From: Alexey Kardashevskiy <aik@ozlabs.ru>
To: qemu-devel@nongnu.org
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>,
Alex Williamson <alex.williamson@redhat.com>,
qemu-ppc@nongnu.org, David Gibson <david@gibson.dropbear.id.au>
Subject: [Qemu-devel] [PATCH qemu v14 13/18] vfio: spapr: Add SPAPR IOMMU v2 support (DMA memory preregistering)
Date: Mon, 21 Mar 2016 18:47:01 +1100 [thread overview]
Message-ID: <1458546426-26222-14-git-send-email-aik@ozlabs.ru> (raw)
In-Reply-To: <1458546426-26222-1-git-send-email-aik@ozlabs.ru>
This makes use of the new "memory registering" feature. The idea is
to provide the userspace ability to notify the host kernel about pages
which are going to be used for DMA. Having this information, the host
kernel can pin them all once per user process, do locked pages
accounting (once) and not spent time on doing that in real time with
possible failures which cannot be handled nicely in some cases.
This adds a prereg memory listener which listens on address_space_memory
and notifies a VFIO container about memory which needs to be
pinned/unpinned. VFIO MMIO regions (i.e. "skip dump" regions) are skipped.
As there is no per-IOMMU-type release() callback anymore, this stores
the IOMMU type in the container so vfio_listener_release() can device
if it needs to unregister @prereg_listener.
The feature is only enabled for SPAPR IOMMU v2. The host kernel changes
are required. Since v2 does not need/support VFIO_IOMMU_ENABLE, this does
not call it when v2 is detected and enabled.
This does not change the guest visible interface.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
Changes:
v14:
* s/free_container_exit/listener_release_exit/g
* added "if memory_region_is_iommu()" to vfio_prereg_listener_skipped_section
---
hw/vfio/Makefile.objs | 1 +
hw/vfio/common.c | 38 +++++++++---
hw/vfio/prereg.c | 137 ++++++++++++++++++++++++++++++++++++++++++
include/hw/vfio/vfio-common.h | 4 ++
trace-events | 2 +
5 files changed, 172 insertions(+), 10 deletions(-)
create mode 100644 hw/vfio/prereg.c
diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs
index ceddbb8..5800e0e 100644
--- a/hw/vfio/Makefile.objs
+++ b/hw/vfio/Makefile.objs
@@ -4,4 +4,5 @@ obj-$(CONFIG_PCI) += pci.o pci-quirks.o
obj-$(CONFIG_SOFTMMU) += platform.o
obj-$(CONFIG_SOFTMMU) += calxeda-xgmac.o
obj-$(CONFIG_SOFTMMU) += amd-xgbe.o
+obj-$(CONFIG_SOFTMMU) += prereg.o
endif
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 9587c25..a8deb16 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -493,6 +493,9 @@ static const MemoryListener vfio_memory_listener = {
static void vfio_listener_release(VFIOContainer *container)
{
memory_listener_unregister(&container->listener);
+ if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
+ memory_listener_unregister(&container->prereg_listener);
+ }
}
int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
@@ -800,8 +803,8 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
goto free_container_exit;
}
- ret = ioctl(fd, VFIO_SET_IOMMU,
- v2 ? VFIO_TYPE1v2_IOMMU : VFIO_TYPE1_IOMMU);
+ container->iommu_type = v2 ? VFIO_TYPE1v2_IOMMU : VFIO_TYPE1_IOMMU;
+ ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type);
if (ret) {
error_report("vfio: failed to set iommu for container: %m");
ret = -errno;
@@ -826,8 +829,10 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
if ((ret == 0) && (info.flags & VFIO_IOMMU_INFO_PGSIZES)) {
container->iova_pgsizes = info.iova_pgsizes;
}
- } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU)) {
+ } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU) ||
+ ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU)) {
struct vfio_iommu_spapr_tce_info info;
+ bool v2 = !!ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU);
ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd);
if (ret) {
@@ -835,7 +840,9 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
ret = -errno;
goto free_container_exit;
}
- ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU);
+ container->iommu_type =
+ v2 ? VFIO_SPAPR_TCE_v2_IOMMU : VFIO_SPAPR_TCE_IOMMU;
+ ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type);
if (ret) {
error_report("vfio: failed to set iommu for container: %m");
ret = -errno;
@@ -847,11 +854,22 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
* when container fd is closed so we do not call it explicitly
* in this file.
