diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index a2ffd60889f8..1a3f186a6a11 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -477,6 +477,9 @@ void afs_fs_fetch_data(struct afs_operation *op) if (!call) return afs_op_nomem(op); + if (op->flags & AFS_OPERATION_ASYNC) + call->async = true; + /* marshall the parameters */ bp = call->request; bp[0] = htonl(FSFETCHDATA); @@ -484,7 +487,7 @@ void afs_fs_fetch_data(struct afs_operation *op) bp[2] = htonl(vp->fid.vnode); bp[3] = htonl(vp->fid.unique); bp[4] = htonl(lower_32_bits(subreq->start + subreq->transferred)); - bp[5] = htonl(lower_32_bits(subreq->len + subreq->transferred)); + bp[5] = htonl(lower_32_bits(subreq->len - subreq->transferred)); call->fid = vp->fid; trace_afs_make_fs_call(call, &vp->fid); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 601f01e5c15f..290873bac89b 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1421,7 +1421,7 @@ static inline void afs_make_op_call(struct afs_operation *op, struct afs_call *c { struct afs_addr_list *alist = op->estate->addresses; - op->call = call; + op->call = afs_get_call(call, afs_call_trace_get); op->type = call->type; call->op = op; call->key = op->key; @@ -1429,6 +1429,7 @@ static inline void afs_make_op_call(struct afs_operation *op, struct afs_call *c call->peer = rxrpc_kernel_get_peer(alist->addrs[op->addr_index].peer); call->service_id = op->server->service_id; afs_make_call(call, gfp); + afs_put_call(call); } static inline void afs_extract_begin(struct afs_call *call, void *buf, size_t size) diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 5de615ca7a75..c97f10b48b5b 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -162,8 +162,10 @@ static Node *get_binfmt_handler(struct binfmt_misc *misc, static void put_binfmt_handler(Node *e) { if (refcount_dec_and_test(&e->users)) { - if (e->flags & MISC_FMT_OPEN_FILE) + if (e->flags & MISC_FMT_OPEN_FILE) { + exe_file_allow_write_access(e->interp_file); filp_close(e->interp_file, NULL); + } kfree(e); } } @@ -247,8 +249,14 @@ static int load_misc_binary(struct linux_binprm *bprm) if (fmt->flags & MISC_FMT_OPEN_FILE) { interp_file = file_clone_open(fmt->interp_file); - if (!IS_ERR(interp_file)) - deny_write_access(interp_file); + if (!IS_ERR(interp_file)) { + int err = exe_file_deny_write_access(interp_file); + + if (err) { + fput(interp_file); + interp_file = ERR_PTR(err); + } + } } else { interp_file = open_exec(fmt->interpreter); } @@ -376,6 +384,10 @@ static Node *create_entry(const char __user *buffer, size_t count) pr_debug("register: delim: %#x {%c}\n", del, del); + /* A flag-char delimiter runs the flag scan off the buffer. */ + if (del == 'P' || del == 'O' || del == 'C' || del == 'F') + goto einval; + /* Pad the buffer with the delim to simplify parsing below. */ memset(buf + count, del, 8); @@ -909,18 +921,9 @@ static const struct file_operations bm_status_operations = { /* Superblock handling */ -static void bm_put_super(struct super_block *sb) -{ - struct user_namespace *user_ns = sb->s_fs_info; - - sb->s_fs_info = NULL; - put_user_ns(user_ns); -} - static const struct super_operations s_ops = { .statfs = simple_statfs, .evict_inode = bm_evict_inode, - .put_super = bm_put_super, }; static int bm_fill_super(struct super_block *sb, struct fs_context *fc) @@ -937,6 +940,10 @@ static int bm_fill_super(struct super_block *sb, struct fs_context *fc) if (WARN_ON(user_ns != current_user_ns())) return -EINVAL; + /* Never exec off this instance and never let anything stack on it. */ + sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV; + sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; + /* * Lazily allocate a new binfmt_misc instance