Kernel/linux-stable
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2025-01-07 13:43:51 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

virtio-mem: keep retrying on offline_and_remove_memory() errors in Sub Block Mode (SBM)

Browse Source 
In case offline_and_remove_memory() fails in SBM, we leave a completely
unplugged Linux memory block stick around until we try plugging memory
again. We won't try removing that memory block again.

offline_and_remove_memory() may, for example, fail if we're racing with
another alloc_contig_range() user, if allocating temporary memory fails,
or if some memory notifier rejected the offlining request.

Let's handle that case better, by simple retrying to offline and remove
such memory.

Tested using CONFIG_MEMORY_NOTIFIER_ERROR_INJECT.

Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20230713145551.2824980-4-david@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This commit is contained in:
David Hildenbrand 2023-07-13 16:55:50 +02:00 committed by Michael S. Tsirkin
parent ddf4098514
commit a31648fd4f
1 changed files with 73 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

92
drivers/virtio/virtio_mem.c
View File

@ -168,6 +168,13 @@ struct virtio_mem {
/* The number of subblocks per Linux memory block. */
uint32_t sbs_per_mb;
/*
* Some of the Linux memory blocks tracked as "partially
* plugged" are completely unplugged and can be offlined
* and removed -- which previously failed.
*/
bool have_unplugged_mb;
/* Summary of all memory block states. */
unsigned long mb_count[VIRTIO_MEM_SBM_MB_COUNT];
@ -765,6 +772,34 @@ static int virtio_mem_sbm_offline_and_remove_mb(struct virtio_mem *vm,
return virtio_mem_offline_and_remove_memory(vm, addr, size);
}
/*
* Try (offlining and) removing memory from Linux in case all subblocks are
* unplugged. Can be called on online and offline memory blocks.
*
* May modify the state of memory blocks in virtio-mem.
*/
static int virtio_mem_sbm_try_remove_unplugged_mb(struct virtio_mem *vm,
unsigned long mb_id)
{
int rc;
/*
* Once all subblocks of a memory block were unplugged, offline and
* remove it.
*/
if (!virtio_mem_sbm_test_sb_unplugged(vm, mb_id, 0, vm->sbm.sbs_per_mb))
return 0;
/* offline_and_remove_memory() works for online and offline memory. */
mutex_unlock(&vm->hotplug_mutex);
rc = virtio_mem_sbm_offline_and_remove_mb(vm, mb_id);
mutex_lock(&vm->hotplug_mutex);
if (!rc)
virtio_mem_sbm_set_mb_state(vm, mb_id,
VIRTIO_MEM_SBM_MB_UNUSED);
return rc;
}
/*
* See virtio_mem_offline_and_remove_memory(): Try to offline and remove a
* all Linux memory blocks covered by the big block.
@ -1988,20 +2023,10 @@ static int virtio_mem_sbm_unplug_any_sb_online(struct virtio_mem *vm,
}
unplugged:
/*
* Once all subblocks of a memory block were unplugged, offline and
* remove it. This will usually not fail, as no memory is in use
* anymore - however some other notifiers might NACK the request.
*/
if (virtio_mem_sbm_test_sb_unplugged(vm, mb_id, 0, vm->sbm.sbs_per_mb)) {
mutex_unlock(&vm->hotplug_mutex);
rc = virtio_mem_sbm_offline_and_remove_mb(vm, mb_id);
mutex_lock(&vm->hotplug_mutex);
if (!rc)
virtio_mem_sbm_set_mb_state(vm, mb_id,
VIRTIO_MEM_SBM_MB_UNUSED);
}
rc = virtio_mem_sbm_try_remove_unplugged_mb(vm, mb_id);
if (rc)
vm->sbm.have_unplugged_mb = 1;
/* Ignore errors, this is not critical. We'll retry later. */
return 0;
}
@ -2253,12 +2278,13 @@ static int virtio_mem_unplug_request(struct virtio_mem *vm, uint64_t diff)
/*
* Try to unplug all blocks that couldn't be unplugged before, for example,
* because the hypervisor was busy.
* because the hypervisor was busy. Further, offline and remove any memory
* blocks where we previously failed.
*/
static int virtio_mem_unplug_pending_mb(struct virtio_mem *vm)
static int virtio_mem_cleanup_pending_mb(struct virtio_mem *vm)
{
unsigned long id;
int rc;
int rc = 0;
if (!vm->in_sbm) {
virtio_mem_bbm_for_each_bb(vm, id,
@ -2280,6 +2306,27 @@ static int virtio_mem_unplug_pending_mb(struct virtio_mem *vm)
VIRTIO_MEM_SBM_MB_UNUSED);
}
if (!vm->sbm.have_unplugged_mb)
return 0;
/*
* Let's retry (offlining and) removing completely unplugged Linux
* memory blocks.
*/
vm->sbm.have_unplugged_mb = false;
mutex_lock(&vm->hotplug_mutex);
virtio_mem_sbm_for_each_mb(vm, id, VIRTIO_MEM_SBM_MB_MOVABLE_PARTIAL)
rc |= virtio_mem_sbm_try_remove_unplugged_mb(vm, id);
virtio_mem_sbm_for_each_mb(vm, id, VIRTIO_MEM_SBM_MB_KERNEL_PARTIAL)
rc |= virtio_mem_sbm_try_remove_unplugged_mb(vm, id);
virtio_mem_sbm_for_each_mb(vm, id, VIRTIO_MEM_SBM_MB_OFFLINE_PARTIAL)
rc |= virtio_mem_sbm_try_remove_unplugged_mb(vm, id);
mutex_unlock(&vm->hotplug_mutex);
if (rc)
vm->sbm.have_unplugged_mb = true;
/* Ignore errors, this is not critical. We'll retry later. */
return 0;
}
@ -2361,9 +2408,9 @@ static void virtio_mem_run_wq(struct work_struct *work)
virtio_mem_refresh_config(vm);
}
/* Unplug any leftovers from previous runs */
/* Cleanup any leftovers from previous runs */
if (!rc)
rc = virtio_mem_unplug_pending_mb(vm);
rc = virtio_mem_cleanup_pending_mb(vm);
if (!rc && vm->requested_size != vm->plugged_size) {
if (vm->requested_size > vm->plugged_size) {
@ -2375,6 +2422,13 @@ static void virtio_mem_run_wq(struct work_struct *work)
}
}
/*
* Keep retrying to offline and remove completely unplugged Linux
* memory blocks.
*/
if (!rc && vm->in_sbm && vm->sbm.have_unplugged_mb)
rc = -EBUSY;
switch (rc) {
case 0:
vm->retry_timer_ms = VIRTIO_MEM_RETRY_TIMER_MIN_MS;