Merge tag 'mem-2023-01-02' of https://github.com/davidhildenbrand/qemu into staging

Hi,

"Host Memory Backends" and "Memory devices" queue ("mem"):
- virtio-mem fixes
- Use new MPOL_PREFERRED_MANY mbind() policy for memory backends if
  possible

# gpg: Signature made Mon 02 Jan 2023 11:22:04 GMT
# gpg:                using RSA key 1BD9CAAD735C4C3A460DFCCA4DDE10F700FF835A
# gpg:                issuer "david@redhat.com"
# gpg: Good signature from "David Hildenbrand <david@redhat.com>" [marginal]
# gpg:                 aka "David Hildenbrand <davidhildenbrand@gmail.com>" [full]
# gpg:                 aka "David Hildenbrand <hildenbr@in.tum.de>" [unknown]
# Primary key fingerprint: 1BD9 CAAD 735C 4C3A 460D  FCCA 4DDE 10F7 00FF 835A

* tag 'mem-2023-01-02' of https://github.com/davidhildenbrand/qemu:
  hostmem: Honor multiple preferred nodes if possible
  virtio-mem: Fix typo in function name
  virtio-mem: Fix the iterator variable in a vmem->rdl_list loop
  virtio-mem: Fix the bitmap index of the section offset

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

3 files changed, 31 insertions, 11 deletions

diff --git a/backends/hostmem.c b/backends/hostmem.c
index 8640294c10..747e7838c0 100644
--- a/backends/hostmem.c
+++ b/backends/hostmem.c
@@ -23,7 +23,12 @@
 
 #ifdef CONFIG_NUMA
 #include <numaif.h>
+#include <numa.h>
 QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_DEFAULT != MPOL_DEFAULT);
+/*
+ * HOST_MEM_POLICY_PREFERRED may either translate to MPOL_PREFERRED or
+ * MPOL_PREFERRED_MANY, see comments further below.
+ */
 QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_PREFERRED != MPOL_PREFERRED);
 QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_BIND != MPOL_BIND);
 QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_INTERLEAVE != MPOL_INTERLEAVE);
@@ -346,6 +351,7 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
          * before mbind(). note: MPOL_MF_STRICT is ignored on hugepages so
          * this doesn't catch hugepage case. */
         unsigned flags = MPOL_MF_STRICT | MPOL_MF_MOVE;
+        int mode = backend->policy;
 
         /* check for invalid host-nodes and policies and give more verbose
          * error messages than mbind(). */
@@ -369,9 +375,18 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
                BITS_TO_LONGS(MAX_NODES + 1) * sizeof(unsigned long));
         assert(maxnode <= MAX_NODES);
 
+#ifdef HAVE_NUMA_HAS_PREFERRED_MANY
+        if (mode == MPOL_PREFERRED && numa_has_preferred_many() > 0) {
+            /*
+             * Replace with MPOL_PREFERRED_MANY otherwise the mbind() below
+             * silently picks the first node.
+             */
+            mode = MPOL_PREFERRED_MANY;
+        }
+#endif
+
         if (maxnode &&
-            mbind(ptr, sz, backend->policy, backend->host_nodes, maxnode + 1,
-                  flags)) {
+            mbind(ptr, sz, mode, backend->host_nodes, maxnode + 1, flags)) {
             if (backend->policy != MPOL_DEFAULT || errno != ENOSYS) {
                 error_setg_errno(errp, errno,
                                  "cannot bind memory to host NUMA nodes");
diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c
index d96bde1fab..1ed1f5a4af 100644
--- a/hw/virtio/virtio-mem.c
+++ b/hw/virtio/virtio-mem.c
@@ -207,7 +207,7 @@ static int virtio_mem_for_each_unplugged_range(const VirtIOMEM *vmem, void *arg,
  *
  * Returns false if the intersection is empty, otherwise returns true.
  */
-static bool virito_mem_intersect_memory_section(MemoryRegionSection *s,
+static bool virtio_mem_intersect_memory_section(MemoryRegionSection *s,
                                                 uint64_t offset, uint64_t size)
 {
     uint64_t start = MAX(s->offset_within_region, offset);
@@ -235,7 +235,7 @@ static int virtio_mem_for_each_plugged_section(const VirtIOMEM *vmem,
     uint64_t offset, size;
     int ret = 0;
 
