On 04/26/2017 08:37 PM, Dr. David Alan Gilbert (git) wrote:
> From: "Dr. David Alan Gilbert" <dgilb...@redhat.com>
>
> When an all-zero page is received during the precopy
> phase of a postcopy-enabled migration we must force
> allocation otherwise accesses to the page will still
> get blocked by userfault.
>
> Symptom:
> a) If the page is accessed by a device during device-load
> then we get a deadlock as the source finishes sending
> all its pages but the destination device-load is still
> paused and so doesn't clean up.
>
> b) If the page is accessed later, then the thread will stay
> paused until the end of migration rather than carrying on
> running, until we release userfault at the end.
>
> Signed-off-by: Dr. David Alan Gilbert <dgilb...@redhat.com>
> Reported-by: Christian Borntraeger <borntrae...@de.ibm.com>
CC stable? after all the guest hangs on both sides
Has survived 40 migrations (usually failed at the 2nd)
Tested-by: Christian Borntraeger <borntrae...@de.ibm.com>
> ---
> include/migration/migration.h | 3 ++-
> migration/ram.c | 12 ++++++++----
> migration/rdma.c | 2 +-
> 3 files changed, 11 insertions(+), 6 deletions(-)
>
> diff --git a/include/migration/migration.h b/include/migration/migration.h
> index ba1a16cbc1..b47904033c 100644
> --- a/include/migration/migration.h
> +++ b/include/migration/migration.h
> @@ -265,7 +265,8 @@ uint64_t xbzrle_mig_pages_overflow(void);
> uint64_t xbzrle_mig_pages_cache_miss(void);
> double xbzrle_mig_cache_miss_rate(void);
>
> -void ram_handle_compressed(void *host, uint8_t ch, uint64_t size);
> +void ram_handle_compressed(void *host, uint8_t ch, uint64_t size,
> + bool always_write);
> void ram_debug_dump_bitmap(unsigned long *todump, bool expected);
> /* For outgoing discard bitmap */
> int ram_postcopy_send_discard_bitmap(MigrationState *ms);
> diff --git a/migration/ram.c b/migration/ram.c
> index f48664ec62..b4ed41c725 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -2274,10 +2274,12 @@ static inline void
> *host_from_ram_block_offset(RAMBlock *block,
> * @host: host address for the zero page
> * @ch: what the page is filled from. We only support zero
> * @size: size of the zero page
> + * @always_write: Always perform the memset even if it's zero
> */
> -void ram_handle_compressed(void *host, uint8_t ch, uint64_t size)
> +void ram_handle_compressed(void *host, uint8_t ch, uint64_t size,
> + bool always_write)
> {
> - if (ch != 0 || !is_zero_range(host, size)) {
> + if (ch != 0 || always_write || !is_zero_range(host, size)) {
> memset(host, ch, size);
> }
> }
> @@ -2514,7 +2516,8 @@ static int ram_load_postcopy(QEMUFile *f)
> switch (flags & ~RAM_SAVE_FLAG_CONTINUE) {
> case RAM_SAVE_FLAG_COMPRESS:
> ch = qemu_get_byte(f);
> - memset(page_buffer, ch, TARGET_PAGE_SIZE);
> + ram_handle_compressed(page_buffer, ch, TARGET_PAGE_SIZE,
> + true);
> if (ch) {
> all_zero = false;
> }
> @@ -2664,7 +2667,8 @@ static int ram_load(QEMUFile *f, void *opaque, int
> version_id)
>
> case RAM_SAVE_FLAG_COMPRESS:
> ch = qemu_get_byte(f);
> - ram_handle_compressed(host, ch, TARGET_PAGE_SIZE);
> + ram_handle_compressed(host, ch, TARGET_PAGE_SIZE,
> + postcopy_advised);
> break;
>
> case RAM_SAVE_FLAG_PAGE:
> diff --git a/migration/rdma.c b/migration/rdma.c
> index fe0a4b5a83..07a9bd75d8 100644
> --- a/migration/rdma.c
> +++ b/migration/rdma.c
> @@ -3164,7 +3164,7 @@ static int qemu_rdma_registration_handle(QEMUFile *f,
> void *opaque)
> host_addr = block->local_host_addr +
> (comp->offset - block->offset);
>
> - ram_handle_compressed(host_addr, comp->value, comp->length);
> + ram_handle_compressed(host_addr, comp->value, comp->length,
> false);
> break;
>
> case RDMA_CONTROL_REGISTER_FINISHED:
>
