diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-07-03 17:12:13 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-07-03 17:12:13 -0700 |
| commit | 7f0ef0267e20d62d45d527911a993b1e998f4968 (patch) | |
| tree | de51abc7da5903f59d83e23937f22420164c9477 /fs | |
| parent | 862f0012549110d6f2586bf54b52ed4540cbff3a (diff) | |
| parent | 9307c29524502c21f0e8a6d96d850b2f5bc0bd9a (diff) | |
| download | op-kernel-dev-7f0ef0267e20d62d45d527911a993b1e998f4968.zip op-kernel-dev-7f0ef0267e20d62d45d527911a993b1e998f4968.tar.gz | |
Merge branch 'akpm' (updates from Andrew Morton)
Merge first patch-bomb from Andrew Morton:
- various misc bits
- I'm been patchmonkeying ocfs2 for a while, as Joel and Mark have been
distracted. There has been quite a bit of activity.
- About half the MM queue
- Some backlight bits
- Various lib/ updates
- checkpatch updates
- zillions more little rtc patches
- ptrace
- signals
- exec
- procfs
- rapidio
- nbd
- aoe
- pps
- memstick
- tools/testing/selftests updates
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (445 commits)
tools/testing/selftests: don't assume the x bit is set on scripts
selftests: add .gitignore for kcmp
selftests: fix clean target in kcmp Makefile
selftests: add .gitignore for vm
selftests: add hugetlbfstest
self-test: fix make clean
selftests: exit 1 on failure
kernel/resource.c: remove the unneeded assignment in function __find_resource
aio: fix wrong comment in aio_complete()
drivers/w1/slaves/w1_ds2408.c: add magic sequence to disable P0 test mode
drivers/memstick/host/r592.c: convert to module_pci_driver
drivers/memstick/host/jmb38x_ms: convert to module_pci_driver
pps-gpio: add device-tree binding and support
drivers/pps/clients/pps-gpio.c: convert to module_platform_driver
drivers/pps/clients/pps-gpio.c: convert to devm_* helpers
drivers/parport/share.c: use kzalloc
Documentation/accounting/getdelays.c: avoid strncpy in accounting tool
aoe: update internal version number to v83
aoe: update copyright date
aoe: perform I/O completions in parallel
...
Diffstat (limited to 'fs')
43 files changed, 991 insertions, 470 deletions
@@ -625,7 +625,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) /* * Add a completion event to the ring buffer. Must be done holding - * ctx->ctx_lock to prevent other code from messing with the tail + * ctx->completion_lock to prevent other code from messing with the tail * pointer since we might be called from irq context. */ spin_lock_irqsave(&ctx->completion_lock, flags); diff --git a/fs/block_dev.c b/fs/block_dev.c index 431b6a0..bb43ce0 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1562,6 +1562,7 @@ static const struct address_space_operations def_blk_aops = { .writepages = generic_writepages, .releasepage = blkdev_releasepage, .direct_IO = blkdev_direct_IO, + .is_dirty_writeback = buffer_check_dirty_writeback, }; const struct file_operations def_blk_fops = { diff --git a/fs/buffer.c b/fs/buffer.c index f93392e..4d74335 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -83,6 +83,40 @@ void unlock_buffer(struct buffer_head *bh) EXPORT_SYMBOL(unlock_buffer); /* + * Returns if the page has dirty or writeback buffers. If all the buffers + * are unlocked and clean then the PageDirty information is stale. If + * any of the pages are locked, it is assumed they are locked for IO. + */ +void buffer_check_dirty_writeback(struct page *page, + bool *dirty, bool *writeback) +{ + struct buffer_head *head, *bh; + *dirty = false; + *writeback = false; + + BUG_ON(!PageLocked(page)); + + if (!page_has_buffers(page)) + return; + + if (PageWriteback(page)) + *writeback = true; + + head = page_buffers(page); + bh = head; + do { + if (buffer_locked(bh)) + *writeback = true; + + if (buffer_dirty(bh)) + *dirty = true; + + bh = bh->b_this_page; + } while (bh != head); +} +EXPORT_SYMBOL(buffer_check_dirty_writeback); + +/* * Block until a buffer comes unlocked. This doesn't stop it * from becoming locked again - you have to lock it yourself * if you want to preserve its state. diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 317f9ee..ebaff36 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -12,6 +12,7 @@ #include <linux/mount.h> #include <linux/slab.h> #include <linux/file.h> +#include <linux/swap.h> #include "internal.h" /* @@ -227,8 +228,7 @@ static void cachefiles_read_copier(struct fscache_operation *_op) */ static int cachefiles_read_backing_file_one(struct cachefiles_object *object, struct fscache_retrieval *op, - struct page *netpage, - struct pagevec *pagevec) + struct page *netpage) { struct cachefiles_one_read *monitor; struct address_space *bmapping; @@ -237,8 +237,6 @@ static int cachefiles_read_backing_file_one(struct cachefiles_object *object, _enter(""); - pagevec_reinit(pagevec); - _debug("read back %p{%lu,%d}", netpage, netpage->index, page_count(netpage)); @@ -283,9 +281,7 @@ installed_new_backing_page: backpage = newpage; newpage = NULL; - page_cache_get(backpage); - pagevec_add(pagevec, backpage); - __pagevec_lru_add_file(pagevec); + lru_cache_add_file(backpage); read_backing_page: ret = bmapping->a_ops->readpage(NULL, backpage); @@ -452,8 +448,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, if (block) { /* submit the apparently valid page to the backing fs to be * read from disk */ - ret = cachefiles_read_backing_file_one(object, op, page, - &pagevec); + ret = cachefiles_read_backing_file_one(object, op, page); } else if (cachefiles_has_space(cache, 0, 1) == 0) { /* there's space in the cache we can use */ fscache_mark_page_cached(op, page); @@ -482,14 +477,11 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, { struct cachefiles_one_read *monitor = NULL; struct address_space *bmapping = object->backer->d_inode->i_mapping; - struct pagevec lru_pvec; struct page *newpage = NULL, *netpage, *_n, *backpage = NULL; int ret = 0; _enter(""); - pagevec_init(&lru_pvec, 0); - list_for_each_entry_safe(netpage, _n, list, lru) { list_del(&netpage->lru); @@ -534,9 +526,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, backpage = newpage; newpage = NULL; - page_cache_get(backpage); - if (!pagevec_add(&lru_pvec, backpage)) - __pagevec_lru_add_file(&lru_pvec); + lru_cache_add_file(backpage); reread_backing_page: ret = bmapping->a_ops->readpage(NULL, backpage); @@ -559,9 +549,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, goto nomem; } - page_cache_get(netpage); - if (!pagevec_add(&lru_pvec, netpage)) - __pagevec_lru_add_file(&lru_pvec); + lru_cache_add_file(netpage); /* install a monitor */ page_cache_get(netpage); @@ -643,9 +631,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, fscache_mark_page_cached(op, netpage); - page_cache_get(netpage); - if (!pagevec_add(&lru_pvec, netpage)) - __pagevec_lru_add_file(&lru_pvec); + lru_cache_add_file(netpage); /* the netpage is unlocked and marked up to date here */ fscache_end_io(op, netpage, 0); @@ -661,8 +647,6 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, out: /* tidy up */ - pagevec_lru_add_file(&lru_pvec); - if (newpage) page_cache_release(newpage); if (netpage) diff --git a/fs/configfs/file.c b/fs/configfs/file.c index 2b6cb23..1d1c41f 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -203,7 +203,7 @@ configfs_write_file(struct file *file, const char __user *buf, size_t count, lof mutex_lock(&buffer->mutex); len = fill_write_buffer(buffer, buf, count); if (len > 0) - len = flush_write_buffer(file->f_path.dentry, buffer, count); + len = flush_write_buffer(file->f_path.dentry, buffer, len); if (len > 0) *ppos += len; mutex_unlock(&buffer->mutex); diff --git a/fs/coredump.c b/fs/coredump.c index dafafba..72f816d 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -45,69 +45,79 @@ #include <trace/events/sched.h> int core_uses_pid; -char core_pattern[CORENAME_MAX_SIZE] = "core"; unsigned int core_pipe_limit; +char core_pattern[CORENAME_MAX_SIZE] = "core"; +static int core_name_size = CORENAME_MAX_SIZE; struct core_name { char *corename; int used, size; }; -static atomic_t call_count = ATOMIC_INIT(1); /* The maximal length of core_pattern is also specified in sysctl.c */ -static int expand_corename(struct core_name *cn) +static int expand_corename(struct core_name *cn, int size) { - char *old_corename = cn->corename; - - cn->size = CORENAME_MAX_SIZE * atomic_inc_return(&call_count); - cn->corename = krealloc(old_corename, cn->size, GFP_KERNEL); + char *corename = krealloc(cn->corename, size, GFP_KERNEL); - if (!cn->corename) { - kfree(old_corename); + if (!corename) return -ENOMEM; - } + if (size > core_name_size) /* racy but harmless */ + core_name_size = size; + + cn->size = ksize(corename); + cn->corename = corename; return 0; } +static int cn_vprintf(struct core_name *cn, const char *fmt, va_list arg) +{ + int free, need; + +again: + free = cn->size - cn->used; + need = vsnprintf(cn->corename + cn->used, free, fmt, arg); + if (need < free) { + cn->used += need; + return 0; + } + + if (!expand_corename(cn, cn->size + need - free + 1)) + goto again; + + return -ENOMEM; +} + static int cn_printf(struct core_name *cn, const char *fmt, ...) { - char *cur; - int need; - int ret; va_list arg; + int ret; va_start(arg, fmt); - need = vsnprintf(NULL, 0, fmt, arg); + ret = cn_vprintf(cn, fmt, arg); va_end(arg); - if (likely(need < cn->size - cn->used - 1)) - goto out_printf; + return ret; +} - ret = expand_corename(cn); - if (ret) - goto expand_fail; +static int cn_esc_printf(struct core_name *cn, const char *fmt, ...) +{ + int cur = cn->used; + va_list arg; + int ret; -out_printf: - cur = cn->corename + cn->used; va_start(arg, fmt); - vsnprintf(cur, need + 1, fmt, arg); + ret = cn_vprintf(cn, fmt, arg); va_end(arg); - cn->used += need; - return 0; -expand_fail: + for (; cur < cn->used; ++cur) { + if (cn->corename[cur] == '/') + cn->corename[cur] = '!'; + } return ret; } -static void cn_escape(char *str) -{ - for (; *str; str++) - if (*str == '/') - *str = '!'; -} - static int cn_print_exe_file(struct core_name *cn) { struct file *exe_file; @@ -115,12 +125,8 @@ static int cn_print_exe_file(struct core_name *cn) int ret; exe_file = get_mm_exe_file(current->mm); - if (!exe_file) { - char *commstart = cn->corename + cn->used; - ret = cn_printf(cn, "%s (path unknown)", current->comm); - cn_escape(commstart); - return ret; - } + if (!exe_file) + return cn_esc_printf(cn, "%s (path unknown)", current->comm); pathbuf = kmalloc(PATH_MAX, GFP_TEMPORARY); if (!pathbuf) { @@ -134,9 +140,7 @@ static int cn_print_exe_file(struct core_name *cn) goto free_buf; } - cn_escape(path); - - ret = cn_printf(cn, "%s", path); + ret = cn_esc_printf(cn, "%s", path); free_buf: kfree(pathbuf); @@ -157,19 +161,19 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) int pid_in_pattern = 0; int err = 0; - cn->size = CORENAME_MAX_SIZE * atomic_read(&call_count); - cn->corename = kmalloc(cn->size, GFP_KERNEL); cn->used = 0; - - if (!cn->corename) + cn->corename = NULL; + if (expand_corename(cn, core_name_size)) return -ENOMEM; + cn->corename[0] = '\0'; + + if (ispipe) + ++pat_ptr; /* Repeat as long as we have more pattern to process and more output space */ while (*pat_ptr) { if (*pat_ptr != '%') { - if (*pat_ptr == 0) - goto out; err = cn_printf(cn, "%c", *pat_ptr++); } else { switch (*++pat_ptr) { @@ -210,22 +214,16 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) break; } /* hostname */ - case 'h': { - char *namestart = cn->corename + cn->used; + case 'h': down_read(&uts_sem); - err = cn_printf(cn, "%s", + err = cn_esc_printf(cn, "%s", utsname()->nodename); up_read(&uts_sem); - cn_escape(namestart); break; - } /* executable */ - case 'e': { - char *commstart = cn->corename + cn->used; - err = cn_printf(cn, "%s", current->comm); - cn_escape(commstart); + case 'e': + err = cn_esc_printf(cn, "%s", current->comm); break; - } case 'E': err = cn_print_exe_file(cn); break; @@ -244,6 +242,7 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) return err; } +out: /* Backward compatibility with core_uses_pid: * * If core_pattern does not include a %p (as is the default) @@ -254,7 +253,6 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) if (err) return err; } -out: return ispipe; } @@ -549,7 +547,7 @@ void do_coredump(siginfo_t *siginfo) if (ispipe < 0) { printk(KERN_WARNING "format_corename failed\n"); printk(KERN_WARNING "Aborting core\n"); - goto fail_corename; + goto fail_unlock; } if (cprm.limit == 1) { @@ -584,7 +582,7 @@ void do_coredump(siginfo_t *siginfo) goto fail_dropcount; } - helper_argv = argv_split(GFP_KERNEL, cn.corename+1, NULL); + helper_argv = argv_split(GFP_KERNEL, cn.corename, NULL); if (!helper_argv) { printk(KERN_WARNING "%s failed to allocate memory\n", __func__); @@ -601,7 +599,7 @@ void do_coredump(siginfo_t *siginfo) argv_free(helper_argv); if (retval) { - printk(KERN_INFO "Core dump to %s pipe failed\n", + printk(KERN_INFO "Core dump to |%s pipe failed\n", cn.corename); goto close_fail; } @@ -669,7 +667,6 @@ fail_dropcount: atomic_dec(&core_dump_count); fail_unlock: kfree(cn.corename); -fail_corename: coredump_finish(mm, core_dumped); revert_creds(old_cred); fail_creds: diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 0cff443..9ad17b15 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1977,8 +1977,8 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, return -EINVAL; if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask))) return -EFAULT; - sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP)); - sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + sigsaved = current->blocked; + set_current_blocked(&ksigmask); } error = sys_epoll_wait(epfd, events, maxevents, timeout); @@ -1995,7 +1995,7 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, sizeof(sigsaved)); set_restore_sigmask(); } else - sigprocmask(SIG_SETMASK, &sigsaved, NULL); + set_current_blocked(&sigsaved); } return error; @@ -2022,8 +2022,8 @@ COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, if (copy_from_user(&csigmask, sigmask, sizeof(csigmask))) return -EFAULT; sigset_from_compat(&ksigmask, &csigmask); - sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP)); - sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + sigsaved = current->blocked; + set_current_blocked(&ksigmask); } err = sys_epoll_wait(epfd, events, maxevents, timeout); @@ -2040,7 +2040,7 @@ COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, sizeof(sigsaved)); set_restore_sigmask(); } else - sigprocmask(SIG_SETMASK, &sigsaved, NULL); + set_current_blocked(&sigsaved); } return err; @@ -932,6 +932,7 @@ static int de_thread(struct task_struct *tsk) * also take its birthdate (always earlier than our own). */ tsk->start_time = leader->start_time; + tsk->real_start_time = leader->real_start_time; BUG_ON(!same_thread_group(leader, tsk)); BUG_ON(has_group_leader_pid(tsk)); @@ -947,9 +948,8 @@ static int de_thread(struct task_struct *tsk) * Note: The old leader also uses this pid until release_task * is called. Odd but simple and correct. */ - detach_pid(tsk, PIDTYPE_PID); tsk->pid = leader->pid; - attach_pid(tsk, PIDTYPE_PID, task_pid(leader)); + change_pid(tsk, PIDTYPE_PID, task_pid(leader)); transfer_pid(leader, tsk, PIDTYPE_PGID); transfer_pid(leader, tsk, PIDTYPE_SID); @@ -1465,7 +1465,6 @@ static int do_execve_common(const char *filename, struct files_struct *displaced; bool clear_in_exec; int retval; - const struct cred *cred = current_cred(); /* * We move the actual failure in case of RLIMIT_NPROC excess from @@ -1474,7 +1473,7 @@ static int do_execve_common(const char *filename, * whether NPROC limit is still exceeded. */ if ((current->flags & PF_NPROC_EXCEEDED) && - atomic_read(&cred->user->processes) > rlimit(RLIMIT_NPROC)) { + atomic_read(¤t_user()->processes) > rlimit(RLIMIT_NPROC)) { retval = -EAGAIN; goto out_ret; } diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index f67668f..2bd8548 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1985,6 +1985,7 @@ static const struct address_space_operations ext3_ordered_aops = { .direct_IO = ext3_direct_IO, .migratepage = buffer_migrate_page, .is_partially_uptodate = block_is_partially_uptodate, + .is_dirty_writeback = buffer_check_dirty_writeback, .error_remove_page = generic_error_remove_page, }; diff --git a/fs/fat/misc.c b/fs/fat/misc.c index 359d307..628e22a 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -30,7 +30,7 @@ void __fat_fs_error(struct super_block *sb, int report, const char *fmt, ...) va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; - printk(KERN_ERR "FAT-fs (%s): error, %pV\n", sb->s_id, &vaf); + fat_msg(sb, KERN_ERR, "error, %pV", &vaf); va_end(args); } @@ -38,8 +38,7 @@ void __fat_fs_error(struct super_block *sb, int report, const char *fmt, ...) panic("FAT-fs (%s): fs panic from previous error\n", sb->s_id); else if (opts->errors == FAT_ERRORS_RO && !(sb->s_flags & MS_RDONLY)) { sb->s_flags |= MS_RDONLY; - printk(KERN_ERR "FAT-fs (%s): Filesystem has been " - "set read-only\n", sb->s_id); + fat_msg(sb, KERN_ERR, "Filesystem has been set read-only"); } } EXPORT_SYMBOL_GPL(__fat_fs_error); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 9a0cdde..0b57859 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -785,7 +785,7 @@ static const struct super_operations fuse_super_operations = { static void sanitize_global_limit(unsigned *limit) { if (*limit == 0) - *limit = ((num_physpages << PAGE_SHIFT) >> 13) / + *limit = ((totalram_pages << PAGE_SHIFT) >> 13) / sizeof(struct fuse_req); if (*limit >= 1 << 16) diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index fc90ab1..4338ff3 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -69,7 +69,7 @@ static char *dentry_name(struct dentry *dentry, int extra) struct dentry *parent; char *root, *name; const char *seg_name; - int len, seg_len; + int len, seg_len, root_len; len = 0; parent = dentry; @@ -81,7 +81,8 @@ static char *dentry_name(struct dentry *dentry, int extra) } root = "proc"; - len += strlen(root); + root_len = strlen(root); + len += root_len; name = kmalloc(len + extra + 1, GFP_KERNEL); if (name == NULL) return NULL; @@ -91,7 +92,7 @@ static char *dentry_name(struct dentry *dentry, int extra) while (parent->d_parent != parent) { if (is_pid(parent)) { seg_name = "pid"; - seg_len = strlen("pid"); + seg_len = strlen(seg_name); } else { seg_name = parent->d_name.name; @@ -100,10 +101,10 @@ static char *dentry_name(struct dentry *dentry, int extra) len -= seg_len + 1; name[len] = '/'; - strncpy(&name[len + 1], seg_name, seg_len); + memcpy(&name[len + 1], seg_name, seg_len); parent = parent->d_parent; } - strncpy(name, root, strlen(root)); + memcpy(name, root, root_len); return name; } diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index a2aa97d..10d6c41 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -305,7 +305,7 @@ static int lockd_start_svc(struct svc_serv *serv) svc_sock_update_bufs(serv); serv->sv_maxconn = nlm_max_connections; - nlmsvc_task = kthread_run(lockd, nlmsvc_rqst, serv->sv_name); + nlmsvc_task = kthread_run(lockd, nlmsvc_rqst, "%s", serv->sv_name); if (IS_ERR(nlmsvc_task)) { error = PTR_ERR(nlmsvc_task); printk(KERN_WARNING diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c index ee24df5..3c5dd55 100644 --- a/fs/ncpfs/mmap.c +++ b/fs/ncpfs/mmap.c @@ -117,7 +117,7 @@ int ncp_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; /* we do not support files bigger than 4GB... We eventually supports just 4GB... */ - if (((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff + if (vma_pages(vma) + vma->vm_pgoff > (1U << (32 - PAGE_SHIFT))) return -EFBIG; diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index cff089a..da6a43d 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -211,7 +211,6 @@ static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt, struct svc_rqst *rqstp; int (*callback_svc)(void *vrqstp); struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion]; - char svc_name[12]; int ret; nfs_callback_bc_serv(minorversion, xprt, serv); @@ -235,10 +234,10 @@ static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt, svc_sock_update_bufs(serv); - sprintf(svc_name, "nfsv4.%u-svc", minorversion); cb_info->serv = serv; cb_info->rqst = rqstp; - cb_info->task = kthread_run(callback_svc, cb_info->rqst, svc_name); + cb_info->task = kthread_run(callback_svc, cb_info->rqst, + "nfsv4.