diff options
Diffstat (limited to 'include/linux')
33 files changed, 840 insertions, 505 deletions
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 5466c96a33db..2ddb256187b5 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -82,11 +82,11 @@ extern nodemask_t cpuset_mems_allowed(struct task_struct *p); void cpuset_init_current_mems_allowed(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); -extern bool cpuset_node_allowed(int node, gfp_t gfp_mask); +extern bool cpuset_current_node_allowed(int node, gfp_t gfp_mask); static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { - return cpuset_node_allowed(zone_to_nid(z), gfp_mask); + return cpuset_current_node_allowed(zone_to_nid(z), gfp_mask); } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) @@ -173,6 +173,7 @@ static inline void set_mems_allowed(nodemask_t nodemask) task_unlock(current); } +extern bool cpuset_node_allowed(struct cgroup *cgroup, int nid); #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } @@ -293,6 +294,10 @@ static inline bool read_mems_allowed_retry(unsigned int seq) return false; } +static inline bool cpuset_node_allowed(struct cgroup *cgroup, int nid) +{ + return true; +} #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ diff --git a/include/linux/damon.h b/include/linux/damon.h index 47e36e6ea203..a4011726cb3b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -145,6 +145,8 @@ enum damos_action { * * @DAMOS_QUOTA_USER_INPUT: User-input value. * @DAMOS_QUOTA_SOME_MEM_PSI_US: System level some memory PSI in us. + * @DAMOS_QUOTA_NODE_MEM_USED_BP: MemUsed ratio of a node. + * @DAMOS_QUOTA_NODE_MEM_FREE_BP: MemFree ratio of a node. * @NR_DAMOS_QUOTA_GOAL_METRICS: Number of DAMOS quota goal metrics. * * Metrics equal to larger than @NR_DAMOS_QUOTA_GOAL_METRICS are unsupported. @@ -152,6 +154,8 @@ enum damos_action { enum damos_quota_goal_metric { DAMOS_QUOTA_USER_INPUT, DAMOS_QUOTA_SOME_MEM_PSI_US, + DAMOS_QUOTA_NODE_MEM_USED_BP, + DAMOS_QUOTA_NODE_MEM_FREE_BP, NR_DAMOS_QUOTA_GOAL_METRICS, }; @@ -161,6 +165,7 @@ enum damos_quota_goal_metric { * @target_value: Target value of @metric to achieve with the tuning. * @current_value: Current value of @metric. * @last_psi_total: Last measured total PSI + * @nid: Node id. * @list: List head for siblings. * * Data structure for getting the current score of the quota tuning goal. The @@ -179,6 +184,7 @@ struct damos_quota_goal { /* metric-dependent fields */ union { u64 last_psi_total; + int nid; }; struct list_head list; }; diff --git a/include/linux/fs.h b/include/linux/fs.h index 27c1eb1f8b37..da86fcb11882 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2189,6 +2189,7 @@ struct file_operations { int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, unsigned int poll_flags); + int (*mmap_prepare)(struct vm_area_desc *); } __randomize_layout; /* Supports async buffered reads */ @@ -2258,11 +2259,35 @@ struct inode_operations { struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; +/* Did the driver provide valid mmap hook configuration? */ +static inline bool file_has_valid_mmap_hooks(struct file *file) +{ + bool has_mmap = file->f_op->mmap; + bool has_mmap_prepare = file->f_op->mmap_prepare; + + /* Hooks are mutually exclusive. */ + if (WARN_ON_ONCE(has_mmap && has_mmap_prepare)) + return false; + if (!has_mmap && !has_mmap_prepare) + return false; + + return true; +} + static inline int call_mmap(struct file *file, struct vm_area_struct *vma) { + if (WARN_ON_ONCE(file->f_op->mmap_prepare)) + return -EINVAL; + return file->f_op->mmap(file, vma); } +static inline int __call_mmap_prepare(struct file *file, + struct vm_area_desc *desc) +{ + return file->f_op->mmap_prepare(desc); +} + extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, diff --git a/include/linux/gfp.h b/include/linux/gfp.h index c9fa6309c903..be160e8d8bcb 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -45,13 +45,13 @@ static inline bool gfpflags_allow_spinning(const gfp_t gfp_flags) * !__GFP_DIRECT_RECLAIM -> direct claim is not allowed. * !__GFP_KSWAPD_RECLAIM -> it's not safe to wake up kswapd. * All GFP_* flags including GFP_NOWAIT use one or both flags. - * try_alloc_pages() is the only API that doesn't specify either flag. + * alloc_pages_nolock() is the only API that doesn't specify either flag. * * This is stronger than GFP_NOWAIT or GFP_ATOMIC because * those are guaranteed to never block on a sleeping lock. * Here we are enforcing that the allocation doesn't ever spin * on any locks (i.e. only trylocks). There is no high level - * GFP_$FOO flag for this use in try_alloc_pages() as the + * GFP_$FOO flag for this use in alloc_pages_nolock() as the * regular page allocator doesn't fully support this * allocation mode. */ @@ -354,8 +354,8 @@ static inline struct page *alloc_page_vma_noprof(gfp_t gfp, } #define alloc_page_vma(...) alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__)) -struct page *try_alloc_pages_noprof(int nid, unsigned int order); -#define try_alloc_pages(...) alloc_hooks(try_alloc_pages_noprof(__VA_ARGS__)) +struct page *alloc_pages_nolock_noprof(int nid, unsigned int order); +#define alloc_pages_nolock(...) alloc_hooks(alloc_pages_nolock_noprof(__VA_ARGS__)) extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order); #define __get_free_pages(...) alloc_hooks(get_free_pages_noprof(__VA_ARGS__)) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index e893d546a49f..2f190c90192d 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -395,7 +395,7 @@ static inline int split_huge_page(struct page *page) void deferred_split_folio(struct folio *folio, bool partially_mapped); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze, struct folio *folio); + unsigned long address, bool freeze); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ @@ -403,12 +403,11 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd) \ || pmd_devmap(*____pmd)) \ __split_huge_pmd(__vma, __pmd, __address, \ - false, NULL); \ + false); \ } while (0) - void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, - bool freeze, struct folio *folio); + bool freeze); void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address); @@ -495,15 +494,13 @@ static inline bool is_huge_zero_pmd(pmd_t pmd) struct folio *mm_get_huge_zero_folio(struct mm_struct *mm); void mm_put_huge_zero_folio(struct mm_struct *mm); -#define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) - static inline bool thp_migration_supported(void) { return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); } void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmd, bool freeze, struct folio *folio); + pmd_t *pmd, bool freeze); bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct folio *folio); @@ -578,12 +575,12 @@ static inline void deferred_split_folio(struct folio *folio, bool partially_mapp do { } while (0) static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze, struct folio *folio) {} + unsigned long address, bool freeze) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, - unsigned long address, bool freeze, struct folio *folio) {} + unsigned long address, bool freeze) {} static inline void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, - bool freeze, struct folio *folio) {} + bool freeze) {} static inline bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 4861a7e304bb..0598f36931de 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -14,6 +14,7 @@ #include <linux/pgtable.h> #include <linux/gfp.h> #include <linux/userfaultfd_k.h> +#include <linux/nodemask.h> struct ctl_table; struct user_struct; @@ -128,12 +129,12 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *, struct vm_area_struct *); void unmap_hugepage_range(struct vm_area_struct *, - unsigned long, unsigned long, struct page *, - zap_flags_t); + unsigned long start, unsigned long end, + struct folio *, zap_flags_t); void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, - struct page *ref_page, zap_flags_t zap_flags); + struct folio *, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo_node(int nid); @@ -176,6 +177,8 @@ extern struct list_head huge_boot_pages[MAX_NUMNODES]; void hugetlb_bootmem_alloc(void); bool hugetlb_bootmem_allocated(void); +extern nodemask_t hugetlb_bootmem_nodes; +void hugetlb_bootmem_set_nodes(void); /* arch callbacks */ @@ -453,7 +456,7 @@ static inline long hugetlb_change_protection( static inline void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page, + unsigned long end, struct folio *folio, zap_flags_t zap_flags) { BUG(); @@ -700,7 +703,7 @@ struct huge_bootmem_page { bool hugetlb_bootmem_page_zones_valid(int nid, struct huge_bootmem_page *m); -int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); +int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list); int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn); void wait_for_freed_hugetlb_folios(void); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, @@ -1088,7 +1091,7 @@ static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, return NULL; } -static inline int isolate_or_dissolve_huge_page(struct page *page, +static inline int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list) { return -ENOMEM; diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 53ef1b6c8712..f03ee2b40816 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -374,6 +374,11 @@ struct kimage { bool is_ima_segment_index_set; #endif + struct { + struct kexec_segment *scratch; + phys_addr_t fdt; + } kho; + /* Core ELF header buffer */ void *elf_headers; unsigned long elf_headers_sz; diff --git a/include/linux/kexec_handover.h b/include/linux/kexec_handover.h new file mode 100644 index 000000000000..348844cffb13 --- /dev/null +++ b/include/linux/kexec_handover.h @@ -0,0 +1,109 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_KEXEC_HANDOVER_H +#define LINUX_KEXEC_HANDOVER_H + +#include <linux/types.h> +#include <linux/errno.h> + +struct kho_scratch { + phys_addr_t addr; + phys_addr_t size; +}; + +/* KHO Notifier index */ +enum kho_event { + KEXEC_KHO_FINALIZE = 0, + KEXEC_KHO_ABORT = 1, +}; + +struct folio; +struct notifier_block; + +#define DECLARE_KHOSER_PTR(name, type) \ + union { \ + phys_addr_t phys; \ + type ptr; \ + } name +#define KHOSER_STORE_PTR(dest, val) \ + ({ \ + typeof(val) v = val; \ + typecheck(typeof((dest).ptr), v); \ + (dest).phys = virt_to_phys(v); \ + }) +#define KHOSER_LOAD_PTR(src) \ + ({ \ + typeof(src) s = src; \ + (typeof((s).ptr))((s).phys ? phys_to_virt((s).phys) : NULL); \ + }) + +struct kho_serialization; + +#ifdef CONFIG_KEXEC_HANDOVER +bool kho_is_enabled(void); + +int kho_preserve_folio(struct folio *folio); +int kho_preserve_phys(phys_addr_t phys, size_t size); +struct folio *kho_restore_folio(phys_addr_t phys); +int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt); +int kho_retrieve_subtree(const char *name, phys_addr_t *phys); + +int register_kho_notifier(struct notifier_block *nb); +int unregister_kho_notifier(struct notifier_block *nb); + +void kho_memory_init(void); + +void kho_populate(phys_addr_t fdt_phys, u64 fdt_len, phys_addr_t scratch_phys, + u64 scratch_len); +#else +static inline bool kho_is_enabled(void) +{ + return false; +} + +static inline int kho_preserve_folio(struct folio *folio) +{ + return -EOPNOTSUPP; +} + +static inline int kho_preserve_phys(phys_addr_t phys, size_t size) +{ + return -EOPNOTSUPP; +} + +static inline struct folio *kho_restore_folio(phys_addr_t phys) +{ + return NULL; +} + +static inline int kho_add_subtree(struct kho_serialization *ser, + const char *name, void *fdt) +{ + return -EOPNOTSUPP; +} + +static inline int kho_retrieve_subtree(const char *name, phys_addr_t *phys) +{ + return -EOPNOTSUPP; +} + +static inline int register_kho_notifier(struct notifier_block *nb) +{ + return -EOPNOTSUPP; +} + +static inline int unregister_kho_notifier(struct notifier_block *nb) +{ + return -EOPNOTSUPP; +} + +static inline void kho_memory_init(void) +{ +} + +static inline void kho_populate(phys_addr_t fdt_phys, u64 fdt_len, + phys_addr_t scratch_phys, u64 scratch_len) +{ +} +#endif /* CONFIG_KEXEC_HANDOVER */ + +#endif /* LINUX_KEXEC_HANDOVER_H */ diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 1f46046080f5..b8d69cfbb58b 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -15,16 +15,8 @@ extern void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags); extern void khugepaged_min_free_kbytes_update(void); extern bool current_is_khugepaged(void); -#ifdef CONFIG_SHMEM extern int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool install_pmd); -#else -static inline int collapse_pte_mapped_thp(struct mm_struct *mm, - unsigned long addr, bool install_pmd) -{ - return 0; -} -#endif static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) { diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index cbbcd18d4186..9ef129038224 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -463,6 +463,8 @@ struct ma_wr_state { void __rcu **slots; /* mas->node->slots pointer */ void *entry; /* The entry to write */ void *content; /* The existing entry that is being overwritten */ + unsigned char vacant_height; /* Height of lowest node with free space */ + unsigned char sufficient_height;/* Height of lowest node with min sufficiency + 1 nodes */ }; #define mas_lock(mas) spin_lock(&((mas)->tree->ma_lock)) @@ -498,6 +500,8 @@ struct ma_wr_state { .mas = ma_state, \ .content = NULL, \ .entry = wr_entry, \ + .vacant_height = 0, \ + .sufficient_height = 0 \ } #define MA_TOPIARY(name, tree) \ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index ef5a1ecc6e59..bb19a2534224 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -42,6 +42,14 @@ extern unsigned long long max_possible_pfn; * kernel resource tree. * @MEMBLOCK_RSRV_NOINIT: memory region for which struct pages are * not initialized (only for reserved regions). + * @MEMBLOCK_RSRV_KERN: memory region that is reserved for kernel use, + * either explictitly with memblock_reserve_kern() or via memblock + * allocation APIs. All memblock allocations set this flag. + * @MEMBLOCK_KHO_SCRATCH: memory region that kexec can pass to the next + * kernel in handover mode. During early boot, we do not know about all + * memory reservations yet, so we get scratch memory from the previous + * kernel that we know is good to use. It is the only memory that + * allocations may happen from in this phase. */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ @@ -50,6 +58,8 @@ enum memblock_flags { MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */ MEMBLOCK_DRIVER_MANAGED = 0x8, /* always detected via a driver */ MEMBLOCK_RSRV_NOINIT = 0x10, /* don't initialize struct pages */ + MEMBLOCK_RSRV_KERN = 0x20, /* memory reserved for kernel use */ + MEMBLOCK_KHO_SCRATCH = 0x40, /* scratch memory for kexec handover */ }; /** @@ -116,7 +126,19 @@ int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid, int memblock_add(phys_addr_t base, phys_addr_t size); int memblock_remove(phys_addr_t base, phys_addr_t size); int memblock_phys_free(phys_addr_t base, phys_addr_t size); -int memblock_reserve(phys_addr_t base, phys_addr_t size); +int __memblock_reserve(phys_addr_t base, phys_addr_t size, int nid, + enum memblock_flags flags); + +static __always_inline int memblock_reserve(phys_addr_t base, phys_addr_t size) +{ + return __memblock_reserve(base, size, NUMA_NO_NODE, 0); +} + +static __always_inline int memblock_reserve_kern(phys_addr_t base, phys_addr_t size) +{ + return __memblock_reserve(base, size, NUMA_NO_NODE, MEMBLOCK_RSRV_KERN); +} + #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP int memblock_physmem_add(phys_addr_t base, phys_addr_t size); #endif @@ -132,6 +154,8 @@ int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); int memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size); +int memblock_mark_kho_scratch(phys_addr_t base, phys_addr_t size); +int memblock_clear_kho_scratch(phys_addr_t base, phys_addr_t size); void memblock_free(void *ptr, size_t size); void reset_all_zones_managed_pages(void); @@ -275,6 +299,11 @@ static inline bool memblock_is_driver_managed(struct memblock_region *m) return m->flags & MEMBLOCK_DRIVER_MANAGED; } +static inline bool memblock_is_kho_scratch(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_KHO_SCRATCH; +} + int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, @@ -476,6 +505,7 @@ static inline __init_memblock bool memblock_bottom_up(void) phys_addr_t memblock_phys_mem_size(void); phys_addr_t memblock_reserved_size(void); +phys_addr_t memblock_reserved_kern_size(phys_addr_t limit, int nid); unsigned long memblock_estimated_nr_free_pages(void); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); @@ -602,5 +632,14 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end) { } static inline void memtest_report_meminfo(struct seq_file *m) { } #endif +#ifdef CONFIG_MEMBLOCK_KHO_SCRATCH +void memblock_set_kho_scratch_only(void); +void memblock_clear_kho_scratch_only(void); +void memmap_init_kho_scratch_pages(void); +#else +static inline void memblock_set_kho_scratch_only(void) { } +static inline void memblock_clear_kho_scratch_only(void) { } +static inline void memmap_init_kho_scratch_pages(void) {} +#endif #endif /* _LINUX_MEMBLOCK_H */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 53364526d877..f7848f73f41c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -903,19 +903,9 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); -void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, - int val); - /* idx can be of type enum memcg_stat_item or node_stat_item */ -static inline void mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, int val) -{ - unsigned long flags; - - local_irq_save(flags); - __mod_memcg_state(memcg, idx, val); - local_irq_restore(flags); -} +void mod_memcg_state(struct mem_cgroup *memcg, + enum memcg_stat_item idx, int val); static inline void mod_memcg_page_state(struct page *page, enum memcg_stat_item