Re: [PATCH v5] mm/page_owner.c: add llseek for page_owner

From: Vlastimil Babka (SUSE)
Date: Tue Aug 09 2022 - 05:30:57 EST


On 8/9/22 04:47, Kassey Li wrote:
> There is usage to dump a given cma region page_owner
> instead of all page's.
>
> This change allows to specify a ppos as start_pfn
> by fseek.
>
> Any invalid ppos will be skipped, so it did not
> broken the origin dump feature.
>
> Suggested-by: Vlastimil Babka <vbabka@xxxxxxx>
> Signed-off-by: Kassey Li <quic_yingangl@xxxxxxxxxxx>
> ---
> Documentation/vm/page_owner.rst | 6 ++++++
> mm/internal.h | 5 +++++
> mm/page_owner.c | 9 ++++++---
> 3 files changed, 17 insertions(+), 3 deletions(-)
>
> diff --git a/Documentation/vm/page_owner.rst b/Documentation/vm/page_owner.rst
> index f5c954afe97c..8d33d976da8a 100644
> --- a/Documentation/vm/page_owner.rst
> +++ b/Documentation/vm/page_owner.rst
> @@ -95,6 +95,12 @@ Usage
> PFN XXX ...
> // Detailed stack
>
> + By default, it will do full pfn dump, to start with a given pfn,
> + page_owner supports fseek.
> +
> + FILE *fp = fopen("/sys/kernel/debug/page_owner", "r");
> + fseek(fp, pfn_start, SEEK_SET);
> +
> The ``page_owner_sort`` tool ignores ``PFN`` rows, puts the remaining rows
> in buf, uses regexp to extract the page order value, counts the times
> and pages of buf, and finally sorts them according to the parameter(s).
> diff --git a/mm/internal.h b/mm/internal.h
> index c0f8fbe0445b..1ad8f86e6e33 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -189,6 +189,11 @@ extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason
> */
> extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
>
> +/*
> + * in mm/page_owner.c:

This should say where it's defined, not used from, and that's
fs/proc/base.c. But it's already declared in fs/proc/internal.h so maybe
page_owner.c could just include that header (although it's a bit meh).

> + */
> +extern loff_t mem_lseek(struct file *, loff_t, int);
> +
> /*
> * in mm/page_alloc.c
> */
> diff --git a/mm/page_owner.c b/mm/page_owner.c
> index e4c6f3f1695b..dcbe05e206e1 100644
> --- a/mm/page_owner.c
> +++ b/mm/page_owner.c
> @@ -497,8 +497,10 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
> return -EINVAL;
>
> page = NULL;
> - pfn = min_low_pfn + *ppos;
> -
> + if (*ppos == 0)
> + pfn= min_low_pfn;

missing space before '='

> + else
> + pfn = *ppos;
> /* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */
> while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0)
> pfn++;
> @@ -561,7 +563,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
> continue;
>
> /* Record the next PFN to read in the file offset */
> - *ppos = (pfn - min_low_pfn) + 1;
> + *ppos = pfn + 1;
>
> return print_page_owner(buf, count, pfn, page,
> page_owner, handle);
> @@ -660,6 +662,7 @@ static void init_early_allocated_pages(void)
>
> static const struct file_operations proc_page_owner_operations = {
> .read = read_page_owner,
> + .llseek = mem_lseek,
> };
>
> static int __init pageowner_init(void)