Re: [PATCH] xen: Drop out of coroutine context xen_invalidate_map_cache_entry

[Stefano Stabellini <sstabellini@xxxxxxxxxx>]

On Tue, 16 Jan 2024, Peng Fan (OSS) wrote:
> From: Peng Fan <peng.fan@xxxxxxx>
> 
> xen_invalidate_map_cache_entry is not expected to run in a
> coroutine. Without this, there is crash:
> 
>     signo=signo@entry=6, no_tid=no_tid@entry=0) at pthread_kill.c:44
>     threadid=<optimized out>) at pthread_kill.c:78
>     at /usr/src/debug/glibc/2.38+git-r0/sysdeps/posix/raise.c:26
>     fmt=0xffff9e1ca8a8 "%s%s%s:%u: %s%sAssertion `%s' failed.\n%n",
>     assertion=assertion@entry=0xaaaae0d25740 "!qemu_in_coroutine()",
>     file=file@entry=0xaaaae0d301a8 
> "../qemu-xen-dir-remote/block/graph-lock.c", line=line@entry=260,
>     function=function@entry=0xaaaae0e522c0 <__PRETTY_FUNCTION__.3> 
> "bdrv_graph_rdlock_main_loop") at assert.c:92
>     assertion=assertion@entry=0xaaaae0d25740 "!qemu_in_coroutine()",
>     file=file@entry=0xaaaae0d301a8 
> "../qemu-xen-dir-remote/block/graph-lock.c", line=line@entry=260,
>     function=function@entry=0xaaaae0e522c0 <__PRETTY_FUNCTION__.3> 
> "bdrv_graph_rdlock_main_loop") at assert.c:101
>     at ../qemu-xen-dir-remote/block/graph-lock.c:260
>     at 
> /home/Freenix/work/sw-stash/xen/upstream/tools/qemu-xen-dir-remote/include/block/graph-lock.h:259
>     host=host@entry=0xffff742c8000, size=size@entry=2097152)
>     at ../qemu-xen-dir-remote/block/io.c:3362
>     host=0xffff742c8000, size=2097152)
>     at ../qemu-xen-dir-remote/block/block-backend.c:2859
>     host=<optimized out>, size=<optimized out>, max_size=<optimized out>)
>     at ../qemu-xen-dir-remote/block/block-ram-registrar.c:33
>     size=2097152, max_size=2097152)
>     at ../qemu-xen-dir-remote/hw/core/numa.c:883
>     buffer=buffer@entry=0xffff743c5000 "")
>     at ../qemu-xen-dir-remote/hw/xen/xen-mapcache.c:475
>     buffer=buffer@entry=0xffff743c5000 "")
>     at ../qemu-xen-dir-remote/hw/xen/xen-mapcache.c:487
>     as=as@entry=0xaaaae1ca3ae8 <address_space_memory>, buffer=0xffff743c5000,
>     len=<optimized out>, is_write=is_write@entry=true,
>     access_len=access_len@entry=32768)
>     at ../qemu-xen-dir-remote/system/physmem.c:3199
>     dir=DMA_DIRECTION_FROM_DEVICE, len=<optimized out>,
>     buffer=<optimized out>, as=0xaaaae1ca3ae8 <address_space_memory>)
>     at 
> /home/Freenix/work/sw-stash/xen/upstream/tools/qemu-xen-dir-remote/include/sysemu/dma.h:236
>     elem=elem@entry=0xaaaaf620aa30, len=len@entry=32769)
>     at ../qemu-xen-dir-remote/hw/virtio/virtio.c:758
>     elem=elem@entry=0xaaaaf620aa30, len=len@entry=32769, idx=idx@entry=0)
>     at ../qemu-xen-dir-remote/hw/virtio/virtio.c:919
>     elem=elem@entry=0xaaaaf620aa30, len=32769)
>     at ../qemu-xen-dir-remote/hw/virtio/virtio.c:994
>     req=req@entry=0xaaaaf620aa30, status=status@entry=0 '\000')
>     at ../qemu-xen-dir-remote/hw/block/virtio-blk.c:67
>     ret=0) at ../qemu-xen-dir-remote/hw/block/virtio-blk.c:136
>     at ../qemu-xen-dir-remote/block/block-backend.c:1559
> --Type <RET> for more, q to quit, c to continue without paging--
>     at ../qemu-xen-dir-remote/block/block-backend.c:1614
>     i1=<optimized out>) at 
> ../qemu-xen-dir-remote/util/coroutine-ucontext.c:177
>     at ../sysdeps/unix/sysv/linux/aarch64/setcontext.S:123
> 
> Signed-off-by: Peng Fan <peng.fan@xxxxxxx>

Hi Peng! Many thanks for the patch and for the investigation!

Only one minor question below


> ---
>  hw/xen/xen-mapcache.c | 31 +++++++++++++++++++++++++++++--
>  1 file changed, 29 insertions(+), 2 deletions(-)
> 
> diff --git a/hw/xen/xen-mapcache.c b/hw/xen/xen-mapcache.c
> index f7d974677d..4e1bb665ee 100644
> --- a/hw/xen/xen-mapcache.c
> +++ b/hw/xen/xen-mapcache.c
> @@ -481,11 +481,38 @@ static void 
> xen_invalidate_map_cache_entry_unlocked(uint8_t *buffer)
>      g_free(entry);
>  }
>  
> -void xen_invalidate_map_cache_entry(uint8_t *buffer)
> +typedef struct XenMapCacheData {
> +    Coroutine *co;
> +    uint8_t *buffer;
> +    int ret;

Do we need int ret? It doesn't look like we are using it.


> +} XenMapCacheData;
> +
> +static void xen_invalidate_map_cache_entry_bh(void *opaque)
>  {
> +    XenMapCacheData *data = opaque;
> +
>      mapcache_lock();
> -    xen_invalidate_map_cache_entry_unlocked(buffer);
> +    xen_invalidate_map_cache_entry_unlocked(data->buffer);
>      mapcache_unlock();
> +
> +    aio_co_wake(data->co);
> +}
> +
> +void coroutine_mixed_fn xen_invalidate_map_cache_entry(uint8_t *buffer)
> +{
> +    if (qemu_in_coroutine()) {
> +        XenMapCacheData data = {
> +            .co = qemu_coroutine_self(),
> +            .buffer = buffer,
> +        };
> +        aio_bh_schedule_oneshot(qemu_get_current_aio_context(),
> +                                xen_invalidate_map_cache_entry_bh, &data);
> +        qemu_coroutine_yield();
> +    } else {
> +        mapcache_lock();
> +        xen_invalidate_map_cache_entry_unlocked(buffer);
> +        mapcache_unlock();
> +    }
>  }
>  
>  void xen_invalidate_map_cache(void)
> -- 
> 2.35.3
>