mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 09:19:51 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
Improvements and bug fixes for the hmm interface in the kernel: - Improve clarity, locking and APIs related to the 'hmm mirror' feature merged last cycle. In linux-next we now see AMDGPU and nouveau to be using this API. - Remove old or transitional hmm APIs. These are hold overs from the past with no users, or APIs that existed only to manage cross tree conflicts. There are still a few more of these cleanups that didn't make the merge window cut off. - Improve some core mm APIs: * export alloc_pages_vma() for driver use * refactor into devm_request_free_mem_region() to manage DEVICE_PRIVATE resource reservations * refactor duplicative driver code into the core dev_pagemap struct - Remove hmm wrappers of improved core mm APIs, instead have drivers use the simplified API directly - Remove DEVICE_PUBLIC - Simplify the kconfig flow for the hmm users and core code -----BEGIN PGP SIGNATURE----- iQIzBAABCgAdFiEEfB7FMLh+8QxL+6i3OG33FX4gmxoFAl0k1zkACgkQOG33FX4g mxrO+w//QF/yI/9Hh30RWEBq8W107cODkDlaT0Z/7cVEXfGetZzIUpqzxnJofRfQ xTw1XmYkc9WpJe/mTTuFZFewNQwWuMM6X0Xi25fV438/Y64EclevlcJTeD49TIH1 CIMsz8bX7CnCEq5sz+UypLg9LPnaD9L/JLyuSbyjqjms/o+yzqa7ji7p/DSINuhZ Qva9OZL1ZSEDJfNGi8uGpYBqryHoBAonIL12R9sCF5pbJEnHfWrH7C06q7AWOAjQ 4vjN/p3F4L9l/v2IQ26Kn/S0AhmN7n3GT//0K66e2gJPfXa8fxRKGuFn/Kd79EGL YPASn5iu3cM23up1XkbMNtzacL8yiIeTOcMdqw26OaOClojy/9OJduv5AChe6qL/ VUQIAn1zvPsJTyC5U7mhmkrGuTpP6ivHpxtcaUp+Ovvi1cyK40nLCmSNvLnbN5ES bxbb0SjE4uupDG5qU6Yct/hFp6uVMSxMqXZOb9Xy8ZBkbMsJyVOLj71G1/rVIfPU hO1AChX5CRG1eJoMo6oBIpiwmSvcOaPp3dqIOQZvwMOqrO869LR8qv7RXyh/g9gi FAEKnwLl4GK3YtEO4Kt/1YI5DXYjSFUbfgAs0SPsRKS6hK2+RgRk2M/B/5dAX0/d lgOf9WPODPwiSXBYLtJB8qHVDX0DIY8faOyTx6BYIKClUtgbBI8= =wKvp -----END PGP SIGNATURE----- Merge tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma Pull HMM updates from Jason Gunthorpe: "Improvements and bug fixes for the hmm interface in the kernel: - Improve clarity, locking and APIs related to the 'hmm mirror' feature merged last cycle. In linux-next we now see AMDGPU and nouveau to be using this API. - Remove old or transitional hmm APIs. These are hold overs from the past with no users, or APIs that existed only to manage cross tree conflicts. There are still a few more of these cleanups that didn't make the merge window cut off. - Improve some core mm APIs: - export alloc_pages_vma() for driver use - refactor into devm_request_free_mem_region() to manage DEVICE_PRIVATE resource reservations - refactor duplicative driver code into the core dev_pagemap struct - Remove hmm wrappers of improved core mm APIs, instead have drivers use the simplified API directly - Remove DEVICE_PUBLIC - Simplify the kconfig flow for the hmm users and core code" * tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (42 commits) mm: don't select MIGRATE_VMA_HELPER from HMM_MIRROR mm: remove the HMM config option mm: sort out the DEVICE_PRIVATE Kconfig mess mm: simplify ZONE_DEVICE page private data mm: remove hmm_devmem_add mm: remove hmm_vma_alloc_locked_page nouveau: use devm_memremap_pages directly nouveau: use alloc_page_vma directly PCI/P2PDMA: use the dev_pagemap internal refcount device-dax: use the dev_pagemap internal refcount memremap: provide an optional internal refcount in struct dev_pagemap memremap: replace the altmap_valid field with a PGMAP_ALTMAP_VALID flag memremap: remove the data field in struct dev_pagemap memremap: add a migrate_to_ram method to struct dev_pagemap_ops memremap: lift the devmap_enable manipulation into devm_memremap_pages memremap: pass a struct dev_pagemap to ->kill and ->cleanup memremap: move dev_pagemap callbacks into a separate structure memremap: validate the pagemap type passed to devm_memremap_pages mm: factor out a devm_request_free_mem_region helper mm: export alloc_pages_vma ...
740 lines
23 KiB
C
740 lines
23 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_MM_TYPES_H
|
|
#define _LINUX_MM_TYPES_H
|
|
|
|
#include <linux/mm_types_task.h>
|
|
|
|
#include <linux/auxvec.h>
|
|
#include <linux/list.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/rbtree.h>
|
|
#include <linux/rwsem.h>
|
|
#include <linux/completion.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/uprobes.h>
|
|
#include <linux/page-flags-layout.h>
|
|
#include <linux/workqueue.h>
|
|
|
|
#include <asm/mmu.h>
|
|
|
|
#ifndef AT_VECTOR_SIZE_ARCH
|
|
#define AT_VECTOR_SIZE_ARCH 0
|
|
#endif
|
|
#define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1))
|
|
|
|
|
|
struct address_space;
|
|
struct mem_cgroup;
|
|
struct hmm;
|
|
|
|
/*
|
|
* Each physical page in the system has a struct page associated with
|
|
* it to keep track of whatever it is we are using the page for at the
|
|
* moment. Note that we have no way to track which tasks are using
|
|
* a page, though if it is a pagecache page, rmap structures can tell us
|
|
* who is mapping it.
|
|
*
|
|
* If you allocate the page using alloc_pages(), you can use some of the
|
|
* space in struct page for your own purposes. The five words in the main
|
|
* union are available, except for bit 0 of the first word which must be
|
|
* kept clear. Many users use this word to store a pointer to an object
|
|
* which is guaranteed to be aligned. If you use the same storage as
|
|
* page->mapping, you must restore it to NULL before freeing the page.
|
|
*
|
|
* If your page will not be mapped to userspace, you can also use the four
|
|
* bytes in the mapcount union, but you must call page_mapcount_reset()
|
|
* before freeing it.
|
|
*
|
|
* If you want to use the refcount field, it must be used in such a way
|
|
* that other CPUs temporarily incrementing and then decrementing the
|
|
* refcount does not cause problems. On receiving the page from
|
|
* alloc_pages(), the refcount will be positive.
|
|
*
|
|
* If you allocate pages of order > 0, you can use some of the fields
|
|
* in each subpage, but you may need to restore some of their values
|
|
* afterwards.
|
|
*
|
|
* SLUB uses cmpxchg_double() to atomically update its freelist and
|
|
* counters. That requires that freelist & counters be adjacent and
|
|
* double-word aligned. We align all struct pages to double-word
|
|
* boundaries, and ensure that 'freelist' is aligned within the
|
|
* struct.
|
|
*/
|
|
#ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE
|
|
#define _struct_page_alignment __aligned(2 * sizeof(unsigned long))
|
|
#else
|
|
#define _struct_page_alignment
|
|
#endif
|
|
|
|
struct page {
|
|
unsigned long flags; /* Atomic flags, some possibly
|
|
* updated asynchronously */
|
|
/*
|
|
* Five words (20/40 bytes) are available in this union.
|
|
* WARNING: bit 0 of the first word is used for PageTail(). That
|
|
* means the other users of this union MUST NOT use the bit to
|
|
* avoid collision and false-positive PageTail().
|
|
*/
|
|
union {
|
|
struct { /* Page cache and anonymous pages */
|
|
/**
|
|
* @lru: Pageout list, eg. active_list protected by
|
|
* pgdat->lru_lock. Sometimes used as a generic list
|
|
* by the page owner.
|
|
*/
|
|
struct list_head lru;
|
|
/* See page-flags.h for PAGE_MAPPING_FLAGS */
|
|
struct address_space *mapping;
|
|
pgoff_t index; /* Our offset within mapping. */
|
|
/**
|
|
* @private: Mapping-private opaque data.
|
|
* Usually used for buffer_heads if PagePrivate.
|
|
* Used for swp_entry_t if PageSwapCache.
|
|
* Indicates order in the buddy system if PageBuddy.
|
|
*/
|
|
unsigned long private;
|
|
};
|
|
struct { /* page_pool used by netstack */
|
|
/**
|
|
* @dma_addr: might require a 64-bit value even on
|
|
* 32-bit architectures.
