Commit bfd20f1c authored by Shaohua Li's avatar Shaohua Li Committed by Joerg Roedel

x86, iommu/vt-d: Add an option to disable Intel IOMMU force on

IOMMU harms performance signficantly when we run very fast networking
workloads. 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. 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: default avatarShaohua Li <shli@fb.com>
Signed-off-by: default avatarJoerg Roedel <jroedel@suse.de>
parent 161b28aa
...@@ -1578,6 +1578,15 @@ ...@@ -1578,6 +1578,15 @@
extended tables themselves, and also PASID support. With extended tables themselves, and also PASID support. With
this option set, extended tables will not be used even this option set, extended tables will not be used even
on hardware which claims to support them. on hardware which claims to support them.
tboot_noforce [Default Off]
Do not force the Intel IOMMU enabled under tboot.
By default, tboot will force Intel IOMMU on, which
could harm performance of some high-throughput
devices like 40GBit network cards, even if identity
mapping is enabled.
Note that using this option lowers the security
provided by tboot because it makes the system
vulnerable to DMA attacks.
intel_idle.max_cstate= [KNL,HW,ACPI,X86] intel_idle.max_cstate= [KNL,HW,ACPI,X86]
0 disables intel_idle and fall back on acpi_idle. 0 disables intel_idle and fall back on acpi_idle.
......
...@@ -510,6 +510,9 @@ int tboot_force_iommu(void) ...@@ -510,6 +510,9 @@ int tboot_force_iommu(void)
if (!tboot_enabled()) if (!tboot_enabled())
return 0; return 0;
if (!intel_iommu_tboot_noforce)
return 1;
if (no_iommu || swiotlb || dmar_disabled) if (no_iommu || swiotlb || dmar_disabled)
pr_warning("Forcing Intel-IOMMU to enabled\n"); pr_warning("Forcing Intel-IOMMU to enabled\n");
......
...@@ -183,6 +183,7 @@ static int rwbf_quirk; ...@@ -183,6 +183,7 @@ static int rwbf_quirk;
* (used when kernel is launched w/ TXT) * (used when kernel is launched w/ TXT)
*/ */
static int force_on = 0; static int force_on = 0;
int intel_iommu_tboot_noforce;
/* /*
* 0: Present * 0: Present
...@@ -607,6 +608,10 @@ static int __init intel_iommu_setup(char *str) ...@@ -607,6 +608,10 @@ static int __init intel_iommu_setup(char *str)
"Intel-IOMMU: enable pre-production PASID support\n"); "Intel-IOMMU: enable pre-production PASID support\n");
intel_iommu_pasid28 = 1; intel_iommu_pasid28 = 1;
iommu_identity_mapping |= IDENTMAP_GFX; iommu_identity_mapping |= IDENTMAP_GFX;
} else if (!strncmp(str, "tboot_noforce", 13)) {
printk(KERN_INFO
"Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
intel_iommu_tboot_noforce = 1;
} }
str += strcspn(str, ","); str += strcspn(str, ",");
...@@ -4850,6 +4855,19 @@ int __init intel_iommu_init(void) ...@@ -4850,6 +4855,19 @@ int __init intel_iommu_init(void)
} }
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);
}
/* /*
* Make sure the IOMMUs are switched off, even when we * Make sure the IOMMUs are switched off, even when we
* boot into a kexec kernel and the previous kernel left * boot into a kexec kernel and the previous kernel left
......
...@@ -39,6 +39,7 @@ extern int iommu_calculate_agaw(struct intel_iommu *iommu); ...@@ -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 iommu_calculate_max_sagaw(struct intel_iommu *iommu);
extern int dmar_disabled; extern int dmar_disabled;
extern int intel_iommu_enabled; extern int intel_iommu_enabled;
extern int intel_iommu_tboot_noforce;
#else #else
static inline int iommu_calculate_agaw(struct intel_iommu *iommu) static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
{ {
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment