summaryrefslogtreecommitdiffstats
path: root/hw/virtio
diff options
context:
space:
mode:
Diffstat (limited to 'hw/virtio')
-rw-r--r--hw/virtio/trace-events16
-rw-r--r--hw/virtio/vhost-user.c411
-rw-r--r--hw/virtio/vhost.c66
3 files changed, 478 insertions, 15 deletions
diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
index 742ff0f90b..1422ff03ab 100644
--- a/hw/virtio/trace-events
+++ b/hw/virtio/trace-events
@@ -3,9 +3,23 @@
# hw/virtio/vhost.c
vhost_commit(bool started, bool changed) "Started: %d Changed: %d"
vhost_region_add_section(const char *name, uint64_t gpa, uint64_t size, uint64_t host) "%s: 0x%"PRIx64"+0x%"PRIx64" @ 0x%"PRIx64
-vhost_region_add_section_abut(const char *name, uint64_t new_size) "%s: 0x%"PRIx64
+vhost_region_add_section_merge(const char *name, uint64_t new_size, uint64_t gpa, uint64_t owr) "%s: size: 0x%"PRIx64 " gpa: 0x%"PRIx64 " owr: 0x%"PRIx64
+vhost_region_add_section_aligned(const char *name, uint64_t gpa, uint64_t size, uint64_t host) "%s: 0x%"PRIx64"+0x%"PRIx64" @ 0x%"PRIx64
vhost_section(const char *name, int r) "%s:%d"
+# hw/virtio/vhost-user.c
+vhost_user_postcopy_end_entry(void) ""
+vhost_user_postcopy_end_exit(void) ""
+vhost_user_postcopy_fault_handler(const char *name, uint64_t fault_address, int nregions) "%s: @0x%"PRIx64" nregions:%d"
+vhost_user_postcopy_fault_handler_loop(int i, uint64_t client_base, uint64_t size) "%d: client 0x%"PRIx64" +0x%"PRIx64
+vhost_user_postcopy_fault_handler_found(int i, uint64_t region_offset, uint64_t rb_offset) "%d: region_offset: 0x%"PRIx64" rb_offset:0x%"PRIx64
+vhost_user_postcopy_listen(void) ""
+vhost_user_set_mem_table_postcopy(uint64_t client_addr, uint64_t qhva, int reply_i, int region_i) "client:0x%"PRIx64" for hva: 0x%"PRIx64" reply %d region %d"
+vhost_user_set_mem_table_withfd(int index, const char *name, uint64_t memory_size, uint64_t guest_phys_addr, uint64_t userspace_addr, uint64_t offset) "%d:%s: size:0x%"PRIx64" GPA:0x%"PRIx64" QVA/userspace:0x%"PRIx64" RB offset:0x%"PRIx64
+vhost_user_postcopy_waker(const char *rb, uint64_t rb_offset) "%s + 0x%"PRIx64
+vhost_user_postcopy_waker_found(uint64_t client_addr) "0x%"PRIx64
+vhost_user_postcopy_waker_nomatch(const char *rb, uint64_t rb_offset) "%s + 0x%"PRIx64
+
# hw/virtio/virtio.c
virtqueue_alloc_element(void *elem, size_t sz, unsigned in_num, unsigned out_num) "elem %p size %zd in_num %u out_num %u"
virtqueue_fill(void *vq, const void *elem, unsigned int len, unsigned int idx) "vq %p elem %p len %u idx %u"
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 41ff5cff41..44aea5c0a8 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -18,11 +18,15 @@
#include "qemu/error-report.h"
#include "qemu/sockets.h"
#include "sysemu/cryptodev.h"
+#include "migration/migration.h"
+#include "migration/postcopy-ram.h"
+#include "trace.h"
#include <sys/ioctl.h>
#include <sys/socket.h>
#include <sys/un.h>
#include <linux/vhost.h>
+#include <linux/userfaultfd.h>
#define VHOST_MEMORY_MAX_NREGIONS 8
#define VHOST_USER_F_PROTOCOL_FEATURES 30
@@ -41,7 +45,7 @@ enum VhostUserProtocolFeature {
VHOST_USER_PROTOCOL_F_SLAVE_REQ = 5,
VHOST_USER_PROTOCOL_F_CROSS_ENDIAN = 6,
VHOST_USER_PROTOCOL_F_CRYPTO_SESSION = 7,
-
+ VHOST_USER_PROTOCOL_F_PAGEFAULT = 8,
VHOST_USER_PROTOCOL_F_MAX
};
@@ -76,6 +80,9 @@ typedef enum VhostUserRequest {
VHOST_USER_SET_CONFIG = 25,
VHOST_USER_CREATE_CRYPTO_SESSION = 26,
VHOST_USER_CLOSE_CRYPTO_SESSION = 27,
+ VHOST_USER_POSTCOPY_ADVISE = 28,
+ VHOST_USER_POSTCOPY_LISTEN = 29,
+ VHOST_USER_POSTCOPY_END = 30,
VHOST_USER_MAX
} VhostUserRequest;
@@ -164,8 +171,23 @@ static VhostUserMsg m __attribute__ ((unused));
#define VHOST_USER_VERSION (0x1)
struct vhost_user {
+ struct vhost_dev *dev;
CharBackend *chr;
int slave_fd;
+ NotifierWithReturn postcopy_notifier;
+ struct PostCopyFD postcopy_fd;
+ uint64_t postcopy_client_bases[VHOST_MEMORY_MAX_NREGIONS];
+ /* Length of the region_rb and region_rb_offset arrays */
+ size_t region_rb_len;
+ /* RAMBlock associated with a given region */
+ RAMBlock **region_rb;
+ /* The offset from the start of the RAMBlock to the start of the
+ * vhost region.
+ */
+ ram_addr_t *region_rb_offset;
+
+ /* True once we've entered postcopy_listen */
+ bool postcopy_listen;
};
static bool ioeventfd_enabled(void)
@@ -330,14 +352,167 @@ static int vhost_user_set_log_base(struct vhost_dev *dev, uint64_t base,
return 0;
}
+static int vhost_user_set_mem_table_postcopy(struct vhost_dev *dev,
+ struct vhost_memory *mem)
+{
+ struct vhost_user *u = dev->opaque;
+ int fds[VHOST_MEMORY_MAX_NREGIONS];
+ int i, fd;
+ size_t fd_num = 0;
+ bool reply_supported = virtio_has_feature(dev->protocol_features,
+ VHOST_USER_PROTOCOL_F_REPLY_ACK);
+ VhostUserMsg msg_reply;
+ int region_i, msg_i;
+
+ VhostUserMsg msg = {
+ .hdr.request = VHOST_USER_SET_MEM_TABLE,
+ .hdr.flags = VHOST_USER_VERSION,
+ };
+
+ if (reply_supported) {
+ msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
+ }
+
+ if (u->region_rb_len < dev->mem->nregions) {
+ u->region_rb = g_renew(RAMBlock*, u->region_rb, dev->mem->nregions);
+ u->region_rb_offset = g_renew(ram_addr_t, u->region_rb_offset,
+ dev->mem->nregions);
+ memset(&(u->region_rb[u->region_rb_len]), '\0',
+ sizeof(RAMBlock *) * (dev->mem->nregions - u->region_rb_len));
+ memset(&(u->region_rb_offset[u->region_rb_len]), '\0',
+ sizeof(ram_addr_t) * (dev->mem->nregions - u->region_rb_len));
+ u->region_rb_len = dev->mem->nregions;
+ }
+
+ 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) {
+ trace_vhost_user_set_mem_table_withfd(fd_num, mr->name,
+ reg->memory_size,
+ reg->guest_phys_addr,
+ reg->userspace_addr, offset);
+ u->region_rb_offset[i] = offset;
+ u->region_rb[i] = mr->ram_block;
+ 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;
+ assert(fd_num < VHOST_MEMORY_MAX_NREGIONS);
+ fds[fd_num++] = fd;
+ } else {
+ u->region_rb_offset[i] = 0;
+ u->region_rb[i] = NULL;
+ }
+ }
+
+ msg.payload.memory.nregions = fd_num;
+
+ if (!fd_num) {
+ error_report("Failed initializing vhost-user memory map, "
+ "consider using -object memory-backend-file share=on");
+ return -1;
+ }
+
+ msg.hdr.size = sizeof(msg.payload.memory.nregions);
+ msg.hdr.size += sizeof(msg.payload.memory.padding);
+ msg.hdr.size += fd_num * sizeof(VhostUserMemoryRegion);
+
+ if (vhost_user_write(dev, &msg, fds, fd_num) < 0) {
+ return -1;
+ }
+
+ if (vhost_user_read(dev, &msg_reply) < 0) {
+ return -1;
+ }
+
+ if (msg_reply.hdr.request != VHOST_USER_SET_MEM_TABLE) {
+ error_report("%s: Received unexpected msg type."
+ "Expected %d received %d", __func__,
+ VHOST_USER_SET_MEM_TABLE, msg_reply.hdr.request);
+ return -1;
+ }
+ /* We're using the same structure, just reusing one of the
+ * fields, so it should be the same size.
+ */
+ if (msg_reply.hdr.size != msg.hdr.size) {
+ error_report("%s: Unexpected size for postcopy reply "
+ "%d vs %d", __func__, msg_reply.hdr.size, msg.hdr.size);
+ return -1;
+ }
+
+ memset(u->postcopy_client_bases, 0,
+ sizeof(uint64_t) * VHOST_MEMORY_MAX_NREGIONS);
+
+ /* They're in the same order as the regions that were sent
+ * but some of the regions were skipped (above) if they
+ * didn't have fd's
+ */
+ for (msg_i = 0, region_i = 0;
+ region_i < dev->mem->nregions;
+ region_i++) {
+ if (msg_i < fd_num &&
+ msg_reply.payload.memory.regions[msg_i].guest_phys_addr ==
+ dev->mem->regions[region_i].guest_phys_addr) {
+ u->postcopy_client_bases[region_i] =
+ msg_reply.payload.memory.regions[msg_i].userspace_addr;
+ trace_vhost_user_set_mem_table_postcopy(
+ msg_reply.payload.memory.regions[msg_i].userspace_addr,
+ msg.payload.memory.regions[msg_i].userspace_addr,
+ msg_i, region_i);
+ msg_i++;
+ }
+ }
+ if (msg_i != fd_num) {
+ error_report("%s: postcopy reply not fully consumed "
+ "%d vs %zd",
+ __func__, msg_i, fd_num);
+ return -1;
+ }
+ /* Now we've registered this with the postcopy code, we ack to the client,
+ * because now we're in the position to be able to deal with any faults
+ * it generates.
+ */
+ /* TODO: Use this for failure cases as well with a bad value */
+ msg.hdr.size = sizeof(msg.payload.u64);
+ msg.payload.u64 = 0; /* OK */
+ if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
+ return -1;
+ }
+
+ if (reply_supported) {
+ return process_message_reply(dev, &msg);
+ }
+
+ return 0;
+}
+
static int vhost_user_set_mem_table(struct vhost_dev *dev,
struct vhost_memory *mem)
{
+ struct vhost_user *u = dev->opaque;
int fds[VHOST_MEMORY_MAX_NREGIONS];
int i, fd;
size_t fd_num = 0;
+ bool do_postcopy = u->postcopy_listen && u->postcopy_fd.handler;
bool reply_supported = virtio_has_feature(dev->protocol_features,
- VHOST_USER_PROTOCOL_F_REPLY_ACK);
+ VHOST_USER_PROTOCOL_F_REPLY_ACK) &&
+ !do_postcopy;
+
+ if (do_postcopy) {
+ /* Postcopy has enough differences that it's best done in it's own
+ * version
+ */
+ return vhost_user_set_mem_table_postcopy(dev, mem);
+ }
VhostUserMsg msg = {
.hdr.request = VHOST_USER_SET_MEM_TABLE,
@@ -362,9 +537,11 @@ static int vhost_user_set_mem_table(struct vhost_dev *dev,
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].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].guest_phys_addr =
+ reg->guest_phys_addr;
msg.payload.memory.regions[fd_num].mmap_offset = offset;
fds[fd_num++] = fd;
}
@@ -791,6 +968,219 @@ out:
return ret;
}
+/*
+ * Called back from the postcopy fault thread when a fault is received on our
+ * ufd.
