All of lore.kernel.org
 help / color / mirror / Atom feed
* [RFC] x86/tboot: add an option to disable iommu force on
@ 2017-03-21 18:37 Shaohua Li
  2017-03-22 10:49 ` Joerg Roedel
  0 siblings, 1 reply; 10+ messages in thread
From: Shaohua Li @ 2017-03-21 18:37 UTC (permalink / raw)
  To: linux-kernel, gang.wei, jroedel, hpa, mingo
  Cc: kernel-team, ning.sun, srihan, alex.eydelberg

IOMMU harms performance signficantly when we run very fast networking
workloads. This is a limitation in hardware based on our observation, so
we'd like to disable the IOMMU force on, but we do want to use TBOOT and
we can sacrifice the DMA security bought by IOMMU. I must admit I know
nothing about TBOOT, but TBOOT guys (cc-ed) think not eabling IOMMU is
totally ok.

So introduce a new boot option to disable the force on. It's kind of
silly we need to run into intel_iommu_init even without force on, but we
need to disable TBOOT PMR registers. For system without the boot option,
nothing is changed.

Signed-off-by: Shaohua Li <shli@fb.com>
---
 arch/x86/kernel/tboot.c       |  3 +++
 drivers/iommu/intel-iommu.c   | 21 ++++++++++++++++++++-
 include/linux/dma_remapping.h |  1 +
 3 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index b868fa1..edbdfe6 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -510,6 +510,9 @@ int tboot_force_iommu(void)
 	if (!tboot_enabled())
 		return 0;
 
+	if (!intel_iommu_tboot_noforce)
+		return 1;
+
 	if (no_iommu || swiotlb || dmar_disabled)
 		pr_warning("Forcing Intel-IOMMU to enabled\n");
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 238ad34..737dfa7 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -183,6 +183,7 @@ static int rwbf_quirk;
  * (used when kernel is launched w/ TXT)
  */
 static int force_on = 0;
+int intel_iommu_tboot_noforce;
 
 /*
  * 0: Present
@@ -607,6 +608,10 @@ static int __init intel_iommu_setup(char *str)
 				"Intel-IOMMU: enable pre-production PASID support\n");
 			intel_iommu_pasid28 = 1;
 			iommu_identity_mapping |= IDENTMAP_GFX;
+		} else if (!strncmp(str, "tboot_noforce", 13)) {
+			 printk(KERN_INFO
+				"Intel-IOMMU: not forcing on after tboot\n");
+			intel_iommu_tboot_noforce = 1;
 		}
 
 		str += strcspn(str, ",");
@@ -4840,8 +4845,22 @@ int __init intel_iommu_init(void)
 		goto out_free_dmar;
 	}
 
-	if (no_iommu || dmar_disabled)
+	if (no_iommu || dmar_disabled) {
+		/*
+		 * We exit the function here to ensure IOMMU's remapping and
+		 * mempool aren't setup, which means that the IOMMU's PMRs
+		 * won't be disabled via the call to init_dmars(). So disable
+		 * it explicitly here. The PMRs were setup by tboot prior to
+		 * calling SENTER, but the kernel is expected to reset/tear
+		 * down the PMRs.
+		 */
+		if (intel_iommu_tboot_noforce) {
+			for_each_iommu(iommu, drhd)
+				iommu_disable_protect_mem_regions(iommu);
+		}
+
 		goto out_free_dmar;
+	}
 
 	if (list_empty(&dmar_rmrr_units))
 		pr_info("No RMRR found\n");
diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h
index 187c102..9088407 100644
--- a/include/linux/dma_remapping.h
+++ b/include/linux/dma_remapping.h
@@ -39,6 +39,7 @@ extern int iommu_calculate_agaw(struct intel_iommu *iommu);
 extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
 extern int dmar_disabled;
 extern int intel_iommu_enabled;
+extern int intel_iommu_tboot_noforce;
 #else
 static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
 {
-- 
2.9.3

