From eb99baa9b371e2f2cd119ad42fa8b236830d8df1 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 11 Jan 2022 13:39:39 +0100 Subject: libvhost-user: Map shared RAM with MAP_NORESERVE to support virtio-mem with hugetlb MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For fd-based shared memory, MAP_NORESERVE is only effective for hugetlb, otherwise it's ignored. Older Linux versions that didn't support reservation of huge pages ignored MAP_NORESERVE completely. The first client to mmap a hugetlb fd without MAP_NORESERVE will trigger reservation of huge pages for the whole mmapped range. There are two cases to consider: 1) QEMU mapped RAM without MAP_NORESERVE We're not dealing with a sparse mapping, huge pages for the whole range have already been reserved by QEMU. An additional mmap() without MAP_NORESERVE won't have any effect on the reservation. 2) QEMU mapped RAM with MAP_NORESERVE We're delaing with a sparse mapping, no huge pages should be reserved. Further mappings without MAP_NORESERVE should be avoided. For 1), it doesn't matter if we set MAP_NORESERVE or not, so we can simply set it. For 2), we'd be overriding QEMUs decision and trigger reservation of huge pages, which might just fail if there are not sufficient huge pages around. We must map with MAP_NORESERVE. This change is required to support virtio-mem with hugetlb: a virtio-mem device mapped into the guest physical memory corresponds to a sparse memory mapping and QEMU maps this memory with MAP_NORESERVE. Whenever memory in that sparse region will be accessed by the VM, QEMU populates huge pages for the affected range by preallocating memory and handling any preallocation errors gracefully. So let's map shared RAM with MAP_NORESERVE. As libvhost-user only supports Linux, there shouldn't be anything to take care of in regard of other OS support. Without this change, libvhost-user will fail mapping the region if there are currently not enough huge pages to perform the reservation: fv_panic: libvhost-user: region mmap error: Cannot allocate memory Cc: "Marc-André Lureau" Cc: "Michael S. Tsirkin" Cc: Paolo Bonzini Cc: Raphael Norwitz Cc: Stefan Hajnoczi Cc: Dr. David Alan Gilbert Signed-off-by: David Hildenbrand Message-Id: <20220111123939.132659-1-david@redhat.com> Acked-by: Raphael Norwitz --- subprojects/libvhost-user/libvhost-user.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'subprojects') diff --git a/subprojects/libvhost-user/libvhost-user.c b/subprojects/libvhost-user/libvhost-user.c index 0ee43b8e93..47d2efc60f 100644 --- a/subprojects/libvhost-user/libvhost-user.c +++ b/subprojects/libvhost-user/libvhost-user.c @@ -751,12 +751,12 @@ vu_add_mem_reg(VuDev *dev, VhostUserMsg *vmsg) { * accessing it before we userfault. */ mmap_addr = mmap(0, dev_region->size + dev_region->mmap_offset, - PROT_NONE, MAP_SHARED, + PROT_NONE, MAP_SHARED | MAP_NORESERVE, vmsg->fds[0], 0); } else { mmap_addr = mmap(0, dev_region->size + dev_region->mmap_offset, - PROT_READ | PROT_WRITE, MAP_SHARED, vmsg->fds[0], - 0); + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_NORESERVE, + vmsg->fds[0], 0); } if (mmap_addr == MAP_FAILED) { @@ -920,7 +920,7 @@ vu_set_mem_table_exec_postcopy(VuDev *dev, VhostUserMsg *vmsg) * accessing it before we userfault */ mmap_addr = mmap(0, dev_region->size + dev_region->mmap_offset, - PROT_NONE, MAP_SHARED, + PROT_NONE, MAP_SHARED | MAP_NORESERVE, vmsg->fds[i], 0); if (mmap_addr == MAP_FAILED) { @@ -1007,7 +1007,7 @@ vu_set_mem_table_exec(VuDev *dev, VhostUserMsg *vmsg) * mapped address has to be page aligned, and we use huge * pages. */ mmap_addr = mmap(0, dev_region->size + dev_region->mmap_offset, - PROT_READ | PROT_WRITE, MAP_SHARED, + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_NORESERVE, vmsg->fds[i], 0); if (mmap_addr == MAP_FAILED) { -- cgit v1.2.3