From c0ba7e5147829eaa607351997bccd06200a8db12 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Mon, 25 Sep 2006 16:24:16 -0700 Subject: [PATCH] autofs4: zero timeout prevents shutdown If the timeout of an autofs mount is set to zero then umounts are disabled. This works fine, however the kernel module checks the expire timeout and goes no further if it is zero. This is not the right thing to do at shutdown as the module is passed an option to expire mounts regardless of their timeout setting. This patch allows autofs to honor the force expire option. Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/autofs4/expire.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 8dbd44f..d96e5c1 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -32,7 +32,7 @@ static inline int autofs4_can_expire(struct dentry *dentry, if (!do_now) { /* Too young to die */ - if (time_after(ino->last_used + timeout, now)) + if (!timeout || time_after(ino->last_used + timeout, now)) return 0; /* update last_used here :- @@ -253,7 +253,7 @@ static struct dentry *autofs4_expire_direct(struct super_block *sb, struct dentry *root = dget(sb->s_root); int do_now = how & AUTOFS_EXP_IMMEDIATE; - if (!sbi->exp_timeout || !root) + if (!root) return NULL; now = jiffies; @@ -293,7 +293,7 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb, int do_now = how & AUTOFS_EXP_IMMEDIATE; int exp_leaves = how & AUTOFS_EXP_LEAVES; - if ( !sbi->exp_timeout || !root ) + if (!root) return NULL; now = jiffies; -- cgit v1.1 From eea3f8911f34001d2450a272c2d02f175279b53c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Juha=20Yrj=F6l=E4?= Date: Thu, 3 Aug 2006 19:06:25 +0300 Subject: sysfs: Make poll behaviour consistent When no events have been reported by sysfs_notify(), sd->s_events was previously set to zero. The initial value for new readers is also zero, so poll was blocking, regardless of whether the attribute was read by the process or not. Make poll behave consistently by setting the initial value of sd->s_events to non-zero. Signed-off-by: Juha Yrjola Signed-off-by: Greg Kroah-Hartman --- fs/sysfs/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 61c4243..5f3d725 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -43,7 +43,7 @@ static struct sysfs_dirent * sysfs_new_dirent(struct sysfs_dirent * parent_sd, memset(sd, 0, sizeof(*sd)); atomic_set(&sd->s_count, 1); - atomic_set(&sd->s_event, 0); + atomic_set(&sd->s_event, 1); INIT_LIST_HEAD(&sd->s_children); list_add(&sd->s_sibling, &parent_sd->s_children); sd->s_element = element; -- cgit v1.1 From 6468b3afa7bcd9b0abc5997e5330d78f0bb6626a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 20 Jul 2006 08:16:42 -0700 Subject: Debugfs: kernel-doc fixes for debugfs Fix kernel-doc and typos/spellos in fs/debugfs/. Signed-off-by: Randy Dunlap Signed-off-by: Greg Kroah-Hartman --- fs/debugfs/file.c | 56 ++++++++++++++++++++++++------------------------------ fs/debugfs/inode.c | 15 ++++++--------- 2 files changed, 31 insertions(+), 40 deletions(-) (limited to 'fs') diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 39640fd..e4b4305 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -55,12 +55,11 @@ static u64 debugfs_u8_get(void *data) DEFINE_SIMPLE_ATTRIBUTE(fops_u8, debugfs_u8_get, debugfs_u8_set, "%llu\n"); /** - * debugfs_create_u8 - create a file in the debugfs filesystem that is used to read and write an unsigned 8 bit value. - * + * debugfs_create_u8 - create a debugfs file that is used to read and write an unsigned 8-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a - * directory dentry if set. If this paramater is NULL, then the + * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. @@ -72,11 +71,11 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u8, debugfs_u8_get, debugfs_u8_set, "%llu\n"); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, NULL will be returned. + * you are responsible here.) If an error occurs, %NULL will be returned. * - * If debugfs is not enabled in the kernel, the value -ENODEV will be + * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. It is not wise to check for this value, but rather, check for - * NULL or !NULL instead as to eliminate the need for #ifdef in the calling + * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling * code. */ struct dentry *debugfs_create_u8(const char *name, mode_t mode, @@ -97,12 +96,11 @@ static u64 debugfs_u16_get(void *data) DEFINE_SIMPLE_ATTRIBUTE(fops_u16, debugfs_u16_get, debugfs_u16_set, "%llu\n"); /** - * debugfs_create_u16 - create a file in the debugfs filesystem that is used to read and write an unsigned 16 bit value. - * + * debugfs_create_u16 - create a debugfs file that is used to read and write an unsigned 16-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a - * directory dentry if set. If this paramater is NULL, then the + * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. @@ -114,11 +112,11 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u16, debugfs_u16_get, debugfs_u16_set, "%llu\n"); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, NULL will be returned. + * you are responsible here.) If an error occurs, %NULL will be returned. * - * If debugfs is not enabled in the kernel, the value -ENODEV will be + * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. It is not wise to check for this value, but rather, check for - * NULL or !NULL instead as to eliminate the need for #ifdef in the calling + * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling * code. */ struct dentry *debugfs_create_u16(const char *name, mode_t mode, @@ -139,12 +137,11 @@ static u64 debugfs_u32_get(void *data) DEFINE_SIMPLE_ATTRIBUTE(fops_u32, debugfs_u32_get, debugfs_u32_set, "%llu\n"); /** - * debugfs_create_u32 - create a file in the debugfs filesystem that is used to read and write an unsigned 32 bit value. - * + * debugfs_create_u32 - create a debugfs file that is used to read and write an unsigned 32-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a - * directory dentry if set. If this paramater is NULL, then the + * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. @@ -156,11 +153,11 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u32, debugfs_u32_get, debugfs_u32_set, "%llu\n"); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, NULL will be returned. + * you are responsible here.) If an error occurs, %NULL will be returned. * - * If debugfs is not enabled in the kernel, the value -ENODEV will be + * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. It is not wise to check for this value, but rather, check for - * NULL or !NULL instead as to eliminate the need for #ifdef in the calling + * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling * code. */ struct dentry *debugfs_create_u32(const char *name, mode_t mode, @@ -219,12 +216,11 @@ static const struct file_operations fops_bool = { }; /** - * debugfs_create_bool - create a file in the debugfs filesystem that is used to read and write a boolean value. - * + * debugfs_create_bool - create a debugfs file that is used to read and write a boolean value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a - * directory dentry if set. If this paramater is NULL, then the + * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. @@ -236,11 +232,11 @@ static const struct file_operations fops_bool = { * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, NULL will be returned. + * you are responsible here.) If an error occurs, %NULL will be returned. * - * If debugfs is not enabled in the kernel, the value -ENODEV will be + * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. It is not wise to check for this value, but rather, check for - * NULL or !NULL instead as to eliminate the need for #ifdef in the calling + * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling * code. */ struct dentry *debugfs_create_bool(const char *name, mode_t mode, @@ -264,13 +260,11 @@ static struct file_operations fops_blob = { }; /** - * debugfs_create_blob - create a file in the debugfs filesystem that is - * used to read and write a binary blob. - * + * debugfs_create_blob - create a debugfs file that is used to read and write a binary blob * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a - * directory dentry if set. If this paramater is NULL, then the + * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @blob: a pointer to a struct debugfs_blob_wrapper which contains a pointer * to the blob data and the size of the data. @@ -282,11 +276,11 @@ static struct file_operations fops_blob = { * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, NULL will be returned. + * you are responsible here.) If an error occurs, %NULL will be returned. * - * If debugfs is not enabled in the kernel, the value -ENODEV will be + * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. It is not wise to check for this value, but rather, check for - * NULL or !NULL instead as to eliminate the need for #ifdef in the calling + * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling * code. */ struct dentry *debugfs_create_blob(const char *name, mode_t mode, diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index e8ae304..3ca268d 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -162,7 +162,6 @@ static int debugfs_create_by_name(const char *name, mode_t mode, /** * debugfs_create_file - create a file in the debugfs filesystem - * * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a @@ -182,11 +181,11 @@ static int debugfs_create_by_name(const char *name, mode_t mode, * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, NULL will be returned. + * you are responsible here.) If an error occurs, %NULL will be returned. * - * If debugfs is not enabled in the kernel, the value -ENODEV will be + * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. It is not wise to check for this value, but rather, check for - * NULL or !NULL instead as to eliminate the need for #ifdef in the calling + * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling * code. */ struct dentry *debugfs_create_file(const char *name, mode_t mode, @@ -221,7 +220,6 @@ EXPORT_SYMBOL_GPL(debugfs_create_file); /** * debugfs_create_dir - create a directory in the debugfs filesystem - * * @name: a pointer to a string containing the name of the directory to * create. * @parent: a pointer to the parent dentry for this file. This should be a @@ -233,11 +231,11 @@ EXPORT_SYMBOL_GPL(debugfs_create_file); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, NULL will be returned. + * you are responsible here.) If an error occurs, %NULL will be returned. * - * If debugfs is not enabled in the kernel, the value -ENODEV will be + * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. It is not wise to check for this value, but rather, check for - * NULL or !NULL instead as to eliminate the need for #ifdef in the calling + * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling * code. */ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) @@ -250,7 +248,6 @@ EXPORT_SYMBOL_GPL(debugfs_create_dir); /** * debugfs_remove - removes a file or directory from the debugfs filesystem - * * @dentry: a pointer to a the dentry of the file or directory to be * removed. * -- cgit v1.1 From ceeee1fb2897651b434547eb26d93e6d2ff5a1a5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 9 Apr 2002 12:14:34 -0700 Subject: SYSFS: allow sysfs_create_link to create symlinks in the root of sysfs This is needed to make the compatible link for /sys/block in the future. Signed-off-by: Greg Kroah-Hartman --- fs/sysfs/symlink.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c index d2eac3c..f50e3cc 100644 --- a/fs/sysfs/symlink.c +++ b/fs/sysfs/symlink.c @@ -3,6 +3,7 @@ */ #include +#include #include #include #include @@ -82,10 +83,19 @@ exit1: */ int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char * name) { - struct dentry * dentry = kobj->dentry; + struct dentry *dentry = NULL; int error = -EEXIST; - BUG_ON(!kobj || !kobj->dentry || !name); + BUG_ON(!name); + + if (!kobj) { + if (sysfs_mount && sysfs_mount->mnt_sb) + dentry = sysfs_mount->mnt_sb->s_root; + } else + dentry = kobj->dentry; + + if (!dentry) + return -EFAULT; mutex_lock(&dentry->d_inode->i_mutex); if (!sysfs_dirent_exist(dentry->d_fsdata, name)) -- cgit v1.1 From 995982ca79d9262869513948ec7c540f32035491 Mon Sep 17 00:00:00 2001 From: "Randy.Dunlap" Date: Mon, 10 Jul 2006 23:05:25 -0700 Subject: sysfs_remove_bin_file: no return value, dump_stack on error Make sysfs_remove_bin_file() void. If it detects an error, printk the file name and call dump_stack(). sysfs_hash_and_remove() now returns an error code indicating its success or failure so that sysfs_remove_bin_file() can know success/failure. Convert the only driver that checked the return value of sysfs_remove_bin_file(). Signed-off-by: Randy Dunlap Signed-off-by: Greg Kroah-Hartman --- fs/sysfs/bin.c | 13 ++++++++----- fs/sysfs/inode.c | 11 ++++++++--- fs/sysfs/sysfs.h | 2 +- 3 files changed, 17 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c index c16a93c..98022e4 100644 --- a/fs/sysfs/bin.c +++ b/fs/sysfs/bin.c @@ -10,6 +10,7 @@ #include #include +#include #include #include #include @@ -176,7 +177,6 @@ const struct file_operations bin_fops = { * sysfs_create_bin_file - create binary file for object. * @kobj: object. * @attr: attribute descriptor. - * */ int sysfs_create_bin_file(struct kobject * kobj, struct bin_attribute * attr) @@ -191,13 +191,16 @@ int sysfs_create_bin_file(struct kobject * kobj, struct bin_attribute * attr) * sysfs_remove_bin_file - remove binary file for object. * @kobj: object. * @attr: attribute descriptor. - * */ -int sysfs_remove_bin_file(struct kobject * kobj, struct bin_attribute * attr) +void sysfs_remove_bin_file(struct kobject * kobj, struct bin_attribute * attr) { - sysfs_hash_and_remove(kobj->dentry,attr->attr.name); - return 0; + if (sysfs_hash_and_remove(kobj->dentry, attr->attr.name) < 0) { + printk(KERN_ERR "%s: " + "bad dentry or inode or no such file: \"%s\"\n", + __FUNCTION__, attr->attr.name); + dump_stack(); + } } EXPORT_SYMBOL_GPL(sysfs_create_bin_file); diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index 9889e54..fd7cd5f 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "sysfs.h" extern struct super_block * sysfs_sb; @@ -234,17 +235,18 @@ void sysfs_drop_dentry(struct sysfs_dirent * sd, struct dentry * parent) } } -void sysfs_hash_and_remove(struct dentry * dir, const char * name) +int sysfs_hash_and_remove(struct dentry * dir, const char * name) { struct sysfs_dirent * sd; struct sysfs_dirent * parent_sd; + int found = 0; if (!dir) - return; + return -ENOENT; if (dir->d_inode == NULL) /* no inode means this hasn't been made visible yet */ - return; + return -ENOENT; parent_sd = dir->d_fsdata; mutex_lock(&dir->d_inode->i_mutex); @@ -255,8 +257,11 @@ void sysfs_hash_and_remove(struct dentry * dir, const char * name) list_del_init(&sd->s_sibling); sysfs_drop_dentry(sd, dir); sysfs_put(sd); + found = 1; break; } } mutex_unlock(&dir->d_inode->i_mutex); + + return found ? 0 : -ENOENT; } diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index 3651ffb..6f3d6bd 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -10,7 +10,7 @@ extern int sysfs_make_dirent(struct sysfs_dirent *, struct dentry *, void *, umode_t, int); extern int sysfs_add_file(struct dentry *, const struct attribute *, int); -extern void sysfs_hash_and_remove(struct dentry * dir, const char * name); +extern int sysfs_hash_and_remove(struct dentry * dir, const char * name); extern struct sysfs_dirent *sysfs_find(struct sysfs_dirent *dir, const char * name); extern int sysfs_create_subdir(struct kobject *, const char *, struct dentry **); -- cgit v1.1 From f20a9ead0d005fbeeae3fc21a96f9bf197ac1c1c Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 14 Aug 2006 22:43:23 -0700 Subject: sysfs: add proper sysfs_init() prototype Don't be crufty. Mark it __must_check too. Cc: "Randy.Dunlap" Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/namespace.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'fs') diff --git a/fs/namespace.c b/fs/namespace.c index fa7ed6a9f..36d1808 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -28,15 +29,6 @@ extern int __init init_rootfs(void); -#ifdef CONFIG_SYSFS -extern int __init sysfs_init(void); -#else -static inline int sysfs_init(void) -{ - return 0; -} -#endif - /* spinlock for vfsmount related operations, inplace of dcache_lock */ __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock); -- cgit v1.1 From c16b63e09d9d03158e0a92e961234e94c4862620 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 26 Sep 2006 10:52:28 +0200 Subject: [PATCH] i386/x86-64: Don't randomize stack top when no randomization personality is set Based on patch from Frank van Maarseveen , but extended. Signed-off-by: Andi Kleen --- fs/binfmt_elf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 672a3b9..5109dbf 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -515,7 +515,8 @@ static unsigned long randomize_stack_top(unsigned long stack_top) { unsigned int random_variable = 0; - if (current->flags & PF_RANDOMIZE) { + if ((current->flags & PF_RANDOMIZE) && + !(current->personality & ADDR_NO_RANDOMIZE)) { random_variable = get_random_int() & STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } -- cgit v1.1 From 758333458aa719bfc26ec16eafd4ad3a9e96014d Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 26 Sep 2006 10:52:39 +0200 Subject: [PATCH] Check return value of copy_to_user in compat_sys_pselect7 Fix linux/fs/compat.c: In function compat_sys_pselect7 linux/fs/compat.c:1869: warning: ignoring return value of copy_to_user, declared with attribute warn_unused_result To make it easier to handle I changed to semantics to not try to write out a timespec if an error occurred. I hope that's ok. Cc: dwmw2@infradead.org Signed-off-by: Andi Kleen --- fs/compat.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/compat.c b/fs/compat.c index e31e9cf..ce982f6 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1855,7 +1855,7 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp, } while (!ret && !timeout && tsp && (ts.tv_sec || ts.tv_nsec)); - if (tsp && !(current->personality & STICKY_TIMEOUTS)) { + if (ret == 0 && tsp && !(current->personality & STICKY_TIMEOUTS)) { struct compat_timespec rts; rts.tv_sec = timeout / HZ; @@ -1866,7 +1866,8 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp, } if (compat_timespec_compare(&rts, &ts) >= 0) rts = ts; - copy_to_user(tsp, &rts, sizeof(rts)); + if (copy_to_user(tsp, &rts, sizeof(rts))) + ret = -EFAULT; } if (ret == -ERESTARTNOHAND) { -- cgit v1.1 From 3998b9301d3d55be8373add22b6bc5e11c1d9b71 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 25 Sep 2006 23:30:53 -0700 Subject: [PATCH] jbd: fix commit of ordered data buffers Original commit code assumes, that when a buffer on BJ_SyncData list is locked, it is being written to disk. But this is not true and hence it can lead to a potential data loss on crash. Also the code didn't count with the fact that journal_dirty_data() can steal buffers from committing transaction and hence could write buffers that no longer belong to the committing transaction. Finally it could possibly happen that we tried writing out one buffer several times. The patch below tries to solve these problems by a complete rewrite of the data commit code. We go through buffers on t_sync_datalist, lock buffers needing write out and store them in an array. Buffers are also immediately refiled to BJ_Locked list or unfiled (if the write out is completed). When the array is full or we have to block on buffer lock, we submit all accumulated buffers for IO. [suitable for 2.6.18.x around the 2.6.19-rc2 timeframe] Signed-off-by: Jan Kara Cc: Badari Pulavarty Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/jbd/commit.c | 182 +++++++++++++++++++++++++++++++++++--------------------- 1 file changed, 113 insertions(+), 69 deletions(-) (limited to 'fs') diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index 42da607..32a8caf 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -160,6 +160,117 @@ static int journal_write_commit_record(journal_t *journal, return (ret == -EIO); } +static void journal_do_submit_data(struct buffer_head **wbuf, int bufs) +{ + int i; + + for (i = 0; i < bufs; i++) { + wbuf[i]->b_end_io = end_buffer_write_sync; + /* We use-up our safety reference in submit_bh() */ + submit_bh(WRITE, wbuf[i]); + } +} + +/* + * Submit all the data buffers to disk + */ +static void journal_submit_data_buffers(journal_t *journal, + transaction_t *commit_transaction) +{ + struct journal_head *jh; + struct buffer_head *bh; + int locked; + int bufs = 0; + struct buffer_head **wbuf = journal->j_wbuf; + + /* + * Whenever we unlock the journal and sleep, things can get added + * onto ->t_sync_datalist, so we have to keep looping back to + * write_out_data until we *know* that the list is empty. + * + * Cleanup any flushed data buffers from the data list. Even in + * abort mode, we want to flush this out as soon as possible. + */ +write_out_data: + cond_resched(); + spin_lock(&journal->j_list_lock); + + while (commit_transaction->t_sync_datalist) { + jh = commit_transaction->t_sync_datalist; + bh = jh2bh(jh); + locked = 0; + + /* Get reference just to make sure buffer does not disappear + * when we are forced to drop various locks */ + get_bh(bh); + /* If the buffer is dirty, we need to submit IO and hence + * we need the buffer lock. We try to lock the buffer without + * blocking. If we fail, we need to drop j_list_lock and do + * blocking lock_buffer(). + */ + if (buffer_dirty(bh)) { + if (test_set_buffer_locked(bh)) { + BUFFER_TRACE(bh, "needs blocking lock"); + spin_unlock(&journal->j_list_lock); + /* Write out all data to prevent deadlocks */ + journal_do_submit_data(wbuf, bufs); + bufs = 0; + lock_buffer(bh); + spin_lock(&journal->j_list_lock); + } + locked = 1; + } + /* We have to get bh_state lock. Again out of order, sigh. */ + if (!inverted_lock(journal, bh)) { + jbd_lock_bh_state(bh); + spin_lock(&journal->j_list_lock); + } + /* Someone already cleaned up the buffer? */ + if (!buffer_jbd(bh) + || jh->b_transaction != commit_transaction + || jh->b_jlist != BJ_SyncData) { + jbd_unlock_bh_state(bh); + if (locked) + unlock_buffer(bh); + BUFFER_TRACE(bh, "already cleaned up"); + put_bh(bh); + continue; + } + if (locked && test_clear_buffer_dirty(bh)) { + BUFFER_TRACE(bh, "needs writeout, adding to array"); + wbuf[bufs++] = bh; + __journal_file_buffer(jh, commit_transaction, + BJ_Locked); + jbd_unlock_bh_state(bh); + if (bufs == journal->j_wbufsize) { + spin_unlock(&journal->j_list_lock); + journal_do_submit_data(wbuf, bufs); + bufs = 0; + goto write_out_data; + } + } + else { + BUFFER_TRACE(bh, "writeout complete: unfile"); + __journal_unfile_buffer(jh); + jbd_unlock_bh_state(bh); + if (locked) + unlock_buffer(bh); + journal_remove_journal_head(bh); + /* Once for our safety reference, once for + * journal_remove_journal_head() */ + put_bh(bh); + put_bh(bh); + } + + if (lock_need_resched(&journal->j_list_lock)) { + spin_unlock(&journal->j_list_lock); + goto write_out_data; + } + } + spin_unlock(&journal->j_list_lock); + journal_do_submit_data(wbuf, bufs); +} + /* * journal_commit_transaction * @@ -313,80 +424,13 @@ void journal_commit_transaction(journal_t *journal) * Now start flushing things to disk, in the order they appear * on the transaction lists. Data blocks go first. */ - err = 0; - /* - * Whenever we unlock the journal and sleep, things can get added - * onto ->t_sync_datalist, so we have to keep looping back to - * write_out_data until we *know* that the list is empty. - */ - bufs = 0; - /* - * Cleanup any flushed data buffers from the data list. Even in - * abort mode, we want to flush this out as soon as possible. - */ -write_out_data: - cond_resched(); - spin_lock(&journal->j_list_lock); - - while (commit_transaction->t_sync_datalist) { - struct buffer_head *bh; - - jh = commit_transaction->t_sync_datalist; - commit_transaction->t_sync_datalist = jh->b_tnext; - bh = jh2bh(jh); - if (buffer_locked(bh)) { - BUFFER_TRACE(bh, "locked"); - if (!inverted_lock(journal, bh)) - goto write_out_data; - __journal_temp_unlink_buffer(jh); - __journal_file_buffer(jh, commit_transaction, - BJ_Locked); - jbd_unlock_bh_state(bh); - if (lock_need_resched(&journal->j_list_lock)) { - spin_unlock(&journal->j_list_lock); - goto write_out_data; - } - } else { - if (buffer_dirty(bh)) { - BUFFER_TRACE(bh, "start journal writeout"); - get_bh(bh); - wbuf[bufs++] = bh; - if (bufs == journal->j_wbufsize) { - jbd_debug(2, "submit %d writes\n", - bufs); - spin_unlock(&journal->j_list_lock); - ll_rw_block(SWRITE, bufs, wbuf); - journal_brelse_array(wbuf, bufs); - bufs = 0; - goto write_out_data; - } - } else { - BUFFER_TRACE(bh, "writeout complete: unfile"); - if (!inverted_lock(journal, bh)) - goto write_out_data; - __journal_unfile_buffer(jh); - jbd_unlock_bh_state(bh); - journal_remove_journal_head(bh); - put_bh(bh); - if (lock_need_resched(&journal->j_list_lock)) { - spin_unlock(&journal->j_list_lock); - goto write_out_data; - } - } - } - } - - if (bufs) { - spin_unlock(&journal->j_list_lock); - ll_rw_block(SWRITE, bufs, wbuf); - journal_brelse_array(wbuf, bufs); - spin_lock(&journal->j_list_lock); - } + journal_submit_data_buffers(journal, commit_transaction); /* * Wait for all previously submitted IO to complete. */ + spin_lock(&journal->j_list_lock); while (commit_transaction->t_locked_list) { struct buffer_head *bh; -- cgit v1.1 From d08b3851da41d0ee60851f2c75b118e1f7a5fc89 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 25 Sep 2006 23:30:57 -0700 Subject: [PATCH] mm: tracking shared dirty pages Tracking of dirty pages in shared writeable mmap()s. The idea is simple: write protect clean shared writeable pages, catch the write-fault, make writeable and set dirty. On page write-back clean all the PTE dirty bits and write protect them once again. The implementation is a tad harder, mainly because the default backing_dev_info capabilities were too loosely maintained. Hence it is not enough to test the backing_dev_info for cap_account_dirty. The current heuristic is as follows, a VMA is eligible when: - its shared writeable (vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED) - it is not a 'special' mapping (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) == 0 - the backing_dev_info is cap_account_dirty mapping_cap_account_dirty(vma->vm_file->f_mapping) - f_op->mmap() didn't change the default page protection Page from remap_pfn_range() are explicitly excluded because their COW semantics are already horrid enough (see vm_normal_page() in do_wp_page()) and because they don't have a backing store anyway. mprotect() is taught about the new behaviour as well. However it overrides the last condition. Cleaning the pages on write-back is done with page_mkclean() a new rmap call. It can be called on any page, but is currently only implemented for mapped pages, if the page is found the be of a VMA that accounts dirty pages it will also wrprotect the PTE. Finally, in fs/buffers.c:try_to_free_buffers(); remove clear_page_dirty() from under ->private_lock. This seems to be safe, since ->private_lock is used to serialize access to the buffers, not the page itself. This is needed because clear_page_dirty() will call into page_mkclean() and would thereby violate locking order. [dhowells@redhat.com: Provide a page_mkclean() implementation for NOMMU] Signed-off-by: Peter Zijlstra Cc: Hugh Dickins Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/buffer.c b/fs/buffer.c index 71649ef..3b6d701 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2987,6 +2987,7 @@ int try_to_free_buffers(struct page *page) spin_lock(&mapping->private_lock); ret = drop_buffers(page, &buffers_to_free); + spin_unlock(&mapping->private_lock); if (ret) { /* * If the filesystem writes its buffers by hand (eg ext3) @@ -2998,7 +2999,6 @@ int try_to_free_buffers(struct page *page) */ clear_page_dirty(page); } - spin_unlock(&mapping->private_lock); out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; -- cgit v1.1 From 182e8e237349e7b6354f45aee4780b6423fd6a50 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:10 -0700 Subject: [PATCH] reduce MAX_NR_ZONES: make display of highmem counters conditional on CONFIG_HIGHMEM Do not display HIGHMEM memory sizes if CONFIG_HIGHMEM is not set. Make HIGHMEM dependent texts and make display of highmem counters optional Some texts are depending on CONFIG_HIGHMEM. Remove those strings and remove the display of highmem counter values if CONFIG_HIGHMEM is not set. [akpm@osdl.org: remove some ifdefs] Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_misc.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'fs') diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 9421562..caa0a51 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -157,10 +157,12 @@ static int meminfo_read_proc(char *page, char **start, off_t off, "SwapCached: %8lu kB\n" "Active: %8lu kB\n" "Inactive: %8lu kB\n" +#ifdef CONFIG_HIGHMEM "HighTotal: %8lu kB\n" "HighFree: %8lu kB\n" "LowTotal: %8lu kB\n" "LowFree: %8lu kB\n" +#endif "SwapTotal: %8lu kB\n" "SwapFree: %8lu kB\n" "Dirty: %8lu kB\n" @@ -183,10 +185,12 @@ static int meminfo_read_proc(char *page, char **start, off_t off, K(total_swapcache_pages), K(active), K(inactive), +#ifdef CONFIG_HIGHMEM K(i.totalhigh), K(i.freehigh), K(i.totalram-i.totalhigh), K(i.freeram-i.freehigh), +#endif K(i.totalswap), K(i.freeswap), K(global_page_state(NR_FILE_DIRTY)), -- cgit v1.1 From 972d1a7b140569084439a81265a0f15b74e924e0 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:51 -0700 Subject: [PATCH] ZVC: Support NR_SLAB_RECLAIMABLE / NR_SLAB_UNRECLAIMABLE Remove the atomic counter for slab_reclaim_pages and replace the counter and NR_SLAB with two ZVC counter that account for unreclaimable and reclaimable slab pages: NR_SLAB_RECLAIMABLE and NR_SLAB_UNRECLAIMABLE. Change the check in vmscan.c to refer to to NR_SLAB_RECLAIMABLE. The intend seems to be to check for slab pages that could be freed. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_misc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index caa0a51..5bbd608 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -170,6 +170,8 @@ static int meminfo_read_proc(char *page, char **start, off_t off, "AnonPages: %8lu kB\n" "Mapped: %8lu kB\n" "Slab: %8lu kB\n" + "SReclaimable: %8lu kB\n" + "SUnreclaim: %8lu kB\n" "PageTables: %8lu kB\n" "NFS_Unstable: %8lu kB\n" "Bounce: %8lu kB\n" @@ -197,7 +199,10 @@ static int meminfo_read_proc(char *page, char **start, off_t off, K(global_page_state(NR_WRITEBACK)), K(global_page_state(NR_ANON_PAGES)), K(global_page_state(NR_FILE_MAPPED)), - K(global_page_state(NR_SLAB)), + K(global_page_state(NR_SLAB_RECLAIMABLE) + + global_page_state(NR_SLAB_UNRECLAIMABLE)), + K(global_page_state(NR_SLAB_RECLAIMABLE)), + K(global_page_state(NR_SLAB_UNRECLAIMABLE)), K(global_page_state(NR_PAGETABLE)), K(global_page_state(NR_UNSTABLE_NFS)), K(global_page_state(NR_BOUNCE)), -- cgit v1.1 From 8d6b5eeea5eb644232cbbbe1c927fdf051e60fa5 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 25 Sep 2006 23:32:04 -0700 Subject: [PATCH] binfmt_elf: consistently use loff_t As David Howells points out, binfmt_elf sometimes uses off_t, sometimes uses loff_t. Use loff_t throughout. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/binfmt_elf.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 672a3b9..64802aa 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1262,7 +1262,7 @@ static void fill_elf_header(struct elfhdr *elf, int segs) return; } -static void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, off_t offset) +static void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, loff_t offset) { phdr->p_type = PT_NOTE; phdr->p_offset = offset; @@ -1428,7 +1428,7 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) int i; struct vm_area_struct *vma; struct elfhdr *elf = NULL; - off_t offset = 0, dataoff; + loff_t offset = 0, dataoff; unsigned long limit = current->signal->rlim[RLIMIT_CORE].rlim_cur; int numnote; struct memelfnote *notes = NULL; @@ -1661,11 +1661,11 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) ELF_CORE_WRITE_EXTRA_DATA; #endif - if ((off_t)file->f_pos != offset) { + if (file->f_pos != offset) { /* Sanity check */ printk(KERN_WARNING - "elf_core_dump: file->f_pos (%ld) != offset (%ld)\n", - (off_t)file->f_pos, offset); + "elf_core_dump: file->f_pos (%Ld) != offset (%Ld)\n", + file->f_pos, offset); } end_coredump: -- cgit v1.1 From e7ab8d65055e9b9dfc131d0467cfc5a8368d7ee4 Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Wed, 27 Sep 2006 01:49:26 -0700 Subject: [PATCH] jbd: add lock annotation to jbd_sync_bh jbd_sync_bh releases journal->j_list_lock. Add a lock annotation to this function so that sparse can check callers for lock pairing, and so that sparse will not complain about this function since it intentionally uses the lock in this manner. Signed-off-by: Josh Triplett Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/jbd/checkpoint.