diff options
Diffstat (limited to 'fs')
96 files changed, 1541 insertions, 923 deletions
diff --git a/fs/afs/file.c b/fs/afs/file.c index d6bc3f5d784b..323ae9912203 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -17,6 +17,7 @@ #include <linux/writeback.h> #include <linux/gfp.h> #include <linux/task_io_accounting_ops.h> +#include <linux/mm.h> #include "internal.h" static int afs_file_mmap(struct file *file, struct vm_area_struct *vma); @@ -441,7 +442,7 @@ static int afs_readpages_one(struct file *file, struct address_space *mapping, /* Count the number of contiguous pages at the front of the list. Note * that the list goes prev-wards rather than next-wards. */ - first = list_entry(pages->prev, struct page, lru); + first = lru_to_page(pages); index = first->index + 1; n = 1; for (p = first->lru.prev; p != pages; p = p->prev) { @@ -473,7 +474,7 @@ static int afs_readpages_one(struct file *file, struct address_space *mapping, * page at the end of the file. */ do { - page = list_entry(pages->prev, struct page, lru); + page = lru_to_page(pages); list_del(&page->lru); index = page->index; if (add_to_page_cache_lru(page, mapping, index, diff --git a/fs/afs/flock.c b/fs/afs/flock.c index 0568fd986821..e432bd27a2e7 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -208,7 +208,7 @@ again: /* The new front of the queue now owns the state variables. */ next = list_entry(vnode->pending_locks.next, struct file_lock, fl_u.afs.link); - vnode->lock_key = afs_file_key(next->fl_file); + vnode->lock_key = key_get(afs_file_key(next->fl_file)); vnode->lock_type = (next->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE; vnode->lock_state = AFS_VNODE_LOCK_WAITING_FOR_CB; goto again; @@ -413,7 +413,7 @@ static void afs_dequeue_lock(struct afs_vnode *vnode, struct file_lock *fl) /* The new front of the queue now owns the state variables. */ next = list_entry(vnode->pending_locks.next, struct file_lock, fl_u.afs.link); - vnode->lock_key = afs_file_key(next->fl_file); + vnode->lock_key = key_get(afs_file_key(next->fl_file)); vnode->lock_type = (next->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE; vnode->lock_state = AFS_VNODE_LOCK_WAITING_FOR_CB; afs_lock_may_be_available(vnode); diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index fde6b4d4121e..3a9eaec06756 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -247,7 +247,7 @@ int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried) } } - if (!still_probing || unlikely(signal_pending(current))) + if (!still_probing || signal_pending(current)) goto stop; schedule(); } diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 6b17d3620414..1a4ce07fb406 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -414,7 +414,6 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) } else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { valid = true; } else { - vnode->cb_s_break = vnode->cb_interest->server->cb_s_break; vnode->cb_v_break = vnode->volume->cb_v_break; valid = false; } @@ -546,6 +545,8 @@ void afs_evict_inode(struct inode *inode) #endif afs_put_permits(rcu_access_pointer(vnode->permit_cache)); + key_put(vnode->lock_key); + vnode->lock_key = NULL; _leave(""); } diff --git a/fs/afs/protocol_yfs.h b/fs/afs/protocol_yfs.h index 07bc10f076aa..d443e2bfa094 100644 --- a/fs/afs/protocol_yfs.h +++ b/fs/afs/protocol_yfs.h @@ -161,3 +161,14 @@ struct yfs_xdr_YFSStoreVolumeStatus { struct yfs_xdr_u64 max_quota; struct yfs_xdr_u64 file_quota; } __packed; + +enum yfs_lock_type { + yfs_LockNone = -1, + yfs_LockRead = 0, + yfs_LockWrite = 1, + yfs_LockExtend = 2, + yfs_LockRelease = 3, + yfs_LockMandatoryRead = 0x100, + yfs_LockMandatoryWrite = 0x101, + yfs_LockMandatoryExtend = 0x102, +}; diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index a7b44863d502..2c588f9bbbda 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -23,6 +23,7 @@ struct workqueue_struct *afs_async_calls; static void afs_wake_up_call_waiter(struct sock *, struct rxrpc_call *, unsigned long); static long afs_wait_for_call_to_complete(struct afs_call *, struct afs_addr_cursor *); static void afs_wake_up_async_call(struct sock *, struct rxrpc_call *, unsigned long); +static void afs_delete_async_call(struct work_struct *); static void afs_process_async_call(struct work_struct *); static void afs_rx_new_call(struct sock *, struct rxrpc_call *, unsigned long); static void afs_rx_discard_new_call(struct rxrpc_call *, unsigned long); @@ -203,20 +204,26 @@ void afs_put_call(struct afs_call *call) } } +static struct afs_call *afs_get_call(struct afs_call *call, + enum afs_call_trace why) +{ + int u = atomic_inc_return(&call->usage); + + trace_afs_call(call, why, u, + atomic_read(&call->net->nr_outstanding_calls), + __builtin_return_address(0)); + return call; +} + /* * Queue the call for actual work. */ static void afs_queue_call_work(struct afs_call *call) { if (call->type->work) { - int u = atomic_inc_return(&call->usage); - - trace_afs_call(call, afs_call_trace_work, u, - atomic_read(&call->net->nr_outstanding_calls), - __builtin_return_address(0)); - INIT_WORK(&call->work, call->type->work); + afs_get_call(call, afs_call_trace_work); if (!queue_work(afs_wq, &call->work)) afs_put_call(call); } @@ -398,6 +405,12 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, } } + /* If the call is going to be asynchronous, we need an extra ref for + * the call to hold itself so the caller need not hang on to its ref. + */ + if (call->async) + afs_get_call(call, afs_call_trace_get); + /* create a call */ rxcall = rxrpc_kernel_begin_call(call->net->socket, srx, call->key, (unsigned long)call, @@ -438,15 +451,17 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, goto error_do_abort; } - /* at this point, an async call may no longer exist as it may have - * already completed */ - if (call->async) + /* Note that at this point, we may have received the reply or an abort + * - and an asynchronous call may already have completed. + */ + if (call->async) { + afs_put_call(call); return -EINPROGRESS; + } return afs_wait_for_call_to_complete(call, ac); error_do_abort: - call->state = AFS_CALL_COMPLETE; if (ret != -ECONNABORTED) { rxrpc_kernel_abort_call(call->net->socket, rxcall, RX_USER_ABORT, ret, "KSD"); @@ -463,8 +478,24 @@ error_do_abort: error_kill_call: if (call->type->done) call->type->done(call); - afs_put_call(call); + + /* We need to dispose of the extra ref we grabbed for an async call. + * The call, however, might be queued on afs_async_calls and we need to + * make sure we don't get any more notifications that might requeue it. + */ + if (call->rxcall) { + rxrpc_kernel_end_call(call->net->socket, call->rxcall); + call->rxcall = NULL; + } + if (call->async) { + if (cancel_work_sync(&call->async_work)) + afs_put_call(call); + afs_put_call(call); + } + ac->error = ret; + call->state = AFS_CALL_COMPLETE; + afs_put_call(call); _leave(" = %d", ret); return ret; } diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c index 95d0761cdb34..155dc14caef9 100644 --- a/fs/afs/server_list.c +++ b/fs/afs/server_list.c @@ -42,9 +42,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell, if (vldb->fs_mask[i] & type_mask) nr_servers++; - slist = kzalloc(sizeof(struct afs_server_list) + - sizeof(struct afs_server_entry) * nr_servers, - GFP_KERNEL); + slist = kzalloc(struct_size(slist, servers, nr_servers), GFP_KERNEL); if (!slist) goto error; diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c index f0b032976487..f402ee8171a1 100644 --- a/fs/afs/vl_probe.c +++ b/fs/afs/vl_probe.c @@ -248,7 +248,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist, } } - if (!still_probing || unlikely(signal_pending(current))) + if (!still_probing || signal_pending(current)) goto stop; schedule(); } diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 12658c1363ae..5aa57929e8c2 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -803,7 +803,7 @@ int yfs_fs_create_file(struct afs_fs_cursor *fc, bp = xdr_encode_YFSFid(bp, &vnode->fid); bp = xdr_encode_string(bp, name, namesz); bp = xdr_encode_YFSStoreStatus_mode(bp, mode); - bp = xdr_encode_u32(bp, 0); /* ViceLockType */ + bp = xdr_encode_u32(bp, yfs_LockNone); /* ViceLockType */ yfs_check_req(call, bp); afs_use_fs_server(call, fc->cbi); diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h index 9f9cadbfbd7a..3e59f0ed777b 100644 --- a/fs/autofs/autofs_i.h +++ b/fs/autofs/autofs_i.h @@ -42,6 +42,8 @@ #endif #define pr_fmt(fmt) KBUILD_MODNAME ":pid:%d:%s: " fmt, current->pid, __func__ +extern struct file_system_type autofs_fs_type; + /* * Unified info structure. This is pointed to by both the dentry and * inode structures. Each file in the filesystem has an instance of this @@ -101,16 +103,19 @@ struct autofs_wait_queue { #define AUTOFS_SBI_MAGIC 0x6d4a556d +#define AUTOFS_SBI_CATATONIC 0x0001 +#define AUTOFS_SBI_STRICTEXPIRE 0x0002 + struct autofs_sb_info { u32 magic; int pipefd; struct file *pipe; struct pid *oz_pgrp; - int catatonic; int version; int sub_version; int min_proto; int max_proto; + unsigned int flags; unsigned long exp_timeout; unsigned int type; struct super_block *sb; @@ -126,8 +131,7 @@ struct autofs_sb_info { static inline struct autofs_sb_info *autofs_sbi(struct super_block *sb) { - return sb->s_magic != AUTOFS_SUPER_MAGIC ? - NULL : (struct autofs_sb_info *)(sb->s_fs_info); + return (struct autofs_sb_info *)(sb->s_fs_info); } static inline struct autofs_info *autofs_dentry_ino(struct dentry *dentry) @@ -141,7 +145,8 @@ static inline struct autofs_info *autofs_dentry_ino(struct dentry *dentry) */ static inline int autofs_oz_mode(struct autofs_sb_info *sbi) { - return sbi->catatonic || task_pgrp(current) == sbi->oz_pgrp; + return ((sbi->flags & AUTOFS_SBI_CATATONIC) || + task_pgrp(current) == sbi->oz_pgrp); } struct inode *autofs_get_inode(struct super_block *, umode_t); diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c index 86eafda4a652..e9fe74d1541b 100644 --- a/fs/autofs/dev-ioctl.c +++ b/fs/autofs/dev-ioctl.c @@ -151,22 +151,6 @@ out: return err; } -/* - * Get the autofs super block info struct from the file opened on - * the autofs mount point. - */ -static struct autofs_sb_info *autofs_dev_ioctl_sbi(struct file *f) -{ - struct autofs_sb_info *sbi = NULL; - struct inode *inode; - - if (f) { - inode = file_inode(f); - sbi = autofs_sbi(inode->i_sb); - } - return sbi; -} - /* Return autofs dev ioctl version */ static int autofs_dev_ioctl_version(struct file *fp, struct autofs_sb_info *sbi, @@ -366,7 +350,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp, pipefd = param->setpipefd.pipefd; mutex_lock(&sbi->wq_mutex); - if (!sbi->catatonic) { + if (!(sbi->flags & AUTOFS_SBI_CATATONIC)) { mutex_unlock(&sbi->wq_mutex); return -EBUSY; } else { @@ -393,7 +377,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp, swap(sbi->oz_pgrp, new_pid); sbi->pipefd = pipefd; sbi->pipe = pipe; - sbi->catatonic = 0; + sbi->flags &= ~AUTOFS_SBI_CATATONIC; } out: put_pid(new_pid); @@ -658,6 +642,8 @@ static int _autofs_dev_ioctl(unsigned int command, if (cmd != AUTOFS_DEV_IOCTL_VERSION_CMD && cmd != AUTOFS_DEV_IOCTL_OPENMOUNT_CMD && cmd != AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD) { + struct super_block *sb; + fp = fget(param->ioctlfd); if (!fp) { if (cmd == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD) @@ -666,12 +652,13 @@ static int _autofs_dev_ioctl(unsigned int command, goto out; } - sbi = autofs_dev_ioctl_sbi(fp); - if (!sbi || sbi->magic != AUTOFS_SBI_MAGIC) { + sb = file_inode(fp)->i_sb; + if (sb->s_type != &autofs_fs_type) { err = -EINVAL; fput(fp); goto out; } + sbi = autofs_sbi(sb); /* * Admin needs to be able to set the mount catatonic in diff --git a/fs/autofs/init.c b/fs/autofs/init.c index 79ae07d9592f..c0c1db2cc6ea 100644 --- a/fs/autofs/init.c +++ b/fs/autofs/init.c @@ -16,7 +16,7 @@ static struct dentry *autofs_mount(struct file_system_type *fs_type, return mount_nodev(fs_type, flags, data, autofs_fill_super); } -static struct file_system_type autofs_fs_type = { +struct file_system_type autofs_fs_type = { .owner = THIS_MODULE, .name = "autofs", .mount = autofs_mount, diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index 846c052569dd..0e8ea2d9a2bb 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -87,6 +87,8 @@ static int autofs_show_options(struct seq_file *m, struct dentry *root) seq_printf(m, ",direct"); else seq_printf(m, ",indirect"); + if (sbi->flags & AUTOFS_SBI_STRICTEXPIRE) + seq_printf(m, ",strictexpire"); #ifdef CONFIG_CHECKPOINT_RESTORE if (sbi->pipe) seq_printf(m, ",pipe_ino=%ld", file_inode(sbi->pipe)->i_ino); @@ -109,7 +111,7 @@ static const struct super_operations autofs_sops = { }; enum {Opt_err, Opt_fd, Opt_uid, Opt_gid, Opt_pgrp, Opt_minproto, Opt_maxproto, - Opt_indirect, Opt_direct, Opt_offset}; + Opt_indirect, Opt_direct, Opt_offset, Opt_strictexpire}; static const match_table_t tokens = { {Opt_fd, "fd=%u"}, @@ -121,24 +123,28 @@ static const match_table_t tokens = { {Opt_indirect, "indirect"}, {Opt_direct, "direct"}, {Opt_offset, "offset"}, + {Opt_strictexpire, "strictexpire"}, {Opt_err, NULL} }; -static int parse_options(char *options, int *pipefd, kuid_t *uid, kgid_t *gid, - int *pgrp, bool *pgrp_set, unsigned int *type, - int *minproto, int *maxproto) +static int parse_options(char *options, + struct inode *root, int *pgrp, bool *pgrp_set, + struct autofs_sb_info *sbi) { char *p; substring_t args[MAX_OPT_ARGS]; int option; + int pipefd = -1; + kuid_t uid; + kgid_t gid; - *uid = current_uid(); - *gid = current_gid(); + root->i_uid = current_uid(); + root->i_gid = current_gid(); - *minproto = AUTOFS_MIN_PROTO_VERSION; - *maxproto = AUTOFS_MAX_PROTO_VERSION; + sbi->min_proto = AUTOFS_MIN_PROTO_VERSION; + sbi->max_proto = AUTOFS_MAX_PROTO_VERSION; - *pipefd = -1; + sbi->pipefd = -1; if (!options) return 1; @@ -152,22 +158,25 @@ static int parse_options(char *options, int *pipefd, kuid_t *uid, kgid_t *gid, token = match_token(p, tokens, args); switch (token) { case Opt_fd: - if (match_int(args, pipefd)) + if (match_int(args, &pipefd)) return 1; + sbi->pipefd = pipefd; break; case Opt_uid: if (match_int(args, &option)) return 1; - *uid = make_kuid(current_user_ns(), option); - if (!uid_valid(*uid)) + uid = make_kuid(current_user_ns(), option); + if (!uid_valid(uid)) return 1; + root->i_uid = uid; break; case Opt_gid: if (match_int(args, &option)) return 1; - *gid = make_kgid(current_user_ns(), option); - if (!gid_valid(*gid)) + gid = make_kgid(current_user_ns(), option); + if (!gid_valid(gid)) return 1; + root->i_gid = gid; break; case Opt_pgrp: if (match_int(args, &option)) @@ -178,27 +187,30 @@ static int parse_options(char *options, int *pipefd, kuid_t *uid, kgid_t *gid, case Opt_minproto: if (match_int(args, &option)) return 1; - *minproto = option; + sbi->min_proto = option; break; case Opt_maxproto: if (match_int(args, &option)) return 1; - *maxproto = option; + sbi->max_proto = option; break; case Opt_indirect: - set_autofs_type_indirect(type); + set_autofs_type_indirect(&sbi->type); break; case Opt_direct: - set_autofs_type_direct(type); + set_autofs_type_direct(&sbi->type); break; case Opt_offset: - set_autofs_type_offset(type); + set_autofs_type_offset(&sbi->type); + break; + case Opt_strictexpire: + sbi->flags |= AUTOFS_SBI_STRICTEXPIRE; break; default: return 1; } } - return (*pipefd < 0); + return (sbi->pipefd < 0); } int autofs_fill_super(struct super_block *s, void *data, int silent) @@ -206,7 +218,6 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) struct inode *root_inode; struct dentry *root; struct file *pipe; - int pipefd; struct autofs_sb_info *sbi; struct autofs_info *ino; int pgrp = 0; @@ -222,12 +233,12 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) sbi->magic = AUTOFS_SBI_MAGIC; sbi->pipefd = -1; sbi->pipe = NULL; - sbi->catatonic = 1; sbi->exp_timeout = 0; sbi->oz_pgrp = NULL; sbi->sb = s; sbi->version = 0; sbi->sub_version = 0; + sbi->flags = AUTOFS_SBI_CATATONIC; set_autofs_type_indirect(&sbi->type); sbi->min_proto = 0; sbi->max_proto = 0; @@ -262,9 +273,7 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) root->d_fsdata = ino; /* Can this call block? */ - if (parse_options(data, &pipefd, &root_inode->i_uid, &root_inode->i_gid, - &pgrp, &pgrp_set, &sbi->type, &sbi->min_proto, - &sbi->max_proto)) { + if (parse_options(data, root_inode, &pgrp, &pgrp_set, sbi)) { pr_err("called with bogus options\n"); goto fail_dput; } @@ -303,8 +312,9 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) root_inode->i_fop = &autofs_root_operations; root_inode->i_op = &autofs_dir_inode_operations; - pr_debug("pipe fd = %d, pgrp = %u\n", pipefd, pid_nr(sbi->oz_pgrp)); - pipe = fget(pipefd); + pr_debug("pipe fd = %d, pgrp = %u\n", + sbi->pipefd, pid_nr(sbi->oz_pgrp)); + pipe = fget(sbi->pipefd); if (!pipe) { pr_err("could not open pipe file descriptor\n"); @@ -314,8 +324,7 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) if (ret < 0) goto fail_fput; sbi->pipe = pipe; - sbi->pipefd = pipefd; - sbi->catatonic = 0; + sbi->flags &= ~AUTOFS_SBI_CATATONIC; /* * Success! Install the root dentry now to indicate completion. diff --git a/fs/autofs/root.c b/fs/autofs/root.c index 782e57b911ab..1246f396bf0e 100644 --- a/fs/autofs/root.c +++ b/fs/autofs/root.c @@ -275,8 +275,11 @@ static int autofs_mount_wait(const struct path *path, bool rcu_walk) pr_debug("waiting for mount name=%pd\n", path->dentry); status = autofs_wait(sbi, path, NFY_MOUNT); pr_debug("mount wait done status=%d\n", status); + ino->last_used = jiffies; + return status; } - ino->last_used = jiffies; + if (!(sbi->flags & AUTOFS_SBI_STRICTEXPIRE)) + ino->last_used = jiffies; return status; } @@ -510,7 +513,8 @@ static struct dentry *autofs_lookup(struct inode *dir, sbi = autofs_sbi(dir->i_sb); pr_debug("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d\n", - current->pid, task_pgrp_nr(current), sbi->catatonic, + current->pid, task_pgrp_nr(current), + sbi->flags & AUTOFS_SBI_CATATONIC, autofs_oz_mode(sbi)); active = autofs_lookup_active(dentry); @@ -563,7 +567,7 @@ static int autofs_dir_symlink(struct inode *dir, * autofs mount is catatonic but the state of an autofs * file system needs to be preserved over restarts. */ - if (sbi->catatonic) + if (sbi->flags & AUTOFS_SBI_CATATONIC) return -EACCES; BUG_ON(!ino); @@ -626,7 +630,7 @@ static int autofs_dir_unlink(struct inode *dir, struct dentry *dentry) * autofs mount is catatonic but the state of an autofs * file system needs to be preserved over restarts. */ - if (sbi->catatonic) + if (sbi->flags & AUTOFS_SBI_CATATONIC) return -EACCES; if (atomic_dec_and_test(&ino->count)) { @@ -714,7 +718,7 @@ static int autofs_dir_rmdir(struct inode *dir, struct dentry *dentry) * autofs mount is catatonic but the state of an autofs * file system needs to be preserved over restarts. */ - if (sbi->catatonic) + if (sbi->flags & AUTOFS_SBI_CATATONIC) return -EACCES; spin_lock(&sbi->lookup_lock); @@ -759,7 +763,7 @@ static int autofs_dir_mkdir(struct inode *dir, * autofs mount is catatonic but the state of an autofs * file system needs to be preserved over restarts. */ - if (sbi->catatonic) + if (sbi->flags & AUTOFS_SBI_CATATONIC) return -EACCES; pr_debug("dentry %p, creating %pd\n", dentry, dentry); diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c index f6385c6ef0a5..15a3e31d0904 100644 --- a/fs/autofs/waitq.c +++ b/fs/autofs/waitq.c @@ -20,14 +20,14 @@ void autofs_catatonic_mode(struct autofs_sb_info *sbi) struct autofs_wait_queue *wq, *nwq; mutex_lock(&sbi->wq_mutex); - if (sbi->catatonic) { + if (sbi->flags & AUTOFS_SBI_CATATONIC) { mutex_unlock(&sbi->wq_mutex); return; } pr_debug("entering catatonic mode\n"); - sbi->catatonic = 1; + sbi->flags |= AUTOFS_SBI_CATATONIC; wq = sbi->queues; sbi->queues = NULL; /* Erase all wait queues */ while (wq) { @@ -255,7 +255,7 @@ static int validate_request(struct autofs_wait_queue **wait, struct autofs_wait_queue *wq; struct autofs_info *ino; - if (sbi->catatonic) + if (sbi->flags & AUTOFS_SBI_CATATONIC) return -ENOENT; /* Wait in progress, continue; */ @@ -290,7 +290,7 @@ static int validate_request(struct autofs_wait_queue **wait, if (mutex_lock_interruptible(&sbi->wq_mutex)) return -EINTR; - if (sbi->catatonic) + if (sbi->flags & AUTOFS_SBI_CATATONIC) return -ENOENT; wq = autofs_find_wait(sbi, qstr); @@ -359,7 +359,7 @@ int autofs_wait(struct autofs_sb_info *sbi, pid_t tgid; /* In catatonic mode, we don't wait for nobody */ - if (sbi->catatonic) + if (sbi->flags & AUTOFS_SBI_CATATONIC) return -ENOENT; /* diff --git a/fs/bfs/bfs.h b/fs/bfs/bfs.h index 67aef3bb89e4..606f9378b2f0 100644 --- a/fs/bfs/bfs.h +++ b/fs/bfs/bfs.h @@ -1,13 +1,20 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * fs/bfs/bfs.h - * Copyright (C) 1999 Tigran Aivazian <tigran@veritas.com> + * Copyright (C) 1999-2018 Tigran Aivazian <aivazian.tigran@gmail.com> */ #ifndef _FS_BFS_BFS_H #define _FS_BFS_BFS_H #include <linux/bfs_fs.h> +/* In theory BFS supports up to 512 inodes, numbered from 2 (for /) up to 513 inclusive. + In actual fact, attempting to create the 512th inode (i.e. inode No. 513 or file No. 511) + will fail with ENOSPC in bfs_add_entry(): the root directory cannot contain so many entries, counting '..'