Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

virtio,vhost,pci,pc: features, cleanups

SRAT tables for DIMM devices
new virtio net flags for speed/duplex
post-copy migration support in vhost
cleanups in pci

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Tue 20 Mar 2018 14:40:43 GMT
# gpg:                using RSA key 281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream: (51 commits)
  postcopy shared docs
  libvhost-user: Claim support for postcopy
  postcopy: Allow shared memory
  vhost: Huge page align and merge
  vhost+postcopy: Wire up POSTCOPY_END notify
  vhost-user: Add VHOST_USER_POSTCOPY_END message
  libvhost-user: mprotect & madvises for postcopy
  vhost+postcopy: Call wakeups
  vhost+postcopy: Add vhost waker
  postcopy: postcopy_notify_shared_wake
  postcopy: helper for waking shared
  vhost+postcopy: Resolve client address
  postcopy-ram: add a stub for postcopy_request_shared_page
  vhost+postcopy: Helper to send requests to source for shared pages
  vhost+postcopy: Stash RAMBlock and offset
  vhost+postcopy: Send address back to qemu
  libvhost-user+postcopy: Register new regions with the ufd
  migration/ram: ramblock_recv_bitmap_test_byte_offset
  postcopy+vhost-user: Split set_mem_table for postcopy
  vhost+postcopy: Transmit 'listen' to slave
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

# Conflicts:
#	scripts/update-linux-headers.sh

8 files changed, 402 insertions, 66 deletions

diff --git a/migration/migration.c b/migration/migration.c
index 623f373326..fc629e5965 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -155,6 +155,8 @@ MigrationIncomingState *migration_incoming_get_current(void)
     if (!once) {
         mis_current.state = MIGRATION_STATUS_NONE;
         memset(&mis_current, 0, sizeof(MigrationIncomingState));
+        mis_current.postcopy_remote_fds = g_array_new(FALSE, TRUE,
+                                                   sizeof(struct PostCopyFD));
         qemu_mutex_init(&mis_current.rp_mutex);
         qemu_event_init(&mis_current.main_thread_load_event, false);
 
@@ -180,6 +182,10 @@ void migration_incoming_state_destroy(void)
         qemu_fclose(mis->from_src_file);
         mis->from_src_file = NULL;
     }
+    if (mis->postcopy_remote_fds) {
+        g_array_free(mis->postcopy_remote_fds, TRUE);
+        mis->postcopy_remote_fds = NULL;
+    }
 
     qemu_event_reset(&mis->main_thread_load_event);
 }
diff --git a/migration/migration.h b/migration/migration.h
index a79540b99c..8d2f320c48 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -49,8 +49,12 @@ struct MigrationIncomingState {
     int       userfault_event_fd;
     QEMUFile *to_src_file;
     QemuMutex rp_mutex;    /* We send replies from multiple threads */
+    /* RAMBlock of last request sent to source */
+    RAMBlock *last_rb;
     void     *postcopy_tmp_page;
     void     *postcopy_tmp_zero_page;
+    /* PostCopyFD's for external userfaultfds & handlers of shared memory */
+    GArray   *postcopy_remote_fds;
 
     QEMUBH *bh;
 
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 032abfbf1a..efd77939af 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -23,6 +23,8 @@
 #include "savevm.h"
 #include "postcopy-ram.h"
 #include "ram.h"
+#include "qapi/error.h"
+#include "qemu/notify.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/balloon.h"
 #include "qemu/error-report.h"
@@ -45,6 +47,33 @@ struct PostcopyDiscardState {
     unsigned int nsentcmds;
 };
 
+static NotifierWithReturnList postcopy_notifier_list;
+
+void postcopy_infrastructure_init(void)
+{
+    notifier_with_return_list_init(&postcopy_notifier_list);
+}
+
+void postcopy_add_notifier(NotifierWithReturn *nn)
+{
+    notifier_with_return_list_add(&postcopy_notifier_list, nn);
+}
+
+void postcopy_remove_notifier(NotifierWithReturn *n)
+{
+    notifier_with_return_remove(n);
+}
+
+int postcopy_notify(enum PostcopyNotifyReason reason, Error **errp)
+{
+    struct PostcopyNotifyData pnd;
+    pnd.reason = reason;
+    pnd.errp = errp;
+
+    return notifier_with_return_list_notify(&postcopy_notifier_list,
+                                            &pnd);
+}
+
 /* Postcopy needs to detect accesses to pages that haven't yet been copied
  * across, and efficiently map new pages in, the techniques for doing this
  * are target OS specific.
@@ -186,12 +215,6 @@ static int test_ramblock_postcopiable(const char *block_name, void *host_addr,
     RAMBlock *rb = qemu_ram_block_by_name(block_name);
     size_t pagesize = qemu_ram_pagesize(rb);
 