idx, int val) @@ -952,19 +942,8 @@ static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, local_irq_restore(flags); } -void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, - unsigned long count); - -static inline void count_memcg_events(struct mem_cgroup *memcg, - enum vm_event_item idx, - unsigned long count) -{ - unsigned long flags; - - local_irq_save(flags); - __count_memcg_events(memcg, idx, count); - local_irq_restore(flags); -} +void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, + unsigned long count); static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) @@ -1057,6 +1036,7 @@ static inline u64 cgroup_id_from_mm(struct mm_struct *mm) return id; } +extern int mem_cgroup_init(void); #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 @@ -1374,12 +1354,6 @@ static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) { } -static inline void __mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, - int nr) -{ -} - static inline void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int nr) @@ -1433,12 +1407,6 @@ static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, } static inline void count_memcg_events(struct mem_cgroup *memcg, - enum vm_event_item idx, - unsigned long count) -{ -} - -static inline void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { @@ -1472,6 +1440,8 @@ static inline u64 cgroup_id_from_mm(struct mm_struct *mm) { return 0; } + +static inline int mem_cgroup_init(void) { return 0; } #endif /* CONFIG_MEMCG */ /* @@ -1736,6 +1706,8 @@ static inline void count_objcg_events(struct obj_cgroup *objcg, rcu_read_unlock(); } +bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid); + #else static inline bool mem_cgroup_kmem_disabled(void) { @@ -1793,6 +1765,15 @@ static inline void count_objcg_events(struct obj_cgroup *objcg, { } +static inline ino_t page_cgroup_ino(struct page *page) +{ + return 0; +} + +static inline bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid) +{ + return true; +} #endif /* CONFIG_MEMCG */ #if defined(CONFIG_MEMCG) && defined(CONFIG_ZSWAP) diff --git a/include/linux/memory.h b/include/linux/memory.h index 12daa6ec7d09..5ec4e6d209b9 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -149,6 +149,14 @@ static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) { return 0; } +static inline int memory_block_advise_max_size(unsigned long size) +{ + return -ENODEV; +} +static inline unsigned long memory_block_advised_max_size(void) +{ + return 0; +} #else /* CONFIG_MEMORY_HOTPLUG */ extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); @@ -181,6 +189,8 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, void memory_block_add_nid(struct memory_block *mem, int nid, enum meminit_context context); #endif /* CONFIG_NUMA */ +int memory_block_advise_max_size(unsigned long size); +unsigned long memory_block_advised_max_size(void); #endif /* CONFIG_MEMORY_HOTPLUG */ /* diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index ce9885e0178a..0fe96f3ab3ef 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -11,6 +11,7 @@ #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/spinlock.h> +#include <linux/node.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <uapi/linux/mempolicy.h> @@ -178,6 +179,9 @@ static inline bool mpol_is_preferred_many(struct mempolicy *pol) extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone); +extern int mempolicy_set_node_perf(unsigned int node, + struct access_coordinate *coords); + #else struct mempolicy {}; diff --git a/include/linux/mm.h b/include/linux/mm.h index e51dba8398f7..9e221ffcb868 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -12,6 +12,7 @@ #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/debug_locks.h> +#include <linux/compiler.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/range.h> @@ -356,9 +357,7 @@ extern unsigned int kobjsize(const void *objp); # define VM_SHADOW_STACK VM_NONE #endif -#if defined(CONFIG_X86) -# define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ -#elif defined(CONFIG_PPC64) +#if defined(CONFIG_PPC64) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 @@ -670,204 +669,11 @@ static inline void vma_numab_state_init(struct vm_area_struct *vma) {} static inline void vma_numab_state_free(struct vm_area_struct *vma) {} #endif /* CONFIG_NUMA_BALANCING */ -#ifdef CONFIG_PER_VMA_LOCK -static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) -{ -#ifdef CONFIG_DEBUG_LOCK_ALLOC - static struct lock_class_key lockdep_key; - - lockdep_init_map(&vma->vmlock_dep_map, "vm_lock", &lockdep_key, 0); -#endif - if (reset_refcnt) - refcount_set(&vma->vm_refcnt, 0); - vma->vm_lock_seq = UINT_MAX; -} - -static inline bool is_vma_writer_only(int refcnt) -{ - /* - * With a writer and no readers, refcnt is VMA_LOCK_OFFSET if the vma - * is detached and (VMA_LOCK_OFFSET + 1) if it is attached. Waiting on - * a detached vma happens only in vma_mark_detached() and is a rare - * case, therefore most of the time there will be no unnecessary wakeup. - */ - return refcnt & VMA_LOCK_OFFSET && refcnt <= VMA_LOCK_OFFSET + 1; -} - -static inline void vma_refcount_put(struct vm_area_struct *vma) -{ - /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */ - struct mm_struct *mm = vma->vm_mm; - int oldcnt; - - rwsem_release(&vma->vmlock_dep_map, _RET_IP_); - if (!__refcount_dec_and_test(&vma->vm_refcnt, &oldcnt)) { - - if (is_vma_writer_only(oldcnt - 1)) - rcuwait_wake_up(&mm->vma_writer_wait); - } -} - -/* - * Try to read-lock a vma. The function is allowed to occasionally yield false - * locked result to avoid performance overhead, in which case we fall back to - * using mmap_lock. The function should never yield false unlocked result. - * False locked result is possible if mm_lock_seq overflows or if vma gets - * reused and attached to a different mm before we lock it. - * Returns the vma on success, NULL on failure to lock and EAGAIN if vma got - * detached. - */ -static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, - struct vm_area_struct *vma) -{ - int oldcnt; - - /* - * Check before locking. A race might cause false locked result. - * We can use READ_ONCE() for the mm_lock_seq here, and don't need - * ACQUIRE semantics, because this is just a lockless check whose result - * we don't rely on for anything - the mm_lock_seq read against which we - * need ordering is below. - */ - if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(mm->mm_lock_seq.sequence)) - return NULL; - - /* - * If VMA_LOCK_OFFSET is set, __refcount_inc_not_zero_limited_acquire() - * will fail because VMA_REF_LIMIT is less than VMA_LOCK_OFFSET. - * Acquire fence is required here to avoid reordering against later - * vm_lock_seq check and checks inside lock_vma_under_rcu(). - */ - if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, - VMA_REF_LIMIT))) { - /* return EAGAIN if vma got detached from under us */ - return oldcnt ? NULL : ERR_PTR(-EAGAIN); - } - - rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); - /* - * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result. - * False unlocked result is impossible because we modify and check - * vma->vm_lock_seq under vma->vm_refcnt protection and mm->mm_lock_seq - * modification invalidates all existing locks. - * - * We must use ACQUIRE semantics for the mm_lock_seq so that if we are - * racing with vma_end_write_all(), we only start reading from the VMA - * after it has been unlocked. - * This pairs with RELEASE semantics in vma_end_write_all(). - */ - if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&mm->mm_lock_seq))) { - vma_refcount_put(vma); - return NULL; - } - - return vma; -} - /* - * Use only while holding mmap read lock which guarantees that locking will not - * fail (nobody can concurrently write-lock the vma). vma_start_read() should - * not be used in such cases because it might fail due to mm_lock_seq overflow. - * This functionality is used to obtain vma read lock and drop the mmap read lock. + * These must be here rather than mmap_lock.h as dependent on vm_fault type, + * declared in this header. */ -static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass) -{ - int oldcnt; - - mmap_assert_locked(vma->vm_mm); - if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, - VMA_REF_LIMIT))) - return false; - - rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); - return true; -} - -/* - * Use only while holding mmap read lock which guarantees that locking will not - * fail (nobody can concurrently write-lock the vma). vma_start_read() should - * not be used in such cases because it might fail due to mm_lock_seq overflow. - * This functionality is used to obtain vma read lock and drop the mmap read lock. - */ -static inline bool vma_start_read_locked(struct vm_area_struct *vma) -{ - return vma_start_read_locked_nested(vma, 0); -} - -static inline void vma_end_read(struct vm_area_struct *vma) -{ - vma_refcount_put(vma); -} - -/* WARNING! Can only be used if mmap_lock is expected to be write-locked */ -static bool __is_vma_write_locked(struct vm_area_struct *vma, unsigned int *mm_lock_seq) -{ - mmap_assert_write_locked(vma->vm_mm); - - /* - * current task is holding mmap_write_lock, both vma->vm_lock_seq and - * mm->mm_lock_seq can't be concurrently modified. - */ - *mm_lock_seq = vma->vm_mm->mm_lock_seq.sequence; - return (vma->vm_lock_seq == *mm_lock_seq); -} - -void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq); - -/* - * Begin writing to a VMA. - * Exclude concurrent readers under the per-VMA lock until the currently - * write-locked mmap_lock is dropped or downgraded. - */ -static inline void vma_start_write(struct vm_area_struct *vma) -{ - unsigned int mm_lock_seq; - - if (__is_vma_write_locked(vma, &mm_lock_seq)) - return; - - __vma_start_write(vma, mm_lock_seq); -} - -static inline void vma_assert_write_locked(struct vm_area_struct *vma) -{ - unsigned int mm_lock_seq; - - VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); -} - -static inline void vma_assert_locked(struct vm_area_struct *vma) -{ - unsigned int mm_lock_seq; - - VM_BUG_ON_VMA(refcount_read(&vma->vm_refcnt) <= 1 && - !