diff options
Diffstat (limited to 'fs')
41 files changed, 517 insertions, 347 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 9fe0b349f4cd..5f4c45d4aa10 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -109,7 +109,7 @@ source "fs/proc/Kconfig" source "fs/sysfs/Kconfig" config TMPFS - bool "Virtual memory file system support (former shm fs)" + bool "Tmpfs virtual memory file system support (former shm fs)" depends on SHMEM help Tmpfs is a file system which keeps all files in virtual memory. @@ -1387,13 +1387,13 @@ static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat) ret = compat_rw_copy_check_uvector(type, (struct compat_iovec __user *)kiocb->ki_buf, kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec, - &kiocb->ki_iovec); + &kiocb->ki_iovec, 1); else #endif ret = rw_copy_check_uvector(type, (struct iovec __user *)kiocb->ki_buf, kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec, - &kiocb->ki_iovec); + &kiocb->ki_iovec, 1); if (ret < 0) goto out; diff --git a/fs/buffer.c b/fs/buffer.c index 936d6035f6e2..70a19745cb61 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -213,13 +213,16 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) * elsewhere, don't buffer_error if we had some unmapped buffers */ if (all_mapped) { + char b[BDEVNAME_SIZE]; + printk("__find_get_block_slow() failed. " "block=%llu, b_blocknr=%llu\n", (unsigned long long)block, (unsigned long long)bh->b_blocknr); printk("b_state=0x%08lx, b_size=%zu\n", bh->b_state, bh->b_size); - printk("device blocksize: %d\n", 1 << bd_inode->i_blkbits); + printk("device %s blocksize: %d\n", bdevname(bdev, b), + 1 << bd_inode->i_blkbits); } out_unlock: spin_unlock(&bd_mapping->private_lock); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 5a3953db8118..4144caf2f9d3 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -228,102 +228,155 @@ static int ceph_readpage(struct file *filp, struct page *page) } /* - * Build a vector of contiguous pages from the provided page list. + * Finish an async read(ahead) op. */ -static struct page **page_vector_from_list(struct list_head *page_list, - unsigned *nr_pages) +static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg) { - struct page **pages; - struct page *page; - int next_index, contig_pages = 0; + struct inode *inode = req->r_inode; + struct ceph_osd_reply_head *replyhead; + int rc, bytes; + int i; - /* build page vector */ - pages = kmalloc(sizeof(*pages) * *nr_pages, GFP_NOFS); - if (!pages) - return ERR_PTR(-ENOMEM); + /* parse reply */ + replyhead = msg->front.iov_base; + WARN_ON(le32_to_cpu(replyhead->num_ops) == 0); + rc = le32_to_cpu(replyhead->result); + bytes = le32_to_cpu(msg->hdr.data_len); - BUG_ON(list_empty(page_list)); - next_index = list_entry(page_list->prev, struct page, lru)->index; - list_for_each_entry_reverse(page, page_list, lru) { - if (page->index == next_index) { - dout("readpages page %d %p\n", contig_pages, page); - pages[contig_pages] = page; - contig_pages++; - next_index++; - } else { - break; + dout("finish_read %p req %p rc %d bytes %d\n", inode, req, rc, bytes); + + /* unlock all pages, zeroing any data we didn't read */ + for (i = 0; i < req->r_num_pages; i++, bytes -= PAGE_CACHE_SIZE) { + struct page *page = req->r_pages[i]; + + if (bytes < (int)PAGE_CACHE_SIZE) { + /* zero (remainder of) page */ + int s = bytes < 0 ? 0 : bytes; + zero_user_segment(page, s, PAGE_CACHE_SIZE); } + dout("finish_read %p uptodate %p idx %lu\n", inode, page, + page->index); + flush_dcache_page(page); + SetPageUptodate(page); + unlock_page(page); + page_cache_release(page); } - *nr_pages = contig_pages; - return pages; + kfree(req->r_pages); } /* - * Read multiple pages. Leave pages we don't read + unlock in page_list; - * the caller (VM) cleans them up. + * start an async read(ahead) operation. return nr_pages we submitted + * a read for on success, or negative error code. */ -static int ceph_readpages(struct file *file, struct address_space *mapping, - struct list_head *page_list, unsigned nr_pages) +static int start_read(struct inode *inode, struct list_head *page_list, int max) { - struct inode *inode = file->f_dentry->d_inode; - struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->client->osdc; - int rc = 0; - struct page **pages; - loff_t offset; + struct ceph_inode_info *ci = ceph_inode(inode); + struct page *page = list_entry(page_list->prev, struct page, lru); + struct ceph_osd_request *req; + u64 off; u64 len; + int i; + struct page **pages; + pgoff_t next_index; + int nr_pages = 0; + int ret; - dout("readpages %p file %p nr_pages %d\n", - inode, file, nr_pages); - - pages = page_vector_from_list(page_list, &nr_pages); - if (IS_ERR(pages)) - return PTR_ERR(pages); + off = page->index << PAGE_CACHE_SHIFT; - /* guess read extent */ - offset = pages[0]->index << PAGE_CACHE_SHIFT; + /* count pages */ + next_index = page->index; + list_for_each_entry_reverse(page, page_list, lru) { + if (page->index != next_index) + break; + nr_pages++; + next_index++; + if (max && nr_pages == max) + break; + } len = nr_pages << PAGE_CACHE_SHIFT; - rc = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout, - offset, &len, - ci->i_truncate_seq, ci->i_truncate_size, - pages, nr_pages, 0); - if (rc == -ENOENT) - rc = 0; - if (rc < 0) - goto out; - - for (; !list_empty(page_list) && len > 0; - rc -= PAGE_CACHE_SIZE, len -= PAGE_CACHE_SIZE) { - struct page *page = - list_entry(page_list->prev, struct page, lru); + dout("start_read %p nr_pages %d is %lld~%lld\n", inode, nr_pages, + off, len); + + req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode), + off, &len, + CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ, + NULL, 0, + ci->i_truncate_seq, ci->i_truncate_size, + NULL, false, 1, 0); + if (!req) + return -ENOMEM; + /* build page vector */ + nr_pages = len >> PAGE_CACHE_SHIFT; + pages = kmalloc(sizeof(*pages) * nr_pages, GFP_NOFS); + ret = -ENOMEM; + if (!pages) + goto out; + for (i = 0; i < nr_pages; ++i) { + page = list_entry(page_list->prev, struct page, lru); + BUG_ON(PageLocked(page)); list_del(&page->lru); - - if (rc < (int)PAGE_CACHE_SIZE) { - /* zero (remainder of) page */ - int s = rc < 0 ? 