-    if (qemu_ram_is_shared(rb)) {
-        error_report("Postcopy on shared RAM (%s) is not yet supported",
-                     block_name);
-        return 1;
-    }
-
     if (length % pagesize) {
         error_report("Postcopy requires RAM blocks to be a page size multiple,"
                      " block %s is 0x" RAM_ADDR_FMT " bytes with a "
@@ -215,6 +238,7 @@ bool postcopy_ram_supported_by_host(MigrationIncomingState *mis)
     struct uffdio_register reg_struct;
     struct uffdio_range range_struct;
     uint64_t feature_mask;
+    Error *local_err = NULL;
 
     if (qemu_target_page_size() > pagesize) {
         error_report("Target page size bigger than host page size");
@@ -228,6 +252,12 @@ bool postcopy_ram_supported_by_host(MigrationIncomingState *mis)
         goto out;
     }
 
+    /* Give devices a chance to object */
+    if (postcopy_notify(POSTCOPY_NOTIFY_PROBE, &local_err)) {
+        error_report_err(local_err);
+        goto out;
+    }
+
     /* Version and features check */
     if (!ufd_check_and_apply(ufd, mis)) {
         goto out;
@@ -377,6 +407,13 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
     trace_postcopy_ram_incoming_cleanup_entry();
 
     if (mis->have_fault_thread) {
+        Error *local_err = NULL;
+
+        if (postcopy_notify(POSTCOPY_NOTIFY_INBOUND_END, &local_err)) {
+            error_report_err(local_err);
+            return -1;
+        }
+
         if (qemu_ram_foreach_block(cleanup_range, mis)) {
             return -1;
         }
@@ -481,10 +518,63 @@ static int ram_block_enable_notify(const char *block_name, void *host_addr,
         error_report("%s userfault: Region doesn't support COPY", __func__);
         return -1;
     }
+    if (reg_struct.ioctls & ((__u64)1 << _UFFDIO_ZEROPAGE)) {
+        RAMBlock *rb = qemu_ram_block_by_name(block_name);
+        qemu_ram_set_uf_zeroable(rb);
+    }
 
     return 0;
 }
 
+int postcopy_wake_shared(struct PostCopyFD *pcfd,
+                         uint64_t client_addr,
+                         RAMBlock *rb)
+{
+    size_t pagesize = qemu_ram_pagesize(rb);
+    struct uffdio_range range;
+    int ret;
+    trace_postcopy_wake_shared(client_addr, qemu_ram_get_idstr(rb));
+    range.start = client_addr & ~(pagesize - 1);
+    range.len = pagesize;
+    ret = ioctl(pcfd->fd, UFFDIO_WAKE, &range);
+    if (ret) {
+        error_report("%s: Failed to wake: %zx in %s (%s)",
+                     __func__, (size_t)client_addr, qemu_ram_get_idstr(rb),
+                     strerror(errno));
+    }
+    return ret;
+}
+
+/*
+ * Callback from shared fault handlers to ask for a page,
+ * the page must be specified by a RAMBlock and an offset in that rb
+ * Note: Only for use by shared fault handlers (in fault thread)
+ */
+int postcopy_request_shared_page(struct PostCopyFD *pcfd, RAMBlock *rb,
+                                 uint64_t client_addr, uint64_t rb_offset)
+{
+    size_t pagesize = qemu_ram_pagesize(rb);
+    uint64_t aligned_rbo = rb_offset & ~(pagesize - 1);
+    MigrationIncomingState *mis = migration_incoming_get_current();
+
+    trace_postcopy_request_shared_page(pcfd->idstr, qemu_ram_get_idstr(rb),
+                                       rb_offset);
+    if (ramblock_recv_bitmap_test_byte_offset(rb, aligned_rbo)) {
+        trace_postcopy_request_shared_page_present(pcfd->idstr,
+                                        qemu_ram_get_idstr(rb), rb_offset);
+        return postcopy_wake_shared(pcfd, client_addr, rb);
+    }
+    if (rb != mis->last_rb) {
+        mis->last_rb = rb;
+        migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb),
+                                  aligned_rbo, pagesize);
+    } else {
+        /* Save some space */
+        migrate_send_rp_req_pages(mis, NULL, aligned_rbo, pagesize);
+    }
+    return 0;
+}
+
 /*
  * Handle faults detected by the USERFAULT markings
  */
@@ -493,29 +583,44 @@ static void *postcopy_ram_fault_thread(void *opaque)
     MigrationIncomingState *mis = opaque;
     struct uffd_msg msg;
     int ret;
+    size_t index;
     RAMBlock *rb = NULL;
-    RAMBlock *last_rb = NULL; /* last RAMBlock we sent part of */
 
