From nobody Sun Apr 28 23:04:51 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id DF78DC7EE2D for ; Fri, 2 Jun 2023 18:17:50 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237040AbjFBSRt (ORCPT ); Fri, 2 Jun 2023 14:17:49 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:36998 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S235298AbjFBSRn (ORCPT ); Fri, 2 Jun 2023 14:17:43 -0400 Received: from mga05.intel.com (mga05.intel.com [192.55.52.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id CE313197; Fri, 2 Jun 2023 11:17:38 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685729858; x=1717265858; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=3FVtuc/IjJgA/TQjAer/Ui08hmWExZQThjvT0VtpwAU=; b=c5t+JsZJdQFgxtJV0Qo2D3FT8affeJD0+m8JMG45NrP6/dF9jMVSBdUR KeTcpR6njCSY4q5ATq0v7lLWbGJD5/JxOkSe/NBBEinsvJYpyd3TU/L6n 3V9+itIB8UzHuPxCsdZ7eSbE83D0k7PWDoBMR6D3yVslBr6h6cUMhvhiB HRfwD7+Ygqg+sA8T8sZObdXwEQPKKQixq1Z3wODECqtKct+634uup/9C5 BrijoYKypYj6PKNtjULNyKwfEBIhrkg/+TXs4if9W3+qr0j7zaWb/Lw1+ bftHNi+w0jdeTGQuYTzHUYnxKX9rL8FFQgk27M0NxjiTWQEzFhZBzXUqF g==; X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="442310213" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="442310213" Received: from orsmga004.jf.intel.com ([10.7.209.38]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 02 Jun 2023 11:17:38 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="832060958" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="832060958" Received: from srinivas-otcpl-7600.jf.intel.com (HELO jacob-builder.jf.intel.com) ([10.54.97.184]) by orsmga004.jf.intel.com with ESMTP; 02 Jun 2023 11:17:37 -0700 From: Jacob Pan To: LKML , iommu@lists.linux.dev, Jason Gunthorpe , "Lu Baolu" , Joerg Roedel , "Robin Murphy" , Jean-Philippe Brucker , dmaengine@vger.kernel.org, vkoul@kernel.org Cc: "Will Deacon" , David Woodhouse , Raj Ashok , "Tian, Kevin" , Yi Liu , "Yu, Fenghua" , Dave Jiang , Tony Luck , "Zanussi, Tom" , rex.zhang@intel.com, xiaochen.shen@intel.com, narayan.ranganathan@intel.com, Jacob Pan , Jean-Philippe Brucker Subject: [PATCH v8 1/7] iommu: Generalize PASID 0 for normal DMA w/o PASID Date: Fri, 2 Jun 2023 11:22:06 -0700 Message-Id: <20230602182212.150825-2-jacob.jun.pan@linux.intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> References: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" PCIe Process address space ID (PASID) is used to tag DMA traffic, it provides finer grained isolation than requester ID (RID). For each device/RID, 0 is a special PASID for the normal DMA (no PASID). This is universal across all architectures that supports PASID, therefore warranted to be reserved globally and declared in the common header. Consequently, we can avoid the conflict between different PASID use cases in the generic code. e.g. SVA and DMA API with PASIDs. This paved away for device drivers to choose global PASID policy while continue doing normal DMA. Noting that VT-d could support none-zero RID/NO_PASID, but currently not used. Reviewed-by: Lu Baolu Reviewed-by: Kevin Tian Reviewed-by: Jean-Philippe Brucker Signed-off-by: Jacob Pan --- v8: - make consistent use of NO_PASID in SMMU code - remove PASID_MIN v7: - renamed IOMMU_DEF_RID_PASID to be IOMMU_NO_PASID to be more generic v6: - let SMMU code use the common RID_PASID macro --- .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 16 ++++++------- drivers/iommu/intel/iommu.c | 24 +++++++++---------- drivers/iommu/intel/pasid.c | 2 +- drivers/iommu/intel/pasid.h | 2 -- include/linux/iommu.h | 1 + 6 files changed, 23 insertions(+), 24 deletions(-) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iomm= u/arm/arm-smmu-v3/arm-smmu-v3-sva.c index a5a63b1c947e..5e6b39881c04 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -80,7 +80,7 @@ arm_smmu_share_asid(struct mm_struct *mm, u16 asid) * be some overlap between use of both ASIDs, until we invalidate the * TLB. */ - arm_smmu_write_ctx_desc(smmu_domain, 0, cd); + arm_smmu_write_ctx_desc(smmu_domain, IOMMU_NO_PASID, cd); =20 /* Invalidate TLB entries previously associated with that context */ arm_smmu_tlb_inv_asid(smmu, asid); diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/ar= m/arm-smmu-v3/arm-smmu-v3.c index 3fd83fb75722..c97710635796 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -1053,7 +1053,7 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *s= mmu_domain, int ssid, /* * This function handles the following cases: * - * (1) Install primary CD, for normal DMA traffic (SSID =3D 0). + * (1) Install primary CD, for normal DMA traffic (SSID =3D IOMMU_NO_PASI= D =3D 0). * (2) Install a secondary CD, for SID+SSID traffic. * (3) Update ASID of a CD. Atomically write the first 64 bits of the * CD, then invalidate the old entry and mappings. @@ -1601,7 +1601,7 @@ static void arm_smmu_handle_ppr(struct arm_smmu_devic= e *smmu, u64 *evt) =20 sid =3D FIELD_GET(PRIQ_0_SID, evt[0]); ssv =3D FIELD_GET(PRIQ_0_SSID_V, evt[0]); - ssid =3D ssv ? FIELD_GET(PRIQ_0_SSID, evt[0]) : 0; + ssid =3D ssv ? FIELD_GET(PRIQ_0_SSID, evt[0]) : IOMMU_NO_PASID; last =3D FIELD_GET(PRIQ_0_PRG_LAST, evt[0]); grpid =3D FIELD_GET(PRIQ_1_PRG_IDX, evt[1]); =20 @@ -1742,7 +1742,7 @@ arm_smmu_atc_inv_to_cmd(int ssid, unsigned long iova,= size_t size, */ *cmd =3D (struct arm_smmu_cmdq_ent) { .opcode =3D CMDQ_OP_ATC_INV, - .substream_valid =3D !!ssid, + .substream_valid =3D (ssid !=3D IOMMU_NO_PASID), .atc.ssid =3D ssid, }; =20 @@ -1789,7 +1789,7 @@ static int arm_smmu_atc_inv_master(struct arm_smmu_ma= ster *master) struct arm_smmu_cmdq_ent cmd; struct arm_smmu_cmdq_batch cmds; =20 - arm_smmu_atc_inv_to_cmd(0, 0, 0, &cmd); + arm_smmu_atc_inv_to_cmd(IOMMU_NO_PASID, 0, 0, &cmd); =20 cmds.num =3D 0; for (i =3D 0; i < master->num_streams; i++) { @@ -1869,7 +1869,7 @@ static void arm_smmu_tlb_inv_context(void *cookie) cmd.tlbi.vmid =3D smmu_domain->s2_cfg.vmid; arm_smmu_cmdq_issue_cmd_with_sync(smmu, &cmd); } - arm_smmu_atc_inv_domain(smmu_domain, 0, 0, 0); + arm_smmu_atc_inv_domain(smmu_domain, IOMMU_NO_PASID, 0, 0); } =20 static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd, @@ -1957,7 +1957,7 @@ static void arm_smmu_tlb_inv_range_domain(unsigned lo= ng iova, size_t size, * Unfortunately, this can't be leaf-only since we may have * zapped an entire table. */ - arm_smmu_atc_inv_domain(smmu_domain, 0, iova, size); + arm_smmu_atc_inv_domain(smmu_domain, IOMMU_NO_PASID, iova, size); } =20 void arm_smmu_tlb_inv_range_asid(unsigned long iova, size_t size, int asid, @@ -2131,7 +2131,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smm= u_domain *smmu_domain, * the master has been added to the devices list for this domain. * This isn't an issue because the STE hasn't been installed yet. */ - ret =3D arm_smmu_write_ctx_desc(smmu_domain, 0, &cfg->cd); + ret =3D arm_smmu_write_ctx_desc(smmu_domain, IOMMU_NO_PASID, &cfg->cd); if (ret) goto out_free_cd_tables; =20 @@ -2317,7 +2317,7 @@ static void arm_smmu_enable_ats(struct arm_smmu_maste= r *master) pdev =3D to_pci_dev(master->dev); =20 atomic_inc(&smmu_domain->nr_ats_masters); - arm_smmu_atc_inv_domain(smmu_domain, 0, 0, 0); + arm_smmu_atc_inv_domain(smmu_domain, IOMMU_NO_PASID, 0, 0); if (pci_enable_ats(pdev, stu)) dev_err(master->dev, "Failed to enable ATS (STU %zu)\n", stu); } diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index b871a6afd803..4eba9973f537 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -877,7 +877,7 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u1= 6 source_id, } /* For request-without-pasid, get the pasid from context entry */ if (intel_iommu_sm && pasid =3D=3D IOMMU_PASID_INVALID) - pasid =3D PASID_RID2PASID; + pasid =3D IOMMU_NO_PASID; =20 dir_index =3D pasid >> PASID_PDE_SHIFT; pde =3D &dir[dir_index]; @@ -1457,7 +1457,7 @@ static void __iommu_flush_dev_iotlb(struct device_dom= ain_info *info, qdep =3D info->ats_qdep; qi_flush_dev_iotlb(info->iommu, sid, info->pfsid, qdep, addr, mask); - quirk_extra_dev_tlb_flush(info, addr, mask, PASID_RID2PASID, qdep); + quirk_extra_dev_tlb_flush(info, addr, mask, IOMMU_NO_PASID, qdep); } =20 static void iommu_flush_dev_iotlb(struct dmar_domain *domain, @@ -1492,7 +1492,7 @@ static void iommu_flush_iotlb_psi(struct intel_iommu = *iommu, ih =3D 1 << 6; =20 if (domain->use_first_level) { - qi_flush_piotlb(iommu, did, PASID_RID2PASID, addr, pages, ih); + qi_flush_piotlb(iommu, did, IOMMU_NO_PASID, addr, pages, ih); } else { unsigned long bitmask =3D aligned_pages - 1; =20 @@ -1562,7 +1562,7 @@ static void intel_flush_iotlb_all(struct iommu_domain= *domain) u16 did =3D domain_id_iommu(dmar_domain, iommu); =20 if (dmar_domain->use_first_level) - qi_flush_piotlb(iommu, did, PASID_RID2PASID, 0, -1, 0); + qi_flush_piotlb(iommu, did, IOMMU_NO_PASID, 0, -1, 0); else iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH); @@ -1952,7 +1952,7 @@ static int domain_context_mapping_one(struct dmar_dom= ain *domain, context_pdts(pds); =20 /* Setup the RID_PASID field: */ - context_set_sm_rid2pasid(context, PASID_RID2PASID); + context_set_sm_rid2pasid(context, IOMMU_NO_PASID); =20 /* * Setup the Device-TLB enable bit and Page request @@ -2432,13 +2432,13 @@ static int dmar_domain_attach_device(struct dmar_do= main *domain, /* Setup the PASID entry for requests without PASID: */ if (hw_pass_through && domain_type_is_si(domain)) ret =3D intel_pasid_setup_pass_through(iommu, domain, - dev, PASID_RID2PASID); + dev, IOMMU_NO_PASID); else if (domain->use_first_level) ret =3D domain_setup_first_level(iommu, domain, dev, - PASID_RID2PASID); + IOMMU_NO_PASID); else ret =3D intel_pasid_setup_second_level(iommu, domain, - dev, PASID_RID2PASID); + dev, IOMMU_NO_PASID); if (ret) { dev_err(dev, "Setup RID2PASID failed\n"); device_block_translation(dev); @@ -3975,7 +3975,7 @@ static void dmar_remove_one_dev_info(struct device *d= ev) if (!dev_is_real_dma_subdevice(info->dev)) { if (dev_is_pci(info->dev) && sm_supported(iommu)) intel_pasid_tear_down_entry(iommu, info->dev, - PASID_RID2PASID, false); + IOMMU_NO_PASID, false); =20 iommu_disable_pci_caps(info); domain_context_clear(info); @@ -4004,7 +4004,7 @@ static void device_block_translation(struct device *d= ev) if (!dev_is_real_dma_subdevice(dev)) { if (sm_supported(iommu)) intel_pasid_tear_down_entry(iommu, dev, - PASID_RID2PASID, false); + IOMMU_NO_PASID, false); else domain_context_clear(info); } @@ -4339,7 +4339,7 @@ static void domain_set_force_snooping(struct dmar_dom= ain *domain) =20 list_for_each_entry(info, &domain->devices, link) intel_pasid_setup_page_snoop_control(info->iommu, info->dev, - PASID_RID2PASID); + IOMMU_NO_PASID); } =20 static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domai= n) @@ -4994,7 +4994,7 @@ void quirk_extra_dev_tlb_flush(struct device_domain_i= nfo *info, return; =20 sid =3D PCI_DEVID(info->bus, info->devfn); - if (pasid =3D=3D PASID_RID2PASID) { + if (pasid =3D=3D IOMMU_NO_PASID) { qi_flush_dev_iotlb(info->iommu, sid, info->pfsid, qdep, address, mask); } else { diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index c5d479770e12..23dca3bc319d 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -438,7 +438,7 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iomm= u, * SVA usage, device could do DMA with multiple PASIDs. It is more * efficient to flush devTLB specific to the PASID. */ - if (pasid =3D=3D PASID_RID2PASID) + if (pasid =3D=3D IOMMU_NO_PASID) qi_flush_dev_iotlb(iommu, sid, pfsid, qdep, 0, 64 - VTD_PAGE_SHIFT); else qi_flush_dev_iotlb_pasid(iommu, sid, pfsid, pasid, qdep, 0, 64 - VTD_PAG= E_SHIFT); diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index d6b7d21244b1..4e9e68c3c388 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -10,8 +10,6 @@ #ifndef __INTEL_PASID_H #define __INTEL_PASID_H =20 -#define PASID_RID2PASID 0x0 -#define PASID_MIN 0x1 #define PASID_MAX 0x100000 #define PASID_PTE_MASK 0x3F #define PASID_PTE_PRESENT 1 diff --git a/include/linux/iommu.h b/include/linux/iommu.h index e8c9a7da1060..c714d659d114 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -190,6 +190,7 @@ enum iommu_dev_features { IOMMU_DEV_FEAT_IOPF, }; =20 +#define IOMMU_NO_PASID (0U) /* Reserved for DMA w/o PASID */ #define IOMMU_PASID_INVALID (-1U) typedef unsigned int ioasid_t; =20 --=20 2.25.1 From nobody Sun Apr 28 23:04:51 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 57069C7EE24 for ; Fri, 2 Jun 2023 18:17:54 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237050AbjFBSRw (ORCPT ); Fri, 2 Jun 2023 14:17:52 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:37000 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S235858AbjFBSRn (ORCPT ); Fri, 2 Jun 2023 14:17:43 -0400 Received: from mga05.intel.com (mga05.intel.com [192.55.52.