mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Wenchao Hao <haowenchao22@gmail.com>
To: Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	Minchan Kim <minchan@kernel.org>,
	Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Nhat Pham <nphamcs@gmail.com>,
	Joshua Hahn <joshua.hahnjy@gmail.com>,
	Barry Song <baohua@kernel.org>,
	Wenchao Hao <haowenchao@xiaomi.com>
Subject: [PATCH v4 1/4] mm/zsmalloc: encode class index in obj value for lockless class lookup
Date: Tue,  9 Jun 2026 19:35:17 +0800	[thread overview]
Message-ID: <20260609113520.3507783-2-haowenchao22@gmail.com> (raw)
In-Reply-To: <20260609113520.3507783-1-haowenchao22@gmail.com>

From: Wenchao Hao <haowenchao@xiaomi.com>

Encode the size_class index (class_idx) into the obj value so that
zs_free() can determine the correct size_class without dereferencing
the handle->obj->PFN->zpdesc->zspage->class chain under pool->lock.
class_idx is invariant across page migration (only PFN is rewritten),
so a lockless read of obj always yields a valid class_idx.

Where obj has more bits below the PFN field than obj_idx alone
needs, split that space into class_idx and obj_idx subfields:

 |<-- _PFN_BITS -->|<-- ZS_OBJ_CLASS_BITS -->|<-- ZS_OBJ_IDX_BITS -->|
 +-----------------+-------------------------+-----------------------+
 |       PFN       |        class_idx        |        obj_idx        |
 +-----------------+-------------------------+-----------------------+
MSB                ^                                                LSB
                   |
                   +-- ZS_OBJ_PFN_SHIFT

The macro layout changes as follows:

    Before            After               Meaning
    ----------------  ------------------  ----------------------------
    OBJ_INDEX_BITS    ZS_OBJ_IDX_BITS     width of obj_idx subfield
    OBJ_INDEX_MASK    ZS_OBJ_IDX_MASK     mask  of obj_idx subfield
    (n/a)             ZS_OBJ_CLASS_BITS   width of class_idx subfield
    (n/a)             ZS_OBJ_CLASS_MASK   mask  of class_idx subfield
    (n/a)             ZS_OBJ_PFN_SHIFT    bit offset of PFN in obj

ZS_OBJ_CLASS_BITS folds to 0 (and the layout collapses to
[PFN | obj_idx]) when obj has no spare bits, i.e. on 32-bit
or on 64-bit fallback paths where MAX_POSSIBLE_PHYSMEM_BITS ==
BITS_PER_LONG (e.g. UML); zs_free() then falls back to
pool->lock.

Signed-off-by: Wenchao Hao <haowenchao@xiaomi.com>
---
 mm/zsmalloc.c | 99 +++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 85 insertions(+), 14 deletions(-)

diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 63128ddb7959..f84258d63917 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -67,8 +67,8 @@
 #define MAX_POSSIBLE_PHYSMEM_BITS MAX_PHYSMEM_BITS
 #else
 /*
- * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just
- * be PAGE_SHIFT
+ * If this definition of MAX_PHYSMEM_BITS is used, ZS_OBJ_PFN_SHIFT will
+ * just be PAGE_SHIFT
  */
 #define MAX_POSSIBLE_PHYSMEM_BITS BITS_PER_LONG
 #endif
@@ -88,8 +88,23 @@
 #define OBJ_TAG_BITS	1
 #define OBJ_TAG_MASK	OBJ_ALLOCATED_TAG
 
-#define OBJ_INDEX_BITS	(BITS_PER_LONG - _PFN_BITS)
-#define OBJ_INDEX_MASK	((_AC(1, UL) << OBJ_INDEX_BITS) - 1)
+/*
+ * obj is encoded as [PFN | class_idx | obj_idx] within an unsigned long:
+ *
+ *   |<-- _PFN_BITS -->|<-- ZS_OBJ_CLASS_BITS -->|<-- ZS_OBJ_IDX_BITS -->|
+ *   +-----------------+-------------------------+-----------------------+
+ *   |       PFN       |        class_idx        |        obj_idx        |
+ *   +-----------------+-------------------------+-----------------------+
+ *  MSB                ^                                                LSB
+ *                     |
+ *                     +-- ZS_OBJ_PFN_SHIFT
+ *
+ * Encoding class_idx into obj lets zs_free() locate the size_class
+ * without holding pool->lock; class_idx is invariant across page
+ * migration (only PFN changes), so a lockless read of the obj value
+ * always yields a valid class_idx.
+ */
+#define ZS_OBJ_PFN_SHIFT	(BITS_PER_LONG - _PFN_BITS)
 