     trace_postcopy_ram_fault_thread_entry();
+    mis->last_rb = NULL; /* last RAMBlock we sent part of */
     qemu_sem_post(&mis->fault_thread_sem);
 
+    struct pollfd *pfd;
+    size_t pfd_len = 2 + mis->postcopy_remote_fds->len;
+
+    pfd = g_new0(struct pollfd, pfd_len);
+
+    pfd[0].fd = mis->userfault_fd;
+    pfd[0].events = POLLIN;
+    pfd[1].fd = mis->userfault_event_fd;
+    pfd[1].events = POLLIN; /* Waiting for eventfd to go positive */
+    trace_postcopy_ram_fault_thread_fds_core(pfd[0].fd, pfd[1].fd);
+    for (index = 0; index < mis->postcopy_remote_fds->len; index++) {
+        struct PostCopyFD *pcfd = &g_array_index(mis->postcopy_remote_fds,
+                                                 struct PostCopyFD, index);
+        pfd[2 + index].fd = pcfd->fd;
+        pfd[2 + index].events = POLLIN;
+        trace_postcopy_ram_fault_thread_fds_extra(2 + index, pcfd->idstr,
+                                                  pcfd->fd);
+    }
+
     while (true) {
         ram_addr_t rb_offset;
-        struct pollfd pfd[2];
+        int poll_result;
 
         /*
          * We're mainly waiting for the kernel to give us a faulting HVA,
          * however we can be told to quit via userfault_quit_fd which is
          * an eventfd
          */
-        pfd[0].fd = mis->userfault_fd;
-        pfd[0].events = POLLIN;
-        pfd[0].revents = 0;
-        pfd[1].fd = mis->userfault_event_fd;
-        pfd[1].events = POLLIN; /* Waiting for eventfd to go positive */
-        pfd[1].revents = 0;
-
-        if (poll(pfd, 2, -1 /* Wait forever */) == -1) {
+
+        poll_result = poll(pfd, pfd_len, -1 /* Wait forever */);
+        if (poll_result == -1) {
             error_report("%s: userfault poll: %s", __func__, strerror(errno));
             break;
         }
@@ -535,57 +640,117 @@ static void *postcopy_ram_fault_thread(void *opaque)
             }
         }
 
-        ret = read(mis->userfault_fd, &msg, sizeof(msg));
-        if (ret != sizeof(msg)) {
-            if (errno == EAGAIN) {
-                /*
-                 * if a wake up happens on the other thread just after
-                 * the poll, there is nothing to read.
-                 */
-                continue;
+        if (pfd[0].revents) {
+            poll_result--;
+            ret = read(mis->userfault_fd, &msg, sizeof(msg));
+            if (ret != sizeof(msg)) {
+                if (errno == EAGAIN) {
+                    /*
+                     * if a wake up happens on the other thread just after
+                     * the poll, there is nothing to read.
+                     */
+                    continue;
+                }
+                if (ret < 0) {
+                    error_report("%s: Failed to read full userfault "
+                                 "message: %s",
+                                 __func__, strerror(errno));
+                    break;
+                } else {
+                    error_report("%s: Read %d bytes from userfaultfd "
+                                 "expected %zd",
+                                 __func__, ret, sizeof(msg));
+                    break; /* Lost alignment, don't know what we'd read next */
+                }
             }
-            if (ret < 0) {
-                error_report("%s: Failed to read full userfault message: %s",
-                             __func__, strerror(errno));
-                break;
-            } else {
-                error_report("%s: Read %d bytes from userfaultfd expected %zd",
-                             __func__, ret, sizeof(msg));
-                break; /* Lost alignment, don't know what we'd read next */
+            if (msg.event != UFFD_EVENT_PAGEFAULT) {
+                error_report("%s: Read unexpected event %ud from userfaultfd",
+                             __func__, msg.event);
+                continue; /* It's not a page fault, shouldn't happen */
             }
-        }
-        if (msg.event != UFFD_EVENT_PAGEFAULT) {
-            error_report("%s: Read unexpected event %ud from userfaultfd",
-                         __func__, msg.event);
-            continue; /* It's not a page fault, shouldn't happen */
-        }
 