0 : rc; - zero_user_segment(page, s, PAGE_CACHE_SIZE); - } - - if (add_to_page_cache_lru(page, mapping, page->index, + + dout("start_read %p adding %p idx %lu\n", inode, page, + page->index); + if (add_to_page_cache_lru(page, &inode->i_data, page->index, GFP_NOFS)) { page_cache_release(page); - dout("readpages %p add_to_page_cache failed %p\n", + dout("start_read %p add_to_page_cache failed %p\n", inode, page); - continue; + nr_pages = i; + goto out_pages; } - dout("readpages %p adding %p idx %lu\n", inode, page, - page->index); - flush_dcache_page(page); - SetPageUptodate(page); - unlock_page(page); - page_cache_release(page); + pages[i] = page; } - rc = 0; + req->r_pages = pages; + req->r_num_pages = nr_pages; + req->r_callback = finish_read; + req->r_inode = inode; + + dout("start_read %p starting %p %lld~%lld\n", inode, req, off, len); + ret = ceph_osdc_start_request(osdc, req, false); + if (ret < 0) + goto out_pages; + ceph_osdc_put_request(req); + return nr_pages; +out_pages: + ceph_release_page_vector(pages, nr_pages); +out: + ceph_osdc_put_request(req); + return ret; +} + + +/* + * Read multiple pages. Leave pages we don't read + unlock in page_list; + * the caller (VM) cleans them up. + */ +static int ceph_readpages(struct file *file, struct address_space *mapping, + struct list_head *page_list, unsigned nr_pages) +{ + struct inode *inode = file->f_dentry->d_inode; + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); + int rc = 0; + int max = 0; + + if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE) + max = (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1) + >> PAGE_SHIFT; + + dout("readpages %p file %p nr_pages %d max %d\n", inode, file, nr_pages, + max); + while (!list_empty(page_list)) { + rc = start_read(inode, page_list, max); + if (rc < 0) + goto out; + BUG_ON(rc == 0); + } out: - kfree(pages); + dout("readpages %p file %p ret %d\n", inode, file, rc); return rc; } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 8d74ad7ba556..b8731bf3ef1f 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -945,7 +945,7 @@ static int send_cap_msg(struct ceph_mds_session *session, seq, issue_seq, mseq, follows, size, max_size, xattr_version, xattrs_buf ? (int)xattrs_buf->vec.iov_len : 0); - msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, sizeof(*fc), GFP_NOFS); + msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, sizeof(*fc), GFP_NOFS, false); if (!msg) return -ENOMEM; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 095799ba9dd1..5dde7d51dc11 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -9,7 +9,6 @@ #include <linux/namei.h> #include <linux/writeback.h> #include <linux/vmalloc.h> -#include <linux/pagevec.h> #include "super.h" #include "mds_client.h" @@ -1364,49 +1363,6 @@ void ceph_queue_invalidate(struct inode *inode) } /* - * invalidate any pages that are not dirty or under writeback. this - * includes pages that are clean and mapped. - */ -static void ceph_invalidate_nondirty_pages(struct address_space *mapping) -{ - struct pagevec pvec; - pgoff_t next = 0; - int i; - - pagevec_init(&pvec, 0); - while (pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; - pgoff_t index; - int skip_page = - (PageDirty(page) || PageWriteback(page)); - - if (!skip_page) - skip_page = !trylock_page(page); - - /* - * We really shouldn't be looking at the ->index of an - * unlocked page. But we're not allowed to lock these - * pages. So we rely upon nobody altering the ->index - * of this (pinned-by-us) page. - */ - index = page->index; - if (index > next) - next = index; - next++; - - if (skip_page) - continue; - - generic_error_remove_page(mapping, page); - unlock_page(page); - } - pagevec_release(&pvec); - cond_resched(); - } -} - -/* * Invalidate inode pages in a worker thread. (This can't be done * in the message handler context.) */ @@ -1429,7 +1385,7 @@ static void ceph_invalidate_work(struct work_struct *work) orig_gen = ci->i_rdcache_gen; spin_unlock(&inode->i_lock); - ceph_invalidate_nondirty_pages(inode->i_mapping); + truncate_inode_pages(&inode->i_data, 0); spin_lock(&inode->i_lock); if (orig_gen == ci->i_rdcache_gen && diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index 3b256b50f7d8..5a14c29cbba6 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -42,17 +42,39 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg) struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_mds_request *req; struct ceph_ioctl_layout l; + struct ceph_inode_info *ci = ceph_inode(file->f_dentry->d_inode); + struct ceph_ioctl_layout nl; int err, i; - /* copy and validate */ if (copy_from_user(&l, arg, sizeof(l))) return -EFAULT; - if ((l.object_size & ~PAGE_MASK) || - (l.stripe_unit & ~PAGE_MASK) || - !l.stripe_unit || - (l.object_size && - (unsigned)l.object_size % (unsigned)l.stripe_unit)) + /* validate changed params against current layout */ + err = ceph_do_getattr(file->f_dentry->d_inode, CEPH_STAT_CAP_LAYOUT); + if (!err) { + nl.stripe_unit = ceph_file_layout_su(ci->i_layout); + nl.stripe_count = ceph_file_layout_stripe_count(ci->i_layout); + nl.object_size = ceph_file_layout_object_size(ci->i_layout); + nl.data_pool = le32_to_cpu(ci->i_layout.fl_pg_pool); + nl.preferred_osd = + (s32)le32_to_cpu(ci->i_layout.fl_pg_preferred); + } else + return err; + + if (l.stripe_count) + nl.stripe_count = l.stripe_count; + if (l.stripe_unit) + nl.stripe_unit = l.stripe_unit; + if (l.object_size) + nl.object_size = l.object_size; + if (l.data_pool) + nl.data_pool = l.data_pool; + if (l.preferred_osd) + nl.preferred_osd = l.preferred_osd; + + if ((nl.object_size & ~PAGE_MASK) || + (nl.stripe_unit & ~PAGE_MASK) || + ((unsigned)nl.object_size % (unsigned)nl.stripe_unit)) return -EINVAL; /* make sure it's a valid data pool */ diff --git a/fs/ceph/ioctl.h b/fs/ceph/ioctl.h index 0c5167e43180..be4a60487333 100644 --- a/fs/ceph/ioctl.h +++ b/fs/ceph/ioctl.h @@ -6,7 +6,31 @@ #define CEPH_IOCTL_MAGIC 0x97 -/* just use u64 to align sanely on all archs */ +/* + * CEPH_IOC_GET_LAYOUT - get file layout or dir layout policy + * CEPH_IOC_SET_LAYOUT - set file layout + * CEPH_IOC_SET_LAYOUT_POLICY - set dir layout policy + * + * The file layout specifies how file data is striped over objects in + * the distributed object store, which object pool they belong to (if + * it differs from the default), and an optional 'preferred osd' to + * store them on. + * + * Files get a new layout based on the policy set on the containing + * directory or one of its ancestors. The GET_LAYOUT ioctl will let + * you examine the layout for a file or the policy on a directory. + * + * SET_LAYOUT will let you set a layout on a newly created file. This + * only works immediately after the file is created and before any + * data is written to it. + * + * SET_LAYOUT_POLICY will let you set a layout policy (default layout) + * on a directory that will apply to any new files created in that + * directory (or any child directory that doesn't specify a layout of + * its own). + */ + +/* use u64 to align sanely on all archs */ struct ceph_ioctl_layout { __u64 stripe_unit, stripe_count, object_size; __u64 data_pool; @@ -21,6 +45,8 @@ struct ceph_ioctl_layout { struct ceph_ioctl_layout) /* + * CEPH_IOC_GET_DATALOC - get location of file data in the cluster + * * Extract identity, address of the OSD and object storing a given * file offset. */ @@ -39,7 +65,34 @@ struct ceph_ioctl_dataloc { #define CEPH_IOC_GET_DATALOC _IOWR(CEPH_IOCTL_MAGIC, 3, \ struct ceph_ioctl_dataloc) +/* + * CEPH_IOC_LAZYIO - relax consistency + * + * Normally Ceph switches to synchronous IO when multiple clients have + * the file open (and or more for write). Reads and writes bypass the + * page cache and go directly to the OSD. Setting this flag on a file + * descriptor will allow buffered IO for this file in cases where the + * application knows it won't interfere with other nodes (or doesn't + * care). + */ #define CEPH_IOC_LAZYIO _IO(CEPH_IOCTL_MAGIC, 4) + +/* + * CEPH_IOC_SYNCIO - force synchronous IO + * + * This ioctl sets a file flag that forces the synchronous IO that + * bypasses the page cache, even if it is not necessary. This is + * essentially the opposite behavior of IOC_LAZYIO. This forces the + * same read/write path as a file opened by multiple clients when one + * or more of those clients is opened for write. + * + * Note that this type of sync IO takes a different path than a file + * opened with O_SYNC/D_SYNC (writes hit the page cache and are + * immediately flushed on page boundaries). It is very similar to + * O_DIRECT (writes bypass the page cache) excep that O_DIRECT writes + * are not copied (user page must remain stable) and O_DIRECT writes + * have alignment restrictions (on the buffer and file offset). + */ #define CEPH_IOC_SYNCIO _IO(CEPH_IOCTL_MAGIC, 5) #endif diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 86c59e16ba74..1d72f15fe9f4 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -764,7 +764,8 @@ static struct ceph_msg *create_session_msg(u32 op, u64 seq) struct ceph_msg *msg; struct ceph_mds_session_head *h; - msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h), GFP_NOFS); + msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h), GFP_NOFS, + false); if (!msg) { pr_err("create_session_msg ENOMEM creating msg\n"); return NULL; @@ -1240,7 +1241,7 @@ int ceph_add_cap_releases(struct ceph_mds_client *mdsc, while (session->s_num_cap_releases < session->s_nr_caps + extra) { spin_unlock(&session->s_cap_lock); msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPRELEASE, PAGE_CACHE_SIZE, - GFP_NOFS); + GFP_NOFS, false); if (!msg) goto out_unlocked; dout("add_cap_releases %p msg %p now %d\n", session, msg, @@ -1652,7 +1653,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, if (req->r_old_dentry_drop) len += req->r_old_dentry->d_name.len; - msg = ceph_msg_new(CEPH_MSG_CLIENT_REQUEST, len, GFP_NOFS); + msg = ceph_msg_new(CEPH_MSG_CLIENT_REQUEST, len, GFP_NOFS, false); if (!msg) { msg = ERR_PTR(-ENOMEM); goto out_free2; @@ -2518,7 +2519,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, goto fail_nopagelist; ceph_pagelist_init(pagelist); - reply = ceph_msg_new(CEPH_MSG_CLIENT_RECONNECT, 0, GFP_NOFS); + reply = ceph_msg_new(CEPH_MSG_CLIENT_RECONNECT, 0, GFP_NOFS, false); if (!reply) goto fail_nomsg; @@ -2831,7 +2832,7 @@ void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session, dnamelen = dentry->d_name.len; len += dnamelen; - msg = ceph_msg_new(CEPH_MSG_CLIENT_LEASE, len, GFP_NOFS); + msg = ceph_msg_new(CEPH_MSG_CLIENT_LEASE, len, GFP_NOFS, false); if (!msg) return; lease = msg->front.iov_base; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 88bacaf385d9..788f5ad8e66d 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -114,6 +114,7 @@ static int ceph_sync_fs(struct super_block *sb, int wait) enum { Opt_wsize, Opt_rsize, + Opt_rasize, Opt_caps_wanted_delay_min, Opt_caps_wanted_delay_max, Opt_cap_release_safety, @@ -136,6 +137,7 @@ enum { static match_table_t fsopt_tokens = { {Opt_wsize, "wsize=%d"}, {Opt_rsize, "rsize=%d"}, + {Opt_rasize, "rasize=%d"}, {Opt_caps_wanted_delay_min, "caps_wanted_delay_min=%d"}, {Opt_caps_wanted_delay_max, "caps_wanted_delay_max=%d"}, {Opt_cap_release_safety, "cap_release_safety=%d"}, @@ -196,6 +198,9 @@ static int parse_fsopt_token(char *c, void *private) case Opt_rsize: fsopt->rsize = intval; break; + case Opt_rasize: + fsopt->rasize = intval; + break; case Opt_caps_wanted_delay_min: fsopt->caps_wanted_delay_min = intval; break; @@ -289,28 +294,29 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt, dout("parse_mount_options %p, dev_name '%s'\n", fsopt, dev_name); - fsopt->sb_flags = flags; - fsopt->flags = CEPH_MOUNT_OPT_DEFAULT; + fsopt->sb_flags = flags; + fsopt->flags = CEPH_MOUNT_OPT_DEFAULT; - fsopt->rsize = CEPH_RSIZE_DEFAULT; - fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL); + fsopt->rsize = CEPH_RSIZE_DEFAULT; + fsopt->rasize = CEPH_RASIZE_DEFAULT; + fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL); fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT; fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT; - fsopt->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT; - fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT; - fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT; - fsopt->congestion_kb = default_congestion_kb(); - - /* ip1[:port1][,ip2[:port2]...]:/subdir/in/fs */ - err = -EINVAL; - if (!dev_name) - goto out; - *path = strstr(dev_name, ":/"); - if (*path == NULL) { - pr_err("device name is missing path (no :/ in %s)\n", - dev_name); - goto out; - } + fsopt->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT; + fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT; + fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT; + fsopt->congestion_kb = default_congestion_kb(); + + /* ip1[:port1][,ip2[:port2]...]:/subdir/in/fs */ + err = -EINVAL; + if (!dev_name) + goto out; + *path = strstr(dev_name, ":/"); + if (*path == NULL) { + pr_err("device name is missing path (no :/ in %s)\n", + dev_name); + goto out; + } dev_name_end = *path; dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name); @@ -376,6 +382,8 @@ static int ceph_show_options(struct seq_file *m, struct vfsmount *mnt) seq_printf(m, ",wsize=%d", fsopt->wsize); if (fsopt->rsize != CEPH_RSIZE_DEFAULT) seq_printf(m, ",rsize=%d", fsopt->rsize); + if (fsopt->rasize != CEPH_RASIZE_DEFAULT) + seq_printf(m, ",rasize=%d", fsopt->rsize); if (fsopt->congestion_kb != default_congestion_kb()) seq_printf(m, ",write_congestion_kb=%d", fsopt->congestion_kb); if (fsopt->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT) @@ -422,20 +430,23 @@ struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, struct ceph_options *opt) { struct ceph_fs_client *fsc; + const unsigned supported_features = + CEPH_FEATURE_FLOCK | + CEPH_FEATURE_DIRLAYOUTHASH; + const unsigned required_features = 0; int err = -ENOMEM; fsc = kzalloc(sizeof(*fsc), GFP_KERNEL); if (!fsc) return ERR_PTR(-ENOMEM); - fsc->client = ceph_create_client(opt, fsc); + fsc->client = ceph_create_client(opt, fsc, supported_features, + required_features); if (IS_ERR(fsc->client)) { err = PTR_ERR(fsc->client); goto fail; } fsc->client->extra_mon_dispatch = extra_mon_dispatch; - fsc->client->supported_features |= CEPH_FEATURE_FLOCK | - CEPH_FEATURE_DIRLAYOUTHASH; fsc->client->monc.want_mdsmap = 1; fsc->mount_options = fsopt; @@ -774,10 +785,10 @@ static int ceph_register_bdi(struct super_block *sb, { int err; - /* set ra_pages based on rsize mount option? */ - if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE) + /* set ra_pages based on rasize mount option? */ + if (fsc->mount_options->rasize >= PAGE_CACHE_SIZE) fsc->backing_dev_info.ra_pages = - (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1) + (fsc->mount_options->rasize + PAGE_CACHE_SIZE - 1) >> PAGE_SHIFT; else fsc->backing_dev_info.ra_pages = diff --git a/fs/ceph/super.h b/fs/ceph/super.h index a23eed526f05..b01442aaf278 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -36,7 +36,8 @@ #define ceph_test_mount_opt(fsc, opt) \ (!