diff options
Diffstat (limited to 'mm/shmem.c')
| -rw-r--r-- | mm/shmem.c | 764 |
1 files changed, 571 insertions, 193 deletions
diff --git a/mm/shmem.c b/mm/shmem.c index 1f18c9d0d93..469f90d5605 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -66,6 +66,9 @@ static struct vfsmount *shm_mnt; #include <linux/highmem.h> #include <linux/seq_file.h> #include <linux/magic.h> +#include <linux/syscalls.h> +#include <linux/fcntl.h> +#include <uapi/linux/memfd.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -80,11 +83,12 @@ static struct vfsmount *shm_mnt; #define SHORT_SYMLINK_LEN 128 /* - * shmem_fallocate and shmem_writepage communicate via inode->i_private - * (with i_mutex making sure that it has only one user at a time): - * we would prefer not to enlarge the shmem inode just for that. + * shmem_fallocate communicates with shmem_fault or shmem_writepage via + * inode->i_private (with i_mutex making sure that it has only one user at + * a time): we would prefer not to enlarge the shmem inode just for that. */ struct shmem_falloc { + wait_queue_head_t *waitq; /* faults into hole wait for punch to end */ pgoff_t start; /* start of range currently being fallocated */ pgoff_t next; /* the next page offset to be fallocated */ pgoff_t nr_falloced; /* how many new pages have been fallocated */ @@ -148,6 +152,19 @@ static inline void shmem_unacct_size(unsigned long flags, loff_t size) vm_unacct_memory(VM_ACCT(size)); } +static inline int shmem_reacct_size(unsigned long flags, + loff_t oldsize, loff_t newsize) +{ + if (!(flags & VM_NORESERVE)) { + if (VM_ACCT(newsize) > VM_ACCT(oldsize)) + return security_vm_enough_memory_mm(current->mm, + VM_ACCT(newsize) - VM_ACCT(oldsize)); + else if (VM_ACCT(newsize) < VM_ACCT(oldsize)) + vm_unacct_memory(VM_ACCT(oldsize) - VM_ACCT(newsize)); + } + return 0; +} + /* * ... whereas tmpfs objects are accounted incrementally as * pages are allocated, in order to allow huge sparse files. @@ -242,19 +259,17 @@ static int shmem_radix_tree_replace(struct address_space *mapping, pgoff_t index, void *expected, void *replacement) { void **pslot; - void *item = NULL; + void *item; VM_BUG_ON(!expected); + VM_BUG_ON(!replacement); pslot = radix_tree_lookup_slot(&mapping->page_tree, index); - if (pslot) - item = radix_tree_deref_slot_protected(pslot, - &mapping->tree_lock); + if (!pslot) + return -ENOENT; + item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock); if (item != expected) return -ENOENT; - if (replacement) - radix_tree_replace_slot(pslot, replacement); - else - radix_tree_delete(&mapping->page_tree, index); + radix_tree_replace_slot(pslot, replacement); return 0; } @@ -281,7 +296,7 @@ static bool shmem_confirm_swap(struct address_space *mapping, */ static int shmem_add_to_page_cache(struct page *page, struct address_space *mapping, - pgoff_t index, gfp_t gfp, void *expected) + pgoff_t index, void *expected) { int error; @@ -331,84 +346,20 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) } /* - * Like find_get_pages, but collecting swap entries as well as pages. - */ -static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping, - pgoff_t start, unsigned int nr_pages, - struct page **pages, pgoff_t *indices) -{ - void **slot; - unsigned int ret = 0; - struct radix_tree_iter iter; - - if (!nr_pages) - return 0; - - rcu_read_lock(); -restart: - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { - struct page *page; -repeat: - page = radix_tree_deref_slot(slot); - if (unlikely(!page)) - continue; - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) - goto restart; - /* - * Otherwise, we must be storing a swap entry - * here as an exceptional entry: so return it - * without attempting to raise page count. - */ - goto export; - } - if (!page_cache_get_speculative(page)) - goto repeat; - - /* Has the page moved? */ - if (unlikely(page != *slot)) { - page_cache_release(page); - goto repeat; - } -export: - indices[ret] = iter.index; - pages[ret] = page; - if (++ret == nr_pages) - break; - } - rcu_read_unlock(); - return ret; -} - -/* * Remove swap entry from radix tree, free the swap and its page