[PATCH v2 8/9] util/mmap-alloc: Support RAM_NORESERVE via MAP_NORESERVE

[David Hildenbrand <david@redhat.com>]

Let's support RAM_NORESERVE via MAP_NORESERVE. At least on Linux,
the flag has no effect on shared mappings - except for hugetlbfs.

Linux man page:
  "MAP_NORESERVE: Do not reserve swap space for this mapping. When swap
  space is reserved, one has the guarantee that it is possible to modify
  the mapping. When swap space is not reserved one might get SIGSEGV
  upon a write if no physical memory is available. See also the discussion
  of the file /proc/sys/vm/overcommit_memory in proc(5). In kernels before
  2.6, this flag had effect only for private writable mappings."

Note that the "guarantee" part is wrong with memory overcommit in Linux.

Also, in Linux hugetlbfs is treated differently - we configure reservation
of huge pages from the pool, not reservation of swap space (huge pages
cannot be swapped).

The rough behavior is [1]:
a) !Hugetlbfs:

  1) Without MAP_NORESERVE *or* with memory overcommit under Linux
     disabled ("/proc/sys/vm/overcommit_memory == 2"), the following
     accounting/reservation happens:
      For a file backed map
       SHARED or READ-only - 0 cost (the file is the map not swap)
       PRIVATE WRITABLE - size of mapping per instance

      For an anonymous or /dev/zero map
       SHARED   - size of mapping
       PRIVATE READ-only - 0 cost (but of little use)
       PRIVATE WRITABLE - size of mapping per instance

  2) With MAP_NORESERVE, no accounting/reservation happens.

b) Hugetlbfs:

  1) Without MAP_NORESERVE, huge pages are reserved.

  2) With MAP_NORESERVE, no huge pages are reserved.

Note: With "/proc/sys/vm/overcommit_memory == 0", we were already able
to configure it for !hugetlbfs globally; this toggle now allows
configuring it more fine-grained, not for the whole system.

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

[1] https://www.kernel.org/doc/Documentation/vm/overcommit-accounting

Signed-off-by: David Hildenbrand <david@redhat.com>
---
 softmmu/physmem.c |  1 +
 util/mmap-alloc.c | 74 ++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 71 insertions(+), 4 deletions(-)

diff --git a/softmmu/physmem.c b/softmmu/physmem.c
index 768e462529..3e85ca8898 100644
--- a/softmmu/physmem.c
+++ b/softmmu/physmem.c
@@ -2224,6 +2224,7 @@ void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
                 abort();
             } else {
                 flags = MAP_FIXED;
+                flags |= (block->flags & RAM_NORESERVE) ? MAP_NORESERVE : 0;
                 if (block->fd >= 0) {
                     flags |= (block->flags & RAM_SHARED ?
                               MAP_SHARED : MAP_PRIVATE);
diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c
index 397cb20a76..29c7a5035b 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/cutils.h"
 #include "qemu/error-report.h"
 
 #define HUGETLBFS_MAGIC       0x958458f6
@@ -120,7 +121,8 @@ static void *mmap_reserve(size_t size, int fd)
  * it accessible.
  */
 static void *mmap_activate(void *ptr, size_t size, int fd, bool readonly,
-                           bool shared, bool is_pmem, off_t map_offset)
+                           bool shared, bool is_pmem, bool noreserve,
+                           off_t map_offset)
 {
     const int prot = PROT_READ | (readonly ? 0 : PROT_WRITE);
     int map_sync_flags = 0;
@@ -129,6 +131,7 @@ static void *mmap_activate(void *ptr, size_t size, int fd, bool readonly,
 
     flags |= fd == -1 ? MAP_ANONYMOUS : 0;
     flags |= shared ? MAP_SHARED : MAP_PRIVATE;
+    flags |= noreserve ? MAP_NORESERVE : 0;
     if (shared && is_pmem) {
         map_sync_flags = MAP_SYNC | MAP_SHARED_VALIDATE;
     }
@@ -171,6 +174,70 @@ static inline size_t mmap_guard_pagesize(int fd)
 #endif
 }
 
+#define OVERCOMMIT_MEMORY_PATH "/proc/sys/vm/overcommit_memory"
+static bool map_noreserve_effective(int fd, bool readonly, bool shared)
+{
+#if defined(__linux__)
+    gchar *content = NULL;
+    const char *endptr;
+    unsigned int tmp;
+
+    /*
+     * Shared anonymous memory -- for sharing memory with forked children --
+     * behaves in weird ways (i.e., in respect to memory accounting) and QEMU
+     * fortunately doesn't make use of it for guest RAM. Let's assert it
+     * remains that way.
+     */
+    g_assert(!shared || fd >= 0);
+
+    /*
+     * hugeltbfs accounting is different than ordinary swap reservation:
+     * a) Hugetlb pages from the pool are reserved for both private and
+     *    shared mappings. For shared mappings, reservations are tracked
+     *    per file - all mappers have to specify MAP_NORESERVE.
+     * b) MAP_NORESERVE is not affected by /proc/sys/vm/overcommit_memory.
+     */
+    if (qemu_fd_getpagesize(fd) != qemu_real_host_page_size) {
+        return true;
+    }
+
+    /*
+     * Accountable mappings in the kernel that can be affected by MAP_NORESEVE
+     * are private writable mappings (see mm/mmap.c:accountable_mapping() in
+     * Linux). For all shared or readonly mappings, MAP_NORESERVE is always
+     * implicitly active -- no reservation; this includes shmem.
+     */
+    if (readonly || shared) {
+        return true;
+    }
+
+    /*
+     * MAP_NORESERVE is globally ignored for private writable mappings when
+     * overcommit is set to "never". Sparse memory regions aren't really
+     * possible in this system configuration.
+     *
+     * Bail out now instead of silently committing way more memory than
+     * currently desired by the user.
+     */
+    if (g_file_get_contents(OVERCOMMIT_MEMORY_PATH, &content, NULL, NULL) &&
+        !qemu_strtoui(content, &endptr, 0, &tmp) &&
+        (!endptr || *endptr == '\n')) {
+        if (tmp == 2) {
+            error_report("Skipping reservation of swap space is not supported:"
+                         " \"" OVERCOMMIT_MEMORY_PATH "\" is \"2\"");
+            return false;
+        }
+        return true;
+    }
+    /* this interface has been around since Linux 2.6 */
+    error_report("Skipping reservation of swap space is not supported:"
+                 " Could not read: \"" OVERCOMMIT_MEMORY_PATH "\"");
+    return false;
+#else
+    return true;
+#endif
+}
+
 void *qemu_ram_mmap(int fd,
                     size_t size,
                     size_t align,
@@ -184,8 +251,7 @@ void *qemu_ram_mmap(int fd,
     size_t offset, total;
     void *ptr, *guardptr;
 
-    if (noreserve) {
-        error_report("Skipping reservation of swap space is not supported");
+    if (noreserve && !map_noreserve_effective(fd, shared, readonly)) {
         return MAP_FAILED;
     }
 
@@ -207,7 +273,7 @@ void *qemu_ram_mmap(int fd,
     offset = QEMU_ALIGN_UP((uintptr_t)guardptr, align) - (uintptr_t)guardptr;
 
     ptr = mmap_activate(guardptr + offset, size, fd, readonly, shared, is_pmem,
-                        map_offset);
+                        noreserve, map_offset);
     if (ptr == MAP_FAILED) {
         munmap(guardptr, total);
         return MAP_FAILED;
-- 
2.29.2