|
|
*/
|
|
dma_addr_t dma_addr;
|
|
};
|
|
struct { /* slab, slob and slub */
|
|
union {
|
|
struct list_head slab_list;
|
|
struct { /* Partial pages */
|
|
struct page *next;
|
|
#ifdef CONFIG_64BIT
|
|
int pages; /* Nr of pages left */
|
|
int pobjects; /* Approximate count */
|
|
#else
|
|
short int pages;
|
|
short int pobjects;
|
|
#endif
|
|
};
|
|
};
|
|
struct kmem_cache *slab_cache; /* not slob */
|
|
/* Double-word boundary */
|
|
void *freelist; /* first free object */
|
|
union {
|
|
void *s_mem; /* slab: first object */
|
|
unsigned long counters; /* SLUB */
|
|
struct { /* SLUB */
|
|
unsigned inuse:16;
|
|
unsigned objects:15;
|
|
unsigned frozen:1;
|
|
};
|
|
};
|
|
};
|
|
struct { /* Tail pages of compound page */
|
|
unsigned long compound_head; /* Bit zero is set */
|
|
|
|
/* First tail page only */
|
|
unsigned char compound_dtor;
|
|
unsigned char compound_order;
|
|
atomic_t compound_mapcount;
|
|
};
|
|
struct { /* Second tail page of compound page */
|
|
unsigned long _compound_pad_1; /* compound_head */
|
|
unsigned long _compound_pad_2;
|
|
struct list_head deferred_list;
|
|
};
|
|
struct { /* Page table pages */
|
|
unsigned long _pt_pad_1; /* compound_head */
|
|
pgtable_t pmd_huge_pte; /* protected by page->ptl */
|
|
unsigned long _pt_pad_2; /* mapping */
|
|
union {
|
|
struct mm_struct *pt_mm; /* x86 pgds only */
|
|
atomic_t pt_frag_refcount; /* powerpc */
|
|
};
|
|
#if ALLOC_SPLIT_PTLOCKS
|
|
spinlock_t *ptl;
|
|
#else
|
|
spinlock_t ptl;
|
|
#endif
|
|
};
|
|
struct { /* ZONE_DEVICE pages */
|
|
/** @pgmap: Points to the hosting device page map. */
|
|
struct dev_pagemap *pgmap;
|
|
void *zone_device_data;
|
|
unsigned long _zd_pad_1; /* uses mapping */
|
|
};
|
|
|
|
/** @rcu_head: You can use this to free a page by RCU. */
|
|
struct rcu_head rcu_head;
|
|
};
|
|
|
|
union { /* This union is 4 bytes in size. */
|
|
/*
|
|
* If the page can be mapped to userspace, encodes the number
|
|
* of times this page is referenced by a page table.
|
|
*/
|
|
atomic_t _mapcount;
|
|
|
|
/*
|
|
* If the page is neither PageSlab nor mappable to userspace,
|
|
* the value stored here may help determine what this page
|
|
* is used for. See page-flags.h for a list of page types
|
|
* which are currently stored here.
|
|
*/
|
|
unsigned int page_type;
|
|
|
|
unsigned int active; /* SLAB */
|
|
int units; /* SLOB */
|
|
};
|
|
|
|
/* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */
|
|
atomic_t _refcount;
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
struct mem_cgroup *mem_cgroup;
|
|
#endif
|
|
|
|
/*
|
|
* On machines where all RAM is mapped into kernel address space,
|
|
* we can simply calculate the virtual address. On machines with
|
|
* highmem some memory is mapped into kernel virtual memory
|
|
* dynamically, so we need a place to store that address.
|
|
* Note that this field could be 16 bits on x86 ... ;)
|
|
*
|
|
* Architectures with slow multiplication can define
|
|
* WANT_PAGE_VIRTUAL in asm/page.h
|
|
*/
|
|
#if defined(WANT_PAGE_VIRTUAL)
|
|
void *virtual; /* Kernel virtual address (NULL if
|
|
not kmapped, ie. highmem) */
|
|
#endif /* WANT_PAGE_VIRTUAL */
|
|
|
|
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
|
|
int _last_cpupid;
|
|
#endif
|
|
} _struct_page_alignment;
|
|
|
|
/*
|
|
* Used for sizing the vmemmap region on some architectures
|
|
*/
|
|
#define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page)))
|
|
|
|
#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK)
|
|
#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE)
|
|
|
|
#define page_private(page) ((page)->private)
|
|
#define set_page_private(page, v) ((page)->private = (v))
|
|
|
|
struct page_frag_cache {
|
|
void * va;
|
|
#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
|
|
__u16 offset;
|
|
__u16 size;
|
|
#else
|
|
__u32 offset;
|
|
#endif
|
|
/* we maintain a pagecount bias, so that we dont dirty cache line
|
|
* containing page->_refcount every time we allocate a fragment.