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt)) -#define CEPH_RSIZE_DEFAULT (512*1024) /* readahead */ +#define CEPH_RSIZE_DEFAULT 0 /* max read size */ +#define CEPH_RASIZE_DEFAULT (8192*1024) /* readahead */ #define CEPH_MAX_READDIR_DEFAULT 1024 #define CEPH_MAX_READDIR_BYTES_DEFAULT (512*1024) #define CEPH_SNAPDIRNAME_DEFAULT ".snap" @@ -45,8 +46,9 @@ struct ceph_mount_options { int flags; int sb_flags; - int wsize; - int rsize; /* max readahead */ + int wsize; /* max write size */ + int rsize; /* max read size */ + int rasize; /* max readahead */ int congestion_kb; /* max writeback in flight */ int caps_wanted_delay_min, caps_wanted_delay_max; int cap_release_safety; @@ -344,9 +346,10 @@ static inline struct ceph_vino ceph_vino(struct inode *inode) * x86_64+ino32 64 32 * x86_64 64 64 */ -static inline u32 ceph_ino_to_ino32(ino_t ino) +static inline u32 ceph_ino_to_ino32(__u64 vino) { - ino ^= ino >> (sizeof(ino) * 8 - 32); + u32 ino = vino & 0xffffffff; + ino ^= vino >> 32; if (!ino) ino = 1; return ino; @@ -357,11 +360,11 @@ static inline u32 ceph_ino_to_ino32(ino_t ino) */ static inline ino_t ceph_vino_to_ino(struct ceph_vino vino) { - ino_t ino = (ino_t)vino.ino; /* ^ (vino.snap << 20); */ #if BITS_PER_LONG == 32 - ino = ceph_ino_to_ino32(ino); + return ceph_ino_to_ino32(vino.ino); +#else + return (ino_t)vino.ino; #endif - return ino; } /* diff --git a/fs/compat.c b/fs/compat.c index 302e761bd0aa..c98787536bb8 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -546,7 +546,7 @@ out: ssize_t compat_rw_copy_check_uvector(int type, const struct compat_iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer) + struct iovec **ret_pointer, int check_access) { compat_ssize_t tot_len; struct iovec *iov = *ret_pointer = fast_pointer; @@ -593,7 +593,8 @@ ssize_t compat_rw_copy_check_uvector(int type, } if (len < 0) /* size_t not fitting in compat_ssize_t .. */ goto out; - if (!access_ok(vrfy_dir(type), compat_ptr(buf), len)) { + if (check_access && + !access_ok(vrfy_dir(type), compat_ptr(buf), len)) { ret = -EFAULT; goto out; } @@ -1107,7 +1108,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, goto out; tot_len = compat_rw_copy_check_uvector(type, uvector, nr_segs, - UIO_FASTIOV, iovstack, &iov); + UIO_FASTIOV, iovstack, &iov, 1); if (tot_len == 0) { ret = 0; goto out; diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index b36c5572b3f3..54481a3b2c79 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -514,7 +514,7 @@ ecryptfs_set_dentry_lower_mnt(struct dentry *dentry, struct vfsmount *lower_mnt) #define ecryptfs_printk(type, fmt, arg...) \ __ecryptfs_printk(type "%s: " fmt, __func__, ## arg); -__attribute__ ((format(printf, 1, 2))) +__printf(1, 2) void __ecryptfs_printk(const char *fmt, ...); extern const struct file_operations ecryptfs_main_fops; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 9026fc91fe3b..828e750af23a 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -70,6 +70,15 @@ * simultaneous inserts (A into B and B into A) from racing and * constructing a cycle without either insert observing that it is * going to. + * It is necessary to acquire multiple "ep->mtx"es at once in the + * case when one epoll fd is added to another. In this case, we + * always acquire the locks in the order of nesting (i.e. after + * epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired + * before e2->mtx). Since we disallow cycles of epoll file + * descriptors, this ensures that the mutexes are well-ordered. In + * order to communicate this nesting to lockdep, when walking a tree + * of epoll file descriptors, we use the current recursion depth as + * the lockdep subkey. * It is possible to drop the "ep->mtx" and to use the global * mutex "epmutex" (together with "ep->lock") to have it working, * but having "ep->mtx" will make the interface more scalable. @@ -464,13 +473,15 @@ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi) * @ep: Pointer to the epoll private data structure. * @sproc: Pointer to the scan callback. * @priv: Private opaque data passed to the @sproc callback. + * @depth: The current depth of recursive f_op->poll calls. * * Returns: The same integer error code returned by the @sproc callback. */ static int ep_scan_ready_list(struct eventpoll *ep, int (*sproc)(struct eventpoll *, struct list_head *, void *), - void *priv) + void *priv, + int depth) { int error, pwake = 0; unsigned long flags; @@ -481,7 +492,7 @@ static int ep_scan_ready_list(struct eventpoll *ep, * We need to lock this because we could be hit by * eventpoll_release_file() and epoll_ctl(). */ - mutex_lock(&ep->mtx); + mutex_lock_nested(&ep->mtx, depth); /* * Steal the ready list, and re-init the original one to the @@ -670,7 +681,7 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, static int ep_poll_readyevents_proc(void *priv, void *cookie, int call_nests) { - return ep_scan_ready_list(priv, ep_read_events_proc, NULL); + return ep_scan_ready_list(priv, ep_read_events_proc, NULL, call_nests + 1); } static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait) @@ -737,7 +748,7 @@ void eventpoll_release_file(struct file *file) ep = epi->ep; list_del_init(&epi->fllink); - mutex_lock(&ep->mtx); + mutex_lock_nested(&ep->mtx, 0); ep_remove(ep, epi); mutex_unlock(&ep->mtx); } @@ -1134,7 +1145,7 @@ static int ep_send_events(struct eventpoll *ep, esed.maxevents = maxevents; esed.events = events; - return ep_scan_ready_list(ep, ep_send_events_proc, &esed); + return ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0); } static inline struct timespec ep_set_mstimeout(long ms) @@ -1267,7 +1278,7 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) struct rb_node *rbp; struct epitem *epi; - mutex_lock(&ep->mtx); + mutex_lock_nested(&ep->mtx, call_nests + 1); for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (unlikely(is_file_epoll(epi->ffd.file))) { @@ -1409,7 +1420,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, } - mutex_lock(&ep->mtx); + mutex_lock_nested(&ep->mtx, 0); /* * Try to lookup the file inside our RB tree, Since we grabbed "mtx" diff --git a/fs/exec.c b/fs/exec.c index 25dcbe5fc356..36254645b7cc 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -841,10 +841,6 @@ static int exec_mmap(struct mm_struct *mm) tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); - if (old_mm && tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) { - atomic_dec(&old_mm->oom_disable_count); - atomic_inc(&tsk->mm->oom_disable_count); - } task_unlock(tsk); arch_pick_mmap_layout(mm); if (old_mm) { diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index af9fc89b1b2d..9a4e5e206d08 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -135,10 +135,10 @@ extern long ext2_compat_ioctl(struct file *, unsigned int, unsigned long); struct dentry *ext2_get_parent(struct dentry *child); /* super.c */ -extern void ext2_error (struct super_block *, const char *, const char *, ...) - __attribute__ ((format (printf, 3, 4))); -extern void ext2_msg(struct super_block *, const char *, const char *, ...) - __attribute__ ((format (printf, 3, 4))); +extern __printf(3, 4) +void ext2_error(struct super_block *, const char *, const char *, ...); +extern __printf(3, 4) +void ext2_msg(struct super_block *, const char *, const char *, ...); extern void ext2_update_dynamic_rev (struct super_block *sb); extern void ext2_write_super (struct super_block *); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b7d7bd0f066e..cec3145e532c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1878,40 +1878,40 @@ extern int ext4_group_extend(struct super_block *sb, extern void *ext4_kvmalloc(size_t size, gfp_t flags); extern void *ext4_kvzalloc(size_t size, gfp_t flags); extern void ext4_kvfree(void *ptr); -extern void __ext4_error(struct super_block *, const char *, unsigned int, - const char *, ...) - __attribute__ ((format (printf, 4, 5))); +extern __printf(4, 5) +void __ext4_error(struct super_block *, const char *, unsigned int, + const char *, ...); #define ext4_error(sb, message...) __ext4_error(sb, __func__, \ __LINE__, ## message) -extern void ext4_error_inode(struct inode *, const char *, unsigned int, - ext4_fsblk_t, const char *, ...) - __attribute__ ((format (printf, 5, 6))); -extern void ext4_error_file(struct file *, const char *, unsigned int, - ext4_fsblk_t, const char *, ...) - __attribute__ ((format (printf, 5, 6))); +extern __printf(5, 6) +void ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t, + const char *, ...); +extern __printf(5, 6) +void ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t, + const char *, ...); extern void __ext4_std_error(struct super_block *, const char *, unsigned int, int); -extern void __ext4_abort(struct super_block *, const char *, unsigned int, - const char *, ...) - __attribute__ ((format (printf, 4, 5))); +extern __printf(4, 5) +void __ext4_abort(struct super_block *, const char *, unsigned int, + const char *, ...); #define ext4_abort(sb, message...) __ext4_abort(sb, __func__, \ __LINE__, ## message) -extern void __ext4_warning(struct super_block *, const char *, unsigned int, - const char *, ...) - __attribute__ ((format (printf, 4, 5))); +extern __printf(4, 5) +void __ext4_warning(struct super_block *, const char *, unsigned int, + const char *, ...); #define ext4_warning(sb, message...) __ext4_warning(sb, __func__, \ __LINE__, ## message) -extern void ext4_msg(struct super_block *, const char *, const char *, ...) - __attribute__ ((format (printf, 3, 4))); +extern __printf(3, 4) +void ext4_msg(struct super_block *, const char *, const char *, ...); extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp, const char *, unsigned int, const char *); #define dump_mmp_msg(sb, mmp, msg) __dump_mmp_msg(sb, mmp, __func__, \ __LINE__, msg) -extern void __ext4_grp_locked_error(const char *, unsigned int, \ - struct super_block *, ext4_group_t, \ - unsigned long, ext4_fsblk_t, \ - const char *, ...) - __attribute__ ((format (printf, 7, 8))); +extern __printf(7, 8) +void __ext4_grp_locked_error(const char *, unsigned int, + struct super_block *, ext4_group_t, + unsigned long, ext4_fsblk_t, + const char *, ...); #define ext4_grp_locked_error(sb, grp, message...) \ __ext4_grp_locked_error(__func__, __LINE__, (sb), (grp), ## message) extern void ext4_update_dynamic_rev(struct super_block *sb); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 986e2388f031..0defe0bfe019 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1811,8 +1811,12 @@ static int ext4_writepage(struct page *page, * We don't want to do block allocation, so redirty * the page and return. We may reach here when we do * a journal commit via journal_submit_inode_data_buffers. - * We can also reach here via shrink_page_list + * We can also reach here via shrink_page_list but it + * should never be for direct reclaim so warn if that + * happens */ + WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == + PF_MEMALLOC); goto redirty_page; } if (commit_write) diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 5efbd5d7701a..aca191bd5f8f 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -156,8 +156,8 @@ static int uni16_to_x8(struct super_block *sb, unsigned char *ascii, } else { if (uni_xlate == 1) { *op++ = ':'; - op = pack_hex_byte(op, ec >> 8); - op = pack_hex_byte(op, ec); + op = hex_byte_pack(op, ec >> 8); + op = hex_byte_pack(op, ec); len -= 5; } else { *op++ = '?'; diff --git a/fs/fat/fat.h b/fs/fat/fat.h index a5d3853822e0..1510a4d51990 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -326,15 +326,14 @@ extern int fat_fill_super(struct super_block *sb, void *data, int silent, extern int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2); /* fat/misc.c */ -extern void -__fat_fs_error(struct super_block *sb, int report, const char *fmt, ...) - __attribute__ ((format (printf, 3, 4))) __cold; +extern __printf(3, 4) __cold +void __fat_fs_error(struct super_block *sb, int report, const char *fmt, ...); #define fat_fs_error(sb, fmt, args...) \ __fat_fs_error(sb, 1, fmt , ## args) #define fat_fs_error_ratelimit(sb, fmt, args...) \ __fat_fs_error(sb, __ratelimit(&MSDOS_SB(sb)->ratelimit), fmt , ## args) -void fat_msg(struct super_block *sb, const char *level, const char *fmt, ...) - __attribute__ ((format (printf, 3, 4))) __cold; +__printf(3, 4) __cold +void fat_msg(struct super_block *sb, const char *level, const char *fmt, ...); extern int fat_clusters_flush(struct super_block *sb); extern int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster); extern void fat_time_fat2unix(struct msdos_sb_info *sbi, struct timespec *ts, diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index 66707118af25..2553b858a72e 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -201,7 +201,7 @@ int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs); void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs); void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs); -__attribute__ ((format(printf, 2, 3))) +__printf(2, 3) void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...); /** diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index 331b5e234ef3..de946170ebb1 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -311,8 +311,8 @@ static inline struct hpfs_sb_info *hpfs_sb(struct super_block *sb) /* super.c */ -void hpfs_error(struct super_block *, const char *, ...) - __attribute__((format (printf, 2, 3))); +__printf(2, 3) +void hpfs_error(struct super_block *, const char *, ...); int hpfs_stop_cycles(struct super_block *, int, int *, int *, char *); unsigned hpfs_count_one_bitmap(struct super_block *, secno); diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h index f22d108bfa5d..398ecff6e548 100644 --- a/fs/logfs/logfs.h +++ b/fs/logfs/logfs.h @@ -618,7 +618,6 @@ static inline int logfs_buf_recover(struct logfs_area *area, u64 ofs, struct page *emergency_read_begin(struct address_space *mapping, pgoff_t index); void