cache. */ static int shmem_free_swap(struct address_space *mapping, pgoff_t index, void *radswap) { - int error; + void *old; spin_lock_irq(&mapping->tree_lock); - error = shmem_radix_tree_replace(mapping, index, radswap, NULL); + old = radix_tree_delete_item(&mapping->page_tree, index, radswap); spin_unlock_irq(&mapping->tree_lock); - if (!error) - free_swap_and_cache(radix_to_swp_entry(radswap)); - return error; -} - -/* - * Pagevec may contain swap entries, so shuffle up pages before releasing. - */ -static void shmem_deswap_pagevec(struct pagevec *pvec) -{ - int i, j; - - for (i = 0, j = 0; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; - if (!radix_tree_exceptional_entry(page)) - pvec->pages[j++] = page; - } - pvec->nr = j; + if (old != radswap) + return -ENOENT; + free_swap_and_cache(radix_to_swp_entry(radswap)); + return 0; } /* @@ -429,12 +380,12 @@ void shmem_unlock_mapping(struct address_space *mapping) * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it * has finished, if it hits a row of PAGEVEC_SIZE swap entries. */ - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - PAGEVEC_SIZE, pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + PAGEVEC_SIZE, pvec.pages, indices); if (!pvec.nr) break; index = indices[pvec.nr - 1] + 1; - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); check_move_unevictable_pages(pvec.pages, pvec.nr); pagevec_release(&pvec); cond_resched(); @@ -466,12 +417,11 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, pagevec_init(&pvec, 0); index = start; while (index < end) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + pvec.pages, indices); if (!pvec.nr) break; - mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; @@ -497,9 +447,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); - mem_cgroup_uncharge_end(); cond_resched(); index++; } @@ -533,23 +482,20 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, return; index = start; - for ( ; ; ) { + while (index < end) { cond_resched(); - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + + pvec.nr = find_get_entries(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.pages, indices); if (!pvec.nr) { - if (index == start || unfalloc) + /* If all gone or hole-punch or unfalloc, we're done */ + if (index == start || end != -1) break; + /* But if truncating, restart to make sure all gone */ index = start; continue; } - if ((index == start || unfalloc) && indices[0] >= end) { - shmem_deswap_pagevec(&pvec); - pagevec_release(&pvec); - break; - } - mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; @@ -560,8 +506,12 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (radix_tree_exceptional_entry(page)) { if (unfalloc) continue; - nr_swaps_freed += !shmem_free_swap(mapping, - index, page); + if (shmem_free_swap(mapping, index, page)) { + /* Swap was replaced by page: retry */ + index--; + break; + } + nr_swaps_freed++; continue; } @@ -570,13 +520,17 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (page->mapping == mapping) { VM_BUG_ON_PAGE(PageWriteback(page), page); truncate_inode_page(mapping, page); + } else { + /* Page was replaced by swap: retry */ + unlock_page(page); + index--; + break; } } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); - mem_cgroup_uncharge_end(); index++; } @@ -596,6 +550,7 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range); static int shmem_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = dentry->d_inode; + struct shmem_inode_info *info = SHMEM_I(inode); int error; error = inode_change_ok(inode, attr); @@ -606,7 +561,16 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) loff_t oldsize = inode->i_size; loff_t newsize = attr->ia_size; + /* protected by i_mutex */ + if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) || + (newsize > oldsize && (info->seals & F_SEAL_GROW))) + return -EPERM; + if (newsize != oldsize) { + error = shmem_reacct_size(SHMEM_I(inode)->flags, + oldsize, newsize); + if (error) + return error; i_size_write(inode, newsize); inode->i_ctime = inode->i_mtime = CURRENT_TIME; } @@ -662,7 +626,7 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, radswap = swp_to_radix_entry(swap); index = radix_tree_locate_item(&mapping->page_tree, radswap); if (index == -1) - return 0; + return -EAGAIN; /* tell shmem_unuse we found nothing */ /* * Move _head_ to start search for next from here. @@ -707,7 +671,7 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, */ if (!error) error = shmem_add_to_page_cache(*pagep, mapping, index, - GFP_NOWAIT, radswap); + radswap); if (error != -ENOMEM) { /* * Truncation and eviction use free_swap_and_cache(), which @@ -721,7 +685,6 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, spin_unlock(&info->lock); swap_free(swap); } - error = 1; /* not an error, but entry was found */ } return error; } @@ -733,7 +696,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page) { struct list_head *this, *next; struct shmem_inode_info *info; - int found = 0; + struct mem_cgroup *memcg; int error = 0; /* @@ -748,26 +711,32 @@ int shmem_unuse(swp_entry_t swap, struct page *page) * the shmem_swaplist_mutex which might hold up shmem_writepage(). * Charged back to the user (not to caller) when swap account is used. */ - error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL); + error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg); if (error) goto out; /* No radix_tree_preload: swap entry keeps a place for page in tree */ + error = -EAGAIN; mutex_lock(&shmem_swaplist_mutex); list_for_each_safe(this, next, &shmem_swaplist) { info = list_entry(this, struct shmem_inode_info, swaplist); if (info->swapped) - found = shmem_unuse_inode(info, swap, &page); + error = shmem_unuse_inode(info, swap, &page); else list_del_init(&info->swaplist); cond_resched(); - if (found) + if (error != -EAGAIN) break; + /* found nothing in this: move on to search the next */ } mutex_unlock(&shmem_swaplist_mutex); - if (found < 0) - error = found; + if (error) { + if (error != -ENOMEM) + error = 0; + mem_cgroup_cancel_charge(page, memcg); + } else + mem_cgroup_commit_charge(page, memcg, true); out: unlock_page(page); page_cache_release(page); @@ -824,6 +793,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) spin_lock(&inode->i_lock); shmem_falloc = inode->i_private; if (shmem_falloc && + !shmem_falloc->waitq && index >= shmem_falloc->start && index < shmem_falloc->next) shmem_falloc->nr_unswapped++; @@ -870,7 +840,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) } mutex_unlock(&shmem_swaplist_mutex); - swapcache_free(swap, NULL); + swapcache_free(swap); redirty: set_page_dirty(page); if (wbc->for_reclaim) @@ -1043,7 +1013,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, */ oldpage = newpage; } else { - mem_cgroup_replace_page_cache(oldpage, newpage); + mem_cgroup_migrate(oldpage, newpage, false); lru_cache_add_anon(newpage); *pagep = newpage; } @@ -1070,6 +1040,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info; struct shmem_sb_info *sbinfo; + struct mem_cgroup *memcg; struct page *page; swp_entry_t swap; int error; @@ -1080,7 +1051,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, return -EFBIG; repeat: swap.val = 0; - page = find_lock_page(mapping, index); + page = find_lock_entry(mapping, index); if (radix_tree_exceptional_entry(page)) { swap = radix_to_swp_entry(page); page = NULL; @@ -1092,6 +1063,9 @@ repeat: goto failed; } + if (page && sgp == SGP_WRITE) + mark_page_accessed(page); + /* fallocated page? */ if (page && !PageUptodate(page)) { if (sgp != SGP_READ) @@ -1145,11 +1119,10 @@ repeat: goto failed; } - error = mem_cgroup_cache_charge(page, current->mm, - gfp & GFP_RECLAIM_MASK); + error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, - gfp, swp_to_radix_entry(swap)); + swp_to_radix_entry(swap)); /* * We already confirmed swap under page lock, and make * no memory allocation here, so usually no possibility @@ -1162,17 +1135,24 @@ repeat: * Reset swap.val? No, leave it so "failed" goes back to * "repeat": reading a hole and writing should succeed. */ - if (error) + if (error) { + mem_cgroup_cancel_charge(page, memcg); delete_from_swap_cache(page); + } } if (error) goto