__is_vma_write_locked(vma, &mm_lock_seq), vma); -} - -/* - * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these - * assertions should be made either under mmap_write_lock or when the object - * has been isolated under mmap_write_lock, ensuring no competing writers. - */ -static inline void vma_assert_attached(struct vm_area_struct *vma) -{ - WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt)); -} - -static inline void vma_assert_detached(struct vm_area_struct *vma) -{ - WARN_ON_ONCE(refcount_read(&vma->vm_refcnt)); -} - -static inline void vma_mark_attached(struct vm_area_struct *vma) -{ - vma_assert_write_locked(vma); - vma_assert_detached(vma); - refcount_set_release(&vma->vm_refcnt, 1); -} - -void vma_mark_detached(struct vm_area_struct *vma); - +#ifdef CONFIG_PER_VMA_LOCK static inline void release_fault_lock(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) @@ -883,36 +689,7 @@ static inline void assert_fault_locked(struct vm_fault *vmf) else mmap_assert_locked(vmf->vma->vm_mm); } - -struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, - unsigned long address); - -#else /* CONFIG_PER_VMA_LOCK */ - -static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) {} -static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, - struct vm_area_struct *vma) - { return NULL; } -static inline void vma_end_read(struct vm_area_struct *vma) {} -static inline void vma_start_write(struct vm_area_struct *vma) {} -static inline void vma_assert_write_locked(struct vm_area_struct *vma) - { mmap_assert_write_locked(vma->vm_mm); } -static inline void vma_assert_attached(struct vm_area_struct *vma) {} -static inline void vma_assert_detached(struct vm_area_struct *vma) {} -static inline void vma_mark_attached(struct vm_area_struct *vma) {} -static inline void vma_mark_detached(struct vm_area_struct *vma) {} - -static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, - unsigned long address) -{ - return NULL; -} - -static inline void vma_assert_locked(struct vm_area_struct *vma) -{ - mmap_assert_locked(vma->vm_mm); -} - +#else static inline void release_fault_lock(struct vm_fault *vmf) { mmap_read_unlock(vmf->vma->vm_mm); @@ -922,7 +699,6 @@ static inline void assert_fault_locked(struct vm_fault *vmf) { mmap_assert_locked(vmf->vma->vm_mm); } - #endif /* CONFIG_PER_VMA_LOCK */ extern const struct vm_operations_struct vma_dummy_vm_ops; @@ -1459,7 +1235,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); +vm_fault_t do_set_pmd(struct vm_fault *vmf, struct folio *folio, struct page *page); void set_pte_range(struct vm_fault *vmf, struct folio *folio, struct page *page, unsigned int nr, unsigned long addr); @@ -2004,6 +1780,45 @@ static inline struct folio *pfn_folio(unsigned long pfn) return page_folio(pfn_to_page(pfn)); } +#ifdef CONFIG_MMU +static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) +{ + return pfn_pte(page_to_pfn(page), pgprot); +} + +/** + * folio_mk_pte - Create a PTE for this folio + * @folio: The folio to create a PTE for + * @pgprot: The page protection bits to use + * + * Create a page table entry for the first page of this folio. + * This is suitable for passing to set_ptes(). + * + * Return: A page table entry suitable for mapping this folio. + */ +static inline pte_t folio_mk_pte(struct folio *folio, pgprot_t pgprot) +{ + return pfn_pte(folio_pfn(folio), pgprot); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/** + * folio_mk_pmd - Create a PMD for this folio + * @folio: The folio to create a PMD for + * @pgprot: The page protection bits to use + * + * Create a page table entry for the first page of this folio. + * This is suitable for passing to set_pmd_at(). + * + * Return: A page table entry suitable for mapping this folio. + */ +static inline pmd_t folio_mk_pmd(struct folio *folio, pgprot_t pgprot) +{ + return pmd_mkhuge(pfn_pmd(folio_pfn(folio), pgprot)); +} +#endif +#endif /* CONFIG_MMU */ + static inline bool folio_has_pincount(const struct folio *folio) { if (IS_ENABLED(CONFIG_64BIT)) @@ -2185,15 +2000,6 @@ static inline long compound_nr(struct page *page) } /** - * thp_nr_pages - The number of regular pages in this huge page. - * @page: The head page of a huge page. - */ -static inline long thp_nr_pages(struct page *page) -{ - return folio_nr_pages((struct folio *)page); -} - -/** * folio_next - Move to the next physical folio. * @folio: The folio we're currently operating on. * @@ -2303,7 +2109,62 @@ static inline bool folio_maybe_mapped_shared(struct folio *folio) */ if (mapcount <= 1) return false; - return folio_test_large_maybe_mapped_shared(folio); + return test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids); +} + +/** + * folio_expected_ref_count - calculate the expected folio refcount + * @folio: the folio + * + * Calculate the expected folio refcount, taking references from the pagecache, + * swapcache, PG_private and page table mappings into account. Useful in + * combination with folio_ref_count() to detect unexpected references (e.g., + * GUP or other temporary references). + * + * Does currently not consider references from the LRU cache. If the folio + * was isolated from the LRU (which is the case during migration or split), + * the LRU cache does not apply. + * + * Calling this function on an unmapped folio -- !folio_mapped() -- that is + * locked will return a stable result. + * + * Calling this function on a mapped folio will not result in a stable result, + * because nothing stops additional page table mappings from coming (e.g., + * fork()) or going (e.g., munmap()). + * + * Calling this function without the folio lock will also not result in a + * stable result: for example, the folio might get dropped from the swapcache + * concurrently. + * + * However, even when called without the folio lock or on a mapped folio, + * this function can be used to detect unexpected references early (for example, + * if it makes sense to even lock the folio and unmap it). + * + * The caller must add any reference (e.g., from folio_try_get()) it might be + * holding itself to the result. + * + * Returns the expected folio refcount. + */ +static inline int folio_expected_ref_count(const struct folio *folio) +{ + const int order = folio_order(folio); + int ref_count = 0; + + if (WARN_ON_ONCE(folio_test_slab(folio))) + return 0; + + if (folio_test_anon(folio)) { + /* One reference per page from the swapcache. */ + ref_count += folio_test_swapcache(folio) << order; + } else if (!((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS)) { + /* One reference per page from the pagecache. */ + ref_count += !!folio->mapping << order; + /* One reference from PG_private. */ + ref_count += folio_test_private(folio); + } + + /* One reference per page table mapping. */ + return ref_count + folio_mapcount(folio); } #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE @@ -2406,7 +2267,6 @@ static inline void clear_page_pfmemalloc(struct page *page) extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) -#define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1)) #define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1)) /* @@ -2767,7 +2627,7 @@ static inline void update_hiwater_rss(struct mm_struct *mm) { unsigned long _rss = get_mm_rss(mm); - if ((mm)->hiwater_rss < _rss) + if (data_race(mm->hiwater_rss) < _rss) (mm)->hiwater_rss = _rss; } @@ -3117,9 +2977,10 @@ static inline void pagetable_dtor_free(struct ptdesc *ptdesc) pagetable_free(ptdesc); } -static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) +static inline bool pagetable_pte_ctor(struct mm_struct *mm, + struct ptdesc *ptdesc) { - if (!ptlock_init(ptdesc)) + if (mm != &init_mm && !ptlock_init(ptdesc)) return false; __pagetable_ctor(ptdesc); return true; @@ -3223,9 +3084,10 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) return