^ permalink raw reply related	[flat|nested] 10+ messages in thread

* Re: [RFC] x86/tboot: add an option to disable iommu force on
  2017-03-21 18:37 [RFC] x86/tboot: add an option to disable iommu force on Shaohua Li
@ 2017-03-22 10:49 ` Joerg Roedel
  2017-03-22 11:50   ` Shaohua Li
  0 siblings, 1 reply; 10+ messages in thread
From: Joerg Roedel @ 2017-03-22 10:49 UTC (permalink / raw)
  To: Shaohua Li
  Cc: linux-kernel, gang.wei, hpa, mingo, kernel-team, ning.sun,
	srihan, alex.eydelberg

Hi Shaohua,

On Tue, Mar 21, 2017 at 11:37:51AM -0700, Shaohua Li wrote:
> IOMMU harms performance signficantly when we run very fast networking
> workloads. This is a limitation in hardware based on our observation, so
> we'd like to disable the IOMMU force on, but we do want to use TBOOT and
> we can sacrifice the DMA security bought by IOMMU. I must admit I know
> nothing about TBOOT, but TBOOT guys (cc-ed) think not eabling IOMMU is
> totally ok.

Can you elaborate a bit more on the setup where the IOMMU still harms
network performance? With the recent scalability improvements I measured
only a minimal impact on 10GBit networking.



	Joerg

^ permalink raw reply	[flat|nested] 10+ messages in thread

* Re: [RFC] x86/tboot: add an option to disable iommu force on
  2017-03-22 10:49 ` Joerg Roedel
@ 2017-03-22 11:50   ` Shaohua Li
  2017-04-03 19:19     ` Shaohua Li
  0 siblings, 1 reply; 10+ messages in thread
From: Shaohua Li @ 2017-03-22 11:50 UTC (permalink / raw)
  To: Joerg Roedel
  Cc: linux-kernel, gang.wei, hpa, mingo, kernel-team, ning.sun,
	srihan, alex.eydelberg

On Wed, Mar 22, 2017 at 11:49:00AM +0100, Joerg Roedel wrote:
> Hi Shaohua,
> 
> On Tue, Mar 21, 2017 at 11:37:51AM -0700, Shaohua Li wrote:
> > IOMMU harms performance signficantly when we run very fast networking
> > workloads. This is a limitation in hardware based on our observation, so
> > we'd like to disable the IOMMU force on, but we do want to use TBOOT and
> > we can sacrifice the DMA security bought by IOMMU. I must admit I know
> > nothing about TBOOT, but TBOOT guys (cc-ed) think not eabling IOMMU is
> > totally ok.
> 
> Can you elaborate a bit more on the setup where the IOMMU still harms
> network performance? With the recent scalability improvements I measured
> only a minimal impact on 10GBit networking.
Hi,

It's 40GB networking doing XDP test. Software overhead is almost unaware, but
it's the IOTLB miss (based on our analysis) which kills the performance. We
observed the same performance issue even with software passthrough (identity
mapping), only the hardware passthrough survives. The pps with iommu (with
software passthrough) is only about ~30% of that without it.

Thanks,
Shaohua

^ permalink raw reply	[flat|nested] 10+ messages in thread

* Re: [RFC] x86/tboot: add an option to disable iommu force on
  2017-03-22 11:50   ` Shaohua Li
@ 2017-04-03 19:19     ` Shaohua Li
  2017-04-07 10:08       ` Joerg Roedel
  0 siblings, 1 reply; 10+ messages in thread
From: Shaohua Li @ 2017-04-03 19:19 UTC (permalink / raw)
  To: Joerg Roedel
  Cc: linux-kernel, gang.wei, hpa, mingo, kernel-team, ning.sun,
	srihan, alex.eydelberg

