qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
To: David Hildenbrand <david@redhat.com>
Cc: "Juan Quintela" <quintela@redhat.com>,
	"Marcel Apfelbaum" <mapfelba@redhat.com>,
	"Cornelia Huck" <cohuck@redhat.com>,
	"Eduardo Habkost" <ehabkost@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	"Stefan Weil" <sw@weilnetz.de>,
	"Murilo Opsfelder Araujo" <muriloo@linux.ibm.com>,
	"Richard Henderson" <richard.henderson@linaro.org>,
	qemu-devel@nongnu.org, "Peter Xu" <peterx@redhat.com>,
	"Greg Kurz" <groug@kaod.org>, "Halil Pasic" <pasic@linux.ibm.com>,
	"Christian Borntraeger" <borntraeger@de.ibm.com>,
	"Stefan Hajnoczi" <stefanha@redhat.com>,
	"Igor Mammedov" <imammedo@redhat.com>,
	"Thomas Huth" <thuth@redhat.com>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Philippe Mathieu-Daudé" <philmd@redhat.com>,
	"Igor Kotrasinski" <i.kotrasinsk@partner.samsung.com>
Subject: Re: [PATCH v3 02/12] softmmu/physmem: Fix ram_block_discard_range() to handle shared anonymous memory
Date: Thu, 11 Mar 2021 16:39:48 +0000	[thread overview]
Message-ID: <YEpH1FAabcILd38K@work-vm> (raw)
In-Reply-To: <20210308150600.14440-3-david@redhat.com>

* David Hildenbrand (david@redhat.com) wrote:
> We can create shared anonymous memory via
>     "-object memory-backend-ram,share=on,..."
> which is, for example, required by PVRDMA for mremap() to work.
> 
> Shared anonymous memory is weird, though. Instead of MADV_DONTNEED, we
> have to use MADV_REMOVE. MADV_DONTNEED fails silently and does nothing.

OK, I wonder how stable these rules are; is it defined anywhere that
it's required?

Still,


Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

> Fixes: 06329ccecfa0 ("mem: add share parameter to memory-backend-ram")
> Signed-off-by: David Hildenbrand <david@redhat.com>
> ---
>  softmmu/physmem.c | 7 ++++++-
>  1 file changed, 6 insertions(+), 1 deletion(-)
> 
> diff --git a/softmmu/physmem.c b/softmmu/physmem.c
> index 62ea4abbdd..2ba815fec6 100644
> --- a/softmmu/physmem.c
> +++ b/softmmu/physmem.c
> @@ -3506,6 +3506,7 @@ int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
>          /* The logic here is messy;
>           *    madvise DONTNEED fails for hugepages
>           *    fallocate works on hugepages and shmem
> +         *    shared anonymous memory requires madvise REMOVE
>           */
>          need_madvise = (rb->page_size == qemu_host_page_size);
>          need_fallocate = rb->fd != -1;
> @@ -3539,7 +3540,11 @@ int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
>               * fallocate'd away).
>               */
>  #if defined(CONFIG_MADVISE)
> -            ret =  madvise(host_startaddr, length, MADV_DONTNEED);
> +            if (qemu_ram_is_shared(rb) && rb->fd < 0) {
> +                ret = madvise(host_startaddr, length, MADV_REMOVE);
> +            } else {
> +                ret = madvise(host_startaddr, length, MADV_DONTNEED);
> +            }
>              if (ret) {
>                  ret = -errno;
>                  error_report("ram_block_discard_range: Failed to discard range "
> -- 
> 2.29.2
> 
-- 
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK



  reply	other threads:[~2021-03-11 16:43 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-08 15:05 [PATCH v3 00/12] RAM_NORESERVE, MAP_NORESERVE and hostmem "reserve" property David Hildenbrand
2021-03-08 15:05 ` [PATCH v3 01/12] softmmu/physmem: Mark shared anonymous memory RAM_SHARED David Hildenbrand
2021-03-08 15:05 ` [PATCH v3 02/12] softmmu/physmem: Fix ram_block_discard_range() to handle shared anonymous memory David Hildenbrand
2021-03-11 16:39   ` Dr. David Alan Gilbert [this message]
2021-03-11 16:45     ` David Hildenbrand
2021-03-11 17:11       ` Peter Xu
2021-03-11 17:15         ` David Hildenbrand
2021-03-11 17:18           ` David Hildenbrand
2021-03-11 17:22           ` Peter Xu
2021-03-11 17:41             ` David Hildenbrand
2021-03-11 21:25               ` Peter Xu
2021-03-11 21:37   ` Peter Xu
2021-03-11 21:49     ` David Hildenbrand
2021-03-08 15:05 ` [PATCH v3 03/12] softmmu/physmem: Fix qemu_ram_remap() " David Hildenbrand
2021-03-08 15:05 ` [PATCH v3 04/12] util/mmap-alloc: Factor out calculation of the pagesize for the guard page David Hildenbrand
2021-03-08 15:05 ` [PATCH v3 05/12] util/mmap-alloc: Factor out reserving of a memory region to mmap_reserve() David Hildenbrand
2021-03-08 15:05 ` [PATCH v3 06/12] util/mmap-alloc: Factor out activating of memory to mmap_activate() David Hildenbrand
2021-03-08 15:05 ` [PATCH v3 07/12] softmmu/memory: Pass ram_flags into qemu_ram_alloc_from_fd() David Hildenbrand
2021-03-08 15:05 ` [PATCH v3 08/12] softmmu/memory: Pass ram_flags into memory_region_init_ram_shared_nomigrate() David Hildenbrand
2021-03-08 15:05 ` [PATCH v3 09/12] util/mmap-alloc: Pass flags instead of separate bools to qemu_ram_mmap() David Hildenbrand
2021-03-09 20:04   ` Peter Xu
2021-03-09 20:27     ` David Hildenbrand
2021-03-09 20:58       ` Peter Xu
2021-03-10  8:41         ` David Hildenbrand
2021-03-10 10:11           ` David Hildenbrand
2021-03-10 10:55             ` David Hildenbrand
2021-03-10 16:27               ` Peter Xu
2021-03-08 15:05 ` [PATCH v3 10/12] memory: introduce RAM_NORESERVE and wire it up in qemu_ram_mmap() David Hildenbrand
2021-03-08 15:05 ` [PATCH v3 11/12] util/mmap-alloc: Support RAM_NORESERVE via MAP_NORESERVE David Hildenbrand
2021-03-10 10:28   ` David Hildenbrand
2021-03-08 15:06 ` [PATCH v3 12/12] hostmem: Wire up RAM_NORESERVE via "reserve" property David Hildenbrand

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=YEpH1FAabcILd38K@work-vm \
    --to=dgilbert@redhat.com \
    --cc=borntraeger@de.ibm.com \
    --cc=cohuck@redhat.com \
    --cc=david@redhat.com \
    --cc=ehabkost@redhat.com \
    --cc=groug@kaod.org \
    --cc=i.kotrasinsk@partner.samsung.com \
    --cc=imammedo@redhat.com \
    --cc=mapfelba@redhat.com \
    --cc=mst@redhat.com \
    --cc=muriloo@linux.ibm.com \
    --cc=pasic@linux.ibm.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=philmd@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=quintela@redhat.com \
    --cc=richard.henderson@linaro.org \
    --cc=stefanha@redhat.com \
    --cc=sw@weilnetz.de \
    --cc=thuth@redhat.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).