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 6879619A; Fri, 2 Jun 2023 11:17:40 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685729860; x=1717265860; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=4ZLNWA9lbj3RPDCkZaIcBniRXsCD3rLw+gS6G1GEZhI=; b=iaca2IvsW+u2IAnXC93CwxTDmpd+bfgBIDFkt6yoYqFlxQi+5EZLYvf0 MDlg4qzanditIMBiIPgj/kiPHTyuk83kqtXPGUCcnWXMrkHKhFjlU5okn xez5B475Z5DZOhCU29If6UaYPPahMWeeIRrEJ8OXb5yM/22xSx1apkGC6 hEjPYRTFpBjvlouhJB1GpaF06PEH7vq39r47POnRcl8Z5j0MopxPIi4xL pTsU+Opgvl6KrBZCDlEZvq/9FiDSnT8G6Pwi2ZlBrLs0B7FJ2hbb2BQ3H Rsle0wDo8NPa5fRQh+gkvM2tRMwwBCsfF7gaxXUTJ0Zed795YFCgcc9Nn w==; X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="442310223" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="442310223" Received: from orsmga004.jf.intel.com ([10.7.209.38]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 02 Jun 2023 11:17:38 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="832060961" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="832060961" Received: from srinivas-otcpl-7600.jf.intel.com (HELO jacob-builder.jf.intel.com) ([10.54.97.184]) by orsmga004.jf.intel.com with ESMTP; 02 Jun 2023 11:17:38 -0700 From: Jacob Pan To: LKML , iommu@lists.linux.dev, Jason Gunthorpe , "Lu Baolu" , Joerg Roedel , "Robin Murphy" , Jean-Philippe Brucker , dmaengine@vger.kernel.org, vkoul@kernel.org Cc: "Will Deacon" , David Woodhouse , Raj Ashok , "Tian, Kevin" , Yi Liu , "Yu, Fenghua" , Dave Jiang , Tony Luck , "Zanussi, Tom" , rex.zhang@intel.com, xiaochen.shen@intel.com, narayan.ranganathan@intel.com, Jacob Pan Subject: [PATCH v8 2/7] iommu: Move global PASID allocation from SVA to core Date: Fri, 2 Jun 2023 11:22:07 -0700 Message-Id: <20230602182212.150825-3-jacob.jun.pan@linux.intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> References: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Global PASID can be used beyond SVA. For example, drivers that use Intel ENQCMD to submit work must use global PASIDs in that PASID is stored in a per CPU MSR. When such device need to submit work for in-kernel DMA with PASID, it must allocate PASIDs from the same global number space to avoid conflict. This patch moves global PASID allocation APIs from SVA to IOMMU APIs. Reserved PASIDs, currently only RID_PASID, are excluded from the global PASID allocation. It is expected that device drivers will use the allocated PASIDs to attach to appropriate IOMMU domains for use. Reviewed-by: Lu Baolu Reviewed-by: Kevin Tian Signed-off-by: Jacob Pan --- v8: fix off-by-one in max_pasid check v7: simplify range check (Baolu) v6: explicitly exclude reserved a range from SVA PASID allocation check mm PASID compatibility with device v5: move PASID range check inside API so that device drivers only pass in struct device* (Kevin) v4: move dummy functions outside ifdef CONFIG_IOMMU_SVA (Baolu) --- drivers/iommu/iommu-sva.c | 28 ++++++++++------------------ drivers/iommu/iommu.c | 28 ++++++++++++++++++++++++++++ include/linux/iommu.h | 10 ++++++++++ 3 files changed, 48 insertions(+), 18 deletions(-) diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index 9821bc44f5ac..b033cc415a00 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -10,33 +10,30 @@ #include "iommu-sva.h" =20 static DEFINE_MUTEX(iommu_sva_lock); -static DEFINE_IDA(iommu_global_pasid_ida); =20 /* Allocate a PASID for the mm within range (inclusive) */ -static int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasi= d_t max) +static int iommu_sva_alloc_pasid(struct mm_struct *mm, struct device *dev) { + ioasid_t pasid; int ret =3D 0; =20 - if (min =3D=3D IOMMU_PASID_INVALID || - max =3D=3D IOMMU_PASID_INVALID || - min =3D=3D 0 || max < min) - return -EINVAL; - if (!arch_pgtable_dma_compat(mm)) return -EBUSY; =20 mutex_lock(&iommu_sva_lock); /* Is a PASID already associated with this mm? */ if (mm_valid_pasid(mm)) { - if (mm->pasid < min || mm->pasid > max) + if (mm->pasid >=3D dev->iommu->max_pasids) ret =3D -EOVERFLOW; goto out; } =20 - ret =3D ida_alloc_range(&iommu_global_pasid_ida, min, max, GFP_KERNEL); - if (ret < min) + pasid =3D iommu_alloc_global_pasid_dev(dev); + if (pasid =3D=3D IOMMU_PASID_INVALID) { + ret =3D -ENOSPC; goto out; - mm->pasid =3D ret; + } + mm->pasid =3D pasid; ret =3D 0; out: mutex_unlock(&iommu_sva_lock); @@ -63,15 +60,10 @@ struct iommu_sva *iommu_sva_bind_device(struct device *= dev, struct mm_struct *mm { struct iommu_domain *domain; struct iommu_sva *handle; - ioasid_t max_pasids; int ret; =20 - max_pasids =3D dev->iommu->max_pasids; - if (!max_pasids) - return ERR_PTR(-EOPNOTSUPP); - /* Allocate mm->pasid if necessary. */ - ret =3D iommu_sva_alloc_pasid(mm, 1, max_pasids - 1); + ret =3D iommu_sva_alloc_pasid(mm, dev); if (ret) return ERR_PTR(ret); =20 @@ -216,5 +208,5 @@ void mm_pasid_drop(struct mm_struct *mm) if (likely(!mm_valid_pasid(mm))) return; =20 - ida_free(&iommu_global_pasid_ida, mm->pasid); + iommu_free_global_pasid(mm->pasid); } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index f1dcfa3f1a1b..d4f9ab210d6b 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -39,6 +39,7 @@ =20 static struct kset *iommu_group_kset; static DEFINE_IDA(iommu_group_ida); +static DEFINE_IDA(iommu_global_pasid_ida); =20 static unsigned int iommu_def_domain_type __read_mostly; static bool iommu_dma_strict __read_mostly =3D IS_ENABLED(CONFIG_IOMMU_DEF= AULT_DMA_STRICT); @@ -3393,3 +3394,30 @@ struct iommu_domain *iommu_sva_domain_alloc(struct d= evice *dev, =20 return domain; } + +ioasid_t iommu_alloc_global_pasid_dev(struct device *dev) +{ + int ret; + ioasid_t max; + + max =3D dev->iommu->max_pasids; + /* + * max_pasids is set up by vendor driver based on number of PASID bits + * supported but the IDA allocation is inclusive. + */ + ret =3D ida_alloc_range(&iommu_global_pasid_ida, IOMMU_FIRST_GLOBAL_PASID= , max - 1, GFP_KERNEL); + if (ret < 0) + return IOMMU_PASID_INVALID; + + return ret; +} +EXPORT_SYMBOL_GPL(iommu_alloc_global_pasid_dev); + +void iommu_free_global_pasid(ioasid_t pasid) +{ + if (WARN_ON(pasid =3D=3D IOMMU_PASID_INVALID)) + return; + + ida_free(&iommu_global_pasid_ida, pasid); +} +EXPORT_SYMBOL_GPL(iommu_free_global_pasid); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index c714d659d114..f7bfe03bda19 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -191,6 +191,7 @@ enum iommu_dev_features { }; =20 #define IOMMU_NO_PASID (0U) /* Reserved for DMA w/o PASID */ +#define IOMMU_FIRST_GLOBAL_PASID (1U) /*starting range for allocation */ #define IOMMU_PASID_INVALID (-1U) typedef unsigned int ioasid_t; =20 @@ -722,6 +723,8 @@ void iommu_detach_device_pasid(struct iommu_domain *dom= ain, struct iommu_domain * iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid, unsigned int type); +ioasid_t iommu_alloc_global_pasid_dev(struct device *dev); +void iommu_free_global_pasid(ioasid_t pasid); #else /* CONFIG_IOMMU_API */ =20 struct iommu_ops {}; @@ -1083,6 +1086,13 @@ iommu_get_domain_for_dev_pasid(struct device *dev, i= oasid_t pasid, { return NULL; } + +static inline ioasid_t iommu_alloc_global_pasid_dev(struct device *dev) +{ + return IOMMU_PASID_INVALID; +} + +static inline void iommu_free_global_pasid(ioasid_t pasid) {} #endif /* CONFIG_IOMMU_API */ =20 /** --=20 2.25.1 From nobody Sun Apr 28 23:04:51 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id AA9CAC7EE24 for ; Fri, 2 Jun 2023 18:17:57 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237056AbjFBSRz (ORCPT ); Fri, 2 Jun 2023 14:17:55 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:37012 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S236869AbjFBSRo (ORCPT ); Fri, 2 Jun 2023 14:17:44 -0400 Received: from mga05.intel.com (mga05.intel.com [192.55.52.