-        rb = qemu_ram_block_from_host(
-                 (void *)(uintptr_t)msg.arg.pagefault.address,
-                 true, &rb_offset);
-        if (!rb) {
-            error_report("postcopy_ram_fault_thread: Fault outside guest: %"
-                         PRIx64, (uint64_t)msg.arg.pagefault.address);
-            break;
-        }
+            rb = qemu_ram_block_from_host(
+                     (void *)(uintptr_t)msg.arg.pagefault.address,
+                     true, &rb_offset);
+            if (!rb) {
+                error_report("postcopy_ram_fault_thread: Fault outside guest: %"
+                             PRIx64, (uint64_t)msg.arg.pagefault.address);
+                break;
+            }
 
-        rb_offset &= ~(qemu_ram_pagesize(rb) - 1);
-        trace_postcopy_ram_fault_thread_request(msg.arg.pagefault.address,
+            rb_offset &= ~(qemu_ram_pagesize(rb) - 1);
+            trace_postcopy_ram_fault_thread_request(msg.arg.pagefault.address,
                                                 qemu_ram_get_idstr(rb),
                                                 rb_offset);
+            /*
+             * Send the request to the source - we want to request one
+             * of our host page sizes (which is >= TPS)
+             */
+            if (rb != mis->last_rb) {
+                mis->last_rb = rb;
+                migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb),
+                                         rb_offset, qemu_ram_pagesize(rb));
+            } else {
+                /* Save some space */
+                migrate_send_rp_req_pages(mis, NULL,
+                                         rb_offset, qemu_ram_pagesize(rb));
+            }
+        }
 
-        /*
-         * Send the request to the source - we want to request one
-         * of our host page sizes (which is >= TPS)
-         */
-        if (rb != last_rb) {
-            last_rb = rb;
-            migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb),
-                                     rb_offset, qemu_ram_pagesize(rb));
-        } else {
-            /* Save some space */
-            migrate_send_rp_req_pages(mis, NULL,
-                                     rb_offset, qemu_ram_pagesize(rb));
+        /* Now handle any requests from external processes on shared memory */
+        /* TODO: May need to handle devices deregistering during postcopy */
+        for (index = 2; index < pfd_len && poll_result; index++) {
+            if (pfd[index].revents) {
+                struct PostCopyFD *pcfd =
+                    &g_array_index(mis->postcopy_remote_fds,
+                                   struct PostCopyFD, index - 2);
+
+                poll_result--;
+                if (pfd[index].revents & POLLERR) {
+                    error_report("%s: POLLERR on poll %zd fd=%d",
+                                 __func__, index, pcfd->fd);
+                    pfd[index].events = 0;
+                    continue;
+                }
+
+                ret = read(pcfd->fd, &msg, sizeof(msg));
+                if (ret != sizeof(msg)) {
+                    if (errno == EAGAIN) {
+                        /*
+                         * if a wake up happens on the other thread just after
+                         * the poll, there is nothing to read.
+                         */
+                        continue;
+                    }
+                    if (ret < 0) {
+                        error_report("%s: Failed to read full userfault "
+                                     "message: %s (shared) revents=%d",
+                                     __func__, strerror(errno),
+                                     pfd[index].revents);
+                        /*TODO: Could just disable this sharer */
+                        break;
+                    } else {
+                        error_report("%s: Read %d bytes from userfaultfd "
+                                     "expected %zd (shared)",
+                                     __func__, ret, sizeof(msg));
+                        /*TODO: Could just disable this sharer */
+                        break; /*Lost alignment,don't know what we'd read next*/
+                    }
+                }
+                if (msg.event != UFFD_EVENT_PAGEFAULT) {
+                    error_report("%s: Read unexpected event %ud "
+                                 "from userfaultfd (shared)",
+                                 __func__, msg.event);
+                    continue; /* It's not a page fault, shouldn't happen */
+                }
+                /* Call the device handler registered with us */
+                ret = pcfd->handler(pcfd, &msg);
+                if (ret) {
+                    error_report("%s: Failed to resolve shared fault on %zd/%s",
+                                 __func__, index, pcfd->idstr);
+                    /* TODO: Fail? Disable this sharer? */
+                }
+            }
         }
     }
     trace_postcopy_ram_fault_thread_exit();
@@ -667,6 +832,22 @@ static int qemu_ufd_copy_ioctl(int userfault_fd, void *host_addr,
     return ret;
 }
 