failed; + mem_cgroup_commit_charge(page, memcg, true); + spin_lock(&info->lock); info->swapped--; shmem_recalc_inode(inode); spin_unlock(&info->lock); + if (sgp == SGP_WRITE) + mark_page_accessed(page); + delete_from_swap_cache(page); set_page_dirty(page); swap_free(swap); @@ -1197,22 +1177,25 @@ repeat: goto decused; } - SetPageSwapBacked(page); + __SetPageSwapBacked(page); __set_page_locked(page); - error = mem_cgroup_cache_charge(page, current->mm, - gfp & GFP_RECLAIM_MASK); + if (sgp == SGP_WRITE) + __SetPageReferenced(page); + + error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg); if (error) goto decused; error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, - gfp, NULL); + NULL); radix_tree_preload_end(); } if (error) { - mem_cgroup_uncharge_cache_page(page); + mem_cgroup_cancel_charge(page, memcg); goto decused; } + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_anon(page); spin_lock(&info->lock); @@ -1298,6 +1281,64 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) int error; int ret = VM_FAULT_LOCKED; + /* + * Trinity finds that probing a hole which tmpfs is punching can + * prevent the hole-punch from ever completing: which in turn + * locks writers out with its hold on i_mutex. So refrain from + * faulting pages into the hole while it's being punched. Although + * shmem_undo_range() does remove the additions, it may be unable to + * keep up, as each new page needs its own unmap_mapping_range() call, + * and the i_mmap tree grows ever slower to scan if new vmas are added. + * + * It does not matter if we sometimes reach this check just before the + * hole-punch begins, so that one fault then races with the punch: + * we just need to make racing faults a rare case. + * + * The implementation below would be much simpler if we just used a + * standard mutex or completion: but we cannot take i_mutex in fault, + * and bloating every shmem inode for this unlikely case would be sad. + */ + if (unlikely(inode->i_private)) { + struct shmem_falloc *shmem_falloc; + + spin_lock(&inode->i_lock); + shmem_falloc = inode->i_private; + if (shmem_falloc && + shmem_falloc->waitq && + vmf->pgoff >= shmem_falloc->start && + vmf->pgoff < shmem_falloc->next) { + wait_queue_head_t *shmem_falloc_waitq; + DEFINE_WAIT(shmem_fault_wait); + + ret = VM_FAULT_NOPAGE; + if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) && + !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) { + /* It's polite to up mmap_sem if we can */ + up_read(&vma->vm_mm->mmap_sem); + ret = VM_FAULT_RETRY; + } + + shmem_falloc_waitq = shmem_falloc->waitq; + prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, + TASK_UNINTERRUPTIBLE); + spin_unlock(&inode->i_lock); + schedule(); + + /* + * shmem_falloc_waitq points into the shmem_fallocate() + * stack of the hole-punching task: shmem_falloc_waitq + * is usually invalid by the time we reach here, but + * finish_wait() does not dereference it in that case; + * though i_lock needed lest racing with wake_up_all(). + */ + spin_lock(&inode->i_lock); + finish_wait(shmem_falloc_waitq, &shmem_fault_wait); + spin_unlock(&inode->i_lock); + return ret; + } + spin_unlock(&inode->i_lock); + } + error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret); if (error) return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS); @@ -1380,6 +1421,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); spin_lock_init(&info->lock); + info->seals = F_SEAL_SEAL; info->flags = flags & VM_NORESERVE; INIT_LIST_HEAD(&info->swaplist); simple_xattrs_init(&info->xattrs); @@ -1417,6 +1459,11 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode return inode; } +bool shmem_mapping(struct address_space *mapping) +{ + return mapping->backing_dev_info == &shmem_backing_dev_info; +} + #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; @@ -1433,7 +1480,17 @@ shmem_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; + struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t index = pos >> PAGE_CACHE_SHIFT; + + /* i_mutex is held by caller */ + if (unlikely(info->seals)) { + if (info->seals & F_SEAL_WRITE) + return -EPERM; + if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size) + return -EPERM; + } + return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); } @@ -1462,13 +1519,17 @@ shmem_write_end(struct file *file, struct address_space *mapping, return copied; } -static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor) +static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { - struct inode *inode = file_inode(filp); + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; pgoff_t index; unsigned long offset; enum sgp_type sgp = SGP_READ; + int error = 0; + ssize_t retval = 0; + loff_t *ppos = &iocb->ki_pos; /* * Might this read be for a stacking filesystem? Then when reading @@ -1496,10 +1557,10 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ break; } - desc->error = shmem_getpage(inode, index, &page, sgp, NULL); - if (desc->error) { - if (desc->error == -EINVAL) - desc->error = 0; + error = shmem_getpage(inode, index, &page, sgp, NULL); + if (error) { + if (error == -EINVAL) + error = 0; break; } if (page) @@ -1543,61 +1604,26 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... - * - * The actor routine returns how many bytes were actually used.. - * NOTE! This may not be the same as how much of a user buffer - * we filled up (we may be padding etc), so we can only update - * "pos" here (the actor routine has to update the user buffer - * pointers and the remaining count). */ - ret = actor(desc, page, offset, nr); + ret = copy_page_to_iter(page, offset, nr, to); + retval += ret; offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; page_cache_release(page); - if (ret != nr || !desc->count) + if (!iov_iter_count(to)) break; - + if (ret < nr) { + error = -EFAULT; + break; + } cond_resched(); } *ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset; - file_accessed(filp); -} - -static ssize_t shmem_file_aio_read(struct kiocb *iocb, - const struct iovec *iov, unsigned long nr_segs, loff_t pos) -{ - struct file *filp = iocb->ki_filp; - ssize_t retval; - unsigned long seg; - size_t count; - loff_t *ppos = &iocb->ki_pos; - - retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); - if (retval) - return retval; - - for (seg = 0; seg < nr_segs; seg++) { - read_descriptor_t desc; - - desc.written = 0; - desc.arg.buf = iov[seg].iov_base; - desc.count = iov[seg].iov_len; - if (desc.count == 0) - continue; - desc.error = 0; - do_shmem_file_read(filp, ppos, &desc, file_read_actor); - retval += desc.written; - if (desc.error) { - retval = retval ?: desc.error; - break; - } - if (desc.count > 0) - break; - } - return retval; + file_accessed(file); + return retval ? retval : error; } static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, @@ -1636,7 +1662,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, index = *ppos >> PAGE_CACHE_SHIFT; loff = *ppos & ~PAGE_CACHE_MASK; req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - nr_pages = min(req_pages, pipe->buffers); + nr_pages = min(req_pages, spd.nr_pages_max); spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, spd.pages); @@ -1729,7 +1755,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, pagevec_init(&pvec, 0); pvec.nr = 1; /* start small: we may be there already */ while (!done) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + pvec.nr = find_get_entries(mapping, index, pvec.nr, pvec.pages, indices); if (!pvec.nr) { if (whence == SEEK_DATA) @@ -1756,7 +1782,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, break; } } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); pvec.nr = PAGEVEC_SIZE; cond_resched(); @@ -1802,27 +1828,271 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) return offset; } +/* + * We need a tag: a new tag would expand every radix_tree_node by 8 bytes, + * so reuse a tag which we firmly believe is never set or cleared on shmem. + */ +#define SHMEM_TAG_PINNED PAGECACHE_TAG_TOWRITE +#define LAST_SCAN 4 /* about 150ms max */ + +static void shmem_tag_pins(struct address_space *mapping) +{ + struct radix_tree_iter iter; + void **slot; + pgoff_t start; + struct page *page; + + lru_add_drain(); + start = 0; + rcu_read_lock(); + +restart: + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + page = radix_tree_deref_slot(slot); + if (!page || radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) + goto restart; + } else if (page_count(page) - page_mapcount(page) > 1) { + spin_lock_irq(&mapping->tree_lock); + radix_tree_tag_set(&mapping->page_tree, iter.index, + SHMEM_TAG_PINNED); + spin_unlock_irq(&mapping->tree_lock); + } + + if (need_resched()) { + cond_resched_rcu(); + start = iter.index + 1; + goto restart; + } + } + rcu_read_unlock(); +} + +/* + * Setting SEAL_WRITE requires us to verify there's no pending writer. However, + * via get_user_pages(), drivers might have some pending I/O without any active + * user-space mappings (eg., direct-IO, AIO). Therefore, we look at all pages + * and see whether it has an elevated ref-count. If so, we tag them and wait for + * them to be dropped. + * The caller must guarantee that no new user will acquire writable references + * to those pages to avoid races. + */ +static int shmem_wait_for_pins(struct address_space *mapping) +{ + struct radix_tree_iter iter; + void **slot; + pgoff_t start; + struct page *page; + int error, scan; + + shmem_tag_pins(mapping); + + error = 0; + for (scan = 0; scan <= LAST_SCAN; scan++) { + if (!radix_tree_tagged(&mapping->page_tree, SHMEM_TAG_PINNED)) + break; + + if (!scan) + lru_add_drain_all(); + else if (schedule_timeout_killable((HZ << scan) / 200)) + scan = LAST_SCAN; + + start = 0; + rcu_read_lock(); +restart: + radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter, + start, SHMEM_TAG_PINNED) { + + page = radix_tree_deref_slot(slot); + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) + goto restart; + + page = NULL; + } + + if (page && + page_count(page) - page_mapcount(page) != 1) { + if (scan < LAST_SCAN) + goto continue_resched; + + /* + * On the last scan, we clean up all those tags + * we inserted; but make a note that we still + * found pages pinned. + */ + error = -EBUSY; + } + + spin_lock_irq(&mapping->tree_lock); + radix_tree_tag_clear(&mapping->page_tree, + iter.index, SHMEM_TAG_PINNED); + spin_unlock_irq(&mapping->tree_lock); +continue_resched: + if (need_resched()) { + cond_resched_rcu(); + start = iter.index + 1; + goto restart; + } + } + rcu_read_unlock(); + } + + return error; +} + +#define F_ALL_SEALS (F_SEAL_SEAL | \ + F_SEAL_SHRINK | \ + F_SEAL_GROW | \ + F_SEAL_WRITE) + +int shmem_add_seals(struct file *file, unsigned int seals) +{ + struct inode *inode = file_inode(file); + struct shmem_inode_info *info = SHMEM_I(inode); + int error; + + /* + * SEALING + * Sealing allows multiple parties to share a shmem-file but restrict + * access to a specific subset of file operations. Seals can only be + * added, but never removed. This way, mutually untrusted parties can + * share common memory regions with a well-defined policy. A malicious + * peer can thus never perform unwanted operations on a shared object. + * + * Seals are only supported on special shmem-files and always affect + * the whole underlying inode. Once a seal is set, it may prevent some + * kinds of access to the file. Currently, the following seals are + * defined: + * SEAL_SEAL: Prevent further seals from being set on this file + * SEAL_SHRINK: Prevent the file from shrinking + * SEAL_GROW: Prevent the file from growing + * SEAL_WRITE: Prevent write access to the file + * + * As we don't require any trust relationship between two parties, we + * must prevent seals from being removed. Therefore, sealing a file + * only adds a given set of seals to the file, it never touches + * existing seals. Furthermore, the "setting seals"-operation can be + * sealed itself, which basically prevents any further seal from being + * added. + * + * Semantics of sealing are only defined on volatile files. Only + * anonymous shmem files support sealing. More importantly, seals are + * never written to disk. Therefore, there's no plan to support it on + * other file types. + */ + + if (file->f_op != &shmem_file_operations) + return -EINVAL; + if (!(file->f_mode & FMODE_WRITE)) + return -EPERM; + if (seals & ~(unsigned int)F_ALL_SEALS) + return -EINVAL; + + mutex_lock(&inode->i_mutex); + + if (info->seals & F_SEAL_SEAL) { + error = -EPERM; + goto unlock; + } + + if ((seals & F_SEAL_WRITE) && !(info->seals & F_SEAL_WRITE)) { + error = mapping_deny_writable(file->f_mapping); + if (error) + goto unlock; + + error = shmem_wait_for_pins(file->f_mapping); + if (error) { + mapping_allow_writable(file->f_mapping); + goto unlock; + } + } + + info->seals |= seals; + error = 0; + +unlock: + mutex_unlock(&inode->i_mutex); + return error; +} +EXPORT_SYMBOL_GPL(shmem_add_seals); + +int shmem_get_seals(struct file *file) +{ + if (file->f_op != &shmem_file_operations) + return -EINVAL; + + return SHMEM_I(file_inode(file))->seals; +} +EXPORT_SYMBOL_GPL(shmem_get_seals); + +long shmem_fcntl(struct file *file, unsigned int cmd, unsigned long arg) +{ + long error; + + switch (cmd) { + case F_ADD_SEALS: + /* disallow upper 32bit */ + if (arg > UINT_MAX) + return -EINVAL; + + error = shmem_add_seals(file, arg); + break; + case F_GET_SEALS: + error = shmem_get_seals(file); + break; + default: + error = -EINVAL; + break; + } + + return error; +} + static long shmem_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_falloc shmem_falloc; pgoff_t start, index, end; int error; + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + return -EOPNOTSUPP; + mutex_lock(&inode->i_mutex); if (mode & FALLOC_FL_PUNCH_HOLE) { struct address_space *mapping = file->f_mapping; loff_t unmap_start = round_up(offset, PAGE_SIZE); loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1; + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq); + + /* protected by i_mutex */ + if (info->seals & F_SEAL_WRITE) { + error = -EPERM; + goto out; + } + + shmem_falloc.waitq = &shmem_falloc_waitq; + shmem_falloc.start = unmap_start >> PAGE_SHIFT; + shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; + spin_lock(&inode->i_lock); + inode->i_private = &shmem_falloc; + spin_unlock(&inode->i_lock); if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); shmem_truncate_range(inode, offset, offset + len - 1); /* No need to unmap again: hole-punching leaves COWed pages */ + + spin_lock(&inode->i_lock); + inode->i_private = NULL; + wake_up_all(&shmem_falloc_waitq); + spin_unlock(&inode->i_lock); error = 0; goto out; } @@ -1832,6 +2102,11 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, if (error) goto out; + if ((info->seals & F_SEAL_GROW) && offset + len > inode->i_size) { + error = -EPERM; + goto out; + } + start = offset >> PAGE_CACHE_SHIFT; end = (offset + len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; /* Try to avoid a swapstorm if len is impossible to satisfy */ @@ -1840,6 +2115,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, goto out; } + shmem_falloc.waitq = NULL; shmem_falloc.start = start; shmem_falloc.next = start; shmem_falloc.nr_falloced = 0; @@ -2047,24 +2323,54 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry) return shmem_unlink(dir, dentry); } +static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) +{ + bool old_is_dir = S_ISDIR(old_dentry->d_inode->i_mode); + bool new_is_dir = S_ISDIR(new_dentry->d_inode->i_mode); + + if (old_dir != new_dir && old_is_dir != new_is_dir) { + if (old_is_dir) { + drop_nlink(old_dir); + inc_nlink(new_dir); + } else { + drop_nlink(new_dir); + inc_nlink(old_dir); + } + } + old_dir->i_ctime = old_dir->i_mtime = + new_dir->i_ctime = new_dir->i_mtime = + old_dentry->d_inode->i_ctime = + new_dentry->d_inode->i_ctime = CURRENT_TIME; + + return 0; +} + /* * The VFS layer already does all the dentry stuff for rename, * we just have to decrement the usage count for the target if * it exists so that the VFS layer correctly free's it when it * gets overwritten. */ -static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) +static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode *inode = old_dentry->d_inode; int they_are_dirs = S_ISDIR(inode->i_mode); + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + return -EINVAL; + + if (flags & RENAME_EXCHANGE) + return shmem_exchange(old_dir, old_dentry, new_dir, new_dentry); + if (!simple_empty(new_dentry)) return -ENOTEMPTY; if (new_dentry->d_inode) { (void) shmem_unlink(new_dir, new_dentry); - if (they_are_dirs) + if (they_are_dirs) { + drop_nlink(new_dentry->d_inode); drop_nlink(old_dir); + } } else if (they_are_dirs) { drop_nlink(old_dir); inc_nlink(new_dir); @@ -2566,6 +2872,77 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root) shmem_show_mpol(seq, sbinfo->mpol); return 0; } + +#define MFD_NAME_PREFIX "memfd:" +#define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1) +#define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN) + +#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING) + +SYSCALL_DEFINE2(memfd_create, + const char __user *, uname, + unsigned int, flags) +{ + struct shmem_inode_info *info; + struct file *file; + int fd, error; + char *name; + long len; + + if (flags & ~(unsigned int)MFD_ALL_FLAGS) + return -EINVAL; + + /* length includes terminating zero */ + len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1); + if (len <= 0) + return -EFAULT; + if (len > MFD_NAME_MAX_LEN + 1) + return -EINVAL; + + name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_TEMPORARY); + if (!name) + return -ENOMEM; + + strcpy(name, MFD_NAME_PREFIX); + if (copy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, len)) { + error = -EFAULT; + goto err_name; + } + + /* terminating-zero may have changed after strnlen_user() returned */ + if (name[len + MFD_NAME_PREFIX_LEN - 1]) { + error = -EFAULT; + goto err_name; + } + + fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0); + if (fd < 0) { + error = fd; + goto err_name; + } + + file = shmem_file_setup(name, 0, VM_NORESERVE); + if (IS_ERR(file)) { + error = PTR_ERR(file); + goto err_fd; + } + info = SHMEM_I(file_inode(file)); + file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; + file->f_flags |= O_RDWR | O_LARGEFILE; + if (flags & MFD_ALLOW_SEALING) + info->seals &= ~F_SEAL_SEAL; + + fd_install(fd, file); + kfree(name); + return fd; + +err_fd: + put_unused_fd(fd); +err_name: + kfree(name); + return error; +} + #endif /* CONFIG_TMPFS */ static void shmem_put_super(struct super_block *sb) @@ -2708,13 +3085,13 @@ static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, #ifdef CONFIG_TMPFS .llseek = shmem_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = shmem_file_aio_read, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = shmem_file_read_iter, + .write_iter = generic_file_write_iter, .fsync = noop_fsync, .splice_read = shmem_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, .fallocate = shmem_fallocate, #endif }; @@ -2740,7 +3117,7 @@ static const struct inode_operations shmem_dir_inode_operations = { .mkdir = shmem_mkdir, .rmdir = shmem_rmdir, .mknod = shmem_mknod, - .rename = shmem_rename, + .rename2 = shmem_rename2, .tmpfile = shmem_tmpfile, #endif #ifdef CONFIG_TMPFS_XATTR @@ -2783,6 +3160,7 @@ static const struct super_operations shmem_ops = { static const struct vm_operations_struct shmem_vm_ops = { .fault = shmem_fault, + .map_pages = filemap_map_pages, #ifdef CONFIG_NUMA .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, @@ -2930,16 +3308,16 @@ static struct file *__shmem_file_setup(const char *name, loff_t size, this.len = strlen(name); this.hash = 0; /* will go */ sb = shm_mnt->mnt_sb; + path.mnt = mntget(shm_mnt); path.dentry = d_alloc_pseudo(sb, &this); if (!path.dentry) goto put_memory; d_set_d_op(path.dentry, &anon_ops); - path.mnt = mntget(shm_mnt); res = ERR_PTR(-ENOSPC); inode = shmem_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0, flags); if (!inode) - goto put_dentry; + goto put_memory; inode->i_flags |= i_flags; d_instantiate(path.dentry, inode); @@ -2947,19 +3325,19 @@ static struct file *__shmem_file_setup(const char *name, loff_t size, clear_nlink(inode); /* It is unlinked */ res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size)); if (IS_ERR(res)) - goto put_dentry; + goto put_path; res = alloc_file(&path, FMODE_WRITE | FMODE_READ, &shmem_file_operations); if (IS_ERR(res)) - goto put_dentry; + goto put_path; return res; -put_dentry: - path_put(&path); put_memory: shmem_unacct_size(flags, size); +put_path: + path_put(&path); return res; } |