memory: Introduce RAM_NORESERVE and wire it up in qemu_ram_mmap()

Let's introduce RAM_NORESERVE, allowing mmap'ing with MAP_NORESERVE. The
new flag has the following semantics:

"
RAM is mmap-ed with MAP_NORESERVE. When set, reserving swap space (or huge
pages if applicable) is skipped: will bail out if not supported. When not
set, the OS will do the reservation, if supported for the memory type.
"

Allow passing it into:
- memory_region_init_ram_nomigrate()
- memory_region_init_resizeable_ram()
- memory_region_init_ram_from_file()

... and teach qemu_ram_mmap() and qemu_anon_ram_alloc() about the flag.
Bail out if the flag is not supported, which is the case right now for
both, POSIX and win32. We will add Linux support next and allow specifying
RAM_NORESERVE via memory backends.

The target use case is virtio-mem, which dynamically exposes memory
inside a large, sparse memory area to the VM.

Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Acked-by: Eduardo Habkost <ehabkost@redhat.com> for memory backend and machine core
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210510114328.21835-9-david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 12 insertions, 3 deletions

diff --git a/softmmu/physmem.c b/softmmu/physmem.c
index a110aa67fd..11ea8e19a6 100644
--- a/softmmu/physmem.c
+++ b/softmmu/physmem.c
@@ -1591,6 +1591,7 @@ static void *file_ram_alloc(RAMBlock *block,
     qemu_map_flags = readonly ? QEMU_MAP_READONLY : 0;
     qemu_map_flags |= (block->flags & RAM_SHARED) ? QEMU_MAP_SHARED : 0;
     qemu_map_flags |= (block->flags & RAM_PMEM) ? QEMU_MAP_SYNC : 0;
+    qemu_map_flags |= (block->flags & RAM_NORESERVE) ? QEMU_MAP_NORESERVE : 0;
     area = qemu_ram_mmap(fd, memory, block->mr->align, qemu_map_flags, offset);
     if (area == MAP_FAILED) {
         error_setg_errno(errp, errno,
@@ -1716,6 +1717,11 @@ bool qemu_ram_is_shared(RAMBlock *rb)
     return rb->flags & RAM_SHARED;
 }
 
+bool qemu_ram_is_noreserve(RAMBlock *rb)
+{
+    return rb->flags & RAM_NORESERVE;
+}
+
 /* Note: Only set at the start of postcopy */
 bool qemu_ram_is_uf_zeroable(RAMBlock *rb)
 {
@@ -1950,6 +1956,7 @@ static void dirty_memory_extend(ram_addr_t old_ram_size,
 
 static void ram_block_add(RAMBlock *new_block, Error **errp)
 {
+    const bool noreserve = qemu_ram_is_noreserve(new_block);
     const bool shared = qemu_ram_is_shared(new_block);
     RAMBlock *block;
     RAMBlock *last_block = NULL;
@@ -1973,7 +1980,7 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
         } else {
             new_block->host = qemu_anon_ram_alloc(new_block->max_length,
                                                   &new_block->mr->align,
-                                                  shared);
+                                                  shared, noreserve);
             if (!new_block->host) {
                 error_setg_errno(errp, errno,
                                  "cannot set up guest memory '%s'",
@@ -2045,7 +2052,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
     int64_t file_size, file_align;
 
     /* Just support these ram flags by now. */
-    assert((ram_flags & ~(RAM_SHARED | RAM_PMEM)) == 0);
+    assert((ram_flags & ~(RAM_SHARED | RAM_PMEM | RAM_NORESERVE)) == 0);
 
     if (xen_enabled()) {
         error_setg(errp, "-mem-path not supported with Xen");
@@ -2137,6 +2144,8 @@ RAMBlock *qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size,
     Error *local_err = NULL;
 
     assert((ram_flags & ~(RAM_SHARED | RAM_RESIZEABLE | RAM_PREALLOC)) == 0);
+    assert((ram_flags & ~(RAM_SHARED | RAM_RESIZEABLE | RAM_PREALLOC |
+                          RAM_NORESERVE)) == 0);
     assert(!host ^ (ram_flags & RAM_PREALLOC));
 
     size = HOST_PAGE_ALIGN(size);
@@ -2170,7 +2179,7 @@ RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
 RAMBlock *qemu_ram_alloc(ram_addr_t size, uint32_t ram_flags,
                          MemoryRegion *mr, Error **errp)
 {
-    assert((ram_flags & ~RAM_SHARED) == 0);
+    assert((ram_flags & ~(RAM_SHARED | RAM_NORESERVE)) == 0);
     return qemu_ram_alloc_internal(size, size, NULL, NULL, ram_flags, mr, errp);
 }