diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2018-03-05 14:47:15 +1100 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2018-03-05 14:47:16 +1100 |
commit | 49d0908ae49e19096d53d3531bfeebb1c371eed5 (patch) | |
tree | 86638cb3b7eaca70656679437eab48f0ac2976d6 /fs | |
parent | 5201c8ba75ccb0056bc72523fdb7d29e6edf6e17 (diff) | |
parent | 9ec53107cdd9d0bf59add6e0f186290ed5ff5f93 (diff) | |
download | linux-next-49d0908ae49e19096d53d3531bfeebb1c371eed5.tar.gz |
Merge branch 'akpm-current/current'
Diffstat (limited to 'fs')
42 files changed, 536 insertions, 496 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index bc821a86d965..8b344110b2cd 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -203,6 +203,9 @@ config HUGETLBFS config HUGETLB_PAGE def_bool HUGETLBFS +config MEMFD_CREATE + def_bool TMPFS || HUGETLBFS + config ARCH_HAS_GIGANTIC_PAGE bool diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index ce1824f47ba6..c3deb2e35f20 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -330,6 +330,7 @@ beyond_if: #ifdef __alpha__ regs->gp = ex.a_gpvalue; #endif + finalize_exec(bprm); start_thread(regs, ex.a_entry, current->mm->start_stack); return 0; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index bdb201230bae..41e04183e4ce 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -377,6 +377,11 @@ static unsigned long elf_map(struct file *filep, unsigned long addr, } else map_addr = vm_mmap(filep, addr, size, prot, type, off); + if ((type & MAP_FIXED_NOREPLACE) && BAD_ADDR(map_addr)) + pr_info("%d (%s): Uhuuh, elf segment at %p requested but the memory is mapped already\n", + task_pid_nr(current), current->comm, + (void *)addr); + return(map_addr); } @@ -575,7 +580,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, elf_prot |= PROT_EXEC; vaddr = eppnt->p_vaddr; if (interp_elf_ex->e_type == ET_EXEC || load_addr_set) - elf_type |= MAP_FIXED; + elf_type |= MAP_FIXED_NOREPLACE; else if (no_base && interp_elf_ex->e_type == ET_DYN) load_addr = -vaddr; @@ -890,7 +895,7 @@ static int load_elf_binary(struct linux_binprm *bprm) the correct location in memory. */ for(i = 0, elf_ppnt = elf_phdata; i < loc->elf_ex.e_phnum; i++, elf_ppnt++) { - int elf_prot = 0, elf_flags; + int elf_prot = 0, elf_flags, elf_fixed = MAP_FIXED_NOREPLACE; unsigned long k, vaddr; unsigned long total_size = 0; @@ -922,6 +927,13 @@ static int load_elf_binary(struct linux_binprm *bprm) */ } } + + /* + * Some binaries have overlapping elf segments and then + * we have to forcefully map over an existing mapping + * e.g. over this newly established brk mapping. + */ + elf_fixed = MAP_FIXED; } if (elf_ppnt->p_flags & PF_R) @@ -939,7 +951,7 @@ static int load_elf_binary(struct linux_binprm *bprm) * the ET_DYN load_addr calculations, proceed normally. */ if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) { - elf_flags |= MAP_FIXED; + elf_flags |= elf_fixed; } else if (loc->elf_ex.e_type == ET_DYN) { /* * This logic is run once for the first LOAD Program @@ -975,7 +987,7 @@ static int load_elf_binary(struct linux_binprm *bprm) load_bias = ELF_ET_DYN_BASE; if (current->flags & PF_RANDOMIZE) load_bias += arch_mmap_rnd(); - elf_flags |= MAP_FIXED; + elf_flags |= elf_fixed; } else load_bias = 0; @@ -1155,6 +1167,7 @@ static int load_elf_binary(struct linux_binprm *bprm) ELF_PLAT_INIT(regs, reloc_func_desc); #endif + finalize_exec(bprm); start_thread(regs, elf_entry, bprm->p); retval = 0; out: @@ -1234,7 +1247,7 @@ static int load_elf_library(struct file *file) (eppnt->p_filesz + ELF_PAGEOFFSET(eppnt->p_vaddr)), PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE, + MAP_FIXED_NOREPLACE | MAP_PRIVATE | MAP_DENYWRITE, (eppnt->p_offset - ELF_PAGEOFFSET(eppnt->p_vaddr))); if (error != ELF_PAGESTART(eppnt->p_vaddr)) diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 429326b6e2e7..d90993adeffa 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -463,6 +463,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) dynaddr); #endif + finalize_exec(bprm); /* everything is now ready... get the userspace context ready to roll */ entryaddr = interp_params.entry_addr ?: exec_params.entry_addr; start_thread(regs, entryaddr, current->mm->start_stack); diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 5d6b94475f27..82a48e830018 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -994,6 +994,7 @@ static int load_flat_binary(struct linux_binprm *bprm) FLAT_PLAT_INIT(regs); #endif + finalize_exec(bprm); pr_debug("start_thread(regs=0x%p, entry=0x%lx, start_stack=0x%lx)\n", regs, start_addr, current->mm->start_stack); start_thread(regs, start_addr, current->mm->start_stack); diff --git a/fs/dcache.c b/fs/dcache.c index 7c38f39958bc..b3dc1870caa8 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -287,7 +287,8 @@ void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry spin_unlock(&dentry->d_lock); name->name = p->name; } else { - memcpy(name->inline_name, dentry->d_iname, DNAME_INLINE_LEN); + memcpy(name->inline_name, dentry->d_iname, + dentry->d_name.len + 1); spin_unlock(&dentry->d_lock); name->name = name->inline_name; } diff --git a/fs/exec.c b/fs/exec.c index 7eb8d21bcab9..08940af394da 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -257,7 +257,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, * to work from. */ limit = _STK_LIM / 4 * 3; - limit = min(limit, rlimit(RLIMIT_STACK) / 4); + limit = min(limit, bprm->rlim_stack.rlim_cur / 4); if (size > limit) goto fail; } @@ -411,6 +411,11 @@ static int bprm_mm_init(struct linux_binprm *bprm) if (!mm) goto err; + /* Save current stack limit for all calculations made during exec. */ + task_lock(current->group_leader); + bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK]; + task_unlock(current->group_leader); + err = __bprm_mm_init(bprm); if (err) goto err; @@ -697,7 +702,7 @@ int setup_arg_pages(struct linux_binprm *bprm, #ifdef CONFIG_STACK_GROWSUP /* Limit stack size */ - stack_base = rlimit_max(RLIMIT_STACK); + stack_base = bprm->rlim_stack.rlim_max; if (stack_base > STACK_SIZE_MAX) stack_base = STACK_SIZE_MAX; @@ -770,7 +775,7 @@ int setup_arg_pages(struct linux_binprm *bprm, * Align this down to a page boundary as expand_stack * will align it up. */ - rlim_stack = rlimit(RLIMIT_STACK) & PAGE_MASK; + rlim_stack = bprm->rlim_stack.rlim_cur & PAGE_MASK; #ifdef CONFIG_STACK_GROWSUP if (stack_size + stack_expand > rlim_stack) stack_base = vma->vm_start + rlim_stack; @@ -1333,6 +1338,7 @@ void setup_new_exec(struct linux_binprm * bprm) if (bprm->secureexec) { /* Make sure parent cannot signal privileged process. */ current->pdeath_signal = 0; + current->signal->pdeath_signal_proc = 0; /* * For secureexec, reset the stack limit to sane default to @@ -1341,11 +1347,11 @@ void setup_new_exec(struct linux_binprm * bprm) * RLIMIT_STACK, but after the point of no return to avoid * needing to clean up the change on failure. */ - if (current->signal->rlim[RLIMIT_STACK].rlim_cur > _STK_LIM) - current->signal->rlim[RLIMIT_STACK].rlim_cur = _STK_LIM; + if (bprm->rlim_stack.rlim_cur > _STK_LIM) + bprm->rlim_stack.rlim_cur = _STK_LIM; } - arch_pick_mmap_layout(current->mm); + arch_pick_mmap_layout(current->mm, &bprm->rlim_stack); current->sas_ss_sp = current->sas_ss_size = 0; @@ -1378,6 +1384,16 @@ void setup_new_exec(struct linux_binprm * bprm) } EXPORT_SYMBOL(setup_new_exec); +/* Runs immediately before start_thread() takes over. */ +void finalize_exec(struct linux_binprm *bprm) +{ + /* Store any stack rlimit changes before starting thread. */ + task_lock(current->group_leader); + current->signal->rlim[RLIMIT_STACK] = bprm->rlim_stack; + task_unlock(current->group_leader); +} +EXPORT_SYMBOL(finalize_exec); + /* * Prepare credentials and lock ->cred_guard_mutex. * install_exec_creds() commits the new creds and drops the lock. diff --git a/fs/fcntl.c b/fs/fcntl.c index 1e97f1fda90c..df113f65a2a1 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -23,7 +23,7 @@ #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> -#include <linux/shmem_fs.h> +#include <linux/memfd.h> #include <linux/compat.h> #include <linux/poll.h> diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index 63a1ca4b9dee..eb5c41284649 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -384,8 +384,9 @@ out_err: static int __init dnotify_init(void) { - dnotify_struct_cache = KMEM_CACHE(dnotify_struct, SLAB_PANIC); - dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC); + dnotify_struct_cache = KMEM_CACHE(dnotify_struct, + SLAB_PANIC|SLAB_ACCOUNT); + dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops); if (IS_ERR(dnotify_group)) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index d51e1bb781cf..01d1df207047 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -157,14 +157,16 @@ struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group, if (fanotify_is_perm_event(mask)) { struct fanotify_perm_event_info *pevent; - pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp); + pevent = kmem_cache_alloc_memcg(fanotify_perm_event_cachep, + gfp, group->memcg); if (!pevent) return NULL; event = &pevent->fae; pevent->response = 0; goto init; } - event = kmem_cache_alloc(fanotify_event_cachep, gfp); + event = kmem_cache_alloc_memcg(fanotify_event_cachep, gfp, + group->memcg); if (!event) return NULL; init: __maybe_unused diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 72e367822efb..6015bbaaa319 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -16,6 +16,7 @@ #include <linux/uaccess.h> #include <linux/compat.h> #include <linux/sched/signal.h> +#include <linux/memcontrol.h> #include <asm/ioctls.h> @@ -756,6 +757,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) group->fanotify_data.user = user; atomic_inc(&user->fanotify_listeners); + group->memcg = get_mem_cgroup_from_mm(current->mm); oevent = fanotify_alloc_event(group, NULL, FS_Q_OVERFLOW, NULL); if (unlikely(!oevent)) { @@ -951,7 +953,8 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark, */ static int __init fanotify_user_setup(void) { - fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC); + fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, + SLAB_PANIC|SLAB_ACCOUNT); fanotify_event_cachep = KMEM_CACHE(fanotify_event_info, SLAB_PANIC); if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) { fanotify_perm_event_cachep = diff --git a/fs/notify/group.c b/fs/notify/group.c index b7a4b6a69efa..3e56459f4773 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -22,6 +22,7 @@ #include <linux/srcu.h> #include <linux/rculist.h> #include <linux/wait.h> +#include <linux/memcontrol.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" @@ -36,6 +37,9 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) if (group->ops->free_group_priv) group->ops->free_group_priv(group); + if (group->memcg) + mem_cgroup_put(group->memcg); + kfree(group); } diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 40dedb37a1f3..b184bff93d02 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -98,7 +98,7 @@ int inotify_handle_event(struct fsnotify_group *group, i_mark = container_of(inode_mark, struct inotify_inode_mark, fsn_mark); - event = kmalloc(alloc_len, GFP_KERNEL); + event = kmalloc_memcg(alloc_len, GFP_KERNEL, group->memcg); if (unlikely(!event)) { /* * Treat lost event due to ENOMEM the same way as queue diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 8f17719842ec..d9e4b243c973 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -38,6 +38,7 @@ #include <linux/uaccess.h> #include <linux/poll.h> #include <linux/wait.h> +#include <linux/memcontrol.h> #include "inotify.h" #include "../fdinfo.h" @@ -632,6 +633,7 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events) oevent->name_len = 0; group->max_events = max_events; + group->memcg = get_mem_cgroup_from_mm(current->mm); spin_lock_init(&group->inotify_data.idr_lock); idr_init(&group->inotify_data.idr); @@ -799,7 +801,8 @@ static int __init inotify_user_setup(void) BUG_ON(hweight32(ALL_INOTIFY_BITS) != 21); - inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark, SLAB_PANIC); + inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark, + SLAB_PANIC|SLAB_ACCOUNT); inotify_max_queued_events = 16384; init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128; diff --git a/fs/notify/mark.c b/fs/notify/mark.c index e9191b416434..c0014d0c3783 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -432,7 +432,8 @@ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) static int fsnotify_attach_connector_to_object( struct fsnotify_mark_connector __rcu **connp, struct inode *inode, - struct vfsmount *mnt) + struct vfsmount *mnt, + struct fsnotify_group *group) { struct fsnotify_mark_connector *conn; @@ -517,7 +518,8 @@ restart: conn = fsnotify_grab_connector(connp); if (!conn) { spin_unlock(&mark->lock); - err = fsnotify_attach_connector_to_object(connp, inode, mnt); + err = fsnotify_attach_connector_to_object(connp, inode, mnt, + mark->group); if (err) return err; goto restart; diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 9a876bb07cac..0f157bbd3e0f 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -7119,7 +7119,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, goto out_commit; did_quota = 1; - data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv; + data_ac->ac_resv = &oi->ip_la_data_resv; ret = ocfs2_claim_clusters(handle, data_ac, 1, &bit_off, &num); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index e8e205bf2e41..302cd7caa4a7 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -346,7 +346,7 @@ static int ocfs2_readpage(struct file *file, struct page *page) unlock = 0; out_alloc: - up_read(&OCFS2_I(inode)->ip_alloc_sem); + up_read(&oi->ip_alloc_sem); out_inode_unlock: ocfs2_inode_unlock(inode, 0); out: @@ -2213,7 +2213,7 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, down_write(&oi->ip_alloc_sem); if (first_get_block) { - if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) + if (ocfs2_sparse_alloc(osb)) ret = ocfs2_zero_tail(inode, di_bh, pos); else ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index 8614ff069d99..3494a62ed749 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -78,7 +78,7 @@ static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level) /* * Using a named enum representing lock types in terms of #N bit stored in * iocb->private, which is going to be used for communication between - * ocfs2_dio_end_io() and ocfs2_file_aio_write/read(). + * ocfs2_dio_end_io() and ocfs2_file_write/read_iter(). */ enum ocfs2_iocb_lock_bits { OCFS2_IOCB_RW_LOCK = 0, diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 977763d4c27d..b048d4fa3959 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -3072,7 +3072,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, * We need to return the correct block within the * cluster which should hold our entry. */ - off = ocfs2_dx_dir_hash_idx(OCFS2_SB(dir->i_sb), + off = ocfs2_dx_dir_hash_idx(osb, &lookup->dl_hinfo); get_bh(dx_leaves[off]); lookup->dl_dx_leaf_bh = dx_leaves[off]; diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index e9f3705c4c9f..953c200e1c30 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -960,13 +960,10 @@ static inline int dlm_send_proxy_ast(struct dlm_ctxt *dlm, void dlm_print_one_lock_resource(struct dlm_lock_resource *res); void __dlm_print_one_lock_resource(struct dlm_lock_resource *res); -u8 dlm_nm_this_node(struct dlm_ctxt *dlm); void dlm_kick_thread(struct dlm_ctxt *dlm, struct dlm_lock_resource *res); void __dlm_dirty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res); -int dlm_nm_init(struct dlm_ctxt *dlm); -int dlm_heartbeat_init(struct dlm_ctxt *dlm); void dlm_hb_node_down_cb(struct o2nm_node *node, int idx, void *data); void dlm_hb_node_up_cb(struct o2nm_node *node, int idx, void *data); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 9479f99c2145..7be6908251bc 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -1756,8 +1756,7 @@ int ocfs2_rw_lock(struct inode *inode, int write) level = write ? DLM_LOCK_EX : DLM_LOCK_PR; - status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres, level, 0, - 0); + status = ocfs2_cluster_lock(osb, lockres, level, 0, 0); if (status < 0) mlog_errno(status); @@ -1796,7 +1795,7 @@ void ocfs2_rw_unlock(struct inode *inode, int write) write ? "EXMODE" : "PRMODE"); if (!ocfs2_mount_local(osb)) - ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level); + ocfs2_cluster_unlock(osb, lockres, level); } /* @@ -1816,8 +1815,7 @@ int ocfs2_open_lock(struct inode *inode) lockres = &OCFS2_I(inode)->ip_open_lockres; - status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres, - DLM_LOCK_PR, 0, 0); + status = ocfs2_cluster_lock(osb, lockres, DLM_LOCK_PR, 0, 0); if (status < 0) mlog_errno(status); @@ -1854,8 +1852,7 @@ int ocfs2_try_open_lock(struct inode *inode, int write) * other nodes and the -EAGAIN will indicate to the caller that * this inode is still in use. */ - status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres, - level, DLM_LKF_NOQUEUE, 0); + status = ocfs2_cluster_lock(osb, lockres, level, DLM_LKF_NOQUEUE, 0); out: return status; @@ -1876,11 +1873,9 @@ void ocfs2_open_unlock(struct inode *inode) goto out; if(lockres->l_ro_holders) - ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, - DLM_LOCK_PR); + ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_PR); if(lockres->l_ex_holders) - ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, - DLM_LOCK_EX); + ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_EX); out: return; @@ -2601,9 +2596,9 @@ void ocfs2_inode_unlock(struct inode *inode, (unsigned long long)OCFS2_I(inode)->ip_blkno, ex ? "EXMODE" : "PRMODE"); - if (!ocfs2_is_hard_readonly(OCFS2_SB(inode->i_sb)) && + if (!ocfs2_is_hard_readonly(osb) && !ocfs2_mount_local(osb)) - ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level); + ocfs2_cluster_unlock(osb, lockres, level); } /* @@ -3539,7 +3534,7 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb, * we can recover correctly from node failure. Otherwise, we may get * invalid LVB in LKB, but without DLM_SBF_VALNOTVALID being set. */ - if (!ocfs2_is_o2cb_active() && + if (ocfs2_userspace_stack(osb) && lockres->l_ops->flags & LOCK_TYPE_USES_LVB) lvb = 1; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 5d1784a365a3..6ee94bc23f5b 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -101,7 +101,7 @@ static int ocfs2_file_open(struct inode *inode, struct file *file) struct ocfs2_inode_info *oi = OCFS2_I(inode); trace_ocfs2_file_open(inode, file, file->f_path.dentry, - (unsigned long long)OCFS2_I(inode)->ip_blkno, + (unsigned long long)oi->ip_blkno, file->f_path.dentry->d_name.len, file->f_path.dentry->d_name.name, mode); @@ -116,7 +116,7 @@ static int ocfs2_file_open(struct inode *inode, struct file *file) /* Check that the inode hasn't been wiped from disk by another * node. If it hasn't then we're safe as long as we hold the * spin lock until our increment of open count. */ - if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_DELETED) { + if (oi->ip_flags & OCFS2_INODE_DELETED) { spin_unlock(&oi->ip_lock); status = -ENOENT; @@ -190,7 +190,7 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end, bool needs_barrier = false; trace_ocfs2_sync_file(inode, file, file->f_path.dentry, - OCFS2_I(inode)->ip_blkno, + oi->ip_blkno, file->f_path.dentry->d_name.len, file->f_path.dentry->d_name.name, (unsigned long long)datasync); @@ -296,7 +296,7 @@ int ocfs2_update_inode_atime(struct inode *inode, ocfs2_journal_dirty(handle, bh); out_commit: - ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle); + ocfs2_commit_trans(osb, handle); out: return ret; } @@ -2257,7 +2257,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb, int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0; int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0; - trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry, + trace_ocfs2_file_write_iter(inode, file, file->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, file->f_path.dentry->d_name.len, file->f_path.dentry->d_name.name, @@ -2405,7 +2405,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0; int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0; - trace_ocfs2_file_aio_read(inode, filp, filp->f_path.dentry, + trace_ocfs2_file_read_iter(inode, filp, filp->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, filp->f_path.dentry->d_name.len, filp->f_path.dentry->d_name.name, @@ -2448,7 +2448,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, * * Take and drop the meta data lock to update inode fields * like i_size. This allows the checks down below - * generic_file_aio_read() a chance of actually working. + * generic_file_read_iter() a chance of actually working. */ ret = ocfs2_inode_lock_atime(inode, filp->f_path.mnt, &lock_level, !nowait); @@ -2460,7 +2460,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, ocfs2_inode_unlock(inode, lock_level); ret = generic_file_read_iter(iocb, to); - trace_generic_file_aio_read_ret(ret); + trace_generic_file_read_iter_ret(ret); /* buffered aio wouldn't have proper lock coverage today */ BUG_ON(ret == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT)); diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c index e87279e49ba3..f65f2b2f594d 100644 --- a/fs/ocfs2/filecheck.c +++ b/fs/ocfs2/filecheck.c @@ -53,36 +53,6 @@ static const char * const ocfs2_filecheck_errs[] = { "UNSUPPORTED" }; -static DEFINE_SPINLOCK(ocfs2_filecheck_sysfs_lock); -static LIST_HEAD(ocfs2_filecheck_sysfs_list); - -struct ocfs2_filecheck { - struct list_head fc_head; /* File check entry list head */ - spinlock_t fc_lock; - unsigned int fc_max; /* Maximum number of entry in list */ - unsigned int fc_size; /* Current entry count in list */ - unsigned int fc_done; /* Finished entry count in list */ -}; - -struct ocfs2_filecheck_sysfs_entry { /* sysfs entry per mounting */ - struct list_head fs_list; - atomic_t fs_count; - struct super_block *fs_sb; - struct kset *fs_devicekset; - struct kset *fs_fcheckkset; - struct ocfs2_filecheck *fs_fcheck; -}; - -#define OCFS2_FILECHECK_MAXSIZE 100 -#define OCFS2_FILECHECK_MINSIZE 10 - -/* File check operation type */ -enum { - OCFS2_FILECHECK_TYPE_CHK = 0, /* Check a file(inode) */ - OCFS2_FILECHECK_TYPE_FIX, /* Fix a file(inode) */ - OCFS2_FILECHECK_TYPE_SET = 100 /* Set entry list maximum size */ -}; - struct ocfs2_filecheck_entry { struct list_head fe_list; unsigned long fe_ino; @@ -110,34 +80,84 @@ ocfs2_filecheck_error(int errno) return ocfs2_filecheck_errs[errno - OCFS2_FILECHECK_ERR_START + 1]; } -static ssize_t ocfs2_filecheck_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf); -static ssize_t ocfs2_filecheck_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count); -static struct kobj_attribute ocfs2_attr_filecheck_chk = +static ssize_t ocfs2_filecheck_attr_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf); +static ssize_t ocfs2_filecheck_attr_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count); +static struct kobj_attribute ocfs2_filecheck_attr_chk = __ATTR(check, S_IRUSR | S_IWUSR, - ocfs2_filecheck_show, - ocfs2_filecheck_store); -static struct kobj_attribute ocfs2_attr_filecheck_fix = + ocfs2_filecheck_attr_show, + ocfs2_filecheck_attr_store); +static struct kobj_attribute ocfs2_filecheck_attr_fix = __ATTR(fix, S_IRUSR | S_IWUSR, - ocfs2_filecheck_show, - ocfs2_filecheck_store); -static struct kobj_attribute ocfs2_attr_filecheck_set = + ocfs2_filecheck_attr_show, + ocfs2_filecheck_attr_store); +static struct kobj_attribute ocfs2_filecheck_attr_set = __ATTR(set, S_IRUSR | S_IWUSR, - ocfs2_filecheck_show, - ocfs2_filecheck_store); + ocfs2_filecheck_attr_show, + ocfs2_filecheck_attr_store); +static struct attribute *ocfs2_filecheck_attrs[] = { + &ocfs2_filecheck_attr_chk.attr, + &ocfs2_filecheck_attr_fix.attr, + &ocfs2_filecheck_attr_set.attr, + NULL +}; + +static void ocfs2_filecheck_release(struct kobject *kobj) +{ + struct ocfs2_filecheck_sysfs_entry *entry = container_of(kobj, + struct ocfs2_filecheck_sysfs_entry, fs_kobj); + + complete(&entry->fs_kobj_unregister); +} + +static ssize_t +ocfs2_filecheck_show(struct kobject *kobj, struct attribute *attr, char *buf) +{ + ssize_t ret = -EIO; + struct kobj_attribute *kattr = container_of(attr, + struct kobj_attribute, attr); + + kobject_get(kobj); + if (kattr->show) + ret = kattr->show(kobj, kattr, buf); + kobject_put(kobj); + return ret; +} + +static ssize_t +ocfs2_filecheck_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + ssize_t ret = -EIO; + struct kobj_attribute *kattr = container_of(attr, + struct kobj_attribute, attr); + + kobject_get(kobj); + if (kattr->store) + ret = kattr->store(kobj, kattr, buf, count); + kobject_put(kobj); + return ret; +} + +static const struct sysfs_ops