mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-27 12:57:53 +00:00
bf75f20056
Patch series "Drain remote per-cpu directly", v5. Some setups, notably NOHZ_FULL CPUs, may be running realtime or latency-sensitive applications that cannot tolerate interference due to per-cpu drain work queued by __drain_all_pages(). Introduce a new mechanism to remotely drain the per-cpu lists. It is made possible by remotely locking 'struct per_cpu_pages' new per-cpu spinlocks. This has two advantages, the time to drain is more predictable and other unrelated tasks are not interrupted. This series has the same intent as Nicolas' series "mm/page_alloc: Remote per-cpu lists drain support" -- avoid interference of a high priority task due to a workqueue item draining per-cpu page lists. While many workloads can tolerate a brief interruption, it may cause a real-time task running on a NOHZ_FULL CPU to miss a deadline and at minimum, the draining is non-deterministic. Currently an IRQ-safe local_lock protects the page allocator per-cpu lists. The local_lock on its own prevents migration and the IRQ disabling protects from corruption due to an interrupt arriving while a page allocation is in progress. This series adjusts the locking. A spinlock is added to struct per_cpu_pages to protect the list contents while local_lock_irq is ultimately replaced by just the spinlock in the final patch. This allows a remote CPU to safely. Follow-on work should allow the spin_lock_irqsave to be converted to spin_lock to avoid IRQs being disabled/enabled in most cases. The follow-on patch will be one kernel release later as it is relatively high risk and it'll make bisections more clear if there are any problems. Patch 1 is a cosmetic patch to clarify when page->lru is storing buddy pages and when it is storing per-cpu pages. Patch 2 shrinks per_cpu_pages to make room for a spin lock. Strictly speaking this is not necessary but it avoids per_cpu_pages consuming another cache line. Patch 3 is a preparation patch to avoid code duplication. Patch 4 is a minor correction. Patch 5 uses a spin_lock to protect the per_cpu_pages contents while still relying on local_lock to prevent migration, stabilise the pcp lookup and prevent IRQ reentrancy. Patch 6 remote drains per-cpu pages directly instead of using a workqueue. Patch 7 uses a normal spinlock instead of local_lock for remote draining This patch (of 7): The page allocator uses page->lru for storing pages on either buddy or PCP lists. Create page->buddy_list and page->pcp_list as a union with page->lru. This is simply to clarify what type of list a page is on in the page allocator. No functional change intended. [minchan@kernel.org: fix page lru fields in macros] Link: https://lkml.kernel.org/r/20220624125423.6126-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Tested-by: Minchan Kim <minchan@kernel.org> Acked-by: Minchan Kim <minchan@kernel.org> Reviewed-by: Nicolas Saenz Julienne <nsaenzju@redhat.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Tested-by: Yu Zhao <yuzhao@google.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
880 lines
28 KiB
C
880 lines
28 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/kref.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/rcupdate.h>
|
|
#include <linux/page-flags-layout.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/seqlock.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))
|
|
|
|
#define INIT_PASID 0
|
|
|
|
struct address_space;
|
|
struct mem_cgroup;
|
|
|
|
/*
|
|
* 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 in struct slab be adjacent and
|
|
* double-word aligned. Because struct slab currently just reinterprets the
|
|
* bits of struct page, we align all struct pages to double-word boundaries,
|
|
* and ensure that 'freelist' is aligned within struct slab.
|
|
*/
|
|
#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
|
|
* lruvec->lru_lock. Sometimes used as a generic list
|
|
* by the page owner.
|
|
*/
|
|
union {
|
|
struct list_head lru;
|
|
|
|
/* Or, for the Unevictable "LRU list" slot */
|
|
struct {
|
|
/* Always even, to negate PageTail */
|
|
void *__filler;
|
|
/* Count page's or folio's mlocks */
|
|
unsigned int mlock_count;
|
|
};
|
|
|
|
/* Or, free page */
|
|
struct list_head buddy_list;
|
|
struct list_head pcp_list;
|
|
};
|
|
/* 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 */
|
|
/**
|
|
* @pp_magic: magic value to avoid recycling non
|
|
* page_pool allocated pages.