*/
- ret = ioctl(fd, VFIO_IOMMU_ENABLE);
- if (ret) {
- error_report("vfio: failed to enable container: %m");
- ret = -errno;
- goto free_container_exit;
+ if (!v2) {
+ ret = ioctl(fd, VFIO_IOMMU_ENABLE);
+ if (ret) {
+ error_report("vfio: failed to enable container: %m");
+ ret = -errno;
+ goto free_container_exit;
+ }
+ } else {
+ container->prereg_listener = vfio_prereg_listener;
+
+ memory_listener_register(&container->prereg_listener,
+ &address_space_memory);
+ if (container->error) {
+ error_report("vfio: RAM memory listener initialization failed for container");
+ goto listener_release_exit;
+ }
}
/*
@@ -864,7 +882,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
if (ret) {
error_report("vfio: VFIO_IOMMU_SPAPR_TCE_GET_INFO failed: %m");
ret = -errno;
- goto free_container_exit;
+ goto listener_release_exit;
}
container->min_iova = info.dma32_window_start;
container->max_iova = container->min_iova + info.dma32_window_size - 1;
diff --git a/hw/vfio/prereg.c b/hw/vfio/prereg.c
new file mode 100644
index 0000000..36c9ff5
--- /dev/null
+++ b/hw/vfio/prereg.c
@@ -0,0 +1,137 @@
+/*
+ * DMA memory preregistration
+ *
+ * Authors:
+ * Alexey Kardashevskiy <aik@ozlabs.ru>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include <sys/ioctl.h>
+#include <linux/vfio.h>
+
+#include "hw/vfio/vfio-common.h"
+#include "qemu/error-report.h"
+#include "trace.h"
+
+static bool vfio_prereg_listener_skipped_section(MemoryRegionSection *section)
+{
+ if (memory_region_is_iommu(section->mr)) {
+ error_report("Cannot possibly preregister IOMMU memory");
+ return true;
+ }
+
+ return !memory_region_is_ram(section->mr) ||
+ memory_region_is_skip_dump(section->mr);
+}
+
+static void vfio_prereg_listener_region_add(MemoryListener *listener,
+ MemoryRegionSection *section)
+{
+ VFIOContainer *container = container_of(listener, VFIOContainer,
+ prereg_listener);
+ hwaddr gpa;
+ Int128 llend;
+ int ret;
+ hwaddr page_mask = qemu_real_host_page_mask;
+ struct vfio_iommu_spapr_register_memory reg = {
+ .argsz = sizeof(reg),
+ .flags = 0,
+ };
+
+ if (vfio_prereg_listener_skipped_section(section)) {
+ trace_vfio_listener_region_add_skip(
+ section->offset_within_address_space,
+ section->offset_within_address_space +
+ int128_get64(int128_sub(section->size, int128_one())));
+ return;
+ }
+
+ if (unlikely((section->offset_within_address_space & ~page_mask) !=
+ (section->offset_within_region & ~page_mask))) {
+ error_report("%s received unaligned region", __func__);
+ return;
+ }
+
+ gpa = ROUND_UP(section->offset_within_address_space, ~page_mask + 1);
+ llend = int128_make64(section->offset_within_address_space);
+ llend = int128_add(llend, section->size);
+ llend = int128_and(llend, int128_exts64(page_mask));
+
+ g_assert(!int128_ge(int128_make64(gpa), llend));
+
+ memory_region_ref(section->mr);
+
+ reg.vaddr = (__u64) memory_region_get_ram_ptr(section->mr) +
+ section->offset_within_region +
+ (gpa - section->offset_within_address_space);
+ reg.size = int128_get64(llend) - gpa;
+
+ ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_REGISTER_MEMORY, ®);
+ trace_vfio_ram_register(reg.vaddr, reg.size, ret ? -errno : 0);
+ if (ret) {
+ /*
+ * On the initfn path, store the first error in the container so we
+ * can gracefully fail. Runtime, there's not much we can do other
+ * than throw a hardware error.
