diff options
34 files changed, 249 insertions, 146 deletions
@@ -371,6 +371,7 @@ Rémi Denis-Courmont <rdenis@simphalempin.com> Ricardo Ribalda <ribalda@kernel.org> <ricardo@ribalda.com> Ricardo Ribalda <ribalda@kernel.org> Ricardo Ribalda Delgado <ribalda@kernel.org> Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com> +Robert Foss <rfoss@kernel.org> <robert.foss@linaro.org> Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com> Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com> Roman Gushchin <roman.gushchin@linux.dev> <klamm@yandex-team.ru> diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst index f67de481c7f6..6dd74a18268b 100644 --- a/Documentation/admin-guide/mm/zswap.rst +++ b/Documentation/admin-guide/mm/zswap.rst @@ -70,9 +70,7 @@ e.g. ``zswap.zpool=zbud``. It can also be changed at runtime using the sysfs The zbud type zpool allocates exactly 1 page to store 2 compressed pages, which means the compression ratio will always be 2:1 or worse (because of half-full zbud pages). The zsmalloc type zpool has a more complex compressed page -storage method, and it can achieve greater storage densities. However, -zsmalloc does not implement compressed page eviction, so once zswap fills it -cannot evict the oldest page, it can only reject new pages. +storage method, and it can achieve greater storage densities. When a swap page is passed from frontswap to zswap, zswap maintains a mapping of the swap entry, a combination of the swap type and swap offset, to the zpool diff --git a/MAINTAINERS b/MAINTAINERS index 42fc47c6edfd..123216b76534 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6948,7 +6948,7 @@ F: drivers/gpu/drm/atmel-hlcdc/ DRM DRIVERS FOR BRIDGE CHIPS M: Andrzej Hajda <andrzej.hajda@intel.com> M: Neil Armstrong <neil.armstrong@linaro.org> -M: Robert Foss <robert.foss@linaro.org> +M: Robert Foss <rfoss@kernel.org> R: Laurent Pinchart <Laurent.pinchart@ideasonboard.com> R: Jonas Karlman <jonas@kwiboo.se> R: Jernej Skrabec <jernej.skrabec@gmail.com> @@ -17238,7 +17238,7 @@ F: Documentation/devicetree/bindings/net/qcom,bam-dmux.yaml F: drivers/net/wwan/qcom_bam_dmux.c QUALCOMM CAMERA SUBSYSTEM DRIVER -M: Robert Foss <robert.foss@linaro.org> +M: Robert Foss <rfoss@kernel.org> M: Todor Tomov <todor.too@gmail.com> L: linux-media@vger.kernel.org S: Maintained @@ -17318,7 +17318,7 @@ F: drivers/dma/qcom/hidma* QUALCOMM I2C CCI DRIVER M: Loic Poulain <loic.poulain@linaro.org> -M: Robert Foss <robert.foss@linaro.org> +M: Robert Foss <rfoss@kernel.org> L: linux-i2c@vger.kernel.org L: linux-arm-msm@vger.kernel.org S: Maintained diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8aeaada1fcae..3aa04224315e 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -367,7 +367,14 @@ error: btrfs_print_tree(eb, 0); btrfs_err(fs_info, "block=%llu write time tree block corruption detected", eb->start); - WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); + /* + * Be noisy if this is an extent buffer from a log tree. We don't abort + * a transaction in case there's a bad log tree extent buffer, we just + * fallback to a transaction commit. Still we want to know when there is + * a bad log tree extent buffer, as that may signal a bug somewhere. + */ + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG) || + btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID); return ret; } diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index a749367e5ae2..37b86acfcbcf 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -119,6 +119,12 @@ enum { /* Indicate that we want to commit the transaction. */ BTRFS_FS_NEED_TRANS_COMMIT, + /* + * Indicate metadata over-commit is disabled. This is set when active + * zone tracking is needed. + */ + BTRFS_FS_NO_OVERCOMMIT, + #if BITS_PER_LONG == 32 /* Indicate if we have error/warn message printed on 32bit systems */ BTRFS_FS_32BIT_ERROR, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index d275bf24b250..00851c86aa8a 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2765,9 +2765,19 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) /* * Old roots should be searched when inserting qgroup - * extent record + * extent record. + * + * But for INCONSISTENT (NO_ACCOUNTING) -> rescan case, + * we may have some record inserted during + * NO_ACCOUNTING (thus no old_roots populated), but + * later we start rescan, which clears NO_ACCOUNTING, + * leaving some inserted records without old_roots + * populated. + * + * Those cases are rare and should not cause too much + * time spent during