system/linux
system/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux synced 2024-10-15 15:59:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

mm/page_owner.c: add llseek for page_owner

Browse source 
It is too slow to dump all the pages, in some usage we just want to dump a
given start pfn, for example: a CMA range or a single page.

To speed up and save time, this change allows specifying of a start pfn by
adding llseek for page_owner.

Link: https://lkml.kernel.org/r/20220818022425.31056-1-quic_yingangl@quicinc.com
Signed-off-by: Kassey Li <quic_yingangl@quicinc.com>
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Kassey Li 2022-08-18 10:24:25 +08:00 committed by Andrew Morton
parent 72c33ef4c0
commit 8f0efa81df
2 changed files with 26 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
Documentation/mm/page_owner.rst
View file

@ -94,6 +94,11 @@ Usage
Page allocated via order XXX, ...
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

24
mm/page_owner.c
View file

@ -516,8 +516,10 @@ 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;
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++;
@ -588,7 +590,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
goto ext_put_continue;
/* Record the next PFN to read in the file offset */
*ppos = (pfn - min_low_pfn) + 1;
*ppos = pfn + 1;
page_owner_tmp = *page_owner;
page_ext_put(page_ext);
@ -601,6 +603,21 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
return 0;
}
static loff_t lseek_page_owner(struct file *file, loff_t offset, int orig)
{
switch (orig) {
case SEEK_SET:
file->f_pos = offset;
break;
case SEEK_CUR:
file->f_pos += offset;
break;
default:
return -EINVAL;
}
return file->f_pos;
}
static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
{
unsigned long pfn = zone->zone_start_pfn;
@ -693,6 +710,7 @@ static void init_early_allocated_pages(void)
static const struct file_operations proc_page_owner_operations = {
.read = read_page_owner,
.llseek = lseek_page_owner,
};
static int __init pageowner_init(void)