The patch titled
Subject: mm, swap_cgroup: remove global swap cgroup lock
has been added to the -mm mm-unstable branch. Its filename is
mm-swap_cgroup-remove-global-swap-cgroup-lock.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-swap_cgroup-remove-global-swap-cgroup-lock.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Kairui Song <kasong@xxxxxxxxxxx>
Subject: mm, swap_cgroup: remove global swap cgroup lock
Date: Tue, 10 Dec 2024 17:28:05 +0800
commit e9e58a4ec3b1 ("memcg: avoid use cmpxchg in swap cgroup
maintainance") replaced the cmpxchg/xchg with a global irq spinlock
because some archs doesn't support 2 bytes cmpxchg/xchg. Clearly this
won't scale well.
And as commented in swap_cgroup.c, this lock is not needed for map
synchronization.
Emulation of 2 bytes xchg with atomic cmpxchg isn't hard, so implement it
to get rid of this lock. Introduced two helpers for doing so and they can
be easily dropped if a generic 2 byte xchg is support.
Testing using 64G brd and build with build kernel with make -j96 in 1.5G
memory cgroup using 4k folios showed below improvement (10 test run):
Before this series:
Sys time: 10809.46 (stdev 80.831491)
Real time: 171.41 (stdev 1.239894)
After this commit:
Sys time: 9621.26 (stdev 34.620000), -10.42%
Real time: 160.00 (stdev 0.497814), -6.57%
With 64k folios and 2G memcg:
Before this series:
Sys time: 8231.99 (stdev 30.030994)
Real time: 143.57 (stdev 0.577394)
After this commit:
Sys time: 7403.47 (stdev 6.270000), -10.06%
Real time: 135.18 (stdev 0.605000), -5.84%
Sequential swapout of 8G 64k zero folios with madvise (24 test run):
Before this series:
5461409.12 us (stdev 183957.827084)
After this commit:
5420447.26 us (stdev 196419.240317)
Sequential swapin of 8G 4k zero folios (24 test run):
Before this series:
19736958.916667 us (stdev 189027.246676)
After this commit:
19662182.629630 us (stdev 172717.640614)
Performance is better or at least not worse for all tests above.
Link: https://lkml.kernel.org/r/20241210092805.87281-4-ryncsn@xxxxxxxxx
Signed-off-by: Kairui Song <kasong@xxxxxxxxxxx>
Cc: Barry Song <baohua@xxxxxxxxxx>
Cc: Chris Li <chrisl@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Roman Gushchin <roman.gushchin@xxxxxxxxx>
Cc: Shakeel Butt <shakeel.butt@xxxxxxxxx>
Cc: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/swap_cgroup.c | 73 +++++++++++++++++++++++++++------------------
1 file changed, 45 insertions(+), 28 deletions(-)
--- a/mm/swap_cgroup.c~mm-swap_cgroup-remove-global-swap-cgroup-lock
+++ a/mm/swap_cgroup.c
@@ -7,19 +7,20 @@
static DEFINE_MUTEX(swap_cgroup_mutex);
+/* Pack two cgroup id (short) of two entries in one swap_cgroup (atomic_t) */
+#define ID_PER_SC (sizeof(atomic_t) / sizeof(unsigned short))
+#define ID_SHIFT (BITS_PER_TYPE(unsigned short))
+#define ID_MASK (BIT(ID_SHIFT) - 1)
struct swap_cgroup {
- unsigned short id;
+ atomic_t ids;
};
struct swap_cgroup_ctrl {
struct swap_cgroup *map;
- spinlock_t lock;
};
static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
-#define SC_PER_PAGE (PAGE_SIZE/sizeof(struct swap_cgroup))
-
/*
* SwapCgroup implements "lookup" and "exchange" operations.
* In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge
@@ -30,19 +31,32 @@ static struct swap_cgroup_ctrl swap_cgro
* SwapCache(and its swp_entry) is under lock.
* - When called via swap_free(), there is no user of this entry and no race.
* Then, we don't need lock around "exchange".
- *
- * TODO: we can push these buffers out to HIGHMEM.
