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>

3 files changed, 23 insertions, 3 deletions

diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c
index 1ddc0e2..d0cf4aa 100644
--- a/util/mmap-alloc.c
+++ b/util/mmap-alloc.c
@@ -20,6 +20,7 @@
 #include "qemu/osdep.h"
 #include "qemu/mmap-alloc.h"
 #include "qemu/host-utils.h"
+#include "qemu/error-report.h"
 
 #define HUGETLBFS_MAGIC       0x958458f6
 
@@ -121,6 +122,7 @@ static void *mmap_reserve(size_t size, int fd)
 static void *mmap_activate(void *ptr, size_t size, int fd,
                            uint32_t qemu_map_flags, off_t map_offset)
 {
+    const bool noreserve = qemu_map_flags & QEMU_MAP_NORESERVE;
     const bool readonly = qemu_map_flags & QEMU_MAP_READONLY;
     const bool shared = qemu_map_flags & QEMU_MAP_SHARED;
     const bool sync = qemu_map_flags & QEMU_MAP_SYNC;
@@ -129,6 +131,11 @@ static void *mmap_activate(void *ptr, size_t size, int fd,
     int flags = MAP_FIXED;
     void *activated_ptr;
 
+    if (noreserve) {
+        error_report("Skipping reservation of swap space is not supported");
+        return MAP_FAILED;
+    }
+
     flags |= fd == -1 ? MAP_ANONYMOUS : 0;
     flags |= shared ? MAP_SHARED : MAP_PRIVATE;
     if (shared && sync) {
diff --git a/util/oslib-posix.c b/util/oslib-posix.c
index 0dd7784..e8bdb02 100644
--- a/util/oslib-posix.c
+++ b/util/oslib-posix.c
@@ -227,9 +227,11 @@ void *qemu_memalign(size_t alignment, size_t size)
 }
 
 /* alloc shared memory pages */
-void *qemu_anon_ram_alloc(size_t size, uint64_t *alignment, bool shared)
+void *qemu_anon_ram_alloc(size_t size, uint64_t *alignment, bool shared,
+                          bool noreserve)
 {
-    const uint32_t qemu_map_flags = shared ? QEMU_MAP_SHARED : 0;
+    const uint32_t qemu_map_flags = (shared ? QEMU_MAP_SHARED : 0) |
+                                    (noreserve ? QEMU_MAP_NORESERVE : 0);
     size_t align = QEMU_VMALLOC_ALIGN;
     void *ptr = qemu_ram_mmap(-1, size, align, qemu_map_flags, 0);
 
diff --git a/util/oslib-win32.c b/util/oslib-win32.c
index ca99356..ee3a369 100644
--- a/util/oslib-win32.c
+++ b/util/oslib-win32.c
@@ -38,6 +38,7 @@
 #include "trace.h"
 #include "qemu/sockets.h"
 #include "qemu/cutils.h"
+#include "qemu/error-report.h"
 #include <malloc.h>
 
 /* this must come after including "trace.h" */
@@ -76,10 +77,20 @@ static int get_allocation_granularity(void)
     return system_info.dwAllocationGranularity;
 }
 
-void *qemu_anon_ram_alloc(size_t size, uint64_t *align, bool shared)
+void *qemu_anon_ram_alloc(size_t size, uint64_t *align, bool shared,
+                          bool noreserve)
 {
     void *ptr;
 
+    if (noreserve) {
+        /*
+         * We need a MEM_COMMIT before accessing any memory in a MEM_RESERVE
+         * area; we cannot easily mimic POSIX MAP_NORESERVE semantics.
+         */
+        error_report("Skipping reservation of swap space is not supported.");
+        return NULL;
+    }
+
     ptr = VirtualAlloc(NULL, size, MEM_COMMIT, PAGE_READWRITE);
     trace_qemu_anon_ram_alloc(size, ptr);