ptl; } -static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) +static inline bool pagetable_pmd_ctor(struct mm_struct *mm, + struct ptdesc *ptdesc) { - if (!pmd_ptlock_init(ptdesc)) + if (mm != &init_mm && !pmd_ptlock_init(ptdesc)) return false; ptdesc_pmd_pts_init(ptdesc); __pagetable_ctor(ptdesc); @@ -3414,7 +3276,6 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void exit_mmap(struct mm_struct *); -int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift); bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, bool write); diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index f9157a0c42a5..89b518ff097e 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -447,6 +447,8 @@ static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, #endif /* CONFIG_ANON_VMA_NAME */ +void pfnmap_track_ctx_release(struct kref *ref); + static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 32ba5126e221..d3cffd8828c9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -28,7 +28,6 @@ #endif #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1)) -#define INIT_PASID 0 struct address_space; struct futex_private_hash; @@ -765,6 +764,38 @@ struct vma_numab_state { int prev_scan_seq; }; +#ifdef __HAVE_PFNMAP_TRACKING +struct pfnmap_track_ctx { + struct kref kref; + unsigned long pfn; + unsigned long size; /* in bytes */ +}; +#endif + +/* + * Describes a VMA that is about to be mmap()'ed. Drivers may choose to + * manipulate mutable fields which will cause those fields to be updated in the + * resultant VMA. + * + * Helper functions are not required for manipulating any field. + */ +struct vm_area_desc { + /* Immutable state. */ + struct mm_struct *mm; + unsigned long start; + unsigned long end; + + /* Mutable fields. Populated with initial state. */ + pgoff_t pgoff; + struct file *file; + vm_flags_t vm_flags; + pgprot_t page_prot; + + /* Write-only fields. */ + const struct vm_operations_struct *vm_ops; + void *private_data; +}; + /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -878,6 +909,9 @@ struct vm_area_struct { struct anon_vma_name *anon_name; #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; +#ifdef __HAVE_PFNMAP_TRACKING + struct pfnmap_track_ctx *pfnmap_track_ctx; +#endif } __randomize_layout; #ifdef CONFIG_NUMA diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index e0eddfd306ef..5da384bd0a26 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -1,6 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMAP_LOCK_H #define _LINUX_MMAP_LOCK_H +/* Avoid a dependency loop by declaring here. */ +extern int rcuwait_wake_up(struct rcuwait *w); + #include <linux/lockdep.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> @@ -105,6 +109,206 @@ static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int return read_seqcount_retry(&mm->mm_lock_seq, seq); } +static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + static struct lock_class_key lockdep_key; + + lockdep_init_map(&vma->vmlock_dep_map, "vm_lock", &lockdep_key, 0); +#endif + if (reset_refcnt) + refcount_set(&vma->vm_refcnt, 0); + vma->vm_lock_seq = UINT_MAX; +} + +static inline bool is_vma_writer_only(int refcnt) +{ + /* + * With a writer and no readers, refcnt is VMA_LOCK_OFFSET if the vma + * is detached and (VMA_LOCK_OFFSET + 1) if it is attached. Waiting on + * a detached vma happens only in vma_mark_detached() and is a rare + * case, therefore most of the time there will be no unnecessary wakeup. + */ + return refcnt & VMA_LOCK_OFFSET && refcnt <= VMA_LOCK_OFFSET + 1; +} + +static inline void vma_refcount_put(struct vm_area_struct *vma) +{ + /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */ + struct mm_struct *mm = vma->vm_mm; + int oldcnt; + + rwsem_release(&vma->vmlock_dep_map, _RET_IP_); + if (!__refcount_dec_and_test(&vma->vm_refcnt, &oldcnt)) { + + if (is_vma_writer_only(oldcnt - 1)) + rcuwait_wake_up(&mm->vma_writer_wait); + } +} + +/* + * Try to read-lock a vma. The function is allowed to occasionally yield false + * locked result to avoid performance overhead, in which case we fall back to + * using mmap_lock. The function should never yield false unlocked result. + * False locked result is possible if mm_lock_seq overflows or if vma gets + * reused and attached to a different mm before we lock it. + * Returns the vma on success, NULL on failure to lock and EAGAIN if vma got + * detached. + */ +static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, + struct vm_area_struct *vma) +{ + int oldcnt; + + /* + * Check before locking. A race might cause false locked result. + * We can use READ_ONCE() for the mm_lock_seq here, and don't need + * ACQUIRE semantics, because this is just a lockless check whose result + * we don't rely on for anything - the mm_lock_seq read against which we + * need ordering is below. + */ + if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(mm->mm_lock_seq.sequence)) + return NULL; + + /* + * If VMA_LOCK_OFFSET is set, __refcount_inc_not_zero_limited_acquire() + * will fail because VMA_REF_LIMIT is less than VMA_LOCK_OFFSET. + * Acquire fence is required here to avoid reordering against later + * vm_lock_seq check and checks inside lock_vma_under_rcu(). + */ + if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, + VMA_REF_LIMIT))) { + /* return EAGAIN if vma got detached from under us */ + return oldcnt ? NULL : ERR_PTR(-EAGAIN); + } + + rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); + /* + * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result. + * False unlocked result is impossible because we modify and check + * vma->vm_lock_seq under vma->vm_refcnt protection and mm->mm_lock_seq + * modification invalidates all existing locks. + * + * We must use ACQUIRE semantics for the mm_lock_seq so that if we are + * racing with vma_end_write_all(), we only start reading from the VMA + * after it has been unlocked. + * This pairs with RELEASE semantics in vma_end_write_all(). + */ + if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&mm->mm_lock_seq))) { + vma_refcount_put(vma); + return NULL; + } + + return vma; +} + +/* + * Use only while holding mmap read lock which guarantees that locking will not + * fail (nobody can concurrently write-lock the vma). vma_start_read() should + * not be used in such cases because it might fail due to mm_lock_seq overflow. + * This functionality is used to obtain vma read lock and drop the mmap read lock. + */ +static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass) +{ + int oldcnt; + + mmap_assert_locked(vma->vm_mm); + if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, + VMA_REF_LIMIT))) + return false; + + rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); + return true; +} + +/* + * Use only while holding mmap read lock which guarantees that locking will not + * fail (nobody can concurrently write-lock the vma). vma_start_read() should + * not be used in such cases because it might fail due to mm_lock_seq overflow. + * This functionality is used to obtain vma read lock and drop the mmap read lock. + */ +static inline bool vma_start_read_locked(struct vm_area_struct *vma) +{ + return vma_start_read_locked_nested(vma, 0); +} + +static inline void vma_end_read(struct vm_area_struct *vma) +{ + vma_refcount_put(vma); +} + +/* WARNING! Can only be used if mmap_lock is expected to be write-locked */ +static bool __is_vma_write_locked(struct vm_area_struct *vma, unsigned int *mm_lock_seq) +{ + mmap_assert_write_locked(vma->vm_mm); + + /* + * current task is holding mmap_write_lock, both vma->vm_lock_seq and + * mm->mm_lock_seq can't be concurrently modified. + */ + *mm_lock_seq = vma->vm_mm->mm_lock_seq.sequence; + return (vma->vm_lock_seq == *mm_lock_seq); +} + +void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq); + +/* + * Begin writing to a VMA. + * Exclude concurrent readers under the per-VMA lock until the currently + * write-locked mmap_lock is dropped or downgraded. + */ +static inline void vma_start_write(struct vm_area_struct *vma) +{ + unsigned int mm_lock_seq; + + if (__is_vma_write_locked(vma, &mm_lock_seq)) + return; + + __vma_start_write(vma, mm_lock_seq); +} + +static inline void vma_assert_write_locked(struct vm_area_struct *vma) +{ + unsigned int mm_lock_seq; + + VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); +} + +static inline void vma_assert_locked(struct vm_area_struct *vma) +{ + unsigned int mm_lock_seq; + + VM_BUG_ON_VMA(refcount_read(&vma->vm_refcnt) <= 1 && + !