diff options
Diffstat (limited to 'fs')
458 files changed, 10634 insertions, 6971 deletions
diff --git a/fs/9p/Makefile b/fs/9p/Makefile index ff7be98f84f2..9619ccadd2fc 100644 --- a/fs/9p/Makefile +++ b/fs/9p/Makefile @@ -10,10 +10,7 @@ obj-$(CONFIG_9P_FS) := 9p.o vfs_dentry.o \ v9fs.o \ fid.o \ - xattr.o \ - xattr_user.o \ - xattr_trusted.o + xattr.o 9p-$(CONFIG_9P_FSCACHE) += cache.o 9p-$(CONFIG_9P_FS_POSIX_ACL) += acl.o -9p-$(CONFIG_9P_FS_SECURITY) += xattr_security.o diff --git a/fs/9p/acl.c b/fs/9p/acl.c index 31c010372660..9da967f38387 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -67,8 +67,8 @@ int v9fs_get_acl(struct inode *inode, struct p9_fid *fid) return 0; } /* get the default/access acl values and cache them */ - dacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_DEFAULT); - pacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_ACCESS); + dacl = __v9fs_get_acl(fid, XATTR_NAME_POSIX_ACL_DEFAULT); + pacl = __v9fs_get_acl(fid, XATTR_NAME_POSIX_ACL_ACCESS); if (!IS_ERR(dacl) && !IS_ERR(pacl)) { set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl); @@ -133,10 +133,10 @@ static int v9fs_set_acl(struct p9_fid *fid, int type, struct posix_acl *acl) goto err_free_out; switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: BUG(); @@ -212,42 +212,22 @@ int v9fs_acl_mode(struct inode *dir, umode_t *modep, return 0; } -static int v9fs_remote_get_acl(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) -{ - char *full_name; - - switch (type) { - case ACL_TYPE_ACCESS: - full_name = POSIX_ACL_XATTR_ACCESS; - break; - case ACL_TYPE_DEFAULT: - full_name = POSIX_ACL_XATTR_DEFAULT; - break; - default: - BUG(); - } - return v9fs_xattr_get(dentry, full_name, buffer, size); -} - -static int v9fs_xattr_get_acl(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int v9fs_xattr_get_acl(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { struct v9fs_session_info *v9ses; struct posix_acl *acl; int error; - if (strcmp(name, "") != 0) - return -EINVAL; - v9ses = v9fs_dentry2v9ses(dentry); /* * We allow set/get/list of acl when access=client is not specified */ if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) - return v9fs_remote_get_acl(dentry, name, buffer, size, type); + return v9fs_xattr_get(dentry, handler->name, buffer, size); - acl = v9fs_get_cached_acl(d_inode(dentry), type); + acl = v9fs_get_cached_acl(d_inode(dentry), handler->flags); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl == NULL) @@ -258,46 +238,23 @@ static int v9fs_xattr_get_acl(struct dentry *dentry, const char *name, return error; } -static int v9fs_remote_set_acl(struct dentry *dentry, const char *name, - const void *value, size_t size, - int flags, int type) -{ - char *full_name; - - switch (type) { - case ACL_TYPE_ACCESS: - full_name = POSIX_ACL_XATTR_ACCESS; - break; - case ACL_TYPE_DEFAULT: - full_name = POSIX_ACL_XATTR_DEFAULT; - break; - default: - BUG(); - } - return v9fs_xattr_set(dentry, full_name, value, size, flags); -} - - -static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name, - const void *value, size_t size, - int flags, int type) +static int v9fs_xattr_set_acl(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { int retval; struct posix_acl *acl; struct v9fs_session_info *v9ses; struct inode *inode = d_inode(dentry); - if (strcmp(name, "") != 0) - return -EINVAL; - v9ses = v9fs_dentry2v9ses(dentry); /* * set the attribute on the remote. Without even looking at the * xattr value. We leave it to the server to validate */ if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) - return v9fs_remote_set_acl(dentry, name, - value, size, flags, type); + return v9fs_xattr_set(dentry, handler->name, value, size, + flags); if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; @@ -316,9 +273,8 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name, } else acl = NULL; - switch (type) { + switch (handler->flags) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; if (acl) { umode_t mode = inode->i_mode; retval = posix_acl_equiv_mode(acl, &mode); @@ -349,7 +305,6 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name, } break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; if (!S_ISDIR(inode->i_mode)) { retval = acl ? -EINVAL : 0; goto err_out; @@ -358,23 +313,23 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name, default: BUG(); } - retval = v9fs_xattr_set(dentry, name, value, size, flags); + retval = v9fs_xattr_set(dentry, handler->name, value, size, flags); if (!retval) - set_cached_acl(inode, type, acl); + set_cached_acl(inode, handler->flags, acl); err_out: posix_acl_release(acl); return retval; } const struct xattr_handler v9fs_xattr_acl_access_handler = { - .prefix = POSIX_ACL_XATTR_ACCESS, + .name = XATTR_NAME_POSIX_ACL_ACCESS, .flags = ACL_TYPE_ACCESS, .get = v9fs_xattr_get_acl, .set = v9fs_xattr_set_acl, }; const struct xattr_handler v9fs_xattr_acl_default_handler = { - .prefix = POSIX_ACL_XATTR_DEFAULT, + .name = XATTR_NAME_POSIX_ACL_DEFAULT, .flags = ACL_TYPE_DEFAULT, .get = v9fs_xattr_get_acl, .set = v9fs_xattr_set_acl, diff --git a/fs/9p/cache.c b/fs/9p/cache.c index a69260f27555..103ca5e1267b 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -243,14 +243,14 @@ void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *filp) if (!v9inode->fscache) return; - spin_lock(&v9inode->fscache_lock); + mutex_lock(&v9inode->fscache_lock); if ((filp->f_flags & O_ACCMODE) != O_RDONLY) v9fs_cache_inode_flush_cookie(inode); else v9fs_cache_inode_get_cookie(inode); - spin_unlock(&v9inode->fscache_lock); + mutex_unlock(&v9inode->fscache_lock); } void v9fs_cache_inode_reset_cookie(struct inode *inode) @@ -264,7 +264,7 @@ void v9fs_cache_inode_reset_cookie(struct inode *inode) old = v9inode->fscache; - spin_lock(&v9inode->fscache_lock); + mutex_lock(&v9inode->fscache_lock); fscache_relinquish_cookie(v9inode->fscache, 1); v9ses = v9fs_inode2v9ses(inode); @@ -274,7 +274,7 @@ void v9fs_cache_inode_reset_cookie(struct inode *inode) p9_debug(P9_DEBUG_FSC, "inode %p revalidating cookie old %p new %p\n", inode, old, v9inode->fscache); - spin_unlock(&v9inode->fscache_lock); + mutex_unlock(&v9inode->fscache_lock); } int __v9fs_fscache_release_page(struct page *page, gfp_t gfp) diff --git a/fs/9p/cache.h b/fs/9p/cache.h index 2f9675491095..247e47e54bcc 100644 --- a/fs/9p/cache.h +++ b/fs/9p/cache.h @@ -21,6 +21,7 @@ */ #ifndef _9P_CACHE_H +#define _9P_CACHE_H #ifdef CONFIG_9P_FSCACHE #include <linux/fscache.h> #include <linux/spinlock.h> diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 0923f2cf3c80..6877050384a1 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -123,7 +123,7 @@ struct v9fs_session_info { struct v9fs_inode { #ifdef CONFIG_9P_FSCACHE - spinlock_t fscache_lock; + struct mutex fscache_lock; struct fscache_cookie *fscache; #endif struct p9_qid qid; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index b1dc51888048..3a08b3e6ff1d 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -244,7 +244,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb) return NULL; #ifdef CONFIG_9P_FSCACHE v9inode->fscache = NULL; - spin_lock_init(&v9inode->fscache_lock); + mutex_init(&v9inode->fscache_lock); #endif v9inode->writeback_fid = NULL; v9inode->cache_validity = 0; @@ -451,9 +451,9 @@ void v9fs_evict_inode(struct inode *inode) { struct v9fs_inode *v9inode = V9FS_I(inode); - truncate_inode_pages_final(inode->i_mapping); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); - filemap_fdatawrite(inode->i_mapping); + filemap_fdatawrite(&inode->i_data); v9fs_cache_inode_put_cookie(inode); /* clunk the fid stashed in writeback_fid */ @@ -1223,18 +1223,26 @@ ino_t v9fs_qid2ino(struct p9_qid *qid) } /** - * v9fs_vfs_follow_link - follow a symlink path + * v9fs_vfs_get_link - follow a symlink path * @dentry: dentry for symlink - * @cookie: place to pass the data to put_link() + * @inode: inode for symlink + * @done: delayed call for when we are done with the return value */ -static const char *v9fs_vfs_follow_link(struct dentry *dentry, void **cookie) +static const char *v9fs_vfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct v9fs_session_info *v9ses = v9fs_dentry2v9ses(dentry); - struct p9_fid *fid = v9fs_fid_lookup(dentry); + struct v9fs_session_info *v9ses; + struct p9_fid *fid; struct p9_wstat *st; char *res; + if (!dentry) + return ERR_PTR(-ECHILD); + + v9ses = v9fs_dentry2v9ses(dentry); + fid = v9fs_fid_lookup(dentry); p9_debug(P9_DEBUG_VFS, "%pd\n", dentry); if (IS_ERR(fid)) @@ -1259,7 +1267,8 @@ static const char *v9fs_vfs_follow_link(struct dentry *dentry, void **cookie) p9stat_free(st); kfree(st); - return *cookie = res; + set_delayed_call(done, kfree_link, res); + return res; } /** @@ -1368,9 +1377,6 @@ v9fs_vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rde dir->i_ino, dentry, mode, MAJOR(rdev), MINOR(rdev)); - if (!new_valid_dev(rdev)) - return -EINVAL; - /* build extension */ if (S_ISBLK(mode)) sprintf(name, "b %u %u", MAJOR(rdev), MINOR(rdev)); @@ -1455,8 +1461,7 @@ static const struct inode_operations v9fs_file_inode_operations = { static const struct inode_operations v9fs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = v9fs_vfs_follow_link, - .put_link = kfree_put_link, + .get_link = v9fs_vfs_get_link, .getattr = v9fs_vfs_getattr, .setattr = v9fs_vfs_setattr, }; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index e8aa57dc8d6d..a34702c998f5 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -829,9 +829,6 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, dir->i_ino, dentry, omode, MAJOR(rdev), MINOR(rdev)); - if (!new_valid_dev(rdev)) - return -EINVAL; - v9ses = v9fs_inode2v9ses(dir); dir_dentry = dentry->d_parent; dfid = v9fs_fid_lookup(dir_dentry); @@ -902,26 +899,34 @@ error: } /** - * v9fs_vfs_follow_link_dotl - follow a symlink path + * v9fs_vfs_get_link_dotl - follow a symlink path * @dentry: dentry for symlink - * @cookie: place to pass the data to put_link() + * @inode: inode for symlink + * @done: destructor for return value */ static const char * -v9fs_vfs_follow_link_dotl(struct dentry *dentry, void **cookie) +v9fs_vfs_get_link_dotl(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct p9_fid *fid = v9fs_fid_lookup(dentry); + struct p9_fid *fid; char *target; int retval; + if (!dentry) + return ERR_PTR(-ECHILD); + p9_debug(P9_DEBUG_VFS, "%pd\n", dentry); + fid = v9fs_fid_lookup(dentry); if (IS_ERR(fid)) return ERR_CAST(fid); retval = p9_client_readlink(fid, &target); if (retval) return ERR_PTR(retval); - return *cookie = target; + set_delayed_call(done, kfree_link, target); + return target; } int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) @@ -987,8 +992,7 @@ const struct inode_operations v9fs_file_inode_operations_dotl = { const struct inode_operations v9fs_symlink_inode_operations_dotl = { .readlink = generic_readlink, - .follow_link = v9fs_vfs_follow_link_dotl, - .put_link = kfree_put_link, + .get_link = v9fs_vfs_get_link_dotl, .getattr = v9fs_vfs_getattr_dotl, .setattr = v9fs_vfs_setattr_dotl, .setxattr = generic_setxattr, diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index 0cf44b6cccd6..9dd9b47a6c1a 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -137,6 +137,44 @@ ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) return v9fs_xattr_get(dentry, NULL, buffer, buffer_size); } +static int v9fs_xattr_handler_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) +{ + const char *full_name = xattr_full_name(handler, name); + + return v9fs_xattr_get(dentry, full_name, buffer, size); +} + +static int v9fs_xattr_handler_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + const char *full_name = xattr_full_name(handler, name); + + return v9fs_xattr_set(dentry, full_name, value, size, flags); +} + +static struct xattr_handler v9fs_xattr_user_handler = { + .prefix = XATTR_USER_PREFIX, + .get = v9fs_xattr_handler_get, + .set = v9fs_xattr_handler_set, +}; + +static struct xattr_handler v9fs_xattr_trusted_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .get = v9fs_xattr_handler_get, + .set = v9fs_xattr_handler_set, +}; + +#ifdef CONFIG_9P_FS_SECURITY +static struct xattr_handler v9fs_xattr_security_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .get = v9fs_xattr_handler_get, + .set = v9fs_xattr_handler_set, +}; +#endif + const struct xattr_handler *v9fs_xattr_handlers[] = { &v9fs_xattr_user_handler, &v9fs_xattr_trusted_handler, diff --git a/fs/9p/xattr.h b/fs/9p/xattr.h index d3e2ea3840be..c63c3bea5de5 100644 --- a/fs/9p/xattr.h +++ b/fs/9p/xattr.h @@ -19,9 +19,6 @@ #include <net/9p/client.h> extern const struct xattr_handler *v9fs_xattr_handlers[]; -extern struct xattr_handler v9fs_xattr_user_handler; -extern struct xattr_handler v9fs_xattr_trusted_handler; -extern struct xattr_handler v9fs_xattr_security_handler; extern const struct xattr_handler v9fs_xattr_acl_access_handler; extern const struct xattr_handler v9fs_xattr_acl_default_handler; diff --git a/fs/9p/xattr_security.c b/fs/9p/xattr_security.c deleted file mode 100644 index cb247a142a6e..000000000000 --- a/fs/9p/xattr_security.c +++ /dev/null @@ -1,80 +0,0 @@ -/* - * Copyright IBM Corporation, 2010 - * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of version 2.1 of the GNU Lesser General Public License - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - * - */ - - -#include <linux/module.h> -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/slab.h> -#include "xattr.h" - -static int v9fs_xattr_security_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) -{ - int retval; - char *full_name; - size_t name_len; - size_t prefix_len = XATTR_SECURITY_PREFIX_LEN; - - if (name == NULL) - return -EINVAL; - - if (strcmp(name, "") == 0) - return -EINVAL; - - name_len = strlen(name); - full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL); - if (!full_name) - return -ENOMEM; - memcpy(full_name, XATTR_SECURITY_PREFIX, prefix_len); - memcpy(full_name+prefix_len, name, name_len); - full_name[prefix_len + name_len] = '\0'; - - retval = v9fs_xattr_get(dentry, full_name, buffer, size); - kfree(full_name); - return retval; -} - -static int v9fs_xattr_security_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) -{ - int retval; - char *full_name; - size_t name_len; - size_t prefix_len = XATTR_SECURITY_PREFIX_LEN; - - if (name == NULL) - return -EINVAL; - - if (strcmp(name, "") == 0) - return -EINVAL; - - name_len = strlen(name); - full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL); - if (!full_name) - return -ENOMEM; - memcpy(full_name, XATTR_SECURITY_PREFIX, prefix_len); - memcpy(full_name + prefix_len, name, name_len); - full_name[prefix_len + name_len] = '\0'; - - retval = v9fs_xattr_set(dentry, full_name, value, size, flags); - kfree(full_name); - return retval; -} - -struct xattr_handler v9fs_xattr_security_handler = { - .prefix = XATTR_SECURITY_PREFIX, - .get = v9fs_xattr_security_get, - .set = v9fs_xattr_security_set, -}; diff --git a/fs/9p/xattr_trusted.c b/fs/9p/xattr_trusted.c deleted file mode 100644 index e30d33b8a3fb..000000000000 --- a/fs/9p/xattr_trusted.c +++ /dev/null @@ -1,80 +0,0 @@ -/* - * Copyright IBM Corporation, 2010 - * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of version 2.1 of the GNU Lesser General Public License - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - * - */ - - -#include <linux/module.h> -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/slab.h> -#include "xattr.h" - -static int v9fs_xattr_trusted_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) -{ - int retval; - char *full_name; - size_t name_len; - size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN; - - if (name == NULL) - return -EINVAL; - - if (strcmp(name, "") == 0) - return -EINVAL; - - name_len = strlen(name); - full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL); - if (!full_name) - return -ENOMEM; - memcpy(full_name, XATTR_TRUSTED_PREFIX, prefix_len); - memcpy(full_name+prefix_len, name, name_len); - full_name[prefix_len + name_len] = '\0'; - - retval = v9fs_xattr_get(dentry, full_name, buffer, size); - kfree(full_name); - return retval; -} - -static int v9fs_xattr_trusted_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) -{ - int retval; - char *full_name; - size_t name_len; - size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN; - - if (name == NULL) - return -EINVAL; - - if (strcmp(name, "") == 0) - return -EINVAL; - - name_len = strlen(name); - full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL); - if (!full_name) - return -ENOMEM; - memcpy(full_name, XATTR_TRUSTED_PREFIX, prefix_len); - memcpy(full_name + prefix_len, name, name_len); - full_name[prefix_len + name_len] = '\0'; - - retval = v9fs_xattr_set(dentry, full_name, value, size, flags); - kfree(full_name); - return retval; -} - -struct xattr_handler v9fs_xattr_trusted_handler = { - .prefix = XATTR_TRUSTED_PREFIX, - .get = v9fs_xattr_trusted_get, - .set = v9fs_xattr_trusted_set, -}; diff --git a/fs/9p/xattr_user.c b/fs/9p/xattr_user.c deleted file mode 100644 index d0b701b72080..000000000000 --- a/fs/9p/xattr_user.c +++ /dev/null @@ -1,80 +0,0 @@ -/* - * Copyright IBM Corporation, 2010 - * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of version 2.1 of the GNU Lesser General Public License - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - * - */ - - -#include <linux/module.h> -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/slab.h> -#include "xattr.h" - -static int v9fs_xattr_user_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) -{ - int retval; - char *full_name; - size_t name_len; - size_t prefix_len = XATTR_USER_PREFIX_LEN; - - if (name == NULL) - return -EINVAL; - - if (strcmp(name, "") == 0) - return -EINVAL; - - name_len = strlen(name); - full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL); - if (!full_name) - return -ENOMEM; - memcpy(full_name, XATTR_USER_PREFIX, prefix_len); - memcpy(full_name+prefix_len, name, name_len); - full_name[prefix_len + name_len] = '\0'; - - retval = v9fs_xattr_get(dentry, full_name, buffer, size); - kfree(full_name); - return retval; -} - -static int v9fs_xattr_user_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) -{ - int retval; - char *full_name; - size_t name_len; - size_t prefix_len = XATTR_USER_PREFIX_LEN; - - if (name == NULL) - return -EINVAL; - - if (strcmp(name, "") == 0) - return -EINVAL; - - name_len = strlen(name); - full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL); - if (!full_name) - return -ENOMEM; - memcpy(full_name, XATTR_USER_PREFIX, prefix_len); - memcpy(full_name + prefix_len, name, name_len); - full_name[prefix_len + name_len] = '\0'; - - retval = v9fs_xattr_set(dentry, full_name, value, size, flags); - kfree(full_name); - return retval; -} - -struct xattr_handler v9fs_xattr_user_handler = { - .prefix = XATTR_USER_PREFIX, - .get = v9fs_xattr_user_get, - .set = v9fs_xattr_user_set, -}; diff --git a/fs/Kconfig b/fs/Kconfig index da3f32f1a4e4..2bb1ef86c411 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -46,6 +46,12 @@ config FS_DAX or if unsure, say N. Saying Y will increase the size of the kernel by about 5kB. +config FS_DAX_PMD + bool + default FS_DAX + depends on FS_DAX + depends on BROKEN + endif # BLOCK # Posix ACL utility routines @@ -67,6 +73,16 @@ config FILE_LOCKING for filesystems like NFS and for the flock() system call. Disabling this option saves about 11k. +config MANDATORY_FILE_LOCKING + bool "Enable Mandatory file locking" + depends on FILE_LOCKING + default y + help + This option enables files appropriately marked files on appropriely + mounted filesystems to support mandatory locking. + + To the best of my knowledge this is dead code that no one cares about. + source "fs/notify/Kconfig" source "fs/quota/Kconfig" diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h index 24575d9d882d..ea4aba56f29d 100644 --- a/fs/adfs/adfs.h +++ b/fs/adfs/adfs.h @@ -45,7 +45,7 @@ struct adfs_dir_ops; struct adfs_sb_info { union { struct { struct adfs_discmap *s_map; /* bh list containing map */ - struct adfs_dir_ops *s_dir; /* directory operations */ + const struct adfs_dir_ops *s_dir; /* directory operations */ }; struct rcu_head rcu; /* used only at shutdown time */ }; @@ -168,8 +168,8 @@ void __adfs_error(struct super_block *sb, const char *function, extern const struct inode_operations adfs_dir_inode_operations; extern const struct file_operations adfs_dir_operations; extern const struct dentry_operations adfs_dentry_operations; -extern struct adfs_dir_ops adfs_f_dir_ops; -extern struct adfs_dir_ops adfs_fplus_dir_ops; +extern const struct adfs_dir_ops adfs_f_dir_ops; +extern const struct adfs_dir_ops adfs_fplus_dir_ops; extern int adfs_dir_update(struct super_block *sb, struct object_info *obj, int wait); diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c index 51c279a29845..fd4cf2c48e48 100644 --- a/fs/adfs/dir.c +++ b/fs/adfs/dir.c @@ -21,7 +21,7 @@ adfs_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; - struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir; + const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir; struct object_info obj; struct adfs_dir dir; int ret = 0; @@ -69,7 +69,7 @@ adfs_dir_update(struct super_block *sb, struct object_info *obj, int wait) { int ret = -EINVAL; #ifdef CONFIG_ADFS_FS_RW - struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir; + const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir; struct adfs_dir dir; printk(KERN_INFO "adfs_dir_update: object %06X in dir %06X\n", @@ -129,7 +129,7 @@ static int adfs_dir_lookup_byname(struct inode *inode, struct qstr *name, struct object_info *obj) { struct super_block *sb = inode->i_sb; - struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir; + const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir; struct adfs_dir dir; int ret; diff --git a/fs/adfs/dir_f.c b/fs/adfs/dir_f.c index 4bbe853ee50a..0fbfd0b04ae0 100644 --- a/fs/adfs/dir_f.c +++ b/fs/adfs/dir_f.c @@ -476,7 +476,7 @@ adfs_f_free(struct adfs_dir *dir) dir->sb = NULL; } -struct adfs_dir_ops adfs_f_dir_ops = { +const struct adfs_dir_ops adfs_f_dir_ops = { .read = adfs_f_read, .setpos = adfs_f_setpos, .getnext = adfs_f_getnext, diff --git a/fs/adfs/dir_fplus.c b/fs/adfs/dir_fplus.c index 82d14cdf70f9..c92cfb638c18 100644 --- a/fs/adfs/dir_fplus.c +++ b/fs/adfs/dir_fplus.c @@ -256,7 +256,7 @@ adfs_fplus_free(struct adfs_dir *dir) dir->sb = NULL; } -struct adfs_dir_ops adfs_fplus_dir_ops = { +const struct adfs_dir_ops adfs_fplus_dir_ops = { .read = adfs_fplus_read, .setpos = adfs_fplus_setpos, .getnext = adfs_fplus_getnext, diff --git a/fs/affs/affs.h b/fs/affs/affs.h index c69a87eaf57d..cc2b2efc9211 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -138,7 +138,7 @@ extern int affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh); extern int affs_remove_header(struct dentry *dentry); extern u32 affs_checksum_block(struct super_block *sb, struct buffer_head *bh); extern void affs_fix_checksum(struct super_block *sb, struct buffer_head *bh); -extern void secs_to_datestamp(time_t secs, struct affs_date *ds); +extern void secs_to_datestamp(time64_t secs, struct affs_date *ds); extern umode_t prot_to_mode(u32 prot); extern void mode_to_prot(struct inode *inode); __printf(3, 4) diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index 5fa92bc790ef..d6c7a51c93e4 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -8,6 +8,7 @@ * Please send bug reports to: hjw@zvw.de */ +#include <linux/math64.h> #include "affs.h" /* @@ -366,22 +367,22 @@ affs_fix_checksum(struct super_block *sb, struct buffer_head *bh) } void -secs_to_datestamp(time_t secs, struct affs_date *ds) +secs_to_datestamp(time64_t secs, struct affs_date *ds) { u32 days; u32 minute; + s32 rem; secs -= sys_tz.tz_minuteswest * 60 + ((8 * 365 + 2) * 24 * 60 * 60); if (secs < 0) secs = 0; - days = secs / 86400; - secs -= days * 86400; - minute = secs / 60; - secs -= minute * 60; + days = div_s64_rem(secs, 86400, &rem); + minute = rem / 60; + rem -= minute * 60; ds->days = cpu_to_be32(days); ds->mins = cpu_to_be32(minute); - ds->ticks = cpu_to_be32(secs * 50); + ds->ticks = cpu_to_be32(rem * 50); } umode_t diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 17349500592d..0fdb0f5b2239 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -140,6 +140,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino) break; case ST_SOFTLINK: inode->i_mode |= S_IFLNK; + inode_nohighmem(inode); inode->i_op = &affs_symlink_inode_operations; inode->i_data.a_ops = &affs_symlink_aops; break; diff --git a/fs/affs/namei.c b/fs/affs/namei.c index 181e05b46e72..00d3002a6780 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -344,6 +344,7 @@ affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) return -ENOSPC; inode->i_op = &affs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &affs_symlink_aops; inode->i_mode = S_IFLNK | 0777; mode_to_prot(inode); diff --git a/fs/affs/super.c b/fs/affs/super.c index 5b50c4ca43a7..8836df5f1e11 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -32,7 +32,7 @@ affs_commit_super(struct super_block *sb, int wait) struct affs_root_tail *tail = AFFS_ROOT_TAIL(sb, bh); lock_buffer(bh); - secs_to_datestamp(get_seconds(), &tail->disk_change); + secs_to_datestamp(ktime_get_real_seconds(), &tail->disk_change); affs_fix_checksum(sb, bh); unlock_buffer(bh); diff --git a/fs/affs/symlink.c b/fs/affs/symlink.c index ea5b69a18ba9..69b03dbb792f 100644 --- a/fs/affs/symlink.c +++ b/fs/affs/symlink.c @@ -14,13 +14,13 @@ static int affs_symlink_readpage(struct file *file, struct page *page) { struct buffer_head *bh; struct inode *inode = page->mapping->host; - char *link = kmap(page); + char *link = page_address(page); struct slink_front *lf; int i, j; char c; char lc; - pr_debug("follow_link(ino=%lu)\n", inode->i_ino); + pr_debug("get_link(ino=%lu)\n", inode->i_ino); bh = affs_bread(inode->i_sb, inode->i_ino); if (!bh) @@ -57,12 +57,10 @@ static int affs_symlink_readpage(struct file *file, struct page *page) link[i] = '\0'; affs_brelse(bh); SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; fail: SetPageError(page); - kunmap(page); unlock_page(page); return -EIO; } @@ -73,7 +71,6 @@ const struct address_space_operations affs_symlink_aops = { const struct inode_operations affs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = affs_notify_change, }; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index e06f5a23352a..86cc7264c21c 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -56,6 +56,7 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key) case AFS_FTYPE_SYMLINK: inode->i_mode = S_IFLNK | vnode->status.mode; inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); break; default: printk("kAFS: AFS vnode with undefined type\n"); diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 24a905b076fd..2853b4095344 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -230,14 +230,9 @@ static ssize_t afs_proc_cells_write(struct file *file, const char __user *buf, if (size <= 1 || size >= PAGE_SIZE) return -EINVAL; - kbuf = kmalloc(size + 1, GFP_KERNEL); - if (!kbuf) - return -ENOMEM; - - ret = -EFAULT; - if (copy_from_user(kbuf, buf, size) != 0) - goto done; - kbuf[size] = 0; + kbuf = memdup_user_nul(buf, size); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); /* trim to first NL */ name = memchr(kbuf, '\n', size); @@ -315,15 +310,9 @@ static ssize_t afs_proc_rootcell_write(struct file *file, if (size <= 1 || size >= PAGE_SIZE) return -EINVAL; - ret = -ENOMEM; - kbuf = kmalloc(size + 1, GFP_KERNEL); - if (!kbuf) - goto nomem; - - ret = -EFAULT; - if (copy_from_user(kbuf, buf, size) != 0) - goto infault; - kbuf[size] = 0; + kbuf = memdup_user_nul(buf, size); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); /* trim to first NL */ s = memchr(kbuf, '\n', size); @@ -337,9 +326,7 @@ static ssize_t afs_proc_rootcell_write(struct file *file, if (ret >= 0) ret = size; /* consume everything, always */ -infault: kfree(kbuf); -nomem: _leave(" = %d", ret); return ret; } diff --git a/fs/autofs4/symlink.c b/fs/autofs4/symlink.c index da0c33481bc0..84e037d1d129 100644 --- a/fs/autofs4/symlink.c +++ b/fs/autofs4/symlink.c @@ -12,10 +12,16 @@ #include "autofs_i.h" -static const char *autofs4_follow_link(struct dentry *dentry, void **cookie) +static const char *autofs4_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_sb_info *sbi; + struct autofs_info *ino; + if (!dentry) + return ERR_PTR(-ECHILD); + sbi = autofs4_sbi(dentry->d_sb); + ino = autofs4_dentry_ino(dentry); if (ino && !autofs4_oz_mode(sbi)) ino->last_used = jiffies; return d_inode(dentry)->i_private; @@ -23,5 +29,5 @@ static const char *autofs4_follow_link(struct dentry *dentry, void **cookie) const struct inode_operations autofs4_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = autofs4_follow_link + .get_link = autofs4_get_link }; diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 861b1e1c4777..103f5d7c3083 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -192,7 +192,7 @@ EXPORT_SYMBOL(make_bad_inode); * Returns true if the inode in question has been marked as bad. */ -int is_bad_inode(struct inode *inode) +bool is_bad_inode(struct inode *inode) { return (inode->i_op == &bad_inode_ops); } diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 46aedacfa6a8..25250fa87086 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -42,7 +42,7 @@ static struct inode *befs_iget(struct super_block *, unsigned long); static struct inode *befs_alloc_inode(struct super_block *sb); static void befs_destroy_inode(struct inode *inode); static void befs_destroy_inodecache(void); -static const char *befs_follow_link(struct dentry *, void **); +static int befs_symlink_readpage(struct file *, struct page *); static int befs_utf2nls(struct super_block *sb, const char *in, int in_len, char **out, int *out_len); static int befs_nls2utf(struct super_block *sb, const char *in, int in_len, @@ -79,10 +79,8 @@ static const struct address_space_operations befs_aops = { .bmap = befs_bmap, }; -static const struct inode_operations befs_symlink_inode_operations = { - .readlink = generic_readlink, - .follow_link = befs_follow_link, - .put_link = kfree_put_link, +static const struct address_space_operations befs_symlink_aops = { + .readpage = befs_symlink_readpage, }; /* @@ -398,7 +396,9 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino) inode->i_fop = &befs_dir_operations; } else if (S_ISLNK(inode->i_mode)) { if (befs_ino->i_flags & BEFS_LONG_SYMLINK) { - inode->i_op = &befs_symlink_inode_operations; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); + inode->i_mapping->a_ops = &befs_symlink_aops; } else { inode->i_link = befs_ino->i_data.symlink; inode->i_op = &simple_symlink_inode_operations; @@ -463,31 +463,33 @@ befs_destroy_inodecache(void) * The data stream become link name. Unless the LONG_SYMLINK * flag is set. */ -static const char * -befs_follow_link(struct dentry *dentry, void **cookie) +static int befs_symlink_readpage(struct file *unused, struct page *page) { - struct super_block *sb = dentry->d_sb; - struct befs_inode_info *befs_ino = BEFS_I(d_inode(dentry)); + struct inode *inode = page->mapping->host; + struct super_block *sb = inode->i_sb; + struct befs_inode_info *befs_ino = BEFS_I(inode); befs_data_stream *data = &befs_ino->i_data.ds; befs_off_t len = data->size; - char *link; + char *link = page_address(page); - if (len == 0) { + if (len == 0 || len > PAGE_SIZE) { befs_error(sb, "Long symlink with illegal length"); - return ERR_PTR(-EIO); + goto fail; } befs_debug(sb, "Follow long symlink"); - link = kmalloc(len, GFP_NOFS); - if (!link) - return ERR_PTR(-ENOMEM); if (befs_read_lsymlink(sb, data, link, len) != len) { - kfree(link); befs_error(sb, "Failed to read entire long symlink"); - return ERR_PTR(-EIO); + goto fail; } link[len - 1] = '\0'; - return *cookie = link; + SetPageUptodate(page); + unlock_page(page); + return 0; +fail: + SetPageError(page); + unlock_page(page); + return -EIO; } /* diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 6b659967898e..3a93755e880f 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -35,6 +35,7 @@ #include <linux/utsname.h> #include <linux/coredump.h> #include <linux/sched.h> +#include <linux/dax.h> #include <asm/uaccess.h> #include <asm/param.h> #include <asm/page.h> @@ -487,7 +488,7 @@ static inline int arch_elf_pt_proc(struct elfhdr *ehdr, } /** - * arch_check_elf() - check a PT_LOPROC..PT_HIPROC ELF program header + * arch_check_elf() - check an ELF executable * @ehdr: The main ELF header * @has_interp: True if the ELF has an interpreter, else false. * @state: Architecture-specific state preserved throughout the process @@ -759,16 +760,16 @@ static int load_elf_binary(struct linux_binprm *bprm) */ would_dump(bprm, interpreter); - retval = kernel_read(interpreter, 0, bprm->buf, - BINPRM_BUF_SIZE); - if (retval != BINPRM_BUF_SIZE) { + /* Get the exec headers */ + retval = kernel_read(interpreter, 0, + (void *)&loc->interp_elf_ex, + sizeof(loc->interp_elf_ex)); + if (retval != sizeof(loc->interp_elf_ex)) { if (retval >= 0) retval = -EIO; goto out_free_dentry; } - /* Get the exec headers */ - loc->interp_elf_ex = *((struct elfhdr *)bprm->buf); break; } elf_ppnt++; @@ -1236,6 +1237,15 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma, if (vma->vm_flags & VM_DONTDUMP) return 0; + /* support for DAX */ + if (vma_is_dax(vma)) { + if ((vma->vm_flags & VM_SHARED) && FILTER(DAX_SHARED)) + goto whole; + if (!(vma->vm_flags & VM_SHARED) && FILTER(DAX_PRIVATE)) + goto whole; + return 0; + } + /* Hugetlb memory check */ if (vma->vm_flags & VM_HUGETLB) { if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED)) diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index d3634bfb7fe1..b1adb92e69de 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -35,6 +35,7 @@ #include <linux/elf-fdpic.h> #include <linux/elfcore.h> #include <linux/coredump.h> +#include <linux/dax.h> #include <asm/uaccess.h> #include <asm/param.h> @@ -103,19 +104,36 @@ static void __exit exit_elf_fdpic_binfmt(void) core_initcall(init_elf_fdpic_binfmt); module_exit(exit_elf_fdpic_binfmt); -static int is_elf_fdpic(struct elfhdr *hdr, struct file *file) +static int is_elf(struct elfhdr *hdr, struct file *file) { if (memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0) return 0; if (hdr->e_type != ET_EXEC && hdr->e_type != ET_DYN) return 0; - if (!elf_check_arch(hdr) || !elf_check_fdpic(hdr)) + if (!elf_check_arch(hdr)) return 0; if (!file->f_op->mmap) return 0; return 1; } +#ifndef elf_check_fdpic +#define elf_check_fdpic(x) 0 +#endif + +#ifndef elf_check_const_displacement +#define elf_check_const_displacement(x) 0 +#endif + +static int is_constdisp(struct elfhdr *hdr) +{ + if (!elf_check_fdpic(hdr)) + return 1; + if (elf_check_const_displacement(hdr)) + return 1; + return 0; +} + /*****************************************************************************/ /* * read the program headers table into memory @@ -191,8 +209,18 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) /* check that this is a binary we know how to deal with */ retval = -ENOEXEC; - if (!is_elf_fdpic(&exec_params.hdr, bprm->file)) + if (!is_elf(&exec_params.hdr, bprm->file)) + goto error; + if (!elf_check_fdpic(&exec_params.hdr)) { +#ifdef CONFIG_MMU + /* binfmt_elf handles non-fdpic elf except on nommu */ goto error; +#else + /* nommu can only load ET_DYN (PIE) ELF */ + if (exec_params.hdr.e_type != ET_DYN) + goto error; +#endif + } /* read the program header table */ retval = elf_fdpic_fetch_phdrs(&exec_params, bprm->file); @@ -269,13 +297,13 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) } - if (elf_check_const_displacement(&exec_params.hdr)) + if (is_constdisp(&exec_params.hdr)) exec_params.flags |= ELF_FDPIC_FLAG_CONSTDISP; /* perform insanity checks on the interpreter */ if (interpreter_name) { retval = -ELIBBAD; - if (!is_elf_fdpic(&interp_params.hdr, interpreter)) + if (!is_elf(&interp_params.hdr, interpreter)) goto error; interp_params.flags = ELF_FDPIC_FLAG_PRESENT; @@ -306,9 +334,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) retval = -ENOEXEC; if (stack_size == 0) - goto error; + stack_size = 131072UL; /* same as exec.c's default commit */ - if (elf_check_const_displacement(&interp_params.hdr)) + if (is_constdisp(&interp_params.hdr)) interp_params.flags |= ELF_FDPIC_FLAG_CONSTDISP; /* flush all traces of the currently running executable */ @@ -319,7 +347,10 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) /* there's now no turning back... the old userspace image is dead, * defunct, deceased, etc. */ - set_personality(PER_LINUX_FDPIC); + if (elf_check_fdpic(&exec_params.hdr)) + set_personality(PER_LINUX_FDPIC); + else + set_personality(PER_LINUX); if (elf_read_implies_exec(&exec_params.hdr, executable_stack)) current->personality |= READ_IMPLIES_EXEC; @@ -374,10 +405,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) PAGE_ALIGN(current->mm->start_brk); #else - /* create a stack and brk area big enough for everyone - * - the brk heap starts at the bottom and works up - * - the stack starts at the top and works down - */ + /* create a stack area and zero-size brk area */ stack_size = (stack_size + PAGE_SIZE - 1) & PAGE_MASK; if (stack_size < PAGE_SIZE * 2) stack_size = PAGE_SIZE * 2; @@ -400,8 +428,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) current->mm->brk = current->mm->start_brk; current->mm->context.end_brk = current->mm->start_brk; - current->mm->context.end_brk += - (stack_size > PAGE_SIZE) ? (stack_size - PAGE_SIZE) : 0; current->mm->start_stack = current->mm->start_brk + stack_size; #endif @@ -1206,6 +1232,20 @@ static int maydump(struct vm_area_struct *vma, unsigned long mm_flags) return 0; } + /* support for DAX */ + if (vma_is_dax(vma)) { + if (vma->vm_flags & VM_SHARED) { + dump_ok = test_bit(MMF_DUMP_DAX_SHARED, &mm_flags); + kdcore("%08lx: %08lx: %s (DAX shared)", vma->vm_start, + vma->vm_flags, dump_ok ? "yes" : "no"); + } else { + dump_ok = test_bit(MMF_DUMP_DAX_PRIVATE, &mm_flags); + kdcore("%08lx: %08lx: %s (DAX private)", vma->vm_start, + vma->vm_flags, dump_ok ? "yes" : "no"); + } + return dump_ok; + } + /* By default, dump shared memory if mapped from an anonymous file. */ if (vma->vm_flags & VM_SHARED) { if (file_inode(vma->vm_file)->i_nlink == 0) { diff --git a/fs/block_dev.c b/fs/block_dev.c index 0a793c7930eb..d878e4860fb7 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -50,12 +50,21 @@ struct block_device *I_BDEV(struct inode *inode) } EXPORT_SYMBOL(I_BDEV); -static void bdev_write_inode(struct inode *inode) +static void bdev_write_inode(struct block_device *bdev) { + struct inode *inode = bdev->bd_inode; + int ret; + spin_lock(&inode->i_lock); while (inode->i_state & I_DIRTY) { spin_unlock(&inode->i_lock); - WARN_ON_ONCE(write_inode_now(inode, true)); + ret = write_inode_now(inode, true); + if (ret) { + char name[BDEVNAME_SIZE]; + pr_warn_ratelimited("VFS: Dirty inode writeback failed " + "for block device %s (err=%d).\n", + bdevname(bdev, name), ret); + } spin_lock(&inode->i_lock); } spin_unlock(&inode->i_lock); @@ -147,11 +156,16 @@ blkdev_get_block(struct inode *inode, sector_t iblock, return 0; } +static struct inode *bdev_file_inode(struct file *file) +{ + return file->f_mapping->host; +} + static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; - struct inode *inode = file->f_mapping->host; + struct inode *inode = bdev_file_inode(file); if (IS_DAX(inode)) return dax_do_io(iocb, inode, iter, offset, blkdev_get_block, @@ -329,7 +343,7 @@ static int blkdev_write_end(struct file *file, struct address_space *mapping, */ static loff_t block_llseek(struct file *file, loff_t offset, int whence) { - struct inode *bd_inode = file->f_mapping->host; + struct inode *bd_inode = bdev_file_inode(file); loff_t retval; mutex_lock(&bd_inode->i_mutex); @@ -340,7 +354,7 @@ static loff_t block_llseek(struct file *file, loff_t offset, int whence) int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) { - struct inode *bd_inode = filp->f_mapping->host; + struct inode *bd_inode = bdev_file_inode(filp); struct block_device *bdev = I_BDEV(bd_inode); int error; @@ -381,9 +395,17 @@ int bdev_read_page(struct block_device *bdev, sector_t sector, struct page *page) { const struct block_device_operations *ops = bdev->bd_disk->fops; + int result = -EOPNOTSUPP; + if (!ops->rw_page || bdev_get_integrity(bdev)) - return -EOPNOTSUPP; - return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ); + return result; + + result = blk_queue_enter(bdev->bd_queue, GFP_KERNEL); + if (result) + return result; + result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ); + blk_queue_exit(bdev->bd_queue); + return result; } EXPORT_SYMBOL_GPL(bdev_read_page); @@ -412,14 +434,20 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, int result; int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE; const struct block_device_operations *ops = bdev->bd_disk->fops; + if (!ops->rw_page || bdev_get_integrity(bdev)) return -EOPNOTSUPP; + result = blk_queue_enter(bdev->bd_queue, GFP_KERNEL); + if (result) + return result; + set_page_writeback(page); result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw); if (result) end_page_writeback(page); else unlock_page(page); + blk_queue_exit(bdev->bd_queue); return result; } EXPORT_SYMBOL_GPL(bdev_write_page); @@ -1019,12 +1047,9 @@ EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); static void flush_disk(struct block_device *bdev, bool kill_dirty) { if (__invalidate_device(bdev, kill_dirty)) { - char name[BDEVNAME_SIZE] = ""; - - if (bdev->bd_disk) - disk_name(bdev->bd_disk, 0, name); printk(KERN_WARNING "VFS: busy inodes on changed media or " - "resized disk %s\n", name); + "resized disk %s\n", + bdev->bd_disk ? bdev->bd_disk->disk_name : ""); } if (!bdev->bd_disk) @@ -1048,12 +1073,9 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev) disk_size = (loff_t)get_capacity(disk) << 9; bdev_size = i_size_read(bdev->bd_inode); if (disk_size != bdev_size) { - char name[BDEVNAME_SIZE]; - - disk_name(disk, 0, name); printk(KERN_INFO "%s: detected capacity change from %lld to %lld\n", - name, bdev_size, disk_size); + disk->disk_name, bdev_size, disk_size); i_size_write(bdev->bd_inode, disk_size); flush_disk(bdev, false); } @@ -1207,8 +1229,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } } - if (!ret) + if (!ret) { bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); + if (!blkdev_dax_capable(bdev)) + bdev->bd_inode->i_flags &= ~S_DAX; + } /* * If the device is invalidated, rescan partition @@ -1222,6 +1247,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) else if (ret == -ENOMEDIUM) invalidate_partitions(disk, bdev); } + if (ret) goto out_clear; } else { @@ -1242,12 +1268,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) goto out_clear; } bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9); - /* - * If the partition is not aligned on a page - * boundary, we can't do dax I/O to it. - */ - if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) || - (bdev->bd_part->nr_sects % (PAGE_SIZE / 512))) + if (!blkdev_dax_capable(bdev)) bdev->bd_inode->i_flags &= ~S_DAX; } } else { @@ -1500,11 +1521,14 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) WARN_ON_ONCE(bdev->bd_holders); sync_blockdev(bdev); kill_bdev(bdev); + + bdev_write_inode(bdev); /* - * ->release can cause the queue to disappear, so flush all - * dirty data before. + * Detaching bdev inode from its wb in __destroy_inode() + * is too late: the queue which embeds its bdi (along with + * root wb) can be gone as soon as we put_disk() below. */ - bdev_write_inode(bdev->bd_inode); + inode_detach_wb(bdev->bd_inode); } if (bdev->bd_contains == bdev) { if (disk->fops->release) @@ -1579,14 +1603,14 @@ EXPORT_SYMBOL(blkdev_put); static int blkdev_close(struct inode * inode, struct file * filp) { - struct block_device *bdev = I_BDEV(filp->f_mapping->host); + struct block_device *bdev = I_BDEV(bdev_file_inode(filp)); blkdev_put(bdev, filp->f_mode); return 0; } static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) { - struct block_device *bdev = I_BDEV(file->f_mapping->host); + struct block_device *bdev = I_BDEV(bdev_file_inode(file)); fmode_t mode = file->f_mode; /* @@ -1611,7 +1635,7 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; - struct inode *bd_inode = file->f_mapping->host; + struct inode *bd_inode = bdev_file_inode(file); loff_t size = i_size_read(bd_inode); struct blk_plug plug; ssize_t ret; @@ -1643,7 +1667,7 @@ EXPORT_SYMBOL_GPL(blkdev_write_iter); ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; - struct inode *bd_inode = file->f_mapping->host; + struct inode *bd_inode = bdev_file_inode(file); loff_t size = i_size_read(bd_inode); loff_t pos = iocb->ki_pos; @@ -1682,13 +1706,101 @@ static const struct address_space_operations def_blk_aops = { .is_dirty_writeback = buffer_check_dirty_writeback, }; +#ifdef CONFIG_FS_DAX +/* + * In the raw block case we do not need to contend with truncation nor + * unwritten file extents. Without those concerns there is no need for + * additional locking beyond the mmap_sem context that these routines + * are already executing under. + * + * Note, there is no protection if the block device is dynamically + * resized (partition grow/shrink) during a fault. A stable block device + * size is already not enforced in the blkdev_direct_IO path. + * + * For DAX, it is the responsibility of the block device driver to + * ensure the whole-disk device size is stable while requests are in + * flight. + * + * Finally, unlike the filemap_page_mkwrite() case there is no + * filesystem superblock to sync against freezing. We still include a + * pfn_mkwrite callback for dax drivers to receive write fault + * notifications. + */ +static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + return __dax_fault(vma, vmf, blkdev_get_block, NULL); +} + +static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, unsigned int flags) +{ + return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL); +} + +static void blkdev_vm_open(struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(vma->vm_file); + struct block_device *bdev = I_BDEV(bd_inode); + + mutex_lock(&bd_inode->i_mutex); + bdev->bd_map_count++; + mutex_unlock(&bd_inode->i_mutex); +} + +static void blkdev_vm_close(struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(vma->vm_file); + struct block_device *bdev = I_BDEV(bd_inode); + + mutex_lock(&bd_inode->i_mutex); + bdev->bd_map_count--; + mutex_unlock(&bd_inode->i_mutex); +} + +static const struct vm_operations_struct blkdev_dax_vm_ops = { + .open = blkdev_vm_open, + .close = blkdev_vm_close, + .fault = blkdev_dax_fault, + .pmd_fault = blkdev_dax_pmd_fault, + .pfn_mkwrite = blkdev_dax_fault, +}; + +static const struct vm_operations_struct blkdev_default_vm_ops = { + .open = blkdev_vm_open, + .close = blkdev_vm_close, + .fault = filemap_fault, + .map_pages = filemap_map_pages, +}; + +static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(file); + struct block_device *bdev = I_BDEV(bd_inode); + + file_accessed(file); + mutex_lock(&bd_inode->i_mutex); + bdev->bd_map_count++; + if (IS_DAX(bd_inode)) { + vma->vm_ops = &blkdev_dax_vm_ops; + vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE; + } else { + vma->vm_ops = &blkdev_default_vm_ops; + } + mutex_unlock(&bd_inode->i_mutex); + + return 0; +} +#else +#define blkdev_mmap generic_file_mmap +#endif + const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, .llseek = block_llseek, .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, - .mmap = generic_file_mmap, + .mmap = blkdev_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = block_ioctl, #ifdef CONFIG_COMPAT diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 9a0124a95851..f89db0c21b51 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -37,10 +37,10 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type) switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: BUG(); @@ -81,7 +81,7 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { ret = posix_acl_equiv_mode(acl, &inode->i_mode); if (ret < 0) @@ -94,7 +94,7 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, case ACL_TYPE_DEFAULT: if (!S_ISDIR(inode->i_mode)) return acl ? -EINVAL : 0; - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: return -EINVAL; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 6dcdb2ec9211..d453d62ab0c6 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -355,7 +355,7 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info, index = srcu_read_lock(&fs_info->subvol_srcu); - root = btrfs_read_fs_root_no_name(fs_info, &root_key); + root = btrfs_get_fs_root(fs_info, &root_key, false); if (IS_ERR(root)) { srcu_read_unlock(&fs_info->subvol_srcu, index); ret = PTR_ERR(root); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 97b049ad0594..c473c42d7d6c 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -482,13 +482,12 @@ static noinline int add_ra_bio_pages(struct inode *inode, goto next; } - page = __page_cache_alloc(mapping_gfp_mask(mapping) & - ~__GFP_FS); + page = __page_cache_alloc(mapping_gfp_constraint(mapping, + ~__GFP_FS)); if (!page) break; - if (add_to_page_cache_lru(page, mapping, pg_index, - GFP_NOFS)) { + if (add_to_page_cache_lru(page, mapping, pg_index, GFP_NOFS)) { page_cache_release(page); goto next; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index a2e73f6053a8..b7e4e344e8e0 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3367,7 +3367,7 @@ static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info) static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping) { - return mapping_gfp_mask(mapping) & ~__GFP_FS; + return mapping_gfp_constraint(mapping, ~__GFP_FS); } /* extent-tree.c */ @@ -3416,6 +3416,7 @@ int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *btrfs_lookup_block_group( struct btrfs_fs_info *info, u64 bytenr); +void btrfs_get_block_group(struct btrfs_block_group_cache *cache); void btrfs_put_block_group(struct btrfs_block_group_cache *cache); int get_block_group_index(struct btrfs_block_group_cache *cache); struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, @@ -3479,6 +3480,9 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytes_used, u64 type, u64 chunk_objectid, u64 chunk_offset, u64 size); +struct btrfs_trans_handle *btrfs_start_trans_remove_block_group( + struct btrfs_fs_info *fs_info, + const u64 chunk_offset); int btrfs_remove_block_group(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 group_start, struct extent_map *em); @@ -4020,7 +4024,8 @@ void btrfs_get_block_group_info(struct list_head *groups_list, struct btrfs_ioctl_space_info *space); void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock, struct btrfs_ioctl_balance_args *bargs); - +ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen, + struct file *dst_file, u64 dst_loff); /* file.c */ int btrfs_auto_defrag_init(void); @@ -4051,6 +4056,11 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode, loff_t pos, size_t write_bytes, struct extent_state **cached); int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); +ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t len, unsigned int flags); +int btrfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len); /* tree-defrag.c */ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 2d4667594681..42a378a4eefb 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -923,7 +923,7 @@ static int check_async_write(struct inode *inode, unsigned long bio_flags) if (bio_flags & EXTENT_BIO_TREE_LOG) return 0; #ifdef CONFIG_X86 - if (cpu_has_xmm4_2) + if (static_cpu_has_safe(X86_FEATURE_XMM4_2)) return 0; #endif return 1; @@ -2575,7 +2575,7 @@ int open_ctree(struct super_block *sb, fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */ /* readahead state */ - INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); spin_lock_init(&fs_info->reada_lock); fs_info->thread_pool_size = min_t(unsigned long, @@ -3780,6 +3780,9 @@ void close_ctree(struct btrfs_root *root) fs_info->closing = 1; smp_mb(); + /* wait for the qgroup rescan worker to stop */ + btrfs_qgroup_wait_for_completion(fs_info); + /* wait for the uuid_scan task to finish */ down(&fs_info->uuid_tree_rescan_sem); /* avoid complains from lockdep et al., set sem back to initial state */ diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 99a8e57da8a1..c4661db2b72a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -124,7 +124,7 @@ static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits) return (cache->flags & bits) == bits; } -static void btrfs_get_block_group(struct btrfs_block_group_cache *cache) +void btrfs_get_block_group(struct btrfs_block_group_cache *cache) { atomic_inc(&cache->count); } @@ -5915,19 +5915,6 @@ static int update_block_group(struct btrfs_trans_handle *trans, set_extent_dirty(info->pinned_extents, bytenr, bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL); - /* - * No longer have used bytes in this block group, queue - * it for deletion. - */ - if (old_val == 0) { - spin_lock(&info->unused_bgs_lock); - if (list_empty(&cache->bg_list)) { - btrfs_get_block_group(cache); - list_add_tail(&cache->bg_list, - &info->unused_bgs); - } - spin_unlock(&info->unused_bgs_lock); - } } spin_lock(&trans->transaction->dirty_bgs_lock); @@ -5939,6 +5926,22 @@ static int update_block_group(struct btrfs_trans_handle *trans, } spin_unlock(&trans->transaction->dirty_bgs_lock); + /* + * No longer have used bytes in this block group, queue it for + * deletion. We do this after adding the block group to the + * dirty list to avoid races between cleaner kthread and space + * cache writeout. + */ + if (!alloc && old_val == 0) { + spin_lock(&info->unused_bgs_lock); + if (list_empty(&cache->bg_list)) { + btrfs_get_block_group(cache); + list_add_tail(&cache->bg_list, + &info->unused_bgs); + } + spin_unlock(&info->unused_bgs_lock); + } + btrfs_put_block_group(cache); total -= num_bytes; bytenr += num_bytes; @@ -8105,21 +8108,47 @@ reada: } /* - * TODO: Modify related function to add related node/leaf to dirty_extent_root, - * for later qgroup accounting. - * - * Current, this function does nothing. + * These may not be seen by the usual inc/dec ref code so we have to + * add them here. */ +static int record_one_subtree_extent(struct btrfs_trans_handle *trans, + struct btrfs_root *root, u64 bytenr, + u64 num_bytes) +{ + struct btrfs_qgroup_extent_record *qrecord; + struct btrfs_delayed_ref_root *delayed_refs; + + qrecord = kmalloc(sizeof(*qrecord), GFP_NOFS); + if (!qrecord) + return -ENOMEM; + + qrecord->bytenr = bytenr; + qrecord->num_bytes = num_bytes; + qrecord->old_roots = NULL; + + delayed_refs = &trans->transaction->delayed_refs; + spin_lock(&delayed_refs->lock); + if (btrfs_qgroup_insert_dirty_extent(delayed_refs, qrecord)) + kfree(qrecord); + spin_unlock(&delayed_refs->lock); + + return 0; +} + static int account_leaf_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *eb) { int nr = btrfs_header_nritems(eb); - int i, extent_type; + int i, extent_type, ret; struct btrfs_key key; struct btrfs_file_extent_item *fi; u64 bytenr, num_bytes; + /* We can be called directly from walk_up_proc() */ + if (!root->fs_info->quota_enabled) + return 0; + for (i = 0; i < nr; i++) { btrfs_item_key_to_cpu(eb, &key, i); @@ -8138,6 +8167,10 @@ static int account_leaf_items(struct btrfs_trans_handle *trans, continue; num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi); + + ret = record_one_subtree_extent(trans, root, bytenr, num_bytes); + if (ret) + return ret; } return 0; } @@ -8206,8 +8239,6 @@ static int adjust_slots_upwards(struct btrfs_root *root, /* * root_eb is the subtree root and is locked before this function is called. - * TODO: Modify this function to mark all (including complete shared node) - * to dirty_extent_root to allow it get accounted in qgroup. */ static int account_shared_subtree(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -8285,6 +8316,11 @@ walk_down: btrfs_tree_read_lock(eb); btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); path->locks[level] = BTRFS_READ_LOCK_BLOCKING; + + ret = record_one_subtree_extent(trans, root, child_bytenr, + root->nodesize); + if (ret) + goto out; } if (level == 0) { @@ -10256,6 +10292,47 @@ out: return ret; } +struct btrfs_trans_handle * +btrfs_start_trans_remove_block_group(struct btrfs_fs_info *fs_info, + const u64 chunk_offset) +{ + struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree; + struct extent_map *em; + struct map_lookup *map; + unsigned int num_items; + + read_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, chunk_offset, 1); + read_unlock(&em_tree->lock); + ASSERT(em && em->start == chunk_offset); + + /* + * We need to reserve 3 + N units from the metadata space info in order + * to remove a block group (done at btrfs_remove_chunk() and at + * btrfs_remove_block_group()), which are used for: + * + * 1 unit for adding the free space inode's orphan (located in the tree + * of tree roots). + * 1 unit for deleting the block group item (located in the extent + * tree). + * 1 unit for deleting the free space item (located in tree of tree + * roots). + * N units for deleting N device extent items corresponding to each + * stripe (located in the device tree). + * + * In order to remove a block group we also need to reserve units in the + * system space info in order to update the chunk tree (update one or + * more device items and remove one chunk item), but this is done at + * btrfs_remove_chunk() through a call to check_system_chunk(). + */ + map = (struct map_lookup *)em->bdev; + num_items = 3 + map->num_stripes; + free_extent_map(em); + + return btrfs_start_transaction_fallback_global_rsv(fs_info->extent_root, + num_items, 1); +} + /* * Process the unused_bgs list and remove any that don't have any allocated * space inside of them. @@ -10279,22 +10356,25 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) block_group = list_first_entry(&fs_info->unused_bgs, struct btrfs_block_group_cache, bg_list); - space_info = block_group->space_info; list_del_init(&block_group->bg_list); + + space_info = block_group->space_info; + if (ret || btrfs_mixed_space_info(space_info)) { btrfs_put_block_group(block_group); continue; } spin_unlock(&fs_info->unused_bgs_lock); - mutex_lock(&root->fs_info->delete_unused_bgs_mutex); + mutex_lock(&fs_info->delete_unused_bgs_mutex); /* Don't want to race with allocators so take the groups_sem */ down_write(&space_info->groups_sem); spin_lock(&block_group->lock); if (block_group->reserved || btrfs_block_group_used(&block_group->item) || - block_group->ro) { + block_group->ro || + list_is_singular(&block_group->list)) { /* * We want to bail if we made new allocations or have * outstanding allocations in this block group. We do @@ -10319,8 +10399,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) * Want to do this before we do anything else so we can recover * properly if we fail to join the transaction. */ - /* 1 for btrfs_orphan_reserve_metadata() */ - trans = btrfs_start_transaction(root, 1); + trans = btrfs_start_trans_remove_block_group(fs_info, + block_group->key.objectid); if (IS_ERR(trans)) { btrfs_dec_block_group_ro(root, block_group); ret = PTR_ERR(trans); @@ -10400,17 +10480,21 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) * until transaction commit to do the actual discard. */ if (trimming) { - WARN_ON(!list_empty(&block_group->bg_list)); - spin_lock(&trans->transaction->deleted_bgs_lock); + spin_lock(&fs_info->unused_bgs_lock); + /* + * A concurrent scrub might have added us to the list + * fs_info->unused_bgs, so use a list_move operation + * to add the block group to the deleted_bgs list. + */ list_move(&block_group->bg_list, &trans->transaction->deleted_bgs); - spin_unlock(&trans->transaction->deleted_bgs_lock); + spin_unlock(&fs_info->unused_bgs_lock); btrfs_get_block_group(block_group); } end_trans: btrfs_end_transaction(trans, root); next: - mutex_unlock(&root->fs_info->delete_unused_bgs_mutex); + mutex_unlock(&fs_info->delete_unused_bgs_mutex); btrfs_put_block_group(block_group); spin_lock(&fs_info->unused_bgs_lock); } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 33a01ea41465..9abe18763a7f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -616,7 +616,7 @@ static int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, if (bits & (EXTENT_IOBITS | EXTENT_BOUNDARY)) clear = 1; again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { /* * Don't care for allocation failure here because we might end * up not needing the pre-allocated extent state at all, which @@ -741,7 +741,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); goto again; } @@ -874,7 +874,7 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, bits |= EXTENT_FIRST_DELALLOC; again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { prealloc = alloc_extent_state(mask); BUG_ON(!prealloc); } @@ -1052,7 +1052,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); goto again; } @@ -1100,7 +1100,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, btrfs_debug_check_extent_io_range(tree, start, end); again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { /* * Best effort, don't worry if extent state allocation fails * here for the first iteration. We might have a cached state @@ -1278,7 +1278,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); first_iteration = false; goto again; @@ -4386,7 +4386,7 @@ int try_release_extent_mapping(struct extent_map_tree *map, u64 start = page_offset(page); u64 end = start + PAGE_CACHE_SIZE - 1; - if ((mask & __GFP_WAIT) && + if (gfpflags_allow_blocking(mask) && page->mapping->host->i_size > 16 * 1024 * 1024) { u64 len; while (start <= end) { diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 6bd5ce9d75f0..e3d9022bfd4e 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -756,8 +756,16 @@ next_slot: } btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); - if (key.objectid > ino || - key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end) + + if (key.objectid > ino) + break; + if (WARN_ON_ONCE(key.objectid < ino) || + key.type < BTRFS_EXTENT_DATA_KEY) { + ASSERT(del_nr == 0); + path->slots[0]++; + goto next_slot; + } + if (key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end) break; fi = btrfs_item_ptr(leaf, path->slots[0], @@ -776,8 +784,8 @@ next_slot: btrfs_file_extent_inline_len(leaf, path->slots[0], fi); } else { - WARN_ON(1); - extent_end = search_start; + /* can't happen */ + BUG(); } /* @@ -1283,7 +1291,8 @@ out: * on error we return an unlocked page and the error value * on success we return a locked page and 0 */ -static int prepare_uptodate_page(struct page *page, u64 pos, +static int prepare_uptodate_page(struct inode *inode, + struct page *page, u64 pos, bool force_uptodate) { int ret = 0; @@ -1298,6 +1307,10 @@ static int prepare_uptodate_page(struct page *page, u64 pos, unlock_page(page); return -EIO; } + if (page->mapping != inode->i_mapping) { + unlock_page(page); + return -EAGAIN; + } } return 0; } @@ -1316,6 +1329,7 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages, int faili; for (i = 0; i < num_pages; i++) { +again: pages[i] = find_or_create_page(inode->i_mapping, index + i, mask | __GFP_WRITE); if (!pages[i]) { @@ -1325,13 +1339,17 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages, } if (i == 0) - err = prepare_uptodate_page(pages[i], pos, + err = prepare_uptodate_page(inode, pages[i], pos, force_uptodate); - if (i == num_pages - 1) - err = prepare_uptodate_page(pages[i], + if (!err && i == num_pages - 1) + err = prepare_uptodate_page(inode, pages[i], pos + write_bytes, false); if (err) { page_cache_release(pages[i]); + if (err == -EAGAIN) { + err = 0; + goto again; + } faili = i - 1; goto fail; } @@ -1874,8 +1892,13 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) struct btrfs_log_ctx ctx; int ret = 0; bool full_sync = 0; - const u64 len = end - start + 1; + u64 len; + /* + * The range length can be represented by u64, we have to do the typecasts + * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync() + */ + len = (u64)end - (u64)start + 1; trace_btrfs_sync_file(file, datasync); /* @@ -2063,8 +2086,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) } } if (!full_sync) { - ret = btrfs_wait_ordered_range(inode, start, - end - start + 1); + ret = btrfs_wait_ordered_range(inode, start, len); if (ret) { btrfs_end_transaction(trans, root); goto out; @@ -2912,6 +2934,9 @@ const struct file_operations btrfs_file_operations = { #ifdef CONFIG_COMPAT .compat_ioctl = btrfs_ioctl, #endif + .copy_file_range = btrfs_copy_file_range, + .clone_file_range = btrfs_clone_file_range, + .dedupe_file_range = btrfs_dedupe_file_range, }; void btrfs_auto_defrag_exit(void) diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 0948d34cb84a..cfe99bec49de 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -85,8 +85,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, } mapping_set_gfp_mask(inode->i_mapping, - mapping_gfp_mask(inode->i_mapping) & - ~(__GFP_FS | __GFP_HIGHMEM)); + mapping_gfp_constraint(inode->i_mapping, + ~(__GFP_FS | __GFP_HIGHMEM))); return inode; } @@ -891,7 +891,7 @@ out: spin_unlock(&block_group->lock); ret = 0; - btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuild it now", + btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuilding it now", block_group->key.objectid); } @@ -2972,7 +2972,7 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group, u64 cont1_bytes, u64 min_bytes) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; - struct btrfs_free_space *entry; + struct btrfs_free_space *entry = NULL; int ret = -ENOSPC; u64 bitmap_offset = offset_to_bitmap(ctl, offset); @@ -2983,8 +2983,10 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group, * The bitmap that covers offset won't be in the list unless offset * is just its start offset. */ - entry = list_first_entry(bitmaps, struct btrfs_free_space, list); - if (entry->offset != bitmap_offset) { + if (!list_empty(bitmaps)) + entry = list_first_entry(bitmaps, struct btrfs_free_space, list); + + if (!entry || entry->offset != bitmap_offset) { entry = tree_search_offset(ctl, bitmap_offset, 1, 0); if (entry && list_empty(&entry->list)) list_add(&entry->list, bitmaps); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4439fbb4ff45..3b8856e182ae 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1304,8 +1304,14 @@ next_slot: num_bytes = 0; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); - if (found_key.objectid > ino || - found_key.type > BTRFS_EXTENT_DATA_KEY || + if (found_key.objectid > ino) + break; + if (WARN_ON_ONCE(found_key.objectid < ino) || + found_key.type < BTRFS_EXTENT_DATA_KEY) { + path->slots[0]++; + goto next_slot; + } + if (found_key.type > BTRFS_EXTENT_DATA_KEY || found_key.offset > end) break; @@ -3544,10 +3550,10 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf, int scanned = 0; if (!xattr_access) { - xattr_access = btrfs_name_hash(POSIX_ACL_XATTR_ACCESS, - strlen(POSIX_ACL_XATTR_ACCESS)); - xattr_default = btrfs_name_hash(POSIX_ACL_XATTR_DEFAULT, - strlen(POSIX_ACL_XATTR_DEFAULT)); + xattr_access = btrfs_name_hash(XATTR_NAME_POSIX_ACL_ACCESS, + strlen(XATTR_NAME_POSIX_ACL_ACCESS)); + xattr_default = btrfs_name_hash(XATTR_NAME_POSIX_ACL_DEFAULT, + strlen(XATTR_NAME_POSIX_ACL_DEFAULT)); } slot++; @@ -3768,6 +3774,7 @@ cache_acl: break; case S_IFLNK: inode->i_op = &btrfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &btrfs_symlink_aops; break; default: @@ -4040,9 +4047,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans, */ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir) { - struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(dir)->root; - int ret; /* * 1 for the possible orphan item @@ -4051,27 +4056,7 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir) * 1 for the inode ref * 1 for the inode */ - trans = btrfs_start_transaction(root, 5); - if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC) - return trans; - - if (PTR_ERR(trans) == -ENOSPC) { - u64 num_bytes = btrfs_calc_trans_metadata_size(root, 5); - - trans = btrfs_start_transaction(root, 0); - if (IS_ERR(trans)) - return trans; - ret = btrfs_cond_migrate_bytes(root->fs_info, - &root->fs_info->trans_block_rsv, - num_bytes, 5); - if (ret) { - btrfs_end_transaction(trans, root); - return ERR_PTR(ret); - } - trans->block_rsv = &root->fs_info->trans_block_rsv; - trans->bytes_reserved = num_bytes; - } - return trans; + return btrfs_start_transaction_fallback_global_rsv(root, 5, 5); } static int btrfs_unlink(struct inode *dir, struct dentry *dentry) @@ -6360,9 +6345,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, u64 objectid; u64 index = 0; - if (!new_valid_dev(rdev)) - return -EINVAL; - /* * 2 for inode item and ref * 2 for dir items @@ -7506,6 +7488,28 @@ struct btrfs_dio_data { u64 reserve; }; +static void adjust_dio_outstanding_extents(struct inode *inode, + struct btrfs_dio_data *dio_data, + const u64 len) +{ + unsigned num_extents; + + num_extents = (unsigned) div64_u64(len + BTRFS_MAX_EXTENT_SIZE - 1, + BTRFS_MAX_EXTENT_SIZE); + /* + * If we have an outstanding_extents count still set then we're + * within our reservation, otherwise we need to adjust our inode + * counter appropriately. + */ + if (dio_data->outstanding_extents) { + dio_data->outstanding_extents -= num_extents; + } else { + spin_lock(&BTRFS_I(inode)->lock); + BTRFS_I(inode)->outstanding_extents += num_extents; + spin_unlock(&BTRFS_I(inode)->lock); + } +} + static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { @@ -7541,8 +7545,11 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, * If this errors out it's because we couldn't invalidate pagecache for * this range and we need to fallback to buffered. */ - if (lock_extent_direct(inode, lockstart, lockend, &cached_state, create)) - return -ENOTBLK; + if (lock_extent_direct(inode, lockstart, lockend, &cached_state, + create)) { + ret = -ENOTBLK; + goto err; + } em = btrfs_get_extent(inode, NULL, 0, start, len, 0); if (IS_ERR(em)) { @@ -7660,19 +7667,7 @@ unlock: if (start + len > i_size_read(inode)) i_size_write(inode, start + len); - /* - * If we have an outstanding_extents count still set then we're - * within our reservation, otherwise we need to adjust our inode - * counter appropriately. - */ - if (dio_data->outstanding_extents) { - (dio_data->outstanding_extents)--; - } else { - spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->outstanding_extents++; - spin_unlock(&BTRFS_I(inode)->lock); - } - + adjust_dio_outstanding_extents(inode, dio_data, len); btrfs_free_reserved_data_space(inode, start, len); WARN_ON(dio_data->reserve < len); dio_data->reserve -= len; @@ -7699,8 +7694,17 @@ unlock: unlock_err: clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, unlock_bits, 1, 0, &cached_state, GFP_NOFS); +err: if (dio_data) current->journal_info = dio_data; + /* + * Compensate the delalloc release we do in btrfs_direct_IO() when we + * write less data then expected, so that we don't underflow our inode's + * outstanding extents counter. + */ + if (create && dio_data) + adjust_dio_outstanding_extents(inode, dio_data, len); + return ret; } @@ -9702,6 +9706,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, btrfs_free_path(path); inode->i_op = &btrfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &btrfs_symlink_aops; inode_set_bytes(inode, name_len); btrfs_i_size_write(inode, name_len); @@ -9991,7 +9996,7 @@ static const struct inode_operations btrfs_dir_inode_operations = { .setattr = btrfs_setattr, .mknod = btrfs_mknod, .setxattr = btrfs_setxattr, - .getxattr = btrfs_getxattr, + .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .permission = btrfs_permission, @@ -10068,7 +10073,7 @@ static const struct inode_operations btrfs_file_inode_operations = { .getattr = btrfs_getattr, .setattr = btrfs_setattr, .setxattr = btrfs_setxattr, - .getxattr = btrfs_getxattr, + .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .permission = btrfs_permission, @@ -10082,7 +10087,7 @@ static const struct inode_operations btrfs_special_inode_operations = { .setattr = btrfs_setattr, .permission = btrfs_permission, .setxattr = btrfs_setxattr, - .getxattr = btrfs_getxattr, + .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .get_acl = btrfs_get_acl, @@ -10091,13 +10096,12 @@ static const struct inode_operations btrfs_special_inode_operations = { }; static const struct inode_operations btrfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getattr = btrfs_getattr, .setattr = btrfs_setattr, .permission = btrfs_permission, .setxattr = btrfs_setxattr, - .getxattr = btrfs_getxattr, + .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .update_time = btrfs_update_time, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index da94138eb85e..e21997385d14 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2962,7 +2962,7 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst, flush_dcache_page(dst_page); if (memcmp(addr, dst_addr, cmp_len)) - ret = BTRFS_SAME_DATA_DIFFERS; + ret = -EBADE; kunmap_atomic(addr); kunmap_atomic(dst_addr); @@ -3098,53 +3098,16 @@ out_unlock: #define BTRFS_MAX_DEDUPE_LEN (16 * 1024 * 1024) -static long btrfs_ioctl_file_extent_same(struct file *file, - struct btrfs_ioctl_same_args __user *argp) +ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen, + struct file *dst_file, u64 dst_loff) { - struct btrfs_ioctl_same_args *same = NULL; - struct btrfs_ioctl_same_extent_info *info; - struct inode *src = file_inode(file); - u64 off; - u64 len; - int i; - int ret; - unsigned long size; + struct inode *src = file_inode(src_file); + struct inode *dst = file_inode(dst_file); u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize; - bool is_admin = capable(CAP_SYS_ADMIN); - u16 count; - - if (!(file->f_mode & FMODE_READ)) - return -EINVAL; - - ret = mnt_want_write_file(file); - if (ret) - return ret; - - if (get_user(count, &argp->dest_count)) { - ret = -EFAULT; - goto out; - } - - size = offsetof(struct btrfs_ioctl_same_args __user, info[count]); - - same = memdup_user(argp, size); - - if (IS_ERR(same)) { - ret = PTR_ERR(same); - same = NULL; - goto out; - } + ssize_t res; - off = same->logical_offset; - len = same->length; - - /* - * Limit the total length we will dedupe for each operation. - * This is intended to bound the total time spent in this - * ioctl to something sane. - */ - if (len > BTRFS_MAX_DEDUPE_LEN) - len = BTRFS_MAX_DEDUPE_LEN; + if (olen > BTRFS_MAX_DEDUPE_LEN) + olen = BTRFS_MAX_DEDUPE_LEN; if (WARN_ON_ONCE(bs < PAGE_CACHE_SIZE)) { /* @@ -3152,58 +3115,13 @@ static long btrfs_ioctl_file_extent_same(struct file *file, * result, btrfs_cmp_data() won't correctly handle * this situation without an update. */ - ret = -EINVAL; - goto out; - } - - ret = -EISDIR; - if (S_ISDIR(src->i_mode)) - goto out; - - ret = -EACCES; - if (!S_ISREG(src->i_mode)) - goto out; - - /* pre-format output fields to sane values */ - for (i = 0; i < count; i++) { - same->info[i].bytes_deduped = 0ULL; - same->info[i].status = 0; - } - - for (i = 0, info = same->info; i < count; i++, info++) { - struct inode *dst; - struct fd dst_file = fdget(info->fd); - if (!dst_file.file) { - info->status = -EBADF; - continue; - } - dst = file_inode(dst_file.file); - - if (!(is_admin || (dst_file.file->f_mode & FMODE_WRITE))) { - info->status = -EINVAL; - } else if (file->f_path.mnt != dst_file.file->f_path.mnt) { - info->status = -EXDEV; - } else if (S_ISDIR(dst->i_mode)) { - info->status = -EISDIR; - } else if (!S_ISREG(dst->i_mode)) { - info->status = -EACCES; - } else { - info->status = btrfs_extent_same(src, off, len, dst, - info->logical_offset); - if (info->status == 0) - info->bytes_deduped += len; - } - fdput(dst_file); + return -EINVAL; } - ret = copy_to_user(argp, same, size); - if (ret) - ret = -EFAULT; - -out: - mnt_drop_write_file(file); - kfree(same); - return ret; + res = btrfs_extent_same(src, loff, olen, dst, dst_loff); + if (res) + return res; + return olen; } static int clone_finish_inode_update(struct btrfs_trans_handle *trans, @@ -3779,17 +3697,16 @@ out: return ret; } -static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, - u64 off, u64 olen, u64 destoff) +static noinline int btrfs_clone_files(struct file *file, struct file *file_src, + u64 off, u64 olen, u64 destoff) { struct inode *inode = file_inode(file); + struct inode *src = file_inode(file_src); struct btrfs_root *root = BTRFS_I(inode)->root; - struct fd src_file; - struct inode *src; int ret; u64 len = olen; u64 bs = root->fs_info->sb->s_blocksize; - int same_inode = 0; + int same_inode = src == inode; /* * TODO: @@ -3802,49 +3719,20 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, * be either compressed or non-compressed. */ - /* the destination must be opened for writing */ - if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND)) - return -EINVAL; - if (btrfs_root_readonly(root)) return -EROFS; - ret = mnt_want_write_file(file); - if (ret) - return ret; - - src_file = fdget(srcfd); - if (!src_file.file) { - ret = -EBADF; - goto out_drop_write; - } - - ret = -EXDEV; - if (src_file.file->f_path.mnt != file->f_path.mnt) - goto out_fput; - - src = file_inode(src_file.file); - - ret = -EINVAL; - if (src == inode) - same_inode = 1; - - /* the src must be open for reading */ - if (!(src_file.file->f_mode & FMODE_READ)) - goto out_fput; + if (file_src->f_path.mnt != file->f_path.mnt || + src->i_sb != inode->i_sb) + return -EXDEV; /* don't make the dst file partly checksummed */ if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) != (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) - goto out_fput; + return -EINVAL; - ret = -EISDIR; if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode)) - goto out_fput; - - ret = -EXDEV; - if (src->i_sb != inode->i_sb) - goto out_fput; + return -EISDIR; if (!same_inode) { btrfs_double_inode_lock(src, inode); @@ -3921,21 +3809,25 @@ out_unlock: btrfs_double_inode_unlock(src, inode); else mutex_unlock(&src->i_mutex); -out_fput: - fdput(src_file); -out_drop_write: - mnt_drop_write_file(file); return ret; } -static long btrfs_ioctl_clone_range(struct file *file, void __user *argp) +ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t len, unsigned int flags) { - struct btrfs_ioctl_clone_range_args args; + ssize_t ret; - if (copy_from_user(&args, argp, sizeof(args))) - return -EFAULT; - return btrfs_ioctl_clone(file, args.src_fd, args.src_offset, - args.src_length, args.dest_offset); + ret = btrfs_clone_files(file_out, file_in, pos_in, len, pos_out); + if (ret == 0) + ret = len; + return ret; +} + +int btrfs_clone_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, u64 len) +{ + return btrfs_clone_files(dst_file, src_file, off, len, destoff); } /* @@ -5485,10 +5377,6 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_dev_info(root, argp); case BTRFS_IOC_BALANCE: return btrfs_ioctl_balance(file, NULL); - case BTRFS_IOC_CLONE: - return btrfs_ioctl_clone(file, arg, 0, 0, 0); - case BTRFS_IOC_CLONE_RANGE: - return btrfs_ioctl_clone_range(file, argp); case BTRFS_IOC_TRANS_START: return btrfs_ioctl_trans_start(file); case BTRFS_IOC_TRANS_END: @@ -5566,8 +5454,6 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_get_fslabel(file, argp); case BTRFS_IOC_SET_FSLABEL: return btrfs_ioctl_set_fslabel(file, argp); - case BTRFS_IOC_FILE_EXTENT_SAME: - return btrfs_ioctl_file_extent_same(file, argp); case BTRFS_IOC_GET_SUPPORTED_FEATURES: return btrfs_ioctl_get_supported_features(file, argp); case BTRFS_IOC_GET_FEATURES: diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 46476c226395..5279fdae7142 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -993,9 +993,10 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) goto out; - spin_lock(&fs_info->qgroup_lock); fs_info->quota_enabled = 0; fs_info->pending_quota_state = 0; + btrfs_qgroup_wait_for_completion(fs_info); + spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; fs_info->quota_root = NULL; fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON; @@ -1461,6 +1462,8 @@ struct btrfs_qgroup_extent_record struct btrfs_qgroup_extent_record *entry; u64 bytenr = record->bytenr; + assert_spin_locked(&delayed_refs->lock); + while (*p) { parent_node = *p; entry = rb_entry(parent_node, struct btrfs_qgroup_extent_record, @@ -2198,7 +2201,6 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path, int slot; int ret; - path->leave_spinning = 1; mutex_lock(&fs_info->qgroup_rescan_lock); ret = btrfs_search_slot_for_read(fs_info->extent_root, &fs_info->qgroup_rescan_progress, @@ -2286,7 +2288,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) goto out; err = 0; - while (!err) { + while (!err && !btrfs_fs_closing(fs_info)) { trans = btrfs_start_transaction(fs_info->fs_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -2307,7 +2309,8 @@ out: btrfs_free_path(path); mutex_lock(&fs_info->qgroup_rescan_lock); - fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; + if (!btrfs_fs_closing(fs_info)) + fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; if (err > 0 && fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) { @@ -2336,7 +2339,9 @@ out: } btrfs_end_transaction(trans, fs_info->quota_root); - if (err >= 0) { + if (btrfs_fs_closing(fs_info)) { + btrfs_info(fs_info, "qgroup scan paused"); + } else if (err >= 0) { btrfs_info(fs_info, "qgroup scan completed%s", err > 0 ? " (inconsistency flag cleared)" : ""); } else { @@ -2384,12 +2389,11 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, memset(&fs_info->qgroup_rescan_progress, 0, sizeof(fs_info->qgroup_rescan_progress)); fs_info->qgroup_rescan_progress.objectid = progress_objectid; + init_completion(&fs_info->qgroup_rescan_completion); spin_unlock(&fs_info->qgroup_lock); mutex_unlock(&fs_info->qgroup_rescan_lock); - init_completion(&fs_info->qgroup_rescan_completion); - memset(&fs_info->qgroup_rescan_work, 0, sizeof(fs_info->qgroup_rescan_work)); btrfs_init_work(&fs_info->qgroup_rescan_work, diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 550de89a8661..b091d94ceef6 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -248,14 +248,9 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check); static int scrub_setup_recheck_block(struct scrub_block *original_sblock, struct scrub_block *sblocks_for_recheck); static void scrub_recheck_block(struct btrfs_fs_info *fs_info, - struct scrub_block *sblock, int is_metadata, - int have_csum, u8 *csum, u64 generation, - u16 csum_size, int retry_failed_mirror); -static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info, - struct scrub_block *sblock, - int is_metadata, int have_csum, - const u8 *csum, u64 generation, - u16 csum_size); + struct scrub_block *sblock, + int retry_failed_mirror); +static void scrub_recheck_block_checksum(struct scrub_block *sblock); static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad, struct scrub_block *sblock_good); static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, @@ -889,11 +884,9 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) struct btrfs_fs_info *fs_info; u64 length; u64 logical; - u64 generation; unsigned int failed_mirror_index; unsigned int is_metadata; unsigned int have_csum; - u8 *csum; struct scrub_block *sblocks_for_recheck; /* holds one for each mirror */ struct scrub_block *sblock_bad; int ret; @@ -918,13 +911,11 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) } length = sblock_to_check->page_count * PAGE_SIZE; logical = sblock_to_check->pagev[0]->logical; - generation = sblock_to_check->pagev[0]->generation; BUG_ON(sblock_to_check->pagev[0]->mirror_num < 1); failed_mirror_index = sblock_to_check->pagev[0]->mirror_num - 1; is_metadata = !(sblock_to_check->pagev[0]->flags & BTRFS_EXTENT_FLAG_DATA); have_csum = sblock_to_check->pagev[0]->have_csum; - csum = sblock_to_check->pagev[0]->csum; dev = sblock_to_check->pagev[0]->dev; if (sctx->is_dev_replace && !is_metadata && !have_csum) { @@ -987,8 +978,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) sblock_bad = sblocks_for_recheck + failed_mirror_index; /* build and submit the bios for the failed mirror, check checksums */ - scrub_recheck_block(fs_info, sblock_bad, is_metadata, have_csum, - csum, generation, sctx->csum_size, 1); + scrub_recheck_block(fs_info, sblock_bad, 1); if (!sblock_bad->header_error && !sblock_bad->checksum_error && sblock_bad->no_io_error_seen) { @@ -1101,9 +1091,7 @@ nodatasum_case: sblock_other = sblocks_for_recheck + mirror_index; /* build and submit the bios, check checksums */ - scrub_recheck_block(fs_info, sblock_other, is_metadata, - have_csum, csum, generation, - sctx->csum_size, 0); + scrub_recheck_block(fs_info, sblock_other, 0); if (!sblock_other->header_error && !sblock_other->checksum_error && @@ -1215,9 +1203,7 @@ nodatasum_case: * is verified, but most likely the data comes out * of the page cache. */ - scrub_recheck_block(fs_info, sblock_bad, - is_metadata, have_csum, csum, - generation, sctx->csum_size, 1); + scrub_recheck_block(fs_info, sblock_bad, 1); if (!sblock_bad->header_error && !sblock_bad->checksum_error && sblock_bad->no_io_error_seen) @@ -1318,6 +1304,9 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock, struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info; u64 length = original_sblock->page_count * PAGE_SIZE; u64 logical = original_sblock->pagev[0]->logical; + u64 generation = original_sblock->pagev[0]->generation; + u64 flags = original_sblock->pagev[0]->flags; + u64 have_csum = original_sblock->pagev[0]->have_csum; struct scrub_recover *recover; struct btrfs_bio *bbio; u64 sublen; @@ -1372,6 +1361,7 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock, sblock = sblocks_for_recheck + mirror_index; sblock->sctx = sctx; + page = kzalloc(sizeof(*page), GFP_NOFS); if (!page) { leave_nomem: @@ -1383,7 +1373,15 @@ leave_nomem: } scrub_page_get(page); sblock->pagev[page_index] = page; + page->sblock = sblock; + page->flags = flags; + page->generation = generation; page->logical = logical; + page->have_csum = have_csum; + if (have_csum) + memcpy(page->csum, + original_sblock->pagev[0]->csum, + sctx->csum_size); scrub_stripe_index_and_offset(logical, bbio->map_type, @@ -1474,15 +1472,12 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info, * the pages that are errored in the just handled mirror can be repaired. */ static void scrub_recheck_block(struct btrfs_fs_info *fs_info, - struct scrub_block *sblock, int is_metadata, - int have_csum, u8 *csum, u64 generation, - u16 csum_size, int retry_failed_mirror) + struct scrub_block *sblock, + int retry_failed_mirror) { int page_num; sblock->no_io_error_seen = 1; - sblock->header_error = 0; - sblock->checksum_error = 0; for (page_num = 0; page_num < sblock->page_count; page_num++) { struct bio *bio; @@ -1518,9 +1513,7 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info, } if (sblock->no_io_error_seen) - scrub_recheck_block_checksum(fs_info, sblock, is_metadata, - have_csum, csum, generation, - csum_size); + scrub_recheck_block_checksum(sblock); return; } @@ -1535,61 +1528,16 @@ static inline int scrub_check_fsid(u8 fsid[], return !ret; } -static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info, - struct scrub_block *sblock, - int is_metadata, int have_csum, - const u8 *csum, u64 generation, - u16 csum_size) +static void scrub_recheck_block_checksum(struct scrub_block *sblock) { - int page_num; - u8 calculated_csum[BTRFS_CSUM_SIZE]; - u32 crc = ~(u32)0; - void *mapped_buffer; - - WARN_ON(!sblock->pagev[0]->page); - if (is_metadata) { - struct btrfs_header *h; - - mapped_buffer = kmap_atomic(sblock->pagev[0]->page); - h = (struct btrfs_header *)mapped_buffer; - - if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h) || - !scrub_check_fsid(h->fsid, sblock->pagev[0]) || - memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid, - BTRFS_UUID_SIZE)) { - sblock->header_error = 1; - } else if (generation != btrfs_stack_header_generation(h)) { - sblock->header_error = 1; - sblock->generation_error = 1; - } - csum = h->csum; - } else { - if (!have_csum) - return; - - mapped_buffer = kmap_atomic(sblock->pagev[0]->page); - } - - for (page_num = 0;;) { - if (page_num == 0 && is_metadata) - crc = btrfs_csum_data( - ((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE, - crc, PAGE_SIZE - BTRFS_CSUM_SIZE); - else - crc = btrfs_csum_data(mapped_buffer, crc, PAGE_SIZE); - - kunmap_atomic(mapped_buffer); - page_num++; - if (page_num >= sblock->page_count) - break; - WARN_ON(!sblock->pagev[page_num]->page); - - mapped_buffer = kmap_atomic(sblock->pagev[page_num]->page); - } + sblock->header_error = 0; + sblock->checksum_error = 0; + sblock->generation_error = 0; - btrfs_csum_final(crc, calculated_csum); - if (memcmp(calculated_csum, csum, csum_size)) - sblock->checksum_error = 1; + if (sblock->pagev[0]->flags & BTRFS_EXTENT_FLAG_DATA) + scrub_checksum_data(sblock); + else + scrub_checksum_tree_block(sblock); } static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad, @@ -1833,6 +1781,18 @@ static int scrub_checksum(struct scrub_block *sblock) u64 flags; int ret; + /* + * No need to initialize these stats currently, + * because this function only use return value + * instead of these stats value. + * + * Todo: + * always use stats + */ + sblock->header_error = 0; + sblock->generation_error = 0; + sblock->checksum_error = 0; + WARN_ON(sblock->page_count < 1); flags = sblock->pagev[0]->flags; ret = 0; @@ -1858,7 +1818,6 @@ static int scrub_checksum_data(struct scrub_block *sblock) struct page *page; void *buffer; u32 crc = ~(u32)0; - int fail = 0; u64 len; int index; @@ -1889,9 +1848,9 @@ static int scrub_checksum_data(struct scrub_block *sblock) btrfs_csum_final(crc, csum); if (memcmp(csum, on_disk_csum, sctx->csum_size)) - fail = 1; + sblock->checksum_error = 1; - return fail; + return sblock->checksum_error; } static int scrub_checksum_tree_block(struct scrub_block *sblock) @@ -1907,8 +1866,6 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) u64 mapped_size; void *p; u32 crc = ~(u32)0; - int fail = 0; - int crc_fail = 0; u64 len; int index; @@ -1923,19 +1880,20 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) * a) don't have an extent buffer and * b) the page is already kmapped */ - if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h)) - ++fail; + sblock->header_error = 1; - if (sblock->pagev[0]->generation != btrfs_stack_header_generation(h)) - ++fail; + if (sblock->pagev[0]->generation != btrfs_stack_header_generation(h)) { + sblock->header_error = 1; + sblock->generation_error = 1; + } if (!scrub_check_fsid(h->fsid, sblock->pagev[0])) - ++fail; + sblock->header_error = 1; if (memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid, BTRFS_UUID_SIZE)) - ++fail; + sblock->header_error = 1; len = sctx->nodesize - BTRFS_CSUM_SIZE; mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE; @@ -1960,9 +1918,9 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) btrfs_csum_final(crc, calculated_csum); if (memcmp(calculated_csum, on_disk_csum, sctx->csum_size)) - ++crc_fail; + sblock->checksum_error = 1; - return fail || crc_fail; + return sblock->header_error || sblock->checksum_error; } static int scrub_checksum_super(struct scrub_block *sblock) @@ -2176,39 +2134,27 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work) { struct scrub_block *sblock = container_of(work, struct scrub_block, work); struct scrub_ctx *sctx = sblock->sctx; - struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info; - unsigned int is_metadata; - unsigned int have_csum; - u8 *csum; - u64 generation; u64 logical; struct btrfs_device *dev; - is_metadata = !(sblock->pagev[0]->flags & BTRFS_EXTENT_FLAG_DATA); - have_csum = sblock->pagev[0]->have_csum; - csum = sblock->pagev[0]->csum; - generation = sblock->pagev[0]->generation; logical = sblock->pagev[0]->logical; dev = sblock->pagev[0]->dev; - if (sblock->no_io_error_seen) { - scrub_recheck_block_checksum(fs_info, sblock, is_metadata, - have_csum, csum, generation, - sctx->csum_size); - } + if (sblock->no_io_error_seen) + scrub_recheck_block_checksum(sblock); if (!sblock->no_io_error_seen) { spin_lock(&sctx->stat_lock); sctx->stat.read_errors++; spin_unlock(&sctx->stat_lock); - btrfs_err_rl_in_rcu(fs_info, + btrfs_err_rl_in_rcu(sctx->dev_root->fs_info, "IO error rebuilding logical %llu for dev %s", logical, rcu_str_deref(dev->name)); } else if (sblock->header_error || sblock->checksum_error) { spin_lock(&sctx->stat_lock); sctx->stat.uncorrectable_errors++; spin_unlock(&sctx->stat_lock); - btrfs_err_rl_in_rcu(fs_info, + btrfs_err_rl_in_rcu(sctx->dev_root->fs_info, "failed to rebuild valid logical %llu for dev %s", logical, rcu_str_deref(dev->name)); } else { @@ -2500,8 +2446,7 @@ static void scrub_block_complete(struct scrub_block *sblock) } } -static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u64 len, - u8 *csum) +static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u8 *csum) { struct btrfs_ordered_sum *sum = NULL; unsigned long index; @@ -2565,7 +2510,7 @@ static int scrub_extent(struct scrub_ctx *sctx, u64 logical, u64 len, if (flags & BTRFS_EXTENT_FLAG_DATA) { /* push csums to sbio */ - have_csum = scrub_find_csum(sctx, logical, l, csum); + have_csum = scrub_find_csum(sctx, logical, csum); if (have_csum == 0) ++sctx->stat.no_csum; if (sctx->is_dev_replace && !have_csum) { @@ -2703,7 +2648,7 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity, if (flags & BTRFS_EXTENT_FLAG_DATA) { /* push csums to sbio */ - have_csum = scrub_find_csum(sctx, logical, l, csum); + have_csum = scrub_find_csum(sctx, logical, csum); if (have_csum == 0) goto skip; } @@ -3012,6 +2957,9 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx, logic_start + map->stripe_len)) { btrfs_err(fs_info, "scrub: tree block %llu spanning stripes, ignored. logical=%llu", key.objectid, logic_start); + spin_lock(&sctx->stat_lock); + sctx->stat.uncorrectable_errors++; + spin_unlock(&sctx->stat_lock); goto next; } again: @@ -3361,6 +3309,9 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, "scrub: tree block %llu spanning " "stripes, ignored. logical=%llu", key.objectid, logical); + spin_lock(&sctx->stat_lock); + sctx->stat.uncorrectable_errors++; + spin_unlock(&sctx->stat_lock); goto next; } @@ -3481,7 +3432,9 @@ out: static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx, struct btrfs_device *scrub_dev, u64 chunk_offset, u64 length, - u64 dev_offset, int is_dev_replace) + u64 dev_offset, + struct btrfs_block_group_cache *cache, + int is_dev_replace) { struct btrfs_mapping_tree *map_tree = &sctx->dev_root->fs_info->mapping_tree; @@ -3494,8 +3447,18 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx, em = lookup_extent_mapping(&map_tree->map_tree, chunk_offset, 1); read_unlock(&map_tree->map_tree.lock); - if (!em) - return -EINVAL; + if (!em) { + /* + * Might have been an unused block group deleted by the cleaner + * kthread or relocation. + */ + spin_lock(&cache->lock); + if (!cache->removed) + ret = -EINVAL; + spin_unlock(&cache->lock); + + return ret; + } map = (struct map_lookup *)em->bdev; if (em->start != chunk_offset) @@ -3532,6 +3495,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, u64 length; u64 chunk_offset; int ret = 0; + int ro_set; int slot; struct extent_buffer *l; struct btrfs_key key; @@ -3617,7 +3581,21 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, scrub_pause_on(fs_info); ret = btrfs_inc_block_group_ro(root, cache); scrub_pause_off(fs_info); - if (ret) { + + if (ret == 0) { + ro_set = 1; + } else if (ret == -ENOSPC) { + /* + * btrfs_inc_block_group_ro return -ENOSPC when it + * failed in creating new chunk for metadata. + * It is not a problem for scrub/replace, because + * metadata are always cowed, and our scrub paused + * commit_transactions. + */ + ro_set = 0; + } else { + btrfs_warn(fs_info, "failed setting block group ro, ret=%d\n", + ret); btrfs_put_block_group(cache); break; } @@ -3626,7 +3604,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, dev_replace->cursor_left = found_key.offset; dev_replace->item_needs_writeback = 1; ret = scrub_chunk(sctx, scrub_dev, chunk_offset, length, - found_key.offset, is_dev_replace); + found_key.offset, cache, is_dev_replace); /* * flush, submit all pending read and write bios, afterwards @@ -3660,7 +3638,30 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, scrub_pause_off(fs_info); - btrfs_dec_block_group_ro(root, cache); + if (ro_set) + btrfs_dec_block_group_ro(root, cache); + + /* + * We might have prevented the cleaner kthread from deleting + * this block group if it was already unused because we raced + * and set it to RO mode first. So add it back to the unused + * list, otherwise it might not ever be deleted unless a manual + * balance is triggered or it becomes used and unused again. + */ + spin_lock(&cache->lock); + if (!cache->removed && !cache->ro && cache->reserved == 0 && + btrfs_block_group_used(&cache->item) == 0) { + spin_unlock(&cache->lock); + spin_lock(&fs_info->unused_bgs_lock); + if (list_empty(&cache->bg_list)) { + btrfs_get_block_group(cache); + list_add_tail(&cache->bg_list, + &fs_info->unused_bgs); + } + spin_unlock(&fs_info->unused_bgs_lock); + } else { + spin_unlock(&cache->lock); + } btrfs_put_block_group(cache); if (ret) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 24154e422945..a0434c179ea9 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1514,9 +1514,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, if ((flags ^ s->s_flags) & MS_RDONLY) error = -EBUSY; } else { - char b[BDEVNAME_SIZE]; - - strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); + snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); btrfs_sb(s)->bdev_holder = fs_type; error = btrfs_fill_super(s, fs_devices, data, flags & MS_SILENT ? 1 : 0); diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c index c8c3d70c31ff..8b72b005bfb9 100644 --- a/fs/btrfs/tests/free-space-tests.c +++ b/fs/btrfs/tests/free-space-tests.c @@ -898,8 +898,10 @@ int btrfs_test_free_space_cache(void) } root = btrfs_alloc_dummy_root(); - if (!root) + if (IS_ERR(root)) { + ret = PTR_ERR(root); goto out; + } root->fs_info = btrfs_alloc_dummy_fs_info(); if (!root->fs_info) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 418c6a2ad7d8..be8eae80ff65 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -274,7 +274,6 @@ loop: cur_trans->num_dirty_bgs = 0; spin_lock_init(&cur_trans->dirty_bgs_lock); INIT_LIST_HEAD(&cur_trans->deleted_bgs); - spin_lock_init(&cur_trans->deleted_bgs_lock); spin_lock_init(&cur_trans->dropped_roots_lock); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(&cur_trans->dirty_pages, @@ -592,6 +591,38 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root, return start_transaction(root, num_items, TRANS_START, BTRFS_RESERVE_FLUSH_ALL); } +struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv( + struct btrfs_root *root, + unsigned int num_items, + int min_factor) +{ + struct btrfs_trans_handle *trans; + u64 num_bytes; + int ret; + + trans = btrfs_start_transaction(root, num_items); + if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC) + return trans; + + trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) + return trans; + + num_bytes = btrfs_calc_trans_metadata_size(root, num_items); + ret = btrfs_cond_migrate_bytes(root->fs_info, + &root->fs_info->trans_block_rsv, + num_bytes, + min_factor); + if (ret) { + btrfs_end_transaction(trans, root); + return ERR_PTR(ret); + } + + trans->block_rsv = &root->fs_info->trans_block_rsv; + trans->bytes_reserved = num_bytes; + + return trans; +} struct btrfs_trans_handle *btrfs_start_transaction_lflush( struct btrfs_root *root, diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index b05b2f64d913..64c8221b6165 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -77,8 +77,8 @@ struct btrfs_transaction { */ struct mutex cache_write_mutex; spinlock_t dirty_bgs_lock; + /* Protected by spin lock fs_info->unused_bgs_lock. */ struct list_head deleted_bgs; - spinlock_t deleted_bgs_lock; spinlock_t dropped_roots_lock; struct btrfs_delayed_ref_root delayed_refs; int aborted; @@ -185,6 +185,10 @@ int btrfs_end_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root); struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root, unsigned int num_items); +struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv( + struct btrfs_root *root, + unsigned int num_items, + int min_factor); struct btrfs_trans_handle *btrfs_start_transaction_lflush( struct btrfs_root *root, unsigned int num_items); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 17ed76d18eb6..a23399e8e3ab 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -232,8 +232,8 @@ static struct btrfs_device *__alloc_device(void) spin_lock_init(&dev->reada_lock); atomic_set(&dev->reada_in_flight, 0); atomic_set(&dev->dev_stats_ccnt, 0); - INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT); - INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); + INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); return dev; } @@ -1973,8 +1973,7 @@ void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info, if (srcdev->writeable) { fs_devices->rw_devices--; /* zero out the old super if it is writable */ - btrfs_scratch_superblocks(srcdev->bdev, - rcu_str_deref(srcdev->name)); + btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str); } if (srcdev->bdev) @@ -2024,8 +2023,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, btrfs_sysfs_rm_device_link(fs_info->fs_devices, tgtdev); if (tgtdev->bdev) { - btrfs_scratch_superblocks(tgtdev->bdev, - rcu_str_deref(tgtdev->name)); + btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str); fs_info->fs_devices->open_devices--; } fs_info->fs_devices->num_devices--; @@ -2853,7 +2851,8 @@ static int btrfs_relocate_chunk(struct btrfs_root *root, u64 chunk_offset) if (ret) return ret; - trans = btrfs_start_transaction(root, 0); + trans = btrfs_start_trans_remove_block_group(root->fs_info, + chunk_offset); if (IS_ERR(trans)) { ret = PTR_ERR(trans); btrfs_std_error(root->fs_info, ret, NULL); @@ -3123,7 +3122,7 @@ static int chunk_profiles_filter(u64 chunk_type, return 1; } -static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset, +static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset, struct btrfs_balance_args *bargs) { struct btrfs_block_group_cache *cache; @@ -3156,7 +3155,7 @@ static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset, return ret; } -static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, +static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset, struct btrfs_balance_args *bargs) { struct btrfs_block_group_cache *cache; @@ -3400,6 +3399,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) u32 count_data = 0; u32 count_meta = 0; u32 count_sys = 0; + int chunk_reserved = 0; /* step one make some room on all the devices */ devices = &fs_info->fs_devices->devices; @@ -3501,6 +3501,7 @@ again: ret = should_balance_chunk(chunk_root, leaf, chunk, found_key.offset); + btrfs_release_path(path); if (!ret) { mutex_unlock(&fs_info->delete_unused_bgs_mutex); @@ -3537,6 +3538,24 @@ again: goto loop; } + if ((chunk_type & BTRFS_BLOCK_GROUP_DATA) && !chunk_reserved) { + trans = btrfs_start_transaction(chunk_root, 0); + if (IS_ERR(trans)) { + mutex_unlock(&fs_info->delete_unused_bgs_mutex); + ret = PTR_ERR(trans); + goto error; + } + + ret = btrfs_force_chunk_alloc(trans, chunk_root, + BTRFS_BLOCK_GROUP_DATA); + btrfs_end_transaction(trans, chunk_root); + if (ret < 0) { + mutex_unlock(&fs_info->delete_unused_bgs_mutex); + goto error; + } + chunk_reserved = 1; + } + ret = btrfs_relocate_chunk(chunk_root, found_key.offset); mutex_unlock(&fs_info->delete_unused_bgs_mutex); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index ec5712372732..d5c84f6b1353 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -382,7 +382,7 @@ struct map_lookup { #define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5) #define BTRFS_BALANCE_ARGS_LIMIT_RANGE (1ULL << 6) #define BTRFS_BALANCE_ARGS_STRIPES_RANGE (1ULL << 7) -#define BTRFS_BALANCE_ARGS_USAGE_RANGE (1ULL << 8) +#define BTRFS_BALANCE_ARGS_USAGE_RANGE (1ULL << 10) #define BTRFS_BALANCE_ARGS_MASK \ (BTRFS_BALANCE_ARGS_PROFILES | \ diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 6f518c90e1c1..7cbef1a14fe1 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -313,8 +313,10 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) /* check to make sure this item is what we want */ if (found_key.objectid != key.objectid) break; - if (found_key.type != BTRFS_XATTR_ITEM_KEY) + if (found_key.type > BTRFS_XATTR_ITEM_KEY) break; + if (found_key.type < BTRFS_XATTR_ITEM_KEY) + goto next; di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item); if (verify_dir_item(root, leaf, di)) @@ -349,137 +351,89 @@ err: return ret; } -/* - * List of handlers for synthetic system.* attributes. All real ondisk - * attributes are handled directly. - */ -const struct xattr_handler *btrfs_xattr_handlers[] = { -#ifdef CONFIG_BTRFS_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif - NULL, -}; - -/* - * Check if the attribute is in a supported namespace. - * - * This is applied after the check for the synthetic attributes in the system - * namespace. - */ -static int btrfs_is_valid_xattr(const char *name) +static int btrfs_xattr_handler_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - int len = strlen(name); - int prefixlen = 0; - - if (!strncmp(name, XATTR_SECURITY_PREFIX, - XATTR_SECURITY_PREFIX_LEN)) - prefixlen = XATTR_SECURITY_PREFIX_LEN; - else if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - prefixlen = XATTR_SYSTEM_PREFIX_LEN; - else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) - prefixlen = XATTR_TRUSTED_PREFIX_LEN; - else if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) - prefixlen = XATTR_USER_PREFIX_LEN; - else if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) - prefixlen = XATTR_BTRFS_PREFIX_LEN; - else - return -EOPNOTSUPP; - - /* - * The name cannot consist of just prefix - */ - if (len <= prefixlen) - return -EINVAL; + struct inode *inode = d_inode(dentry); - return 0; + name = xattr_full_name(handler, name); + return __btrfs_getxattr(inode, name, buffer, size); } -ssize_t btrfs_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size) +static int btrfs_xattr_handler_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *buffer, size_t size, + int flags) { - int ret; + struct inode *inode = d_inode(dentry); - /* - * If this is a request for a synthetic attribute in the system.* - * namespace use the generic infrastructure to resolve a handler - * for it via sb->s_xattr. - */ - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_getxattr(dentry, name, buffer, size); + name = xattr_full_name(handler, name); + return __btrfs_setxattr(NULL, inode, name, buffer, size, flags); +} - ret = btrfs_is_valid_xattr(name); - if (ret) - return ret; - return __btrfs_getxattr(d_inode(dentry), name, buffer, size); +static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, + struct dentry *dentry, + const char *name, const void *value, + size_t size, int flags) +{ + name = xattr_full_name(handler, name); + return btrfs_set_prop(d_inode(dentry), name, value, size, flags); } +static const struct xattr_handler btrfs_security_xattr_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .get = btrfs_xattr_handler_get, + .set = btrfs_xattr_handler_set, +}; + +static const struct xattr_handler btrfs_trusted_xattr_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .get = btrfs_xattr_handler_get, + .set = btrfs_xattr_handler_set, +}; + +static const struct xattr_handler btrfs_user_xattr_handler = { + .prefix = XATTR_USER_PREFIX, + .get = btrfs_xattr_handler_get, + .set = btrfs_xattr_handler_set, +}; + +static const struct xattr_handler btrfs_btrfs_xattr_handler = { + .prefix = XATTR_BTRFS_PREFIX, + .get = btrfs_xattr_handler_get, + .set = btrfs_xattr_handler_set_prop, +}; + +const struct xattr_handler *btrfs_xattr_handlers[] = { + &btrfs_security_xattr_handler, +#ifdef CONFIG_BTRFS_FS_POSIX_ACL + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, +#endif + &btrfs_trusted_xattr_handler, + &btrfs_user_xattr_handler, + &btrfs_btrfs_xattr_handler, + NULL, +}; + int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root; - int ret; - /* - * The permission on security.* and system.* is not checked - * in permission(). - */ if (btrfs_root_readonly(root)) return -EROFS; - - /* - * If this is a request for a synthetic attribute in the system.* - * namespace use the generic infrastructure to resolve a handler - * for it via sb->s_xattr. - */ - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_setxattr(dentry, name, value, size, flags); - - ret = btrfs_is_valid_xattr(name); - if (ret) - return ret; - - if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) - return btrfs_set_prop(d_inode(dentry), name, - value, size, flags); - - if (size == 0) - value = ""; /* empty EA, do not remove */ - - return __btrfs_setxattr(NULL, d_inode(dentry), name, value, size, - flags); + return generic_setxattr(dentry, name, value, size, flags); } int btrfs_removexattr(struct dentry *dentry, const char *name) { struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root; - int ret; - /* - * The permission on security.* and system.* is not checked - * in permission(). - */ if (btrfs_root_readonly(root)) return -EROFS; - - /* - * If this is a request for a synthetic attribute in the system.* - * namespace use the generic infrastructure to resolve a handler - * for it via sb->s_xattr. - */ - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_removexattr(dentry, name); - - ret = btrfs_is_valid_xattr(name); - if (ret) - return ret; - - if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) - return btrfs_set_prop(d_inode(dentry), name, - NULL, 0, XATTR_REPLACE); - - return __btrfs_setxattr(NULL, d_inode(dentry), name, NULL, 0, - XATTR_REPLACE); + return generic_removexattr(dentry, name); } static int btrfs_initxattrs(struct inode *inode, diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h index 5049608d1388..96807b3d22f5 100644 --- a/fs/btrfs/xattr.h +++ b/fs/btrfs/xattr.h @@ -28,8 +28,6 @@ extern ssize_t __btrfs_getxattr(struct inode *inode, const char *name, extern int __btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, const char *name, const void *value, size_t size, int flags); -extern ssize_t btrfs_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size); extern int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); extern int btrfs_removexattr(struct dentry *dentry, const char *name); diff --git a/fs/buffer.c b/fs/buffer.c index 82283abb2795..e1632abb4ca9 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -134,13 +134,10 @@ __clear_page_buffers(struct page *page) static void buffer_io_error(struct buffer_head *bh, char *msg) { - char b[BDEVNAME_SIZE]; - if (!test_bit(BH_Quiet, &bh->b_state)) printk_ratelimited(KERN_ERR - "Buffer I/O error on dev %s, logical block %llu%s\n", - bdevname(bh->b_bdev, b), - (unsigned long long)bh->b_blocknr, msg); + "Buffer I/O error on dev %pg, logical block %llu%s\n", + bh->b_bdev, (unsigned long long)bh->b_blocknr, msg); } /* @@ -237,15 +234,13 @@ __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 %s blocksize: %d\n", bdevname(bdev, b), + printk("device %pg blocksize: %d\n", bdev, 1 << bd_inode->i_blkbits); } out_unlock: @@ -531,10 +526,8 @@ repeat: static void do_thaw_one(struct super_block *sb, void *unused) { - char b[BDEVNAME_SIZE]; while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb)) - printk(KERN_WARNING "Emergency Thaw on %s\n", - bdevname(sb->s_bdev, b)); + printk(KERN_WARNING "Emergency Thaw on %pg\n", sb->s_bdev); } static void do_thaw_all(struct work_struct *work) @@ -999,7 +992,7 @@ grow_dev_page(struct block_device *bdev, sector_t block, int ret = 0; /* Will call free_more_memory() */ gfp_t gfp_mask; - gfp_mask = (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS) | gfp; + gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp; /* * XXX: __getblk_slow() can not really deal with failure and @@ -1074,12 +1067,10 @@ grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp) * pagecache index. (this comparison is done using sector_t types). */ if (unlikely(index != block >> sizebits)) { - char b[BDEVNAME_SIZE]; - printk(KERN_ERR "%s: requested out-of-range block %llu for " - "device %s\n", + "device %pg\n", __func__, (unsigned long long)block, - bdevname(bdev, b)); + bdev); return -EIO; } @@ -2420,9 +2411,9 @@ EXPORT_SYMBOL(block_commit_write); * unlock the page. * * Direct callers of this function should protect against filesystem freezing - * using sb_start_write() - sb_end_write() functions. + * using sb_start_pagefault() - sb_end_pagefault() functions. */ -int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, +int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block) { struct page *page = vmf->page; @@ -2459,26 +2450,6 @@ out_unlock: unlock_page(page); return ret; } -EXPORT_SYMBOL(__block_page_mkwrite); - -int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, - get_block_t get_block) -{ - int ret; - struct super_block *sb = file_inode(vma->vm_file)->i_sb; - - sb_start_pagefault(sb); - - /* - * Update file times before taking page lock. We may end up failing the - * fault so this update may be superfluous but who really cares... - */ - file_update_time(vma->vm_file); - - ret = __block_page_mkwrite(vma, vmf, get_block); - sb_end_pagefault(sb); - return block_page_mkwrite_return(ret); -} EXPORT_SYMBOL(block_page_mkwrite); /* diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index f601def05bdf..452e98dd7560 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -226,15 +226,9 @@ static ssize_t cachefiles_daemon_write(struct file *file, return -EOPNOTSUPP; /* drag the command string into the kernel so we can parse it */ - data = kmalloc(datalen + 1, GFP_KERNEL); - if (!data) - return -ENOMEM; - - ret = -EFAULT; - if (copy_from_user(data, _data, datalen) != 0) - goto error; - - data[datalen] = '\0'; + data = memdup_user_nul(_data, datalen); + if (IS_ERR(data)) + return PTR_ERR(data); ret = -EINVAL; if (memchr(data, '\0', datalen)) diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index aecd0859eacb..9c4b737a54df 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -30,7 +30,7 @@ extern unsigned cachefiles_debug; #define CACHEFILES_DEBUG_KLEAVE 2 #define CACHEFILES_DEBUG_KDEBUG 4 -#define cachefiles_gfp (__GFP_WAIT | __GFP_NORETRY | __GFP_NOMEMALLOC) +#define cachefiles_gfp (__GFP_RECLAIM | __GFP_NORETRY | __GFP_NOMEMALLOC) /* * node records diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index fc1056f5c96a..c4b893453e0e 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -655,6 +655,8 @@ lookup_again: aops = d_backing_inode(object->dentry)->i_mapping->a_ops; if (!aops->bmap) goto check_error; + if (object->dentry->d_sb->s_blocksize > PAGE_SIZE) + goto check_error; object->backer = object->dentry; } else { diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 3cbb0e834694..c0f3da3926a0 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -414,9 +414,6 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, ASSERT(inode->i_mapping->a_ops->readpages); /* calculate the shift required to use bmap */ - if (inode->i_sb->s_blocksize > PAGE_SIZE) - goto enobufs; - shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; op->op.flags &= FSCACHE_OP_KEEP_FLAGS; @@ -711,9 +708,6 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op, ASSERT(inode->i_mapping->a_ops->readpages); /* calculate the shift required to use bmap */ - if (inode->i_sb->s_blocksize > PAGE_SIZE) - goto all_enobufs; - shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; pagevec_init(&pagevec, 0); @@ -885,7 +879,7 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) loff_t pos, eof; size_t len; void *data; - int ret; + int ret = -ENOBUFS; ASSERT(op != NULL); ASSERT(page != NULL); @@ -905,6 +899,15 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) cache = container_of(object->fscache.cache, struct cachefiles_cache, cache); + pos = (loff_t)page->index << PAGE_SHIFT; + + /* We mustn't write more data than we have, so we have to beware of a + * partial page at EOF. + */ + eof = object->fscache.store_limit_l; + if (pos >= eof) + goto error; + /* write the page to the backing filesystem and let it store it in its * own time */ path.mnt = cache->mnt; @@ -912,40 +915,38 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) file = dentry_open(&path, O_RDWR | O_LARGEFILE, cache->cache_cred); if (IS_ERR(file)) { ret = PTR_ERR(file); - } else { - pos = (loff_t) page->index << PAGE_SHIFT; - - /* we mustn't write more data than we have, so we have - * to beware of a partial page at EOF */ - eof = object->fscache.store_limit_l; - len = PAGE_SIZE; - if (eof & ~PAGE_MASK) { - ASSERTCMP(pos, <, eof); - if (eof - pos < PAGE_SIZE) { - _debug("cut short %llx to %llx", - pos, eof); - len = eof - pos; - ASSERTCMP(pos + len, ==, eof); - } - } - - data = kmap(page); - ret = __kernel_write(file, data, len, &pos); - kunmap(page); - if (ret != len) - ret = -EIO; - fput(file); + goto error_2; } - if (ret < 0) { - if (ret == -EIO) - cachefiles_io_error_obj( - object, "Write page to backing file failed"); - ret = -ENOBUFS; + len = PAGE_SIZE; + if (eof & ~PAGE_MASK) { + if (eof - pos < PAGE_SIZE) { + _debug("cut short %llx to %llx", + pos, eof); + len = eof - pos; + ASSERTCMP(pos + len, ==, eof); + } } - _leave(" = %d", ret); - return ret; + data = kmap(page); + ret = __kernel_write(file, data, len, &pos); + kunmap(page); + fput(file); + if (ret != len) + goto error_eio; + + _leave(" = 0"); + return 0; + +error_eio: + ret = -EIO; +error_2: + if (ret == -EIO) + cachefiles_io_error_obj(object, + "Write page to backing file failed"); +error: + _leave(" = -ENOBUFS [%d]", ret); + return -ENOBUFS; } /* diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 8f84646f10e9..f19708487e2f 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -49,10 +49,10 @@ struct posix_acl *ceph_get_acl(struct inode *inode, int type) switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: BUG(); @@ -92,7 +92,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { ret = posix_acl_equiv_mode(acl, &new_mode); if (ret < 0) @@ -106,7 +106,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) ret = acl ? -EINVAL : 0; goto out; } - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: ret = -EINVAL; @@ -202,11 +202,11 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode, ceph_pagelist_encode_32(pagelist, acl && default_acl ? 2 : 1); if (acl) { - size_t len = strlen(POSIX_ACL_XATTR_ACCESS); + size_t len = strlen(XATTR_NAME_POSIX_ACL_ACCESS); err = ceph_pagelist_reserve(pagelist, len + val_size1 + 8); if (err) goto out_err; - ceph_pagelist_encode_string(pagelist, POSIX_ACL_XATTR_ACCESS, + ceph_pagelist_encode_string(pagelist, XATTR_NAME_POSIX_ACL_ACCESS, len); err = posix_acl_to_xattr(&init_user_ns, acl, tmp_buf, val_size1); @@ -216,12 +216,12 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode, ceph_pagelist_append(pagelist, tmp_buf, val_size1); } if (default_acl) { - size_t len = strlen(POSIX_ACL_XATTR_DEFAULT); + size_t len = strlen(XATTR_NAME_POSIX_ACL_DEFAULT); err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8); if (err) goto out_err; err = ceph_pagelist_encode_string(pagelist, - POSIX_ACL_XATTR_DEFAULT, len); + XATTR_NAME_POSIX_ACL_DEFAULT, len); err = posix_acl_to_xattr(&init_user_ns, default_acl, tmp_buf, val_size2); if (err < 0) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 9d23e788d1df..b7d218a168fb 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1283,8 +1283,8 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) int ret1; struct address_space *mapping = inode->i_mapping; struct page *page = find_or_create_page(mapping, 0, - mapping_gfp_mask(mapping) & - ~__GFP_FS); + mapping_gfp_constraint(mapping, + ~__GFP_FS)); if (!page) { ret = VM_FAULT_OOM; goto out; @@ -1428,7 +1428,8 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page, if (i_size_read(inode) == 0) return; page = find_or_create_page(mapping, 0, - mapping_gfp_mask(mapping) & ~__GFP_FS); + mapping_gfp_constraint(mapping, + ~__GFP_FS)); if (!page) return; if (PageUptodate(page)) { diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 834f9f3723fb..a4766ded1ba7 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -88,7 +88,7 @@ static uint16_t ceph_fscache_inode_get_key(const void *cookie_netfs_data, const struct ceph_inode_info* ci = cookie_netfs_data; uint16_t klen; - /* use ceph virtual inode (id + snaphot) */ + /* use ceph virtual inode (id + snapshot) */ klen = sizeof(ci->i_vino); if (klen > maxbuf) return 0; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 27b566874bc1..c69e1253b47b 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1655,9 +1655,8 @@ retry_locked: !S_ISDIR(inode->i_mode) && /* ignore readdir cache */ ci->i_wrbuffer_ref == 0 && /* no dirty pages... */ inode->i_data.nrpages && /* have cached pages */ - (file_wanted == 0 || /* no open files */ - (revoking & (CEPH_CAP_FILE_CACHE| - CEPH_CAP_FILE_LAZYIO))) && /* or revoking cache */ + (revoking & (CEPH_CAP_FILE_CACHE| + CEPH_CAP_FILE_LAZYIO)) && /* or revoking cache */ !tried_invalidate) { dout("check_caps trying to invalidate on %p\n", inode); if (try_nonblocking_invalidate(inode) < 0) { @@ -1971,49 +1970,46 @@ out: } /* - * wait for any uncommitted directory operations to commit. + * wait for any unsafe requests to complete. */ -static int unsafe_dirop_wait(struct inode *inode) +static int unsafe_request_wait(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); - struct list_head *head = &ci->i_unsafe_dirops; - struct ceph_mds_request *req; - u64 last_tid; - int ret = 0; - - if (!S_ISDIR(inode->i_mode)) - return 0; + struct ceph_mds_request *req1 = NULL, *req2 = NULL; + int ret, err = 0; spin_lock(&ci->i_unsafe_lock); - if (list_empty(head)) - goto out; - - req = list_last_entry(head, struct ceph_mds_request, - r_unsafe_dir_item); - last_tid = req->r_tid; - - do { - ceph_mdsc_get_request(req); - spin_unlock(&ci->i_unsafe_lock); + if (S_ISDIR(inode->i_mode) && !list_empty(&ci->i_unsafe_dirops)) { + req1 = list_last_entry(&ci->i_unsafe_dirops, + struct ceph_mds_request, + r_unsafe_dir_item); + ceph_mdsc_get_request(req1); + } + if (!list_empty(&ci->i_unsafe_iops)) { + req2 = list_last_entry(&ci->i_unsafe_iops, + struct ceph_mds_request, + r_unsafe_target_item); + ceph_mdsc_get_request(req2); + } + spin_unlock(&ci->i_unsafe_lock); - dout("unsafe_dirop_wait %p wait on tid %llu (until %llu)\n", - inode, req->r_tid, last_tid); - ret = !wait_for_completion_timeout(&req->r_safe_completion, - ceph_timeout_jiffies(req->r_timeout)); + dout("unsafe_requeset_wait %p wait on tid %llu %llu\n", + inode, req1 ? req1->r_tid : 0ULL, req2 ? req2->r_tid : 0ULL); + if (req1) { + ret = !wait_for_completion_timeout(&req1->r_safe_completion, + ceph_timeout_jiffies(req1->r_timeout)); if (ret) - ret = -EIO; /* timed out */ - - ceph_mdsc_put_request(req); - - spin_lock(&ci->i_unsafe_lock); - if (ret || list_empty(head)) - break; - req = list_first_entry(head, struct ceph_mds_request, - r_unsafe_dir_item); - } while (req->r_tid < last_tid); -out: - spin_unlock(&ci->i_unsafe_lock); - return ret; + err = -EIO; + ceph_mdsc_put_request(req1); + } + if (req2) { + ret = !wait_for_completion_timeout(&req2->r_safe_completion, + ceph_timeout_jiffies(req2->r_timeout)); + if (ret) + err = -EIO; + ceph_mdsc_put_request(req2); + } + return err; } int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync) @@ -2039,7 +2035,7 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync) dirty = try_flush_caps(inode, &flush_tid); dout("fsync dirty caps are %s\n", ceph_cap_string(dirty)); - ret = unsafe_dirop_wait(inode); + ret = unsafe_request_wait(inode); /* * only wait on non-file metadata writeback (the mds diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 0c62868b5c56..3c68e6aee2f0 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -34,6 +34,74 @@ * need to wait for MDS acknowledgement. */ +/* + * Calculate the length sum of direct io vectors that can + * be combined into one page vector. + */ +static size_t dio_get_pagev_size(const struct iov_iter *it) +{ + const struct iovec *iov = it->iov; + const struct iovec *iovend = iov + it->nr_segs; + size_t size; + + size = iov->iov_len - it->iov_offset; + /* + * An iov can be page vectored when both the current tail + * and the next base are page aligned. + */ + while (PAGE_ALIGNED((iov->iov_base + iov->iov_len)) && + (++iov < iovend && PAGE_ALIGNED((iov->iov_base)))) { + size += iov->iov_len; + } + dout("dio_get_pagevlen len = %zu\n", size); + return size; +} + +/* + * Allocate a page vector based on (@it, @nbytes). + * The return value is the tuple describing a page vector, + * that is (@pages, @page_align, @num_pages). + */ +static struct page ** +dio_get_pages_alloc(const struct iov_iter *it, size_t nbytes, + size_t *page_align, int *num_pages) +{ + struct iov_iter tmp_it = *it; + size_t align; + struct page **pages; + int ret = 0, idx, npages; + + align = (unsigned long)(it->iov->iov_base + it->iov_offset) & + (PAGE_SIZE - 1); + npages = calc_pages_for(align, nbytes); + pages = kmalloc(sizeof(*pages) * npages, GFP_KERNEL); + if (!pages) { + pages = vmalloc(sizeof(*pages) * npages); + if (!pages) + return ERR_PTR(-ENOMEM); + } + + for (idx = 0; idx < npages; ) { + size_t start; + ret = iov_iter_get_pages(&tmp_it, pages + idx, nbytes, + npages - idx, &start); + if (ret < 0) + goto fail; + + iov_iter_advance(&tmp_it, ret); + nbytes -= ret; + idx += (ret + start + PAGE_SIZE - 1) / PAGE_SIZE; + } + + BUG_ON(nbytes != 0); + *num_pages = npages; + *page_align = align; + dout("dio_get_pages_alloc: got %d pages align %zu\n", npages, align); + return pages; +fail: + ceph_put_page_vector(pages, idx, false); + return ERR_PTR(ret); +} /* * Prepare an open request. Preallocate ceph_cap to avoid an @@ -458,11 +526,10 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i, size_t start; ssize_t n; - n = iov_iter_get_pages_alloc(i, &pages, INT_MAX, &start); - if (n < 0) - return n; - - num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE; + n = dio_get_pagev_size(i); + pages = dio_get_pages_alloc(i, n, &start, &num_pages); + if (IS_ERR(pages)) + return PTR_ERR(pages); ret = striped_read(inode, off, n, pages, num_pages, checkeof, @@ -592,7 +659,7 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos, CEPH_OSD_FLAG_WRITE; while (iov_iter_count(from) > 0) { - u64 len = iov_iter_single_seg_count(from); + u64 len = dio_get_pagev_size(from); size_t start; ssize_t n; @@ -611,14 +678,14 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos, osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC, 0); - n = iov_iter_get_pages_alloc(from, &pages, len, &start); - if (unlikely(n < 0)) { - ret = n; + n = len; + pages = dio_get_pages_alloc(from, len, &start, &num_pages); + if (IS_ERR(pages)) { ceph_osdc_put_request(req); + ret = PTR_ERR(pages); break; } - num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE; /* * throw out any page cache pages in this range. this * may block. diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 96d2bd829902..da55eb8bcffa 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -452,6 +452,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb) INIT_LIST_HEAD(&ci->i_unsafe_writes); INIT_LIST_HEAD(&ci->i_unsafe_dirops); + INIT_LIST_HEAD(&ci->i_unsafe_iops); spin_lock_init(&ci->i_unsafe_lock); ci->i_snap_realm = NULL; @@ -1755,7 +1756,7 @@ retry: */ static const struct inode_operations ceph_symlink_iops = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = ceph_setattr, .getattr = ceph_getattr, .setxattr = ceph_setxattr, diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 51cb02da75d9..e7b130a637f9 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -633,13 +633,8 @@ static void __register_request(struct ceph_mds_client *mdsc, mdsc->oldest_tid = req->r_tid; if (dir) { - struct ceph_inode_info *ci = ceph_inode(dir); - ihold(dir); - spin_lock(&ci->i_unsafe_lock); req->r_unsafe_dir = dir; - list_add_tail(&req->r_unsafe_dir_item, &ci->i_unsafe_dirops); - spin_unlock(&ci->i_unsafe_lock); } } @@ -665,13 +660,20 @@ static void __unregister_request(struct ceph_mds_client *mdsc, rb_erase(&req->r_node, &mdsc->request_tree); RB_CLEAR_NODE(&req->r_node); - if (req->r_unsafe_dir) { + if (req->r_unsafe_dir && req->r_got_unsafe) { struct ceph_inode_info *ci = ceph_inode(req->r_unsafe_dir); - spin_lock(&ci->i_unsafe_lock); list_del_init(&req->r_unsafe_dir_item); spin_unlock(&ci->i_unsafe_lock); + } + if (req->r_target_inode && req->r_got_unsafe) { + struct ceph_inode_info *ci = ceph_inode(req->r_target_inode); + spin_lock(&ci->i_unsafe_lock); + list_del_init(&req->r_unsafe_target_item); + spin_unlock(&ci->i_unsafe_lock); + } + if (req->r_unsafe_dir) { iput(req->r_unsafe_dir); req->r_unsafe_dir = NULL; } @@ -1430,6 +1432,13 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) if ((used | wanted) & CEPH_CAP_ANY_WR) goto out; } + /* The inode has cached pages, but it's no longer used. + * we can safely drop it */ + if (wanted == 0 && used == CEPH_CAP_FILE_CACHE && + !(oissued & CEPH_CAP_FILE_CACHE)) { + used = 0; + oissued = 0; + } if ((used | wanted) & ~oissued & mine) goto out; /* we need these caps */ @@ -1438,7 +1447,7 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) /* we aren't the only cap.. just remove us */ __ceph_remove_cap(cap, true); } else { - /* try to drop referring dentries */ + /* try dropping referring dentries */ spin_unlock(&ci->i_ceph_lock); d_prune_aliases(inode); dout("trim_caps_cb %p cap %p pruned, count now %d\n", @@ -1704,6 +1713,7 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode) req->r_started = jiffies; req->r_resend_mds = -1; INIT_LIST_HEAD(&req->r_unsafe_dir_item); + INIT_LIST_HEAD(&req->r_unsafe_target_item); req->r_fmode = -1; kref_init(&req->r_kref); INIT_LIST_HEAD(&req->r_wait); @@ -1935,7 +1945,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, len = sizeof(*head) + pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) + - sizeof(struct timespec); + sizeof(struct ceph_timespec); /* calculate (max) length for cap releases */ len += sizeof(struct ceph_mds_request_release) * @@ -2477,6 +2487,14 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) } else { req->r_got_unsafe = true; list_add_tail(&req->r_unsafe_item, &req->r_session->s_unsafe); + if (req->r_unsafe_dir) { + struct ceph_inode_info *ci = + ceph_inode(req->r_unsafe_dir); + spin_lock(&ci->i_unsafe_lock); + list_add_tail(&req->r_unsafe_dir_item, + &ci->i_unsafe_dirops); + spin_unlock(&ci->i_unsafe_lock); + } } dout("handle_reply tid %lld result %d\n", tid, result); @@ -2518,6 +2536,13 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) up_read(&mdsc->snap_rwsem); if (realm) ceph_put_snap_realm(mdsc, realm); + + if (err == 0 && req->r_got_unsafe && req->r_target_inode) { + struct ceph_inode_info *ci = ceph_inode(req->r_target_inode); + spin_lock(&ci->i_unsafe_lock); + list_add_tail(&req->r_unsafe_target_item, &ci->i_unsafe_iops); + spin_unlock(&ci->i_unsafe_lock); + } out_err: mutex_lock(&mdsc->mutex); if (!req->r_aborted) { @@ -3917,17 +3942,19 @@ static struct ceph_msg *mds_alloc_msg(struct ceph_connection *con, return msg; } -static int sign_message(struct ceph_connection *con, struct ceph_msg *msg) +static int mds_sign_message(struct ceph_msg *msg) { - struct ceph_mds_session *s = con->private; + struct ceph_mds_session *s = msg->con->private; struct ceph_auth_handshake *auth = &s->s_auth; + return ceph_auth_sign_message(auth, msg); } -static int check_message_signature(struct ceph_connection *con, struct ceph_msg *msg) +static int mds_check_message_signature(struct ceph_msg *msg) { - struct ceph_mds_session *s = con->private; + struct ceph_mds_session *s = msg->con->private; struct ceph_auth_handshake *auth = &s->s_auth; + return ceph_auth_check_message_signature(auth, msg); } @@ -3940,8 +3967,8 @@ static const struct ceph_connection_operations mds_con_ops = { .invalidate_authorizer = invalidate_authorizer, .peer_reset = peer_reset, .alloc_msg = mds_alloc_msg, - .sign_message = sign_message, - .check_message_signature = check_message_signature, + .sign_message = mds_sign_message, + .check_message_signature = mds_check_message_signature, }; /* eof */ diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index f575eafe2261..ccf11ef0ca87 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -236,6 +236,9 @@ struct ceph_mds_request { struct inode *r_unsafe_dir; struct list_head r_unsafe_dir_item; + /* unsafe requests that modify the target inode */ + struct list_head r_unsafe_target_item; + struct ceph_mds_session *r_session; int r_attempts; /* resend attempts */ diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 2f2460d23a06..75b7d125ce66 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -342,6 +342,7 @@ struct ceph_inode_info { struct list_head i_unsafe_writes; /* uncommitted sync writes */ struct list_head i_unsafe_dirops; /* uncommitted mds dir ops */ + struct list_head i_unsafe_iops; /* uncommitted mds inode ops */ spinlock_t i_unsafe_lock; struct ceph_snap_realm *i_snap_realm; /* snap realm (if caps) */ diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index e739950ca084..b7fcb3151103 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -454,6 +454,10 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_puts(s, ",nocase"); if (tcon->retry) seq_puts(s, ",hard"); + if (tcon->use_persistent) + seq_puts(s, ",persistenthandles"); + else if (tcon->use_resilient) + seq_puts(s, ",resilienthandles"); if (tcon->unix_ext) seq_puts(s, ",unix"); else @@ -896,8 +900,7 @@ const struct inode_operations cifs_file_inode_ops = { const struct inode_operations cifs_symlink_inode_ops = { .readlink = generic_readlink, - .follow_link = cifs_follow_link, - .put_link = kfree_put_link, + .get_link = cifs_get_link, .permission = cifs_permission, /* BB add the following two eventually */ /* revalidate: cifs_revalidate, @@ -910,6 +913,59 @@ const struct inode_operations cifs_symlink_inode_ops = { #endif }; +static int cifs_clone_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, u64 len) +{ + struct inode *src_inode = file_inode(src_file); + struct inode *target_inode = file_inode(dst_file); + struct cifsFileInfo *smb_file_src = src_file->private_data; + struct cifsFileInfo *smb_file_target = dst_file->private_data; + struct cifs_tcon *target_tcon = tlink_tcon(smb_file_target->tlink); + unsigned int xid; + int rc; + + cifs_dbg(FYI, "clone range\n"); + + xid = get_xid(); + + if (!src_file->private_data || !dst_file->private_data) { + rc = -EBADF; + cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); + goto out; + } + + /* + * Note: cifs case is easier than btrfs since server responsible for + * checks for proper open modes and file type and if it wants + * server could even support copy of range where source = target + */ + lock_two_nondirectories(target_inode, src_inode); + + if (len == 0) + len = src_inode->i_size - off; + + cifs_dbg(FYI, "about to flush pages\n"); + /* should we flush first and last page first */ + truncate_inode_pages_range(&target_inode->i_data, destoff, + PAGE_CACHE_ALIGN(destoff + len)-1); + + if (target_tcon->ses->server->ops->duplicate_extents) + rc = target_tcon->ses->server->ops->duplicate_extents(xid, + smb_file_src, smb_file_target, off, len, destoff); + else + rc = -EOPNOTSUPP; + + /* force revalidate of size and timestamps of target file now + that target is updated on the server */ + CIFS_I(target_inode)->time = 0; + /* although unlocking in the reverse order from locking is not + strictly necessary here it is a little cleaner to be consistent */ + unlock_two_nondirectories(src_inode, target_inode); +out: + free_xid(xid); + return rc; +} + const struct file_operations cifs_file_ops = { .read_iter = cifs_loose_read_iter, .write_iter = cifs_file_write_iter, @@ -921,9 +977,8 @@ const struct file_operations cifs_file_ops = { .