emergency_read_end(struct page *page); void logfs_crash_dump(struct super_block *sb); -void *memchr_inv(const void *s, int c, size_t n); int logfs_statfs(struct dentry *dentry, struct kstatfs *stats); int logfs_check_ds(struct logfs_disk_super *ds); int logfs_write_sb(struct super_block *sb); diff --git a/fs/logfs/super.c b/fs/logfs/super.c index ce03a182c771..f2697e4df109 100644 --- a/fs/logfs/super.c +++ b/fs/logfs/super.c @@ -91,28 +91,6 @@ void logfs_crash_dump(struct super_block *sb) } /* - * TODO: move to lib/string.c - */ -/** - * memchr_inv - Find a character in an area of memory. - * @s: The memory area - * @c: The byte to search for - * @n: The size of the area. - * - * returns the address of the first character other than @c, or %NULL - * if the whole buffer contains just @c. - */ -void *memchr_inv(const void *s, int c, size_t n) -{ - const unsigned char *p = s; - while (n-- != 0) - if ((unsigned char)c != *p++) - return (void *)(p - 1); - - return NULL; -} - -/* * FIXME: There should be a reserve for root, similar to ext2. */ int logfs_statfs(struct dentry *dentry, struct kstatfs *stats) diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 255d5e1c03b7..3777d138f895 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -276,10 +276,10 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, /* super.c */ extern struct inode *nilfs_alloc_inode(struct super_block *); extern void nilfs_destroy_inode(struct inode *); -extern void nilfs_error(struct super_block *, const char *, const char *, ...) - __attribute__ ((format (printf, 3, 4))); -extern void nilfs_warning(struct super_block *, const char *, const char *, ...) - __attribute__ ((format (printf, 3, 4))); +extern __printf(3, 4) +void nilfs_error(struct super_block *, const char *, const char *, ...); +extern __printf(3, 4) +void nilfs_warning(struct super_block *, const char *, const char *, ...); extern struct nilfs_super_block * nilfs_read_super_block(struct super_block *, u64, int, struct buffer_head **); extern int nilfs_store_magic_and_option(struct super_block *, diff --git a/fs/ntfs/debug.h b/fs/ntfs/debug.h index 2142b1c68b61..53c27eaf2307 100644 --- a/fs/ntfs/debug.h +++ b/fs/ntfs/debug.h @@ -30,8 +30,9 @@ extern int debug_msgs; -extern void __ntfs_debug(const char *file, int line, const char *function, - const char *format, ...) __attribute__ ((format (printf, 4, 5))); +extern __printf(4, 5) +void __ntfs_debug(const char *file, int line, const char *function, + const char *format, ...); /** * ntfs_debug - write a debug level message to syslog * @f: a printf format string containing the message @@ -52,12 +53,14 @@ extern void ntfs_debug_dump_runlist(const runlist_element *rl); #endif /* !DEBUG */ -extern void __ntfs_warning(const char *function, const struct super_block *sb, - const char *fmt, ...) __attribute__ ((format (printf, 3, 4))); +extern __printf(3, 4) +void __ntfs_warning(const char *function, const struct super_block *sb, + const char *fmt, ...); #define ntfs_warning(sb, f, a...) __ntfs_warning(__func__, sb, f, ##a) -extern void __ntfs_error(const char *function, const struct super_block *sb, - const char *fmt, ...) __attribute__ ((format (printf, 3, 4))); +extern __printf(3, 4) +void __ntfs_error(const char *function, const struct super_block *sb, + const char *fmt, ...); #define ntfs_error(sb, f, a...) __ntfs_error(__func__, sb, f, ##a) #endif /* _LINUX_NTFS_DEBUG_H */ diff --git a/fs/ocfs2/super.h b/fs/ocfs2/super.h index 40c7de084c10..74ff74cf78fe 100644 --- a/fs/ocfs2/super.h +++ b/fs/ocfs2/super.h @@ -31,17 +31,15 @@ extern struct workqueue_struct *ocfs2_wq; int ocfs2_publish_get_mount_state(struct ocfs2_super *osb, int node_num); -void __ocfs2_error(struct super_block *sb, - const char *function, - const char *fmt, ...) - __attribute__ ((format (printf, 3, 4))); +__printf(3, 4) +void __ocfs2_error(struct super_block *sb, const char *function, + const char *fmt, ...); #define ocfs2_error(sb, fmt, args...) __ocfs2_error(sb, __PRETTY_FUNCTION__, fmt, ##args) -void __ocfs2_abort(struct super_block *sb, - const char *function, - const char *fmt, ...) - __attribute__ ((format (printf, 3, 4))); +__printf(3, 4) +void __ocfs2_abort(struct super_block *sb, const char *function, + const char *fmt, ...); #define ocfs2_abort(sb, fmt, args...) __ocfs2_abort(sb, __PRETTY_FUNCTION__, fmt, ##args) diff --git a/fs/partitions/ldm.c b/fs/partitions/ldm.c index af9fdf046769..bd8ae788f689 100644 --- a/fs/partitions/ldm.c +++ b/fs/partitions/ldm.c @@ -49,18 +49,20 @@ #define ldm_error(f, a...) _ldm_printk (KERN_ERR, __func__, f, ##a) #define ldm_info(f, a...) _ldm_printk (KERN_INFO, __func__, f, ##a) -__attribute__ ((format (printf, 3, 4))) -static void _ldm_printk (const char *level, const char *function, - const char *fmt, ...) +static __printf(3, 4) +void _ldm_printk(const char *level, const char *function, const char *fmt, ...) { - static char buf[128]; + struct va_format vaf; va_list args; va_start (args, fmt); - vsnprintf (buf, sizeof (buf), fmt, args); - va_end (args); - printk ("%s%s(): %s\n", level, function, buf); + vaf.fmt = fmt; + vaf.va = &args; + + printk("%s%s(): %pV\n", level, function, &vaf); + + va_end(args); } /** diff --git a/fs/pipe.c b/fs/pipe.c index 0e0be1dc0f8e..4065f07366b3 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1254,6 +1254,7 @@ out: static const struct super_operations pipefs_ops = { .destroy_inode = free_inode_nonrcu, + .statfs = simple_statfs, }; /* diff --git a/fs/proc/base.c b/fs/proc/base.c index 5eb02069e1b8..8f0087e20e16 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1107,13 +1107,6 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, goto err_sighand; } - if (oom_adjust != task->signal->oom_adj) { - if (oom_adjust == OOM_DISABLE) - atomic_inc(&task->mm->oom_disable_count); - if (task->signal->oom_adj == OOM_DISABLE) - atomic_dec(&task->mm->oom_disable_count); - } - /* * Warn that /proc/pid/oom_adj is deprecated, see * Documentation/feature-removal-schedule.txt. @@ -1215,12 +1208,6 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, goto err_sighand; } - if (oom_score_adj != task->signal->oom_score_adj) { - if (oom_score_adj == OOM_SCORE_ADJ_MIN) - atomic_inc(&task->mm->oom_disable_count); - if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) - atomic_dec(&task->mm->oom_disable_count); - } task->signal->oom_score_adj = oom_score_adj; if (has_capability_noaudit(current, CAP_SYS_RESOURCE)) task->signal->oom_score_adj_min = oom_score_adj; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5afaa58a8630..e418c5abdb0e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -44,6 +44,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) "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" "VmData:\t%8lu kB\n" @@ -55,6 +56,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) hiwater_vm << (PAGE_SHIFT-10), (total_vm - mm->reserved_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), data << (PAGE_SHIFT-10), @@ -1039,6 +1041,9 @@ static int show_numa_map(struct seq_file *m, void *v) seq_printf(m, " stack"); } + if (is_vm_hugetlb_page(vma)) + seq_printf(m, " huge"); + walk_page_range(vma->vm_start, vma->vm_end, &walk); if (!md->pages) diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 893b961dcfd8..379a02dc1217 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -24,6 +24,7 @@ #include <linux/highmem.h> #include <linux/time.h> #include <linux/init.h> +#include <linux/list.h> #include <linux/string.h> #include <linux/mount.h> #include <linux/ramfs.h> @@ -32,13 +33,18 @@ #include <linux/magic.h> #include <linux/pstore.