diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index b6e5ba22176a01bdd407d6c8365cfbf08063b90e..f9dc42f4451f5f90d7fdd1ad8a399cdf76bf48ad 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -360,6 +360,31 @@ deny force Force the huge option on for all - very useful for testing; +Shmem can also use "multi-size THP" (mTHP) by adding a new sysfs knob to +control mTHP allocation: +'/sys/kernel/mm/transparent_hugepage/hugepages-kB/shmem_enabled', +and its value for each mTHP is essentially consistent with the global +setting. An 'inherit' option is added to ensure compatibility with these +global settings. Conversely, the options 'force' and 'deny' are dropped, +which are rather testing artifacts from the old ages. + +always + Attempt to allocate huge pages every time we need a new page; + +inherit + Inherit the top-level "shmem_enabled" value. By default, PMD-sized hugepages + have enabled="inherit" and all other hugepage sizes have enabled="never"; + +never + Do not allocate huge pages; + +within_size + Only allocate huge page if it will be fully within i_size. + Also respect fadvise()/madvise() hints; + +advise + Only allocate huge pages if requested with fadvise()/madvise(); + Need of application restart =========================== @@ -372,10 +397,6 @@ also applies to the regions registered in khugepaged. Monitoring usage ================ -.. note:: - Currently the below counters only record events relating to - PMD-sized THP. Events relating to other THP sizes are not included. - The number of PMD-sized anonymous transparent huge pages currently used by the system is available by reading the AnonHugePages field in ``/proc/meminfo``. To identify what applications are using PMD-sized anonymous transparent huge @@ -420,20 +441,23 @@ thp_collapse_alloc_failed the allocation. thp_file_alloc - is incremented every time a file huge page is successfully - allocated. + is incremented every time a shmem huge page is successfully + allocated (Note that despite being named after "file", the counter + measures only shmem). thp_file_fallback - is incremented if a file huge page is attempted to be allocated - but fails and instead falls back to using small pages. + is incremented if a shmem huge page is attempted to be allocated + but fails and instead falls back to using small pages. (Note that + despite being named after "file", the counter measures only shmem). thp_file_fallback_charge - is incremented if a file huge page cannot be charged and instead + is incremented if a shmem huge page cannot be charged and instead falls back to using small pages even though the allocation was - successful. + successful. (Note that despite being named after "file", the + counter measures only shmem). thp_file_mapped - is incremented every time a file huge page is mapped into + is incremented every time a file or shmem huge page is mapped into user address space. thp_split_page @@ -504,6 +528,34 @@ swpout_fallback Usually because failed to allocate some continuous swap space for the huge page. +shmem_alloc + is incremented every time a shmem huge page is successfully + allocated. + +shmem_fallback + is incremented if a shmem huge page is attempted to be allocated + but fails and instead falls back to using small pages. + +shmem_fallback_charge + is incremented if a shmem huge page cannot be charged and instead + falls back to using small pages even though the allocation was + successful. + +split + is incremented every time a huge page is successfully split into + smaller orders. This can happen for a variety of reasons but a + common reason is that a huge page is old and is being reclaimed. + +split_failed + is incremented if kernel fails to split huge + page. This can happen if the page was pinned by somebody. + +split_deferred + is incremented when a huge page is put onto split queue. + This happens when a huge page is partially unmapped and splitting + it would free up some memory. Pages on split queue are going to + be split under memory pressure, if splitting is possible. + As the system ages, allocating huge pages may be expensive as the system uses memory compaction to copy data around memory to free a huge page for use. There are some counters in ``/proc/vmstat`` to help diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 29d9b12298bc843ecf24012d37f9042079d939e5..f5300b66a39d9a055ead439e6c13b2f71605b538 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -470,8 +470,8 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf, #define update_mmu_cache(vma, addr, ptep) \ update_mmu_cache_range(NULL, vma, addr, ptep, 1) -#define __HAVE_ARCH_UPDATE_MMU_TLB -#define update_mmu_tlb update_mmu_cache +#define update_mmu_tlb_range(vma, addr, ptep, nr) \ + update_mmu_cache_range(NULL, vma, addr, ptep, nr) static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 430b208c01307b7db1ea367ee12efb2317ee81ff..daa48f28ce5e03d217480dee45ce595bab02d4bd 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -594,8 +594,8 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf, #define update_mmu_cache(vma, address, ptep) \ update_mmu_cache_range(NULL, vma, address, ptep, 1) -#define __HAVE_ARCH_UPDATE_MMU_TLB -#define update_mmu_tlb update_mmu_cache +#define update_mmu_tlb_range(vma, address, ptep, nr) \ + update_mmu_cache_range(NULL, vma, address, ptep, nr) static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index a16fcdf91f39a5cfe07d20f6f4c8b5128b1fbad4..5f02effb5b4b26bc66052f7320ab13f6bfce94cb 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -491,8 +491,8 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf, #define update_mmu_cache(vma, addr, ptep) \ update_mmu_cache_range(NULL, vma, addr, ptep, 1) -#define __HAVE_ARCH_UPDATE_MMU_TLB -#define update_mmu_tlb update_mmu_cache +#define update_mmu_tlb_range(vma, addr, ptep, nr) \ + update_mmu_cache_range(NULL, vma, addr, ptep, nr) static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index 9a7e5e57ee9ad05bfa8c83541cb2f2410f4c8c28..1647a7cc3fbf6760e4187858d3a20f6ccf9773a3 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -410,9 +410,9 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, typedef pte_t *pte_addr_t; -void update_mmu_tlb(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep); -#define __HAVE_ARCH_UPDATE_MMU_TLB +void update_mmu_tlb_range(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, unsigned int nr); +#define update_mmu_tlb_range update_mmu_tlb_range #endif /* !defined (__ASSEMBLY__) */ diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c index 4f974b74883caeb7960d8f825f0759ca3f40d16e..f69feee19d590761bda015de862e5940c472403c 100644 --- a/arch/xtensa/mm/tlb.c +++ b/arch/xtensa/mm/tlb.c @@ -163,10 +163,10 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end) } } -void update_mmu_tlb(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep) +void update_mmu_tlb_range(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, unsigned int nr) { - local_flush_tlb_page(vma, address); + local_flush_tlb_range(vma, address, address + PAGE_SIZE * nr); } #ifdef CONFIG_DEBUG_TLB_SANITY diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ddde4762356221a05e25b9ba9f18fa568a667992..1474fd9c63ad2cc58cf6cf5c41da4aa3cfbc679f 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -6,6 +6,7 @@ #include #include /* only for vma_is_dax() */ +#include vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, @@ -68,6 +69,7 @@ ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; +extern struct kobj_attribute thpsize_shmem_enabled_attr; /* * Mask of all large folio orders supported for anonymous THP; all orders up to @@ -265,12 +267,26 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, return __thp_vma_allowable_orders(vma, vm_flags, tva_flags, orders); } +struct thpsize { + struct kobject kobj; + struct list_head node; + int order; +}; + +#define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj) + enum mthp_stat_item { MTHP_STAT_ANON_FAULT_ALLOC, MTHP_STAT_ANON_FAULT_FALLBACK, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, MTHP_STAT_SWPOUT, MTHP_STAT_SWPOUT_FALLBACK, + MTHP_STAT_SHMEM_ALLOC, + MTHP_STAT_SHMEM_FALLBACK, + MTHP_STAT_SHMEM_FALLBACK_CHARGE, + MTHP_STAT_SPLIT, + MTHP_STAT_SPLIT_FAILED, + MTHP_STAT_SPLIT_DEFERRED, __MTHP_STAT_COUNT }; @@ -565,6 +581,16 @@ static inline bool thp_migration_supported(void) { return false; } + +static inline int highest_order(unsigned long orders) +{ + return 0; +} + +static inline int next_order(unsigned long *orders, int prev) +{ + return 0; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline int split_folio_to_list_to_order(struct folio *folio, diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 1a0f25a27d7bdaedd67fcfb84140ae1f502316ec..c50716df9fa37fc6b91238ec3e14d6aeadff5ce7 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -68,6 +68,8 @@ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); +bool __percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, + s64 amount, s32 batch); void percpu_counter_sync(struct percpu_counter *fbc); static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) @@ -80,6 +82,13 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } +static inline bool +percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount) +{ + return __percpu_counter_limited_add(fbc, limit, amount, + percpu_counter_batch); +} + /* * With percpu_counter_add_local() and percpu_counter_sub_local(), counts * are accumulated in local per cpu counter and not in fbc->count until @@ -210,6 +219,20 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount) local_irq_restore(flags); } +static inline bool +percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount) +{ + unsigned long flags; + s64 count; + + local_irq_save(flags); + count = fbc->count + amount; + if (count <= limit) + fbc->count = count; + local_irq_restore(flags); + return count <= limit; +} + /* non-SMP percpu_counter_add_local is the same with percpu_counter_add */ static inline void percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 2ac8e48031cb88afc399f5325fd90f3fec39c910..db4faa88865de3a6dcae5a88b8de27f5ffea4be3 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -715,13 +715,18 @@ static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, * fault. This function updates TLB only, do nothing with cache or others. * It is the difference with function update_mmu_cache. */ -#ifndef __HAVE_ARCH_UPDATE_MMU_TLB +#ifndef update_mmu_tlb_range +static inline void update_mmu_tlb_range(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, unsigned int nr) +{ +} +#endif + static inline void update_mmu_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { + update_mmu_tlb_range(vma, address, ptep, 1); } -#define __HAVE_ARCH_UPDATE_MMU_TLB -#endif /* * Some architectures may be able to avoid expensive synchronization diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 134c686c8676cf6e0e5315b2259eb836aedc6402..41aa4e0d6dbcc4638e7b89126980e3d931648963 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -23,18 +23,22 @@ struct shmem_inode_info { unsigned long flags; unsigned long alloced; /* data pages alloced to file */ unsigned long swapped; /* subtotal assigned to swap */ - pgoff_t fallocend; /* highest fallocate endindex */ - struct list_head shrinklist; /* shrinkable hpage inodes */ - struct list_head swaplist; /* chain of maybes on swap */ + union { + struct offset_ctx dir_offsets; /* stable directory offsets */ + struct { + struct list_head shrinklist; /* shrinkable hpage inodes */ + struct list_head swaplist; /* chain of maybes on swap */ + }; + }; + struct timespec64 i_crtime; /* file creation time */ struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ + pgoff_t fallocend; /* highest fallocate endindex */ + unsigned int fsflags; /* for FS_IOC_[SG]ETFLAGS */ atomic_t stop_eviction; /* hold when working on inode */ - struct timespec64 i_crtime; /* file creation time */ - unsigned int fsflags; /* flags for FS_IOC_[SG]ETFLAGS */ #ifdef CONFIG_TMPFS_QUOTA struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif - struct offset_ctx dir_offsets; /* stable entry offsets */ struct inode vfs_inode; }; @@ -113,12 +117,21 @@ int shmem_unuse(unsigned int type); #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags); +unsigned long shmem_allowable_huge_orders(struct inode *inode, + struct vm_area_struct *vma, pgoff_t index, + bool global_huge); #else static __always_inline bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags) { return false; } +static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, + struct vm_area_struct *vma, pgoff_t index, + bool global_huge) +{ + return 0; +} #endif #ifdef CONFIG_SHMEM diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 7d2eaba4db1d8333dc47ab595f83f0ed3188ffa7..fb30d739f4b50f96e1adba576a8d21f52f0ceae4 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -279,6 +279,59 @@ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) } EXPORT_SYMBOL(__percpu_counter_compare); +/* + * Compare counter, and add amount if the total is within limit. + * Return true if amount was added, false if it would exceed limit. + */ +bool __percpu_counter_limited_add(struct percpu_counter *fbc, + s64 limit, s64 amount, s32 batch) +{ + s64 count; + s64 unknown; + unsigned long flags; + bool good; + + if (amount > limit) + return false; + + local_irq_save(flags); + unknown = batch * num_online_cpus(); + count = __this_cpu_read(*fbc->counters); + + /* Skip taking the lock when safe */ + if (abs(count + amount) <= batch && + fbc->count + unknown <= limit) { + this_cpu_add(*fbc->counters, amount); + local_irq_restore(flags); + return true; + } + + raw_spin_lock(&fbc->lock); + count = fbc->count + amount; + + /* Skip percpu_counter_sum() when safe */ + if (count + unknown > limit) { + s32 *pcount; + int cpu; + + for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) { + pcount = per_cpu_ptr(fbc->counters, cpu); + count += *pcount; + } + } + + good = count <= limit; + if (good) { + count = __this_cpu_read(*fbc->counters); + fbc->count += count + amount; + __this_cpu_sub(*fbc->counters, count); + } + + raw_spin_unlock(&fbc->lock); + local_irq_restore(flags); + return good; +} + /* * percpu_counter_switch_to_pcpu_many: Converts struct percpu_counters from * atomic mode to percpu mode. diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 6bf5708503f108d83385a4d80e1f3b0a5b3ceb26..fec3ee2c020b0dc9027a4817e586fd566fa413f1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -154,10 +155,15 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, * Must be done before hugepage flags check since shmem has its * own flags. */ - if (!in_pf && shmem_file(vma->vm_file)) - return shmem_is_huge(file_inode(vma->vm_file), vma->vm_pgoff, - !enforce_sysfs, vma->vm_mm, vm_flags) - ? orders : 0; + if (!in_pf && shmem_file(vma->vm_file)) { + bool global_huge = shmem_is_huge(file_inode(vma->vm_file), vma->vm_pgoff, + !enforce_sysfs, vma->vm_mm, vm_flags); + + if (!vma_is_anon_shmem(vma)) + return global_huge ? orders : 0; + return shmem_allowable_huge_orders(file_inode(vma->vm_file), + vma, vma->vm_pgoff, global_huge); + } if (!vma_is_anonymous(vma)) { /* @@ -600,14 +606,6 @@ static void thpsize_release(struct kobject *kobj); static