[PATCH mm-hotfixes] mm/page_alloc: prevent pcp corruption with SMP=n

[Vlastimil Babka <vbabka@suse.cz>]

The kernel test robot has reported:

 BUG: spinlock trylock failure on UP on CPU#0, kcompactd0/28
  lock: 0xffff888807e35ef0, .magic: dead4ead, .owner: kcompactd0/28, .owner_cpu: 0
 CPU: 0 UID: 0 PID: 28 Comm: kcompactd0 Not tainted 6.18.0-rc5-00127-ga06157804399 #1 PREEMPT  8cc09ef94dcec767faa911515ce9e609c45db470
 Call Trace:
  <IRQ>
  __dump_stack (lib/dump_stack.c:95)
  dump_stack_lvl (lib/dump_stack.c:123)
  dump_stack (lib/dump_stack.c:130)
  spin_dump (kernel/locking/spinlock_debug.c:71)
  do_raw_spin_trylock (kernel/locking/spinlock_debug.c:?)
  _raw_spin_trylock (include/linux/spinlock_api_smp.h:89 kernel/locking/spinlock.c:138)
  __free_frozen_pages (mm/page_alloc.c:2973)
  ___free_pages (mm/page_alloc.c:5295)
  __free_pages (mm/page_alloc.c:5334)
  tlb_remove_table_rcu (include/linux/mm.h:? include/linux/mm.h:3122 include/asm-generic/tlb.h:220 mm/mmu_gather.c:227 mm/mmu_gather.c:290)
  ? __cfi_tlb_remove_table_rcu (mm/mmu_gather.c:289)
  ? rcu_core (kernel/rcu/tree.c:?)
  rcu_core (include/linux/rcupdate.h:341 kernel/rcu/tree.c:2607 kernel/rcu/tree.c:2861)
  rcu_core_si (kernel/rcu/tree.c:2879)
  handle_softirqs (arch/x86/include/asm/jump_label.h:36 include/trace/events/irq.h:142 kernel/softirq.c:623)
  __irq_exit_rcu (arch/x86/include/asm/jump_label.h:36 kernel/softirq.c:725)
  irq_exit_rcu (kernel/softirq.c:741)
  sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1052)
  </IRQ>
  <TASK>
 RIP: 0010:_raw_spin_unlock_irqrestore (arch/x86/include/asm/preempt.h:95 include/linux/spinlock_api_smp.h:152 kernel/locking/spinlock.c:194)
  free_pcppages_bulk (mm/page_alloc.c:1494)
  drain_pages_zone (include/linux/spinlock.h:391 mm/page_alloc.c:2632)
  __drain_all_pages (mm/page_alloc.c:2731)
  drain_all_pages (mm/page_alloc.c:2747)
  kcompactd (mm/compaction.c:3115)
  kthread (kernel/kthread.c:465)
  ? __cfi_kcompactd (mm/compaction.c:3166)
  ? __cfi_kthread (kernel/kthread.c:412)
  ret_from_fork (arch/x86/kernel/process.c:164)
  ? __cfi_kthread (kernel/kthread.c:412)
  ret_from_fork_asm (arch/x86/entry/entry_64.S:255)
  </TASK>

Matthew has analyzed the report and identified that in drain_page_zone()
we are in a section protected by spin_lock(&pcp->lock) and then get an
interrupt that attempts spin_trylock() on the same lock. The code is
designed to work this way without disabling IRQs and occasionally fail
the trylock with a fallback. However, the SMP=n spinlock implementation
assumes spin_trylock() will always succeed, and thus it's normally a
no-op. Here the enabled lock debugging catches the problem, but
otherwise it could cause a corruption of the pcp structure.

The problem has been introduced by commit 574907741599 ("mm/page_alloc:
leave IRQs enabled for per-cpu page allocations"). The pcp locking
scheme recognizes the need for disabling IRQs to prevent nesting
spin_trylock() sections on SMP=n, but the need to prevent the nesting in
spin_lock() has not been recognized. Fix it by introducing local
wrappers that change the spin_lock() to spin_lock_iqsave() with SMP=n
and use them in all places that do spin_lock(&pcp->lock).

Fixes: 574907741599 ("mm/page_alloc: leave IRQs enabled for per-cpu page allocations")
Cc: stable@vger.kernel.org
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202512101320.e2f2dd6f-lkp@intel.com
Analyzed-by: Matthew Wilcox <willy@infradead.org>
Link: https://lore.kernel.org/all/aUW05pyc9nZkvY-1@casper.infradead.org/
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
This fix is intentionally made self-contained and not trying to expand
upon the existing pcp[u]_spin() helpers. This is to make stable
backports easier due to recent cleanups to that helpers.