|
|
*/
|
|
unsigned long pp_magic;
|
|
struct page_pool *pp;
|
|
unsigned long _pp_mapping_pad;
|
|
unsigned long dma_addr;
|
|
union {
|
|
/**
|
|
* dma_addr_upper: might require a 64-bit
|
|
* value on 32-bit architectures.
|
|
*/
|
|
unsigned long dma_addr_upper;
|
|
/**
|
|
* For frag page support, not supported in
|
|
* 32-bit architectures with 64-bit DMA.
|
|
*/
|
|
atomic_long_t pp_frag_count;
|
|
};
|
|
};
|
|
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;
|
|
atomic_t compound_pincount;
|
|
#ifdef CONFIG_64BIT
|
|
unsigned int compound_nr; /* 1 << compound_order */
|
|
#endif
|
|
};
|
|
struct { /* Second tail page of compound page */
|
|
unsigned long _compound_pad_1; /* compound_head */
|
|
unsigned long _compound_pad_2;
|
|
/* For both global and memcg */
|
|
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;
|
|
/*
|
|
* ZONE_DEVICE private pages are counted as being
|
|
* mapped so the next 3 words hold the mapping, index,
|
|
* and private fields from the source anonymous or
|
|
* page cache page while the page is migrated to device
|
|
* private memory.
|
|
* ZONE_DEVICE MEMORY_DEVICE_FS_DAX pages also
|
|
* use the mapping, index, and private fields when
|
|
* pmem backed DAX files are mapped.
|
|
*/
|
|
};
|
|
|
|
/** @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;
|
|
};
|
|
|
|
/* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */
|
|
atomic_t _refcount;
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
unsigned long memcg_data;
|
|
#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;
|
|
|
|
/**
|
|
* struct folio - Represents a contiguous set of bytes.
|
|
* @flags: Identical to the page flags.
|
|
* @lru: Least Recently Used list; tracks how recently this folio was used.
|
|
* @mlock_count: Number of times this folio has been pinned by mlock().
|
|
* @mapping: The file this page belongs to, or refers to the anon_vma for
|
|
* anonymous memory.
|
|
* @index: Offset within the file, in units of pages. For anonymous memory,
|
|
* this is the index from the beginning of the mmap.
|
|
* @private: Filesystem per-folio data (see folio_attach_private()).
|
|
* Used for swp_entry_t if folio_test_swapcache().
|
|
* @_mapcount: Do not access this member directly. Use folio_mapcount() to
|
|
* find out how many times this folio is mapped by userspace.
|
|
* @_refcount: Do not access this member directly. Use folio_ref_count()
|
|
* to find how many references there are to this folio.
|
|
* @memcg_data: Memory Control Group data.
|
|
*
|
|
* A folio is a physically, virtually and logically contiguous set
|
|
* of bytes. It is a power-of-two in size, and it is aligned to that
|
|
* same power-of-two. It is at least as large as %PAGE_SIZE. If it is
|
|
* in the page cache, it is at a file offset which is a multiple of that
|
|
* power-of-two. It may be mapped into userspace at an address which is
|
|
* at an arbitrary page offset, but its kernel virtual address is aligned
|
|
* to its size.