DEFINE_SPINLOCK(huge_anon_orders_lock); static LIST_HEAD(thpsize_list); -struct thpsize { - struct kobject kobj; - struct list_head node; - int order; -}; - -#define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj) - static ssize_t thpsize_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -675,6 +673,9 @@ static struct kobj_attribute thpsize_enabled_attr = static struct attribute *thpsize_attrs[] = { &thpsize_enabled_attr.attr, +#ifdef CONFIG_SHMEM + &thpsize_shmem_enabled_attr.attr, +#endif NULL, }; @@ -718,6 +719,12 @@ DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT); DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK); +DEFINE_MTHP_STAT_ATTR(shmem_alloc, MTHP_STAT_SHMEM_ALLOC); +DEFINE_MTHP_STAT_ATTR(shmem_fallback, MTHP_STAT_SHMEM_FALLBACK); +DEFINE_MTHP_STAT_ATTR(shmem_fallback_charge, MTHP_STAT_SHMEM_FALLBACK_CHARGE); +DEFINE_MTHP_STAT_ATTR(split, MTHP_STAT_SPLIT); +DEFINE_MTHP_STAT_ATTR(split_failed, MTHP_STAT_SPLIT_FAILED); +DEFINE_MTHP_STAT_ATTR(split_deferred, MTHP_STAT_SPLIT_DEFERRED); static struct attribute *stats_attrs[] = { &anon_fault_alloc_attr.attr, @@ -725,6 +732,12 @@ static struct attribute *stats_attrs[] = { &anon_fault_fallback_charge_attr.attr, &swpout_attr.attr, &swpout_fallback_attr.attr, + &shmem_alloc_attr.attr, + &shmem_fallback_attr.attr, + &shmem_fallback_charge_attr.attr, + &split_attr.attr, + &split_failed_attr.attr, + &split_deferred_attr.attr, NULL, }; @@ -3243,7 +3256,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, XA_STATE_ORDER(xas, &folio->mapping->i_pages, folio->index, new_order); struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; - bool is_thp = folio_test_pmd_mappable(folio); + int order = folio_order(folio); int extra_pins, ret; pgoff_t end; bool is_hzp; @@ -3428,8 +3441,9 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, i_mmap_unlock_read(mapping); out: xas_destroy(&xas); - if (is_thp) + if (order == HPAGE_PMD_ORDER) count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); + count_mthp_stat(order, !ret ? MTHP_STAT_SPLIT : MTHP_STAT_SPLIT_FAILED); return ret; } @@ -3482,6 +3496,7 @@ void deferred_split_folio(struct folio *folio) if (list_empty(&folio->_deferred_list)) { if (folio_test_pmd_mappable(folio)) count_vm_event(THP_DEFERRED_SPLIT_PAGE); + count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED); list_add_tail(&folio->_deferred_list, &ds_queue->split_queue); ds_queue->split_queue_len++; #ifdef CONFIG_MEMCG diff --git a/mm/memory.c b/mm/memory.c index 7fd1f71cebebd35fe07005fc3420070fbe8dc485..bfc25fa206a2a23e9b7a8d74ce3e69e6c7571914 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4411,7 +4411,6 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) vm_fault_t ret = 0; int nr_pages = 1; pte_t entry; - int i; /* File mapping without ->vm_ops ? */ if (vma->vm_flags & VM_SHARED) @@ -4481,8 +4480,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) update_mmu_tlb(vma, addr, vmf->pte); goto release; } else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) { - for (i = 0; i < nr_pages; i++) - update_mmu_tlb(vma, addr + PAGE_SIZE * i, vmf->pte + i); + update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages); goto release; } @@ -4741,9 +4739,12 @@ vm_fault_t finish_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; + struct folio *folio; vm_fault_t ret; bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED); + int type, nr_pages; + unsigned long addr = vmf->address; /* Did we COW the page? */ if (is_cow) @@ -4774,24 +4775,62 @@ vm_fault_t finish_fault(struct vm_fault *vmf) return VM_FAULT_OOM; } + folio = page_folio(page); + nr_pages = folio_nr_pages(folio); + + /* + * Using per-page fault to maintain the uffd semantics, and same + * approach also applies to non-anonymous-shmem faults to avoid + * inflating the RSS of the process. + */ + if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma))) { + nr_pages = 1; + } else if (nr_pages > 1) { + pgoff_t idx = folio_page_idx(folio, page); + /* The page offset of vmf->address within the VMA. */ + pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff; + /* The index of the entry in the pagetable for fault page. */ + pgoff_t pte_off = pte_index(vmf->address); + + /* + * Fallback to per-page fault in case the folio size in page + * cache beyond the VMA limits and PMD pagetable limits. + */ + if (unlikely(vma_off < idx || + vma_off + (nr_pages - idx) > vma_pages(vma) || + pte_off < idx || + pte_off + (nr_pages - idx) > PTRS_PER_PTE)) { + nr_pages = 1; + } else { + /* Now we can set mappings for the whole large folio. */ + addr = vmf->address - idx * PAGE_SIZE; + page = &folio->page; + } + } + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); + addr, &vmf->ptl); if (!vmf->pte) return VM_FAULT_NOPAGE; /* Re-check under ptl */ - if (likely(!vmf_pte_changed(vmf))) { - struct folio *folio = page_folio(page); - int type = is_cow ? MM_ANONPAGES : mm_counter_file(folio); - - set_pte_range(vmf, folio, page, 1, vmf->address); - add_mm_counter(vma->vm_mm, type, 1); - ret = 0; - } else { - update_mmu_tlb(vma, vmf->address, vmf->pte); + if (nr_pages == 1 && unlikely(vmf_pte_changed(vmf))) { + update_mmu_tlb(vma, addr, vmf->pte); + ret = VM_FAULT_NOPAGE; + goto unlock; + } else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) { + update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages); ret = VM_FAULT_NOPAGE; + goto unlock; } + folio_ref_add(folio, nr_pages - 1); + set_pte_range(vmf, folio, page, nr_pages, addr); + type = is_cow ? MM_ANONPAGES : mm_counter_file(folio); + add_mm_counter(vma->vm_mm, type, nr_pages); + ret = 0; + +unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; } diff --git a/mm/shmem.c b/mm/shmem.c index 0b82806727cff9c80508ab4bcdeb03454403d6f5..3e1d36c98b927375626ed60cde865ec4878c6c18 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -131,6 +131,13 @@ struct shmem_options { #define SHMEM_SEEN_QUOTA 32 }; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static unsigned long huge_shmem_orders_always __read_mostly; +static unsigned long huge_shmem_orders_madvise __read_mostly; +static unsigned long huge_shmem_orders_inherit __read_mostly; +static unsigned long huge_shmem_orders_within_size __read_mostly; +#endif + #ifdef CONFIG_TMPFS static unsigned long shmem_default_max_blocks(void) { @@ -147,9 +154,8 @@ static unsigned long shmem_default_max_inodes(void) #endif static int shmem_swapin_folio(struct inode *inode, pgoff_t index, - struct folio **foliop, enum sgp_type sgp, - gfp_t gfp, struct vm_area_struct *vma, - vm_fault_t *fault_type); + struct folio **foliop, enum sgp_type sgp, gfp_t gfp, + struct mm_struct *fault_mm, vm_fault_t *fault_type); static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) { @@ -190,10 +196,10 @@ static inline int shmem_reacct_size(unsigned long flags, /* * ... whereas tmpfs objects are accounted incrementally as * pages are allocated, in order to allow large sparse files. - * shmem_get_folio reports shmem_acct_block failure as -ENOSPC not -ENOMEM, + * shmem_get_folio reports shmem_acct_blocks failure as -ENOSPC not -ENOMEM, * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM. */ -static inline int shmem_acct_block(unsigned long flags, long pages) +static inline int shmem_acct_blocks(unsigned long flags, long pages) { if (!