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c index 47678a2..d068559 100644 --- a/fs/jbd/checkpoint.c +++ b/fs/jbd/checkpoint.c @@ -145,6 +145,7 @@ void __log_wait_for_space(journal_t *journal) * jbd_unlock_bh_state(). */ static void jbd_sync_bh(journal_t *journal, struct buffer_head *bh) + __releases(journal->j_list_lock) { get_bh(bh); spin_unlock(&journal->j_list_lock); -- cgit v1.1 From ae6ddcc5f24d6b06ae9231dc128904750a4155e0 Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Wed, 27 Sep 2006 01:49:27 -0700 Subject: [PATCH] ext3 and jbd cleanup: remove whitespace Remove whitespace from ext3 and jbd, before we clone ext4. Signed-off-by: Mingming Cao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/balloc.c | 16 +++---- fs/ext3/bitmap.c | 2 +- fs/ext3/dir.c | 14 +++--- fs/ext3/file.c | 2 +- fs/ext3/fsync.c | 6 +-- fs/ext3/hash.c | 6 +-- fs/ext3/ialloc.c | 48 +++++++++---------- fs/ext3/inode.c | 64 +++++++++++++------------- fs/ext3/namei.c | 28 +++++------ fs/ext3/super.c | 24 +++++----- fs/jbd/checkpoint.c | 30 ++++++------ fs/jbd/journal.c | 56 +++++++++++----------- fs/jbd/recovery.c | 54 +++++++++++----------- fs/jbd/revoke.c | 70 ++++++++++++++-------------- fs/jbd/transaction.c | 128 +++++++++++++++++++++++++-------------------------- 15 files changed, 274 insertions(+), 274 deletions(-) (limited to 'fs') diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index 063d994..e6b9837 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -74,7 +74,7 @@ struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb, } /* - * Read the bitmap for a given block_group, reading into the specified + * Read the bitmap for a given block_group, reading into the specified * slot in the superblock's bitmap cache. * * Return buffer_head on success or NULL in case of failure. @@ -419,8 +419,8 @@ do_more: } /* @@@ This prevents newly-allocated data from being * freed and then reallocated within the same - * transaction. - * + * transaction. + * * Ideally we would want to allow that to happen, but to * do so requires making journal_forget() capable of * revoking the queued write of a data block, which @@ -433,7 +433,7 @@ do_more: * safe not to set the allocation bit in the committed * bitmap, because we know that there is no outstanding * activity on the buffer any more and so it is safe to - * reallocate it. + * reallocate it. */ BUFFER_TRACE(bitmap_bh, "set in b_committed_data"); J_ASSERT_BH(bitmap_bh, @@ -518,7 +518,7 @@ void ext3_free_blocks(handle_t *handle, struct inode *inode, * data would allow the old block to be overwritten before the * transaction committed (because we force data to disk before commit). * This would lead to corruption if we crashed between overwriting the - * data and committing the delete. + * data and committing the delete. * * @@@ We may want to make this allocation behaviour conditional on * data-writes at some point, and disable it for metadata allocations or @@ -584,7 +584,7 @@ find_next_usable_block(ext3_grpblk_t start, struct buffer_head *bh, if (start > 0) { /* - * The goal was occupied; search forward for a free + * The goal was occupied; search forward for a free * block within the next XX blocks. * * end_goal is more or less random, but it has to be @@ -1194,7 +1194,7 @@ int ext3_should_retry_alloc(struct super_block *sb, int *retries) /* * ext3_new_block uses a goal block to assist allocation. If the goal is * free, or there is a free block within 32 blocks of the goal, that block - * is allocated. Otherwise a forward search is made for a free block; within + * is allocated. Otherwise a forward search is made for a free block; within * each block group the search first looks for an entire free byte in the block * bitmap, and then for any free bit if that fails. * This function also updates quota and i_blocks field. @@ -1303,7 +1303,7 @@ retry_alloc: smp_rmb(); /* - * Now search the rest of the groups. We assume that + * Now search the rest of the groups. We assume that * i and gdp correctly point to the last group visited. */ for (bgi = 0; bgi < ngroups; bgi++) { diff --git a/fs/ext3/bitmap.c b/fs/ext3/bitmap.c index ce4f82b..b9176ee 100644 --- a/fs/ext3/bitmap.c +++ b/fs/ext3/bitmap.c @@ -20,7 +20,7 @@ unsigned long ext3_count_free (struct buffer_head * map, unsigned int numchars) unsigned int i; unsigned long sum = 0; - if (!map) + if (!map) return (0); for (i = 0; i < numchars; i++) sum += nibblemap[map->b_data[i] & 0xf] + diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c index fbb0d4e..6f9e5a5 100644 --- a/fs/ext3/dir.c +++ b/fs/ext3/dir.c @@ -59,7 +59,7 @@ static unsigned char get_dtype(struct super_block *sb, int filetype) return (ext3_filetype_table[filetype]); } - + int ext3_check_dir_entry (const char * function, struct inode * dir, struct ext3_dir_entry_2 * de, @@ -162,7 +162,7 @@ revalidate: * to make sure. */ if (filp->f_version != inode->i_version) { for (i = 0; i < sb->s_blocksize && i < offset; ) { - de = (struct ext3_dir_entry_2 *) + de = (struct ext3_dir_entry_2 *) (bh->b_data + i); /* It's too expensive to do a full * dirent test each time round this @@ -181,7 +181,7 @@ revalidate: filp->f_version = inode->i_version; } - while (!error && filp->f_pos < inode->i_size + while (!error && filp->f_pos < inode->i_size && offset < sb->s_blocksize) { de = (struct ext3_dir_entry_2 *) (bh->b_data + offset); if (!ext3_check_dir_entry ("ext3_readdir", inode, de, @@ -229,7 +229,7 @@ out: /* * These functions convert from the major/minor hash to an f_pos * value. - * + * * Currently we only use major hash numer. This is unfortunate, but * on 32-bit machines, the same VFS interface is used for lseek and * llseek, so if we use the 64 bit offset, then the 32-bit versions of @@ -250,7 +250,7 @@ out: struct fname { __u32 hash; __u32 minor_hash; - struct rb_node rb_hash; + struct rb_node rb_hash; struct fname *next; __u32 inode; __u8 name_len; @@ -410,7 +410,7 @@ static int call_filldir(struct file * filp, void * dirent, curr_pos = hash2pos(fname->hash, fname->minor_hash); while (fname) { error = filldir(dirent, fname->name, - fname->name_len, curr_pos, + fname->name_len, curr_pos, fname->inode, get_dtype(sb, fname->file_type)); if (error) { @@ -465,7 +465,7 @@ static int ext3_dx_readdir(struct file * filp, /* * Fill the rbtree if we have no more entries, * or the inode has changed since we last read in the - * cached entries. + * cached entries. */ if ((!info->curr_node) || (filp->f_version != inode->i_version)) { diff --git a/fs/ext3/file.c b/fs/ext3/file.c index 1efefb6..994efd1 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -100,7 +100,7 @@ ext3_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t force_commit: err = ext3_force_commit(inode->i_sb); - if (err) + if (err) return err; return ret; } diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c index 49382a2..dd1fd3c 100644 --- a/fs/ext3/fsync.c +++ b/fs/ext3/fsync.c @@ -8,14 +8,14 @@ * Universite Pierre et Marie Curie (Paris VI) * from * linux/fs/minix/truncate.c Copyright (C) 1991, 1992 Linus Torvalds - * + * * ext3fs fsync primitive * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 - * + * * Removed unnecessary code duplication for little endian machines - * and excessive __inline__s. + * and excessive __inline__s. * Andi Kleen, 1997 * * Major simplications and cleanup - we only need to do the metadata, because diff --git a/fs/ext3/hash.c b/fs/ext3/hash.c index 5a2d123..7fa637c 100644 --- a/fs/ext3/hash.c +++ b/fs/ext3/hash.c @@ -4,7 +4,7 @@ * Copyright (C) 2002 by Theodore Ts'o * * This file is released under the GPL v2. - * + * * This file may be redistributed under the terms of the GNU Public * License. */ @@ -80,11 +80,11 @@ static void str2hashbuf(const char *msg, int len, __u32 *buf, int num) * Returns the hash of a filename. If len is 0 and name is NULL, then * this function can be used to test whether or not a hash version is * supported. - * + * * The seed is an 4 longword (32 bits) "secret" which can be used to * uniquify a hash. If the seed is all zero's, then some default seed * may be used. - * + * * A particular hash version specifies whether or not the seed is * represented, and whether or not the returned hash is 32 bits or 64 * bits. 32 bit hashes will return 0 for the minor hash. diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c index 36546ed..5e28836 100644 --- a/fs/ext3/ialloc.c +++ b/fs/ext3/ialloc.c @@ -216,7 +216,7 @@ static int find_group_dir(struct super_block *sb, struct inode *parent) continue; if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei) continue; - if (!best_desc || + if (!best_desc || (le16_to_cpu(desc->bg_free_blocks_count) > le16_to_cpu(best_desc->bg_free_blocks_count))) { best_group = group; @@ -226,30 +226,30 @@ static int find_group_dir(struct super_block *sb, struct inode *parent) return best_group; } -/* - * Orlov's allocator for directories. - * +/* + * Orlov's allocator for directories. + * * We always try to spread first-level directories. * - * If there are blockgroups with both free inodes and free blocks counts - * not worse than average we return one with smallest directory count. - * Otherwise we simply return a random group. - * - * For the rest rules look so: - * - * It's OK to put directory into a group unless - * it has too many directories already (max_dirs) or - * it has too few free inodes left (min_inodes) or - * it has too few free blocks left (min_blocks) or - * it's already running too large debt (max_debt). - * Parent's group is prefered, if it doesn't satisfy these - * conditions we search cyclically through the rest. If none - * of the groups look good we just look for a group with more - * free inodes than average (starting at parent's group). - * - * Debt is incremented each time we allocate a directory and decremented - * when we allocate an inode, within 0--255. - */ + * If there are blockgroups with both free inodes and free blocks counts + * not worse than average we return one with smallest directory count. + * Otherwise we simply return a random group. + * + * For the rest rules look so: + * + * It's OK to put directory into a group unless + * it has too many directories already (max_dirs) or + * it has too few free inodes left (min_inodes) or + * it has too few free blocks left (min_blocks) or + * it's already running too large debt (max_debt). + * Parent's group is prefered, if it doesn't satisfy these + * conditions we search cyclically through the rest. If none + * of the groups look good we just look for a group with more + * free inodes than average (starting at parent's group). + * + * Debt is incremented each time we allocate a directory and decremented + * when we allocate an inode, within 0--255. + */ #define INODE_COST 64 #define BLOCK_COST 256 @@ -454,7 +454,7 @@ struct inode *ext3_new_inode(handle_t *handle, struct inode * dir, int mode) group = find_group_dir(sb, dir); else group = find_group_orlov(sb, dir); - } else + } else group = find_group_other(sb, dir); err = -ENOSPC; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 84be02e..473d206 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -55,7 +55,7 @@ static int ext3_inode_is_fast_symlink(struct inode *inode) /* * The ext3 forget function must perform a revoke if we are freeing data * which has been journaled. Metadata (eg. indirect blocks) must be - * revoked in all cases. + * revoked in all cases. * * "bh" may be NULL: a metadata block may have been freed from memory * but there may still be a record of it in the journal, and that record @@ -105,7 +105,7 @@ int ext3_forget(handle_t *handle, int is_metadata, struct inode *inode, * Work out how many blocks we need to proceed with the next chunk of a * truncate transaction. */ -static unsigned long blocks_for_truncate(struct inode *inode) +static unsigned long blocks_for_truncate(struct inode *inode) { unsigned long needed; @@ -122,13 +122,13 @@ static unsigned long blocks_for_truncate(struct inode *inode) /* But we need to bound the transaction so we don't overflow the * journal. */ - if (needed > EXT3_MAX_TRANS_DATA) + if (needed > EXT3_MAX_TRANS_DATA) needed = EXT3_MAX_TRANS_DATA; return EXT3_DATA_TRANS_BLOCKS(inode->i_sb) + needed; } -/* +/* * Truncate transactions can be complex and absolutely huge. So we need to * be able to restart the transaction at a conventient checkpoint to make * sure we don't overflow the journal. @@ -136,9 +136,9 @@ static unsigned long blocks_for_truncate(struct inode *inode) * start_transaction gets us a new handle for a truncate transaction, * and extend_transaction tries to extend the existing one a bit. If * extend fails, we need to propagate the failure up and restart the - * transaction in the top-level truncate loop. --sct + * transaction in the top-level truncate loop. --sct */ -static handle_t *start_transaction(struct inode *inode) +static handle_t *start_transaction(struct inode *inode) { handle_t *result; @@ -215,12 +215,12 @@ void ext3_delete_inode (struct inode * inode) ext3_orphan_del(handle, inode); EXT3_I(inode)->i_dtime = get_seconds(); - /* + /* * One subtle ordering requirement: if anything has gone wrong * (transaction abort, IO errors, whatever), then we can still * do these next steps (the fs will already have been marked as * having errors), but we can't free the inode if the mark_dirty - * fails. + * fails. */ if (ext3_mark_inode_dirty(handle, inode)) /* If that failed, just do the required in-core inode clear. */ @@ -398,7 +398,7 @@ no_block: * + if there is a block to the left of our position - allocate near it. * + if pointer will live in indirect block - allocate near that block. * + if pointer will live in inode - allocate in the same - * cylinder group. + * cylinder group. * * In the latter case we colour the starting block by the callers PID to * prevent it from clashing with concurrent allocations for a different inode @@ -744,7 +744,7 @@ static int ext3_splice_branch(handle_t *handle, struct inode *inode, jbd_debug(5, "splicing indirect only\n"); BUFFER_TRACE(where->bh, "call ext3_journal_dirty_metadata"); err = ext3_journal_dirty_metadata(handle, where->bh); - if (err) + if (err) goto err_out; } else { /* @@ -1137,7 +1137,7 @@ static int walk_page_buffers( handle_t *handle, * So what we do is to rely on the fact that journal_stop/journal_start * will _not_ run commit under these circumstances because handle->h_ref * is elevated. We'll still have enough credits for the tiny quotafile - * write. + * write. */ static int do_journal_get_write_access(handle_t *handle, struct buffer_head *bh) @@ -1282,7 +1282,7 @@ static int ext3_journalled_commit_write(struct file *file, if (inode->i_size > EXT3_I(inode)->i_disksize) { EXT3_I(inode)->i_disksize = inode->i_size; ret2 = ext3_mark_inode_dirty(handle, inode); - if (!ret) + if (!ret) ret = ret2; } ret2 = ext3_journal_stop(handle); @@ -1291,7 +1291,7 @@ static int ext3_journalled_commit_write(struct file *file, return ret; } -/* +/* * bmap() is special. It gets used by applications such as lilo and by * the swapper to find the on-disk block of a specific piece of data. * @@ -1300,10 +1300,10 @@ static int ext3_journalled_commit_write(struct file *file, * filesystem and enables swap, then they may get a nasty shock when the * data getting swapped to that swapfile suddenly gets overwritten by * the original zero's written out previously to the journal and - * awaiting writeback in the kernel's buffer cache. + * awaiting writeback in the kernel's buffer cache. * * So, if we see any bmap calls here on a modified, data-journaled file, - * take extra steps to flush any blocks which might be in the cache. + * take extra steps to flush any blocks which might be in the cache. */ static sector_t ext3_bmap(struct address_space *mapping, sector_t block) { @@ -1312,16 +1312,16 @@ static sector_t ext3_bmap(struct address_space *mapping, sector_t block) int err; if (EXT3_I(inode)->i_state & EXT3_STATE_JDATA) { - /* + /* * This is a REALLY heavyweight approach, but the use of * bmap on dirty files is expected to be extremely rare: * only if we run lilo or swapon on a freshly made file - * do we expect this to happen. + * do we expect this to happen. * * (bmap requires CAP_SYS_RAWIO so this does not * represent an unprivileged user DOS attack --- we'd be * in trouble if mortal users could trigger this path at - * will.) + * will.) * * NB. EXT3_STATE_JDATA is not set on files other than * regular files. If somebody wants to bmap a directory @@ -1457,7 +1457,7 @@ static int ext3_ordered_writepage(struct page *page, */ /* - * And attach them to the current transaction. But only if + * And attach them to the current transaction. But only if * block_write_full_page() succeeded. Otherwise they are unmapped, * and generally junk. */ @@ -1644,7 +1644,7 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, } } - ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, + ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, offset, nr_segs, ext3_get_block, NULL); @@ -2025,7 +2025,7 @@ static void ext3_free_data(handle_t *handle, struct inode *inode, __le32 *first, __le32 *last) { ext3_fsblk_t block_to_free = 0; /* Starting block # of a run */ - unsigned long count = 0; /* Number of blocks in the run */ + unsigned long count = 0; /* Number of blocks in the run */ __le32 *block_to_free_p = NULL; /* Pointer into inode/ind corresponding to block_to_free */ @@ -2054,7 +2054,7 @@ static void ext3_free_data(handle_t *handle, struct inode *inode, } else if (nr == block_to_free + count) { count++; } else { - ext3_clear_blocks(handle, inode, this_bh, + ext3_clear_blocks(handle, inode, this_bh, block_to_free, count, block_to_free_p, p); block_to_free = nr; @@ -2184,7 +2184,7 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode, *p = 0; BUFFER_TRACE(parent_bh, "call ext3_journal_dirty_metadata"); - ext3_journal_dirty_metadata(handle, + ext3_journal_dirty_metadata(handle, parent_bh); } } @@ -2704,7 +2704,7 @@ void ext3_read_inode(struct inode * inode) if (raw_inode->i_block[0]) init_special_inode(inode, inode->i_mode, old_decode_dev(le32_to_cpu(raw_inode->i_block[0]))); - else + else init_special_inode(inode, inode->i_mode, new_decode_dev(le32_to_cpu(raw_inode->i_block[1]))); } @@ -2724,8 +2724,8 @@ bad_inode: * * The caller must have write access to iloc->bh. */ -static int ext3_do_update_inode(handle_t *handle, - struct inode *inode, +static int ext3_do_update_inode(handle_t *handle, + struct inode *inode, struct ext3_iloc *iloc) { struct ext3_inode *raw_inode = ext3_raw_inode(iloc); @@ -2900,7 +2900,7 @@ int ext3_write_inode(struct inode *inode, int wait) * commit will leave the blocks being flushed in an unused state on * disk. (On recovery, the inode will get truncated and the blocks will * be freed, so we have a strong guarantee that no future commit will - * leave these blocks visible to the user.) + * leave these blocks visible to the user.) * * Called with inode->sem down. */ @@ -3043,13 +3043,13 @@ int ext3_mark_iloc_dirty(handle_t *handle, return err; } -/* +/* * On success, We end up with an outstanding reference count against - * iloc->bh. This _must_ be cleaned up later. + * iloc->bh. This _must_ be cleaned up later. */ int -ext3_reserve_inode_write(handle_t *handle, struct inode *inode, +ext3_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext3_iloc *iloc) { int err = 0; @@ -3139,7 +3139,7 @@ out: } #if 0 -/* +/* * Bind an inode's backing buffer_head into this transaction, to prevent * it from being flushed to disk early. Unlike * ext3_reserve_inode_write, this leaves behind no bh reference and @@ -3157,7 +3157,7 @@ static int ext3_pin_inode(handle_t *handle, struct inode *inode) BUFFER_TRACE(iloc.bh, "get_write_access"); err = journal_get_write_access(handle, iloc.bh); if (!err) - err = ext3_journal_dirty_metadata(handle, + err = ext3_journal_dirty_metadata(handle, iloc.bh); brelse(iloc.bh); } diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 2aa7101..4123f52 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -76,7 +76,7 @@ static struct buffer_head *ext3_append(handle_t *handle, #ifdef DX_DEBUG #define dxtrace(command) command #else -#define dxtrace(command) +#define dxtrace(command) #endif struct fake_dirent @@ -169,7 +169,7 @@ static struct ext3_dir_entry_2* dx_pack_dirents (char *base, int size); static void dx_insert_block (struct dx_frame *frame, u32 hash, u32 block); static int ext3_htree_next_block(struct inode *dir, __u32 hash, struct dx_frame *frame, - struct dx_frame *frames, + struct dx_frame *frames, __u32 *start_hash); static struct buffer_head * ext3_dx_find_entry(struct dentry *dentry, struct ext3_dir_entry_2 **res_dir, int *err); @@ -250,7 +250,7 @@ static void dx_show_index (char * label, struct dx_entry *entries) } struct stats -{ +{ unsigned names; unsigned space; unsigned bcount; @@ -464,7 +464,7 @@ static void dx_release (struct dx_frame *frames) */ static int ext3_htree_next_block(struct inode *dir, __u32 hash, struct dx_frame *frame, - struct dx_frame *frames, + struct dx_frame *frames, __u32 *start_hash) { struct dx_frame *p; @@ -632,7 +632,7 @@ int ext3_htree_fill_tree(struct file *dir_file, __u32 start_hash, } count += ret; hashval = ~0; - ret = ext3_htree_next_block(dir, HASH_NB_ALWAYS, + ret = ext3_htree_next_block(dir, HASH_NB_ALWAYS, frame, frames, &hashval); *next_hash = hashval; if (ret < 0) { @@ -649,7 +649,7 @@ int ext3_htree_fill_tree(struct file *dir_file, __u32 start_hash, break; } dx_release(frames); - dxtrace(printk("Fill tree: returned %d entries, next hash: %x\n", + dxtrace(printk("Fill tree: returned %d entries, next hash: %x\n", count, *next_hash)); return count; errout: @@ -1050,7 +1050,7 @@ struct dentry *ext3_get_parent(struct dentry *child) parent = ERR_PTR(-ENOMEM); } return parent; -} +} #define S_SHIFT 12 static unsigned char ext3_type_by_mode[S_IFMT >> S_SHIFT] = { @@ -1198,7 +1198,7 @@ errout: * add_dirent_to_buf will attempt search the directory block for * space. It will return -ENOSPC if no space is available, and -EIO * and -EEXIST if directory entry already exists. - * + * * NOTE! bh is NOT released in the case where ENOSPC is returned. In * all other cases bh is released. */ @@ -1572,7 +1572,7 @@ cleanup: * ext3_delete_entry deletes a directory entry by merging it with the * previous entry */ -static int ext3_delete_entry (handle_t *handle, +static int ext3_delete_entry (handle_t *handle, struct inode * dir, struct ext3_dir_entry_2 * de_del, struct buffer_head * bh) @@ -1643,12 +1643,12 @@ static int ext3_add_nondir(handle_t *handle, * is so far negative - it has no inode. * * If the create succeeds, we fill in the inode information - * with d_instantiate(). + * with d_instantiate(). */ static int ext3_create (struct inode * dir, struct dentry * dentry, int mode, struct nameidata *nd) { - handle_t *handle; + handle_t *handle; struct inode * inode; int err, retries = 0; @@ -1813,7 +1813,7 @@ static int empty_dir (struct inode * inode) de1 = (struct ext3_dir_entry_2 *) ((char *) de + le16_to_cpu(de->rec_len)); if (le32_to_cpu(de->inode) != inode->i_ino || - !le32_to_cpu(de1->inode) || + !le32_to_cpu(de1->inode) || strcmp (".", de->name) || strcmp ("..", de1->name)) { ext3_warning (inode->i_sb, "empty_dir", @@ -1883,7 +1883,7 @@ int ext3_orphan_add(handle_t *handle, struct inode *inode) * being truncated, or files being unlinked. */ /* @@@ FIXME: Observation from aviro: - * I think I can trigger J_ASSERT in ext3_orphan_add(). We block + * I think I can trigger J_ASSERT in ext3_orphan_add(). We block * here (on lock_super()), so race with ext3_link() which might bump * ->i_nlink. For, say it, character device. Not a regular file, * not a directory, not a symlink and ->i_nlink > 0. @@ -2393,4 +2393,4 @@ struct inode_operations ext3_special_inode_operations = { .removexattr = generic_removexattr, #endif .permission = ext3_permission, -}; +}; diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 3559086..4b95bfe 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -62,13 +62,13 @@ static void ext3_unlockfs(struct super_block *sb); static void ext3_write_super (struct super_block * sb); static void ext3_write_super_lockfs(struct super_block *sb); -/* +/* * Wrappers for journal_start/end. * * The only special thing we need to do here is to make sure that all * journal_end calls result in the superblock being marked dirty, so * that sync() will call the filesystem's write_super callback if - * appropriate. + * appropriate. */ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks) { @@ -90,11 +90,11 @@ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks) return journal_start(journal, nblocks); } -/* +/* * The only special thing we need to do here is to make sure that all * journal_stop calls result in the superblock being marked dirty, so * that sync() will call the filesystem's write_super callback if - * appropriate. + * appropriate. */ int __ext3_journal_stop(const char *where, handle_t *handle) { @@ -369,7 +369,7 @@ static void dump_orphan_list(struct super_block *sb, struct ext3_sb_info *sbi) { struct list_head *l; - printk(KERN_ERR "sb orphan head is %d\n", + printk(KERN_ERR "sb orphan head is %d\n", le32_to_cpu(sbi->s_es->s_last_orphan)); printk(KERN_ERR "sb_info orphan list:\n"); @@ -378,7 +378,7 @@ static void dump_orphan_list(struct super_block *sb, struct ext3_sb_info *sbi) printk(KERN_ERR " " "inode %s:%ld at %p: mode %o, nlink %d, next %d\n", inode->i_sb->s_id, inode->i_ino, inode, - inode->i_mode, inode->i_nlink, + inode->i_mode, inode->i_nlink, NEXT_ORPHAN(inode)); } } @@ -475,7 +475,7 @@ static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags) inode_init_once(&ei->vfs_inode); } } - + static int init_inodecache(void) { ext3_inode_cachep = kmem_cache_create("ext3_inode_cache", @@ -1483,7 +1483,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) (EXT3_HAS_COMPAT_FEATURE(sb, ~0U) || EXT3_HAS_RO_COMPAT_FEATURE(sb, ~0U) || EXT3_HAS_INCOMPAT_FEATURE(sb, ~0U))) - printk(KERN_WARNING + printk(KERN_WARNING "EXT3-fs warning: feature flags set on rev 0 fs, " "running e2fsck is recommended\n"); /* @@ -1509,7 +1509,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) if (blocksize < EXT3_MIN_BLOCK_SIZE || blocksize > EXT3_MAX_BLOCK_SIZE) { - printk(KERN_ERR + printk(KERN_ERR "EXT3-fs: Unsupported filesystem blocksize %d on %s.\n", blocksize, sb->s_id); goto failed_mount; @@ -1533,14 +1533,14 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) offset = (sb_block * EXT3_MIN_BLOCK_SIZE) % blocksize; bh = sb_bread(sb, logic_sb_block); if (!bh) { - printk(KERN_ERR + printk(KERN_ERR "EXT3-fs: Can't read superblock on 2nd try.\n"); goto failed_mount; } es = (struct ext3_super_block *)(((char *)bh->b_data) + offset); sbi->s_es = es; if (es->s_magic != cpu_to_le16(EXT3_SUPER_MAGIC)) { - printk (KERN_ERR + printk (KERN_ERR "EXT3-fs: Magic mismatch, very weird !\n"); goto failed_mount; } @@ -1820,7 +1820,7 @@ out_fail: /* * Setup any per-fs journal parameters now. We'll do this both on * initial mount, once the journal has been initialised but before we've - * done any recovery; and again on any subsequent remount. + * done any recovery; and again on any subsequent remount. */ static void ext3_init_journal_params(struct super_block *sb, journal_t *journal) { diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c index d068559..961ada2 100644 --- a/fs/jbd/checkpoint.c +++ b/fs/jbd/checkpoint.c @@ -1,6 +1,6 @@ /* * linux/fs/checkpoint.c - * + * * Written by Stephen C. Tweedie , 1999 * * Copyright 1999 Red Hat Software --- All Rights Reserved @@ -9,8 +9,8 @@ * the terms of the GNU General Public License, version 2, or at your * option, any later version, incorporated herein by reference. * - * Checkpoint routines for the generic filesystem journaling code. - * Part of the ext2fs journaling system. + * Checkpoint routines for the generic filesystem journaling code. + * Part of the ext2fs journaling system. * * Checkpointing is the process of ensuring that a section of the log is * committed fully to disk, so that that portion of the log can be @@ -226,7 +226,7 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count) * Try to flush one buffer from the checkpoint list to disk. * * Return 1 if something happened which requires us to abort the current - * scan of the checkpoint list. + * scan of the checkpoint list. * * Called with j_list_lock held and drops it if 1 is returned * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it @@ -270,7 +270,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh, * possibly block, while still holding the journal lock. * We cannot afford to let the transaction logic start * messing around with this buffer before we write it to - * disk, as that would break recoverability. + * disk, as that would break recoverability. */ BUFFER_TRACE(bh, "queue"); get_bh(bh); @@ -293,7 +293,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh, * Perform an actual checkpoint. We take the first transaction on the * list of transactions to be checkpointed and send all its buffers * to disk. We submit larger chunks of data at once. - * + * * The journal should be locked before calling this function. */ int log_do_checkpoint(journal_t *journal) @@ -304,10 +304,10 @@ int log_do_checkpoint(journal_t *journal) jbd_debug(1, "Start checkpoint\n"); - /* + /* * First thing: if there are any transactions in the log which * don't need checkpointing, just eliminate them from the - * journal straight away. + * journal straight away. */ result = cleanup_journal_tail(journal); jbd_debug(1, "cleanup_journal_tail returned %d\n", result); @@ -385,9 +385,9 @@ out: * we have already got rid of any since the last update of the log tail * in the journal superblock. If so, we can instantly roll the * superblock forward to remove those transactions from the log. - * + * * Return <0 on error, 0 on success, 1 if there was nothing to clean up. - * + * * Called with the journal lock held. * * This is the only part of the journaling code which really needs to be @@ -404,8 +404,8 @@ int cleanup_journal_tail(journal_t *journal) unsigned long blocknr, freed; /* OK, work out the oldest transaction remaining in the log, and - * the log block it starts at. - * + * the log block it starts at. + * * If the log is now empty, we need to work out which is the * next transaction ID we will write, and where it will * start. */ @@ -558,7 +558,7 @@ out: return ret; } -/* +/* * journal_remove_checkpoint: called after a buffer has been committed * to disk (either by being write-back flushed to disk, or being * committed to the log). @@ -636,7 +636,7 @@ out: * Called with the journal locked. * Called with j_list_lock held. */ -void __journal_insert_checkpoint(struct journal_head *jh, +void __journal_insert_checkpoint(struct journal_head *jh, transaction_t *transaction) { JBUFFER_TRACE(jh, "entry"); @@ -658,7 +658,7 @@ void __journal_insert_checkpoint(struct journal_head *jh, /* * We've finished with this transaction structure: adios... - * + * * The transaction must have no links except for the checkpoint by this * point. * diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index f66724c..87c5a6d 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -578,7 +578,7 @@ int journal_next_log_block(journal_t *journal, unsigned long *retp) * this is a no-op. If needed, we can use j_blk_offset - everything is * ready. */ -int journal_bmap(journal_t *journal, unsigned long blocknr, +int journal_bmap(journal_t *journal, unsigned long blocknr, unsigned long *retp) { int err = 0; @@ -699,10 +699,10 @@ fail: * @len: Lenght of the journal in blocks. * @blocksize: blocksize of journalling device * @returns: a newly created journal_t * - * + * * journal_init_dev creates a journal which maps a fixed contiguous * range of blocks on an arbitrary block device. - * + * */ journal_t * journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, @@ -739,11 +739,11 @@ journal_t * journal_init_dev(struct block_device *bdev, return journal; } - -/** + +/** * journal_t * journal_init_inode () - creates a journal which maps to a inode. * @inode: An inode to create the journal in - * + * * journal_init_inode creates a journal which maps an on-disk inode as * the journal. The inode must exist already, must support bmap() and * must have all data blocks preallocated. @@ -763,7 +763,7 @@ journal_t * journal_init_inode (struct inode *inode) journal->j_inode = inode; jbd_debug(1, "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n", - journal, inode->i_sb->s_id, inode->i_ino, + journal, inode->i_sb->s_id, inode->i_ino, (long long) inode->i_size, inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize); @@ -798,10 +798,10 @@ journal_t * journal_init_inode (struct inode *inode) return journal; } -/* +/* * If the journal init or create aborts, we need to mark the journal * superblock as being NULL to prevent the journal destroy from writing - * back a bogus superblock. + * back a bogus superblock. */ static void journal_fail_superblock (journal_t *journal) { @@ -844,13 +844,13 @@ static int journal_reset(journal_t *journal) return 0; } -/** +/** * int journal_create() - Initialise the new journal file * @journal: Journal to create. This structure must have been initialised - * + * * Given a journal_t structure which tells us which disk blocks we can * use, create a new journal superblock and initialise all of the - * journal fields from scratch. + * journal fields from scratch. **/ int journal_create(journal_t *journal) { @@ -915,7 +915,7 @@ int journal_create(journal_t *journal) return journal_reset(journal); } -/** +/** * void journal_update_superblock() - Update journal sb on disk. * @journal: The journal to update. * @wait: Set to '0' if you don't want to wait for IO completion. @@ -939,7 +939,7 @@ void journal_update_superblock(journal_t *journal, int wait) journal->j_transaction_sequence) { jbd_debug(1,"JBD: Skipping superblock update on recovered sb " "(start %ld, seq %d, errno %d)\n", - journal->j_tail, journal->j_tail_sequence, + journal->j_tail, journal->j_tail_sequence, journal->j_errno); goto out; } @@ -1062,7 +1062,7 @@ static int load_superblock(journal_t *journal) /** * int journal_load() - Read journal from disk. * @journal: Journal to act on. - * + * * Given a journal_t structure which tells us which disk blocks contain * a journal, read the journal from disk to initialise the in-memory * structures. @@ -1172,9 +1172,9 @@ void journal_destroy(journal_t *journal) * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features - * + * * Check whether the journal uses all of a given set of - * features. Return true (non-zero) if it does. + * features. Return true (non-zero) if it does. **/ int journal_check_used_features (journal_t *journal, unsigned long compat, @@ -1203,7 +1203,7 @@ int journal_check_used_features (journal_t *journal, unsigned long compat, * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features - * + * * Check whether the journaling code supports the use of * all of a given set of features on this journal. Return true * (non-zero) if it can. */ @@ -1241,7 +1241,7 @@ int journal_check_available_features (journal_t *journal, unsigned long compat, * @incompat: bitmask of incompatible features * * Mark a given journal feature as present on the - * superblock. Returns true if the requested features could be set. + * superblock. Returns true if the requested features could be set. * */ @@ -1327,7 +1327,7 @@ static int journal_convert_superblock_v1(journal_t *journal, /** * int journal_flush () - Flush journal * @journal: Journal to act on. - * + * * Flush all data for a given journal to disk and empty the journal. * Filesystems can use this when remounting readonly to ensure that * recovery does not need to happen on remount. @@ -1394,7 +1394,7 @@ int journal_flush(journal_t *journal) * int journal_wipe() - Wipe journal contents * @journal: Journal to act on. * @write: flag (see below) - * + * * Wipe out all of the contents of a journal, safely. This will produce * a warning if the journal contains any valid recovery information. * Must be called between journal_init_*() and journal_load(). @@ -1449,7 +1449,7 @@ static const char *journal_dev_name(journal_t *journal, char *buffer) /* * Journal abort has very specific semantics, which we describe - * for journal abort. + * for journal abort. * * Two internal function, which provide abort to te jbd layer * itself are here. @@ -1504,7 +1504,7 @@ static void __journal_abort_soft (journal_t *journal, int errno) * Perform a complete, immediate shutdown of the ENTIRE * journal (not of a single transaction). This operation cannot be * undone without closing and reopening the journal. - * + * * The journal_abort function is intended to support higher level error * recovery mechanisms such as the ext2/ext3 remount-readonly error * mode. @@ -1538,7 +1538,7 @@ static void __journal_abort_soft (journal_t *journal, int errno) * supply an errno; a null errno implies that absolutely no further * writes are done to the journal (unless there are any already in * progress). - * + * */ void journal_abort(journal_t *journal, int errno) @@ -1546,7 +1546,7 @@ void journal_abort(journal_t *journal, int errno) __journal_abort_soft(journal, errno); } -/** +/** * int journal_errno () - returns the journal's error state. * @journal: journal to examine. * @@ -1570,7 +1570,7 @@ int journal_errno(journal_t *journal) return err; } -/** +/** * int journal_clear_err () - clears the journal's error state * @journal: journal to act on. * @@ -1590,7 +1590,7 @@ int journal_clear_err(journal_t *journal) return err; } -/** +/** * void journal_ack_err() - Ack journal err. * @journal: journal to act on. * @@ -1612,7 +1612,7 @@ int journal_blocks_per_page(struct inode *inode) /* * Simple support for retrying memory allocations. Introduced to help to - * debug different VM deadlock avoidance strategies. + * debug different VM deadlock avoidance strategies. */ void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry) { diff --git a/fs/jbd/recovery.c b/fs/jbd/recovery.c index de5bafb4e..73bb648 100644 --- a/fs/jbd/recovery.c +++ b/fs/jbd/recovery.c @@ -1,6 +1,6 @@ /* * linux/fs/recovery.c - * + * * Written by Stephen C. Tweedie , 1999 * * Copyright 1999-2000 Red Hat Software --- All Rights Reserved @@ -10,7 +10,7 @@ * option, any later version, incorporated herein by reference. * * Journal recovery routines for the generic filesystem journaling code; - * part of the ext2fs journaling system. + * part of the ext2fs journaling system. */ #ifndef __KERNEL__ @@ -25,9 +25,9 @@ /* * Maintain information about the progress of the recovery job, so that - * the different passes can carry information between them. + * the different passes can carry information between them. */ -struct recovery_info +struct recovery_info { tid_t start_transaction; tid_t end_transaction; @@ -116,7 +116,7 @@ static int do_readahead(journal_t *journal, unsigned int start) err = 0; failed: - if (nbufs) + if (nbufs) journal_brelse_array(bufs, nbufs); return err; } @@ -128,7 +128,7 @@ failed: * Read a block from the journal */ -static int jread(struct buffer_head **bhp, journal_t *journal, +static int jread(struct buffer_head **bhp, journal_t *journal, unsigned int offset) { int err; @@ -212,14 +212,14 @@ do { \ /** * journal_recover - recovers a on-disk journal * @journal: the journal to recover - * + * * The primary function for recovering the log contents when mounting a - * journaled device. + * journaled device. * * Recovery is done in three passes. In the first pass, we look for the * end of the log. In the second, we assemble the list of revoke * blocks. In the third and final pass, we replay any un-revoked blocks - * in the log. + * in the log. */ int journal_recover(journal_t *journal) { @@ -231,10 +231,10 @@ int journal_recover(journal_t *journal) memset(&info, 0, sizeof(info)); sb = journal->j_superblock; - /* + /* * The journal superblock's s_start field (the current log head) * is always zero if, and only if, the journal was cleanly - * unmounted. + * unmounted. */ if (!sb->s_start) { @@ -253,7 +253,7 @@ int journal_recover(journal_t *journal) jbd_debug(0, "JBD: recovery, exit status %d, " "recovered transactions %u to %u\n", err, info.start_transaction, info.end_transaction); - jbd_debug(0, "JBD: Replayed %d and revoked %d/%d blocks\n", + jbd_debug(0, "JBD: Replayed %d and revoked %d/%d blocks\n", info.nr_replays, info.nr_revoke_hits, info.nr_revokes); /* Restart the log at the next transaction ID, thus invalidating @@ -268,15 +268,15 @@ int journal_recover(journal_t *journal) /** * journal_skip_recovery - Start journal and wipe exiting records * @journal: journal to startup - * + * * Locate any valid recovery information from the journal and set up the * journal structures in memory to ignore it (presumably because the - * caller has evidence that it is out of date). + * caller has evidence that it is out of date). * This function does'nt appear to be exorted.. * * We perform one pass over the journal to allow us to tell the user how * much recovery information is being erased, and to let us initialise - * the journal transaction sequence numbers to the next unused ID. + * the journal transaction sequence numbers to the next unused ID. */ int journal_skip_recovery(journal_t *journal) { @@ -297,7 +297,7 @@ int journal_skip_recovery(journal_t *journal) #ifdef CONFIG_JBD_DEBUG int dropped = info.end_transaction - be32_to_cpu(sb->s_sequence); #endif - jbd_debug(0, + jbd_debug(0, "JBD: ignoring %d transaction%s from the journal.