[PATCH v2 11/13] vfio: powerpc/spapr: Move locked_vm accounting to helpers

[Alexey Kardashevskiy]

There moves locked pages accounting to helpers.
Later they will be reused for Dynamic DMA windows (DDW).

While we are here, update the comment explaining why RLIMIT_MEMLOCK
might be required to be bigger than the guest RAM.

Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
 drivers/vfio/vfio_iommu_spapr_tce.c | 71 +++++++++++++++++++++++++++----------
 1 file changed, 53 insertions(+), 18 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c 
b/drivers/vfio/vfio_iommu_spapr_tce.c
index 1c1a9c4..c9fac97 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -29,6 +29,46 @@
 static void tce_iommu_detach_group(void *iommu_data,
                struct iommu_group *iommu_group);
 
+static long try_increment_locked_vm(struct iommu_table *tbl)
+{
+       long ret = 0, locked, lock_limit, npages;
+
+       if (!current || !current->mm)
+               return -ESRCH; /* process exited */
+
+       npages = (tbl->it_size << IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
+
+       down_write(&current->mm->mmap_sem);
+       locked = current->mm->locked_vm + npages;
+       lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+       if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
+               pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n",
+                               rlimit(RLIMIT_MEMLOCK));
+               ret = -ENOMEM;
+       } else {
+               current->mm->locked_vm += npages;
+       }
+       up_write(&current->mm->mmap_sem);
+
+       return ret;
+}
+
+static void decrement_locked_vm(struct iommu_table *tbl)
+{
+       long npages;
+
+       if (!current || !current->mm)
+               return; /* process exited */
+
+       npages = (tbl->it_size << IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
+
+       down_write(&current->mm->mmap_sem);
+       if (npages > current->mm->locked_vm)
+               npages = current->mm->locked_vm;
+       current->mm->locked_vm -= npages;
+       up_write(&current->mm->mmap_sem);
+}
+
 /*
  * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
  *
@@ -86,7 +126,6 @@ static void tce_iommu_take_ownership_notify(struct 
spapr_tce_iommu_group *data,
 static int tce_iommu_enable(struct tce_container *container)
 {
        int ret = 0;
-       unsigned long locked, lock_limit, npages;
        struct iommu_table *tbl;
        struct spapr_tce_iommu_group *data;
 
@@ -120,24 +159,23 @@ static int tce_iommu_enable(struct tce_container 
*container)
         * Also we don't have a nice way to fail on H_PUT_TCE due to ulimits,
         * that would effectively kill the guest at random points, much better
         * enforcing the limit based on the max that the guest can map.
+        *
+        * Unfortunately at the moment it counts whole tables, no matter how
+        * much memory the guest has. I.e. for 4GB guest and 4 IOMMU groups
+        * each with 2GB DMA window, 8GB will be counted here. The reason for
+        * this is that we cannot tell here the amount of RAM used by the guest
+        * as this information is only available from KVM and VFIO is
+        * KVM agnostic.
         */
        tbl = data->ops->get_table(data, 0);
        if (!tbl)
                return -ENXIO;
 
-       down_write(&current->mm->mmap_sem);
-       npages = (tbl->it_size << IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
-       locked = current->mm->locked_vm + npages;
-       lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-       if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
-               pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n",
-                               rlimit(RLIMIT_MEMLOCK));
-               ret = -ENOMEM;
-       } else {
-               current->mm->locked_vm += npages;
-               container->enabled = true;
-       }
-       up_write(&current->mm->mmap_sem);
+       ret = try_increment_locked_vm(tbl);
+       if (ret)
+               return ret;
+
+       container->enabled = true;
 
        return ret;
 }
@@ -163,10 +201,7 @@ static void tce_iommu_disable(struct tce_container 
*container)
        if (!tbl)
                return;
 
-       down_write(&current->mm->mmap_sem);
-       current->mm->locked_vm -= (tbl->it_size <<
-                       IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
-       up_write(&current->mm->mmap_sem);
+       decrement_locked_vm(tbl);
 }
 
 static void *tce_iommu_open(unsigned long arg)
-- 
2.0.0

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html