+ * TODO: This is Linux specific
+ */
+static int vhost_user_postcopy_fault_handler(struct PostCopyFD *pcfd,
+ void *ufd)
+{
+ struct vhost_dev *dev = pcfd->data;
+ struct vhost_user *u = dev->opaque;
+ struct uffd_msg *msg = ufd;
+ uint64_t faultaddr = msg->arg.pagefault.address;
+ RAMBlock *rb = NULL;
+ uint64_t rb_offset;
+ int i;
+
+ trace_vhost_user_postcopy_fault_handler(pcfd->idstr, faultaddr,
+ dev->mem->nregions);
+ for (i = 0; i < MIN(dev->mem->nregions, u->region_rb_len); i++) {
+ trace_vhost_user_postcopy_fault_handler_loop(i,
+ u->postcopy_client_bases[i], dev->mem->regions[i].memory_size);
+ if (faultaddr >= u->postcopy_client_bases[i]) {
+ /* Ofset of the fault address in the vhost region */
+ uint64_t region_offset = faultaddr - u->postcopy_client_bases[i];
+ if (region_offset < dev->mem->regions[i].memory_size) {
+ rb_offset = region_offset + u->region_rb_offset[i];
+ trace_vhost_user_postcopy_fault_handler_found(i,
+ region_offset, rb_offset);
+ rb = u->region_rb[i];
+ return postcopy_request_shared_page(pcfd, rb, faultaddr,
+ rb_offset);
+ }
+ }
+ }
+ error_report("%s: Failed to find region for fault %" PRIx64,
+ __func__, faultaddr);
+ return -1;
+}
+
+static int vhost_user_postcopy_waker(struct PostCopyFD *pcfd, RAMBlock *rb,
+ uint64_t offset)
+{
+ struct vhost_dev *dev = pcfd->data;
+ struct vhost_user *u = dev->opaque;
+ int i;
+
+ trace_vhost_user_postcopy_waker(qemu_ram_get_idstr(rb), offset);
+
+ if (!u) {
+ return 0;
+ }
+ /* Translate the offset into an address in the clients address space */
+ for (i = 0; i < MIN(dev->mem->nregions, u->region_rb_len); i++) {
+ if (u->region_rb[i] == rb &&
+ offset >= u->region_rb_offset[i] &&
+ offset < (u->region_rb_offset[i] +
+ dev->mem->regions[i].memory_size)) {
+ uint64_t client_addr = (offset - u->region_rb_offset[i]) +
+ u->postcopy_client_bases[i];
+ trace_vhost_user_postcopy_waker_found(client_addr);
+ return postcopy_wake_shared(pcfd, client_addr, rb);
+ }
+ }
+
+ trace_vhost_user_postcopy_waker_nomatch(qemu_ram_get_idstr(rb), offset);
+ return 0;
+}
+
+/*
+ * Called at the start of an inbound postcopy on reception of the
+ * 'advise' command.
+ */
+static int vhost_user_postcopy_advise(struct vhost_dev *dev, Error **errp)
+{
+ struct vhost_user *u = dev->opaque;
+ CharBackend *chr = u->chr;
+ int ufd;
+ VhostUserMsg msg = {
+ .hdr.request = VHOST_USER_POSTCOPY_ADVISE,
+ .hdr.flags = VHOST_USER_VERSION,
+ };
+
+ if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
+ error_setg(errp, "Failed to send postcopy_advise to vhost");
+ return -1;
+ }
+
+ if (vhost_user_read(dev, &msg) < 0) {
+ error_setg(errp, "Failed to get postcopy_advise reply from vhost");
+ return -1;
+ }
+
+ if (msg.hdr.request != VHOST_USER_POSTCOPY_ADVISE) {
+ error_setg(errp, "Unexpected msg type. Expected %d received %d",
+ VHOST_USER_POSTCOPY_ADVISE, msg.hdr.request);
+ return -1;
+ }
+
+ if (msg.hdr.size) {
+ error_setg(errp, "Received bad msg size.");
+ return -1;
+ }
+ ufd = qemu_chr_fe_get_msgfd(chr);
+ if (ufd < 0) {
+ error_setg(errp, "%s: Failed to get ufd", __func__);
+ return -1;
+ }
+ fcntl(ufd, F_SETFL, O_NONBLOCK);
+
+ /* register ufd with userfault thread */
+ u->postcopy_fd.fd = ufd;
+ u->postcopy_fd.data = dev;
+ u->postcopy_fd.handler = vhost_user_postcopy_fault_handler;
+ u->postcopy_fd.waker = vhost_user_postcopy_waker;
+ u->postcopy_fd.idstr = "vhost-user"; /* Need to find unique name */
+ postcopy_register_shared_ufd(&u->postcopy_fd);
+ return 0;
+}
+
+/*
+ * Called at the switch to postcopy on reception of the 'listen' command.