|
|
*/
|
|
unsigned int pagecnt_bias;
|
|
bool pfmemalloc;
|
|
};
|
|
|
|
typedef unsigned long vm_flags_t;
|
|
|
|
/*
|
|
* A region containing a mapping of a non-memory backed file under NOMMU
|
|
* conditions. These are held in a global tree and are pinned by the VMAs that
|
|
* map parts of them.
|
|
*/
|
|
struct vm_region {
|
|
struct rb_node vm_rb; /* link in global region tree */
|
|
vm_flags_t vm_flags; /* VMA vm_flags */
|
|
unsigned long vm_start; /* start address of region */
|
|
unsigned long vm_end; /* region initialised to here */
|
|
unsigned long vm_top; /* region allocated to here */
|
|
unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */
|
|
struct file *vm_file; /* the backing file or NULL */
|
|
|
|
int vm_usage; /* region usage count (access under nommu_region_sem) */
|
|
bool vm_icache_flushed : 1; /* true if the icache has been flushed for
|
|
* this region */
|
|
};
|
|
|
|
#ifdef CONFIG_USERFAULTFD
|
|
#define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) { NULL, })
|
|
struct vm_userfaultfd_ctx {
|
|
struct userfaultfd_ctx *ctx;
|
|
};
|
|
#else /* CONFIG_USERFAULTFD */
|
|
#define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) {})
|
|
struct vm_userfaultfd_ctx {};
|
|
#endif /* CONFIG_USERFAULTFD */
|
|
|
|
/*
|
|
* This struct defines a memory VMM memory area. There is one of these
|
|
* per VM-area/task. A VM area is any part of the process virtual memory
|
|
* space that has a special rule for the page-fault handlers (ie a shared
|
|
* library, the executable area etc).
|
|
*/
|
|
struct vm_area_struct {
|
|
/* The first cache line has the info for VMA tree walking. */
|
|
|
|
unsigned long vm_start; /* Our start address within vm_mm. */
|
|
unsigned long vm_end; /* The first byte after our end address
|
|
within vm_mm. */
|
|
|
|
/* linked list of VM areas per task, sorted by address */
|
|
struct vm_area_struct *vm_next, *vm_prev;
|
|
|
|
struct rb_node vm_rb;
|
|
|
|
/*
|
|
* Largest free memory gap in bytes to the left of this VMA.
|
|
* Either between this VMA and vma->vm_prev, or between one of the
|
|
* VMAs below us in the VMA rbtree and its ->vm_prev. This helps
|
|
* get_unmapped_area find a free area of the right size.
|
|
*/
|
|
unsigned long rb_subtree_gap;
|
|
|
|
/* Second cache line starts here. */
|
|
|
|
struct mm_struct *vm_mm; /* The address space we belong to. */
|
|
pgprot_t vm_page_prot; /* Access permissions of this VMA. */
|
|
unsigned long vm_flags; /* Flags, see mm.h. */
|
|
|
|
/*
|
|
* For areas with an address space and backing store,
|
|
* linkage into the address_space->i_mmap interval tree.
|
|
*/
|
|
struct {
|
|
struct rb_node rb;
|
|
unsigned long rb_subtree_last;
|
|
} shared;
|
|
|
|
/*
|
|
* A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
|
|
* list, after a COW of one of the file pages. A MAP_SHARED vma
|
|
* can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack
|
|
* or brk vma (with NULL file) can only be in an anon_vma list.
|
|
*/
|
|
struct list_head anon_vma_chain; /* Serialized by mmap_sem &
|
|
* page_table_lock */
|
|
struct anon_vma *anon_vma; /* Serialized by page_table_lock */
|
|
|
|
/* Function pointers to deal with this struct. */
|
|
const struct vm_operations_struct *vm_ops;
|
|
|
|
/* Information about our backing store: */
|
|
unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
|
|
units */
|
|
struct file * vm_file; /* File we map to (can be NULL). */
|
|
void * vm_private_data; /* was vm_pte (shared mem) */
|
|
|
|
#ifdef CONFIG_SWAP
|
|
atomic_long_t swap_readahead_info;
|
|
#endif
|
|
#ifndef CONFIG_MMU
|
|
struct vm_region *vm_region; /* NOMMU mapping region */
|
|
#endif
|
|
#ifdef CONFIG_NUMA
|
|
struct mempolicy *vm_policy; /* NUMA policy for the VMA */
|
|
#endif
|
|
struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
|
|
} __randomize_layout;
|
|
|
|
struct core_thread {
|
|
struct task_struct *task;
|
|
struct core_thread *next;
|
|
};
|
|
|
|
struct core_state {
|
|
atomic_t nr_threads;
|
|
struct core_thread dumper;
|
|
struct completion startup;
|
|
};
|
|
|
|
struct kioctx_table;
|
|
struct mm_struct {
|
|
struct {
|
|
struct vm_area_struct *mmap; /* list of VMAs */
|
|
struct rb_root mm_rb;
|
|
u64 vmacache_seqnum; /* per-thread vmacache */
|
|
#ifdef CONFIG_MMU
|
|
unsigned long (*get_unmapped_area) (struct file *filp,
|
|
unsigned long addr, unsigned long len,
|
|
unsigned long pgoff, unsigned long flags);
|
|
#endif
|
|
unsigned long mmap_base; /* base of mmap area */
|
|
unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */
|
|
#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
|
|
/* Base adresses for compatible mmap() */
|
|
unsigned long mmap_compat_base;
|
|
unsigned long mmap_compat_legacy_base;
|
|
#endif
|
|
unsigned long task_size; /* size of task vm space */
|
|
unsigned long highest_vm_end; /* highest vma end address */
|
|
pgd_t * pgd;
|
|
|
|
/**
|
|
* @mm_users: The number of users including userspace.
|
|
*
|
|
* Use mmget()/mmget_not_zero()/mmput() to modify. When this
|
|
* drops to 0 (i.e. when the task exits and there are no other
|
|
* temporary reference holders), we also release a reference on
|
|
* @mm_count (which may then free the &struct mm_struct if
|
|
* @mm_count also drops to 0).
|
|
*/
|
|
atomic_t mm_users;
|
|
|
|
/**
|
|
* @mm_count: The number of references to &struct mm_struct
|
|
* (@mm_users count as 1).
|
|
*
|
|
* Use mmgrab()/mmdrop() to modify. When this drops to 0, the
|
|
* &struct mm_struct is freed.
|
|
*/
|
|
atomic_t mm_count;
|
|
|
|
#ifdef CONFIG_MMU
|
|
atomic_long_t pgtables_bytes; /* PTE page table pages */
|
|
#endif
|
|
int map_count; /* number of VMAs */
|
|
|
|
spinlock_t page_table_lock; /* Protects page tables and some
|
|
* counters
|
|
*/
|
|
struct rw_semaphore mmap_sem;
|
|
|
|
struct list_head mmlist; /* List of maybe swapped mm's. These
|
|
* are globally strung together off
|
|
* init_mm.mmlist, and are protected
|
|
* by mmlist_lock
|
|
*/
|
|
|
|
|
|
unsigned long hiwater_rss; /* High-watermark of RSS usage */
|
|
unsigned long hiwater_vm; /* High-water virtual memory usage */
|
|
|
|
unsigned long total_vm; /* Total pages mapped */
|
|
unsigned long locked_vm; /* Pages that have PG_mlocked set */
|
|
atomic64_t pinned_vm; /* Refcount permanently increased */
|
|
unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
|
|
unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
|
|
unsigned long stack_vm; /* VM_STACK */
|
|
unsigned long def_flags;
|
|
|
|
spinlock_t arg_lock; /* protect the below fields */
|
|
unsigned long start_code, end_code, start_data, end_data;
|
|
unsigned long start_brk, brk, start_stack;
|
|
unsigned long arg_start, arg_end, env_start, env_end;
|
|
|
|
unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
|
|
|
|
/*
|
|
* Special counters, in some configurations protected by the
|
|
* page_table_lock, in other configurations by being atomic.
