All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Gibson <david@gibson.dropbear.id.au>
To: peter.maydell@linaro.org
Cc: agraf@suse.de, alex.williamson@redhat.com, qemu-ppc@nongnu.org,
	qemu-devel@nongnu.org, benh@kernel.crashing.org, aik@ozlabs.ru,
	David Gibson <david@gibson.dropbear.id.au>
Subject: [Qemu-devel] [PULL 05/14] vfio: spapr: Add DMA memory preregistering (SPAPR IOMMU v2)
Date: Tue,  5 Jul 2016 15:10:39 +1000	[thread overview]
Message-ID: <1467695448-7780-6-git-send-email-david@gibson.dropbear.id.au> (raw)
In-Reply-To: <1467695448-7780-1-git-send-email-david@gibson.dropbear.id.au>

From: Alexey Kardashevskiy <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.

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 enforces guest RAM blocks to be host page size aligned; however
this is not new as KVM already requires memory slots to be host page
size aligned.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
[dwg: Fix compile error on 32-bit host]
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
---
 hw/vfio/Makefile.objs         |   1 +
 hw/vfio/common.c              |  40 +++++++++---
 hw/vfio/spapr.c               | 139 ++++++++++++++++++++++++++++++++++++++++++
 hw/vfio/trace-events          |   6 ++
 include/hw/vfio/vfio-common.h |   4 ++
 5 files changed, 181 insertions(+), 9 deletions(-)
 create mode 100644 hw/vfio/spapr.c

diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs
index ceddbb8..c25e32b 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) += spapr.o
 endif
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 7be638e..46381e6 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -503,6 +503,9 @@ 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);
+    }
 }
 
 static struct vfio_info_cap_header *
@@ -861,8 +864,8 @@ 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;
@@ -887,8 +890,10 @@ 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) {
@@ -896,7 +901,9 @@ 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;
@@ -908,11 +915,23 @@ 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) {
+                memory_listener_unregister(&container->prereg_listener);
+                error_report("vfio: RAM memory listener initialization failed for container");
+                goto free_container_exit;
+            }
         }
 
         /*
@@ -925,6 +944,9 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
         if (ret) {
             error_report("vfio: VFIO_IOMMU_SPAPR_TCE_GET_INFO failed: %m");
             ret = -errno;
+            if (v2) {
+                memory_listener_unregister(&container->prereg_listener);
+            }
             goto free_container_exit;
         }
         container->min_iova = info.dma32_window_start;
diff --git a/hw/vfio/spapr.c b/hw/vfio/spapr.c
new file mode 100644
index 0000000..7d64443
--- /dev/null
+++ b/hw/vfio/spapr.c
@@ -0,0 +1,139 @@
+/*
+ * 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 "cpu.h"
+#include <sys/ioctl.h>
+#include <linux/vfio.h>
+
+#include "hw/vfio/vfio-common.h"
+#include "hw/hw.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)) {
+        hw_error("Cannot possibly preregister IOMMU memory");
+    }
+
+    return !memory_region_is_ram(section->mr) ||
+            memory_region_is_skip_dump(section->mr);
+}
+
+static void *vfio_prereg_gpa_to_vaddr(MemoryRegionSection *section, hwaddr gpa)
+{
+    return memory_region_get_ram_ptr(section->mr) +
+        section->offset_within_region +
+        (gpa - section->offset_within_address_space);
+}
+
+static void vfio_prereg_listener_region_add(MemoryListener *listener,
+                                            MemoryRegionSection *section)
+{
+    VFIOContainer *container = container_of(listener, VFIOContainer,
+                                            prereg_listener);
+    const hwaddr gpa = section->offset_within_address_space;
+    hwaddr 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_prereg_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) ||
+                 (int128_get64(section->size) & ~page_mask))) {
+        error_report("%s received unaligned region", __func__);
+        return;
+    }
+
+    end = section->offset_within_address_space + int128_get64(section->size);
+    if (gpa >= end) {
+        return;
+    }
+
+    memory_region_ref(section->mr);
+
+    reg.vaddr = (uintptr_t) vfio_prereg_gpa_to_vaddr(section, gpa);
+    reg.size = end - gpa;
+
+    ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_REGISTER_MEMORY, &reg);
+    trace_vfio_prereg_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);
+    const hwaddr gpa = section->offset_within_address_space;
+    hwaddr 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_prereg_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) ||
+                 (int128_get64(section->size) & ~page_mask))) {
+        error_report("%s received unaligned region", __func__);
+        return;
+    }
+
+    end = section->offset_within_address_space + int128_get64(section->size);
+    if (gpa >= end) {
+        return;
+    }
+
+    reg.vaddr = (uintptr_t) vfio_prereg_gpa_to_vaddr(section, gpa);
+    reg.size = end - gpa;
+
+    ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY, &reg);
+    trace_vfio_prereg_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/hw/vfio/trace-events b/hw/vfio/trace-events
index a768fb5..0b02a3b 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -115,3 +115,9 @@ vfio_platform_populate_interrupts(int pin, int count, int flags) "- IRQ index %d
 vfio_intp_interrupt_set_pending(int index) "irq %d is set PENDING"
 vfio_platform_start_level_irqfd_injection(int index, int fd, int resamplefd) "IRQ index=%d, fd = %d, resamplefd = %d"
 vfio_platform_start_edge_irqfd_injection(int index, int fd) "IRQ index=%d, fd = %d"
+
+# hw/vfio/spapr.c
+vfio_prereg_listener_region_add_skip(uint64_t start, uint64_t end) "%"PRIx64" - %"PRIx64
+vfio_prereg_listener_region_del_skip(uint64_t start, uint64_t end) "%"PRIx64" - %"PRIx64
+vfio_prereg_register(uint64_t va, uint64_t size, int ret) "va=%"PRIx64" size=%"PRIx64" ret=%d"
+vfio_prereg_unregister(uint64_t va, uint64_t size, int ret) "va=%"PRIx64" size=%"PRIx64" ret=%d"
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 0610377..405c3b2 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;
     /*
@@ -158,4 +160,6 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index,
 int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
                              uint32_t subtype, struct vfio_region_info **info);
 #endif
+extern const MemoryListener vfio_prereg_listener;
+
 #endif /* !HW_VFIO_VFIO_COMMON_H */
-- 
2.7.4