+int postcopy_notify_shared_wake(RAMBlock *rb, uint64_t offset)
+{
+    int i;
+    MigrationIncomingState *mis = migration_incoming_get_current();
+    GArray *pcrfds = mis->postcopy_remote_fds;
+
+    for (i = 0; i < pcrfds->len; i++) {
+        struct PostCopyFD *cur = &g_array_index(pcrfds, struct PostCopyFD, i);
+        int ret = cur->waker(cur, rb, offset);
+        if (ret) {
+            return ret;
+        }
+    }
+    return 0;
+}
+
 /*
  * Place a host page (from) at (host) atomically
  * returns 0 on success
@@ -690,7 +871,8 @@ int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from,
     }
 
     trace_postcopy_place_page(host);
-    return 0;
+    return postcopy_notify_shared_wake(rb,
+                                       qemu_ram_block_host_offset(rb, host));
 }
 
 /*
@@ -700,17 +882,23 @@ int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from,
 int postcopy_place_page_zero(MigrationIncomingState *mis, void *host,
                              RAMBlock *rb)
 {
+    size_t pagesize = qemu_ram_pagesize(rb);
     trace_postcopy_place_page_zero(host);
 
-    if (qemu_ram_pagesize(rb) == getpagesize()) {
-        if (qemu_ufd_copy_ioctl(mis->userfault_fd, host, NULL, getpagesize(),
-                                rb)) {
+    /* Normal RAMBlocks can zero a page using UFFDIO_ZEROPAGE
+     * but it's not available for everything (e.g. hugetlbpages)
+     */
+    if (qemu_ram_is_uf_zeroable(rb)) {
+        if (qemu_ufd_copy_ioctl(mis->userfault_fd, host, NULL, pagesize, rb)) {
             int e = errno;
             error_report("%s: %s zero host: %p",
                          __func__, strerror(e), host);
 
             return -e;
         }
+        return postcopy_notify_shared_wake(rb,
+                                           qemu_ram_block_host_offset(rb,
+                                                                      host));
     } else {
         /* The kernel can't use UFFDIO_ZEROPAGE for hugepages */
         if (!mis->postcopy_tmp_zero_page) {
@@ -730,8 +918,6 @@ int postcopy_place_page_zero(MigrationIncomingState *mis, void *host,
         return postcopy_place_page(mis, host, mis->postcopy_tmp_zero_page,
                                    rb);
     }
-
-    return 0;
 }
 
 /*
@@ -784,6 +970,13 @@ int postcopy_ram_prepare_discard(MigrationIncomingState *mis)
     return -1;
 }
 
+int postcopy_request_shared_page(struct PostCopyFD *pcfd, RAMBlock *rb,
+                                 uint64_t client_addr, uint64_t rb_offset)
+{
+    assert(0);
+    return -1;
+}
+
 int postcopy_ram_enable_notify(MigrationIncomingState *mis)
 {
     assert(0);
@@ -810,6 +1003,13 @@ void *postcopy_get_tmp_page(MigrationIncomingState *mis)
     return NULL;
 }
 
+int postcopy_wake_shared(struct PostCopyFD *pcfd,
+                         uint64_t client_addr,
+                         RAMBlock *rb)
+{
+    assert(0);
+    return -1;
+}
 #endif
 
