From: "Michael S. Tsirkin" <mst@redhat.com>
To: qemu-devel@nongnu.org
Cc: Peter Maydell <peter.maydell@linaro.org>,
Jay Zhou <jianjay.zhou@huawei.com>,
Igor Mammedov <imammedo@redhat.com>, Liuzhe <liuzhe13@huawei.com>
Subject: [Qemu-devel] [PULL v2 34/34] vhost: used_memslots refactoring
Date: Tue, 16 Jan 2018 19:53:11 +0200 [thread overview]
Message-ID: <1516121887-32738-35-git-send-email-mst@redhat.com> (raw)
In-Reply-To: <1516121887-32738-1-git-send-email-mst@redhat.com>
From: Jay Zhou <jianjay.zhou@huawei.com>
Used_memslots is shared by vhost kernel and user, it is equal to
dev->mem->nregions, which is correct for vhost kernel, but not for
vhost user, the latter one uses memory regions that have file
descriptor. E.g. a VM has a vhost-user NIC and 8(vhost user memslot
upper limit) memory slots, it will be failed to hotplug a new DIMM
device since vhost_has_free_slot() finds no free slot left. It
should be successful if only part of memory slots have file
descriptor, so setting used memslots for vhost-user and
vhost-kernel respectively.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Jay Zhou <jianjay.zhou@huawei.com>
Signed-off-by: Liuzhe <liuzhe13@huawei.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
include/hw/virtio/vhost-backend.h | 6 ++-
hw/virtio/vhost-backend.c | 15 +++++++-
hw/virtio/vhost-user.c | 77 ++++++++++++++++++++++++++-------------
hw/virtio/vhost.c | 13 +++----
4 files changed, 75 insertions(+), 36 deletions(-)
diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h
index 592254f..2eac224 100644
--- a/include/hw/virtio/vhost-backend.h
+++ b/include/hw/virtio/vhost-backend.h
@@ -36,7 +36,7 @@ struct vhost_iotlb_msg;
typedef int (*vhost_backend_init)(struct vhost_dev *dev, void *opaque);
typedef int (*vhost_backend_cleanup)(struct vhost_dev *dev);
-typedef int (*vhost_backend_memslots_limit)(struct vhost_dev *dev);
+typedef bool (*vhost_backend_has_free_memslots)(struct vhost_dev *dev);
typedef int (*vhost_net_set_backend_op)(struct vhost_dev *dev,
struct vhost_vring_file *file);
@@ -94,12 +94,13 @@ typedef int (*vhost_set_config_op)(struct vhost_dev *dev, const uint8_t *data,
uint32_t flags);
typedef int (*vhost_get_config_op)(struct vhost_dev *dev, uint8_t *config,
uint32_t config_len);
+typedef void (*vhost_set_used_memslots_op)(struct vhost_dev *dev);
typedef struct VhostOps {
VhostBackendType backend_type;
vhost_backend_init vhost_backend_init;
vhost_backend_cleanup vhost_backend_cleanup;
- vhost_backend_memslots_limit vhost_backend_memslots_limit;
+ vhost_backend_has_free_memslots vhost_backend_has_free_memslots;
vhost_net_set_backend_op vhost_net_set_backend;
vhost_net_set_mtu_op vhost_net_set_mtu;
vhost_scsi_set_endpoint_op vhost_scsi_set_endpoint;
@@ -130,6 +131,7 @@ typedef struct VhostOps {
vhost_send_device_iotlb_msg_op vhost_send_device_iotlb_msg;
vhost_get_config_op vhost_get_config;
vhost_set_config_op vhost_set_config;
+ vhost_set_used_memslots_op vhost_set_used_memslots;
} VhostOps;
extern const VhostOps user_ops;
diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c
index 7f09efa..59def69 100644
--- a/hw/virtio/vhost-backend.c
+++ b/hw/virtio/vhost-backend.c
@@ -15,6 +15,8 @@
#include "hw/virtio/vhost-backend.h"
#include "qemu/error-report.h"
+static unsigned int vhost_kernel_used_memslots;
+
static int vhost_kernel_call(struct vhost_dev *dev, unsigned long int request,
void *arg)
{
@@ -62,6 +64,11 @@ static int vhost_kernel_memslots_limit(struct vhost_dev *dev)
return limit;
}
+static bool vhost_kernel_has_free_memslots(struct vhost_dev *dev)
+{
+ return vhost_kernel_used_memslots < vhost_kernel_memslots_limit(dev);
+}
+
static int vhost_kernel_net_set_backend(struct vhost_dev *dev,
struct vhost_vring_file *file)
{
@@ -233,11 +240,16 @@ static void vhost_kernel_set_iotlb_callback(struct vhost_dev *dev,
qemu_set_fd_handler((uintptr_t)dev->opaque, NULL, NULL, NULL);
}
+static void vhost_kernel_set_used_memslots(struct vhost_dev *dev)
+{
+ vhost_kernel_used_memslots = dev->mem->nregions;
+}
+
static const VhostOps kernel_ops = {
.backend_type = VHOST_BACKEND_TYPE_KERNEL,
.vhost_backend_init = vhost_kernel_init,
.vhost_backend_cleanup = vhost_kernel_cleanup,
- .vhost_backend_memslots_limit = vhost_kernel_memslots_limit,
+ .vhost_backend_has_free_memslots = vhost_kernel_has_free_memslots,
.vhost_net_set_backend = vhost_kernel_net_set_backend,
.vhost_scsi_set_endpoint = vhost_kernel_scsi_set_endpoint,
.vhost_scsi_clear_endpoint = vhost_kernel_scsi_clear_endpoint,
@@ -264,6 +276,7 @@ static const VhostOps kernel_ops = {
#endif /* CONFIG_VHOST_VSOCK */
.vhost_set_iotlb_callback = vhost_kernel_set_iotlb_callback,
.vhost_send_device_iotlb_msg = vhost_kernel_send_device_iotlb_msg,
+ .vhost_set_used_memslots = vhost_kernel_set_used_memslots,
};
int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 6eb9798..f732c80 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -147,6 +147,8 @@ static VhostUserMsg m __attribute__ ((unused));
/* The version of the protocol we support */
#define VHOST_USER_VERSION (0x1)
+static bool vhost_user_free_memslots = true;
+
struct vhost_user {
CharBackend *chr;
int slave_fd;
@@ -314,12 +316,43 @@ static int vhost_user_set_log_base(struct vhost_dev *dev, uint64_t base,
return 0;
}
+static int vhost_user_prepare_msg(struct vhost_dev *dev, VhostUserMemory *mem,
+ int *fds)
+{
+ int i, fd;
+
+ vhost_user_free_memslots = true;
+ for (i = 0, mem->nregions = 0; i < dev->mem->nregions; ++i) {
+ struct vhost_memory_region *reg = dev->mem->regions + i;
+ ram_addr_t offset;
+ MemoryRegion *mr;
+
+ assert((uintptr_t)reg->userspace_addr == reg->userspace_addr);
+ mr = memory_region_from_host((void *)(uintptr_t)reg->userspace_addr,
+ &offset);
+ fd = memory_region_get_fd(mr);
+ if (fd > 0) {
+ if (mem->nregions == VHOST_MEMORY_MAX_NREGIONS) {
+ vhost_user_free_memslots = false;
+ return -1;
+ }
+
+ mem->regions[mem->nregions].userspace_addr = reg->userspace_addr;
+ mem->regions[mem->nregions].memory_size = reg->memory_size;
+ mem->regions[mem->nregions].guest_phys_addr = reg->guest_phys_addr;
+ mem->regions[mem->nregions].mmap_offset = offset;
+ fds[mem->nregions++] = fd;
+ }
+ }
+
+ return 0;
+}
+
static int vhost_user_set_mem_table(struct vhost_dev *dev,
struct vhost_memory *mem)
{
int fds[VHOST_MEMORY_MAX_NREGIONS];
- int i, fd;
- size_t fd_num = 0;
+ size_t fd_num;
bool reply_supported = virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_REPLY_ACK);
@@ -332,29 +365,12 @@ static int vhost_user_set_mem_table(struct vhost_dev *dev,
msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
}
- for (i = 0; i < dev->mem->nregions; ++i) {
- struct vhost_memory_region *reg = dev->mem->regions + i;
- ram_addr_t offset;
- MemoryRegion *mr;
-
- assert((uintptr_t)reg->userspace_addr == reg->userspace_addr);
- mr = memory_region_from_host((void *)(uintptr_t)reg->userspace_addr,
- &offset);
- fd = memory_region_get_fd(mr);
- if (fd > 0) {
- if (fd_num == VHOST_MEMORY_MAX_NREGIONS) {
- error_report("Failed preparing vhost-user memory table msg");
- return -1;
- }
- msg.payload.memory.regions[fd_num].userspace_addr = reg->userspace_addr;
- msg.payload.memory.regions[fd_num].memory_size = reg->memory_size;
- msg.payload.memory.regions[fd_num].guest_phys_addr = reg->guest_phys_addr;
- msg.payload.memory.regions[fd_num].mmap_offset = offset;
- fds[fd_num++] = fd;
- }
+ if (vhost_user_prepare_msg(dev, &msg.payload.memory, fds) < 0) {
+ error_report("Failed preparing vhost-user memory table msg");
+ return -1;
}
- msg.payload.memory.nregions = fd_num;
+ fd_num = msg.payload.memory.nregions;
if (!fd_num) {
error_report("Failed initializing vhost-user memory map, "
@@ -870,9 +886,9 @@ static int vhost_user_get_vq_index(struct vhost_dev *dev, int idx)
return idx;
}
-static int vhost_user_memslots_limit(struct vhost_dev *dev)
+static bool vhost_user_has_free_memslots(struct vhost_dev *dev)
{
- return VHOST_MEMORY_MAX_NREGIONS;
+ return vhost_user_free_memslots;
}
static bool vhost_user_requires_shm_log(struct vhost_dev *dev)
@@ -1054,11 +1070,19 @@ static int vhost_user_set_config(struct vhost_dev *dev, const uint8_t *data,
return 0;
}
+static void vhost_user_set_used_memslots(struct vhost_dev *dev)
+{
+ int fds[VHOST_MEMORY_MAX_NREGIONS];
+ VhostUserMsg msg;
+
+ vhost_user_prepare_msg(dev, &msg.payload.memory, fds);
+}
+
const VhostOps user_ops = {
.backend_type = VHOST_BACKEND_TYPE_USER,
.vhost_backend_init = vhost_user_init,
.vhost_backend_cleanup = vhost_user_cleanup,
- .vhost_backend_memslots_limit = vhost_user_memslots_limit,
+ .vhost_backend_has_free_memslots = vhost_user_has_free_memslots,
.vhost_set_log_base = vhost_user_set_log_base,
.vhost_set_mem_table = vhost_user_set_mem_table,
.vhost_set_vring_addr = vhost_user_set_vring_addr,
@@ -1082,4 +1106,5 @@ const VhostOps user_ops = {
.vhost_send_device_iotlb_msg = vhost_user_send_device_iotlb_msg,
.vhost_get_config = vhost_user_get_config,
.vhost_set_config = vhost_user_set_config,
+ .vhost_set_used_memslots = vhost_user_set_used_memslots,
};
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index e9e56c0..0043bef 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -44,20 +44,19 @@
static struct vhost_log *vhost_log;
static struct vhost_log *vhost_log_shm;
-static unsigned int used_memslots;
static QLIST_HEAD(, vhost_dev) vhost_devices =
QLIST_HEAD_INITIALIZER(vhost_devices);
bool vhost_has_free_slot(void)
{
- unsigned int slots_limit = ~0U;
struct vhost_dev *hdev;
QLIST_FOREACH(hdev, &vhost_devices, entry) {
- unsigned int r = hdev->vhost_ops->vhost_backend_memslots_limit(hdev);
- slots_limit = MIN(slots_limit, r);
+ if (!hdev->vhost_ops->vhost_backend_has_free_memslots(hdev)) {
+ return false;
+ }
}
- return slots_limit > used_memslots;
+ return true;
}
static void vhost_dev_sync_region(struct vhost_dev *dev,
@@ -612,7 +611,7 @@ static void vhost_set_memory(MemoryListener *listener,
dev->mem_changed_start_addr = MIN(dev->mem_changed_start_addr, start_addr);
dev->mem_changed_end_addr = MAX(dev->mem_changed_end_addr, start_addr + size - 1);
dev->memory_changed = true;
- used_memslots = dev->mem->nregions;
+ dev->vhost_ops->vhost_set_used_memslots(dev);
}
static bool vhost_section(MemoryRegionSection *section)
@@ -1414,7 +1413,7 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
memory_listener_register(&hdev->memory_listener, &address_space_memory);
QLIST_INSERT_HEAD(&vhost_devices, hdev, entry);
- if (used_memslots > hdev->vhost_ops->vhost_backend_memslots_limit(hdev)) {
+ if (!hdev->vhost_ops->vhost_backend_has_free_memslots(hdev)) {
error_report("vhost backend memory slots limit is less"
" than current number of present memory slots");
r = -1;
--
MST
next prev parent reply other threads:[~2018-01-16 17:53 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-16 17:46 [Qemu-devel] [PULL v2 00/34] pc, pci, virtio: features, fixes, cleanups Michael S. Tsirkin
2018-01-16 17:46 ` [Qemu-devel] [PULL v2 01/34] MAINTAINERS: Add myself as maintainer to X86 machines Michael S. Tsirkin
2018-01-16 17:47 ` [Qemu-devel] [PULL v2 02/34] vhost-user: add new vhost user messages to support virtio config space Michael S. Tsirkin
2018-01-16 17:47 ` [Qemu-devel] [PULL v2 03/34] vhost-user-blk: introduce a new vhost-user-blk host device Michael S. Tsirkin
2018-01-16 17:48 ` [Qemu-devel] [PULL v2 04/34] contrib/libvhost-user: enable virtio config space messages Michael S. Tsirkin
2018-01-16 17:48 ` [Qemu-devel] [PULL v2 05/34] contrib/vhost-user-blk: introduce a vhost-user-blk sample application Michael S. Tsirkin
2018-01-16 17:49 ` [Qemu-devel] [PULL v2 06/34] qemu: add a cleanup callback function to EventNotifier Michael S. Tsirkin
2018-01-16 17:49 ` [Qemu-devel] [PULL v2 07/34] virtio: postpone the execution of event_notifier_cleanup function Michael S. Tsirkin
2018-01-16 17:49 ` [Qemu-devel] [PULL v2 08/34] virtio: improve virtio devices initialization time Michael S. Tsirkin
2018-01-16 17:49 ` [Qemu-devel] [PULL v2 09/34] pci/shpc: Move function to generic header file Michael S. Tsirkin
2018-01-16 17:49 ` [Qemu-devel] [PULL v2 10/34] vhost-user: fix multiple queue specification Michael S. Tsirkin
2018-01-16 17:49 ` [Qemu-devel] [PULL v2 11/34] intel-iommu: Redefine macros to enable supporting 48 bit address width Michael S. Tsirkin
2018-01-16 17:49 ` [Qemu-devel] [PULL v2 12/34] intel-iommu: Extend address width to 48 bits Michael S. Tsirkin
2018-01-16 17:49 ` [Qemu-devel] [PULL v2 13/34] hw/pci-bridge: fix QEMU crash because of pcie-root-port Michael S. Tsirkin
2018-01-16 17:49 ` [Qemu-devel] [PULL v2 14/34] ACPI/unit-test: Add a testcase for RAM allocation in numa node Michael S. Tsirkin
2018-01-16 17:50 ` [Qemu-devel] [PULL v2 15/34] hw/acpi-build: Make next_base easy to follow Michael S. Tsirkin
2018-01-16 17:50 ` [Qemu-devel] [PULL v2 16/34] vhost-user-test: fix features mask Michael S. Tsirkin
2018-01-16 17:50 ` [Qemu-devel] [PULL v2 17/34] vhost-user-test: extract read-guest-mem test from main loop Michael S. Tsirkin
2018-01-16 17:50 ` [Qemu-devel] [PULL v2 18/34] vhost-user-test: setup virtqueues in all tests Michael S. Tsirkin
2018-01-16 17:51 ` [Qemu-devel] [PULL v2 19/34] vhost-user-test: make features mask an init_virtio_dev() argument Michael S. Tsirkin
2018-01-16 17:51 ` [Qemu-devel] [PULL v2 20/34] vhost-user-test: use init_virtio_dev in multiqueue test Michael S. Tsirkin
2018-01-16 17:51 ` [Qemu-devel] [PULL v2 21/34] vhost: Build temporary section list and deref after commit Michael S. Tsirkin
2018-01-16 17:51 ` [Qemu-devel] [PULL v2 22/34] vhost: Simplify ring verification checks Michael S. Tsirkin
2018-01-16 17:52 ` [Qemu-devel] [PULL v2 23/34] vhost: Merge sections added to temporary list Michael S. Tsirkin
2018-01-16 17:52 ` [Qemu-devel] [PULL v2 24/34] x86_iommu: Move machine check to x86_iommu_realize() Michael S. Tsirkin
2018-01-16 17:52 ` [Qemu-devel] [PULL v2 25/34] x86_iommu: check if machine has PCI bus Michael S. Tsirkin
2018-01-16 17:52 ` [Qemu-devel] [PULL v2 26/34] tests: acpi: move tested tables array allocation outside of test_acpi_dsdt_table() Michael S. Tsirkin
2018-01-16 17:52 ` [Qemu-devel] [PULL v2 27/34] tests: acpi: init table descriptor in test_dst_table() Michael S. Tsirkin
2018-01-16 17:52 ` [Qemu-devel] [PULL v2 28/34] tests: acpi: rename test_acpi_tables()/test_dst_table() to reflect its usage Michael S. Tsirkin
2018-01-16 17:52 ` [Qemu-devel] [PULL v2 29/34] tests: acpi: add comments to fetch_rsdt_referenced_tables/data->tables usage Michael S. Tsirkin
2018-01-16 17:53 ` [Qemu-devel] [PULL v2 30/34] vhost-user: factor out msg head and payload Michael S. Tsirkin
2018-01-16 17:53 ` [Qemu-devel] [PULL v2 31/34] vhost-user: fix misaligned access to payload Michael S. Tsirkin
2018-01-16 17:53 ` [Qemu-devel] [PULL v2 32/34] vhost: remove assertion to prevent crash Michael S. Tsirkin
2018-01-16 17:53 ` [Qemu-devel] [PULL v2 33/34] vhost: fix memslot limit check Michael S. Tsirkin
2018-01-16 17:53 ` Michael S. Tsirkin [this message]
2018-01-18 10:09 ` [Qemu-devel] [PULL v2 00/34] pc, pci, virtio: features, fixes, cleanups Peter Maydell
2018-01-18 19:30 ` Michael S. Tsirkin
2018-01-19 10:13 ` Peter Maydell
2018-01-18 20:48 ` Michael S. Tsirkin
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=1516121887-32738-35-git-send-email-mst@redhat.com \
--to=mst@redhat.com \
--cc=imammedo@redhat.com \
--cc=jianjay.zhou@huawei.com \
--cc=liuzhe13@huawei.com \
--cc=peter.maydell@linaro.org \
--cc=qemu-devel@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).