commit_transaction(). */ - if (WARN_ON(!record->old_roots)) { + if (!record->old_roots) { /* Search commit root to find old_roots */ ret = btrfs_find_all_roots(&ctx, false); if (ret < 0) diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index d28ee4e36f3d..69c09508afb5 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -407,7 +407,8 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, return 0; used = btrfs_space_info_used(space_info, true); - if (btrfs_is_zoned(fs_info) && (space_info->flags & BTRFS_BLOCK_GROUP_METADATA)) + if (test_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags) && + (space_info->flags & BTRFS_BLOCK_GROUP_METADATA)) avail = 0; else avail = calc_available_free_space(fs_info, space_info, flush); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index fb52aa060093..d43261545264 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2980,7 +2980,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, ret = 0; if (ret) { blk_finish_plug(&plug); - btrfs_abort_transaction(trans, ret); btrfs_set_log_full_commit(trans); mutex_unlock(&root->log_mutex); goto out; @@ -3045,15 +3044,12 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, blk_finish_plug(&plug); btrfs_set_log_full_commit(trans); - - if (ret != -ENOSPC) { - btrfs_abort_transaction(trans, ret); - mutex_unlock(&log_root_tree->log_mutex); - goto out; - } + if (ret != -ENOSPC) + btrfs_err(fs_info, + "failed to update log for root %llu ret %d", + root->root_key.objectid, ret); btrfs_wait_tree_log_extents(log, mark); mutex_unlock(&log_root_tree->log_mutex); - ret = BTRFS_LOG_FORCE_COMMIT; goto out; } @@ -3112,7 +3108,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, goto out_wake_log_root; } else if (ret) { btrfs_set_log_full_commit(trans); - btrfs_abort_transaction(trans, ret); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } @@ -3826,7 +3821,10 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, path->slots[0]); if (tmp.type == BTRFS_DIR_INDEX_KEY) last_old_dentry_offset = tmp.offset; + } else if (ret < 0) { + err = ret; } + goto done; } @@ -3846,19 +3844,34 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, */ if (tmp.type == BTRFS_DIR_INDEX_KEY) last_old_dentry_offset = tmp.offset; + } else if (ret < 0) { + err = ret; + goto done; } + btrfs_release_path(path); /* - * Find the first key from this transaction again. See the note for - * log_new_dir_dentries, if we're logging a directory recursively we - * won't be holding its i_mutex, which means we can modify the directory - * while we're logging it. If we remove an entry between our first - * search and this search we'll not find the key again and can just - * bail. + * Find the first key from this transaction again or the one we were at + * in the loop below in case we had to reschedule. We may be logging the + * directory without holding its VFS lock, which happen when logging new + * dentries (through log_new_dir_dentries()) or in some cases when we + * need to log the parent directory of an inode. This means a dir index + * key might be deleted from the inode's root, and therefore we may not + * find it anymore. If we can't find it, just move to the next key. We + * can not bail out and ignore, because if we do that we will simply + * not log dir index keys that come after the one that was just deleted + * and we can end up logging a dir index range that ends at (u64)-1 + * (@last_offset is initialized to that), resulting in removing dir + * entries we should not remove at log replay time. */ search: ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); + if (ret > 0) + ret = btrfs_next_item(root, path); + if (ret < 0) + err = ret; + /* If ret is 1, there are no more keys in the inode's root. */ if (ret != 0) goto done; @@ -5580,8 +5593,10 @@ static int add_conflicting_inode(struct btrfs_trans_handle *trans, * LOG_INODE_EXISTS mode) and slow down other fsyncs or transaction * commits. */ - if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES) + if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES) { + btrfs_set_log_full_commit(trans); return BTRFS_LOG_FORCE_COMMIT; + } inode = btrfs_iget(root->fs_info->sb, ino, root); /* diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index aa25fa335d3e..bf0decaac7f3 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -768,8 +768,11 @@ static noinline struct btrfs_device *device_list_add(const char *path, BTRFS_SUPER_FLAG_CHANGING_FSID_V2); error = lookup_bdev(path, &path_devt); - if (error) + if (error) { + btrfs_err(NULL, "failed