|
|
*/
|
|
struct mm_rss_stat rss_stat;
|
|
|
|
struct linux_binfmt *binfmt;
|
|
|
|
/* Architecture-specific MM context */
|
|
mm_context_t context;
|
|
|
|
unsigned long flags; /* Must use atomic bitops to access */
|
|
|
|
struct core_state *core_state; /* coredumping support */
|
|
#ifdef CONFIG_MEMBARRIER
|
|
atomic_t membarrier_state;
|
|
#endif
|
|
#ifdef CONFIG_AIO
|
|
spinlock_t ioctx_lock;
|
|
struct kioctx_table __rcu *ioctx_table;
|
|
#endif
|
|
#ifdef CONFIG_MEMCG
|
|
/*
|
|
* "owner" points to a task that is regarded as the canonical
|
|
* user/owner of this mm. All of the following must be true in
|
|
* order for it to be changed:
|
|
*
|
|
* current == mm->owner
|
|
* current->mm != mm
|
|
* new_owner->mm == mm
|
|
* new_owner->alloc_lock is held
|
|
*/
|
|
struct task_struct __rcu *owner;
|
|
#endif
|
|
struct user_namespace *user_ns;
|
|
|
|
/* store ref to file /proc/<pid>/exe symlink points to */
|
|
struct file __rcu *exe_file;
|
|
#ifdef CONFIG_MMU_NOTIFIER
|
|
struct mmu_notifier_mm *mmu_notifier_mm;
|
|
#endif
|
|
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
|
|
pgtable_t pmd_huge_pte; /* protected by page_table_lock */
|
|
#endif
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
/*
|
|
* numa_next_scan is the next time that the PTEs will be marked
|
|
* pte_numa. NUMA hinting faults will gather statistics and
|
|
* migrate pages to new nodes if necessary.
|
|
*/
|
|
unsigned long numa_next_scan;
|
|
|
|
/* Restart point for scanning and setting pte_numa */
|
|
unsigned long numa_scan_offset;
|
|
|
|
/* numa_scan_seq prevents two threads setting pte_numa */
|
|
int numa_scan_seq;
|
|
#endif
|
|
/*
|
|
* An operation with batched TLB flushing is going on. Anything
|
|
* that can move process memory needs to flush the TLB when
|
|
* moving a PROT_NONE or PROT_NUMA mapped page.
|
|
*/
|
|
atomic_t tlb_flush_pending;
|
|
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
|
|
/* See flush_tlb_batched_pending() */
|
|
bool tlb_flush_batched;
|
|
#endif
|
|
struct uprobes_state uprobes_state;
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
atomic_long_t hugetlb_usage;
|
|
#endif
|
|
struct work_struct async_put_work;
|
|
|
|
#ifdef CONFIG_HMM_MIRROR
|
|
/* HMM needs to track a few things per mm */
|
|
struct hmm *hmm;
|
|
#endif
|
|
} __randomize_layout;
|
|
|
|
/*
|
|
* The mm_cpumask needs to be at the end of mm_struct, because it
|
|
* is dynamically sized based on nr_cpu_ids.
|
|
*/
|
|
unsigned long cpu_bitmap[];
|
|
};
|
|
|
|
extern struct mm_struct init_mm;
|
|
|
|
/* Pointer magic because the dynamic array size confuses some compilers. */
|
|
static inline void mm_init_cpumask(struct mm_struct *mm)
|
|
{
|
|
unsigned long cpu_bitmap = (unsigned long)mm;
|
|
|
|
cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap);
|
|
cpumask_clear((struct cpumask *)cpu_bitmap);
|
|
}
|
|
|
|
/* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
|
|
static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
|
|
{
|
|
return (struct cpumask *)&mm->cpu_bitmap;
|
|
}
|
|
|
|
struct mmu_gather;
|
|
extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
|
|
unsigned long start, unsigned long end);
|
|
extern void tlb_finish_mmu(struct mmu_gather *tlb,
|
|
unsigned long start, unsigned long end);
|
|
|
|
static inline void init_tlb_flush_pending(struct mm_struct *mm)
|
|
{
|
|
atomic_set(&mm->tlb_flush_pending, 0);
|
|
}
|
|
|
|
static inline void inc_tlb_flush_pending(struct mm_struct *mm)
|
|
{
|
|
atomic_inc(&mm->tlb_flush_pending);
|
|
/*
|
|
* The only time this value is relevant is when there are indeed pages
|
|
* to flush. And we'll only flush pages after changing them, which
|
|
* requires the PTL.
|
|
*
|
|
* So the ordering here is:
|
|
*
|
|
* atomic_inc(&mm->tlb_flush_pending);
|
|
* spin_lock(&ptl);
|
|
* ...