%u-svc", minorversion); if (IS_ERR(cb_info->task)) { ret = PTR_ERR(cb_info->task); svc_exit_thread(cb_info->rqst); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 5d05141..d7ed697 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -33,6 +33,7 @@ #include <linux/pagevec.h> #include <linux/namei.h> #include <linux/mount.h> +#include <linux/swap.h> #include <linux/sched.h> #include <linux/kmemleak.h> #include <linux/xattr.h> @@ -1758,7 +1759,6 @@ EXPORT_SYMBOL_GPL(nfs_unlink); */ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) { - struct pagevec lru_pvec; struct page *page; char *kaddr; struct iattr attr; @@ -1798,11 +1798,8 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) * No big deal if we can't add this page to the page cache here. * READLINK will get the missing page from the server if needed. */ - pagevec_init(&lru_pvec, 0); - if (!add_to_page_cache(page, dentry->d_inode->i_mapping, 0, + if (!add_to_page_cache_lru(page, dentry->d_inode->i_mapping, 0, GFP_KERNEL)) { - pagevec_add(&lru_pvec, page); - pagevec_lru_add_file(&lru_pvec); SetPageUptodate(page); unlock_page(page); } else diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 6b4a79f..94e94bd 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -495,6 +495,35 @@ static int nfs_release_page(struct page *page, gfp_t gfp) return nfs_fscache_release_page(page, gfp); } +static void nfs_check_dirty_writeback(struct page *page, + bool *dirty, bool *writeback) +{ + struct nfs_inode *nfsi; + struct address_space *mapping = page_file_mapping(page); + + if (!mapping || PageSwapCache(page)) + return; + + /* + * Check if an unstable page is currently being committed and + * if so, have the VM treat it as if the page is under writeback + * so it will not block due to pages that will shortly be freeable. + */ + nfsi = NFS_I(mapping->host); + if (test_bit(NFS_INO_COMMIT, &nfsi->flags)) { + *writeback = true; + return; + } + + /* + * If PagePrivate() is set, then the page is not freeable and as the + * inode is not being committed, it's not going to be cleaned in the + * near future so treat it as dirty + */ + if (PagePrivate(page)) + *dirty = true; +} + /* * Attempt to clear the private state associated with a page when an error * occurs that requires the cached contents of an inode to be written back or @@ -542,6 +571,7 @@ const struct address_space_operations nfs_file_aops = { .direct_IO = nfs_direct_IO, .migratepage = nfs_migrate_page, .launder_page = nfs_launder_page, + .is_dirty_writeback = nfs_check_dirty_writeback, .error_remove_page = generic_error_remove_page, #ifdef CONFIG_NFS_SWAP .swap_activate = nfs_swap_activate, diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index ff10b4a..5541881 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1194,7 +1194,7 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) snprintf(buf, sizeof(buf), "%s-manager", rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR)); rcu_read_unlock(); - task = kthread_run(nfs4_run_state_manager, clp, buf); + task = kthread_run(nfs4_run_state_manager, clp, "%s", buf); if (IS_ERR(task)) { printk(KERN_ERR "%s: kthread_run: %ld\n", __func__, PTR_ERR(task)); diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index eed4d7b..741fd02 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -398,6 +398,69 @@ nilfs_palloc_rest_groups_in_desc_block(const struct inode *inode, } /** + * nilfs_palloc_count_desc_blocks - count descriptor blocks number + * @inode: inode of metadata file using this allocator + * @desc_blocks: descriptor blocks number [out] + */ +static int nilfs_palloc_count_desc_blocks(struct inode *inode, + unsigned long *desc_blocks) +{ + unsigned long blknum; + int ret; + + ret = nilfs_bmap_last_key(NILFS_I(inode)->i_bmap, &blknum); + if (likely(!ret)) + *desc_blocks = DIV_ROUND_UP( + blknum, NILFS_MDT(inode)->mi_blocks_per_desc_block); + return ret; +} + +/** + * nilfs_palloc_mdt_file_can_grow - check potential opportunity for + * MDT file growing + * @inode: inode of metadata file using this allocator + * @desc_blocks: known current descriptor blocks count + */ +static inline bool nilfs_palloc_mdt_file_can_grow(struct inode *inode, + unsigned long desc_blocks) +{ + return (nilfs_palloc_groups_per_desc_block(inode) * desc_blocks) < + nilfs_palloc_groups_count(inode); +} + +/** + * nilfs_palloc_count_max_entries - count max number of entries that can be + * described by descriptor blocks count + * @inode: inode of metadata file using this allocator + * @nused: current number of used entries + * @nmaxp: max number of entries [out] + */ +int nilfs_palloc_count_max_entries(struct inode *inode, u64 nused, u64 *nmaxp) +{ + unsigned long desc_blocks = 0; + u64 entries_per_desc_block, nmax; + int err; + + err = nilfs_palloc_count_desc_blocks(inode, &desc_blocks); + if (unlikely(err)) + return err; + + entries_per_desc_block = (u64)nilfs_palloc_entries_per_group(inode) * + nilfs_palloc_groups_per_desc_block(inode); + nmax = entries_per_desc_block * desc_blocks; + + if (nused == nmax && + nilfs_palloc_mdt_file_can_grow(inode, desc_blocks)) + nmax += entries_per_desc_block; + + if (nused > nmax) + return -ERANGE; + + *nmaxp = nmax; + return 0; +} + +/** * nilfs_palloc_prepare_alloc_entry - prepare to allocate a persistent object * @inode: inode of metadata file using this allocator * @req: nilfs_palloc_req structure exchanged for the allocation diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h index fb72381..4bd6451 100644 --- a/fs/nilfs2/alloc.h +++ b/fs/nilfs2/alloc.h @@ -48,6 +48,8 @@ int nilfs_palloc_get_entry_block(struct inode *, __u64, int, void *nilfs_palloc_block_get_entry(const struct inode *, __u64, const struct buffer_head *, void *); +int nilfs_palloc_count_max_entries(struct inode *, u64, u64 *); + /** * nilfs_palloc_req - persistent allocator request and reply * @pr_entry_nr: entry number (vblocknr or inode number) diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c index d8e65bd..6548c78 100644 --- a/fs/nilfs2/ifile.c +++ b/fs/nilfs2/ifile.c @@ -160,6 +160,28 @@ int nilfs_ifile_get_inode_block(struct inode *ifile, ino_t ino, } /** + * nilfs_ifile_count_free_inodes - calculate free inodes count + * @ifile: ifile inode + * @nmaxinodes: current maximum of available inodes count [out] + * @nfreeinodes: free inodes count [out] + */ +int nilfs_ifile_count_free_inodes(struct inode *ifile, + u64 *nmaxinodes, u64 *nfreeinodes) +{ + u64 nused; + int err; + + *nmaxinodes = 0; + *nfreeinodes = 0; + + nused = atomic64_read(&NILFS_I(ifile)->i_root->inodes_count); + err = nilfs_palloc_count_max_entries(ifile, nused, nmaxinodes); + if (likely(!err)) + *nfreeinodes = *nmaxinodes - nused; + return err; +} + +/** * nilfs_ifile_read - read or get ifile inode * @sb: super block instance * @root: root object diff --git a/fs/nilfs2/ifile.h b/fs/nilfs2/ifile.h index 59b6f2b..679674d 100644 --- a/fs/nilfs2/ifile.h +++ b/fs/nilfs2/ifile.h @@ -49,6 +49,8 @@ int nilfs_ifile_create_inode(struct inode *, ino_t *, struct buffer_head **); int nilfs_ifile_delete_inode(struct inode *, ino_t); int nilfs_ifile_get_inode_block(struct inode *, ino_t, struct buffer_head **); +int nilfs_ifile_count_free_inodes(struct inode *, u64 *, u64 *); + int nilfs_ifile_read(struct super_block *sb, struct nilfs_root *root, size_t inode_size, struct nilfs_inode *raw_inode, struct inode **inodep); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index bccfec8..b1a5277 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -54,7 +54,7 @@ void nilfs_inode_add_blocks(struct inode *inode, int n) inode_add_bytes(inode, (1 << inode->i_blkbits) * n); if (root) - atomic_add(n, &root->blocks_count); + atomic64_add(n, &root->blocks_count); } void nilfs_inode_sub_blocks(struct inode *inode, int n) @@ -63,7 +63,7 @@ void nilfs_inode_sub_blocks(struct inode *inode, int n) inode_sub_bytes(inode, (1 << inode->i_blkbits) * n); if (root) - atomic_sub(n, &root->blocks_count); + atomic64_sub(n, &root->blocks_count); } /** @@ -369,7 +369,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) goto failed_ifile_create_inode; /* reference count of i_bh inherits from nilfs_mdt_read_block() */ - atomic_inc(&root->inodes_count); + atomic64_inc(&root->inodes_count); inode_init_owner(inode, dir, mode); inode->i_ino = ino; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; @@ -801,7 +801,7 @@ void nilfs_evict_inode(struct inode *inode) ret = nilfs_ifile_delete_inode(ii->i_root->ifile, inode->i_ino); if (!ret) - atomic_dec(&ii->i_root->inodes_count); + atomic64_dec(&ii->i_root->inodes_count); nilfs_clear_inode(inode); diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index a5752a58..bd88a74 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -835,9 +835,9 @@ static int nilfs_segctor_fill_in_checkpoint(struct nilfs_sc_info *sci) raw_cp->cp_snapshot_list.ssl_next = 0; raw_cp->cp_snapshot_list.ssl_prev = 0; raw_cp->cp_inodes_count = - cpu_to_le64(atomic_read(&sci->sc_root->inodes_count)); + cpu_to_le64(atomic64_read(&sci->sc_root->inodes_count)); raw_cp->cp_blocks_count = - cpu_to_le64(atomic_read(&sci->sc_root->blocks_count)); + cpu_to_le64(atomic64_read(&sci->sc_root->blocks_count)); raw_cp->cp_nblk_inc = cpu_to_le64(sci->sc_nblk_inc + sci->sc_nblk_this_inc); raw_cp->cp_create = cpu_to_le64(sci->sc_seg_ctime); diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index c7d1f9f..1427de5 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -554,8 +554,10 @@ int nilfs_attach_checkpoint(struct super_block *sb, __u64 cno, int curr_mnt, if (err) goto failed_bh; - atomic_set(&root->inodes_count, le64_to_cpu(raw_cp->cp_inodes_count)); - atomic_set(&root->blocks_count, le64_to_cpu(raw_cp->cp_blocks_count)); + atomic64_set(&root->inodes_count, + le64_to_cpu(raw_cp->cp_inodes_count)); + atomic64_set(&root->blocks_count, + le64_to_cpu(raw_cp->cp_blocks_count)); nilfs_cpfile_put_checkpoint(nilfs->ns_cpfile, cno, bh_cp); @@ -609,6 +611,7 @@ static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf) unsigned long overhead; unsigned long nrsvblocks; sector_t nfreeblocks; + u64 nmaxinodes, nfreeinodes; int err; /* @@ -633,14 +636,34 @@ static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf) if (unlikely(err)) return err; + err = nilfs_ifile_count_free_inodes(root->ifile, + &nmaxinodes, &nfreeinodes); + if (unlikely(err)) { + printk(KERN_WARNING + "NILFS warning: fail to count free inodes: err %d.\n", + err); + if (err == -ERANGE) { + /* + * If nilfs_palloc_count_max_entries() returns + * -ERANGE error code then we simply treat + * curent inodes count as maximum possible and + * zero as free inodes value. + */ + nmaxinodes = atomic64_read(&root->inodes_count); + nfreeinodes = 0; + err = 0; + } else + return err; + } + buf->f_type = NILFS_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = blocks - overhead; buf->f_bfree = nfreeblocks; buf->f_bavail = (buf->f_bfree >= nrsvblocks) ? (buf->f_bfree - nrsvblocks) : 0; - buf->f_files = atomic_read(&root->inodes_count); - buf->f_ffree = 0; /* nilfs_count_free_inodes(sb); */ + buf->f_files = nmaxinodes; + buf->f_ffree = nfreeinodes; buf->f_namelen = NILFS_NAME_LEN; buf->f_fsid.val[0] = (u32)id; buf->f_fsid.val[1] = (u32)(id >> 32); diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 41e6a04..94c451c 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -764,8 +764,8 @@ nilfs_find_or_create_root(struct the_nilfs *nilfs, __u64 cno) new->ifile = NULL; new->nilfs = nilfs; atomic_set(&new->count, 1); - atomic_set(&new->inodes_count, 0); - atomic_set(&new->blocks_count, 0); + atomic64_set(&new->inodes_count, 0); + atomic64_set(&new->blocks_count, 0); rb_link_node(&new->rb_node, parent, p); rb_insert_color(&new->rb_node, &nilfs->ns_cptree); diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index be1267a..de8cc53 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -241,8 +241,8 @@ struct nilfs_root { struct the_nilfs *nilfs; struct inode *ifile; - atomic_t inodes_count; - atomic_t blocks_count; + atomic64_t inodes_count; + atomic64_t blocks_count; }; /* Special checkpoint number */ diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index b8a9d87..17e6bdd 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -5655,7 +5655,7 @@ int ocfs2_remove_btree_range(struct inode *inode, &ref_tree, NULL); if (ret) { mlog_errno(ret); - goto out; + goto bail; } ret = ocfs2_prepare_refcount_change_for_del(inode, @@ -5666,7 +5666,7 @@ int ocfs2_remove_btree_range(struct inode *inode, &extra_blocks); if (ret < 0) { mlog_errno(ret); - goto out; + goto bail; } } @@ -5674,7 +5674,7 @@ int ocfs2_remove_btree_range(struct inode *inode, extra_blocks); if (ret) { mlog_errno(ret); - return ret; + goto bail; } mutex_lock(&tl_inode->i_mutex); @@ -5734,7 +5734,7 @@ out_commit: ocfs2_commit_trans(osb, handle); out: mutex_unlock(&tl_inode->i_mutex); - +bail: if (meta_ac) ocfs2_free_alloc_context(meta_ac); diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 42252bf..5c1c864 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -176,7 +176,7 @@ static void o2hb_dead_threshold_set(unsigned int threshold) } } -static int o2hb_global_hearbeat_mode_set(unsigned int hb_mode) +static int o2hb_global_heartbeat_mode_set(unsigned int hb_mode) { int ret = -1; @@ -500,7 +500,7 @@ static int o2hb_issue_node_write(struct o2hb_region *reg, } atomic_inc(&write_wc->wc_num_reqs); - submit_bio(WRITE, bio); + submit_bio(WRITE_SYNC, bio); status = 0; bail: @@ -2271,7 +2271,7 @@ ssize_t o2hb_heartbeat_group_mode_store(struct o2hb_heartbeat_group *group, if (strnicmp(page, o2hb_heartbeat_mode_desc[i], len)) continue; - ret = o2hb_global_hearbeat_mode_set(i); + ret = o2hb_global_heartbeat_mode_set(i); if (!ret) printk(KERN_NOTICE "o2hb: Heartbeat mode set to %s\n", o2hb_heartbeat_mode_desc[i]); @@ -2304,7 +2304,7 @@ static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = { NULL, }; -static struct configfs_item_operations o2hb_hearbeat_group_item_ops = { +static struct configfs_item_operations o2hb_heartbeat_group_item_ops = { .show_attribute = o2hb_heartbeat_group_show, .store_attribute = o2hb_heartbeat_group_store, }; @@ -2316,7 +2316,7 @@ static struct configfs_group_operations o2hb_heartbeat_group_group_ops = { static struct config_item_type o2hb_heartbeat_group_type = { .ct_group_ops = &o2hb_heartbeat_group_group_ops, - .ct_item_ops = &o2hb_hearbeat_group_item_ops, + .ct_item_ops = &o2hb_heartbeat_group_item_ops, .ct_attrs = o2hb_heartbeat_group_attrs, .ct_owner = THIS_MODULE, }; @@ -2389,6 +2389,9 @@ static int o2hb_region_pin(const char *region_uuid) assert_spin_locked(&o2hb_live_lock); list_for_each_entry(reg, &o2hb_all_regions, hr_all_item) { + if (reg->hr_item_dropped) + continue; + uuid = config_item_name(®->hr_item); /* local heartbeat */ @@ -2439,6 +2442,9 @@ static void o2hb_region_unpin(const char *region_uuid) assert_spin_locked(&o2hb_live_lock); list_for_each_entry(reg, &o2hb_all_regions, hr_all_item) { + if (reg->hr_item_dropped) + continue; + uuid = config_item_name(®->hr_item); if (region_uuid) { if (strcmp(region_uuid, uuid)) @@ -2654,6 +2660,9 @@ int o2hb_get_all_regions(char *region_uuids, u8 max_regions) p = region_uuids; list_for_each_entry(reg, &o2hb_all_regions, hr_all_item) { + if (reg->hr_item_dropped) + continue; + mlog(0, "Region: %s\n", config_item_name(®->hr_item)); if (numregs < max_regions) { memcpy(p, config_item_name(®->hr_item), diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c index c19897d..1ec141e 100644 --- a/fs/ocfs2/cluster/quorum.c +++ b/fs/ocfs2/cluster/quorum.c @@ -264,7 +264,7 @@ void o2quo_hb_still_up(u8 node) /* This is analogous to hb_up. as a node's connection comes up we delay the * quorum decision until we see it heartbeating. the hold will be droped in * hb_up or hb_down. it might be perpetuated by con_err until hb_down. if - * it's already heartbeating we we might be dropping a hold that conn_up got. + * it's already heartbeating we might be dropping a hold that conn_up got. * */ void o2quo_conn_up(u8 node) { diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index aa88bd8..d644dc6 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -406,6 +406,9 @@ static void sc_kref_release(struct kref *kref) sc->sc_node = NULL; o2net_debug_del_sc(sc); + + if (sc->sc_page) + __free_page(sc->sc_page); kfree(sc); } @@ -630,19 +633,19 @@ static void o2net_state_change(struct sock *sk) state_change = sc->sc_state_change; switch(sk->sk_state) { - /* ignore connecting sockets as they make progress */ - case TCP_SYN_SENT: - case TCP_SYN_RECV: - break; - case TCP_ESTABLISHED: - o2net_sc_queue_work(sc, &sc->sc_connect_work); - break; - default: - printk(KERN_INFO "o2net: Connection to " SC_NODEF_FMT - " shutdown, state %d\n", - SC_NODEF_ARGS(sc), sk->sk_state); - o2net_sc_queue_work(sc, &sc->sc_shutdown_work); - break; + /* ignore connecting sockets as they make progress */ + case TCP_SYN_SENT: + case TCP_SYN_RECV: + break; + case TCP_ESTABLISHED: + o2net_sc_queue_work(sc, &sc->sc_connect_work); + break; + default: + printk(KERN_INFO "o2net: Connection to " SC_NODEF_FMT + " shutdown, state %d\n", + SC_NODEF_ARGS(sc), sk->sk_state); + o2net_sc_queue_work(sc, &sc->sc_shutdown_work); + break; } out: read_unlock(&sk->sk_callback_lock); diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c index 975810b..47e67c2 100644 --- a/fs/ocfs2/dlm/dlmlock.c +++ b/fs/ocfs2/dlm/dlmlock.c @@ -178,6 +178,7 @@ static enum dlm_status dlmlock_master(struct dlm_ctxt *dlm, lock->ml.node); } } else { + status = DLM_NORMAL; dlm_lock_get(lock); list_add_tail(&lock->list, &res->blocked); kick_thread = 1; diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index e68588e..773bd32 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -55,9 +55,6 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node); static int dlm_recovery_thread(void *data); -void dlm_complete_recovery_thread(struct dlm_ctxt *dlm); -int dlm_launch_recovery_thread(struct dlm_ctxt *dlm); -void dlm_kick_recovery_thread(struct dlm_ctxt *dlm); static int dlm_do_recovery(struct dlm_ctxt *dlm); static int dlm_pick_recovery_master(struct dlm_ctxt *dlm); @@ -789,7 +786,7 @@ static int dlm_request_all_locks(struct dlm_ctxt *dlm, u8 request_from, u8 dead_node) { struct dlm_lock_request lr; - enum dlm_status ret; + int ret; mlog(0, "\n"); @@ -802,7 +799,6 @@ static int dlm_request_all_locks(struct dlm_ctxt *dlm, u8 request_from, lr.dead_node = dead_node; // send message - ret = DLM_NOLOCKMGR; ret = o2net_send_message(DLM_LOCK_REQUEST_MSG, dlm->key, &lr, sizeof(lr), request_from, NULL); @@ -2696,6 +2692,7 @@ int dlm_begin_reco_handler(struct o2net_msg *msg, u32 len, void *data, dlm->name, br->node_idx, br->dead_node, dlm->reco.dead_node, dlm->reco.new_master); spin_unlock(&dlm->spinlock); + dlm_put(dlm); return -EAGAIN; } spin_unlock(&dlm->spinlock); diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index a3385b6..96f9ac2 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -200,7 +200,6 @@ void ocfs2_complete_quota_recovery(struct ocfs2_super *osb); static inline void ocfs2_start_checkpoint(struct ocfs2_super *osb) { - atomic_set(&osb->needs_checkpoint, 1); wake_up(&osb->checkpoint_event); } @@ -538,7 +537,7 @@ static inline int ocfs2_calc_extend_credits(struct super_block *sb, extent_blocks = 1 + 1 + le16_to_cpu(root_el->l_tree_depth); return bitmap_blocks + sysfile_bitmap_blocks + extent_blocks + - ocfs2_quota_trans_credits(sb); + ocfs2_quota_trans_credits(sb) + bits_wanted; } static inline int ocfs2_calc_symlink_credits(struct super_block *sb) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index b4a5cdf..be3f867 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -522,7 +522,7 @@ static int __ocfs2_mknod_locked(struct inode *dir, fe->i_last_eb_blk = 0; strcpy(fe->i_signature, OCFS2_INODE_SIGNATURE); - le32_add_cpu(&fe->i_flags, OCFS2_VALID_FL); + fe->i_flags |= cpu_to_le32(OCFS2_VALID_FL); fe->i_atime = fe->i_ctime = fe->i_mtime = cpu_to_le64(CURRENT_TIME.tv_sec); fe->i_mtime_nsec = fe->i_ctime_nsec = fe->i_atime_nsec = @@ -773,7 +773,7 @@ static int ocfs2_remote_dentry_delete(struct dentry *dentry) return ret; } -static inline int inode_is_unlinkable(struct inode *inode) +static inline int ocfs2_inode_is_unlinkable(struct inode *inode) { if (S_ISDIR(inode->i_mode)) { if (inode->i_nlink == 2) @@ -791,6 +791,7 @@ static int ocfs2_unlink(struct inode *dir, { int status; int child_locked = 0; + bool is_unlinkable = false; struct inode *inode = dentry->d_inode; struct inode *orphan_dir = NULL; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); @@ -865,7 +866,7 @@ static int ocfs2_unlink(struct inode *dir, goto leave; } - if (inode_is_unlinkable(inode)) { + if (ocfs2_inode_is_unlinkable(inode)) { status = ocfs2_prepare_orphan_dir(osb, &orphan_dir, OCFS2_I(inode)->ip_blkno, orphan_name, &orphan_insert); @@ -873,6 +874,7 @@ static int ocfs2_unlink(struct inode *dir, mlog_errno(status); goto leave; } + is_unlinkable = true; } handle = ocfs2_start_trans(osb, ocfs2_unlink_credits(osb->sb)); @@ -892,15 +894,6 @@ static int ocfs2_unlink(struct inode *dir, fe = (struct ocfs2_dinode *) fe_bh->b_data; - if (inode_is_unlinkable(inode)) { - status = ocfs2_orphan_add(osb, handle, inode, fe_bh, orphan_name, - &orphan_insert, orphan_dir); - if (status < 0) { - mlog_errno(status); - goto leave; - } - } - /* delete the name from the parent dir */ status = ocfs2_delete_entry(handle, dir, &lookup); if (status < 0) { @@ -923,6 +916,14 @@ static int ocfs2_unlink(struct inode *dir, mlog_errno(status); if (S_ISDIR(inode->i_mode)) inc_nlink(dir); + goto leave; + } + + if (is_unlinkable) { + status = ocfs2_orphan_add(osb, handle, inode, fe_bh, + orphan_name, &orphan_insert, orphan_dir); + if (status < 0) + mlog_errno(status); } leave: @@ -2012,6 +2013,21 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb, goto leave; } + /* + * We're going to journal the change of i_flags and i_orphaned_slot. + * It's safe anyway, though some callers may duplicate the journaling. + * Journaling within the func just make the logic look more + * straightforward. + */ + status = ocfs2_journal_access_di(handle, + INODE_CACHE(inode), + fe_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (status < 0) { + mlog_errno(status); + goto leave; + } + /* we're a cluster, and nlink can change on disk from * underneath us... */ orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data; @@ -2026,25 +2042,10 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb, orphan_dir_bh, lookup); if (status < 0) { mlog_errno(status); - goto leave; - } - - /* - * We're going to journal the change of i_flags and i_orphaned_slot. - * It's safe anyway, though some callers may duplicate the journaling. - * Journaling within the func just make the logic look more - * straightforward. - */ - status = ocfs2_journal_access_di(handle, - INODE_CACHE(inode), - fe_bh, - OCFS2_JOURNAL_ACCESS_WRITE); - if (status < 0) { - mlog_errno(status); - goto leave; + goto rollback; } - le32_add_cpu(&fe->i_flags, OCFS2_ORPHANED_FL); + fe->i_flags |= cpu_to_le32(OCFS2_ORPHANED_FL); OCFS2_I(inode)->ip_flags &= ~OCFS2_INODE_SKIP_ORPHAN_DIR; /* Record which orphan dir our inode now resides @@ -2057,11 +2058,16 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb, trace_ocfs2_orphan_add_end((unsigned