*/
-static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent,
- struct swap_cgroup_ctrl **ctrlp)
+static unsigned short __swap_cgroup_id_lookup(struct swap_cgroup *map,
+ pgoff_t offset)
{
- pgoff_t offset = swp_offset(ent);
- struct swap_cgroup_ctrl *ctrl;
+ unsigned int shift = (offset & 1) ? 0 : ID_SHIFT;
+ unsigned int old_ids = atomic_read(&map[offset / ID_PER_SC].ids);
- ctrl = &swap_cgroup_ctrl[swp_type(ent)];
- if (ctrlp)
- *ctrlp = ctrl;
- return &ctrl->map[offset];
+ return (old_ids & (ID_MASK << shift)) >> shift;
+}
+
+static unsigned short __swap_cgroup_id_xchg(struct swap_cgroup *map,
+ pgoff_t offset,
+ unsigned short new_id)
+{
+ unsigned short old_id;
+ unsigned int shift = (offset & 1) ? 0 : ID_SHIFT;
+ struct swap_cgroup *sc = &map[offset / ID_PER_SC];
+ unsigned int new_ids, old_ids = atomic_read(&sc->ids);
+
+ do {
+ old_id = (old_ids & (ID_MASK << shift)) >> shift;
+ new_ids = (old_ids & ~(ID_MASK << shift));
+ new_ids |= ((unsigned int)new_id) << shift;
+ } while (!atomic_try_cmpxchg(&sc->ids, &old_ids, new_ids));
+
+ return old_id;
}
/**
@@ -58,21 +72,19 @@ unsigned short swap_cgroup_record(swp_en
unsigned int nr_ents)
{
struct swap_cgroup_ctrl *ctrl;
- struct swap_cgroup *sc;
- unsigned short old;
- unsigned long flags;
pgoff_t offset = swp_offset(ent);
pgoff_t end = offset + nr_ents;
+ unsigned short old, iter;
+ struct swap_cgroup *map;
- sc = lookup_swap_cgroup(ent, &ctrl);
+ ctrl = &swap_cgroup_ctrl[swp_type(ent)];
+ map = ctrl->map;
- spin_lock_irqsave(&ctrl->lock, flags);
- old = sc->id;
- for (; offset < end; offset++, sc++) {
- VM_BUG_ON(sc->id != old);
- sc->id = id;
- }
- spin_unlock_irqrestore(&ctrl->lock, flags);
+ old = __swap_cgroup_id_lookup(map, offset);
+ do {
+ iter = __swap_cgroup_id_xchg(map, offset, id);
+ VM_BUG_ON(iter != old);
+ } while (++offset != end);
return old;
}
@@ -85,9 +97,13 @@ unsigned short swap_cgroup_record(swp_en
*/
unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
{
+ struct swap_cgroup_ctrl *ctrl;
+
if (mem_cgroup_disabled())
return 0;
- return lookup_swap_cgroup(ent, NULL)->id;
+
+ ctrl = &swap_cgroup_ctrl[swp_type(ent)];
+ return __swap_cgroup_id_lookup(ctrl->map, swp_offset(ent));
}
int swap_cgroup_swapon(int type, unsigned long max_pages)
@@ -98,14 +114,15 @@ int swap_cgroup_swapon(int type, unsigne
if (mem_cgroup_disabled())
return 0;
- map = vcalloc(max_pages, sizeof(struct swap_cgroup));
+ BUILD_BUG_ON(!ID_PER_SC);
+ map = vcalloc(DIV_ROUND_UP(max_pages, ID_PER_SC),
+ sizeof(struct swap_cgroup));
if (!map)
goto nomem;
ctrl = &swap_cgroup_ctrl[type];
mutex_lock(&swap_cgroup_mutex);
ctrl->map = map;
- spin_lock_init(&ctrl->lock);
mutex_unlock(&swap_cgroup_mutex);
return 0;
_
Patches currently in -mm which might be from kasong@xxxxxxxxxxx are
zram-refuse-to-use-zero-sized-block-device-as-backing-device.patch
zram-fix-uninitialized-zram-not-releasing-backing-device.patch
mm-memcontrol-avoid-duplicated-memcg-enable-check.patch
mm-swap_cgroup-remove-swap_cgroup_cmpxchg.patch
mm-swap_cgroup-remove-global-swap-cgroup-lock.patch