ocfs2_filecheck_ops = { + .show = ocfs2_filecheck_show, + .store = ocfs2_filecheck_store, +}; + +static struct kobj_type ocfs2_ktype_filecheck = { + .default_attrs = ocfs2_filecheck_attrs, + .sysfs_ops = &ocfs2_filecheck_ops, + .release = ocfs2_filecheck_release, +}; static void ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry) { struct ocfs2_filecheck_entry *p; - if (!atomic_dec_and_test(&entry->fs_count)) - wait_on_atomic_t(&entry->fs_count, atomic_t_wait, - TASK_UNINTERRUPTIBLE); - spin_lock(&entry->fs_fcheck->fc_lock); while (!list_empty(&entry->fs_fcheck->fc_head)) { p = list_first_entry(&entry->fs_fcheck->fc_head, @@ -148,151 +168,48 @@ ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry) } spin_unlock(&entry->fs_fcheck->fc_lock); - kset_unregister(entry->fs_fcheckkset); - kset_unregister(entry->fs_devicekset); kfree(entry->fs_fcheck); - kfree(entry); -} - -static void -ocfs2_filecheck_sysfs_add(struct ocfs2_filecheck_sysfs_entry *entry) -{ - spin_lock(&ocfs2_filecheck_sysfs_lock); - list_add_tail(&entry->fs_list, &ocfs2_filecheck_sysfs_list); - spin_unlock(&ocfs2_filecheck_sysfs_lock); + entry->fs_fcheck = NULL; } -static int ocfs2_filecheck_sysfs_del(const char *devname) +int ocfs2_filecheck_create_sysfs(struct ocfs2_super *osb) { - struct ocfs2_filecheck_sysfs_entry *p; - - spin_lock(&ocfs2_filecheck_sysfs_lock); - list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) { - if (!strcmp(p->fs_sb->s_id, devname)) { - list_del(&p->fs_list); - spin_unlock(&ocfs2_filecheck_sysfs_lock); - ocfs2_filecheck_sysfs_free(p); - return 0; - } - } - spin_unlock(&ocfs2_filecheck_sysfs_lock); - return 1; -} - -static void -ocfs2_filecheck_sysfs_put(struct ocfs2_filecheck_sysfs_entry *entry) -{ - if (atomic_dec_and_test(&entry->fs_count)) - wake_up_atomic_t(&entry->fs_count); -} - -static struct ocfs2_filecheck_sysfs_entry * -ocfs2_filecheck_sysfs_get(const char *devname) -{ - struct ocfs2_filecheck_sysfs_entry *p = NULL; - - spin_lock(&ocfs2_filecheck_sysfs_lock); - list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) { - if (!strcmp(p->fs_sb->s_id, devname)) { - atomic_inc(&p->fs_count); - spin_unlock(&ocfs2_filecheck_sysfs_lock); - return p; - } - } - spin_unlock(&ocfs2_filecheck_sysfs_lock); - return NULL; -} - -int ocfs2_filecheck_create_sysfs(struct super_block *sb) -{ - int ret = 0; - struct kset *device_kset = NULL; - struct kset *fcheck_kset = NULL; - struct ocfs2_filecheck *fcheck = NULL; - struct ocfs2_filecheck_sysfs_entry *entry = NULL; - struct attribute **attrs = NULL; - struct attribute_group attrgp; - - if (!ocfs2_kset) - return -ENOMEM; - - attrs = kmalloc(sizeof(struct attribute *) * 4, GFP_NOFS); - if (!attrs) { - ret = -ENOMEM; - goto error; - } else { - attrs[0] = &ocfs2_attr_filecheck_chk.attr; - attrs[1] = &ocfs2_attr_filecheck_fix.attr; - attrs[2] = &ocfs2_attr_filecheck_set.attr; - attrs[3] = NULL; - memset(&attrgp, 0, sizeof(attrgp)); - attrgp.attrs = attrs; - } + int ret; + struct ocfs2_filecheck *fcheck; + struct ocfs2_filecheck_sysfs_entry *entry = &osb->osb_fc_ent; fcheck = kmalloc(sizeof(struct ocfs2_filecheck), GFP_NOFS); - if (!fcheck) { - ret = -ENOMEM; - goto error; - } else { - INIT_LIST_HEAD(&fcheck->fc_head); - spin_lock_init(&fcheck->fc_lock); - fcheck->fc_max = OCFS2_FILECHECK_MINSIZE; - fcheck->fc_size = 0; - fcheck->fc_done = 0; - } - - if (strlen(sb->s_id) <= 0) { - mlog(ML_ERROR, - "Cannot get device basename when create filecheck sysfs\n"); - ret = -ENODEV; - goto error; - } - - device_kset = kset_create_and_add(sb->s_id, NULL, &ocfs2_kset->kobj); - if (!device_kset) { - ret = -ENOMEM; - goto error; - } + if (!fcheck) + return -ENOMEM; - fcheck_kset = kset_create_and_add("filecheck", NULL, - &device_kset->kobj); - if (!fcheck_kset) { - ret = -ENOMEM; - goto error; + INIT_LIST_HEAD(&fcheck->fc_head); + spin_lock_init(&fcheck->fc_lock); + fcheck->fc_max = OCFS2_FILECHECK_MINSIZE; + fcheck->fc_size = 0; + fcheck->fc_done = 0; + + entry->fs_kobj.kset = osb->osb_dev_kset; + init_completion(&entry->fs_kobj_unregister); + ret = kobject_init_and_add(&entry->fs_kobj, &ocfs2_ktype_filecheck, + NULL, "filecheck"); + if (ret) { + kfree(fcheck); + return ret; } - ret = sysfs_create_group(&fcheck_kset->kobj, &attrgp); - if (ret) - goto error; - - entry = kmalloc(sizeof(struct ocfs2_filecheck_sysfs_entry), GFP_NOFS); - if (!entry) { - ret = -ENOMEM; - goto error; - } else { - atomic_set(&entry->fs_count, 1); - entry->fs_sb = sb; - entry->fs_devicekset = device_kset; - entry->fs_fcheckkset = fcheck_kset; - entry->fs_fcheck = fcheck; - ocfs2_filecheck_sysfs_add(entry); - } - - kfree(attrs); + entry->fs_fcheck = fcheck; return 0; - -error: - kfree(attrs); - kfree(entry); - kfree(fcheck); - kset_unregister(fcheck_kset); - kset_unregister(device_kset); - return ret; } -int ocfs2_filecheck_remove_sysfs(struct super_block *sb) +void ocfs2_filecheck_remove_sysfs(struct ocfs2_super *osb) { - return ocfs2_filecheck_sysfs_del(sb->s_id); + if (!osb->osb_fc_ent.fs_fcheck) + return; + + kobject_del(&osb->osb_fc_ent.fs_kobj); + kobject_put(&osb->osb_fc_ent.fs_kobj); + wait_for_completion(&osb->osb_fc_ent.fs_kobj_unregister); + ocfs2_filecheck_sysfs_free(&osb->osb_fc_ent); } static int @@ -309,7 +226,7 @@ ocfs2_filecheck_adjust_max(struct ocfs2_filecheck_sysfs_entry *ent, spin_lock(&ent->fs_fcheck->fc_lock); if (len < (ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done)) { - mlog(ML_ERROR, + mlog(ML_NOTICE, "Cannot set online file check maximum entry number " "to %u due to too many pending entries(%u)\n", len, ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done); @@ -386,7 +303,7 @@ ocfs2_filecheck_args_parse(const char *name, const char *buf, size_t count, return 0; } -static ssize_t ocfs2_filecheck_show(struct kobject *kobj, +static ssize_t ocfs2_filecheck_attr_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -394,19 +311,12 @@ static ssize_t ocfs2_filecheck_show(struct kobject *kobj, ssize_t ret = 0, total = 0, remain = PAGE_SIZE; unsigned int type; struct ocfs2_filecheck_entry *p; - struct ocfs2_filecheck_sysfs_entry *ent; + struct ocfs2_filecheck_sysfs_entry *ent = container_of(kobj, + struct ocfs2_filecheck_sysfs_entry, fs_kobj); if (ocfs2_filecheck_type_parse(attr->attr.name, &type)) return -EINVAL; - ent = ocfs2_filecheck_sysfs_get(kobj->parent->name); - if (!ent) { - mlog(ML_ERROR, - "Cannot get the corresponding entry via device basename %s\n", - kobj->name); - return -ENODEV; - } - if (type == OCFS2_FILECHECK_TYPE_SET) { spin_lock(&ent->fs_fcheck->fc_lock); total = snprintf(buf, remain, "%u\n", ent->fs_fcheck->fc_max); @@ -440,11 +350,26 @@ static ssize_t ocfs2_filecheck_show(struct kobject *kobj, spin_unlock(&ent->fs_fcheck->fc_lock); exit: - ocfs2_filecheck_sysfs_put(ent); return total; } -static int +static inline int +ocfs2_filecheck_is_dup_entry(struct ocfs2_filecheck_sysfs_entry *ent, + unsigned long ino) +{ + struct ocfs2_filecheck_entry *p; + + list_for_each_entry(p, &ent->fs_fcheck->fc_head, fe_list) { + if (!p->fe_done) { + if (p->fe_ino == ino) + return 1; + } + } + + return 0; +} + +static inline int ocfs2_filecheck_erase_entry(struct ocfs2_filecheck_sysfs_entry *ent) { struct ocfs2_filecheck_entry *p; @@ -483,21 +408,21 @@ static void ocfs2_filecheck_done_entry(struct ocfs2_filecheck_sysfs_entry *ent, struct ocfs2_filecheck_entry *entry) { - entry->fe_done = 1; spin_lock(&ent->fs_fcheck->fc_lock); + entry->fe_done = 1; ent->fs_fcheck->fc_done++; spin_unlock(&ent->fs_fcheck->fc_lock); } static unsigned int -ocfs2_filecheck_handle(struct super_block *sb, +ocfs2_filecheck_handle(struct ocfs2_super *osb, unsigned long ino, unsigned int flags) { unsigned int ret = OCFS2_FILECHECK_ERR_SUCCESS; struct inode *inode = NULL; int rc; - inode = ocfs2_iget(OCFS2_SB(sb), ino, flags, 0); + inode = ocfs2_iget(osb, ino, flags, 0); if (IS_ERR(inode)) { rc = (int)(-(long)inode); if (rc >= OCFS2_FILECHECK_ERR_START && @@ -515,11 +440,14 @@ static void ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent, struct ocfs2_filecheck_entry *entry) { + struct ocfs2_super *osb = container_of(ent, struct ocfs2_super, + osb_fc_ent); + if (entry->fe_type == OCFS2_FILECHECK_TYPE_CHK) - entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb, + entry->fe_status = ocfs2_filecheck_handle(osb, entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_CHK); else if (entry->fe_type == OCFS2_FILECHECK_TYPE_FIX) - entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb, + entry->fe_status = ocfs2_filecheck_handle(osb, entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_FIX); else entry->fe_status = OCFS2_FILECHECK_ERR_UNSUPPORTED; @@ -527,30 +455,21 @@ ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent, ocfs2_filecheck_done_entry(ent, entry); } -static ssize_t ocfs2_filecheck_store(struct kobject *kobj, +static ssize_t ocfs2_filecheck_attr_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { + ssize_t ret = 0; struct ocfs2_filecheck_args args; struct ocfs2_filecheck_entry *entry; - struct ocfs2_filecheck_sysfs_entry *ent; - ssize_t ret = 0; + struct ocfs2_filecheck_sysfs_entry *ent = container_of(kobj, + struct ocfs2_filecheck_sysfs_entry, fs_kobj); if (count == 0) return count; - if (ocfs2_filecheck_args_parse(attr->attr.name, buf, count, &args)) { - mlog(ML_ERROR, "Invalid arguments for online file check\n"); + if (ocfs2_filecheck_args_parse(attr->attr.name, buf, count, &args)) return -EINVAL; - } - - ent = ocfs2_filecheck_sysfs_get(kobj->parent->name); - if (!ent) { - mlog(ML_ERROR, - "Cannot get the corresponding entry via device basename %s\n", - kobj->parent->name); - return -ENODEV; - } if (args.fa_type == OCFS2_FILECHECK_TYPE_SET) { ret = ocfs2_filecheck_adjust_max(ent, args.fa_len); @@ -564,13 +483,16 @@ static ssize_t ocfs2_filecheck_store(struct kobject *kobj, } spin_lock(&ent->fs_fcheck->fc_lock); - if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) && - (ent->fs_fcheck->fc_done == 0)) { - mlog(ML_ERROR, + if (ocfs2_filecheck_is_dup_entry(ent, args.fa_ino)) { + ret = -EEXIST; + kfree(entry); + } else if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) && + (ent->fs_fcheck->fc_done == 0)) { + mlog(ML_NOTICE, "Cannot do more file check " "since file check queue(%u) is full now\n", ent->fs_fcheck->fc_max); - ret = -EBUSY; + ret = -EAGAIN; kfree(entry); } else { if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) && @@ -595,6 +517,5 @@ static ssize_t ocfs2_filecheck_store(struct kobject *kobj, ocfs2_filecheck_handle_entry(ent, entry); exit: - ocfs2_filecheck_sysfs_put(ent); return (!ret ? count : ret); } diff --git a/fs/ocfs2/filecheck.h b/fs/ocfs2/filecheck.h index e5cd002a2c09..6a22ee79e8d0 100644 --- a/fs/ocfs2/filecheck.h +++ b/fs/ocfs2/filecheck.h @@ -43,7 +43,32 @@ enum { #define OCFS2_FILECHECK_ERR_START OCFS2_FILECHECK_ERR_FAILED #define OCFS2_FILECHECK_ERR_END OCFS2_FILECHECK_ERR_UNSUPPORTED -int ocfs2_filecheck_create_sysfs(struct super_block *sb); -int ocfs2_filecheck_remove_sysfs(struct super_block *sb); +struct ocfs2_filecheck { + struct list_head fc_head; /* File check entry list head */ + spinlock_t fc_lock; + unsigned int fc_max; /* Maximum number of entry in list */ + unsigned int fc_size; /* Current entry count in list */ + unsigned int fc_done; /* Finished entry count in list */ +}; + +#define OCFS2_FILECHECK_MAXSIZE 100 +#define OCFS2_FILECHECK_MINSIZE 10 + +/* File check operation type */ +enum { + OCFS2_FILECHECK_TYPE_CHK = 0, /* Check a file(inode) */ + OCFS2_FILECHECK_TYPE_FIX, /* Fix a file(inode) */ + OCFS2_FILECHECK_TYPE_SET = 100 /* Set entry list maximum size */ +}; + +struct ocfs2_filecheck_sysfs_entry { /* sysfs entry per partition */ + struct kobject fs_kobj; + struct completion fs_kobj_unregister; + struct ocfs2_filecheck *fs_fcheck; +}; + + +int ocfs2_filecheck_create_sysfs(struct ocfs2_super *osb); +void ocfs2_filecheck_remove_sysfs(struct ocfs2_super *osb); #endif /* FILECHECK_H */ diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index d51b80edd972..ddc3e9470c87 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -1135,7 +1135,7 @@ static void ocfs2_clear_inode(struct inode *inode) trace_ocfs2_clear_inode((unsigned long long)oi->ip_blkno, inode->i_nlink); - mlog_bug_on_msg(OCFS2_SB(inode->i_sb) == NULL, + mlog_bug_on_msg(osb == NULL, "Inode=%lu\n", inode->i_ino); dquot_drop(inode); @@ -1150,7 +1150,7 @@ static void ocfs2_clear_inode(struct inode *inode) ocfs2_mark_lockres_freeing(osb, &oi->ip_inode_lockres); ocfs2_mark_lockres_freeing(osb, &oi->ip_open_lockres); - ocfs2_resv_discard(&OCFS2_SB(inode->i_sb)->osb_la_resmap, + ocfs2_resv_discard(&osb->osb_la_resmap, &oi->ip_la_data_resv); ocfs2_resv_init_once(&oi->ip_la_data_resv); @@ -1160,7 +1160,7 @@ static void ocfs2_clear_inode(struct inode *inode) * exception here are successfully wiped inodes - their * metadata can now be considered to be part of the system * inodes from which it came. */ - if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_DELETED)) + if (!(oi->ip_flags & OCFS2_INODE_DELETED)) ocfs2_checkpoint_inode(inode); mlog_bug_on_msg(!list_empty(&oi->ip_io_markers), @@ -1223,7 +1223,7 @@ static void ocfs2_clear_inode(struct inode *inode) * the journal is flushed before journal shutdown. Thus it is safe to * have inodes get cleaned up after journal shutdown. */ - jbd2_journal_release_jbd_inode(OCFS2_SB(inode->i_sb)->journal->j_journal, + jbd2_journal_release_jbd_inode(osb->journal->j_journal, &oi->ip_jinode); } diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index c801eddc4bf3..8dd6f703c819 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -525,7 +525,7 @@ static int __ocfs2_mknod_locked(struct inode *dir, * these are used by the support functions here and in * callers. */ inode->i_ino = ino_from_blkno(osb->sb, fe_blkno); - OCFS2_I(inode)->ip_blkno = fe_blkno; + oi->ip_blkno = fe_blkno; spin_lock(&osb->osb_lock); inode->i_generation = osb->s_next_generation++; spin_unlock(&osb->osb_lock); @@ -1186,8 +1186,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, } trace_ocfs2_double_lock_end( - (unsigned long long)OCFS2_I(inode1)->ip_blkno, - (unsigned long long)OCFS2_I(inode2)->ip_blkno); + (unsigned long long)oi1->ip_blkno, + (unsigned long long)oi2->ip_blkno); bail: if (status) diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 6867eef2e06b..4f86ac0027b5 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -50,6 +50,8 @@ #include "reservations.h" +#include "filecheck.h" + /* Caching of metadata buffers */ /* Most user visible OCFS2 inodes will have very few pieces of @@ -472,6 +474,12 @@ struct ocfs2_super * workqueue and schedule on our own. */ struct workqueue_struct *ocfs2_wq; + + /* sysfs directory per partition */ + struct kset *osb_dev_kset; + + /* file check related stuff */ + struct ocfs2_filecheck_sysfs_entry osb_fc_ent; }; #define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info) diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h index e2a11aaece10..2ee76a90ba8f 100644 --- a/fs/ocfs2/ocfs2_trace.h +++ b/fs/ocfs2/ocfs2_trace.h @@ -1311,11 +1311,11 @@ DEFINE_OCFS2_FILE_OPS(ocfs2_file_release); DEFINE_OCFS2_FILE_OPS(ocfs2_sync_file); -DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_write); +DEFINE_OCFS2_FILE_OPS(ocfs2_file_write_iter); DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_write); -DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_read); +DEFINE_OCFS2_FILE_OPS(ocfs2_file_read_iter); DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_truncate_file); @@ -1467,7 +1467,7 @@ TRACE_EVENT(ocfs2_prepare_inode_for_write, __entry->saved_pos, __entry->count, __entry->wait) ); -DEFINE_OCFS2_INT_EVENT(generic_file_aio_read_ret); +DEFINE_OCFS2_INT_EVENT(generic_file_read_iter_ret); /* End of trace events for fs/ocfs2/file.c. */ diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index ab156e35ec00..01c6b3894406 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -573,7 +573,7 @@ static int ocfs2_create_refcount_tree(struct inode *inode, BUG_ON(ocfs2_is_refcount_inode(inode)); trace_ocfs2_create_refcount_tree( - (unsigned long long)OCFS2_I(inode)->ip_blkno); + (unsigned long long)oi->ip_blkno); ret = ocfs2_reserve_new_metadata_blocks(osb, 1, &meta_ac); if (ret) { @@ -3359,7 +3359,7 @@ static int ocfs2_replace_cow(struct ocfs2_cow_context *context) unsigned int ext_flags; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) { + if (!ocfs2_refcount_tree(osb)) { return ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n", inode->i_ino); } @@ -3707,7 +3707,7 @@ int ocfs2_add_refcount_flag(struct inode *inode, trace_ocfs2_add_refcount_flag(ref_blocks, credits); if (ref_blocks) { - ret = ocfs2_reserve_new_metadata_blocks(OCFS2_SB(inode->i_sb), + ret = ocfs2_reserve_new_metadata_blocks(osb, ref_blocks, &meta_ac); if (ret) { mlog_errno(ret); @@ -4766,8 +4766,8 @@ static int ocfs2_reflink_inodes_lock(struct inode *s_inode, *bh2 = *bh1; trace_ocfs2_double_lock_end( - (unsigned long long)OCFS2_I(inode1)->ip_blkno, - (unsigned long long)OCFS2_I(inode2)->ip_blkno); + (unsigned long long)oi1->ip_blkno, + (unsigned long long)oi2->ip_blkno); return 0; diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index d6c350ba25b9..c4b029c43464 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -48,12 +48,6 @@ static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl"; */ static struct ocfs2_stack_plugin *active_stack; -inline int ocfs2_is_o2cb_active(void) -{ - return !strcmp(active_stack->sp_name, OCFS2_STACK_PLUGIN_O2CB); -} -EXPORT_SYMBOL_GPL(ocfs2_is_o2cb_active); - static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name) { struct ocfs2_stack_plugin *p; diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h index e3036e1790e8..f2dce10fae54 100644 --- a/fs/ocfs2/stackglue.h +++ b/fs/ocfs2/stackglue.h @@ -298,9 +298,6 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin); void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin); -/* In ocfs2_downconvert_lock(), we need to know which stack we are using */ -int ocfs2_is_o2cb_active(void); - extern struct kset *ocfs2_kset; #endif /* STACKGLUE_H */ diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index d8f5f6ce99dc..40be6474e3d1 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -387,7 +387,7 @@ static int ocfs2_block_group_fill(handle_t *handle, memset(bg, 0, sb->s_blocksize); strcpy(bg->bg_signature, OCFS2_GROUP_DESC_SIGNATURE); - bg->bg_generation = cpu_to_le32(OCFS2_SB(sb)->fs_generation); + bg->bg_generation = cpu_to_le32(osb->fs_generation); bg->bg_size = cpu_to_le16(ocfs2_group_bitmap_size(sb, 1, osb->s_feature_incompat)); bg->bg_chain = cpu_to_le16(my_chain); @@ -1521,7 +1521,7 @@ static int ocfs2_cluster_group_search(struct inode *inode, OCFS2_I(inode)->ip_clusters, max_bits); } - ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb), + ret = ocfs2_block_group_find_clear_bits(osb, group_bh, bits_wanted, max_bits, res); if (ret) diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index ffa4952d432b..c492941e9d31 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -423,10 +423,10 @@ static int ocfs2_sync_fs(struct super_block *sb, int wait) ocfs2_schedule_truncate_log_flush(osb, 0); } - if (jbd2_journal_start_commit(OCFS2_SB(sb)->journal->j_journal, + if (jbd2_journal_start_commit(osb->journal->j_journal, &target)) { if (wait) - jbd2_log_wait_commit(OCFS2_SB(sb)->journal->j_journal, + jbd2_log_wait_commit(osb->journal->j_journal, target); } return 0; @@ -1161,6 +1161,23 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) ocfs2_complete_mount_recovery(osb); + osb->osb_dev_kset = kset_create_and_add(sb->s_id, NULL, + &ocfs2_kset->kobj); + if (!osb->osb_dev_kset) { + status = -ENOMEM; + mlog(ML_ERROR, "Unable to create device kset %s.\n", sb->s_id); + goto read_super_error; + } + + /* Create filecheck sysfs related directories/files at + * /sys/fs/ocfs2/<devname>/filecheck */ + if (ocfs2_filecheck_create_sysfs(osb)) { + status = -ENOMEM; + mlog(ML_ERROR, "Unable to create filecheck sysfs directory at " + "/sys/fs/ocfs2/%s/filecheck.\n", sb->s_id); + goto read_super_error; + } + if (ocfs2_mount_local(osb)) snprintf(nodestr, sizeof(nodestr), "local"); else @@ -1199,9 +1216,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) /* Start this when the mount is almost sure of being successful */ ocfs2_orphan_scan_start(osb); - /* Create filecheck sysfile /sys/fs/ocfs2/<devname>/filecheck */ - ocfs2_filecheck_create_sysfs(sb); - return status; read_super_error: @@ -1653,7 +1667,6 @@ static void ocfs2_put_super(struct super_block *sb) ocfs2_sync_blockdev(sb); ocfs2_dismount_volume(sb, 0); - ocfs2_filecheck_remove_sysfs(sb); } static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf) @@ -1899,6 +1912,12 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) osb = OCFS2_SB(sb); BUG_ON(!osb); + /* Remove file check sysfs related directores/files, + * and wait for the pending file check operations */ + ocfs2_filecheck_remove_sysfs(osb); + + kset_unregister(osb->osb_dev_kset); + debugfs_remove(osb->osb_ctxt); /* Orphan scan should be stopped as early as possible */ diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index c261c1dfd374..3a24ce3deb01 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -3564,7 +3564,7 @@ int ocfs2_xattr_set(struct inode *inode, .not_found = -ENODATA, }; - if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb))) + if (!ocfs2_supports_xattr(osb)) return -EOPNOTSUPP; /* diff --git a/fs/proc/array.c b/fs/proc/array.c index 598803576e4c..ae2c807fd719 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -141,25 +141,12 @@ static inline const char *get_task_state(struct task_struct *tsk) return task_state_array[task_state_index(tsk)]; } -static inline int get_task_umask(struct task_struct *tsk) -{ - struct fs_struct *fs; - int umask = -ENOENT; - - task_lock(tsk); - fs = tsk->fs; - if (fs) - umask = fs->umask; - task_unlock(tsk); - return umask; -} - static inline void task_state(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *p) { struct user_namespace *user_ns = seq_user_ns(m); struct group_info *group_info; - int g, umask; + int g, umask = -1; struct task_struct *tracer; const struct cred *cred; pid_t ppid, tpid = 0, tgid, ngid; @@ -177,17 +164,18 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, ngid = task_numa_group_id(p); cred = get_task_cred(p); - umask = get_task_umask(p); - if (umask >= 0) - seq_printf(m, "Umask:\t%#04o\n", umask); - task_lock(p); + if (p->fs) + umask = p->fs->umask; if (p->files) max_fds = files_fdtable(p->files)->max_fds; task_unlock(p); rcu_read_unlock(); - seq_printf(m, "State:\t%s", get_task_state(p)); + if (umask >= 0) + seq_printf(m, "Umask:\t%#04o\n", umask); + seq_puts(m, "State:\t"); + seq_puts(m, get_task_state(p)); seq_put_decimal_ull(m, "\nTgid:\t", tgid); seq_put_decimal_ull(m, "\nNgid:\t", ngid); @@ -313,8 +301,8 @@ static void render_cap_t(struct seq_file *m, const char *header, seq_puts(m, header); CAP_FOR_EACH_U32(__capi) { - seq_printf(m, "%08x", - a->cap[CAP_LAST_U32 - __capi]); + seq_put_hex_ll(m, NULL, + a->cap[CAP_LAST_U32 - __capi], 8); } seq_putc(m, '\n'); } @@ -368,7 +356,8 @@ static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm) { - seq_printf(m, "CoreDumping:\t%d\n", !!mm->core_state); + seq_put_decimal_ull(m, "CoreDumping:\t", !!mm->core_state); + seq_putc(m, '\n'); } int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, @@ -504,7 +493,11 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, /* convert nsec -> ticks */ start_time = nsec_to_clock_t(task->real_start_time); - seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state); + seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns)); + seq_puts(m, " ("); + seq_puts(m, tcomm); + seq_puts(m, ") "); + seq_putc(m, state); seq_put_decimal_ll(m, " ", ppid); seq_put_decimal_ll(m, " ", pgid); seq_put_decimal_ll(m, " ", sid); diff --git a/fs/proc/base.c b/fs/proc/base.c index 9298324325ed..b4ae3e474418 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -391,14 +391,17 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, unsigned long wchan; char symname[KSYM_NAME_LEN]; - wchan = get_wchan(task); + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) + goto print0; - if (wchan && ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS) - && !lookup_symbol_name(wchan, symname)) - seq_printf(m, "%s", symname); - else - seq_putc(m, '0'); + wchan = get_wchan(task); + if (wchan && !lookup_symbol_name(wchan, symname)) { + seq_puts(m, symname); + return 0; + } +print0: + seq_putc(m, '0'); return 0; } #endif /* CONFIG_KALLSYMS */ @@ -1913,6 +1916,8 @@ static int dname_to_vma_addr(struct dentry *dentry, unsigned long long sval, eval; unsigned int len; + if (str[0] == '0' && str[1]) + return -EINVAL; len = _parse_integer(str, 