to lookup block device for path %s: %d", + path, error); return ERR_PTR(error); + } if (fsid_change_in_progress) { if (!has_metadata_uuid) @@ -836,6 +839,9 @@ static noinline struct btrfs_device *device_list_add(const char *path, unsigned int nofs_flag; if (fs_devices->opened) { + btrfs_err(NULL, + "device %s belongs to fsid %pU, and the fs is already mounted", + path, fs_devices->fsid); mutex_unlock(&fs_devices->device_list_mutex); return ERR_PTR(-EBUSY); } @@ -905,6 +911,9 @@ static noinline struct btrfs_device *device_list_add(const char *path, * generation are equal. */ mutex_unlock(&fs_devices->device_list_mutex); + btrfs_err(NULL, +"device %s already registered with a higher generation, found %llu expect %llu", + path, found_transid, device->generation); return ERR_PTR(-EEXIST); } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index a759668477bb..1f503e8e42d4 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -539,6 +539,8 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) } atomic_set(&zone_info->active_zones_left, max_active_zones - nactive); + /* Overcommit does not work well with active zone tacking. */ + set_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags); } /* Validate superblock log */ diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 8c854ba3285b..51a4b7885cae 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -195,7 +195,7 @@ struct nfsd_net { atomic_t nfsd_courtesy_clients; struct shrinker nfsd_client_shrinker; - struct delayed_work nfsd_shrinker_work; + struct work_struct nfsd_shrinker_work; }; /* Simple check to find out if a given net was properly initialized */ diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 9b81d012666e..f189ba7995f5 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1318,6 +1318,7 @@ try_again: /* allow 20secs for mount/unmount for now - revisit */ if (signal_pending(current) || (schedule_timeout(20*HZ) == 0)) { + finish_wait(&nn->nfsd_ssc_waitq, &wait); kfree(work); return nfserr_eagain; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 4809ae0f0138..4ef529379065 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4411,7 +4411,7 @@ nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) if (!count) count = atomic_long_read(&num_delegations); if (count) - mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0); + queue_work(laundry_wq, &nn->nfsd_shrinker_work); return (unsigned long)count; } @@ -4421,7 +4421,7 @@ nfsd4_state_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc) return SHRINK_STOP; } -int +void nfsd4_init_leases_net(struct nfsd_net *nn) { struct sysinfo si; @@ -4443,16 +4443,6 @@ nfsd4_init_leases_net(struct nfsd_net *nn) nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB); atomic_set(&nn->nfsd_courtesy_clients, 0); - nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan; - nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count; - nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; - return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client"); -} - -void -nfsd4_leases_net_shutdown(struct nfsd_net *nn) -{ - unregister_shrinker(&nn->nfsd_client_shrinker); } static void init_nfs4_replay(struct nfs4_replay *rp) @@ -6235,8 +6225,7 @@ deleg_reaper(struct nfsd_net *nn) static void nfsd4_state_shrinker_worker(struct work_struct *work) { - struct delayed_work *dwork = to_delayed_work(work); - struct nfsd_net *nn = container_of(dwork, struct nfsd_net, + struct nfsd_net *nn = container_of(work, struct nfsd_net, nfsd_shrinker_work); courtesy_client_reaper(nn); @@ -8066,11 +8055,20 @@ static int nfs4_state_create_net(struct net *net) INIT_LIST_HEAD(&nn->blocked_locks_lru); INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main); - INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); + INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); get_net(net); + nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan; + nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count; + nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; + + if (register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client")) + goto err_shrinker; return 0; +err_shrinker: + put_net(net); + kfree(nn->sessionid_hashtbl); err_sessionid: kfree(nn->unconf_id_hashtbl); err_unconf_id: @@ -8163,6 +8161,8 @@ nfs4_state_shutdown_net(struct net *net) struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + unregister_shrinker(&nn->nfsd_client_shrinker); + cancel_work(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index d1e581a60480..c2577ee7ffb2 