+ */
+static int vhost_user_postcopy_listen(struct vhost_dev *dev, Error **errp)
+{
+ struct vhost_user *u = dev->opaque;
+ int ret;
+ VhostUserMsg msg = {
+ .hdr.request = VHOST_USER_POSTCOPY_LISTEN,
+ .hdr.flags = VHOST_USER_VERSION | VHOST_USER_NEED_REPLY_MASK,
+ };
+ u->postcopy_listen = true;
+ trace_vhost_user_postcopy_listen();
+ if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
+ error_setg(errp, "Failed to send postcopy_listen to vhost");
+ return -1;
+ }
+
+ ret = process_message_reply(dev, &msg);
+ if (ret) {
+ error_setg(errp, "Failed to receive reply to postcopy_listen");
+ return ret;
+ }
+
+ return 0;
+}
+
+/*
+ * Called at the end of postcopy
+ */
+static int vhost_user_postcopy_end(struct vhost_dev *dev, Error **errp)
+{
+ VhostUserMsg msg = {
+ .hdr.request = VHOST_USER_POSTCOPY_END,
+ .hdr.flags = VHOST_USER_VERSION | VHOST_USER_NEED_REPLY_MASK,
+ };
+ int ret;
+ struct vhost_user *u = dev->opaque;
+
+ trace_vhost_user_postcopy_end_entry();
+ if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
+ error_setg(errp, "Failed to send postcopy_end to vhost");
+ return -1;
+ }
+
+ ret = process_message_reply(dev, &msg);
+ if (ret) {
+ error_setg(errp, "Failed to receive reply to postcopy_end");
+ return ret;
+ }
+ postcopy_unregister_shared_ufd(&u->postcopy_fd);
+ u->postcopy_fd.handler = NULL;
+
+ trace_vhost_user_postcopy_end_exit();
+
+ return 0;
+}
+
+static int vhost_user_postcopy_notifier(NotifierWithReturn *notifier,
+ void *opaque)
+{
+ struct PostcopyNotifyData *pnd = opaque;
+ struct vhost_user *u = container_of(notifier, struct vhost_user,
+ postcopy_notifier);
+ struct vhost_dev *dev = u->dev;
+
+ switch (pnd->reason) {
+ case POSTCOPY_NOTIFY_PROBE:
+ if (!virtio_has_feature(dev->protocol_features,
+ VHOST_USER_PROTOCOL_F_PAGEFAULT)) {
+ /* TODO: Get the device name into this error somehow */
+ error_setg(pnd->errp,
+ "vhost-user backend not capable of postcopy");
+ return -ENOENT;
+ }
+ break;
+
+ case POSTCOPY_NOTIFY_INBOUND_ADVISE:
+ return vhost_user_postcopy_advise(dev, pnd->errp);
+
+ case POSTCOPY_NOTIFY_INBOUND_LISTEN:
+ return vhost_user_postcopy_listen(dev, pnd->errp);
+
+ case POSTCOPY_NOTIFY_INBOUND_END:
+ return vhost_user_postcopy_end(dev, pnd->errp);
+
+ default:
+ /* We ignore notifications we don't know */
+ break;
+ }
+
+ return 0;
+}
+
static int vhost_user_init(struct vhost_dev *dev, void *opaque)
{
uint64_t features, protocol_features;
@@ -802,6 +1192,7 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
u = g_new0(struct vhost_user, 1);
u->chr = opaque;
u->slave_fd = -1;
+ u->dev = dev;
dev->opaque = u;
err = vhost_user_get_features(dev, &features);
@@ -858,6 +1249,9 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
return err;
}
+ u->postcopy_notifier.notify = vhost_user_postcopy_notifier;
+ postcopy_add_notifier(&u->postcopy_notifier);
+
return 0;
}
@@ -868,11 +1262,20 @@ static int vhost_user_cleanup(struct vhost_dev *dev)
assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
u = dev->opaque;
+ if (u->postcopy_notifier.notify) {
+ postcopy_remove_notifier(&u->postcopy_notifier);
+ u->postcopy_notifier.notify = NULL;
+ }
if (u->slave_fd >= 0) {
qemu_set_fd_handler(u->slave_fd, NULL, NULL, NULL);
close(u->slave_fd);
u->slave_fd = -1;
}
+ g_free(u->region_rb);
+ u->region_rb = NULL;
