diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-15 20:37:06 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-15 20:37:06 +0200 |
commit | f56caedaf94f9ced5dbfcdb0060a3e788d2078af (patch) | |
tree | e213532d1b3d32f9f0e81948f3b23804baff287d /include/linux/mm_types.h | |
parent | a33f5c380c4bd3fa5278d690421b72052456d9fe (diff) | |
parent | 76fd0285b447991267e838842c0be7395eb454bb (diff) |
Merge branch 'akpm' (patches from Andrew)
Merge misc updates from Andrew Morton:
"146 patches.
Subsystems affected by this patch series: kthread, ia64, scripts,
ntfs, squashfs, ocfs2, vfs, and mm (slab-generic, slab, kmemleak,
dax, kasan, debug, pagecache, gup, shmem, frontswap, memremap,
memcg, selftests, pagemap, dma, vmalloc, memory-failure, hugetlb,
userfaultfd, vmscan, mempolicy, oom-kill, hugetlbfs, migration, thp,
ksm, page-poison, percpu, rmap, zswap, zram, cleanups, hmm, and
damon)"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (146 commits)
mm/damon: hide kernel pointer from tracepoint event
mm/damon/vaddr: hide kernel pointer from damon_va_three_regions() failure log
mm/damon/vaddr: use pr_debug() for damon_va_three_regions() failure logging
mm/damon/dbgfs: remove an unnecessary variable
mm/damon: move the implementation of damon_insert_region to damon.h
mm/damon: add access checking for hugetlb pages
Docs/admin-guide/mm/damon/usage: update for schemes statistics
mm/damon/dbgfs: support all DAMOS stats
Docs/admin-guide/mm/damon/reclaim: document statistics parameters
mm/damon/reclaim: provide reclamation statistics
mm/damon/schemes: account how many times quota limit has exceeded
mm/damon/schemes: account scheme actions that successfully applied
mm/damon: remove a mistakenly added comment for a future feature
Docs/admin-guide/mm/damon/usage: update for kdamond_pid and (mk|rm)_contexts
Docs/admin-guide/mm/damon/usage: mention tracepoint at the beginning
Docs/admin-guide/mm/damon/usage: remove redundant information
Docs/admin-guide/mm/damon/usage: update for scheme quotas and watermarks
mm/damon: convert macro functions to static inline functions
mm/damon: modify damon_rand() macro to static inline function
mm/damon: move damon_rand() definition into damon.h
...
Diffstat (limited to 'include/linux/mm_types.h')
-rw-r--r-- | include/linux/mm_types.h | 154 |
1 files changed, 65 insertions, 89 deletions
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 1ae3537c7920..3764c1b51b02 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -5,6 +5,7 @@ #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> @@ -386,6 +387,12 @@ 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 @@ -426,11 +433,19 @@ struct vm_area_struct { /* * 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. */ - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } shared; + + union { + struct { + struct rb_node rb; + unsigned long rb_subtree_last; + } shared; + /* Serialized by mmap_sem. */ + struct anon_vma_name *anon_name; + }; /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma @@ -632,7 +647,7 @@ struct mm_struct { atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ - bool tlb_flush_batched; + atomic_t tlb_flush_batched; #endif struct uprobes_state uprobes_state; #ifdef CONFIG_PREEMPT_RT @@ -677,90 +692,6 @@ 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); -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; /** @@ -875,4 +806,49 @@ 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. + * + * 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. + */ +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, +}; + #endif /* _LINUX_MM_TYPES_H */ |