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, .llseek = cifs_llseek, -#ifdef CONFIG_CIFS_POSIX .unlocked_ioctl = cifs_ioctl, -#endif /* CONFIG_CIFS_POSIX */ + .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -939,9 +994,9 @@ const struct file_operations cifs_file_strict_ops = { .mmap = cifs_file_strict_mmap, .splice_read = generic_file_splice_read, .llseek = cifs_llseek, -#ifdef CONFIG_CIFS_POSIX .unlocked_ioctl = cifs_ioctl, -#endif /* CONFIG_CIFS_POSIX */ + .clone_file_range = cifs_clone_file_range, + .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -957,9 +1012,8 @@ const struct file_operations cifs_file_direct_ops = { .flush = cifs_flush, .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, -#ifdef CONFIG_CIFS_POSIX .unlocked_ioctl = cifs_ioctl, -#endif /* CONFIG_CIFS_POSIX */ + .clone_file_range = cifs_clone_file_range, .llseek = cifs_llseek, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -975,9 +1029,8 @@ const struct file_operations cifs_file_nobrl_ops = { .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, .llseek = cifs_llseek, -#ifdef CONFIG_CIFS_POSIX .unlocked_ioctl = cifs_ioctl, -#endif /* CONFIG_CIFS_POSIX */ + .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -992,9 +1045,8 @@ const struct file_operations cifs_file_strict_nobrl_ops = { .mmap = cifs_file_strict_mmap, .splice_read = generic_file_splice_read, .llseek = cifs_llseek, -#ifdef CONFIG_CIFS_POSIX .unlocked_ioctl = cifs_ioctl, -#endif /* CONFIG_CIFS_POSIX */ + .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -1009,9 +1061,8 @@ const struct file_operations cifs_file_direct_nobrl_ops = { .flush = cifs_flush, .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, -#ifdef CONFIG_CIFS_POSIX .unlocked_ioctl = cifs_ioctl, -#endif /* CONFIG_CIFS_POSIX */ + .clone_file_range = cifs_clone_file_range, .llseek = cifs_llseek, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1022,6 +1073,7 @@ const struct file_operations cifs_dir_ops = { .release = cifs_closedir, .read = generic_read_dir, .unlocked_ioctl = cifs_ioctl, + .clone_file_range = cifs_clone_file_range, .llseek = generic_file_llseek, }; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index c3cc1609025f..68c4547528c4 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -120,9 +120,8 @@ extern struct vfsmount *cifs_dfs_d_automount(struct path *path); #endif /* Functions related to symlinks */ -extern const char *cifs_follow_link(struct dentry *direntry, void **cookie); -extern int cifs_readlink(struct dentry *direntry, char __user *buffer, - int buflen); +extern const char *cifs_get_link(struct dentry *, struct inode *, + struct delayed_call *); extern int cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname); extern int cifs_removexattr(struct dentry *, const char *); @@ -131,7 +130,6 @@ extern int cifs_setxattr(struct dentry *, const char *, const void *, extern ssize_t cifs_getxattr(struct dentry *, const char *, void *, size_t); extern ssize_t cifs_listxattr(struct dentry *, char *, size_t); extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); - #ifdef CONFIG_CIFS_NFSD_EXPORT extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index b406a32deb1f..2b510c537a0d 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -493,7 +493,10 @@ struct smb_vol { bool mfsymlinks:1; /* use Minshall+French Symlinks */ bool multiuser:1; bool rwpidforward:1; /* pid forward for read/write operations */ - bool nosharesock; + bool nosharesock:1; + bool persistent:1; + bool nopersistent:1; + bool resilient:1; /* noresilient not required since not fored for CA */ unsigned int rsize; unsigned int wsize; bool sockopt_tcp_nodelay:1; @@ -895,6 +898,8 @@ struct cifs_tcon { bool broken_posix_open; /* e.g. Samba server versions < 3.3.2, 3.2.9 */ bool broken_sparse_sup; /* if server or share does not support sparse */ bool need_reconnect:1; /* connection reset, tid now invalid */ + bool use_resilient:1; /* use resilient instead of durable handles */ + bool use_persistent:1; /* use persistent instead of durable handles */ #ifdef CONFIG_CIFS_SMB2 bool print:1; /* set if connection to printer share */ bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */ @@ -1015,6 +1020,7 @@ struct cifs_fid { __u64 persistent_fid; /* persist file id for smb2 */ __u64 volatile_fid; /* volatile file id for smb2 */ __u8 lease_key[SMB2_LEASE_KEY_SIZE]; /* lease key for smb2 */ + __u8 create_guid[16]; #endif struct cifs_pending_open *pending_open; unsigned int epoch; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 3f2228570d44..ecb0803bdb0e 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -87,6 +87,8 @@ enum { Opt_sign, Opt_seal, Opt_noac, Opt_fsc, Opt_mfsymlinks, Opt_multiuser, Opt_sloppy, Opt_nosharesock, + Opt_persistent, Opt_nopersistent, + Opt_resilient, Opt_noresilient, /* Mount options which take numeric value */ Opt_backupuid, Opt_backupgid, Opt_uid, @@ -169,6 +171,10 @@ static const match_table_t cifs_mount_option_tokens = { { Opt_multiuser, "multiuser" }, { Opt_sloppy, "sloppy" }, { Opt_nosharesock, "nosharesock" }, + { Opt_persistent, "persistenthandles"}, + { Opt_nopersistent, "nopersistenthandles"}, + { Opt_resilient, "resilienthandles"}, + { Opt_noresilient, "noresilienthandles"}, { Opt_backupuid, "backupuid=%s" }, { Opt_backupgid, "backupgid=%s" }, @@ -1497,6 +1503,33 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, case Opt_nosharesock: vol->nosharesock = true; break; + case Opt_nopersistent: + vol->nopersistent = true; + if (vol->persistent) { + cifs_dbg(VFS, + "persistenthandles mount options conflict\n"); + goto cifs_parse_mount_err; + } + break; + case Opt_persistent: + vol->persistent = true; + if ((vol->nopersistent) || (vol->resilient)) { + cifs_dbg(VFS, + "persistenthandles mount options conflict\n"); + goto cifs_parse_mount_err; + } + break; + case Opt_resilient: + vol->resilient = true; + if (vol->persistent) { + cifs_dbg(VFS, + "persistenthandles mount options conflict\n"); + goto cifs_parse_mount_err; + } + break; + case Opt_noresilient: + vol->resilient = false; /* already the default */ + break; /* Numeric Values */ case Opt_backupuid: @@ -2655,6 +2688,42 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) cifs_dbg(FYI, "DFS disabled (%d)\n", tcon->Flags); } tcon->seal = volume_info->seal; + tcon->use_persistent = false; + /* check if SMB2 or later, CIFS does not support persistent handles */ + if (volume_info->persistent) { + if (ses->server->vals->protocol_id == 0) { + cifs_dbg(VFS, + "SMB3 or later required for persistent handles\n"); + rc = -EOPNOTSUPP; + goto out_fail; +#ifdef CONFIG_CIFS_SMB2 + } else if (ses->server->capabilities & + SMB2_GLOBAL_CAP_PERSISTENT_HANDLES) + tcon->use_persistent = true; + else /* persistent handles requested but not supported */ { + cifs_dbg(VFS, + "Persistent handles not supported on share\n"); + rc = -EOPNOTSUPP; + goto out_fail; +#endif /* CONFIG_CIFS_SMB2 */ + } +#ifdef CONFIG_CIFS_SMB2 + } else if ((tcon->capabilities & SMB2_SHARE_CAP_CONTINUOUS_AVAILABILITY) + && (ses->server->capabilities & SMB2_GLOBAL_CAP_PERSISTENT_HANDLES) + && (volume_info->nopersistent == false)) { + cifs_dbg(FYI, "enabling persistent handles\n"); + tcon->use_persistent = true; +#endif /* CONFIG_CIFS_SMB2 */ + } else if (volume_info->resilient) { + if (ses->server->vals->protocol_id == 0) { + cifs_dbg(VFS, + "SMB2.1 or later required for resilient handles\n"); + rc = -EOPNOTSUPP; + goto out_fail; + } + tcon->use_resilient = true; + } + /* * We can have only one retry value for a connection to a share so for * resources mounted more than once to the same server share the last @@ -3503,6 +3572,15 @@ try_mount_again: goto mount_fail_check; } +#ifdef CONFIG_CIFS_SMB2 + if ((volume_info->persistent == true) && ((ses->server->capabilities & + SMB2_GLOBAL_CAP_PERSISTENT_HANDLES) == 0)) { + cifs_dbg(VFS, "persistent handles not supported by server\n"); + rc = -EOPNOTSUPP; + goto mount_fail_check; + } +#endif /* CONFIG_CIFS_SMB2*/ + /* search for existing tcon to this server share */ tcon = cifs_get_tcon(ses, volume_info); if (IS_ERR(tcon)) { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 47c5c97e2dd3..0068e82217c3 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3380,7 +3380,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, struct page *page, *tpage; unsigned int expected_index; int rc; - gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping); + gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL); INIT_LIST_HEAD(tmplist); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 6b66dd5d1540..a329f5ba35aa 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1831,11 +1831,11 @@ cifs_invalidate_mapping(struct inode *inode) * @word: long word containing the bit lock */ static int -cifs_wait_bit_killable(struct wait_bit_key *key) +cifs_wait_bit_killable(struct wait_bit_key *key, int mode) { - if (fatal_signal_pending(current)) - return -ERESTARTSYS; freezable_schedule_unsafe(); + if (signal_pending_state(mode, current)) + return -ERESTARTSYS; return 0; } diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 28a77bf1d559..7a3b84e300f8 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -34,68 +34,36 @@ #include "cifs_ioctl.h" #include <linux/btrfs.h> -static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, - unsigned long srcfd, u64 off, u64 len, u64 destoff, - bool dup_extents) +static int cifs_file_clone_range(unsigned int xid, struct file *src_file, + struct file *dst_file) { - int rc; - struct cifsFileInfo *smb_file_target = dst_file->private_data; + struct inode *src_inode = file_inode(src_file); struct inode *target_inode = file_inode(dst_file); - struct cifs_tcon *target_tcon; - struct fd src_file; struct cifsFileInfo *smb_file_src; - struct inode *src_inode; + struct cifsFileInfo *smb_file_target; struct cifs_tcon *src_tcon; + struct cifs_tcon *target_tcon; + int rc; cifs_dbg(FYI, "ioctl clone range\n"); - /* the destination must be opened for writing */ - if (!(dst_file->f_mode & FMODE_WRITE)) { - cifs_dbg(FYI, "file target not open for write\n"); - return -EINVAL; - } - - /* check if target volume is readonly and take reference */ - rc = mnt_want_write_file(dst_file); - if (rc) { - cifs_dbg(FYI, "mnt_want_write failed with rc %d\n", rc); - return rc; - } - src_file = fdget(srcfd); - if (!src_file.file) { - rc = -EBADF; - goto out_drop_write; - } - - if (src_file.file->f_op->unlocked_ioctl != cifs_ioctl) { - rc = -EBADF; - cifs_dbg(VFS, "src file seems to be from a different filesystem type\n"); - goto out_fput; - } - - if ((!src_file.file->private_data) || (!dst_file->private_data)) { + if (!src_file->private_data || !dst_file->private_data) { rc = -EBADF; cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); - goto out_fput; + goto out; } rc = -EXDEV; smb_file_target = dst_file->private_data; - smb_file_src = src_file.file->private_data; + smb_file_src = src_file->private_data; src_tcon = tlink_tcon(smb_file_src->tlink); target_tcon = tlink_tcon(smb_file_target->tlink); - /* check if source and target are on same tree connection */ - if (src_tcon != target_tcon) { - cifs_dbg(VFS, "file copy src and target on different volume\n"); - goto out_fput; + if (src_tcon->ses != target_tcon->ses) { + cifs_dbg(VFS, "source and target of copy not on same server\n"); + goto out; } - src_inode = file_inode(src_file.file); - rc = -EINVAL; - if (S_ISDIR(src_inode->i_mode)) - goto out_fput; - /* * Note: cifs case is easier than btrfs since server responsible for * checks for proper open modes and file type and if it wants @@ -103,34 +71,66 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, */ lock_two_nondirectories(target_inode, src_inode); - /* determine range to clone */ - rc = -EINVAL; - if (off + len > src_inode->i_size || off + len < off) - goto out_unlock; - if (len == 0) - len = src_inode->i_size - off; - cifs_dbg(FYI, "about to flush pages\n"); /* should we flush first and last page first */ - truncate_inode_pages_range(&target_inode->i_data, destoff, - PAGE_CACHE_ALIGN(destoff + len)-1); + truncate_inode_pages(&target_inode->i_data, 0); - if (dup_extents && target_tcon->ses->server->ops->duplicate_extents) - rc = target_tcon->ses->server->ops->duplicate_extents(xid, - smb_file_src, smb_file_target, off, len, destoff); - else if (!dup_extents && target_tcon->ses->server->ops->clone_range) + if (target_tcon->ses->server->ops->clone_range) rc = target_tcon->ses->server->ops->clone_range(xid, - smb_file_src, smb_file_target, off, len, destoff); + smb_file_src, smb_file_target, 0, src_inode->i_size, 0); else rc = -EOPNOTSUPP; /* force revalidate of size and timestamps of target file now that target is updated on the server */ CIFS_I(target_inode)->time = 0; -out_unlock: /* although unlocking in the reverse order from locking is not strictly necessary here it is a little cleaner to be consistent */ unlock_two_nondirectories(src_inode, target_inode); +out: + return rc; +} + +static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, + unsigned long srcfd) +{ + int rc; + struct fd src_file; + struct inode *src_inode; + + cifs_dbg(FYI, "ioctl clone range\n"); + /* the destination must be opened for writing */ + if (!(dst_file->f_mode & FMODE_WRITE)) { + cifs_dbg(FYI, "file target not open for write\n"); + return -EINVAL; + } + + /* check if target volume is readonly and take reference */ + rc = mnt_want_write_file(dst_file); + if (rc) { + cifs_dbg(FYI, "mnt_want_write failed with rc %d\n", rc); + return rc; + } + + src_file = fdget(srcfd); + if (!src_file.file) { + rc = -EBADF; + goto out_drop_write; + } + + if (src_file.file->f_op->unlocked_ioctl != cifs_ioctl) { + rc = -EBADF; + cifs_dbg(VFS, "src file seems to be from a different filesystem type\n"); + goto out_fput; + } + + src_inode = file_inode(src_file.file); + rc = -EINVAL; + if (S_ISDIR(src_inode->i_mode)) + goto out_fput; + + rc = cifs_file_clone_range(xid, src_file.file, dst_file); + out_fput: fdput(src_file); out_drop_write: @@ -251,10 +251,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) } break; case CIFS_IOC_COPYCHUNK_FILE: - rc = cifs_ioctl_clone(xid, filep, arg, 0, 0, 0, false); - break; - case BTRFS_IOC_CLONE: - rc = cifs_ioctl_clone(xid, filep, arg, 0, 0, 0, true); + rc = cifs_ioctl_clone(xid, filep, arg); break; case CIFS_IOC_SET_INTEGRITY: if (pSMBFile == NULL) diff --git a/fs/cifs/link.c b/fs/cifs/link.c index e3548f73bdea..062c2375549a 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -627,9 +627,9 @@ cifs_hl_exit: } const char * -cifs_follow_link(struct dentry *direntry, void **cookie) +cifs_get_link(struct dentry *direntry, struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(direntry); int rc = -ENOMEM; unsigned int xid; char *full_path = NULL; @@ -639,6 +639,9 @@ cifs_follow_link(struct dentry *direntry, void **cookie) struct cifs_tcon *tcon; struct TCP_Server_Info *server; + if (!direntry) + return ERR_PTR(-ECHILD); + xid = get_xid(); tlink = cifs_sb_tlink(cifs_sb); @@ -678,7 +681,8 @@ cifs_follow_link(struct dentry *direntry, void **cookie) kfree(target_path); return ERR_PTR(rc); } - return *cookie = target_path; + set_delayed_call(done, kfree_link, target_path); + return target_path; } int diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 2ab297dae5a7..f9e766f464be 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -43,6 +43,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, struct smb2_file_all_info *smb2_data = NULL; __u8 smb2_oplock[17]; struct cifs_fid *fid = oparms->fid; + struct network_resiliency_req nr_ioctl_req; smb2_path = cifs_convert_path_to_utf16(oparms->path, oparms->cifs_sb); if (smb2_path == NULL) { @@ -67,6 +68,24 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, if (rc) goto out; + + if (oparms->tcon->use_resilient) { + nr_ioctl_req.Timeout = 0; /* use server default (120 seconds) */ + nr_ioctl_req.Reserved = 0; + rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid, + fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY, true, + (char *)&nr_ioctl_req, sizeof(nr_ioctl_req), + NULL, NULL /* no return info */); + if (rc == -EOPNOTSUPP) { + cifs_dbg(VFS, + "resiliency not supported by server, disabling\n"); + oparms->tcon->use_resilient = false; + } else if (rc) + cifs_dbg(FYI, "error %d setting resiliency\n", rc); + + rc = 0; + } + if (buf) { /* open response does not have IndexNumber field - get it */ rc = SMB2_get_srv_num(xid, oparms->tcon, fid->persistent_fid, diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 18da19f4f811..53ccdde6ff18 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -810,7 +810,6 @@ smb2_set_file_size(const unsigned int xid, struct cifs_tcon *tcon, cfile->fid.volatile_fid, cfile->pid, &eof, false); } -#ifdef CONFIG_CIFS_SMB311 static int smb2_duplicate_extents(const unsigned int xid, struct cifsFileInfo *srcfile, @@ -854,8 +853,6 @@ smb2_duplicate_extents(const unsigned int xid, duplicate_extents_out: return rc; } -#endif /* CONFIG_CIFS_SMB311 */ - static int smb2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, @@ -1703,6 +1700,7 @@ struct smb_version_operations smb30_operations = { .create_lease_buf = smb3_create_lease_buf, .parse_lease_buf = smb3_parse_lease_buf, .clone_range = smb2_clone_range, + .duplicate_extents = smb2_duplicate_extents, .validate_negotiate = smb3_validate_negotiate, .wp_retry_size = smb2_wp_retry_size, .dir_needs_close = smb2_dir_needs_close, @@ -1840,7 +1838,7 @@ struct smb_version_values smb21_values = { struct smb_version_values smb30_values = { .version_string = SMB30_VERSION_STRING, .protocol_id = SMB30_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -1860,7 +1858,7 @@ struct smb_version_values smb30_values = { struct smb_version_values smb302_values = { .version_string = SMB302_VERSION_STRING, .protocol_id = SMB302_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -1881,7 +1879,7 @@ struct smb_version_values smb302_values = { struct smb_version_values smb311_values = { .version_string = SMB311_VERSION_STRING, .protocol_id = SMB311_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 61276929d139..767555518d40 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1151,13 +1151,130 @@ add_lease_context(struct TCP_Server_Info *server, struct kvec *iov, return 0; } +static struct create_durable_v2 * +create_durable_v2_buf(struct cifs_fid *pfid) +{ + struct create_durable_v2 *buf; + + buf = kzalloc(sizeof(struct create_durable_v2), GFP_KERNEL); + if (!buf) + return NULL; + + buf->ccontext.DataOffset = cpu_to_le16(offsetof + (struct create_durable_v2, dcontext)); + buf->ccontext.DataLength = cpu_to_le32(sizeof(struct durable_context_v2)); + buf->ccontext.NameOffset = cpu_to_le16(offsetof + (struct create_durable_v2, Name)); + buf->ccontext.NameLength = cpu_to_le16(4); + + buf->dcontext.Timeout = 0; /* Should this be configurable by workload */ + buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT); + get_random_bytes(buf->dcontext.CreateGuid, 16); + memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16); + + /* SMB2_CREATE_DURABLE_HANDLE_REQUEST is "DH2Q" */ + buf->Name[0] = 'D'; + buf->Name[1] = 'H'; + buf->Name[2] = '2'; + buf->Name[3] = 'Q'; + return buf; +} + +static struct create_durable_handle_reconnect_v2 * +create_reconnect_durable_v2_buf(struct cifs_fid *fid) +{ + struct create_durable_handle_reconnect_v2 *buf; + + buf = kzalloc(sizeof(struct create_durable_handle_reconnect_v2), + GFP_KERNEL); + if (!buf) + return NULL; + + buf->ccontext.DataOffset = + cpu_to_le16(offsetof(struct create_durable_handle_reconnect_v2, + dcontext)); + buf->ccontext.DataLength = + cpu_to_le32(sizeof(struct durable_reconnect_context_v2)); + buf->ccontext.NameOffset = + cpu_to_le16(offsetof(struct create_durable_handle_reconnect_v2, + Name)); + buf->ccontext.NameLength = cpu_to_le16(4); + + buf->dcontext.Fid.PersistentFileId = fid->persistent_fid; + buf->dcontext.Fid.VolatileFileId = fid->volatile_fid; + buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT); + memcpy(buf->dcontext.CreateGuid, fid->create_guid, 16); + + /* SMB2_CREATE_DURABLE_HANDLE_RECONNECT_V2 is "DH2C" */ + buf->Name[0] = 'D'; + buf->Name[1] = 'H'; + buf->Name[2] = '2'; + buf->Name[3] = 'C'; + return buf; +} + static int -add_durable_context(struct kvec *iov, unsigned int *num_iovec, +add_durable_v2_context(struct kvec *iov, unsigned int *num_iovec, struct cifs_open_parms *oparms) { struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; + iov[num].iov_base = create_durable_v2_buf(oparms->fid); + if (iov[num].iov_base == NULL) + return -ENOMEM; + iov[num].iov_len = sizeof(struct create_durable_v2); + if (!req->CreateContextsOffset) + req->CreateContextsOffset = + cpu_to_le32(sizeof(struct smb2_create_req) - 4 + + iov[1].iov_len); + le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_durable_v2)); + inc_rfc1001_len(&req->hdr, sizeof(struct create_durable_v2)); + *num_iovec = num + 1; + return 0; +} + +static int +add_durable_reconnect_v2_context(struct kvec *iov, unsigned int *num_iovec, + struct cifs_open_parms *oparms) +{ + struct smb2_create_req *req = iov[0].iov_base; + unsigned int num = *num_iovec; + + /* indicate that we don't need to relock the file */ + oparms->reconnect = false; + + iov[num].iov_base = create_reconnect_durable_v2_buf(oparms->fid); + if (iov[num].iov_base == NULL) + return -ENOMEM; + iov[num].iov_len = sizeof(struct create_durable_handle_reconnect_v2); + if (!req->CreateContextsOffset) + req->CreateContextsOffset = + cpu_to_le32(sizeof(struct smb2_create_req) - 4 + + iov[1].iov_len); + le32_add_cpu(&req->CreateContextsLength, + sizeof(struct create_durable_handle_reconnect_v2)); + inc_rfc1001_len(&req->hdr, + sizeof(struct create_durable_handle_reconnect_v2)); + *num_iovec = num + 1; + return 0; +} + +static int +add_durable_context(struct kvec *iov, unsigned int *num_iovec, + struct cifs_open_parms *oparms, bool use_persistent) +{ + struct smb2_create_req *req = iov[0].iov_base; + unsigned int num = *num_iovec; + + if (use_persistent) { + if (oparms->reconnect) + return add_durable_reconnect_v2_context(iov, num_iovec, + oparms); + else + return add_durable_v2_context(iov, num_iovec, oparms); + } + if (oparms->reconnect) { iov[num].iov_base = create_reconnect_durable_buf(oparms->fid); /* indicate that we don't need to relock the file */ @@ -1275,7 +1392,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, ccontext->Next = cpu_to_le32(server->vals->create_lease_size); } - rc = add_durable_context(iov, &num_iovecs, oparms); + + rc = add_durable_context(iov, &num_iovecs, oparms, + tcon->use_persistent); if (rc) { cifs_small_buf_release(req); kfree(copy_path); diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 451108284a2f..4af52780ec35 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -590,6 +590,44 @@ struct create_durable { } Data; } __packed; +/* See MS-SMB2 2.2.13.2.11 */ +/* Flags */ +#define SMB2_DHANDLE_FLAG_PERSISTENT 0x00000002 +struct durable_context_v2 { + __le32 Timeout; + __le32 Flags; + __u64 Reserved; + __u8 CreateGuid[16]; +} __packed; + +struct create_durable_v2 { + struct create_context ccontext; + __u8 Name[8]; + struct durable_context_v2 dcontext; +} __packed; + +/* See MS-SMB2 2.2.13.2.12 */ +struct durable_reconnect_context_v2 { + struct { + __u64 PersistentFileId; + __u64 VolatileFileId; + } Fid; + __u8 CreateGuid[16]; + __le32 Flags; /* see above DHANDLE_FLAG_PERSISTENT */ +} __packed; + +/* See MS-SMB2 2.2.14.2.12 */ +struct durable_reconnect_context_v2_rsp { + __le32 Timeout; + __le32 Flags; /* see above DHANDLE_FLAG_PERSISTENT */ +} __packed; + +struct create_durable_handle_reconnect_v2 { + struct create_context ccontext; + __u8 Name[8]; + struct durable_reconnect_context_v2 dcontext; +} __packed; + #define COPY_CHUNK_RES_KEY_SIZE 24 struct resume_key_req { char ResumeKey[COPY_CHUNK_RES_KEY_SIZE]; @@ -643,6 +681,13 @@ struct fsctl_get_integrity_information_rsp { /* Integrity flags for above */ #define FSCTL_INTEGRITY_FLAG_CHECKSUM_ENFORCEMENT_OFF 0x00000001 +/* See MS-SMB2 2.2.31.3 */ +struct network_resiliency_req { + __le32 Timeout; + __le32 Reserved; +} __packed; +/* There is no buffer for the response ie no struct network_resiliency_rsp */ + struct validate_negotiate_info_req { __le32 Capabilities; diff --git a/fs/cifs/smbfsctl.h b/fs/cifs/smbfsctl.h index a639d0dab453..f996daeea271 100644 --- a/fs/cifs/smbfsctl.h +++ b/fs/cifs/smbfsctl.h @@ -90,7 +90,7 @@ #define FSCTL_SRV_ENUMERATE_SNAPSHOTS 0x00144064 /* Retrieve an opaque file reference for server-side data movement ie copy */ #define FSCTL_SRV_REQUEST_RESUME_KEY 0x00140078 -#define FSCTL_LMR_REQUEST_RESILIENCY 0x001401D4 /* BB add struct */ +#define FSCTL_LMR_REQUEST_RESILIENCY 0x001401D4 #define FSCTL_LMR_GET_LINK_TRACK_INF 0x001400E8 /* BB add struct */ #define FSCTL_LMR_SET_LINK_TRACK_INF 0x001400EC /* BB add struct */ #define FSCTL_VALIDATE_NEGOTIATE_INFO 0x00140204 diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index ff9e1f8b16a4..f5dc2f0df4ad 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -190,8 +190,8 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, #endif /* CONFIG_CIFS_ACL */ } else { int temp; - temp = strncmp(ea_name, POSIX_ACL_XATTR_ACCESS, - strlen(POSIX_ACL_XATTR_ACCESS)); + temp = strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS, + strlen(XATTR_NAME_POSIX_ACL_ACCESS)); if (temp == 0) { #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) @@ -203,8 +203,8 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, #else cifs_dbg(FYI, "set POSIX ACL not supported\n"); #endif - } else if (strncmp(ea_name, POSIX_ACL_XATTR_DEFAULT, - strlen(POSIX_ACL_XATTR_DEFAULT)) == 0) { + } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT, + strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) { #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) rc = CIFSSMBSetPosixACL(xid, pTcon, full_path, @@ -292,8 +292,8 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon, full_path, ea_name, ea_value, buf_size, cifs_sb->local_nls, cifs_remap(cifs_sb)); - } else if (strncmp(ea_name, POSIX_ACL_XATTR_ACCESS, - strlen(POSIX_ACL_XATTR_ACCESS)) == 0) { + } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS, + strlen(XATTR_NAME_POSIX_ACL_ACCESS)) == 0) { #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) rc = CIFSSMBGetPosixACL(xid, pTcon, full_path, @@ -303,8 +303,8 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, #else cifs_dbg(FYI, "Query POSIX ACL not supported yet\n"); #endif /* CONFIG_CIFS_POSIX */ - } else if (strncmp(ea_name, POSIX_ACL_XATTR_DEFAULT, - strlen(POSIX_ACL_XATTR_DEFAULT)) == 0) { + } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT, + strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) { #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) rc = CIFSSMBGetPosixACL(xid, pTcon, full_path, diff --git a/fs/coda/cnode.c b/fs/coda/cnode.c index 7740b1c871c1..1bfb7ba4e85e 100644 --- a/fs/coda/cnode.c +++ b/fs/coda/cnode.c @@ -8,6 +8,7 @@ #include <linux/coda.h> #include <linux/coda_psdev.h> +#include <linux/pagemap.h> #include "coda_linux.h" static inline int coda_fideq(struct CodaFid *fid1, struct CodaFid *fid2) @@ -17,8 +18,7 @@ static inline int coda_fideq(struct CodaFid *fid1, struct CodaFid *fid2) static const struct inode_operations coda_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = coda_setattr, }; @@ -35,6 +35,7 @@ static void coda_fill_inode(struct inode *inode, struct coda_vattr *attr) inode->i_fop = &coda_dir_operations; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &coda_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &coda_symlink_aops; inode->i_mapping = &inode->i_data; } else diff --git a/fs/coda/symlink.c b/fs/coda/symlink.c index ab94ef63caef..03736e20d720 100644 --- a/fs/coda/symlink.c +++ b/fs/coda/symlink.c @@ -26,7 +26,7 @@ static int coda_symlink_filler(struct file *file, struct page *page) int error; struct coda_inode_info *cii; unsigned int len = PAGE_SIZE; - char *p = kmap(page); + char *p = page_address(page); cii = ITOC(inode); @@ -34,13 +34,11 @@ static int coda_symlink_filler(struct file *file, struct page *page) if (error) goto fail; SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; fail: SetPageError(page); - kunmap(page); unlock_page(page); return error; } diff --git a/fs/compat.c b/fs/compat.c index 6fd272d455e4..a71936a3f4cb 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -792,7 +792,7 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name, const void __user *, data) { char *kernel_type; - unsigned long data_page; + void *options; char *kernel_dev; int retval; @@ -806,26 +806,25 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name, if (IS_ERR(kernel_dev)) goto out1; - retval = copy_mount_options(data, &data_page); - if (retval < 0) + options = copy_mount_options(data); + retval = PTR_ERR(options); + if (IS_ERR(options)) goto out2; - retval = -EINVAL; - - if (kernel_type && data_page) { + if (kernel_type && options) { if (!strcmp(kernel_type, NCPFS_NAME)) { - do_ncp_super_data_conv((void *)data_page); + do_ncp_super_data_conv(options); } else if (!strcmp(kernel_type, NFS4_NAME)) { - if (do_nfs4_super_data_conv((void *) data_page)) + retval = -EINVAL; + if (do_nfs4_super_data_conv(options)) goto out3; } } - retval = do_mount(kernel_dev, dir_name, kernel_type, - flags, (void*)data_page); + retval = do_mount(kernel_dev, dir_name, kernel_type, flags, options); out3: - free_page(data_page); + kfree(options); out2: kfree(kernel_dev); out1: diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 48851f6ea6ec..a5b8eb69a8f4 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -58,6 +58,8 @@ #include <linux/atalk.h> #include <linux/gfp.h> +#include "internal.h" + #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_sock.h> #include <net/bluetooth/rfcomm.h> @@ -115,19 +117,38 @@ #include <asm/fbio.h> #endif -static int w_long(unsigned int fd, unsigned int cmd, - compat_ulong_t __user *argp) +#define convert_in_user(srcptr, dstptr) \ +({ \ + typeof(*srcptr) val; \ + \ + get_user(val, srcptr) || put_user(val, dstptr); \ +}) + +static int do_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - mm_segment_t old_fs = get_fs(); int err; - unsigned long val; - set_fs (KERNEL_DS); - err = sys_ioctl(fd, cmd, (unsigned long)&val); - set_fs (old_fs); - if (!err && put_user(val, argp)) + err = security_file_ioctl(file, cmd, arg); + if (err) + return err; + + return vfs_ioctl(file, cmd, arg); +} + +static int w_long(struct file *file, + unsigned int cmd, compat_ulong_t __user *argp) +{ + int err; + unsigned long __user *valp = compat_alloc_user_space(sizeof(*valp)); + + if (valp == NULL) return -EFAULT; - return err; + err = do_ioctl(file, cmd, (unsigned long)valp); + if (err) + return err; + if (convert_in_user(valp, argp)) + return -EFAULT; + return 0; } struct compat_video_event { @@ -139,23 +160,23 @@ struct compat_video_event { } u; }; -static int do_video_get_event(unsigned int fd, unsigned int cmd, - struct compat_video_event __user *up) +static int do_video_get_event(struct file *file, + unsigned int cmd, struct compat_video_event __user *up) { - struct video_event kevent; - mm_segment_t old_fs = get_fs(); + struct video_event __user *kevent = + compat_alloc_user_space(sizeof(*kevent)); int err; - set_fs(KERNEL_DS); - err = sys_ioctl(fd, cmd, (unsigned long) &kevent); - set_fs(old_fs); + if (kevent == NULL) + return -EFAULT; + err = do_ioctl(file, cmd, (unsigned long)kevent); if (!err) { - err = put_user(kevent.type, &up->type); - err |= put_user(kevent.timestamp, &up->timestamp); - err |= put_user(kevent.u.size.w, &up->u.size.w); - err |= put_user(kevent.u.size.h, &up->u.size.h); - err |= put_user(kevent.u.size.aspect_ratio, + err = convert_in_user(&kevent->type, &up->type); + err |= convert_in_user(&kevent->timestamp, &up->timestamp); + err |= convert_in_user(&kevent->u.size.w, &up->u.size.w); + err |= convert_in_user(&kevent->u.size.h, &up->u.size.h); + err |= convert_in_user(&kevent->u.size.aspect_ratio, &up->u.size.aspect_ratio); if (err) err = -EFAULT; @@ -169,8 +190,8 @@ struct compat_video_still_picture { int32_t size; }; -static int do_video_stillpicture(unsigned int fd, unsigned int cmd, - struct compat_video_still_picture __user *up) +static int do_video_stillpicture(struct file *file, + unsigned int cmd, struct compat_video_still_picture __user *up) { struct video_still_picture __user *up_native; compat_uptr_t fp; @@ -190,7 +211,7 @@ static int do_video_stillpicture(unsigned int fd, unsigned int cmd, if (err) return -EFAULT; - err = sys_ioctl(fd, cmd, (unsigned long) up_native); + err = do_ioctl(file, cmd, (unsigned long) up_native); return err; } @@ -200,8 +221,8 @@ struct compat_video_spu_palette { compat_uptr_t palette; }; -static int do_video_set_spu_palette(unsigned int fd, unsigned int cmd, - struct compat_video_spu_palette __user *up) +static int do_video_set_spu_palette(struct file *file, + unsigned int cmd, struct compat_video_spu_palette __user *up) { struct video_spu_palette __user *up_native; compat_uptr_t palp; @@ -218,7 +239,7 @@ static int do_video_set_spu_palette(unsigned int fd, unsigned int cmd, if (err) return -EFAULT; - err = sys_ioctl(fd, cmd, (unsigned long) up_native); + err = do_ioctl(file, cmd, (unsigned long) up_native); return err; } @@ -276,7 +297,7 @@ static int sg_build_iovec(sg_io_hdr_t __user *sgio, void __user *dxferp, u16 iov return 0; } -static int sg_ioctl_trans(unsigned int fd, unsigned int cmd, +static int sg_ioctl_trans(struct file *file, unsigned int cmd, sg_io_hdr32_t __user *sgio32) { sg_io_hdr_t __user *sgio; @@ -289,7 +310,7 @@ static int sg_ioctl_trans(unsigned int fd, unsigned int cmd, if (get_user(interface_id, &sgio32->interface_id)) return -EFAULT; if (interface_id != 'S') - return sys_ioctl(fd, cmd, (unsigned long)sgio32); + return do_ioctl(file, cmd, (unsigned long)sgio32); if (get_user(iovec_count, &sgio32->iovec_count)) return -EFAULT; @@ -349,7 +370,7 @@ static int sg_ioctl_trans(unsigned int fd, unsigned int cmd, if (put_user(compat_ptr(data), &sgio->usr_ptr)) return -EFAULT; - err = sys_ioctl(fd, cmd, (unsigned long) sgio); + err = do_ioctl(file, cmd, (unsigned long) sgio); if (err >= 0) { void __user *datap; @@ -380,13 +401,13 @@ struct compat_sg_req_info { /* used by SG_GET_REQUEST_TABLE ioctl() */ int unused; }; -static int sg_grt_trans(unsigned int fd, unsigned int cmd, struct - compat_sg_req_info __user *o) +static int sg_grt_trans(struct file *file, + unsigned int cmd, struct compat_sg_req_info __user *o) { int err, i; sg_req_info_t __user *r; r = compat_alloc_user_space(sizeof(sg_req_info_t)*SG_MAX_QUEUE); - err = sys_ioctl(fd,cmd,(unsigned long)r); + err = do_ioctl(file, cmd, (unsigned long)r); if (err < 0) return err; for (i = 0; i < SG_MAX_QUEUE; i++) { @@ -412,8 +433,8 @@ struct sock_fprog32 { #define PPPIOCSPASS32 _IOW('t', 71, struct sock_fprog32) #define PPPIOCSACTIVE32 _IOW('t', 70, struct sock_fprog32) -static int ppp_sock_fprog_ioctl_trans(unsigned int fd, unsigned int cmd, - struct sock_fprog32 __user *u_fprog32) +static int ppp_sock_fprog_ioctl_trans(struct file *file, + unsigned int cmd, struct sock_fprog32 __user *u_fprog32) { struct sock_fprog __user *u_fprog64 = compat_alloc_user_space(sizeof(struct sock_fprog)); void __user *fptr64; @@ -435,7 +456,7 @@ static int ppp_sock_fprog_ioctl_trans(unsigned int fd, unsigned int cmd, else cmd = PPPIOCSACTIVE; - return sys_ioctl(fd, cmd, (unsigned long) u_fprog64); + return do_ioctl(file, cmd, (unsigned long) u_fprog64); } struct ppp_option_data32 { @@ -451,7 +472,7 @@ struct ppp_idle32 { }; #define PPPIOCGIDLE32 _IOR('t', 63, struct ppp_idle32) -static int ppp_gidle(unsigned int fd, unsigned int cmd, +static int ppp_gidle(struct file *file, unsigned int cmd, struct ppp_idle32 __user *idle32) { struct ppp_idle __user *idle; @@ -460,7 +481,7 @@ static int ppp_gidle(unsigned int fd, unsigned int cmd, idle = compat_alloc_user_space(sizeof(*idle)); - err = sys_ioctl(fd, PPPIOCGIDLE, (unsigned long) idle); + err = do_ioctl(file, PPPIOCGIDLE, (unsigned long) idle); if (!err) { if (get_user(xmit, &idle->xmit_idle) || @@ -472,7 +493,7 @@ static int ppp_gidle(unsigned int fd, unsigned int cmd, return err; } -static int ppp_scompress(unsigned int fd, unsigned int cmd, +static int ppp_scompress(struct file *file, unsigned int cmd, struct ppp_option_data32 __user *odata32) { struct ppp_option_data __user *odata; @@ -492,7 +513,7 @@ static int ppp_scompress(unsigned int fd, unsigned int cmd, sizeof(__u32) + sizeof(int))) return -EFAULT; - return sys_ioctl(fd, PPPIOCSCOMPRESS, (unsigned long) odata); + return do_ioctl(file, PPPIOCSCOMPRESS, (unsigned long) odata); } #ifdef CONFIG_BLOCK @@ -512,12 +533,13 @@ struct mtpos32 { }; #define MTIOCPOS32 _IOR('m', 3, struct mtpos32) -static int mt_ioctl_trans(unsigned int fd, unsigned int cmd, void __user *argp) +static int mt_ioctl_trans(struct file *file, + unsigned int cmd, void __user *argp) { - mm_segment_t old_fs = get_fs(); - struct mtget get; + /* NULL initialization to make gcc shut up */ + struct mtget __user *get = NULL; struct mtget32 __user *umget32; - struct mtpos pos; + struct mtpos __user *pos = NULL; struct mtpos32 __user *upos32; unsigned long kcmd; void *karg; @@ -526,32 +548,34 @@ static int mt_ioctl_trans(unsigned int fd, unsigned int cmd, void __user *argp) switch(cmd) { case MTIOCPOS32: kcmd = MTIOCPOS; - karg = &pos; + pos = compat_alloc_user_space(sizeof(*pos)); + karg = pos; break; default: /* MTIOCGET32 */ kcmd = MTIOCGET; - karg = &get; + get = compat_alloc_user_space(sizeof(*get)); + karg = get; break; } - set_fs (KERNEL_DS); - err = sys_ioctl (fd, kcmd, (unsigned long)karg); - set_fs (old_fs); + if (karg == NULL) + return -EFAULT; + err = do_ioctl(file, kcmd, (unsigned long)karg); if (err) return err; switch (cmd) { case MTIOCPOS32: upos32 = argp; - err = __put_user(pos.mt_blkno, &upos32->mt_blkno); + err = convert_in_user(&pos->mt_blkno, &upos32->mt_blkno); break; case MTIOCGET32: umget32 = argp; - err = __put_user(get.mt_type, &umget32->mt_type); - err |= __put_user(get.mt_resid, &umget32->mt_resid); - err |= __put_user(get.mt_dsreg, &umget32->mt_dsreg); - err |= __put_user(get.mt_gstat, &umget32->mt_gstat); - err |= __put_user(get.mt_erreg, &umget32->mt_erreg); - err |= __put_user(get.mt_fileno, &umget32->mt_fileno); - err |= __put_user(get.mt_blkno, &umget32->mt_blkno); + err = convert_in_user(&get->mt_type, &umget32->mt_type); + err |= convert_in_user(&get->mt_resid, &umget32->mt_resid); + err |= convert_in_user(&get->mt_dsreg, &umget32->mt_dsreg); + err |= convert_in_user(&get->mt_gstat, &umget32->mt_gstat); + err |= convert_in_user(&get->mt_erreg, &umget32->mt_erreg); + err |= convert_in_user(&get->mt_fileno, &umget32->mt_fileno); + err |= convert_in_user(&get->mt_blkno, &umget32->mt_blkno); break; } return err ? -EFAULT: 0; @@ -605,42 +629,41 @@ struct serial_struct32 { compat_int_t reserved[1]; }; -static int serial_struct_ioctl(unsigned fd, unsigned cmd, - struct serial_struct32 __user *ss32) +static int serial_struct_ioctl(struct file *file, + unsigned cmd, struct serial_struct32 __user *ss32) { typedef struct serial_struct32 SS32; int err; - struct serial_struct ss; - mm_segment_t oldseg = get_fs(); + struct serial_struct __user *ss = compat_alloc_user_space(sizeof(*ss)); __u32 udata; unsigned int base; + unsigned char *iomem_base; + if (ss == NULL) + return -EFAULT; if (cmd == TIOCSSERIAL) { - if (!access_ok(VERIFY_READ, ss32, sizeof(SS32))) - return -EFAULT; - if (__copy_from_user(&ss, ss32, offsetof(SS32, iomem_base))) - return -EFAULT; - if (__get_user(udata, &ss32->iomem_base)) + if (copy_in_user(ss, ss32, offsetof(SS32, iomem_base)) || + get_user(udata, &ss32->iomem_base)) return -EFAULT; - ss.iomem_base = compat_ptr(udata); - if (__get_user(ss.iomem_reg_shift, &ss32->iomem_reg_shift) || - __get_user(ss.port_high, &ss32->port_high)) + iomem_base = compat_ptr(udata); + if (put_user(iomem_base, &ss->iomem_base) || + convert_in_user(&ss32->iomem_reg_shift, + &ss->iomem_reg_shift) || + convert_in_user(&ss32->port_high, &ss->port_high) || + put_user(0UL, &ss->iomap_base)) return -EFAULT; - ss.iomap_base = 0UL; } - set_fs(KERNEL_DS); - err = sys_ioctl(fd,cmd,(unsigned long)(&ss)); - set_fs(oldseg); + err = do_ioctl(file, cmd, (unsigned long)ss); if (cmd == TIOCGSERIAL && err >= 0) { - if (!access_ok(VERIFY_WRITE, ss32, sizeof(SS32))) - return -EFAULT; - if (__copy_to_user(ss32,&ss,offsetof(SS32,iomem_base))) + if (copy_in_user(ss32, ss, offsetof(SS32, iomem_base)) || + get_user(iomem_base, &ss->iomem_base)) return -EFAULT; - base = (unsigned long)ss.iomem_base >> 32 ? - 0xffffffff : (unsigned)(unsigned long)ss.iomem_base; - if (__put_user(base, &ss32->iomem_base) || - __put_user(ss.iomem_reg_shift, &ss32->iomem_reg_shift) || - __put_user(ss.port_high, &ss32->port_high)) + base = (unsigned long)iomem_base >> 32 ? + 0xffffffff : (unsigned)(unsigned long)iomem_base; + if (put_user(base, &ss32->iomem_base) || + convert_in_user(&ss->iomem_reg_shift, + &ss32->iomem_reg_shift) || + convert_in_user(&ss->port_high, &ss32->port_high)) return -EFAULT; } return err; @@ -674,8 +697,8 @@ struct i2c_rdwr_aligned { struct i2c_msg msgs[0]; }; -static int do_i2c_rdwr_ioctl(unsigned int fd, unsigned int cmd, - struct i2c_rdwr_ioctl_data32 __user *udata) +static int do_i2c_rdwr_ioctl(struct file *file, + unsigned int cmd, struct i2c_rdwr_ioctl_data32 __user *udata) { struct i2c_rdwr_aligned __user *tdata; struct i2c_msg __user *tmsgs; @@ -686,7 +709,7 @@ static int do_i2c_rdwr_ioctl(unsigned int fd, unsigned int cmd, if (get_user(nmsgs, &udata->nmsgs)) return -EFAULT; - if (nmsgs > I2C_RDRW_IOCTL_MAX_MSGS) + if (nmsgs > I2C_RDWR_IOCTL_MAX_MSGS) return -EINVAL; if (get_user(datap, &udata->msgs)) @@ -708,11 +731,11 @@ static int do_i2c_rdwr_ioctl(unsigned int fd, unsigned int cmd, put_user(compat_ptr(datap), &tmsgs[i].buf)) return -EFAULT; } - return sys_ioctl(fd, cmd, (unsigned long)tdata); + return do_ioctl(file, cmd, (unsigned long)tdata); } -static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd, - struct i2c_smbus_ioctl_data32 __user *udata) +static int do_i2c_smbus_ioctl(struct file *file, + unsigned int cmd, struct i2c_smbus_ioctl_data32 __user *udata) { struct i2c_smbus_ioctl_data __user *tdata; compat_caddr_t datap; @@ -734,7 +757,7 @@ static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd, __put_user(compat_ptr(datap), &tdata->data)) return -EFAULT; - return sys_ioctl(fd, cmd, (unsigned long)tdata); + return do_ioctl(file, cmd, (unsigned long)tdata); } #define RTC_IRQP_READ32 _IOR('p', 0x0b, compat_ulong_t) @@ -742,29 +765,27 @@ static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd, #define RTC_EPOCH_READ32 _IOR('p', 0x0d, compat_ulong_t) #define RTC_EPOCH_SET32 _IOW('p', 0x0e, compat_ulong_t) -static int rtc_ioctl(unsigned fd, unsigned cmd, void __user *argp) +static int rtc_ioctl(struct file *file, + unsigned cmd, void __user *argp) { - mm_segment_t oldfs = get_fs(); - compat_ulong_t val32; - unsigned long kval; + unsigned long __user *valp = compat_alloc_user_space(sizeof(*valp)); int ret; + if (valp == NULL) + return -EFAULT; switch (cmd) { case RTC_IRQP_READ32: case RTC_EPOCH_READ32: - set_fs(KERNEL_DS); - ret = sys_ioctl(fd, (cmd == RTC_IRQP_READ32) ? + ret = do_ioctl(file, (cmd == RTC_IRQP_READ32) ? RTC_IRQP_READ : RTC_EPOCH_READ, - (unsigned long)&kval); - set_fs(oldfs); + (unsigned long)valp); if (ret) return ret; - val32 = kval; - return put_user(val32, (unsigned int __user *)argp); + return convert_in_user(valp, (unsigned int __user *)argp); case RTC_IRQP_SET32: - return sys_ioctl(fd, RTC_IRQP_SET, (unsigned long)argp); + return do_ioctl(file, RTC_IRQP_SET, (unsigned long)argp); case RTC_EPOCH_SET32: - return sys_ioctl(fd, RTC_EPOCH_SET, (unsigned long)argp); + return do_ioctl(file, RTC_EPOCH_SET, (unsigned long)argp); } return -ENOIOCTLCMD; @@ -1284,12 +1305,6 @@ COMPATIBLE_IOCTL(PCIIOC_CONTROLLER) COMPATIBLE_IOCTL(PCIIOC_MMAP_IS_IO) COMPATIBLE_IOCTL(PCIIOC_MMAP_IS_MEM) COMPATIBLE_IOCTL(PCIIOC_WRITE_COMBINE) -/* NBD */ -COMPATIBLE_IOCTL(NBD_DO_IT) -COMPATIBLE_IOCTL(NBD_CLEAR_SOCK) -COMPATIBLE_IOCTL(NBD_CLEAR_QUE) -COMPATIBLE_IOCTL(NBD_PRINT_DEBUG) -COMPATIBLE_IOCTL(NBD_DISCONNECT) /* i2c */ COMPATIBLE_IOCTL(I2C_SLAVE) COMPATIBLE_IOCTL(I2C_SLAVE_FORCE) @@ -1436,53 +1451,53 @@ IGNORE_IOCTL(FBIOGCURSOR32) * a compat_ioctl operation in the place that handleÑ• the * ioctl for the native case. */ -static long do_ioctl_trans(int fd, unsigned int cmd, +static long do_ioctl_trans(unsigned int cmd, unsigned long arg, struct file *file) { void __user *argp = compat_ptr(arg); switch (cmd) { case PPPIOCGIDLE32: - return ppp_gidle(fd, cmd, argp); + return ppp_gidle(file, cmd, argp); case PPPIOCSCOMPRESS32: - return ppp_scompress(fd, cmd, argp); + return ppp_scompress(file, cmd, argp); case PPPIOCSPASS32: case PPPIOCSACTIVE32: - return ppp_sock_fprog_ioctl_trans(fd, cmd, argp); + return ppp_sock_fprog_ioctl_trans(file, cmd, argp); #ifdef CONFIG_BLOCK case SG_IO: - return sg_ioctl_trans(fd, cmd, argp); + return sg_ioctl_trans(file, cmd, argp); case SG_GET_REQUEST_TABLE: - return sg_grt_trans(fd, cmd, argp); + return sg_grt_trans(file, cmd, argp); case MTIOCGET32: case MTIOCPOS32: - return mt_ioctl_trans(fd, cmd, argp); + return mt_ioctl_trans(file, cmd, argp); #endif /* Serial */ case TIOCGSERIAL: case TIOCSSERIAL: - return serial_struct_ioctl(fd, cmd, argp); + return serial_struct_ioctl(file, cmd, argp); /* i2c */ case I2C_FUNCS: - return w_long(fd, cmd, argp); + return w_long(file, cmd, argp); case I2C_RDWR: - return do_i2c_rdwr_ioctl(fd, cmd, argp); + return do_i2c_rdwr_ioctl(file, cmd, argp); case I2C_SMBUS: - return do_i2c_smbus_ioctl(fd, cmd, argp); + return do_i2c_smbus_ioctl(file, cmd, argp); /* Not implemented in the native kernel */ case RTC_IRQP_READ32: case RTC_IRQP_SET32: case RTC_EPOCH_READ32: case RTC_EPOCH_SET32: - return rtc_ioctl(fd, cmd, argp); + return rtc_ioctl(file, cmd, argp); /* dvb */ case VIDEO_GET_EVENT: - return do_video_get_event(fd, cmd, argp); + return do_video_get_event(file, cmd, argp); case VIDEO_STILLPICTURE: - return do_video_stillpicture(fd, cmd, argp); + return do_video_stillpicture(file, cmd, argp); case VIDEO_SET_SPU_PALETTE: - return do_video_set_spu_palette(fd, cmd, argp); + return do_video_set_spu_palette(file, cmd, argp); } /* @@ -1508,12 +1523,7 @@ static long do_ioctl_trans(int fd, unsigned int cmd, case KDSKBMETA: case KDSKBLED: case KDSETLED: - /* NBD */ - case NBD_SET_SOCK: - case NBD_SET_BLKSIZE: - case NBD_SET_SIZE: - case NBD_SET_SIZE_BLOCKS: - return do_vfs_ioctl(file, fd, cmd, arg); + return vfs_ioctl(file, cmd, arg); } return -ENOIOCTLCMD; @@ -1580,6 +1590,11 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, goto out_fput; #endif + case FICLONE: + case FICLONERANGE: + case FIDEDUPERANGE: + goto do_ioctl; + case FIBMAP: case FIGETBSZ: case FIONREAD: @@ -1602,7 +1617,7 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, if (compat_ioctl_check_table(XFORM(cmd))) goto found_handler; - error = do_ioctl_trans(fd, cmd, arg, f.file); + error = do_ioctl_trans(cmd, arg, f.file); if (error == -ENOIOCTLCMD) error = -ENOTTY; diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h index b65d1ef532d5..ccc31fa6f1a7 100644 --- a/fs/configfs/configfs_internal.h +++ b/fs/configfs/configfs_internal.h @@ -53,13 +53,14 @@ struct configfs_dirent { #define CONFIGFS_ROOT 0x0001 #define CONFIGFS_DIR 0x0002 #define CONFIGFS_ITEM_ATTR 0x0004 +#define CONFIGFS_ITEM_BIN_ATTR 0x0008 #define CONFIGFS_ITEM_LINK 0x0020 #define CONFIGFS_USET_DIR 0x0040 #define CONFIGFS_USET_DEFAULT 0x0080 #define CONFIGFS_USET_DROPPING 0x0100 #define CONFIGFS_USET_IN_MKDIR 0x0200 #define CONFIGFS_USET_CREATING 0x0400 -#define CONFIGFS_NOT_PINNED (CONFIGFS_ITEM_ATTR) +#define CONFIGFS_NOT_PINNED (CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR) extern struct mutex configfs_symlink_mutex; extern spinlock_t configfs_dirent_lock; @@ -72,6 +73,8 @@ extern struct inode * configfs_new_inode(umode_t mode, struct configfs_dirent *, extern int configfs_create(struct dentry *, umode_t mode, void (*init)(struct inode *)); extern int configfs_create_file(struct config_item *, const struct configfs_attribute *); +extern int configfs_create_bin_file(struct config_item *, + const struct configfs_bin_attribute *); extern int configfs_make_dirent(struct configfs_dirent *, struct dentry *, void *, umode_t, int); extern int configfs_dirent_is_ready(struct configfs_dirent *); @@ -88,7 +91,7 @@ extern void configfs_release_fs(void); extern struct rw_semaphore configfs_rename_sem; extern const struct file_operations configfs_dir_operations; extern const struct file_operations configfs_file_operations; -extern const struct file_operations bin_fops; +extern const struct file_operations configfs_bin_file_operations; extern const struct inode_operations configfs_dir_inode_operations; extern const struct inode_operations configfs_root_inode_operations; extern const struct inode_operations configfs_symlink_inode_operations; @@ -119,6 +122,13 @@ static inline struct configfs_attribute * to_attr(struct dentry * dentry) return ((struct configfs_attribute *) sd->s_element); } +static inline struct configfs_bin_attribute *to_bin_attr(struct dentry *dentry) +{ + struct configfs_attribute *attr = to_attr(dentry); + + return container_of(attr, struct configfs_bin_attribute, cb_attr); +} + static inline struct config_item *configfs_get_config_item(struct dentry *dentry) { struct config_item * item = NULL; diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index c81ce7f200a6..7ae97e83f121 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -255,6 +255,12 @@ static void configfs_init_file(struct inode * inode) inode->i_fop = &configfs_file_operations; } +static void configfs_init_bin_file(struct inode *inode) +{ + inode->i_size = 0; + inode->i_fop = &configfs_bin_file_operations; +} + static void init_symlink(struct inode * inode) { inode->i_op = &configfs_symlink_inode_operations; @@ -423,7 +429,9 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den spin_unlock(&configfs_dirent_lock); error = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG, - configfs_init_file); + (sd->s_type & CONFIGFS_ITEM_BIN_ATTR) ? + configfs_init_bin_file : + configfs_init_file); if (error) { configfs_put(sd); return error; @@ -583,6 +591,7 @@ static int populate_attrs(struct config_item *item) { struct config_item_type *t = item->ci_type; struct configfs_attribute *attr; + struct configfs_bin_attribute *bin_attr; int error = 0; int i; @@ -594,6 +603,13 @@ static int populate_attrs(struct config_item *item) break; } } + if (t->ct_bin_attrs) { + for (i = 0; (bin_attr = t->ct_bin_attrs[i]) != NULL; i++) { + error = configfs_create_bin_file(item, bin_attr); + if (error) + break; + } + } if (error) detach_attrs(item); @@ -1636,6 +1652,116 @@ const struct file_operations configfs_dir_operations = { .iterate = configfs_readdir, }; +/** + * configfs_register_group - creates a parent-child relation between two groups + * @parent_group: parent group + * @group: child group + * + * link groups, creates dentry for the child and attaches it to the + * parent dentry. + * + * Return: 0 on success, negative errno code on error + */ +int configfs_register_group(struct config_group *parent_group, + struct config_group *group) +{ + struct configfs_subsystem *subsys = parent_group->cg_subsys; + struct dentry *parent; + int ret; + + mutex_lock(&subsys->su_mutex); + link_group(parent_group, group); + mutex_unlock(&subsys->su_mutex); + + parent = parent_group->cg_item.ci_dentry; + + mutex_lock_nested(&d_inode(parent)->i_mutex, I_MUTEX_PARENT); + ret = create_default_group(parent_group, group); + if (!ret) { + spin_lock(&configfs_dirent_lock); + configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); + spin_unlock(&configfs_dirent_lock); + } + mutex_unlock(&d_inode(parent)->i_mutex); + return ret; +} +EXPORT_SYMBOL(configfs_register_group); + +/** + * configfs_unregister_group() - unregisters a child group from its parent + * @group: parent group to be unregistered + * + * Undoes configfs_register_group() + */ +void configfs_unregister_group(struct config_group *group) +{ + struct configfs_subsystem *subsys = group->cg_subsys; + struct dentry *dentry = group->cg_item.ci_dentry; + struct dentry *parent = group->cg_item.ci_parent->ci_dentry; + + mutex_lock_nested(&d_inode(parent)->i_mutex, I_MUTEX_PARENT); + spin_lock(&configfs_dirent_lock); + configfs_detach_prep(dentry, NULL); + spin_unlock(&configfs_dirent_lock); + + configfs_detach_group(&group->cg_item); + d_inode(dentry)->i_flags |= S_DEAD; + dont_mount(dentry); + d_delete(dentry); + mutex_unlock(&d_inode(parent)->i_mutex); + + dput(dentry); + + mutex_lock(&subsys->su_mutex); + unlink_group(group); + mutex_unlock(&subsys->su_mutex); +} +EXPORT_SYMBOL(configfs_unregister_group); + +/** + * configfs_register_default_group() - allocates and registers a child group + * @parent_group: parent group + * @name: child group name + * @item_type: child item type description + * + * boilerplate to allocate and register a child group with its parent. We need + * kzalloc'ed memory because child's default_group is initially empty. + * + * Return: allocated config group or ERR_PTR() on error + */ +struct config_group * +configfs_register_default_group(struct config_group *parent_group, + const char *name, + struct config_item_type *item_type) +{ + int ret; + struct config_group *group; + + group = kzalloc(sizeof(*group), GFP_KERNEL); + if (!group) + return ERR_PTR(-ENOMEM); + config_group_init_type_name(group, name, item_type); + + ret = configfs_register_group(parent_group, group); + if (ret) { + kfree(group); + return ERR_PTR(ret); + } + return group; +} +EXPORT_SYMBOL(configfs_register_default_group); + +/** + * configfs_unregister_default_group() - unregisters and frees a child group + * @group: the group to act on + */ +void configfs_unregister_default_group(struct config_group *group) +{ + configfs_unregister_group(group); + kfree(group); +} +EXPORT_SYMBOL(configfs_unregister_default_group); + int configfs_register_subsystem(struct configfs_subsystem *subsys) { int err; diff --git a/fs/configfs/file.c b/fs/configfs/file.c index 403269ffcdf3..3687187c8ea5 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -28,6 +28,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/mutex.h> +#include <linux/vmalloc.h> #include <asm/uaccess.h> #include <linux/configfs.h> @@ -48,6 +49,10 @@ struct configfs_buffer { struct configfs_item_operations * ops; struct mutex mutex; int needs_read_fill; + bool read_in_progress; + bool write_in_progress; + char *bin_buffer; + int bin_buffer_size; }; @@ -65,7 +70,6 @@ static int fill_read_buffer(struct dentry * dentry, struct configfs_buffer * buf { struct configfs_attribute * attr = to_attr(dentry); struct config_item * item = to_item(dentry->d_parent); - struct configfs_item_operations * ops = buffer->ops; int ret = 0; ssize_t count; @@ -74,7 +78,8 @@ static int fill_read_buffer(struct dentry * dentry, struct configfs_buffer * buf if (!buffer->page) return -ENOMEM; - count = ops->show_attribute(item,attr,buffer->page); + count = attr->show(item, buffer->page); + buffer->needs_read_fill = 0; BUG_ON(count > (ssize_t)SIMPLE_ATTR_SIZE); if (count >= 0) @@ -123,6 +128,87 @@ out: return retval; } +/** + * configfs_read_bin_file - read a binary attribute. + * @file: file pointer. + * @buf: buffer to fill. + * @count: number of bytes to read. + * @ppos: starting offset in file. + * + * Userspace wants to read a binary attribute file. The attribute + * descriptor is in the file's ->d_fsdata. The target item is in the + * directory's ->d_fsdata. + * + * We check whether we need to refill the buffer. If so we will + * call the attributes' attr->read() twice. The first time we + * will pass a NULL as a buffer pointer, which the attributes' method + * will use to return the size of the buffer required. If no error + * occurs we will allocate the buffer using vmalloc and call + * attr->read() again passing that buffer as an argument. + * Then we just copy to user-space using simple_read_from_buffer. + */ + +static ssize_t +configfs_read_bin_file(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct configfs_buffer *buffer = file->private_data; + struct dentry *dentry = file->f_path.dentry; + struct config_item *item = to_item(dentry->d_parent); + struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry); + ssize_t retval = 0; + ssize_t len = min_t(size_t, count, PAGE_SIZE); + + mutex_lock(&buffer->mutex); + + /* we don't support switching read/write modes */ + if (buffer->write_in_progress) { + retval = -ETXTBSY; + goto out; + } + buffer->read_in_progress = 1; + + if (buffer->needs_read_fill) { + /* perform first read with buf == NULL to get extent */ + len = bin_attr->read(item, NULL, 0); + if (len <= 0) { + retval = len; + goto out; + } + + /* do not exceed the maximum value */ + if (bin_attr->cb_max_size && len > bin_attr->cb_max_size) { + retval = -EFBIG; + goto out; + } + + buffer->bin_buffer = vmalloc(len); + if (buffer->bin_buffer == NULL) { + retval = -ENOMEM; + goto out; + } + buffer->bin_buffer_size = len; + + /* perform second read to fill buffer */ + len = bin_attr->read(item, buffer->bin_buffer, len); + if (len < 0) { + retval = len; + vfree(buffer->bin_buffer); + buffer->bin_buffer_size = 0; + buffer->bin_buffer = NULL; + goto out; + } + + buffer->needs_read_fill = 0; + } + + retval = simple_read_from_buffer(buf, count, ppos, buffer->bin_buffer, + buffer->bin_buffer_size); +out: + mutex_unlock(&buffer->mutex); + return retval; +} + /** * fill_write_buffer - copy buffer from userspace. @@ -171,9 +257,8 @@ flush_write_buffer(struct dentry * dentry, struct configfs_buffer * buffer, size { struct configfs_attribute * attr = to_attr(dentry); struct config_item * item = to_item(dentry->d_parent); - struct configfs_item_operations * ops = buffer->ops; - return ops->store_attribute(item,attr,buffer->page,count); + return attr->store(item, buffer->page, count); } @@ -210,10 +295,80 @@ configfs_write_file(struct file *file, const char __user *buf, size_t count, lof return len; } -static int check_perm(struct inode * inode, struct file * file) +/** + * configfs_write_bin_file - write a binary attribute. + * @file: file pointer + * @buf: data to write + * @count: number of bytes + * @ppos: starting offset + * + * Writing to a binary attribute file is similar to a normal read. + * We buffer the consecutive writes (binary attribute files do not + * support lseek) in a continuously growing buffer, but we don't + * commit until the close of the file. + */ + +static ssize_t +configfs_write_bin_file(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct configfs_buffer *buffer = file->private_data; + struct dentry *dentry = file->f_path.dentry; + struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry); + void *tbuf = NULL; + ssize_t len; + + mutex_lock(&buffer->mutex); + + /* we don't support switching read/write modes */ + if (buffer->read_in_progress) { + len = -ETXTBSY; + goto out; + } + buffer->write_in_progress = 1; + + /* buffer grows? */ + if (*ppos + count > buffer->bin_buffer_size) { + + if (bin_attr->cb_max_size && + *ppos + count > bin_attr->cb_max_size) { + len = -EFBIG; + } + + tbuf = vmalloc(*ppos + count); + if (tbuf == NULL) { + len = -ENOMEM; + goto out; + } + + /* copy old contents */ + if (buffer->bin_buffer) { + memcpy(tbuf, buffer->bin_buffer, + buffer->bin_buffer_size); + vfree(buffer->bin_buffer); + } + + /* clear the new area */ + memset(tbuf + buffer->bin_buffer_size, 0, + *ppos + count - buffer->bin_buffer_size); + buffer->bin_buffer = tbuf; + buffer->bin_buffer_size = *ppos + count; + } + + len = simple_write_to_buffer(buffer->bin_buffer, + buffer->bin_buffer_size, ppos, buf, count); + if (len > 0) + *ppos += len; +out: + mutex_unlock(&buffer->mutex); + return len; +} + +static int check_perm(struct inode * inode, struct file * file, int type) { struct config_item *item = configfs_get_config_item(file->f_path.dentry->d_parent); struct configfs_attribute * attr = to_attr(file->f_path.dentry); + struct configfs_bin_attribute *bin_attr = NULL; struct configfs_buffer * buffer; struct configfs_item_operations * ops = NULL; int error = 0; @@ -221,6 +376,9 @@ static int check_perm(struct inode * inode, struct file * file) if (!item || !attr) goto Einval; + if (type & CONFIGFS_ITEM_BIN_ATTR) + bin_attr = to_bin_attr(file->f_path.dentry); + /* Grab the module reference for this attribute if we have one */ if (!try_module_get(attr->ca_owner)) { error = -ENODEV; @@ -237,10 +395,14 @@ static int check_perm(struct inode * inode, struct file * file) * and we must have a store method. */ if (file->f_mode & FMODE_WRITE) { + if (!(inode->i_mode & S_IWUGO)) + goto Eaccess; - if (!(inode->i_mode & S_IWUGO) || !ops->store_attribute) + if ((type & CONFIGFS_ITEM_ATTR) && !attr->store) goto Eaccess; + if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->write) + goto Eaccess; } /* File needs read support. @@ -248,7 +410,13 @@ static int check_perm(struct inode * inode, struct file * file) * must be a show method for it. */ if (file->f_mode & FMODE_READ) { - if (!(inode->i_mode & S_IRUGO) || !ops->show_attribute) + if (!(inode->i_mode & S_IRUGO)) + goto Eaccess; + + if ((type & CONFIGFS_ITEM_ATTR) && !attr->show) + goto Eaccess; + + if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->read) goto Eaccess; } @@ -262,6 +430,8 @@ static int check_perm(struct inode * inode, struct file * file) } mutex_init(&buffer->mutex); buffer->needs_read_fill = 1; + buffer->read_in_progress = 0; + buffer->write_in_progress = 0; buffer->ops = ops; file->private_data = buffer; goto Done; @@ -279,12 +449,7 @@ static int check_perm(struct inode * inode, struct file * file) return error; } -static int configfs_open_file(struct inode * inode, struct file * filp) -{ - return check_perm(inode,filp); -} - -static int configfs_release(struct inode * inode, struct file * filp) +static int configfs_release(struct inode *inode, struct file *filp) { struct config_item * item = to_item(filp->f_path.dentry->d_parent); struct configfs_attribute * attr = to_attr(filp->f_path.dentry); @@ -305,6 +470,47 @@ static int configfs_release(struct inode * inode, struct file * filp) return 0; } +static int configfs_open_file(struct inode *inode, struct file *filp) +{ + return check_perm(inode, filp, CONFIGFS_ITEM_ATTR); +} + +static int configfs_open_bin_file(struct inode *inode, struct file *filp) +{ + return check_perm(inode, filp, CONFIGFS_ITEM_BIN_ATTR); +} + +static int configfs_release_bin_file(struct inode *inode, struct file *filp) +{ + struct configfs_buffer *buffer = filp->private_data; + struct dentry *dentry = filp->f_path.dentry; + struct config_item *item = to_item(dentry->d_parent); + struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry); + ssize_t len = 0; + int ret; + + buffer->read_in_progress = 0; + + if (buffer->write_in_progress) { + buffer->write_in_progress = 0; + + len = bin_attr->write(item, buffer->bin_buffer, + buffer->bin_buffer_size); + + /* vfree on NULL is safe */ + vfree(buffer->bin_buffer); + buffer->bin_buffer = NULL; + buffer->bin_buffer_size = 0; + buffer->needs_read_fill = 1; + } + + ret = configfs_release(inode, filp); + if (len < 0) + return len; + return ret; +} + + const struct file_operations configfs_file_operations = { .read = configfs_read_file, .write = configfs_write_file, @@ -313,6 +519,14 @@ const struct file_operations configfs_file_operations = { .release = configfs_release, }; +const struct file_operations configfs_bin_file_operations = { + .read = configfs_read_bin_file, + .write = configfs_write_bin_file, + .llseek = NULL, /* bin file is not seekable */ + .open = configfs_open_bin_file, + .release = configfs_release_bin_file, +}; + /** * configfs_create_file - create an attribute file for an item. * @item: item we're creating for. @@ -334,3 +548,24 @@ int configfs_create_file(struct config_item * item, const struct configfs_attrib return error; } +/** + * configfs_create_bin_file - create a binary attribute file for an item. + * @item: item we're creating for. + * @attr: atrribute descriptor. + */ + +int configfs_create_bin_file(struct config_item *item, + const struct configfs_bin_attribute *bin_attr) +{ + struct dentry *dir = item->ci_dentry; + struct configfs_dirent *parent_sd = dir->d_fsdata; + umode_t mode = (bin_attr->cb_attr.ca_mode & S_IALLUGO) | S_IFREG; + int error = 0; + + mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_NORMAL); + error = configfs_make_dirent(parent_sd, NULL, (void *) bin_attr, mode, + CONFIGFS_ITEM_BIN_ATTR); + mutex_unlock(&dir->d_inode->i_mutex); + + return error; +} diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index eae87575e681..0cc810e9dccc 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -218,7 +218,7 @@ const unsigned char * configfs_get_name(struct configfs_dirent *sd) if (sd->s_type & (CONFIGFS_DIR | CONFIGFS_ITEM_LINK)) return sd->s_dentry->d_name.name; - if (sd->s_type & CONFIGFS_ITEM_ATTR) { + if (sd->s_type & (CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR)) { attr = sd->s_element; return attr->ca_name; } diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index ec5c8325b503..db6d69289608 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -279,27 +279,33 @@ static int configfs_getlink(struct dentry *dentry, char * path) } -static const char *configfs_follow_link(struct dentry *dentry, void **cookie) +static const char *configfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - unsigned long page = get_zeroed_page(GFP_KERNEL); + char *body; int error; - if (!page) + if (!dentry) + return ERR_PTR(-ECHILD); + + body = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!body) return ERR_PTR(-ENOMEM); - error = configfs_getlink(dentry, (char *)page); + error = configfs_getlink(dentry, body); if (!error) { - return *cookie = (void *)page; + set_delayed_call(done, kfree_link, body); + return body; } - free_page(page); + kfree(body); return ERR_PTR(error); } const struct inode_operations configfs_symlink_inode_operations = { - .follow_link = configfs_follow_link, + .get_link = configfs_get_link, .readlink = generic_readlink, - .put_link = free_page_put_link, .setattr = configfs_setattr, }; diff --git a/fs/coredump.c b/fs/coredump.c index a8f75640ac86..b3c153ca435d 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -32,6 +32,7 @@ #include <linux/pipe_fs_i.h> #include <linux/oom.h> #include <linux/compat.h> +#include <linux/timekeeping.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> @@ -232,9 +233,10 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) break; /* UNIX time of coredump */ case 't': { - struct timeval tv; - do_gettimeofday(&tv); - err = cn_printf(cn, "%lu", tv.tv_sec); + time64_t time; + + time = ktime_get_real_seconds(); + err = cn_printf(cn, "%lld", time); break; } /* hostname */ @@ -280,23 +282,24 @@ out: return ispipe; } -static int zap_process(struct task_struct *start, int exit_code) +static int zap_process(struct task_struct *start, int exit_code, int flags) { struct task_struct *t; int nr = 0; + /* ignore all signals except SIGKILL, see prepare_signal() */ + start->signal->flags = SIGNAL_GROUP_COREDUMP | flags; start->signal->group_exit_code = exit_code; start->signal->group_stop_count = 0; - t = start; - do { + for_each_thread(start, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); if (t != current && t->mm) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); nr++; } - } while_each_thread(start, t); + } return nr; } @@ -311,10 +314,8 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, spin_lock_irq(&tsk->sighand->siglock); if (!signal_group_exit(tsk->signal)) { mm->core_state = core_state; - nr = zap_process(tsk, exit_code); tsk->signal->group_exit_task = tsk; - /* ignore all signals except SIGKILL, see prepare_signal() */ - tsk->signal->flags = SIGNAL_GROUP_COREDUMP; + nr = zap_process(tsk, exit_code, 0); clear_tsk_thread_flag(tsk, TIF_SIGPENDING); } spin_unlock_irq(&tsk->sighand->siglock); @@ -360,18 +361,18 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, continue; if (g->flags & PF_KTHREAD) continue; - p = g; - do { - if (p->mm) { - if (unlikely(p->mm == mm)) { - lock_task_sighand(p, &flags); - nr += zap_process(p, exit_code); - p->signal->flags = SIGNAL_GROUP_EXIT; - unlock_task_sighand(p, &flags); - } - break; + + for_each_thread(g, p) { + if (unlikely(!p->mm)) + continue; + if (unlikely(p->mm == mm)) { + lock_task_sighand(p, &flags); + nr += zap_process(p, exit_code, + SIGNAL_GROUP_EXIT); + unlock_task_sighand(p, &flags); } - } while_each_thread(g, p); + break; + } } rcu_read_unlock(); done: diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 355c522f3585..b862bc219cd7 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -100,6 +100,7 @@ static struct inode *get_cramfs_inode(struct super_block *sb, break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &cramfs_aops; break; default: @@ -29,6 +29,11 @@ #include <linux/uio.h> #include <linux/vmstat.h> +/* + * dax_clear_blocks() is called from within transaction context from XFS, + * and hence this means the stack from this point must follow GFP_NOFS + * semantics for all operations. + */ int dax_clear_blocks(struct inode *inode, sector_t block, long size) { struct block_device *bdev = inode->i_sb->s_bdev; @@ -169,8 +174,10 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, else len = iov_iter_zero(max - pos, iter); - if (!len) + if (!len) { + retval = -EFAULT; break; + } pos += len; addr += len; @@ -534,6 +541,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, unsigned long pfn; int result = 0; + /* dax pmd mappings are broken wrt gup and fork */ + if (!IS_ENABLED(CONFIG_FS_DAX_PMD)) + return VM_FAULT_FALLBACK; + /* Fall back to PTEs if we're going to COW */ if (write && !(vma->vm_flags & VM_SHARED)) return VM_FAULT_FALLBACK; @@ -622,6 +633,13 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR)) goto fallback; + /* + * TODO: teach vmf_insert_pfn_pmd() to support + * 'pte_special' for pmds + */ + if (pfn_valid(pfn)) + goto fallback; + if (buffer_unwritten(&bh) || buffer_new(&bh)) { int i; for (i = 0; i < PTRS_PER_PMD; i++) diff --git a/fs/dcache.c b/fs/dcache.c index 5c33aeb0f68f..8d38cd07b207 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1734,7 +1734,7 @@ static unsigned d_flags_for_inode(struct inode *inode) } if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { - if (unlikely(inode->i_op->follow_link)) { + if (unlikely(inode->i_op->get_link)) { add_flags = DCACHE_SYMLINK_TYPE; goto type_determined; } @@ -3303,18 +3303,18 @@ out: * @new_dentry: new dentry * @old_dentry: old dentry * - * Returns 1 if new_dentry is a subdirectory of the parent (at any depth). - * Returns 0 otherwise. + * Returns true if new_dentry is a subdirectory of the parent (at any depth). + * Returns false otherwise. * Caller must ensure that "new_dentry" is pinned before calling is_subdir() */ -int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) +bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { - int result; + bool result; unsigned seq; if (new_dentry == old_dentry) - return 1; + return true; do { /* for restarting inner loop in case of seq retry */ @@ -3325,9 +3325,9 @@ int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) */ rcu_read_lock(); if (d_ancestor(old_dentry, new_dentry)) - result = 1; + result = true; else - result = 0; + result = false; rcu_read_unlock(); } while (read_seqretry(&rename_lock, seq)); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 5d8f35f1382a..b7fcc0de0b2f 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -271,8 +271,12 @@ static struct dentry *start_creating(const char *name, struct dentry *parent) dput(dentry); dentry = ERR_PTR(-EEXIST); } - if (IS_ERR(dentry)) + + if (IS_ERR(dentry)) { mutex_unlock(&d_inode(parent)->i_mutex); + simple_release_fs(&debugfs_mount, &debugfs_mount_count); + } + return dentry; } diff --git a/fs/direct-io.c b/fs/direct-io.c index 3ae0e0427191..602e8441bc0f 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -109,6 +109,8 @@ struct dio_submit { struct dio { int flags; /* doesn't change */ int rw; + blk_qc_t bio_cookie; + struct block_device *bio_bdev; struct inode *inode; loff_t i_size; /* i_size when submitted */ dio_iodone_t *end_io; /* IO completion function */ @@ -361,7 +363,7 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, /* * bio_alloc() is guaranteed to return a bio when called with - * __GFP_WAIT and we request a valid number of vectors. + * __GFP_RECLAIM and we request a valid number of vectors. */ bio = bio_alloc(GFP_KERNEL, nr_vecs); @@ -397,11 +399,14 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) if (dio->is_async && dio->rw == READ && dio->should_dirty) bio_set_pages_dirty(bio); - if (sdio->submit_io) + dio->bio_bdev = bio->bi_bdev; + + if (sdio->submit_io) { sdio->submit_io(dio->rw, bio, dio->inode, sdio->logical_offset_in_bio); - else - submit_bio(dio->rw, bio); + dio->bio_cookie = BLK_QC_T_NONE; + } else + dio->bio_cookie = submit_bio(dio->rw, bio); sdio->bio = NULL; sdio->boundary = 0; @@ -440,7 +445,8 @@ static struct bio *dio_await_one(struct dio *dio) __set_current_state(TASK_UNINTERRUPTIBLE); dio->waiter = current; spin_unlock_irqrestore(&dio->bio_lock, flags); - io_schedule(); + if (!blk_poll(bdev_get_queue(dio->bio_bdev), dio->bio_cookie)) + io_schedule(); /* wake up sets us TASK_RUNNING */ spin_lock_irqsave(&dio->bio_lock, flags); dio->waiter = NULL; @@ -1163,6 +1169,16 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, } } + /* Once we sampled i_size check for reads beyond EOF */ + dio->i_size = i_size_read(inode); + if (iov_iter_rw(iter) == READ && offset >= dio->i_size) { + if (dio->flags & DIO_LOCKING) + mutex_unlock(&inode->i_mutex); + kmem_cache_free(dio_cache, dio); + retval = 0; + goto out; + } + /* * For file extending writes updating i_size before data writeouts * complete can expose uninitialized blocks in dumb filesystems. @@ -1216,7 +1232,6 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, sdio.next_block_for_io = -1; dio->iocb = iocb; - dio->i_size = i_size_read(inode); spin_lock_init(&dio->bio_lock); dio->refcount = 1; diff --git a/fs/dlm/config.c b/fs/dlm/config.c index d521bddf876d..8e294fbbac39 100644 --- a/fs/dlm/config.c +++ b/fs/dlm/config.c @@ -61,35 +61,8 @@ static struct config_item *make_node(struct config_group *, const char *); static void drop_node(struct config_group *, struct config_item *); static void release_node(struct config_item *); -static ssize_t show_cluster(struct config_item *i, struct configfs_attribute *a, - char *buf); -static ssize_t store_cluster(struct config_item *i, - struct configfs_attribute *a, - const char *buf, size_t len); -static ssize_t show_comm(struct config_item *i, struct configfs_attribute *a, - char *buf); -static ssize_t store_comm(struct config_item *i, struct configfs_attribute *a, - const char *buf, size_t len); -static ssize_t show_node(struct config_item *i, struct configfs_attribute *a, - char *buf); -static ssize_t store_node(struct config_item *i, struct configfs_attribute *a, - const char *buf, size_t len); - -static ssize_t comm_nodeid_read(struct dlm_comm *cm, char *buf); -static ssize_t comm_nodeid_write(struct dlm_comm *cm, const char *buf, - size_t len); -static ssize_t comm_local_read(struct dlm_comm *cm, char *buf); -static ssize_t comm_local_write(struct dlm_comm *cm, const char *buf, - size_t len); -static ssize_t comm_addr_write(struct dlm_comm *cm, const char *buf, - size_t len); -static ssize_t comm_addr_list_read(struct dlm_comm *cm, char *buf); -static ssize_t node_nodeid_read(struct dlm_node *nd, char *buf); -static ssize_t node_nodeid_write(struct dlm_node *nd, const char *buf, - size_t len); -static ssize_t node_weight_read(struct dlm_node *nd, char *buf); -static ssize_t node_weight_write(struct dlm_node *nd, const char *buf, - size_t len); +static struct configfs_attribute *comm_attrs[]; +static struct configfs_attribute *node_attrs[]; struct dlm_cluster { struct config_group group; @@ -108,6 +81,12 @@ struct dlm_cluster { char cl_cluster_name[DLM_LOCKSPACE_LEN]; }; +static struct dlm_cluster *config_item_to_cluster(struct config_item *i) +{ + return i ? container_of(to_config_group(i), struct dlm_cluster, group) : + NULL; +} + enum { CLUSTER_ATTR_TCP_PORT = 0, CLUSTER_ATTR_BUFFER_SIZE, @@ -124,33 +103,24 @@ enum { CLUSTER_ATTR_CLUSTER_NAME, }; -struct cluster_attribute { - struct configfs_attribute attr; - ssize_t (*show)(struct dlm_cluster *, char *); - ssize_t (*store)(struct dlm_cluster *, const char *, size_t); -}; - -static ssize_t cluster_cluster_name_read(struct dlm_cluster *cl, char *buf) +static ssize_t cluster_cluster_name_show(struct config_item *item, char *buf) { + struct dlm_cluster *cl = config_item_to_cluster(item); return sprintf(buf, "%s\n", cl->cl_cluster_name); } -static ssize_t cluster_cluster_name_write(struct dlm_cluster *cl, +static ssize_t cluster_cluster_name_store(struct config_item *item, const char *buf, size_t len) { + struct dlm_cluster *cl = config_item_to_cluster(item); + strlcpy(dlm_config.ci_cluster_name, buf, sizeof(dlm_config.ci_cluster_name)); strlcpy(cl->cl_cluster_name, buf, sizeof(cl->cl_cluster_name)); return len; } -static struct cluster_attribute cluster_attr_cluster_name = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "cluster_name", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = cluster_cluster_name_read, - .store = cluster_cluster_name_write, -}; +CONFIGFS_ATTR(cluster_, cluster_name); static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field, int *info_field, int check_zero, @@ -175,17 +145,19 @@ static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field, } #define CLUSTER_ATTR(name, check_zero) \ -static ssize_t name##_write(struct dlm_cluster *cl, const char *buf, size_t len) \ +static ssize_t cluster_##name##_store(struct config_item *item, \ + const char *buf, size_t len) \ { \ + struct dlm_cluster *cl = config_item_to_cluster(item); \ return cluster_set(cl, &cl->cl_##name, &dlm_config.ci_##name, \ check_zero, buf, len); \ } \ -static ssize_t name##_read(struct dlm_cluster *cl, char *buf) \ +static ssize_t cluster_##name##_show(struct config_item *item, char *buf) \ { \ + struct dlm_cluster *cl = config_item_to_cluster(item); \ return snprintf(buf, PAGE_SIZE, "%u\n", cl->cl_##name); \ } \ -static struct cluster_attribute cluster_attr_##name = \ -__CONFIGFS_ATTR(name, 0644, name##_read, name##_write) +CONFIGFS_ATTR(cluster_, name); CLUSTER_ATTR(tcp_port, 1); CLUSTER_ATTR(buffer_size, 1); @@ -201,19 +173,19 @@ CLUSTER_ATTR(new_rsb_count, 0); CLUSTER_ATTR(recover_callbacks, 0); static struct configfs_attribute *cluster_attrs[] = { - [CLUSTER_ATTR_TCP_PORT] = &cluster_attr_tcp_port.attr, - [CLUSTER_ATTR_BUFFER_SIZE] = &cluster_attr_buffer_size.attr, - [CLUSTER_ATTR_RSBTBL_SIZE] = &cluster_attr_rsbtbl_size.attr, - [CLUSTER_ATTR_RECOVER_TIMER] = &cluster_attr_recover_timer.attr, - [CLUSTER_ATTR_TOSS_SECS] = &cluster_attr_toss_secs.attr, - [CLUSTER_ATTR_SCAN_SECS] = &cluster_attr_scan_secs.attr, - [CLUSTER_ATTR_LOG_DEBUG] = &cluster_attr_log_debug.attr, - [CLUSTER_ATTR_PROTOCOL] = &cluster_attr_protocol.attr, - [CLUSTER_ATTR_TIMEWARN_CS] = &cluster_attr_timewarn_cs.attr, - [CLUSTER_ATTR_WAITWARN_US] = &cluster_attr_waitwarn_us.attr, - [CLUSTER_ATTR_NEW_RSB_COUNT] = &cluster_attr_new_rsb_count.attr, - [CLUSTER_ATTR_RECOVER_CALLBACKS] = &cluster_attr_recover_callbacks.attr, - [CLUSTER_ATTR_CLUSTER_NAME] = &cluster_attr_cluster_name.attr, + [CLUSTER_ATTR_TCP_PORT] = &cluster_attr_tcp_port, + [CLUSTER_ATTR_BUFFER_SIZE] = &cluster_attr_buffer_size, + [CLUSTER_ATTR_RSBTBL_SIZE] = &cluster_attr_rsbtbl_size, + [CLUSTER_ATTR_RECOVER_TIMER] = &cluster_attr_recover_timer, + [CLUSTER_ATTR_TOSS_SECS] = &cluster_attr_toss_secs, + [CLUSTER_ATTR_SCAN_SECS] = &cluster_attr_scan_secs, + [CLUSTER_ATTR_LOG_DEBUG] = &cluster_attr_log_debug, + [CLUSTER_ATTR_PROTOCOL] = &cluster_attr_protocol, + [CLUSTER_ATTR_TIMEWARN_CS] = &cluster_attr_timewarn_cs, + [CLUSTER_ATTR_WAITWARN_US] = &cluster_attr_waitwarn_us, + [CLUSTER_ATTR_NEW_RSB_COUNT] = &cluster_attr_new_rsb_count, + [CLUSTER_ATTR_RECOVER_CALLBACKS] = &cluster_attr_recover_callbacks, + [CLUSTER_ATTR_CLUSTER_NAME] = &cluster_attr_cluster_name, NULL, }; @@ -224,83 +196,11 @@ enum { COMM_ATTR_ADDR_LIST, }; -struct comm_attribute { - struct configfs_attribute attr; - ssize_t (*show)(struct dlm_comm *, char *); - ssize_t (*store)(struct dlm_comm *, const char *, size_t); -}; - -static struct comm_attribute comm_attr_nodeid = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "nodeid", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = comm_nodeid_read, - .store = comm_nodeid_write, -}; - -static struct comm_attribute comm_attr_local = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "local", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = comm_local_read, - .store = comm_local_write, -}; - -static struct comm_attribute comm_attr_addr = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "addr", - .ca_mode = S_IWUSR }, - .store = comm_addr_write, -}; - -static struct comm_attribute comm_attr_addr_list = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "addr_list", - .ca_mode = S_IRUGO }, - .show = comm_addr_list_read, -}; - -static struct configfs_attribute *comm_attrs[] = { - [COMM_ATTR_NODEID] = &comm_attr_nodeid.attr, - [COMM_ATTR_LOCAL] = &comm_attr_local.attr, - [COMM_ATTR_ADDR] = &comm_attr_addr.attr, - [COMM_ATTR_ADDR_LIST] = &comm_attr_addr_list.attr, - NULL, -}; - enum { NODE_ATTR_NODEID = 0, NODE_ATTR_WEIGHT, }; -struct node_attribute { - struct configfs_attribute attr; - ssize_t (*show)(struct dlm_node *, char *); - ssize_t (*store)(struct dlm_node *, const char *, size_t); -}; - -static struct node_attribute node_attr_nodeid = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "nodeid", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = node_nodeid_read, - .store = node_nodeid_write, -}; - -static struct node_attribute node_attr_weight = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "weight", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = node_weight_read, - .store = node_weight_write, -}; - -static struct configfs_attribute *node_attrs[] = { - [NODE_ATTR_NODEID] = &node_attr_nodeid.attr, - [NODE_ATTR_WEIGHT] = &node_attr_weight.attr, - NULL, -}; - struct dlm_clusters { struct configfs_subsystem subsys; }; @@ -349,8 +249,6 @@ static struct configfs_group_operations clusters_ops = { static struct configfs_item_operations cluster_ops = { .release = release_cluster, - .show_attribute = show_cluster, - .store_attribute = store_cluster, }; static struct configfs_group_operations spaces_ops = { @@ -369,8 +267,6 @@ static struct configfs_group_operations comms_ops = { static struct configfs_item_operations comm_ops = { .release = release_comm, - .show_attribute = show_comm, - .store_attribute = store_comm, }; static struct configfs_group_operations nodes_ops = { @@ -380,8 +276,6 @@ static struct configfs_group_operations nodes_ops = { static struct configfs_item_operations node_ops = { .release = release_node, - .show_attribute = show_node, - .store_attribute = store_node, }; static struct config_item_type clusters_type = { @@ -427,12 +321,6 @@ static struct config_item_type node_type = { .ct_owner = THIS_MODULE, }; -static struct dlm_cluster *config_item_to_cluster(struct config_item *i) -{ - return i ? container_of(to_config_group(i), struct dlm_cluster, group) : - NULL; -} - static struct dlm_space *config_item_to_space(struct config_item *i) { return i ? container_of(to_config_group(i), struct dlm_space, group) : @@ -687,66 +575,30 @@ void dlm_config_exit(void) * Functions for user space to read/write attributes */ -static ssize_t show_cluster(struct config_item *i, struct configfs_attribute *a, - char *buf) -{ - struct dlm_cluster *cl = config_item_to_cluster(i); - struct cluster_attribute *cla = - container_of(a, struct cluster_attribute, attr); - return cla->show ? cla->show(cl, buf) : 0; -} - -static ssize_t store_cluster(struct config_item *i, - struct configfs_attribute *a, - const char *buf, size_t len) +static ssize_t comm_nodeid_show(struct config_item *item, char *buf) { - struct dlm_cluster *cl = config_item_to_cluster(i); - struct cluster_attribute *cla = - container_of(a, struct cluster_attribute, attr); - return cla->store ? cla->store(cl, buf, len) : -EINVAL; -} - -static ssize_t show_comm(struct config_item *i, struct configfs_attribute *a, - char *buf) -{ - struct dlm_comm *cm = config_item_to_comm(i); - struct comm_attribute *cma = - container_of(a, struct comm_attribute, attr); - return cma->show ? cma->show(cm, buf) : 0; -} - -static ssize_t store_comm(struct config_item *i, struct configfs_attribute *a, - const char *buf, size_t len) -{ - struct dlm_comm *cm = config_item_to_comm(i); - struct comm_attribute *cma = - container_of(a, struct comm_attribute, attr); - return cma->store ? cma->store(cm, buf, len) : -EINVAL; + return sprintf(buf, "%d\n", config_item_to_comm(item)->nodeid); } -static ssize_t comm_nodeid_read(struct dlm_comm *cm, char *buf) -{ - return sprintf(buf, "%d\n", cm->nodeid); -} - -static ssize_t comm_nodeid_write(struct dlm_comm *cm, const char *buf, +static ssize_t comm_nodeid_store(struct config_item *item, const char *buf, size_t len) { - int rc = kstrtoint(buf, 0, &cm->nodeid); + int rc = kstrtoint(buf, 0, &config_item_to_comm(item)->nodeid); if (rc) return rc; return len; } -static ssize_t comm_local_read(struct dlm_comm *cm, char *buf) +static ssize_t comm_local_show(struct config_item *item, char *buf) { - return sprintf(buf, "%d\n", cm->local); + return sprintf(buf, "%d\n", config_item_to_comm(item)->local); } -static ssize_t comm_local_write(struct dlm_comm *cm, const char *buf, +static ssize_t comm_local_store(struct config_item *item, const char *buf, size_t len) { + struct dlm_comm *cm = config_item_to_comm(item); int rc = kstrtoint(buf, 0, &cm->local); if (rc) @@ -756,8 +608,10 @@ static ssize_t comm_local_write(struct dlm_comm *cm, const char *buf, return len; } -static ssize_t comm_addr_write(struct dlm_comm *cm, const char *buf, size_t len) +static ssize_t comm_addr_store(struct config_item *item, const char *buf, + size_t len) { + struct dlm_comm *cm = config_item_to_comm(item); struct sockaddr_storage *addr; int rv; @@ -783,8 +637,9 @@ static ssize_t comm_addr_write(struct dlm_comm *cm, const char *buf, size_t len) return len; } -static ssize_t comm_addr_list_read(struct dlm_comm *cm, char *buf) +static ssize_t comm_addr_list_show(struct config_item *item, char *buf) { + struct dlm_comm *cm = config_item_to_comm(item); ssize_t s; ssize_t allowance; int i; @@ -827,32 +682,28 @@ static ssize_t comm_addr_list_read(struct dlm_comm *cm, char *buf) return 4096 - allowance; } -static ssize_t show_node(struct config_item *i, struct configfs_attribute *a, - char *buf) -{ - struct dlm_node *nd = config_item_to_node(i); - struct node_attribute *nda = - container_of(a, struct node_attribute, attr); - return nda->show ? nda->show(nd, buf) : 0; -} +CONFIGFS_ATTR(comm_, nodeid); +CONFIGFS_ATTR(comm_, local); +CONFIGFS_ATTR_WO(comm_, addr); +CONFIGFS_ATTR_RO(comm_, addr_list); -static ssize_t store_node(struct config_item *i, struct configfs_attribute *a, - const char *buf, size_t len) -{ - struct dlm_node *nd = config_item_to_node(i); - struct node_attribute *nda = - container_of(a, struct node_attribute, attr); - return nda->store ? nda->store(nd, buf, len) : -EINVAL; -} +static struct configfs_attribute *comm_attrs[] = { + [COMM_ATTR_NODEID] = &comm_attr_nodeid, + [COMM_ATTR_LOCAL] = &comm_attr_local, + [COMM_ATTR_ADDR] = &comm_attr_addr, + [COMM_ATTR_ADDR_LIST] = &comm_attr_addr_list, + NULL, +}; -static ssize_t node_nodeid_read(struct dlm_node *nd, char *buf) +static ssize_t node_nodeid_show(struct config_item *item, char *buf) { - return sprintf(buf, "%d\n", nd->nodeid); + return sprintf(buf, "%d\n", config_item_to_node(item)->nodeid); } -static ssize_t node_nodeid_write(struct dlm_node *nd, const char *buf, +static ssize_t node_nodeid_store(struct config_item *item, const char *buf, size_t len) { + struct dlm_node *nd = config_item_to_node(item); uint32_t seq = 0; int rc = kstrtoint(buf, 0, &nd->nodeid); @@ -863,21 +714,30 @@ static ssize_t node_nodeid_write(struct dlm_node *nd, const char *buf, return len; } -static ssize_t node_weight_read(struct dlm_node *nd, char *buf) +static ssize_t node_weight_show(struct config_item *item, char *buf) { - return sprintf(buf, "%d\n", nd->weight); + return sprintf(buf, "%d\n", config_item_to_node(item)->weight); } -static ssize_t node_weight_write(struct dlm_node *nd, const char *buf, +static ssize_t node_weight_store(struct config_item *item, const char *buf, size_t len) { - int rc = kstrtoint(buf, 0, &nd->weight); + int rc = kstrtoint(buf, 0, &config_item_to_node(item)->weight); if (rc) return rc; return len; } +CONFIGFS_ATTR(node_, nodeid); +CONFIGFS_ATTR(node_, weight); + +static struct configfs_attribute *node_attrs[] = { + [NODE_ATTR_NODEID] = &node_attr_nodeid, + [NODE_ATTR_WEIGHT] = &node_attr_weight, + NULL, +}; + /* * Functions for the dlm to get the info that's been configured */ diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 87e9d796cf7d..3a37bd3f9637 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -421,7 +421,7 @@ static void lowcomms_write_space(struct sock *sk) if (test_and_clear_bit(CF_APP_LIMITED, &con->flags)) { con->sock->sk->sk_write_pending--; - clear_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags); + clear_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags); } if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags)) @@ -1448,7 +1448,7 @@ static void send_to_sock(struct connection *con) msg_flags); if (ret == -EAGAIN || ret == 0) { if (ret == -EAGAIN && - test_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags) && + test_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags) && !test_and_set_bit(CF_APP_LIMITED, &con->flags)) { /* Notify TCP that we're limited by the * application window size. diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 173b3873a4f4..1925d6d222b8 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -515,14 +515,9 @@ static ssize_t device_write(struct file *file, const char __user *buf, if (count > sizeof(struct dlm_write_request) + DLM_RESNAME_MAXLEN) return -EINVAL; - kbuf = kzalloc(count + 1, GFP_NOFS); - if (!kbuf) - return -ENOMEM; - - if (copy_from_user(kbuf, buf, count)) { - error = -EFAULT; - goto out_free; - } + kbuf = memdup_user_nul(buf, count); + if (!IS_ERR(kbuf)) + return PTR_ERR(kbuf); if (check_version(kbuf)) { error = -EBADE; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index e2e47ba5d313..040aa879d634 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -282,9 +282,7 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry, if (rc) { ecryptfs_do_unlink(directory_inode, ecryptfs_dentry, ecryptfs_inode); - make_bad_inode(ecryptfs_inode); - unlock_new_inode(ecryptfs_inode); - iput(ecryptfs_inode); + iget_failed(ecryptfs_inode); goto out; } unlock_new_inode(ecryptfs_inode); @@ -674,16 +672,24 @@ out: return rc ? ERR_PTR(rc) : buf; } -static const char *ecryptfs_follow_link(struct dentry *dentry, void **cookie) +static const char *ecryptfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { size_t len; - char *buf = ecryptfs_readlink_lower(dentry, &len); + char *buf; + + if (!dentry) + return ERR_PTR(-ECHILD); + + buf = ecryptfs_readlink_lower(dentry, &len); if (IS_ERR(buf)) return buf; fsstack_copy_attr_atime(d_inode(dentry), d_inode(ecryptfs_dentry_to_lower(dentry))); buf[len] = '\0'; - return *cookie = buf; + set_delayed_call(done, kfree_link, buf); + return buf; } /** @@ -1095,8 +1101,7 @@ out: const struct inode_operations ecryptfs_symlink_iops = { .readlink = generic_readlink, - .follow_link = ecryptfs_follow_link, - .put_link = kfree_put_link, + .get_link = ecryptfs_get_link, .permission = ecryptfs_permission, .setattr = ecryptfs_setattr, .getattr = ecryptfs_getattr_link, diff --git a/fs/efs/inode.c b/fs/efs/inode.c index 079d20306ee1..cdf0872382af 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -151,6 +151,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &efs_symlink_aops; break; case S_IFCHR: diff --git a/fs/efs/symlink.c b/fs/efs/symlink.c index 75117d0dac2b..4870cc82deb0 100644 --- a/fs/efs/symlink.c +++ b/fs/efs/symlink.c @@ -13,7 +13,7 @@ static int efs_symlink_readpage(struct file *file, struct page *page) { - char *link = kmap(page); + char *link = page_address(page); struct buffer_head * bh; struct inode * inode = page->mapping->host; efs_block_t size = inode->i_size; @@ -39,12 +39,10 @@ static int efs_symlink_readpage(struct file *file, struct page *page) } link[size] = '\0'; SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; fail: SetPageError(page); - kunmap(page); unlock_page(page); return err; } diff --git a/fs/exec.c b/fs/exec.c index b06623a9347f..828ec5f07de0 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -119,7 +119,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) int error = PTR_ERR(tmp); static const struct open_flags uselib_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, - .acc_mode = MAY_READ | MAY_EXEC | MAY_OPEN, + .acc_mode = MAY_READ | MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, }; @@ -763,7 +763,7 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) int err; struct open_flags open_exec_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, - .acc_mode = MAY_EXEC | MAY_OPEN, + .acc_mode = MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, }; diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 73c64daa0f55..9eaf595aeaf8 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -592,10 +592,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) } unlock_page(page); } - if (PageDirty(page) || PageWriteback(page)) - *uptodate = true; - else - *uptodate = PageUptodate(page); + *uptodate = PageUptodate(page); EXOFS_DBGMSG2("index=0x%lx uptodate=%d\n", index, *uptodate); return page; } else { @@ -1227,6 +1224,7 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino) inode->i_link = (char *)oi->i_data; } else { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &exofs_aops; } } else { diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c index 09a6bb1ad63c..c20d77df2679 100644 --- a/fs/exofs/namei.c +++ b/fs/exofs/namei.c @@ -80,9 +80,6 @@ static int exofs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, struct inode *inode; int err; - if (!new_valid_dev(rdev)) - return -EINVAL; - inode = exofs_new_inode(dir, mode); err = PTR_ERR(inode); if (!IS_ERR(inode)) { @@ -114,6 +111,7 @@ static int exofs_symlink(struct inode *dir, struct dentry *dentry, if (l > sizeof(oi->i_data)) { /* slow symlink */ inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &exofs_aops; memset(oi->i_data, 0, sizeof(oi->i_data)); diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 8d15febd0aa3..4c69c94cafd8 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -684,6 +684,9 @@ struct ext2_inode_info { struct rw_semaphore xattr_sem; #endif rwlock_t i_meta_lock; +#ifdef CONFIG_FS_DAX + struct rw_semaphore dax_sem; +#endif /* * truncate_mutex is for serialising ext2_truncate() against @@ -699,6 +702,14 @@ struct ext2_inode_info { #endif }; +#ifdef CONFIG_FS_DAX +#define dax_sem_down_write(ext2_inode) down_write(&(ext2_inode)->dax_sem) +#define dax_sem_up_write(ext2_inode) up_write(&(ext2_inode)->dax_sem) +#else +#define dax_sem_down_write(ext2_inode) +#define dax_sem_up_write(ext2_inode) +#endif + /* * Inode dynamic state flags */ diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 1982c3f11aec..11a42c5a09ae 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -27,27 +27,103 @@ #include "acl.h" #ifdef CONFIG_FS_DAX +/* + * The lock ordering for ext2 DAX fault paths is: + * + * mmap_sem (MM) + * sb_start_pagefault (vfs, freeze) + * ext2_inode_info->dax_sem + * address_space->i_mmap_rwsem or page_lock (mutually exclusive in DAX) + * ext2_inode_info->truncate_mutex + * + * The default page_lock and i_size verification done by non-DAX fault paths + * is sufficient because ext2 doesn't support hole punching. + */ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { - return dax_fault(vma, vmf, ext2_get_block, NULL); + struct inode *inode = file_inode(vma->vm_file); + struct ext2_inode_info *ei = EXT2_I(inode); + int ret; + + if (vmf->flags & FAULT_FLAG_WRITE) { + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + } + down_read(&ei->dax_sem); + + ret = __dax_fault(vma, vmf, ext2_get_block, NULL); + + up_read(&ei->dax_sem); + if (vmf->flags & FAULT_FLAG_WRITE) + sb_end_pagefault(inode->i_sb); + return ret; } static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags) { - return dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL); + struct inode *inode = file_inode(vma->vm_file); + struct ext2_inode_info *ei = EXT2_I(inode); + int ret; + + if (flags & FAULT_FLAG_WRITE) { + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + } + down_read(&ei->dax_sem); + + ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL); + + up_read(&ei->dax_sem); + if (flags & FAULT_FLAG_WRITE) + sb_end_pagefault(inode->i_sb); + return ret; } static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { - return dax_mkwrite(vma, vmf, ext2_get_block, NULL); + struct inode *inode = file_inode(vma->vm_file); + struct ext2_inode_info *ei = EXT2_I(inode); + int ret; + + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + down_read(&ei->dax_sem); + + ret = __dax_mkwrite(vma, vmf, ext2_get_block, NULL); + + up_read(&ei->dax_sem); + sb_end_pagefault(inode->i_sb); + return ret; +} + +static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma, + struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vma->vm_file); + struct ext2_inode_info *ei = EXT2_I(inode); + int ret = VM_FAULT_NOPAGE; + loff_t size; + + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + down_read(&ei->dax_sem); + + /* check that the faulting page hasn't raced with truncate */ + size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (vmf->pgoff >= size) + ret = VM_FAULT_SIGBUS; + + up_read(&ei->dax_sem); + sb_end_pagefault(inode->i_sb); + return ret; } static const struct vm_operations_struct ext2_dax_vm_ops = { .fault = ext2_dax_fault, .pmd_fault = ext2_dax_pmd_fault, .page_mkwrite = ext2_dax_mkwrite, - .pfn_mkwrite = dax_pfn_mkwrite, + .pfn_mkwrite = ext2_dax_pfn_mkwrite, }; static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index c60a248c640c..338eefda70c6 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1085,6 +1085,7 @@ static void ext2_free_branches(struct inode *inode, __le32 *p, __le32 *q, int de ext2_free_data(inode, p, q); } +/* dax_sem must be held when calling this function */ static void __ext2_truncate_blocks(struct inode *inode, loff_t offset) { __le32 *i_data = EXT2_I(inode)->i_data; @@ -1100,6 +1101,10 @@ static void __ext2_truncate_blocks(struct inode *inode, loff_t offset) blocksize = inode->i_sb->s_blocksize; iblock = (offset + blocksize-1) >> EXT2_BLOCK_SIZE_BITS(inode->i_sb); +#ifdef CONFIG_FS_DAX + WARN_ON(!rwsem_is_locked(&ei->dax_sem)); +#endif + n = ext2_block_to_path(inode, iblock, offsets, NULL); if (n == 0) return; @@ -1185,7 +1190,10 @@ static void ext2_truncate_blocks(struct inode *inode, loff_t offset) return; if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) return; + + dax_sem_down_write(EXT2_I(inode)); __ext2_truncate_blocks(inode, offset); + dax_sem_up_write(EXT2_I(inode)); } static int ext2_setsize(struct inode *inode, loff_t newsize) @@ -1213,8 +1221,10 @@ static int ext2_setsize(struct inode *inode, loff_t newsize) if (error) return error; + dax_sem_down_write(EXT2_I(inode)); truncate_setsize(inode, newsize); __ext2_truncate_blocks(inode, newsize); + dax_sem_up_write(EXT2_I(inode)); inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; if (inode_needs_sync(inode)) { @@ -1410,6 +1420,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) sizeof(ei->i_data) - 1); } else { inode->i_op = &ext2_symlink_inode_operations; + inode_nohighmem(inode); if (test_opt(inode->i_sb, NOBH)) inode->i_mapping->a_ops = &ext2_nobh_aops; else diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index b4841e3066a5..7a2be8f7f3c3 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -143,9 +143,6 @@ static int ext2_mknod (struct inode * dir, struct dentry *dentry, umode_t mode, struct inode * inode; int err; - if (!new_valid_dev(rdev)) - return -EINVAL; - err = dquot_initialize(dir); if (err) return err; @@ -186,6 +183,7 @@ static int ext2_symlink (struct inode * dir, struct dentry * dentry, if (l > sizeof (EXT2_I(inode)->i_data)) { /* slow symlink */ inode->i_op = &ext2_symlink_inode_operations; + inode_nohighmem(inode); if (test_opt(inode->i_sb, NOBH)) inode->i_mapping->a_ops = &ext2_nobh_aops; else diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 900e19cf9ef6..748d35afc902 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -192,6 +192,9 @@ static void init_once(void *foo) init_rwsem(&ei->xattr_sem); #endif mutex_init(&ei->truncate_mutex); +#ifdef CONFIG_FS_DAX + init_rwsem(&ei->dax_sem); +#endif inode_init_once(&ei->vfs_inode); } @@ -566,6 +569,8 @@ static int parse_options(char *options, struct super_block *sb) /* Fall through */ case Opt_dax: #ifdef CONFIG_FS_DAX + ext2_msg(sb, KERN_WARNING, + "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); set_opt(sbi->s_mount_opt, DAX); #else ext2_msg(sb, KERN_INFO, "dax option not supported"); diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c index ae17179f3810..3495d8ae4b33 100644 --- a/fs/ext2/symlink.c +++ b/fs/ext2/symlink.c @@ -22,8 +22,7 @@ const struct inode_operations ext2_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = ext2_setattr, #ifdef CONFIG_EXT2_FS_XATTR .setxattr = generic_setxattr, @@ -35,7 +34,7 @@ const struct inode_operations ext2_symlink_inode_operations = { const struct inode_operations ext2_fast_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = ext2_setattr, #ifdef CONFIG_EXT2_FS_XATTR .setxattr = generic_setxattr, diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 0b6bfd3a398b..f57a7aba32eb 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -77,10 +77,8 @@ printk("\n"); \ } while (0) # define ea_bdebug(bh, f...) do { \ - char b[BDEVNAME_SIZE]; \ - printk(KERN_DEBUG "block %s:%lu: ", \ - bdevname(bh->b_bdev, b), \ - (unsigned long) bh->b_blocknr); \ + printk(KERN_DEBUG "block %pg:%lu: ", \ + bh->b_bdev, (unsigned long) bh->b_blocknr); \ printk(f); \ printk("\n"); \ } while (0) @@ -292,17 +290,21 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_list", const struct xattr_handler *handler = ext2_xattr_handler(entry->e_name_index); - if (handler) { - size_t size = handler->list(dentry, buffer, rest, - entry->e_name, - entry->e_name_len, - handler->flags); + if (handler && (!handler->list || handler->list(dentry))) { + const char *prefix = handler->prefix ?: handler->name; + size_t prefix_len = strlen(prefix); + size_t size = prefix_len + entry->e_name_len + 1; + if (buffer) { if (size > rest) { error = -ERANGE; goto cleanup; } - buffer += size; + memcpy(buffer, prefix, prefix_len); + buffer += prefix_len; + memcpy(buffer, entry->e_name, entry->e_name_len); + buffer += entry->e_name_len; + *buffer++ = 0; } rest -= size; } diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c index 702fc6840246..ba97f243b050 100644 --- a/fs/ext2/xattr_security.c +++ b/fs/ext2/xattr_security.c @@ -7,37 +7,20 @@ #include <linux/security.h> #include "xattr.h" -static size_t -ext2_xattr_security_list(struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len, int type) -{ - const int prefix_len = XATTR_SECURITY_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_SECURITY_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - static int -ext2_xattr_security_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +ext2_xattr_security_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name, buffer, size); } static int -ext2_xattr_security_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +ext2_xattr_security_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name, value, size, flags); } @@ -68,7 +51,6 @@ ext2_init_security(struct inode *inode, struct inode *dir, const struct xattr_handler ext2_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = ext2_xattr_security_list, .get = ext2_xattr_security_get, .set = ext2_xattr_security_set, }; diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c index 42b6e9874bcc..2c94d1930626 100644 --- a/fs/ext2/xattr_trusted.c +++ b/fs/ext2/xattr_trusted.c @@ -8,40 +8,26 @@ #include "ext2.h" #include "xattr.h" -static size_t -ext2_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len, int type) +static bool +ext2_xattr_trusted_list(struct dentry *dentry) { - const int prefix_len = XATTR_TRUSTED_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!capable(CAP_SYS_ADMIN)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; + return capable(CAP_SYS_ADMIN); } static int -ext2_xattr_trusted_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +ext2_xattr_trusted_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name, buffer, size); } static int -ext2_xattr_trusted_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +ext2_xattr_trusted_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name, value, size, flags); } diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c index ecdc4605192c..72a2a96d677f 100644 --- a/fs/ext2/xattr_user.c +++ b/fs/ext2/xattr_user.c @@ -10,30 +10,17 @@ #include "ext2.h" #include "xattr.h" -static size_t -ext2_xattr_user_list(struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len, int type) +static bool +ext2_xattr_user_list(struct dentry *dentry) { - const size_t prefix_len = XATTR_USER_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!test_opt(dentry->d_sb, XATTR_USER)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_USER_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; + return test_opt(dentry->d_sb, XATTR_USER); } static int -ext2_xattr_user_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +ext2_xattr_user_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; if (!test_opt(dentry->d_sb, XATTR_USER)) return -EOPNOTSUPP; return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_USER, @@ -41,11 +28,10 @@ ext2_xattr_user_get(struct dentry *dentry, const char *name, } static int -ext2_xattr_user_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +ext2_xattr_user_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; if (!test_opt(dentry->d_sb, XATTR_USER)) return -EOPNOTSUPP; diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index af06830bfc00..1a0835073663 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -389,7 +389,7 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) struct ext4_crypto_ctx *ctx; struct page *ciphertext_page = NULL; struct bio *bio; - ext4_lblk_t lblk = ex->ee_block; + ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); ext4_fsblk_t pblk = ext4_ext_pblock(ex); unsigned int len = ext4_ext_get_actual_len(ex); int ret, err = 0; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 750063f7a50c..cc7ca4e87144 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -26,6 +26,7 @@ #include <linux/seqlock.h> #include <linux/mutex.h> #include <linux/timer.h> +#include <linux/version.h> #include <linux/wait.h> #include <linux/blockgroup_lock.h> #include <linux/percpu_counter.h> @@ -727,19 +728,55 @@ struct move_extent { <= (EXT4_GOOD_OLD_INODE_SIZE + \ (einode)->i_extra_isize)) \ +/* + * We use an encoding that preserves the times for extra epoch "00": + * + * extra msb of adjust for signed + * epoch 32-bit 32-bit tv_sec to + * bits time decoded 64-bit tv_sec 64-bit tv_sec valid time range + * 0 0 1 -0x80000000..-0x00000001 0x000000000 1901-12-13..1969-12-31 + * 0 0 0 0x000000000..0x07fffffff 0x000000000 1970-01-01..2038-01-19 + * 0 1 1 0x080000000..0x0ffffffff 0x100000000 2038-01-19..2106-02-07 + * 0 1 0 0x100000000..0x17fffffff 0x100000000 2106-02-07..2174-02-25 + * 1 0 1 0x180000000..0x1ffffffff 0x200000000 2174-02-25..2242-03-16 + * 1 0 0 0x200000000..0x27fffffff 0x200000000 2242-03-16..2310-04-04 + * 1 1 1 0x280000000..0x2ffffffff 0x300000000 2310-04-04..2378-04-22 + * 1 1 0 0x300000000..0x37fffffff 0x300000000 2378-04-22..2446-05-10 + * + * Note that previous versions of the kernel on 64-bit systems would + * incorrectly use extra epoch bits 1,1 for dates between 1901 and + * 1970. e2fsck will correct this, assuming that it is run on the + * affected filesystem before 2242. + */ + static inline __le32 ext4_encode_extra_time(struct timespec *time) { - return cpu_to_le32((sizeof(time->tv_sec) > 4 ? - (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) | - ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK)); + u32 extra = sizeof(time->tv_sec) > 4 ? + ((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK : 0; + return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS)); } static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra) { - if (sizeof(time->tv_sec) > 4) - time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) - << 32; - time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; + if (unlikely(sizeof(time->tv_sec) > 4 && + (extra & cpu_to_le32(EXT4_EPOCH_MASK)))) { +#if LINUX_VERSION_CODE < KERNEL_VERSION(4,20,0) + /* Handle legacy encoding of pre-1970 dates with epoch + * bits 1,1. We assume that by kernel version 4.20, + * everyone will have run fsck over the affected + * filesystems to correct the problem. (This + * backwards compatibility may be removed before this + * time, at the discretion of the ext4 developers.) + */ + u64 extra_bits = le32_to_cpu(extra) & EXT4_EPOCH_MASK; + if (extra_bits == 3 && ((time->tv_sec) & 0x80000000) != 0) + extra_bits = 0; + time->tv_sec += extra_bits << 32; +#else + time->tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32; +#endif + } + time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; } #define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e8d620a484f6..b3bd912df6bf 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3386,7 +3386,7 @@ static int __ext4_block_zero_page_range(handle_t *handle, int err = 0; page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT, - mapping_gfp_mask(mapping) & ~__GFP_FS); + mapping_gfp_constraint(mapping, ~__GFP_FS)); if (!page) return -ENOMEM; @@ -4283,6 +4283,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_op = &ext4_symlink_inode_operations; ext4_set_aops(inode); } + inode_nohighmem(inode); } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { inode->i_op = &ext4_special_inode_operations; @@ -5283,7 +5284,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) !ext4_should_journal_data(inode) && !ext4_nonda_switch(inode->i_sb)) { do { - ret = __block_page_mkwrite(vma, vmf, + ret = block_page_mkwrite(vma, vmf, ext4_da_get_block_prep); } while (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); @@ -5330,7 +5331,7 @@ retry_alloc: ret = VM_FAULT_SIGBUS; goto out; } - ret = __block_page_mkwrite(vma, vmf, get_block); + ret = block_page_mkwrite(vma, vmf, get_block); if (!ret && ext4_should_journal_data(inode)) { if (ext4_walk_page_buffers(handle, page_buffers(page), 0, PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index b4b3c1f91814..61eaf74dca37 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3333,8 +3333,8 @@ ext4_mb_check_group_pa(ext4_fsblk_t goal_block, atomic_inc(&pa->pa_count); return pa; } - cur_distance = abs64(goal_block - cpa->pa_pstart); - new_distance = abs64(goal_block - pa->pa_pstart); + cur_distance = abs(goal_block - cpa->pa_pstart); + new_distance = abs(goal_block - pa->pa_pstart); if (cur_distance <= new_distance) return cpa; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a969ab39f302..f27e0c2598c5 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3132,6 +3132,7 @@ static int ext4_symlink(struct inode *dir, if ((disk_link.len > EXT4_N_BLOCKS * 4)) { if (!encryption_required) inode->i_op = &ext4_symlink_inode_operations; + inode_nohighmem(inode); ext4_set_aops(inode); /* * We cannot call page_symlink() with transaction started diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 17fbe3882b8e..090b3498638e 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -52,9 +52,8 @@ void ext4_exit_pageio(void) */ static void buffer_io_error(struct buffer_head *bh) { - char b[BDEVNAME_SIZE]; - printk_ratelimited(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n", - bdevname(bh->b_bdev, b), + printk_ratelimited(KERN_ERR "Buffer I/O error on device %pg, logical block %llu\n", + bh->b_bdev, (unsigned long long)bh->b_blocknr); } diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index d94af71a4e7f..5dc5e95063de 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -166,7 +166,7 @@ int ext4_mpage_readpages(struct address_space *mapping, page = list_entry(pages->prev, struct page, lru); list_del(&page->lru); if (add_to_page_cache_lru(page, mapping, page->index, - GFP_KERNEL & mapping_gfp_mask(mapping))) + mapping_gfp_constraint(mapping, GFP_KERNEL))) goto next_page; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 04d0f1b33409..c9ab67da6e5a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1061,7 +1061,7 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page, return 0; if (journal) return jbd2_journal_try_to_free_buffers(journal, page, - wait & ~__GFP_WAIT); + wait & ~__GFP_DIRECT_RECLAIM); return try_to_free_buffers(page); } @@ -1664,8 +1664,12 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, } sbi->s_jquota_fmt = m->mount_opt; #endif -#ifndef CONFIG_FS_DAX } else if (token == Opt_dax) { +#ifdef CONFIG_FS_DAX + ext4_msg(sb, KERN_WARNING, + "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); + sbi->s_mount_opt |= m->mount_opt; +#else ext4_msg(sb, KERN_INFO, "dax option not supported"); return -1; #endif diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index abe2401ce405..6f7ee30a89ce 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -23,17 +23,21 @@ #include "xattr.h" #ifdef CONFIG_EXT4_FS_ENCRYPTION -static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cookie) +static const char *ext4_encrypted_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { struct page *cpage = NULL; char *caddr, *paddr = NULL; struct ext4_str cstr, pstr; - struct inode *inode = d_inode(dentry); struct ext4_encrypted_symlink_data *sd; loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1); int res; u32 plen, max_size = inode->i_sb->s_blocksize; + if (!dentry) + return ERR_PTR(-ECHILD); + res = ext4_get_encryption_info(inode); if (res) return ERR_PTR(res); @@ -45,14 +49,14 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook cpage = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(cpage)) return ERR_CAST(cpage); - caddr = kmap(cpage); + caddr = page_address(cpage); caddr[size] = 0; } /* Symlink is encrypted */ sd = (struct ext4_encrypted_symlink_data *)caddr; cstr.name = sd->encrypted_path; - cstr.len = le32_to_cpu(sd->len); + cstr.len = le16_to_cpu(sd->len); if ((cstr.len + sizeof(struct ext4_encrypted_symlink_data) - 1) > max_size) { @@ -75,24 +79,20 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook /* Null-terminate the name */ if (res <= plen) paddr[res] = '\0'; - if (cpage) { - kunmap(cpage); + if (cpage) page_cache_release(cpage); - } - return *cookie = paddr; + set_delayed_call(done, kfree_link, paddr); + return paddr; errout: - if (cpage) { - kunmap(cpage); + if (cpage) page_cache_release(cpage); - } kfree(paddr); return ERR_PTR(res); } const struct inode_operations ext4_encrypted_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = ext4_encrypted_follow_link, - .put_link = kfree_put_link, + .get_link = ext4_encrypted_get_link, .