|
|
*/
|
|
struct folio {
|
|
/* private: don't document the anon union */
|
|
union {
|
|
struct {
|
|
/* public: */
|
|
unsigned long flags;
|
|
union {
|
|
struct list_head lru;
|
|
/* private: avoid cluttering the output */
|
|
struct {
|
|
void *__filler;
|
|
/* public: */
|
|
unsigned int mlock_count;
|
|
/* private: */
|
|
};
|
|
/* public: */
|
|
};
|
|
struct address_space *mapping;
|
|
pgoff_t index;
|
|
void *private;
|
|
atomic_t _mapcount;
|
|
atomic_t _refcount;
|
|
#ifdef CONFIG_MEMCG
|
|
unsigned long memcg_data;
|
|
#endif
|
|
/* private: the union with struct page is transitional */
|
|
};
|
|
struct page page;
|
|
};
|
|
};
|
|
|
|
static_assert(sizeof(struct page) == sizeof(struct folio));
|
|
#define FOLIO_MATCH(pg, fl) \
|
|
static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl))
|
|
FOLIO_MATCH(flags, flags);
|
|
FOLIO_MATCH(lru, lru);
|
|
FOLIO_MATCH(mapping, mapping);
|
|
FOLIO_MATCH(compound_head, lru);
|
|
FOLIO_MATCH(index, index);
|
|
FOLIO_MATCH(private, private);
|
|
FOLIO_MATCH(_mapcount, _mapcount);
|
|
FOLIO_MATCH(_refcount, _refcount);
|
|
#ifdef CONFIG_MEMCG
|
|
FOLIO_MATCH(memcg_data, memcg_data);
|
|
#endif
|
|
#undef FOLIO_MATCH
|
|
|
|
static inline atomic_t *folio_mapcount_ptr(struct folio *folio)
|
|
{
|
|
struct page *tail = &folio->page + 1;
|
|
return &tail->compound_mapcount;
|
|
}
|
|
|
|
static inline atomic_t *compound_mapcount_ptr(struct page *page)
|
|
{
|
|
return &page[1].compound_mapcount;
|
|
}
|
|
|
|
static inline atomic_t *compound_pincount_ptr(struct page *page)
|
|
{
|
|
return &page[1].compound_pincount;
|
|
}
|
|
|
|
/*
|
|
* 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)
|
|
|
|
/*
|
|
* page_private can be used on tail pages. However, PagePrivate is only
|
|
* checked by the VM on the head page. So page_private on the tail pages
|
|
* should be used for data that's ancillary to the head page (eg attaching
|
|
* buffer heads to tail pages after attaching buffer heads to the head page)
|
|
*/
|
|
#define page_private(page) ((page)->private)
|
|
|
|
static inline void set_page_private(struct page *page, unsigned long private)
|
|
{
|
|
page->private = private;
|
|
}
|
|
|
|
static inline void *folio_get_private(struct folio *folio)
|
|
{
|
|
return folio->private;
|
|
}
|
|
|
|
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 */
|
|
|
|
struct anon_vma_name {
|
|
struct kref kref;
|
|
/* The name needs to be at the end because it is dynamically sized. */
|
|
char name[];
|
|
};
|
|
|
|
/*
|
|
* 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
|
|
* 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. */
|
|
|
|
/*
|
|
* Access permissions of this VMA.
|
|
* See vmf_insert_mixed_prot() for discussion.
|
|
*/
|
|
pgprot_t vm_page_prot;
|
|
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.
|
|
*
|
|
* For private anonymous mappings, a pointer to a null terminated string
|
|
* containing the name given to the vma, or NULL if unnamed.
|
|
*/
|
|
|
|
union {
|
|
struct {
|
|
struct rb_node rb;
|
|
unsigned long rb_subtree_last;
|
|
} shared;
|
|
/*
|
|
* Serialized by mmap_sem. Never use directly because it is
|
|
* valid only when vm_file is NULL. Use anon_vma_name instead.
|
|
*/
|
|
struct anon_vma_name *anon_name;
|
|
};
|
|
|
|
/*
|
|
* 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_lock &
|
|
* 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 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 addresses 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;
|
|
|
|
#ifdef CONFIG_MEMBARRIER
|
|
/**
|
|
* @membarrier_state: Flags controlling membarrier behavior.
|
|
*
|
|
* This field is close to @pgd to hopefully fit in the same
|
|
* cache-line, which needs to be touched by switch_mm().
|
|
*/
|
|
atomic_t membarrier_state;
|
|
#endif
|
|
|
|
/**
|
|
* @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
|
|
*/
|
|
/*
|
|
* With some kernel config, the current mmap_lock's offset
|
|
* inside 'mm_struct' is at 0x120, which is very optimal, as
|
|
* its two hot fields 'count' and 'owner' sit in 2 different
|
|
* cachelines, and when mmap_lock is highly contended, both
|
|
* of the 2 fields will be accessed frequently, current layout
|
|
* will help to reduce cache bouncing.
|
|
*
|
|
* So please be careful with adding new fields before
|
|
* mmap_lock, which can easily push the 2 fields into one
|
|
* cacheline.
|
|
*/
|
|
struct rw_semaphore mmap_lock;
|
|
|
|
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;
|
|
|
|
/**
|
|
* @write_protect_seq: Locked when any thread is write
|
|
* protecting pages mapped by this mm to enforce a later COW,
|
|
* for instance during page table copying for fork().