 #define HUGE_BITS	1
 #define FULLNESS_BITS	4
@@ -98,9 +113,55 @@
 
 #define ZS_MAX_PAGES_PER_ZSPAGE	(_AC(CONFIG_ZSMALLOC_CHAIN_SIZE, UL))
 
+/*
+ * ceil(log2(ZS_MAX_PAGES_PER_ZSPAGE)) at preprocessor time, for use
+ * in #if below.  Kconfig restricts ZSMALLOC_CHAIN_SIZE to [4, 16].
+ */
+#if ZS_MAX_PAGES_PER_ZSPAGE <= 4
+#define ZS_CHAIN_LOG2		2
+#elif ZS_MAX_PAGES_PER_ZSPAGE <= 8
+#define ZS_CHAIN_LOG2		3
+#elif ZS_MAX_PAGES_PER_ZSPAGE <= 16
+#define ZS_CHAIN_LOG2		4
+#else
+#error "ZSMALLOC_CHAIN_SIZE out of expected range [4,16]"
+#endif
+
+/* PAGE_SHIFT - 5 = log2(PAGE_SIZE / 32); 32 = ZS_MIN_ALLOC_SIZE floor. */
+#define ZS_MAX_OBJ_PER_PAGE_LOG2	(PAGE_SHIFT - 5)
+
+/*
+ * obj_idx width that keeps ZS_MIN_ALLOC_SIZE at its 32-byte floor.
+ * Below this, ZS_MIN_ALLOC_SIZE is auto-raised by the MAX(32, ...)
+ * formula -- still correct, but objects are coarser.
+ */
+#define ZS_OBJ_IDX_DENSE_BITS	(ZS_CHAIN_LOG2 + ZS_MAX_OBJ_PER_PAGE_LOG2)
+
+/*
+ * Encode class_idx only when obj has spare bits; otherwise
+ * ZS_OBJ_CLASS_BITS folds to 0 (32-bit, or 64-bit UML/fallback).
+ */
+#if BITS_PER_LONG >= 64 && \
+	ZS_OBJ_PFN_SHIFT >= (CLASS_BITS + 1) + ZS_OBJ_IDX_DENSE_BITS
+#define ZS_OBJ_CLASS_BITS	(CLASS_BITS + 1)
+#else
+#define ZS_OBJ_CLASS_BITS	0
+#endif
+#define ZS_OBJ_CLASS_MASK	((_AC(1, UL) << ZS_OBJ_CLASS_BITS) - 1)
+
+#define ZS_OBJ_IDX_BITS		(ZS_OBJ_PFN_SHIFT - ZS_OBJ_CLASS_BITS)
+#define ZS_OBJ_IDX_MASK		((_AC(1, UL) << ZS_OBJ_IDX_BITS) - 1)
+
+/*
+ * Belt-and-suspenders: the #if above already guarantees this when
+ * class_idx is enabled.  Catches future tweaks that bypass it.
+ */
+static_assert(ZS_OBJ_IDX_BITS >= ZS_CHAIN_LOG2,
+	      "zsmalloc: ZS_MIN_ALLOC_SIZE would exceed ZS_MAX_ALLOC_SIZE");
+
 /* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */
 #define ZS_MIN_ALLOC_SIZE \
-	MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS))
+	MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> ZS_OBJ_IDX_BITS))
 /* each chunk includes extra space to keep handle */
 #define ZS_MAX_ALLOC_SIZE	PAGE_SIZE
 