(flags & VM_NORESERVE)) return 0; @@ -208,26 +214,26 @@ static inline void shmem_unacct_blocks(unsigned long flags, long pages) vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE)); } -static int shmem_inode_acct_block(struct inode *inode, long pages) +static int shmem_inode_acct_blocks(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); int err = -ENOSPC; - if (shmem_acct_block(info->flags, pages)) + if (shmem_acct_blocks(info->flags, pages)) return err; might_sleep(); /* when quotas */ if (sbinfo->max_blocks) { - if (percpu_counter_compare(&sbinfo->used_blocks, - sbinfo->max_blocks - pages) > 0) + if (!percpu_counter_limited_add(&sbinfo->used_blocks, + sbinfo->max_blocks, pages)) goto unacct; err = dquot_alloc_block_nodirty(inode, pages); - if (err) + if (err) { + percpu_counter_sub(&sbinfo->used_blocks, pages); goto unacct; - - percpu_counter_add(&sbinfo->used_blocks, pages); + } } else { err = dquot_alloc_block_nodirty(inode, pages); if (err) @@ -448,7 +454,7 @@ bool shmem_charge(struct inode *inode, long pages) { struct address_space *mapping = inode->i_mapping; - if (shmem_inode_acct_block(inode, pages)) + if (shmem_inode_acct_blocks(inode, pages)) return false; /* nrpages adjustment first, then shmem_recalc_inode() when balanced */ @@ -762,16 +768,14 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* - * Like filemap_add_folio, but error if expected item has gone. + * Somewhat like filemap_add_folio, but error if expected item has gone. */ static int shmem_add_to_page_cache(struct folio *folio, struct address_space *mapping, - pgoff_t index, void *expected, gfp_t gfp, - struct mm_struct *charge_mm) + pgoff_t index, void *expected, gfp_t gfp) { XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio)); long nr = folio_nr_pages(folio); - int error; VM_BUG_ON_FOLIO(index != round_down(index, nr), folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); @@ -782,16 +786,7 @@ static int shmem_add_to_page_cache(struct folio *folio, folio->mapping = mapping; folio->index = index; - if (!folio_test_swapcache(folio)) { - error = mem_cgroup_charge(folio, charge_mm, gfp); - if (error) { - if (folio_test_pmd_mappable(folio)) { - count_vm_event(THP_FILE_FALLBACK); - count_vm_event(THP_FILE_FALLBACK_CHARGE); - } - goto error; - } - } + gfp &= GFP_RECLAIM_MASK; folio_throttle_swaprate(folio, gfp); do { @@ -807,32 +802,27 @@ static int shmem_add_to_page_cache(struct folio *folio, xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; - if (folio_test_pmd_mappable(folio)) { - count_vm_event(THP_FILE_ALLOC); + if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr); - } - mapping->nrpages += nr; __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); __lruvec_stat_mod_folio(folio, NR_SHMEM, nr); shmem_reliable_folio_add(folio, nr); + mapping->nrpages += nr; unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) { - error = xas_error(&xas); - goto error; + folio->mapping = NULL; + folio_ref_sub(folio, nr); + return xas_error(&xas); } return 0; -error: - folio->mapping = NULL; - folio_ref_sub(folio, nr); - return error; } /* - * Like delete_from_page_cache, but substitutes swap for @folio. + * Somewhat like filemap_remove_folio, but substitutes swap for @folio. */ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap) { @@ -895,7 +885,6 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping, cond_resched_rcu(); } } - rcu_read_unlock(); return swapped << PAGE_SHIFT; @@ -1238,7 +1227,6 @@ static int shmem_setattr(struct mnt_idmap *idmap, if (i_uid_needs_update(idmap, attr, inode) || i_gid_needs_update(idmap, attr, inode)) { error = dquot_transfer(idmap, inode, attr); - if (error) return error; } @@ -1351,10 +1339,8 @@ static int shmem_unuse_swap_entries(struct inode *inode, if (!xa_is_value(folio)) continue; - error = shmem_swapin_folio(inode, indices[i], - &folio, SGP_CACHE, - mapping_gfp_mask(mapping), - NULL, NULL); + error = shmem_swapin_folio(inode, indices[i], &folio, SGP_CACHE, + mapping_gfp_mask(mapping), NULL, NULL); if (error == 0) { folio_unlock(folio); folio_put(folio); @@ -1652,74 +1638,237 @@ static gfp_t limit_gfp_mask(gfp_t huge_gfp, gfp_t limit_gfp) return result; } -static struct folio *shmem_alloc_hugefolio(gfp_t gfp, - struct shmem_inode_info *info, pgoff_t index) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +unsigned long shmem_allowable_huge_orders(struct inode *inode, + struct vm_area_struct *vma, pgoff_t index, + bool global_huge) { - struct vm_area_struct pvma; - struct address_space *mapping = info->vfs_inode.i_mapping; - pgoff_t hindex; - struct folio *folio; + unsigned long mask = READ_ONCE(huge_shmem_orders_always); + unsigned long within_size_orders = READ_ONCE(huge_shmem_orders_within_size); + unsigned long vm_flags = vma->vm_flags; + loff_t i_size; + int order; - hindex = round_down(index, HPAGE_PMD_NR); - if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1, - XA_PRESENT)) - return NULL; + if ((vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + return 0; - shmem_pseudo_vma_init(&pvma, info, hindex); - folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, &pvma, 0, true); - shmem_pseudo_vma_destroy(&pvma); - if (!folio) - count_vm_event(THP_FILE_FALLBACK); - return folio; + /* If the hardware/firmware marked hugepage support disabled. */ + if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) + return 0; + + /* + * Following the 'deny' semantics of the top level, force the huge + * option off from all mounts. + */ + if (shmem_huge == SHMEM_HUGE_DENY) + return 0; + + /* + * Only allow inherit orders if the top-level value is 'force', which + * means non-PMD sized THP can not override 'huge' mount option now. + */ + if (shmem_huge == SHMEM_HUGE_FORCE) + return READ_ONCE(huge_shmem_orders_inherit); + + /* Allow mTHP that will be fully within i_size. */ + order = highest_order(within_size_orders); + while (within_size_orders) { + index = round_up(index + 1, order); + i_size = round_up(i_size_read(inode), PAGE_SIZE); + if (i_size >> PAGE_SHIFT >= index) { + mask |= within_size_orders; + break; + } + + order = next_order(&within_size_orders, order); + } + + if (vm_flags & VM_HUGEPAGE) + mask |= READ_ONCE(huge_shmem_orders_madvise); + + if (global_huge) + mask |= READ_ONCE(huge_shmem_orders_inherit); + + return THP_ORDERS_ALL_FILE_DEFAULT & mask; } -static struct folio *shmem_alloc_folio(gfp_t gfp, - struct shmem_inode_info *info, pgoff_t index) +static unsigned long shmem_suitable_orders(struct inode *inode, struct vm_fault *vmf, + struct address_space *mapping, pgoff_t index, + unsigned long orders) +{ + struct vm_area_struct *vma = vmf->vma; + pgoff_t aligned_index; + unsigned long pages; + int order; + + orders = thp_vma_suitable_orders(vma, vmf->address, orders); + if (!orders) + return 0; + + /* Find the highest order that can add into the page cache */ + order = highest_order(orders); + while (orders) { + pages = 1UL << order; + aligned_index = round_down(index, pages); + if (!xa_find(&mapping->i_pages, &aligned_index, + aligned_index + pages - 1, XA_PRESENT)) + break; + order = next_order(&orders, order); + } + + return orders; +} +#else +static unsigned long shmem_suitable_orders(struct inode *inode, struct vm_fault *vmf, + struct address_space *mapping, pgoff_t index, + unsigned long orders) +{ + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static struct folio *shmem_alloc_folio(gfp_t gfp, int order, + struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct folio *folio; + bool hugepage = !!order; shmem_pseudo_vma_init(&pvma, info, index); - folio = vma_alloc_folio(gfp, 0, &pvma, 0, false); + folio = vma_alloc_folio(gfp, order, &pvma, 0, hugepage); shmem_pseudo_vma_destroy(&pvma); return folio; } -static struct folio *shmem_alloc_and_acct_folio(gfp_t gfp, struct inode *inode, - pgoff_t index, bool huge) +static struct folio *shmem_alloc_and_add_folio(struct vm_fault *vmf, + gfp_t gfp, struct inode *inode, pgoff_t