP_KERNEL); + if (!p->pages) + return -ENOMEM; + + ret =3D kmem_cache_alloc_bulk(pt_cache, GFP_KERNEL, p->count, p->pages); + if (ret !=3D p->count) { + p->count =3D ret; + return -ENOMEM; + } + + return 0; +} + +static void +msm_iommu_pagetable_prealloc_cleanup(struct msm_mmu *mmu, struct msm_mmu_p= realloc *p) +{ + struct kmem_cache *pt_cache =3D get_pt_cache(mmu); + uint32_t remaining_pt_count =3D p->count - p->ptr; + + kmem_cache_free_bulk(pt_cache, remaining_pt_count, &p->pages[p->ptr]); + kvfree(p->pages); +} + +/** + * alloc_pt() - Custom page table allocator + * @cookie: Cookie passed at page table allocation time. + * @size: Size of the page table. This size should be fixed, + * and determined at creation time based on the granule size. + * @gfp: GFP flags. + * + * We want a custom allocator so we can use a cache for page table + * allocations and amortize the cost of the over-reservation that's + * done to allow asynchronous VM operations. + * + * Return: non-NULL on success, NULL if the allocation failed for any + * reason. + */ +static void * +msm_iommu_pagetable_alloc_pt(void *cookie, size_t size, gfp_t gfp) +{ + struct msm_iommu_pagetable *pagetable =3D cookie; + struct msm_mmu_prealloc *p =3D pagetable->base.prealloc; + void *page; + + /* Allocation of the root page table happening during init. */ + if (unlikely(!pagetable->root_page_table)) { + struct page *p; + + p =3D alloc_pages_node(dev_to_node(pagetable->iommu_dev), + gfp | __GFP_ZERO, get_order(size)); + page =3D p ? page_address(p) : NULL; + pagetable->root_page_table =3D page; + return page; + } + + if (WARN_ON(!p) || WARN_ON(p->ptr >=3D p->count)) + return NULL; + + page =3D p->pages[p->ptr++]; + memset(page, 0, size); + + /* + * Page table entries don't use virtual addresses, which trips out + * kmemleak. kmemleak_alloc_phys() might work, but physical addresses + * are mixed with other fields, and I fear kmemleak won't detect that + * either. + * + * Let's just ignore memory passed to the page-table driver for now. + */ + kmemleak_ignore(page); + + return page; +} + + +/** + * free_pt() - Custom page table free function + * @cookie: Cookie passed at page table allocation time. + * @data: Page table to free. + * @size: Size of the page table. This size should be fixed, + * and determined at creation time based on the granule size. + */ +static void +msm_iommu_pagetable_free_pt(void *cookie, void *data, size_t size) +{ + struct msm_iommu_pagetable *pagetable =3D cookie; + + if (unlikely(pagetable->root_page_table =3D=3D data)) { + free_pages((unsigned long)data, get_order(size)); + pagetable->root_page_table =3D NULL; + return; + } + + kmem_cache_free(get_pt_cache(&pagetable->base), data); +} + static const struct msm_mmu_funcs pagetable_funcs =3D { + .prealloc_count =3D msm_iommu_pagetable_prealloc_count, + .prealloc_allocate =3D msm_iommu_pagetable_prealloc_allocate, + .prealloc_cleanup =3D msm_iommu_pagetable_prealloc_cleanup, .map =3D msm_iommu_pagetable_map, .unmap =3D msm_iommu_pagetable_unmap, .destroy =3D msm_iommu_pagetable_destroy, @@ -333,6 +477,17 @@ static const struct iommu_flush_ops tlb_ops =3D { static int msm_gpu_fault_handler(struct iommu_domain *domain, struct devic= e *dev, unsigned long iova, int flags, void *arg); =20 +static size_t get_tblsz(const struct io_pgtable_cfg *cfg) +{ + int pg_shift, bits_per_level; + + pg_shift =3D __ffs(cfg->pgsize_bitmap); + /* arm_lpae_iopte is u64: */ + bits_per_level =3D pg_shift - ilog2(sizeof(u64)); + + return sizeof(u64) << bits_per_level; +} + struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent, bool ke= rnel_managed) { struct adreno_smmu_priv *adreno_smmu =3D dev_get_drvdata(parent->dev); @@ -369,8 +524,34 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_= mmu *parent, bool kernel_m =20 if (!kernel_managed) { ttbr0_cfg.quirks |=3D IO_PGTABLE_QUIRK_NO_WARN; + + /* + * With userspace managed VM (aka VM_BIND), we need