The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: Baoquan He <baoquan.he@linux.dev>
To: linux-mm@kvack.org
Cc: akpm@linux-foundation.org, chrisl@kernel.org, kasong@tencent.com,
	shikemeng@huaweicloud.com, nphamcs@gmail.com, baohua@kernel.org,
	youngjun.park@lge.com, hannes@cmpxchg.org, yosry@kernel.org,
	chengming.zhou@linux.dev, linux-kernel@vger.kernel.org,
	Baoquan He <baoquan.he@linux.dev>
Subject: [RFC PATCH 02/10] mm/swap_table: add Redirect entry encoding for ghost swap backend switching
Date: Tue,  7 Jul 2026 16:26:04 +0800	[thread overview]
Message-ID: <20260707082614.95030-3-baoquan.he@linux.dev> (raw)
In-Reply-To: <20260707082614.95030-1-baoquan.he@linux.dev>

Introduce SWP_TB_REDIRECT_MARK (0b101) as a new swap table entry type
that stores a physical swp_entry_t directly.  This allows a ghost
swap slot to redirect to a physical swap slot after zswap writeback.

The swp_entry_t has its low 12 bits clear (page-aligned offset), so
the 3-bit mark is ORed directly into the value without shifting and
without losing any type or offset bits.

Add inline helpers:
- swp_tb_is_redirect():  type check
- swp_entry_to_redirect(): encode a swp_entry_t as a Redirect entry
- redirect_to_swp_entry(): decode a Redirect entry back to swp_entry_t

Update the swap table entry type documentation to include the new
Redirect type.

Signed-off-by: Baoquan He <baoquan.he@linux.dev>
---
 mm/swap_table.h | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/mm/swap_table.h b/mm/swap_table.h
index 6318bf8aa76b..5a971152cf23 100644
--- a/mm/swap_table.h
+++ b/mm/swap_table.h
@@ -29,6 +29,7 @@ struct swap_memcg_table {
  * Shadow:   |SWAP_COUNT|Z|---- SHADOW_VAL ---|1| - Swapped out slot
  * PFN:      |SWAP_COUNT|Z|------ PFN -------|10| - Cached slot
  * Pointer:  |----------- Pointer ----------|100| - Zswap compressed entry
+ * Redirect: |------- swp_entry_t.val ------|101| - Redirect to phys swap
  * Bad:      |------------- 1 -------------|1000| - Bad slot
  *
  * COUNT is `SWP_TB_COUNT_BITS` long, Z is the `SWP_TB_ZERO_FLAG` bit,
@@ -55,6 +56,11 @@ struct swap_memcg_table {
  *   all upper bits. `0b100` is used as the marker because zswap_entry
  *   pointers are at least 8-byte aligned, leaving the lower three bits free.
  *
+ * - Redirect: Stores a physical swp_entry_t directly, ending with `0b101`.
+ *   Used by ghost swapfiles to redirect a virtual slot to a physical swap
+ *   slot after zswap writeback.  swp_entry_t has bits 0-11 clear (page-aligned
+ *   offset), so the 3-bit mark is ORed directly into the value without shifting.
+ *
  * - Bad: Swap slot is reserved, protects swap header or holes on swap devices.
  */
 
@@ -83,6 +89,15 @@ struct swap_memcg_table {
 /* Pointer: zswap_entry pointer stored directly, ends with 0b100 */
 #define SWP_TB_POINTER_MARK	0b100UL
 
+/*
+ * Redirect: stores a physical swp_entry_t directly, ends with 0b101.
+ * Used by ghost swapfiles to redirect a virtual slot to a physical
+ * swap slot after writeback.  swp_entry_t has its low 12 bits clear
+ * (page-aligned offset), so we can OR the 3-bit mark directly into
+ * the entry value without shifting and without losing type bits.
+ */
+#define SWP_TB_REDIRECT_MARK	0b101UL
+
 /* Bad slot: ends with 0b1000 and rests of bits are all 1 */
 #define SWP_TB_BAD		((~0UL) << 3)
 
