softmmu/physmem: Fix ram_block_discard_range() to handle shared anonymous memory

We can create shared anonymous memory via
    "-object memory-backend-ram,share=on,..."
which is, for example, required by PVRDMA for mremap() to work.

Shared anonymous memory is weird, though. Instead of MADV_DONTNEED, we
have to use MADV_REMOVE: MADV_DONTNEED will only remove / zap all
relevant page table entries of the current process, the backend storage
will not get removed, resulting in no reduced memory consumption and
a repopulation of previous content on next access.

Shared anonymous memory is internally really just shmem, but without a
fd exposed. As we cannot use fallocate() without the fd to discard the
backing storage, MADV_REMOVE gets the same job done without a fd as
documented in "man 2 madvise". Removing backing storage implicitly
invalidates all page table entries with relevant mappings - an additional
MADV_DONTNEED is not required.

Fixes: 06329ccecfa0 ("mem: add share parameter to memory-backend-ram")
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210406080126.24010-3-david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h
index 236a045..18a9e3f 100644 (file)
--- a/include/qemu/osdep.h
+++ b/include/qemu/osdep.h
@@ -410,7 +410,7 @@ void qemu_anon_ram_free(void *ptr, size_t size);
 #ifdef MADV_REMOVE
 #define QEMU_MADV_REMOVE MADV_REMOVE
 #else
-#define QEMU_MADV_REMOVE QEMU_MADV_INVALID
+#define QEMU_MADV_REMOVE QEMU_MADV_DONTNEED
 #endif
 
 #elif defined(CONFIG_POSIX_MADVISE)
@@ -424,7 +424,7 @@ void qemu_anon_ram_free(void *ptr, size_t size);
 #define QEMU_MADV_DONTDUMP QEMU_MADV_INVALID
 #define QEMU_MADV_HUGEPAGE  QEMU_MADV_INVALID
 #define QEMU_MADV_NOHUGEPAGE  QEMU_MADV_INVALID
-#define QEMU_MADV_REMOVE QEMU_MADV_INVALID
+#define QEMU_MADV_REMOVE QEMU_MADV_DONTNEED
 
 #else /* no-op */
 

diff --git a/softmmu/physmem.c b/softmmu/physmem.c
index b78b30e..c0a3c47 100644 (file)
--- a/softmmu/physmem.c
+++ b/softmmu/physmem.c
@@ -3527,6 +3527,7 @@ int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
         /* The logic here is messy;
          *    madvise DONTNEED fails for hugepages
          *    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;
@@ -3560,7 +3561,11 @@ int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
              * fallocate'd away).
              */
 #if defined(CONFIG_MADVISE)
-            ret =  madvise(host_startaddr, length, MADV_DONTNEED);
+            if (qemu_ram_is_shared(rb) && rb->fd < 0) {
+                ret = madvise(host_startaddr, length, QEMU_MADV_REMOVE);
+            } else {
+                ret = madvise(host_startaddr, length, QEMU_MADV_DONTNEED);
+            }
             if (ret) {
                 ret = -errno;
                 error_report("ram_block_discard_range: Failed to discard range "