for this namespace, i.e. * do it here during the first mount of binfmt_misc. We don't need to @@ -974,13 +981,12 @@ static int bm_fill_super(struct super_block *sb, struct fs_context *fc) /* * When the binfmt_misc superblock for this userns is shutdown * ->enabled might have been set to false and we don't reinitialize - * ->enabled again in put_super() as someone might already be mounting - * binfmt_misc again. It also would be pointless since by the time - * ->put_super() is called we know that the binary type list for this - * bintfmt_misc mount is empty making load_misc_binary() return - * -ENOEXEC independent of whether ->enabled is true. Instead, if - * someone mounts binfmt_misc for the first time or again we simply - * reset ->enabled to true. + * ->enabled again during shutdown as someone might already be mounting + * binfmt_misc again. It also would be pointless since by then we know + * that the binary type list for this binfmt_misc mount is empty making + * load_misc_binary() return -ENOEXEC independent of whether ->enabled + * is true. Instead, if someone mounts binfmt_misc for the first time or + * again we simply reset ->enabled to true. */ misc->enabled = true; @@ -1006,6 +1012,14 @@ static const struct fs_context_operations bm_context_ops = { .get_tree = bm_get_tree, }; +static void bm_kill_sb(struct super_block *sb) +{ + struct user_namespace *user_ns = sb->s_fs_info; + + kill_anon_super(sb); + put_user_ns(user_ns); +} + static int bm_init_fs_context(struct fs_context *fc) { fc->ops = &bm_context_ops; @@ -1022,7 +1036,7 @@ static struct file_system_type bm_fs_type = { .name = "binfmt_misc", .init_fs_context = bm_init_fs_context, .fs_flags = FS_USERNS_MOUNT, - .kill_sb = kill_anon_super, + .kill_sb = bm_kill_sb, }; MODULE_ALIAS_FS("binfmt_misc"); diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c index 30468d51b5ad..fb636dce43af 100644 --- a/fs/iomap/ioend.c +++ b/fs/iomap/ioend.c @@ -13,6 +13,7 @@ struct bio_set iomap_ioend_bioset; EXPORT_SYMBOL_GPL(iomap_ioend_bioset); +static struct bio_set iomap_ioend_split_bioset; struct iomap_ioend *iomap_init_ioend(struct inode *inode, struct bio *bio, loff_t file_offset, u16 ioend_flags) @@ -488,7 +489,8 @@ struct iomap_ioend *iomap_split_ioend(struct iomap_ioend *ioend, sector_offset = ALIGN_DOWN(sector_offset << SECTOR_SHIFT, i_blocksize(ioend->io_inode)) >> SECTOR_SHIFT; - split = bio_split(bio, sector_offset, GFP_NOFS, &iomap_ioend_bioset); + split = bio_split(bio, sector_offset, GFP_NOFS, + &iomap_ioend_split_bioset); if (IS_ERR(split)) return ERR_CAST(split); split->bi_private = bio->bi_private; @@ -511,8 +513,23 @@ EXPORT_SYMBOL_GPL(iomap_split_ioend); static int __init iomap_ioend_init(void) { - return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE), + const unsigned int nr_mempool_entries = 4 * (PAGE_SIZE / SECTOR_SIZE); + int error; + + error = bioset_init(&iomap_ioend_bioset, nr_mempool_entries, offsetof(struct iomap_ioend, io_bio), BIOSET_NEED_BVECS); + if (error) + return error; + error = bioset_init(&iomap_ioend_split_bioset, nr_mempool_entries, + offsetof(struct iomap_ioend, io_bio), + BIOSET_NEED_BVECS); + if (error) + goto out_exit_ioend_bioset; + return 0; + +out_exit_ioend_bioset: + bioset_exit(&iomap_ioend_bioset); + return error; } fs_initcall(iomap_ioend_init); diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 24a8a5418e31..7fdfa4f27e34 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -102,8 +102,10 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq, added = rolling_buffer_load_from_ra(&rreq->buffer, ractl, &put_batch); - if (added < 0) + if (added < 0) { + folio_batch_release(&put_batch); return added; + } rreq->submitted += added; } folio_batch_release(&put_batch); @@ -359,7 +361,7 @@ void netfs_readahead(struct readahead_control *ractl) netfs_rreq_expand(rreq, ractl); rreq->submitted = rreq->start; - if (rolling_buffer_init(&rreq->buffer, rreq->debug_id, ITER_DEST) < 0) + if (rolling_buffer_init(&rreq->buffer, rreq->debug_id, ITER_DEST, rreq->gfp) < 0) goto cleanup_free; netfs_read_to_pagecache(rreq, ractl); @@ -378,10 +380,10 @@ static int netfs_create_singular_buffer(struct netfs_io_request *rreq, struct fo { ssize_t added; - if (rolling_buffer_init(&rreq->buffer, rreq->debug_id, ITER_DEST) < 0) + if (rolling_buffer_init(&rreq->buffer, rreq->debug_id, ITER_DEST, rreq->gfp) < 0) return -ENOMEM; - added = rolling_buffer_append(&rreq->buffer, folio, rollbuf_flags); + added = rolling_buffer_append(&rreq->buffer, folio, rollbuf_flags, rreq->gfp); if (added < 0) return added; rreq->submitted = rreq->start + added; diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index d889caa401dc..420ee7b26580 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -43,6 +43,7 @@ extern struct list_head netfs_io_requests; extern spinlock_t netfs_proc_lock; extern mempool_t netfs_request_pool; extern mempool_t netfs_subrequest_pool; +extern mempool_t netfs_folioq_pool; #ifdef CONFIG_PROC_FS static inline void netfs_proc_add_rreq(struct netfs_io_request *rreq) diff --git a/fs/netfs/main.c b/fs/netfs/main.c index 73da6c9f5777..927badf3989d 100644 --- a/fs/netfs/main.c +++ b/fs/netfs/main.c @@ -28,6 +28,7 @@ static struct kmem_cache *netfs_request_slab; static struct kmem_cache *netfs_subrequest_slab; mempool_t netfs_request_pool; mempool_t netfs_subrequest_pool; +mempool_t netfs_folioq_pool; #ifdef CONFIG_PROC_FS LIST_HEAD(netfs_io_requests); @@ -108,6 +109,9 @@ static int __init netfs_init(void) { int ret = -ENOMEM; + if (mempool_init_kmalloc_pool(&netfs_folioq_pool, 100, sizeof(struct folio_queue)) < 0) + goto error_folioq_pool; + netfs_request_slab = kmem_cache_create("netfs_request", sizeof(struct netfs_io_request), 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, @@ -160,6 +164,8 @@ error_subreq: error_reqpool: kmem_cache_destroy(netfs_request_slab); error_req: + mempool_exit(&netfs_folioq_pool); +error_folioq_pool: return ret; } fs_initcall(netfs_init); @@ -172,5 +178,6 @@ static void __exit netfs_exit(void) kmem_cache_destroy(netfs_subrequest_slab); mempool_exit(&netfs_request_pool); kmem_cache_destroy(netfs_request_slab); + mempool_exit(&netfs_folioq_pool); } module_exit(netfs_exit); diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index b8c4918d3dcd..01461a74642d 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -7,7 +7,6 @@ #include #include -#include #include "internal.h" static void netfs_free_request(struct work_struct *work); @@ -26,17 +25,23 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, struct netfs_io_request *rreq; mempool_t *mempool = ctx->ops->request_pool ?: &netfs_request_pool; struct kmem_cache *cache = mempool->pool_data; + gfp_t gfp = GFP_KERNEL; int ret; - for (;;) { - rreq = mempool_alloc(mempool, GFP_KERNEL); - if (rreq) - break; - msleep(10); + /* Writeback is part of memory reclaim and must not fail due to ENOMEM. */ + if (origin == NETFS_WRITEBACK || origin == NETFS_WRITEBACK_SINGLE) { + gfp = GFP_NOFS; /* Allows use of mempools. */ + + rreq = mempool_alloc(mempool, gfp); + } else { + rreq = mempool->alloc(gfp, mempool->pool_data); + if (!rreq) + return ERR_PTR(-ENOMEM); } memset(rreq, 0, kmem_cache_size(cache)); INIT_WORK(&rreq->cleanup_work, netfs_free_request); + rreq->gfp = gfp; rreq->start = start; rreq->len = len; rreq->origin = origin; @@ -200,13 +205,12 @@ struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq mempool_t *mempool = rreq->netfs_ops->subrequest_pool ?: &netfs_subrequest_pool; struct kmem_cache *cache = mempool->pool_data; - for (;;) { - subreq = mempool_alloc(rreq->netfs_ops->subrequest_pool ?: &netfs_subrequest_pool, - GFP_KERNEL); - if (subreq) - break; - msleep(10); - } + if (rreq->gfp == GFP_KERNEL) + subreq = mempool->alloc(rreq->gfp, mempool->pool_data); + else + subreq = mempool_alloc(mempool, rreq->gfp); + if (!subreq) + return NULL; memset(subreq, 0, kmem_cache_size(cache)); INIT_WORK(&subreq->work, NULL); diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c index a1489aa29f78..c31190993b76 100644 --- a/fs/netfs/read_pgpriv2.c +++ b/fs/netfs/read_pgpriv2.c @@ -53,7 +53,8 @@ static void netfs_pgpriv2_copy_folio(struct netfs_io_request *creq, struct folio trace_netfs_folio(folio, netfs_folio_trace_store_copy); /* Attach the folio to the rolling buffer. */ - if (rolling_buffer_append(&creq->buffer, folio, 0) < 0) { + if (rolling_buffer_append(&creq->buffer, folio, 0, creq->gfp) < 0) { + folio_end_private_2(folio); clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &creq->flags); return; } diff --git a/fs/netfs/rolling_buffer.c b/fs/netfs/rolling_buffer.c index a17fbf9853a4..8c0026836f9c 100644 --- a/fs/netfs/rolling_buffer.c +++ b/fs/netfs/rolling_buffer.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include @@ -27,7 +28,10 @@ struct folio_queue *netfs_folioq_alloc(unsigned int rreq_id, gfp_t gfp, { struct folio_queue *fq; - fq = kmalloc_obj(*fq, gfp); + if (gfp == GFP_KERNEL) + fq = netfs_folioq_pool.alloc(gfp, netfs_folioq_pool.pool_data); + else + fq = mempool_alloc(&netfs_folioq_pool, gfp); if (fq) { netfs_stat(&netfs_n_folioq); folioq_init(fq, rreq_id); @@ -50,7 +54,7 @@ void netfs_folioq_free(struct folio_queue *folioq, { trace_netfs_folioq(folioq, trace); netfs_stat_d(&netfs_n_folioq); - kfree(folioq); + mempool_free(folioq, &netfs_folioq_pool); } EXPORT_SYMBOL(netfs_folioq_free); @@ -60,11 +64,11 @@ EXPORT_SYMBOL(netfs_folioq_free); * consumer. */ int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id, - unsigned int direction) + unsigned int direction, gfp_t gfp) { struct folio_queue *fq; - fq = netfs_folioq_alloc(rreq_id, GFP_NOFS, netfs_trace_folioq_rollbuf_init); + fq = netfs_folioq_alloc(rreq_id, gfp, netfs_trace_folioq_rollbuf_init); if (!fq) return -ENOMEM; @@ -77,14 +81,14 @@ int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id, /* * Add another folio_queue to a rolling buffer if there's no space left. */ -int rolling_buffer_make_space(struct rolling_buffer *roll) +int rolling_buffer_make_space(struct rolling_buffer *roll, gfp_t gfp) { struct folio_queue *fq, *head = roll->head; if (!folioq_full(head)) return 0; - fq = netfs_folioq_alloc(head->rreq_id, GFP_NOFS, netfs_trace_folioq_make_space); + fq = netfs_folioq_alloc(head->rreq_id, gfp, netfs_trace_folioq_make_space); if (!fq) return -ENOMEM; fq->prev = head; @@ -122,7 +126,7 @@ ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, int nr, ix, to; ssize_t size = 0; - if (rolling_buffer_make_space(roll) < 0) + if (rolling_buffer_make_space(roll, GFP_KERNEL) < 0) return -ENOMEM; fq = roll->head; @@ -153,12 +157,12 @@ ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, * Append a folio to the rolling buffer. */ ssize_t rolling_buffer_append(struct rolling_buffer *roll, struct folio *folio, - unsigned int flags) + unsigned int flags, gfp_t gfp) { ssize_t size = folio_size(folio); int slot; - if (rolling_buffer_make_space(roll) < 0) + if (rolling_buffer_make_space(roll, gfp) < 0) return -ENOMEM; slot = folioq_append(roll->head, folio); diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index