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, @@ -103,8 +103,7 @@ const struct inode_operations ext4_encrypted_symlink_inode_operations = { const struct inode_operations ext4_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, @@ -114,7 +113,7 @@ const struct inode_operations ext4_symlink_inode_operations = { const struct inode_operations ext4_fast_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 1b57c72f4a00..1420a3c614af 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -358,7 +358,7 @@ static int name##_open(struct inode *inode, struct file *file) \ return single_open(file, ext4_seq_##name##_show, PDE_DATA(inode)); \ } \ \ -const struct file_operations ext4_seq_##name##_fops = { \ +static const struct file_operations ext4_seq_##name##_fops = { \ .owner = THIS_MODULE, \ .open = name##_open, \ .read = seq_read, \ diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 984448c6f5f0..a95151e875bd 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -68,10 +68,8 @@ printk("\n"); \ } while (0) # define ea_bdebug(bh, f...) do { \ - char b[BDEVNAME_SIZE]; \ - printk(KERN_DEBUG "block %s:%lu: ", \ - bdevname(bh->b_bdev, b), \ - (unsigned long) bh->b_blocknr); \ + printk(KERN_DEBUG "block %pg:%lu: ", \ + bh->b_bdev, (unsigned long) bh->b_blocknr); \ printk(f); \ printk("\n"); \ } while (0) @@ -404,20 +402,24 @@ ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry, const struct xattr_handler *handler = ext4_xattr_handler(entry->e_name_index); - if (handler) { - size_t size = handler->list(dentry, buffer, rest, - entry->e_name, - entry->e_name_len, - handler->flags); + if (handler && (!handler->list || handler->list(dentry))) { + const char *prefix = handler->prefix ?: handler->name; + size_t prefix_len = strlen(prefix); + size_t size = prefix_len + entry->e_name_len + 1; + if (buffer) { if (size > rest) return -ERANGE; - buffer += size; + memcpy(buffer, prefix, prefix_len); + buffer += prefix_len; + memcpy(buffer, entry->e_name, entry->e_name_len); + buffer += entry->e_name_len; + *buffer++ = 0; } rest -= size; } } - return buffer_size - rest; + return buffer_size - rest; /* total size */ } static int diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c index 95d90e0560f0..3e81bdca071a 100644 --- a/fs/ext4/xattr_security.c +++ b/fs/ext4/xattr_security.c @@ -11,38 +11,20 @@ #include "ext4.h" #include "xattr.h" -static size_t -ext4_xattr_security_list(struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len, int type) -{ - const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1; - const size_t total_len = prefix_len + name_len + 1; - - - if (list && total_len <= list_size) { - memcpy(list, XATTR_SECURITY_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - static int -ext4_xattr_security_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +ext4_xattr_security_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY, name, buffer, size); } static int -ext4_xattr_security_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +ext4_xattr_security_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY, name, value, size, flags); } @@ -76,7 +58,6 @@ ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir, const struct xattr_handler ext4_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = ext4_xattr_security_list, .get = ext4_xattr_security_get, .set = ext4_xattr_security_set, }; diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c index 891ee2ddfbd6..2a3c6f9b8cb8 100644 --- a/fs/ext4/xattr_trusted.c +++ b/fs/ext4/xattr_trusted.c @@ -12,40 +12,26 @@ #include "ext4.h" #include "xattr.h" -static size_t -ext4_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len, int type) +static bool +ext4_xattr_trusted_list(struct dentry *dentry) { - const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!capable(CAP_SYS_ADMIN)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; + return capable(CAP_SYS_ADMIN); } static int -ext4_xattr_trusted_get(struct dentry *dentry, const char *name, void *buffer, - size_t size, int type) +ext4_xattr_trusted_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, void *buffer, + size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_TRUSTED, name, buffer, size); } static int -ext4_xattr_trusted_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +ext4_xattr_trusted_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_TRUSTED, name, value, size, flags); } diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c index 6ed932b3c043..d152f431e432 100644 --- a/fs/ext4/xattr_user.c +++ b/fs/ext4/xattr_user.c @@ -11,30 +11,17 @@ #include "ext4.h" #include "xattr.h" -static size_t -ext4_xattr_user_list(struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len, int type) +static bool +ext4_xattr_user_list(struct dentry *dentry) { - const size_t prefix_len = XATTR_USER_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!test_opt(dentry->d_sb, XATTR_USER)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_USER_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; + return test_opt(dentry->d_sb, XATTR_USER); } static int -ext4_xattr_user_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +ext4_xattr_user_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; if (!test_opt(dentry->d_sb, XATTR_USER)) return -EOPNOTSUPP; return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_USER, @@ -42,11 +29,10 @@ ext4_xattr_user_get(struct dentry *dentry, const char *name, } static int -ext4_xattr_user_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +ext4_xattr_user_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; if (!test_opt(dentry->d_sb, XATTR_USER)) return -EOPNOTSUPP; return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_USER, diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index f661d80474be..3842af954cd5 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -237,7 +237,7 @@ static int f2fs_write_meta_page(struct page *page, dec_page_count(sbi, F2FS_DIRTY_META); unlock_page(page); - if (wbc->for_reclaim) + if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi))) f2fs_submit_merged_bio(sbi, META, WRITE); return 0; @@ -410,13 +410,13 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) spin_unlock(&im->ino_lock); } -void add_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type) +void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { /* add new dirty ino entry into list */ __add_ino_entry(sbi, ino, type); } -void remove_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type) +void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { /* remove dirty ino entry from list */ __remove_ino_entry(sbi, ino, type); @@ -434,7 +434,7 @@ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) return e ? true : false; } -void release_dirty_inode(struct f2fs_sb_info *sbi) +void release_ino_entry(struct f2fs_sb_info *sbi) { struct ino_entry *e, *tmp; int i; @@ -722,47 +722,48 @@ fail_no_cp: return -EINVAL; } -static int __add_dirty_inode(struct inode *inode, struct inode_entry *new) +static void __add_dirty_inode(struct inode *inode, enum inode_type type) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); + int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE; - if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) - return -EEXIST; + if (is_inode_flag_set(fi, flag)) + return; - set_inode_flag(F2FS_I(inode), FI_DIRTY_DIR); - F2FS_I(inode)->dirty_dir = new; - list_add_tail(&new->list, &sbi->dir_inode_list); - stat_inc_dirty_dir(sbi); - return 0; + set_inode_flag(fi, flag); + list_add_tail(&fi->dirty_list, &sbi->inode_list[type]); + stat_inc_dirty_inode(sbi, type); +} + +static void __remove_dirty_inode(struct inode *inode, enum inode_type type) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE; + + if (get_dirty_pages(inode) || + !is_inode_flag_set(F2FS_I(inode), flag)) + return; + + list_del_init(&fi->dirty_list); + clear_inode_flag(fi, flag); + stat_dec_dirty_inode(F2FS_I_SB(inode), type); } void update_dirty_page(struct inode *inode, struct page *page) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct inode_entry *new; - int ret = 0; + enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE; if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode)) return; - if (!S_ISDIR(inode->i_mode)) { - inode_inc_dirty_pages(inode); - goto out; - } - - new = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS); - new->inode = inode; - INIT_LIST_HEAD(&new->list); - - spin_lock(&sbi->dir_inode_lock); - ret = __add_dirty_inode(inode, new); + spin_lock(&sbi->inode_lock[type]); + __add_dirty_inode(inode, type); inode_inc_dirty_pages(inode); - spin_unlock(&sbi->dir_inode_lock); + spin_unlock(&sbi->inode_lock[type]); - if (ret) - kmem_cache_free(inode_entry_slab, new); -out: SetPagePrivate(page); f2fs_trace_pid(page); } @@ -770,70 +771,60 @@ out: void add_dirty_dir_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct inode_entry *new = - f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS); - int ret = 0; - - new->inode = inode; - INIT_LIST_HEAD(&new->list); - spin_lock(&sbi->dir_inode_lock); - ret = __add_dirty_inode(inode, new); - spin_unlock(&sbi->dir_inode_lock); - - if (ret) - kmem_cache_free(inode_entry_slab, new); + spin_lock(&sbi->inode_lock[DIR_INODE]); + __add_dirty_inode(inode, DIR_INODE); + spin_unlock(&sbi->inode_lock[DIR_INODE]); } -void remove_dirty_dir_inode(struct inode *inode) +void remove_dirty_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct inode_entry *entry; - - if (!S_ISDIR(inode->i_mode)) - return; + struct f2fs_inode_info *fi = F2FS_I(inode); + enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE; - spin_lock(&sbi->dir_inode_lock); - if (get_dirty_pages(inode) || - !is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) { - spin_unlock(&sbi->dir_inode_lock); + if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) && + !S_ISLNK(inode->i_mode)) return; - } - entry = F2FS_I(inode)->dirty_dir; - list_del(&entry->list); - F2FS_I(inode)->dirty_dir = NULL; - clear_inode_flag(F2FS_I(inode), FI_DIRTY_DIR); - stat_dec_dirty_dir(sbi); - spin_unlock(&sbi->dir_inode_lock); - kmem_cache_free(inode_entry_slab, entry); + spin_lock(&sbi->inode_lock[type]); + __remove_dirty_inode(inode, type); + spin_unlock(&sbi->inode_lock[type]); /* Only from the recovery routine */ - if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) { - clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT); + if (is_inode_flag_set(fi, FI_DELAY_IPUT)) { + clear_inode_flag(fi, FI_DELAY_IPUT); iput(inode); } } -void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi) +int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type) { struct list_head *head; - struct inode_entry *entry; struct inode *inode; + struct f2fs_inode_info *fi; + bool is_dir = (type == DIR_INODE); + + trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir, + get_pages(sbi, is_dir ? + F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA)); retry: if (unlikely(f2fs_cp_error(sbi))) - return; + return -EIO; - spin_lock(&sbi->dir_inode_lock); + spin_lock(&sbi->inode_lock[type]); - head = &sbi->dir_inode_list; + head = &sbi->inode_list[type]; if (list_empty(head)) { - spin_unlock(&sbi->dir_inode_lock); - return; + spin_unlock(&sbi->inode_lock[type]); + trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir, + get_pages(sbi, is_dir ? + F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA)); + return 0; } - entry = list_entry(head->next, struct inode_entry, list); - inode = igrab(entry->inode); - spin_unlock(&sbi->dir_inode_lock); + fi = list_entry(head->next, struct f2fs_inode_info, dirty_list); + inode = igrab(&fi->vfs_inode); + spin_unlock(&sbi->inode_lock[type]); if (inode) { filemap_fdatawrite(inode->i_mapping); iput(inode); @@ -868,11 +859,9 @@ retry_flush_dents: /* write all the dirty dentry pages */ if (get_pages(sbi, F2FS_DIRTY_DENTS)) { f2fs_unlock_all(sbi); - sync_dirty_dir_inodes(sbi); - if (unlikely(f2fs_cp_error(sbi))) { - err = -EIO; + err = sync_dirty_inodes(sbi, DIR_INODE); + if (err) goto out; - } goto retry_flush_dents; } @@ -885,10 +874,9 @@ retry_flush_nodes: if (get_pages(sbi, F2FS_DIRTY_NODES)) { up_write(&sbi->node_write); - sync_node_pages(sbi, 0, &wbc); - if (unlikely(f2fs_cp_error(sbi))) { + err = sync_node_pages(sbi, 0, &wbc); + if (err) { f2fs_unlock_all(sbi); - err = -EIO; goto out; } goto retry_flush_nodes; @@ -919,7 +907,7 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi) finish_wait(&sbi->cp_wait, &wait); } -static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) +static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); @@ -945,7 +933,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) while (get_pages(sbi, F2FS_DIRTY_META)) { sync_meta_pages(sbi, META, LONG_MAX); if (unlikely(f2fs_cp_error(sbi))) - return; + return -EIO; } next_free_nid(sbi, &last_nid); @@ -1030,7 +1018,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* need to wait for end_io results */ wait_on_all_pages_writeback(sbi); if (unlikely(f2fs_cp_error(sbi))) - return; + return -EIO; /* write out checkpoint buffer at block 0 */ update_meta_page(sbi, ckpt, start_blk++); @@ -1058,7 +1046,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) wait_on_all_pages_writeback(sbi); if (unlikely(f2fs_cp_error(sbi))) - return; + return -EIO; filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LONG_MAX); filemap_fdatawait_range(META_MAPPING(sbi), 0, LONG_MAX); @@ -1081,22 +1069,25 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) invalidate_mapping_pages(META_MAPPING(sbi), discard_blk, discard_blk); - release_dirty_inode(sbi); + release_ino_entry(sbi); if (unlikely(f2fs_cp_error(sbi))) - return; + return -EIO; clear_prefree_segments(sbi, cpc); clear_sbi_flag(sbi, SBI_IS_DIRTY); + + return 0; } /* * We guarantee that this checkpoint procedure will not fail. */ -void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) +int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); unsigned long long ckpt_ver; + int err = 0; mutex_lock(&sbi->cp_mutex); @@ -1104,14 +1095,19 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) (cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC || (cpc->reason == CP_DISCARD && !sbi->discard_blks))) goto out; - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi))) { + err = -EIO; goto out; - if (f2fs_readonly(sbi->sb)) + } + if (f2fs_readonly(sbi->sb)) { + err = -EROFS; goto out; + } trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops"); - if (block_operations(sbi)) + err = block_operations(sbi); + if (err) goto out; trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops"); @@ -1133,7 +1129,7 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) flush_sit_entries(sbi, cpc); /* unlock all the fs_lock[] in do_checkpoint() */ - do_checkpoint(sbi, cpc); + err = do_checkpoint(sbi, cpc); unblock_operations(sbi); stat_inc_cp_count(sbi->stat_info); @@ -1143,10 +1139,11 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) "checkpoint: version = %llx", ckpt_ver); /* do checkpoint periodically */ - sbi->cp_expires = round_jiffies_up(jiffies + HZ * sbi->cp_interval); + f2fs_update_time(sbi, CP_TIME); + trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint"); out: mutex_unlock(&sbi->cp_mutex); - trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint"); + return err; } void init_ino_entry_info(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 972eab7ac071..ac9e7c6aac74 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -225,7 +225,8 @@ void set_data_blkaddr(struct dnode_of_data *dn) /* Get physical address of data block */ addr_array = blkaddr_in_node(rn); addr_array[ofs_in_node] = cpu_to_le32(dn->data_blkaddr); - set_page_dirty(node_page); + if (set_page_dirty(node_page)) + dn->node_changed = true; } int reserve_new_block(struct dnode_of_data *dn) @@ -412,7 +413,7 @@ struct page *get_new_data_page(struct inode *inode, struct page *page; struct dnode_of_data dn; int err; -repeat: + page = f2fs_grab_cache_page(mapping, index, true); if (!page) { /* @@ -441,12 +442,11 @@ repeat: } else { f2fs_put_page(page, 1); - page = get_read_data_page(inode, index, READ_SYNC, true); + /* if ipage exists, blkaddr should be NEW_ADDR */ + f2fs_bug_on(F2FS_I_SB(inode), ipage); + page = get_lock_data_page(inode, index, true); if (IS_ERR(page)) - goto repeat; - - /* wait for read completion */ - lock_page(page); + return page; } got_it: if (new_i_size && i_size_read(inode) < @@ -494,14 +494,10 @@ alloc: if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT)) i_size_write(dn->inode, ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT)); - - /* direct IO doesn't use extent cache to maximize the performance */ - f2fs_drop_largest_extent(dn->inode, fofs); - return 0; } -static void __allocate_data_blocks(struct inode *inode, loff_t offset, +static int __allocate_data_blocks(struct inode *inode, loff_t offset, size_t count) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -510,14 +506,15 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset, u64 len = F2FS_BYTES_TO_BLK(count); bool allocated; u64 end_offset; + int err = 0; while (len) { - f2fs_balance_fs(sbi); f2fs_lock_op(sbi); /* When reading holes, we need its node page */ set_new_dnode(&dn, inode, NULL, NULL, 0); - if (get_dnode_of_data(&dn, start, ALLOC_NODE)) + err = get_dnode_of_data(&dn, start, ALLOC_NODE); + if (err) goto out; allocated = false; @@ -526,12 +523,15 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset, while (dn.ofs_in_node < end_offset && len) { block_t blkaddr; - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi))) { + err = -EIO; goto sync_out; + } blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) { - if (__allocate_data_block(&dn)) + err = __allocate_data_block(&dn); + if (err) goto sync_out; allocated = true; } @@ -545,8 +545,10 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset, f2fs_put_dnode(&dn); f2fs_unlock_op(sbi); + + f2fs_balance_fs(sbi, dn.node_changed); } - return; + return err; sync_out: if (allocated) @@ -554,7 +556,8 @@ sync_out: f2fs_put_dnode(&dn); out: f2fs_unlock_op(sbi); - return; + f2fs_balance_fs(sbi, dn.node_changed); + return err; } /* @@ -566,7 +569,7 @@ out: * b. do not use extent cache for better performance * c. give the block addresses to blockdev */ -static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, +int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int create, int flag) { unsigned int maxblocks = map->m_len; @@ -577,6 +580,7 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int err = 0, ofs = 1; struct extent_info ei; bool allocated = false; + block_t blkaddr; map->m_len = 0; map->m_flags = 0; @@ -592,7 +596,7 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, } if (create) - f2fs_lock_op(F2FS_I_SB(inode)); + f2fs_lock_op(sbi); /* When reading holes, we need its node page */ set_new_dnode(&dn, inode, NULL, NULL, 0); @@ -640,12 +644,21 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, pgofs++; get_next: + if (map->m_len >= maxblocks) + goto sync_out; + if (dn.ofs_in_node >= end_offset) { if (allocated) sync_inode_page(&dn); allocated = false; f2fs_put_dnode(&dn); + if (create) { + f2fs_unlock_op(sbi); + f2fs_balance_fs(sbi, dn.node_changed); + f2fs_lock_op(sbi); + } + set_new_dnode(&dn, inode, NULL, NULL, 0); err = get_dnode_of_data(&dn, pgofs, mode); if (err) { @@ -657,52 +670,53 @@ get_next: end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); } - if (maxblocks > map->m_len) { - block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); + blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); - if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) { - if (create) { - if (unlikely(f2fs_cp_error(sbi))) { - err = -EIO; - goto sync_out; - } - err = __allocate_data_block(&dn); - if (err) - goto sync_out; - allocated = true; - map->m_flags |= F2FS_MAP_NEW; - blkaddr = dn.data_blkaddr; - } else { - /* - * we only merge preallocated unwritten blocks - * for fiemap. - */ - if (flag != F2FS_GET_BLOCK_FIEMAP || - blkaddr != NEW_ADDR) - goto sync_out; + if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) { + if (create) { + if (unlikely(f2fs_cp_error(sbi))) { + err = -EIO; + goto sync_out; } + err = __allocate_data_block(&dn); + if (err) + goto sync_out; + allocated = true; + map->m_flags |= F2FS_MAP_NEW; + blkaddr = dn.data_blkaddr; + } else { + /* + * we only merge preallocated unwritten blocks + * for fiemap. + */ + if (flag != F2FS_GET_BLOCK_FIEMAP || + blkaddr != NEW_ADDR) + goto sync_out; } + } - /* Give more consecutive addresses for the readahead */ - if ((map->m_pblk != NEW_ADDR && - blkaddr == (map->m_pblk + ofs)) || - (map->m_pblk == NEW_ADDR && - blkaddr == NEW_ADDR)) { - ofs++; - dn.ofs_in_node++; - pgofs++; - map->m_len++; - goto get_next; - } + /* Give more consecutive addresses for the readahead */ + if ((map->m_pblk != NEW_ADDR && + blkaddr == (map->m_pblk + ofs)) || + (map->m_pblk == NEW_ADDR && + blkaddr == NEW_ADDR)) { + ofs++; + dn.ofs_in_node++; + pgofs++; + map->m_len++; + goto get_next; } + sync_out: if (allocated) sync_inode_page(&dn); put_out: f2fs_put_dnode(&dn); unlock_out: - if (create) - f2fs_unlock_op(F2FS_I_SB(inode)); + if (create) { + f2fs_unlock_op(sbi); + f2fs_balance_fs(sbi, dn.node_changed); + } out: trace_f2fs_map_blocks(inode, map, err); return err; @@ -742,6 +756,10 @@ static int get_data_block_dio(struct inode *inode, sector_t iblock, static int get_data_block_bmap(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { + /* Block number less than F2FS MAX BLOCKS */ + if (unlikely(iblock >= F2FS_I_SB(inode)->max_file_blocks)) + return -EFBIG; + return __get_data_block(inode, iblock, bh_result, create, F2FS_GET_BLOCK_BMAP); } @@ -761,10 +779,9 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, { struct buffer_head map_bh; sector_t start_blk, last_blk; - loff_t isize = i_size_read(inode); + loff_t isize; u64 logical = 0, phys = 0, size = 0; u32 flags = 0; - bool past_eof = false, whole_file = false; int ret = 0; ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC); @@ -779,16 +796,19 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, mutex_lock(&inode->i_mutex); - if (len >= isize) { - whole_file = true; - len = isize; - } + isize = i_size_read(inode); + if (start >= isize) + goto out; + + if (start + len > isize) + len = isize - start; if (logical_to_blk(inode, len) == 0) len = blk_to_logical(inode, 1); start_blk = logical_to_blk(inode, start); last_blk = logical_to_blk(inode, start + len - 1); + next: memset(&map_bh, 0, sizeof(struct buffer_head)); map_bh.b_size = len; @@ -800,59 +820,37 @@ next: /* HOLE */ if (!buffer_mapped(&map_bh)) { - start_blk++; - - if (!past_eof && blk_to_logical(inode, start_blk) >= isize) - past_eof = 1; - - if (past_eof && size) { - flags |= FIEMAP_EXTENT_LAST; - ret = fiemap_fill_next_extent(fieinfo, logical, - phys, size, flags); - } else if (size) { - ret = fiemap_fill_next_extent(fieinfo, logical, - phys, size, flags); - size = 0; - } + /* Go through holes util pass the EOF */ + if (blk_to_logical(inode, start_blk++) < isize) + goto prep_next; + /* Found a hole beyond isize means no more extents. + * Note that the premise is that filesystems don't + * punch holes beyond isize and keep size unchanged. + */ + flags |= FIEMAP_EXTENT_LAST; + } - /* if we have holes up to/past EOF then we're done */ - if (start_blk > last_blk || past_eof || ret) - goto out; - } else { - if (start_blk > last_blk && !whole_file) { - ret = fiemap_fill_next_extent(fieinfo, logical, - phys, size, flags); - goto out; - } + if (size) { + if (f2fs_encrypted_inode(inode)) + flags |= FIEMAP_EXTENT_DATA_ENCRYPTED; - /* - * if size != 0 then we know we already have an extent - * to add, so add it. - */ - if (size) { - ret = fiemap_fill_next_extent(fieinfo, logical, - phys, size, flags); - if (ret) - goto out; - } + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, flags); + } - logical = blk_to_logical(inode, start_blk); - phys = blk_to_logical(inode, map_bh.b_blocknr); - size = map_bh.b_size; - flags = 0; - if (buffer_unwritten(&map_bh)) - flags = FIEMAP_EXTENT_UNWRITTEN; + if (start_blk > last_blk || ret) + goto out; - start_blk += logical_to_blk(inode, size); + logical = blk_to_logical(inode, start_blk); + phys = blk_to_logical(inode, map_bh.b_blocknr); + size = map_bh.b_size; + flags = 0; + if (buffer_unwritten(&map_bh)) + flags = FIEMAP_EXTENT_UNWRITTEN; - /* - * If we are past the EOF, then we need to make sure as - * soon as we find a hole that the last extent we found - * is marked with FIEMAP_EXTENT_LAST - */ - if (!past_eof && logical + size >= isize) - past_eof = true; - } + start_blk += logical_to_blk(inode, size); + +prep_next: cond_resched(); if (fatal_signal_pending(current)) ret = -EINTR; @@ -1083,6 +1081,7 @@ int do_write_data_page(struct f2fs_io_info *fio) */ if (unlikely(fio->blk_addr != NEW_ADDR && !is_cold_data(page) && + !IS_ATOMIC_WRITTEN_PAGE(page) && need_inplace_update(inode))) { rewrite_data_page(fio); set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE); @@ -1179,10 +1178,11 @@ out: if (err) ClearPageUptodate(page); unlock_page(page); - if (need_balance_fs) - f2fs_balance_fs(sbi); - if (wbc->for_reclaim) + f2fs_balance_fs(sbi, need_balance_fs); + if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi))) { f2fs_submit_merged_bio(sbi, DATA, WRITE); + remove_dirty_inode(inode); + } return 0; redirty_out: @@ -1354,6 +1354,10 @@ static int f2fs_write_data_pages(struct address_space *mapping, available_free_memory(sbi, DIRTY_DENTS)) goto skip_write; + /* skip writing during file defragment */ + if (is_inode_flag_set(F2FS_I(inode), FI_DO_DEFRAG)) + goto skip_write; + /* during POR, we don't need to trigger writepage at all. */ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto skip_write; @@ -1369,7 +1373,7 @@ static int f2fs_write_data_pages(struct address_space *mapping, if (locked) mutex_unlock(&sbi->writepages); - remove_dirty_dir_inode(inode); + remove_dirty_inode(inode); wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff); return ret; @@ -1382,13 +1386,85 @@ skip_write: static void f2fs_write_failed(struct address_space *mapping, loff_t to) { struct inode *inode = mapping->host; + loff_t i_size = i_size_read(inode); - if (to > inode->i_size) { - truncate_pagecache(inode, inode->i_size); - truncate_blocks(inode, inode->i_size, true); + if (to > i_size) { + truncate_pagecache(inode, i_size); + truncate_blocks(inode, i_size, true); } } +static int prepare_write_begin(struct f2fs_sb_info *sbi, + struct page *page, loff_t pos, unsigned len, + block_t *blk_addr, bool *node_changed) +{ + struct inode *inode = page->mapping->host; + pgoff_t index = page->index; + struct dnode_of_data dn; + struct page *ipage; + bool locked = false; + struct extent_info ei; + int err = 0; + + if (f2fs_has_inline_data(inode) || + (pos & PAGE_CACHE_MASK) >= i_size_read(inode)) { + f2fs_lock_op(sbi); + locked = true; + } +restart: + /* check inline_data */ + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + err = PTR_ERR(ipage); + goto unlock_out; + } + + set_new_dnode(&dn, inode, ipage, ipage, 0); + + if (f2fs_has_inline_data(inode)) { + if (pos + len <= MAX_INLINE_DATA) { + read_inline_data(page, ipage); + set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); + sync_inode_page(&dn); + } else { + err = f2fs_convert_inline_page(&dn, page); + if (err) + goto out; + if (dn.data_blkaddr == NULL_ADDR) + err = f2fs_get_block(&dn, index); + } + } else if (locked) { + err = f2fs_get_block(&dn, index); + } else { + if (f2fs_lookup_extent_cache(inode, index, &ei)) { + dn.data_blkaddr = ei.blk + index - ei.fofs; + } else { + bool restart = false; + + /* hole case */ + err = get_dnode_of_data(&dn, index, LOOKUP_NODE); + if (err || (!err && dn.data_blkaddr == NULL_ADDR)) + restart = true; + if (restart) { + f2fs_put_dnode(&dn); + f2fs_lock_op(sbi); + locked = true; + goto restart; + } + } + } + + /* convert_inline_page can make node_changed */ + *blk_addr = dn.data_blkaddr; + *node_changed = dn.node_changed; +out: + f2fs_put_dnode(&dn); +unlock_out: + if (locked) + f2fs_unlock_op(sbi); + return err; +} + static int f2fs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) @@ -1396,15 +1472,13 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *page = NULL; - struct page *ipage; pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT; - struct dnode_of_data dn; + bool need_balance = false; + block_t blkaddr = NULL_ADDR; int err = 0; trace_f2fs_write_begin(inode, pos, len, flags); - f2fs_balance_fs(sbi); - /* * We should check this at this moment to avoid deadlock on inode page * and #0 page. The locking rule for inline_data conversion should be: @@ -1424,41 +1498,27 @@ repeat: *pagep = page; - f2fs_lock_op(sbi); - - /* check inline_data */ - ipage = get_node_page(sbi, inode->i_ino); - if (IS_ERR(ipage)) { - err = PTR_ERR(ipage); - goto unlock_fail; - } - - set_new_dnode(&dn, inode, ipage, ipage, 0); + err = prepare_write_begin(sbi, page, pos, len, + &blkaddr, &need_balance); + if (err) + goto fail; - if (f2fs_has_inline_data(inode)) { - if (pos + len <= MAX_INLINE_DATA) { - read_inline_data(page, ipage); - set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); - sync_inode_page(&dn); - goto put_next; + if (need_balance && has_not_enough_free_secs(sbi, 0)) { + unlock_page(page); + f2fs_balance_fs(sbi, true); + lock_page(page); + if (page->mapping != mapping) { + /* The page got truncated from under us */ + f2fs_put_page(page, 1); + goto repeat; } - err = f2fs_convert_inline_page(&dn, page); - if (err) - goto put_fail; } - err = f2fs_get_block(&dn, index); - if (err) - goto put_fail; -put_next: - f2fs_put_dnode(&dn); - f2fs_unlock_op(sbi); - f2fs_wait_on_page_writeback(page, DATA); /* wait for GCed encrypted page writeback */ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) - f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr); + f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr); if (len == PAGE_CACHE_SIZE) goto out_update; @@ -1474,14 +1534,14 @@ put_next: goto out_update; } - if (dn.data_blkaddr == NEW_ADDR) { + if (blkaddr == NEW_ADDR) { zero_user_segment(page, 0, PAGE_CACHE_SIZE); } else { struct f2fs_io_info fio = { .sbi = sbi, .type = DATA, .rw = READ_SYNC, - .blk_addr = dn.data_blkaddr, + .blk_addr = blkaddr, .page = page, .encrypted_page = NULL, }; @@ -1512,10 +1572,6 @@ out_clear: clear_cold_data(page); return 0; -put_fail: - f2fs_put_dnode(&dn); -unlock_fail: - f2fs_unlock_op(sbi); fail: f2fs_put_page(page, 1); f2fs_write_failed(mapping, pos + len); @@ -1540,6 +1596,7 @@ static int f2fs_write_end(struct file *file, } f2fs_put_page(page, 1); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return copied; } @@ -1567,11 +1624,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int err; /* we don't need to use inline_data strictly */ - if (f2fs_has_inline_data(inode)) { - err = f2fs_convert_inline_inode(inode); - if (err) - return err; - } + err = f2fs_convert_inline_inode(inode); + if (err) + return err; if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) return 0; @@ -1583,11 +1638,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); if (iov_iter_rw(iter) == WRITE) { - __allocate_data_blocks(inode, offset, count); - if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) { - err = -EIO; + err = __allocate_data_blocks(inode, offset, count); + if (err) goto out; - } } err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio); diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 478e5d54154f..4fb6ef88a34f 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -38,12 +38,15 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->hit_rbtree = atomic64_read(&sbi->read_hit_rbtree); si->hit_total = si->hit_largest + si->hit_cached + si->hit_rbtree; si->total_ext = atomic64_read(&sbi->total_hit_ext); - si->ext_tree = sbi->total_ext_tree; + si->ext_tree = atomic_read(&sbi->total_ext_tree); + si->zombie_tree = atomic_read(&sbi->total_zombie_tree); si->ext_node = atomic_read(&sbi->total_ext_node); si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES); si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS); - si->ndirty_dirs = sbi->n_dirty_dirs; si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META); + si->ndirty_data = get_pages(sbi, F2FS_DIRTY_DATA); + si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE]; + si->ndirty_files = sbi->ndirty_inode[FILE_INODE]; si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES); si->wb_pages = get_pages(sbi, F2FS_WRITEBACK); si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg; @@ -105,7 +108,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi) bimodal = 0; total_vblocks = 0; - blks_per_sec = sbi->segs_per_sec * (1 << sbi->log_blocks_per_seg); + blks_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg; hblks_per_sec = blks_per_sec / 2; for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) { vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec); @@ -189,10 +192,10 @@ get_cache: si->cache_mem += NM_I(sbi)->dirty_nat_cnt * sizeof(struct nat_entry_set); si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages); - si->cache_mem += sbi->n_dirty_dirs * sizeof(struct inode_entry); for (i = 0; i <= UPDATE_INO; i++) si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry); - si->cache_mem += sbi->total_ext_tree * sizeof(struct extent_tree); + si->cache_mem += atomic_read(&sbi->total_ext_tree) * + sizeof(struct extent_tree); si->cache_mem += atomic_read(&sbi->total_ext_node) * sizeof(struct extent_node); @@ -211,12 +214,10 @@ static int stat_show(struct seq_file *s, void *v) mutex_lock(&f2fs_stat_mutex); list_for_each_entry(si, &f2fs_stat_list, stat_list) { - char devname[BDEVNAME_SIZE]; - update_general_status(si->sbi); - seq_printf(s, "\n=====[ partition info(%s). #%d ]=====\n", - bdevname(si->sbi->sb->s_bdev, devname), i++); + seq_printf(s, "\n=====[ partition info(%pg). #%d ]=====\n", + si->sbi->sb->s_bdev, i++); seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ", si->sit_area_segs, si->nat_area_segs); seq_printf(s, "[SSA: %d] [MAIN: %d", @@ -269,7 +270,8 @@ static int stat_show(struct seq_file *s, void *v) si->dirty_count); seq_printf(s, " - Prefree: %d\n - Free: %d (%d)\n\n", si->prefree_count, si->free_segs, si->free_secs); - seq_printf(s, "CP calls: %d\n", si->cp_count); + seq_printf(s, "CP calls: %d (BG: %d)\n", + si->cp_count, si->bg_cp_count); seq_printf(s, "GC calls: %d (BG: %d)\n", si->call_count, si->bg_gc); seq_printf(s, " - data segments : %d (%d)\n", @@ -290,8 +292,8 @@ static int stat_show(struct seq_file *s, void *v) !si->total_ext ? 0 : div64_u64(si->hit_total * 100, si->total_ext), si->hit_total, si->total_ext); - seq_printf(s, " - Inner Struct Count: tree: %d, node: %d\n", - si->ext_tree, si->ext_node); + seq_printf(s, " - Inner Struct Count: tree: %d(%d), node: %d\n", + si->ext_tree, si->zombie_tree, si->ext_node); seq_puts(s, "\nBalancing F2FS Async:\n"); seq_printf(s, " - inmem: %4d, wb: %4d\n", si->inmem_pages, si->wb_pages); @@ -299,6 +301,8 @@ static int stat_show(struct seq_file *s, void *v) si->ndirty_node, si->node_pages); seq_printf(s, " - dents: %4d in dirs:%4d\n", si->ndirty_dent, si->ndirty_dirs); + seq_printf(s, " - datas: %4d in files:%4d\n", + si->ndirty_data, si->ndirty_files); seq_printf(s, " - meta: %4d in %4d\n", si->ndirty_meta, si->meta_pages); seq_printf(s, " - NATs: %9d/%9d\n - SITs: %9d/%9d\n", @@ -406,20 +410,23 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi) kfree(si); } -void __init f2fs_create_root_stats(void) +int __init f2fs_create_root_stats(void) { struct dentry *file; f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL); if (!f2fs_debugfs_root) - return; + return -ENOMEM; file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, NULL, &stat_fops); if (!file) { debugfs_remove(f2fs_debugfs_root); f2fs_debugfs_root = NULL; + return -ENOMEM; } + + return 0; } void f2fs_destroy_root_stats(void) diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 7c1678ba8f92..faa7495e2d7e 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -172,8 +172,6 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, namehash = f2fs_dentry_hash(&name); - f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH); - nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level); nblock = bucket_blocks(level); @@ -238,6 +236,14 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir, goto out; max_depth = F2FS_I(dir)->i_current_depth; + if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) { + f2fs_msg(F2FS_I_SB(dir)->sb, KERN_WARNING, + "Corrupted max_depth of %lu: %u", + dir->i_ino, max_depth); + max_depth = MAX_DIR_HASH_DEPTH; + F2FS_I(dir)->i_current_depth = max_depth; + mark_inode_dirty(dir); + } for (level = 0; level < max_depth; level++) { de = find_in_level(dir, level, &fname, res_page); @@ -444,7 +450,7 @@ error: /* once the failed inode becomes a bad inode, i_mode is S_IFREG */ truncate_inode_pages(&inode->i_data, 0); truncate_blocks(inode, 0, false); - remove_dirty_dir_inode(inode); + remove_dirty_inode(inode); remove_inode_page(inode); return ERR_PTR(err); } @@ -630,6 +636,7 @@ fail: f2fs_put_page(dentry_page, 1); out: f2fs_fname_free_filename(&fname); + f2fs_update_time(F2FS_I_SB(dir), REQ_TIME); return err; } @@ -651,6 +658,7 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir) clear_inode_flag(F2FS_I(inode), FI_NEW_INODE); fail: up_write(&F2FS_I(inode)->i_sem); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return err; } @@ -695,6 +703,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len)); int i; + f2fs_update_time(F2FS_I_SB(dir), REQ_TIME); + if (f2fs_has_inline_dentry(dir)) return f2fs_delete_inline_entry(dentry, page, dir, inode); @@ -855,25 +865,27 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) for (; n < npages; n++) { dentry_page = get_lock_data_page(inode, n, false); - if (IS_ERR(dentry_page)) - continue; + if (IS_ERR(dentry_page)) { + err = PTR_ERR(dentry_page); + if (err == -ENOENT) + continue; + else + goto out; + } dentry_blk = kmap(dentry_page); make_dentry_ptr(inode, &d, (void *)dentry_blk, 1); - if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr)) - goto stop; + if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr)) { + kunmap(dentry_page); + f2fs_put_page(dentry_page, 1); + break; + } ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK; kunmap(dentry_page); f2fs_put_page(dentry_page, 1); - dentry_page = NULL; - } -stop: - if (dentry_page && !IS_ERR(dentry_page)) { - kunmap(dentry_page); - f2fs_put_page(dentry_page, 1); } out: f2fs_fname_crypto_free_buffer(&fstr); diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 7ddba812e11b..ccd5c636d3fe 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -36,7 +36,7 @@ static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi, rb_link_node(&en->rb_node, parent, p); rb_insert_color(&en->rb_node, &et->root); - et->count++; + atomic_inc(&et->node_cnt); atomic_inc(&sbi->total_ext_node); return en; } @@ -45,7 +45,7 @@ static void __detach_extent_node(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_node *en) { rb_erase(&en->rb_node, &et->root); - et->count--; + atomic_dec(&et->node_cnt); atomic_dec(&sbi->total_ext_node); if (et->cached_en == en) @@ -68,11 +68,13 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode) et->root = RB_ROOT; et->cached_en = NULL; rwlock_init(&et->lock); - atomic_set(&et->refcount, 0); - et->count = 0; - sbi->total_ext_tree++; + INIT_LIST_HEAD(&et->list); + atomic_set(&et->node_cnt, 0); + atomic_inc(&sbi->total_ext_tree); + } else { + atomic_dec(&sbi->total_zombie_tree); + list_del_init(&et->list); } - atomic_inc(&et->refcount); up_write(&sbi->extent_tree_lock); /* never died until evict_inode */ @@ -131,7 +133,7 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, { struct rb_node *node, *next; struct extent_node *en; - unsigned int count = et->count; + unsigned int count = atomic_read(&et->node_cnt); node = rb_first(&et->root); while (node) { @@ -152,7 +154,7 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, node = next; } - return count - et->count; + return count - atomic_read(&et->node_cnt); } static void __drop_largest_extent(struct inode *inode, @@ -164,34 +166,33 @@ static void __drop_largest_extent(struct inode *inode, largest->len = 0; } -void f2fs_drop_largest_extent(struct inode *inode, pgoff_t fofs) -{ - if (!f2fs_may_extent_tree(inode)) - return; - - __drop_largest_extent(inode, fofs, 1); -} - -void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) +/* return true, if inode page is changed */ +bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree *et; struct extent_node *en; struct extent_info ei; - if (!f2fs_may_extent_tree(inode)) - return; + if (!f2fs_may_extent_tree(inode)) { + /* drop largest extent */ + if (i_ext && i_ext->len) { + i_ext->len = 0; + return true; + } + return false; + } et = __grab_extent_tree(inode); - if (!i_ext || le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN) - return; + if (!i_ext || !i_ext->len) + return false; set_extent_info(&ei, le32_to_cpu(i_ext->fofs), le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len)); write_lock(&et->lock); - if (et->count) + if (atomic_read(&et->node_cnt)) goto out; en = __init_extent_tree(sbi, et, &ei); @@ -202,6 +203,7 @@ void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) } out: write_unlock(&et->lock); + return false; } static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, @@ -549,45 +551,44 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode, unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) { struct extent_tree *treevec[EXT_TREE_VEC_SIZE]; + struct extent_tree *et, *next; struct extent_node *en, *tmp; unsigned long ino = F2FS_ROOT_INO(sbi); - struct radix_tree_root *root = &sbi->extent_tree_root; unsigned int found; unsigned int node_cnt = 0, tree_cnt = 0; int remained; + bool do_free = false; if (!test_opt(sbi, EXTENT_CACHE)) return 0; + if (!atomic_read(&sbi->total_zombie_tree)) + goto free_node; + if (!down_write_trylock(&sbi->extent_tree_lock)) goto out; /* 1. remove unreferenced extent tree */ - while ((found = radix_tree_gang_lookup(root, - (void **)treevec, ino, EXT_TREE_VEC_SIZE))) { - unsigned i; - - ino = treevec[found - 1]->ino + 1; - for (i = 0; i < found; i++) { - struct extent_tree *et = treevec[i]; - - if (!atomic_read(&et->refcount)) { - write_lock(&et->lock); - node_cnt += __free_extent_tree(sbi, et, true); - write_unlock(&et->lock); + list_for_each_entry_safe(et, next, &sbi->zombie_list, list) { + if (atomic_read(&et->node_cnt)) { + write_lock(&et->lock); + node_cnt += __free_extent_tree(sbi, et, true); + write_unlock(&et->lock); + } - radix_tree_delete(root, et->ino); - kmem_cache_free(extent_tree_slab, et); - sbi->total_ext_tree--; - tree_cnt++; + list_del_init(&et->list); + radix_tree_delete(&sbi->extent_tree_root, et->ino); + kmem_cache_free(extent_tree_slab, et); + atomic_dec(&sbi->total_ext_tree); + atomic_dec(&sbi->total_zombie_tree); + tree_cnt++; - if (node_cnt + tree_cnt >= nr_shrink) - goto unlock_out; - } - } + if (node_cnt + tree_cnt >= nr_shrink) + goto unlock_out; } up_write(&sbi->extent_tree_lock); +free_node: /* 2. remove LRU extent entries */ if (!down_write_trylock(&sbi->extent_tree_lock)) goto out; @@ -599,15 +600,19 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) if (!remained--) break; list_del_init(&en->list); + do_free = true; } spin_unlock(&sbi->extent_lock); + if (do_free == false) + goto unlock_out; + /* * reset ino for searching victims from beginning of global extent tree. */ ino = F2FS_ROOT_INO(sbi); - while ((found = radix_tree_gang_lookup(root, + while ((found = radix_tree_gang_lookup(&sbi->extent_tree_root, (void **)treevec, ino, EXT_TREE_VEC_SIZE))) { unsigned i; @@ -615,9 +620,13 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) for (i = 0; i < found; i++) { struct extent_tree *et = treevec[i]; - write_lock(&et->lock); - node_cnt += __free_extent_tree(sbi, et, false); - write_unlock(&et->lock); + if (!atomic_read(&et->node_cnt)) + continue; + + if (write_trylock(&et->lock)) { + node_cnt += __free_extent_tree(sbi, et, false); + write_unlock(&et->lock); + } if (node_cnt + tree_cnt >= nr_shrink) goto unlock_out; @@ -637,7 +646,7 @@ unsigned int f2fs_destroy_extent_node(struct inode *inode) struct extent_tree *et = F2FS_I(inode)->extent_tree; unsigned int node_cnt = 0; - if (!et) + if (!et || !atomic_read(&et->node_cnt)) return 0; write_lock(&et->lock); @@ -656,8 +665,12 @@ void f2fs_destroy_extent_tree(struct inode *inode) if (!et) return; - if (inode->i_nlink && !is_bad_inode(inode) && et->count) { - atomic_dec(&et->refcount); + if (inode->i_nlink && !is_bad_inode(inode) && + atomic_read(&et->node_cnt)) { + down_write(&sbi->extent_tree_lock); + list_add_tail(&et->list, &sbi->zombie_list); + atomic_inc(&sbi->total_zombie_tree); + up_write(&sbi->extent_tree_lock); return; } @@ -666,11 +679,10 @@ void f2fs_destroy_extent_tree(struct inode *inode) /* delete extent tree entry in radix tree */ down_write(&sbi->extent_tree_lock); - atomic_dec(&et->refcount); - f2fs_bug_on(sbi, atomic_read(&et->refcount) || et->count); + f2fs_bug_on(sbi, atomic_read(&et->node_cnt)); radix_tree_delete(&sbi->extent_tree_root, inode->i_ino); kmem_cache_free(extent_tree_slab, et); - sbi->total_ext_tree--; + atomic_dec(&sbi->total_ext_tree); up_write(&sbi->extent_tree_lock); F2FS_I(inode)->extent_tree = NULL; @@ -722,7 +734,9 @@ void init_extent_cache_info(struct f2fs_sb_info *sbi) init_rwsem(&sbi->extent_tree_lock); INIT_LIST_HEAD(&sbi->extent_list); spin_lock_init(&sbi->extent_lock); - sbi->total_ext_tree = 0; + atomic_set(&sbi->total_ext_tree, 0); + INIT_LIST_HEAD(&sbi->zombie_list); + atomic_set(&sbi->total_zombie_tree, 0); atomic_set(&sbi->total_ext_node, 0); } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 9db5500d63d9..ff79054c6cf6 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -21,6 +21,7 @@ #include <linux/sched.h> #include <linux/vmalloc.h> #include <linux/bio.h> +#include <linux/blkdev.h> #ifdef CONFIG_F2FS_CHECK_FS #define f2fs_bug_on(sbi, condition) BUG_ON(condition) @@ -54,6 +55,7 @@ #define F2FS_MOUNT_FASTBOOT 0x00001000 #define F2FS_MOUNT_EXTENT_CACHE 0x00002000 #define F2FS_MOUNT_FORCE_FG_GC 0x00004000 +#define F2FS_MOUNT_DATA_FLUSH 0x00008000 #define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option) #define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option) @@ -125,6 +127,7 @@ enum { #define BATCHED_TRIM_BLOCKS(sbi) \ (BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg) #define DEF_CP_INTERVAL 60 /* 60 secs */ +#define DEF_IDLE_INTERVAL 120 /* 2 mins */ struct cp_control { int reason; @@ -158,13 +161,7 @@ struct ino_entry { nid_t ino; /* inode number */ }; -/* - * for the list of directory inodes or gc inodes. - * NOTE: there are two slab users for this structure, if we add/modify/delete - * fields in structure for one of slab users, it may affect fields or size of - * other one, in this condition, it's better to split both of slab and related - * data structure. - */ +/* for the list of inodes to be GCed */ struct inode_entry { struct list_head list; /* list head */ struct inode *inode; /* vfs inode pointer */ @@ -234,6 +231,7 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, #define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5) #define F2FS_IOC_GARBAGE_COLLECT _IO(F2FS_IOCTL_MAGIC, 6) #define F2FS_IOC_WRITE_CHECKPOINT _IO(F2FS_IOCTL_MAGIC, 7) +#define F2FS_IOC_DEFRAGMENT _IO(F2FS_IOCTL_MAGIC, 8) #define F2FS_IOC_SET_ENCRYPTION_POLICY \ _IOR('f', 19, struct f2fs_encryption_policy) @@ -256,10 +254,16 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, /* * ioctl commands in 32 bit emulation */ -#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS -#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS +#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#define F2FS_IOC32_GETVERSION FS_IOC32_GETVERSION #endif +struct f2fs_defragment { + u64 start; + u64 len; +}; + /* * For INODE and NODE manager */ @@ -357,9 +361,9 @@ struct extent_tree { struct rb_root root; /* root of extent info rb-tree */ struct extent_node *cached_en; /* recently accessed extent node */ struct extent_info largest; /* largested extent info */ + struct list_head list; /* to be used by sbi->zombie_list */ rwlock_t lock; /* protect extent info rb-tree */ - atomic_t refcount; /* reference count of rb-tree */ - unsigned int count; /* # of extent node in rb-tree*/ + atomic_t node_cnt; /* # of extent node in rb-tree*/ }; /* @@ -434,8 +438,8 @@ struct f2fs_inode_info { unsigned int clevel; /* maximum level of given file name */ nid_t i_xattr_nid; /* node id that contains xattrs */ unsigned long long xattr_ver; /* cp version of xattr modification */ - struct inode_entry *dirty_dir; /* the pointer of dirty dir */ + struct list_head dirty_list; /* linked in global dirty list */ struct list_head inmem_pages; /* inmemory pages managed by f2fs */ struct mutex inmem_lock; /* lock for inmemory pages */ @@ -544,6 +548,7 @@ struct dnode_of_data { nid_t nid; /* node id of the direct node block */ unsigned int ofs_in_node; /* data offset in the node page */ bool inode_page_locked; /* inode page is locked or not */ + bool node_changed; /* is node block changed */ block_t data_blkaddr; /* block address of the node block */ }; @@ -647,6 +652,7 @@ struct f2fs_sm_info { enum count_type { F2FS_WRITEBACK, F2FS_DIRTY_DENTS, + F2FS_DIRTY_DATA, F2FS_DIRTY_NODES, F2FS_DIRTY_META, F2FS_INMEM_PAGES, @@ -695,6 +701,12 @@ struct f2fs_bio_info { struct rw_semaphore io_rwsem; /* blocking op for bio */ }; +enum inode_type { + DIR_INODE, /* for dirty dir inode */ + FILE_INODE, /* for dirty regular/symlink inode */ + NR_INODE_TYPE, +}; + /* for inner inode cache management */ struct inode_management { struct radix_tree_root ino_root; /* ino entry array */ @@ -711,11 +723,17 @@ enum { SBI_POR_DOING, /* recovery is doing or not */ }; +enum { + CP_TIME, + REQ_TIME, + MAX_TIME, +}; + struct f2fs_sb_info { struct super_block *sb; /* pointer to VFS super block */ struct proc_dir_entry *s_proc; /* proc entry */ - struct buffer_head *raw_super_buf; /* buffer head of raw sb */ struct f2fs_super_block *raw_super; /* raw super block pointer */ + int valid_super_block; /* valid super block no */ int s_flag; /* flags for sbi */ /* for node-related operations */ @@ -737,23 +755,26 @@ struct f2fs_sb_info { struct rw_semaphore node_write; /* locking node writes */ struct mutex writepages; /* mutex for writepages() */ wait_queue_head_t cp_wait; - long cp_expires, cp_interval; /* next expected periodic cp */ + unsigned long last_time[MAX_TIME]; /* to store time in jiffies */ + long interval_time[MAX_TIME]; /* to store thresholds */ struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ /* for orphan inode, use 0'th array */ unsigned int max_orphans; /* max orphan inodes */ - /* for directory inode management */ - struct list_head dir_inode_list; /* dir inode list */ - spinlock_t dir_inode_lock; /* for dir inode list lock */ + /* for inode management */ + struct list_head inode_list[NR_INODE_TYPE]; /* dirty inode list */ + spinlock_t inode_lock[NR_INODE_TYPE]; /* for dirty inode list lock */ /* for extent tree cache */ struct radix_tree_root extent_tree_root;/* cache extent cache entries */ struct rw_semaphore extent_tree_lock; /* locking extent radix tree */ struct list_head extent_list; /* lru list for shrinker */ spinlock_t extent_lock; /* locking extent lru list */ - int total_ext_tree; /* extent tree count */ + atomic_t total_ext_tree; /* extent tree count */ + struct list_head zombie_list; /* extent zombie tree list */ + atomic_t total_zombie_tree; /* extent zombie tree count */ atomic_t total_ext_node; /* extent info count */ /* basic filesystem units */ @@ -771,6 +792,7 @@ struct f2fs_sb_info { unsigned int total_node_count; /* total node block count */ unsigned int total_valid_node_count; /* valid node block count */ unsigned int total_valid_inode_count; /* valid inode count */ + loff_t max_file_blocks; /* max block index of file */ int active_logs; /* # of active logs */ int dir_level; /* directory level */ @@ -809,7 +831,7 @@ struct f2fs_sb_info { atomic_t inline_inode; /* # of inline_data inodes */ atomic_t inline_dir; /* # of inline_dentry inodes */ int bg_gc; /* background gc calls */ - unsigned int n_dirty_dirs; /* # of dir inodes */ + unsigned int ndirty_inode[NR_INODE_TYPE]; /* # of dirty inodes */ #endif unsigned int last_victim[2]; /* last victim segment # */ spinlock_t stat_lock; /* lock for stat operations */ @@ -824,6 +846,31 @@ struct f2fs_sb_info { unsigned int shrinker_run_no; }; +static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type) +{ + sbi->last_time[type] = jiffies; +} + +static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type) +{ + struct timespec ts = {sbi->interval_time[type], 0}; + unsigned long interval = timespec_to_jiffies(&ts); + + return time_after(jiffies, sbi->last_time[type] + interval); +} + +static inline bool is_idle(struct f2fs_sb_info *sbi) +{ + struct block_device *bdev = sbi->sb->s_bdev; + struct request_queue *q = bdev_get_queue(bdev); + struct request_list *rl = &q->root_rl; + + if (rl->count[BLK_RW_SYNC] || rl->count[BLK_RW_ASYNC]) + return 0; + + return f2fs_time_over(sbi, REQ_TIME); +} + /* * Inline functions */ @@ -1059,8 +1106,8 @@ static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) static inline void inode_inc_dirty_pages(struct inode *inode) { atomic_inc(&F2FS_I(inode)->dirty_pages); - if (S_ISDIR(inode->i_mode)) - inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS); + inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ? + F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA); } static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type) @@ -1075,9 +1122,8 @@ static inline void inode_dec_dirty_pages(struct inode *inode) return; atomic_dec(&F2FS_I(inode)->dirty_pages); - - if (S_ISDIR(inode->i_mode)) - dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS); + dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ? + F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA); } static inline int get_pages(struct f2fs_sb_info *sbi, int count_type) @@ -1092,8 +1138,7 @@ static inline int get_dirty_pages(struct inode *inode) static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type) { - unsigned int pages_per_sec = sbi->segs_per_sec * - (1 << sbi->log_blocks_per_seg); + unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg; return ((get_pages(sbi, block_type) + pages_per_sec - 1) >> sbi->log_blocks_per_seg) / sbi->segs_per_sec; } @@ -1416,6 +1461,8 @@ enum { FI_DROP_CACHE, /* drop dirty page cache */ FI_DATA_EXIST, /* indicate data exists */ FI_INLINE_DOTS, /* indicate inline dot dentries */ + FI_DO_DEFRAG, /* indicate defragment is running */ + FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */ }; static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag) @@ -1602,13 +1649,11 @@ static inline bool is_dot_dotdot(const struct qstr *str) static inline bool f2fs_may_extent_tree(struct inode *inode) { - mode_t mode = inode->i_mode; - if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) || is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) return false; - return S_ISREG(mode); + return S_ISREG(inode->i_mode); } static inline void *f2fs_kvmalloc(size_t size, gfp_t flags) @@ -1661,8 +1706,8 @@ long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long); void f2fs_set_inode_flags(struct inode *); struct inode *f2fs_iget(struct super_block *, unsigned long); int try_to_free_nats(struct f2fs_sb_info *, int); -void update_inode(struct inode *, struct page *); -void update_inode_page(struct inode *); +int update_inode(struct inode *, struct page *); +int update_inode_page(struct inode *); int f2fs_write_inode(struct inode *, struct writeback_control *); void f2fs_evict_inode(struct inode *); void handle_failed_inode(struct inode *); @@ -1767,7 +1812,7 @@ void destroy_node_manager_caches(void); */ void register_inmem_page(struct inode *, struct page *); int commit_inmem_pages(struct inode *, bool); -void f2fs_balance_fs(struct f2fs_sb_info *); +void f2fs_balance_fs(struct f2fs_sb_info *, bool); void f2fs_balance_fs_bg(struct f2fs_sb_info *); int f2fs_issue_flush(struct f2fs_sb_info *); int create_flush_cmd_control(struct f2fs_sb_info *); @@ -1813,9 +1858,9 @@ bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int); int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int, bool); void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t); long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long); -void add_dirty_inode(struct f2fs_sb_info *, nid_t, int type); -void remove_dirty_inode(struct f2fs_sb_info *, nid_t, int type); -void release_dirty_inode(struct f2fs_sb_info *); +void add_ino_entry(struct f2fs_sb_info *, nid_t, int type); +void remove_ino_entry(struct f2fs_sb_info *, nid_t, int type); +void release_ino_entry(struct f2fs_sb_info *); bool exist_written_data(struct f2fs_sb_info *, nid_t, int); int acquire_orphan_inode(struct f2fs_sb_info *); void release_orphan_inode(struct f2fs_sb_info *); @@ -1825,9 +1870,9 @@ int recover_orphan_inodes(struct f2fs_sb_info *); int get_valid_checkpoint(struct f2fs_sb_info *); void update_dirty_page(struct inode *, struct page *); void add_dirty_dir_inode(struct inode *); -void remove_dirty_dir_inode(struct inode *); -void sync_dirty_dir_inodes(struct f2fs_sb_info *); -void write_checkpoint(struct f2fs_sb_info *, struct cp_control *); +void remove_dirty_inode(struct inode *); +int sync_dirty_inodes(struct f2fs_sb_info *, enum inode_type); +int write_checkpoint(struct f2fs_sb_info *, struct cp_control *); void init_ino_entry_info(struct f2fs_sb_info *); int __init create_checkpoint_caches(void); void destroy_checkpoint_caches(void); @@ -1847,6 +1892,7 @@ struct page *find_data_page(struct inode *, pgoff_t); struct page *get_lock_data_page(struct inode *, pgoff_t, bool); struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool); int do_write_data_page(struct f2fs_io_info *); +int f2fs_map_blocks(struct inode *, struct f2fs_map_blocks *, int, int); int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64); void f2fs_invalidate_page(struct page *, unsigned int, unsigned int); int f2fs_release_page(struct page *, gfp_t); @@ -1877,8 +1923,9 @@ struct f2fs_stat_info { int main_area_segs, main_area_sections, main_area_zones; unsigned long long hit_largest, hit_cached, hit_rbtree; unsigned long long hit_total, total_ext; - int ext_tree, ext_node; - int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta; + int ext_tree, zombie_tree, ext_node; + int ndirty_node, ndirty_meta; + int ndirty_dent, ndirty_dirs, ndirty_data, ndirty_files; int nats, dirty_nats, sits, dirty_sits, fnids; int total_count, utilization; int bg_gc, inmem_pages, wb_pages; @@ -1888,7 +1935,7 @@ struct f2fs_stat_info { int util_free, util_valid, util_invalid; int rsvd_segs, overp_segs; int dirty_count, node_pages, meta_pages; - int prefree_count, call_count, cp_count; + int prefree_count, call_count, cp_count, bg_cp_count; int tot_segs, node_segs, data_segs, free_segs, free_secs; int bg_node_segs, bg_data_segs; int tot_blks, data_blks, node_blks; @@ -1909,10 +1956,11 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) } #define stat_inc_cp_count(si) ((si)->cp_count++) +#define stat_inc_bg_cp_count(si) ((si)->bg_cp_count++) #define stat_inc_call_count(si) ((si)->call_count++) #define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++) -#define stat_inc_dirty_dir(sbi) ((sbi)->n_dirty_dirs++) -#define stat_dec_dirty_dir(sbi) ((sbi)->n_dirty_dirs--) +#define stat_inc_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]++) +#define stat_dec_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]--) #define stat_inc_total_hit(sbi) (atomic64_inc(&(sbi)->total_hit_ext)) #define stat_inc_rbtree_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_rbtree)) #define stat_inc_largest_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_largest)) @@ -1987,14 +2035,15 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) int f2fs_build_stats(struct f2fs_sb_info *); void f2fs_destroy_stats(struct f2fs_sb_info *); -void __init f2fs_create_root_stats(void); +int __init f2fs_create_root_stats(void); void f2fs_destroy_root_stats(void); #else #define stat_inc_cp_count(si) +#define stat_inc_bg_cp_count(si) #define stat_inc_call_count(si) #define stat_inc_bggc_count(si) -#define stat_inc_dirty_dir(sbi) -#define stat_dec_dirty_dir(sbi) +#define stat_inc_dirty_inode(sbi, type) +#define stat_dec_dirty_inode(sbi, type) #define stat_inc_total_hit(sb) #define stat_inc_rbtree_node_hit(sb) #define stat_inc_largest_node_hit(sbi) @@ -2015,7 +2064,7 @@ void f2fs_destroy_root_stats(void); static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { } -static inline void __init f2fs_create_root_stats(void) { } +static inline int __init f2fs_create_root_stats(void) { return 0; } static inline void f2fs_destroy_root_stats(void) { } #endif @@ -2069,8 +2118,7 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *); * extent_cache.c */ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *, int); -void f2fs_drop_largest_extent(struct inode *, pgoff_t); -void f2fs_init_extent_tree(struct inode *, struct f2fs_extent *); +bool f2fs_init_extent_tree(struct inode *, struct f2fs_extent *); unsigned int f2fs_destroy_extent_node(struct inode *); void f2fs_destroy_extent_tree(struct inode *); bool f2fs_lookup_extent_cache(struct inode *, pgoff_t, struct extent_info *); @@ -2121,7 +2169,7 @@ static inline int f2fs_sb_has_crypto(struct super_block *sb) static inline bool f2fs_may_encrypt(struct inode *inode) { #ifdef CONFIG_F2FS_FS_ENCRYPTION - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)); #else diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index a197215ad52b..18ddb1e5182a 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -40,8 +40,6 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, struct dnode_of_data dn; int err; - f2fs_balance_fs(sbi); - sb_start_pagefault(inode->i_sb); f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); @@ -57,6 +55,8 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, f2fs_put_dnode(&dn); f2fs_unlock_op(sbi); + f2fs_balance_fs(sbi, dn.node_changed); + file_update_time(vma->vm_file); lock_page(page); if (unlikely(page->mapping != inode->i_mapping || @@ -96,6 +96,7 @@ mapped: clear_cold_data(page); out: sb_end_pagefault(inode->i_sb); + f2fs_update_time(sbi, REQ_TIME); return block_page_mkwrite_return(err); } @@ -201,7 +202,7 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) trace_f2fs_sync_file_enter(inode); /* if fdatasync is triggered, let's do in-place-update */ - if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks) + if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks) set_inode_flag(fi, FI_NEED_IPU); ret = filemap_write_and_wait_range(inode->i_mapping, start, end); clear_inode_flag(fi, FI_NEED_IPU); @@ -233,9 +234,6 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } go_write: - /* guarantee free sections for fsync */ - f2fs_balance_fs(sbi); - /* * Both of fdatasync() and fsync() are able to be recovered from * sudden-power-off. @@ -261,8 +259,10 @@ sync_nodes: sync_node_pages(sbi, ino, &wbc); /* if cp_error was enabled, we should avoid infinite loop */ - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi))) { + ret = -EIO; goto out; + } if (need_inode_block_update(sbi, ino)) { mark_inode_dirty_sync(inode); @@ -275,12 +275,13 @@ sync_nodes: goto out; /* once recovery info is written, don't need to tack this */ - remove_dirty_inode(sbi, ino, APPEND_INO); + remove_ino_entry(sbi, ino, APPEND_INO); clear_inode_flag(fi, FI_APPEND_WRITE); flush_out: - remove_dirty_inode(sbi, ino, UPDATE_INO); + remove_ino_entry(sbi, ino, UPDATE_INO); clear_inode_flag(fi, FI_UPDATE_WRITE); ret = f2fs_issue_flush(sbi); + f2fs_update_time(sbi, REQ_TIME); out: trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); f2fs_trace_ios(NULL, 1); @@ -418,19 +419,18 @@ static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence) static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); + int err; if (f2fs_encrypted_inode(inode)) { - int err = f2fs_get_encryption_info(inode); + err = f2fs_get_encryption_info(inode); if (err) return 0; } /* we don't need to use inline_data strictly */ - if (f2fs_has_inline_data(inode)) { - int err = f2fs_convert_inline_inode(inode); - if (err) - return err; - } + err = f2fs_convert_inline_inode(inode); + if (err) + return err; file_accessed(file); vma->vm_ops = &f2fs_file_vm_ops; @@ -483,11 +483,11 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count) F2FS_I(dn->inode)) + ofs; f2fs_update_extent_cache_range(dn, fofs, 0, len); dec_valid_block_count(sbi, dn->inode, nr_free); - set_page_dirty(dn->node_page); sync_inode_page(dn); } dn->ofs_in_node = ofs; + f2fs_update_time(sbi, REQ_TIME); trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid, dn->ofs_in_node, nr_free); return nr_free; @@ -604,7 +604,7 @@ int f2fs_truncate(struct inode *inode, bool lock) trace_f2fs_truncate(inode); /* we should check inline_data size */ - if (f2fs_has_inline_data(inode) && !f2fs_may_inline_data(inode)) { + if (!f2fs_may_inline_data(inode)) { err = f2fs_convert_inline_inode(inode); if (err) return err; @@ -679,13 +679,20 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) err = f2fs_truncate(inode, true); if (err) return err; - f2fs_balance_fs(F2FS_I_SB(inode)); + f2fs_balance_fs(F2FS_I_SB(inode), true); } else { /* * do not trim all blocks after i_size if target size is * larger than i_size. */ truncate_setsize(inode, attr->ia_size); + + /* should convert inline inode here */ + if (!f2fs_may_inline_data(inode)) { + err = f2fs_convert_inline_inode(inode); + if (err) + return err; + } inode->i_mtime = inode->i_ctime = CURRENT_TIME; } } @@ -727,7 +734,7 @@ static int fill_zero(struct inode *inode, pgoff_t index, if (!len) return 0; - f2fs_balance_fs(sbi); + f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); page = get_new_data_page(inode, NULL, index, false); @@ -778,13 +785,11 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) { pgoff_t pg_start, pg_end; loff_t off_start, off_end; - int ret = 0; + int ret; - if (f2fs_has_inline_data(inode)) { - ret = f2fs_convert_inline_inode(inode); - if (ret) - return ret; - } + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; @@ -815,7 +820,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) loff_t blk_start, blk_end; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - f2fs_balance_fs(sbi); + f2fs_balance_fs(sbi, true); blk_start = (loff_t)pg_start << PAGE_CACHE_SHIFT; blk_end = (loff_t)pg_end << PAGE_CACHE_SHIFT; @@ -918,7 +923,7 @@ static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end) int ret = 0; for (; end < nrpages; start++, end++) { - f2fs_balance_fs(sbi); + f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); ret = __exchange_data_block(inode, end, start, true); f2fs_unlock_op(sbi); @@ -941,13 +946,9 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1)) return -EINVAL; - f2fs_balance_fs(F2FS_I_SB(inode)); - - if (f2fs_has_inline_data(inode)) { - ret = f2fs_convert_inline_inode(inode); - if (ret) - return ret; - } + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; pg_start = offset >> PAGE_CACHE_SHIFT; pg_end = (offset + len) >> PAGE_CACHE_SHIFT; @@ -991,13 +992,9 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, if (ret) return ret; - f2fs_balance_fs(sbi); - - if (f2fs_has_inline_data(inode)) { - ret = f2fs_convert_inline_inode(inode); - if (ret) - return ret; - } + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1); if (ret) @@ -1104,13 +1101,11 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1)) return -EINVAL; - f2fs_balance_fs(sbi); + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; - if (f2fs_has_inline_data(inode)) { - ret = f2fs_convert_inline_inode(inode); - if (ret) - return ret; - } + f2fs_balance_fs(sbi, true); ret = truncate_blocks(inode, i_size_read(inode), true); if (ret) @@ -1154,17 +1149,15 @@ static int expand_inode_data(struct inode *inode, loff_t offset, loff_t off_start, off_end; int ret = 0; - f2fs_balance_fs(sbi); - ret = inode_newsize_ok(inode, (len + offset)); if (ret) return ret; - if (f2fs_has_inline_data(inode)) { - ret = f2fs_convert_inline_inode(inode); - if (ret) - return ret; - } + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; + + f2fs_balance_fs(sbi, true); pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; @@ -1246,6 +1239,7 @@ static long f2fs_fallocate(struct file *file, int mode, if (!ret) { inode->i_mtime = inode->i_ctime = CURRENT_TIME; mark_inode_dirty(inode); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); } out: @@ -1353,8 +1347,6 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) if (!inode_owner_or_capable(inode)) return -EACCES; - f2fs_balance_fs(F2FS_I_SB(inode)); - if (f2fs_is_atomic_file(inode)) return 0; @@ -1363,6 +1355,8 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) return ret; set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + return 0; } @@ -1384,8 +1378,10 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) if (f2fs_is_atomic_file(inode)) { clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); ret = commit_inmem_pages(inode, false); - if (ret) + if (ret) { + set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); goto err_out; + } } ret = f2fs_sync_file(filp, 0, LLONG_MAX, 0); @@ -1410,6 +1406,7 @@ static int f2fs_ioc_start_volatile_write(struct file *filp) return ret; set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return 0; } @@ -1441,13 +1438,17 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp) if (ret) return ret; - f2fs_balance_fs(F2FS_I_SB(inode)); - - clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); - clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); - commit_inmem_pages(inode, true); + if (f2fs_is_atomic_file(inode)) { + clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); + commit_inmem_pages(inode, true); + } + if (f2fs_is_volatile_file(inode)) { + clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); + ret = f2fs_sync_file(filp, 0, LLONG_MAX, 0); + } mnt_drop_write_file(filp); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return ret; } @@ -1487,6 +1488,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) default: return -EINVAL; } + f2fs_update_time(sbi, REQ_TIME); return 0; } @@ -1517,6 +1519,7 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range))) return -EFAULT; + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return 0; } @@ -1540,6 +1543,7 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg) sizeof(policy))) return -EFAULT; + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return f2fs_process_policy(&policy, inode); #else return -EOPNOTSUPP; @@ -1586,13 +1590,13 @@ static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) generate_random_uuid(sbi->raw_super->encrypt_pw_salt); err = f2fs_commit_super(sbi, false); - - mnt_drop_write_file(filp); if (err) { /* undo new data */ memset(sbi->raw_super->encrypt_pw_salt, 0, 16); + mnt_drop_write_file(filp); return err; } + mnt_drop_write_file(filp); got_it: if (copy_to_user((__u8 __user *)arg, sbi->raw_super->encrypt_pw_salt, 16)) @@ -1629,7 +1633,6 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct cp_control cpc; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1637,13 +1640,196 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; - cpc.reason = __get_cp_reason(sbi); + return f2fs_sync_fs(sbi->sb, 1); +} - mutex_lock(&sbi->gc_mutex); - write_checkpoint(sbi, &cpc); - mutex_unlock(&sbi->gc_mutex); +static int f2fs_defragment_range(struct f2fs_sb_info *sbi, + struct file *filp, + struct f2fs_defragment *range) +{ + struct inode *inode = file_inode(filp); + struct f2fs_map_blocks map; + struct extent_info ei; + pgoff_t pg_start, pg_end; + unsigned int blk_per_seg = sbi->blocks_per_seg; + unsigned int total = 0, sec_num; + unsigned int pages_per_sec = sbi->segs_per_sec * blk_per_seg; + block_t blk_end = 0; + bool fragmented = false; + int err; - return 0; + /* if in-place-update policy is enabled, don't waste time here */ + if (need_inplace_update(inode)) + return -EINVAL; + + pg_start = range->start >> PAGE_CACHE_SHIFT; + pg_end = (range->start + range->len) >> PAGE_CACHE_SHIFT; + + f2fs_balance_fs(sbi, true); + + mutex_lock(&inode->i_mutex); + + /* writeback all dirty pages in the range */ + err = filemap_write_and_wait_range(inode->i_mapping, range->start, + range->start + range->len - 1); + if (err) + goto out; + + /* + * lookup mapping info in extent cache, skip defragmenting if physical + * block addresses are continuous. + */ + if (f2fs_lookup_extent_cache(inode, pg_start, &ei)) { + if (ei.fofs + ei.len >= pg_end) + goto out; + } + + map.m_lblk = pg_start; + + /* + * lookup mapping info in dnode page cache, skip defragmenting if all + * physical block addresses are continuous even if there are hole(s) + * in logical blocks. + */ + while (map.m_lblk < pg_end) { + map.m_len = pg_end - map.m_lblk; + err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ); + if (err) + goto out; + + if (!(map.m_flags & F2FS_MAP_FLAGS)) { + map.m_lblk++; + continue; + } + + if (blk_end && blk_end != map.m_pblk) { + fragmented = true; + break; + } + blk_end = map.m_pblk + map.m_len; + + map.m_lblk += map.m_len; + } + + if (!fragmented) + goto out; + + map.m_lblk = pg_start; + map.m_len = pg_end - pg_start; + + sec_num = (map.m_len + pages_per_sec - 1) / pages_per_sec; + + /* + * make sure there are enough free section for LFS allocation, this can + * avoid defragment running in SSR mode when free section are allocated + * intensively + */ + if (has_not_enough_free_secs(sbi, sec_num)) { + err = -EAGAIN; + goto out; + } + + while (map.m_lblk < pg_end) { + pgoff_t idx; + int cnt = 0; + +do_map: + map.m_len = pg_end - map.m_lblk; + err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ); + if (err) + goto clear_out; + + if (!(map.m_flags & F2FS_MAP_FLAGS)) { + map.m_lblk++; + continue; + } + + set_inode_flag(F2FS_I(inode), FI_DO_DEFRAG); + + idx = map.m_lblk; + while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) { + struct page *page; + + page = get_lock_data_page(inode, idx, true); + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto clear_out; + } + + set_page_dirty(page); + f2fs_put_page(page, 1); + + idx++; + cnt++; + total++; + } + + map.m_lblk = idx; + + if (idx < pg_end && cnt < blk_per_seg) + goto do_map; + + clear_inode_flag(F2FS_I(inode), FI_DO_DEFRAG); + + err = filemap_fdatawrite(inode->i_mapping); + if (err) + goto out; + } +clear_out: + clear_inode_flag(F2FS_I(inode), FI_DO_DEFRAG); +out: + mutex_unlock(&inode->i_mutex); + if (!err) + range->len = (u64)total << PAGE_CACHE_SHIFT; + return err; +} + +static int f2fs_ioc_defragment(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_defragment range; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!S_ISREG(inode->i_mode)) + return -EINVAL; + + err = mnt_want_write_file(filp); + if (err) + return err; + + if (f2fs_readonly(sbi->sb)) { + err = -EROFS; + goto out; + } + + if (copy_from_user(&range, (struct f2fs_defragment __user *)arg, + sizeof(range))) { + err = -EFAULT; + goto out; + } + + /* verify alignment of offset & size */ + if (range.start & (F2FS_BLKSIZE - 1) || + range.len & (F2FS_BLKSIZE - 1)) { + err = -EINVAL; + goto out; + } + + err = f2fs_defragment_range(sbi, filp, &range); + f2fs_update_time(sbi, REQ_TIME); + if (err < 0) + goto out; + + if (copy_to_user((struct f2fs_defragment __user *)arg, &range, + sizeof(range))) + err = -EFAULT; +out: + mnt_drop_write_file(filp); + return err; } long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) @@ -1679,6 +1865,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_gc(filp, arg); case F2FS_IOC_WRITE_CHECKPOINT: return f2fs_ioc_write_checkpoint(filp, arg); + case F2FS_IOC_DEFRAGMENT: + return f2fs_ioc_defragment(filp, arg); default: return -ENOTTY; } @@ -1706,6 +1894,22 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC32_SETFLAGS: cmd = F2FS_IOC_SETFLAGS; break; + case F2FS_IOC32_GETVERSION: + cmd = F2FS_IOC_GETVERSION; + break; + case F2FS_IOC_START_ATOMIC_WRITE: + case F2FS_IOC_COMMIT_ATOMIC_WRITE: + case F2FS_IOC_START_VOLATILE_WRITE: + case F2FS_IOC_RELEASE_VOLATILE_WRITE: + case F2FS_IOC_ABORT_VOLATILE_WRITE: + case F2FS_IOC_SHUTDOWN: + case F2FS_IOC_SET_ENCRYPTION_POLICY: + case F2FS_IOC_GET_ENCRYPTION_PWSALT: + case F2FS_IOC_GET_ENCRYPTION_POLICY: + case F2FS_IOC_GARBAGE_COLLECT: + case F2FS_IOC_WRITE_CHECKPOINT: + case F2FS_IOC_DEFRAGMENT: + break; default: return -ENOIOCTLCMD; } diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index fedbf67a0842..f610c2a9bdde 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -16,7 +16,6 @@ #include <linux/kthread.h> #include <linux/delay.h> #include <linux/freezer.h> -#include <linux/blkdev.h> #include "f2fs.h" #include "node.h" @@ -173,9 +172,9 @@ static unsigned int get_max_cost(struct f2fs_sb_info *sbi, { /* SSR allocates in a segment unit */ if (p->alloc_mode == SSR) - return 1 << sbi->log_blocks_per_seg; + return sbi->blocks_per_seg; if (p->gc_mode == GC_GREEDY) - return (1 << sbi->log_blocks_per_seg) * p->ofs_unit; + return sbi->blocks_per_seg * p->ofs_unit; else if (p->gc_mode == GC_CB) return UINT_MAX; else /* No other gc_mode */ @@ -832,8 +831,10 @@ gc_more: if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) goto stop; - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi))) { + ret = -EIO; goto stop; + } if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed)) { gc_type = FG_GC; diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index b4a65be9f7d3..a993967dcdb9 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -100,11 +100,3 @@ static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi) return true; return false; } - -static inline int is_idle(struct f2fs_sb_info *sbi) -{ - struct block_device *bdev = sbi->sb->s_bdev; - struct request_queue *q = bdev_get_queue(bdev); - struct request_list *rl = &q->root_rl; - return !(rl->count[BLK_RW_SYNC]) && !(rl->count[BLK_RW_ASYNC]); -} diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index bda7126466c0..c3f0b7d4cfca 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -16,9 +16,6 @@ bool f2fs_may_inline_data(struct inode *inode) { - if (!test_opt(F2FS_I_SB(inode), INLINE_DATA)) - return false; - if (f2fs_is_atomic_file(inode)) return false; @@ -177,6 +174,9 @@ int f2fs_convert_inline_inode(struct inode *inode) struct page *ipage, *page; int err = 0; + if (!f2fs_has_inline_data(inode)) + return 0; + page = grab_cache_page(inode->i_mapping, 0); if (!page) return -ENOMEM; @@ -199,6 +199,9 @@ out: f2fs_unlock_op(sbi); f2fs_put_page(page, 1); + + f2fs_balance_fs(sbi, dn.node_changed); + return err; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 97e20decacb4..2adeff26be11 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -138,7 +138,8 @@ static int do_read_inode(struct inode *inode) fi->i_pino = le32_to_cpu(ri->i_pino); fi->i_dir_level = ri->i_dir_level; - f2fs_init_extent_tree(inode, &ri->i_ext); + if (f2fs_init_extent_tree(inode, &ri->i_ext)) + set_page_dirty(node_page); get_inline_info(fi, ri); @@ -202,6 +203,7 @@ make_now: inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &f2fs_dblock_aops; } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { @@ -221,7 +223,7 @@ bad_inode: return ERR_PTR(ret); } -void update_inode(struct inode *inode, struct page *node_page) +int update_inode(struct inode *inode, struct page *node_page) { struct f2fs_inode *ri; @@ -259,15 +261,16 @@ void update_inode(struct inode *inode, struct page *node_page) __set_inode_rdev(inode, ri); set_cold_node(inode, node_page); - set_page_dirty(node_page); - clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE); + + return set_page_dirty(node_page); } -void update_inode_page(struct inode *inode) +int update_inode_page(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *node_page; + int ret = 0; retry: node_page = get_node_page(sbi, inode->i_ino); if (IS_ERR(node_page)) { @@ -278,10 +281,11 @@ retry: } else if (err != -ENOENT) { f2fs_stop_checkpoint(sbi); } - return; + return 0; } - update_inode(inode, node_page); + ret = update_inode(inode, node_page); f2fs_put_page(node_page, 1); + return ret; } int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) @@ -299,9 +303,8 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) * We need to balance fs here to prevent from producing dirty node pages * during the urgent cleaning time when runing out of free sections. */ - update_inode_page(inode); - - f2fs_balance_fs(sbi); + if (update_inode_page(inode)) + f2fs_balance_fs(sbi, true); return 0; } @@ -327,7 +330,7 @@ void f2fs_evict_inode(struct inode *inode) goto out_clear; f2fs_bug_on(sbi, get_dirty_pages(inode)); - remove_dirty_dir_inode(inode); + remove_dirty_inode(inode); f2fs_destroy_extent_tree(inode); @@ -357,9 +360,9 @@ no_delete: if (xnid) invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid); if (is_inode_flag_set(fi, FI_APPEND_WRITE)) - add_dirty_inode(sbi, inode->i_ino, APPEND_INO); + add_ino_entry(sbi, inode->i_ino, APPEND_INO); if (is_inode_flag_set(fi, FI_UPDATE_WRITE)) - add_dirty_inode(sbi, inode->i_ino, UPDATE_INO); + add_ino_entry(sbi, inode->i_ino, UPDATE_INO); if (is_inode_flag_set(fi, FI_FREE_NID)) { if (err && err != -ENOENT) alloc_nid_done(sbi, inode->i_ino); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index e48b80c49090..6f944e5eb76e 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -60,7 +60,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) f2fs_set_encrypted_inode(inode); - if (f2fs_may_inline_data(inode)) + if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode)) set_inode_flag(F2FS_I(inode), FI_INLINE_DATA); if (f2fs_may_inline_dentry(inode)) set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY); @@ -128,8 +128,6 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, nid_t ino = 0; int err; - f2fs_balance_fs(sbi); - inode = f2fs_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -142,6 +140,8 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, inode->i_mapping->a_ops = &f2fs_dblock_aops; ino = inode->i_ino; + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) @@ -172,7 +172,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, !f2fs_is_child_context_consistent_with_parent(dir, inode)) return -EPERM; - f2fs_balance_fs(sbi); + f2fs_balance_fs(sbi, true); inode->i_ctime = CURRENT_TIME; ihold(inode); @@ -214,6 +214,15 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino) struct page *page; int err = 0; + if (f2fs_readonly(sbi->sb)) { + f2fs_msg(sbi->sb, KERN_INFO, + "skip recovering inline_dots inode (ino:%lu, pino:%u) " + "in readonly mountpoint", dir->i_ino, pino); + return 0; + } + + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); de = f2fs_find_entry(dir, &dot, &page); @@ -288,12 +297,13 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) int err = -ENOENT; trace_f2fs_unlink_enter(dir, dentry); - f2fs_balance_fs(sbi); de = f2fs_find_entry(dir, &dentry->d_name, &page); if (!de) goto fail; + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = acquire_orphan_inode(sbi); if (err) { @@ -315,12 +325,15 @@ fail: return err; } -static const char *f2fs_follow_link(struct dentry *dentry, void **cookie) +static const char *f2fs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - const char *link = page_follow_link_light(dentry, cookie); + const char *link = page_get_link(dentry, inode, done); if (!IS_ERR(link) && !*link) { /* this is broken symlink case */ - page_put_link(NULL, *cookie); + do_delayed_call(done); + clear_delayed_call(done); link = ERR_PTR(-ENOENT); } return link; @@ -341,8 +354,6 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, if (len > dir->i_sb->s_blocksize) return -ENAMETOOLONG; - f2fs_balance_fs(sbi); - inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -351,8 +362,11 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &f2fs_dblock_aops; + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) @@ -433,8 +447,6 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) struct inode *inode; int err; - f2fs_balance_fs(sbi); - inode = f2fs_new_inode(dir, S_IFDIR | mode); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -444,6 +456,8 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) inode->i_mapping->a_ops = &f2fs_dblock_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO); + f2fs_balance_fs(sbi, true); + set_inode_flag(F2FS_I(inode), FI_INC_LINK); f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); @@ -481,11 +495,6 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, struct inode *inode; int err = 0; - if (!new_valid_dev(rdev)) - return -EINVAL; - - f2fs_balance_fs(sbi); - inode = f2fs_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -493,6 +502,8 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, init_special_inode(inode, inode->i_mode, rdev); inode->i_op = &f2fs_special_inode_operations; + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) @@ -519,9 +530,6 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, struct inode *inode; int err; - if (!whiteout) - f2fs_balance_fs(sbi); - inode = f2fs_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -535,6 +543,8 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, inode->i_mapping->a_ops = &f2fs_dblock_aops; } + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = acquire_orphan_inode(sbi); if (err) @@ -607,8 +617,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out; } - f2fs_balance_fs(sbi); - old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); if (!old_entry) goto out; @@ -638,6 +646,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (!new_entry) goto out_whiteout; + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = acquire_orphan_inode(sbi); @@ -669,6 +679,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, update_inode_page(old_inode); update_inode_page(new_inode); } else { + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = f2fs_add_link(new_dentry, old_inode); @@ -766,8 +778,6 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, new_inode))) return -EPERM; - f2fs_balance_fs(sbi); - old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); if (!old_entry) goto out; @@ -810,6 +820,8 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, goto out_new_dir; } + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = update_dent_inode(old_inode, new_inode, &new_dentry->d_name); @@ -926,18 +938,22 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry, } #ifdef CONFIG_F2FS_FS_ENCRYPTION -static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cookie) +static const char *f2fs_encrypted_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { struct page *cpage = NULL; char *caddr, *paddr = NULL; - struct f2fs_str cstr; + struct f2fs_str cstr = FSTR_INIT(NULL, 0); struct f2fs_str pstr = FSTR_INIT(NULL, 0); - struct inode *inode = d_inode(dentry); struct f2fs_encrypted_symlink_data *sd; loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1); u32 max_size = inode->i_sb->s_blocksize; int res; + if (!dentry) + return ERR_PTR(-ECHILD); + res = f2fs_get_encryption_info(inode); if (res) return ERR_PTR(res); @@ -945,12 +961,18 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook cpage = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(cpage)) return ERR_CAST(cpage); - caddr = kmap(cpage); + caddr = page_address(cpage); caddr[size] = 0; /* Symlink is encrypted */ sd = (struct f2fs_encrypted_symlink_data *)caddr; cstr.len = le16_to_cpu(sd->len); + + /* this is broken symlink case */ + if (unlikely(cstr.len == 0)) { + res = -ENOENT; + goto errout; + } cstr.name = kmalloc(cstr.len, GFP_NOFS); if (!cstr.name) { res = -ENOMEM; @@ -959,7 +981,7 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook memcpy(cstr.name, sd->encrypted_path, cstr.len); /* this is broken symlink case */ - if (cstr.name[0] == 0 && cstr.len == 0) { + if (unlikely(cstr.name[0] == 0)) { res = -ENOENT; goto errout; } @@ -985,27 +1007,27 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook /* Null-terminate the name */ paddr[res] = '\0'; - kunmap(cpage); page_cache_release(cpage); - return *cookie = paddr; + set_delayed_call(done, kfree_link, paddr); + return paddr; errout: kfree(cstr.name); f2fs_fname_crypto_free_buffer(&pstr); - kunmap(cpage); page_cache_release(cpage); return ERR_PTR(res); } const struct inode_operations f2fs_encrypted_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = f2fs_encrypted_follow_link, - .put_link = kfree_put_link, + .get_link = f2fs_encrypted_get_link, .getattr = f2fs_getattr, .setattr = f2fs_setattr, +#ifdef CONFIG_F2FS_FS_XATTR .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = f2fs_listxattr, .removexattr = generic_removexattr, +#endif }; #endif @@ -1034,8 +1056,7 @@ const struct inode_operations f2fs_dir_inode_operations = { const struct inode_operations f2fs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = f2fs_follow_link, - .put_link = page_put_link, + .get_link = f2fs_get_link, .getattr = f2fs_getattr, .setattr = f2fs_setattr, #ifdef CONFIG_F2FS_FS_XATTR diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 7bcbc6e9c40d..342597a5897f 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -65,13 +65,14 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) sizeof(struct ino_entry)) >> PAGE_CACHE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } else if (type == EXTENT_CACHE) { - mem_size = (sbi->total_ext_tree * sizeof(struct extent_tree) + + mem_size = (atomic_read(&sbi->total_ext_tree) * + sizeof(struct extent_tree) + atomic_read(&sbi->total_ext_node) * sizeof(struct extent_node)) >> PAGE_CACHE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } else { - if (sbi->sb->s_bdi->wb.dirty_exceeded) - return false; + if (!sbi->sb->s_bdi->wb.dirty_exceeded) + return true; } return res; } @@ -261,13 +262,11 @@ static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid, { struct nat_entry *e; - down_write(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (!e) { e = grab_nat_entry(nm_i, nid); node_info_from_raw_nat(&e->ni, ne); } - up_write(&nm_i->nat_tree_lock); } static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, @@ -379,6 +378,8 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) memset(&ne, 0, sizeof(struct f2fs_nat_entry)); + down_write(&nm_i->nat_tree_lock); + /* Check current segment summary */ mutex_lock(&curseg->curseg_mutex); i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0); @@ -399,6 +400,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) cache: /* cache nat entry */ cache_nat_entry(NM_I(sbi), nid, &ne); + up_write(&nm_i->nat_tree_lock); } /* @@ -676,7 +678,8 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, ret = truncate_dnode(&rdn); if (ret < 0) goto out_err; - set_nid(page, i, 0, false); + if (set_nid(page, i, 0, false)) + dn->node_changed = true; } } else { child_nofs = nofs + ofs * (NIDS_PER_BLOCK + 1) + 1; @@ -689,7 +692,8 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, rdn.nid = child_nid; ret = truncate_nodes(&rdn, child_nofs, 0, depth - 1); if (ret == (NIDS_PER_BLOCK + 1)) { - set_nid(page, i, 0, false); + if (set_nid(page, i, 0, false)) + dn->node_changed = true; child_nofs += ret; } else if (ret < 0 && ret != -ENOENT) { goto out_err; @@ -750,7 +754,8 @@ static int truncate_partial_nodes(struct dnode_of_data *dn, err = truncate_dnode(dn); if (err < 0) goto fail; - set_nid(pages[idx], i, 0, false); + if (set_nid(pages[idx], i, 0, false)) + dn->node_changed = true; } if (offset[idx + 1] == 0) { @@ -975,7 +980,8 @@ struct page *new_node_page(struct dnode_of_data *dn, fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true); set_cold_node(dn->inode, page); SetPageUptodate(page); - set_page_dirty(page); + if (set_page_dirty(page)) + dn->node_changed = true; if (f2fs_has_xattr_block(ofs)) F2FS_I(dn->inode)->i_xattr_nid = dn->nid; @@ -1035,6 +1041,10 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) struct page *apage; int err; + if (!nid) + return; + f2fs_bug_on(sbi, check_nid_range(sbi, nid)); + apage = find_get_page(NODE_MAPPING(sbi), nid); if (apage && PageUptodate(apage)) { f2fs_put_page(apage, 0); @@ -1050,51 +1060,38 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) f2fs_put_page(apage, err ? 1 : 0); } -struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) +/* + * readahead MAX_RA_NODE number of node pages. + */ +void ra_node_pages(struct page *parent, int start) { - struct page *page; - int err; -repeat: - page = grab_cache_page(NODE_MAPPING(sbi), nid); - if (!page) - return ERR_PTR(-ENOMEM); + struct f2fs_sb_info *sbi = F2FS_P_SB(parent); + struct blk_plug plug; + int i, end; + nid_t nid; - err = read_node_page(page, READ_SYNC); - if (err < 0) { - f2fs_put_page(page, 1); - return ERR_PTR(err); - } else if (err != LOCKED_PAGE) { - lock_page(page); - } + blk_start_plug(&plug); - if (unlikely(!PageUptodate(page) || nid != nid_of_node(page))) { - ClearPageUptodate(page); - f2fs_put_page(page, 1); - return ERR_PTR(-EIO); - } - if (unlikely(page->mapping != NODE_MAPPING(sbi))) { - f2fs_put_page(page, 1); - goto repeat; + /* Then, try readahead for siblings of the desired node */ + end = start + MAX_RA_NODE; + end = min(end, NIDS_PER_BLOCK); + for (i = start; i < end; i++) { + nid = get_nid(parent, i, false); + ra_node_page(sbi, nid); } - return page; + + blk_finish_plug(&plug); } -/* - * Return a locked page for the desired node page. - * And, readahead MAX_RA_NODE number of node pages. - */ -struct page *get_node_page_ra(struct page *parent, int start) +struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid, + struct page *parent, int start) { - struct f2fs_sb_info *sbi = F2FS_P_SB(parent); - struct blk_plug plug; struct page *page; - int err, i, end; - nid_t nid; + int err; - /* First, try getting the desired direct node. */ - nid = get_nid(parent, start, false); if (!nid) return ERR_PTR(-ENOENT); + f2fs_bug_on(sbi, check_nid_range(sbi, nid)); repeat: page = grab_cache_page(NODE_MAPPING(sbi), nid); if (!page) @@ -1108,46 +1105,53 @@ repeat: goto page_hit; } - blk_start_plug(&plug); - - /* Then, try readahead for siblings of the desired node */ - end = start + MAX_RA_NODE; - end = min(end, NIDS_PER_BLOCK); - for (i = start + 1; i < end; i++) { - nid = get_nid(parent, i, false); - if (!nid) - continue; - ra_node_page(sbi, nid); - } - - blk_finish_plug(&plug); + if (parent) + ra_node_pages(parent, start + 1); lock_page(page); + + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 1); + return ERR_PTR(-EIO); + } if (unlikely(page->mapping != NODE_MAPPING(sbi))) { f2fs_put_page(page, 1); goto repeat; } page_hit: - if (unlikely(!PageUptodate(page))) { - f2fs_put_page(page, 1); - return ERR_PTR(-EIO); - } + f2fs_bug_on(sbi, nid != nid_of_node(page)); return page; } +struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) +{ + return __get_node_page(sbi, nid, NULL, 0); +} + +struct page *get_node_page_ra(struct page *parent, int start) +{ + struct f2fs_sb_info *sbi = F2FS_P_SB(parent); + nid_t nid = get_nid(parent, start, false); + + return __get_node_page(sbi, nid, parent, start); +} + void sync_inode_page(struct dnode_of_data *dn) { + int ret = 0; + if (IS_INODE(dn->node_page) || dn->inode_page == dn->node_page) { - update_inode(dn->inode, dn->node_page); + ret = update_inode(dn->inode, dn->node_page); } else if (dn->inode_page) { if (!dn->inode_page_locked) lock_page(dn->inode_page); - update_inode(dn->inode, dn->inode_page); + ret = update_inode(dn->inode, dn->inode_page); if (!dn->inode_page_locked) unlock_page(dn->inode_page); } else { - update_inode_page(dn->inode); + ret = update_inode_page(dn->inode); } + dn->node_changed = ret ? true: false; } int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino, @@ -1175,6 +1179,11 @@ next_step: for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; + if (unlikely(f2fs_cp_error(sbi))) { + pagevec_release(&pvec); + return -EIO; + } + /* * flushing sequence with step: * 0. indirect nodes @@ -1349,7 +1358,7 @@ static int f2fs_write_node_page(struct page *page, up_read(&sbi->node_write); unlock_page(page); - if (wbc->for_reclaim) + if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi))) f2fs_submit_merged_bio(sbi, NODE, WRITE); return 0; @@ -1440,13 +1449,10 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) if (build) { /* do not add allocated nids */ - down_read(&nm_i->nat_tree_lock); ne = __lookup_nat_cache(nm_i, nid); - if (ne && - (!get_nat_flag(ne, IS_CHECKPOINTED) || + if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) || nat_get_blkaddr(ne) != NULL_ADDR)) allocated = true; - up_read(&nm_i->nat_tree_lock); if (allocated) return 0; } @@ -1532,6 +1538,8 @@ static void build_free_nids(struct f2fs_sb_info *sbi) ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT, true); + down_read(&nm_i->nat_tree_lock); + while (1) { struct page *page = get_current_nat_page(sbi, nid); @@ -1560,6 +1568,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi) remove_free_nid(nm_i, nid); } mutex_unlock(&curseg->curseg_mutex); + up_read(&nm_i->nat_tree_lock); ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), nm_i->ra_nid_pages, META_NAT, false); @@ -1582,8 +1591,6 @@ retry: /* We should not use stale free nids created by build_free_nids */ if (nm_i->fcnt && !on_build_free_nids(nm_i)) { - struct node_info ni; - f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list)); list_for_each_entry(i, &nm_i->free_nid_list, list) if (i->state == NID_NEW) @@ -1594,13 +1601,6 @@ retry: i->state = NID_ALLOC; nm_i->fcnt--; spin_unlock(&nm_i->free_nid_list_lock); - - /* check nid is allocated already */ - get_node_info(sbi, *nid, &ni); - if (ni.blk_addr != NULL_ADDR) { - alloc_nid_done(sbi, *nid); - goto retry; - } return true; } spin_unlock(&nm_i->free_nid_list_lock); @@ -1842,14 +1842,12 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi) raw_ne = nat_in_journal(sum, i); - down_write(&nm_i->nat_tree_lock); ne = __lookup_nat_cache(nm_i, nid); if (!ne) { ne = grab_nat_entry(nm_i, nid); node_info_from_raw_nat(&ne->ni, &raw_ne); } __set_nat_cache_dirty(nm_i, ne); - up_write(&nm_i->nat_tree_lock); } update_nats_in_cursum(sum, -i); mutex_unlock(&curseg->curseg_mutex); @@ -1883,7 +1881,6 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, struct f2fs_nat_block *nat_blk; struct nat_entry *ne, *cur; struct page *page = NULL; - struct f2fs_nm_info *nm_i = NM_I(sbi); /* * there are two steps to flush nat entries: @@ -1920,12 +1917,8 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, raw_ne = &nat_blk->entries[nid - start_nid]; } raw_nat_from_node_info(raw_ne, &ne->ni); - - down_write(&NM_I(sbi)->nat_tree_lock); nat_reset_flag(ne); __clear_nat_cache_dirty(NM_I(sbi), ne); - up_write(&NM_I(sbi)->nat_tree_lock); - if (nat_get_blkaddr(ne) == NULL_ADDR) add_free_nid(sbi, nid, false); } @@ -1937,9 +1930,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, set->entry_cnt); - down_write(&nm_i->nat_tree_lock); radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set); - up_write(&nm_i->nat_tree_lock); kmem_cache_free(nat_entry_set_slab, set); } @@ -1959,6 +1950,9 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) if (!nm_i->dirty_nat_cnt) return; + + down_write(&nm_i->nat_tree_lock); + /* * if there are no enough space in journal to store dirty nat * entries, remove all entries from journal and merge them @@ -1967,7 +1961,6 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL)) remove_nats_in_journal(sbi); - down_write(&nm_i->nat_tree_lock); while ((found = __gang_lookup_nat_set(nm_i, set_idx, SETVEC_SIZE, setvec))) { unsigned idx; @@ -1976,12 +1969,13 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) __adjust_nat_entry_set(setvec[idx], &sets, MAX_NAT_JENTRIES(sum)); } - up_write(&nm_i->nat_tree_lock); /* flush dirty nats in nat entry set */ list_for_each_entry_safe(set, tmp, &sets, set_list) __flush_nat_entry_set(sbi, set); + up_write(&nm_i->nat_tree_lock); + f2fs_bug_on(sbi, nm_i->dirty_nat_cnt); } diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index e4fffd2d98c4..d4d1f636fe1c 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -183,7 +183,7 @@ static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start) block_addr = (pgoff_t)(nm_i->nat_blkaddr + (seg_off << sbi->log_blocks_per_seg << 1) + - (block_off & ((1 << sbi->log_blocks_per_seg) - 1))); + (block_off & (sbi->blocks_per_seg - 1))); if (f2fs_test_bit(block_off, nm_i->nat_bitmap)) block_addr += sbi->blocks_per_seg; @@ -317,7 +317,7 @@ static inline bool IS_DNODE(struct page *node_page) return true; } -static inline void set_nid(struct page *p, int off, nid_t nid, bool i) +static inline int set_nid(struct page *p, int off, nid_t nid, bool i) { struct f2fs_node *rn = F2FS_NODE(p); @@ -327,7 +327,7 @@ static inline void set_nid(struct page *p, int off, nid_t nid, bool i) rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid); else rn->in.nid[off] = cpu_to_le32(nid); - set_page_dirty(p); + return set_page_dirty(p); } static inline nid_t get_nid(struct page *p, int off, bool i) diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index cbf74f47cce8..589b20b8677b 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -168,6 +168,32 @@ static void recover_inode(struct inode *inode, struct page *page) ino_of_node(page), name); } +static bool is_same_inode(struct inode *inode, struct page *ipage) +{ + struct f2fs_inode *ri = F2FS_INODE(ipage); + struct timespec disk; + + if (!IS_INODE(ipage)) + return true; + + disk.tv_sec = le64_to_cpu(ri->i_ctime); + disk.tv_nsec = le32_to_cpu(ri->i_ctime_nsec); + if (timespec_compare(&inode->i_ctime, &disk) > 0) + return false; + + disk.tv_sec = le64_to_cpu(ri->i_atime); + disk.tv_nsec = le32_to_cpu(ri->i_atime_nsec); + if (timespec_compare(&inode->i_atime, &disk) > 0) + return false; + + disk.tv_sec = le64_to_cpu(ri->i_mtime); + disk.tv_nsec = le32_to_cpu(ri->i_mtime_nsec); + if (timespec_compare(&inode->i_mtime, &disk) > 0) + return false; + + return true; +} + static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) { unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi)); @@ -197,7 +223,10 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) goto next; entry = get_fsync_inode(head, ino_of_node(page)); - if (!entry) { + if (entry) { + if (!is_same_inode(entry->inode, page)) + goto next; + } else { if (IS_INODE(page) && is_dent_dnode(page)) { err = recover_inode_page(sbi, page); if (err) @@ -459,8 +488,7 @@ out: return err; } -static int recover_data(struct f2fs_sb_info *sbi, - struct list_head *head, int type) +static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head) { unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi)); struct curseg_info *curseg; @@ -469,7 +497,7 @@ static int recover_data(struct f2fs_sb_info *sbi, block_t blkaddr; /* get node pages in the current segment */ - curseg = CURSEG_I(sbi, type); + curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); while (1) { @@ -556,7 +584,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi) need_writecp = true; /* step #2: recover data */ - err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE); + err = recover_data(sbi, &inode_list); if (!err) f2fs_bug_on(sbi, !list_empty(&inode_list)); out: @@ -595,7 +623,7 @@ out: .reason = CP_RECOVERY, }; mutex_unlock(&sbi->cp_mutex); - write_checkpoint(sbi, &cpc); + err = write_checkpoint(sbi, &cpc); } else { mutex_unlock(&sbi->cp_mutex); } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index f77b3258454a..5904a411c86f 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -86,6 +86,7 @@ static inline unsigned long __reverse_ffs(unsigned long word) /* * __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c because * f2fs_set_bit makes MSB and LSB reversed in a byte. + * @size must be integral times of unsigned long. * Example: * MSB <--> LSB * f2fs_set_bit(0, bitmap) => 1000 0000 @@ -95,94 +96,73 @@ static unsigned long __find_rev_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { const unsigned long *p = addr + BIT_WORD(offset); - unsigned long result = offset & ~(BITS_PER_LONG - 1); + unsigned long result = size; unsigned long tmp; if (offset >= size) return size; - size -= result; + size -= (offset & ~(BITS_PER_LONG - 1)); offset %= BITS_PER_LONG; - if (!offset) - goto aligned; - - tmp = __reverse_ulong((unsigned char *)p); - tmp &= ~0UL >> offset; - - if (size < BITS_PER_LONG) - goto found_first; - if (tmp) - goto found_middle; - - size -= BITS_PER_LONG; - result += BITS_PER_LONG; - p++; -aligned: - while (size & ~(BITS_PER_LONG-1)) { + + while (1) { + if (*p == 0) + goto pass; + tmp = __reverse_ulong((unsigned char *)p); + + tmp &= ~0UL >> offset; + if (size < BITS_PER_LONG) + tmp &= (~0UL << (BITS_PER_LONG - size)); if (tmp) - goto found_middle; - result += BITS_PER_LONG; + goto found; +pass: + if (size <= BITS_PER_LONG) + break; size -= BITS_PER_LONG; + offset = 0; p++; } - if (!size) - return result; - - tmp = __reverse_ulong((unsigned char *)p); -found_first: - tmp &= (~0UL << (BITS_PER_LONG - size)); - if (!tmp) /* Are any bits set? */ - return result + size; /* Nope. */ -found_middle: - return result + __reverse_ffs(tmp); + return result; +found: + return result - size + __reverse_ffs(tmp); } static unsigned long __find_rev_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { const unsigned long *p = addr + BIT_WORD(offset); - unsigned long result = offset & ~(BITS_PER_LONG - 1); + unsigned long result = size; unsigned long tmp; if (offset >= size) return size; - size -= result; + size -= (offset & ~(BITS_PER_LONG - 1)); offset %= BITS_PER_LONG; - if (!offset) - goto aligned; - - tmp = __reverse_ulong((unsigned char *)p); - tmp |= ~((~0UL << offset) >> offset); - - if (size < BITS_PER_LONG) - goto found_first; - if (tmp != ~0UL) - goto found_middle; - - size -= BITS_PER_LONG; - result += BITS_PER_LONG; - p++; -aligned: - while (size & ~(BITS_PER_LONG - 1)) { + + while (1) { + if (*p == ~0UL) + goto pass; + tmp = __reverse_ulong((unsigned char *)p); + + if (offset) + tmp |= ~0UL << (BITS_PER_LONG - offset); + if (size < BITS_PER_LONG) + tmp |= ~0UL >> size; if (tmp != ~0UL) - goto found_middle; - result += BITS_PER_LONG; + goto found; +pass: + if (size <= BITS_PER_LONG) + break; size -= BITS_PER_LONG; + offset = 0; p++; } - if (!size) - return result; - - tmp = __reverse_ulong((unsigned char *)p); -found_first: - tmp |= ~(~0UL << (BITS_PER_LONG - size)); - if (tmp == ~0UL) /* Are any bits zero? */ - return result + size; /* Nope. */ -found_middle: - return result + __reverse_ffz(tmp); + return result; +found: + return result - size + __reverse_ffz(tmp); } void register_inmem_page(struct inode *inode, struct page *page) @@ -233,7 +213,7 @@ int commit_inmem_pages(struct inode *inode, bool abort) * inode becomes free by iget_locked in f2fs_iget. */ if (!abort) { - f2fs_balance_fs(sbi); + f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); } @@ -257,6 +237,7 @@ int commit_inmem_pages(struct inode *inode, bool abort) submit_bio = true; } } else { + ClearPageUptodate(cur->page); trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP); } set_page_private(cur->page, 0); @@ -281,8 +262,10 @@ int commit_inmem_pages(struct inode *inode, bool abort) * This function balances dirty node and dentry pages. * In addition, it controls garbage collection. */ -void f2fs_balance_fs(struct f2fs_sb_info *sbi) +void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) { + if (!need) + return; /* * We should do GC or end up with checkpoint, if there are so many dirty * dir/node pages without enough free segments. @@ -310,8 +293,12 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) if (!available_free_memory(sbi, NAT_ENTRIES) || excess_prefree_segs(sbi) || !available_free_memory(sbi, INO_ENTRIES) || - jiffies > sbi->cp_expires) + (is_idle(sbi) && f2fs_time_over(sbi, CP_TIME))) { + if (test_opt(sbi, DATA_FLUSH)) + sync_dirty_inodes(sbi, FILE_INODE); f2fs_sync_fs(sbi->sb, true); + stat_inc_bg_cp_count(sbi->stat_info); + } } static int issue_flush_thread(void *data) @@ -1134,6 +1121,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) __u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1; unsigned int start_segno, end_segno; struct cp_control cpc; + int err = 0; if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize) return -EINVAL; @@ -1164,12 +1152,12 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) sbi->segs_per_sec) - 1, end_segno); mutex_lock(&sbi->gc_mutex); - write_checkpoint(sbi, &cpc); + err = write_checkpoint(sbi, &cpc); mutex_unlock(&sbi->gc_mutex); } out: range->len = F2FS_BLK_TO_BYTES(cpc.trimmed); - return 0; + return err; } static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type) @@ -1749,13 +1737,13 @@ int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type, if (le32_to_cpu(nid_in_journal(sum, i)) == val) return i; } - if (alloc && nats_in_cursum(sum) < NAT_JOURNAL_ENTRIES) + if (alloc && __has_cursum_space(sum, 1, NAT_JOURNAL)) return update_nats_in_cursum(sum, 1); } else if (type == SIT_JOURNAL) { for (i = 0; i < sits_in_cursum(sum); i++) if (le32_to_cpu(segno_in_journal(sum, i)) == val) return i; - if (alloc && sits_in_cursum(sum) < SIT_JOURNAL_ENTRIES) + if (alloc && __has_cursum_space(sum, 1, SIT_JOURNAL)) return update_sits_in_cursum(sum, 1); } return -1; diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c index da0d8e0b55a5..93606f281bf9 100644 --- a/fs/f2fs/shrinker.c +++ b/fs/f2fs/shrinker.c @@ -32,7 +32,8 @@ static unsigned long __count_free_nids(struct f2fs_sb_info *sbi) static unsigned long __count_extent_cache(struct f2fs_sb_info *sbi) { - return sbi->total_ext_tree + atomic_read(&sbi->total_ext_node); + return atomic_read(&sbi->total_zombie_tree) + + atomic_read(&sbi->total_ext_node); } unsigned long f2fs_shrink_count(struct shrinker *shrink, diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 3a65e0132352..3bf990b80026 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -67,6 +67,7 @@ enum { Opt_extent_cache, Opt_noextent_cache, Opt_noinline_data, + Opt_data_flush, Opt_err, }; @@ -91,6 +92,7 @@ static match_table_t f2fs_tokens = { {Opt_extent_cache, "extent_cache"}, {Opt_noextent_cache, "noextent_cache"}, {Opt_noinline_data, "noinline_data"}, + {Opt_data_flush, "data_flush"}, {Opt_err, NULL}, }; @@ -216,7 +218,8 @@ F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh); F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, cp_interval); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -235,6 +238,7 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(ram_thresh), ATTR_LIST(ra_nid_pages), ATTR_LIST(cp_interval), + ATTR_LIST(idle_interval), NULL, }; @@ -406,6 +410,9 @@ static int parse_options(struct super_block *sb, char *options) case Opt_noinline_data: clear_opt(sbi, INLINE_DATA); break; + case Opt_data_flush: + set_opt(sbi, DATA_FLUSH); + break; default: f2fs_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" or missing value", @@ -432,6 +439,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) fi->i_current_depth = 1; fi->i_advise = 0; init_rwsem(&fi->i_sem); + INIT_LIST_HEAD(&fi->dirty_list); INIT_LIST_HEAD(&fi->inmem_pages); mutex_init(&fi->inmem_lock); @@ -548,7 +556,7 @@ static void f2fs_put_super(struct super_block *sb) * normally superblock is clean, so we need to release this. * In addition, EIO will skip do checkpoint, we need this as well. */ - release_dirty_inode(sbi); + release_ino_entry(sbi); release_discard_addrs(sbi); f2fs_leave_shrinker(sbi); @@ -566,13 +574,14 @@ static void f2fs_put_super(struct super_block *sb) wait_for_completion(&sbi->s_kobj_unregister); sb->s_fs_info = NULL; - brelse(sbi->raw_super_buf); + kfree(sbi->raw_super); kfree(sbi); } int f2fs_sync_fs(struct super_block *sb, int sync) { struct f2fs_sb_info *sbi = F2FS_SB(sb); + int err = 0; trace_f2fs_sync_fs(sb, sync); @@ -582,14 +591,12 @@ int f2fs_sync_fs(struct super_block *sb, int sync) cpc.reason = __get_cp_reason(sbi); mutex_lock(&sbi->gc_mutex); - write_checkpoint(sbi, &cpc); + err = write_checkpoint(sbi, &cpc); mutex_unlock(&sbi->gc_mutex); - } else { - f2fs_balance_fs(sbi); } f2fs_trace_ios(NULL, 1); - return 0; + return err; } static int f2fs_freeze(struct super_block *sb) @@ -686,6 +693,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",extent_cache"); else seq_puts(seq, ",noextent_cache"); + if (test_opt(sbi, DATA_FLUSH)) + seq_puts(seq, ",data_flush"); seq_printf(seq, ",active_logs=%u", sbi->active_logs); return 0; @@ -898,7 +907,7 @@ static const struct export_operations f2fs_export_ops = { .get_parent = f2fs_get_parent, }; -static loff_t max_file_size(unsigned bits) +static loff_t max_file_blocks(void) { loff_t result = (DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS); loff_t leaf_count = ADDRS_PER_BLOCK; @@ -914,10 +923,82 @@ static loff_t max_file_size(unsigned bits) leaf_count *= NIDS_PER_BLOCK; result += leaf_count; - result <<= bits; return result; } +static inline bool sanity_check_area_boundary(struct super_block *sb, + struct f2fs_super_block *raw_super) +{ + u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr); + u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr); + u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr); + u32 nat_blkaddr = le32_to_cpu(raw_super->nat_blkaddr); + u32 ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr); + u32 main_blkaddr = le32_to_cpu(raw_super->main_blkaddr); + u32 segment_count_ckpt = le32_to_cpu(raw_super->segment_count_ckpt); + u32 segment_count_sit = le32_to_cpu(raw_super->segment_count_sit); + u32 segment_count_nat = le32_to_cpu(raw_super->segment_count_nat); + u32 segment_count_ssa = le32_to_cpu(raw_super->segment_count_ssa); + u32 segment_count_main = le32_to_cpu(raw_super->segment_count_main); + u32 segment_count = le32_to_cpu(raw_super->segment_count); + u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg); + + if (segment0_blkaddr != cp_blkaddr) { + f2fs_msg(sb, KERN_INFO, + "Mismatch start address, segment0(%u) cp_blkaddr(%u)", + segment0_blkaddr, cp_blkaddr); + return true; + } + + if (cp_blkaddr + (segment_count_ckpt << log_blocks_per_seg) != + sit_blkaddr) { + f2fs_msg(sb, KERN_INFO, + "Wrong CP boundary, start(%u) end(%u) blocks(%u)", + cp_blkaddr, sit_blkaddr, + segment_count_ckpt << log_blocks_per_seg); + return true; + } + + if (sit_blkaddr + (segment_count_sit << log_blocks_per_seg) != + nat_blkaddr) { + f2fs_msg(sb, KERN_INFO, + "Wrong SIT boundary, start(%u) end(%u) blocks(%u)", + sit_blkaddr, nat_blkaddr, + segment_count_sit << log_blocks_per_seg); + return true; + } + + if (nat_blkaddr + (segment_count_nat << log_blocks_per_seg) != + ssa_blkaddr) { + f2fs_msg(sb, KERN_INFO, + "Wrong NAT boundary, start(%u) end(%u) blocks(%u)", + nat_blkaddr, ssa_blkaddr, + segment_count_nat << log_blocks_per_seg); + return true; + } + + if (ssa_blkaddr + (segment_count_ssa << log_blocks_per_seg) != + main_blkaddr) { + f2fs_msg(sb, KERN_INFO, + "Wrong SSA boundary, start(%u) end(%u) blocks(%u)", + ssa_blkaddr, main_blkaddr, + segment_count_ssa << log_blocks_per_seg); + return true; + } + + if (main_blkaddr + (segment_count_main << log_blocks_per_seg) != + segment0_blkaddr + (segment_count << log_blocks_per_seg)) { + f2fs_msg(sb, KERN_INFO, + "Wrong MAIN_AREA boundary, start(%u) end(%u) blocks(%u)", + main_blkaddr, + segment0_blkaddr + (segment_count << log_blocks_per_seg), + segment_count_main << log_blocks_per_seg); + return true; + } + + return false; +} + static int sanity_check_raw_super(struct super_block *sb, struct f2fs_super_block *raw_super) { @@ -947,6 +1028,14 @@ static int sanity_check_raw_super(struct super_block *sb, return 1; } + /* check log blocks per segment */ + if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) { + f2fs_msg(sb, KERN_INFO, + "Invalid log blocks per segment (%u)\n", + le32_to_cpu(raw_super->log_blocks_per_seg)); + return 1; + } + /* Currently, support 512/1024/2048/4096 bytes sector size */ if (le32_to_cpu(raw_super->log_sectorsize) > F2FS_MAX_LOG_SECTOR_SIZE || @@ -965,6 +1054,23 @@ static int sanity_check_raw_super(struct super_block *sb, le32_to_cpu(raw_super->log_sectorsize)); return 1; } + + /* check reserved ino info */ + if (le32_to_cpu(raw_super->node_ino) != 1 || + le32_to_cpu(raw_super->meta_ino) != 2 || + le32_to_cpu(raw_super->root_ino) != 3) { + f2fs_msg(sb, KERN_INFO, + "Invalid Fs Meta Ino: node(%u) meta(%u) root(%u)", + le32_to_cpu(raw_super->node_ino), + le32_to_cpu(raw_super->meta_ino), + le32_to_cpu(raw_super->root_ino)); + return 1; + } + + /* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */ + if (sanity_check_area_boundary(sb, raw_super)) + return 1; + return 0; } @@ -1018,7 +1124,8 @@ static void init_sb_info(struct f2fs_sb_info *sbi) atomic_set(&sbi->nr_pages[i], 0); sbi->dir_level = DEF_DIR_LEVEL; - sbi->cp_interval = DEF_CP_INTERVAL; + sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL; + sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL; clear_sbi_flag(sbi, SBI_NEED_FSCK); INIT_LIST_HEAD(&sbi->s_list); @@ -1032,111 +1139,114 @@ static void init_sb_info(struct f2fs_sb_info *sbi) */ static int read_raw_super_block(struct super_block *sb, struct f2fs_super_block **raw_super, - struct buffer_head **raw_super_buf, - int *recovery) + int *valid_super_block, int *recovery) { int block = 0; - struct buffer_head *buffer; - struct f2fs_super_block *super; + struct buffer_head *bh; + struct f2fs_super_block *super, *buf; int err = 0; + super = kzalloc(sizeof(struct f2fs_super_block), GFP_KERNEL); + if (!super) + return -ENOMEM; retry: - buffer = sb_bread(sb, block); - if (!buffer) { + bh = sb_bread(sb, block); + if (!bh) { *recovery = 1; f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock", block + 1); - if (block == 0) { - block++; - goto retry; - } else { - err = -EIO; - goto out; - } + err = -EIO; + goto next; } - super = (struct f2fs_super_block *) - ((char *)(buffer)->b_data + F2FS_SUPER_OFFSET); + buf = (struct f2fs_super_block *)(bh->b_data + F2FS_SUPER_OFFSET); /* sanity checking of raw super */ - if (sanity_check_raw_super(sb, super)) { - brelse(buffer); + if (sanity_check_raw_super(sb, buf)) { + brelse(bh); *recovery = 1; f2fs_msg(sb, KERN_ERR, "Can't find valid F2FS filesystem in %dth superblock", block + 1); - if (block == 0) { - block++; - goto retry; - } else { - err = -EINVAL; - goto out; - } + err = -EINVAL; + goto next; } if (!*raw_super) { - *raw_super_buf = buffer; + memcpy(super, buf, sizeof(*super)); + *valid_super_block = block; *raw_super = super; - } else { - /* already have a valid superblock */ - brelse(buffer); } + brelse(bh); +next: /* check the validity of the second superblock */ if (block == 0) { block++; goto retry; } -out: /* No valid superblock */ - if (!*raw_super) + if (!*raw_super) { + kfree(super); return err; + } return 0; } +static int __f2fs_commit_super(struct f2fs_sb_info *sbi, int block) +{ + struct f2fs_super_block *super = F2FS_RAW_SUPER(sbi); + struct buffer_head *bh; + int err; + + bh = sb_getblk(sbi->sb, block); + if (!bh) + return -EIO; + + lock_buffer(bh); + memcpy(bh->b_data + F2FS_SUPER_OFFSET, super, sizeof(*super)); + set_buffer_uptodate(bh); + set_buffer_dirty(bh); + unlock_buffer(bh); + + /* it's rare case, we can do fua all the time */ + err = __sync_dirty_buffer(bh, WRITE_FLUSH_FUA); + brelse(bh); + + return err; +} + int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) { - struct buffer_head *sbh = sbi->raw_super_buf; - sector_t block = sbh->b_blocknr; int err; /* write back-up superblock first */ - sbh->b_blocknr = block ? 0 : 1; - mark_buffer_dirty(sbh); - err = sync_dirty_buffer(sbh); - - sbh->b_blocknr = block; + err = __f2fs_commit_super(sbi, sbi->valid_super_block ? 0 : 1); /* if we are in recovery path, skip writing valid superblock */ if (recover || err) - goto out; + return err; /* write current valid superblock */ - mark_buffer_dirty(sbh); - err = sync_dirty_buffer(sbh); -out: - clear_buffer_write_io_error(sbh); - set_buffer_uptodate(sbh); - return err; + return __f2fs_commit_super(sbi, sbi->valid_super_block); } static int f2fs_fill_super(struct super_block *sb, void *data, int silent) { struct f2fs_sb_info *sbi; struct f2fs_super_block *raw_super; - struct buffer_head *raw_super_buf; struct inode *root; long err; bool retry = true, need_fsck = false; char *options = NULL; - int recovery, i; + int recovery, i, valid_super_block; try_onemore: err = -EINVAL; raw_super = NULL; - raw_super_buf = NULL; + valid_super_block = -1; recovery = 0; /* allocate memory for f2fs-specific super block info */ @@ -1150,7 +1260,8 @@ try_onemore: goto free_sbi; } - err = read_raw_super_block(sb, &raw_super, &raw_super_buf, &recovery); + err = read_raw_super_block(sb, &raw_super, &valid_super_block, + &recovery); if (err) goto free_sbi; @@ -1167,7 +1278,9 @@ try_onemore: if (err) goto free_options; - sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize)); + sbi->max_file_blocks = max_file_blocks(); + sb->s_maxbytes = sbi->max_file_blocks << + le32_to_cpu(raw_super->log_blocksize); sb->s_max_links = F2FS_LINK_MAX; get_random_bytes(&sbi->s_next_generation, sizeof(u32)); @@ -1183,7 +1296,7 @@ try_onemore: /* init f2fs-specific super block info */ sbi->sb = sb; sbi->raw_super = raw_super; - sbi->raw_super_buf = raw_super_buf; + sbi->valid_super_block = valid_super_block; mutex_init(&sbi->gc_mutex); mutex_init(&sbi->writepages); mutex_init(&sbi->cp_mutex); @@ -1236,8 +1349,10 @@ try_onemore: le64_to_cpu(sbi->ckpt->valid_block_count); sbi->last_valid_block_count = sbi->total_valid_block_count; sbi->alloc_valid_block_count = 0; - INIT_LIST_HEAD(&sbi->dir_inode_list); - spin_lock_init(&sbi->dir_inode_lock); + for (i = 0; i < NR_INODE_TYPE; i++) { + INIT_LIST_HEAD(&sbi->inode_list[i]); + spin_lock_init(&sbi->inode_lock[i]); + } init_extent_cache_info(sbi); @@ -1355,12 +1470,14 @@ try_onemore: f2fs_commit_super(sbi, true); } - sbi->cp_expires = round_jiffies_up(jiffies); - + f2fs_update_time(sbi, CP_TIME); + f2fs_update_time(sbi, REQ_TIME); return 0; free_kobj: kobject_del(&sbi->s_kobj); + kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); free_proc: if (sbi->s_proc) { remove_proc_entry("segment_info", sbi->s_proc); @@ -1387,7 +1504,7 @@ free_meta_inode: free_options: kfree(options); free_sb_buf: - brelse(raw_super_buf); + kfree(raw_super); free_sbi: kfree(sbi); @@ -1478,10 +1595,14 @@ static int __init init_f2fs_fs(void) err = register_filesystem(&f2fs_fs_type); if (err) goto free_shrinker; - f2fs_create_root_stats(); + err = f2fs_create_root_stats(); + if (err) + goto free_filesystem; f2fs_proc_root = proc_mkdir("fs/f2fs", NULL); return 0; +free_filesystem: + unregister_filesystem(&f2fs_fs_type); free_shrinker: unregister_shrinker(&f2fs_shrinker_info); free_crypto: diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 4de2286c0e4d..10f1e784fa23 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -25,49 +25,37 @@ #include "f2fs.h" #include "xattr.h" -static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list, - size_t list_size, const char *name, size_t len, int type) +static int f2fs_xattr_generic_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, void *buffer, + size_t size) { struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); - int total_len, prefix_len = 0; - const char *prefix = NULL; - switch (type) { + switch (handler->flags) { case F2FS_XATTR_INDEX_USER: if (!test_opt(sbi, XATTR_USER)) return -EOPNOTSUPP; - prefix = XATTR_USER_PREFIX; - prefix_len = XATTR_USER_PREFIX_LEN; break; case F2FS_XATTR_INDEX_TRUSTED: if (!capable(CAP_SYS_ADMIN)) return -EPERM; - prefix = XATTR_TRUSTED_PREFIX; - prefix_len = XATTR_TRUSTED_PREFIX_LEN; break; case F2FS_XATTR_INDEX_SECURITY: - prefix = XATTR_SECURITY_PREFIX; - prefix_len = XATTR_SECURITY_PREFIX_LEN; break; default: return -EINVAL; } - - total_len = prefix_len + len + 1; - if (list && total_len <= list_size) { - memcpy(list, prefix, prefix_len); - memcpy(list + prefix_len, name, len); - list[prefix_len + len] = '\0'; - } - return total_len; + return f2fs_getxattr(d_inode(dentry), handler->flags, name, + buffer, size, NULL); } -static int f2fs_xattr_generic_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int f2fs_xattr_generic_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, const void *value, + size_t size, int flags) { struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); - switch (type) { + switch (handler->flags) { case F2FS_XATTR_INDEX_USER: if (!test_opt(sbi, XATTR_USER)) return -EOPNOTSUPP; @@ -81,72 +69,39 @@ static int f2fs_xattr_generic_get(struct dentry *dentry, const char *name, default: return -EINVAL; } - if (strcmp(name, "") == 0) - return -EINVAL; - return f2fs_getxattr(d_inode(dentry), type, name, buffer, size, NULL); + return f2fs_setxattr(d_inode(dentry), handler->flags, name, + value, size, NULL, flags); } -static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +static bool f2fs_xattr_user_list(struct dentry *dentry) { struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); - switch (type) { - case F2FS_XATTR_INDEX_USER: - if (!test_opt(sbi, XATTR_USER)) - return -EOPNOTSUPP; - break; - case F2FS_XATTR_INDEX_TRUSTED: - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - break; - case F2FS_XATTR_INDEX_SECURITY: - break; - default: - return -EINVAL; - } - if (strcmp(name, "") == 0) - return -EINVAL; - - return f2fs_setxattr(d_inode(dentry), type, name, - value, size, NULL, flags); + return test_opt(sbi, XATTR_USER); } -static size_t f2fs_xattr_advise_list(struct dentry *dentry, char *list, - size_t list_size, const char *name, size_t len, int type) +static bool f2fs_xattr_trusted_list(struct dentry *dentry) { - const char *xname = F2FS_SYSTEM_ADVISE_PREFIX; - size_t size; - - if (type != F2FS_XATTR_INDEX_ADVISE) - return 0; - - size = strlen(xname) + 1; - if (list && size <= list_size) - memcpy(list, xname, size); - return size; + return capable(CAP_SYS_ADMIN); } -static int f2fs_xattr_advise_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int f2fs_xattr_advise_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, void *buffer, + size_t size) { struct inode *inode = d_inode(dentry); - if (strcmp(name, "") != 0) - return -EINVAL; - if (buffer) *((char *)buffer) = F2FS_I(inode)->i_advise; return sizeof(char); } -static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +static int f2fs_xattr_advise_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, const void *value, + size_t size, int flags) { struct inode *inode = d_inode(dentry); - if (strcmp(name, "") != 0) - return -EINVAL; if (!inode_owner_or_capable(inode)) return -EPERM; if (value == NULL) @@ -185,7 +140,7 @@ int f2fs_init_security(struct inode *inode, struct inode *dir, const struct xattr_handler f2fs_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, .flags = F2FS_XATTR_INDEX_USER, - .list = f2fs_xattr_generic_list, + .list = f2fs_xattr_user_list, .get = f2fs_xattr_generic_get, .set = f2fs_xattr_generic_set, }; @@ -193,15 +148,14 @@ const struct xattr_handler f2fs_xattr_user_handler = { const struct xattr_handler f2fs_xattr_trusted_handler = { .prefix = XATTR_TRUSTED_PREFIX, .flags = F2FS_XATTR_INDEX_TRUSTED, - .list = f2fs_xattr_generic_list, + .list = f2fs_xattr_trusted_list, .get = f2fs_xattr_generic_get, .set = f2fs_xattr_generic_set, }; const struct xattr_handler f2fs_xattr_advise_handler = { - .prefix = F2FS_SYSTEM_ADVISE_PREFIX, + .name = F2FS_SYSTEM_ADVISE_NAME, .flags = F2FS_XATTR_INDEX_ADVISE, - .list = f2fs_xattr_advise_list, .get = f2fs_xattr_advise_get, .set = f2fs_xattr_advise_set, }; @@ -209,7 +163,6 @@ const struct xattr_handler f2fs_xattr_advise_handler = { const struct xattr_handler f2fs_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .flags = F2FS_XATTR_INDEX_SECURITY, - .list = f2fs_xattr_generic_list, .get = f2fs_xattr_generic_get, .set = f2fs_xattr_generic_set, }; @@ -457,20 +410,27 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) list_for_each_xattr(entry, base_addr) { const struct xattr_handler *handler = f2fs_xattr_handler(entry->e_name_index); + const char *prefix; + size_t prefix_len; size_t size; - if (!handler) + if (!handler || (handler->list && !handler->list(dentry))) continue; - size = handler->list(dentry, buffer, rest, entry->e_name, - entry->e_name_len, handler->flags); - if (buffer && size > rest) { - error = -ERANGE; - goto cleanup; + prefix = handler->prefix ?: handler->name; + prefix_len = strlen(prefix); + size = prefix_len + entry->e_name_len + 1; + if (buffer) { + if (size > rest) { + error = -ERANGE; + goto cleanup; + } + memcpy(buffer, prefix, prefix_len); + buffer += prefix_len; + memcpy(buffer, entry->e_name, entry->e_name_len); + buffer += entry->e_name_len; + *buffer++ = 0; } - - if (buffer) - buffer += size; rest -= size; } error = buffer_size - rest; @@ -611,7 +571,7 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, if (ipage) return __f2fs_setxattr(inode, index, name, value, size, ipage, flags); - f2fs_balance_fs(sbi); + f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); /* protect xattr_ver */ @@ -620,5 +580,6 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, up_write(&F2FS_I(inode)->i_sem); f2fs_unlock_op(sbi); + f2fs_update_time(sbi, REQ_TIME); return err; } diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 71a7100d5492..79dccc8252dd 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -27,7 +27,7 @@ #define F2FS_XATTR_REFCOUNT_MAX 1024 /* Name indexes */ -#define F2FS_SYSTEM_ADVISE_PREFIX "system.advise" +#define F2FS_SYSTEM_ADVISE_NAME "system.advise" #define F2FS_XATTR_INDEX_USER 1 #define F2FS_XATTR_INDEX_POSIX_ACL_ACCESS 2 #define F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT 3 diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 4afc4d9d2e41..8b2127ffb226 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -610,9 +610,9 @@ parse_record: int status = fat_parse_long(inode, &cpos, &bh, &de, &unicode, &nr_slots); if (status < 0) { - ctx->pos = cpos; + bh = NULL; ret = status; - goto out; + goto end_of_dir; } else if (status == PARSE_INVALID) goto record_end; else if (status == PARSE_NOT_LONGNAME) @@ -654,8 +654,9 @@ parse_record: fill_len = short_len; start_filldir: - if (!fake_offset) - ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry); + ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry); + if (fake_offset && ctx->pos < 2) + ctx->pos = 2; if (!memcmp(de->name, MSDOS_DOT, MSDOS_NAME)) { if (!dir_emit_dot(file, ctx)) @@ -681,14 +682,19 @@ record_end: fake_offset = 0; ctx->pos = cpos; goto get_new; + end_of_dir: - ctx->pos = cpos; + if (fake_offset && cpos < 2) + ctx->pos = 2; + else + ctx->pos = cpos; fill_failed: brelse(bh); if (unicode) __putname(unicode); out: mutex_unlock(&sbi->s_lock); + return ret; } diff --git a/fs/fcntl.c b/fs/fcntl.c index ee85cd4e136a..350a2c8cfd28 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -51,7 +51,8 @@ static int setfl(int fd, struct file * filp, unsigned long arg) if (arg & O_NDELAY) arg |= O_NONBLOCK; - if (arg & O_DIRECT) { + /* Pipe packetized mode is controlled by O_DIRECT flag */ + if (!S_ISFIFO(filp->f_inode->i_mode) && (arg & O_DIRECT)) { if (!filp->f_mapping || !filp->f_mapping->a_ops || !filp->f_mapping->a_ops->direct_IO) return -EINVAL; diff --git a/fs/file.c b/fs/file.c index 39f8f15921da..1aed0add16a2 100644 --- a/fs/file.c +++ b/fs/file.c @@ -25,9 +25,9 @@ int sysctl_nr_open __read_mostly = 1024*1024; int sysctl_nr_open_min = BITS_PER_LONG; -/* our max() is unusable in constant expressions ;-/ */ -#define __const_max(x, y) ((x) < (y) ? (x) : (y)) -int sysctl_nr_open_max = __const_max(INT_MAX, ~(size_t)0/sizeof(void *)) & +/* our min() is unusable in constant expressions ;-/ */ +#define __const_min(x, y) ((x) < (y) ? (x) : (y)) +int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void *alloc_fdmem(size_t size) diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index ef73ed674a27..3e2ccade61ed 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -326,6 +326,7 @@ vxfs_iget(struct super_block *sbp, ino_t ino) } else if (S_ISLNK(ip->i_mode)) { if (!VXFS_ISIMMED(vip)) { ip->i_op = &page_symlink_inode_operations; + inode_nohighmem(ip); ip->i_mapping->a_ops = &vxfs_aops; } else { ip->i_op = &simple_symlink_inode_operations; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 206a68b1db1a..023f6a1f23cd 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1981,9 +1981,9 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode) * page->mapping->host, so the page-dirtying time is recorded in the internal * blockdev inode. */ -#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) void __mark_inode_dirty(struct inode *inode, int flags) { +#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) struct super_block *sb = inode->i_sb; int dirtytime; @@ -2093,6 +2093,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) out_unlock_inode: spin_unlock(&inode->i_lock); +#undef I_DIRTY_INODE } EXPORT_SYMBOL(__mark_inode_dirty); diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index d403c69bee08..4304072161aa 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -111,7 +111,7 @@ struct fscache_cookie *__fscache_acquire_cookie( /* radix tree insertion won't use the preallocation pool unless it's * told it may not wait */ - INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); switch (cookie->def->type) { case FSCACHE_COOKIE_TYPE_INDEX: diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c index 6d941f56faf4..9b28649df3a1 100644 --- a/fs/fscache/netfs.c +++ b/fs/fscache/netfs.c @@ -22,6 +22,7 @@ static LIST_HEAD(fscache_netfs_list); int __fscache_register_netfs(struct fscache_netfs *netfs) { struct fscache_netfs *ptr; + struct fscache_cookie *cookie; int ret; _enter("{%s}", netfs->name); @@ -29,29 +30,25 @@ int __fscache_register_netfs(struct fscache_netfs *netfs) INIT_LIST_HEAD(&netfs->link); /* allocate a cookie for the primary index */ - netfs->primary_index = - kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL); + cookie = kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL); - if (!netfs->primary_index) { + if (!cookie) { _leave(" = -ENOMEM"); return -ENOMEM; } /* initialise the primary index cookie */ - atomic_set(&netfs->primary_index->usage, 1); - atomic_set(&netfs->primary_index->n_children, 0); - atomic_set(&netfs->primary_index->n_active, 1); + atomic_set(&cookie->usage, 1); + atomic_set(&cookie->n_children, 0); + atomic_set(&cookie->n_active, 1); - netfs->primary_index->def = &fscache_fsdef_netfs_def; - netfs->primary_index->parent = &fscache_fsdef_index; - netfs->primary_index->netfs_data = netfs; - netfs->primary_index->flags = 1 << FSCACHE_COOKIE_ENABLED; + cookie->def = &fscache_fsdef_netfs_def; + cookie->parent = &fscache_fsdef_index; + cookie->netfs_data = netfs; + cookie->flags = 1 << FSCACHE_COOKIE_ENABLED; - atomic_inc(&netfs->primary_index->parent->usage); - atomic_inc(&netfs->primary_index->parent->n_children); - - spin_lock_init(&netfs->primary_index->lock); - INIT_HLIST_HEAD(&netfs->primary_index->backing_objects); + spin_lock_init(&cookie->lock); + INIT_HLIST_HEAD(&cookie->backing_objects); /* check the netfs type is not already present */ down_write(&fscache_addremove_sem); @@ -62,6 +59,10 @@ int __fscache_register_netfs(struct fscache_netfs *netfs) goto already_registered; } + atomic_inc(&cookie->parent->usage); + atomic_inc(&cookie->parent->n_children); + + netfs->primary_index = cookie; list_add(&netfs->link, &fscache_netfs_list); ret = 0; @@ -70,11 +71,8 @@ int __fscache_register_netfs(struct fscache_netfs *netfs) already_registered: up_write(&fscache_addremove_sem); - if (ret < 0) { - netfs->primary_index->parent = NULL; - __fscache_cookie_put(netfs->primary_index); - netfs->primary_index = NULL; - } + if (ret < 0) + kmem_cache_free(fscache_cookie_jar, cookie); _leave(" = %d", ret); return ret; diff --git a/fs/fscache/page.c b/fs/fscache/page.c index 483bbc613bf0..6b35fc4860a0 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -58,7 +58,7 @@ bool release_page_wait_timeout(struct fscache_cookie *cookie, struct page *page) /* * decide whether a page can be released, possibly by cancelling a store to it - * - we're allowed to sleep if __GFP_WAIT is flagged + * - we're allowed to sleep if __GFP_DIRECT_RECLAIM is flagged */ bool __fscache_maybe_release_page(struct fscache_cookie *cookie, struct page *page, @@ -122,7 +122,7 @@ page_busy: * allocator as the work threads writing to the cache may all end up * sleeping on memory allocation, so we may need to impose a timeout * too. */ - if (!(gfp & __GFP_WAIT) || !(gfp & __GFP_FS)) { + if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) { fscache_stat(&fscache_n_store_vmscan_busy); return false; } @@ -132,7 +132,7 @@ page_busy: _debug("fscache writeout timeout page: %p{%lx}", page, page->index); - gfp &= ~__GFP_WAIT; + gfp &= ~__GFP_DIRECT_RECLAIM; goto try_again; } EXPORT_SYMBOL(__fscache_maybe_release_page); @@ -816,7 +816,7 @@ static void fscache_write_op(struct fscache_operation *_op) goto superseded; page = results[0]; _debug("gang %d [%lx]", n, page->index); - if (page->index > op->store_limit) { + if (page->index >= op->store_limit) { fscache_stat(&fscache_n_store_pages_over_limit); goto superseded; } diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index eae2c11268bc..8e3ee1936c7e 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -549,6 +549,8 @@ static int cuse_channel_release(struct inode *inode, struct file *file) unregister_chrdev_region(cc->cdev->dev, 1); cdev_del(cc->cdev); } + /* Base reference is now owned by "fud" */ + fuse_conn_put(&cc->fc); rc = fuse_dev_release(inode, file); /* puts the base reference */ diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 5e2e08712d3b..712601f299b8 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1365,15 +1365,19 @@ static int fuse_readdir(struct file *file, struct dir_context *ctx) return err; } -static const char *fuse_follow_link(struct dentry *dentry, void **cookie) +static const char *fuse_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(dentry); struct fuse_conn *fc = get_fuse_conn(inode); FUSE_ARGS(args); char *link; ssize_t ret; - link = (char *) __get_free_page(GFP_KERNEL); + if (!dentry) + return ERR_PTR(-ECHILD); + + link = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!link) return ERR_PTR(-ENOMEM); @@ -1385,11 +1389,11 @@ static const char *fuse_follow_link(struct dentry *dentry, void **cookie) args.out.args[0].value = link; ret = fuse_simple_request(fc, &args); if (ret < 0) { - free_page((unsigned long) link); + kfree(link); link = ERR_PTR(ret); } else { link[ret] = '\0'; - *cookie = link; + set_delayed_call(done, kfree_link, link); } fuse_invalidate_atime(inode); return link; @@ -1909,8 +1913,7 @@ static const struct inode_operations fuse_common_inode_operations = { static const struct inode_operations fuse_symlink_inode_operations = { .setattr = fuse_setattr, - .follow_link = fuse_follow_link, - .put_link = free_page_put_link, + .get_link = fuse_get_link, .readlink = generic_readlink, .getattr = fuse_getattr, .setxattr = fuse_setxattr, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index e0faf8f2c868..570ca4053c80 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1049,6 +1049,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes); flush_dcache_page(page); + iov_iter_advance(ii, tmp); if (!tmp) { unlock_page(page); page_cache_release(page); @@ -1061,7 +1062,6 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, req->page_descs[req->num_pages].length = tmp; req->num_pages++; - iov_iter_advance(ii, tmp); count += tmp; pos += tmp; offset += tmp; diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 1be3b061c05c..791932617d1a 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -31,9 +31,9 @@ static const char *gfs2_acl_name(int type) { switch (type) { case ACL_TYPE_ACCESS: - return GFS2_POSIX_ACL_ACCESS; + return XATTR_POSIX_ACL_ACCESS; case ACL_TYPE_DEFAULT: - return GFS2_POSIX_ACL_DEFAULT; + return XATTR_POSIX_ACL_DEFAULT; } return NULL; } diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h index 2d65ec4cd4be..3af4f407a483 100644 --- a/fs/gfs2/acl.h +++ b/fs/gfs2/acl.h @@ -12,8 +12,6 @@ #include "incore.h" -#define GFS2_POSIX_ACL_ACCESS "posix_acl_access" -#define GFS2_POSIX_ACL_DEFAULT "posix_acl_default" #define GFS2_ACL_MAX_ENTRIES(sdp) ((300 << (sdp)->sd_sb.sb_bsize_shift) >> 12) extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 1caee0534587..93f07465e5a6 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -914,7 +914,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, failed: gfs2_trans_end(sdp); gfs2_inplace_release(ip); - if (ip->i_res->rs_qa_qd_num) + if (ip->i_qadata && ip->i_qadata->qa_qd_num) gfs2_quota_unlock(ip); if (inode == sdp->sd_rindex) { gfs2_glock_dq(&m_ip->i_gh); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 61296ecbd0e2..0860f0b5b3f1 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -787,8 +787,8 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, if (error) goto out_rlist; - if (gfs2_rs_active(ip->i_res)) /* needs to be done with the rgrp glock held */ - gfs2_rs_deltree(ip->i_res); + if (gfs2_rs_active(&ip->i_res)) /* needs to be done with the rgrp glock held */ + gfs2_rs_deltree(&ip->i_res); error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE + RES_INDIRECT + RES_STATFS + RES_QUOTA, @@ -1291,13 +1291,9 @@ int gfs2_setattr_size(struct inode *inode, u64 newsize) if (ret) return ret; - ret = get_write_access(inode); - if (ret) - return ret; - inode_dio_wait(inode); - ret = gfs2_rs_alloc(ip); + ret = gfs2_rsqa_alloc(ip); if (ret) goto out; @@ -1307,10 +1303,9 @@ int gfs2_setattr_size(struct inode *inode, u64 newsize) goto out; } - gfs2_rs_deltree(ip->i_res); ret = do_shrink(inode, oldsize, newsize); out: - put_write_access(inode); + gfs2_rsqa_delete(ip, NULL); return ret; } diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 487527b42d94..6a92592304fb 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -82,6 +82,8 @@ #define gfs2_disk_hash2offset(h) (((u64)(h)) >> 1) #define gfs2_dir_offset2hash(p) ((u32)(((u64)(p)) << 1)) +#define GFS2_HASH_INDEX_MASK 0xffffc000 +#define GFS2_USE_HASH_FLAG 0x2000 struct qstr gfs2_qdot __read_mostly; struct qstr gfs2_qdotdot __read_mostly; @@ -108,7 +110,7 @@ static int gfs2_dir_get_existing_buffer(struct gfs2_inode *ip, u64 block, struct buffer_head *bh; int error; - error = gfs2_meta_read(ip->i_gl, block, DIO_WAIT, &bh); + error = gfs2_meta_read(ip->i_gl, block, DIO_WAIT, 0, &bh); if (error) return error; if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), bh, GFS2_METATYPE_JD)) { @@ -305,7 +307,7 @@ static int gfs2_dir_read_data(struct gfs2_inode *ip, __be64 *buf, BUG_ON(extlen < 1); bh = gfs2_meta_ra(ip->i_gl, dblock, extlen); } else { - error = gfs2_meta_read(ip->i_gl, dblock, DIO_WAIT, &bh); + error = gfs2_meta_read(ip->i_gl, dblock, DIO_WAIT, 0, &bh); if (error) goto fail; } @@ -388,8 +390,13 @@ static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip) */ void gfs2_dir_hash_inval(struct gfs2_inode *ip) { - __be64 *hc = ip->i_hash_cache; + __be64 *hc; + + spin_lock(&ip->i_inode.i_lock); + hc = ip->i_hash_cache; ip->i_hash_cache = NULL; + spin_unlock(&ip->i_inode.i_lock); + kvfree(hc); } @@ -438,6 +445,27 @@ static int gfs2_dirent_last(const struct gfs2_dirent *dent, return 0; } +/* Look for the dirent that contains the offset specified in data. Once we + * find that dirent, there must be space available there for the new dirent */ +static int gfs2_dirent_find_offset(const struct gfs2_dirent *dent, + const struct qstr *name, + void *ptr) +{ + unsigned required = GFS2_DIRENT_SIZE(name->len); + unsigned actual = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len)); + unsigned totlen = be16_to_cpu(dent->de_rec_len); + + if (ptr < (void *)dent || ptr >= (void *)dent + totlen) + return 0; + if (gfs2_dirent_sentinel(dent)) + actual = 0; + if (ptr < (void *)dent + actual) + return -1; + if ((void *)dent + totlen >= ptr + required) + return 1; + return -1; +} + static int gfs2_dirent_find_space(const struct gfs2_dirent *dent, const struct qstr *name, void *opaque) @@ -677,6 +705,27 @@ static void dirent_del(struct gfs2_inode *dip, struct buffer_head *bh, prev->de_rec_len = cpu_to_be16(prev_rec_len); } + +static struct gfs2_dirent *do_init_dirent(struct inode *inode, + struct gfs2_dirent *dent, + const struct qstr *name, + struct buffer_head *bh, + unsigned offset) +{ + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_dirent *ndent; + unsigned totlen; + + totlen = be16_to_cpu(dent->de_rec_len); + BUG_ON(offset + name->len > totlen); + gfs2_trans_add_meta(ip->i_gl, bh); + ndent = (struct gfs2_dirent *)((char *)dent + offset); + dent->de_rec_len = cpu_to_be16(offset); + gfs2_qstr2dirent(name, totlen - offset, ndent); + return ndent; +} + + /* * Takes a dent from which to grab space as an argument. Returns the * newly created dent. @@ -686,31 +735,25 @@ static struct gfs2_dirent *gfs2_init_dirent(struct inode *inode, const struct qstr *name, struct buffer_head *bh) { - struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_dirent *ndent; - unsigned offset = 0, totlen; + unsigned offset = 0; if (!gfs2_dirent_sentinel(dent)) offset = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len)); - totlen = be16_to_cpu(dent->de_rec_len); - BUG_ON(offset + name->len > totlen); - gfs2_trans_add_meta(ip->i_gl, bh); - ndent = (struct gfs2_dirent *)((char *)dent + offset); - dent->de_rec_len = cpu_to_be16(offset); - gfs2_qstr2dirent(name, totlen - offset, ndent); - return ndent; + return do_init_dirent(inode, dent, name, bh, offset); } -static struct gfs2_dirent *gfs2_dirent_alloc(struct inode *inode, - struct buffer_head *bh, - const struct qstr *name) +static struct gfs2_dirent *gfs2_dirent_split_alloc(struct inode *inode, + struct buffer_head *bh, + const struct qstr *name, + void *ptr) { struct gfs2_dirent *dent; dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size, - gfs2_dirent_find_space, name, NULL); + gfs2_dirent_find_offset, name, ptr); if (!dent || IS_ERR(dent)) return dent; - return gfs2_init_dirent(inode, dent, name, bh); + return do_init_dirent(inode, dent, name, bh, + (unsigned)(ptr - (void *)dent)); } static int get_leaf(struct gfs2_inode *dip, u64 leaf_no, @@ -718,7 +761,7 @@ static int get_leaf(struct gfs2_inode *dip, u64 leaf_no, { int error; - error = gfs2_meta_read(dip->i_gl, leaf_no, DIO_WAIT, bhp); + error = gfs2_meta_read(dip->i_gl, leaf_no, DIO_WAIT, 0, bhp); if (!error && gfs2_metatype_check(GFS2_SB(&dip->i_inode), *bhp, GFS2_METATYPE_LF)) { /* pr_info("block num=%llu\n", leaf_no); */ error = -EIO; @@ -1046,10 +1089,11 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name) if (!gfs2_dirent_sentinel(dent) && be32_to_cpu(dent->de_hash) < divider) { struct qstr str; + void *ptr = ((char *)dent - obh->b_data) + nbh->b_data; str.name = (char*)(dent+1); str.len = be16_to_cpu(dent->de_name_len); str.hash = be32_to_cpu(dent->de_hash); - new = gfs2_dirent_alloc(inode, nbh, &str); + new = gfs2_dirent_split_alloc(inode, nbh, &str, ptr); if (IS_ERR(new)) { error = PTR_ERR(new); break; @@ -1181,10 +1225,10 @@ static int compare_dents(const void *a, const void *b) int ret = 0; dent_a = *(const struct gfs2_dirent **)a; - hash_a = be32_to_cpu(dent_a->de_hash); + hash_a = dent_a->de_cookie; dent_b = *(const struct gfs2_dirent **)b; - hash_b = be32_to_cpu(dent_b->de_hash); + hash_b = dent_b->de_cookie; if (hash_a > hash_b) ret = 1; @@ -1222,19 +1266,20 @@ static int compare_dents(const void *a, const void *b) */ static int do_filldir_main(struct gfs2_inode *dip, struct dir_context *ctx, - const struct gfs2_dirent **darr, u32 entries, - int *copied) + struct gfs2_dirent **darr, u32 entries, + u32 sort_start, int *copied) { const struct gfs2_dirent *dent, *dent_next; u64 off, off_next; unsigned int x, y; int run = 0; - sort(darr, entries, sizeof(struct gfs2_dirent *), compare_dents, NULL); + if (sort_start < entries) + sort(&darr[sort_start], entries - sort_start, + sizeof(struct gfs2_dirent *), compare_dents, NULL); dent_next = darr[0]; - off_next = be32_to_cpu(dent_next->de_hash); - off_next = gfs2_disk_hash2offset(off_next); + off_next = dent_next->de_cookie; for (x = 0, y = 1; x < entries; x++, y++) { dent = dent_next; @@ -1242,8 +1287,7 @@ static int do_filldir_main(struct gfs2_inode *dip, struct dir_context *ctx, if (y < entries) { dent_next = darr[y]; - off_next = be32_to_cpu(dent_next->de_hash); - off_next = gfs2_disk_hash2offset(off_next); + off_next = dent_next->de_cookie; if (off < ctx->pos) continue; @@ -1290,6 +1334,40 @@ static void *gfs2_alloc_sort_buffer(unsigned size) return ptr; } + +static int gfs2_set_cookies(struct gfs2_sbd *sdp, struct buffer_head *bh, + unsigned leaf_nr, struct gfs2_dirent **darr, + unsigned entries) +{ + int sort_id = -1; + int i; + + for (i = 0; i < entries; i++) { + unsigned offset; + + darr[i]->de_cookie = be32_to_cpu(darr[i]->de_hash); + darr[i]->de_cookie = gfs2_disk_hash2offset(darr[i]->de_cookie); + + if (!sdp->sd_args.ar_loccookie) + continue; + offset = (char *)(darr[i]) - + (bh->b_data + gfs2_dirent_offset(bh->b_data)); + offset /= GFS2_MIN_DIRENT_SIZE; + offset += leaf_nr * sdp->sd_max_dents_per_leaf; + if (offset >= GFS2_USE_HASH_FLAG || + leaf_nr >= GFS2_USE_HASH_FLAG) { + darr[i]->de_cookie |= GFS2_USE_HASH_FLAG; + if (sort_id < 0) + sort_id = i; + continue; + } + darr[i]->de_cookie &= GFS2_HASH_INDEX_MASK; + darr[i]->de_cookie |= offset; + } + return sort_id; +} + + static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, int *copied, unsigned *depth, u64 leaf_no) @@ -1299,12 +1377,11 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, struct buffer_head *bh; struct gfs2_leaf *lf; unsigned entries = 0, entries2 = 0; - unsigned leaves = 0; - const struct gfs2_dirent **darr, *dent; + unsigned leaves = 0, leaf = 0, offset, sort_offset; + struct gfs2_dirent **darr, *dent; struct dirent_gather g; struct buffer_head **larr; - int leaf = 0; - int error, i; + int error, i, need_sort = 0, sort_id; u64 lfn = leaf_no; do { @@ -1320,6 +1397,11 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, brelse(bh); } while(lfn); + if (*depth < GFS2_DIR_MAX_DEPTH || !sdp->sd_args.ar_loccookie) { + need_sort = 1; + sort_offset = 0; + } + if (!entries) return 0; @@ -1333,8 +1415,8 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, larr = gfs2_alloc_sort_buffer((leaves + entries + 99) * sizeof(void *)); if (!larr) goto out; - darr = (const struct gfs2_dirent **)(larr + leaves); - g.pdent = darr; + darr = (struct gfs2_dirent **)(larr + leaves); + g.pdent = (const struct gfs2_dirent **)darr; g.offset = 0; lfn = leaf_no; @@ -1345,6 +1427,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, lf = (struct gfs2_leaf *)bh->b_data; lfn = be64_to_cpu(lf->lf_next); if (lf->lf_entries) { + offset = g.offset; entries2 += be16_to_cpu(lf->lf_entries); dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size, gfs2_dirent_gather, NULL, &g); @@ -1362,17 +1445,26 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, goto out_free; } error = 0; + sort_id = gfs2_set_cookies(sdp, bh, leaf, &darr[offset], + be16_to_cpu(lf->lf_entries)); + if (!need_sort && sort_id >= 0) { + need_sort = 1; + sort_offset = offset + sort_id; + } larr[leaf++] = bh; } else { + larr[leaf++] = NULL; brelse(bh); } } while(lfn); BUG_ON(entries2 != entries); - error = do_filldir_main(ip, ctx, darr, entries, copied); + error = do_filldir_main(ip, ctx, darr, entries, need_sort ? + sort_offset : entries, copied); out_free: for(i = 0; i < leaf; i++) - brelse(larr[i]); + if (larr[i]) + brelse(larr[i]); kvfree(larr); out: return error; @@ -1478,7 +1570,7 @@ int gfs2_dir_read(struct inode *inode, struct dir_context *ctx, struct gfs2_inode *dip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct dirent_gather g; - const struct gfs2_dirent **darr, *dent; + struct gfs2_dirent **darr, *dent; struct buffer_head *dibh; int copied = 0; int error; @@ -1502,7 +1594,7 @@ int gfs2_dir_read(struct inode *inode, struct dir_context *ctx, /* 96 is max number of dirents which can be stuffed into an inode */ darr = kmalloc(96 * sizeof(struct gfs2_dirent *), GFP_NOFS); if (darr) { - g.pdent = darr; + g.pdent = (const struct gfs2_dirent **)darr; g.offset = 0; dent = gfs2_dirent_scan(inode, dibh->b_data, dibh->b_size, gfs2_dirent_gather, NULL, &g); @@ -1519,8 +1611,9 @@ int gfs2_dir_read(struct inode *inode, struct dir_context *ctx, error = -EIO; goto out; } + gfs2_set_cookies(sdp, dibh, 0, darr, dip->i_entries); error = do_filldir_main(dip, ctx, darr, - dip->i_entries, &copied); + dip->i_entries, 0, &copied); out: kfree(darr); } @@ -1555,15 +1648,22 @@ struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *name, dent = gfs2_dirent_search(dir, name, gfs2_dirent_find, &bh); if (dent) { + struct inode *inode; + u16 rahead; + if (IS_ERR(dent)) return ERR_CAST(dent); dtype = be16_to_cpu(dent->de_type); + rahead = be16_to_cpu(dent->de_rahead); addr = be64_to_cpu(dent->de_inum.no_addr); formal_ino = be64_to_cpu(dent->de_inum.no_formal_ino); brelse(bh); if (fail_on_exist) return ERR_PTR(-EEXIST); - return gfs2_inode_lookup(dir->i_sb, dtype, addr, formal_ino, 0); + inode = gfs2_inode_lookup(dir->i_sb, dtype, addr, formal_ino, 0); + if (!IS_ERR(inode)) + GFS2_I(inode)->i_rahead = rahead; + return inode; } return ERR_PTR(-ENOENT); } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 9287a2d17b8c..7412863cda1e 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -298,9 +298,9 @@ static int gfs2_set_flags(struct file *filp, u32 __user *ptr) gfsflags &= ~GFS2_DIF_TOPDIR; if (gfsflags & GFS2_DIF_INHERIT_JDATA) gfsflags ^= (GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA); - return do_gfs2_set_flags(filp, gfsflags, ~0); + return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_SYSTEM); } - return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_JDATA); + return do_gfs2_set_flags(filp, gfsflags, ~(GFS2_DIF_SYSTEM | GFS2_DIF_JDATA)); } static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) @@ -336,8 +336,8 @@ static void gfs2_size_hint(struct file *filep, loff_t offset, size_t size) size_t blks = (size + sdp->sd_sb.sb_bsize - 1) >> sdp->sd_sb.sb_bsize_shift; int hint = min_t(size_t, INT_MAX, blks); - if (hint > atomic_read(&ip->i_res->rs_sizehint)) - atomic_set(&ip->i_res->rs_sizehint, hint); + if (hint > atomic_read(&ip->i_res.rs_sizehint)) + atomic_set(&ip->i_res.rs_sizehint, hint); } /** @@ -397,14 +397,10 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) /* Update file times before taking page lock */ file_update_time(vma->vm_file); - ret = get_write_access(inode); + ret = gfs2_rsqa_alloc(ip); if (ret) goto out; - ret = gfs2_rs_alloc(ip); - if (ret) - goto out_write_access; - gfs2_size_hint(vma->vm_file, pos, PAGE_CACHE_SIZE); gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); @@ -486,8 +482,6 @@ out_uninit: set_page_dirty(page); wait_for_stable_page(page); } -out_write_access: - put_write_access(inode); out: sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(ret); @@ -623,7 +617,7 @@ static int gfs2_release(struct inode *inode, struct file *file) if (!