include/linux/mmzone.h | 1 + mm/page_alloc.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 47 insertions(+), 2 deletions(-)
Atomic allocations (GFP_ATOMIC) are prone to failure under heavy memory
pressure as they cannot enter direct reclaim. This patch introduces a
watermark boost mechanism to mitigate this issue.
When a GFP_ATOMIC request enters the slowpath, the preferred zone's
watermark_boost is increased under zone->lock protection. This triggers
kswapd to proactively reclaim memory, creating a safety buffer for
future atomic allocations. A 1-second debounce timer prevents excessive
boosts during traffic bursts.
This approach reuses existing watermark_boost infrastructure with
minimal overhead and proper locking to ensure thread safety.
Allocation failure logs:
[38535644.718700] node 0: slabs: 1031, objs: 43328, free: 0
[38535644.725059] node 1: slabs: 339, objs: 17616, free: 317
[38535645.428345] SLUB: Unable to allocate memory on node -1, gfp=0x480020(GFP_ATOMIC)
[38535645.436888] cache: skbuff_head_cache, object size: 232, buffer size: 256, default order: 2, min order: 0
[38535645.447664] node 0: slabs: 940, objs: 40864, free: 144
[38535645.454026] node 1: slabs: 322, objs: 19168, free: 383
[38535645.556122] SLUB: Unable to allocate memory on node -1, gfp=0x480020(GFP_ATOMIC)
[38535645.564576] cache: skbuff_head_cache, object size: 232, buffer size: 256, default order: 2, min order: 0
[38535649.655523] warn_alloc: 59 callbacks suppressed
[38535649.655527] swapper/100: page allocation failure: order:0, mode:0x480020(GFP_ATOMIC), nodemask=(null)
[38535649.671692] swapper/100 cpuset=/ mems_allowed=0-1
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202601271341.5d24a59f-lkp@intel.com
Signed-off-by: Qiliang Yuan <yuanql9@chinatelecom.cn>
Signed-off-by: Qiliang Yuan <realwujing@gmail.com>
---
v8:
- Use spin_lock_irqsave() to prevent inconsistent lock state (softirq-on
vs in-softirq) as reported by LKP.
v7:
- Use local variable for boost_amount to improve code readability
- Add zone->lock protection in boost_zones_for_atomic()
- Add lockdep assertion in boost_watermark() to prevent locking mistakes
- Remove redundant boost call at fail label due to 1-second debounce
- Link: https://lore.kernel.org/all/20260123064231.250767-1-realwujing@gmail.com/
v6:
- Replace magic number ">> 10" with ATOMIC_BOOST_SCALE_SHIFT define
- Add documentation explaining 0.1% zone size boost rationale
v5:
- Simplify to use native boost_watermark() instead of custom logic
v4:
- Add watermark_scale_boost and gradual decay via balance_pgdat
v3:
- Move debounce timer to per-zone; optimize zone selection
v2:
- Add debounce logic and zone-proportional boosting
v1:
- Initial: boost min_free_kbytes on GFP_ATOMIC failure
---
include/linux/mmzone.h | 1 +
mm/page_alloc.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++--
2 files changed, 47 insertions(+), 2 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 75ef7c9f9307..8e37e4e6765b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -882,6 +882,7 @@ struct zone {
/* zone watermarks, access with *_wmark_pages(zone) macros */
unsigned long _watermark[NR_WMARK];
unsigned long watermark_boost;
+ unsigned long last_boost_jiffies;
unsigned long nr_reserved_highatomic;
unsigned long nr_free_highatomic;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c380f063e8b7..7dc1e056a082 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -218,6 +218,13 @@ unsigned int pageblock_order __read_mostly;
static void __free_pages_ok(struct page *page, unsigned int order,
fpi_t fpi_flags);
+/*
+ * Boost watermarks by ~0.1% of zone size on atomic allocation pressure.
+ * This provides zone-proportional safety buffers: ~1MB per 1GB of zone size.
+ * Larger zones under GFP_ATOMIC pressure need proportionally larger reserves.