\n", dropped, (dropped == 1) ? "" : "s"); journal->j_transaction_sequence = ++info.end_transaction; @@ -324,10 +324,10 @@ static int do_one_pass(journal_t *journal, MAX_BLOCKS_PER_DESC = ((journal->j_blocksize-sizeof(journal_header_t)) / sizeof(journal_block_tag_t)); - /* + /* * First thing is to establish what we expect to find in the log * (in terms of transaction IDs), and where (in terms of log - * block offsets): query the superblock. + * block offsets): query the superblock. */ sb = journal->j_superblock; @@ -344,7 +344,7 @@ static int do_one_pass(journal_t *journal, * Now we walk through the log, transaction by transaction, * making sure that each transaction has a commit block in the * expected place. Each complete transaction gets replayed back - * into the main filesystem. + * into the main filesystem. */ while (1) { @@ -379,8 +379,8 @@ static int do_one_pass(journal_t *journal, next_log_block++; wrap(journal, next_log_block); - /* What kind of buffer is it? - * + /* What kind of buffer is it? + * * If it is a descriptor block, check that it has the * expected sequence number. Otherwise, we're all done * here. */ @@ -394,7 +394,7 @@ static int do_one_pass(journal_t *journal, blocktype = be32_to_cpu(tmp->h_blocktype); sequence = be32_to_cpu(tmp->h_sequence); - jbd_debug(3, "Found magic %d, sequence %d\n", + jbd_debug(3, "Found magic %d, sequence %d\n", blocktype, sequence); if (sequence != next_commit_ID) { @@ -438,7 +438,7 @@ static int do_one_pass(journal_t *journal, /* Recover what we can, but * report failure at the end. */ success = err; - printk (KERN_ERR + printk (KERN_ERR "JBD: IO error %d recovering " "block %ld in log\n", err, io_block); @@ -452,7 +452,7 @@ static int do_one_pass(journal_t *journal, * revoked, then we're all done * here. */ if (journal_test_revoke - (journal, blocknr, + (journal, blocknr, next_commit_ID)) { brelse(obh); ++info->nr_revoke_hits; @@ -465,7 +465,7 @@ static int do_one_pass(journal_t *journal, blocknr, journal->j_blocksize); if (nbh == NULL) { - printk(KERN_ERR + printk(KERN_ERR "JBD: Out of memory " "during recovery.\n"); err = -ENOMEM; @@ -537,7 +537,7 @@ static int do_one_pass(journal_t *journal, } done: - /* + /* * We broke out of the log scan loop: either we came to the * known end of the log or we found an unexpected block in the * log. If the latter happened, then we know that the "current" @@ -567,7 +567,7 @@ static int do_one_pass(journal_t *journal, /* Scan a revoke record, marking all blocks mentioned as revoked. */ -static int scan_revoke_records(journal_t *journal, struct buffer_head *bh, +static int scan_revoke_records(journal_t *journal, struct buffer_head *bh, tid_t sequence, struct recovery_info *info) { journal_revoke_header_t *header; diff --git a/fs/jbd/revoke.c b/fs/jbd/revoke.c index a561441..c532429 100644 --- a/fs/jbd/revoke.c +++ b/fs/jbd/revoke.c @@ -1,6 +1,6 @@ /* * linux/fs/revoke.c - * + * * Written by Stephen C. Tweedie , 2000 * * Copyright 2000 Red Hat corp --- All Rights Reserved @@ -15,10 +15,10 @@ * Revoke is the mechanism used to prevent old log records for deleted * metadata from being replayed on top of newer data using the same * blocks. The revoke mechanism is used in two separate places: - * + * * + Commit: during commit we write the entire list of the current * transaction's revoked blocks to the journal - * + * * + Recovery: during recovery we record the transaction ID of all * revoked blocks. If there are multiple revoke records in the log * for a single block, only the last one counts, and if there is a log @@ -29,7 +29,7 @@ * single transaction: * * Block is revoked and then journaled: - * The desired end result is the journaling of the new block, so we + * The desired end result is the journaling of the new block, so we * cancel the revoke before the transaction commits. * * Block is journaled and then revoked: @@ -41,7 +41,7 @@ * transaction must have happened after the block was journaled and so * the revoke must take precedence. * - * Block is revoked and then written as data: + * Block is revoked and then written as data: * The data write is allowed to succeed, but the revoke is _not_ * cancelled. We still need to prevent old log records from * overwriting the new data. We don't even need to clear the revoke @@ -54,7 +54,7 @@ * buffer has not been revoked, and cancel_revoke * need do nothing. * RevokeValid set, Revoked set: - * buffer has been revoked. + * buffer has been revoked. */ #ifndef __KERNEL__ @@ -77,7 +77,7 @@ static kmem_cache_t *revoke_table_cache; journal replay, this involves recording the transaction ID of the last transaction to revoke this block. */ -struct jbd_revoke_record_s +struct jbd_revoke_record_s { struct list_head hash; tid_t sequence; /* Used for recovery only */ @@ -90,8 +90,8 @@ struct jbd_revoke_table_s { /* It is conceivable that we might want a larger hash table * for recovery. Must be a power of two. */ - int hash_size; - int hash_shift; + int hash_size; + int hash_shift; struct list_head *hash_table; }; @@ -301,22 +301,22 @@ void journal_destroy_revoke(journal_t *journal) #ifdef __KERNEL__ -/* +/* * journal_revoke: revoke a given buffer_head from the journal. This * prevents the block from being replayed during recovery if we take a * crash after this current transaction commits. Any subsequent * metadata writes of the buffer in this transaction cancel the - * revoke. + * revoke. * * Note that this call may block --- it is up to the caller to make * sure that there are no further calls to journal_write_metadata * before the revoke is complete. In ext3, this implies calling the * revoke before clearing the block bitmap when we are deleting - * metadata. + * metadata. * * Revoke performs a journal_forget on any buffer_head passed in as a * parameter, but does _not_ forget the buffer_head if the bh was only - * found implicitly. + * found implicitly. * * bh_in may not be a journalled buffer - it may have come off * the hash tables without an attached journal_head. @@ -325,7 +325,7 @@ void journal_destroy_revoke(journal_t *journal) * by one. */ -int journal_revoke(handle_t *handle, unsigned long blocknr, +int journal_revoke(handle_t *handle, unsigned long blocknr, struct buffer_head *bh_in) { struct buffer_head *bh = NULL; @@ -487,7 +487,7 @@ void journal_switch_revoke_table(journal_t *journal) else journal->j_revoke = journal->j_revoke_table[0]; - for (i = 0; i < journal->j_revoke->hash_size; i++) + for (i = 0; i < journal->j_revoke->hash_size; i++) INIT_LIST_HEAD(&journal->j_revoke->hash_table[i]); } @@ -498,7 +498,7 @@ void journal_switch_revoke_table(journal_t *journal) * Called with the journal lock held. */ -void journal_write_revoke_records(journal_t *journal, +void journal_write_revoke_records(journal_t *journal, transaction_t *transaction) { struct journal_head *descriptor; @@ -507,7 +507,7 @@ void journal_write_revoke_records(journal_t *journal, struct list_head *hash_list; int i, offset, count; - descriptor = NULL; + descriptor = NULL; offset = 0; count = 0; @@ -519,10 +519,10 @@ void journal_write_revoke_records(journal_t *journal, hash_list = &revoke->hash_table[i]; while (!list_empty(hash_list)) { - record = (struct jbd_revoke_record_s *) + record = (struct jbd_revoke_record_s *) hash_list->next; write_one_revoke_record(journal, transaction, - &descriptor, &offset, + &descriptor, &offset, record); count++; list_del(&record->hash); @@ -534,14 +534,14 @@ void journal_write_revoke_records(journal_t *journal, jbd_debug(1, "Wrote %d revoke records\n", count); } -/* +/* * Write out one revoke record. We need to create a new descriptor - * block if the old one is full or if we have not already created one. + * block if the old one is full or if we have not already created one. */ -static void write_one_revoke_record(journal_t *journal, +static void write_one_revoke_record(journal_t *journal, transaction_t *transaction, - struct journal_head **descriptorp, + struct journal_head **descriptorp, int *offsetp, struct jbd_revoke_record_s *record) { @@ -584,21 +584,21 @@ static void write_one_revoke_record(journal_t *journal, *descriptorp = descriptor; } - * ((__be32 *)(&jh2bh(descriptor)->b_data[offset])) = + * ((__be32 *)(&jh2bh(descriptor)->b_data[offset])) = cpu_to_be32(record->blocknr); offset += 4; *offsetp = offset; } -/* +/* * Flush a revoke descriptor out to the journal. If we are aborting, * this is a noop; otherwise we are generating a buffer which needs to * be waited for during commit, so it has to go onto the appropriate * journal buffer list. */ -static void flush_descriptor(journal_t *journal, - struct journal_head *descriptor, +static void flush_descriptor(journal_t *journal, + struct journal_head *descriptor, int offset) { journal_revoke_header_t *header; @@ -618,7 +618,7 @@ static void flush_descriptor(journal_t *journal, } #endif -/* +/* * Revoke support for recovery. * * Recovery needs to be able to: @@ -629,7 +629,7 @@ static void flush_descriptor(journal_t *journal, * check whether a given block in a given transaction should be replayed * (ie. has not been revoked by a revoke record in that or a subsequent * transaction) - * + * * empty the revoke table after recovery. */ @@ -637,11 +637,11 @@ static void flush_descriptor(journal_t *journal, * First, setting revoke records. We create a new revoke record for * every block ever revoked in the log as we scan it for recovery, and * we update the existing records if we find multiple revokes for a - * single block. + * single block. */ -int journal_set_revoke(journal_t *journal, - unsigned long blocknr, +int journal_set_revoke(journal_t *journal, + unsigned long blocknr, tid_t sequence) { struct jbd_revoke_record_s *record; @@ -653,18 +653,18 @@ int journal_set_revoke(journal_t *journal, if (tid_gt(sequence, record->sequence)) record->sequence = sequence; return 0; - } + } return insert_revoke_hash(journal, blocknr, sequence); } -/* +/* * Test revoke records. For a given block referenced in the log, has * that block been revoked? A revoke record with a given transaction * sequence number revokes all blocks in that transaction and earlier * ones, but later transactions still need replayed. */ -int journal_test_revoke(journal_t *journal, +int journal_test_revoke(journal_t *journal, unsigned long blocknr, tid_t sequence) { diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index f5169a9..bf7fd71 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -1,6 +1,6 @@ /* * linux/fs/transaction.c - * + * * Written by Stephen C. Tweedie , 1998 * * Copyright 1998 Red Hat corp --- All Rights Reserved @@ -10,7 +10,7 @@ * option, any later version, incorporated herein by reference. * * Generic filesystem transaction handling code; part of the ext2fs - * journaling system. + * journaling system. * * This file manages transactions (compound commits managed by the * journaling code) and handles (individual atomic operations by the @@ -74,7 +74,7 @@ get_transaction(journal_t *journal, transaction_t *transaction) * start_this_handle: Given a handle, deal with any locking or stalling * needed to make sure that there is enough journal space for the handle * to begin. Attach the handle to a transaction and set up the - * transaction's buffer credits. + * transaction's buffer credits. */ static int start_this_handle(journal_t *journal, handle_t *handle) @@ -117,7 +117,7 @@ repeat_locked: if (is_journal_aborted(journal) || (journal->j_errno != 0 && !(journal->j_flags & JFS_ACK_ERR))) { spin_unlock(&journal->j_state_lock); - ret = -EROFS; + ret = -EROFS; goto out; } @@ -182,7 +182,7 @@ repeat_locked: goto repeat; } - /* + /* * The commit code assumes that it can get enough log space * without forcing a checkpoint. This is *critical* for * correctness: a checkpoint of a buffer which is also @@ -191,7 +191,7 @@ repeat_locked: * * We must therefore ensure the necessary space in the journal * *before* starting to dirty potentially checkpointed buffers - * in the new transaction. + * in the new transaction. * * The worst part is, any transaction currently committing can * reduce the free space arbitrarily. Be careful to account for @@ -246,13 +246,13 @@ static handle_t *new_handle(int nblocks) } /** - * handle_t *journal_start() - Obtain a new handle. + * handle_t *journal_start() - Obtain a new handle. * @journal: Journal to start transaction on. * @nblocks: number of block buffer we might modify * * We make sure that the transaction can guarantee at least nblocks of * modified buffers in the log. We block until the log can guarantee - * that much space. + * that much space. * * This function is visible to journal users (like ext3fs), so is not * called with the journal already locked. @@ -292,11 +292,11 @@ handle_t *journal_start(journal_t *journal, int nblocks) * int journal_extend() - extend buffer credits. * @handle: handle to 'extend' * @nblocks: nr blocks to try to extend by. - * + * * Some transactions, such as large extends and truncates, can be done * atomically all at once or in several stages. The operation requests * a credit for a number of buffer modications in advance, but can - * extend its credit if it needs more. + * extend its credit if it needs more. * * journal_extend tries to give the running handle more buffer credits. * It does not guarantee that allocation - this is a best-effort only. @@ -363,7 +363,7 @@ out: * int journal_restart() - restart a handle . * @handle: handle to restart * @nblocks: nr credits requested - * + * * Restart a handle for a multi-transaction filesystem * operation. * @@ -462,7 +462,7 @@ void journal_lock_updates(journal_t *journal) /** * void journal_unlock_updates (journal_t* journal) - release barrier * @journal: Journal to release the barrier on. - * + * * Release a transaction barrier obtained with journal_lock_updates(). * * Should be called without the journal lock held. @@ -547,8 +547,8 @@ repeat: jbd_lock_bh_state(bh); /* We now hold the buffer lock so it is safe to query the buffer - * state. Is the buffer dirty? - * + * state. Is the buffer dirty? + * * If so, there are two possibilities. The buffer may be * non-journaled, and undergoing a quite legitimate writeback. * Otherwise, it is journaled, and we don't expect dirty buffers @@ -566,7 +566,7 @@ repeat: */ if (jh->b_transaction) { J_ASSERT_JH(jh, - jh->b_transaction == transaction || + jh->b_transaction == transaction || jh->b_transaction == journal->j_committing_transaction); if (jh->b_next_transaction) @@ -653,7 +653,7 @@ repeat: * buffer had better remain locked during the kmalloc, * but that should be true --- we hold the journal lock * still and the buffer is already on the BUF_JOURNAL - * list so won't be flushed. + * list so won't be flushed. * * Subtle point, though: if this is a get_undo_access, * then we will be relying on the frozen_data to contain @@ -765,8 +765,8 @@ int journal_get_write_access(handle_t *handle, struct buffer_head *bh) * manually rather than reading off disk), then we need to keep the * buffer_head locked until it has been completely filled with new * data. In this case, we should be able to make the assertion that - * the bh is not already part of an existing transaction. - * + * the bh is not already part of an existing transaction. + * * The buffer should already be locked by the caller by this point. * There is no lock ranking violation: it was a newly created, * unlocked buffer beforehand. */ @@ -778,7 +778,7 @@ int journal_get_write_access(handle_t *handle, struct buffer_head *bh) * * Call this if you create a new bh. */ -int journal_get_create_access(handle_t *handle, struct buffer_head *bh) +int journal_get_create_access(handle_t *handle, struct buffer_head *bh) { transaction_t *transaction = handle->h_transaction; journal_t *journal = transaction->t_journal; @@ -847,13 +847,13 @@ out: * do not reuse freed space until the deallocation has been committed, * since if we overwrote that space we would make the delete * un-rewindable in case of a crash. - * + * * To deal with that, journal_get_undo_access requests write access to a * buffer for parts of non-rewindable operations such as delete * operations on the bitmaps. The journaling code must keep a copy of * the buffer's contents prior to the undo_access call until such time * as we know that the buffer has definitely been committed to disk. - * + * * We never need to know which transaction the committed data is part * of, buffers touched here are guaranteed to be dirtied later and so * will be committed to a new transaction in due course, at which point @@ -911,13 +911,13 @@ out: return err; } -/** +/** * int journal_dirty_data() - mark a buffer as containing dirty data which * needs to be flushed before we can commit the - * current transaction. + * current transaction. * @handle: transaction * @bh: bufferhead to mark - * + * * The buffer is placed on the transaction's data list and is marked as * belonging to the transaction. * @@ -946,15 +946,15 @@ int journal_dirty_data(handle_t *handle, struct buffer_head *bh) /* * What if the buffer is already part of a running transaction? - * + * * There are two cases: * 1) It is part of the current running transaction. Refile it, * just in case we have allocated it as metadata, deallocated - * it, then reallocated it as data. + * it, then reallocated it as data. * 2) It is part of the previous, still-committing transaction. * If all we want to do is to guarantee that the buffer will be * written to disk before this new transaction commits, then - * being sure that the *previous* transaction has this same + * being sure that the *previous* transaction has this same * property is sufficient for us! Just leave it on its old * transaction. * @@ -1076,18 +1076,18 @@ no_journal: return 0; } -/** +/** * int journal_dirty_metadata() - mark a buffer as containing dirty metadata * @handle: transaction to add buffer to. - * @bh: buffer to mark - * + * @bh: buffer to mark + * * mark dirty metadata which needs to be journaled as part of the current * transaction. * * The buffer is placed on the transaction's metadata list and is marked - * as belonging to the transaction. + * as belonging to the transaction. * - * Returns error number or 0 on success. + * Returns error number or 0 on success. * * Special care needs to be taken if the buffer already belongs to the * current committing transaction (in which case we should have frozen @@ -1135,11 +1135,11 @@ int journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) set_buffer_jbddirty(bh); - /* + /* * Metadata already on the current transaction list doesn't * need to be filed. Metadata on another transaction's list must * be committing, and will be refiled once the commit completes: - * leave it alone for now. + * leave it alone for now. */ if (jh->b_transaction != transaction) { JBUFFER_TRACE(jh, "already on other transaction"); @@ -1165,7 +1165,7 @@ out: return 0; } -/* +/* * journal_release_buffer: undo a get_write_access without any buffer * updates, if the update decided in the end that it didn't need access. * @@ -1176,20 +1176,20 @@ journal_release_buffer(handle_t *handle, struct buffer_head *bh) BUFFER_TRACE(bh, "entry"); } -/** +/** * void journal_forget() - bforget() for potentially-journaled buffers. * @handle: transaction handle * @bh: bh to 'forget' * * We can only do the bforget if there are no commits pending against the * buffer. If the buffer is dirty in the current running transaction we - * can safely unlink it. + * can safely unlink it. * * bh may not be a journalled buffer at all - it may be a non-JBD * buffer which came off the hashtable. Check for this. * * Decrements bh->b_count by one. - * + * * Allow this call even if the handle has aborted --- it may be part of * the caller's cleanup after an abort. */ @@ -1237,7 +1237,7 @@ int journal_forget (handle_t *handle, struct buffer_head *bh) drop_reserve = 1; - /* + /* * We are no longer going to journal this buffer. * However, the commit of this transaction is still * important to the buffer: the delete that we are now @@ -1246,7 +1246,7 @@ int journal_forget (handle_t *handle, struct buffer_head *bh) * * So, if we have a checkpoint on the buffer, we should * now refile the buffer on our BJ_Forget list so that - * we know to remove the checkpoint after we commit. + * we know to remove the checkpoint after we commit. */ if (jh->b_cp_transaction) { @@ -1264,7 +1264,7 @@ int journal_forget (handle_t *handle, struct buffer_head *bh) } } } else if (jh->b_transaction) { - J_ASSERT_JH(jh, (jh->b_transaction == + J_ASSERT_JH(jh, (jh->b_transaction == journal->j_committing_transaction)); /* However, if the buffer is still owned by a prior * (committing) transaction, we can't drop it yet... */ @@ -1294,7 +1294,7 @@ drop: /** * int journal_stop() - complete a transaction * @handle: tranaction to complete. - * + * * All done for a particular handle. * * There is not much action needed here. We just return any remaining @@ -1303,7 +1303,7 @@ drop: * filesystem is marked for synchronous update. * * journal_stop itself will not usually return an error, but it may - * do so in unusual circumstances. In particular, expect it to + * do so in unusual circumstances. In particular, expect it to * return -EIO if a journal_abort has been executed since the * transaction began. */ @@ -1388,7 +1388,7 @@ int journal_stop(handle_t *handle) /* * Special case: JFS_SYNC synchronous updates require us - * to wait for the commit to complete. + * to wait for the commit to complete. */ if (handle->h_sync && !(current->flags & PF_MEMALLOC)) err = log_wait_commit(journal, tid); @@ -1439,7 +1439,7 @@ int journal_force_commit(journal_t *journal) * jbd_lock_bh_state(jh2bh(jh)) is held. */ -static inline void +static inline void __blist_add_buffer(struct journal_head **list, struct journal_head *jh) { if (!*list) { @@ -1454,7 +1454,7 @@ __blist_add_buffer(struct journal_head **list, struct journal_head *jh) } } -/* +/* * Remove a buffer from a transaction list, given the transaction's list * head pointer. * @@ -1475,7 +1475,7 @@ __blist_del_buffer(struct journal_head **list, struct journal_head *jh) jh->b_tnext->b_tprev = jh->b_tprev; } -/* +/* * Remove a buffer from the appropriate transaction list. * * Note that this function can *change* the value of @@ -1595,17 +1595,17 @@ out: } -/** +/** * int journal_try_to_free_buffers() - try to free page buffers. * @journal: journal for operation * @page: to try and free * @unused_gfp_mask: unused * - * + * * For all the buffers on this page, * if they are fully written out ordered data, move them onto BUF_CLEAN * so try_to_free_buffers() can reap them. - * + * * This function returns non-zero if we wish try_to_free_buffers() * to be called. We do this if the page is releasable by try_to_free_buffers(). * We also do it if the page has locked or dirty buffers and the caller wants @@ -1629,7 +1629,7 @@ out: * cannot happen because we never reallocate freed data as metadata * while the data is part of a transaction. Yes? */ -int journal_try_to_free_buffers(journal_t *journal, +int journal_try_to_free_buffers(journal_t *journal, struct page *page, gfp_t unused_gfp_mask) { struct buffer_head *head; @@ -1697,7 +1697,7 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) } /* - * journal_invalidatepage + * journal_invalidatepage * * This code is tricky. It has a number of cases to deal with. * @@ -1705,15 +1705,15 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) * * i_size must be updated on disk before we start calling invalidatepage on the * data. - * + * * This is done in ext3 by defining an ext3_setattr method which * updates i_size before truncate gets going. By maintaining this * invariant, we can be sure that it is safe to throw away any buffers * attached to the current transaction: once the transaction commits, * we know that the data will not be needed. - * + * * Note however that we can *not* throw away data belonging to the - * previous, committing transaction! + * previous, committing transaction! * * Any disk blocks which *are* part of the previous, committing * transaction (and which therefore cannot be discarded immediately) are @@ -1732,7 +1732,7 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) * don't make guarantees about the order in which data hits disk --- in * particular we don't guarantee that new dirty data is flushed before * transaction commit --- so it is always safe just to discard data - * immediately in that mode. --sct + * immediately in that mode. --sct */ /* @@ -1876,9 +1876,9 @@ zap_buffer_unlocked: return may_free; } -/** +/** * void journal_invalidatepage() - * @journal: journal to use for flush... + * @journal: journal to use for flush... * @page: page to flush * @offset: length of page to invalidate. * @@ -1886,7 +1886,7 @@ zap_buffer_unlocked: * */ void journal_invalidatepage(journal_t *journal, - struct page *page, + struct page *page, unsigned long offset) { struct buffer_head *head, *bh, *next; @@ -1924,8 +1924,8 @@ void journal_invalidatepage(journal_t *journal, } } -/* - * File a buffer on the given transaction list. +/* + * File a buffer on the given transaction list. */ void __journal_file_buffer(struct journal_head *jh, transaction_t *transaction, int jlist) @@ -1948,7 +1948,7 @@ void __journal_file_buffer(struct journal_head *jh, * with __jbd_unexpected_dirty_buffer()'s handling of dirty * state. */ - if (jlist == BJ_Metadata || jlist == BJ_Reserved || + if (jlist == BJ_Metadata || jlist == BJ_Reserved || jlist == BJ_Shadow || jlist == BJ_Forget) { if (test_clear_buffer_dirty(bh) || test_clear_buffer_jbddirty(bh)) @@ -2008,7 +2008,7 @@ void journal_file_buffer(struct journal_head *jh, jbd_unlock_bh_state(jh2bh(jh)); } -/* +/* * Remove a buffer from its current buffer list in preparation for * dropping it from its current transaction entirely. If the buffer has * already started to be used by a subsequent transaction, refile the @@ -2060,7 +2060,7 @@ void __journal_refile_buffer(struct journal_head *jh) * to the caller to remove the journal_head if necessary. For the * unlocked journal_refile_buffer call, the caller isn't going to be * doing anything else to the buffer so we need to do the cleanup - * ourselves to avoid a jh leak. + * ourselves to avoid a jh leak. * * *** The journal_head may be freed by this call! *** */ -- cgit v1.1 From 2aed3484695ecb03f1395bb62f1099e8b0826124 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 27 Sep 2006 01:49:28 -0700 Subject: [PATCH] jbd: use BUILD_BUG_ON in journal init Signed-off-by: Alexey Dobriyan Acked-by: Stephen Tweedie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/jbd/journal.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'fs') diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 87c5a6d..2613fca 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -2047,13 +2047,7 @@ static int __init journal_init(void) { int ret; -/* Static check for data structure consistency. There's no code - * invoked --- we'll just get a linker failure if things aren't right. - */ - extern void journal_bad_superblock_size(void); - if (sizeof(struct journal_superblock_s) != 1024) - journal_bad_superblock_size(); - + BUILD_BUG_ON(sizeof(struct journal_superblock_s) != 1024); ret = journal_init_caches(); if (ret != 0) -- cgit v1.1 From 855565e81ad8940cc645b5110ec2c7f124a76d23 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Wed, 27 Sep 2006 01:49:29 -0700 Subject: [PATCH] fix ext3 mounts at 16T I need to do some actual IO testing now, but this gets things mounting for a 16T ext3 filesystem. (patched up e2fsprogs is needed too, I'll send that off the kernel list) This patch fixes these issues in the kernel: o sbi->s_groups_count overflows in ext3_fill_super() sbi->s_groups_count = (le32_to_cpu(es->s_blocks_count) - le32_to_cpu(es->s_first_data_block) + EXT3_BLOCKS_PER_GROUP(sb) - 1) / EXT3_BLOCKS_PER_GROUP(sb); at 16T, s_blocks_count is already maxed out; adding EXT3_BLOCKS_PER_GROUP(sb) overflows it and groups_count comes out to 0. Not really what we want, and causes a failed mount. Feel free to check my math (actually, please do!), but changing it this way should work & avoid the overflow: (A + B - 1)/B changed to: ((A - 1)/B) + 1 o ext3_check_descriptors() overflows range checks ext3_check_descriptors() iterates over all block groups making sure that various bits are within the right block ranges... on the last pass through, it is checking the error case [item] >= block + EXT3_BLOCKS_PER_GROUP(sb) where "block" is the first block in the last block group. The last block in this group (and the last one that will fit in 32 bits) is block + EXT3_BLOCKS_PER_GROUP(sb)- 1. block + EXT3_BLOCKS_PER_GROUP(sb) wraps back around to 0. so, make things clearer with "first_block" and "last_block" where those are first and last, inclusive, and use <, > rather than <, >=. Finally, the last block group may be smaller than the rest, so account for this on the last pass through: last_block = sb->s_blocks_count - 1; (a similar patch could be done for ext2; does anyone in their right mind use ext2 at 16T? I'll send an ext2 patch doing the same thing if that's warranted) Signed-off-by: Eric Sandeen Cc: Mingming Cao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/super.c | 34 +++++++++++++++++++--------------- 1 file changed, 19 insertions(+), 15 deletions(-) (limited to 'fs') diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 4b95bfe..762dff7 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1174,7 +1174,8 @@ static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es, static int ext3_check_descriptors (struct super_block * sb) { struct ext3_sb_info *sbi = EXT3_SB(sb); - ext3_fsblk_t block = le32_to_cpu(sbi->s_es->s_first_data_block); + ext3_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); + ext3_fsblk_t last_block; struct ext3_group_desc * gdp = NULL; int desc_block = 0; int i; @@ -1183,12 +1184,17 @@ static int ext3_check_descriptors (struct super_block * sb) for (i = 0; i < sbi->s_groups_count; i++) { + if (i == sbi->s_groups_count - 1) + last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1; + else + last_block = first_block + + (EXT3_BLOCKS_PER_GROUP(sb) - 1); + if ((i % EXT3_DESC_PER_BLOCK(sb)) == 0) gdp = (struct ext3_group_desc *) sbi->s_group_desc[desc_block++]->b_data; - if (le32_to_cpu(gdp->bg_block_bitmap) < block || - le32_to_cpu(gdp->bg_block_bitmap) >= - block + EXT3_BLOCKS_PER_GROUP(sb)) + if (le32_to_cpu(gdp->bg_block_bitmap) < first_block || + le32_to_cpu(gdp->bg_block_bitmap) > last_block) { ext3_error (sb, "ext3_check_descriptors", "Block bitmap for group %d" @@ -1197,9 +1203,8 @@ static int ext3_check_descriptors (struct super_block * sb) le32_to_cpu(gdp->bg_block_bitmap)); return 0; } - if (le32_to_cpu(gdp->bg_inode_bitmap) < block || - le32_to_cpu(gdp->bg_inode_bitmap) >= - block + EXT3_BLOCKS_PER_GROUP(sb)) + if (le32_to_cpu(gdp->bg_inode_bitmap) < first_block || + le32_to_cpu(gdp->bg_inode_bitmap) > last_block) { ext3_error (sb, "ext3_check_descriptors", "Inode bitmap for group %d" @@ -1208,9 +1213,9 @@ static int ext3_check_descriptors (struct super_block * sb) le32_to_cpu(gdp->bg_inode_bitmap)); return 0; } - if (le32_to_cpu(gdp->bg_inode_table) < block || - le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group >= - block + EXT3_BLOCKS_PER_GROUP(sb)) + if (le32_to_cpu(gdp->bg_inode_table) < first_block || + le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group > + last_block) { ext3_error (sb, "ext3_check_descriptors", "Inode table for group %d" @@ -1219,7 +1224,7 @@ static int ext3_check_descriptors (struct super_block * sb) le32_to_cpu(gdp->bg_inode_table)); return 0; } - block += EXT3_BLOCKS_PER_GROUP(sb); + first_block += EXT3_BLOCKS_PER_GROUP(sb); gdp++; } @@ -1622,10 +1627,9 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) if (EXT3_BLOCKS_PER_GROUP(sb) == 0) goto cantfind_ext3; - sbi->s_groups_count = (le32_to_cpu(es->s_blocks_count) - - le32_to_cpu(es->s_first_data_block) + - EXT3_BLOCKS_PER_GROUP(sb) - 1) / - EXT3_BLOCKS_PER_GROUP(sb); + sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) - + le32_to_cpu(es->s_first_data_block) - 1) + / EXT3_BLOCKS_PER_GROUP(sb)) + 1; db_count = (sbi->s_groups_count + EXT3_DESC_PER_BLOCK(sb) - 1) / EXT3_DESC_PER_BLOCK(sb); sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *), -- cgit v1.1 From 41f04d852e359582518f950d12b2287766613022 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Wed, 27 Sep 2006 01:49:30 -0700 Subject: [PATCH] ext2: fix mounts at 16T Signed-off-by: Eric Sandeen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext2/super.c | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) (limited to 'fs') diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 4286ff6..d978d3f 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -544,17 +544,24 @@ static int ext2_check_descriptors (struct super_block * sb) int i; int desc_block = 0; struct ext2_sb_info *sbi = EXT2_SB(sb); - unsigned long block = le32_to_cpu(sbi->s_es->s_first_data_block); + unsigned long first_block = le32_to_cpu(sbi->s_es->s_first_data_block); + unsigned long last_block; struct ext2_group_desc * gdp = NULL; ext2_debug ("Checking group descriptors"); for (i = 0; i < sbi->s_groups_count; i++) { + if (i == sbi->s_groups_count - 1) + last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1; + else + last_block = first_block + + (EXT2_BLOCKS_PER_GROUP(sb) - 1); + if ((i % EXT2_DESC_PER_BLOCK(sb)) == 0) gdp = (struct ext2_group_desc *) sbi->s_group_desc[desc_block++]->b_data; - if (le32_to_cpu(gdp->bg_block_bitmap) < block || - le32_to_cpu(gdp->bg_block_bitmap) >= block + EXT2_BLOCKS_PER_GROUP(sb)) + if (le32_to_cpu(gdp->bg_block_bitmap) < first_block || + le32_to_cpu(gdp->bg_block_bitmap) > last_block) { ext2_error (sb, "ext2_check_descriptors", "Block bitmap for group %d" @@ -562,8 +569,8 @@ static int ext2_check_descriptors (struct super_block * sb) i, (unsigned long) le32_to_cpu(gdp->bg_block_bitmap)); return 0; } - if (le32_to_cpu(gdp->bg_inode_bitmap) < block || - le32_to_cpu(gdp->bg_inode_bitmap) >= block + EXT2_BLOCKS_PER_GROUP(sb)) + if (le32_to_cpu(gdp->bg_inode_bitmap) < first_block || + le32_to_cpu(gdp->bg_inode_bitmap) > last_block) { ext2_error (sb, "ext2_check_descriptors", "Inode bitmap for group %d" @@ -571,9 +578,9 @@ static int ext2_check_descriptors (struct super_block * sb) i, (unsigned long) le32_to_cpu(gdp->bg_inode_bitmap)); return 0; } - if (le32_to_cpu(gdp->bg_inode_table) < block || - le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group >= - block + EXT2_BLOCKS_PER_GROUP(sb)) + if (le32_to_cpu(gdp->bg_inode_table) < first_block || + le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group > + last_block) { ext2_error (sb, "ext2_check_descriptors", "Inode table for group %d" @@ -581,7 +588,7 @@ static int ext2_check_descriptors (struct super_block * sb) i, (unsigned long) le32_to_cpu(gdp->bg_inode_table)); return 0; } - block += EXT2_BLOCKS_PER_GROUP(sb); + first_block += EXT2_BLOCKS_PER_GROUP(sb); gdp++; } return 1; @@ -861,10 +868,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) if (EXT2_BLOCKS_PER_GROUP(sb) == 0) goto cantfind_ext2; - sbi->s_groups_count = (le32_to_cpu(es->s_blocks_count) - - le32_to_cpu(es->s_first_data_block) + - EXT2_BLOCKS_PER_GROUP(sb) - 1) / - EXT2_BLOCKS_PER_GROUP(sb); + sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) - + le32_to_cpu(es->s_first_data_block) - 1) + / EXT2_BLOCKS_PER_GROUP(sb)) + 1; db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) / EXT2_DESC_PER_BLOCK(sb); sbi->s_group_desc = kmalloc (db_count * sizeof (struct buffer_head *), GFP_KERNEL); -- cgit v1.1 From eee194e76c681dbdbf5024b889fda1181b66ef57 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Wed, 27 Sep 2006 01:49:30 -0700 Subject: [PATCH] ext3: inode numbers are unsigned long This is primarily format string fixes, with changes to ialloc.c where large inode counts could overflow, and also pass around journal_inum as an unsigned long, just to be pedantic about it.... Signed-off-by: Eric Sandeen Cc: Mingming Cao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/ialloc.c | 6 +++--- fs/ext3/inode.c | 2 +- fs/ext3/namei.c | 4 ++-- fs/ext3/super.c | 25 +++++++++++++------------ fs/ext3/xattr.c | 16 ++++++++-------- 5 files changed, 27 insertions(+), 26 deletions(-) (limited to 'fs') diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c index 5e28836..1e4ded8 100644 --- a/fs/ext3/ialloc.c +++ b/fs/ext3/ialloc.c @@ -202,7 +202,7 @@ error_return: static int find_group_dir(struct super_block *sb, struct inode *parent) { int ngroups = EXT3_SB(sb)->s_groups_count; - int freei, avefreei; + unsigned int freei, avefreei; struct ext3_group_desc *desc, *best_desc = NULL; struct buffer_head *bh; int group, best_group = -1; @@ -261,10 +261,10 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent) struct ext3_super_block *es = sbi->s_es; int ngroups = sbi->s_groups_count; int inodes_per_group = EXT3_INODES_PER_GROUP(sb); - int freei, avefreei; + unsigned int freei, avefreei; ext3_fsblk_t freeb, avefreeb; ext3_fsblk_t blocks_per_dir; - int ndirs; + unsigned int ndirs; int max_debt, max_dirs, min_inodes; ext3_grpblk_t min_blocks; int group = -1, i; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 473d206..56665fa 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -2115,7 +2115,7 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode, */ if (!bh) { ext3_error(inode->i_sb, "ext3_free_branches", - "Read failure, inode=%ld, block="E3FSBLK, + "Read failure, inode=%lu, block="E3FSBLK, inode->i_ino, nr); continue; } diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 4123f52..70dc520 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1919,8 +1919,8 @@ int ext3_orphan_add(handle_t *handle, struct inode *inode) if (!err) list_add(&EXT3_I(inode)->i_orphan, &EXT3_SB(sb)->s_orphan); - jbd_debug(4, "superblock will point to %ld\n", inode->i_ino); - jbd_debug(4, "orphan inode %ld will point to %d\n", + jbd_debug(4, "superblock will point to %lu\n", inode->i_ino); + jbd_debug(4, "orphan inode %lu will point to %d\n", inode->i_ino, NEXT_ORPHAN(inode)); out_unlock: unlock_super(sb); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 762dff7..bc7a768 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -45,7 +45,7 @@ static int ext3_load_journal(struct super_block *, struct ext3_super_block *, unsigned long journal_devnum); static int ext3_create_journal(struct super_block *, struct ext3_super_block *, - int); + unsigned int); static void ext3_commit_super (struct super_block * sb, struct ext3_super_block * es, int sync); @@ -376,7 +376,7 @@ static void dump_orphan_list(struct super_block *sb, struct ext3_sb_info *sbi) list_for_each(l, &sbi->s_orphan) { struct inode *inode = orphan_list_entry(l); printk(KERN_ERR " " - "inode %s:%ld at %p: mode %o, nlink %d, next %d\n", + "inode %s:%lu at %p: mode %o, nlink %d, next %d\n", inode->i_sb->s_id, inode->i_ino, inode, inode->i_mode, inode->i_nlink, NEXT_ORPHAN(inode)); @@ -753,7 +753,7 @@ static ext3_fsblk_t get_sb_block(void **data) } static int parse_options (char *options, struct super_block *sb, - unsigned long *inum, unsigned long *journal_devnum, + unsigned int *inum, unsigned long *journal_devnum, ext3_fsblk_t *n_blocks_count, int is_remount) { struct ext3_sb_info *sbi = EXT3_SB(sb); @@ -1306,17 +1306,17 @@ static void ext3_orphan_cleanup (struct super_block * sb, DQUOT_INIT(inode); if (inode->i_nlink) { printk(KERN_DEBUG - "%s: truncating inode %ld to %Ld bytes\n", + "%s: truncating inode %lu to %Ld bytes\n", __FUNCTION__, inode->i_ino, inode->i_size); - jbd_debug(2, "truncating inode %ld to %Ld bytes\n", + jbd_debug(2, "truncating inode %lu to %Ld bytes\n", inode->i_ino, inode->i_size); ext3_truncate(inode); nr_truncates++; } else { printk(KERN_DEBUG - "%s: deleting unreferenced inode %ld\n", + "%s: deleting unreferenced inode %lu\n", __FUNCTION__, inode->i_ino); - jbd_debug(2, "deleting unreferenced inode %ld\n", + jbd_debug(2, "deleting unreferenced inode %lu\n", inode->i_ino); nr_orphans++; } @@ -1395,7 +1395,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) ext3_fsblk_t sb_block = get_sb_block(&data); ext3_fsblk_t logic_sb_block; unsigned long offset = 0; - unsigned long journal_inum = 0; + unsigned int journal_inum = 0; unsigned long journal_devnum = 0; unsigned long def_mount_opts; struct inode *root; @@ -1844,7 +1844,8 @@ static void ext3_init_journal_params(struct super_block *sb, journal_t *journal) spin_unlock(&journal->j_state_lock); } -static journal_t *ext3_get_journal(struct super_block *sb, int journal_inum) +static journal_t *ext3_get_journal(struct super_block *sb, + unsigned int journal_inum) { struct inode *journal_inode; journal_t *journal; @@ -1979,7 +1980,7 @@ static int ext3_load_journal(struct super_block *sb, unsigned long journal_devnum) { journal_t *journal; - int journal_inum = le32_to_cpu(es->s_journal_inum); + unsigned int journal_inum = le32_to_cpu(es->s_journal_inum); dev_t journal_dev; int err = 0; int really_read_only; @@ -2065,7 +2066,7 @@ static int ext3_load_journal(struct super_block *sb, static int ext3_create_journal(struct super_block * sb, struct ext3_super_block * es, - int journal_inum) + unsigned int journal_inum) { journal_t *journal; @@ -2078,7 +2079,7 @@ static int ext3_create_journal(struct super_block * sb, if (!(journal = ext3_get_journal(sb, journal_inum))) return -EINVAL; - printk(KERN_INFO "EXT3-fs: creating new journal on inode %d\n", + printk(KERN_INFO "EXT3-fs: creating new journal on inode %u\n", journal_inum); if (journal_create(journal)) { diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c index a44a056..f86f248 100644 --- a/fs/ext3/xattr.c +++ b/fs/ext3/xattr.c @@ -75,7 +75,7 @@ #ifdef EXT3_XATTR_DEBUG # define ea_idebug(inode, f...) do { \ - printk(KERN_DEBUG "inode %s:%ld: ", \ + printk(KERN_DEBUG "inode %s:%lu: ", \ inode->i_sb->s_id, inode->i_ino); \ printk(f); \ printk("\n"); \ @@ -233,7 +233,7 @@ ext3_xattr_block_get(struct inode *inode, int name_index, const char *name, atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); if (ext3_xattr_check_block(bh)) { bad_block: ext3_error(inode->i_sb, __FUNCTION__, - "inode %ld: bad block "E3FSBLK, inode->i_ino, + "inode %lu: bad block "E3FSBLK, inode->i_ino, EXT3_I(inode)->i_file_acl); error = -EIO; goto cleanup; @@ -375,7 +375,7 @@ ext3_xattr_block_list(struct inode *inode, char *buffer, size_t buffer_size) atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); if (ext3_xattr_check_block(bh)) { ext3_error(inode->i_sb, __FUNCTION__, - "inode %ld: bad block "E3FSBLK, inode->i_ino, + "inode %lu: bad block "E3FSBLK, inode->i_ino, EXT3_I(inode)->i_file_acl); error = -EIO; goto cleanup; @@ -647,7 +647,7 @@ ext3_xattr_block_find(struct inode *inode, struct ext3_xattr_info *i, le32_to_cpu(BHDR(bs->bh)->h_refcount)); if (ext3_xattr_check_block(bs->bh)) { ext3_error(sb, __FUNCTION__, - "inode %ld: bad block "E3FSBLK, inode->i_ino, + "inode %lu: bad block "E3FSBLK, inode->i_ino, EXT3_I(inode)->i_file_acl); error = -EIO; goto cleanup; @@ -848,7 +848,7 @@ cleanup_dquot: bad_block: ext3_error(inode->i_sb, __FUNCTION__, - "inode %ld: bad block "E3FSBLK, inode->i_ino, + "inode %lu: bad block "E3FSBLK, inode->i_ino, EXT3_I(inode)->i_file_acl); goto cleanup; @@ -1077,14 +1077,14 @@ ext3_xattr_delete_inode(handle_t *handle, struct inode *inode) bh = sb_bread(inode->i_sb, EXT3_I(inode)->i_file_acl); if (!bh) { ext3_error(inode->i_sb, __FUNCTION__, - "inode %ld: block "E3FSBLK" read error", inode->i_ino, + "inode %lu: block "E3FSBLK" read error", inode->i_ino, EXT3_I(inode)->i_file_acl); goto cleanup; } if (BHDR(bh)->h_magic != cpu_to_le32(EXT3_XATTR_MAGIC) || BHDR(bh)->h_blocks != cpu_to_le32(1)) { ext3_error(inode->i_sb, __FUNCTION__, - "inode %ld: bad block "E3FSBLK, inode->i_ino, + "inode %lu: bad block "E3FSBLK, inode->i_ino, EXT3_I(inode)->i_file_acl); goto cleanup; } @@ -1211,7 +1211,7 @@ again: bh = sb_bread(inode->i_sb, ce->e_block); if (!bh) { ext3_error(inode->i_sb, __FUNCTION__, - "inode %ld: block %lu read error", + "inode %lu: block %lu read error", inode->i_ino, (unsigned long) ce->e_block); } else if (le32_to_cpu(BHDR(bh)->h_refcount) >= EXT3_XATTR_REFCOUNT_MAX) { -- cgit v1.1 From 37ed322290eb6d5cf2ab33915793ed4219eae1d6 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Wed, 27 Sep 2006 01:49:31 -0700 Subject: [PATCH] JBD: 16T fixes These are a few places I've found in jbd that look like they may not be 16T-safe, or consistent with the use of unsigned longs for block containers. Problems here would be somewhat hard to hit, would require journal blocks past the 8T boundary, which would not be terribly common. Still, should fix. (some of these have come from the ext4 work on jbd as well). I think there's one more possibility that the wrap() function may not be safe IF your last block in the journal butts right up against the 232 block boundary, but that seems like a VERY remote possibility, and I'm not worrying about it at this point. Signed-off-by: Eric Sandeen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/jbd/journal.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 2613fca..88d970e 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -271,7 +271,7 @@ static void journal_kill_thread(journal_t *journal) int journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct journal_head **jh_out, - int blocknr) + unsigned long blocknr) { int need_copy_out = 0; int done_copy_out = 0; @@ -696,7 +696,7 @@ fail: * @bdev: Block device on which to create the journal * @fs_dev: Device which hold journalled filesystem for this journal. * @start: Block nr Start of journal. - * @len: Lenght of the journal in blocks. + * @len: Length of the journal in blocks. * @blocksize: blocksize of journalling device * @returns: a newly created journal_t * * @@ -820,7 +820,7 @@ static void journal_fail_superblock (journal_t *journal) static int journal_reset(journal_t *journal) { journal_superblock_t *sb = journal->j_superblock; - unsigned int first, last; + unsigned long first, last; first = be32_to_cpu(sb->s_first); last = be32_to_cpu(sb->s_maxlen); -- cgit v1.1 From 321fb9e81821a81b2cda1328698b0c19d57c717f Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Wed, 27 Sep 2006 01:49:32 -0700 Subject: [PATCH] ext3: turn on reservation dump on block allocation errors In the past there were a few kernel panics related to block reservation tree operations failure (insert/remove etc). It would be very useful to get the block allocation reservation map info when such error happens. Signed-off-by: Mingming Cao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/balloc.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index e6b9837..2bd836f 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -111,7 +111,7 @@ error_out: * we could easily switch to that without changing too much * code. */ -#if 0 +#if 1 static void __rsv_window_dump(struct rb_root *root, int verbose, const char *fn) { @@ -129,7 +129,7 @@ restart: rsv = list_entry(n, struct ext3_reserve_window_node, rsv_node); if (verbose) printk("reservation window 0x%p " - "start: %d, end: %d\n", + "start: %lu, end: %lu\n", rsv, rsv->rsv_start, rsv->rsv_end); if (rsv->rsv_start && rsv->rsv_start >= rsv->rsv_end) { printk("Bad reservation %p (start >= end)\n", @@ -236,8 +236,10 @@ void ext3_rsv_window_add(struct super_block *sb, p = &(*p)->rb_left; else if (start > this->rsv_end) p = &(*p)->rb_right; - else + else { + rsv_window_dump(root, 1); BUG(); + } } rb_link_node(node, parent, p); @@ -1133,8 +1135,10 @@ ext3_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle, *count-my_rsv->rsv_end + grp_goal - 1); if ((my_rsv->rsv_start >= group_first_block + EXT3_BLOCKS_PER_GROUP(sb)) - || (my_rsv->rsv_end < group_first_block)) + || (my_rsv->rsv_end < group_first_block)) { + rsv_window_dump(&EXT3_SB(sb)->s_rsv_window_root, 1); BUG(); + } ret = ext3_try_to_allocate(sb, handle, group, bitmap_bh, grp_goal, &num, &my_rsv->rsv_window); if (ret >= 0) { -- cgit v1.1 From 36faadc144477b4929c8fe60b8053f4472eeb3d2 Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Wed, 27 Sep 2006 01:49:32 -0700 Subject: [PATCH] ext3: more comments about block allocation/reservation code Signed-off-by: Mingming Cao Acked-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/balloc.c | 292 ++++++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 247 insertions(+), 45 deletions(-) (limited to 'fs') diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index 2bd836f..f1897fe 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -38,6 +38,13 @@ #define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1) +/** + * ext3_get_group_desc() -- load group descriptor from disk + * @sb: super block + * @block_group: given block group + * @bh: pointer to the buffer head to store the block + * group descriptor + */ struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb, unsigned int block_group, struct buffer_head ** bh) @@ -73,7 +80,11 @@ struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb, return desc + offset; } -/* +/** + * read_block_bitmap() + * @sb: super block + * @block_group: given block group + * * Read the bitmap for a given block_group, reading into the specified * slot in the superblock's bitmap cache. * @@ -103,13 +114,20 @@ error_out: * Operations include: * dump, find, add, remove, is_empty, find_next_reservable_window, etc. * - * We use sorted double linked list for the per-filesystem reservation - * window list. (like in vm_region). + * We use a red-black tree to represent per-filesystem reservation + * windows. * - * Initially, we keep those small operations in the abstract functions, - * so later if we need a better searching tree than double linked-list, - * we could easily switch to that without changing too much - * code. + */ + +/** + * __rsv_window_dump() -- Dump the filesystem block allocation reservation map + * @rb_root: root of per-filesystem reservation rb tree + * @verbose: verbose mode + * @fn: function which wishes to dump the reservation map + * + * If verbose is turned on, it will print the whole block reservation + * windows(start, end). Otherwise, it will only print out the "bad" windows, + * those windows that overlap with their immediate neighbors. */ #if 1 static void __rsv_window_dump(struct rb_root *root, int verbose, @@ -161,6 +179,22 @@ restart: #define rsv_window_dump(root, verbose) do {} while (0) #endif +/** + * goal_in_my_reservation() + * @rsv: inode's reservation window + * @grp_goal: given goal block relative to the allocation block group + * @group: the current allocation block group + * @sb: filesystem super block + * + * Test if the given goal block (group relative) is within the file's + * own block reservation window range. + * + * If the reservation window is outside the goal allocation group, return 0; + * grp_goal (given goal block) could be -1, which means no specific + * goal block. In this case, always return 1. + * If the goal block is within the reservation window, return 1; + * otherwise, return 0; + */ static int goal_in_my_reservation(struct ext3_reserve_window *rsv, ext3_grpblk_t grp_goal, unsigned int group, struct super_block * sb) @@ -179,7 +213,11 @@ goal_in_my_reservation(struct ext3_reserve_window *rsv, ext3_grpblk_t grp_goal, return 1; } -/* +/** + * search_reserve_window() + * @rb_root: root of reservation tree + * @goal: target allocation block + * * Find the reserved window which includes the goal, or the previous one * if the goal is not in any window. * Returns NULL if there are no windows or if all windows start after the goal. @@ -216,6 +254,13 @@ search_reserve_window(struct rb_root *root, ext3_fsblk_t goal) return rsv; } +/** + * ext3_rsv_window_add() -- Insert a window to the block reservation rb tree. + * @sb: super block + * @rsv: reservation window to add + * + * Must be called with rsv_lock hold. + */ void ext3_rsv_window_add(struct super_block *sb, struct ext3_reserve_window_node *rsv) { @@ -246,6 +291,15 @@ void ext3_rsv_window_add(struct super_block *sb, rb_insert_color(node, root); } +/** + * ext3_rsv_window_remove() -- unlink a window from the reservation rb tree + * @sb: super block + * @rsv: reservation window to remove + * + * Mark the block reservation window as not allocated, and unlink it + * from the filesystem reservation window rb tree. Must be called with + * rsv_lock hold. + */ static void rsv_window_remove(struct super_block *sb, struct ext3_reserve_window_node *rsv) { @@ -255,11 +309,39 @@ static void rsv_window_remove(struct super_block *sb, rb_erase(&rsv->rsv_node, &EXT3_SB(sb)->s_rsv_window_root); } +/* + * rsv_is_empty() -- Check if the reservation window is allocated. + * @rsv: given reservation window to check + * + * returns 1 if the end block is EXT3_RESERVE_WINDOW_NOT_ALLOCATED. + */ static inline int rsv_is_empty(struct ext3_reserve_window *rsv) { /* a valid reservation end block could not be 0 */ - return (rsv->_rsv_end == EXT3_RESERVE_WINDOW_NOT_ALLOCATED); + return rsv->_rsv_end == EXT3_RESERVE_WINDOW_NOT_ALLOCATED; } + +/** + * ext3_init_block_alloc_info() + * @inode: file inode structure + * + * Allocate and initialize the reservation window structure, and + * link the window to the ext3 inode structure at last + * + * The reservation window structure is only dynamically allocated + * and linked to ext3 inode the first time the open file + * needs a new block. So, before every ext3_new_block(s) call, for + * regular files, we should check whether the reservation window + * structure exists or not. In the latter case, this function is called. + * Fail to do so will result in block reservation being turned off for that + * open file. + * + * This function is called from ext3_get_blocks_handle(), also called + * when setting the reservation window size through ioctl before the file + * is open for write (needs block allocation). + * + * Needs truncate_mutex protection prior to call this function. + */ void ext3_init_block_alloc_info(struct inode *inode) { struct ext3_inode_info *ei = EXT3_I(inode); @@ -289,6 +371,19 @@ void ext3_init_block_alloc_info(struct inode *inode) ei->i_block_alloc_info = block_i; } +/** + * ext3_discard_reservation() + * @inode: inode + * + * Discard(free) block reservation window on last file close, or truncate + * or at last iput(). + * + * It is being called in three cases: + * ext3_release_file(): last writer close the file + * ext3_clear_inode(): last iput(), when nobody link to this file. + * ext3_truncate(): when the block indirect map is about to change. + * + */ void ext3_discard_reservation(struct inode *inode) { struct ext3_inode_info *ei = EXT3_I(inode); @@ -308,7 +403,14 @@ void ext3_discard_reservation(struct inode *inode) } } -/* Free given blocks, update quota and i_blocks field */ +/** + * ext3_free_blocks_sb() -- Free given blocks and update quota + * @handle: handle to this transaction + * @sb: super block + * @block: start physcial block to free + * @count: number of blocks to free + * @pdquot_freed_blocks: pointer to quota + */ void ext3_free_blocks_sb(handle_t *handle, struct super_block *sb, ext3_fsblk_t block, unsigned long count, unsigned long *pdquot_freed_blocks) @@ -492,7 +594,13 @@ error_return: return; } -/* Free given blocks, update quota and i_blocks field */ +/** + * ext3_free_blocks() -- Free given blocks and update quota + * @handle: handle for this transaction + * @inode: inode + * @block: start physical block to free + * @count: number of blocks to count + */ void ext3_free_blocks(handle_t *handle, struct inode *inode, ext3_fsblk_t block, unsigned long count) { @@ -510,7 +618,11 @@ void ext3_free_blocks(handle_t *handle, struct inode *inode, return; } -/* +/** + * ext3_test_allocatable() + * @nr: given allocation block group + * @bh: bufferhead contains the bitmap of the given block group + * * For ext3 allocations, we must not reuse any blocks which are * allocated in the bitmap buffer's "last committed data" copy. This * prevents deletes from freeing up the page for reuse until we have @@ -543,6 +655,16 @@ static int ext3_test_allocatable(ext3_grpblk_t nr, struct buffer_head *bh) return ret; } +/** + * bitmap_search_next_usable_block() + * @start: the starting block (group relative) of the search + * @bh: bufferhead contains the block group bitmap + * @maxblocks: the ending block (group relative) of the reservation + * + * The bitmap search --- search forward alternately through the actual + * bitmap on disk and the last-committed copy in journal, until we find a + * bit free in both bitmaps. + */ static ext3_grpblk_t bitmap_search_next_usable_block(ext3_grpblk_t start, struct buffer_head *bh, ext3_grpblk_t maxblocks) @@ -550,11 +672,6 @@ bitmap_search_next_usable_block(ext3_grpblk_t start, struct buffer_head *bh, ext3_grpblk_t next; struct journal_head *jh = bh2jh(bh); - /* - * The bitmap search --- search forward alternately through the actual - * bitmap and the last-committed copy until we find a bit free in - * both - */ while (start < maxblocks) { next = ext3_find_next_zero_bit(bh->b_data, maxblocks, start); if (next >= maxblocks) @@ -570,8 +687,14 @@ bitmap_search_next_usable_block(ext3_grpblk_t start, struct buffer_head *bh, return -1; } -/* - * Find an allocatable block in a bitmap. We honour both the bitmap and +/** + * find_next_usable_block() + * @start: the starting block (group relative) to find next + * allocatable block in bitmap. + * @bh: bufferhead contains the block group bitmap + * @maxblocks: the ending block (group relative) for the search + * + * Find an allocatable block in a bitmap. We honor both the bitmap and * its last-committed copy (if that exists), and perform the "most * appropriate allocation" algorithm of looking for a free block near * the initial goal; then for a free byte somewhere in the bitmap; then @@ -622,7 +745,11 @@ find_next_usable_block(ext3_grpblk_t start, struct buffer_head *bh, return here; } -/* +/** + * claim_block() + * @block: the free block (group relative) to allocate + * @bh: the bufferhead containts the block group bitmap + * * We think we can allocate this block in this bitmap. Try to set the bit. * If that succeeds then check that nobody has allocated and then freed the * block since we saw that is was not marked in b_committed_data. If it _was_ @@ -648,7 +775,26 @@ claim_block(spinlock_t *lock, ext3_grpblk_t block, struct buffer_head *bh) return ret; } -/* +/** + * ext3_try_to_allocate() + * @sb: superblock + * @handle: handle to this transaction + * @group: given allocation block group + * @bitmap_bh: bufferhead holds the block bitmap + * @grp_goal: given target block within the group + * @count: target number of blocks to allocate + * @my_rsv: reservation window + * + * Attempt to allocate blocks within a give range. Set the range of allocation + * first, then find the first free bit(s) from the bitmap (within the range), + * and at last, allocate the blocks by claiming the found free bit as allocated. + * + * To set the range of this allocation: + * if there is a reservation window, only try to allocate block(s) from the + * file's own reservation window; + * Otherwise, the allocation range starts from the give goal block, ends at + * the block group's last block. + * * If we failed to allocate the desired block then we may end up crossing to a * new bitmap. In that case we must release write access to the old one via * ext3_journal_release_buffer(), else we'll run out of credits. @@ -705,7 +851,8 @@ repeat: } start = grp_goal; - if (!claim_block(sb_bgl_lock(EXT3_SB(sb), group), grp_goal, bitmap_bh)) { + if (!claim_block(sb_bgl_lock(EXT3_SB(sb), group), + grp_goal, bitmap_bh)) { /* * The block was allocated by another thread, or it was * allocated and then freed by another thread @@ -720,7 +867,8 @@ repeat: grp_goal++; while (num < *count && grp_goal < end && ext3_test_allocatable(grp_goal, bitmap_bh) - && claim_block(sb_bgl_lock(EXT3_SB(sb), group), grp_goal, bitmap_bh)) { + && claim_block(sb_bgl_lock(EXT3_SB(sb), group), + grp_goal, bitmap_bh)) { num++; grp_goal++; } @@ -931,9 +1079,10 @@ static int alloc_new_reservation(struct ext3_reserve_window_node *my_rsv, if ((my_rsv->rsv_alloc_hit > (my_rsv->rsv_end - my_rsv->rsv_start + 1) / 2)) { /* - * if we previously allocation hit ration is greater than half - * we double the size of reservation window next time - * otherwise keep the same + * if the previously allocation hit ratio is + * greater than 1/2, then we double the size of + * the reservation window the next time, + * otherwise we keep the same size window */ size = size * 2; if (size > EXT3_MAX_RESERVE_BLOCKS) @@ -1012,6 +1161,23 @@ retry: goto retry; } +/** + * try_to_extend_reservation() + * @my_rsv: given reservation window + * @sb: super block + * @size: the delta to extend + * + * Attempt to expand the reservation window large enough to have + * required number of free blocks + * + * Since ext3_try_to_allocate() will always allocate blocks within + * the reservation window range, if the window size is too small, + * multiple blocks allocation has to stop at the end of the reservation + * window. To make this more efficient, given the total number of + * blocks needed and the current size of the window, we try to + * expand the reservation window size if necessary on a best-effort + * basis before ext3_new_blocks() tries to allocate blocks, + */ static void try_to_extend_reservation(struct ext3_reserve_window_node *my_rsv, struct super_block *sb, int size) { @@ -1037,7 +1203,17 @@ static void try_to_extend_reservation(struct ext3_reserve_window_node *my_rsv, spin_unlock(rsv_lock); } -/* +/** + * ext3_try_to_allocate_with_rsv() + * @sb: superblock + * @handle: handle to this transaction + * @group: given allocation block group + * @bitmap_bh: bufferhead holds the block bitmap + * @grp_goal: given target block within the group + * @count: target number of blocks to allocate + * @my_rsv: reservation window + * @errp: pointer to store the error code + * * This is the main function used to allocate a new block and its reservation * window. * @@ -1053,9 +1229,7 @@ static void try_to_extend_reservation(struct ext3_reserve_window_node *my_rsv, * reservation), and there are lots of free blocks, but they are all * being reserved. * - * We use a sorted double linked list for the per-filesystem reservation list. - * The insert, remove and find a free space(non-reserved) operations for the - * sorted double linked list should be fast. + * We use a red-black tree for the per-filesystem reservation list. * */ static ext3_grpblk_t @@ -1120,7 +1294,8 @@ ext3_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle, */ while (1) { if (rsv_is_empty(&my_rsv->rsv_window) || (ret < 0) || - !goal_in_my_reservation(&my_rsv->rsv_window, grp_goal, group, sb)) { + !goal_in_my_reservation(&my_rsv->rsv_window, + grp_goal, group, sb)) { if (my_rsv->rsv_goal_size < *count) my_rsv->rsv_goal_size = *count; ret = alloc_new_reservation(my_rsv, grp_goal, sb, @@ -1128,19 +1303,22 @@ ext3_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle, if (ret < 0) break; /* failed */ - if (!goal_in_my_reservation(&my_rsv->rsv_window, grp_goal, group, sb)) + if (!goal_in_my_reservation(&my_rsv->rsv_window, + grp_goal, group, sb)) grp_goal = -1; - } else if (grp_goal > 0 && (my_rsv->rsv_end-grp_goal+1) < *count) + } else if (grp_goal > 0 && + (my_rsv->rsv_end-grp_goal+1) < *count) try_to_extend_reservation(my_rsv, sb, *count-my_rsv->rsv_end + grp_goal - 1); - if ((my_rsv->rsv_start >= group_first_block + EXT3_BLOCKS_PER_GROUP(sb)) + if ((my_rsv->rsv_start >= group_first_block + + EXT3_BLOCKS_PER_GROUP(sb)) || (my_rsv->rsv_end < group_first_block)) { rsv_window_dump(&EXT3_SB(sb)->s_rsv_window_root, 1); BUG(); } - ret = ext3_try_to_allocate(sb, handle, group, bitmap_bh, grp_goal, - &num, &my_rsv->rsv_window); + ret = ext3_try_to_allocate(sb, handle, group, bitmap_bh, + grp_goal, &num, &my_rsv->rsv_window); if (ret >= 0) { my_rsv->rsv_alloc_hit += num; *count = num; @@ -1165,6 +1343,12 @@ out: return ret; } +/** + * ext3_has_free_blocks() + * @sbi: in-core super block structure. + * + * Check if filesystem has at least 1 free block available for allocation. + */ static int ext3_has_free_blocks(struct ext3_sb_info *sbi) { ext3_fsblk_t free_blocks, root_blocks; @@ -1179,11 +1363,17 @@ static int ext3_has_free_blocks(struct ext3_sb_info *sbi) return 1; } -/* +/** + * ext3_should_retry_alloc() + * @sb: super block + * @retries number of attemps has been made + * * ext3_should_retry_alloc() is called when ENOSPC is returned, and if * it is profitable to retry the operation, this function will wait * for the current or commiting transaction to complete, and then * return TRUE. + * + * if the total number of retries exceed three times, return FALSE. */ int ext3_should_retry_alloc(struct super_block *sb, int *retries) { @@ -1195,13 +1385,19 @@ int ext3_should_retry_alloc(struct super_block *sb, int *retries) return journal_force_commit_nested(EXT3_SB(sb)->s_journal); } -/* - * ext3_new_block uses a goal block to assist allocation. If the goal is - * free, or there is a free block within 32 blocks of the goal, that block - * is allocated. Otherwise a forward search is made for a free block; within - * each block group the search first looks for an entire free byte in the block - * bitmap, and then for any free bit if that fails. - * This function also updates quota and i_blocks field. +/** + * ext3_new_blocks() -- core block(s) allocation function + * @handle: handle to this transaction + * @inode: file inode + * @goal: given target block(filesystem wide) + * @count: target number of blocks to allocate + * @errp: error code + * + * ext3_new_blocks uses a goal block to assist allocation. It tries to + * allocate block(s) from the block group contains the goal block first. If that + * fails, it will try to allocate block(s) from other block groups without + * any specific goal block. + * */ ext3_fsblk_t ext3_new_blocks(handle_t *handle, struct inode *inode, ext3_fsblk_t goal, unsigned long *count, int *errp) @@ -1432,7 +1628,7 @@ allocated: spin_lock(sb_bgl_lock(sbi, group_no)); gdp->bg_free_blocks_count = - cpu_to_le16(le16_to_cpu(gdp->bg_free_blocks_count) - num); + cpu_to_le16(le16_to_cpu(gdp->bg_free_blocks_count)-num); spin_unlock(sb_bgl_lock(sbi, group_no)); percpu_counter_mod(&sbi->s_freeblocks_counter, -num); @@ -1475,6 +1671,12 @@ ext3_fsblk_t ext3_new_block(handle_t *handle, struct inode *inode, return ext3_new_blocks(handle, inode, goal, &count, errp); } +/** + * ext3_count_free_blocks() -- count filesystem free blocks + * @sb: superblock + * + * Adds up the number of free blocks from each block group. + */ ext3_fsblk_t ext3_count_free_blocks(struct super_block *sb) { ext3_fsblk_t desc_count; -- cgit v1.1 From 7543fc7b3abfee8c6cd6349ebd5e5fde02fac984 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Wed, 27 Sep 2006 01:49:33 -0700 Subject: [PATCH] ext3: wrong error behavior SWsoft Virtuozzo/OpenVZ Linux kernel team has discovered that ext3 error behavior was broken in linux kernels since 2.5.x versions by the following patch: 2002/10/31 02:15:26-05:00 tytso@snap.thunk.org Default mount options from superblock for ext2/3 filesystems http://linux.bkbits.net:8080/linux-2.6/gnupatch@3dc0d88eKbV9ivV4ptRNM8fBuA3JBQ In case ext3 file system is mounted with errors=continue (EXT3_ERRORS_CONTINUE) errors should be ignored when possible. However at present in case of any error kernel aborts journal and remounts filesystem to read-only. Such behavior was hit number of times and noted to differ from that of 2.4.x kernels. This patch fixes this: - do nothing in case of EXT3_ERRORS_CONTINUE, - set EXT3_MOUNT_ABORT and call journal_abort() in all other cases - panic() should be called after ext3_commit_super() to save sb marked as EXT3_ERROR_FS Signed-off-by: Vasily Averin Acked-by: Kirill Korotaev Cc: Theodore Ts'o Cc: "Stephen C. Tweedie" Cc: Mingming Cao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/super.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/ext3/super.c b/fs/ext3/super.c index bc7a768..4b526b4 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -159,20 +159,21 @@ static void ext3_handle_error(struct super_block *sb) if (sb->s_flags & MS_RDONLY) return; - if (test_opt (sb, ERRORS_RO)) { - printk (KERN_CRIT "Remounting filesystem read-only\n"); - sb->s_flags |= MS_RDONLY; - } else { + if (!test_opt (sb, ERRORS_CONT)) { journal_t *journal = EXT3_SB(sb)->s_journal; EXT3_SB(sb)->s_mount_opt |= EXT3_MOUNT_ABORT; if (journal) journal_abort(journal, -EIO); } + if (test_opt (sb, ERRORS_RO)) { + printk (KERN_CRIT "Remounting filesystem read-only\n"); + sb->s_flags |= MS_RDONLY; + } + ext3_commit_super(sb, es, 1); if (test_opt(sb, ERRORS_PANIC)) panic("EXT3-fs (device %s): panic forced after error\n", sb->s_id); - ext3_commit_super(sb, es, 1); } void ext3_error (struct super_block * sb, const char * function, -- cgit v1.1 From e9ad5620bfb901df8a7a2603c88689ededeecaf1 Mon Sep 17 00:00:00 2001 From: Dave Kleikamp Date: Wed, 27 Sep 2006 01:49:35 -0700 Subject: [PATCH] ext3: More whitespace cleanups More white space cleanups in preparation of cloning ext4 from ext3. Removing spaces that precede a tab. Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/acl.c | 2 +- fs/ext3/balloc.c | 32 ++++++++++++++++---------------- fs/ext3/dir.c | 2 +- fs/ext3/hash.c | 2 +- fs/ext3/inode.c | 8 ++++---- fs/ext3/namei.c | 18 +++++++++--------- fs/ext3/super.c | 6 +++--- fs/jbd/checkpoint.c | 2 +- fs/jbd/journal.c | 2 +- fs/jbd/recovery.c | 2 +- fs/jbd/transaction.c | 6 +++--- 11 files changed, 41 insertions(+), 41 deletions(-) (limited to 'fs') diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index 0d21d55..92bf782 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -258,7 +258,7 @@ ext3_set_acl(handle_t *handle, struct inode *inode, int type, default: return -EINVAL; } - if (acl) { + if (acl) { value = ext3_acl_to_disk(acl, &size); if (IS_ERR(value)) return (int)PTR_ERR(value); diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index f1897fe..c19be8f 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -40,7 +40,7 @@ /** * ext3_get_group_desc() -- load group descriptor from disk - * @sb: super block + * @sb: super block * @block_group: given block group * @bh: pointer to the buffer head to store the block * group descriptor @@ -355,7 +355,7 @@ void ext3_init_block_alloc_info(struct inode *inode) rsv->rsv_start = EXT3_RESERVE_WINDOW_NOT_ALLOCATED; rsv->rsv_end = EXT3_RESERVE_WINDOW_NOT_ALLOCATED; - /* + /* * if filesystem is mounted with NORESERVATION, the goal * reservation window size is set to zero to indicate * block reservation is off @@ -681,7 +681,7 @@ bitmap_search_next_usable_block(ext3_grpblk_t start, struct buffer_head *bh, jbd_lock_bh_state(bh); if (jh->b_committed_data) start = ext3_find_next_zero_bit(jh->b_committed_data, - maxblocks, next); + maxblocks, next); jbd_unlock_bh_state(bh); } return -1; @@ -790,10 +790,10 @@ claim_block(spinlock_t *lock, ext3_grpblk_t block, struct buffer_head *bh) * and at last, allocate the blocks by claiming the found free bit as allocated. * * To set the range of this allocation: - * if there is a reservation window, only try to allocate block(s) from the + * if there is a reservation window, only try to allocate block(s) from the * file's own reservation window; * Otherwise, the allocation range starts from the give goal block, ends at - * the block group's last block. + * the block group's last block. * * If we failed to allocate the desired block then we may end up crossing to a * new bitmap. In that case we must release write access to the old one via @@ -880,12 +880,12 @@ fail_access: } /** - * find_next_reservable_window(): + * find_next_reservable_window(): * find a reservable space within the given range. * It does not allocate the reservation window for now: * alloc_new_reservation() will do the work later. * - * @search_head: the head of the searching list; + * @search_head: the head of the searching list; * This is not necessarily the list head of the whole filesystem * * We have both head and start_block to assist the search @@ -893,12 +893,12 @@ fail_access: * but we will shift to the place where start_block is, * then start from there, when looking for a reservable space. * - * @size: the target new reservation window size + * @size: the target new reservation window size * - * @group_first_block: the first block we consider to start + * @group_first_block: the first block we consider to start * the real search from * - * @last_block: + * @last_block: * the maximum block number that our goal reservable space * could start from. This is normally the last block in this * group. The search will end when we found the start of next @@ -906,10 +906,10 @@ fail_access: * This could handle the cross boundary reservation window * request. * - * basically we search from the given range, rather than the whole - * reservation double linked list, (start_block, last_block) - * to find a free region that is of my size and has not - * been reserved. + * basically we search from the given range, rather than the whole + * reservation double linked list, (start_block, last_block) + * to find a free region that is of my size and has not + * been reserved. * */ static int find_next_reservable_window( @@ -962,7 +962,7 @@ static int find_next_reservable_window( /* * Found a reserveable space big enough. We could * have a reservation across the group boundary here - */ + */ break; } } @@ -998,7 +998,7 @@ static int find_next_reservable_window( } /** - * alloc_new_reservation()--allocate a new reservation window + * alloc_new_reservation()--allocate a new reservation window * * To make a new reservation, we search part of the filesystem * reservation list (the list that inside the group). We try to diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c index 6f9e5a5..4d97f43 100644 --- a/fs/ext3/dir.c +++ b/fs/ext3/dir.c @@ -67,7 +67,7 @@ int ext3_check_dir_entry (const char * function, struct inode * dir, unsigned long offset) { const char * error_msg = NULL; - const int rlen = le16_to_cpu(de->rec_len); + const int rlen = le16_to_cpu(de->rec_len); if (rlen < EXT3_DIR_REC_LEN(1)) error_msg = "rec_len is smaller than minimal"; diff --git a/fs/ext3/hash.c b/fs/ext3/hash.c index 7fa637c..deeb27b 100644 --- a/fs/ext3/hash.c +++ b/fs/ext3/hash.c @@ -95,7 +95,7 @@ int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo) __u32 minor_hash = 0; const char *p; int i; - __u32 in[8], buf[4]; + __u32 in[8], buf[4]; /* Initialize the default seed for the hash checksum functions */ buf[0] = 0x67452301; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 56665fa..c9fc15f 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -13,11 +13,11 @@ * Copyright (C) 1991, 1992 Linus Torvalds * * Goal-directed block allocation by Stephen Tweedie - * (sct@redhat.com), 1993, 1998 + * (sct@redhat.com), 1993, 1998 * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 * 64-bit file support on 64-bit platforms by Jakub Jelinek - * (jj@sunsite.ms.mff.cuni.cz) + * (jj@sunsite.ms.mff.cuni.cz) * * Assorted race fixes, rewrite of ext3_get_block() by Al Viro, 2000 */ @@ -470,7 +470,7 @@ static ext3_fsblk_t ext3_find_goal(struct inode *inode, long block, * ext3_blks_to_allocate: Look up the block map and count the number * of direct blocks need to be allocated for the given branch. * - * @branch: chain of indirect blocks + * @branch: chain of indirect blocks * @k: number of blocks need for indirect blocks * @blks: number of data blocks to be mapped. * @blocks_to_boundary: the offset in the indirect block @@ -1098,7 +1098,7 @@ static int walk_page_buffers( handle_t *handle, for ( bh = head, block_start = 0; ret == 0 && (bh != head || !block_start); - block_start = block_end, bh = next) + block_start = block_end, bh = next) { next = bh->b_this_page; block_end = block_start + blocksize; diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 70dc520..85d132c 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -15,13 +15,13 @@ * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 * Directory entry file type support and forward compatibility hooks - * for B-tree directories by Theodore Ts'o (tytso@mit.edu), 1998 + * for B-tree directories by Theodore Ts'o (tytso@mit.edu), 1998 * Hash Tree Directory indexing (c) - * Daniel Phillips, 2001 + * Daniel Phillips, 2001 * Hash Tree Directory indexing porting - * Christopher Li, 2002 + * Christopher Li, 2002 * Hash Tree Directory indexing cleanup - * Theodore Ts'o, 2002 + * Theodore Ts'o, 2002 */ #include @@ -278,7 +278,7 @@ static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext3_dir_ent ((char *) de - base)); } space += EXT3_DIR_REC_LEN(de->name_len); - names++; + names++; } de = (struct ext3_dir_entry_2 *) ((char *) de + le16_to_cpu(de->rec_len)); } @@ -1688,7 +1688,7 @@ static int ext3_mknod (struct inode * dir, struct dentry *dentry, retry: handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT3_INDEX_EXTRA_TRANS_BLOCKS + 3 + + EXT3_INDEX_EXTRA_TRANS_BLOCKS + 3 + 2*EXT3_QUOTA_INIT_BLOCKS(dir->i_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); @@ -1816,7 +1816,7 @@ static int empty_dir (struct inode * inode) !le32_to_cpu(de1->inode) || strcmp (".", de->name) || strcmp ("..", de1->name)) { - ext3_warning (inode->i_sb, "empty_dir", + ext3_warning (inode->i_sb, "empty_dir", "bad directory (dir #%lu) - no `.' or `..'", inode->i_ino); brelse (bh); @@ -2129,7 +2129,7 @@ static int ext3_symlink (struct inode * dir, retry: handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT3_INDEX_EXTRA_TRANS_BLOCKS + 5 + + EXT3_INDEX_EXTRA_TRANS_BLOCKS + 5 + 2*EXT3_QUOTA_INIT_BLOCKS(dir->i_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); @@ -2227,7 +2227,7 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry, DQUOT_INIT(new_dentry->d_inode); handle = ext3_journal_start(old_dir, 2 * EXT3_DATA_TRANS_BLOCKS(old_dir->i_sb) + - EXT3_INDEX_EXTRA_TRANS_BLOCKS + 2); + EXT3_INDEX_EXTRA_TRANS_BLOCKS + 2); if (IS_ERR(handle)) return PTR_ERR(handle); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 4b526b4..0544325 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -734,8 +734,8 @@ static match_table_t tokens = { static ext3_fsblk_t get_sb_block(void **data) { - ext3_fsblk_t sb_block; - char *options = (char *) *data; + ext3_fsblk_t sb_block; + char *options = (char *) *data; if (!options || strncmp(options, "sb=", 3) != 0) return 1; /* Default location */ @@ -2740,7 +2740,7 @@ static int __init init_ext3_fs(void) out: destroy_inodecache(); out1: - exit_ext3_xattr(); + exit_ext3_xattr(); return err; } diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c index 961ada2..0208cc7 100644 --- a/fs/jbd/checkpoint.c +++ b/fs/jbd/checkpoint.c @@ -480,7 +480,7 @@ static int journal_clean_one_cp_list(struct journal_head *jh, int *released) if (!jh) return 0; - last_jh = jh->b_cpprev; + last_jh = jh->b_cpprev; do { jh = next_jh; next_jh = jh->b_cpnext; diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 88d970e..b571209 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -181,7 +181,7 @@ loop: transaction->t_expires)) should_sleep = 0; if (journal->j_flags & JFS_UNMOUNT) - should_sleep = 0; + should_sleep = 0; if (should_sleep) { spin_unlock(&journal->j_state_lock); schedule(); diff --git a/fs/jbd/recovery.c b/fs/jbd/recovery.c index 73bb648..445eed6 100644 --- a/fs/jbd/recovery.c +++ b/fs/jbd/recovery.c @@ -314,7 +314,7 @@ static int do_one_pass(journal_t *journal, unsigned long next_log_block; int err, success = 0; journal_superblock_t * sb; - journal_header_t * tmp; + journal_header_t * tmp; struct buffer_head * bh; unsigned int sequence; int blocktype; diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index bf7fd71..e1b3c8a 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -580,7 +580,7 @@ repeat: */ JBUFFER_TRACE(jh, "Unexpected dirty buffer"); jbd_unexpected_dirty_buffer(jh); - } + } unlock_buffer(bh); @@ -1373,7 +1373,7 @@ int journal_stop(handle_t *handle) if (handle->h_sync || transaction->t_outstanding_credits > journal->j_max_transaction_buffers || - time_after_eq(jiffies, transaction->t_expires)) { + time_after_eq(jiffies, transaction->t_expires)) { /* Do this even for aborted journals: an abort still * completes the commit thread, it just doesn't write * anything to disk. */ @@ -1908,7 +1908,7 @@ void journal_invalidatepage(journal_t *journal, next = bh->b_this_page; if (offset <= curr_off) { - /* This block is wholly outside the truncation point */ + /* This block is wholly outside the truncation point */ lock_buffer(bh); may_free &= journal_unmap_buffer(journal, bh); unlock_buffer(bh); -- cgit v1.1 From a4e4de36dc446b2193bdc8ebb96a96e44b69dd94 Mon Sep 17 00:00:00 2001 From: Dave Kleikamp Date: Wed, 27 Sep 2006 01:49:36 -0700 Subject: [PATCH] ext3: Fix sparse warnings Fixing up some endian-ness warnings in preparation to clone ext4 from ext3. Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/resize.c | 21 +++++++++++---------- fs/ext3/super.c | 4 +--- fs/jbd/journal.c | 2 +- 3 files changed, 13 insertions(+), 14 deletions(-) (limited to 'fs') diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c index 5e1337f..e186f7f 100644 --- a/fs/ext3/resize.c +++ b/fs/ext3/resize.c @@ -336,7 +336,7 @@ static int verify_reserved_gdb(struct super_block *sb, unsigned five = 5; unsigned seven = 7; unsigned grp; - __u32 *p = (__u32 *)primary->b_data; + __le32 *p = (__le32 *)primary->b_data; int gdbackups = 0; while ((grp = ext3_list_backups(sb, &three, &five, &seven)) < end) { @@ -380,7 +380,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, struct buffer_head *dind; int gdbackups; struct ext3_iloc iloc; - __u32 *data; + __le32 *data; int err; if (test_opt(sb, DEBUG)) @@ -417,7 +417,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, goto exit_bh; } - data = (__u32 *)dind->b_data; + data = (__le32 *)dind->b_data; if (le32_to_cpu(data[gdb_num % EXT3_ADDR_PER_BLOCK(sb)]) != gdblock) { ext3_warning(sb, __FUNCTION__, "new group %u GDT block "E3FSBLK" not reserved", @@ -519,7 +519,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, struct buffer_head *dind; struct ext3_iloc iloc; ext3_fsblk_t blk; - __u32 *data, *end; + __le32 *data, *end; int gdbackups = 0; int res, i; int err; @@ -536,8 +536,8 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, } blk = EXT3_SB(sb)->s_sbh->b_blocknr + 1 + EXT3_SB(sb)->s_gdb_count; - data = (__u32 *)dind->b_data + EXT3_SB(sb)->s_gdb_count; - end = (__u32 *)dind->b_data + EXT3_ADDR_PER_BLOCK(sb); + data = (__le32 *)dind->b_data + EXT3_SB(sb)->s_gdb_count; + end = (__le32 *)dind->b_data + EXT3_ADDR_PER_BLOCK(sb); /* Get each reserved primary GDT block and verify it holds backups */ for (res = 0; res < reserved_gdb; res++, blk++) { @@ -545,7 +545,8 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, ext3_warning(sb, __FUNCTION__, "reserved block "E3FSBLK " not at offset %ld", - blk, (long)(data - (__u32 *)dind->b_data)); + blk, + (long)(data - (__le32 *)dind->b_data)); err = -EINVAL; goto exit_bh; } @@ -560,7 +561,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, goto exit_bh; } if (++data >= end) - data = (__u32 *)dind->b_data; + data = (__le32 *)dind->b_data; } for (i = 0; i < reserved_gdb; i++) { @@ -584,7 +585,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, blk = input->group * EXT3_BLOCKS_PER_GROUP(sb); for (i = 0; i < reserved_gdb; i++) { int err2; - data = (__u32 *)primary[i]->b_data; + data = (__le32 *)primary[i]->b_data; /* printk("reserving backup %lu[%u] = %lu\n", primary[i]->b_blocknr, gdbackups, blk + primary[i]->b_blocknr); */ @@ -689,7 +690,7 @@ exit_err: "can't update backup for group %d (err %d), " "forcing fsck on next reboot", group, err); sbi->s_mount_state &= ~EXT3_VALID_FS; - sbi->s_es->s_state &= ~cpu_to_le16(EXT3_VALID_FS); + sbi->s_es->s_state &= cpu_to_le16(~EXT3_VALID_FS); mark_buffer_dirty(sbi->s_sbh); } } diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 0544325..1098501 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -2348,10 +2348,8 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data) */ ext3_clear_journal_err(sb, es); sbi->s_mount_state = le16_to_cpu(es->s_state); - if ((ret = ext3_group_extend(sb, es, n_blocks_count))) { - err = ret; + if ((err = ext3_group_extend(sb, es, n_blocks_count))) goto restore_opts; - } if (!ext3_setup_super (sb, es, 0)) sb->s_flags &= ~MS_RDONLY; } diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index b571209..2fc66c3 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -1094,7 +1094,7 @@ int journal_load(journal_t *journal) /* * Create a slab for this blocksize */ - err = journal_create_jbd_slab(cpu_to_be32(sb->s_blocksize)); + err = journal_create_jbd_slab(be32_to_cpu(sb->s_blocksize)); if (err) return err; -- cgit v1.1 From 32c2d2bc4bed61323f14f2a7d69ccbd567253d8a Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Wed, 27 Sep 2006 01:49:36 -0700 Subject: [PATCH] more ext3 16T overflow fixes Some of the changes in balloc.c are just cosmetic, as Andreas pointed out - if they overflow they'll then underflow and things are fine. 5th hunk actually fixes an overflow problem. Also check for potential overflows in inode & block counts when resizing. Signed-off-by: Eric Sandeen Cc: Mingming Cao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/balloc.c | 12 ++++++------ fs/ext3/resize.c | 17 +++++++++++++++++ 2 files changed, 23 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index c19be8f..b41a7d7 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -202,7 +202,7 @@ goal_in_my_reservation(struct ext3_reserve_window *rsv, ext3_grpblk_t grp_goal, ext3_fsblk_t group_first_block, group_last_block; group_first_block = ext3_group_first_block_no(sb, group); - group_last_block = group_first_block + EXT3_BLOCKS_PER_GROUP(sb) - 1; + group_last_block = group_first_block + (EXT3_BLOCKS_PER_GROUP(sb) - 1); if ((rsv->_rsv_start > group_last_block) || (rsv->_rsv_end < group_first_block)) @@ -1047,7 +1047,7 @@ static int alloc_new_reservation(struct ext3_reserve_window_node *my_rsv, spinlock_t *rsv_lock = &EXT3_SB(sb)->s_rsv_window_lock; group_first_block = ext3_group_first_block_no(sb, group); - group_end_block = group_first_block + EXT3_BLOCKS_PER_GROUP(sb) - 1; + group_end_block = group_first_block + (EXT3_BLOCKS_PER_GROUP(sb) - 1); if (grp_goal < 0) start_block = group_first_block; @@ -1239,7 +1239,7 @@ ext3_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle, struct ext3_reserve_window_node * my_rsv, unsigned long *count, int *errp) { - ext3_fsblk_t group_first_block; + ext3_fsblk_t group_first_block, group_last_block; ext3_grpblk_t ret = 0; int fatal; unsigned long num = *count; @@ -1276,6 +1276,7 @@ ext3_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle, * first block is the block number of the first block in this group */ group_first_block = ext3_group_first_block_no(sb, group); + group_last_block = group_first_block + (EXT3_BLOCKS_PER_GROUP(sb) - 1); /* * Basically we will allocate a new block from inode's reservation @@ -1311,9 +1312,8 @@ ext3_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle, try_to_extend_reservation(my_rsv, sb, *count-my_rsv->rsv_end + grp_goal - 1); - if ((my_rsv->rsv_start >= group_first_block + - EXT3_BLOCKS_PER_GROUP(sb)) - || (my_rsv->rsv_end < group_first_block)) { + if ((my_rsv->rsv_start > group_last_block) || + (my_rsv->rsv_end < group_first_block)) { rsv_window_dump(&EXT3_SB(sb)->s_rsv_window_root, 1); BUG(); } diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c index e186f7f..9e318a5 100644 --- a/fs/ext3/resize.c +++ b/fs/ext3/resize.c @@ -731,6 +731,18 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input) return -EPERM; } + if (le32_to_cpu(es->s_blocks_count) + input->blocks_count < + le32_to_cpu(es->s_blocks_count)) { + ext3_warning(sb, __FUNCTION__, "blocks_count overflow\n"); + return -EINVAL; + } + + if (le32_to_cpu(es->s_inodes_count) + EXT3_INODES_PER_GROUP(sb) < + le32_to_cpu(es->s_inodes_count)) { + ext3_warning(sb, __FUNCTION__, "inodes_count overflow\n"); + return -EINVAL; + } + if (reserved_gdb || gdb_off == 0) { if (!EXT3_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_RESIZE_INODE)){ @@ -959,6 +971,11 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es, add = EXT3_BLOCKS_PER_GROUP(sb) - last; + if (o_blocks_count + add < o_blocks_count) { + ext3_warning(sb, __FUNCTION__, "blocks_count overflow"); + return -EINVAL; + } + if (o_blocks_count + add > n_blocks_count) add = n_blocks_count - o_blocks_count; -- cgit v1.1 From f8314dc60ccba7e41f425048c4160dc7f63377d5 Mon Sep 17 00:00:00 2001 From: Panagiotis Issaris Date: Wed, 27 Sep 2006 01:49:37 -0700 Subject: [PATCH] fs: Conversions from kmalloc+memset to k(z|c)alloc Conversions from kmalloc+memset to kzalloc. Signed-off-by: Panagiotis Issaris Jffs2-bit-acked-by: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/adfs/super.c | 3 +-- fs/affs/super.c | 3 +-- fs/afs/vlocation.c | 3 +-- fs/afs/volume.c | 3 +-- fs/autofs/inode.c | 3 +-- fs/bfs/inode.c | 6 ++---- fs/configfs/file.c | 3 +-- fs/configfs/inode.c | 3 +-- fs/cramfs/inode.c | 3 +-- fs/efs/super.c | 3 +-- fs/ext2/super.c | 3 +-- fs/ext2/xattr.c | 3 +-- fs/ext3/dir.c | 3 +-- fs/ext3/super.c | 3 +-- fs/fat/inode.c | 3 +-- fs/hfs/bnode.c | 3 +-- fs/hfs/btree.c | 3 +-- fs/hfs/super.c | 3 +-- fs/hfsplus/bnode.c | 3 +-- fs/hfsplus/btree.c | 3 +-- fs/hpfs/super.c | 3 +-- fs/isofs/inode.c | 3 +-- fs/jffs2/super.c | 3 +-- fs/lockd/host.c | 4 ++-- fs/lockd/svcsubs.c | 3 +-- fs/minix/inode.c | 6 ++---- fs/ncpfs/inode.c | 3 +-- fs/nfsd/nfs4idmap.c | 3 +-- fs/nfsd/nfs4state.c | 3 +-- fs/partitions/efi.c | 9 +++------ fs/proc/kcore.c | 6 ++---- fs/qnx4/inode.c | 3 +-- fs/sysv/super.c | 6 ++---- fs/udf/ialloc.c | 6 ++---- fs/ufs/super.c | 3 +-- 35 files changed, 43 insertions(+), 84 deletions(-) (limited to 'fs') diff --git a/fs/adfs/super.c b/fs/adfs/super.c index 8201101..959dbf1 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -339,11 +339,10 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags |= MS_NODIRATIME; - asb = kmalloc(sizeof(*asb), GFP_KERNEL); + asb = kzalloc(sizeof(*asb), GFP_KERNEL); if (!asb) return -ENOMEM; sb->s_fs_info = asb; - memset(asb, 0, sizeof(*asb)); /* set default options */ asb->s_uid = 0; diff --git a/fs/affs/super.c b/fs/affs/super.c index 1735201..b35f514 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -280,11 +280,10 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent) sb->s_op = &affs_sops; sb->s_flags |= MS_NODIRATIME; - sbi = kmalloc(sizeof(struct affs_sb_info), GFP_KERNEL); + sbi = kzalloc(sizeof(struct affs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; sb->s_fs_info = sbi; - memset(sbi, 0, sizeof(*sbi)); init_MUTEX(&sbi->s_bmlock); if (!parse_options(data,&uid,&gid,&i,&reserved,&root_block, diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c index 331f730..782ee7c 100644 --- a/fs/afs/vlocation.c +++ b/fs/afs/vlocation.c @@ -281,11 +281,10 @@ int afs_vlocation_lookup(struct afs_cell *cell, spin_unlock(&cell->vl_gylock); /* not in the cell's in-memory lists - create a new record */ - vlocation = kmalloc(sizeof(struct afs_vlocation), GFP_KERNEL); + vlocation = kzalloc(sizeof(struct afs_vlocation), GFP_KERNEL); if (!vlocation) return -ENOMEM; - memset(vlocation, 0, sizeof(struct afs_vlocation)); atomic_set(&vlocation->usage, 1); INIT_LIST_HEAD(&vlocation->link); rwlock_init(&vlocation->lock); diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 0ff4b86..768c6db 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -186,11 +186,10 @@ int afs_volume_lookup(const char *name, struct afs_cell *cell, int rwpath, _debug("creating new volume record"); ret = -ENOMEM; - volume = kmalloc(sizeof(struct afs_volume), GFP_KERNEL); + volume = kzalloc(sizeof(struct afs_volume), GFP_KERNEL); if (!volume) goto error_up; - memset(volume, 0, sizeof(struct afs_volume)); atomic_set(&volume->usage, 1); volume->type = type; volume->type_force = force; diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index af2efbb..c81d6b8 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -129,10 +129,9 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) struct autofs_sb_info *sbi; int minproto, maxproto; - sbi = kmalloc(sizeof(*sbi), GFP_KERNEL); + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if ( !sbi ) goto fail_unlock; - memset(sbi, 0, sizeof(*sbi)); DPRINTK(("autofs: starting up, sbi = %p\n",sbi)); s->s_fs_info = sbi; diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index cf74f3d..3e4d6c7 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -311,11 +311,10 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) unsigned i, imap_len; struct bfs_sb_info * info; - info = kmalloc(sizeof(*info), GFP_KERNEL); + info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; s->s_fs_info = info; - memset(info, 0, sizeof(*info)); sb_set_blocksize(s, BFS_BSIZE); @@ -338,10 +337,9 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) + BFS_ROOT_INO - 1; imap_len = info->si_lasti/8 + 1; - info->si_imap = kmalloc(imap_len, GFP_KERNEL); + info->si_imap = kzalloc(imap_len, GFP_KERNEL); if (!info->si_imap) goto out; - memset(info->si_imap, 0, imap_len); for (i=0; isi_imap); diff --git a/fs/configfs/file.c b/fs/configfs/file.c index f499803..85105e5 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -274,9 +274,8 @@ static int check_perm(struct inode * inode, struct file * file) /* No error? Great, allocate a buffer for the file, and store it * it in file->private_data for easy access. */ - buffer = kmalloc(sizeof(struct configfs_buffer),GFP_KERNEL); + buffer = kzalloc(sizeof(struct configfs_buffer),GFP_KERNEL); if (buffer) { - memset(buffer,0,sizeof(struct configfs_buffer)); init_MUTEX(&buffer->sem); buffer->needs_read_fill = 1; buffer->ops = ops; diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index e14488c..5047e6a 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -76,11 +76,10 @@ int configfs_setattr(struct dentry * dentry, struct iattr * iattr) if (!sd_iattr) { /* setting attributes for the first time, allocate now */ - sd_iattr = kmalloc(sizeof(struct iattr), GFP_KERNEL); + sd_iattr = kzalloc(sizeof(struct iattr), GFP_KERNEL); if (!sd_iattr) return -ENOMEM; /* assign default attributes */ - memset(sd_iattr, 0, sizeof(struct iattr)); sd_iattr->ia_mode = sd->s_mode; sd_iattr->ia_uid = 0; sd_iattr->ia_gid = 0; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 223c043..d09b677 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -242,11 +242,10 @@ static int cramfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags |= MS_RDONLY; - sbi = kmalloc(sizeof(struct cramfs_sb_info), GFP_KERNEL); + sbi = kzalloc(sizeof(struct cramfs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; sb->s_fs_info = sbi; - memset(sbi, 0, sizeof(struct cramfs_sb_info)); /* Invalidate the read buffers on mount: think disk change.. */ mutex_lock(&read_mutex); diff --git a/fs/efs/super.c b/fs/efs/super.c index 8ac2462..7089269 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -248,11 +248,10 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) struct buffer_head *bh; struct inode *root; - sb = kmalloc(sizeof(struct efs_sb_info), GFP_KERNEL); + sb = kzalloc(sizeof(struct efs_sb_info), GFP_KERNEL); if (!sb) return -ENOMEM; s->s_fs_info = sb; - memset(sb, 0, sizeof(struct efs_sb_info)); s->s_magic = EFS_SUPER_MAGIC; if (!sb_set_blocksize(s, EFS_BLOCKSIZE)) { diff --git a/fs/ext2/super.c b/fs/ext2/super.c index d978d3f..69435fb 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -655,11 +655,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) int i, j; __le32 features; - sbi = kmalloc(sizeof(*sbi), GFP_KERNEL); + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; sb->s_fs_info = sbi; - memset(sbi, 0, sizeof(*sbi)); /* * See what the current blocksize for the device is, and diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 86ae8e9..af52a7f 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -521,11 +521,10 @@ bad_block: ext2_error(sb, "ext2_xattr_set", } } else { /* Allocate a buffer where we construct the new block. */ - header = kmalloc(sb->s_blocksize, GFP_KERNEL); + header = kzalloc(sb->s_blocksize, GFP_KERNEL); error = -ENOMEM; if (header == NULL) goto cleanup; - memset(header, 0, sb->s_blocksize); end = (char *)header + sb->s_blocksize; header->h_magic = cpu_to_le32(EXT2_XATTR_MAGIC); header->h_blocks = header->h_refcount = cpu_to_le32(1); diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c index 4d97f43..429acbb 100644 --- a/fs/ext3/dir.c +++ b/fs/ext3/dir.c @@ -343,10 +343,9 @@ int ext3_htree_store_dirent(struct file *dir_file, __u32 hash, /* Create and allocate the fname structure */ len = sizeof(struct fname) + dirent->name_len + 1; - new_fn = kmalloc(len, GFP_KERNEL); + new_fn = kzalloc(len, GFP_KERNEL); if (!new_fn) return -ENOMEM; - memset(new_fn, 0, len); new_fn->hash = hash; new_fn->minor_hash = minor_hash; new_fn->inode = le32_to_cpu(dirent->inode); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 1098501..09b4b31 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1407,11 +1407,10 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) int needs_recovery; __le32 features; - sbi = kmalloc(sizeof(*sbi), GFP_KERNEL); + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; sb->s_fs_info = sbi; - memset(sbi, 0, sizeof(*sbi)); sbi->s_mount_opt = 0; sbi->s_resuid = EXT3_DEF_RESUID; sbi->s_resgid = EXT3_DEF_RESGID; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 31b7174..bc4da3a 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1168,11 +1168,10 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, long error; char buf[50]; - sbi = kmalloc(sizeof(struct msdos_sb_info), GFP_KERNEL); + sbi = kzalloc(sizeof(struct msdos_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; sb->s_fs_info = sbi; - memset(sbi, 0, sizeof(struct msdos_sb_info)); sb->s_flags |= MS_NODIRATIME; sb->s_magic = MSDOS_SUPER_MAGIC; diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index 13231dd..0d20006 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -249,10 +249,9 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) sb = tree->inode->i_sb; size = sizeof(struct hfs_bnode) + tree->pages_per_bnode * sizeof(struct page *); - node = kmalloc(size, GFP_KERNEL); + node = kzalloc(size, GFP_KERNEL); if (!node) return NULL; - memset(node, 0, size); node->tree = tree; node->this = cnid; set_bit(HFS_BNODE_NEW, &node->flags); diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 4003579..5fd0ed7 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -21,10 +21,9 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke struct page *page; unsigned int size; - tree = kmalloc(sizeof(*tree), GFP_KERNEL); + tree = kzalloc(sizeof(*tree), GFP_KERNEL); if (!tree) return NULL; - memset(tree, 0, sizeof(*tree)); init_MUTEX(&tree->tree_lock); spin_lock_init(&tree->hash_lock); diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 34937ee..05dffff 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -356,11 +356,10 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) struct inode *root_inode; int res; - sbi = kmalloc(sizeof(struct hfs_sb_info), GFP_KERNEL); + sbi = kzalloc(sizeof(struct hfs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; sb->s_fs_info = sbi; - memset(sbi, 0, sizeof(struct hfs_sb_info)); INIT_HLIST_HEAD(&sbi->rsrc_inodes); res = -EINVAL; diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c index 77bf434..29da657 100644 --- a/fs/hfsplus/bnode.c +++ b/fs/hfsplus/bnode.c @@ -409,10 +409,9 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) sb = tree->inode->i_sb; size = sizeof(struct hfs_bnode) + tree->pages_per_bnode * sizeof(struct page *); - node = kmalloc(size, GFP_KERNEL); + node = kzalloc(size, GFP_KERNEL); if (!node) return NULL; - memset(node, 0, size); node->tree = tree; node->this = cnid; set_bit(HFS_BNODE_NEW, &node->flags); diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index cfc852f..a9b9e87 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -24,10 +24,9 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) struct page *page; unsigned int size; - tree = kmalloc(sizeof(*tree), GFP_KERNEL); + tree = kzalloc(sizeof(*tree), GFP_KERNEL); if (!tree) return NULL; - memset(tree, 0, sizeof(*tree)); init_MUTEX(&tree->tree_lock); spin_lock_init(&tree->hash_lock); diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 8fe51c3..b76d608 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -462,11 +462,10 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) int o; - sbi = kmalloc(sizeof(*sbi), GFP_KERNEL); + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; s->s_fs_info = sbi; - memset(sbi, 0, sizeof(*sbi)); sbi->sb_bmp_dir = NULL; sbi->sb_cp_table = NULL; diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 1439136..ab15e90 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -557,11 +557,10 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) struct iso9660_options opt; struct isofs_sb_info * sbi; - sbi = kmalloc(sizeof(*sbi), GFP_KERNEL); + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; s->s_fs_info = sbi; - memset(sbi, 0, sizeof(*sbi)); if (!parse_options((char *)data, &opt)) goto out_freesbi; diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 68e3953..6de3745 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -119,10 +119,9 @@ static int jffs2_get_sb_mtd(struct file_system_type *fs_type, struct jffs2_sb_info *c; int ret; - c = kmalloc(sizeof(*c), GFP_KERNEL); + c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) return -ENOMEM; - memset(c, 0, sizeof(*c)); c->mtd = mtd; sb = sget(fs_type, jffs2_sb_compare, jffs2_sb_set, c); diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 703fb03..a0d0b58 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -99,9 +99,9 @@ nlm_lookup_host(int server, struct sockaddr_in *sin, /* Ooops, no host found, create it */ dprintk("lockd: creating host entry\n"); - if (!(host = (struct nlm_host *) kmalloc(sizeof(*host), GFP_KERNEL))) + host = kzalloc(sizeof(*host), GFP_KERNEL); + if (!host) goto nohost; - memset(host, 0, sizeof(*host)); addr = sin->sin_addr.s_addr; sprintf(host->h_name, "%u.%u.%u.%u", NIPQUAD(addr)); diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 01b4db9e..a92dd98f 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -100,11 +100,10 @@ nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result, nlm_debug_print_fh("creating file for", f); nfserr = nlm_lck_denied_nolocks; - file = (struct nlm_file *) kmalloc(sizeof(*file), GFP_KERNEL); + file = kzalloc(sizeof(*file), GFP_KERNEL); if (!file) goto out_unlock; - memset(file, 0, sizeof(*file)); memcpy(&file->f_handle, f, sizeof(struct nfs_fh)); file->f_hash = hash; init_MUTEX(&file->f_sema); diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 330ff9f..e24be7f 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -145,11 +145,10 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) struct inode *root_inode; struct minix_sb_info *sbi; - sbi = kmalloc(sizeof(struct minix_sb_info), GFP_KERNEL); + sbi = kzalloc(sizeof(struct minix_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; s->s_fs_info = sbi; - memset(sbi, 0, sizeof(struct minix_sb_info)); /* N.B. These should be compile-time tests. Unfortunately that is impossible. */ @@ -207,10 +206,9 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0) goto out_illegal_sb; i = (sbi->s_imap_blocks + sbi->s_zmap_blocks) * sizeof(bh); - map = kmalloc(i, GFP_KERNEL); + map = kzalloc(i, GFP_KERNEL); if (!map) goto out_no_map; - memset(map, 0, i); sbi->s_imap = &map[0]; sbi->s_zmap = &map[sbi->s_imap_blocks]; diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 1ddf77b..752f02e 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -411,11 +411,10 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent) #endif struct ncp_entry_info finfo; - server = kmalloc(sizeof(struct ncp_server), GFP_KERNEL); + server = kzalloc(sizeof(struct ncp_server), GFP_KERNEL); if (!server) return -ENOMEM; sb->s_fs_info = server; - memset(server, 0, sizeof(struct ncp_server)); error = -EFAULT; if (raw_data == NULL) diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index bea6b94..b1902eb 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -573,10 +573,9 @@ idmap_lookup(struct svc_rqst *rqstp, struct idmap_defer_req *mdr; int ret; - mdr = kmalloc(sizeof(*mdr), GFP_KERNEL); + mdr = kzalloc(sizeof(*mdr), GFP_KERNEL); if (!mdr) return -ENOMEM; - memset(mdr, 0, sizeof(*mdr)); atomic_set(&mdr->count, 1); init_waitqueue_head(&mdr->waitq); mdr->req.defer = idmap_defer; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 9daa0b9..1a25c01 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -339,8 +339,7 @@ alloc_client(struct xdr_netobj name) { struct nfs4_client *clp; - if ((clp = kmalloc(sizeof(struct nfs4_client), GFP_KERNEL))!= NULL) { - memset(clp, 0, sizeof(*clp)); + if ((clp = kzalloc(sizeof(struct nfs4_client), GFP_KERNEL))!