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id B4955123; Fri, 2 Jun 2023 11:17:42 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685729862; x=1717265862; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=4p3zIDhXUsEFoA0tsNg8+G8DCi8YsUnHZ4JrFrt/SXY=; b=ewvxt5VBrpIzcm4zCFYiMBj75RhX/OO/w11Tm/R0ZpzkzuiyuGoKkqVc YEQJIGkIYPI6TapJ5/3rVPvD7C/OPami4TIR+L1tVaBUyOtl/kmiSkMt6 L8I9D8yTJq5fStUSa1nh3gtfPfkLTXrsanF+mLau4nrBJ+f1sFp08BnZ/ IwrglVoJV51Ibuh5qdEY9Pr8DgjoWgmI2+M5opuzew1Qy4RAy1wPzUNx6 F94AwSuScxRs/m8QDQom3KvZ2ClH6iSJpvch9b5loE2cAuCejjLzGvARj ZMg6+V2c/ZJRds/JRJcnbOotlnxgT8084H+O8GdUODOSzKrRK/IYVyKUx w==; X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="442310232" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="442310232" Received: from orsmga004.jf.intel.com ([10.7.209.38]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 02 Jun 2023 11:17:38 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="832060965" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="832060965" Received: from srinivas-otcpl-7600.jf.intel.com (HELO jacob-builder.jf.intel.com) ([10.54.97.184]) by orsmga004.jf.intel.com with ESMTP; 02 Jun 2023 11:17:38 -0700 From: Jacob Pan To: LKML , iommu@lists.linux.dev, Jason Gunthorpe , "Lu Baolu" , Joerg Roedel , "Robin Murphy" , Jean-Philippe Brucker , dmaengine@vger.kernel.org, vkoul@kernel.org Cc: "Will Deacon" , David Woodhouse , Raj Ashok , "Tian, Kevin" , Yi Liu , "Yu, Fenghua" , Dave Jiang , Tony Luck , "Zanussi, Tom" , rex.zhang@intel.com, xiaochen.shen@intel.com, narayan.ranganathan@intel.com, Jacob Pan Subject: [PATCH v8 3/7] iommu/vt-d: Add domain_flush_pasid_iotlb() Date: Fri, 2 Jun 2023 11:22:08 -0700 Message-Id: <20230602182212.150825-4-jacob.jun.pan@linux.intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> References: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" From: Lu Baolu The VT-d spec requires to use PASID-based-IOTLB invalidation descriptor to invalidate IOTLB and the paging-structure caches for a first-stage page table. Add a generic helper to do this. RID2PASID is used if the domain has been attached to a physical device, otherwise real PASIDs that the domain has been attached to will be used. Signed-off-by: Lu Baolu Signed-off-by: Jacob Pan Reviewed-by: Kevin Tian --- drivers/iommu/intel/iommu.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 4eba9973f537..3214990b69b7 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1475,6 +1475,24 @@ static void iommu_flush_dev_iotlb(struct dmar_domain= *domain, spin_unlock_irqrestore(&domain->lock, flags); } =20 +/* + * The VT-d spec requires to use PASID-based-IOTLB Invalidation to + * invalidate IOTLB and the paging-structure-caches for a first-stage + * page table. + */ +static void domain_flush_pasid_iotlb(struct intel_iommu *iommu, + struct dmar_domain *domain, u64 addr, + unsigned long npages, bool ih) +{ + u16 did =3D domain_id_iommu(domain, iommu); + unsigned long flags; + + spin_lock_irqsave(&domain->lock, flags); + if (!list_empty(&domain->devices)) + qi_flush_piotlb(iommu, did, IOMMU_NO_PASID, addr, npages, ih); + spin_unlock_irqrestore(&domain->lock, flags); +} + static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, struct dmar_domain *domain, unsigned long pfn, unsigned int pages, @@ -1492,7 +1510,7 @@ static void iommu_flush_iotlb_psi(struct intel_iommu = *iommu, ih =3D 1 << 6; =20 if (domain->use_first_level) { - qi_flush_piotlb(iommu, did, IOMMU_NO_PASID, addr, pages, ih); + domain_flush_pasid_iotlb(iommu, domain, addr, pages, ih); } else { unsigned long bitmask =3D aligned_pages - 1; =20 @@ -1562,7 +1580,7 @@ static void intel_flush_iotlb_all(struct iommu_domain= *domain) u16 did =3D domain_id_iommu(dmar_domain, iommu); =20 if (dmar_domain->use_first_level) - qi_flush_piotlb(iommu, did, IOMMU_NO_PASID, 0, -1, 0); + domain_flush_pasid_iotlb(iommu, dmar_domain, 0, -1, 0); else iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH); --=20 2.25.1 From nobody Sun Apr 28 23:04:51 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id C774FC7EE24 for ; Fri, 2 Jun 2023 18:18:04 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S235994AbjFBSSD (ORCPT ); Fri, 2 Jun 2023 14:18:03 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:37012 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S236650AbjFBSRp (ORCPT ); Fri, 2 Jun 2023 14:17:45 -0400 Received: from mga05.intel.com (mga05.intel.com [192.55.52.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id B248C196; Fri, 2 Jun 2023 11:17:43 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685729863; x=1717265863; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=mm0RBRlxNTWUVWGSjZmJqXmc9M/wdroaapVIA3ESeqk=; b=D4kq+b1VRziy0PKQ04jgIDM2PuZ+qDqnw3jKCl6yKcwLXynHw8rkyUTj bKzWoPAu7z6NIP1SUnp/b3y45ggwAKwEOrrTbYcEm1MfVUkDb2TkFOFzq M72mlTClM83srvsSQ7musGEdySgU/h65zUXpnPDK53IoTolfT5St7V/5e /Mfs9cymgWk6I8UiBUyQ1cMbZP8wfTG5e9xM2YJbKij/z/5lnYl66J0ks yV72wlzmUoifFfR67b70sD4dMYupPSkeNqj/LnlAYQEEAKOPiH7WIwatM mDpMbej2zVSjxIZ3wTvCyFS2DKe9IsED++CHTaeA5apYuJFIL1SD69mDo Q==; X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="442310244" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="442310244" Received: from orsmga004.jf.intel.com ([10.7.209.38]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 02 Jun 2023 11:17:39 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="832060968" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="832060968" Received: from srinivas-otcpl-7600.jf.intel.com (HELO jacob-builder.jf.intel.com) ([10.54.97.184]) by orsmga004.jf.intel.com with ESMTP; 02 Jun 2023 11:17:38 -0700 From: Jacob Pan To: LKML , iommu@lists.linux.dev, Jason Gunthorpe , "Lu Baolu" , Joerg Roedel , "Robin Murphy" , Jean-Philippe Brucker , dmaengine@vger.kernel.org, vkoul@kernel.org Cc: "Will Deacon" , David Woodhouse , Raj Ashok , "Tian, Kevin" , Yi Liu , "Yu, Fenghua" , Dave Jiang , Tony Luck , "Zanussi, Tom" , rex.zhang@intel.com, xiaochen.shen@intel.com, narayan.ranganathan@intel.com, Jacob Pan Subject: [PATCH v8 4/7] iommu/vt-d: Remove pasid_mutex Date: Fri, 2 Jun 2023 11:22:09 -0700 Message-Id: <20230602182212.150825-5-jacob.jun.pan@linux.intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> References: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" From: Lu Baolu The pasid_mutex was used to protect the paths of set/remove_dev_pasid(). It's duplicate with iommu_sva_lock. Remove it to avoid duplicate code. Reviewed-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian --- drivers/iommu/intel/svm.c | 45 +++++---------------------------------- 1 file changed, 5 insertions(+), 40 deletions(-) diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index e95b339e9cdc..2a82864e9d57 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -259,8 +259,6 @@ static const struct mmu_notifier_ops intel_mmuops =3D { .invalidate_range =3D intel_invalidate_range, }; =20 -static