From 35e340a47888e3574ee4e8ef7da3f73a32034e58 Mon Sep 17 00:00:00 2001 From: "Lorenzo Stoakes (ARM)" Date: Fri, 25 Sep 2026 21:09:46 +0100 Subject: mm: userland pgtable freeing is RCU-safe now, remove leftover bits Now every architecture has been converted to support CONFIG_MMU_GATHER_RCU_TABLE_FREE, this configuration option no longer makes any sense to keep around. Therefore remove it, and remove all the dead code that existed for !CONFIG_MMU_GATHER_RCU_TABLE_FREE architectures previously. Additionally, CONFIG_MMU_GATHER_TABLE_FREE is no longer necessary, as all architectures instead use CONFIG_HAVE_ARCH_TLB_REMOVE_TABLE when a custom __tlb_remove_table() is required, so remove this too. A number of architectures only enabled CONFIG_MMU_GATHER_RCU_TABLE_FREE if CONFIG_MMU was set, however the mmu_gather logic only actually does something meaningful if CONFIG_MMU is set (mmu_gather.c is only compiled in this case, for instance). As a result, there's no need to gate any of this logic on CONFIG_MMU explicitly. CONFIG_PT_RECLAIM however does have a strict dependency on CONFIG_MMU, so make this dependency explicit. Additionally, correct comments to remove references to non-RCU page table gathering and make it clear that this is not 'semi-RCU', nor has it been since commit 1fb3d8c20bfa ("mm/mmu_gather: replace IPI with synchronize_rcu() when batch allocation fails"). With this change in place the kernel policy is now that userspace page tables are freed after an RCU grace period, and thus it is now safe to unconditionally perform page table walks under RCU, safe in the knowledge that page tables will not be freed underneath the walker. This is all that is guaranteed, however, so naturally it is still incumbent upon page table walkers to ensure that the page table entries are as expected. Link: https://lore.kernel.org/20260925-rcu-pagetable-freeing-v5-11-31e91065fea4@kernel.org Signed-off-by: Lorenzo Stoakes (ARM) Signed-off-by: Andrew Morton Acked-by: Kiryl Shutsemau (Meta) Reviewed-by: Lance Yang Acked-by: David Hildenbrand (Arm) Cc: Zi Yan Cc: Baolin Wang Cc: Liam R. Howlett Cc: Nico Pache Cc: Ryan Roberts Cc: Dev Jain Cc: Barry Song Cc: Usama Arif Cc: Guo Ren Cc: Brian Cain Cc: Geert Uytterhoeven Cc: Dinh Nguyen Cc: Simon Schuster Cc: Jonas Bonn Cc: Stefan Kristiansson Cc: Stafford Horne Cc: Rich Felker Cc: John Paul Adrian Glaubitz Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Alexandre Ghiti Cc: Russell King Cc: Vineet Gupta Cc: Michal Simek Cc: Chris Zankel Cc: Max Filippov Cc: Will Deacon Cc: Aneesh Kumar K.V Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: David S. Miller Cc: Andreas Larsson Cc: Richard Henderson Cc: Matt Turner Cc: Magnus Lindholm Cc: Catalin Marinas Cc: Mark Rutland Cc: Huacai Chen Cc: WANG Xuerui Cc: Thomas Bogendoerfer Cc: James Bottomley Cc: Helge Deller Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Christophe Leroy Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Sven Schnelle Cc: Richard Weinberger Cc: Anton Ivanov Cc: Johannes Berg Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Arnd Bergmann Cc: Vlastimil Babka Cc: Mike Rapoport Cc: Suren Baghdasaryan Cc: Michal Hocko Cc: Jason Gunthorpe Cc: John Hubbard Cc: Peter Xu Cc: Yoshinori Sato Cc: Shakeel Butt Cc: Jonathan Corbet Cc: Randy Dunlap Cc: Hugh Dickins Cc: Qi Zheng --- include/asm-generic/tlb.h | 66 +++++++---------------------------------------- 1 file changed, 9 insertions(+), 57 deletions(-) (limited to 'include') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index bdcc2778ac64..9d827076db19 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -67,11 +67,8 @@ * - tlb_remove_table() * * tlb_remove_table() is the basic primitive to free page-table directories - * (__p*_free_tlb()). In it's most primitive form it is an alias for - * tlb_remove_page() below, for when page directories are pages and have no - * additional constraints. - * - * See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE. + * (__p*_free_tlb()). Page directories are freed after an RCU grace + * period - see the comment in mm/mmu_gather.c. * * - tlb_remove_page() / tlb_remove_page_size() * - __tlb_remove_folio_pages() / __tlb_remove_page_size() @@ -151,24 +148,15 @@ * This might be useful if your architecture has size specific TLB * invalidation instructions. * - * MMU_GATHER_TABLE_FREE - * - * This provides tlb_remove_table(), to be used instead of tlb_remove_page() - * for page directores (__p*_free_tlb()). - * - * Useful if your architecture has non-page page directories. + * Page directories (__p*_free_tlb()) are always freed via tlb_remove_table(), + * after an RCU grace period (see mm/mmu_gather.c). * - * When used, an architecture is expected to provide __tlb_remove_table() or - * use the generic __tlb_remove_table(), which does the actual freeing of these - * pages. + * This serialises against software page-table walkers, including architectures + * which do not use IPIs for remote TLB invalidates. * - * MMU_GATHER_RCU_TABLE_FREE - * - * Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see - * comment below). - * - * Useful if your architecture doesn't use IPIs for remote TLB invalidates - * and therefore doesn't naturally serialize with software page-table walkers. + * An architecture is expected to provide __tlb_remove_table() (see + * HAVE_ARCH_TLB_REMOVE_TABLE) or use the generic __tlb_remove_table(), which + * does the actual freeing of these pages. * * MMU_GATHER_NO_FLUSH_CACHE * @@ -200,12 +188,8 @@ * various ptep_get_and_clear() functions. */ -#ifdef CONFIG_MMU_GATHER_TABLE_FREE - struct mmu_table_batch { -#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE struct rcu_head rcu; -#endif unsigned int nr; void *tables[]; }; @@ -224,23 +208,6 @@ static inline void __tlb_remove_table(void *table) extern void tlb_remove_table(struct mmu_gather *tlb, void *table); -#else /* !CONFIG_MMU_GATHER_TABLE_FREE */ - -static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page); -/* - * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based - * page directories and we can use the normal page batching to free them. - */ -static inline void tlb_remove_table(struct mmu_gather *tlb, void *table) -{ - struct ptdesc *ptdesc = (struct ptdesc *)table; - - pagetable_dtor(ptdesc); - tlb_remove_page(tlb, ptdesc_page(ptdesc)); -} -#endif /* CONFIG_MMU_GATHER_TABLE_FREE */ - -#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE /* * This allows an architecture that does not use the linux page-tables for * hardware to skip the TLBI when freeing page tables. @@ -253,19 +220,6 @@ void tlb_remove_table_sync_one(void); void tlb_remove_table_sync_rcu(void); -#else - -#ifdef tlb_needs_table_invalidate -#error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE -#endif - -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 */ - - #ifndef CONFIG_MMU_GATHER_NO_GATHER /* * If we can't allocate a page to make a big batch of page pointers @@ -325,9 +279,7 @@ static inline void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct struct mmu_gather { struct mm_struct *mm; -#ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch *batch; -#endif unsigned long start; unsigned long end; -- cgit v1.2.3