. + So, mkfs.bfs(8) should really limit its -N option to 511 and not 512. For now, we just print a warning + if a filesystem is mounted with such "impossible to fill up" number of inodes */ +#define BFS_MAX_LASTI 513 + /* * BFS file system in-core superblock info */ @@ -17,7 +24,7 @@ struct bfs_sb_info { unsigned long si_freei; unsigned long si_lf_eblk; unsigned long si_lasti; - unsigned long *si_imap; + DECLARE_BITMAP(si_imap, BFS_MAX_LASTI+1); struct mutex bfs_lock; }; diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index f32f21c3bbc7..d8dfe3a0cb39 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -2,8 +2,8 @@ /* * fs/bfs/dir.c * BFS directory operations. - * Copyright (C) 1999,2000 Tigran Aivazian <tigran@veritas.com> - * Made endianness-clean by Andrew Stribblehill <ads@wompom.org> 2005 + * Copyright (C) 1999-2018 Tigran Aivazian <aivazian.tigran@gmail.com> + * Made endianness-clean by Andrew Stribblehill <ads@wompom.org> 2005 */ #include <linux/time.h> diff --git a/fs/bfs/file.c b/fs/bfs/file.c index 1476cdd90cfb..0dceefc54b48 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -2,7 +2,7 @@ /* * fs/bfs/file.c * BFS file operations. - * Copyright (C) 1999,2000 Tigran Aivazian <tigran@veritas.com> + * Copyright (C) 1999-2018 Tigran Aivazian <aivazian.tigran@gmail.com> * * Make the file block allocation algorithm understand the size * of the underlying block device. diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index d81c148682e7..d136b2aaafb3 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -1,10 +1,9 @@ /* * fs/bfs/inode.c * BFS superblock and inode operations. - * Copyright (C) 1999-2006 Tigran Aivazian <aivazian.tigran@gmail.com> + * Copyright (C) 1999-2018 Tigran Aivazian <aivazian.tigran@gmail.com> * From fs/minix, Copyright (C) 1991, 1992 Linus Torvalds. - * - * Made endianness-clean by Andrew Stribblehill <ads@wompom.org>, 2005. + * Made endianness-clean by Andrew Stribblehill <ads@wompom.org>, 2005. */ #include <linux/module.h> @@ -118,12 +117,12 @@ static int bfs_write_inode(struct inode *inode, struct writeback_control *wbc) { struct bfs_sb_info *info = BFS_SB(inode->i_sb); unsigned int ino = (u16)inode->i_ino; - unsigned long i_sblock; + unsigned long i_sblock; struct bfs_inode *di; struct buffer_head *bh; int err = 0; - dprintf("ino=%08x\n", ino); + dprintf("ino=%08x\n", ino); di = find_inode(inode->i_sb, ino, &bh); if (IS_ERR(di)) @@ -144,7 +143,7 @@ static int bfs_write_inode(struct inode *inode, struct writeback_control *wbc) di->i_atime = cpu_to_le32(inode->i_atime.tv_sec); di->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec); di->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec); - i_sblock = BFS_I(inode)->i_sblock; + i_sblock = BFS_I(inode)->i_sblock; di->i_sblock = cpu_to_le32(i_sblock); di->i_eblock = cpu_to_le32(BFS_I(inode)->i_eblock); di->i_eoffset = cpu_to_le32(i_sblock * BFS_BSIZE + inode->i_size - 1); @@ -188,13 +187,13 @@ static void bfs_evict_inode(struct inode *inode) mark_buffer_dirty(bh); brelse(bh); - if (bi->i_dsk_ino) { + if (bi->i_dsk_ino) { if (bi->i_sblock) info->si_freeb += bi->i_eblock + 1 - bi->i_sblock; info->si_freei++; clear_bit(ino, info->si_imap); - bfs_dump_imap("delete_inode", s); - } + bfs_dump_imap("evict_inode", s); + } /* * If this was the last file, make the previous block @@ -214,7 +213,6 @@ static void bfs_put_super(struct super_block *s) return; mutex_destroy(&info->bfs_lock); - kfree(info->si_imap); kfree(info); s->s_fs_info = NULL; } @@ -311,8 +309,7 @@ void bfs_dump_imap(const char *prefix, struct super_block *s) else strcat(tmpbuf, "0"); } - printf("BFS-fs: %s: lasti=%08lx <%s>\n", - prefix, BFS_SB(s)->si_lasti, tmpbuf); + printf("%s: lasti=%08lx <%s>\n", prefix, BFS_SB(s)->si_lasti, tmpbuf); free_page((unsigned long)tmpbuf); #endif } @@ -322,7 +319,7 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) struct buffer_head *bh, *sbh; struct bfs_super_block *bfs_sb; struct inode *inode; - unsigned i, imap_len; + unsigned i; struct bfs_sb_info *info; int ret = -EINVAL; unsigned long i_sblock, i_eblock, i_eoff, s_size; @@ -341,8 +338,7 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) bfs_sb = (struct bfs_super_block *)sbh->b_data; if (le32_to_cpu(bfs_sb->s_magic) != BFS_MAGIC) { if (!silent) - printf("No BFS filesystem on %s (magic=%08x)\n", - s->s_id, le32_to_cpu(bfs_sb->s_magic)); + printf("No BFS filesystem on %s (magic=%08x)\n", s->s_id, le32_to_cpu(bfs_sb->s_magic)); goto out1; } if (BFS_UNCLEAN(bfs_sb, s) && !silent) @@ -351,18 +347,16 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) s->s_magic = BFS_MAGIC; if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end) || - le32_to_cpu(bfs_sb->s_start) < BFS_BSIZE) { - printf("Superblock is corrupted\n"); + le32_to_cpu(bfs_sb->s_start) < sizeof(struct bfs_super_block) + sizeof(struct bfs_dirent)) { + printf("Superblock is corrupted on %s\n", s->s_id); goto out1; } - info->si_lasti = (le32_to_cpu(bfs_sb->s_start) - BFS_BSIZE) / - sizeof(struct bfs_inode) - + BFS_ROOT_INO - 1; - imap_len = (info->si_lasti / 8) + 1; - info->si_imap = kzalloc(imap_len, GFP_KERNEL | __GFP_NOWARN); - if (!info->si_imap) { - printf("Cannot allocate %u bytes\n", imap_len); + info->si_lasti = (le32_to_cpu(bfs_sb->s_start) - BFS_BSIZE) / sizeof(struct bfs_inode) + BFS_ROOT_INO - 1; + if (info->si_lasti == BFS_MAX_LASTI) + printf("WARNING: filesystem %s was created with 512 inodes, the real maximum is 511, mounting anyway\n", s->s_id); + else if (info->si_lasti > BFS_MAX_LASTI) { + printf("Impossible last inode number %lu > %d on %s\n", info->si_lasti, BFS_MAX_LASTI, s->s_id); goto out1; } for (i = 0; i < BFS_ROOT_INO; i++) @@ -372,26 +366,25 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) inode = bfs_iget(s, BFS_ROOT_INO); if (IS_ERR(inode)) { ret = PTR_ERR(inode); - goto out2; + goto out1; } s->s_root = d_make_root(inode); if (!s->s_root) { ret = -ENOMEM; - goto out2; + goto out1; } info->si_blocks = (le32_to_cpu(bfs_sb->s_end) + 1) >> BFS_BSIZE_BITS; - info->si_freeb = (le32_to_cpu(bfs_sb->s_end) + 1 - - le32_to_cpu(bfs_sb->s_start)) >> BFS_BSIZE_BITS; + info->si_freeb = (le32_to_cpu(bfs_sb->s_end) + 1 - le32_to_cpu(bfs_sb->s_start)) >> BFS_BSIZE_BITS; info->si_freei = 0; info->si_lf_eblk = 0; /* can we read the last block? */ bh = sb_bread(s, info->si_blocks - 1); if (!bh) { - printf("Last block not available: %lu\n", info->si_blocks - 1); + printf("Last block not available on %s: %lu\n", s->s_id, info->si_blocks - 1); ret = -EIO; - goto out3; + goto out2; } brelse(bh); @@ -425,11 +418,11 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) (i_eoff != le32_to_cpu(-1) && i_eoff > s_size) || i_sblock * BFS_BSIZE > i_eoff) { - printf("Inode 0x%08x corrupted\n", i); + printf("Inode 0x%08x corrupted on %s\n", i, s->s_id); brelse(bh); ret = -EIO; - goto out3; + goto out2; } if (!di->i_ino) { @@ -445,14 +438,12 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) } brelse(bh); brelse(sbh); - bfs_dump_imap("read_super", s); + bfs_dump_imap("fill_super", s); return 0; -out3: +out2: dput(s->s_root); s->s_root = NULL; -out2: - kfree(info->si_imap); out1: brelse(sbh); out: @@ -482,7 +473,7 @@ static int __init init_bfs_fs(void) int err = init_inodecache(); if (err) goto out1; - err = register_filesystem(&bfs_fs_type); + err = register_filesystem(&bfs_fs_type); if (err) goto out; return 0; diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index c3deb2e35f20..ca9725f18e00 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -78,9 +78,9 @@ static int aout_core_dump(struct coredump_params *cprm) /* make sure we actually have a data and stack area to dump */ set_fs(USER_DS); - if (!access_ok(VERIFY_READ, START_DATA(dump), dump.u_dsize << PAGE_SHIFT)) + if (!access_ok(START_DATA(dump), dump.u_dsize << PAGE_SHIFT)) dump.u_dsize = 0; - if (!access_ok(VERIFY_READ, START_STACK(dump), dump.u_ssize << PAGE_SHIFT)) + if (!access_ok(START_STACK(dump), dump.u_ssize << PAGE_SHIFT)) dump.u_ssize = 0; set_fs(KERNEL_DS); diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index 7cde3f46ad26..d0078cbb718b 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -42,10 +42,14 @@ static int load_script(struct linux_binprm *bprm) fput(bprm->file); bprm->file = NULL; - bprm->buf[BINPRM_BUF_SIZE - 1] = '\0'; - if ((cp = strchr(bprm->buf, '\n')) == NULL) - cp = bprm->buf+BINPRM_BUF_SIZE-1; + for (cp = bprm->buf+2;; cp++) { + if (cp >= bprm->buf + BINPRM_BUF_SIZE) + return -ENOEXEC; + if (!*cp || (*cp == '\n')) + break; + } *cp = '\0'; + while (cp > bprm->buf) { cp--; if ((*cp == ' ') || (*cp == '\t')) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index d92462fe66c8..f64aad613727 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1016,19 +1016,21 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, parent_start = parent->start; /* - * If we are COWing a node/leaf from the extent, chunk or device trees, - * make sure that we do not finish block group creation of pending block - * groups. We do this to avoid a deadlock. + * If we are COWing a node/leaf from the extent, chunk, device or free + * space trees, make sure that we do not finish block group creation of + * pending block groups. We do this to avoid a deadlock. * COWing can result in allocation of a new chunk, and flushing pending * block groups (btrfs_create_pending_block_groups()) can be triggered * when finishing allocation of a new chunk. Creation of a pending block - * group modifies the extent, chunk and device trees, therefore we could - * deadlock with ourselves since we are holding a lock on an extent - * buffer that btrfs_create_pending_block_groups() may try to COW later. + * group modifies the extent, chunk, device and free space trees, + * therefore we could deadlock with ourselves since we are holding a + * lock on an extent buffer that btrfs_create_pending_block_groups() may + * try to COW later. */ if (root == fs_info->extent_root || root == fs_info->chunk_root || - root == fs_info->dev_root) + root == fs_info->dev_root || + root == fs_info->free_space_root) trans->can_flush_pending_bgs = false; cow = btrfs_alloc_tree_block(trans, root, parent_start, diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index f031a447a047..0a68cf7032f5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1144,9 +1144,6 @@ struct btrfs_fs_info { struct mutex unused_bg_unpin_mutex; struct mutex delete_unused_bgs_mutex; - /* For btrfs to record security options */ - struct security_mnt_opts security_opts; - /* * Chunks that can't be freed yet (under a trim/discard operation) * and will be latter freed. Protected by fs_info->chunk_mutex. @@ -3021,7 +3018,6 @@ static inline void free_fs_info(struct btrfs_fs_info *fs_info) kfree(fs_info->free_space_root); kfree(fs_info->super_copy); kfree(fs_info->super_for_commit); - security_free_mnt_opts(&fs_info->security_opts); kvfree(fs_info); } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index fc126b92ea59..52abe4082680 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4103,8 +4103,7 @@ int extent_readpages(struct address_space *mapping, struct list_head *pages, while (!list_empty(pages)) { for (nr = 0; nr < ARRAY_SIZE(pagepool) && !list_empty(pages);) { - struct page *page = list_entry(pages->prev, - struct page, lru); + struct page *page = lru_to_page(pages); prefetchw(&page->flags); list_del(&page->lru); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index fab9443f6a42..9c8e1734429c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3221,6 +3221,26 @@ static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2) inode_lock_nested(inode2, I_MUTEX_CHILD); } +static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1, + struct inode *inode2, u64 loff2, u64 len) +{ + unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1); + unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1); +} + +static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1, + struct inode *inode2, u64 loff2, u64 len) +{ + if (inode1 < inode2) { + swap(inode1, inode2); + swap(loff1, loff2); + } else if (inode1 == inode2 && loff2 < loff1) { + swap(loff1, loff2); + } + lock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1); + lock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1); +} + static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen, struct inode *dst, u64 dst_loff) { @@ -3242,11 +3262,12 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen, return -EINVAL; /* - * Lock destination range to serialize with concurrent readpages(). + * Lock destination range to serialize with concurrent readpages() and + * source range to serialize with relocation. */ - lock_extent(&BTRFS_I(dst)->io_tree, dst_loff, dst_loff + len - 1); + btrfs_double_extent_lock(src, loff, dst, dst_loff, len); ret = btrfs_clone(src, dst, loff, olen, len, dst_loff, 1); - unlock_extent(&BTRFS_I(dst)->io_tree, dst_loff, dst_loff + len - 1); + btrfs_double_extent_unlock(src, loff, dst, dst_loff, len); return ret; } @@ -3905,17 +3926,33 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, len = ALIGN(src->i_size, bs) - off; if (destoff > inode->i_size) { + const u64 wb_start = ALIGN_DOWN(inode->i_size, bs); + ret = btrfs_cont_expand(inode, inode->i_size, destoff); if (ret) return ret; + /* + * We may have truncated the last block if the inode's size is + * not sector size aligned, so we need to wait for writeback to + * complete before proceeding further, otherwise we can race + * with cloning and attempt to increment a reference to an + * extent that no longer exists (writeback completed right after + * we found the previous extent covering eof and before we + * attempted to increment its reference count). + */ + ret = btrfs_wait_ordered_range(inode, wb_start, + destoff - wb_start); + if (ret) + return ret; } /* - * Lock destination range to serialize with concurrent readpages(). + * Lock destination range to serialize with concurrent readpages() and + * source range to serialize with relocation. */ - lock_extent(&BTRFS_I(inode)->io_tree, destoff, destoff + len - 1); + btrfs_double_extent_lock(src, off, inode, destoff, len); ret = btrfs_clone(src, inode, off, olen, len, destoff, 0); - unlock_extent(&BTRFS_I(inode)->io_tree, destoff, destoff + len - 1); + btrfs_double_extent_unlock(src, off, inode, destoff, len); /* * Truncate page cache pages so that future reads will see the cloned * data immediately and not the previous data. diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 1b15b43905f8..7ea2d6b1f170 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6646,7 +6646,7 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) goto out; } - if (!access_ok(VERIFY_READ, arg->clone_sources, + if (!access_ok(arg->clone_sources, sizeof(*arg->clone_sources) * arg->clone_sources_count)) { ret = -EFAULT; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 368a5b9e6c13..c5586ffd1426 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1458,56 +1458,6 @@ out: return root; } -static int parse_security_options(char *orig_opts, - struct security_mnt_opts *sec_opts) -{ - char *secdata = NULL; - int ret = 0; - - secdata = alloc_secdata(); - if (!secdata) - return -ENOMEM; - ret = security_sb_copy_data(orig_opts, secdata); - if (ret) { - free_secdata(secdata); - return ret; - } - ret = security_sb_parse_opts_str(secdata, sec_opts); - free_secdata(secdata); - return ret; -} - -static int setup_security_options(struct btrfs_fs_info *fs_info, - struct super_block *sb, - struct security_mnt_opts *sec_opts) -{ - int ret = 0; - - /* - * Call security_sb_set_mnt_opts() to check whether new sec_opts - * is valid. - */ - ret = security_sb_set_mnt_opts(sb, sec_opts, 0, NULL); - if (ret) - return ret; - -#ifdef CONFIG_SECURITY - if (!fs_info->security_opts.num_mnt_opts) { - /* first time security setup, copy sec_opts to fs_info */ - memcpy(&fs_info->security_opts, sec_opts, sizeof(*sec_opts)); - } else { - /* - * Since SELinux (the only one supporting security_mnt_opts) - * does NOT support changing context during remount/mount of - * the same sb, this must be the same or part of the same - * security options, just free it. - */ - security_free_mnt_opts(sec_opts); - } -#endif - return ret; -} - /* * Find a superblock for the given device / mount point. * @@ -1522,16 +1472,15 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, struct btrfs_device *device = NULL; struct btrfs_fs_devices *fs_devices = NULL; struct btrfs_fs_info *fs_info = NULL; - struct security_mnt_opts new_sec_opts; + void *new_sec_opts = NULL; fmode_t mode = FMODE_READ; int error = 0; if (!(flags & SB_RDONLY)) mode |= FMODE_WRITE; - security_init_mnt_opts(&new_sec_opts); if (data) { - error = parse_security_options(data, &new_sec_opts); + error = security_sb_eat_lsm_opts(data, &new_sec_opts); if (error) return ERR_PTR(error); } @@ -1550,7 +1499,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL); fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL); - security_init_mnt_opts(&fs_info->security_opts); if (!fs_info->super_copy || !fs_info->super_for_commit) { error = -ENOMEM; goto error_fs_info; @@ -1601,16 +1549,12 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, btrfs_sb(s)->bdev_holder = fs_type; error = btrfs_fill_super(s, fs_devices, data); } + if (!error) + error = security_sb_set_mnt_opts(s, new_sec_opts, 0, NULL); + security_free_mnt_opts(&new_sec_opts); if (error) { deactivate_locked_super(s); - goto error_sec_opts; - } - - fs_info = btrfs_sb(s); - error = setup_security_options(fs_info, s, &new_sec_opts); - if (error) { - deactivate_locked_super(s); - goto error_sec_opts; + return ERR_PTR(error); } return dget(s->s_root); @@ -1779,18 +1723,14 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) btrfs_remount_prepare(fs_info); if (data) { - struct security_mnt_opts new_sec_opts; + void *new_sec_opts = NULL; - security_init_mnt_opts(&new_sec_opts); - ret = parse_security_options(data, &new_sec_opts); + ret = security_sb_eat_lsm_opts(data, &new_sec_opts); + if (!ret) + ret = security_sb_remount(sb, new_sec_opts); + security_free_mnt_opts(&new_sec_opts); if (ret) goto restore; - ret = setup_security_options(fs_info, sb, - &new_sec_opts); - if (ret) { - security_free_mnt_opts(&new_sec_opts); - goto restore; - } } ret = btrfs_parse_options(fs_info, data, *flags); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2576b1a379c9..3e4f8f88353e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -7825,6 +7825,18 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info, ret = -EUCLEAN; goto out; } + + /* It's possible this device is a dummy for seed device */ + if (dev->disk_total_bytes == 0) { + dev = find_device(fs_info->fs_devices->seed, devid, NULL); + if (!dev) { + btrfs_err(fs_info, "failed to find seed devid %llu", + devid); + ret = -EUCLEAN; + goto out; + } + } + if (physical_offset + physical_len > dev->disk_total_bytes) { btrfs_err(fs_info, "dev extent devid %llu physical offset %llu len %llu is beyond device boundary %llu", diff --git a/fs/buffer.c b/fs/buffer.c index d60d61e8ed7d..52d024bfdbc1 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2366,7 +2366,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, balance_dirty_pages_ratelimited(mapping); - if (unlikely(fatal_signal_pending(current))) { + if (fatal_signal_pending(current)) { err = -EINTR; goto out; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8eade7a993c1..a47c541f8006 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -306,7 +306,7 @@ static int start_read(struct inode *inode, struct ceph_rw_context *rw_ctx, struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->client->osdc; struct ceph_inode_info *ci = ceph_inode(inode); - struct page *page = list_entry(page_list->prev, struct page, lru); + struct page *page = lru_to_page(page_list); struct ceph_vino vino; struct ceph_osd_request *req; u64 off; @@ -333,8 +333,7 @@ static int start_read(struct inode *inode, struct ceph_rw_context *rw_ctx, if (got) ceph_put_cap_refs(ci, got); while (!list_empty(page_list)) { - page = list_entry(page_list->prev, - struct page, lru); + page = lru_to_page(page_list); list_del(&page->lru); put_page(page); } @@ -1495,10 +1494,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf) if (err < 0 || off >= i_size_read(inode)) { unlock_page(page); put_page(page); - if (err == -ENOMEM) - ret = VM_FAULT_OOM; - else - ret = VM_FAULT_SIGBUS; + ret = vmf_error(err); goto out_inline; } if (err < PAGE_SIZE) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index f3496db4bb3e..94c026bba2c2 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -657,6 +657,9 @@ void ceph_add_cap(struct inode *inode, session->s_nr_caps++; spin_unlock(&session->s_cap_lock); } else { + if (cap->cap_gen < session->s_cap_gen) + cap->issued = cap->implemented = CEPH_CAP_PIN; + /* * auth mds of the inode changed. we received the cap export * message, but still haven't received the cap import message. @@ -1855,14 +1858,17 @@ retry_locked: retain |= CEPH_CAP_ANY; /* be greedy */ } else if (S_ISDIR(inode->i_mode) && (issued & CEPH_CAP_FILE_SHARED) && - __ceph_dir_is_complete(ci)) { + __ceph_dir_is_complete(ci)) { /* * If a directory is complete, we want to keep * the exclusive cap. So that MDS does not end up * revoking the shared cap on every create/unlink * operation. */ - want = CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_EXCL; + if (IS_RDONLY(inode)) + want = CEPH_CAP_ANY_SHARED; + else + want = CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_EXCL; retain |= want; } else { @@ -1970,8 +1976,7 @@ retry_locked: goto ack; /* things we might delay */ - if ((cap->issued & ~retain) == 0 && - cap->mds_wanted == want) + if ((cap->issued & ~retain) == 0) continue; /* nope, all good */ if (no_delay) @@ -3048,7 +3053,8 @@ static void handle_cap_grant(struct inode *inode, int used, wanted, dirty; u64 size = le64_to_cpu(grant->size); u64 max_size = le64_to_cpu(grant->max_size); - int check_caps = 0; + unsigned char check_caps = 0; + bool was_stale = cap->cap_gen < session->s_cap_gen; bool wake = false; bool writeback = false; bool queue_trunc = false; @@ -3063,21 +3069,6 @@ static void handle_cap_grant(struct inode *inode, /* - * auth mds of the inode changed. we received the cap export message, - * but still haven't received the cap import message. handle_cap_export - * updated the new auth MDS' cap. - * - * "ceph_seq_cmp(seq, cap->seq) <= 0" means we are processing a message - * that was sent before the cap import message. So don't remove caps. - */ - if (ceph_seq_cmp(seq, cap->seq) <= 0) { - WARN_ON(cap != ci->i_auth_cap); - WARN_ON(cap->cap_id != le64_to_cpu(grant->cap_id)); - seq = cap->seq; - newcaps |= cap->issued; - } - - /* * If CACHE is being revoked, and we have no dirty buffers, * try to invalidate (once). (If there are dirty buffers, we * will invalidate _after_ writeback.) @@ -3096,6 +3087,24 @@ static void handle_cap_grant(struct inode *inode, } } + if (was_stale) + cap->issued = cap->implemented = CEPH_CAP_PIN; + + /* + * auth mds of the inode changed. we received the cap export message, + * but still haven't received the cap import message. handle_cap_export + * updated the new auth MDS' cap. + * + * "ceph_seq_cmp(seq, cap->seq) <= 0" means we are processing a message + * that was sent before the cap import message. So don't remove caps. + */ + if (ceph_seq_cmp(seq, cap->seq) <= 0) { + WARN_ON(cap != ci->i_auth_cap); + WARN_ON(cap->cap_id != le64_to_cpu(grant->cap_id)); + seq = cap->seq; + newcaps |= cap->issued; + } + /* side effects now are allowed */ cap->cap_gen = session->s_cap_gen; cap->seq = seq; @@ -3200,13 +3209,20 @@ static void handle_cap_grant(struct inode *inode, ceph_cap_string(wanted), ceph_cap_string(used), ceph_cap_string(dirty)); - if (wanted != le32_to_cpu(grant->wanted)) { - dout("mds wanted %s -> %s\n", - ceph_cap_string(le32_to_cpu(grant->wanted)), - ceph_cap_string(wanted)); - /* imported cap may not have correct mds_wanted */ - if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) - check_caps = 1; + + if ((was_stale || le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) && + (wanted & ~(cap->mds_wanted | newcaps))) { + /* + * If mds is importing cap, prior cap messages that update + * 'wanted' may get dropped by mds (migrate seq mismatch). + * + * We don't send cap message to update 'wanted' if what we + * want are already issued. If mds revokes caps, cap message + * that releases caps also tells mds what we want. But if + * caps got revoked by mds forcedly (session stale). We may + * haven't told mds what we want. + */ + check_caps = 1; } /* revocation, grant, or no-op? */ @@ -3539,9 +3555,9 @@ retry: goto out_unlock; if (target < 0) { - __ceph_remove_cap(cap, false); - if (!ci->i_auth_cap) + if (cap->mds_wanted | cap->issued) ci->i_ceph_flags |= CEPH_I_CAP_DROPPED; + __ceph_remove_cap(cap, false); goto out_unlock; } @@ -3569,7 +3585,6 @@ retry: tcap->cap_id = t_cap_id; tcap->seq = t_seq - 1; tcap->issue_seq = t_seq - 1; - tcap->mseq = t_mseq; tcap->issued |= issued; tcap->implemented |= issued; if (cap == ci->i_auth_cap) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 79dd5e6ed755..9d1f34d46627 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1098,8 +1098,9 @@ out_unlock: * splice a dentry to an inode. * caller must hold directory i_mutex for this to be safe. */ -static struct dentry *splice_dentry(struct dentry *dn, struct inode *in) +static int splice_dentry(struct dentry **pdn, struct inode *in) { + struct dentry *dn = *pdn; struct dentry *realdn; BUG_ON(d_inode(dn)); @@ -1132,28 +1133,23 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in) if (IS_ERR(realdn)) { pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n", PTR_ERR(realdn), dn, in, ceph_vinop(in)); - dn = realdn; - /* - * Caller should release 'dn' in the case of error. - * If 'req->r_dentry' is passed to this function, - * caller should leave 'req->r_dentry' untouched. - */ - goto out; - } else if (realdn) { + return PTR_ERR(realdn); + } + + if (realdn) { dout("dn %p (%d) spliced with %p (%d) " "inode %p ino %llx.%llx\n", dn, d_count(dn), realdn, d_count(realdn), d_inode(realdn), ceph_vinop(d_inode(realdn))); dput(dn); - dn = realdn; + *pdn = realdn; } else { BUG_ON(!ceph_dentry(dn)); dout("dn %p attached to %p ino %llx.%llx\n", dn, d_inode(dn), ceph_vinop(d_inode(dn))); } -out: - return dn; + return 0; } /* @@ -1340,7 +1336,12 @@ retry_lookup: dout("dn %p gets new offset %lld\n", req->r_old_dentry, ceph_dentry(req->r_old_dentry)->offset); - dn = req->r_old_dentry; /* use old_dentry */ + /* swap r_dentry and r_old_dentry in case that + * splice_dentry() gets called later. This is safe + * because no other place will use them */ + req->r_dentry = req->r_old_dentry; + req->r_old_dentry = dn; + dn = req->r_dentry; } /* null dentry? */ @@ -1365,12 +1366,10 @@ retry_lookup: if (d_really_is_negative(dn)) { ceph_dir_clear_ordered(dir); ihold(in); - dn = splice_dentry(dn, in); - if (IS_ERR(dn)) { - err = PTR_ERR(dn); + err = splice_dentry(&req->r_dentry, in); + if (err < 0) goto done; - } - req->r_dentry = dn; /* may have spliced */ + dn = req->r_dentry; /* may have spliced */ } else if (d_really_is_positive(dn) && d_inode(dn) != in) { dout(" %p links to %p %llx.%llx, not %llx.%llx\n", dn, d_inode(dn), ceph_vinop(d_inode(dn)), @@ -1390,22 +1389,18 @@ retry_lookup: } else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP || req->r_op == CEPH_MDS_OP_MKSNAP) && !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) { - struct dentry *dn = req->r_dentry; struct inode *dir = req->r_parent; /* fill out a snapdir LOOKUPSNAP dentry */ - BUG_ON(!dn); BUG_ON(!dir); BUG_ON(ceph_snap(dir) != CEPH_SNAPDIR); - dout(" linking snapped dir %p to dn %p\n", in, dn); + BUG_ON(!req->r_dentry); + dout(" linking snapped dir %p to dn %p\n", in, req->r_dentry); ceph_dir_clear_ordered(dir); ihold(in); - dn = splice_dentry(dn, in); - if (IS_ERR(dn)) { - err = PTR_ERR(dn); + err = splice_dentry(&req->r_dentry, in); + if (err < 0) goto done; - } - req->r_dentry = dn; /* may have spliced */ } else if (rinfo->head->is_dentry) { struct ceph_vino *ptvino = NULL; @@ -1669,8 +1664,6 @@ retry_lookup: } if (d_really_is_negative(dn)) { - struct dentry *realdn; - if (ceph_security_xattr_deadlock(in)) { dout(" skip splicing dn %p to inode %p" " (security xattr deadlock)\n", dn, in); @@ -1679,13 +1672,9 @@ retry_lookup: goto next_item; } - realdn = splice_dentry(dn, in); - if (IS_ERR(realdn)) { - err = PTR_ERR(realdn); - d_drop(dn); + err = splice_dentry(&dn, in); + if (err < 0) goto next_item; - } - dn = realdn; } ceph_dentry(dn)->offset = rde->offset; @@ -1701,8 +1690,7 @@ retry_lookup: err = ret; } next_item: - if (dn) - dput(dn); + dput(dn); } out: if (err == 0 && skipped == 0) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index bd13a3267ae0..163fc74bf221 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1232,13 +1232,13 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, dout("removing cap %p, ci is %p, inode is %p\n", cap, ci, &ci->vfs_inode); spin_lock(&ci->i_ceph_lock); + if (cap->mds_wanted | cap->issued) + ci->i_ceph_flags |= CEPH_I_CAP_DROPPED; __ceph_remove_cap(cap, false); if (!ci->i_auth_cap) { struct ceph_cap_flush *cf; struct ceph_mds_client *mdsc = fsc->mdsc; - ci->i_ceph_flags |= CEPH_I_CAP_DROPPED; - if (ci->i_wrbuffer_ref > 0 && READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) invalidate = true; @@ -1355,6 +1355,12 @@ static void remove_session_caps(struct ceph_mds_session *session) dispose_cap_releases(session->s_mdsc, &dispose); } +enum { + RECONNECT, + RENEWCAPS, + FORCE_RO, +}; + /* * wake up any threads waiting on this session's caps. if the cap is * old (didn't get renewed on the client reconnect), remove it now. @@ -1365,23 +1371,34 @@ static int wake_up_session_cb(struct inode *inode, struct ceph_cap *cap, void *arg) { struct ceph_inode_info *ci = ceph_inode(inode); + unsigned long ev = (unsigned long)arg; - if (arg) { + if (ev == RECONNECT) { spin_lock(&ci->i_ceph_lock); ci->i_wanted_max_size = 0; ci->i_requested_max_size = 0; spin_unlock(&ci->i_ceph_lock); + } else if (ev == RENEWCAPS) { + if (cap->cap_gen < cap->session->s_cap_gen) { + /* mds did not re-issue stale cap */ + spin_lock(&ci->i_ceph_lock); + cap->issued = cap->implemented = CEPH_CAP_PIN; + /* make sure mds knows what we want */ + if (__ceph_caps_file_wanted(ci) & ~cap->mds_wanted) + ci->i_ceph_flags |= CEPH_I_CAP_DROPPED; + spin_unlock(&ci->i_ceph_lock); + } + } else if (ev == FORCE_RO) { } wake_up_all(&ci->i_cap_wq); return 0; } -static void wake_up_session_caps(struct ceph_mds_session *session, - int reconnect) +static void wake_up_session_caps(struct ceph_mds_session *session, int ev) { dout("wake_up_session_caps %p mds%d\n", session, session->s_mds); iterate_session_caps(session, wake_up_session_cb, - (void *)(unsigned long)reconnect); + (void *)(unsigned long)ev); } /* @@ -1466,7 +1483,7 @@ static void renewed_caps(struct ceph_mds_client *mdsc, spin_unlock(&session->s_cap_lock); if (wake) - wake_up_session_caps(session, 0); + wake_up_session_caps(session, RENEWCAPS); } /* @@ -2847,7 +2864,7 @@ static void handle_session(struct ceph_mds_session *session, spin_lock(&session->s_cap_lock); session->s_readonly = true; spin_unlock(&session->s_cap_lock); - wake_up_session_caps(session, 0); + wake_up_session_caps(session, FORCE_RO); break; case CEPH_SESSION_REJECT: @@ -2943,11 +2960,8 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, struct ceph_inode_info *ci = cap->ci; struct ceph_reconnect_state *recon_state = arg; struct ceph_pagelist *pagelist = recon_state->pagelist; - char *path; - int pathlen, err; - u64 pathbase; + int err; u64 snap_follows; - struct dentry *dentry; dout(" adding %p ino %llx.%llx cap %p %lld %s\n", inode, ceph_vinop(inode), cap, cap->cap_id, @@ -2956,19 +2970,6 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, if (err) return err; - dentry = d_find_alias(inode); - if (dentry) { - path = ceph_mdsc_build_path(dentry, &pathlen, &pathbase, 0); - if (IS_ERR(path)) { - err = PTR_ERR(path); - goto out_dput; - } - } else { - path = NULL; - pathlen = 0; - pathbase = 0; - } - spin_lock(&ci->i_ceph_lock); cap->seq = 0; /* reset cap seq */ cap->issue_seq = 0; /* and issue_seq */ @@ -2980,7 +2981,7 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, rec.v2.wanted = cpu_to_le32(__ceph_caps_wanted(ci)); rec.v2.issued = cpu_to_le32(cap->issued); rec.v2.snaprealm = cpu_to_le64(ci->i_snap_realm->ino); - rec.v2.pathbase = cpu_to_le64(pathbase); + rec.v2.pathbase = 0; rec.v2.flock_len = (__force __le32) ((ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) ? 0 : 1); } else { @@ -2991,7 +2992,7 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, ceph_encode_timespec64(&rec.v1.mtime, &inode->i_mtime); ceph_encode_timespec64(&rec.v1.atime, &inode->i_atime); rec.v1.snaprealm = cpu_to_le64(ci->i_snap_realm->ino); - rec.v1.pathbase = cpu_to_le64(pathbase); + rec.v1.pathbase = 0; } if (list_empty(&ci->i_cap_snaps)) { @@ -3023,7 +3024,7 @@ encode_again: GFP_NOFS); if (!flocks) { err = -ENOMEM; - goto out_free; + goto out_err; } err = ceph_encode_locks_to_buffer(inode, flocks, num_fcntl_locks, @@ -3033,7 +3034,7 @@ encode_again: flocks = NULL; if (err == -ENOSPC) goto encode_again; - goto out_free; + goto out_err; } } else { kfree(flocks); @@ -3053,44 +3054,64 @@ encode_again: sizeof(struct ceph_filelock); rec.v2.flock_len = cpu_to_le32(struct_len); - struct_len += sizeof(rec.v2); - struct_len += sizeof(u32) + pathlen; + struct_len += sizeof(u32) + sizeof(rec.v2); if (struct_v >= 2) struct_len += sizeof(u64); /* snap_follows */ total_len += struct_len; err = ceph_pagelist_reserve(pagelist, total_len); + if (err) { + kfree(flocks); + goto out_err; + } - if (!err) { - if (recon_state->msg_version >= 3) { - ceph_pagelist_encode_8(pagelist, struct_v); - ceph_pagelist_encode_8(pagelist, 1); - ceph_pagelist_encode_32(pagelist, struct_len); - } - ceph_pagelist_encode_string(pagelist, path, pathlen); - ceph_pagelist_append(pagelist, &rec, sizeof(rec.v2)); - ceph_locks_to_pagelist(flocks, pagelist, - num_fcntl_locks, - num_flock_locks); - if (struct_v >= 2) - ceph_pagelist_encode_64(pagelist, snap_follows); + if (recon_state->msg_version >= 3) { + ceph_pagelist_encode_8(pagelist, struct_v); + ceph_pagelist_encode_8(pagelist, 1); + ceph_pagelist_encode_32(pagelist, struct_len); } + ceph_pagelist_encode_string(pagelist, NULL, 0); + ceph_pagelist_append(pagelist, &rec, sizeof(rec.v2)); + ceph_locks_to_pagelist(flocks, pagelist, + num_fcntl_locks, num_flock_locks); + if (struct_v >= 2) + ceph_pagelist_encode_64(pagelist, snap_follows); + kfree(flocks); } else { - size_t size = sizeof(u32) + pathlen + sizeof(rec.v1); - err = ceph_pagelist_reserve(pagelist, size); - if (!err) { - ceph_pagelist_encode_string(pagelist, path, pathlen); - ceph_pagelist_append(pagelist, &rec, sizeof(rec.v1)); + u64 pathbase = 0; + int pathlen = 0; + char *path = NULL; + struct dentry *dentry; + + dentry = d_find_alias(inode); + if (dentry) { + path = ceph_mdsc_build_path(dentry, + &pathlen, &pathbase, 0); + dput(dentry); + if (IS_ERR(path)) { + err = PTR_ERR(path); + goto out_err; + } + rec.v1.pathbase = cpu_to_le64(pathbase); } + + err = ceph_pagelist_reserve(pagelist, + pathlen + sizeof(u32) + sizeof(rec.v1)); + if (err) { + kfree(path); + goto out_err; + } + + ceph_pagelist_encode_string(pagelist, path, pathlen); + ceph_pagelist_append(pagelist, &rec, sizeof(rec.v1)); + + kfree(path); } recon_state->nr_caps++; -out_free: - kfree(path); -out_dput: - dput(dentry); +out_err: return err; } @@ -3339,7 +3360,7 @@ static void check_new_map(struct ceph_mds_client *mdsc, pr_info("mds%d recovery completed\n", s->s_mds); kick_requests(mdsc, i); ceph_kick_flushing_caps(mdsc, s); - wake_up_session_caps(s, 1); + wake_up_session_caps(s, RECONNECT); } } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 32fcce0d4d3c..729da155ebf0 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -17,14 +17,16 @@ #include <linux/ceph/auth.h> /* The first 8 bits are reserved for old ceph releases */ -#define CEPHFS_FEATURE_MIMIC 8 - -#define CEPHFS_FEATURES_ALL { \ - 0, 1, 2, 3, 4, 5, 6, 7, \ - CEPHFS_FEATURE_MIMIC, \ +#define CEPHFS_FEATURE_MIMIC 8 +#define CEPHFS_FEATURE_REPLY_ENCODING 9 +#define CEPHFS_FEATURE_RECLAIM_CLIENT 10 +#define CEPHFS_FEATURE_LAZY_CAP_WANTED 11 + +#define CEPHFS_FEATURES_CLIENT_SUPPORTED { \ + 0, 1, 2, 3, 4, 5, 6, 7, \ + CEPHFS_FEATURE_MIMIC, \ + CEPHFS_FEATURE_LAZY_CAP_WANTED, \ } - -#define CEPHFS_FEATURES_CLIENT_SUPPORTED CEPHFS_FEATURES_ALL #define CEPHFS_FEATURES_CLIENT_REQUIRED {} diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 44e53abeb32a..1a2c5d390f7f 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -35,7 +35,6 @@ int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m) /* pick */ n = prandom_u32() % n; - i = 0; for (i = 0; n > 0; i++, n--) while (m->m_info[i].state <= 0) i++; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 4e9a7cc488da..da2cd8e89062 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -530,7 +530,7 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_putc(m, ','); pos = m->count; - ret = ceph_print_client_options(m, fsc->client); + ret = ceph_print_client_options(m, fsc->client, false); if (ret) return ret; @@ -640,7 +640,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, opt = NULL; /* fsc->client now owns this */ fsc->client->extra_mon_dispatch = extra_mon_dispatch; - fsc->client->osdc.abort_on_full = true; + ceph_set_opt(fsc->client, ABORT_ON_FULL); if (!fsopt->mds_namespace) { ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_MDSMAP, diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 26776eddd85d..d1f9c2f3f575 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -150,5 +150,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.15" +#define CIFS_VERSION "2.16" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 01ded7038b19..94dbdbe5be34 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1438,6 +1438,7 @@ struct mid_q_entry { int mid_state; /* wish this were enum but can not pass to wait_event */ unsigned int mid_flags; __le16 command; /* smb command code */ + unsigned int optype; /* operation type */ bool large_buf:1; /* if valid response, is pointer to large buf */ bool multiRsp:1; /* multiple trans2 responses for one request */ bool multiEnd:1; /* both received */ @@ -1574,6 +1575,25 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param, kfree(param); } +static inline bool is_interrupt_error(int error) +{ + switch (error) { + case -EINTR: + case -ERESTARTSYS: + case -ERESTARTNOHAND: + case -ERESTARTNOINTR: + return true; + } + return false; +} + +static inline bool is_retryable_error(int error) +{ + if (is_interrupt_error(error) || error == -EAGAIN) + return true; + return false; +} + #define MID_FREE 0 #define MID_REQUEST_ALLOCATED 1 #define MID_REQUEST_SUBMITTED 2 diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index b1f49c1c543a..e18915415e13 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -128,24 +128,31 @@ static int __cifs_reconnect_tcon(const struct nls_table *nlsc, int rc; struct dfs_cache_tgt_list tl; struct dfs_cache_tgt_iterator *it = NULL; - char tree[MAX_TREE_SIZE + 1]; + char *tree; const char *tcp_host; size_t tcp_host_len; const char *dfs_host; size_t dfs_host_len; + tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL); + if (!tree) + return -ENOMEM; + if (tcon->ipc) { - snprintf(tree, sizeof(tree), "\\\\%s\\IPC$", + snprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", tcon->ses->server->hostname); - return CIFSTCon(0, tcon->ses, tree, tcon, nlsc); + rc = CIFSTCon(0, tcon->ses, tree, tcon, nlsc); + goto out; } - if (!tcon->dfs_path) - return CIFSTCon(0, tcon->ses, tcon->treeName, tcon, nlsc); + if (!tcon->dfs_path) { + rc = CIFSTCon(0, tcon->ses, tcon->treeName, tcon, nlsc); + goto out; + } rc = dfs_cache_noreq_find(tcon->dfs_path + 1, NULL, &tl); if (rc) - return rc; + goto out; extract_unc_hostname(tcon->ses->server->hostname, &tcp_host, &tcp_host_len); @@ -165,7 +172,7 @@ static int __cifs_reconnect_tcon(const struct nls_table *nlsc, continue; } - snprintf(tree, sizeof(tree), "\\%s", tgt); + snprintf(tree, MAX_TREE_SIZE, "\\%s", tgt); rc = CIFSTCon(0, tcon->ses, tree, tcon, nlsc); if (!rc) @@ -182,6 +189,8 @@ static int __cifs_reconnect_tcon(const struct nls_table *nlsc, rc = -ENOENT; } dfs_cache_free_tgts(&tl); +out: + kfree(tree); return rc; } #else @@ -2114,7 +2123,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata) for (j = 0; j < nr_pages; j++) { unlock_page(wdata2->pages[j]); - if (rc != 0 && rc != -EAGAIN) { + if (rc != 0 && !is_retryable_error(rc)) { SetPageError(wdata2->pages[j]); end_page_writeback(wdata2->pages[j]); put_page(wdata2->pages[j]); @@ -2123,7 +2132,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata) if (rc) { kref_put(&wdata2->refcount, cifs_writedata_release); - if (rc == -EAGAIN) + if (is_retryable_error(rc)) continue; break; } @@ -2132,7 +2141,8 @@ cifs_writev_requeue(struct cifs_writedata *wdata) i += nr_pages; } while (i < wdata->nr_pages); - mapping_set_error(inode->i_mapping, rc); + if (rc != 0 && !is_retryable_error(rc)) + mapping_set_error(inode->i_mapping, rc); kref_put(&wdata->refcount, cifs_writedata_release); } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 69b9d5606eba..683310f26171 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -433,9 +433,10 @@ static void reconn_inval_dfs_target(struct TCP_Server_Info *server, kfree(server->hostname); server->hostname = extract_hostname(name); - if (!server->hostname) { - cifs_dbg(FYI, "%s: failed to extract hostname from target: %d\n", - __func__, -ENOMEM); + if (IS_ERR(server->hostname)) { + cifs_dbg(FYI, + "%s: failed to extract hostname from target: %ld\n", + __func__, PTR_ERR(server->hostname)); } } @@ -483,7 +484,7 @@ cifs_reconnect(struct TCP_Server_Info *server) cifs_sb = NULL; } else { rc = reconn_setup_dfs_targets(cifs_sb, &tgt_list, &tgt_it); - if (rc) { + if (rc && (rc != -EOPNOTSUPP)) { cifs_dbg(VFS, "%s: no target servers for DFS failover\n", __func__); } else { diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index cd63c4a70875..09b7d0d4f6e4 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -776,6 +776,7 @@ static int get_tgt_list(const struct dfs_cache_entry *ce, it->it_name = kstrndup(t->t_name, strlen(t->t_name), GFP_KERNEL); if (!it->it_name) { + kfree(it); rc = -ENOMEM; goto err_free_it; } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 5e405164394a..2c7689f3998d 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -33,6 +33,7 @@ #include <linux/mount.h> #include <linux/slab.h> #include <linux/swap.h> +#include <linux/mm.h> #include <asm/div64.h> #include "cifsfs.h" #include "cifspdu.h" @@ -732,7 +733,8 @@ reopen_success: if (can_flush) { rc = filemap_write_and_wait(inode->i_mapping); - mapping_set_error(inode->i_mapping, rc); + if (!is_interrupt_error(rc)) + mapping_set_error(inode->i_mapping, rc); if (tcon->unix_ext) rc = cifs_get_inode_info_unix(&inode, full_path, @@ -1131,14 +1133,18 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) /* * Accessing maxBuf is racy with cifs_reconnect - need to store value - * and check it for zero before using. + * and check it before using. */ max_buf = tcon->ses->server->maxBuf; - if (!max_buf) { + if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE))) { free_xid(xid); return -EINVAL; } + BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) > + PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr), + PAGE_SIZE); max_num = (max_buf - sizeof(struct smb_hdr)) / sizeof(LOCKING_ANDX_RANGE); buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); @@ -1471,12 +1477,16 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, /* * Accessing maxBuf is racy with cifs_reconnect - need to store value - * and check it for zero before using. + * and check it before using. */ max_buf = tcon->ses->server->maxBuf; - if (!max_buf) + if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE))) return -EINVAL; + BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) > + PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr), + PAGE_SIZE); max_num = (max_buf - sizeof(struct smb_hdr)) / sizeof(LOCKING_ANDX_RANGE); buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); @@ -2109,6 +2119,7 @@ static int cifs_writepages(struct address_space *mapping, pgoff_t end, index; struct cifs_writedata *wdata; int rc = 0; + int saved_rc = 0; unsigned int xid; /* @@ -2137,8 +2148,10 @@ retry: rc = server->ops->wait_mtu_credits(server, cifs_sb->wsize, &wsize, &credits); - if (rc) + if (rc != 0) { + done = true; break; + } tofind = min((wsize / PAGE_SIZE) - 1, end - index) + 1; @@ -2146,6 +2159,7 @@ retry: &found_pages); if (!wdata) { rc = -ENOMEM; + done = true; add_credits_and_wake_if(server, credits, 0); break; } @@ -2174,7 +2188,7 @@ retry: if (rc != 0) { add_credits_and_wake_if(server, wdata->credits, 0); for (i = 0; i < nr_pages; ++i) { - if (rc == -EAGAIN) + if (is_retryable_error(rc)) redirty_page_for_writepage(wbc, wdata->pages[i]); else @@ -2182,7 +2196,7 @@ retry: end_page_writeback(wdata->pages[i]); put_page(wdata->pages[i]); } - if (rc != -EAGAIN) + if (!is_retryable_error(rc)) mapping_set_error(mapping, rc); } kref_put(&wdata->refcount, cifs_writedata_release); @@ -2192,6 +2206,15 @@ retry: continue; } + /* Return immediately if we received a signal during writing */ + if (is_interrupt_error(rc)) { + done = true; + break; + } + + if (rc != 0 && saved_rc == 0) + saved_rc = rc; + wbc->nr_to_write -= nr_pages; if (wbc->nr_to_write <= 0) done = true; @@ -2209,6 +2232,9 @@ retry: goto retry; } + if (saved_rc != 0) + rc = saved_rc; + if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = index; @@ -2241,8 +2267,8 @@ cifs_writepage_locked(struct page *page, struct writeback_control *wbc) set_page_writeback(page); retry_write: rc = cifs_partialpagewrite(page, 0, PAGE_SIZE); - if (rc == -EAGAIN) { - if (wbc->sync_mode == WB_SYNC_ALL) + if (is_retryable_error(rc)) { + if (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN) goto retry_write; redirty_page_for_writepage(wbc, page); } else if (rc != 0) { @@ -3964,7 +3990,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, INIT_LIST_HEAD(tmplist); - page = list_entry(page_list->prev, struct page, lru); + page = lru_to_page(page_list); /* * Lock the page and put it in the cache. Since no one else diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 13fb59aadebc..478003644916 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2257,6 +2257,11 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) * the flush returns error? */ rc = filemap_write_and_wait(inode->i_mapping); + if (is_interrupt_error(rc)) { + rc = -ERESTARTSYS; + goto out; + } + mapping_set_error(inode->i_mapping, rc); rc = 0; @@ -2400,6 +2405,11 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) * the flush returns error? */ rc = filemap_write_and_wait(inode->i_mapping); + if (is_interrupt_error(rc)) { + rc = -ERESTARTSYS; + goto cifs_setattr_exit; + } + mapping_set_error(inode->i_mapping, rc); rc = 0; diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 4ed10dd086e6..b204e84b87fb 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -122,12 +122,14 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, /* * Accessing maxBuf is racy with cifs_reconnect - need to store value - * and check it for zero before using. + * and check it before using. */ max_buf = tcon->ses->server->maxBuf; - if (!max_buf) + if (max_buf < sizeof(struct smb2_lock_element)) return -EINVAL; + BUILD_BUG_ON(sizeof(struct smb2_lock_element) > PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf, PAGE_SIZE); max_num = max_buf / sizeof(struct smb2_lock_element); buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL); if (!buf) @@ -264,6 +266,8 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile) return -EINVAL; } + BUILD_BUG_ON(sizeof(struct smb2_lock_element) > PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf, PAGE_SIZE); max_num = max_buf / sizeof(struct smb2_lock_element); buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL); if (!buf) { diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 33100ef74d7f..cf7eb891804f 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3472,8 +3472,10 @@ smb3_receive_transform(struct TCP_Server_Info *server, } /* TODO: add support for compounds containing READ. */ - if (pdu_length > CIFSMaxBufSize + MAX_HEADER_SIZE(server)) + if (pdu_length > CIFSMaxBufSize + MAX_HEADER_SIZE(server)) { + *num_mids = 1; return receive_encrypted_read(server, &mids[0]); + } return receive_encrypted_standard(server, mids, bufs, num_mids); } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index e283590955cd..50811a7dc0e0 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -162,24 +162,31 @@ static int __smb2_reconnect(const struct nls_table *nlsc, int rc; struct dfs_cache_tgt_list tl; struct dfs_cache_tgt_iterator *it = NULL; - char tree[MAX_TREE_SIZE + 1]; + char *tree; const char *tcp_host; size_t tcp_host_len; const char *dfs_host; size_t dfs_host_len; + tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL); + if (!tree) + return -ENOMEM; + if (tcon->ipc) { - snprintf(tree, sizeof(tree), "\\\\%s\\IPC$", + snprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", tcon->ses->server->hostname); - return SMB2_tcon(0, tcon->ses, tree, tcon, nlsc); + rc = SMB2_tcon(0, tcon->ses, tree, tcon, nlsc); + goto out; } - if (!tcon->dfs_path) - return SMB2_tcon(0, tcon->ses, tcon->treeName, tcon, nlsc); + if (!tcon->dfs_path) { + rc = SMB2_tcon(0, tcon->ses, tcon->treeName, tcon, nlsc); + goto out; + } rc = dfs_cache_noreq_find(tcon->dfs_path + 1, NULL, &tl); if (rc) - return rc; + goto out; extract_unc_hostname(tcon->ses->server->hostname, &tcp_host, &tcp_host_len); @@ -199,7 +206,7 @@ static int __smb2_reconnect(const struct nls_table *nlsc, continue; } - snprintf(tree, sizeof(tree), "\\%s", tgt); + snprintf(tree, MAX_TREE_SIZE, "\\%s", tgt); rc = SMB2_tcon(0, tcon->ses, tree, tcon, nlsc); if (!rc) @@ -216,6 +223,8 @@ static int __smb2_reconnect(const struct nls_table *nlsc, rc = -ENOENT; } dfs_cache_free_tgts(&tl); +out: + kfree(tree); return rc; } #else @@ -451,10 +460,6 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, } -/* offset is sizeof smb2_negotiate_req but rounded up to 8 bytes */ -#define OFFSET_OF_NEG_CONTEXT 0x68 /* sizeof(struct smb2_negotiate_req) */ - - #define SMB2_PREAUTH_INTEGRITY_CAPABILITIES cpu_to_le16(1) #define SMB2_ENCRYPTION_CAPABILITIES cpu_to_le16(2) #define SMB2_POSIX_EXTENSIONS_AVAILABLE cpu_to_le16(0x100) @@ -491,10 +496,24 @@ static void assemble_neg_contexts(struct smb2_negotiate_req *req, unsigned int *total_len) { - char *pneg_ctxt = (char *)req + OFFSET_OF_NEG_CONTEXT; + char *pneg_ctxt = (char *)req; unsigned int ctxt_len; - *total_len += 2; /* Add 2 due to round to 8 byte boundary for 1st ctxt */ + if (*total_len > 200) { + /* In case length corrupted don't want to overrun smb buffer */ + cifs_dbg(VFS, "Bad frame length assembling neg contexts\n"); + return; + } + + /* + * round up total_len of fixed part of SMB3 negotiate request to 8 + * byte boundary before adding negotiate contexts + */ + *total_len = roundup(*total_len, 8); + + pneg_ctxt = (*total_len) + (char *)req; + req->NegotiateContextOffset = cpu_to_le32(*total_len); + build_preauth_ctxt((struct smb2_preauth_neg_context *)pneg_ctxt); ctxt_len = DIV_ROUND_UP(sizeof(struct smb2_preauth_neg_context), 8) * 8; *total_len += ctxt_len; @@ -508,7 +527,6 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt); *total_len += sizeof(struct smb2_posix_neg_context); - req->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT); req->NegotiateContextCount = cpu_to_le16(3); } @@ -724,8 +742,9 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) req->Dialects[0] = cpu_to_le16(SMB21_PROT_ID); req->Dialects[1] = cpu_to_le16(SMB30_PROT_ID); req->Dialects[2] = cpu_to_le16(SMB302_PROT_ID); - req->DialectCount = cpu_to_le16(3); - total_len += 6; + req->Dialects[3] = cpu_to_le16(SMB311_PROT_ID); + req->DialectCount = cpu_to_le16(4); + total_len += 8; } else { /* otherwise send specific dialect */ req->Dialects[0] = cpu_to_le16(ses->server->vals->protocol_id); @@ -749,7 +768,9 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) else { memcpy(req->ClientGUID, server->client_guid, SMB2_CLIENT_GUID_SIZE); - if (ses->server->vals->protocol_id == SMB311_PROT_ID) + if ((ses->server->vals->protocol_id == SMB311_PROT_ID) || + (strcmp(ses->server->vals->version_string, + SMBDEFAULT_VERSION_STRING) == 0)) assemble_neg_contexts(req, &total_len); } iov[0].iov_base = (char *)req; @@ -794,7 +815,8 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) { /* ops set to 3.0 by default for default so update */ ses->server->ops = &smb21_operations; - } + } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) + ses->server->ops = &smb311_operations; } else if (le16_to_cpu(rsp->DialectRevision) != ses->server->vals->protocol_id) { /* if requested single dialect ensure returned dialect matched */ @@ -941,13 +963,14 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) pneg_inbuf->DialectCount = cpu_to_le16(2); /* structure is big enough for 3 dialects, sending only 2 */ inbuflen = sizeof(*pneg_inbuf) - - sizeof(pneg_inbuf->Dialects[0]); + (2 * sizeof(pneg_inbuf->Dialects[0])); } else if (strcmp(tcon->ses->server->vals->version_string, SMBDEFAULT_VERSION_STRING) == 0) { pneg_inbuf->Dialects[0] = cpu_to_le16(SMB21_PROT_ID); pneg_inbuf->Dialects[1] = cpu_to_le16(SMB30_PROT_ID); pneg_inbuf->Dialects[2] = cpu_to_le16(SMB302_PROT_ID); - pneg_inbuf->DialectCount = cpu_to_le16(3); + pneg_inbuf->Dialects[3] = cpu_to_le16(SMB311_PROT_ID); + pneg_inbuf->DialectCount = cpu_to_le16(4); /* structure is big enough for 3 dialects */ inbuflen = sizeof(*pneg_inbuf); } else { @@ -3264,12 +3287,14 @@ smb2_async_readv(struct cifs_readdata *rdata) if (rdata->credits) { shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes, SMB2_MAX_BUFFER_SIZE)); - shdr->CreditRequest = shdr->CreditCharge; + shdr->CreditRequest = + cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 1); spin_lock(&server->req_lock); server->credits += rdata->credits - le16_to_cpu(shdr->CreditCharge); spin_unlock(&server->req_lock); wake_up(&server->request_q); + rdata->credits = le16_to_cpu(shdr->CreditCharge); flags |= CIFS_HAS_CREDITS; } @@ -3541,12 +3566,14 @@ smb2_async_writev(struct cifs_writedata *wdata, if (wdata->credits) { shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes, SMB2_MAX_BUFFER_SIZE)); - shdr->CreditRequest = shdr->CreditCharge; + shdr->CreditRequest = + cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 1); spin_lock(&server->req_lock); server->credits += wdata->credits - le16_to_cpu(shdr->CreditCharge); spin_unlock(&server->req_lock); wake_up(&server->request_q); + wdata->credits = le16_to_cpu(shdr->CreditCharge); flags |= CIFS_HAS_CREDITS; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 05dea6750c33..7a2d0a2255e6 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -898,7 +898,7 @@ struct validate_negotiate_info_req { __u8 Guid[SMB2_CLIENT_GUID_SIZE]; __le16 SecurityMode; __le16 DialectCount; - __le16 Dialects[3]; /* BB expand this if autonegotiate > 3 dialects */ + __le16 Dialects[4]; /* BB expand this if autonegotiate > 4 dialects */ } __packed; struct validate_negotiate_info_rsp { diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 5be7302853b6..202e0e84efdd 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -387,7 +387,7 @@ smbd_done: if (rc < 0 && rc != -EINTR) cifs_dbg(VFS, "Error %d sending data on socket to server\n", rc); - else + else if (rc > 0) rc = 0; return rc; @@ -783,8 +783,34 @@ cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst) } static void -cifs_noop_callback(struct mid_q_entry *mid) +cifs_compound_callback(struct mid_q_entry *mid) { + struct TCP_Server_Info *server = mid->server; + unsigned int optype = mid->optype; + unsigned int credits_received = 0; + + if (mid->mid_state == MID_RESPONSE_RECEIVED) { + if (mid->resp_buf) + credits_received = server->ops->get_credits(mid); + else + cifs_dbg(FYI, "Bad state for cancelled MID\n"); + } + + add_credits(server, credits_received, optype); +} + +static void +cifs_compound_last_callback(struct mid_q_entry *mid) +{ + cifs_compound_callback(mid); + cifs_wake_up_task(mid); +} + +static void +cifs_cancelled_callback(struct mid_q_entry *mid) +{ + cifs_compound_callback(mid); + DeleteMidQEntry(mid); } int @@ -795,7 +821,8 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, int i, j, rc = 0; int timeout, optype; struct mid_q_entry *midQ[MAX_COMPOUND]; - unsigned int credits = 0; + bool cancelled_mid[MAX_COMPOUND] = {false}; + unsigned int credits[MAX_COMPOUND] = {0}; char *buf; timeout = flags & CIFS_TIMEOUT_MASK; @@ -813,13 +840,31 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, return -ENOENT; /* - * Ensure that we do not send more than 50 overlapping requests - * to the same server. We may make this configurable later or - * use ses->maxReq. + * Ensure we obtain 1 credit per request in the compound chain. + * It can be optimized further by waiting for all the credits + * at once but this can wait long enough if we don't have enough + * credits due to some heavy operations in progress or the server + * not granting us much, so a fallback to the current approach is + * needed anyway. */ - rc = wait_for_free_request(ses->server, timeout, optype); - if (rc) - return rc; + for (i = 0; i < num_rqst; i++) { + rc = wait_for_free_request(ses->server, timeout, optype); + if (rc) { + /* + * We haven't sent an SMB packet to the server yet but + * we already obtained credits for i requests in the + * compound chain - need to return those credits back + * for future use. Note that we need to call add_credits + * multiple times to match the way we obtained credits + * in the first place and to account for in flight + * requests correctly. + */ + for (j = 0; j < i; j++) + add_credits(ses->server, 1, optype); + return rc; + } + credits[i] = 1; + } /* * Make sure that we sign in the same order that we send on this socket @@ -835,18 +880,24 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, for (j = 0; j < i; j++) cifs_delete_mid(midQ[j]); mutex_unlock(&ses->server->srv_mutex); + /* Update # of requests on wire to server */ - add_credits(ses->server, 1, optype); + for (j = 0; j < num_rqst; j++) + add_credits(ses->server, credits[j], optype); return PTR_ERR(midQ[i]); } midQ[i]->mid_state = MID_REQUEST_SUBMITTED; + midQ[i]->optype = optype; /* - * We don't invoke the callback compounds unless it is the last - * request. + * Invoke callback for every part of the compound chain + * to calculate credits properly. Wake up this thread only when + * the last element is received. */ if (i < num_rqst - 1) - midQ[i]->callback = cifs_noop_callback; + midQ[i]->callback = cifs_compound_callback; + else + midQ[i]->callback = cifs_compound_last_callback; } cifs_in_send_inc(ses->server); rc = smb_send_rqst(ses->server, num_rqst, rqst, flags); @@ -860,8 +911,20 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, mutex_unlock(&ses->server->srv_mutex); - if (rc < 0) + if (rc < 0) { + /* Sending failed for some reason - return credits back */ + for (i = 0; i < num_rqst; i++) + add_credits(ses->server, credits[i], optype); goto out; + } + + /* + * At this point the request is passed to the network stack - we assume + * that any credits taken from the server structure on the client have + * been spent and we can't return them back. Once we receive responses + * we will collect credits granted by the server in the mid callbacks + * and add those credits to the server structure. + */ /* * Compounding is never used during session establish. @@ -875,36 +938,34 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, for (i = 0; i < num_rqst; i++) { rc = wait_for_response(ses->server, midQ[i]); - if (rc != 0) { + if (rc != 0) + break; + } + if (rc != 0) { + for (; i < num_rqst; i++) { cifs_dbg(VFS, "Cancelling wait for mid %llu cmd: %d\n", midQ[i]->mid, le16_to_cpu(midQ[i]->command)); send_cancel(ses->server, &rqst[i], midQ[i]); spin_lock(&GlobalMid_Lock); if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED) { midQ[i]->mid_flags |= MID_WAIT_CANCELLED; - midQ[i]->callback = DeleteMidQEntry; - spin_unlock(&GlobalMid_Lock); - add_credits(ses->server, 1, optype); - return rc; + midQ[i]->callback = cifs_cancelled_callback; + cancelled_mid[i] = true; + credits[i] = 0; } spin_unlock(&GlobalMid_Lock); } } - for (i = 0; i < num_rqst; i++) - if (midQ[i]->resp_buf) - credits += ses->server->ops->get_credits(midQ[i]); - if (!credits) - credits = 1; - for (i = 0; i < num_rqst; i++) { if (rc < 0) goto out; rc = cifs_sync_mid_result(midQ[i], ses->server); if (rc != 0) { - add_credits(ses->server, credits, optype); - return rc; + /* mark this mid as cancelled to not free it below */ + cancelled_mid[i] = true; + goto out; } if (!midQ[i]->resp_buf || @@ -951,9 +1012,10 @@ out: * This is prevented above by using a noop callback that will not * wake this thread except for the very last PDU. */ - for (i = 0; i < num_rqst; i++) - cifs_delete_mid(midQ[i]); - add_credits(ses->server, credits, optype); + for (i = 0; i < num_rqst; i++) { + if (!cancelled_mid[i]) + cifs_delete_mid(midQ[i]); + } return rc; } diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 0f46cf550907..4dc788e3bc96 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -133,15 +133,25 @@ struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, gfp_t gfp_flags) } EXPORT_SYMBOL(fscrypt_get_ctx); +void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, + const struct fscrypt_info *ci) +{ + memset(iv, 0, ci->ci_mode->ivsize); + iv->lblk_num = cpu_to_le64(lblk_num); + + if (ci->ci_flags & FS_POLICY_FLAG_DIRECT_KEY) + memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE); + + if (ci->ci_essiv_tfm != NULL) + crypto_cipher_encrypt_one(ci->ci_essiv_tfm, iv->raw, iv->raw); +} + int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, u64 lblk_num, struct page *src_page, struct page *dest_page, unsigned int len, unsigned int offs, gfp_t gfp_flags) { - struct { - __le64 index; - u8 padding[FS_IV_SIZE - sizeof(__le64)]; - } iv; + union fscrypt_iv iv; struct skcipher_request *req = NULL; DECLARE_CRYPTO_WAIT(wait); struct scatterlist dst, src; @@ -151,15 +161,7 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, BUG_ON(len == 0); - BUILD_BUG_ON(sizeof(iv) != FS_IV_SIZE); - BUILD_BUG_ON(AES_BLOCK_SIZE != FS_IV_SIZE); - iv.index = cpu_to_le64(lblk_num); - memset(iv.padding, 0, sizeof(iv.padding)); - - if (ci->ci_essiv_tfm != NULL) { - crypto_cipher_encrypt_one(ci->ci_essiv_tfm, (u8 *)&iv, - (u8 *)&iv); - } + fscrypt_generate_iv(&iv, lblk_num, ci); req = skcipher_request_alloc(tfm, gfp_flags); if (!req) diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index d7a0f682ca12..7ff40a73dbec 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -40,10 +40,11 @@ int fname_encrypt(struct inode *inode, const struct qstr *iname, { struct skcipher_request *req = NULL; DECLARE_CRYPTO_WAIT(wait); - struct crypto_skcipher *tfm = inode->i_crypt_info->ci_ctfm; - int res = 0; - char iv[FS_CRYPTO_BLOCK_SIZE]; + struct fscrypt_info *ci = inode->i_crypt_info; + struct crypto_skcipher *tfm = ci->ci_ctfm; + union fscrypt_iv iv; struct scatterlist sg; + int res; /* * Copy the filename to the output buffer for encrypting in-place and @@ -55,7 +56,7 @@ int fname_encrypt(struct inode *inode, const struct qstr *iname, memset(out + iname->len, 0, olen - iname->len); /* Initialize the IV */ - memset(iv, 0, FS_CRYPTO_BLOCK_SIZE); + fscrypt_generate_iv(&iv, 0, ci); /* Set up the encryption request */ req = skcipher_request_alloc(tfm, GFP_NOFS); @@ -65,7 +66,7 @@ int fname_encrypt(struct inode *inode, const struct qstr *iname, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &wait); sg_init_one(&sg, out, olen); - skcipher_request_set_crypt(req, &sg, &sg, olen, iv); + skcipher_request_set_crypt(req, &sg, &sg, olen, &iv); /* Do the encryption */ res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait); @@ -94,9 +95,10 @@ static int fname_decrypt(struct inode *inode, struct skcipher_request *req = NULL; DECLARE_CRYPTO_WAIT(wait); struct scatterlist src_sg, dst_sg; - struct crypto_skcipher *tfm = inode->i_crypt_info->ci_ctfm; - int res = 0; - char iv[FS_CRYPTO_BLOCK_SIZE]; + struct fscrypt_info *ci = inode->i_crypt_info; + struct crypto_skcipher *tfm = ci->ci_ctfm; + union fscrypt_iv iv; + int res; /* Allocate request */ req = skcipher_request_alloc(tfm, GFP_NOFS); @@ -107,12 +109,12 @@ static int fname_decrypt(struct inode *inode, crypto_req_done, &wait); /* Initialize IV */ - memset(iv, 0, FS_CRYPTO_BLOCK_SIZE); + fscrypt_generate_iv(&iv, 0, ci); /* Create decryption request */ sg_init_one(&src_sg, iname->name, iname->len); sg_init_one(&dst_sg, oname->name, oname->len); - skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv); + skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, &iv); res = crypto_wait_req(crypto_skcipher_decrypt(req), &wait); skcipher_request_free(req); if (res < 0) { diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 79debfc9cef9..7424f851eb5c 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -17,7 +17,6 @@ #include <crypto/hash.h> /* Encryption parameters */ -#define FS_IV_SIZE 16 #define FS_KEY_DERIVATION_NONCE_SIZE 16 /** @@ -52,16 +51,42 @@ struct fscrypt_symlink_data { } __packed; /* - * A pointer to this structure is stored in the file system's in-core - * representation of an inode. + * fscrypt_info - the "encryption key" for an inode + * + * When an encrypted file's key is made available, an instance of this struct is + * allocated and stored in ->i_crypt_info. Once created, it remains until the + * inode is evicted. */ struct fscrypt_info { + + /* The actual crypto transform used for encryption and decryption */ + struct crypto_skcipher *ci_ctfm; + + /* + * Cipher for ESSIV IV generation. Only set for CBC contents + * encryption, otherwise is NULL. + */ + struct crypto_cipher *ci_essiv_tfm; + + /* + * Encryption mode used for this inode. It corresponds to either + * ci_data_mode or ci_filename_mode, depending on the inode type. + */ + struct fscrypt_mode *ci_mode; + + /* + * If non-NULL, then this inode uses a master key directly rather than a + * derived key, and ci_ctfm will equal ci_master_key->mk_ctfm. + * Otherwise, this inode uses a derived key. + */ + struct fscrypt_master_key *ci_master_key; + + /* fields from the fscrypt_context */ u8 ci_data_mode; u8 ci_filename_mode; u8 ci_flags; - struct crypto_skcipher *ci_ctfm; - struct crypto_cipher *ci_essiv_tfm; - u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE]; + u8 ci_master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE]; + u8 ci_nonce[FS_KEY_DERIVATION_NONCE_SIZE]; }; typedef enum { @@ -83,6 +108,10 @@ static inline bool fscrypt_valid_enc_modes(u32 contents_mode, filenames_mode == FS_ENCRYPTION_MODE_AES_256_CTS) return true; + if (contents_mode == FS_ENCRYPTION_MODE_ADIANTUM && + filenames_mode == FS_ENCRYPTION_MODE_ADIANTUM) + return true; + return false; } @@ -107,6 +136,22 @@ fscrypt_msg(struct super_block *sb, const char *level, const char *fmt, ...); #define fscrypt_err(sb, fmt, ...) \ fscrypt_msg(sb, KERN_ERR, fmt, ##__VA_ARGS__) +#define FSCRYPT_MAX_IV_SIZE 32 + +union fscrypt_iv { + struct { + /* logical block number within the file */ + __le64 lblk_num; + + /* per-file nonce; only set in DIRECT_KEY mode */ + u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE]; + }; + u8 raw[FSCRYPT_MAX_IV_SIZE]; +}; + +void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, + const struct fscrypt_info *ci); + /* fname.c */ extern int fname_encrypt(struct inode *inode, const struct qstr *iname, u8 *out, unsigned int olen); @@ -115,6 +160,16 @@ extern bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 *encrypted_len_ret); /* keyinfo.c */ + +struct fscrypt_mode { + const char *friendly_name; + const char *cipher_str; + int keysize; + int ivsize; + bool logged_impl_name; + bool needs_essiv; +}; + extern void __exit fscrypt_essiv_cleanup(void); #endif /* _FSCRYPT_PRIVATE_H */ diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 7874c9bb2fc5..1e11a683f63d 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -10,15 +10,21 @@ */ #include <keys/user-type.h> +#include <linux/hashtable.h> #include <linux/scatterlist.h> #include <linux/ratelimit.h> #include <crypto/aes.h> +#include <crypto/algapi.h> #include <crypto/sha.h> #include <crypto/skcipher.h> #include "fscrypt_private.h" static struct crypto_shash *essiv_hash_tfm; +/* Table of keys referenced by FS_POLICY_FLAG_DIRECT_KEY policies */ +static DEFINE_HASHTABLE(fscrypt_master_keys, 6); /* 6 bits = 64 buckets */ +static DEFINE_SPINLOCK(fscrypt_master_keys_lock); + /* * Key derivation function. This generates the derived key by encrypting the * master key with AES-128-ECB using the inode's nonce as the AES key. @@ -123,56 +129,37 @@ invalid: return ERR_PTR(-ENOKEY); } -/* Find the master key, then derive the inode's actual encryption key */ -static int find_and_derive_key(const struct inode *inode, - const struct fscrypt_context *ctx, - u8 *derived_key, unsigned int derived_keysize) -{ - struct key *key; - const struct fscrypt_key *payload; - int err; - - key = find_and_lock_process_key(FS_KEY_DESC_PREFIX, - ctx->master_key_descriptor, - derived_keysize, &payload); - if (key == ERR_PTR(-ENOKEY) && inode->i_sb->s_cop->key_prefix) { - key = find_and_lock_process_key(inode->i_sb->s_cop->key_prefix, - ctx->master_key_descriptor, - derived_keysize, &payload); - } - if (IS_ERR(key)) - return PTR_ERR(key); - err = derive_key_aes(payload->raw, ctx, derived_key, derived_keysize); - up_read(&key->sem); - key_put(key); - return err; -} - -static struct fscrypt_mode { - const char *friendly_name; - const char *cipher_str; - int keysize; - bool logged_impl_name; -} available_modes[] = { +static struct fscrypt_mode available_modes[] = { [FS_ENCRYPTION_MODE_AES_256_XTS] = { .friendly_name = "AES-256-XTS", .cipher_str = "xts(aes)", .keysize = 64, + .ivsize = 16, }, [FS_ENCRYPTION_MODE_AES_256_CTS] = { .friendly_name = "AES-256-CTS-CBC", .cipher_str = "cts(cbc(aes))", .keysize = 32, + .ivsize = 16, }, [FS_ENCRYPTION_MODE_AES_128_CBC] = { .friendly_name = "AES-128-CBC", .cipher_str = "cbc(aes)", .keysize = 16, + .ivsize = 16, + .needs_essiv = true, }, [FS_ENCRYPTION_MODE_AES_128_CTS] = { .friendly_name = "AES-128-CTS-CBC", .cipher_str = "cts(cbc(aes))", .keysize = 16, + .ivsize = 16, + }, + [FS_ENCRYPTION_MODE_ADIANTUM] = { + .friendly_name = "Adiantum", + .cipher_str = "adiantum(xchacha12,aes)", + .keysize = 32, + .ivsize = 32, }, }; @@ -198,14 +185,196 @@ select_encryption_mode(const struct fscrypt_info *ci, const struct inode *inode) return ERR_PTR(-EINVAL); } -static void put_crypt_info(struct fscrypt_info *ci) +/* Find the master key, then derive the inode's actual encryption key */ +static int find_and_derive_key(const struct inode *inode, + const struct fscrypt_context *ctx, + u8 *derived_key, const struct fscrypt_mode *mode) { - if (!ci) + struct key *key; + const struct fscrypt_key *payload; + int err; + + key = find_and_lock_process_key(FS_KEY_DESC_PREFIX, + ctx->master_key_descriptor, + mode->keysize, &payload); + if (key == ERR_PTR(-ENOKEY) && inode->i_sb->s_cop->key_prefix) { + key = find_and_lock_process_key(inode->i_sb->s_cop->key_prefix, + ctx->master_key_descriptor, + mode->keysize, &payload); + } + if (IS_ERR(key)) + return PTR_ERR(key); + + if (ctx->flags & FS_POLICY_FLAG_DIRECT_KEY) { + if (mode->ivsize < offsetofend(union fscrypt_iv, nonce)) { + fscrypt_warn(inode->i_sb, + "direct key mode not allowed with %s", + mode->friendly_name); + err = -EINVAL; + } else if (ctx->contents_encryption_mode != + ctx->filenames_encryption_mode) { + fscrypt_warn(inode->i_sb, + "direct key mode not allowed with different contents and filenames modes"); + err = -EINVAL; + } else { + memcpy(derived_key, payload->raw, mode->keysize); + err = 0; + } + } else { + err = derive_key_aes(payload->raw, ctx, derived_key, + mode->keysize); + } + up_read(&key->sem); + key_put(key); + return err; +} + +/* Allocate and key a symmetric cipher object for the given encryption mode */ +static struct crypto_skcipher * +allocate_skcipher_for_mode(struct fscrypt_mode *mode, const u8 *raw_key, + const struct inode *inode) +{ + struct crypto_skcipher *tfm; + int err; + + tfm = crypto_alloc_skcipher(mode->cipher_str, 0, 0); + if (IS_ERR(tfm)) { + fscrypt_warn(inode->i_sb, + "error allocating '%s' transform for inode %lu: %ld", + mode->cipher_str, inode->i_ino, PTR_ERR(tfm)); + return tfm; + } + if (unlikely(!mode->logged_impl_name)) { + /* + * fscrypt performance can vary greatly depending on which + * crypto algorithm implementation is used. Help people debug + * performance problems by logging the ->cra_driver_name the + * first time a mode is used. Note that multiple threads can + * race here, but it doesn't really matter. + */ + mode->logged_impl_name = true; + pr_info("fscrypt: %s using implementation \"%s\"\n", + mode->friendly_name, + crypto_skcipher_alg(tfm)->base.cra_driver_name); + } + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + err = crypto_skcipher_setkey(tfm, raw_key, mode->keysize); + if (err) + goto err_free_tfm; + + return tfm; + +err_free_tfm: + crypto_free_skcipher(tfm); + return ERR_PTR(err); +} + +/* Master key referenced by FS_POLICY_FLAG_DIRECT_KEY policy */ +struct fscrypt_master_key { + struct hlist_node mk_node; + refcount_t mk_refcount; + const struct fscrypt_mode *mk_mode; + struct crypto_skcipher *mk_ctfm; + u8 mk_descriptor[FS_KEY_DESCRIPTOR_SIZE]; + u8 mk_raw[FS_MAX_KEY_SIZE]; +}; + +static void free_master_key(struct fscrypt_master_key *mk) +{ + if (mk) { + crypto_free_skcipher(mk->mk_ctfm); + kzfree(mk); + } +} + +static void put_master_key(struct fscrypt_master_key *mk) +{ + if (!refcount_dec_and_lock(&mk->mk_refcount, &fscrypt_master_keys_lock)) return; + hash_del(&mk->mk_node); + spin_unlock(&fscrypt_master_keys_lock); - crypto_free_skcipher(ci->ci_ctfm); - crypto_free_cipher(ci->ci_essiv_tfm); - kmem_cache_free(fscrypt_info_cachep, ci); + free_master_key(mk); +} + +/* + * Find/insert the given master key into the fscrypt_master_keys table. If + * found, it is returned with elevated refcount, and 'to_insert' is freed if + * non-NULL. If not found, 'to_insert' is inserted and returned if it's + * non-NULL; otherwise NULL is returned. + */ +static struct fscrypt_master_key * +find_or_insert_master_key(struct fscrypt_master_key *to_insert, + const u8 *raw_key, const struct fscrypt_mode *mode, + const struct fscrypt_info *ci) +{ + unsigned long hash_key; + struct fscrypt_master_key *mk; + + /* + * Careful: to avoid potentially leaking secret key bytes via timing + * information, we must key the hash table by descriptor rather than by + * raw key, and use crypto_memneq() when comparing raw keys. + */ + + BUILD_BUG_ON(sizeof(hash_key) > FS_KEY_DESCRIPTOR_SIZE); + memcpy(&hash_key, ci->ci_master_key_descriptor, sizeof(hash_key)); + + spin_lock(&fscrypt_master_keys_lock); + hash_for_each_possible(fscrypt_master_keys, mk, mk_node, hash_key) { + if (memcmp(ci->ci_master_key_descriptor, mk->mk_descriptor, + FS_KEY_DESCRIPTOR_SIZE) != 0) + continue; + if (mode != mk->mk_mode) + continue; + if (crypto_memneq(raw_key, mk->mk_raw, mode->keysize)) + continue; + /* using existing tfm with same (descriptor, mode, raw_key) */ + refcount_inc(&mk->mk_refcount); + spin_unlock(&fscrypt_master_keys_lock); + free_master_key(to_insert); + return mk; + } + if (to_insert) + hash_add(fscrypt_master_keys, &to_insert->mk_node, hash_key); + spin_unlock(&fscrypt_master_keys_lock); + return to_insert; +} + +/* Prepare to encrypt directly using the master key in the given mode */ +static struct fscrypt_master_key * +fscrypt_get_master_key(const struct fscrypt_info *ci, struct fscrypt_mode *mode, + const u8 *raw_key, const struct inode *inode) +{ + struct fscrypt_master_key *mk; + int err; + + /* Is there already a tfm for this key? */ + mk = find_or_insert_master_key(NULL, raw_key, mode, ci); + if (mk) + return mk; + + /* Nope, allocate one. */ + mk = kzalloc(sizeof(*mk), GFP_NOFS); + if (!mk) + return ERR_PTR(-ENOMEM); + refcount_set(&mk->mk_refcount, 1); + mk->mk_mode = mode; + mk->mk_ctfm = allocate_skcipher_for_mode(mode, raw_key, inode); + if (IS_ERR(mk->mk_ctfm)) { + err = PTR_ERR(mk->mk_ctfm); + mk->mk_ctfm = NULL; + goto err_free_mk; + } + memcpy(mk->mk_descriptor, ci->ci_master_key_descriptor, + FS_KEY_DESCRIPTOR_SIZE); + memcpy(mk->mk_raw, raw_key, mode->keysize); + + return find_or_insert_master_key(mk, raw_key, mode, ci); + +err_free_mk: + free_master_key(mk); + return ERR_PTR(err); } static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt) @@ -275,11 +444,67 @@ void __exit fscrypt_essiv_cleanup(void) crypto_free_shash(essiv_hash_tfm); } +/* + * Given the encryption mode and key (normally the derived key, but for + * FS_POLICY_FLAG_DIRECT_KEY mode it's the master key), set up the inode's + * symmetric cipher transform object(s). + */ +static int setup_crypto_transform(struct fscrypt_info *ci, + struct fscrypt_mode *mode, + const u8 *raw_key, const struct inode *inode) +{ + struct fscrypt_master_key *mk; + struct crypto_skcipher *ctfm; + int err; + + if (ci->ci_flags & FS_POLICY_FLAG_DIRECT_KEY) { + mk = fscrypt_get_master_key(ci, mode, raw_key, inode); + if (IS_ERR(mk)) + return PTR_ERR(mk); + ctfm = mk->mk_ctfm; + } else { + mk = NULL; + ctfm = allocate_skcipher_for_mode(mode, raw_key, inode); + if (IS_ERR(ctfm)) + return PTR_ERR(ctfm); + } + ci->ci_master_key = mk; + ci->ci_ctfm = ctfm; + + if (mode->needs_essiv) { + /* ESSIV implies 16-byte IVs which implies !DIRECT_KEY */ + WARN_ON(mode->ivsize != AES_BLOCK_SIZE); + WARN_ON(ci->ci_flags & FS_POLICY_FLAG_DIRECT_KEY); + + err = init_essiv_generator(ci, raw_key, mode->keysize); + if (err) { + fscrypt_warn(inode->i_sb, + "error initializing ESSIV generator for inode %lu: %d", + inode->i_ino, err); + return err; + } + } + return 0; +} + +static void put_crypt_info(struct fscrypt_info *ci) +{ + if (!ci) + return; + + if (ci->ci_master_key) { + put_master_key(ci->ci_master_key); + } else { + crypto_free_skcipher(ci->ci_ctfm); + crypto_free_cipher(ci->ci_essiv_tfm); + } + kmem_cache_free(fscrypt_info_cachep, ci); +} + int fscrypt_get_encryption_info(struct inode *inode) { struct fscrypt_info *crypt_info; struct fscrypt_context ctx; - struct crypto_skcipher *ctfm; struct fscrypt_mode *mode; u8 *raw_key = NULL; int res; @@ -312,74 +537,42 @@ int fscrypt_get_encryption_info(struct inode *inode) if (ctx.flags & ~FS_POLICY_FLAGS_VALID) return -EINVAL; - crypt_info = kmem_cache_alloc(fscrypt_info_cachep, GFP_NOFS); + crypt_info = kmem_cache_zalloc(fscrypt_info_cachep, GFP_NOFS); if (!crypt_info) return -ENOMEM; crypt_info->ci_flags = ctx.flags; crypt_info->ci_data_mode = ctx.contents_encryption_mode; crypt_info->ci_filename_mode = ctx.filenames_encryption_mode; - crypt_info->ci_ctfm = NULL; - crypt_info->ci_essiv_tfm = NULL; - memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor, - sizeof(crypt_info->ci_master_key)); + memcpy(crypt_info->ci_master_key_descriptor, ctx.master_key_descriptor, + FS_KEY_DESCRIPTOR_SIZE); + memcpy(crypt_info->ci_nonce, ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE); mode = select_encryption_mode(crypt_info, inode); if (IS_ERR(mode)) { res = PTR_ERR(mode); goto out; } + WARN_ON(mode->ivsize > FSCRYPT_MAX_IV_SIZE); + crypt_info->ci_mode = mode; /* - * This cannot be a stack buffer because it is passed to the scatterlist - * crypto API as part of key derivation. + * This cannot be a stack buffer because it may be passed to the + * scatterlist crypto API as part of key derivation. */ res = -ENOMEM; raw_key = kmalloc(mode->keysize, GFP_NOFS); if (!raw_key) goto out; - res = find_and_derive_key(inode, &ctx, raw_key, mode->keysize); + res = find_and_derive_key(inode, &ctx, raw_key, mode); if (res) goto out; - ctfm = crypto_alloc_skcipher(mode->cipher_str, 0, 0); - if (IS_ERR(ctfm)) { - res = PTR_ERR(ctfm); - fscrypt_warn(inode->i_sb, - "error allocating '%s' transform for inode %lu: %d", - mode->cipher_str, inode->i_ino, res); - goto out; - } - if (unlikely(!mode->logged_impl_name)) { - /* - * fscrypt performance can vary greatly depending on which - * crypto algorithm implementation is used. Help people debug - * performance problems by logging the ->cra_driver_name the - * first time a mode is used. Note that multiple threads can - * race here, but it doesn't really matter. - */ - mode->logged_impl_name = true; - pr_info("fscrypt: %s using implementation \"%s\"\n", - mode->friendly_name, - crypto_skcipher_alg(ctfm)->base.cra_driver_name); - } - crypt_info->ci_ctfm = ctfm; - crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY); - res = crypto_skcipher_setkey(ctfm, raw_key, mode->keysize); + res = setup_crypto_transform(crypt_info, mode, raw_key, inode); if (res) goto out; - if (S_ISREG(inode->i_mode) && - crypt_info->ci_data_mode == FS_ENCRYPTION_MODE_AES_128_CBC) { - res = init_essiv_generator(crypt_info, raw_key, mode->keysize); - if (res) { - fscrypt_warn(inode->i_sb, - "error initializing ESSIV generator for inode %lu: %d", - inode->i_ino, res); - goto out; - } - } if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL) crypt_info = NULL; out: diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index c6d431a5cce9..f490de921ce8 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -199,7 +199,8 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child) child_ci = child->i_crypt_info; if (parent_ci && child_ci) { - return memcmp(parent_ci->ci_master_key, child_ci->ci_master_key, + return memcmp(parent_ci->ci_master_key_descriptor, + child_ci->ci_master_key_descriptor, FS_KEY_DESCRIPTOR_SIZE) == 0 && (parent_ci->ci_data_mode == child_ci->ci_data_mode) && (parent_ci->ci_filename_mode == @@ -254,7 +255,7 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child, ctx.contents_encryption_mode = ci->ci_data_mode; ctx.filenames_encryption_mode = ci->ci_filename_mode; ctx.flags = ci->ci_flags; - memcpy(ctx.master_key_descriptor, ci->ci_master_key, + memcpy(ctx.master_key_descriptor, ci->ci_master_key_descriptor, FS_KEY_DESCRIPTOR_SIZE); get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE); BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 8a5a1010886b..a5d219d920e7 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -381,7 +381,8 @@ static void ep_nested_calls_init(struct nested_calls *ncalls) */ static inline int ep_events_available(struct eventpoll *ep) { - return !