[RFC,14/19] physmem: Add ram_block_convert_range

Commit Message

Xiaoyao Li July 31, 2023, 4:21 p.m. UTC

From: Chao Peng <[e-mail]>

This new routine adds support for memory conversion between
shared/private memory for gmem fd based private ram_block.

Signed-off-by: Chao Peng <[e-mail]>
Signed-off-by: Xiaoyao Li <[e-mail]>
---
 include/exec/cpu-common.h |  2 ++
 softmmu/physmem.c         | 61 ++++++++++++++++++++++++++++++---------
 2 files changed, 50 insertions(+), 13 deletions(-)

Patch

diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h
index 87dc9a752c9a..558684b9f246 100644
--- a/include/exec/cpu-common.h
+++ b/include/exec/cpu-common.h
@@ -157,6 +157,8 @@  typedef int (RAMBlockIterFunc)(RAMBlock *rb, void *opaque);
 
 int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque);
 int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length);
+int ram_block_convert_range(RAMBlock *rb, uint64_t start, size_t length,
+                            bool shared_to_private);
 
 #endif
 
diff --git a/softmmu/physmem.c b/softmmu/physmem.c
index 05c981e5c18e..2acc8bee5b33 100644
--- a/softmmu/physmem.c
+++ b/softmmu/physmem.c
@@ -3415,15 +3415,9 @@  int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque)
     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)
+static int ram_block_discard_range_fd(RAMBlock *rb, uint64_t start,
+                                      size_t length, int fd)
+
 {
     int ret = -1;
 
@@ -3449,8 +3443,8 @@  int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
          *    fallocate works on hugepages and shmem
          *    shared anonymous memory requires madvise REMOVE
          */
-        need_madvise = (rb->page_size == qemu_host_page_size);
-        need_fallocate = rb->fd != -1;
+        need_madvise = (rb->page_size == qemu_host_page_size) && (rb->fd == fd);
+        need_fallocate = fd != -1;
         if (need_fallocate) {
             /* For a file, this causes the area of the file to be zero'd
              * if read, and for hugetlbfs also causes it to be unmapped
@@ -3475,7 +3469,7 @@  int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
                                  " users of the file", __func__);
             }
 
-            ret = fallocate(rb->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+            ret = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
                             start, length);
             if (ret) {
                 ret = -errno;
@@ -3498,7 +3492,7 @@  int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
              * fallocate'd away).
              */
 #if defined(CONFIG_MADVISE)
-            if (qemu_ram_is_shared(rb) && rb->fd < 0) {
+            if (qemu_ram_is_shared(rb) && fd < 0) {
                 ret = madvise(host_startaddr, length, QEMU_MADV_REMOVE);
             } else {
                 ret = madvise(host_startaddr, length, QEMU_MADV_DONTNEED);
@@ -3528,6 +3522,20 @@  err:
     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)
+{
+    return ram_block_discard_range_fd(rb, start, length, rb->fd);
+}
+
+
 bool ramblock_is_pmem(RAMBlock *rb)
 {
     return rb->flags & RAM_PMEM;
@@ -3715,3 +3723,30 @@  bool ram_block_discard_is_required(void)
     return qatomic_read(&ram_block_discard_required_cnt) ||
            qatomic_read(&ram_block_coordinated_discard_required_cnt);
 }
+
+int ram_block_convert_range(RAMBlock *rb, uint64_t start, size_t length,
+                            bool shared_to_private)
+{
+    int fd;
+
+    if (!rb || rb->gmem_fd < 0) {
+        return -1;
+    }
+
+    if (!QEMU_PTR_IS_ALIGNED(start, rb->page_size) ||
+        !QEMU_PTR_IS_ALIGNED(length, rb->page_size)) {
+        return -1;
+    }
+
+    if (length > rb->max_length) {
+        return -1;
+    }
+
+    if (shared_to_private) {
+        fd = rb->fd;
+    } else {
+        fd = rb->gmem_fd;
+    }
+
+    return ram_block_discard_range_fd(rb, start, length, fd);
+}