|
|
*/
|
|
seqcount_t write_protect_seq;
|
|
|
|
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 */
|
|
|
|
#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_subscriptions *notifier_subscriptions;
|
|
#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() */
|
|
atomic_t tlb_flush_batched;
|
|
#endif
|
|
struct uprobes_state uprobes_state;
|
|
#ifdef CONFIG_PREEMPT_RT
|
|
struct rcu_head delayed_drop;
|
|
#endif
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
atomic_long_t hugetlb_usage;
|
|
#endif
|
|
struct work_struct async_put_work;
|
|
|
|
#ifdef CONFIG_IOMMU_SVA
|
|
u32 pasid;
|
|
#endif
|
|
#ifdef CONFIG_KSM
|
|
/*
|
|
* Represent how many pages of this process are involved in KSM
|
|
* merging.
|
|
*/
|
|
unsigned long ksm_merging_pages;
|
|
#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);
|
|
extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm);
|
|
extern void tlb_finish_mmu(struct mmu_gather *tlb);
|
|
|
|
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_COMPLETED: ->fault completed, meanwhile mmap lock released
|
|
* @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_COMPLETED = (__force vm_fault_t)0x004000,
|
|
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;
|
|
|
|
/**
|
|
* enum fault_flag - Fault flag definitions.
|
|
* @FAULT_FLAG_WRITE: Fault was a write fault.
|
|
* @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE.
|
|
* @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked.
|
|
* @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying.
|
|
* @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region.
|
|
* @FAULT_FLAG_TRIED: The fault has been tried once.
|
|
* @FAULT_FLAG_USER: The fault originated in userspace.
|
|
* @FAULT_FLAG_REMOTE: The fault is not for current task/mm.
|
|
* @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch.
|
|
* @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals.
|
|
* @FAULT_FLAG_UNSHARE: The fault is an unsharing request to unshare (and mark
|
|
* exclusive) a possibly shared anonymous page that is
|
|
* mapped R/O.
|
|
* @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached.
|
|
* We should only access orig_pte if this flag set.
|
|
*
|
|
* About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify
|
|
* whether we would allow page faults to retry by specifying these two
|
|
* fault flags correctly. Currently there can be three legal combinations:
|
|
*
|
|
* (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and
|
|
* this is the first try
|
|
*
|
|
* (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and
|
|
* we've already tried at least once
|
|
*
|
|
* (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry
|
|
*
|
|
* The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never
|
|
* be used. Note that page faults can be allowed to retry for multiple times,
|
|
* in which case we'll have an initial fault with flags (a) then later on
|
|
* continuous faults with flags (b). We should always try to detect pending
|
|
* signals before a retry to make sure the continuous page faults can still be
|
|
* interrupted if necessary.
|
|
*
|
|
* The combination FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE is illegal.
|
|
* FAULT_FLAG_UNSHARE is ignored and treated like an ordinary read fault when
|
|
* no existing R/O-mapped anonymous page is encountered.
|
|
*/
|
|
enum fault_flag {
|
|
FAULT_FLAG_WRITE = 1 << 0,
|
|
FAULT_FLAG_MKWRITE = 1 << 1,
|
|
FAULT_FLAG_ALLOW_RETRY = 1 << 2,
|
|
FAULT_FLAG_RETRY_NOWAIT = 1 << 3,
|
|
FAULT_FLAG_KILLABLE = 1 << 4,
|
|
FAULT_FLAG_TRIED = 1 << 5,
|
|
FAULT_FLAG_USER = 1 << 6,
|
|
FAULT_FLAG_REMOTE = 1 << 7,
|
|
FAULT_FLAG_INSTRUCTION = 1 << 8,
|
|
FAULT_FLAG_INTERRUPTIBLE = 1 << 9,
|
|
FAULT_FLAG_UNSHARE = 1 << 10,
|
|
FAULT_FLAG_ORIG_PTE_VALID = 1 << 11,
|
|
};
|
|
|
|
typedef unsigned int __bitwise zap_flags_t;
|
|
|
|
#endif /* _LINUX_MM_TYPES_H */
|