On Wed, Mar 22, 2017 at 07:50:55AM -0400, Shaohua Li wrote:
> On Wed, Mar 22, 2017 at 11:49:00AM +0100, Joerg Roedel wrote:
> > Hi Shaohua,
> > 
> > On Tue, Mar 21, 2017 at 11:37:51AM -0700, Shaohua Li wrote:
> > > IOMMU harms performance signficantly when we run very fast networking
> > > workloads. This is a limitation in hardware based on our observation, so
> > > we'd like to disable the IOMMU force on, but we do want to use TBOOT and
> > > we can sacrifice the DMA security bought by IOMMU. I must admit I know
> > > nothing about TBOOT, but TBOOT guys (cc-ed) think not eabling IOMMU is
> > > totally ok.
> > 
> > Can you elaborate a bit more on the setup where the IOMMU still harms
> > network performance? With the recent scalability improvements I measured
> > only a minimal impact on 10GBit networking.
> Hi,
> 
> It's 40GB networking doing XDP test. Software overhead is almost unaware, but
> it's the IOTLB miss (based on our analysis) which kills the performance. We
> observed the same performance issue even with software passthrough (identity
> mapping), only the hardware passthrough survives. The pps with iommu (with
> software passthrough) is only about ~30% of that without it.

Hi,

Any update on this?

Thanks,
Shaohua

^ permalink raw reply	[flat|nested] 10+ messages in thread

* Re: [RFC] x86/tboot: add an option to disable iommu force on
  2017-04-03 19:19     ` Shaohua Li
@ 2017-04-07 10:08       ` Joerg Roedel
  2017-04-07 21:49         ` Sun, Ning
  0 siblings, 1 reply; 10+ messages in thread
From: Joerg Roedel @ 2017-04-07 10:08 UTC (permalink / raw)
  To: Shaohua Li
  Cc: linux-kernel, gang.wei, hpa, mingo, kernel-team, ning.sun,
	srihan, alex.eydelberg

On Mon, Apr 03, 2017 at 12:19:28PM -0700, Shaohua Li wrote:
> On Wed, Mar 22, 2017 at 07:50:55AM -0400, Shaohua Li wrote:
> > On Wed, Mar 22, 2017 at 11:49:00AM +0100, Joerg Roedel wrote:
> > > Hi Shaohua,
> > > 
> > > On Tue, Mar 21, 2017 at 11:37:51AM -0700, Shaohua Li wrote:
> > > > IOMMU harms performance signficantly when we run very fast networking
> > > > workloads. This is a limitation in hardware based on our observation, so
> > > > we'd like to disable the IOMMU force on, but we do want to use TBOOT and
> > > > we can sacrifice the DMA security bought by IOMMU. I must admit I know
> > > > nothing about TBOOT, but TBOOT guys (cc-ed) think not eabling IOMMU is
> > > > totally ok.
> > > 
> > > Can you elaborate a bit more on the setup where the IOMMU still harms
> > > network performance? With the recent scalability improvements I measured
> > > only a minimal impact on 10GBit networking.
> > Hi,
> > 
> > It's 40GB networking doing XDP test. Software overhead is almost unaware, but
> > it's the IOTLB miss (based on our analysis) which kills the performance. We
> > observed the same performance issue even with software passthrough (identity
> > mapping), only the hardware passthrough survives. The pps with iommu (with
> > software passthrough) is only about ~30% of that without it.
> 
> Any update on this?

An explicit Ack from the tboot guys would be good to have.


	Joerg

^ permalink raw reply	[flat|nested] 10+ messages in thread

* RE: [RFC] x86/tboot: add an option to disable iommu force on
  2017-04-07 10:08       ` Joerg Roedel
@ 2017-04-07 21:49         ` Sun, Ning
  2017-04-10  4:31           ` Shaohua Li
  0 siblings, 1 reply; 10+ messages in thread
From: Sun, Ning @ 2017-04-07 21:49 UTC (permalink / raw)
  To: Joerg Roedel, Shaohua Li
  Cc: linux-kernel, Wei, Gang, hpa, mingo, kernel-team, srihan,
	Eydelberg, Alex

Hi Shaohua,

One question, did you still see the network performance penalty when Linux kernel cmdline intel_iommu was set to off ( intel_iommu=off) ?

