mm/page_alloc: prevent pcp corruption with SMP=n

[ Upstream commit 038a102535eb49e10e93eafac54352fcc5d78847 ]

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).

[vbabka@suse.cz: add pcp_ prefix to the spin_lock_irqsave wrappers, per Steven]
Link: https://lkml.kernel.org/r/20260105-fix-pcp-up-v1-1-5579662d2071@suse.cz
Fixes: 574907741599 ("mm/page_alloc: leave IRQs enabled for per-cpu page allocations")
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
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/
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
[ drop changes to decay_pcp_high() and zone_pcp_update_cacheinfo() ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d418752ac4e0f0065c8f3f13ae27ecb3ff05b8ad..6c042f7796e48b53ea9e4b5c1c47529df8378d1f 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -160,6 +160,33 @@ static DEFINE_MUTEX(pcp_batch_high_lock);
 #define pcp_spin_unlock(ptr)                                           \
        pcpu_spin_unlock(lock, ptr)
 
+/*
+ * 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 pcp_spin_lock_maybe_irqsave(ptr, flags)                \
+({                                                     \
+        __flags_noop(&(flags));                        \
+        spin_lock(&(ptr)->lock);                       \
+})
+#define pcp_spin_unlock_maybe_irqrestore(ptr, flags)   \
+({                                                     \
+        spin_unlock(&(ptr)->lock);                     \
+        __flags_noop(&(flags));                        \
+})
+#else
+#define pcp_spin_lock_maybe_irqsave(ptr, flags)                \
+               spin_lock_irqsave(&(ptr)->lock, flags)
+#define pcp_spin_unlock_maybe_irqrestore(ptr, flags)   \
+               spin_unlock_irqrestore(&(ptr)->lock, flags)
+#endif
+
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DEFINE_PER_CPU(int, numa_node);
 EXPORT_PER_CPU_SYMBOL(numa_node);
@@ -2181,14 +2208,15 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
  */
 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);
+               pcp_spin_lock_maybe_irqsave(pcp, UP_flags);
                free_pcppages_bulk(zone, to_drain, pcp, 0);
-               spin_unlock(&pcp->lock);
+               pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags);
        }
 }
 #endif
@@ -2199,10 +2227,11 @@ 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);
+               pcp_spin_lock_maybe_irqsave(pcp, UP_flags);
                count = pcp->count;
                if (count) {
                        int to_drain = min(count,
@@ -2211,7 +2240,7 @@ 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);
+               pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags);
        } while (count);
 }