In the past, QEMU would create memory regions that could partially cover
hugetlb pages, making mmap() fail if we would use the mmap_offset as an
fd_offset. For that reason, we never used the mmap_offset as an offset into
the fd and instead always mapped the fd from the very start.

However, that can easily result in us mmap'ing a lot of unnecessary
parts of an fd, possibly repeatedly.

QEMU nowadays does not create memory regions that partially cover huge
pages -- it never really worked with postcopy. QEMU handles merging of
regions that partially cover huge pages (due to holes in boot memory) since
2018 in c1ece84e7c93 ("vhost: Huge page align and merge").

Let's be a bit careful and not unconditionally convert the
mmap_offset into an fd_offset. Instead, let's simply detect the hugetlb
size and pass as much as we can as fd_offset, making sure that we call
mmap() with a properly aligned offset.

With QEMU and a virtio-mem device that is fully plugged (50GiB using 50
memslots) the qemu-storage daemon process consumes in the VA space
1281GiB before this change and 58GiB after this change.

================ Vhost user message ================
Request: VHOST_USER_ADD_MEM_REG (37)
Flags:   0x9
Size:    40
Fds: 59
Adding region 4
    guest_phys_addr: 0x0000000200000000
    memory_size:     0x0000000040000000
    userspace_addr:  0x00007fb73bffe000
    old mmap_offset: 0x0000000080000000
    fd_offset:       0x0000000080000000
    new mmap_offset: 0x0000000000000000
    mmap_addr:       0x00007f02f1bdc000
Successfully added new region
================ Vhost user message ================
Request: VHOST_USER_ADD_MEM_REG (37)
Flags:   0x9
Size:    40
Fds: 59
Adding region 5
    guest_phys_addr: 0x0000000240000000
    memory_size:     0x0000000040000000
    userspace_addr:  0x00007fb77bffe000
    old mmap_offset: 0x00000000c0000000
    fd_offset:       0x00000000c0000000
    new mmap_offset: 0x0000000000000000
    mmap_addr:       0x00007f0284000000
Successfully added new region

Reviewed-by: Raphael Norwitz <raphael@enfabrica.net>
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 subprojects/libvhost-user/libvhost-user.c | 54 ++++++++++++++++++++---
 1 file changed, 48 insertions(+), 6 deletions(-)

diff --git a/subprojects/libvhost-user/libvhost-user.c b/subprojects/libvhost-user/libvhost-user.c
index ef6353d847..55aef5fcc6 100644
--- a/subprojects/libvhost-user/libvhost-user.c
+++ b/subprojects/libvhost-user/libvhost-user.c
@@ -43,6 +43,8 @@
 #include <fcntl.h>
 #include <sys/ioctl.h>
 #include <linux/vhost.h>
+#include <sys/vfs.h>
+#include <linux/magic.h>
 
 #ifdef __NR_userfaultfd
 #include <linux/userfaultfd.h>
@@ -281,12 +283,32 @@ vu_remove_all_mem_regs(VuDev *dev)
     dev->nregions = 0;
 }
 
+static size_t
+get_fd_hugepagesize(int fd)
+{
+#if defined(__linux__)
+    struct statfs fs;
+    int ret;
+
+    do {
+        ret = fstatfs(fd, &fs);
+    } while (ret != 0 && errno == EINTR);
+
+    if (!ret && (unsigned int)fs.f_type == HUGETLBFS_MAGIC) {
+        return fs.f_bsize;
+    }
+#endif
+    return 0;
+}
+
 static void
 _vu_add_mem_reg(VuDev *dev, VhostUserMemoryRegion *msg_region, int fd)
 {
     const uint64_t start_gpa = msg_region->guest_phys_addr;
     const uint64_t end_gpa = start_gpa + msg_region->memory_size;
     int prot = PROT_READ | PROT_WRITE;
+    uint64_t mmap_offset, fd_offset;
+    size_t hugepagesize;
     VuDevRegion *r;
     void *mmap_addr;
     int low = 0;
@@ -300,7 +322,7 @@ _vu_add_mem_reg(VuDev *dev, VhostUserMemoryRegion *msg_region, int fd)
            msg_region->memory_size);
     DPRINT("    userspace_addr:  0x%016"PRIx64"\n",
            msg_region->userspace_addr);
-    DPRINT("    mmap_offset:     0x%016"PRIx64"\n",
+    DPRINT("    old mmap_offset: 0x%016"PRIx64"\n",
            msg_region->mmap_offset);
 
     if (dev->postcopy_listening) {
@@ -335,11 +357,31 @@ _vu_add_mem_reg(VuDev *dev, VhostUserMemoryRegion *msg_region, int fd)
     idx = low;
 
     /*
-     * We don't use offset argument of mmap() since the mapped address has
-     * to be page aligned, and we use huge pages.
+     * Convert most of msg_region->mmap_offset to fd_offset. In almost all
+     * cases, this will leave us with mmap_offset == 0, mmap()'ing only
+     * what we really need. Only if a memory region would partially cover
+     * hugetlb pages, we'd get mmap_offset != 0, which usually doesn't happen
+     * anymore (i.e., modern QEMU).
+     *
+     * Note that mmap() with hugetlb would fail if the offset into the file
+     * is not aligned to the huge page size.
      */
-    mmap_addr = mmap(0, msg_region->memory_size + msg_region->mmap_offset,
-                     prot, MAP_SHARED | MAP_NORESERVE, fd, 0);
+    hugepagesize = get_fd_hugepagesize(fd);
+    if (hugepagesize) {
+        fd_offset = ALIGN_DOWN(msg_region->mmap_offset, hugepagesize);
+        mmap_offset = msg_region->mmap_offset - fd_offset;
+    } else {
+        fd_offset = msg_region->mmap_offset;
+        mmap_offset = 0;
+    }
+
+    DPRINT("    fd_offset:       0x%016"PRIx64"\n",
+           fd_offset);
+    DPRINT("    new mmap_offset: 0x%016"PRIx64"\n",
+           mmap_offset);
+
+    mmap_addr = mmap(0, msg_region->memory_size + mmap_offset,
+                     prot, MAP_SHARED | MAP_NORESERVE, fd, fd_offset);
     if (mmap_addr == MAP_FAILED) {
         vu_panic(dev, "region mmap error: %s", strerror(errno));
         return;
@@ -354,7 +396,7 @@ _vu_add_mem_reg(VuDev *dev, VhostUserMemoryRegion *msg_region, int fd)
     r->size = msg_region->memory_size;
     r->qva = msg_region->userspace_addr;
     r->mmap_addr = (uint64_t)(uintptr_t)mmap_addr;
-    r->mmap_offset = msg_region->mmap_offset;
+    r->mmap_offset = mmap_offset;
     dev->nregions++;
 
     if (dev->postcopy_listening) {
-- 
2.43.0