long long)OCFS2_I(inode)->ip_blkno, osb->slot_num); +rollback: + if (status < 0) { + if (S_ISDIR(inode->i_mode)) + ocfs2_add_links_count(orphan_fe, -1); + set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe)); + } + leave: brelse(orphan_dir_bh); - if (status) - mlog_errno(status); return status; } @@ -2434,7 +2440,7 @@ int ocfs2_mv_orphaned_inode_to_new(struct inode *dir, } di = (struct ocfs2_dinode *)di_bh->b_data; - le32_add_cpu(&di->i_flags, -OCFS2_ORPHANED_FL); + di->i_flags &= ~cpu_to_le32(OCFS2_ORPHANED_FL); di->i_orphaned_slot = 0; set_nlink(inode, 1); ocfs2_set_links_count(di, inode->i_nlink); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index d355e6e..3a90347 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -347,7 +347,6 @@ struct ocfs2_super struct task_struct *recovery_thread_task; int disable_recovery; wait_queue_head_t checkpoint_event; - atomic_t needs_checkpoint; struct ocfs2_journal *journal; unsigned long osb_commit_interval; diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index b7e74b5..5397c07 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -1422,7 +1422,7 @@ static int ocfs2_relink_block_group(handle_t *handle, int status; /* there is a really tiny chance the journal calls could fail, * but we wouldn't want inconsistent blocks in *any* case. */ - u64 fe_ptr, bg_ptr, prev_bg_ptr; + u64 bg_ptr, prev_bg_ptr; struct ocfs2_dinode *fe = (struct ocfs2_dinode *) fe_bh->b_data; struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data; struct ocfs2_group_desc *prev_bg = (struct ocfs2_group_desc *) prev_bg_bh->b_data; @@ -1437,51 +1437,44 @@ static int ocfs2_relink_block_group(handle_t *handle, (unsigned long long)le64_to_cpu(bg->bg_blkno), (unsigned long long)le64_to_cpu(prev_bg->bg_blkno)); - fe_ptr = le64_to_cpu(fe->id2.i_chain.cl_recs[chain].c_blkno); bg_ptr = le64_to_cpu(bg->bg_next_group); prev_bg_ptr = le64_to_cpu(prev_bg->bg_next_group); status = ocfs2_journal_access_gd(handle, INODE_CACHE(alloc_inode), prev_bg_bh, OCFS2_JOURNAL_ACCESS_WRITE); - if (status < 0) { - mlog_errno(status); - goto out_rollback; - } + if (status < 0) + goto out; prev_bg->bg_next_group = bg->bg_next_group; ocfs2_journal_dirty(handle, prev_bg_bh); status = ocfs2_journal_access_gd(handle, INODE_CACHE(alloc_inode), bg_bh, OCFS2_JOURNAL_ACCESS_WRITE); - if (status < 0) { - mlog_errno(status); - goto out_rollback; - } + if (status < 0) + goto out_rollback_prev_bg; bg->bg_next_group = fe->id2.i_chain.cl_recs[chain].c_blkno; ocfs2_journal_dirty(handle, bg_bh); status = ocfs2_journal_access_di(handle, INODE_CACHE(alloc_inode), fe_bh, OCFS2_JOURNAL_ACCESS_WRITE); - if (status < 0) { - mlog_errno(status); - goto out_rollback; - } + if (status < 0) + goto out_rollback_bg; fe->id2.i_chain.cl_recs[chain].c_blkno = bg->bg_blkno; ocfs2_journal_dirty(handle, fe_bh); -out_rollback: - if (status < 0) { - fe->id2.i_chain.cl_recs[chain].c_blkno = cpu_to_le64(fe_ptr); - bg->bg_next_group = cpu_to_le64(bg_ptr); - prev_bg->bg_next_group = cpu_to_le64(prev_bg_ptr); - } - - if (status) +out: + if (status < 0) mlog_errno(status); return status; + +out_rollback_bg: + bg->bg_next_group = cpu_to_le64(bg_ptr); +out_rollback_prev_bg: + prev_bg->bg_next_group = cpu_to_le64(prev_bg_ptr); + goto out; } static inline int ocfs2_block_group_reasonably_empty(struct ocfs2_group_desc *bg, diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 01b8516..854d809 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -286,10 +286,9 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len) spin_unlock(&osb->osb_lock); out += snprintf(buf + out, len - out, - "%10s => Pid: %d Interval: %lu Needs: %d\n", "Commit", + "%10s => Pid: %d Interval: %lu\n", "Commit", (osb->commit_task ? task_pid_nr(osb->commit_task) : -1), - osb->osb_commit_interval, - atomic_read(&osb->needs_checkpoint)); + osb->osb_commit_interval); out += snprintf(buf + out, len - out, "%10s => State: %d TxnId: %lu NumTxns: %d\n", @@ -2154,7 +2153,6 @@ static int ocfs2_initialize_super(struct super_block *sb, } init_waitqueue_head(&osb->checkpoint_event); - atomic_set(&osb->needs_checkpoint, 0); osb->s_atime_quantum = OCFS2_DEFAULT_ATIME_QUANTUM; diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 2e3ea30..317ef0a 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -2751,7 +2751,6 @@ static int ocfs2_xattr_ibody_set(struct inode *inode, { int ret; struct ocfs2_inode_info *oi = OCFS2_I(inode); - struct ocfs2_dinode *di = (struct ocfs2_dinode *)xs->inode_bh->b_data; struct ocfs2_xa_loc loc; if (inode->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE) @@ -2759,13 +2758,6 @@ static int ocfs2_xattr_ibody_set(struct inode *inode, down_write(&oi->ip_alloc_sem); if (!(oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)) { - if (!ocfs2_xattr_has_space_inline(inode, di)) { - ret = -ENOSPC; - goto out; - } - } - - if (!(oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)) { ret = ocfs2_xattr_ibody_init(inode, xs->inode_bh, ctxt); if (ret) { if (ret != -ENOSPC) @@ -6499,6 +6491,16 @@ static int ocfs2_reflink_xattr_inline(struct ocfs2_xattr_reflink *args) } new_oi = OCFS2_I(args->new_inode); + /* + * Adjust extent record count to reserve space for extended attribute. + * Inline data count had been adjusted in ocfs2_duplicate_inline_data(). + */ + if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) && + !(ocfs2_inode_is_fast_symlink(args->new_inode))) { + struct ocfs2_extent_list *el = &new_di->id2.i_list; + le16_add_cpu(&el->l_count, -(inline_size / + sizeof(struct ocfs2_extent_rec))); + } spin_lock(&new_oi->ip_lock); new_oi->ip_dyn_features |= OCFS2_HAS_XATTR_FL | OCFS2_INLINE_XATTR_FL; new_di->i_dyn_features = cpu_to_le16(new_oi->ip_dyn_features); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 0a22194..06ea155 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -408,7 +408,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff) prpsinfo.pr_zomb = 0; strcpy(prpsinfo.pr_fname, "vmlinux"); - strncpy(prpsinfo.pr_psargs, saved_command_line, ELF_PRARGSZ); + strlcpy(prpsinfo.pr_psargs, saved_command_line, sizeof(prpsinfo.pr_psargs)); nhdr->p_filesz += notesize(¬es[1]); bufp = storenote(¬es[1], bufp); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 3e636d8..dbf61f6 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -11,6 +11,7 @@ #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/mmu_notifier.h> #include <asm/elf.h> #include <asm/uaccess.h> @@ -688,10 +689,58 @@ const struct file_operations proc_tid_smaps_operations = { .release = seq_release_private, }; +/* + * We do not want to have constant page-shift bits sitting in + * pagemap entries and are about to reuse them some time soon. + * + * Here's the "migration strategy": + * 1. when the system boots these bits remain what they are, + * but a warning about future change is printed in log; + * 2. once anyone clears soft-dirty bits via clear_refs file, + * these flag is set to denote, that user is aware of the + * new API and those page-shift bits change their meaning. + * The respective warning is printed in dmesg; + * 3. In a couple of releases we will remove all the mentions + * of page-shift in pagemap entries. + */ + +static bool soft_dirty_cleared __read_mostly; + +enum clear_refs_types { + CLEAR_REFS_ALL = 1, + CLEAR_REFS_ANON, + CLEAR_REFS_MAPPED, + CLEAR_REFS_SOFT_DIRTY, + CLEAR_REFS_LAST, +}; + +struct clear_refs_private { + struct vm_area_struct *vma; + enum clear_refs_types type; +}; + +static inline void clear_soft_dirty(struct vm_area_struct *vma, + unsigned long addr, pte_t *pte) +{ +#ifdef CONFIG_MEM_SOFT_DIRTY + /* + * The soft-dirty tracker uses #PF-s to catch writes + * to pages, so write-protect the pte as well. See the + * Documentation/vm/soft-dirty.txt for full description + * of how soft-dirty works. + */ + pte_t ptent = *pte; + ptent = pte_wrprotect(ptent); + ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY); + set_pte_at(vma->vm_mm, addr, pte, ptent); +#endif +} + static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct vm_area_struct *vma = walk->private; + struct clear_refs_private *cp = walk->private; + struct vm_area_struct *vma = cp->vma; pte_t *pte, ptent; spinlock_t *ptl; struct page *page; @@ -706,6 +755,11 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, if (!pte_present(ptent)) continue; + if (cp->type == CLEAR_REFS_SOFT_DIRTY) { + clear_soft_dirty(vma, addr, pte); + continue; + } + page = vm_normal_page(vma, addr, ptent); if (!page) continue; @@ -719,10 +773,6 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, return 0; } -#define CLEAR_REFS_ALL 1 -#define CLEAR_REFS_ANON 2 -#define CLEAR_REFS_MAPPED 3 - static ssize_t clear_refs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -730,7 +780,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, char buffer[PROC_NUMBUF]; struct mm_struct *mm; struct vm_area_struct *vma; - int type; + enum clear_refs_types type; + int itype; int rv; memset(buffer, 0, sizeof(buffer)); @@ -738,23 +789,37 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; - rv = kstrtoint(strstrip(buffer), 10, &type); + rv = kstrtoint(strstrip(buffer), 10, &itype); if (rv < 0) return rv; - if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED) + type = (enum clear_refs_types)itype; + if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST) return -EINVAL; + + if (type == CLEAR_REFS_SOFT_DIRTY) { + soft_dirty_cleared = true; + pr_warn_once("The pagemap bits 55-60 has changed their meaning! " + "See the linux/Documentation/vm/pagemap.txt for details.