Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Kassey Li <quic_yingangl@quicinc.com>
To:     akpm@linux-foundation.org, vbabka@kernel.org
Cc:     Kassey Li <quic_yingangl@quicinc.com>, minchan@kernel.org,
        vbabka@suse.cz, iamjoonsoo.kim@lge.com,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [PATCH v9] mm/page_owner.c: add llseek for page_owner
Date:   Thu, 18 Aug 2022 10:24:25 +0800
Message-Id: <20220818022425.31056-1-quic_yingangl@quicinc.com>
Precedence: bulk

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

To speed up and save time, this change allows specify start pfn
by add llseek for page_onwer.

Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Kassey Li <quic_yingangl@quicinc.com>
---
 Documentation/mm/page_owner.rst |  5 +++++
 mm/page_owner.c                 | 24 +++++++++++++++++++++---
 2 files changed, 26 insertions(+), 3 deletions(-)

diff --git a/Documentation/mm/page_owner.rst b/Documentation/mm/page_owner.rst
index f5c954afe97c..f18fd8907049 100644
--- a/Documentation/mm/page_owner.rst
+++ b/Documentation/mm/page_owner.rst
@@ -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
diff --git a/mm/page_owner.c b/mm/page_owner.c
index e4c6f3f1695b..25720d81bc26 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;
+	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);
@@ -570,6 +572,21 @@ 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;
@@ -660,6 +677,7 @@ 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)
-- 
2.17.1