= NULL) { if ((clp->cl_name.data = kmalloc(name.len, GFP_KERNEL)) != NULL) { memcpy(clp->cl_name.data, name.data, name.len); clp->cl_name.len = name.len; diff --git a/fs/partitions/efi.c b/fs/partitions/efi.c index 6373028..1bea610 100644 --- a/fs/partitions/efi.c +++ b/fs/partitions/efi.c @@ -238,10 +238,9 @@ alloc_read_gpt_entries(struct block_device *bdev, gpt_header *gpt) le32_to_cpu(gpt->sizeof_partition_entry); if (!count) return NULL; - pte = kmalloc(count, GFP_KERNEL); + pte = kzalloc(count, GFP_KERNEL); if (!pte) return NULL; - memset(pte, 0, count); if (read_lba(bdev, le64_to_cpu(gpt->partition_entry_lba), (u8 *) pte, @@ -269,10 +268,9 @@ alloc_read_gpt_header(struct block_device *bdev, u64 lba) if (!bdev) return NULL; - gpt = kmalloc(sizeof (gpt_header), GFP_KERNEL); + gpt = kzalloc(sizeof (gpt_header), GFP_KERNEL); if (!gpt) return NULL; - memset(gpt, 0, sizeof (gpt_header)); if (read_lba(bdev, lba, (u8 *) gpt, sizeof (gpt_header)) < sizeof (gpt_header)) { @@ -526,9 +524,8 @@ find_valid_gpt(struct block_device *bdev, gpt_header **gpt, gpt_entry **ptes) lastlba = last_lba(bdev); if (!force_gpt) { /* This will be added to the EFI Spec. per Intel after v1.02. */ - legacymbr = kmalloc(sizeof (*legacymbr), GFP_KERNEL); + legacymbr = kzalloc(sizeof (*legacymbr), GFP_KERNEL); if (legacymbr) { - memset(legacymbr, 0, sizeof (*legacymbr)); read_lba(bdev, 0, (u8 *) legacymbr, sizeof (*legacymbr)); good_pmbr = is_pmbr_valid(legacymbr, lastlba); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 6a984f6..3ceff38 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -279,12 +279,11 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) tsz = elf_buflen - *fpos; if (buflen < tsz) tsz = buflen; - elf_buf = kmalloc(elf_buflen, GFP_ATOMIC); + elf_buf = kzalloc(elf_buflen, GFP_ATOMIC); if (!elf_buf) { read_unlock(&kclist_lock); return -ENOMEM; } - memset(elf_buf, 0, elf_buflen); elf_kcore_store_hdr(elf_buf, nphdr, elf_buflen); read_unlock(&kclist_lock); if (copy_to_user(buffer, elf_buf + *fpos, tsz)) { @@ -330,10 +329,9 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) unsigned long curstart = start; unsigned long cursize = tsz; - elf_buf = kmalloc(tsz, GFP_KERNEL); + elf_buf = kzalloc(tsz, GFP_KERNEL); if (!elf_buf) return -ENOMEM; - memset(elf_buf, 0, tsz); read_lock(&vmlist_lock); for (m=vmlist; m && cursize; m=m->next) { diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index 5a90349..8497609 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -358,11 +358,10 @@ static int qnx4_fill_super(struct super_block *s, void *data, int silent) const char *errmsg; struct qnx4_sb_info *qs; - qs = kmalloc(sizeof(struct qnx4_sb_info), GFP_KERNEL); + qs = kzalloc(sizeof(struct qnx4_sb_info), GFP_KERNEL); if (!qs) return -ENOMEM; s->s_fs_info = qs; - memset(qs, 0, sizeof(struct qnx4_sb_info)); sb_set_blocksize(s, QNX4_BLOCK_SIZE); diff --git a/fs/sysv/super.c b/fs/sysv/super.c index 876639b..350cba5 100644 --- a/fs/sysv/super.c +++ b/fs/sysv/super.c @@ -369,10 +369,9 @@ static int sysv_fill_super(struct super_block *sb, void *data, int silent) if (64 != sizeof (struct sysv_inode)) panic("sysv fs: bad inode size"); - sbi = kmalloc(sizeof(struct sysv_sb_info), GFP_KERNEL); + sbi = kzalloc(sizeof(struct sysv_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; - memset(sbi, 0, sizeof(struct sysv_sb_info)); sbi->s_sb = sb; sbi->s_block_base = 0; @@ -453,10 +452,9 @@ static int v7_fill_super(struct super_block *sb, void *data, int silent) if (64 != sizeof (struct sysv_inode)) panic("sysv fs: bad i-node size"); - sbi = kmalloc(sizeof(struct sysv_sb_info), GFP_KERNEL); + sbi = kzalloc(sizeof(struct sysv_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; - memset(sbi, 0, sizeof(struct sysv_sb_info)); sbi->s_sb = sb; sbi->s_block_base = 0; diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c index 3332347..d1d3823 100644 --- a/fs/udf/ialloc.c +++ b/fs/udf/ialloc.c @@ -130,14 +130,12 @@ struct inode * udf_new_inode (struct inode *dir, int mode, int * err) { UDF_I_EFE(inode) = 1; UDF_UPDATE_UDFREV(inode->i_sb, UDF_VERS_USE_EXTENDED_FE); - UDF_I_DATA(inode) = kmalloc(inode->i_sb->s_blocksize - sizeof(struct extendedFileEntry), GFP_KERNEL); - memset(UDF_I_DATA(inode), 0x00, inode->i_sb->s_blocksize - sizeof(struct extendedFileEntry)); + UDF_I_DATA(inode) = kzalloc(inode->i_sb->s_blocksize - sizeof(struct extendedFileEntry), GFP_KERNEL); } else { UDF_I_EFE(inode) = 0; - UDF_I_DATA(inode) = kmalloc(inode->i_sb->s_blocksize - sizeof(struct fileEntry), GFP_KERNEL); - memset(UDF_I_DATA(inode), 0x00, inode->i_sb->s_blocksize - sizeof(struct fileEntry)); + UDF_I_DATA(inode) = kzalloc(inode->i_sb->s_blocksize - sizeof(struct fileEntry), GFP_KERNEL); } if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_AD_IN_ICB)) UDF_I_ALLOCTYPE(inode) = ICBTAG_FLAG_AD_IN_ICB; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 992ee0b..ef910e7 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -611,11 +611,10 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) UFSD("ENTER\n"); - sbi = kmalloc(sizeof(struct ufs_sb_info), GFP_KERNEL); + sbi = kzalloc(sizeof(struct ufs_sb_info), GFP_KERNEL); if (!sbi) goto failed_nomem; sb->s_fs_info = sbi; - memset(sbi, 0, sizeof(struct ufs_sb_info)); UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY)); -- cgit v1.1 From f52720ca5f48574e347dff35ffe6b389ace61537 Mon Sep 17 00:00:00 2001 From: Panagiotis Issaris Date: Wed, 27 Sep 2006 01:49:39 -0700 Subject: [PATCH] fs: Removing useless casts * Removing useless casts * Removing useless wrapper * Conversion from kmalloc+memset to kzalloc Signed-off-by: Panagiotis Issaris Acked-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/coda/dir.c | 2 +- fs/ext2/acl.c | 4 ++-- fs/ext3/acl.c | 4 ++-- fs/ext3/resize.c | 4 ++-- fs/hpfs/buffer.c | 2 +- fs/jffs/inode-v23.c | 8 ++++---- fs/jffs/intrep.c | 11 ++++------- fs/jffs/jffs_fm.c | 6 ++---- fs/jfs/jfs_txnmgr.c | 4 ++-- fs/lockd/clntproc.c | 2 +- fs/ncpfs/symlink.c | 4 ++-- fs/nfs/delegation.c | 7 +------ fs/nfs/inode.c | 2 +- fs/nfs/nfs3proc.c | 2 +- fs/nfs/proc.c | 2 +- fs/ntfs/dir.c | 5 ++--- fs/ntfs/inode.c | 2 +- fs/ntfs/mft.c | 4 ++-- fs/ntfs/unistr.c | 4 ++-- fs/xfs/linux-2.6/xfs_file.c | 2 +- fs/xfs/linux-2.6/xfs_iops.c | 4 ++-- 21 files changed, 37 insertions(+), 48 deletions(-) (limited to 'fs') diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 71f2ea6..8651ea6 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -513,7 +513,7 @@ static int coda_venus_readdir(struct file *filp, filldir_t filldir, ino_t ino; int ret, i; - vdir = (struct venus_dirent *)kmalloc(sizeof(*vdir), GFP_KERNEL); + vdir = kmalloc(sizeof(*vdir), GFP_KERNEL); if (!vdir) return -ENOMEM; i = filp->f_pos; diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index da52b4a..7c420b8 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -89,8 +89,8 @@ ext2_acl_to_disk(const struct posix_acl *acl, size_t *size) size_t n; *size = ext2_acl_size(acl->a_count); - ext_acl = (ext2_acl_header *)kmalloc(sizeof(ext2_acl_header) + - acl->a_count * sizeof(ext2_acl_entry), GFP_KERNEL); + ext_acl = kmalloc(sizeof(ext2_acl_header) + acl->a_count * + sizeof(ext2_acl_entry), GFP_KERNEL); if (!ext_acl) return ERR_PTR(-ENOMEM); ext_acl->a_version = cpu_to_le32(EXT2_ACL_VERSION); diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index 92bf782..1e5038d 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -90,8 +90,8 @@ ext3_acl_to_disk(const struct posix_acl *acl, size_t *size) size_t n; *size = ext3_acl_size(acl->a_count); - ext_acl = (ext3_acl_header *)kmalloc(sizeof(ext3_acl_header) + - acl->a_count * sizeof(ext3_acl_entry), GFP_KERNEL); + ext_acl = kmalloc(sizeof(ext3_acl_header) + acl->a_count * + sizeof(ext3_acl_entry), GFP_KERNEL); if (!ext_acl) return ERR_PTR(-ENOMEM); ext_acl->a_version = cpu_to_le32(EXT3_ACL_VERSION); diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c index 9e318a5..b73cba1 100644 --- a/fs/ext3/resize.c +++ b/fs/ext3/resize.c @@ -439,8 +439,8 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, if ((err = ext3_reserve_inode_write(handle, inode, &iloc))) goto exit_dindj; - n_group_desc = (struct buffer_head **)kmalloc((gdb_num + 1) * - sizeof(struct buffer_head *), GFP_KERNEL); + n_group_desc = kmalloc((gdb_num + 1) * sizeof(struct buffer_head *), + GFP_KERNEL); if (!n_group_desc) { err = -ENOMEM; ext3_warning (sb, __FUNCTION__, diff --git a/fs/hpfs/buffer.c b/fs/hpfs/buffer.c index 2807aa8..b52b738 100644 --- a/fs/hpfs/buffer.c +++ b/fs/hpfs/buffer.c @@ -76,7 +76,7 @@ void *hpfs_map_4sectors(struct super_block *s, unsigned secno, struct quad_buffe return NULL; } - qbh->data = data = (char *)kmalloc(2048, GFP_NOFS); + qbh->data = data = kmalloc(2048, GFP_NOFS); if (!data) { printk("HPFS: hpfs_map_4sectors: out of memory\n"); goto bail; diff --git a/fs/jffs/inode-v23.c b/fs/jffs/inode-v23.c index 9306869..b59553d 100644 --- a/fs/jffs/inode-v23.c +++ b/fs/jffs/inode-v23.c @@ -652,7 +652,7 @@ jffs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) lock_kernel(); D3({ - char *s = (char *)kmalloc(len + 1, GFP_KERNEL); + char *s = kmalloc(len + 1, GFP_KERNEL); memcpy(s, name, len); s[len] = '\0'; printk("jffs_lookup(): dir: 0x%p, name: \"%s\"\n", dir, s); @@ -1173,8 +1173,8 @@ jffs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) lock_kernel(); D1({ int len = dentry->d_name.len; - char *_name = (char *)kmalloc(len + 1, GFP_KERNEL); - char *_symname = (char *)kmalloc(symname_len + 1, GFP_KERNEL); + char *_name = kmalloc(len + 1, GFP_KERNEL); + char *_symname = kmalloc(symname_len + 1, GFP_KERNEL); memcpy(_name, dentry->d_name.name, len); _name[len] = '\0'; memcpy(_symname, symname, symname_len); @@ -1282,7 +1282,7 @@ jffs_create(struct inode *dir, struct dentry *dentry, int mode, lock_kernel(); D1({ int len = dentry->d_name.len; - char *s = (char *)kmalloc(len + 1, GFP_KERNEL); + char *s = kmalloc(len + 1, GFP_KERNEL); memcpy(s, dentry->d_name.name, len); s[len] = '\0'; printk("jffs_create(): dir: 0x%p, name: \"%s\"\n", dir, s); diff --git a/fs/jffs/intrep.c b/fs/jffs/intrep.c index 9000f1e..4a543e1 100644 --- a/fs/jffs/intrep.c +++ b/fs/jffs/intrep.c @@ -488,13 +488,11 @@ jffs_create_file(struct jffs_control *c, { struct jffs_file *f; - if (!(f = (struct jffs_file *)kmalloc(sizeof(struct jffs_file), - GFP_KERNEL))) { + if (!(f = kzalloc(sizeof(*f), GFP_KERNEL))) { D(printk("jffs_create_file(): Failed!\n")); return NULL; } no_jffs_file++; - memset(f, 0, sizeof(struct jffs_file)); f->ino = raw_inode->ino; f->pino = raw_inode->pino; f->nlink = raw_inode->nlink; @@ -516,7 +514,7 @@ jffs_create_control(struct super_block *sb) D2(printk("jffs_create_control()\n")); - if (!(c = (struct jffs_control *)kmalloc(s, GFP_KERNEL))) { + if (!(c = kmalloc(s, GFP_KERNEL))) { goto fail_control; } DJM(no_jffs_control++); @@ -524,7 +522,7 @@ jffs_create_control(struct super_block *sb) c->gc_task = NULL; c->hash_len = JFFS_HASH_SIZE; s = sizeof(struct list_head) * c->hash_len; - if (!(c->hash = (struct list_head *)kmalloc(s, GFP_KERNEL))) { + if (!(c->hash = kmalloc(s, GFP_KERNEL))) { goto fail_hash; } DJM(no_hash++); @@ -593,8 +591,7 @@ jffs_add_virtual_root(struct jffs_control *c) D2(printk("jffs_add_virtual_root(): " "Creating a virtual root directory.\n")); - if (!(root = (struct jffs_file *)kmalloc(sizeof(struct jffs_file), - GFP_KERNEL))) { + if (!(root = kmalloc(sizeof(struct jffs_file), GFP_KERNEL))) { return -ENOMEM; } no_jffs_file++; diff --git a/fs/jffs/jffs_fm.c b/fs/jffs/jffs_fm.c index 7d8ca1a..29b68d9 100644 --- a/fs/jffs/jffs_fm.c +++ b/fs/jffs/jffs_fm.c @@ -94,8 +94,7 @@ jffs_build_begin(struct jffs_control *c, int unit) struct mtd_info *mtd; D3(printk("jffs_build_begin()\n")); - fmc = (struct jffs_fmcontrol *)kmalloc(sizeof(struct jffs_fmcontrol), - GFP_KERNEL); + fmc = kmalloc(sizeof(*fmc), GFP_KERNEL); if (!fmc) { D(printk("jffs_build_begin(): Allocation of " "struct jffs_fmcontrol failed!\n")); @@ -486,8 +485,7 @@ jffs_add_node(struct jffs_node *node) D3(printk("jffs_add_node(): ino = %u\n", node->ino)); - ref = (struct jffs_node_ref *)kmalloc(sizeof(struct jffs_node_ref), - GFP_KERNEL); + ref = kmalloc(sizeof(*ref), GFP_KERNEL); if (!ref) return -ENOMEM; diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index efbb586..3856efc 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -282,7 +282,7 @@ int txInit(void) TxLockVHWM = (nTxLock * 8) / 10; size = sizeof(struct tblock) * nTxBlock; - TxBlock = (struct tblock *) vmalloc(size); + TxBlock = vmalloc(size); if (TxBlock == NULL) return -ENOMEM; @@ -307,7 +307,7 @@ int txInit(void) * tlock id = 0 is reserved. */ size = sizeof(struct tlock) * nTxLock; - TxLock = (struct tlock *) vmalloc(size); + TxLock = vmalloc(size); if (TxLock == NULL) { vfree(TxBlock); return -ENOMEM; diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index 50dbb67..271e216 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -100,7 +100,7 @@ static struct nlm_lockowner *nlm_find_lockowner(struct nlm_host *host, fl_owner_ res = __nlm_find_lockowner(host, owner); if (res == NULL) { spin_unlock(&host->h_lock); - new = (struct nlm_lockowner *)kmalloc(sizeof(*new), GFP_KERNEL); + new = kmalloc(sizeof(*new), GFP_KERNEL); spin_lock(&host->h_lock); res = __nlm_find_lockowner(host, owner); if (res == NULL && new != NULL) { diff --git a/fs/ncpfs/symlink.c b/fs/ncpfs/symlink.c index ca92c24..e3d26c1 100644 --- a/fs/ncpfs/symlink.c +++ b/fs/ncpfs/symlink.c @@ -48,7 +48,7 @@ static int ncp_symlink_readpage(struct file *file, struct page *page) char *buf = kmap(page); error = -ENOMEM; - rawlink=(char *)kmalloc(NCP_MAX_SYMLINK_SIZE, GFP_KERNEL); + rawlink = kmalloc(NCP_MAX_SYMLINK_SIZE, GFP_KERNEL); if (!rawlink) goto fail; @@ -126,7 +126,7 @@ int ncp_symlink(struct inode *dir, struct dentry *dentry, const char *symname) { /* EPERM is returned by VFS if symlink procedure does not exist */ return -EPERM; - rawlink=(char *)kmalloc(NCP_MAX_SYMLINK_SIZE, GFP_KERNEL); + rawlink = kmalloc(NCP_MAX_SYMLINK_SIZE, GFP_KERNEL); if (!rawlink) return -ENOMEM; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 5713367..841c99a 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -20,11 +20,6 @@ #include "delegation.h" #include "internal.h" -static struct nfs_delegation *nfs_alloc_delegation(void) -{ - return (struct nfs_delegation *)kmalloc(sizeof(struct nfs_delegation), GFP_KERNEL); -} - static void nfs_free_delegation(struct nfs_delegation *delegation) { if (delegation->cred) @@ -124,7 +119,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct if ((nfsi->cache_validity & (NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_ATTR))) __nfs_revalidate_inode(NFS_SERVER(inode), inode); - delegation = nfs_alloc_delegation(); + delegation = kmalloc(sizeof(*delegation), GFP_KERNEL); if (delegation == NULL) return -ENOMEM; memcpy(delegation->stateid.data, res->delegation.data, diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e8c143d..a9d0f71 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -443,7 +443,7 @@ static struct nfs_open_context *alloc_nfs_open_context(struct vfsmount *mnt, str { struct nfs_open_context *ctx; - ctx = (struct nfs_open_context *)kmalloc(sizeof(*ctx), GFP_KERNEL); + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (ctx != NULL) { atomic_set(&ctx->count, 1); ctx->dentry = dget(dentry); diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index f8688ea..3b234d4 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -449,7 +449,7 @@ nfs3_proc_unlink_setup(struct rpc_message *msg, struct dentry *dir, struct qstr struct nfs_fattr res; } *ptr; - ptr = (struct unlinkxdr *)kmalloc(sizeof(*ptr), GFP_KERNEL); + ptr = kmalloc(sizeof(*ptr), GFP_KERNEL); if (!ptr) return -ENOMEM; ptr->arg.fh = NFS_FH(dir->d_inode); diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 630e506..4529cc4 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -352,7 +352,7 @@ nfs_proc_unlink_setup(struct rpc_message *msg, struct dentry *dir, struct qstr * { struct nfs_diropargs *arg; - arg = (struct nfs_diropargs *)kmalloc(sizeof(*arg), GFP_KERNEL); + arg = kmalloc(sizeof(*arg), GFP_KERNEL); if (!arg) return -ENOMEM; arg->fh = NFS_FH(dir->d_inode); diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index d1e2c6f..85c36b8 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -1149,8 +1149,7 @@ static int ntfs_readdir(struct file *filp, void *dirent, filldir_t filldir) * Allocate a buffer to store the current name being processed * converted to format determined by current NLS. */ - name = (u8*)kmalloc(NTFS_MAX_NAME_LEN * NLS_MAX_CHARSET_SIZE + 1, - GFP_NOFS); + name = kmalloc(NTFS_MAX_NAME_LEN * NLS_MAX_CHARSET_SIZE + 1, GFP_NOFS); if (unlikely(!name)) { err = -ENOMEM; goto err_out; @@ -1191,7 +1190,7 @@ static int ntfs_readdir(struct file *filp, void *dirent, filldir_t filldir) * map the mft record without deadlocking. */ rc = le32_to_cpu(ctx->attr->data.resident.value_length); - ir = (INDEX_ROOT*)kmalloc(rc, GFP_NOFS); + ir = kmalloc(rc, GFP_NOFS); if (unlikely(!ir)) { err = -ENOMEM; goto err_out; diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index d313f35..3185212 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -137,7 +137,7 @@ static int ntfs_init_locked_inode(struct inode *vi, ntfs_attr *na) BUG_ON(!na->name); i = na->name_len * sizeof(ntfschar); - ni->name = (ntfschar*)kmalloc(i + sizeof(ntfschar), GFP_ATOMIC); + ni->name = kmalloc(i + sizeof(ntfschar), GFP_ATOMIC); if (!ni->name) return -ENOMEM; memcpy(ni->name, na->name, i); diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 2438c00..578fb3d 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -331,7 +331,7 @@ map_err_out: ntfs_inode **tmp; int new_size = (base_ni->nr_extents + 4) * sizeof(ntfs_inode *); - tmp = (ntfs_inode **)kmalloc(new_size, GFP_NOFS); + tmp = kmalloc(new_size, GFP_NOFS); if (unlikely(!tmp)) { ntfs_error(base_ni->vol->sb, "Failed to allocate " "internal buffer."); @@ -2893,7 +2893,7 @@ rollback: if (!(base_ni->nr_extents & 3)) { int new_size = (base_ni->nr_extents + 4) * sizeof(ntfs_inode*); - extent_nis = (ntfs_inode**)kmalloc(new_size, GFP_NOFS); + extent_nis = kmalloc(new_size, GFP_NOFS); if (unlikely(!extent_nis)) { ntfs_error(vol->sb, "Failed to allocate internal " "buffer during rollback.%s", es); diff --git a/fs/ntfs/unistr.c b/fs/ntfs/unistr.c index b123c0f..a1b5721 100644 --- a/fs/ntfs/unistr.c +++ b/fs/ntfs/unistr.c @@ -350,7 +350,7 @@ int ntfs_ucstonls(const ntfs_volume *vol, const ntfschar *ins, } if (!ns) { ns_len = ins_len * NLS_MAX_CHARSET_SIZE; - ns = (unsigned char*)kmalloc(ns_len + 1, GFP_NOFS); + ns = kmalloc(ns_len + 1, GFP_NOFS); if (!ns) goto mem_err_out; } @@ -365,7 +365,7 @@ retry: wc = nls->uni2char(le16_to_cpu(ins[i]), ns + o, else if (wc == -ENAMETOOLONG && ns != *outs) { unsigned char *tc; /* Grow in multiples of 64 bytes. */ - tc = (unsigned char*)kmalloc((ns_len + 64) & + tc = kmalloc((ns_len + 64) & ~63, GFP_NOFS); if (tc) { memcpy(tc, ns, ns_len); diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index 3d4f6df..41cfcba 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -370,7 +370,7 @@ xfs_file_readdir( /* Try fairly hard to get memory */ do { - if ((read_buf = (caddr_t)kmalloc(rlen, GFP_KERNEL))) + if ((read_buf = kmalloc(rlen, GFP_KERNEL))) break; rlen >>= 1; } while (rlen >= 1024); diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c index d918002..22e3b71 100644 --- a/fs/xfs/linux-2.6/xfs_iops.c +++ b/fs/xfs/linux-2.6/xfs_iops.c @@ -553,13 +553,13 @@ xfs_vn_follow_link( ASSERT(dentry); ASSERT(nd); - link = (char *)kmalloc(MAXPATHLEN+1, GFP_KERNEL); + link = kmalloc(MAXPATHLEN+1, GFP_KERNEL); if (!link) { nd_set_link(nd, ERR_PTR(-ENOMEM)); return NULL; } - uio = (uio_t *)kmalloc(sizeof(uio_t), GFP_KERNEL); + uio = kmalloc(sizeof(uio_t), GFP_KERNEL); if (!uio) { kfree(link); nd_set_link(nd, ERR_PTR(-ENOMEM)); -- cgit v1.1 From 1a1d92c10dd24bbdc28b3d6e2d03ec199dd3a65b Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 27 Sep 2006 01:49:40 -0700 Subject: [PATCH] Really ignore kmem_cache_destroy return value * Rougly half of callers already do it by not checking return value * Code in drivers/acpi/osl.c does the following to be sure: (void)kmem_cache_destroy(cache); * Those who check it printk something, however, slab_error already printed the name of failed cache. * XFS BUGs on failed kmem_cache_destroy which is not the decision low-level filesystem driver should make. Converted to ignore. Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/adfs/super.c | 3 +-- fs/affs/super.c | 3 +-- fs/befs/linuxvfs.c | 4 +--- fs/bfs/inode.c | 3 +-- fs/cifs/cifsfs.c | 20 +++++--------------- fs/coda/inode.c | 3 +-- fs/efs/super.c | 3 +-- fs/ext2/super.c | 3 +-- fs/ext3/super.c | 3 +-- fs/fat/cache.c | 3 +-- fs/fat/inode.c | 3 +-- fs/hfs/super.c | 3 +-- fs/hfsplus/super.c | 3 +-- fs/hpfs/super.c | 3 +-- fs/isofs/inode.c | 4 +--- fs/minix/inode.c | 3 +-- fs/ncpfs/inode.c | 3 +-- fs/nfs/direct.c | 3 +-- fs/nfs/inode.c | 3 +-- fs/nfs/pagelist.c | 3 +-- fs/nfs/read.c | 3 +-- fs/nfs/write.c | 3 +-- fs/nfsd/nfs4state.c | 5 +---- fs/ntfs/super.c | 28 +++++----------------------- fs/ocfs2/dlm/dlmfs.c | 4 +--- fs/qnx4/inode.c | 4 +--- fs/reiserfs/super.c | 4 +--- fs/romfs/inode.c | 3 +-- fs/smbfs/inode.c | 3 +-- fs/smbfs/request.c | 3 +-- fs/udf/super.c | 3 +-- fs/ufs/super.c | 3 +-- fs/xfs/linux-2.6/kmem.h | 4 ++-- 33 files changed, 42 insertions(+), 107 deletions(-) (limited to 'fs') diff --git a/fs/adfs/super.c b/fs/adfs/super.c index 959dbf1..9ade139 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -251,8 +251,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(adfs_inode_cachep)) - printk(KERN_INFO "adfs_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(adfs_inode_cachep); } static struct super_operations adfs_sops = { diff --git a/fs/affs/super.c b/fs/affs/super.c index b35f514..5ea72c3 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -109,8 +109,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(affs_inode_cachep)) - printk(KERN_INFO "affs_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(affs_inode_cachep); } static struct super_operations affs_sops = { diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 50cfca5..f6676fb 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -446,9 +446,7 @@ befs_init_inodecache(void) static void befs_destroy_inodecache(void) { - if (kmem_cache_destroy(befs_inode_cachep)) - printk(KERN_ERR "befs_destroy_inodecache: " - "not all structures were freed\n"); + kmem_cache_destroy(befs_inode_cachep); } /* diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 3e4d6c7..8fc2e8e 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -268,8 +268,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(bfs_inode_cachep)) - printk(KERN_INFO "bfs_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(bfs_inode_cachep); } static struct super_operations bfs_sops = { diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index c3ef1c0..4197a50 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -699,8 +699,7 @@ cifs_init_inodecache(void) static void cifs_destroy_inodecache(void) { - if (kmem_cache_destroy(cifs_inode_cachep)) - printk(KERN_WARNING "cifs_inode_cache: error freeing\n"); + kmem_cache_destroy(cifs_inode_cachep); } static int @@ -778,13 +777,9 @@ static void cifs_destroy_request_bufs(void) { mempool_destroy(cifs_req_poolp); - if (kmem_cache_destroy(cifs_req_cachep)) - printk(KERN_WARNING - "cifs_destroy_request_cache: error not all structures were freed\n"); + kmem_cache_destroy(cifs_req_cachep); mempool_destroy(cifs_sm_req_poolp); - if (kmem_cache_destroy(cifs_sm_req_cachep)) - printk(KERN_WARNING - "cifs_destroy_request_cache: cifs_small_rq free error\n"); + kmem_cache_destroy(cifs_sm_req_cachep); } static int @@ -819,13 +814,8 @@ static void cifs_destroy_mids(void) { mempool_destroy(cifs_mid_poolp); - if (kmem_cache_destroy(cifs_mid_cachep)) - printk(KERN_WARNING - "cifs_destroy_mids: error not all structures were freed\n"); - - if (kmem_cache_destroy(cifs_oplock_cachep)) - printk(KERN_WARNING - "error not all oplock structures were freed\n"); + kmem_cache_destroy(cifs_mid_cachep); + kmem_cache_destroy(cifs_oplock_cachep); } static int cifs_oplock_thread(void * dummyarg) diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 87f1dc8..88d1233 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -80,8 +80,7 @@ int coda_init_inodecache(void) void coda_destroy_inodecache(void) { - if (kmem_cache_destroy(coda_inode_cachep)) - printk(KERN_INFO "coda_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(coda_inode_cachep); } static int coda_remount(struct super_block *sb, int *flags, char *data) diff --git a/fs/efs/super.c b/fs/efs/super.c index 7089269..b3f5065 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -90,8 +90,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(efs_inode_cachep)) - printk(KERN_INFO "efs_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(efs_inode_cachep); } static void efs_put_super(struct super_block *s) diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 69435fb..513cd42 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -184,8 +184,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(ext2_inode_cachep)) - printk(KERN_INFO "ext2_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(ext2_inode_cachep); } static void ext2_clear_inode(struct inode *inode) diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 09b4b31..8bfd56e 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -491,8 +491,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(ext3_inode_cachep)) - printk(KERN_INFO "ext3_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(ext3_inode_cachep); } static void ext3_clear_inode(struct inode *inode) diff --git a/fs/fat/cache.c b/fs/fat/cache.c index 97b967b..82cc4f59 100644 --- a/fs/fat/cache.c +++ b/fs/fat/cache.c @@ -58,8 +58,7 @@ int __init fat_cache_init(void) void fat_cache_destroy(void) { - if (kmem_cache_destroy(fat_cache_cachep)) - printk(KERN_INFO "fat_cache: not all structures were freed\n"); + kmem_cache_destroy(fat_cache_cachep); } static inline struct fat_cache *fat_cache_alloc(struct inode *inode) diff --git a/fs/fat/inode.c b/fs/fat/inode.c index bc4da3a..d301511 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -528,8 +528,7 @@ static int __init fat_init_inodecache(void) static void __exit fat_destroy_inodecache(void) { - if (kmem_cache_destroy(fat_inode_cachep)) - printk(KERN_INFO "fat_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(fat_inode_cachep); } static int fat_remount(struct super_block *sb, int *flags, char *data) diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 05dffff..d43b4fc 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -454,8 +454,7 @@ static int __init init_hfs_fs(void) static void __exit exit_hfs_fs(void) { unregister_filesystem(&hfs_fs_type); - if (kmem_cache_destroy(hfs_inode_cachep)) - printk(KERN_ERR "hfs_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(hfs_inode_cachep); } module_init(init_hfs_fs) diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index d279d59..194eede 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -493,8 +493,7 @@ static int __init init_hfsplus_fs(void) static void __exit exit_hfsplus_fs(void) { unregister_filesystem(&hfsplus_fs_type); - if (kmem_cache_destroy(hfsplus_inode_cachep)) - printk(KERN_ERR "hfsplus_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(hfsplus_inode_cachep); } module_init(init_hfsplus_fs) diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index b76d608..450b5e0 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -203,8 +203,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(hpfs_inode_cachep)) - printk(KERN_INFO "hpfs_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(hpfs_inode_cachep); } /* diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index ab15e90..10e4789 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -96,9 +96,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(isofs_inode_cachep)) - printk(KERN_INFO "iso_inode_cache: not all structures were " - "freed\n"); + kmem_cache_destroy(isofs_inode_cachep); } static int isofs_remount(struct super_block *sb, int *flags, char *data) diff --git a/fs/minix/inode.c b/fs/minix/inode.c index e24be7f..826b9d8 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -90,8 +90,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(minix_inode_cachep)) - printk(KERN_INFO "minix_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(minix_inode_cachep); } static struct super_operations minix_sops = { diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 752f02e..8244710 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -81,8 +81,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(ncp_inode_cachep)) - printk(KERN_INFO "ncp_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(ncp_inode_cachep); } static int ncp_remount(struct super_block *sb, int *flags, char* data) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 76ca1cb..377839b 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -855,6 +855,5 @@ int __init nfs_init_directcache(void) */ void nfs_destroy_directcache(void) { - if (kmem_cache_destroy(nfs_direct_cachep)) - printk(KERN_INFO "nfs_direct_cache: not all structures were freed\n"); + kmem_cache_destroy(nfs_direct_cachep); } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index a9d0f71..931f52a 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1134,8 +1134,7 @@ static int __init nfs_init_inodecache(void) static void nfs_destroy_inodecache(void) { - if (kmem_cache_destroy(nfs_inode_cachep)) - printk(KERN_INFO "nfs_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(nfs_inode_cachep); } /* diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 36e902a..829af32 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -392,7 +392,6 @@ int __init nfs_init_nfspagecache(void) void nfs_destroy_nfspagecache(void) { - if (kmem_cache_destroy(nfs_page_cachep)) - printk(KERN_INFO "nfs_page: not all structures were freed\n"); + kmem_cache_destroy(nfs_page_cachep); } diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 69f1549..c2e49c3 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -737,6 +737,5 @@ int __init nfs_init_readpagecache(void) void nfs_destroy_readpagecache(void) { mempool_destroy(nfs_rdata_mempool); - if (kmem_cache_destroy(nfs_rdata_cachep)) - printk(KERN_INFO "nfs_read_data: not all structures were freed\n"); + kmem_cache_destroy(nfs_rdata_cachep); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index c12effb..b674462 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1565,7 +1565,6 @@ void nfs_destroy_writepagecache(void) { mempool_destroy(nfs_commit_mempool); mempool_destroy(nfs_wdata_mempool); - if (kmem_cache_destroy(nfs_wdata_cachep)) - printk(KERN_INFO "nfs_write_data: not all structures were freed\n"); + kmem_cache_destroy(nfs_wdata_cachep); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 1a25c01..ebcf226 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1005,13 +1005,10 @@ alloc_init_file(struct inode *ino) static void nfsd4_free_slab(kmem_cache_t **slab) { - int status; - if (*slab == NULL) return; - status = kmem_cache_destroy(*slab); + kmem_cache_destroy(*slab); *slab = NULL; - WARN_ON(status); } static void diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 74e0ee8..6b2712f 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -3248,32 +3248,14 @@ ictx_err_out: static void __exit exit_ntfs_fs(void) { - int err = 0; - ntfs_debug("Unregistering NTFS driver."); unregister_filesystem(&ntfs_fs_type); - - if (kmem_cache_destroy(ntfs_big_inode_cache) && (err = 1)) - printk(KERN_CRIT "NTFS: Failed to destory %s.\n", - ntfs_big_inode_cache_name); - if (kmem_cache_destroy(ntfs_inode_cache) && (err = 1)) - printk(KERN_CRIT "NTFS: Failed to destory %s.\n", - ntfs_inode_cache_name); - if (kmem_cache_destroy(ntfs_name_cache) && (err = 1)) - printk(KERN_CRIT "NTFS: Failed to destory %s.\n", - ntfs_name_cache_name); - if (kmem_cache_destroy(ntfs_attr_ctx_cache) && (err = 1)) - printk(KERN_CRIT "NTFS: Failed to destory %s.\n", - ntfs_attr_ctx_cache_name); - if (kmem_cache_destroy(ntfs_index_ctx_cache) && (err = 1)) - printk(KERN_CRIT "NTFS: Failed to destory %s.\n", - ntfs_index_ctx_cache_name); - if (err) - printk(KERN_CRIT "NTFS: This causes memory to leak! There is " - "probably a BUG in the driver! Please report " - "you saw this message to " - "linux-ntfs-dev@lists.sourceforge.net\n"); + kmem_cache_destroy(ntfs_big_inode_cache); + kmem_cache_destroy(ntfs_inode_cache); + kmem_cache_destroy(ntfs_name_cache); + kmem_cache_destroy(ntfs_attr_ctx_cache); + kmem_cache_destroy(ntfs_index_ctx_cache); /* Unregister the ntfs sysctls. */ ntfs_sysctl(0); } diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c index 033ad17..0ff0898 100644 --- a/fs/ocfs2/dlm/dlmfs.c +++ b/fs/ocfs2/dlm/dlmfs.c @@ -629,9 +629,7 @@ static void __exit exit_dlmfs_fs(void) flush_workqueue(user_dlm_worker); destroy_workqueue(user_dlm_worker); - if (kmem_cache_destroy(dlmfs_inode_cache)) - printk(KERN_INFO "dlmfs_inode_cache: not all structures " - "were freed\n"); + kmem_cache_destroy(dlmfs_inode_cache); } MODULE_AUTHOR("Oracle"); diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index 8497609..fddbd61 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -556,9 +556,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(qnx4_inode_cachep)) - printk(KERN_INFO - "qnx4_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(qnx4_inode_cachep); } static int qnx4_get_sb(struct file_system_type *fs_type, diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 5567328..1cd4d38 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -530,9 +530,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(reiserfs_inode_cachep)) - reiserfs_warning(NULL, - "reiserfs_inode_cache: not all structures were freed"); + kmem_cache_destroy(reiserfs_inode_cachep); } /* we don't mark inodes dirty, we just log them */ diff --git a/fs/romfs/inode.c b/fs/romfs/inode.c index 22eed61..ddcd9e1 100644 --- a/fs/romfs/inode.c +++ b/fs/romfs/inode.c @@ -589,8 +589,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(romfs_inode_cachep)) - printk(KERN_INFO "romfs_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(romfs_inode_cachep); } static int romfs_remount(struct super_block *sb, int *flags, char *data) diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c index a1ed657..92cf60a 100644 --- a/fs/smbfs/inode.c +++ b/fs/smbfs/inode.c @@ -89,8 +89,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(smb_inode_cachep)) - printk(KERN_INFO "smb_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(smb_inode_cachep); } static int smb_remount(struct super_block *sb, int *flags, char *data) diff --git a/fs/smbfs/request.c b/fs/smbfs/request.c index c8e9619..0fb7469 100644 --- a/fs/smbfs/request.c +++ b/fs/smbfs/request.c @@ -49,8 +49,7 @@ int smb_init_request_cache(void) void smb_destroy_request_cache(void) { - if (kmem_cache_destroy(req_cachep)) - printk(KERN_INFO "smb_destroy_request_cache: not all structures were freed\n"); + kmem_cache_destroy(req_cachep); } /* diff --git a/fs/udf/super.c b/fs/udf/super.c index fcce1a2..5dd356c 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -156,8 +156,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(udf_inode_cachep)) - printk(KERN_INFO "udf_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(udf_inode_cachep); } /* Superblock operations */ diff --git a/fs/ufs/super.c b/fs/ufs/super.c index ef910e7..ec79e30 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1244,8 +1244,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(ufs_inode_cachep)) - printk(KERN_INFO "ufs_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(ufs_inode_cachep); } #ifdef CONFIG_QUOTA diff --git a/fs/xfs/linux-2.6/kmem.h b/fs/xfs/linux-2.6/kmem.h index 939bd84..0e8293c 100644 --- a/fs/xfs/linux-2.6/kmem.h +++ b/fs/xfs/linux-2.6/kmem.h @@ -91,8 +91,8 @@ kmem_zone_free(kmem_zone_t *zone, void *ptr) static inline void kmem_zone_destroy(kmem_zone_t *zone) { - if (zone && kmem_cache_destroy(zone)) - BUG(); + if (zone) + kmem_cache_destroy(zone); } extern void *kmem_zone_alloc(kmem_zone_t *, unsigned int __nocast); -- cgit v1.1 From 5da6185bca064e35aa73a7c1f27488d2b96434f4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 27 Sep 2006 01:50:16 -0700 Subject: [PATCH] NOMMU: Set BDI capabilities for /dev/mem and /dev/kmem Set the backing device info capabilities for /dev/mem and /dev/kmem to permit direct sharing under no-MMU conditions and full mapping capabilities under MMU conditions. Make the BDI used by these available to all directly mappable character devices. Also comment the capabilities for /dev/zero. [akpm@osdl.org: ifdef reductions] Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/char_dev.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'fs') diff --git a/fs/char_dev.c b/fs/char_dev.c index 3483d3c..0009346 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -19,11 +19,30 @@ #include #include #include +#include #ifdef CONFIG_KMOD #include #endif +/* + * capabilities for /dev/mem, /dev/kmem and similar directly mappable character + * devices + * - permits shared-mmap for read, write and/or exec + * - does not permit private mmap in NOMMU mode (can't do COW) + * - no readahead or I/O queue unplugging required + */ +struct backing_dev_info directly_mappable_cdev_bdi = { + .capabilities = ( +#ifdef CONFIG_MMU + /* permit private copies of the data to be taken */ + BDI_CAP_MAP_COPY | +#endif + /* permit direct mmap, for read, write or exec */ + BDI_CAP_MAP_DIRECT | + BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP), +}; + static struct kobj_map *cdev_map; static DEFINE_MUTEX(chrdevs_lock); @@ -461,3 +480,4 @@ EXPORT_SYMBOL(cdev_del); EXPORT_SYMBOL(cdev_add); EXPORT_SYMBOL(register_chrdev); EXPORT_SYMBOL(unregister_chrdev); +EXPORT_SYMBOL(directly_mappable_cdev_bdi); -- cgit v1.1 From dbf8685c8e21404e3a8ed244bd0219d3c4b89101 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 27 Sep 2006 01:50:19 -0700 Subject: [PATCH] NOMMU: Implement /proc/pid/maps for NOMMU Implement /proc/pid/maps for NOMMU by reading the vm_area_list attached to current->mm->context.vmlist. Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/internal.h | 1 + fs/proc/nommu.c | 20 +++++++++----- fs/proc/task_nommu.c | 74 ++++++++++++++++++++++++++++++++++++++++++---------- 3 files changed, 75 insertions(+), 20 deletions(-) (limited to 'fs') diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 146a434..987c773 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -28,6 +28,7 @@ do { \ (vmi)->largest_chunk = 0; \ } while(0) +extern int nommu_vma_show(struct seq_file *, struct vm_area_struct *); #endif extern void create_seq_entry(char *name, mode_t mode, const struct file_operations *f); diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index cff10ab..d7dbdf9 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -33,19 +33,15 @@ #include "internal.h" /* - * display a list of all the VMAs the kernel knows about - * - nommu kernals have a single flat list + * display a single VMA to a sequenced file */ -static int nommu_vma_list_show(struct seq_file *m, void *v) +int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) { - struct vm_area_struct *vma; unsigned long ino = 0; struct file *file; dev_t dev = 0; int flags, len; - vma = rb_entry((struct rb_node *) v, struct vm_area_struct, vm_rb); - flags = vma->vm_flags; file = vma->vm_file; @@ -78,6 +74,18 @@ static int nommu_vma_list_show(struct seq_file *m, void *v) return 0; } +/* + * display a list of all the VMAs the kernel knows about + * - nommu kernals have a single flat list + */ +static int nommu_vma_list_show(struct seq_file *m, void *v) +{ + struct vm_area_struct *vma; + + vma = rb_entry((struct rb_node *) v, struct vm_area_struct, vm_rb); + return nommu_vma_show(m, vma); +} + static void *nommu_vma_list_start(struct seq_file *m, loff_t *_pos) { struct rb_node *_rb; diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 4616ed5..091aa8e 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -138,25 +138,63 @@ out: } /* - * Albert D. Cahalan suggested to fake entries for the traditional - * sections here. This might be worth investigating. + * display mapping lines for a particular process's /proc/pid/maps */ -static int show_map(struct seq_file *m, void *v) +static int show_map(struct seq_file *m, void *_vml) { - return 0; + struct vm_list_struct *vml = _vml; + return nommu_vma_show(m, vml->vma); } + static void *m_start(struct seq_file *m, loff_t *pos) { + struct proc_maps_private *priv = m->private; + struct vm_list_struct *vml; + struct mm_struct *mm; + loff_t n = *pos; + + /* pin the task and mm whilst we play with them */ + priv->task = get_pid_task(priv->pid, PIDTYPE_PID); + if (!priv->task) + return NULL; + + mm = get_task_mm(priv->task); + if (!mm) { + put_task_struct(priv->task); + priv->task = NULL; + return NULL; + } + + down_read(&mm->mmap_sem); + + /* start from the Nth VMA */ + for (vml = mm->context.vmlist; vml; vml = vml->next) + if (n-- == 0) + return vml; return NULL; } -static void m_stop(struct seq_file *m, void *v) + +static void m_stop(struct seq_file *m, void *_vml) { + struct proc_maps_private *priv = m->private; + + if (priv->task) { + struct mm_struct *mm = priv->task->mm; + up_read(&mm->mmap_sem); + mmput(mm); + put_task_struct(priv->task); + } } -static void *m_next(struct seq_file *m, void *v, loff_t *pos) + +static void *m_next(struct seq_file *m, void *_vml, loff_t *pos) { - return NULL; + struct vm_list_struct *vml = _vml; + + (*pos)++; + return vml ? vml->next : NULL; } -static struct seq_operations proc_pid_maps_op = { + +static struct seq_operations proc_pid_maps_ops = { .start = m_start, .next = m_next, .stop = m_stop, @@ -165,11 +203,19 @@ static struct seq_operations proc_pid_maps_op = { static int maps_open(struct inode *inode, struct file *file) { - int ret; - ret = seq_open(file, &proc_pid_maps_op); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = NULL; + struct proc_maps_private *priv; + int ret = -ENOMEM; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (priv) { + priv->pid = proc_pid(inode); + ret = seq_open(file, &proc_pid_maps_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = priv; + } else { + kfree(priv); + } } return ret; } @@ -178,6 +224,6 @@ struct file_operations proc_maps_operations = { .open = maps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; -- cgit v1.1 From f269fdd1829acc5e53bf57b145003e5733133f2b Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 27 Sep 2006 01:50:23 -0700 Subject: [PATCH] NOMMU: move the fallback arch_vma_name() to a sensible place Move the fallback arch_vma_name() to a sensible place (kernel/signal.c). Currently it's in fs/proc/task_mmu.c, a file that is dependent on both CONFIG_PROC_FS and CONFIG_MMU being enabled, but it's used from kernel/signal.c from where it is called unconditionally. [akpm@osdl.org: build fix] Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'fs') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 0a163a4..6b769af 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -122,11 +122,6 @@ struct mem_size_stats unsigned long private_dirty; }; -__attribute__((weak)) const char *arch_vma_name(struct vm_area_struct *vma) -{ - return NULL; -} - static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats *mss) { struct proc_maps_private *priv = m->private; -- cgit v1.1 From bcdc5e019d9f525a9f181a7de642d3a9c27c7610 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Wed, 27 Sep 2006 01:50:44 -0700 Subject: [PATCH] autofs4 needs to force fail return revalidate For a long time now I have had a problem with not being able to return a lookup failure on an existsing directory. In autofs this corresponds to a mount failure on a autofs managed mount entry that is browsable (and so the mount point directory exists). While this problem has been present for a long time I've avoided resolving it because it was not very visible. But now that autofs v5 has "mount and expire on demand" of nested multiple mounts, such as is found when mounting an export list from a server, solving the problem cannot be avoided any longer. I've tried very hard to find a way to do this entirely within the autofs4 module but have not been able to find a satisfactory way to achieve it. So, I need to propose a change to the VFS. Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/autofs4/root.c | 38 ++++++++++++++++++++++++++++++-------- fs/namei.c | 50 +++++++++++++++++++++++++++++++++++--------------- 2 files changed, 65 insertions(+), 23 deletions(-) (limited to 'fs') diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 5100f984..27e17f9 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -137,7 +137,9 @@ static int autofs4_dir_open(struct inode *inode, struct file *file) nd.flags = LOOKUP_DIRECTORY; ret = (dentry->d_op->d_revalidate)(dentry, &nd); - if (!ret) { + if (ret <= 0) { + if (ret < 0) + status = ret; dcache_dir_close(inode, file); goto out; } @@ -400,13 +402,23 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd) struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb); int oz_mode = autofs4_oz_mode(sbi); int flags = nd ? nd->flags : 0; - int status = 0; + int status = 1; /* Pending dentry */ if (autofs4_ispending(dentry)) { - if (!oz_mode) - status = try_to_fill_dentry(dentry, flags); - return !status; + /* The daemon never causes a mount to trigger */ + if (oz_mode) + return 1; + + /* + * A zero status is success otherwise we have a + * negative error code. + */ + status = try_to_fill_dentry(dentry, flags); + if (status == 0) + return 1; + + return status; } /* Negative dentry.. invalidate if "old" */ @@ -421,9 +433,19 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd) DPRINTK("dentry=%p %.*s, emptydir", dentry, dentry->d_name.len, dentry->d_name.name); spin_unlock(&dcache_lock); - if (!oz_mode) - status = try_to_fill_dentry(dentry, flags); - return !status; + /* The daemon never causes a mount to trigger */ + if (oz_mode) + return 1; + + /* + * A zero status is success otherwise we have a + * negative error code. + */ + status = try_to_fill_dentry(dentry, flags); + if (status == 0) + return 1; + + return status; } spin_unlock(&dcache_lock); diff --git a/fs/namei.c b/fs/namei.c index 6b591c0..808e4ea 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -372,6 +372,30 @@ void release_open_intent(struct nameidata *nd) fput(nd->intent.open.file); } +static inline struct dentry * +do_revalidate(struct dentry *dentry, struct nameidata *nd) +{ + int status = dentry->d_op->d_revalidate(dentry, nd); + if (unlikely(status <= 0)) { + /* + * The dentry failed validation. + * If d_revalidate returned 0 attempt to invalidate + * the dentry otherwise d_revalidate is asking us + * to return a fail status. + */ + if (!status) { + if (!d_invalidate(dentry)) { + dput(dentry); + dentry = NULL; + } + } else { + dput(dentry); + dentry = ERR_PTR(status); + } + } + return dentry; +} + /* * Internal lookup() using the new generic dcache. * SMP-safe @@ -386,12 +410,9 @@ static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name, if (!dentry) dentry = d_lookup(parent, name); - if (dentry && dentry->d_op && dentry->d_op->d_revalidate) { - if (!dentry->d_op->d_revalidate(dentry, nd) && !d_invalidate(dentry)) { - dput(dentry); - dentry = NULL; - } - } + if (dentry && dentry->d_op && dentry->d_op->d_revalidate) + dentry = do_revalidate(dentry, nd); + return dentry; } @@ -484,10 +505,9 @@ static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, s */ mutex_unlock(&dir->i_mutex); if (result->d_op && result->d_op->d_revalidate) { - if (!result->d_op->d_revalidate(result, nd) && !d_invalidate(result)) { - dput(result); + result = do_revalidate(result, nd); + if (!result) result = ERR_PTR(-ENOENT); - } } return result; } @@ -767,12 +787,12 @@ need_lookup: goto done; need_revalidate: - if (dentry->d_op->d_revalidate(dentry, nd)) - goto done; - if (d_invalidate(dentry)) - goto done; - dput(dentry); - goto need_lookup; + dentry = do_revalidate(dentry, nd); + if (!dentry) + goto need_lookup; + if (IS_ERR(dentry)) + goto fail; + goto done; fail: return PTR_ERR(dentry); -- cgit v1.1 From 6a1d9805ec506d8b9d04450997707da5f643d87c Mon Sep 17 00:00:00 2001 From: OGAWA Hirofumi Date: Wed, 27 Sep 2006 01:50:45 -0700 Subject: [PATCH] fat: cleanup fat_get_block(s) get_blocks() was removed. So, this removes it on fat, and will take advantage of the multi block mapping. Signed-off-by: OGAWA Hirofumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fat/inode.c | 29 ++++++++++++----------------- 1 file changed, 12 insertions(+), 17 deletions(-) (limited to 'fs') diff --git a/fs/fat/inode.c b/fs/fat/inode.c index d301511..e1035a5 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -50,14 +50,14 @@ static int fat_add_cluster(struct inode *inode) return err; } -static int __fat_get_blocks(struct inode *inode, sector_t iblock, - unsigned long *max_blocks, - struct buffer_head *bh_result, int create) +static inline int __fat_get_block(struct inode *inode, sector_t iblock, + unsigned long *max_blocks, + struct buffer_head *bh_result, int create) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); - sector_t phys; unsigned long mapped_blocks; + sector_t phys; int err, offset; err = fat_bmap(inode, iblock, &phys, &mapped_blocks); @@ -73,7 +73,7 @@ static int __fat_get_blocks(struct inode *inode, sector_t iblock, if (iblock != MSDOS_I(inode)->mmu_private >> sb->s_blocksize_bits) { fat_fs_panic(sb, "corrupted file size (i_pos %lld, %lld)", - MSDOS_I(inode)->i_pos, MSDOS_I(inode)->mmu_private); + MSDOS_I(inode)->i_pos, MSDOS_I(inode)->mmu_private); return -EIO; } @@ -93,34 +93,29 @@ static int __fat_get_blocks(struct inode *inode, sector_t iblock, err = fat_bmap(inode, iblock, &phys, &mapped_blocks); if (err) return err; + BUG_ON(!phys); BUG_ON(*max_blocks != mapped_blocks); set_buffer_new(bh_result); map_bh(bh_result, sb, phys); + return 0; } -static int fat_get_blocks(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) +static int fat_get_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) { struct super_block *sb = inode->i_sb; - int err; unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; + int err; - err = __fat_get_blocks(inode, iblock, &max_blocks, bh_result, create); + err = __fat_get_block(inode, iblock, &max_blocks, bh_result, create); if (err) return err; bh_result->b_size = max_blocks << sb->s_blocksize_bits; return 0; } -static int fat_get_block(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) -{ - unsigned long max_blocks = 1; - return __fat_get_blocks(inode, iblock, &max_blocks, bh_result, create); -} - static int fat_writepage(struct page *page, struct writeback_control *wbc) { return block_write_full_page(page, fat_get_block, wbc); @@ -188,7 +183,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, * condition of fat_get_block() and ->truncate(). */ return blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, - offset, nr_segs, fat_get_blocks, NULL); + offset, nr_segs, fat_get_block, NULL); } static sector_t _fat_bmap(struct address_space *mapping, sector_t block) -- cgit v1.1 From 8e18e2941c53416aa219708e7dcad21fb4bd6794 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:46 -0700 Subject: [PATCH] inode_diet: Replace inode.u.generic_ip with inode.i_private The following patches reduce the size of the VFS inode structure by 28 bytes on a UP x86. (It would be more on an x86_64 system). This is a 10% reduction in the inode size on a UP kernel that is configured in a production mode (i.e., with no spinlock or other debugging functions enabled; if you want to save memory taken up by in-core inodes, the first thing you should do is disable the debugging options; they are responsible for a huge amount of bloat in the VFS inode structure). This patch: The filesystem or device-specific pointer in the inode is inside a union, which is pretty pointless given that all 30+ users of this field have been using the void pointer. Get rid of the union and rename it to i_private, with a comment to explain who is allowed to use the void pointer. This is just a cleanup, but it allows us to reuse the union 'u' for something something where the union will actually be used. [judith@osdl.org: powerpc build fix] Signed-off-by: "Theodore Ts'o" Signed-off-by: Judith Lebzelter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/autofs/inode.c | 2 +- fs/autofs/symlink.c | 2 +- fs/binfmt_misc.c | 8 ++++---- fs/debugfs/file.c | 4 ++-- fs/debugfs/inode.c | 4 ++-- fs/devpts/inode.c | 4 ++-- fs/freevxfs/vxfs.h | 2 +- fs/freevxfs/vxfs_inode.c | 4 ++-- fs/fuse/control.c | 6 +++--- fs/inode.c | 2 +- fs/jffs/inode-v23.c | 34 +++++++++++++++++----------------- fs/libfs.c | 2 +- fs/ocfs2/dlmglue.c | 2 +- 13 files changed, 38 insertions(+), 38 deletions(-) (limited to 'fs') diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index c81d6b8..d39d2ac 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -241,7 +241,7 @@ static void autofs_read_inode(struct inode *inode) inode->i_op = &autofs_symlink_inode_operations; sl = &sbi->symlink[n]; - inode->u.generic_ip = sl; + inode->i_private = sl; inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_mtime.tv_sec = inode->i_ctime.tv_sec = sl->mtime; inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = 0; diff --git a/fs/autofs/symlink.c b/fs/autofs/symlink.c index 52e8772..c74f2eb 100644 --- a/fs/autofs/symlink.c +++ b/fs/autofs/symlink.c @@ -15,7 +15,7 @@ /* Nothing to release.. */ static void *autofs_follow_link(struct dentry *dentry, struct nameidata *nd) { - char *s=((struct autofs_symlink *)dentry->d_inode->u.generic_ip)->data; + char *s=((struct autofs_symlink *)dentry->d_inode->i_private)->data; nd_set_link(nd, s); return NULL; } diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 34ebbc1..6759b98 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -517,7 +517,7 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) static void bm_clear_inode(struct inode *inode) { - kfree(inode->u.generic_ip); + kfree(inode->i_private); } static void kill_node(Node *e) @@ -545,7 +545,7 @@ static void kill_node(Node *e) static ssize_t bm_entry_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos) { - Node *e = file->f_dentry->d_inode->u.generic_ip; + Node *e = file->f_dentry->d_inode->i_private; loff_t pos = *ppos; ssize_t res; char *page; @@ -579,7 +579,7 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct dentry *root; - Node *e = file->f_dentry->d_inode->u.generic_ip; + Node *e = file->f_dentry->d_inode->i_private; int res = parse_command(buffer, count); switch (res) { @@ -646,7 +646,7 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer, } e->dentry = dget(dentry); - inode->u.generic_ip = e; + inode->i_private = e; inode->i_fop = &bm_entry_operations; d_instantiate(dentry, inode); diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index e4b4305..bf3901a 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -32,8 +32,8 @@ static ssize_t default_write_file(struct file *file, const char __user *buf, static int default_open(struct inode *inode, struct file *file) { - if (inode->u.generic_ip) - file->private_data = inode->u.generic_ip; + if (inode->i_private) + file->private_data = inode->i_private; return 0; } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 3ca268d..717f4821 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -168,7 +168,7 @@ static int debugfs_create_by_name(const char *name, mode_t mode, * directory dentry if set. If this paramater is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later - * on. The inode.u.generic_ip pointer will point to this value on + * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. @@ -209,7 +209,7 @@ struct dentry *debugfs_create_file(const char *name, mode_t mode, if (dentry->d_inode) { if (data) - dentry->d_inode->u.generic_ip = data; + dentry->d_inode->i_private = data; if (fops) dentry->d_inode->i_fop = fops; } diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index f7aef5b..5bf06a1 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -177,7 +177,7 @@ int devpts_pty_new(struct tty_struct *tty) inode->i_gid = config.setgid ? config.gid : current->fsgid; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; init_special_inode(inode, S_IFCHR|config.mode, device); - inode->u.generic_ip = tty; + inode->i_private = tty; dentry = get_node(number); if (!IS_ERR(dentry) && !dentry->d_inode) @@ -196,7 +196,7 @@ struct tty_struct *devpts_get_tty(int number) tty = NULL; if (!IS_ERR(dentry)) { if (dentry->d_inode) - tty = dentry->d_inode->u.generic_ip; + tty = dentry->d_inode->i_private; dput(dentry); } diff --git a/fs/freevxfs/vxfs.h b/fs/freevxfs/vxfs.h index d35979a..c8a9265 100644 --- a/fs/freevxfs/vxfs.h +++ b/fs/freevxfs/vxfs.h @@ -252,7 +252,7 @@ enum { * Get filesystem private data from VFS inode. */ #define VXFS_INO(ip) \ - ((struct vxfs_inode_info *)(ip)->u.generic_ip) + ((struct vxfs_inode_info *)(ip)->i_private) /* * Get filesystem private data from VFS superblock. diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index ca6a397..32a82ed 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -243,7 +243,7 @@ vxfs_iinit(struct inode *ip, struct vxfs_inode_info *vip) ip->i_blocks = vip->vii_blocks; ip->i_generation = vip->vii_gen; - ip->u.generic_ip = (void *)vip; + ip->i_private = vip; } @@ -338,5 +338,5 @@ vxfs_read_inode(struct inode *ip) void vxfs_clear_inode(struct inode *ip) { - kmem_cache_free(vxfs_inode_cachep, ip->u.generic_ip); + kmem_cache_free(vxfs_inode_cachep, ip->i_private); } diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 46fe60b..79ec1f2 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -23,7 +23,7 @@ static struct fuse_conn *fuse_ctl_file_conn_get(struct file *file) { struct fuse_conn *fc; mutex_lock(&fuse_mutex); - fc = file->f_dentry->d_inode->u.generic_ip; + fc = file->f_dentry->d_inode->i_private; if (fc) fc = fuse_conn_get(fc); mutex_unlock(&fuse_mutex); @@ -98,7 +98,7 @@ static struct dentry *fuse_ctl_add_dentry(struct dentry *parent, inode->i_op = iop; inode->i_fop = fop; inode->i_nlink = nlink; - inode->u.generic_ip = fc; + inode->i_private = fc; d_add(dentry, inode); return dentry; } @@ -150,7 +150,7 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc) for (i = fc->ctl_ndents - 1; i >= 0; i--) { struct dentry *dentry = fc->ctl_dentry[i]; - dentry->d_inode->u.generic_ip = NULL; + dentry->d_inode->i_private = NULL; d_drop(dentry); dput(dentry); } diff --git a/fs/inode.c b/fs/inode.c index 0bf9f04..77e2547 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -163,7 +163,7 @@ static struct inode *alloc_inode(struct super_block *sb) bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info; mapping->backing_dev_info = bdi; } - memset(&inode->u, 0, sizeof(inode->u)); + inode->i_private = 0; inode->i_mapping = mapping; } return inode; diff --git a/fs/jffs/inode-v23.c b/fs/jffs/inode-v23.c index b59553d..7358ef8 100644 --- a/fs/jffs/inode-v23.c +++ b/fs/jffs/inode-v23.c @@ -369,7 +369,7 @@ jffs_new_inode(const struct inode * dir, struct jffs_raw_inode *raw_inode, f = jffs_find_file(c, raw_inode->ino); - inode->u.generic_ip = (void *)f; + inode->i_private = (void *)f; insert_inode_hash(inode); return inode; @@ -442,7 +442,7 @@ jffs_rename(struct inode *old_dir, struct dentry *old_dentry, }); result = -ENOTDIR; - if (!(old_dir_f = (struct jffs_file *)old_dir->u.generic_ip)) { + if (!(old_dir_f = old_dir->i_private)) { D(printk("jffs_rename(): Old dir invalid.\n")); goto jffs_rename_end; } @@ -456,7 +456,7 @@ jffs_rename(struct inode *old_dir, struct dentry *old_dentry, /* Find the new directory. */ result = -ENOTDIR; - if (!(new_dir_f = (struct jffs_file *)new_dir->u.generic_ip)) { + if (!(new_dir_f = new_dir->i_private)) { D(printk("jffs_rename(): New dir invalid.\n")); goto jffs_rename_end; } @@ -593,7 +593,7 @@ jffs_readdir(struct file *filp, void *dirent, filldir_t filldir) } else { ddino = ((struct jffs_file *) - inode->u.generic_ip)->pino; + inode->i_private)->pino; } D3(printk("jffs_readdir(): \"..\" %u\n", ddino)); if (filldir(dirent, "..", 2, filp->f_pos, ddino, DT_DIR) < 0) { @@ -604,7 +604,7 @@ jffs_readdir(struct file *filp, void *dirent, filldir_t filldir) } filp->f_pos++; } - f = ((struct jffs_file *)inode->u.generic_ip)->children; + f = ((struct jffs_file *)inode->i_private)->children; j = 2; while(f && (f->deleted || j++ < filp->f_pos )) { @@ -668,7 +668,7 @@ jffs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) } r = -EACCES; - if (!(d = (struct jffs_file *)dir->u.generic_ip)) { + if (!(d = (struct jffs_file *)dir->i_private)) { D(printk("jffs_lookup(): No such inode! (%lu)\n", dir->i_ino)); goto jffs_lookup_end; @@ -739,7 +739,7 @@ jffs_do_readpage_nolock(struct file *file, struct page *page) unsigned long read_len; int result; struct inode *inode = (struct inode*)page->mapping->host; - struct jffs_file *f = (struct jffs_file *)inode->u.generic_ip; + struct jffs_file *f = (struct jffs_file *)inode->i_private; struct jffs_control *c = (struct jffs_control *)inode->i_sb->s_fs_info; int r; loff_t offset; @@ -828,7 +828,7 @@ jffs_mkdir(struct inode *dir, struct dentry *dentry, int mode) }); lock_kernel(); - dir_f = (struct jffs_file *)dir->u.generic_ip; + dir_f = dir->i_private; ASSERT(if (!dir_f) { printk(KERN_ERR "jffs_mkdir(): No reference to a " @@ -972,7 +972,7 @@ jffs_remove(struct inode *dir, struct dentry *dentry, int type) kfree(_name); }); - dir_f = (struct jffs_file *) dir->u.generic_ip; + dir_f = dir->i_private; c = dir_f->c; result = -ENOENT; @@ -1082,7 +1082,7 @@ jffs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t rdev) if (!old_valid_dev(rdev)) return -EINVAL; lock_kernel(); - dir_f = (struct jffs_file *)dir->u.generic_ip; + dir_f = dir->i_private; c = dir_f->c; D3(printk (KERN_NOTICE "mknod(): down biglock\n")); @@ -1186,7 +1186,7 @@ jffs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) kfree(_symname); }); - dir_f = (struct jffs_file *)dir->u.generic_ip; + dir_f = dir->i_private; ASSERT(if (!dir_f) { printk(KERN_ERR "jffs_symlink(): No reference to a " "jffs_file struct in inode.\n"); @@ -1289,7 +1289,7 @@ jffs_create(struct inode *dir, struct dentry *dentry, int mode, kfree(s); }); - dir_f = (struct jffs_file *)dir->u.generic_ip; + dir_f = dir->i_private; ASSERT(if (!dir_f) { printk(KERN_ERR "jffs_create(): No reference to a " "jffs_file struct in inode.\n"); @@ -1403,9 +1403,9 @@ jffs_file_write(struct file *filp, const char *buf, size_t count, goto out_isem; } - if (!(f = (struct jffs_file *)inode->u.generic_ip)) { - D(printk("jffs_file_write(): inode->u.generic_ip = 0x%p\n", - inode->u.generic_ip)); + if (!(f = inode->i_private)) { + D(printk("jffs_file_write(): inode->i_private = 0x%p\n", + inode->i_private)); goto out_isem; } @@ -1693,7 +1693,7 @@ jffs_read_inode(struct inode *inode) mutex_unlock(&c->fmc->biglock); return; } - inode->u.generic_ip = (void *)f; + inode->i_private = f; inode->i_mode = f->mode; inode->i_nlink = f->nlink; inode->i_uid = f->uid; @@ -1748,7 +1748,7 @@ jffs_delete_inode(struct inode *inode) lock_kernel(); inode->i_size = 0; inode->i_blocks = 0; - inode->u.generic_ip = NULL; + inode->i_private = NULL; clear_inode(inode); if (inode->i_nlink == 0) { c = (struct jffs_control *) inode->i_sb->s_fs_info; diff --git a/fs/libfs.c b/fs/libfs.c index ac02ea6..2751793 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -547,7 +547,7 @@ int simple_attr_open(struct inode *inode, struct file *file, attr->get = get; attr->set = set; - attr->data = inode->u.generic_ip; + attr->data = inode->i_private; attr->fmt = fmt; mutex_init(&attr->mutex); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index de88706..8801e41 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2052,7 +2052,7 @@ static int ocfs2_dlm_debug_open(struct inode *inode, struct file *file) mlog_errno(ret); goto out; } - osb = (struct ocfs2_super *) inode->u.generic_ip; + osb = inode->i_private; ocfs2_get_dlm_debug(osb->osb_dlm_debug); priv->p_dlm_debug = osb->osb_dlm_debug; INIT_LIST_HEAD(&priv->p_iter_res.l_debug_list); -- cgit v1.1 From eaf796e7ef6014f208c409b2b14fddcfaafe7e3a Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:48 -0700 Subject: [PATCH] inode-diet: Move i_bdev into a union Move the i_bdev pointer in struct inode into a union. Signed-off-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/inode.c b/fs/inode.c index 77e2547..41b4622 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -254,7 +254,7 @@ void clear_inode(struct inode *inode) DQUOT_DROP(inode); if (inode->i_sb && inode->i_sb->s_op->clear_inode) inode->i_sb->s_op->clear_inode(inode); - if (inode->i_bdev) + if (S_ISBLK(inode->i_mode) && inode->i_bdev) bd_forget(inode); if (inode->i_cdev) cd_forget(inode); -- cgit v1.1 From 577c4eb09d1034d0739e3135fd2cff50588024be Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:49 -0700 Subject: [PATCH] inode-diet: Move i_cdev into a union Move the i_cdev pointer in struct inode into a union. Signed-off-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/file_table.c | 2 +- fs/inode.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/file_table.c b/fs/file_table.c index 0131ba0..bc35a40 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -169,7 +169,7 @@ void fastcall __fput(struct file *file) if (file->f_op && file->f_op->release) file->f_op->release(inode, file); security_file_free(file); - if (unlikely(inode->i_cdev != NULL)) + if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL)) cdev_put(inode->i_cdev); fops_put(file->f_op); if (file->f_mode & FMODE_WRITE) diff --git a/fs/inode.c b/fs/inode.c index 41b4622..f5c04dd 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -256,7 +256,7 @@ void clear_inode(struct inode *inode) inode->i_sb->s_op->clear_inode(inode); if (S_ISBLK(inode->i_mode) && inode->i_bdev) bd_forget(inode); - if (inode->i_cdev) + if (S_ISCHR(inode->i_mode) && inode->i_cdev) cd_forget(inode); inode->i_state = I_CLEAR; } -- cgit v1.1 From ba52de123d454b57369f291348266d86f4b35070 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:49 -0700 Subject: [PATCH] inode-diet: Eliminate i_blksize from the inode structure This eliminates the i_blksize field from struct inode. Filesystems that want to provide a per-inode st_blksize can do so by providing their own getattr routine instead of using the generic_fillattr() function. Note that some filesystems were providing pretty much random (and incorrect) values for i_blksize. [bunk@stusta.de: cleanup] [akpm@osdl.org: generic_fillattr() fix] Signed-off-by: "Theodore Ts'o" Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/9p/vfs_inode.c | 4 +--- fs/adfs/inode.c | 1 - fs/afs/inode.c | 1 - fs/autofs/inode.c | 1 - fs/autofs4/inode.c | 1 - fs/befs/linuxvfs.c | 1 - fs/bfs/dir.c | 2 +- fs/bfs/inode.c | 1 - fs/binfmt_misc.c | 1 - fs/cifs/cifsfs.c | 1 - fs/cifs/readdir.c | 5 ++--- fs/coda/coda_linux.c | 2 -- fs/configfs/inode.c | 1 - fs/cramfs/inode.c | 1 - fs/debugfs/inode.c | 1 - fs/devpts/inode.c | 2 -- fs/eventpoll.c | 1 - fs/ext2/ialloc.c | 1 - fs/ext2/inode.c | 1 - fs/ext3/ialloc.c | 1 - fs/ext3/inode.c | 3 --- fs/fat/inode.c | 3 --- fs/freevxfs/vxfs_inode.c | 1 - fs/fuse/inode.c | 1 - fs/hfs/inode.c | 2 -- fs/hfsplus/inode.c | 2 -- fs/hostfs/hostfs_kern.c | 1 - fs/hpfs/inode.c | 1 - fs/hppfs/hppfs_kern.c | 1 - fs/hugetlbfs/inode.c | 1 - fs/isofs/inode.c | 3 +-- fs/jffs/inode-v23.c | 2 -- fs/jffs2/fs.c | 2 -- fs/jfs/jfs_extent.c | 2 +- fs/jfs/jfs_imap.c | 1 - fs/jfs/jfs_inode.c | 1 - fs/jfs/jfs_metapage.c | 2 +- fs/libfs.c | 2 -- fs/minix/bitmap.c | 2 +- fs/minix/inode.c | 4 ++-- fs/ncpfs/inode.c | 1 - fs/nfs/inode.c | 4 ---- fs/ntfs/inode.c | 4 ---- fs/ntfs/mft.c | 5 ----- fs/ocfs2/dlm/dlmfs.c | 2 -- fs/ocfs2/inode.c | 4 ---- fs/pipe.c | 1 - fs/qnx4/inode.c | 1 - fs/ramfs/inode.c | 1 - fs/reiserfs/inode.c | 4 ---- fs/smbfs/inode.c | 2 -- fs/smbfs/proc.c | 1 - fs/stat.c | 3 ++- fs/sysfs/inode.c | 1 - fs/sysv/ialloc.c | 2 +- fs/sysv/inode.c | 2 +- fs/udf/ialloc.c | 1 - fs/udf/inode.c | 2 -- fs/ufs/ialloc.c | 1 - fs/ufs/inode.c | 1 - fs/xfs/linux-2.6/xfs_super.c | 1 - fs/xfs/linux-2.6/xfs_vnode.c | 1 - 62 files changed, 14 insertions(+), 98 deletions(-) (limited to 'fs') diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index eae50c9..7a7ec2d 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -204,7 +204,6 @@ struct inode *v9fs_get_inode(struct super_block *sb, int mode) inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = sb->s_blocksize; inode->i_blocks = 0; inode->i_rdev = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; @@ -950,9 +949,8 @@ v9fs_stat2inode(struct v9fs_stat *stat, struct inode *inode, inode->i_size = stat->length; - inode->i_blksize = sb->s_blocksize; inode->i_blocks = - (inode->i_size + inode->i_blksize - 1) >> sb->s_blocksize_bits; + (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; } /** diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 534f3ee..7e7a04b 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -269,7 +269,6 @@ adfs_iget(struct super_block *sb, struct object_info *obj) inode->i_ino = obj->file_id; inode->i_size = obj->size; inode->i_nlink = 2; - inode->i_blksize = PAGE_SIZE; inode->i_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 4ebb30a..6f37754 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -72,7 +72,6 @@ static int afs_inode_map_status(struct afs_vnode *vnode) inode->i_ctime.tv_sec = vnode->status.mtime_server; inode->i_ctime.tv_nsec = 0; inode->i_atime = inode->i_mtime = inode->i_ctime; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_version = vnode->fid.unique; inode->i_mapping->a_ops = &afs_fs_aops; diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index d39d2ac..2c9759ba 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -216,7 +216,6 @@ static void autofs_read_inode(struct inode *inode) inode->i_nlink = 2; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; inode->i_blocks = 0; - inode->i_blksize = 1024; if ( ino == AUTOFS_ROOT_INO ) { inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR; diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index 11a6a9a..800ce87 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -447,7 +447,6 @@ struct inode *autofs4_get_inode(struct super_block *sb, inode->i_uid = 0; inode->i_gid = 0; } - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index f6676fb..57020c7 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -365,7 +365,6 @@ befs_read_inode(struct inode *inode) inode->i_mtime.tv_nsec = 0; /* lower 16 bits are not a time */ inode->i_ctime = inode->i_mtime; inode->i_atime = inode->i_mtime; - inode->i_blksize = befs_sb->block_size; befs_ino->i_inode_num = fsrun_to_cpu(sb, raw_inode->inode_num); befs_ino->i_parent = fsrun_to_cpu(sb, raw_inode->parent); diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index 26fad96..dcf04cb 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -102,7 +102,7 @@ static int bfs_create(struct inode * dir, struct dentry * dentry, int mode, inode->i_uid = current->fsuid; inode->i_gid = (dir->i_mode & S_ISGID) ? dir->i_gid : current->fsgid; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; inode->i_op = &bfs_file_inops; inode->i_fop = &bfs_file_operations; inode->i_mapping->a_ops = &bfs_aops; diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 8fc2e8e..ed27ffb 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -76,7 +76,6 @@ static void bfs_read_inode(struct inode * inode) inode->i_size = BFS_FILESIZE(di); inode->i_blocks = BFS_FILEBLOCKS(di); if (inode->i_size || inode->i_blocks) dprintf("Registered inode with %lld size, %ld blocks\n", inode->i_size, inode->i_blocks); - inode->i_blksize = PAGE_SIZE; inode->i_atime.tv_sec = le32_to_cpu(di->i_atime); inode->i_mtime.tv_sec = le32_to_cpu(di->i_mtime); inode->i_ctime.tv_sec = le32_to_cpu(di->i_ctime); diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 6759b98..66ba137 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -507,7 +507,6 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) inode->i_mode = mode; inode->i_uid = 0; inode->i_gid = 0; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = current_fs_time(inode->i_sb); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 4197a50..22bcf4d 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -253,7 +253,6 @@ cifs_alloc_inode(struct super_block *sb) file data or metadata */ cifs_inode->clientCanCacheRead = FALSE; cifs_inode->clientCanCacheAll = FALSE; - cifs_inode->vfs_inode.i_blksize = CIFS_MAX_MSGSIZE; cifs_inode->vfs_inode.i_blkbits = 14; /* 2**14 = CIFS_MAX_MSGSIZE */ cifs_inode->vfs_inode.i_flags = S_NOATIME | S_NOCMTIME; INIT_LIST_HEAD(&cifs_inode->openFileList); diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 9aeb58a..b27b345 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -216,10 +216,9 @@ static void fill_in_inode(struct inode *tmp_inode, int new_buf_type, if (allocation_size < end_of_file) cFYI(1, ("May be sparse file, allocation less than file size")); - cFYI(1, ("File Size %ld and blocks %llu and blocksize %ld", + cFYI(1, ("File Size %ld and blocks %llu", (unsigned long)tmp_inode->i_size, - (unsigned long long)tmp_inode->i_blocks, - tmp_inode->i_blksize)); + (unsigned long long)tmp_inode->i_blocks)); if (S_ISREG(tmp_inode->i_mode)) { cFYI(1, ("File inode")); tmp_inode->i_op = &cifs_file_inode_ops; diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c index 5597080..95a5425 100644 --- a/fs/coda/coda_linux.c +++ b/fs/coda/coda_linux.c @@ -110,8 +110,6 @@ void coda_vattr_to_iattr(struct inode *inode, struct coda_vattr *attr) inode->i_nlink = attr->va_nlink; if (attr->va_size != -1) inode->i_size = attr->va_size; - if (attr->va_blocksize != -1) - inode->i_blksize = attr->va_blocksize; if (attr->va_size != -1) inode->i_blocks = (attr->va_size + 511) >> 9; if (attr->va_atime.tv_sec != -1) diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index 5047e6a..fb18917 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -135,7 +135,6 @@ struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent * sd) { struct inode * inode = new_inode(configfs_sb); if (inode) { - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_mapping->a_ops = &configfs_aops; inode->i_mapping->backing_dev_info = &configfs_backing_dev_info; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index d09b677..ad96b69 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -73,7 +73,6 @@ static int cramfs_iget5_set(struct inode *inode, void *opaque) inode->i_uid = cramfs_inode->uid; inode->i_size = cramfs_inode->size; inode->i_blocks = (cramfs_inode->size - 1) / 512 + 1; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_gid = cramfs_inode->gid; /* Struct copy intentional */ inode->i_mtime = inode->i_atime = inode->i_ctime = zerotime; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 717f4821..269e649 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -40,7 +40,6 @@ static struct inode *debugfs_get_inode(struct super_block *sb, int mode, dev_t d inode->i_mode = mode; inode->i_uid = 0; inode->i_gid = 0; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 5bf06a1..5f7b5a6 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -113,7 +113,6 @@ devpts_fill_super(struct super_block *s, void *data, int silent) inode->i_ino = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; inode->i_blocks = 0; - inode->i_blksize = 1024; inode->i_uid = inode->i_gid = 0; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR; inode->i_op = &simple_dir_inode_operations; @@ -172,7 +171,6 @@ int devpts_pty_new(struct tty_struct *tty) return -ENOMEM; inode->i_ino = number+2; - inode->i_blksize = 1024; inode->i_uid = config.setuid ? config.uid : current->fsuid; inode->i_gid = config.setgid ? config.gid : current->fsgid; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 3a35674..8d54433 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1590,7 +1590,6 @@ static struct inode *ep_eventpoll_inode(void) inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - inode->i_blksize = PAGE_SIZE; return inode; eexit_1: diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index 695f69c..2cb545b 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -574,7 +574,6 @@ got: inode->i_mode = mode; inode->i_ino = ino; - inode->i_blksize = PAGE_SIZE; /* This is the optimal IO size (for stat), not the fs block size */ inode->i_blocks = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; memset(ei->i_data, 0, sizeof(ei->i_data)); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index fb4d322..dd4e14c 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1094,7 +1094,6 @@ void ext2_read_inode (struct inode * inode) brelse (bh); goto bad_inode; } - inode->i_blksize = PAGE_SIZE; /* This is the optimal IO size (for stat), not the fs block size */ inode->i_blocks = le32_to_cpu(raw_inode->i_blocks); ei->i_flags = le32_to_cpu(raw_inode->i_flags); ei->i_faddr = le32_to_cpu(raw_inode->i_faddr); diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c index 1e4ded8..e45dbd6 100644 --- a/fs/ext3/ialloc.c +++ b/fs/ext3/ialloc.c @@ -559,7 +559,6 @@ got: inode->i_ino = ino; /* This is the optimal IO size (for stat), not the fs block size */ - inode->i_blksize = PAGE_SIZE; inode->i_blocks = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index c9fc15f..dcf4f1d 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -2632,9 +2632,6 @@ void ext3_read_inode(struct inode * inode) * recovery code: that's fine, we're about to complete * the process of deleting those. */ } - inode->i_blksize = PAGE_SIZE; /* This is the optimal IO size - * (for stat), not the fs block - * size */ inode->i_blocks = le32_to_cpu(raw_inode->i_blocks); ei->i_flags = le32_to_cpu(raw_inode->i_flags); #ifdef EXT3_FRAGMENTS diff --git a/fs/fat/inode.c b/fs/fat/inode.c index e1035a5..ab96ae8 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -370,8 +370,6 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) inode->i_flags |= S_IMMUTABLE; } MSDOS_I(inode)->i_attrs = de->attr & ATTR_UNUSED; - /* this is as close to the truth as we can get ... */ - inode->i_blksize = sbi->cluster_size; inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) & ~((loff_t)sbi->cluster_size - 1)) >> 9; inode->i_mtime.tv_sec = @@ -1131,7 +1129,6 @@ static int fat_read_root(struct inode *inode) MSDOS_I(inode)->i_start = 0; inode->i_size = sbi->dir_entries * sizeof(struct msdos_dir_entry); } - inode->i_blksize = sbi->cluster_size; inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) & ~((loff_t)sbi->cluster_size - 1)) >> 9; MSDOS_I(inode)->i_logstart = 0; diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index 32a82ed..4786d51 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -239,7 +239,6 @@ vxfs_iinit(struct inode *ip, struct vxfs_inode_info *vip) ip->i_ctime.tv_nsec = 0; ip->i_mtime.tv_nsec = 0; - ip->i_blksize = PAGE_SIZE; ip->i_blocks = vip->vii_blocks; ip->i_generation = vip->vii_gen; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 7d25092..cb7cadb 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -118,7 +118,6 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr) inode->i_uid = attr->uid; inode->i_gid = attr->gid; i_size_write(inode, attr->size); - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = attr->blocks; inode->i_atime.tv_sec = attr->atime; inode->i_atime.tv_nsec = attr->atimensec; diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 315cf44..d05641c 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -154,7 +154,6 @@ struct inode *hfs_new_inode(struct inode *dir, struct qstr *name, int mode) inode->i_gid = current->fsgid; inode->i_nlink = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; - inode->i_blksize = HFS_SB(sb)->alloc_blksz; HFS_I(inode)->flags = 0; HFS_I(inode)->rsrc_inode = NULL; HFS_I(inode)->fs_blocks = 0; @@ -284,7 +283,6 @@ static int hfs_read_inode(struct inode *inode, void *data) inode->i_uid = hsb->s_uid; inode->i_gid = hsb->s_gid; inode->i_nlink = 1; - inode->i_blksize = HFS_SB(inode->i_sb)->alloc_blksz; if (idata->key) HFS_I(inode)->cat_key = *idata->key; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 924ecde..0eb1a60 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -304,7 +304,6 @@ struct inode *hfsplus_new_inode(struct super_block *sb, int mode) inode->i_gid = current->fsgid; inode->i_nlink = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; - inode->i_blksize = HFSPLUS_SB(sb).alloc_blksz; INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list); init_MUTEX(&HFSPLUS_I(inode).extents_lock); atomic_set(&HFSPLUS_I(inode).opencnt, 0); @@ -407,7 +406,6 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) type = hfs_bnode_read_u16(fd->bnode, fd->entryoffset); HFSPLUS_I(inode).dev = 0; - inode->i_blksize = HFSPLUS_SB(inode->i_sb).alloc_blksz; if (type == HFSPLUS_FOLDER) { struct hfsplus_cat_folder *folder = &entry.folder; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index b82e3d9..322e876 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -156,7 +156,6 @@ static int read_name(struct inode *ino, char *name) ino->i_mode = i_mode; ino->i_nlink = i_nlink; ino->i_size = i_size; - ino->i_blksize = i_blksize; ino->i_blocks = i_blocks; return(0); } diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 56f2c33..bcf6ee3 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -17,7 +17,6 @@ void hpfs_init_inode(struct inode *i) i->i_gid = hpfs_sb(sb)->sb_gid; i->i_mode = hpfs_sb(sb)->sb_mode; hpfs_inode->i_conv = hpfs_sb(sb)->sb_conv; - i->i_blksize = 512; i->i_size = -1; i->i_blocks = -1; diff --git a/fs/hppfs/hppfs_kern.c b/fs/hppfs/hppfs_kern.c index 3a9bdf58..dcb6d2e 100644 --- a/fs/hppfs/hppfs_kern.c +++ b/fs/hppfs/hppfs_kern.c @@ -152,7 +152,6 @@ static void hppfs_read_inode(struct inode *ino) ino->i_mode = proc_ino->i_mode; ino->i_nlink = proc_ino->i_nlink; ino->i_size = proc_ino->i_size; - ino->i_blksize = proc_ino->i_blksize; ino->i_blocks = proc_ino->i_blocks; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index c3920c9..e025a31 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -357,7 +357,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, inode->i_mode = mode; inode->i_uid = uid; inode->i_gid = gid; - inode->i_blksize = HPAGE_SIZE; inode->i_blocks = 0; inode->i_mapping->a_ops = &hugetlbfs_aops; inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info; diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 10e4789..4527692 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1235,7 +1235,7 @@ static void isofs_read_inode(struct inode *inode) } inode->i_uid = sbi->s_uid; inode->i_gid = sbi->s_gid; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; ei->i_format_parm[0] = 0; ei->i_format_parm[1] = 0; @@ -1291,7 +1291,6 @@ static void isofs_read_inode(struct inode *inode) isonum_711 (de->ext_attr_length)); /* Set the number of blocks for stat() - should be done before RR */ - inode->i_blksize = PAGE_CACHE_SIZE; /* For stat() only */ inode->i_blocks = (inode->i_size + 511) >> 9; /* diff --git a/fs/jffs/inode-v23.c b/fs/jffs/inode-v23.c index 7358ef8..f5cf9c9 100644 --- a/fs/jffs/inode-v23.c +++ b/fs/jffs/inode-v23.c @@ -364,7 +364,6 @@ jffs_new_inode(const struct inode * dir, struct jffs_raw_inode *raw_inode, inode->i_ctime.tv_nsec = 0; inode->i_mtime.tv_nsec = 0; inode->i_atime.tv_nsec = 0; - inode->i_blksize = PAGE_SIZE; inode->i_blocks = (inode->i_size + 511) >> 9; f = jffs_find_file(c, raw_inode->ino); @@ -1706,7 +1705,6 @@ jffs_read_inode(struct inode *inode) inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = 0; - inode->i_blksize = PAGE_SIZE; inode->i_blocks = (inode->i_size + 511) >> 9; if (S_ISREG(inode->i_mode)) { inode->i_op = &jffs_file_inode_operations; diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 4780f82..72d9909d 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -263,7 +263,6 @@ void jffs2_read_inode (struct inode *inode) inode->i_nlink = f->inocache->nlink; - inode->i_blksize = PAGE_SIZE; inode->i_blocks = (inode->i_size + 511) >> 9; switch (inode->i_mode & S_IFMT) { @@ -449,7 +448,6 @@ struct inode *jffs2_new_inode (struct inode *dir_i, int mode, struct jffs2_raw_i inode->i_atime = inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC; ri->atime = ri->mtime = ri->ctime = cpu_to_je32(I_SEC(inode->i_mtime)); - inode->i_blksize = PAGE_SIZE; inode->i_blocks = 0; inode->i_size = 0; diff --git a/fs/jfs/jfs_extent.c b/fs/jfs/jfs_extent.c index 4d52593..4c74f09 100644 --- a/fs/jfs/jfs_extent.c +++ b/fs/jfs/jfs_extent.c @@ -468,7 +468,7 @@ int extRecord(struct inode *ip, xad_t * xp) int extFill(struct inode *ip, xad_t * xp) { int rc, nbperpage = JFS_SBI(ip->i_sb)->nbperpage; - s64 blkno = offsetXAD(xp) >> ip->i_blksize; + s64 blkno = offsetXAD(xp) >> ip->i_blkbits; // assert(ISSPARSE(ip)); diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index ccbe60a..369d7f3 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -3115,7 +3115,6 @@ static int copy_from_dinode(struct dinode * dip, struct inode *ip) ip->i_mtime.tv_nsec = le32_to_cpu(dip->di_mtime.tv_nsec); ip->i_ctime.tv_sec = le32_to_cpu(dip->di_ctime.tv_sec); ip->i_ctime.tv_nsec = le32_to_cpu(dip->di_ctime.tv_nsec); - ip->i_blksize = ip->i_sb->s_blocksize; ip->i_blocks = LBLK2PBLK(ip->i_sb, le64_to_cpu(dip->di_nblocks)); ip->i_generation = le32_to_cpu(dip->di_gen); diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c index 495df40..bffaca9 100644 --- a/fs/jfs/jfs_inode.c +++ b/fs/jfs/jfs_inode.c @@ -115,7 +115,6 @@ struct inode *ialloc(struct inode *parent, umode_t mode) } jfs_inode->mode2 |= mode; - inode->i_blksize = sb->s_blocksize; inode->i_blocks = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; jfs_inode->otime = inode->i_ctime.tv_sec; diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index e1e0a6e..f5afc12 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -257,7 +257,7 @@ static sector_t metapage_get_blocks(struct inode *inode, sector_t lblock, int rc = 0; int xflag; s64 xaddr; - sector_t file_blocks = (inode->i_size + inode->i_blksize - 1) >> + sector_t file_blocks = (inode->i_size + inode->i_sb->s_blocksize - 1) >> inode->i_blkbits; if (lblock >= file_blocks) diff --git a/fs/libfs.c b/fs/libfs.c index 2751793..8db5afb 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -383,7 +383,6 @@ int simple_fill_super(struct super_block *s, int magic, struct tree_descr *files return -ENOMEM; inode->i_mode = S_IFDIR | 0755; inode->i_uid = inode->i_gid = 0; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_op = &simple_dir_inode_operations; @@ -405,7 +404,6 @@ int simple_fill_super(struct super_block *s, int magic, struct tree_descr *files goto out; inode->i_mode = S_IFREG | files->mode; inode->i_uid = inode->i_gid = 0; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_fop = files->ops; diff --git a/fs/minix/bitmap.c b/fs/minix/bitmap.c index 4a6abc4..df6b107 100644 --- a/fs/minix/bitmap.c +++ b/fs/minix/bitmap.c @@ -254,7 +254,7 @@ struct inode * minix_new_inode(const struct inode * dir, int * error) inode->i_gid = (dir->i_mode & S_ISGID) ? dir->i_gid : current->fsgid; inode->i_ino = j; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; memset(&minix_i(inode)->u, 0, sizeof(minix_i(inode)->u)); insert_inode_hash(inode); mark_inode_dirty(inode); diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 826b9d8..c11a4b9 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -396,7 +396,7 @@ static void V1_minix_read_inode(struct inode * inode) inode->i_mtime.tv_nsec = 0; inode->i_atime.tv_nsec = 0; inode->i_ctime.tv_nsec = 0; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; for (i = 0; i < 9; i++) minix_inode->u.i1_data[i] = raw_inode->i_zone[i]; minix_set_inode(inode, old_decode_dev(raw_inode->i_zone[0])); @@ -429,7 +429,7 @@ static void V2_minix_read_inode(struct inode * inode) inode->i_mtime.tv_nsec = 0; inode->i_atime.tv_nsec = 0; inode->i_ctime.tv_nsec = 0; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; for (i = 0; i < 10; i++) minix_inode->u.i2_data[i] = raw_inode->i_zone[i]; minix_set_inode(inode, old_decode_dev(raw_inode->i_zone[0])); diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 8244710..42e3bef 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -223,7 +223,6 @@ static void ncp_set_attr(struct inode *inode, struct ncp_entry_info *nwinfo) inode->i_nlink = 1; inode->i_uid = server->m.uid; inode->i_gid = server->m.gid; - inode->i_blksize = NCP_BLOCK_SIZE; ncp_update_dates(inode, &nwinfo->i); ncp_update_inode(inode, nwinfo); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 931f52a..bc9376c 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -277,10 +277,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); - inode->i_blksize = inode->i_sb->s_blocksize; } else { inode->i_blocks = fattr->du.nfs2.blocks; - inode->i_blksize = fattr->du.nfs2.blocksize; } nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = jiffies; @@ -969,10 +967,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); - inode->i_blksize = inode->i_sb->s_blocksize; } else { inode->i_blocks = fattr->du.nfs2.blocks; - inode->i_blksize = fattr->du.nfs2.blocksize; } if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 && diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 3185212..933dbd8 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -556,8 +556,6 @@ static int ntfs_read_locked_inode(struct inode *vi) /* Setup the generic vfs inode parts now. */ - /* This is the optimal IO size (for stat), not the fs block size. */ - vi->i_blksize = PAGE_CACHE_SIZE; /* * This is for checking whether an inode has changed w.r.t. a file so * that the file can be updated if necessary (compare with f_version). @@ -1234,7 +1232,6 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi) base_ni = NTFS_I(base_vi); /* Just mirror the values from the base inode. */ - vi->i_blksize = base_vi->i_blksize; vi->i_version = base_vi->i_version; vi->i_uid = base_vi->i_uid; vi->i_gid = base_vi->i_gid; @@ -1504,7 +1501,6 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi) ni = NTFS_I(vi); base_ni = NTFS_I(base_vi); /* Just mirror the values from the base inode. */ - vi->i_blksize = base_vi->i_blksize; vi->i_version = base_vi->i_version; vi->i_uid = base_vi->i_uid; vi->i_gid = base_vi->i_gid; diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 578fb3d..584260f 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -2638,11 +2638,6 @@ mft_rec_already_initialized: } vi->i_ino = bit; /* - * This is the optimal IO size (for stat), not the fs block - * size. - */ - vi->i_blksize = PAGE_CACHE_SIZE; - /* * This is for checking whether an inode has changed w.r.t. a * file so that the file can be updated if necessary (compare * with f_version). diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c index 0ff0898..0368c64 100644 --- a/fs/ocfs2/dlm/dlmfs.c +++ b/fs/ocfs2/dlm/dlmfs.c @@ -335,7 +335,6 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; @@ -362,7 +361,6 @@ static struct inode *dlmfs_get_inode(struct inode *parent, inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 69d3db5..16e8e74 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -269,7 +269,6 @@ int ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe, inode->i_mode = le16_to_cpu(fe->i_mode); inode->i_uid = le32_to_cpu(fe->i_uid); inode->i_gid = le32_to_cpu(fe->i_gid); - inode->i_blksize = (u32)osb->s_clustersize; /* Fast symlinks will have i_size but no allocated clusters. */ if (S_ISLNK(inode->i_mode) && !fe->i_clusters) @@ -1258,8 +1257,6 @@ leave: void ocfs2_refresh_inode(struct inode *inode, struct ocfs2_dinode *fe) { - struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - spin_lock(&OCFS2_I(inode)->ip_lock); OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters); @@ -1270,7 +1267,6 @@ void ocfs2_refresh_inode(struct inode *inode, inode->i_uid = le32_to_cpu(fe->i_uid); inode->i_gid = le32_to_cpu(fe->i_gid); inode->i_mode = le16_to_cpu(fe->i_mode); - inode->i_blksize = (u32) osb->s_clustersize; if (S_ISLNK(inode->i_mode) && le32_to_cpu(fe->i_clusters) == 0) inode->i_blocks = 0; else diff --git a/fs/pipe.c b/fs/pipe.c index 2035257..f3b6f71 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -879,7 +879,6 @@ static struct inode * get_pipe_inode(void) inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - inode->i_blksize = PAGE_SIZE; return inode; diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index fddbd61..5a41db2 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -496,7 +496,6 @@ static void qnx4_read_inode(struct inode *inode) inode->i_ctime.tv_sec = le32_to_cpu(raw_inode->di_ctime); inode->i_ctime.tv_nsec = 0; inode->i_blocks = le32_to_cpu(raw_inode->di_first_xtnt.xtnt_size); - inode->i_blksize = QNX4_DIR_ENTRY_SIZE; memcpy(qnx4_inode, raw_inode, QNX4_DIR_ENTRY_SIZE); if (S_ISREG(inode->i_mode)) { diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index b967733..bc0e516 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -58,7 +58,6 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev) inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_mapping->a_ops = &ramfs_aops; inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 52f1e21..8810fda 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -17,8 +17,6 @@ #include #include -extern int reiserfs_default_io_size; /* default io size devuned in super.c */ - static int reiserfs_commit_write(struct file *f, struct page *page, unsigned from, unsigned to); static int reiserfs_prepare_write(struct file *f, struct page *page, @@ -1122,7 +1120,6 @@ static void init_inode(struct inode *inode, struct path *path) ih = PATH_PITEM_HEAD(path); copy_key(INODE_PKEY(inode), &(ih->ih_key)); - inode->i_blksize = reiserfs_default_io_size; INIT_LIST_HEAD(&(REISERFS_I(inode)->i_prealloc_list)); REISERFS_I(inode)->i_flags = 0; @@ -1877,7 +1874,6 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, } // these do not go to on-disk stat data inode->i_ino = le32_to_cpu(ih.ih_key.k_objectid); - inode->i_blksize = reiserfs_default_io_size; // store in in-core inode the key of stat data and version all // object items will have (directory items will have old offset diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c index 92cf60a..2c122ee 100644 --- a/fs/smbfs/inode.c +++ b/fs/smbfs/inode.c @@ -166,7 +166,6 @@ smb_get_inode_attr(struct inode *inode, struct smb_fattr *fattr) fattr->f_mtime = inode->i_mtime; fattr->f_ctime = inode->i_ctime; fattr->f_atime = inode->i_atime; - fattr->f_blksize= inode->i_blksize; fattr->f_blocks = inode->i_blocks; fattr->attr = SMB_I(inode)->attr; @@ -200,7 +199,6 @@ smb_set_inode_attr(struct inode *inode, struct smb_fattr *fattr) inode->i_uid = fattr->f_uid; inode->i_gid = fattr->f_gid; inode->i_ctime = fattr->f_ctime; - inode->i_blksize= fattr->f_blksize; inode->i_blocks = fattr->f_blocks; inode->i_size = fattr->f_size; inode->i_mtime = fattr->f_mtime; diff --git a/fs/smbfs/proc.c b/fs/smbfs/proc.c index c349505..40e174d 100644 --- a/fs/smbfs/proc.c +++ b/fs/smbfs/proc.c @@ -1826,7 +1826,6 @@ smb_init_dirent(struct smb_sb_info *server, struct smb_fattr *fattr) fattr->f_nlink = 1; fattr->f_uid = server->mnt->uid; fattr->f_gid = server->mnt->gid; - fattr->f_blksize = SMB_ST_BLKSIZE; fattr->f_unix = 0; } diff --git a/fs/stat.c b/fs/stat.c index 3a44dcf..60a31d5 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -32,7 +33,7 @@ void generic_fillattr(struct inode *inode, struct kstat *stat) stat->ctime = inode->i_ctime; stat->size = i_size_read(inode); stat->blocks = inode->i_blocks; - stat->blksize = inode->i_blksize; + stat->blksize = (1 << inode->i_blkbits); } EXPORT_SYMBOL(generic_fillattr); diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index fd7cd5f..e79e38d 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -125,7 +125,6 @@ struct inode * sysfs_new_inode(mode_t mode, struct sysfs_dirent * sd) { struct inode * inode = new_inode(sysfs_sb); if (inode) { - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_mapping->a_ops = &sysfs_aops; inode->i_mapping->backing_dev_info = &sysfs_backing_dev_info; diff --git a/fs/sysv/ialloc.c b/fs/sysv/ialloc.c index 9b585d1..115ab0d 100644 --- a/fs/sysv/ialloc.c +++ b/fs/sysv/ialloc.c @@ -170,7 +170,7 @@ struct inode * sysv_new_inode(const struct inode * dir, mode_t mode) inode->i_uid = current->fsuid; inode->i_ino = fs16_to_cpu(sbi, ino); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; memset(SYSV_I(inode)->i_data, 0, sizeof(SYSV_I(inode)->i_data)); SYSV_I(inode)->i_dir_start_lookup = 0; insert_inode_hash(inode); diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 58b2d22..d63c5e4 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -201,7 +201,7 @@ static void sysv_read_inode(struct inode *inode) inode->i_ctime.tv_nsec = 0; inode->i_atime.tv_nsec = 0; inode->i_mtime.tv_nsec = 0; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; si = SYSV_I(inode); for (block = 0; block < 10+1+1+1; block++) diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c index d1d3823..8206983 100644 --- a/fs/udf/ialloc.c +++ b/fs/udf/ialloc.c @@ -121,7 +121,6 @@ struct inode * udf_new_inode (struct inode *dir, int mode, int * err) UDF_I_LOCATION(inode).logicalBlockNum = block; UDF_I_LOCATION(inode).partitionReferenceNum = UDF_I_LOCATION(dir).partitionReferenceNum; inode->i_ino = udf_get_lb_pblock(sb, UDF_I_LOCATION(inode), 0); - inode->i_blksize = PAGE_SIZE; inode->i_blocks = 0; UDF_I_LENEATTR(inode) = 0; UDF_I_LENALLOC(inode) = 0; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 605f511..b223b32 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -916,8 +916,6 @@ __udf_read_inode(struct inode *inode) * i_nlink = 1 * i_op = NULL; */ - inode->i_blksize = PAGE_SIZE; - bh = udf_read_ptagged(inode->i_sb, UDF_I_LOCATION(inode), 0, &ident); if (!bh) diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index 9501dcd..2ad1259 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -255,7 +255,6 @@ cg_found: inode->i_gid = current->fsgid; inode->i_ino = cg * uspi->s_ipg + bit; - inode->i_blksize = PAGE_SIZE; /* This is the optimal IO size (for stat), not the fs block size */ inode->i_blocks = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; ufsi->i_flags = UFS_I(dir)->i_flags; diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 30c6e8a9..ee1eaa6 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -741,7 +741,6 @@ void ufs_read_inode(struct inode * inode) ufs1_read_inode(inode, ufs_inode + ufs_inotofsbo(inode->i_ino)); } - inode->i_blksize = PAGE_SIZE;/*This is the optimal IO size (for stat)*/ inode->i_version++; ufsi->i_lastfrag = (inode->i_size + uspi->s_fsize - 1) >> uspi->s_fshift; diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 4754f34..9df9ed3 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -171,7 +171,6 @@ xfs_revalidate_inode( break; } - inode->i_blksize = xfs_preferred_iosize(mp); inode->i_generation = ip->i_d.di_gen; i_size_write(inode, ip->i_d.di_size); inode->i_blocks = diff --git a/fs/xfs/linux-2.6/xfs_vnode.c b/fs/xfs/linux-2.6/xfs_vnode.c index 6628d96..553fa73 100644 --- a/fs/xfs/linux-2.6/xfs_vnode.c +++ b/fs/xfs/linux-2.6/xfs_vnode.c @@ -122,7 +122,6 @@ vn_revalidate_core( inode->i_blocks = vap->va_nblocks; inode->i_mtime = vap->va_mtime; inode->i_ctime = vap->va_ctime; - inode->i_blksize = vap->va_blocksize; if (vap->va_xflags & XFS_XFLAG_IMMUTABLE) inode->i_flags |= S_IMMUTABLE; else -- cgit v1.1 From 36b756f2b5762e6d5acba0c18e75cb5c11f11c1b Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 27 Sep 2006 01:50:50 -0700 Subject: [PATCH] reiserfs: warn about the useless nolargeio option Since the nolargeio option no longer has any effect, print a warning instead of setting a write-only variable. Signed-off-by: Adrian Bunk Cc: Jeff Mahoney Cc: Chris Mason Cc: Hans Reiser Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/reiserfs/super.c | 21 ++------------------- 1 file changed, 2 insertions(+), 19 deletions(-) (limited to 'fs') diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 1cd4d38..b40d4d6 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -723,12 +723,6 @@ static const arg_desc_t error_actions[] = { {NULL, 0, 0}, }; -int reiserfs_default_io_size = 128 * 1024; /* Default recommended I/O size is 128k. - There might be broken applications that are - confused by this. Use nolargeio mount option - to get usual i/o size = PAGE_SIZE. - */ - /* proceed only one option from a list *cur - string containing of mount options opts - array of options which are accepted opt_arg - if option is found and requires an argument and if it is specifed @@ -957,19 +951,8 @@ static int reiserfs_parse_options(struct super_block *s, char *options, /* strin } if (c == 'w') { - char *p = NULL; - int val = simple_strtoul(arg, &p, 0); - - if (*p != '\0') { - reiserfs_warning(s, - "reiserfs_parse_options: non-numeric value %s for nolargeio option", - arg); - return 0; - } - if (val) - reiserfs_default_io_size = PAGE_SIZE; - else - reiserfs_default_io_size = 128 * 1024; + reiserfs_warning(s, "reiserfs: nolargeio option is no longer supported"); + return 0; } if (c == 'j') { -- cgit v1.1 From 8b0e330b7720a206339887044fa275bf537a5264 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 27 Sep 2006 01:51:02 -0700 Subject: [PATCH] alloc_fdtable() cleanup free_fdset(NULL, ...) is legal. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/file.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/file.c b/fs/file.c index b3c6b82..8d3bfca 100644 --- a/fs/file.c +++ b/fs/file.c @@ -281,10 +281,8 @@ static struct fdtable *alloc_fdtable(int nr) out2: nfds = fdt->max_fdset; out: - if (new_openset) - free_fdset(new_openset, nfds); - if (new_execset) - free_fdset(new_execset, nfds); + free_fdset(new_openset, nfds); + free_fdset(new_execset, nfds); kfree(fdt); return NULL; } -- cgit v1.1 From b89a81712f486e4f7a606987413e387605fdeaf4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 27 Sep 2006 01:51:04 -0700 Subject: [PATCH] sysctl: Allow /proc/sys without sys_sysctl Since sys_sysctl is deprecated start allow it to be compiled out. This should catch any remaining user space code that cares, and paves the way for further sysctl cleanups. [akpm@osdl.org: If sys_sysctl() is not compiled-in, emit a warning] Signed-off-by: Eric W. Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/Kconfig | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'fs') diff --git a/fs/Kconfig b/fs/Kconfig index a270026..d311198 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -826,6 +826,25 @@ config PROC_VMCORE help Exports the dump image of crashed kernel in ELF format. +config PROC_SYSCTL + bool "Sysctl support (/proc/sys)" if EMBEDDED + depends on PROC_FS + select SYSCTL + default y + ---help--- + The sysctl interface provides a means of dynamically changing + certain kernel parameters and variables on the fly without requiring + a recompile of the kernel or reboot of the system. The primary + interface is through /proc/sys. If you say Y here a tree of + modifiable sysctl entries will be generated beneath the + /proc/sys directory. They are explained in the files + in . Note that enabling this + option will enlarge the kernel by at least 8 KB. + + As it is generally a good thing, you should say Y here unless + building a kernel for install/rescue disks or your system is very + limited in memory. + config SYSFS bool "sysfs file system support" if EMBEDDED default y -- cgit v1.1 From c18258c6f0848f97e85287f6271c511a092bb784 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 27 Sep 2006 01:51:06 -0700 Subject: [PATCH] pid: Implement transfer_pid and use it to simplify de_thread In de_thread we move pids from one process to another, a rather ugly case. The function transfer_pid makes it clear what we are doing, and makes the action atomic. This is useful we ever want to atomically traverse the process group and session lists, in a rcu safe manner. Even if the atomic properties this change should be a win as transfer_pid should be less code to execute than executing both attach_pid and detach_pid, and this should make de_thread slightly smaller as only a single function call needs to be emitted. The only downside is that the code might be slower to execute as the odds are against transfer_pid being in cache. Signed-off-by: Eric W. Biederman Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exec.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'fs') diff --git a/fs/exec.c b/fs/exec.c index 54135df..b7aa3d6 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -696,23 +696,20 @@ static int de_thread(struct task_struct *tsk) */ /* Become a process group leader with the old leader's pid. - * Note: The old leader also uses thispid until release_task + * The old leader becomes a thread of the this thread group. + * Note: The old leader also uses this pid until release_task * is called. Odd but simple and correct. */ detach_pid(current, PIDTYPE_PID); current->pid = leader->pid; attach_pid(current, PIDTYPE_PID, current->pid); - attach_pid(current, PIDTYPE_PGID, current->signal->pgrp); - attach_pid(current, PIDTYPE_SID, current->signal->session); + transfer_pid(leader, current, PIDTYPE_PGID); + transfer_pid(leader, current, PIDTYPE_SID); list_replace_rcu(&leader->tasks, ¤t->tasks); current->group_leader = current; leader->group_leader = current; - /* Reduce leader to a thread */ - detach_pid(leader, PIDTYPE_PGID); - detach_pid(leader, PIDTYPE_SID); - current->exit_signal = SIGCHLD; BUG_ON(leader->exit_state != EXIT_ZOMBIE); -- cgit v1.1 From b7b52630deca785c4fc2bf4c53500cee066786af Mon Sep 17 00:00:00 2001 From: Martin Bligh Date: Wed, 27 Sep 2006 01:51:12 -0700 Subject: [PATCH] add newline to nfs dprintk Add missing \n to dprintk Signed-off-by: Martin Bligh Acked-by: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/lockd/clntlock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index 52774fe..f95cc3f 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -160,7 +160,7 @@ static void nlmclnt_prepare_reclaim(struct nlm_host *host) */ list_splice_init(&host->h_granted, &host->h_reclaim); - dprintk("NLM: reclaiming locks for host %s", host->h_name); + dprintk("NLM: reclaiming locks for host %s\n", host->h_name); } static void nlmclnt_finish_reclaim(struct nlm_host *host) -- cgit v1.1 From 66f37509fc7191df468a8d183374f48b13bacb73 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 27 Sep 2006 01:51:13 -0700 Subject: [PATCH] fs/nfs/: make code static Signed-off-by: Adrian Bunk Acked-by: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nfs/namespace.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 77b0068..6040864 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -26,6 +26,11 @@ LIST_HEAD(nfs_automount_list); static DECLARE_WORK(nfs_automount_task, nfs_expire_automounts, &nfs_automount_list); int nfs_mountpoint_expiry_timeout = 500 * HZ; +static struct vfsmount *nfs_do_submount(const struct vfsmount *mnt_parent, + const struct dentry *dentry, + struct nfs_fh *fh, + struct nfs_fattr *fattr); + /* * nfs_path - reconstruct the path given an arbitrary dentry * @base - arbitrary string to prepend to the path @@ -209,9 +214,10 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, * @fattr - attributes for new root inode * */ -struct vfsmount *nfs_do_submount(const struct vfsmount *mnt_parent, - const struct dentry *dentry, struct nfs_fh *fh, - struct nfs_fattr *fattr) +static struct vfsmount *nfs_do_submount(const struct vfsmount *mnt_parent, + const struct dentry *dentry, + struct nfs_fh *fh, + struct nfs_fattr *fattr) { struct nfs_clone_mount mountdata = { .sb = mnt_parent->mnt_sb, -- cgit v1.1 From aafe6c2a2b6bce5a3a4913ce5c07e85ea143144d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 27 Sep 2006 01:51:13 -0700 Subject: [PATCH] de_thread: Use tsk not current Ingo Oeser pointed out that because current expands to an inline function it is more space efficient and somewhat faster to simply keep a cached copy of current in another variable. This patch implements that for the de_thread function. (akpm: saves nearly 100 bytes of text on x86) Signed-off-by: Eric W. Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exec.c | 46 +++++++++++++++++++++++----------------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'fs') diff --git a/fs/exec.c b/fs/exec.c index b7aa3d6..97df6e0 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -595,7 +595,7 @@ static int de_thread(struct task_struct *tsk) if (!newsighand) return -ENOMEM; - if (thread_group_empty(current)) + if (thread_group_empty(tsk)) goto no_thread_group; /* @@ -620,17 +620,17 @@ static int de_thread(struct task_struct *tsk) * Reparenting needs write_lock on tasklist_lock, * so it is safe to do it under read_lock. */ - if (unlikely(current->group_leader == child_reaper)) - child_reaper = current; + if (unlikely(tsk->group_leader == child_reaper)) + child_reaper = tsk; - zap_other_threads(current); + zap_other_threads(tsk); read_unlock(&tasklist_lock); /* * Account for the thread group leader hanging around: */ count = 1; - if (!thread_group_leader(current)) { + if (!thread_group_leader(tsk)) { count = 2; /* * The SIGALRM timer survives the exec, but needs to point @@ -639,14 +639,14 @@ static int de_thread(struct task_struct *tsk) * synchronize with any firing (by calling del_timer_sync) * before we can safely let the old group leader die. */ - sig->tsk = current; + sig->tsk = tsk; spin_unlock_irq(lock); if (hrtimer_cancel(&sig->real_timer)) hrtimer_restart(&sig->real_timer); spin_lock_irq(lock); } while (atomic_read(&sig->count) > count) { - sig->group_exit_task = current; + sig->group_exit_task = tsk; sig->notify_count = count; __set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock_irq(lock); @@ -662,13 +662,13 @@ static int de_thread(struct task_struct *tsk) * do is to wait for the thread group leader to become inactive, * and to assume its PID: */ - if (!thread_group_leader(current)) { + if (!thread_group_leader(tsk)) { /* * Wait for the thread group leader to be a zombie. * It should already be zombie at this point, most * of the time. */ - leader = current->group_leader; + leader = tsk->group_leader; while (leader->exit_state != EXIT_ZOMBIE) yield(); @@ -682,12 +682,12 @@ static int de_thread(struct task_struct *tsk) * When we take on its identity by switching to its PID, we * also take its birthdate (always earlier than our own). */ - current->start_time = leader->start_time; + tsk->start_time = leader->start_time; write_lock_irq(&tasklist_lock); - BUG_ON(leader->tgid != current->tgid); - BUG_ON(current->pid == current->tgid); + BUG_ON(leader->tgid != tsk->tgid); + BUG_ON(tsk->pid == tsk->tgid); /* * An exec() starts a new thread group with the * TGID of the previous thread group. Rehash the @@ -700,17 +700,17 @@ static int de_thread(struct task_struct *tsk) * Note: The old leader also uses this pid until release_task * is called. Odd but simple and correct. */ - detach_pid(current, PIDTYPE_PID); - current->pid = leader->pid; - attach_pid(current, PIDTYPE_PID, current->pid); - transfer_pid(leader, current, PIDTYPE_PGID); - transfer_pid(leader, current, PIDTYPE_SID); - list_replace_rcu(&leader->tasks, ¤t->tasks); + detach_pid(tsk, PIDTYPE_PID); + tsk->pid = leader->pid; + attach_pid(tsk, PIDTYPE_PID, tsk->pid); + transfer_pid(leader, tsk, PIDTYPE_PGID); + transfer_pid(leader, tsk, PIDTYPE_SID); + list_replace_rcu(&leader->tasks, &tsk->tasks); - current->group_leader = current; - leader->group_leader = current; + tsk->group_leader = tsk; + leader->group_leader = tsk; - current->exit_signal = SIGCHLD; + tsk->exit_signal = SIGCHLD; BUG_ON(leader->exit_state != EXIT_ZOMBIE); leader->exit_state = EXIT_DEAD; @@ -750,7 +750,7 @@ no_thread_group: spin_lock(&oldsighand->siglock); spin_lock_nested(&newsighand->siglock, SINGLE_DEPTH_NESTING); - rcu_assign_pointer(current->sighand, newsighand); + rcu_assign_pointer(tsk->sighand, newsighand); recalc_sigpending(); spin_unlock(&newsighand->siglock); @@ -761,7 +761,7 @@ no_thread_group: kmem_cache_free(sighand_cachep, oldsighand); } - BUG_ON(!thread_group_leader(current)); + BUG_ON(!thread_group_leader(tsk)); return 0; } -- cgit v1.1