\n"); + } + task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; mm = get_task_mm(task); if (mm) { + struct clear_refs_private cp = { + .type = type, + }; struct mm_walk clear_refs_walk = { .pmd_entry = clear_refs_pte_range, .mm = mm, + .private = &cp, }; down_read(&mm->mmap_sem); + if (type == CLEAR_REFS_SOFT_DIRTY) + mmu_notifier_invalidate_range_start(mm, 0, -1); for (vma = mm->mmap; vma; vma = vma->vm_next) { - clear_refs_walk.private = vma; + cp.vma = vma; if (is_vm_hugetlb_page(vma)) continue; /* @@ -773,6 +838,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, walk_page_range(vma->vm_start, vma->vm_end, &clear_refs_walk); } + if (type == CLEAR_REFS_SOFT_DIRTY) + mmu_notifier_invalidate_range_end(mm, 0, -1); flush_tlb_mm(mm); up_read(&mm->mmap_sem); mmput(mm); @@ -794,6 +861,7 @@ typedef struct { struct pagemapread { int pos, len; pagemap_entry_t *buffer; + bool v2; }; #define PAGEMAP_WALK_SIZE (PMD_SIZE) @@ -807,14 +875,17 @@ struct pagemapread { #define PM_PSHIFT_BITS 6 #define PM_PSHIFT_OFFSET (PM_STATUS_OFFSET - PM_PSHIFT_BITS) #define PM_PSHIFT_MASK (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET) -#define PM_PSHIFT(x) (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK) +#define __PM_PSHIFT(x) (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK) #define PM_PFRAME_MASK ((1LL << PM_PSHIFT_OFFSET) - 1) #define PM_PFRAME(x) ((x) & PM_PFRAME_MASK) +/* in "new" pagemap pshift bits are occupied with more status bits */ +#define PM_STATUS2(v2, x) (__PM_PSHIFT(v2 ? x : PAGE_SHIFT)) +#define __PM_SOFT_DIRTY (1LL) #define PM_PRESENT PM_STATUS(4LL) #define PM_SWAP PM_STATUS(2LL) #define PM_FILE PM_STATUS(1LL) -#define PM_NOT_PRESENT PM_PSHIFT(PAGE_SHIFT) +#define PM_NOT_PRESENT(v2) PM_STATUS2(v2, 0) #define PM_END_OF_BUFFER 1 static inline pagemap_entry_t make_pme(u64 val) @@ -837,7 +908,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end, struct pagemapread *pm = walk->private; unsigned long addr; int err = 0; - pagemap_entry_t pme = make_pme(PM_NOT_PRESENT); + pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2)); for (addr = start; addr < end; addr += PAGE_SIZE) { err = add_to_pagemap(addr, &pme, pm); @@ -847,11 +918,12 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end, return err; } -static void pte_to_pagemap_entry(pagemap_entry_t *pme, +static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, struct vm_area_struct *vma, unsigned long addr, pte_t pte) { u64 frame, flags; struct page *page = NULL; + int flags2 = 0; if (pte_present(pte)) { frame = pte_pfn(pte); @@ -866,19 +938,21 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, if (is_migration_entry(entry)) page = migration_entry_to_page(entry); } else { - *pme = make_pme(PM_NOT_PRESENT); + *pme = make_pme(PM_NOT_PRESENT(pm->v2)); return; } if (page && !PageAnon(page)) flags |= PM_FILE; + if (pte_soft_dirty(pte)) + flags2 |= __PM_SOFT_DIRTY; - *pme = make_pme(PM_PFRAME(frame) | PM_PSHIFT(PAGE_SHIFT) | flags); + *pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, - pmd_t pmd, int offset) +static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, + pmd_t pmd, int offset, int pmd_flags2) { /* * Currently pmd for thp is always present because thp can not be @@ -887,13 +961,13 @@ static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, */ if (pmd_present(pmd)) *pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset) - | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT); + | PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT); else - *pme = make_pme(PM_NOT_PRESENT); + *pme = make_pme(PM_NOT_PRESENT(pm->v2)); } #else -static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, - pmd_t pmd, int offset) +static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, + pmd_t pmd, int offset, int pmd_flags2) { } #endif @@ -905,17 +979,20 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct pagemapread *pm = walk->private; pte_t *pte; int err = 0; - pagemap_entry_t pme = make_pme(PM_NOT_PRESENT); + pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2)); /* find the first VMA at or above 'addr' */ vma = find_vma(walk->mm, addr); if (vma && pmd_trans_huge_lock(pmd, vma) == 1) { + int pmd_flags2; + + pmd_flags2 = (pmd_soft_dirty(*pmd) ? __PM_SOFT_DIRTY : 0); for (; addr != end; addr += PAGE_SIZE) { unsigned long offset; offset = (addr & ~PAGEMAP_WALK_MASK) >> PAGE_SHIFT; - thp_pmd_to_pagemap_entry(&pme, *pmd, offset); + thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset, pmd_flags2); err = add_to_pagemap(addr, &pme, pm); if (err) break; @@ -932,7 +1009,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, * and need a new, higher one */ if (vma && (addr >= vma->vm_end)) { vma = find_vma(walk->mm, addr); - pme = make_pme(PM_NOT_PRESENT); + pme = make_pme(PM_NOT_PRESENT(pm->v2)); } /* check that 'vma' actually covers this address, @@ -940,7 +1017,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, if (vma && (vma->vm_start <= addr) && !is_vm_hugetlb_page(vma)) { pte = pte_offset_map(pmd, addr); - pte_to_pagemap_entry(&pme, vma, addr, *pte); + pte_to_pagemap_entry(&pme, pm, vma, addr, *pte); /* unmap before userspace copy */ pte_unmap(pte); } @@ -955,14 +1032,14 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, } #ifdef CONFIG_HUGETLB_PAGE -static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, +static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, pte_t pte, int offset) { if (pte_present(pte)) *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset) - | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT); + | PM_STATUS2(pm->v2, 0) | PM_PRESENT); else - *pme = make_pme(PM_NOT_PRESENT); + *pme = make_pme(PM_NOT_PRESENT(pm->v2)); } /* This function walks within one hugetlb entry in the single call */ @@ -976,7 +1053,7 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask, for (; addr != end; addr += PAGE_SIZE) { int offset = (addr & ~hmask) >> PAGE_SHIFT; - huge_pte_to_pagemap_entry(&pme, *pte, offset); + huge_pte_to_pagemap_entry(&pme, pm, *pte, offset); err = add_to_pagemap(addr, &pme, pm); if (err) return err; @@ -1038,6 +1115,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, if (!count) goto out_task; + pm.v2 = soft_dirty_cleared; pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT); pm.buffer = kmalloc(pm.len, GFP_TEMPORARY); ret = -ENOMEM; @@ -1110,9 +1188,18 @@ out: return ret; } +static int pagemap_open(struct inode *inode, struct file *file) +{ + pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about " + "to stop being page-shift some time soon. See the " + "linux/Documentation/vm/pagemap.txt for details.\n"); + return 0; +} + const struct file_operations proc_pagemap_operations = { .llseek = mem_lseek, /* borrow this */ .read = pagemap_read, + .open = pagemap_open, }; #endif /* CONFIG_PROC_PAGE_MONITOR */ diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c index 9610ac7..0618946 100644 --- a/fs/proc/uptime.c +++ b/fs/proc/uptime.c @@ -20,8 +20,7 @@ static int uptime_proc_show(struct seq_file *m, void *v) for_each_possible_cpu(i) idletime += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE]; - do_posix_clock_monotonic_gettime(&uptime); - monotonic_to_bootbased(&uptime); + get_monotonic_boottime(&uptime); nsec = cputime64_to_jiffies64(idletime) * TICK_NSEC; idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); idle.tv_nsec = rem; diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 17f7e08..2850317 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -20,6 +20,7 @@ #include <linux/init.h> #include <linux/crash_dump.h> #include <linux/list.h> +#include <linux/vmalloc.h> #include <asm/uaccess.h> #include <asm/io.h> #include "internal.h" @@ -32,6 +33,10 @@ static LIST_HEAD(vmcore_list); /* Stores the pointer to the buffer containing kernel elf core headers. */ static char *elfcorebuf; static size_t elfcorebuf_sz; +static size_t elfcorebuf_sz_orig; + +static char *elfnotes_buf; +static size_t elfnotes_sz; /* Total size of vmcore file. */ static u64 vmcore_size; @@ -118,27 +123,6 @@ static ssize_t read_from_oldmem(char *buf, size_t count, return read; } -/* Maps vmcore file offset to respective physical address in memroy. */ -static u64 map_offset_to_paddr(loff_t offset, struct list_head *vc_list, - struct vmcore **m_ptr) -{ - struct vmcore *m; - u64 paddr; - - list_for_each_entry(m, vc_list, list) { - u64 start, end; - start = m->offset; - end = m->offset + m->size - 1; - if (offset >= start && offset <= end) { - paddr = m->paddr + offset - start; - *m_ptr = m; - return paddr; - } - } - *m_ptr = NULL; - return 0; -} - /* Read from the ELF header and then the crash dump. On error, negative value is * returned otherwise number of bytes read are returned. */ @@ -147,8 +131,8 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer, { ssize_t acc = 0, tmp; size_t tsz; - u64 start, nr_bytes; - struct vmcore *curr_m = NULL; + u64 start; + struct vmcore *m = NULL; if (buflen == 0 || *fpos >= vmcore_size) return 0; @@ -159,9 +143,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer, /* Read ELF core header */ if (*fpos < elfcorebuf_sz) { - tsz = elfcorebuf_sz - *fpos; - if (buflen < tsz) - tsz = buflen; + tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen); if (copy_to_user(buffer, elfcorebuf + *fpos, tsz)) return -EFAULT; buflen -= tsz; @@ -174,39 +156,161 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer, return acc; } - start = map_offset_to_paddr(*fpos, &vmcore_list, &curr_m); - if (!curr_m) - return -EINVAL; - - while (buflen) { - tsz = min_t(size_t, buflen, PAGE_SIZE - (start & ~PAGE_MASK)); + /* Read Elf note segment */ + if (*fpos < elfcorebuf_sz + elfnotes_sz) { + void *kaddr; - /* Calculate left bytes in current memory segment. */ - nr_bytes = (curr_m->size - (start - curr_m->paddr)); - if (tsz > nr_bytes) - tsz = nr_bytes; - - tmp = read_from_oldmem(buffer, tsz, &start, 1); - if (tmp < 0) - return tmp; + tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen); + kaddr = elfnotes_buf + *fpos - elfcorebuf_sz; + if (copy_to_user(buffer, kaddr, tsz)) + return -EFAULT; buflen -= tsz; *fpos += tsz; buffer += tsz; acc += tsz; - if (start >= (curr_m->paddr + curr_m->size)) { - if (curr_m->list.next == &vmcore_list) - return acc; /*EOF*/ - curr_m = list_entry(curr_m->list.next, - struct vmcore, list); - start = curr_m->paddr; + + /* leave now if filled buffer already */ + if (buflen == 0) + return acc; + } + + list_for_each_entry(m, &vmcore_list, list) { + if (*fpos < m->offset + m->size) { + tsz = min_t(size_t, m->offset + m->size - *fpos, buflen); + start = m->paddr + *fpos - m->offset; + tmp = read_from_oldmem(buffer, tsz, &start, 1); + if (tmp < 0) + return tmp; + buflen -= tsz; + *fpos += tsz; + buffer += tsz; + acc += tsz; + + /* leave now if filled buffer already */ + if (buflen == 0) + return acc; } } + return acc; } +/** + * alloc_elfnotes_buf - allocate buffer for ELF note segment in + * vmalloc memory + * + * @notes_sz: size of buffer + * + * If CONFIG_MMU is defined, use vmalloc_user() to allow users to mmap + * the buffer to user-space by means of remap_vmalloc_range(). + * + * If CONFIG_MMU is not defined, use vzalloc() since mmap_vmcore() is + * disabled and there's no need to allow users to mmap the buffer. + */ +static inline char *alloc_elfnotes_buf(size_t notes_sz) +{ +#ifdef CONFIG_MMU + return vmalloc_user(notes_sz); +#else + return vzalloc(notes_sz); +#endif +} + +/* + * Disable mmap_vmcore() if CONFIG_MMU is not defined. MMU is + * essential for mmap_vmcore() in order to map physically + * non-contiguous objects (ELF header, ELF note segment and memory + * regions in the 1st kernel pointed to by PT_LOAD entries) into + * virtually contiguous user-space in ELF layout. + */ +#ifdef CONFIG_MMU +static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) +{ + size_t size = vma->vm_end - vma->vm_start; + u64 start, end, len, tsz; + struct vmcore *m; + + start = (u64)vma->vm_pgoff << PAGE_SHIFT; + end = start + size; + + if (size > vmcore_size || end > vmcore_size) + return -EINVAL; + + if (vma->vm_flags & (VM_WRITE | VM_EXEC)) + return -EPERM; + + vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC); + vma->vm_flags |= VM_MIXEDMAP; + + len = 0; + + if (start < elfcorebuf_sz) { + u64 pfn; + + tsz = min(elfcorebuf_sz - (size_t)start, size); + pfn = __pa(elfcorebuf + start) >> PAGE_SHIFT; + if (remap_pfn_range(vma, vma->vm_start, pfn, tsz, + vma->vm_page_prot)) + return -EAGAIN; + size -= tsz; + start += tsz; + len += tsz; + + if (size == 0) + return 0; + } + + if (start < elfcorebuf_sz + elfnotes_sz) { + void *kaddr; + + tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size); + kaddr = elfnotes_buf + start - elfcorebuf_sz; + if (remap_vmalloc_range_partial(vma, vma->vm_start + len, + kaddr, tsz)) + goto fail; + size -= tsz; + start += tsz; + len += tsz; + + if (size == 0) + return 0; + } + + list_for_each_entry(m, &vmcore_list, list) { + if (start < m->offset + m->size) { + u64 paddr = 0; + + tsz = min_t(size_t, m->offset + m->size - start, size); + paddr = m->paddr + start - m->offset; + if (remap_pfn_range(vma, vma->vm_start + len, + paddr >> PAGE_SHIFT, tsz, + vma->vm_page_prot)) + goto fail; + size -= tsz; + start += tsz; + len += tsz; + + if (size == 0) + return 0; + } + } + + return 0; +fail: + do_munmap(vma->vm_mm, vma->vm_start, len); + return -EAGAIN; +} +#else +static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) +{ + return -ENOSYS; +} +#endif + static const struct file_operations proc_vmcore_operations = { .read = read_vmcore, .llseek = default_llseek, + .mmap = mmap_vmcore, }; static struct vmcore* __init get_new_element(void) @@ -214,61 +318,40 @@ static struct vmcore* __init get_new_element(void) return kzalloc(sizeof(struct vmcore), GFP_KERNEL); } -static u64 __init get_vmcore_size_elf64(char *elfptr) +static u64 __init get_vmcore_size(size_t elfsz, size_t elfnotesegsz, + struct list_head *vc_list) { - int i; - u64 size; - Elf64_Ehdr *ehdr_ptr; - Elf64_Phdr *phdr_ptr; - - ehdr_ptr = (Elf64_Ehdr *)elfptr; - phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); - size = sizeof(Elf64_Ehdr) + ((ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr)); - for (i = 0; i < ehdr_ptr->e_phnum; i++) { - size += phdr_ptr->p_memsz; - phdr_ptr++; - } - return size; -} - -static u64 __init get_vmcore_size_elf32(char *elfptr) -{ - int i; u64 size; - Elf32_Ehdr *ehdr_ptr; - Elf32_Phdr *phdr_ptr; + struct vmcore *m; - ehdr_ptr = (Elf32_Ehdr *)elfptr; - phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); - size = sizeof(Elf32_Ehdr) + ((ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr)); - for (i = 0; i < ehdr_ptr->e_phnum; i++) { - size += phdr_ptr->p_memsz; - phdr_ptr++; + size = elfsz + elfnotesegsz; + list_for_each_entry(m, vc_list, list) { + size += m->size; } return size; } -/* Merges all the PT_NOTE headers into one. */ -static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz, - struct list_head *vc_list) +/** + * update_note_header_size_elf64 - update p_memsz member of each PT_NOTE entry + * + * @ehdr_ptr: ELF header + * + * This function updates p_memsz member of each PT_NOTE entry in the + * program header table pointed to by @ehdr_ptr to real size of ELF + * note segment. + */ +static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr) { - int i, nr_ptnote=0, rc=0; - char *tmp; - Elf64_Ehdr *ehdr_ptr; - Elf64_Phdr phdr, *phdr_ptr; + int i, rc=0; + Elf64_Phdr *phdr_ptr; Elf64_Nhdr *nhdr_ptr; - u64 phdr_sz = 0, note_off; - ehdr_ptr = (Elf64_Ehdr *)elfptr; - phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); + phdr_ptr = (Elf64_Phdr *)(ehdr_ptr + 1); for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { - int j; void *notes_section; - struct vmcore *new; u64 offset, max_sz, sz, real_sz = 0; if (phdr_ptr->p_type != PT_NOTE) continue; - nr_ptnote++; max_sz = phdr_ptr->p_memsz; offset = phdr_ptr->p_offset; notes_section = kmalloc(max_sz, GFP_KERNEL); @@ -280,7 +363,7 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz, return rc; } nhdr_ptr = notes_section; - for (j = 0; j < max_sz; j += sz) { + while (real_sz < max_sz) { if (nhdr_ptr->n_namesz == 0) break; sz = sizeof(Elf64_Nhdr) + @@ -289,26 +372,122 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz, real_sz += sz; nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz); } - - /* Add this contiguous chunk of notes section to vmcore list.*/ - new = get_new_element(); - if (!new) { - kfree(notes_section); - return -ENOMEM; - } - new->paddr = phdr_ptr->p_offset; - new->size = real_sz; - list_add_tail(&new->list, vc_list); - phdr_sz += real_sz; kfree(notes_section); + phdr_ptr->p_memsz = real_sz; + } + + return 0; +} + +/** + * get_note_number_and_size_elf64 - get the number of PT_NOTE program + * headers and sum of real size of their ELF note segment headers and + * data. + * + * @ehdr_ptr: ELF header + * @nr_ptnote: buffer for the number of PT_NOTE program headers + * @sz_ptnote: buffer for size of unique PT_NOTE program header + * + * This function is used to merge multiple PT_NOTE program headers + * into a unique single one. The resulting unique entry will have + * @sz_ptnote in its phdr->p_mem. + * + * It is assumed that program headers with PT_NOTE type pointed to by + * @ehdr_ptr has already been updated by update_note_header_size_elf64 + * and each of PT_NOTE program headers has actual ELF note segment + * size in its p_memsz member. + */ +static int __init get_note_number_and_size_elf64(const Elf64_Ehdr *ehdr_ptr, + int *nr_ptnote, u64 *sz_ptnote) +{ + int i; + Elf64_Phdr *phdr_ptr; + + *nr_ptnote = *sz_ptnote = 0; + + phdr_ptr = (Elf64_Phdr *)(ehdr_ptr + 1); + for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { + if (phdr_ptr->p_type != PT_NOTE) + continue; + *nr_ptnote += 1; + *sz_ptnote += phdr_ptr->p_memsz; + } + + return 0; +} + +/** + * copy_notes_elf64 - copy ELF note segments in a given buffer + * + * @ehdr_ptr: ELF header + * @notes_buf: buffer into which ELF note segments are copied + * + * This function is used to copy ELF note segment in the 1st kernel + * into the buffer @notes_buf in the 2nd kernel. It is assumed that + * size of the buffer @notes_buf is equal to or larger than sum of the + * real ELF note segment headers and data. + * + * It is assumed that program headers with PT_NOTE type pointed to by + * @ehdr_ptr has already been updated by update_note_header_size_elf64 + * and each of PT_NOTE program headers has actual ELF note segment + * size in its p_memsz member. + */ +static int __init copy_notes_elf64(const Elf64_Ehdr *ehdr_ptr, char *notes_buf) +{ + int i, rc=0; + Elf64_Phdr *phdr_ptr; + + phdr_ptr = (Elf64_Phdr*)(ehdr_ptr + 1); + + for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { + u64 offset; + if (phdr_ptr->p_type != PT_NOTE) + continue; + offset = phdr_ptr->p_offset; + rc = read_from_oldmem(notes_buf, phdr_ptr->p_memsz, &offset, 0); + if (rc < 0) + return rc; + notes_buf += phdr_ptr->p_memsz; } + return 0; +} + +/* Merges all the PT_NOTE headers into one. */ +static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz, + char **notes_buf, size_t *notes_sz) +{ + int i, nr_ptnote=0, rc=0; + char *tmp; + Elf64_Ehdr *ehdr_ptr; + Elf64_Phdr phdr; + u64 phdr_sz = 0, note_off; + + ehdr_ptr = (Elf64_Ehdr *)elfptr; + + rc = update_note_header_size_elf64(ehdr_ptr); + if (rc < 0) + return rc; + + rc = get_note_number_and_size_elf64(ehdr_ptr, &nr_ptnote, &phdr_sz); + if (rc < 0) + return rc; + + *notes_sz = roundup(phdr_sz, PAGE_SIZE); + *notes_buf = alloc_elfnotes_buf(*notes_sz); + if (!*notes_buf) + return -ENOMEM; + + rc = copy_notes_elf64(ehdr_ptr, *notes_buf); + if (rc < 0) + return rc; + /* Prepare merged PT_NOTE program header. */ phdr.p_type = PT_NOTE; phdr.p_flags = 0; note_off = sizeof(Elf64_Ehdr) + (ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf64_Phdr); - phdr.p_offset = note_off; + phdr.p_offset = roundup(note_off, PAGE_SIZE); phdr.p_vaddr = phdr.p_paddr = 0; phdr.p_filesz = phdr.p_memsz = phdr_sz; phdr.p_align = 0; @@ -322,6 +501,8 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz, i = (nr_ptnote - 1) * sizeof(Elf64_Phdr); *elfsz = *elfsz - i; memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf64_Ehdr)-sizeof(Elf64_Phdr))); + memset(elfptr + *elfsz, 0, i); + *elfsz = roundup(*elfsz, PAGE_SIZE); /* Modify e_phnum to reflect merged headers. */ ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1; @@ -329,27 +510,27 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz, return 0; } -/* Merges all the PT_NOTE headers into one. */ -static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz, - struct list_head *vc_list) +/** + * update_note_header_size_elf32 - update p_memsz member of each PT_NOTE entry + * + * @ehdr_ptr: ELF header + * + * This function updates p_memsz member of each PT_NOTE entry in the + * program header table pointed to by @ehdr_ptr to real size of ELF + * note segment. + */ +static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr) { - int i, nr_ptnote=0, rc=0; - char *tmp; - Elf32_Ehdr *ehdr_ptr; - Elf32_Phdr phdr, *phdr_ptr; + int i, rc=0; + Elf32_Phdr *phdr_ptr; Elf32_Nhdr *nhdr_ptr; - u64 phdr_sz = 0, note_off; - ehdr_ptr = (Elf32_Ehdr *)elfptr; - phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); + phdr_ptr = (Elf32_Phdr *)(ehdr_ptr + 1); for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { - int j; void *notes_section; - struct vmcore *new; u64 offset, max_sz, sz, real_sz = 0; if (phdr_ptr->p_type != PT_NOTE) continue; - nr_ptnote++; max_sz = phdr_ptr->p_memsz; offset = phdr_ptr->p_offset; notes_section = kmalloc(max_sz, GFP_KERNEL); @@ -361,7 +542,7 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz, return rc; } nhdr_ptr = notes_section; - for (j = 0; j < max_sz; j += sz) { + while (real_sz < max_sz) { if (nhdr_ptr->n_namesz == 0) break; sz = sizeof(Elf32_Nhdr) + @@ -370,26 +551,122 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz, real_sz += sz; nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz); } - - /* Add this contiguous chunk of notes section to vmcore list.