+ */
+#define ATOMIC_BOOST_SCALE_SHIFT 10
+
/*
* results with 256, 32 in the lowmem_reserve sysctl:
* 1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
@@ -2161,6 +2168,9 @@ bool pageblock_unisolate_and_move_free_pages(struct zone *zone, struct page *pag
static inline bool boost_watermark(struct zone *zone)
{
unsigned long max_boost;
+ unsigned long boost_amount;
+
+ lockdep_assert_held(&zone->lock);
if (!watermark_boost_factor)
return false;
@@ -2189,12 +2199,42 @@ static inline bool boost_watermark(struct zone *zone)
max_boost = max(pageblock_nr_pages, max_boost);
- zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages,
- max_boost);
+ boost_amount = max(pageblock_nr_pages,
+ zone_managed_pages(zone) >> ATOMIC_BOOST_SCALE_SHIFT);
+ zone->watermark_boost = min(zone->watermark_boost + boost_amount,
+ max_boost);
return true;
}
+static void boost_zones_for_atomic(struct alloc_context *ac, gfp_t gfp_mask)
+{
+ struct zoneref *z;
+ struct zone *zone;
+ unsigned long now = jiffies;
+ bool should_wake;
+
+ for_each_zone_zonelist(zone, z, ac->zonelist, ac->highest_zoneidx) {
+ /* Rate-limit boosts to once per second per zone */
+ if (time_after(now, zone->last_boost_jiffies + HZ)) {
+ unsigned long flags;
+
+ zone->last_boost_jiffies = now;
+
+ /* Modify watermark under lock, wake kswapd outside */
+ spin_lock_irqsave(&zone->lock, flags);
+ should_wake = boost_watermark(zone);
+ spin_unlock_irqrestore(&zone->lock, flags);
+
+ if (should_wake)
+ wakeup_kswapd(zone, gfp_mask, 0, ac->highest_zoneidx);
+
+ /* Boost only the preferred zone */
+ break;
+ }
+ }
+}
+
/*
* When we are falling back to another migratetype during allocation, should we
* try to claim an entire block to satisfy further allocations, instead of
@@ -4742,6 +4782,10 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
if (page)
goto got_pg;
+ /* Boost watermarks for atomic requests entering slowpath */
+ if ((gfp_mask & GFP_ATOMIC) && order == 0)
+ boost_zones_for_atomic(ac, gfp_mask);
+
/*
* For costly allocations, try direct compaction first, as it's likely
* that we have enough base pages and don't need to reclaim. For non-
---
base-commit: b54345928fa1dbde534e32ecaa138678fd5d2135
change-id: 20260206-wujing-mm-page_alloc-v8-fb1979bac6fe
Best regards,
--
Qiliang Yuan <realwujing@gmail.com>On Thu, 12 Feb 2026 15:27:41 +0800 Qiliang Yuan <realwujing@gmail.com> wrote:
> Atomic allocations (GFP_ATOMIC) are prone to failure under heavy memory
> pressure as they cannot enter direct reclaim. This patch introduces a
> watermark boost mechanism to mitigate this issue.
>
> When a GFP_ATOMIC request enters the slowpath, the preferred zone's
> watermark_boost is increased under zone->lock protection. This triggers
> kswapd to proactively reclaim memory, creating a safety buffer for
> future atomic allocations. A 1-second debounce timer prevents excessive
> boosts during traffic bursts.
>
> This approach reuses existing watermark_boost infrastructure with
> minimal overhead and proper locking to ensure thread safety.
>
> Allocation failure logs:
> [38535644.718700] node 0: slabs: 1031, objs: 43328, free: 0
> [38535644.725059] node 1: slabs: 339, objs: 17616, free: 317
> [38535645.428345] SLUB: Unable to allocate memory on node -1, gfp=0x480020(GFP_ATOMIC)
> [38535645.436888] cache: skbuff_head_cache, object size: 232, buffer size: 256, default order: 2, min order: 0
> [38535645.447664] node 0: slabs: 940, objs: 40864, free: 144
> [38535645.454026] node 1: slabs: 322, objs: 19168, free: 383
> [38535645.556122] SLUB: Unable to allocate memory on node -1, gfp=0x480020(GFP_ATOMIC)
> [38535645.564576] cache: skbuff_head_cache, object size: 232, buffer size: 256, default order: 2, min order: 0
> [38535649.655523] warn_alloc: 59 callbacks suppressed
> [38535649.655527] swapper/100: page allocation failure: order:0, mode:0x480020(GFP_ATOMIC), nodemask=(null)
> [38535649.671692] swapper/100 cpuset=/ mems_allowed=0-1
>
> Reported-by: kernel test robot <oliver.sang@intel.com>
I was surprised the robot can find this kind of issue, too.
> Closes: https://lore.kernel.org/oe-lkp/202601271341.5d24a59f-lkp@intel.com
But seems the report was inconsistent_lock_state warning on the previous
revision of this patch.
The report was saying
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <oliver.sang@intel.com>
| Closes: https://lore.kernel.org/oe-lkp/202601271341.5d24a59f-lkp@intel.com
And this is a new version of the reported patch, so I don't think the above two
tags are needed here.
> Signed-off-by: Qiliang Yuan <yuanql9@chinatelecom.cn>
> Signed-off-by: Qiliang Yuan <realwujing@gmail.com>
Having two signed-off-by tags for single person looks weird to me.
> ---
> v8:
> - Use spin_lock_irqsave() to prevent inconsistent lock state (softirq-on
> vs in-softirq) as reported by LKP.
> v7:
> - Use local variable for boost_amount to improve code readability
> - Add zone->lock protection in boost_zones_for_atomic()
> - Add lockdep assertion in boost_watermark() to prevent locking mistakes
> - Remove redundant boost call at fail label due to 1-second debounce
> - Link: https://lore.kernel.org/all/20260123064231.250767-1-realwujing@gmail.com/
> v6:
> - Replace magic number ">> 10" with ATOMIC_BOOST_SCALE_SHIFT define
> - Add documentation explaining 0.1% zone size boost rationale
> v5:
> - Simplify to use native boost_watermark() instead of custom logic
> v4:
> - Add watermark_scale_boost and gradual decay via balance_pgdat
> v3:
> - Move debounce timer to per-zone; optimize zone selection
> v2:
> - Add debounce logic and zone-proportional boosting
> v1:
> - Initial: boost min_free_kbytes on GFP_ATOMIC failure
> ---
> include/linux/mmzone.h | 1 +
> mm/page_alloc.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++--
> 2 files changed, 47 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 75ef7c9f9307..8e37e4e6765b 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -882,6 +882,7 @@ struct zone {
> /* zone watermarks, access with *_wmark_pages(zone) macros */
> unsigned long _watermark[NR_WMARK];
> unsigned long watermark_boost;
> + unsigned long last_boost_jiffies;
>
> unsigned long nr_reserved_highatomic;
> unsigned long nr_free_highatomic;
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index c380f063e8b7..7dc1e056a082 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -218,6 +218,13 @@ unsigned int pageblock_order __read_mostly;
> static void __free_pages_ok(struct page *page, unsigned int order,
> fpi_t fpi_flags);
>
> +/*
> + * Boost watermarks by ~0.1% of zone size on atomic allocation pressure.
> + * This provides zone-proportional safety buffers: ~1MB per 1GB of zone size.
> + * Larger zones under GFP_ATOMIC pressure need proportionally larger reserves.
> + */
> +#define ATOMIC_BOOST_SCALE_SHIFT 10
Why don't you use '_FACOTR' as the suffix of the namethis a factor, and use
mult_frac() for calculation, consistent to others like watermark_boost_factor?
> +
> /*
> * results with 256, 32 in the lowmem_reserve sysctl:
> * 1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
> @@ -2161,6 +2168,9 @@ bool pageblock_unisolate_and_move_free_pages(struct zone *zone, struct page *pag
> static inline bool boost_watermark(struct zone *zone)
> {
> unsigned long max_boost;
> + unsigned long boost_amount;
> +
> + lockdep_assert_held(&zone->lock);
>
> if (!watermark_boost_factor)
> return false;
> @@ -2189,12 +2199,42 @@ static inline bool boost_watermark(struct zone *zone)
>
> max_boost = max(pageblock_nr_pages, max_boost);
>
> - zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages,
> - max_boost);
> + boost_amount = max(pageblock_nr_pages,
> + zone_managed_pages(zone) >> ATOMIC_BOOST_SCALE_SHIFT);
> + zone->watermark_boost = min(zone->watermark_boost + boost_amount,
> + max_boost);
>
> return true;
> }
>
> +static void boost_zones_for_atomic(struct alloc_context *ac, gfp_t gfp_mask)
> +{
> + struct zoneref *z;
> + struct zone *zone;
> + unsigned long now = jiffies;
> + bool should_wake;
> +
> + for_each_zone_zonelist(zone, z, ac->zonelist, ac->highest_zoneidx) {
> + /* Rate-limit boosts to once per second per zone */
> + if (time_after(now, zone->last_boost_jiffies + HZ)) {
> + unsigned long flags;
Why don't you define 'should_wake' here together?
