diff options
Diffstat (limited to 'mm/filemap.c')
| -rw-r--r-- | mm/filemap.c | 237 |
1 files changed, 194 insertions, 43 deletions
diff --git a/mm/filemap.c b/mm/filemap.c index f61cf51c2238..804d7365680c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -47,6 +47,7 @@ #include <linux/splice.h> #include <linux/rcupdate_wait.h> #include <linux/sched/mm.h> +#include <linux/fsnotify.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "internal.h" @@ -124,15 +125,6 @@ * ->private_lock (zap_pte_range->block_dirty_folio) */ -static void mapping_set_update(struct xa_state *xas, - struct address_space *mapping) -{ - if (dax_mapping(mapping) || shmem_mapping(mapping)) - return; - xas_set_update(xas, workingset_update_node); - xas_set_lru(xas, &shadow_nodes); -} - static void page_cache_delete(struct address_space *mapping, struct folio *folio, void *shadow) { @@ -450,6 +442,24 @@ int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, EXPORT_SYMBOL(filemap_fdatawrite_range); /** + * filemap_fdatawrite_range_kick - start writeback on a range + * @mapping: target address_space + * @start: index to start writeback on + * @end: last (non-inclusive) index for writeback + * + * This is a non-integrity writeback helper, to start writing back folios + * for the indicated range. + * + * Return: %0 on success, negative error code otherwise. + */ +int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start, + loff_t end) +{ + return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_NONE); +} +EXPORT_SYMBOL_GPL(filemap_fdatawrite_range_kick); + +/** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space * @@ -1473,25 +1483,6 @@ static int folio_put_wait_locked(struct folio *folio, int state) } /** - * folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue - * @folio: Folio defining the wait queue of interest - * @waiter: Waiter to add to the queue - * - * Add an arbitrary @waiter to the wait queue for the nominated @folio. - */ -void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter) -{ - wait_queue_head_t *q = folio_waitqueue(folio); - unsigned long flags; - - spin_lock_irqsave(&q->lock, flags); - __add_wait_queue_entry_tail(q, waiter); - folio_set_waiters(folio); - spin_unlock_irqrestore(&q->lock, flags); -} -EXPORT_SYMBOL_GPL(folio_add_wait_queue); - -/** * folio_unlock - Unlock a locked folio. * @folio: The folio. * @@ -1532,7 +1523,7 @@ void folio_end_read(struct folio *folio, bool success) /* Must be in bottom byte for x86 to work */ BUILD_BUG_ON(PG_uptodate > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio); + VM_BUG_ON_FOLIO(success && folio_test_uptodate(folio), folio); if (likely(success)) mask |= 1 << PG_uptodate; @@ -1599,6 +1590,27 @@ int folio_wait_private_2_killable(struct folio *folio) } EXPORT_SYMBOL(folio_wait_private_2_killable); +/* + * If folio was marked as dropbehind, then pages should be dropped when writeback + * completes. Do that now. If we fail, it's likely because of a big folio - + * just reset dropbehind for that case and latter completions should invalidate. + */ +static void folio_end_dropbehind_write(struct folio *folio) +{ + /* + * Hitting !in_task() should not happen off RWF_DONTCACHE writeback, + * but can happen if normal writeback just happens to find dirty folios + * that were created as part of uncached writeback, and that writeback + * would otherwise not need non-IRQ handling. Just skip the + * invalidation in that case. + */ + if (in_task() && folio_trylock(folio)) { + if (folio->mapping) + folio_unmap_invalidate(folio->mapping, folio, 0); + folio_unlock(folio); + } +} + /** * folio_end_writeback - End writeback against a folio. * @folio: The folio. @@ -1609,6 +1621,8 @@ EXPORT_SYMBOL(folio_wait_private_2_killable); */ void folio_end_writeback(struct folio *folio) { + bool folio_dropbehind = false; + VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); /* @@ -1630,9 +1644,14 @@ void folio_end_writeback(struct folio *folio) * reused before the folio_wake_bit(). */ folio_get(folio); + if (!folio_test_dirty(folio)) + folio_dropbehind = folio_test_clear_dropbehind(folio); if (__folio_end_writeback(folio)) folio_wake_bit(folio, PG_writeback); acct_reclaim_writeback(folio); + + if (folio_dropbehind) + folio_end_dropbehind_write(folio); folio_put(folio); } EXPORT_SYMBOL(folio_end_writeback); @@ -1955,6 +1974,8 @@ no_page: /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __folio_set_referenced(folio); + if (fgp_flags & FGP_DONTCACHE) + __folio_set_dropbehind(folio); err = filemap_add_folio(mapping, folio, index, gfp); if (!err) @@ -1977,6 +1998,9 @@ no_page: if (!folio) return ERR_PTR(-ENOENT); + /* not an uncached lookup, clear uncached if set */ + if (folio_test_dropbehind(folio) && !