-    first_bit = s->offset_within_region / vmem->bitmap_size;
+    first_bit = s->offset_within_region / vmem->block_size;
     first_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size, first_bit);
     while (first_bit < vmem->bitmap_size) {
         MemoryRegionSection tmp = *s;
@@ -245,7 +245,7 @@ static int virtio_mem_for_each_plugged_section(const VirtIOMEM *vmem,
                                       first_bit + 1) - 1;
         size = (last_bit - first_bit + 1) * vmem->block_size;
 
-        if (!virito_mem_intersect_memory_section(&tmp, offset, size)) {
+        if (!virtio_mem_intersect_memory_section(&tmp, offset, size)) {
             break;
         }
         ret = cb(&tmp, arg);
@@ -267,7 +267,7 @@ static int virtio_mem_for_each_unplugged_section(const VirtIOMEM *vmem,
     uint64_t offset, size;
     int ret = 0;
 
-    first_bit = s->offset_within_region / vmem->bitmap_size;
+    first_bit = s->offset_within_region / vmem->block_size;
     first_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size, first_bit);
     while (first_bit < vmem->bitmap_size) {
         MemoryRegionSection tmp = *s;
@@ -277,7 +277,7 @@ static int virtio_mem_for_each_unplugged_section(const VirtIOMEM *vmem,
                                  first_bit + 1) - 1;
         size = (last_bit - first_bit + 1) * vmem->block_size;
 
-        if (!virito_mem_intersect_memory_section(&tmp, offset, size)) {
+        if (!virtio_mem_intersect_memory_section(&tmp, offset, size)) {
             break;
         }
         ret = cb(&tmp, arg);
@@ -313,7 +313,7 @@ static void virtio_mem_notify_unplug(VirtIOMEM *vmem, uint64_t offset,
     QLIST_FOREACH(rdl, &vmem->rdl_list, next) {
         MemoryRegionSection tmp = *rdl->section;
 
-        if (!virito_mem_intersect_memory_section(&tmp, offset, size)) {
+        if (!virtio_mem_intersect_memory_section(&tmp, offset, size)) {
             continue;
         }
         rdl->notify_discard(rdl, &tmp);
@@ -329,7 +329,7 @@ static int virtio_mem_notify_plug(VirtIOMEM *vmem, uint64_t offset,
     QLIST_FOREACH(rdl, &vmem->rdl_list, next) {
         MemoryRegionSection tmp = *rdl->section;
 
-        if (!virito_mem_intersect_memory_section(&tmp, offset, size)) {
+        if (!virtio_mem_intersect_memory_section(&tmp, offset, size)) {
             continue;
         }
         ret = rdl->notify_populate(rdl, &tmp);
@@ -341,12 +341,12 @@ static int virtio_mem_notify_plug(VirtIOMEM *vmem, uint64_t offset,
     if (ret) {
         /* Notify all already-notified listeners. */
         QLIST_FOREACH(rdl2, &vmem->rdl_list, next) {
-            MemoryRegionSection tmp = *rdl->section;
+            MemoryRegionSection tmp = *rdl2->section;
 
             if (rdl2 == rdl) {
                 break;
             }
-            if (!virito_mem_intersect_memory_section(&tmp, offset, size)) {
+            if (!virtio_mem_intersect_memory_section(&tmp, offset, size)) {
                 continue;
             }
             rdl2->notify_discard(rdl2, &tmp);
diff --git a/meson.build b/meson.build
index 4c6f8a674a..3f31db5963 100644
--- a/meson.build
+++ b/meson.build
@@ -1858,6 +1858,11 @@ config_host_data.set('CONFIG_LINUX_AIO', libaio.found())
 config_host_data.set('CONFIG_LINUX_IO_URING', linux_io_uring.found())
 config_host_data.set('CONFIG_LIBPMEM', libpmem.found())
 config_host_data.set('CONFIG_NUMA', numa.found())
+if numa.found()
+  config_host_data.set('HAVE_NUMA_HAS_PREFERRED_MANY',
+                       cc.has_function('numa_has_preferred_many',
+                                       dependencies: numa))
+endif
 config_host_data.set('CONFIG_OPENGL', opengl.found())
 config_host_data.set('CONFIG_PROFILER', get_option('profiler'))
 config_host_data.set('CONFIG_RBD', rbd.found())