Thanks,
-ning

-----Original Message-----
From: Joerg Roedel [mailto:jroedel@suse.de] 
Sent: Friday, April 07, 2017 3:09 AM
To: Shaohua Li <shli@fb.com>
Cc: linux-kernel@vger.kernel.org; Wei, Gang <gang.wei@intel.com>; hpa@linux.intel.com; mingo@kernel.org; kernel-team@fb.com; Sun, Ning <ning.sun@intel.com>; srihan@fb.com; Eydelberg, Alex <alex.eydelberg@intel.com>
Subject: Re: [RFC] x86/tboot: add an option to disable iommu force on

On Mon, Apr 03, 2017 at 12:19:28PM -0700, Shaohua Li wrote:
> On Wed, Mar 22, 2017 at 07:50:55AM -0400, Shaohua Li wrote:
> > On Wed, Mar 22, 2017 at 11:49:00AM +0100, Joerg Roedel wrote:
> > > Hi Shaohua,
> > > 
> > > On Tue, Mar 21, 2017 at 11:37:51AM -0700, Shaohua Li wrote:
> > > > IOMMU harms performance signficantly when we run very fast 
> > > > networking workloads. This is a limitation in hardware based on 
> > > > our observation, so we'd like to disable the IOMMU force on, but 
> > > > we do want to use TBOOT and we can sacrifice the DMA security 
> > > > bought by IOMMU. I must admit I know nothing about TBOOT, but 
> > > > TBOOT guys (cc-ed) think not eabling IOMMU is totally ok.
> > > 
> > > Can you elaborate a bit more on the setup where the IOMMU still 
> > > harms network performance? With the recent scalability 
> > > improvements I measured only a minimal impact on 10GBit networking.
> > Hi,
> > 
> > It's 40GB networking doing XDP test. Software overhead is almost 
> > unaware, but it's the IOTLB miss (based on our analysis) which kills 
> > the performance. We observed the same performance issue even with 
> > software passthrough (identity mapping), only the hardware 
> > passthrough survives. The pps with iommu (with software passthrough) is only about ~30% of that without it.
> 
> Any update on this?

An explicit Ack from the tboot guys would be good to have.


	Joerg

^ permalink raw reply	[flat|nested] 10+ messages in thread

* Re: [RFC] x86/tboot: add an option to disable iommu force on
  2017-04-07 21:49         ` Sun, Ning
@ 2017-04-10  4:31           ` Shaohua Li
  2017-04-10 21:28             ` Sun, Ning
  0 siblings, 1 reply; 10+ messages in thread
From: Shaohua Li @ 2017-04-10  4:31 UTC (permalink / raw)
  To: Sun, Ning
  Cc: Joerg Roedel, linux-kernel, Wei, Gang, hpa, mingo, kernel-team,
	srihan, Eydelberg, Alex

On Fri, Apr 07, 2017 at 09:49:52PM +0000, Sun, Ning wrote:
> Hi Shaohua,
> 
> One question, did you still see the network performance penalty when Linux kernel cmdline intel_iommu was set to off ( intel_iommu=off) ?

the boot parameter has no effect, it runs very early and set dmar_disable=1.
The tboot code (tboot_force_iommu) runs later and force dmar_disabled = 0.