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR; + return !list_empty_careful(&ep->rdllist) || + READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR; } #ifdef CONFIG_NET_RX_BUSY_POLL @@ -471,7 +472,6 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) * no re-entered. * * @ncalls: Pointer to the nested_calls structure to be used for this call. - * @max_nests: Maximum number of allowed nesting calls. * @nproc: Nested call core function pointer. * @priv: Opaque data to be passed to the @nproc callback. * @cookie: Cookie to be used to identify this nested call. @@ -480,7 +480,7 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) * Returns: Returns the code returned by the @nproc callback, or -1 if * the maximum recursion limit has been exceeded. */ -static int ep_call_nested(struct nested_calls *ncalls, int max_nests, +static int ep_call_nested(struct nested_calls *ncalls, int (*nproc)(void *, void *, int), void *priv, void *cookie, void *ctx) { @@ -499,7 +499,7 @@ static int ep_call_nested(struct nested_calls *ncalls, int max_nests, */ list_for_each_entry(tncur, lsthead, llink) { if (tncur->ctx == ctx && - (tncur->cookie == cookie || ++call_nests > max_nests)) { + (tncur->cookie == cookie || ++call_nests > EP_MAX_NESTS)) { /* * Ops ... loop detected or maximum nest level reached. * We abort this wake by breaking the cycle itself. @@ -573,7 +573,7 @@ static void ep_poll_safewake(wait_queue_head_t *wq) { int this_cpu = get_cpu(); - ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS, + ep_call_nested(&poll_safewake_ncalls, ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu); put_cpu(); @@ -699,7 +699,7 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep, */ spin_lock_irq(&ep->wq.lock); list_splice_init(&ep->rdllist, &txlist); - ep->ovflist = NULL; + WRITE_ONCE(ep->ovflist, NULL); spin_unlock_irq(&ep->wq.lock); /* @@ -713,7 +713,7 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep, * other events might have been queued by the poll callback. * We re-insert them inside the main ready-list here. */ - for (nepi = ep->ovflist; (epi = nepi) != NULL; + for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL; nepi = epi->next, epi->next = EP_UNACTIVE_PTR) { /* * We need to check if the item is already in the list. @@ -731,7 +731,7 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep, * releasing the lock, events will be queued in the normal way inside * ep->rdllist. */ - ep->ovflist = EP_UNACTIVE_PTR; + WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR); /* * Quickly re-inject items left on "txlist". @@ -1154,10 +1154,10 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * semantics). All the events that happen during that period of time are * chained in ep->ovflist and requeued later on. */ - if (unlikely(ep->ovflist != EP_UNACTIVE_PTR)) { + if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { if (epi->next == EP_UNACTIVE_PTR) { - epi->next = ep->ovflist; - ep->ovflist = epi; + epi->next = READ_ONCE(ep->ovflist); + WRITE_ONCE(ep->ovflist, epi); if (epi->ws) { /* * Activate ep->ws since epi->ws may get @@ -1333,7 +1333,6 @@ static int reverse_path_check_proc(void *priv, void *cookie, int call_nests) } } else { error = ep_call_nested(&poll_loop_ncalls, - EP_MAX_NESTS, reverse_path_check_proc, child_file, child_file, current); @@ -1367,7 +1366,7 @@ static int reverse_path_check(void) /* let's call this for all tfiles */ list_for_each_entry(current_file, &tfile_check_list, f_tfile_llink) { path_count_init(); - error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS, + error = ep_call_nested(&poll_loop_ncalls, reverse_path_check_proc, current_file, current_file, current); if (error) @@ -1626,21 +1625,24 @@ static __poll_t ep_send_events_proc(struct eventpoll *ep, struct list_head *head { struct ep_send_events_data *esed = priv; __poll_t revents; - struct epitem *epi; - struct epoll_event __user *uevent; + struct epitem *epi, *tmp; + struct epoll_event __user *uevent = esed->events; struct wakeup_source *ws; poll_table pt; init_poll_funcptr(&pt, NULL); + esed->res = 0; /* * We can loop without lock because we are passed a task private list. * Items cannot vanish during the loop because ep_scan_ready_list() is * holding "mtx" during this call. */ - for (esed->res = 0, uevent = esed->events; - !list_empty(head) && esed->res < esed->maxevents;) { - epi = list_first_entry(head, struct epitem, rdllink); + lockdep_assert_held(&ep->mtx); + + list_for_each_entry_safe(epi, tmp, head, rdllink) { + if (esed->res >= esed->maxevents) + break; /* * Activate ep->ws before deactivating epi->ws to prevent @@ -1660,42 +1662,42 @@ static __poll_t ep_send_events_proc(struct eventpoll *ep, struct list_head *head list_del_init(&epi->rdllink); - revents = ep_item_poll(epi, &pt, 1); - /* * If the event mask intersect the caller-requested one, * deliver the event to userspace. Again, ep_scan_ready_list() - * is holding "mtx", so no operations coming from userspace + * is holding ep->mtx, so no operations coming from userspace * can change the item. */ - if (revents) { - if (__put_user(revents, &uevent->events) || - __put_user(epi->event.data, &uevent->data)) { - list_add(&epi->rdllink, head); - ep_pm_stay_awake(epi); - if (!esed->res) - esed->res = -EFAULT; - return 0; - } - esed->res++; - uevent++; - if (epi->event.events & EPOLLONESHOT) - epi->event.events &= EP_PRIVATE_BITS; - else if (!(epi->event.events & EPOLLET)) { - /* - * If this file has been added with Level - * Trigger mode, we need to insert back inside - * the ready list, so that the next call to - * epoll_wait() will check again the events - * availability. At this point, no one can insert - * into ep->rdllist besides us. The epoll_ctl() - * callers are locked out by - * ep_scan_ready_list() holding "mtx" and the - * poll callback will queue them in ep->ovflist. - */ - list_add_tail(&epi->rdllink, &ep->rdllist); - ep_pm_stay_awake(epi); - } + revents = ep_item_poll(epi, &pt, 1); + if (!revents) + continue; + + if (__put_user(revents, &uevent->events) || + __put_user(epi->event.data, &uevent->data)) { + list_add(&epi->rdllink, head); + ep_pm_stay_awake(epi); + if (!esed->res) + esed->res = -EFAULT; + return 0; + } + esed->res++; + uevent++; + if (epi->event.events & EPOLLONESHOT) + epi->event.events &= EP_PRIVATE_BITS; + else if (!(epi->event.events & EPOLLET)) { + /* + * If this file has been added with Level + * Trigger mode, we need to insert back inside + * the ready list, so that the next call to + * epoll_wait() will check again the events + * availability. At this point, no one can insert + * into ep->rdllist besides us. The epoll_ctl() + * callers are locked out by + * ep_scan_ready_list() holding "mtx" and the + * poll callback will queue them in ep->ovflist. + */ + list_add_tail(&epi->rdllink, &ep->rdllist); + ep_pm_stay_awake(epi); } } @@ -1747,6 +1749,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, { int res = 0, eavail, timed_out = 0; u64 slack = 0; + bool waiter = false; wait_queue_entry_t wait; ktime_t expires, *to = NULL; @@ -1761,11 +1764,18 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, } else if (timeout == 0) { /* * Avoid the unnecessary trip to the wait queue loop, if the - * caller specified a non blocking operation. + * caller specified a non blocking operation. We still need + * lock because we could race and not see an epi being added + * to the ready list while in irq callback. Thus incorrectly + * returning 0 back to userspace. */ timed_out = 1; + spin_lock_irq(&ep->wq.lock); - goto check_events; + eavail = ep_events_available(ep); + spin_unlock_irq(&ep->wq.lock); + + goto send_events; } fetch_events: @@ -1773,64 +1783,66 @@ fetch_events: if (!ep_events_available(ep)) ep_busy_loop(ep, timed_out); - spin_lock_irq(&ep->wq.lock); + eavail = ep_events_available(ep); + if (eavail) + goto send_events; - if (!ep_events_available(ep)) { - /* - * Busy poll timed out. Drop NAPI ID for now, we can add - * it back in when we have moved a socket with a valid NAPI - * ID onto the ready list. - */ - ep_reset_busy_poll_napi_id(ep); + /* + * Busy poll timed out. Drop NAPI ID for now, we can add + * it back in when we have moved a socket with a valid NAPI + * ID onto the ready list. + */ + ep_reset_busy_poll_napi_id(ep); - /* - * We don't have any available event to return to the caller. - * We need to sleep here, and we will be wake up by - * ep_poll_callback() when events will become available. - */ + /* + * We don't have any available event to return to the caller. We need + * to sleep here, and we will be woken by ep_poll_callback() when events + * become available. + */ + if (!waiter) { + waiter = true; init_waitqueue_entry(&wait, current); - __add_wait_queue_exclusive(&ep->wq, &wait); - for (;;) { - /* - * We don't want to sleep if the ep_poll_callback() sends us - * a wakeup in between. That's why we set the task state - * to TASK_INTERRUPTIBLE before doing the checks. - */ - set_current_state(TASK_INTERRUPTIBLE); - /* - * Always short-circuit for fatal signals to allow - * threads to make a timely exit without the chance of - * finding more events available and fetching - * repeatedly. - */ - if (fatal_signal_pending(current)) { - res = -EINTR; - break; - } - if (ep_events_available(ep) || timed_out) - break; - if (signal_pending(current)) { - res = -EINTR; - break; - } + spin_lock_irq(&ep->wq.lock); + __add_wait_queue_exclusive(&ep->wq, &wait); + spin_unlock_irq(&ep->wq.lock); + } - spin_unlock_irq(&ep->wq.lock); - if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) - timed_out = 1; + for (;;) { + /* + * We don't want to sleep if the ep_poll_callback() sends us + * a wakeup in between. That's why we set the task state + * to TASK_INTERRUPTIBLE before doing the checks. + */ + set_current_state(TASK_INTERRUPTIBLE); + /* + * Always short-circuit for fatal signals to allow + * threads to make a timely exit without the chance of + * finding more events available and fetching + * repeatedly. + */ + if (fatal_signal_pending(current)) { + res = -EINTR; + break; + } - spin_lock_irq(&ep->wq.lock); + eavail = ep_events_available(ep); + if (eavail) + break; + if (signal_pending(current)) { + res = -EINTR; + break; } - __remove_wait_queue(&ep->wq, &wait); - __set_current_state(TASK_RUNNING); + if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) { + timed_out = 1; + break; + } } -check_events: - /* Is it worth to try to dig for events ? */ - eavail = ep_events_available(ep); - spin_unlock_irq(&ep->wq.lock); + __set_current_state(TASK_RUNNING); +send_events: /* * Try to transfer events to user space. In case we get 0 events and * there's still timeout left over, we go trying again in search of @@ -1840,6 +1852,12 @@ check_events: !(res = ep_send_events(ep, events, maxevents)) && !timed_out) goto fetch_events; + if (waiter) { + spin_lock_irq(&ep->wq.lock); + __remove_wait_queue(&ep->wq, &wait); + spin_unlock_irq(&ep->wq.lock); + } + return res; } @@ -1876,7 +1894,7 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) ep_tovisit = epi->ffd.file->private_data; if (ep_tovisit->visited) continue; - error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS, + error = ep_call_nested(&poll_loop_ncalls, ep_loop_check_proc, epi->ffd.file, ep_tovisit, current); if (error != 0) @@ -1916,7 +1934,7 @@ static int ep_loop_check(struct eventpoll *ep, struct file *file) int ret; struct eventpoll *ep_cur, *ep_next; - ret = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS, + ret = ep_call_nested(&poll_loop_ncalls, ep_loop_check_proc, file, ep, current); /* clear visited list */ list_for_each_entry_safe(ep_cur, ep_next, &visited_list, @@ -2172,7 +2190,7 @@ static int do_epoll_wait(int epfd, struct epoll_event __user *events, return -EINVAL; /* Verify that the area passed by the user is writeable */ - if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event))) + if (!access_ok(events, maxevents * sizeof(struct epoll_event))) return -EFAULT; /* Get the "struct file *" for the eventpoll file */ diff --git a/fs/exec.c b/fs/exec.c index fc281b738a98..fb72d36f7823 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -218,55 +218,10 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, if (ret <= 0) return NULL; - if (write) { - unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start; - unsigned long ptr_size, limit; - - /* - * Since the stack will hold pointers to the strings, we - * must account for them as well. - * - * The size calculation is the entire vma while each arg page is - * built, so each time we get here it's calculating how far it - * is currently (rather than each call being just the newly - * added size from the arg page). As a result, we need to - * always add the entire size of the pointers, so that on the - * last call to get_arg_page() we'll actually have the entire - * correct size. - */ - ptr_size = (bprm->argc + bprm->envc) * sizeof(void *); - if (ptr_size > ULONG_MAX - size) - goto fail; - size += ptr_size; - - acct_arg_size(bprm, size / PAGE_SIZE); - - /* - * We've historically supported up to 32 pages (ARG_MAX) - * of argument strings even with small stacks - */ - if (size <= ARG_MAX) - return page; - - /* - * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM - * (whichever is smaller) for the argv+env strings. - * This ensures that: - * - the remaining binfmt code will not run out of stack space, - * - the program will have a reasonable amount of stack left - * to work from. - */ - limit = _STK_LIM / 4 * 3; - limit = min(limit, bprm->rlim_stack.rlim_cur / 4); - if (size > limit) - goto fail; - } + if (write) + acct_arg_size(bprm, vma_pages(bprm->vma)); return page; - -fail: - put_page(page); - return NULL; } static void put_arg_page(struct page *page) @@ -492,6 +447,50 @@ static int count(struct user_arg_ptr argv, int max) return i; } +static int prepare_arg_pages(struct linux_binprm *bprm, + struct user_arg_ptr argv, struct user_arg_ptr envp) +{ + unsigned long limit, ptr_size; + + bprm->argc = count(argv, MAX_ARG_STRINGS); + if (bprm->argc < 0) + return bprm->argc; + + bprm->envc = count(envp, MAX_ARG_STRINGS); + if (bprm->envc < 0) + return bprm->envc; + + /* + * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM + * (whichever is smaller) for the argv+env strings. + * This ensures that: + * - the remaining binfmt code will not run out of stack space, + * - the program will have a reasonable amount of stack left + * to work from. + */ + limit = _STK_LIM / 4 * 3; + limit = min(limit, bprm->rlim_stack.rlim_cur / 4); + /* + * We've historically supported up to 32 pages (ARG_MAX) + * of argument strings even with small stacks + */ + limit = max_t(unsigned long, limit, ARG_MAX); + /* + * We must account for the size of all the argv and envp pointers to + * the argv and envp strings, since they will also take up space in + * the stack. They aren't stored until much later when we can't + * signal to the parent that the child has run out of stack space. + * Instead, calculate it here so it's possible to fail gracefully. + */ + ptr_size = (bprm->argc + bprm->envc) * sizeof(void *); + if (limit <= ptr_size) + return -E2BIG; + limit -= ptr_size; + + bprm->argmin = bprm->p - limit; + return 0; +} + /* * 'copy_strings()' copies argument/environment strings from the old * processes's memory to the new process's stack. The call to get_user_pages() @@ -527,6 +526,10 @@ static int copy_strings(int argc, struct user_arg_ptr argv, pos = bprm->p; str += len; bprm->p -= len; +#ifdef CONFIG_MMU + if (bprm->p < bprm->argmin) + goto out; +#endif while (len > 0) { int offset, bytes_to_copy; @@ -1084,7 +1087,7 @@ static int de_thread(struct task_struct *tsk) __set_current_state(TASK_KILLABLE); spin_unlock_irq(lock); schedule(); - if (unlikely(__fatal_signal_pending(tsk))) + if (__fatal_signal_pending(tsk)) goto killed; spin_lock_irq(lock); } @@ -1112,7 +1115,7 @@ static int de_thread(struct task_struct *tsk) write_unlock_irq(&tasklist_lock); cgroup_threadgroup_change_end(tsk); schedule(); - if (unlikely(__fatal_signal_pending(tsk))) + if (__fatal_signal_pending(tsk)) goto killed; } @@ -1399,7 +1402,7 @@ EXPORT_SYMBOL(finalize_exec); * Or, if exec fails before, free_bprm() should release ->cred and * and unlock. */ -int prepare_bprm_creds(struct linux_binprm *bprm) +static int prepare_bprm_creds(struct linux_binprm *bprm) { if (mutex_lock_interruptible(¤t->signal->cred_guard_mutex)) return -ERESTARTNOINTR; @@ -1789,12 +1792,8 @@ static int __do_execve_file(int fd, struct filename *filename, if (retval) goto out_unmark; - bprm->argc = count(argv, MAX_ARG_STRINGS); - if ((retval = bprm->argc) < 0) - goto out; - - bprm->envc = count(envp, MAX_ARG_STRINGS); - if ((retval = bprm->envc) < 0) + retval = prepare_arg_pages(bprm, argv, envp); + if (retval < 0) goto out; retval = prepare_binprm(bprm); diff --git a/fs/exofs/super.c b/fs/exofs/super.c index 906839a4da8f..fc80c7233fa5 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -705,21 +705,18 @@ out: /* * Read the superblock from the OSD and fill in the fields */ -static int exofs_fill_super(struct super_block *sb, void *data, int silent) +static int exofs_fill_super(struct super_block *sb, + struct exofs_mountopt *opts, + struct exofs_sb_info *sbi, + int silent) { struct inode *root; - struct exofs_mountopt *opts = data; - struct exofs_sb_info *sbi; /*extended info */ struct osd_dev *od; /* Master device */ struct exofs_fscb fscb; /*on-disk superblock info */ struct ore_comp comp; unsigned table_count; int ret; - sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); - if (!sbi) - return -ENOMEM; - /* use mount options to fill superblock */ if (opts->is_osdname) { struct osd_dev_info odi = {.systemid_len = 0}; @@ -863,7 +860,9 @@ static struct dentry *exofs_mount(struct file_system_type *type, int flags, const char *dev_name, void *data) { + struct super_block *s; struct exofs_mountopt opts; + struct exofs_sb_info *sbi; int ret; ret = parse_options(data, &opts); @@ -872,9 +871,31 @@ static struct dentry *exofs_mount(struct file_system_type *type, return ERR_PTR(ret); } + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + if (!sbi) { + kfree(opts.dev_name); + return ERR_PTR(-ENOMEM); + } + + s = sget(type, NULL, set_anon_super, flags, NULL); + + if (IS_ERR(s)) { + kfree(opts.dev_name); + kfree(sbi); + return ERR_CAST(s); + } + if (!opts.dev_name) opts.dev_name = dev_name; - return mount_nodev(type, flags, &opts, exofs_fill_super); + + + ret = exofs_fill_super(s, &opts, sbi, flags & SB_SILENT ? 1 : 0); + if (ret) { + deactivate_locked_super(s); + return ERR_PTR(ret); + } + s->s_flags |= SB_ACTIVE; + return dget(s->s_root); } /* diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 26a7fe5c4fd3..712f00995390 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -116,8 +116,16 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } + ret = file_write_and_wait_range(file, start, end); + if (ret) + return ret; + if (!journal) { - ret = __generic_file_fsync(file, start, end, datasync); + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL + }; + + ret = ext4_write_inode(inode, &wbc); if (!ret) ret = ext4_sync_parent(inode); if (test_opt(inode->i_sb, BARRIER)) @@ -125,9 +133,6 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } - ret = file_write_and_wait_range(file, start, end); - if (ret) - return ret; /* * data=writeback,ordered: * The caller's filemap_fdatawrite()/wait will sync the data. @@ -159,6 +164,9 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) ret = err; } out: + err = file_check_and_advance_wb_err(file); + if (ret == 0) + ret = err; trace_ext4_sync_file_exit(inode, ret); return ret; } diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 27373d88b5f0..56f6e1782d5f 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1890,12 +1890,12 @@ int ext4_inline_data_fiemap(struct inode *inode, physical += (char *)ext4_raw_inode(&iloc) - iloc.bh->b_data; physical += offsetof(struct ext4_inode, i_block); - if (physical) - error = fiemap_fill_next_extent(fieinfo, start, physical, - inline_len, flags); brelse(iloc.bh); out: up_read(&EXT4_I(inode)->xattr_sem); + if (physical) + error = fiemap_fill_next_extent(fieinfo, start, physical, + inline_len, flags); return (error < 0 ? error : 0); } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9affabd07682..34d7e0703cc6 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2778,7 +2778,8 @@ static int ext4_writepages(struct address_space *mapping, * We may need to convert up to one extent per block in * the page and we may dirty the inode. */ - rsv_blocks = 1 + (PAGE_SIZE >> inode->i_blkbits); + rsv_blocks = 1 + ext4_chunk_trans_blocks(inode, + PAGE_SIZE >> inode->i_blkbits); } /* @@ -4833,7 +4834,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, gid_t i_gid; projid_t i_projid; - if (((flags & EXT4_IGET_NORMAL) && + if ((!