DEFINE_MUTEX(pasid_mutex); - static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid, struct intel_svm **rsvm, struct intel_svm_dev **rsdev) @@ -268,10 +266,6 @@ static int pasid_to_svm_sdev(struct device *dev, unsig= ned int pasid, struct intel_svm_dev *sdev =3D NULL; struct intel_svm *svm; =20 - /* The caller should hold the pasid_mutex lock */ - if (WARN_ON(!mutex_is_locked(&pasid_mutex))) - return -EINVAL; - if (pasid =3D=3D IOMMU_PASID_INVALID || pasid >=3D PASID_MAX) return -EINVAL; =20 @@ -371,22 +365,19 @@ static int intel_svm_bind_mm(struct intel_iommu *iomm= u, struct device *dev, return ret; } =20 -/* Caller must hold pasid_mutex */ -static int intel_svm_unbind_mm(struct device *dev, u32 pasid) +void intel_svm_remove_dev_pasid(struct device *dev, u32 pasid) { struct intel_svm_dev *sdev; struct intel_iommu *iommu; struct intel_svm *svm; struct mm_struct *mm; - int ret =3D -EINVAL; =20 iommu =3D device_to_iommu(dev, NULL, NULL); if (!iommu) - goto out; + return; =20 - ret =3D pasid_to_svm_sdev(dev, pasid, &svm, &sdev); - if (ret) - goto out; + if (pasid_to_svm_sdev(dev, pasid, &svm, &sdev)) + return; mm =3D svm->mm; =20 if (sdev) { @@ -418,8 +409,6 @@ static int intel_svm_unbind_mm(struct device *dev, u32 = pasid) kfree(svm); } } -out: - return ret; } =20 /* Page request queue descriptor */ @@ -520,19 +509,7 @@ static void intel_svm_drain_prq(struct device *dev, u3= 2 pasid) goto prq_retry; } =20 - /* - * A work in IO page fault workqueue may try to lock pasid_mutex now. - * Holding pasid_mutex while waiting in iopf_queue_flush_dev() for - * all works in the workqueue to finish may cause deadlock. - * - * It's unnecessary to hold pasid_mutex in iopf_queue_flush_dev(). - * Unlock it to allow the works to be handled while waiting for - * them to finish. - */ - lockdep_assert_held(&pasid_mutex); - mutex_unlock(&pasid_mutex); iopf_queue_flush_dev(dev); - mutex_lock(&pasid_mutex); =20 /* * Perform steps described in VT-d spec CH7.10 to drain page @@ -827,26 +804,14 @@ int intel_svm_page_response(struct device *dev, return ret; } =20 -void intel_svm_remove_dev_pasid(struct device *dev, ioasid_t pasid) -{ - mutex_lock(&pasid_mutex); - intel_svm_unbind_mm(dev, pasid); - mutex_unlock(&pasid_mutex); -} - static int intel_svm_set_dev_pasid(struct iommu_domain *domain, struct device *dev, ioasid_t pasid) { struct device_domain_info *info =3D dev_iommu_priv_get(dev); struct intel_iommu *iommu =3D info->iommu; struct mm_struct *mm =3D domain->mm; - int ret; =20 - mutex_lock(&pasid_mutex); - ret =3D intel_svm_bind_mm(iommu, dev, mm); - mutex_unlock(&pasid_mutex); - - return ret; + return intel_svm_bind_mm(iommu, dev, mm); } =20 static void intel_svm_domain_free(struct iommu_domain *domain) --=20 2.25.1 From nobody Sun Apr 28 23:04:51 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3B1C9C77B7A for ; Fri, 2 Jun 2023 18:18:10 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237085AbjFBSSG (ORCPT ); Fri, 2 Jun 2023 14:18:06 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:37030 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S237025AbjFBSRp (ORCPT ); Fri, 2 Jun 2023 14:17:45 -0400 Received: from mga05.intel.com (mga05.intel.com [192.55.52.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 5607B197; Fri, 2 Jun 2023 11:17:44 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685729864; x=1717265864; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=3e3OFmQg7r8dzQcmVaorP5GcY9XosK0gMzuLCkej4As=; b=LF2RMysN3WigRIgediM2uJHHyDIqBrx2a1kRI3rO4tfzRDOpmhEQml7S b7y3O5tah9BPnLjxj0NdqAxxY6GwnrauxMaUIAxhtZQiHancava6d9VEt NqnOkaZ6CzcRBI7LJCybXKZ0xHlV9WDMMRnbx7KDf7MvR98uiK1QB59hd 2OKckK8WiTj6FiT7dbXT4z5BKIwN8THxs5gXFPwNLkmBvmG76eUu0TUYh SWc3C5E0aPGLRn5bzJ3cE26kjrQEdC33ppT5p9+NNguOeiShzegE5is7m EW4NotsyETtk57gOBa2UDcvXaYfNRP9r58nWNpWlhA28gKM6xG43tUscs Q==; X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="442310254" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="442310254" Received: from orsmga004.jf.intel.com ([10.7.209.38]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 02 Jun 2023 11:17:39 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="832060971" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="832060971" Received: from srinivas-otcpl-7600.jf.intel.com (HELO jacob-builder.jf.intel.com) ([10.54.97.184]) by orsmga004.jf.intel.com with ESMTP; 02 Jun 2023 11:17:38 -0700 From: Jacob Pan To: LKML , iommu@lists.linux.dev, Jason Gunthorpe , "Lu Baolu" , Joerg Roedel , "Robin Murphy" , Jean-Philippe Brucker , dmaengine@vger.kernel.org, vkoul@kernel.org Cc: "Will Deacon" , David Woodhouse , Raj Ashok , "Tian, Kevin" , Yi Liu , "Yu, Fenghua" , Dave Jiang , Tony Luck , "Zanussi, Tom" , rex.zhang@intel.com, xiaochen.shen@intel.com, narayan.ranganathan@intel.com, Jacob Pan Subject: [PATCH v8 5/7] iommu/vt-d: Make prq draining code generic Date: Fri, 2 Jun 2023 11:22:10 -0700 Message-Id: <20230602182212.150825-6-jacob.jun.pan@linux.intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> References: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" From: Lu Baolu Currently draining page requests and responses for a pasid is part of SVA implementation. This is because the driver only supports attaching an SVA domain to a device pasid. As we are about to support attaching other types of domains to a device pasid, the prq draining code becomes generic. Reviewed-by: Jacob Pan Signed-off-by: Lu Baolu --- drivers/iommu/intel/iommu.c | 30 +++++++++++++++++++----------- drivers/iommu/intel/iommu.h | 2 ++ drivers/iommu/intel/svm.c | 8 ++------ 3 files changed, 23 insertions(+), 17 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 3214990b69b7..8ea656446616 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4740,21 +4740,29 @@ static void intel_iommu_remove_dev_pasid(struct dev= ice *dev, ioasid_t pasid) struct intel_iommu *iommu =3D device_to_iommu(dev, NULL, NULL); struct iommu_domain *domain; =20 - /* Domain type specific cleanup: */ domain =3D iommu_get_domain_for_dev_pasid(dev, pasid, 0); - if (domain) { - switch (domain->type) { - case IOMMU_DOMAIN_SVA: - intel_svm_remove_dev_pasid(dev, pasid); - break; - default: - /* should never reach here */ - WARN_ON(1); - break; - } + if (!domain) + goto out_tear_down; + + /* + * The SVA implementation needs to handle its own stuffs like the mm + * notification. Before consolidating that code into iommu core, let + * the intel sva code handle it. + */ + if (domain->type =3D=3D IOMMU_DOMAIN_SVA) { + intel_svm_remove_dev_pasid(dev, pasid); + goto out_tear_down; } =20 + /* + * Should never reach here until we add support for attaching + * non-SVA domain to a pasid. + */ + WARN_ON(1); + +out_tear_down: intel_pasid_tear_down_entry(iommu, dev, pasid, false); + intel_drain_pasid_prq(dev, pasid); } =20 const struct iommu_ops intel_iommu_ops =3D { diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 