[Qemu-devel] [PATCH v6 37/47] 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>
---
 include/migration/migration.h    |  1 +
 include/migration/postcopy-ram.h | 16 ++++++++
 migration/postcopy-ram.c         | 87 ++++++++++++++++++++++++++++++++++++++++
 trace-events                     |  1 +
 4 files changed, 105 insertions(+)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index 75c3299..db06fd2 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -82,6 +82,7 @@ struct MigrationIncomingState {
     int            userfault_fd;
     QEMUFile *return_path;
     QemuMutex      rp_mutex;    /* We send replies from multiple threads */
+    void          *postcopy_tmp_page;
 };
 
 MigrationIncomingState *migration_incoming_get_current(void);
diff --git a/include/migration/postcopy-ram.h b/include/migration/postcopy-ram.h
index 88793b3..5d8ec61 100644
--- a/include/migration/postcopy-ram.h
+++ b/include/migration/postcopy-ram.h
@@ -69,4 +69,20 @@ 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,
+                        bool all_zero);
+
+/*
+ * 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 1be3bc9..33aadbc 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -278,6 +278,10 @@ 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;
 }
 
@@ -344,6 +348,77 @@ int postcopy_ram_enable_notify(MigrationIncomingState *mis)
     return 0;
 }
 
+/*
+ * Place a host page (from) at (host) atomically
+ * all_zero: Hint that the page being placed is 0 throughout
+ * returns 0 on success
+ */
+int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from,
+                        bool all_zero)
+{
+    if (!all_zero) {
+        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;
+        }
+    } else {
+        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 from: %p",
+                         __func__, strerror(e), host, from);
+
+            return -e;
+        }
+    }
+
+    trace_postcopy_place_page(host, all_zero);
+    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)
@@ -373,6 +448,18 @@ int postcopy_ram_enable_notify(MigrationIncomingState *mis)
 {
     assert(0);
 }
+
+int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from,
+                        bool all_zero)
+{
+    assert(0);
+}
+
+void *postcopy_get_tmp_page(MigrationIncomingState *mis)
+{
+    assert(0);
+}
+
 #endif
 
 /* ------------------------------------------------------------------------- */
diff --git a/trace-events b/trace-events
index c4b92ce..b65740c 100644
--- a/trace-events
+++ b/trace-events
@@ -1499,6 +1499,7 @@ postcopy_discard_send_finish(const char *ramblock, int nwords, int ncmds) "%s ma
 postcopy_cleanup_area(const char *ramblock, void *host_addr, size_t offset, size_t length) "%s: %p offset=%zx length=%zx"
 postcopy_ram_discard_range(void *start, void *end) "%p,%p"
 postcopy_init_area(const char *ramblock, void *host_addr, size_t offset, size_t length) "%s: %p offset=%zx length=%zx"
+postcopy_place_page(void *host_addr, bool all_zero) "host=%p all_zero=%d"
 
 # kvm-all.c
 kvm_ioctl(int type, void *arg) "type 0x%x, arg %p"
-- 
2.1.0