We could follow up with a proper helpers integration going forward.
However I think the assumptions SMP=n of the spinlock UP implementation
are just wrong. It should be valid to do a spin_lock() without disabling
irq's and rely on a nested spin_trylock() to fail. I will thus try
proposing the remove the UP implementation first. It should be within
the current trend of removing stuff that's optimized for a minority
configuration if it makes maintainability of the majority worse.
(c.f. recent scheduler SMP=n removal)
---
 mm/page_alloc.c | 45 +++++++++++++++++++++++++++++++++++++--------
 1 file changed, 37 insertions(+), 8 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 822e05f1a964..ec3551d56cde 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -167,6 +167,31 @@ static inline void __pcp_trylock_noop(unsigned long *flags) { }
 	pcp_trylock_finish(UP_flags);					\
 })
 
+/*
+ * With the UP spinlock implementation, when we spin_lock(&pcp->lock) (for i.e.
+ * a potentially remote cpu drain) and get interrupted by an operation that
+ * attempts pcp_spin_trylock(), we can't rely on the trylock failure due to UP
+ * spinlock assumptions making the trylock a no-op. So we have to turn that
+ * spin_lock() to a spin_lock_irqsave(). This works because on UP there are no
+ * remote cpu's so we can only be locking the only existing local one.
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
+static inline void __flags_noop(unsigned long *flags) { }
+#define spin_lock_maybe_irqsave(lock, flags)		\
+({							\
+	 __flags_noop(&(flags));			\
+	 spin_lock(lock);				\
+})
+#define spin_unlock_maybe_irqrestore(lock, flags)	\
+({							\
+	 spin_unlock(lock);				\
+	 __flags_noop(&(flags));			\
+})
+#else
+#define spin_lock_maybe_irqsave(lock, flags)		spin_lock_irqsave(lock, flags)
+#define spin_unlock_maybe_irqrestore(lock, flags)	spin_unlock_irqrestore(lock, flags)
+#endif
+
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DEFINE_PER_CPU(int, numa_node);
 EXPORT_PER_CPU_SYMBOL(numa_node);
@@ -2556,6 +2581,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp)
 {
 	int high_min, to_drain, to_drain_batched, batch;
+	unsigned long UP_flags;
 	bool todo = false;
 
 	high_min = READ_ONCE(pcp->high_min);
@@ -2575,9 +2601,9 @@ bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp)
 	to_drain = pcp->count - pcp->high;
 	while (to_drain > 0) {
 		to_drain_batched = min(to_drain, batch);
-		spin_lock(&pcp->lock);
+		spin_lock_maybe_irqsave(&pcp->lock, UP_flags);
 		free_pcppages_bulk(zone, to_drain_batched, pcp, 0);
-		spin_unlock(&pcp->lock);
+		spin_unlock_maybe_irqrestore(&pcp->lock, UP_flags);
 		todo = true;
 
 		to_drain -= to_drain_batched;
@@ -2594,14 +2620,15 @@ bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp)
  */
 void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 {
+	unsigned long UP_flags;
 	int to_drain, batch;
 
 	batch = READ_ONCE(pcp->batch);
 	to_drain = min(pcp->count, batch);
 	if (to_drain > 0) {
-		spin_lock(&pcp->lock);
+		spin_lock_maybe_irqsave(&pcp->lock, UP_flags);
 		free_pcppages_bulk(zone, to_drain, pcp, 0);
-		spin_unlock(&pcp->lock);
+		spin_unlock_maybe_irqrestore(&pcp->lock, UP_flags);
 	}
 }
 #endif
@@ -2612,10 +2639,11 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 static void drain_pages_zone(unsigned int cpu, struct zone *zone)
 {
 	struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
+	unsigned long UP_flags;
 	int count;
 
 	do {
-		spin_lock(&pcp->lock);
+		spin_lock_maybe_irqsave(&pcp->lock, UP_flags);
 		count = pcp->count;
 		if (count) {
 			int to_drain = min(count,
@@ -2624,7 +2652,7 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone)
 			free_pcppages_bulk(zone, to_drain, pcp, 0);
 			count -= to_drain;
 		}
-		spin_unlock(&pcp->lock);
+		spin_unlock_maybe_irqrestore(&pcp->lock, UP_flags);
 	} while (count);
 }
 
@@ -6109,6 +6137,7 @@ static void zone_pcp_update_cacheinfo(struct zone *zone, unsigned int cpu)
 {
 	struct per_cpu_pages *pcp;
 	struct cpu_cacheinfo *cci;
+	unsigned long UP_flags;
 
 	pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
 	cci = get_cpu_cacheinfo(cpu);
@@ -6119,12 +6148,12 @@ static void zone_pcp_update_cacheinfo(struct zone *zone, unsigned int cpu)
 	 * This can reduce zone lock contention without hurting
 	 * cache-hot pages sharing.
 	 */
-	spin_lock(&pcp->lock);
+	spin_lock_maybe_irqsave(&pcp->lock, UP_flags);
 	if ((cci->per_cpu_data_slice_size >> PAGE_SHIFT) > 3 * pcp->batch)
 		pcp->flags |= PCPF_FREE_HIGH_BATCH;
 	else
 		pcp->flags &= ~PCPF_FREE_HIGH_BATCH;
-	spin_unlock(&pcp->lock);
+	spin_unlock_maybe_irqrestore(&pcp->lock, UP_flags);
 }
 
 void setup_pcp_cacheinfo(unsigned int cpu)

---
base-commit: 8f0b4cce4481fb22653697cced8d0d04027cb1e8
change-id: 20260105-fix-pcp-up-3c88c09752ec

Best regards,
-- 
Vlastimil Babka <vbabka@suse.cz>