lkml.org 
[lkml]   [2011]   [Sep]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[090/244] iommu/amd: Dont take domain->lock recursivly
3.0-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Joerg Roedel <joerg.roedel@amd.com>

commit e33acde91140f1809952d1c135c36feb66a51887 upstream.

The domain_flush_devices() function takes the domain->lock.
But this function is only called from update_domain() which
itself is already called unter the domain->lock. This causes
a deadlock situation when the dma-address-space of a domain
grows larger than 1GB.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
arch/x86/kernel/amd_iommu.c | 5 -----
1 file changed, 5 deletions(-)
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -773,14 +773,9 @@ static void domain_flush_complete(struct
static void domain_flush_devices(struct protection_domain *domain)
{
struct iommu_dev_data *dev_data;
- unsigned long flags;
-
- spin_lock_irqsave(&domain->lock, flags);

list_for_each_entry(dev_data, &domain->dev_list, list)
device_flush_dte(dev_data->dev);
-
- spin_unlock_irqrestore(&domain->lock, flags);
}

/****************************************************************************



\
 
 \ /
  Last update: 2011-09-29 01:23    [from the cache]
©2003-2011 Jasper Spaans