16, &sval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; @@ -1924,6 +1929,8 @@ static int dname_to_vma_addr(struct dentry *dentry, return -EINVAL; str++; + if (str[0] == '0' && str[1]) + return -EINVAL; len = _parse_integer(str, 16, &eval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 6e8724958116..89618836887d 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -54,6 +54,7 @@ static void proc_evict_inode(struct inode *inode) } static struct kmem_cache *proc_inode_cachep __ro_after_init; +static struct kmem_cache *pde_opener_cache __ro_after_init; static struct inode *proc_alloc_inode(struct super_block *sb) { @@ -92,7 +93,7 @@ static void init_once(void *foo) inode_init_once(&ei->vfs_inode); } -void __init proc_init_inodecache(void) +void __init proc_init_kmemcache(void) { proc_inode_cachep = kmem_cache_create("proc_inode_cache", sizeof(struct proc_inode), @@ -100,6 +101,9 @@ void __init proc_init_inodecache(void) SLAB_MEM_SPREAD|SLAB_ACCOUNT| SLAB_PANIC), init_once); + pde_opener_cache = + kmem_cache_create("pde_opener", sizeof(struct pde_opener), 0, + SLAB_ACCOUNT|SLAB_PANIC, NULL); } static int proc_show_options(struct seq_file *seq, struct dentry *root) @@ -138,7 +142,7 @@ static void unuse_pde(struct proc_dir_entry *pde) complete(pde->pde_unload_completion); } -/* pde is locked */ +/* pde is locked on entry, unlocked on exit */ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) { /* @@ -157,9 +161,10 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) pdeo->c = &c; spin_unlock(&pde->pde_unload_lock); wait_for_completion(&c); - spin_lock(&pde->pde_unload_lock); } else { struct file *file; + struct completion *c; + pdeo->closing = true; spin_unlock(&pde->pde_unload_lock); file = pdeo->file; @@ -167,9 +172,11 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) spin_lock(&pde->pde_unload_lock); /* After ->release. */ list_del(&pdeo->lh); - if (unlikely(pdeo->c)) - complete(pdeo->c); - kfree(pdeo); + c = pdeo->c; + spin_unlock(&pde->pde_unload_lock); + if (unlikely(c)) + complete(c); + kmem_cache_free(pde_opener_cache, pdeo); } } @@ -188,6 +195,7 @@ void proc_entry_rundown(struct proc_dir_entry *de) struct pde_opener *pdeo; pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh); close_pdeo(de, pdeo); + spin_lock(&de->pde_unload_lock); } spin_unlock(&de->pde_unload_lock); } @@ -338,31 +346,36 @@ static int proc_reg_open(struct inode *inode, struct file *file) * * Save every "struct file" with custom ->release hook. */ - pdeo = kmalloc(sizeof(struct pde_opener), GFP_KERNEL); - if (!pdeo) - return -ENOMEM; - - if (!use_pde(pde)) { - kfree(pdeo); + if (!use_pde(pde)) return -ENOENT; - } - open = pde->proc_fops->open; + release = pde->proc_fops->release; + if (release) { + pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL); + if (!pdeo) { + rv = -ENOMEM; + goto out_unuse; + } + } + open = pde->proc_fops->open; if (open) rv = open(inode, file); - if (rv == 0 && release) { - /* To know what to release. */ - pdeo->file = file; - pdeo->closing = false; - pdeo->c = NULL; - spin_lock(&pde->pde_unload_lock); - list_add(&pdeo->lh, &pde->pde_openers); - spin_unlock(&pde->pde_unload_lock); - } else - kfree(pdeo); + if (release) { + if (rv == 0) { + /* To know what to release. */ + pdeo->file = file; + pdeo->closing = false; + pdeo->c = NULL; + spin_lock(&pde->pde_unload_lock); + list_add(&pdeo->lh, &pde->pde_openers); + spin_unlock(&pde->pde_unload_lock); + } else + kmem_cache_free(pde_opener_cache, pdeo); + } +out_unuse: unuse_pde(pde); return rv; } @@ -375,7 +388,7 @@ static int proc_reg_release(struct inode *inode, struct file *file) list_for_each_entry(pdeo, &pde->pde_openers, lh) { if (pdeo->file == file) { close_pdeo(pde, pdeo); - break; + return 0; } } spin_unlock(&pde->pde_unload_lock); diff --git a/fs/proc/internal.h b/fs/proc/internal.h index d697c8ab0a14..dc00ef8538cb 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -177,12 +177,12 @@ struct pde_opener { struct list_head lh; bool closing; struct completion *c; -}; +} __randomize_layout; extern const struct inode_operations proc_link_inode_operations; extern const struct inode_operations proc_pid_link_inode_operations; -extern void proc_init_inodecache(void); +void proc_init_kmemcache(void); void set_proc_pid_nlink(void); extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *); extern int proc_fill_super(struct super_block *, void *data, int flags); diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 6bb20f864259..65a72ab57471 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -26,20 +26,7 @@ void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) static void show_val_kb(struct seq_file *m, const char *s, unsigned long num) { - char v[32]; - static const char blanks[7] = {' ', ' ', ' ', ' ',' ', ' ', ' '}; - int len; - - len = num_to_str(v, sizeof(v), num << (PAGE_SHIFT - 10)); - - seq_write(m, s, 16); - - if (len > 0) { - if (len < 8) - seq_write(m, blanks, 8 - len); - - seq_write(m, v, len); - } + seq_put_decimal_ull_width(m, s, num << (PAGE_SHIFT - 10), 8); seq_write(m, " kB\n", 4); } diff --git a/fs/proc/root.c b/fs/proc/root.c index ede8e64974be..98797b762a71 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -125,7 +125,7 @@ void __init proc_root_init(void) { int err; - proc_init_inodecache(); + proc_init_kmemcache(); set_proc_pid_nlink(); err = register_filesystem(&proc_fs_type); if (err) @@ -136,10 +136,6 @@ void __init proc_root_init(void) proc_symlink("mounts", NULL, "self/mounts"); proc_net_init(); - -#ifdef CONFIG_SYSVIPC - proc_mkdir("sysvipc", NULL); -#endif proc_mkdir("fs", NULL); proc_mkdir("driver", NULL); proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */ diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ec6d2983a5cb..65ae54659833 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -24,6 +24,8 @@ #include <asm/tlbflush.h> #include "internal.h" +#define SEQ_PUT_DEC(str, val) \ + seq_put_decimal_ull_width(m, str, (val) << (PAGE_SHIFT-10), 8) void task_mem(struct seq_file *m, struct mm_struct *mm) { unsigned long text, lib, swap, anon, file, shmem; @@ -53,39 +55,28 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) lib = (mm->exec_vm << PAGE_SHIFT) - text; swap = get_mm_counter(mm, MM_SWAPENTS); - seq_printf(m, - "VmPeak:\t%8lu kB\n" - "VmSize:\t%8lu kB\n" - "VmLck:\t%8lu kB\n" - "VmPin:\t%8lu kB\n" - "VmHWM:\t%8lu kB\n" - "VmRSS:\t%8lu kB\n" - "RssAnon:\t%8lu kB\n" - "RssFile:\t%8lu kB\n" - "RssShmem:\t%8lu kB\n" - "VmData:\t%8lu kB\n" - "VmStk:\t%8lu kB\n" - "VmExe:\t%8lu kB\n" - "VmLib:\t%8lu kB\n" - "VmPTE:\t%8lu kB\n" - "VmSwap:\t%8lu kB\n", - hiwater_vm << (PAGE_SHIFT-10), - total_vm << (PAGE_SHIFT-10), - mm->locked_vm << (PAGE_SHIFT-10), - mm->pinned_vm << (PAGE_SHIFT-10), - hiwater_rss << (PAGE_SHIFT-10), - total_rss << (PAGE_SHIFT-10), - anon << (PAGE_SHIFT-10), - file << (PAGE_SHIFT-10), - shmem << (PAGE_SHIFT-10), - mm->data_vm << (PAGE_SHIFT-10), - mm->stack_vm << (PAGE_SHIFT-10), - text >> 10, - lib >> 10, - mm_pgtables_bytes(mm) >> 10, - swap << (PAGE_SHIFT-10)); + SEQ_PUT_DEC("VmPeak:\t", hiwater_vm); + SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm); + SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm); + SEQ_PUT_DEC(" kB\nVmPin:\t", mm->pinned_vm); + SEQ_PUT_DEC(" kB\nVmHWM:\t", hiwater_rss); + SEQ_PUT_DEC(" kB\nVmRSS:\t", total_rss); + SEQ_PUT_DEC(" kB\nRssAnon:\t", anon); + SEQ_PUT_DEC(" kB\nRssFile:\t", file); + SEQ_PUT_DEC(" kB\nRssShmem:\t", shmem); + SEQ_PUT_DEC(" kB\nVmData:\t", mm->data_vm); + SEQ_PUT_DEC(" kB\nVmStk:\t", mm->stack_vm); + seq_put_decimal_ull_width(m, + " kB\nVmExe:\t", text >> 10, 8); + seq_put_decimal_ull_width(m, + " kB\nVmLib:\t", lib >> 10, 8); + seq_put_decimal_ull_width(m, + " kB\nVmPTE:\t", mm_pgtables_bytes(mm) >> 10, 8); + SEQ_PUT_DEC(" kB\nVmSwap:\t", swap); + seq_puts(m, " kB\n"); hugetlb_report_usage(m, mm); } +#undef SEQ_PUT_DEC unsigned long task_vsize(struct mm_struct *mm) { @@ -287,15 +278,18 @@ static void show_vma_header_prefix(struct seq_file *m, dev_t dev, unsigned long ino) { seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); - seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", - start, - end, - flags & VM_READ ? 'r' : '-', - flags & VM_WRITE ? 'w' : '-', - flags & VM_EXEC ? 