Re: [PATCH] mm: net: memcg accounting for TCP rx zerocopy

[Roman Gushchin]

On Tue, Jan 12, 2021 at 01:41:05PM -0800, Shakeel Butt wrote:
> From: Arjun Roy <arjunroy@xxxxxxxxxx>
> 
> TCP zerocopy receive is used by high performance network applications to
> further scale. For RX zerocopy, the memory containing the network data
> filled by network driver is directly mapped into the address space of
> high performance applications. To keep the TLB cost low, these
> applications unmaps the network memory in big batches. So, this memory
> can remain mapped for long time. This can cause memory isolation issue
> as this memory becomes unaccounted after getting mapped into the
> application address space. This patch adds the memcg accounting for such
> memory.
> 
> Accounting the network memory comes with its own unique challenge. The
> high performance NIC drivers use page pooling to reuse the pages to
> eliminate/reduce the expensive setup steps like IOMMU. These drivers
> keep an extra reference on the pages and thus we can not depends on the
> page reference for the uncharging. The page in the pool may keep a memcg
> pinned for arbitrary long time or may get used by other memcg.
> 
> This patch decouples the uncharging of the page from the refcnt and
> associate it with the map count i.e. the page gets uncharged when the
> last address space unmaps it. Now the question what if the driver drops
> its reference while the page is still mapped. That is fine as the
> address space also holds a reference to the page i.e. the reference
> count can not drop to zero before the map count.
> 
> Signed-off-by: Arjun Roy <arjunroy@xxxxxxxxxx>
> Co-developed-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
> Signed-off-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
> ---
>  include/linux/memcontrol.h | 34 +++++++++++++++++++--
>  mm/memcontrol.c            | 60 ++++++++++++++++++++++++++++++++++++++
>  mm/rmap.c                  |  3 ++
>  net/ipv4/tcp.c             | 27 +++++++++++++----
>  4 files changed, 116 insertions(+), 8 deletions(-)
> 
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 7a38a1517a05..0b0e3b4615cf 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -349,11 +349,13 @@ extern struct mem_cgroup *root_mem_cgroup;
>  
>  enum page_memcg_data_flags {
>  	/* page->memcg_data is a pointer to an objcgs vector */
> -	MEMCG_DATA_OBJCGS = (1UL << 0),
> +	MEMCG_DATA_OBJCGS	= (1UL << 0),
>  	/* page has been accounted as a non-slab kernel page */
> -	MEMCG_DATA_KMEM = (1UL << 1),
> +	MEMCG_DATA_KMEM		= (1UL << 1),
> +	/* page has been accounted as network memory */
> +	MEMCG_DATA_SOCK		= (1UL << 2),
>  	/* the next bit after the last actual flag */
> -	__NR_MEMCG_DATA_FLAGS  = (1UL << 2),
> +	__NR_MEMCG_DATA_FLAGS	= (1UL << 3),
>  };
>  
>  #define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1)
> @@ -444,6 +446,11 @@ static inline bool PageMemcgKmem(struct page *page)
>  	return page->memcg_data & MEMCG_DATA_KMEM;
>  }
>  
> +static inline bool PageMemcgSock(struct page *page)
> +{
> +	return page->memcg_data & MEMCG_DATA_SOCK;
> +}
> +
>  #ifdef CONFIG_MEMCG_KMEM
>  /*
>   * page_objcgs - get the object cgroups vector associated with a page
> @@ -1095,6 +1102,11 @@ static inline bool PageMemcgKmem(struct page *page)
>  	return false;
>  }
>  
> +static inline bool PageMemcgSock(struct page *page)
> +{
> +	return false;
> +}
> +
>  static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
>  {
>  	return true;
> @@ -1561,6 +1573,10 @@ extern struct static_key_false memcg_sockets_enabled_key;
>  #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key)
>  void mem_cgroup_sk_alloc(struct sock *sk);
>  void mem_cgroup_sk_free(struct sock *sk);
> +int mem_cgroup_charge_sock_pages(struct mem_cgroup *memcg, struct page **pages,
> +				 unsigned int nr_pages);
> +void mem_cgroup_uncharge_sock_pages(struct page **pages, unsigned int nr_pages);
> +
>  static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
>  {
>  	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure)
> @@ -1589,6 +1605,18 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
>  					  int nid, int shrinker_id)
>  {
>  }
> +
> +static inline int mem_cgroup_charge_sock_pages(struct mem_cgroup *memcg,
> +					       struct page **pages,
> +					       unsigned int nr_pages)
> +{
> +	return 0;
> +}
> +
> +static inline void mem_cgroup_uncharge_sock_pages(struct page **pages,
> +						  unsigned int nr_pages)
> +{
> +}
>  #endif
>  
>  #ifdef CONFIG_MEMCG_KMEM
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index db9836f4b64b..38e94538e081 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -7061,6 +7061,66 @@ void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages)
>  	refill_stock(memcg, nr_pages);
>  }
>  
> +/**
> + * mem_cgroup_charge_sock_pages - charge socket memory
> + * @memcg: memcg to charge
> + * @pages: array of pages to charge
> + * @nr_pages: number of pages
> + *
> + * Charges all @pages to current's memcg. The caller should have a reference on
> + * the given memcg.
> + *
> + * Returns 0 on success.
> + */
> +int mem_cgroup_charge_sock_pages(struct mem_cgroup *memcg, struct page **pages,
> +				 unsigned int nr_pages)
> +{
> +	int ret = 0;
> +
> +	if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg))
> +		goto out;
> +
> +	ret = try_charge(memcg, GFP_KERNEL, nr_pages);
> +
> +	if (!ret) {
> +		int i;
> +
> +		for (i = 0; i < nr_pages; i++)
> +			pages[i]->memcg_data = (unsigned long)memcg |
> +				MEMCG_DATA_SOCK;
> +		css_get_many(&memcg->css, nr_pages);
> +	}
> +out:
> +	return ret;
> +}
> +
> +/**
> + * mem_cgroup_uncharge_sock_pages - uncharge socket pages
> + * @pages: array of pages to uncharge
> + * @nr_pages: number of pages
> + *
> + * This assumes all pages are charged to the same memcg.
> + */
> +void mem_cgroup_uncharge_sock_pages(struct page **pages, unsigned int nr_pages)
> +{
> +	int i;
> +	struct mem_cgroup *memcg;
> +
> +	if (mem_cgroup_disabled())
> +		return;
> +
> +	memcg = page_memcg(pages[0]);
> +
> +	if (unlikely(!memcg))
> +		return;
> +
> +	refill_stock(memcg, nr_pages);
> +
> +	for (i = 0; i < nr_pages; i++)
> +		pages[i]->memcg_data = 0;
> +	css_put_many(&memcg->css, nr_pages);
> +}

What about statistics? Should it be accounted towards "sock", "slab/kmem" or deserves
a separate counter? Do we plan to eventually have shrinkers for this type of memory?

Two functions above do not contain anything network-related,
except the MEMCG_DATA_SOCK flag. Can it be merged with the kmem charging path?

Code-wise the patch looks good to me.

Thanks!