(flags & EXT4_IGET_SPECIAL) && (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO)) || (ino < EXT4_ROOT_INO) || (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))) { diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index f461d75ac049..6aa282ee455a 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -128,7 +128,7 @@ int ext4_mpage_readpages(struct address_space *mapping, prefetchw(&page->flags); if (pages) { - page = list_entry(pages->prev, struct page, lru); + page = lru_to_page(pages); list_del(&page->lru); if (add_to_page_cache_lru(page, mapping, page->index, readahead_gfp_mask(mapping))) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d6c142d73d99..fb12d3c17c1b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4902,7 +4902,7 @@ static int ext4_commit_super(struct super_block *sb, int sync) ext4_superblock_csum_set(sb); if (sync) lock_buffer(sbh); - if (buffer_write_io_error(sbh)) { + if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { /* * Oh, dear. A previous attempt to write the * superblock failed. This could happen because the diff --git a/fs/fat/cache.c b/fs/fat/cache.c index 78d501c1fb65..738e427e2d21 100644 --- a/fs/fat/cache.c +++ b/fs/fat/cache.c @@ -363,7 +363,7 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, *phys = 0; *mapped_blocks = 0; - if ((sbi->fat_bits != 32) && (inode->i_ino == MSDOS_ROOT_INO)) { + if (!is_fat32(sbi) && (inode->i_ino == MSDOS_ROOT_INO)) { if (sector < (sbi->dir_entries >> sbi->dir_per_block_bits)) { *phys = sector + sbi->dir_start; *mapped_blocks = 1; diff --git a/fs/fat/dir.c b/fs/fat/dir.c index c8366cb8eccd..9d01db37183f 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -57,7 +57,7 @@ static inline void fat_dir_readahead(struct inode *dir, sector_t iblock, if ((iblock & (sbi->sec_per_clus - 1)) || sbi->sec_per_clus == 1) return; /* root dir of FAT12/FAT16 */ - if ((sbi->fat_bits != 32) && (dir->i_ino == MSDOS_ROOT_INO)) + if (!is_fat32(sbi) && (dir->i_ino == MSDOS_ROOT_INO)) return; bh = sb_find_get_block(sb, phys); @@ -805,7 +805,7 @@ static long fat_dir_ioctl(struct file *filp, unsigned int cmd, return fat_generic_ioctl(filp, cmd, arg); } - if (!access_ok(VERIFY_WRITE, d1, sizeof(struct __fat_dirent[2]))) + if (!access_ok(d1, sizeof(struct __fat_dirent[2]))) return -EFAULT; /* * Yes, we don't need this put_user() absolutely. However old @@ -845,7 +845,7 @@ static long fat_compat_dir_ioctl(struct file *filp, unsigned cmd, return fat_generic_ioctl(filp, cmd, (unsigned long)arg); } - if (!access_ok(VERIFY_WRITE, d1, sizeof(struct compat_dirent[2]))) + if (!access_ok(d1, sizeof(struct compat_dirent[2]))) return -EFAULT; /* * Yes, we don't need this put_user() absolutely. However old @@ -1313,7 +1313,7 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots, } } if (dir->i_ino == MSDOS_ROOT_INO) { - if (sbi->fat_bits != 32) + if (!is_fat32(sbi)) goto error; } else if (MSDOS_I(dir)->i_start == 0) { fat_msg(sb, KERN_ERR, "Corrupted directory (i_pos %lld)", diff --git a/fs/fat/fat.h b/fs/fat/fat.h index 4e1b2f6df5e6..922a0c6ba46c 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -142,6 +142,34 @@ static inline struct msdos_sb_info *MSDOS_SB(struct super_block *sb) return sb->s_fs_info; } +/* + * Functions that determine the variant of the FAT file system (i.e., + * whether this is FAT12, FAT16 or FAT32. + */ +static inline bool is_fat12(const struct msdos_sb_info *sbi) +{ + return sbi->fat_bits == 12; +} + +static inline bool is_fat16(const struct msdos_sb_info *sbi) +{ + return sbi->fat_bits == 16; +} + +static inline bool is_fat32(const struct msdos_sb_info *sbi) +{ + return sbi->fat_bits == 32; +} + +/* Maximum number of clusters */ +static inline u32 max_fat(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + return is_fat32(sbi) ? MAX_FAT32 : + is_fat16(sbi) ? MAX_FAT16 : MAX_FAT12; +} + static inline struct msdos_inode_info *MSDOS_I(struct inode *inode) { return container_of(inode, struct msdos_inode_info, vfs_inode); @@ -257,7 +285,7 @@ static inline int fat_get_start(const struct msdos_sb_info *sbi, const struct msdos_dir_entry *de) { int cluster = le16_to_cpu(de->start); - if (sbi->fat_bits == 32) + if (is_fat32(sbi)) cluster |= (le16_to_cpu(de->starthi) << 16); return cluster; } diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index f58c0cacc531..495edeafd60a 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -290,19 +290,17 @@ void fat_ent_access_init(struct super_block *sb) mutex_init(&sbi->fat_lock); - switch (sbi->fat_bits) { - case 32: + if (is_fat32(sbi)) { sbi->fatent_shift = 2; sbi->fatent_ops = &fat32_ops; - break; - case 16: + } else if (is_fat16(sbi)) { sbi->fatent_shift = 1; sbi->fatent_ops = &fat16_ops; - break; - case 12: + } else if (is_fat12(sbi)) { sbi->fatent_shift = -1; sbi->fatent_ops = &fat12_ops; - break; + } else { + fat_fs_error(sb, "invalid FAT variant, %u bits", sbi->fat_bits); } } @@ -310,7 +308,7 @@ static void mark_fsinfo_dirty(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); - if (sb_rdonly(sb) || sbi->fat_bits != 32) + if (sb_rdonly(sb) || !is_fat32(sbi)) return; __mark_inode_dirty(sbi->fsinfo_inode, I_DIRTY_SYNC); @@ -327,7 +325,7 @@ static inline int fat_ent_update_ptr(struct super_block *sb, /* Is this fatent's blocks including this entry? */ if (!fatent->nr_bhs || bhs[0]->b_blocknr != blocknr) return 0; - if (sbi->fat_bits == 12) { + if (is_fat12(sbi)) { if ((offset + 1) < sb->s_blocksize) { /* This entry is on bhs[0]. */ if (fatent->nr_bhs == 2) { diff --git a/fs/fat/inode.c b/fs/fat/inode.c index c0b5b5c3373b..79bb0e73a65f 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -686,7 +686,7 @@ static void fat_set_state(struct super_block *sb, b = (struct fat_boot_sector *) bh->b_data; - if (sbi->fat_bits == 32) { + if (is_fat32(sbi)) { if (set) b->fat32.state |= FAT_STATE_DIRTY; else @@ -1396,7 +1396,7 @@ static int fat_read_root(struct inode *inode) inode->i_mode = fat_make_mode(sbi, ATTR_DIR, S_IRWXUGO); inode->i_op = sbi->dir_ops; inode->i_fop = &fat_dir_operations; - if (sbi->fat_bits == 32) { + if (is_fat32(sbi)) { MSDOS_I(inode)->i_start = sbi->root_cluster; error = fat_calc_dir_size(inode); if (error < 0) @@ -1423,7 +1423,7 @@ static unsigned long calc_fat_clusters(struct super_block *sb) struct msdos_sb_info *sbi = MSDOS_SB(sb); /* Divide first to avoid overflow */ - if (sbi->fat_bits != 12) { + if (!is_fat12(sbi)) { unsigned long ent_per_sec = sb->s_blocksize * 8 / sbi->fat_bits; return ent_per_sec * sbi->fat_length; } @@ -1743,7 +1743,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, } /* interpret volume ID as a little endian 32 bit integer */ - if (sbi->fat_bits == 32) + if (is_fat32(sbi)) sbi->vol_id = bpb.fat32_vol_id; else /* fat 16 or 12 */ sbi->vol_id = bpb.fat16_vol_id; @@ -1769,11 +1769,11 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, total_clusters = (total_sectors - sbi->data_start) / sbi->sec_per_clus; - if (sbi->fat_bits != 32) + if (!is_fat32(sbi)) sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12; /* some OSes set FAT_STATE_DIRTY and clean it on unmount. */ - if (sbi->fat_bits == 32) + if (is_fat32(sbi)) sbi->dirty = bpb.fat32_state & FAT_STATE_DIRTY; else /* fat 16 or 12 */ sbi->dirty = bpb.fat16_state & FAT_STATE_DIRTY; @@ -1781,7 +1781,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, /* check that FAT table does not overflow */ fat_clusters = calc_fat_clusters(sb); total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT); - if (total_clusters > MAX_FAT(sb)) { + if (total_clusters > max_fat(sb)) { if (!silent) fat_msg(sb, KERN_ERR, "count of clusters too big (%u)", total_clusters); @@ -1803,11 +1803,15 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, fat_ent_access_init(sb); /* - * The low byte of FAT's first entry must have same value with - * media-field. But in real world, too many devices is - * writing wrong value. So, removed that validity check. + * The low byte of the first FAT entry must have the same value as + * the media field of the boot sector. But in real world, too many + * devices are writing wrong values. So, removed that validity check. * - * if (FAT_FIRST_ENT(sb, media) != first) + * The removed check compared the first FAT entry to a value dependent + * on the media field like this: + * == (0x0F00 | media), for FAT12 + * == (0XFF00 | media), for FAT16 + * == (0x0FFFFF | media), for FAT32 */ error = -EINVAL; diff --git a/fs/fat/misc.c b/fs/fat/misc.c index fce0a76f3f1e..4fc950bb6433 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -64,7 +64,7 @@ int fat_clusters_flush(struct super_block *sb) struct buffer_head *bh; struct fat_boot_fsinfo *fsinfo; - if (sbi->fat_bits != 32) + if (!is_fat32(sbi)) return 0; bh = sb_bread(sb, sbi->fsinfo_sector); diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index f37662675c3a..29a9dcfbe81f 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -565,6 +565,7 @@ const struct inode_operations hfsplus_dir_inode_operations = { .symlink = hfsplus_symlink, .mknod = hfsplus_mknod, .rename = hfsplus_rename, + .getattr = hfsplus_getattr, .listxattr = hfsplus_listxattr, }; diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index dd7ad9f13e3a..b8471bf05def 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -488,6 +488,8 @@ void hfsplus_inode_write_fork(struct inode *inode, struct hfsplus_fork_raw *fork); int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd); int hfsplus_cat_write_inode(struct inode *inode); +int hfsplus_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int query_flags); int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index d7ab9d8c4b67..d131c8ea7eb6 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -270,6 +270,26 @@ static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr) return 0; } +int hfsplus_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int query_flags) +{ + struct inode *inode = d_inode(path->dentry); + struct hfsplus_inode_info *hip = HFSPLUS_I(inode); + + if (inode->i_flags & S_APPEND) + stat->attributes |= STATX_ATTR_APPEND; + if (inode->i_flags & S_IMMUTABLE) + stat->attributes |= STATX_ATTR_IMMUTABLE; + if (hip->userflags & HFSPLUS_FLG_NODUMP) + stat->attributes |= STATX_ATTR_NODUMP; + + stat->attributes_mask |= STATX_ATTR_APPEND | STATX_ATTR_IMMUTABLE | + STATX_ATTR_NODUMP; + + generic_fillattr(inode, stat); + return 0; +} + int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { @@ -329,6 +349,7 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, static const struct inode_operations hfsplus_file_inode_operations = { .setattr = hfsplus_setattr, + .getattr = hfsplus_getattr, .listxattr = hfsplus_listxattr, }; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a2fcea5f8225..32920a10100e 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -383,16 +383,17 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end) * truncation is indicated by end of range being LLONG_MAX * In this case, we first scan the range and release found pages. * After releasing pages, hugetlb_unreserve_pages cleans up region/reserv - * maps and global counts. + * maps and global counts. Page faults can not race with truncation + * in this routine. hugetlb_no_page() prevents page faults in the + * truncated range. It checks i_size before allocation, and again after + * with the page table lock for the page held. The same lock must be + * acquired to unmap a page. * hole punch is indicated if end is not LLONG_MAX * In the hole punch case we scan the range and release found pages. * Only when releasing a page is the associated region/reserv map * deleted. The region/reserv map for ranges without associated - * pages are not modified. - * - * Callers of this routine must hold the i_mmap_rwsem in write mode to prevent - * races with page faults. - * + * pages are not modified. Page faults can race with hole punch. + * This is indicated if we find a mapped page. * Note: If the passed end of range value is beyond the end of file, but * not LLONG_MAX this routine still performs a hole punch operation. */ @@ -422,14 +423,32 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, for (i = 0; i < pagevec_count(&pvec); ++i) { struct page *page = pvec.pages[i]; + u32 hash; index = page->index; + hash = hugetlb_fault_mutex_hash(h, current->mm, + &pseudo_vma, + mapping, index, 0); + mutex_lock(&hugetlb_fault_mutex_table[hash]); + /* - * A mapped page is impossible as callers should unmap - * all references before calling. And, i_mmap_rwsem - * prevents the creation of additional mappings. + * If page is mapped, it was faulted in after being + * unmapped in caller. Unmap (again) now after taking + * the fault mutex. The mutex will prevent faults + * until we finish removing the page. + * + * This race can only happen in the hole punch case. + * Getting here in a truncate operation is a bug. */ - VM_BUG_ON(page_mapped(page)); + if (unlikely(page_mapped(page))) { + BUG_ON(truncate_op); + + i_mmap_lock_write(mapping); + hugetlb_vmdelete_list(&mapping->i_mmap, + index * pages_per_huge_page(h), + (index + 1) * pages_per_huge_page(h)); + i_mmap_unlock_write(mapping); + } lock_page(page); /* @@ -451,6 +470,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, } unlock_page(page); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); } huge_pagevec_release(&pvec); cond_resched(); @@ -462,20 +482,9 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, static void hugetlbfs_evict_inode(struct inode *inode) { - struct address_space *mapping = inode->i_mapping; struct resv_map *resv_map; - /* - * The vfs layer guarantees that there are no other users of this - * inode. Therefore, it would be safe to call remove_inode_hugepages - * without holding i_mmap_rwsem. We acquire and hold here to be - * consistent with other callers. Since there will be no contention - * on the semaphore, overhead is negligible. - */ - i_mmap_lock_write(mapping); remove_inode_hugepages(inode, 0, LLONG_MAX); - i_mmap_unlock_write(mapping); - resv_map = (struct resv_map *)inode->i_mapping->private_data; /* root inode doesn't have the resv_map, so we should check it */ if (resv_map) @@ -496,8 +505,8 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) i_mmap_lock_write(mapping); if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0); - remove_inode_hugepages(inode, offset, LLONG_MAX); i_mmap_unlock_write(mapping); + remove_inode_hugepages(inode, offset, LLONG_MAX); return 0; } @@ -531,8 +540,8 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) hugetlb_vmdelete_list(&mapping->i_mmap, hole_start >> PAGE_SHIFT, hole_end >> PAGE_SHIFT); - remove_inode_hugepages(inode, hole_start, hole_end); i_mmap_unlock_write(mapping); + remove_inode_hugepages(inode, hole_start, hole_end); inode_unlock(inode); } @@ -615,11 +624,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, /* addr is the offset within the file (zero based) */ addr = index * hpage_size; - /* - * fault mutex taken here, protects against fault path - * and hole punch. inode_lock previously taken protects - * against truncation. - */ + /* mutex taken here, fault path and hole punch */ hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping, index, addr); mutex_lock(&hugetlb_fault_mutex_table[hash]); diff --git a/fs/ioctl.c b/fs/ioctl.c index d64f622cac8b..fef3a6bf7c78 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -203,7 +203,7 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg) fieinfo.fi_extents_start = ufiemap->fm_extents; if (fiemap.fm_extent_count != 0 && - !access_ok(VERIFY_WRITE, fieinfo.fi_extents_start, + !access_ok(fieinfo.fi_extents_start, fieinfo.fi_extents_max * sizeof(struct fiemap_extent))) return -EFAULT; diff --git a/fs/locks.c b/fs/locks.c index f0b24d98f36b..ff6af2c32601 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -453,7 +453,7 @@ static void locks_move_blocks(struct file_lock *new, struct file_lock *fl) return; spin_lock(&blocked_lock_lock); list_splice_init(&fl->fl_blocked_requests, &new->fl_blocked_requests); - list_for_each_entry(f, &fl->fl_blocked_requests, fl_blocked_member) + list_for_each_entry(f, &new->fl_blocked_requests, fl_blocked_member) f->fl_blocker = new; spin_unlock(&blocked_lock_lock); } diff --git a/fs/namespace.c b/fs/namespace.c index a7f91265ea67..a677b59efd74 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -26,6 +26,7 @@ #include <linux/memblock.h> #include <linux/task_work.h> #include <linux/sched/task.h> +#include <uapi/linux/mount.h> #include "pnode.h" #include "internal.h" @@ -245,13 +246,9 @@ out_free_cache: * mnt_want/drop_write() will _keep_ the filesystem * r/w. */ -int __mnt_is_readonly(struct vfsmount *mnt) +bool __mnt_is_readonly(struct vfsmount *mnt) { - if (mnt->mnt_flags & MNT_READONLY) - return 1; - if (sb_rdonly(mnt->mnt_sb)) - return 1; - return 0; + return (mnt->mnt_flags & MNT_READONLY) || sb_rdonly(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(__mnt_is_readonly); @@ -507,11 +504,12 @@ static int mnt_make_readonly(struct mount *mnt) return ret; } -static void __mnt_unmake_readonly(struct mount *mnt) +static int __mnt_unmake_readonly(struct mount *mnt) { lock_mount_hash(); mnt->mnt.mnt_flags &= ~MNT_READONLY; unlock_mount_hash(); + return 0; } int sb_prepare_remount_readonly(struct super_block *sb) @@ -1360,7 +1358,7 @@ static void namespace_unlock(void) if (likely(hlist_empty(&head))) return; - synchronize_rcu(); + synchronize_rcu_expedited(); group_pin_kill(&head); } @@ -2215,21 +2213,91 @@ out: return err; } -static int change_mount_flags(struct vfsmount *mnt, int ms_flags) +/* + * Don't allow locked mount flags to be cleared. + * + * No locks need to be held here while testing the various MNT_LOCK + * flags because those flags can never be cleared once they are set. + */ +static bool can_change_locked_flags(struct mount *mnt, unsigned int mnt_flags) { - int error = 0; - int readonly_request = 0; + unsigned int fl = mnt->mnt.mnt_flags; + + if ((fl & MNT_LOCK_READONLY) && + !(mnt_flags & MNT_READONLY)) + return false; - if (ms_flags & MS_RDONLY) - readonly_request = 1; - if (readonly_request == __mnt_is_readonly(mnt)) + if ((fl & MNT_LOCK_NODEV) && + !(mnt_flags & MNT_NODEV)) + return false; + + if ((fl & MNT_LOCK_NOSUID) && + !(mnt_flags & MNT_NOSUID)) + return false; + + if ((fl & MNT_LOCK_NOEXEC) && + !(mnt_flags & MNT_NOEXEC)) + return false; + + if ((fl & MNT_LOCK_ATIME) && + ((fl & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) + return false; + + return true; +} + +static int change_mount_ro_state(struct mount *mnt, unsigned int mnt_flags) +{ + bool readonly_request = (mnt_flags & MNT_READONLY); + + if (readonly_request == __mnt_is_readonly(&mnt->mnt)) return 0; if (readonly_request) - error = mnt_make_readonly(real_mount(mnt)); - else - __mnt_unmake_readonly(real_mount(mnt)); - return error; + return mnt_make_readonly(mnt); + + return __mnt_unmake_readonly(mnt); +} + +/* + * Update the user-settable attributes on a mount. The caller must hold + * sb->s_umount for writing. + */ +static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags) +{ + lock_mount_hash(); + mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; + mnt->mnt.mnt_flags = mnt_flags; + touch_mnt_namespace(mnt->mnt_ns); + unlock_mount_hash(); +} + +/* + * Handle reconfiguration of the mountpoint only without alteration of the + * superblock it refers to. This is triggered by specifying MS_REMOUNT|MS_BIND + * to mount(2). + */ +static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags) +{ + struct super_block *sb = path->mnt->mnt_sb; + struct mount *mnt = real_mount(path->mnt); + int ret; + + if (!check_mnt(mnt)) + return -EINVAL; + + if (path->dentry != mnt->mnt.mnt_root) + return -EINVAL; + + if (!can_change_locked_flags(mnt, mnt_flags)) + return -EPERM; + + down_write(&sb->s_umount); + ret = change_mount_ro_state(mnt, mnt_flags); + if (ret == 0) + set_mount_attributes(mnt, mnt_flags); + up_write(&sb->s_umount); + return ret; } /* @@ -2243,6 +2311,7 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags, int err; struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); + void *sec_opts = NULL; if (!check_mnt(mnt)) return -EINVAL; @@ -2250,50 +2319,25 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags, if (path->dentry != path->mnt->mnt_root) return -EINVAL; - /* Don't allow changing of locked mnt flags. - * - * No locks need to be held here while testing the various - * MNT_LOCK flags because those flags can never be cleared - * once they are set. - */ - if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) && - !