1c5e1d88862b..6d94a29f5d52 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -844,6 +844,7 @@ int intel_svm_page_response(struct device *dev, struct = iommu_fault_event *evt, struct iommu_page_response *msg); struct iommu_domain *intel_svm_domain_alloc(void); void intel_svm_remove_dev_pasid(struct device *dev, ioasid_t pasid); +void intel_drain_pasid_prq(struct device *dev, u32 pasid); =20 struct intel_svm_dev { struct list_head list; @@ -862,6 +863,7 @@ struct intel_svm { }; #else static inline void intel_svm_check(struct intel_iommu *iommu) {} +static inline void intel_drain_pasid_prq(struct device *dev, u32 pasid) {} static inline struct iommu_domain *intel_svm_domain_alloc(void) { return NULL; diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 2a82864e9d57..588367a9e9b5 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -26,8 +26,6 @@ #include "trace.h" =20 static irqreturn_t prq_event_thread(int irq, void *d); -static void intel_svm_drain_prq(struct device *dev, u32 pasid); -#define to_intel_svm_dev(handle) container_of(handle, struct intel_svm_dev= , sva) =20 static DEFINE_XARRAY_ALLOC(pasid_private_array); static int pasid_private_add(ioasid_t pasid, void *priv) @@ -391,8 +389,6 @@ void intel_svm_remove_dev_pasid(struct device *dev, u32= pasid) * large and has to be physically contiguous. So it's * hard to be as defensive as we might like. */ - intel_pasid_tear_down_entry(iommu, dev, svm->pasid, false); - intel_svm_drain_prq(dev, svm->pasid); kfree_rcu(sdev, rcu); =20 if (list_empty(&svm->devs)) { @@ -449,7 +445,7 @@ static bool is_canonical_address(u64 addr) } =20 /** - * intel_svm_drain_prq - Drain page requests and responses for a pasid + * intel_drain_pasid_prq - Drain page requests and responses for a pasid * @dev: target device * @pasid: pasid for draining * @@ -463,7 +459,7 @@ static bool is_canonical_address(u64 addr) * described in VT-d spec CH7.10 to drain all page requests and page * responses pending in the hardware. */ -static void intel_svm_drain_prq(struct device *dev, u32 pasid) +void intel_drain_pasid_prq(struct device *dev, u32 pasid) { struct device_domain_info *info; struct dmar_domain *domain; --=20 2.25.1 From nobody Sun Apr 28 23:04:51 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id BEA1FC77B7A for ; Fri, 2 Jun 2023 18:18:12 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237093AbjFBSSL (ORCPT ); Fri, 2 Jun 2023 14:18:11 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:37028 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S237026AbjFBSRp (ORCPT ); Fri, 2 Jun 2023 14:17:45 -0400 Received: from mga05.intel.com (mga05.intel.com [192.55.52.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id B63F5198; Fri, 2 Jun 2023 11:17:43 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685729863; x=1717265863; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=n9e+x5KIG9y3L9yhpC/i1d2YZuCh2BS2PfXSQcvbH+g=; b=XnaY/ywRsrLF0yQKZLI49UmGyPUM81cFJzVLW6LOTNntlFUbXQkJZvWz 0jNN+R+dRXVaG91XJ4PZ8p7i6os9hOOvQmLH+SAlsdyD2fVWLVG3OmEvO HMnV1t1K1oAZWeBQYeGUaPWJxVZs4SS52hWRvem4VbnLDxDz0FwznWJsH IJWrMxlWeFkhEWGQzHWtsuw5gLM/nfD9zQy57W4AI3lwRT8inQiO5LfFG AINJHeEtCmJ1A4VTTxAZMdrWY5bjVOGoz2zw3BYlBTzQcQfj34xQ3vAO8 XA7WkYI9+PjIdY0G3UhtFMTMKRk1cbjgaito51RkQcwAnBNigwQbZgpYW w==; X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="442310256" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="442310256" Received: from orsmga004.jf.intel.com ([10.7.209.38]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 02 Jun 2023 11:17:39 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="832060974" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="832060974" Received: from srinivas-otcpl-7600.jf.intel.com (HELO jacob-builder.jf.intel.com) ([10.54.97.184]) by orsmga004.jf.intel.com with ESMTP; 02 Jun 2023 11:17:39 -0700 From: Jacob Pan To: LKML , iommu@lists.linux.dev, Jason Gunthorpe , "Lu Baolu" , Joerg Roedel , "Robin Murphy" , Jean-Philippe Brucker , dmaengine@vger.kernel.org, vkoul@kernel.org Cc: "Will Deacon" , David Woodhouse , Raj Ashok , "Tian, Kevin" , Yi Liu , "Yu, Fenghua" , Dave Jiang , Tony Luck , "Zanussi, Tom" , rex.zhang@intel.com, xiaochen.shen@intel.com, narayan.ranganathan@intel.com, Jacob Pan Subject: [PATCH v8 6/7] iommu/vt-d: Add set_dev_pasid callback for dma domain Date: Fri, 2 Jun 2023 11:22:11 -0700 Message-Id: <20230602182212.150825-7-jacob.jun.pan@linux.intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> References: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" From: Lu Baolu This allows the upper layers to set a domain to a PASID of a device if the PASID feature is supported by the IOMMU hardware. The typical use cases are, for example, kernel DMA with PASID and hardware assisted mediated device drivers. The attaching device and pasid information is tracked in a per-domain list and is used for IOTLB and devTLB invalidation. Signed-off-by: Lu Baolu Signed-off-by: Jacob Pan --- drivers/iommu/intel/iommu.c | 103 ++++++++++++++++++++++++++++++++++-- drivers/iommu/intel/iommu.h | 7 +++ 2 files changed, 105 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 8ea656446616..a1f4730743ee 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1367,6 +1367,7 @@ domain_lookup_dev_info(struct dmar_domain *domain, =20 static void domain_update_iotlb(struct dmar_domain *domain) { + struct dev_pasid_info *dev_pasid; struct device_domain_info *info; bool has_iotlb_device =3D false; unsigned long flags; @@ -1378,6 +1379,14 @@ static void domain_update_iotlb(struct dmar_domain *= domain) break; } } + + list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain) { + info =3D dev_iommu_priv_get(dev_pasid->dev); + if (info->ats_enabled) { + has_iotlb_device =3D true; + break; + } + } domain->has_iotlb_device =3D has_iotlb_device; spin_unlock_irqrestore(&domain->lock, flags); } @@ -1463,6 +1472,7 @@ static void __iommu_flush_dev_iotlb(struct device_dom= ain_info *info, static void iommu_flush_dev_iotlb(struct dmar_domain *domain, u64 addr, unsigned mask) { + struct dev_pasid_info *dev_pasid; struct device_domain_info *info; unsigned long flags; =20 @@ -1472,6 +1482,19 @@ static void iommu_flush_dev_iotlb(struct dmar_domain= *domain, spin_lock_irqsave(&domain->lock, flags); list_for_each_entry(info, &domain->devices, link) __iommu_flush_dev_iotlb(info, addr, mask); + + list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain) { + info =3D dev_iommu_priv_get(dev_pasid->dev); + + if (!info->ats_enabled) + continue; + + qi_flush_dev_iotlb_pasid(info->iommu, + PCI_DEVID(info->bus, info->devfn), + info->pfsid, dev_pasid->pasid, + info->ats_qdep, addr, + mask); + } spin_unlock_irqrestore(&domain->lock, flags); } =20 @@ -1485,9 +1508,13 @@ static void domain_flush_pasid_iotlb(struct intel_io= mmu *iommu, unsigned long npages, bool