(file->f_mode & FMODE_WRITE)) return 0; - gfs2_rs_delete(ip, &inode->i_writecount); + gfs2_rsqa_delete(ip, &inode->i_writecount); return 0; } @@ -703,7 +697,7 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct gfs2_inode *ip = GFS2_I(file_inode(file)); int ret; - ret = gfs2_rs_alloc(ip); + ret = gfs2_rsqa_alloc(ip); if (ret) return ret; @@ -897,8 +891,8 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t if (!(mode & FALLOC_FL_KEEP_SIZE) && (pos + count) > inode->i_size) { i_size_write(inode, pos + count); - /* Marks the inode as dirty */ file_update_time(file); + mark_inode_dirty(inode); } return generic_write_sync(file, pos, count); @@ -938,13 +932,14 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t le if (ret) goto out_unlock; - ret = gfs2_rs_alloc(ip); + ret = gfs2_rsqa_alloc(ip); if (ret) goto out_putw; ret = __gfs2_fallocate(file, mode, offset, len); if (ret) - gfs2_rs_deltree(ip->i_res); + gfs2_rs_deltree(&ip->i_res); + out_putw: put_write_access(inode); out_unlock: @@ -962,7 +957,7 @@ static ssize_t gfs2_file_splice_write(struct pipe_inode_info *pipe, int error; struct gfs2_inode *ip = GFS2_I(out->f_mapping->host); - error = gfs2_rs_alloc(ip); + error = gfs2_rsqa_alloc(ip); if (error) return (ssize_t)error; @@ -1018,7 +1013,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) struct gfs2_inode *ip = GFS2_I(file_inode(file)); struct gfs2_glock *gl; unsigned int state; - int flags; + u16 flags; int error = 0; int sleeptime; @@ -1032,7 +1027,10 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) if (fl_gh->gh_state == state) goto out; locks_lock_file_wait(file, - &(struct file_lock){.fl_type = F_UNLCK}); + &(struct file_lock) { + .fl_type = F_UNLCK, + .fl_flags = FL_FLOCK + }); gfs2_glock_dq(fl_gh); gfs2_holder_reinit(state, flags, fl_gh); } else { diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 9bd1244caf38..a4ff7b56f5cd 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -246,8 +246,8 @@ static inline void do_error(struct gfs2_glock *gl, const int ret) */ static int do_promote(struct gfs2_glock *gl) -__releases(&gl->gl_spin) -__acquires(&gl->gl_spin) +__releases(&gl->gl_lockref.lock) +__acquires(&gl->gl_lockref.lock) { const struct gfs2_glock_operations *glops = gl->gl_ops; struct gfs2_holder *gh, *tmp; @@ -260,10 +260,10 @@ restart: if (may_grant(gl, gh)) { if (gh->gh_list.prev == &gl->gl_holders && glops->go_lock) { - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); /* FIXME: eliminate this eventually */ ret = glops->go_lock(gh); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); if (ret) { if (ret == 1) return 2; @@ -361,7 +361,7 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret) unsigned state = ret & LM_OUT_ST_MASK; int rv; - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); trace_gfs2_glock_state_change(gl, state); state_change(gl, state); gh = find_first_waiter(gl); @@ -405,7 +405,7 @@ retry: pr_err("wanted %u got %u\n", gl->gl_target, state); GLOCK_BUG_ON(gl, 1); } - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); return; } @@ -414,9 +414,9 @@ retry: gfs2_demote_wake(gl); if (state != LM_ST_UNLOCKED) { if (glops->go_xmote_bh) { - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); rv = glops->go_xmote_bh(gl, gh); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); if (rv) { do_error(gl, rv); goto out; @@ -429,7 +429,7 @@ retry: out: clear_bit(GLF_LOCK, &gl->gl_flags); out_locked: - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); } /** @@ -441,12 +441,12 @@ out_locked: */ static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target) -__releases(&gl->gl_spin) -__acquires(&gl->gl_spin) +__releases(&gl->gl_lockref.lock) +__acquires(&gl->gl_lockref.lock) { const struct gfs2_glock_operations *glops = gl->gl_ops; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - unsigned int lck_flags = gh ? gh->gh_flags : 0; + unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0); int ret; lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP | @@ -464,7 +464,7 @@ __acquires(&gl->gl_spin) (gl->gl_state == LM_ST_EXCLUSIVE) || (lck_flags & (LM_FLAG_TRY|LM_FLAG_TRY_1CB))) clear_bit(GLF_BLOCKING, &gl->gl_flags); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (glops->go_sync) glops->go_sync(gl); if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags)) @@ -485,7 +485,7 @@ __acquires(&gl->gl_spin) gfs2_glock_put(gl); } - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); } /** @@ -513,8 +513,8 @@ static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl) */ static void run_queue(struct gfs2_glock *gl, const int nonblock) -__releases(&gl->gl_spin) -__acquires(&gl->gl_spin) +__releases(&gl->gl_lockref.lock) +__acquires(&gl->gl_lockref.lock) { struct gfs2_holder *gh = NULL; int ret; @@ -596,7 +596,7 @@ static void glock_work_func(struct work_struct *work) finish_xmote(gl, gl->gl_reply); drop_ref = 1; } - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && gl->gl_state != LM_ST_UNLOCKED && gl->gl_demote_state != LM_ST_EXCLUSIVE) { @@ -612,7 +612,7 @@ static void glock_work_func(struct work_struct *work) } } run_queue(gl, 0); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (!delay) gfs2_glock_put(gl); else { @@ -750,7 +750,7 @@ again: * */ -void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags, +void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, u16 flags, struct gfs2_holder *gh) { INIT_LIST_HEAD(&gh->gh_list); @@ -774,7 +774,7 @@ void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags, * */ -void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder *gh) +void gfs2_holder_reinit(unsigned int state, u16 flags, struct gfs2_holder *gh) { gh->gh_state = state; gh->gh_flags = flags; @@ -876,8 +876,8 @@ void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...) */ static inline void add_to_queue(struct gfs2_holder *gh) -__releases(&gl->gl_spin) -__acquires(&gl->gl_spin) +__releases(&gl->gl_lockref.lock) +__acquires(&gl->gl_lockref.lock) { struct gfs2_glock *gl = gh->gh_gl; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; @@ -926,10 +926,10 @@ fail: do_cancel: gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list); if (!(gh->gh_flags & LM_FLAG_PRIORITY)) { - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (sdp->sd_lockstruct.ls_ops->lm_cancel) sdp->sd_lockstruct.ls_ops->lm_cancel(gl); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); } return; @@ -967,7 +967,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh) if (test_bit(GLF_LRU, &gl->gl_flags)) gfs2_glock_remove_from_lru(gl); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); add_to_queue(gh); if (unlikely((LM_FLAG_NOEXP & gh->gh_flags) && test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))) { @@ -977,7 +977,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh) gl->gl_lockref.count--; } run_queue(gl, 1); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (!(gh->gh_flags & GL_ASYNC)) error = gfs2_glock_wait(gh); @@ -1010,7 +1010,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh) unsigned delay = 0; int fast_path = 0; - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); if (gh->gh_flags & GL_NOCACHE) handle_callback(gl, LM_ST_UNLOCKED, 0, false); @@ -1018,9 +1018,9 @@ void gfs2_glock_dq(struct gfs2_holder *gh) if (find_first_holder(gl) == NULL) { if (glops->go_unlock) { GLOCK_BUG_ON(gl, test_and_set_bit(GLF_LOCK, &gl->gl_flags)); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); glops->go_unlock(gh); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); clear_bit(GLF_LOCK, &gl->gl_flags); } if (list_empty(&gl->gl_holders) && @@ -1033,7 +1033,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh) gfs2_glock_add_to_lru(gl); trace_gfs2_glock_queue(gh, 0); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (likely(fast_path)) return; @@ -1080,7 +1080,7 @@ void gfs2_glock_dq_uninit(struct gfs2_holder *gh) int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number, const struct gfs2_glock_operations *glops, - unsigned int state, int flags, struct gfs2_holder *gh) + unsigned int state, u16 flags, struct gfs2_holder *gh) { struct gfs2_glock *gl; int error; @@ -1217,9 +1217,9 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) delay = gl->gl_hold_time; } - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); handle_callback(gl, state, delay, true); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) gfs2_glock_put(gl); } @@ -1259,7 +1259,7 @@ static int gfs2_should_freeze(const struct gfs2_glock *gl) * @gl: Pointer to the glock * @ret: The return value from the dlm * - * The gl_reply field is under the gl_spin lock so that it is ok + * The gl_reply field is under the gl_lockref.lock lock so that it is ok * to use a bitfield shared with other glock state fields. */ @@ -1267,20 +1267,20 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret) { struct lm_lockstruct *ls = &gl->gl_name.ln_sbd->sd_lockstruct; - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); gl->gl_reply = ret; if (unlikely(test_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags))) { if (gfs2_should_freeze(gl)) { set_bit(GLF_FROZEN, &gl->gl_flags); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); return; } } gl->gl_lockref.count++; set_bit(GLF_REPLY_PENDING, &gl->gl_flags); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gfs2_glock_put(gl); @@ -1326,14 +1326,14 @@ __acquires(&lru_lock) while(!list_empty(list)) { gl = list_entry(list->next, struct gfs2_glock, gl_lru); list_del_init(&gl->gl_lru); - if (!spin_trylock(&gl->gl_spin)) { + if (!spin_trylock(&gl->gl_lockref.lock)) { add_back_to_lru: list_add(&gl->gl_lru, &lru_list); atomic_inc(&lru_count); continue; } if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) { - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); goto add_back_to_lru; } clear_bit(GLF_LRU, &gl->gl_flags); @@ -1343,7 +1343,7 @@ add_back_to_lru: WARN_ON(!test_and_clear_bit(GLF_LOCK, &gl->gl_flags)); if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gl->gl_lockref.count--; - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); cond_resched_lock(&lru_lock); } } @@ -1417,14 +1417,14 @@ static struct shrinker glock_shrinker = { static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp) { struct gfs2_glock *gl; - struct rhash_head *pos, *next; + struct rhash_head *pos; const struct bucket_table *tbl; int i; rcu_read_lock(); tbl = rht_dereference_rcu(gl_hash_table.tbl, &gl_hash_table); for (i = 0; i < tbl->size; i++) { - rht_for_each_entry_safe(gl, pos, next, tbl, i, gl_node) { + rht_for_each_entry_rcu(gl, pos, tbl, i, gl_node) { if ((gl->gl_name.ln_sbd == sdp) && lockref_get_not_dead(&gl->gl_lockref)) examiner(gl); @@ -1461,10 +1461,10 @@ static void clear_glock(struct gfs2_glock *gl) { gfs2_glock_remove_from_lru(gl); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); if (gl->gl_state != LM_ST_UNLOCKED) handle_callback(gl, LM_ST_UNLOCKED, 0, false); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gfs2_glock_put(gl); } @@ -1482,9 +1482,9 @@ void gfs2_glock_thaw(struct gfs2_sbd *sdp) static void dump_glock(struct seq_file *seq, struct gfs2_glock *gl) { - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); gfs2_dump_glock(seq, gl); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); } static void dump_glock_func(struct gfs2_glock *gl) @@ -1506,7 +1506,9 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp) flush_workqueue(glock_workqueue); glock_hash_walk(clear_glock, sdp); flush_workqueue(glock_workqueue); - wait_event(sdp->sd_glock_wait, atomic_read(&sdp->sd_glock_disposal) == 0); + wait_event_timeout(sdp->sd_glock_wait, + atomic_read(&sdp->sd_glock_disposal) == 0, + HZ * 600); glock_hash_walk(dump_glock_func, sdp); } @@ -1518,10 +1520,10 @@ void gfs2_glock_finish_truncate(struct gfs2_inode *ip) ret = gfs2_truncatei_resume(ip); gfs2_assert_withdraw(gl->gl_name.ln_sbd, ret == 0); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); clear_bit(GLF_LOCK, &gl->gl_flags); run_queue(gl, 1); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); } static const char *state2str(unsigned state) @@ -1539,7 +1541,7 @@ static const char *state2str(unsigned state) return "??"; } -static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags) +static const char *hflags2str(char *buf, u16 flags, unsigned long iflags) { char *p = buf; if (flags & LM_FLAG_TRY) diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index 32572f71f027..46ab67fc16da 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -79,15 +79,15 @@ enum { * requested had acquired and released the lock. */ -#define LM_FLAG_TRY 0x00000001 -#define LM_FLAG_TRY_1CB 0x00000002 -#define LM_FLAG_NOEXP 0x00000004 -#define LM_FLAG_ANY 0x00000008 -#define LM_FLAG_PRIORITY 0x00000010 -#define GL_ASYNC 0x00000040 -#define GL_EXACT 0x00000080 -#define GL_SKIP 0x00000100 -#define GL_NOCACHE 0x00000400 +#define LM_FLAG_TRY 0x0001 +#define LM_FLAG_TRY_1CB 0x0002 +#define LM_FLAG_NOEXP 0x0004 +#define LM_FLAG_ANY 0x0008 +#define LM_FLAG_PRIORITY 0x0010 +#define GL_ASYNC 0x0040 +#define GL_EXACT 0x0080 +#define GL_SKIP 0x0100 +#define GL_NOCACHE 0x0400 /* * lm_async_cb return flags @@ -141,7 +141,7 @@ static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock * struct pid *pid; /* Look in glock's list of holders for one with current task as owner */ - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); pid = task_pid(current); list_for_each_entry(gh, &gl->gl_holders, gh_list) { if (!test_bit(HIF_HOLDER, &gh->gh_iflags)) @@ -151,7 +151,7 @@ static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock * } gh = NULL; out: - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); return gh; } @@ -183,8 +183,8 @@ extern int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, int create, struct gfs2_glock **glp); extern void gfs2_glock_put(struct gfs2_glock *gl); extern void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, - unsigned flags, struct gfs2_holder *gh); -extern void gfs2_holder_reinit(unsigned int state, unsigned flags, + u16 flags, struct gfs2_holder *gh); +extern void gfs2_holder_reinit(unsigned int state, u16 flags, struct gfs2_holder *gh); extern void gfs2_holder_uninit(struct gfs2_holder *gh); extern int gfs2_glock_nq(struct gfs2_holder *gh); @@ -195,7 +195,7 @@ extern void gfs2_glock_dq_wait(struct gfs2_holder *gh); extern void gfs2_glock_dq_uninit(struct gfs2_holder *gh); extern int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number, const struct gfs2_glock_operations *glops, - unsigned int state, int flags, + unsigned int state, u16 flags, struct gfs2_holder *gh); extern int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs); extern void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs); @@ -215,7 +215,7 @@ void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...); */ static inline int gfs2_glock_nq_init(struct gfs2_glock *gl, - unsigned int state, int flags, + unsigned int state, u16 flags, struct gfs2_holder *gh) { int error; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 1f6c9c3fe5cb..f348cfb6b69a 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -146,11 +146,11 @@ static void rgrp_go_sync(struct gfs2_glock *gl) struct gfs2_rgrpd *rgd; int error; - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); rgd = gl->gl_object; if (rgd) gfs2_rgrp_brelse(rgd); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) return; @@ -162,11 +162,11 @@ static void rgrp_go_sync(struct gfs2_glock *gl) mapping_set_error(mapping, error); gfs2_ail_empty_gl(gl); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); rgd = gl->gl_object; if (rgd) gfs2_free_clones(rgd); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); } /** @@ -542,7 +542,7 @@ static int freeze_go_demote_ok(const struct gfs2_glock *gl) * iopen_go_callback - schedule the dcache entry for the inode to be deleted * @gl: the glock * - * gl_spin lock is held while calling this + * gl_lockref.lock lock is held while calling this */ static void iopen_go_callback(struct gfs2_glock *gl, bool remote) { diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 121ed08d9d9f..845fb09cc606 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -259,8 +259,8 @@ struct gfs2_holder { struct gfs2_glock *gh_gl; struct pid *gh_owner_pid; - unsigned int gh_state; - unsigned gh_flags; + u16 gh_flags; + u16 gh_state; int gh_error; unsigned long gh_iflags; /* HIF_... */ @@ -270,6 +270,13 @@ struct gfs2_holder { /* Number of quota types we support */ #define GFS2_MAXQUOTAS 2 +struct gfs2_qadata { /* quota allocation data */ + /* Quota stuff */ + struct gfs2_quota_data *qa_qd[2 * GFS2_MAXQUOTAS]; + struct gfs2_holder qa_qd_ghs[2 * GFS2_MAXQUOTAS]; + unsigned int qa_qd_num; +}; + /* Resource group multi-block reservation, in order of appearance: Step 1. Function prepares to write, allocates a mb, sets the size hint. @@ -288,11 +295,6 @@ struct gfs2_blkreserv { struct gfs2_rbm rs_rbm; /* Start of reservation */ u32 rs_free; /* how many blocks are still free */ u64 rs_inum; /* Inode number for reservation */ - - /* ancillary quota stuff */ - struct gfs2_quota_data *rs_qa_qd[2 * GFS2_MAXQUOTAS]; - struct gfs2_holder rs_qa_qd_ghs[2 * GFS2_MAXQUOTAS]; - unsigned int rs_qa_qd_num; }; /* @@ -334,9 +336,8 @@ struct gfs2_glock { struct lm_lockname gl_name; struct lockref gl_lockref; -#define gl_spin gl_lockref.lock - /* State fields protected by gl_spin */ + /* State fields protected by gl_lockref.lock */ unsigned int gl_state:2, /* Current state */ gl_target:2, /* Target state */ gl_demote_state:2, /* State requested by remote node */ @@ -392,7 +393,8 @@ struct gfs2_inode { struct gfs2_glock *i_gl; /* Move into i_gh? */ struct gfs2_holder i_iopen_gh; struct gfs2_holder i_gh; /* for prepare/commit_write only */ - struct gfs2_blkreserv *i_res; /* rgrp multi-block reservation */ + struct gfs2_qadata *i_qadata; /* quota allocation data */ + struct gfs2_blkreserv i_res; /* rgrp multi-block reservation */ struct gfs2_rgrpd *i_rgd; u64 i_goal; /* goal block for allocations */ struct rw_semaphore i_rw_mutex; @@ -403,6 +405,7 @@ struct gfs2_inode { u32 i_diskflags; u8 i_height; u8 i_depth; + u16 i_rahead; }; /* @@ -559,6 +562,8 @@ struct gfs2_args { unsigned int ar_errors:2; /* errors=withdraw | panic */ unsigned int ar_nobarrier:1; /* do not send barriers */ unsigned int ar_rgrplvb:1; /* use lvbs for rgrp info */ + unsigned int ar_loccookie:1; /* use location based readdir + cookies */ int ar_commit; /* Commit interval */ int ar_statfs_quantum; /* The fast statfs interval */ int ar_quota_quantum; /* The quota interval */ @@ -686,6 +691,7 @@ struct gfs2_sbd { u64 sd_heightsize[GFS2_MAX_META_HEIGHT + 1]; u32 sd_max_jheight; /* Max height of journaled file's meta tree */ u64 sd_jheightsize[GFS2_MAX_META_HEIGHT + 1]; + u32 sd_max_dents_per_leaf; /* Max number of dirents in a leaf block */ struct gfs2_args sd_args; /* Mount arguments */ struct gfs2_tune sd_tune; /* Filesystem tuning structure */ diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 063fdfcf8275..3e94400d587c 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -191,13 +191,13 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, fail_refresh: ip->i_iopen_gh.gh_flags |= GL_NOCACHE; ip->i_iopen_gh.gh_gl->gl_object = NULL; - gfs2_glock_dq_uninit(&ip->i_iopen_gh); + gfs2_glock_dq_wait(&ip->i_iopen_gh); + gfs2_holder_uninit(&ip->i_iopen_gh); fail_iopen: if (io_gl) gfs2_glock_put(io_gl); fail_put: ip->i_gl->gl_object = NULL; - gfs2_glock_put(ip->i_gl); fail: iget_failed(inode); return ERR_PTR(error); @@ -593,7 +593,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, struct gfs2_inode *dip = GFS2_I(dir), *ip; struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); struct gfs2_glock *io_gl; - int error, free_vfs_inode = 0; + int error, free_vfs_inode = 1; u32 aflags = 0; unsigned blocks = 1; struct gfs2_diradd da = { .bh = NULL, .save_loc = 1, }; @@ -601,7 +601,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (!name->len || name->len > GFS2_FNAMESIZE) return -ENAMETOOLONG; - error = gfs2_rs_alloc(dip); + error = gfs2_rsqa_alloc(dip); if (error) return error; @@ -650,10 +650,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = posix_acl_create(dir, &mode, &default_acl, &acl); if (error) - goto fail_free_vfs_inode; + goto fail_gunlock; ip = GFS2_I(inode); - error = gfs2_rs_alloc(ip); + error = gfs2_rsqa_alloc(ip); if (error) goto fail_free_acls; @@ -685,6 +685,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, ip->i_entries = 2; break; } + + /* Force SYSTEM flag on all files and subdirs of a SYSTEM directory */ + if (dip->i_diskflags & GFS2_DIF_SYSTEM) + ip->i_diskflags |= GFS2_DIF_SYSTEM; + gfs2_set_inode_flags(inode); if ((GFS2_I(d_inode(sdp->sd_root_dir)) == dip) || @@ -733,6 +738,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, gfs2_set_iop(inode); insert_inode_hash(inode); + free_vfs_inode = 0; /* After this point, the inode is no longer + considered free. Any failures need to undo + the gfs2 structures. */ if (default_acl) { error = gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); posix_acl_release(default_acl); @@ -766,24 +774,19 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, return error; fail_gunlock3: - gfs2_glock_dq_uninit(ghs + 1); - if (ip->i_gl) - gfs2_glock_put(ip->i_gl); - goto fail_gunlock; - + gfs2_glock_dq_uninit(&ip->i_iopen_gh); + gfs2_glock_put(io_gl); fail_gunlock2: gfs2_glock_dq_uninit(ghs + 1); fail_free_inode: if (ip->i_gl) gfs2_glock_put(ip->i_gl); - gfs2_rs_delete(ip, NULL); + gfs2_rsqa_delete(ip, NULL); fail_free_acls: if (default_acl) posix_acl_release(default_acl); if (acl) posix_acl_release(acl); -fail_free_vfs_inode: - free_vfs_inode = 1; fail_gunlock: gfs2_dir_no_add(&da); gfs2_glock_dq_uninit(ghs); @@ -898,7 +901,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, if (S_ISDIR(inode->i_mode)) return -EPERM; - error = gfs2_rs_alloc(dip); + error = gfs2_rsqa_alloc(dip); if (error) return error; @@ -1371,7 +1374,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, if (error) return error; - error = gfs2_rs_alloc(ndip); + error = gfs2_rsqa_alloc(ndip); if (error) return error; @@ -1712,24 +1715,30 @@ static int gfs2_rename2(struct inode *odir, struct dentry *odentry, } /** - * gfs2_follow_link - Follow a symbolic link + * gfs2_get_link - Follow a symbolic link * @dentry: The dentry of the link - * @nd: Data that we pass to vfs_follow_link() + * @inode: The inode of the link + * @done: destructor for return value * * This can handle symlinks of any size. * * Returns: 0 on success or error code */ -static const char *gfs2_follow_link(struct dentry *dentry, void **cookie) +static const char *gfs2_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct gfs2_inode *ip = GFS2_I(d_inode(dentry)); + struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder i_gh; struct buffer_head *dibh; unsigned int size; char *buf; int error; + if (!dentry) + return ERR_PTR(-ECHILD); + gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh); error = gfs2_glock_nq(&i_gh); if (error) { @@ -1759,7 +1768,7 @@ static const char *gfs2_follow_link(struct dentry *dentry, void **cookie) out: gfs2_glock_dq_uninit(&i_gh); if (!IS_ERR(buf)) - *cookie = buf; + set_delayed_call(done, kfree_link, buf); return buf; } @@ -1854,11 +1863,7 @@ static int setattr_chown(struct inode *inode, struct iattr *attr) if (!(attr->ia_valid & ATTR_GID) || gid_eq(ogid, ngid)) ogid = ngid = NO_GID_QUOTA_CHANGE; - error = get_write_access(inode); - if (error) - return error; - - error = gfs2_rs_alloc(ip); + error = gfs2_rsqa_alloc(ip); if (error) goto out; @@ -1898,7 +1903,6 @@ out_end_trans: out_gunlock_q: gfs2_quota_unlock(ip); out: - put_write_access(inode); return error; } @@ -1920,7 +1924,7 @@ static int gfs2_setattr(struct dentry *dentry, struct iattr *attr) struct gfs2_holder i_gh; int error; - error = gfs2_rs_alloc(ip); + error = gfs2_rsqa_alloc(ip); if (error) return error; @@ -2002,7 +2006,7 @@ static int gfs2_setxattr(struct dentry *dentry, const char *name, gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); ret = gfs2_glock_nq(&gh); if (ret == 0) { - ret = gfs2_rs_alloc(ip); + ret = gfs2_rsqa_alloc(ip); if (ret == 0) ret = generic_setxattr(dentry, name, data, size, flags); gfs2_glock_dq(&gh); @@ -2043,7 +2047,7 @@ static int gfs2_removexattr(struct dentry *dentry, const char *name) gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); ret = gfs2_glock_nq(&gh); if (ret == 0) { - ret = gfs2_rs_alloc(ip); + ret = gfs2_rsqa_alloc(ip); if (ret == 0) ret = generic_removexattr(dentry, name); gfs2_glock_dq(&gh); @@ -2132,8 +2136,7 @@ const struct inode_operations gfs2_dir_iops = { const struct inode_operations gfs2_symlink_iops = { .readlink = generic_readlink, - .follow_link = gfs2_follow_link, - .put_link = kfree_put_link, + .get_link = gfs2_get_link, .permission = gfs2_permission, .setattr = gfs2_setattr, .getattr = gfs2_getattr, diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 284c1542783e..8b907c5cc913 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -50,7 +50,7 @@ static inline void gfs2_update_stats(struct gfs2_lkstats *s, unsigned index, s64 delta = sample - s->stats[index]; s->stats[index] += (delta >> 3); index++; - s->stats[index] += ((abs64(delta) - s->stats[index]) >> 2); + s->stats[index] += ((abs(delta) - s->stats[index]) >> 2); } /** diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 536e7a6252cd..0ff028c15199 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -716,6 +716,9 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, } trace_gfs2_log_flush(sdp, 1); + if (type == SHUTDOWN_FLUSH) + clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); + sdp->sd_log_flush_head = sdp->sd_log_head; sdp->sd_log_flush_wrapped = 0; tr = sdp->sd_log_tr; diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 241a399bf83d..1d709d496364 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -41,7 +41,9 @@ static void gfs2_init_inode_once(void *foo) inode_init_once(&ip->i_inode); init_rwsem(&ip->i_rw_mutex); INIT_LIST_HEAD(&ip->i_trunc_list); - ip->i_res = NULL; + ip->i_qadata = NULL; + memset(&ip->i_res, 0, sizeof(ip->i_res)); + RB_CLEAR_NODE(&ip->i_res.rs_node); ip->i_hash_cache = NULL; } @@ -50,7 +52,7 @@ static void gfs2_init_glock_once(void *foo) struct gfs2_glock *gl = foo; INIT_HLIST_BL_NODE(&gl->gl_list); - spin_lock_init(&gl->gl_spin); + spin_lock_init(&gl->gl_lockref.lock); INIT_LIST_HEAD(&gl->gl_holders); INIT_LIST_HEAD(&gl->gl_lru); INIT_LIST_HEAD(&gl->gl_ail_list); @@ -135,10 +137,10 @@ static int __init init_gfs2_fs(void) if (!gfs2_quotad_cachep) goto fail; - gfs2_rsrv_cachep = kmem_cache_create("gfs2_mblk", - sizeof(struct gfs2_blkreserv), + gfs2_qadata_cachep = kmem_cache_create("gfs2_qadata", + sizeof(struct gfs2_qadata), 0, 0, NULL); - if (!gfs2_rsrv_cachep) + if (!gfs2_qadata_cachep) goto fail; register_shrinker(&gfs2_qd_shrinker); @@ -193,8 +195,8 @@ fail_lru: unregister_shrinker(&gfs2_qd_shrinker); gfs2_glock_exit(); - if (gfs2_rsrv_cachep) - kmem_cache_destroy(gfs2_rsrv_cachep); + if (gfs2_qadata_cachep) + kmem_cache_destroy(gfs2_qadata_cachep); if (gfs2_quotad_cachep) kmem_cache_destroy(gfs2_quotad_cachep); @@ -238,7 +240,7 @@ static void __exit exit_gfs2_fs(void) rcu_barrier(); mempool_destroy(gfs2_page_pool); - kmem_cache_destroy(gfs2_rsrv_cachep); + kmem_cache_destroy(gfs2_qadata_cachep); kmem_cache_destroy(gfs2_quotad_cachep); kmem_cache_destroy(gfs2_rgrpd_cachep); kmem_cache_destroy(gfs2_bufdata_cachep); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 0e1d4be5865a..e137d96f1b17 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -187,6 +187,52 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno) return bh; } +static void gfs2_meta_read_endio(struct bio *bio) +{ + struct bio_vec *bvec; + int i; + + bio_for_each_segment_all(bvec, bio, i) { + struct page *page = bvec->bv_page; + struct buffer_head *bh = page_buffers(page); + unsigned int len = bvec->bv_len; + + while (bh_offset(bh) < bvec->bv_offset) + bh = bh->b_this_page; + do { + struct buffer_head *next = bh->b_this_page; + len -= bh->b_size; + bh->b_end_io(bh, !bio->bi_error); + bh = next; + } while (bh && len); + } + bio_put(bio); +} + +/* + * Submit several consecutive buffer head I/O requests as a single bio I/O + * request. (See submit_bh_wbc.) + */ +static void gfs2_submit_bhs(int rw, struct buffer_head *bhs[], int num) +{ + struct buffer_head *bh = bhs[0]; + struct bio *bio; + int i; + + if (!num) + return; + + bio = bio_alloc(GFP_NOIO, num); + bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); + bio->bi_bdev = bh->b_bdev; + for (i = 0; i < num; i++) { + bh = bhs[i]; + bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); + } + bio->bi_end_io = gfs2_meta_read_endio; + submit_bio(rw, bio); +} + /** * gfs2_meta_read - Read a block from disk * @gl: The glock covering the block @@ -198,10 +244,11 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno) */ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, - struct buffer_head **bhp) + int rahead, struct buffer_head **bhp) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - struct buffer_head *bh; + struct buffer_head *bh, *bhs[2]; + int num = 0; if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) { *bhp = NULL; @@ -213,14 +260,31 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); - return 0; + flags &= ~DIO_WAIT; + } else { + bh->b_end_io = end_buffer_read_sync; + get_bh(bh); + bhs[num++] = bh; } - bh->b_end_io = end_buffer_read_sync; - get_bh(bh); - submit_bh(READ_SYNC | REQ_META | REQ_PRIO, bh); + + if (rahead) { + bh = gfs2_getbuf(gl, blkno + 1, CREATE); + + lock_buffer(bh); + if (buffer_uptodate(bh)) { + unlock_buffer(bh); + brelse(bh); + } else { + bh->b_end_io = end_buffer_read_sync; + bhs[num++] = bh; + } + } + + gfs2_submit_bhs(READ_SYNC | REQ_META | REQ_PRIO, bhs, num); if (!(flags & DIO_WAIT)) return 0; + bh = *bhp; wait_on_buffer(bh); if (unlikely(!buffer_uptodate(bh))) { struct gfs2_trans *tr = current->journal_info; @@ -341,8 +405,12 @@ int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num, struct buffer_head *bh; int ret = 0; u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI; + int rahead = 0; + + if (num == ip->i_no_addr) + rahead = ip->i_rahead; - ret = gfs2_meta_read(gl, num, DIO_WAIT, &bh); + ret = gfs2_meta_read(gl, num, DIO_WAIT, rahead, &bh); if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) { brelse(bh); ret = -EIO; diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index 8ca161567a93..c5086c8af5ed 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -53,7 +53,7 @@ static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping) extern struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno); extern int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, - struct buffer_head **bhp); + int rahead, struct buffer_head **bhp); extern int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh); extern struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 02586e7eb964..dbed9e243ea2 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -352,6 +352,9 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent) sdp->sd_jheightsize[x] = ~0; gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT); + sdp->sd_max_dents_per_leaf = (sdp->sd_sb.sb_bsize - + sizeof(struct gfs2_leaf)) / + GFS2_MIN_DIRENT_SIZE; return 0; } @@ -910,8 +913,7 @@ fail_qc_i: fail_ut_i: iput(sdp->sd_sc_inode); fail: - if (pn) - iput(pn); + iput(pn); return error; } @@ -1291,6 +1293,9 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, up_write(&s->s_umount); blkdev_put(bdev, mode); down_write(&s->s_umount); + } else { + /* s_mode must be set before deactivate_locked_super calls */ + s->s_mode = mode; } memset(&args, 0, sizeof(args)); @@ -1312,10 +1317,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, if ((flags ^ s->s_flags) & MS_RDONLY) goto error_super; } else { - char b[BDEVNAME_SIZE]; - - s->s_mode = mode; - strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); + snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, &args, flags & MS_SILENT ? 1 : 0); if (error) diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 3a31226531ea..be6d9c450b22 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -388,7 +388,7 @@ static int bh_get(struct gfs2_quota_data *qd) error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0); if (error) goto fail; - error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, &bh); + error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, 0, &bh); if (error) goto fail; error = -EIO; @@ -527,37 +527,70 @@ static void qdsb_put(struct gfs2_quota_data *qd) qd_put(qd); } +/** + * gfs2_qa_alloc - make sure we have a quota allocations data structure, + * if necessary + * @ip: the inode for this reservation + */ +int gfs2_qa_alloc(struct gfs2_inode *ip) +{ + int error = 0; + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + + if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) + return 0; + + down_write(&ip->i_rw_mutex); + if (ip->i_qadata == NULL) { + ip->i_qadata = kmem_cache_zalloc(gfs2_qadata_cachep, GFP_NOFS); + if (!ip->i_qadata) + error = -ENOMEM; + } + up_write(&ip->i_rw_mutex); + return error; +} + +void gfs2_qa_delete(struct gfs2_inode *ip, atomic_t *wcount) +{ + down_write(&ip->i_rw_mutex); + if (ip->i_qadata && ((wcount == NULL) || (atomic_read(wcount) <= 1))) { + kmem_cache_free(gfs2_qadata_cachep, ip->i_qadata); + ip->i_qadata = NULL; + } + up_write(&ip->i_rw_mutex); +} + int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data **qd; int error; - if (ip->i_res == NULL) { - error = gfs2_rs_alloc(ip); + if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) + return 0; + + if (ip->i_qadata == NULL) { + error = gfs2_rsqa_alloc(ip); if (error) return error; } - qd = ip->i_res->rs_qa_qd; + qd = ip->i_qadata->qa_qd; - if (gfs2_assert_warn(sdp, !ip->i_res->rs_qa_qd_num) || + if (gfs2_assert_warn(sdp, !ip->i_qadata->qa_qd_num) || gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags))) return -EIO; - if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) - return 0; - error = qdsb_get(sdp, make_kqid_uid(ip->i_inode.i_uid), qd); if (error) goto out; - ip->i_res->rs_qa_qd_num++; + ip->i_qadata->qa_qd_num++; qd++; error = qdsb_get(sdp, make_kqid_gid(ip->i_inode.i_gid), qd); if (error) goto out; - ip->i_res->rs_qa_qd_num++; + ip->i_qadata->qa_qd_num++; qd++; if (!uid_eq(uid, NO_UID_QUOTA_CHANGE) && @@ -565,7 +598,7 @@ int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) error = qdsb_get(sdp, make_kqid_uid(uid), qd); if (error) goto out; - ip->i_res->rs_qa_qd_num++; + ip->i_qadata->qa_qd_num++; qd++; } @@ -574,7 +607,7 @@ int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) error = qdsb_get(sdp, make_kqid_gid(gid), qd); if (error) goto out; - ip->i_res->rs_qa_qd_num++; + ip->i_qadata->qa_qd_num++; qd++; } @@ -587,17 +620,17 @@ out: void gfs2_quota_unhold(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - unsigned int x; + u32 x; - if (ip->i_res == NULL) + if (ip->i_qadata == NULL) return; gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags)); - for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) { - qdsb_put(ip->i_res->rs_qa_qd[x]); - ip->i_res->rs_qa_qd[x] = NULL; + for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { + qdsb_put(ip->i_qadata->qa_qd[x]); + ip->i_qadata->qa_qd[x] = NULL; } - ip->i_res->rs_qa_qd_num = 0; + ip->i_qadata->qa_qd_num = 0; } static int sort_qd(const void *a, const void *b) @@ -843,7 +876,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda) unsigned int nalloc = 0, blocks; int error; - error = gfs2_rs_alloc(ip); + error = gfs2_rsqa_alloc(ip); if (error) return error; @@ -1003,23 +1036,23 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qd; - unsigned int x; + u32 x; int error = 0; - error = gfs2_quota_hold(ip, uid, gid); - if (error) - return error; - if (capable(CAP_SYS_RESOURCE) || sdp->sd_args.ar_quota != GFS2_QUOTA_ON) return 0; - sort(ip->i_res->rs_qa_qd, ip->i_res->rs_qa_qd_num, + error = gfs2_quota_hold(ip, uid, gid); + if (error) + return error; + + sort(ip->i_qadata->qa_qd, ip->i_qadata->qa_qd_num, sizeof(struct gfs2_quota_data *), sort_qd, NULL); - for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) { - qd = ip->i_res->rs_qa_qd[x]; - error = do_glock(qd, NO_FORCE, &ip->i_res->rs_qa_qd_ghs[x]); + for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { + qd = ip->i_qadata->qa_qd[x]; + error = do_glock(qd, NO_FORCE, &ip->i_qadata->qa_qd_ghs[x]); if (error) break; } @@ -1028,7 +1061,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) set_bit(GIF_QD_LOCKED, &ip->i_flags); else { while (x--) - gfs2_glock_dq_uninit(&ip->i_res->rs_qa_qd_ghs[x]); + gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]); gfs2_quota_unhold(ip); } @@ -1076,20 +1109,20 @@ void gfs2_quota_unlock(struct gfs2_inode *ip) struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qda[4]; unsigned int count = 0; - unsigned int x; + u32 x; int found; if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags)) goto out; - for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) { + for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { struct gfs2_quota_data *qd; int sync; - qd = ip->i_res->rs_qa_qd[x]; + qd = ip->i_qadata->qa_qd[x]; sync = need_sync(qd); - gfs2_glock_dq_uninit(&ip->i_res->rs_qa_qd_ghs[x]); + gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]); if (!sync) continue; @@ -1158,7 +1191,7 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid, struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qd; s64 value, warn, limit; - unsigned int x; + u32 x; int error = 0; ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */ @@ -1168,8 +1201,8 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid, if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON) return 0; - for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) { - qd = ip->i_res->rs_qa_qd[x]; + for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { + qd = ip->i_qadata->qa_qd[x]; if (!(qid_eq(qd->qd_id, make_kqid_uid(uid)) || qid_eq(qd->qd_id, make_kqid_gid(gid)))) @@ -1216,15 +1249,17 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change, kuid_t uid, kgid_t gid) { struct gfs2_quota_data *qd; - unsigned int x; + u32 x; + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - if (gfs2_assert_warn(GFS2_SB(&ip->i_inode), change)) + if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON || + gfs2_assert_warn(sdp, change)) return; if (ip->i_diskflags & GFS2_DIF_SYSTEM) return; - for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) { - qd = ip->i_res->rs_qa_qd[x]; + for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { + qd = ip->i_qadata->qa_qd[x]; if (qid_eq(qd->qd_id, make_kqid_uid(uid)) || qid_eq(qd->qd_id, make_kqid_gid(gid))) { @@ -1635,7 +1670,7 @@ static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid, if (error) return error; - error = gfs2_rs_alloc(ip); + error = gfs2_rsqa_alloc(ip); if (error) goto out_put; diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index ad04b3acae2b..5e47c935a515 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -18,6 +18,8 @@ struct gfs2_sbd; #define NO_UID_QUOTA_CHANGE INVALID_UID #define NO_GID_QUOTA_CHANGE INVALID_GID +extern int gfs2_qa_alloc(struct gfs2_inode *ip); +extern void gfs2_qa_delete(struct gfs2_inode *ip, atomic_t *wcount); extern int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid); extern void gfs2_quota_unhold(struct gfs2_inode *ip); diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 475985d14758..07c0265aa195 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -596,27 +596,13 @@ void gfs2_free_clones(struct gfs2_rgrpd *rgd) } /** - * gfs2_rs_alloc - make sure we have a reservation assigned to the inode + * gfs2_rsqa_alloc - make sure we have a reservation assigned to the inode + * plus a quota allocations data structure, if necessary * @ip: the inode for this reservation */ -int gfs2_rs_alloc(struct gfs2_inode *ip) +int gfs2_rsqa_alloc(struct gfs2_inode *ip) { - int error = 0; - - down_write(&ip->i_rw_mutex); - if (ip->i_res) - goto out; - - ip->i_res = kmem_cache_zalloc(gfs2_rsrv_cachep, GFP_NOFS); - if (!ip->i_res) { - error = -ENOMEM; - goto out; - } - - RB_CLEAR_NODE(&ip->i_res->rs_node); -out: - up_write(&ip->i_rw_mutex); - return error; + return gfs2_qa_alloc(ip); } static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs) @@ -678,21 +664,20 @@ void gfs2_rs_deltree(struct gfs2_blkreserv *rs) } /** - * gfs2_rs_delete - delete a multi-block reservation + * gfs2_rsqa_delete - delete a multi-block reservation and quota allocation * @ip: The inode for this reservation * @wcount: The inode's write count, or NULL * */ -void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount) +void gfs2_rsqa_delete(struct gfs2_inode *ip, atomic_t *wcount) { down_write(&ip->i_rw_mutex); - if (ip->i_res && ((wcount == NULL) || (atomic_read(wcount) <= 1))) { - gfs2_rs_deltree(ip->i_res); - BUG_ON(ip->i_res->rs_free); - kmem_cache_free(gfs2_rsrv_cachep, ip->i_res); - ip->i_res = NULL; + if ((wcount == NULL) || (atomic_read(wcount) <= 1)) { + gfs2_rs_deltree(&ip->i_res); + BUG_ON(ip->i_res.rs_free); } up_write(&ip->i_rw_mutex); + gfs2_qa_delete(ip, wcount); } /** @@ -729,9 +714,9 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp) rb_erase(n, &sdp->sd_rindex_tree); if (gl) { - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); gl->gl_object = NULL; - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); gfs2_glock_add_to_lru(gl); gfs2_glock_put(gl); } @@ -933,8 +918,9 @@ static int read_rindex_entry(struct gfs2_inode *ip) goto fail; rgd->rd_gl->gl_object = rgd; - rgd->rd_gl->gl_vm.start = rgd->rd_addr * bsize; - rgd->rd_gl->gl_vm.end = rgd->rd_gl->gl_vm.start + (rgd->rd_length * bsize) - 1; + rgd->rd_gl->gl_vm.start = (rgd->rd_addr * bsize) & PAGE_CACHE_MASK; + rgd->rd_gl->gl_vm.end = PAGE_CACHE_ALIGN((rgd->rd_addr + + rgd->rd_length) * bsize) - 1; rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lksb.sb_lvbptr; rgd->rd_flags &= ~(GFS2_RDF_UPTODATE | GFS2_RDF_PREFERRED); if (rgd->rd_data > sdp->sd_max_rg_data) @@ -1157,7 +1143,7 @@ static int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd) for (x = 0; x < length; x++) { bi = rgd->rd_bits + x; - error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, &bi->bi_bh); + error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, 0, &bi->bi_bh); if (error) goto fail; } @@ -1455,7 +1441,7 @@ static void rs_insert(struct gfs2_inode *ip) { struct rb_node **newn, *parent = NULL; int rc; - struct gfs2_blkreserv *rs = ip->i_res; + struct gfs2_blkreserv *rs = &ip->i_res; struct gfs2_rgrpd *rgd = rs->rs_rbm.rgd; u64 fsblock = gfs2_rbm_to_block(&rs->rs_rbm); @@ -1502,7 +1488,7 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip, { struct gfs2_rbm rbm = { .rgd = rgd, }; u64 goal; - struct gfs2_blkreserv *rs = ip->i_res; + struct gfs2_blkreserv *rs = &ip->i_res; u32 extlen; u32 free_blocks = rgd->rd_free_clone - rgd->rd_reserved; int ret; @@ -1573,7 +1559,7 @@ static u64 gfs2_next_unreserved_block(struct gfs2_rgrpd *rgd, u64 block, } if (n) { - while ((rs_cmp(block, length, rs) == 0) && (ip->i_res != rs)) { + while ((rs_cmp(block, length, rs) == 0) && (&ip->i_res != rs)) { block = gfs2_rbm_to_block(&rs->rs_rbm) + rs->rs_free; n = n->rb_right; if (n == NULL) @@ -1803,7 +1789,7 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip continue; *last_unlinked = block; - error = gfs2_glock_get(sdp, block, &gfs2_inode_glops, CREATE, &gl); + error = gfs2_glock_get(sdp, block, &gfs2_iopen_glops, CREATE, &gl); if (error) continue; @@ -1983,7 +1969,7 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_rgrpd *begin = NULL; - struct gfs2_blkreserv *rs = ip->i_res; + struct gfs2_blkreserv *rs = &ip->i_res; int error = 0, rg_locked, flags = 0; u64 last_unlinked = NO_BLOCK; int loops = 0; @@ -2112,7 +2098,7 @@ next_rgrp: void gfs2_inplace_release(struct gfs2_inode *ip) { - struct gfs2_blkreserv *rs = ip->i_res; + struct gfs2_blkreserv *rs = &ip->i_res; if (rs->rs_rgd_gh.gh_gl) gfs2_glock_dq_uninit(&rs->rs_rgd_gh); @@ -2266,7 +2252,7 @@ static void gfs2_rgrp_error(struct gfs2_rgrpd *rgd) static void gfs2_adjust_reservation(struct gfs2_inode *ip, const struct gfs2_rbm *rbm, unsigned len) { - struct gfs2_blkreserv *rs = ip->i_res; + struct gfs2_blkreserv *rs = &ip->i_res; struct gfs2_rgrpd *rgd = rbm->rgd; unsigned rlen; u64 block; @@ -2309,8 +2295,8 @@ static void gfs2_set_alloc_start(struct gfs2_rbm *rbm, { u64 goal; - if (gfs2_rs_active(ip->i_res)) { - *rbm = ip->i_res->rs_rbm; + if (gfs2_rs_active(&ip->i_res)) { + *rbm = ip->i_res.rs_rbm; return; } @@ -2364,7 +2350,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks, gfs2_alloc_extent(&rbm, dinode, nblocks); block = gfs2_rbm_to_block(&rbm); rbm.rgd->rd_last_alloc = block - rbm.rgd->rd_data0; - if (gfs2_rs_active(ip->i_res)) + if (gfs2_rs_active(&ip->i_res)) gfs2_adjust_reservation(ip, &rbm, *nblocks); ndata = *nblocks; if (dinode) diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index c0ab33fa3eed..66b51cf66dfa 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -49,9 +49,9 @@ extern void gfs2_inplace_release(struct gfs2_inode *ip); extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n, bool dinode, u64 *generation); -extern int gfs2_rs_alloc(struct gfs2_inode *ip); +extern int gfs2_rsqa_alloc(struct gfs2_inode *ip); extern void gfs2_rs_deltree(struct gfs2_blkreserv *rs); -extern void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount); +extern void gfs2_rsqa_delete(struct gfs2_inode *ip, atomic_t *wcount); extern void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta); extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen); extern void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip); @@ -78,7 +78,7 @@ extern int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, extern int gfs2_fitrim(struct file *filp, void __user *argp); /* This is how to tell if a reservation is in the rgrp tree: */ -static inline bool gfs2_rs_active(struct gfs2_blkreserv *rs) +static inline bool gfs2_rs_active(const struct gfs2_blkreserv *rs) { return rs && !RB_EMPTY_NODE(&rs->rs_node); } diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 894fb01a91da..8f960a51a9a0 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -83,6 +83,8 @@ enum { Opt_nobarrier, Opt_rgrplvb, Opt_norgrplvb, + Opt_loccookie, + Opt_noloccookie, Opt_error, }; @@ -122,6 +124,8 @@ static const match_table_t tokens = { {Opt_nobarrier, "nobarrier"}, {Opt_rgrplvb, "rgrplvb"}, {Opt_norgrplvb, "norgrplvb"}, + {Opt_loccookie, "loccookie"}, + {Opt_noloccookie, "noloccookie"}, {Opt_error, NULL} }; @@ -278,6 +282,12 @@ int gfs2_mount_args(struct gfs2_args *args, char *options) case Opt_norgrplvb: args->ar_rgrplvb = 0; break; + case Opt_loccookie: + args->ar_loccookie = 1; + break; + case Opt_noloccookie: + args->ar_loccookie = 0; + break; case Opt_error: default: pr_warn("invalid mount option: %s\n", o); @@ -556,6 +566,7 @@ void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh, struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local; gfs2_trans_add_meta(l_ip->i_gl, l_bh); + gfs2_trans_add_meta(m_ip->i_gl, m_bh); spin_lock(&sdp->sd_statfs_spin); m_sc->sc_total += l_sc->sc_total; @@ -564,10 +575,8 @@ void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh, memset(l_sc, 0, sizeof(struct gfs2_statfs_change)); memset(l_bh->b_data + sizeof(struct gfs2_dinode), 0, sizeof(struct gfs2_statfs_change)); - spin_unlock(&sdp->sd_statfs_spin); - - gfs2_trans_add_meta(m_ip->i_gl, m_bh); gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode)); + spin_unlock(&sdp->sd_statfs_spin); } int gfs2_statfs_sync(struct super_block *sb, int type) @@ -842,10 +851,6 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) gfs2_quota_sync(sdp->sd_vfs, 0); gfs2_statfs_sync(sdp->sd_vfs, 0); - down_write(&sdp->sd_log_flush_lock); - clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); - up_write(&sdp->sd_log_flush_lock); - gfs2_log_flush(sdp, NULL, SHUTDOWN_FLUSH); wait_event(sdp->sd_reserving_log_wait, atomic_read(&sdp->sd_reserving_log) == 0); gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks); @@ -1419,6 +1424,8 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root) seq_puts(s, ",demote_interface_used"); if (args->ar_rgrplvb) seq_puts(s, ",rgrplvb"); + if (args->ar_loccookie) + seq_puts(s, ",loccookie"); return 0; } @@ -1512,6 +1519,7 @@ static void gfs2_evict_inode(struct inode *inode) struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder gh; + struct address_space *metamapping; int error; if (test_bit(GIF_FREE_VFS_INODE, &ip->i_flags)) { @@ -1526,7 +1534,8 @@ static void gfs2_evict_inode(struct inode *inode) error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh); if (unlikely(error)) { ip->i_iopen_gh.gh_flags |= GL_NOCACHE; - gfs2_glock_dq_uninit(&ip->i_iopen_gh); + gfs2_glock_dq_wait(&ip->i_iopen_gh); + gfs2_holder_uninit(&ip->i_iopen_gh); goto out; } @@ -1575,8 +1584,8 @@ static void gfs2_evict_inode(struct inode *inode) out_truncate: gfs2_log_flush(sdp, ip->i_gl, NORMAL_FLUSH); + metamapping = gfs2_glock2aspace(ip->i_gl); if (test_bit(GLF_DIRTY, &ip->i_gl->gl_flags)) { - struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl); filemap_fdatawrite(metamapping); filemap_fdatawait(metamapping); } @@ -1589,16 +1598,17 @@ out_truncate: goto out_unlock; /* Needs to be done before glock release & also in a transaction */ truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages(metamapping, 0); gfs2_trans_end(sdp); out_unlock: /* Error path for case 1 */ - if (gfs2_rs_active(ip->i_res)) - gfs2_rs_deltree(ip->i_res); + if (gfs2_rs_active(&ip->i_res)) + gfs2_rs_deltree(&ip->i_res); if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) { ip->i_iopen_gh.gh_flags |= GL_NOCACHE; - gfs2_glock_dq(&ip->i_iopen_gh); + gfs2_glock_dq_wait(&ip->i_iopen_gh); } gfs2_holder_uninit(&ip->i_iopen_gh); gfs2_glock_dq_uninit(&gh); @@ -1607,7 +1617,7 @@ out_unlock: out: /* Case 3 starts here */ truncate_inode_pages_final(&inode->i_data); - gfs2_rs_delete(ip, NULL); + gfs2_rsqa_delete(ip, NULL); gfs2_ordered_del_inode(ip); clear_inode(inode); gfs2_dir_hash_inval(ip); @@ -1619,7 +1629,8 @@ out: if (ip->i_iopen_gh.gh_gl) { ip->i_iopen_gh.gh_gl->gl_object = NULL; ip->i_iopen_gh.gh_flags |= GL_NOCACHE; - gfs2_glock_dq_uninit(&ip->i_iopen_gh); + gfs2_glock_dq_wait(&ip->i_iopen_gh); + gfs2_holder_uninit(&ip->i_iopen_gh); } } @@ -1632,7 +1643,9 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb) ip->i_flags = 0; ip->i_gl = NULL; ip->i_rgd = NULL; - ip->i_res = NULL; + memset(&ip->i_res, 0, sizeof(ip->i_res)); + RB_CLEAR_NODE(&ip->i_res.rs_node); + ip->i_rahead = 0; } return &ip->i_inode; } diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index b95d0d625f32..0c1bde395062 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -176,6 +176,8 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh) unlock_buffer(bh); if (bh->b_private == NULL) bd = gfs2_alloc_bufdata(gl, bh, &gfs2_databuf_lops); + else + bd = bh->b_private; lock_buffer(bh); gfs2_log_lock(sdp); } @@ -236,6 +238,8 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) lock_page(bh->b_page); if (bh->b_private == NULL) bd = gfs2_alloc_bufdata(gl, bh, &gfs2_buf_lops); + else + bd = bh->b_private; unlock_page(bh->b_page); lock_buffer(bh); gfs2_log_lock(sdp); diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 86d2035ac669..cf645835710f 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -27,7 +27,7 @@ struct kmem_cache *gfs2_inode_cachep __read_mostly; struct kmem_cache *gfs2_bufdata_cachep __read_mostly; struct kmem_cache *gfs2_rgrpd_cachep __read_mostly; struct kmem_cache *gfs2_quotad_cachep __read_mostly; -struct kmem_cache *gfs2_rsrv_cachep __read_mostly; +struct kmem_cache *gfs2_qadata_cachep __read_mostly; mempool_t *gfs2_page_pool __read_mostly; void gfs2_assert_i(struct gfs2_sbd *sdp) diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h index cbdcbdf39614..c81295f407f6 100644 --- a/fs/gfs2/util.h +++ b/fs/gfs2/util.h @@ -149,7 +149,7 @@ extern struct kmem_cache *gfs2_inode_cachep; extern struct kmem_cache *gfs2_bufdata_cachep; extern struct kmem_cache *gfs2_rgrpd_cachep; extern struct kmem_cache *gfs2_quotad_cachep; -extern struct kmem_cache *gfs2_rsrv_cachep; +extern struct kmem_cache *gfs2_qadata_cachep; extern mempool_t *gfs2_page_pool; static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt, diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 4c096fa9e2a1..e8dfb4740c04 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -119,7 +119,7 @@ static int ea_foreach(struct gfs2_inode *ip, ea_call_t ea_call, void *data) __be64 *eablk, *end; int error; - error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, &bh); + error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0, &bh); if (error) return error; @@ -143,7 +143,7 @@ static int ea_foreach(struct gfs2_inode *ip, ea_call_t ea_call, void *data) break; bn = be64_to_cpu(*eablk); - error = gfs2_meta_read(ip->i_gl, bn, DIO_WAIT, &eabh); + error = gfs2_meta_read(ip->i_gl, bn, DIO_WAIT, 0, &eabh); if (error) break; error = ea_foreach_i(ip, eabh, ea_call, data); @@ -477,7 +477,7 @@ static int gfs2_iter_unstuffed(struct gfs2_inode *ip, struct gfs2_ea_header *ea, return -ENOMEM; for (x = 0; x < nptrs; x++) { - error = gfs2_meta_read(ip->i_gl, be64_to_cpu(*dataptrs), 0, + error = gfs2_meta_read(ip->i_gl, be64_to_cpu(*dataptrs), 0, 0, bh + x); if (error) { while (x--) @@ -583,11 +583,13 @@ out: * * Returns: actual size of data on success, -errno on error */ -static int gfs2_xattr_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int gfs2_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { struct gfs2_inode *ip = GFS2_I(d_inode(dentry)); struct gfs2_ea_location el; + int type = handler->flags; int error; if (!ip->i_eattr) @@ -977,7 +979,7 @@ static int ea_set_block(struct gfs2_inode *ip, struct gfs2_ea_request *er, if (ip->i_diskflags & GFS2_DIF_EA_INDIRECT) { __be64 *end; - error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, + error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0, &indbh); if (error) return error; @@ -1227,61 +1229,12 @@ int __gfs2_xattr_set(struct inode *inode, const char *name, return error; } -static int gfs2_xattr_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +static int gfs2_xattr_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { return __gfs2_xattr_set(d_inode(dentry), name, value, - size, flags, type); -} - - -static int ea_acl_chmod_unstuffed(struct gfs2_inode *ip, - struct gfs2_ea_header *ea, char *data) -{ - struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - unsigned int amount = GFS2_EA_DATA_LEN(ea); - unsigned int nptrs = DIV_ROUND_UP(amount, sdp->sd_jbsize); - int ret; - - ret = gfs2_trans_begin(sdp, nptrs + RES_DINODE, 0); - if (ret) - return ret; - - ret = gfs2_iter_unstuffed(ip, ea, data, NULL); - gfs2_trans_end(sdp); - - return ret; -} - -int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data) -{ - struct inode *inode = &ip->i_inode; - struct gfs2_sbd *sdp = GFS2_SB(inode); - struct gfs2_ea_location el; - int error; - - error = gfs2_ea_find(ip, GFS2_EATYPE_SYS, GFS2_POSIX_ACL_ACCESS, &el); - if (error) - return error; - - if (GFS2_EA_IS_STUFFED(el.el_ea)) { - error = gfs2_trans_begin(sdp, RES_DINODE + RES_EATTR, 0); - if (error == 0) { - gfs2_trans_add_meta(ip->i_gl, el.el_bh); - memcpy(GFS2_EA2DATA(el.el_ea), data, - GFS2_EA_DATA_LEN(el.el_ea)); - } - } else { - error = ea_acl_chmod_unstuffed(ip, el.el_ea, data); - } - - brelse(el.el_bh); - if (error) - return error; - - error = gfs2_setattr_simple(inode, attr); - gfs2_trans_end(sdp); - return error; + size, flags, handler->flags); } static int ea_dealloc_indirect(struct gfs2_inode *ip) @@ -1303,7 +1256,7 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip) memset(&rlist, 0, sizeof(struct gfs2_rgrp_list)); - error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, &indbh); + error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0, &indbh); if (error) return error; diff --git a/fs/gfs2/xattr.h b/fs/gfs2/xattr.h index d392f8358f2f..2d887c88eb49 100644 --- a/fs/gfs2/xattr.h +++ b/fs/gfs2/xattr.h @@ -62,6 +62,5 @@ extern int gfs2_ea_dealloc(struct gfs2_inode *ip); /* Exported to acl.c */ extern int gfs2_xattr_acl_get(struct gfs2_inode *ip, const char *name, char **data); -extern int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data); #endif /* __EATTR_DOT_H__ */ diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index aa3f0d6d043c..a3ec3ae7d347 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -166,7 +166,7 @@ int hfs_mdb_get(struct super_block *sb) pr_warn("continuing without an alternate MDB\n"); } - HFS_SB(sb)->bitmap = (__be32 *)__get_free_pages(GFP_KERNEL, PAGE_SIZE < 8192 ? 1 : 0); + HFS_SB(sb)->bitmap = kmalloc(8192, GFP_KERNEL); if (!HFS_SB(sb)->bitmap) goto out; @@ -360,7 +360,7 @@ void hfs_mdb_put(struct super_block *sb) unload_nls(HFS_SB(sb)->nls_io); unload_nls(HFS_SB(sb)->nls_disk); - free_pages((unsigned long)HFS_SB(sb)->bitmap, PAGE_SIZE < 8192 ? 1 : 0); + kfree(HFS_SB(sb)->bitmap); kfree(HFS_SB(sb)); sb->s_fs_info = NULL; } diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 6dd107d7421e..19b33f8151f1 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -403,6 +403,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode) } else if (S_ISLNK(inode->i_mode)) { sbi->file_count++; inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &hfsplus_aops; hip->clump_blocks = 1; } else @@ -526,6 +527,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) inode->i_mapping->a_ops = &hfsplus_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &hfsplus_aops; } else { init_special_inode(inode, inode->i_mode, diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c index df0c9af68d05..afb33eda6d7d 100644 --- a/fs/hfsplus/posix_acl.c +++ b/fs/hfsplus/posix_acl.c @@ -21,10 +21,10 @@ struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type) switch (type) { case ACL_TYPE_ACCESS: - xattr_name = POSIX_ACL_XATTR_ACCESS; + xattr_name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - xattr_name = POSIX_ACL_XATTR_DEFAULT; + xattr_name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: return ERR_PTR(-EINVAL); @@ -66,7 +66,7 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, switch (type) { case ACL_TYPE_ACCESS: - xattr_name = POSIX_ACL_XATTR_ACCESS; + xattr_name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { err = posix_acl_equiv_mode(acl, &inode->i_mode); if (err < 0) @@ -76,7 +76,7 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, break; case ACL_TYPE_DEFAULT: - xattr_name = POSIX_ACL_XATTR_DEFAULT; + xattr_name = XATTR_NAME_POSIX_ACL_DEFAULT; if (!S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; break; diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index 416b1dbafe51..ab01530b4930 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -431,9 +431,6 @@ int hfsplus_setxattr(struct dentry *dentry, const char *name, char *xattr_name; int res; - if (!strcmp(name, "")) - return -EINVAL; - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, GFP_KERNEL); if (!xattr_name) @@ -589,9 +586,6 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, int res; char *xattr_name; - if (!strcmp(name, "")) - return -EINVAL; - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, GFP_KERNEL); if (!xattr_name) @@ -849,12 +843,10 @@ end_removexattr: return err; } -static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int hfsplus_osx_getxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - if (!strcmp(name, "")) - return -EINVAL; - /* * Don't allow retrieving properly prefixed attributes * by prepending them with "osx." @@ -871,12 +863,10 @@ static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name, return __hfsplus_getxattr(d_inode(dentry), name, buffer, size); } -static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name, - const void *buffer, size_t size, int flags, int type) +static int hfsplus_osx_setxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags) { - if (!strcmp(name, "")) - return -EINVAL; - /* * Don't allow setting properly prefixed attributes * by prepending them with "osx." @@ -893,19 +883,8 @@ static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name, return __hfsplus_setxattr(d_inode(dentry), name, buffer, size, flags); } -static size_t hfsplus_osx_listxattr(struct dentry *dentry, char *list, - size_t list_size, const char *name, size_t name_len, int type) -{ - /* - * This method is not used. - * It is used hfsplus_listxattr() instead of generic_listxattr(). - */ - return -EOPNOTSUPP; -} - const struct xattr_handler hfsplus_xattr_osx_handler = { .prefix = XATTR_MAC_OSX_PREFIX, - .list = hfsplus_osx_listxattr, .get = hfsplus_osx_getxattr, .set = hfsplus_osx_setxattr, }; diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c index aacff00a9ff9..72a68a3a0c99 100644 --- a/fs/hfsplus/xattr_security.c +++ b/fs/hfsplus/xattr_security.c @@ -13,32 +13,24 @@ #include "xattr.h" #include "acl.h" -static int hfsplus_security_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int hfsplus_security_getxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { return hfsplus_getxattr(dentry, name, buffer, size, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); } -static int hfsplus_security_setxattr(struct dentry *dentry, const char *name, - const void *buffer, size_t size, int flags, int type) +static int hfsplus_security_setxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags) { return hfsplus_setxattr(dentry, name, buffer, size, flags, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); } -static size_t hfsplus_security_listxattr(struct dentry *dentry, char *list, - size_t list_size, const char *name, size_t name_len, int type) -{ - /* - * This method is not used. - * It is used hfsplus_listxattr() instead of generic_listxattr(). - */ - return -EOPNOTSUPP; -} - static int hfsplus_initxattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) @@ -92,7 +84,6 @@ int hfsplus_init_inode_security(struct inode *inode, const struct xattr_handler hfsplus_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = hfsplus_security_listxattr, .get = hfsplus_security_getxattr, .set = hfsplus_security_setxattr, }; diff --git a/fs/hfsplus/xattr_trusted.c b/fs/hfsplus/xattr_trusted.c index bcf65089b7f7..95a7704c7abb 100644 --- a/fs/hfsplus/xattr_trusted.c +++ b/fs/hfsplus/xattr_trusted.c @@ -11,34 +11,25 @@ #include "hfsplus_fs.h" #include "xattr.h" -static int hfsplus_trusted_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int hfsplus_trusted_getxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { return hfsplus_getxattr(dentry, name, buffer, size, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } -static int hfsplus_trusted_setxattr(struct dentry *dentry, const char *name, - const void *buffer, size_t size, int flags, int type) +static int hfsplus_trusted_setxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags) { return hfsplus_setxattr(dentry, name, buffer, size, flags, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } -static size_t hfsplus_trusted_listxattr(struct dentry *dentry, char *list, - size_t list_size, const char *name, size_t name_len, int type) -{ - /* - * This method is not used. - * It is used hfsplus_listxattr() instead of generic_listxattr(). - */ - return -EOPNOTSUPP; -} - const struct xattr_handler hfsplus_xattr_trusted_handler = { .prefix = XATTR_TRUSTED_PREFIX, - .list = hfsplus_trusted_listxattr, .get = hfsplus_trusted_getxattr, .set = hfsplus_trusted_setxattr, }; diff --git a/fs/hfsplus/xattr_user.c b/fs/hfsplus/xattr_user.c index 5aa0e6dc4a1e..6fc269baf959 100644 --- a/fs/hfsplus/xattr_user.c +++ b/fs/hfsplus/xattr_user.c @@ -11,34 +11,25 @@ #include "hfsplus_fs.h" #include "xattr.h" -static int hfsplus_user_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int hfsplus_user_getxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { return hfsplus_getxattr(dentry, name, buffer, size, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN); } -static int hfsplus_user_setxattr(struct dentry *dentry, const char *name, - const void *buffer, size_t size, int flags, int type) +static int hfsplus_user_setxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags) { return hfsplus_setxattr(dentry, name, buffer, size, flags, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN); } -static size_t hfsplus_user_listxattr(struct dentry *dentry, char *list, - size_t list_size, const char *name, size_t name_len, int type) -{ - /* - * This method is not used. - * It is used hfsplus_listxattr() instead of generic_listxattr(). - */ - return -EOPNOTSUPP; -} - const struct xattr_handler hfsplus_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, - .list = hfsplus_user_listxattr, .get = hfsplus_user_getxattr, .set = hfsplus_user_setxattr, }; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 2ac99db3750e..f49be23e78aa 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -730,15 +730,13 @@ static int hostfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, init_special_inode(inode, mode, dev); err = do_mknod(name, mode, MAJOR(dev), MINOR(dev)); - if (!err) + if (err) goto out_free; err = read_name(inode, name); __putname(name); if (err) goto out_put; - if (err) - goto out_put; d_instantiate(dentry, inode); return 0; @@ -892,9 +890,14 @@ static const struct inode_operations hostfs_dir_iops = { .setattr = hostfs_setattr, }; -static const char *hostfs_follow_link(struct dentry *dentry, void **cookie) +static const char *hostfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - char *link = __getname(); + char *link; + if (!dentry) + return ERR_PTR(-ECHILD); + link = kmalloc(PATH_MAX, GFP_KERNEL); if (link) { char *path = dentry_name(dentry); int err = -ENOMEM; @@ -905,25 +908,20 @@ static const char *hostfs_follow_link(struct dentry *dentry, void **cookie) __putname(path); } if (err < 0) { - __putname(link); + kfree(link); return ERR_PTR(err); } } else { return ERR_PTR(-ENOMEM); } - return *cookie = link; -} - -static void hostfs_put_link(struct inode *unused, void *cookie) -{ - __putname(cookie); + set_delayed_call(done, kfree_link, link); + return link; } static const struct inode_operations hostfs_link_iops = { .readlink = generic_readlink, - .follow_link = hostfs_follow_link, - .put_link = hostfs_put_link, + .get_link = hostfs_get_link, }; static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent) diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 933c73780813..1f3c6d76200b 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -77,6 +77,7 @@ void hpfs_read_inode(struct inode *i) kfree(ea); i->i_mode = S_IFLNK | 0777; i->i_op = &page_symlink_inode_operations; + inode_nohighmem(i); i->i_data.a_ops = &hpfs_symlink_aops; set_nlink(i, 1); i->i_size = ea_size; diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c index a69bbc1e87f8..a136929189f0 100644 --- a/fs/hpfs/map.c +++ b/fs/hpfs/map.c @@ -133,7 +133,7 @@ __le32 *hpfs_load_bitmap_directory(struct super_block *s, secno bmp) void hpfs_load_hotfix_map(struct super_block *s, struct hpfs_spare_block *spareblock) { struct quad_buffer_head qbh; - u32 *directory; + __le32 *directory; u32 n_hotfixes, n_used_hotfixes; unsigned i; diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 9e92c9c2d319..506765afa1a3 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -227,8 +227,6 @@ static int hpfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, de int err; if ((err = hpfs_chk_name(name, &len))) return err==-ENOENT ? -EINVAL : err; if (hpfs_sb(dir->i_sb)->sb_eas < 2) return -EPERM; - if (!new_valid_dev(rdev)) - return -EINVAL; hpfs_lock(dir->i_sb); err = -ENOSPC; fnode = hpfs_alloc_fnode(dir->i_sb, hpfs_i(dir)->i_dno, &fno, &bh); @@ -334,6 +332,7 @@ static int hpfs_symlink(struct inode *dir, struct dentry *dentry, const char *sy result->i_blocks = 1; set_nlink(result, 1); result->i_size = strlen(symlink); + inode_nohighmem(result); result->i_op = &page_symlink_inode_operations; result->i_data.a_ops = &hpfs_symlink_aops; @@ -502,7 +501,7 @@ out: static int hpfs_symlink_readpage(struct file *file, struct page *page) { - char *link = kmap(page); + char *link = page_address(page); struct inode *i = page->mapping->host; struct fnode *fnode; struct buffer_head *bh; @@ -518,14 +517,12 @@ static int hpfs_symlink_readpage(struct file *file, struct page *page) goto fail; hpfs_unlock(i->i_sb); SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; fail: hpfs_unlock(i->i_sb); SetPageError(page); - kunmap(page); unlock_page(page); return err; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 316adb968b65..d8f51ee8126b 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -332,12 +332,17 @@ static void remove_huge_page(struct page *page) * truncation is indicated by end of range being LLONG_MAX * In this case, we first scan the range and release found pages. * After releasing pages, hugetlb_unreserve_pages cleans up region/reserv - * maps and global counts. + * maps and global counts. Page faults can not race with truncation + * in this routine. hugetlb_no_page() prevents page faults in the + * truncated range. It checks i_size before allocation, and again after + * with the page table lock for the page held. The same lock must be + * acquired to unmap a page. * hole punch is indicated if end is not LLONG_MAX * In the hole punch case we scan the range and release found pages. * Only when releasing a page is the associated region/reserv map * deleted. The region/reserv map for ranges without associated - * pages are not modified. + * pages are not modified. Page faults can race with hole punch. + * This is indicated if we find a mapped page. * Note: If the passed end of range value is beyond the end of file, but * not LLONG_MAX this routine still performs a hole punch operation. */ @@ -361,46 +366,37 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, next = start; while (next < end) { /* - * Make sure to never grab more pages that we - * might possibly need. + * Don't grab more pages than the number left in the range. */ if (end - next < lookup_nr) lookup_nr = end - next; /* - * This pagevec_lookup() may return pages past 'end', - * so we must check for page->index > end. + * When no more pages are found, we are done. */ - if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) { - if (next == start) - break; - next = start; - continue; - } + if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) + break; for (i = 0; i < pagevec_count(&pvec); ++i) { struct page *page = pvec.pages[i]; u32 hash; + /* + * The page (index) could be beyond end. This is + * only possible in the punch hole case as end is + * max page offset in the truncate case. + */ + next = page->index; + if (next >= end) + break; + hash = hugetlb_fault_mutex_hash(h, current->mm, &pseudo_vma, mapping, next, 0); mutex_lock(&hugetlb_fault_mutex_table[hash]); lock_page(page); - if (page->index >= end) { - unlock_page(page); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); - next = end; /* we are done */ - break; - } - - /* - * If page is mapped, it was faulted in after being - * unmapped. Do nothing in this race case. In the - * normal case page is not mapped. - */ - if (!page_mapped(page)) { + if (likely(!page_mapped(page))) { bool rsv_on_error = !PagePrivate(page); /* * We must free the huge page and remove @@ -421,17 +417,23 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, hugetlb_fix_reserve_counts( inode, rsv_on_error); } + } else { + /* + * If page is mapped, it was faulted in after + * being unmapped. It indicates a race between + * hole punch and page fault. Do nothing in + * this case. Getting here in a truncate + * operation is a bug. + */ + BUG_ON(truncate_op); } - if (page->index > next) - next = page->index; - - ++next; unlock_page(page); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); } + ++next; huge_pagevec_release(&pvec); + cond_resched(); } if (truncate_op) @@ -647,9 +649,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); inode->i_ctime = CURRENT_TIME; - spin_lock(&inode->i_lock); - inode->i_private = NULL; - spin_unlock(&inode->i_lock); out: mutex_unlock(&inode->i_mutex); return error; @@ -761,6 +760,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); break; } lockdep_annotate_inode_mutex_key(inode); diff --git a/fs/inode.c b/fs/inode.c index 78a17b8859e1..4230f66b7410 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -225,7 +225,7 @@ void __destroy_inode(struct inode *inode) inode_detach_wb(inode); security_inode_free(inode); fsnotify_inode_delete(inode); - locks_free_lock_context(inode->i_flctx); + locks_free_lock_context(inode); if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count); @@ -1597,6 +1597,7 @@ static int update_time(struct inode *inode, struct timespec *time, int flags) /** * touch_atime - update the access time * @path: the &struct path to update + * @inode: inode to update * * Update the accessed time on an inode and mark it for writeback. * This function automatically handles read only file systems and media, @@ -2027,3 +2028,9 @@ void inode_set_flags(struct inode *inode, unsigned int flags, new_flags) != old_flags)); } EXPORT_SYMBOL(inode_set_flags); + +void inode_nohighmem(struct inode *inode) +{ + mapping_set_gfp_mask(inode->i_mapping, GFP_USER); +} +EXPORT_SYMBOL(inode_nohighmem); diff --git a/fs/internal.h b/fs/internal.h index 71859c4d0b41..b71deeecea17 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -55,7 +55,7 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *, /* * namespace.c */ -extern int copy_mount_options(const void __user *, unsigned long *); +extern void *copy_mount_options(const void __user *); extern char *copy_mount_string(const void __user *); extern struct vfsmount *lookup_mnt(struct path *); @@ -151,3 +151,10 @@ extern void mnt_pin_kill(struct mount *m); * fs/nsfs.c */ extern struct dentry_operations ns_dentry_operations; + +/* + * fs/ioctl.c + */ +extern int do_vfs_ioctl(struct file *file, unsigned int fd, unsigned int cmd, + unsigned long arg); +extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); diff --git a/fs/ioctl.c b/fs/ioctl.c index 5d01d2638ca5..29466c380958 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -15,6 +15,7 @@ #include <linux/writeback.h> #include <linux/buffer_head.h> #include <linux/falloc.h> +#include "internal.h" #include <asm/ioctls.h> @@ -32,8 +33,7 @@ * * Returns 0 on success, -errno on error. */ -static long vfs_ioctl(struct file *filp, unsigned int cmd, - unsigned long arg) +long vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int error = -ENOTTY; @@ -215,6 +215,29 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg) return error; } +static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, + u64 off, u64 olen, u64 destoff) +{ + struct fd src_file = fdget(srcfd); + int ret; + + if (!src_file.file) + return -EBADF; + ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen); + fdput(src_file); + return ret; +} + +static long ioctl_file_clone_range(struct file *file, void __user *argp) +{ + struct file_clone_range args; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + return ioctl_file_clone(file, args.src_fd, args.src_offset, + args.src_length, args.dest_offset); +} + #ifdef CONFIG_BLOCK static inline sector_t logical_to_blk(struct inode *inode, loff_t offset) @@ -545,6 +568,41 @@ static int ioctl_fsthaw(struct file *filp) return thaw_super(sb); } +static long ioctl_file_dedupe_range(struct file *file, void __user *arg) +{ + struct file_dedupe_range __user *argp = arg; + struct file_dedupe_range *same = NULL; + int ret; + unsigned long size; + u16 count; + + if (get_user(count, &argp->dest_count)) { + ret = -EFAULT; + goto out; + } + + size = offsetof(struct file_dedupe_range __user, info[count]); + + same = memdup_user(argp, size); + if (IS_ERR(same)) { + ret = PTR_ERR(same); + same = NULL; + goto out; + } + + ret = vfs_dedupe_file_range(file, same); + if (ret) + goto out; + + ret = copy_to_user(argp, same, size); + if (ret) + ret = -EFAULT; + +out: + kfree(same); + return ret; +} + /* * When you add any new common ioctls to the switches above and below * please update compat_sys_ioctl() too. @@ -600,6 +658,15 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, case FIGETBSZ: return put_user(inode->i_sb->s_blocksize, argp); + case FICLONE: + return ioctl_file_clone(filp, arg, 0, 0, 0); + + case FICLONERANGE: + return ioctl_file_clone_range(filp, argp); + + case FIDEDUPERANGE: + return ioctl_file_dedupe_range(filp, argp); + default: if (S_ISREG(inode->i_mode)) error = file_ioctl(filp, cmd, arg); diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index d67a16f2a45d..61abdc4920da 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1417,6 +1417,7 @@ static int isofs_read_inode(struct inode *inode, int relocated) inode->i_fop = &isofs_dir_operations; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &isofs_symlink_aops; } else /* XXX - parse_rock_ridge_inode() had already set i_rdev. */ diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index 735d7522a3a9..5384ceb35b1c 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -687,7 +687,7 @@ static int rock_ridge_symlink_readpage(struct file *file, struct page *page) struct inode *inode = page->mapping->host; struct iso_inode_info *ei = ISOFS_I(inode); struct isofs_sb_info *sbi = ISOFS_SB(inode->i_sb); - char *link = kmap(page); + char *link = page_address(page); unsigned long bufsize = ISOFS_BUFFER_SIZE(inode); struct buffer_head *bh; char *rpnt = link; @@ -774,7 +774,6 @@ repeat: brelse(bh); *rpnt = '\0'; SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; @@ -791,7 +790,6 @@ fail: brelse(bh); error: SetPageError(page); - kunmap(page); unlock_page(page); return -EIO; } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 6b8338ec2464..081dff087fc0 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -764,13 +764,11 @@ void jbd2_journal_unlock_updates (journal_t *journal) static void warn_dirty_buffer(struct buffer_head *bh) { - char b[BDEVNAME_SIZE]; - printk(KERN_WARNING - "JBD2: Spotted dirty metadata buffer (dev = %s, blocknr = %llu). " + "JBD2: Spotted dirty metadata buffer (dev = %pg, blocknr = %llu). " "There's a risk of filesystem corruption in case of system " "crash.\n", - bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr); + bh->b_bdev, (unsigned long long)bh->b_blocknr); } /* Call t_frozen trigger and copy buffer data into jh->b_frozen_data. */ @@ -1009,7 +1007,8 @@ out: } /* Fast check whether buffer is already attached to the required transaction */ -static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh) +static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh, + bool undo) { struct journal_head *jh; bool ret = false; @@ -1036,6 +1035,9 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh) jh = READ_ONCE(bh->b_private); if (!jh) goto out; + /* For undo access buffer must have data copied */ + if (undo && !jh->b_committed_data) + goto out; if (jh->b_transaction != handle->h_transaction && jh->b_next_transaction != handle->h_transaction) goto out; @@ -1073,7 +1075,7 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) struct journal_head *jh; int rc; - if (jbd2_write_access_granted(handle, bh)) + if (jbd2_write_access_granted(handle, bh, false)) return 0; jh = jbd2_journal_add_journal_head(bh); @@ -1210,7 +1212,7 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh) char *committed_data = NULL; JBUFFER_TRACE(jh, "entry"); - if (jbd2_write_access_granted(handle, bh)) + if (jbd2_write_access_granted(handle, bh, true)) return 0; jh = jbd2_journal_add_journal_head(bh); @@ -1937,8 +1939,8 @@ out: * @journal: journal for operation * @page: to try and free * @gfp_mask: we use the mask to detect how hard should we try to release - * buffers. If __GFP_WAIT and __GFP_FS is set, we wait for commit code to - * release the buffers. + * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit + * code to release the buffers. * * * For all the buffers on this page, @@ -2152,6 +2154,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, if (!buffer_dirty(bh)) { /* bdflush has written it. We can drop it now */ + __jbd2_journal_remove_checkpoint(jh); goto zap_buffer; } @@ -2181,6 +2184,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, /* The orphan record's transaction has * committed. We can cleanse this buffer */ clear_buffer_jbddirty(bh); + __jbd2_journal_remove_checkpoint(jh); goto zap_buffer; } } diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index bb9cebc9ca8a..e5c1783ab64a 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -80,7 +80,6 @@ static int jffs2_garbage_collect_thread(void *_c) siginitset(&hupmask, sigmask(SIGHUP)); allow_signal(SIGKILL); allow_signal(SIGSTOP); - allow_signal(SIGCONT); allow_signal(SIGHUP); c->gc_task = current; @@ -121,20 +120,18 @@ static int jffs2_garbage_collect_thread(void *_c) /* Put_super will send a SIGKILL and then wait on the sem. */ while (signal_pending(current) || freezing(current)) { - siginfo_t info; unsigned long signr; if (try_to_freeze()) goto again; - signr = dequeue_signal_lock(current, ¤t->blocked, &info); + signr = kernel_dequeue_signal(NULL); switch(signr) { case SIGSTOP: jffs2_dbg(1, "%s(): SIGSTOP received\n", __func__); - set_current_state(TASK_STOPPED); - schedule(); + kernel_signal_stop(); break; case SIGKILL: diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c index d4b43fb7adb1..7a28facd7175 100644 --- a/fs/jffs2/security.c +++ b/fs/jffs2/security.c @@ -48,42 +48,24 @@ int jffs2_init_security(struct inode *inode, struct inode *dir, } /* ---- XATTR Handler for "security.*" ----------------- */ -static int jffs2_security_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int jffs2_security_getxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - if (!strcmp(name, "")) - return -EINVAL; - return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_SECURITY, name, buffer, size); } -static int jffs2_security_setxattr(struct dentry *dentry, const char *name, - const void *buffer, size_t size, int flags, int type) +static int jffs2_security_setxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags) { - if (!strcmp(name, "")) - return -EINVAL; - return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_SECURITY, name, buffer, size, flags); } -static size_t jffs2_security_listxattr(struct dentry *dentry, char *list, - size_t list_size, const char *name, size_t name_len, int type) -{ - size_t retlen = XATTR_SECURITY_PREFIX_LEN + name_len + 1; - - if (list && retlen <= list_size) { - strcpy(list, XATTR_SECURITY_PREFIX); - strcpy(list + XATTR_SECURITY_PREFIX_LEN, name); - } - - return retlen; -} - const struct xattr_handler jffs2_security_xattr_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = jffs2_security_listxattr, .set = jffs2_security_setxattr, .get = jffs2_security_getxattr }; diff --git a/fs/jffs2/symlink.c b/fs/jffs2/symlink.c index 8ce2f240125b..2cabd649d4fb 100644 --- a/fs/jffs2/symlink.c +++ b/fs/jffs2/symlink.c @@ -14,7 +14,7 @@ const struct inode_operations jffs2_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = jffs2_setattr, .setxattr = jffs2_setxattr, .getxattr = jffs2_getxattr, diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c index 63f31c0733c5..5a3da3f52908 100644 --- a/fs/jffs2/wbuf.c +++ b/fs/jffs2/wbuf.c @@ -1153,7 +1153,7 @@ static struct jffs2_sb_info *work_to_sb(struct work_struct *work) { struct delayed_work *dwork; - dwork = container_of(work, struct delayed_work, work); + dwork = to_delayed_work(work); return container_of(dwork, struct jffs2_sb_info, wbuf_dwork); } @@ -1264,7 +1264,7 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) { if ((c->flash_size % c->sector_size) != 0) { c->flash_size = (c->flash_size / c->sector_size) * c->sector_size; pr_warn("flash size adjusted to %dKiB\n", c->flash_size); - }; + } c->wbuf_ofs = 0xFFFFFFFF; c->wbuf = kmalloc(c->wbuf_pagesize, GFP_KERNEL); diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index f092fee5be50..da3e18503c65 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -967,7 +967,8 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size) struct jffs2_xattr_ref *ref, **pref; struct jffs2_xattr_datum *xd; const struct xattr_handler *xhandle; - ssize_t len, rc; + const char *prefix; + ssize_t prefix_len, len, rc; int retry = 0; rc = check_xattr_ref_inode(c, ic); @@ -998,17 +999,23 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size) } } xhandle = xprefix_to_handler(xd->xprefix); - if (!xhandle) + if (!xhandle || (xhandle->list && !xhandle->list(dentry))) continue; + prefix = xhandle->prefix ?: xhandle->name; + prefix_len = strlen(prefix); + rc = prefix_len + xd->name_len + 1; + if (buffer) { - rc = xhandle->list(dentry, buffer+len, size-len, - xd->xname, xd->name_len, xd->flags); - } else { - rc = xhandle->list(dentry, NULL, 0, xd->xname, - xd->name_len, xd->flags); + if (rc > size - len) { + rc = -ERANGE; + goto out; + } + memcpy(buffer, prefix, prefix_len); + buffer += prefix_len; + memcpy(buffer, xd->xname, xd->name_len); + buffer += xd->name_len; + *buffer++ = 0; } - if (rc < 0) - goto out; len += rc; } rc = len; diff --git a/fs/jffs2/xattr_trusted.c b/fs/jffs2/xattr_trusted.c index ceaf9c693225..b2555ef07a12 100644 --- a/fs/jffs2/xattr_trusted.c +++ b/fs/jffs2/xattr_trusted.c @@ -16,35 +16,25 @@ #include <linux/mtd/mtd.h> #include "nodelist.h" -static int jffs2_trusted_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int jffs2_trusted_getxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - if (!strcmp(name, "")) - return -EINVAL; return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_TRUSTED, name, buffer, size); } -static int jffs2_trusted_setxattr(struct dentry *dentry, const char *name, - const void *buffer, size_t size, int flags, int type) +static int jffs2_trusted_setxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags) { - if (!strcmp(name, "")) - return -EINVAL; return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_TRUSTED, name, buffer, size, flags); } -static size_t jffs2_trusted_listxattr(struct dentry *dentry, char *list, - size_t list_size, const char *name, size_t name_len, int type) +static bool jffs2_trusted_listxattr(struct dentry *dentry) { - size_t retlen = XATTR_TRUSTED_PREFIX_LEN + name_len + 1; - - if (list && retlen<=list_size) { - strcpy(list, XATTR_TRUSTED_PREFIX); - strcpy(list + XATTR_TRUSTED_PREFIX_LEN, name); - } - - return retlen; + return capable(CAP_SYS_ADMIN); } const struct xattr_handler jffs2_trusted_xattr_handler = { diff --git a/fs/jffs2/xattr_user.c b/fs/jffs2/xattr_user.c index a71391eba514..539bd630b5e4 100644 --- a/fs/jffs2/xattr_user.c +++ b/fs/jffs2/xattr_user.c @@ -16,40 +16,24 @@ #include <linux/mtd/mtd.h> #include "nodelist.h" -static int jffs2_user_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int jffs2_user_getxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - if (!strcmp(name, "")) - return -EINVAL; return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_USER, name, buffer, size); } -static int jffs2_user_setxattr(struct dentry *dentry, const char *name, - const void *buffer, size_t size, int flags, int type) +static int jffs2_user_setxattr(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags) { - if (!strcmp(name, "")) - return -EINVAL; return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_USER, name, buffer, size, flags); } -static size_t jffs2_user_listxattr(struct dentry *dentry, char *list, - size_t list_size, const char *name, size_t name_len, int type) -{ - size_t retlen = XATTR_USER_PREFIX_LEN + name_len + 1; - - if (list && retlen <= list_size) { - strcpy(list, XATTR_USER_PREFIX); - strcpy(list + XATTR_USER_PREFIX_LEN, name); - } - - return retlen; -} - const struct xattr_handler jffs2_user_xattr_handler = { .prefix = XATTR_USER_PREFIX, - .list = jffs2_user_listxattr, .set = jffs2_user_setxattr, .get = jffs2_user_getxattr }; diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 0c8ca830b113..49456853e9de 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -40,10 +40,10 @@ struct posix_acl *jfs_get_acl(struct inode *inode, int type) switch(type) { case ACL_TYPE_ACCESS: - ea_name = POSIX_ACL_XATTR_ACCESS; + ea_name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - ea_name = POSIX_ACL_XATTR_DEFAULT; + ea_name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: return ERR_PTR(-EINVAL); @@ -82,7 +82,7 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type, switch (type) { case ACL_TYPE_ACCESS: - ea_name = POSIX_ACL_XATTR_ACCESS; + ea_name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { rc = posix_acl_equiv_mode(acl, &inode->i_mode); if (rc < 0) @@ -94,7 +94,7 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type, } break; case ACL_TYPE_DEFAULT: - ea_name = POSIX_ACL_XATTR_DEFAULT; + ea_name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: return -EINVAL; diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 41aa3ca6a6a4..9d9bae63ae2a 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -60,6 +60,7 @@ struct inode *jfs_iget(struct super_block *sb, unsigned long ino) } else if (S_ISLNK(inode->i_mode)) { if (inode->i_size >= IDATASIZE) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &jfs_aops; } else { inode->i_op = &jfs_fast_symlink_inode_operations; diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index a69bdf2a1085..a270cb7ff4e0 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1835,17 +1835,16 @@ static int lbmLogInit(struct jfs_log * log) for (i = 0; i < LOGPAGES;) { char *buffer; uint offset; - struct page *page; + struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO); - buffer = (char *) get_zeroed_page(GFP_KERNEL); - if (buffer == NULL) + if (!page) goto error; - page = virt_to_page(buffer); + buffer = page_address(page); for (offset = 0; offset < PAGE_SIZE; offset += LOGPSIZE) { lbuf = kmalloc(sizeof(struct lbuf), GFP_KERNEL); if (lbuf == NULL) { if (offset == 0) - free_page((unsigned long) buffer); + __free_page(page); goto error; } if (offset) /* we already have one reference */ diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 35976bdccafc..701f89370de7 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -983,6 +983,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry, jfs_info("jfs_symlink: allocate extent ip:0x%p", ip); ip->i_op = &jfs_symlink_inode_operations; + inode_nohighmem(ip); ip->i_mapping->a_ops = &jfs_aops; /* @@ -1372,9 +1373,6 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry, tid_t tid; struct tblock *tblk; - if (!new_valid_dev(rdev)) - return -EINVAL; - jfs_info("jfs_mknod: %pd", dentry); rc = dquot_initialize(dir); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 4cd9798f4948..8f9176caf098 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -496,9 +496,6 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) jfs_info("In jfs_read_super: s_flags=0x%lx", sb->s_flags); - if (!new_valid_dev(sb->s_bdev->bd_dev)) - return -EOVERFLOW; - sbi = kzalloc(sizeof(struct jfs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; diff --git a/fs/jfs/symlink.c b/fs/jfs/symlink.c index 5929e2363cb8..f8db4fde0b0b 100644 --- a/fs/jfs/symlink.c +++ b/fs/jfs/symlink.c @@ -23,7 +23,7 @@ const struct inode_operations jfs_fast_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = jfs_setattr, .setxattr = jfs_setxattr, .getxattr = jfs_getxattr, @@ -33,8 +33,7 @@ const struct inode_operations jfs_fast_symlink_inode_operations = { const struct inode_operations jfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = jfs_setattr, .setxattr = jfs_setxattr, .getxattr = jfs_getxattr, diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 91e004518237..742bf4a230e8 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -694,6 +694,29 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, return NULL; } +static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, + const unsigned char *path, + const void *ns) +{ + static char path_buf[PATH_MAX]; /* protected by kernfs_mutex */ + size_t len = strlcpy(path_buf, path, PATH_MAX); + char *p = path_buf; + char *name; + + lockdep_assert_held(&kernfs_mutex); + + if (len >= PATH_MAX) + return NULL; + + while ((name = strsep(&p, "/")) && parent) { + if (*name == '\0') + continue; + parent = kernfs_find_ns(parent, name, ns); + } + + return parent; +} + /** * kernfs_find_and_get_ns - find and get kernfs_node with the given name * @parent: kernfs_node to search under @@ -719,6 +742,29 @@ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns); /** + * kernfs_walk_and_get_ns - find and get kernfs_node with the given path + * @parent: kernfs_node to search under + * @path: path to look for + * @ns: the namespace tag to use + * + * Look for kernfs_node with path @path under @parent and get a reference + * if found. This function may sleep and returns pointer to the found + * kernfs_node on success, %NULL on failure. + */ +struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, + const char *path, const void *ns) +{ + struct kernfs_node *kn; + + mutex_lock(&kernfs_mutex); + kn = kernfs_walk_ns(parent, path, ns); + kernfs_get(kn); + mutex_unlock(&kernfs_mutex); + + return kn; +} + +/** * kernfs_create_root - create a new kernfs hierarchy * @scops: optional syscall operations for the hierarchy * @flags: KERNFS_ROOT_* flags diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 756dd56aaf60..16405ae88d2d 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -205,7 +205,7 @@ int kernfs_iop_removexattr(struct dentry *dentry, const char *name) if (!attrs) return -ENOMEM; - return simple_xattr_remove(&attrs->xattrs, name); + return simple_xattr_set(&attrs->xattrs, name, NULL, 0, XATTR_REPLACE); } ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf, @@ -230,7 +230,7 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size) if (!attrs) return -ENOMEM; - return simple_xattr_list(&attrs->xattrs, buf, size); + return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size); } static inline void set_default_inode_attr(struct inode *inode, umode_t mode) diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index db272528ab5b..117b8b3416f9 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -112,18 +112,25 @@ static int kernfs_getlink(struct dentry *dentry, char *path) return error; } -static const char *kernfs_iop_follow_link(struct dentry *dentry, void **cookie) +static const char *kernfs_iop_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - int error = -ENOMEM; - unsigned long page = get_zeroed_page(GFP_KERNEL); - if (!page) + char *body; + int error; + + if (!dentry) + return ERR_PTR(-ECHILD); + body = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!body) return ERR_PTR(-ENOMEM); - error = kernfs_getlink(dentry, (char *)page); + error = kernfs_getlink(dentry, body); if (unlikely(error < 0)) { - free_page((unsigned long)page); + kfree(body); return ERR_PTR(error); } - return *cookie = (char *)page; + set_delayed_call(done, kfree_link, body); + return body; } const struct inode_operations kernfs_symlink_iops = { @@ -132,8 +139,7 @@ const struct inode_operations kernfs_symlink_iops = { .getxattr = kernfs_iop_getxattr, .listxattr = kernfs_iop_listxattr, .readlink = generic_readlink, - .follow_link = kernfs_iop_follow_link, - .put_link = free_page_put_link, + .get_link = kernfs_iop_get_link, .setattr = kernfs_iop_setattr, .getattr = kernfs_iop_getattr, .permission = kernfs_iop_permission, diff --git a/fs/libfs.c b/fs/libfs.c index c7cbfb092e94..01491299f348 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1019,17 +1019,12 @@ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync) } EXPORT_SYMBOL(noop_fsync); -void kfree_put_link(struct inode *unused, void *cookie) +/* Because kfree isn't assignment-compatible with void(void*) ;-/ */ +void kfree_link(void *p) { - kfree(cookie); + kfree(p); } -EXPORT_SYMBOL(kfree_put_link); - -void free_page_put_link(struct inode *unused, void *cookie) -{ - free_page((unsigned long) cookie); -} -EXPORT_SYMBOL(free_page_put_link); +EXPORT_SYMBOL(kfree_link); /* * nop .set_page_dirty method so that people can use .page_mkwrite on @@ -1092,14 +1087,15 @@ simple_nosetlease(struct file *filp, long arg, struct file_lock **flp, } EXPORT_SYMBOL(simple_nosetlease); -const char *simple_follow_link(struct dentry *dentry, void **cookie) +const char *simple_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *done) { - return d_inode(dentry)->i_link; + return inode->i_link; } -EXPORT_SYMBOL(simple_follow_link); +EXPORT_SYMBOL(simple_get_link); const struct inode_operations simple_symlink_inode_operations = { - .follow_link = simple_follow_link, + .get_link = simple_get_link, .readlink = generic_readlink }; EXPORT_SYMBOL(simple_symlink_inode_operations); diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 969d589c848d..d716c9993a26 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -116,7 +116,7 @@ static struct nlm_host *nlm_alloc_host(struct nlm_lookup_host_info *ni, atomic_inc(&nsm->sm_count); else { host = NULL; - nsm = nsm_get_handle(ni->sap, ni->salen, + nsm = nsm_get_handle(ni->net, ni->sap, ni->salen, ni->hostname, ni->hostname_len); if (unlikely(nsm == NULL)) { dprintk("lockd: %s failed; no nsm handle\n", @@ -161,6 +161,7 @@ static struct nlm_host *nlm_alloc_host(struct nlm_lookup_host_info *ni, host->h_nsmhandle = nsm; host->h_addrbuf = nsm->sm_addrbuf; host->net = ni->net; + strlcpy(host->nodename, utsname()->nodename, sizeof(host->nodename)); out: return host; @@ -534,17 +535,18 @@ static struct nlm_host *next_host_state(struct hlist_head *cache, /** * nlm_host_rebooted - Release all resources held by rebooted host + * @net: network namespace * @info: pointer to decoded results of NLM_SM_NOTIFY call * * We were notified that the specified host has rebooted. Release * all resources held by that peer. */ -void nlm_host_rebooted(const struct nlm_reboot *info) +void nlm_host_rebooted(const struct net *net, const struct nlm_reboot *info) { struct nsm_handle *nsm; struct nlm_host *host; - nsm = nsm_reboot_lookup(info); + nsm = nsm_reboot_lookup(net, info); if (unlikely(nsm == NULL)) return; diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 47a32b6d9b90..19166d4a8d31 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -42,7 +42,7 @@ struct nsm_args { u32 proc; char *mon_name; - char *nodename; + const char *nodename; }; struct nsm_res { @@ -51,7 +51,6 @@ struct nsm_res { }; static const struct rpc_program nsm_program; -static LIST_HEAD(nsm_handles); static DEFINE_SPINLOCK(nsm_lock); /* @@ -87,69 +86,18 @@ static struct rpc_clnt *nsm_create(struct net *net, const char *nodename) return rpc_create(&args); } -static struct rpc_clnt *nsm_client_set(struct lockd_net *ln, - struct rpc_clnt *clnt) -{ - spin_lock(&ln->nsm_clnt_lock); - if (ln->nsm_users == 0) { - if (clnt == NULL) - goto out; - ln->nsm_clnt = clnt; - } - clnt = ln->nsm_clnt; - ln->nsm_users++; -out: - spin_unlock(&ln->nsm_clnt_lock); - return clnt; -} - -static struct rpc_clnt *nsm_client_get(struct net *net, const char *nodename) -{ - struct rpc_clnt *clnt, *new; - struct lockd_net *ln = net_generic(net, lockd_net_id); - - clnt = nsm_client_set(ln, NULL); - if (clnt != NULL) - goto out; - - clnt = new = nsm_create(net, nodename); - if (IS_ERR(clnt)) - goto out; - - clnt = nsm_client_set(ln, new); - if (clnt != new) - rpc_shutdown_client(new); -out: - return clnt; -} - -static void nsm_client_put(struct net *net) -{ - struct lockd_net *ln = net_generic(net, lockd_net_id); - struct rpc_clnt *clnt = NULL; - - spin_lock(&ln->nsm_clnt_lock); - ln->nsm_users--; - if (ln->nsm_users == 0) { - clnt = ln->nsm_clnt; - ln->nsm_clnt = NULL; - } - spin_unlock(&ln->nsm_clnt_lock); - if (clnt != NULL) - rpc_shutdown_client(clnt); -} - static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res, - struct rpc_clnt *clnt) + const struct nlm_host *host) { int status; + struct rpc_clnt *clnt; struct nsm_args args = { .priv = &nsm->sm_priv, .prog = NLM_PROGRAM, .vers = 3, .proc = NLMPROC_NSM_NOTIFY, .mon_name = nsm->sm_mon_name, - .nodename = clnt->cl_nodename, + .nodename = host->nodename, }; struct rpc_message msg = { .rpc_argp = &args, @@ -158,6 +106,13 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res, memset(res, 0, sizeof(*res)); + clnt = nsm_create(host->net, host->nodename); + if (IS_ERR(clnt)) { + dprintk("lockd: failed to create NSM upcall transport, " + "status=%ld, net=%p\n", PTR_ERR(clnt), host->net); + return PTR_ERR(clnt); + } + msg.rpc_proc = &clnt->cl_procinfo[proc]; status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN); if (status == -ECONNREFUSED) { @@ -171,6 +126,8 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res, status); else status = 0; + + rpc_shutdown_client(clnt); return status; } @@ -190,32 +147,19 @@ int nsm_monitor(const struct nlm_host *host) struct nsm_handle *nsm = host->h_nsmhandle; struct nsm_res res; int status; - struct rpc_clnt *clnt; - const char *nodename = NULL; dprintk("lockd: nsm_monitor(%s)\n", nsm->sm_name); if (nsm->sm_monitored) return 0; - if (host->h_rpcclnt) - nodename = host->h_rpcclnt->cl_nodename; - /* * Choose whether to record the caller_name or IP address of * this peer in the local rpc.statd's database. */ nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf; - clnt = nsm_client_get(host->net, nodename); - if (IS_ERR(clnt)) { - status = PTR_ERR(clnt); - dprintk("lockd: failed to create NSM upcall transport, " - "status=%d, net=%p\n", status, host->net); - return status; - } - - status = nsm_mon_unmon(nsm, NSMPROC_MON, &res, clnt); + status = nsm_mon_unmon(nsm, NSMPROC_MON, &res, host); if (unlikely(res.status != 0)) status = -EIO; if (unlikely(status < 0)) { @@ -247,11 +191,9 @@ void nsm_unmonitor(const struct nlm_host *host) if (atomic_read(&nsm->sm_count) == 1 && nsm->sm_monitored && !nsm->sm_sticky) { - struct lockd_net *ln = net_generic(host->net, lockd_net_id); - dprintk("lockd: nsm_unmonitor(%s)\n", nsm->sm_name); - status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res, ln->nsm_clnt); + status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res, host); if (res.status != 0) status = -EIO; if (status < 0) @@ -259,38 +201,38 @@ void nsm_unmonitor(const struct nlm_host *host) nsm->sm_name); else nsm->sm_monitored = 0; - - nsm_client_put(host->net); } } -static struct nsm_handle *nsm_lookup_hostname(const char *hostname, - const size_t len) +static struct nsm_handle *nsm_lookup_hostname(const struct list_head *nsm_handles, + const char *hostname, const size_t len) { struct nsm_handle *nsm; - list_for_each_entry(nsm, &nsm_handles, sm_link) + list_for_each_entry(nsm, nsm_handles, sm_link) if (strlen(nsm->sm_name) == len && memcmp(nsm->sm_name, hostname, len) == 0) return nsm; return NULL; } -static struct nsm_handle *nsm_lookup_addr(const struct sockaddr *sap) +static struct nsm_handle *nsm_lookup_addr(const struct list_head *nsm_handles, + const struct sockaddr *sap) { struct nsm_handle *nsm; - list_for_each_entry(nsm, &nsm_handles, sm_link) + list_for_each_entry(nsm, nsm_handles, sm_link) if (rpc_cmp_addr(nsm_addr(nsm), sap)) return nsm; return NULL; } -static struct nsm_handle *nsm_lookup_priv(const struct nsm_private *priv) +static struct nsm_handle *nsm_lookup_priv(const struct list_head *nsm_handles, + const struct nsm_private *priv) { struct nsm_handle *nsm; - list_for_each_entry(nsm, &nsm_handles, sm_link) + list_for_each_entry(nsm, nsm_handles, sm_link) if (memcmp(nsm->sm_priv.data, priv->data, sizeof(priv->data)) == 0) return nsm; @@ -353,6 +295,7 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap, /** * nsm_get_handle - Find or create a cached nsm_handle + * @net: network namespace * @sap: pointer to socket address of handle to find * @salen: length of socket address * @hostname: pointer to C string containing hostname to find @@ -365,11 +308,13 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap, * @hostname cannot be found in the handle cache. Returns NULL if * an error occurs. */ -struct nsm_handle *nsm_get_handle(const struct sockaddr *sap, +struct nsm_handle *nsm_get_handle(const struct net *net, + const struct sockaddr *sap, const size_t salen, const char *hostname, const size_t hostname_len) { struct nsm_handle *cached, *new = NULL; + struct lockd_net *ln = net_generic(net, lockd_net_id); if (hostname && memchr(hostname, '/', hostname_len) != NULL) { if (printk_ratelimit()) { @@ -384,9 +329,10 @@ retry: spin_lock(&nsm_lock); if (nsm_use_hostnames && hostname != NULL) - cached = nsm_lookup_hostname(hostname, hostname_len); + cached = nsm_lookup_hostname(&ln->nsm_handles, + hostname, hostname_len); else - cached = nsm_lookup_addr(sap); + cached = nsm_lookup_addr(&ln->nsm_handles, sap); if (cached != NULL) { atomic_inc(&cached->sm_count); @@ -400,7 +346,7 @@ retry: } if (new != NULL) { - list_add(&new->sm_link, &nsm_handles); + list_add(&new->sm_link, &ln->nsm_handles); spin_unlock(&nsm_lock); dprintk("lockd: created nsm_handle for %s (%s)\n", new->sm_name, new->sm_addrbuf); @@ -417,19 +363,22 @@ retry: /** * nsm_reboot_lookup - match NLMPROC_SM_NOTIFY arguments to an nsm_handle + * @net: network namespace * @info: pointer to NLMPROC_SM_NOTIFY arguments * * Returns a matching nsm_handle if found in the nsm cache. The returned * nsm_handle's reference count is bumped. Otherwise returns NULL if some * error occurred. */ -struct nsm_handle *nsm_reboot_lookup(const struct nlm_reboot *info) +struct nsm_handle *nsm_reboot_lookup(const struct net *net, + const struct nlm_reboot *info) { struct nsm_handle *cached; + struct lockd_net *ln = net_generic(net, lockd_net_id); spin_lock(&nsm_lock); - cached = nsm_lookup_priv(&info->priv); + cached = nsm_lookup_priv(&ln->nsm_handles, &info->priv); if (unlikely(cached == NULL)) { spin_unlock(&nsm_lock); dprintk("lockd: never saw rebooted peer '%.*s' before\n", diff --git a/fs/lockd/netns.h b/fs/lockd/netns.h index 097bfa3adb1c..5426189406c1 100644 --- a/fs/lockd/netns.h +++ b/fs/lockd/netns.h @@ -12,9 +12,7 @@ struct lockd_net { struct delayed_work grace_period_end; struct lock_manager lockd_manager; - spinlock_t nsm_clnt_lock; - unsigned int nsm_users; - struct rpc_clnt *nsm_clnt; + struct list_head nsm_handles; }; extern int lockd_net_id; diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index d678bcc3cbcb..5f31ebd96c06 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -592,7 +592,7 @@ static int lockd_init_net(struct net *net) INIT_DELAYED_WORK(&ln->grace_period_end, grace_ender); INIT_LIST_HEAD(&ln->lockd_manager.list); ln->lockd_manager.block_opens = false; - spin_lock_init(&ln->nsm_clnt_lock); + INIT_LIST_HEAD(&ln->nsm_handles); return 0; } diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index b147d1ae71fd..09c576f26c7b 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -421,7 +421,7 @@ nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, return rpc_system_err; } - nlm_host_rebooted(argp); + nlm_host_rebooted(SVC_NET(rqstp), argp); return rpc_success; } diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 21171f0c6477..fb26b9f522e7 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -464,7 +464,7 @@ nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, return rpc_system_err; } - nlm_host_rebooted(argp); + nlm_host_rebooted(SVC_NET(rqstp), argp); return rpc_success; } diff --git a/fs/locks.c b/fs/locks.c index 0d2b3267e2a3..af1ed74a657f 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -119,7 +119,6 @@ #include <linux/fdtable.h> #include <linux/fs.h> #include <linux/init.h> -#include <linux/module.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/syscalls.h> @@ -230,16 +229,44 @@ locks_get_lock_context(struct inode *inode, int type) ctx = smp_load_acquire(&inode->i_flctx); } out: + trace_locks_get_lock_context(inode, type, ctx); return ctx; } +static void +locks_dump_ctx_list(struct list_head *list, char *list_type) +{ + struct file_lock *fl; + + list_for_each_entry(fl, list, fl_list) { + pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid); + } +} + +static void +locks_check_ctx_lists(struct inode *inode) +{ + struct file_lock_context *ctx = inode->i_flctx; + + if (unlikely(!list_empty(&ctx->flc_flock) || + !list_empty(&ctx->flc_posix) || + !list_empty(&ctx->flc_lease))) { + pr_warn("Leaked locks on dev=0x%x:0x%x ino=0x%lx:\n", + MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), + inode->i_ino); + locks_dump_ctx_list(&ctx->flc_flock, "FLOCK"); + locks_dump_ctx_list(&ctx->flc_posix, "POSIX"); + locks_dump_ctx_list(&ctx->flc_lease, "LEASE"); + } +} + void -locks_free_lock_context(struct file_lock_context *ctx) +locks_free_lock_context(struct inode *inode) { - if (ctx) { - WARN_ON_ONCE(!list_empty(&ctx->flc_flock)); - WARN_ON_ONCE(!list_empty(&ctx->flc_posix)); - WARN_ON_ONCE(!list_empty(&ctx->flc_lease)); + struct file_lock_context *ctx = inode->i_flctx; + + if (unlikely(ctx)) { + locks_check_ctx_lists(inode); kmem_cache_free(flctx_cache, ctx); } } @@ -934,7 +961,8 @@ out: return error; } -static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock) +static int posix_lock_inode(struct inode *inode, struct file_lock *request, + struct file_lock *conflock) { struct file_lock *fl, *tmp; struct file_lock *new_fl = NULL; @@ -1142,6 +1170,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str if (new_fl2) locks_free_lock(new_fl2); locks_dispose_list(&dispose); + trace_posix_lock_inode(inode, request, error); + return error; } @@ -1162,7 +1192,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { - return __posix_lock_file(file_inode(filp), fl, conflock); + return posix_lock_inode(file_inode(filp), fl, conflock); } EXPORT_SYMBOL(posix_lock_file); @@ -1178,7 +1208,7 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) int error; might_sleep (); for (;;) { - error = __posix_lock_file(inode, fl, NULL); + error = posix_lock_inode(inode, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, !fl->fl_next); @@ -1191,6 +1221,7 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) return error; } +#ifdef CONFIG_MANDATORY_FILE_LOCKING /** * locks_mandatory_locked - Check for an active lock * @file: the file to check @@ -1227,20 +1258,16 @@ int locks_mandatory_locked(struct file *file) /** * locks_mandatory_area - Check for a conflicting lock - * @read_write: %FLOCK_VERIFY_WRITE for exclusive access, %FLOCK_VERIFY_READ - * for shared - * @inode: the file to check + * @inode: the file to check * @filp: how the file was opened (if it was) - * @offset: start of area to check - * @count: length of area to check + * @start: first byte in the file to check + * @end: lastbyte in the file to check + * @type: %F_WRLCK for a write lock, else %F_RDLCK * * Searches the inode's list of locks to find any POSIX locks which conflict. - * This function is called from rw_verify_area() and - * locks_verify_truncate(). */ -int locks_mandatory_area(int read_write, struct inode *inode, - struct file *filp, loff_t offset, - size_t count) +int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start, + loff_t end, unsigned char type) { struct file_lock fl; int error; @@ -1252,15 +1279,15 @@ int locks_mandatory_area(int read_write, struct inode *inode, fl.fl_flags = FL_POSIX | FL_ACCESS; if (filp && !(filp->f_flags & O_NONBLOCK)) sleep = true; - fl.fl_type = (read_write == FLOCK_VERIFY_WRITE) ? F_WRLCK : F_RDLCK; - fl.fl_start = offset; - fl.fl_end = offset + count - 1; + fl.fl_type = type; + fl.fl_start = start; + fl.fl_end = end; for (;;) { if (filp) { fl.fl_owner = filp; fl.fl_flags &= ~FL_SLEEP; - error = __posix_lock_file(inode, &fl, NULL); + error = posix_lock_inode(inode, &fl, NULL); if (!error) break; } @@ -1268,7 +1295,7 @@ int locks_mandatory_area(int read_write, struct inode *inode, if (sleep) fl.fl_flags |= FL_SLEEP; fl.fl_owner = current->files; - error = __posix_lock_file(inode, &fl, NULL); + error = posix_lock_inode(inode, &fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl.fl_wait, !fl.fl_next); @@ -1289,6 +1316,7 @@ int locks_mandatory_area(int read_write, struct inode *inode, } EXPORT_SYMBOL(locks_mandatory_area); +#endif /* CONFIG_MANDATORY_FILE_LOCKING */ static void lease_clear_pending(struct file_lock *fl, int arg) { @@ -1503,12 +1531,10 @@ void lease_get_mtime(struct inode *inode, struct timespec *time) ctx = smp_load_acquire(&inode->i_flctx); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); - if (!list_empty(&ctx->flc_lease)) { - fl = list_first_entry(&ctx->flc_lease, - struct file_lock, fl_list); - if (fl->fl_type == F_WRLCK) - has_lease = true; - } + fl = list_first_entry_or_null(&ctx->flc_lease, + struct file_lock, fl_list); + if (fl && (fl->fl_type == F_WRLCK)) + has_lease = true; spin_unlock(&ctx->flc_lock); } @@ -2165,6 +2191,8 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, if (file_lock == NULL) return -ENOLCK; + inode = file_inode(filp); + /* * This might block, so we do it before checking the inode. */ @@ -2172,8 +2200,6 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, if (copy_from_user(&flock, l, sizeof(flock))) goto out; - inode = file_inode(filp); - /* Don't allow mandatory locks on files that may be memory mapped * and shared. */ @@ -2182,7 +2208,6 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } -again: error = flock_to_posix_lock(filp, file_lock, &flock); if (error) goto out; @@ -2221,23 +2246,29 @@ again: error = do_lock_file_wait(filp, cmd, file_lock); /* - * Attempt to detect a close/fcntl race and recover by - * releasing the lock that was just acquired. - */ - /* - * we need that spin_lock here - it prevents reordering between - * update of i_flctx->flc_posix and check for it done in close(). - * rcu_read_lock() wouldn't do. + * Attempt to detect a close/fcntl race and recover by releasing the + * lock that was just acquired. There is no need to do that when we're + * unlocking though, or for OFD locks. */ - spin_lock(¤t->files->file_lock); - f = fcheck(fd); - spin_unlock(¤t->files->file_lock); - if (!error && f != filp && flock.l_type != F_UNLCK) { - flock.l_type = F_UNLCK; - goto again; + if (!error && file_lock->fl_type != F_UNLCK && + !(file_lock->fl_flags & FL_OFDLCK)) { + /* + * We need that spin_lock here - it prevents reordering between + * update of i_flctx->flc_posix and check for it done in + * close(). rcu_read_lock() wouldn't do. + */ + spin_lock(¤t->files->file_lock); + f = fcheck(fd); + spin_unlock(¤t->files->file_lock); + if (f != filp) { + file_lock->fl_type = F_UNLCK; + error = do_lock_file_wait(filp, cmd, file_lock); + WARN_ON_ONCE(error); + error = -EBADF; + } } - out: + trace_fcntl_setlk(inode, file_lock, error); locks_free_lock(file_lock); return error; } @@ -2322,7 +2353,6 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } -again: error = flock64_to_posix_lock(filp, file_lock, &flock); if (error) goto out; @@ -2361,17 +2391,27 @@ again: error = do_lock_file_wait(filp, cmd, file_lock); /* - * Attempt to detect a close/fcntl race and recover by - * releasing the lock that was just acquired. + * Attempt to detect a close/fcntl race and recover by releasing the + * lock that was just acquired. There is no need to do that when we're + * unlocking though, or for OFD locks. */ - spin_lock(¤t->files->file_lock); - f = fcheck(fd); - spin_unlock(¤t->files->file_lock); - if (!error && f != filp && flock.l_type != F_UNLCK) { - flock.l_type = F_UNLCK; - goto again; + if (!error && file_lock->fl_type != F_UNLCK && + !(file_lock->fl_flags & FL_OFDLCK)) { + /* + * We need that spin_lock here - it prevents reordering between + * update of i_flctx->flc_posix and check for it done in + * close(). rcu_read_lock() wouldn't do. + */ + spin_lock(¤t->files->file_lock); + f = fcheck(fd); + spin_unlock(¤t->files->file_lock); + if (f != filp) { + file_lock->fl_type = F_UNLCK; + error = do_lock_file_wait(filp, cmd, file_lock); + WARN_ON_ONCE(error); + error = -EBADF; + } } - out: locks_free_lock(file_lock); return error; @@ -2385,6 +2425,7 @@ out: */ void locks_remove_posix(struct file *filp, fl_owner_t owner) { + int error; struct file_lock lock; struct file_lock_context *ctx; @@ -2407,10 +2448,11 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) lock.fl_ops = NULL; lock.fl_lmops = NULL; - vfs_lock_file(filp, F_SETLK, &lock, NULL); + error = vfs_lock_file(filp, F_SETLK, &lock, NULL); if (lock.fl_ops && lock.fl_ops->fl_release_private) lock.fl_ops->fl_release_private(&lock); + trace_locks_remove_posix(file_inode(filp), &lock, error); } EXPORT_SYMBOL(locks_remove_posix); @@ -2706,7 +2748,7 @@ static int __init proc_locks_init(void) proc_create("locks", 0, NULL, &proc_locks_operations); return 0; } -module_init(proc_locks_init); +fs_initcall(proc_locks_init); #endif static int __init filelock_init(void) diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c index f9b45d46d4c4..542468e9bfb4 100644 --- a/fs/logfs/dir.c +++ b/fs/logfs/dir.c @@ -528,7 +528,8 @@ static int logfs_symlink(struct inode *dir, struct dentry *dentry, if (IS_ERR(inode)) return PTR_ERR(inode); - inode->i_op = &logfs_symlink_iops; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &logfs_reg_aops; return __logfs_create(dir, dentry, inode, target, destlen); @@ -776,12 +777,6 @@ fail: return -EIO; } -const struct inode_operations logfs_symlink_iops = { - .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, -}; - const struct inode_operations logfs_dir_iops = { .create = logfs_create, .link = logfs_link, diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c index af49e2d6941a..0fce46d62b9c 100644 --- a/fs/logfs/inode.c +++ b/fs/logfs/inode.c @@ -64,7 +64,8 @@ static void logfs_inode_setops(struct inode *inode) inode->i_mapping->a_ops = &logfs_reg_aops; break; case S_IFLNK: - inode->i_op = &logfs_symlink_iops; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &logfs_reg_aops; break; case S_IFSOCK: /* fall through */ diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h index 5f0937609465..39d91f86cd35 100644 --- a/fs/logfs/logfs.h +++ b/fs/logfs/logfs.h @@ -302,7 +302,7 @@ struct logfs_block { struct inode *inode; struct logfs_transaction *ta; unsigned long alias_map[LOGFS_BLOCK_FACTOR / BITS_PER_LONG]; - struct logfs_block_ops *ops; + const struct logfs_block_ops *ops; int full; int partial; int reserved_bytes; @@ -495,7 +495,6 @@ static inline int logfs_get_sb_mtd(struct logfs_super *s, int mtdnr) #endif /* dir.c */ -extern const struct inode_operations logfs_symlink_iops; extern const struct inode_operations logfs_dir_iops; extern const struct file_operations logfs_dir_fops; int logfs_replay_journal(struct super_block *sb); @@ -579,7 +578,7 @@ int logfs_exist_block(struct inode *inode, u64 bix); int get_page_reserve(struct inode *inode, struct page *page); void logfs_get_wblocks(struct super_block *sb, struct page *page, int lock); void logfs_put_wblocks(struct super_block *sb, struct page *page, int lock); -extern struct logfs_block_ops indirect_block_ops; +extern const struct logfs_block_ops indirect_block_ops; /* segment.c */ int logfs_erase_segment(struct super_block *sb, u32 ofs, int ensure_erase); diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c index 380d86e1ab45..20973c9e52f8 100644 --- a/fs/logfs/readwrite.c +++ b/fs/logfs/readwrite.c @@ -569,13 +569,13 @@ static void indirect_free_block(struct super_block *sb, } -static struct logfs_block_ops inode_block_ops = { +static const struct logfs_block_ops inode_block_ops = { .write_block = inode_write_block, .free_block = inode_free_block, .write_alias = inode_write_alias, }; -struct logfs_block_ops indirect_block_ops = { +const struct logfs_block_ops indirect_block_ops = { .write_block = indirect_write_block, .free_block = indirect_free_block, .write_alias = indirect_write_alias, diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c index 7f9b096d8d57..d270e4b2ab6b 100644 --- a/fs/logfs/segment.c +++ b/fs/logfs/segment.c @@ -57,7 +57,7 @@ static struct page *get_mapping_page(struct super_block *sb, pgoff_t index, filler_t *filler = super->s_devops->readpage; struct page *page; - BUG_ON(mapping_gfp_mask(mapping) & __GFP_FS); + BUG_ON(mapping_gfp_constraint(mapping, __GFP_FS)); if (use_filler) page = read_cache_page(mapping, index, filler, sb); else { @@ -197,7 +197,7 @@ static int btree_write_alias(struct super_block *sb, struct logfs_block *block, return 0; } -static struct logfs_block_ops btree_block_ops = { +static const struct logfs_block_ops btree_block_ops = { .write_block = btree_write_block, .free_block = __free_block, .write_alias = btree_write_alias, diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 086cd0a61e80..cb1789ca1ee6 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -435,8 +435,7 @@ static const struct address_space_operations minix_aops = { static const struct inode_operations minix_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getattr = minix_getattr, }; @@ -452,6 +451,7 @@ void minix_set_inode(struct inode *inode, dev_t rdev) inode->i_mapping->a_ops = &minix_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &minix_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &minix_aops; } else init_special_inode(inode, inode->i_mode, rdev); diff --git a/fs/minix/itree_v1.c b/fs/minix/itree_v1.c index 282e15ad8cd8..46ca39d6c735 100644 --- a/fs/minix/itree_v1.c +++ b/fs/minix/itree_v1.c @@ -24,16 +24,15 @@ static inline block_t *i_data(struct inode *inode) static int block_to_path(struct inode * inode, long block, int offsets[DEPTH]) { int n = 0; - char b[BDEVNAME_SIZE]; if (block < 0) { - printk("MINIX-fs: block_to_path: block %ld < 0 on dev %s\n", - block, bdevname(inode->i_sb->s_bdev, b)); + printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n", + block, inode->i_sb->s_bdev); } else if (block >= (minix_sb(inode->i_sb)->s_max_size/BLOCK_SIZE)) { if (printk_ratelimit()) printk("MINIX-fs: block_to_path: " - "block %ld too big on dev %s\n", - block, bdevname(inode->i_sb->s_bdev, b)); + "block %ld too big on dev %pg\n", + block, inode->i_sb->s_bdev); } else if (block < 7) { offsets[n++] = block; } else if ((block -= 7) < 512) { diff --git a/fs/minix/itree_v2.c b/fs/minix/itree_v2.c index 78e2d93e5c83..1ee101352586 100644 --- a/fs/minix/itree_v2.c +++ b/fs/minix/itree_v2.c @@ -26,18 +26,17 @@ static inline block_t *i_data(struct inode *inode) static int block_to_path(struct inode * inode, long block, int offsets[DEPTH]) { int n = 0; - char b[BDEVNAME_SIZE]; struct super_block *sb = inode->i_sb; if (block < 0) { - printk("MINIX-fs: block_to_path: block %ld < 0 on dev %s\n", - block, bdevname(sb->s_bdev, b)); + printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n", + block, sb->s_bdev); } else if ((u64)block * (u64)sb->s_blocksize >= minix_sb(sb)->s_max_size) { if (printk_ratelimit()) printk("MINIX-fs: block_to_path: " - "block %ld too big on dev %s\n", - block, bdevname(sb->s_bdev, b)); + "block %ld too big on dev %pg\n", + block, sb->s_bdev); } else if (block < DIRCOUNT) { offsets[n++] = block; } else if ((block -= DIRCOUNT) < INDIRCOUNT(sb)) { diff --git a/fs/mpage.c b/fs/mpage.c index 09abba7653aa..1480d3a18037 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -361,7 +361,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, sector_t last_block_in_bio = 0; struct buffer_head map_bh; unsigned long first_logical_block = 0; - gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping); + gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL); map_bh.b_state = 0; map_bh.b_size = 0; @@ -397,7 +397,7 @@ int mpage_readpage(struct page *page, get_block_t get_block) sector_t last_block_in_bio = 0; struct buffer_head map_bh; unsigned long first_logical_block = 0; - gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(page->mapping); + gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL); map_bh.b_state = 0; map_bh.b_size = 0; diff --git a/fs/namei.c b/fs/namei.c index 6f567347f14f..bceefd5588a2 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -505,13 +505,13 @@ struct nameidata { int total_link_count; struct saved { struct path link; - void *cookie; + struct delayed_call done; const char *name; - struct inode *inode; unsigned seq; } *stack, internal[EMBEDDED_LEVELS]; struct filename *name; struct nameidata *saved; + struct inode *link_inode; unsigned root_seq; int dfd; }; @@ -534,10 +534,8 @@ static void restore_nameidata(void) current->nameidata = old; if (old) old->total_link_count = now->total_link_count; - if (now->stack != now->internal) { + if (now->stack != now->internal) kfree(now->stack); - now->stack = now->internal; - } } static int __nd_alloc_stack(struct nameidata *nd) @@ -592,11 +590,8 @@ static void drop_links(struct nameidata *nd) int i = nd->depth; while (i--) { struct saved *last = nd->stack + i; - struct inode *inode = last->inode; - if (last->cookie && inode->i_op->put_link) { - inode->i_op->put_link(inode, last->cookie); - last->cookie = NULL; - } + do_delayed_call(&last->done); + clear_delayed_call(&last->done); } } @@ -657,7 +652,7 @@ static bool legitimize_links(struct nameidata *nd) * Path walking has 2 modes, rcu-walk and ref-walk (see * Documentation/filesystems/path-lookup.txt). In situations when we can't * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab - * normal reference counts on dentries and vfsmounts to transition to rcu-walk + * normal reference counts on dentries and vfsmounts to transition to ref-walk * mode. Refcounts are grabbed at the last known good point before rcu-walk * got stuck, so ref-walk may continue from there. If this is not successful * (eg. a seqcount has changed), then failure is returned and it's up to caller @@ -807,19 +802,19 @@ static int complete_walk(struct nameidata *nd) static void set_root(struct nameidata *nd) { - get_fs_root(current->fs, &nd->root); -} - -static void set_root_rcu(struct nameidata *nd) -{ struct fs_struct *fs = current->fs; - unsigned seq; - do { - seq = read_seqcount_begin(&fs->seq); - nd->root = fs->root; - nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq); - } while (read_seqcount_retry(&fs->seq, seq)); + if (nd->flags & LOOKUP_RCU) { + unsigned seq; + + do { + seq = read_seqcount_begin(&fs->seq); + nd->root = fs->root; + nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq); + } while (read_seqcount_retry(&fs->seq, seq)); + } else { + get_fs_root(fs, &nd->root); + } } static void path_put_conditional(struct path *path, struct nameidata *nd) @@ -841,8 +836,28 @@ static inline void path_to_nameidata(const struct path *path, nd->path.dentry = path->dentry; } +static int nd_jump_root(struct nameidata *nd) +{ + if (nd->flags & LOOKUP_RCU) { + struct dentry *d; + nd->path = nd->root; + d = nd->path.dentry; + nd->inode = d->d_inode; + nd->seq = nd->root_seq; + if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq))) + return -ECHILD; + } else { + path_put(&nd->path); + nd->path = nd->root; + path_get(&nd->path); + nd->inode = nd->path.dentry->d_inode; + } + nd->flags |= LOOKUP_JUMPED; + return 0; +} + /* - * Helper to directly jump to a known parsed path from ->follow_link, + * Helper to directly jump to a known parsed path from ->get_link, * caller must have taken a reference to path beforehand. */ void nd_jump_link(struct path *path) @@ -858,9 +873,7 @@ void nd_jump_link(struct path *path) static inline void put_link(struct nameidata *nd) { struct saved *last = nd->stack + --nd->depth; - struct inode *inode = last->inode; - if (last->cookie && inode->i_op->put_link) - inode->i_op->put_link(inode, last->cookie); + do_delayed_call(&last->done); if (!(nd->flags & LOOKUP_RCU)) path_put(&last->link); } @@ -892,7 +905,7 @@ static inline int may_follow_link(struct nameidata *nd) return 0; /* Allowed if owner and follower match. */ - inode = nd->stack[0].inode; + inode = nd->link_inode; if (uid_eq(current_cred()->fsuid, inode->i_uid)) return 0; @@ -983,7 +996,7 @@ const char *get_link(struct nameidata *nd) { struct saved *last = nd->stack + nd->depth - 1; struct dentry *dentry = last->link.dentry; - struct inode *inode = last->inode; + struct inode *inode = nd->link_inode; int error; const char *res; @@ -1004,36 +1017,27 @@ const char *get_link(struct nameidata *nd) nd->last_type = LAST_BIND; res = inode->i_link; if (!res) { + const char * (*get)(struct dentry *, struct inode *, + struct delayed_call *); + get = inode->i_op->get_link; if (nd->flags & LOOKUP_RCU) { - if (unlikely(unlazy_walk(nd, NULL, 0))) - return ERR_PTR(-ECHILD); + res = get(NULL, inode, &last->done); + if (res == ERR_PTR(-ECHILD)) { + if (unlikely(unlazy_walk(nd, NULL, 0))) + return ERR_PTR(-ECHILD); + res = get(dentry, inode, &last->done); + } + } else { + res = get(dentry, inode, &last->done); } - res = inode->i_op->follow_link(dentry, &last->cookie); - if (IS_ERR_OR_NULL(res)) { - last->cookie = NULL; + if (IS_ERR_OR_NULL(res)) return res; - } } if (*res == '/') { - if (nd->flags & LOOKUP_RCU) { - struct dentry *d; - if (!nd->root.mnt) - set_root_rcu(nd); - nd->path = nd->root; - d = nd->path.dentry; - nd->inode = d->d_inode; - nd->seq = nd->root_seq; - if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq))) - return ERR_PTR(-ECHILD); - } else { - if (!nd->root.mnt) - set_root(nd); - path_put(&nd->path); - nd->path = nd->root; - path_get(&nd->root); - nd->inode = nd->path.dentry->d_inode; - } - nd->flags |= LOOKUP_JUMPED; + if (!nd->root.mnt) + set_root(nd); + if (unlikely(nd_jump_root(nd))) + return ERR_PTR(-ECHILD); while (unlikely(*++res == '/')) ; } @@ -1294,8 +1298,6 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, static int follow_dotdot_rcu(struct nameidata *nd) { struct inode *inode = nd->inode; - if (!nd->root.mnt) - set_root_rcu(nd); while (1) { if (path_equal(&nd->path, &nd->root)) @@ -1415,9 +1417,6 @@ static void follow_mount(struct path *path) static int follow_dotdot(struct nameidata *nd) { - if (!nd->root.mnt) - set_root(nd); - while(1) { struct dentry *old = nd->path.dentry; @@ -1655,6 +1654,8 @@ static inline int may_lookup(struct nameidata *nd) static inline int handle_dots(struct nameidata *nd, int type) { if (type == LAST_DOTDOT) { + if (!nd->root.mnt) + set_root(nd); if (nd->flags & LOOKUP_RCU) { return follow_dotdot_rcu(nd); } else @@ -1691,8 +1692,8 @@ static int pick_link(struct nameidata *nd, struct path *link, last = nd->stack + nd->depth++; last->link = *link; - last->cookie = NULL; - last->inode = inode; + clear_delayed_call(&last->done); + nd->link_inode = inode; last->seq = seq; return 1; } @@ -1996,7 +1997,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags) nd->last_type = LAST_ROOT; /* if there are only slashes... */ nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT; nd->depth = 0; - nd->total_link_count = 0; if (flags & LOOKUP_ROOT) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; @@ -2021,18 +2021,19 @@ static const char *path_init(struct nameidata *nd, unsigned flags) } nd->root.mnt = NULL; + nd->path.mnt = NULL; + nd->path.dentry = NULL; nd->m_seq = read_seqbegin(&mount_lock); if (*s == '/') { - if (flags & LOOKUP_RCU) { + if (flags & LOOKUP_RCU) rcu_read_lock(); - set_root_rcu(nd); - nd->seq = nd->root_seq; - } else { - set_root(nd); - path_get(&nd->root); - } - nd->path = nd->root; + set_root(nd); + if (likely(!nd_jump_root(nd))) + return s; + nd->root.mnt = NULL; + rcu_read_unlock(); + return ERR_PTR(-ECHILD); } else if (nd->dfd == AT_FDCWD) { if (flags & LOOKUP_RCU) { struct fs_struct *fs = current->fs; @@ -2043,11 +2044,14 @@ static const char *path_init(struct nameidata *nd, unsigned flags) do { seq = read_seqcount_begin(&fs->seq); nd->path = fs->pwd; + nd->inode = nd->path.dentry->d_inode; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq)); } else { get_fs_pwd(current->fs, &nd->path); + nd->inode = nd->path.dentry->d_inode; } + return s; } else { /* Caller must check execute permissions on the starting path component */ struct fd f = fdget_raw(nd->dfd); @@ -2077,16 +2081,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags) fdput(f); return s; } - - nd->inode = nd->path.dentry->d_inode; - if (!