From: Filippo Sironi via iommu <iommu@lists.linux-foundation.org>
To: sironi@amazon.de, joro@8bytes.org,
iommu@lists.linux-foundation.org, linux-kernel@vger.kernel.org
Subject: [PATCH 3/5] iommu/amd: Hold the domain lock when calling __unmap_single
Date: Tue, 10 Sep 2019 19:49:23 +0200 [thread overview]
Message-ID: <1568137765-20278-4-git-send-email-sironi@amazon.de> (raw)
In-Reply-To: <1568137765-20278-1-git-send-email-sironi@amazon.de>
__unmap_single makes several calls to __domain_flush_pages, which
traverses the device list that is protected by the domain lock.
__attach_device and __detach_device).
Also, this is in line with the comment on top of __unmap_single, which
says that the domain lock should be held when calling.
Signed-off-by: Filippo Sironi <sironi@amazon.de>
---
drivers/iommu/amd_iommu.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 8e3664821b3c..d4f25767622e 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -2508,6 +2508,7 @@ static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
{
struct protection_domain *domain;
struct dma_ops_domain *dma_dom;
+ unsigned long flags;
domain = get_domain(dev);
if (IS_ERR(domain))
@@ -2515,7 +2516,9 @@ static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
dma_dom = to_dma_ops_domain(domain);
+ spin_lock_irqsave(&domain->lock, flags);
__unmap_single(dma_dom, dma_addr, size, dir);
+ spin_unlock_irqrestore(&domain->lock, flags);
}
static int sg_num_pages(struct device *dev,
@@ -2645,6 +2648,7 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
struct dma_ops_domain *dma_dom;
unsigned long startaddr;
int npages;
+ unsigned long flags;
domain = get_domain(dev);
if (IS_ERR(domain))
@@ -2654,7 +2658,9 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
dma_dom = to_dma_ops_domain(domain);
npages = sg_num_pages(dev, sglist, nelems);
+ spin_lock_irqsave(&domain->lock, flags);
__unmap_single(dma_dom, startaddr, npages << PAGE_SHIFT, dir);
+ spin_unlock_irqrestore(&domain->lock, flags);
}
/*
@@ -2726,6 +2732,7 @@ static void free_coherent(struct device *dev, size_t size,
struct protection_domain *domain;
struct dma_ops_domain *dma_dom;
struct page *page;
+ unsigned long flags;
page = virt_to_page(virt_addr);
size = PAGE_ALIGN(size);
@@ -2736,7 +2743,9 @@ static void free_coherent(struct device *dev, size_t size,
dma_dom = to_dma_ops_domain(domain);
+ spin_lock_irqsave(&domain->lock, flags);
__unmap_single(dma_dom, dma_addr, size, DMA_BIDIRECTIONAL);
+ spin_unlock_irqrestore(&domain->lock, flags);
free_mem:
if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
--
2.7.4
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2019-09-10 17:55 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-09-10 17:49 iommu/amd: Flushing and locking fixes Filippo Sironi via iommu
2019-09-10 17:49 ` [PATCH 1/5] iommu/amd: Wait for completion of IOTLB flush in attach_device Filippo Sironi via iommu
2019-09-24 9:41 ` Joerg Roedel
2019-09-10 17:49 ` [PATCH 2/5] iommu/amd: Hold the domain lock when calling __map_single Filippo Sironi via iommu
2019-09-10 17:49 ` Filippo Sironi via iommu [this message]
2019-09-10 17:49 ` [PATCH 4/5] iommu/amd: Hold the domain lock when calling iommu_map_page Filippo Sironi via iommu
2019-09-20 18:05 ` Sironi, Filippo via iommu
2019-09-10 17:49 ` [PATCH 5/5] iommu/amd: Hold the domain lock when calling domain_flush_tlb[_pde] Filippo Sironi via iommu
2019-09-11 11:34 ` iommu/amd: Flushing and locking fixes Joerg Roedel
2019-09-13 17:37 ` Sironi, Filippo via iommu
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=1568137765-20278-4-git-send-email-sironi@amazon.de \
--to=iommu@lists.linux-foundation.org \
--cc=joro@8bytes.org \
--cc=linux-kernel@vger.kernel.org \
--cc=sironi@amazon.de \
/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;
as well as URLs for NNTP newsgroup(s).