  parent reply	other threads:[~2016-07-05  5:09 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-07-05  5:10 [Qemu-devel] [PULL 00/14] ppc-for-2.7 queue 20160705 David Gibson
2016-07-05  5:10 ` [Qemu-devel] [PULL 01/14] ppc: Fix xsrdpi, xvrdpi and xvrspi rounding David Gibson
2016-07-05  5:10 ` [Qemu-devel] [PULL 02/14] spapr: Ensure thread0 of CPU core is always realized first David Gibson
2016-07-05  5:10 ` [Qemu-devel] [PULL 03/14] ppc: simplify max_smt initialization in ppc_cpu_realizefn() David Gibson
2016-07-05  5:10 ` [Qemu-devel] [PULL 04/14] spapr_iommu: Realloc guest visible TCE table when starting/stopping listening David Gibson
2016-07-05  5:10 ` David Gibson [this message]
2016-07-05  5:10 ` [Qemu-devel] [PULL 06/14] vfio: Add host side DMA window capabilities David Gibson
2016-07-05  5:10 ` [Qemu-devel] [PULL 07/14] vfio/spapr: Create DMA window dynamically (SPAPR IOMMU v2) David Gibson
2016-07-05  5:10 ` [Qemu-devel] [PULL 08/14] spapr_pci/spapr_pci_vfio: Support Dynamic DMA Windows (DDW) David Gibson
2016-07-05  5:10 ` [Qemu-devel] [PULL 09/14] ppc: simplify ppc_hash64_hpte_page_shift_noslb() David Gibson
2016-07-05  5:10 ` [Qemu-devel] [PULL 10/14] target-ppc: Correct page size decoding in ppc_hash64_pteg_search() David Gibson
2016-07-05  5:10 ` [Qemu-devel] [PULL 11/14] target-ppc: Simplify HPTE matching David Gibson
2016-07-05  5:10 ` [Qemu-devel] [PULL 12/14] target-ppc: Return page shift from PTEG search David Gibson
2016-07-05  5:10 ` [Qemu-devel] [PULL 13/14] ppc/hash64: Add proper real mode translation support David Gibson
2016-07-05  5:10 ` [Qemu-devel] [PULL 14/14] ppc/hash64: Fix support for LPCR:ISL David Gibson
2016-07-05  5:12   ` Benjamin Herrenschmidt
2016-07-05  5:16     ` David Gibson
2016-07-05  5:32 ` [Qemu-devel] [PULL 00/14] ppc-for-2.7 queue 20160705 David Gibson
2016-07-05  5:36   ` Benjamin Herrenschmidt
2016-07-05  5:31 [Qemu-devel] [PULL 00/14] ppc-for-2.7 queue 20160705 (v2) David Gibson
2016-07-05  5:31 ` [Qemu-devel] [PULL 05/14] vfio: spapr: Add DMA memory preregistering (SPAPR IOMMU v2) 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=1467695448-7780-6-git-send-email-david@gibson.dropbear.id.au \
    --to=david@gibson.dropbear.id.au \
    --cc=agraf@suse.de \
    --cc=aik@ozlabs.ru \
    --cc=alex.williamson@redhat.com \
    --cc=benh@kernel.crashing.org \
    --cc=peter.maydell@linaro.org \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.