On Mon, 24 Feb 2020, Dan Schatzberg wrote:
> memalloc_use_memcg() worked for kernel allocations but was silently
> ignored for user pages.
>
> This patch establishes a precedence order for who gets charged:
>
> 1. If there is a memcg associated with the page already, that memcg is
> charged. This happens during swapin.
>
> 2. If an explicit mm is passed, mm->memcg is charged. This happens
> during page faults, which can be triggered in remote VMs (eg gup).
>
> 3. Otherwise consult the current process context. If it has configured
> a current->active_memcg, use that. Otherwise, current->mm->memcg.
>
> Previously, if a NULL mm was passed to mem_cgroup_try_charge (case 3) it
> would always charge the root cgroup. Now it looks up the current
> active_memcg first (falling back to charging the root cgroup if not
> set).
>
> Signed-off-by: Dan Schatzberg <schatzberg.dan@xxxxxxxxx>
> Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
> Acked-by: Tejun Heo <tj@xxxxxxxxxx>
> Acked-by: Chris Down <chris@xxxxxxxxxxxxxx>
Acked-by: Hugh Dickins <hughd@xxxxxxxxxx>
> Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
> Signed-off-by: Dan Schatzberg <schatzberg.dan@xxxxxxxxx>
> ---
> mm/memcontrol.c | 11 ++++++++---
> mm/shmem.c | 4 ++--
> 2 files changed, 10 insertions(+), 5 deletions(-)
>
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index d09776cd6e10..222e4aac0c85 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -6319,7 +6319,8 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
> * @compound: charge the page as compound or small page
> *
> * Try to charge @page to the memcg that @mm belongs to, reclaiming
> - * pages according to @gfp_mask if necessary.
> + * pages according to @gfp_mask if necessary. If @mm is NULL, try to
> + * charge to the active memcg.
> *
> * Returns 0 on success, with *@memcgp pointing to the charged memcg.
> * Otherwise, an error code is returned.
> @@ -6363,8 +6364,12 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
> }
> }
>
> - if (!memcg)
> - memcg = get_mem_cgroup_from_mm(mm);
> + if (!memcg) {
> + if (!mm)
> + memcg = get_mem_cgroup_from_current();
> + else
> + memcg = get_mem_cgroup_from_mm(mm);
> + }
>
> ret = try_charge(memcg, gfp_mask, nr_pages);
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> index c8f7540ef048..8664c97851f2 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -1631,7 +1631,7 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
> {
> struct address_space *mapping = inode->i_mapping;
> struct shmem_inode_info *info = SHMEM_I(inode);
> - struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm;
> + struct mm_struct *charge_mm = vma ? vma->vm_mm : NULL;
> struct mem_cgroup *memcg;
> struct page *page;
> swp_entry_t swap;
> @@ -1766,7 +1766,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
> }
>
> sbinfo = SHMEM_SB(inode->i_sb);
> - charge_mm = vma ? vma->vm_mm : current->mm;
> + charge_mm = vma ? vma->vm_mm : NULL;
>
> page = find_lock_entry(mapping, index);
> if (xa_is_value(page)) {
> --
> 2.17.1