Thanks,
Shaohua
 
> Thanks,
> -ning
> 
> -----Original Message-----
> From: Joerg Roedel [mailto:jroedel@suse.de] 
> Sent: Friday, April 07, 2017 3:09 AM
> To: Shaohua Li <shli@fb.com>
> Cc: linux-kernel@vger.kernel.org; Wei, Gang <gang.wei@intel.com>; hpa@linux.intel.com; mingo@kernel.org; kernel-team@fb.com; Sun, Ning <ning.sun@intel.com>; srihan@fb.com; Eydelberg, Alex <alex.eydelberg@intel.com>
> Subject: Re: [RFC] x86/tboot: add an option to disable iommu force on
> 
> On Mon, Apr 03, 2017 at 12:19:28PM -0700, Shaohua Li wrote:
> > On Wed, Mar 22, 2017 at 07:50:55AM -0400, Shaohua Li wrote:
> > > On Wed, Mar 22, 2017 at 11:49:00AM +0100, Joerg Roedel wrote:
> > > > Hi Shaohua,
> > > > 
> > > > On Tue, Mar 21, 2017 at 11:37:51AM -0700, Shaohua Li wrote:
> > > > > IOMMU harms performance signficantly when we run very fast 
> > > > > networking workloads. This is a limitation in hardware based on 
> > > > > our observation, so we'd like to disable the IOMMU force on, but 
> > > > > we do want to use TBOOT and we can sacrifice the DMA security 
> > > > > bought by IOMMU. I must admit I know nothing about TBOOT, but 
> > > > > TBOOT guys (cc-ed) think not eabling IOMMU is totally ok.
> > > > 
> > > > Can you elaborate a bit more on the setup where the IOMMU still 
> > > > harms network performance? With the recent scalability 
> > > > improvements I measured only a minimal impact on 10GBit networking.
> > > Hi,
> > > 
> > > It's 40GB networking doing XDP test. Software overhead is almost 
> > > unaware, but it's the IOTLB miss (based on our analysis) which kills 
> > > the performance. We observed the same performance issue even with 
> > > software passthrough (identity mapping), only the hardware 
> > > passthrough survives. The pps with iommu (with software passthrough) is only about ~30% of that without it.
> > 
> > Any update on this?
> 
> An explicit Ack from the tboot guys would be good to have.
> 
> 
> 	Joerg
> 

^ permalink raw reply	[flat|nested] 10+ messages in thread

* RE: [RFC] x86/tboot: add an option to disable iommu force on
  2017-04-10  4:31           ` Shaohua Li
@ 2017-04-10 21:28             ` Sun, Ning
  2017-04-24 16:50               ` Shaohua Li
  0 siblings, 1 reply; 10+ messages in thread
From: Sun, Ning @ 2017-04-10 21:28 UTC (permalink / raw)
  To: Shaohua Li
  Cc: Joerg Roedel, linux-kernel, Wei, Gang, hpa, mingo, kernel-team,
	srihan, Eydelberg, Alex

>From tboot perspective, it is ok to add the option "tboot_noforce" to Linux kernel Intel_iommu parameter for those performance hungry tboot users, so long as the users are aware of the security implication behind of this option.
 
Thanks,
-ning

-----Original Message-----
From: Shaohua Li [mailto:shli@fb.com] 
Sent: Sunday, April 09, 2017 9:31 PM
To: Sun, Ning <ning.sun@intel.com>
Cc: Joerg Roedel <jroedel@suse.de>; linux-kernel@vger.kernel.org; Wei, Gang <gang.wei@intel.com>; hpa@linux.intel.com; mingo@kernel.org; kernel-team@fb.com; srihan@fb.com; Eydelberg, Alex <alex.eydelberg@intel.com>
Subject: Re: [RFC] x86/tboot: add an option to disable iommu force on

On Fri, Apr 07, 2017 at 09:49:52PM +0000, Sun, Ning wrote:
> Hi Shaohua,
> 
> One question, did you still see the network performance penalty when Linux kernel cmdline intel_iommu was set to off ( intel_iommu=off) ?

the boot parameter has no effect, it runs very early and set dmar_disable=1.
The tboot code (tboot_force_iommu) runs later and force dmar_disabled = 0.