(flags & LOOKUP_RCU)) - return s; - if (likely(!read_seqcount_retry(&nd->path.dentry->d_seq, nd->seq))) - return s; - if (!(nd->flags & LOOKUP_ROOT)) - nd->root.mnt = NULL; - rcu_read_unlock(); - return ERR_PTR(-ECHILD); } static const char *trailing_symlink(struct nameidata *nd) @@ -2279,6 +2273,8 @@ EXPORT_SYMBOL(vfs_path_lookup); * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. + * + * The caller must hold base->i_mutex. */ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) { @@ -2322,6 +2318,75 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) } EXPORT_SYMBOL(lookup_one_len); +/** + * lookup_one_len_unlocked - filesystem helper to lookup single pathname component + * @name: pathname component to lookup + * @base: base directory to lookup from + * @len: maximum length @len should be interpreted to + * + * Note that this routine is purely a helper for filesystem usage and should + * not be called by generic code. + * + * Unlike lookup_one_len, it should be called without the parent + * i_mutex held, and will take the i_mutex itself if necessary. + */ +struct dentry *lookup_one_len_unlocked(const char *name, + struct dentry *base, int len) +{ + struct qstr this; + unsigned int c; + int err; + struct dentry *ret; + + this.name = name; + this.len = len; + this.hash = full_name_hash(name, len); + if (!len) + return ERR_PTR(-EACCES); + + if (unlikely(name[0] == '.')) { + if (len < 2 || (len == 2 && name[1] == '.')) + return ERR_PTR(-EACCES); + } + + while (len--) { + c = *(const unsigned char *)name++; + if (c == '/' || c == '\0') + return ERR_PTR(-EACCES); + } + /* + * See if the low-level filesystem might want + * to use its own hash.. + */ + if (base->d_flags & DCACHE_OP_HASH) { + int err = base->d_op->d_hash(base, &this); + if (err < 0) + return ERR_PTR(err); + } + + err = inode_permission(base->d_inode, MAY_EXEC); + if (err) + return ERR_PTR(err); + + /* + * __d_lookup() is used to try to get a quick answer and avoid the + * mutex. A false-negative does no harm. + */ + ret = __d_lookup(base, &this); + if (ret && unlikely(ret->d_flags & DCACHE_OP_REVALIDATE)) { + dput(ret); + ret = NULL; + } + if (ret) + return ret; + + mutex_lock(&base->d_inode->i_mutex); + ret = __lookup_hash(&this, base, 0); + mutex_unlock(&base->d_inode->i_mutex); + return ret; +} +EXPORT_SYMBOL(lookup_one_len_unlocked); + int user_path_at_empty(int dfd, const char __user *name, unsigned flags, struct path *path, int *empty) { @@ -2670,10 +2735,6 @@ static int may_open(struct path *path, int acc_mode, int flag) struct inode *inode = dentry->d_inode; int error; - /* O_PATH? */ - if (!acc_mode) - return 0; - if (!inode) return -ENOENT; @@ -2695,7 +2756,7 @@ static int may_open(struct path *path, int acc_mode, int flag) break; } - error = inode_permission(inode, acc_mode); + error = inode_permission(inode, MAY_OPEN | acc_mode); if (error) return error; @@ -2887,7 +2948,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, if (*opened & FILE_CREATED) { WARN_ON(!(open_flag & O_CREAT)); fsnotify_create(dir, dentry); - acc_mode = MAY_OPEN; + acc_mode = 0; } error = may_open(&file->f_path, acc_mode, open_flag); if (error) @@ -3100,7 +3161,7 @@ retry_lookup: /* Don't check for write permission, don't truncate */ open_flag &= ~O_TRUNC; will_truncate = false; - acc_mode = MAY_OPEN; + acc_mode = 0; path_to_nameidata(&path, nd); goto finish_open_created; } @@ -3184,10 +3245,11 @@ finish_open: got_write = true; } finish_open_created: - error = may_open(&nd->path, acc_mode, open_flag); - if (error) - goto out; - + if (likely(!(open_flag & O_PATH))) { + error = may_open(&nd->path, acc_mode, open_flag); + if (error) + goto out; + } BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */ error = vfs_open(&nd->path, file, current_cred()); if (!error) { @@ -3274,7 +3336,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, goto out2; audit_inode(nd->name, child, 0); /* Don't check for other permissions, the inode was just created */ - error = may_open(&path, MAY_OPEN, op->open_flag); + error = may_open(&path, 0, op->open_flag); if (error) goto out2; file->f_path.mnt = path.mnt; @@ -4496,72 +4558,73 @@ EXPORT_SYMBOL(readlink_copy); /* * A helper for ->readlink(). This should be used *ONLY* for symlinks that - * have ->follow_link() touching nd only in nd_set_link(). Using (or not - * using) it for any given inode is up to filesystem. + * have ->get_link() not calling nd_jump_link(). Using (or not using) it + * for any given inode is up to filesystem. */ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen) { - void *cookie; + DEFINE_DELAYED_CALL(done); struct inode *inode = d_inode(dentry); const char *link = inode->i_link; int res; if (!link) { - link = inode->i_op->follow_link(dentry, &cookie); + link = inode->i_op->get_link(dentry, inode, &done); if (IS_ERR(link)) return PTR_ERR(link); } res = readlink_copy(buffer, buflen, link); - if (inode->i_op->put_link) - inode->i_op->put_link(inode, cookie); + do_delayed_call(&done); return res; } EXPORT_SYMBOL(generic_readlink); /* get the link contents into pagecache */ -static char *page_getlink(struct dentry * dentry, struct page **ppage) +const char *page_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) { char *kaddr; struct page *page; - struct address_space *mapping = dentry->d_inode->i_mapping; - page = read_mapping_page(mapping, 0, NULL); - if (IS_ERR(page)) - return (char*)page; - *ppage = page; - kaddr = kmap(page); - nd_terminate_link(kaddr, dentry->d_inode->i_size, PAGE_SIZE - 1); + struct address_space *mapping = inode->i_mapping; + + if (!dentry) { + page = find_get_page(mapping, 0); + if (!page) + return ERR_PTR(-ECHILD); + if (!PageUptodate(page)) { + put_page(page); + return ERR_PTR(-ECHILD); + } + } else { + page = read_mapping_page(mapping, 0, NULL); + if (IS_ERR(page)) + return (char*)page; + } + set_delayed_call(callback, page_put_link, page); + BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM); + kaddr = page_address(page); + nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); return kaddr; } -int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) -{ - struct page *page = NULL; - int res = readlink_copy(buffer, buflen, page_getlink(dentry, &page)); - if (page) { - kunmap(page); - page_cache_release(page); - } - return res; -} -EXPORT_SYMBOL(page_readlink); +EXPORT_SYMBOL(page_get_link); -const char *page_follow_link_light(struct dentry *dentry, void **cookie) +void page_put_link(void *arg) { - struct page *page = NULL; - char *res = page_getlink(dentry, &page); - if (!IS_ERR(res)) - *cookie = page; - return res; + put_page(arg); } -EXPORT_SYMBOL(page_follow_link_light); +EXPORT_SYMBOL(page_put_link); -void page_put_link(struct inode *unused, void *cookie) +int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { - struct page *page = cookie; - kunmap(page); - page_cache_release(page); + DEFINE_DELAYED_CALL(done); + int res = readlink_copy(buffer, buflen, + page_get_link(dentry, d_inode(dentry), + &done)); + do_delayed_call(&done); + return res; } -EXPORT_SYMBOL(page_put_link); +EXPORT_SYMBOL(page_readlink); /* * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS @@ -4572,7 +4635,6 @@ int __page_symlink(struct inode *inode, const char *symname, int len, int nofs) struct page *page; void *fsdata; int err; - char *kaddr; unsigned int flags = AOP_FLAG_UNINTERRUPTIBLE; if (nofs) flags |= AOP_FLAG_NOFS; @@ -4583,9 +4645,7 @@ retry: if (err) goto fail; - kaddr = kmap_atomic(page); - memcpy(kaddr, symname, len-1); - kunmap_atomic(kaddr); + memcpy(page_address(page), symname, len-1); err = pagecache_write_end(NULL, mapping, 0, len-1, len-1, page, fsdata); @@ -4604,13 +4664,12 @@ EXPORT_SYMBOL(__page_symlink); int page_symlink(struct inode *inode, const char *symname, int len) { return __page_symlink(inode, symname, len, - !(mapping_gfp_mask(inode->i_mapping) & __GFP_FS)); + !mapping_gfp_constraint(inode->i_mapping, __GFP_FS)); } EXPORT_SYMBOL(page_symlink); const struct inode_operations page_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, }; EXPORT_SYMBOL(page_symlink_inode_operations); diff --git a/fs/namespace.c b/fs/namespace.c index 0570729c87fd..a830e1463704 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1584,6 +1584,14 @@ static inline bool may_mount(void) return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } +static inline bool may_mandlock(void) +{ +#ifndef CONFIG_MANDATORY_FILE_LOCKING + return false; +#endif + return capable(CAP_SYS_ADMIN); +} + /* * Now umount can handle mount points as well as block devices. * This is important for filesystems which use unnamed block devices. @@ -2601,18 +2609,18 @@ static long exact_copy_from_user(void *to, const void __user * from, return n; } -int copy_mount_options(const void __user * data, unsigned long *where) +void *copy_mount_options(const void __user * data) { int i; - unsigned long page; unsigned long size; + char *copy; - *where = 0; if (!data) - return 0; + return NULL; - if (!(page = __get_free_page(GFP_KERNEL))) - return -ENOMEM; + copy = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!copy) + return ERR_PTR(-ENOMEM); /* We only care that *some* data at the address the user * gave us is valid. Just in case, we'll zero @@ -2623,15 +2631,14 @@ int copy_mount_options(const void __user * data, unsigned long *where) if (size > PAGE_SIZE) size = PAGE_SIZE; - i = size - exact_copy_from_user((void *)page, data, size); + i = size - exact_copy_from_user(copy, data, size); if (!i) { - free_page(page); - return -EFAULT; + kfree(copy); + return ERR_PTR(-EFAULT); } if (i != PAGE_SIZE) - memset((char *)page + i, 0, PAGE_SIZE - i); - *where = page; - return 0; + memset(copy + i, 0, PAGE_SIZE - i); + return copy; } char *copy_mount_string(const void __user *data) @@ -2677,6 +2684,8 @@ long do_mount(const char *dev_name, const char __user *dir_name, type_page, flags, data_page); if (!retval && !may_mount()) retval = -EPERM; + if (!retval && (flags & MS_MANDLOCK) && !may_mandlock()) + retval = -EPERM; if (retval) goto dput_out; @@ -2896,7 +2905,7 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, int ret; char *kernel_type; char *kernel_dev; - unsigned long data_page; + void *options; kernel_type = copy_mount_string(type); ret = PTR_ERR(kernel_type); @@ -2908,14 +2917,14 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, if (IS_ERR(kernel_dev)) goto out_dev; - ret = copy_mount_options(data, &data_page); - if (ret < 0) + options = copy_mount_options(data); + ret = PTR_ERR(options); + if (IS_ERR(options)) goto out_data; - ret = do_mount(kernel_dev, dir_name, kernel_type, flags, - (void *) data_page); + ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options); - free_page(data_page); + kfree(options); out_data: kfree(kernel_dev); out_dev: @@ -2939,9 +2948,9 @@ bool is_path_reachable(struct mount *mnt, struct dentry *dentry, return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry); } -int path_is_under(struct path *path1, struct path *path2) +bool path_is_under(struct path *path1, struct path *path2) { - int res; + bool res; read_seqlock_excl(&mount_lock); res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2); read_sequnlock_excl(&mount_lock); diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index 356816e7bc90..f0e3e9e747dd 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -1165,8 +1165,6 @@ out: static int ncp_mknod(struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev) { - if (!new_valid_dev(rdev)) - return -EINVAL; if (ncp_is_nfs_extras(NCP_SERVER(dir), NCP_FINFO(dir)->volNumber)) { ncp_dbg(1, "mode = 0%ho\n", mode); return ncp_create_new(dir, dentry, mode, rdev, 0); diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 9605a2f63549..ce1eb3f9dfe8 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -244,8 +244,7 @@ static void ncp_set_attr(struct inode *inode, struct ncp_entry_info *nwinfo) #if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS) static const struct inode_operations ncp_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = ncp_notify_change, }; #endif @@ -283,6 +282,7 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info) #if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS) } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &ncp_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &ncp_symlink_aops; #endif } else { diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 79b113048eac..0a3f9b594602 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -525,6 +525,8 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg switch (rqdata.cmd) { case NCP_LOCK_EX: case NCP_LOCK_SH: + if (rqdata.timeout < 0) + return -EINVAL; if (rqdata.timeout == 0) rqdata.timeout = NCP_LOCK_DEFAULT_TIMEOUT; else if (rqdata.timeout > NCP_LOCK_MAX_TIMEOUT) diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 9cd4eb3a1e22..ddd0138f410c 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -229,7 +229,7 @@ bl_read_pagelist(struct nfs_pgio_header *header) struct parallel_io *par; loff_t f_offset = header->args.offset; size_t bytes_left = header->args.count; - unsigned int pg_offset, pg_len; + unsigned int pg_offset = header->args.pgbase, pg_len; struct page **pages = header->args.pages; int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT; const bool is_dio = (header->dreq != NULL); @@ -262,7 +262,6 @@ bl_read_pagelist(struct nfs_pgio_header *header) extent_length = be.be_length - (isect - be.be_f_offset); } - pg_offset = f_offset & ~PAGE_CACHE_MASK; if (is_dio) { if (pg_offset + bytes_left > PAGE_CACHE_SIZE) pg_len = PAGE_CACHE_SIZE - pg_offset; @@ -273,9 +272,6 @@ bl_read_pagelist(struct nfs_pgio_header *header) pg_len = PAGE_CACHE_SIZE; } - isect += (pg_offset >> SECTOR_SHIFT); - extent_length -= (pg_offset >> SECTOR_SHIFT); - if (is_hole(&be)) { bio = bl_submit_bio(READ, bio); /* Fill hole w/ zeroes w/o accessing device */ @@ -301,6 +297,7 @@ bl_read_pagelist(struct nfs_pgio_header *header) extent_length -= (pg_len >> SECTOR_SHIFT); f_offset += pg_len; bytes_left -= pg_len; + pg_offset = 0; } if ((isect << SECTOR_SHIFT) >= header->inode->i_size) { header->res.eof = 1; diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 75f7c0a7538a..a7f2e6e33305 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -99,17 +99,6 @@ nfs4_callback_up(struct svc_serv *serv) } #if defined(CONFIG_NFS_V4_1) -static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net) -{ - /* - * Create an svc_sock for the back channel service that shares the - * fore channel connection. - * Returns the input port (0) and sets the svc_serv bc_xprt on success - */ - return svc_create_xprt(serv, "tcp-bc", net, PF_INET, 0, - SVC_SOCK_ANONYMOUS); -} - /* * The callback service for NFSv4.1 callbacks */ @@ -184,11 +173,6 @@ static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt, xprt->bc_serv = serv; } #else -static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net) -{ - return 0; -} - static void nfs_minorversion_callback_svc_setup(struct svc_serv *serv, struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp)) { @@ -259,7 +243,8 @@ static void nfs_callback_down_net(u32 minorversion, struct svc_serv *serv, struc svc_shutdown_net(serv, net); } -static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, struct net *net) +static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, + struct net *net, struct rpc_xprt *xprt) { struct nfs_net *nn = net_generic(net, nfs_net_id); int ret; @@ -275,20 +260,11 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, struct n goto err_bind; } - switch (minorversion) { - case 0: - ret = nfs4_callback_up_net(serv, net); - break; - case 1: - case 2: - ret = nfs41_callback_up_net(serv, net); - break; - default: - printk(KERN_ERR "NFS: unknown callback version: %d\n", - minorversion); - ret = -EINVAL; - break; - } + ret = -EPROTONOSUPPORT; + if (minorversion == 0) + ret = nfs4_callback_up_net(serv, net); + else if (xprt->ops->bc_up) + ret = xprt->ops->bc_up(serv, net); if (ret < 0) { printk(KERN_ERR "NFS: callback service start failed\n"); @@ -364,7 +340,7 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt) goto err_create; } - ret = nfs_callback_up_net(minorversion, serv, net); + ret = nfs_callback_up_net(minorversion, serv, net, xprt); if (ret < 0) goto err_net; diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index 84326e9fb47a..ff8195bd75ea 100644 --- a/fs/nfs/callback.h +++ b/fs/nfs/callback.h @@ -61,7 +61,6 @@ struct cb_compound_hdr_res { }; struct cb_getattrargs { - struct sockaddr *addr; struct nfs_fh fh; uint32_t bitmap[2]; }; @@ -76,7 +75,6 @@ struct cb_getattrres { }; struct cb_recallargs { - struct sockaddr *addr; struct nfs_fh fh; nfs4_stateid stateid; uint32_t truncate; @@ -119,9 +117,6 @@ extern __be32 nfs4_callback_sequence(struct cb_sequenceargs *args, struct cb_sequenceres *res, struct cb_process_state *cps); -extern int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, - const nfs4_stateid *stateid); - #define RCA4_TYPE_MASK_RDATA_DLG 0 #define RCA4_TYPE_MASK_WDATA_DLG 1 #define RCA4_TYPE_MASK_DIR_DLG 2 @@ -134,7 +129,6 @@ extern int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, #define RCA4_TYPE_MASK_ALL 0xf31f struct cb_recallanyargs { - struct sockaddr *craa_addr; uint32_t craa_objs_to_keep; uint32_t craa_type_mask; }; @@ -144,7 +138,6 @@ extern __be32 nfs4_callback_recallany(struct cb_recallanyargs *args, struct cb_process_state *cps); struct cb_recallslotargs { - struct sockaddr *crsa_addr; uint32_t crsa_target_highest_slotid; }; extern __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, @@ -152,7 +145,6 @@ extern __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, struct cb_process_state *cps); struct cb_layoutrecallargs { - struct sockaddr *cbl_addr; uint32_t cbl_recall_type; uint32_t cbl_layout_type; uint32_t cbl_layoutchanged; @@ -196,9 +188,6 @@ extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt); extern void nfs_callback_down(int minorversion, struct net *net); -extern int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation, - const nfs4_stateid *stateid); -extern int nfs4_set_callback_sessionid(struct nfs_client *clp); #endif /* CONFIG_NFS_V4 */ /* * nfs41: Callbacks are expected to not cause substantial latency, @@ -209,6 +198,5 @@ extern int nfs4_set_callback_sessionid(struct nfs_client *clp); #define NFS41_BC_MAX_CALLBACKS 1 extern unsigned int nfs_callback_set_tcpport; -extern unsigned short nfs_callback_tcpport; #endif /* __LINUX_FS_NFS_CALLBACK_H */ diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index b85cf7a30232..f0939d097406 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -17,9 +17,7 @@ #include "nfs4session.h" #include "nfs4trace.h" -#ifdef NFS_DEBUG #define NFSDBG_FACILITY NFSDBG_CALLBACK -#endif __be32 nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *res, @@ -85,8 +83,11 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, res = htonl(NFS4ERR_BADHANDLE); inode = nfs_delegation_find_inode(cps->clp, &args->fh); - if (inode == NULL) + if (inode == NULL) { + trace_nfs4_cb_recall(cps->clp, &args->fh, NULL, + &args->stateid, -ntohl(res)); goto out; + } /* Set up a helper thread to actually return the delegation */ switch (nfs_async_inode_return_delegation(inode, &args->stateid)) { case 0: @@ -98,7 +99,8 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, default: res = htonl(NFS4ERR_RESOURCE); } - trace_nfs4_recall_delegation(inode, -ntohl(res)); + trace_nfs4_cb_recall(cps->clp, &args->fh, inode, + &args->stateid, -ntohl(res)); iput(inode); out: dprintk("%s: exit with status = %d\n", __func__, ntohl(res)); @@ -162,6 +164,22 @@ static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp, return lo; } +/* + * Enforce RFC5661 section 12.5.5.2.1. (Layout Recall and Return Sequencing) + */ +static bool pnfs_check_stateid_sequence(struct pnfs_layout_hdr *lo, + const nfs4_stateid *new) +{ + u32 oldseq, newseq; + + oldseq = be32_to_cpu(lo->plh_stateid.seqid); + newseq = be32_to_cpu(new->seqid); + + if (newseq > oldseq + 1) + return false; + return true; +} + static u32 initiate_file_draining(struct nfs_client *clp, struct cb_layoutrecallargs *args) { @@ -171,34 +189,52 @@ static u32 initiate_file_draining(struct nfs_client *clp, LIST_HEAD(free_me_list); lo = get_layout_by_fh(clp, &args->cbl_fh, &args->cbl_stateid); - if (!lo) + if (!lo) { + trace_nfs4_cb_layoutrecall_file(clp, &args->cbl_fh, NULL, + &args->cbl_stateid, -rv); goto out; + } ino = lo->plh_inode; spin_lock(&ino->i_lock); + if (!pnfs_check_stateid_sequence(lo, &args->cbl_stateid)) { + rv = NFS4ERR_DELAY; + goto unlock; + } pnfs_set_layout_stateid(lo, &args->cbl_stateid, true); spin_unlock(&ino->i_lock); pnfs_layoutcommit_inode(ino, false); spin_lock(&ino->i_lock); - if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) || - pnfs_mark_matching_lsegs_invalid(lo, &free_me_list, - &args->cbl_range)) { + /* + * Enforce RFC5661 Section 12.5.5.2.1.5 (Bulk Recall and Return) + */ + if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) { rv = NFS4ERR_DELAY; goto unlock; } + if (pnfs_mark_matching_lsegs_return(lo, &free_me_list, + &args->cbl_range)) { + rv = NFS4_OK; + goto unlock; + } + if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) { NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, &args->cbl_range); } + pnfs_mark_layout_returned_if_empty(lo); unlock: spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&free_me_list); + /* Free all lsegs that are attached to commit buckets */ + nfs_commit_inode(ino, 0); pnfs_put_layout_hdr(lo); - trace_nfs4_cb_layoutrecall_inode(clp, &args->cbl_fh, ino, -rv); + trace_nfs4_cb_layoutrecall_file(clp, &args->cbl_fh, ino, + &args->cbl_stateid, -rv); iput(ino); out: return rv; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 6b1697a01dde..646cdac73488 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -18,19 +18,21 @@ #include "internal.h" #include "nfs4session.h" -#define CB_OP_TAGLEN_MAXSZ (512) -#define CB_OP_HDR_RES_MAXSZ (2 + CB_OP_TAGLEN_MAXSZ) -#define CB_OP_GETATTR_BITMAP_MAXSZ (4) -#define CB_OP_GETATTR_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ + \ - CB_OP_GETATTR_BITMAP_MAXSZ + \ - 2 + 2 + 3 + 3) -#define CB_OP_RECALL_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) +#define CB_OP_TAGLEN_MAXSZ (512) +#define CB_OP_HDR_RES_MAXSZ (2 * 4) // opcode, status +#define CB_OP_GETATTR_BITMAP_MAXSZ (4 * 4) // bitmap length, 3 bitmaps +#define CB_OP_GETATTR_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ + \ + CB_OP_GETATTR_BITMAP_MAXSZ + \ + /* change, size, ctime, mtime */\ + (2 + 2 + 3 + 3) * 4) +#define CB_OP_RECALL_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) #if defined(CONFIG_NFS_V4_1) #define CB_OP_LAYOUTRECALL_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) #define CB_OP_DEVICENOTIFY_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) #define CB_OP_SEQUENCE_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ + \ - 4 + 1 + 3) + NFS4_MAX_SESSIONID_LEN + \ + (1 + 3) * 4) // seqid, 3 slotids #define CB_OP_RECALLANY_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) #define CB_OP_RECALLSLOT_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) #endif /* CONFIG_NFS_V4_1 */ @@ -157,7 +159,7 @@ static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound if (unlikely(status != 0)) return status; /* We do not like overly long tags! */ - if (hdr->taglen > CB_OP_TAGLEN_MAXSZ - 12) { + if (hdr->taglen > CB_OP_TAGLEN_MAXSZ) { printk("NFS: NFSv4 CALLBACK %s: client sent tag of length %u\n", __func__, hdr->taglen); return htonl(NFS4ERR_RESOURCE); @@ -198,7 +200,6 @@ static __be32 decode_getattr_args(struct svc_rqst *rqstp, struct xdr_stream *xdr status = decode_fh(xdr, &args->fh); if (unlikely(status != 0)) goto out; - args->addr = svc_addr(rqstp); status = decode_bitmap(xdr, args->bitmap); out: dprintk("%s: exit with status = %d\n", __func__, ntohl(status)); @@ -210,7 +211,6 @@ static __be32 decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, __be32 *p; __be32 status; - args->addr = svc_addr(rqstp); status = decode_stateid(xdr, &args->stateid); if (unlikely(status != 0)) goto out; @@ -236,7 +236,6 @@ static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp, __be32 status = 0; uint32_t iomode; - args->cbl_addr = svc_addr(rqstp); p = read_buf(xdr, 4 * sizeof(uint32_t)); if (unlikely(p == NULL)) { status = htonl(NFS4ERR_BADXDR); @@ -383,13 +382,12 @@ static __be32 decode_sessionid(struct xdr_stream *xdr, struct nfs4_sessionid *sid) { __be32 *p; - int len = NFS4_MAX_SESSIONID_LEN; - p = read_buf(xdr, len); + p = read_buf(xdr, NFS4_MAX_SESSIONID_LEN); if (unlikely(p == NULL)) return htonl(NFS4ERR_RESOURCE); - memcpy(sid->data, p, len); + memcpy(sid->data, p, NFS4_MAX_SESSIONID_LEN); return 0; } @@ -500,7 +498,6 @@ static __be32 decode_recallany_args(struct svc_rqst *rqstp, uint32_t bitmap[2]; __be32 *p, status; - args->craa_addr = svc_addr(rqstp); p = read_buf(xdr, 4); if (unlikely(p == NULL)) return htonl(NFS4ERR_BADXDR); @@ -519,7 +516,6 @@ static __be32 decode_recallslot_args(struct svc_rqst *rqstp, { __be32 *p; - args->crsa_addr = svc_addr(rqstp); p = read_buf(xdr, 4); if (unlikely(p == NULL)) return htonl(NFS4ERR_BADXDR); @@ -684,13 +680,12 @@ static __be32 encode_sessionid(struct xdr_stream *xdr, const struct nfs4_sessionid *sid) { __be32 *p; - int len = NFS4_MAX_SESSIONID_LEN; - p = xdr_reserve_space(xdr, len); + p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN); if (unlikely(p == NULL)) return htonl(NFS4ERR_RESOURCE); - memcpy(p, sid, len); + memcpy(p, sid, NFS4_MAX_SESSIONID_LEN); return 0; } @@ -704,7 +699,9 @@ static __be32 encode_cb_sequence_res(struct svc_rqst *rqstp, if (unlikely(status != 0)) goto out; - encode_sessionid(xdr, &res->csr_sessionid); + status = encode_sessionid(xdr, &res->csr_sessionid); + if (status) + goto out; p = xdr_reserve_space(xdr, 4 * sizeof(uint32_t)); if (unlikely(p == NULL)) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 57c5a02f6213..d6d5d2a48e83 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -764,6 +764,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, server->time_delta = fsinfo->time_delta; + server->clone_blksize = fsinfo->clone_blksize; /* We're airborne Set socket buffersize */ rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100); } diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index be806ead7f4d..5166adcfc0fb 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -721,14 +721,12 @@ int nfs_async_inode_return_delegation(struct inode *inode, struct nfs_client *clp = server->nfs_client; struct nfs_delegation *delegation; - filemap_flush(inode->i_mapping); - rcu_read_lock(); delegation = rcu_dereference(NFS_I(inode)->delegation); if (delegation == NULL) goto out_enoent; - - if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) + if (stateid != NULL && + !clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) goto out_enoent; nfs_mark_return_delegation(server, delegation); rcu_read_unlock(); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 3d8e4ffa0a33..c82a21228a34 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1714,9 +1714,6 @@ nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) dfprintk(VFS, "NFS: mknod(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); - if (!new_valid_dev(rdev)) - return -EINVAL; - attr.ia_mode = mode; attr.ia_valid = ATTR_MODE; @@ -1897,15 +1894,14 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) attr.ia_mode = S_IFLNK | S_IRWXUGO; attr.ia_valid = ATTR_MODE; - page = alloc_page(GFP_HIGHUSER); + page = alloc_page(GFP_USER); if (!page) return -ENOMEM; - kaddr = kmap_atomic(page); + kaddr = page_address(page); memcpy(kaddr, symname, pathlen); if (pathlen < PAGE_SIZE) memset(kaddr + pathlen, 0, PAGE_SIZE - pathlen); - kunmap_atomic(kaddr); trace_nfs_symlink_enter(dir, dentry); error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr); @@ -2435,6 +2431,20 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags) } EXPORT_SYMBOL_GPL(nfs_may_open); +static int nfs_execute_ok(struct inode *inode, int mask) +{ + struct nfs_server *server = NFS_SERVER(inode); + int ret; + + if (mask & MAY_NOT_BLOCK) + ret = nfs_revalidate_inode_rcu(server, inode); + else + ret = nfs_revalidate_inode(server, inode); + if (ret == 0 && !execute_ok(inode)) + ret = -EACCES; + return ret; +} + int nfs_permission(struct inode *inode, int mask) { struct rpc_cred *cred; @@ -2452,6 +2462,9 @@ int nfs_permission(struct inode *inode, int mask) case S_IFLNK: goto out; case S_IFREG: + if ((mask & MAY_OPEN) && + nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN)) + return 0; break; case S_IFDIR: /* @@ -2484,8 +2497,8 @@ force_lookup: res = PTR_ERR(cred); } out: - if (!res && (mask & MAY_EXEC) && !execute_ok(inode)) - res = -EACCES; + if (!res && (mask & MAY_EXEC)) + res = nfs_execute_ok(inode, mask); dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n", inode->i_sb->s_id, inode->i_ino, mask, res); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 4b1d08f56aba..7ab7ec9f4eed 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -117,12 +117,6 @@ static inline int put_dreq(struct nfs_direct_req *dreq) return atomic_dec_and_test(&dreq->io_count); } -void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq) -{ - dreq->flags = NFS_ODIRECT_RESCHED_WRITES; -} -EXPORT_SYMBOL_GPL(nfs_direct_set_resched_writes); - static void nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr) { @@ -670,6 +664,10 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) req = nfs_list_entry(reqs.next); nfs_direct_setup_mirroring(dreq, &desc, req); + if (desc.pg_error < 0) { + list_splice_init(&reqs, &failed); + goto out_failed; + } list_for_each_entry_safe(req, tmp, &reqs, wb_list) { if (!nfs_pageio_add_request(&desc, req)) { @@ -677,13 +675,17 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) nfs_list_add_request(req, &failed); spin_lock(cinfo.lock); dreq->flags = 0; - dreq->error = -EIO; + if (desc.pg_error < 0) + dreq->error = desc.pg_error; + else + dreq->error = -EIO; spin_unlock(cinfo.lock); } nfs_release_request(req); } nfs_pageio_complete(&desc); +out_failed: while (!list_empty(&failed)) { req = nfs_list_entry(failed.next); nfs_list_remove_request(req); @@ -727,14 +729,20 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) nfs_direct_write_complete(dreq, data->inode); } -static void nfs_direct_error_cleanup(struct nfs_inode *nfsi) +static void nfs_direct_resched_write(struct nfs_commit_info *cinfo, + struct nfs_page *req) { - /* There is no lock to clear */ + struct nfs_direct_req *dreq = cinfo->dreq; + + spin_lock(&dreq->lock); + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&dreq->lock); + nfs_mark_request_commit(req, NULL, cinfo, 0); } static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops = { .completion = nfs_direct_commit_complete, - .error_cleanup = nfs_direct_error_cleanup, + .resched_write = nfs_direct_resched_write, }; static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) @@ -839,10 +847,25 @@ static void nfs_write_sync_pgio_error(struct list_head *head) } } +static void nfs_direct_write_reschedule_io(struct nfs_pgio_header *hdr) +{ + struct nfs_direct_req *dreq = hdr->dreq; + + spin_lock(&dreq->lock); + if (dreq->error == 0) { + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + /* fake unstable write to let common nfs resend pages */ + hdr->verf.committed = NFS_UNSTABLE; + hdr->good_bytes = hdr->args.count; + } + spin_unlock(&dreq->lock); +} + static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = { .error_cleanup = nfs_write_sync_pgio_error, .init_hdr = nfs_direct_pgio_init, .completion = nfs_direct_write_completion, + .reschedule_io = nfs_direct_write_reschedule_io, }; @@ -900,6 +923,11 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, } nfs_direct_setup_mirroring(dreq, &desc, req); + if (desc.pg_error < 0) { + nfs_free_request(req); + result = desc.pg_error; + break; + } nfs_lock_request(req); req->wb_index = pos >> PAGE_SHIFT; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 37f639d50af5..4ef8f5addcad 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -473,8 +473,8 @@ static int nfs_release_page(struct page *page, gfp_t gfp) dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page); /* Always try to initiate a 'commit' if relevant, but only - * wait for it if __GFP_WAIT is set. Even then, only wait 1 - * second and only if the 'bdi' is not congested. + * wait for it if the caller allows blocking. Even then, + * only wait 1 second and only if the 'bdi' is not congested. * Waiting indefinitely can cause deadlocks when the NFS * server is on this machine, when a new TCP connection is * needed and in other rare cases. There is no particular @@ -484,7 +484,7 @@ static int nfs_release_page(struct page *page, gfp_t gfp) if (mapping) { struct nfs_server *nfss = NFS_SERVER(mapping->host); nfs_commit_inode(mapping->host, 0); - if ((gfp & __GFP_WAIT) && + if (gfpflags_allow_blocking(gfp) && !bdi_write_congested(&nfss->backing_dev_info)) { wait_on_page_bit_killable_timeout(page, PG_private, HZ); @@ -514,7 +514,7 @@ static void nfs_check_dirty_writeback(struct page *page, * 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)) { + if (atomic_read(&nfsi->commit_info.rpcs_out)) { *writeback = true; return; } @@ -545,7 +545,7 @@ static int nfs_launder_page(struct page *page) inode->i_ino, (long long)page_offset(page)); nfs_fscache_wait_on_page_write(nfsi, page); - return nfs_wb_page(inode, page); + return nfs_wb_launder_page(inode, page); } static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, @@ -756,7 +756,7 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) l_ctx = nfs_get_lock_context(nfs_file_open_context(filp)); if (!IS_ERR(l_ctx)) { - status = nfs_iocounter_wait(&l_ctx->io_count); + status = nfs_iocounter_wait(l_ctx); nfs_put_lock_context(l_ctx); if (status < 0) return status; diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 02ec07973bc4..bb1f4e7a3270 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -202,6 +202,7 @@ static int filelayout_async_handle_error(struct rpc_task *task, task->tk_status); nfs4_mark_deviceid_unavailable(devid); pnfs_error_mark_layout_for_return(inode, lseg); + pnfs_set_lo_fail(lseg); rpc_wake_up(&tbl->slot_tbl_waitq); /* fall through */ default: @@ -883,13 +884,19 @@ static void filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { - if (!pgio->pg_lseg) + if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, NFS4_MAX_UINT64, IOMODE_READ, GFP_KERNEL); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + return; + } + } /* If no lseg, fall back to read through mds */ if (pgio->pg_lseg == NULL) nfs_pageio_reset_read_mds(pgio); @@ -902,13 +909,20 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_commit_info cinfo; int status; - if (!pgio->pg_lseg) + if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, NFS4_MAX_UINT64, IOMODE_RW, GFP_NOFS); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + return; + } + } + /* If no lseg, fall back to write through mds */ if (pgio->pg_lseg == NULL) goto out_mds; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index fbc5a56de875..6594e9f903a0 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -145,7 +145,7 @@ static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1, return false; for (i = 0; i < m1->fh_versions_cnt; i++) { bool found_fh = false; - for (j = 0; j < m2->fh_versions_cnt; i++) { + for (j = 0; j < m2->fh_versions_cnt; j++) { if (nfs_compare_fh(&m1->fh_versions[i], &m2->fh_versions[j]) == 0) { found_fh = true; @@ -339,6 +339,19 @@ static void ff_layout_sort_mirrors(struct nfs4_ff_layout_segment *fls) } } +static void ff_layout_mark_devices_valid(struct nfs4_ff_layout_segment *fls) +{ + struct nfs4_deviceid_node *node; + int i; + + if (!(fls->flags & FF_FLAGS_NO_IO_THRU_MDS)) + return; + for (i = 0; i < fls->mirror_array_cnt; i++) { + node = &fls->mirror_array[i]->mirror_ds->id_node; + clear_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags); + } +} + static struct pnfs_layout_segment * ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, struct nfs4_layoutget_res *lgr, @@ -492,13 +505,22 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, } p = xdr_inline_decode(&stream, 4); - if (p) - fls->flags = be32_to_cpup(p); + if (!p) + goto out_sort_mirrors; + fls->flags = be32_to_cpup(p); + + p = xdr_inline_decode(&stream, 4); + if (!p) + goto out_sort_mirrors; + for (i=0; i < fls->mirror_array_cnt; i++) + fls->mirror_array[i]->report_interval = be32_to_cpup(p); +out_sort_mirrors: ff_layout_sort_mirrors(fls); rc = ff_layout_check_layout(lgr); if (rc) goto out_err_free; + ff_layout_mark_devices_valid(fls); ret = &fls->generic_hdr; dprintk("<-- %s (success)\n", __func__); @@ -589,7 +611,9 @@ nfs4_ff_layoutstat_start_io(struct nfs4_ff_layout_mirror *mirror, mirror->start_time = now; if (ktime_equal(mirror->last_report_time, notime)) mirror->last_report_time = now; - if (layoutstats_timer != 0) + if (mirror->report_interval != 0) + report_interval = (s64)mirror->report_interval * 1000LL; + else if (layoutstats_timer != 0) report_interval = (s64)layoutstats_timer * 1000LL; if (ktime_to_ms(ktime_sub(now, mirror->last_report_time)) >= report_interval) { @@ -741,17 +765,17 @@ ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg, } static struct nfs4_pnfs_ds * -ff_layout_choose_best_ds_for_read(struct nfs_pageio_descriptor *pgio, +ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg, + int start_idx, int *best_idx) { - struct nfs4_ff_layout_segment *fls; + struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg); struct nfs4_pnfs_ds *ds; int idx; - fls = FF_LAYOUT_LSEG(pgio->pg_lseg); /* mirrors are sorted by efficiency */ - for (idx = 0; idx < fls->mirror_array_cnt; idx++) { - ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, idx, false); + for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) { + ds = nfs4_ff_layout_prepare_ds(lseg, idx, false); if (ds) { *best_idx = idx; return ds; @@ -771,18 +795,24 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, int ds_idx; /* Use full layout for now */ - if (!pgio->pg_lseg) + if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, NFS4_MAX_UINT64, IOMODE_READ, GFP_KERNEL); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + return; + } + } /* If no lseg, fall back to read through mds */ if (pgio->pg_lseg == NULL) goto out_mds; - ds = ff_layout_choose_best_ds_for_read(pgio, &ds_idx); + ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx); if (!ds) goto out_mds; mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx); @@ -811,13 +841,19 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, int i; int status; - if (!pgio->pg_lseg) + if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, NFS4_MAX_UINT64, IOMODE_RW, GFP_NOFS); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + return; + } + } /* If no lseg, fall back to write through mds */ if (pgio->pg_lseg == NULL) goto out_mds; @@ -853,18 +889,25 @@ static unsigned int ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { - if (!pgio->pg_lseg) + if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, NFS4_MAX_UINT64, IOMODE_RW, GFP_NOFS); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + goto out; + } + } if (pgio->pg_lseg) return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg); /* no lseg means that pnfs is not in use, so no mirroring here */ nfs_pageio_reset_write_mds(pgio); +out: return 1; } @@ -898,18 +941,7 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs) hdr->args.count, (unsigned long long)hdr->args.offset); - if (!hdr->dreq) { - struct nfs_open_context *ctx; - - ctx = nfs_list_entry(hdr->pages.next)->wb_context; - set_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags); - hdr->completion_ops->error_cleanup(&hdr->pages); - } else { - nfs_direct_set_resched_writes(hdr->dreq); - /* fake unstable write to let common nfs resend pages */ - hdr->verf.committed = NFS_UNSTABLE; - hdr->good_bytes = hdr->args.count; - } + hdr->completion_ops->reschedule_io(hdr); return; } @@ -1035,7 +1067,8 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, rpc_wake_up(&tbl->slot_tbl_waitq); /* fall through */ default: - if (ff_layout_has_available_ds(lseg)) + if (ff_layout_no_fallback_to_mds(lseg) || + ff_layout_has_available_ds(lseg)) return -NFS4ERR_RESET_TO_PNFS; reset: dprintk("%s Retry through MDS. Error %d\n", __func__, @@ -1086,7 +1119,7 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task, return -NFS4ERR_RESET_TO_PNFS; out_retry: task->tk_status = 0; - rpc_restart_call(task); + rpc_restart_call_prepare(task); rpc_delay(task, NFS_JUKEBOX_RETRY_TIME); return -EAGAIN; } @@ -1144,6 +1177,14 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, } } + switch (status) { + case NFS4ERR_DELAY: + case NFS4ERR_GRACE: + return; + default: + break; + } + mirror = FF_LAYOUT_COMP(lseg, idx); err = ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), mirror, offset, length, status, opnum, @@ -1153,7 +1194,6 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, } /* NFS_PROTO call done callback routines */ - static int ff_layout_read_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr) { @@ -1171,6 +1211,10 @@ static int ff_layout_read_done_cb(struct rpc_task *task, switch (err) { case -NFS4ERR_RESET_TO_PNFS: + if (ff_layout_choose_best_ds_for_read(hdr->lseg, + hdr->pgio_mirror_idx + 1, + &hdr->pgio_mirror_idx)) + goto out_eagain; set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &hdr->lseg->pls_layout->plh_flags); pnfs_read_resend_pnfs(hdr); @@ -1179,11 +1223,13 @@ static int ff_layout_read_done_cb(struct rpc_task *task, ff_layout_reset_read(hdr); return task->tk_status; case -EAGAIN: - rpc_restart_call_prepare(task); - return -EAGAIN; + goto out_eagain; } return 0; +out_eagain: + rpc_restart_call_prepare(task); + return -EAGAIN; } static bool @@ -1222,14 +1268,31 @@ ff_layout_reset_to_mds(struct pnfs_layout_segment *lseg, int idx) return ff_layout_test_devid_unavailable(node); } -static int ff_layout_read_prepare_common(struct rpc_task *task, - struct nfs_pgio_header *hdr) +static void ff_layout_read_record_layoutstats_start(struct rpc_task *task, + struct nfs_pgio_header *hdr) { + if (test_and_set_bit(NFS_IOHDR_STAT, &hdr->flags)) + return; nfs4_ff_layout_stat_io_start_read(hdr->inode, FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), hdr->args.count, task->tk_start); +} + +static void ff_layout_read_record_layoutstats_done(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (!test_and_clear_bit(NFS_IOHDR_STAT, &hdr->flags)) + return; + nfs4_ff_layout_stat_io_end_read(task, + FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), + hdr->args.count, + hdr->res.count); +} +static int ff_layout_read_prepare_common(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { rpc_exit(task, -EIO); return -EIO; @@ -1245,6 +1308,7 @@ static int ff_layout_read_prepare_common(struct rpc_task *task, } hdr->pgio_done_cb = ff_layout_read_done_cb; + ff_layout_read_record_layoutstats_start(task, hdr); return 0; } @@ -1303,10 +1367,6 @@ static void ff_layout_read_call_done(struct rpc_task *task, void *data) dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status); - nfs4_ff_layout_stat_io_end_read(task, - FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), - hdr->args.count, hdr->res.count); - if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && task->tk_status == 0) { nfs4_sequence_done(task, &hdr->res.seq_res); @@ -1321,10 +1381,20 @@ static void ff_layout_read_count_stats(struct rpc_task *task, void *data) { struct nfs_pgio_header *hdr = data; + ff_layout_read_record_layoutstats_done(task, hdr); rpc_count_iostats_metrics(task, &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_READ]); } +static void ff_layout_read_release(void *data) +{ + struct nfs_pgio_header *hdr = data; + + ff_layout_read_record_layoutstats_done(&hdr->task, hdr); + pnfs_generic_rw_release(data); +} + + static int ff_layout_write_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr) { @@ -1342,15 +1412,12 @@ static int ff_layout_write_done_cb(struct rpc_task *task, switch (err) { case -NFS4ERR_RESET_TO_PNFS: - pnfs_set_retry_layoutget(hdr->lseg->pls_layout); ff_layout_reset_write(hdr, true); return task->tk_status; case -NFS4ERR_RESET_TO_MDS: - pnfs_clear_retry_layoutget(hdr->lseg->pls_layout); ff_layout_reset_write(hdr, false); return task->tk_status; case -EAGAIN: - rpc_restart_call_prepare(task); return -EAGAIN; } @@ -1382,11 +1449,9 @@ static int ff_layout_commit_done_cb(struct rpc_task *task, switch (err) { case -NFS4ERR_RESET_TO_PNFS: - pnfs_set_retry_layoutget(data->lseg->pls_layout); pnfs_generic_prepare_to_resend_writes(data); return -EAGAIN; case -NFS4ERR_RESET_TO_MDS: - pnfs_clear_retry_layoutget(data->lseg->pls_layout); pnfs_generic_prepare_to_resend_writes(data); return -EAGAIN; case -EAGAIN: @@ -1401,14 +1466,31 @@ static int ff_layout_commit_done_cb(struct rpc_task *task, return 0; } -static int ff_layout_write_prepare_common(struct rpc_task *task, - struct nfs_pgio_header *hdr) +static void ff_layout_write_record_layoutstats_start(struct rpc_task *task, + struct nfs_pgio_header *hdr) { + if (test_and_set_bit(NFS_IOHDR_STAT, &hdr->flags)) + return; nfs4_ff_layout_stat_io_start_write(hdr->inode, FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), hdr->args.count, task->tk_start); +} +static void ff_layout_write_record_layoutstats_done(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (!test_and_clear_bit(NFS_IOHDR_STAT, &hdr->flags)) + return; + nfs4_ff_layout_stat_io_end_write(task, + FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), + hdr->args.count, hdr->res.count, + hdr->res.verf->committed); +} + +static int ff_layout_write_prepare_common(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { rpc_exit(task, -EIO); return -EIO; @@ -1425,6 +1507,7 @@ static int ff_layout_write_prepare_common(struct rpc_task *task, return -EAGAIN; } + ff_layout_write_record_layoutstats_start(task, hdr); return 0; } @@ -1460,11 +1543,6 @@ static void ff_layout_write_call_done(struct rpc_task *task, void *data) { struct nfs_pgio_header *hdr = data; - nfs4_ff_layout_stat_io_end_write(task, - FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), - hdr->args.count, hdr->res.count, - hdr->res.verf->committed); - if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && task->tk_status == 0) { nfs4_sequence_done(task, &hdr->res.seq_res); @@ -1479,18 +1557,53 @@ static void ff_layout_write_count_stats(struct rpc_task *task, void *data) { struct nfs_pgio_header *hdr = data; + ff_layout_write_record_layoutstats_done(task, hdr); rpc_count_iostats_metrics(task, &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_WRITE]); } -static void ff_layout_commit_prepare_common(struct rpc_task *task, +static void ff_layout_write_release(void *data) +{ + struct nfs_pgio_header *hdr = data; + + ff_layout_write_record_layoutstats_done(&hdr->task, hdr); + pnfs_generic_rw_release(data); +} + +static void ff_layout_commit_record_layoutstats_start(struct rpc_task *task, struct nfs_commit_data *cdata) { + if (test_and_set_bit(NFS_IOHDR_STAT, &cdata->flags)) + return; nfs4_ff_layout_stat_io_start_write(cdata->inode, FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index), 0, task->tk_start); } +static void ff_layout_commit_record_layoutstats_done(struct rpc_task *task, + struct nfs_commit_data *cdata) +{ + struct nfs_page *req; + __u64 count = 0; + + if (!test_and_clear_bit(NFS_IOHDR_STAT, &cdata->flags)) + return; + + if (task->tk_status == 0) { + list_for_each_entry(req, &cdata->pages, wb_list) + count += req->wb_bytes; + } + nfs4_ff_layout_stat_io_end_write(task, + FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index), + count, count, NFS_FILE_SYNC); +} + +static void ff_layout_commit_prepare_common(struct rpc_task *task, + struct nfs_commit_data *cdata) +{ + ff_layout_commit_record_layoutstats_start(task, cdata); +} + static void ff_layout_commit_prepare_v3(struct rpc_task *task, void *data) { ff_layout_commit_prepare_common(task, data); @@ -1511,19 +1624,6 @@ static void ff_layout_commit_prepare_v4(struct rpc_task *task, void *data) static void ff_layout_commit_done(struct rpc_task *task, void *data) { - struct nfs_commit_data *cdata = data; - struct nfs_page *req; - __u64 count = 0; - - if (task->tk_status == 0) { - list_for_each_entry(req, &cdata->pages, wb_list) - count += req->wb_bytes; - } - - nfs4_ff_layout_stat_io_end_write(task, - FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index), - count, count, NFS_FILE_SYNC); - pnfs_generic_write_commit_done(task, data); } @@ -1531,50 +1631,59 @@ static void ff_layout_commit_count_stats(struct rpc_task *task, void *data) { struct nfs_commit_data *cdata = data; + ff_layout_commit_record_layoutstats_done(task, cdata); rpc_count_iostats_metrics(task, &NFS_CLIENT(cdata->inode)->cl_metrics[NFSPROC4_CLNT_COMMIT]); } +static void ff_layout_commit_release(void *data) +{ + struct nfs_commit_data *cdata = data; + + ff_layout_commit_record_layoutstats_done(&cdata->task, cdata); + pnfs_generic_commit_release(data); +} + static const struct rpc_call_ops ff_layout_read_call_ops_v3 = { .rpc_call_prepare = ff_layout_read_prepare_v3, .rpc_call_done = ff_layout_read_call_done, .rpc_count_stats = ff_layout_read_count_stats, - .rpc_release = pnfs_generic_rw_release, + .rpc_release = ff_layout_read_release, }; static const struct rpc_call_ops ff_layout_read_call_ops_v4 = { .rpc_call_prepare = ff_layout_read_prepare_v4, .rpc_call_done = ff_layout_read_call_done, .rpc_count_stats = ff_layout_read_count_stats, - .rpc_release = pnfs_generic_rw_release, + .rpc_release = ff_layout_read_release, }; static const struct rpc_call_ops ff_layout_write_call_ops_v3 = { .rpc_call_prepare = ff_layout_write_prepare_v3, .rpc_call_done = ff_layout_write_call_done, .rpc_count_stats = ff_layout_write_count_stats, - .rpc_release = pnfs_generic_rw_release, + .rpc_release = ff_layout_write_release, }; static const struct rpc_call_ops ff_layout_write_call_ops_v4 = { .rpc_call_prepare = ff_layout_write_prepare_v4, .rpc_call_done = ff_layout_write_call_done, .rpc_count_stats = ff_layout_write_count_stats, - .rpc_release = pnfs_generic_rw_release, + .rpc_release = ff_layout_write_release, }; static const struct rpc_call_ops ff_layout_commit_call_ops_v3 = { .rpc_call_prepare = ff_layout_commit_prepare_v3, .rpc_call_done = ff_layout_commit_done, .rpc_count_stats = ff_layout_commit_count_stats, - .rpc_release = pnfs_generic_commit_release, + .rpc_release = ff_layout_commit_release, }; static const struct rpc_call_ops ff_layout_commit_call_ops_v4 = { .rpc_call_prepare = ff_layout_commit_prepare_v4, .rpc_call_done = ff_layout_commit_done, .rpc_count_stats = ff_layout_commit_count_stats, - .rpc_release = pnfs_generic_commit_release, + .rpc_release = ff_layout_commit_release, }; static enum pnfs_try_status diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h index 68cc0d9828f9..dd353bb7dc0a 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.h +++ b/fs/nfs/flexfilelayout/flexfilelayout.h @@ -10,6 +10,7 @@ #define FS_NFS_NFS4FLEXFILELAYOUT_H #define FF_FLAGS_NO_LAYOUTCOMMIT 1 +#define FF_FLAGS_NO_IO_THRU_MDS 2 #include "../pnfs.h" @@ -84,6 +85,7 @@ struct nfs4_ff_layout_mirror { struct nfs4_ff_layoutstat write_stat; ktime_t start_time; ktime_t last_report_time; + u32 report_interval; }; struct nfs4_ff_layout_segment { @@ -146,6 +148,12 @@ FF_LAYOUT_MIRROR_COUNT(struct pnfs_layout_segment *lseg) } static inline bool +ff_layout_no_fallback_to_mds(struct pnfs_layout_segment *lseg) +{ + return FF_LAYOUT_LSEG(lseg)->flags & FF_FLAGS_NO_IO_THRU_MDS; +} + +static inline bool ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node) { return nfs4_test_deviceid_unavailable(node); diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index e125e55de86d..bd0327541366 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -429,22 +429,14 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, mirror, lseg->pls_range.offset, lseg->pls_range.length, NFS4ERR_NXIO, OP_ILLEGAL, GFP_NOIO); - if (fail_return) { - pnfs_error_mark_layout_for_return(ino, lseg); - if (ff_layout_has_available_ds(lseg)) - pnfs_set_retry_layoutget(lseg->pls_layout); - else - pnfs_clear_retry_layoutget(lseg->pls_layout); - - } else { + if (!fail_return) { if (ff_layout_has_available_ds(lseg)) set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lseg->pls_layout->plh_flags); - else { + else pnfs_error_mark_layout_for_return(ino, lseg); - pnfs_clear_retry_layoutget(lseg->pls_layout); - } - } + } else + pnfs_error_mark_layout_for_return(ino, lseg); } out_update_creds: if (ff_layout_update_mirror_cred(mirror, ds)) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 326d9e10d833..c11e855e0e18 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -71,19 +71,25 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr) return nfs_fileid_to_ino_t(fattr->fileid); } -/** - * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks - * @word: long word containing the bit lock - */ -int nfs_wait_bit_killable(struct wait_bit_key *key) +static int nfs_wait_killable(int mode) { - if (fatal_signal_pending(current)) - return -ERESTARTSYS; freezable_schedule_unsafe(); + if (signal_pending_state(mode, current)) + return -ERESTARTSYS; return 0; } + +int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) +{ + return nfs_wait_killable(mode); +} EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); +int nfs_wait_atomic_killable(atomic_t *p) +{ + return nfs_wait_killable(TASK_KILLABLE); +} + /** * nfs_compat_user_ino64 - returns the user-visible inode number * @fileid: 64-bit fileid @@ -408,9 +414,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st inode->i_fop = NULL; inode->i_flags |= S_AUTOMOUNT; } - } else if (S_ISLNK(inode->i_mode)) + } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &nfs_symlink_inode_operations; - else + inode_nohighmem(inode); + } else init_special_inode(inode, inode->i_mode, fattr->rdev); memset(&inode->i_atime, 0, sizeof(inode->i_atime)); @@ -618,7 +625,10 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC); nfs_vmtruncate(inode, attr->ia_size); } - nfs_update_inode(inode, fattr); + if (fattr->valid) + nfs_update_inode(inode, fattr); + else + NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_setattr_update_inode); @@ -696,7 +706,7 @@ static void nfs_init_lock_context(struct nfs_lock_context *l_ctx) l_ctx->lockowner.l_owner = current->files; l_ctx->lockowner.l_pid = current->tgid; INIT_LIST_HEAD(&l_ctx->list); - nfs_iocounter_init(&l_ctx->io_count); + atomic_set(&l_ctx->io_count, 0); } static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx) @@ -909,6 +919,12 @@ void nfs_file_clear_open_context(struct file *filp) if (ctx) { struct inode *inode = d_inode(ctx->dentry); + /* + * We fatal error on write before. Try to writeback + * every page again. + */ + if (ctx->error < 0) + invalidate_inode_pages2(inode->i_mapping); filp->private_data = NULL; spin_lock(&inode->i_lock); list_move_tail(&ctx->list, &NFS_I(inode)->open_files); @@ -1083,6 +1099,27 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode) || NFS_STALE(inode); } +int nfs_revalidate_mapping_rcu(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + unsigned long *bitlock = &nfsi->flags; + int ret = 0; + + if (IS_SWAPFILE(inode)) + goto out; + if (nfs_mapping_need_revalidate_inode(inode)) { + ret = -ECHILD; + goto out; + } + spin_lock(&inode->i_lock); + if (test_bit(NFS_INO_INVALIDATING, bitlock) || + (nfsi->cache_validity & NFS_INO_INVALID_DATA)) + ret = -ECHILD; + spin_unlock(&inode->i_lock); +out: + return ret; +} + /** * __nfs_revalidate_mapping - Revalidate the pagecache * @inode - pointer to host inode @@ -1638,6 +1675,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) unsigned long invalid = 0; unsigned long now = jiffies; unsigned long save_cache_validity; + bool cache_revalidated = true; dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n", __func__, inode->i_sb->s_id, inode->i_ino, @@ -1699,22 +1737,28 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_force_lookup_revalidate(inode); inode->i_version = fattr->change_attr; } - } else + } else { nfsi->cache_validity |= save_cache_validity; + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_MTIME) { memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); - } else if (server->caps & NFS_CAP_MTIME) + } else if (server->caps & NFS_CAP_MTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_CTIME) { memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); - } else if (server->caps & NFS_CAP_CTIME) + } else if (server->caps & NFS_CAP_CTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } /* Check if our cached file size is stale */ if (fattr->valid & NFS_ATTR_FATTR_SIZE) { @@ -1734,19 +1778,23 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) (long long)cur_isize, (long long)new_isize); } - } else + } else { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_ATIME) memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime)); - else if (server->caps & NFS_CAP_ATIME) + else if (server->caps & NFS_CAP_ATIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_MODE) { if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) { @@ -1755,36 +1803,42 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_mode = newmode; invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; } - } else if (server->caps & NFS_CAP_MODE) + } else if (server->caps & NFS_CAP_MODE) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_OWNER) { if (!uid_eq(inode->i_uid, fattr->uid)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_uid = fattr->uid; } - } else if (server->caps & NFS_CAP_OWNER) + } else if (server->caps & NFS_CAP_OWNER) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_GROUP) { if (!gid_eq(inode->i_gid, fattr->gid)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_gid = fattr->gid; } - } else if (server->caps & NFS_CAP_OWNER_GROUP) + } else if (server->caps & NFS_CAP_OWNER_GROUP) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_NLINK) { if (inode->i_nlink != fattr->nlink) { @@ -1793,19 +1847,22 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_DATA; set_nlink(inode, fattr->nlink); } - } else if (server->caps & NFS_CAP_NLINK) + } else if (server->caps & NFS_CAP_NLINK) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); - } - if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) + } else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; + else + cache_revalidated = false; /* Update attrtimeo value if we're out of the unstable period */ if (invalid & NFS_INO_INVALID_ATTR) { @@ -1815,16 +1872,24 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) /* Set barrier to be more recent than all outstanding updates */ nfsi->attr_gencount = nfs_inc_attr_generation_counter(); } else { - if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { - if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode)) - nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); + if (cache_revalidated) { + if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, + nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { + nfsi->attrtimeo <<= 1; + if (nfsi->attrtimeo > NFS_MAXATTRTIMEO(inode)) + nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); + } nfsi->attrtimeo_timestamp = now; } /* Set the barrier to be more recent than this fattr */ if ((long)fattr->gencount - (long)nfsi->attr_gencount > 0) nfsi->attr_gencount = fattr->gencount; } - invalid &= ~NFS_INO_INVALID_ATTR; + + /* Don't declare attrcache up to date if there were no attrs! */ + if (cache_revalidated) + invalid &= ~NFS_INO_INVALID_ATTR; + /* Don't invalidate the data if we were to blame */ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 56cfde26fb9c..4e8cc942336c 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -238,7 +238,7 @@ extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)); void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos); -int nfs_iocounter_wait(struct nfs_io_counter *c); +int nfs_iocounter_wait(struct nfs_lock_context *l_ctx); extern const struct nfs_pageio_ops nfs_pgio_rw_ops; struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *); @@ -252,18 +252,18 @@ void nfs_free_request(struct nfs_page *req); struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc); -static inline void nfs_iocounter_init(struct nfs_io_counter *c) -{ - c->flags = 0; - atomic_set(&c->io_count, 0); -} - static inline bool nfs_pgio_has_mirroring(struct nfs_pageio_descriptor *desc) { WARN_ON_ONCE(desc->pg_mirror_count < 1); return desc->pg_mirror_count > 1; } +static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1, + const struct nfs_open_context *ctx2) +{ + return ctx1->cred == ctx2->cred && ctx1->state == ctx2->state; +} + /* nfs2xdr.c */ extern struct rpc_procinfo nfs_procedures[]; extern int nfs2_decode_dirent(struct xdr_stream *, @@ -379,7 +379,8 @@ extern int nfs_drop_inode(struct inode *); extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); void nfs_zap_acl_cache(struct inode *inode); -extern int nfs_wait_bit_killable(struct wait_bit_key *key); +extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); +extern int nfs_wait_atomic_killable(atomic_t *p); /* super.c */ extern const struct super_operations nfs_sops; @@ -519,7 +520,6 @@ static inline void nfs_inode_dio_wait(struct inode *inode) inode_dio_wait(inode); } extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq); -extern void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq); /* nfs4proc.c */ extern void __nfs4_read_done_cb(struct nfs_pgio_header *); @@ -696,9 +696,32 @@ static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) { return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size); } +static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid) +{ + return ~crc32_le(0xFFFFFFFF, &stateid->other[0], + NFS4_STATEID_OTHER_SIZE); +} #else static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) { return 0; } +static inline u32 nfs_stateid_hash(nfs4_stateid *stateid) +{ + return 0; +} #endif + +static inline bool nfs_error_is_fatal(int err) +{ + switch (err) { + case -ERESTARTSYS: + case -EIO: + case -ENOSPC: + case -EROFS: + case -E2BIG: + return true; + default: + return false; + } +} diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 99a45283b9ee..09b190015df4 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -16,9 +16,7 @@ #include <linux/nfs_fs.h> #include "internal.h" -#ifdef NFS_DEBUG -# define NFSDBG_FACILITY NFSDBG_MOUNT -#endif +#define NFSDBG_FACILITY NFSDBG_MOUNT /* * Defined by RFC 1094, section A.3; and RFC 1813, section 5.1.4 diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 1ebe2fc7cda2..17c0fa1eccfa 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -284,12 +284,12 @@ nfs3_listxattr(struct dentry *dentry, char *data, size_t size) int error; error = nfs3_list_one_acl(inode, ACL_TYPE_ACCESS, - POSIX_ACL_XATTR_ACCESS, data, size, &result); + XATTR_NAME_POSIX_ACL_ACCESS, data, size, &result); if (error) return error; error = nfs3_list_one_acl(inode, ACL_TYPE_DEFAULT, - POSIX_ACL_XATTR_DEFAULT, data, size, &result); + XATTR_NAME_POSIX_ACL_DEFAULT, data, size, &result); if (error) return error; return result; diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index 814c1255f1d2..b587ccd31083 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -17,5 +17,6 @@ int nfs42_proc_deallocate(struct file *, loff_t, loff_t); loff_t nfs42_proc_llseek(struct file *, loff_t, int); int nfs42_proc_layoutstats_generic(struct nfs_server *, struct nfs42_layoutstat_data *); +int nfs42_proc_clone(struct file *, struct file *, loff_t, loff_t, loff_t); #endif /* __LINUX_FS_NFS_NFS4_2_H */ diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 0f020e4d8421..6e8174930a48 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -14,7 +14,7 @@ #include "pnfs.h" #include "internal.h" -#define NFSDBG_FACILITY NFSDBG_PNFS +#define NFSDBG_FACILITY NFSDBG_PROC static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file, fmode_t fmode) @@ -204,6 +204,8 @@ static void nfs42_layoutstat_done(struct rpc_task *task, void *calldata) { struct nfs42_layoutstat_data *data = calldata; + struct inode *inode = data->inode; + struct pnfs_layout_hdr *lo; if (!nfs4_sequence_done(task, &data->res.seq_res)) return; @@ -211,12 +213,35 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata) switch (task->tk_status) { case 0: break; + case -NFS4ERR_EXPIRED: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_OLD_STATEID: + case -NFS4ERR_BAD_STATEID: + spin_lock(&inode->i_lock); + lo = NFS_I(inode)->layout; + if (lo && nfs4_stateid_match(&data->args.stateid, + &lo->plh_stateid)) { + LIST_HEAD(head); + + /* + * Mark the bad layout state as invalid, then retry + * with the current stateid. + */ + set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); + pnfs_mark_matching_lsegs_invalid(lo, &head, NULL); + spin_unlock(&inode->i_lock); + pnfs_free_lseg_list(&head); + } else + spin_unlock(&inode->i_lock); + break; case -ENOTSUPP: case -EOPNOTSUPP: - NFS_SERVER(data->inode)->caps &= ~NFS_CAP_LAYOUTSTATS; + NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTSTATS; default: - dprintk("%s server returns %d\n", __func__, task->tk_status); + break; } + + dprintk("%s server returns %d\n", __func__, task->tk_status); } static void @@ -271,3 +296,75 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server, return PTR_ERR(task); return 0; } + +static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, + struct file *dst_f, loff_t src_offset, + loff_t dst_offset, loff_t count) +{ + struct inode *src_inode = file_inode(src_f); + struct inode *dst_inode = file_inode(dst_f); + struct nfs_server *server = NFS_SERVER(dst_inode); + struct nfs42_clone_args args = { + .src_fh = NFS_FH(src_inode), + .dst_fh = NFS_FH(dst_inode), + .src_offset = src_offset, + .dst_offset = dst_offset, + .count = count, + .dst_bitmask = server->cache_consistency_bitmask, + }; + struct nfs42_clone_res res = { + .server = server, + }; + int status; + + msg->rpc_argp = &args; + msg->rpc_resp = &res; + + status = nfs42_set_rw_stateid(&args.src_stateid, src_f, FMODE_READ); + if (status) + return status; + + status = nfs42_set_rw_stateid(&args.dst_stateid, dst_f, FMODE_WRITE); + if (status) + return status; + + res.dst_fattr = nfs_alloc_fattr(); + if (!res.dst_fattr) + return -ENOMEM; + + status = nfs4_call_sync(server->client, server, msg, + &args.seq_args, &res.seq_res, 0); + if (status == 0) + status = nfs_post_op_update_inode(dst_inode, res.dst_fattr); + + kfree(res.dst_fattr); + return status; +} + +int nfs42_proc_clone(struct file *src_f, struct file *dst_f, + loff_t src_offset, loff_t dst_offset, loff_t count) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLONE], + }; + struct inode *inode = file_inode(src_f); + struct nfs_server *server = NFS_SERVER(file_inode(src_f)); + struct nfs4_exception exception = { }; + int err; + + if (!nfs_server_capable(inode, NFS_CAP_CLONE)) + return -EOPNOTSUPP; + + do { + err = _nfs42_proc_clone(&msg, src_f, dst_f, src_offset, + dst_offset, count); + if (err == -ENOTSUPP || err == -EOPNOTSUPP) { + NFS_SERVER(inode)->caps &= ~NFS_CAP_CLONE; + return -EOPNOTSUPP; + } + err = nfs4_handle_exception(server, err, &exception); + } while (exception.retry); + + return err; + +} diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 0eb29e14070d..0ca482a51e53 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -34,6 +34,12 @@ 1 /* opaque devaddr4 length */ + \ XDR_QUADLEN(PNFS_LAYOUTSTATS_MAXSIZE)) #define decode_layoutstats_maxsz (op_decode_hdr_maxsz) +#define encode_clone_maxsz (encode_stateid_maxsz + \ + encode_stateid_maxsz + \ + 2 /* src offset */ + \ + 2 /* dst offset */ + \ + 2 /* count */) +#define decode_clone_maxsz (op_decode_hdr_maxsz) #define NFS4_enc_allocate_sz (compound_encode_hdr_maxsz + \ encode_putfh_maxsz + \ @@ -65,7 +71,20 @@ decode_sequence_maxsz + \ decode_putfh_maxsz + \ PNFS_LAYOUTSTATS_MAXDEV * decode_layoutstats_maxsz) - +#define NFS4_enc_clone_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_savefh_maxsz + \ + encode_putfh_maxsz + \ + encode_clone_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_clone_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_savefh_maxsz + \ + decode_putfh_maxsz + \ + decode_clone_maxsz + \ + decode_getattr_maxsz) static void encode_fallocate(struct xdr_stream *xdr, struct nfs42_falloc_args *args) @@ -128,6 +147,21 @@ static void encode_layoutstats(struct xdr_stream *xdr, encode_uint32(xdr, 0); } +static void encode_clone(struct xdr_stream *xdr, + struct nfs42_clone_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_CLONE, decode_clone_maxsz, hdr); + encode_nfs4_stateid(xdr, &args->src_stateid); + encode_nfs4_stateid(xdr, &args->dst_stateid); + p = reserve_space(xdr, 3*8); + p = xdr_encode_hyper(p, args->src_offset); + p = xdr_encode_hyper(p, args->dst_offset); + xdr_encode_hyper(p, args->count); +} + /* * Encode ALLOCATE request */ @@ -206,6 +240,27 @@ static void nfs4_xdr_enc_layoutstats(struct rpc_rqst *req, encode_nops(&hdr); } +/* + * Encode CLONE request + */ +static void nfs4_xdr_enc_clone(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs42_clone_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->src_fh, &hdr); + encode_savefh(xdr, &hdr); + encode_putfh(xdr, args->dst_fh, &hdr); + encode_clone(xdr, args, &hdr); + encode_getfattr(xdr, args->dst_bitmask, &hdr); + encode_nops(&hdr); +} + static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res) { return decode_op_hdr(xdr, OP_ALLOCATE); @@ -243,6 +298,11 @@ static int decode_layoutstats(struct xdr_stream *xdr) return decode_op_hdr(xdr, OP_LAYOUTSTATS); } +static int decode_clone(struct xdr_stream *xdr) +{ + return decode_op_hdr(xdr, OP_CLONE); +} + /* * Decode ALLOCATE request */ @@ -351,4 +411,39 @@ out: return status; } +/* + * Decode CLONE request + */ +static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs42_clone_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_savefh(xdr); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_clone(xdr); + if (status) + goto out; + status = decode_getfattr(xdr, res->dst_fattr, res->server); + +out: + res->rpc_status = status; + return status; +} + #endif /* __LINUX_FS_NFS_NFS4_2XDR_H */ diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 50cfc4ca7a02..4afdee420d25 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -183,10 +183,12 @@ struct nfs4_state { struct nfs4_exception { - long timeout; - int retry; struct nfs4_state *state; struct inode *inode; + long timeout; + unsigned char delay : 1, + recovering : 1, + retry : 1; }; struct nfs4_state_recovery_ops { diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 223bedda64ae..10410e8b5853 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -33,7 +33,7 @@ static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion) return ret; idr_preload(GFP_KERNEL); spin_lock(&nn->nfs_client_lock); - ret = idr_alloc(&nn->cb_ident_idr, clp, 0, 0, GFP_NOWAIT); + ret = idr_alloc(&nn->cb_ident_idr, clp, 1, 0, GFP_NOWAIT); if (ret >= 0) clp->cl_cb_ident = ret; spin_unlock(&nn->nfs_client_lock); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index b0dbe0abed53..26f9a23e2b25 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -4,8 +4,10 @@ * Copyright (C) 1992 Rick Sladkey */ #include <linux/fs.h> +#include <linux/file.h> #include <linux/falloc.h> #include <linux/nfs_fs.h> +#include <uapi/linux/btrfs.h> /* BTRFS_IOC_CLONE/BTRFS_IOC_CLONE_RANGE */ #include "delegation.h" #include "internal.h" #include "iostat.h" @@ -192,14 +194,72 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t return nfs42_proc_deallocate(filep, offset, len); return nfs42_proc_allocate(filep, offset, len); } + +static int nfs42_clone_file_range(struct file *src_file, loff_t src_off, + struct file *dst_file, loff_t dst_off, u64 count) +{ + struct inode *dst_inode = file_inode(dst_file); + struct nfs_server *server = NFS_SERVER(dst_inode); + struct inode *src_inode = file_inode(src_file); + unsigned int bs = server->clone_blksize; + bool same_inode = false; + int ret; + + /* check alignment w.r.t. clone_blksize */ + ret = -EINVAL; + if (bs) { + if (!IS_ALIGNED(src_off, bs) || !IS_ALIGNED(dst_off, bs)) + goto out; + if (!IS_ALIGNED(count, bs) && i_size_read(src_inode) != (src_off + count)) + goto out; + } + + if (src_inode == dst_inode) + same_inode = true; + + /* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */ + if (same_inode) { + mutex_lock(&src_inode->i_mutex); + } else if (dst_inode < src_inode) { + mutex_lock_nested(&dst_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD); + } else { + mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&dst_inode->i_mutex, I_MUTEX_CHILD); + } + + /* flush all pending writes on both src and dst so that server + * has the latest data */ + ret = nfs_sync_inode(src_inode); + if (ret) + goto out_unlock; + ret = nfs_sync_inode(dst_inode); + if (ret) + goto out_unlock; + + ret = nfs42_proc_clone(src_file, dst_file, src_off, dst_off, count); + + /* truncate inode page cache of the dst range so that future reads can fetch + * new data from server */ + if (!ret) + truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1); + +out_unlock: + if (same_inode) { + mutex_unlock(&src_inode->i_mutex); + } else if (dst_inode < src_inode) { + mutex_unlock(&src_inode->i_mutex); + mutex_unlock(&dst_inode->i_mutex); + } else { + mutex_unlock(&dst_inode->i_mutex); + mutex_unlock(&src_inode->i_mutex); + } +out: + return ret; +} #endif /* CONFIG_NFS_V4_2 */ const struct file_operations nfs4_file_operations = { -#ifdef CONFIG_NFS_V4_2 - .llseek = nfs4_file_llseek, -#else - .llseek = nfs_file_llseek, -#endif .read_iter = nfs_file_read, .write_iter = nfs_file_write, .mmap = nfs_file_mmap, @@ -211,9 +271,13 @@ const struct file_operations nfs4_file_operations = { .flock = nfs_flock, .splice_read = nfs_file_splice_read, .splice_write = iter_file_splice_write, -#ifdef CONFIG_NFS_V4_2 - .fallocate = nfs42_fallocate, -#endif /* CONFIG_NFS_V4_2 */ .check_flags = nfs_check_flags, .setlease = simple_nosetlease, +#ifdef CONFIG_NFS_V4_2 + .llseek = nfs4_file_llseek, + .fallocate = nfs42_fallocate, + .clone_file_range = nfs42_clone_file_range, +#else + .llseek = nfs_file_llseek, +#endif }; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 0e5ff69455c7..4bfc33ad0563 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -78,7 +78,6 @@ struct nfs4_opendata; static int _nfs4_proc_open(struct nfs4_opendata *data); static int _nfs4_recover_proc_open(struct nfs4_opendata *data); static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); -static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *, long *); static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr); static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *label); static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label); @@ -209,6 +208,9 @@ static const u32 nfs4_pnfs_open_bitmap[3] = { | FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_MODIFY, FATTR4_WORD2_MDSTHRESHOLD +#ifdef CONFIG_NFS_V4_SECURITY_LABEL + | FATTR4_WORD2_SECURITY_LABEL +#endif }; static const u32 nfs4_open_noattr_bitmap[3] = { @@ -239,6 +241,7 @@ const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE FATTR4_WORD1_TIME_DELTA | FATTR4_WORD1_FS_LAYOUT_TYPES, FATTR4_WORD2_LAYOUT_BLKSIZE + | FATTR4_WORD2_CLONE_BLKSIZE }; const u32 nfs4_fs_locations_bitmap[3] = { @@ -344,13 +347,16 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout) /* This is the error handling routine for processes that are allowed * to sleep. */ -int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception) +static int nfs4_do_handle_exception(struct nfs_server *server, + int errorcode, struct nfs4_exception *exception) { struct nfs_client *clp = server->nfs_client; struct nfs4_state *state = exception->state; struct inode *inode = exception->inode; int ret = errorcode; + exception->delay = 0; + exception->recovering = 0; exception->retry = 0; switch(errorcode) { case 0: @@ -359,11 +365,9 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_ case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_BAD_STATEID: - if (inode && nfs4_have_delegation(inode, FMODE_READ)) { - nfs4_inode_return_delegation(inode); - exception->retry = 1; - return 0; - } + if (inode && nfs_async_inode_return_delegation(inode, + NULL) == 0) + goto wait_on_recovery; if (state == NULL) break; ret = nfs4_schedule_stateid_recovery(server, state); @@ -409,11 +413,12 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_ ret = -EBUSY; break; } - case -NFS4ERR_GRACE: case -NFS4ERR_DELAY: - ret = nfs4_delay(server->client, &exception->timeout); - if (ret != 0) - break; + nfs_inc_server_stats(server, NFSIOS_DELAY); + case -NFS4ERR_GRACE: + exception->delay = 1; + return 0; + case -NFS4ERR_RETRY_UNCACHED_REP: case -NFS4ERR_OLD_STATEID: exception->retry = 1; @@ -434,14 +439,85 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_ /* We failed to handle the error */ return nfs4_map_errors(ret); wait_on_recovery: - ret = nfs4_wait_clnt_recover(clp); + exception->recovering = 1; + return 0; +} + +/* This is the error handling routine for processes that are allowed + * to sleep. + */ +int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception) +{ + struct nfs_client *clp = server->nfs_client; + int ret; + + ret = nfs4_do_handle_exception(server, errorcode, exception); + if (exception->delay) { + ret = nfs4_delay(server->client, &exception->timeout); + goto out_retry; + } + if (exception->recovering) { + ret = nfs4_wait_clnt_recover(clp); + if (test_bit(NFS_MIG_FAILED, &server->mig_status)) + return -EIO; + goto out_retry; + } + return ret; +out_retry: + if (ret == 0) + exception->retry = 1; + return ret; +} + +static int +nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server, + int errorcode, struct nfs4_exception *exception) +{ + struct nfs_client *clp = server->nfs_client; + int ret; + + ret = nfs4_do_handle_exception(server, errorcode, exception); + if (exception->delay) { + rpc_delay(task, nfs4_update_delay(&exception->timeout)); + goto out_retry; + } + if (exception->recovering) { + rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL); + if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0) + rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task); + goto out_retry; + } if (test_bit(NFS_MIG_FAILED, &server->mig_status)) - return -EIO; + ret = -EIO; + return ret; +out_retry: if (ret == 0) exception->retry = 1; return ret; } +static int +nfs4_async_handle_error(struct rpc_task *task, struct nfs_server *server, + struct nfs4_state *state, long *timeout) +{ + struct nfs4_exception exception = { + .state = state, + }; + + if (task->tk_status >= 0) + return 0; + if (timeout) + exception.timeout = *timeout; + task->tk_status = nfs4_async_handle_exception(task, server, + task->tk_status, + &exception); + if (exception.delay && timeout) + *timeout = exception.timeout; + if (exception.retry) + return -EAGAIN; + return 0; +} + /* * Return 'true' if 'clp' is using an rpc_client that is integrity protected * or 'false' otherwise. @@ -1312,6 +1388,7 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s * Protect the call to nfs4_state_set_mode_locked and * serialise the stateid update */ + spin_lock(&state->owner->so_lock); write_seqlock(&state->seqlock); if (deleg_stateid != NULL) { nfs4_stateid_copy(&state->stateid, deleg_stateid); @@ -1320,7 +1397,6 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s if (open_stateid != NULL) nfs_set_open_stateid_locked(state, open_stateid, fmode); write_sequnlock(&state->seqlock); - spin_lock(&state->owner->so_lock); update_open_stateflags(state, fmode); spin_unlock(&state->owner->so_lock); } @@ -1525,6 +1601,7 @@ _nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) if (!data->rpc_done) { state = nfs4_try_open_cached(data); + trace_nfs4_cached_open(data->state); goto out; } @@ -1942,6 +2019,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) } return; unlock_no_action: + trace_nfs4_cached_open(data->state); rcu_read_unlock(); out_no_action: task->tk_action = NULL; @@ -2630,6 +2708,7 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (status == 0 && state != NULL) renew_lease(server, timestamp); + trace_nfs4_setattr(inode, &arg.stateid, status); return status; } @@ -2646,7 +2725,6 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, int err; do { err = _nfs4_do_setattr(inode, cred, fattr, sattr, state, ilabel, olabel); - trace_nfs4_setattr(inode, err); switch (err) { case -NFS4ERR_OPENMODE: if (!(sattr->ia_valid & ATTR_SIZE)) { @@ -4530,7 +4608,7 @@ static inline int nfs4_server_supports_acls(struct nfs_server *server) #define NFS4ACL_MAXPAGES DIV_ROUND_UP(XATTR_SIZE_MAX, PAGE_SIZE) static int buf_to_pages_noslab(const void *buf, size_t buflen, - struct page **pages, unsigned int *pgbase) + struct page **pages) { struct page *newpage, **spages; int rc = 0; @@ -4674,7 +4752,6 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu goto out_free; args.acl_len = npages * PAGE_SIZE; - args.acl_pgbase = 0; dprintk("%s buf %p buflen %zu npages %d args.acl_len %zu\n", __func__, buf, buflen, npages, args.acl_len); @@ -4766,7 +4843,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl return -EOPNOTSUPP; if (npages > ARRAY_SIZE(pages)) return -ERANGE; - i = buf_to_pages_noslab(buf, buflen, arg.acl_pages, &arg.acl_pgbase); + i = buf_to_pages_noslab(buf, buflen, arg.acl_pages); if (i < 0) return i; nfs4_inode_return_delegation(inode); @@ -4955,79 +5032,6 @@ out: #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ -static int -nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, - struct nfs4_state *state, long *timeout) -{ - struct nfs_client *clp = server->nfs_client; - - if (task->tk_status >= 0) - return 0; - switch(task->tk_status) { - case -NFS4ERR_DELEG_REVOKED: - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_BAD_STATEID: - case -NFS4ERR_OPENMODE: - if (state == NULL) - break; - if (nfs4_schedule_stateid_recovery(server, state) < 0) - goto recovery_failed; - goto wait_on_recovery; - case -NFS4ERR_EXPIRED: - if (state != NULL) { - if (nfs4_schedule_stateid_recovery(server, state) < 0) - goto recovery_failed; - } - case -NFS4ERR_STALE_STATEID: - case -NFS4ERR_STALE_CLIENTID: - nfs4_schedule_lease_recovery(clp); - goto wait_on_recovery; - case -NFS4ERR_MOVED: - if (nfs4_schedule_migration_recovery(server) < 0) - goto recovery_failed; - goto wait_on_recovery; - case -NFS4ERR_LEASE_MOVED: - nfs4_schedule_lease_moved_recovery(clp); - goto wait_on_recovery; -#if defined(CONFIG_NFS_V4_1) - case -NFS4ERR_BADSESSION: - case -NFS4ERR_BADSLOT: - case -NFS4ERR_BAD_HIGH_SLOT: - case -NFS4ERR_DEADSESSION: - case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: - case -NFS4ERR_SEQ_FALSE_RETRY: - case -NFS4ERR_SEQ_MISORDERED: - dprintk("%s ERROR %d, Reset session\n", __func__, - task->tk_status); - nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); - goto wait_on_recovery; -#endif /* CONFIG_NFS_V4_1 */ - case -NFS4ERR_DELAY: - nfs_inc_server_stats(server, NFSIOS_DELAY); - rpc_delay(task, nfs4_update_delay(timeout)); - goto restart_call; - case -NFS4ERR_GRACE: - rpc_delay(task, NFS4_POLL_RETRY_MAX); - case -NFS4ERR_RETRY_UNCACHED_REP: - case -NFS4ERR_OLD_STATEID: - goto restart_call; - } - task->tk_status = nfs4_map_errors(task->tk_status); - return 0; -recovery_failed: - task->tk_status = -EIO; - return 0; -wait_on_recovery: - rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL); - if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0) - rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task); - if (test_bit(NFS_MIG_FAILED, &server->mig_status)) - goto recovery_failed; -restart_call: - task->tk_status = 0; - return -EAGAIN; -} - static void nfs4_init_boot_verifier(const struct nfs_client *clp, nfs4_verifier *bootverf) { @@ -5049,7 +5053,6 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp, static int nfs4_init_nonuniform_client_string(struct nfs_client *clp) { - int result; size_t len; char *str; @@ -5077,7 +5080,7 @@ nfs4_init_nonuniform_client_string(struct nfs_client *clp) return -ENOMEM; rcu_read_lock(); - result = scnprintf(str, len, "Linux NFSv4.0 %s/%s %s", + scnprintf(str, len, "Linux NFSv4.0 %s/%s %s", clp->cl_ipaddr, rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR), rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_PROTO)); @@ -5090,7 +5093,6 @@ nfs4_init_nonuniform_client_string(struct nfs_client *clp) static int nfs4_init_uniquifier_client_string(struct nfs_client *clp) { - int result; size_t len; char *str; @@ -5110,7 +5112,7 @@ nfs4_init_uniquifier_client_string(struct nfs_client *clp) if (!str) return -ENOMEM; - result = scnprintf(str, len, "Linux NFSv%u.%u %s/%s", + scnprintf(str, len, "Linux NFSv%u.%u %s/%s", clp->rpc_ops->version, clp->cl_minorversion, nfs4_client_id_uniquifier, clp->cl_rpcclient->cl_nodename); @@ -5121,7 +5123,6 @@ nfs4_init_uniquifier_client_string(struct nfs_client *clp) static int nfs4_init_uniform_client_string(struct nfs_client *clp) { - int result; size_t len; char *str; @@ -5146,7 +5147,7 @@ nfs4_init_uniform_client_string(struct nfs_client *clp) if (!str) return -ENOMEM; - result = scnprintf(str, len, "Linux NFSv%u.%u %s", + scnprintf(str, len, "Linux NFSv%u.%u %s", clp->rpc_ops->version, clp->cl_minorversion, clp->cl_rpcclient->cl_nodename); clp->cl_owner_id = str; @@ -5385,6 +5386,11 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co if (data == NULL) return -ENOMEM; nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); + + nfs4_state_protect(server->nfs_client, + NFS_SP4_MACH_CRED_CLEANUP, + &task_setup_data.rpc_client, &msg); + data->args.fhandle = &data->fh; data->args.stateid = &data->stateid; data->args.bitmask = server->cache_consistency_bitmask; @@ -5427,7 +5433,7 @@ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4 int err; do { err = _nfs4_proc_delegreturn(inode, cred, stateid, issync); - trace_nfs4_delegreturn(inode, err); + trace_nfs4_delegreturn(inode, stateid, err); switch (err) { case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: @@ -5522,7 +5528,7 @@ struct nfs4_unlockdata { struct nfs4_lock_state *lsp; struct nfs_open_context *ctx; struct file_lock fl; - const struct nfs_server *server; + struct nfs_server *server; unsigned long timestamp; }; @@ -5937,6 +5943,7 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f data->cancelled = 1; rpc_put_task(task); dprintk("%s: done, ret = %d!\n", __func__, ret); + trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret); return ret; } @@ -5953,7 +5960,6 @@ static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0) return 0; err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_RECLAIM); - trace_nfs4_lock_reclaim(request, state, F_SETLK, err); if (err != -NFS4ERR_DELAY) break; nfs4_handle_exception(server, err, &exception); @@ -5980,7 +5986,6 @@ static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0) return 0; err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_EXPIRED); - trace_nfs4_lock_expired(request, state, F_SETLK, err); switch (err) { default: goto out; @@ -6088,7 +6093,6 @@ static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock * do { err = _nfs4_proc_setlk(state, cmd, request); - trace_nfs4_set_lock(request, state, cmd, err); if (err == -NFS4ERR_DENIED) err = -EAGAIN; err = nfs4_handle_exception(NFS_SERVER(state->inode), @@ -6249,48 +6253,32 @@ nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_state *lsp) #define XATTR_NAME_NFSV4_ACL "system.nfs4_acl" -static int nfs4_xattr_set_nfs4_acl(struct dentry *dentry, const char *key, +static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler, + struct dentry *dentry, const char *key, const void *buf, size_t buflen, - int flags, int type) + int flags) { - if (strcmp(key, "") != 0) - return -EINVAL; - return nfs4_proc_set_acl(d_inode(dentry), buf, buflen); } -static int nfs4_xattr_get_nfs4_acl(struct dentry *dentry, const char *key, - void *buf, size_t buflen, int type) +static int nfs4_xattr_get_nfs4_acl(const struct xattr_handler *handler, + struct dentry *dentry, const char *key, + void *buf, size_t buflen) { - if (strcmp(key, "") != 0) - return -EINVAL; - return nfs4_proc_get_acl(d_inode(dentry), buf, buflen); } -static size_t nfs4_xattr_list_nfs4_acl(struct dentry *dentry, char *list, - size_t list_len, const char *name, - size_t name_len, int type) +static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry) { - size_t len = sizeof(XATTR_NAME_NFSV4_ACL); - - if (!nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry)))) - return 0; - - if (list && len <= list_len) - memcpy(list, XATTR_NAME_NFSV4_ACL, len); - return len; + return nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry))); } #ifdef CONFIG_NFS_V4_SECURITY_LABEL -static inline int nfs4_server_supports_labels(struct nfs_server *server) -{ - return server->caps & NFS_CAP_SECURITY_LABEL; -} -static int nfs4_xattr_set_nfs4_label(struct dentry *dentry, const char *key, - const void *buf, size_t buflen, - int flags, int type) +static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler, + struct dentry *dentry, const char *key, + const void *buf, size_t buflen, + int flags) { if (security_ismaclabel(key)) return nfs4_set_security_label(dentry, buf, buflen); @@ -6298,36 +6286,43 @@ static int nfs4_xattr_set_nfs4_label(struct dentry *dentry, const char *key, return -EOPNOTSUPP; } -static int nfs4_xattr_get_nfs4_label(struct dentry *dentry, const char *key, - void *buf, size_t buflen, int type) +static int nfs4_xattr_get_nfs4_label(const struct xattr_handler *handler, + struct dentry *dentry, const char *key, + void *buf, size_t buflen) { if (security_ismaclabel(key)) return nfs4_get_security_label(d_inode(dentry), buf, buflen); return -EOPNOTSUPP; } -static size_t nfs4_xattr_list_nfs4_label(struct dentry *dentry, char *list, - size_t list_len, const char *name, - size_t name_len, int type) +static ssize_t +nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len) { - size_t len = 0; + int len = 0; - if (nfs_server_capable(d_inode(dentry), NFS_CAP_SECURITY_LABEL)) { - len = security_inode_listsecurity(d_inode(dentry), NULL, 0); - if (list && len <= list_len) - security_inode_listsecurity(d_inode(dentry), list, len); + if (nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL)) { + len = security_inode_listsecurity(inode, list, list_len); + if (list_len && len > list_len) + return -ERANGE; } return len; } static const struct xattr_handler nfs4_xattr_nfs4_label_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = nfs4_xattr_list_nfs4_label, .get = nfs4_xattr_get_nfs4_label, .set = nfs4_xattr_set_nfs4_label, }; -#endif +#else + +static ssize_t +nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len) +{ + return 0; +} + +#endif /* * nfs_fhget will use either the mounted_on_fileid or the fileid @@ -6857,10 +6852,13 @@ static const struct nfs41_state_protection nfs4_sp4_mach_cred_request = { }, .allow.u.words = { [0] = 1 << (OP_CLOSE) | + 1 << (OP_OPEN_DOWNGRADE) | 1 << (OP_LOCKU) | + 1 << (OP_DELEGRETURN) | 1 << (OP_COMMIT), [1] = 1 << (OP_SECINFO - 32) | 1 << (OP_SECINFO_NO_NAME - 32) | + 1 << (OP_LAYOUTRETURN - 32) | 1 << (OP_TEST_STATEID - 32) | 1 << (OP_FREE_STATEID - 32) | 1 << (OP_WRITE - 32) @@ -6925,11 +6923,19 @@ static int nfs4_sp4_select_mode(struct nfs_client *clp, } if (test_bit(OP_CLOSE, sp->allow.u.longs) && + test_bit(OP_OPEN_DOWNGRADE, sp->allow.u.longs) && + test_bit(OP_DELEGRETURN, sp->allow.u.longs) && test_bit(OP_LOCKU, sp->allow.u.longs)) { dfprintk(MOUNT, " cleanup mode enabled\n"); set_bit(NFS_SP4_MACH_CRED_CLEANUP, &clp->cl_sp4_flags); } + if (test_bit(OP_LAYOUTRETURN, sp->allow.u.longs)) { + dfprintk(MOUNT, " pnfs cleanup mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_PNFS_CLEANUP, + &clp->cl_sp4_flags); + } + if (test_bit(OP_SECINFO, sp->allow.u.longs) && test_bit(OP_SECINFO_NO_NAME, sp->allow.u.longs)) { dfprintk(MOUNT, " secinfo mode enabled\n"); @@ -7758,6 +7764,7 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata) struct nfs4_layoutget *lgp = calldata; struct nfs_server *server = NFS_SERVER(lgp->args.inode); struct nfs4_session *session = nfs4_get_session(server); + int ret; dprintk("--> %s\n", __func__); /* Note the is a race here, where a CB_LAYOUTRECALL can come in @@ -7768,12 +7775,12 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata) if (nfs41_setup_sequence(session, &lgp->args.seq_args, &lgp->res.seq_res, task)) return; - if (pnfs_choose_layoutget_stateid(&lgp->args.stateid, + ret = pnfs_choose_layoutget_stateid(&lgp->args.stateid, NFS_I(lgp->args.inode)->layout, &lgp->args.range, - lgp->args.ctx->state)) { - rpc_exit(task, NFS4_OK); - } + lgp->args.ctx->state); + if (ret < 0) + rpc_exit(task, ret); } static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) @@ -7793,6 +7800,15 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) switch (task->tk_status) { case 0: goto out; + + /* + * NFS4ERR_LAYOUTUNAVAILABLE means we are not supposed to use pnfs + * on the file. set tk_status to -ENODATA to tell upper layer to + * retry go inband. + */ + case -NFS4ERR_LAYOUTUNAVAILABLE: + task->tk_status = -ENODATA; + goto out; /* * NFS4ERR_BADLAYOUT means the MDS cannot return a layout of * length lgp->args.minlength != 0 (see RFC5661 section 18.43.3). @@ -7861,7 +7877,7 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) spin_unlock(&inode->i_lock); goto out_restart; } - if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN) + if (nfs4_async_handle_error(task, server, state, &lgp->timeout) == -EAGAIN) goto out_restart; out: dprintk("<-- %s\n", __func__); @@ -7989,6 +8005,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) trace_nfs4_layoutget(lgp->args.ctx, &lgp->args.range, &lgp->res.range, + &lgp->res.stateid, status); /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */ if (status == 0 && lgp->res.layoutp->len) @@ -8045,11 +8062,11 @@ static void nfs4_layoutreturn_release(void *calldata) dprintk("--> %s\n", __func__); spin_lock(&lo->plh_inode->i_lock); + pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range); + pnfs_mark_layout_returned_if_empty(lo); if (lrp->res.lrs_present) pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); - pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range); pnfs_clear_layoutreturn_waitbit(lo); - lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); pnfs_free_lseg_list(&freeme); pnfs_put_layout_hdr(lrp->args.layout); @@ -8081,6 +8098,10 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) }; int status = 0; + nfs4_state_protect(NFS_SERVER(lrp->args.inode)->nfs_client, + NFS_SP4_MACH_CRED_PNFS_CLEANUP, + &task_setup_data.rpc_client, &msg); + dprintk("--> %s\n", __func__); if (!sync) { lrp->inode = nfs_igrab_and_active(lrp->args.inode); @@ -8096,7 +8117,7 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) return PTR_ERR(task); if (sync) status = task->tk_status; - trace_nfs4_layoutreturn(lrp->args.inode, status); + trace_nfs4_layoutreturn(lrp->args.inode, &lrp->args.stateid, status); dprintk("<-- %s status=%d\n", __func__, status); rpc_put_task(task); return status; @@ -8244,7 +8265,7 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync) return PTR_ERR(task); if (sync) status = task->tk_status; - trace_nfs4_layoutcommit(data->args.inode, status); + trace_nfs4_layoutcommit(data->args.inode, &data->args.stateid, status); dprintk("%s: status %d\n", __func__, status); rpc_put_task(task); return status; @@ -8718,7 +8739,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { | NFS_CAP_ALLOCATE | NFS_CAP_DEALLOCATE | NFS_CAP_SEEK - | NFS_CAP_LAYOUTSTATS, + | NFS_CAP_LAYOUTSTATS + | NFS_CAP_CLONE, .init_client = nfs41_init_client, .shutdown_client = nfs41_shutdown_client, .match_stateid = nfs41_match_stateid, @@ -8743,6 +8765,24 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { #endif }; +ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) +{ + ssize_t error, error2; + + error = generic_listxattr(dentry, list, size); + if (error < 0) + return error; + if (list) { + list += error; + size -= error; + } + + error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size); + if (error2 < 0) + return error2; + return error + error2; +} + static const struct inode_operations nfs4_dir_inode_operations = { .create = nfs_create, .lookup = nfs_lookup, @@ -8759,7 +8799,7 @@ static const struct inode_operations nfs4_dir_inode_operations = { .setattr = nfs_setattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, - .listxattr = generic_listxattr, + .listxattr = nfs4_listxattr, .removexattr = generic_removexattr, }; @@ -8769,7 +8809,7 @@ static const struct inode_operations nfs4_file_inode_operations = { .setattr = nfs_setattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, - .listxattr = generic_listxattr, + .listxattr = nfs4_listxattr, .removexattr = generic_removexattr, }; @@ -8828,7 +8868,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { - .prefix = XATTR_NAME_NFSV4_ACL, + .name = XATTR_NAME_NFSV4_ACL, .list = nfs4_xattr_list_nfs4_acl, .get = nfs4_xattr_get_nfs4_acl, .set = nfs4_xattr_set_nfs4_acl, diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c index 0fbd3ab1be22..8693d77c45ea 100644 --- a/fs/nfs/nfs4sysctl.c +++ b/fs/nfs/nfs4sysctl.c @@ -12,7 +12,7 @@ #include "nfs4idmap.h" #include "callback.h" -static const int nfs_set_port_min = 0; +static const int nfs_set_port_min; static const int nfs_set_port_max = 65535; static struct ctl_table_header *nfs4_callback_sysctl_table; diff --git a/fs/nfs/nfs4trace.c b/fs/nfs/nfs4trace.c index d774335cc8bc..2850bce19244 100644 --- a/fs/nfs/nfs4trace.c +++ b/fs/nfs/nfs4trace.c @@ -6,6 +6,7 @@ #include "internal.h" #include "nfs4session.h" #include "callback.h" +#include "pnfs.h" #define CREATE_TRACE_POINTS #include "nfs4trace.h" diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 671cf68fe56b..2c8d05dae5b1 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -321,6 +321,7 @@ TRACE_EVENT(nfs4_sequence_done, __entry->highest_slotid = res->sr_highest_slotid; __entry->target_highest_slotid = res->sr_target_highest_slotid; + __entry->status_flags = res->sr_status_flags; __entry->error = res->sr_status; ), TP_printk( @@ -399,6 +400,10 @@ DECLARE_EVENT_CLASS(nfs4_open_event, __field(u64, fileid) __field(u64, dir) __string(name, ctx->dentry->d_name.name) + __field(int, stateid_seq) + __field(u32, stateid_hash) + __field(int, openstateid_seq) + __field(u32, openstateid_hash) ), TP_fast_assign( @@ -409,8 +414,22 @@ DECLARE_EVENT_CLASS(nfs4_open_event, __entry->flags = flags; __entry->fmode = (__force unsigned int)ctx->mode; __entry->dev = ctx->dentry->d_sb->s_dev; - if (!IS_ERR_OR_NULL(state)) + if (!IS_ERR_OR_NULL(state)) { inode = state->inode; + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); + __entry->openstateid_seq = + be32_to_cpu(state->open_stateid.seqid); + __entry->openstateid_hash = + nfs_stateid_hash(&state->open_stateid); + } else { + __entry->stateid_seq = 0; + __entry->stateid_hash = 0; + __entry->openstateid_seq = 0; + __entry->openstateid_hash = 0; + } if (inode != NULL) { __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); @@ -425,7 +444,8 @@ DECLARE_EVENT_CLASS(nfs4_open_event, TP_printk( "error=%d (%s) flags=%d (%s) fmode=%s " "fileid=%02x:%02x:%llu fhandle=0x%08x " - "name=%02x:%02x:%llu/%s", + "name=%02x:%02x:%llu/%s stateid=%d:0x%08x " + "openstateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), __entry->flags, @@ -436,7 +456,9 @@ DECLARE_EVENT_CLASS(nfs4_open_event, __entry->fhandle, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, - __get_str(name) + __get_str(name), + __entry->stateid_seq, __entry->stateid_hash, + __entry->openstateid_seq, __entry->openstateid_hash ) ); @@ -452,6 +474,45 @@ DEFINE_NFS4_OPEN_EVENT(nfs4_open_reclaim); DEFINE_NFS4_OPEN_EVENT(nfs4_open_expired); DEFINE_NFS4_OPEN_EVENT(nfs4_open_file); +TRACE_EVENT(nfs4_cached_open, + TP_PROTO( + const struct nfs4_state *state + ), + TP_ARGS(state), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(unsigned int, fmode) + __field(int, stateid_seq) + __field(u32, stateid_hash) + ), + + TP_fast_assign( + const struct inode *inode = state->inode; + + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->fmode = (__force unsigned int)state->state; + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); + ), + + TP_printk( + "fmode=%s fileid=%02x:%02x:%llu " + "fhandle=0x%08x stateid=%d:0x%08x", + __entry->fmode ? show_fmode_flags(__entry->fmode) : + "closed", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash + ) +); + TRACE_EVENT(nfs4_close, TP_PROTO( const struct nfs4_state *state, @@ -468,6 +529,8 @@ TRACE_EVENT(nfs4_close, __field(u64, fileid) __field(unsigned int, fmode) __field(int, error) + __field(int, stateid_seq) + __field(u32, stateid_hash) ), TP_fast_assign( @@ -478,18 +541,23 @@ TRACE_EVENT(nfs4_close, __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); __entry->fmode = (__force unsigned int)state->state; __entry->error = error; + __entry->stateid_seq = + be32_to_cpu(args->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&args->stateid); ), TP_printk( "error=%d (%s) fmode=%s fileid=%02x:%02x:%llu " - "fhandle=0x%08x", + "fhandle=0x%08x openstateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), __entry->fmode ? show_fmode_flags(__entry->fmode) : "closed", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, - __entry->fhandle + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash ) ); @@ -523,6 +591,8 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) + __field(int, stateid_seq) + __field(u32, stateid_hash) ), TP_fast_assign( @@ -536,11 +606,16 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); ), TP_printk( "error=%d (%s) cmd=%s:%s range=%lld:%lld " - "fileid=%02x:%02x:%llu fhandle=0x%08x", + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "stateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), show_lock_cmd(__entry->cmd), @@ -549,7 +624,8 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, (long long)__entry->end, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, - __entry->fhandle + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash ) ); @@ -563,11 +639,73 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, ), \ TP_ARGS(request, state, cmd, error)) DEFINE_NFS4_LOCK_EVENT(nfs4_get_lock); -DEFINE_NFS4_LOCK_EVENT(nfs4_set_lock); -DEFINE_NFS4_LOCK_EVENT(nfs4_lock_reclaim); -DEFINE_NFS4_LOCK_EVENT(nfs4_lock_expired); DEFINE_NFS4_LOCK_EVENT(nfs4_unlock); +TRACE_EVENT(nfs4_set_lock, + TP_PROTO( + const struct file_lock *request, + const struct nfs4_state *state, + const nfs4_stateid *lockstateid, + int cmd, + int error + ), + + TP_ARGS(request, state, lockstateid, cmd, error), + + TP_STRUCT__entry( + __field(int, error) + __field(int, cmd) + __field(char, type) + __field(loff_t, start) + __field(loff_t, end) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(int, stateid_seq) + __field(u32, stateid_hash) + __field(int, lockstateid_seq) + __field(u32, lockstateid_hash) + ), + + TP_fast_assign( + const struct inode *inode = state->inode; + + __entry->error = error; + __entry->cmd = cmd; + __entry->type = request->fl_type; + __entry->start = request->fl_start; + __entry->end = request->fl_end; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); + __entry->lockstateid_seq = + be32_to_cpu(lockstateid->seqid); + __entry->lockstateid_hash = + nfs_stateid_hash(lockstateid); + ), + + TP_printk( + "error=%d (%s) cmd=%s:%s range=%lld:%lld " + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "stateid=%d:0x%08x lockstateid=%d:0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + show_lock_cmd(__entry->cmd), + show_lock_type(__entry->type), + (long long)__entry->start, + (long long)__entry->end, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash, + __entry->lockstateid_seq, __entry->lockstateid_hash + ) +); + DECLARE_EVENT_CLASS(nfs4_set_delegation_event, TP_PROTO( const struct inode *inode, @@ -621,20 +759,28 @@ TRACE_EVENT(nfs4_delegreturn_exit, __field(dev_t, dev) __field(u32, fhandle) __field(int, error) + __field(int, stateid_seq) + __field(u32, stateid_hash) ), TP_fast_assign( __entry->dev = res->server->s_dev; __entry->fhandle = nfs_fhandle_hash(args->fhandle); __entry->error = error; + __entry->stateid_seq = + be32_to_cpu(args->stateid->seqid); + __entry->stateid_hash = + nfs_stateid_hash(args->stateid); ), TP_printk( - "error=%d (%s) dev=%02x:%02x fhandle=0x%08x", + "error=%d (%s) dev=%02x:%02x fhandle=0x%08x " + "stateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->fhandle + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash ) ); @@ -653,6 +799,8 @@ DECLARE_EVENT_CLASS(nfs4_test_stateid_event, __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) + __field(int, stateid_seq) + __field(u32, stateid_hash) ), TP_fast_assign( @@ -662,15 +810,21 @@ DECLARE_EVENT_CLASS(nfs4_test_stateid_event, __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); ), TP_printk( - "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x", + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "stateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, - __entry->fhandle + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash ) ); @@ -820,7 +974,6 @@ DECLARE_EVENT_CLASS(nfs4_inode_event, ), \ TP_ARGS(inode, error)) -DEFINE_NFS4_INODE_EVENT(nfs4_setattr); DEFINE_NFS4_INODE_EVENT(nfs4_access); DEFINE_NFS4_INODE_EVENT(nfs4_readlink); DEFINE_NFS4_INODE_EVENT(nfs4_readdir); @@ -830,8 +983,59 @@ DEFINE_NFS4_INODE_EVENT(nfs4_set_acl); DEFINE_NFS4_INODE_EVENT(nfs4_get_security_label); DEFINE_NFS4_INODE_EVENT(nfs4_set_security_label); #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ -DEFINE_NFS4_INODE_EVENT(nfs4_recall_delegation); -DEFINE_NFS4_INODE_EVENT(nfs4_delegreturn); + +DECLARE_EVENT_CLASS(nfs4_inode_stateid_event, + TP_PROTO( + const struct inode *inode, + const nfs4_stateid *stateid, + int error + ), + + TP_ARGS(inode, stateid, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(int, error) + __field(int, stateid_seq) + __field(u32, stateid_hash) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->error = error; + __entry->stateid_seq = + be32_to_cpu(stateid->seqid); + __entry->stateid_hash = + nfs_stateid_hash(stateid); + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "stateid=%d:0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash + ) +); + +#define DEFINE_NFS4_INODE_STATEID_EVENT(name) \ + DEFINE_EVENT(nfs4_inode_stateid_event, name, \ + TP_PROTO( \ + const struct inode *inode, \ + const nfs4_stateid *stateid, \ + int error \ + ), \ + TP_ARGS(inode, stateid, error)) + +DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_setattr); +DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_delegreturn); DECLARE_EVENT_CLASS(nfs4_getattr_event, TP_PROTO( @@ -941,8 +1145,74 @@ DECLARE_EVENT_CLASS(nfs4_inode_callback_event, ), \ TP_ARGS(clp, fhandle, inode, error)) DEFINE_NFS4_INODE_CALLBACK_EVENT(nfs4_cb_getattr); -DEFINE_NFS4_INODE_CALLBACK_EVENT(nfs4_cb_layoutrecall_inode); +DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event, + TP_PROTO( + const struct nfs_client *clp, + const struct nfs_fh *fhandle, + const struct inode *inode, + const nfs4_stateid *stateid, + int error + ), + + TP_ARGS(clp, fhandle, inode, stateid, error), + + TP_STRUCT__entry( + __field(int, error) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __string(dstaddr, clp ? + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_ADDR) : "unknown") + __field(int, stateid_seq) + __field(u32, stateid_hash) + ), + + TP_fast_assign( + __entry->error = error; + __entry->fhandle = nfs_fhandle_hash(fhandle); + if (inode != NULL) { + __entry->fileid = NFS_FILEID(inode); + __entry->dev = inode->i_sb->s_dev; + } else { + __entry->fileid = 0; + __entry->dev = 0; + } + __assign_str(dstaddr, clp ? + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_ADDR) : "unknown") + __entry->stateid_seq = + be32_to_cpu(stateid->seqid); + __entry->stateid_hash = + nfs_stateid_hash(stateid); + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "stateid=%d:0x%08x dstaddr=%s", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash, + __get_str(dstaddr) + ) +); + +#define DEFINE_NFS4_INODE_STATEID_CALLBACK_EVENT(name) \ + DEFINE_EVENT(nfs4_inode_stateid_callback_event, name, \ + TP_PROTO( \ + const struct nfs_client *clp, \ + const struct nfs_fh *fhandle, \ + const struct inode *inode, \ + const nfs4_stateid *stateid, \ + int error \ + ), \ + TP_ARGS(clp, fhandle, inode, stateid, error)) +DEFINE_NFS4_INODE_STATEID_CALLBACK_EVENT(nfs4_cb_recall); +DEFINE_NFS4_INODE_STATEID_CALLBACK_EVENT(nfs4_cb_layoutrecall_file); DECLARE_EVENT_CLASS(nfs4_idmap_event, TP_PROTO( @@ -1005,28 +1275,37 @@ DECLARE_EVENT_CLASS(nfs4_read_event, __field(loff_t, offset) __field(size_t, count) __field(int, error) + __field(int, stateid_seq) + __field(u32, stateid_hash) ), TP_fast_assign( const struct inode *inode = hdr->inode; + const struct nfs4_state *state = + hdr->args.context->state; __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); __entry->offset = hdr->args.offset; __entry->count = hdr->args.count; __entry->error = error; + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); ), TP_printk( "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%zu", + "offset=%lld count=%zu stateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, - __entry->count + __entry->count, + __entry->stateid_seq, __entry->stateid_hash ) ); #define DEFINE_NFS4_READ_EVENT(name) \ @@ -1056,28 +1335,37 @@ DECLARE_EVENT_CLASS(nfs4_write_event, __field(loff_t, offset) __field(size_t, count) __field(int, error) + __field(int, stateid_seq) + __field(u32, stateid_hash) ), TP_fast_assign( const struct inode *inode = hdr->inode; + const struct nfs4_state *state = + hdr->args.context->state; __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); __entry->offset = hdr->args.offset; __entry->count = hdr->args.count; __entry->error = error; + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); ), TP_printk( "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%zu", + "offset=%lld count=%zu stateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, - __entry->count + __entry->count, + __entry->stateid_seq, __entry->stateid_hash ) ); @@ -1154,10 +1442,11 @@ TRACE_EVENT(nfs4_layoutget, const struct nfs_open_context *ctx, const struct pnfs_layout_range *args, const struct pnfs_layout_range *res, + const nfs4_stateid *layout_stateid, int error ), - TP_ARGS(ctx, args, res, error), + TP_ARGS(ctx, args, res, layout_stateid, error), TP_STRUCT__entry( __field(dev_t, dev) @@ -1167,10 +1456,15 @@ TRACE_EVENT(nfs4_layoutget, __field(u64, offset) __field(u64, count) __field(int, error) + __field(int, stateid_seq) + __field(u32, stateid_hash) + __field(int, layoutstateid_seq) + __field(u32, layoutstateid_hash) ), TP_fast_assign( const struct inode *inode = d_inode(ctx->dentry); + const struct nfs4_state *state = ctx->state; __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); @@ -1178,11 +1472,25 @@ TRACE_EVENT(nfs4_layoutget, __entry->offset = args->offset; __entry->count = args->length; __entry->error = error; + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); + if (!error) { + __entry->layoutstateid_seq = + be32_to_cpu(layout_stateid->seqid); + __entry->layoutstateid_hash = + nfs_stateid_hash(layout_stateid); + } else { + __entry->layoutstateid_seq = 0; + __entry->layoutstateid_hash = 0; + } ), TP_printk( "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "iomode=%s offset=%llu count=%llu", + "iomode=%s offset=%llu count=%llu stateid=%d:0x%08x " + "layoutstateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), @@ -1190,14 +1498,83 @@ TRACE_EVENT(nfs4_layoutget, __entry->fhandle, show_pnfs_iomode(__entry->iomode), (unsigned long long)__entry->offset, - (unsigned long long)__entry->count + (unsigned long long)__entry->count, + __entry->stateid_seq, __entry->stateid_hash, + __entry->layoutstateid_seq, __entry->layoutstateid_hash ) ); -DEFINE_NFS4_INODE_EVENT(nfs4_layoutcommit); -DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn); +DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutcommit); +DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutreturn); DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn_on_close); +#define show_pnfs_update_layout_reason(reason) \ + __print_symbolic(reason, \ + { PNFS_UPDATE_LAYOUT_UNKNOWN, "unknown" }, \ + { PNFS_UPDATE_LAYOUT_NO_PNFS, "no pnfs" }, \ + { PNFS_UPDATE_LAYOUT_RD_ZEROLEN, "read+zerolen" }, \ + { PNFS_UPDATE_LAYOUT_MDSTHRESH, "mdsthresh" }, \ + { PNFS_UPDATE_LAYOUT_NOMEM, "nomem" }, \ + { PNFS_UPDATE_LAYOUT_BULK_RECALL, "bulk recall" }, \ + { PNFS_UPDATE_LAYOUT_IO_TEST_FAIL, "io test fail" }, \ + { PNFS_UPDATE_LAYOUT_FOUND_CACHED, "found cached" }, \ + { PNFS_UPDATE_LAYOUT_RETURN, "layoutreturn" }, \ + { PNFS_UPDATE_LAYOUT_BLOCKED, "layouts blocked" }, \ + { PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, "sent layoutget" }) + +TRACE_EVENT(pnfs_update_layout, + TP_PROTO(struct inode *inode, + loff_t pos, + u64 count, + enum pnfs_iomode iomode, + struct pnfs_layout_hdr *lo, + enum pnfs_update_layout_reason reason + ), + TP_ARGS(inode, pos, count, iomode, lo, reason), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, fileid) + __field(u32, fhandle) + __field(loff_t, pos) + __field(u64, count) + __field(enum pnfs_iomode, iomode) + __field(int, layoutstateid_seq) + __field(u32, layoutstateid_hash) + __field(enum pnfs_update_layout_reason, reason) + ), + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->pos = pos; + __entry->count = count; + __entry->iomode = iomode; + __entry->reason = reason; + if (lo != NULL) { + __entry->layoutstateid_seq = + be32_to_cpu(lo->plh_stateid.seqid); + __entry->layoutstateid_hash = + nfs_stateid_hash(&lo->plh_stateid); + } else { + __entry->layoutstateid_seq = 0; + __entry->layoutstateid_hash = 0; + } + ), + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "iomode=%s pos=%llu count=%llu " + "layoutstateid=%d:0x%08x (%s)", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + show_pnfs_iomode(__entry->iomode), + (unsigned long long)__entry->pos, + (unsigned long long)__entry->count, + __entry->layoutstateid_seq, __entry->layoutstateid_hash, + show_pnfs_update_layout_reason(__entry->reason) + ) +); + #endif /* CONFIG_NFS_V4_1 */ #endif /* _TRACE_NFS4_H */ diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 788adf3897c7..4e4441216804 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1659,7 +1659,7 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun *p = cpu_to_be32(FATTR4_WORD0_ACL); p = reserve_space(xdr, 4); *p = cpu_to_be32(arg->acl_len); - xdr_write_pages(xdr, arg->acl_pages, arg->acl_pgbase, arg->acl_len); + xdr_write_pages(xdr, arg->acl_pages, 0, arg->acl_len); } static void @@ -2491,7 +2491,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr); xdr_inline_pages(&req->rq_rcv_buf, replen << 2, - args->acl_pages, args->acl_pgbase, args->acl_len); + args->acl_pages, 0, args->acl_len); encode_nops(&hdr); } @@ -3615,6 +3615,7 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st status = 0; if (unlikely(!(bitmap[0] & FATTR4_WORD0_FS_LOCATIONS))) goto out; + bitmap[0] &= ~FATTR4_WORD0_FS_LOCATIONS; status = -EIO; /* Ignore borken servers that return unrequested attrs */ if (unlikely(res == NULL)) @@ -4375,6 +4376,11 @@ static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat) goto xdr_error; if ((status = decode_attr_files_total(xdr, bitmap, &fsstat->tfiles)) != 0) goto xdr_error; + + status = -EIO; + if (unlikely(bitmap[0])) + goto xdr_error; + if ((status = decode_attr_space_avail(xdr, bitmap, &fsstat->abytes)) != 0) goto xdr_error; if ((status = decode_attr_space_free(xdr, bitmap, &fsstat->fbytes)) != 0) @@ -4574,6 +4580,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, goto xdr_error; fattr->valid |= status; + status = -EIO; + if (unlikely(bitmap[0])) + goto xdr_error; + status = decode_attr_mode(xdr, bitmap, &fmode); if (status < 0) goto xdr_error; @@ -4627,6 +4637,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, goto xdr_error; fattr->valid |= status; + status = -EIO; + if (unlikely(bitmap[1])) + goto xdr_error; + status = decode_attr_mdsthreshold(xdr, bitmap, fattr->mdsthreshold); if (status < 0) goto xdr_error; @@ -4764,6 +4778,28 @@ static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap, return 0; } +/* + * The granularity of a CLONE operation. + */ +static int decode_attr_clone_blksize(struct xdr_stream *xdr, uint32_t *bitmap, + uint32_t *res) +{ + __be32 *p; + + dprintk("%s: bitmap is %x\n", __func__, bitmap[2]); + *res = 0; + if (bitmap[2] & FATTR4_WORD2_CLONE_BLKSIZE) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) { + print_overflow_msg(__func__, xdr); + return -EIO; + } + *res = be32_to_cpup(p); + bitmap[2] &= ~FATTR4_WORD2_CLONE_BLKSIZE; + } + return 0; +} + static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) { unsigned int savep; @@ -4789,15 +4825,28 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) if ((status = decode_attr_maxwrite(xdr, bitmap, &fsinfo->wtmax)) != 0) goto xdr_error; fsinfo->wtpref = fsinfo->wtmax; + + status = -EIO; + if (unlikely(bitmap[0])) + goto xdr_error; + status = decode_attr_time_delta(xdr, bitmap, &fsinfo->time_delta); if (status != 0) goto xdr_error; status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype); if (status != 0) goto xdr_error; + + status = -EIO; + if (unlikely(bitmap[1])) + goto xdr_error; + status = decode_attr_layout_blksize(xdr, bitmap, &fsinfo->blksize); if (status) goto xdr_error; + status = decode_attr_clone_blksize(xdr, bitmap, &fsinfo->clone_blksize); + if (status) + goto xdr_error; status = verify_attr_len(xdr, savep, attrlen); xdr_error: @@ -7465,6 +7514,7 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(ALLOCATE, enc_allocate, dec_allocate), PROC(DEALLOCATE, enc_deallocate, dec_deallocate), PROC(LAYOUTSTATS, enc_layoutstats, dec_layoutstats), + PROC(CLONE, enc_clone, dec_clone), #endif /* CONFIG_NFS_V4_2 */ }; diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index 9bc9f04fb7f6..89a15dbe5efc 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -90,7 +90,7 @@ #define NFS_DEF_OPTIONS "vers=2,udp,rsize=4096,wsize=4096" /* Parameters passed from the kernel command line */ -static char nfs_root_parms[256] __initdata = ""; +static char nfs_root_parms[NFS_MAXPATHLEN + 1] __initdata = ""; /* Text-based mount options passed to super.c */ static char nfs_root_options[256] __initdata = NFS_DEF_OPTIONS; diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 59f838cdc009..9f80a086b612 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -39,7 +39,6 @@ { 1 << NFS_INO_INVALIDATING, "INVALIDATING" }, \ { 1 << NFS_INO_FLUSHING, "FLUSHING" }, \ { 1 << NFS_INO_FSCACHE, "FSCACHE" }, \ - { 1 << NFS_INO_COMMIT, "COMMIT" }, \ { 1 << NFS_INO_LAYOUTCOMMIT, "NEED_LAYOUTCOMMIT" }, \ { 1 << NFS_INO_LAYOUTCOMMITTING, "LAYOUTCOMMIT" }) diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 5c0c6b58157f..9aebffb40505 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -476,10 +476,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) } unlock_page(page); } - if (PageDirty(page) || PageWriteback(page)) - *uptodate = true; - else - *uptodate = PageUptodate(page); + *uptodate = PageUptodate(page); dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate); return page; } diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index fe3ddd20ff89..8ce4f61cbaa5 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -101,53 +101,18 @@ nfs_page_free(struct nfs_page *p) kmem_cache_free(nfs_page_cachep, p); } -static void -nfs_iocounter_inc(struct nfs_io_counter *c) -{ - atomic_inc(&c->io_count); -} - -static void -nfs_iocounter_dec(struct nfs_io_counter *c) -{ - if (atomic_dec_and_test(&c->io_count)) { - clear_bit(NFS_IO_INPROGRESS, &c->flags); - smp_mb__after_atomic(); - wake_up_bit(&c->flags, NFS_IO_INPROGRESS); - } -} - -static int -__nfs_iocounter_wait(struct nfs_io_counter *c) -{ - wait_queue_head_t *wq = bit_waitqueue(&c->flags, NFS_IO_INPROGRESS); - DEFINE_WAIT_BIT(q, &c->flags, NFS_IO_INPROGRESS); - int ret = 0; - - do { - prepare_to_wait(wq, &q.wait, TASK_KILLABLE); - set_bit(NFS_IO_INPROGRESS, &c->flags); - if (atomic_read(&c->io_count) == 0) - break; - ret = nfs_wait_bit_killable(&q.key); - } while (atomic_read(&c->io_count) != 0 && !ret); - finish_wait(wq, &q.wait); - return ret; -} - /** * nfs_iocounter_wait - wait for i/o to complete - * @c: nfs_io_counter to use + * @l_ctx: nfs_lock_context with io_counter to use * * returns -ERESTARTSYS if interrupted by a fatal signal. * Otherwise returns 0 once the io_count hits 0. */ int -nfs_iocounter_wait(struct nfs_io_counter *c) +nfs_iocounter_wait(struct nfs_lock_context *l_ctx) { - if (atomic_read(&c->io_count) == 0) - return 0; - return __nfs_iocounter_wait(c); + return wait_on_atomic_t(&l_ctx->io_count, nfs_wait_atomic_killable, + TASK_KILLABLE); } /* @@ -370,7 +335,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct page *page, return ERR_CAST(l_ctx); } req->wb_lock_context = l_ctx; - nfs_iocounter_inc(&l_ctx->io_count); + atomic_inc(&l_ctx->io_count); /* Initialize the request struct. Initially, we assume a * long write-back delay. This will be adjusted in @@ -431,7 +396,8 @@ static void nfs_clear_request(struct nfs_page *req) req->wb_page = NULL; } if (l_ctx != NULL) { - nfs_iocounter_dec(&l_ctx->io_count); + if (atomic_dec_and_test(&l_ctx->io_count)) + wake_up_atomic_t(&l_ctx->io_count); nfs_put_lock_context(l_ctx); req->wb_lock_context = NULL; } @@ -664,22 +630,11 @@ EXPORT_SYMBOL_GPL(nfs_initiate_pgio); * @desc: IO descriptor * @hdr: pageio header */ -static int nfs_pgio_error(struct nfs_pageio_descriptor *desc, - struct nfs_pgio_header *hdr) +static void nfs_pgio_error(struct nfs_pgio_header *hdr) { - struct nfs_pgio_mirror *mirror; - u32 midx; - set_bit(NFS_IOHDR_REDO, &hdr->flags); nfs_pgio_data_destroy(hdr); hdr->completion_ops->completion(hdr); - /* TODO: Make sure it's right to clean up all mirrors here - * and not just hdr->pgio_mirror_idx */ - for (midx = 0; midx < desc->pg_mirror_count; midx++) { - mirror = &desc->pg_mirrors[midx]; - desc->pg_completion_ops->error_cleanup(&mirror->pg_list); - } - return -ENOMEM; } /** @@ -800,8 +755,11 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, unsigned int pagecount, pageused; pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count); - if (!nfs_pgarray_set(&hdr->page_array, pagecount)) - return nfs_pgio_error(desc, hdr); + if (!nfs_pgarray_set(&hdr->page_array, pagecount)) { + nfs_pgio_error(hdr); + desc->pg_error = -ENOMEM; + return desc->pg_error; + } nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq); pages = hdr->page_array.pagevec; @@ -819,8 +777,11 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, *pages++ = last_page = req->wb_page; } } - if (WARN_ON_ONCE(pageused != pagecount)) - return nfs_pgio_error(desc, hdr); + if (WARN_ON_ONCE(pageused != pagecount)) { + nfs_pgio_error(hdr); + desc->pg_error = -EINVAL; + return desc->pg_error; + } if ((desc->pg_ioflags & FLUSH_COND_STABLE) && (desc->pg_moreio || nfs_reqs_to_commit(&cinfo))) @@ -835,18 +796,13 @@ EXPORT_SYMBOL_GPL(nfs_generic_pgio); static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) { - struct nfs_pgio_mirror *mirror; struct nfs_pgio_header *hdr; int ret; - mirror = nfs_pgio_current_mirror(desc); - hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { - /* TODO: make sure this is right with mirroring - or - * should it back out all mirrors? */ - desc->pg_completion_ops->error_cleanup(&mirror->pg_list); - return -ENOMEM; + desc->pg_error = -ENOMEM; + return desc->pg_error; } nfs_pgheader_init(desc, hdr, nfs_pgio_header_free); ret = nfs_generic_pgio(desc, hdr); @@ -874,6 +830,9 @@ static int nfs_pageio_setup_mirroring(struct nfs_pageio_descriptor *pgio, mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req); + if (pgio->pg_error < 0) + return pgio->pg_error; + if (!mirror_count || mirror_count > NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX) return -EINVAL; @@ -903,12 +862,6 @@ static void nfs_pageio_cleanup_mirroring(struct nfs_pageio_descriptor *pgio) pgio->pg_mirrors_dynamic = NULL; } -static bool nfs_match_open_context(const struct nfs_open_context *ctx1, - const struct nfs_open_context *ctx2) -{ - return ctx1->cred == ctx2->cred && ctx1->state == ctx2->state; -} - static bool nfs_match_lock_context(const struct nfs_lock_context *l1, const struct nfs_lock_context *l2) { @@ -982,6 +935,8 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, } else { if (desc->pg_ops->pg_init) desc->pg_ops->pg_init(desc, req); + if (desc->pg_error < 0) + return 0; mirror->pg_base = req->wb_pgbase; } if (!nfs_can_coalesce_requests(prev, req, desc)) @@ -1147,6 +1102,8 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, bytes = req->wb_bytes; nfs_pageio_setup_mirroring(desc, req); + if (desc->pg_error < 0) + goto out_failed; for (midx = 0; midx < desc->pg_mirror_count; midx++) { if (midx) { @@ -1163,7 +1120,8 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, if (IS_ERR(dupreq)) { nfs_page_group_unlock(req); - return 0; + desc->pg_error = PTR_ERR(dupreq); + goto out_failed; } nfs_lock_request(dupreq); @@ -1176,10 +1134,32 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, if (nfs_pgio_has_mirroring(desc)) desc->pg_mirror_idx = midx; if (!nfs_pageio_add_request_mirror(desc, dupreq)) - return 0; + goto out_failed; } return 1; + +out_failed: + /* + * We might have failed before sending any reqs over wire. + * Clean up rest of the reqs in mirror pg_list. + */ + if (desc->pg_error) { + struct nfs_pgio_mirror *mirror; + void (*func)(struct list_head *); + + /* remember fatal errors */ + if (nfs_error_is_fatal(desc->pg_error)) + mapping_set_error(desc->pg_inode->i_mapping, + desc->pg_error); + + func = desc->pg_completion_ops->error_cleanup; + for (midx = 0; midx < desc->pg_mirror_count; midx++) { + mirror = &desc->pg_mirrors[midx]; + func(&mirror->pg_list); + } + } + return 0; } /* @@ -1232,7 +1212,7 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc, nfs_pageio_complete(desc); if (!list_empty(&failed)) { list_move(&failed, &hdr->pages); - return -EIO; + return desc->pg_error < 0 ? desc->pg_error : -EIO; } return 0; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 8abe27165ad0..a3592cc34a20 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -53,7 +53,7 @@ static DEFINE_SPINLOCK(pnfs_spinlock); static LIST_HEAD(pnfs_modules_tbl); static int -pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, +pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid, enum pnfs_iomode iomode, bool sync); /* Return the registered pnfs layout driver module matching given id */ @@ -385,13 +385,13 @@ static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg, enum pnfs_iomode iomode; bool send; - stateid = lo->plh_stateid; + nfs4_stateid_copy(&stateid, &lo->plh_stateid); iomode = lo->plh_return_iomode; send = pnfs_prepare_layoutreturn(lo); spin_unlock(&inode->i_lock); if (send) { /* Send an async layoutreturn so we dont deadlock */ - pnfs_send_layoutreturn(lo, stateid, iomode, false); + pnfs_send_layoutreturn(lo, &stateid, iomode, false); } } else spin_unlock(&inode->i_lock); @@ -566,10 +566,10 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg, int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, struct list_head *tmp_list, - struct pnfs_layout_range *recall_range) + const struct pnfs_layout_range *recall_range) { struct pnfs_layout_segment *lseg, *next; - int invalid = 0, removed = 0; + int remaining = 0; dprintk("%s:Begin lo %p\n", __func__, lo); @@ -582,11 +582,11 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, "offset %llu length %llu\n", __func__, lseg, lseg->pls_range.iomode, lseg->pls_range.offset, lseg->pls_range.length); - invalid++; - removed += mark_lseg_invalid(lseg, tmp_list); + if (!mark_lseg_invalid(lseg, tmp_list)) + remaining++; } - dprintk("%s:Return %i\n", __func__, invalid - removed); - return invalid - removed; + dprintk("%s:Return %i\n", __func__, remaining); + return remaining; } /* note free_me must contain lsegs from a single layout_hdr */ @@ -618,7 +618,6 @@ pnfs_destroy_layout(struct nfs_inode *nfsi) pnfs_get_layout_hdr(lo); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED); - pnfs_clear_retry_layoutget(lo); spin_unlock(&nfsi->vfs_inode.i_lock); pnfs_free_lseg_list(&tmp_list); pnfs_put_layout_hdr(lo); @@ -703,6 +702,8 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list, ret = -EAGAIN; spin_unlock(&inode->i_lock); pnfs_free_lseg_list(&lseg_list); + /* Free all lsegs that are attached to commit buckets */ + nfs_commit_inode(inode, 0); pnfs_put_layout_hdr(lo); iput(inode); } @@ -826,7 +827,7 @@ pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo) int pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, - struct pnfs_layout_range *range, + const struct pnfs_layout_range *range, struct nfs4_state *open_state) { int status = 0; @@ -861,7 +862,7 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, static struct pnfs_layout_segment * send_layoutget(struct pnfs_layout_hdr *lo, struct nfs_open_context *ctx, - struct pnfs_layout_range *range, + const struct pnfs_layout_range *range, gfp_t gfp_flags) { struct inode *ino = lo->plh_inode; @@ -872,44 +873,41 @@ send_layoutget(struct pnfs_layout_hdr *lo, dprintk("--> %s\n", __func__); - lgp = kzalloc(sizeof(*lgp), gfp_flags); - if (lgp == NULL) - return NULL; - - i_size = i_size_read(ino); - - lgp->args.minlength = PAGE_CACHE_SIZE; - if (lgp->args.minlength > range->length) - lgp->args.minlength = range->length; - if (range->iomode == IOMODE_READ) { - if (range->offset >= i_size) - lgp->args.minlength = 0; - else if (i_size - range->offset < lgp->args.minlength) - lgp->args.minlength = i_size - range->offset; - } - lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE; - lgp->args.range = *range; - lgp->args.type = server->pnfs_curr_ld->id; - lgp->args.inode = ino; - lgp->args.ctx = get_nfs_open_context(ctx); - lgp->gfp_flags = gfp_flags; - lgp->cred = lo->plh_lc_cred; - - /* Synchronously retrieve layout information from server and - * store in lseg. + /* + * Synchronously retrieve layout information from server and + * store in lseg. If we race with a concurrent seqid morphing + * op, then re-send the LAYOUTGET. */ - lseg = nfs4_proc_layoutget(lgp, gfp_flags); - if (IS_ERR(lseg)) { - switch (PTR_ERR(lseg)) { - case -ENOMEM: - case -ERESTARTSYS: - break; - default: - /* remember that LAYOUTGET failed and suspend trying */ - pnfs_layout_io_set_failed(lo, range->iomode); + do { + lgp = kzalloc(sizeof(*lgp), gfp_flags); + if (lgp == NULL) + return NULL; + + i_size = i_size_read(ino); + + lgp->args.minlength = PAGE_CACHE_SIZE; + if (lgp->args.minlength > range->length) + lgp->args.minlength = range->length; + if (range->iomode == IOMODE_READ) { + if (range->offset >= i_size) + lgp->args.minlength = 0; + else if (i_size - range->offset < lgp->args.minlength) + lgp->args.minlength = i_size - range->offset; } - return NULL; - } else + lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE; + pnfs_copy_range(&lgp->args.range, range); + lgp->args.type = server->pnfs_curr_ld->id; + lgp->args.inode = ino; + lgp->args.ctx = get_nfs_open_context(ctx); + lgp->gfp_flags = gfp_flags; + lgp->cred = lo->plh_lc_cred; + + lseg = nfs4_proc_layoutget(lgp, gfp_flags); + } while (lseg == ERR_PTR(-EAGAIN)); + + if (IS_ERR(lseg) && !nfs_error_is_fatal(PTR_ERR(lseg))) + lseg = NULL; + else pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(range->iomode)); @@ -940,7 +938,7 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) } static int -pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, +pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid, enum pnfs_iomode iomode, bool sync) { struct inode *ino = lo->plh_inode; @@ -957,7 +955,7 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, goto out; } - lrp->args.stateid = stateid; + nfs4_stateid_copy(&lrp->args.stateid, stateid); lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id; lrp->args.inode = ino; lrp->args.range.iomode = iomode; @@ -1000,7 +998,7 @@ _pnfs_return_layout(struct inode *ino) dprintk("NFS: %s no layout to return\n", __func__); goto out; } - stateid = nfsi->layout->plh_stateid; + nfs4_stateid_copy(&stateid, &nfsi->layout->plh_stateid); /* Reference matched in nfs4_layoutreturn_release */ pnfs_get_layout_hdr(lo); empty = list_empty(&lo->plh_segs); @@ -1028,7 +1026,7 @@ _pnfs_return_layout(struct inode *ino) spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&tmp_list); if (send) - status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true); + status = pnfs_send_layoutreturn(lo, &stateid, IOMODE_ANY, true); out_put_layout_hdr: pnfs_put_layout_hdr(lo); out: @@ -1091,13 +1089,12 @@ bool pnfs_roc(struct inode *ino) goto out_noroc; } - stateid = lo->plh_stateid; + nfs4_stateid_copy(&stateid, &lo->plh_stateid); /* always send layoutreturn if being marked so */ if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags)) layoutreturn = pnfs_prepare_layoutreturn(lo); - pnfs_clear_retry_layoutget(lo); list_for_each_entry_safe(lseg, tmp, &lo->plh_segs, pls_list) /* If we are sending layoutreturn, invalidate all valid lsegs */ if (layoutreturn || test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) { @@ -1119,7 +1116,7 @@ out_noroc: pnfs_free_lseg_list(&tmp_list); pnfs_layoutcommit_inode(ino, true); if (layoutreturn) - pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true); + pnfs_send_layoutreturn(lo, &stateid, IOMODE_ANY, true); return roc; } @@ -1144,6 +1141,7 @@ void pnfs_roc_set_barrier(struct inode *ino, u32 barrier) spin_lock(&ino->i_lock); lo = NFS_I(ino)->layout; + pnfs_mark_layout_returned_if_empty(lo); if (pnfs_seqid_is_newer(barrier, lo->plh_barrier)) lo->plh_barrier = barrier; spin_unlock(&ino->i_lock); @@ -1460,25 +1458,15 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx, return ret; } -/* stop waiting if someone clears NFS_LAYOUT_RETRY_LAYOUTGET bit. */ -static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key) -{ - if (!test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, key->flags)) - return 1; - return nfs_wait_bit_killable(key); -} - static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) { - if (!pnfs_should_retry_layoutget(lo)) - return false; /* * send layoutcommit as it can hold up layoutreturn due to lseg * reference */ pnfs_layoutcommit_inode(lo->plh_inode, false); return !wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN, - pnfs_layoutget_retry_bit_wait, + nfs_wait_bit_killable, TASK_UNINTERRUPTIBLE); } @@ -1515,14 +1503,23 @@ pnfs_update_layout(struct inode *ino, struct pnfs_layout_segment *lseg = NULL; bool first; - if (!pnfs_enabled_sb(NFS_SERVER(ino))) + if (!pnfs_enabled_sb(NFS_SERVER(ino))) { + trace_pnfs_update_layout(ino, pos, count, iomode, NULL, + PNFS_UPDATE_LAYOUT_NO_PNFS); goto out; + } - if (iomode == IOMODE_READ && i_size_read(ino) == 0) + if (iomode == IOMODE_READ && i_size_read(ino) == 0) { + trace_pnfs_update_layout(ino, pos, count, iomode, NULL, + PNFS_UPDATE_LAYOUT_RD_ZEROLEN); goto out; + } - if (pnfs_within_mdsthreshold(ctx, ino, iomode)) + if (pnfs_within_mdsthreshold(ctx, ino, iomode)) { + trace_pnfs_update_layout(ino, pos, count, iomode, NULL, + PNFS_UPDATE_LAYOUT_MDSTHRESH); goto out; + } lookup_again: first = false; @@ -1530,19 +1527,25 @@ lookup_again: lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); if (lo == NULL) { spin_unlock(&ino->i_lock); + trace_pnfs_update_layout(ino, pos, count, iomode, NULL, + PNFS_UPDATE_LAYOUT_NOMEM); goto out; } /* Do we even need to bother with this? */ if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) { + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + PNFS_UPDATE_LAYOUT_BULK_RECALL); dprintk("%s matches recall, use MDS\n", __func__); goto out_unlock; } /* if LAYOUTGET already failed once we don't try again */ - if (pnfs_layout_io_test_failed(lo, iomode) && - !pnfs_should_retry_layoutget(lo)) + if (pnfs_layout_io_test_failed(lo, iomode)) { + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + PNFS_UPDATE_LAYOUT_IO_TEST_FAIL); goto out_unlock; + } first = list_empty(&lo->plh_segs); if (first) { @@ -1562,8 +1565,11 @@ lookup_again: * already exists */ lseg = pnfs_find_lseg(lo, &arg); - if (lseg) + if (lseg) { + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + PNFS_UPDATE_LAYOUT_FOUND_CACHED); goto out_unlock; + } } /* @@ -1580,11 +1586,16 @@ lookup_again: dprintk("%s retrying\n", __func__); goto lookup_again; } + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + PNFS_UPDATE_LAYOUT_RETURN); goto out_put_layout_hdr; } - if (pnfs_layoutgets_blocked(lo)) + if (pnfs_layoutgets_blocked(lo)) { + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + PNFS_UPDATE_LAYOUT_BLOCKED); goto out_unlock; + } atomic_inc(&lo->plh_outstanding); spin_unlock(&ino->i_lock); @@ -1607,8 +1618,9 @@ lookup_again: arg.length = PAGE_CACHE_ALIGN(arg.length); lseg = send_layoutget(lo, ctx, &arg, gfp_flags); - pnfs_clear_retry_layoutget(lo); atomic_dec(&lo->plh_outstanding); + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET); out_put_layout_hdr: if (first) pnfs_clear_first_layoutget(lo); @@ -1618,7 +1630,7 @@ out: "(%s, offset: %llu, length: %llu)\n", __func__, ino->i_sb->s_id, (unsigned long long)NFS_FILEID(ino), - lseg == NULL ? "not found" : "found", + IS_ERR_OR_NULL(lseg) ? "not found" : "found", iomode==IOMODE_RW ? "read/write" : "read-only", (unsigned long long)pos, (unsigned long long)count); @@ -1687,6 +1699,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp) /* existing state ID, make sure the sequence number matches. */ if (pnfs_layout_stateid_blocked(lo, &res->stateid)) { dprintk("%s forget reply due to sequence\n", __func__); + status = -EAGAIN; goto out_forget_reply; } pnfs_set_layout_stateid(lo, &res->stateid, false); @@ -1724,16 +1737,29 @@ out_forget_reply: } static void +pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode) +{ + if (lo->plh_return_iomode == iomode) + return; + if (lo->plh_return_iomode != 0) + iomode = IOMODE_ANY; + lo->plh_return_iomode = iomode; +} + +int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, struct list_head *tmp_list, - struct pnfs_layout_range *return_range) + const struct pnfs_layout_range *return_range) { struct pnfs_layout_segment *lseg, *next; + int remaining = 0; dprintk("%s:Begin lo %p\n", __func__, lo); if (list_empty(&lo->plh_segs)) - return; + return 0; + + assert_spin_locked(&lo->plh_inode->i_lock); list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) if (should_free_lseg(&lseg->pls_range, return_range)) { @@ -1743,38 +1769,47 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, lseg->pls_range.offset, lseg->pls_range.length); set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); - mark_lseg_invalid(lseg, tmp_list); + pnfs_set_plh_return_iomode(lo, return_range->iomode); + if (!mark_lseg_invalid(lseg, tmp_list)) + remaining++; set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); } + return remaining; } void pnfs_error_mark_layout_for_return(struct inode *inode, struct pnfs_layout_segment *lseg) { struct pnfs_layout_hdr *lo = NFS_I(inode)->layout; - int iomode = pnfs_iomode_to_fail_bit(lseg->pls_range.iomode); struct pnfs_layout_range range = { .iomode = lseg->pls_range.iomode, .offset = 0, .length = NFS4_MAX_UINT64, }; LIST_HEAD(free_me); + bool return_now = false; spin_lock(&inode->i_lock); - /* set failure bit so that pnfs path will be retried later */ - pnfs_layout_set_fail_bit(lo, iomode); - if (lo->plh_return_iomode == 0) - lo->plh_return_iomode = range.iomode; - else if (lo->plh_return_iomode != range.iomode) - lo->plh_return_iomode = IOMODE_ANY; + pnfs_set_plh_return_iomode(lo, range.iomode); /* * mark all matching lsegs so that we are sure to have no live * segments at hand when sending layoutreturn. See pnfs_put_lseg() * for how it works. */ - pnfs_mark_matching_lsegs_return(lo, &free_me, &range); - spin_unlock(&inode->i_lock); + if (!pnfs_mark_matching_lsegs_return(lo, &free_me, &range)) { + nfs4_stateid stateid; + enum pnfs_iomode iomode = lo->plh_return_iomode; + + nfs4_stateid_copy(&stateid, &lo->plh_stateid); + return_now = pnfs_prepare_layoutreturn(lo); + spin_unlock(&inode->i_lock); + if (return_now) + pnfs_send_layoutreturn(lo, &stateid, iomode, false); + } else { + spin_unlock(&inode->i_lock); + nfs_commit_inode(inode, 0); + } pnfs_free_lseg_list(&free_me); } EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return); @@ -1796,6 +1831,11 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r rd_size, IOMODE_READ, GFP_KERNEL); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + return; + } } /* If no lseg, fall back to read through mds */ if (pgio->pg_lseg == NULL) @@ -1808,13 +1848,19 @@ void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req, u64 wb_size) { - if (pgio->pg_lseg == NULL) + if (pgio->pg_lseg == NULL) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, req_offset(req), wb_size, IOMODE_RW, GFP_NOFS); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + return; + } + } /* If no lseg, fall back to write through mds */ if (pgio->pg_lseg == NULL) nfs_pageio_reset_write_mds(pgio); @@ -1912,12 +1958,13 @@ static void pnfs_ld_handle_write_error(struct nfs_pgio_header *hdr) */ void pnfs_ld_write_done(struct nfs_pgio_header *hdr) { - trace_nfs4_pnfs_write(hdr, hdr->pnfs_error); - if (!hdr->pnfs_error) { + if (likely(!hdr->pnfs_error)) { pnfs_set_layoutcommit(hdr->inode, hdr->lseg, hdr->mds_offset + hdr->res.count); hdr->mds_ops->rpc_call_done(&hdr->task, hdr); - } else + } + trace_nfs4_pnfs_write(hdr, hdr->pnfs_error); + if (unlikely(hdr->pnfs_error)) pnfs_ld_handle_write_error(hdr); hdr->mds_ops->rpc_release(hdr); } @@ -1981,15 +2028,13 @@ static void pnfs_writehdr_free(struct nfs_pgio_header *hdr) int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) { - struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); - struct nfs_pgio_header *hdr; int ret; hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { - desc->pg_completion_ops->error_cleanup(&mirror->pg_list); - return -ENOMEM; + desc->pg_error = -ENOMEM; + return desc->pg_error; } nfs_pgheader_init(desc, hdr, pnfs_writehdr_free); @@ -2028,11 +2073,12 @@ static void pnfs_ld_handle_read_error(struct nfs_pgio_header *hdr) */ void pnfs_ld_read_done(struct nfs_pgio_header *hdr) { - trace_nfs4_pnfs_read(hdr, hdr->pnfs_error); if (likely(!hdr->pnfs_error)) { __nfs4_read_done_cb(hdr); hdr->mds_ops->rpc_call_done(&hdr->task, hdr); - } else + } + trace_nfs4_pnfs_read(hdr, hdr->pnfs_error); + if (unlikely(hdr->pnfs_error)) pnfs_ld_handle_read_error(hdr); hdr->mds_ops->rpc_release(hdr); } @@ -2111,15 +2157,13 @@ static void pnfs_readhdr_free(struct nfs_pgio_header *hdr) int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) { - struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); - struct nfs_pgio_header *hdr; int ret; hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { - desc->pg_completion_ops->error_cleanup(&mirror->pg_list); - return -ENOMEM; + desc->pg_error = -ENOMEM; + return desc->pg_error; } nfs_pgheader_init(desc, hdr, pnfs_readhdr_free); hdr->lseg = pnfs_get_lseg(desc->pg_lseg); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index d1990e90e7a0..9f4e2a47f4aa 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -98,7 +98,6 @@ enum { NFS_LAYOUT_RETURN_BEFORE_CLOSE, /* Return this layout before close */ NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */ NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */ - NFS_LAYOUT_RETRY_LAYOUTGET, /* Retry layoutget */ }; enum layoutdriver_policy_flags { @@ -261,11 +260,14 @@ void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, bool update_barrier); int pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, - struct pnfs_layout_range *range, + const struct pnfs_layout_range *range, struct nfs4_state *open_state); int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, struct list_head *tmp_list, - struct pnfs_layout_range *recall_range); + const struct pnfs_layout_range *recall_range); +int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, + struct list_head *tmp_list, + const struct pnfs_layout_range *recall_range); bool pnfs_roc(struct inode *ino); void pnfs_roc_release(struct inode *ino); void pnfs_roc_set_barrier(struct inode *ino, u32 barrier); @@ -379,26 +381,6 @@ nfs4_get_deviceid(struct nfs4_deviceid_node *d) return d; } -static inline void pnfs_set_retry_layoutget(struct pnfs_layout_hdr *lo) -{ - if (!test_and_set_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) - atomic_inc(&lo->plh_refcount); -} - -static inline void pnfs_clear_retry_layoutget(struct pnfs_layout_hdr *lo) -{ - if (test_and_clear_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) { - atomic_dec(&lo->plh_refcount); - /* wake up waiters for LAYOUTRETURN as that is not needed */ - wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN); - } -} - -static inline bool pnfs_should_retry_layoutget(struct pnfs_layout_hdr *lo) -{ - return test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags); -} - static inline struct pnfs_layout_segment * pnfs_get_lseg(struct pnfs_layout_segment *lseg) { @@ -409,6 +391,12 @@ pnfs_get_lseg(struct pnfs_layout_segment *lseg) return lseg; } +static inline bool +pnfs_is_valid_lseg(struct pnfs_layout_segment *lseg) +{ + return test_bit(NFS_LSEG_VALID, &lseg->pls_flags) != 0; +} + /* Return true if a layout driver is being used for this mountpoint */ static inline int pnfs_enabled_sb(struct nfs_server *nfss) { @@ -556,6 +544,26 @@ pnfs_calc_offset_length(u64 offset, u64 end) return 1 + end - offset; } +/** + * pnfs_mark_layout_returned_if_empty - marks the layout as returned + * @lo: layout header + * + * Note: Caller must hold inode->i_lock + */ +static inline void +pnfs_mark_layout_returned_if_empty(struct pnfs_layout_hdr *lo) +{ + if (list_empty(&lo->plh_segs)) + set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); +} + +static inline void +pnfs_copy_range(struct pnfs_layout_range *dst, + const struct pnfs_layout_range *src) +{ + memcpy(dst, src, sizeof(*dst)); +} + extern unsigned int layoutstats_timer; #ifdef NFS_DEBUG diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 24655b807d44..81ac6480f9e7 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -266,17 +266,14 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, } else { nfs_retry_commit(mds_pages, NULL, cinfo, 0); pnfs_generic_retry_commit(cinfo, 0); - cinfo->completion_ops->error_cleanup(NFS_I(inode)); return -ENOMEM; } } nreq += pnfs_generic_alloc_ds_commits(cinfo, &list); - if (nreq == 0) { - cinfo->completion_ops->error_cleanup(NFS_I(inode)); + if (nreq == 0) goto out; - } atomic_add(nreq, &cinfo->mds->rpcs_out); @@ -871,6 +868,11 @@ pnfs_layout_mark_request_commit(struct nfs_page *req, buckets = cinfo->ds->buckets; list = &buckets[ds_commit_idx].written; if (list_empty(list)) { + if (!pnfs_is_valid_lseg(lseg)) { + spin_unlock(cinfo->lock); + cinfo->completion_ops->resched_write(cinfo, req); + return; + } /* Non-empty buckets hold a reference on the lseg. That ref * is normally transferred to the COMMIT call and released * there. It could also be released if the last req is pulled diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 01b8cc8e8cfc..eb31e23e7def 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -85,6 +85,23 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) } EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); +static void nfs_readpage_release(struct nfs_page *req) +{ + struct inode *inode = d_inode(req->wb_context->dentry); + + dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(inode), req->wb_bytes, + (long long)req_offset(req)); + + if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) { + if (PageUptodate(req->wb_page)) + nfs_readpage_to_fscache(inode, req->wb_page, 0); + + unlock_page(req->wb_page); + } + nfs_release_request(req); +} + int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, struct page *page) { @@ -106,7 +123,10 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, nfs_pageio_init_read(&pgio, inode, false, &nfs_async_read_completion_ops); - nfs_pageio_add_request(&pgio, new); + if (!nfs_pageio_add_request(&pgio, new)) { + nfs_list_remove_request(new); + nfs_readpage_release(new); + } nfs_pageio_complete(&pgio); /* It doesn't make sense to do mirrored reads! */ @@ -115,24 +135,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, pgm = &pgio.pg_mirrors[0]; NFS_I(inode)->read_io += pgm->pg_bytes_written; - return 0; -} - -static void nfs_readpage_release(struct nfs_page *req) -{ - struct inode *inode = d_inode(req->wb_context->dentry); - - dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id, - (unsigned long long)NFS_FILEID(inode), req->wb_bytes, - (long long)req_offset(req)); - - if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) { - if (PageUptodate(req->wb_page)) - nfs_readpage_to_fscache(inode, req->wb_page, 0); - - unlock_page(req->wb_page); - } - nfs_release_request(req); + return pgio.pg_error < 0 ? pgio.pg_error : 0; } static void nfs_page_group_set_uptodate(struct nfs_page *req) @@ -246,6 +249,13 @@ static void nfs_readpage_retry(struct rpc_task *task, nfs_set_pgio_error(hdr, -EIO, argp->offset); return; } + + /* For non rpc-based layout drivers, retry-through-MDS */ + if (!task->tk_ops) { + hdr->pnfs_error = -EAGAIN; + return; + } + /* Yes, so retry the read at the end of the hdr */ hdr->mds_offset += resp->count; argp->offset += resp->count; @@ -268,7 +278,7 @@ static void nfs_readpage_result(struct rpc_task *task, hdr->good_bytes = bound - hdr->io_start; } spin_unlock(&hdr->lock); - } else if (hdr->res.count != hdr->args.count) + } else if (hdr->res.count < hdr->args.count) nfs_readpage_retry(task, hdr); } @@ -354,6 +364,8 @@ readpage_async_filler(void *data, struct page *page) if (len < PAGE_CACHE_SIZE) zero_user_segment(page, len, PAGE_CACHE_SIZE); if (!nfs_pageio_add_request(desc->pgio, new)) { + nfs_list_remove_request(new); + nfs_readpage_release(new); error = desc->pgio->pg_error; goto out_unlock; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 383a027de452..f1268280244e 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2816,7 +2816,6 @@ out_invalid_transport_udp: * NFS client for backwards compatibility */ unsigned int nfs_callback_set_tcpport; -unsigned short nfs_callback_tcpport; /* Default cache timeout is 10 minutes */ unsigned int nfs_idmap_cache_timeout = 600; /* Turn off NFSv4 uid/gid mapping when using AUTH_SYS */ @@ -2827,7 +2826,6 @@ char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN] = ""; bool recover_lost_locks = false; EXPORT_SYMBOL_GPL(nfs_callback_set_tcpport); -EXPORT_SYMBOL_GPL(nfs_callback_tcpport); EXPORT_SYMBOL_GPL(nfs_idmap_cache_timeout); EXPORT_SYMBOL_GPL(nfs4_disable_idmapping); EXPORT_SYMBOL_GPL(max_session_slots); diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c index b6de433da5db..4fe3eead3868 100644 --- a/fs/nfs/symlink.c +++ b/fs/nfs/symlink.c @@ -42,21 +42,35 @@ error: return -EIO; } -static const char *nfs_follow_link(struct dentry *dentry, void **cookie) +static const char *nfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(dentry); struct page *page; void *err; - err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping)); - if (err) - return err; - page = read_cache_page(&inode->i_data, 0, - (filler_t *)nfs_symlink_filler, inode); - if (IS_ERR(page)) - return ERR_CAST(page); - *cookie = page; - return kmap(page); + if (!dentry) { + err = ERR_PTR(nfs_revalidate_mapping_rcu(inode)); + if (err) + return err; + page = find_get_page(inode->i_mapping, 0); + if (!page) + return ERR_PTR(-ECHILD); + if (!PageUptodate(page)) { + put_page(page); + return ERR_PTR(-ECHILD); + } + } else { + err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping)); + if (err) + return err; + page = read_cache_page(&inode->i_data, 0, + (filler_t *)nfs_symlink_filler, inode); + if (IS_ERR(page)) + return ERR_CAST(page); + } + set_delayed_call(done, page_put_link, page); + return page_address(page); } /* @@ -64,8 +78,7 @@ static const char *nfs_follow_link(struct dentry *dentry, void **cookie) */ const struct inode_operations nfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = nfs_follow_link, - .put_link = page_put_link, + .get_link = nfs_get_link, .getattr = nfs_getattr, .setattr = nfs_setattr, }; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 75ab7622e0cc..ce43cd6d88c6 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -21,6 +21,8 @@ #include <linux/nfs_page.h> #include <linux/backing-dev.h> #include <linux/export.h> +#include <linux/freezer.h> +#include <linux/wait.h> #include <asm/uaccess.h> @@ -244,11 +246,9 @@ static int wb_priority(struct writeback_control *wbc) { int ret = 0; if (wbc->for_reclaim) - return FLUSH_HIGHPRI | FLUSH_STABLE; + return FLUSH_HIGHPRI | FLUSH_COND_STABLE; if (wbc->sync_mode == WB_SYNC_ALL) ret = FLUSH_COND_STABLE; - if (wbc->for_kupdate || wbc->for_background) - ret |= FLUSH_LOWPRI; return ret; } @@ -545,12 +545,22 @@ try_again: return head; } +static void nfs_write_error_remove_page(struct nfs_page *req) +{ + nfs_unlock_request(req); + nfs_end_page_writeback(req); + nfs_release_request(req); + generic_error_remove_page(page_file_mapping(req->wb_page), + req->wb_page); +} + /* * Find an associated nfs write request, and prepare to flush it out * May return an error if the user signalled nfs_wait_on_request(). */ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, - struct page *page, bool nonblock) + struct page *page, bool nonblock, + bool launder) { struct nfs_page *req; int ret = 0; @@ -567,8 +577,21 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, ret = 0; if (!nfs_pageio_add_request(pgio, req)) { - nfs_redirty_request(req); ret = pgio->pg_error; + /* + * Remove the problematic req upon fatal errors + * in launder case, while other dirty pages can + * still be around until they get flushed. + */ + if (nfs_error_is_fatal(ret)) { + nfs_context_set_write_error(req->wb_context, ret); + if (launder) { + nfs_write_error_remove_page(req); + goto out; + } + } + nfs_redirty_request(req); + ret = -EAGAIN; } else nfs_add_stats(page_file_mapping(page)->host, NFSIOS_WRITEPAGES, 1); @@ -576,12 +599,14 @@ out: return ret; } -static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio) +static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, + struct nfs_pageio_descriptor *pgio, bool launder) { int ret; nfs_pageio_cond_complete(pgio, page_file_index(page)); - ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); + ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE, + launder); if (ret == -EAGAIN) { redirty_page_for_writepage(wbc, page); ret = 0; @@ -592,7 +617,9 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st /* * Write an mmapped page to the server. */ -static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc) +static int nfs_writepage_locked(struct page *page, + struct writeback_control *wbc, + bool launder) { struct nfs_pageio_descriptor pgio; struct inode *inode = page_file_mapping(page)->host; @@ -601,7 +628,7 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false, &nfs_async_write_completion_ops); - err = nfs_do_writepage(page, wbc, &pgio); + err = nfs_do_writepage(page, wbc, &pgio, launder); nfs_pageio_complete(&pgio); if (err < 0) return err; @@ -614,7 +641,7 @@ int nfs_writepage(struct page *page, struct writeback_control *wbc) { int ret; - ret = nfs_writepage_locked(page, wbc); + ret = nfs_writepage_locked(page, wbc, false); unlock_page(page); return ret; } @@ -623,7 +650,7 @@ static int nfs_writepages_callback(struct page *page, struct writeback_control * { int ret; - ret = nfs_do_writepage(page, wbc, data); + ret = nfs_do_writepage(page, wbc, data, false); unlock_page(page); return ret; } @@ -1128,7 +1155,8 @@ int nfs_flush_incompatible(struct file *file, struct page *page) if (req == NULL) return 0; l_ctx = req->wb_lock_context; - do_flush = req->wb_page != page || req->wb_context != ctx; + do_flush = req->wb_page != page || + !nfs_match_open_context(req->wb_context, ctx); /* for now, flush if more than 1 request in page_group */ do_flush |= req->wb_this_page != req; if (l_ctx && flctx && @@ -1326,9 +1354,15 @@ static void nfs_async_write_error(struct list_head *head) } } +static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr) +{ + nfs_async_write_error(&hdr->pages); +} + static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = { .error_cleanup = nfs_async_write_error, .completion = nfs_write_completion, + .reschedule_io = nfs_async_write_reschedule_io, }; void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, @@ -1505,6 +1539,13 @@ static void nfs_writeback_result(struct rpc_task *task, task->tk_status = -EIO; return; } + + /* For non rpc-based layout drivers, retry-through-MDS */ + if (!task->tk_ops) { + hdr->pnfs_error = -EAGAIN; + return; + } + /* Was this an NFSv2 write or an NFSv3 stable write? */ if (resp->verf->committed != NFS_UNSTABLE) { /* Resend from where the server left off */ @@ -1522,27 +1563,21 @@ static void nfs_writeback_result(struct rpc_task *task, } } - -static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait) +static int wait_on_commit(struct nfs_mds_commit_info *cinfo) { - int ret; + return wait_on_atomic_t(&cinfo->rpcs_out, + nfs_wait_atomic_killable, TASK_KILLABLE); +} - if (!test_and_set_bit(NFS_INO_COMMIT, &nfsi->flags)) - return 1; - if (!may_wait) - return 0; - ret = out_of_line_wait_on_bit_lock(&nfsi->flags, - NFS_INO_COMMIT, - nfs_wait_bit_killable, - TASK_KILLABLE); - return (ret < 0) ? ret : 1; +static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) +{ + atomic_inc(&cinfo->rpcs_out); } -static void nfs_commit_clear_lock(struct nfs_inode *nfsi) +static void nfs_commit_end(struct nfs_mds_commit_info *cinfo) { - clear_bit(NFS_INO_COMMIT, &nfsi->flags); - smp_mb__after_atomic(); - wake_up_bit(&nfsi->flags, NFS_INO_COMMIT); + if (atomic_dec_and_test(&cinfo->rpcs_out)) + wake_up_atomic_t(&cinfo->rpcs_out); } void nfs_commitdata_release(struct nfs_commit_data *data) @@ -1659,6 +1694,13 @@ void nfs_retry_commit(struct list_head *page_list, } EXPORT_SYMBOL_GPL(nfs_retry_commit); +static void +nfs_commit_resched_write(struct nfs_commit_info *cinfo, + struct nfs_page *req) +{ + __set_page_dirty_nobuffers(req->wb_page); +} + /* * Commit dirty pages */ @@ -1680,7 +1722,6 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, data->mds_ops, how, 0); out_bad: nfs_retry_commit(head, NULL, cinfo, 0); - cinfo->completion_ops->error_cleanup(NFS_I(inode)); return -ENOMEM; } @@ -1742,8 +1783,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); nfs_init_cinfo(&cinfo, data->inode, data->dreq); - if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) - nfs_commit_clear_lock(NFS_I(data->inode)); + nfs_commit_end(cinfo.mds); } static void nfs_commit_release(void *calldata) @@ -1762,7 +1802,7 @@ static const struct rpc_call_ops nfs_commit_ops = { static const struct nfs_commit_completion_ops nfs_commit_completion_ops = { .completion = nfs_commit_release_pages, - .error_cleanup = nfs_commit_clear_lock, + .resched_write = nfs_commit_resched_write, }; int nfs_generic_commit_list(struct inode *inode, struct list_head *head, @@ -1781,30 +1821,25 @@ int nfs_commit_inode(struct inode *inode, int how) LIST_HEAD(head); struct nfs_commit_info cinfo; int may_wait = how & FLUSH_SYNC; + int error = 0; int res; - res = nfs_commit_set_lock(NFS_I(inode), may_wait); - if (res <= 0) - goto out_mark_dirty; nfs_init_cinfo_from_inode(&cinfo, inode); + nfs_commit_begin(cinfo.mds); res = nfs_scan_commit(inode, &head, &cinfo); - if (res) { - int error; - + if (res) error = nfs_generic_commit_list(inode, &head, how, &cinfo); - if (error < 0) - return error; - if (!may_wait) - goto out_mark_dirty; - error = wait_on_bit_action(&NFS_I(inode)->flags, - NFS_INO_COMMIT, - nfs_wait_bit_killable, - TASK_KILLABLE); - if (error < 0) - return error; - } else - nfs_commit_clear_lock(NFS_I(inode)); + nfs_commit_end(cinfo.mds); + if (error < 0) + goto out_error; + if (!may_wait) + goto out_mark_dirty; + error = wait_on_commit(cinfo.mds); + if (error < 0) + return error; return res; +out_error: + res = error; /* Note: If we exit without ensuring that the commit is complete, * we must mark the inode as dirty. Otherwise, future calls to * sync_inode() with the WB_SYNC_ALL flag set will fail to ensure @@ -1814,6 +1849,7 @@ out_mark_dirty: __mark_inode_dirty(inode, I_DIRTY_DATASYNC); return res; } +EXPORT_SYMBOL_GPL(nfs_commit_inode); int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) { @@ -1904,7 +1940,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) /* * Write back all requests on one page - we do this before reading it. */ -int nfs_wb_page(struct inode *inode, struct page *page) +int nfs_wb_single_page(struct inode *inode, struct page *page, bool launder) { loff_t range_start = page_file_offset(page); loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1); @@ -1921,7 +1957,7 @@ int nfs_wb_page(struct inode *inode, struct page *page) for (;;) { wait_on_page_writeback(page); if (clear_page_dirty_for_io(page)) { - ret = nfs_writepage_locked(page, &wbc); + ret = nfs_writepage_locked(page, &wbc, launder); if (ret < 0) goto out_error; continue; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index f6e7cbabac5a..2246454dec76 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -262,11 +262,11 @@ void fill_post_wcc(struct svc_fh *fhp) err = fh_getattr(fhp, &fhp->fh_post_attr); fhp->fh_post_change = d_inode(fhp->fh_dentry)->i_version; if (err) { - fhp->fh_post_saved = 0; + fhp->fh_post_saved = false; /* Grab the ctime anyway - set_change_info might use it */ fhp->fh_post_attr.ctime = d_inode(fhp->fh_dentry)->i_ctime; } else - fhp->fh_post_saved = 1; + fhp->fh_post_saved = true; } /* @@ -823,7 +823,7 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, } else dchild = dget(dparent); } else - dchild = lookup_one_len(name, dparent, namlen); + dchild = lookup_one_len_unlocked(name, dparent, namlen); if (IS_ERR(dchild)) return rv; if (d_mountpoint(dchild)) diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index ebf90e487c75..c9d6c715c0fb 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -201,6 +201,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, INIT_LIST_HEAD(&ls->ls_perfile); spin_lock_init(&ls->ls_lock); INIT_LIST_HEAD(&ls->ls_layouts); + mutex_init(&ls->ls_mutex); ls->ls_layout_type = layout_type; nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops, NFSPROC4_CLNT_CB_LAYOUT); @@ -262,19 +263,23 @@ nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp, status = nfserr_jukebox; if (!ls) goto out; + mutex_lock(&ls->ls_mutex); } else { ls = container_of(stid, struct nfs4_layout_stateid, ls_stid); status = nfserr_bad_stateid; + mutex_lock(&ls->ls_mutex); if (stateid->si_generation > stid->sc_stateid.si_generation) - goto out_put_stid; + goto out_unlock_stid; if (layout_type != ls->ls_layout_type) - goto out_put_stid; + goto out_unlock_stid; } *lsp = ls; return 0; +out_unlock_stid: + mutex_unlock(&ls->ls_mutex); out_put_stid: nfs4_put_stid(stid); out: @@ -296,8 +301,6 @@ nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls) trace_layout_recall(&ls->ls_stid.sc_stateid); atomic_inc(&ls->ls_stid.sc_count); - update_stateid(&ls->ls_stid.sc_stateid); - memcpy(&ls->ls_recall_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t)); nfsd4_run_cb(&ls->ls_recall); out_unlock: @@ -406,8 +409,7 @@ nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls) list_add_tail(&new->lo_perstate, &ls->ls_layouts); new = NULL; done: - update_stateid(&ls->ls_stid.sc_stateid); - memcpy(&lgp->lg_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&lgp->lg_sid, &ls->ls_stid); spin_unlock(&ls->ls_lock); out: spin_unlock(&fp->fi_lock); @@ -481,11 +483,8 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp, } } if (!list_empty(&ls->ls_layouts)) { - if (found) { - update_stateid(&ls->ls_stid.sc_stateid); - memcpy(&lrp->lr_sid, &ls->ls_stid.sc_stateid, - sizeof(stateid_t)); - } + if (found) + nfs4_inc_and_copy_stateid(&lrp->lr_sid, &ls->ls_stid); lrp->lrs_present = 1; } else { trace_layoutstate_unhash(&ls->ls_stid.sc_stateid); @@ -494,6 +493,7 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp, } spin_unlock(&ls->ls_lock); + mutex_unlock(&ls->ls_mutex); nfs4_put_stid(&ls->ls_stid); nfsd4_free_layouts(&reaplist); return nfs_ok; @@ -608,6 +608,17 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) } } +static void +nfsd4_cb_layout_prepare(struct nfsd4_callback *cb) +{ + struct nfs4_layout_stateid *ls = + container_of(cb, struct nfs4_layout_stateid, ls_recall); + + mutex_lock(&ls->ls_mutex); + nfs4_inc_and_copy_stateid(&ls->ls_recall_sid, &ls->ls_stid); + mutex_unlock(&ls->ls_mutex); +} + static int nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) { @@ -655,6 +666,7 @@ nfsd4_cb_layout_release(struct nfsd4_callback *cb) } static struct nfsd4_callback_ops nfsd4_cb_layout_ops = { + .prepare = nfsd4_cb_layout_prepare, .done = nfsd4_cb_layout_done, .release = nfsd4_cb_layout_release, }; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 4ce6b97b31ad..819ad812c71b 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -774,8 +774,9 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* check stateid */ - status = nfs4_preprocess_stateid_op(rqstp, cstate, &read->rd_stateid, - RD_STATE, &read->rd_filp, &read->rd_tmp_file); + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, + &read->rd_stateid, RD_STATE, + &read->rd_filp, &read->rd_tmp_file); if (status) { dprintk("NFSD: nfsd4_read: couldn't process stateid!\n"); goto out; @@ -921,7 +922,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (setattr->sa_iattr.ia_valid & ATTR_SIZE) { status = nfs4_preprocess_stateid_op(rqstp, cstate, - &setattr->sa_stateid, WR_STATE, NULL, NULL); + &cstate->current_fh, &setattr->sa_stateid, + WR_STATE, NULL, NULL); if (status) { dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n"); return status; @@ -985,8 +987,8 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (write->wr_offset >= OFFSET_MAX) return nfserr_inval; - status = nfs4_preprocess_stateid_op(rqstp, cstate, stateid, WR_STATE, - &filp, NULL); + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, + stateid, WR_STATE, &filp, NULL); if (status) { dprintk("NFSD: nfsd4_write: couldn't process stateid!\n"); return status; @@ -1010,13 +1012,54 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } static __be32 +nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + struct nfsd4_clone *clone) +{ + struct file *src, *dst; + __be32 status; + + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh, + &clone->cl_src_stateid, RD_STATE, + &src, NULL); + if (status) { + dprintk("NFSD: %s: couldn't process src stateid!\n", __func__); + goto out; + } + + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, + &clone->cl_dst_stateid, WR_STATE, + &dst, NULL); + if (status) { + dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__); + goto out_put_src; + } + + /* fix up for NFS-specific error code */ + if (!S_ISREG(file_inode(src)->i_mode) || + !S_ISREG(file_inode(dst)->i_mode)) { + status = nfserr_wrong_type; + goto out_put_dst; + } + + status = nfsd4_clone_file_range(src, clone->cl_src_pos, + dst, clone->cl_dst_pos, clone->cl_count); + +out_put_dst: + fput(dst); +out_put_src: + fput(src); +out: + return status; +} + +static __be32 nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_fallocate *fallocate, int flags) { __be32 status = nfserr_notsupp; struct file *file; - status = nfs4_preprocess_stateid_op(rqstp, cstate, + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &fallocate->falloc_stateid, WR_STATE, &file, NULL); if (status != nfs_ok) { @@ -1055,7 +1098,7 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct file *file; - status = nfs4_preprocess_stateid_op(rqstp, cstate, + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &seek->seek_stateid, RD_STATE, &file, NULL); if (status) { @@ -1309,6 +1352,7 @@ nfsd4_layoutget(struct svc_rqst *rqstp, nfserr = nfsd4_insert_layout(lgp, ls); out_put_stid: + mutex_unlock(&ls->ls_mutex); nfs4_put_stid(&ls->ls_stid); out: return nfserr; @@ -1362,6 +1406,9 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp, goto out; } + /* LAYOUTCOMMIT does not require any serialization */ + mutex_unlock(&ls->ls_mutex); + if (new_size > i_size_read(inode)) { lcp->lc_size_chg = 1; lcp->lc_newsize = new_size; @@ -2275,6 +2322,12 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_name = "OP_DEALLOCATE", .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, + [OP_CLONE] = { + .op_func = (nfsd4op_func)nfsd4_clone, + .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, + .op_name = "OP_CLONE", + .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + }, [OP_SEEK] = { .op_func = (nfsd4op_func)nfsd4_seek, .op_name = "OP_SEEK", diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 0f1d5691b795..df5dba687265 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -575,6 +575,7 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid; /* Will be incremented before return to client: */ atomic_set(&stid->sc_count, 1); + spin_lock_init(&stid->sc_lock); /* * It shouldn't be a problem to reuse an opaque stateid value. @@ -745,6 +746,18 @@ nfs4_put_stid(struct nfs4_stid *s) put_nfs4_file(fp); } +void +nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid) +{ + stateid_t *src = &stid->sc_stateid; + + spin_lock(&stid->sc_lock); + if (unlikely(++src->si_generation == 0)) + src->si_generation = 1; + memcpy(dst, src, sizeof(*dst)); + spin_unlock(&stid->sc_lock); +} + static void nfs4_put_deleg_lease(struct nfs4_file *fp) { struct file *filp = NULL; @@ -765,16 +778,68 @@ void nfs4_unhash_stid(struct nfs4_stid *s) s->sc_type = 0; } -static void +/** + * nfs4_get_existing_delegation - Discover if this delegation already exists + * @clp: a pointer to the nfs4_client we're granting a delegation to + * @fp: a pointer to the nfs4_file we're granting a delegation on + * + * Return: + * On success: NULL if an existing delegation was not found. + * + * On error: -EAGAIN if one was previously granted to this nfs4_client + * for this nfs4_file. + * + */ + +static int +nfs4_get_existing_delegation(struct nfs4_client *clp, struct nfs4_file *fp) +{ + struct nfs4_delegation *searchdp = NULL; + struct nfs4_client *searchclp = NULL; + + lockdep_assert_held(&state_lock); + lockdep_assert_held(&fp->fi_lock); + + list_for_each_entry(searchdp, &fp->fi_delegations, dl_perfile) { + searchclp = searchdp->dl_stid.sc_client; + if (clp == searchclp) { + return -EAGAIN; + } + } + return 0; +} + +/** + * hash_delegation_locked - Add a delegation to the appropriate lists + * @dp: a pointer to the nfs4_delegation we are adding. + * @fp: a pointer to the nfs4_file we're granting a delegation on + * + * Return: + * On success: NULL if the delegation was successfully hashed. + * + * On error: -EAGAIN if one was previously granted to this + * nfs4_client for this nfs4_file. Delegation is not hashed. + * + */ + +static int hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) { + int status; + struct nfs4_client *clp = dp->dl_stid.sc_client; + lockdep_assert_held(&state_lock); lockdep_assert_held(&fp->fi_lock); + status = nfs4_get_existing_delegation(clp, fp); + if (status) + return status; + ++fp->fi_delegees; atomic_inc(&dp->dl_stid.sc_count); dp->dl_stid.sc_type = NFS4_DELEG_STID; list_add(&dp->dl_perfile, &fp->fi_delegations); - list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations); + list_add(&dp->dl_perclnt, &clp->cl_delegations); + return 0; } static bool @@ -2256,15 +2321,20 @@ nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid) clid->flags = new->cl_exchange_flags; } +static bool client_has_openowners(struct nfs4_client *clp) +{ + struct nfs4_openowner *oo; + + list_for_each_entry(oo, &clp->cl_openowners, oo_perclient) { + if (!list_empty(&oo->oo_owner.so_stateids)) + return true; + } + return false; +} + static bool client_has_state(struct nfs4_client *clp) { - /* - * Note clp->cl_openowners check isn't quite right: there's no - * need to count owners without stateid's. - * - * Also note we should probably be using this in 4.0 case too. - */ - return !list_empty(&clp->cl_openowners) + return client_has_openowners(clp) #ifdef CONFIG_NFSD_PNFS || !list_empty(&clp->cl_lo_states) #endif @@ -3049,7 +3119,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, /* Cases below refer to rfc 3530 section 14.2.33: */ spin_lock(&nn->client_lock); conf = find_confirmed_client_by_name(&clname, nn); - if (conf) { + if (conf && client_has_state(conf)) { /* case 0: */ status = nfserr_clid_inuse; if (clp_used_exchangeid(conf)) @@ -3136,6 +3206,11 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, } else { /* case 3: normal case; new or rebooted client */ old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) { + status = nfserr_clid_inuse; + if (client_has_state(old) + && !same_creds(&unconf->cl_cred, + &old->cl_cred)) + goto out; status = mark_client_expired_locked(old); if (status) { old = NULL; @@ -3317,6 +3392,27 @@ static const struct nfs4_stateowner_operations openowner_ops = { .so_free = nfs4_free_openowner, }; +static struct nfs4_ol_stateid * +nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) +{ + struct nfs4_ol_stateid *local, *ret = NULL; + struct nfs4_openowner *oo = open->op_openowner; + + lockdep_assert_held(&fp->fi_lock); + + list_for_each_entry(local, &fp->fi_stateids, st_perfile) { + /* ignore lock owners */ + if (local->st_stateowner->so_is_open_owner == 0) + continue; + if (local->st_stateowner == &oo->oo_owner) { + ret = local; + atomic_inc(&ret->st_stid.sc_count); + break; + } + } + return ret; +} + static struct nfs4_openowner * alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, struct nfsd4_compound_state *cstate) @@ -3348,9 +3444,20 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, return ret; } -static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) { +static struct nfs4_ol_stateid * +init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, + struct nfsd4_open *open) +{ + struct nfs4_openowner *oo = open->op_openowner; + struct nfs4_ol_stateid *retstp = NULL; + spin_lock(&oo->oo_owner.so_client->cl_lock); + spin_lock(&fp->fi_lock); + + retstp = nfsd4_find_existing_open(fp, open); + if (retstp) + goto out_unlock; atomic_inc(&stp->st_stid.sc_count); stp->st_stid.sc_type = NFS4_OPEN_STID; INIT_LIST_HEAD(&stp->st_locks); @@ -3360,12 +3467,14 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, stp->st_access_bmap = 0; stp->st_deny_bmap = 0; stp->st_openstp = NULL; - spin_lock(&oo->oo_owner.so_client->cl_lock); + init_rwsem(&stp->st_rwsem); list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids); - spin_lock(&fp->fi_lock); list_add(&stp->st_perfile, &fp->fi_stateids); + +out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&oo->oo_owner.so_client->cl_lock); + return retstp; } /* @@ -3776,27 +3885,6 @@ out: return nfs_ok; } -static struct nfs4_ol_stateid * -nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) -{ - struct nfs4_ol_stateid *local, *ret = NULL; - struct nfs4_openowner *oo = open->op_openowner; - - spin_lock(&fp->fi_lock); - list_for_each_entry(local, &fp->fi_stateids, st_perfile) { - /* ignore lock owners */ - if (local->st_stateowner->so_is_open_owner == 0) - continue; - if (local->st_stateowner == &oo->oo_owner) { - ret = local; - atomic_inc(&ret->st_stid.sc_count); - break; - } - } - spin_unlock(&fp->fi_lock); - return ret; -} - static inline int nfs4_access_to_access(u32 nfs4_access) { int flags = 0; @@ -3945,6 +4033,18 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_file *fp, int flag) return fl; } +/** + * nfs4_setlease - Obtain a delegation by requesting lease from vfs layer + * @dp: a pointer to the nfs4_delegation we're adding. + * + * Return: + * On success: Return code will be 0 on success. + * + * On error: -EAGAIN if there was an existing delegation. + * nonzero if there is an error in other cases. + * + */ + static int nfs4_setlease(struct nfs4_delegation *dp) { struct nfs4_file *fp = dp->dl_stid.sc_file; @@ -3976,16 +4076,19 @@ static int nfs4_setlease(struct nfs4_delegation *dp) goto out_unlock; /* Race breaker */ if (fp->fi_deleg_file) { - status = 0; - ++fp->fi_delegees; - hash_delegation_locked(dp, fp); + status = hash_delegation_locked(dp, fp); goto out_unlock; } fp->fi_deleg_file = filp; - fp->fi_delegees = 1; - hash_delegation_locked(dp, fp); + fp->fi_delegees = 0; + status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); + if (status) { + /* Should never happen, this is a new fi_deleg_file */ + WARN_ON_ONCE(1); + goto out_fput; + } return 0; out_unlock: spin_unlock(&fp->fi_lock); @@ -4005,6 +4108,15 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, if (fp->fi_had_conflict) return ERR_PTR(-EAGAIN); + spin_lock(&state_lock); + spin_lock(&fp->fi_lock); + status = nfs4_get_existing_delegation(clp, fp); + spin_unlock(&fp->fi_lock); + spin_unlock(&state_lock); + + if (status) + return ERR_PTR(status); + dp = alloc_init_deleg(clp, fh, odstate); if (!dp) return ERR_PTR(-ENOMEM); @@ -4023,9 +4135,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, status = -EAGAIN; goto out_unlock; } - ++fp->fi_delegees; - hash_delegation_locked(dp, fp); - status = 0; + status = hash_delegation_locked(dp, fp); out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); @@ -4160,6 +4270,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf struct nfs4_client *cl = open->op_openowner->oo_owner.so_client; struct nfs4_file *fp = NULL; struct nfs4_ol_stateid *stp = NULL; + struct nfs4_ol_stateid *swapstp = NULL; struct nfs4_delegation *dp = NULL; __be32 status; @@ -4173,7 +4284,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf status = nfs4_check_deleg(cl, open, &dp); if (status) goto out; + spin_lock(&fp->fi_lock); stp = nfsd4_find_existing_open(fp, open); + spin_unlock(&fp->fi_lock); } else { open->op_file = NULL; status = nfserr_bad_stateid; @@ -4187,15 +4300,32 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf */ if (stp) { /* Stateid was found, this is an OPEN upgrade */ + down_read(&stp->st_rwsem); status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open); - if (status) + if (status) { + up_read(&stp->st_rwsem); goto out; + } } else { stp = open->op_stp; open->op_stp = NULL; - init_open_stateid(stp, fp, open); + swapstp = init_open_stateid(stp, fp, open); + if (swapstp) { + nfs4_put_stid(&stp->st_stid); + stp = swapstp; + down_read(&stp->st_rwsem); + status = nfs4_upgrade_open(rqstp, fp, current_fh, + stp, open); + if (status) { + up_read(&stp->st_rwsem); + goto out; + } + goto upgrade_out; + } + down_read(&stp->st_rwsem); status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open); if (status) { + up_read(&stp->st_rwsem); release_open_stateid(stp); goto out; } @@ -4205,8 +4335,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf if (stp->st_clnt_odstate == open->op_odstate) open->op_odstate = NULL; } - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); +upgrade_out: + nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid); + up_read(&stp->st_rwsem); if (nfsd4_has_session(&resp->cstate)) { if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) { @@ -4666,10 +4797,9 @@ nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s, */ __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, stateid_t *stateid, - int flags, struct file **filpp, bool *tmp_file) + struct nfsd4_compound_state *cstate, struct svc_fh *fhp, + stateid_t *stateid, int flags, struct file **filpp, bool *tmp_file) { - struct svc_fh *fhp = &cstate->current_fh; struct inode *ino = d_inode(fhp->fh_dentry); struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); @@ -4819,10 +4949,13 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ * revoked delegations are kept only for free_stateid. */ return nfserr_bad_stateid; + down_write(&stp->st_rwsem); status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate)); - if (status) - return status; - return nfs4_check_fh(current_fh, &stp->st_stid); + if (status == nfs_ok) + status = nfs4_check_fh(current_fh, &stp->st_stid); + if (status != nfs_ok) + up_write(&stp->st_rwsem); + return status; } /* @@ -4869,6 +5002,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs return status; oo = openowner(stp->st_stateowner); if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) { + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); return nfserr_bad_stateid; } @@ -4899,11 +5033,13 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; oo = openowner(stp->st_stateowner); status = nfserr_bad_stateid; - if (oo->oo_flags & NFS4_OO_CONFIRMED) + if (oo->oo_flags & NFS4_OO_CONFIRMED) { + up_write(&stp->st_rwsem); goto put_stateid; + } oo->oo_flags |= NFS4_OO_CONFIRMED; - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&oc->oc_resp_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid); + up_write(&stp->st_rwsem); dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n", __func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid)); @@ -4975,13 +5111,11 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, goto put_stateid; } nfs4_stateid_downgrade(stp, od->od_share_access); - reset_union_bmap_deny(od->od_share_deny, stp); - - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&od->od_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid); status = nfs_ok; put_stateid: + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); @@ -5033,8 +5167,8 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfsd4_bump_seqid(cstate, status); if (status) goto out; - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid); + up_write(&stp->st_rwsem); nfsd4_close_open_stateid(stp); @@ -5260,6 +5394,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; + init_rwsem(&stp->st_rwsem); list_add(&stp->st_locks, &open_stp->st_locks); list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids); spin_lock(&fp->fi_lock); @@ -5428,6 +5563,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &open_stp, nn); if (status) goto out; + up_write(&open_stp->st_rwsem); open_sop = openowner(open_stp->st_stateowner); status = nfserr_bad_stateid; if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid, @@ -5435,6 +5571,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; status = lookup_or_create_lock_state(cstate, open_stp, lock, &lock_stp, &new); + if (status == nfs_ok) + down_write(&lock_stp->st_rwsem); } else { status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, @@ -5512,9 +5650,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, err = vfs_lock_file(filp, F_SETLK, file_lock, conflock); switch (-err) { case 0: /* success! */ - update_stateid(&lock_stp->st_stid.sc_stateid); - memcpy(&lock->lk_resp_stateid, &lock_stp->st_stid.sc_stateid, - sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&lock->lk_resp_stateid, &lock_stp->st_stid); status = 0; break; case (EAGAIN): /* conflock holds conflicting lock */ @@ -5540,6 +5676,8 @@ out: seqid_mutating_err(ntohl(status))) lock_sop->lo_owner.so_seqid++; + up_write(&lock_stp->st_rwsem); + /* * If this is a new, never-before-used stateid, and we are * returning an error, then just go ahead and release it. @@ -5704,11 +5842,11 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("NFSD: nfs4_locku: vfs_lock_file failed!\n"); goto out_nfserr; } - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&locku->lu_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&locku->lu_stateid, &stp->st_stid); fput: fput(filp); put_stateid: + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 51c9e9ca39a4..d6ef0955a979 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1675,6 +1675,25 @@ nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp, } static __be32 +nfsd4_decode_clone(struct nfsd4_compoundargs *argp, struct nfsd4_clone *clone) +{ + DECODE_HEAD; + + status = nfsd4_decode_stateid(argp, &clone->cl_src_stateid); + if (status) + return status; + status = nfsd4_decode_stateid(argp, &clone->cl_dst_stateid); + if (status) + return status; + + READ_BUF(8 + 8 + 8); + p = xdr_decode_hyper(p, &clone->cl_src_pos); + p = xdr_decode_hyper(p, &clone->cl_dst_pos); + p = xdr_decode_hyper(p, &clone->cl_count); + DECODE_TAIL; +} + +static __be32 nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) { DECODE_HEAD; @@ -1785,6 +1804,7 @@ static nfsd4_dec nfsd4_dec_ops[] = { [OP_READ_PLUS] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_SEEK] = (nfsd4_dec)nfsd4_decode_seek, [OP_WRITE_SAME] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_CLONE] = (nfsd4_dec)nfsd4_decode_clone, }; static inline bool @@ -2838,14 +2858,14 @@ nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd, __be32 nfserr; int ignore_crossmnt = 0; - dentry = lookup_one_len(name, cd->rd_fhp->fh_dentry, namlen); + dentry = lookup_one_len_unlocked(name, cd->rd_fhp->fh_dentry, namlen); if (IS_ERR(dentry)) return nfserrno(PTR_ERR(dentry)); if (d_really_is_negative(dentry)) { /* - * nfsd_buffered_readdir drops the i_mutex between - * readdir and calling this callback, leaving a window - * where this directory entry could have gone away. + * we're not holding the i_mutex here, so there's + * a window where this directory entry could have gone + * away. */ dput(dentry); return nfserr_noent; @@ -4292,6 +4312,7 @@ static nfsd4_enc nfsd4_enc_ops[] = { [OP_READ_PLUS] = (nfsd4_enc)nfsd4_encode_noop, [OP_SEEK] = (nfsd4_enc)nfsd4_encode_seek, [OP_WRITE_SAME] = (nfsd4_enc)nfsd4_encode_noop, + [OP_CLONE] = (nfsd4_enc)nfsd4_encode_noop, }; /* diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 46ec934f5dee..54cde9a5864e 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -63,7 +63,6 @@ static unsigned int longest_chain; static unsigned int longest_chain_cachesize; static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec); -static void cache_cleaner_func(struct work_struct *unused); static unsigned long nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc); static unsigned long nfsd_reply_cache_scan(struct shrinker *shrink, @@ -76,13 +75,6 @@ static struct shrinker nfsd_reply_cache_shrinker = { }; /* - * locking for the reply cache: - * A cache entry is "single use" if c_state == RC_INPROG - * Otherwise, it when accessing _prev or _next, the lock must be held. - */ -static DECLARE_DELAYED_WORK(cache_cleaner, cache_cleaner_func); - -/* * Put a cap on the size of the DRC based on the amount of available * low memory in the machine. * @@ -203,7 +195,6 @@ void nfsd_reply_cache_shutdown(void) unsigned int i; unregister_shrinker(&nfsd_reply_cache_shrinker); - cancel_delayed_work_sync(&cache_cleaner); for (i = 0; i < drc_hashsize; i++) { struct list_head *head = &drc_hashtbl[i].lru_head; @@ -217,10 +208,8 @@ void nfsd_reply_cache_shutdown(void) drc_hashtbl = NULL; drc_hashsize = 0; - if (drc_slab) { - kmem_cache_destroy(drc_slab); - drc_slab = NULL; - } + kmem_cache_destroy(drc_slab); + drc_slab = NULL; } /* @@ -232,7 +221,6 @@ lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp) { rp->c_timestamp = jiffies; list_move_tail(&rp->c_lru, &b->lru_head); - schedule_delayed_work(&cache_cleaner, RC_EXPIRE); } static long @@ -266,7 +254,6 @@ prune_cache_entries(void) { unsigned int i; long freed = 0; - bool cancel = true; for (i = 0; i < drc_hashsize; i++) { struct nfsd_drc_bucket *b = &drc_hashtbl[i]; @@ -275,26 +262,11 @@ prune_cache_entries(void) continue; spin_lock(&b->cache_lock); freed += prune_bucket(b); - if (!list_empty(&b->lru_head)) - cancel = false; spin_unlock(&b->cache_lock); } - - /* - * Conditionally rearm the job to run in RC_EXPIRE since we just - * ran the pruner. - */ - if (!cancel) - mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE); return freed; } -static void -cache_cleaner_func(struct work_struct *unused) -{ - prune_cache_entries(); -} - static unsigned long nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc) { diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 350041a40fe5..c1681ce894c5 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -631,10 +631,7 @@ fh_put(struct svc_fh *fhp) fh_unlock(fhp); fhp->fh_dentry = NULL; dput(dentry); -#ifdef CONFIG_NFSD_V3 - fhp->fh_pre_saved = 0; - fhp->fh_post_saved = 0; -#endif + fh_clear_wcc(fhp); } fh_drop_write(fhp); if (exp) { diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 1e90dad4926b..2087bae17582 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -26,16 +26,16 @@ static inline ino_t u32_to_ino_t(__u32 uino) */ typedef struct svc_fh { struct knfsd_fh fh_handle; /* FH data */ + int fh_maxsize; /* max size for fh_handle */ struct dentry * fh_dentry; /* validated dentry */ struct svc_export * fh_export; /* export pointer */ - int fh_maxsize; /* max size for fh_handle */ - unsigned char fh_locked; /* inode locked by us */ - unsigned char fh_want_write; /* remount protection taken */ + bool fh_locked; /* inode locked by us */ + bool fh_want_write; /* remount protection taken */ #ifdef CONFIG_NFSD_V3 - unsigned char fh_post_saved; /* post-op attrs saved */ - unsigned char fh_pre_saved; /* pre-op attrs saved */ + bool fh_post_saved; /* post-op attrs saved */ + bool fh_pre_saved; /* pre-op attrs saved */ /* Pre-op attributes saved during fh_lock */ __u64 fh_pre_size; /* size before operation */ @@ -213,8 +213,8 @@ static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) static inline void fh_clear_wcc(struct svc_fh *fhp) { - fhp->fh_post_saved = 0; - fhp->fh_pre_saved = 0; + fhp->fh_post_saved = false; + fhp->fh_pre_saved = false; } /* @@ -231,7 +231,7 @@ fill_pre_wcc(struct svc_fh *fhp) fhp->fh_pre_ctime = inode->i_ctime; fhp->fh_pre_size = inode->i_size; fhp->fh_pre_change = inode->i_version; - fhp->fh_pre_saved = 1; + fhp->fh_pre_saved = true; } } @@ -267,7 +267,7 @@ fh_lock_nested(struct svc_fh *fhp, unsigned int subclass) inode = d_inode(dentry); mutex_lock_nested(&inode->i_mutex, subclass); fill_pre_wcc(fhp); - fhp->fh_locked = 1; + fhp->fh_locked = true; } static inline void @@ -285,7 +285,7 @@ fh_unlock(struct svc_fh *fhp) if (fhp->fh_locked) { fill_post_wcc(fhp); mutex_unlock(&d_inode(fhp->fh_dentry)->i_mutex); - fhp->fh_locked = 0; + fhp->fh_locked = false; } } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 583ffc13cae2..99432b7ecb9c 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -84,7 +84,7 @@ struct nfsd4_callback_ops { * fields that are of general use to any stateid. */ struct nfs4_stid { - atomic_t sc_count; + atomic_t sc_count; #define NFS4_OPEN_STID 1 #define NFS4_LOCK_STID 2 #define NFS4_DELEG_STID 4 @@ -94,11 +94,12 @@ struct nfs4_stid { #define NFS4_REVOKED_DELEG_STID 16 #define NFS4_CLOSED_DELEG_STID 32 #define NFS4_LAYOUT_STID 64 - unsigned char sc_type; - stateid_t sc_stateid; - struct nfs4_client *sc_client; - struct nfs4_file *sc_file; - void (*sc_free)(struct nfs4_stid *); + unsigned char sc_type; + stateid_t sc_stateid; + spinlock_t sc_lock; + struct nfs4_client *sc_client; + struct nfs4_file *sc_file; + void (*sc_free)(struct nfs4_stid *); }; /* @@ -364,15 +365,6 @@ struct nfs4_client_reclaim { char cr_recdir[HEXDIR_LEN]; /* recover dir */ }; -static inline void -update_stateid(stateid_t *stateid) -{ - stateid->si_generation++; - /* Wraparound recommendation from 3530bis-13 9.1.3.2: */ - if (stateid->si_generation == 0) - stateid->si_generation = 1; -} - /* A reasonable value for REPLAY_ISIZE was estimated as follows: * The OPEN response, typically the largest, requires * 4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) + 8(verifier) + @@ -534,15 +526,16 @@ struct nfs4_file { * Better suggestions welcome. */ struct nfs4_ol_stateid { - struct nfs4_stid st_stid; /* must be first field */ - struct list_head st_perfile; - struct list_head st_perstateowner; - struct list_head st_locks; - struct nfs4_stateowner * st_stateowner; - struct nfs4_clnt_odstate * st_clnt_odstate; - unsigned char st_access_bmap; - unsigned char st_deny_bmap; - struct nfs4_ol_stateid * st_openstp; + struct nfs4_stid st_stid; + struct list_head st_perfile; + struct list_head st_perstateowner; + struct list_head st_locks; + struct nfs4_stateowner *st_stateowner; + struct nfs4_clnt_odstate *st_clnt_odstate; + unsigned char st_access_bmap; + unsigned char st_deny_bmap; + struct nfs4_ol_stateid *st_openstp; + struct rw_semaphore st_rwsem; }; static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s) @@ -561,6 +554,7 @@ struct nfs4_layout_stateid { struct nfsd4_callback ls_recall; stateid_t ls_recall_sid; bool ls_recalled; + struct mutex ls_mutex; }; static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s) @@ -584,8 +578,8 @@ struct nfsd4_compound_state; struct nfsd_net; extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, stateid_t *stateid, - int flags, struct file **filp, bool *tmp_file); + struct nfsd4_compound_state *cstate, struct svc_fh *fhp, + stateid_t *stateid, int flags, struct file **filp, bool *tmp_file); __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s, struct nfsd_net *nn); @@ -593,6 +587,7 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab); void nfs4_unhash_stid(struct nfs4_stid *s); void nfs4_put_stid(struct nfs4_stid *s); +void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid); void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *); extern void nfs4_release_reclaim(struct nfsd_net *); extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir, diff --git a/fs/nfsd/trace.c b/fs/nfsd/trace.c index 82f89070594c..90967466a1e5 100644 --- a/fs/nfsd/trace.c +++ b/fs/nfsd/trace.c @@ -1,5 +1,3 @@ -#include "state.h" - #define CREATE_TRACE_POINTS #include "trace.h" diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index c668520c344b..0befe762762b 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -9,6 +9,8 @@ #include <linux/tracepoint.h> +#include "state.h" + DECLARE_EVENT_CLASS(nfsd_stateid_class, TP_PROTO(stateid_t *stp), TP_ARGS(stp), diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 45c04979e7b3..d41c149fae75 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -36,6 +36,7 @@ #endif /* CONFIG_NFSD_V3 */ #ifdef CONFIG_NFSD_V4 +#include "../internal.h" #include "acl.h" #include "idmap.h" #endif /* CONFIG_NFSD_V4 */ @@ -217,10 +218,16 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, host_err = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_nfserr; - /* - * check if we have crossed a mount point ... - */ if (nfsd_mountpoint(dentry, exp)) { + /* + * We don't need the i_mutex after all. It's + * still possible we could open this (regular + * files can be mountpoints too), but the + * i_mutex is just there to prevent renames of + * something that we might be about to delegate, + * and a mountpoint won't be renamed: + */ + fh_unlock(fhp); if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) { dput(dentry); goto out_nfserr; @@ -498,6 +505,13 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, } #endif +__be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, + u64 dst_pos, u64 count) +{ + return nfserrno(vfs_clone_file_range(src, src_pos, dst, dst_pos, + count)); +} + __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, loff_t len, int flags) @@ -1631,7 +1645,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, /* cannot use fh_lock as we need deadlock protective ordering * so do it by hand */ trap = lock_rename(tdentry, fdentry); - ffhp->fh_locked = tfhp->fh_locked = 1; + ffhp->fh_locked = tfhp->fh_locked = true; fill_pre_wcc(ffhp); fill_pre_wcc(tfhp); @@ -1681,7 +1695,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, fill_post_wcc(ffhp); fill_post_wcc(tfhp); unlock_rename(tdentry, fdentry); - ffhp->fh_locked = tfhp->fh_locked = 0; + ffhp->fh_locked = tfhp->fh_locked = false; fh_drop_write(ffhp); out: @@ -1809,7 +1823,6 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func, offset = *offsetp; while (1) { - struct inode *dir_inode = file_inode(file); unsigned int reclen; cdp->err = nfserr_eof; /* will be cleared on successful read */ @@ -1828,15 +1841,6 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func, if (!size) break; - /* - * Various filldir functions may end up calling back into - * lookup_one_len() and the file system's ->lookup() method. - * These expect i_mutex to be held, as it would within readdir. - */ - host_err = mutex_lock_killable(&dir_inode->i_mutex); - if (host_err) - break; - de = (struct buffered_dirent *)buf.dirent; while (size > 0) { offset = de->offset; @@ -1853,7 +1857,6 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func, size -= reclen; de = (struct buffered_dirent *)((char *)de + reclen); } - mutex_unlock(&dir_inode->i_mutex); if (size > 0) /* We bailed out early */ break; diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index fee2451ae248..c11ba316f23f 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -56,6 +56,8 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *, struct xdr_netobj *); __be32 nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *, struct file *, loff_t, loff_t, int); +__be32 nfsd4_clone_file_range(struct file *, u64, struct file *, + u64, u64); #endif /* CONFIG_NFSD_V4 */ __be32 nfsd_create(struct svc_rqst *, struct svc_fh *, char *name, int len, struct iattr *attrs, @@ -112,14 +114,14 @@ static inline int fh_want_write(struct svc_fh *fh) int ret = mnt_want_write(fh->fh_export->ex_path.mnt); if (!ret) - fh->fh_want_write = 1; + fh->fh_want_write = true; return ret; } static inline void fh_drop_write(struct svc_fh *fh) { if (fh->fh_want_write) { - fh->fh_want_write = 0; + fh->fh_want_write = false; mnt_drop_write(fh->fh_export->ex_path.mnt); } } diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 9f991007a578..d9554813e58a 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -491,6 +491,15 @@ struct nfsd4_fallocate { u64 falloc_length; }; +struct nfsd4_clone { + /* request */ + stateid_t cl_src_stateid; + stateid_t cl_dst_stateid; + u64 cl_src_pos; + u64 cl_dst_pos; + u64 cl_count; +}; + struct nfsd4_seek { /* request */ stateid_t seek_stateid; @@ -555,6 +564,7 @@ struct nfsd4_op { /* NFSv4.2 */ struct nfsd4_fallocate allocate; struct nfsd4_fallocate deallocate; + struct nfsd4_clone clone; struct nfsd4_seek seek; } u; struct nfs4_replay * replay; @@ -632,7 +642,7 @@ static inline void set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) { BUG_ON(!fhp->fh_pre_saved); - cinfo->atomic = fhp->fh_post_saved; + cinfo->atomic = (u32)fhp->fh_post_saved; cinfo->change_supported = IS_I_VERSION(d_inode(fhp->fh_dentry)); cinfo->before_change = fhp->fh_pre_change; diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 8df0f3b7839b..2ccbf5531554 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -133,38 +133,38 @@ nilfs_palloc_bitmap_blkoff(const struct inode *inode, unsigned long group) /** * nilfs_palloc_group_desc_nfrees - get the number of free entries in a group - * @inode: inode of metadata file using this allocator - * @group: group number * @desc: pointer to descriptor structure for the group + * @lock: spin lock protecting @desc */ static unsigned long -nilfs_palloc_group_desc_nfrees(struct inode *inode, unsigned long group, - const struct nilfs_palloc_group_desc *desc) +nilfs_palloc_group_desc_nfrees(const struct nilfs_palloc_group_desc *desc, + spinlock_t *lock) { unsigned long nfree; - spin_lock(nilfs_mdt_bgl_lock(inode, group)); + spin_lock(lock); nfree = le32_to_cpu(desc->pg_nfrees); - spin_unlock(nilfs_mdt_bgl_lock(inode, group)); + spin_unlock(lock); return nfree; } /** * nilfs_palloc_group_desc_add_entries - adjust count of free entries - * @inode: inode of metadata file using this allocator - * @group: group number * @desc: pointer to descriptor structure for the group + * @lock: spin lock protecting @desc * @n: delta to be added */ -static void -nilfs_palloc_group_desc_add_entries(struct inode *inode, - unsigned long group, - struct nilfs_palloc_group_desc *desc, - u32 n) +static u32 +nilfs_palloc_group_desc_add_entries(struct nilfs_palloc_group_desc *desc, + spinlock_t *lock, u32 n) { - spin_lock(nilfs_mdt_bgl_lock(inode, group)); + u32 nfree; + + spin_lock(lock); le32_add_cpu(&desc->pg_nfrees, n); - spin_unlock(nilfs_mdt_bgl_lock(inode, group)); + nfree = le32_to_cpu(desc->pg_nfrees); + spin_unlock(lock); + return nfree; } /** @@ -240,6 +240,26 @@ static int nilfs_palloc_get_block(struct inode *inode, unsigned long blkoff, } /** + * nilfs_palloc_delete_block - delete a block on the persistent allocator file + * @inode: inode of metadata file using this allocator + * @blkoff: block offset + * @prev: nilfs_bh_assoc struct of the last used buffer + * @lock: spin lock protecting @prev + */ +static int nilfs_palloc_delete_block(struct inode *inode, unsigned long blkoff, + struct nilfs_bh_assoc *prev, + spinlock_t *lock) +{ + spin_lock(lock); + if (prev->bh && blkoff == prev->blkoff) { + brelse(prev->bh); + prev->bh = NULL; + } + spin_unlock(lock); + return nilfs_mdt_delete_block(inode, blkoff); +} + +/** * nilfs_palloc_get_desc_block - get buffer head of a group descriptor block * @inode: inode of metadata file using this allocator * @group: group number @@ -278,6 +298,22 @@ static int nilfs_palloc_get_bitmap_block(struct inode *inode, } /** + * nilfs_palloc_delete_bitmap_block - delete a bitmap block + * @inode: inode of metadata file using this allocator + * @group: group number + */ +static int nilfs_palloc_delete_bitmap_block(struct inode *inode, + unsigned long group) +{ + struct nilfs_palloc_cache *cache = NILFS_MDT(inode)->mi_palloc_cache; + + return nilfs_palloc_delete_block(inode, + nilfs_palloc_bitmap_blkoff(inode, + group), + &cache->prev_bitmap, &cache->lock); +} + +/** * nilfs_palloc_get_entry_block - get buffer head of an entry block * @inode: inode of metadata file using this allocator * @nr: serial number of the entry (e.g. inode number) @@ -296,6 +332,20 @@ int nilfs_palloc_get_entry_block(struct inode *inode, __u64 nr, } /** + * nilfs_palloc_delete_entry_block - delete an entry block + * @inode: inode of metadata file using this allocator + * @nr: serial number of the entry + */ +static int nilfs_palloc_delete_entry_block(struct inode *inode, __u64 nr) +{ + struct nilfs_palloc_cache *cache = NILFS_MDT(inode)->mi_palloc_cache; + + return nilfs_palloc_delete_block(inode, + nilfs_palloc_entry_blkoff(inode, nr), + &cache->prev_entry, &cache->lock); +} + +/** * nilfs_palloc_block_get_group_desc - get kernel address of a group descriptor * @inode: inode of metadata file using this allocator * @group: group number @@ -332,51 +382,40 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr, /** * nilfs_palloc_find_available_slot - find available slot in a group - * @inode: inode of metadata file using this allocator - * @group: group number - * @target: offset number of an entry in the group (start point) * @bitmap: bitmap of the group + * @target: offset number of an entry in the group (start point) * @bsize: size in bits + * @lock: spin lock protecting @bitmap */ -static int nilfs_palloc_find_available_slot(struct inode *inode, - unsigned long group, +static int nilfs_palloc_find_available_slot(unsigned char *bitmap, unsigned long target, - unsigned char *bitmap, - int bsize) -{ - int curr, pos, end, i; - - if (target > 0) { - end = (target + BITS_PER_LONG - 1) & ~(BITS_PER_LONG - 1); - if (end > bsize) - end = bsize; - pos = nilfs_find_next_zero_bit(bitmap, end, target); - if (pos < end && - !nilfs_set_bit_atomic( - nilfs_mdt_bgl_lock(inode, group), pos, bitmap)) - return pos; - } else - end = 0; - - for (i = 0, curr = end; - i < bsize; - i += BITS_PER_LONG, curr += BITS_PER_LONG) { - /* wrap around */ - if (curr >= bsize) - curr = 0; - while (*((unsigned long *)bitmap + curr / BITS_PER_LONG) - != ~0UL) { - end = curr + BITS_PER_LONG; - if (end > bsize) - end = bsize; - pos = nilfs_find_next_zero_bit(bitmap, end, curr); - if ((pos < end) && - !nilfs_set_bit_atomic( - nilfs_mdt_bgl_lock(inode, group), pos, - bitmap)) + unsigned bsize, + spinlock_t *lock) +{ + int pos, end = bsize; + + if (likely(target < bsize)) { + pos = target; + do { + pos = nilfs_find_next_zero_bit(bitmap, end, pos); + if (pos >= end) + break; + if (!nilfs_set_bit_atomic(lock, pos, bitmap)) return pos; - } + } while (++pos < end); + + end = target; + } + + /* wrap around */ + for (pos = 0; pos < end; pos++) { + pos = nilfs_find_next_zero_bit(bitmap, end, pos); + if (pos >= end) + break; + if (!nilfs_set_bit_atomic(lock, pos, bitmap)) + return pos; } + return -ENOSPC; } @@ -475,15 +514,15 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode, void *desc_kaddr, *bitmap_kaddr; unsigned long group, maxgroup, ngroups; unsigned long group_offset, maxgroup_offset; - unsigned long n, entries_per_group, groups_per_desc_block; + unsigned long n, entries_per_group; unsigned long i, j; + spinlock_t *lock; int pos, ret; ngroups = nilfs_palloc_groups_count(inode); maxgroup = ngroups - 1; group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset); entries_per_group = nilfs_palloc_entries_per_group(inode); - groups_per_desc_block = nilfs_palloc_groups_per_desc_block(inode); for (i = 0; i < ngroups; i += n) { if (group >= ngroups) { @@ -501,8 +540,8 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode, n = nilfs_palloc_rest_groups_in_desc_block(inode, group, maxgroup); for (j = 0; j < n; j++, desc++, group++) { - if (nilfs_palloc_group_desc_nfrees(inode, group, desc) - > 0) { + lock = nilfs_mdt_bgl_lock(inode, group); + if (nilfs_palloc_group_desc_nfrees(desc, lock) > 0) { ret = nilfs_palloc_get_bitmap_block( inode, group, 1, &bitmap_bh); if (ret < 0) @@ -510,12 +549,12 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode, bitmap_kaddr = kmap(bitmap_bh->b_page); bitmap = bitmap_kaddr + bh_offset(bitmap_bh); pos = nilfs_palloc_find_available_slot( - inode, group, group_offset, bitmap, - entries_per_group); + bitmap, group_offset, + entries_per_group, lock); if (pos >= 0) { /* found a free entry */ nilfs_palloc_group_desc_add_entries( - inode, group, desc, -1); + desc, lock, -1); req->pr_entry_nr = entries_per_group * group + pos; kunmap(desc_bh->b_page); @@ -573,6 +612,7 @@ void nilfs_palloc_commit_free_entry(struct inode *inode, unsigned long group, group_offset; unsigned char *bitmap; void *desc_kaddr, *bitmap_kaddr; + spinlock_t *lock; group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset); desc_kaddr = kmap(req->pr_desc_bh->b_page); @@ -580,13 +620,15 @@ void nilfs_palloc_commit_free_entry(struct inode *inode, req->pr_desc_bh, desc_kaddr); bitmap_kaddr = kmap(req->pr_bitmap_bh->b_page); bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh); + lock = nilfs_mdt_bgl_lock(inode, group); - if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group), - group_offset, bitmap)) - printk(KERN_WARNING "%s: entry number %llu already freed\n", - __func__, (unsigned long long)req->pr_entry_nr); + if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) + nilfs_warning(inode->i_sb, __func__, + "entry number %llu already freed: ino=%lu\n", + (unsigned long long)req->pr_entry_nr, + (unsigned long)inode->i_ino); else - nilfs_palloc_group_desc_add_entries(inode, group, desc, 1); + nilfs_palloc_group_desc_add_entries(desc, lock, 1); kunmap(req->pr_bitmap_bh->b_page); kunmap(req->pr_desc_bh->b_page); @@ -611,6 +653,7 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode, void *desc_kaddr, *bitmap_kaddr; unsigned char *bitmap; unsigned long group, group_offset; + spinlock_t *lock; group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset); desc_kaddr = kmap(req->pr_desc_bh->b_page); @@ -618,12 +661,15 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode, req->pr_desc_bh, desc_kaddr); bitmap_kaddr = kmap(req->pr_bitmap_bh->b_page); bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh); - if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group), - group_offset, bitmap)) - printk(KERN_WARNING "%s: entry number %llu already freed\n", - __func__, (unsigned long long)req->pr_entry_nr); + lock = nilfs_mdt_bgl_lock(inode, group); + + if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) + nilfs_warning(inode->i_sb, __func__, + "entry number %llu already freed: ino=%lu\n", + (unsigned long long)req->pr_entry_nr, + (unsigned long)inode->i_ino); else - nilfs_palloc_group_desc_add_entries(inode, group, desc, 1); + nilfs_palloc_group_desc_add_entries(desc, lock, 1); kunmap(req->pr_bitmap_bh->b_page); kunmap(req->pr_desc_bh->b_page); @@ -680,22 +726,6 @@ void nilfs_palloc_abort_free_entry(struct inode *inode, } /** - * nilfs_palloc_group_is_in - judge if an entry is in a group - * @inode: inode of metadata file using this allocator - * @group: group number - * @nr: serial number of the entry (e.g. inode number) - */ -static int -nilfs_palloc_group_is_in(struct inode *inode, unsigned long group, __u64 nr) -{ - __u64 first, last; - - first = group * nilfs_palloc_entries_per_group(inode); - last = first + nilfs_palloc_entries_per_group(inode) - 1; - return (nr >= first) && (nr <= last); -} - -/** * nilfs_palloc_freev - deallocate a set of persistent objects * @inode: inode of metadata file using this allocator * @entry_nrs: array of entry numbers to be deallocated @@ -708,9 +738,18 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) unsigned char *bitmap; void *desc_kaddr, *bitmap_kaddr; unsigned long group, group_offset; - int i, j, n, ret; + __u64 group_min_nr, last_nrs[8]; + const unsigned long epg = nilfs_palloc_entries_per_group(inode); + const unsigned epb = NILFS_MDT(inode)->mi_entries_per_block; + unsigned entry_start, end, pos; + spinlock_t *lock; + int i, j, k, ret; + u32 nfree; for (i = 0; i < nitems; i = j) { + int change_group = false; + int nempties = 0, n = 0; + group = nilfs_palloc_group(inode, entry_nrs[i], &group_offset); ret = nilfs_palloc_get_desc_block(inode, group, 0, &desc_bh); if (ret < 0) @@ -721,38 +760,89 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) brelse(desc_bh); return ret; } - desc_kaddr = kmap(desc_bh->b_page); - desc = nilfs_palloc_block_get_group_desc( - inode, group, desc_bh, desc_kaddr); + + /* Get the first entry number of the group */ + group_min_nr = (__u64)group * epg; + bitmap_kaddr = kmap(bitmap_bh->b_page); bitmap = bitmap_kaddr + bh_offset(bitmap_bh); - for (j = i, n = 0; - (j < nitems) && nilfs_palloc_group_is_in(inode, group, - entry_nrs[j]); - j++) { - nilfs_palloc_group(inode, entry_nrs[j], &group_offset); - if (!nilfs_clear_bit_atomic( - nilfs_mdt_bgl_lock(inode, group), - group_offset, bitmap)) { - printk(KERN_WARNING - "%s: entry number %llu already freed\n", - __func__, - (unsigned long long)entry_nrs[j]); + lock = nilfs_mdt_bgl_lock(inode, group); + + j = i; + entry_start = rounddown(group_offset, epb); + do { + if (!nilfs_clear_bit_atomic(lock, group_offset, + bitmap)) { + nilfs_warning(inode->i_sb, __func__, + "entry number %llu already freed: ino=%lu\n", + (unsigned long long)entry_nrs[j], + (unsigned long)inode->i_ino); } else { n++; } - } - nilfs_palloc_group_desc_add_entries(inode, group, desc, n); + + j++; + if (j >= nitems || entry_nrs[j] < group_min_nr || + entry_nrs[j] >= group_min_nr + epg) { + change_group = true; + } else { + group_offset = entry_nrs[j] - group_min_nr; + if (group_offset >= entry_start && + group_offset < entry_start + epb) { + /* This entry is in the same block */ + continue; + } + } + + /* Test if the entry block is empty or not */ + end = entry_start + epb; + pos = nilfs_find_next_bit(bitmap, end, entry_start); + if (pos >= end) { + last_nrs[nempties++] = entry_nrs[j - 1]; + if (nempties >= ARRAY_SIZE(last_nrs)) + break; + } + + if (change_group) + break; + + /* Go on to the next entry block */ + entry_start = rounddown(group_offset, epb); + } while (true); kunmap(bitmap_bh->b_page); - kunmap(desc_bh->b_page); + mark_buffer_dirty(bitmap_bh); + brelse(bitmap_bh); + for (k = 0; k < nempties; k++) { + ret = nilfs_palloc_delete_entry_block(inode, + last_nrs[k]); + if (ret && ret != -ENOENT) { + nilfs_warning(inode->i_sb, __func__, + "failed to delete block of entry %llu: ino=%lu, err=%d\n", + (unsigned long long)last_nrs[k], + (unsigned long)inode->i_ino, ret); + } + } + + desc_kaddr = kmap_atomic(desc_bh->b_page); + desc = nilfs_palloc_block_get_group_desc( + inode, group, desc_bh, desc_kaddr); + nfree = nilfs_palloc_group_desc_add_entries(desc, lock, n); + kunmap_atomic(desc_kaddr); mark_buffer_dirty(desc_bh); - mark_buffer_dirty(bitmap_bh); nilfs_mdt_mark_dirty(inode); - - brelse(bitmap_bh); brelse(desc_bh); + + if (nfree == nilfs_palloc_entries_per_group(inode)) { + ret = nilfs_palloc_delete_bitmap_block(inode, group); + if (ret && ret != -ENOENT) { + nilfs_warning(inode->i_sb, __func__, + "failed to delete bitmap block of group %lu: ino=%lu, err=%d\n", + group, + (unsigned long)inode->i_ino, ret); + } + } } return 0; } diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h index 4bd6451b5703..6e6f49aa53df 100644 --- a/fs/nilfs2/alloc.h +++ b/fs/nilfs2/alloc.h @@ -77,6 +77,7 @@ int nilfs_palloc_freev(struct inode *, __u64 *, size_t); #define nilfs_set_bit_atomic ext2_set_bit_atomic #define nilfs_clear_bit_atomic ext2_clear_bit_atomic #define nilfs_find_next_zero_bit find_next_zero_bit_le +#define nilfs_find_next_bit find_next_bit_le /** * struct nilfs_bh_assoc - block offset and buffer head association diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 919fd5bb14a8..3a3821b00486 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -919,8 +919,6 @@ static void nilfs_btree_split(struct nilfs_bmap *btree, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *right; - __u64 newkey; - __u64 newptr; int nchildren, n, move, ncblk; node = nilfs_btree_get_nonroot_node(path, level); @@ -942,9 +940,6 @@ static void nilfs_btree_split(struct nilfs_bmap *btree, if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); - newkey = nilfs_btree_node_get_key(right, 0); - newptr = path[level].bp_newreq.bpr_ptr; - if (move) { path[level].bp_index -= nilfs_btree_node_get_nchildren(node); nilfs_btree_node_insert(right, path[level].bp_index, @@ -1856,7 +1851,7 @@ int nilfs_btree_convert_and_insert(struct nilfs_bmap *btree, __u64 key, __u64 ptr, const __u64 *keys, const __u64 *ptrs, int n) { - struct buffer_head *bh; + struct buffer_head *bh = NULL; union nilfs_bmap_ptr_req dreq, nreq, *di, *ni; struct nilfs_bmap_stats stats; int ret; diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 0d5fada91191..7dc23f100e57 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -155,7 +155,6 @@ void nilfs_dat_commit_start(struct inode *dat, struct nilfs_palloc_req *req, int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req) { struct nilfs_dat_entry *entry; - __u64 start; sector_t blocknr; void *kaddr; int ret; @@ -169,7 +168,6 @@ int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req) kaddr = kmap_atomic(req->pr_entry_bh->b_page); entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr, req->pr_entry_bh, kaddr); - start = le64_to_cpu(entry->de_start); blocknr = le64_to_cpu(entry->de_blocknr); kunmap_atomic(kaddr); diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 54575e3cc1a2..088ba001c6ef 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -109,7 +109,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) goto out; file_update_time(vma->vm_file); - ret = __block_page_mkwrite(vma, vmf, nilfs_get_block); + ret = block_page_mkwrite(vma, vmf, nilfs_get_block); if (ret) { nilfs_transaction_abort(inode->i_sb); goto out; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 4a73d6dffabf..10b22527a617 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -356,7 +356,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) goto failed; mapping_set_gfp_mask(inode->i_mapping, - mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); + mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS)); root = NILFS_I(dir)->i_root; ii = NILFS_I(inode); @@ -510,6 +510,7 @@ static int __nilfs_read_inode(struct super_block *sb, inode->i_mapping->a_ops = &nilfs_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &nilfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &nilfs_aops; } else { inode->i_op = &nilfs_special_inode_operations; @@ -522,7 +523,7 @@ static int __nilfs_read_inode(struct super_block *sb, up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); nilfs_set_inode_flags(inode); mapping_set_gfp_mask(inode->i_mapping, - mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); + mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS)); return 0; failed_unmap: diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index dee34d990281..1125f40233ff 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -33,6 +33,7 @@ #include "page.h" #include "mdt.h" +#include <trace/events/nilfs2.h> #define NILFS_MDT_MAX_RA_BLOCKS (16 - 1) @@ -68,6 +69,9 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block, set_buffer_uptodate(bh); mark_buffer_dirty(bh); nilfs_mdt_mark_dirty(inode); + + trace_nilfs2_mdt_insert_new_block(inode, inode->i_ino, block); + return 0; } @@ -158,6 +162,8 @@ nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff, get_bh(bh); submit_bh(mode, bh); ret = 0; + + trace_nilfs2_mdt_submit_block(inode, inode->i_ino, blkoff, mode); out: get_bh(bh); *out_bh = bh; diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h index fe529a87a208..03246cac3338 100644 --- a/fs/nilfs2/mdt.h +++ b/fs/nilfs2/mdt.h @@ -72,7 +72,7 @@ static inline struct nilfs_mdt_info *NILFS_MDT(const struct inode *inode) } /* Default GFP flags using highmem */ -#define NILFS_MDT_GFP (__GFP_WAIT | __GFP_IO | __GFP_HIGHMEM) +#define NILFS_MDT_GFP (__GFP_RECLAIM | __GFP_IO | __GFP_HIGHMEM) int nilfs_mdt_get_block(struct inode *, unsigned long, int, void (*init_block)(struct inode *, diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 37dd6b05b1b5..7ccdb961eea9 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -120,9 +120,6 @@ nilfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) struct nilfs_transaction_info ti; int err; - if (!new_valid_dev(rdev)) - return -EINVAL; - err = nilfs_transaction_begin(dir->i_sb, &ti, 1); if (err) return err; @@ -164,6 +161,7 @@ static int nilfs_symlink(struct inode *dir, struct dentry *dentry, /* slow symlink */ inode->i_op = &nilfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &nilfs_aops; err = page_symlink(inode, symname, l); if (err) @@ -571,8 +569,7 @@ const struct inode_operations nilfs_special_inode_operations = { const struct inode_operations nilfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .permission = nilfs_permission, }; diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index ff00a0b7acb9..9b4f205d1173 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -582,7 +582,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs, struct nilfs_recovery_info *ri) { struct buffer_head *bh_sum = NULL; - struct nilfs_segment_summary *sum; + struct nilfs_segment_summary *sum = NULL; sector_t pseg_start; sector_t seg_start, seg_end; /* Starting/ending DBN of full segment */ unsigned long nsalvaged_blocks = 0; @@ -814,7 +814,7 @@ int nilfs_search_super_root(struct the_nilfs *nilfs, struct nilfs_recovery_info *ri) { struct buffer_head *bh_sum = NULL; - struct nilfs_segment_summary *sum; + struct nilfs_segment_summary *sum = NULL; sector_t pseg_start, pseg_end, sr_pseg_start = 0; sector_t seg_start, seg_end; /* range of full segment (block number) */ sector_t b, end; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index c6abbad9b8e3..3b65adaae7e4 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -77,6 +77,36 @@ enum { NILFS_ST_DONE, }; +#define CREATE_TRACE_POINTS +#include <trace/events/nilfs2.h> + +/* + * nilfs_sc_cstage_inc(), nilfs_sc_cstage_set(), nilfs_sc_cstage_get() are + * wrapper functions of stage count (nilfs_sc_info->sc_stage.scnt). Users of + * the variable must use them because transition of stage count must involve + * trace events (trace_nilfs2_collection_stage_transition). + * + * nilfs_sc_cstage_get() isn't required for the above purpose because it doesn't + * produce tracepoint events. It is provided just for making the intention + * clear. + */ +static inline void nilfs_sc_cstage_inc(struct nilfs_sc_info *sci) +{ + sci->sc_stage.scnt++; + trace_nilfs2_collection_stage_transition(sci); +} + +static inline void nilfs_sc_cstage_set(struct nilfs_sc_info *sci, int next_scnt) +{ + sci->sc_stage.scnt = next_scnt; + trace_nilfs2_collection_stage_transition(sci); +} + +static inline int nilfs_sc_cstage_get(struct nilfs_sc_info *sci) +{ + return sci->sc_stage.scnt; +} + /* State flags of collection */ #define NILFS_CF_NODE 0x0001 /* Collecting node blocks */ #define NILFS_CF_IFILE_STARTED 0x0002 /* IFILE stage has started */ @@ -184,11 +214,18 @@ int nilfs_transaction_begin(struct super_block *sb, { struct the_nilfs *nilfs; int ret = nilfs_prepare_segment_lock(ti); + struct nilfs_transaction_info *trace_ti; if (unlikely(ret < 0)) return ret; - if (ret > 0) + if (ret > 0) { + trace_ti = current->journal_info; + + trace_nilfs2_transaction_transition(sb, trace_ti, + trace_ti->ti_count, trace_ti->ti_flags, + TRACE_NILFS2_TRANSACTION_BEGIN); return 0; + } sb_start_intwrite(sb); @@ -199,6 +236,11 @@ int nilfs_transaction_begin(struct super_block *sb, ret = -ENOSPC; goto failed; } + + trace_ti = current->journal_info; + trace_nilfs2_transaction_transition(sb, trace_ti, trace_ti->ti_count, + trace_ti->ti_flags, + TRACE_NILFS2_TRANSACTION_BEGIN); return 0; failed: @@ -231,6 +273,8 @@ int nilfs_transaction_commit(struct super_block *sb) ti->ti_flags |= NILFS_TI_COMMIT; if (ti->ti_count > 0) { ti->ti_count--; + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_COMMIT); return 0; } if (nilfs->ns_writer) { @@ -242,6 +286,9 @@ int nilfs_transaction_commit(struct super_block *sb) nilfs_segctor_do_flush(sci, 0); } up_read(&nilfs->ns_segctor_sem); + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_COMMIT); + current->journal_info = ti->ti_save; if (ti->ti_flags & NILFS_TI_SYNC) @@ -260,10 +307,15 @@ void nilfs_transaction_abort(struct super_block *sb) BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC); if (ti->ti_count > 0) { ti->ti_count--; + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_ABORT); return; } up_read(&nilfs->ns_segctor_sem); + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_ABORT); + current->journal_info = ti->ti_save; if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC) kmem_cache_free(nilfs_transaction_cachep, ti); @@ -309,6 +361,9 @@ static void nilfs_transaction_lock(struct super_block *sb, current->journal_info = ti; for (;;) { + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_TRYLOCK); + down_write(&nilfs->ns_segctor_sem); if (!test_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags)) break; @@ -320,6 +375,9 @@ static void nilfs_transaction_lock(struct super_block *sb, } if (gcflag) ti->ti_flags |= NILFS_TI_GC; + + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_LOCK); } static void nilfs_transaction_unlock(struct super_block *sb) @@ -332,6 +390,9 @@ static void nilfs_transaction_unlock(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); current->journal_info = ti->ti_save; + + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_UNLOCK); } static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci, @@ -1062,7 +1123,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) size_t ndone; int err = 0; - switch (sci->sc_stage.scnt) { + switch (nilfs_sc_cstage_get(sci)) { case NILFS_ST_INIT: /* Pre-processes */ sci->sc_stage.flags = 0; @@ -1071,7 +1132,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) sci->sc_nblk_inc = 0; sci->sc_curseg->sb_sum.flags = NILFS_SS_LOGBGN; if (mode == SC_LSEG_DSYNC) { - sci->sc_stage.scnt = NILFS_ST_DSYNC; + nilfs_sc_cstage_set(sci, NILFS_ST_DSYNC); goto dsync_mode; } } @@ -1079,10 +1140,10 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) sci->sc_stage.dirty_file_ptr = NULL; sci->sc_stage.gc_inode_ptr = NULL; if (mode == SC_FLUSH_DAT) { - sci->sc_stage.scnt = NILFS_ST_DAT; + nilfs_sc_cstage_set(sci, NILFS_ST_DAT); goto dat_stage; } - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_GC: if (nilfs_doing_gc()) { head = &sci->sc_gc_inodes; @@ -1103,7 +1164,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) } sci->sc_stage.gc_inode_ptr = NULL; } - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_FILE: head = &sci->sc_dirty_files; ii = list_prepare_entry(sci->sc_stage.dirty_file_ptr, head, @@ -1125,10 +1186,10 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) } sci->sc_stage.dirty_file_ptr = NULL; if (mode == SC_FLUSH_FILE) { - sci->sc_stage.scnt = NILFS_ST_DONE; + nilfs_sc_cstage_set(sci, NILFS_ST_DONE); return 0; } - sci->sc_stage.scnt++; + nilfs_sc_cstage_inc(sci); sci->sc_stage.flags |= NILFS_CF_IFILE_STARTED; /* Fall through */ case NILFS_ST_IFILE: @@ -1136,7 +1197,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) &nilfs_sc_file_ops); if (unlikely(err)) break; - sci->sc_stage.scnt++; + nilfs_sc_cstage_inc(sci); /* Creating a checkpoint */ err = nilfs_segctor_create_checkpoint(sci); if (unlikely(err)) @@ -1147,7 +1208,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) &nilfs_sc_file_ops); if (unlikely(err)) break; - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_SUFILE: err = nilfs_sufile_freev(nilfs->ns_sufile, sci->sc_freesegs, sci->sc_nfreesegs, &ndone); @@ -1163,7 +1224,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) &nilfs_sc_file_ops); if (unlikely(err)) break; - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_DAT: dat_stage: err = nilfs_segctor_scan_file(sci, nilfs->ns_dat, @@ -1171,10 +1232,10 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) if (unlikely(err)) break; if (mode == SC_FLUSH_DAT) { - sci->sc_stage.scnt = NILFS_ST_DONE; + nilfs_sc_cstage_set(sci, NILFS_ST_DONE); return 0; } - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_SR: if (mode == SC_LSEG_SR) { /* Appending a super root */ @@ -1184,7 +1245,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) } /* End of a logical segment */ sci->sc_curseg->sb_sum.flags |= NILFS_SS_LOGEND; - sci->sc_stage.scnt = NILFS_ST_DONE; + nilfs_sc_cstage_set(sci, NILFS_ST_DONE); return 0; case NILFS_ST_DSYNC: dsync_mode: @@ -1197,7 +1258,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) if (unlikely(err)) break; sci->sc_curseg->sb_sum.flags |= NILFS_SS_LOGEND; - sci->sc_stage.scnt = NILFS_ST_DONE; + nilfs_sc_cstage_set(sci, NILFS_ST_DONE); return 0; case NILFS_ST_DONE: return 0; @@ -1442,7 +1503,8 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci, goto failed; /* The current segment is filled up */ - if (mode != SC_LSEG_SR || sci->sc_stage.scnt < NILFS_ST_CPFILE) + if (mode != SC_LSEG_SR || + nilfs_sc_cstage_get(sci) < NILFS_ST_CPFILE) break; nilfs_clear_logs(&sci->sc_segbufs); @@ -1946,7 +2008,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) struct the_nilfs *nilfs = sci->sc_super->s_fs_info; int err; - sci->sc_stage.scnt = NILFS_ST_INIT; + nilfs_sc_cstage_set(sci, NILFS_ST_INIT); sci->sc_cno = nilfs->ns_cno; err = nilfs_segctor_collect_dirty_files(sci, nilfs); @@ -1974,7 +2036,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) goto failed; /* Avoid empty segment */ - if (sci->sc_stage.scnt == NILFS_ST_DONE && + if (nilfs_sc_cstage_get(sci) == NILFS_ST_DONE && nilfs_segbuf_empty(sci->sc_curseg)) { nilfs_segctor_abort_construction(sci, nilfs, 1); goto out; @@ -1988,7 +2050,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) nilfs_segctor_fill_in_file_bmap(sci); if (mode == SC_LSEG_SR && - sci->sc_stage.scnt >= NILFS_ST_CPFILE) { + nilfs_sc_cstage_get(sci) >= NILFS_ST_CPFILE) { err = nilfs_segctor_fill_in_checkpoint(sci); if (unlikely(err)) goto failed_to_write; @@ -2007,7 +2069,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) if (unlikely(err)) goto failed_to_write; - if (sci->sc_stage.scnt == NILFS_ST_DONE || + if (nilfs_sc_cstage_get(sci) == NILFS_ST_DONE || nilfs->ns_blocksize_bits != PAGE_CACHE_SHIFT) { /* * At this point, we avoid double buffering @@ -2020,7 +2082,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) if (err) goto failed_to_write; } - } while (sci->sc_stage.scnt != NILFS_ST_DONE); + } while (nilfs_sc_cstage_get(sci) != NILFS_ST_DONE); out: nilfs_segctor_drop_written_files(sci, nilfs); @@ -2430,7 +2492,6 @@ static void nilfs_segctor_thread_construct(struct nilfs_sc_info *sci, int mode) static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *sci) { int mode = 0; - int err; spin_lock(&sci->sc_state_lock); mode = (sci->sc_flush_request & FLUSH_DAT_BIT) ? @@ -2438,7 +2499,7 @@ static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *sci) spin_unlock(&sci->sc_state_lock); if (mode) { - err = nilfs_segctor_do_construct(sci, mode); + nilfs_segctor_do_construct(sci, mode); spin_lock(&sci->sc_state_lock); sci->sc_flush_request &= (mode == SC_FLUSH_FILE) ? diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index a48d6de1e02c..0408b9b2814b 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -67,7 +67,8 @@ struct nilfs_recovery_info { /** * struct nilfs_cstage - Context of collection stage - * @scnt: Stage count + * @scnt: Stage count, must be accessed via wrappers: + * nilfs_sc_cstage_inc(), nilfs_sc_cstage_set(), nilfs_sc_cstage_get() * @flags: State flags * @dirty_file_ptr: Pointer on dirty_files list, or inode of a target file * @gc_inode_ptr: Pointer on the list of gc-inodes diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 2a869c35c362..52821ffc11f4 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -30,6 +30,8 @@ #include "mdt.h" #include "sufile.h" +#include <trace/events/nilfs2.h> + /** * struct nilfs_sufile_info - on-memory private data of sufile * @mi: on-memory private data of metadata file @@ -317,7 +319,7 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) size_t susz = NILFS_MDT(sufile)->mi_entry_size; __u64 segnum, maxsegnum, last_alloc; void *kaddr; - unsigned long nsegments, ncleansegs, nsus, cnt; + unsigned long nsegments, nsus, cnt; int ret, j; down_write(&NILFS_MDT(sufile)->mi_sem); @@ -327,7 +329,6 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) goto out_sem; kaddr = kmap_atomic(header_bh->b_page); header = kaddr + bh_offset(header_bh); - ncleansegs = le64_to_cpu(header->sh_ncleansegs); last_alloc = le64_to_cpu(header->sh_last_alloc); kunmap_atomic(kaddr); @@ -358,6 +359,7 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) break; /* never happens */ } } + trace_nilfs2_segment_usage_check(sufile, segnum, cnt); ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 1, &su_bh); if (ret < 0) @@ -388,6 +390,9 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) nilfs_mdt_mark_dirty(sufile); brelse(su_bh); *segnump = segnum; + + trace_nilfs2_segment_usage_allocated(sufile, segnum); + goto out_header; } @@ -490,6 +495,8 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum, NILFS_SUI(sufile)->ncleansegs++; nilfs_mdt_mark_dirty(sufile); + + trace_nilfs2_segment_usage_freed(sufile, segnum); } /** diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index f47585bfeb01..c7343844e6b6 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -361,7 +361,7 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) struct nilfs_super_block *nsbp; sector_t blocknr, newblocknr; unsigned long offset; - int sb2i = -1; /* array index of the secondary superblock */ + int sb2i; /* array index of the secondary superblock */ int ret = 0; /* nilfs->ns_sem must be locked by the caller. */ @@ -372,6 +372,9 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) } else if (nilfs->ns_sbh[0]->b_blocknr > nilfs->ns_first_data_block) { sb2i = 0; blocknr = nilfs->ns_sbh[0]->b_blocknr; + } else { + sb2i = -1; + blocknr = 0; } if (sb2i >= 0 && (u64)blocknr << nilfs->ns_blocksize_bits == sb2off) goto out; /* super block location is unchanged */ @@ -1313,13 +1316,11 @@ nilfs_mount(struct file_system_type *fs_type, int flags, } if (!s->s_root) { - char b[BDEVNAME_SIZE]; - - s_new = true; + s_new = true; /* New superblock instance created */ s->s_mode = mode; - strlcpy(s->s_id, bdevname(sd.bdev, b), sizeof(s->s_id)); + snprintf(s->s_id, sizeof(s->s_id), "%pg", sd.bdev); sb_set_blocksize(s, block_size(sd.bdev)); err = nilfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0); @@ -1405,14 +1406,10 @@ static void nilfs_destroy_cachep(void) */ rcu_barrier(); - if (nilfs_inode_cachep) - kmem_cache_destroy(nilfs_inode_cachep); - if (nilfs_transaction_cachep) - kmem_cache_destroy(nilfs_transaction_cachep); - if (nilfs_segbuf_cachep) - kmem_cache_destroy(nilfs_segbuf_cachep); - if (nilfs_btree_path_cache) - kmem_cache_destroy(nilfs_btree_path_cache); + kmem_cache_destroy(nilfs_inode_cachep); + kmem_cache_destroy(nilfs_transaction_cachep); + kmem_cache_destroy(nilfs_segbuf_cachep); + kmem_cache_destroy(nilfs_btree_path_cache); } static int __init nilfs_init_cachep(void) diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 262561fea923..9d383e5eff0e 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -525,8 +525,8 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping, } } err = add_to_page_cache_lru(*cached_page, mapping, - index, - GFP_KERNEL & mapping_gfp_mask(mapping)); + index, + mapping_gfp_constraint(mapping, GFP_KERNEL)); if (unlikely(err)) { if (err == -EEXIST) continue; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index ddddef0021a0..709fbbd44c65 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1480,16 +1480,17 @@ static int o2hb_read_block_input(struct o2hb_region *reg, return 0; } -static ssize_t o2hb_region_block_bytes_read(struct o2hb_region *reg, +static ssize_t o2hb_region_block_bytes_show(struct config_item *item, char *page) { - return sprintf(page, "%u\n", reg->hr_block_bytes); + return sprintf(page, "%u\n", to_o2hb_region(item)->hr_block_bytes); } -static ssize_t o2hb_region_block_bytes_write(struct o2hb_region *reg, +static ssize_t o2hb_region_block_bytes_store(struct config_item *item, const char *page, size_t count) { + struct o2hb_region *reg = to_o2hb_region(item); int status; unsigned long block_bytes; unsigned int block_bits; @@ -1508,16 +1509,17 @@ static ssize_t o2hb_region_block_bytes_write(struct o2hb_region *reg, return count; } -static ssize_t o2hb_region_start_block_read(struct o2hb_region *reg, +static ssize_t o2hb_region_start_block_show(struct config_item *item, char *page) { - return sprintf(page, "%llu\n", reg->hr_start_block); + return sprintf(page, "%llu\n", to_o2hb_region(item)->hr_start_block); } -static ssize_t o2hb_region_start_block_write(struct o2hb_region *reg, +static ssize_t o2hb_region_start_block_store(struct config_item *item, const char *page, size_t count) { + struct o2hb_region *reg = to_o2hb_region(item); unsigned long long tmp; char *p = (char *)page; @@ -1533,16 +1535,16 @@ static ssize_t o2hb_region_start_block_write(struct o2hb_region *reg, return count; } -static ssize_t o2hb_region_blocks_read(struct o2hb_region *reg, - char *page) +static ssize_t o2hb_region_blocks_show(struct config_item *item, char *page) { - return sprintf(page, "%d\n", reg->hr_blocks); + return sprintf(page, "%d\n", to_o2hb_region(item)->hr_blocks); } -static ssize_t o2hb_region_blocks_write(struct o2hb_region *reg, +static ssize_t o2hb_region_blocks_store(struct config_item *item, const char *page, size_t count) { + struct o2hb_region *reg = to_o2hb_region(item); unsigned long tmp; char *p = (char *)page; @@ -1561,13 +1563,12 @@ static ssize_t o2hb_region_blocks_write(struct o2hb_region *reg, return count; } -static ssize_t o2hb_region_dev_read(struct o2hb_region *reg, - char *page) +static ssize_t o2hb_region_dev_show(struct config_item *item, char *page) { unsigned int ret = 0; - if (reg->hr_bdev) - ret = sprintf(page, "%s\n", reg->hr_dev_name); + if (to_o2hb_region(item)->hr_bdev) + ret = sprintf(page, "%s\n", to_o2hb_region(item)->hr_dev_name); return ret; } @@ -1677,10 +1678,11 @@ out: } /* this is acting as commit; we set up all of hr_bdev and hr_task or nothing */ -static ssize_t o2hb_region_dev_write(struct o2hb_region *reg, +static ssize_t o2hb_region_dev_store(struct config_item *item, const char *page, size_t count) { + struct o2hb_region *reg = to_o2hb_region(item); struct task_struct *hb_task; long fd; int sectsize; @@ -1841,9 +1843,9 @@ out: return ret; } -static ssize_t o2hb_region_pid_read(struct o2hb_region *reg, - char *page) +static ssize_t o2hb_region_pid_show(struct config_item *item, char *page) { + struct o2hb_region *reg = to_o2hb_region(item); pid_t pid = 0; spin_lock(&o2hb_live_lock); @@ -1857,92 +1859,23 @@ static ssize_t o2hb_region_pid_read(struct o2hb_region *reg, return sprintf(page, "%u\n", pid); } -struct o2hb_region_attribute { - struct configfs_attribute attr; - ssize_t (*show)(struct o2hb_region *, char *); - ssize_t (*store)(struct o2hb_region *, const char *, size_t); -}; - -static struct o2hb_region_attribute o2hb_region_attr_block_bytes = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "block_bytes", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2hb_region_block_bytes_read, - .store = o2hb_region_block_bytes_write, -}; - -static struct o2hb_region_attribute o2hb_region_attr_start_block = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "start_block", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2hb_region_start_block_read, - .store = o2hb_region_start_block_write, -}; - -static struct o2hb_region_attribute o2hb_region_attr_blocks = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "blocks", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2hb_region_blocks_read, - .store = o2hb_region_blocks_write, -}; - -static struct o2hb_region_attribute o2hb_region_attr_dev = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "dev", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2hb_region_dev_read, - .store = o2hb_region_dev_write, -}; - -static struct o2hb_region_attribute o2hb_region_attr_pid = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "pid", - .ca_mode = S_IRUGO | S_IRUSR }, - .show = o2hb_region_pid_read, -}; +CONFIGFS_ATTR(o2hb_region_, block_bytes); +CONFIGFS_ATTR(o2hb_region_, start_block); +CONFIGFS_ATTR(o2hb_region_, blocks); +CONFIGFS_ATTR(o2hb_region_, dev); +CONFIGFS_ATTR_RO(o2hb_region_, pid); static struct configfs_attribute *o2hb_region_attrs[] = { - &o2hb_region_attr_block_bytes.attr, - &o2hb_region_attr_start_block.attr, - &o2hb_region_attr_blocks.attr, - &o2hb_region_attr_dev.attr, - &o2hb_region_attr_pid.attr, + &o2hb_region_attr_block_bytes, + &o2hb_region_attr_start_block, + &o2hb_region_attr_blocks, + &o2hb_region_attr_dev, + &o2hb_region_attr_pid, NULL, }; -static ssize_t o2hb_region_show(struct config_item *item, - struct configfs_attribute *attr, - char *page) -{ - struct o2hb_region *reg = to_o2hb_region(item); - struct o2hb_region_attribute *o2hb_region_attr = - container_of(attr, struct o2hb_region_attribute, attr); - ssize_t ret = 0; - - if (o2hb_region_attr->show) - ret = o2hb_region_attr->show(reg, page); - return ret; -} - -static ssize_t o2hb_region_store(struct config_item *item, - struct configfs_attribute *attr, - const char *page, size_t count) -{ - struct o2hb_region *reg = to_o2hb_region(item); - struct o2hb_region_attribute *o2hb_region_attr = - container_of(attr, struct o2hb_region_attribute, attr); - ssize_t ret = -EINVAL; - - if (o2hb_region_attr->store) - ret = o2hb_region_attr->store(reg, page, count); - return ret; -} - static struct configfs_item_operations o2hb_region_item_ops = { .release = o2hb_region_release, - .show_attribute = o2hb_region_show, - .store_attribute = o2hb_region_store, }; static struct config_item_type o2hb_region_type = { @@ -2137,49 +2070,14 @@ unlock: spin_unlock(&o2hb_live_lock); } -struct o2hb_heartbeat_group_attribute { - struct configfs_attribute attr; - ssize_t (*show)(struct o2hb_heartbeat_group *, char *); - ssize_t (*store)(struct o2hb_heartbeat_group *, const char *, size_t); -}; - -static ssize_t o2hb_heartbeat_group_show(struct config_item *item, - struct configfs_attribute *attr, - char *page) -{ - struct o2hb_heartbeat_group *reg = to_o2hb_heartbeat_group(to_config_group(item)); - struct o2hb_heartbeat_group_attribute *o2hb_heartbeat_group_attr = - container_of(attr, struct o2hb_heartbeat_group_attribute, attr); - ssize_t ret = 0; - - if (o2hb_heartbeat_group_attr->show) - ret = o2hb_heartbeat_group_attr->show(reg, page); - return ret; -} - -static ssize_t o2hb_heartbeat_group_store(struct config_item *item, - struct configfs_attribute *attr, - const char *page, size_t count) -{ - struct o2hb_heartbeat_group *reg = to_o2hb_heartbeat_group(to_config_group(item)); - struct o2hb_heartbeat_group_attribute *o2hb_heartbeat_group_attr = - container_of(attr, struct o2hb_heartbeat_group_attribute, attr); - ssize_t ret = -EINVAL; - - if (o2hb_heartbeat_group_attr->store) - ret = o2hb_heartbeat_group_attr->store(reg, page, count); - return ret; -} - -static ssize_t o2hb_heartbeat_group_threshold_show(struct o2hb_heartbeat_group *group, - char *page) +static ssize_t o2hb_heartbeat_group_threshold_show(struct config_item *item, + char *page) { return sprintf(page, "%u\n", o2hb_dead_threshold); } -static ssize_t o2hb_heartbeat_group_threshold_store(struct o2hb_heartbeat_group *group, - const char *page, - size_t count) +static ssize_t o2hb_heartbeat_group_threshold_store(struct config_item *item, + const char *page, size_t count) { unsigned long tmp; char *p = (char *)page; @@ -2194,17 +2092,15 @@ static ssize_t o2hb_heartbeat_group_threshold_store(struct o2hb_heartbeat_group return count; } -static -ssize_t o2hb_heartbeat_group_mode_show(struct o2hb_heartbeat_group *group, - char *page) +static ssize_t o2hb_heartbeat_group_mode_show(struct config_item *item, + char *page) { return sprintf(page, "%s\n", o2hb_heartbeat_mode_desc[o2hb_heartbeat_mode]); } -static -ssize_t o2hb_heartbeat_group_mode_store(struct o2hb_heartbeat_group *group, - const char *page, size_t count) +static ssize_t o2hb_heartbeat_group_mode_store(struct config_item *item, + const char *page, size_t count) { unsigned int i; int ret; @@ -2229,33 +2125,15 @@ ssize_t o2hb_heartbeat_group_mode_store(struct o2hb_heartbeat_group *group, } -static struct o2hb_heartbeat_group_attribute o2hb_heartbeat_group_attr_threshold = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "dead_threshold", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2hb_heartbeat_group_threshold_show, - .store = o2hb_heartbeat_group_threshold_store, -}; - -static struct o2hb_heartbeat_group_attribute o2hb_heartbeat_group_attr_mode = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "mode", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2hb_heartbeat_group_mode_show, - .store = o2hb_heartbeat_group_mode_store, -}; +CONFIGFS_ATTR(o2hb_heartbeat_group_, threshold); +CONFIGFS_ATTR(o2hb_heartbeat_group_, mode); static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = { - &o2hb_heartbeat_group_attr_threshold.attr, - &o2hb_heartbeat_group_attr_mode.attr, + &o2hb_heartbeat_group_attr_threshold, + &o2hb_heartbeat_group_attr_mode, NULL, }; -static struct configfs_item_operations o2hb_heartbeat_group_item_ops = { - .show_attribute = o2hb_heartbeat_group_show, - .store_attribute = o2hb_heartbeat_group_store, -}; - static struct configfs_group_operations o2hb_heartbeat_group_group_ops = { .make_item = o2hb_heartbeat_group_make_item, .drop_item = o2hb_heartbeat_group_drop_item, @@ -2263,7 +2141,6 @@ 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_heartbeat_group_item_ops, .ct_attrs = o2hb_heartbeat_group_attrs, .ct_owner = THIS_MODULE, }; diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index 441c84e169e6..72afdca3cea7 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -172,9 +172,9 @@ static void o2nm_node_release(struct config_item *item) kfree(node); } -static ssize_t o2nm_node_num_read(struct o2nm_node *node, char *page) +static ssize_t o2nm_node_num_show(struct config_item *item, char *page) { - return sprintf(page, "%d\n", node->nd_num); + return sprintf(page, "%d\n", to_o2nm_node(item)->nd_num); } static struct o2nm_cluster *to_o2nm_cluster_from_node(struct o2nm_node *node) @@ -188,15 +188,16 @@ enum { O2NM_NODE_ATTR_NUM = 0, O2NM_NODE_ATTR_PORT, O2NM_NODE_ATTR_ADDRESS, - O2NM_NODE_ATTR_LOCAL, }; -static ssize_t o2nm_node_num_write(struct o2nm_node *node, const char *page, +static ssize_t o2nm_node_num_store(struct config_item *item, const char *page, size_t count) { + struct o2nm_node *node = to_o2nm_node(item); struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node); unsigned long tmp; char *p = (char *)page; + int ret = 0; tmp = simple_strtoul(p, &p, 0); if (!p || (*p && (*p != '\n'))) @@ -215,26 +216,30 @@ static ssize_t o2nm_node_num_write(struct o2nm_node *node, const char *page, write_lock(&cluster->cl_nodes_lock); if (cluster->cl_nodes[tmp]) - p = NULL; + ret = -EEXIST; + else if (test_and_set_bit(O2NM_NODE_ATTR_NUM, + &node->nd_set_attributes)) + ret = -EBUSY; else { cluster->cl_nodes[tmp] = node; node->nd_num = tmp; set_bit(tmp, cluster->cl_nodes_bitmap); } write_unlock(&cluster->cl_nodes_lock); - if (p == NULL) - return -EEXIST; + if (ret) + return ret; return count; } -static ssize_t o2nm_node_ipv4_port_read(struct o2nm_node *node, char *page) +static ssize_t o2nm_node_ipv4_port_show(struct config_item *item, char *page) { - return sprintf(page, "%u\n", ntohs(node->nd_ipv4_port)); + return sprintf(page, "%u\n", ntohs(to_o2nm_node(item)->nd_ipv4_port)); } -static ssize_t o2nm_node_ipv4_port_write(struct o2nm_node *node, +static ssize_t o2nm_node_ipv4_port_store(struct config_item *item, const char *page, size_t count) { + struct o2nm_node *node = to_o2nm_node(item); unsigned long tmp; char *p = (char *)page; @@ -247,20 +252,23 @@ static ssize_t o2nm_node_ipv4_port_write(struct o2nm_node *node, if (tmp >= (u16)-1) return -ERANGE; + if (test_and_set_bit(O2NM_NODE_ATTR_PORT, &node->nd_set_attributes)) + return -EBUSY; node->nd_ipv4_port = htons(tmp); return count; } -static ssize_t o2nm_node_ipv4_address_read(struct o2nm_node *node, char *page) +static ssize_t o2nm_node_ipv4_address_show(struct config_item *item, char *page) { - return sprintf(page, "%pI4\n", &node->nd_ipv4_address); + return sprintf(page, "%pI4\n", &to_o2nm_node(item)->nd_ipv4_address); } -static ssize_t o2nm_node_ipv4_address_write(struct o2nm_node *node, +static ssize_t o2nm_node_ipv4_address_store(struct config_item *item, const char *page, size_t count) { + struct o2nm_node *node = to_o2nm_node(item); struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node); int ret, i; struct rb_node **p, *parent; @@ -282,6 +290,9 @@ static ssize_t o2nm_node_ipv4_address_write(struct o2nm_node *node, write_lock(&cluster->cl_nodes_lock); if (o2nm_node_ip_tree_lookup(cluster, ipv4_addr, &p, &parent)) ret = -EEXIST; + else if (test_and_set_bit(O2NM_NODE_ATTR_ADDRESS, + &node->nd_set_attributes)) + ret = -EBUSY; else { rb_link_node(&node->nd_ip_node, parent, p); rb_insert_color(&node->nd_ip_node, &cluster->cl_node_ip_tree); @@ -295,14 +306,15 @@ static ssize_t o2nm_node_ipv4_address_write(struct o2nm_node *node, return count; } -static ssize_t o2nm_node_local_read(struct o2nm_node *node, char *page) +static ssize_t o2nm_node_local_show(struct config_item *item, char *page) { - return sprintf(page, "%d\n", node->nd_local); + return sprintf(page, "%d\n", to_o2nm_node(item)->nd_local); } -static ssize_t o2nm_node_local_write(struct o2nm_node *node, const char *page, +static ssize_t o2nm_node_local_store(struct config_item *item, const char *page, size_t count) { + struct o2nm_node *node = to_o2nm_node(item); struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node); unsigned long tmp; char *p = (char *)page; @@ -349,108 +361,21 @@ static ssize_t o2nm_node_local_write(struct o2nm_node *node, const char *page, return count; } -struct o2nm_node_attribute { - struct configfs_attribute attr; - ssize_t (*show)(struct o2nm_node *, char *); - ssize_t (*store)(struct o2nm_node *, const char *, size_t); -}; - -static struct o2nm_node_attribute o2nm_node_attr_num = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "num", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2nm_node_num_read, - .store = o2nm_node_num_write, -}; - -static struct o2nm_node_attribute o2nm_node_attr_ipv4_port = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "ipv4_port", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2nm_node_ipv4_port_read, - .store = o2nm_node_ipv4_port_write, -}; - -static struct o2nm_node_attribute o2nm_node_attr_ipv4_address = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "ipv4_address", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2nm_node_ipv4_address_read, - .store = o2nm_node_ipv4_address_write, -}; - -static struct o2nm_node_attribute o2nm_node_attr_local = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "local", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2nm_node_local_read, - .store = o2nm_node_local_write, -}; +CONFIGFS_ATTR(o2nm_node_, num); +CONFIGFS_ATTR(o2nm_node_, ipv4_port); +CONFIGFS_ATTR(o2nm_node_, ipv4_address); +CONFIGFS_ATTR(o2nm_node_, local); static struct configfs_attribute *o2nm_node_attrs[] = { - [O2NM_NODE_ATTR_NUM] = &o2nm_node_attr_num.attr, - [O2NM_NODE_ATTR_PORT] = &o2nm_node_attr_ipv4_port.attr, - [O2NM_NODE_ATTR_ADDRESS] = &o2nm_node_attr_ipv4_address.attr, - [O2NM_NODE_ATTR_LOCAL] = &o2nm_node_attr_local.attr, + &o2nm_node_attr_num, + &o2nm_node_attr_ipv4_port, + &o2nm_node_attr_ipv4_address, + &o2nm_node_attr_local, NULL, }; -static int o2nm_attr_index(struct configfs_attribute *attr) -{ - int i; - for (i = 0; i < ARRAY_SIZE(o2nm_node_attrs); i++) { - if (attr == o2nm_node_attrs[i]) - return i; - } - BUG(); - return 0; -} - -static ssize_t o2nm_node_show(struct config_item *item, - struct configfs_attribute *attr, - char *page) -{ - struct o2nm_node *node = to_o2nm_node(item); - struct o2nm_node_attribute *o2nm_node_attr = - container_of(attr, struct o2nm_node_attribute, attr); - ssize_t ret = 0; - - if (o2nm_node_attr->show) - ret = o2nm_node_attr->show(node, page); - return ret; -} - -static ssize_t o2nm_node_store(struct config_item *item, - struct configfs_attribute *attr, - const char *page, size_t count) -{ - struct o2nm_node *node = to_o2nm_node(item); - struct o2nm_node_attribute *o2nm_node_attr = - container_of(attr, struct o2nm_node_attribute, attr); - ssize_t ret; - int attr_index = o2nm_attr_index(attr); - - if (o2nm_node_attr->store == NULL) { - ret = -EINVAL; - goto out; - } - - if (test_bit(attr_index, &node->nd_set_attributes)) - return -EBUSY; - - ret = o2nm_node_attr->store(node, page, count); - if (ret < count) - goto out; - - set_bit(attr_index, &node->nd_set_attributes); -out: - return ret; -} - static struct configfs_item_operations o2nm_node_item_ops = { .release = o2nm_node_release, - .show_attribute = o2nm_node_show, - .store_attribute = o2nm_node_store, }; static struct config_item_type o2nm_node_type = { @@ -475,12 +400,6 @@ static struct o2nm_node_group *to_o2nm_node_group(struct config_group *group) } #endif -struct o2nm_cluster_attribute { - struct configfs_attribute attr; - ssize_t (*show)(struct o2nm_cluster *, char *); - ssize_t (*store)(struct o2nm_cluster *, const char *, size_t); -}; - static ssize_t o2nm_cluster_attr_write(const char *page, ssize_t count, unsigned int *val) { @@ -501,15 +420,16 @@ static ssize_t o2nm_cluster_attr_write(const char *page, ssize_t count, return count; } -static ssize_t o2nm_cluster_attr_idle_timeout_ms_read( - struct o2nm_cluster *cluster, char *page) +static ssize_t o2nm_cluster_idle_timeout_ms_show(struct config_item *item, + char *page) { - return sprintf(page, "%u\n", cluster->cl_idle_timeout_ms); + return sprintf(page, "%u\n", to_o2nm_cluster(item)->cl_idle_timeout_ms); } -static ssize_t o2nm_cluster_attr_idle_timeout_ms_write( - struct o2nm_cluster *cluster, const char *page, size_t count) +static ssize_t o2nm_cluster_idle_timeout_ms_store(struct config_item *item, + const char *page, size_t count) { + struct o2nm_cluster *cluster = to_o2nm_cluster(item); ssize_t ret; unsigned int val; @@ -536,15 +456,17 @@ static ssize_t o2nm_cluster_attr_idle_timeout_ms_write( return ret; } -static ssize_t o2nm_cluster_attr_keepalive_delay_ms_read( - struct o2nm_cluster *cluster, char *page) +static ssize_t o2nm_cluster_keepalive_delay_ms_show( + struct config_item *item, char *page) { - return sprintf(page, "%u\n", cluster->cl_keepalive_delay_ms); + return sprintf(page, "%u\n", + to_o2nm_cluster(item)->cl_keepalive_delay_ms); } -static ssize_t o2nm_cluster_attr_keepalive_delay_ms_write( - struct o2nm_cluster *cluster, const char *page, size_t count) +static ssize_t o2nm_cluster_keepalive_delay_ms_store( + struct config_item *item, const char *page, size_t count) { + struct o2nm_cluster *cluster = to_o2nm_cluster(item); ssize_t ret; unsigned int val; @@ -571,22 +493,24 @@ static ssize_t o2nm_cluster_attr_keepalive_delay_ms_write( return ret; } -static ssize_t o2nm_cluster_attr_reconnect_delay_ms_read( - struct o2nm_cluster *cluster, char *page) +static ssize_t o2nm_cluster_reconnect_delay_ms_show( + struct config_item *item, char *page) { - return sprintf(page, "%u\n", cluster->cl_reconnect_delay_ms); + return sprintf(page, "%u\n", + to_o2nm_cluster(item)->cl_reconnect_delay_ms); } -static ssize_t o2nm_cluster_attr_reconnect_delay_ms_write( - struct o2nm_cluster *cluster, const char *page, size_t count) +static ssize_t o2nm_cluster_reconnect_delay_ms_store( + struct config_item *item, const char *page, size_t count) { return o2nm_cluster_attr_write(page, count, - &cluster->cl_reconnect_delay_ms); + &to_o2nm_cluster(item)->cl_reconnect_delay_ms); } -static ssize_t o2nm_cluster_attr_fence_method_read( - struct o2nm_cluster *cluster, char *page) +static ssize_t o2nm_cluster_fence_method_show( + struct config_item *item, char *page) { + struct o2nm_cluster *cluster = to_o2nm_cluster(item); ssize_t ret = 0; if (cluster) @@ -595,8 +519,8 @@ static ssize_t o2nm_cluster_attr_fence_method_read( return ret; } -static ssize_t o2nm_cluster_attr_fence_method_write( - struct o2nm_cluster *cluster, const char *page, size_t count) +static ssize_t o2nm_cluster_fence_method_store( + struct config_item *item, const char *page, size_t count) { unsigned int i; @@ -608,10 +532,10 @@ static ssize_t o2nm_cluster_attr_fence_method_write( continue; if (strncasecmp(page, o2nm_fence_method_desc[i], count - 1)) continue; - if (cluster->cl_fence_method != i) { + if (to_o2nm_cluster(item)->cl_fence_method != i) { printk(KERN_INFO "ocfs2: Changing fence method to %s\n", o2nm_fence_method_desc[i]); - cluster->cl_fence_method = i; + to_o2nm_cluster(item)->cl_fence_method = i; } return count; } @@ -620,79 +544,18 @@ bail: return -EINVAL; } -static struct o2nm_cluster_attribute o2nm_cluster_attr_idle_timeout_ms = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "idle_timeout_ms", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2nm_cluster_attr_idle_timeout_ms_read, - .store = o2nm_cluster_attr_idle_timeout_ms_write, -}; - -static struct o2nm_cluster_attribute o2nm_cluster_attr_keepalive_delay_ms = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "keepalive_delay_ms", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2nm_cluster_attr_keepalive_delay_ms_read, - .store = o2nm_cluster_attr_keepalive_delay_ms_write, -}; - -static struct o2nm_cluster_attribute o2nm_cluster_attr_reconnect_delay_ms = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "reconnect_delay_ms", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2nm_cluster_attr_reconnect_delay_ms_read, - .store = o2nm_cluster_attr_reconnect_delay_ms_write, -}; - -static struct o2nm_cluster_attribute o2nm_cluster_attr_fence_method = { - .attr = { .ca_owner = THIS_MODULE, - .ca_name = "fence_method", - .ca_mode = S_IRUGO | S_IWUSR }, - .show = o2nm_cluster_attr_fence_method_read, - .store = o2nm_cluster_attr_fence_method_write, -}; +CONFIGFS_ATTR(o2nm_cluster_, idle_timeout_ms); +CONFIGFS_ATTR(o2nm_cluster_, keepalive_delay_ms); +CONFIGFS_ATTR(o2nm_cluster_, reconnect_delay_ms); +CONFIGFS_ATTR(o2nm_cluster_, fence_method); static struct configfs_attribute *o2nm_cluster_attrs[] = { - &o2nm_cluster_attr_idle_timeout_ms.attr, - &o2nm_cluster_attr_keepalive_delay_ms.attr, - &o2nm_cluster_attr_reconnect_delay_ms.attr, - &o2nm_cluster_attr_fence_method.attr, + &o2nm_cluster_attr_idle_timeout_ms, + &o2nm_cluster_attr_keepalive_delay_ms, + &o2nm_cluster_attr_reconnect_delay_ms, + &o2nm_cluster_attr_fence_method, NULL, }; -static ssize_t o2nm_cluster_show(struct config_item *item, - struct configfs_attribute *attr, - char *page) -{ - struct o2nm_cluster *cluster = to_o2nm_cluster(item); - struct o2nm_cluster_attribute *o2nm_cluster_attr = - container_of(attr, struct o2nm_cluster_attribute, attr); - ssize_t ret = 0; - - if (o2nm_cluster_attr->show) - ret = o2nm_cluster_attr->show(cluster, page); - return ret; -} - -static ssize_t o2nm_cluster_store(struct config_item *item, - struct configfs_attribute *attr, - const char *page, size_t count) -{ - struct o2nm_cluster *cluster = to_o2nm_cluster(item); - struct o2nm_cluster_attribute *o2nm_cluster_attr = - container_of(attr, struct o2nm_cluster_attribute, attr); - ssize_t ret; - - if (o2nm_cluster_attr->store == NULL) { - ret = -EINVAL; - goto out; - } - - ret = o2nm_cluster_attr->store(cluster, page, count); - if (ret < count) - goto out; -out: - return ret; -} static struct config_item *o2nm_node_group_make_item(struct config_group *group, const char *name) @@ -773,8 +636,6 @@ static void o2nm_cluster_release(struct config_item *item) static struct configfs_item_operations o2nm_cluster_item_ops = { .release = o2nm_cluster_release, - .show_attribute = o2nm_cluster_show, - .store_attribute = o2nm_cluster_store, }; static struct config_item_type o2nm_cluster_type = { diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index ce38b4ccc9ab..84f2f8079466 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2843,6 +2843,8 @@ again: res->state &= ~DLM_LOCK_RES_BLOCK_DIRTY; if (!ret) BUG_ON(!(res->state & DLM_LOCK_RES_MIGRATING)); + else + res->migration_pending = 0; spin_unlock(&res->spinlock); /* diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 8f87e05ee25d..97a563bab9a8 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -361,6 +361,7 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe, break; case S_IFLNK: inode->i_op = &ocfs2_symlink_inode_operations; + inode_nohighmem(inode); i_size_write(inode, le64_to_cpu(fe->i_size)); break; default: diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c index 652ece4a9d9e..d56f0079b858 100644 --- a/fs/ocfs2/locks.c +++ b/fs/ocfs2/locks.c @@ -67,7 +67,10 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode, */ locks_lock_file_wait(file, - &(struct file_lock){.fl_type = F_UNLCK}); + &(struct file_lock) { + .fl_type = F_UNLCK, + .fl_flags = FL_FLOCK + }); ocfs2_file_unlock(file); } diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 3b48ac25d8a7..afb81eae2c18 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -367,7 +367,7 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } - status = posix_acl_create(dir, &mode, &default_acl, &acl); + status = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); if (status) { mlog_errno(status); goto leave; @@ -1958,6 +1958,7 @@ static int ocfs2_symlink(struct inode *dir, inode->i_rdev = 0; newsize = l - 1; inode->i_op = &ocfs2_symlink_inode_operations; + inode_nohighmem(inode); if (l > ocfs2_fast_symlink_chars(sb)) { u32 offset = 0; diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index d5da6f624142..79b8021302b3 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -54,11 +54,12 @@ static u16 ocfs2_calc_new_backup_super(struct inode *inode, struct ocfs2_group_desc *gd, u16 cl_cpg, + u16 old_bg_clusters, int set) { int i; u16 backups = 0; - u32 cluster; + u32 cluster, lgd_cluster; u64 blkno, gd_blkno, lgd_blkno = le64_to_cpu(gd->bg_blkno); for (i = 0; i < OCFS2_MAX_BACKUP_SUPERBLOCKS; i++) { @@ -71,6 +72,12 @@ static u16 ocfs2_calc_new_backup_super(struct inode *inode, else if (gd_blkno > lgd_blkno) break; + /* check if already done backup super */ + lgd_cluster = ocfs2_blocks_to_clusters(inode->i_sb, lgd_blkno); + lgd_cluster += old_bg_clusters; + if (lgd_cluster >= cluster) + continue; + if (set) ocfs2_set_bit(cluster % cl_cpg, (unsigned long *)gd->bg_bitmap); @@ -99,6 +106,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, u16 chain, num_bits, backups = 0; u16 cl_bpc = le16_to_cpu(cl->cl_bpc); u16 cl_cpg = le16_to_cpu(cl->cl_cpg); + u16 old_bg_clusters; trace_ocfs2_update_last_group_and_inode(new_clusters, first_new_cluster); @@ -112,6 +120,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, group = (struct ocfs2_group_desc *)group_bh->b_data; + old_bg_clusters = le16_to_cpu(group->bg_bits) / cl_bpc; /* update the group first. */ num_bits = new_clusters * cl_bpc; le16_add_cpu(&group->bg_bits, num_bits); @@ -125,7 +134,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, OCFS2_FEATURE_COMPAT_BACKUP_SB)) { backups = ocfs2_calc_new_backup_super(bm_inode, group, - cl_cpg, 1); + cl_cpg, old_bg_clusters, 1); le16_add_cpu(&group->bg_free_bits_count, -1 * backups); } @@ -163,7 +172,7 @@ out_rollback: if (ret < 0) { ocfs2_calc_new_backup_super(bm_inode, group, - cl_cpg, 0); + cl_cpg, old_bg_clusters, 0); le16_add_cpu(&group->bg_free_bits_count, backups); le16_add_cpu(&group->bg_bits, -1 * num_bits); le16_add_cpu(&group->bg_free_bits_count, -1 * num_bits); diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c index 66edce7ecfd7..6c2a3e3c521c 100644 --- a/fs/ocfs2/symlink.c +++ b/fs/ocfs2/symlink.c @@ -88,8 +88,7 @@ const struct address_space_operations ocfs2_fast_symlink_aops = { const struct inode_operations ocfs2_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getattr = ocfs2_getattr, .setattr = ocfs2_setattr, .setxattr = generic_setxattr, diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index ebfdea78659b..f0e241ffd94f 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -544,8 +544,7 @@ static inline const char *ocfs2_xattr_prefix(int name_index) if (name_index > 0 && name_index < OCFS2_XATTR_MAX) handler = ocfs2_xattr_handler_map[name_index]; - - return handler ? handler->prefix : NULL; + return handler ? xattr_prefix(handler) : NULL; } static u32 ocfs2_xattr_name_hash(struct inode *inode, @@ -884,14 +883,39 @@ static int ocfs2_xattr_value_truncate(struct inode *inode, return ret; } -static int ocfs2_xattr_list_entry(char *buffer, size_t size, - size_t *result, const char *prefix, +static int ocfs2_xattr_list_entry(struct super_block *sb, + char *buffer, size_t size, + size_t *result, int type, const char *name, int name_len) { char *p = buffer + *result; - int prefix_len = strlen(prefix); - int total_len = prefix_len + name_len + 1; + const char *prefix; + int prefix_len; + int total_len; + switch(type) { + case OCFS2_XATTR_INDEX_USER: + if (OCFS2_SB(sb)->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR) + return 0; + break; + + case OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS: + case OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT: + if (!(sb->s_flags & MS_POSIXACL)) + return 0; + break; + + case OCFS2_XATTR_INDEX_TRUSTED: + if (!capable(CAP_SYS_ADMIN)) + return 0; + break; + } + + prefix = ocfs2_xattr_prefix(type); + if (!prefix) + return 0; + prefix_len = strlen(prefix); + total_len = prefix_len + name_len + 1; *result += total_len; /* we are just looking for how big our buffer needs to be */ @@ -914,23 +938,20 @@ static int ocfs2_xattr_list_entries(struct inode *inode, { size_t result = 0; int i, type, ret; - const char *prefix, *name; + const char *name; for (i = 0 ; i < le16_to_cpu(header->xh_count); i++) { struct ocfs2_xattr_entry *entry = &header->xh_entries[i]; type = ocfs2_xattr_get_type(entry); - prefix = ocfs2_xattr_prefix(type); - - if (prefix) { - name = (const char *)header + - le16_to_cpu(entry->xe_name_offset); + name = (const char *)header + + le16_to_cpu(entry->xe_name_offset); - ret = ocfs2_xattr_list_entry(buffer, buffer_size, - &result, prefix, name, - entry->xe_name_len); - if (ret) - return ret; - } + ret = ocfs2_xattr_list_entry(inode->i_sb, + buffer, buffer_size, + &result, type, name, + entry->xe_name_len); + if (ret) + return ret; } return result; @@ -4033,32 +4054,30 @@ static int ocfs2_list_xattr_bucket(struct inode *inode, int ret = 0, type; struct ocfs2_xattr_tree_list *xl = (struct ocfs2_xattr_tree_list *)para; int i, block_off, new_offset; - const char *prefix, *name; + const char *name; for (i = 0 ; i < le16_to_cpu(bucket_xh(bucket)->xh_count); i++) { struct ocfs2_xattr_entry *entry = &bucket_xh(bucket)->xh_entries[i]; type = ocfs2_xattr_get_type(entry); - prefix = ocfs2_xattr_prefix(type); - if (prefix) { - ret = ocfs2_xattr_bucket_get_name_value(inode->i_sb, - bucket_xh(bucket), - i, - &block_off, - &new_offset); - if (ret) - break; + ret = ocfs2_xattr_bucket_get_name_value(inode->i_sb, + bucket_xh(bucket), + i, + &block_off, + &new_offset); + if (ret) + break; - name = (const char *)bucket_block(bucket, block_off) + - new_offset; - ret = ocfs2_xattr_list_entry(xl->buffer, - xl->buffer_size, - &xl->result, - prefix, name, - entry->xe_name_len); - if (ret) - break; - } + name = (const char *)bucket_block(bucket, block_off) + + new_offset; + ret = ocfs2_xattr_list_entry(inode->i_sb, + xl->buffer, + xl->buffer_size, + &xl->result, + type, name, + entry->xe_name_len); + if (ret) + break; } return ret; @@ -7226,39 +7245,22 @@ int ocfs2_init_security_and_acl(struct inode *dir, leave: return ret; } + /* * 'security' attributes support */ -static size_t ocfs2_xattr_security_list(struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len, int type) -{ - const size_t prefix_len = XATTR_SECURITY_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_SECURITY_PREFIX, prefix_len); - memcpy(list + prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - -static int ocfs2_xattr_security_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int ocfs2_xattr_security_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_SECURITY, name, buffer, size); } -static int ocfs2_xattr_security_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +static int ocfs2_xattr_security_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; - return ocfs2_xattr_set(d_inode(dentry), OCFS2_XATTR_INDEX_SECURITY, name, value, size, flags); } @@ -7311,7 +7313,6 @@ int ocfs2_init_security_set(handle_t *handle, const struct xattr_handler ocfs2_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = ocfs2_xattr_security_list, .get = ocfs2_xattr_security_get, .set = ocfs2_xattr_security_set, }; @@ -7319,46 +7320,24 @@ const struct xattr_handler ocfs2_xattr_security_handler = { /* * 'trusted' attributes support */ -static size_t ocfs2_xattr_trusted_list(struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len, int type) -{ - const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!capable(CAP_SYS_ADMIN)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len); - memcpy(list + prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - -static int ocfs2_xattr_trusted_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int ocfs2_xattr_trusted_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_TRUSTED, name, buffer, size); } -static int ocfs2_xattr_trusted_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +static int ocfs2_xattr_trusted_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; - return ocfs2_xattr_set(d_inode(dentry), OCFS2_XATTR_INDEX_TRUSTED, name, value, size, flags); } const struct xattr_handler ocfs2_xattr_trusted_handler = { .prefix = XATTR_TRUSTED_PREFIX, - .list = ocfs2_xattr_trusted_list, .get = ocfs2_xattr_trusted_get, .set = ocfs2_xattr_trusted_set, }; @@ -7366,45 +7345,24 @@ const struct xattr_handler ocfs2_xattr_trusted_handler = { /* * 'user' attributes support */ -static size_t ocfs2_xattr_user_list(struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len, int type) -{ - const size_t prefix_len = XATTR_USER_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb); - - if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_USER_PREFIX, prefix_len); - memcpy(list + prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - -static int ocfs2_xattr_user_get(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) +static int ocfs2_xattr_user_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb); - if (strcmp(name, "") == 0) - return -EINVAL; if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR) return -EOPNOTSUPP; return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_USER, name, buffer, size); } -static int ocfs2_xattr_user_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +static int ocfs2_xattr_user_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb); - if (strcmp(name, "") == 0) - return -EINVAL; if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR) return -EOPNOTSUPP; @@ -7414,7 +7372,6 @@ static int ocfs2_xattr_user_set(struct dentry *dentry, const char *name, const struct xattr_handler ocfs2_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, - .list = ocfs2_xattr_user_list, .get = ocfs2_xattr_user_get, .set = ocfs2_xattr_user_set, }; diff --git a/fs/open.c b/fs/open.c index b6f1e96a7c0b..b25b1542c530 100644 --- a/fs/open.c +++ b/fs/open.c @@ -887,7 +887,7 @@ EXPORT_SYMBOL(dentry_open); static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op) { int lookup_flags = 0; - int acc_mode; + int acc_mode = ACC_MODE(flags); if (flags & (O_CREAT | __O_TMPFILE)) op->mode = (mode & S_IALLUGO) | S_IFREG; @@ -909,7 +909,6 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o if (flags & __O_TMPFILE) { if ((flags & O_TMPFILE_MASK) != O_TMPFILE) return -EINVAL; - acc_mode = MAY_OPEN | ACC_MODE(flags); if (!(acc_mode & MAY_WRITE)) return -EINVAL; } else if (flags & O_PATH) { @@ -919,8 +918,6 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o */ flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH; acc_mode = 0; - } else { - acc_mode = MAY_OPEN | ACC_MODE(flags); } op->open_flag = flags; diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 871fcb67be97..0a8983492d91 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -195,8 +195,7 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat) static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, struct dentry *dentry, struct path *lowerpath, - struct kstat *stat, struct iattr *attr, - const char *link) + struct kstat *stat, const char *link) { struct inode *wdir = workdir->d_inode; struct inode *udir = upperdir->d_inode; @@ -240,8 +239,6 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, mutex_lock(&newdentry->d_inode->i_mutex); err = ovl_set_attr(newdentry, stat); - if (!err && attr) - err = notify_change(newdentry, attr, NULL); mutex_unlock(&newdentry->d_inode->i_mutex); if (err) goto out_cleanup; @@ -286,8 +283,7 @@ out_cleanup: * that point the file will have already been copied up anyway. */ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, - struct path *lowerpath, struct kstat *stat, - struct iattr *attr) + struct path *lowerpath, struct kstat *stat) { struct dentry *workdir = ovl_workdir(dentry); int err; @@ -345,26 +341,19 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, } upperdentry = ovl_dentry_upper(dentry); if (upperdentry) { - unlock_rename(workdir, upperdir); + /* Raced with another copy-up? Nothing to do, then... */ err = 0; - /* Raced with another copy-up? Do the setattr here */ - if (attr) { - mutex_lock(&upperdentry->d_inode->i_mutex); - err = notify_change(upperdentry, attr, NULL); - mutex_unlock(&upperdentry->d_inode->i_mutex); - } - goto out_put_cred; + goto out_unlock; } err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath, - stat, attr, link); + stat, link); if (!err) { /* Restore timestamps on parent (best effort) */ ovl_set_timestamps(upperdir, &pstat); } out_unlock: unlock_rename(workdir, upperdir); -out_put_cred: revert_creds(old_cred); put_cred(override_cred); @@ -406,7 +395,7 @@ int ovl_copy_up(struct dentry *dentry) ovl_path_lower(next, &lowerpath); err = vfs_getattr(&lowerpath, &stat); if (!err) - err = ovl_copy_up_one(parent, next, &lowerpath, &stat, NULL); + err = ovl_copy_up_one(parent, next, &lowerpath, &stat); dput(parent); dput(next); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index ec0c2a050043..964a60fa7afc 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -12,8 +12,7 @@ #include <linux/xattr.h> #include "overlayfs.h" -static int ovl_copy_up_last(struct dentry *dentry, struct iattr *attr, - bool no_data) +static int ovl_copy_up_truncate(struct dentry *dentry) { int err; struct dentry *parent; @@ -30,10 +29,8 @@ static int ovl_copy_up_last(struct dentry *dentry, struct iattr *attr, if (err) goto out_dput_parent; - if (no_data) - stat.size = 0; - - err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat, attr); + stat.size = 0; + err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat); out_dput_parent: dput(parent); @@ -49,13 +46,13 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) if (err) goto out; - upperdentry = ovl_dentry_upper(dentry); - if (upperdentry) { + err = ovl_copy_up(dentry); + if (!err) { + upperdentry = ovl_dentry_upper(dentry); + mutex_lock(&upperdentry->d_inode->i_mutex); err = notify_change(upperdentry, attr, NULL); mutex_unlock(&upperdentry->d_inode->i_mutex); - } else { - err = ovl_copy_up_last(dentry, attr, false); } ovl_drop_write(dentry); out: @@ -134,57 +131,23 @@ out_dput: return err; } - -struct ovl_link_data { - struct dentry *realdentry; - void *cookie; -}; - -static const char *ovl_follow_link(struct dentry *dentry, void **cookie) +static const char *ovl_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { struct dentry *realdentry; struct inode *realinode; - struct ovl_link_data *data = NULL; - const char *ret; + + if (!dentry) + return ERR_PTR(-ECHILD); realdentry = ovl_dentry_real(dentry); realinode = realdentry->d_inode; - if (WARN_ON(!realinode->i_op->follow_link)) + if (WARN_ON(!realinode->i_op->get_link)) return ERR_PTR(-EPERM); - if (realinode->i_op->put_link) { - data = kmalloc(sizeof(struct ovl_link_data), GFP_KERNEL); - if (!data) - return ERR_PTR(-ENOMEM); - data->realdentry = realdentry; - } - - ret = realinode->i_op->follow_link(realdentry, cookie); - if (IS_ERR_OR_NULL(ret)) { - kfree(data); - return ret; - } - - if (data) - data->cookie = *cookie; - - *cookie = data; - - return ret; -} - -static void ovl_put_link(struct inode *unused, void *c) -{ - struct inode *realinode; - struct ovl_link_data *data = c; - - if (!data) - return; - - realinode = data->realdentry->d_inode; - realinode->i_op->put_link(realinode, data->cookie); - kfree(data); + return realinode->i_op->get_link(realdentry, realinode, done); } static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz) @@ -353,7 +316,7 @@ struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags) return ERR_PTR(err); if (file_flags & O_TRUNC) - err = ovl_copy_up_last(dentry, NULL, true); + err = ovl_copy_up_truncate(dentry); else err = ovl_copy_up(dentry); ovl_drop_write(dentry); @@ -381,8 +344,7 @@ static const struct inode_operations ovl_file_inode_operations = { static const struct inode_operations ovl_symlink_inode_operations = { .setattr = ovl_setattr, - .follow_link = ovl_follow_link, - .put_link = ovl_put_link, + .get_link = ovl_get_link, .readlink = ovl_readlink, .getattr = ovl_getattr, .setxattr = ovl_setxattr, diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index ea5a40b06e3a..e17154aeaae4 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -194,7 +194,6 @@ void ovl_cleanup(struct inode *dir, struct dentry *dentry); /* copy_up.c */ int ovl_copy_up(struct dentry *dentry); int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, - struct path *lowerpath, struct kstat *stat, - struct iattr *attr); + struct path *lowerpath, struct kstat *stat); int ovl_copy_xattr(struct dentry *old, struct dentry *new); int ovl_set_attr(struct dentry *upper, struct kstat *stat); diff --git a/fs/pipe.c b/fs/pipe.c index 8865f7963700..42cf8ddf0e55 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -366,18 +366,17 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) int offset = buf->offset + buf->len; if (ops->can_merge && offset + chars <= PAGE_SIZE) { - int error = ops->confirm(pipe, buf); - if (error) + ret = ops->confirm(pipe, buf); + if (ret) goto out; ret = copy_page_from_iter(buf->page, offset, chars, from); if (unlikely(ret < chars)) { - error = -EFAULT; + ret = -EFAULT; goto out; } do_wakeup = 1; - buf->len += chars; - ret = chars; + buf->len += ret; if (!iov_iter_count(from)) goto out; } @@ -693,17 +692,20 @@ int create_pipe_files(struct file **res, int flags) d_instantiate(path.dentry, inode); - err = -ENFILE; f = alloc_file(&path, FMODE_WRITE, &pipefifo_fops); - if (IS_ERR(f)) + if (IS_ERR(f)) { + err = PTR_ERR(f); goto err_dentry; + } f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)); f->private_data = inode->i_pipe; res[0] = alloc_file(&path, FMODE_READ, &pipefifo_fops); - if (IS_ERR(res[0])) + if (IS_ERR(res[0])) { + err = PTR_ERR(res[0]); goto err_file; + } path_get(&path); res[0]->private_data = inode->i_pipe; diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 4fb17ded7d47..711dd5170376 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -762,8 +762,9 @@ posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl, EXPORT_SYMBOL (posix_acl_to_xattr); static int -posix_acl_xattr_get(struct dentry *dentry, const char *name, - void *value, size_t size, int type) +posix_acl_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *value, size_t size) { struct posix_acl *acl; int error; @@ -773,7 +774,7 @@ posix_acl_xattr_get(struct dentry *dentry, const char *name, if (d_is_symlink(dentry)) return -EOPNOTSUPP; - acl = get_acl(d_backing_inode(dentry), type); + acl = get_acl(d_backing_inode(dentry), handler->flags); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl == NULL) @@ -786,8 +787,9 @@ posix_acl_xattr_get(struct dentry *dentry, const char *name, } static int -posix_acl_xattr_set(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, int type) +posix_acl_xattr_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); struct posix_acl *acl = NULL; @@ -798,7 +800,7 @@ posix_acl_xattr_set(struct dentry *dentry, const char *name, if (!inode->i_op->set_acl) return -EOPNOTSUPP; - if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) + if (handler->flags == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) return value ? -EACCES : 0; if (!inode_owner_or_capable(inode)) return -EPERM; @@ -815,37 +817,20 @@ posix_acl_xattr_set(struct dentry *dentry, const char *name, } } - ret = inode->i_op->set_acl(inode, acl, type); + ret = inode->i_op->set_acl(inode, acl, handler->flags); out: posix_acl_release(acl); return ret; } -static size_t -posix_acl_xattr_list(struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len, int type) +static bool +posix_acl_xattr_list(struct dentry *dentry) { - const char *xname; - size_t size; - - if (!IS_POSIXACL(d_backing_inode(dentry))) - return -EOPNOTSUPP; - if (d_is_symlink(dentry)) - return -EOPNOTSUPP; - - if (type == ACL_TYPE_ACCESS) - xname = POSIX_ACL_XATTR_ACCESS; - else - xname = POSIX_ACL_XATTR_DEFAULT; - - size = strlen(xname) + 1; - if (list && size <= list_size) - memcpy(list, xname, size); - return size; + return IS_POSIXACL(d_backing_inode(dentry)); } const struct xattr_handler posix_acl_access_xattr_handler = { - .prefix = POSIX_ACL_XATTR_ACCESS, + .name = XATTR_NAME_POSIX_ACL_ACCESS, .flags = ACL_TYPE_ACCESS, .list = posix_acl_xattr_list, .get = posix_acl_xattr_get, @@ -854,7 +839,7 @@ const struct xattr_handler posix_acl_access_xattr_handler = { EXPORT_SYMBOL_GPL(posix_acl_access_xattr_handler); const struct xattr_handler posix_acl_default_xattr_handler = { - .prefix = POSIX_ACL_XATTR_DEFAULT, + .name = XATTR_NAME_POSIX_ACL_DEFAULT, .flags = ACL_TYPE_DEFAULT, .list = posix_acl_xattr_list, .get = posix_acl_xattr_get, diff --git a/fs/proc/array.c b/fs/proc/array.c index eed2050db9be..d73291f5f0fc 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -91,18 +91,18 @@ static inline void task_name(struct seq_file *m, struct task_struct *p) { char *buf; + size_t size; char tcomm[sizeof(p->comm)]; + int ret; get_task_comm(tcomm, p); seq_puts(m, "Name:\t"); - buf = m->buf + m->count; - /* Ignore error for now */ - buf += string_escape_str(tcomm, buf, m->size - m->count, - ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); + size = seq_get_buf(m, &buf); + ret = string_escape_str(tcomm, buf, size, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); + seq_commit(m, ret < size ? ret : -1); - m->count = buf - m->buf; seq_putc(m, '\n'); } diff --git a/fs/proc/base.c b/fs/proc/base.c index bd3e9e68125b..2cf5d7e37375 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1564,12 +1564,16 @@ static int proc_exe_link(struct dentry *dentry, struct path *exe_path) return -ENOENT; } -static const char *proc_pid_follow_link(struct dentry *dentry, void **cookie) +static const char *proc_pid_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(dentry); struct path path; int error = -EACCES; + if (!dentry) + return ERR_PTR(-ECHILD); + /* Are we allowed to snoop on the tasks file descriptors? */ if (!proc_fd_access_allowed(inode)) goto out; @@ -1630,7 +1634,7 @@ out: const struct inode_operations proc_pid_link_inode_operations = { .readlink = proc_pid_readlink, - .follow_link = proc_pid_follow_link, + .get_link = proc_pid_get_link, .setattr = proc_setattr, }; @@ -1895,7 +1899,7 @@ static const struct dentry_operations tid_map_files_dentry_operations = { .d_delete = pid_delete_dentry, }; -static int proc_map_files_get_link(struct dentry *dentry, struct path *path) +static int map_files_get_link(struct dentry *dentry, struct path *path) { unsigned long vm_start, vm_end; struct vm_area_struct *vma; @@ -1945,20 +1949,22 @@ struct map_files_info { * path to the file in question. */ static const char * -proc_map_files_follow_link(struct dentry *dentry, void **cookie) +proc_map_files_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - return proc_pid_follow_link(dentry, NULL); + return proc_pid_get_link(dentry, inode, done); } /* - * Identical to proc_pid_link_inode_operations except for follow_link() + * Identical to proc_pid_link_inode_operations except for get_link() */ static const struct inode_operations proc_map_files_link_inode_operations = { .readlink = proc_pid_readlink, - .follow_link = proc_map_files_follow_link, + .get_link = proc_map_files_get_link, .setattr = proc_setattr, }; @@ -1975,7 +1981,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry, return -ENOENT; ei = PROC_I(inode); - ei->op.proc_get_link = proc_map_files_get_link; + ei->op.proc_get_link = map_files_get_link; inode->i_op = &proc_map_files_link_inode_operations; inode->i_size = 64; @@ -2359,7 +2365,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); - char *page; + void *page; ssize_t length; struct task_struct *task = get_proc_task(inode); @@ -2374,14 +2380,11 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, if (*ppos != 0) goto out; - length = -ENOMEM; - page = (char*)__get_free_page(GFP_TEMPORARY); - if (!page) + page = memdup_user(buf, count); + if (IS_ERR(page)) { + length = PTR_ERR(page); goto out; - - length = -EFAULT; - if (copy_from_user(page, buf, count)) - goto out_free; + } /* Guard against adverse ptrace interaction */ length = mutex_lock_interruptible(&task->signal->cred_guard_mutex); @@ -2390,10 +2393,10 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, length = security_setprocattr(task, (char*)file->f_path.dentry->d_name.name, - (void*)page, count); + page, count); mutex_unlock(&task->signal->cred_guard_mutex); out_free: - free_page((unsigned long) page); + kfree(page); out: put_task_struct(task); out_no_task: @@ -2494,6 +2497,7 @@ static ssize_t proc_coredump_filter_write(struct file *file, mm = get_task_mm(task); if (!mm) goto out_no_mm; + ret = 0; for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) { if (val & mask) diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 6e5fcd00733e..56afa5ef08f2 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -258,6 +258,7 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx, name, len, instantiate, p, (void *)(unsigned long)fd)) goto out_fd_loop; + cond_resched(); rcu_read_lock(); } rcu_read_unlock(); @@ -291,11 +292,19 @@ static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry, */ int proc_fd_permission(struct inode *inode, int mask) { - int rv = generic_permission(inode, mask); + struct task_struct *p; + int rv; + + rv = generic_permission(inode, mask); if (rv == 0) - return 0; - if (task_tgid(current) == proc_pid(inode)) + return rv; + + rcu_read_lock(); + p = pid_task(proc_pid(inode), PIDTYPE_PID); + if (p && same_thread_group(p, current)) rv = 0; + rcu_read_unlock(); + return rv; } diff --git a/fs/proc/inode.c b/fs/proc/inode.c index bd95b9fdebb0..d0e9b9b6223e 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -393,24 +393,25 @@ static const struct file_operations proc_reg_file_ops_no_compat = { }; #endif -static const char *proc_follow_link(struct dentry *dentry, void **cookie) +static void proc_put_link(void *p) { - struct proc_dir_entry *pde = PDE(d_inode(dentry)); - if (unlikely(!use_pde(pde))) - return ERR_PTR(-EINVAL); - *cookie = pde; - return pde->data; + unuse_pde(p); } -static void proc_put_link(struct inode *unused, void *p) +static const char *proc_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - unuse_pde(p); + struct proc_dir_entry *pde = PDE(inode); + if (unlikely(!use_pde(pde))) + return ERR_PTR(-EINVAL); + set_delayed_call(done, proc_put_link, pde); + return pde->data; } const struct inode_operations proc_link_inode_operations = { .readlink = generic_readlink, - .follow_link = proc_follow_link, - .put_link = proc_put_link, + .get_link = proc_get_link, }; struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index f6e8354b8cea..1dece8781f91 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -30,14 +30,18 @@ static const struct proc_ns_operations *ns_entries[] = { &mntns_operations, }; -static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie) +static const char *proc_ns_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(dentry); const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops; struct task_struct *task; struct path ns_path; void *error = ERR_PTR(-EACCES); + if (!dentry) + return ERR_PTR(-ECHILD); + task = get_proc_task(inode); if (!task) return error; @@ -74,7 +78,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl static const struct inode_operations proc_ns_link_inode_operations = { .readlink = proc_ns_readlink, - .follow_link = proc_ns_follow_link, + .get_link = proc_ns_get_link, .setattr = proc_setattr, }; diff --git a/fs/proc/self.c b/fs/proc/self.c index 113b8d061fc0..67e8db442cf0 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -18,26 +18,28 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer, return readlink_copy(buffer, buflen, tmp); } -static const char *proc_self_follow_link(struct dentry *dentry, void **cookie) +static const char *proc_self_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct pid_namespace *ns = dentry->d_sb->s_fs_info; + struct pid_namespace *ns = inode->i_sb->s_fs_info; pid_t tgid = task_tgid_nr_ns(current, ns); char *name; if (!tgid) return ERR_PTR(-ENOENT); /* 11 for max length of signed int in decimal + NULL term */ - name = kmalloc(12, GFP_KERNEL); - if (!name) - return ERR_PTR(-ENOMEM); + name = kmalloc(12, dentry ? GFP_KERNEL : GFP_ATOMIC); + if (unlikely(!name)) + return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); sprintf(name, "%d", tgid); - return *cookie = name; + set_delayed_call(done, kfree_link, name); + return name; } static const struct inode_operations proc_self_inode_operations = { .readlink = proc_self_readlink, - .follow_link = proc_self_follow_link, - .put_link = kfree_put_link, + .get_link = proc_self_get_link, }; static unsigned self_inum; diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index 947b0f4fd0a1..9eacd59e0360 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -19,26 +19,29 @@ static int proc_thread_self_readlink(struct dentry *dentry, char __user *buffer, return readlink_copy(buffer, buflen, tmp); } -static const char *proc_thread_self_follow_link(struct dentry *dentry, void **cookie) +static const char *proc_thread_self_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct pid_namespace *ns = dentry->d_sb->s_fs_info; + struct pid_namespace *ns = inode->i_sb->s_fs_info; pid_t tgid = task_tgid_nr_ns(current, ns); pid_t pid = task_pid_nr_ns(current, ns); char *name; if (!pid) return ERR_PTR(-ENOENT); - name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL); - if (!name) - return ERR_PTR(-ENOMEM); + name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, + dentry ? GFP_KERNEL : GFP_ATOMIC); + if (unlikely(!name)) + return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); sprintf(name, "%d/task/%d", tgid, pid); - return *cookie = name; + set_delayed_call(done, kfree_link, name); + return name; } static const struct inode_operations proc_thread_self_inode_operations = { .readlink = proc_thread_self_readlink, - .follow_link = proc_thread_self_follow_link, - .put_link = kfree_put_link, + .get_link = proc_thread_self_get_link, }; static unsigned thread_self_inum; diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 8ebd9a334085..2256e7e23e67 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -95,9 +95,9 @@ static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt) { struct proc_mounts *p = m->private; struct mount *r = real_mount(mnt); - int err = 0; struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; struct super_block *sb = mnt_path.dentry->d_sb; + int err; if (sb->s_op->show_devname) { err = sb->s_op->show_devname(m, mnt_path.dentry); @@ -131,16 +131,17 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) struct mount *r = real_mount(mnt); struct super_block *sb = mnt->mnt_sb; struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; - int err = 0; + int err; seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id, MAJOR(sb->s_dev), MINOR(sb->s_dev)); - if (sb->s_op->show_path) + if (sb->s_op->show_path) { err = sb->s_op->show_path(m, mnt->mnt_root); - else + if (err) + goto out; + } else { seq_dentry(m, mnt->mnt_root, " \t\n\\"); - if (err) - goto out; + } seq_putc(m, ' '); /* mountpoints outside of chroot jail will give SEQ_SKIP on this */ @@ -168,12 +169,13 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) seq_puts(m, " - "); show_type(m, sb); seq_putc(m, ' '); - if (sb->s_op->show_devname) + if (sb->s_op->show_devname) { err = sb->s_op->show_devname(m, mnt->mnt_root); - else + if (err) + goto out; + } else { mangle(m, r->mnt_devname ? r->mnt_devname : "none"); - if (err) - goto out; + } seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw"); err = show_sb_opts(m, sb); if (err) @@ -191,7 +193,7 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt) struct mount *r = real_mount(mnt); struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; struct super_block *sb = mnt_path.dentry->d_sb; - int err = 0; + int err; /* device */ if (sb->s_op->show_devname) { @@ -220,8 +222,7 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt) /* optional statistics */ if (sb->s_op->show_stats) { seq_putc(m, ' '); - if (!err) - err = sb->s_op->show_stats(m, mnt_path.dentry); + err = sb->s_op->show_stats(m, mnt_path.dentry); } seq_putc(m, '\n'); diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index c4bcb778886e..f37b3deb01b4 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -316,6 +316,7 @@ struct inode *qnx4_iget(struct super_block *sb, unsigned long ino) inode->i_fop = &qnx4_dir_operations; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &qnx4_aops; qnx4_i(inode)->mmu_private = inode->i_size; } else { diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 32d2e1a9774c..9728b5499e1d 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -582,6 +582,7 @@ struct inode *qnx6_iget(struct super_block *sb, unsigned ino) inode->i_mapping->a_ops = &qnx6_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &qnx6_aops; } else init_special_inode(inode, inode->i_mode, 0); diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 889d558b4e05..38981b037524 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -79,6 +79,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); break; } } diff --git a/fs/read_write.c b/fs/read_write.c index 819ef3faf1bb..06b07d5a08fe 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -16,6 +16,7 @@ #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/compat.h> +#include <linux/mount.h> #include "internal.h" #include <asm/uaccess.h> @@ -171,6 +172,45 @@ loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t si EXPORT_SYMBOL(fixed_size_llseek); /** + * no_seek_end_llseek - llseek implementation for fixed-sized devices + * @file: file structure to seek on + * @offset: file offset to seek to + * @whence: type of seek + * + */ +loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) +{ + switch (whence) { + case SEEK_SET: case SEEK_CUR: + return generic_file_llseek_size(file, offset, whence, + ~0ULL, 0); + default: + return -EINVAL; + } +} +EXPORT_SYMBOL(no_seek_end_llseek); + +/** + * no_seek_end_llseek_size - llseek implementation for fixed-sized devices + * @file: file structure to seek on + * @offset: file offset to seek to + * @whence: type of seek + * @size: maximal offset allowed + * + */ +loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size) +{ + switch (whence) { + case SEEK_SET: case SEEK_CUR: + return generic_file_llseek_size(file, offset, whence, + size, 0); + default: + return -EINVAL; + } +} +EXPORT_SYMBOL(no_seek_end_llseek_size); + +/** * noop_llseek - No Operation Performed llseek implementation * @file: file structure to seek on * @offset: file offset to seek to @@ -395,9 +435,8 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t } if (unlikely(inode->i_flctx && mandatory_lock(inode))) { - retval = locks_mandatory_area( - read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE, - inode, file, pos, count); + retval = locks_mandatory_area(inode, file, pos, pos + count - 1, + read_write == READ ? F_RDLCK : F_WRLCK); if (retval < 0) return retval; } @@ -1327,3 +1366,299 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, return do_sendfile(out_fd, in_fd, NULL, count, 0); } #endif + +/* + * copy_file_range() differs from regular file read and write in that it + * specifically allows return partial success. When it does so is up to + * the copy_file_range method. + */ +ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t len, unsigned int flags) +{ + struct inode *inode_in = file_inode(file_in); + struct inode *inode_out = file_inode(file_out); + ssize_t ret; + + if (flags != 0) + return -EINVAL; + + /* copy_file_range allows full ssize_t len, ignoring MAX_RW_COUNT */ + ret = rw_verify_area(READ, file_in, &pos_in, len); + if (ret >= 0) + ret = rw_verify_area(WRITE, file_out, &pos_out, len); + if (ret < 0) + return ret; + + if (!(file_in->f_mode & FMODE_READ) || + !(file_out->f_mode & FMODE_WRITE) || + (file_out->f_flags & O_APPEND)) + return -EBADF; + + /* this could be relaxed once a method supports cross-fs copies */ + if (inode_in->i_sb != inode_out->i_sb) + return -EXDEV; + + if (len == 0) + return 0; + + ret = mnt_want_write_file(file_out); + if (ret) + return ret; + + ret = -EOPNOTSUPP; + if (file_out->f_op->copy_file_range) + ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, + pos_out, len, flags); + if (ret == -EOPNOTSUPP) + ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out, + len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); + + if (ret > 0) { + fsnotify_access(file_in); + add_rchar(current, ret); + fsnotify_modify(file_out); + add_wchar(current, ret); + } + inc_syscr(current); + inc_syscw(current); + + mnt_drop_write_file(file_out); + + return ret; +} +EXPORT_SYMBOL(vfs_copy_file_range); + +SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, + int, fd_out, loff_t __user *, off_out, + size_t, len, unsigned int, flags) +{ + loff_t pos_in; + loff_t pos_out; + struct fd f_in; + struct fd f_out; + ssize_t ret = -EBADF; + + f_in = fdget(fd_in); + if (!f_in.file) + goto out2; + + f_out = fdget(fd_out); + if (!f_out.file) + goto out1; + + ret = -EFAULT; + if (off_in) { + if (copy_from_user(&pos_in, off_in, sizeof(loff_t))) + goto out; + } else { + pos_in = f_in.file->f_pos; + } + + if (off_out) { + if (copy_from_user(&pos_out, off_out, sizeof(loff_t))) + goto out; + } else { + pos_out = f_out.file->f_pos; + } + + ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len, + flags); + if (ret > 0) { + pos_in += ret; + pos_out += ret; + + if (off_in) { + if (copy_to_user(off_in, &pos_in, sizeof(loff_t))) + ret = -EFAULT; + } else { + f_in.file->f_pos = pos_in; + } + + if (off_out) { + if (copy_to_user(off_out, &pos_out, sizeof(loff_t))) + ret = -EFAULT; + } else { + f_out.file->f_pos = pos_out; + } + } + +out: + fdput(f_out); +out1: + fdput(f_in); +out2: + return ret; +} + +static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write) +{ + struct inode *inode = file_inode(file); + + if (unlikely(pos < 0)) + return -EINVAL; + + if (unlikely((loff_t) (pos + len) < 0)) + return -EINVAL; + + if (unlikely(inode->i_flctx && mandatory_lock(inode))) { + loff_t end = len ? pos + len - 1 : OFFSET_MAX; + int retval; + + retval = locks_mandatory_area(inode, file, pos, end, + write ? F_WRLCK : F_RDLCK); + if (retval < 0) + return retval; + } + + return security_file_permission(file, write ? MAY_WRITE : MAY_READ); +} + +int vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len) +{ + struct inode *inode_in = file_inode(file_in); + struct inode *inode_out = file_inode(file_out); + int ret; + + if (inode_in->i_sb != inode_out->i_sb || + file_in->f_path.mnt != file_out->f_path.mnt) + return -EXDEV; + + if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) + return -EISDIR; + if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) + return -EINVAL; + + if (!(file_in->f_mode & FMODE_READ) || + !(file_out->f_mode & FMODE_WRITE) || + (file_out->f_flags & O_APPEND) || + !file_in->f_op->clone_file_range) + return -EBADF; + + ret = clone_verify_area(file_in, pos_in, len, false); + if (ret) + return ret; + + ret = clone_verify_area(file_out, pos_out, len, true); + if (ret) + return ret; + + if (pos_in + len > i_size_read(inode_in)) + return -EINVAL; + + ret = mnt_want_write_file(file_out); + if (ret) + return ret; + + ret = file_in->f_op->clone_file_range(file_in, pos_in, + file_out, pos_out, len); + if (!ret) { + fsnotify_access(file_in); + fsnotify_modify(file_out); + } + + mnt_drop_write_file(file_out); + return ret; +} +EXPORT_SYMBOL(vfs_clone_file_range); + +int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) +{ + struct file_dedupe_range_info *info; + struct inode *src = file_inode(file); + u64 off; + u64 len; + int i; + int ret; + bool is_admin = capable(CAP_SYS_ADMIN); + u16 count = same->dest_count; + struct file *dst_file; + loff_t dst_off; + ssize_t deduped; + + if (!(file->f_mode & FMODE_READ)) + return -EINVAL; + + if (same->reserved1 || same->reserved2) + return -EINVAL; + + off = same->src_offset; + len = same->src_length; + + ret = -EISDIR; + if (S_ISDIR(src->i_mode)) + goto out; + + ret = -EINVAL; + if (!S_ISREG(src->i_mode)) + goto out; + + ret = clone_verify_area(file, off, len, false); + if (ret < 0) + goto out; + ret = 0; + + /* pre-format output fields to sane values */ + for (i = 0; i < count; i++) { + same->info[i].bytes_deduped = 0ULL; + same->info[i].status = FILE_DEDUPE_RANGE_SAME; + } + + for (i = 0, info = same->info; i < count; i++, info++) { + struct inode *dst; + struct fd dst_fd = fdget(info->dest_fd); + + dst_file = dst_fd.file; + if (!dst_file) { + info->status = -EBADF; + goto next_loop; + } + dst = file_inode(dst_file); + + ret = mnt_want_write_file(dst_file); + if (ret) { + info->status = ret; + goto next_loop; + } + + dst_off = info->dest_offset; + ret = clone_verify_area(dst_file, dst_off, len, true); + if (ret < 0) { + info->status = ret; + goto next_file; + } + ret = 0; + + if (info->reserved) { + info->status = -EINVAL; + } else if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) { + info->status = -EINVAL; + } else if (file->f_path.mnt != dst_file->f_path.mnt) { + info->status = -EXDEV; + } else if (S_ISDIR(dst->i_mode)) { + info->status = -EISDIR; + } else if (dst_file->f_op->dedupe_file_range == NULL) { + info->status = -EINVAL; + } else { + deduped = dst_file->f_op->dedupe_file_range(file, off, + len, dst_file, + info->dest_offset); + if (deduped == -EBADE) + info->status = FILE_DEDUPE_RANGE_DIFFERS; + else if (deduped < 0) + info->status = deduped; + else + info->bytes_deduped += deduped; + } + +next_file: + mnt_drop_write_file(dst_file); +next_loop: + fdput(dst_fd); + } + +out: + return ret; +} +EXPORT_SYMBOL(vfs_dedupe_file_range); diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 3d8e7e671d5b..ae9e5b308cf9 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1361,6 +1361,7 @@ static void init_inode(struct inode *inode, struct treepath *path) inode->i_fop = &reiserfs_dir_operations; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &reiserfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &reiserfs_address_space_operations; } else { inode->i_blocks = 0; diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 9d6486d416a3..44c2bdced1c8 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -618,12 +618,10 @@ static void release_buffer_page(struct buffer_head *bh) static void reiserfs_end_buffer_io_sync(struct buffer_head *bh, int uptodate) { - char b[BDEVNAME_SIZE]; - if (buffer_journaled(bh)) { reiserfs_warning(NULL, "clm-2084", - "pinned buffer %lu:%s sent to disk", - bh->b_blocknr, bdevname(bh->b_bdev, b)); + "pinned buffer %lu:%pg sent to disk", + bh->b_blocknr, bh->b_bdev); } if (uptodate) set_buffer_uptodate(bh); @@ -2387,11 +2385,10 @@ static int journal_read(struct super_block *sb) int replay_count = 0; int continue_replay = 1; int ret; - char b[BDEVNAME_SIZE]; cur_dblock = SB_ONDISK_JOURNAL_1st_BLOCK(sb); - reiserfs_info(sb, "checking transaction log (%s)\n", - bdevname(journal->j_dev_bd, b)); + reiserfs_info(sb, "checking transaction log (%pg)\n", + journal->j_dev_bd); start = get_seconds(); /* @@ -2651,8 +2648,8 @@ static int journal_init_dev(struct super_block *super, set_blocksize(journal->j_dev_bd, super->s_blocksize); reiserfs_info(super, - "journal_init_dev: journal device: %s\n", - bdevname(journal->j_dev_bd, b)); + "journal_init_dev: journal device: %pg\n", + journal->j_dev_bd); return 0; } @@ -2724,7 +2721,6 @@ int journal_init(struct super_block *sb, const char *j_dev_name, struct reiserfs_journal_header *jh; struct reiserfs_journal *journal; struct reiserfs_journal_list *jl; - char b[BDEVNAME_SIZE]; int ret; journal = SB_JOURNAL(sb) = vzalloc(sizeof(struct reiserfs_journal)); @@ -2794,10 +2790,10 @@ int journal_init(struct super_block *sb, const char *j_dev_name, && (le32_to_cpu(jh->jh_journal.jp_journal_magic) != sb_jp_journal_magic(rs))) { reiserfs_warning(sb, "sh-460", - "journal header magic %x (device %s) does " + "journal header magic %x (device %pg) does " "not match to magic found in super block %x", jh->jh_journal.jp_journal_magic, - bdevname(journal->j_dev_bd, b), + journal->j_dev_bd, sb_jp_journal_magic(rs)); brelse(bhjh); goto free_and_return; @@ -2818,10 +2814,10 @@ int journal_init(struct super_block *sb, const char *j_dev_name, journal->j_max_trans_age = commit_max_age; } - reiserfs_info(sb, "journal params: device %s, size %u, " + reiserfs_info(sb, "journal params: device %pg, size %u, " "journal first block %u, max trans len %u, max batch %u, " "max commit age %u, max trans age %u\n", - bdevname(journal->j_dev_bd, b), + journal->j_dev_bd, SB_ONDISK_JOURNAL_SIZE(sb), SB_ONDISK_JOURNAL_1st_BLOCK(sb), journal->j_trans_max, diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 5f1c9c29eb8c..2a12d46d7fb4 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -712,9 +712,6 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode 2 * (REISERFS_QUOTA_INIT_BLOCKS(dir->i_sb) + REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb)); - if (!new_valid_dev(rdev)) - return -EINVAL; - retval = dquot_initialize(dir); if (retval) return retval; @@ -1173,6 +1170,7 @@ static int reiserfs_symlink(struct inode *parent_dir, reiserfs_update_inode_transaction(parent_dir); inode->i_op = &reiserfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &reiserfs_address_space_operations; retval = reiserfs_add_entry(&th, parent_dir, dentry->d_name.name, @@ -1667,8 +1665,7 @@ const struct inode_operations reiserfs_dir_inode_operations = { */ const struct inode_operations reiserfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = reiserfs_setattr, .setxattr = reiserfs_setxattr, .getxattr = reiserfs_getxattr, diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index ae1dc841db3a..4f3f928076f3 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -139,11 +139,9 @@ static void sprintf_block_head(char *buf, struct buffer_head *bh) static void sprintf_buffer_head(char *buf, struct buffer_head *bh) { - char b[BDEVNAME_SIZE]; - sprintf(buf, - "dev %s, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)", - bdevname(bh->b_bdev, b), bh->b_size, + "dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)", + bh->b_bdev, bh->b_size, (unsigned long long)bh->b_blocknr, atomic_read(&(bh->b_count)), bh->b_state, bh->b_page, buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE", @@ -530,7 +528,6 @@ static int print_super_block(struct buffer_head *bh) (struct reiserfs_super_block *)(bh->b_data); int skipped, data_blocks; char *version; - char b[BDEVNAME_SIZE]; if (is_reiserfs_3_5(rs)) { version = "3.5"; @@ -543,7 +540,7 @@ static int print_super_block(struct buffer_head *bh) return 1; } - printk("%s\'s super block is in block %llu\n", bdevname(bh->b_bdev, b), + printk("%pg\'s super block is in block %llu\n", bh->b_bdev, (unsigned long long)bh->b_blocknr); printk("Reiserfs version %s\n", version); printk("Block count %u\n", sb_block_count(rs)); diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c index 621b9f381fe1..fe999157dd97 100644 --- a/fs/reiserfs/procfs.c +++ b/fs/reiserfs/procfs.c @@ -303,11 +303,10 @@ static int show_journal(struct seq_file *m, void *unused) struct reiserfs_sb_info *r = REISERFS_SB(sb); struct reiserfs_super_block *rs = r->s_rs; struct journal_params *jp = &rs->s_v1.s_journal; - char b[BDEVNAME_SIZE]; seq_printf(m, /* on-disk fields */ "jp_journal_1st_block: \t%i\n" - "jp_journal_dev: \t%s[%x]\n" + "jp_journal_dev: \t%pg[%x]\n" "jp_journal_size: \t%i\n" "jp_journal_trans_max: \t%i\n" "jp_journal_magic: \t%i\n" @@ -348,7 +347,7 @@ static int show_journal(struct seq_file *m, void *unused) "prepare: \t%12lu\n" "prepare_retry: \t%12lu\n", DJP(jp_journal_1st_block), - bdevname(SB_JOURNAL(sb)->j_dev_bd, b), + SB_JOURNAL(sb)->j_dev_bd, DJP(jp_journal_dev), DJP(jp_journal_size), DJP(jp_journal_trans_max), diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index e87f9b52bf06..e5ddb4e5ea94 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -756,7 +756,8 @@ find_xattr_handler_prefix(const struct xattr_handler **handlers, return NULL; for_each_xattr_handler(handlers, xah) { - if (strncmp(xah->prefix, name, strlen(xah->prefix)) == 0) + const char *prefix = xattr_prefix(xah); + if (strncmp(prefix, name, strlen(prefix)) == 0) break; } @@ -778,7 +779,7 @@ reiserfs_getxattr(struct dentry * dentry, const char *name, void *buffer, if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1) return -EOPNOTSUPP; - return handler->get(dentry, name, buffer, size, handler->flags); + return handler->get(handler, dentry, name, buffer, size); } /* @@ -797,7 +798,7 @@ reiserfs_setxattr(struct dentry *dentry, const char *name, const void *value, if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1) return -EOPNOTSUPP; - return handler->set(dentry, name, value, size, flags, handler->flags); + return handler->set(handler, dentry, name, value, size, flags); } /* @@ -814,7 +815,7 @@ int reiserfs_removexattr(struct dentry *dentry, const char *name) if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1) return -EOPNOTSUPP; - return handler->set(dentry, name, NULL, 0, XATTR_REPLACE, handler->flags); + return handler->set(handler, dentry, name, NULL, 0, XATTR_REPLACE); } struct listxattr_buf { @@ -839,19 +840,16 @@ static int listxattr_filler(struct dir_context *ctx, const char *name, handler = find_xattr_handler_prefix(b->dentry->d_sb->s_xattr, name); - if (!handler) /* Unsupported xattr name */ + if (!handler /* Unsupported xattr name */ || + (handler->list && !handler->list(b->dentry))) return 0; + size = namelen + 1; if (b->buf) { - size = handler->list(b->dentry, b->buf + b->pos, - b->size, name, namelen, - handler->flags); if (size > b->size) return -ERANGE; - } else { - size = handler->list(b->dentry, NULL, 0, name, - namelen, handler->flags); + memcpy(b->buf + b->pos, name, namelen); + b->buf[b->pos + namelen] = 0; } - b->pos += size; } return 0; diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 4b34b9dc03dd..558a16beaacb 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -186,10 +186,10 @@ struct posix_acl *reiserfs_get_acl(struct inode *inode, int type) switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: BUG(); @@ -244,7 +244,7 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { error = posix_acl_equiv_mode(acl, &inode->i_mode); if (error < 0) @@ -256,7 +256,7 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, } break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; if (!S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; break; diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index 9a3b0616f283..ab0217d32039 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -9,8 +9,8 @@ #include <linux/uaccess.h> static int -security_get(struct dentry *dentry, const char *name, void *buffer, size_t size, - int handler_flags) +security_get(const struct xattr_handler *handler, struct dentry *dentry, + const char *name, void *buffer, size_t size) { if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX)) return -EINVAL; @@ -22,8 +22,8 @@ security_get(struct dentry *dentry, const char *name, void *buffer, size_t size, } static int -security_set(struct dentry *dentry, const char *name, const void *buffer, - size_t size, int flags, int handler_flags) +security_set(const struct xattr_handler *handler, struct dentry *dentry, + const char *name, const void *buffer, size_t size, int flags) { if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX)) return -EINVAL; @@ -34,20 +34,9 @@ security_set(struct dentry *dentry, const char *name, const void *buffer, return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); } -static size_t security_list(struct dentry *dentry, char *list, size_t list_len, - const char *name, size_t namelen, int handler_flags) +static bool security_list(struct dentry *dentry) { - const size_t len = namelen + 1; - - if (IS_PRIVATE(d_inode(dentry))) - return 0; - - if (list && len <= list_len) { - memcpy(list, name, namelen); - list[namelen] = '\0'; - } - - return len; + return !IS_PRIVATE(d_inode(dentry)); } /* Initializes the security context for a new inode and returns the number diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c index e4f1343714e0..64b67aa643a9 100644 --- a/fs/reiserfs/xattr_trusted.c +++ b/fs/reiserfs/xattr_trusted.c @@ -8,8 +8,8 @@ #include <linux/uaccess.h> static int -trusted_get(struct dentry *dentry, const char *name, void *buffer, size_t size, - int handler_flags) +trusted_get(const struct xattr_handler *handler, struct dentry *dentry, + const char *name, void *buffer, size_t size) { if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX)) return -EINVAL; @@ -21,8 +21,8 @@ trusted_get(struct dentry *dentry, const char *name, void *buffer, size_t size, } static int -trusted_set(struct dentry *dentry, const char *name, const void *buffer, - size_t size, int flags, int handler_flags) +trusted_set(const struct xattr_handler *handler, struct dentry *dentry, + const char *name, const void *buffer, size_t size, int flags) { if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX)) return -EINVAL; @@ -33,19 +33,9 @@ trusted_set(struct dentry *dentry, const char *name, const void *buffer, return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); } -static size_t trusted_list(struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len, int handler_flags) +static bool trusted_list(struct dentry *dentry) { - const size_t len = name_len + 1; - - if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry))) - return 0; - - if (list && len <= list_size) { - memcpy(list, name, name_len); - list[name_len] = '\0'; - } - return len; + return capable(CAP_SYS_ADMIN) && !IS_PRIVATE(d_inode(dentry)); } const struct xattr_handler reiserfs_xattr_trusted_handler = { diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c index d0b08d3e5689..12e6306f562a 100644 --- a/fs/reiserfs/xattr_user.c +++ b/fs/reiserfs/xattr_user.c @@ -7,8 +7,8 @@ #include <linux/uaccess.h> static int -user_get(struct dentry *dentry, const char *name, void *buffer, size_t size, - int handler_flags) +user_get(const struct xattr_handler *handler, struct dentry *dentry, + const char *name, void *buffer, size_t size) { if (strlen(name) < sizeof(XATTR_USER_PREFIX)) @@ -19,8 +19,8 @@ user_get(struct dentry *dentry, const char *name, void *buffer, size_t size, } static int -user_set(struct dentry *dentry, const char *name, const void *buffer, - size_t size, int flags, int handler_flags) +user_set(const struct xattr_handler *handler, struct dentry *dentry, + const char *name, const void *buffer, size_t size, int flags) { if (strlen(name) < sizeof(XATTR_USER_PREFIX)) return -EINVAL; @@ -30,18 +30,9 @@ user_set(struct dentry *dentry, const char *name, const void *buffer, return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); } -static size_t user_list(struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len, int handler_flags) +static bool user_list(struct dentry *dentry) { - const size_t len = name_len + 1; - - if (!reiserfs_xattrs_user(dentry->d_sb)) - return 0; - if (list && len <= list_size) { - memcpy(list, name, name_len); - list[name_len] = '\0'; - } - return len; + return reiserfs_xattrs_user(dentry->d_sb); } const struct xattr_handler reiserfs_xattr_user_handler = { diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 268733cda397..bb894e78a821 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -360,6 +360,7 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos) break; case ROMFH_SYM: i->i_op = &page_symlink_inode_operations; + inode_nohighmem(i); i->i_data.a_ops = &romfs_aops; mode |= S_IRWXUGO; break; diff --git a/fs/select.c b/fs/select.c index 015547330e88..79d0d4953cad 100644 --- a/fs/select.c +++ b/fs/select.c @@ -778,8 +778,8 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait, return mask; } -static int do_poll(unsigned int nfds, struct poll_list *list, - struct poll_wqueues *wait, struct timespec *end_time) +static int do_poll(struct poll_list *list, struct poll_wqueues *wait, + struct timespec *end_time) { poll_table* pt = &wait->pt; ktime_t expire, *to = NULL; @@ -908,7 +908,7 @@ int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, } poll_initwait(&table); - fdcount = do_poll(nfds, head, &table, end_time); + fdcount = do_poll(head, &table, end_time); poll_freewait(&table); for (walk = head; walk; walk = walk->next) { diff --git a/fs/seq_file.c b/fs/seq_file.c index 225586e141ca..e85664b7c7d9 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -13,6 +13,7 @@ #include <linux/cred.h> #include <linux/mm.h> #include <linux/printk.h> +#include <linux/string_helpers.h> #include <asm/uaccess.h> #include <asm/page.h> @@ -25,12 +26,17 @@ static void seq_set_overflow(struct seq_file *m) static void *seq_buf_alloc(unsigned long size) { void *buf; + gfp_t gfp = GFP_KERNEL; /* - * __GFP_NORETRY to avoid oom-killings with high-order allocations - - * it's better to fall back to vmalloc() than to kill things. + * For high order allocations, use __GFP_NORETRY to avoid oom-killing - + * it's better to fall back to vmalloc() than to kill things. For small + * allocations, just use GFP_KERNEL which will oom kill, thus no need + * for vmalloc fallback. */ - buf = kmalloc(size, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + if (size > PAGE_SIZE) + gfp |= __GFP_NORETRY | __GFP_NOWARN; + buf = kmalloc(size, gfp); if (!buf && size > PAGE_SIZE) buf = vmalloc(size); return buf; @@ -377,26 +383,12 @@ EXPORT_SYMBOL(seq_release); */ void seq_escape(struct seq_file *m, const char *s, const char *esc) { - char *end = m->buf + m->size; - char *p; - char c; + char *buf; + size_t size = seq_get_buf(m, &buf); + int ret; - for (p = m->buf + m->count; (c = *s) != '\0' && p < end; s++) { - if (!strchr(esc, c)) { - *p++ = c; - continue; - } - if (p + 3 < end) { - *p++ = '\\'; - *p++ = '0' + ((c & 0300) >> 6); - *p++ = '0' + ((c & 070) >> 3); - *p++ = '0' + (c & 07); - continue; - } - seq_set_overflow(m); - return; - } - m->count = p - m->buf; + ret = string_escape_str(s, buf, size, ESCAPE_OCTAL, esc); + seq_commit(m, ret < size ? ret : -1); } EXPORT_SYMBOL(seq_escape); @@ -773,6 +765,8 @@ void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, { const u8 *ptr = buf; int i, linelen, remaining = len; + char *buffer; + size_t size; int ret; if (rowsize != 16 && rowsize != 32) @@ -794,15 +788,12 @@ void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, break; } + size = seq_get_buf(m, &buffer); ret = hex_dump_to_buffer(ptr + i, linelen, rowsize, groupsize, - m->buf + m->count, m->size - m->count, - ascii); - if (ret >= m->size - m->count) { - seq_set_overflow(m); - } else { - m->count += ret; - seq_putc(m, '\n'); - } + buffer, size, ascii); + seq_commit(m, ret < size ? ret : -1); + + seq_putc(m, '\n'); } } EXPORT_SYMBOL(seq_hex_dump); diff --git a/fs/splice.c b/fs/splice.c index 5fc1e50a7f30..82bc0d64fc38 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -360,7 +360,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, break; error = add_to_page_cache_lru(page, mapping, index, - GFP_KERNEL & mapping_gfp_mask(mapping)); + mapping_gfp_constraint(mapping, GFP_KERNEL)); if (unlikely(error)) { page_cache_release(page); if (error == -EEXIST) @@ -415,6 +415,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, */ if (!page->mapping) { unlock_page(page); +retry_lookup: page = find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); @@ -439,13 +440,10 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, error = mapping->a_ops->readpage(in, page); if (unlikely(error)) { /* - * We really should re-lookup the page here, - * but it complicates things a lot. Instead - * lets just do what we already stored, and - * we'll get it the next time we are called. + * Re-lookup the page */ if (error == AOP_TRUNCATED_PAGE) - error = 0; + goto retry_lookup; break; } @@ -809,6 +807,13 @@ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_des */ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd) { + /* + * Check for signal early to make process killable when there are + * always buffers available + */ + if (signal_pending(current)) + return -ERESTARTSYS; + while (!pipe->nrbufs) { if (!pipe->writers) return 0; @@ -884,6 +889,7 @@ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd, splice_from_pipe_begin(sd); do { + cond_resched(); ret = splice_from_pipe_next(pipe, sd); if (ret > 0) ret = splice_from_pipe_feed(pipe, sd, actor); diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index a1ce5ce60632..0927b1e80ab6 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -41,6 +41,7 @@ #include <linux/fs.h> #include <linux/vfs.h> #include <linux/xattr.h> +#include <linux/pagemap.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" @@ -291,6 +292,7 @@ int squashfs_read_inode(struct inode *inode, long long ino) set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_size = le32_to_cpu(sqsh_ino->symlink_size); inode->i_op = &squashfs_symlink_inode_ops; + inode_nohighmem(inode); inode->i_data.a_ops = &squashfs_symlink_aops; inode->i_mode |= S_IFLNK; squashfs_i(inode)->start = block; diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 5056babe00df..dded920cbc8f 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -80,7 +80,6 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) { struct squashfs_sb_info *msblk; struct squashfs_super_block *sblk = NULL; - char b[BDEVNAME_SIZE]; struct inode *root; long long root_inode; unsigned short flags; @@ -124,8 +123,8 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_magic = le32_to_cpu(sblk->s_magic); if (sb->s_magic != SQUASHFS_MAGIC) { if (!silent) - ERROR("Can't find a SQUASHFS superblock on %s\n", - bdevname(sb->s_bdev, b)); + ERROR("Can't find a SQUASHFS superblock on %pg\n", + sb->s_bdev); goto failed_mount; } @@ -178,7 +177,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) msblk->inodes = le32_to_cpu(sblk->inodes); flags = le16_to_cpu(sblk->flags); - TRACE("Found valid superblock on %s\n", bdevname(sb->s_bdev, b)); + TRACE("Found valid superblock on %pg\n", sb->s_bdev); TRACE("Inodes are %scompressed\n", SQUASHFS_UNCOMPRESSED_INODES(flags) ? "un" : ""); TRACE("Data is %scompressed\n", SQUASHFS_UNCOMPRESSED_DATA(flags) diff --git a/fs/squashfs/symlink.c b/fs/squashfs/symlink.c index 12806dffb345..dbcc2f54bad4 100644 --- a/fs/squashfs/symlink.c +++ b/fs/squashfs/symlink.c @@ -119,8 +119,7 @@ const struct address_space_operations squashfs_symlink_aops = { const struct inode_operations squashfs_symlink_inode_ops = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getxattr = generic_getxattr, .listxattr = squashfs_listxattr }; diff --git a/fs/squashfs/xattr.c b/fs/squashfs/xattr.c index e5e0ddf5b143..1e9de96288d8 100644 --- a/fs/squashfs/xattr.c +++ b/fs/squashfs/xattr.c @@ -58,7 +58,7 @@ ssize_t squashfs_listxattr(struct dentry *d, char *buffer, struct squashfs_xattr_entry entry; struct squashfs_xattr_val val; const struct xattr_handler *handler; - int name_size, prefix_size = 0; + int name_size; err = squashfs_read_metadata(sb, &entry, &start, &offset, sizeof(entry)); @@ -67,15 +67,16 @@ ssize_t squashfs_listxattr(struct dentry *d, char *buffer, name_size = le16_to_cpu(entry.size); handler = squashfs_xattr_handler(le16_to_cpu(entry.type)); - if (handler) - prefix_size = handler->list(d, buffer, rest, NULL, - name_size, handler->flags); - if (prefix_size) { + if (handler && (!handler->list || handler->list(d))) { + const char *prefix = handler->prefix ?: handler->name; + size_t prefix_size = strlen(prefix); + if (buffer) { if (prefix_size + name_size + 1 > rest) { err = -ERANGE; goto failed; } + memcpy(buffer, prefix, prefix_size); buffer += prefix_size; } err = squashfs_read_metadata(sb, buffer, &start, @@ -212,88 +213,45 @@ failed: } -/* - * User namespace support - */ -static size_t squashfs_user_list(struct dentry *d, char *list, size_t list_size, - const char *name, size_t name_len, int type) -{ - if (list && XATTR_USER_PREFIX_LEN <= list_size) - memcpy(list, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN); - return XATTR_USER_PREFIX_LEN; -} - -static int squashfs_user_get(struct dentry *d, const char *name, void *buffer, - size_t size, int type) +static int squashfs_xattr_handler_get(const struct xattr_handler *handler, + struct dentry *d, const char *name, + void *buffer, size_t size) { - if (name[0] == '\0') - return -EINVAL; - - return squashfs_xattr_get(d_inode(d), SQUASHFS_XATTR_USER, name, + return squashfs_xattr_get(d_inode(d), handler->flags, name, buffer, size); } +/* + * User namespace support + */ static const struct xattr_handler squashfs_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, - .list = squashfs_user_list, - .get = squashfs_user_get + .flags = SQUASHFS_XATTR_USER, + .get = squashfs_xattr_handler_get }; /* * Trusted namespace support */ -static size_t squashfs_trusted_list(struct dentry *d, char *list, - size_t list_size, const char *name, size_t name_len, int type) +static bool squashfs_trusted_xattr_handler_list(struct dentry *d) { - if (!capable(CAP_SYS_ADMIN)) - return 0; - - if (list && XATTR_TRUSTED_PREFIX_LEN <= list_size) - memcpy(list, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); - return XATTR_TRUSTED_PREFIX_LEN; -} - -static int squashfs_trusted_get(struct dentry *d, const char *name, - void *buffer, size_t size, int type) -{ - if (name[0] == '\0') - return -EINVAL; - - return squashfs_xattr_get(d_inode(d), SQUASHFS_XATTR_TRUSTED, name, - buffer, size); + return capable(CAP_SYS_ADMIN); } static const struct xattr_handler squashfs_xattr_trusted_handler = { .prefix = XATTR_TRUSTED_PREFIX, - .list = squashfs_trusted_list, - .get = squashfs_trusted_get + .flags = SQUASHFS_XATTR_TRUSTED, + .list = squashfs_trusted_xattr_handler_list, + .get = squashfs_xattr_handler_get }; /* * Security namespace support */ -static size_t squashfs_security_list(struct dentry *d, char *list, - size_t list_size, const char *name, size_t name_len, int type) -{ - if (list && XATTR_SECURITY_PREFIX_LEN <= list_size) - memcpy(list, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); - return XATTR_SECURITY_PREFIX_LEN; -} - -static int squashfs_security_get(struct dentry *d, const char *name, - void *buffer, size_t size, int type) -{ - if (name[0] == '\0') - return -EINVAL; - - return squashfs_xattr_get(d_inode(d), SQUASHFS_XATTR_SECURITY, name, - buffer, size); -} - static const struct xattr_handler squashfs_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = squashfs_security_list, - .get = squashfs_security_get + .flags = SQUASHFS_XATTR_SECURITY, + .get = squashfs_xattr_handler_get }; static const struct xattr_handler *squashfs_xattr_handler(int type) diff --git a/fs/stat.c b/fs/stat.c index cccc1aab9a8b..d4a61d8dc021 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -367,8 +367,6 @@ static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf) INIT_STRUCT_STAT64_PADDING(tmp); #ifdef CONFIG_MIPS /* mips has weird padding, so we don't get 64 bits there */ - if (!new_valid_dev(stat->dev) || !new_valid_dev(stat->rdev)) - return -EOVERFLOW; tmp.st_dev = new_encode_dev(stat->dev); tmp.st_rdev = new_encode_dev(stat->rdev); #else diff --git a/fs/super.c b/fs/super.c index 7ea56de57d4b..1182af8fd5ff 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1012,10 +1012,8 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, blkdev_put(bdev, mode); down_write(&s->s_umount); } else { - char b[BDEVNAME_SIZE]; - s->s_mode = mode; - strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); + snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { diff --git a/fs/sync.c b/fs/sync.c index 4ec430ae2b0d..dd5d1711c7ac 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -348,7 +348,8 @@ SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, } if (flags & SYNC_FILE_RANGE_WRITE) { - ret = filemap_fdatawrite_range(mapping, offset, endbyte); + ret = __filemap_fdatawrite_range(mapping, offset, endbyte, + WB_SYNC_NONE); if (ret < 0) goto out_put; } diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index e1236594fffe..dc1358b5ec95 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -73,13 +73,26 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj, } if (grp->bin_attrs) { - for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) { + for (i = 0, bin_attr = grp->bin_attrs; *bin_attr; i++, bin_attr++) { + umode_t mode = (*bin_attr)->attr.mode; + if (update) kernfs_remove_by_name(parent, (*bin_attr)->attr.name); + if (grp->is_bin_visible) { + mode = grp->is_bin_visible(kobj, *bin_attr, i); + if (!mode) + continue; + } + + WARN(mode & ~(SYSFS_PREALLOC | 0664), + "Attribute %s: Invalid permissions 0%o\n", + (*bin_attr)->attr.name, mode); + + mode &= SYSFS_PREALLOC | 0664; error = sysfs_add_file_mode_ns(parent, &(*bin_attr)->attr, true, - (*bin_attr)->attr.mode, NULL); + mode, NULL); if (error) break; } diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 590ad9206e3f..07ac18c355e7 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -146,8 +146,7 @@ static inline void write3byte(struct sysv_sb_info *sbi, static const struct inode_operations sysv_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getattr = sysv_getattr, }; @@ -162,15 +161,9 @@ void sysv_set_inode(struct inode *inode, dev_t rdev) inode->i_fop = &sysv_dir_operations; inode->i_mapping->a_ops = &sysv_aops; } else if (S_ISLNK(inode->i_mode)) { - if (inode->i_blocks) { - inode->i_op = &sysv_symlink_inode_operations; - inode->i_mapping->a_ops = &sysv_aops; - } else { - inode->i_op = &simple_symlink_inode_operations; - inode->i_link = (char *)SYSV_I(inode)->i_data; - nd_terminate_link(inode->i_link, inode->i_size, - sizeof(SYSV_I(inode)->i_data) - 1); - } + inode->i_op = &sysv_symlink_inode_operations; + inode_nohighmem(inode); + inode->i_mapping->a_ops = &sysv_aops; } else init_special_inode(inode, inode->i_mode, rdev); } diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig index ba66d508006a..7ff7712f284e 100644 --- a/fs/ubifs/Kconfig +++ b/fs/ubifs/Kconfig @@ -35,3 +35,18 @@ config UBIFS_FS_ZLIB default y help Zlib compresses better than LZO but it is slower. Say 'Y' if unsure. + +config UBIFS_ATIME_SUPPORT + bool "Access time support" if UBIFS_FS + depends on UBIFS_FS + default n + help + Originally UBIFS did not support atime, because it looked like a bad idea due + increased flash wear. This option adds atime support and it is disabled by default + to preserve the old behavior. If you enable this option, UBIFS starts updating atime, + which means that file-system read operations will cause writes (inode atime + updates). This may affect file-system performance and increase flash device wear, + so be careful. How often atime is updated depends on the selected strategy: + strictatime is the "heavy", relatime is "lighter", etc. + + If unsure, say 'N' diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 4c46a9865fa7..595ca0debe11 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -2573,7 +2573,7 @@ int dbg_leb_write(struct ubifs_info *c, int lnum, const void *buf, { int err, failing; - if (c->dbg->pc_happened) + if (dbg_is_power_cut(c)) return -EROFS; failing = power_cut_emulated(c, lnum, 1); @@ -2595,7 +2595,7 @@ int dbg_leb_change(struct ubifs_info *c, int lnum, const void *buf, { int err; - if (c->dbg->pc_happened) + if (dbg_is_power_cut(c)) return -EROFS; if (power_cut_emulated(c, lnum, 1)) return -EROFS; @@ -2611,7 +2611,7 @@ int dbg_leb_unmap(struct ubifs_info *c, int lnum) { int err; - if (c->dbg->pc_happened) + if (dbg_is_power_cut(c)) return -EROFS; if (power_cut_emulated(c, lnum, 0)) return -EROFS; @@ -2627,7 +2627,7 @@ int dbg_leb_map(struct ubifs_info *c, int lnum) { int err; - if (c->dbg->pc_happened) + if (dbg_is_power_cut(c)) return -EROFS; if (power_cut_emulated(c, lnum, 0)) return -EROFS; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 5c27c66c224a..e49bd2808bf3 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -449,13 +449,14 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx) } out: + kfree(file->private_data); + file->private_data = NULL; + if (err != -ENOENT) { ubifs_err(c, "cannot find next direntry, error %d", err); return err; } - kfree(file->private_data); - file->private_data = NULL; /* 2 is a special value indicating that there are no more direntries */ ctx->pos = 2; return 0; @@ -787,9 +788,6 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, dbg_gen("dent '%pd' in dir ino %lu", dentry, dir->i_ino); - if (!new_valid_dev(rdev)) - return -EINVAL; - if (S_ISBLK(mode) || S_ISCHR(mode)) { dev = kmalloc(sizeof(union ubifs_dev_desc), GFP_NOFS); if (!dev) @@ -1188,6 +1186,9 @@ const struct inode_operations ubifs_dir_inode_operations = { .getxattr = ubifs_getxattr, .listxattr = ubifs_listxattr, .removexattr = ubifs_removexattr, +#ifdef CONFIG_UBIFS_ATIME_SUPPORT + .update_time = ubifs_update_time, +#endif }; const struct file_operations ubifs_dir_operations = { diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index a3dfe2ae79f2..eff62801acbf 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1354,6 +1354,47 @@ static inline int mctime_update_needed(const struct inode *inode, return 0; } +#ifdef CONFIG_UBIFS_ATIME_SUPPORT +/** + * ubifs_update_time - update time of inode. + * @inode: inode to update + * + * This function updates time of the inode. + */ +int ubifs_update_time(struct inode *inode, struct timespec *time, + int flags) +{ + struct ubifs_inode *ui = ubifs_inode(inode); + struct ubifs_info *c = inode->i_sb->s_fs_info; + struct ubifs_budget_req req = { .dirtied_ino = 1, + .dirtied_ino_d = ALIGN(ui->data_len, 8) }; + int iflags = I_DIRTY_TIME; + int err, release; + + err = ubifs_budget_space(c, &req); + if (err) + return err; + + mutex_lock(&ui->ui_mutex); + if (flags & S_ATIME) + inode->i_atime = *time; + if (flags & S_CTIME) + inode->i_ctime = *time; + if (flags & S_MTIME) + inode->i_mtime = *time; + + if (!(inode->i_sb->s_flags & MS_LAZYTIME)) + iflags |= I_DIRTY_SYNC; + + release = ui->dirty; + __mark_inode_dirty(inode, iflags); + mutex_unlock(&ui->ui_mutex); + if (release) + ubifs_release_budget(c, &req); + return 0; +} +#endif + /** * update_ctime - update mtime and ctime of an inode. * @inode: inode to update @@ -1537,6 +1578,9 @@ static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma) if (err) return err; vma->vm_ops = &ubifs_file_vm_ops; +#ifdef CONFIG_UBIFS_ATIME_SUPPORT + file_accessed(file); +#endif return 0; } @@ -1557,17 +1601,23 @@ const struct inode_operations ubifs_file_inode_operations = { .getxattr = ubifs_getxattr, .listxattr = ubifs_listxattr, .removexattr = ubifs_removexattr, +#ifdef CONFIG_UBIFS_ATIME_SUPPORT + .update_time = ubifs_update_time, +#endif }; const struct inode_operations ubifs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = ubifs_setattr, .getattr = ubifs_getattr, .setxattr = ubifs_setxattr, .getxattr = ubifs_getxattr, .listxattr = ubifs_listxattr, .removexattr = ubifs_removexattr, +#ifdef CONFIG_UBIFS_ATIME_SUPPORT + .update_time = ubifs_update_time, +#endif }; const struct file_operations ubifs_file_operations = { diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h index 92a8491a8f8c..c0a95e393347 100644 --- a/fs/ubifs/key.h +++ b/fs/ubifs/key.h @@ -34,6 +34,12 @@ * node. We use "r5" hash borrowed from reiserfs. */ +/* + * Lot's of the key helpers require a struct ubifs_info *c as the first parameter. + * But we are not using it at all currently. That's designed for future extensions of + * different c->key_format. But right now, there is only one key type, UBIFS_SIMPLE_KEY_FMT. + */ + #ifndef __UBIFS_KEY_H__ #define __UBIFS_KEY_H__ diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c index dc9f27e9d61b..9a517109da0f 100644 --- a/fs/ubifs/lpt.c +++ b/fs/ubifs/lpt.c @@ -1498,11 +1498,10 @@ static struct ubifs_nnode *dirty_cow_nnode(struct ubifs_info *c, } /* nnode is being committed, so copy it */ - n = kmalloc(sizeof(struct ubifs_nnode), GFP_NOFS); + n = kmemdup(nnode, sizeof(struct ubifs_nnode), GFP_NOFS); if (unlikely(!n)) return ERR_PTR(-ENOMEM); - memcpy(n, nnode, sizeof(struct ubifs_nnode)); n->cnext = NULL; __set_bit(DIRTY_CNODE, &n->flags); __clear_bit(COW_CNODE, &n->flags); @@ -1549,11 +1548,10 @@ static struct ubifs_pnode *dirty_cow_pnode(struct ubifs_info *c, } /* pnode is being committed, so copy it */ - p = kmalloc(sizeof(struct ubifs_pnode), GFP_NOFS); + p = kmemdup(pnode, sizeof(struct ubifs_pnode), GFP_NOFS); if (unlikely(!p)) return ERR_PTR(-ENOMEM); - memcpy(p, pnode, sizeof(struct ubifs_pnode)); p->cnext = NULL; __set_bit(DIRTY_CNODE, &p->flags); __clear_bit(COW_CNODE, &p->flags); diff --git a/fs/ubifs/misc.h b/fs/ubifs/misc.h index ee7cb5ebb6e8..8ece6ca58c0b 100644 --- a/fs/ubifs/misc.h +++ b/fs/ubifs/misc.h @@ -155,13 +155,8 @@ static inline int ubifs_wbuf_sync(struct ubifs_wbuf *wbuf) */ static inline int ubifs_encode_dev(union ubifs_dev_desc *dev, dev_t rdev) { - if (new_valid_dev(rdev)) { - dev->new = cpu_to_le32(new_encode_dev(rdev)); - return sizeof(dev->new); - } else { - dev->huge = cpu_to_le64(huge_encode_dev(rdev)); - return sizeof(dev->huge); - } + dev->new = cpu_to_le32(new_encode_dev(rdev)); + return sizeof(dev->new); } /** diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c index 695fc71d5244..586d59347fff 100644 --- a/fs/ubifs/recovery.c +++ b/fs/ubifs/recovery.c @@ -789,7 +789,7 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum, corrupted_rescan: /* Re-scan the corrupted data with verbose messages */ ubifs_err(c, "corruption %d", ret); - ubifs_scan_a_node(c, buf, len, lnum, offs, 1); + ubifs_scan_a_node(c, buf, len, lnum, offs, 0); corrupted: ubifs_scanned_corruption(c, lnum, offs, buf); err = -EUCLEAN; @@ -1331,8 +1331,7 @@ void ubifs_destroy_size_tree(struct ubifs_info *c) struct size_entry *e, *n; rbtree_postorder_for_each_entry_safe(e, n, &c->size_tree, rb) { - if (e->inode) - iput(e->inode); + iput(e->inode); kfree(e); } @@ -1533,8 +1532,7 @@ int ubifs_recover_size(struct ubifs_info *c) err = fix_size_in_place(c, e); if (err) return err; - if (e->inode) - iput(e->inode); + iput(e->inode); } } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 9547a27868ad..1fd90c079537 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -128,7 +128,10 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum) if (err) goto out_ino; - inode->i_flags |= (S_NOCMTIME | S_NOATIME); + inode->i_flags |= S_NOCMTIME; +#ifndef CONFIG_UBIFS_ATIME_SUPPORT + inode->i_flags |= S_NOATIME; +#endif set_nlink(inode, le32_to_cpu(ino->nlink)); i_uid_write(inode, le32_to_cpu(ino->uid)); i_gid_write(inode, le32_to_cpu(ino->gid)); @@ -2037,7 +2040,6 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent) if (c->max_inode_sz > MAX_LFS_FILESIZE) sb->s_maxbytes = c->max_inode_sz = MAX_LFS_FILESIZE; sb->s_op = &ubifs_super_operations; - sb->s_xattr = ubifs_xattr_handlers; mutex_lock(&c->umount_mutex); err = mount_ubifs(c); @@ -2139,7 +2141,12 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, if (err) goto out_deact; /* We do not support atime */ - sb->s_flags |= MS_ACTIVE | MS_NOATIME; + sb->s_flags |= MS_ACTIVE; +#ifndef CONFIG_UBIFS_ATIME_SUPPORT + sb->s_flags |= MS_NOATIME; +#else + ubifs_msg(c, "full atime support is enabled."); +#endif } /* 'fill_super()' opens ubi again so we must close it here */ diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 957f5757f374..fa9a20cc60d6 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -198,11 +198,10 @@ static struct ubifs_znode *copy_znode(struct ubifs_info *c, { struct ubifs_znode *zn; - zn = kmalloc(c->max_znode_sz, GFP_NOFS); + zn = kmemdup(znode, c->max_znode_sz, GFP_NOFS); if (unlikely(!zn)) return ERR_PTR(-ENOMEM); - memcpy(zn, znode, c->max_znode_sz); zn->cnext = NULL; __set_bit(DIRTY_ZNODE, &zn->flags); __clear_bit(COW_ZNODE, &zn->flags); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index de759022f3d6..a5697de763f5 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -858,9 +858,9 @@ struct ubifs_compressor { * @mod_dent: non-zero if the operation removes or modifies an existing * directory entry * @new_ino: non-zero if the operation adds a new inode - * @new_ino_d: now much data newly created inode contains + * @new_ino_d: how much data newly created inode contains * @dirtied_ino: how many inodes the operation makes dirty - * @dirtied_ino_d: now much data dirtied inode contains + * @dirtied_ino_d: how much data dirtied inode contains * @idx_growth: how much the index will supposedly grow * @data_growth: how much new data the operation will supposedly add * @dd_growth: how much data that makes other data dirty the operation will @@ -1470,7 +1470,6 @@ extern spinlock_t ubifs_infos_lock; extern atomic_long_t ubifs_clean_zn_cnt; extern struct kmem_cache *ubifs_inode_slab; extern const struct super_operations ubifs_super_operations; -extern const struct xattr_handler *ubifs_xattr_handlers[]; extern const struct address_space_operations ubifs_file_address_operations; extern const struct file_operations ubifs_file_operations; extern const struct inode_operations ubifs_file_inode_operations; @@ -1746,6 +1745,9 @@ int ubifs_calc_dark(const struct ubifs_info *c, int spc); /* file.c */ int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync); int ubifs_setattr(struct dentry *dentry, struct iattr *attr); +#ifdef CONFIG_UBIFS_ATIME_SUPPORT +int ubifs_update_time(struct inode *inode, struct timespec *time, int flags); +#endif /* dir.c */ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir, diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index fd65b3f1923c..e53292d0c21b 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -200,6 +200,7 @@ static int change_xattr(struct ubifs_info *c, struct inode *host, int err; struct ubifs_inode *host_ui = ubifs_inode(host); struct ubifs_inode *ui = ubifs_inode(inode); + void *buf = NULL; struct ubifs_budget_req req = { .dirtied_ino = 2, .dirtied_ino_d = ALIGN(size, 8) + ALIGN(host_ui->data_len, 8) }; @@ -208,14 +209,17 @@ static int change_xattr(struct ubifs_info *c, struct inode *host, if (err) return err; - kfree(ui->data); - ui->data = kmemdup(value, size, GFP_NOFS); - if (!ui->data) { + buf = kmemdup(value, size, GFP_NOFS); + if (!buf) { err = -ENOMEM; goto out_free; } + mutex_lock(&ui->ui_mutex); + kfree(ui->data); + ui->data = buf; inode->i_size = ui->ui_size = size; ui->data_len = size; + mutex_unlock(&ui->ui_mutex); mutex_lock(&host_ui->ui_mutex); host->i_ctime = ubifs_current_time(host); @@ -263,7 +267,7 @@ static int check_namespace(const struct qstr *nm) if (!strncmp(nm->name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) { - if (nm->name[sizeof(XATTR_TRUSTED_PREFIX) - 1] == '\0') + if (nm->name[XATTR_TRUSTED_PREFIX_LEN] == '\0') return -EINVAL; type = TRUSTED_XATTR; } else if (!strncmp(nm->name, XATTR_USER_PREFIX, @@ -273,7 +277,7 @@ static int check_namespace(const struct qstr *nm) type = USER_XATTR; } else if (!strncmp(nm->name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { - if (nm->name[sizeof(XATTR_SECURITY_PREFIX) - 1] == '\0') + if (nm->name[XATTR_SECURITY_PREFIX_LEN] == '\0') return -EINVAL; type = SECURITY_XATTR; } else @@ -409,6 +413,7 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf, ubifs_assert(inode->i_size == ui->data_len); ubifs_assert(ubifs_inode(host)->xattr_size > ui->data_len); + mutex_lock(&ui->ui_mutex); if (buf) { /* If @buf is %NULL we are supposed to return the length */ if (ui->data_len > size) { @@ -423,6 +428,7 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf, err = ui->data_len; out_iput: + mutex_unlock(&ui->ui_mutex); iput(inode); out_unlock: kfree(xent); @@ -582,46 +588,6 @@ out_free: return err; } -static size_t security_listxattr(struct dentry *d, char *list, size_t list_size, - const char *name, size_t name_len, int flags) -{ - const int prefix_len = XATTR_SECURITY_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_SECURITY_PREFIX, prefix_len); - memcpy(list + prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - - return total_len; -} - -static int security_getxattr(struct dentry *d, const char *name, void *buffer, - size_t size, int flags) -{ - return ubifs_getxattr(d, name, buffer, size); -} - -static int security_setxattr(struct dentry *d, const char *name, - const void *value, size_t size, int flags, - int handler_flags) -{ - return ubifs_setxattr(d, name, value, size, flags); -} - -static const struct xattr_handler ubifs_xattr_security_handler = { - .prefix = XATTR_SECURITY_PREFIX, - .list = security_listxattr, - .get = security_getxattr, - .set = security_setxattr, -}; - -const struct xattr_handler *ubifs_xattr_handlers[] = { - &ubifs_xattr_security_handler, - NULL, -}; - static int init_xattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) { diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 8d0b3ade0ff0..055746350d16 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1540,7 +1540,8 @@ reread: break; case ICBTAG_FILE_TYPE_SYMLINK: inode->i_data.a_ops = &udf_symlink_aops; - inode->i_op = &udf_symlink_inode_operations; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mode = S_IFLNK | S_IRWXUGO; break; case ICBTAG_FILE_TYPE_MAIN: diff --git a/fs/udf/namei.c b/fs/udf/namei.c index c97b5a8d1e24..42eafb91f7ff 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -921,7 +921,8 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry, } inode->i_data.a_ops = &udf_symlink_aops; - inode->i_op = &udf_symlink_inode_operations; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { struct kernel_lb_addr eloc; @@ -1344,8 +1345,3 @@ const struct inode_operations udf_dir_inode_operations = { .rename = udf_rename, .tmpfile = udf_tmpfile, }; -const struct inode_operations udf_symlink_inode_operations = { - .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, -}; diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index 862535b3ba58..8d619773056b 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -107,7 +107,7 @@ static int udf_symlink_filler(struct file *file, struct page *page) struct buffer_head *bh = NULL; unsigned char *symlink; int err; - unsigned char *p = kmap(page); + unsigned char *p = page_address(page); struct udf_inode_info *iinfo; uint32_t pos; @@ -141,7 +141,6 @@ static int udf_symlink_filler(struct file *file, struct page *page) up_read(&iinfo->i_data_sem); SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; @@ -149,7 +148,6 @@ out_unlock_inode: up_read(&iinfo->i_data_sem); SetPageError(page); out_unmap: - kunmap(page); unlock_page(page); return err; } diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index 47bb3f5ca360..ce169b49429d 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -85,7 +85,6 @@ extern const struct inode_operations udf_dir_inode_operations; extern const struct file_operations udf_dir_operations; extern const struct inode_operations udf_file_inode_operations; extern const struct file_operations udf_file_operations; -extern const struct inode_operations udf_symlink_inode_operations; extern const struct address_space_operations udf_aops; extern const struct address_space_operations udf_adinicb_aops; extern const struct address_space_operations udf_symlink_aops; diff --git a/fs/ufs/Makefile b/fs/ufs/Makefile index 392db25c0b56..ec4a6b49fa13 100644 --- a/fs/ufs/Makefile +++ b/fs/ufs/Makefile @@ -5,5 +5,5 @@ obj-$(CONFIG_UFS_FS) += ufs.o ufs-objs := balloc.o cylinder.o dir.o file.o ialloc.o inode.o \ - namei.o super.o symlink.o util.o + namei.o super.o util.o ccflags-$(CONFIG_UFS_DEBUG) += -DDEBUG diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index a064cf44b143..d897e169ab9c 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -528,11 +528,12 @@ static void ufs_set_inode_ops(struct inode *inode) inode->i_mapping->a_ops = &ufs_aops; } else if (S_ISLNK(inode->i_mode)) { if (!inode->i_blocks) { - inode->i_op = &ufs_fast_symlink_inode_operations; inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink; + inode->i_op = &simple_symlink_inode_operations; } else { - inode->i_op = &ufs_symlink_inode_operations; inode->i_mapping->a_ops = &ufs_aops; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); } } else init_special_inode(inode, inode->i_mode, diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index 47966554317c..acf4a3b61b81 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -123,14 +123,15 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry, if (l > UFS_SB(sb)->s_uspi->s_maxsymlinklen) { /* slow symlink */ - inode->i_op = &ufs_symlink_inode_operations; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &ufs_aops; err = page_symlink(inode, symname, l); if (err) goto out_fail; } else { /* fast symlink */ - inode->i_op = &ufs_fast_symlink_inode_operations; + inode->i_op = &simple_symlink_inode_operations; inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink; memcpy(inode->i_link, symname, l); inode->i_size = l-1; diff --git a/fs/ufs/symlink.c b/fs/ufs/symlink.c deleted file mode 100644 index 874480bb43e9..000000000000 --- a/fs/ufs/symlink.c +++ /dev/null @@ -1,42 +0,0 @@ -/* - * linux/fs/ufs/symlink.c - * - * Only fast symlinks left here - the rest is done by generic code. AV, 1999 - * - * Copyright (C) 1998 - * Daniel Pirkl <daniel.pirkl@emai.cz> - * Charles University, Faculty of Mathematics and Physics - * - * from - * - * linux/fs/ext2/symlink.c - * - * Copyright (C) 1992, 1993, 1994, 1995 - * Remy Card (card@masi.ibp.fr) - * Laboratoire MASI - Institut Blaise Pascal - * Universite Pierre et Marie Curie (Paris VI) - * - * from - * - * linux/fs/minix/symlink.c - * - * Copyright (C) 1991, 1992 Linus Torvalds - * - * ext2 symlink handling code - */ - -#include "ufs_fs.h" -#include "ufs.h" - -const struct inode_operations ufs_fast_symlink_inode_operations = { - .readlink = generic_readlink, - .follow_link = simple_follow_link, - .setattr = ufs_setattr, -}; - -const struct inode_operations ufs_symlink_inode_operations = { - .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, - .setattr = ufs_setattr, -}; diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index 7da4aca868c0..c87f4c3fa9dd 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -136,10 +136,6 @@ extern __printf(3, 4) void ufs_panic(struct super_block *, const char *, const char *, ...); void ufs_mark_sb_dirty(struct super_block *sb); -/* symlink.c */ -extern const struct inode_operations ufs_fast_symlink_inode_operations; -extern const struct inode_operations ufs_symlink_inode_operations; - static inline struct ufs_sb_info *UFS_SB(struct super_block *sb) { return sb->s_fs_info; diff --git a/fs/xattr.c b/fs/xattr.c index 072fee1258dd..d5dd6c8b82a7 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -208,25 +208,6 @@ vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, return error; } -/* Compare an extended attribute value with the given value */ -int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name, - const char *value, size_t size, gfp_t flags) -{ - char *xattr_value = NULL; - int rc; - - rc = vfs_getxattr_alloc(dentry, xattr_name, &xattr_value, 0, flags); - if (rc < 0) - return rc; - - if ((rc != size) || (memcmp(xattr_value, value, rc) != 0)) - rc = -EINVAL; - else - rc = 0; - kfree(xattr_value); - return rc; -} - ssize_t vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) { @@ -324,7 +305,6 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value, { int error; void *kvalue = NULL; - void *vvalue = NULL; /* If non-NULL, we used vmalloc() */ char kname[XATTR_NAME_MAX + 1]; if (flags & ~(XATTR_CREATE|XATTR_REPLACE)) @@ -341,10 +321,9 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value, return -E2BIG; kvalue = kmalloc(size, GFP_KERNEL | __GFP_NOWARN); if (!kvalue) { - vvalue = vmalloc(size); - if (!vvalue) + kvalue = vmalloc(size); + if (!kvalue) return -ENOMEM; - kvalue = vvalue; } if (copy_from_user(kvalue, value, size)) { error = -EFAULT; @@ -357,10 +336,8 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value, error = vfs_setxattr(d, kname, kvalue, size, flags); out: - if (vvalue) - vfree(vvalue); - else - kfree(kvalue); + kvfree(kvalue); + return error; } @@ -428,7 +405,6 @@ getxattr(struct dentry *d, const char __user *name, void __user *value, { ssize_t error; void *kvalue = NULL; - void *vvalue = NULL; char kname[XATTR_NAME_MAX + 1]; error = strncpy_from_user(kname, name, sizeof(kname)); @@ -442,10 +418,9 @@ getxattr(struct dentry *d, const char __user *name, void __user *value, size = XATTR_SIZE_MAX; kvalue = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); if (!kvalue) { - vvalue = vmalloc(size); - if (!vvalue) + kvalue = vmalloc(size); + if (!kvalue) return -ENOMEM; - kvalue = vvalue; } } @@ -461,10 +436,9 @@ getxattr(struct dentry *d, const char __user *name, void __user *value, than XATTR_SIZE_MAX bytes. Not possible. */ error = -E2BIG; } - if (vvalue) - vfree(vvalue); - else - kfree(kvalue); + + kvfree(kvalue); + return error; } @@ -521,17 +495,15 @@ listxattr(struct dentry *d, char __user *list, size_t size) { ssize_t error; char *klist = NULL; - char *vlist = NULL; /* If non-NULL, we used vmalloc() */ if (size) { if (size > XATTR_LIST_MAX) size = XATTR_LIST_MAX; klist = kmalloc(size, __GFP_NOWARN | GFP_KERNEL); if (!klist) { - vlist = vmalloc(size); - if (!vlist) + klist = vmalloc(size); + if (!klist) return -ENOMEM; - klist = vlist; } } @@ -544,10 +516,9 @@ listxattr(struct dentry *d, char __user *list, size_t size) than XATTR_LIST_MAX bytes. Not possible. */ error = -E2BIG; } - if (vlist) - vfree(vlist); - else - kfree(klist); + + kvfree(klist); + return error; } @@ -700,13 +671,20 @@ xattr_resolve_name(const struct xattr_handler **handlers, const char **name) return NULL; for_each_xattr_handler(handlers, handler) { - const char *n = strcmp_prefix(*name, handler->prefix); + const char *n; + + n = strcmp_prefix(*name, xattr_prefix(handler)); if (n) { + if (!handler->prefix ^ !*n) { + if (*n) + continue; + return ERR_PTR(-EINVAL); + } *name = n; - break; + return handler; } } - return handler; + return ERR_PTR(-EOPNOTSUPP); } /* @@ -718,9 +696,9 @@ generic_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t s const struct xattr_handler *handler; handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name); - if (!handler) - return -EOPNOTSUPP; - return handler->get(dentry, name, buffer, size, handler->flags); + if (IS_ERR(handler)) + return PTR_ERR(handler); + return handler->get(handler, dentry, name, buffer, size); } /* @@ -735,19 +713,25 @@ generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) if (!buffer) { for_each_xattr_handler(handlers, handler) { - size += handler->list(dentry, NULL, 0, NULL, 0, - handler->flags); + if (!handler->name || + (handler->list && !handler->list(dentry))) + continue; + size += strlen(handler->name) + 1; } } else { char *buf = buffer; + size_t len; for_each_xattr_handler(handlers, handler) { - size = handler->list(dentry, buf, buffer_size, - NULL, 0, handler->flags); - if (size > buffer_size) + if (!handler->name || + (handler->list && !handler->list(dentry))) + continue; + len = strlen(handler->name); + if (len + 1 > buffer_size) return -ERANGE; - buf += size; - buffer_size -= size; + memcpy(buf, handler->name, len + 1); + buf += len + 1; + buffer_size -= len + 1; } size = buf - buffer; } @@ -765,9 +749,9 @@ generic_setxattr(struct dentry *dentry, const char *name, const void *value, siz if (size == 0) value = ""; /* empty EA, do not remove */ handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name); - if (!handler) - return -EOPNOTSUPP; - return handler->set(dentry, name, value, size, flags, handler->flags); + if (IS_ERR(handler)) + return PTR_ERR(handler); + return handler->set(handler, dentry, name, value, size, flags); } /* @@ -780,10 +764,9 @@ generic_removexattr(struct dentry *dentry, const char *name) const struct xattr_handler *handler; handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name); - if (!handler) - return -EOPNOTSUPP; - return handler->set(dentry, name, NULL, 0, - XATTR_REPLACE, handler->flags); + if (IS_ERR(handler)) + return PTR_ERR(handler); + return handler->set(handler, dentry, name, NULL, 0, XATTR_REPLACE); } EXPORT_SYMBOL(generic_getxattr); @@ -791,6 +774,30 @@ EXPORT_SYMBOL(generic_listxattr); EXPORT_SYMBOL(generic_setxattr); EXPORT_SYMBOL(generic_removexattr); +/** + * xattr_full_name - Compute full attribute name from suffix + * + * @handler: handler of the xattr_handler operation + * @name: name passed to the xattr_handler operation + * + * The get and set xattr handler operations are called with the remainder of + * the attribute name after skipping the handler's prefix: for example, "foo" + * is passed to the get operation of a handler with prefix "user." to get + * attribute "user.foo". The full name is still "there" in the name though. + * + * Note: the list xattr handler operation when called from the vfs is passed a + * NULL name; some file systems use this operation internally, with varying + * semantics. + */ +const char *xattr_full_name(const struct xattr_handler *handler, + const char *name) +{ + size_t prefix_len = strlen(xattr_prefix(handler)); + + return name - prefix_len; +} +EXPORT_SYMBOL(xattr_full_name); + /* * Allocate new xattr and copy in the value; but leave the name to callers. */ @@ -840,8 +847,22 @@ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, return ret; } -static int __simple_xattr_set(struct simple_xattrs *xattrs, const char *name, - const void *value, size_t size, int flags) +/** + * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems + * @xattrs: target simple_xattr list + * @name: name of the extended attribute + * @value: value of the xattr. If %NULL, will remove the attribute. + * @size: size of the new xattr + * @flags: %XATTR_{CREATE|REPLACE} + * + * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails + * with -EEXIST. If %XATTR_REPLACE is set, the xattr should exist; + * otherwise, fails with -ENODATA. + * + * Returns 0 on success, -errno on failure. + */ +int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, + const void *value, size_t size, int flags) { struct simple_xattr *xattr; struct simple_xattr *new_xattr = NULL; @@ -891,73 +912,64 @@ out: } -/** - * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems - * @xattrs: target simple_xattr list - * @name: name of the new extended attribute - * @value: value of the new xattr. If %NULL, will remove the attribute - * @size: size of the new xattr - * @flags: %XATTR_{CREATE|REPLACE} - * - * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails - * with -EEXIST. If %XATTR_REPLACE is set, the xattr should exist; - * otherwise, fails with -ENODATA. - * - * Returns 0 on success, -errno on failure. - */ -int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, - const void *value, size_t size, int flags) -{ - if (size == 0) - value = ""; /* empty EA, do not remove */ - return __simple_xattr_set(xattrs, name, value, size, flags); -} - -/* - * xattr REMOVE operation for in-memory/pseudo filesystems - */ -int simple_xattr_remove(struct simple_xattrs *xattrs, const char *name) +static bool xattr_is_trusted(const char *name) { - return __simple_xattr_set(xattrs, name, NULL, 0, XATTR_REPLACE); + return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } -static bool xattr_is_trusted(const char *name) +static int xattr_list_one(char **buffer, ssize_t *remaining_size, + const char *name) { - return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); + size_t len = strlen(name) + 1; + if (*buffer) { + if (*remaining_size < len) + return -ERANGE; + memcpy(*buffer, name, len); + *buffer += len; + } + *remaining_size -= len; + return 0; } /* * xattr LIST operation for in-memory/pseudo filesystems */ -ssize_t simple_xattr_list(struct simple_xattrs *xattrs, char *buffer, - size_t size) +ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, + char *buffer, size_t size) { bool trusted = capable(CAP_SYS_ADMIN); struct simple_xattr *xattr; - size_t used = 0; + ssize_t remaining_size = size; + int err; + +#ifdef CONFIG_FS_POSIX_ACL + if (inode->i_acl) { + err = xattr_list_one(&buffer, &remaining_size, + XATTR_NAME_POSIX_ACL_ACCESS); + if (err) + return err; + } + if (inode->i_default_acl) { + err = xattr_list_one(&buffer, &remaining_size, + XATTR_NAME_POSIX_ACL_DEFAULT); + if (err) + return err; + } +#endif spin_lock(&xattrs->lock); list_for_each_entry(xattr, &xattrs->head, list) { - size_t len; - /* skip "trusted." attributes for unprivileged callers */ if (!trusted && xattr_is_trusted(xattr->name)) continue; - len = strlen(xattr->name) + 1; - used += len; - if (buffer) { - if (size < used) { - used = -ERANGE; - break; - } - memcpy(buffer, xattr->name, len); - buffer += len; - } + err = xattr_list_one(&buffer, &remaining_size, xattr->name); + if (err) + return err; } spin_unlock(&xattrs->lock); - return used; + return size - remaining_size; } /* diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index a096841bd06c..f64639176670 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -84,6 +84,7 @@ xfs-y += xfs_aops.o \ xfs_message.o \ xfs_mount.o \ xfs_mru_cache.o \ + xfs_stats.o \ xfs_super.o \ xfs_symlink.o \ xfs_sysfs.o \ @@ -118,7 +119,6 @@ xfs-$(CONFIG_XFS_QUOTA) += xfs_dquot.o \ xfs-$(CONFIG_XFS_RT) += xfs_rtalloc.o xfs-$(CONFIG_XFS_POSIX_ACL) += xfs_acl.o -xfs-$(CONFIG_PROC_FS) += xfs_stats.o xfs-$(CONFIG_SYSCTL) += xfs_sysctl.o xfs-$(CONFIG_COMPAT) += xfs_ioctl32.o xfs-$(CONFIG_NFSD_PNFS) += xfs_pnfs.o diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index a7a3a63bb360..686ba6fb20dd 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -55,8 +55,9 @@ kmem_alloc(size_t size, xfs_km_flags_t flags) return ptr; if (!(++retries % 100)) xfs_err(NULL, - "possible memory allocation deadlock in %s (mode:0x%x)", - __func__, lflags); + "%s(%u) possible memory allocation deadlock size %u in %s (mode:0x%x)", + current->comm, current->pid, + (unsigned int)size, __func__, lflags); congestion_wait(BLK_RW_ASYNC, HZ/50); } while (1); } @@ -120,8 +121,9 @@ kmem_zone_alloc(kmem_zone_t *zone, xfs_km_flags_t flags) return ptr; if (!(++retries % 100)) xfs_err(NULL, - "possible memory allocation deadlock in %s (mode:0x%x)", - __func__, lflags); + "%s(%u) possible memory allocation deadlock in %s (mode:0x%x)", + current->comm, current->pid, + __func__, lflags); congestion_wait(BLK_RW_ASYNC, HZ/50); } while (1); } diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index ffad7f20342f..a708e38b494c 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -482,7 +482,9 @@ xfs_agfl_verify( be32_to_cpu(agfl->agfl_bno[i]) >= mp->m_sb.sb_agblocks) return false; } - return true; + + return xfs_log_check_lsn(mp, + be64_to_cpu(XFS_BUF_TO_AGFL(bp)->agfl_lsn)); } static void @@ -533,6 +535,7 @@ xfs_agfl_write_verify( } const struct xfs_buf_ops xfs_agfl_buf_ops = { + .name = "xfs_agfl", .verify_read = xfs_agfl_read_verify, .verify_write = xfs_agfl_write_verify, }; @@ -651,8 +654,8 @@ xfs_alloc_ag_vextent( -((long)(args->len))); } - XFS_STATS_INC(xs_allocx); - XFS_STATS_ADD(xs_allocb, args->len); + XFS_STATS_INC(args->mp, xs_allocx); + XFS_STATS_ADD(args->mp, xs_allocb, args->len); return error; } @@ -1808,8 +1811,8 @@ xfs_free_ag_extent( if (!isfl) xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, (long)len); - XFS_STATS_INC(xs_freex); - XFS_STATS_ADD(xs_freeb, len); + XFS_STATS_INC(mp, xs_freex); + XFS_STATS_ADD(mp, xs_freeb, len); trace_xfs_free_extent(mp, agno, bno, len, isfl, haveleft, haveright); @@ -1924,7 +1927,7 @@ xfs_alloc_space_available( * Decide whether to use this allocation group for this allocation. * If so, fix up the btree freelist's size. */ -STATIC int /* error */ +int /* error */ xfs_alloc_fix_freelist( struct xfs_alloc_arg *args, /* allocation argument structure */ int flags) /* XFS_ALLOC_FLAG_... */ @@ -2259,9 +2262,13 @@ xfs_agf_verify( { struct xfs_agf *agf = XFS_BUF_TO_AGF(bp); - if (xfs_sb_version_hascrc(&mp->m_sb) && - !uuid_equal(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid)) + if (xfs_sb_version_hascrc(&mp->m_sb)) { + if (!uuid_equal(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid)) + return false; + if (!xfs_log_check_lsn(mp, + be64_to_cpu(XFS_BUF_TO_AGF(bp)->agf_lsn))) return false; + } if (!(agf->agf_magicnum == cpu_to_be32(XFS_AGF_MAGIC) && XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) && @@ -2333,6 +2340,7 @@ xfs_agf_write_verify( } const struct xfs_buf_ops xfs_agf_buf_ops = { + .name = "xfs_agf", .verify_read = xfs_agf_read_verify, .verify_write = xfs_agf_write_verify, }; @@ -2503,7 +2511,7 @@ xfs_alloc_vextent( * Try near allocation first, then anywhere-in-ag after * the first a.g. fails. */ - if ((args->userdata == XFS_ALLOC_INITIAL_USER_DATA) && + if ((args->userdata & XFS_ALLOC_INITIAL_USER_DATA) && (mp->m_flags & XFS_MOUNT_32BITINODES)) { args->fsbno = XFS_AGB_TO_FSB(mp, ((mp->m_agfrotor / rotorstep) % @@ -2634,6 +2642,14 @@ xfs_alloc_vextent( XFS_AG_CHECK_DADDR(mp, XFS_FSB_TO_DADDR(mp, args->fsbno), args->len); #endif + + /* Zero the extent if we were asked to do so */ + if (args->userdata & XFS_ALLOC_USERDATA_ZERO) { + error = xfs_zero_extent(args->ip, args->fsbno, args->len); + if (error) + goto error0; + } + } xfs_perag_put(args->pag); return 0; diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index ca1c8168373a..135eb3d24db7 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -101,6 +101,7 @@ typedef struct xfs_alloc_arg { struct xfs_mount *mp; /* file system mount point */ struct xfs_buf *agbp; /* buffer for a.g. freelist header */ struct xfs_perag *pag; /* per-ag struct for this agno */ + struct xfs_inode *ip; /* for userdata zeroing method */ xfs_fsblock_t fsbno; /* file system block number */ xfs_agnumber_t agno; /* allocation group number */ xfs_agblock_t agbno; /* allocation group-relative block # */ @@ -120,15 +121,16 @@ typedef struct xfs_alloc_arg { char wasdel; /* set if allocation was prev delayed */ char wasfromfl; /* set if allocation is from freelist */ char isfl; /* set if is freelist blocks - !acctg */ - char userdata; /* set if this is user data */ + char userdata; /* mask defining userdata treatment */ xfs_fsblock_t firstblock; /* io first block allocated */ } xfs_alloc_arg_t; /* * Defines for userdata */ -#define XFS_ALLOC_USERDATA 1 /* allocation is for user data*/ -#define XFS_ALLOC_INITIAL_USER_DATA 2 /* special case start of file */ +#define XFS_ALLOC_USERDATA (1 << 0)/* allocation is for user data*/ +#define XFS_ALLOC_INITIAL_USER_DATA (1 << 1)/* special case start of file */ +#define XFS_ALLOC_USERDATA_ZERO (1 << 2)/* zero extent on allocation */ xfs_extlen_t xfs_alloc_longest_free_extent(struct xfs_mount *mp, struct xfs_perag *pag, xfs_extlen_t need); @@ -233,5 +235,6 @@ xfs_alloc_get_rec( int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, int flags, struct xfs_buf **bpp); +int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags); #endif /* __XFS_ALLOC_H__ */ diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c index 90de071dd4c2..444626ddbd1b 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.c +++ b/fs/xfs/libxfs/xfs_alloc_btree.c @@ -293,14 +293,7 @@ xfs_allocbt_verify( level = be16_to_cpu(block->bb_level); switch (block->bb_magic) { case cpu_to_be32(XFS_ABTB_CRC_MAGIC): - if (!xfs_sb_version_hascrc(&mp->m_sb)) - return false; - if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid)) - return false; - if (block->bb_u.s.bb_blkno != cpu_to_be64(bp->b_bn)) - return false; - if (pag && - be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno) + if (!xfs_btree_sblock_v5hdr_verify(bp)) return false; /* fall through */ case cpu_to_be32(XFS_ABTB_MAGIC): @@ -311,14 +304,7 @@ xfs_allocbt_verify( return false; break; case cpu_to_be32(XFS_ABTC_CRC_MAGIC): - if (!xfs_sb_version_hascrc(&mp->m_sb)) - return false; - if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid)) - return false; - if (block->bb_u.s.bb_blkno != cpu_to_be64(bp->b_bn)) - return false; - if (pag && - be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno) + if (!xfs_btree_sblock_v5hdr_verify(bp)) return false; /* fall through */ case cpu_to_be32(XFS_ABTC_MAGIC): @@ -332,21 +318,7 @@ xfs_allocbt_verify( return false; } - /* numrecs verification */ - if (be16_to_cpu(block->bb_numrecs) > mp->m_alloc_mxr[level != 0]) - return false; - - /* sibling pointer verification */ - if (!block->bb_u.s.bb_leftsib || - (be32_to_cpu(block->bb_u.s.bb_leftsib) >= mp->m_sb.sb_agblocks && - block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK))) - return false; - if (!block->bb_u.s.bb_rightsib || - (be32_to_cpu(block->bb_u.s.bb_rightsib) >= mp->m_sb.sb_agblocks && - block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK))) - return false; - - return true; + return xfs_btree_sblock_verify(bp, mp->m_alloc_mxr[level != 0]); } static void @@ -379,6 +351,7 @@ xfs_allocbt_write_verify( } const struct xfs_buf_ops xfs_allocbt_buf_ops = { + .name = "xfs_allocbt", .verify_read = xfs_allocbt_read_verify, .verify_write = xfs_allocbt_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index ff065578969f..fa3b948ef9c2 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -125,7 +125,7 @@ xfs_attr_get( uint lock_mode; int error; - XFS_STATS_INC(xs_attr_get); + XFS_STATS_INC(ip->i_mount, xs_attr_get); if (XFS_FORCED_SHUTDOWN(ip->i_mount)) return -EIO; @@ -207,9 +207,9 @@ xfs_attr_set( struct xfs_trans_res tres; xfs_fsblock_t firstblock; int rsvd = (flags & ATTR_ROOT) != 0; - int error, err2, committed, local; + int error, err2, local; - XFS_STATS_INC(xs_attr_set); + XFS_STATS_INC(mp, xs_attr_set); if (XFS_FORCED_SHUTDOWN(dp->i_mount)) return -EIO; @@ -334,25 +334,15 @@ xfs_attr_set( */ xfs_bmap_init(args.flist, args.firstblock); error = xfs_attr_shortform_to_leaf(&args); - if (!error) { - error = xfs_bmap_finish(&args.trans, args.flist, - &committed); - } + if (!error) + error = xfs_bmap_finish(&args.trans, args.flist, dp); if (error) { - ASSERT(committed); args.trans = NULL; xfs_bmap_cancel(&flist); goto out; } /* - * bmap_finish() may have committed the last trans and started - * a new one. We need the inode to be in all transactions. - */ - if (committed) - xfs_trans_ijoin(args.trans, dp, 0); - - /* * Commit the leaf transformation. We'll need another (linked) * transaction to add the new attribute to the leaf. */ @@ -412,7 +402,7 @@ xfs_attr_remove( xfs_fsblock_t firstblock; int error; - XFS_STATS_INC(xs_attr_remove); + XFS_STATS_INC(mp, xs_attr_remove); if (XFS_FORCED_SHUTDOWN(dp->i_mount)) return -EIO; @@ -568,7 +558,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args) { xfs_inode_t *dp; struct xfs_buf *bp; - int retval, error, committed, forkoff; + int retval, error, forkoff; trace_xfs_attr_leaf_addname(args); @@ -628,25 +618,15 @@ xfs_attr_leaf_addname(xfs_da_args_t *args) */ xfs_bmap_init(args->flist, args->firstblock); error = xfs_attr3_leaf_to_node(args); - if (!error) { - error = xfs_bmap_finish(&args->trans, args->flist, - &committed); - } + if (!error) + error = xfs_bmap_finish(&args->trans, args->flist, dp); if (error) { - ASSERT(committed); args->trans = NULL; xfs_bmap_cancel(args->flist); return error; } /* - * bmap_finish() may have committed the last trans and started - * a new one. We need the inode to be in all transactions. - */ - if (committed) - xfs_trans_ijoin(args->trans, dp, 0); - - /* * Commit the current trans (including the inode) and start * a new one. */ @@ -729,25 +709,14 @@ xfs_attr_leaf_addname(xfs_da_args_t *args) xfs_bmap_init(args->flist, args->firstblock); error = xfs_attr3_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ - if (!error) { + if (!error) error = xfs_bmap_finish(&args->trans, - args->flist, - &committed); - } + args->flist, dp); if (error) { - ASSERT(committed); args->trans = NULL; xfs_bmap_cancel(args->flist); return error; } - - /* - * bmap_finish() may have committed the last trans - * and started a new one. We need the inode to be - * in all transactions. - */ - if (committed) - xfs_trans_ijoin(args->trans, dp, 0); } /* @@ -775,7 +744,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args) { xfs_inode_t *dp; struct xfs_buf *bp; - int error, committed, forkoff; + int error, forkoff; trace_xfs_attr_leaf_removename(args); @@ -803,23 +772,13 @@ xfs_attr_leaf_removename(xfs_da_args_t *args) xfs_bmap_init(args->flist, args->firstblock); error = xfs_attr3_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ - if (!error) { - error = xfs_bmap_finish(&args->trans, args->flist, - &committed); - } + if (!error) + error = xfs_bmap_finish(&args->trans, args->flist, dp); if (error) { - ASSERT(committed); args->trans = NULL; xfs_bmap_cancel(args->flist); return error; } - - /* - * bmap_finish() may have committed the last trans and started - * a new one. We need the inode to be in all transactions. - */ - if (committed) - xfs_trans_ijoin(args->trans, dp, 0); } return 0; } @@ -877,7 +836,7 @@ xfs_attr_node_addname(xfs_da_args_t *args) xfs_da_state_blk_t *blk; xfs_inode_t *dp; xfs_mount_t *mp; - int committed, retval, error; + int retval, error; trace_xfs_attr_node_addname(args); @@ -938,27 +897,16 @@ restart: state = NULL; xfs_bmap_init(args->flist, args->firstblock); error = xfs_attr3_leaf_to_node(args); - if (!error) { + if (!error) error = xfs_bmap_finish(&args->trans, - args->flist, - &committed); - } + args->flist, dp); if (error) { - ASSERT(committed); args->trans = NULL; xfs_bmap_cancel(args->flist); goto out; } /* - * bmap_finish() may have committed the last trans - * and started a new one. We need the inode to be - * in all transactions. - */ - if (committed) - xfs_trans_ijoin(args->trans, dp, 0); - - /* * Commit the node conversion and start the next * trans in the chain. */ @@ -977,23 +925,13 @@ restart: */ xfs_bmap_init(args->flist, args->firstblock); error = xfs_da3_split(state); - if (!error) { - error = xfs_bmap_finish(&args->trans, args->flist, - &committed); - } + if (!error) + error = xfs_bmap_finish(&args->trans, args->flist, dp); if (error) { - ASSERT(committed); args->trans = NULL; xfs_bmap_cancel(args->flist); goto out; } - - /* - * bmap_finish() may have committed the last trans and started - * a new one. We need the inode to be in all transactions. - */ - if (committed) - xfs_trans_ijoin(args->trans, dp, 0); } else { /* * Addition succeeded, update Btree hashvals. @@ -1086,25 +1024,14 @@ restart: if (retval && (state->path.active > 1)) { xfs_bmap_init(args->flist, args->firstblock); error = xfs_da3_join(state); - if (!error) { + if (!error) error = xfs_bmap_finish(&args->trans, - args->flist, - &committed); - } + args->flist, dp); if (error) { - ASSERT(committed); args->trans = NULL; xfs_bmap_cancel(args->flist); goto out; } - - /* - * bmap_finish() may have committed the last trans - * and started a new one. We need the inode to be - * in all transactions. - */ - if (committed) - xfs_trans_ijoin(args->trans, dp, 0); } /* @@ -1146,7 +1073,7 @@ xfs_attr_node_removename(xfs_da_args_t *args) xfs_da_state_blk_t *blk; xfs_inode_t *dp; struct xfs_buf *bp; - int retval, error, committed, forkoff; + int retval, error, forkoff; trace_xfs_attr_node_removename(args); @@ -1220,24 +1147,13 @@ xfs_attr_node_removename(xfs_da_args_t *args) if (retval && (state->path.active > 1)) { xfs_bmap_init(args->flist, args->firstblock); error = xfs_da3_join(state); - if (!error) { - error = xfs_bmap_finish(&args->trans, args->flist, - &committed); - } + if (!error) + error = xfs_bmap_finish(&args->trans, args->flist, dp); if (error) { - ASSERT(committed); args->trans = NULL; xfs_bmap_cancel(args->flist); goto out; } - - /* - * bmap_finish() may have committed the last trans and started - * a new one. We need the inode to be in all transactions. - */ - if (committed) - xfs_trans_ijoin(args->trans, dp, 0); - /* * Commit the Btree join operation and start a new trans. */ @@ -1265,25 +1181,14 @@ xfs_attr_node_removename(xfs_da_args_t *args) xfs_bmap_init(args->flist, args->firstblock); error = xfs_attr3_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ - if (!error) { + if (!error) error = xfs_bmap_finish(&args->trans, - args->flist, - &committed); - } + args->flist, dp); if (error) { - ASSERT(committed); args->trans = NULL; xfs_bmap_cancel(args->flist); goto out; } - - /* - * bmap_finish() may have committed the last trans - * and started a new one. We need the inode to be - * in all transactions. - */ - if (committed) - xfs_trans_ijoin(args->trans, dp, 0); } else xfs_trans_brelse(args->trans, bp); } diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 33df52d97ec7..01a5ecfedfcf 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -41,6 +41,7 @@ #include "xfs_buf_item.h" #include "xfs_cksum.h" #include "xfs_dir2.h" +#include "xfs_log.h" /* @@ -266,6 +267,8 @@ xfs_attr3_leaf_verify( return false; if (be64_to_cpu(hdr3->info.blkno) != bp->b_bn) return false; + if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr3->info.lsn))) + return false; } else { if (ichdr.magic != XFS_ATTR_LEAF_MAGIC) return false; @@ -325,6 +328,7 @@ xfs_attr3_leaf_read_verify( } const struct xfs_buf_ops xfs_attr3_leaf_buf_ops = { + .name = "xfs_attr3_leaf", .verify_read = xfs_attr3_leaf_read_verify, .verify_write = xfs_attr3_leaf_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c index f38f9bd81557..a572532a55cd 100644 --- a/fs/xfs/libxfs/xfs_attr_remote.c +++ b/fs/xfs/libxfs/xfs_attr_remote.c @@ -107,7 +107,7 @@ xfs_attr3_rmt_verify( if (be32_to_cpu(rmt->rm_bytes) > fsbsize - sizeof(*rmt)) return false; if (be32_to_cpu(rmt->rm_offset) + - be32_to_cpu(rmt->rm_bytes) > XATTR_SIZE_MAX) + be32_to_cpu(rmt->rm_bytes) > XFS_XATTR_SIZE_MAX) return false; if (rmt->rm_owner == 0) return false; @@ -201,6 +201,7 @@ xfs_attr3_rmt_write_verify( } const struct xfs_buf_ops xfs_attr3_rmt_buf_ops = { + .name = "xfs_attr3_rmt", .verify_read = xfs_attr3_rmt_read_verify, .verify_write = xfs_attr3_rmt_write_verify, }; @@ -447,8 +448,6 @@ xfs_attr_rmtval_set( * Roll through the "value", allocating blocks on disk as required. */ while (blkcnt > 0) { - int committed; - /* * Allocate a single extent, up to the size of the value. * @@ -466,24 +465,14 @@ xfs_attr_rmtval_set( error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno, blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock, args->total, &map, &nmap, args->flist); - if (!error) { - error = xfs_bmap_finish(&args->trans, args->flist, - &committed); - } + if (!error) + error = xfs_bmap_finish(&args->trans, args->flist, dp); if (error) { - ASSERT(committed); args->trans = NULL; xfs_bmap_cancel(args->flist); return error; } - /* - * bmap_finish() may have committed the last trans and started - * a new one. We need the inode to be in all transactions. - */ - if (committed) - xfs_trans_ijoin(args->trans, dp, 0); - ASSERT(nmap == 1); ASSERT((map.br_startblock != DELAYSTARTBLOCK) && (map.br_startblock != HOLESTARTBLOCK)); @@ -614,31 +603,20 @@ xfs_attr_rmtval_remove( blkcnt = args->rmtblkcnt; done = 0; while (!done) { - int committed; - xfs_bmap_init(args->flist, args->firstblock); error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt, XFS_BMAPI_ATTRFORK, 1, args->firstblock, args->flist, &done); - if (!error) { + if (!error) error = xfs_bmap_finish(&args->trans, args->flist, - &committed); - } + args->dp); if (error) { - ASSERT(committed); args->trans = NULL; xfs_bmap_cancel(args->flist); return error; } /* - * bmap_finish() may have committed the last trans and started - * a new one. We need the inode to be in all transactions. - */ - if (committed) - xfs_trans_ijoin(args->trans, args->dp, 0); - - /* * Close out trans and start the next one in the chain. */ error = xfs_trans_roll(&args->trans, args->dp); diff --git a/fs/xfs/libxfs/xfs_bit.c b/fs/xfs/libxfs/xfs_bit.c index 0e8885a59646..0a94cce5ea35 100644 --- a/fs/xfs/libxfs/xfs_bit.c +++ b/fs/xfs/libxfs/xfs_bit.c @@ -32,13 +32,13 @@ int xfs_bitmap_empty(uint *map, uint size) { uint i; - uint ret = 0; for (i = 0; i < size; i++) { - ret |= map[i]; + if (map[i] != 0) + return 0; } - return (ret == 0); + return 1; } /* diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 8e2010d53b07..ef00156f4f96 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -325,9 +325,11 @@ xfs_check_block( /* * Check that the extents for the inode ip are in the right order in all - * btree leaves. + * btree leaves. THis becomes prohibitively expensive for large extent count + * files, so don't bother with inodes that have more than 10,000 extents in + * them. The btree record ordering checks will still be done, so for such large + * bmapbt constructs that is going to catch most corruptions. */ - STATIC void xfs_bmap_check_leaf_extents( xfs_btree_cur_t *cur, /* btree cursor or null */ @@ -352,6 +354,10 @@ xfs_bmap_check_leaf_extents( return; } + /* skip large extent count inodes */ + if (ip->i_d.di_nextents > 10000) + return; + bno = NULLFSBLOCK; mp = ip->i_mount; ifp = XFS_IFORK_PTR(ip, whichfork); @@ -948,14 +954,16 @@ xfs_bmap_local_to_extents( bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0); /* - * Initialise the block and copy the data + * Initialize the block, copy the data and log the remote buffer. * - * Note: init_fn must set the buffer log item type correctly! + * The callout is responsible for logging because the remote format + * might differ from the local format and thus we don't know how much to + * log here. Note that init_fn must also set the buffer log item type + * correctly. */ init_fn(tp, bp, ip, ifp); - /* account for the change in fork size and log everything */ - xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1); + /* account for the change in fork size */ xfs_idata_realloc(ip, -ifp->if_bytes, whichfork); xfs_bmap_local_to_extents_empty(ip, whichfork); flags |= XFS_ILOG_CORE; @@ -1109,7 +1117,6 @@ xfs_bmap_add_attrfork( xfs_trans_t *tp; /* transaction pointer */ int blks; /* space reservation */ int version = 1; /* superblock attr version */ - int committed; /* xaction was committed */ int logflags; /* logging flags */ int error; /* error return value */ @@ -1212,7 +1219,7 @@ xfs_bmap_add_attrfork( xfs_log_sb(tp); } - error = xfs_bmap_finish(&tp, &flist, &committed); + error = xfs_bmap_finish(&tp, &flist, NULL); if (error) goto bmap_cancel; error = xfs_trans_commit(tp); @@ -1435,7 +1442,7 @@ xfs_bmap_search_extents( xfs_ifork_t *ifp; /* inode fork pointer */ xfs_bmbt_rec_host_t *ep; /* extent record pointer */ - XFS_STATS_INC(xs_look_exlist); + XFS_STATS_INC(ip->i_mount, xs_look_exlist); ifp = XFS_IFORK_PTR(ip, fork); ep = xfs_bmap_search_multi_extents(ifp, bno, eofp, lastxp, gotp, prevp); @@ -1721,10 +1728,11 @@ xfs_bmap_add_extent_delay_real( xfs_filblks_t temp=0; /* value for da_new calculations */ xfs_filblks_t temp2=0;/* value for da_new calculations */ int tmp_rval; /* partial logging flags */ + int whichfork = XFS_DATA_FORK; struct xfs_mount *mp; - mp = bma->tp ? bma->tp->t_mountp : NULL; - ifp = XFS_IFORK_PTR(bma->ip, XFS_DATA_FORK); + mp = bma->ip->i_mount; + ifp = XFS_IFORK_PTR(bma->ip, whichfork); ASSERT(bma->idx >= 0); ASSERT(bma->idx <= ifp->if_bytes / sizeof(struct xfs_bmbt_rec)); @@ -1732,7 +1740,7 @@ xfs_bmap_add_extent_delay_real( ASSERT(!bma->cur || (bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL)); - XFS_STATS_INC(xs_add_exlist); + XFS_STATS_INC(mp, xs_add_exlist); #define LEFT r[0] #define RIGHT r[1] @@ -1783,7 +1791,7 @@ xfs_bmap_add_extent_delay_real( * Don't set contiguous if the combined extent would be too large. * Also check for all-three-contiguous being too large. */ - if (bma->idx < bma->ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) { + if (bma->idx < ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) { state |= BMAP_RIGHT_VALID; xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx + 1), &RIGHT); @@ -2014,10 +2022,10 @@ xfs_bmap_add_extent_delay_real( XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); } - if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) { + if (xfs_bmap_needs_btree(bma->ip, whichfork)) { error = xfs_bmap_extents_to_btree(bma->tp, bma->ip, bma->firstblock, bma->flist, - &bma->cur, 1, &tmp_rval, XFS_DATA_FORK); + &bma->cur, 1, &tmp_rval, whichfork); rval |= tmp_rval; if (error) goto done; @@ -2098,10 +2106,10 @@ xfs_bmap_add_extent_delay_real( XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); } - if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) { + if (xfs_bmap_needs_btree(bma->ip, whichfork)) { error = xfs_bmap_extents_to_btree(bma->tp, bma->ip, bma->firstblock, bma->flist, &bma->cur, 1, - &tmp_rval, XFS_DATA_FORK); + &tmp_rval, whichfork); rval |= tmp_rval; if (error) goto done; @@ -2167,10 +2175,10 @@ xfs_bmap_add_extent_delay_real( XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); } - if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) { + if (xfs_bmap_needs_btree(bma->ip, whichfork)) { error = xfs_bmap_extents_to_btree(bma->tp, bma->ip, bma->firstblock, bma->flist, &bma->cur, - 1, &tmp_rval, XFS_DATA_FORK); + 1, &tmp_rval, whichfork); rval |= tmp_rval; if (error) goto done; @@ -2213,13 +2221,13 @@ xfs_bmap_add_extent_delay_real( } /* convert to a btree if necessary */ - if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) { + if (xfs_bmap_needs_btree(bma->ip, whichfork)) { int tmp_logflags; /* partial log flag return val */ ASSERT(bma->cur == NULL); error = xfs_bmap_extents_to_btree(bma->tp, bma->ip, bma->firstblock, bma->flist, &bma->cur, - da_old > 0, &tmp_logflags, XFS_DATA_FORK); + da_old > 0, &tmp_logflags, whichfork); bma->logflags |= tmp_logflags; if (error) goto done; @@ -2240,7 +2248,7 @@ xfs_bmap_add_extent_delay_real( if (bma->cur) bma->cur->bc_private.b.allocated = 0; - xfs_bmap_check_leaf_extents(bma->cur, bma->ip, XFS_DATA_FORK); + xfs_bmap_check_leaf_extents(bma->cur, bma->ip, whichfork); done: bma->logflags |= rval; return error; @@ -2286,7 +2294,7 @@ xfs_bmap_add_extent_unwritten_real( ASSERT(*idx <= ifp->if_bytes / sizeof(struct xfs_bmbt_rec)); ASSERT(!isnullstartblock(new->br_startblock)); - XFS_STATS_INC(xs_add_exlist); + XFS_STATS_INC(mp, xs_add_exlist); #define LEFT r[0] #define RIGHT r[1] @@ -2937,7 +2945,7 @@ xfs_bmap_add_extent_hole_real( int state; /* state bits, accessed thru macros */ struct xfs_mount *mp; - mp = bma->tp ? bma->tp->t_mountp : NULL; + mp = bma->ip->i_mount; ifp = XFS_IFORK_PTR(bma->ip, whichfork); ASSERT(bma->idx >= 0); @@ -2946,7 +2954,7 @@ xfs_bmap_add_extent_hole_real( ASSERT(!bma->cur || !(bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL)); - XFS_STATS_INC(xs_add_exlist); + XFS_STATS_INC(mp, xs_add_exlist); state = 0; if (whichfork == XFS_ATTR_FORK) @@ -3800,8 +3808,13 @@ xfs_bmap_btalloc( args.wasdel = ap->wasdel; args.isfl = 0; args.userdata = ap->userdata; - if ((error = xfs_alloc_vextent(&args))) + if (ap->userdata & XFS_ALLOC_USERDATA_ZERO) + args.ip = ap->ip; + + error = xfs_alloc_vextent(&args); + if (error) return error; + if (tryagain && args.fsbno == NULLFSBLOCK) { /* * Exact allocation failed. Now try with alignment @@ -4036,7 +4049,7 @@ xfs_bmapi_read( if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - XFS_STATS_INC(xs_blk_mapr); + XFS_STATS_INC(mp, xs_blk_mapr); ifp = XFS_IFORK_PTR(ip, whichfork); @@ -4221,7 +4234,7 @@ xfs_bmapi_delay( if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - XFS_STATS_INC(xs_blk_mapw); + XFS_STATS_INC(mp, xs_blk_mapw); if (!(ifp->if_flags & XFS_IFEXTENTS)) { error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK); @@ -4300,11 +4313,14 @@ xfs_bmapi_allocate( /* * Indicate if this is the first user data in the file, or just any - * user data. + * user data. And if it is userdata, indicate whether it needs to + * be initialised to zero during allocation. */ if (!(bma->flags & XFS_BMAPI_METADATA)) { bma->userdata = (bma->offset == 0) ? XFS_ALLOC_INITIAL_USER_DATA : XFS_ALLOC_USERDATA; + if (bma->flags & XFS_BMAPI_ZERO) + bma->userdata |= XFS_ALLOC_USERDATA_ZERO; } bma->minlen = (bma->flags & XFS_BMAPI_CONTIG) ? bma->length : 1; @@ -4419,6 +4435,17 @@ xfs_bmapi_convert_unwritten( mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN) ? XFS_EXT_NORM : XFS_EXT_UNWRITTEN; + /* + * Before insertion into the bmbt, zero the range being converted + * if required. + */ + if (flags & XFS_BMAPI_ZERO) { + error = xfs_zero_extent(bma->ip, mval->br_startblock, + mval->br_blockcount); + if (error) + return error; + } + error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, &bma->idx, &bma->cur, mval, bma->firstblock, bma->flist, &tmp_logflags); @@ -4512,6 +4539,18 @@ xfs_bmapi_write( ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + /* zeroing is for currently only for data extents, not metadata */ + ASSERT((flags & (XFS_BMAPI_METADATA | XFS_BMAPI_ZERO)) != + (XFS_BMAPI_METADATA | XFS_BMAPI_ZERO)); + /* + * we can allocate unwritten extents or pre-zero allocated blocks, + * but it makes no sense to do both at once. This would result in + * zeroing the unwritten extent twice, but it still being an + * unwritten extent.... + */ + ASSERT((flags & (XFS_BMAPI_PREALLOC | XFS_BMAPI_ZERO)) != + (XFS_BMAPI_PREALLOC | XFS_BMAPI_ZERO)); + if (unlikely(XFS_TEST_ERROR( (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE), @@ -4525,7 +4564,7 @@ xfs_bmapi_write( ifp = XFS_IFORK_PTR(ip, whichfork); - XFS_STATS_INC(xs_blk_mapw); + XFS_STATS_INC(mp, xs_blk_mapw); if (*firstblock == NULLFSBLOCK) { if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE) @@ -4718,12 +4757,12 @@ xfs_bmap_del_extent( xfs_filblks_t temp2; /* for indirect length calculations */ int state = 0; - XFS_STATS_INC(xs_del_exlist); + mp = ip->i_mount; + XFS_STATS_INC(mp, xs_del_exlist); if (whichfork == XFS_ATTR_FORK) state |= BMAP_ATTRFORK; - mp = ip->i_mount; ifp = XFS_IFORK_PTR(ip, whichfork); ASSERT((*idx >= 0) && (*idx < ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))); @@ -5070,7 +5109,7 @@ xfs_bunmapi( *done = 1; return 0; } - XFS_STATS_INC(xs_blk_unmap); + XFS_STATS_INC(mp, xs_blk_unmap); isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip); start = bno; bno = start + len - 1; @@ -5917,7 +5956,6 @@ xfs_bmap_split_extent( struct xfs_trans *tp; struct xfs_bmap_free free_list; xfs_fsblock_t firstfsb; - int committed; int error; tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT); @@ -5938,7 +5976,7 @@ xfs_bmap_split_extent( if (error) goto out; - error = xfs_bmap_finish(&tp, &free_list, &committed); + error = xfs_bmap_finish(&tp, &free_list, NULL); if (error) goto out; diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 6aaa0c1c7200..423a34e832bd 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -52,9 +52,9 @@ struct xfs_bmalloca { xfs_extlen_t minleft; /* amount must be left after alloc */ bool eof; /* set if allocating past last extent */ bool wasdel; /* replacing a delayed allocation */ - bool userdata;/* set if is user data */ bool aeof; /* allocated space at eof */ bool conv; /* overwriting unwritten extents */ + char userdata;/* userdata mask */ int flags; }; @@ -109,6 +109,14 @@ typedef struct xfs_bmap_free */ #define XFS_BMAPI_CONVERT 0x040 +/* + * allocate zeroed extents - this requires all newly allocated user data extents + * to be initialised to zero. It will be ignored if XFS_BMAPI_METADATA is set. + * Use in conjunction with XFS_BMAPI_CONVERT to convert unwritten extents found + * during the allocation range to zeroed written extents. + */ +#define XFS_BMAPI_ZERO 0x080 + #define XFS_BMAPI_FLAGS \ { XFS_BMAPI_ENTIRE, "ENTIRE" }, \ { XFS_BMAPI_METADATA, "METADATA" }, \ @@ -116,7 +124,8 @@ typedef struct xfs_bmap_free { XFS_BMAPI_PREALLOC, "PREALLOC" }, \ { XFS_BMAPI_IGSTATE, "IGSTATE" }, \ { XFS_BMAPI_CONTIG, "CONTIG" }, \ - { XFS_BMAPI_CONVERT, "CONVERT" } + { XFS_BMAPI_CONVERT, "CONVERT" }, \ + { XFS_BMAPI_ZERO, "ZERO" } static inline int xfs_bmapi_aflag(int w) @@ -186,7 +195,7 @@ void xfs_bmap_add_free(xfs_fsblock_t bno, xfs_filblks_t len, struct xfs_bmap_free *flist, struct xfs_mount *mp); void xfs_bmap_cancel(struct xfs_bmap_free *flist); int xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist, - int *committed); + struct xfs_inode *ip); void xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork); int xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip, xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork); diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 6b0cf6546a82..1637c37bfbaa 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -720,6 +720,7 @@ xfs_bmbt_write_verify( } const struct xfs_buf_ops xfs_bmbt_buf_ops = { + .name = "xfs_bmbt", .verify_read = xfs_bmbt_read_verify, .verify_write = xfs_bmbt_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index f7d7ee7a2607..a0eb18ce3ad3 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -32,6 +32,7 @@ #include "xfs_trace.h" #include "xfs_cksum.h" #include "xfs_alloc.h" +#include "xfs_log.h" /* * Cursor allocation zone. @@ -222,7 +223,7 @@ xfs_btree_check_ptr( * long-form btree header. * * Prior to calculting the CRC, pull the LSN out of the buffer log item and put - * it into the buffer so recovery knows what the last modifcation was that made + * it into the buffer so recovery knows what the last modification was that made * it to disk. */ void @@ -243,8 +244,14 @@ bool xfs_btree_lblock_verify_crc( struct xfs_buf *bp) { - if (xfs_sb_version_hascrc(&bp->b_target->bt_mount->m_sb)) + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + struct xfs_mount *mp = bp->b_target->bt_mount; + + if (xfs_sb_version_hascrc(&mp->m_sb)) { + if (!xfs_log_check_lsn(mp, be64_to_cpu(block->bb_u.l.bb_lsn))) + return false; return xfs_buf_verify_cksum(bp, XFS_BTREE_LBLOCK_CRC_OFF); + } return true; } @@ -254,7 +261,7 @@ xfs_btree_lblock_verify_crc( * short-form btree header. * * Prior to calculting the CRC, pull the LSN out of the buffer log item and put - * it into the buffer so recovery knows what the last modifcation was that made + * it into the buffer so recovery knows what the last modification was that made * it to disk. */ void @@ -275,8 +282,14 @@ bool xfs_btree_sblock_verify_crc( struct xfs_buf *bp) { - if (xfs_sb_version_hascrc(&bp->b_target->bt_mount->m_sb)) + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + struct xfs_mount *mp = bp->b_target->bt_mount; + + if (xfs_sb_version_hascrc(&mp->m_sb)) { + if (!xfs_log_check_lsn(mp, be64_to_cpu(block->bb_u.s.bb_lsn))) + return false; return xfs_buf_verify_cksum(bp, XFS_BTREE_SBLOCK_CRC_OFF); + } return true; } @@ -4067,3 +4080,61 @@ xfs_btree_change_owner( return 0; } + +/** + * xfs_btree_sblock_v5hdr_verify() -- verify the v5 fields of a short-format + * btree block + * + * @bp: buffer containing the btree block + * @max_recs: pointer to the m_*_mxr max records field in the xfs mount + * @pag_max_level: pointer to the per-ag max level field + */ +bool +xfs_btree_sblock_v5hdr_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + struct xfs_perag *pag = bp->b_pag; + + if (!xfs_sb_version_hascrc(&mp->m_sb)) + return false; + if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid)) + return false; + if (block->bb_u.s.bb_blkno != cpu_to_be64(bp->b_bn)) + return false; + if (pag && be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno) + return false; + return true; +} + +/** + * xfs_btree_sblock_verify() -- verify a short-format btree block + * + * @bp: buffer containing the btree block + * @max_recs: maximum records allowed in this btree node + */ +bool +xfs_btree_sblock_verify( + struct xfs_buf *bp, + unsigned int max_recs) +{ + struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + + /* numrecs verification */ + if (be16_to_cpu(block->bb_numrecs) > max_recs) + return false; + + /* sibling pointer verification */ + if (!block->bb_u.s.bb_leftsib || + (be32_to_cpu(block->bb_u.s.bb_leftsib) >= mp->m_sb.sb_agblocks && + block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK))) + return false; + if (!block->bb_u.s.bb_rightsib || + (be32_to_cpu(block->bb_u.s.bb_rightsib) >= mp->m_sb.sb_agblocks && + block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK))) + return false; + + return true; +} diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index 8f18bab73ea5..2e874be70209 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -84,31 +84,38 @@ union xfs_btree_rec { /* * Generic stats interface */ -#define __XFS_BTREE_STATS_INC(type, stat) \ - XFS_STATS_INC(xs_ ## type ## _2_ ## stat) -#define XFS_BTREE_STATS_INC(cur, stat) \ +#define __XFS_BTREE_STATS_INC(mp, type, stat) \ + XFS_STATS_INC(mp, xs_ ## type ## _2_ ## stat) +#define XFS_BTREE_STATS_INC(cur, stat) \ do { \ + struct xfs_mount *__mp = cur->bc_mp; \ switch (cur->bc_btnum) { \ - case XFS_BTNUM_BNO: __XFS_BTREE_STATS_INC(abtb, stat); break; \ - case XFS_BTNUM_CNT: __XFS_BTREE_STATS_INC(abtc, stat); break; \ - case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_INC(bmbt, stat); break; \ - case XFS_BTNUM_INO: __XFS_BTREE_STATS_INC(ibt, stat); break; \ - case XFS_BTNUM_FINO: __XFS_BTREE_STATS_INC(fibt, stat); break; \ + case XFS_BTNUM_BNO: __XFS_BTREE_STATS_INC(__mp, abtb, stat); break; \ + case XFS_BTNUM_CNT: __XFS_BTREE_STATS_INC(__mp, abtc, stat); break; \ + case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_INC(__mp, bmbt, stat); break; \ + case XFS_BTNUM_INO: __XFS_BTREE_STATS_INC(__mp, ibt, stat); break; \ + case XFS_BTNUM_FINO: __XFS_BTREE_STATS_INC(__mp, fibt, stat); break; \ case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break; \ } \ } while (0) -#define __XFS_BTREE_STATS_ADD(type, stat, val) \ - XFS_STATS_ADD(xs_ ## type ## _2_ ## stat, val) +#define __XFS_BTREE_STATS_ADD(mp, type, stat, val) \ + XFS_STATS_ADD(mp, xs_ ## type ## _2_ ## stat, val) #define XFS_BTREE_STATS_ADD(cur, stat, val) \ do { \ + struct xfs_mount *__mp = cur->bc_mp; \ switch (cur->bc_btnum) { \ - case XFS_BTNUM_BNO: __XFS_BTREE_STATS_ADD(abtb, stat, val); break; \ - case XFS_BTNUM_CNT: __XFS_BTREE_STATS_ADD(abtc, stat, val); break; \ - case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_ADD(bmbt, stat, val); break; \ - case XFS_BTNUM_INO: __XFS_BTREE_STATS_ADD(ibt, stat, val); break; \ - case XFS_BTNUM_FINO: __XFS_BTREE_STATS_ADD(fibt, stat, val); break; \ - case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break; \ + case XFS_BTNUM_BNO: \ + __XFS_BTREE_STATS_ADD(__mp, abtb, stat, val); break; \ + case XFS_BTNUM_CNT: \ + __XFS_BTREE_STATS_ADD(__mp, abtc, stat, val); break; \ + case XFS_BTNUM_BMAP: \ + __XFS_BTREE_STATS_ADD(__mp, bmbt, stat, val); break; \ + case XFS_BTNUM_INO: \ + __XFS_BTREE_STATS_ADD(__mp, ibt, stat, val); break; \ + case XFS_BTNUM_FINO: \ + __XFS_BTREE_STATS_ADD(__mp, fibt, stat, val); break; \ + case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break; \ } \ } while (0) @@ -465,4 +472,7 @@ static inline int xfs_btree_get_level(struct xfs_btree_block *block) #define XFS_BTREE_TRACE_ARGR(c, r) #define XFS_BTREE_TRACE_CURSOR(c, t) +bool xfs_btree_sblock_v5hdr_verify(struct xfs_buf *bp); +bool xfs_btree_sblock_verify(struct xfs_buf *bp, unsigned int max_recs); + #endif /* __XFS_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index be43248a5822..097bf7717d80 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -39,6 +39,7 @@ #include "xfs_trace.h" #include "xfs_cksum.h" #include "xfs_buf_item.h" +#include "xfs_log.h" /* * xfs_da_btree.c @@ -150,6 +151,8 @@ xfs_da3_node_verify( return false; if (be64_to_cpu(hdr3->info.blkno) != bp->b_bn) return false; + if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr3->info.lsn))) + return false; } else { if (ichdr.magic != XFS_DA_NODE_MAGIC) return false; @@ -242,6 +245,7 @@ xfs_da3_node_read_verify( } const struct xfs_buf_ops xfs_da3_node_buf_ops = { + .name = "xfs_da3_node", .verify_read = xfs_da3_node_read_verify, .verify_write = xfs_da3_node_write_verify, }; @@ -322,6 +326,7 @@ xfs_da3_node_create( if (xfs_sb_version_hascrc(&mp->m_sb)) { struct xfs_da3_node_hdr *hdr3 = bp->b_addr; + memset(hdr3, 0, sizeof(struct xfs_da3_node_hdr)); ichdr.magic = XFS_DA3_NODE_MAGIC; hdr3->info.blkno = cpu_to_be64(bp->b_bn); hdr3->info.owner = cpu_to_be64(args->dp->i_ino); diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 9de401d297e5..2fb53a5c0a74 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -271,7 +271,7 @@ xfs_dir_createname( rval = xfs_dir_ino_validate(tp->t_mountp, inum); if (rval) return rval; - XFS_STATS_INC(xs_dir_create); + XFS_STATS_INC(dp->i_mount, xs_dir_create); } args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS); @@ -365,7 +365,7 @@ xfs_dir_lookup( int lock_mode; ASSERT(S_ISDIR(dp->i_d.di_mode)); - XFS_STATS_INC(xs_dir_lookup); + XFS_STATS_INC(dp->i_mount, xs_dir_lookup); /* * We need to use KM_NOFS here so that lockdep will not throw false @@ -444,7 +444,7 @@ xfs_dir_removename( int v; /* type-checking value */ ASSERT(S_ISDIR(dp->i_d.di_mode)); - XFS_STATS_INC(xs_dir_remove); + XFS_STATS_INC(dp->i_mount, xs_dir_remove); args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS); if (!args) diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c index 4778d1dd511a..aa17cb788946 100644 --- a/fs/xfs/libxfs/xfs_dir2_block.c +++ b/fs/xfs/libxfs/xfs_dir2_block.c @@ -34,6 +34,7 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_cksum.h" +#include "xfs_log.h" /* * Local function prototypes. @@ -71,6 +72,8 @@ xfs_dir3_block_verify( return false; if (be64_to_cpu(hdr3->blkno) != bp->b_bn) return false; + if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr3->lsn))) + return false; } else { if (hdr3->magic != cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)) return false; @@ -120,6 +123,7 @@ xfs_dir3_block_write_verify( } const struct xfs_buf_ops xfs_dir3_block_buf_ops = { + .name = "xfs_dir3_block", .verify_read = xfs_dir3_block_read_verify, .verify_write = xfs_dir3_block_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c index 824131e71bc5..725fc7841fde 100644 --- a/fs/xfs/libxfs/xfs_dir2_data.c +++ b/fs/xfs/libxfs/xfs_dir2_data.c @@ -31,6 +31,7 @@ #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_cksum.h" +#include "xfs_log.h" /* * Check the consistency of the data block. @@ -224,6 +225,8 @@ xfs_dir3_data_verify( return false; if (be64_to_cpu(hdr3->blkno) != bp->b_bn) return false; + if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr3->lsn))) + return false; } else { if (hdr3->magic != cpu_to_be32(XFS_DIR2_DATA_MAGIC)) return false; @@ -302,11 +305,13 @@ xfs_dir3_data_write_verify( } const struct xfs_buf_ops xfs_dir3_data_buf_ops = { + .name = "xfs_dir3_data", .verify_read = xfs_dir3_data_read_verify, .verify_write = xfs_dir3_data_write_verify, }; static const struct xfs_buf_ops xfs_dir3_data_reada_buf_ops = { + .name = "xfs_dir3_data_reada", .verify_read = xfs_dir3_data_reada_verify, .verify_write = xfs_dir3_data_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c index f300240ebb8d..b887fb2a2bcf 100644 --- a/fs/xfs/libxfs/xfs_dir2_leaf.c +++ b/fs/xfs/libxfs/xfs_dir2_leaf.c @@ -33,6 +33,7 @@ #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_cksum.h" +#include "xfs_log.h" /* * Local function declarations. @@ -164,6 +165,8 @@ xfs_dir3_leaf_verify( return false; if (be64_to_cpu(leaf3->info.blkno) != bp->b_bn) return false; + if (!xfs_log_check_lsn(mp, be64_to_cpu(leaf3->info.lsn))) + return false; } else { if (leaf->hdr.info.magic != cpu_to_be16(magic)) return false; @@ -242,11 +245,13 @@ xfs_dir3_leafn_write_verify( } const struct xfs_buf_ops xfs_dir3_leaf1_buf_ops = { + .name = "xfs_dir3_leaf1", .verify_read = xfs_dir3_leaf1_read_verify, .verify_write = xfs_dir3_leaf1_write_verify, }; const struct xfs_buf_ops xfs_dir3_leafn_buf_ops = { + .name = "xfs_dir3_leafn", .verify_read = xfs_dir3_leafn_read_verify, .verify_write = xfs_dir3_leafn_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index cc28e924545b..63ee03db796c 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -33,6 +33,7 @@ #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_cksum.h" +#include "xfs_log.h" /* * Function declarations. @@ -97,6 +98,8 @@ xfs_dir3_free_verify( return false; if (be64_to_cpu(hdr3->blkno) != bp->b_bn) return false; + if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr3->lsn))) + return false; } else { if (hdr->magic != cpu_to_be32(XFS_DIR2_FREE_MAGIC)) return false; @@ -147,6 +150,7 @@ xfs_dir3_free_write_verify( } const struct xfs_buf_ops xfs_dir3_free_buf_ops = { + .name = "xfs_dir3_free", .verify_read = xfs_dir3_free_read_verify, .verify_write = xfs_dir3_free_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c index 5331b7f0460c..3cc3cf767474 100644 --- a/fs/xfs/libxfs/xfs_dquot_buf.c +++ b/fs/xfs/libxfs/xfs_dquot_buf.c @@ -54,7 +54,7 @@ xfs_dqcheck( xfs_dqid_t id, uint type, /* used only when IO_dorepair is true */ uint flags, - char *str) + const char *str) { xfs_dqblk_t *d = (xfs_dqblk_t *)ddq; int errs = 0; @@ -207,7 +207,8 @@ xfs_dquot_buf_verify_crc( STATIC bool xfs_dquot_buf_verify( struct xfs_mount *mp, - struct xfs_buf *bp) + struct xfs_buf *bp, + int warn) { struct xfs_dqblk *d = (struct xfs_dqblk *)bp->b_addr; xfs_dqid_t id = 0; @@ -240,8 +241,7 @@ xfs_dquot_buf_verify( if (i == 0) id = be32_to_cpu(ddq->d_id); - error = xfs_dqcheck(mp, ddq, id + i, 0, XFS_QMOPT_DOWARN, - "xfs_dquot_buf_verify"); + error = xfs_dqcheck(mp, ddq, id + i, 0, warn, __func__); if (error) return false; } @@ -256,7 +256,7 @@ xfs_dquot_buf_read_verify( if (!xfs_dquot_buf_verify_crc(mp, bp)) xfs_buf_ioerror(bp, -EFSBADCRC); - else if (!xfs_dquot_buf_verify(mp, bp)) + else if (!xfs_dquot_buf_verify(mp, bp, XFS_QMOPT_DOWARN)) xfs_buf_ioerror(bp, -EFSCORRUPTED); if (bp->b_error) @@ -264,6 +264,25 @@ xfs_dquot_buf_read_verify( } /* + * readahead errors are silent and simply leave the buffer as !done so a real + * read will then be run with the xfs_dquot_buf_ops verifier. See + * xfs_inode_buf_verify() for why we use EIO and ~XBF_DONE here rather than + * reporting the failure. + */ +static void +xfs_dquot_buf_readahead_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_target->bt_mount; + + if (!xfs_dquot_buf_verify_crc(mp, bp) || + !xfs_dquot_buf_verify(mp, bp, 0)) { + xfs_buf_ioerror(bp, -EIO); + bp->b_flags &= ~XBF_DONE; + } +} + +/* * we don't calculate the CRC here as that is done when the dquot is flushed to * the buffer after the update is done. This ensures that the dquot in the * buffer always has an up-to-date CRC value. @@ -274,7 +293,7 @@ xfs_dquot_buf_write_verify( { struct xfs_mount *mp = bp->b_target->bt_mount; - if (!xfs_dquot_buf_verify(mp, bp)) { + if (!xfs_dquot_buf_verify(mp, bp, XFS_QMOPT_DOWARN)) { xfs_buf_ioerror(bp, -EFSCORRUPTED); xfs_verifier_error(bp); return; @@ -282,7 +301,13 @@ xfs_dquot_buf_write_verify( } const struct xfs_buf_ops xfs_dquot_buf_ops = { + .name = "xfs_dquot", .verify_read = xfs_dquot_buf_read_verify, .verify_write = xfs_dquot_buf_write_verify, }; +const struct xfs_buf_ops xfs_dquot_buf_ra_ops = { + .name = "xfs_dquot_ra", + .verify_read = xfs_dquot_buf_readahead_verify, + .verify_write = xfs_dquot_buf_write_verify, +}; diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 9590a069e556..e2536bb1c760 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -60,6 +60,14 @@ struct xfs_ifork; #define XFS_SB_VERSION_MOREBITSBIT 0x8000 /* + * The size of a single extended attribute on disk is limited by + * the size of index values within the attribute entries themselves. + * These are be16 fields, so we can only support attribute data + * sizes up to 2^16 bytes in length. + */ +#define XFS_XATTR_SIZE_MAX (1 << 16) + +/* * Supported feature bit list is just all bits in the versionnum field because * we've used them all up and understand them all. Except, of course, for the * shared superblock bit, which nobody knows what it does and so is unsupported. @@ -778,7 +786,7 @@ typedef struct xfs_agfl { __be64 agfl_lsn; __be32 agfl_crc; __be32 agfl_bno[]; /* actually XFS_AGFL_SIZE(mp) */ -} xfs_agfl_t; +} __attribute__((packed)) xfs_agfl_t; #define XFS_AGFL_CRC_OFF offsetof(struct xfs_agfl, agfl_crc) @@ -1483,13 +1491,17 @@ struct xfs_acl { */ #define XFS_ACL_MAX_ENTRIES(mp) \ (xfs_sb_version_hascrc(&mp->m_sb) \ - ? (XATTR_SIZE_MAX - sizeof(struct xfs_acl)) / \ + ? (XFS_XATTR_SIZE_MAX - sizeof(struct xfs_acl)) / \ sizeof(struct xfs_acl_entry) \ : 25) -#define XFS_ACL_MAX_SIZE(mp) \ +#define XFS_ACL_SIZE(cnt) \ (sizeof(struct xfs_acl) + \ - sizeof(struct xfs_acl_entry) * XFS_ACL_MAX_ENTRIES((mp))) + sizeof(struct xfs_acl_entry) * cnt) + +#define XFS_ACL_MAX_SIZE(mp) \ + XFS_ACL_SIZE(XFS_ACL_MAX_ENTRIES((mp))) + /* On-disk XFS extended attribute names */ #define SGI_ACL_FILE "SGI_ACL_FILE" diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index 89689c6a43e2..b2b73a998d42 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -490,6 +490,16 @@ typedef struct xfs_swapext #define XFS_FSOP_GOING_FLAGS_NOLOGFLUSH 0x2 /* don't flush log nor data */ /* + * ioctl limits + */ +#ifdef XATTR_LIST_MAX +# define XFS_XATTR_LIST_MAX XATTR_LIST_MAX +#else +# define XFS_XATTR_LIST_MAX 65536 +#endif + + +/* * ioctl commands that are used by Linux filesystems */ #define XFS_IOC_GETXFLAGS FS_IOC_GETFLAGS diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 54deb2d12ac6..66d702e6b9ff 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -38,6 +38,7 @@ #include "xfs_icreate_item.h" #include "xfs_icache.h" #include "xfs_trace.h" +#include "xfs_log.h" /* @@ -2500,9 +2501,14 @@ xfs_agi_verify( struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_agi *agi = XFS_BUF_TO_AGI(bp); - if (xfs_sb_version_hascrc(&mp->m_sb) && - !uuid_equal(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid)) + if (xfs_sb_version_hascrc(&mp->m_sb)) { + if (!uuid_equal(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid)) + return false; + if (!xfs_log_check_lsn(mp, + be64_to_cpu(XFS_BUF_TO_AGI(bp)->agi_lsn))) return false; + } + /* * Validate the magic number of the agi block. */ @@ -2566,6 +2572,7 @@ xfs_agi_write_verify( } const struct xfs_buf_ops xfs_agi_buf_ops = { + .name = "xfs_agi", .verify_read = xfs_agi_read_verify, .verify_write = xfs_agi_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index f39b285beb19..c679f3c05b63 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -221,7 +221,6 @@ xfs_inobt_verify( { struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); - struct xfs_perag *pag = bp->b_pag; unsigned int level; /* @@ -237,14 +236,7 @@ xfs_inobt_verify( switch (block->bb_magic) { case cpu_to_be32(XFS_IBT_CRC_MAGIC): case cpu_to_be32(XFS_FIBT_CRC_MAGIC): - if (!xfs_sb_version_hascrc(&mp->m_sb)) - return false; - if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid)) - return false; - if (block->bb_u.s.bb_blkno != cpu_to_be64(bp->b_bn)) - return false; - if (pag && - be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno) + if (!xfs_btree_sblock_v5hdr_verify(bp)) return false; /* fall through */ case cpu_to_be32(XFS_IBT_MAGIC): @@ -254,24 +246,12 @@ xfs_inobt_verify( return 0; } - /* numrecs and level verification */ + /* level verification */ level = be16_to_cpu(block->bb_level); if (level >= mp->m_in_maxlevels) return false; - if (be16_to_cpu(block->bb_numrecs) > mp->m_inobt_mxr[level != 0]) - return false; - - /* sibling pointer verification */ - if (!block->bb_u.s.bb_leftsib || - (be32_to_cpu(block->bb_u.s.bb_leftsib) >= mp->m_sb.sb_agblocks && - block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK))) - return false; - if (!block->bb_u.s.bb_rightsib || - (be32_to_cpu(block->bb_u.s.bb_rightsib) >= mp->m_sb.sb_agblocks && - block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK))) - return false; - return true; + return xfs_btree_sblock_verify(bp, mp->m_inobt_mxr[level != 0]); } static void @@ -304,6 +284,7 @@ xfs_inobt_write_verify( } const struct xfs_buf_ops xfs_inobt_buf_ops = { + .name = "xfs_inobt", .verify_read = xfs_inobt_read_verify, .verify_write = xfs_inobt_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 268c00f4f83a..1aabfda669b0 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -62,11 +62,14 @@ xfs_inobp_check( * has not had the inode cores stamped into it. Hence for readahead, the buffer * may be potentially invalid. * - * If the readahead buffer is invalid, we don't want to mark it with an error, - * but we do want to clear the DONE status of the buffer so that a followup read - * will re-read it from disk. This will ensure that we don't get an unnecessary - * warnings during log recovery and we don't get unnecssary panics on debug - * kernels. + * If the readahead buffer is invalid, we need to mark it with an error and + * clear the DONE status of the buffer so that a followup read will re-read it + * from disk. We don't report the error otherwise to avoid warnings during log + * recovery and we don't get unnecssary panics on debug kernels. We use EIO here + * because all we want to do is say readahead failed; there is no-one to report + * the error to, so this will distinguish it from a non-ra verifier failure. + * Changes to this readahead error behavour also need to be reflected in + * xfs_dquot_buf_readahead_verify(). */ static void xfs_inode_buf_verify( @@ -93,6 +96,7 @@ xfs_inode_buf_verify( XFS_RANDOM_ITOBP_INOTOBP))) { if (readahead) { bp->b_flags &= ~XBF_DONE; + xfs_buf_ioerror(bp, -EIO); return; } @@ -132,11 +136,13 @@ xfs_inode_buf_write_verify( } const struct xfs_buf_ops xfs_inode_buf_ops = { + .name = "xfs_inode", .verify_read = xfs_inode_buf_read_verify, .verify_write = xfs_inode_buf_write_verify, }; const struct xfs_buf_ops xfs_inode_buf_ra_ops = { + .name = "xxfs_inode_ra", .verify_read = xfs_inode_buf_readahead_verify, .verify_write = xfs_inode_buf_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h index 1c55ccbb379d..8e385f91d660 100644 --- a/fs/xfs/libxfs/xfs_log_recover.h +++ b/fs/xfs/libxfs/xfs_log_recover.h @@ -60,6 +60,7 @@ typedef struct xlog_recover { */ #define XLOG_BC_TABLE_SIZE 64 +#define XLOG_RECOVER_CRCPASS 0 #define XLOG_RECOVER_PASS1 1 #define XLOG_RECOVER_PASS2 2 diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h index 1b0a08379759..f51078f1e92a 100644 --- a/fs/xfs/libxfs/xfs_quota_defs.h +++ b/fs/xfs/libxfs/xfs_quota_defs.h @@ -153,7 +153,7 @@ typedef __uint16_t xfs_qwarncnt_t; #define XFS_QMOPT_RESBLK_MASK (XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS) extern int xfs_dqcheck(struct xfs_mount *mp, xfs_disk_dquot_t *ddq, - xfs_dqid_t id, uint type, uint flags, char *str); + xfs_dqid_t id, uint type, uint flags, const char *str); extern int xfs_calc_dquots_per_chunk(unsigned int nbblks); #endif /* __XFS_QUOTA_H__ */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 47425140f343..8a53eaa349f4 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -35,6 +35,7 @@ #include "xfs_bmap_btree.h" #include "xfs_alloc_btree.h" #include "xfs_ialloc_btree.h" +#include "xfs_log.h" /* * Physical superblock buffer manipulations. Shared with libxfs in userspace. @@ -163,6 +164,15 @@ xfs_mount_validate_sb( "Filesystem can not be safely mounted by this kernel."); return -EINVAL; } + } else if (xfs_sb_version_hascrc(sbp)) { + /* + * We can't read verify the sb LSN because the read verifier is + * called before the log is allocated and processed. We know the + * log is set up before write verifier (!check_version) calls, + * so just check it here. + */ + if (!xfs_log_check_lsn(mp, sbp->sb_lsn)) + return -EFSCORRUPTED; } if (xfs_sb_version_has_pquotino(sbp)) { @@ -669,11 +679,13 @@ xfs_sb_write_verify( } const struct xfs_buf_ops xfs_sb_buf_ops = { + .name = "xfs_sb", .verify_read = xfs_sb_read_verify, .verify_write = xfs_sb_write_verify, }; const struct xfs_buf_ops xfs_sb_quiet_buf_ops = { + .name = "xfs_sb_quiet", .verify_read = xfs_sb_quiet_read_verify, .verify_write = xfs_sb_write_verify, }; diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h index 5be529707903..15c3ceb845b9 100644 --- a/fs/xfs/libxfs/xfs_shared.h +++ b/fs/xfs/libxfs/xfs_shared.h @@ -49,6 +49,7 @@ extern const struct xfs_buf_ops xfs_inobt_buf_ops; extern const struct xfs_buf_ops xfs_inode_buf_ops; extern const struct xfs_buf_ops xfs_inode_buf_ra_ops; extern const struct xfs_buf_ops xfs_dquot_buf_ops; +extern const struct xfs_buf_ops xfs_dquot_buf_ra_ops; extern const struct xfs_buf_ops xfs_sb_buf_ops; extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops; extern const struct xfs_buf_ops xfs_symlink_buf_ops; diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c index 8f8af05b3f13..2e2c6716b623 100644 --- a/fs/xfs/libxfs/xfs_symlink_remote.c +++ b/fs/xfs/libxfs/xfs_symlink_remote.c @@ -31,6 +31,7 @@ #include "xfs_cksum.h" #include "xfs_trans.h" #include "xfs_buf_item.h" +#include "xfs_log.h" /* @@ -60,6 +61,7 @@ xfs_symlink_hdr_set( if (!xfs_sb_version_hascrc(&mp->m_sb)) return 0; + memset(dsl, 0, sizeof(struct xfs_dsymlink_hdr)); dsl->sl_magic = cpu_to_be32(XFS_SYMLINK_MAGIC); dsl->sl_offset = cpu_to_be32(offset); dsl->sl_bytes = cpu_to_be32(size); @@ -116,6 +118,8 @@ xfs_symlink_verify( return false; if (dsl->sl_owner == 0) return false; + if (!xfs_log_check_lsn(mp, be64_to_cpu(dsl->sl_lsn))) + return false; return true; } @@ -164,6 +168,7 @@ xfs_symlink_write_verify( } const struct xfs_buf_ops xfs_symlink_buf_ops = { + .name = "xfs_symlink", .verify_read = xfs_symlink_read_verify, .verify_write = xfs_symlink_write_verify, }; @@ -183,6 +188,7 @@ xfs_symlink_local_to_remote( if (!xfs_sb_version_hascrc(&mp->m_sb)) { bp->b_ops = NULL; memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes); + xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1); return; } @@ -198,4 +204,6 @@ xfs_symlink_local_to_remote( buf = bp->b_addr; buf += xfs_symlink_hdr_set(mp, ip->i_ino, 0, ifp->if_bytes, bp); memcpy(buf, ifp->if_u1.if_data, ifp->if_bytes); + xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsymlink_hdr) + + ifp->if_bytes - 1); } diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 4b641676f258..2d5df1f23bbc 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -37,16 +37,19 @@ STATIC struct posix_acl * xfs_acl_from_disk( - struct xfs_acl *aclp, - int max_entries) + const struct xfs_acl *aclp, + int len, + int max_entries) { struct posix_acl_entry *acl_e; struct posix_acl *acl; - struct xfs_acl_entry *ace; + const struct xfs_acl_entry *ace; unsigned int count, i; + if (len < sizeof(*aclp)) + return ERR_PTR(-EFSCORRUPTED); count = be32_to_cpu(aclp->acl_cnt); - if (count > max_entries) + if (count > max_entries || XFS_ACL_SIZE(count) != len) return ERR_PTR(-EFSCORRUPTED); acl = posix_acl_alloc(count, GFP_KERNEL); @@ -160,10 +163,11 @@ xfs_get_acl(struct inode *inode, int type) */ if (error == -ENOATTR) goto out_update_cache; + acl = ERR_PTR(error); goto out; } - acl = xfs_acl_from_disk(xfs_acl, XFS_ACL_MAX_ENTRIES(ip->i_mount)); + acl = xfs_acl_from_disk(xfs_acl, len, XFS_ACL_MAX_ENTRIES(ip->i_mount)); if (IS_ERR(acl)) goto out; @@ -248,29 +252,6 @@ xfs_set_mode(struct inode *inode, umode_t mode) return error; } -static int -xfs_acl_exists(struct inode *inode, unsigned char *name) -{ - int len = XFS_ACL_MAX_SIZE(XFS_M(inode->i_sb)); - - return (xfs_attr_get(XFS_I(inode), name, NULL, &len, - ATTR_ROOT|ATTR_KERNOVAL) == 0); -} - -int -posix_acl_access_exists(struct inode *inode) -{ - return xfs_acl_exists(inode, SGI_ACL_FILE); -} - -int -posix_acl_default_exists(struct inode *inode) -{ - if (!S_ISDIR(inode->i_mode)) - return 0; - return xfs_acl_exists(inode, SGI_ACL_DEFAULT); -} - int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index 3841b07f27bf..286fa89217f5 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -20,20 +20,18 @@ struct inode; struct posix_acl; -struct xfs_inode; #ifdef CONFIG_XFS_POSIX_ACL extern struct posix_acl *xfs_get_acl(struct inode *inode, int type); extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); -extern int posix_acl_access_exists(struct inode *inode); -extern int posix_acl_default_exists(struct inode *inode); #else static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type) { return NULL; } # define xfs_set_acl NULL -# define posix_acl_access_exists(inode) 0 -# define posix_acl_default_exists(inode) 0 #endif /* CONFIG_XFS_POSIX_ACL */ + +extern void xfs_forget_acl(struct inode *inode, const char *name, int xflags); + #endif /* __XFS_ACL_H__ */ diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 50ab2879b9da..379c089fb051 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -172,6 +172,12 @@ xfs_setfilesize_ioend( current_set_flags_nested(&tp->t_pflags, PF_FSTRANS); __sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS); + /* we abort the update if there was an IO error */ + if (ioend->io_error) { + xfs_trans_cancel(tp); + return ioend->io_error; + } + return xfs_setfilesize(ip, tp, ioend->io_offset, ioend->io_size); } @@ -212,14 +218,17 @@ xfs_end_io( ioend->io_error = -EIO; goto done; } - if (ioend->io_error) - goto done; /* * For unwritten extents we need to issue transactions to convert a * range to normal written extens after the data I/O has finished. + * Detecting and handling completion IO errors is done individually + * for each case as different cleanup operations need to be performed + * on error. */ if (ioend->io_type == XFS_IO_UNWRITTEN) { + if (ioend->io_error) + goto done; error = xfs_iomap_write_unwritten(ip, ioend->io_offset, ioend->io_size); } else if (ioend->io_append_trans) { @@ -1250,13 +1259,28 @@ xfs_vm_releasepage( * the DIO. There is only going to be one reference to the ioend and its life * cycle is constrained by the DIO completion code. hence we don't need * reference counting here. + * + * Note that for DIO, an IO to the highest supported file block offset (i.e. + * 2^63 - 1FSB bytes) will result in the offset + count overflowing a signed 64 + * bit variable. Hence if we see this overflow, we have to assume that the IO is + * extending the file size. We won't know for sure until IO completion is run + * and the actual max write offset is communicated to the IO completion + * routine. + * + * For DAX page faults, we are preparing to never see unwritten extents here, + * nor should we ever extend the inode size. Hence we will soon have nothing to + * do here for this case, ensuring we don't have to provide an IO completion + * callback to free an ioend that we don't actually need for a fault into the + * page at offset (2^63 - 1FSB) bytes. */ + static void xfs_map_direct( struct inode *inode, struct buffer_head *bh_result, struct xfs_bmbt_irec *imap, - xfs_off_t offset) + xfs_off_t offset, + bool dax_fault) { struct xfs_ioend *ioend; xfs_off_t size = bh_result->b_size; @@ -1269,6 +1293,13 @@ xfs_map_direct( trace_xfs_gbmap_direct(XFS_I(inode), offset, size, type, imap); + if (dax_fault) { + ASSERT(type == XFS_IO_OVERWRITE); + trace_xfs_gbmap_direct_none(XFS_I(inode), offset, size, type, + imap); + return; + } + if (bh_result->b_private) { ioend = bh_result->b_private; ASSERT(ioend->io_size > 0); @@ -1283,7 +1314,8 @@ xfs_map_direct( ioend->io_size, ioend->io_type, imap); } else if (type == XFS_IO_UNWRITTEN || - offset + size > i_size_read(inode)) { + offset + size > i_size_read(inode) || + offset + size < 0) { ioend = xfs_alloc_ioend(inode, type); ioend->io_offset = offset; ioend->io_size = size; @@ -1345,7 +1377,8 @@ __xfs_get_blocks( sector_t iblock, struct buffer_head *bh_result, int create, - bool direct) + bool direct, + bool dax_fault) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; @@ -1393,18 +1426,20 @@ __xfs_get_blocks( if (error) goto out_unlock; + /* for DAX, we convert unwritten extents directly */ if (create && (!nimaps || (imap.br_startblock == HOLESTARTBLOCK || - imap.br_startblock == DELAYSTARTBLOCK))) { + imap.br_startblock == DELAYSTARTBLOCK) || + (IS_DAX(inode) && ISUNWRITTEN(&imap)))) { if (direct || xfs_get_extsz_hint(ip)) { /* - * Drop the ilock in preparation for starting the block - * allocation transaction. It will be retaken - * exclusively inside xfs_iomap_write_direct for the - * actual allocation. + * xfs_iomap_write_direct() expects the shared lock. It + * is unlocked on return. */ - xfs_iunlock(ip, lockmode); + if (lockmode == XFS_ILOCK_EXCL) + xfs_ilock_demote(ip, lockmode); + error = xfs_iomap_write_direct(ip, offset, size, &imap, nimaps); if (error) @@ -1441,6 +1476,12 @@ __xfs_get_blocks( goto out_unlock; } + if (IS_DAX(inode) && create) { + ASSERT(!ISUNWRITTEN(&imap)); + /* zeroing is not needed at a higher layer */ + new = 0; + } + /* trim mapping down to size requested */ if (direct || size > (1 << inode->i_blkbits)) xfs_map_trim_size(inode, iblock, bh_result, @@ -1458,7 +1499,8 @@ __xfs_get_blocks( set_buffer_unwritten(bh_result); /* direct IO needs special help */ if (create && direct) - xfs_map_direct(inode, bh_result, &imap, offset); + xfs_map_direct(inode, bh_result, &imap, offset, + dax_fault); } /* @@ -1505,7 +1547,7 @@ xfs_get_blocks( struct buffer_head *bh_result, int create) { - return __xfs_get_blocks(inode, iblock, bh_result, create, false); + return __xfs_get_blocks(inode, iblock, bh_result, create, false, false); } int @@ -1515,7 +1557,17 @@ xfs_get_blocks_direct( struct buffer_head *bh_result, int create) { - return __xfs_get_blocks(inode, iblock, bh_result, create, true); + return __xfs_get_blocks(inode, iblock, bh_result, create, true, false); +} + +int +xfs_get_blocks_dax_fault( + struct inode *inode, + sector_t iblock, + struct buffer_head *bh_result, + int create) +{ + return __xfs_get_blocks(inode, iblock, bh_result, create, true, true); } static void @@ -1614,45 +1666,6 @@ xfs_end_io_direct_write( __xfs_end_io_direct_write(inode, ioend, offset, size); } -/* - * For DAX we need a mapping buffer callback for unwritten extent conversion - * when page faults allocate blocks and then zero them. Note that in this - * case the mapping indicated by the ioend may extend beyond EOF. We most - * definitely do not want to extend EOF here, so we trim back the ioend size to - * EOF. - */ -#ifdef CONFIG_FS_DAX -void -xfs_end_io_dax_write( - struct buffer_head *bh, - int uptodate) -{ - struct xfs_ioend *ioend = bh->b_private; - struct inode *inode = ioend->io_inode; - ssize_t size = ioend->io_size; - - ASSERT(IS_DAX(ioend->io_inode)); - - /* if there was an error zeroing, then don't convert it */ - if (!uptodate) - ioend->io_error = -EIO; - - /* - * Trim update to EOF, so we don't extend EOF during unwritten extent - * conversion of partial EOF blocks. - */ - spin_lock(&XFS_I(inode)->i_flags_lock); - if (ioend->io_offset + size > i_size_read(inode)) - size = i_size_read(inode) - ioend->io_offset; - spin_unlock(&XFS_I(inode)->i_flags_lock); - - __xfs_end_io_direct_write(inode, ioend, ioend->io_offset, size); - -} -#else -void xfs_end_io_dax_write(struct buffer_head *bh, int uptodate) { } -#endif - static inline ssize_t xfs_vm_do_dio( struct inode *inode, @@ -1904,6 +1917,7 @@ xfs_vm_readpage( struct file *unused, struct page *page) { + trace_xfs_vm_readpage(page->mapping->host, 1); return mpage_readpage(page, xfs_get_blocks); } @@ -1914,6 +1928,7 @@ xfs_vm_readpages( struct list_head *pages, unsigned nr_pages) { + trace_xfs_vm_readpages(mapping->host, nr_pages); return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks); } diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index 86afd1ac7895..f6ffc9ae5ceb 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -58,7 +58,8 @@ int xfs_get_blocks(struct inode *inode, sector_t offset, struct buffer_head *map_bh, int create); int xfs_get_blocks_direct(struct inode *inode, sector_t offset, struct buffer_head *map_bh, int create); -void xfs_end_io_dax_write(struct buffer_head *bh, int uptodate); +int xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset, + struct buffer_head *map_bh, int create); extern void xfs_count_page_state(struct page *, int *, int *); diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c index 65fb37a18e92..0ef7c2ed3f8a 100644 --- a/fs/xfs/xfs_attr_list.c +++ b/fs/xfs/xfs_attr_list.c @@ -511,7 +511,7 @@ xfs_attr_list_int( xfs_inode_t *dp = context->dp; uint lock_mode; - XFS_STATS_INC(xs_attr_list); + XFS_STATS_INC(dp->i_mount, xs_attr_list); if (XFS_FORCED_SHUTDOWN(dp->i_mount)) return -EIO; diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 3bf4ad0d19e4..45ec9e40150c 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -57,37 +57,66 @@ xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb) } /* + * Routine to zero an extent on disk allocated to the specific inode. + * + * The VFS functions take a linearised filesystem block offset, so we have to + * convert the sparse xfs fsb to the right format first. + * VFS types are real funky, too. + */ +int +xfs_zero_extent( + struct xfs_inode *ip, + xfs_fsblock_t start_fsb, + xfs_off_t count_fsb) +{ + struct xfs_mount *mp = ip->i_mount; + xfs_daddr_t sector = xfs_fsb_to_db(ip, start_fsb); + sector_t block = XFS_BB_TO_FSBT(mp, sector); + ssize_t size = XFS_FSB_TO_B(mp, count_fsb); + + if (IS_DAX(VFS_I(ip))) + return dax_clear_blocks(VFS_I(ip), block, size); + + /* + * let the block layer decide on the fastest method of + * implementing the zeroing. + */ + return sb_issue_zeroout(mp->m_super, block, count_fsb, GFP_NOFS); + +} + +/* * Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi * caller. Frees all the extents that need freeing, which must be done * last due to locking considerations. We never free any extents in * the first transaction. * - * Return 1 if the given transaction was committed and a new one - * started, and 0 otherwise in the committed parameter. + * If an inode *ip is provided, rejoin it to the transaction if + * the transaction was committed. */ int /* error */ xfs_bmap_finish( struct xfs_trans **tp, /* transaction pointer addr */ struct xfs_bmap_free *flist, /* i/o: list extents to free */ - int *committed)/* xact committed or not */ + struct xfs_inode *ip) { struct xfs_efd_log_item *efd; /* extent free data */ struct xfs_efi_log_item *efi; /* extent free intention */ int error; /* error return value */ + int committed;/* xact committed or not */ struct xfs_bmap_free_item *free; /* free extent item */ struct xfs_bmap_free_item *next; /* next item on free list */ ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES); - if (flist->xbf_count == 0) { - *committed = 0; + if (flist->xbf_count == 0) return 0; - } + efi = xfs_trans_get_efi(*tp, flist->xbf_count); for (free = flist->xbf_first; free; free = free->xbfi_next) xfs_trans_log_efi_extent(*tp, efi, free->xbfi_startblock, free->xbfi_blockcount); - error = __xfs_trans_roll(tp, NULL, committed); + error = __xfs_trans_roll(tp, ip, &committed); if (error) { /* * If the transaction was committed, drop the EFD reference @@ -99,16 +128,13 @@ xfs_bmap_finish( * transaction so we should return committed=1 even though we're * returning an error. */ - if (*committed) { + if (committed) { xfs_efi_release(efi); xfs_force_shutdown((*tp)->t_mountp, (error == -EFSCORRUPTED) ? SHUTDOWN_CORRUPT_INCORE : SHUTDOWN_META_IO_ERROR); - } else { - *committed = 1; } - return error; } @@ -229,6 +255,13 @@ xfs_bmap_rtalloc( xfs_trans_mod_dquot_byino(ap->tp, ap->ip, ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT : XFS_TRANS_DQ_RTBCOUNT, (long) ralen); + + /* Zero the extent if we were asked to do so */ + if (ap->userdata & XFS_ALLOC_USERDATA_ZERO) { + error = xfs_zero_extent(ap->ip, ap->blkno, ap->length); + if (error) + return error; + } } else { ap->length = 0; } @@ -933,7 +966,6 @@ xfs_alloc_file_space( xfs_bmbt_irec_t imaps[1], *imapp; xfs_bmap_free_t free_list; uint qblocks, resblks, resrtextents; - int committed; int error; trace_xfs_alloc_file_space(ip); @@ -1027,24 +1059,21 @@ xfs_alloc_file_space( xfs_bmap_init(&free_list, &firstfsb); error = xfs_bmapi_write(tp, ip, startoffset_fsb, allocatesize_fsb, alloc_type, &firstfsb, - 0, imapp, &nimaps, &free_list); - if (error) { + resblks, imapp, &nimaps, &free_list); + if (error) goto error0; - } /* * Complete the transaction */ - error = xfs_bmap_finish(&tp, &free_list, &committed); - if (error) { + error = xfs_bmap_finish(&tp, &free_list, NULL); + if (error) goto error0; - } error = xfs_trans_commit(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); - if (error) { + if (error) break; - } allocated_fsb = imapp->br_blockcount; @@ -1170,7 +1199,6 @@ xfs_free_file_space( xfs_off_t offset, xfs_off_t len) { - int committed; int done; xfs_fileoff_t endoffset_fsb; int error; @@ -1310,17 +1338,15 @@ xfs_free_file_space( error = xfs_bunmapi(tp, ip, startoffset_fsb, endoffset_fsb - startoffset_fsb, 0, 2, &firstfsb, &free_list, &done); - if (error) { + if (error) goto error0; - } /* * complete the transaction */ - error = xfs_bmap_finish(&tp, &free_list, &committed); - if (error) { + error = xfs_bmap_finish(&tp, &free_list, NULL); + if (error) goto error0; - } error = xfs_trans_commit(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); @@ -1398,7 +1424,6 @@ xfs_shift_file_space( int error; struct xfs_bmap_free free_list; xfs_fsblock_t first_block; - int committed; xfs_fileoff_t stop_fsb; xfs_fileoff_t next_fsb; xfs_fileoff_t shift_fsb; @@ -1490,7 +1515,7 @@ xfs_shift_file_space( if (error) goto out_bmap_cancel; - error = xfs_bmap_finish(&tp, &free_list, &committed); + error = xfs_bmap_finish(&tp, &free_list, NULL); if (error) goto out_bmap_cancel; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 8ecffb35935b..daed4bfb85b2 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -201,7 +201,7 @@ _xfs_buf_alloc( atomic_set(&bp->b_pin_count, 0); init_waitqueue_head(&bp->b_waiters); - XFS_STATS_INC(xb_create); + XFS_STATS_INC(target->bt_mount, xb_create); trace_xfs_buf_init(bp, _RET_IP_); return bp; @@ -354,15 +354,16 @@ retry: */ if (!(++retries % 100)) xfs_err(NULL, - "possible memory allocation deadlock in %s (mode:0x%x)", + "%s(%u) possible memory allocation deadlock in %s (mode:0x%x)", + current->comm, current->pid, __func__, gfp_mask); - XFS_STATS_INC(xb_page_retries); + XFS_STATS_INC(bp->b_target->bt_mount, xb_page_retries); congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry; } - XFS_STATS_INC(xb_page_found); + XFS_STATS_INC(bp->b_target->bt_mount, xb_page_found); nbytes = min_t(size_t, size, PAGE_SIZE - offset); size -= nbytes; @@ -516,7 +517,7 @@ _xfs_buf_find( new_bp->b_pag = pag; spin_unlock(&pag->pag_buf_lock); } else { - XFS_STATS_INC(xb_miss_locked); + XFS_STATS_INC(btp->bt_mount, xb_miss_locked); spin_unlock(&pag->pag_buf_lock); xfs_perag_put(pag); } @@ -529,11 +530,11 @@ found: if (!xfs_buf_trylock(bp)) { if (flags & XBF_TRYLOCK) { xfs_buf_rele(bp); - XFS_STATS_INC(xb_busy_locked); + XFS_STATS_INC(btp->bt_mount, xb_busy_locked); return NULL; } xfs_buf_lock(bp); - XFS_STATS_INC(xb_get_locked_waited); + XFS_STATS_INC(btp->bt_mount, xb_get_locked_waited); } /* @@ -549,7 +550,7 @@ found: } trace_xfs_buf_find(bp, flags, _RET_IP_); - XFS_STATS_INC(xb_get_locked); + XFS_STATS_INC(btp->bt_mount, xb_get_locked); return bp; } @@ -603,7 +604,14 @@ found: } } - XFS_STATS_INC(xb_get); + /* + * Clear b_error if this is a lookup from a caller that doesn't expect + * valid data to be found in the buffer. + */ + if (!(flags & XBF_READ)) + xfs_buf_ioerror(bp, 0); + + XFS_STATS_INC(target->bt_mount, xb_get); trace_xfs_buf_get(bp, flags, _RET_IP_); return bp; } @@ -643,7 +651,7 @@ xfs_buf_read_map( trace_xfs_buf_read(bp, flags, _RET_IP_); if (!XFS_BUF_ISDONE(bp)) { - XFS_STATS_INC(xb_get_read); + XFS_STATS_INC(target->bt_mount, xb_get_read); bp->b_ops = ops; _xfs_buf_read(bp, flags); } else if (flags & XBF_ASYNC) { @@ -1044,7 +1052,7 @@ xfs_buf_ioend_work( xfs_buf_ioend(bp); } -void +static void xfs_buf_ioend_async( struct xfs_buf *bp) { @@ -1631,13 +1639,9 @@ xfs_setsize_buftarg( btp->bt_meta_sectormask = sectorsize - 1; if (set_blocksize(btp->bt_bdev, sectorsize)) { - char name[BDEVNAME_SIZE]; - - bdevname(btp->bt_bdev, name); - xfs_warn(btp->bt_mount, - "Cannot set_blocksize to %u on device %s", - sectorsize, name); + "Cannot set_blocksize to %u on device %pg", + sectorsize, btp->bt_bdev); return -EINVAL; } diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index c79b717d9b88..c75721acd867 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -132,6 +132,7 @@ struct xfs_buf_map { struct xfs_buf_map (map) = { .bm_bn = (blkno), .bm_len = (numblk) }; struct xfs_buf_ops { + char *name; void (*verify_read)(struct xfs_buf *); void (*verify_write)(struct xfs_buf *); }; diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c index a989a9c7edb7..642d55d10075 100644 --- a/fs/xfs/xfs_dir2_readdir.c +++ b/fs/xfs/xfs_dir2_readdir.c @@ -666,7 +666,7 @@ xfs_readdir( return -EIO; ASSERT(S_ISDIR(dp->i_d.di_mode)); - XFS_STATS_INC(xs_dir_getdents); + XFS_STATS_INC(dp->i_mount, xs_dir_getdents); args.dp = dp; args.geo = dp->i_mount->m_dir_geo; diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 30cb3afb67f0..9c44d38dcd1f 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -75,9 +75,9 @@ xfs_qm_dqdestroy( ASSERT(list_empty(&dqp->q_lru)); mutex_destroy(&dqp->q_qlock); - kmem_zone_free(xfs_qm_dqzone, dqp); - XFS_STATS_DEC(xs_qm_dquot); + XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot); + kmem_zone_free(xfs_qm_dqzone, dqp); } /* @@ -306,7 +306,7 @@ xfs_qm_dqalloc( xfs_fsblock_t firstblock; xfs_bmap_free_t flist; xfs_bmbt_irec_t map; - int nmaps, error, committed; + int nmaps, error; xfs_buf_t *bp; xfs_trans_t *tp = *tpp; @@ -379,11 +379,12 @@ xfs_qm_dqalloc( xfs_trans_bhold(tp, bp); - if ((error = xfs_bmap_finish(tpp, &flist, &committed))) { + error = xfs_bmap_finish(tpp, &flist, NULL); + if (error) goto error1; - } - if (committed) { + /* Transaction was committed? */ + if (*tpp != tp) { tp = *tpp; xfs_trans_bjoin(tp, bp); } else { @@ -393,9 +394,9 @@ xfs_qm_dqalloc( *O_bpp = bp; return 0; - error1: +error1: xfs_bmap_cancel(&flist); - error0: +error0: xfs_iunlock(quotip, XFS_ILOCK_EXCL); return error; @@ -605,7 +606,7 @@ xfs_qm_dqread( break; } - XFS_STATS_INC(xs_qm_dquot); + XFS_STATS_INC(mp, xs_qm_dquot); trace_xfs_dqread(dqp); @@ -747,12 +748,12 @@ restart: mutex_unlock(&qi->qi_tree_lock); trace_xfs_dqget_hit(dqp); - XFS_STATS_INC(xs_qm_dqcachehits); + XFS_STATS_INC(mp, xs_qm_dqcachehits); *O_dqpp = dqp; return 0; } mutex_unlock(&qi->qi_tree_lock); - XFS_STATS_INC(xs_qm_dqcachemisses); + XFS_STATS_INC(mp, xs_qm_dqcachemisses); /* * Dquot cache miss. We don't want to keep the inode lock across @@ -806,7 +807,7 @@ restart: mutex_unlock(&qi->qi_tree_lock); trace_xfs_dqget_dup(dqp); xfs_qm_dqdestroy(dqp); - XFS_STATS_INC(xs_qm_dquot_dups); + XFS_STATS_INC(mp, xs_qm_dquot_dups); goto restart; } @@ -846,7 +847,7 @@ xfs_qm_dqput( trace_xfs_dqput_free(dqp); if (list_lru_add(&qi->qi_lru, &dqp->q_lru)) - XFS_STATS_INC(xs_qm_dquot_unused); + XFS_STATS_INC(dqp->q_mount, xs_qm_dquot_unused); } xfs_dqunlock(dqp); } diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index 74d0e5966ebc..88693a98fac5 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -164,9 +164,9 @@ xfs_verifier_error( { struct xfs_mount *mp = bp->b_target->bt_mount; - xfs_alert(mp, "Metadata %s detected at %pF, block 0x%llx", + xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx", bp->b_error == -EFSBADCRC ? "CRC error" : "corruption", - __return_address, bp->b_bn); + __return_address, bp->b_ops->name, bp->b_bn); xfs_alert(mp, "Unmount and run xfs_repair"); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index e78feb400e22..ebe9b8290a70 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -242,19 +242,30 @@ xfs_file_fsync( } /* - * All metadata updates are logged, which means that we just have - * to flush the log up to the latest LSN that touched the inode. + * All metadata updates are logged, which means that we just have to + * flush the log up to the latest LSN that touched the inode. If we have + * concurrent fsync/fdatasync() calls, we need them to all block on the + * log force before we clear the ili_fsync_fields field. This ensures + * that we don't get a racing sync operation that does not wait for the + * metadata to hit the journal before returning. If we race with + * clearing the ili_fsync_fields, then all that will happen is the log + * force will do nothing as the lsn will already be on disk. We can't + * race with setting ili_fsync_fields because that is done under + * XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared + * until after the ili_fsync_fields is cleared. */ xfs_ilock(ip, XFS_ILOCK_SHARED); if (xfs_ipincount(ip)) { if (!datasync || - (ip->i_itemp->ili_fields & ~XFS_ILOG_TIMESTAMP)) + (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)) lsn = ip->i_itemp->ili_last_lsn; } - xfs_iunlock(ip, XFS_ILOCK_SHARED); - if (lsn) + if (lsn) { error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed); + ip->i_itemp->ili_fsync_fields = 0; + } + xfs_iunlock(ip, XFS_ILOCK_SHARED); /* * If we only have a single device, and the log force about was @@ -287,7 +298,7 @@ xfs_file_read_iter( xfs_fsize_t n; loff_t pos = iocb->ki_pos; - XFS_STATS_INC(xs_read_calls); + XFS_STATS_INC(mp, xs_read_calls); if (unlikely(iocb->ki_flags & IOCB_DIRECT)) ioflags |= XFS_IO_ISDIRECT; @@ -365,7 +376,7 @@ xfs_file_read_iter( ret = generic_file_read_iter(iocb, to); if (ret > 0) - XFS_STATS_ADD(xs_read_bytes, ret); + XFS_STATS_ADD(mp, xs_read_bytes, ret); xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); return ret; @@ -383,7 +394,7 @@ xfs_file_splice_read( int ioflags = 0; ssize_t ret; - XFS_STATS_INC(xs_read_calls); + XFS_STATS_INC(ip->i_mount, xs_read_calls); if (infilp->f_mode & FMODE_NOCMTIME) ioflags |= XFS_IO_INVIS; @@ -391,19 +402,26 @@ xfs_file_splice_read( if (XFS_FORCED_SHUTDOWN(ip->i_mount)) return -EIO; - xfs_rw_ilock(ip, XFS_IOLOCK_SHARED); - trace_xfs_file_splice_read(ip, count, *ppos, ioflags); - /* for dax, we need to avoid the page cache */ - if (IS_DAX(VFS_I(ip))) - ret = default_file_splice_read(infilp, ppos, pipe, count, flags); - else - ret = generic_file_splice_read(infilp, ppos, pipe, count, flags); - if (ret > 0) - XFS_STATS_ADD(xs_read_bytes, ret); + /* + * DAX inodes cannot ues the page cache for splice, so we have to push + * them through the VFS IO path. This means it goes through + * ->read_iter, which for us takes the XFS_IOLOCK_SHARED. Hence we + * cannot lock the splice operation at this level for DAX inodes. + */ + if (IS_DAX(VFS_I(ip))) { + ret = default_file_splice_read(infilp, ppos, pipe, count, + flags); + goto out; + } + xfs_rw_ilock(ip, XFS_IOLOCK_SHARED); + ret = generic_file_splice_read(infilp, ppos, pipe, count, flags); xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); +out: + if (ret > 0) + XFS_STATS_ADD(ip->i_mount, xs_read_bytes, ret); return ret; } @@ -482,6 +500,8 @@ xfs_zero_eof( ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(offset > isize); + trace_xfs_zero_eof(ip, isize, offset - isize); + /* * First handle zeroing the block on which isize resides. * @@ -574,6 +594,7 @@ xfs_file_aio_write_checks( struct xfs_inode *ip = XFS_I(inode); ssize_t error = 0; size_t count = iov_iter_count(from); + bool drained_dio = false; restart: error = generic_write_checks(iocb, from); @@ -611,12 +632,13 @@ restart: bool zero = false; spin_unlock(&ip->i_flags_lock); - if (*iolock == XFS_IOLOCK_SHARED) { - xfs_rw_iunlock(ip, *iolock); - *iolock = XFS_IOLOCK_EXCL; - xfs_rw_ilock(ip, *iolock); - iov_iter_reexpand(from, count); - + if (!drained_dio) { + if (*iolock == XFS_IOLOCK_SHARED) { + xfs_rw_iunlock(ip, *iolock); + *iolock = XFS_IOLOCK_EXCL; + xfs_rw_ilock(ip, *iolock); + iov_iter_reexpand(from, count); + } /* * We now have an IO submission barrier in place, but * AIO can do EOF updates during IO completion and hence @@ -626,6 +648,7 @@ restart: * no-op. */ inode_dio_wait(inode); + drained_dio = true; goto restart; } error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero); @@ -867,7 +890,7 @@ xfs_file_write_iter( ssize_t ret; size_t ocount = iov_iter_count(from); - XFS_STATS_INC(xs_write_calls); + XFS_STATS_INC(ip->i_mount, xs_write_calls); if (ocount == 0) return 0; @@ -883,7 +906,7 @@ xfs_file_write_iter( if (ret > 0) { ssize_t err; - XFS_STATS_ADD(xs_write_bytes, ret); + XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret); /* Handle various SYNC-type writes */ err = generic_write_sync(file, iocb->ki_pos - ret, ret); @@ -1477,7 +1500,7 @@ xfs_file_llseek( * * mmap_sem (MM) * sb_start_pagefault(vfs, freeze) - * i_mmap_lock (XFS - truncate serialisation) + * i_mmaplock (XFS - truncate serialisation) * page_lock (MM) * i_lock (XFS - extent map serialisation) */ @@ -1503,10 +1526,9 @@ xfs_filemap_page_mkwrite( xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); if (IS_DAX(inode)) { - ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_direct, - xfs_end_io_dax_write); + ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL); } else { - ret = __block_page_mkwrite(vma, vmf, xfs_get_blocks); + ret = block_page_mkwrite(vma, vmf, xfs_get_blocks); ret = block_page_mkwrite_return(ret); } @@ -1538,7 +1560,7 @@ xfs_filemap_fault( * changes to xfs_get_blocks_direct() to map unwritten extent * ioend for conversion on read-only mappings. */ - ret = __dax_fault(vma, vmf, xfs_get_blocks_direct, NULL); + ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL); } else ret = filemap_fault(vma, vmf); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); @@ -1546,6 +1568,13 @@ xfs_filemap_fault( return ret; } +/* + * Similar to xfs_filemap_fault(), the DAX fault path can call into here on + * both read and write faults. Hence we need to handle both cases. There is no + * ->pmd_mkwrite callout for huge pages, so we have a single function here to + * handle both cases here. @flags carries the information on the type of fault + * occuring. + */ STATIC int xfs_filemap_pmd_fault( struct vm_area_struct *vma, @@ -1562,22 +1591,62 @@ xfs_filemap_pmd_fault( trace_xfs_filemap_pmd_fault(ip); - sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); + if (flags & FAULT_FLAG_WRITE) { + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + } + xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_direct, - xfs_end_io_dax_write); + ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault, + NULL); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - sb_end_pagefault(inode->i_sb); + + if (flags & FAULT_FLAG_WRITE) + sb_end_pagefault(inode->i_sb); return ret; } +/* + * pfn_mkwrite was originally inteneded to ensure we capture time stamp + * updates on write faults. In reality, it's need to serialise against + * truncate similar to page_mkwrite. Hence we open-code dax_pfn_mkwrite() + * here and cycle the XFS_MMAPLOCK_SHARED to ensure we serialise the fault + * barrier in place. + */ +static int +xfs_filemap_pfn_mkwrite( + struct vm_area_struct *vma, + struct vm_fault *vmf) +{ + + struct inode *inode = file_inode(vma->vm_file); + struct xfs_inode *ip = XFS_I(inode); + int ret = VM_FAULT_NOPAGE; + loff_t size; + + trace_xfs_filemap_pfn_mkwrite(ip); + + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + + /* check if the faulting page hasn't raced with truncate */ + xfs_ilock(ip, XFS_MMAPLOCK_SHARED); + size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (vmf->pgoff >= size) + ret = VM_FAULT_SIGBUS; + xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); + sb_end_pagefault(inode->i_sb); + return ret; + +} + static const struct vm_operations_struct xfs_file_vm_ops = { .fault = xfs_filemap_fault, .pmd_fault = xfs_filemap_pmd_fault, .map_pages = filemap_map_pages, .page_mkwrite = xfs_filemap_page_mkwrite, + .pfn_mkwrite = xfs_filemap_pfn_mkwrite, }; STATIC int diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 0a326bd64d4e..d7a490f24ead 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -63,7 +63,7 @@ xfs_inode_alloc( return NULL; } - XFS_STATS_INC(vn_active); + XFS_STATS_INC(mp, vn_active); ASSERT(atomic_read(&ip->i_pincount) == 0); ASSERT(!spin_is_locked(&ip->i_flags_lock)); ASSERT(!xfs_isiflocked(ip)); @@ -129,7 +129,7 @@ xfs_inode_free( /* asserts to verify all state is correct here */ ASSERT(atomic_read(&ip->i_pincount) == 0); ASSERT(!xfs_isiflocked(ip)); - XFS_STATS_DEC(vn_active); + XFS_STATS_DEC(ip->i_mount, vn_active); call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback); } @@ -159,7 +159,7 @@ xfs_iget_cache_hit( spin_lock(&ip->i_flags_lock); if (ip->i_ino != ino) { trace_xfs_iget_skip(ip); - XFS_STATS_INC(xs_ig_frecycle); + XFS_STATS_INC(mp, xs_ig_frecycle); error = -EAGAIN; goto out_error; } @@ -177,7 +177,7 @@ xfs_iget_cache_hit( */ if (ip->i_flags & (XFS_INEW|XFS_IRECLAIM)) { trace_xfs_iget_skip(ip); - XFS_STATS_INC(xs_ig_frecycle); + XFS_STATS_INC(mp, xs_ig_frecycle); error = -EAGAIN; goto out_error; } @@ -259,7 +259,7 @@ xfs_iget_cache_hit( xfs_ilock(ip, lock_flags); xfs_iflags_clear(ip, XFS_ISTALE | XFS_IDONTCACHE); - XFS_STATS_INC(xs_ig_found); + XFS_STATS_INC(mp, xs_ig_found); return 0; @@ -342,7 +342,7 @@ xfs_iget_cache_miss( error = radix_tree_insert(&pag->pag_ici_root, agino, ip); if (unlikely(error)) { WARN_ON(error != -EEXIST); - XFS_STATS_INC(xs_ig_dup); + XFS_STATS_INC(mp, xs_ig_dup); error = -EAGAIN; goto out_preload_end; } @@ -412,7 +412,7 @@ xfs_iget( if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount) return -EINVAL; - XFS_STATS_INC(xs_ig_attempts); + XFS_STATS_INC(mp, xs_ig_attempts); /* get the perag structure and ensure that it's inode capable */ pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino)); @@ -429,7 +429,7 @@ again: goto out_error_or_again; } else { rcu_read_unlock(); - XFS_STATS_INC(xs_ig_missed); + XFS_STATS_INC(mp, xs_ig_missed); error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip, flags, lock_flags); @@ -965,7 +965,7 @@ reclaim: xfs_ifunlock(ip); xfs_iunlock(ip, XFS_ILOCK_EXCL); - XFS_STATS_INC(xs_ig_reclaims); + XFS_STATS_INC(ip->i_mount, xs_ig_reclaims); /* * Remove the inode from the per-AG radix tree. * diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index dc40a6d5ae0d..ae3758a90ed6 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1143,7 +1143,6 @@ xfs_create( xfs_bmap_free_t free_list; xfs_fsblock_t first_block; bool unlock_dp_on_error = false; - int committed; prid_t prid; struct xfs_dquot *udqp = NULL; struct xfs_dquot *gdqp = NULL; @@ -1226,7 +1225,7 @@ xfs_create( * pointing to itself. */ error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, - prid, resblks > 0, &ip, &committed); + prid, resblks > 0, &ip, NULL); if (error) goto out_trans_cancel; @@ -1275,7 +1274,7 @@ xfs_create( */ xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp); - error = xfs_bmap_finish(&tp, &free_list, &committed); + error = xfs_bmap_finish(&tp, &free_list, NULL); if (error) goto out_bmap_cancel; @@ -1427,7 +1426,6 @@ xfs_link( int error; xfs_bmap_free_t free_list; xfs_fsblock_t first_block; - int committed; int resblks; trace_xfs_link(tdp, target_name); @@ -1502,11 +1500,10 @@ xfs_link( * link transaction goes to disk before returning to * the user. */ - if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) { + if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) xfs_trans_set_sync(tp); - } - error = xfs_bmap_finish (&tp, &free_list, &committed); + error = xfs_bmap_finish(&tp, &free_list, NULL); if (error) { xfs_bmap_cancel(&free_list); goto error_return; @@ -1555,7 +1552,6 @@ xfs_itruncate_extents( xfs_fileoff_t first_unmap_block; xfs_fileoff_t last_block; xfs_filblks_t unmap_len; - int committed; int error = 0; int done = 0; @@ -1601,9 +1597,7 @@ xfs_itruncate_extents( * Duplicate the transaction that has the permanent * reservation and commit the old transaction. */ - error = xfs_bmap_finish(&tp, &free_list, &committed); - if (committed) - xfs_trans_ijoin(tp, ip, 0); + error = xfs_bmap_finish(&tp, &free_list, ip); if (error) goto out_bmap_cancel; @@ -1774,7 +1768,6 @@ xfs_inactive_ifree( { xfs_bmap_free_t free_list; xfs_fsblock_t first_block; - int committed; struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; int error; @@ -1841,7 +1834,7 @@ xfs_inactive_ifree( * Just ignore errors at this point. There is nothing we can do except * to try to keep going. Make sure it's not a silent error. */ - error = xfs_bmap_finish(&tp, &free_list, &committed); + error = xfs_bmap_finish(&tp, &free_list, NULL); if (error) { xfs_notice(mp, "%s: xfs_bmap_finish returned error %d", __func__, error); @@ -2365,6 +2358,7 @@ retry: iip->ili_last_fields = iip->ili_fields; iip->ili_fields = 0; + iip->ili_fsync_fields = 0; iip->ili_logged = 1; xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn, &iip->ili_item.li_lsn); @@ -2522,7 +2516,6 @@ xfs_remove( int error = 0; xfs_bmap_free_t free_list; xfs_fsblock_t first_block; - int committed; uint resblks; trace_xfs_remove(dp, name); @@ -2623,7 +2616,7 @@ xfs_remove( if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) xfs_trans_set_sync(tp); - error = xfs_bmap_finish(&tp, &free_list, &committed); + error = xfs_bmap_finish(&tp, &free_list, NULL); if (error) goto out_bmap_cancel; @@ -2700,7 +2693,6 @@ xfs_finish_rename( struct xfs_trans *tp, struct xfs_bmap_free *free_list) { - int committed = 0; int error; /* @@ -2710,7 +2702,7 @@ xfs_finish_rename( if (tp->t_mountp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) xfs_trans_set_sync(tp); - error = xfs_bmap_finish(&tp, free_list, &committed); + error = xfs_bmap_finish(&tp, free_list, NULL); if (error) { xfs_bmap_cancel(free_list); xfs_trans_cancel(tp); @@ -3271,8 +3263,8 @@ xfs_iflush_cluster( } if (clcount) { - XFS_STATS_INC(xs_icluster_flushcnt); - XFS_STATS_ADD(xs_icluster_flushinode, clcount); + XFS_STATS_INC(mp, xs_icluster_flushcnt); + XFS_STATS_ADD(mp, xs_icluster_flushinode, clcount); } out_free: @@ -3345,7 +3337,7 @@ xfs_iflush( struct xfs_dinode *dip; int error; - XFS_STATS_INC(xs_iflush_count); + XFS_STATS_INC(mp, xs_iflush_count); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); ASSERT(xfs_isiflocked(ip)); @@ -3560,6 +3552,7 @@ xfs_iflush_int( */ iip->ili_last_fields = iip->ili_fields; iip->ili_fields = 0; + iip->ili_fsync_fields = 0; iip->ili_logged = 1; xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn, diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 62bd80f4edd9..d14b12b8cfef 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -719,6 +719,7 @@ xfs_iflush_abort( * attempted. */ iip->ili_fields = 0; + iip->ili_fsync_fields = 0; } /* * Release the inode's flush lock since we're done with it. diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h index 488d81254e28..4c7722e325b3 100644 --- a/fs/xfs/xfs_inode_item.h +++ b/fs/xfs/xfs_inode_item.h @@ -34,6 +34,7 @@ typedef struct xfs_inode_log_item { unsigned short ili_logged; /* flushed logged data */ unsigned int ili_last_fields; /* fields when flushed */ unsigned int ili_fields; /* fields to be logged */ + unsigned int ili_fsync_fields; /* logged since last fsync */ } xfs_inode_log_item_t; static inline int xfs_inode_clean(xfs_inode_t *ip) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index ea7d85af5310..d42738deec6d 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -40,6 +40,7 @@ #include "xfs_symlink.h" #include "xfs_trans.h" #include "xfs_pnfs.h" +#include "xfs_acl.h" #include <linux/capability.h> #include <linux/dcache.h> @@ -411,7 +412,7 @@ xfs_attrlist_by_handle( if (copy_from_user(&al_hreq, arg, sizeof(xfs_fsop_attrlist_handlereq_t))) return -EFAULT; if (al_hreq.buflen < sizeof(struct attrlist) || - al_hreq.buflen > XATTR_LIST_MAX) + al_hreq.buflen > XFS_XATTR_LIST_MAX) return -EINVAL; /* @@ -455,7 +456,7 @@ xfs_attrmulti_attr_get( unsigned char *kbuf; int error = -EFAULT; - if (*len > XATTR_SIZE_MAX) + if (*len > XFS_XATTR_SIZE_MAX) return -EINVAL; kbuf = kmem_zalloc_large(*len, KM_SLEEP); if (!kbuf) @@ -482,17 +483,22 @@ xfs_attrmulti_attr_set( __uint32_t flags) { unsigned char *kbuf; + int error; if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; - if (len > XATTR_SIZE_MAX) + if (len > XFS_XATTR_SIZE_MAX) return -EINVAL; kbuf = memdup_user(ubuf, len); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); - return xfs_attr_set(XFS_I(inode), name, kbuf, len, flags); + error = xfs_attr_set(XFS_I(inode), name, kbuf, len, flags); + if (!error) + xfs_forget_acl(inode, name, flags); + kfree(kbuf); + return error; } int @@ -501,9 +507,14 @@ xfs_attrmulti_attr_remove( unsigned char *name, __uint32_t flags) { + int error; + if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; - return xfs_attr_remove(XFS_I(inode), name, flags); + error = xfs_attr_remove(XFS_I(inode), name, flags); + if (!error) + xfs_forget_acl(inode, name, flags); + return error; } STATIC int @@ -1028,7 +1039,7 @@ xfs_ioctl_setattr_xflags( xfs_diflags_to_linux(ip); xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - XFS_STATS_INC(xs_ig_attrchg); + XFS_STATS_INC(mp, xs_ig_attrchg); return 0; } diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index b88bdc85dd3d..1a05d8ae327d 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -356,7 +356,7 @@ xfs_compat_attrlist_by_handle( sizeof(compat_xfs_fsop_attrlist_handlereq_t))) return -EFAULT; if (al_hreq.buflen < sizeof(struct attrlist) || - al_hreq.buflen > XATTR_LIST_MAX) + al_hreq.buflen > XFS_XATTR_LIST_MAX) return -EINVAL; /* diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 1f86033171c8..d81bdc080370 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -129,22 +129,31 @@ xfs_iomap_write_direct( xfs_trans_t *tp; xfs_bmap_free_t free_list; uint qblocks, resblks, resrtextents; - int committed; int error; - - error = xfs_qm_dqattach(ip, 0); - if (error) - return error; + int lockmode; + int bmapi_flags = XFS_BMAPI_PREALLOC; rt = XFS_IS_REALTIME_INODE(ip); extsz = xfs_get_extsz_hint(ip); + lockmode = XFS_ILOCK_SHARED; /* locked by caller */ + + ASSERT(xfs_isilocked(ip, lockmode)); offset_fsb = XFS_B_TO_FSBT(mp, offset); last_fsb = XFS_B_TO_FSB(mp, ((xfs_ufsize_t)(offset + count))); if ((offset + count) > XFS_ISIZE(ip)) { + /* + * Assert that the in-core extent list is present since this can + * call xfs_iread_extents() and we only have the ilock shared. + * This should be safe because the lock was held around a bmapi + * call in the caller and we only need it to access the in-core + * list. + */ + ASSERT(XFS_IFORK_PTR(ip, XFS_DATA_FORK)->if_flags & + XFS_IFEXTENTS); error = xfs_iomap_eof_align_last_fsb(mp, ip, extsz, &last_fsb); if (error) - return error; + goto out_unlock; } else { if (nmaps && (imap->br_startblock == HOLESTARTBLOCK)) last_fsb = MIN(last_fsb, (xfs_fileoff_t) @@ -174,9 +183,40 @@ xfs_iomap_write_direct( } /* + * Drop the shared lock acquired by the caller, attach the dquot if + * necessary and move on to transaction setup. + */ + xfs_iunlock(ip, lockmode); + error = xfs_qm_dqattach(ip, 0); + if (error) + return error; + + /* * Allocate and setup the transaction */ tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT); + + /* + * For DAX, we do not allocate unwritten extents, but instead we zero + * the block before we commit the transaction. Ideally we'd like to do + * this outside the transaction context, but if we commit and then crash + * we may not have zeroed the blocks and this will be exposed on + * recovery of the allocation. Hence we must zero before commit. + * + * Further, if we are mapping unwritten extents here, we need to zero + * and convert them to written so that we don't need an unwritten extent + * callback for DAX. This also means that we need to be able to dip into + * the reserve block pool for bmbt block allocation if there is no space + * left but we need to do unwritten extent conversion. + */ + + if (IS_DAX(VFS_I(ip))) { + bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO; + if (ISUNWRITTEN(imap)) { + tp->t_flags |= XFS_TRANS_RESERVE; + resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1; + } + } error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write, resblks, resrtextents); /* @@ -187,7 +227,8 @@ xfs_iomap_write_direct( return error; } - xfs_ilock(ip, XFS_ILOCK_EXCL); + lockmode = XFS_ILOCK_EXCL; + xfs_ilock(ip, lockmode); error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks, 0, quota_flag); if (error) @@ -202,17 +243,18 @@ xfs_iomap_write_direct( xfs_bmap_init(&free_list, &firstfsb); nimaps = 1; error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, - XFS_BMAPI_PREALLOC, &firstfsb, 0, - imap, &nimaps, &free_list); + bmapi_flags, &firstfsb, resblks, imap, + &nimaps, &free_list); if (error) goto out_bmap_cancel; /* * Complete the transaction */ - error = xfs_bmap_finish(&tp, &free_list, &committed); + error = xfs_bmap_finish(&tp, &free_list, NULL); if (error) goto out_bmap_cancel; + error = xfs_trans_commit(tp); if (error) goto out_unlock; @@ -229,7 +271,7 @@ xfs_iomap_write_direct( error = xfs_alert_fsblock_zero(ip, imap); out_unlock: - xfs_iunlock(ip, XFS_ILOCK_EXCL); + xfs_iunlock(ip, lockmode); return error; out_bmap_cancel: @@ -655,7 +697,7 @@ xfs_iomap_write_allocate( xfs_bmap_free_t free_list; xfs_filblks_t count_fsb; xfs_trans_t *tp; - int nimaps, committed; + int nimaps; int error = 0; int nres; @@ -670,7 +712,7 @@ xfs_iomap_write_allocate( count_fsb = imap->br_blockcount; map_start_fsb = imap->br_startoff; - XFS_STATS_ADD(xs_xstrat_bytes, XFS_FSB_TO_B(mp, count_fsb)); + XFS_STATS_ADD(mp, xs_xstrat_bytes, XFS_FSB_TO_B(mp, count_fsb)); while (count_fsb != 0) { /* @@ -750,13 +792,13 @@ xfs_iomap_write_allocate( * pointer that the caller gave to us. */ error = xfs_bmapi_write(tp, ip, map_start_fsb, - count_fsb, 0, - &first_block, 1, - imap, &nimaps, &free_list); + count_fsb, 0, &first_block, + nres, imap, &nimaps, + &free_list); if (error) goto trans_cancel; - error = xfs_bmap_finish(&tp, &free_list, &committed); + error = xfs_bmap_finish(&tp, &free_list, NULL); if (error) goto trans_cancel; @@ -777,7 +819,7 @@ xfs_iomap_write_allocate( if ((offset_fsb >= imap->br_startoff) && (offset_fsb < (imap->br_startoff + imap->br_blockcount))) { - XFS_STATS_INC(xs_xstrat_quick); + XFS_STATS_INC(mp, xs_xstrat_quick); return 0; } @@ -814,7 +856,6 @@ xfs_iomap_write_unwritten( xfs_bmap_free_t free_list; xfs_fsize_t i_size; uint resblks; - int committed; int error; trace_xfs_unwritten_convert(ip, offset, count); @@ -866,8 +907,8 @@ xfs_iomap_write_unwritten( xfs_bmap_init(&free_list, &firstfsb); nimaps = 1; error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, - XFS_BMAPI_CONVERT, &firstfsb, - 1, &imap, &nimaps, &free_list); + XFS_BMAPI_CONVERT, &firstfsb, resblks, + &imap, &nimaps, &free_list); if (error) goto error_on_bmapi_transaction; @@ -886,7 +927,7 @@ xfs_iomap_write_unwritten( xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } - error = xfs_bmap_finish(&tp, &free_list, &committed); + error = xfs_bmap_finish(&tp, &free_list, NULL); if (error) goto error_on_bmapi_transaction; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 8294132e6a3c..06eafafe636e 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -414,13 +414,17 @@ xfs_vn_rename( * uio is kmalloced for this reason... */ STATIC const char * -xfs_vn_follow_link( +xfs_vn_get_link( struct dentry *dentry, - void **cookie) + struct inode *inode, + struct delayed_call *done) { char *link; int error = -ENOMEM; + if (!dentry) + return ERR_PTR(-ECHILD); + link = kmalloc(MAXPATHLEN+1, GFP_KERNEL); if (!link) goto out_err; @@ -429,7 +433,8 @@ xfs_vn_follow_link( if (unlikely(error)) goto out_kfree; - return *cookie = link; + set_delayed_call(done, kfree_link, link); + return link; out_kfree: kfree(link); @@ -695,7 +700,7 @@ xfs_setattr_nonsize( xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - XFS_STATS_INC(xs_ig_attrchg); + XFS_STATS_INC(mp, xs_ig_attrchg); if (mp->m_flags & XFS_MOUNT_WSYNC) xfs_trans_set_sync(tp); @@ -922,7 +927,7 @@ xfs_setattr_size( xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - XFS_STATS_INC(xs_ig_attrchg); + XFS_STATS_INC(mp, xs_ig_attrchg); if (mp->m_flags & XFS_MOUNT_WSYNC) xfs_trans_set_sync(tp); @@ -1172,8 +1177,7 @@ static const struct inode_operations xfs_dir_ci_inode_operations = { static const struct inode_operations xfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = xfs_vn_follow_link, - .put_link = kfree_put_link, + .get_link = xfs_vn_get_link, .getattr = xfs_vn_getattr, .setattr = xfs_vn_setattr, .setxattr = generic_setxattr, diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index 85f883dd6207..ec0e239a0fa9 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -171,6 +171,13 @@ struct xfs_kobj { struct completion complete; }; +struct xstats { + struct xfsstats __percpu *xs_stats; + struct xfs_kobj xs_kobj; +}; + +extern struct xstats xfsstats; + /* Kernel uid/gid conversion. These are used to convert to/from the on disk * uid_t/gid_t types to the kuid_t/kgid_t types that the kernel uses internally. * The conversion here is type only, the value will remain the same since we diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index aaadee0969c9..9c9a1c9bcc7f 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -268,7 +268,7 @@ xlog_grant_head_wait( __set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&head->lock); - XFS_STATS_INC(xs_sleep_logspace); + XFS_STATS_INC(log->l_mp, xs_sleep_logspace); trace_xfs_log_grant_sleep(log, tic); schedule(); @@ -379,7 +379,7 @@ xfs_log_regrant( if (XLOG_FORCED_SHUTDOWN(log)) return -EIO; - XFS_STATS_INC(xs_try_logspace); + XFS_STATS_INC(mp, xs_try_logspace); /* * This is a new transaction on the ticket, so we need to change the @@ -448,7 +448,7 @@ xfs_log_reserve( if (XLOG_FORCED_SHUTDOWN(log)) return -EIO; - XFS_STATS_INC(xs_try_logspace); + XFS_STATS_INC(mp, xs_try_logspace); ASSERT(*ticp == NULL); tic = xlog_ticket_alloc(log, unit_bytes, cnt, client, permanent, @@ -1188,10 +1188,16 @@ xlog_iodone(xfs_buf_t *bp) int aborted = 0; /* - * Race to shutdown the filesystem if we see an error. + * Race to shutdown the filesystem if we see an error or the iclog is in + * IOABORT state. The IOABORT state is only set in DEBUG mode to inject + * CRC errors into log recovery. */ - if (XFS_TEST_ERROR(bp->b_error, l->l_mp, - XFS_ERRTAG_IODONE_IOERR, XFS_RANDOM_IODONE_IOERR)) { + if (XFS_TEST_ERROR(bp->b_error, l->l_mp, XFS_ERRTAG_IODONE_IOERR, + XFS_RANDOM_IODONE_IOERR) || + iclog->ic_state & XLOG_STATE_IOABORT) { + if (iclog->ic_state & XLOG_STATE_IOABORT) + iclog->ic_state &= ~XLOG_STATE_IOABORT; + xfs_buf_ioerror_alert(bp, __func__); xfs_buf_stale(bp); xfs_force_shutdown(l->l_mp, SHUTDOWN_LOG_IO_ERROR); @@ -1768,7 +1774,7 @@ xlog_sync( int v2 = xfs_sb_version_haslogv2(&log->l_mp->m_sb); int size; - XFS_STATS_INC(xs_log_writes); + XFS_STATS_INC(log->l_mp, xs_log_writes); ASSERT(atomic_read(&iclog->ic_refcnt) == 0); /* Add for LR header */ @@ -1805,7 +1811,7 @@ xlog_sync( bp = iclog->ic_bp; XFS_BUF_SET_ADDR(bp, BLOCK_LSN(be64_to_cpu(iclog->ic_header.h_lsn))); - XFS_STATS_ADD(xs_log_blocks, BTOBB(count)); + XFS_STATS_ADD(log->l_mp, xs_log_blocks, BTOBB(count)); /* Do we need to split this write into 2 parts? */ if (XFS_BUF_ADDR(bp) + BTOBB(count) > log->l_logBBsize) { @@ -1838,6 +1844,23 @@ xlog_sync( /* calculcate the checksum */ iclog->ic_header.h_crc = xlog_cksum(log, &iclog->ic_header, iclog->ic_datap, size); +#ifdef DEBUG + /* + * Intentionally corrupt the log record CRC based on the error injection + * frequency, if defined. This facilitates testing log recovery in the + * event of torn writes. Hence, set the IOABORT state to abort the log + * write on I/O completion and shutdown the fs. The subsequent mount + * detects the bad CRC and attempts to recover. + */ + if (log->l_badcrc_factor && + (prandom_u32() % log->l_badcrc_factor == 0)) { + iclog->ic_header.h_crc &= 0xAAAAAAAA; + iclog->ic_state |= XLOG_STATE_IOABORT; + xfs_warn(log->l_mp, + "Intentionally corrupted log record at LSN 0x%llx. Shutdown imminent.", + be64_to_cpu(iclog->ic_header.h_lsn)); + } +#endif bp->b_io_length = BTOBB(count); bp->b_fspriv = iclog; @@ -2045,12 +2068,14 @@ xlog_print_tic_res( "QM_DQCLUSTER", "QM_QINOCREATE", "QM_QUOTAOFF_END", - "SB_UNIT", "FSYNC_TS", "GROWFSRT_ALLOC", "GROWFSRT_ZERO", "GROWFSRT_FREE", - "SWAPEXT" + "SWAPEXT", + "CHECKPOINT", + "ICREATE", + "CREATE_TMPFILE" }; xfs_warn(mp, "xlog_write: reservation summary:"); @@ -2422,11 +2447,20 @@ xlog_write( &partial_copy_len); xlog_verify_dest_ptr(log, ptr); - /* copy region */ + /* + * Copy region. + * + * Unmount records just log an opheader, so can have + * empty payloads with no data region to copy. Hence we + * only copy the payload if the vector says it has data + * to copy. + */ ASSERT(copy_len >= 0); - memcpy(ptr, reg->i_addr + copy_off, copy_len); - xlog_write_adv_cnt(&ptr, &len, &log_offset, copy_len); - + if (copy_len > 0) { + memcpy(ptr, reg->i_addr + copy_off, copy_len); + xlog_write_adv_cnt(&ptr, &len, &log_offset, + copy_len); + } copy_len += start_rec_copy + sizeof(xlog_op_header_t); record_cnt++; data_cnt += contwr ? copy_len : 0; @@ -2782,11 +2816,19 @@ xlog_state_do_callback( } } while (!ioerrors && loopdidcallbacks); +#ifdef DEBUG /* - * make one last gasp attempt to see if iclogs are being left in - * limbo.. + * Make one last gasp attempt to see if iclogs are being left in limbo. + * If the above loop finds an iclog earlier than the current iclog and + * in one of the syncing states, the current iclog is put into + * DO_CALLBACK and the callbacks are deferred to the completion of the + * earlier iclog. Walk the iclogs in order and make sure that no iclog + * is in DO_CALLBACK unless an earlier iclog is in one of the syncing + * states. + * + * Note that SYNCING|IOABORT is a valid state so we cannot just check + * for ic_state == SYNCING. */ -#ifdef DEBUG if (funcdidcallbacks) { first_iclog = iclog = log->l_iclog; do { @@ -2801,7 +2843,7 @@ xlog_state_do_callback( * IOERROR - give up hope all ye who enter here */ if (iclog->ic_state == XLOG_STATE_WANT_SYNC || - iclog->ic_state == XLOG_STATE_SYNCING || + iclog->ic_state & XLOG_STATE_SYNCING || iclog->ic_state == XLOG_STATE_DONE_SYNC || iclog->ic_state == XLOG_STATE_IOERROR ) break; @@ -2913,7 +2955,7 @@ restart: iclog = log->l_iclog; if (iclog->ic_state != XLOG_STATE_ACTIVE) { - XFS_STATS_INC(xs_log_noiclogs); + XFS_STATS_INC(log->l_mp, xs_log_noiclogs); /* Wait for log writes to have flushed */ xlog_wait(&log->l_flush_wait, &log->l_icloglock); @@ -3165,11 +3207,19 @@ xlog_state_switch_iclogs( } if (log->l_curr_block >= log->l_logBBsize) { + /* + * Rewind the current block before the cycle is bumped to make + * sure that the combined LSN never transiently moves forward + * when the log wraps to the next cycle. This is to support the + * unlocked sample of these fields from xlog_valid_lsn(). Most + * other cases should acquire l_icloglock. + */ + log->l_curr_block -= log->l_logBBsize; + ASSERT(log->l_curr_block >= 0); + smp_wmb(); log->l_curr_cycle++; if (log->l_curr_cycle == XLOG_HEADER_MAGIC_NUM) log->l_curr_cycle++; - log->l_curr_block -= log->l_logBBsize; - ASSERT(log->l_curr_block >= 0); } ASSERT(iclog == log->l_iclog); log->l_iclog = iclog->ic_next; @@ -3212,7 +3262,7 @@ _xfs_log_force( struct xlog_in_core *iclog; xfs_lsn_t lsn; - XFS_STATS_INC(xs_log_force); + XFS_STATS_INC(mp, xs_log_force); xlog_cil_force(log); @@ -3297,7 +3347,7 @@ maybe_sleep: spin_unlock(&log->l_icloglock); return -EIO; } - XFS_STATS_INC(xs_log_force_sleep); + XFS_STATS_INC(mp, xs_log_force_sleep); xlog_wait(&iclog->ic_force_wait, &log->l_icloglock); /* * No need to grab the log lock here since we're @@ -3362,7 +3412,7 @@ _xfs_log_force_lsn( ASSERT(lsn != 0); - XFS_STATS_INC(xs_log_force); + XFS_STATS_INC(mp, xs_log_force); lsn = xlog_cil_force_lsn(log, lsn); if (lsn == NULLCOMMITLSN) @@ -3411,7 +3461,7 @@ try_again: (XLOG_STATE_WANT_SYNC | XLOG_STATE_SYNCING))) { ASSERT(!(iclog->ic_state & XLOG_STATE_IOERROR)); - XFS_STATS_INC(xs_log_force_sleep); + XFS_STATS_INC(mp, xs_log_force_sleep); xlog_wait(&iclog->ic_prev->ic_write_wait, &log->l_icloglock); @@ -3441,7 +3491,7 @@ try_again: spin_unlock(&log->l_icloglock); return -EIO; } - XFS_STATS_INC(xs_log_force_sleep); + XFS_STATS_INC(mp, xs_log_force_sleep); xlog_wait(&iclog->ic_force_wait, &log->l_icloglock); /* * No need to grab the log lock here since we're @@ -4023,3 +4073,45 @@ xlog_iclogs_empty( return 1; } +/* + * Verify that an LSN stamped into a piece of metadata is valid. This is + * intended for use in read verifiers on v5 superblocks. + */ +bool +xfs_log_check_lsn( + struct xfs_mount *mp, + xfs_lsn_t lsn) +{ + struct xlog *log = mp->m_log; + bool valid; + + /* + * norecovery mode skips mount-time log processing and unconditionally + * resets the in-core LSN. We can't validate in this mode, but + * modifications are not allowed anyways so just return true. + */ + if (mp->m_flags & XFS_MOUNT_NORECOVERY) + return true; + + /* + * Some metadata LSNs are initialized to NULL (e.g., the agfl). This is + * handled by recovery and thus safe to ignore here. + */ + if (lsn == NULLCOMMITLSN) + return true; + + valid = xlog_valid_lsn(mp->m_log, lsn); + + /* warn the user about what's gone wrong before verifier failure */ + if (!valid) { + spin_lock(&log->l_icloglock); + xfs_warn(mp, +"Corruption warning: Metadata has LSN (%d:%d) ahead of current LSN (%d:%d). " +"Please unmount and run xfs_repair (>= v4.3) to resolve.", + CYCLE_LSN(lsn), BLOCK_LSN(lsn), + log->l_curr_cycle, log->l_curr_block); + spin_unlock(&log->l_icloglock); + } + + return valid; +} diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index 09d91d3166cd..aa533a7d50f2 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -181,5 +181,6 @@ bool xfs_log_item_in_current_chkpt(struct xfs_log_item *lip); void xfs_log_work_queue(struct xfs_mount *mp); void xfs_log_worker(struct work_struct *work); void xfs_log_quiesce(struct xfs_mount *mp); +bool xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t); #endif /* __XFS_LOG_H__ */ diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 950f3f94720c..ed8896310c00 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -62,6 +62,7 @@ static inline uint xlog_get_client_id(__be32 i) #define XLOG_STATE_CALLBACK 0x0020 /* Callback functions now */ #define XLOG_STATE_DIRTY 0x0040 /* Dirty IC log, not ready for ACTIVE status*/ #define XLOG_STATE_IOERROR 0x0080 /* IO error happened in sync'ing log */ +#define XLOG_STATE_IOABORT 0x0100 /* force abort on I/O completion (debug) */ #define XLOG_STATE_ALL 0x7FFF /* All possible valid flags */ #define XLOG_STATE_NOTUSED 0x8000 /* This IC log not being used */ @@ -410,6 +411,8 @@ struct xlog { /* The following field are used for debugging; need to hold icloglock */ #ifdef DEBUG void *l_iclog_bak[XLOG_MAX_ICLOGS]; + /* log record crc error injection factor */ + uint32_t l_badcrc_factor; #endif }; @@ -560,4 +563,55 @@ static inline void xlog_wait(wait_queue_head_t *wq, spinlock_t *lock) remove_wait_queue(wq, &wait); } +/* + * The LSN is valid so long as it is behind the current LSN. If it isn't, this + * means that the next log record that includes this metadata could have a + * smaller LSN. In turn, this means that the modification in the log would not + * replay. + */ +static inline bool +xlog_valid_lsn( + struct xlog *log, + xfs_lsn_t lsn) +{ + int cur_cycle; + int cur_block; + bool valid = true; + + /* + * First, sample the current lsn without locking to avoid added + * contention from metadata I/O. The current cycle and block are updated + * (in xlog_state_switch_iclogs()) and read here in a particular order + * to avoid false negatives (e.g., thinking the metadata LSN is valid + * when it is not). + * + * The current block is always rewound before the cycle is bumped in + * xlog_state_switch_iclogs() to ensure the current LSN is never seen in + * a transiently forward state. Instead, we can see the LSN in a + * transiently behind state if we happen to race with a cycle wrap. + */ + cur_cycle = ACCESS_ONCE(log->l_curr_cycle); + smp_rmb(); + cur_block = ACCESS_ONCE(log->l_curr_block); + + if ((CYCLE_LSN(lsn) > cur_cycle) || + (CYCLE_LSN(lsn) == cur_cycle && BLOCK_LSN(lsn) > cur_block)) { + /* + * If the metadata LSN appears invalid, it's possible the check + * above raced with a wrap to the next log cycle. Grab the lock + * to check for sure. + */ + spin_lock(&log->l_icloglock); + cur_cycle = log->l_curr_cycle; + cur_block = log->l_curr_block; + spin_unlock(&log->l_icloglock); + + if ((CYCLE_LSN(lsn) > cur_cycle) || + (CYCLE_LSN(lsn) == cur_cycle && BLOCK_LSN(lsn) > cur_block)) + valid = false; + } + + return valid; +} + #endif /* __XFS_LOG_PRIV_H__ */ diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 512a0945d52a..da37beb76f6e 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -61,6 +61,9 @@ xlog_recover_check_summary( #else #define xlog_recover_check_summary(log) #endif +STATIC int +xlog_do_recovery_pass( + struct xlog *, xfs_daddr_t, xfs_daddr_t, int, xfs_daddr_t *); /* * This structure is used during recovery to record the buf log items which @@ -868,6 +871,351 @@ validate_head: } /* + * Seek backwards in the log for log record headers. + * + * Given a starting log block, walk backwards until we find the provided number + * of records or hit the provided tail block. The return value is the number of + * records encountered or a negative error code. The log block and buffer + * pointer of the last record seen are returned in rblk and rhead respectively. + */ +STATIC int +xlog_rseek_logrec_hdr( + struct xlog *log, + xfs_daddr_t head_blk, + xfs_daddr_t tail_blk, + int count, + struct xfs_buf *bp, + xfs_daddr_t *rblk, + struct xlog_rec_header **rhead, + bool *wrapped) +{ + int i; + int error; + int found = 0; + char *offset = NULL; + xfs_daddr_t end_blk; + + *wrapped = false; + + /* + * Walk backwards from the head block until we hit the tail or the first + * block in the log. + */ + end_blk = head_blk > tail_blk ? tail_blk : 0; + for (i = (int) head_blk - 1; i >= end_blk; i--) { + error = xlog_bread(log, i, 1, bp, &offset); + if (error) + goto out_error; + + if (*(__be32 *) offset == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) { + *rblk = i; + *rhead = (struct xlog_rec_header *) offset; + if (++found == count) + break; + } + } + + /* + * If we haven't hit the tail block or the log record header count, + * start looking again from the end of the physical log. Note that + * callers can pass head == tail if the tail is not yet known. + */ + if (tail_blk >= head_blk && found != count) { + for (i = log->l_logBBsize - 1; i >= (int) tail_blk; i--) { + error = xlog_bread(log, i, 1, bp, &offset); + if (error) + goto out_error; + + if (*(__be32 *)offset == + cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) { + *wrapped = true; + *rblk = i; + *rhead = (struct xlog_rec_header *) offset; + if (++found == count) + break; + } + } + } + + return found; + +out_error: + return error; +} + +/* + * Seek forward in the log for log record headers. + * + * Given head and tail blocks, walk forward from the tail block until we find + * the provided number of records or hit the head block. The return value is the + * number of records encountered or a negative error code. The log block and + * buffer pointer of the last record seen are returned in rblk and rhead + * respectively. + */ +STATIC int +xlog_seek_logrec_hdr( + struct xlog *log, + xfs_daddr_t head_blk, + xfs_daddr_t tail_blk, + int count, + struct xfs_buf *bp, + xfs_daddr_t *rblk, + struct xlog_rec_header **rhead, + bool *wrapped) +{ + int i; + int error; + int found = 0; + char *offset = NULL; + xfs_daddr_t end_blk; + + *wrapped = false; + + /* + * Walk forward from the tail block until we hit the head or the last + * block in the log. + */ + end_blk = head_blk > tail_blk ? head_blk : log->l_logBBsize - 1; + for (i = (int) tail_blk; i <= end_blk; i++) { + error = xlog_bread(log, i, 1, bp, &offset); + if (error) + goto out_error; + + if (*(__be32 *) offset == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) { + *rblk = i; + *rhead = (struct xlog_rec_header *) offset; + if (++found == count) + break; + } + } + + /* + * If we haven't hit the head block or the log record header count, + * start looking again from the start of the physical log. + */ + if (tail_blk > head_blk && found != count) { + for (i = 0; i < (int) head_blk; i++) { + error = xlog_bread(log, i, 1, bp, &offset); + if (error) + goto out_error; + + if (*(__be32 *)offset == + cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) { + *wrapped = true; + *rblk = i; + *rhead = (struct xlog_rec_header *) offset; + if (++found == count) + break; + } + } + } + + return found; + +out_error: + return error; +} + +/* + * Check the log tail for torn writes. This is required when torn writes are + * detected at the head and the head had to be walked back to a previous record. + * The tail of the previous record must now be verified to ensure the torn + * writes didn't corrupt the previous tail. + * + * Return an error if CRC verification fails as recovery cannot proceed. + */ +STATIC int +xlog_verify_tail( + struct xlog *log, + xfs_daddr_t head_blk, + xfs_daddr_t tail_blk) +{ + struct xlog_rec_header *thead; + struct xfs_buf *bp; + xfs_daddr_t first_bad; + int count; + int error = 0; + bool wrapped; + xfs_daddr_t tmp_head; + + bp = xlog_get_bp(log, 1); + if (!bp) + return -ENOMEM; + + /* + * Seek XLOG_MAX_ICLOGS + 1 records past the current tail record to get + * a temporary head block that points after the last possible + * concurrently written record of the tail. + */ + count = xlog_seek_logrec_hdr(log, head_blk, tail_blk, + XLOG_MAX_ICLOGS + 1, bp, &tmp_head, &thead, + &wrapped); + if (count < 0) { + error = count; + goto out; + } + + /* + * If the call above didn't find XLOG_MAX_ICLOGS + 1 records, we ran + * into the actual log head. tmp_head points to the start of the record + * so update it to the actual head block. + */ + if (count < XLOG_MAX_ICLOGS + 1) + tmp_head = head_blk; + + /* + * We now have a tail and temporary head block that covers at least + * XLOG_MAX_ICLOGS records from the tail. We need to verify that these + * records were completely written. Run a CRC verification pass from + * tail to head and return the result. + */ + error = xlog_do_recovery_pass(log, tmp_head, tail_blk, + XLOG_RECOVER_CRCPASS, &first_bad); + +out: + xlog_put_bp(bp); + return error; +} + +/* + * Detect and trim torn writes from the head of the log. + * + * Storage without sector atomicity guarantees can result in torn writes in the + * log in the event of a crash. Our only means to detect this scenario is via + * CRC verification. While we can't always be certain that CRC verification + * failure is due to a torn write vs. an unrelated corruption, we do know that + * only a certain number (XLOG_MAX_ICLOGS) of log records can be written out at + * one time. Therefore, CRC verify up to XLOG_MAX_ICLOGS records at the head of + * the log and treat failures in this range as torn writes as a matter of + * policy. In the event of CRC failure, the head is walked back to the last good + * record in the log and the tail is updated from that record and verified. + */ +STATIC int +xlog_verify_head( + struct xlog *log, + xfs_daddr_t *head_blk, /* in/out: unverified head */ + xfs_daddr_t *tail_blk, /* out: tail block */ + struct xfs_buf *bp, + xfs_daddr_t *rhead_blk, /* start blk of last record */ + struct xlog_rec_header **rhead, /* ptr to last record */ + bool *wrapped) /* last rec. wraps phys. log */ +{ + struct xlog_rec_header *tmp_rhead; + struct xfs_buf *tmp_bp; + xfs_daddr_t first_bad; + xfs_daddr_t tmp_rhead_blk; + int found; + int error; + bool tmp_wrapped; + + /* + * Search backwards through the log looking for the log record header + * block. This wraps all the way back around to the head so something is + * seriously wrong if we can't find it. + */ + found = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, bp, rhead_blk, + rhead, wrapped); + if (found < 0) + return found; + if (!found) { + xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__); + return -EIO; + } + + *tail_blk = BLOCK_LSN(be64_to_cpu((*rhead)->h_tail_lsn)); + + /* + * Now that we have a tail block, check the head of the log for torn + * writes. Search again until we hit the tail or the maximum number of + * log record I/Os that could have been in flight at one time. Use a + * temporary buffer so we don't trash the rhead/bp pointer from the + * call above. + */ + tmp_bp = xlog_get_bp(log, 1); + if (!tmp_bp) + return -ENOMEM; + error = xlog_rseek_logrec_hdr(log, *head_blk, *tail_blk, + XLOG_MAX_ICLOGS, tmp_bp, &tmp_rhead_blk, + &tmp_rhead, &tmp_wrapped); + xlog_put_bp(tmp_bp); + if (error < 0) + return error; + + /* + * Now run a CRC verification pass over the records starting at the + * block found above to the current head. If a CRC failure occurs, the + * log block of the first bad record is saved in first_bad. + */ + error = xlog_do_recovery_pass(log, *head_blk, tmp_rhead_blk, + XLOG_RECOVER_CRCPASS, &first_bad); + if (error == -EFSBADCRC) { + /* + * We've hit a potential torn write. Reset the error and warn + * about it. + */ + error = 0; + xfs_warn(log->l_mp, +"Torn write (CRC failure) detected at log block 0x%llx. Truncating head block from 0x%llx.", + first_bad, *head_blk); + + /* + * Get the header block and buffer pointer for the last good + * record before the bad record. + * + * Note that xlog_find_tail() clears the blocks at the new head + * (i.e., the records with invalid CRC) if the cycle number + * matches the the current cycle. + */ + found = xlog_rseek_logrec_hdr(log, first_bad, *tail_blk, 1, bp, + rhead_blk, rhead, wrapped); + if (found < 0) + return found; + if (found == 0) /* XXX: right thing to do here? */ + return -EIO; + + /* + * Reset the head block to the starting block of the first bad + * log record and set the tail block based on the last good + * record. + * + * Bail out if the updated head/tail match as this indicates + * possible corruption outside of the acceptable + * (XLOG_MAX_ICLOGS) range. This is a job for xfs_repair... + */ + *head_blk = first_bad; + *tail_blk = BLOCK_LSN(be64_to_cpu((*rhead)->h_tail_lsn)); + if (*head_blk == *tail_blk) { + ASSERT(0); + return 0; + } + + /* + * Now verify the tail based on the updated head. This is + * required because the torn writes trimmed from the head could + * have been written over the tail of a previous record. Return + * any errors since recovery cannot proceed if the tail is + * corrupt. + * + * XXX: This leaves a gap in truly robust protection from torn + * writes in the log. If the head is behind the tail, the tail + * pushes forward to create some space and then a crash occurs + * causing the writes into the previous record's tail region to + * tear, log recovery isn't able to recover. + * + * How likely is this to occur? If possible, can we do something + * more intelligent here? Is it safe to push the tail forward if + * we can determine that the tail is within the range of the + * torn write (e.g., the kernel can only overwrite the tail if + * it has actually been pushed forward)? Alternatively, could we + * somehow prevent this condition at runtime? + */ + error = xlog_verify_tail(log, *head_blk, *tail_blk); + } + + return error; +} + +/* * Find the sync block number or the tail of the log. * * This will be the block number of the last record to have its @@ -893,13 +1241,13 @@ xlog_find_tail( xlog_op_header_t *op_head; char *offset = NULL; xfs_buf_t *bp; - int error, i, found; + int error; xfs_daddr_t umount_data_blk; xfs_daddr_t after_umount_blk; + xfs_daddr_t rhead_blk; xfs_lsn_t tail_lsn; int hblks; - - found = 0; + bool wrapped = false; /* * Find previous log record @@ -923,48 +1271,16 @@ xlog_find_tail( } /* - * Search backwards looking for log record header block + * Trim the head block back to skip over torn records. We can have + * multiple log I/Os in flight at any time, so we assume CRC failures + * back through the previous several records are torn writes and skip + * them. */ ASSERT(*head_blk < INT_MAX); - for (i = (int)(*head_blk) - 1; i >= 0; i--) { - error = xlog_bread(log, i, 1, bp, &offset); - if (error) - goto done; - - if (*(__be32 *)offset == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) { - found = 1; - break; - } - } - /* - * If we haven't found the log record header block, start looking - * again from the end of the physical log. XXXmiken: There should be - * a check here to make sure we didn't search more than N blocks in - * the previous code. - */ - if (!found) { - for (i = log->l_logBBsize - 1; i >= (int)(*head_blk); i--) { - error = xlog_bread(log, i, 1, bp, &offset); - if (error) - goto done; - - if (*(__be32 *)offset == - cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) { - found = 2; - break; - } - } - } - if (!found) { - xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__); - xlog_put_bp(bp); - ASSERT(0); - return -EIO; - } - - /* find blk_no of tail of log */ - rhead = (xlog_rec_header_t *)offset; - *tail_blk = BLOCK_LSN(be64_to_cpu(rhead->h_tail_lsn)); + error = xlog_verify_head(log, head_blk, tail_blk, bp, &rhead_blk, + &rhead, &wrapped); + if (error) + goto done; /* * Reset log values according to the state of the log when we @@ -976,10 +1292,10 @@ xlog_find_tail( * written was complete and ended exactly on the end boundary * of the physical log. */ - log->l_prev_block = i; + log->l_prev_block = rhead_blk; log->l_curr_block = (int)*head_blk; log->l_curr_cycle = be32_to_cpu(rhead->h_cycle); - if (found == 2) + if (wrapped) log->l_curr_cycle++; atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn)); atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn)); @@ -1014,12 +1330,13 @@ xlog_find_tail( } else { hblks = 1; } - after_umount_blk = (i + hblks + (int) - BTOBB(be32_to_cpu(rhead->h_len))) % log->l_logBBsize; + after_umount_blk = rhead_blk + hblks + BTOBB(be32_to_cpu(rhead->h_len)); + after_umount_blk = do_mod(after_umount_blk, log->l_logBBsize); tail_lsn = atomic64_read(&log->l_tail_lsn); if (*head_blk == after_umount_blk && be32_to_cpu(rhead->h_num_logops) == 1) { - umount_data_blk = (i + hblks) % log->l_logBBsize; + umount_data_blk = rhead_blk + hblks; + umount_data_blk = do_mod(umount_data_blk, log->l_logBBsize); error = xlog_bread(log, umount_data_blk, 1, bp, &offset); if (error) goto done; @@ -3204,6 +3521,7 @@ xlog_recover_dquot_ra_pass2( struct xfs_disk_dquot *recddq; struct xfs_dq_logformat *dq_f; uint type; + int len; if (mp->m_qflags == 0) @@ -3224,8 +3542,12 @@ xlog_recover_dquot_ra_pass2( ASSERT(dq_f); ASSERT(dq_f->qlf_len == 1); - xfs_buf_readahead(mp->m_ddev_targp, dq_f->qlf_blkno, - XFS_FSB_TO_BB(mp, dq_f->qlf_len), NULL); + len = XFS_FSB_TO_BB(mp, dq_f->qlf_len); + if (xlog_peek_buffer_cancelled(log, dq_f->qlf_blkno, len, 0)) + return; + + xfs_buf_readahead(mp->m_ddev_targp, dq_f->qlf_blkno, len, + &xfs_dquot_buf_ra_ops); } STATIC void @@ -3431,7 +3753,7 @@ xlog_recover_add_to_cont_trans( * previous record. Copy the rest of the header. */ if (list_empty(&trans->r_itemq)) { - ASSERT(len < sizeof(struct xfs_trans_header)); + ASSERT(len <= sizeof(struct xfs_trans_header)); if (len > sizeof(struct xfs_trans_header)) { xfs_warn(log->l_mp, "%s: bad header length", __func__); return -EIO; @@ -4118,26 +4440,69 @@ xlog_recover_process_iunlinks( mp->m_dmevmask = mp_dmevmask; } +STATIC int +xlog_unpack_data( + struct xlog_rec_header *rhead, + char *dp, + struct xlog *log) +{ + int i, j, k; + + for (i = 0; i < BTOBB(be32_to_cpu(rhead->h_len)) && + i < (XLOG_HEADER_CYCLE_SIZE / BBSIZE); i++) { + *(__be32 *)dp = *(__be32 *)&rhead->h_cycle_data[i]; + dp += BBSIZE; + } + + if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) { + xlog_in_core_2_t *xhdr = (xlog_in_core_2_t *)rhead; + for ( ; i < BTOBB(be32_to_cpu(rhead->h_len)); i++) { + j = i / (XLOG_HEADER_CYCLE_SIZE / BBSIZE); + k = i % (XLOG_HEADER_CYCLE_SIZE / BBSIZE); + *(__be32 *)dp = xhdr[j].hic_xheader.xh_cycle_data[k]; + dp += BBSIZE; + } + } + + return 0; +} + /* - * Upack the log buffer data and crc check it. If the check fails, issue a - * warning if and only if the CRC in the header is non-zero. This makes the - * check an advisory warning, and the zero CRC check will prevent failure - * warnings from being emitted when upgrading the kernel from one that does not - * add CRCs by default. - * - * When filesystems are CRC enabled, this CRC mismatch becomes a fatal log - * corruption failure + * CRC check, unpack and process a log record. */ STATIC int -xlog_unpack_data_crc( +xlog_recover_process( + struct xlog *log, + struct hlist_head rhash[], struct xlog_rec_header *rhead, char *dp, - struct xlog *log) + int pass) { + int error; __le32 crc; crc = xlog_cksum(log, rhead, dp, be32_to_cpu(rhead->h_len)); - if (crc != rhead->h_crc) { + + /* + * Nothing else to do if this is a CRC verification pass. Just return + * if this a record with a non-zero crc. Unfortunately, mkfs always + * sets h_crc to 0 so we must consider this valid even on v5 supers. + * Otherwise, return EFSBADCRC on failure so the callers up the stack + * know precisely what failed. + */ + if (pass == XLOG_RECOVER_CRCPASS) { + if (rhead->h_crc && crc != le32_to_cpu(rhead->h_crc)) + return -EFSBADCRC; + return 0; + } + + /* + * We're in the normal recovery path. Issue a warning if and only if the + * CRC in the header is non-zero. This is an advisory warning and the + * zero CRC check prevents warnings from being emitted when upgrading + * the kernel from one that does not add CRCs by default. + */ + if (crc != le32_to_cpu(rhead->h_crc)) { if (rhead->h_crc || xfs_sb_version_hascrc(&log->l_mp->m_sb)) { xfs_alert(log->l_mp, "log record CRC mismatch: found 0x%x, expected 0x%x.", @@ -4147,47 +4512,18 @@ xlog_unpack_data_crc( } /* - * If we've detected a log record corruption, then we can't - * recover past this point. Abort recovery if we are enforcing - * CRC protection by punting an error back up the stack. + * If the filesystem is CRC enabled, this mismatch becomes a + * fatal log corruption failure. */ if (xfs_sb_version_hascrc(&log->l_mp->m_sb)) return -EFSCORRUPTED; } - return 0; -} - -STATIC int -xlog_unpack_data( - struct xlog_rec_header *rhead, - char *dp, - struct xlog *log) -{ - int i, j, k; - int error; - - error = xlog_unpack_data_crc(rhead, dp, log); + error = xlog_unpack_data(rhead, dp, log); if (error) return error; - for (i = 0; i < BTOBB(be32_to_cpu(rhead->h_len)) && - i < (XLOG_HEADER_CYCLE_SIZE / BBSIZE); i++) { - *(__be32 *)dp = *(__be32 *)&rhead->h_cycle_data[i]; - dp += BBSIZE; - } - - if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) { - xlog_in_core_2_t *xhdr = (xlog_in_core_2_t *)rhead; - for ( ; i < BTOBB(be32_to_cpu(rhead->h_len)); i++) { - j = i / (XLOG_HEADER_CYCLE_SIZE / BBSIZE); - k = i % (XLOG_HEADER_CYCLE_SIZE / BBSIZE); - *(__be32 *)dp = xhdr[j].hic_xheader.xh_cycle_data[k]; - dp += BBSIZE; - } - } - - return 0; + return xlog_recover_process_data(log, rhash, rhead, dp, pass); } STATIC int @@ -4239,18 +4575,21 @@ xlog_do_recovery_pass( struct xlog *log, xfs_daddr_t head_blk, xfs_daddr_t tail_blk, - int pass) + int pass, + xfs_daddr_t *first_bad) /* out: first bad log rec */ { xlog_rec_header_t *rhead; xfs_daddr_t blk_no; + xfs_daddr_t rhead_blk; char *offset; xfs_buf_t *hbp, *dbp; - int error = 0, h_size; + int error = 0, h_size, h_len; int bblks, split_bblks; int hblks, split_hblks, wrapped_hblks; struct hlist_head rhash[XLOG_RHASH_SIZE]; ASSERT(head_blk != tail_blk); + rhead_blk = 0; /* * Read the header of the tail block and get the iclog buffer size from @@ -4274,7 +4613,31 @@ xlog_do_recovery_pass( error = xlog_valid_rec_header(log, rhead, tail_blk); if (error) goto bread_err1; + + /* + * xfsprogs has a bug where record length is based on lsunit but + * h_size (iclog size) is hardcoded to 32k. Now that we + * unconditionally CRC verify the unmount record, this means the + * log buffer can be too small for the record and cause an + * overrun. + * + * Detect this condition here. Use lsunit for the buffer size as + * long as this looks like the mkfs case. Otherwise, return an + * error to avoid a buffer overrun. + */ h_size = be32_to_cpu(rhead->h_size); + h_len = be32_to_cpu(rhead->h_len); + if (h_len > h_size) { + if (h_len <= log->l_mp->m_logbsize && + be32_to_cpu(rhead->h_num_logops) == 1) { + xfs_warn(log->l_mp, + "invalid iclog size (%d bytes), using lsunit (%d bytes)", + h_size, log->l_mp->m_logbsize); + h_size = log->l_mp->m_logbsize; + } else + return -EFSCORRUPTED; + } + if ((be32_to_cpu(rhead->h_version) & XLOG_VERSION_2) && (h_size > XLOG_HEADER_CYCLE_SIZE)) { hblks = h_size / XLOG_HEADER_CYCLE_SIZE; @@ -4301,7 +4664,7 @@ xlog_do_recovery_pass( } memset(rhash, 0, sizeof(rhash)); - blk_no = tail_blk; + blk_no = rhead_blk = tail_blk; if (tail_blk > head_blk) { /* * Perform recovery around the end of the physical log. @@ -4408,19 +4771,18 @@ xlog_do_recovery_pass( goto bread_err2; } - error = xlog_unpack_data(rhead, offset, log); + error = xlog_recover_process(log, rhash, rhead, offset, + pass); if (error) goto bread_err2; - error = xlog_recover_process_data(log, rhash, - rhead, offset, pass); - if (error) - goto bread_err2; blk_no += bblks; + rhead_blk = blk_no; } ASSERT(blk_no >= log->l_logBBsize); blk_no -= log->l_logBBsize; + rhead_blk = blk_no; } /* read first part of physical log */ @@ -4441,21 +4803,22 @@ xlog_do_recovery_pass( if (error) goto bread_err2; - error = xlog_unpack_data(rhead, offset, log); + error = xlog_recover_process(log, rhash, rhead, offset, pass); if (error) goto bread_err2; - error = xlog_recover_process_data(log, rhash, - rhead, offset, pass); - if (error) - goto bread_err2; blk_no += bblks + hblks; + rhead_blk = blk_no; } bread_err2: xlog_put_bp(dbp); bread_err1: xlog_put_bp(hbp); + + if (error && first_bad) + *first_bad = rhead_blk; + return error; } @@ -4493,7 +4856,7 @@ xlog_do_log_recovery( INIT_LIST_HEAD(&log->l_buf_cancel_table[i]); error = xlog_do_recovery_pass(log, head_blk, tail_blk, - XLOG_RECOVER_PASS1); + XLOG_RECOVER_PASS1, NULL); if (error != 0) { kmem_free(log->l_buf_cancel_table); log->l_buf_cancel_table = NULL; @@ -4504,7 +4867,7 @@ xlog_do_log_recovery( * When it is complete free the table of buf cancel items. */ error = xlog_do_recovery_pass(log, head_blk, tail_blk, - XLOG_RECOVER_PASS2); + XLOG_RECOVER_PASS2, NULL); #ifdef DEBUG if (!error) { int i; @@ -4609,9 +4972,19 @@ xlog_recover( int error; /* find the tail of the log */ - if ((error = xlog_find_tail(log, &head_blk, &tail_blk))) + error = xlog_find_tail(log, &head_blk, &tail_blk); + if (error) return error; + /* + * The superblock was read before the log was available and thus the LSN + * could not be verified. Check the superblock LSN against the current + * LSN now that it's known. + */ + if (xfs_sb_version_hascrc(&log->l_mp->m_sb) && + !xfs_log_check_lsn(log->l_mp, log->l_mp->m_sb.sb_lsn)) + return -EINVAL; + if (tail_blk != head_blk) { /* There used to be a comment here: * diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c index d8b67547ab34..11792d888e4e 100644 --- a/fs/xfs/xfs_message.c +++ b/fs/xfs/xfs_message.c @@ -17,6 +17,7 @@ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_error.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" @@ -43,6 +44,7 @@ void func(const struct xfs_mount *mp, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ + int level; \ \ va_start(args, fmt); \ \ @@ -51,6 +53,11 @@ void func(const struct xfs_mount *mp, const char *fmt, ...) \ \ __xfs_printk(kern_level, mp, &vaf); \ va_end(args); \ + \ + if (!kstrtoint(kern_level, 0, &level) && \ + level <= LOGLEVEL_ERR && \ + xfs_error_level >= XFS_ERRLEVEL_HIGH) \ + xfs_stack_trace(); \ } \ define_xfs_printk_level(xfs_emerg, KERN_EMERG); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index bf92e0c037c7..bb753b359bee 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -47,6 +47,16 @@ static DEFINE_MUTEX(xfs_uuid_table_mutex); static int xfs_uuid_table_size; static uuid_t *xfs_uuid_table; +void +xfs_uuid_table_free(void) +{ + if (xfs_uuid_table_size == 0) + return; + kmem_free(xfs_uuid_table); + xfs_uuid_table = NULL; + xfs_uuid_table_size = 0; +} + /* * See if the UUID is unique among mounted XFS filesystems. * Mount fails if UUID is nil or a FS with the same UUID is already mounted. @@ -693,10 +703,15 @@ xfs_mountfs( if (error) goto out; - error = xfs_uuid_mount(mp); + error = xfs_sysfs_init(&mp->m_stats.xs_kobj, &xfs_stats_ktype, + &mp->m_kobj, "stats"); if (error) goto out_remove_sysfs; + error = xfs_uuid_mount(mp); + if (error) + goto out_del_stats; + /* * Set the minimum read and write sizes */ @@ -971,6 +986,8 @@ xfs_mountfs( xfs_da_unmount(mp); out_remove_uuid: xfs_uuid_unmount(mp); + out_del_stats: + xfs_sysfs_del(&mp->m_stats.xs_kobj); out_remove_sysfs: xfs_sysfs_del(&mp->m_kobj); out: @@ -1047,6 +1064,7 @@ xfs_unmountfs( xfs_warn(mp, "Unable to update superblock counters. " "Freespace may not be correct on next mount."); + xfs_log_unmount(mp); xfs_da_unmount(mp); xfs_uuid_unmount(mp); @@ -1056,6 +1074,7 @@ xfs_unmountfs( #endif xfs_free_perag(mp); + xfs_sysfs_del(&mp->m_stats.xs_kobj); xfs_sysfs_del(&mp->m_kobj); } diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 7999e91cd49a..b57098481c10 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -127,6 +127,7 @@ typedef struct xfs_mount { int64_t m_low_space[XFS_LOWSP_MAX]; /* low free space thresholds */ struct xfs_kobj m_kobj; + struct xstats m_stats; /* per-fs stats */ struct workqueue_struct *m_buf_workqueue; struct workqueue_struct *m_data_workqueue; @@ -312,6 +313,7 @@ typedef struct xfs_perag { int pagb_count; /* pagb slots in use */ } xfs_perag_t; +extern void xfs_uuid_table_free(void); extern int xfs_log_sbcount(xfs_mount_t *); extern __uint64_t xfs_default_resblks(xfs_mount_t *mp); extern int xfs_mountfs(xfs_mount_t *mp); @@ -336,4 +338,7 @@ extern int xfs_dev_is_read_only(struct xfs_mount *, char *); extern void xfs_set_low_space_thresholds(struct xfs_mount *); +int xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb, + xfs_off_t count_fsb); + #endif /* __XFS_MOUNT_H__ */ diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index ab4a6066f7ca..dc6221942b85 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -181,6 +181,11 @@ xfs_fs_map_blocks( ASSERT(imap.br_startblock != DELAYSTARTBLOCK); if (!nimaps || imap.br_startblock == HOLESTARTBLOCK) { + /* + * xfs_iomap_write_direct() expects to take ownership of + * the shared ilock. + */ + xfs_ilock(ip, XFS_ILOCK_SHARED); error = xfs_iomap_write_direct(ip, offset, length, &imap, nimaps); if (error) diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index eac9549efd52..532ab79d38fe 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -184,7 +184,7 @@ xfs_qm_dqpurge( */ ASSERT(!list_empty(&dqp->q_lru)); list_lru_del(&qi->qi_lru, &dqp->q_lru); - XFS_STATS_DEC(xs_qm_dquot_unused); + XFS_STATS_DEC(mp, xs_qm_dquot_unused); xfs_qm_dqdestroy(dqp); return 0; @@ -448,11 +448,11 @@ xfs_qm_dquot_isolate( */ if (dqp->q_nrefs) { xfs_dqunlock(dqp); - XFS_STATS_INC(xs_qm_dqwants); + XFS_STATS_INC(dqp->q_mount, xs_qm_dqwants); trace_xfs_dqreclaim_want(dqp); list_lru_isolate(lru, &dqp->q_lru); - XFS_STATS_DEC(xs_qm_dquot_unused); + XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot_unused); return LRU_REMOVED; } @@ -496,19 +496,19 @@ xfs_qm_dquot_isolate( ASSERT(dqp->q_nrefs == 0); list_lru_isolate_move(lru, &dqp->q_lru, &isol->dispose); - XFS_STATS_DEC(xs_qm_dquot_unused); + XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot_unused); trace_xfs_dqreclaim_done(dqp); - XFS_STATS_INC(xs_qm_dqreclaims); + XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaims); return LRU_REMOVED; out_miss_busy: trace_xfs_dqreclaim_busy(dqp); - XFS_STATS_INC(xs_qm_dqreclaim_misses); + XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses); return LRU_SKIP; out_unlock_dirty: trace_xfs_dqreclaim_busy(dqp); - XFS_STATS_INC(xs_qm_dqreclaim_misses); + XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses); xfs_dqunlock(dqp); spin_lock(lru_lock); return LRU_RETRY; @@ -525,7 +525,7 @@ xfs_qm_shrink_scan( unsigned long freed; int error; - if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT)) + if ((sc->gfp_mask & (__GFP_FS|__GFP_DIRECT_RECLAIM)) != (__GFP_FS|__GFP_DIRECT_RECLAIM)) return 0; INIT_LIST_HEAD(&isol.buffers); diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index ab1bac6a3a1c..be02a68b2fe2 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -766,7 +766,6 @@ xfs_growfs_rt_alloc( { xfs_fileoff_t bno; /* block number in file */ struct xfs_buf *bp; /* temporary buffer for zeroing */ - int committed; /* transaction committed flag */ xfs_daddr_t d; /* disk block address */ int error; /* error return value */ xfs_fsblock_t firstblock;/* first block allocated in xaction */ @@ -811,7 +810,7 @@ xfs_growfs_rt_alloc( /* * Free any blocks freed up in the transaction, then commit. */ - error = xfs_bmap_finish(&tp, &flist, &committed); + error = xfs_bmap_finish(&tp, &flist, NULL); if (error) goto out_bmap_cancel; error = xfs_trans_commit(tp); diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c index f2240383d4bb..8686df6c7609 100644 --- a/fs/xfs/xfs_stats.c +++ b/fs/xfs/xfs_stats.c @@ -18,20 +18,21 @@ #include "xfs.h" #include <linux/proc_fs.h> -DEFINE_PER_CPU(struct xfsstats, xfsstats); +struct xstats xfsstats; -static int counter_val(int idx) +static int counter_val(struct xfsstats __percpu *stats, int idx) { int val = 0, cpu; for_each_possible_cpu(cpu) - val += *(((__u32 *)&per_cpu(xfsstats, cpu) + idx)); + val += *(((__u32 *)per_cpu_ptr(stats, cpu) + idx)); return val; } -static int xfs_stat_proc_show(struct seq_file *m, void *v) +int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) { int i, j; + int len = 0; __uint64_t xs_xstrat_bytes = 0; __uint64_t xs_write_bytes = 0; __uint64_t xs_read_bytes = 0; @@ -65,54 +66,59 @@ static int xfs_stat_proc_show(struct seq_file *m, void *v) }; /* Loop over all stats groups */ + for (i = j = 0; i < ARRAY_SIZE(xstats); i++) { - seq_printf(m, "%s", xstats[i].desc); + len += snprintf(buf + len, PATH_MAX - len, "%s", + xstats[i].desc); /* inner loop does each group */ for (; j < xstats[i].endpoint; j++) - seq_printf(m, " %u", counter_val(j)); - seq_putc(m, '\n'); + len += snprintf(buf + len, PATH_MAX - len, " %u", + counter_val(stats, j)); + len += snprintf(buf + len, PATH_MAX - len, "\n"); } /* extra precision counters */ for_each_possible_cpu(i) { - xs_xstrat_bytes += per_cpu(xfsstats, i).xs_xstrat_bytes; - xs_write_bytes += per_cpu(xfsstats, i).xs_write_bytes; - xs_read_bytes += per_cpu(xfsstats, i).xs_read_bytes; + xs_xstrat_bytes += per_cpu_ptr(stats, i)->xs_xstrat_bytes; + xs_write_bytes += per_cpu_ptr(stats, i)->xs_write_bytes; + xs_read_bytes += per_cpu_ptr(stats, i)->xs_read_bytes; } - seq_printf(m, "xpc %Lu %Lu %Lu\n", + len += snprintf(buf + len, PATH_MAX-len, "xpc %Lu %Lu %Lu\n", xs_xstrat_bytes, xs_write_bytes, xs_read_bytes); - seq_printf(m, "debug %u\n", + len += snprintf(buf + len, PATH_MAX-len, "debug %u\n", #if defined(DEBUG) 1); #else 0); #endif - return 0; + + return len; } -static int xfs_stat_proc_open(struct inode *inode, struct file *file) +void xfs_stats_clearall(struct xfsstats __percpu *stats) { - return single_open(file, xfs_stat_proc_show, NULL); + int c; + __uint32_t vn_active; + + xfs_notice(NULL, "Clearing xfsstats"); + for_each_possible_cpu(c) { + preempt_disable(); + /* save vn_active, it's a universal truth! */ + vn_active = per_cpu_ptr(stats, c)->vn_active; + memset(per_cpu_ptr(stats, c), 0, sizeof(*stats)); + per_cpu_ptr(stats, c)->vn_active = vn_active; + preempt_enable(); + } } -static const struct file_operations xfs_stat_proc_fops = { - .owner = THIS_MODULE, - .open = xfs_stat_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - /* legacy quota interfaces */ #ifdef CONFIG_XFS_QUOTA static int xqm_proc_show(struct seq_file *m, void *v) { /* maximum; incore; ratio free to inuse; freelist */ seq_printf(m, "%d\t%d\t%d\t%u\n", - 0, - counter_val(XFSSTAT_END_XQMSTAT), - 0, - counter_val(XFSSTAT_END_XQMSTAT + 1)); + 0, counter_val(xfsstats.xs_stats, XFSSTAT_END_XQMSTAT), + 0, counter_val(xfsstats.xs_stats, XFSSTAT_END_XQMSTAT + 1)); return 0; } @@ -136,7 +142,7 @@ static int xqmstat_proc_show(struct seq_file *m, void *v) seq_printf(m, "qm"); for (j = XFSSTAT_END_IBT_V2; j < XFSSTAT_END_XQMSTAT; j++) - seq_printf(m, " %u", counter_val(j)); + seq_printf(m, " %u", counter_val(xfsstats.xs_stats, j)); seq_putc(m, '\n'); return 0; } @@ -155,44 +161,35 @@ static const struct file_operations xqmstat_proc_fops = { }; #endif /* CONFIG_XFS_QUOTA */ +#ifdef CONFIG_PROC_FS int xfs_init_procfs(void) { if (!proc_mkdir("fs/xfs", NULL)) + return -ENOMEM; + + if (!proc_symlink("fs/xfs/stat", NULL, + "/sys/fs/xfs/stats/stats")) goto out; - if (!proc_create("fs/xfs/stat", 0, NULL, - &xfs_stat_proc_fops)) - goto out_remove_xfs_dir; #ifdef CONFIG_XFS_QUOTA if (!proc_create("fs/xfs/xqmstat", 0, NULL, &xqmstat_proc_fops)) - goto out_remove_stat_file; + goto out; if (!proc_create("fs/xfs/xqm", 0, NULL, &xqm_proc_fops)) - goto out_remove_xqmstat_file; + goto out; #endif return 0; -#ifdef CONFIG_XFS_QUOTA - out_remove_xqmstat_file: - remove_proc_entry("fs/xfs/xqmstat", NULL); - out_remove_stat_file: - remove_proc_entry("fs/xfs/stat", NULL); -#endif - out_remove_xfs_dir: - remove_proc_entry("fs/xfs", NULL); - out: +out: + remove_proc_subtree("fs/xfs", NULL); return -ENOMEM; } void xfs_cleanup_procfs(void) { -#ifdef CONFIG_XFS_QUOTA - remove_proc_entry("fs/xfs/xqm", NULL); - remove_proc_entry("fs/xfs/xqmstat", NULL); -#endif - remove_proc_entry("fs/xfs/stat", NULL); - remove_proc_entry("fs/xfs", NULL); + remove_proc_subtree("fs/xfs", NULL); } +#endif /* CONFIG_PROC_FS */ diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h index c8f238b8299a..483b0eff1988 100644 --- a/fs/xfs/xfs_stats.h +++ b/fs/xfs/xfs_stats.h @@ -19,8 +19,6 @@ #define __XFS_STATS_H__ -#if defined(CONFIG_PROC_FS) && !defined(XFS_STATS_OFF) - #include <linux/percpu.h> /* @@ -215,15 +213,29 @@ struct xfsstats { __uint64_t xs_read_bytes; }; -DECLARE_PER_CPU(struct xfsstats, xfsstats); +int xfs_stats_format(struct xfsstats __percpu *stats, char *buf); +void xfs_stats_clearall(struct xfsstats __percpu *stats); +extern struct xstats xfsstats; -/* - * We don't disable preempt, not too worried about poking the - * wrong CPU's stat for now (also aggregated before reporting). - */ -#define XFS_STATS_INC(v) (per_cpu(xfsstats, current_cpu()).v++) -#define XFS_STATS_DEC(v) (per_cpu(xfsstats, current_cpu()).v--) -#define XFS_STATS_ADD(v, inc) (per_cpu(xfsstats, current_cpu()).v += (inc)) +#define XFS_STATS_INC(mp, v) \ +do { \ + per_cpu_ptr(xfsstats.xs_stats, current_cpu())->v++; \ + per_cpu_ptr(mp->m_stats.xs_stats, current_cpu())->v++; \ +} while (0) + +#define XFS_STATS_DEC(mp, v) \ +do { \ + per_cpu_ptr(xfsstats.xs_stats, current_cpu())->v--; \ + per_cpu_ptr(mp->m_stats.xs_stats, current_cpu())->v--; \ +} while (0) + +#define XFS_STATS_ADD(mp, v, inc) \ +do { \ + per_cpu_ptr(xfsstats.xs_stats, current_cpu())->v += (inc); \ + per_cpu_ptr(mp->m_stats.xs_stats, current_cpu())->v += (inc); \ +} while (0) + +#if defined(CONFIG_PROC_FS) extern int xfs_init_procfs(void); extern void xfs_cleanup_procfs(void); @@ -231,10 +243,6 @@ extern void xfs_cleanup_procfs(void); #else /* !CONFIG_PROC_FS */ -# define XFS_STATS_INC(count) -# define XFS_STATS_DEC(count) -# define XFS_STATS_ADD(count, inc) - static inline int xfs_init_procfs(void) { return 0; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 904f637cfa5f..b35775752b74 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -137,7 +137,7 @@ static const match_table_t tokens = { }; -STATIC unsigned long +STATIC int suffix_kstrtoint(char *s, unsigned int base, int *res) { int last, shift_left_factor = 0, _res; @@ -838,17 +838,18 @@ xfs_init_mount_workqueues( goto out_destroy_unwritten; mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s", - WQ_FREEZABLE, 0, mp->m_fsname); + WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname); if (!mp->m_reclaim_workqueue) goto out_destroy_cil; mp->m_log_workqueue = alloc_workqueue("xfs-log/%s", - WQ_FREEZABLE|WQ_HIGHPRI, 0, mp->m_fsname); + WQ_MEM_RECLAIM|WQ_FREEZABLE|WQ_HIGHPRI, 0, + mp->m_fsname); if (!mp->m_log_workqueue) goto out_destroy_reclaim; mp->m_eofblocks_workqueue = alloc_workqueue("xfs-eofblocks/%s", - WQ_FREEZABLE, 0, mp->m_fsname); + WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname); if (!mp->m_eofblocks_workqueue) goto out_destroy_log; @@ -922,7 +923,7 @@ xfs_fs_destroy_inode( trace_xfs_destroy_inode(ip); - XFS_STATS_INC(vn_reclaim); + XFS_STATS_INC(ip->i_mount, vn_reclaim); ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0); @@ -983,8 +984,8 @@ xfs_fs_evict_inode( truncate_inode_pages_final(&inode->i_data); clear_inode(inode); - XFS_STATS_INC(vn_rele); - XFS_STATS_INC(vn_remove); + XFS_STATS_INC(ip->i_mount, vn_rele); + XFS_STATS_INC(ip->i_mount, vn_remove); xfs_inactive(ip); } @@ -1474,9 +1475,16 @@ xfs_fs_fill_super( if (error) goto out_destroy_workqueues; + /* Allocate stats memory before we do operations that might use it */ + mp->m_stats.xs_stats = alloc_percpu(struct xfsstats); + if (!mp->m_stats.xs_stats) { + error = -ENOMEM; + goto out_destroy_counters; + } + error = xfs_readsb(mp, flags); if (error) - goto out_destroy_counters; + goto out_free_stats; error = xfs_finish_flags(mp); if (error) @@ -1545,9 +1553,11 @@ xfs_fs_fill_super( xfs_filestream_unmount(mp); out_free_sb: xfs_freesb(mp); + out_free_stats: + free_percpu(mp->m_stats.xs_stats); out_destroy_counters: xfs_destroy_percpu_counters(mp); -out_destroy_workqueues: + out_destroy_workqueues: xfs_destroy_mount_workqueues(mp); out_close_devices: xfs_close_devices(mp); @@ -1574,6 +1584,7 @@ xfs_fs_put_super( xfs_unmountfs(mp); xfs_freesb(mp); + free_percpu(mp->m_stats.xs_stats); xfs_destroy_percpu_counters(mp); xfs_destroy_mount_workqueues(mp); xfs_close_devices(mp); @@ -1838,19 +1849,32 @@ init_xfs_fs(void) xfs_kset = kset_create_and_add("xfs", NULL, fs_kobj); if (!xfs_kset) { error = -ENOMEM; - goto out_sysctl_unregister;; + goto out_sysctl_unregister; + } + + xfsstats.xs_kobj.kobject.kset = xfs_kset; + + xfsstats.xs_stats = alloc_percpu(struct xfsstats); + if (!xfsstats.xs_stats) { + error = -ENOMEM; + goto out_kset_unregister; } + error = xfs_sysfs_init(&xfsstats.xs_kobj, &xfs_stats_ktype, NULL, + "stats"); + if (error) + goto out_free_stats; + #ifdef DEBUG xfs_dbg_kobj.kobject.kset = xfs_kset; error = xfs_sysfs_init(&xfs_dbg_kobj, &xfs_dbg_ktype, NULL, "debug"); if (error) - goto out_kset_unregister; + goto out_remove_stats_kobj; #endif error = xfs_qm_init(); if (error) - goto out_remove_kobj; + goto out_remove_dbg_kobj; error = register_filesystem(&xfs_fs_type); if (error) @@ -1859,11 +1883,15 @@ init_xfs_fs(void) out_qm_exit: xfs_qm_exit(); - out_remove_kobj: + out_remove_dbg_kobj: #ifdef DEBUG xfs_sysfs_del(&xfs_dbg_kobj); - out_kset_unregister: + out_remove_stats_kobj: #endif + xfs_sysfs_del(&xfsstats.xs_kobj); + out_free_stats: + free_percpu(xfsstats.xs_stats); + out_kset_unregister: kset_unregister(xfs_kset); out_sysctl_unregister: xfs_sysctl_unregister(); @@ -1889,6 +1917,8 @@ exit_xfs_fs(void) #ifdef DEBUG xfs_sysfs_del(&xfs_dbg_kobj); #endif + xfs_sysfs_del(&xfsstats.xs_kobj); + free_percpu(xfsstats.xs_stats); kset_unregister(xfs_kset); xfs_sysctl_unregister(); xfs_cleanup_procfs(); @@ -1896,6 +1926,7 @@ exit_xfs_fs(void) xfs_mru_cache_uninit(); xfs_destroy_workqueues(); xfs_destroy_zones(); + xfs_uuid_table_free(); } module_init(init_xfs_fs); diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 996481eeb491..b44284c1adda 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -178,7 +178,6 @@ xfs_symlink( struct xfs_bmap_free free_list; xfs_fsblock_t first_block; bool unlock_dp_on_error = false; - int committed; xfs_fileoff_t first_fsb; xfs_filblks_t fs_blocks; int nmaps; @@ -387,7 +386,7 @@ xfs_symlink( xfs_trans_set_sync(tp); } - error = xfs_bmap_finish(&tp, &free_list, &committed); + error = xfs_bmap_finish(&tp, &free_list, NULL); if (error) goto out_bmap_cancel; @@ -434,7 +433,6 @@ xfs_inactive_symlink_rmt( struct xfs_inode *ip) { xfs_buf_t *bp; - int committed; int done; int error; xfs_fsblock_t first_block; @@ -510,16 +508,10 @@ xfs_inactive_symlink_rmt( /* * Commit the first transaction. This logs the EFI and the inode. */ - error = xfs_bmap_finish(&tp, &free_list, &committed); + error = xfs_bmap_finish(&tp, &free_list, ip); if (error) goto error_bmap_cancel; /* - * The transaction must have been committed, since there were - * actually extents freed by xfs_bunmapi. See xfs_bmap_finish. - * The new tp has the extent freeing and EFDs. - */ - ASSERT(committed); - /* * The first xact was committed, so add the inode to the new one. * Mark it dirty so it will be logged and moved forward in the log as * part of every commit. diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c index a0c8067cea6f..aed74d3f8da9 100644 --- a/fs/xfs/xfs_sysctl.c +++ b/fs/xfs/xfs_sysctl.c @@ -19,6 +19,7 @@ #include <linux/sysctl.h> #include <linux/proc_fs.h> #include "xfs_error.h" +#include "xfs_stats.h" static struct ctl_table_header *xfs_table_header; @@ -31,22 +32,12 @@ xfs_stats_clear_proc_handler( size_t *lenp, loff_t *ppos) { - int c, ret, *valp = ctl->data; - __uint32_t vn_active; + int ret, *valp = ctl->data; ret = proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); if (!ret && write && *valp) { - xfs_notice(NULL, "Clearing xfsstats"); - for_each_possible_cpu(c) { - preempt_disable(); - /* save vn_active, it's a universal truth! */ - vn_active = per_cpu(xfsstats, c).vn_active; - memset(&per_cpu(xfsstats, c), 0, - sizeof(struct xfsstats)); - per_cpu(xfsstats, c).vn_active = vn_active; - preempt_enable(); - } + xfs_stats_clearall(xfsstats.xs_stats); xfs_stats_clear = 0; } diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index aa03670851d8..641d625eb334 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -21,11 +21,13 @@ #include "xfs_log_format.h" #include "xfs_log.h" #include "xfs_log_priv.h" +#include "xfs_stats.h" struct xfs_sysfs_attr { struct attribute attr; - ssize_t (*show)(char *buf, void *data); - ssize_t (*store)(const char *buf, size_t count, void *data); + ssize_t (*show)(struct kobject *kobject, char *buf); + ssize_t (*store)(struct kobject *kobject, const char *buf, + size_t count); }; static inline struct xfs_sysfs_attr * @@ -38,6 +40,8 @@ to_attr(struct attribute *attr) static struct xfs_sysfs_attr xfs_sysfs_attr_##name = __ATTR_RW(name) #define XFS_SYSFS_ATTR_RO(name) \ static struct xfs_sysfs_attr xfs_sysfs_attr_##name = __ATTR_RO(name) +#define XFS_SYSFS_ATTR_WO(name) \ + static struct xfs_sysfs_attr xfs_sysfs_attr_##name = __ATTR_WO(name) #define ATTR_LIST(name) &xfs_sysfs_attr_##name.attr @@ -51,14 +55,42 @@ struct kobj_type xfs_mp_ktype = { .release = xfs_sysfs_release, }; +STATIC ssize_t +xfs_sysfs_object_show( + struct kobject *kobject, + struct attribute *attr, + char *buf) +{ + struct xfs_sysfs_attr *xfs_attr = to_attr(attr); + + return xfs_attr->show ? xfs_attr->show(kobject, buf) : 0; +} + +STATIC ssize_t +xfs_sysfs_object_store( + struct kobject *kobject, + struct attribute *attr, + const char *buf, + size_t count) +{ + struct xfs_sysfs_attr *xfs_attr = to_attr(attr); + + return xfs_attr->store ? xfs_attr->store(kobject, buf, count) : 0; +} + +static const struct sysfs_ops xfs_sysfs_ops = { + .show = xfs_sysfs_object_show, + .store = xfs_sysfs_object_store, +}; + #ifdef DEBUG /* debug */ STATIC ssize_t log_recovery_delay_store( + struct kobject *kobject, const char *buf, - size_t count, - void *data) + size_t count) { int ret; int val; @@ -77,8 +109,8 @@ log_recovery_delay_store( STATIC ssize_t log_recovery_delay_show( - char *buf, - void *data) + struct kobject *kobject, + char *buf) { return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.log_recovery_delay); } @@ -89,52 +121,87 @@ static struct attribute *xfs_dbg_attrs[] = { NULL, }; +struct kobj_type xfs_dbg_ktype = { + .release = xfs_sysfs_release, + .sysfs_ops = &xfs_sysfs_ops, + .default_attrs = xfs_dbg_attrs, +}; + +#endif /* DEBUG */ + +/* stats */ + +static inline struct xstats * +to_xstats(struct kobject *kobject) +{ + struct xfs_kobj *kobj = to_kobj(kobject); + + return container_of(kobj, struct xstats, xs_kobj); +} + STATIC ssize_t -xfs_dbg_show( - struct kobject *kobject, - struct attribute *attr, - char *buf) +stats_show( + struct kobject *kobject, + char *buf) { - struct xfs_sysfs_attr *xfs_attr = to_attr(attr); + struct xstats *stats = to_xstats(kobject); - return xfs_attr->show ? xfs_attr->show(buf, NULL) : 0; + return xfs_stats_format(stats->xs_stats, buf); } +XFS_SYSFS_ATTR_RO(stats); STATIC ssize_t -xfs_dbg_store( - struct kobject *kobject, - struct attribute *attr, - const char *buf, - size_t count) +stats_clear_store( + struct kobject *kobject, + const char *buf, + size_t count) { - struct xfs_sysfs_attr *xfs_attr = to_attr(attr); + int ret; + int val; + struct xstats *stats = to_xstats(kobject); + + ret = kstrtoint(buf, 0, &val); + if (ret) + return ret; - return xfs_attr->store ? xfs_attr->store(buf, count, NULL) : 0; + if (val != 1) + return -EINVAL; + + xfs_stats_clearall(stats->xs_stats); + return count; } +XFS_SYSFS_ATTR_WO(stats_clear); -static struct sysfs_ops xfs_dbg_ops = { - .show = xfs_dbg_show, - .store = xfs_dbg_store, +static struct attribute *xfs_stats_attrs[] = { + ATTR_LIST(stats), + ATTR_LIST(stats_clear), + NULL, }; -struct kobj_type xfs_dbg_ktype = { +struct kobj_type xfs_stats_ktype = { .release = xfs_sysfs_release, - .sysfs_ops = &xfs_dbg_ops, - .default_attrs = xfs_dbg_attrs, + .sysfs_ops = &xfs_sysfs_ops, + .default_attrs = xfs_stats_attrs, }; -#endif /* DEBUG */ - /* xlog */ +static inline struct xlog * +to_xlog(struct kobject *kobject) +{ + struct xfs_kobj *kobj = to_kobj(kobject); + + return container_of(kobj, struct xlog, l_kobj); +} + STATIC ssize_t log_head_lsn_show( - char *buf, - void *data) + struct kobject *kobject, + char *buf) { - struct xlog *log = data; int cycle; int block; + struct xlog *log = to_xlog(kobject); spin_lock(&log->l_icloglock); cycle = log->l_curr_cycle; @@ -147,12 +214,12 @@ XFS_SYSFS_ATTR_RO(log_head_lsn); STATIC ssize_t log_tail_lsn_show( - char *buf, - void *data) + struct kobject *kobject, + char *buf) { - struct xlog *log = data; int cycle; int block; + struct xlog *log = to_xlog(kobject); xlog_crack_atomic_lsn(&log->l_tail_lsn, &cycle, &block); return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, block); @@ -161,12 +228,13 @@ XFS_SYSFS_ATTR_RO(log_tail_lsn); STATIC ssize_t reserve_grant_head_show( - char *buf, - void *data) + struct kobject *kobject, + char *buf) + { - struct xlog *log = data; int cycle; int bytes; + struct xlog *log = to_xlog(kobject); xlog_crack_grant_head(&log->l_reserve_head.grant, &cycle, &bytes); return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, bytes); @@ -175,65 +243,64 @@ XFS_SYSFS_ATTR_RO(reserve_grant_head); STATIC ssize_t write_grant_head_show( - char *buf, - void *data) + struct kobject *kobject, + char *buf) { - struct xlog *log = data; int cycle; int bytes; + struct xlog *log = to_xlog(kobject); xlog_crack_grant_head(&log->l_write_head.grant, &cycle, &bytes); return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, bytes); } XFS_SYSFS_ATTR_RO(write_grant_head); -static struct attribute *xfs_log_attrs[] = { - ATTR_LIST(log_head_lsn), - ATTR_LIST(log_tail_lsn), - ATTR_LIST(reserve_grant_head), - ATTR_LIST(write_grant_head), - NULL, -}; - -static inline struct xlog * -to_xlog(struct kobject *kobject) -{ - struct xfs_kobj *kobj = to_kobj(kobject); - return container_of(kobj, struct xlog, l_kobj); -} - +#ifdef DEBUG STATIC ssize_t -xfs_log_show( - struct kobject *kobject, - struct attribute *attr, - char *buf) +log_badcrc_factor_store( + struct kobject *kobject, + const char *buf, + size_t count) { - struct xlog *log = to_xlog(kobject); - struct xfs_sysfs_attr *xfs_attr = to_attr(attr); + struct xlog *log = to_xlog(kobject); + int ret; + uint32_t val; - return xfs_attr->show ? xfs_attr->show(buf, log) : 0; + ret = kstrtouint(buf, 0, &val); + if (ret) + return ret; + + log->l_badcrc_factor = val; + + return count; } STATIC ssize_t -xfs_log_store( - struct kobject *kobject, - struct attribute *attr, - const char *buf, - size_t count) +log_badcrc_factor_show( + struct kobject *kobject, + char *buf) { - struct xlog *log = to_xlog(kobject); - struct xfs_sysfs_attr *xfs_attr = to_attr(attr); + struct xlog *log = to_xlog(kobject); - return xfs_attr->store ? xfs_attr->store(buf, count, log) : 0; + return snprintf(buf, PAGE_SIZE, "%d\n", log->l_badcrc_factor); } -static struct sysfs_ops xfs_log_ops = { - .show = xfs_log_show, - .store = xfs_log_store, +XFS_SYSFS_ATTR_RW(log_badcrc_factor); +#endif /* DEBUG */ + +static struct attribute *xfs_log_attrs[] = { + ATTR_LIST(log_head_lsn), + ATTR_LIST(log_tail_lsn), + ATTR_LIST(reserve_grant_head), + ATTR_LIST(write_grant_head), +#ifdef DEBUG + ATTR_LIST(log_badcrc_factor), +#endif + NULL, }; struct kobj_type xfs_log_ktype = { .release = xfs_sysfs_release, - .sysfs_ops = &xfs_log_ops, + .sysfs_ops = &xfs_sysfs_ops, .default_attrs = xfs_log_attrs, }; diff --git a/fs/xfs/xfs_sysfs.h b/fs/xfs/xfs_sysfs.h index 240eee35f342..be692e59938d 100644 --- a/fs/xfs/xfs_sysfs.h +++ b/fs/xfs/xfs_sysfs.h @@ -22,6 +22,7 @@ extern struct kobj_type xfs_mp_ktype; /* xfs_mount */ extern struct kobj_type xfs_dbg_ktype; /* debug */ extern struct kobj_type xfs_log_ktype; /* xlog */ +extern struct kobj_type xfs_stats_ktype; /* stats */ static inline struct xfs_kobj * to_kobj(struct kobject *kobject) diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 5ed36b1e04c1..391d797cb53f 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -689,6 +689,7 @@ DEFINE_INODE_EVENT(xfs_inode_free_eofblocks_invalid); DEFINE_INODE_EVENT(xfs_filemap_fault); DEFINE_INODE_EVENT(xfs_filemap_pmd_fault); DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite); +DEFINE_INODE_EVENT(xfs_filemap_pfn_mkwrite); DECLARE_EVENT_CLASS(xfs_iref_class, TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip), @@ -1221,6 +1222,32 @@ DEFINE_PAGE_EVENT(xfs_writepage); DEFINE_PAGE_EVENT(xfs_releasepage); DEFINE_PAGE_EVENT(xfs_invalidatepage); +DECLARE_EVENT_CLASS(xfs_readpage_class, + TP_PROTO(struct inode *inode, int nr_pages), + TP_ARGS(inode, nr_pages), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_ino_t, ino) + __field(int, nr_pages) + ), + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->nr_pages = nr_pages; + ), + TP_printk("dev %d:%d ino 0x%llx nr_pages %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->nr_pages) +) + +#define DEFINE_READPAGE_EVENT(name) \ +DEFINE_EVENT(xfs_readpage_class, name, \ + TP_PROTO(struct inode *inode, int nr_pages), \ + TP_ARGS(inode, nr_pages)) +DEFINE_READPAGE_EVENT(xfs_vm_readpage); +DEFINE_READPAGE_EVENT(xfs_vm_readpages); + DECLARE_EVENT_CLASS(xfs_imap_class, TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count, int type, struct xfs_bmbt_irec *irec), @@ -1312,6 +1339,7 @@ DEFINE_SIMPLE_IO_EVENT(xfs_delalloc_enospc); DEFINE_SIMPLE_IO_EVENT(xfs_unwritten_convert); DEFINE_SIMPLE_IO_EVENT(xfs_get_blocks_notfound); DEFINE_SIMPLE_IO_EVENT(xfs_setfilesize); +DEFINE_SIMPLE_IO_EVENT(xfs_zero_eof); DECLARE_EVENT_CLASS(xfs_itrunc_class, TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size), diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index a0ab1dae9c31..748b16aff45a 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -930,9 +930,9 @@ __xfs_trans_commit( */ if (sync) { error = _xfs_log_force_lsn(mp, commit_lsn, XFS_LOG_SYNC, NULL); - XFS_STATS_INC(xs_trans_sync); + XFS_STATS_INC(mp, xs_trans_sync); } else { - XFS_STATS_INC(xs_trans_async); + XFS_STATS_INC(mp, xs_trans_async); } return error; @@ -955,7 +955,7 @@ out_unreserve: xfs_trans_free_items(tp, NULLCOMMITLSN, !!error); xfs_trans_free(tp); - XFS_STATS_INC(xs_trans_empty); + XFS_STATS_INC(mp, xs_trans_empty); return error; } diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 1098cf490189..aa67339b9537 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -349,7 +349,7 @@ xfsaild_push( xfs_ail_min_lsn(ailp))) { ailp->xa_log_flush = 0; - XFS_STATS_INC(xs_push_ail_flush); + XFS_STATS_INC(mp, xs_push_ail_flush); xfs_log_force(mp, XFS_LOG_SYNC); } @@ -371,7 +371,7 @@ xfsaild_push( goto out_done; } - XFS_STATS_INC(xs_push_ail); + XFS_STATS_INC(mp, xs_push_ail); lsn = lip->li_lsn; while ((XFS_LSN_CMP(lip->li_lsn, target) <= 0)) { @@ -385,7 +385,7 @@ xfsaild_push( lock_result = lip->li_ops->iop_push(lip, &ailp->xa_buf_list); switch (lock_result) { case XFS_ITEM_SUCCESS: - XFS_STATS_INC(xs_push_ail_success); + XFS_STATS_INC(mp, xs_push_ail_success); trace_xfs_ail_push(lip); ailp->xa_last_pushed_lsn = lsn; @@ -403,7 +403,7 @@ xfsaild_push( * re-try the flushing relatively soon if most of the * AIL is beeing flushed. */ - XFS_STATS_INC(xs_push_ail_flushing); + XFS_STATS_INC(mp, xs_push_ail_flushing); trace_xfs_ail_flushing(lip); flushing++; @@ -411,14 +411,14 @@ xfsaild_push( break; case XFS_ITEM_PINNED: - XFS_STATS_INC(xs_push_ail_pinned); + XFS_STATS_INC(mp, xs_push_ail_pinned); trace_xfs_ail_pinned(lip); stuck++; ailp->xa_log_flush++; break; case XFS_ITEM_LOCKED: - XFS_STATS_INC(xs_push_ail_locked); + XFS_STATS_INC(mp, xs_push_ail_locked); trace_xfs_ail_locked(lip); stuck++; @@ -497,6 +497,7 @@ xfsaild( long tout = 0; /* milliseconds */ current->flags |= PF_MEMALLOC; + set_freezable(); while (!kthread_should_stop()) { if (tout && tout <= 20) diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index ce78534a047e..995170194df0 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -572,12 +572,16 @@ xfs_quota_warn( struct xfs_dquot *dqp, int type) { - /* no warnings for project quotas - we just return ENOSPC later */ + enum quota_type qtype; + if (dqp->dq_flags & XFS_DQ_PROJ) - return; - quota_send_warning(make_kqid(&init_user_ns, - (dqp->dq_flags & XFS_DQ_USER) ? - USRQUOTA : GRPQUOTA, + qtype = PRJQUOTA; + else if (dqp->dq_flags & XFS_DQ_USER) + qtype = USRQUOTA; + else + qtype = GRPQUOTA; + + quota_send_warning(make_kqid(&init_user_ns, qtype, be32_to_cpu(dqp->q_core.d_id)), mp->m_super->s_dev, type); } diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c index 17280cd71934..b97f1df910ab 100644 --- a/fs/xfs/xfs_trans_inode.c +++ b/fs/xfs/xfs_trans_inode.c @@ -108,6 +108,15 @@ xfs_trans_log_inode( ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); /* + * Record the specific change for fdatasync optimisation. This + * allows fdatasync to skip log forces for inodes that are only + * timestamp dirty. We do this before the change count so that + * the core being logged in this case does not impact on fdatasync + * behaviour. + */ + ip->i_itemp->ili_fsync_fields |= flags; + + /* * First time we log the inode in a transaction, bump the inode change * counter if it is configured for this to occur. We don't use * inode_inc_version() because there is no need for extra locking around diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index c036815183cb..110f1d7d86b0 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -32,15 +32,13 @@ static int -xfs_xattr_get(struct dentry *dentry, const char *name, - void *value, size_t size, int xflags) +xfs_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, + const char *name, void *value, size_t size) { + int xflags = handler->flags; struct xfs_inode *ip = XFS_I(d_inode(dentry)); int error, asize = size; - if (strcmp(name, "") == 0) - return -EINVAL; - /* Convert Linux syscall to XFS internal ATTR flags */ if (!size) { xflags |= ATTR_KERNOVAL; @@ -53,14 +51,35 @@ xfs_xattr_get(struct dentry *dentry, const char *name, return asize; } -static int -xfs_xattr_set(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags, int xflags) +void +xfs_forget_acl( + struct inode *inode, + const char *name, + int xflags) { - struct xfs_inode *ip = XFS_I(d_inode(dentry)); + /* + * Invalidate any cached ACLs if the user has bypassed the ACL + * interface. We don't validate the content whatsoever so it is caller + * responsibility to provide data in valid format and ensure i_mode is + * consistent. + */ + if (xflags & ATTR_ROOT) { +#ifdef CONFIG_XFS_POSIX_ACL + if (!strcmp(name, SGI_ACL_FILE)) + forget_cached_acl(inode, ACL_TYPE_ACCESS); + else if (!strcmp(name, SGI_ACL_DEFAULT)) + forget_cached_acl(inode, ACL_TYPE_DEFAULT); +#endif + } +} - if (strcmp(name, "") == 0) - return -EINVAL; +static int +xfs_xattr_set(const struct xattr_handler *handler, struct dentry *dentry, + const char *name, const void *value, size_t size, int flags) +{ + int xflags = handler->flags; + struct xfs_inode *ip = XFS_I(d_inode(dentry)); + int error; /* Convert Linux syscall to XFS internal ATTR flags */ if (flags & XATTR_CREATE) @@ -70,8 +89,12 @@ xfs_xattr_set(struct dentry *dentry, const char *name, const void *value, if (!value) return xfs_attr_remove(ip, (unsigned char *)name, xflags); - return xfs_attr_set(ip, (unsigned char *)name, + error = xfs_attr_set(ip, (unsigned char *)name, (void *)value, size, xflags); + if (!error) + xfs_forget_acl(d_inode(dentry), name, xflags); + + return error; } static const struct xattr_handler xfs_xattr_user_handler = { @@ -106,47 +129,19 @@ const struct xattr_handler *xfs_xattr_handlers[] = { NULL }; -static unsigned int xfs_xattr_prefix_len(int flags) -{ - if (flags & XFS_ATTR_SECURE) - return sizeof("security"); - else if (flags & XFS_ATTR_ROOT) - return sizeof("trusted"); - else - return sizeof("user"); -} - -static const char *xfs_xattr_prefix(int flags) -{ - if (flags & XFS_ATTR_SECURE) - return xfs_xattr_security_handler.prefix; - else if (flags & XFS_ATTR_ROOT) - return xfs_xattr_trusted_handler.prefix; - else - return xfs_xattr_user_handler.prefix; -} - static int -xfs_xattr_put_listent( +__xfs_xattr_put_listent( struct xfs_attr_list_context *context, - int flags, - unsigned char *name, - int namelen, - int valuelen, - unsigned char *value) + char *prefix, + int prefix_len, + unsigned char *name, + int namelen) { - unsigned int prefix_len = xfs_xattr_prefix_len(flags); char *offset; int arraytop; - ASSERT(context->count >= 0); - - /* - * Only show root namespace entries if we are actually allowed to - * see them. - */ - if ((flags & XFS_ATTR_ROOT) && !capable(CAP_SYS_ADMIN)) - return 0; + if (!context->alist) + goto compute_size; arraytop = context->count + prefix_len + namelen + 1; if (arraytop > context->firstu) { @@ -154,17 +149,19 @@ xfs_xattr_put_listent( return 1; } offset = (char *)context->alist + context->count; - strncpy(offset, xfs_xattr_prefix(flags), prefix_len); + strncpy(offset, prefix, prefix_len); offset += prefix_len; strncpy(offset, (char *)name, namelen); /* real name */ offset += namelen; *offset = '\0'; + +compute_size: context->count += prefix_len + namelen + 1; return 0; } static int -xfs_xattr_put_listent_sizes( +xfs_xattr_put_listent( struct xfs_attr_list_context *context, int flags, unsigned char *name, @@ -172,24 +169,55 @@ xfs_xattr_put_listent_sizes( int valuelen, unsigned char *value) { - context->count += xfs_xattr_prefix_len(flags) + namelen + 1; - return 0; -} + char *prefix; + int prefix_len; -static int -list_one_attr(const char *name, const size_t len, void *data, - size_t size, ssize_t *result) -{ - char *p = data + *result; + ASSERT(context->count >= 0); - *result += len; - if (!size) - return 0; - if (*result > size) - return -ERANGE; + if (flags & XFS_ATTR_ROOT) { +#ifdef CONFIG_XFS_POSIX_ACL + if (namelen == SGI_ACL_FILE_SIZE && + strncmp(name, SGI_ACL_FILE, + SGI_ACL_FILE_SIZE) == 0) { + int ret = __xfs_xattr_put_listent( + context, XATTR_SYSTEM_PREFIX, + XATTR_SYSTEM_PREFIX_LEN, + XATTR_POSIX_ACL_ACCESS, + strlen(XATTR_POSIX_ACL_ACCESS)); + if (ret) + return ret; + } else if (namelen == SGI_ACL_DEFAULT_SIZE && + strncmp(name, SGI_ACL_DEFAULT, + SGI_ACL_DEFAULT_SIZE) == 0) { + int ret = __xfs_xattr_put_listent( + context, XATTR_SYSTEM_PREFIX, + XATTR_SYSTEM_PREFIX_LEN, + XATTR_POSIX_ACL_DEFAULT, + strlen(XATTR_POSIX_ACL_DEFAULT)); + if (ret) + return ret; + } +#endif - strcpy(p, name); - return 0; + /* + * Only show root namespace entries if we are actually allowed to + * see them. + */ + if (!capable(CAP_SYS_ADMIN)) + return 0; + + prefix = XATTR_TRUSTED_PREFIX; + prefix_len = XATTR_TRUSTED_PREFIX_LEN; + } else if (flags & XFS_ATTR_SECURE) { + prefix = XATTR_SECURITY_PREFIX; + prefix_len = XATTR_SECURITY_PREFIX_LEN; + } else { + prefix = XATTR_USER_PREFIX; + prefix_len = XATTR_USER_PREFIX_LEN; + } + + return __xfs_xattr_put_listent(context, prefix, prefix_len, name, + namelen); } ssize_t @@ -198,7 +226,6 @@ xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size) struct xfs_attr_list_context context; struct attrlist_cursor_kern cursor = { 0 }; struct inode *inode = d_inode(dentry); - int error; /* * First read the regular on-disk attributes. @@ -207,37 +234,14 @@ xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size) context.dp = XFS_I(inode); context.cursor = &cursor; context.resynch = 1; - context.alist = data; + context.alist = size ? data : NULL; context.bufsize = size; context.firstu = context.bufsize; - - if (size) - context.put_listent = xfs_xattr_put_listent; - else - context.put_listent = xfs_xattr_put_listent_sizes; + context.put_listent = xfs_xattr_put_listent; xfs_attr_list_int(&context); if (context.count < 0) return -ERANGE; - /* - * Then add the two synthetic ACL attributes. - */ - if (posix_acl_access_exists(inode)) { - error = list_one_attr(POSIX_ACL_XATTR_ACCESS, - strlen(POSIX_ACL_XATTR_ACCESS) + 1, - data, size, &context.count); - if (error) - return error; - } - - if (posix_acl_default_exists(inode)) { - error = list_one_attr(POSIX_ACL_XATTR_DEFAULT, - strlen(POSIX_ACL_XATTR_DEFAULT) + 1, - data, size, &context.count); - if (error) - return error; - } - return context.count; } |