From: SeongJae Park <sj@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: SeongJae Park <sj@kernel.org>,
damon@lists.linux.dev, linux-kernel@vger.kernel.org,
linux-mm@kvack.org
Subject: [PATCH 06/16] mm/damon/paddr: report filter-passed bytes back for DAMOS_STAT action
Date: Mon, 6 Jan 2025 11:33:51 -0800 [thread overview]
Message-ID: <20250106193401.109161-7-sj@kernel.org> (raw)
In-Reply-To: <20250106193401.109161-1-sj@kernel.org>
DAMOS_STAT action handling of paddr DAMON operations set implementation
is simply ignoring the region-internal DAMOS filters, and therefore not
reporting back the filter-passed bytes. Apply the filters and report
back the information.
Before this change, DAMOS_STAT was doing nothing for DAMOS filters.
Hence users might see some performance regressions. Such regression for
use cases where no region-internal DAMOS filter is added to the scheme
will be negligible, since this change avoids unnecessary filtering works
if no such filter is installed.
For old users who are using DAMOS_STAT with the types of filters, the
regression could be visible depending on the size of the region and the
overhead of the installed DAMOS filters. But, because the filters were
completely ignored before in the use case, no real users would really
depend on such use case that makes no point.
Signed-off-by: SeongJae Park <sj@kernel.org>
---
mm/damon/paddr.c | 35 ++++++++++++++++++++++++++++++++++-
1 file changed, 34 insertions(+), 1 deletion(-)
diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
index 5944316a0b4c..b0c283808ba6 100644
--- a/mm/damon/paddr.c
+++ b/mm/damon/paddr.c
@@ -485,6 +485,39 @@ static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s,
return applied * PAGE_SIZE;
}
+static bool damon_pa_scheme_has_filter(struct damos *s)
+{
+ struct damos_filter *f;
+
+ damos_for_each_filter(f, s)
+ return true;
+ return false;
+}
+
+static unsigned long damon_pa_stat(struct damon_region *r, struct damos *s,
+ unsigned long *sz_filter_passed)
+{
+ unsigned long addr;
+ LIST_HEAD(folio_list);
+
+ if (!damon_pa_scheme_has_filter(s))
+ return 0;
+
+ for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
+ struct folio *folio = damon_get_folio(PHYS_PFN(addr));
+
+ if (!folio)
+ continue;
+
+ if (damos_pa_filter_out(s, folio))
+ goto put_folio;
+ else
+ *sz_filter_passed += folio_size(folio);
+put_folio:
+ folio_put(folio);
+ }
+ return 0;
+}
static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx,
struct damon_target *t, struct damon_region *r,
@@ -501,7 +534,7 @@ static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx,
case DAMOS_MIGRATE_COLD:
return damon_pa_migrate(r, scheme, sz_filter_passed);
case DAMOS_STAT:
- break;
+ return damon_pa_stat(r, scheme, sz_filter_passed);
default:
/* DAMOS actions that not yet supported by 'paddr'. */
break;
--
2.39.5
next prev parent reply other threads:[~2025-01-06 19:34 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-01-06 19:33 [PATCH 00/16] mm/damon: enable page level properties based monitoring SeongJae Park
2025-01-06 19:33 ` [PATCH 01/16] mm/damon: clarify trying vs applying on damos_stat kernel-doc comment SeongJae Park
2025-01-06 19:33 ` [PATCH 02/16] Docs/mm/damon/design: add 'statistics' section SeongJae Park
2025-01-06 19:33 ` [PATCH 03/16] Docs/admin-guide/mm/damon/usage: link damos stat design doc SeongJae Park
2025-01-06 19:33 ` [PATCH 04/16] mm/damon: ask apply_scheme() to report filter-passed region-internal bytes SeongJae Park
2025-01-06 19:33 ` [PATCH 05/16] mm/damon/paddr: report filter-passed bytes back for normal actions SeongJae Park
2025-01-06 19:33 ` SeongJae Park [this message]
2025-01-06 19:33 ` [PATCH 07/16] mm/damon/core: implement per-scheme ops-handled filter-passed bytes stat SeongJae Park
2025-01-06 19:33 ` [PATCH 08/16] mm/damon/syfs-schemes: implement per-scheme " SeongJae Park
2025-01-06 19:33 ` [PATCH 09/16] Docs/mm/damon/design: document sz_ops_filter_passed SeongJae Park
2025-01-06 19:33 ` [PATCH 10/16] Docs/admin-guide/mm/damon/usage: " SeongJae Park
2025-01-06 19:33 ` [PATCH 11/16] Docs/ABI/damon: document per-scheme filter-passed bytes stat file SeongJae Park
2025-01-06 19:33 ` [PATCH 12/16] mm/damon/core: pass per-region filter-passed bytes to damos_walk_control->walk_fn() SeongJae Park
2025-01-06 19:33 ` [PATCH 13/16] mm/damon/sysfs-schemes: expose per-region filter-passed bytes SeongJae Park
2025-01-06 19:33 ` [PATCH 14/16] Docs/mm/damon/design: document per-region sz_filter_passed stat SeongJae Park
2025-01-06 19:34 ` [PATCH 15/16] Docs/admin-guide/mm/damon/usage: document sz_filtered_out of scheme tried region directories SeongJae Park
2025-01-06 19:34 ` [PATCH 16/16] Docs/ABI/damon: document per-region DAMOS filter-passed bytes stat file SeongJae Park
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250106193401.109161-7-sj@kernel.org \
--to=sj@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=damon@lists.linux.dev \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox