public inbox for iommu@lists.linux-foundation.org
 help / color / mirror / Atom feed
From: Lu Baolu <baolu.lu@linux.intel.com>
To: Joerg Roedel <joro@8bytes.org>
Cc: Fenghua Yu <fenghua.yu@intel.com>,
	Kevin Tian <kevin.tian@intel.com>,
	Liujunjie <liujunjie23@huawei.com>,
	Tvrtko Ursulin <tvrtko.ursulin@intel.com>,
	Kyung Min Park <kyung.min.park@intel.com>,
	iommu@lists.linux-foundation.org, Longpeng <longpeng2@huawei.com>
Subject: [PATCH 9/9] iommu/vt-d: Avoid duplicate removing in __domain_mapping()
Date: Thu, 14 Oct 2021 13:38:39 +0800	[thread overview]
Message-ID: <20211014053839.727419-10-baolu.lu@linux.intel.com> (raw)
In-Reply-To: <20211014053839.727419-1-baolu.lu@linux.intel.com>

From: "Longpeng(Mike)" <longpeng2@huawei.com>

The __domain_mapping() always removes the pages in the range from
'iov_pfn' to 'end_pfn', but the 'end_pfn' is always the last pfn
of the range that the caller wants to map.

This would introduce too many duplicated removing and leads the
map operation take too long, for example:

  Map iova=0x100000,nr_pages=0x7d61800
    iov_pfn: 0x100000, end_pfn: 0x7e617ff
    iov_pfn: 0x140000, end_pfn: 0x7e617ff
    iov_pfn: 0x180000, end_pfn: 0x7e617ff
    iov_pfn: 0x1c0000, end_pfn: 0x7e617ff
    iov_pfn: 0x200000, end_pfn: 0x7e617ff
    ...
  it takes about 50ms in total.

We can reduce the cost by recalculate the 'end_pfn' and limit it
to the boundary of the end of this pte page.

  Map iova=0x100000,nr_pages=0x7d61800
    iov_pfn: 0x100000, end_pfn: 0x13ffff
    iov_pfn: 0x140000, end_pfn: 0x17ffff
    iov_pfn: 0x180000, end_pfn: 0x1bffff
    iov_pfn: 0x1c0000, end_pfn: 0x1fffff
    iov_pfn: 0x200000, end_pfn: 0x23ffff
    ...
  it only need 9ms now.

This also removes a meaningless BUG_ON() in __domain_mapping().

Signed-off-by: Longpeng(Mike) <longpeng2@huawei.com>
Tested-by: Liujunjie <liujunjie23@huawei.com>
Link: https://lore.kernel.org/r/20211008000433.1115-1-longpeng2@huawei.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 include/linux/intel-iommu.h |  6 ++++++
 drivers/iommu/intel/iommu.c | 11 ++++++-----
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 52481625838c..69230fd695ea 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -710,6 +710,12 @@ static inline bool first_pte_in_page(struct dma_pte *pte)
 	return IS_ALIGNED((unsigned long)pte, VTD_PAGE_SIZE);
 }
 
+static inline int nr_pte_to_next_page(struct dma_pte *pte)
+{
+	return first_pte_in_page(pte) ? BIT_ULL(VTD_STRIDE_SHIFT) :
+		(struct dma_pte *)ALIGN((unsigned long)pte, VTD_PAGE_SIZE) - pte;
+}
+
 extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev);
 extern int dmar_find_matched_atsr_unit(struct pci_dev *dev);
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 16a35669a9d0..0bde0c8b4126 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -2479,12 +2479,17 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 				return -ENOMEM;
 			first_pte = pte;
 
+			lvl_pages = lvl_to_nr_pages(largepage_lvl);
+
 			/* It is large page*/
 			if (largepage_lvl > 1) {
 				unsigned long end_pfn;
+				unsigned long pages_to_remove;
 
 				pteval |= DMA_PTE_LARGE_PAGE;
-				end_pfn = ((iov_pfn + nr_pages) & level_mask(largepage_lvl)) - 1;
+				pages_to_remove = min_t(unsigned long, nr_pages,
+							nr_pte_to_next_page(pte) * lvl_pages);
+				end_pfn = iov_pfn + pages_to_remove - 1;
 				switch_to_super_page(domain, iov_pfn, end_pfn, largepage_lvl);
 			} else {
 				pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE;
@@ -2506,10 +2511,6 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			WARN_ON(1);
 		}
 
-		lvl_pages = lvl_to_nr_pages(largepage_lvl);
-
-		BUG_ON(nr_pages < lvl_pages);
-
 		nr_pages -= lvl_pages;
 		iov_pfn += lvl_pages;
 		phys_pfn += lvl_pages;
-- 
2.25.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

  parent reply	other threads:[~2021-10-14  5:43 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-14  5:38 [PATCH 0/9] [PULL REQUEST] Intel IOMMU Updates for Linux v5.16 Lu Baolu
2021-10-14  5:38 ` [PATCH 1/9] iommu/vt-d: Do not falsely log intel_iommu is unsupported kernel option Lu Baolu
2021-10-14  5:38 ` [PATCH 2/9] iommu/vt-d: Dump DMAR translation structure when DMA fault occurs Lu Baolu
2021-10-14  5:38 ` [PATCH 3/9] iommu/vt-d: Remove duplicate identity domain flag Lu Baolu
2021-10-14  5:38 ` [PATCH 4/9] iommu/vt-d: Check FL and SL capability sanity in scalable mode Lu Baolu
2021-10-14  5:38 ` [PATCH 5/9] iommu/vt-d: Use second level for GPA->HPA translation Lu Baolu
2021-10-14  5:38 ` [PATCH 6/9] iommu/vt-d: Delete dev_has_feat callback Lu Baolu
2021-10-14  5:38 ` [PATCH 7/9] iommu/vt-d: Clean up unused PASID updating functions Lu Baolu
2021-10-14  5:38 ` [PATCH 8/9] iommu/vt-d: Convert the return type of first_pte_in_page to bool Lu Baolu
2021-10-14  5:38 ` Lu Baolu [this message]
2021-10-18 18:33 ` [PATCH 0/9] [PULL REQUEST] Intel IOMMU Updates for Linux v5.16 Joerg Roedel

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=20211014053839.727419-10-baolu.lu@linux.intel.com \
    --to=baolu.lu@linux.intel.com \
    --cc=fenghua.yu@intel.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=joro@8bytes.org \
    --cc=kevin.tian@intel.com \
    --cc=kyung.min.park@intel.com \
    --cc=liujunjie23@huawei.com \
    --cc=longpeng2@huawei.com \
    --cc=tvrtko.ursulin@intel.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox