On Thu, Jan 21, 2021 at 02:27:20PM +0200, Mike Rapoport wrote:
> From: Mike Rapoport <rppt@xxxxxxxxxxxxx>
>
> Account memory consumed by secretmem to memcg. The accounting is updated
> when the memory is actually allocated and freed.
I think this is wrong. It fails to account subsequent allocators from
the same PMD. If you want to track like this, you need separate pools
per memcg.
I think you shouldn't try to track like this; better to just track on
a per-page basis. After all, the page allocator doesn't track order-10
pages to the memcg that initially caused them to be split.
> Signed-off-by: Mike Rapoport <rppt@xxxxxxxxxxxxx>
> Acked-by: Roman Gushchin <guro@xxxxxx>
> Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
> Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
> Cc: Andy Lutomirski <luto@xxxxxxxxxx>
> Cc: Arnd Bergmann <arnd@xxxxxxxx>
> Cc: Borislav Petkov <bp@xxxxxxxxx>
> Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
> Cc: Christopher Lameter <cl@xxxxxxxxx>
> Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
> Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
> Cc: David Hildenbrand <david@xxxxxxxxxx>
> Cc: Elena Reshetova <elena.reshetova@xxxxxxxxx>
> Cc: Hagen Paul Pfeifer <hagen@xxxxxxxx>
> Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
> Cc: Ingo Molnar <mingo@xxxxxxxxxx>
> Cc: James Bottomley <jejb@xxxxxxxxxxxxx>
> Cc: "Kirill A. Shutemov" <kirill@xxxxxxxxxxxxx>
> Cc: Mark Rutland <mark.rutland@xxxxxxx>
> Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
> Cc: Michael Kerrisk <mtk.manpages@xxxxxxxxx>
> Cc: Palmer Dabbelt <palmer@xxxxxxxxxxx>
> Cc: Palmer Dabbelt <palmerdabbelt@xxxxxxxxxx>
> Cc: Paul Walmsley <paul.walmsley@xxxxxxxxxx>
> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Cc: Rick Edgecombe <rick.p.edgecombe@xxxxxxxxx>
> Cc: Shuah Khan <shuah@xxxxxxxxxx>
> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> Cc: Tycho Andersen <tycho@xxxxxxxx>
> Cc: Will Deacon <will@xxxxxxxxxx>
> ---
> 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 2d0c6721879d..bb28dd6d9e22 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
> @@ -839,7 +840,7 @@ 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 469211c7cc3a..05026460e2ee 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_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B,
> + PAGE_SIZE << order);
> +
> + return 0;
> +}
> +
> +static void secretmem_unaccount_pages(struct page *page, int order)
> +{
> +
> + mod_lruvec_page_state(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);
> @@ -56,6 +83,10 @@ static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp)
> if (!page)
> return -ENOMEM;
>
> + err = secretmem_account_pages(page, gfp, PMD_PAGE_ORDER);
> + if (err)
> + goto err_cma_release;
> +
> /*
> * clear the data left from the prevoius user before dropping the
> * pages from the direct map
> @@ -65,7 +96,7 @@ static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp)
>
> err = set_direct_map_invalid_noflush(page, nr_pages);
> if (err)
> - goto err_cma_release;
> + goto err_memcg_uncharge;
>
> addr = (unsigned long)page_address(page);
> err = gen_pool_add(pool, addr, PMD_SIZE, NUMA_NO_NODE);
> @@ -83,6 +114,8 @@ 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;
> @@ -314,6 +347,7 @@ 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
>