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <linux/uaccess.h> #include "internal.h" #define PSTORE_NAMELEN 64 +static DEFINE_SPINLOCK(allpstore_lock); +static LIST_HEAD(allpstore); + struct pstore_private { + struct list_head list; struct pstore_info *psi; enum pstore_type_id type; u64 id; @@ -81,8 +87,16 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry) static void pstore_evict_inode(struct inode *inode) { + struct pstore_private *p = inode->i_private; + unsigned long flags; + end_writeback(inode); - kfree(inode->i_private); + if (p) { + spin_lock_irqsave(&allpstore_lock, flags); + list_del(&p->list); + spin_unlock_irqrestore(&allpstore_lock, flags); + kfree(p); + } } static const struct inode_operations pstore_dir_inode_operations = { @@ -182,9 +196,23 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, struct dentry *root = pstore_sb->s_root; struct dentry *dentry; struct inode *inode; - int rc; + int rc = 0; char name[PSTORE_NAMELEN]; - struct pstore_private *private; + struct pstore_private *private, *pos; + unsigned long flags; + + spin_lock_irqsave(&allpstore_lock, flags); + list_for_each_entry(pos, &allpstore, list) { + if (pos->type == type && + pos->id == id && + pos->psi == psi) { + rc = -EEXIST; + break; + } + } + spin_unlock_irqrestore(&allpstore_lock, flags); + if (rc) + return rc; rc = -ENOMEM; inode = pstore_get_inode(pstore_sb, root->d_inode, S_IFREG | 0444, 0); @@ -229,6 +257,10 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, d_add(dentry, inode); + spin_lock_irqsave(&allpstore_lock, flags); + list_add(&private->list, &allpstore); + spin_unlock_irqrestore(&allpstore_lock, flags); + mutex_unlock(&root->d_inode->i_mutex); return 0; @@ -277,7 +309,7 @@ int pstore_fill_super(struct super_block *sb, void *data, int silent) goto fail; } - pstore_get_records(); + pstore_get_records(0); return 0; fail: diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index 611c1b3c46fa..3bde461c3f34 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -1,5 +1,5 @@ extern void pstore_set_kmsg_bytes(int); -extern void pstore_get_records(void); +extern void pstore_get_records(int); extern int pstore_mkfile(enum pstore_type_id, char *psname, u64 id, char *data, size_t size, struct timespec time, struct pstore_info *psi); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index c5300ec31696..2bd620f0d796 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -25,12 +25,30 @@ #include <linux/module.h> #include <linux/pstore.h> #include <linux/string.h> +#include <linux/timer.h> #include <linux/slab.h> #include <linux/uaccess.h> +#include <linux/hardirq.h> +#include <linux/workqueue.h> #include "internal.h" /* + * We defer making "oops" entries appear in pstore - see + * whether the system is actually still running well enough + * to let someone see the entry + */ +#define PSTORE_INTERVAL (60 * HZ) + +static int pstore_new_entry; + +static void pstore_timefunc(unsigned long); +static DEFINE_TIMER(pstore_timer, pstore_timefunc, 0, 0); + +static void pstore_dowork(struct work_struct *); +static DECLARE_WORK(pstore_work, pstore_dowork); + +/* * pstore_lock just protects "psinfo" during * calls to pstore_register() */ @@ -69,15 +87,22 @@ static void pstore_dump(struct kmsg_dumper *dumper, unsigned long size, total = 0; char *dst, *why; u64 id; - int hsize; + int hsize, ret; unsigned int part = 1; + unsigned long flags = 0; + int is_locked = 0; if (reason < ARRAY_SIZE(reason_str)) why = reason_str[reason]; else why = "Unknown"; - mutex_lock(&psinfo->buf_mutex); + if (in_nmi()) { + is_locked = spin_trylock(&psinfo->buf_lock); + if (!is_locked) + pr_err("pstore dump routine blocked in NMI, may corrupt error record\n"); + } else + spin_lock_irqsave(&psinfo->buf_lock, flags); oopscount++; while (total < kmsg_bytes) { dst = psinfo->buf; @@ -97,18 +122,20 @@ static void pstore_dump(struct kmsg_dumper *dumper, memcpy(dst, s1 + s1_start, l1_cpy); memcpy(dst + l1_cpy, s2 + s2_start, l2_cpy); - id = psinfo->write(PSTORE_TYPE_DMESG, part, + ret = psinfo->write(PSTORE_TYPE_DMESG, &id, part, hsize + l1_cpy + l2_cpy, psinfo); - if (reason == KMSG_DUMP_OOPS && pstore_is_mounted()) - pstore_mkfile(PSTORE_TYPE_DMESG, psinfo->name, id, - psinfo->buf, hsize + l1_cpy + l2_cpy, - CURRENT_TIME, psinfo); + if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted()) + pstore_new_entry = 1; l1 -= l1_cpy; l2 -= l2_cpy; total += l1_cpy + l2_cpy; part++; } - mutex_unlock(&psinfo->buf_mutex); + if (in_nmi()) { + if (is_locked) + spin_unlock(&psinfo->buf_lock); + } else + spin_unlock_irqrestore(&psinfo->buf_lock, flags); } static struct kmsg_dumper pstore_dumper = { @@ -148,19 +175,24 @@ int pstore_register(struct pstore_info *psi) } if (pstore_is_mounted()) - pstore_get_records(); + pstore_get_records(0); kmsg_dump_register(&pstore_dumper); + pstore_timer.expires = jiffies + PSTORE_INTERVAL; + add_timer(&pstore_timer); + return 0; } EXPORT_SYMBOL_GPL(pstore_register); /* - * Read all the records from the persistent store. Create and - * file files in our filesystem. + * Read all the records from the persistent store. Create + * files in our filesystem. Don't warn about -EEXIST errors + * when we are re-scanning the backing store looking to add new + * error records. */ -void pstore_get_records(void) +void pstore_get_records(int quiet) { struct pstore_info *psi = psinfo; ssize_t size; @@ -168,36 +200,55 @@ void pstore_get_records(void) enum pstore_type_id type; struct timespec time; int failed = 0, rc; + unsigned long flags; if (!psi) return; - mutex_lock(&psinfo->buf_mutex); + spin_lock_irqsave(&psinfo->buf_lock, flags); rc = psi->open(psi); if (rc) goto out; while ((size = psi->read(&id, &type, &time, psi)) > 0) { - if (pstore_mkfile(type, psi->name, id, psi->buf, (size_t)size, - time, psi)) + rc = pstore_mkfile(type, psi->name, id, psi->buf, (size_t)size, + time, psi); + if (rc && (rc != -EEXIST || !quiet)) failed++; } psi->close(psi); out: - mutex_unlock(&psinfo->buf_mutex); + spin_unlock_irqrestore(&psinfo->buf_lock, flags); if (failed) printk(KERN_WARNING "pstore: failed to load %d record(s) from '%s'\n", failed, psi->name); } +static void pstore_dowork(struct work_struct *work) +{ + pstore_get_records(1); +} + +static void pstore_timefunc(unsigned long dummy) +{ + if (pstore_new_entry) { + pstore_new_entry = 0; + schedule_work(&pstore_work); + } + + mod_timer(&pstore_timer, jiffies + PSTORE_INTERVAL); +} + /* * Call platform driver to write a record to the * persistent store. */ int pstore_write(enum pstore_type_id type, char *buf, size_t size) { - u64 id; + u64 id; + int ret; + unsigned long flags; if (!psinfo) return -ENODEV; @@ -205,13 +256,13 @@ int pstore_write(enum pstore_type_id type, char *buf, size_t size) if (size > psinfo->bufsize) return -EFBIG; - mutex_lock(&psinfo->buf_mutex); + spin_lock_irqsave(&psinfo->buf_lock, flags); memcpy(psinfo->buf, buf, size); - id = psinfo->write(type, 0, size, psinfo); - if (pstore_is_mounted()) + ret = psinfo->write(type, &id, 0, size, psinfo); + if (ret == 0 && pstore_is_mounted()) pstore_mkfile(PSTORE_TYPE_DMESG, psinfo->name, id, psinfo->buf, size, CURRENT_TIME, psinfo); - mutex_unlock(&psinfo->buf_mutex); + spin_unlock_irqrestore(&psinfo->buf_lock, flags); return 0; } diff --git a/fs/read_write.c b/fs/read_write.c index dfd125798791..5ad4248b0cd8 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -633,7 +633,8 @@ ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer) + struct iovec **ret_pointer, + int check_access) { unsigned long seg; ssize_t ret; @@ -689,7 +690,8 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, ret = -EINVAL; goto out; } - if (unlikely(!access_ok(vrfy_dir(type), buf, len))) { + if (check_access + && unlikely(!access_ok(vrfy_dir(type), buf, len))) { ret = -EFAULT; goto out; } @@ -721,7 +723,7 @@ static ssize_t do_readv_writev(int type, struct file *file, } ret = rw_copy_check_uvector(type, uvector, nr_segs, - ARRAY_SIZE(iovstack), iovstack, &iov); + ARRAY_SIZE(iovstack), iovstack, &iov, 1); if (ret <= 0) goto out; diff --git a/fs/super.c b/fs/super.c index 3f56a269a4f4..32a81f3467e0 100644 --- a/fs/super.c +++ b/fs/super.c @@ -61,7 +61,7 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc) return -1; if (!grab_super_passive(sb)) - return -1; + return !sc->nr_to_scan ? 0 : -1; if (sb->s_op && sb->s_op->nr_cached_objects) fs_objects = sb->s_op->nr_cached_objects(sb); diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 48ffbdf0d017..7fdf6a7b7436 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -865,15 +865,13 @@ int sysfs_rename(struct sysfs_dirent *sd, sd->s_name = new_name; } - /* Remove from old parent's list and insert into new parent's list. */ - if (sd->s_parent != new_parent_sd) { - sysfs_unlink_sibling(sd); - sysfs_get(new_parent_sd); - sysfs_put(sd->s_parent); - sd->s_parent = new_parent_sd; - sysfs_link_sibling(sd); - } + /* Move to the appropriate place in the appropriate directories rbtree. */ + sysfs_unlink_sibling(sd); + sysfs_get(new_parent_sd); + sysfs_put(sd->s_parent); sd->s_ns = new_ns; + sd->s_parent = new_parent_sd; + sysfs_link_sibling(sd); error = 0; out: diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index dbd52d4b5eed..dc8a8dcc5ae1 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -112,8 +112,8 @@ struct extent_position { /* super.c */ -__attribute__((format(printf, 3, 4))) -extern void udf_warning(struct super_block *, const char *, const char *, ...); +extern __printf(3, 4) void udf_warning(struct super_block *, const char *, + const char *, ...); static inline void udf_updated_lvid(struct super_block *sb) { struct buffer_head *bh = UDF_SB(sb)->s_lvid_bh; diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index 5be2755dd715..c26f2bcec264 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -117,9 +117,12 @@ extern int ufs_getfrag_block (struct inode *inode, sector_t fragment, struct buf extern const struct file_operations ufs_dir_operations; /* super.c */ -extern void ufs_warning (struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); -extern void ufs_error (struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); -extern void ufs_panic (struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); +extern __printf(3, 4) +void ufs_warning(struct super_block *, const char *, const char *, ...); +extern __printf(3, 4) +void ufs_error(struct super_block *, const char *, const char *, ...); +extern __printf(3, 4) +void ufs_panic(struct super_block *, const char *, const char *, ...); /* symlink.c */ extern const struct inode_operations ufs_fast_symlink_inode_operations; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 11b2aad982d4..33b13310ee0c 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -902,11 +902,11 @@ xfs_vm_writepage( * random callers for direct reclaim or memcg reclaim. We explicitly * allow reclaim from kswapd as the stack usage there is relatively low. * - * This should really be done by the core VM, but until that happens - * filesystems like XFS, btrfs and ext4 have to take care of this - * by themselves. + * This should never happen except in the case of a VM regression so + * warn about it. */ - if ((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == PF_MEMALLOC) + if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == + PF_MEMALLOC)) goto redirty; /* diff --git a/fs/xfs/xfs_message.h b/fs/xfs/xfs_message.h index 7fb7ea007672..56dc0c17f16a 100644 --- a/fs/xfs/xfs_message.h +++ b/fs/xfs/xfs_message.h @@ -3,31 +3,29 @@ struct xfs_mount; -extern void xfs_emerg(const struct xfs_mount *mp, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern void xfs_alert(const struct xfs_mount *mp, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern void xfs_alert_tag(const struct xfs_mount *mp, int tag, - const char *fmt, ...) - __attribute__ ((format (printf, 3, 4))); -extern void xfs_crit(const struct xfs_mount *mp, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern void xfs_err(const struct xfs_mount *mp, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern void xfs_warn(const struct xfs_mount *mp, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern void xfs_notice(const struct xfs_mount *mp, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern void xfs_info(const struct xfs_mount *mp, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); +extern __printf(2, 3) +void xfs_emerg(const struct xfs_mount *mp, const char *fmt, ...); +extern __printf(2, 3) +void xfs_alert(const struct xfs_mount *mp, const char *fmt, ...); +extern __printf(3, 4) +void xfs_alert_tag(const struct xfs_mount *mp, int tag, const char *fmt, ...); +extern __printf(2, 3) +void xfs_crit(const struct xfs_mount *mp, const char *fmt, ...); +extern __printf(2, 3) +void xfs_err(const struct xfs_mount *mp, const char *fmt, ...); +extern __printf(2, 3) +void xfs_warn(const struct xfs_mount *mp, const char *fmt, ...); +extern __printf(2, 3) +void xfs_notice(const struct xfs_mount *mp, const char *fmt, ...); +extern __printf(2, 3) +void xfs_info(const struct xfs_mount *mp, const char *fmt, ...); #ifdef DEBUG -extern void xfs_debug(const struct xfs_mount *mp, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); +extern __printf(2, 3) +void xfs_debug(const struct xfs_mount *mp, const char *fmt, ...); #else -static inline void -__attribute__ ((format (printf, 2, 3))) -xfs_debug(const struct xfs_mount *mp, const char *fmt, ...) +static inline __printf(2, 3) +void xfs_debug(const struct xfs_mount *mp, const char *fmt, ...) { } #endif |