system/qemu
system/qemu
1
0
Fork 0
mirror of https://gitlab.com/qemu-project/qemu synced 2024-09-30 00:04:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

libvhost-user: Dynamically remap rings after (temporarily?) removing memory regions

Browse source 
Currently, we try to remap all rings whenever we add a single new memory
region. That doesn't quite make sense, because we already map rings when
setting the ring address, and panic if that goes wrong. Likely, that
handling was simply copied from set_mem_table code, where we actually
have to remap all rings.

Remapping all rings might require us to walk quite a lot of memory
regions to perform the address translations. Ideally, we'd simply remove
that remapping.

However, let's be a bit careful. There might be some weird corner cases
where we might temporarily remove a single memory region (e.g., resize
it), that would have worked for now. Further, a ring might be located on
hotplugged memory, and as the VM reboots, we might unplug that memory, to
hotplug memory before resetting the ring addresses.

So let's unmap affected rings as we remove a memory region, and try
dynamically mapping the ring again when required.

Acked-by: Raphael Norwitz <raphael@enfabrica.net>
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20240214151701.29906-14-david@redhat.com>
Tested-by: Mario Casquero <mcasquer@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This commit is contained in:
David Hildenbrand 2024-02-14 16:17:00 +01:00 committed by Michael S. Tsirkin
parent 2a29022768
commit 67f4f663cd
1 changed files with 78 additions and 29 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

107
subprojects/libvhost-user/libvhost-user.c
View file

@ -283,10 +283,75 @@ vu_remove_all_mem_regs(VuDev *dev)
dev->nregions = 0;
}
static bool
map_ring(VuDev *dev, VuVirtq *vq)
{
vq->vring.desc = qva_to_va(dev, vq->vra.desc_user_addr);
vq->vring.used = qva_to_va(dev, vq->vra.used_user_addr);
vq->vring.avail = qva_to_va(dev, vq->vra.avail_user_addr);
DPRINT("Setting virtq addresses:\n");
DPRINT(" vring_desc at %p\n", vq->vring.desc);
DPRINT(" vring_used at %p\n", vq->vring.used);
DPRINT(" vring_avail at %p\n", vq->vring.avail);
return !(vq->vring.desc && vq->vring.used && vq->vring.avail);
}
static bool
vu_is_vq_usable(VuDev *dev, VuVirtq *vq)
{
return likely(!dev->broken) && likely(vq->vring.avail);
if (unlikely(dev->broken)) {
return false;
}
if (likely(vq->vring.avail)) {
return true;
}
/*
* In corner cases, we might temporarily remove a memory region that
* mapped a ring. When removing a memory region we make sure to
* unmap any rings that would be impacted. Let's try to remap if we
* already succeeded mapping this ring once.
*/
if (!vq->vra.desc_user_addr || !vq->vra.used_user_addr ||
!vq->vra.avail_user_addr) {
return false;
}
if (map_ring(dev, vq)) {
vu_panic(dev, "remapping queue on access");
return false;
}
return true;
}
static void
unmap_rings(VuDev *dev, VuDevRegion *r)
{
int i;
for (i = 0; i < dev->max_queues; i++) {
VuVirtq *vq = &dev->vq[i];
const uintptr_t desc = (uintptr_t)vq->vring.desc;
const uintptr_t used = (uintptr_t)vq->vring.used;
const uintptr_t avail = (uintptr_t)vq->vring.avail;
if (desc < r->mmap_addr || desc >= r->mmap_addr + r->size) {
continue;
}
if (used < r->mmap_addr || used >= r->mmap_addr + r->size) {
continue;
}
if (avail < r->mmap_addr || avail >= r->mmap_addr + r->size) {
continue;
}
DPRINT("Unmapping rings of queue %d\n", i);
vq->vring.desc = NULL;
vq->vring.used = NULL;
vq->vring.avail = NULL;
}
}
static size_t
@ -786,21 +851,6 @@ vu_reset_device_exec(VuDev *dev, VhostUserMsg *vmsg)
return false;
}
static bool
map_ring(VuDev *dev, VuVirtq *vq)
{
vq->vring.desc = qva_to_va(dev, vq->vra.desc_user_addr);
vq->vring.used = qva_to_va(dev, vq->vra.used_user_addr);
vq->vring.avail = qva_to_va(dev, vq->vra.avail_user_addr);
DPRINT("Setting virtq addresses:\n");
DPRINT(" vring_desc at %p\n", vq->vring.desc);
DPRINT(" vring_used at %p\n", vq->vring.used);
DPRINT(" vring_avail at %p\n", vq->vring.avail);
return !(vq->vring.desc && vq->vring.used && vq->vring.avail);
}
static bool
generate_faults(VuDev *dev) {
unsigned int i;
@ -884,7 +934,6 @@ generate_faults(VuDev *dev) {
static bool
vu_add_mem_reg(VuDev *dev, VhostUserMsg *vmsg) {
int i;
VhostUserMemoryRegion m = vmsg->payload.memreg.region, *msg_region = &m;
if (vmsg->fd_num != 1) {
@ -930,19 +979,9 @@ vu_add_mem_reg(VuDev *dev, VhostUserMsg *vmsg) {
vmsg->fd_num = 0;
DPRINT("Successfully added new region in postcopy\n");
return true;
} else {
for (i = 0; i < dev->max_queues; i++) {
if (dev->vq[i].vring.desc) {
if (map_ring(dev, &dev->vq[i])) {
vu_panic(dev, "remapping queue %d for new memory region",
i);
}
}
}
DPRINT("Successfully added new region\n");
return false;
}
DPRINT("Successfully added new region\n");
return false;
}
static inline bool reg_equal(VuDevRegion *vudev_reg,
@ -995,6 +1034,16 @@ vu_rem_mem_reg(VuDev *dev, VhostUserMsg *vmsg) {
return false;
}
/*
* There might be valid cases where we temporarily remove memory regions
* to readd them again, or remove memory regions and don't use the rings
* anymore before we set the ring addresses and restart the device.
*
* Unmap all affected rings, remapping them on demand later. This should
* be a corner case.
*/
unmap_rings(dev, r);
munmap((void *)(uintptr_t)r->mmap_addr, r->size + r->mmap_offset);
idx = r - dev->regions;