|
|
* set_pte_at();
|
|
* spin_unlock(&ptl);
|
|
*
|
|
* spin_lock(&ptl)
|
|
* mm_tlb_flush_pending();
|
|
* ....
|
|
* spin_unlock(&ptl);
|
|
*
|
|
* flush_tlb_range();
|
|
* atomic_dec(&mm->tlb_flush_pending);
|
|
*
|
|
* Where the increment if constrained by the PTL unlock, it thus
|
|
* ensures that the increment is visible if the PTE modification is
|
|
* visible. After all, if there is no PTE modification, nobody cares
|
|
* about TLB flushes either.
|
|
*
|
|
* This very much relies on users (mm_tlb_flush_pending() and
|
|
* mm_tlb_flush_nested()) only caring about _specific_ PTEs (and
|
|
* therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc
|
|
* locks (PPC) the unlock of one doesn't order against the lock of
|
|
* another PTL.
|
|
*
|
|
* The decrement is ordered by the flush_tlb_range(), such that
|
|
* mm_tlb_flush_pending() will not return false unless all flushes have
|
|
* completed.
|
|
*/
|
|
}
|
|
|
|
static inline void dec_tlb_flush_pending(struct mm_struct *mm)
|
|
{
|
|
/*
|
|
* See inc_tlb_flush_pending().
|
|
*
|
|
* This cannot be smp_mb__before_atomic() because smp_mb() simply does
|
|
* not order against TLB invalidate completion, which is what we need.
|
|
*
|
|
* Therefore we must rely on tlb_flush_*() to guarantee order.
|
|
*/
|
|
atomic_dec(&mm->tlb_flush_pending);
|
|
}
|
|
|
|
static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
|
|
{
|
|
/*
|
|
* Must be called after having acquired the PTL; orders against that
|
|
* PTLs release and therefore ensures that if we observe the modified
|
|
* PTE we must also observe the increment from inc_tlb_flush_pending().
|
|
*
|
|
* That is, it only guarantees to return true if there is a flush
|
|
* pending for _this_ PTL.
|
|
*/
|
|
return atomic_read(&mm->tlb_flush_pending);
|
|
}
|
|
|
|
static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
|
|
{
|
|
/*
|
|
* Similar to mm_tlb_flush_pending(), we must have acquired the PTL
|
|
* for which there is a TLB flush pending in order to guarantee
|
|
* we've seen both that PTE modification and the increment.
|
|
*
|
|
* (no requirement on actually still holding the PTL, that is irrelevant)
|
|
*/
|
|
return atomic_read(&mm->tlb_flush_pending) > 1;
|
|
}
|
|
|
|
struct vm_fault;
|
|
|
|
/**
|
|
* typedef vm_fault_t - Return type for page fault handlers.
|
|
*
|
|
* Page fault handlers return a bitmask of %VM_FAULT values.
|
|
*/
|
|
typedef __bitwise unsigned int vm_fault_t;
|
|
|
|
/**
|
|
* enum vm_fault_reason - Page fault handlers return a bitmask of
|
|
* these values to tell the core VM what happened when handling the
|
|
* fault. Used to decide whether a process gets delivered SIGBUS or
|
|
* just gets major/minor fault counters bumped up.