 /* ------------------------------------------------------------------------- */
@@ -927,3 +1127,31 @@ PostcopyState postcopy_state_set(PostcopyState new_state)
 {
     return atomic_xchg(&incoming_postcopy_state, new_state);
 }
+
+/* Register a handler for external shared memory postcopy
+ * called on the destination.
+ */
+void postcopy_register_shared_ufd(struct PostCopyFD *pcfd)
+{
+    MigrationIncomingState *mis = migration_incoming_get_current();
+
+    mis->postcopy_remote_fds = g_array_append_val(mis->postcopy_remote_fds,
+                                                  *pcfd);
+}
+
+/* Unregister a handler for external shared memory postcopy
+ */
+void postcopy_unregister_shared_ufd(struct PostCopyFD *pcfd)
+{
+    guint i;
+    MigrationIncomingState *mis = migration_incoming_get_current();
+    GArray *pcrfds = mis->postcopy_remote_fds;
+
+    for (i = 0; i < pcrfds->len; i++) {
+        struct PostCopyFD *cur = &g_array_index(pcrfds, struct PostCopyFD, i);
+        if (cur->fd == pcfd->fd) {
+            mis->postcopy_remote_fds = g_array_remove_index(pcrfds, i);
+            return;
+        }
+    }
+}
diff --git a/migration/postcopy-ram.h b/migration/postcopy-ram.h
index 14f6cadcbd..d900d9c34f 100644
--- a/migration/postcopy-ram.h
+++ b/migration/postcopy-ram.h
@@ -116,4 +116,77 @@ PostcopyState postcopy_state_set(PostcopyState new_state);
 
 void postcopy_fault_thread_notify(MigrationIncomingState *mis);
 
+/*
+ * To be called once at the start before any device initialisation
+ */
+void postcopy_infrastructure_init(void);
+
+/* Add a notifier to a list to be called when checking whether the devices
+ * can support postcopy.
+ * It's data is a *PostcopyNotifyData
+ * It should return 0 if OK, or a negative value on failure.
+ * On failure it must set the data->errp to an error.
+ *
+ */
+enum PostcopyNotifyReason {
+    POSTCOPY_NOTIFY_PROBE = 0,
+    POSTCOPY_NOTIFY_INBOUND_ADVISE,
+    POSTCOPY_NOTIFY_INBOUND_LISTEN,
+    POSTCOPY_NOTIFY_INBOUND_END,
+};
+
+struct PostcopyNotifyData {
+    enum PostcopyNotifyReason reason;
+    Error **errp;
+};
+
+void postcopy_add_notifier(NotifierWithReturn *nn);
+void postcopy_remove_notifier(NotifierWithReturn *n);
+/* Call the notifier list set by postcopy_add_start_notifier */
+int postcopy_notify(enum PostcopyNotifyReason reason, Error **errp);
+
+struct PostCopyFD;
+
+/* ufd is a pointer to the struct uffd_msg *TODO: more Portable! */
+typedef int (*pcfdhandler)(struct PostCopyFD *pcfd, void *ufd);
+/* Notification to wake, either on place or on reception of
+ * a fault on something that's already arrived (race)
+ */
+typedef int (*pcfdwake)(struct PostCopyFD *pcfd, RAMBlock *rb, uint64_t offset);
+
+struct PostCopyFD {
+    int fd;
+    /* Data to pass to handler */
+    void *data;
+    /* Handler to be called whenever we get a poll event */
+    pcfdhandler handler;
+    /* Notification to wake shared client */
+    pcfdwake waker;
+    /* A string to use in error messages */
+    const char *idstr;
+};
+
+/* Register a userfaultfd owned by an external process for
+ * shared memory.
+ */
+void postcopy_register_shared_ufd(struct PostCopyFD *pcfd);
+void postcopy_unregister_shared_ufd(struct PostCopyFD *pcfd);
+/* Call each of the shared 'waker's registerd telling them of
+ * availability of a block.
+ */
+int postcopy_notify_shared_wake(RAMBlock *rb, uint64_t offset);
+/* postcopy_wake_shared: Notify a client ufd that a page is available
+ *
+ * Returns 0 on success
+ *
+ * @pcfd: Structure with fd, handler and name as above
+ * @client_addr: Address in the client program, not QEMU
+ * @rb: The RAMBlock the page is in
+ */
+int postcopy_wake_shared(struct PostCopyFD *pcfd, uint64_t client_addr,
+                         RAMBlock *rb);
+/* Callback from shared fault handlers to ask for a page */
+int postcopy_request_shared_page(struct PostCopyFD *pcfd, RAMBlock *rb,
+                                 uint64_t client_addr, uint64_t offset);
+
 #endif
diff --git a/migration/ram.c b/migration/ram.c
index 590fceb7e9..0e90efa092 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -169,6 +169,11 @@ int ramblock_recv_bitmap_test(RAMBlock *rb, void *host_addr)
                     rb->receivedmap);
 }
 