ih) { u16 did =3D domain_id_iommu(domain, iommu); + struct dev_pasid_info *dev_pasid; unsigned long flags; =20 spin_lock_irqsave(&domain->lock, flags); + list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain) + qi_flush_piotlb(iommu, did, dev_pasid->pasid, addr, npages, ih); + if (!list_empty(&domain->devices)) qi_flush_piotlb(iommu, did, IOMMU_NO_PASID, addr, npages, ih); spin_unlock_irqrestore(&domain->lock, flags); @@ -1752,6 +1779,7 @@ static struct dmar_domain *alloc_domain(unsigned int = type) domain->use_first_level =3D true; domain->has_iotlb_device =3D false; INIT_LIST_HEAD(&domain->devices); + INIT_LIST_HEAD(&domain->dev_pasids); spin_lock_init(&domain->lock); xa_init(&domain->iommu_array); =20 @@ -4738,7 +4766,10 @@ static void intel_iommu_iotlb_sync_map(struct iommu_= domain *domain, static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasi= d) { struct intel_iommu *iommu =3D device_to_iommu(dev, NULL, NULL); + struct dev_pasid_info *curr, *dev_pasid =3D NULL; + struct dmar_domain *dmar_domain; struct iommu_domain *domain; + unsigned long flags; =20 domain =3D iommu_get_domain_for_dev_pasid(dev, pasid, 0); if (!domain) @@ -4754,17 +4785,78 @@ static void intel_iommu_remove_dev_pasid(struct dev= ice *dev, ioasid_t pasid) goto out_tear_down; } =20 - /* - * Should never reach here until we add support for attaching - * non-SVA domain to a pasid. - */ - WARN_ON(1); + dmar_domain =3D to_dmar_domain(domain); + spin_lock_irqsave(&dmar_domain->lock, flags); + list_for_each_entry(curr, &dmar_domain->dev_pasids, link_domain) { + if (curr->dev =3D=3D dev && curr->pasid =3D=3D pasid) { + list_del(&curr->link_domain); + dev_pasid =3D curr; + break; + } + } + spin_unlock_irqrestore(&dmar_domain->lock, flags); =20 + domain_detach_iommu(dmar_domain, iommu); + kfree(dev_pasid); out_tear_down: intel_pasid_tear_down_entry(iommu, dev, pasid, false); intel_drain_pasid_prq(dev, pasid); } =20 +static int intel_iommu_set_dev_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid) +{ + struct device_domain_info *info =3D dev_iommu_priv_get(dev); + struct dmar_domain *dmar_domain =3D to_dmar_domain(domain); + struct intel_iommu *iommu =3D info->iommu; + struct dev_pasid_info *dev_pasid; + unsigned long flags; + int ret; + + if (!pasid_supported(iommu) || dev_is_real_dma_subdevice(dev)) + return -EOPNOTSUPP; + + if (context_copied(iommu, info->bus, info->devfn)) + return -EBUSY; + + ret =3D prepare_domain_attach_device(domain, dev); + if (ret) + return ret; + + dev_pasid =3D kzalloc(sizeof(*dev_pasid), GFP_KERNEL); + if (!dev_pasid) + return -ENOMEM; + + ret =3D domain_attach_iommu(dmar_domain, iommu); + if (ret) + goto out_free; + + if (domain_type_is_si(dmar_domain)) + ret =3D intel_pasid_setup_pass_through(iommu, dmar_domain, + dev, pasid); + else if (dmar_domain->use_first_level) + ret =3D domain_setup_first_level(iommu, dmar_domain, + dev, pasid); + else + ret =3D intel_pasid_setup_second_level(iommu, dmar_domain, + dev, pasid); + if (ret) + goto out_detach_iommu; + + dev_pasid->dev =3D dev; + dev_pasid->pasid =3D pasid; + spin_lock_irqsave(&dmar_domain->lock, flags); + list_add(&dev_pasid->link_domain, &dmar_domain->dev_pasids); + spin_unlock_irqrestore(&dmar_domain->lock, flags); + + return 0; +out_detach_iommu: + domain_detach_iommu(dmar_domain, iommu); +out_free: + kfree(dev_pasid); + return ret; +} + const struct iommu_ops intel_iommu_ops =3D { .capable =3D intel_iommu_capable, .domain_alloc =3D intel_iommu_domain_alloc, @@ -4784,6 +4876,7 @@ const struct iommu_ops intel_iommu_ops =3D { #endif .default_domain_ops =3D &(const struct iommu_domain_ops) { .attach_dev =3D intel_iommu_attach_device, + .set_dev_pasid =3D intel_iommu_set_dev_pasid, .map_pages =3D intel_iommu_map_pages, .unmap_pages =3D intel_iommu_unmap_pages, .iotlb_sync_map =3D intel_iommu_iotlb_sync_map, diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 6d94a29f5d52..68bb7cdf5543 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -595,6 +595,7 @@ struct dmar_domain { =20 spinlock_t lock; /* Protect device tracking lists */ struct list_head devices; /* all devices' list */ + struct list_head dev_pasids; /* all attached pasids */ =20 struct dma_pte *pgd; /* virtual address */ int gaw; /* max guest address width */ @@ -717,6 +718,12 @@ struct device_domain_info { struct pasid_table *pasid_table; /* pasid table */ }; =20 +struct dev_pasid_info { + struct list_head link_domain; /* link to domain siblings */ + struct device *dev; /* the physical device */ + ioasid_t pasid; /* PASID of the physical device */ +}; + static inline void __iommu_flush_cache( struct intel_iommu *iommu, void *addr, int size) { --=20 2.25.1 From nobody Sun Apr 28 23:04:51 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id ECEC3C7EE24 for ; Fri, 2 Jun 2023 18:18:16 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237104AbjFBSSP (ORCPT ); Fri, 2 Jun 2023 14:18:15 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:37034 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S237030AbjFBSRq (ORCPT ); Fri, 2 Jun 2023 14:17:46 -0400 Received: from mga05.intel.com (mga05.intel.com [192.55.52.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id D370B123; Fri, 2 Jun 2023 11:17:44 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1685729864; x=1717265864; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=3l8xEOg1j9eYw8bKEK7cjmoMcmI99b2shaUO5f1bGAc=; b=Jwwpevk6K/l7CDmDhM66bsBNrUqWnvR4IJAj9ptNzbNkD+3WihXb7GtV F/ZlBb3cglnJHNuRhaz6VsGpGs7R5s1uMiQTLThp1bF7wj4KNcPCuv4zk WsX0hCPks25RWaIC4O8oG2Yh4Qf5TjDG+spkR7BdVweiTAJ5zxGPhv0Fq Fcs22tEGDZmWWaHA4Tv/rYuEVpRGYrcgFsxs37//bqh3bzgVRZwOE+Yjq 6vOS1l+8TS/74JddYQr15j7ql1Khr28Oij4VJtBkCK97u005W9Xw+PlGs c+bby+raaGDj1VN/8MNATYYPWZfvYDywzaG89ohLXkLQSRWfkDy4H5wYF g==; X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="442310266" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="442310266" Received: from orsmga004.jf.intel.com ([10.7.209.38]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 02 Jun 2023 11:17:39 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10729"; a="832060977" X-IronPort-AV: E=Sophos;i="6.00,213,1681196400"; d="scan'208";a="832060977" Received: from srinivas-otcpl-7600.jf.intel.com (HELO jacob-builder.jf.intel.com) ([10.54.97.184]) by orsmga004.jf.intel.com with ESMTP; 02 Jun 2023 11:17:39 -0700 From: Jacob Pan To: LKML , iommu@lists.linux.dev, Jason Gunthorpe , "Lu Baolu" , Joerg Roedel , "Robin Murphy" , Jean-Philippe Brucker , dmaengine@vger.kernel.org, vkoul@kernel.org Cc: "Will Deacon" , David Woodhouse , Raj Ashok , "Tian, Kevin" , Yi Liu , "Yu, Fenghua" , Dave Jiang , Tony Luck , "Zanussi, Tom" , rex.zhang@intel.com, xiaochen.shen@intel.com, narayan.ranganathan@intel.com, Jacob Pan Subject: [PATCH v8 7/7] dmaengine/idxd: Re-enable kernel workqueue under DMA API Date: Fri, 2 Jun 