|
|
*
|
|
* @VM_FAULT_OOM: Out Of Memory
|
|
* @VM_FAULT_SIGBUS: Bad access
|
|
* @VM_FAULT_MAJOR: Page read from storage
|
|
* @VM_FAULT_WRITE: Special case for get_user_pages
|
|
* @VM_FAULT_HWPOISON: Hit poisoned small page
|
|
* @VM_FAULT_HWPOISON_LARGE: Hit poisoned large page. Index encoded
|
|
* in upper bits
|
|
* @VM_FAULT_SIGSEGV: segmentation fault
|
|
* @VM_FAULT_NOPAGE: ->fault installed the pte, not return page
|
|
* @VM_FAULT_LOCKED: ->fault locked the returned page
|
|
* @VM_FAULT_RETRY: ->fault blocked, must retry
|
|
* @VM_FAULT_FALLBACK: huge page fault failed, fall back to small
|
|
* @VM_FAULT_DONE_COW: ->fault has fully handled COW
|
|
* @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs
|
|
* fsync() to complete (for synchronous page faults
|
|
* in DAX)
|
|
* @VM_FAULT_HINDEX_MASK: mask HINDEX value
|
|
*
|
|
*/
|
|
enum vm_fault_reason {
|
|
VM_FAULT_OOM = (__force vm_fault_t)0x000001,
|
|
VM_FAULT_SIGBUS = (__force vm_fault_t)0x000002,
|
|
VM_FAULT_MAJOR = (__force vm_fault_t)0x000004,
|
|
VM_FAULT_WRITE = (__force vm_fault_t)0x000008,
|
|
VM_FAULT_HWPOISON = (__force vm_fault_t)0x000010,
|
|
VM_FAULT_HWPOISON_LARGE = (__force vm_fault_t)0x000020,
|
|
VM_FAULT_SIGSEGV = (__force vm_fault_t)0x000040,
|
|
VM_FAULT_NOPAGE = (__force vm_fault_t)0x000100,
|
|
VM_FAULT_LOCKED = (__force vm_fault_t)0x000200,
|
|
VM_FAULT_RETRY = (__force vm_fault_t)0x000400,
|
|
VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800,
|
|
VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000,
|
|
VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000,
|
|
VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000,
|
|
};
|
|
|
|
/* Encode hstate index for a hwpoisoned large page */
|
|
#define VM_FAULT_SET_HINDEX(x) ((__force vm_fault_t)((x) << 16))
|
|
#define VM_FAULT_GET_HINDEX(x) (((__force unsigned int)(x) >> 16) & 0xf)
|
|
|
|
#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | \
|
|
VM_FAULT_SIGSEGV | VM_FAULT_HWPOISON | \
|
|
VM_FAULT_HWPOISON_LARGE | VM_FAULT_FALLBACK)
|
|
|
|
#define VM_FAULT_RESULT_TRACE \
|
|
{ VM_FAULT_OOM, "OOM" }, \
|
|
{ VM_FAULT_SIGBUS, "SIGBUS" }, \
|
|
{ VM_FAULT_MAJOR, "MAJOR" }, \
|
|
{ VM_FAULT_WRITE, "WRITE" }, \
|
|
{ VM_FAULT_HWPOISON, "HWPOISON" }, \
|
|
{ VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \
|
|
{ VM_FAULT_SIGSEGV, "SIGSEGV" }, \
|
|
{ VM_FAULT_NOPAGE, "NOPAGE" }, \
|
|
{ VM_FAULT_LOCKED, "LOCKED" }, \
|
|
{ VM_FAULT_RETRY, "RETRY" }, \
|
|
{ VM_FAULT_FALLBACK, "FALLBACK" }, \
|
|
{ VM_FAULT_DONE_COW, "DONE_COW" }, \
|
|
{ VM_FAULT_NEEDDSYNC, "NEEDDSYNC" }
|
|
|
|
struct vm_special_mapping {
|
|
const char *name; /* The name, e.g. "[vdso]". */
|
|
|
|
/*
|
|
* If .fault is not provided, this points to a
|
|
* NULL-terminated array of pages that back the special mapping.
|
|
*
|
|
* This must not be NULL unless .fault is provided.
|
|
*/
|
|
struct page **pages;
|
|
|
|
/*
|
|
* If non-NULL, then this is called to resolve page faults
|
|
* on the special mapping. If used, .pages is not checked.
|
|
*/
|
|
vm_fault_t (*fault)(const struct vm_special_mapping *sm,
|
|
struct vm_area_struct *vma,
|
|
struct vm_fault *vmf);
|
|
|
|
int (*mremap)(const struct vm_special_mapping *sm,
|
|
struct vm_area_struct *new_vma);
|
|
};
|
|
|
|
enum tlb_flush_reason {
|
|
TLB_FLUSH_ON_TASK_SWITCH,
|
|
TLB_REMOTE_SHOOTDOWN,
|
|
TLB_LOCAL_SHOOTDOWN,
|
|
TLB_LOCAL_MM_SHOOTDOWN,
|
|
TLB_REMOTE_SEND_IPI,
|
|
NR_TLB_FLUSH_REASONS,
|
|
};
|
|
|
|
/*
|
|
* A swap entry has to fit into a "unsigned long", as the entry is hidden
|
|
* in the "index" field of the swapper address space.
|
|
*/
|
|
typedef struct {
|
|
unsigned long val;
|
|
} swp_entry_t;
|
|
|
|
#endif /* _LINUX_MM_TYPES_H */
|