+ */
+ if (!container->initialized) {
+ if (!container->error) {
+ container->error = ret;
+ }
+ } else {
+ hw_error("vfio: Memory registering failed, unable to continue");
+ }
+ }
+}
+
+static void vfio_prereg_listener_region_del(MemoryListener *listener,
+ MemoryRegionSection *section)
+{
+ VFIOContainer *container = container_of(listener, VFIOContainer,
+ prereg_listener);
+ hwaddr gpa, end;
+ int ret;
+ hwaddr page_mask = qemu_real_host_page_mask;
+ struct vfio_iommu_spapr_register_memory reg = {
+ .argsz = sizeof(reg),
+ .flags = 0,
+ };
+
+ if (vfio_prereg_listener_skipped_section(section)) {
+ trace_vfio_listener_region_del_skip(
+ section->offset_within_address_space,
+ section->offset_within_address_space +
+ int128_get64(int128_sub(section->size, int128_one())));
+ return;
+ }
+
+ if (unlikely((section->offset_within_address_space & ~page_mask) !=
+ (section->offset_within_region & ~page_mask))) {
+ error_report("%s received unaligned region", __func__);
+ return;
+ }
+
+ gpa = ROUND_UP(section->offset_within_address_space, ~page_mask + 1);
+ end = (section->offset_within_address_space + int128_get64(section->size)) &
+ page_mask;
+
+ if (gpa >= end) {
+ return;
+ }
+
+ reg.vaddr = (__u64) memory_region_get_ram_ptr(section->mr) +
+ section->offset_within_region +
+ (gpa - section->offset_within_address_space);
+ reg.size = end - gpa;
+
+ ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY, ®);
+ trace_vfio_ram_unregister(reg.vaddr, reg.size, ret ? -errno : 0);
+}
+
+const MemoryListener vfio_prereg_listener = {
+ .region_add = vfio_prereg_listener_region_add,
+ .region_del = vfio_prereg_listener_region_del,
+};
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 5341e05..b861eec 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -73,6 +73,8 @@ typedef struct VFIOContainer {
VFIOAddressSpace *space;
int fd; /* /dev/vfio/vfio, empowered by the attached groups */
MemoryListener listener;
+ MemoryListener prereg_listener;
+ unsigned iommu_type;
int error;
bool initialized;
/*
@@ -156,4 +158,6 @@ extern QLIST_HEAD(vfio_as_head, VFIOAddressSpace) vfio_address_spaces;
int vfio_get_region_info(VFIODevice *vbasedev, int index,
struct vfio_region_info **info);
#endif
+extern const MemoryListener vfio_prereg_listener;
+
#endif /* !HW_VFIO_VFIO_COMMON_H */
diff --git a/trace-events b/trace-events
index 6a94736..cc619e1 100644
--- a/trace-events
+++ b/trace-events
@@ -1734,6 +1734,8 @@ vfio_region_mmap(const char *name, unsigned long offset, unsigned long end) "Reg
vfio_region_exit(const char *name, int index) "Device %s, region %d"
vfio_region_finalize(const char *name, int index) "Device %s, region %d"
vfio_region_mmaps_set_enabled(const char *name, bool enabled) "Region %s mmaps enabled: %d"
+vfio_ram_register(uint64_t va, uint64_t size, int ret) "va=%"PRIx64" size=%"PRIx64" ret=%d"
+vfio_ram_unregister(uint64_t va, uint64_t size, int ret) "va=%"PRIx64" size=%"PRIx64" ret=%d"
# hw/vfio/platform.c
vfio_platform_base_device_init(char *name, int groupid) "%s belongs to group #%d"
--
2.5.0.rc3
next prev parent reply other threads:[~2016-03-21 7:48 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-03-21 7:46 [Qemu-devel] [PATCH qemu v14 00/18] spapr: vfio: Enable Dynamic DMA windows (DDW) Alexey Kardashevskiy
2016-03-21 7:46 ` [Qemu-devel] [PATCH qemu v14 01/18] memory: Fix IOMMU replay base address Alexey Kardashevskiy
2016-03-22 0:49 ` David Gibson
2016-03-22 3:12 ` Alexey Kardashevskiy
2016-03-22 3:26 ` David Gibson
2016-03-22 4:28 ` Alexey Kardashevskiy
2016-03-22 4:59 ` David Gibson
2016-03-22 7:19 ` Alexey Kardashevskiy
2016-03-22 23:07 ` David Gibson
2016-03-23 10:58 ` Paolo Bonzini