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1457,9 +1457,7 @@ static __net_init int nfsd_init_net(struct net *net) goto out_idmap_error; nn->nfsd_versions = NULL; nn->nfsd4_minorversions = NULL; - retval = nfsd4_init_leases_net(nn); - if (retval) - goto out_drc_error; + nfsd4_init_leases_net(nn); retval = nfsd_reply_cache_init(nn); if (retval) goto out_cache_error; @@ -1469,8 +1467,6 @@ static __net_init int nfsd_init_net(struct net *net) return 0; out_cache_error: - nfsd4_leases_net_shutdown(nn); -out_drc_error: nfsd_idmap_shutdown(net); out_idmap_error: nfsd_export_shutdown(net); @@ -1486,7 +1482,6 @@ static __net_exit void nfsd_exit_net(struct net *net) nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); nfsd_netns_free_versions(net_generic(net, nfsd_net_id)); - nfsd4_leases_net_shutdown(nn); } static struct pernet_operations nfsd_net_ops = { diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 93b42ef9ed91..fa0144a74267 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -504,8 +504,7 @@ extern void unregister_cld_notifier(void); extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn); #endif -extern int nfsd4_init_leases_net(struct nfsd_net *nn); -extern void nfsd4_leases_net_shutdown(struct nfsd_net *nn); +extern void nfsd4_init_leases_net(struct nfsd_net *nn); #else /* CONFIG_NFSD_V4 */ static inline int nfsd4_is_junction(struct dentry *dentry) @@ -513,8 +512,7 @@ static inline int nfsd4_is_junction(struct dentry *dentry) return 0; } -static inline int nfsd4_init_leases_net(struct nfsd_net *nn) { return 0; }; -static inline void nfsd4_leases_net_shutdown(struct nfsd_net *nn) {}; +static inline void nfsd4_init_leases_net(struct nfsd_net *nn) { }; #define register_cld_notifier() 0 #define unregister_cld_notifier() do { } while(0) diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index b9d15c3df3cc..40ce92a332fe 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -480,9 +480,18 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, &bh, &submit_ptr); if (ret) { - if (ret != -EEXIST) - return ret; - goto out_check; + if (likely(ret == -EEXIST)) + goto out_check; + if (ret == -ENOENT) { + /* + * Block address translation failed due to invalid + * value of 'ptr'. In this case, return internal code + * -EINVAL (broken bmap) to notify bmap layer of fatal + * metadata corruption. + */ + ret = -EINVAL; + } + return ret; } if (ra) { diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 98ac37e34e3d..cc694846617a 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -108,6 +108,21 @@ static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx) return ctx->features & UFFD_FEATURE_INITIALIZED; } +static void userfaultfd_set_vm_flags(struct vm_area_struct *vma, + vm_flags_t flags) +{ + const bool uffd_wp_changed = (vma->vm_flags ^ flags) & VM_UFFD_WP; + + vma->vm_flags = flags; + /* + * For shared mappings, we want to enable writenotify while + * userfaultfd-wp is enabled (see vma_wants_writenotify()). We'll simply + * recalculate vma->vm_page_prot whenever userfaultfd-wp changes. + */ + if ((vma->vm_flags & VM_SHARED) && uffd_wp_changed) + vma_set_page_prot(vma); +} + static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode, int wake_flags, void *key) { @@ -618,7 +633,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, for_each_vma(vmi, vma) { if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - vma->vm_flags &= ~__VM_UFFD_FLAGS; + userfaultfd_set_vm_flags(vma, + vma->vm_flags & ~__VM_UFFD_FLAGS); } } mmap_write_unlock(mm); @@ -652,7 +668,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) octx = vma->vm_userfaultfd_ctx.ctx; if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - vma->vm_flags &= ~__VM_UFFD_FLAGS; + userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS); return 0; } @@ -733,7 +749,7 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma, } else { /* Drop uffd context if remap feature not enabled */ vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - vma->vm_flags &= ~__VM_UFFD_FLAGS; + userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS); } } @@ -895,7 +911,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) prev = vma; } - vma->vm_flags = new_flags; + userfaultfd_set_vm_flags(vma, new_flags); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } mmap_write_unlock(mm); @@ -1463,7 +1479,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, * the next vma was merged into the current one and * the current one has not been updated yet. */ - vma->vm_flags = new_flags; + userfaultfd_set_vm_flags(vma, new_flags); vma->vm_userfaultfd_ctx.ctx = ctx; if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma)) @@ -1651,7 +1667,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, * the next vma was merged into the current one and * the current one has not been updated yet. */ - vma->vm_flags = new_flags; + userfaultfd_set_vm_flags(vma, new_flags); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; skip: diff --git a/include/linux/mm.h b/include/linux/mm.h index f3f196e4d66d..8f857163ac89 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1270,10 +1270,10 @@ static inline void folio_put_refs(struct folio *folio, int refs) __folio_put(folio); } -/** - * release_pages - release an array of pages or folios +/* + * union release_pages_arg - an array of pages or folios * - * This just releases a simple array of multiple pages, and + * release_pages() releases a simple array of multiple pages, and * accepts various different forms of said page array: either * a regular old boring array of pages, an array of folios, or * an array of encoded page pointers. diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index e8ed225d8f7c..ff3f3f23f649 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -413,8 +413,7 @@ static inline void free_anon_vma_name(struct vm_area_struct *vma) * Not using anon_vma_name because it generates a warning if mmap_lock * is not held, which might be the case here. */ - if (!vma->vm_file) - anon_vma_name_put(vma->anon_name); + anon_vma_name_put(vma->anon_name); } static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3b8475007734..9757067c3053 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -581,7 +581,7 @@ struct vm_area_struct { /* * For private and shared anonymous mappings, a pointer to a null * terminated string containing the name given to the vma, or NULL if - * unnamed. Serialized by mmap_sem. Use anon_vma_name to access. + * unnamed. Serialized by mmap_lock. Use anon_vma_name to access. */ struct anon_vma_name *anon_name; #endif diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 2e677e6ad09f..d7c2d33baa7f 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -301,7 +301,7 @@ static inline bool folio_ref_try_add_rcu(struct folio *folio, int count) * * You can also use this function if you're holding a lock that prevents * pages being frozen & removed; eg the i_pages lock for the page cache - * or the mmap_sem or page table lock for page tables. In this case, + * or the mmap_lock or page table lock for page tables. In this case, * it will always succeed, and you could have used a plain folio_get(), * but it's sometimes more convenient to have a common function called * from both locked and RCU-protected contexts. diff --git a/init/Kconfig b/init/Kconfig index 0958846b005e..7ceabd320425 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -776,7 +776,7 @@ config PRINTK_SAFE_LOG_BUF_SHIFT depends on PRINTK help Select the size of an alternate printk per-CPU buffer where messages - printed from usafe contexts are temporary stored. One example would + printed from unsafe contexts are temporary stored. One example would be NMI messages, another one - printk recursion. The messages are copied to the main log buffer in a safe context to avoid a deadlock. The value defines the size as a power of 2. diff --git a/lib/win_minmax.c b/lib/win_minmax.c index 6bdc1cd15f76..ec10506834b6 100644 --- a/lib/win_minmax.c +++ b/lib/win_minmax.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/** +/* * lib/minmax.c: windowed min/max tracker * * Kathleen Nichols' algorithm for tracking the minimum (or maximum) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index db895230ee7e..7fcdb98c9e68 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -94,6 +94,8 @@ static int hugetlb_acct_memory(struct hstate *h, long delta); static void hugetlb_vma_lock_free(struct vm_area_struct *vma); static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma); static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); +static void hugetlb_unshare_pmds(struct vm_area_struct *vma, + unsigned long start, unsigned long end); static inline bool subpool_is_free(struct hugepage_subpool *spool) { @@ -1181,7 +1183,7 @@ void hugetlb_dup_vma_private(struct vm_area_struct *vma) /* * Reset and decrement one ref on hugepage private reservation. - * Called with mm->mmap_sem writer semaphore held. + * Called with mm->mmap_lock writer semaphore held. * This function should be only used by move_vma() and operate