+ g_free(u->region_rb_offset);
+ u->region_rb_offset = NULL;
+ u->region_rb_len = 0;
g_free(u);
dev->opaque = 0;
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index d8d0ef92e1..250f886acb 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -522,10 +522,28 @@ static void vhost_region_add_section(struct vhost_dev *dev,
uint64_t mrs_gpa = section->offset_within_address_space;
uintptr_t mrs_host = (uintptr_t)memory_region_get_ram_ptr(section->mr) +
section->offset_within_region;
+ RAMBlock *mrs_rb = section->mr->ram_block;
+ size_t mrs_page = qemu_ram_pagesize(mrs_rb);
trace_vhost_region_add_section(section->mr->name, mrs_gpa, mrs_size,
mrs_host);
+ /* Round the section to it's page size */
+ /* First align the start down to a page boundary */
+ uint64_t alignage = mrs_host & (mrs_page - 1);
+ if (alignage) {
+ mrs_host -= alignage;
+ mrs_size += alignage;
+ mrs_gpa -= alignage;
+ }
+ /* Now align the size up to a page boundary */
+ alignage = mrs_size & (mrs_page - 1);
+ if (alignage) {
+ mrs_size += mrs_page - alignage;
+ }
+ trace_vhost_region_add_section_aligned(section->mr->name, mrs_gpa, mrs_size,
+ mrs_host);
+
if (dev->n_tmp_sections) {
/* Since we already have at least one section, lets see if
* this extends it; since we're scanning in order, we only
@@ -542,18 +560,46 @@ static void vhost_region_add_section(struct vhost_dev *dev,
prev_sec->offset_within_region;
uint64_t prev_host_end = range_get_last(prev_host_start, prev_size);
- if (prev_gpa_end + 1 == mrs_gpa &&
- prev_host_end + 1 == mrs_host &&
- section->mr == prev_sec->mr &&
- (!dev->vhost_ops->vhost_backend_can_merge ||
- dev->vhost_ops->vhost_backend_can_merge(dev,
+ if (mrs_gpa <= (prev_gpa_end + 1)) {
+ /* OK, looks like overlapping/intersecting - it's possible that
+ * the rounding to page sizes has made them overlap, but they should
+ * match up in the same RAMBlock if they do.
+ */
+ if (mrs_gpa < prev_gpa_start) {
+ error_report("%s:Section rounded to %"PRIx64
+ " prior to previous %"PRIx64,
+ __func__, mrs_gpa, prev_gpa_start);
+ /* A way to cleanly fail here would be better */
+ return;
+ }
+ /* Offset from the start of the previous GPA to this GPA */
+ size_t offset = mrs_gpa - prev_gpa_start;
+
+ if (prev_host_start + offset == mrs_host &&
+ section->mr == prev_sec->mr &&
+ (!dev->vhost_ops->vhost_backend_can_merge ||
+ dev->vhost_ops->vhost_backend_can_merge(dev,
mrs_host, mrs_size,
prev_host_start, prev_size))) {
- /* The two sections abut */
- need_add = false;
- prev_sec->size = int128_add(prev_sec->size, section->size);
- trace_vhost_region_add_section_abut(section->mr->name,
- mrs_size + prev_size);
+ uint64_t max_end = MAX(prev_host_end, mrs_host + mrs_size);
+ need_add = false;
+ prev_sec->offset_within_address_space =
+ MIN(prev_gpa_start, mrs_gpa);
+ prev_sec->offset_within_region =
+ MIN(prev_host_start, mrs_host) -
+ (uintptr_t)memory_region_get_ram_ptr(prev_sec->mr);
+ prev_sec->size = int128_make64(max_end - MIN(prev_host_start,
+ mrs_host));
+ trace_vhost_region_add_section_merge(section->mr->name,
+ int128_get64(prev_sec->size),
+ prev_sec->offset_within_address_space,
+ prev_sec->offset_within_region);
+ } else {
+ error_report("%s: Overlapping but not coherent sections "
+ "at %"PRIx64,
+ __func__, mrs_gpa);
+ return;
+ }
}
}