/* * mm/rmap.c - physical to virtual reverse mappings * * Copyright 2001, Rik van Riel * Released under the General Public License (GPL). * * Simple, low overhead reverse mapping scheme. * Please try to keep this thing as modular as possible. * * Provides methods for unmapping each kind of mapped page: * the anon methods track anonymous pages, and * the file methods track pages belonging to an inode. * * Original design by Rik van Riel 2001 * File methods by Dave McCracken 2003, 2004 * Anonymous methods by Andrea Arcangeli 2004 * Contributions by Hugh Dickins 2003, 2004 */ /* * Lock ordering in mm: * * inode->i_mutex (while writing or truncating, not reading or faulting) * mm->mmap_sem * page->flags PG_locked (lock_page) * mapping->i_mmap_rwsem * anon_vma->rwsem * mm->page_table_lock or pte_lock * zone->lru_lock (in mark_page_accessed, isolate_lru_page) * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) * mem_cgroup_{begin,end}_page_stat (memcg->move_lock) * mapping->tree_lock (widely used) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * mapping->tree_lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mutex (memory_failure, collect_procs_anon) * ->tasklist_lock * pte map lock */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "internal.h" static struct kmem_cache *anon_vma_cachep; static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { struct anon_vma *anon_vma; anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); anon_vma->degree = 1; /* Reference for first vma */ anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. */ anon_vma->root = anon_vma; } return anon_vma; } static inline void anon_vma_free(struct anon_vma *anon_vma) { VM_BUG_ON(atomic_read(&anon_vma->refcount)); /* * Synchronize against page_lock_anon_vma_read() such that * we can safely hold the lock without the anon_vma getting * freed. * * Relies on the full mb implied by the atomic_dec_and_test() from * put_anon_vma() against the acquire barrier implied by * down_read_trylock() from page_lock_anon_vma_read(). This orders: * * page_lock_anon_vma_read() VS put_anon_vma() * down_read_trylock() atomic_dec_and_test() * LOCK MB * atomic_read() rwsem_is_locked() * * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); } static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { return kmem_cache_alloc(anon_vma_chain_cachep, gfp); } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } static void anon_vma_chain_link(struct vm_area_struct *vma, struct anon_vma_chain *avc, struct anon_vma *anon_vma) { avc->vma = vma; avc->anon_vma = anon_vma; list_add(&avc->same_vma, &vma->anon_vma_chain); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); } /** * anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question * * This makes sure the memory mapping described by 'vma' has * an 'anon_vma' attached to it, so that we can associate the * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, but if * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in page_lock_anon_vma_read() * and that may actually touch the spinlock even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * * As a result, we need to do proper anon_vma locking even * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. * * This must be called with the mmap_sem held for reading. */ int anon_vma_prepare(struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; might_sleep(); if (unlikely(!anon_vma)) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *allocated; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_enomem; anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; allocated = anon_vma; } anon_vma_lock_write(anon_vma); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); /* vma reference or self-parent link for new root */ anon_vma->degree++; allocated = NULL; avc = NULL; } spin_unlock(&mm->page_table_lock); anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); } return 0; out_enomem_free_avc: anon_vma_chain_free(avc); out_enomem: return -ENOMEM; } /* * This is a useful helper function for locking the anon_vma root as * we traverse the vma->anon_vma_chain, looping over anon_vma's that * have the same vma. * * Such anon_vma's should have the same root, so you'd expect to see * just a single mutex_lock for the whole traversal. */ static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma) { struct anon_vma *new_root = anon_vma->root; if (new_root != root) { if (WARN_ON_ONCE(root)) up_write(&root->rwsem); root = new_root; down_write(&root->rwsem); } return root; } static inline void unlock_anon_vma_root(struct anon_vma *root) { if (root) up_write(&root->rwsem); } /* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. * * If dst->anon_vma is NULL this function tries to find and reuse existing * anon_vma which has no vmas and only one child anon_vma. This prevents * degradation of anon_vma hierarchy to endless linear chain in case of * constantly forking task. On the other hand, an anon_vma with more than one * child isn't reused even if there was no alive vma, thus rmap walker has a * good chance of avoiding scanning the whole hierarchy when it searches where * page is mapped. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { struct anon_vma_chain *avc, *pavc; struct anon_vma *root = NULL; list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { struct anon_vma *anon_vma; avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!avc)) { unlock_anon_vma_root(root); root = NULL; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto enomem_failure; } anon_vma = pavc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_chain_link(dst, avc, anon_vma); /* * Reuse existing anon_vma if its degree lower than two, * that means it has no vma and only one anon_vma child. * * Do not chose parent anon_vma, otherwise first child * will always reuse it. Root anon_vma is never reused: * it has self-parent reference and at least one child. */ if (!dst->anon_vma && anon_vma != src->anon_vma && anon_vma->degree < 2) dst->anon_vma = anon_vma; } if (dst->anon_vma) dst->anon_vma->degree++; unlock_anon_vma_root(root); return 0; enomem_failure: /* * dst->anon_vma is dropped here otherwise its degree can be incorrectly * decremented in unlink_anon_vmas(). * We can safely do this because callers of anon_vma_clone() don't care * about dst->anon_vma if anon_vma_clone() failed. */ dst->anon_vma = NULL; unlink_anon_vmas(dst); return -ENOMEM; } /* * Attach vma to its own anon_vma, as well as to the anon_vmas that * the corresponding VMA in the parent process is attached to. * Returns 0 on success, non-zero on failure. */ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; int error; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ vma->anon_vma = NULL; /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ error = anon_vma_clone(vma, pvma); if (error) return error; /* An existing anon_vma has been reused, all done then. */ if (vma->anon_vma) return 0; /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; /* * The root anon_vma's spinlock is the lock actually used when we * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); anon_vma->parent->degree++; anon_vma_unlock_write(anon_vma); return 0; out_error_free_anon_vma: put_anon_vma(anon_vma); out_error: unlink_anon_vmas(vma); return -ENOMEM; } void unlink_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; struct anon_vma *root = NULL; /* * Unlink each anon_vma chained to the VMA. This list is ordered * from newest to oldest, ensuring the root anon_vma gets freed last. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); /* * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root)) { anon_vma->parent->degree--; continue; } list_del(&avc->same_vma); anon_vma_chain_free(avc); } if (vma->anon_vma) vma->anon_vma->degree--; unlock_anon_vma_root(root); /* * Iterate the list once more, it now only contains empty and unlinked * anon_vmas, destroy them. Could not do before due to __put_anon_vma() * needing to write-acquire the anon_vma->root->rwsem. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; BUG_ON(anon_vma->degree); put_anon_vma(anon_vma); list_del(&avc->same_vma); anon_vma_chain_free(avc); } } static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; init_rwsem(&anon_vma->rwsem); atomic_set(&anon_vma->refcount, 0); anon_vma->rb_root = RB_ROOT; } void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_DESTROY_BY_RCU|SLAB_PANIC, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC); } /* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against page_remove_rmap() * the best this function can do is return a locked anon_vma that might * have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). * * In case it was remapped to a different anon_vma, the new anon_vma will be a * child of the old anon_vma, and the anon_vma lifetime rules will therefore * ensure that any anon_vma obtained from the page will still be valid for as * long as we observe page_mapped() [ hence all those page_mapped() tests ]. * * All users of this function must be very careful when walking the anon_vma * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is DESTROY_BY_RCU and we know from page_remove_rmap() * that the anon_vma pointer from page->mapping is valid if there is a * mapcount, we can dereference the anon_vma after observing those. */ struct anon_vma *page_get_anon_vma(struct page *page) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } /* * If this page is still mapped, then its anon_vma cannot have been * freed. But if it has been unmapped, we have no security against the * anon_vma structure being freed and reused (for another anon_vma: * SLAB_DESTROY_BY_RCU guarantees that - so the atomic_inc_not_zero() * above cannot corrupt). */ if (!page_mapped(page)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } out: rcu_read_unlock(); return anon_vma; } /* * Similar to page_get_anon_vma() except it locks the anon_vma. * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with page_get_anon_vma() and then block on the mutex. */ struct anon_vma *page_lock_anon_vma_read(struct page *page) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * If the page is still mapped, then this anon_vma is still * its anon_vma, and holding the mutex ensures that it will * not go away, see anon_vma_free(). */ if (!page_mapped(page)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } goto out; } /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } if (!page_mapped(page)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } /* we pinned the anon_vma, its safe to sleep */ rcu_read_unlock(); anon_vma_lock_read(anon_vma); if (atomic_dec_and_test(&anon_vma->refcount)) { /* * Oops, we held the last refcount, release the lock * and bail -- can't simply use put_anon_vma() because * we'll deadlock on the anon_vma_lock_write() recursion. */ anon_vma_unlock_read(anon_vma); __put_anon_vma(anon_vma); anon_vma = NULL; } return anon_vma; out: rcu_read_unlock(); return anon_vma; } void page_unlock_anon_vma_read(struct anon_vma *anon_vma) { anon_vma_unlock_read(anon_vma); } /* * At what user virtual address is page expected in @vma? */ static inline unsigned long __vma_address(struct page *page, struct vm_area_struct *vma) { pgoff_t pgoff = page_to_pgoff(page); return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); } inline unsigned long vma_address(struct page *page, struct vm_area_struct *vma) { unsigned long address = __vma_address(page, vma); /* page should be within @vma mapping range */ VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); return address; } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH static void percpu_flush_tlb_batch_pages(void *data) { /* * All TLB entries are flushed on the assumption that it is * cheaper to flush all TLBs and let them be refilled than * flushing individual PFNs. Note that we do not track mm's * to flush as that might simply be multiple full TLB flushes * for no gain. */ count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); flush_tlb_local(); } /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed * before any IO is initiated on the page to prevent lost writes. Similarly, * it must be flushed before freeing to prevent data leakage. */ void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; int cpu; if (!tlb_ubc->flush_required) return; cpu = get_cpu(); trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, -1UL); if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) percpu_flush_tlb_batch_pages(&tlb_ubc->cpumask); if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) { smp_call_function_many(&tlb_ubc->cpumask, percpu_flush_tlb_batch_pages, (void *)tlb_ubc, true); } cpumask_clear(&tlb_ubc->cpumask); tlb_ubc->flush_required = false; tlb_ubc->writable = false; put_cpu(); } /* Flush iff there are potentially writable TLB entries that can race with IO */ void try_to_unmap_flush_dirty(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (tlb_ubc->writable) try_to_unmap_flush(); } static void set_tlb_ubc_flush_pending(struct mm_struct *mm, struct page *page, bool writable) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(mm)); tlb_ubc->flush_required = true; /* * If the PTE was dirty then it's best to assume it's writable. The * caller must us
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/smp.h>