2016-03-21 7:46 ` [Qemu-devel] [PATCH qemu v14 02/18] vmstate: Define VARRAY with VMS_ALLOC Alexey Kardashevskiy
2016-03-21 7:46 ` [Qemu-devel] [PATCH qemu v14 03/18] spapr_pci: Move DMA window enablement to a helper Alexey Kardashevskiy
2016-03-22 1:02 ` David Gibson
2016-03-22 3:17 ` Alexey Kardashevskiy
2016-03-22 3:28 ` David Gibson
2016-03-21 7:46 ` [Qemu-devel] [PATCH qemu v14 04/18] spapr_iommu: Move table allocation to helpers Alexey Kardashevskiy
2016-03-21 7:46 ` [Qemu-devel] [PATCH qemu v14 05/18] spapr_iommu: Introduce "enabled" state for TCE table Alexey Kardashevskiy
2016-03-22 1:11 ` David Gibson
2016-03-21 7:46 ` [Qemu-devel] [PATCH qemu v14 06/18] spapr_iommu: Finish renaming vfio_accel to need_vfio Alexey Kardashevskiy
2016-03-22 1:18 ` David Gibson
2016-03-21 7:46 ` [Qemu-devel] [PATCH qemu v14 07/18] spapr_iommu: Realloc table during migration Alexey Kardashevskiy
2016-03-22 1:23 ` David Gibson
2016-03-21 7:46 ` [Qemu-devel] [PATCH qemu v14 08/18] spapr_iommu: Migrate full state Alexey Kardashevskiy
2016-03-22 1:31 ` David Gibson
2016-03-21 7:46 ` [Qemu-devel] [PATCH qemu v14 09/18] spapr_iommu: Add root memory region Alexey Kardashevskiy
2016-03-21 7:46 ` [Qemu-devel] [PATCH qemu v14 10/18] spapr_pci: Reset DMA config on PHB reset Alexey Kardashevskiy
2016-03-21 7:46 ` [Qemu-devel] [PATCH qemu v14 11/18] memory: Add reporting of supported page sizes Alexey Kardashevskiy
2016-03-22 3:02 ` David Gibson
2016-03-21 7:47 ` [Qemu-devel] [PATCH qemu v14 12/18] vfio: Check that IOMMU MR translates to system address space Alexey Kardashevskiy
2016-03-22 3:05 ` David Gibson
2016-03-22 15:47 ` Alex Williamson
2016-03-23 0:43 ` David Gibson
2016-03-23 0:44 ` Alexey Kardashevskiy
2016-03-21 7:47 ` Alexey Kardashevskiy [this message]
2016-03-22 4:04 ` [Qemu-devel] [PATCH qemu v14 13/18] vfio: spapr: Add SPAPR IOMMU v2 support (DMA memory preregistering) David Gibson
2016-03-21 7:47 ` [Qemu-devel] [PATCH qemu v14 14/18] spapr_pci: Add and export DMA resetting helper Alexey Kardashevskiy
2016-03-21 7:47 ` [Qemu-devel] [PATCH qemu v14 15/18] vfio: Add host side IOMMU capabilities Alexey Kardashevskiy
2016-03-22 4:20 ` David Gibson
2016-03-22 6:47 ` Alexey Kardashevskiy
2016-03-21 7:47 ` [Qemu-devel] [PATCH qemu v14 16/18] spapr_iommu, vfio, memory: Notify IOMMU about starting/stopping being used by VFIO Alexey Kardashevskiy
2016-03-22 4:45 ` David Gibson
2016-03-22 6:24 ` Alexey Kardashevskiy
2016-03-22 10:22 ` David Gibson
2016-03-21 7:47 ` [Qemu-devel] [PATCH qemu v14 17/18] vfio/spapr: Use VFIO_SPAPR_TCE_v2_IOMMU Alexey Kardashevskiy
2016-03-22 5:14 ` David Gibson
2016-03-22 5:54 ` Alexey Kardashevskiy
2016-03-23 1:08 ` David Gibson
2016-03-23 2:12 ` Alexey Kardashevskiy
2016-03-23 2:53 ` David Gibson
2016-03-23 3:06 ` Alexey Kardashevskiy
2016-03-23 6:03 ` David Gibson
2016-03-24 0:03 ` Alexey Kardashevskiy
2016-03-24 9:10 ` Alexey Kardashevskiy
2016-03-29 5:30 ` David Gibson
2016-03-29 5:44 ` Alexey Kardashevskiy
2016-03-29 6:44 ` David Gibson
2016-03-21 7:47 ` [Qemu-devel] [PATCH qemu v14 18/18] spapr_pci/spapr_pci_vfio: Support Dynamic DMA Windows (DDW) Alexey Kardashevskiy
2016-03-23 2:13 ` David Gibson
2016-03-23 3:28 ` Alexey Kardashevskiy
2016-03-23 6:11 ` David Gibson
2016-03-24 2:32 ` Alexey Kardashevskiy
2016-03-29 5:22 ` David Gibson
2016-03-29 6:23 ` Alexey Kardashevskiy
2016-03-31 3:19 ` David Gibson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1458546426-26222-14-git-send-email-aik@ozlabs.ru \
--to=aik@ozlabs.ru \
--cc=alex.williamson@redhat.com \
--cc=david@gibson.dropbear.id.au \
--cc=qemu-devel@nongnu.org \
--cc=qemu-ppc@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).