exec: ram_block_discard_range

Create ram_block_discard_range in exec.c to replace
postcopy_ram_discard_range and most of ram_discard_range.

Those two routines are a bit of a weird combination, and
ram_discard_range is about to get more complex for hugepages.
It's OS dependent code (so shouldn't be in migration/ram.c) but
it needs quite a bit of the innards of RAMBlock so doesn't belong in
the os*.c.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Laurent Vivier <lvivier@redhat.com>
Message-Id: <20170224182844.32452-5-dgilbert@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

6 files changed, 60 insertions, 58 deletions

diff --git a/exec.c b/exec.c
index 3adf2b1861..8ac556a2d4 100644
--- a/exec.c
+++ b/exec.c
@@ -45,6 +45,7 @@
 #include "exec/address-spaces.h"
 #include "sysemu/xen-mapcache.h"
 #include "trace-root.h"
+
 #endif
 #include "exec/cpu-all.h"
 #include "qemu/rcu_queue.h"
@@ -3294,4 +3295,57 @@ int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque)
     rcu_read_unlock();
     return ret;
 }
+
+/*
+ * Unmap pages of memory from start to start+length such that
+ * they a) read as 0, b) Trigger whatever fault mechanism
+ * the OS provides for postcopy.
+ * The pages must be unmapped by the end of the function.
+ * Returns: 0 on success, none-0 on failure
+ *
+ */
+int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
+{
+    int ret = -1;
+
+    uint8_t *host_startaddr = rb->host + start;
+
+    if ((uintptr_t)host_startaddr & (rb->page_size - 1)) {
+        error_report("ram_block_discard_range: Unaligned start address: %p",
+                     host_startaddr);
+        goto err;
+    }
+
+    if ((start + length) <= rb->used_length) {
+        uint8_t *host_endaddr = host_startaddr + length;
+        if ((uintptr_t)host_endaddr & (rb->page_size - 1)) {
+            error_report("ram_block_discard_range: Unaligned end address: %p",
+                         host_endaddr);
+            goto err;
+        }
+
+        errno = ENOTSUP; /* If we are missing MADVISE etc */
+
+#if defined(CONFIG_MADVISE)
+        /* Note: We need the madvise MADV_DONTNEED behaviour of definitely
+         * freeing the page.
+         */
+        ret = madvise(host_startaddr, length, MADV_DONTNEED);
+#endif
+        if (ret) {
+            ret = -errno;
+            error_report("ram_block_discard_range: Failed to discard range "
+                         "%s:%" PRIx64 " +%zx (%d)",
+                         rb->idstr, start, length, ret);
+        }
+    } else {
+        error_report("ram_block_discard_range: Overrun block '%s' (%" PRIu64
+                     "/%zx/" RAM_ADDR_FMT")",
+                     rb->idstr, start, length, rb->used_length);
+    }
+
+err:
+    return ret;
+}
+
 #endif
diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h
index bd15853e51..1350c2e441 100644
--- a/include/exec/cpu-common.h
+++ b/include/exec/cpu-common.h
@@ -105,6 +105,7 @@ typedef int (RAMBlockIterFunc)(const char *block_name, void *host_addr,
     ram_addr_t offset, ram_addr_t length, void *opaque);
 
 int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque);
+int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length);
 
 #endif
 
diff --git a/include/migration/postcopy-ram.h b/include/migration/postcopy-ram.h
index b6a7491f2d..43bbbcadc5 100644
--- a/include/migration/postcopy-ram.h
+++ b/include/migration/postcopy-ram.h
@@ -35,13 +35,6 @@ int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages);
 int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis);
 
 /*
- * Discard the contents of 'length' bytes from 'start'
- * We can assume that if we've been called postcopy_ram_hosttest returned true
- */
-int postcopy_ram_discard_range(MigrationIncomingState *mis, uint8_t *start,
-                               size_t length);
-
-/*
  * Userfault requires us to mark RAM as NOHUGEPAGE prior to discard
  * however leaving it until after precopy means that most of the precopy
  * data is still THPd
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index a40dddbaf6..1e3d22fddc 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -200,27 +200,6 @@ out:
     return ret;
 }
 