Thanks,
Shaohua
 
> Thanks,
> -ning
> 
> -----Original Message-----
> From: Joerg Roedel [mailto:jroedel@suse.de]
> Sent: Friday, April 07, 2017 3:09 AM
> To: Shaohua Li <shli@fb.com>
> Cc: linux-kernel@vger.kernel.org; Wei, Gang <gang.wei@intel.com>; 
> hpa@linux.intel.com; mingo@kernel.org; kernel-team@fb.com; Sun, Ning 
> <ning.sun@intel.com>; srihan@fb.com; Eydelberg, Alex 
> <alex.eydelberg@intel.com>
> Subject: Re: [RFC] x86/tboot: add an option to disable iommu force on
> 
> On Mon, Apr 03, 2017 at 12:19:28PM -0700, Shaohua Li wrote:
> > On Wed, Mar 22, 2017 at 07:50:55AM -0400, Shaohua Li wrote:
> > > On Wed, Mar 22, 2017 at 11:49:00AM +0100, Joerg Roedel wrote:
> > > > Hi Shaohua,
> > > > 
> > > > On Tue, Mar 21, 2017 at 11:37:51AM -0700, Shaohua Li wrote:
> > > > > IOMMU harms performance signficantly when we run very fast 
> > > > > networking workloads. This is a limitation in hardware based 
> > > > > on our observation, so we'd like to disable the IOMMU force 
> > > > > on, but we do want to use TBOOT and we can sacrifice the DMA 
> > > > > security bought by IOMMU. I must admit I know nothing about 
> > > > > TBOOT, but TBOOT guys (cc-ed) think not eabling IOMMU is totally ok.
> > > > 
> > > > Can you elaborate a bit more on the setup where the IOMMU still 
> > > > harms network performance? With the recent scalability 
> > > > improvements I measured only a minimal impact on 10GBit networking.
> > > Hi,
> > > 
> > > It's 40GB networking doing XDP test. Software overhead is almost 
> > > unaware, but it's the IOTLB miss (based on our analysis) which 
> > > kills the performance. We observed the same performance issue even 
> > > with software passthrough (identity mapping), only the hardware 
> > > passthrough survives. The pps with iommu (with software passthrough) is only about ~30% of that without it.
> > 
> > Any update on this?
> 
> An explicit Ack from the tboot guys would be good to have.
> 
> 
> 	Joerg
> 

^ permalink raw reply	[flat|nested] 10+ messages in thread

* Re: [RFC] x86/tboot: add an option to disable iommu force on
  2017-04-10 21:28             ` Sun, Ning
@ 2017-04-24 16:50               ` Shaohua Li
  2017-04-25 11:02                 ` Joerg Roedel
  0 siblings, 1 reply; 10+ messages in thread
From: Shaohua Li @ 2017-04-24 16:50 UTC (permalink / raw)
  To: Sun, Ning
  Cc: Joerg Roedel, linux-kernel, Wei, Gang, hpa, mingo, kernel-team,
	srihan, Eydelberg, Alex

Hi Joerg,

Is Ning's answer sufficient to justify merging the patch?