(mnt_flags & MNT_READONLY)) { - return -EPERM; - } - if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) && - !(mnt_flags & MNT_NODEV)) { - return -EPERM; - } - if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) && - !(mnt_flags & MNT_NOSUID)) { - return -EPERM; - } - if ((mnt->mnt.mnt_flags & MNT_LOCK_NOEXEC) && - !(mnt_flags & MNT_NOEXEC)) { - return -EPERM; - } - if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) && - ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) { + if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; - } - err = security_sb_remount(sb, data); + if (data && !(sb->s_type->fs_flags & FS_BINARY_MOUNTDATA)) { + err = security_sb_eat_lsm_opts(data, &sec_opts); + if (err) + return err; + } + err = security_sb_remount(sb, sec_opts); + security_free_mnt_opts(&sec_opts); if (err) return err; down_write(&sb->s_umount); - if (ms_flags & MS_BIND) - err = change_mount_flags(path->mnt, ms_flags); - else if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) - err = -EPERM; - else + err = -EPERM; + if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { err = do_remount_sb(sb, sb_flags, data, 0); - if (!err) { - lock_mount_hash(); - mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; - mnt->mnt.mnt_flags = mnt_flags; - touch_mnt_namespace(mnt->mnt_ns); - unlock_mount_hash(); + if (!err) + set_mount_attributes(mnt, mnt_flags); } up_write(&sb->s_umount); return err; @@ -2651,7 +2695,7 @@ static long exact_copy_from_user(void *to, const void __user * from, const char __user *f = from; char c; - if (!access_ok(VERIFY_READ, from, n)) + if (!access_ok(from, n)) return n; current->kernel_uaccess_faults_ok++; @@ -2788,7 +2832,9 @@ long do_mount(const char *dev_name, const char __user *dir_name, SB_LAZYTIME | SB_I_VERSION); - if (flags & MS_REMOUNT) + if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND)) + retval = do_reconfigure_mnt(&path, mnt_flags); + else if (flags & MS_REMOUNT) retval = do_remount(&path, flags, sb_flags, mnt_flags, data_page); else if (flags & MS_BIND) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7f80f036ebd9..b1e577302518 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -123,7 +123,7 @@ struct nfs_parsed_mount_data { unsigned short protocol; } nfs_server; - struct security_mnt_opts lsm_opts; + void *lsm_opts; struct net *net; }; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 7c942462d8c6..22ce3c8a2f46 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -929,7 +929,7 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void) data->minorversion = 0; data->need_mount = true; data->net = current->nsproxy->net_ns; - security_init_mnt_opts(&data->lsm_opts); + data->lsm_opts = NULL; } return data; } @@ -1206,7 +1206,7 @@ static int nfs_get_option_ul_bound(substring_t args[], unsigned long *option, static int nfs_parse_mount_options(char *raw, struct nfs_parsed_mount_data *mnt) { - char *p, *string, *secdata; + char *p, *string; int rc, sloppy = 0, invalid_option = 0; unsigned short protofamily = AF_UNSPEC; unsigned short mountfamily = AF_UNSPEC; @@ -1217,20 +1217,10 @@ static int nfs_parse_mount_options(char *raw, } dfprintk(MOUNT, "NFS: nfs mount opts='%s'\n", raw); - secdata = alloc_secdata(); - if (!secdata) - goto out_nomem; - - rc = security_sb_copy_data(raw, secdata); + rc = security_sb_eat_lsm_opts(raw, &mnt->lsm_opts); if (rc) goto out_security_failure; - rc = security_sb_parse_opts_str(secdata, &mnt->lsm_opts); - if (rc) - goto out_security_failure; - - free_secdata(secdata); - while ((p = strsep(&raw, ",")) != NULL) { substring_t args[MAX_OPT_ARGS]; unsigned long option; @@ -1682,7 +1672,6 @@ out_nomem: printk(KERN_INFO "NFS: not enough memory to parse option\n"); return 0; out_security_failure: - free_secdata(secdata); printk(KERN_INFO "NFS: security options invalid: %d\n", rc); return 0; } @@ -2081,14 +2070,9 @@ static int nfs23_validate_mount_data(void *options, if (data->context[0]){ #ifdef CONFIG_SECURITY_SELINUX int rc; - char *opts_str = kmalloc(sizeof(data->context) + 8, GFP_KERNEL); - if (!opts_str) - return -ENOMEM; - strcpy(opts_str, "context="); data->context[NFS_MAX_CONTEXT_LEN] = '\0'; - strcat(opts_str, &data->context[0]); - rc = security_sb_parse_opts_str(opts_str, &args->lsm_opts); - kfree(opts_str); + rc = security_add_mnt_opt("context", data->context, + strlen(data->context), &args->lsm_opts); if (rc) return rc; #else @@ -2271,7 +2255,7 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) options->version <= 6)))) return 0; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = nfs_alloc_parsed_mount_data(); if (data == NULL) return -ENOMEM; @@ -2310,8 +2294,10 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) /* compare new mount options with old ones */ error = nfs_compare_remount_data(nfss, data); + if (!error) + error = security_sb_remount(sb, data->lsm_opts); out: - kfree(data); + nfs_free_parsed_mount_data(data); return error; } EXPORT_SYMBOL_GPL(nfs_remount); @@ -2548,7 +2534,7 @@ int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot, if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL) kflags |= SECURITY_LSM_NATIVE_LABELS; - error = security_sb_set_mnt_opts(s, &mount_info->parsed->lsm_opts, + error = security_sb_set_mnt_opts(s, mount_info->parsed->lsm_opts, kflags, &kflags_out); if (error) goto err; diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index eb1ce30412dc..832c1759a09a 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -30,6 +30,7 @@ #include <linux/quotaops.h> #include <linux/blkdev.h> #include <linux/uio.h> +#include <linux/mm.h> #include <cluster/masklog.h> @@ -397,7 +398,7 @@ static int ocfs2_readpages(struct file *filp, struct address_space *mapping, * Check whether a remote node truncated this file - we just * drop out in that case as it's not worth handling here. */ - last = list_entry(pages->prev, struct page, lru); + last = lru_to_page(pages); start = (loff_t)last->index << PAGE_SHIFT; if (start >= i_size_read(inode)) goto out_unlock; diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index b8fa1487cd85..8decbe95dcec 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -254,7 +254,7 @@ static ssize_t dlmfs_file_read(struct file *filp, if (!count) return 0; - if (!access_ok(VERIFY_WRITE, buf, count)) + if (!access_ok(buf, count)) return -EFAULT; /* don't read past the lvb */ @@ -302,7 +302,7 @@ static ssize_t dlmfs_file_write(struct file *filp, if (!count) return 0; - if (!access_ok(VERIFY_READ, buf, count)) + if (!access_ok(buf, count)) return -EFAULT; /* don't write past the lvb */ diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index fe53381b26b1..f038235c64bd 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -77,7 +77,7 @@ static int orangefs_readpages(struct file *file, for (page_idx = 0; page_idx < nr_pages; page_idx++) { struct page *page; - page = list_entry(pages->prev, struct page, lru); + page = lru_to_page(pages); list_del(&page->lru); if (!add_to_page_cache(page, mapping, diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c index c4e98c9c1621..443bcd8c3c19 100644 --- a/fs/orangefs/orangefs-bufmap.c +++ b/fs/orangefs/orangefs-bufmap.c @@ -105,7 +105,7 @@ static int wait_for_free(struct slot_map *m) left = t; else left = t + (left - n); - if (unlikely(signal_pending(current))) + if (signal_pending(current)) left = -EINTR; } while (left > 0); diff --git a/fs/pnode.c b/fs/pnode.c index 53d411a371ce..1100e810d855 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -10,6 +10,7 @@ #include <linux/mount.h> #include <linux/fs.h> #include <linux/nsproxy.h> +#include <uapi/linux/mount.h> #include "internal.h" #include "pnode.h" diff --git a/fs/proc/base.c b/fs/proc/base.c index d7fd1ca807d2..633a63462573 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -581,8 +581,10 @@ static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns, /* * print the file header */ - seq_printf(m, "%-25s %-20s %-20s %-10s\n", - "Limit", "Soft Limit", "Hard Limit", "Units"); + seq_puts(m, "Limit " + "Soft Limit " + "Hard Limit " + "Units \n"); for (i = 0; i < RLIM_NLIMITS; i++) { if (rlim[i].rlim_cur == RLIM_INFINITY) @@ -2356,10 +2358,13 @@ static ssize_t timerslack_ns_write(struct file *file, const char __user *buf, return -ESRCH; if (p != current) { - if (!capable(CAP_SYS_NICE)) { + rcu_read_lock(); + if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { + rcu_read_unlock(); count = -EPERM; goto out; } + rcu_read_unlock(); err = security_task_setscheduler(p); if (err) { @@ -2392,11 +2397,14 @@ static int timerslack_ns_show(struct seq_file *m, void *v) return -ESRCH; if (p != current) { - - if (!capable(CAP_SYS_NICE)) { + rcu_read_lock(); + if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { + rcu_read_unlock(); err = -EPERM; goto out; } + rcu_read_unlock(); + err = security_task_getscheduler(p); if (err) goto out; diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 5792f9e39466..da649ccd6804 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -59,7 +59,6 @@ static struct kmem_cache *pde_opener_cache __ro_after_init; static struct inode *proc_alloc_inode(struct super_block *sb) { struct proc_inode *ei; - struct inode *inode; ei = kmem_cache_alloc(proc_inode_cachep, GFP_KERNEL); if (!ei) @@ -71,8 +70,7 @@ static struct inode *proc_alloc_inode(struct super_block *sb) ei->sysctl = NULL; ei->sysctl_entry = NULL; ei->ns_ops = NULL; - inode = &ei->vfs_inode; - return inode; + return &ei->vfs_inode; } static void proc_i_callback(struct rcu_head *head) diff --git a/fs/proc/util.c b/fs/proc/util.c index b161cfa0f9fa..98f8adc17345 100644 --- a/fs/proc/util.c +++ b/fs/proc/util.c @@ -1,4 +1,5 @@ #include <linux/dcache.h> +#include "internal.h" unsigned name_to_int(const struct qstr *qstr) { diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c index 24db02de1787..97fcef74e5af 100644 --- a/fs/pstore/pmsg.c +++ b/fs/pstore/pmsg.c @@ -33,7 +33,7 @@ static ssize_t write_pmsg(struct file *file, const char __user *buf, record.size = count; /* check outside lock, page in any data. write_user also checks */ - if (!access_ok(VERIFY_READ, buf, count)) + if (!access_ok(buf, count)) return -EFAULT; mutex_lock(&pmsg_lock); diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index c11711c2cc83..f375c0735351 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -357,7 +357,7 @@ int notrace persistent_ram_write_user(struct persistent_ram_zone *prz, int rem, ret = 0, c = count; size_t start; - if (unlikely(!access_ok(VERIFY_READ, s, count))) + if (unlikely(!access_ok(s, count))) return -EFAULT; if (unlikely(c > prz->buffer_size)) { s += c - prz->buffer_size; diff --git a/fs/read_write.c b/fs/read_write.c index 58f30537c47a..ff3c5e6f87cf 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -442,7 +442,7 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; - if (unlikely(!access_ok(VERIFY_WRITE, buf, count))) + if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); @@ -538,7 +538,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; - if (unlikely(!access_ok(VERIFY_READ, buf, count))) + if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); @@ -718,9 +718,6 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, return ret; } -/* A write operation does a read from user space and vice versa */ -#define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ) - /** * rw_copy_check_uvector() - Copy an array of &struct iovec from userspace * into the kernel and check that it is valid. @@ -810,7 +807,7 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, goto out; } if (type >= 0 - && unlikely(!access_ok(vrfy_dir(type), buf, len))) { + && unlikely(!access_ok(buf, len))) { ret = -EFAULT; goto out; } @@ -856,7 +853,7 @@ ssize_t compat_rw_copy_check_uvector(int type, *ret_pointer = iov; ret = -EFAULT; - if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector))) + if (!access_ok(uvector, nr_segs*sizeof(*uvector))) goto out; /* @@ -881,7 +878,7 @@ ssize_t compat_rw_copy_check_uvector(int type, if (len < 0) /* size_t not fitting in compat_ssize_t .. */ goto out; if (type >= 0 && - !access_ok(vrfy_dir(type), compat_ptr(buf), len)) { + !access_ok(compat_ptr(buf), len)) { ret = -EFAULT; goto out; } diff --git a/fs/readdir.c b/fs/readdir.c index d97f548e6323..2f6a4534e0df 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -105,7 +105,7 @@ static int fillonedir(struct dir_context *ctx, const char *name, int namlen, } buf->result++; dirent = buf->dirent; - if (!access_ok(VERIFY_WRITE, dirent, + if (!access_ok(dirent, (unsigned long)(dirent->d_name + namlen + 1) - (unsigned long)dirent)) goto efault; @@ -221,7 +221,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, }; int error; - if (!access_ok(VERIFY_WRITE, dirent, count)) + if (!access_ok(dirent, count)) return -EFAULT; f = fdget_pos(fd); @@ -304,7 +304,7 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, }; int error; - if (!access_ok(VERIFY_WRITE, dirent, count)) + if (!access_ok(dirent, count)) return -EFAULT; f = fdget_pos(fd); @@ -365,7 +365,7 @@ static int compat_fillonedir(struct dir_context *ctx, const char *name, } buf->result++; dirent = buf->dirent; - if (!access_ok(VERIFY_WRITE, dirent, + if (!access_ok(dirent, (unsigned long)(dirent->d_name + namlen + 1) - (unsigned long)dirent)) goto efault; @@ -475,7 +475,7 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, }; int error; - if (!access_ok(VERIFY_WRITE, dirent, count)) + if (!access_ok(dirent, count)) return -EFAULT; f = fdget_pos(fd); diff --git a/fs/select.c b/fs/select.c index 4c8652390c94..d0f35dbc0e8f 100644 --- a/fs/select.c +++ b/fs/select.c @@ -381,9 +381,6 @@ typedef struct { #define FDS_BYTES(nr) (FDS_LONGS(nr)*sizeof(long)) /* - * We do a VERIFY_WRITE here even though we are only reading this time: - * we'll write to it eventually.. - * * Use "unsigned long" accesses to let user-mode fd_set's be long-aligned. */ static inline @@ -782,7 +779,7 @@ SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp, sigset_t __user *up = NULL; if (sig) { - if (!access_ok(VERIFY_READ, sig, sizeof(void *)+sizeof(size_t)) + if (!access_ok(sig, sizeof(void *)+sizeof(size_t)) || __get_user(up, (sigset_t __user * __user *)sig) || __get_user(sigsetsize, (size_t __user *)(sig+sizeof(void *)))) @@ -802,7 +799,7 @@ SYSCALL_DEFINE6(pselect6_time32, int, n, fd_set __user *, inp, fd_set __user *, sigset_t __user *up = NULL; if (sig) { - if (!access_ok(VERIFY_READ, sig, sizeof(void *)+sizeof(size_t)) + if (!access_ok(sig, sizeof(void *)+sizeof(size_t)) || __get_user(up, (sigset_t __user * __user *)sig) || __get_user(sigsetsize, (size_t __user *)(sig+sizeof(void *)))) @@ -1368,7 +1365,7 @@ COMPAT_SYSCALL_DEFINE6(pselect6_time64, int, n, compat_ulong_t __user *, inp, compat_uptr_t up = 0; if (sig) { - if (!access_ok(VERIFY_READ, sig, + if (!access_ok(sig, sizeof(compat_uptr_t)+sizeof(compat_size_t)) || __get_user(up, (compat_uptr_t __user *)sig) || __get_user(sigsetsize, @@ -1390,7 +1387,7 @@ COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, compat_uptr_t up = 0; if (sig) { - if (!access_ok(VERIFY_READ, sig, + if (!access_ok(sig, sizeof(compat_uptr_t)+sizeof(compat_size_t)) || __get_user(up, (compat_uptr_t __user *)sig) || __get_user(sigsetsize, diff --git a/fs/super.c b/fs/super.c index ca53a08497ed..48e25eba8465 100644 --- a/fs/super.c +++ b/fs/super.c @@ -35,6 +35,7 @@ #include <linux/fsnotify.h> #include <linux/lockdep.h> #include <linux/user_namespace.h> +#include <uapi/linux/mount.h> #include "internal.h" static int thaw_super_locked(struct super_block *sb); @@ -1245,17 +1246,13 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data) { struct dentry *root; struct super_block *sb; - char *secdata = NULL; int error = -ENOMEM; + void *sec_opts = NULL; if (data && !(type->fs_flags & FS_BINARY_MOUNTDATA)) { - secdata = alloc_secdata(); - if (!secdata) - goto out; - - error = security_sb_copy_data(data, secdata); + error = security_sb_eat_lsm_opts(data, &sec_opts); if (error) - goto out_free_secdata; + return ERR_PTR(error); } root = type->mount(type, flags, name, data); @@ -1276,10 +1273,16 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data) smp_wmb(); sb->s_flags |= SB_BORN; - error = security_sb_kern_mount(sb, flags, secdata); + error = security_sb_set_mnt_opts(sb, sec_opts, 0, NULL); if (error) goto out_sb; + if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT))) { + error = security_sb_kern_mount(sb); + if (error) + goto out_sb; + } + /* * filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE * but s_maxbytes was an unsigned long long for many releases. Throw @@ -1290,14 +1293,13 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data) "negative value (%lld)\n", type->name, sb->s_maxbytes); up_write(&sb->s_umount); - free_secdata(secdata); + security_free_mnt_opts(&sec_opts); return root; out_sb: dput(root); deactivate_locked_super(sb); out_free_secdata: - free_secdata(secdata); -out: + security_free_mnt_opts(&sec_opts); return ERR_PTR(error); } diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index feeae8081c22..aa85f2874a9f 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -43,7 +43,8 @@ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) kuid_t uid; kgid_t gid; - BUG_ON(!kobj); + if (WARN_ON(!kobj)) + return -EINVAL; if (kobj->parent) parent = kobj->parent->sd; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index bb71db63c99c..51398457fe00 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -325,7 +325,8 @@ int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, kuid_t uid; kgid_t gid; - BUG_ON(!kobj || !kobj->sd || !attr); + if (WARN_ON(!kobj || !kobj->sd || !attr)) + return -EINVAL; kobject_get_ownership(kobj, &uid, &gid); return sysfs_add_file_mode_ns(kobj->sd, attr, false, attr->mode, @@ -537,7 +538,8 @@ int sysfs_create_bin_file(struct kobject *kobj, kuid_t uid; kgid_t gid; - BUG_ON(!kobj || !kobj->sd || !attr); + if (WARN_ON(!kobj || !kobj->sd || !attr)) + return -EINVAL; kobject_get_ownership(kobj, &uid, &gid); return sysfs_add_file_mode_ns(kobj->sd, &attr->attr, true, diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index 1eb2d6307663..57038604d4a8 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -112,7 +112,8 @@ static int internal_create_group(struct kobject *kobj, int update, kgid_t gid; int error; - BUG_ON(!kobj || (!update && !kobj->sd)); + if (WARN_ON(!kobj || (!update && !kobj->sd))) + return -EINVAL; /* Updates may happen before the object has been instantiated */ if (unlikely(update && !kobj->sd)) diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c index 215c225b2ca1..c4deecc80f67 100644 --- a/fs/sysfs/symlink.c +++ b/fs/sysfs/symlink.c @@ -23,7 +23,8 @@ static int sysfs_do_create_link_sd(struct kernfs_node *parent, { struct kernfs_node *kn, *target = NULL; - BUG_ON(!name || !parent); + if (WARN_ON(!name || !parent)) + return -EINVAL; /* * We don't own @target_kobj and it may be removed at any time. diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index b21ea2ba768d..eedc5e0156ff 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1992,7 +1992,6 @@ xfs_buf_delwri_submit_buffers( struct list_head *wait_list) { struct xfs_buf *bp, *n; - LIST_HEAD (submit_list); int pinned = 0; struct blk_plug plug; diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index ec2e63a7963b..f3ef70c542e1 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -40,7 +40,6 @@ xfs_growfs_data_private( xfs_rfsblock_t new; xfs_agnumber_t oagcount; xfs_trans_t *tp; - LIST_HEAD (buffer_list); struct aghdr_init_data id = {}; nb = in->newblocks; |