[Qemu-devel] [PATCH v8 41/54] postcopy_ram.c: place_page and helpers

["Dr. David Alan Gilbert (git)" <dgilbert@redhat.com>]

From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>

postcopy_place_page (etc) provide a way for postcopy to place a page
into guests memory atomically (using the copy ioctl on the ufd).

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Amit Shah <amit.shah@redhat.com>
---
 include/migration/migration.h    |  1 +
 include/migration/postcopy-ram.h | 21 +++++++++
 migration/postcopy-ram.c         | 97 ++++++++++++++++++++++++++++++++++++++++
 trace-events                     |  2 +
 4 files changed, 121 insertions(+)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index fbf3b99..218b2ca 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -96,6 +96,7 @@ struct MigrationIncomingState {
     int       userfault_fd;
     QEMUFile *to_src_file;
     QemuMutex rp_mutex;    /* We send replies from multiple threads */
+    void     *postcopy_tmp_page;
 
     /* See savevm.c */
     LoadStateEntry_Head loadvm_handlers;
diff --git a/include/migration/postcopy-ram.h b/include/migration/postcopy-ram.h
index 9d037ff..50c1ce5 100644
--- a/include/migration/postcopy-ram.h
+++ b/include/migration/postcopy-ram.h
@@ -69,4 +69,25 @@ void postcopy_discard_send_range(MigrationState *ms, PostcopyDiscardState *pds,
 void postcopy_discard_send_finish(MigrationState *ms,
                                   PostcopyDiscardState *pds);
 
+/*
+ * Place a page (from) at (host) efficiently
+ *    There are restrictions on how 'from' must be mapped, in general best
+ *    to use other postcopy_ routines to allocate.
+ * returns 0 on success
+ */
+int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from);
+
+/*
+ * Place a zero page at (host) atomically
+ * returns 0 on success
+ */
+int postcopy_place_page_zero(MigrationIncomingState *mis, void *host);
+
+/*
+ * Allocate a page of memory that can be mapped at a later point in time
+ * using postcopy_place_page
+ * Returns: Pointer to allocated page
+ */
+void *postcopy_get_tmp_page(MigrationIncomingState *mis);
+
 #endif
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index e89a99e..09a1349 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -272,6 +272,10 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
         return -1;
     }
 
+    if (mis->postcopy_tmp_page) {
+        munmap(mis->postcopy_tmp_page, getpagesize());
+        mis->postcopy_tmp_page = NULL;
+    }
     return 0;
 }
 
@@ -338,6 +342,83 @@ int postcopy_ram_enable_notify(MigrationIncomingState *mis)
     return 0;
 }
 
+/*
+ * Place a host page (from) at (host) atomically
+ * returns 0 on success
+ */
+int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from)
+{
+    struct uffdio_copy copy_struct;
+
+    copy_struct.dst = (uint64_t)(uintptr_t)host;
+    copy_struct.src = (uint64_t)(uintptr_t)from;
+    copy_struct.len = getpagesize();
+    copy_struct.mode = 0;
+
+    /* copy also acks to the kernel waking the stalled thread up
+     * TODO: We can inhibit that ack and only do it if it was requested
+     * which would be slightly cheaper, but we'd have to be careful
+     * of the order of updating our page state.
+     */
+    if (ioctl(mis->userfault_fd, UFFDIO_COPY, &copy_struct)) {
+        int e = errno;
+        error_report("%s: %s copy host: %p from: %p",
+                     __func__, strerror(e), host, from);
+
+        return -e;
+    }
+
+    trace_postcopy_place_page(host);
+    return 0;
+}
+
+/*
+ * Place a zero page at (host) atomically
+ * returns 0 on success
+ */
+int postcopy_place_page_zero(MigrationIncomingState *mis, void *host)
+{
+    struct uffdio_zeropage zero_struct;
+
+    zero_struct.range.start = (uint64_t)(uintptr_t)host;
+    zero_struct.range.len = getpagesize();
+    zero_struct.mode = 0;
+
+    if (ioctl(mis->userfault_fd, UFFDIO_ZEROPAGE, &zero_struct)) {
+        int e = errno;
+        error_report("%s: %s zero host: %p",
+                     __func__, strerror(e), host);
+
+        return -e;
+    }
+
+    trace_postcopy_place_page_zero(host);
+    return 0;
+}
+
+/*
+ * Returns a target page of memory that can be mapped at a later point in time
+ * using postcopy_place_page
+ * The same address is used repeatedly, postcopy_place_page just takes the
+ * backing page away.
+ * Returns: Pointer to allocated page
+ *
+ */
+void *postcopy_get_tmp_page(MigrationIncomingState *mis)
+{
+    if (!mis->postcopy_tmp_page) {
+        mis->postcopy_tmp_page = mmap(NULL, getpagesize(),
+                             PROT_READ | PROT_WRITE, MAP_PRIVATE |
+                             MAP_ANONYMOUS, -1, 0);
+        if (!mis->postcopy_tmp_page) {
+            error_report("%s: %s", __func__, strerror(errno));
+            return NULL;
+        }
+    }
+
+    return mis->postcopy_tmp_page;
+}
+
 #else
 /* No target OS support, stubs just fail */
 bool postcopy_ram_supported_by_host(void)
@@ -367,6 +448,22 @@ int postcopy_ram_enable_notify(MigrationIncomingState *mis)
 {
     assert(0);
 }
+
+int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from)
+{
+    assert(0);
+}
+
+int postcopy_place_page_zero(MigrationIncomingState *mis, void *host)
+{
+    assert(0);
+}
+
+void *postcopy_get_tmp_page(MigrationIncomingState *mis)
+{
+    assert(0);
+}
+
 #endif
 
 /* ------------------------------------------------------------------------- */
diff --git a/trace-events b/trace-events
index 9e4206b..2f27385 100644
--- a/trace-events
+++ b/trace-events
@@ -1538,6 +1538,8 @@ postcopy_discard_send_finish(const char *ramblock, int nwords, int ncmds) "%s ma
 postcopy_ram_discard_range(void *start, size_t length) "%p,+%zx"
 postcopy_cleanup_range(const char *ramblock, void *host_addr, size_t offset, size_t length) "%s: %p offset=%zx length=%zx"
 postcopy_init_range(const char *ramblock, void *host_addr, size_t offset, size_t length) "%s: %p offset=%zx length=%zx"
+postcopy_place_page(void *host_addr) "host=%p"
+postcopy_place_page_zero(void *host_addr) "host=%p"
 
 # kvm-all.c
 kvm_ioctl(int type, void *arg) "type 0x%x, arg %p"
-- 
2.5.0