+bool ramblock_recv_bitmap_test_byte_offset(RAMBlock *rb, uint64_t byte_offset)
+{
+    return test_bit(byte_offset >> TARGET_PAGE_BITS, rb->receivedmap);
+}
+
 void ramblock_recv_bitmap_set(RAMBlock *rb, void *host_addr)
 {
     set_bit_atomic(ramblock_recv_bitmap_offset(host_addr, rb), rb->receivedmap);
diff --git a/migration/ram.h b/migration/ram.h
index 53f0021c51..5030be110a 100644
--- a/migration/ram.h
+++ b/migration/ram.h
@@ -60,6 +60,7 @@ int ram_postcopy_incoming_init(MigrationIncomingState *mis);
 void ram_handle_compressed(void *host, uint8_t ch, uint64_t size);
 
 int ramblock_recv_bitmap_test(RAMBlock *rb, void *host_addr);
+bool ramblock_recv_bitmap_test_byte_offset(RAMBlock *rb, uint64_t byte_offset);
 void ramblock_recv_bitmap_set(RAMBlock *rb, void *host_addr);
 void ramblock_recv_bitmap_set_range(RAMBlock *rb, void *host_addr, size_t nr);
 
diff --git a/migration/savevm.c b/migration/savevm.c
index f417cef7d5..e2be02afe4 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -1395,6 +1395,7 @@ static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis,
 {
     PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_ADVISE);
     uint64_t remote_pagesize_summary, local_pagesize_summary, remote_tps;
+    Error *local_err = NULL;
 
     trace_loadvm_postcopy_handle_advise();
     if (ps != POSTCOPY_INCOMING_NONE) {
@@ -1460,6 +1461,11 @@ static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis,
         return -1;
     }
 
+    if (postcopy_notify(POSTCOPY_NOTIFY_INBOUND_ADVISE, &local_err)) {
+        error_report_err(local_err);
+        return -1;
+    }
+
     if (ram_postcopy_incoming_init(mis)) {
         return -1;
     }
@@ -1621,6 +1627,8 @@ static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis)
 {
     PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_LISTENING);
     trace_loadvm_postcopy_handle_listen();
+    Error *local_err = NULL;
+
     if (ps != POSTCOPY_INCOMING_ADVISE && ps != POSTCOPY_INCOMING_DISCARD) {
         error_report("CMD_POSTCOPY_LISTEN in wrong postcopy state (%d)", ps);
         return -1;
@@ -1646,6 +1654,11 @@ static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis)
         }
     }
 
+    if (postcopy_notify(POSTCOPY_NOTIFY_INBOUND_LISTEN, &local_err)) {
+        error_report_err(local_err);
+        return -1;
+    }
+
     if (mis->have_listen_thread) {
         error_report("CMD_POSTCOPY_RAM_LISTEN already has a listen thread");
         return -1;
diff --git a/migration/trace-events b/migration/trace-events
index 314e1be6bc..a180d7b008 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -190,12 +190,18 @@ postcopy_place_page_zero(void *host_addr) "host=%p"
 postcopy_ram_enable_notify(void) ""
 postcopy_ram_fault_thread_entry(void) ""
 postcopy_ram_fault_thread_exit(void) ""
+postcopy_ram_fault_thread_fds_core(int baseufd, int quitfd) "ufd: %d quitfd: %d"
+postcopy_ram_fault_thread_fds_extra(size_t index, const char *name, int fd) "%zd/%s: %d"
 postcopy_ram_fault_thread_quit(void) ""
 postcopy_ram_fault_thread_request(uint64_t hostaddr, const char *ramblock, size_t offset) "Request for HVA=0x%" PRIx64 " rb=%s offset=0x%zx"
 postcopy_ram_incoming_cleanup_closeuf(void) ""
 postcopy_ram_incoming_cleanup_entry(void) ""
 postcopy_ram_incoming_cleanup_exit(void) ""
 postcopy_ram_incoming_cleanup_join(void) ""
+postcopy_request_shared_page(const char *sharer, const char *rb, uint64_t rb_offset) "for %s in %s offset 0x%"PRIx64
+postcopy_request_shared_page_present(const char *sharer, const char *rb, uint64_t rb_offset) "%s already %s offset 0x%"PRIx64
+postcopy_wake_shared(uint64_t client_addr, const char *rb) "at 0x%"PRIx64" in %s"
+
 save_xbzrle_page_skipping(void) ""
 save_xbzrle_page_overflow(void) ""
 ram_save_iterate_big_wait(uint64_t milliconds, int iterations) "big wait: %" PRIu64 " milliseconds, %d iterations"