__is_vma_write_locked(vma, &mm_lock_seq), vma); +} + +/* + * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these + * assertions should be made either under mmap_write_lock or when the object + * has been isolated under mmap_write_lock, ensuring no competing writers. + */ +static inline void vma_assert_attached(struct vm_area_struct *vma) +{ + WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt)); +} + +static inline void vma_assert_detached(struct vm_area_struct *vma) +{ + WARN_ON_ONCE(refcount_read(&vma->vm_refcnt)); +} + +static inline void vma_mark_attached(struct vm_area_struct *vma) +{ + vma_assert_write_locked(vma); + vma_assert_detached(vma); + refcount_set_release(&vma->vm_refcnt, 1); +} + +void vma_mark_detached(struct vm_area_struct *vma); + +struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, + unsigned long address); + #else /* CONFIG_PER_VMA_LOCK */ static inline void mm_lock_seqcount_init(struct mm_struct *mm) {} @@ -120,6 +324,29 @@ static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int { return true; } +static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) {} +static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, + struct vm_area_struct *vma) + { return NULL; } +static inline void vma_end_read(struct vm_area_struct *vma) {} +static inline void vma_start_write(struct vm_area_struct *vma) {} +static inline void vma_assert_write_locked(struct vm_area_struct *vma) + { mmap_assert_write_locked(vma->vm_mm); } +static inline void vma_assert_attached(struct vm_area_struct *vma) {} +static inline void vma_assert_detached(struct vm_area_struct *vma) {} +static inline void vma_mark_attached(struct vm_area_struct *vma) {} +static inline void vma_mark_detached(struct vm_area_struct *vma) {} + +static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, + unsigned long address) +{ + return NULL; +} + +static inline void vma_assert_locked(struct vm_area_struct *vma) +{ + mmap_assert_locked(vma->vm_mm); +} #endif /* CONFIG_PER_VMA_LOCK */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b1c459f7a485..28066b4ced81 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -2074,11 +2074,37 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) return usage ? test_bit(idx, usage->subsection_map) : 0; } + +static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn) +{ + struct mem_section_usage *usage = READ_ONCE(ms->usage); + int idx = subsection_map_index(*pfn); + unsigned long bit; + + if (!usage) + return false; + + if (test_bit(idx, usage->subsection_map)) + return true; + + /* Find the next subsection that exists */ + bit = find_next_bit(usage->subsection_map, SUBSECTIONS_PER_SECTION, idx); + if (bit == SUBSECTIONS_PER_SECTION) + return false; + + *pfn = (*pfn & PAGE_SECTION_MASK) + (bit * PAGES_PER_SUBSECTION); + return true; +} #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { return 1; } + +static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn) +{ + return true; +} #endif void sparse_init_early_section(int nid, struct page *map, unsigned long pnum, @@ -2127,6 +2153,58 @@ static inline int pfn_valid(unsigned long pfn) return ret; } + +/* Returns end_pfn or higher if no valid PFN remaining in range */ +static inline unsigned long first_valid_pfn(unsigned long pfn, unsigned long end_pfn) +{ + unsigned long nr = pfn_to_section_nr(pfn); + + rcu_read_lock_sched(); + + while (nr <= __highest_present_section_nr && pfn < end_pfn) { + struct mem_section *ms = __pfn_to_section(pfn); + + if (valid_section(ms) && + (early_section(ms) || pfn_section_first_valid(ms, &pfn))) { + rcu_read_unlock_sched(); + return pfn; + } + + /* Nothing left in this section? Skip to next section */ + nr++; + pfn = section_nr_to_pfn(nr); + } + + rcu_read_unlock_sched(); + return end_pfn; +} + +static inline unsigned long next_valid_pfn(unsigned long pfn, unsigned long end_pfn) +{ + pfn++; + + if (pfn >= end_pfn) + return end_pfn; + + /* + * Either every PFN within the section (or subsection for VMEMMAP) is + * valid, or none of them are. So there's no point repeating the check + * for every PFN; only call first_valid_pfn() again when crossing a + * (sub)section boundary (i.e. !(pfn & ~PAGE_{SUB,}SECTION_MASK)). + */ + if (pfn & ~(IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP) ? + PAGE_SUBSECTION_MASK : PAGE_SECTION_MASK)) + return pfn; + + return first_valid_pfn(pfn, end_pfn); +} + + +#define for_each_valid_pfn(_pfn, _start_pfn, _end_pfn) \ + for ((_pfn) = first_valid_pfn((_start_pfn), (_end_pfn)); \ + (_pfn) < (_end_pfn); \ + (_pfn) = next_valid_pfn((_pfn), (_end_pfn))) + #endif static inline int pfn_in_present_section(unsigned long pfn) @@ -2176,6 +2254,16 @@ void sparse_init(void); #define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ +/* + * Fallback case for when the architecture provides its own pfn_valid() but + * not a corresponding for_each_valid_pfn(). + */ +#ifndef for_each_valid_pfn +#define for_each_valid_pfn(_pfn, _start_pfn, _end_pfn) \ + for ((_pfn) = (_start_pfn); (_pfn) < (_end_pfn); (_pfn)++) \ + if (pfn_valid(_pfn)) +#endif + #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ diff --git a/include/linux/numa_memblks.h b/include/linux/numa_memblks.h index dd85613cdd86..991076cba7c5 100644 --- a/include/linux/numa_memblks.h +++ b/include/linux/numa_memblks.h @@ -22,6 +22,7 @@ struct numa_meminfo { }; int __init numa_add_memblk(int nodeid, u64 start, u64 end); +int __init numa_add_reserved_memblk(int nid, u64 start, u64 end); void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi); int __init numa_cleanup_meminfo(struct numa_meminfo *mi); diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index 4f5c9e979bb9..760006b1c480 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -72,8 +72,10 @@ #define NODE_NOT_IN_PAGE_FLAGS 1 #endif -#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) +#if defined(CONFIG_KASAN_SW_TAGS) #define KASAN_TAG_WIDTH 8 +#elif defined(CONFIG_KASAN_HW_TAGS) +#define KASAN_TAG_WIDTH 4 #else #define KASAN_TAG_WIDTH 0 #endif diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 3b814ce08331..4fe5ee67535b 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -915,20 +915,6 @@ FOLIO_FLAG_FALSE(partially_mapped) #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* - * PageHuge() only returns true for hugetlbfs pages, but not for - * normal or transparent huge pages. - * - * PageTransHuge() returns true for both transparent huge and - * hugetlbfs pages, but not normal pages. PageTransHuge() can only be - * called only in the core VM paths where hugetlbfs pages can't exist. - */ -static inline int PageTransHuge(const struct page *page) -{ - VM_BUG_ON_PAGE(PageTail(page), page); - return PageHead(page); -} - -/* * PageTransCompound returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. @@ -938,7 +924,6 @@ static inline int PageTransCompound(const struct page *page) return PageCompound(page); } #else -TESTPAGEFLAG_FALSE(TransHuge, transhuge) TESTPAGEFLAG_FALSE(TransCompound, transcompound) #endif @@ -989,7 +974,7 @@ static inline bool page_mapcount_is_type(unsigned int mapcount) static inline bool page_has_type(const struct page *page) { - return page_mapcount_is_type(data_race(page->page_type)); + return page_type_has_type(data_race(page->page_type)); } #define FOLIO_TYPE_OPS(lname, fname) \ @@ -1237,10 +1222,6 @@ static inline int folio_has_private(const struct folio *folio) return !!(folio->flags & PAGE_FLAGS_PRIVATE); } -static inline bool folio_test_large_maybe_mapped_shared(const struct folio *folio) -{ - return test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids); -} #undef PF_ANY #undef PF_HEAD #undef PF_NO_TAIL diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 26baa78f1ca7..d2ced9920992 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -533,7 +533,6 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) } struct address_space *folio_mapping(struct folio *); -struct address_space *swapcache_mapping(struct folio *); /** * folio_flush_mapping - Find the file mapping this folio belongs to. @@ -884,26 +883,6 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, mapping_gfp_mask(mapping)); } -extern pgoff_t __folio_swap_cache_index(struct folio *folio); - -/** - * folio_index - File index of a folio. - * @folio: The folio. - * - * For a folio which is either in the page cache or the swap cache, - * return its index within the address_space it belongs to. If you know - * the page is definitely in the page cache, you can look at the folio's - * index directly. - * - * Return: The index (offset in units of pages) of a folio in its file. - */ -static inline pgoff_t folio_index(struct folio *folio) -{ - if (unlikely(folio_test_swapcache(folio))) - return __folio_swap_cache_index(folio); - return folio->index; -} - /** * folio_next_index - Get the index of the next folio. * @folio: The current folio. @@ -935,27 +914,14 @@ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) * @folio: The folio. * @index: The page index within the file. * - * Context: The caller should have the page locked in order to prevent - * (eg) shmem from moving the page between the page cache and swap cache - * and changing its index in the middle of the operation. + * Context: The caller should have the folio locked and ensure + * e.g., shmem did not move this folio to the swap cache. * Return: true or false. */ static inline bool folio_contains(struct folio *folio, pgoff_t index) { - return index - folio_index(folio) < folio_nr_pages(folio); -} - -/* - * Given the page we found in the page cache, return the page corresponding - * to this index in the file - */ -static inline struct page *find_subpage(struct page *head, pgoff_t index) -{ - /* HugeTLBfs wants the head page regardless */ - if (PageHuge(head)) - return head; - - return head + (index & (thp_nr_pages(head) - 1)); + VM_WARN_ON_ONCE_FOLIO(folio_test_swapcache(folio), folio); + return index - folio->index < folio_nr_pages(folio); } unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, @@ -1308,9 +1274,9 @@ static inline bool filemap_range_needs_writeback(struct address_space *mapping, * struct readahead_control - Describes a readahead request. * * A readahead request is for consecutive pages. Filesystems which - * implement the ->readahead method should call readahead_page() or - * readahead_page_batch() in a loop and attempt to start I/O against - * each page in the request. + * implement the ->readahead method should call readahead_folio() or + * __readahead_batch() in a loop and attempt to start reads into each + * folio in the request. * * Most of the fields in this struct are private and should be accessed * by the functions below. @@ -1416,22 +1382,6 @@ static inline struct folio *__readahead_folio(struct readahead_control *ractl) } /** - * readahead_page - Get the next page to read. - * @ractl: The current readahead request. - * - * Context: The page is locked and has an elevated refcount. The caller - * should decreases the refcount once the page has been submitted for I/O - * and unlock the page once all I/O to that page has completed. - * Return: A pointer to the next page, or %NULL if we are done. - */ -static inline struct page *readahead_page(struct readahead_control *ractl) -{ - struct folio *folio = __readahead_folio(ractl); - - return &folio->page; -} - -/** * readahead_folio - Get the next folio to read. * @ractl: The current readahead request. * @@ -1453,7 +1403,7 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, { unsigned int i = 0; XA_STATE(xas, &rac->mapping->i_pages, 0); - struct page *page; + struct folio *folio; BUG_ON(rac->_batch_count > rac->_nr_pages); rac->_nr_pages -= rac->_batch_count; @@ -1462,13 +1412,12 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, xas_set(&xas, rac->_index); rcu_read_lock(); - xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) { - if (xas_retry(&xas, page)) + xas_for_each(&xas, folio, rac->_index + rac->_nr_pages - 1) { + if (xas_retry(&xas, folio)) continue; - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(PageTail(page), page); - array[i++] = page; - rac->_batch_count += thp_nr_pages(page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + array[i++] = folio_page(folio, 0); + rac->_batch_count += folio_nr_pages(folio); if (i == array_sz) break; } @@ -1478,20 +1427,6 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, } /** - * readahead_page_batch - Get a batch of pages to read. - * @rac: The current readahead request. - * @array: An array of pointers to struct page. - * - * Context: The pages are locked and have an elevated refcount. The caller - * should decreases the refcount once the page has been submitted for I/O - * and unlock the page once all I/O to that page has completed. - * Return: The number of pages placed in the array. 0 indicates the request - * is complete. - */ -#define readahead_page_batch(rac, array) \ - __readahead_batch(rac, array, ARRAY_SIZE(array)) - -/** * readahead_pos - The byte offset into the file of this readahead request. * @rac: The readahead request. */ diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 0aeb0e276a3e..c16cdeaa505e 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -375,7 +375,7 @@ do { \ } while (0) /* - * this_cpu operations (C) 2008-2013 Christoph Lameter <cl@linux.com> + * this_cpu operations (C) 2008-2013 Christoph Lameter <cl@gentwo.org> * * Optimized manipulation for memory allocated through the per cpu * allocator or for addresses of per cpu variables. diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index b50447ef1c92..0b6e1f781d86 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1164,10 +1164,6 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) } #endif -#ifndef __HAVE_ARCH_PGD_OFFSET_GATE -#define pgd_offset_gate(mm, addr) pgd_offset(mm, addr) -#endif - #ifndef __HAVE_ARCH_MOVE_PTE #define move_pte(pte, old_addr, new_addr) (pte) #endif @@ -1489,83 +1485,92 @@ static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) * vmf_insert_pfn. */ -/* - * track_pfn_remap is called when a _new_ pfn mapping is being established - * by remap_pfn_range() for physical range indicated by pfn and size. - */ -static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn, unsigned long addr, - unsigned long size) +static inline int pfnmap_setup_cachemode(unsigned long pfn, unsigned long size, + pgprot_t *prot) { return 0; } -/* - * track_pfn_insert is called when a _new_ single pfn is established - * by vmf_insert_pfn(). - */ -static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, - pfn_t pfn) +static inline int pfnmap_track(unsigned long pfn, unsigned long size, + pgprot_t *prot) { + return 0; } -/* - * track_pfn_copy is called when a VM_PFNMAP VMA is about to get the page - * tables copied during copy_page_range(). Will store the pfn to be - * passed to untrack_pfn_copy() only if there is something to be untracked. - * Callers should initialize the pfn to 0. - */ -static inline int track_pfn_copy(struct vm_area_struct *dst_vma, - struct vm_area_struct *src_vma, unsigned long *pfn) +static inline void pfnmap_untrack(unsigned long pfn, unsigned long size) { - return 0; } +#else +/** + * pfnmap_setup_cachemode - setup the cachemode in the pgprot for a pfn range + * @pfn: the start of the pfn range + * @size: the size of the pfn range in bytes + * @prot: the pgprot to modify + * + * Lookup the cachemode for the pfn range starting at @pfn with the size + * @size and store it in @prot, leaving other data in @prot unchanged. + * + * This allows for a hardware implementation to have fine-grained control of + * memory cache behavior at page level granularity. Without a hardware + * implementation, this function does nothing. + * + * Currently there is only one implementation for this - x86 Page Attribute + * Table (PAT). See Documentation/arch/x86/pat.rst for more details. + * + * This function can fail if the pfn range spans pfns that require differing + * cachemodes. If the pfn range was previously verified to have a single + * cachemode, it is sufficient to query only a single pfn. The assumption is + * that this is the case for drivers using the vmf_insert_pfn*() interface. + * + * Returns 0 on success and -EINVAL on error. + */ +int pfnmap_setup_cachemode(unsigned long pfn, unsigned long size, + pgprot_t *prot); -/* - * untrack_pfn_copy is called when a VM_PFNMAP VMA failed to copy during - * copy_page_range(), but after track_pfn_copy() was already called. Can - * be called even if track_pfn_copy() did not actually track anything: - * handled internally. +/** + * pfnmap_track - track a pfn range + * @pfn: the start of the pfn range + * @size: the size of the pfn range in bytes + * @prot: the pgprot to track + * + * Requested the pfn range to be 'tracked' by a hardware implementation and + * setup the cachemode in @prot similar to pfnmap_setup_cachemode(). + * + * This allows for fine-grained control of memory cache behaviour at page + * level granularity. Tracking memory this way is persisted across VMA splits + * (VMA merging does not apply for VM_PFNMAP). + * + * Currently, there is only one implementation for this - x86 Page Attribute + * Table (PAT). See Documentation/arch/x86/pat.rst for more details. + * + * Returns 0 on success and -EINVAL on error. */ -static inline void untrack_pfn_copy(struct vm_area_struct *dst_vma, - unsigned long pfn) -{ -} +int pfnmap_track(unsigned long pfn, unsigned long size, pgprot_t *prot); -/* - * untrack_pfn is called while unmapping a pfnmap for a region. - * untrack can be called for a specific region indicated by pfn and size or - * can be for the entire vma (in which case pfn, size are zero). +/** + * pfnmap_untrack - untrack a pfn range + * @pfn: the start of the pfn range + * @size: the size of the pfn range in bytes + * + * Untrack a pfn range previously tracked through pfnmap_track(). */ -static inline void untrack_pfn(struct vm_area_struct *vma, - unsigned long pfn, unsigned long size, - bool mm_wr_locked) -{ -} +void pfnmap_untrack(unsigned long pfn, unsigned long size); +#endif -/* - * untrack_pfn_clear is called in the following cases on a VM_PFNMAP VMA: +/** + * pfnmap_setup_cachemode_pfn - setup the cachemode in the pgprot for a pfn + * @pfn: the pfn + * @prot: the pgprot to modify + * + * Lookup the cachemode for @pfn and store it in @prot, leaving other + * data in @prot unchanged. * - * 1) During mremap() on the src VMA after the page tables