> +
> + zone->last_boost_jiffies = now;
> +
> + /* Modify watermark under lock, wake kswapd outside */
> + spin_lock_irqsave(&zone->lock, flags);
> + should_wake = boost_watermark(zone);
> + spin_unlock_irqrestore(&zone->lock, flags);
> +
> + if (should_wake)
> + wakeup_kswapd(zone, gfp_mask, 0, ac->highest_zoneidx);
Why don't you wrap the line for the 80 columns limit?
> +
> + /* Boost only the preferred zone */
> + break;
So, this function boosts only one zone per call? How about renaming the
function to use a singular noun? That is, s/zones/zone/ ?
> + }
> + }
> +}
> +
> /*
> * When we are falling back to another migratetype during allocation, should we
> * try to claim an entire block to satisfy further allocations, instead of
> @@ -4742,6 +4782,10 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
> if (page)
> goto got_pg;
>
> + /* Boost watermarks for atomic requests entering slowpath */
> + if ((gfp_mask & GFP_ATOMIC) && order == 0)
> + boost_zones_for_atomic(ac, gfp_mask);
> +
> /*
> * For costly allocations, try direct compaction first, as it's likely
> * that we have enough base pages and don't need to reclaim. For non-
>
> ---
> base-commit: b54345928fa1dbde534e32ecaa138678fd5d2135
> change-id: 20260206-wujing-mm-page_alloc-v8-fb1979bac6fe
>
> Best regards,
> --
> Qiliang Yuan <realwujing@gmail.com>
Thanks,
SJ
On 2/12/26 08:27, Qiliang Yuan wrote:
> Atomic allocations (GFP_ATOMIC) are prone to failure under heavy memory
> pressure as they cannot enter direct reclaim. This patch introduces a
> watermark boost mechanism to mitigate this issue.
>
> When a GFP_ATOMIC request enters the slowpath, the preferred zone's
> watermark_boost is increased under zone->lock protection. This triggers
> kswapd to proactively reclaim memory, creating a safety buffer for
> future atomic allocations. A 1-second debounce timer prevents excessive
> boosts during traffic bursts.
>
> This approach reuses existing watermark_boost infrastructure with
> minimal overhead and proper locking to ensure thread safety.
>
> Allocation failure logs:
> [38535644.718700] node 0: slabs: 1031, objs: 43328, free: 0
> [38535644.725059] node 1: slabs: 339, objs: 17616, free: 317
> [38535645.428345] SLUB: Unable to allocate memory on node -1, gfp=0x480020(GFP_ATOMIC)
> [38535645.436888] cache: skbuff_head_cache, object size: 232, buffer size: 256, default order: 2, min order: 0
> [38535645.447664] node 0: slabs: 940, objs: 40864, free: 144
> [38535645.454026] node 1: slabs: 322, objs: 19168, free: 383
> [38535645.556122] SLUB: Unable to allocate memory on node -1, gfp=0x480020(GFP_ATOMIC)
> [38535645.564576] cache: skbuff_head_cache, object size: 232, buffer size: 256, default order: 2, min order: 0
> [38535649.655523] warn_alloc: 59 callbacks suppressed
> [38535649.655527] swapper/100: page allocation failure: order:0, mode:0x480020(GFP_ATOMIC), nodemask=(null)
> [38535649.671692] swapper/100 cpuset=/ mems_allowed=0-1
>
> Reported-by: kernel test robot <oliver.sang@intel.com>
> Closes: https://lore.kernel.org/oe-lkp/202601271341.5d24a59f-lkp@intel.com
> Signed-off-by: Qiliang Yuan <yuanql9@chinatelecom.cn>
> Signed-off-by: Qiliang Yuan <realwujing@gmail.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Nit:
> ---
> v8:
> - Use spin_lock_irqsave() to prevent inconsistent lock state (softirq-on
> vs in-softirq) as reported by LKP.
