vfio/type1: Chunk contiguous reserved/invalid page mappings
We currently map invalid and reserved pages, such as often occur from
mapping MMIO regions of a VM through the IOMMU, using single pages.
There's really no reason we can't instead follow the methodology we
use for normal pages and find the largest possible physically
contiguous chunk for mapping. The only difference is that we don't
do locked memory accounting for these since they're not back by RAM.
In most applications this will be a very minor improvement, but when
graphics and GPGPU devices are in play, MMIO BARs become non-trivial.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index e6e7f15..35c9008 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -265,6 +265,7 @@
unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
bool lock_cap = capable(CAP_IPC_LOCK);
long ret, i;
+ bool rsvd;
if (!current->mm)
return -ENODEV;
@@ -273,10 +274,9 @@
if (ret)
return ret;
- if (is_invalid_reserved_pfn(*pfn_base))
- return 1;
+ rsvd = is_invalid_reserved_pfn(*pfn_base);
- if (!lock_cap && current->mm->locked_vm + 1 > limit) {
+ if (!rsvd && !lock_cap && current->mm->locked_vm + 1 > limit) {
put_pfn(*pfn_base, prot);
pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", __func__,
limit << PAGE_SHIFT);
@@ -284,7 +284,8 @@
}
if (unlikely(disable_hugepages)) {
- vfio_lock_acct(1);
+ if (!rsvd)
+ vfio_lock_acct(1);
return 1;
}
@@ -296,12 +297,14 @@
if (ret)
break;
- if (pfn != *pfn_base + i || is_invalid_reserved_pfn(pfn)) {
+ if (pfn != *pfn_base + i ||
+ rsvd != is_invalid_reserved_pfn(pfn)) {
put_pfn(pfn, prot);
break;
}
- if (!lock_cap && current->mm->locked_vm + i + 1 > limit) {
+ if (!rsvd && !lock_cap &&
+ current->mm->locked_vm + i + 1 > limit) {
put_pfn(pfn, prot);
pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
__func__, limit << PAGE_SHIFT);
@@ -309,7 +312,8 @@
}
}
- vfio_lock_acct(i);
+ if (!rsvd)
+ vfio_lock_acct(i);
return i;
}