were moved. - * 2) During fork() on the dst VMA, immediately after duplicating the src VMA. + * See pfnmap_setup_cachemode() for details. */ -static inline void untrack_pfn_clear(struct vm_area_struct *vma) +static inline void pfnmap_setup_cachemode_pfn(unsigned long pfn, pgprot_t *prot) { + pfnmap_setup_cachemode(pfn, PAGE_SIZE, prot); } -#else -extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn, unsigned long addr, - unsigned long size); -extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, - pfn_t pfn); -extern int track_pfn_copy(struct vm_area_struct *dst_vma, - struct vm_area_struct *src_vma, unsigned long *pfn); -extern void untrack_pfn_copy(struct vm_area_struct *dst_vma, - unsigned long pfn); -extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, - unsigned long size, bool mm_wr_locked); -extern void untrack_pfn_clear(struct vm_area_struct *vma); -#endif #ifdef CONFIG_MMU #ifdef __HAVE_COLOR_ZERO_PAGE diff --git a/include/linux/ptdump.h b/include/linux/ptdump.h index 8dbd51ea8626..240bd3bff18d 100644 --- a/include/linux/ptdump.h +++ b/include/linux/ptdump.h @@ -11,10 +11,17 @@ struct ptdump_range { }; struct ptdump_state { - /* level is 0:PGD to 4:PTE, or -1 if unknown */ - void (*note_page)(struct ptdump_state *st, unsigned long addr, - int level, u64 val); - void (*effective_prot)(struct ptdump_state *st, int level, u64 val); + void (*note_page_pte)(struct ptdump_state *st, unsigned long addr, pte_t pte); + void (*note_page_pmd)(struct ptdump_state *st, unsigned long addr, pmd_t pmd); + void (*note_page_pud)(struct ptdump_state *st, unsigned long addr, pud_t pud); + void (*note_page_p4d)(struct ptdump_state *st, unsigned long addr, p4d_t p4d); + void (*note_page_pgd)(struct ptdump_state *st, unsigned long addr, pgd_t pgd); + void (*note_page_flush)(struct ptdump_state *st); + void (*effective_prot_pte)(struct ptdump_state *st, pte_t pte); + void (*effective_prot_pmd)(struct ptdump_state *st, pmd_t pmd); + void (*effective_prot_pud)(struct ptdump_state *st, pud_t pud); + void (*effective_prot_p4d)(struct ptdump_state *st, p4d_t p4d); + void (*effective_prot_pgd)(struct ptdump_state *st, pgd_t pgd); const struct ptdump_range *range; }; diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 6b82b618846e..c4f4903b1088 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -223,7 +223,7 @@ static inline void __folio_large_mapcount_sanity_checks(const struct folio *foli VM_WARN_ON_ONCE(folio_mm_id(folio, 1) != MM_ID_DUMMY && folio->_mm_id_mapcount[1] < 0); VM_WARN_ON_ONCE(!folio_mapped(folio) && - folio_test_large_maybe_mapped_shared(folio)); + test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids)); } static __always_inline void folio_set_large_mapcount(struct folio *folio, diff --git a/include/linux/swap.h b/include/linux/swap.h index db46b25a65ae..bc0e1c275fc0 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -414,6 +414,10 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, #define MEMCG_RECLAIM_PROACTIVE (1 << 2) #define MIN_SWAPPINESS 0 #define MAX_SWAPPINESS 200 + +/* Just recliam from anon folios in proactive memory reclaim */ +#define SWAPPINESS_ANON_ONLY (MAX_SWAPPINESS + 1) + extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, @@ -450,7 +454,7 @@ static inline unsigned long total_swapcache_pages(void) } void free_swap_cache(struct folio *folio); -void free_page_and_swap_cache(struct page *); +void free_folio_and_swap_cache(struct folio *folio); void free_pages_and_swap_cache(struct encoded_page **, int); /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; @@ -520,10 +524,8 @@ static inline void put_swap_device(struct swap_info_struct *si) #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) -/* only sparc can not include linux/pagemap.h in this file - * so leave put_page and release_pages undeclared... */ -#define free_page_and_swap_cache(page) \ - put_page(page) +#define free_folio_and_swap_cache(folio) \ + folio_put(folio) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 2e46b69ff0a6..516217c39094 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -188,13 +188,13 @@ struct uprobes_state { }; extern void __init uprobes_init(void); -extern int set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); -extern int set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); +extern int set_swbp(struct arch_uprobe *aup, struct vm_area_struct *vma, unsigned long vaddr); +extern int set_orig_insn(struct arch_uprobe *aup, struct vm_area_struct *vma, unsigned long vaddr); extern bool is_swbp_insn(uprobe_opcode_t *insn); extern bool is_trap_insn(uprobe_opcode_t *insn); extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs); extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); -extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); +extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct vm_area_struct *vma, unsigned long vaddr, uprobe_opcode_t); extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool); extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc); diff --git a/include/linux/util_macros.h b/include/linux/util_macros.h index 3b570b765b75..76ca2b83c13e 100644 --- a/include/linux/util_macros.h +++ b/include/linux/util_macros.h @@ -2,7 +2,10 @@ #ifndef _LINUX_HELPER_MACROS_H_ #define _LINUX_HELPER_MACROS_H_ +#include <linux/compiler_attributes.h> #include <linux/math.h> +#include <linux/typecheck.h> +#include <linux/stddef.h> /** * for_each_if - helper for handling conditionals in various for_each macros diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 78eede109b1a..be850174e802 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -965,10 +965,12 @@ static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id, * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * + * Note that callers interested in whether wrapping has occurred should + * use __xa_alloc_cyclic() instead. + * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. - * Return: 0 if the allocation succeeded without wrapping. 1 if the - * allocation succeeded after wrapping, -ENOMEM if memory could not be + * Return: 0 if the allocation succeeded, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, @@ -981,7 +983,7 @@ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock(xa); - return err; + return err < 0 ? err : 0; } /** @@ -1002,10 +1004,12 @@ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * + * Note that callers interested in whether wrapping has occurred should + * use __xa_alloc_cyclic() instead. + * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. - * Return: 0 if the allocation succeeded without wrapping. 1 if the - * allocation succeeded after wrapping, -ENOMEM if memory could not be + * Return: 0 if the allocation succeeded, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry, @@ -1018,7 +1022,7 @@ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry, err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_bh(xa); - return err; + return err < 0 ? err : 0; } /** @@ -1039,10 +1043,12 @@ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry, * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * + * Note that callers interested in whether wrapping has occurred should + * use __xa_alloc_cyclic() instead. + * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. - * Return: 0 if the allocation succeeded without wrapping. 1 if the - * allocation succeeded after wrapping, -ENOMEM if memory could not be + * Return: 0 if the allocation succeeded, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry, @@ -1055,7 +1061,7 @@ static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry, err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_irq(xa); - return err; + return err < 0 ? err : 0; } /** diff --git a/include/linux/zpool.h b/include/linux/zpool.h index 52f30e526607..369ef068fad8 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -22,7 +22,7 @@ const char *zpool_get_type(struct zpool *pool); void zpool_destroy_pool(struct zpool *pool); int zpool_malloc(struct zpool *pool, size_t size, gfp_t gfp, - unsigned long *handle); + unsigned long *handle, const int nid); void zpool_free(struct zpool *pool, unsigned long handle); @@ -64,7 +64,7 @@ struct zpool_driver { void (*destroy)(void *pool); int (*malloc)(void *pool, size_t size, gfp_t gfp, - unsigned long *handle); + unsigned long *handle, const int nid); void (*free)(void *pool, unsigned long handle); void *(*obj_read_begin)(void *pool, unsigned long handle, diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index c26baf9fb331..13e9cc5490f7 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -26,7 +26,8 @@ struct zs_pool; struct zs_pool *zs_create_pool(const char *name); void zs_destroy_pool(struct zs_pool *pool); -unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t flags); +unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t flags, + const int nid); void zs_free(struct zs_pool *pool, unsigned long obj); size_t zs_huge_class_size(struct zs_pool *pool); |