f2761c99795a..2d9cfcd43658 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -108,7 +108,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, ictx = netfs_inode(wreq->inode); if (is_cacheable) fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx)); - if (rolling_buffer_init(&wreq->buffer, wreq->debug_id, ITER_SOURCE) < 0) + if (rolling_buffer_init(&wreq->buffer, wreq->debug_id, ITER_SOURCE, wreq->gfp) < 0) goto nomem; wreq->cleaned_to = wreq->start; @@ -167,7 +167,7 @@ void netfs_prepare_write(struct netfs_io_request *wreq, */ if (iov_iter_is_folioq(wreq_iter) && wreq_iter->folioq_slot >= folioq_nr_slots(wreq_iter->folioq)) - rolling_buffer_make_space(&wreq->buffer); + rolling_buffer_make_space(&wreq->buffer, wreq->gfp); subreq = netfs_alloc_subrequest(wreq); subreq->source = stream->source; @@ -334,7 +334,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq, _enter(""); - if (rolling_buffer_make_space(&wreq->buffer) < 0) + if (rolling_buffer_make_space(&wreq->buffer, wreq->gfp) < 0) return -ENOMEM; /* netfs_perform_write() may shift i_size around the page or from out @@ -436,7 +436,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq, } /* Attach the folio to the rolling buffer. */ - rolling_buffer_append(&wreq->buffer, folio, 0); + rolling_buffer_append(&wreq->buffer, folio, 0, wreq->gfp); /* Move the submission point forward to allow for write-streaming data * not starting at the front of the page. We don't do write-streaming @@ -720,6 +720,7 @@ static int netfs_write_folio_single(struct netfs_io_request *wreq, size_t iter_off = 0; size_t fsize = folio_size(folio), flen; loff_t fpos = folio_pos(folio); + ssize_t ret; bool to_eof = false; bool no_debug = false; @@ -748,7 +749,11 @@ static int netfs_write_folio_single(struct netfs_io_request *wreq, /* Attach the folio to the rolling buffer. */ folio_get(folio); - rolling_buffer_append(&wreq->buffer, folio, NETFS_ROLLBUF_PUT_MARK); + ret = rolling_buffer_append(&wreq->buffer, folio, NETFS_ROLLBUF_PUT_MARK, wreq->gfp); + if (ret < 0) { + folio_put(folio); + return ret; + } /* Move the submission point forward to allow for write-streaming data * not starting at the front of the page. We don't do write-streaming diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 1bc120d61c5b..d0b62d53eea9 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -255,6 +255,7 @@ struct netfs_io_request { unsigned long long cleaned_to; /* Position we've cleaned folios to */ unsigned long long abandon_to; /* Position to abandon folios to */ const struct folio *no_unlock_folio; /* Don't unlock this folio after read */ + gfp_t gfp; /* GFP flags to use */ unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; unsigned int rsize; /* Maximum read size (0 for none) */ diff --git a/include/linux/rolling_buffer.h b/include/linux/rolling_buffer.h index ac15b1ffdd83..9e5dad29669c 100644 --- a/include/linux/rolling_buffer.h +++ b/include/linux/rolling_buffer.h @@ -43,13 +43,13 @@ struct rolling_buffer_snapshot { #define ROLLBUF_MARK_2 BIT(1) int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id, - unsigned int direction); -int rolling_buffer_make_space(struct rolling_buffer *roll); + unsigned int direction, gfp_t gfp); +int rolling_buffer_make_space(struct rolling_buffer *roll, gfp_t gfp); ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, struct readahead_control *ractl, struct folio_batch *put_batch); ssize_t rolling_buffer_append(struct rolling_buffer *roll, struct folio *folio, - unsigned int flags); + unsigned int flags, gfp_t gfp); struct folio_queue *rolling_buffer_delete_spent(struct rolling_buffer *roll); void rolling_buffer_clear(struct rolling_buffer *roll);