linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Lu Baolu <baolu.lu@linux.intel.com>
To: David Woodhouse <dwmw2@infradead.org>, Joerg Roedel <joro@8bytes.org>
Cc: ashok.raj@intel.com, jacob.jun.pan@intel.com,
	kevin.tian@intel.com, Christoph Hellwig <hch@lst.de>,
	Robin Murphy <robin.murphy@arm.com>,
	iommu@lists.linux-foundation.org, linux-kernel@vger.kernel.org,
	Lu Baolu <baolu.lu@linux.intel.com>,
	Jacob Pan <jacob.jun.pan@linux.intel.com>
Subject: [PATCH 2/3] iommu/vt-d: Apply per-device dma_ops
Date: Thu,  1 Aug 2019 14:01:55 +0800	[thread overview]
Message-ID: <20190801060156.8564-3-baolu.lu@linux.intel.com> (raw)
In-Reply-To: <20190801060156.8564-1-baolu.lu@linux.intel.com>

Current Intel IOMMU driver sets the system level dma_ops. This
implementation has at least the following drawbacks: 1) each
dma API will go through the IOMMU driver even the devices are
using identity mapped domains; 2) if user requests to use an
identity mapped domain (a.k.a. bypass iommu translation), the
driver might fall back to dma domain blindly if the device is
not able to address all system memory.

This sets per-device dma_ops if a device is using a dma domain.
Otherwise, use the default system level dma_ops for direct dma.

Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel-iommu.c | 48 ++++++++-----------------------------
 1 file changed, 10 insertions(+), 38 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index d2ac89a2026e..609b539b93f6 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3431,43 +3431,10 @@ static struct dmar_domain *get_private_domain_for_dev(struct device *dev)
 /* Check if the dev needs to go through non-identity map and unmap process.*/
 static bool iommu_need_mapping(struct device *dev)
 {
-	int ret;
-
 	if (iommu_dummy(dev))
 		return false;
 
-	ret = identity_mapping(dev);
-	if (ret) {
-		u64 dma_mask = *dev->dma_mask;
-
-		if (dev->coherent_dma_mask && dev->coherent_dma_mask < dma_mask)
-			dma_mask = dev->coherent_dma_mask;
-
-		if (dma_mask >= dma_get_required_mask(dev))
-			return false;
-
-		/*
-		 * 32 bit DMA is removed from si_domain and fall back to
-		 * non-identity mapping.
-		 */
-		dmar_remove_one_dev_info(dev);
-		ret = iommu_request_dma_domain_for_dev(dev);
-		if (ret) {
-			struct iommu_domain *domain;
-			struct dmar_domain *dmar_domain;
-
-			domain = iommu_get_domain_for_dev(dev);
-			if (domain) {
-				dmar_domain = to_dmar_domain(domain);
-				dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN;
-			}
-			get_private_domain_for_dev(dev);
-		}
-
-		dev_info(dev, "32bit DMA uses non-identity mapping\n");
-	}
-
-	return true;
+	return !identity_mapping(dev);
 }
 
 static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
@@ -4895,8 +4862,6 @@ int __init intel_iommu_init(void)
 	}
 	up_write(&dmar_global_lock);
 
-	dma_ops = &intel_dma_ops;
-
 	init_iommu_pm_ops();
 
 	for_each_active_iommu(iommu, drhd) {
@@ -5487,8 +5452,13 @@ static int intel_iommu_add_device(struct device *dev)
 		}
 	}
 
-	if (device_needs_bounce(dev))
-		set_dma_ops(dev, &bounce_dma_ops);
+	dmar_domain = find_domain(dev);
+	if (dmar_domain && !domain_type_is_si(dmar_domain)) {
+		if (device_needs_bounce(dev))
+			set_dma_ops(dev, &bounce_dma_ops);
+		else
+			set_dma_ops(dev, &intel_dma_ops);
+	}
 
 	return 0;
 }
@@ -5507,6 +5477,8 @@ static void intel_iommu_remove_device(struct device *dev)
 	iommu_group_remove_device(dev);
 
 	iommu_device_unlink(&iommu->iommu, dev);
+
+	set_dma_ops(dev, NULL);
 }
 
 static void intel_iommu_get_resv_regions(struct device *device,
-- 
2.17.1


  parent reply	other threads:[~2019-08-01  6:03 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-01  6:01 [PATCH 0/3] iommu/vtd: Per device dma ops Lu Baolu
2019-08-01  6:01 ` [PATCH 1/3] iommu/vt-d: Refactor find_domain() helper Lu Baolu
2019-08-01  6:10   ` Christoph Hellwig
2019-08-01  6:20     ` Lu Baolu
2019-08-01 14:09       ` Christoph Hellwig
2019-08-02  2:06         ` Lu Baolu
2019-08-01  6:01 ` Lu Baolu [this message]
2019-08-06  6:43   ` [PATCH 2/3] iommu/vt-d: Apply per-device dma_ops Christoph Hellwig
2019-08-07  3:06     ` Lu Baolu
2019-08-13  7:38       ` Lu Baolu
2019-08-01  6:01 ` [PATCH 3/3] iommu/vt-d: Cleanup after using per-device dma ops Lu Baolu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190801060156.8564-3-baolu.lu@linux.intel.com \
    --to=baolu.lu@linux.intel.com \
    --cc=ashok.raj@intel.com \
    --cc=dwmw2@infradead.org \
    --cc=hch@lst.de \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jacob.jun.pan@intel.com \
    --cc=jacob.jun.pan@linux.intel.com \
    --cc=joro@8bytes.org \
    --cc=kevin.tian@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=robin.murphy@arm.com \
    --subject='Re: [PATCH 2/3] iommu/vt-d: Apply per-device dma_ops' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).