(fgp_flags & FGP_DONTCACHE)) + folio_clear_dropbehind(folio); return folio; } EXPORT_SYMBOL(__filemap_get_folio); @@ -2459,18 +2483,22 @@ unlock_mapping: return error; } -static int filemap_create_folio(struct file *file, - struct address_space *mapping, loff_t pos, - struct folio_batch *fbatch) +static int filemap_create_folio(struct kiocb *iocb, struct folio_batch *fbatch) { + struct address_space *mapping = iocb->ki_filp->f_mapping; struct folio *folio; int error; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t index; + if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) + return -EAGAIN; + folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order); if (!folio) return -ENOMEM; + if (iocb->ki_flags & IOCB_DONTCACHE) + __folio_set_dropbehind(folio); /* * Protect against truncate / hole punch. Grabbing invalidate_lock @@ -2486,7 +2514,7 @@ static int filemap_create_folio(struct file *file, * well to keep locking rules simple. */ filemap_invalidate_lock_shared(mapping); - index = (pos >> (PAGE_SHIFT + min_order)) << min_order; + index = (iocb->ki_pos >> (PAGE_SHIFT + min_order)) << min_order; error = filemap_add_folio(mapping, folio, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) @@ -2494,7 +2522,8 @@ static int filemap_create_folio(struct file *file, if (error) goto error; - error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); + error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, + folio); if (error) goto error; @@ -2515,6 +2544,8 @@ static int filemap_readahead(struct kiocb *iocb, struct file *file, if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; + if (iocb->ki_flags & IOCB_DONTCACHE) + ractl.dropbehind = 1; page_cache_async_ra(&ractl, folio, last_index - folio->index); return 0; } @@ -2524,7 +2555,6 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count, { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; - struct file_ra_state *ra = &filp->f_ra; pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; pgoff_t last_index; struct folio *folio; @@ -2539,20 +2569,21 @@ retry: filemap_get_read_batch(mapping, index, last_index - 1, fbatch); if (!folio_batch_count(fbatch)) { + DEFINE_READAHEAD(ractl, filp, &filp->f_ra, mapping, index); + if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; if (iocb->ki_flags & IOCB_NOWAIT) flags = memalloc_noio_save(); - page_cache_sync_readahead(mapping, ra, filp, index, - last_index - index); + if (iocb->ki_flags & IOCB_DONTCACHE) + ractl.dropbehind = 1; + page_cache_sync_ra(&ractl, last_index - index); if (iocb->ki_flags & IOCB_NOWAIT) memalloc_noio_restore(flags); filemap_get_read_batch(mapping, index, last_index - 1, fbatch); } if (!folio_batch_count(fbatch)) { - if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) - return -EAGAIN; - err = filemap_create_folio(filp, mapping, iocb->ki_pos, fbatch); + err = filemap_create_folio(iocb, fbatch); if (err == AOP_TRUNCATED_PAGE) goto retry; return err; @@ -2593,6 +2624,20 @@ static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio) return (pos1 >> shift == pos2 >> shift); } +static void filemap_end_dropbehind_read(struct address_space *mapping, + struct folio *folio) +{ + if (!folio_test_dropbehind(folio)) + return; + if (folio_test_writeback(folio) || folio_test_dirty(folio)) + return; + if (folio_trylock(folio)) { + if (folio_test_clear_dropbehind(folio)) + folio_unmap_invalidate(mapping, folio, 0); + folio_unlock(folio); + } +} + /** * filemap_read - Read data from the page cache. * @iocb: The iocb to read. @@ -2706,8 +2751,12 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, } } put_folios: - for (i = 0; i < folio_batch_count(&fbatch); i++) - folio_put(fbatch.folios[i]); + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct folio *folio = fbatch.folios[i]; + + filemap_end_dropbehind_read(mapping, folio); + folio_put(folio); + } folio_batch_init(&fbatch); } while (iov_iter_count(iter) && iocb->ki_pos < isize && !error); @@ -3005,7 +3054,7 @@ static inline loff_t