*/ - new = get_new_element(); - if (!new) { - kfree(notes_section); - return -ENOMEM; - } - new->paddr = phdr_ptr->p_offset; - new->size = real_sz; - list_add_tail(&new->list, vc_list); - phdr_sz += real_sz; kfree(notes_section); + phdr_ptr->p_memsz = real_sz; + } + + return 0; +} + +/** + * get_note_number_and_size_elf32 - get the number of PT_NOTE program + * headers and sum of real size of their ELF note segment headers and + * data. + * + * @ehdr_ptr: ELF header + * @nr_ptnote: buffer for the number of PT_NOTE program headers + * @sz_ptnote: buffer for size of unique PT_NOTE program header + * + * This function is used to merge multiple PT_NOTE program headers + * into a unique single one. The resulting unique entry will have + * @sz_ptnote in its phdr->p_mem. + * + * It is assumed that program headers with PT_NOTE type pointed to by + * @ehdr_ptr has already been updated by update_note_header_size_elf32 + * and each of PT_NOTE program headers has actual ELF note segment + * size in its p_memsz member. + */ +static int __init get_note_number_and_size_elf32(const Elf32_Ehdr *ehdr_ptr, + int *nr_ptnote, u64 *sz_ptnote) +{ + int i; + Elf32_Phdr *phdr_ptr; + + *nr_ptnote = *sz_ptnote = 0; + + phdr_ptr = (Elf32_Phdr *)(ehdr_ptr + 1); + for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { + if (phdr_ptr->p_type != PT_NOTE) + continue; + *nr_ptnote += 1; + *sz_ptnote += phdr_ptr->p_memsz; + } + + return 0; +} + +/** + * copy_notes_elf32 - copy ELF note segments in a given buffer + * + * @ehdr_ptr: ELF header + * @notes_buf: buffer into which ELF note segments are copied + * + * This function is used to copy ELF note segment in the 1st kernel + * into the buffer @notes_buf in the 2nd kernel. It is assumed that + * size of the buffer @notes_buf is equal to or larger than sum of the + * real ELF note segment headers and data. + * + * It is assumed that program headers with PT_NOTE type pointed to by + * @ehdr_ptr has already been updated by update_note_header_size_elf32 + * and each of PT_NOTE program headers has actual ELF note segment + * size in its p_memsz member. + */ +static int __init copy_notes_elf32(const Elf32_Ehdr *ehdr_ptr, char *notes_buf) +{ + int i, rc=0; + Elf32_Phdr *phdr_ptr; + + phdr_ptr = (Elf32_Phdr*)(ehdr_ptr + 1); + + for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { + u64 offset; + if (phdr_ptr->p_type != PT_NOTE) + continue; + offset = phdr_ptr->p_offset; + rc = read_from_oldmem(notes_buf, phdr_ptr->p_memsz, &offset, 0); + if (rc < 0) + return rc; + notes_buf += phdr_ptr->p_memsz; } + return 0; +} + +/* Merges all the PT_NOTE headers into one. */ +static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz, + char **notes_buf, size_t *notes_sz) +{ + int i, nr_ptnote=0, rc=0; + char *tmp; + Elf32_Ehdr *ehdr_ptr; + Elf32_Phdr phdr; + u64 phdr_sz = 0, note_off; + + ehdr_ptr = (Elf32_Ehdr *)elfptr; + + rc = update_note_header_size_elf32(ehdr_ptr); + if (rc < 0) + return rc; + + rc = get_note_number_and_size_elf32(ehdr_ptr, &nr_ptnote, &phdr_sz); + if (rc < 0) + return rc; + + *notes_sz = roundup(phdr_sz, PAGE_SIZE); + *notes_buf = alloc_elfnotes_buf(*notes_sz); + if (!*notes_buf) + return -ENOMEM; + + rc = copy_notes_elf32(ehdr_ptr, *notes_buf); + if (rc < 0) + return rc; + /* Prepare merged PT_NOTE program header. */ phdr.p_type = PT_NOTE; phdr.p_flags = 0; note_off = sizeof(Elf32_Ehdr) + (ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf32_Phdr); - phdr.p_offset = note_off; + phdr.p_offset = roundup(note_off, PAGE_SIZE); phdr.p_vaddr = phdr.p_paddr = 0; phdr.p_filesz = phdr.p_memsz = phdr_sz; phdr.p_align = 0; @@ -403,6 +680,8 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz, i = (nr_ptnote - 1) * sizeof(Elf32_Phdr); *elfsz = *elfsz - i; memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf32_Ehdr)-sizeof(Elf32_Phdr))); + memset(elfptr + *elfsz, 0, i); + *elfsz = roundup(*elfsz, PAGE_SIZE); /* Modify e_phnum to reflect merged headers. */ ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1; @@ -414,6 +693,7 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz, * the new offset fields of exported program headers. */ static int __init process_ptload_program_headers_elf64(char *elfptr, size_t elfsz, + size_t elfnotes_sz, struct list_head *vc_list) { int i; @@ -425,32 +705,38 @@ static int __init process_ptload_program_headers_elf64(char *elfptr, ehdr_ptr = (Elf64_Ehdr *)elfptr; phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */ - /* First program header is PT_NOTE header. */ - vmcore_off = sizeof(Elf64_Ehdr) + - (ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr) + - phdr_ptr->p_memsz; /* Note sections */ + /* Skip Elf header, program headers and Elf note segment. */ + vmcore_off = elfsz + elfnotes_sz; for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { + u64 paddr, start, end, size; + if (phdr_ptr->p_type != PT_LOAD) continue; + paddr = phdr_ptr->p_offset; + start = rounddown(paddr, PAGE_SIZE); + end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE); + size = end - start; + /* Add this contiguous chunk of memory to vmcore list.*/ new = get_new_element(); if (!new) return -ENOMEM; - new->paddr = phdr_ptr->p_offset; - new->size = phdr_ptr->p_memsz; + new->paddr = start; + new->size = size; list_add_tail(&new->list, vc_list); /* Update the program header offset. */ - phdr_ptr->p_offset = vmcore_off; - vmcore_off = vmcore_off + phdr_ptr->p_memsz; + phdr_ptr->p_offset = vmcore_off + (paddr - start); + vmcore_off = vmcore_off + size; } return 0; } static int __init process_ptload_program_headers_elf32(char *elfptr, size_t elfsz, + size_t elfnotes_sz, struct list_head *vc_list) { int i; @@ -462,43 +748,44 @@ static int __init process_ptload_program_headers_elf32(char *elfptr, ehdr_ptr = (Elf32_Ehdr *)elfptr; phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); /* PT_NOTE hdr */ - /* First program header is PT_NOTE header. */ - vmcore_off = sizeof(Elf32_Ehdr) + - (ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr) + - phdr_ptr->p_memsz; /* Note sections */ + /* Skip Elf header, program headers and Elf note segment. */ + vmcore_off = elfsz + elfnotes_sz; for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { + u64 paddr, start, end, size; + if (phdr_ptr->p_type != PT_LOAD) continue; + paddr = phdr_ptr->p_offset; + start = rounddown(paddr, PAGE_SIZE); + end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE); + size = end - start; + /* Add this contiguous chunk of memory to vmcore list.*/ new = get_new_element(); if (!new) return -ENOMEM; - new->paddr = phdr_ptr->p_offset; - new->size = phdr_ptr->p_memsz; + new->paddr = start; + new->size = size; list_add_tail(&new->list, vc_list); /* Update the program header offset */ - phdr_ptr->p_offset = vmcore_off; - vmcore_off = vmcore_off + phdr_ptr->p_memsz; + phdr_ptr->p_offset = vmcore_off + (paddr - start); + vmcore_off = vmcore_off + size; } return 0; } /* Sets offset fields of vmcore elements. */ -static void __init set_vmcore_list_offsets_elf64(char *elfptr, - struct list_head *vc_list) +static void __init set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz, + struct list_head *vc_list) { loff_t vmcore_off; - Elf64_Ehdr *ehdr_ptr; struct vmcore *m; - ehdr_ptr = (Elf64_Ehdr *)elfptr; - - /* Skip Elf header and program headers. */ - vmcore_off = sizeof(Elf64_Ehdr) + - (ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr); + /* Skip Elf header, program headers and Elf note segment. */ + vmcore_off = elfsz + elfnotes_sz; list_for_each_entry(m, vc_list, list) { m->offset = vmcore_off; @@ -506,24 +793,12 @@ static void __init set_vmcore_list_offsets_elf64(char *elfptr, } } -/* Sets offset fields of vmcore elements. */ -static void __init set_vmcore_list_offsets_elf32(char *elfptr, - struct list_head *vc_list) +static void free_elfcorebuf(void) { - loff_t vmcore_off; - Elf32_Ehdr *ehdr_ptr; - struct vmcore *m; - - ehdr_ptr = (Elf32_Ehdr *)elfptr; - - /* Skip Elf header and program headers. */ - vmcore_off = sizeof(Elf32_Ehdr) + - (ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr); - - list_for_each_entry(m, vc_list, list) { - m->offset = vmcore_off; - vmcore_off += m->size; - } + free_pages((unsigned long)elfcorebuf, get_order(elfcorebuf_sz_orig)); + elfcorebuf = NULL; + vfree(elfnotes_buf); + elfnotes_buf = NULL; } static int __init parse_crash_elf64_headers(void) @@ -554,31 +829,32 @@ static int __init parse_crash_elf64_headers(void) } /* Read in all elf headers. */ - elfcorebuf_sz = sizeof(Elf64_Ehdr) + ehdr.e_phnum * sizeof(Elf64_Phdr); - elfcorebuf = kmalloc(elfcorebuf_sz, GFP_KERNEL); + elfcorebuf_sz_orig = sizeof(Elf64_Ehdr) + + ehdr.e_phnum * sizeof(Elf64_Phdr); + elfcorebuf_sz = elfcorebuf_sz_orig; + elfcorebuf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(elfcorebuf_sz_orig)); if (!elfcorebuf) return -ENOMEM; addr = elfcorehdr_addr; - rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz, &addr, 0); - if (rc < 0) { - kfree(elfcorebuf); - return rc; - } + rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz_orig, &addr, 0); + if (rc < 0) + goto fail; /* Merge all PT_NOTE headers into one. */ - rc = merge_note_headers_elf64(elfcorebuf, &elfcorebuf_sz, &vmcore_list); - if (rc) { - kfree(elfcorebuf); - return rc; - } + rc = merge_note_headers_elf64(elfcorebuf, &elfcorebuf_sz, + &elfnotes_buf, &elfnotes_sz); + if (rc) + goto fail; rc = process_ptload_program_headers_elf64(elfcorebuf, elfcorebuf_sz, - &vmcore_list); - if (rc) { - kfree(elfcorebuf); - return rc; - } - set_vmcore_list_offsets_elf64(elfcorebuf, &vmcore_list); + elfnotes_sz, &vmcore_list); + if (rc) + goto fail; + set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list); return 0; +fail: + free_elfcorebuf(); + return rc; } static int __init parse_crash_elf32_headers(void) @@ -609,31 +885,31 @@ static int __init parse_crash_elf32_headers(void) } /* Read in all elf headers. */ - elfcorebuf_sz = sizeof(Elf32_Ehdr) + ehdr.e_phnum * sizeof(Elf32_Phdr); - elfcorebuf = kmalloc(elfcorebuf_sz, GFP_KERNEL); + elfcorebuf_sz_orig = sizeof(Elf32_Ehdr) + ehdr.e_phnum * sizeof(Elf32_Phdr); + elfcorebuf_sz = elfcorebuf_sz_orig; + elfcorebuf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(elfcorebuf_sz_orig)); if (!elfcorebuf) return -ENOMEM; addr = elfcorehdr_addr; - rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz, &addr, 0); - if (rc < 0) { - kfree(elfcorebuf); - return rc; - } + rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz_orig, &addr, 0); + if (rc < 0) + goto fail; /* Merge all PT_NOTE headers into one. */ - rc = merge_note_headers_elf32(elfcorebuf, &elfcorebuf_sz, &vmcore_list); - if (rc) { - kfree(elfcorebuf); - return rc; - } + rc = merge_note_headers_elf32(elfcorebuf, &elfcorebuf_sz, + &elfnotes_buf, &elfnotes_sz); + if (rc) + goto fail; rc = process_ptload_program_headers_elf32(elfcorebuf, elfcorebuf_sz, - &vmcore_list); - if (rc) { - kfree(elfcorebuf); - return rc; - } - set_vmcore_list_offsets_elf32(elfcorebuf, &vmcore_list); + elfnotes_sz, &vmcore_list); + if (rc) + goto fail; + set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list); return 0; +fail: + free_elfcorebuf(); + return rc; } static int __init parse_crash_elf_headers(void) @@ -655,20 +931,19 @@ static int __init parse_crash_elf_headers(void) rc = parse_crash_elf64_headers(); if (rc) return rc; - - /* Determine vmcore size. */ - vmcore_size = get_vmcore_size_elf64(elfcorebuf); } else if (e_ident[EI_CLASS] == ELFCLASS32) { rc = parse_crash_elf32_headers(); if (rc) return rc; - - /* Determine vmcore size. */ - vmcore_size = get_vmcore_size_elf32(elfcorebuf); } else { pr_warn("Warning: Core image elf header is not sane\n"); return -EINVAL; } + + /* Determine vmcore size. */ + vmcore_size = get_vmcore_size(elfcorebuf_sz, elfnotes_sz, + &vmcore_list); + return 0; } @@ -711,7 +986,6 @@ void vmcore_cleanup(void) list_del(&m->list); kfree(m); } - kfree(elfcorebuf); - elfcorebuf = NULL; + free_elfcorebuf(); } EXPORT_SYMBOL_GPL(vmcore_cleanup); |