2023 11:22:12 -0700 Message-Id: <20230602182212.150825-8-jacob.jun.pan@linux.intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> References: <20230602182212.150825-1-jacob.jun.pan@linux.intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Kernel workqueues were disabled due to flawed use of kernel VA and SVA API. Now that we have the support for attaching PASID to the device's default domain and the ability to reserve global PASIDs from SVA APIs, we can re-enable the kernel work queues and use them under DMA API. We also use non-privileged access for in-kernel DMA to be consistent with the IOMMU settings. Consequently, interrupt for user privilege is enabled for work completion IRQs. Link:https://lore.kernel.org/linux-iommu/20210511194726.GP1002214@nvidia.co= m/ Reviewed-by: Dave Jiang Reviewed-by: Fenghua Yu Reviewed-by: Lu Baolu Acked-by: Vinod Koul Signed-off-by: Jacob Pan --- drivers/dma/idxd/device.c | 30 ++++---------------- drivers/dma/idxd/dma.c | 5 ++-- drivers/dma/idxd/init.c | 60 ++++++++++++++++++++++++++++++++++++--- drivers/dma/idxd/sysfs.c | 7 ----- 4 files changed, 64 insertions(+), 38 deletions(-) diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 5abbcc61c528..66b6665a45cb 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -299,21 +299,6 @@ void idxd_wqs_unmap_portal(struct idxd_device *idxd) } } =20 -static void __idxd_wq_set_priv_locked(struct idxd_wq *wq, int priv) -{ - struct idxd_device *idxd =3D wq->idxd; - union wqcfg wqcfg; - unsigned int offset; - - offset =3D WQCFG_OFFSET(idxd, wq->id, WQCFG_PRIVL_IDX); - spin_lock(&idxd->dev_lock); - wqcfg.bits[WQCFG_PRIVL_IDX] =3D ioread32(idxd->reg_base + offset); - wqcfg.priv =3D priv; - wq->wqcfg->bits[WQCFG_PRIVL_IDX] =3D wqcfg.bits[WQCFG_PRIVL_IDX]; - iowrite32(wqcfg.bits[WQCFG_PRIVL_IDX], idxd->reg_base + offset); - spin_unlock(&idxd->dev_lock); -} - static void __idxd_wq_set_pasid_locked(struct idxd_wq *wq, int pasid) { struct idxd_device *idxd =3D wq->idxd; @@ -1423,15 +1408,14 @@ int drv_enable_wq(struct idxd_wq *wq) } =20 /* - * In the event that the WQ is configurable for pasid and priv bits. - * For kernel wq, the driver should setup the pasid, pasid_en, and priv b= it. - * However, for non-kernel wq, the driver should only set the pasid_en bi= t for - * shared wq. A dedicated wq that is not 'kernel' type will configure pas= id and + * In the event that the WQ is configurable for pasid, the driver + * should setup the pasid, pasid_en bit. This is true for both kernel + * and user shared workqueues. There is no need to setup priv bit in + * that in-kernel DMA will also do user privileged requests. + * A dedicated wq that is not 'kernel' type will configure pasid and * pasid_en later on so there is no need to setup. */ if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) { - int priv =3D 0; - if (wq_pasid_enabled(wq)) { if (is_idxd_wq_kernel(wq) || wq_shared(wq)) { u32 pasid =3D wq_dedicated(wq) ? idxd->pasid : 0; @@ -1439,10 +1423,6 @@ int drv_enable_wq(struct idxd_wq *wq) __idxd_wq_set_pasid_locked(wq, pasid); } } - - if (is_idxd_wq_kernel(wq)) - priv =3D 1; - __idxd_wq_set_priv_locked(wq, priv); } =20 rc =3D 0; diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c index eb35ca313684..07623fb0f52f 100644 --- a/drivers/dma/idxd/dma.c +++ b/drivers/dma/idxd/dma.c @@ -75,9 +75,10 @@ static inline void idxd_prep_desc_common(struct idxd_wq = *wq, hw->xfer_size =3D len; /* * For dedicated WQ, this field is ignored and HW will use the WQCFG.priv - * field instead. This field should be set to 1 for kernel descriptors. + * field instead. This field should be set to 0 for kernel descriptors + * since kernel DMA on VT-d supports "user" privilege only. */ - hw->priv =3D 1; + hw->priv =3D 0; hw->completion_addr =3D compl; } =20 diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 1aa823974cda..bd7b9bd40f0a 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -550,14 +550,65 @@ static struct idxd_device *idxd_alloc(struct pci_dev = *pdev, struct idxd_driver_d =20 static int idxd_enable_system_pasid(struct idxd_device *idxd) { - return -EOPNOTSUPP; + struct pci_dev *pdev =3D idxd->pdev; + struct device *dev =3D &pdev->dev; + struct iommu_domain *domain; + union gencfg_reg gencfg; + ioasid_t pasid; + int ret; + + /* + * Attach a global PASID to the DMA domain so that we can use ENQCMDS + * to submit work on buffers mapped by DMA API. + */ + domain =3D iommu_get_domain_for_dev(dev); + if (!domain) + return -EPERM; + + pasid =3D iommu_alloc_global_pasid_dev(dev); + if (pasid =3D=3D IOMMU_PASID_INVALID) + return -ENOSPC; + + /* + * DMA domain is owned by the driver, it should support all valid + * types such as DMA-FQ, identity, etc. + */ + ret =3D iommu_attach_device_pasid(domain, dev, pasid); + if (ret) { + dev_err(dev, "failed to attach device pasid %d, domain type %d", + pasid, domain->type); + iommu_free_global_pasid(pasid); + return ret; + } + + /* Since we set user privilege for kernel DMA, enable completion IRQ */ + gencfg.bits =3D ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET); + gencfg.user_int_en =3D 1; + iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET); + idxd->pasid =3D pasid; + + return ret; } =20 static void idxd_disable_system_pasid(struct idxd_device *idxd) { + struct pci_dev *pdev =3D idxd->pdev; + struct device *dev =3D &pdev->dev; + struct iommu_domain *domain; + union gencfg_reg gencfg; + + domain =3D iommu_get_domain_for_dev(dev); + if (!domain) + return; + + iommu_detach_device_pasid(domain, dev, idxd->pasid); + iommu_free_global_pasid(idxd->pasid); =20 - iommu_sva_unbind_device(idxd->sva); + gencfg.bits =3D ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET); + gencfg.user_int_en =3D 0; + iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET); idxd->sva =3D NULL; + idxd->pasid =3D IOMMU_PASID_INVALID; } =20 static int idxd_enable_sva(struct pci_dev *pdev) @@ -600,8 +651,9 @@ static int idxd_probe(struct idxd_device *idxd) } else { set_bit(IDXD_FLAG_USER_PASID_ENABLED, &idxd->flags); =20 - if (idxd_enable_system_pasid(idxd)) - dev_warn(dev, "No in-kernel DMA with PASID.\n"); + rc =3D idxd_enable_system_pasid(idxd); + if (rc) + dev_warn(dev, "No in-kernel DMA with PASID. %d\n", rc); else set_bit(IDXD_FLAG_PASID_ENABLED, &idxd->flags); } diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 293739ac5596..63f6966c51aa 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -948,13 +948,6 @@ static ssize_t wq_name_store(struct device *dev, if (strlen(buf) > WQ_NAME_SIZE || strlen(buf) =3D=3D 0) return -EINVAL; =20 - /* - * This is temporarily placed here until we have SVM support for - * dmaengine. - */ - if (wq->type =3D=3D IDXD_WQT_KERNEL && device_pasid_enabled(wq->idxd)) - return -EOPNOTSUPP; - input =3D kstrndup(buf, count, GFP_KERNEL); if (!input) return -ENOMEM; --=20 2.25.1