on * same sized vma. It should never come here with last ref on the * reservation. @@ -4834,6 +4836,25 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; + + /* + * PMD sharing is only possible for PUD_SIZE-aligned address ranges + * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this + * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. + */ + if (addr & ~PUD_MASK) { + /* + * hugetlb_vm_op_split is called right before we attempt to + * split the VMA. We will need to unshare PMDs in the old and + * new VMAs, so let's unshare before we split. + */ + unsigned long floor = addr & PUD_MASK; + unsigned long ceil = floor + PUD_SIZE; + + if (floor >= vma->vm_start && ceil <= vma->vm_end) + hugetlb_unshare_pmds(vma, floor, ceil); + } + return 0; } @@ -5131,7 +5152,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, /* * We don't have to worry about the ordering of src and dst ptlocks - * because exclusive mmap_sem (or the i_mmap_lock) prevents deadlock. + * because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock. */ if (src_ptl != dst_ptl) spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); @@ -6639,8 +6660,17 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, spinlock_t *ptl; ptep = huge_pte_offset(mm, address, psize); if (!ptep) { - address |= last_addr_mask; - continue; + if (!uffd_wp) { + address |= last_addr_mask; + continue; + } + /* + * Userfaultfd wr-protect requires pgtable + * pre-allocations to install pte markers. + */ + ptep = huge_pte_alloc(mm, vma, address, psize); + if (!ptep) + break; } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, address, ptep)) { @@ -6658,16 +6688,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, } pte = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { - spin_unlock(ptl); - continue; - } - if (unlikely(is_hugetlb_entry_migration(pte))) { + /* Nothing to do. */ + } else if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); struct page *page = pfn_swap_entry_to_page(entry); + pte_t newpte = pte; - if (!is_readable_migration_entry(entry)) { - pte_t newpte; - + if (is_writable_migration_entry(entry)) { if (PageAnon(page)) entry = make_readable_exclusive_migration_entry( swp_offset(entry)); @@ -6675,25 +6702,22 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, entry = make_readable_migration_entry( swp_offset(entry)); newpte = swp_entry_to_pte(entry); - if (uffd_wp) - newpte = pte_swp_mkuffd_wp(newpte); - else if (uffd_wp_resolve) - newpte = pte_swp_clear_uffd_wp(newpte); - set_huge_pte_at(mm, address, ptep, newpte); pages++; } - spin_unlock(ptl); - continue; - } - if (unlikely(pte_marker_uffd_wp(pte))) { - /* - * This is changing a non-present pte into a none pte, - * no need for huge_ptep_modify_prot_start/commit(). - */ + + if (uffd_wp) + newpte = pte_swp_mkuffd_wp(newpte); + else if (uffd_wp_resolve) + newpte = pte_swp_clear_uffd_wp(newpte); + if (!pte_same(pte, newpte)) + set_huge_pte_at(mm, address, ptep, newpte); + } else if (unlikely(is_pte_marker(pte))) { + /* No other markers apply for now. */ + WARN_ON_ONCE(!pte_marker_uffd_wp(pte)); if (uffd_wp_resolve) + /* Safe to modify directly (non-present->none). */ huge_pte_clear(mm, address, ptep, psize); - } - if (!huge_pte_none(pte)) { + } else if (!huge_pte_none(pte)) { pte_t old_pte; unsigned int shift = huge_page_shift(hstate_vma(vma)); @@ -7328,26 +7352,21 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re } } -/* - * This function will unconditionally remove all the shared pmd pgtable entries - * within the specific vma for a hugetlbfs memory range. - */ -void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) +static void hugetlb_unshare_pmds(struct vm_area_struct *vma, + unsigned long start, + unsigned long end) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; - unsigned long address, start, end; + unsigned long address; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & VM_MAYSHARE)) return; - start = ALIGN(vma->vm_start, PUD_SIZE); - end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); - if (start >= end) return; @@ -7379,6 +7398,16 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) mmu_notifier_invalidate_range_end(&range); } +/* + * This function will unconditionally remove all the shared pmd pgtable entries + * within the specific vma for a hugetlbfs memory range. + */ +void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) +{ + hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), + ALIGN_DOWN(vma->vm_end, PUD_SIZE)); +} + #ifdef CONFIG_CMA static bool