From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from out30-101.freemail.mail.aliyun.com (out30-101.freemail.mail.aliyun.com [115.124.30.101]) (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 3A77E450909; Tue, 28 Apr 2026 13:14:27 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.101 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1777382072; cv=none; b=EoBTU00Y+twYrBWJXg/VTfz1X8NLAzVpCocky6D1ncPSudhzt9hNo4EDWm2lllITqeXpn2pzxbC8LZyQKyAIyEgS3t2CJWLY7vgvO1oPg6FdszWxg1EgXo0ATRaDnJ9uUDzJfU5SH7iZBQgl0PMVkzoWj1Gu/MuyvFvAH+RRqHM= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1777382072; c=relaxed/simple; bh=T4H+/LpGeeu7kcTVvhLBYQ/XYxFHumzultQXItxHw80=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=cheod4NDrpQNO3M/yDctdRt5fNxOeXppNKTpkeAa1oR26/90amRyp5Fy+wHMXWRcNyREKE/81W+bpHPHsA6J9so04W/tSLbzc3Lmk3Eo6Pji10EooTeR/PjMs5qxmwSMghBYft3GoYYyOV+Il3boN9F6fmJKJyq6e0KegFOMscc= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com; spf=pass smtp.mailfrom=linux.alibaba.com; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b=ZfS8a9z3; arc=none smtp.client-ip=115.124.30.101 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b="ZfS8a9z3" DKIM-Signature:v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1777382065; h=From:To:Subject:Date:Message-Id:MIME-Version; bh=Qsv/5zq52oNQKyoYl2cE2fHq6XjpzP4W+zUJu/N+63k=; b=ZfS8a9z3NVCZNAyt8G5hcKma8DzaFJdle7Q0tFKRq/YsW6CnhcQPxILrS0pi+Oi+oTysQqfqOff6+P16h6y3zNHibMm9PwIb4sUmY6rWzfwGni93Nsiw3c/yJkoqrkgJ1cULnB+TMfmnvT2Gh4TI/cxDKs6AZc9DYa7yIMlfakk= X-Alimail-AntiSpam:AC=PASS;BC=-1|-1;BR=01201311R211e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=maildocker-contentspam011083073210;MF=fangyu.yu@linux.alibaba.com;NM=1;PH=DS;RN=23;SR=0;TI=SMTPD_---0X1ubIFt_1777382062; Received: from localhost.localdomain(mailfrom:fangyu.yu@linux.alibaba.com fp:SMTPD_---0X1ubIFt_1777382062 cluster:ay36) by smtp.aliyun-inc.com; Tue, 28 Apr 2026 21:14:23 +0800 From: fangyu.yu@linux.alibaba.com To: joro@8bytes.org, will@kernel.org, robin.murphy@arm.com, pjw@kernel.org, palmer@dabbelt.com, aou@eecs.berkeley.edu, alex@ghiti.fr, tjeznach@rivosinc.com, jgg@ziepe.ca, kevin.tian@intel.com, baolu.lu@linux.intel.com, vasant.hegde@amd.com, anup@brainfault.org, atish.patra@linux.dev, skhawaja@google.com, jgg@nvidia.com Cc: guoren@kernel.org, kvm@vger.kernel.org, iommu@lists.linux.dev, kvm-riscv@lists.infradead.org, linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org, Fangyu Yu Subject: [RFC PATCH 06/11] iommu/riscv: Add domain_alloc_paging_flags for second-stage domain Date: Tue, 28 Apr 2026 21:13:54 +0800 Message-Id: <20260428131359.34872-7-fangyu.yu@linux.alibaba.com> X-Mailer: git-send-email 2.39.3 (Apple Git-146) In-Reply-To: <20260428131359.34872-1-fangyu.yu@linux.alibaba.com> References: <20260428131359.34872-1-fangyu.yu@linux.alibaba.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit From: Fangyu Yu Replace .domain_alloc_paging with .domain_alloc_paging_flags so callers can pass allocation flags to select the appropriate page-table type. When IOMMU_HWPT_ALLOC_NEST_PARENT or IOMMU_HWPT_ALLOC_DIRTY_TRACKING is set in @flags, allocate a second-stage (iohgatp) domain. When @flags is 0 the behaviour is identical to the previous domain_alloc_paging: first-stage (iosatp) domain. Signed-off-by: Fangyu Yu --- drivers/iommu/riscv/iommu.c | 66 ++++++++++++++++++++++++++++--------- 1 file changed, 51 insertions(+), 15 deletions(-) diff --git a/drivers/iommu/riscv/iommu.c b/drivers/iommu/riscv/iommu.c index 5dadf6d09139..0c13430ecc7f 100644 --- a/drivers/iommu/riscv/iommu.c +++ b/drivers/iommu/riscv/iommu.c @@ -1255,23 +1255,50 @@ static const struct iommu_domain_ops riscv_iommu_paging_domain_ops = { .flush_iotlb_all = riscv_iommu_iotlb_flush_all, }; -static struct iommu_domain *riscv_iommu_alloc_paging_domain(struct device *dev) +static struct iommu_domain *riscv_iommu_domain_alloc_paging_flags( + struct device *dev, u32 flags, + const struct iommu_user_data *user_data) { + const bool second_stage = flags & + (IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING); struct pt_iommu_riscv_64_cfg cfg = {}; struct riscv_iommu_domain *domain; struct riscv_iommu_device *iommu; int ret; + if (user_data) + return ERR_PTR(-EOPNOTSUPP); + iommu = dev_to_iommu(dev); - if (iommu->caps & RISCV_IOMMU_CAPABILITIES_SV57) { - cfg.common.hw_max_vasz_lg2 = 57; - } else if (iommu->caps & RISCV_IOMMU_CAPABILITIES_SV48) { - cfg.common.hw_max_vasz_lg2 = 48; - } else if (iommu->caps & RISCV_IOMMU_CAPABILITIES_SV39) { - cfg.common.hw_max_vasz_lg2 = 39; + + if (second_stage) { + /* + * Second-stage (iohgatp) page table for KVM VFIO device + * pass-through and dirty tracking. The GPA space is 2 bits + * wider than the corresponding first-stage VA space (x4 root + * page table), so hw_max_vasz_lg2 values are 41/50/59. + */ + if (iommu->caps & RISCV_IOMMU_CAPABILITIES_SV57X4) { + cfg.common.hw_max_vasz_lg2 = 59; + } else if (iommu->caps & RISCV_IOMMU_CAPABILITIES_SV48X4) { + cfg.common.hw_max_vasz_lg2 = 50; + } else if (iommu->caps & RISCV_IOMMU_CAPABILITIES_SV39X4) { + cfg.common.hw_max_vasz_lg2 = 41; + } else { + dev_err(dev, "cannot find supported second-stage page table mode\n"); + return ERR_PTR(-ENODEV); + } } else { - dev_err(dev, "cannot find supported page table mode\n"); - return ERR_PTR(-ENODEV); + if (iommu->caps & RISCV_IOMMU_CAPABILITIES_SV57) { + cfg.common.hw_max_vasz_lg2 = 57; + } else if (iommu->caps & RISCV_IOMMU_CAPABILITIES_SV48) { + cfg.common.hw_max_vasz_lg2 = 48; + } else if (iommu->caps & RISCV_IOMMU_CAPABILITIES_SV39) { + cfg.common.hw_max_vasz_lg2 = 39; + } else { + dev_err(dev, "cannot find supported page table mode\n"); + return ERR_PTR(-ENODEV); + } } cfg.common.hw_max_oasz_lg2 = 56; @@ -1291,11 +1318,20 @@ static struct iommu_domain *riscv_iommu_alloc_paging_domain(struct device *dev) domain->riscvpt.iommu.nid = dev_to_node(iommu->dev); domain->domain.ops = &riscv_iommu_paging_domain_ops; - domain->pscid = ida_alloc_range(&riscv_iommu_pscids, 1, - RISCV_IOMMU_MAX_PSCID, GFP_KERNEL); - if (domain->pscid < 0) { - riscv_iommu_free_paging_domain(&domain->domain); - return ERR_PTR(-ENOMEM); + if (second_stage) { + domain->gscid = ida_alloc_range(&riscv_iommu_gscids, 1, + RISCV_IOMMU_MAX_GSCID, GFP_KERNEL); + if (domain->gscid < 0) { + riscv_iommu_free_paging_domain(&domain->domain); + return ERR_PTR(-ENOMEM); + } + } else { + domain->pscid = ida_alloc_range(&riscv_iommu_pscids, 1, + RISCV_IOMMU_MAX_PSCID, GFP_KERNEL); + if (domain->pscid < 0) { + riscv_iommu_free_paging_domain(&domain->domain); + return ERR_PTR(-ENOMEM); + } } ret = pt_iommu_riscv_64_init(&domain->riscvpt, &cfg, GFP_KERNEL); @@ -1439,7 +1475,7 @@ static const struct iommu_ops riscv_iommu_ops = { .identity_domain = &riscv_iommu_identity_domain, .blocked_domain = &riscv_iommu_blocking_domain, .release_domain = &riscv_iommu_blocking_domain, - .domain_alloc_paging = riscv_iommu_alloc_paging_domain, + .domain_alloc_paging_flags = riscv_iommu_domain_alloc_paging_flags, .device_group = riscv_iommu_device_group, .probe_device = riscv_iommu_probe_device, .release_device = riscv_iommu_release_device, -- 2.50.1