@@ -176,6 +191,11 @@ static inline bool swp_tb_is_pointer(unsigned long swp_tb)
 	return (swp_tb & (BIT(3) - 1)) == SWP_TB_POINTER_MARK;
 }
 
+static inline bool swp_tb_is_redirect(unsigned long swp_tb)
+{
+	return (swp_tb & (BIT(3) - 1)) == SWP_TB_REDIRECT_MARK;
+}
+
 static inline bool swp_tb_is_countable(unsigned long swp_tb)
 {
 	return (swp_tb_is_shadow(swp_tb) || swp_tb_is_folio(swp_tb) ||
@@ -215,6 +235,24 @@ static inline void *swp_tb_to_pointer(unsigned long swp_tb)
 	return (void *)(swp_tb & ~((unsigned long)(BIT(3) - 1)));
 }
 
+/*
+ * Redirect encoding: swp_entry_t is stored directly, with the 3-bit
+ * mark ORed into the low bits.  swp_entry_t.val has bits 0-11 clear
+ * (page-aligned offset), so no shifting is needed and no type bits
+ * are lost.
+ */
+static inline unsigned long swp_entry_to_redirect(swp_entry_t entry)
+{
+	VM_WARN_ON(entry.val & (BIT(3) - 1));
+	return entry.val | SWP_TB_REDIRECT_MARK;
+}
+
+static inline swp_entry_t redirect_to_swp_entry(unsigned long swp_tb)
+{
+	VM_WARN_ON(!swp_tb_is_redirect(swp_tb));
+	return (swp_entry_t){ .val = swp_tb & ~((unsigned long)(BIT(3) - 1)) };
+}
+
 static inline unsigned char __swp_tb_get_count(unsigned long swp_tb)
 {
 	VM_WARN_ON(!swp_tb_is_countable(swp_tb));
-- 
2.54.0


  parent reply	other threads:[~2026-07-07  8:26 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-07  8:26 [RFC PATCH 00/10] mm/swap: ghost swapfile with backend switching via Redirect entries Baoquan He
2026-07-07  8:26 ` [RFC PATCH 01/10] mm: ghost swapfile support for zswap Baoquan He
2026-07-07  8:26 ` Baoquan He [this message]
2026-07-07  8:26 ` [RFC PATCH 03/10] mm/swap: add redirect_xa field and ghost redirect helper declarations Baoquan He
2026-07-07  8:26 ` [RFC PATCH 04/10] mm/swapfile: implement ghost redirect helpers and free-path cascade Baoquan He
2026-07-07  8:26 ` [RFC PATCH 05/10] mm/swap_state: restore Redirect entry when swap cache folio is removed Baoquan He
2026-07-07  8:26 ` [RFC PATCH 06/10] mm/zswap: implement ghost-to-physical writeback for backend switching Baoquan He
2026-07-07  8:26 ` [RFC PATCH 07/10] mm/page_io: forward ghost swap reads to physical device via Redirect Baoquan He
2026-07-07  8:26 ` [RFC PATCH 08/10] mm/swapfile: manage ghost cluster_info via lazy vmalloc Baoquan He
2026-07-07  8:26 ` [RFC PATCH 09/10] mm/swapfile: implement swap_ghost_extend_max() for dynamic growth Baoquan He
2026-07-07 22:36   ` Nhat Pham
2026-07-07  8:26 ` [RFC PATCH 10/10] mm/swapfile: add sysfs interface for ghost swap extension Baoquan He
2026-07-07  8:56 ` [RFC PATCH 00/10] mm/swap: ghost swapfile with backend switching via Redirect entries Baoquan He
2026-07-07 21:23 ` Nhat Pham
2026-07-07 21:25   ` Nhat Pham

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=20260707082614.95030-3-baoquan.he@linux.dev \
    --to=baoquan.he@linux.dev \
    --cc=akpm@linux-foundation.org \
    --cc=baohua@kernel.org \
    --cc=chengming.zhou@linux.dev \
    --cc=chrisl@kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=kasong@tencent.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=nphamcs@gmail.com \
    --cc=shikemeng@huaweicloud.com \
    --cc=yosry@kernel.org \
    --cc=youngjun.park@lge.com \
    /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