qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Philippe Mathieu-Daudé" <philmd@redhat.com>
To: David Hildenbrand <david@redhat.com>, qemu-devel@nongnu.org
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
	Peter Xu <peterx@redhat.com>, Eric Auger <eric.auger@redhat.com>,
	Alex Williamson <alex.williamson@redhat.com>,
	Wei Yang <richardw.yang@linux.intel.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Igor Mammedov <imammedo@redhat.com>
Subject: Re: [PATCH] util/vfio-helpers.c: Use ram_block_discard_disable() in qemu_vfio_open_pci()
Date: Mon, 16 Nov 2020 14:14:20 +0100	[thread overview]
Message-ID: <1cbb9248-aaf1-ed15-643c-0be73f14f1a9@redhat.com> (raw)
In-Reply-To: <20201116105947.9194-1-david@redhat.com>

Hi David,

Is this aiming at 5.2?

On 11/16/20 11:59 AM, David Hildenbrand wrote:
> Currently, when using "nvme://" for a block device, like
>     -drive file=nvme://0000:01:00.0/1,if=none,id=drive0 \
>     -device virtio-blk,drive=drive0 \
> 
> VFIO may pin all guest memory, and discarding of RAM no longer works as
> expected. I was able to reproduce this easily with my
>     01:00.0 Non-Volatile memory controller: Samsung Electronics Co Ltd
>             NVMe SSD Controller SM981/PM981/PM983
> 
> Similar to common VFIO, we have to disable it, making sure that:
> a) virtio-balloon won't discard any memory ("silently disabled")
> b) virtio-mem and nvme:// run mutually exclusive
> 
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: "Michael S. Tsirkin" <mst@redhat.com>
> Cc: Alex Williamson <alex.williamson@redhat.com>
> Cc: Wei Yang <richardw.yang@linux.intel.com>
> Cc: Dr. David Alan Gilbert <dgilbert@redhat.com>
> Cc: Igor Mammedov <imammedo@redhat.com>
> Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
> Cc: Peter Xu <peterx@redhat.com>
> Signed-off-by: David Hildenbrand <david@redhat.com>
> ---
>  stubs/ram-block.c   |  6 ++++++
>  util/vfio-helpers.c | 14 ++++++++++++++
>  2 files changed, 20 insertions(+)
> 
> diff --git a/stubs/ram-block.c b/stubs/ram-block.c
> index 73c0a3ee08..108197683b 100644
> --- a/stubs/ram-block.c
> +++ b/stubs/ram-block.c
> @@ -1,6 +1,7 @@
>  #include "qemu/osdep.h"
>  #include "exec/ramlist.h"
>  #include "exec/cpu-common.h"
> +#include "exec/memory.h"
>  
>  void *qemu_ram_get_host_addr(RAMBlock *rb)
>  {
> @@ -29,3 +30,8 @@ int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque)
>  {
>      return 0;
>  }
> +
> +int ram_block_discard_disable(bool state)
> +{
> +    return 0;
> +}
> diff --git a/util/vfio-helpers.c b/util/vfio-helpers.c
> index c469beb061..2bec48e163 100644
> --- a/util/vfio-helpers.c
> +++ b/util/vfio-helpers.c
> @@ -16,6 +16,7 @@
>  #include "qapi/error.h"
>  #include "exec/ramlist.h"
>  #include "exec/cpu-common.h"
> +#include "exec/memory.h"
>  #include "trace.h"
>  #include "qemu/error-report.h"
>  #include "standard-headers/linux/pci_regs.h"
> @@ -494,8 +495,20 @@ QEMUVFIOState *qemu_vfio_open_pci(const char *device, Error **errp)
>      int r;
>      QEMUVFIOState *s = g_new0(QEMUVFIOState, 1);
>  
> +    /*
> +     * VFIO may pin all memory inside mappings, resulting it in pinning
> +     * all memory inside RAM blocks unconditionally.
> +     */
> +    r = ram_block_discard_disable(true);
> +    if (r) {
> +        error_setg_errno(errp, -r, "Cannot set discarding of RAM broken");
> +        g_free(s);
> +        return NULL;
> +    }
> +
>      r = qemu_vfio_init_pci(s, device, errp);
>      if (r) {
> +        ram_block_discard_disable(false);
>          g_free(s);
>          return NULL;
>      }
> @@ -837,4 +850,5 @@ void qemu_vfio_close(QEMUVFIOState *s)
>      close(s->device);
>      close(s->group);
>      close(s->container);
> +    ram_block_discard_disable(false);
>  }
> 



  reply	other threads:[~2020-11-16 13:21 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-16 10:59 [PATCH] util/vfio-helpers.c: Use ram_block_discard_disable() in qemu_vfio_open_pci() David Hildenbrand
2020-11-16 13:14 ` Philippe Mathieu-Daudé [this message]
2020-11-16 13:16   ` David Hildenbrand
2020-11-16 18:20 ` Paolo Bonzini

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1cbb9248-aaf1-ed15-643c-0be73f14f1a9@redhat.com \
    --to=philmd@redhat.com \
    --cc=alex.williamson@redhat.com \
    --cc=david@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=eric.auger@redhat.com \
    --cc=imammedo@redhat.com \
    --cc=mst@redhat.com \
    --cc=pankaj.gupta.linux@gmail.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=richardw.yang@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).