> v7:
> - Use local variable for boost_amount to improve code readability
> - Add zone->lock protection in boost_zones_for_atomic()
> - Add lockdep assertion in boost_watermark() to prevent locking mistakes
> - Remove redundant boost call at fail label due to 1-second debounce
> - Link: https://lore.kernel.org/all/20260123064231.250767-1-realwujing@gmail.com/
> v6:
> - Replace magic number ">> 10" with ATOMIC_BOOST_SCALE_SHIFT define
> - Add documentation explaining 0.1% zone size boost rationale
> v5:
> - Simplify to use native boost_watermark() instead of custom logic
> v4:
> - Add watermark_scale_boost and gradual decay via balance_pgdat
> v3:
> - Move debounce timer to per-zone; optimize zone selection
> v2:
> - Add debounce logic and zone-proportional boosting
> v1:
> - Initial: boost min_free_kbytes on GFP_ATOMIC failure
> ---
> include/linux/mmzone.h | 1 +
> mm/page_alloc.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++--
> 2 files changed, 47 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 75ef7c9f9307..8e37e4e6765b 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -882,6 +882,7 @@ struct zone {
> /* zone watermarks, access with *_wmark_pages(zone) macros */
> unsigned long _watermark[NR_WMARK];
> unsigned long watermark_boost;
> + unsigned long last_boost_jiffies;
>
> unsigned long nr_reserved_highatomic;
> unsigned long nr_free_highatomic;
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index c380f063e8b7..7dc1e056a082 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -218,6 +218,13 @@ unsigned int pageblock_order __read_mostly;
> static void __free_pages_ok(struct page *page, unsigned int order,
> fpi_t fpi_flags);
>
> +/*
> + * Boost watermarks by ~0.1% of zone size on atomic allocation pressure.
> + * This provides zone-proportional safety buffers: ~1MB per 1GB of zone size.
> + * Larger zones under GFP_ATOMIC pressure need proportionally larger reserves.
> + */
> +#define ATOMIC_BOOST_SCALE_SHIFT 10
> +
> /*
> * results with 256, 32 in the lowmem_reserve sysctl:
> * 1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
> @@ -2161,6 +2168,9 @@ bool pageblock_unisolate_and_move_free_pages(struct zone *zone, struct page *pag
> static inline bool boost_watermark(struct zone *zone)
> {
> unsigned long max_boost;
> + unsigned long boost_amount;
> +
> + lockdep_assert_held(&zone->lock);
>
> if (!watermark_boost_factor)
> return false;
> @@ -2189,12 +2199,42 @@ static inline bool boost_watermark(struct zone *zone)
>
> max_boost = max(pageblock_nr_pages, max_boost);
>
> - zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages,
> - max_boost);
> + boost_amount = max(pageblock_nr_pages,
> + zone_managed_pages(zone) >> ATOMIC_BOOST_SCALE_SHIFT);
> + zone->watermark_boost = min(zone->watermark_boost + boost_amount,
> + max_boost);
>
> return true;
> }
>
> +static void boost_zones_for_atomic(struct alloc_context *ac, gfp_t gfp_mask)
> +{
> + struct zoneref *z;
> + struct zone *zone;
> + unsigned long now = jiffies;
> + bool should_wake;
> +
> + for_each_zone_zonelist(zone, z, ac->zonelist, ac->highest_zoneidx) {
> + /* Rate-limit boosts to once per second per zone */
> + if (time_after(now, zone->last_boost_jiffies + HZ)) {
> + unsigned long flags;
> +
> + zone->last_boost_jiffies = now;
> +
> + /* Modify watermark under lock, wake kswapd outside */
> + spin_lock_irqsave(&zone->lock, flags);
> + should_wake = boost_watermark(zone);
> + spin_unlock_irqrestore(&zone->lock, flags);
> +
> + if (should_wake)
> + wakeup_kswapd(zone, gfp_mask, 0, ac->highest_zoneidx);
> +
> + /* Boost only the preferred zone */
> + break;
> + }
> + }
> +}
> +
> /*
> * When we are falling back to another migratetype during allocation, should we
> * try to claim an entire block to satisfy further allocations, instead of
> @@ -4742,6 +4782,10 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
> if (page)
> goto got_pg;
>
> + /* Boost watermarks for atomic requests entering slowpath */
> + if ((gfp_mask & GFP_ATOMIC) && order == 0)
I'd also test && !can_direct_reclaim, we don't want to boost for allocations
that can reclaim and yet specify __GFP_HIGH.
> + boost_zones_for_atomic(ac, gfp_mask);
> +
> /*
> * For costly allocations, try direct compaction first, as it's likely
> * that we have enough base pages and don't need to reclaim. For non-
>
> ---
> base-commit: b54345928fa1dbde534e32ecaa138678fd5d2135
> change-id: 20260206-wujing-mm-page_alloc-v8-fb1979bac6fe
>
> Best regards,
© 2016 - 2026 Red Hat, Inc.