On 2024-02-07 5:41 pm, Pasha Tatashin wrote:
> Add NR_IOMMU_PAGES into node_stat_item that counts number of pages
> that are allocated by the IOMMU subsystem.
>
> The allocations can be view per-node via:
> /sys/devices/system/node/nodeN/vmstat.
>
> For example:
>
> $ grep iommu /sys/devices/system/node/node*/vmstat
> /sys/devices/system/node/node0/vmstat:nr_iommu_pages 106025
> /sys/devices/system/node/node1/vmstat:nr_iommu_pages 3464
>
> The value is in page-count, therefore, in the above example
> the iommu allocations amount to ~428M.
>
> Signed-off-by: Pasha Tatashin <[email protected]>
> Acked-by: David Rientjes <[email protected]>
> Tested-by: Bagas Sanjaya <[email protected]>
> ---
> drivers/iommu/iommu-pages.h | 30 ++++++++++++++++++++++++++++++
> include/linux/mmzone.h | 3 +++
> mm/vmstat.c | 3 +++
> 3 files changed, 36 insertions(+)
>
> diff --git a/drivers/iommu/iommu-pages.h b/drivers/iommu/iommu-pages.h
> index c412d0aaa399..7336f976b641 100644
> --- a/drivers/iommu/iommu-pages.h
> +++ b/drivers/iommu/iommu-pages.h
> @@ -17,6 +17,30 @@
> * state can be rather large, i.e. multiple gigabytes in size.
> */
>
> +/**
> + * __iommu_alloc_account - account for newly allocated page.
> + * @page: head struct page of the page.
> + * @order: order of the page
> + */
> +static inline void __iommu_alloc_account(struct page *page, int order)
> +{
> + const long pgcnt = 1l << order;
> +
> + mod_node_page_state(page_pgdat(page), NR_IOMMU_PAGES, pgcnt);
> +}
> +
> +/**
> + * __iommu_free_account - account a page that is about to be freed.
> + * @page: head struct page of the page.
> + * @order: order of the page
> + */
> +static inline void __iommu_free_account(struct page *page, int order)
> +{
> + const long pgcnt = 1l << order;
> +
> + mod_node_page_state(page_pgdat(page), NR_IOMMU_PAGES, -pgcnt);
> +}
> +
> /**
> * __iommu_alloc_pages_node - allocate a zeroed page of a given order from
> * specific NUMA node.
> @@ -35,6 +59,8 @@ static inline struct page *__iommu_alloc_pages_node(int nid, gfp_t gfp,
> if (unlikely(!page))
> return NULL;
>
> + __iommu_alloc_account(page, order);
> +
> return page;
> }
>
> @@ -53,6 +79,8 @@ static inline struct page *__iommu_alloc_pages(gfp_t gfp, int order)
> if (unlikely(!page))
> return NULL;
>
> + __iommu_alloc_account(page, order);
> +
> return page;
> }
>
> @@ -89,6 +117,7 @@ static inline void __iommu_free_pages(struct page *page, int order)
> if (!page)
> return;
>
> + __iommu_free_account(page, order);
> __free_pages(page, order);
> }
>
> @@ -197,6 +226,7 @@ static inline void iommu_free_pages_list(struct list_head *page)
> struct page *p = list_entry(page->prev, struct page, lru);
>
> list_del(&p->lru);
> + __iommu_free_account(p, 0);
I'm keen to revive my patches to hook up freelist support in
io-pgtable-arm, which would then mean a chance of higher-order GFP_COMP
allocations coming back though this path - do you have any pointers for
what I'd have to do here to make it work properly?
Thanks,
Robin.
> put_page(p);
> }
> }
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index a497f189d988..bb6bc504915a 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -203,6 +203,9 @@ enum node_stat_item {
> #endif
> NR_PAGETABLE, /* used for pagetables */
> NR_SECONDARY_PAGETABLE, /* secondary pagetables, e.g. KVM pagetables */
> +#ifdef CONFIG_IOMMU_SUPPORT
> + NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */
> +#endif
> #ifdef CONFIG_SWAP
> NR_SWAPCACHE,
> #endif
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index db79935e4a54..8507c497218b 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1242,6 +1242,9 @@ const char * const vmstat_text[] = {
> #endif
> "nr_page_table_pages",
> "nr_sec_page_table_pages",
> +#ifdef CONFIG_IOMMU_SUPPORT
> + "nr_iommu_pages",
> +#endif
> #ifdef CONFIG_SWAP
> "nr_swapcached",
> #endif