LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Mike Rapoport <rppt@kernel.org>
To: Shakeel Butt <shakeelb@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Andy Lutomirski <luto@kernel.org>, Arnd Bergmann <arnd@arndb.de>,
	Borislav Petkov <bp@alien8.de>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Christopher Lameter <cl@linux.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	David Hildenbrand <david@redhat.com>,
	Elena Reshetova <elena.reshetova@intel.com>,
	"H. Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@redhat.com>,
	James Bottomley <jejb@linux.ibm.com>,
	"Kirill A. Shutemov" <kirill@shutemov.name>,
	Matthew Wilcox <willy@infradead.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Mike Rapoport <rppt@linux.ibm.com>,
	Michael Kerrisk <mtk.manpages@gmail.com>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Rick Edgecombe <rick.p.edgecombe@intel.com>,
	Roman Gushchin <guro@fb.com>, Shuah Khan <shuah@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Tycho Andersen <tycho@tycho.ws>, Will Deacon <will@kernel.org>,
	linux-api@vger.kernel.org, linux-arch@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org,
	linux-fsdevel <linux-fsdevel@vger.kernel.org>,
	Linux MM <linux-mm@kvack.org>,
	LKML <linux-kernel@vger.kernel.org>,
	linux-kselftest@vger.kernel.org, linux-nvdimm@lists.01.org,
	linux-riscv@lists.infradead.org, x86@kernel.org
Subject: Re: [PATCH v12 07/10] secretmem: add memcg accounting
Date: Sun, 29 Nov 2020 19:26:25 +0200
Message-ID: <20201129172625.GD557259@kernel.org> (raw)
In-Reply-To: <CALvZod4MoXod_YkbO+4k2=PS=xdMVbZa2HWWuUnMZ1G9hSr+Jw@mail.gmail.com>

On Sun, Nov 29, 2020 at 07:53:45AM -0800, Shakeel Butt wrote:
> On Wed, Nov 25, 2020 at 1:51 AM Mike Rapoport <rppt@kernel.org> wrote:
> >
> > From: Mike Rapoport <rppt@linux.ibm.com>
> >
> > Account memory consumed by secretmem to memcg. The accounting is updated
> > when the memory is actually allocated and freed.
> >
> > Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
> > Acked-by: Roman Gushchin <guro@fb.com>
> > ---
> >  mm/filemap.c   |  3 ++-
> >  mm/secretmem.c | 36 +++++++++++++++++++++++++++++++++++-
> >  2 files changed, 37 insertions(+), 2 deletions(-)
> >
> > diff --git a/mm/filemap.c b/mm/filemap.c
> > index 249cf489f5df..cf7f1dc9f4b8 100644
> > --- a/mm/filemap.c
> > +++ b/mm/filemap.c
> > @@ -42,6 +42,7 @@
> >  #include <linux/psi.h>
> >  #include <linux/ramfs.h>
> >  #include <linux/page_idle.h>
> > +#include <linux/secretmem.h>
> >  #include "internal.h"
> >
> >  #define CREATE_TRACE_POINTS
> > @@ -844,7 +845,7 @@ static noinline int __add_to_page_cache_locked(struct page *page,
> >         page->mapping = mapping;
> >         page->index = offset;
> >
> > -       if (!huge) {
> > +       if (!huge && !page_is_secretmem(page)) {
> >                 error = mem_cgroup_charge(page, current->mm, gfp);
> >                 if (error)
> >                         goto error;
> > diff --git a/mm/secretmem.c b/mm/secretmem.c
> > index 52a900a135a5..eb6628390444 100644
> > --- a/mm/secretmem.c
> > +++ b/mm/secretmem.c
> > @@ -18,6 +18,7 @@
> >  #include <linux/memblock.h>
> >  #include <linux/pseudo_fs.h>
> >  #include <linux/secretmem.h>
> > +#include <linux/memcontrol.h>
> >  #include <linux/set_memory.h>
> >  #include <linux/sched/signal.h>
> >
> > @@ -44,6 +45,32 @@ struct secretmem_ctx {
> >
> >  static struct cma *secretmem_cma;
> >
> > +static int secretmem_account_pages(struct page *page, gfp_t gfp, int order)
> > +{
> > +       int err;
> > +
> > +       err = memcg_kmem_charge_page(page, gfp, order);
> > +       if (err)
> > +               return err;
> > +
> > +       /*
> > +        * seceremem caches are unreclaimable kernel allocations, so treat
> > +        * them as unreclaimable slab memory for VM statistics purposes
> > +        */
> > +       mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B,
> > +                           PAGE_SIZE << order);
> 
> Please use mod_lruvec_page_state() instead, so we get the memcg stats too.

Ok

> BTW I think secretmem deserves a vmstat entry instead of overloading
> NR_SLAB_UNRECLAIMABLE_B.

I'd prefer to wait with a dedicated vmstat for now. We can always add it
later, once we have better picture of secremem usage.

> > +
> > +       return 0;
> > +}
> > +
> > +static void secretmem_unaccount_pages(struct page *page, int order)
> > +{
> > +
> > +       mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B,
> > +                           -PAGE_SIZE << order);
> > +       memcg_kmem_uncharge_page(page, order);
> > +}
> > +
> >  static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp)
> >  {
> >         unsigned long nr_pages = (1 << PMD_PAGE_ORDER);
> > @@ -56,10 +83,14 @@ static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp)
> >         if (!page)
> >                 return -ENOMEM;
> >
> > -       err = set_direct_map_invalid_noflush(page, nr_pages);
> > +       err = secretmem_account_pages(page, gfp, PMD_PAGE_ORDER);
> >         if (err)
> >                 goto err_cma_release;
> >
> > +       err = set_direct_map_invalid_noflush(page, nr_pages);
> > +       if (err)
> > +               goto err_memcg_uncharge;
> > +
> >         addr = (unsigned long)page_address(page);
> >         err = gen_pool_add(pool, addr, PMD_SIZE, NUMA_NO_NODE);
> >         if (err)
> > @@ -76,6 +107,8 @@ static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp)
> >          * won't fail
> >          */
> >         set_direct_map_default_noflush(page, nr_pages);
> > +err_memcg_uncharge:
> > +       secretmem_unaccount_pages(page, PMD_PAGE_ORDER);
> >  err_cma_release:
> >         cma_release(secretmem_cma, page, nr_pages);
> >         return err;
> > @@ -302,6 +335,7 @@ static void secretmem_cleanup_chunk(struct gen_pool *pool,
> >         int i;
> >
> >         set_direct_map_default_noflush(page, nr_pages);
> > +       secretmem_unaccount_pages(page, PMD_PAGE_ORDER);
> >
> >         for (i = 0; i < nr_pages; i++)
> >                 clear_highpage(page + i);
> > --
> > 2.28.0
> >

-- 
Sincerely yours,
Mike.

  reply index

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-25  9:21 [PATCH v12 00/10] mm: introduce memfd_secret system call to create "secret" memory areas Mike Rapoport
2020-11-25  9:21 ` [PATCH v12 01/10] mm: add definition of PMD_PAGE_ORDER Mike Rapoport
2020-11-25  9:22 ` [PATCH v12 02/10] mmap: make mlock_future_check() global Mike Rapoport
2020-11-25  9:22 ` [PATCH v12 03/10] set_memory: allow set_direct_map_*_noflush() for multiple pages Mike Rapoport
2020-11-25  9:22 ` [PATCH v12 04/10] set_memory: allow querying whether set_direct_map_*() is actually enabled Mike Rapoport
2020-11-25 11:22   ` David Hildenbrand
2020-11-25 12:11     ` Mike Rapoport
2020-11-25 12:42       ` David Hildenbrand
2020-11-25 18:36   ` Catalin Marinas
2020-11-25  9:22 ` [PATCH v12 05/10] mm: introduce memfd_secret system call to create "secret" memory areas Mike Rapoport
2020-11-25  9:22 ` [PATCH v12 06/10] secretmem: use PMD-size pages to amortize direct map fragmentation Mike Rapoport
2020-11-25  9:22 ` [PATCH v12 07/10] secretmem: add memcg accounting Mike Rapoport
2020-11-29 15:53   ` Shakeel Butt
2020-11-29 17:26     ` Mike Rapoport [this message]
2020-11-30 20:15       ` Roman Gushchin
2020-11-25  9:22 ` [PATCH v12 08/10] PM: hibernate: disable when there are active secretmem users Mike Rapoport
2020-11-25  9:22 ` [PATCH v12 09/10] arch, mm: wire up memfd_secret system call were relevant Mike Rapoport
2020-11-25  9:22 ` [PATCH v12 10/10] secretmem: test: add basic selftest for memfd_secret(2) Mike Rapoport

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=20201129172625.GD557259@kernel.org \
    --to=rppt@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=arnd@arndb.de \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=cl@linux.com \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=david@redhat.com \
    --cc=elena.reshetova@intel.com \
    --cc=guro@fb.com \
    --cc=hpa@zytor.com \
    --cc=jejb@linux.ibm.com \
    --cc=kirill@shutemov.name \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=luto@kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=mtk.manpages@gmail.com \
    --cc=palmer@dabbelt.com \
    --cc=paul.walmsley@sifive.com \
    --cc=peterz@infradead.org \
    --cc=rick.p.edgecombe@intel.com \
    --cc=rppt@linux.ibm.com \
    --cc=shakeelb@google.com \
    --cc=shuah@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=tycho@tycho.ws \
    --cc=viro@zeniv.linux.org.uk \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=x86@kernel.org \
    /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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git
	git clone --mirror https://lore.kernel.org/lkml/10 lkml/git/10.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git