Thanks,
Shaohua


On Mon, Apr 10, 2017 at 09:28:46PM +0000, Sun, Ning wrote:
> From tboot perspective, it is ok to add the option "tboot_noforce" to Linux kernel Intel_iommu parameter for those performance hungry tboot users, so long as the users are aware of the security implication behind of this option.
>  
> Thanks,
> -ning
> 
> -----Original Message-----
> From: Shaohua Li [mailto:shli@fb.com] 
> Sent: Sunday, April 09, 2017 9:31 PM
> To: Sun, Ning <ning.sun@intel.com>
> Cc: Joerg Roedel <jroedel@suse.de>; linux-kernel@vger.kernel.org; Wei, Gang <gang.wei@intel.com>; hpa@linux.intel.com; mingo@kernel.org; kernel-team@fb.com; srihan@fb.com; Eydelberg, Alex <alex.eydelberg@intel.com>
> Subject: Re: [RFC] x86/tboot: add an option to disable iommu force on
> 
> On Fri, Apr 07, 2017 at 09:49:52PM +0000, Sun, Ning wrote:
> > Hi Shaohua,
> > 
> > One question, did you still see the network performance penalty when Linux kernel cmdline intel_iommu was set to off ( intel_iommu=off) ?
> 
> the boot parameter has no effect, it runs very early and set dmar_disable=1.
> The tboot code (tboot_force_iommu) runs later and force dmar_disabled = 0.
> 
> Thanks,
> Shaohua
>  
> > Thanks,
> > -ning
> > 
> > -----Original Message-----
> > From: Joerg Roedel [mailto:jroedel@suse.de]
> > Sent: Friday, April 07, 2017 3:09 AM
> > To: Shaohua Li <shli@fb.com>
> > Cc: linux-kernel@vger.kernel.org; Wei, Gang <gang.wei@intel.com>; 
> > hpa@linux.intel.com; mingo@kernel.org; kernel-team@fb.com; Sun, Ning 
> > <ning.sun@intel.com>; srihan@fb.com; Eydelberg, Alex 
> > <alex.eydelberg@intel.com>
> > Subject: Re: [RFC] x86/tboot: add an option to disable iommu force on
> > 
> > On Mon, Apr 03, 2017 at 12:19:28PM -0700, Shaohua Li wrote:
> > > On Wed, Mar 22, 2017 at 07:50:55AM -0400, Shaohua Li wrote:
> > > > On Wed, Mar 22, 2017 at 11:49:00AM +0100, Joerg Roedel wrote:
> > > > > Hi Shaohua,
> > > > > 
> > > > > On Tue, Mar 21, 2017 at 11:37:51AM -0700, Shaohua Li wrote:
> > > > > > IOMMU harms performance signficantly when we run very fast 
> > > > > > networking workloads. This is a limitation in hardware based 
> > > > > > on our observation, so we'd like to disable the IOMMU force 
> > > > > > on, but we do want to use TBOOT and we can sacrifice the DMA 
> > > > > > security bought by IOMMU. I must admit I know nothing about 
> > > > > > TBOOT, but TBOOT guys (cc-ed) think not eabling IOMMU is totally ok.
> > > > > 
> > > > > Can you elaborate a bit more on the setup where the IOMMU still 
> > > > > harms network performance? With the recent scalability 
> > > > > improvements I measured only a minimal impact on 10GBit networking.
> > > > Hi,
> > > > 
> > > > It's 40GB networking doing XDP test. Software overhead is almost 
> > > > unaware, but it's the IOTLB miss (based on our analysis) which 
> > > > kills the performance. We observed the same performance issue even 
> > > > with software passthrough (identity mapping), only the hardware 
> > > > passthrough survives. The pps with iommu (with software passthrough) is only about ~30% of that without it.
> > > 
> > > Any update on this?
> > 
> > An explicit Ack from the tboot guys would be good to have.
> > 
> > 
> > 	Joerg
> > 

^ permalink raw reply	[flat|nested] 10+ messages in thread

* Re: [RFC] x86/tboot: add an option to disable iommu force on
  2017-04-24 16:50               ` Shaohua Li
@ 2017-04-25 11:02                 ` Joerg Roedel
  0 siblings, 0 replies; 10+ messages in thread
From: Joerg Roedel @ 2017-04-25 11:02 UTC (permalink / raw)
  To: Shaohua Li
  Cc: Sun, Ning, linux-kernel, Wei, Gang, hpa, mingo, kernel-team,
	srihan, Eydelberg, Alex

On Mon, Apr 24, 2017 at 09:50:59AM -0700, Shaohua Li wrote:
> Hi Joerg,
> 
> Is Ning's answer sufficient to justify merging the patch?

Yes, I will take it if you repost without the RFC tag and when you add
documentation for the new command-line parameter.

I think a kernel-log message about the potential security impact also
makes sense.


	Joerg

^ permalink raw reply	[flat|nested] 10+ messages in thread

end of thread, other threads:[~2017-04-25 11:02 UTC | newest]

Thread overview: 10+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-03-21 18:37 [RFC] x86/tboot: add an option to disable iommu force on Shaohua Li
2017-03-22 10:49 ` Joerg Roedel
2017-03-22 11:50   ` Shaohua Li
2017-04-03 19:19     ` Shaohua Li
2017-04-07 10:08       ` Joerg Roedel
2017-04-07 21:49         ` Sun, Ning
2017-04-10  4:31           ` Shaohua Li
2017-04-10 21:28             ` Sun, Ning
2017-04-24 16:50               ` Shaohua Li
2017-04-25 11:02                 ` Joerg Roedel

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.