#include <linux/blk-mq.h>
#include "blk-mq.h"
#include "blk-mq-tag.h"

static void blk_mq_sysfs_release(struct kobject *kobj)
{
}

struct blk_mq_ctx_sysfs_entry {
	struct attribute attr;
	ssize_t (*show)(struct blk_mq_ctx *, char *);
	ssize_t (*store)(struct blk_mq_ctx *, const char *, size_t);
};

struct blk_mq_hw_ctx_sysfs_entry {
	struct attribute attr;
	ssize_t (*show)(struct blk_mq_hw_ctx *, char *);
	ssize_t (*store)(struct blk_mq_hw_ctx *, const char *, size_t);
};

static ssize_t blk_mq_sysfs_show(struct kobject *kobj, struct attribute *attr,
				 char *page)
{
	struct blk_mq_ctx_sysfs_entry *entry;
	struct blk_mq_ctx *ctx;
	struct request_queue *q;
	ssize_t res;

	entry = container_of(attr, struct blk_mq_ctx_sysfs_entry, attr);
	ctx = container_of(kobj, struct blk_mq_ctx, kobj);
	q = ctx->queue;

	if (!entry->show)
		return -EIO;

	res = -ENOENT;
	mutex_lock(&q->sysfs_lock);
	if (!blk_queue_dying(q))
		res = entry->show(ctx, page);
	mutex_unlock(&q->sysfs_lock);
	return res;
}

static ssize_t blk_mq_sysfs_store(struct kobject *kobj, struct attribute *attr,
				  const char *page, size_t length)
{
	struct blk_mq_ctx_sysfs_entry *entry;
	struct blk_mq_ctx *ctx;
	struct request_queue *q;
	ssize_t res;

	entry = container_of(attr, struct blk_mq_ctx_sysfs_entry, attr);
	ctx = container_of(kobj, struct blk_mq_ctx, kobj);
	q = ctx->queue;

	if (!entry->store)
		return -EIO;

	res = -ENOENT;
	mutex_lock(&q->sysfs_lock);
	if (!blk_queue_dying(q))
		res = entry->store(ctx, page, length);
	mutex_unlock(&q->sysfs_lock);
	return res;
}

static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj,
				    struct attribute *attr, char *page)
{
	struct blk_mq_hw_ctx_sysfs_entry *entry;
	struct blk_mq_hw_ctx *hctx;
	struct request_queue *q;
	ssize_t res;

	entry = container_of(attr, struct blk_mq_hw_ctx_sysfs_entry, attr);
	hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj);
	q = hctx->queue;

	if (!entry->show)
		return -EIO;

	res = -ENOENT;
	mutex_lock(&q->sysfs_lock);
	if (!blk_queue_dying(q))
		res = entry->show(hctx, page);
	mutex_unlock(&q->sysfs_lock);
	return res;
}

static ssize_t blk_mq_hw_sysfs_store(struct kobject *kobj,
				     struct attribute *attr, const char *page,
				     size_t length)
{
	struct blk_mq_hw_ctx_sysfs_entry *entry;
	struct blk_mq_hw_ctx *hctx;
	struct request_queue *q;
	ssize_t res;

	entry = container_of(attr, struct blk_mq_hw_ctx_sysfs_entry, attr);
	hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj);
	q = hctx->queue;

	if (!entry->store)
		return -EIO;

	res = -ENOENT;
	mutex_lock(&q->sysfs_lock);
	if (!blk_queue_dying(q))
		res = entry->store(hctx, page, length);
	mutex_unlock(&q->sysfs_lock);
	return res;
}

static ssize_t blk_mq_sysfs_dispatched_show(struct blk_mq_ctx *ctx, char *page)
{
	ret