index, + struct mm_struct *fault_mm, unsigned long orders) { + struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); - struct folio *folio; - int nr; - int err; + struct vm_area_struct *vma = vmf ? vmf->vma : NULL; + unsigned long suitable_orders = 0; + struct folio *folio = NULL; + long pages; + int error, order; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) - huge = false; - nr = huge ? HPAGE_PMD_NR : 1; - - err = shmem_inode_acct_block(inode, nr); - if (err) - goto failed; + orders = 0; if (!shmem_prepare_alloc(&gfp)) goto no_mem; - if (huge) - folio = shmem_alloc_hugefolio(gfp, info, index); - else - folio = shmem_alloc_folio(gfp, info, index); - if (folio) { - __folio_set_locked(folio); - __folio_set_swapbacked(folio); - return folio; + if (orders > 0) { + if (vma && vma_is_anon_shmem(vma)) { + suitable_orders = shmem_suitable_orders(inode, vmf, + mapping, index, orders); + } else if (orders & BIT(HPAGE_PMD_ORDER)) { + pages = HPAGE_PMD_NR; + suitable_orders = BIT(HPAGE_PMD_ORDER); + index = round_down(index, HPAGE_PMD_NR); + + /* + * Check for conflict before waiting on a huge allocation. + * Conflict might be that a huge page has just been allocated + * and added to page cache by a racing thread, or that there + * is already at least one small page in the huge extent. + * Be careful to retry when appropriate, but not forever! + * Elsewhere -EEXIST would be the right code, but not here. + */ + if (xa_find(&mapping->i_pages, &index, + index + HPAGE_PMD_NR - 1, XA_PRESENT)) + return ERR_PTR(-E2BIG); + } + + order = highest_order(suitable_orders); + while (suitable_orders) { + pages = 1UL << order; + index = round_down(index, pages); + folio = shmem_alloc_folio(gfp, order, info, index); + if (folio) + goto allocated; + + if (pages == HPAGE_PMD_NR) + count_vm_event(THP_FILE_FALLBACK); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + count_mthp_stat(order, MTHP_STAT_SHMEM_FALLBACK); +#endif + order = next_order(&suitable_orders, order); + } + } else { + pages = 1; + folio = shmem_alloc_folio(gfp, 0, info, index); } no_mem: - err = -ENOMEM; - shmem_inode_unacct_blocks(inode, nr); -failed: - return ERR_PTR(err); + if (!folio) + return ERR_PTR(-ENOMEM); + +allocated: + __folio_set_locked(folio); + __folio_set_swapbacked(folio); + + gfp &= GFP_RECLAIM_MASK; + error = mem_cgroup_charge(folio, fault_mm, gfp); + if (error) { + if (xa_find(&mapping->i_pages, &index, + index + pages - 1, XA_PRESENT)) { + error = -EEXIST; + } else if (pages > 1) { + if (pages == HPAGE_PMD_NR) { + count_vm_event(THP_FILE_FALLBACK); + count_vm_event(THP_FILE_FALLBACK_CHARGE); + } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + count_mthp_stat(folio_order(folio), MTHP_STAT_SHMEM_FALLBACK); + count_mthp_stat(folio_order(folio), MTHP_STAT_SHMEM_FALLBACK_CHARGE); +#endif + } + goto unlock; + } + + error = shmem_add_to_page_cache(folio, mapping, index, NULL, gfp); + if (error) + goto unlock; + + error = shmem_inode_acct_blocks(inode, pages); + if (error) { + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + long freed; + /* + * Try to reclaim some space by splitting a few + * large folios beyond i_size on the filesystem. + */ + shmem_unused_huge_shrink(sbinfo, NULL, 2); + /* + * And do a shmem_recalc_inode() to account for freed pages: + * except our folio is there in cache, so not quite balanced. + */ + spin_lock(&info->lock); + freed = pages + info->alloced - info->swapped - + READ_ONCE(mapping->nrpages); + if (freed > 0) + info->alloced -= freed; + spin_unlock(&info->lock); + if (freed > 0) + shmem_inode_unacct_blocks(inode, freed); + error = shmem_inode_acct_blocks(inode, pages); + if (error) { + filemap_remove_folio(folio); + goto unlock; + } + } + + shmem_recalc_inode(inode, pages, 0); + folio_add_lru(folio); + return folio; + +unlock: + folio_unlock(folio); + folio_put(folio); + return ERR_PTR(error); } /* @@ -1759,7 +1908,7 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp, */ gfp &= ~GFP_CONSTRAINT_MASK; VM_BUG_ON_FOLIO(folio_test_large(old), old); - new = shmem_alloc_folio(gfp, info, index); + new = shmem_alloc_folio(gfp, 0, info, index); if (!new) return -ENOMEM; @@ -1843,12 +1992,11 @@ static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index, */ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp, - gfp_t gfp, struct vm_area_struct *vma, + gfp_t gfp, struct mm_struct *fault_mm, vm_fault_t *fault_type) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); - struct mm_struct *charge_mm = vma ? vma->vm_mm : NULL; struct swap_info_struct *si; struct folio *folio = NULL; swp_entry_t swap; @@ -1876,7 +2024,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, if (fault_type) { *fault_type |= VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); - count_memcg_event_mm(charge_mm, PGMAJFAULT); + count_memcg_event_mm(fault_mm, PGMAJFAULT); } /* Here we actually start the io */ folio = shmem_swapin(swap, gfp, info, index); @@ -1913,8 +2061,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, } error = shmem_add_to_page_cache(folio, mapping, index, - swp_to_radix_entry(swap), gfp, - charge_mm); + swp_to_radix_entry(swap), gfp); if (error) goto failed; @@ -1952,37 +2099,33 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, * vm. If we swap it in we mark it dirty since we also free the swap * entry since a page cannot live in both the swap and page cache. * - * vma, vmf, and fault_type are only supplied by shmem_fault: - * otherwise they are NULL. + * vmf and fault_type are only supplied by shmem_fault: otherwise they are NULL. */ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp, gfp_t gfp, - struct vm_area_struct *vma, struct vm_fault *vmf, - vm_fault_t *fault_type) + struct vm_fault *vmf, vm_fault_t *fault_type) { - struct address_space *mapping = inode->i_mapping; - struct shmem_inode_info *info = SHMEM_I(inode); - struct shmem_sb_info *sbinfo; - struct mm_struct *charge_mm; + struct vm_area_struct *vma = vmf ? vmf->vma : NULL; + struct mm_struct *fault_mm; struct folio *folio; - pgoff_t hindex; - gfp_t huge_gfp; int error; - int once = 0; - int alloced = 0; + bool alloced, huge; + unsigned long orders = 0; + + if (WARN_ON_ONCE(!shmem_mapping(inode->i_mapping))) + return -EINVAL; if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT)) return -EFBIG; repeat: if (sgp <= SGP_CACHE && - ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { + ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) return -EINVAL; - } - sbinfo = SHMEM_SB(inode->i_sb); - charge_mm = vma ? vma->vm_mm : NULL; + alloced = false; + fault_mm = vma ? vma->vm_mm : NULL; - folio = filemap_get_entry(mapping, index); + folio = filemap_get_entry(inode->i_mapping, index); if (folio && vma && userfaultfd_minor(vma)) { if (!xa_is_value(folio)) folio_put(folio); @@ -1992,7 +2135,7 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, if (xa_is_value(folio)) { error = shmem_swapin_folio(inode, index, &folio, - sgp, gfp, vma, fault_type); + sgp, gfp, fault_mm, fault_type); if (error == -EEXIST) goto repeat; @@ -2004,7 +2147,7 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, folio_lock(folio); /* Has the folio been truncated or swapped out? */ - if (unlikely(folio->mapping != mapping)) { + if (unlikely(folio->mapping != inode->i_mapping)) { folio_unlock(folio); folio_put(folio); goto repeat; @@ -2039,60 +2182,52 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, return 0; } - if (!shmem_is_huge(inode, index, false, - vma ? vma->vm_mm : NULL, vma ? vma->vm_flags : 0)) - goto alloc_nohuge; - if (mm_in_dynamic_pool(vma ? vma->vm_mm : current->mm)) - goto alloc_nohuge; + huge = shmem_is_huge(inode, index, false, fault_mm, + vma ? vma->vm_flags : 0); - huge_gfp = vma_thp_gfp_mask(vma); - huge_gfp = limit_gfp_mask(huge_gfp, gfp); - folio = shmem_alloc_and_acct_folio(huge_gfp, inode, index, true); - if (IS_ERR(folio)) { -alloc_nohuge: - folio = shmem_alloc_and_acct_folio(gfp, inode, index, false); + /* Find hugepage orders that are allowed for anonymous shmem. */ + if (mm_in_dynamic_pool(vma ? vma->vm_mm : current->mm)) + orders = 0; + else if (vma && vma_is_anon_shmem(vma)) + orders = shmem_allowable_huge_orders(inode, vma, index, huge); + else if (huge) + orders = BIT(HPAGE_PMD_ORDER); + + if (orders > 0) { + gfp_t huge_gfp; + + huge_gfp = vma_thp_gfp_mask(vma); + huge_gfp = limit_gfp_mask(huge_gfp, gfp); + folio = shmem_alloc_and_add_folio(vmf, huge_gfp, + inode, index, fault_mm, orders); + if (!IS_ERR(folio)) { + if (folio_test_pmd_mappable(folio)) + count_vm_event(THP_FILE_ALLOC); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + count_mthp_stat(folio_order(folio), MTHP_STAT_SHMEM_ALLOC); +#endif + goto alloced; + } + if (PTR_ERR(folio) == -EEXIST) + goto repeat; } - if (IS_ERR(folio)) { - int retry = 5; + folio = shmem_alloc_and_add_folio(vmf, gfp, inode, index, fault_mm, 0); + if (IS_ERR(folio)) { error = PTR_ERR(folio); + if (error == -EEXIST) + goto repeat; folio = NULL; - if (error != -ENOSPC) - goto unlock; - /* - * Try to reclaim some space by splitting a large folio - * beyond i_size on the filesystem. - */ - while (retry--) { - int ret; - - ret = shmem_unused_huge_shrink(sbinfo, NULL, 1); - if (ret == SHRINK_STOP) - break; - if (ret) - goto alloc_nohuge; - } goto unlock; } - hindex = round_down(index, folio_nr_pages(folio)); - - if (sgp == SGP_WRITE) - __folio_set_referenced(folio); - - error = shmem_add_to_page_cache(folio, mapping, hindex, - NULL, gfp & GFP_RECLAIM_MASK, - charge_mm); - if (error) - goto unacct; - - folio_add_lru(folio); - shmem_recalc_inode(inode, folio_nr_pages(folio), 0); +alloced: alloced = true; - - if (folio_test_pmd_mappable(folio) && + if (folio_test_large(folio) && DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE) < folio_next_index(folio) - 1) { + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + struct shmem_inode_info *info = SHMEM_I(inode); /* * Part of the large folio is beyond i_size: subject * to shrink under memory pressure. @@ -2110,6 +2245,8 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, spin_unlock(&sbinfo->shrinklist_lock); } + if (sgp == SGP_WRITE) + folio_set_referenced(folio); /* * Let SGP_FALLOC use the SGP_WRITE optimization on a new folio. */ @@ -2133,11 +2270,6 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, /* Perhaps the file has been truncated since we checked */ if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { - if (alloced) { - folio_clear_dirty(folio); - filemap_remove_folio(folio); - shmem_recalc_inode(inode, 0, 0); - } error = -EINVAL; goto unlock; } @@ -2148,25 +2280,14 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, /* * Error recovery. */ -unacct: - shmem_inode_unacct_blocks(inode, folio_nr_pages(folio)); - - if (folio_test_large(folio)) { - folio_unlock(folio); - folio_put(folio); - goto alloc_nohuge; - } unlock: + if (alloced) + filemap_remove_folio(folio); + shmem_recalc_inode(inode, 0, 0); if (folio) { folio_unlock(folio); folio_put(folio); } - if (error == -ENOSPC && !once++) { - shmem_recalc_inode(inode, 0, 0); - goto repeat; - } - if (error == -EEXIST) - goto repeat; return error; } @@ -2174,7 +2295,7 @@ int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp) { return shmem_get_folio_gfp(inode, index, foliop, sgp, - mapping_gfp_mask(inode->i_mapping), NULL, NULL, NULL); + mapping_gfp_mask(inode->i_mapping), NULL, NULL); } /* @@ -2182,87 +2303,99 @@ int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop, * entry unconditionally - even if something else had already woken the * target. */ -static int synchronous_wake_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) +static int synchronous_wake_function(wait_queue_entry_t *wait, + unsigned int mode, int sync, void *key) { int ret = default_wake_function(wait, mode, sync, key); list_del_init(&wait->entry); return ret; } +/* + * Trinity finds that probing a hole which tmpfs is punching can + * prevent the hole-punch from ever completing: which in turn + * locks writers out with its hold on i_rwsem. So refrain from + * faulting pages into the hole while it's being punched. Although + * shmem_undo_range() does remove the additions, it may be unable to + * keep up, as each new page needs its own unmap_mapping_range() call, + * and the i_mmap tree grows ever slower to scan if new vmas are added. + * + * It does not matter if we sometimes reach this check just before the + * hole-punch begins, so that one fault then races with the punch: + * we just need to make racing faults a rare case. + * + * The implementation below would be much simpler if we just used a + * standard mutex or completion: but we cannot take i_rwsem in fault, + * and bloating every shmem inode for this unlikely case would be sad. + */ +static vm_fault_t shmem_falloc_wait(struct vm_fault *vmf, struct inode *inode) +{ + struct shmem_falloc *shmem_falloc; + struct file *fpin = NULL; + vm_fault_t ret = 0; + + spin_lock(&inode->i_lock); + shmem_falloc = inode->i_private; + if (shmem_falloc && + shmem_falloc->waitq && + vmf->pgoff >= shmem_falloc->start && + vmf->pgoff < shmem_falloc->next) { + wait_queue_head_t *shmem_falloc_waitq; + DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function); + + ret = VM_FAULT_NOPAGE; + fpin = maybe_unlock_mmap_for_io(vmf, NULL); + shmem_falloc_waitq = shmem_falloc->waitq; + prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, + TASK_UNINTERRUPTIBLE); + spin_unlock(&inode->i_lock); + schedule(); + + /* + * shmem_falloc_waitq points into the shmem_fallocate() + * stack of the hole-punching task: shmem_falloc_waitq + * is usually invalid by the time we reach here, but + * finish_wait() does not dereference it in that case; + * though i_lock needed lest racing with wake_up_all(). + */ + spin_lock(&inode->i_lock); + finish_wait(shmem_falloc_waitq, &shmem_fault_wait); + } + spin_unlock(&inode->i_lock); + if (fpin) { + fput(fpin); + ret = VM_FAULT_RETRY; + } + return ret; +} + static vm_fault_t shmem_fault(struct vm_fault *vmf) { - struct vm_area_struct *vma = vmf->vma; - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); gfp_t gfp = mapping_gfp_mask(inode->i_mapping); struct folio *folio = NULL; + vm_fault_t ret = 0; int err; - vm_fault_t ret = VM_FAULT_LOCKED; /* * Trinity finds that probing a hole which tmpfs is punching can - * prevent the hole-punch from ever completing: which in turn - * locks writers out with its hold on i_rwsem. So refrain from - * faulting pages into the hole while it's being punched. Although - * shmem_undo_range() does remove the additions, it may be unable to - * keep up, as each new page needs its own unmap_mapping_range() call, - * and the i_mmap tree grows ever slower to scan if new vmas are added. - * - * It does not matter if we sometimes reach this check just before the - * hole-punch begins, so that one fault then races with the punch: - * we just need to make racing faults a rare case. - * - * The implementation below would be much simpler if we just used a - * standard mutex or completion: but we cannot take i_rwsem in fault, - * and bloating every shmem inode for this unlikely case would be sad. + * prevent the hole-punch from ever completing: noted in i_private. */ if (unlikely(inode->i_private)) { - struct shmem_falloc *shmem_falloc; - - spin_lock(&inode->i_lock); - shmem_falloc = inode->i_private; - if (shmem_falloc && - shmem_falloc->waitq && - vmf->pgoff >= shmem_falloc->start && - vmf->pgoff < shmem_falloc->next) { - struct file *fpin; - wait_queue_head_t *shmem_falloc_waitq; - DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function); - - ret = VM_FAULT_NOPAGE; - fpin = maybe_unlock_mmap_for_io(vmf, NULL); - if (fpin) - ret = VM_FAULT_RETRY; - - shmem_falloc_waitq = shmem_falloc->waitq; - prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, - TASK_UNINTERRUPTIBLE); - spin_unlock(&inode->i_lock); - schedule(); - - /* - * shmem_falloc_waitq points into the shmem_fallocate() - * stack of the hole-punching task: shmem_falloc_waitq - * is usually invalid by the time we reach here, but - * finish_wait() does not dereference it in that case; - * though i_lock needed lest racing with wake_up_all(). - */ - spin_lock(&inode->i_lock); - finish_wait(shmem_falloc_waitq, &shmem_fault_wait); - spin_unlock(&inode->i_lock); - - if (fpin) - fput(fpin); + ret = shmem_falloc_wait(vmf, inode); + if (ret) return ret; - } - spin_unlock(&inode->i_lock); } + WARN_ON_ONCE(vmf->page != NULL); err = shmem_get_folio_gfp(inode, vmf->pgoff, &folio, SGP_CACHE, - gfp, vma, vmf, &ret); + gfp, vmf, &ret); if (err) return vmf_error(err); - if (folio) + if (folio) { vmf->page = folio_file_page(folio, vmf->pgoff); + ret |= VM_FAULT_LOCKED; + } return ret; } @@ -2277,6 +2410,7 @@ unsigned long shmem_get_unmapped_area(struct file *file, unsigned long inflated_len; unsigned long inflated_addr; unsigned long inflated_offset; + unsigned long hpage_size; if (len > TASK_SIZE) return -ENOMEM; @@ -2295,8 +2429,6 @@ unsigned long shmem_get_unmapped_area(struct file *file, if (shmem_huge == SHMEM_HUGE_DENY) return addr; - if (len < HPAGE_PMD_SIZE) - return addr; if (flags & MAP_FIXED) return addr; /* @@ -2308,8 +2440,11 @@ unsigned long shmem_get_unmapped_area(struct file *file, if (uaddr == addr) return addr; + hpage_size = HPAGE_PMD_SIZE; if (shmem_huge != SHMEM_HUGE_FORCE) { struct super_block *sb; + unsigned long __maybe_unused hpage_orders; + int order = 0; if (file) { VM_BUG_ON(file->f_op != &shmem_file_operations); @@ -2322,18 +2457,38 @@ unsigned long shmem_get_unmapped_area(struct file *file, if (IS_ERR(shm_mnt)) return addr; sb = shm_mnt->mnt_sb; + + /* + * Find the highest mTHP order used for anonymous shmem to + * provide a suitable alignment address. + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + hpage_orders = READ_ONCE(huge_shmem_orders_always); + hpage_orders |= READ_ONCE(huge_shmem_orders_within_size); + hpage_orders |= READ_ONCE(huge_shmem_orders_madvise); + if (SHMEM_SB(sb)->huge != SHMEM_HUGE_NEVER) + hpage_orders |= READ_ONCE(huge_shmem_orders_inherit); + + if (hpage_orders > 0) { + order = highest_order(hpage_orders); + hpage_size = PAGE_SIZE << order; + } +#endif } - if (SHMEM_SB(sb)->huge == SHMEM_HUGE_NEVER) + if (SHMEM_SB(sb)->huge == SHMEM_HUGE_NEVER && !order) return addr; } - offset = (pgoff << PAGE_SHIFT) & (HPAGE_PMD_SIZE-1); - if (offset && offset + len < 2 * HPAGE_PMD_SIZE) + if (len < hpage_size) + return addr; + + offset = (pgoff << PAGE_SHIFT) & (hpage_size - 1); + if (offset && offset + len < 2 * hpage_size) return addr; - if ((addr & (HPAGE_PMD_SIZE-1)) == offset) + if ((addr & (hpage_size - 1)) == offset) return addr; - inflated_len = len + HPAGE_PMD_SIZE - PAGE_SIZE; + inflated_len = len + hpage_size - PAGE_SIZE; if (inflated_len > TASK_SIZE) return addr; if (inflated_len < len) @@ -2345,10 +2500,10 @@ unsigned long shmem_get_unmapped_area(struct file *file, if (inflated_addr & ~PAGE_MASK) return addr; - inflated_offset = inflated_addr & (HPAGE_PMD_SIZE-1); + inflated_offset = inflated_addr & (hpage_size - 1); inflated_addr += offset - inflated_offset; if (inflated_offset > offset) - inflated_addr += HPAGE_PMD_SIZE; + inflated_addr += hpage_size; if (inflated_addr > TASK_SIZE - len) return addr; @@ -2478,7 +2633,6 @@ static struct inode *__shmem_get_inode(struct mnt_idmap *idmap, if (err) return ERR_PTR(err); - inode = new_inode(sb); if (!inode) { shmem_free_inode(sb, 0); @@ -2503,11 +2657,10 @@ static struct inode *__shmem_get_inode(struct mnt_idmap *idmap, shmem_set_inode_flags(inode, info->fsflags); INIT_LIST_HEAD(&info->shrinklist); INIT_LIST_HEAD(&info->swaplist); - INIT_LIST_HEAD(&info->swaplist); - if (sbinfo->noswap) - mapping_set_unevictable(inode->i_mapping); simple_xattrs_init(&info->xattrs); cache_no_acl(inode); + if (sbinfo->noswap) + mapping_set_unevictable(inode->i_mapping); mapping_set_large_folios(inode->i_mapping); switch (mode & S_IFMT) { @@ -2598,7 +2751,7 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd, int ret; pgoff_t max_off; - if (shmem_inode_acct_block(inode, 1)) { + if (shmem_inode_acct_blocks(inode, 1)) { /* * We may have got a page, returned -ENOENT triggering a retry, * and now we find ourselves with -ENOMEM. Release the page, to @@ -2613,7 +2766,7 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd, if (!*foliop) { ret = -ENOMEM; - folio = shmem_alloc_folio(gfp, info, pgoff); + folio = shmem_alloc_folio(gfp, 0, info, pgoff); if (!folio) goto out_unacct_blocks; @@ -2670,8 +2823,10 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd, if (unlikely(pgoff >= max_off)) goto out_release; - ret = shmem_add_to_page_cache(folio, mapping, pgoff, NULL, - gfp & GFP_RECLAIM_MASK, dst_vma->vm_mm); + ret = mem_cgroup_charge(folio, dst_vma->vm_mm, gfp); + if (ret) + goto out_release; + ret = shmem_add_to_page_cache(folio, mapping, pgoff, NULL, gfp); if (ret) goto out_release; @@ -2719,7 +2874,6 @@ shmem_write_begin(struct file *file, struct address_space *mapping, } ret = shmem_get_folio(inode, index, &folio, SGP_WRITE); - if (ret) return ret; @@ -3251,8 +3405,7 @@ shmem_mknod(struct mnt_idmap *idmap, struct inode *dir, error = simple_acl_create(dir, inode); if (error) goto out_iput; - error = security_inode_init_security(inode, dir, - &dentry->d_name, + error = security_inode_init_security(inode, dir, &dentry->d_name, shmem_initxattrs, NULL); if (error && error != -EOPNOTSUPP) goto out_iput; @@ -3281,14 +3434,11 @@ shmem_tmpfile(struct mnt_idmap *idmap, struct inode *dir, int error; inode = shmem_get_inode(idmap, dir->i_sb, dir, mode, 0, VM_NORESERVE); - if (IS_ERR(inode)) { error = PTR_ERR(inode); goto err_out; } - - error = security_inode_init_security(inode, dir, - NULL, + error = security_inode_init_security(inode, dir, NULL, shmem_initxattrs, NULL); if (error && error != -EOPNOTSUPP) goto out_iput; @@ -3325,7 +3475,8 @@ static int shmem_create(struct mnt_idmap *idmap, struct inode *dir, /* * Link a file.. */ -static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) +static int shmem_link(struct dentry *old_dentry, struct inode *dir, + struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); int ret = 0; @@ -3356,7 +3507,7 @@ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentr inode_inc_iversion(dir); inc_nlink(inode); ihold(inode); /* New dentry reference */ - dget(dentry); /* Extra pinning count for the created dentry */ + dget(dentry); /* Extra pinning count for the created dentry */ d_instantiate(dentry, inode); out: return ret; @@ -3376,7 +3527,7 @@ static int shmem_unlink(struct inode *dir, struct dentry *dentry) inode_set_ctime_current(inode)); inode_inc_iversion(dir); drop_nlink(inode); - dput(dentry); /* Undo the count from "create" - this does all the work */ + dput(dentry); /* Undo the count from "create" - does all the work */ return 0; } @@ -3486,7 +3637,6 @@ static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir, inode = shmem_get_inode(idmap, dir->i_sb, dir, S_IFLNK | 0777, 0, VM_NORESERVE); - if (IS_ERR(inode)) return PTR_ERR(inode); @@ -3509,10 +3659,10 @@ static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir, inode->i_op = &shmem_short_symlink_operations; } else { inode_nohighmem(inode); + inode->i_mapping->a_ops = &shmem_aops; error = shmem_get_folio(inode, 0, &folio, SGP_WRITE); if (error) goto out_remove_offset; - inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_symlink_inode_operations; memcpy(folio_address(folio), symname, len); folio_mark_uptodate(folio); @@ -3540,8 +3690,7 @@ static void shmem_put_link(void *arg) folio_put(arg); } -static const char *shmem_get_link(struct dentry *dentry, - struct inode *inode, +static const char *shmem_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct folio *folio = NULL; @@ -3615,8 +3764,7 @@ static int shmem_fileattr_set(struct mnt_idmap *idmap, * Callback for security_inode_init_security() for acquiring xattrs. */ static int shmem_initxattrs(struct inode *inode, - const struct xattr *xattr_array, - void *fs_info) + const struct xattr *xattr_array, void *fs_info) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); @@ -3800,7 +3948,6 @@ static struct dentry *shmem_find_alias(struct inode *inode) return alias ?: d_find_any_alias(inode); } - static struct dentry *shmem_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { @@ -4384,8 +4531,8 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc) } #endif /* CONFIG_TMPFS_QUOTA */ - inode = shmem_get_inode(&nop_mnt_idmap, sb, NULL, S_IFDIR | sbinfo->mode, 0, - VM_NORESERVE); + inode = shmem_get_inode(&nop_mnt_idmap, sb, NULL, + S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); if (IS_ERR(inode)) { error = PTR_ERR(inode); goto failed; @@ -4657,6 +4804,12 @@ void __init shmem_init(void) SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; else shmem_huge = SHMEM_HUGE_NEVER; /* just in case it was patched */ + + /* + * Default to setting PMD-sized THP to inherit the global setting and + * disable all other multi-size THPs. + */ + huge_shmem_orders_inherit = BIT(HPAGE_PMD_ORDER); #endif shmem_reliable_init(); @@ -4691,11 +4844,9 @@ static ssize_t shmem_enabled_show(struct kobject *kobj, for (i = 0; i < ARRAY_SIZE(values); i++) { len += sysfs_emit_at(buf, len, - shmem_huge == values[i] ? "%s[%s]" : "%s%s", - i ? " " : "", - shmem_format_huge(values[i])); + shmem_huge == values[i] ? "%s[%s]" : "%s%s", + i ? " " : "", shmem_format_huge(values[i])); } - len += sysfs_emit_at(buf, len, "\n"); return len; @@ -4721,6 +4872,11 @@ static ssize_t shmem_enabled_store(struct kobject *kobj, huge != SHMEM_HUGE_NEVER && huge != SHMEM_HUGE_DENY) return -EINVAL; + /* Do not override huge allocation policy with non-PMD sized mTHP */ + if (huge == SHMEM_HUGE_FORCE && + huge_shmem_orders_inherit != BIT(HPAGE_PMD_ORDER)) + return -EINVAL; + shmem_huge = huge; if (shmem_huge > SHMEM_HUGE_DENY) SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; @@ -4728,6 +4884,84 @@ static ssize_t shmem_enabled_store(struct kobject *kobj, } struct kobj_attribute shmem_enabled_attr = __ATTR_RW(shmem_enabled); +static DEFINE_SPINLOCK(huge_shmem_orders_lock); + +static ssize_t thpsize_shmem_enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + int order = to_thpsize(kobj)->order; + const char *output; + + if (test_bit(order, &huge_shmem_orders_always)) + output = "[always] inherit within_size advise never"; + else if (test_bit(order, &huge_shmem_orders_inherit)) + output = "always [inherit] within_size advise never"; + else if (test_bit(order, &huge_shmem_orders_within_size)) + output = "always inherit [within_size] advise never"; + else if (test_bit(order, &huge_shmem_orders_madvise)) + output = "always inherit within_size [advise] never"; + else + output = "always inherit within_size advise [never]"; + + return sysfs_emit(buf, "%s\n", output); +} + +static ssize_t thpsize_shmem_enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int order = to_thpsize(kobj)->order; + ssize_t ret = count; + + if (sysfs_streq(buf, "always")) { + spin_lock(&huge_shmem_orders_lock); + clear_bit(order, &huge_shmem_orders_inherit); + clear_bit(order, &huge_shmem_orders_madvise); + clear_bit(order, &huge_shmem_orders_within_size); + set_bit(order, &huge_shmem_orders_always); + spin_unlock(&huge_shmem_orders_lock); + } else if (sysfs_streq(buf, "inherit")) { + /* Do not override huge allocation policy with non-PMD sized mTHP */ + if (shmem_huge == SHMEM_HUGE_FORCE && + order != HPAGE_PMD_ORDER) + return -EINVAL; + + spin_lock(&huge_shmem_orders_lock); + clear_bit(order, &huge_shmem_orders_always); + clear_bit(order, &huge_shmem_orders_madvise); + clear_bit(order, &huge_shmem_orders_within_size); + set_bit(order, &huge_shmem_orders_inherit); + spin_unlock(&huge_shmem_orders_lock); + } else if (sysfs_streq(buf, "within_size")) { + spin_lock(&huge_shmem_orders_lock); + clear_bit(order, &huge_shmem_orders_always); + clear_bit(order, &huge_shmem_orders_inherit); + clear_bit(order, &huge_shmem_orders_madvise); + set_bit(order, &huge_shmem_orders_within_size); + spin_unlock(&huge_shmem_orders_lock); + } else if (sysfs_streq(buf, "advise")) { + spin_lock(&huge_shmem_orders_lock); + clear_bit(order, &huge_shmem_orders_always); + clear_bit(order, &huge_shmem_orders_inherit); + clear_bit(order, &huge_shmem_orders_within_size); + set_bit(order, &huge_shmem_orders_madvise); + spin_unlock(&huge_shmem_orders_lock); + } else if (sysfs_streq(buf, "never")) { + spin_lock(&huge_shmem_orders_lock); + clear_bit(order, &huge_shmem_orders_always); + clear_bit(order, &huge_shmem_orders_inherit); + clear_bit(order, &huge_shmem_orders_within_size); + clear_bit(order, &huge_shmem_orders_madvise); + spin_unlock(&huge_shmem_orders_lock); + } else { + ret = -EINVAL; + } + + return ret; +} + +struct kobj_attribute thpsize_shmem_enabled_attr = + __ATTR(shmem_enabled, 0644, thpsize_shmem_enabled_show, thpsize_shmem_enabled_store); #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_SYSFS */ #else /* !CONFIG_SHMEM */ @@ -4792,8 +5026,9 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range); #define shmem_acct_size(flags, size) 0 #define shmem_unacct_size(flags, size) do {} while (0) -static inline struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block *sb, struct inode *dir, - umode_t mode, dev_t dev, unsigned long flags) +static inline struct inode *shmem_get_inode(struct mnt_idmap *idmap, + struct super_block *sb, struct inode *dir, + umode_t mode, dev_t dev, unsigned long flags) { struct inode *inode = ramfs_get_inode(sb, dir, mode, dev); return inode ? inode : ERR_PTR(-ENOSPC); @@ -4803,8 +5038,8 @@ static inline struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct supe /* common code */ -static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, loff_t size, - unsigned long flags, unsigned int i_flags) +static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, + loff_t size, unsigned long flags, unsigned int i_flags) { struct inode *inode; struct file *res; @@ -4823,7 +5058,6 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l inode = shmem_get_inode(&nop_mnt_idmap, mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0, flags); - if (IS_ERR(inode)) { shmem_unacct_size(flags, size); return ERR_CAST(inode); @@ -4931,9 +5165,8 @@ struct folio *shmem_read_folio_gfp(struct address_space *mapping, struct folio *folio; int error; - BUG_ON(!shmem_mapping(mapping)); error = shmem_get_folio_gfp(inode, index, &folio, SGP_CACHE, - gfp, NULL, NULL, NULL); + gfp, NULL, NULL); if (error) return ERR_PTR(error);