cma_reserve_called __initdata; diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 1d02757e90a3..22598b20c7b7 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -119,7 +119,7 @@ EXPORT_SYMBOL_GPL(kasan_restore_multi_shot); * Whether the KASAN KUnit test suite is currently being executed. * Updated in kasan_test.c. */ -bool kasan_kunit_executing; +static bool kasan_kunit_executing; void kasan_kunit_test_suite_start(void) { diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 5cb401aa2b9d..79be13133322 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1460,14 +1460,6 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false)) return SCAN_VMA_CHECK; - /* - * Symmetry with retract_page_tables(): Exclude MAP_PRIVATE mappings - * that got written to. Without this, we'd have to also lock the - * anon_vma if one exists. - */ - if (vma->anon_vma) - return SCAN_VMA_CHECK; - /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ if (userfaultfd_wp(vma)) return SCAN_PTE_UFFD_WP; @@ -1567,8 +1559,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, } /* step 4: remove pte entries */ + /* we make no change to anon, but protect concurrent anon page lookup */ + if (vma->anon_vma) + anon_vma_lock_write(vma->anon_vma); + collapse_and_free_pmd(mm, vma, haddr, pmd); + if (vma->anon_vma) + anon_vma_unlock_write(vma->anon_vma); i_mmap_unlock_write(vma->vm_file->f_mapping); maybe_install_pmd: @@ -2649,7 +2647,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, goto out_nolock; } - hend = vma->vm_end & HPAGE_PMD_MASK; + hend = min(hend, vma->vm_end & HPAGE_PMD_MASK); } mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); diff --git a/mm/madvise.c b/mm/madvise.c index a56a6d17e201..b6ea204d4e23 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -130,7 +130,7 @@ static int replace_anon_vma_name(struct vm_area_struct *vma, #endif /* CONFIG_ANON_VMA_NAME */ /* * Update the vm_flags on region of a vma, splitting it or merging it as - * necessary. Must be called with mmap_sem held for writing; + * necessary. Must be called with mmap_lock held for writing; * Caller should ensure anon_name stability by raising its refcount even when * anon_name belongs to a valid vma because this function might free that vma. */ diff --git a/mm/mmap.c b/mm/mmap.c index 87d929316d57..425a9349e610 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1524,6 +1524,10 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) return 1; + /* Do we need write faults for uffd-wp tracking? */ + if (userfaultfd_wp(vma)) + return 1; + /* Specialty mapping? */ if (vm_flags & VM_PFNMAP) return 0; @@ -2290,7 +2294,7 @@ static inline int munmap_sidetree(struct vm_area_struct *vma, * @start: The aligned start address to munmap. * @end: The aligned end address to munmap. * @uf: The userfaultfd list_head - * @downgrade: Set to true to attempt a write downgrade of the mmap_sem + * @downgrade: Set to true to attempt a write downgrade of the mmap_lock * * If @downgrade is true, check return code for potential release of the lock. */ @@ -2465,7 +2469,7 @@ map_count_exceeded: * @len: The length of the range to munmap * @uf: The userfaultfd list_head * @downgrade: set to true if the user wants to attempt to write_downgrade the - * mmap_sem + * mmap_lock * * This function takes a @mas that is either pointing to the previous VMA or set * to MA_START and sets it up to remove the mapping(s). The @len will be diff --git a/mm/nommu.c b/mm/nommu.c index 214c70e1d059..5b83938ecb67 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -559,7 +559,6 @@ void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas) static void setup_vma_to_mm(struct vm_area_struct *vma, struct mm_struct *mm) { - mm->map_count++; vma->vm_mm = mm; /* add the VMA to the mapping */ @@ -587,6 +586,7 @@ static void mas_add_vma_to_mm(struct ma_state *mas, struct mm_struct *mm, BUG_ON(!vma->vm_region); setup_vma_to_mm(vma, mm); + mm->map_count++; /* add the VMA to the tree */ vma_mas_store(vma, mas); @@ -1240,6 +1240,7 @@ share: error_just_free: up_write(&nommu_region_sem); error: + mas_destroy(&mas); if (region->vm_file) fput(region->vm_file); kmem_cache_free(vm_region_jar, region); @@ -1250,7 +1251,6 @@ error: sharing_violation: up_write(&nommu_region_sem); - mas_destroy(&mas); pr_warn("Attempt to share mismatched mappings\n"); ret = -EINVAL; goto error; @@ -1347,6 +1347,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, if (vma->vm_file) return -ENOMEM; + mm = vma->vm_mm; if (mm->map_count >= sysctl_max_map_count) return -ENOMEM; @@ -1398,6 +1399,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, mas_set_range(&mas, vma->vm_start, vma->vm_end - 1); mas_store(&mas, vma); vma_mas_store(new, &mas); + mm->map_count++; return 0; err_mas_preallocate: @@ -1509,7 +1511,8 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list erase_whole_vma: if (delete_vma_from_mm(vma)) ret = -ENOMEM; - delete_vma(mm, vma); + else + delete_vma(mm, vma); return ret; } diff --git a/mm/shmem.c b/mm/shmem.c index c301487be5fb..0005ab2c29af 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -478,12 +478,10 @@ bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))) return false; - if (shmem_huge_force) - return true; - if (shmem_huge == SHMEM_HUGE_FORCE) - return true; if (shmem_huge == SHMEM_HUGE_DENY) return false; + if (shmem_huge_force || shmem_huge == SHMEM_HUGE_FORCE) + return true; switch (SHMEM_SB(inode->i_sb)->huge) { case SHMEM_HUGE_ALWAYS: diff --git a/security/tomoyo/Kconfig b/security/tomoyo/Kconfig index b9f867100a9f..fad75be5f381 100644 --- a/security/tomoyo/Kconfig +++ b/security/tomoyo/Kconfig @@ -6,13 +6,11 @@ config SECURITY_TOMOYO select SECURITYFS select SECURITY_PATH select SECURITY_NETWORK - select SRCU - select BUILD_BIN2C default n help This selects TOMOYO Linux, pathname-based access control. Required userspace tools and further information may be - found at <http://tomoyo.sourceforge.jp/>. + found at <https://tomoyo.osdn.jp/>. If you are unsure how to answer this question, answer N. config SECURITY_TOMOYO_MAX_ACCEPT_ENTRY diff --git a/security/tomoyo/Makefile b/security/tomoyo/Makefile index cca5a3012fee..884ff155edc3 100644 --- a/security/tomoyo/Makefile +++ b/security/tomoyo/Makefile @@ -2,15 +2,18 @@ obj-y = audit.o common.o condition.o domain.o environ.o file.o gc.o group.o load_policy.o memory.o mount.o network.o realpath.o securityfs_if.o tomoyo.o util.o targets += builtin-policy.h -define do_policy -echo "static char tomoyo_builtin_$(1)[] __initdata ="; \ -$(objtree)/scripts/bin2c <$(firstword $(wildcard $(obj)/policy/$(1).conf $(srctree)/$(src)/policy/$(1).conf.default) /dev/null); \ -echo ";" -endef -quiet_cmd_policy = POLICY $@ - cmd_policy = ($(call do_policy,profile); $(call do_policy,exception_policy); $(call do_policy,domain_policy); $(call do_policy,manager); $(call do_policy,stat)) >$@ -$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(src)/policy/*.conf.default) FORCE +quiet_cmd_policy = POLICY $@ + cmd_policy = { \ + $(foreach x, profile exception_policy domain_policy manager stat, \ + printf 'static char tomoyo_builtin_$x[] __initdata =\n'; \ + sed -e 's/\\/\\\\/g' -e 's/\"/\\"/g' -e 's/\(.*\)/\t"\1\\n"/' -- $(firstword $(filter %/$x.conf %/$x.conf.default, $^) /dev/null); \ + printf '\t"";\n';) \ + } > $@ + +$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(srctree)/$(src)/policy/*.conf.default) FORCE $(call if_changed,policy) +ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING $(obj)/common.o: $(obj)/builtin-policy.h +endif diff --git a/tools/testing/selftests/proc/proc-empty-vm.c b/tools/testing/selftests/proc/proc-empty-vm.c index d95b1cb43d9d..7588428b8fcd 100644 --- a/tools/testing/selftests/proc/proc-empty-vm.c +++ b/tools/testing/selftests/proc/proc-empty-vm.c @@ -25,6 +25,7 @@ #undef NDEBUG #include <assert.h> #include <errno.h> +#include <stdint.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -41,7 +42,7 @@ * 1: vsyscall VMA is --xp vsyscall=xonly * 2: vsyscall VMA is r-xp vsyscall=emulate */ -static int g_vsyscall; +static volatile int g_vsyscall; static const char *g_proc_pid_maps_vsyscall; static const char *g_proc_pid_smaps_vsyscall; @@ -147,11 +148,12 @@ static void vsyscall(void) g_vsyscall = 0; /* gettimeofday(NULL, NULL); */ + uint64_t rax = 0xffffffffff600000; asm volatile ( - "call %P0" - : - : "i" (0xffffffffff600000), "D" (NULL), "S" (NULL) - : "rax", "rcx", "r11" + "call *%[rax]" + : [rax] "+a" (rax) + : "D" (NULL), "S" (NULL) + : "rcx", "r11" ); g_vsyscall = 1; diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c index 69551bfa215c..cacbd2a4aec9 100644 --- a/tools/testing/selftests/proc/proc-pid-vm.c +++ b/tools/testing/selftests/proc/proc-pid-vm.c @@ -257,11 +257,12 @@ static void vsyscall(void) g_vsyscall = 0; /* gettimeofday(NULL, NULL); */ + uint64_t rax = 0xffffffffff600000; asm volatile ( - "call %P0" - : - : "i" (0xffffffffff600000), "D" (NULL), "S" (NULL) - : "rax", "rcx", "r11" + "call *%[rax]" + : [rax] "+a" (rax) + : "D" (NULL), "S" (NULL) + : "rcx", "r11" ); g_vsyscall = 1; |