@@ -721,26 +782,35 @@ static struct zpdesc *get_next_zpdesc(struct zpdesc *zpdesc)
 static void obj_to_location(unsigned long obj, struct zpdesc **zpdesc,
 				unsigned int *obj_idx)
 {
-	*zpdesc = pfn_zpdesc(obj >> OBJ_INDEX_BITS);
-	*obj_idx = (obj & OBJ_INDEX_MASK);
+	*zpdesc = pfn_zpdesc(obj >> ZS_OBJ_PFN_SHIFT);
+	*obj_idx = (obj & ZS_OBJ_IDX_MASK);
 }
 
 static void obj_to_zpdesc(unsigned long obj, struct zpdesc **zpdesc)
 {
-	*zpdesc = pfn_zpdesc(obj >> OBJ_INDEX_BITS);
+	*zpdesc = pfn_zpdesc(obj >> ZS_OBJ_PFN_SHIFT);
+}
+
+/* Folds to 0 when ZS_OBJ_CLASS_BITS == 0; no ifdef needed at callers. */
+static unsigned int obj_to_class_idx(unsigned long obj)
+{
+	return (obj >> ZS_OBJ_IDX_BITS) & ZS_OBJ_CLASS_MASK;
 }
 
 /**
- * location_to_obj - get obj value encoded from (<zpdesc>, <obj_idx>)
+ * location_to_obj - encode (<zpdesc>, <obj_idx>, <class_idx>) into obj value
  * @zpdesc: zpdesc object resides in zspage
  * @obj_idx: object index
+ * @class_idx: size class index; ignored when ZS_OBJ_CLASS_BITS == 0
  */
-static unsigned long location_to_obj(struct zpdesc *zpdesc, unsigned int obj_idx)
+static unsigned long location_to_obj(struct zpdesc *zpdesc, unsigned int obj_idx,
+				     unsigned int class_idx)
 {
 	unsigned long obj;
 
-	obj = zpdesc_pfn(zpdesc) << OBJ_INDEX_BITS;
-	obj |= obj_idx & OBJ_INDEX_MASK;
+	obj  = zpdesc_pfn(zpdesc) << ZS_OBJ_PFN_SHIFT;
+	obj |= (unsigned long)(class_idx & ZS_OBJ_CLASS_MASK) << ZS_OBJ_IDX_BITS;
+	obj |= obj_idx & ZS_OBJ_IDX_MASK;
 
 	return obj;
 }
@@ -1276,7 +1346,7 @@ static unsigned long obj_malloc(struct zs_pool *pool,
 	kunmap_local(vaddr);
 	mod_zspage_inuse(zspage, 1);
 
-	obj = location_to_obj(m_zpdesc, obj);
+	obj = location_to_obj(m_zpdesc, obj, zspage->class);
 	record_obj(handle, obj);
 
 	return obj;
@@ -1762,7 +1832,8 @@ static int zs_page_migrate(struct page *newpage, struct page *page,
 
 			old_obj = handle_to_obj(handle);
 			obj_to_location(old_obj, &dummy, &obj_idx);
-			new_obj = (unsigned long)location_to_obj(newzpdesc, obj_idx);
+			new_obj = location_to_obj(newzpdesc, obj_idx,
+						  obj_to_class_idx(old_obj));
 			record_obj(handle, new_obj);
 		}
 	}
-- 
2.34.1


  reply	other threads:[~2026-06-09 11:35 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-09 11:35 [PATCH v4 0/4] mm/zsmalloc: reduce lock contention in zs_free() Wenchao Hao
2026-06-09 11:35 ` Wenchao Hao [this message]
2026-06-09 17:56   ` [PATCH v4 1/4] mm/zsmalloc: encode class index in obj value for lockless class lookup Nhat Pham
2026-06-10  3:18     ` Wenchao Hao
2026-06-10 21:27       ` Barry Song
2026-06-11  3:15         ` Wenchao Hao
2026-06-11 14:31           ` Nhat Pham
2026-06-12  2:00             ` Wenchao Hao
2026-06-15  2:49               ` Nhat Pham
2026-06-09 11:35 ` [PATCH v4 2/4] mm/zsmalloc: drop pool->lock from zs_free on 64-bit systems Wenchao Hao
2026-06-09 17:58   ` Nhat Pham
2026-06-09 11:35 ` [PATCH v4 3/4] mm/zsmalloc: drop class lock before freeing zspage Wenchao Hao
2026-06-09 11:35 ` [PATCH v4 4/4] mm/zsmalloc: document free_zspage helper variants Wenchao Hao

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=20260609113520.3507783-2-haowenchao22@gmail.com \
    --to=haowenchao22@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=baohua@kernel.org \
    --cc=haowenchao@xiaomi.com \
    --cc=joshua.hahnjy@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=minchan@kernel.org \
    --cc=nphamcs@gmail.com \
    --cc=senozhatsky@chromium.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

all inboxes | Powered by JetHome®