folio_seek_hole_data(struct xa_state *xas, if (ops->is_partially_uptodate(folio, offset, bsz) == seek_data) break; - start = (start + bsz) & ~(bsz - 1); + start = (start + bsz) & ~((u64)bsz - 1); offset += bsz; } while (offset < folio_size(folio)); unlock: @@ -3150,6 +3199,14 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) unsigned long vm_flags = vmf->vma->vm_flags; unsigned int mmap_miss; + /* + * If we have pre-content watches we need to disable readahead to make + * sure that we don't populate our mapping with 0 filled pages that we + * never emitted an event for. + */ + if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) + return fpin; + #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Use the readahead code, even if readahead is disabled */ if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) { @@ -3218,6 +3275,10 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct file *fpin = NULL; unsigned int mmap_miss; + /* See comment in do_sync_mmap_readahead. */ + if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) + return fpin; + /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; @@ -3277,6 +3338,48 @@ static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) } /** + * filemap_fsnotify_fault - maybe emit a pre-content event. + * @vmf: struct vm_fault containing details of the fault. + * + * If we have a pre-content watch on this file we will emit an event for this + * range. If we return anything the fault caller should return immediately, we + * will return VM_FAULT_RETRY if we had to emit an event, which will trigger the + * fault again and then the fault handler will run the second time through. + * + * Return: a bitwise-OR of %VM_FAULT_ codes, 0 if nothing happened. + */ +vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf) +{ + struct file *fpin = NULL; + int mask = (vmf->flags & FAULT_FLAG_WRITE) ? MAY_WRITE : MAY_ACCESS; + loff_t pos = vmf->pgoff >> PAGE_SHIFT; + size_t count = PAGE_SIZE; + int err; + + /* + * We already did this and now we're retrying with everything locked, + * don't emit the event and continue. + */ + if (vmf->flags & FAULT_FLAG_TRIED) + return 0; + + /* No watches, we're done. */ + if (likely(!FMODE_FSNOTIFY_HSM(vmf->vma->vm_file->f_mode))) + return 0; + + fpin = maybe_unlock_mmap_for_io(vmf, fpin); + if (!fpin) + return VM_FAULT_SIGBUS; + + err = fsnotify_file_area_perm(fpin, mask, &pos, count); + fput(fpin); + if (err) + return VM_FAULT_SIGBUS; + return VM_FAULT_RETRY; +} +EXPORT_SYMBOL_GPL(filemap_fsnotify_fault); + +/** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault * @@ -3380,6 +3483,37 @@ retry_find: */ if (unlikely(!folio_test_uptodate(folio))) { /* + * If this is a precontent file we have can now emit an event to + * try and populate the folio. + */ + if (!(vmf->flags & FAULT_FLAG_TRIED) && + unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) { + loff_t pos = folio_pos(folio); + size_t count = folio_size(folio); + + /* We're NOWAIT, we have to retry. */ + if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) { + folio_unlock(folio); + goto out_retry; + } + + if (mapping_locked) + filemap_invalidate_unlock_shared(mapping); + mapping_locked = false; + + folio_unlock(folio); + fpin = maybe_unlock_mmap_for_io(vmf, fpin); + if (!fpin) + goto out_retry; + + error = fsnotify_file_area_perm(fpin, MAY_ACCESS, &pos, + count); + if (error) + ret = VM_FAULT_SIGBUS; + goto out_retry; + } + + /* * If the invalidate lock is not held, the folio was in cache * and uptodate and now it is not. Strange but possible since we * didn't hold the page lock all the time. Let's drop @@ -4385,6 +4519,20 @@ resched: } /* + * See mincore: reveal pagecache information only for files + * that the calling process has write access to, or could (if + * tried) open for writing. + */ +static inline bool can_do_cachestat(struct file *f) +{ + if (f->f_mode & FMODE_WRITE) + return true; + if (inode_owner_or_capable(file_mnt_idmap(f), file_inode(f))) + return true; + return file_permission(f, MAY_WRITE) == 0; +} + +/* * The cachestat(2) system call. * * cachestat() returns the page cache statistics of a file in the @@ -4439,6 +4587,9 @@ SYSCALL_DEFINE4(cachestat, unsigned int, fd, if (is_file_hugepages(fd_file(f))) return -EOPNOTSUPP; + if (!can_do_cachestat(fd_file(f))) + return -EPERM; + if (flags != 0) return -EINVAL; |