-/**
- * postcopy_ram_discard_range: Discard a range of memory.
- * We can assume that if we've been called postcopy_ram_hosttest returned true.
- *
- * @mis: Current incoming migration state.
- * @start, @length: range of memory to discard.
- *
- * returns: 0 on success.
- */
-int postcopy_ram_discard_range(MigrationIncomingState *mis, uint8_t *start,
-                               size_t length)
-{
-    trace_postcopy_ram_discard_range(start, length);
-    if (madvise(start, length, MADV_DONTNEED)) {
-        error_report("%s MADV_DONTNEED: %s", __func__, strerror(errno));
-        return -1;
-    }
-
-    return 0;
-}
-
 /*
  * Setup an area of RAM so that it *can* be used for postcopy later; this
  * must be done right at the start prior to pre-copy.
@@ -239,7 +218,7 @@ static int init_range(const char *block_name, void *host_addr,
      * - we're going to get the copy from the source anyway.
      * (Precopy will just overwrite this data, so doesn't need the discard)
      */
-    if (postcopy_ram_discard_range(mis, host_addr, length)) {
+    if (ram_discard_range(mis, block_name, 0, length)) {
         return -1;
     }
 
@@ -658,13 +637,6 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
     return -1;
 }
 
-int postcopy_ram_discard_range(MigrationIncomingState *mis, uint8_t *start,
-                               size_t length)
-{
-    assert(0);
-    return -1;
-}
-
 int postcopy_ram_prepare_discard(MigrationIncomingState *mis)
 {
     assert(0);
diff --git a/migration/ram.c b/migration/ram.c
index 7c5cdf98c9..44fe960eb5 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1890,6 +1890,8 @@ int ram_discard_range(MigrationIncomingState *mis,
 {
     int ret = -1;
 
+    trace_ram_discard_range(block_name, start, length);
+
     rcu_read_lock();
     RAMBlock *rb = qemu_ram_block_by_name(block_name);
 
@@ -1899,27 +1901,7 @@ int ram_discard_range(MigrationIncomingState *mis,
         goto err;
     }
 
-    uint8_t *host_startaddr = rb->host + start;
-
-    if ((uintptr_t)host_startaddr & (qemu_host_page_size - 1)) {
-        error_report("ram_discard_range: Unaligned start address: %p",
-                     host_startaddr);
-        goto err;
-    }
-
-    if ((start + length) <= rb->used_length) {
-        uint8_t *host_endaddr = host_startaddr + length;
-        if ((uintptr_t)host_endaddr & (qemu_host_page_size - 1)) {
-            error_report("ram_discard_range: Unaligned end address: %p",
-                         host_endaddr);
-            goto err;
-        }
-        ret = postcopy_ram_discard_range(mis, host_startaddr, length);
-    } else {
-        error_report("ram_discard_range: Overrun block '%s' (%" PRIu64
-                     "/%zx/" RAM_ADDR_FMT")",
-                     block_name, start, length, rb->used_length);
-    }
+    ret = ram_block_discard_range(rb, start, length);
 
 err:
     rcu_read_unlock();
diff --git a/migration/trace-events b/migration/trace-events
index fa660e35b1..7372ce2a51 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -68,6 +68,7 @@ get_queued_page_not_dirty(const char *block_name, uint64_t tmp_offset, uint64_t
 migration_bitmap_sync_start(void) ""
 migration_bitmap_sync_end(uint64_t dirty_pages) "dirty_pages %" PRIu64
 migration_throttle(void) ""
+ram_discard_range(const char *rbname, uint64_t start, size_t len) "%s: start: %" PRIx64 " %zx"
 ram_load_postcopy_loop(uint64_t addr, int flags) "@%" PRIx64 " %x"
 ram_postcopy_send_discard_bitmap(void) ""
 ram_save_queue_pages(const char *rbname, size_t start, size_t len) "%s: start: %zx len: %zx"
@@ -176,7 +177,6 @@ rdma_start_outgoing_migration_after_rdma_source_init(void) ""
 # migration/postcopy-ram.c
 postcopy_discard_send_finish(const char *ramblock, int nwords, int ncmds) "%s mask words sent=%d in %d commands"
 postcopy_discard_send_range(const char *ramblock, unsigned long start, unsigned long length) "%s:%lx/%lx"
-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_nhp_range(const char *ramblock, void *host_addr, size_t offset, size_t length) "%s: %p offset=%zx length=%zx"