From: Nathan Chen<[email protected]>
Implement the IOMMU_OPTION_RLIMIT_MODE
ioctl to set per-process memory accounting for
iommufd. This prevents ENOMEM errors from the
default per-user memory accounting when multiple
VMs under the libvirt-qemu user have their pinned
memory summed and checked against a per-process
RLIMIT_MEMLOCK limit.
Signed-off-by: Nathan Chen<[email protected]>
---
meson.build | 1 +
po/POTFILES | 1 +
src/libvirt_private.syms | 3 ++
src/util/meson.build | 1 +
src/util/viriommufd.c | 111 +++++++++++++++++++++++++++++++++++++++
src/util/viriommufd.h | 25 +++++++++
6 files changed, 142 insertions(+)
create mode 100644 src/util/viriommufd.c
create mode 100644 src/util/viriommufd.h
diff --git a/meson.build b/meson.build
index 964d1fa4e1..a6db70f13e 100644
--- a/meson.build
+++ b/meson.build
@@ -732,6 +732,7 @@ headers = [
'ifaddrs.h',
'libtasn1.h',
'linux/kvm.h',
+ 'linux/iommufd.h',
'mntent.h',
'net/ethernet.h',
'net/if.h',
diff --git a/po/POTFILES b/po/POTFILES
index f0aad35c8c..c78d2b8000 100644
--- a/po/POTFILES
+++ b/po/POTFILES
@@ -303,6 +303,7 @@ src/util/virhostuptime.c
src/util/viridentity.c
src/util/virinhibitor.c
src/util/virinitctl.c
+src/util/viriommufd.c
src/util/viriscsi.c
src/util/virjson.c
src/util/virlease.c
diff --git a/src/libvirt_private.syms b/src/libvirt_private.syms
index 6bffd2eb6d..7fa76a1ec3 100644
--- a/src/libvirt_private.syms
+++ b/src/libvirt_private.syms
@@ -2646,6 +2646,9 @@ virInhibitorRelease;
virInitctlFifos;
virInitctlSetRunLevel;
+# util/viriommufd.h
+virIOMMUFDSetRLimitMode;
+
# util/viriscsi.h
virISCSIConnectionLogin;
virISCSIConnectionLogout;
diff --git a/src/util/meson.build b/src/util/meson.build
index 4950a795cc..9fb0aa0fe7 100644
--- a/src/util/meson.build
+++ b/src/util/meson.build
@@ -46,6 +46,7 @@ util_sources = [
'viridentity.c',
'virinhibitor.c',
'virinitctl.c',
+ 'viriommufd.c',
'viriscsi.c',
'virjson.c',
'virkeycode.c',
diff --git a/src/util/viriommufd.c b/src/util/viriommufd.c
new file mode 100644
index 0000000000..225c76f4b2
--- /dev/null
+++ b/src/util/viriommufd.c
@@ -0,0 +1,111 @@
+#include <config.h>
+
+#include "viriommufd.h"
+#include "virlog.h"
+#include "virerror.h"
+#include "virfile.h"
+
+#ifdef __linux__
+
+# include <sys/ioctl.h>
+# include <linux/types.h>
+
+# ifdef HAVE_LINUX_IOMMUFD_H
+# include <linux/iommufd.h>
+# endif
+
+# define VIR_FROM_THIS VIR_FROM_NONE
+
+VIR_LOG_INIT("util.iommufd");
+
+# ifndef IOMMU_OPTION
+
+enum iommufd_option {
+ IOMMU_OPTION_RLIMIT_MODE = 0,
+ IOMMU_OPTION_HUGE_PAGES = 1,
+};
+
+enum iommufd_option_ops {
+ IOMMU_OPTION_OP_SET = 0,
+ IOMMU_OPTION_OP_GET = 1,
+};
+
+struct iommu_option {
+ __u32 size;
+ __u32 option_id;
+ __u16 op;
+ __u16 __reserved;
+ __u32 object_id;
+ __aligned_u64 val64;
+};
+
+# define IOMMUFD_TYPE (';')
+# define IOMMUFD_CMD_OPTION 0x87
+# define IOMMU_OPTION _IO(IOMMUFD_TYPE, IOMMUFD_CMD_OPTION)
+
+# endif
+
+/**
+ * virIOMMUFDSetRLimitMode:
+ * @fd: iommufd file descriptor
+ * @processAccounting: true for per-process, false for per-user
+ *
+ * Set RLIMIT_MEMLOCK accounting mode for the iommufd.
+ *
+ * Returns: 0 on success, -1 on error
+ */
+int
+virIOMMUFDSetRLimitMode(int fd, bool processAccounting)
+{
+ struct iommu_option option = {
+ .size = sizeof(struct iommu_option),
+ .option_id = IOMMU_OPTION_RLIMIT_MODE,
+ .op = IOMMU_OPTION_OP_SET,
+ .__reserved = 0,
+ .object_id = 0,
+ .val64 = processAccounting ? 1 : 0,
+ };
+
+ if (ioctl(fd, IOMMU_OPTION, &option) < 0) {
+ switch (errno) {
+ case ENOTTY:
+ VIR_WARN("IOMMU_OPTION ioctl not supported");
+ return 0;
+
+ case EOPNOTSUPP:
+ VIR_WARN("IOMMU_OPTION_RLIMIT_MODE not supported by kernel");
+ return 0;
+
+ case EINVAL:
+ virReportSystemError(errno, "%s",
+ _("invalid iommufd option parameters"));
+ return -1;
+
+ case EPERM:
+ VIR_WARN("Permission denied for IOMMU_OPTION ioctl. "
+ "Per-user-based memory accounting to be used by
default.");
+ return 0;
+
+ default:
+ virReportSystemError(errno, "%s",
+ _("failed to set iommufd option"));
+ return -1;
+ }
+ }