to pre- + * allocate pages ahead of time for map/unmap operations, + * handing them to io-pgtable via custom alloc/free ops as + * needed: + */ + ttbr0_cfg.alloc =3D msm_iommu_pagetable_alloc_pt; + ttbr0_cfg.free =3D msm_iommu_pagetable_free_pt; + + /* + * Restrict to single page granules. Otherwise we may run + * into a situation where userspace wants to unmap/remap + * only a part of a larger block mapping, which is not + * possible without unmapping the entire block. Which in + * turn could cause faults if the GPU is accessing other + * parts of the block mapping. + * + * Note that prior to commit 33729a5fc0ca ("iommu/io-pgtable-arm: + * Remove split on unmap behavior)" this was handled in + * io-pgtable-arm. But this apparently does not work + * correctly on SMMUv3. + */ + WARN_ON(!(ttbr0_cfg.pgsize_bitmap & PAGE_SIZE)); + ttbr0_cfg.pgsize_bitmap =3D PAGE_SIZE; } =20 + pagetable->iommu_dev =3D ttbr1_cfg->iommu_dev; pagetable->pgtbl_ops =3D alloc_io_pgtable_ops(ARM_64_LPAE_S1, &ttbr0_cfg, pagetable); =20 @@ -414,7 +595,6 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_m= mu *parent, bool kernel_m /* Needed later for TLB flush */ pagetable->parent =3D parent; pagetable->tlb =3D ttbr1_cfg->tlb; - pagetable->iommu_dev =3D ttbr1_cfg->iommu_dev; pagetable->pgsize_bitmap =3D ttbr0_cfg.pgsize_bitmap; pagetable->ttbr =3D ttbr0_cfg.arm_lpae_s1_cfg.ttbr; =20 @@ -510,6 +690,7 @@ static void msm_iommu_destroy(struct msm_mmu *mmu) { struct msm_iommu *iommu =3D to_msm_iommu(mmu); iommu_domain_free(iommu->domain); + kmem_cache_destroy(iommu->pt_cache); kfree(iommu); } =20 @@ -583,6 +764,14 @@ struct msm_mmu *msm_iommu_gpu_new(struct device *dev, = struct msm_gpu *gpu, unsig return mmu; =20 iommu =3D to_msm_iommu(mmu); + if (adreno_smmu && adreno_smmu->cookie) { + const struct io_pgtable_cfg *cfg =3D + adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie); + size_t tblsz =3D get_tblsz(cfg); + + iommu->pt_cache =3D + kmem_cache_create("msm-mmu-pt", tblsz, tblsz, 0, NULL); + } iommu_set_fault_handler(iommu->domain, msm_gpu_fault_handler, iommu); =20 /* Enable stall on iommu fault: */ diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h index 04dce0faaa3a..8915662fbd4d 100644 --- a/drivers/gpu/drm/msm/msm_mmu.h +++ b/drivers/gpu/drm/msm/msm_mmu.h @@ -9,8 +9,16 @@ =20 #include =20 +struct msm_mmu_prealloc; +struct msm_mmu; +struct msm_gpu; + struct msm_mmu_funcs { void (*detach)(struct msm_mmu *mmu); + void (*prealloc_count)(struct msm_mmu *mmu, struct msm_mmu_prealloc *p, + uint64_t iova, size_t len); + int (*prealloc_allocate)(struct msm_mmu *mmu, struct msm_mmu_prealloc *p); + void (*prealloc_cleanup)(struct msm_mmu *mmu, struct msm_mmu_prealloc *p); int (*map)(struct msm_mmu *mmu, uint64_t iova, struct sg_table *sgt, size_t off, size_t len, int prot); int (*unmap)(struct msm_mmu *mmu, uint64_t iova, size_t len); @@ -24,12 +32,38 @@ enum msm_mmu_type { MSM_MMU_IOMMU_PAGETABLE, }; =20 +/** + * struct msm_mmu_prealloc - Tracking for pre-allocated pages for MMU upda= tes. + */ +struct msm_mmu_prealloc { + /** @count: Number of pages reserved. */ + uint32_t count; + /** @ptr: Index of first unused page in @pages */ + uint32_t ptr; + /** + * @pages: Array of pages preallocated for MMU table updates. + * + * After a VM operation, there might be free pages remaining in this + * array (since the amount allocated is a worst-case). These are + * returned to the pt_cache at mmu->prealloc_cleanup(). + */ + void **pages; +}; + struct msm_mmu { const struct msm_mmu_funcs *funcs; struct device *dev; int (*handler)(void *arg, unsigned long iova, int flags, void *data); void *arg; enum msm_mmu_type type; + + /** + * @prealloc: pre-allocated pages for pgtable + * + * Set while a VM_BIND job is running, serialized under + * msm_gem_vm::mmu_lock. + */ + struct msm_mmu_prealloc *prealloc; }; =20 static inline void msm_mmu_init(struct msm_mmu *mmu, struct device *dev, --=20 2.50.0