From 1fb3d8c20bfadbbe2d9e5de18074de9282a52b5f Mon Sep 17 00:00:00 2001 From: Lance Yang Date: Tue, 24 Feb 2026 22:21:01 +0800 Subject: mm/mmu_gather: replace IPI with synchronize_rcu() when batch allocation fails When freeing page tables, we try to batch them. If batch allocation fails (GFP_NOWAIT), __tlb_remove_table_one() immediately frees the one without batching. On !CONFIG_PT_RECLAIM, the fallback sends an IPI to all CPUs via tlb_remove_table_sync_one(). It disrupts all CPUs even when only a single process is unmapping memory. IPI broadcast was reported to hurt RT workloads[1]. tlb_remove_table_sync_one() synchronizes with lockless page-table walkers (e.g. GUP-fast) that rely on IRQ disabling. These walkers use local_irq_disable(), which is also an RCU read-side critical section. This patch introduces tlb_remove_table_sync_rcu() which uses RCU grace period (synchronize_rcu()) instead of IPI broadcast. This provides the same guarantee as IPI but without disrupting all CPUs. Since batch allocation already failed, we are in a slow path where sleeping is acceptable - we are in process context (unmap_region, exit_mmap) with only mmap_lock held. tlb_remove_table_sync_one() is retained for other callers (e.g., khugepaged after pmdp_collapse_flush(), tlb_finish_mmu() when tlb->fully_unshared_tables) that are not slow paths. Converting those may require different approaches such as targeted IPIs. Link: https://lore.kernel.org/linux-mm/1b27a3fa-359a-43d0-bdeb-c31341749367@kernel.org/ [1] Link: https://lore.kernel.org/linux-mm/20260202150957.GD1282955@noisy.programming.kicks-ass.net/ Link: https://lore.kernel.org/linux-mm/dfdfeac9-5cd5-46fc-a5c1-9ccf9bd3502a@intel.com/ Link: https://lore.kernel.org/linux-mm/bc489455-bb18-44dc-8518-ae75abda6bec@kernel.org/ Link: https://lkml.kernel.org/r/20260224142101.20500-1-lance.yang@linux.dev Signed-off-by: Lance Yang Suggested-by: Peter Zijlstra (Intel) Suggested-by: Dave Hansen Suggested-by: David Hildenbrand (Arm) Acked-by: David Hildenbrand (Arm) Acked-by: Peter Zijlstra (Intel) Cc: Arnd Bergmann Cc: Nicholas Piggin Cc: Nick Piggin Cc: Will Deacon Signed-off-by: Andrew Morton --- include/asm-generic/tlb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/asm-generic') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 4aeac0c3d3f0..bdcc2778ac64 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -251,6 +251,8 @@ static inline void tlb_remove_table(struct mmu_gather *tlb, void *table) void tlb_remove_table_sync_one(void); +void tlb_remove_table_sync_rcu(void); + #else #ifdef tlb_needs_table_invalidate @@ -259,6 +261,8 @@ void tlb_remove_table_sync_one(void); static inline void tlb_remove_table_sync_one(void) { } +static inline void tlb_remove_table_sync_rcu(void) { } + #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ -- cgit