'x' : '-', - flags & VM_MAYSHARE ? 's' : 'p', - pgoff, - MAJOR(dev), MINOR(dev), ino); + seq_put_hex_ll(m, NULL, start, 8); + seq_put_hex_ll(m, "-", end, 8); + seq_putc(m, ' '); + seq_putc(m, flags & VM_READ ? 'r' : '-'); + seq_putc(m, flags & VM_WRITE ? 'w' : '-'); + seq_putc(m, flags & VM_EXEC ? 'x' : '-'); + seq_putc(m, flags & VM_MAYSHARE ? 's' : 'p'); + seq_put_hex_ll(m, " ", pgoff, 8); + seq_put_hex_ll(m, " ", MAJOR(dev), 2); + seq_put_hex_ll(m, ":", MINOR(dev), 2); + seq_put_decimal_ull(m, " ", ino); + seq_putc(m, ' '); } static void @@ -694,8 +688,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) if (!mnemonics[i][0]) continue; if (vma->vm_flags & (1UL << i)) { - seq_printf(m, "%c%c ", - mnemonics[i][0], mnemonics[i][1]); + seq_putc(m, mnemonics[i][0]); + seq_putc(m, mnemonics[i][1]); + seq_putc(m, ' '); } } seq_putc(m, '\n'); @@ -736,6 +731,8 @@ void __weak arch_show_smap(struct seq_file *m, struct vm_area_struct *vma) { } +#define SEQ_PUT_DEC(str, val) \ + seq_put_decimal_ull_width(m, str, (val) >> 10, 8) static int show_smap(struct seq_file *m, void *v, int is_pid) { struct proc_maps_private *priv = m->private; @@ -809,51 +806,34 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) ret = SEQ_SKIP; } - if (!rollup_mode) - seq_printf(m, - "Size: %8lu kB\n" - "KernelPageSize: %8lu kB\n" - "MMUPageSize: %8lu kB\n", - (vma->vm_end - vma->vm_start) >> 10, - vma_kernel_pagesize(vma) >> 10, - vma_mmu_pagesize(vma) >> 10); - - - if (!rollup_mode || last_vma) - seq_printf(m, - "Rss: %8lu kB\n" - "Pss: %8lu kB\n" - "Shared_Clean: %8lu kB\n" - "Shared_Dirty: %8lu kB\n" - "Private_Clean: %8lu kB\n" - "Private_Dirty: %8lu kB\n" - "Referenced: %8lu kB\n" - "Anonymous: %8lu kB\n" - "LazyFree: %8lu kB\n" - "AnonHugePages: %8lu kB\n" - "ShmemPmdMapped: %8lu kB\n" - "Shared_Hugetlb: %8lu kB\n" - "Private_Hugetlb: %7lu kB\n" - "Swap: %8lu kB\n" - "SwapPss: %8lu kB\n" - "Locked: %8lu kB\n", - mss->resident >> 10, - (unsigned long)(mss->pss >> (10 + PSS_SHIFT)), - mss->shared_clean >> 10, - mss->shared_dirty >> 10, - mss->private_clean >> 10, - mss->private_dirty >> 10, - mss->referenced >> 10, - mss->anonymous >> 10, - mss->lazyfree >> 10, - mss->anonymous_thp >> 10, - mss->shmem_thp >> 10, - mss->shared_hugetlb >> 10, - mss->private_hugetlb >> 10, - mss->swap >> 10, - (unsigned long)(mss->swap_pss >> (10 + PSS_SHIFT)), - (unsigned long)(mss->pss >> (10 + PSS_SHIFT))); + if (!rollup_mode) { + SEQ_PUT_DEC("Size: ", vma->vm_end - vma->vm_start); + SEQ_PUT_DEC(" kB\nKernelPageSize: ", vma_kernel_pagesize(vma)); + SEQ_PUT_DEC(" kB\nMMUPageSize: ", vma_mmu_pagesize(vma)); + seq_puts(m, " kB\n"); + } + if (!rollup_mode || last_vma) { + SEQ_PUT_DEC("Rss: ", mss->resident); + SEQ_PUT_DEC(" kB\nPss: ", mss->pss >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nShared_Clean: ", mss->shared_clean); + SEQ_PUT_DEC(" kB\nShared_Dirty: ", mss->shared_dirty); + SEQ_PUT_DEC(" kB\nPrivate_Clean: ", mss->private_clean); + SEQ_PUT_DEC(" kB\nPrivate_Dirty: ", mss->private_dirty); + SEQ_PUT_DEC(" kB\nReferenced: ", mss->referenced); + SEQ_PUT_DEC(" kB\nAnonymous: ", mss->anonymous); + SEQ_PUT_DEC(" kB\nLazyFree: ", mss->lazyfree); + SEQ_PUT_DEC(" kB\nAnonHugePages: ", mss->anonymous_thp); + SEQ_PUT_DEC(" kB\nShmemPmdMapped: ", mss->shmem_thp); + SEQ_PUT_DEC(" kB\nShared_Hugetlb: ", mss->shared_hugetlb); + seq_put_decimal_ull_width(m, " kB\nPrivate_Hugetlb: ", + mss->private_hugetlb >> 10, 7); + SEQ_PUT_DEC(" kB\nSwap: ", mss->swap); + SEQ_PUT_DEC(" kB\nSwapPss: ", + mss->swap_pss >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nLocked: ", mss->pss >> PSS_SHIFT); + seq_puts(m, " kB\n"); + } if (!rollup_mode) { arch_show_smap(m, vma); show_smap_vma_flags(m, vma); @@ -861,6 +841,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) m_cache_vma(m, vma); return ret; } +#undef SEQ_PUT_DEC static int show_pid_smap(struct seq_file *m, void *v) { diff --git a/fs/seq_file.c b/fs/seq_file.c index eea09f6d8830..18f121d37a30 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -673,37 +673,40 @@ void seq_puts(struct seq_file *m, const char *s) } EXPORT_SYMBOL(seq_puts); -/* +/** * A helper routine for putting decimal numbers without rich format of printf(). * only 'unsigned long long' is supported. - * This routine will put strlen(delimiter) + number into seq_file. + * @m: seq_file identifying the buffer to which data should be written + * @delimiter: a string which is printed before the number + * @num: the number + * @width: a minimum field width + * + * This routine will put strlen(delimiter) + number into seq_filed. * This routine is very quick when you show lots of numbers. * In usual cases, it will be better to use seq_printf(). It's easier to read. */ -void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, - unsigned long long num) +void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter, + unsigned long long num, unsigned int width) { int len; if (m->count + 2 >= m->size) /* we'll write 2 bytes at least */ goto overflow; - len = strlen(delimiter); - if (m->count + len >= m->size) - goto overflow; + if (delimiter && delimiter[0]) { + if (delimiter[1] == 0) + seq_putc(m, delimiter[0]); + else + seq_puts(m, delimiter); + } - memcpy(m->buf + m->count, delimiter, len); - m->count += len; + if (!width) + width = 1; - if (m->count + 1 >= m->size) + if (m->count + width >= m->size) goto overflow; - if (num < 10) { - m->buf[m->count++] = num + '0'; - return; - } - - len = num_to_str(m->buf + m->count, m->size - m->count, num); + len = num_to_str(m->buf + m->count, m->size - m->count, num, width); if (!len) goto overflow; @@ -713,8 +716,60 @@ void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, overflow: seq_set_overflow(m); } + +void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, + unsigned long long num) +{ + return seq_put_decimal_ull_width(m, delimiter, num, 0); +} EXPORT_SYMBOL(seq_put_decimal_ull); +/** + * seq_put_hex_ll - put a number in hexadecimal notation + * @m: seq_file identifying the buffer to which data should be written + * @delimiter: a string which is printed before the number + * @v: the number + * @width: a minimum field width + * + * seq_put_hex_ll(m, "", v, 8) is equal to seq_printf(m, "%08llx", v) + * + * This routine is very quick when you show lots of numbers. + * In usual cases, it will be better to use seq_printf(). It's easier to read. + */ +void seq_put_hex_ll(struct seq_file *m, const char *delimiter, + unsigned long long v, unsigned int width) +{ + unsigned int len; + int i; + + if (delimiter && delimiter[0]) { + if (delimiter[1] == 0) + seq_putc(m, delimiter[0]); + else + seq_puts(m, delimiter); + } + + /* If x is 0, the result of __builtin_clzll is undefined */ + if (v == 0) + len = 1; + else + len = (sizeof(v) * 8 - __builtin_clzll(v) + 3) / 4; + + if (len < width) + len = width; + + if (m->count + len > m->size) { + seq_set_overflow(m); + return; + } + + for (i = len - 1; i >= 0; i--) { + m->buf[m->count + i] = hex_asc[0xf & v]; + v = v >> 4; + } + m->count += len; +} + void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num) { int len; @@ -722,12 +777,12 @@ void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num if (m->count + 3 >= m->size) /* we'll write 2 bytes at least */ goto overflow; - len = strlen(delimiter); - if (m->count + len >= m->size) - goto overflow; - - memcpy(m->buf + m->count, delimiter, len); - m->count += len; + if (delimiter && delimiter[0]) { + if (delimiter[1] == 0) + seq_putc(m, delimiter[0]); + else + seq_puts(m, delimiter); + } if (m->count + 2 >= m->size) goto overflow; @@ -737,12 +792,7 @@ void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num num = -num; } - if (num < 10) { - m->buf[m->count++] = num + '0'; - return; - } - - len = num_to_str(m->buf + m->count, m->size - m->count, num); + len = num_to_str(m->buf + m->count, m->size - m->count, num, 0); if (!len) goto overflow; @@ -782,8 +832,14 @@ EXPORT_SYMBOL(seq_write); void seq_pad(struct seq_file *m, char c) { int size = m->pad_until - m->count; - if (size > 0) - seq_printf(m, "%*s", size, ""); + if (size > 0) { + if (size + m->count > m->size) { + seq_set_overflow(m); + return; + } + memset(m->buf + m->count, ' ', size); + m->count += size; + } if (c) seq_putc(m, c); } |