diff --git a/include/linux/mm.h b/include/linux/mm.h index 2e5ef71b8629..9372bc058b43 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2320,6 +2320,7 @@ extern void pagefault_out_of_memory(void); struct zap_details { struct folio *single_folio; /* Locked folio to be unmapped */ bool even_cows; /* Zap COWed private pages too? */ + bool reclaim_pt; /* Need reclaim page tables? */ zap_flags_t zap_flags; /* Extra flags for zapping */ }; diff --git a/mm/Kconfig b/mm/Kconfig index 84000b016808..7949ab121070 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1301,6 +1301,21 @@ config ARCH_HAS_USER_SHADOW_STACK The architecture has hardware support for userspace shadow call stacks (eg, x86 CET, arm64 GCS or RISC-V Zicfiss). +config ARCH_SUPPORTS_PT_RECLAIM + def_bool n + +config PT_RECLAIM + bool "reclaim empty user page table pages" + default y + depends on ARCH_SUPPORTS_PT_RECLAIM && MMU && SMP + select MMU_GATHER_RCU_TABLE_FREE + help + Try to reclaim empty user page table pages in paths other than munmap + and exit_mmap path. + + Note: now only empty user PTE page table pages will be reclaimed. + + source "mm/damon/Kconfig" endmenu diff --git a/mm/Makefile b/mm/Makefile index dba52bb0da8a..850386a67b3e 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -146,3 +146,4 @@ obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o obj-$(CONFIG_EXECMEM) += execmem.o obj-$(CONFIG_TMPFS_QUOTA) += shmem_quota.o +obj-$(CONFIG_PT_RECLAIM) += pt_reclaim.o diff --git a/mm/internal.h b/mm/internal.h index 02890b29da5f..b438d35045de 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1541,4 +1541,23 @@ int walk_page_range_mm(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private); +/* pt_reclaim.c */ +bool try_get_and_clear_pmd(struct mm_struct *mm, pmd_t *pmd, pmd_t *pmdval); +void free_pte(struct mm_struct *mm, unsigned long addr, struct mmu_gather *tlb, + pmd_t pmdval); +void try_to_free_pte(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, + struct mmu_gather *tlb); + +#ifdef CONFIG_PT_RECLAIM +bool reclaim_pt_is_enabled(unsigned long start, unsigned long end, + struct zap_details *details); +#else +static inline bool reclaim_pt_is_enabled(unsigned long start, unsigned long end, + struct zap_details *details) +{ + return false; +} +#endif /* CONFIG_PT_RECLAIM */ + + #endif /* __MM_INTERNAL_H */ diff --git a/mm/madvise.c b/mm/madvise.c index 0ceae57da7da..49f3a75046f6 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -851,7 +851,12 @@ static int madvise_free_single_vma(struct vm_area_struct *vma, static long madvise_dontneed_single_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - zap_page_range_single(vma, start, end - start, NULL); + struct zap_details details = { + .reclaim_pt = true, + .even_cows = true, + }; + + zap_page_range_single(vma, start, end - start, &details); return 0; } diff --git a/mm/memory.c b/mm/memory.c index d4d5bd7046e7..560520e20ead 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1436,7 +1436,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) static inline bool should_zap_cows(struct zap_details *details) { /* By default, zap all pages */ - if (!details) + if (!details || details->reclaim_pt) return true; /* Or, we zap COWed pages only if the caller wants to */ @@ -1710,12 +1710,15 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, struct zap_details *details) { bool force_flush = false, force_break = false; - bool any_skipped = false; struct mm_struct *mm = tlb->mm; int rss[NR_MM_COUNTERS]; spinlock_t *ptl; pte_t *start_pte; pte_t *pte; + pmd_t pmdval; + unsigned long start = addr; + bool can_reclaim_pt = reclaim_pt_is_enabled(start, end, details); + bool direct_reclaim = false; int nr; retry: @@ -1728,17 +1731,24 @@ retry: flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); do { + bool any_skipped = false; + if (need_resched()) break; nr = do_zap_pte_range(tlb, vma, pte, addr, end, details, rss, &force_flush, &force_break, &any_skipped); + if (any_skipped) + can_reclaim_pt = false; if (unlikely(force_break)) { addr += nr * PAGE_SIZE; break; } } while (pte += nr, addr += PAGE_SIZE * nr, addr != end); + if (can_reclaim_pt && addr == end) + direct_reclaim = try_get_and_clear_pmd(mm, pmd, &pmdval); + add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); @@ -1765,6 +1775,13 @@ retry: goto retry; } + if (can_reclaim_pt) { + if (direct_reclaim) + free_pte(mm, start, tlb, pmdval); + else + try_to_free_pte(mm, pmd, start, tlb); + } + return addr; } diff --git a/mm/pt_reclaim.c b/mm/pt_reclaim.c new file mode 100644 index 000000000000..7e9455a18aae --- /dev/null +++ b/mm/pt_reclaim.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include + +#include "internal.h" + +bool reclaim_pt_is_enabled(unsigned long start, unsigned long end, + struct zap_details *details) +{ + return details && details->reclaim_pt && (end - start >= PMD_SIZE); +} + +bool try_get_and_clear_pmd(struct mm_struct *mm, pmd_t *pmd, pmd_t *pmdval) +{ + spinlock_t *pml = pmd_lockptr(mm, pmd); + + if (!spin_trylock(pml)) + return false; + + *pmdval = pmdp_get_lockless(pmd); + pmd_clear(pmd); + spin_unlock(pml); + + return true; +} + +void free_pte(struct mm_struct *mm, unsigned long addr, struct mmu_gather *tlb, + pmd_t pmdval) +{ + pte_free_tlb(tlb, pmd_pgtable(pmdval), addr); + mm_dec_nr_ptes(mm); +} + +void try_to_free_pte(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, + struct mmu_gather *tlb) +{ + pmd_t pmdval; + spinlock_t *pml, *ptl = NULL; + pte_t *start_pte, *pte; + int i; + + pml = pmd_lock(mm, pmd); + start_pte = pte_offset_map_rw_nolock(mm, pmd, addr, &pmdval, &ptl); + if (!start_pte) + goto out_ptl; + if (ptl != pml) + spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); + + /* Check if it is empty PTE page */ + for (i = 0, pte = start_pte; i < PTRS_PER_PTE; i++, pte++) { + if (!pte_none(ptep_get(pte))) + goto out_ptl; + } + pte_unmap(start_pte); + + pmd_clear(pmd); + + if (ptl != pml) + spin_unlock(ptl); + spin_unlock(pml); + + free_pte(mm, addr, tlb, pmdval); + + return; +out_ptl: + if (start_pte) + pte_unmap_unlock(start_pte, ptl); + if (ptl != pml) + spin_unlock(pml); +}